diff --git a/.gitattributes b/.gitattributes index c7e0c4779df108cca06ce19a3019c16992a5df0d..86a861a820f7108ce39f6eb66320bb5e8b9e3a06 100644 --- a/.gitattributes +++ b/.gitattributes @@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text git.diff filter=lfs diff=lfs merge=lfs -text replay.mp4 filter=lfs diff=lfs merge=lfs -text +sf_log.txt filter=lfs diff=lfs merge=lfs -text diff --git a/.summary/0/events.out.tfevents.1701181561.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1701181561.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..8436b6b9223a0d29818234e602cf0b1c2e7c5fcf --- /dev/null +++ b/.summary/0/events.out.tfevents.1701181561.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab12a4387d7e53e2ba4bf164d20a73c71831ae8951ddb8f35b6ebfd1ffd5d5e3 +size 9231042 diff --git a/.summary/0/events.out.tfevents.1701275508.rhmmedcatt-proliant-ml350-gen10 b/.summary/0/events.out.tfevents.1701275508.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..abb75df0bf942c5ce5f99a430b9f2d6f39b8adb2 --- /dev/null +++ b/.summary/0/events.out.tfevents.1701275508.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a9091226258887182224dfee3b60c7bcfab35a1a4840dcd3b7156b592a5a3f +size 62301595 diff --git a/.summary/1/events.out.tfevents.1701181561.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1701181561.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..29798dcdf2391fe6f1aaed7e3681d01f7aff13da --- /dev/null +++ b/.summary/1/events.out.tfevents.1701181561.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b82d60102fa4e5ba5c05f32d90d8ac59a5b68b8a3c31958b96953fc07890c06 +size 4851267 diff --git a/.summary/1/events.out.tfevents.1701275508.rhmmedcatt-proliant-ml350-gen10 b/.summary/1/events.out.tfevents.1701275508.rhmmedcatt-proliant-ml350-gen10 new file mode 100644 index 0000000000000000000000000000000000000000..2155cee3f4744ecd5c11a8a952c4ffbbb657a45f --- /dev/null +++ b/.summary/1/events.out.tfevents.1701275508.rhmmedcatt-proliant-ml350-gen10 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010bb248f523240e82c71b54f9fb1831df6beb8ccb2ae1c0dca1d816a677b65b +size 32377807 diff --git a/README.md b/README.md index 3394a0045bb52ad4a2ff6a769e136c3ded3a386d..68f85c18e27b5a48dea7c0e50f14236cd3744f4a 100644 --- a/README.md +++ b/README.md @@ -15,7 +15,7 @@ model-index: type: atari_skiing metrics: - type: mean_reward - value: -8894.80 +/- 1235.78 + value: -8400.60 +/- 225.55 name: mean_reward verified: false --- diff --git a/checkpoint_p0/checkpoint_001952880_499941376.pth b/checkpoint_p0/checkpoint_001952880_499941376.pth new file mode 100644 index 0000000000000000000000000000000000000000..2513e287095ca9faaecf7316726a47fb6134688c --- /dev/null +++ b/checkpoint_p0/checkpoint_001952880_499941376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45a85c5c61460d35c942f6bb15f9c69338ebb0accc97b8d7100c2f00346709d5 +size 20703939 diff --git a/checkpoint_p0/checkpoint_001953168_500015104.pth b/checkpoint_p0/checkpoint_001953168_500015104.pth new file mode 100644 index 0000000000000000000000000000000000000000..49c22cca3e21f03f9eaa249f64f81e283aaa2f0e --- /dev/null +++ b/checkpoint_p0/checkpoint_001953168_500015104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2deca57dafdef501048642782fb9d611e647e5af5a63051efed2c65b1315fb0 +size 20703939 diff --git a/checkpoint_p0/milestones/checkpoint_000419040_107274240.pth b/checkpoint_p0/milestones/checkpoint_000419040_107274240.pth new file mode 100644 index 0000000000000000000000000000000000000000..8f9a096da87d24cc420c1cd5ca512cf0cf35160a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000419040_107274240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cad3dd83359c62f7ed88127a8b7b2d8f439bb7bcf672a99e6d2b80f2b3cb67c +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000431424_110444544.pth b/checkpoint_p0/milestones/checkpoint_000431424_110444544.pth new file mode 100644 index 0000000000000000000000000000000000000000..278f07043d3222167a9a01ec4f3b0fb71e61c349 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000431424_110444544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a283ec5b1b824a6bdc444c9b64945f471b418ac2ed70c9dfad376f9b3c02a84 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000443808_113614848.pth b/checkpoint_p0/milestones/checkpoint_000443808_113614848.pth new file mode 100644 index 0000000000000000000000000000000000000000..5fc8e69494f64c10e60db4df524da3e4576c7cf3 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000443808_113614848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fe28bddc367c00a46ccd15c3c4598e61b7658c8a41cdee75e06e61ead5f0761 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000456320_116817920.pth b/checkpoint_p0/milestones/checkpoint_000456320_116817920.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f3d4fa2177ca0f1e84bf896c5f569323517e65e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000456320_116817920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1250d2307e6f43ee5e5bcd3f10d44c2ae7e6b678e693ce7a66f36eb561863574 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000468768_120004608.pth b/checkpoint_p0/milestones/checkpoint_000468768_120004608.pth new file mode 100644 index 0000000000000000000000000000000000000000..2ed05859d939139c91f9ca81d649938e256da66e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000468768_120004608.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d14ad3a416dcfb85d9aa5c71f7de2ab7f1e39cf047b2cd5ea8014dc78de6363c +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000481304_123215872.pth b/checkpoint_p0/milestones/checkpoint_000481304_123215872.pth new file mode 100644 index 0000000000000000000000000000000000000000..4473c4e182004bec00f677f1cbc8edaa9509fcc9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000481304_123215872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ce8e7395fe06f8a0d04f0b75fef3e1ec3c85d9cb1b2fda880129061027c7d36 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000493912_126443520.pth b/checkpoint_p0/milestones/checkpoint_000493912_126443520.pth new file mode 100644 index 0000000000000000000000000000000000000000..473ab23c69d5e52d38dd4602e7e44e8a640d4267 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000493912_126443520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d0d214244ab0383f915e86e941083ee674561212da46d4363471adb0598ef84 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000506424_129646592.pth b/checkpoint_p0/milestones/checkpoint_000506424_129646592.pth new file mode 100644 index 0000000000000000000000000000000000000000..13f33612ca67900b35bd9a76069dde9fa1ac491f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000506424_129646592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96761b9b1eca2d2e9162dbef66b555c598787a0446aa29420a34290042450711 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000518872_132833280.pth b/checkpoint_p0/milestones/checkpoint_000518872_132833280.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c2c3b3c2d263f28f81557d333f197d0c3c9584c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000518872_132833280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3e4dd87682a39a696389663fe3f9972482260f569e32ffee92260336e02331 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000531384_136036352.pth b/checkpoint_p0/milestones/checkpoint_000531384_136036352.pth new file mode 100644 index 0000000000000000000000000000000000000000..54fd96aac462d060a9deeda4f89716e6a0a795de --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000531384_136036352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6384661f162f059235244a80a2e7dbef36f6ccefd36d6b73a5e403db45402da4 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000543960_139255808.pth b/checkpoint_p0/milestones/checkpoint_000543960_139255808.pth new file mode 100644 index 0000000000000000000000000000000000000000..73f45d0f6d68b729f5adf8b3dfa921df9e736f93 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000543960_139255808.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:849da75e1f1339dfcdbfaa9740b58237d19d115a8deed18f0507d993dbc12a25 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000556504_142467072.pth b/checkpoint_p0/milestones/checkpoint_000556504_142467072.pth new file mode 100644 index 0000000000000000000000000000000000000000..7770d6f795c989a52fdc5950c944a43384c0a707 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000556504_142467072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bfcc04553fc599440441119d8bc099224eecffcee8a4c2cc7e06c831e75b778 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000569048_145678336.pth b/checkpoint_p0/milestones/checkpoint_000569048_145678336.pth new file mode 100644 index 0000000000000000000000000000000000000000..1192970ba1191db3c7e930e904e19427b37dca6a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000569048_145678336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e4f4b1cef475a7553626b36a32806a82c3eeeefbb2ba7e8c2989d0630cd5a4b +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000581560_148881408.pth b/checkpoint_p0/milestones/checkpoint_000581560_148881408.pth new file mode 100644 index 0000000000000000000000000000000000000000..09e7a5d23162093cd0c260e5395f0d0bf0eb1d2e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000581560_148881408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2d9e0ee930bf9199913141d80ac1b50fe0a776cf2b47c812bfa9b600bd24258 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000594104_152092672.pth b/checkpoint_p0/milestones/checkpoint_000594104_152092672.pth new file mode 100644 index 0000000000000000000000000000000000000000..9cc11de10154718d857cfc50aef5412e08d315e7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000594104_152092672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b8f17e98cb945804bb3aeeb1dec46c112865421f8fa1eab6773200fa00098e5 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000616536_157835264.pth b/checkpoint_p0/milestones/checkpoint_000616536_157835264.pth new file mode 100644 index 0000000000000000000000000000000000000000..f109c6a62c9212ce4ea1fb12e2c4afaae0067530 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000616536_157835264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae923c25f636d25228c098f53cba13193e9a996982e3641123ec6bf2c00a7e17 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000629176_161071104.pth b/checkpoint_p0/milestones/checkpoint_000629176_161071104.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4ad7d96a5275e9c11b3994455a2b0fb2f6130f5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000629176_161071104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a93090362b61f843ed7edc0e92f88c76b1b2d73d1aedf43da2f8cd6531b857f +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000641880_164323328.pth b/checkpoint_p0/milestones/checkpoint_000641880_164323328.pth new file mode 100644 index 0000000000000000000000000000000000000000..c6882e10f33144100e0cdbdad1cf7eb11088e4fc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000641880_164323328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a57706d79922226514b973c51c04a4bcba44dfacda8becf3e108a552ebbac0f +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000654616_167583744.pth b/checkpoint_p0/milestones/checkpoint_000654616_167583744.pth new file mode 100644 index 0000000000000000000000000000000000000000..e40e4156e7545208c3dc4a215b4eb6ab535f9172 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000654616_167583744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:092b0c6d9d6963a168b67a367e1cb029bc5be65b7b1b39199a68e9a6db547d02 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000667288_170827776.pth b/checkpoint_p0/milestones/checkpoint_000667288_170827776.pth new file mode 100644 index 0000000000000000000000000000000000000000..96dc3f5cb71c9dabc277c25381e16f47000bf2b4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000667288_170827776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53f0decfb945a277e8a3044107fea2a42d93db5fc6a59f8593f14d6fe593b602 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000680088_174104576.pth b/checkpoint_p0/milestones/checkpoint_000680088_174104576.pth new file mode 100644 index 0000000000000000000000000000000000000000..bbd97b4c359e90f1ae646c5cc18d65db2756052f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000680088_174104576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65e5d4e4e1c6a4180dd06d0767069cdbbea3c7072c9db6b152cdc9e25550bfe8 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000692824_177364992.pth b/checkpoint_p0/milestones/checkpoint_000692824_177364992.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3170e48925089a78650ecba55abb90aa4257f91 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000692824_177364992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:237ac12152fba705247e44381f4af2353a5dfbe9d7e88ee228d6d2e04debd34e +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000705560_180625408.pth b/checkpoint_p0/milestones/checkpoint_000705560_180625408.pth new file mode 100644 index 0000000000000000000000000000000000000000..afb51629739363779034cfb59d7d399fd7f4a040 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000705560_180625408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c639ad4e80f67935e7b122f6c211f04370a4478e7dea2c6b82be4daca6791950 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000718328_183894016.pth b/checkpoint_p0/milestones/checkpoint_000718328_183894016.pth new file mode 100644 index 0000000000000000000000000000000000000000..8b46d008f989f92eb276fde4b1bb1600946eae9b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000718328_183894016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f88a65c80333de7e36a116d9b5834b82266ad2331a35e3709ec79130a18ac3 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000731032_187146240.pth b/checkpoint_p0/milestones/checkpoint_000731032_187146240.pth new file mode 100644 index 0000000000000000000000000000000000000000..382f9cae0a0bbd47183ce3d0b79996932131f260 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000731032_187146240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4f6d6ccfd56e8ea10edb81b9fdffa42aa034396fd6e45d85e7ddbe1b329d623 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000743704_190390272.pth b/checkpoint_p0/milestones/checkpoint_000743704_190390272.pth new file mode 100644 index 0000000000000000000000000000000000000000..4859aa2a3c666156a575b130f3e46c2045e2597e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000743704_190390272.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e6fd06abcd7e2da5568ec6e59f994e5052cb5665b3bebc71dbde0091870f164 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000756472_193658880.pth b/checkpoint_p0/milestones/checkpoint_000756472_193658880.pth new file mode 100644 index 0000000000000000000000000000000000000000..d115eb9f60c5f047d740c1708632ec9b6737d21e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000756472_193658880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7074742761c9da0a9fe55c552df010a57630b9f9ed3d8129d9961259384c4fb7 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000769144_196902912.pth b/checkpoint_p0/milestones/checkpoint_000769144_196902912.pth new file mode 100644 index 0000000000000000000000000000000000000000..ade598422b9bad2cfbb51d3c5904a292b44d85f8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000769144_196902912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b62f501f0ebb006b82f1c9472430a2ae5053684d9fe252545782eb5129b2eba +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000781784_200138752.pth b/checkpoint_p0/milestones/checkpoint_000781784_200138752.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d9f7afc92c941296b0cfb4a9b9268eae5be2ff4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000781784_200138752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8efaa9b4e5b02ca8c8071c5964ee153175ba894f8862015c4f17b05cf0e6e703 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000794520_203399168.pth b/checkpoint_p0/milestones/checkpoint_000794520_203399168.pth new file mode 100644 index 0000000000000000000000000000000000000000..55430bdea9c5515ab4b9c04129a36a193416f79c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000794520_203399168.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b10b8c0655de3d4abde81a8304fa4207c031b5de0c5ee005c458509f25ddda9c +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000807192_206643200.pth b/checkpoint_p0/milestones/checkpoint_000807192_206643200.pth new file mode 100644 index 0000000000000000000000000000000000000000..dc727572fc3671ff9d90f0c13e79045a7779e47a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000807192_206643200.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed7491d54dd1e9c8eb90ef18a96de908c43db9e00d82e02d79a598a938d64be0 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000819864_209887232.pth b/checkpoint_p0/milestones/checkpoint_000819864_209887232.pth new file mode 100644 index 0000000000000000000000000000000000000000..ca3992fb44919f1ee6acff0d3f6553290d60cbbd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000819864_209887232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07240e731094f727f8eac99f6ca79d65c1f4e4448ca99eaadbfc6347b9cac1aa +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000832568_213139456.pth b/checkpoint_p0/milestones/checkpoint_000832568_213139456.pth new file mode 100644 index 0000000000000000000000000000000000000000..b79961a2d969dfde7f6bdca264a450ef1f541af0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000832568_213139456.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59b9ae92c4243175eb1c18e985e9338b00aa769e8d10544a054f53d4d3abf4c6 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000845336_216408064.pth b/checkpoint_p0/milestones/checkpoint_000845336_216408064.pth new file mode 100644 index 0000000000000000000000000000000000000000..9815d052429ae49f72edc4d4f26fd547fdcb4ed0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000845336_216408064.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81893104ae7c40e5c86b7b5fb7a78457feb13796d59d5c762b7a42d24c7f0f82 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000858032_219660288.pth b/checkpoint_p0/milestones/checkpoint_000858032_219660288.pth new file mode 100644 index 0000000000000000000000000000000000000000..74865e6eaa5eb9d43f7ceee001bb8430867145f0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000858032_219660288.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feed2f6dd8a65d0788308d7f915f6e2bf0f2264af52921ef90363bba51d6f6e4 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000870736_222912512.pth b/checkpoint_p0/milestones/checkpoint_000870736_222912512.pth new file mode 100644 index 0000000000000000000000000000000000000000..b859b688794a95c0ffb775f3b94ccba284df831a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000870736_222912512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a152dab8bf81c5b0a32591713311f4e20ff382757c5a281dc0e2173cb8e9dd +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000883472_226172928.pth b/checkpoint_p0/milestones/checkpoint_000883472_226172928.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f09db469295a06f73e87887d89735d4bfd9538d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000883472_226172928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3dad38f76edcfc14997236bdae0c6cfeeacd5733b07921972e60484283e1b6f3 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000895856_229343232.pth b/checkpoint_p0/milestones/checkpoint_000895856_229343232.pth new file mode 100644 index 0000000000000000000000000000000000000000..073b4b0c7a0da97e3d622234d3688645ac6a6b4b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000895856_229343232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1febeab01da3fe2edd5c1fc33c375e58a72ec8fa6ce083c0a2d3d615f9a84c20 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000908592_232603648.pth b/checkpoint_p0/milestones/checkpoint_000908592_232603648.pth new file mode 100644 index 0000000000000000000000000000000000000000..3ca89fcfcc7a069b9ae5d67688c4241f33c8d683 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000908592_232603648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d6f865da6574369679738972ee6fb6653e46bea8dcc7a20a31fed0a08a788e8 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000921424_235888640.pth b/checkpoint_p0/milestones/checkpoint_000921424_235888640.pth new file mode 100644 index 0000000000000000000000000000000000000000..f3f8943951b431ed7881171019b6e3330ffcbf3c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000921424_235888640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d340f9c2bf0c49b3e6b5d645f571a55e26c71f59f7fb1b253cd0dc767b8b6737 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000934128_239140864.pth b/checkpoint_p0/milestones/checkpoint_000934128_239140864.pth new file mode 100644 index 0000000000000000000000000000000000000000..22a3edd58f93157a2e3aaaa74b15d524ef8c19b6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000934128_239140864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a0630ccff0eb4114d356c4b0ea4918dc60cc16a0f409987c2fcf5da68f15b9e +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000946864_242401280.pth b/checkpoint_p0/milestones/checkpoint_000946864_242401280.pth new file mode 100644 index 0000000000000000000000000000000000000000..1df1d1566324d6b8c706abacf36c1304abb67c3b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000946864_242401280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17e36e42b54c8e8258475e33dff405942db1928938d3165b49b68744a94633f2 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000959568_245653504.pth b/checkpoint_p0/milestones/checkpoint_000959568_245653504.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4f965f334028ce65750432296b20264f6e7b601 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000959568_245653504.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a6804daeca9273af1b57638c560c23acf1499d34615de37ca22a7ebbd1a308f +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000972272_248905728.pth b/checkpoint_p0/milestones/checkpoint_000972272_248905728.pth new file mode 100644 index 0000000000000000000000000000000000000000..41512a46e8ea58b29e79c68ca62551afb3a3db52 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000972272_248905728.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcd28e93626d3a35104774472b9654f3e6f225901ca6ded216741ddd0c435281 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000984976_252157952.pth b/checkpoint_p0/milestones/checkpoint_000984976_252157952.pth new file mode 100644 index 0000000000000000000000000000000000000000..bf1ac98d58f910bef1de684ad2219b3d9d0894f6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000984976_252157952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b661b995ed19edf46d6376ad6a2c17f19865071f33e08f37df73b036a8c538a0 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_000997648_255401984.pth b/checkpoint_p0/milestones/checkpoint_000997648_255401984.pth new file mode 100644 index 0000000000000000000000000000000000000000..5587bfb1f4cb33c9fd01bccd6f1afeade39bd459 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_000997648_255401984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ab4831c4f3175f7a969db7cb2709ebdb1c83c9f82d692a9e8ac011dc103f987 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001010384_258662400.pth b/checkpoint_p0/milestones/checkpoint_001010384_258662400.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad2cb85e25b24a034d785a4775726d6f247fcbb0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001010384_258662400.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de625009009c0163202260a11b8a4897be6e22541f7f19270066929a6f05953e +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001023088_261914624.pth b/checkpoint_p0/milestones/checkpoint_001023088_261914624.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c973c79b16340177af6d1ecf97aca41aff305b6 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001023088_261914624.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac56e71db243c98b7e0dcedc4130e79657510ab2097d1e6cce317c6d4228d066 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001035792_265166848.pth b/checkpoint_p0/milestones/checkpoint_001035792_265166848.pth new file mode 100644 index 0000000000000000000000000000000000000000..50e1bff23f190a928ae97f0e420647c3417b486b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001035792_265166848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23744dbd8f5464d367ef227e7ef714a534b153a49006e558d51a47be922ddfc4 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001048464_268410880.pth b/checkpoint_p0/milestones/checkpoint_001048464_268410880.pth new file mode 100644 index 0000000000000000000000000000000000000000..4dfcd643f7b1e4a360650f6a9b20c7e773988230 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001048464_268410880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a42ed8b2b2ac41b3261bb95d6fe29f789155d3ceea9be10d4de62a4d8d7fea6d +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001061104_271646720.pth b/checkpoint_p0/milestones/checkpoint_001061104_271646720.pth new file mode 100644 index 0000000000000000000000000000000000000000..1de7d455548d421ed9ab38ee84cb1c72e5aaaca7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001061104_271646720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:151bc6aaab966e145f489aaecbc330f669d070ef81bd49f9dbf99d6b91c1a720 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001073808_274898944.pth b/checkpoint_p0/milestones/checkpoint_001073808_274898944.pth new file mode 100644 index 0000000000000000000000000000000000000000..2323f121f9239c0bc09f6cfd2cddeb5f5db8f7a5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001073808_274898944.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e48f3eee95385624716525445ab1c8ec000a71253617e7bbc341be9d89432dd +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001086544_278159360.pth b/checkpoint_p0/milestones/checkpoint_001086544_278159360.pth new file mode 100644 index 0000000000000000000000000000000000000000..0949491bb72c18c472e9be32f7358908136664b1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001086544_278159360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da3b0a6cff081c7cd13ad4a2ec6492249bc199e3902588dfac2d3eb845af4ce4 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001099248_281411584.pth b/checkpoint_p0/milestones/checkpoint_001099248_281411584.pth new file mode 100644 index 0000000000000000000000000000000000000000..a18bf3aa325bbcb08210ae90c6f50912f4457488 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001099248_281411584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d32032da50020b44f4a93c5b5415b701d0d53d5f9950c87c72a66e47d05313ab +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001111920_284655616.pth b/checkpoint_p0/milestones/checkpoint_001111920_284655616.pth new file mode 100644 index 0000000000000000000000000000000000000000..be525b0c662b9411cf01a251003db5c0196b51fe --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001111920_284655616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:219df5e1be3fec176d329efd74ce77e085997081f3ce287534906f49cb843011 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001124720_287932416.pth b/checkpoint_p0/milestones/checkpoint_001124720_287932416.pth new file mode 100644 index 0000000000000000000000000000000000000000..501788c27e5b6c9b929f0b2bf54d61c36126d432 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001124720_287932416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56f9008cb66f67c8d87740c8bec9d27a58edb9c31e6d27ea4304958649e39450 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001137392_291176448.pth b/checkpoint_p0/milestones/checkpoint_001137392_291176448.pth new file mode 100644 index 0000000000000000000000000000000000000000..42801bc2d5dc5220d377b2eabff6b408d88badf0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001137392_291176448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63243fd9fbda76ee3f8739acda6a384ba35f4635d6891e45b465d83040065385 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001150096_294428672.pth b/checkpoint_p0/milestones/checkpoint_001150096_294428672.pth new file mode 100644 index 0000000000000000000000000000000000000000..9abdc412565182cbfadf1ff45f3564c7e8e9959a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001150096_294428672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16b10f42f74dd02d9da46b2899ef3492fe37bab4f26158ec4ce6b030f11cda70 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001162800_297680896.pth b/checkpoint_p0/milestones/checkpoint_001162800_297680896.pth new file mode 100644 index 0000000000000000000000000000000000000000..2b65cff4b18da0b74404937b74d942b15a7c96c8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001162800_297680896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54b4bbbc24bb5d0a9d4539c9ee0006d6011ca2ad2c7d0ea4ac644df94ac6508a +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001175472_300924928.pth b/checkpoint_p0/milestones/checkpoint_001175472_300924928.pth new file mode 100644 index 0000000000000000000000000000000000000000..75caa1f87342903ca06a8a28714e356696d5c615 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001175472_300924928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0d1481169e80d540a9562c6d46f0c09036159772c838963fc3f3d001bfadcab +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001188112_304160768.pth b/checkpoint_p0/milestones/checkpoint_001188112_304160768.pth new file mode 100644 index 0000000000000000000000000000000000000000..e70b31ca98d2c29fbcec0105337802e8b7934bbc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001188112_304160768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd8023f595f72f88a209d60827b205aec82495b8ae5b54bfd1e5dcbf17134e28 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001200720_307388416.pth b/checkpoint_p0/milestones/checkpoint_001200720_307388416.pth new file mode 100644 index 0000000000000000000000000000000000000000..bcce8dc4f188f8a4d1c816f55b71cda0681da53c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001200720_307388416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fda70b439859d6fedaca1fb803849951c00b39ed2e0e1ef1e7a5f50a5671ed6e +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001213424_310640640.pth b/checkpoint_p0/milestones/checkpoint_001213424_310640640.pth new file mode 100644 index 0000000000000000000000000000000000000000..1eb9cdeb7caf6499ee3d3e1a6d2ccdc9943115fd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001213424_310640640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25463bd26f4a96ad0d95ed7dddfde30668b04b6148085b342a2125b6e87cb613 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001226160_313901056.pth b/checkpoint_p0/milestones/checkpoint_001226160_313901056.pth new file mode 100644 index 0000000000000000000000000000000000000000..bc5923f6e457edde5aac0a62b218b800a3f63b07 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001226160_313901056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f11ed74c886d1a6530248cb0ab260aebaa6392017c8c4a2fd31c5343b08b4e6c +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001238832_317145088.pth b/checkpoint_p0/milestones/checkpoint_001238832_317145088.pth new file mode 100644 index 0000000000000000000000000000000000000000..1941e0d235963b23b87a7dabb70fee9a15da874c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001238832_317145088.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4d4da43653a13b7b12adce47d8b7ab3f0064b8a121520894cf8ab4f44ca264f +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001251472_320380928.pth b/checkpoint_p0/milestones/checkpoint_001251472_320380928.pth new file mode 100644 index 0000000000000000000000000000000000000000..6c93e90c1f5ae2205c5ad4e56a18ccfe5b01c012 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001251472_320380928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ca9d57b35367f926c0204181db50836b39a26e702b6195b34dd93b3ebcd0b8f +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001264112_323616768.pth b/checkpoint_p0/milestones/checkpoint_001264112_323616768.pth new file mode 100644 index 0000000000000000000000000000000000000000..fd31824503e528ae80b2b6080c09202d4d7326e7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001264112_323616768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dcd0ae8cec7337693ec9cdccc0faf850a47c94b3a1aca07d5b3d468fced1d82 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001276816_326868992.pth b/checkpoint_p0/milestones/checkpoint_001276816_326868992.pth new file mode 100644 index 0000000000000000000000000000000000000000..e109d9e9a200b5e25871553c74f03def3e3de840 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001276816_326868992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9150acfd8157d70efa10060fef767d9a161636244e20d183218e5bcf2e1f28f7 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001289520_330121216.pth b/checkpoint_p0/milestones/checkpoint_001289520_330121216.pth new file mode 100644 index 0000000000000000000000000000000000000000..052c9e137feaef0b5ce6df85a90bf25c0a650443 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001289520_330121216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:815816b02fefafd7b2a8ae70fc2213a2892a3b7649d6fae464e8c57889a6ac5f +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001302160_333357056.pth b/checkpoint_p0/milestones/checkpoint_001302160_333357056.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc2ed6b3f80df6cca507abaafbcc4f5eaa4d0bbe --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001302160_333357056.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7595867af46c9e150d37b80373b9da0b58f92796626e0350f97483211ea75734 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001314736_336576512.pth b/checkpoint_p0/milestones/checkpoint_001314736_336576512.pth new file mode 100644 index 0000000000000000000000000000000000000000..6eb4085367b76d5b98167dd0e4cfa666eb8450d0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001314736_336576512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:384659cbd38083a443de1120be62093a7a8cd557d3c343aa066cf93e5f7c0983 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001327376_339812352.pth b/checkpoint_p0/milestones/checkpoint_001327376_339812352.pth new file mode 100644 index 0000000000000000000000000000000000000000..7948f6e5a2f32aa06746c38c95391eae3cf833f8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001327376_339812352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0285a74e54a1ec1f8efb43674270b7645cf975461944089396b98dda4a3d18a6 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001339920_343023616.pth b/checkpoint_p0/milestones/checkpoint_001339920_343023616.pth new file mode 100644 index 0000000000000000000000000000000000000000..1a03dc86b9fd48109351f93a5a6bf1d131dafab9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001339920_343023616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04bbd627d39f59bc730ad29ddf9d194b64d4f1b07726434aac109051c0a4bfd +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001352592_346267648.pth b/checkpoint_p0/milestones/checkpoint_001352592_346267648.pth new file mode 100644 index 0000000000000000000000000000000000000000..aaba29e9257edbe27797ab25bcf5c4a34a1a6464 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001352592_346267648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d02f78a366f9b989f0a139841ffa21a8c3f122da8150895233f0df6f6312cfb +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001365296_349519872.pth b/checkpoint_p0/milestones/checkpoint_001365296_349519872.pth new file mode 100644 index 0000000000000000000000000000000000000000..30424bde847d4ba246d770d84ba811909af63f90 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001365296_349519872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0bd738fdb9059bb7308b2368bea162d3695d847bfcf0c274ea0419128bc31ac +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001378000_352772096.pth b/checkpoint_p0/milestones/checkpoint_001378000_352772096.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed6d2832435b94bfa1e7a3fd9c64bf2e14431d80 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001378000_352772096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d498579dd5a4625463c8571bf91364779f67a06193228e373b5afb2aba083543 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001389616_355745792.pth b/checkpoint_p0/milestones/checkpoint_001389616_355745792.pth new file mode 100644 index 0000000000000000000000000000000000000000..90c5ef862fc1012718e83d5408a6d0c72d6f64dd --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001389616_355745792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a442c9254fa6469954778c744aecd79faa346754ff507bdbbae5de625bb6364 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001400048_358416384.pth b/checkpoint_p0/milestones/checkpoint_001400048_358416384.pth new file mode 100644 index 0000000000000000000000000000000000000000..02e0552b8686ebfdc0543e57227ada5bd684b25d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001400048_358416384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df7b05d256f515b5c2d6b0d6a86ce7a9ce5c30786b18eb48e6d4715b8851209c +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001412592_361627648.pth b/checkpoint_p0/milestones/checkpoint_001412592_361627648.pth new file mode 100644 index 0000000000000000000000000000000000000000..3d9087580f322a159637f23f56a07555e752d46d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001412592_361627648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93263a431cc1a9c8b9a4a874c03abef541dd842dbfcfa47d881567d0301be789 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001424976_364797952.pth b/checkpoint_p0/milestones/checkpoint_001424976_364797952.pth new file mode 100644 index 0000000000000000000000000000000000000000..03e779fe5a891ace111c84e01e79431ad51e7d17 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001424976_364797952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04d83e6777cc915a2781a462fcaae291829fa0b19a467b63c6b0238f5585e8f9 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001437520_368009216.pth b/checkpoint_p0/milestones/checkpoint_001437520_368009216.pth new file mode 100644 index 0000000000000000000000000000000000000000..575be44d3b666ba0396b5e8c88bc0f3c9e01dd9c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001437520_368009216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9fb2e291943459f8b0ff466382e0375bdd356023055f5445379ff493f88e7b0 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001450096_371228672.pth b/checkpoint_p0/milestones/checkpoint_001450096_371228672.pth new file mode 100644 index 0000000000000000000000000000000000000000..24a1402bcfbe12197c279eb3caf6c30634fa280c --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001450096_371228672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c404527387eb72ab785e8a9d486075bf7abc4a7e5ba24c65d5f5f41d9b45362b +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001462640_374439936.pth b/checkpoint_p0/milestones/checkpoint_001462640_374439936.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a6ea0ad10022c3ac3a210bd9d4447786a96758d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001462640_374439936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acaa37e1f48097f85497acf6dd27fffbeae727c0cc7866de1408d3b94bdce1ef +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001475248_377667584.pth b/checkpoint_p0/milestones/checkpoint_001475248_377667584.pth new file mode 100644 index 0000000000000000000000000000000000000000..4a273dbc99e4a77372ffb5736f41d08107b4c201 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001475248_377667584.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6af3fd3e9563d07b76099fa615a19bb562dc549a81ced88aa13dc538de6ce80 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001487504_380805120.pth b/checkpoint_p0/milestones/checkpoint_001487504_380805120.pth new file mode 100644 index 0000000000000000000000000000000000000000..38be5701fc62c0d3c061a1725672839cc297fbf0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001487504_380805120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6964d2c11a091660aad79d83b6d3fa125c529a6e9342be0d2227c2528bd1ec3c +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001500080_384024576.pth b/checkpoint_p0/milestones/checkpoint_001500080_384024576.pth new file mode 100644 index 0000000000000000000000000000000000000000..58e8a155010135dfc147c329bcc7b335f452728a --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001500080_384024576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b8c277f4996c8345e4df15595db2750302832b7683818f4bc69b3ec386894cb +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001512688_387252224.pth b/checkpoint_p0/milestones/checkpoint_001512688_387252224.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a8bc2b330b6a57659cf5c4f58936c968fa889cc --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001512688_387252224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be12d28a39391108c6b48699e4a8a2f4496327a1c33640b215343789638389bd +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001525296_390479872.pth b/checkpoint_p0/milestones/checkpoint_001525296_390479872.pth new file mode 100644 index 0000000000000000000000000000000000000000..7aa47a92be56e895413b4e3d6dd828237dac4eb4 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001525296_390479872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d5c2c9549635bcaabe276334ffefb4e5fa3088814bf0c5f12e8283b2d1b813e +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001537840_393691136.pth b/checkpoint_p0/milestones/checkpoint_001537840_393691136.pth new file mode 100644 index 0000000000000000000000000000000000000000..a7e1fae9e0eb848f21bcf1457b449244d515a206 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001537840_393691136.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bc7b2b632329eec85d4e2a213d0a184cfab3aac69727f54e12ccf6959910982 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001550416_396910592.pth b/checkpoint_p0/milestones/checkpoint_001550416_396910592.pth new file mode 100644 index 0000000000000000000000000000000000000000..075d14cdc2bbd28c89e3e3cd4030fb7331d1258f --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001550416_396910592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7e9966c2eab097a164d86a3f0e7890270ac8e9a53ca4c45489a4d323774a3d +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001563024_400138240.pth b/checkpoint_p0/milestones/checkpoint_001563024_400138240.pth new file mode 100644 index 0000000000000000000000000000000000000000..72ec23d58e39c36ccaacaeebe16bf285ccb892fb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001563024_400138240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdcc820e51c060cc9a33f2431f1b90f7d7229b5224e4af7000ddeced615f412c +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001575600_403357696.pth b/checkpoint_p0/milestones/checkpoint_001575600_403357696.pth new file mode 100644 index 0000000000000000000000000000000000000000..85c86e3d6255612c425b339af89fee6578a5f2c9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001575600_403357696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:488ec356c80db9d3ad55a6bac41160edb49a0724c8871ddf0e03f3bb8512a3e3 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001588240_406593536.pth b/checkpoint_p0/milestones/checkpoint_001588240_406593536.pth new file mode 100644 index 0000000000000000000000000000000000000000..ff50c10497f3c2f9abf355f960803ca5ffb56886 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001588240_406593536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b9cf2606f856dcc0cd96c16a1b07c777bba3fae3e46a4c96a1de1e61083e676 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001600880_409829376.pth b/checkpoint_p0/milestones/checkpoint_001600880_409829376.pth new file mode 100644 index 0000000000000000000000000000000000000000..f11627f3b4143c10c6fb4fee6c549ad97b7f51b5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001600880_409829376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:709ec652f22e2085e0401690f38e92879c8daa1c14458fa41fe81d4bb6fa2fca +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001613520_413065216.pth b/checkpoint_p0/milestones/checkpoint_001613520_413065216.pth new file mode 100644 index 0000000000000000000000000000000000000000..31594e8c0316b0334e08f42a1c903d02710473c9 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001613520_413065216.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ab4eec8b150e75bd47cbbada0c926295f8928948724dad2b8977a80f28aa976 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001626256_416325632.pth b/checkpoint_p0/milestones/checkpoint_001626256_416325632.pth new file mode 100644 index 0000000000000000000000000000000000000000..ba840d58e06b42704d64139ff3be2c9b7eac2cb5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001626256_416325632.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cd932a60aebe257f8286b6d062bdcf35b7bbd4375f3c108738e1655589ba174 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001638896_419561472.pth b/checkpoint_p0/milestones/checkpoint_001638896_419561472.pth new file mode 100644 index 0000000000000000000000000000000000000000..f7116e0c7f6f9dd94ef9620a19ca0fa809c7c1c5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001638896_419561472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1d59d6029730ef9214db181f9d5f0a86c31d865c0571be45f45563c02acb6f +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001651536_422797312.pth b/checkpoint_p0/milestones/checkpoint_001651536_422797312.pth new file mode 100644 index 0000000000000000000000000000000000000000..9a20be3686afb6b17b1e01257789e0ef68d805a8 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001651536_422797312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c57261b952daf438d72a4b6e4cc5540948052caa1979d9c2004e68db2dd318c +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001664240_426049536.pth b/checkpoint_p0/milestones/checkpoint_001664240_426049536.pth new file mode 100644 index 0000000000000000000000000000000000000000..cd907e4444823bca8d903ee1ec3f2adf5877c670 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001664240_426049536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb6f0a9ee2599c2d7d7f7919a332c94405830992943aae117b7097f1001eed6 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001676912_429293568.pth b/checkpoint_p0/milestones/checkpoint_001676912_429293568.pth new file mode 100644 index 0000000000000000000000000000000000000000..b7c06491be5ed58da132bef677065dfe7fd43bf1 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001676912_429293568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee49ea509f358b46b29ba08ba4824ad29a09b38e9892925635d49d9bd3661c3b +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001689584_432537600.pth b/checkpoint_p0/milestones/checkpoint_001689584_432537600.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7d94a9ca5ec7ab6738a17c9692e6297fa4908eb --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001689584_432537600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a2d0272645588abc68ccc186ae7e755fc0802cbe028bf42325f43d084802723 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001702288_435789824.pth b/checkpoint_p0/milestones/checkpoint_001702288_435789824.pth new file mode 100644 index 0000000000000000000000000000000000000000..c127a1837eb3141c602070f4f346ed94978d9e5b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001702288_435789824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33eccda040320741a45fe4d965a007ae98af92fbcc55c75cc367caf96ba0cfec +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001714896_439017472.pth b/checkpoint_p0/milestones/checkpoint_001714896_439017472.pth new file mode 100644 index 0000000000000000000000000000000000000000..fbdef612cb95608f48ce20b8a0ee7fe1a95f28c7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001714896_439017472.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b429af4fbbf1b4a4bc1af9235ce6431abf3a918d01cd9d164b8c2890b869a0dc +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001727600_442269696.pth b/checkpoint_p0/milestones/checkpoint_001727600_442269696.pth new file mode 100644 index 0000000000000000000000000000000000000000..ec913316e417812c3518809987e9804431f73d04 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001727600_442269696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:989ac31e7a721ca8b5ae532180e9832d7d4e068e3b8e877094317f84d04ec368 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001740304_445521920.pth b/checkpoint_p0/milestones/checkpoint_001740304_445521920.pth new file mode 100644 index 0000000000000000000000000000000000000000..094494eccacfde5247606a61b23b46c4606e4774 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001740304_445521920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:634557bd1aea2317700c6dd0e79dff3d3c98855e1113aa352b8ac69a10a81066 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001752976_448765952.pth b/checkpoint_p0/milestones/checkpoint_001752976_448765952.pth new file mode 100644 index 0000000000000000000000000000000000000000..b78d9e09215014f7fbae52b6c224dd0cd846df49 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001752976_448765952.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:416bfa3006f5e0459ccbe516fe5438580a9bfc8dc372129c478a8b5fac82a125 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001765648_452009984.pth b/checkpoint_p0/milestones/checkpoint_001765648_452009984.pth new file mode 100644 index 0000000000000000000000000000000000000000..d6cd9e44cbe7bd83789c8b20befb6b14cb33891e --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001765648_452009984.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4a3dd709b81d307db3380c8a4edf2ad27e794db8168d9f508cf0eed4c4ea108 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001778320_455254016.pth b/checkpoint_p0/milestones/checkpoint_001778320_455254016.pth new file mode 100644 index 0000000000000000000000000000000000000000..b886b1b60e74c87c42dc2af9231506bd34336506 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001778320_455254016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf26baaf6cf47c9349394e9295303695f35944a1713af986a343be2daded74b9 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001790992_458498048.pth b/checkpoint_p0/milestones/checkpoint_001790992_458498048.pth new file mode 100644 index 0000000000000000000000000000000000000000..057440a885b218cebfb057c896d307834ae8d7b7 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001790992_458498048.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69a6d446dd2e3b07d929d00737556a10efebc2a8c71bf235d09f04a775fb2e61 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001803408_461676544.pth b/checkpoint_p0/milestones/checkpoint_001803408_461676544.pth new file mode 100644 index 0000000000000000000000000000000000000000..a8ef38cc21ac4e04bb606f6d2b3eb33fcc1a4761 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001803408_461676544.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e952e9a0a7df1394826daa1f8eed1bb4ea5c8ce96a4c5936a33a17fea6e12271 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001816016_464904192.pth b/checkpoint_p0/milestones/checkpoint_001816016_464904192.pth new file mode 100644 index 0000000000000000000000000000000000000000..89ebd6d7e1d228277137e3e7267639afb515b8cf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001816016_464904192.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f112c137bcd55572ee705972648ea126142016675762c3acf75b15987a92e7c9 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001828656_468140032.pth b/checkpoint_p0/milestones/checkpoint_001828656_468140032.pth new file mode 100644 index 0000000000000000000000000000000000000000..5b4fb95c227952ef37ffe9a90cb20fe7a1747aa2 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001828656_468140032.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57f8eae967280637e4a9d3283f1c9411e33d46d6ff655881a4daa037bfb73c2 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001841232_471359488.pth b/checkpoint_p0/milestones/checkpoint_001841232_471359488.pth new file mode 100644 index 0000000000000000000000000000000000000000..0b2279175655397ca8dcb34e62b9d3178ced563b --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001841232_471359488.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4330bde733a499245d5dc5edaf3ded5be7bccab0649211d71525c9a7082a76e9 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001853936_474611712.pth b/checkpoint_p0/milestones/checkpoint_001853936_474611712.pth new file mode 100644 index 0000000000000000000000000000000000000000..243393a09fcef4ab9f6032c495926a90133bbc71 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001853936_474611712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:487d4f6771e2a52d1bc8023278b1fd9dbf7f7ac4ab04f902f4ffe30e50e01e2a +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001866608_477855744.pth b/checkpoint_p0/milestones/checkpoint_001866608_477855744.pth new file mode 100644 index 0000000000000000000000000000000000000000..c5e2a3a96988aaa10156cbc5b6da24dd74d33862 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001866608_477855744.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89bb5141831110cc81e26b31b4a958d012486029d657deefad51e9cada863733 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001879280_481099776.pth b/checkpoint_p0/milestones/checkpoint_001879280_481099776.pth new file mode 100644 index 0000000000000000000000000000000000000000..6a3668cca0696a0f097c35d87bf18e8403e1f0cf --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001879280_481099776.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ce63c7d5b6ffc830ecc264494362ca1eb91d9512e3e7a9836eaffe1b46ff003 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001891920_484335616.pth b/checkpoint_p0/milestones/checkpoint_001891920_484335616.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c5627653ea70ee2e8c04a68cde5f1ac90bac445 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001891920_484335616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22d25ba6977dd52b459d2065cec9de31a65f9a0f51ef82070fdcd4e54b5372ea +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001904624_487587840.pth b/checkpoint_p0/milestones/checkpoint_001904624_487587840.pth new file mode 100644 index 0000000000000000000000000000000000000000..fa7887892631640a99dc81c760eef105250b2cc5 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001904624_487587840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75599f1b41440dc632083db390ec4646aa4e99792fbe588a1ddbce804152a45c +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001917296_490831872.pth b/checkpoint_p0/milestones/checkpoint_001917296_490831872.pth new file mode 100644 index 0000000000000000000000000000000000000000..7c8bcb49f1c7bec1be13b45dba6117d70dadf1a0 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001917296_490831872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0f56ee11c4ebda9530a197918e739c7ff43cc05c6e37005c089b7f8dfc32d74 +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001929968_494075904.pth b/checkpoint_p0/milestones/checkpoint_001929968_494075904.pth new file mode 100644 index 0000000000000000000000000000000000000000..29c6b1694665c1ecda42e3f604508a1f57f95693 --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001929968_494075904.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73daa681510ed7917391b9764df2247ea74890299307ba529898f313e2b8a9fc +size 20704843 diff --git a/checkpoint_p0/milestones/checkpoint_001942704_497336320.pth b/checkpoint_p0/milestones/checkpoint_001942704_497336320.pth new file mode 100644 index 0000000000000000000000000000000000000000..4c22365bf68240eae398da64fed6a5010419cd7d --- /dev/null +++ b/checkpoint_p0/milestones/checkpoint_001942704_497336320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37a04ed2310eee5e7a6681dd64632b46b39cbdc9f94bbccf79ec626cdebca73d +size 20704843 diff --git a/checkpoint_p1/checkpoint_001952808_499933184.pth b/checkpoint_p1/checkpoint_001952808_499933184.pth new file mode 100644 index 0000000000000000000000000000000000000000..13265dab0027c923eaf1106e0aee8644142e3274 --- /dev/null +++ b/checkpoint_p1/checkpoint_001952808_499933184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83542b88a3a30cdb13866b0bec18157b97f137a624819b7283642bc90d08ce7d +size 20703939 diff --git a/checkpoint_p1/checkpoint_001953096_500006912.pth b/checkpoint_p1/checkpoint_001953096_500006912.pth new file mode 100644 index 0000000000000000000000000000000000000000..298da2f8d582f9f57824d842cbaea0f538689fe2 --- /dev/null +++ b/checkpoint_p1/checkpoint_001953096_500006912.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9769a637beddd2356bb440230cfe9c98e43a037e645ec0537e6097761d75fa +size 20703939 diff --git a/checkpoint_p1/milestones/checkpoint_000418944_107249664.pth b/checkpoint_p1/milestones/checkpoint_000418944_107249664.pth new file mode 100644 index 0000000000000000000000000000000000000000..d2a196a45642b2226da6e648e7a5a336d4e29e33 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000418944_107249664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29a243a32d7b9d2447ea9aa588831feeffc8207c32c7984a1c8d95c9c014a84 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000431520_110469120.pth b/checkpoint_p1/milestones/checkpoint_000431520_110469120.pth new file mode 100644 index 0000000000000000000000000000000000000000..990d7b13673963ce94cb4ab9fa8be287a291e531 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000431520_110469120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c1d87c0a547df3eadaa8755a37dd32a61123d2ee925e5328538f4f609cf17e5 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000444096_113688576.pth b/checkpoint_p1/milestones/checkpoint_000444096_113688576.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a7a970e7ad87c72ab182fbeac9753092b165866 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000444096_113688576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b23265f8515987b3a615abf40bcc3bb7bb81c807d238ea8c03b29c92fafaa240 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000456736_116924416.pth b/checkpoint_p1/milestones/checkpoint_000456736_116924416.pth new file mode 100644 index 0000000000000000000000000000000000000000..040b987588b57594cb43a3013dc6ce1f124b8e6c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000456736_116924416.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:534eca5fb4bc7bfaa21ddf6e61393aeeb5d33e21d0699d15baee37d52f507d2b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000469440_120176640.pth b/checkpoint_p1/milestones/checkpoint_000469440_120176640.pth new file mode 100644 index 0000000000000000000000000000000000000000..4137bbcf88024463c2551c7cdd581f68a5630c27 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000469440_120176640.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5473761663c3feb96759c17577f4ac1c8e0816178333065611a68c15093a09b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000482080_123412480.pth b/checkpoint_p1/milestones/checkpoint_000482080_123412480.pth new file mode 100644 index 0000000000000000000000000000000000000000..c37d150a71a499fc2e0368b11ecc88f639fd2598 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000482080_123412480.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5c6c9c9052cd553acd05bd27acc138f90a2cbe842b72871c7e6b83f12367269 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000494688_126640128.pth b/checkpoint_p1/milestones/checkpoint_000494688_126640128.pth new file mode 100644 index 0000000000000000000000000000000000000000..d4d54ea4a1f411444e4b52dba9d414361c86ad64 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000494688_126640128.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf5848412af88f0ee01329b44d21d70050efcdea449ec8c902df2f60bab0b16a +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000507392_129892352.pth b/checkpoint_p1/milestones/checkpoint_000507392_129892352.pth new file mode 100644 index 0000000000000000000000000000000000000000..a2c0a139a08496546b1e6c85fb5b81145b77c727 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000507392_129892352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306f6cbb20d448eeb9395ede959c166c988a0a3318ab450235ece0c8fffd30c6 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000520000_133120000.pth b/checkpoint_p1/milestones/checkpoint_000520000_133120000.pth new file mode 100644 index 0000000000000000000000000000000000000000..b711b0e31842f5d044df4a95ce1eeda4fc9b83ac --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000520000_133120000.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7a43e2b28a33971a7de0c5238897da95895a4c0c695355d699052873ad2e8ba +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000532704_136372224.pth b/checkpoint_p1/milestones/checkpoint_000532704_136372224.pth new file mode 100644 index 0000000000000000000000000000000000000000..484c5f2749b080ad66a0f1bc86dba4b821189465 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000532704_136372224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b221d19e9507f94e1242c3d54db6b28d0c3b55b63005fbef97e0f7e16a4029a0 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000545312_139599872.pth b/checkpoint_p1/milestones/checkpoint_000545312_139599872.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f96e033554acca74b23da62d213406fdb764f2b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000545312_139599872.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e6ee60a559ab79acb1bef5e48cc10ee5694c4dfd6c3fe56553c5a9eb5850cd7 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000558016_142852096.pth b/checkpoint_p1/milestones/checkpoint_000558016_142852096.pth new file mode 100644 index 0000000000000000000000000000000000000000..afc4c430936e2e48ebc877f4da580e52fb548b0a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000558016_142852096.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14227d2954689217ac325ea9932f6adf93b02574291d7b22281e8e18dbf71501 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000570720_146104320.pth b/checkpoint_p1/milestones/checkpoint_000570720_146104320.pth new file mode 100644 index 0000000000000000000000000000000000000000..09dca246d616db0ce70c2c9c3ef6ac78963d4f7d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000570720_146104320.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38ef87a02d7dfcb6eb74e0288674f78213d8651675241e010f7d6f056e328e6b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000583392_149348352.pth b/checkpoint_p1/milestones/checkpoint_000583392_149348352.pth new file mode 100644 index 0000000000000000000000000000000000000000..c99b77ae4c35c700b7aa3d4e21cbfa166a44c3c6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000583392_149348352.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4ae416897bac5247e5c05c3bfda842ecd667d6833cffd11ffb02b488bf2dc0 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000596064_152592384.pth b/checkpoint_p1/milestones/checkpoint_000596064_152592384.pth new file mode 100644 index 0000000000000000000000000000000000000000..5859745d84ab4f6a29ca758d196b4da4951bb661 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000596064_152592384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09a2bdb94d29c24364fae5f9245e2b8832509ba9ec2735abdf900044123ba655 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000618496_158334976.pth b/checkpoint_p1/milestones/checkpoint_000618496_158334976.pth new file mode 100644 index 0000000000000000000000000000000000000000..4e62f0606b73db6ee87a2642a5d86ce15cbed6ad --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000618496_158334976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29c28a9328a279ba4d46b6a7a657687b04947173135e112cdc3e21ce4de2b08b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000631136_161570816.pth b/checkpoint_p1/milestones/checkpoint_000631136_161570816.pth new file mode 100644 index 0000000000000000000000000000000000000000..73f24f876d0d30f37dab57a3851d0ff86360e8ac --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000631136_161570816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:233e7d34d65707ec2197934dc0dbee47315555e508ca751cdb50006157228164 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000643808_164814848.pth b/checkpoint_p1/milestones/checkpoint_000643808_164814848.pth new file mode 100644 index 0000000000000000000000000000000000000000..93d2f3895fe41e6b127485a2df03052c7a6c722e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000643808_164814848.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:262196249a641d70eeea5e9b258c9a704034fb943efbd921cb4cb2e0c3eb2b58 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000656336_168026112.pth b/checkpoint_p1/milestones/checkpoint_000656336_168026112.pth new file mode 100644 index 0000000000000000000000000000000000000000..704af5f11b7d8ebde10d56aeff7dabc2e1e91ec8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000656336_168026112.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e257c7cfd9308b08c7ced594a772caa6faad1bfebb23983f5b1f9d2a012b4ac7 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000668944_171253760.pth b/checkpoint_p1/milestones/checkpoint_000668944_171253760.pth new file mode 100644 index 0000000000000000000000000000000000000000..3312ba2774bf797f9cc836640143ca32f92d749e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000668944_171253760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d21ebb5404bef7556ede8248dec8e95d84a3640d695aa56871c548f9dbb50c9c +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000681552_174481408.pth b/checkpoint_p1/milestones/checkpoint_000681552_174481408.pth new file mode 100644 index 0000000000000000000000000000000000000000..8a44a774c7f71c472326c865e64d2701e41dcd75 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000681552_174481408.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4891b72d17553a9507f4f62197001b1e8faed410559924beaa06c84105719c70 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000694128_177700864.pth b/checkpoint_p1/milestones/checkpoint_000694128_177700864.pth new file mode 100644 index 0000000000000000000000000000000000000000..7df1515ebc88c7eee4de6e0b9419f87513c58371 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000694128_177700864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebc114d3d7f79252eea6efa448708f20bde0b61371aba11aab72ed169dd8ef96 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000706800_180944896.pth b/checkpoint_p1/milestones/checkpoint_000706800_180944896.pth new file mode 100644 index 0000000000000000000000000000000000000000..3e2853b421838522b9bd055b8eb5eea59a6dc82b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000706800_180944896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dd7b445deb8cd5342df6965b0921b34ac73cc986f9296c7b0b012623e937dac +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000719440_184180736.pth b/checkpoint_p1/milestones/checkpoint_000719440_184180736.pth new file mode 100644 index 0000000000000000000000000000000000000000..99bfe4d608413d3288678cfc17ddf4bbf54fab47 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000719440_184180736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dbd8c4df54c51ce00bfa13af457f9791c22e8d8563a398fe7df2d3c4d3471e48 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000732048_187408384.pth b/checkpoint_p1/milestones/checkpoint_000732048_187408384.pth new file mode 100644 index 0000000000000000000000000000000000000000..0d881f9915a48bd638b85a814a5c3942ac368c4c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000732048_187408384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d506c1a44ee9f6cddf60176ee1d3a24cd02ca80a9542d1774f4187bfbe350f4 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000744592_190619648.pth b/checkpoint_p1/milestones/checkpoint_000744592_190619648.pth new file mode 100644 index 0000000000000000000000000000000000000000..c4b9ba642e25343cdc97d9fb4e0114690fcfdf5c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000744592_190619648.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8e788793618b5e79bcc5fbf332f4cc0a749b5550ac77d47e9fad43fef81da1a +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000757168_193839104.pth b/checkpoint_p1/milestones/checkpoint_000757168_193839104.pth new file mode 100644 index 0000000000000000000000000000000000000000..e67bf9a93b7aa8ffe726ce15c7269fbd9b17cf53 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000757168_193839104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4388af67d14cc8d9a2e1cf5779930e3a0dfcaad552305f88117198c5ad1555ff +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000769776_197066752.pth b/checkpoint_p1/milestones/checkpoint_000769776_197066752.pth new file mode 100644 index 0000000000000000000000000000000000000000..e13810920145bf7c80f92388599ee0e14f9c93fc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000769776_197066752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e213534274b6af9ba67c9a6efad6a33f933719f741cab3b948469f1b1e7795c4 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000782416_200302592.pth b/checkpoint_p1/milestones/checkpoint_000782416_200302592.pth new file mode 100644 index 0000000000000000000000000000000000000000..d835894e00c00b70068e4380045a30be392582c6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000782416_200302592.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c61ef42e5cee302d6e409a7c0be26e8fe194042b054356956dd6852a2fbae393 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000794960_203513856.pth b/checkpoint_p1/milestones/checkpoint_000794960_203513856.pth new file mode 100644 index 0000000000000000000000000000000000000000..ef4e303a3b91810d44a99edb939705060ccca214 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000794960_203513856.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:523b85ca1a6878b049b042d338afef31bb73a31528b0559a422465f5e7987ac7 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000807472_206716928.pth b/checkpoint_p1/milestones/checkpoint_000807472_206716928.pth new file mode 100644 index 0000000000000000000000000000000000000000..6c2c891479a9e06bf19ba49deb106251bc364ad5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000807472_206716928.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3db0fd8b17803f9c03ae4e292a633fa3ff447c4f31550a9588361fe2560a80 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000820048_209936384.pth b/checkpoint_p1/milestones/checkpoint_000820048_209936384.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad2df03a47721cfe412ddba1de1c7b8babde3baa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000820048_209936384.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:510bfde19e9685e99aafd7c4487abcdac40ad1fdb9e55dc72bf3529c2ca7c695 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000832624_213155840.pth b/checkpoint_p1/milestones/checkpoint_000832624_213155840.pth new file mode 100644 index 0000000000000000000000000000000000000000..68ccca67ea819b991e329349286702998ac36b23 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000832624_213155840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c221bb1e71d191c7c005c69522d6c258b87b6b7e6f06743244e94e3cd8799774 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000845200_216375296.pth b/checkpoint_p1/milestones/checkpoint_000845200_216375296.pth new file mode 100644 index 0000000000000000000000000000000000000000..e44a7081681be8da33edd6f744e4f32d64d405e2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000845200_216375296.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:877165de2534a3af087ac88f6f5a33c37c97982cdfb195619639cfc2aef365ce +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000857872_219619328.pth b/checkpoint_p1/milestones/checkpoint_000857872_219619328.pth new file mode 100644 index 0000000000000000000000000000000000000000..c7b009fc91aedc83d2cc0c841e2d09bff40e7433 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000857872_219619328.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1d0bc0d470f90c3a774292cc94a2993145be89a210ee5a18b7d9452b538c6b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000870480_222846976.pth b/checkpoint_p1/milestones/checkpoint_000870480_222846976.pth new file mode 100644 index 0000000000000000000000000000000000000000..e557c8bcd34b9c7760e09f0359f196677fe2df3c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000870480_222846976.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9bdf61b131a654c859f01b1c17e02235a8e7dc2433779bc6f3193dff3bd3d98 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000883056_226066432.pth b/checkpoint_p1/milestones/checkpoint_000883056_226066432.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0cdd2d3d747319f7e544fdb24de2e9593fa9097 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000883056_226066432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0ea9913c50a374e7c7bf48a7af82cd66646d62c5359b6fd4f5f14c6292525e5 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000895312_229203968.pth b/checkpoint_p1/milestones/checkpoint_000895312_229203968.pth new file mode 100644 index 0000000000000000000000000000000000000000..7176a8f2cc12f2a265365c4dc42eb89cab033615 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000895312_229203968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b05833f7edcd17b472fded8a1b9438d1be3d1b5d24458eb1d61213acedac6703 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000907888_232423424.pth b/checkpoint_p1/milestones/checkpoint_000907888_232423424.pth new file mode 100644 index 0000000000000000000000000000000000000000..3aeb8d95fe6d33eaf7fab743c46f2307f8d695bf --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000907888_232423424.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fad1d66654f6b725c1f0193748ca15d80293379f40664fd8e11f3bd5f30265b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000920496_235651072.pth b/checkpoint_p1/milestones/checkpoint_000920496_235651072.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f21bb78cad901728f9c5424f566015110f5f3fe --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000920496_235651072.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6368d6a797c4f5550967add76d07334b99487e559cec42054398eaee17e632d4 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000933008_238854144.pth b/checkpoint_p1/milestones/checkpoint_000933008_238854144.pth new file mode 100644 index 0000000000000000000000000000000000000000..0974397a7d21b6f9a665a3b15a7f6fd5a6e45a31 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000933008_238854144.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e76bd2c5e3882753d4878206a3f1b58dafbd7d6705e248c89a5cffbaeb558d4 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000945616_242081792.pth b/checkpoint_p1/milestones/checkpoint_000945616_242081792.pth new file mode 100644 index 0000000000000000000000000000000000000000..59e33d1cc88a862fed12e4afda280dadaeba3162 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000945616_242081792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:099ec371aee00e068fd504374da18dcd038862afc52da5c7c6d8691747dc2d35 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000958192_245301248.pth b/checkpoint_p1/milestones/checkpoint_000958192_245301248.pth new file mode 100644 index 0000000000000000000000000000000000000000..1d3e927876b55c552f7eac832c16a433d65afa53 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000958192_245301248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b614fdf337e407811d807b2f2970128cef2e0442903c2749e44f400487e78923 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000970736_248512512.pth b/checkpoint_p1/milestones/checkpoint_000970736_248512512.pth new file mode 100644 index 0000000000000000000000000000000000000000..b389283fa68fa946142b6f1ed07cb7478fca6bd4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000970736_248512512.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0646be6d771dc54928e5eab60c8c8835eb7d4c15ca6c8ab47f5eba026ec02144 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000983312_251731968.pth b/checkpoint_p1/milestones/checkpoint_000983312_251731968.pth new file mode 100644 index 0000000000000000000000000000000000000000..6ea8874c0c2f1b8dfa73d6c12e6efc470e6a7316 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000983312_251731968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7211874c57ece35ddcdf1c9a0420a4225519a627c910fab0e78f1439d5d876d8 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_000995920_254959616.pth b/checkpoint_p1/milestones/checkpoint_000995920_254959616.pth new file mode 100644 index 0000000000000000000000000000000000000000..55fd0a46b23e34ea10955647ac2b3368106fa4c4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_000995920_254959616.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:731a49413cbc6967e8f11766473712119b8246a3a6bf83941a22b53a2f9aaa49 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001008464_258170880.pth b/checkpoint_p1/milestones/checkpoint_001008464_258170880.pth new file mode 100644 index 0000000000000000000000000000000000000000..15a8193723ecb79d09cd8c06f5707f60bd6ba07e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001008464_258170880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d21701a8a74f2a3a33a45199809e60f534d6281de0ea66c7b9000adfd8a5f6e +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001021040_261390336.pth b/checkpoint_p1/milestones/checkpoint_001021040_261390336.pth new file mode 100644 index 0000000000000000000000000000000000000000..bca8d750e9ed4de7524eb7911b81219769faf339 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001021040_261390336.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4806f8dc752e2850d6f888685c909ce510a537a80ea0909d7b544d4e97dc6224 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001033616_264609792.pth b/checkpoint_p1/milestones/checkpoint_001033616_264609792.pth new file mode 100644 index 0000000000000000000000000000000000000000..879a7d5612db6aa88f056d1df71c48266249a28e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001033616_264609792.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254e445c76ed4998b3e0b70782f6a7f41fe4a6cec936b25bd9d4003fe9a49177 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001046192_267829248.pth b/checkpoint_p1/milestones/checkpoint_001046192_267829248.pth new file mode 100644 index 0000000000000000000000000000000000000000..e5c0ee70601489827dc7377a2481b51d4b397787 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001046192_267829248.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54e9620aa56c399e3b36c7c0b1ba516ac03a34fda9f9f7572c5e1bc1b857dc4b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001058768_271048704.pth b/checkpoint_p1/milestones/checkpoint_001058768_271048704.pth new file mode 100644 index 0000000000000000000000000000000000000000..94882320470efb3bf0eb63d2af6e88c669d1bf3e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001058768_271048704.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99387cf29fd16b9221d87a2205f238faa96b18fd57a740eeed036c7c6e218e86 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001071312_274259968.pth b/checkpoint_p1/milestones/checkpoint_001071312_274259968.pth new file mode 100644 index 0000000000000000000000000000000000000000..1c5e7670a0e7a1d4782edc5961c80ff5f066c60f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001071312_274259968.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a842aedbc7f3915a2fe7594467731c7b235ca996722190a474b796672e409ce +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001083856_277471232.pth b/checkpoint_p1/milestones/checkpoint_001083856_277471232.pth new file mode 100644 index 0000000000000000000000000000000000000000..d48001f00085df9a13a74876659f25ddf13db2b1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001083856_277471232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09c68ea838dc888673cadfa74ae949a427a0ae63c581012fdd46257a547dc55b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001096528_280715264.pth b/checkpoint_p1/milestones/checkpoint_001096528_280715264.pth new file mode 100644 index 0000000000000000000000000000000000000000..afa4134055b51dc1456b1e2a71b518f16dad49be --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001096528_280715264.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:014dcefb2084c94072d0f1fa44b4281a8dbfebdf75401b8c0af5757b1daed447 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001109104_283934720.pth b/checkpoint_p1/milestones/checkpoint_001109104_283934720.pth new file mode 100644 index 0000000000000000000000000000000000000000..e8216db8ca497f92a9f6e13065eead70216583af --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001109104_283934720.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c228fa1cf9c0ee48afac67745c12aad57cc362bf025606a8b77085c969fc0b9c +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001121712_287162368.pth b/checkpoint_p1/milestones/checkpoint_001121712_287162368.pth new file mode 100644 index 0000000000000000000000000000000000000000..ed9d3a1d5d0d6ea3d36f0daf1dc30583d065a671 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001121712_287162368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36ff53f6802c5f320a1e338197d33f3037d53adebb0acb1b4b10ba67700f8915 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001134352_290398208.pth b/checkpoint_p1/milestones/checkpoint_001134352_290398208.pth new file mode 100644 index 0000000000000000000000000000000000000000..eff6378a163bdd098c61e10a9ded251bfdbbd61e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001134352_290398208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc2881f3f421bfdb73c2f67bbe3562e6c76ad0b78c7f5e1dbe5201321b5d64e4 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001147024_293642240.pth b/checkpoint_p1/milestones/checkpoint_001147024_293642240.pth new file mode 100644 index 0000000000000000000000000000000000000000..a4c0dae35130bfde750ba47dfeeb77a405018795 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001147024_293642240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f45c1a09e271e4b6b5084c44a18ac5c02c84587f7bb4ff5ba7680e2caba7997 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001159664_296878080.pth b/checkpoint_p1/milestones/checkpoint_001159664_296878080.pth new file mode 100644 index 0000000000000000000000000000000000000000..d5efeafafda5c6cfe3a1d701d6ac36daea403f16 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001159664_296878080.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eae36f307fd33d643a5b49bb68515246e2597817d809171e2484fe3e81d7495 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001172240_300097536.pth b/checkpoint_p1/milestones/checkpoint_001172240_300097536.pth new file mode 100644 index 0000000000000000000000000000000000000000..58fa810e109360a4f1f1f11e8af233036544ca9d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001172240_300097536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dc952a2ed1f5e96474db3db5fdbe634fdf31621deadfea96cdac37b1c2a805d +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001184848_303325184.pth b/checkpoint_p1/milestones/checkpoint_001184848_303325184.pth new file mode 100644 index 0000000000000000000000000000000000000000..0dc410d39eff7cc7488b7731d434a2bc515693e9 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001184848_303325184.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ded20f7810f3681f44d9df578b684264639e1ee362c838f744486bbf01c11c6 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001197488_306561024.pth b/checkpoint_p1/milestones/checkpoint_001197488_306561024.pth new file mode 100644 index 0000000000000000000000000000000000000000..10d7ba9e73a95c7f1eccbd0e92d7f1e5f458e84d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001197488_306561024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e058852c5bd85b7ade3102cd596f2d96abdf3841f50f2ef192abb63c0f65e886 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001210128_309796864.pth b/checkpoint_p1/milestones/checkpoint_001210128_309796864.pth new file mode 100644 index 0000000000000000000000000000000000000000..5ada8a0e59f65f5542a49590b87e47f0c9199c79 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001210128_309796864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd12cc8b9d8333327c8716f0b284afdcf6f6a583207507020a8b704a71175683 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001222864_313057280.pth b/checkpoint_p1/milestones/checkpoint_001222864_313057280.pth new file mode 100644 index 0000000000000000000000000000000000000000..5c7fc4c80a4ecdecceca07001e74138ff13a969f --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001222864_313057280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f00f2bd27a843f96e794a4220d4255e9a263089b4745e62bb1f017fa90232bf3 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001235504_316293120.pth b/checkpoint_p1/milestones/checkpoint_001235504_316293120.pth new file mode 100644 index 0000000000000000000000000000000000000000..12ec9bc3648d772e94e963870d9e3f7e4ae7b109 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001235504_316293120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bdb08e393b447f12ab6500b810bad0b8c94c0890e60c0ee98fba99274f67572 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001248080_319512576.pth b/checkpoint_p1/milestones/checkpoint_001248080_319512576.pth new file mode 100644 index 0000000000000000000000000000000000000000..4319f5390a897a59fca271470d80cc5f857b2f5e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001248080_319512576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3468d8cd5027888fa1b02b49b281a942f617d7a4ec218da36f10bc581129e01f +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001260688_322740224.pth b/checkpoint_p1/milestones/checkpoint_001260688_322740224.pth new file mode 100644 index 0000000000000000000000000000000000000000..5a6ad8cdaddc74de5f524b70ba78e0ff0c59c408 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001260688_322740224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fd7a78b0e04b38264edaa04124d2d5f34fa32ad6ffe655e4c02eea5b716974b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001273264_325959680.pth b/checkpoint_p1/milestones/checkpoint_001273264_325959680.pth new file mode 100644 index 0000000000000000000000000000000000000000..4ef825388a0e1dc996b793f341851a04a13c2d34 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001273264_325959680.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:825e91ff0981dcf1ac055dde515989dee5cde3c76d8c89471b0673353f8cd216 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001285904_329195520.pth b/checkpoint_p1/milestones/checkpoint_001285904_329195520.pth new file mode 100644 index 0000000000000000000000000000000000000000..825e3fab4dce1809822b1cc979aa9a25d9aac2e6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001285904_329195520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d100c35ef8b59bfae54d1ec39a055b550826dbf89886f2407b64e33024642d6b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001298544_332431360.pth b/checkpoint_p1/milestones/checkpoint_001298544_332431360.pth new file mode 100644 index 0000000000000000000000000000000000000000..5f81d7fb112f5546b6b6aad81a3ae9d828f5b900 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001298544_332431360.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d6987c73537cd07c2214d50e9f2e3863594aa74c65fe9157841633a0d2f9c3f +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001311024_335626240.pth b/checkpoint_p1/milestones/checkpoint_001311024_335626240.pth new file mode 100644 index 0000000000000000000000000000000000000000..841665eb468a88fd7252ae28de8bcdd168bdc151 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001311024_335626240.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93b67d1fb95cb1776175e667632160b9fd874505b483d7ade78e83786dd53525 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001323600_338845696.pth b/checkpoint_p1/milestones/checkpoint_001323600_338845696.pth new file mode 100644 index 0000000000000000000000000000000000000000..fb1d9c0750ee93934b7a54e9b18762467d454181 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001323600_338845696.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190923dd7113482920199714cf9b449f0a753c082d85767995fa60b1c7668237 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001336080_342040576.pth b/checkpoint_p1/milestones/checkpoint_001336080_342040576.pth new file mode 100644 index 0000000000000000000000000000000000000000..966dec800493a91bbb536865e566c4f73d34015a --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001336080_342040576.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68e398d77fd337690f8ea4e20a68ac0eb827e40a79b341a577a76cccee83e603 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001348936_345333760.pth b/checkpoint_p1/milestones/checkpoint_001348936_345333760.pth new file mode 100644 index 0000000000000000000000000000000000000000..1a643144cc3c131c92ee213b7f15e840a3707224 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001348936_345333760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a929243ac9bdc7453e4c26d288a5932981ea0eb6e2a6530dba372d1dba13492 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001361760_348618752.pth b/checkpoint_p1/milestones/checkpoint_001361760_348618752.pth new file mode 100644 index 0000000000000000000000000000000000000000..7a52071a50a6a9d916aca589e4ee37e2d602f0dd --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001361760_348618752.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0bf448cee9f0323fabe60f52c381e3155f7fc48f6bc43ff75179b8b48c195bb +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001374560_351895552.pth b/checkpoint_p1/milestones/checkpoint_001374560_351895552.pth new file mode 100644 index 0000000000000000000000000000000000000000..47ec34bcce34e7d8db84f0dd06a16c74fe3acaa4 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001374560_351895552.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47db84cac6e11d9d00bbe2c4a59f5b979c7ee4cc17ec6762df00ef67654cc51c +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001386272_354893824.pth b/checkpoint_p1/milestones/checkpoint_001386272_354893824.pth new file mode 100644 index 0000000000000000000000000000000000000000..93f549c6fc465ad2d7d443fa02b97b50371c61e1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001386272_354893824.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a9e4161090df4dff02ebff9645541fec1aa325b111dd2d1e28d9006f0bd6cad +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001396784_357588992.pth b/checkpoint_p1/milestones/checkpoint_001396784_357588992.pth new file mode 100644 index 0000000000000000000000000000000000000000..0bc1ddbdcb2a4d342288af456248fb6e35cd6cfb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001396784_357588992.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b767519fa338e5a40064e95bb08a235f2c40901d372bc08df4616908b9bd455a +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001409456_360833024.pth b/checkpoint_p1/milestones/checkpoint_001409456_360833024.pth new file mode 100644 index 0000000000000000000000000000000000000000..1f859f41fb02ea7e820f475c61e807edf75b994e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001409456_360833024.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:532ae15536d61caa48d8919bfd003ae603cc8e00dccd6b6f076e1da0f8b9fe0d +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001421872_364011520.pth b/checkpoint_p1/milestones/checkpoint_001421872_364011520.pth new file mode 100644 index 0000000000000000000000000000000000000000..86f30b3343f704e6f5218db9dd5317083ed7f295 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001421872_364011520.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3a92e1b394eea07c6cc09c80b0c518ec49ddcd0a7022f401c6becee669257bc +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001434416_367222784.pth b/checkpoint_p1/milestones/checkpoint_001434416_367222784.pth new file mode 100644 index 0000000000000000000000000000000000000000..74fdfad042dbd9a45d4857dbcf5da0f29cd47ec7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001434416_367222784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1623a6ed287a808d42077b71c472e6d9ac508e7eae56709b0917e40849510309 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001447016_370450432.pth b/checkpoint_p1/milestones/checkpoint_001447016_370450432.pth new file mode 100644 index 0000000000000000000000000000000000000000..02b77fbbafcd875d87a3ef637fbfba4934dc84cb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001447016_370450432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77cdfc02efb54e69290144ce85ee22c7d8e47f1035c9b5b8ea58a07cecfcad33 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001459592_373669888.pth b/checkpoint_p1/milestones/checkpoint_001459592_373669888.pth new file mode 100644 index 0000000000000000000000000000000000000000..8d5e877a375a2e5e15787c213ab97fd7a531a3c5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001459592_373669888.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:841165616879a72aabb35a06fe838a62f2904018e4fa899a1803b4a09f26bc6a +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001472264_376913920.pth b/checkpoint_p1/milestones/checkpoint_001472264_376913920.pth new file mode 100644 index 0000000000000000000000000000000000000000..b012cbf2f9457b186ec13c7b29824c2f7084ce31 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001472264_376913920.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8651963f1f24c88447792472d32fe11c8c79b91b9ceaca9027e6d19de641ee66 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001484648_380084224.pth b/checkpoint_p1/milestones/checkpoint_001484648_380084224.pth new file mode 100644 index 0000000000000000000000000000000000000000..1a03aba1d98ee93074d48186fa531d9cc3c7657c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001484648_380084224.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a6df353d58f092ce666e9aa446213bf78876e89a416fe7ba8afe7325fd09916 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001497352_383336448.pth b/checkpoint_p1/milestones/checkpoint_001497352_383336448.pth new file mode 100644 index 0000000000000000000000000000000000000000..0c46e7174a9b8ae970694a65144cd90602c78432 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001497352_383336448.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b2e5c17bbc03978ef4aa2122eb0aa9b704e8e9f6a07b0ac65033a1f427c4d05b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001510088_386596864.pth b/checkpoint_p1/milestones/checkpoint_001510088_386596864.pth new file mode 100644 index 0000000000000000000000000000000000000000..b314f34ed4b96d3c134b6e24f6f8f007863e5344 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001510088_386596864.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b3f480efb3a20ac2aad6a538614721db800906d9355900d589d7234981a74d7 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001522824_389857280.pth b/checkpoint_p1/milestones/checkpoint_001522824_389857280.pth new file mode 100644 index 0000000000000000000000000000000000000000..4672b7583afa3b9e796ac02060bad5331e5e64c5 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001522824_389857280.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:820500d37a60c2b60bdae9982339e73967add980983c154f7d5bf18e7ba07566 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001535464_393093120.pth b/checkpoint_p1/milestones/checkpoint_001535464_393093120.pth new file mode 100644 index 0000000000000000000000000000000000000000..881594b4a6967593599f9e4c9c408cb4694dee10 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001535464_393093120.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ee939b3ca7e41a9e12b2c9273e94d2f2e9474fff2c155baa705ff405a99e49 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001548168_396345344.pth b/checkpoint_p1/milestones/checkpoint_001548168_396345344.pth new file mode 100644 index 0000000000000000000000000000000000000000..536498f7ac8eedf4f46f6303f7a8916249110598 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001548168_396345344.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94cbf5613f20c54c355bad6787466577abb8d4b09cc30baa233f143a96614cc1 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001560840_399589376.pth b/checkpoint_p1/milestones/checkpoint_001560840_399589376.pth new file mode 100644 index 0000000000000000000000000000000000000000..cfccc697dccd2b487c75f52459ec730912b49541 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001560840_399589376.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d24216b9159b3a9cc53a9e4c121aa597cd889bd6ffadd809e49d973091b51bd +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001573544_402841600.pth b/checkpoint_p1/milestones/checkpoint_001573544_402841600.pth new file mode 100644 index 0000000000000000000000000000000000000000..79e88dff66232ddd11f27cbec7b4f9455a27de15 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001573544_402841600.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6943afad57ed8ccb7003ccdadabf629df536b00ad88688e1ff1066e13fb660c +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001586280_406102016.pth b/checkpoint_p1/milestones/checkpoint_001586280_406102016.pth new file mode 100644 index 0000000000000000000000000000000000000000..5307799f2934a1a602ec17708d09bff1de26c206 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001586280_406102016.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cdd06ac5600c485a12f2f960fe35d6a1f703a8c5adbaf2fb099806c84516cf3 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001599176_409403392.pth b/checkpoint_p1/milestones/checkpoint_001599176_409403392.pth new file mode 100644 index 0000000000000000000000000000000000000000..bedfe62bea42fa4d539ff8c028bf45bcb54fc8a7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001599176_409403392.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fc090b93f765d278d659aed903c36ae4d522715a8fde09880375aae2ca0e526 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001612072_412704768.pth b/checkpoint_p1/milestones/checkpoint_001612072_412704768.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad302b3c2929e0a1592ff021a6df3c056e13041e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001612072_412704768.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecccc2b144767c255a19a96f64ef131922ced2f01aafbd57eeb5ae9f35e5ee51 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001624872_415981568.pth b/checkpoint_p1/milestones/checkpoint_001624872_415981568.pth new file mode 100644 index 0000000000000000000000000000000000000000..9b51b0f0f932b48ff5efbc9cb44afc85d9be4d15 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001624872_415981568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43321e75385b8aa15bff13c26ec544bc4affd324614280a025b9c04db95e2a59 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001637640_419250176.pth b/checkpoint_p1/milestones/checkpoint_001637640_419250176.pth new file mode 100644 index 0000000000000000000000000000000000000000..7ac91f09dda68a04eb0c1077000f8ba7a752c317 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001637640_419250176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29baedfb3b72d04308db660618663b5b1f8e6b4501ac250c0dcbb2ad14332a2a +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001650312_422494208.pth b/checkpoint_p1/milestones/checkpoint_001650312_422494208.pth new file mode 100644 index 0000000000000000000000000000000000000000..16adc963a19b9a792ff9fb62b4df4197a00357b6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001650312_422494208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35a95e310179a4466b6461b83224878519ca940147507f098b5eb8fc9e7bb801 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001663080_425762816.pth b/checkpoint_p1/milestones/checkpoint_001663080_425762816.pth new file mode 100644 index 0000000000000000000000000000000000000000..7ecf7f23d64a255c883e1e929a5cf0373c440c63 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001663080_425762816.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:323176f0f5e621ed0c5cc1b18865c5947fbc8f46c4bf9f72b38d7cf3685cc716 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001675816_429023232.pth b/checkpoint_p1/milestones/checkpoint_001675816_429023232.pth new file mode 100644 index 0000000000000000000000000000000000000000..a3ebb49cfd1754c68276268663bac3589151141e --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001675816_429023232.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a7556d418d0a7f3a6ab4a114266e0d5dd2c187ff58027e7c88355043c02a6e2 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001688584_432291840.pth b/checkpoint_p1/milestones/checkpoint_001688584_432291840.pth new file mode 100644 index 0000000000000000000000000000000000000000..c968ffe113240a74ded4a54bef18b72577ca497d --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001688584_432291840.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87aaf526e22deff406ab2176a1f61779c4c8b85e496d05feab3124edcd7a7b12 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001701320_435552256.pth b/checkpoint_p1/milestones/checkpoint_001701320_435552256.pth new file mode 100644 index 0000000000000000000000000000000000000000..401fd0c92cde56df9cbc4ee7a9fa61023049b3d6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001701320_435552256.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72ce4d8e6341ca625e36bf06774da6d29808f7ace917c280920913d5239f793f +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001714056_438812672.pth b/checkpoint_p1/milestones/checkpoint_001714056_438812672.pth new file mode 100644 index 0000000000000000000000000000000000000000..ad947dac41449d043686788453cfc314c0ea83fb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001714056_438812672.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:356ff4c5f432860d244e008314fc222b6ccc8ce92429eae00a621de5e0d973fc +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001726760_442064896.pth b/checkpoint_p1/milestones/checkpoint_001726760_442064896.pth new file mode 100644 index 0000000000000000000000000000000000000000..f0714d81db5ea89a2088ebbeb6a2a1e3523ea3bb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001726760_442064896.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:586f40933a475580be1c7765992debe27d8c93c39a7c0dd4698164e2e5a7f074 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001739400_445300736.pth b/checkpoint_p1/milestones/checkpoint_001739400_445300736.pth new file mode 100644 index 0000000000000000000000000000000000000000..42eefeb9ed68d0ae93dd8e7f644d35baaca83adc --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001739400_445300736.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f14eb4902df792fd85dfa8ac3d4f981ec38d51973df1806fe5e3f69499c3818 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001752200_448577536.pth b/checkpoint_p1/milestones/checkpoint_001752200_448577536.pth new file mode 100644 index 0000000000000000000000000000000000000000..22956cd7d3e1c6842465fadd31d12492b1662f5b --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001752200_448577536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0304566920bd7a1f1e77166c71318525eb2dc9de97b084178d481d4a298cc6e4 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001764904_451829760.pth b/checkpoint_p1/milestones/checkpoint_001764904_451829760.pth new file mode 100644 index 0000000000000000000000000000000000000000..583bcd6aa721a300ad25ef5a0e842d23eb6f0e0c --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001764904_451829760.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0aa2af5c6a39568f3ca7f2652941a7cd2f7f321b41a3227f78758e05aae7c4b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001777672_455098368.pth b/checkpoint_p1/milestones/checkpoint_001777672_455098368.pth new file mode 100644 index 0000000000000000000000000000000000000000..54a9d59e72bf207edd662435ae257acbf34e29cb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001777672_455098368.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d2b5477069a1043f3bb1f937152c1a6dbd4de38687a40b3fcd260197639203b +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001790408_458358784.pth b/checkpoint_p1/milestones/checkpoint_001790408_458358784.pth new file mode 100644 index 0000000000000000000000000000000000000000..f18be60be9c93cbc66296a4676c56281eeabd5f2 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001790408_458358784.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8475a93c2106c19adb8501d0e0be49535d94e0ffeb3438617b5381be2f1b8c +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001802888_461553664.pth b/checkpoint_p1/milestones/checkpoint_001802888_461553664.pth new file mode 100644 index 0000000000000000000000000000000000000000..573c93ee44c34ff939e674d6934da7f4addec553 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001802888_461553664.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ada22f9558ddaf1daee445b191127242ddcaec56f567dbab94c1a41aa4d15f81 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001815496_464781312.pth b/checkpoint_p1/milestones/checkpoint_001815496_464781312.pth new file mode 100644 index 0000000000000000000000000000000000000000..ce71d230e9c4953534c1c7307b43ed6e00c2f783 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001815496_464781312.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc59f393d402fae35c730621e539d5c4632fa8dee0e61c551204c5820eeff47d +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001828200_468033536.pth b/checkpoint_p1/milestones/checkpoint_001828200_468033536.pth new file mode 100644 index 0000000000000000000000000000000000000000..4dcf7d3bf853b087ae090d9f9abf9eb375aff418 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001828200_468033536.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8db444279f4d3852a8fe69680c926edc26e12e3e02fb1fba11e78dff5025b585 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001840872_471277568.pth b/checkpoint_p1/milestones/checkpoint_001840872_471277568.pth new file mode 100644 index 0000000000000000000000000000000000000000..ac4d383ed3fc0e231dcab6ec0909e5fa406c88aa --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001840872_471277568.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:962d774709f23c66062ec0cb0d966afffc52389a100485160d295b80cd026578 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001853640_474546176.pth b/checkpoint_p1/milestones/checkpoint_001853640_474546176.pth new file mode 100644 index 0000000000000000000000000000000000000000..b0f118395796cbb89957468a9d74b504f9c05f41 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001853640_474546176.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ffa9195cee5c52bf683e2b1beae6b7fdff633ba19b7fff70ffc8d5b9a0bd322 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001866312_477790208.pth b/checkpoint_p1/milestones/checkpoint_001866312_477790208.pth new file mode 100644 index 0000000000000000000000000000000000000000..641ab1fd5ec3d938bbd71d0678ff62ab10ddc0c8 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001866312_477790208.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:769af6c3e9070d0ffd1406af14bc8108b6d4dbc5ef4f1ad1d90f1098acdfe02d +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001879016_481042432.pth b/checkpoint_p1/milestones/checkpoint_001879016_481042432.pth new file mode 100644 index 0000000000000000000000000000000000000000..cc5afe11f4f118615a554de02e60c2329c03d3f7 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001879016_481042432.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f94f7783d563b49e4dee645e13f99ff6a57015ad900582c9581f67a3c658bab1 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001891720_484294656.pth b/checkpoint_p1/milestones/checkpoint_001891720_484294656.pth new file mode 100644 index 0000000000000000000000000000000000000000..5befae2ecd42e52b18e99d131201affd2a7edb78 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001891720_484294656.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdd2a8fee5c216225a3ecf5decd1e15454b7a875f341094c5977bf1f419f0a5f +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001904424_487546880.pth b/checkpoint_p1/milestones/checkpoint_001904424_487546880.pth new file mode 100644 index 0000000000000000000000000000000000000000..c289983061eca4ad7b3398d35b6e69468d36c5eb --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001904424_487546880.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f67f9e0c9297c6d9a4256846314bc7414a3c51c6f7e735a2e839c5cac725e8a +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001917128_490799104.pth b/checkpoint_p1/milestones/checkpoint_001917128_490799104.pth new file mode 100644 index 0000000000000000000000000000000000000000..853336339099fb72c842cc75c62f991ee361e8c6 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001917128_490799104.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a6513b5e2b481a0010f21f9f0d6517b732f4ea27046ca803b4c325ba9385a02 +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001929896_494067712.pth b/checkpoint_p1/milestones/checkpoint_001929896_494067712.pth new file mode 100644 index 0000000000000000000000000000000000000000..a1e7ec7d743d5d7dccd4f2842aef7540bab2bbf1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001929896_494067712.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b5c6dc11740d4418684d578922997691f130199f01bd2ba4173dd32162c94e +size 20704843 diff --git a/checkpoint_p1/milestones/checkpoint_001942600_497319936.pth b/checkpoint_p1/milestones/checkpoint_001942600_497319936.pth new file mode 100644 index 0000000000000000000000000000000000000000..64b9e43ba58d3f33ce0c7f2c2060baf83c4907e1 --- /dev/null +++ b/checkpoint_p1/milestones/checkpoint_001942600_497319936.pth @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9eaf015d11a0c548d07b29af30ef37513a8f736dee3f0f411762f183b9adb73 +size 20704843 diff --git a/replay.mp4 b/replay.mp4 index 99d337c82bc9a48eed932fa9e610e03b8f46878b..e33c0939329a1f1e4ad53a63963211d8927510dc 100644 --- a/replay.mp4 +++ b/replay.mp4 @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:41b08e1973ca584b3541bb7c90fe8a0d364f801d55327993a5215d1f72daff62 -size 1208619 +oid sha256:86a03b653de5398c9d1f0b0e177cd5e1e41fcd931f6e601a7e259f1ce373e30d +size 1130191 diff --git a/sf_log.txt b/sf_log.txt index e676f3f9c75ad7dc9a248e5741ded006b70c6806..b52d3fd4c3c77ded0a810427b13150a6d6541763 100644 --- a/sf_log.txt +++ b/sf_log.txt @@ -1,98507 +1,3 @@ -[2023-11-28 00:12:22,889][86177] Saving configuration to ./train_atari/atari_skiing_APPO/config.json... -[2023-11-28 00:12:23,891][86177] Rollout worker 0 uses device cpu -[2023-11-28 00:12:23,891][86177] Rollout worker 1 uses device cpu -[2023-11-28 00:12:23,892][86177] Rollout worker 2 uses device cpu -[2023-11-28 00:12:23,893][86177] Rollout worker 3 uses device cpu -[2023-11-28 00:12:23,893][86177] Rollout worker 4 uses device cpu -[2023-11-28 00:12:23,894][86177] Rollout worker 5 uses device cpu -[2023-11-28 00:12:23,894][86177] Rollout worker 6 uses device cpu -[2023-11-28 00:12:23,894][86177] Rollout worker 7 uses device cpu -[2023-11-28 00:12:23,895][86177] Rollout worker 8 uses device cpu -[2023-11-28 00:12:23,895][86177] Rollout worker 9 uses device cpu -[2023-11-28 00:12:23,896][86177] Rollout worker 10 uses device cpu -[2023-11-28 00:12:23,896][86177] Rollout worker 11 uses device cpu -[2023-11-28 00:12:23,897][86177] Rollout worker 12 uses device cpu -[2023-11-28 00:12:23,897][86177] Rollout worker 13 uses device cpu -[2023-11-28 00:12:23,897][86177] Rollout worker 14 uses device cpu -[2023-11-28 00:12:23,898][86177] Rollout worker 15 uses device cpu -[2023-11-28 00:12:24,191][86177] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-11-28 00:12:24,192][86177] InferenceWorker_p0-w0: min num requests: 2 -[2023-11-28 00:12:24,195][86177] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-11-28 00:12:24,195][86177] InferenceWorker_p1-w0: min num requests: 2 -[2023-11-28 00:12:24,245][86177] Starting all processes... -[2023-11-28 00:12:24,245][86177] Starting process learner_proc0 -[2023-11-28 00:12:26,001][86177] Starting process learner_proc1 -[2023-11-28 00:12:26,004][87281] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-11-28 00:12:26,004][87281] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 -[2023-11-28 00:12:26,045][87281] Num visible devices: 1 -[2023-11-28 00:12:26,061][87281] Setting fixed seed 1234 -[2023-11-28 00:12:26,063][87281] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-11-28 00:12:26,063][87281] Initializing actor-critic model on device cuda:0 -[2023-11-28 00:12:26,064][87281] RunningMeanStd input shape: (4, 84, 84) -[2023-11-28 00:12:26,064][87281] RunningMeanStd input shape: (1,) -[2023-11-28 00:12:26,081][87281] ConvEncoder: input_channels=4 -[2023-11-28 00:12:26,229][87281] Conv encoder output size: 512 -[2023-11-28 00:12:26,231][87281] Created Actor Critic model with architecture: -[2023-11-28 00:12:26,231][87281] ActorCriticSharedWeights( - (obs_normalizer): ObservationNormalizer( - (running_mean_std): RunningMeanStdDictInPlace( - (running_mean_std): ModuleDict( - (obs): RunningMeanStdInPlace() - ) - ) - ) - (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) - (encoder): MultiInputEncoder( - (encoders): ModuleDict( - (obs): ConvEncoder( - (enc): RecursiveScriptModule( - original_name=ConvEncoderImpl - (conv_head): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Conv2d) - (1): RecursiveScriptModule(original_name=ReLU) - (2): RecursiveScriptModule(original_name=Conv2d) - (3): RecursiveScriptModule(original_name=ReLU) - (4): RecursiveScriptModule(original_name=Conv2d) - (5): RecursiveScriptModule(original_name=ReLU) - ) - (mlp_layers): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Linear) - (1): RecursiveScriptModule(original_name=ReLU) - ) - ) - ) - ) - ) - (core): ModelCoreIdentity() - (decoder): MlpDecoder( - (mlp): Identity() - ) - (critic_linear): Linear(in_features=512, out_features=1, bias=True) - (action_parameterization): ActionParameterizationDefault( - (distribution_linear): Linear(in_features=512, out_features=3, bias=True) - ) -) -[2023-11-28 00:12:26,822][87281] Using optimizer -[2023-11-28 00:12:26,823][87281] No checkpoints found -[2023-11-28 00:12:26,823][87281] Did not load from checkpoint, starting from scratch! -[2023-11-28 00:12:26,823][87281] Initialized policy 0 weights for model version 0 -[2023-11-28 00:12:26,825][87281] LearnerWorker_p0 finished initialization! -[2023-11-28 00:12:26,826][87281] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-11-28 00:12:27,801][86177] Starting all processes... -[2023-11-28 00:12:27,805][87320] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-11-28 00:12:27,805][87320] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for learning process 1 -[2023-11-28 00:12:27,810][86177] Starting process inference_proc0-0 -[2023-11-28 00:12:27,811][86177] Starting process inference_proc1-0 -[2023-11-28 00:12:27,811][86177] Starting process rollout_proc0 -[2023-11-28 00:12:27,811][86177] Starting process rollout_proc1 -[2023-11-28 00:12:27,811][86177] Starting process rollout_proc2 -[2023-11-28 00:12:27,812][86177] Starting process rollout_proc3 -[2023-11-28 00:12:27,812][86177] Starting process rollout_proc4 -[2023-11-28 00:12:27,812][86177] Starting process rollout_proc5 -[2023-11-28 00:12:27,818][86177] Starting process rollout_proc6 -[2023-11-28 00:12:27,819][86177] Starting process rollout_proc7 -[2023-11-28 00:12:27,858][87320] Num visible devices: 1 -[2023-11-28 00:12:27,819][86177] Starting process rollout_proc8 -[2023-11-28 00:12:27,824][86177] Starting process rollout_proc9 -[2023-11-28 00:12:27,825][86177] Starting process rollout_proc10 -[2023-11-28 00:12:27,828][86177] Starting process rollout_proc11 -[2023-11-28 00:12:27,882][87320] Setting fixed seed 1234 -[2023-11-28 00:12:27,831][86177] Starting process rollout_proc12 -[2023-11-28 00:12:27,883][87320] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-11-28 00:12:27,884][87320] Initializing actor-critic model on device cuda:0 -[2023-11-28 00:12:27,884][87320] RunningMeanStd input shape: (4, 84, 84) -[2023-11-28 00:12:27,885][87320] RunningMeanStd input shape: (1,) -[2023-11-28 00:12:27,834][86177] Starting process rollout_proc13 -[2023-11-28 00:12:27,914][87320] ConvEncoder: input_channels=4 -[2023-11-28 00:12:28,455][87320] Conv encoder output size: 512 -[2023-11-28 00:12:28,457][87320] Created Actor Critic model with architecture: -[2023-11-28 00:12:28,458][87320] ActorCriticSharedWeights( - (obs_normalizer): ObservationNormalizer( - (running_mean_std): RunningMeanStdDictInPlace( - (running_mean_std): ModuleDict( - (obs): RunningMeanStdInPlace() - ) - ) - ) - (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) - (encoder): MultiInputEncoder( - (encoders): ModuleDict( - (obs): ConvEncoder( - (enc): RecursiveScriptModule( - original_name=ConvEncoderImpl - (conv_head): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Conv2d) - (1): RecursiveScriptModule(original_name=ReLU) - (2): RecursiveScriptModule(original_name=Conv2d) - (3): RecursiveScriptModule(original_name=ReLU) - (4): RecursiveScriptModule(original_name=Conv2d) - (5): RecursiveScriptModule(original_name=ReLU) - ) - (mlp_layers): RecursiveScriptModule( - original_name=Sequential - (0): RecursiveScriptModule(original_name=Linear) - (1): RecursiveScriptModule(original_name=ReLU) - ) - ) - ) - ) - ) - (core): ModelCoreIdentity() - (decoder): MlpDecoder( - (mlp): Identity() - ) - (critic_linear): Linear(in_features=512, out_features=1, bias=True) - (action_parameterization): ActionParameterizationDefault( - (distribution_linear): Linear(in_features=512, out_features=3, bias=True) - ) -) -[2023-11-28 00:12:29,308][87320] Using optimizer -[2023-11-28 00:12:29,309][87320] No checkpoints found -[2023-11-28 00:12:29,309][87320] Did not load from checkpoint, starting from scratch! -[2023-11-28 00:12:29,309][87320] Initialized policy 1 weights for model version 0 -[2023-11-28 00:12:29,312][87320] LearnerWorker_p1 finished initialization! -[2023-11-28 00:12:29,312][87320] Using GPUs [0] for process 1 (actually maps to GPUs [1]) -[2023-11-28 00:12:30,176][86177] Starting process rollout_proc14 -[2023-11-28 00:12:30,184][87430] Worker 2 uses CPU cores [4, 5] -[2023-11-28 00:12:30,195][86177] Starting process rollout_proc15 -[2023-11-28 00:12:30,200][87448] Worker 6 uses CPU cores [12, 13] -[2023-11-28 00:12:30,223][87434] Worker 4 uses CPU cores [8, 9] -[2023-11-28 00:12:30,232][87428] Worker 1 uses CPU cores [2, 3] -[2023-11-28 00:12:30,428][87427] Worker 0 uses CPU cores [0, 1] -[2023-11-28 00:12:30,540][87426] Using GPUs [1] for process 1 (actually maps to GPUs [1]) -[2023-11-28 00:12:30,540][87426] Set environment var CUDA_VISIBLE_DEVICES to '1' (GPU indices [1]) for inference process 1 -[2023-11-28 00:12:30,552][87506] Worker 12 uses CPU cores [24, 25] -[2023-11-28 00:12:30,585][87426] Num visible devices: 1 -[2023-11-28 00:12:30,608][87505] Worker 11 uses CPU cores [22, 23] -[2023-11-28 00:12:30,617][87431] Worker 5 uses CPU cores [10, 11] -[2023-11-28 00:12:30,633][87471] Worker 9 uses CPU cores [18, 19] -[2023-11-28 00:12:30,664][87504] Worker 13 uses CPU cores [26, 27] -[2023-11-28 00:12:30,718][87468] Worker 7 uses CPU cores [14, 15] -[2023-11-28 00:12:30,804][87472] Worker 10 uses CPU cores [20, 21] -[2023-11-28 00:12:30,852][87424] Using GPUs [0] for process 0 (actually maps to GPUs [0]) -[2023-11-28 00:12:30,853][87424] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 -[2023-11-28 00:12:30,900][87424] Num visible devices: 1 -[2023-11-28 00:12:31,000][87432] Worker 3 uses CPU cores [6, 7] -[2023-11-28 00:12:31,114][87469] Worker 8 uses CPU cores [16, 17] -[2023-11-28 00:12:31,209][87426] RunningMeanStd input shape: (4, 84, 84) -[2023-11-28 00:12:31,209][87426] RunningMeanStd input shape: (1,) -[2023-11-28 00:12:31,222][87426] ConvEncoder: input_channels=4 -[2023-11-28 00:12:31,327][87426] Conv encoder output size: 512 -[2023-11-28 00:12:31,531][87424] RunningMeanStd input shape: (4, 84, 84) -[2023-11-28 00:12:31,531][87424] RunningMeanStd input shape: (1,) -[2023-11-28 00:12:31,544][87424] ConvEncoder: input_channels=4 -[2023-11-28 00:12:31,667][87424] Conv encoder output size: 512 -[2023-11-28 00:12:32,103][88215] Worker 14 uses CPU cores [28, 29] -[2023-11-28 00:12:32,218][88248] Worker 15 uses CPU cores [30, 31] -[2023-11-28 00:12:32,220][86177] Inference worker 1-0 is ready! -[2023-11-28 00:12:32,225][86177] Inference worker 0-0 is ready! -[2023-11-28 00:12:32,226][86177] All inference workers are ready! Signal rollout workers to start! -[2023-11-28 00:12:32,226][87448] EnvRunner 6-0 uses policy 0 -[2023-11-28 00:12:32,227][87472] EnvRunner 10-0 uses policy 0 -[2023-11-28 00:12:32,227][87427] EnvRunner 0-0 uses policy 0 -[2023-11-28 00:12:32,227][87468] EnvRunner 7-0 uses policy 1 -[2023-11-28 00:12:32,227][87506] EnvRunner 12-0 uses policy 0 -[2023-11-28 00:12:32,227][87430] EnvRunner 2-0 uses policy 0 -[2023-11-28 00:12:32,227][87434] EnvRunner 4-0 uses policy 0 -[2023-11-28 00:12:32,227][87428] EnvRunner 1-0 uses policy 1 -[2023-11-28 00:12:32,227][87504] EnvRunner 13-0 uses policy 1 -[2023-11-28 00:12:32,227][87471] EnvRunner 9-0 uses policy 1 -[2023-11-28 00:12:32,227][87432] EnvRunner 3-0 uses policy 1 -[2023-11-28 00:12:32,227][87469] EnvRunner 8-0 uses policy 0 -[2023-11-28 00:12:32,227][87505] EnvRunner 11-0 uses policy 1 -[2023-11-28 00:12:32,227][86177] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan, 1: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-11-28 00:12:32,228][87431] EnvRunner 5-0 uses policy 1 -[2023-11-28 00:12:32,329][88215] EnvRunner 14-0 uses policy 0 -[2023-11-28 00:12:32,433][88248] EnvRunner 15-0 uses policy 1 -[2023-11-28 00:12:33,444][86177] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0, 1: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-11-28 00:12:33,900][87448] EnvRunner 6-1 uses policy 0 -[2023-11-28 00:12:33,926][87471] EnvRunner 9-1 uses policy 1 -[2023-11-28 00:12:33,971][87472] EnvRunner 10-1 uses policy 0 -[2023-11-28 00:12:34,008][88215] EnvRunner 14-1 uses policy 0 -[2023-11-28 00:12:34,178][86177] Heartbeat connected on Batcher_0 -[2023-11-28 00:12:34,181][86177] Heartbeat connected on LearnerWorker_p0 -[2023-11-28 00:12:34,185][86177] Heartbeat connected on Batcher_1 -[2023-11-28 00:12:34,187][86177] Heartbeat connected on LearnerWorker_p1 -[2023-11-28 00:12:34,235][86177] Heartbeat connected on InferenceWorker_p1-w0 -[2023-11-28 00:12:34,236][86177] Heartbeat connected on InferenceWorker_p0-w0 -[2023-11-28 00:12:34,516][87430] EnvRunner 2-1 uses policy 0 -[2023-11-28 00:12:34,711][87428] EnvRunner 1-1 uses policy 1 -[2023-11-28 00:12:34,887][87469] EnvRunner 8-1 uses policy 0 -[2023-11-28 00:12:34,902][87427] EnvRunner 0-1 uses policy 0 -[2023-11-28 00:12:35,147][87468] EnvRunner 7-1 uses policy 1 -[2023-11-28 00:12:35,228][87431] EnvRunner 5-1 uses policy 1 -[2023-11-28 00:12:35,231][87506] EnvRunner 12-1 uses policy 0 -[2023-11-28 00:12:35,233][87504] EnvRunner 13-1 uses policy 1 -[2023-11-28 00:12:35,234][87432] EnvRunner 3-1 uses policy 1 -[2023-11-28 00:12:35,235][87434] EnvRunner 4-1 uses policy 0 -[2023-11-28 00:12:35,261][87505] EnvRunner 11-1 uses policy 1 -[2023-11-28 00:12:35,449][88248] EnvRunner 15-1 uses policy 1 -[2023-11-28 00:12:35,479][86177] Heartbeat connected on RolloutWorker_w6 -[2023-11-28 00:12:35,511][86177] Heartbeat connected on RolloutWorker_w9 -[2023-11-28 00:12:35,613][86177] Heartbeat connected on RolloutWorker_w14 -[2023-11-28 00:12:35,647][86177] Heartbeat connected on RolloutWorker_w10 -[2023-11-28 00:12:36,451][86177] Heartbeat connected on RolloutWorker_w2 -[2023-11-28 00:12:36,453][86177] Heartbeat connected on RolloutWorker_w8 -[2023-11-28 00:12:36,479][86177] Heartbeat connected on RolloutWorker_w0 -[2023-11-28 00:12:37,080][86177] Heartbeat connected on RolloutWorker_w1 -[2023-11-28 00:12:38,062][86177] Heartbeat connected on RolloutWorker_w7 -[2023-11-28 00:12:38,129][86177] Heartbeat connected on RolloutWorker_w5 -[2023-11-28 00:12:38,132][86177] Heartbeat connected on RolloutWorker_w4 -[2023-11-28 00:12:38,139][86177] Heartbeat connected on RolloutWorker_w3 -[2023-11-28 00:12:38,141][86177] Heartbeat connected on RolloutWorker_w13 -[2023-11-28 00:12:38,149][86177] Heartbeat connected on RolloutWorker_w12 -[2023-11-28 00:12:38,192][86177] Heartbeat connected on RolloutWorker_w11 -[2023-11-28 00:12:38,314][86177] Heartbeat connected on RolloutWorker_w15 -[2023-11-28 00:12:38,444][86177] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 642.7, 1: 86.2. Samples: 4532. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-11-28 00:12:43,445][86177] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 1195.6, 1: 1372.9. Samples: 28812. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) -[2023-11-28 00:12:44,152][87281] Signal inference workers to stop experience collection... -[2023-11-28 00:12:44,157][87424] InferenceWorker_p0-w0: stopping experience collection -[2023-11-28 00:12:44,170][87426] InferenceWorker_p1-w0: stopping experience collection -[2023-11-28 00:12:45,720][87281] Signal inference workers to resume experience collection... -[2023-11-28 00:12:45,721][87426] InferenceWorker_p1-w0: resuming experience collection -[2023-11-28 00:12:45,721][87424] InferenceWorker_p0-w0: resuming experience collection -[2023-11-28 00:12:46,150][87426] Updated weights for policy 1, policy_version 16 (0.0009) -[2023-11-28 00:12:46,529][87426] Updated weights for policy 1, policy_version 26 (0.0008) -[2023-11-28 00:12:46,805][87320] Signal inference workers to stop experience collection... -[2023-11-28 00:12:46,806][87320] Signal inference workers to resume experience collection... -[2023-11-28 00:12:47,223][87424] Updated weights for policy 0, policy_version 40 (0.0460) -[2023-11-28 00:12:47,596][87424] Updated weights for policy 0, policy_version 50 (0.0009) -[2023-11-28 00:12:47,968][87424] Updated weights for policy 0, policy_version 60 (0.0012) -[2023-11-28 00:12:48,444][86177] Fps is (10 sec: 2457.6, 60 sec: 1515.4, 300 sec: 1515.4). Total num frames: 24576. Throughput: 0: 1478.2, 1: 1148.2. Samples: 42592. Policy #0 lag: (min: 21.0, avg: 21.0, max: 21.0) -[2023-11-28 00:12:48,471][87426] Updated weights for policy 1, policy_version 36 (0.0011) -[2023-11-28 00:12:48,845][87426] Updated weights for policy 1, policy_version 46 (0.0009) -[2023-11-28 00:12:49,304][87426] Updated weights for policy 1, policy_version 58 (0.0008) -[2023-11-28 00:12:49,480][87424] Updated weights for policy 0, policy_version 72 (0.0010) -[2023-11-28 00:12:49,856][87424] Updated weights for policy 0, policy_version 82 (0.0008) -[2023-11-28 00:12:50,248][87424] Updated weights for policy 0, policy_version 92 (0.0008) -[2023-11-28 00:12:50,625][87426] Updated weights for policy 1, policy_version 68 (0.0008) -[2023-11-28 00:12:50,998][87426] Updated weights for policy 1, policy_version 78 (0.0011) -[2023-11-28 00:12:51,384][87426] Updated weights for policy 1, policy_version 88 (0.0008) -[2023-11-28 00:12:52,045][87424] Updated weights for policy 0, policy_version 102 (0.0011) -[2023-11-28 00:12:52,416][87424] Updated weights for policy 0, policy_version 112 (0.0012) -[2023-11-28 00:12:52,801][87424] Updated weights for policy 0, policy_version 122 (0.0012) -[2023-11-28 00:12:53,263][87426] Updated weights for policy 1, policy_version 100 (0.0009) -[2023-11-28 00:12:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 2702.7, 300 sec: 2702.7). Total num frames: 57344. Throughput: 0: 1867.7, 1: 1598.7. Samples: 73548. Policy #0 lag: (min: 31.0, avg: 55.2, max: 95.0) -[2023-11-28 00:12:53,445][86177] Avg episode reward: [(0, '-719.000')] -[2023-11-28 00:12:53,631][87426] Updated weights for policy 1, policy_version 110 (0.0011) -[2023-11-28 00:12:54,002][87426] Updated weights for policy 1, policy_version 120 (0.0010) -[2023-11-28 00:12:54,997][87424] Updated weights for policy 0, policy_version 132 (0.0012) -[2023-11-28 00:12:55,379][87424] Updated weights for policy 0, policy_version 142 (0.0012) -[2023-11-28 00:12:55,837][87424] Updated weights for policy 0, policy_version 154 (0.0012) -[2023-11-28 00:12:55,858][87426] Updated weights for policy 1, policy_version 130 (0.0012) -[2023-11-28 00:12:56,238][87426] Updated weights for policy 1, policy_version 140 (0.0012) -[2023-11-28 00:12:56,605][87426] Updated weights for policy 1, policy_version 150 (0.0012) -[2023-11-28 00:12:56,976][87426] Updated weights for policy 1, policy_version 160 (0.0012) -[2023-11-28 00:12:58,383][87424] Updated weights for policy 0, policy_version 164 (0.0010) -[2023-11-28 00:12:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 3124.7, 300 sec: 3124.7). Total num frames: 81920. Throughput: 0: 1804.0, 1: 2003.6. Samples: 99824. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 00:12:58,445][86177] Avg episode reward: [(0, '-791.000')] -[2023-11-28 00:12:58,762][87424] Updated weights for policy 0, policy_version 174 (0.0009) -[2023-11-28 00:12:58,915][87426] Updated weights for policy 1, policy_version 170 (0.0011) -[2023-11-28 00:12:59,144][87424] Updated weights for policy 0, policy_version 184 (0.0008) -[2023-11-28 00:12:59,290][87426] Updated weights for policy 1, policy_version 180 (0.0011) -[2023-11-28 00:12:59,656][87426] Updated weights for policy 1, policy_version 190 (0.0012) -[2023-11-28 00:13:01,277][87424] Updated weights for policy 0, policy_version 194 (0.0008) -[2023-11-28 00:13:01,650][87424] Updated weights for policy 0, policy_version 204 (0.0008) -[2023-11-28 00:13:02,038][87424] Updated weights for policy 0, policy_version 214 (0.0010) -[2023-11-28 00:13:02,137][87426] Updated weights for policy 1, policy_version 200 (0.0009) -[2023-11-28 00:13:02,410][87424] Updated weights for policy 0, policy_version 224 (0.0011) -[2023-11-28 00:13:02,515][87426] Updated weights for policy 1, policy_version 210 (0.0011) -[2023-11-28 00:13:02,886][87426] Updated weights for policy 1, policy_version 220 (0.0012) -[2023-11-28 00:13:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 3673.9, 300 sec: 3673.9). Total num frames: 114688. Throughput: 0: 2054.4, 1: 1940.9. Samples: 124720. Policy #0 lag: (min: 31.0, avg: 31.0, max: 31.0) -[2023-11-28 00:13:03,445][86177] Avg episode reward: [(0, '-978.529'), (1, '-987.714')] -[2023-11-28 00:13:04,555][87424] Updated weights for policy 0, policy_version 234 (0.0012) -[2023-11-28 00:13:04,641][87426] Updated weights for policy 1, policy_version 230 (0.0012) -[2023-11-28 00:13:04,932][87424] Updated weights for policy 0, policy_version 244 (0.0010) -[2023-11-28 00:13:05,012][87426] Updated weights for policy 1, policy_version 240 (0.0012) -[2023-11-28 00:13:05,310][87424] Updated weights for policy 0, policy_version 254 (0.0010) -[2023-11-28 00:13:05,383][87426] Updated weights for policy 1, policy_version 250 (0.0010) -[2023-11-28 00:13:07,401][87426] Updated weights for policy 1, policy_version 260 (0.0010) -[2023-11-28 00:13:07,484][87424] Updated weights for policy 0, policy_version 264 (0.0011) -[2023-11-28 00:13:07,780][87426] Updated weights for policy 1, policy_version 270 (0.0011) -[2023-11-28 00:13:07,851][87424] Updated weights for policy 0, policy_version 274 (0.0011) -[2023-11-28 00:13:08,161][87426] Updated weights for policy 1, policy_version 280 (0.0011) -[2023-11-28 00:13:08,234][87424] Updated weights for policy 0, policy_version 284 (0.0012) -[2023-11-28 00:13:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 3845.2, 300 sec: 3845.2). Total num frames: 139264. Throughput: 0: 2228.0, 1: 2152.1. Samples: 158636. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 00:13:08,445][86177] Avg episode reward: [(0, '-1098.250'), (1, '-1091.911')] -[2023-11-28 00:13:10,069][87424] Updated weights for policy 0, policy_version 294 (0.0010) -[2023-11-28 00:13:10,452][87424] Updated weights for policy 0, policy_version 304 (0.0009) -[2023-11-28 00:13:10,538][87426] Updated weights for policy 1, policy_version 290 (0.0011) -[2023-11-28 00:13:10,839][87424] Updated weights for policy 0, policy_version 314 (0.0010) -[2023-11-28 00:13:10,906][87426] Updated weights for policy 1, policy_version 300 (0.0011) -[2023-11-28 00:13:11,279][87426] Updated weights for policy 1, policy_version 310 (0.0011) -[2023-11-28 00:13:11,660][87426] Updated weights for policy 1, policy_version 320 (0.0012) -[2023-11-28 00:13:12,870][87424] Updated weights for policy 0, policy_version 324 (0.0011) -[2023-11-28 00:13:13,251][87424] Updated weights for policy 0, policy_version 334 (0.0016) -[2023-11-28 00:13:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 3975.0, 300 sec: 3975.0). Total num frames: 163840. Throughput: 0: 2157.6, 1: 2307.7. Samples: 184048. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 00:13:13,445][86177] Avg episode reward: [(0, '-1155.268'), (1, '-1158.548')] -[2023-11-28 00:13:13,624][87424] Updated weights for policy 0, policy_version 344 (0.0012) -[2023-11-28 00:13:13,726][87426] Updated weights for policy 1, policy_version 330 (0.0012) -[2023-11-28 00:13:14,100][87426] Updated weights for policy 1, policy_version 340 (0.0012) -[2023-11-28 00:13:14,475][87426] Updated weights for policy 1, policy_version 350 (0.0011) -[2023-11-28 00:13:15,738][87424] Updated weights for policy 0, policy_version 354 (0.0012) -[2023-11-28 00:13:16,125][87424] Updated weights for policy 0, policy_version 364 (0.0011) -[2023-11-28 00:13:16,363][87426] Updated weights for policy 1, policy_version 360 (0.0009) -[2023-11-28 00:13:16,500][87424] Updated weights for policy 0, policy_version 374 (0.0011) -[2023-11-28 00:13:16,733][87426] Updated weights for policy 1, policy_version 370 (0.0007) -[2023-11-28 00:13:16,866][87424] Updated weights for policy 0, policy_version 384 (0.0008) -[2023-11-28 00:13:17,110][87426] Updated weights for policy 1, policy_version 380 (0.0007) -[2023-11-28 00:13:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 4254.0, 300 sec: 4254.0). Total num frames: 196608. Throughput: 0: 2324.5, 1: 2300.4. Samples: 208116. Policy #0 lag: (min: 32.0, avg: 56.0, max: 73.0) -[2023-11-28 00:13:18,445][86177] Avg episode reward: [(0, '-1196.855'), (1, '-1170.078')] -[2023-11-28 00:13:19,369][87424] Updated weights for policy 0, policy_version 394 (0.0012) -[2023-11-28 00:13:19,399][87426] Updated weights for policy 1, policy_version 390 (0.0008) -[2023-11-28 00:13:19,746][87424] Updated weights for policy 0, policy_version 404 (0.0011) -[2023-11-28 00:13:19,768][87426] Updated weights for policy 1, policy_version 400 (0.0011) -[2023-11-28 00:13:20,129][87424] Updated weights for policy 0, policy_version 414 (0.0010) -[2023-11-28 00:13:20,138][87426] Updated weights for policy 1, policy_version 410 (0.0010) -[2023-11-28 00:13:22,419][87426] Updated weights for policy 1, policy_version 420 (0.0011) -[2023-11-28 00:13:22,457][87424] Updated weights for policy 0, policy_version 424 (0.0009) -[2023-11-28 00:13:22,798][87426] Updated weights for policy 1, policy_version 430 (0.0012) -[2023-11-28 00:13:22,838][87424] Updated weights for policy 0, policy_version 434 (0.0008) -[2023-11-28 00:13:23,181][87426] Updated weights for policy 1, policy_version 440 (0.0012) -[2023-11-28 00:13:23,203][87424] Updated weights for policy 0, policy_version 444 (0.0010) -[2023-11-28 00:13:23,445][86177] Fps is (10 sec: 5734.2, 60 sec: 4318.5, 300 sec: 4318.5). Total num frames: 221184. Throughput: 0: 2588.2, 1: 2646.7. Samples: 240108. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:13:23,446][86177] Avg episode reward: [(0, '-1208.892'), (1, '-1153.362')] -[2023-11-28 00:13:23,448][87281] Saving new best policy, reward=-1208.892! -[2023-11-28 00:13:23,478][87320] Saving new best policy, reward=-1153.362! -[2023-11-28 00:13:25,030][87426] Updated weights for policy 1, policy_version 450 (0.0012) -[2023-11-28 00:13:25,405][87426] Updated weights for policy 1, policy_version 460 (0.0012) -[2023-11-28 00:13:25,542][87424] Updated weights for policy 0, policy_version 454 (0.0008) -[2023-11-28 00:13:25,775][87426] Updated weights for policy 1, policy_version 470 (0.0012) -[2023-11-28 00:13:25,921][87424] Updated weights for policy 0, policy_version 464 (0.0010) -[2023-11-28 00:13:26,162][87426] Updated weights for policy 1, policy_version 480 (0.0012) -[2023-11-28 00:13:26,299][87424] Updated weights for policy 0, policy_version 474 (0.0011) -[2023-11-28 00:13:27,944][87426] Updated weights for policy 1, policy_version 490 (0.0011) -[2023-11-28 00:13:28,319][87426] Updated weights for policy 1, policy_version 500 (0.0012) -[2023-11-28 00:13:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4371.6, 300 sec: 4371.6). Total num frames: 245760. Throughput: 0: 2559.7, 1: 2701.8. Samples: 265580. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:13:28,445][86177] Avg episode reward: [(0, '-1193.452'), (1, '-1133.658')] -[2023-11-28 00:13:28,493][87424] Updated weights for policy 0, policy_version 486 (0.0010) -[2023-11-28 00:13:28,692][87426] Updated weights for policy 1, policy_version 510 (0.0010) -[2023-11-28 00:13:28,764][87320] Saving new best policy, reward=-1133.658! -[2023-11-28 00:13:28,881][87424] Updated weights for policy 0, policy_version 496 (0.0008) -[2023-11-28 00:13:29,256][87424] Updated weights for policy 0, policy_version 506 (0.0008) -[2023-11-28 00:13:29,482][87281] Saving new best policy, reward=-1193.452! -[2023-11-28 00:13:31,147][87426] Updated weights for policy 1, policy_version 520 (0.0010) -[2023-11-28 00:13:31,528][87426] Updated weights for policy 1, policy_version 530 (0.0007) -[2023-11-28 00:13:31,783][87424] Updated weights for policy 0, policy_version 516 (0.0010) -[2023-11-28 00:13:31,899][87426] Updated weights for policy 1, policy_version 540 (0.0010) -[2023-11-28 00:13:32,159][87424] Updated weights for policy 0, policy_version 526 (0.0009) -[2023-11-28 00:13:32,535][87424] Updated weights for policy 0, policy_version 536 (0.0010) -[2023-11-28 00:13:33,444][86177] Fps is (10 sec: 5734.6, 60 sec: 4642.1, 300 sec: 4549.8). Total num frames: 278528. Throughput: 0: 2693.0, 1: 2802.5. Samples: 289888. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) -[2023-11-28 00:13:33,445][86177] Avg episode reward: [(0, '-1189.176'), (1, '-1137.722')] -[2023-11-28 00:13:33,448][87281] Saving new best policy, reward=-1189.176! -[2023-11-28 00:13:34,248][87424] Updated weights for policy 0, policy_version 546 (0.0009) -[2023-11-28 00:13:34,444][87426] Updated weights for policy 1, policy_version 550 (0.0011) -[2023-11-28 00:13:34,631][87424] Updated weights for policy 0, policy_version 556 (0.0007) -[2023-11-28 00:13:34,820][87426] Updated weights for policy 1, policy_version 560 (0.0009) -[2023-11-28 00:13:35,009][87424] Updated weights for policy 0, policy_version 566 (0.0009) -[2023-11-28 00:13:35,206][87426] Updated weights for policy 1, policy_version 570 (0.0010) -[2023-11-28 00:13:35,382][87424] Updated weights for policy 0, policy_version 576 (0.0010) -[2023-11-28 00:13:36,969][87426] Updated weights for policy 1, policy_version 580 (0.0009) -[2023-11-28 00:13:37,343][87426] Updated weights for policy 1, policy_version 590 (0.0009) -[2023-11-28 00:13:37,641][87424] Updated weights for policy 0, policy_version 586 (0.0012) -[2023-11-28 00:13:37,720][87426] Updated weights for policy 1, policy_version 600 (0.0009) -[2023-11-28 00:13:38,019][87424] Updated weights for policy 0, policy_version 596 (0.0011) -[2023-11-28 00:13:38,405][87424] Updated weights for policy 0, policy_version 606 (0.0008) -[2023-11-28 00:13:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5051.7, 300 sec: 4577.4). Total num frames: 303104. Throughput: 0: 2696.8, 1: 2812.3. Samples: 321456. Policy #0 lag: (min: 31.0, avg: 46.4, max: 63.0) -[2023-11-28 00:13:38,445][86177] Avg episode reward: [(0, '-1220.760'), (1, '-1173.660')] -[2023-11-28 00:13:39,720][87426] Updated weights for policy 1, policy_version 610 (0.0008) -[2023-11-28 00:13:40,102][87426] Updated weights for policy 1, policy_version 620 (0.0011) -[2023-11-28 00:13:40,466][87426] Updated weights for policy 1, policy_version 630 (0.0009) -[2023-11-28 00:13:40,506][87424] Updated weights for policy 0, policy_version 616 (0.0009) -[2023-11-28 00:13:40,846][87426] Updated weights for policy 1, policy_version 640 (0.0012) -[2023-11-28 00:13:40,882][87424] Updated weights for policy 0, policy_version 626 (0.0011) -[2023-11-28 00:13:41,268][87424] Updated weights for policy 0, policy_version 636 (0.0007) -[2023-11-28 00:13:43,265][87426] Updated weights for policy 1, policy_version 650 (0.0008) -[2023-11-28 00:13:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 4601.1). Total num frames: 327680. Throughput: 0: 2708.6, 1: 2762.7. Samples: 346032. Policy #0 lag: (min: 24.0, avg: 52.1, max: 81.0) -[2023-11-28 00:13:43,445][86177] Avg episode reward: [(0, '-1245.840'), (1, '-1223.650')] -[2023-11-28 00:13:43,649][87426] Updated weights for policy 1, policy_version 660 (0.0009) -[2023-11-28 00:13:43,773][87424] Updated weights for policy 0, policy_version 646 (0.0010) -[2023-11-28 00:13:44,018][87426] Updated weights for policy 1, policy_version 670 (0.0011) -[2023-11-28 00:13:44,158][87424] Updated weights for policy 0, policy_version 656 (0.0011) -[2023-11-28 00:13:44,541][87424] Updated weights for policy 0, policy_version 666 (0.0010) -[2023-11-28 00:13:45,864][87426] Updated weights for policy 1, policy_version 680 (0.0008) -[2023-11-28 00:13:46,243][87426] Updated weights for policy 1, policy_version 690 (0.0007) -[2023-11-28 00:13:46,457][87424] Updated weights for policy 0, policy_version 676 (0.0010) -[2023-11-28 00:13:46,628][87426] Updated weights for policy 1, policy_version 700 (0.0007) -[2023-11-28 00:13:46,834][87424] Updated weights for policy 0, policy_version 686 (0.0011) -[2023-11-28 00:13:47,215][87424] Updated weights for policy 0, policy_version 696 (0.0011) -[2023-11-28 00:13:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 4729.2). Total num frames: 360448. Throughput: 0: 2712.8, 1: 2760.4. Samples: 371016. Policy #0 lag: (min: 31.0, avg: 49.3, max: 63.0) -[2023-11-28 00:13:48,445][86177] Avg episode reward: [(0, '-1258.220'), (1, '-1241.510')] -[2023-11-28 00:13:48,814][87426] Updated weights for policy 1, policy_version 710 (0.0009) -[2023-11-28 00:13:49,120][87424] Updated weights for policy 0, policy_version 706 (0.0012) -[2023-11-28 00:13:49,204][87426] Updated weights for policy 1, policy_version 720 (0.0011) -[2023-11-28 00:13:49,501][87424] Updated weights for policy 0, policy_version 716 (0.0011) -[2023-11-28 00:13:49,574][87426] Updated weights for policy 1, policy_version 730 (0.0007) -[2023-11-28 00:13:49,881][87424] Updated weights for policy 0, policy_version 726 (0.0011) -[2023-11-28 00:13:50,266][87424] Updated weights for policy 0, policy_version 736 (0.0008) -[2023-11-28 00:13:52,102][87426] Updated weights for policy 1, policy_version 740 (0.0008) -[2023-11-28 00:13:52,349][87424] Updated weights for policy 0, policy_version 746 (0.0011) -[2023-11-28 00:13:52,476][87426] Updated weights for policy 1, policy_version 750 (0.0010) -[2023-11-28 00:13:52,719][87424] Updated weights for policy 0, policy_version 756 (0.0012) -[2023-11-28 00:13:52,852][87426] Updated weights for policy 1, policy_version 760 (0.0008) -[2023-11-28 00:13:53,090][87424] Updated weights for policy 0, policy_version 766 (0.0012) -[2023-11-28 00:13:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 4841.5). Total num frames: 393216. Throughput: 0: 2732.7, 1: 2732.2. Samples: 404556. Policy #0 lag: (min: 31.0, avg: 58.5, max: 72.0) -[2023-11-28 00:13:53,445][86177] Avg episode reward: [(0, '-1269.010'), (1, '-1253.390')] -[2023-11-28 00:13:54,770][87426] Updated weights for policy 1, policy_version 770 (0.0011) -[2023-11-28 00:13:55,063][87424] Updated weights for policy 0, policy_version 776 (0.0008) -[2023-11-28 00:13:55,148][87426] Updated weights for policy 1, policy_version 780 (0.0012) -[2023-11-28 00:13:55,446][87424] Updated weights for policy 0, policy_version 786 (0.0008) -[2023-11-28 00:13:55,522][87426] Updated weights for policy 1, policy_version 790 (0.0007) -[2023-11-28 00:13:55,829][87424] Updated weights for policy 0, policy_version 796 (0.0007) -[2023-11-28 00:13:55,895][87426] Updated weights for policy 1, policy_version 800 (0.0007) -[2023-11-28 00:13:57,615][87424] Updated weights for policy 0, policy_version 806 (0.0010) -[2023-11-28 00:13:57,994][87424] Updated weights for policy 0, policy_version 816 (0.0011) -[2023-11-28 00:13:58,178][87426] Updated weights for policy 1, policy_version 810 (0.0008) -[2023-11-28 00:13:58,375][87424] Updated weights for policy 0, policy_version 826 (0.0012) -[2023-11-28 00:13:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 4750.8). Total num frames: 409600. Throughput: 0: 2734.6, 1: 2726.1. Samples: 429776. Policy #0 lag: (min: 31.0, avg: 58.5, max: 72.0) -[2023-11-28 00:13:58,445][86177] Avg episode reward: [(0, '-1253.830'), (1, '-1247.450')] -[2023-11-28 00:13:58,564][87426] Updated weights for policy 1, policy_version 820 (0.0009) -[2023-11-28 00:13:58,944][87426] Updated weights for policy 1, policy_version 830 (0.0011) -[2023-11-28 00:14:00,728][87424] Updated weights for policy 0, policy_version 836 (0.0010) -[2023-11-28 00:14:01,106][87424] Updated weights for policy 0, policy_version 846 (0.0009) -[2023-11-28 00:14:01,461][87426] Updated weights for policy 1, policy_version 840 (0.0008) -[2023-11-28 00:14:01,479][87424] Updated weights for policy 0, policy_version 856 (0.0009) -[2023-11-28 00:14:01,845][87426] Updated weights for policy 1, policy_version 850 (0.0009) -[2023-11-28 00:14:02,218][87426] Updated weights for policy 1, policy_version 860 (0.0010) -[2023-11-28 00:14:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 4849.6). Total num frames: 442368. Throughput: 0: 2751.0, 1: 2718.6. Samples: 454248. Policy #0 lag: (min: 34.0, avg: 50.4, max: 72.0) -[2023-11-28 00:14:03,445][86177] Avg episode reward: [(0, '-1226.900'), (1, '-1243.530')] -[2023-11-28 00:14:04,034][87424] Updated weights for policy 0, policy_version 866 (0.0011) -[2023-11-28 00:14:04,419][87424] Updated weights for policy 0, policy_version 876 (0.0012) -[2023-11-28 00:14:04,702][87426] Updated weights for policy 1, policy_version 870 (0.0010) -[2023-11-28 00:14:04,803][87424] Updated weights for policy 0, policy_version 886 (0.0012) -[2023-11-28 00:14:05,069][87426] Updated weights for policy 1, policy_version 880 (0.0011) -[2023-11-28 00:14:05,173][87424] Updated weights for policy 0, policy_version 896 (0.0011) -[2023-11-28 00:14:05,454][87426] Updated weights for policy 1, policy_version 890 (0.0012) -[2023-11-28 00:14:07,028][87424] Updated weights for policy 0, policy_version 906 (0.0012) -[2023-11-28 00:14:07,244][87426] Updated weights for policy 1, policy_version 900 (0.0010) -[2023-11-28 00:14:07,408][87424] Updated weights for policy 0, policy_version 916 (0.0011) -[2023-11-28 00:14:07,616][87426] Updated weights for policy 1, policy_version 910 (0.0007) -[2023-11-28 00:14:07,782][87424] Updated weights for policy 0, policy_version 926 (0.0010) -[2023-11-28 00:14:08,000][87426] Updated weights for policy 1, policy_version 920 (0.0008) -[2023-11-28 00:14:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 4938.2). Total num frames: 475136. Throughput: 0: 2768.3, 1: 2727.2. Samples: 487404. Policy #0 lag: (min: 45.0, avg: 50.5, max: 69.0) -[2023-11-28 00:14:08,445][86177] Avg episode reward: [(0, '-1230.570'), (1, '-1240.310')] -[2023-11-28 00:14:09,898][87426] Updated weights for policy 1, policy_version 930 (0.0008) -[2023-11-28 00:14:10,277][87426] Updated weights for policy 1, policy_version 940 (0.0010) -[2023-11-28 00:14:10,320][87424] Updated weights for policy 0, policy_version 936 (0.0010) -[2023-11-28 00:14:10,650][87426] Updated weights for policy 1, policy_version 950 (0.0010) -[2023-11-28 00:14:10,698][87424] Updated weights for policy 0, policy_version 946 (0.0010) -[2023-11-28 00:14:11,041][87426] Updated weights for policy 1, policy_version 960 (0.0011) -[2023-11-28 00:14:11,084][87424] Updated weights for policy 0, policy_version 956 (0.0011) -[2023-11-28 00:14:13,017][87424] Updated weights for policy 0, policy_version 966 (0.0012) -[2023-11-28 00:14:13,400][87424] Updated weights for policy 0, policy_version 976 (0.0009) -[2023-11-28 00:14:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 4856.1). Total num frames: 491520. Throughput: 0: 2751.8, 1: 2693.1. Samples: 510600. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 00:14:13,445][86177] Avg episode reward: [(0, '-1235.970'), (1, '-1292.240')] -[2023-11-28 00:14:13,543][87426] Updated weights for policy 1, policy_version 970 (0.0011) -[2023-11-28 00:14:13,783][87424] Updated weights for policy 0, policy_version 986 (0.0009) -[2023-11-28 00:14:13,917][87426] Updated weights for policy 1, policy_version 980 (0.0011) -[2023-11-28 00:14:14,300][87426] Updated weights for policy 1, policy_version 990 (0.0011) -[2023-11-28 00:14:16,013][87424] Updated weights for policy 0, policy_version 996 (0.0009) -[2023-11-28 00:14:16,327][87426] Updated weights for policy 1, policy_version 1000 (0.0008) -[2023-11-28 00:14:16,403][87424] Updated weights for policy 0, policy_version 1006 (0.0009) -[2023-11-28 00:14:16,701][87426] Updated weights for policy 1, policy_version 1010 (0.0007) -[2023-11-28 00:14:16,783][87424] Updated weights for policy 0, policy_version 1016 (0.0007) -[2023-11-28 00:14:17,070][87426] Updated weights for policy 1, policy_version 1020 (0.0010) -[2023-11-28 00:14:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 4936.0). Total num frames: 524288. Throughput: 0: 2754.6, 1: 2707.3. Samples: 535672. Policy #0 lag: (min: 13.0, avg: 37.4, max: 71.0) -[2023-11-28 00:14:18,445][86177] Avg episode reward: [(0, '-1241.180'), (1, '-1306.720')] -[2023-11-28 00:14:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000001024_262144.pth... -[2023-11-28 00:14:18,501][87424] Updated weights for policy 0, policy_version 1026 (0.0011) -[2023-11-28 00:14:18,880][87424] Updated weights for policy 0, policy_version 1036 (0.0011) -[2023-11-28 00:14:19,261][87424] Updated weights for policy 0, policy_version 1046 (0.0008) -[2023-11-28 00:14:19,508][87426] Updated weights for policy 1, policy_version 1030 (0.0010) -[2023-11-28 00:14:19,648][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000001056_270336.pth... -[2023-11-28 00:14:19,649][87424] Updated weights for policy 0, policy_version 1056 (0.0009) -[2023-11-28 00:14:19,881][87426] Updated weights for policy 1, policy_version 1040 (0.0012) -[2023-11-28 00:14:20,259][87426] Updated weights for policy 1, policy_version 1050 (0.0012) -[2023-11-28 00:14:22,151][87424] Updated weights for policy 0, policy_version 1066 (0.0011) -[2023-11-28 00:14:22,527][87424] Updated weights for policy 0, policy_version 1076 (0.0011) -[2023-11-28 00:14:22,711][87426] Updated weights for policy 1, policy_version 1060 (0.0012) -[2023-11-28 00:14:22,903][87424] Updated weights for policy 0, policy_version 1086 (0.0012) -[2023-11-28 00:14:23,088][87426] Updated weights for policy 1, policy_version 1070 (0.0012) -[2023-11-28 00:14:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 4935.1). Total num frames: 548864. Throughput: 0: 2752.4, 1: 2723.3. Samples: 567864. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:14:23,445][86177] Avg episode reward: [(0, '-1236.460'), (1, '-1314.590')] -[2023-11-28 00:14:23,466][87426] Updated weights for policy 1, policy_version 1080 (0.0011) -[2023-11-28 00:14:24,670][87424] Updated weights for policy 0, policy_version 1096 (0.0012) -[2023-11-28 00:14:25,041][87424] Updated weights for policy 0, policy_version 1106 (0.0012) -[2023-11-28 00:14:25,421][87424] Updated weights for policy 0, policy_version 1116 (0.0012) -[2023-11-28 00:14:25,607][87426] Updated weights for policy 1, policy_version 1090 (0.0011) -[2023-11-28 00:14:25,989][87426] Updated weights for policy 1, policy_version 1100 (0.0007) -[2023-11-28 00:14:26,372][87426] Updated weights for policy 1, policy_version 1110 (0.0007) -[2023-11-28 00:14:26,760][87426] Updated weights for policy 1, policy_version 1120 (0.0007) -[2023-11-28 00:14:27,475][87424] Updated weights for policy 0, policy_version 1126 (0.0010) -[2023-11-28 00:14:27,854][87424] Updated weights for policy 0, policy_version 1136 (0.0011) -[2023-11-28 00:14:28,233][87424] Updated weights for policy 0, policy_version 1146 (0.0011) -[2023-11-28 00:14:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 4934.2). Total num frames: 573440. Throughput: 0: 2757.5, 1: 2705.0. Samples: 591844. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:14:28,445][86177] Avg episode reward: [(0, '-1226.190'), (1, '-1316.960')] -[2023-11-28 00:14:28,961][87426] Updated weights for policy 1, policy_version 1130 (0.0012) -[2023-11-28 00:14:29,345][87426] Updated weights for policy 1, policy_version 1140 (0.0012) -[2023-11-28 00:14:29,714][87426] Updated weights for policy 1, policy_version 1150 (0.0011) -[2023-11-28 00:14:30,277][87424] Updated weights for policy 0, policy_version 1156 (0.0010) -[2023-11-28 00:14:30,658][87424] Updated weights for policy 0, policy_version 1166 (0.0008) -[2023-11-28 00:14:31,032][87424] Updated weights for policy 0, policy_version 1176 (0.0008) -[2023-11-28 00:14:32,210][87426] Updated weights for policy 1, policy_version 1160 (0.0011) -[2023-11-28 00:14:32,585][87426] Updated weights for policy 1, policy_version 1170 (0.0008) -[2023-11-28 00:14:32,993][87426] Updated weights for policy 1, policy_version 1180 (0.0008) -[2023-11-28 00:14:33,401][87424] Updated weights for policy 0, policy_version 1186 (0.0008) -[2023-11-28 00:14:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5001.0). Total num frames: 606208. Throughput: 0: 2745.8, 1: 2697.2. Samples: 615948. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 00:14:33,445][86177] Avg episode reward: [(0, '-1220.360'), (1, '-1283.190')] -[2023-11-28 00:14:33,773][87424] Updated weights for policy 0, policy_version 1196 (0.0011) -[2023-11-28 00:14:34,147][87424] Updated weights for policy 0, policy_version 1206 (0.0012) -[2023-11-28 00:14:34,511][87426] Updated weights for policy 1, policy_version 1190 (0.0011) -[2023-11-28 00:14:34,525][87424] Updated weights for policy 0, policy_version 1216 (0.0011) -[2023-11-28 00:14:34,898][87426] Updated weights for policy 1, policy_version 1200 (0.0010) -[2023-11-28 00:14:35,277][87426] Updated weights for policy 1, policy_version 1210 (0.0011) -[2023-11-28 00:14:36,533][87424] Updated weights for policy 0, policy_version 1226 (0.0012) -[2023-11-28 00:14:36,924][87424] Updated weights for policy 0, policy_version 1236 (0.0011) -[2023-11-28 00:14:36,952][87426] Updated weights for policy 1, policy_version 1220 (0.0012) -[2023-11-28 00:14:37,302][87424] Updated weights for policy 0, policy_version 1246 (0.0011) -[2023-11-28 00:14:37,330][87426] Updated weights for policy 1, policy_version 1230 (0.0010) -[2023-11-28 00:14:37,709][87426] Updated weights for policy 1, policy_version 1240 (0.0010) -[2023-11-28 00:14:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5062.5). Total num frames: 638976. Throughput: 0: 2727.0, 1: 2729.1. Samples: 650080. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 00:14:38,445][86177] Avg episode reward: [(0, '-1226.920'), (1, '-1278.030')] -[2023-11-28 00:14:39,124][87424] Updated weights for policy 0, policy_version 1256 (0.0012) -[2023-11-28 00:14:39,506][87424] Updated weights for policy 0, policy_version 1266 (0.0012) -[2023-11-28 00:14:39,869][87426] Updated weights for policy 1, policy_version 1250 (0.0011) -[2023-11-28 00:14:39,882][87424] Updated weights for policy 0, policy_version 1276 (0.0011) -[2023-11-28 00:14:40,249][87426] Updated weights for policy 1, policy_version 1260 (0.0008) -[2023-11-28 00:14:40,629][87426] Updated weights for policy 1, policy_version 1270 (0.0008) -[2023-11-28 00:14:41,015][87426] Updated weights for policy 1, policy_version 1280 (0.0010) -[2023-11-28 00:14:42,252][87424] Updated weights for policy 0, policy_version 1286 (0.0010) -[2023-11-28 00:14:42,642][87424] Updated weights for policy 0, policy_version 1296 (0.0010) -[2023-11-28 00:14:43,015][87424] Updated weights for policy 0, policy_version 1306 (0.0011) -[2023-11-28 00:14:43,394][87426] Updated weights for policy 1, policy_version 1290 (0.0007) -[2023-11-28 00:14:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5056.9). Total num frames: 663552. Throughput: 0: 2730.4, 1: 2744.4. Samples: 676144. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 00:14:43,446][86177] Avg episode reward: [(0, '-1228.720'), (1, '-1295.860')] -[2023-11-28 00:14:43,766][87426] Updated weights for policy 1, policy_version 1300 (0.0009) -[2023-11-28 00:14:44,144][87426] Updated weights for policy 1, policy_version 1310 (0.0011) -[2023-11-28 00:14:45,418][87424] Updated weights for policy 0, policy_version 1316 (0.0011) -[2023-11-28 00:14:45,800][87424] Updated weights for policy 0, policy_version 1326 (0.0012) -[2023-11-28 00:14:46,176][87424] Updated weights for policy 0, policy_version 1336 (0.0011) -[2023-11-28 00:14:46,225][87426] Updated weights for policy 1, policy_version 1320 (0.0010) -[2023-11-28 00:14:46,596][87426] Updated weights for policy 1, policy_version 1330 (0.0010) -[2023-11-28 00:14:46,978][87426] Updated weights for policy 1, policy_version 1340 (0.0012) -[2023-11-28 00:14:47,903][87424] Updated weights for policy 0, policy_version 1346 (0.0010) -[2023-11-28 00:14:48,284][87424] Updated weights for policy 0, policy_version 1356 (0.0009) -[2023-11-28 00:14:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5051.7). Total num frames: 688128. Throughput: 0: 2728.5, 1: 2758.6. Samples: 701168. Policy #0 lag: (min: 28.0, avg: 41.7, max: 60.0) -[2023-11-28 00:14:48,445][86177] Avg episode reward: [(0, '-1235.160'), (1, '-1298.240')] -[2023-11-28 00:14:48,657][87424] Updated weights for policy 0, policy_version 1366 (0.0012) -[2023-11-28 00:14:48,820][87426] Updated weights for policy 1, policy_version 1350 (0.0011) -[2023-11-28 00:14:49,044][87424] Updated weights for policy 0, policy_version 1376 (0.0011) -[2023-11-28 00:14:49,198][87426] Updated weights for policy 1, policy_version 1360 (0.0012) -[2023-11-28 00:14:49,581][87426] Updated weights for policy 1, policy_version 1370 (0.0011) -[2023-11-28 00:14:51,401][87424] Updated weights for policy 0, policy_version 1386 (0.0009) -[2023-11-28 00:14:51,785][87424] Updated weights for policy 0, policy_version 1396 (0.0010) -[2023-11-28 00:14:52,066][87426] Updated weights for policy 1, policy_version 1380 (0.0011) -[2023-11-28 00:14:52,164][87424] Updated weights for policy 0, policy_version 1406 (0.0012) -[2023-11-28 00:14:52,451][87426] Updated weights for policy 1, policy_version 1390 (0.0010) -[2023-11-28 00:14:52,833][87426] Updated weights for policy 1, policy_version 1400 (0.0011) -[2023-11-28 00:14:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5104.9). Total num frames: 720896. Throughput: 0: 2718.8, 1: 2737.5. Samples: 732936. Policy #0 lag: (min: 10.0, avg: 26.4, max: 53.0) -[2023-11-28 00:14:53,445][86177] Avg episode reward: [(0, '-1238.170'), (1, '-1314.770')] -[2023-11-28 00:14:54,711][87424] Updated weights for policy 0, policy_version 1416 (0.0011) -[2023-11-28 00:14:54,733][87426] Updated weights for policy 1, policy_version 1410 (0.0010) -[2023-11-28 00:14:55,098][87424] Updated weights for policy 0, policy_version 1426 (0.0008) -[2023-11-28 00:14:55,113][87426] Updated weights for policy 1, policy_version 1420 (0.0011) -[2023-11-28 00:14:55,478][87424] Updated weights for policy 0, policy_version 1436 (0.0007) -[2023-11-28 00:14:55,496][87426] Updated weights for policy 1, policy_version 1430 (0.0012) -[2023-11-28 00:14:55,870][87426] Updated weights for policy 1, policy_version 1440 (0.0012) -[2023-11-28 00:14:57,480][87424] Updated weights for policy 0, policy_version 1446 (0.0010) -[2023-11-28 00:14:57,788][87426] Updated weights for policy 1, policy_version 1450 (0.0007) -[2023-11-28 00:14:57,868][87424] Updated weights for policy 0, policy_version 1456 (0.0010) -[2023-11-28 00:14:58,172][87426] Updated weights for policy 1, policy_version 1460 (0.0011) -[2023-11-28 00:14:58,251][87424] Updated weights for policy 0, policy_version 1466 (0.0008) -[2023-11-28 00:14:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5042.4). Total num frames: 737280. Throughput: 0: 2729.6, 1: 2764.6. Samples: 757840. Policy #0 lag: (min: 15.0, avg: 31.7, max: 47.0) -[2023-11-28 00:14:58,445][86177] Avg episode reward: [(0, '-1204.830'), (1, '-1288.380')] -[2023-11-28 00:14:58,546][87426] Updated weights for policy 1, policy_version 1470 (0.0012) -[2023-11-28 00:14:59,819][87424] Updated weights for policy 0, policy_version 1476 (0.0009) -[2023-11-28 00:15:00,200][87424] Updated weights for policy 0, policy_version 1486 (0.0009) -[2023-11-28 00:15:00,585][87424] Updated weights for policy 0, policy_version 1496 (0.0010) -[2023-11-28 00:15:00,966][87426] Updated weights for policy 1, policy_version 1480 (0.0010) -[2023-11-28 00:15:01,343][87426] Updated weights for policy 1, policy_version 1490 (0.0011) -[2023-11-28 00:15:01,725][87426] Updated weights for policy 1, policy_version 1500 (0.0016) -[2023-11-28 00:15:02,662][87424] Updated weights for policy 0, policy_version 1506 (0.0011) -[2023-11-28 00:15:03,050][87424] Updated weights for policy 0, policy_version 1516 (0.0010) -[2023-11-28 00:15:03,439][87424] Updated weights for policy 0, policy_version 1526 (0.0008) -[2023-11-28 00:15:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5092.3). Total num frames: 770048. Throughput: 0: 2760.7, 1: 2758.5. Samples: 784036. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 00:15:03,445][86177] Avg episode reward: [(0, '-1199.300'), (1, '-1263.090')] -[2023-11-28 00:15:03,822][87424] Updated weights for policy 0, policy_version 1536 (0.0012) -[2023-11-28 00:15:04,145][87426] Updated weights for policy 1, policy_version 1510 (0.0011) -[2023-11-28 00:15:04,509][87426] Updated weights for policy 1, policy_version 1520 (0.0012) -[2023-11-28 00:15:04,886][87426] Updated weights for policy 1, policy_version 1530 (0.0012) -[2023-11-28 00:15:05,786][87424] Updated weights for policy 0, policy_version 1546 (0.0012) -[2023-11-28 00:15:06,165][87424] Updated weights for policy 0, policy_version 1556 (0.0012) -[2023-11-28 00:15:06,550][87424] Updated weights for policy 0, policy_version 1566 (0.0012) -[2023-11-28 00:15:06,970][87426] Updated weights for policy 1, policy_version 1540 (0.0012) -[2023-11-28 00:15:07,350][87426] Updated weights for policy 1, policy_version 1550 (0.0012) -[2023-11-28 00:15:07,737][87426] Updated weights for policy 1, policy_version 1560 (0.0011) -[2023-11-28 00:15:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5139.1). Total num frames: 802816. Throughput: 0: 2778.3, 1: 2787.3. Samples: 818316. Policy #0 lag: (min: 17.0, avg: 33.2, max: 49.0) -[2023-11-28 00:15:08,445][86177] Avg episode reward: [(0, '-1194.130'), (1, '-1254.540')] -[2023-11-28 00:15:08,923][87424] Updated weights for policy 0, policy_version 1576 (0.0009) -[2023-11-28 00:15:09,302][87424] Updated weights for policy 0, policy_version 1586 (0.0012) -[2023-11-28 00:15:09,513][87426] Updated weights for policy 1, policy_version 1570 (0.0011) -[2023-11-28 00:15:09,687][87424] Updated weights for policy 0, policy_version 1596 (0.0012) -[2023-11-28 00:15:09,889][87426] Updated weights for policy 1, policy_version 1580 (0.0011) -[2023-11-28 00:15:10,275][87426] Updated weights for policy 1, policy_version 1590 (0.0011) -[2023-11-28 00:15:10,656][87426] Updated weights for policy 1, policy_version 1600 (0.0011) -[2023-11-28 00:15:11,919][87424] Updated weights for policy 0, policy_version 1606 (0.0012) -[2023-11-28 00:15:12,311][87424] Updated weights for policy 0, policy_version 1616 (0.0011) -[2023-11-28 00:15:12,684][87424] Updated weights for policy 0, policy_version 1626 (0.0011) -[2023-11-28 00:15:12,926][87426] Updated weights for policy 1, policy_version 1610 (0.0011) -[2023-11-28 00:15:13,308][87426] Updated weights for policy 1, policy_version 1620 (0.0012) -[2023-11-28 00:15:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5132.2). Total num frames: 827392. Throughput: 0: 2769.3, 1: 2797.2. Samples: 842332. Policy #0 lag: (min: 13.0, avg: 16.5, max: 36.0) -[2023-11-28 00:15:13,445][86177] Avg episode reward: [(0, '-1186.340'), (1, '-1245.490')] -[2023-11-28 00:15:13,446][87281] Saving new best policy, reward=-1186.340! -[2023-11-28 00:15:13,696][87426] Updated weights for policy 1, policy_version 1630 (0.0009) -[2023-11-28 00:15:15,021][87424] Updated weights for policy 0, policy_version 1636 (0.0010) -[2023-11-28 00:15:15,404][87424] Updated weights for policy 0, policy_version 1646 (0.0008) -[2023-11-28 00:15:15,787][87424] Updated weights for policy 0, policy_version 1656 (0.0009) -[2023-11-28 00:15:16,134][87426] Updated weights for policy 1, policy_version 1640 (0.0010) -[2023-11-28 00:15:16,532][87426] Updated weights for policy 1, policy_version 1650 (0.0011) -[2023-11-28 00:15:16,899][87426] Updated weights for policy 1, policy_version 1660 (0.0009) -[2023-11-28 00:15:18,289][87424] Updated weights for policy 0, policy_version 1666 (0.0007) -[2023-11-28 00:15:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5125.6). Total num frames: 851968. Throughput: 0: 2756.2, 1: 2791.9. Samples: 865612. Policy #0 lag: (min: 13.0, avg: 16.5, max: 36.0) -[2023-11-28 00:15:18,445][86177] Avg episode reward: [(0, '-1174.560'), (1, '-1249.990')] -[2023-11-28 00:15:18,673][87424] Updated weights for policy 0, policy_version 1676 (0.0011) -[2023-11-28 00:15:18,679][87426] Updated weights for policy 1, policy_version 1670 (0.0007) -[2023-11-28 00:15:19,053][87426] Updated weights for policy 1, policy_version 1680 (0.0009) -[2023-11-28 00:15:19,058][87424] Updated weights for policy 0, policy_version 1686 (0.0011) -[2023-11-28 00:15:19,434][87426] Updated weights for policy 1, policy_version 1690 (0.0011) -[2023-11-28 00:15:19,445][87281] Saving new best policy, reward=-1174.560! -[2023-11-28 00:15:19,446][87424] Updated weights for policy 0, policy_version 1696 (0.0011) -[2023-11-28 00:15:21,993][87426] Updated weights for policy 1, policy_version 1700 (0.0010) -[2023-11-28 00:15:22,040][87424] Updated weights for policy 0, policy_version 1706 (0.0011) -[2023-11-28 00:15:22,374][87426] Updated weights for policy 1, policy_version 1710 (0.0011) -[2023-11-28 00:15:22,411][87424] Updated weights for policy 0, policy_version 1716 (0.0011) -[2023-11-28 00:15:22,753][87426] Updated weights for policy 1, policy_version 1720 (0.0011) -[2023-11-28 00:15:22,801][87424] Updated weights for policy 0, policy_version 1726 (0.0008) -[2023-11-28 00:15:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5167.3). Total num frames: 884736. Throughput: 0: 2749.2, 1: 2741.2. Samples: 897144. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:15:23,445][86177] Avg episode reward: [(0, '-1159.180'), (1, '-1247.270')] -[2023-11-28 00:15:23,446][87281] Saving new best policy, reward=-1159.180! -[2023-11-28 00:15:24,825][87426] Updated weights for policy 1, policy_version 1730 (0.0011) -[2023-11-28 00:15:25,192][87426] Updated weights for policy 1, policy_version 1740 (0.0011) -[2023-11-28 00:15:25,272][87424] Updated weights for policy 0, policy_version 1736 (0.0011) -[2023-11-28 00:15:25,568][87426] Updated weights for policy 1, policy_version 1750 (0.0008) -[2023-11-28 00:15:25,661][87424] Updated weights for policy 0, policy_version 1746 (0.0012) -[2023-11-28 00:15:25,947][87426] Updated weights for policy 1, policy_version 1760 (0.0007) -[2023-11-28 00:15:26,048][87424] Updated weights for policy 0, policy_version 1756 (0.0012) -[2023-11-28 00:15:27,547][87424] Updated weights for policy 0, policy_version 1766 (0.0012) -[2023-11-28 00:15:27,924][87424] Updated weights for policy 0, policy_version 1776 (0.0012) -[2023-11-28 00:15:28,194][87426] Updated weights for policy 1, policy_version 1770 (0.0008) -[2023-11-28 00:15:28,307][87424] Updated weights for policy 0, policy_version 1786 (0.0012) -[2023-11-28 00:15:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5113.7). Total num frames: 901120. Throughput: 0: 2746.1, 1: 2706.2. Samples: 921496. Policy #0 lag: (min: 31.0, avg: 32.3, max: 45.0) -[2023-11-28 00:15:28,445][86177] Avg episode reward: [(0, '-1155.970'), (1, '-1233.520')] -[2023-11-28 00:15:28,533][87281] Saving new best policy, reward=-1155.970! -[2023-11-28 00:15:28,581][87426] Updated weights for policy 1, policy_version 1780 (0.0007) -[2023-11-28 00:15:28,966][87426] Updated weights for policy 1, policy_version 1790 (0.0008) -[2023-11-28 00:15:29,917][87424] Updated weights for policy 0, policy_version 1796 (0.0010) -[2023-11-28 00:15:30,295][87424] Updated weights for policy 0, policy_version 1806 (0.0012) -[2023-11-28 00:15:30,674][87424] Updated weights for policy 0, policy_version 1816 (0.0012) -[2023-11-28 00:15:31,165][87426] Updated weights for policy 1, policy_version 1800 (0.0011) -[2023-11-28 00:15:31,554][87426] Updated weights for policy 1, policy_version 1810 (0.0012) -[2023-11-28 00:15:31,932][87426] Updated weights for policy 1, policy_version 1820 (0.0011) -[2023-11-28 00:15:33,180][87424] Updated weights for policy 0, policy_version 1826 (0.0011) -[2023-11-28 00:15:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5153.4). Total num frames: 933888. Throughput: 0: 2736.6, 1: 2692.8. Samples: 945492. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 00:15:33,445][86177] Avg episode reward: [(0, '-1135.960'), (1, '-1200.720')] -[2023-11-28 00:15:33,553][87424] Updated weights for policy 0, policy_version 1836 (0.0012) -[2023-11-28 00:15:33,941][87424] Updated weights for policy 0, policy_version 1846 (0.0012) -[2023-11-28 00:15:34,319][87281] Saving new best policy, reward=-1135.960! -[2023-11-28 00:15:34,321][87424] Updated weights for policy 0, policy_version 1856 (0.0012) -[2023-11-28 00:15:34,461][87426] Updated weights for policy 1, policy_version 1830 (0.0009) -[2023-11-28 00:15:34,843][87426] Updated weights for policy 1, policy_version 1840 (0.0008) -[2023-11-28 00:15:35,222][87426] Updated weights for policy 1, policy_version 1850 (0.0009) -[2023-11-28 00:15:36,108][87424] Updated weights for policy 0, policy_version 1866 (0.0012) -[2023-11-28 00:15:36,487][87424] Updated weights for policy 0, policy_version 1876 (0.0011) -[2023-11-28 00:15:36,872][87424] Updated weights for policy 0, policy_version 1886 (0.0012) -[2023-11-28 00:15:37,152][87426] Updated weights for policy 1, policy_version 1860 (0.0011) -[2023-11-28 00:15:37,535][87426] Updated weights for policy 1, policy_version 1870 (0.0009) -[2023-11-28 00:15:37,920][87426] Updated weights for policy 1, policy_version 1880 (0.0007) -[2023-11-28 00:15:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5191.0). Total num frames: 966656. Throughput: 0: 2738.4, 1: 2712.5. Samples: 978228. Policy #0 lag: (min: 26.0, avg: 44.4, max: 58.0) -[2023-11-28 00:15:38,445][86177] Avg episode reward: [(0, '-1136.880'), (1, '-1181.550')] -[2023-11-28 00:15:38,918][87424] Updated weights for policy 0, policy_version 1896 (0.0010) -[2023-11-28 00:15:39,307][87424] Updated weights for policy 0, policy_version 1906 (0.0010) -[2023-11-28 00:15:39,690][87424] Updated weights for policy 0, policy_version 1916 (0.0009) -[2023-11-28 00:15:39,937][87426] Updated weights for policy 1, policy_version 1890 (0.0009) -[2023-11-28 00:15:40,321][87426] Updated weights for policy 1, policy_version 1900 (0.0011) -[2023-11-28 00:15:40,696][87426] Updated weights for policy 1, policy_version 1910 (0.0011) -[2023-11-28 00:15:41,081][87426] Updated weights for policy 1, policy_version 1920 (0.0010) -[2023-11-28 00:15:42,200][87424] Updated weights for policy 0, policy_version 1926 (0.0011) -[2023-11-28 00:15:42,581][87424] Updated weights for policy 0, policy_version 1936 (0.0011) -[2023-11-28 00:15:42,964][87424] Updated weights for policy 0, policy_version 1946 (0.0011) -[2023-11-28 00:15:43,133][87426] Updated weights for policy 1, policy_version 1930 (0.0012) -[2023-11-28 00:15:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5183.8). Total num frames: 991232. Throughput: 0: 2756.1, 1: 2694.0. Samples: 1003096. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 00:15:43,445][86177] Avg episode reward: [(0, '-1126.750'), (1, '-1191.900')] -[2023-11-28 00:15:43,445][87281] Saving new best policy, reward=-1126.750! -[2023-11-28 00:15:43,515][87426] Updated weights for policy 1, policy_version 1940 (0.0011) -[2023-11-28 00:15:43,884][87426] Updated weights for policy 1, policy_version 1950 (0.0011) -[2023-11-28 00:15:45,400][87424] Updated weights for policy 0, policy_version 1956 (0.0008) -[2023-11-28 00:15:45,773][87424] Updated weights for policy 0, policy_version 1966 (0.0009) -[2023-11-28 00:15:46,158][87424] Updated weights for policy 0, policy_version 1976 (0.0009) -[2023-11-28 00:15:46,456][87426] Updated weights for policy 1, policy_version 1960 (0.0010) -[2023-11-28 00:15:46,836][87426] Updated weights for policy 1, policy_version 1970 (0.0007) -[2023-11-28 00:15:47,215][87426] Updated weights for policy 1, policy_version 1980 (0.0007) -[2023-11-28 00:15:47,843][87424] Updated weights for policy 0, policy_version 1986 (0.0009) -[2023-11-28 00:15:48,229][87424] Updated weights for policy 0, policy_version 1996 (0.0011) -[2023-11-28 00:15:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5177.0). Total num frames: 1015808. Throughput: 0: 2722.4, 1: 2691.0. Samples: 1027640. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 00:15:48,445][86177] Avg episode reward: [(0, '-1104.550'), (1, '-1210.360')] -[2023-11-28 00:15:48,620][87424] Updated weights for policy 0, policy_version 2006 (0.0011) -[2023-11-28 00:15:49,003][87281] Saving new best policy, reward=-1104.550! -[2023-11-28 00:15:49,004][87424] Updated weights for policy 0, policy_version 2016 (0.0012) -[2023-11-28 00:15:49,617][87426] Updated weights for policy 1, policy_version 1990 (0.0010) -[2023-11-28 00:15:49,986][87426] Updated weights for policy 1, policy_version 2000 (0.0012) -[2023-11-28 00:15:50,362][87426] Updated weights for policy 1, policy_version 2010 (0.0012) -[2023-11-28 00:15:51,436][87424] Updated weights for policy 0, policy_version 2026 (0.0012) -[2023-11-28 00:15:51,817][87424] Updated weights for policy 0, policy_version 2036 (0.0012) -[2023-11-28 00:15:52,203][87424] Updated weights for policy 0, policy_version 2046 (0.0009) -[2023-11-28 00:15:52,931][87426] Updated weights for policy 1, policy_version 2020 (0.0012) -[2023-11-28 00:15:53,311][87426] Updated weights for policy 1, policy_version 2030 (0.0012) -[2023-11-28 00:15:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5170.5). Total num frames: 1040384. Throughput: 0: 2723.6, 1: 2653.9. Samples: 1060300. Policy #0 lag: (min: 31.0, avg: 46.2, max: 68.0) -[2023-11-28 00:15:53,445][86177] Avg episode reward: [(0, '-1093.600'), (1, '-1184.780')] -[2023-11-28 00:15:53,446][87281] Saving new best policy, reward=-1093.600! -[2023-11-28 00:15:53,693][87426] Updated weights for policy 1, policy_version 2040 (0.0012) -[2023-11-28 00:15:54,242][87424] Updated weights for policy 0, policy_version 2056 (0.0008) -[2023-11-28 00:15:54,629][87424] Updated weights for policy 0, policy_version 2066 (0.0007) -[2023-11-28 00:15:55,008][87424] Updated weights for policy 0, policy_version 2076 (0.0007) -[2023-11-28 00:15:55,648][87426] Updated weights for policy 1, policy_version 2050 (0.0011) -[2023-11-28 00:15:56,034][87426] Updated weights for policy 1, policy_version 2060 (0.0011) -[2023-11-28 00:15:56,424][87426] Updated weights for policy 1, policy_version 2070 (0.0011) -[2023-11-28 00:15:56,799][87426] Updated weights for policy 1, policy_version 2080 (0.0011) -[2023-11-28 00:15:57,200][87424] Updated weights for policy 0, policy_version 2086 (0.0007) -[2023-11-28 00:15:57,598][87424] Updated weights for policy 0, policy_version 2096 (0.0007) -[2023-11-28 00:15:57,976][87424] Updated weights for policy 0, policy_version 2106 (0.0008) -[2023-11-28 00:15:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5204.0). Total num frames: 1073152. Throughput: 0: 2729.3, 1: 2658.2. Samples: 1084768. Policy #0 lag: (min: 27.0, avg: 52.7, max: 66.0) -[2023-11-28 00:15:58,445][86177] Avg episode reward: [(0, '-1080.190'), (1, '-1201.460')] -[2023-11-28 00:15:58,445][87281] Saving new best policy, reward=-1080.190! -[2023-11-28 00:15:58,898][87426] Updated weights for policy 1, policy_version 2090 (0.0011) -[2023-11-28 00:15:59,281][87426] Updated weights for policy 1, policy_version 2100 (0.0007) -[2023-11-28 00:15:59,664][87426] Updated weights for policy 1, policy_version 2110 (0.0008) -[2023-11-28 00:16:00,119][87424] Updated weights for policy 0, policy_version 2116 (0.0008) -[2023-11-28 00:16:00,499][87424] Updated weights for policy 0, policy_version 2126 (0.0008) -[2023-11-28 00:16:00,883][87424] Updated weights for policy 0, policy_version 2136 (0.0009) -[2023-11-28 00:16:02,124][87426] Updated weights for policy 1, policy_version 2120 (0.0011) -[2023-11-28 00:16:02,506][87426] Updated weights for policy 1, policy_version 2130 (0.0012) -[2023-11-28 00:16:02,877][87426] Updated weights for policy 1, policy_version 2140 (0.0011) -[2023-11-28 00:16:02,940][87424] Updated weights for policy 0, policy_version 2146 (0.0010) -[2023-11-28 00:16:03,322][87424] Updated weights for policy 0, policy_version 2156 (0.0011) -[2023-11-28 00:16:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5197.2). Total num frames: 1097728. Throughput: 0: 2749.9, 1: 2680.0. Samples: 1109956. Policy #0 lag: (min: 27.0, avg: 52.7, max: 66.0) -[2023-11-28 00:16:03,445][86177] Avg episode reward: [(0, '-1070.710'), (1, '-1211.420')] -[2023-11-28 00:16:03,708][87424] Updated weights for policy 0, policy_version 2166 (0.0012) -[2023-11-28 00:16:04,095][87281] Saving new best policy, reward=-1070.710! -[2023-11-28 00:16:04,100][87424] Updated weights for policy 0, policy_version 2176 (0.0010) -[2023-11-28 00:16:04,631][87426] Updated weights for policy 1, policy_version 2150 (0.0010) -[2023-11-28 00:16:05,006][87426] Updated weights for policy 1, policy_version 2160 (0.0011) -[2023-11-28 00:16:05,379][87426] Updated weights for policy 1, policy_version 2170 (0.0011) -[2023-11-28 00:16:06,393][87424] Updated weights for policy 0, policy_version 2186 (0.0008) -[2023-11-28 00:16:06,786][87424] Updated weights for policy 0, policy_version 2196 (0.0008) -[2023-11-28 00:16:07,168][87424] Updated weights for policy 0, policy_version 2206 (0.0008) -[2023-11-28 00:16:07,346][87426] Updated weights for policy 1, policy_version 2180 (0.0008) -[2023-11-28 00:16:07,737][87426] Updated weights for policy 1, policy_version 2190 (0.0008) -[2023-11-28 00:16:08,111][87426] Updated weights for policy 1, policy_version 2200 (0.0008) -[2023-11-28 00:16:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5228.5). Total num frames: 1130496. Throughput: 0: 2753.4, 1: 2717.3. Samples: 1143328. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 00:16:08,445][86177] Avg episode reward: [(0, '-1041.940'), (1, '-1197.690')] -[2023-11-28 00:16:08,446][87281] Saving new best policy, reward=-1041.940! -[2023-11-28 00:16:08,970][87424] Updated weights for policy 0, policy_version 2216 (0.0012) -[2023-11-28 00:16:09,347][87424] Updated weights for policy 0, policy_version 2226 (0.0012) -[2023-11-28 00:16:09,728][87424] Updated weights for policy 0, policy_version 2236 (0.0012) -[2023-11-28 00:16:10,280][87426] Updated weights for policy 1, policy_version 2210 (0.0009) -[2023-11-28 00:16:10,660][87426] Updated weights for policy 1, policy_version 2220 (0.0010) -[2023-11-28 00:16:11,038][87426] Updated weights for policy 1, policy_version 2230 (0.0010) -[2023-11-28 00:16:11,421][87426] Updated weights for policy 1, policy_version 2240 (0.0008) -[2023-11-28 00:16:12,040][87424] Updated weights for policy 0, policy_version 2246 (0.0011) -[2023-11-28 00:16:12,423][87424] Updated weights for policy 0, policy_version 2256 (0.0010) -[2023-11-28 00:16:12,817][87424] Updated weights for policy 0, policy_version 2266 (0.0008) -[2023-11-28 00:16:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5221.4). Total num frames: 1155072. Throughput: 0: 2758.6, 1: 2725.7. Samples: 1168288. Policy #0 lag: (min: 31.0, avg: 50.0, max: 63.0) -[2023-11-28 00:16:13,445][86177] Avg episode reward: [(0, '-1003.700'), (1, '-1194.300')] -[2023-11-28 00:16:13,446][87281] Saving new best policy, reward=-1003.700! -[2023-11-28 00:16:13,689][87426] Updated weights for policy 1, policy_version 2250 (0.0010) -[2023-11-28 00:16:14,078][87426] Updated weights for policy 1, policy_version 2260 (0.0007) -[2023-11-28 00:16:14,442][87424] Updated weights for policy 0, policy_version 2276 (0.0011) -[2023-11-28 00:16:14,468][87426] Updated weights for policy 1, policy_version 2270 (0.0009) -[2023-11-28 00:16:14,828][87424] Updated weights for policy 0, policy_version 2286 (0.0011) -[2023-11-28 00:16:15,207][87424] Updated weights for policy 0, policy_version 2296 (0.0012) -[2023-11-28 00:16:16,820][87426] Updated weights for policy 1, policy_version 2280 (0.0007) -[2023-11-28 00:16:17,211][87426] Updated weights for policy 1, policy_version 2290 (0.0007) -[2023-11-28 00:16:17,583][87426] Updated weights for policy 1, policy_version 2300 (0.0007) -[2023-11-28 00:16:17,642][87424] Updated weights for policy 0, policy_version 2306 (0.0011) -[2023-11-28 00:16:18,027][87424] Updated weights for policy 0, policy_version 2316 (0.0008) -[2023-11-28 00:16:18,426][87424] Updated weights for policy 0, policy_version 2326 (0.0009) -[2023-11-28 00:16:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5214.7). Total num frames: 1179648. Throughput: 0: 2782.6, 1: 2723.2. Samples: 1193252. Policy #0 lag: (min: 30.0, avg: 40.7, max: 52.0) -[2023-11-28 00:16:18,445][86177] Avg episode reward: [(0, '-1000.110'), (1, '-1193.380')] -[2023-11-28 00:16:18,452][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000002304_589824.pth... -[2023-11-28 00:16:18,799][87424] Updated weights for policy 0, policy_version 2336 (0.0011) -[2023-11-28 00:16:18,799][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000002336_598016.pth... -[2023-11-28 00:16:18,846][87281] Saving new best policy, reward=-1000.110! -[2023-11-28 00:16:19,288][87426] Updated weights for policy 1, policy_version 2310 (0.0009) -[2023-11-28 00:16:19,674][87426] Updated weights for policy 1, policy_version 2320 (0.0007) -[2023-11-28 00:16:20,063][87426] Updated weights for policy 1, policy_version 2330 (0.0012) -[2023-11-28 00:16:21,375][87424] Updated weights for policy 0, policy_version 2346 (0.0009) -[2023-11-28 00:16:21,754][87424] Updated weights for policy 0, policy_version 2356 (0.0012) -[2023-11-28 00:16:22,137][87424] Updated weights for policy 0, policy_version 2366 (0.0008) -[2023-11-28 00:16:22,336][87426] Updated weights for policy 1, policy_version 2340 (0.0012) -[2023-11-28 00:16:22,710][87426] Updated weights for policy 1, policy_version 2350 (0.0011) -[2023-11-28 00:16:23,092][87426] Updated weights for policy 1, policy_version 2360 (0.0012) -[2023-11-28 00:16:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5243.6). Total num frames: 1212416. Throughput: 0: 2783.9, 1: 2722.8. Samples: 1226028. Policy #0 lag: (min: 14.0, avg: 28.9, max: 46.0) -[2023-11-28 00:16:23,445][86177] Avg episode reward: [(0, '-991.990'), (1, '-1172.910')] -[2023-11-28 00:16:23,446][87281] Saving new best policy, reward=-991.990! -[2023-11-28 00:16:24,241][87424] Updated weights for policy 0, policy_version 2376 (0.0012) -[2023-11-28 00:16:24,615][87424] Updated weights for policy 0, policy_version 2386 (0.0012) -[2023-11-28 00:16:25,006][87424] Updated weights for policy 0, policy_version 2396 (0.0012) -[2023-11-28 00:16:25,390][87426] Updated weights for policy 1, policy_version 2370 (0.0012) -[2023-11-28 00:16:25,770][87426] Updated weights for policy 1, policy_version 2380 (0.0009) -[2023-11-28 00:16:26,159][87426] Updated weights for policy 1, policy_version 2390 (0.0007) -[2023-11-28 00:16:26,544][87426] Updated weights for policy 1, policy_version 2400 (0.0007) -[2023-11-28 00:16:27,236][87424] Updated weights for policy 0, policy_version 2406 (0.0009) -[2023-11-28 00:16:27,611][87424] Updated weights for policy 0, policy_version 2416 (0.0007) -[2023-11-28 00:16:28,003][87424] Updated weights for policy 0, policy_version 2426 (0.0007) -[2023-11-28 00:16:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5236.7). Total num frames: 1236992. Throughput: 0: 2770.6, 1: 2717.7. Samples: 1250068. Policy #0 lag: (min: 4.0, avg: 29.4, max: 44.0) -[2023-11-28 00:16:28,445][86177] Avg episode reward: [(0, '-1001.260'), (1, '-1151.750')] -[2023-11-28 00:16:28,826][87426] Updated weights for policy 1, policy_version 2410 (0.0007) -[2023-11-28 00:16:29,215][87426] Updated weights for policy 1, policy_version 2420 (0.0008) -[2023-11-28 00:16:29,584][87426] Updated weights for policy 1, policy_version 2430 (0.0007) -[2023-11-28 00:16:29,962][87424] Updated weights for policy 0, policy_version 2436 (0.0009) -[2023-11-28 00:16:30,349][87424] Updated weights for policy 0, policy_version 2446 (0.0010) -[2023-11-28 00:16:30,738][87424] Updated weights for policy 0, policy_version 2456 (0.0008) -[2023-11-28 00:16:32,106][87426] Updated weights for policy 1, policy_version 2440 (0.0009) -[2023-11-28 00:16:32,487][87426] Updated weights for policy 1, policy_version 2450 (0.0011) -[2023-11-28 00:16:32,873][87426] Updated weights for policy 1, policy_version 2460 (0.0012) -[2023-11-28 00:16:33,054][87424] Updated weights for policy 0, policy_version 2466 (0.0008) -[2023-11-28 00:16:33,438][87424] Updated weights for policy 0, policy_version 2476 (0.0012) -[2023-11-28 00:16:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5230.0). Total num frames: 1261568. Throughput: 0: 2757.5, 1: 2715.7. Samples: 1273932. Policy #0 lag: (min: 4.0, avg: 29.4, max: 44.0) -[2023-11-28 00:16:33,445][86177] Avg episode reward: [(0, '-986.050'), (1, '-1130.490')] -[2023-11-28 00:16:33,451][87320] Saving new best policy, reward=-1130.490! -[2023-11-28 00:16:33,836][87424] Updated weights for policy 0, policy_version 2486 (0.0012) -[2023-11-28 00:16:34,202][87281] Saving new best policy, reward=-986.050! -[2023-11-28 00:16:34,204][87424] Updated weights for policy 0, policy_version 2496 (0.0012) -[2023-11-28 00:16:35,072][87426] Updated weights for policy 1, policy_version 2470 (0.0012) -[2023-11-28 00:16:35,447][87426] Updated weights for policy 1, policy_version 2480 (0.0012) -[2023-11-28 00:16:35,833][87426] Updated weights for policy 1, policy_version 2490 (0.0011) -[2023-11-28 00:16:36,038][87424] Updated weights for policy 0, policy_version 2506 (0.0012) -[2023-11-28 00:16:36,421][87424] Updated weights for policy 0, policy_version 2516 (0.0012) -[2023-11-28 00:16:36,795][87424] Updated weights for policy 0, policy_version 2526 (0.0012) -[2023-11-28 00:16:37,715][87426] Updated weights for policy 1, policy_version 2500 (0.0009) -[2023-11-28 00:16:38,093][87426] Updated weights for policy 1, policy_version 2510 (0.0010) -[2023-11-28 00:16:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5223.6). Total num frames: 1286144. Throughput: 0: 2749.2, 1: 2713.3. Samples: 1306116. Policy #0 lag: (min: 21.0, avg: 34.9, max: 53.0) -[2023-11-28 00:16:38,445][86177] Avg episode reward: [(0, '-970.090'), (1, '-1093.030')] -[2023-11-28 00:16:38,445][87281] Saving new best policy, reward=-970.090! -[2023-11-28 00:16:38,467][87426] Updated weights for policy 1, policy_version 2520 (0.0008) -[2023-11-28 00:16:38,778][87320] Saving new best policy, reward=-1093.030! -[2023-11-28 00:16:39,341][87424] Updated weights for policy 0, policy_version 2536 (0.0012) -[2023-11-28 00:16:39,719][87424] Updated weights for policy 0, policy_version 2546 (0.0012) -[2023-11-28 00:16:40,100][87424] Updated weights for policy 0, policy_version 2556 (0.0012) -[2023-11-28 00:16:41,027][87426] Updated weights for policy 1, policy_version 2530 (0.0008) -[2023-11-28 00:16:41,410][87426] Updated weights for policy 1, policy_version 2540 (0.0012) -[2023-11-28 00:16:41,783][87426] Updated weights for policy 1, policy_version 2550 (0.0012) -[2023-11-28 00:16:42,057][87424] Updated weights for policy 0, policy_version 2566 (0.0012) -[2023-11-28 00:16:42,169][87426] Updated weights for policy 1, policy_version 2560 (0.0010) -[2023-11-28 00:16:42,449][87424] Updated weights for policy 0, policy_version 2576 (0.0012) -[2023-11-28 00:16:42,833][87424] Updated weights for policy 0, policy_version 2586 (0.0010) -[2023-11-28 00:16:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5250.1). Total num frames: 1318912. Throughput: 0: 2729.9, 1: 2702.7. Samples: 1329240. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:16:43,446][86177] Avg episode reward: [(0, '-976.260'), (1, '-1065.470')] -[2023-11-28 00:16:43,447][87320] Saving new best policy, reward=-1065.470! -[2023-11-28 00:16:44,489][87426] Updated weights for policy 1, policy_version 2570 (0.0009) -[2023-11-28 00:16:44,862][87426] Updated weights for policy 1, policy_version 2580 (0.0011) -[2023-11-28 00:16:44,902][87424] Updated weights for policy 0, policy_version 2596 (0.0010) -[2023-11-28 00:16:45,242][87426] Updated weights for policy 1, policy_version 2590 (0.0010) -[2023-11-28 00:16:45,300][87424] Updated weights for policy 0, policy_version 2606 (0.0027) -[2023-11-28 00:16:45,664][87424] Updated weights for policy 0, policy_version 2616 (0.0012) -[2023-11-28 00:16:47,652][87426] Updated weights for policy 1, policy_version 2600 (0.0011) -[2023-11-28 00:16:47,739][87424] Updated weights for policy 0, policy_version 2626 (0.0012) -[2023-11-28 00:16:48,032][87426] Updated weights for policy 1, policy_version 2610 (0.0012) -[2023-11-28 00:16:48,116][87424] Updated weights for policy 0, policy_version 2636 (0.0009) -[2023-11-28 00:16:48,412][87426] Updated weights for policy 1, policy_version 2620 (0.0011) -[2023-11-28 00:16:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5211.6). Total num frames: 1335296. Throughput: 0: 2723.8, 1: 2688.6. Samples: 1353516. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 00:16:48,445][86177] Avg episode reward: [(0, '-987.610'), (1, '-1024.980')] -[2023-11-28 00:16:48,495][87424] Updated weights for policy 0, policy_version 2646 (0.0007) -[2023-11-28 00:16:48,565][87320] Saving new best policy, reward=-1024.980! -[2023-11-28 00:16:48,882][87424] Updated weights for policy 0, policy_version 2656 (0.0008) -[2023-11-28 00:16:50,853][87426] Updated weights for policy 1, policy_version 2630 (0.0012) -[2023-11-28 00:16:50,947][87424] Updated weights for policy 0, policy_version 2666 (0.0011) -[2023-11-28 00:16:51,224][87426] Updated weights for policy 1, policy_version 2640 (0.0011) -[2023-11-28 00:16:51,326][87424] Updated weights for policy 0, policy_version 2676 (0.0011) -[2023-11-28 00:16:51,623][87426] Updated weights for policy 1, policy_version 2650 (0.0009) -[2023-11-28 00:16:51,711][87424] Updated weights for policy 0, policy_version 2686 (0.0010) -[2023-11-28 00:16:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5237.3). Total num frames: 1368064. Throughput: 0: 2728.6, 1: 2661.1. Samples: 1385864. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 00:16:53,445][86177] Avg episode reward: [(0, '-974.680'), (1, '-1028.980')] -[2023-11-28 00:16:53,653][87426] Updated weights for policy 1, policy_version 2660 (0.0009) -[2023-11-28 00:16:53,829][87424] Updated weights for policy 0, policy_version 2696 (0.0011) -[2023-11-28 00:16:54,032][87426] Updated weights for policy 1, policy_version 2670 (0.0011) -[2023-11-28 00:16:54,217][87424] Updated weights for policy 0, policy_version 2706 (0.0012) -[2023-11-28 00:16:54,416][87426] Updated weights for policy 1, policy_version 2680 (0.0010) -[2023-11-28 00:16:54,592][87424] Updated weights for policy 0, policy_version 2716 (0.0011) -[2023-11-28 00:16:56,437][87424] Updated weights for policy 0, policy_version 2726 (0.0011) -[2023-11-28 00:16:56,655][87426] Updated weights for policy 1, policy_version 2690 (0.0008) -[2023-11-28 00:16:56,824][87424] Updated weights for policy 0, policy_version 2736 (0.0012) -[2023-11-28 00:16:57,036][87426] Updated weights for policy 1, policy_version 2700 (0.0007) -[2023-11-28 00:16:57,206][87424] Updated weights for policy 0, policy_version 2746 (0.0012) -[2023-11-28 00:16:57,422][87426] Updated weights for policy 1, policy_version 2710 (0.0007) -[2023-11-28 00:16:57,802][87426] Updated weights for policy 1, policy_version 2720 (0.0007) -[2023-11-28 00:16:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5262.0). Total num frames: 1400832. Throughput: 0: 2723.6, 1: 2650.8. Samples: 1410136. Policy #0 lag: (min: 15.0, avg: 21.6, max: 47.0) -[2023-11-28 00:16:58,445][86177] Avg episode reward: [(0, '-977.840'), (1, '-1024.150')] -[2023-11-28 00:16:58,446][87320] Saving new best policy, reward=-1024.150! -[2023-11-28 00:16:59,271][87424] Updated weights for policy 0, policy_version 2756 (0.0010) -[2023-11-28 00:16:59,654][87424] Updated weights for policy 0, policy_version 2766 (0.0007) -[2023-11-28 00:17:00,044][87424] Updated weights for policy 0, policy_version 2776 (0.0010) -[2023-11-28 00:17:00,151][87426] Updated weights for policy 1, policy_version 2730 (0.0008) -[2023-11-28 00:17:00,535][87426] Updated weights for policy 1, policy_version 2740 (0.0010) -[2023-11-28 00:17:00,924][87426] Updated weights for policy 1, policy_version 2750 (0.0008) -[2023-11-28 00:17:02,546][87424] Updated weights for policy 0, policy_version 2786 (0.0011) -[2023-11-28 00:17:02,924][87424] Updated weights for policy 0, policy_version 2796 (0.0010) -[2023-11-28 00:17:03,301][87424] Updated weights for policy 0, policy_version 2806 (0.0008) -[2023-11-28 00:17:03,402][87426] Updated weights for policy 1, policy_version 2760 (0.0008) -[2023-11-28 00:17:03,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5225.4). Total num frames: 1417216. Throughput: 0: 2737.1, 1: 2643.1. Samples: 1435364. Policy #0 lag: (min: 15.0, avg: 21.6, max: 47.0) -[2023-11-28 00:17:03,446][86177] Avg episode reward: [(0, '-958.440'), (1, '-1011.720')] -[2023-11-28 00:17:03,674][87281] Saving new best policy, reward=-958.440! -[2023-11-28 00:17:03,679][87424] Updated weights for policy 0, policy_version 2816 (0.0011) -[2023-11-28 00:17:03,793][87426] Updated weights for policy 1, policy_version 2770 (0.0012) -[2023-11-28 00:17:04,168][87426] Updated weights for policy 1, policy_version 2780 (0.0011) -[2023-11-28 00:17:04,316][87320] Saving new best policy, reward=-1011.720! -[2023-11-28 00:17:05,859][87424] Updated weights for policy 0, policy_version 2826 (0.0012) -[2023-11-28 00:17:06,240][87424] Updated weights for policy 0, policy_version 2836 (0.0012) -[2023-11-28 00:17:06,560][87426] Updated weights for policy 1, policy_version 2790 (0.0009) -[2023-11-28 00:17:06,627][87424] Updated weights for policy 0, policy_version 2846 (0.0008) -[2023-11-28 00:17:06,935][87426] Updated weights for policy 1, policy_version 2800 (0.0008) -[2023-11-28 00:17:07,317][87426] Updated weights for policy 1, policy_version 2810 (0.0007) -[2023-11-28 00:17:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5249.4). Total num frames: 1449984. Throughput: 0: 2727.6, 1: 2633.0. Samples: 1467252. Policy #0 lag: (min: 19.0, avg: 33.3, max: 51.0) -[2023-11-28 00:17:08,445][86177] Avg episode reward: [(0, '-930.050'), (1, '-1000.940')] -[2023-11-28 00:17:08,446][87281] Saving new best policy, reward=-930.050! -[2023-11-28 00:17:08,446][87320] Saving new best policy, reward=-1000.940! -[2023-11-28 00:17:09,144][87424] Updated weights for policy 0, policy_version 2856 (0.0010) -[2023-11-28 00:17:09,528][87424] Updated weights for policy 0, policy_version 2866 (0.0011) -[2023-11-28 00:17:09,823][87426] Updated weights for policy 1, policy_version 2820 (0.0009) -[2023-11-28 00:17:09,912][87424] Updated weights for policy 0, policy_version 2876 (0.0011) -[2023-11-28 00:17:10,203][87426] Updated weights for policy 1, policy_version 2830 (0.0010) -[2023-11-28 00:17:10,597][87426] Updated weights for policy 1, policy_version 2840 (0.0010) -[2023-11-28 00:17:12,309][87424] Updated weights for policy 0, policy_version 2886 (0.0011) -[2023-11-28 00:17:12,460][87426] Updated weights for policy 1, policy_version 2850 (0.0012) -[2023-11-28 00:17:12,691][87424] Updated weights for policy 0, policy_version 2896 (0.0011) -[2023-11-28 00:17:12,837][87426] Updated weights for policy 1, policy_version 2860 (0.0010) -[2023-11-28 00:17:13,070][87424] Updated weights for policy 0, policy_version 2906 (0.0011) -[2023-11-28 00:17:13,218][87426] Updated weights for policy 1, policy_version 2870 (0.0008) -[2023-11-28 00:17:13,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5243.5). Total num frames: 1474560. Throughput: 0: 2720.5, 1: 2626.0. Samples: 1490664. Policy #0 lag: (min: 39.0, avg: 52.6, max: 80.0) -[2023-11-28 00:17:13,445][86177] Avg episode reward: [(0, '-909.600'), (1, '-987.520')] -[2023-11-28 00:17:13,446][87281] Saving new best policy, reward=-909.600! -[2023-11-28 00:17:13,599][87426] Updated weights for policy 1, policy_version 2880 (0.0007) -[2023-11-28 00:17:13,599][87320] Saving new best policy, reward=-987.520! -[2023-11-28 00:17:15,404][87424] Updated weights for policy 0, policy_version 2916 (0.0011) -[2023-11-28 00:17:15,781][87424] Updated weights for policy 0, policy_version 2926 (0.0010) -[2023-11-28 00:17:16,091][87426] Updated weights for policy 1, policy_version 2890 (0.0011) -[2023-11-28 00:17:16,166][87424] Updated weights for policy 0, policy_version 2936 (0.0007) -[2023-11-28 00:17:16,467][87426] Updated weights for policy 1, policy_version 2900 (0.0011) -[2023-11-28 00:17:16,841][87426] Updated weights for policy 1, policy_version 2910 (0.0012) -[2023-11-28 00:17:18,371][87424] Updated weights for policy 0, policy_version 2946 (0.0009) -[2023-11-28 00:17:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5237.8). Total num frames: 1499136. Throughput: 0: 2707.4, 1: 2630.4. Samples: 1514132. Policy #0 lag: (min: 3.0, avg: 27.0, max: 45.0) -[2023-11-28 00:17:18,445][86177] Avg episode reward: [(0, '-901.370'), (1, '-1014.610')] -[2023-11-28 00:17:18,749][87424] Updated weights for policy 0, policy_version 2956 (0.0010) -[2023-11-28 00:17:18,831][87426] Updated weights for policy 1, policy_version 2920 (0.0012) -[2023-11-28 00:17:19,135][87424] Updated weights for policy 0, policy_version 2966 (0.0010) -[2023-11-28 00:17:19,205][87426] Updated weights for policy 1, policy_version 2930 (0.0012) -[2023-11-28 00:17:19,518][87281] Saving new best policy, reward=-901.370! -[2023-11-28 00:17:19,520][87424] Updated weights for policy 0, policy_version 2976 (0.0011) -[2023-11-28 00:17:19,587][87426] Updated weights for policy 1, policy_version 2940 (0.0011) -[2023-11-28 00:17:21,492][87424] Updated weights for policy 0, policy_version 2986 (0.0010) -[2023-11-28 00:17:21,666][87426] Updated weights for policy 1, policy_version 2950 (0.0010) -[2023-11-28 00:17:21,876][87424] Updated weights for policy 0, policy_version 2996 (0.0010) -[2023-11-28 00:17:22,053][87426] Updated weights for policy 1, policy_version 2960 (0.0009) -[2023-11-28 00:17:22,260][87424] Updated weights for policy 0, policy_version 3006 (0.0011) -[2023-11-28 00:17:22,425][87426] Updated weights for policy 1, policy_version 2970 (0.0011) -[2023-11-28 00:17:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5260.4). Total num frames: 1531904. Throughput: 0: 2697.2, 1: 2625.4. Samples: 1545636. Policy #0 lag: (min: 31.0, avg: 55.9, max: 95.0) -[2023-11-28 00:17:23,445][86177] Avg episode reward: [(0, '-903.210'), (1, '-1025.450')] -[2023-11-28 00:17:24,559][87426] Updated weights for policy 1, policy_version 2980 (0.0012) -[2023-11-28 00:17:24,828][87424] Updated weights for policy 0, policy_version 3016 (0.0008) -[2023-11-28 00:17:24,933][87426] Updated weights for policy 1, policy_version 2990 (0.0011) -[2023-11-28 00:17:25,210][87424] Updated weights for policy 0, policy_version 3026 (0.0009) -[2023-11-28 00:17:25,315][87426] Updated weights for policy 1, policy_version 3000 (0.0007) -[2023-11-28 00:17:25,601][87424] Updated weights for policy 0, policy_version 3036 (0.0008) -[2023-11-28 00:17:27,014][87426] Updated weights for policy 1, policy_version 3010 (0.0007) -[2023-11-28 00:17:27,389][87426] Updated weights for policy 1, policy_version 3020 (0.0011) -[2023-11-28 00:17:27,780][87426] Updated weights for policy 1, policy_version 3030 (0.0011) -[2023-11-28 00:17:28,004][87424] Updated weights for policy 0, policy_version 3046 (0.0009) -[2023-11-28 00:17:28,157][87426] Updated weights for policy 1, policy_version 3040 (0.0008) -[2023-11-28 00:17:28,390][87424] Updated weights for policy 0, policy_version 3056 (0.0007) -[2023-11-28 00:17:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5276.2). Total num frames: 1556480. Throughput: 0: 2709.1, 1: 2651.8. Samples: 1570480. Policy #0 lag: (min: 31.0, avg: 55.9, max: 95.0) -[2023-11-28 00:17:28,445][86177] Avg episode reward: [(0, '-905.510'), (1, '-1043.980')] -[2023-11-28 00:17:28,775][87424] Updated weights for policy 0, policy_version 3066 (0.0007) -[2023-11-28 00:17:30,587][87426] Updated weights for policy 1, policy_version 3050 (0.0011) -[2023-11-28 00:17:30,969][87426] Updated weights for policy 1, policy_version 3060 (0.0011) -[2023-11-28 00:17:31,149][87424] Updated weights for policy 0, policy_version 3076 (0.0008) -[2023-11-28 00:17:31,350][87426] Updated weights for policy 1, policy_version 3070 (0.0008) -[2023-11-28 00:17:31,533][87424] Updated weights for policy 0, policy_version 3086 (0.0007) -[2023-11-28 00:17:31,917][87424] Updated weights for policy 0, policy_version 3096 (0.0008) -[2023-11-28 00:17:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 1581056. Throughput: 0: 2674.1, 1: 2650.7. Samples: 1593136. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:17:33,445][86177] Avg episode reward: [(0, '-878.920'), (1, '-1026.990')] -[2023-11-28 00:17:33,454][87281] Saving new best policy, reward=-878.920! -[2023-11-28 00:17:33,463][87426] Updated weights for policy 1, policy_version 3080 (0.0011) -[2023-11-28 00:17:33,841][87426] Updated weights for policy 1, policy_version 3090 (0.0011) -[2023-11-28 00:17:34,223][87426] Updated weights for policy 1, policy_version 3100 (0.0011) -[2023-11-28 00:17:34,309][87424] Updated weights for policy 0, policy_version 3106 (0.0009) -[2023-11-28 00:17:34,696][87424] Updated weights for policy 0, policy_version 3116 (0.0008) -[2023-11-28 00:17:35,085][87424] Updated weights for policy 0, policy_version 3126 (0.0008) -[2023-11-28 00:17:35,474][87424] Updated weights for policy 0, policy_version 3136 (0.0009) -[2023-11-28 00:17:36,199][87426] Updated weights for policy 1, policy_version 3110 (0.0009) -[2023-11-28 00:17:36,583][87426] Updated weights for policy 1, policy_version 3120 (0.0008) -[2023-11-28 00:17:36,968][87426] Updated weights for policy 1, policy_version 3130 (0.0011) -[2023-11-28 00:17:37,335][87424] Updated weights for policy 0, policy_version 3146 (0.0012) -[2023-11-28 00:17:37,720][87424] Updated weights for policy 0, policy_version 3156 (0.0009) -[2023-11-28 00:17:38,109][87424] Updated weights for policy 0, policy_version 3166 (0.0007) -[2023-11-28 00:17:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 1613824. Throughput: 0: 2666.4, 1: 2656.0. Samples: 1625372. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 00:17:38,445][86177] Avg episode reward: [(0, '-883.710'), (1, '-1041.040')] -[2023-11-28 00:17:39,510][87426] Updated weights for policy 1, policy_version 3140 (0.0010) -[2023-11-28 00:17:39,893][87426] Updated weights for policy 1, policy_version 3150 (0.0009) -[2023-11-28 00:17:40,273][87426] Updated weights for policy 1, policy_version 3160 (0.0009) -[2023-11-28 00:17:40,517][87424] Updated weights for policy 0, policy_version 3176 (0.0009) -[2023-11-28 00:17:40,896][87424] Updated weights for policy 0, policy_version 3186 (0.0011) -[2023-11-28 00:17:41,284][87424] Updated weights for policy 0, policy_version 3196 (0.0010) -[2023-11-28 00:17:42,627][87426] Updated weights for policy 1, policy_version 3170 (0.0010) -[2023-11-28 00:17:43,007][87426] Updated weights for policy 1, policy_version 3180 (0.0010) -[2023-11-28 00:17:43,385][87426] Updated weights for policy 1, policy_version 3190 (0.0009) -[2023-11-28 00:17:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5442.8). Total num frames: 1630208. Throughput: 0: 2658.0, 1: 2670.4. Samples: 1649912. Policy #0 lag: (min: 29.0, avg: 54.5, max: 72.0) -[2023-11-28 00:17:43,445][86177] Avg episode reward: [(0, '-881.150'), (1, '-1027.270')] -[2023-11-28 00:17:43,721][87424] Updated weights for policy 0, policy_version 3206 (0.0008) -[2023-11-28 00:17:43,762][87426] Updated weights for policy 1, policy_version 3200 (0.0010) -[2023-11-28 00:17:44,094][87424] Updated weights for policy 0, policy_version 3216 (0.0012) -[2023-11-28 00:17:44,472][87424] Updated weights for policy 0, policy_version 3226 (0.0012) -[2023-11-28 00:17:45,529][87426] Updated weights for policy 1, policy_version 3210 (0.0012) -[2023-11-28 00:17:45,911][87426] Updated weights for policy 1, policy_version 3220 (0.0008) -[2023-11-28 00:17:46,289][87426] Updated weights for policy 1, policy_version 3230 (0.0007) -[2023-11-28 00:17:46,563][87424] Updated weights for policy 0, policy_version 3236 (0.0012) -[2023-11-28 00:17:46,941][87424] Updated weights for policy 0, policy_version 3246 (0.0012) -[2023-11-28 00:17:47,334][87424] Updated weights for policy 0, policy_version 3256 (0.0012) -[2023-11-28 00:17:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 1662976. Throughput: 0: 2614.6, 1: 2701.6. Samples: 1674592. Policy #0 lag: (min: 19.0, avg: 37.2, max: 51.0) -[2023-11-28 00:17:48,445][86177] Avg episode reward: [(0, '-855.450'), (1, '-1001.560')] -[2023-11-28 00:17:48,457][87281] Saving new best policy, reward=-855.450! -[2023-11-28 00:17:48,686][87426] Updated weights for policy 1, policy_version 3240 (0.0008) -[2023-11-28 00:17:49,057][87426] Updated weights for policy 1, policy_version 3250 (0.0008) -[2023-11-28 00:17:49,436][87426] Updated weights for policy 1, policy_version 3260 (0.0007) -[2023-11-28 00:17:49,753][87424] Updated weights for policy 0, policy_version 3266 (0.0011) -[2023-11-28 00:17:50,132][87424] Updated weights for policy 0, policy_version 3276 (0.0010) -[2023-11-28 00:17:50,514][87424] Updated weights for policy 0, policy_version 3286 (0.0009) -[2023-11-28 00:17:50,901][87424] Updated weights for policy 0, policy_version 3296 (0.0011) -[2023-11-28 00:17:51,932][87426] Updated weights for policy 1, policy_version 3270 (0.0008) -[2023-11-28 00:17:52,311][87426] Updated weights for policy 1, policy_version 3280 (0.0008) -[2023-11-28 00:17:52,689][87426] Updated weights for policy 1, policy_version 3290 (0.0011) -[2023-11-28 00:17:53,007][87424] Updated weights for policy 0, policy_version 3306 (0.0011) -[2023-11-28 00:17:53,391][87424] Updated weights for policy 0, policy_version 3316 (0.0011) -[2023-11-28 00:17:53,445][86177] Fps is (10 sec: 5733.8, 60 sec: 5324.7, 300 sec: 5442.8). Total num frames: 1687552. Throughput: 0: 2613.6, 1: 2685.7. Samples: 1705728. Policy #0 lag: (min: 19.0, avg: 37.2, max: 51.0) -[2023-11-28 00:17:53,446][86177] Avg episode reward: [(0, '-835.080'), (1, '-943.490')] -[2023-11-28 00:17:53,448][87320] Saving new best policy, reward=-943.490! -[2023-11-28 00:17:53,778][87424] Updated weights for policy 0, policy_version 3326 (0.0012) -[2023-11-28 00:17:53,853][87281] Saving new best policy, reward=-835.080! -[2023-11-28 00:17:54,681][87426] Updated weights for policy 1, policy_version 3300 (0.0009) -[2023-11-28 00:17:55,065][87426] Updated weights for policy 1, policy_version 3310 (0.0008) -[2023-11-28 00:17:55,452][87426] Updated weights for policy 1, policy_version 3320 (0.0009) -[2023-11-28 00:17:56,313][87424] Updated weights for policy 0, policy_version 3336 (0.0011) -[2023-11-28 00:17:56,686][87424] Updated weights for policy 0, policy_version 3346 (0.0011) -[2023-11-28 00:17:57,074][87424] Updated weights for policy 0, policy_version 3356 (0.0011) -[2023-11-28 00:17:57,567][87426] Updated weights for policy 1, policy_version 3330 (0.0008) -[2023-11-28 00:17:57,939][87426] Updated weights for policy 1, policy_version 3340 (0.0011) -[2023-11-28 00:17:58,330][87426] Updated weights for policy 1, policy_version 3350 (0.0011) -[2023-11-28 00:17:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 1712128. Throughput: 0: 2626.0, 1: 2721.1. Samples: 1731284. Policy #0 lag: (min: 31.0, avg: 51.3, max: 85.0) -[2023-11-28 00:17:58,445][86177] Avg episode reward: [(0, '-811.370'), (1, '-894.990')] -[2023-11-28 00:17:58,697][87424] Updated weights for policy 0, policy_version 3366 (0.0010) -[2023-11-28 00:17:58,706][87320] Saving new best policy, reward=-894.990! -[2023-11-28 00:17:58,710][87426] Updated weights for policy 1, policy_version 3360 (0.0011) -[2023-11-28 00:17:59,093][87424] Updated weights for policy 0, policy_version 3376 (0.0008) -[2023-11-28 00:17:59,473][87424] Updated weights for policy 0, policy_version 3386 (0.0008) -[2023-11-28 00:17:59,708][87281] Saving new best policy, reward=-811.370! -[2023-11-28 00:18:00,792][87426] Updated weights for policy 1, policy_version 3370 (0.0012) -[2023-11-28 00:18:01,142][87424] Updated weights for policy 0, policy_version 3396 (0.0008) -[2023-11-28 00:18:01,164][87426] Updated weights for policy 1, policy_version 3380 (0.0011) -[2023-11-28 00:18:01,523][87424] Updated weights for policy 0, policy_version 3406 (0.0008) -[2023-11-28 00:18:01,548][87426] Updated weights for policy 1, policy_version 3390 (0.0012) -[2023-11-28 00:18:01,907][87424] Updated weights for policy 0, policy_version 3416 (0.0010) -[2023-11-28 00:18:03,444][86177] Fps is (10 sec: 5735.0, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 1744896. Throughput: 0: 2678.2, 1: 2728.2. Samples: 1757420. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:18:03,445][86177] Avg episode reward: [(0, '-832.980'), (1, '-859.400')] -[2023-11-28 00:18:03,650][87426] Updated weights for policy 1, policy_version 3400 (0.0011) -[2023-11-28 00:18:03,725][87424] Updated weights for policy 0, policy_version 3426 (0.0011) -[2023-11-28 00:18:04,033][87426] Updated weights for policy 1, policy_version 3410 (0.0008) -[2023-11-28 00:18:04,111][87424] Updated weights for policy 0, policy_version 3436 (0.0012) -[2023-11-28 00:18:04,404][87426] Updated weights for policy 1, policy_version 3420 (0.0009) -[2023-11-28 00:18:04,490][87424] Updated weights for policy 0, policy_version 3446 (0.0012) -[2023-11-28 00:18:04,552][87320] Saving new best policy, reward=-859.400! -[2023-11-28 00:18:04,877][87424] Updated weights for policy 0, policy_version 3456 (0.0012) -[2023-11-28 00:18:06,214][87426] Updated weights for policy 1, policy_version 3430 (0.0010) -[2023-11-28 00:18:06,591][87426] Updated weights for policy 1, policy_version 3440 (0.0008) -[2023-11-28 00:18:06,969][87426] Updated weights for policy 1, policy_version 3450 (0.0008) -[2023-11-28 00:18:07,394][87424] Updated weights for policy 0, policy_version 3466 (0.0008) -[2023-11-28 00:18:07,770][87424] Updated weights for policy 0, policy_version 3476 (0.0007) -[2023-11-28 00:18:08,155][87424] Updated weights for policy 0, policy_version 3486 (0.0008) -[2023-11-28 00:18:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 1777664. Throughput: 0: 2689.4, 1: 2748.5. Samples: 1790344. Policy #0 lag: (min: 7.0, avg: 14.2, max: 39.0) -[2023-11-28 00:18:08,445][86177] Avg episode reward: [(0, '-818.200'), (1, '-821.450')] -[2023-11-28 00:18:08,446][87320] Saving new best policy, reward=-821.450! -[2023-11-28 00:18:08,974][87426] Updated weights for policy 1, policy_version 3460 (0.0008) -[2023-11-28 00:18:09,358][87426] Updated weights for policy 1, policy_version 3470 (0.0009) -[2023-11-28 00:18:09,740][87426] Updated weights for policy 1, policy_version 3480 (0.0010) -[2023-11-28 00:18:10,004][87424] Updated weights for policy 0, policy_version 3496 (0.0010) -[2023-11-28 00:18:10,391][87424] Updated weights for policy 0, policy_version 3506 (0.0011) -[2023-11-28 00:18:10,770][87424] Updated weights for policy 0, policy_version 3516 (0.0011) -[2023-11-28 00:18:12,208][87426] Updated weights for policy 1, policy_version 3490 (0.0010) -[2023-11-28 00:18:12,593][87426] Updated weights for policy 1, policy_version 3500 (0.0010) -[2023-11-28 00:18:12,974][87426] Updated weights for policy 1, policy_version 3510 (0.0012) -[2023-11-28 00:18:13,319][87424] Updated weights for policy 0, policy_version 3526 (0.0011) -[2023-11-28 00:18:13,356][87426] Updated weights for policy 1, policy_version 3520 (0.0011) -[2023-11-28 00:18:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 1802240. Throughput: 0: 2701.7, 1: 2717.8. Samples: 1814356. Policy #0 lag: (min: 7.0, avg: 14.2, max: 39.0) -[2023-11-28 00:18:13,445][86177] Avg episode reward: [(0, '-832.540'), (1, '-818.410')] -[2023-11-28 00:18:13,445][87320] Saving new best policy, reward=-818.410! -[2023-11-28 00:18:13,704][87424] Updated weights for policy 0, policy_version 3536 (0.0012) -[2023-11-28 00:18:14,095][87424] Updated weights for policy 0, policy_version 3546 (0.0011) -[2023-11-28 00:18:15,354][87426] Updated weights for policy 1, policy_version 3530 (0.0009) -[2023-11-28 00:18:15,737][87426] Updated weights for policy 1, policy_version 3540 (0.0011) -[2023-11-28 00:18:16,116][87426] Updated weights for policy 1, policy_version 3550 (0.0010) -[2023-11-28 00:18:16,656][87424] Updated weights for policy 0, policy_version 3556 (0.0011) -[2023-11-28 00:18:17,034][87424] Updated weights for policy 0, policy_version 3566 (0.0011) -[2023-11-28 00:18:17,422][87424] Updated weights for policy 0, policy_version 3576 (0.0008) -[2023-11-28 00:18:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 1826816. Throughput: 0: 2727.0, 1: 2733.9. Samples: 1838876. Policy #0 lag: (min: 31.0, avg: 53.9, max: 95.0) -[2023-11-28 00:18:18,445][86177] Avg episode reward: [(0, '-838.640'), (1, '-823.170')] -[2023-11-28 00:18:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000003584_917504.pth... -[2023-11-28 00:18:18,497][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000001056_270336.pth -[2023-11-28 00:18:18,537][87426] Updated weights for policy 1, policy_version 3560 (0.0011) -[2023-11-28 00:18:18,908][87426] Updated weights for policy 1, policy_version 3570 (0.0012) -[2023-11-28 00:18:19,280][87426] Updated weights for policy 1, policy_version 3580 (0.0011) -[2023-11-28 00:18:19,314][87424] Updated weights for policy 0, policy_version 3586 (0.0009) -[2023-11-28 00:18:19,431][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000003584_917504.pth... -[2023-11-28 00:18:19,477][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000001024_262144.pth -[2023-11-28 00:18:19,699][87424] Updated weights for policy 0, policy_version 3596 (0.0012) -[2023-11-28 00:18:20,080][87424] Updated weights for policy 0, policy_version 3606 (0.0012) -[2023-11-28 00:18:20,456][87424] Updated weights for policy 0, policy_version 3616 (0.0012) -[2023-11-28 00:18:21,623][87426] Updated weights for policy 1, policy_version 3590 (0.0012) -[2023-11-28 00:18:22,006][87426] Updated weights for policy 1, policy_version 3600 (0.0012) -[2023-11-28 00:18:22,380][87426] Updated weights for policy 1, policy_version 3610 (0.0011) -[2023-11-28 00:18:22,457][87424] Updated weights for policy 0, policy_version 3626 (0.0011) -[2023-11-28 00:18:22,828][87424] Updated weights for policy 0, policy_version 3636 (0.0011) -[2023-11-28 00:18:23,207][87424] Updated weights for policy 0, policy_version 3646 (0.0010) -[2023-11-28 00:18:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 1859584. Throughput: 0: 2722.6, 1: 2734.1. Samples: 1870924. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 00:18:23,445][86177] Avg episode reward: [(0, '-830.590'), (1, '-828.920')] -[2023-11-28 00:18:24,700][87426] Updated weights for policy 1, policy_version 3620 (0.0011) -[2023-11-28 00:18:25,080][87426] Updated weights for policy 1, policy_version 3630 (0.0009) -[2023-11-28 00:18:25,142][87424] Updated weights for policy 0, policy_version 3656 (0.0010) -[2023-11-28 00:18:25,453][87426] Updated weights for policy 1, policy_version 3640 (0.0008) -[2023-11-28 00:18:25,526][87424] Updated weights for policy 0, policy_version 3666 (0.0009) -[2023-11-28 00:18:25,923][87424] Updated weights for policy 0, policy_version 3676 (0.0007) -[2023-11-28 00:18:27,606][87426] Updated weights for policy 1, policy_version 3650 (0.0009) -[2023-11-28 00:18:27,979][87426] Updated weights for policy 1, policy_version 3660 (0.0007) -[2023-11-28 00:18:28,321][87424] Updated weights for policy 0, policy_version 3686 (0.0008) -[2023-11-28 00:18:28,355][87426] Updated weights for policy 1, policy_version 3670 (0.0008) -[2023-11-28 00:18:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 1875968. Throughput: 0: 2745.0, 1: 2733.2. Samples: 1896432. Policy #0 lag: (min: 21.0, avg: 39.2, max: 64.0) -[2023-11-28 00:18:28,445][86177] Avg episode reward: [(0, '-844.820'), (1, '-809.630')] -[2023-11-28 00:18:28,714][87424] Updated weights for policy 0, policy_version 3696 (0.0012) -[2023-11-28 00:18:28,734][87320] Saving new best policy, reward=-809.630! -[2023-11-28 00:18:28,738][87426] Updated weights for policy 1, policy_version 3680 (0.0010) -[2023-11-28 00:18:29,086][87424] Updated weights for policy 0, policy_version 3706 (0.0012) -[2023-11-28 00:18:30,934][87426] Updated weights for policy 1, policy_version 3690 (0.0007) -[2023-11-28 00:18:31,071][87424] Updated weights for policy 0, policy_version 3716 (0.0011) -[2023-11-28 00:18:31,316][87426] Updated weights for policy 1, policy_version 3700 (0.0008) -[2023-11-28 00:18:31,451][87424] Updated weights for policy 0, policy_version 3726 (0.0010) -[2023-11-28 00:18:31,697][87426] Updated weights for policy 1, policy_version 3710 (0.0008) -[2023-11-28 00:18:31,838][87424] Updated weights for policy 0, policy_version 3736 (0.0010) -[2023-11-28 00:18:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 1908736. Throughput: 0: 2757.3, 1: 2711.8. Samples: 1920700. Policy #0 lag: (min: 31.0, avg: 49.7, max: 76.0) -[2023-11-28 00:18:33,445][86177] Avg episode reward: [(0, '-816.210'), (1, '-790.310')] -[2023-11-28 00:18:33,746][87426] Updated weights for policy 1, policy_version 3720 (0.0010) -[2023-11-28 00:18:33,991][87424] Updated weights for policy 0, policy_version 3746 (0.0011) -[2023-11-28 00:18:34,125][87426] Updated weights for policy 1, policy_version 3730 (0.0007) -[2023-11-28 00:18:34,389][87424] Updated weights for policy 0, policy_version 3756 (0.0011) -[2023-11-28 00:18:34,491][87426] Updated weights for policy 1, policy_version 3740 (0.0008) -[2023-11-28 00:18:34,641][87320] Saving new best policy, reward=-790.310! -[2023-11-28 00:18:34,765][87424] Updated weights for policy 0, policy_version 3766 (0.0012) -[2023-11-28 00:18:35,160][87424] Updated weights for policy 0, policy_version 3776 (0.0011) -[2023-11-28 00:18:36,411][87426] Updated weights for policy 1, policy_version 3750 (0.0010) -[2023-11-28 00:18:36,788][87426] Updated weights for policy 1, policy_version 3760 (0.0011) -[2023-11-28 00:18:37,076][87424] Updated weights for policy 0, policy_version 3786 (0.0011) -[2023-11-28 00:18:37,165][87426] Updated weights for policy 1, policy_version 3770 (0.0012) -[2023-11-28 00:18:37,456][87424] Updated weights for policy 0, policy_version 3796 (0.0012) -[2023-11-28 00:18:37,832][87424] Updated weights for policy 0, policy_version 3806 (0.0012) -[2023-11-28 00:18:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 1941504. Throughput: 0: 2762.4, 1: 2756.2. Samples: 1954064. Policy #0 lag: (min: 31.0, avg: 55.6, max: 95.0) -[2023-11-28 00:18:38,446][86177] Avg episode reward: [(0, '-792.360'), (1, '-789.300')] -[2023-11-28 00:18:38,447][87281] Saving new best policy, reward=-792.360! -[2023-11-28 00:18:38,447][87320] Saving new best policy, reward=-789.300! -[2023-11-28 00:18:39,257][87426] Updated weights for policy 1, policy_version 3780 (0.0010) -[2023-11-28 00:18:39,637][87426] Updated weights for policy 1, policy_version 3790 (0.0008) -[2023-11-28 00:18:40,008][87426] Updated weights for policy 1, policy_version 3800 (0.0009) -[2023-11-28 00:18:40,225][87424] Updated weights for policy 0, policy_version 3816 (0.0008) -[2023-11-28 00:18:40,611][87424] Updated weights for policy 0, policy_version 3826 (0.0010) -[2023-11-28 00:18:40,992][87424] Updated weights for policy 0, policy_version 3836 (0.0011) -[2023-11-28 00:18:42,339][87426] Updated weights for policy 1, policy_version 3810 (0.0008) -[2023-11-28 00:18:42,715][87426] Updated weights for policy 1, policy_version 3820 (0.0011) -[2023-11-28 00:18:43,093][87426] Updated weights for policy 1, policy_version 3830 (0.0011) -[2023-11-28 00:18:43,434][87424] Updated weights for policy 0, policy_version 3846 (0.0010) -[2023-11-28 00:18:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 1957888. Throughput: 0: 2754.8, 1: 2725.9. Samples: 1977916. Policy #0 lag: (min: 31.0, avg: 55.6, max: 95.0) -[2023-11-28 00:18:43,445][86177] Avg episode reward: [(0, '-797.420'), (1, '-792.550')] -[2023-11-28 00:18:43,472][87426] Updated weights for policy 1, policy_version 3840 (0.0011) -[2023-11-28 00:18:43,821][87424] Updated weights for policy 0, policy_version 3856 (0.0012) -[2023-11-28 00:18:44,217][87424] Updated weights for policy 0, policy_version 3866 (0.0010) -[2023-11-28 00:18:45,568][87426] Updated weights for policy 1, policy_version 3850 (0.0008) -[2023-11-28 00:18:45,948][87426] Updated weights for policy 1, policy_version 3860 (0.0011) -[2023-11-28 00:18:46,276][87424] Updated weights for policy 0, policy_version 3876 (0.0009) -[2023-11-28 00:18:46,336][87426] Updated weights for policy 1, policy_version 3870 (0.0011) -[2023-11-28 00:18:46,667][87424] Updated weights for policy 0, policy_version 3886 (0.0011) -[2023-11-28 00:18:47,064][87424] Updated weights for policy 0, policy_version 3896 (0.0012) -[2023-11-28 00:18:48,402][87426] Updated weights for policy 1, policy_version 3880 (0.0012) -[2023-11-28 00:18:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 1990656. Throughput: 0: 2710.3, 1: 2743.3. Samples: 2002832. Policy #0 lag: (min: 23.0, avg: 51.0, max: 81.0) -[2023-11-28 00:18:48,445][86177] Avg episode reward: [(0, '-811.540'), (1, '-769.520')] -[2023-11-28 00:18:48,788][87426] Updated weights for policy 1, policy_version 3890 (0.0012) -[2023-11-28 00:18:49,166][87426] Updated weights for policy 1, policy_version 3900 (0.0009) -[2023-11-28 00:18:49,318][87320] Saving new best policy, reward=-769.520! -[2023-11-28 00:18:49,590][87424] Updated weights for policy 0, policy_version 3906 (0.0012) -[2023-11-28 00:18:49,980][87424] Updated weights for policy 0, policy_version 3916 (0.0009) -[2023-11-28 00:18:50,358][87424] Updated weights for policy 0, policy_version 3926 (0.0008) -[2023-11-28 00:18:50,751][87424] Updated weights for policy 0, policy_version 3936 (0.0008) -[2023-11-28 00:18:51,536][87426] Updated weights for policy 1, policy_version 3910 (0.0010) -[2023-11-28 00:18:51,916][87426] Updated weights for policy 1, policy_version 3920 (0.0012) -[2023-11-28 00:18:52,286][87426] Updated weights for policy 1, policy_version 3930 (0.0012) -[2023-11-28 00:18:52,819][87424] Updated weights for policy 0, policy_version 3946 (0.0011) -[2023-11-28 00:18:53,206][87424] Updated weights for policy 0, policy_version 3956 (0.0011) -[2023-11-28 00:18:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 2015232. Throughput: 0: 2718.4, 1: 2739.6. Samples: 2035956. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:18:53,445][86177] Avg episode reward: [(0, '-821.440'), (1, '-773.690')] -[2023-11-28 00:18:53,598][87424] Updated weights for policy 0, policy_version 3966 (0.0010) -[2023-11-28 00:18:54,512][87426] Updated weights for policy 1, policy_version 3940 (0.0011) -[2023-11-28 00:18:54,878][87426] Updated weights for policy 1, policy_version 3950 (0.0012) -[2023-11-28 00:18:55,265][87426] Updated weights for policy 1, policy_version 3960 (0.0012) -[2023-11-28 00:18:55,511][87424] Updated weights for policy 0, policy_version 3976 (0.0011) -[2023-11-28 00:18:55,898][87424] Updated weights for policy 0, policy_version 3986 (0.0009) -[2023-11-28 00:18:56,293][87424] Updated weights for policy 0, policy_version 3996 (0.0007) -[2023-11-28 00:18:57,286][87426] Updated weights for policy 1, policy_version 3970 (0.0009) -[2023-11-28 00:18:57,666][87426] Updated weights for policy 1, policy_version 3980 (0.0007) -[2023-11-28 00:18:58,047][87426] Updated weights for policy 1, policy_version 3990 (0.0007) -[2023-11-28 00:18:58,429][87426] Updated weights for policy 1, policy_version 4000 (0.0007) -[2023-11-28 00:18:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 2048000. Throughput: 0: 2712.1, 1: 2741.5. Samples: 2059768. Policy #0 lag: (min: 21.0, avg: 37.4, max: 53.0) -[2023-11-28 00:18:58,445][86177] Avg episode reward: [(0, '-813.250'), (1, '-763.560')] -[2023-11-28 00:18:58,447][87320] Saving new best policy, reward=-763.560! -[2023-11-28 00:18:58,733][87424] Updated weights for policy 0, policy_version 4006 (0.0010) -[2023-11-28 00:18:59,131][87424] Updated weights for policy 0, policy_version 4016 (0.0011) -[2023-11-28 00:18:59,506][87424] Updated weights for policy 0, policy_version 4026 (0.0009) -[2023-11-28 00:19:00,048][87426] Updated weights for policy 1, policy_version 4010 (0.0011) -[2023-11-28 00:19:00,427][87426] Updated weights for policy 1, policy_version 4020 (0.0012) -[2023-11-28 00:19:00,800][87426] Updated weights for policy 1, policy_version 4030 (0.0010) -[2023-11-28 00:19:01,726][87424] Updated weights for policy 0, policy_version 4036 (0.0009) -[2023-11-28 00:19:02,102][87424] Updated weights for policy 0, policy_version 4046 (0.0012) -[2023-11-28 00:19:02,494][87424] Updated weights for policy 0, policy_version 4056 (0.0009) -[2023-11-28 00:19:03,138][87426] Updated weights for policy 1, policy_version 4040 (0.0012) -[2023-11-28 00:19:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 2072576. Throughput: 0: 2695.8, 1: 2732.4. Samples: 2083144. Policy #0 lag: (min: 9.0, avg: 40.7, max: 73.0) -[2023-11-28 00:19:03,445][86177] Avg episode reward: [(0, '-802.290'), (1, '-791.350')] -[2023-11-28 00:19:03,515][87426] Updated weights for policy 1, policy_version 4050 (0.0012) -[2023-11-28 00:19:03,888][87426] Updated weights for policy 1, policy_version 4060 (0.0009) -[2023-11-28 00:19:04,440][87424] Updated weights for policy 0, policy_version 4066 (0.0009) -[2023-11-28 00:19:04,819][87424] Updated weights for policy 0, policy_version 4076 (0.0011) -[2023-11-28 00:19:05,200][87424] Updated weights for policy 0, policy_version 4086 (0.0012) -[2023-11-28 00:19:05,584][87424] Updated weights for policy 0, policy_version 4096 (0.0012) -[2023-11-28 00:19:06,377][87426] Updated weights for policy 1, policy_version 4070 (0.0011) -[2023-11-28 00:19:06,749][87426] Updated weights for policy 1, policy_version 4080 (0.0012) -[2023-11-28 00:19:07,132][87426] Updated weights for policy 1, policy_version 4090 (0.0011) -[2023-11-28 00:19:07,835][87424] Updated weights for policy 0, policy_version 4106 (0.0011) -[2023-11-28 00:19:08,214][87424] Updated weights for policy 0, policy_version 4116 (0.0011) -[2023-11-28 00:19:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 2097152. Throughput: 0: 2728.3, 1: 2765.6. Samples: 2118148. Policy #0 lag: (min: 9.0, avg: 40.7, max: 73.0) -[2023-11-28 00:19:08,445][86177] Avg episode reward: [(0, '-840.500'), (1, '-766.730')] -[2023-11-28 00:19:08,593][87424] Updated weights for policy 0, policy_version 4126 (0.0009) -[2023-11-28 00:19:08,883][87426] Updated weights for policy 1, policy_version 4100 (0.0012) -[2023-11-28 00:19:09,257][87426] Updated weights for policy 1, policy_version 4110 (0.0008) -[2023-11-28 00:19:09,639][87426] Updated weights for policy 1, policy_version 4120 (0.0009) -[2023-11-28 00:19:10,951][87424] Updated weights for policy 0, policy_version 4136 (0.0011) -[2023-11-28 00:19:11,339][87424] Updated weights for policy 0, policy_version 4146 (0.0012) -[2023-11-28 00:19:11,737][87424] Updated weights for policy 0, policy_version 4156 (0.0012) -[2023-11-28 00:19:12,066][87426] Updated weights for policy 1, policy_version 4130 (0.0010) -[2023-11-28 00:19:12,442][87426] Updated weights for policy 1, policy_version 4140 (0.0009) -[2023-11-28 00:19:12,820][87426] Updated weights for policy 1, policy_version 4150 (0.0008) -[2023-11-28 00:19:13,198][87426] Updated weights for policy 1, policy_version 4160 (0.0008) -[2023-11-28 00:19:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 2129920. Throughput: 0: 2701.5, 1: 2752.6. Samples: 2141868. Policy #0 lag: (min: 7.0, avg: 17.8, max: 39.0) -[2023-11-28 00:19:13,445][86177] Avg episode reward: [(0, '-825.520'), (1, '-777.170')] -[2023-11-28 00:19:13,962][87424] Updated weights for policy 0, policy_version 4166 (0.0011) -[2023-11-28 00:19:14,348][87424] Updated weights for policy 0, policy_version 4176 (0.0012) -[2023-11-28 00:19:14,736][87424] Updated weights for policy 0, policy_version 4186 (0.0012) -[2023-11-28 00:19:15,403][87426] Updated weights for policy 1, policy_version 4170 (0.0008) -[2023-11-28 00:19:15,785][87426] Updated weights for policy 1, policy_version 4180 (0.0010) -[2023-11-28 00:19:16,170][87426] Updated weights for policy 1, policy_version 4190 (0.0011) -[2023-11-28 00:19:16,476][87424] Updated weights for policy 0, policy_version 4196 (0.0012) -[2023-11-28 00:19:16,862][87424] Updated weights for policy 0, policy_version 4206 (0.0012) -[2023-11-28 00:19:17,248][87424] Updated weights for policy 0, policy_version 4216 (0.0011) -[2023-11-28 00:19:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 2154496. Throughput: 0: 2704.8, 1: 2763.6. Samples: 2166780. Policy #0 lag: (min: 21.0, avg: 41.2, max: 53.0) -[2023-11-28 00:19:18,445][86177] Avg episode reward: [(0, '-819.350'), (1, '-776.320')] -[2023-11-28 00:19:18,612][87426] Updated weights for policy 1, policy_version 4200 (0.0012) -[2023-11-28 00:19:18,982][87426] Updated weights for policy 1, policy_version 4210 (0.0012) -[2023-11-28 00:19:19,366][87426] Updated weights for policy 1, policy_version 4220 (0.0012) -[2023-11-28 00:19:19,579][87424] Updated weights for policy 0, policy_version 4226 (0.0011) -[2023-11-28 00:19:19,955][87424] Updated weights for policy 0, policy_version 4236 (0.0011) -[2023-11-28 00:19:20,344][87424] Updated weights for policy 0, policy_version 4246 (0.0012) -[2023-11-28 00:19:20,726][87424] Updated weights for policy 0, policy_version 4256 (0.0012) -[2023-11-28 00:19:21,605][87426] Updated weights for policy 1, policy_version 4230 (0.0012) -[2023-11-28 00:19:21,992][87426] Updated weights for policy 1, policy_version 4240 (0.0011) -[2023-11-28 00:19:22,369][87426] Updated weights for policy 1, policy_version 4250 (0.0012) -[2023-11-28 00:19:22,961][87424] Updated weights for policy 0, policy_version 4266 (0.0012) -[2023-11-28 00:19:23,348][87424] Updated weights for policy 0, policy_version 4276 (0.0012) -[2023-11-28 00:19:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 2179072. Throughput: 0: 2707.3, 1: 2738.7. Samples: 2199132. Policy #0 lag: (min: 31.0, avg: 46.9, max: 72.0) -[2023-11-28 00:19:23,445][86177] Avg episode reward: [(0, '-813.360'), (1, '-753.360')] -[2023-11-28 00:19:23,446][87320] Saving new best policy, reward=-753.360! -[2023-11-28 00:19:23,727][87424] Updated weights for policy 0, policy_version 4286 (0.0012) -[2023-11-28 00:19:24,187][87426] Updated weights for policy 1, policy_version 4260 (0.0012) -[2023-11-28 00:19:24,559][87426] Updated weights for policy 1, policy_version 4270 (0.0011) -[2023-11-28 00:19:24,946][87426] Updated weights for policy 1, policy_version 4280 (0.0012) -[2023-11-28 00:19:26,080][87424] Updated weights for policy 0, policy_version 4296 (0.0011) -[2023-11-28 00:19:26,469][87424] Updated weights for policy 0, policy_version 4306 (0.0009) -[2023-11-28 00:19:26,736][87426] Updated weights for policy 1, policy_version 4290 (0.0012) -[2023-11-28 00:19:26,844][87424] Updated weights for policy 0, policy_version 4316 (0.0007) -[2023-11-28 00:19:27,125][87426] Updated weights for policy 1, policy_version 4300 (0.0011) -[2023-11-28 00:19:27,512][87426] Updated weights for policy 1, policy_version 4310 (0.0007) -[2023-11-28 00:19:27,896][87426] Updated weights for policy 1, policy_version 4320 (0.0007) -[2023-11-28 00:19:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 2211840. Throughput: 0: 2717.9, 1: 2761.1. Samples: 2224472. Policy #0 lag: (min: 32.0, avg: 35.4, max: 57.0) -[2023-11-28 00:19:28,446][86177] Avg episode reward: [(0, '-797.680'), (1, '-767.750')] -[2023-11-28 00:19:28,656][87424] Updated weights for policy 0, policy_version 4326 (0.0010) -[2023-11-28 00:19:29,041][87424] Updated weights for policy 0, policy_version 4336 (0.0012) -[2023-11-28 00:19:29,427][87424] Updated weights for policy 0, policy_version 4346 (0.0011) -[2023-11-28 00:19:30,190][87426] Updated weights for policy 1, policy_version 4330 (0.0012) -[2023-11-28 00:19:30,577][87426] Updated weights for policy 1, policy_version 4340 (0.0012) -[2023-11-28 00:19:30,954][87426] Updated weights for policy 1, policy_version 4350 (0.0011) -[2023-11-28 00:19:31,359][87424] Updated weights for policy 0, policy_version 4356 (0.0010) -[2023-11-28 00:19:31,740][87424] Updated weights for policy 0, policy_version 4366 (0.0009) -[2023-11-28 00:19:32,134][87424] Updated weights for policy 0, policy_version 4376 (0.0012) -[2023-11-28 00:19:33,157][87426] Updated weights for policy 1, policy_version 4360 (0.0011) -[2023-11-28 00:19:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 2236416. Throughput: 0: 2728.9, 1: 2751.2. Samples: 2249436. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 00:19:33,445][86177] Avg episode reward: [(0, '-761.480'), (1, '-760.440')] -[2023-11-28 00:19:33,453][87281] Saving new best policy, reward=-761.480! -[2023-11-28 00:19:33,537][87426] Updated weights for policy 1, policy_version 4370 (0.0012) -[2023-11-28 00:19:33,926][87426] Updated weights for policy 1, policy_version 4380 (0.0011) -[2023-11-28 00:19:34,453][87424] Updated weights for policy 0, policy_version 4386 (0.0008) -[2023-11-28 00:19:34,845][87424] Updated weights for policy 0, policy_version 4396 (0.0009) -[2023-11-28 00:19:35,227][87424] Updated weights for policy 0, policy_version 4406 (0.0009) -[2023-11-28 00:19:35,615][87424] Updated weights for policy 0, policy_version 4416 (0.0007) -[2023-11-28 00:19:36,043][87426] Updated weights for policy 1, policy_version 4390 (0.0012) -[2023-11-28 00:19:36,410][87426] Updated weights for policy 1, policy_version 4400 (0.0011) -[2023-11-28 00:19:36,795][87426] Updated weights for policy 1, policy_version 4410 (0.0012) -[2023-11-28 00:19:38,185][87424] Updated weights for policy 0, policy_version 4426 (0.0007) -[2023-11-28 00:19:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 2260992. Throughput: 0: 2709.7, 1: 2739.4. Samples: 2281164. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 00:19:38,446][86177] Avg episode reward: [(0, '-783.880'), (1, '-727.020')] -[2023-11-28 00:19:38,447][87320] Saving new best policy, reward=-727.020! -[2023-11-28 00:19:38,568][87424] Updated weights for policy 0, policy_version 4436 (0.0007) -[2023-11-28 00:19:38,954][87424] Updated weights for policy 0, policy_version 4446 (0.0009) -[2023-11-28 00:19:39,113][87426] Updated weights for policy 1, policy_version 4420 (0.0010) -[2023-11-28 00:19:39,492][87426] Updated weights for policy 1, policy_version 4430 (0.0009) -[2023-11-28 00:19:39,872][87426] Updated weights for policy 1, policy_version 4440 (0.0010) -[2023-11-28 00:19:41,062][87424] Updated weights for policy 0, policy_version 4456 (0.0012) -[2023-11-28 00:19:41,442][87424] Updated weights for policy 0, policy_version 4466 (0.0012) -[2023-11-28 00:19:41,704][87426] Updated weights for policy 1, policy_version 4450 (0.0012) -[2023-11-28 00:19:41,840][87424] Updated weights for policy 0, policy_version 4476 (0.0011) -[2023-11-28 00:19:42,088][87426] Updated weights for policy 1, policy_version 4460 (0.0012) -[2023-11-28 00:19:42,471][87426] Updated weights for policy 1, policy_version 4470 (0.0012) -[2023-11-28 00:19:42,844][87426] Updated weights for policy 1, policy_version 4480 (0.0010) -[2023-11-28 00:19:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 2293760. Throughput: 0: 2711.0, 1: 2749.9. Samples: 2305508. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 00:19:43,445][86177] Avg episode reward: [(0, '-799.730'), (1, '-712.270')] -[2023-11-28 00:19:43,446][87320] Saving new best policy, reward=-712.270! -[2023-11-28 00:19:44,220][87424] Updated weights for policy 0, policy_version 4486 (0.0008) -[2023-11-28 00:19:44,603][87424] Updated weights for policy 0, policy_version 4496 (0.0008) -[2023-11-28 00:19:44,989][87424] Updated weights for policy 0, policy_version 4506 (0.0009) -[2023-11-28 00:19:45,299][87426] Updated weights for policy 1, policy_version 4490 (0.0008) -[2023-11-28 00:19:45,681][87426] Updated weights for policy 1, policy_version 4500 (0.0009) -[2023-11-28 00:19:46,057][87426] Updated weights for policy 1, policy_version 4510 (0.0012) -[2023-11-28 00:19:47,203][87424] Updated weights for policy 0, policy_version 4516 (0.0012) -[2023-11-28 00:19:47,584][87424] Updated weights for policy 0, policy_version 4526 (0.0010) -[2023-11-28 00:19:47,963][87424] Updated weights for policy 0, policy_version 4536 (0.0008) -[2023-11-28 00:19:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 2318336. Throughput: 0: 2701.5, 1: 2751.5. Samples: 2328528. Policy #0 lag: (min: 31.0, avg: 51.5, max: 85.0) -[2023-11-28 00:19:48,445][86177] Avg episode reward: [(0, '-778.850'), (1, '-699.980')] -[2023-11-28 00:19:48,513][87426] Updated weights for policy 1, policy_version 4520 (0.0012) -[2023-11-28 00:19:48,883][87426] Updated weights for policy 1, policy_version 4530 (0.0011) -[2023-11-28 00:19:49,262][87426] Updated weights for policy 1, policy_version 4540 (0.0012) -[2023-11-28 00:19:49,416][87320] Saving new best policy, reward=-699.980! -[2023-11-28 00:19:50,488][87424] Updated weights for policy 0, policy_version 4546 (0.0008) -[2023-11-28 00:19:50,877][87424] Updated weights for policy 0, policy_version 4556 (0.0012) -[2023-11-28 00:19:51,264][87424] Updated weights for policy 0, policy_version 4566 (0.0012) -[2023-11-28 00:19:51,382][87426] Updated weights for policy 1, policy_version 4550 (0.0011) -[2023-11-28 00:19:51,648][87424] Updated weights for policy 0, policy_version 4576 (0.0009) -[2023-11-28 00:19:51,760][87426] Updated weights for policy 1, policy_version 4560 (0.0011) -[2023-11-28 00:19:52,131][87426] Updated weights for policy 1, policy_version 4570 (0.0009) -[2023-11-28 00:19:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 2342912. Throughput: 0: 2673.3, 1: 2722.8. Samples: 2360972. Policy #0 lag: (min: 20.0, avg: 35.3, max: 52.0) -[2023-11-28 00:19:53,445][86177] Avg episode reward: [(0, '-766.700'), (1, '-671.610')] -[2023-11-28 00:19:53,446][87320] Saving new best policy, reward=-671.610! -[2023-11-28 00:19:53,889][87424] Updated weights for policy 0, policy_version 4586 (0.0012) -[2023-11-28 00:19:54,272][87424] Updated weights for policy 0, policy_version 4596 (0.0012) -[2023-11-28 00:19:54,488][87426] Updated weights for policy 1, policy_version 4580 (0.0010) -[2023-11-28 00:19:54,653][87424] Updated weights for policy 0, policy_version 4606 (0.0011) -[2023-11-28 00:19:54,868][87426] Updated weights for policy 1, policy_version 4590 (0.0007) -[2023-11-28 00:19:55,246][87426] Updated weights for policy 1, policy_version 4600 (0.0011) -[2023-11-28 00:19:57,256][87426] Updated weights for policy 1, policy_version 4610 (0.0008) -[2023-11-28 00:19:57,274][87424] Updated weights for policy 0, policy_version 4616 (0.0011) -[2023-11-28 00:19:57,634][87426] Updated weights for policy 1, policy_version 4620 (0.0011) -[2023-11-28 00:19:57,656][87424] Updated weights for policy 0, policy_version 4626 (0.0012) -[2023-11-28 00:19:58,015][87426] Updated weights for policy 1, policy_version 4630 (0.0008) -[2023-11-28 00:19:58,043][87424] Updated weights for policy 0, policy_version 4636 (0.0009) -[2023-11-28 00:19:58,397][87426] Updated weights for policy 1, policy_version 4640 (0.0007) -[2023-11-28 00:19:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 2375680. Throughput: 0: 2671.0, 1: 2717.6. Samples: 2384356. Policy #0 lag: (min: 31.0, avg: 49.0, max: 66.0) -[2023-11-28 00:19:58,445][86177] Avg episode reward: [(0, '-770.700'), (1, '-659.830')] -[2023-11-28 00:19:58,446][87320] Saving new best policy, reward=-659.830! -[2023-11-28 00:20:00,029][87424] Updated weights for policy 0, policy_version 4646 (0.0010) -[2023-11-28 00:20:00,329][87426] Updated weights for policy 1, policy_version 4650 (0.0011) -[2023-11-28 00:20:00,412][87424] Updated weights for policy 0, policy_version 4656 (0.0009) -[2023-11-28 00:20:00,716][87426] Updated weights for policy 1, policy_version 4660 (0.0009) -[2023-11-28 00:20:00,794][87424] Updated weights for policy 0, policy_version 4666 (0.0009) -[2023-11-28 00:20:01,090][87426] Updated weights for policy 1, policy_version 4670 (0.0008) -[2023-11-28 00:20:03,287][87424] Updated weights for policy 0, policy_version 4676 (0.0008) -[2023-11-28 00:20:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 2392064. Throughput: 0: 2666.3, 1: 2706.4. Samples: 2408552. Policy #0 lag: (min: 31.0, avg: 49.0, max: 66.0) -[2023-11-28 00:20:03,445][86177] Avg episode reward: [(0, '-744.520'), (1, '-658.110')] -[2023-11-28 00:20:03,510][87426] Updated weights for policy 1, policy_version 4680 (0.0009) -[2023-11-28 00:20:03,667][87424] Updated weights for policy 0, policy_version 4686 (0.0008) -[2023-11-28 00:20:03,894][87426] Updated weights for policy 1, policy_version 4690 (0.0011) -[2023-11-28 00:20:04,048][87424] Updated weights for policy 0, policy_version 4696 (0.0008) -[2023-11-28 00:20:04,280][87426] Updated weights for policy 1, policy_version 4700 (0.0011) -[2023-11-28 00:20:04,362][87281] Saving new best policy, reward=-744.520! -[2023-11-28 00:20:04,422][87320] Saving new best policy, reward=-658.110! -[2023-11-28 00:20:05,644][87424] Updated weights for policy 0, policy_version 4706 (0.0009) -[2023-11-28 00:20:06,039][87424] Updated weights for policy 0, policy_version 4716 (0.0012) -[2023-11-28 00:20:06,420][87424] Updated weights for policy 0, policy_version 4726 (0.0012) -[2023-11-28 00:20:06,802][87424] Updated weights for policy 0, policy_version 4736 (0.0011) -[2023-11-28 00:20:06,870][87426] Updated weights for policy 1, policy_version 4710 (0.0010) -[2023-11-28 00:20:07,242][87426] Updated weights for policy 1, policy_version 4720 (0.0007) -[2023-11-28 00:20:07,629][87426] Updated weights for policy 1, policy_version 4730 (0.0007) -[2023-11-28 00:20:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 2424832. Throughput: 0: 2651.6, 1: 2707.5. Samples: 2440288. Policy #0 lag: (min: 31.0, avg: 50.9, max: 86.0) -[2023-11-28 00:20:08,445][86177] Avg episode reward: [(0, '-715.110'), (1, '-674.440')] -[2023-11-28 00:20:08,761][87424] Updated weights for policy 0, policy_version 4746 (0.0012) -[2023-11-28 00:20:09,140][87424] Updated weights for policy 0, policy_version 4756 (0.0012) -[2023-11-28 00:20:09,528][87424] Updated weights for policy 0, policy_version 4766 (0.0012) -[2023-11-28 00:20:09,543][87426] Updated weights for policy 1, policy_version 4740 (0.0009) -[2023-11-28 00:20:09,601][87281] Saving new best policy, reward=-715.110! -[2023-11-28 00:20:09,913][87426] Updated weights for policy 1, policy_version 4750 (0.0012) -[2023-11-28 00:20:10,292][87426] Updated weights for policy 1, policy_version 4760 (0.0012) -[2023-11-28 00:20:11,597][87424] Updated weights for policy 0, policy_version 4776 (0.0009) -[2023-11-28 00:20:11,969][87424] Updated weights for policy 0, policy_version 4786 (0.0011) -[2023-11-28 00:20:12,185][87426] Updated weights for policy 1, policy_version 4770 (0.0012) -[2023-11-28 00:20:12,348][87424] Updated weights for policy 0, policy_version 4796 (0.0009) -[2023-11-28 00:20:12,556][87426] Updated weights for policy 1, policy_version 4780 (0.0009) -[2023-11-28 00:20:12,938][87426] Updated weights for policy 1, policy_version 4790 (0.0012) -[2023-11-28 00:20:13,315][87426] Updated weights for policy 1, policy_version 4800 (0.0012) -[2023-11-28 00:20:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 2457600. Throughput: 0: 2631.8, 1: 2677.9. Samples: 2463408. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-11-28 00:20:13,445][86177] Avg episode reward: [(0, '-727.540'), (1, '-674.610')] -[2023-11-28 00:20:14,791][87424] Updated weights for policy 0, policy_version 4806 (0.0011) -[2023-11-28 00:20:15,172][87424] Updated weights for policy 0, policy_version 4816 (0.0012) -[2023-11-28 00:20:15,368][87426] Updated weights for policy 1, policy_version 4810 (0.0009) -[2023-11-28 00:20:15,563][87424] Updated weights for policy 0, policy_version 4826 (0.0012) -[2023-11-28 00:20:15,749][87426] Updated weights for policy 1, policy_version 4820 (0.0009) -[2023-11-28 00:20:16,133][87426] Updated weights for policy 1, policy_version 4830 (0.0012) -[2023-11-28 00:20:17,723][87424] Updated weights for policy 0, policy_version 4836 (0.0011) -[2023-11-28 00:20:18,023][87426] Updated weights for policy 1, policy_version 4840 (0.0012) -[2023-11-28 00:20:18,115][87424] Updated weights for policy 0, policy_version 4846 (0.0008) -[2023-11-28 00:20:18,403][87426] Updated weights for policy 1, policy_version 4850 (0.0011) -[2023-11-28 00:20:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 2473984. Throughput: 0: 2627.1, 1: 2685.3. Samples: 2488496. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-11-28 00:20:18,445][86177] Avg episode reward: [(0, '-752.500'), (1, '-656.090')] -[2023-11-28 00:20:18,498][87424] Updated weights for policy 0, policy_version 4856 (0.0008) -[2023-11-28 00:20:18,785][87426] Updated weights for policy 1, policy_version 4860 (0.0008) -[2023-11-28 00:20:18,799][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000004864_1245184.pth... -[2023-11-28 00:20:18,844][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000002336_598016.pth -[2023-11-28 00:20:18,938][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000004864_1245184.pth... -[2023-11-28 00:20:18,983][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000002304_589824.pth -[2023-11-28 00:20:18,989][87320] Saving new best policy, reward=-656.090! -[2023-11-28 00:20:20,254][87424] Updated weights for policy 0, policy_version 4866 (0.0008) -[2023-11-28 00:20:20,645][87424] Updated weights for policy 0, policy_version 4876 (0.0012) -[2023-11-28 00:20:21,025][87424] Updated weights for policy 0, policy_version 4886 (0.0011) -[2023-11-28 00:20:21,264][87426] Updated weights for policy 1, policy_version 4870 (0.0010) -[2023-11-28 00:20:21,405][87424] Updated weights for policy 0, policy_version 4896 (0.0011) -[2023-11-28 00:20:21,644][87426] Updated weights for policy 1, policy_version 4880 (0.0012) -[2023-11-28 00:20:22,024][87426] Updated weights for policy 1, policy_version 4890 (0.0012) -[2023-11-28 00:20:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 2506752. Throughput: 0: 2640.8, 1: 2697.2. Samples: 2521372. Policy #0 lag: (min: 12.0, avg: 21.3, max: 44.0) -[2023-11-28 00:20:23,445][86177] Avg episode reward: [(0, '-749.490'), (1, '-652.400')] -[2023-11-28 00:20:23,446][87320] Saving new best policy, reward=-652.400! -[2023-11-28 00:20:23,929][87426] Updated weights for policy 1, policy_version 4900 (0.0012) -[2023-11-28 00:20:23,998][87424] Updated weights for policy 0, policy_version 4906 (0.0012) -[2023-11-28 00:20:24,311][87426] Updated weights for policy 1, policy_version 4910 (0.0007) -[2023-11-28 00:20:24,368][87424] Updated weights for policy 0, policy_version 4916 (0.0008) -[2023-11-28 00:20:24,683][87426] Updated weights for policy 1, policy_version 4920 (0.0010) -[2023-11-28 00:20:24,754][87424] Updated weights for policy 0, policy_version 4926 (0.0007) -[2023-11-28 00:20:26,988][87424] Updated weights for policy 0, policy_version 4936 (0.0011) -[2023-11-28 00:20:27,119][87426] Updated weights for policy 1, policy_version 4930 (0.0012) -[2023-11-28 00:20:27,379][87424] Updated weights for policy 0, policy_version 4946 (0.0011) -[2023-11-28 00:20:27,502][87426] Updated weights for policy 1, policy_version 4940 (0.0011) -[2023-11-28 00:20:27,776][87424] Updated weights for policy 0, policy_version 4956 (0.0011) -[2023-11-28 00:20:27,882][87426] Updated weights for policy 1, policy_version 4950 (0.0011) -[2023-11-28 00:20:28,271][87426] Updated weights for policy 1, policy_version 4960 (0.0012) -[2023-11-28 00:20:28,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 2539520. Throughput: 0: 2638.3, 1: 2711.8. Samples: 2546264. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 00:20:28,446][86177] Avg episode reward: [(0, '-749.530'), (1, '-626.860')] -[2023-11-28 00:20:28,447][87320] Saving new best policy, reward=-626.860! -[2023-11-28 00:20:30,044][87424] Updated weights for policy 0, policy_version 4966 (0.0011) -[2023-11-28 00:20:30,424][87424] Updated weights for policy 0, policy_version 4976 (0.0011) -[2023-11-28 00:20:30,567][87426] Updated weights for policy 1, policy_version 4970 (0.0009) -[2023-11-28 00:20:30,812][87424] Updated weights for policy 0, policy_version 4986 (0.0010) -[2023-11-28 00:20:30,942][87426] Updated weights for policy 1, policy_version 4980 (0.0011) -[2023-11-28 00:20:31,327][87426] Updated weights for policy 1, policy_version 4990 (0.0012) -[2023-11-28 00:20:33,126][87426] Updated weights for policy 1, policy_version 5000 (0.0011) -[2023-11-28 00:20:33,389][87424] Updated weights for policy 0, policy_version 4996 (0.0010) -[2023-11-28 00:20:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 2555904. Throughput: 0: 2660.4, 1: 2708.5. Samples: 2570128. Policy #0 lag: (min: 8.0, avg: 34.5, max: 48.0) -[2023-11-28 00:20:33,445][86177] Avg episode reward: [(0, '-756.780'), (1, '-631.400')] -[2023-11-28 00:20:33,505][87426] Updated weights for policy 1, policy_version 5010 (0.0010) -[2023-11-28 00:20:33,773][87424] Updated weights for policy 0, policy_version 5006 (0.0008) -[2023-11-28 00:20:33,884][87426] Updated weights for policy 1, policy_version 5020 (0.0011) -[2023-11-28 00:20:34,159][87424] Updated weights for policy 0, policy_version 5016 (0.0007) -[2023-11-28 00:20:35,825][87426] Updated weights for policy 1, policy_version 5030 (0.0011) -[2023-11-28 00:20:36,123][87424] Updated weights for policy 0, policy_version 5026 (0.0009) -[2023-11-28 00:20:36,213][87426] Updated weights for policy 1, policy_version 5040 (0.0011) -[2023-11-28 00:20:36,508][87424] Updated weights for policy 0, policy_version 5036 (0.0007) -[2023-11-28 00:20:36,588][87426] Updated weights for policy 1, policy_version 5050 (0.0011) -[2023-11-28 00:20:36,899][87424] Updated weights for policy 0, policy_version 5046 (0.0009) -[2023-11-28 00:20:37,280][87424] Updated weights for policy 0, policy_version 5056 (0.0010) -[2023-11-28 00:20:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 2588672. Throughput: 0: 2667.4, 1: 2721.7. Samples: 2603480. Policy #0 lag: (min: 27.0, avg: 47.7, max: 59.0) -[2023-11-28 00:20:38,445][86177] Avg episode reward: [(0, '-740.910'), (1, '-641.630')] -[2023-11-28 00:20:39,076][87426] Updated weights for policy 1, policy_version 5060 (0.0011) -[2023-11-28 00:20:39,451][87426] Updated weights for policy 1, policy_version 5070 (0.0011) -[2023-11-28 00:20:39,571][87424] Updated weights for policy 0, policy_version 5066 (0.0011) -[2023-11-28 00:20:39,832][87426] Updated weights for policy 1, policy_version 5080 (0.0011) -[2023-11-28 00:20:39,950][87424] Updated weights for policy 0, policy_version 5076 (0.0010) -[2023-11-28 00:20:40,338][87424] Updated weights for policy 0, policy_version 5086 (0.0012) -[2023-11-28 00:20:42,063][87424] Updated weights for policy 0, policy_version 5096 (0.0009) -[2023-11-28 00:20:42,302][87426] Updated weights for policy 1, policy_version 5090 (0.0009) -[2023-11-28 00:20:42,436][87424] Updated weights for policy 0, policy_version 5106 (0.0009) -[2023-11-28 00:20:42,684][87426] Updated weights for policy 1, policy_version 5100 (0.0009) -[2023-11-28 00:20:42,824][87424] Updated weights for policy 0, policy_version 5116 (0.0008) -[2023-11-28 00:20:43,059][87426] Updated weights for policy 1, policy_version 5110 (0.0008) -[2023-11-28 00:20:43,443][87426] Updated weights for policy 1, policy_version 5120 (0.0007) -[2023-11-28 00:20:43,447][86177] Fps is (10 sec: 6552.0, 60 sec: 5461.1, 300 sec: 5442.8). Total num frames: 2621440. Throughput: 0: 2680.6, 1: 2736.5. Samples: 2628140. Policy #0 lag: (min: 27.0, avg: 47.7, max: 59.0) -[2023-11-28 00:20:43,448][86177] Avg episode reward: [(0, '-746.810'), (1, '-646.350')] -[2023-11-28 00:20:45,447][87424] Updated weights for policy 0, policy_version 5126 (0.0010) -[2023-11-28 00:20:45,821][87426] Updated weights for policy 1, policy_version 5130 (0.0010) -[2023-11-28 00:20:45,829][87424] Updated weights for policy 0, policy_version 5136 (0.0011) -[2023-11-28 00:20:46,199][87426] Updated weights for policy 1, policy_version 5140 (0.0011) -[2023-11-28 00:20:46,213][87424] Updated weights for policy 0, policy_version 5146 (0.0010) -[2023-11-28 00:20:46,578][87426] Updated weights for policy 1, policy_version 5150 (0.0010) -[2023-11-28 00:20:47,997][87424] Updated weights for policy 0, policy_version 5156 (0.0009) -[2023-11-28 00:20:48,384][87424] Updated weights for policy 0, policy_version 5166 (0.0012) -[2023-11-28 00:20:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 2637824. Throughput: 0: 2687.3, 1: 2727.6. Samples: 2652224. Policy #0 lag: (min: 0.0, avg: 23.4, max: 58.0) -[2023-11-28 00:20:48,445][86177] Avg episode reward: [(0, '-729.950'), (1, '-647.090')] -[2023-11-28 00:20:48,552][87426] Updated weights for policy 1, policy_version 5160 (0.0009) -[2023-11-28 00:20:48,774][87424] Updated weights for policy 0, policy_version 5176 (0.0011) -[2023-11-28 00:20:48,931][87426] Updated weights for policy 1, policy_version 5170 (0.0011) -[2023-11-28 00:20:49,301][87426] Updated weights for policy 1, policy_version 5180 (0.0012) -[2023-11-28 00:20:50,976][87424] Updated weights for policy 0, policy_version 5186 (0.0012) -[2023-11-28 00:20:51,358][87424] Updated weights for policy 0, policy_version 5196 (0.0011) -[2023-11-28 00:20:51,512][87426] Updated weights for policy 1, policy_version 5190 (0.0012) -[2023-11-28 00:20:51,741][87424] Updated weights for policy 0, policy_version 5206 (0.0011) -[2023-11-28 00:20:51,901][87426] Updated weights for policy 1, policy_version 5200 (0.0011) -[2023-11-28 00:20:52,135][87424] Updated weights for policy 0, policy_version 5216 (0.0010) -[2023-11-28 00:20:52,271][87426] Updated weights for policy 1, policy_version 5210 (0.0010) -[2023-11-28 00:20:53,444][86177] Fps is (10 sec: 4916.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 2670592. Throughput: 0: 2718.5, 1: 2736.3. Samples: 2685752. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:20:53,445][86177] Avg episode reward: [(0, '-726.420'), (1, '-644.860')] -[2023-11-28 00:20:54,218][87424] Updated weights for policy 0, policy_version 5226 (0.0009) -[2023-11-28 00:20:54,573][87426] Updated weights for policy 1, policy_version 5220 (0.0010) -[2023-11-28 00:20:54,600][87424] Updated weights for policy 0, policy_version 5236 (0.0008) -[2023-11-28 00:20:54,955][87426] Updated weights for policy 1, policy_version 5230 (0.0007) -[2023-11-28 00:20:54,985][87424] Updated weights for policy 0, policy_version 5246 (0.0009) -[2023-11-28 00:20:55,329][87426] Updated weights for policy 1, policy_version 5240 (0.0009) -[2023-11-28 00:20:57,232][87424] Updated weights for policy 0, policy_version 5256 (0.0011) -[2023-11-28 00:20:57,612][87424] Updated weights for policy 0, policy_version 5266 (0.0010) -[2023-11-28 00:20:57,636][87426] Updated weights for policy 1, policy_version 5250 (0.0009) -[2023-11-28 00:20:57,991][87424] Updated weights for policy 0, policy_version 5276 (0.0011) -[2023-11-28 00:20:58,019][87426] Updated weights for policy 1, policy_version 5260 (0.0011) -[2023-11-28 00:20:58,393][87426] Updated weights for policy 1, policy_version 5270 (0.0011) -[2023-11-28 00:20:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 2695168. Throughput: 0: 2726.9, 1: 2750.3. Samples: 2709884. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:20:58,445][86177] Avg episode reward: [(0, '-725.270'), (1, '-639.440')] -[2023-11-28 00:20:58,771][87426] Updated weights for policy 1, policy_version 5280 (0.0012) -[2023-11-28 00:20:59,633][87424] Updated weights for policy 0, policy_version 5286 (0.0012) -[2023-11-28 00:21:00,018][87424] Updated weights for policy 0, policy_version 5296 (0.0012) -[2023-11-28 00:21:00,399][87424] Updated weights for policy 0, policy_version 5306 (0.0012) -[2023-11-28 00:21:01,132][87426] Updated weights for policy 1, policy_version 5290 (0.0011) -[2023-11-28 00:21:01,510][87426] Updated weights for policy 1, policy_version 5300 (0.0008) -[2023-11-28 00:21:01,891][87426] Updated weights for policy 1, policy_version 5310 (0.0010) -[2023-11-28 00:21:02,714][87424] Updated weights for policy 0, policy_version 5316 (0.0012) -[2023-11-28 00:21:03,103][87424] Updated weights for policy 0, policy_version 5326 (0.0012) -[2023-11-28 00:21:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 2719744. Throughput: 0: 2747.4, 1: 2744.0. Samples: 2735608. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 00:21:03,445][86177] Avg episode reward: [(0, '-713.950'), (1, '-630.750')] -[2023-11-28 00:21:03,478][87424] Updated weights for policy 0, policy_version 5336 (0.0012) -[2023-11-28 00:21:03,782][87281] Saving new best policy, reward=-713.950! -[2023-11-28 00:21:03,986][87426] Updated weights for policy 1, policy_version 5320 (0.0012) -[2023-11-28 00:21:04,363][87426] Updated weights for policy 1, policy_version 5330 (0.0011) -[2023-11-28 00:21:04,745][87426] Updated weights for policy 1, policy_version 5340 (0.0011) -[2023-11-28 00:21:05,548][87424] Updated weights for policy 0, policy_version 5346 (0.0011) -[2023-11-28 00:21:05,925][87424] Updated weights for policy 0, policy_version 5356 (0.0012) -[2023-11-28 00:21:06,305][87424] Updated weights for policy 0, policy_version 5366 (0.0012) -[2023-11-28 00:21:06,681][87424] Updated weights for policy 0, policy_version 5376 (0.0010) -[2023-11-28 00:21:06,694][87426] Updated weights for policy 1, policy_version 5350 (0.0008) -[2023-11-28 00:21:07,074][87426] Updated weights for policy 1, policy_version 5360 (0.0008) -[2023-11-28 00:21:07,458][87426] Updated weights for policy 1, policy_version 5370 (0.0011) -[2023-11-28 00:21:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 2752512. Throughput: 0: 2754.1, 1: 2730.1. Samples: 2768164. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 00:21:08,446][86177] Avg episode reward: [(0, '-676.660'), (1, '-630.290')] -[2023-11-28 00:21:08,447][87281] Saving new best policy, reward=-676.660! -[2023-11-28 00:21:09,006][87424] Updated weights for policy 0, policy_version 5386 (0.0009) -[2023-11-28 00:21:09,385][87426] Updated weights for policy 1, policy_version 5380 (0.0011) -[2023-11-28 00:21:09,401][87424] Updated weights for policy 0, policy_version 5396 (0.0010) -[2023-11-28 00:21:09,764][87426] Updated weights for policy 1, policy_version 5390 (0.0011) -[2023-11-28 00:21:09,785][87424] Updated weights for policy 0, policy_version 5406 (0.0012) -[2023-11-28 00:21:10,144][87426] Updated weights for policy 1, policy_version 5400 (0.0012) -[2023-11-28 00:21:11,857][87424] Updated weights for policy 0, policy_version 5416 (0.0011) -[2023-11-28 00:21:12,230][87424] Updated weights for policy 0, policy_version 5426 (0.0011) -[2023-11-28 00:21:12,622][87424] Updated weights for policy 0, policy_version 5436 (0.0011) -[2023-11-28 00:21:12,693][87426] Updated weights for policy 1, policy_version 5410 (0.0012) -[2023-11-28 00:21:13,088][87426] Updated weights for policy 1, policy_version 5420 (0.0010) -[2023-11-28 00:21:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 2777088. Throughput: 0: 2752.2, 1: 2719.3. Samples: 2792480. Policy #0 lag: (min: 3.0, avg: 19.3, max: 35.0) -[2023-11-28 00:21:13,445][86177] Avg episode reward: [(0, '-655.640'), (1, '-638.020')] -[2023-11-28 00:21:13,446][87281] Saving new best policy, reward=-655.640! -[2023-11-28 00:21:13,467][87426] Updated weights for policy 1, policy_version 5430 (0.0012) -[2023-11-28 00:21:13,847][87426] Updated weights for policy 1, policy_version 5440 (0.0011) -[2023-11-28 00:21:14,407][87424] Updated weights for policy 0, policy_version 5446 (0.0010) -[2023-11-28 00:21:14,795][87424] Updated weights for policy 0, policy_version 5456 (0.0011) -[2023-11-28 00:21:15,176][87424] Updated weights for policy 0, policy_version 5466 (0.0012) -[2023-11-28 00:21:16,067][87426] Updated weights for policy 1, policy_version 5450 (0.0010) -[2023-11-28 00:21:16,459][87426] Updated weights for policy 1, policy_version 5460 (0.0007) -[2023-11-28 00:21:16,843][87426] Updated weights for policy 1, policy_version 5470 (0.0008) -[2023-11-28 00:21:17,525][87424] Updated weights for policy 0, policy_version 5476 (0.0009) -[2023-11-28 00:21:17,917][87424] Updated weights for policy 0, policy_version 5486 (0.0007) -[2023-11-28 00:21:18,311][87424] Updated weights for policy 0, policy_version 5496 (0.0007) -[2023-11-28 00:21:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 2801664. Throughput: 0: 2768.1, 1: 2731.8. Samples: 2817624. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 00:21:18,445][86177] Avg episode reward: [(0, '-658.870'), (1, '-636.810')] -[2023-11-28 00:21:19,282][87426] Updated weights for policy 1, policy_version 5480 (0.0011) -[2023-11-28 00:21:19,667][87426] Updated weights for policy 1, policy_version 5490 (0.0009) -[2023-11-28 00:21:20,041][87426] Updated weights for policy 1, policy_version 5500 (0.0010) -[2023-11-28 00:21:20,561][87424] Updated weights for policy 0, policy_version 5506 (0.0008) -[2023-11-28 00:21:20,945][87424] Updated weights for policy 0, policy_version 5516 (0.0011) -[2023-11-28 00:21:21,341][87424] Updated weights for policy 0, policy_version 5526 (0.0010) -[2023-11-28 00:21:21,720][87424] Updated weights for policy 0, policy_version 5536 (0.0010) -[2023-11-28 00:21:22,088][87426] Updated weights for policy 1, policy_version 5510 (0.0011) -[2023-11-28 00:21:22,460][87426] Updated weights for policy 1, policy_version 5520 (0.0010) -[2023-11-28 00:21:22,842][87426] Updated weights for policy 1, policy_version 5530 (0.0011) -[2023-11-28 00:21:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 2834432. Throughput: 0: 2761.8, 1: 2717.1. Samples: 2850028. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 00:21:23,445][86177] Avg episode reward: [(0, '-663.870'), (1, '-643.810')] -[2023-11-28 00:21:24,204][87424] Updated weights for policy 0, policy_version 5546 (0.0008) -[2023-11-28 00:21:24,590][87424] Updated weights for policy 0, policy_version 5556 (0.0009) -[2023-11-28 00:21:24,985][87424] Updated weights for policy 0, policy_version 5566 (0.0010) -[2023-11-28 00:21:25,075][87426] Updated weights for policy 1, policy_version 5540 (0.0011) -[2023-11-28 00:21:25,448][87426] Updated weights for policy 1, policy_version 5550 (0.0012) -[2023-11-28 00:21:25,840][87426] Updated weights for policy 1, policy_version 5560 (0.0012) -[2023-11-28 00:21:26,905][87424] Updated weights for policy 0, policy_version 5576 (0.0011) -[2023-11-28 00:21:27,285][87424] Updated weights for policy 0, policy_version 5586 (0.0012) -[2023-11-28 00:21:27,667][87426] Updated weights for policy 1, policy_version 5570 (0.0008) -[2023-11-28 00:21:27,684][87424] Updated weights for policy 0, policy_version 5596 (0.0012) -[2023-11-28 00:21:28,050][87426] Updated weights for policy 1, policy_version 5580 (0.0009) -[2023-11-28 00:21:28,440][87426] Updated weights for policy 1, policy_version 5590 (0.0007) -[2023-11-28 00:21:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 2859008. Throughput: 0: 2743.2, 1: 2732.9. Samples: 2874548. Policy #0 lag: (min: 17.0, avg: 46.1, max: 81.0) -[2023-11-28 00:21:28,445][86177] Avg episode reward: [(0, '-659.270'), (1, '-653.210')] -[2023-11-28 00:21:28,808][87426] Updated weights for policy 1, policy_version 5600 (0.0007) -[2023-11-28 00:21:30,152][87424] Updated weights for policy 0, policy_version 5606 (0.0012) -[2023-11-28 00:21:30,530][87424] Updated weights for policy 0, policy_version 5616 (0.0011) -[2023-11-28 00:21:30,667][87426] Updated weights for policy 1, policy_version 5610 (0.0009) -[2023-11-28 00:21:30,918][87424] Updated weights for policy 0, policy_version 5626 (0.0007) -[2023-11-28 00:21:31,045][87426] Updated weights for policy 1, policy_version 5620 (0.0007) -[2023-11-28 00:21:31,427][87426] Updated weights for policy 1, policy_version 5630 (0.0011) -[2023-11-28 00:21:32,996][87424] Updated weights for policy 0, policy_version 5636 (0.0009) -[2023-11-28 00:21:33,382][87424] Updated weights for policy 0, policy_version 5646 (0.0011) -[2023-11-28 00:21:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 2883584. Throughput: 0: 2729.8, 1: 2745.6. Samples: 2898616. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 00:21:33,445][86177] Avg episode reward: [(0, '-662.470'), (1, '-637.360')] -[2023-11-28 00:21:33,641][87426] Updated weights for policy 1, policy_version 5640 (0.0012) -[2023-11-28 00:21:33,764][87424] Updated weights for policy 0, policy_version 5656 (0.0012) -[2023-11-28 00:21:34,027][87426] Updated weights for policy 1, policy_version 5650 (0.0012) -[2023-11-28 00:21:34,405][87426] Updated weights for policy 1, policy_version 5660 (0.0011) -[2023-11-28 00:21:35,968][87424] Updated weights for policy 0, policy_version 5666 (0.0011) -[2023-11-28 00:21:36,348][87424] Updated weights for policy 0, policy_version 5676 (0.0012) -[2023-11-28 00:21:36,740][87424] Updated weights for policy 0, policy_version 5686 (0.0012) -[2023-11-28 00:21:36,976][87426] Updated weights for policy 1, policy_version 5670 (0.0011) -[2023-11-28 00:21:37,113][87424] Updated weights for policy 0, policy_version 5696 (0.0011) -[2023-11-28 00:21:37,352][87426] Updated weights for policy 1, policy_version 5680 (0.0010) -[2023-11-28 00:21:37,736][87426] Updated weights for policy 1, policy_version 5690 (0.0008) -[2023-11-28 00:21:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 2916352. Throughput: 0: 2734.6, 1: 2735.5. Samples: 2931904. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 00:21:38,445][86177] Avg episode reward: [(0, '-694.890'), (1, '-639.060')] -[2023-11-28 00:21:38,970][87424] Updated weights for policy 0, policy_version 5706 (0.0012) -[2023-11-28 00:21:39,357][87424] Updated weights for policy 0, policy_version 5716 (0.0012) -[2023-11-28 00:21:39,751][87424] Updated weights for policy 0, policy_version 5726 (0.0012) -[2023-11-28 00:21:39,767][87426] Updated weights for policy 1, policy_version 5700 (0.0009) -[2023-11-28 00:21:40,138][87426] Updated weights for policy 1, policy_version 5710 (0.0011) -[2023-11-28 00:21:40,518][87426] Updated weights for policy 1, policy_version 5720 (0.0011) -[2023-11-28 00:21:41,604][87424] Updated weights for policy 0, policy_version 5736 (0.0011) -[2023-11-28 00:21:41,987][87424] Updated weights for policy 0, policy_version 5746 (0.0012) -[2023-11-28 00:21:42,370][87424] Updated weights for policy 0, policy_version 5756 (0.0011) -[2023-11-28 00:21:42,521][87426] Updated weights for policy 1, policy_version 5730 (0.0011) -[2023-11-28 00:21:42,889][87426] Updated weights for policy 1, policy_version 5740 (0.0011) -[2023-11-28 00:21:43,281][87426] Updated weights for policy 1, policy_version 5750 (0.0012) -[2023-11-28 00:21:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5325.0, 300 sec: 5442.8). Total num frames: 2940928. Throughput: 0: 2753.0, 1: 2736.7. Samples: 2956920. Policy #0 lag: (min: 12.0, avg: 35.7, max: 65.0) -[2023-11-28 00:21:43,445][86177] Avg episode reward: [(0, '-702.710'), (1, '-622.680')] -[2023-11-28 00:21:43,656][87320] Saving new best policy, reward=-622.680! -[2023-11-28 00:21:43,657][87426] Updated weights for policy 1, policy_version 5760 (0.0011) -[2023-11-28 00:21:44,140][87424] Updated weights for policy 0, policy_version 5766 (0.0010) -[2023-11-28 00:21:44,513][87424] Updated weights for policy 0, policy_version 5776 (0.0008) -[2023-11-28 00:21:44,899][87424] Updated weights for policy 0, policy_version 5786 (0.0007) -[2023-11-28 00:21:45,884][87426] Updated weights for policy 1, policy_version 5770 (0.0011) -[2023-11-28 00:21:46,258][87426] Updated weights for policy 1, policy_version 5780 (0.0012) -[2023-11-28 00:21:46,636][87426] Updated weights for policy 1, policy_version 5790 (0.0011) -[2023-11-28 00:21:47,347][87424] Updated weights for policy 0, policy_version 5796 (0.0009) -[2023-11-28 00:21:47,723][87424] Updated weights for policy 0, policy_version 5806 (0.0012) -[2023-11-28 00:21:48,106][87424] Updated weights for policy 0, policy_version 5816 (0.0011) -[2023-11-28 00:21:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 2973696. Throughput: 0: 2738.9, 1: 2718.7. Samples: 2981200. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 00:21:48,445][86177] Avg episode reward: [(0, '-695.050'), (1, '-610.750')] -[2023-11-28 00:21:48,532][87426] Updated weights for policy 1, policy_version 5800 (0.0011) -[2023-11-28 00:21:48,911][87426] Updated weights for policy 1, policy_version 5810 (0.0012) -[2023-11-28 00:21:49,296][87426] Updated weights for policy 1, policy_version 5820 (0.0010) -[2023-11-28 00:21:49,438][87320] Saving new best policy, reward=-610.750! -[2023-11-28 00:21:50,638][87424] Updated weights for policy 0, policy_version 5826 (0.0011) -[2023-11-28 00:21:51,027][87424] Updated weights for policy 0, policy_version 5836 (0.0012) -[2023-11-28 00:21:51,423][87424] Updated weights for policy 0, policy_version 5846 (0.0012) -[2023-11-28 00:21:51,746][87426] Updated weights for policy 1, policy_version 5830 (0.0012) -[2023-11-28 00:21:51,805][87424] Updated weights for policy 0, policy_version 5856 (0.0010) -[2023-11-28 00:21:52,119][87426] Updated weights for policy 1, policy_version 5840 (0.0012) -[2023-11-28 00:21:52,506][87426] Updated weights for policy 1, policy_version 5850 (0.0012) -[2023-11-28 00:21:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 2998272. Throughput: 0: 2734.1, 1: 2730.6. Samples: 3014076. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 00:21:53,445][86177] Avg episode reward: [(0, '-723.720'), (1, '-601.610')] -[2023-11-28 00:21:53,446][87320] Saving new best policy, reward=-601.610! -[2023-11-28 00:21:54,331][87424] Updated weights for policy 0, policy_version 5866 (0.0008) -[2023-11-28 00:21:54,723][87424] Updated weights for policy 0, policy_version 5876 (0.0007) -[2023-11-28 00:21:54,869][87426] Updated weights for policy 1, policy_version 5860 (0.0011) -[2023-11-28 00:21:55,104][87424] Updated weights for policy 0, policy_version 5886 (0.0008) -[2023-11-28 00:21:55,242][87426] Updated weights for policy 1, policy_version 5870 (0.0007) -[2023-11-28 00:21:55,620][87426] Updated weights for policy 1, policy_version 5880 (0.0007) -[2023-11-28 00:21:56,860][87424] Updated weights for policy 0, policy_version 5896 (0.0010) -[2023-11-28 00:21:57,245][87424] Updated weights for policy 0, policy_version 5906 (0.0009) -[2023-11-28 00:21:57,639][87424] Updated weights for policy 0, policy_version 5916 (0.0007) -[2023-11-28 00:21:57,740][87426] Updated weights for policy 1, policy_version 5890 (0.0010) -[2023-11-28 00:21:58,127][87426] Updated weights for policy 1, policy_version 5900 (0.0012) -[2023-11-28 00:21:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3022848. Throughput: 0: 2733.3, 1: 2722.1. Samples: 3037972. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 00:21:58,445][86177] Avg episode reward: [(0, '-733.650'), (1, '-598.000')] -[2023-11-28 00:21:58,511][87426] Updated weights for policy 1, policy_version 5910 (0.0011) -[2023-11-28 00:21:58,877][87320] Saving new best policy, reward=-598.000! -[2023-11-28 00:21:58,877][87426] Updated weights for policy 1, policy_version 5920 (0.0012) -[2023-11-28 00:21:59,933][87424] Updated weights for policy 0, policy_version 5926 (0.0010) -[2023-11-28 00:22:00,318][87424] Updated weights for policy 0, policy_version 5936 (0.0012) -[2023-11-28 00:22:00,655][87426] Updated weights for policy 1, policy_version 5930 (0.0012) -[2023-11-28 00:22:00,709][87424] Updated weights for policy 0, policy_version 5946 (0.0010) -[2023-11-28 00:22:01,024][87426] Updated weights for policy 1, policy_version 5940 (0.0011) -[2023-11-28 00:22:01,410][87426] Updated weights for policy 1, policy_version 5950 (0.0009) -[2023-11-28 00:22:02,616][87424] Updated weights for policy 0, policy_version 5956 (0.0009) -[2023-11-28 00:22:03,002][87424] Updated weights for policy 0, policy_version 5966 (0.0012) -[2023-11-28 00:22:03,383][87424] Updated weights for policy 0, policy_version 5976 (0.0011) -[2023-11-28 00:22:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 3047424. Throughput: 0: 2745.0, 1: 2723.5. Samples: 3063704. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 00:22:03,445][86177] Avg episode reward: [(0, '-714.270'), (1, '-593.090')] -[2023-11-28 00:22:03,453][87320] Saving new best policy, reward=-593.090! -[2023-11-28 00:22:03,890][87426] Updated weights for policy 1, policy_version 5960 (0.0010) -[2023-11-28 00:22:04,285][87426] Updated weights for policy 1, policy_version 5970 (0.0010) -[2023-11-28 00:22:04,667][87426] Updated weights for policy 1, policy_version 5980 (0.0011) -[2023-11-28 00:22:05,594][87424] Updated weights for policy 0, policy_version 5986 (0.0011) -[2023-11-28 00:22:05,980][87424] Updated weights for policy 0, policy_version 5996 (0.0011) -[2023-11-28 00:22:06,371][87424] Updated weights for policy 0, policy_version 6006 (0.0012) -[2023-11-28 00:22:06,642][87426] Updated weights for policy 1, policy_version 5990 (0.0010) -[2023-11-28 00:22:06,758][87424] Updated weights for policy 0, policy_version 6016 (0.0012) -[2023-11-28 00:22:07,019][87426] Updated weights for policy 1, policy_version 6000 (0.0007) -[2023-11-28 00:22:07,406][87426] Updated weights for policy 1, policy_version 6010 (0.0010) -[2023-11-28 00:22:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 3080192. Throughput: 0: 2729.1, 1: 2737.8. Samples: 3096036. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 00:22:08,445][86177] Avg episode reward: [(0, '-728.050'), (1, '-596.260')] -[2023-11-28 00:22:08,990][87424] Updated weights for policy 0, policy_version 6026 (0.0008) -[2023-11-28 00:22:09,190][87426] Updated weights for policy 1, policy_version 6020 (0.0009) -[2023-11-28 00:22:09,378][87424] Updated weights for policy 0, policy_version 6036 (0.0008) -[2023-11-28 00:22:09,569][87426] Updated weights for policy 1, policy_version 6030 (0.0011) -[2023-11-28 00:22:09,777][87424] Updated weights for policy 0, policy_version 6046 (0.0010) -[2023-11-28 00:22:09,942][87426] Updated weights for policy 1, policy_version 6040 (0.0011) -[2023-11-28 00:22:12,037][87424] Updated weights for policy 0, policy_version 6056 (0.0012) -[2023-11-28 00:22:12,426][87424] Updated weights for policy 0, policy_version 6066 (0.0012) -[2023-11-28 00:22:12,479][87426] Updated weights for policy 1, policy_version 6050 (0.0012) -[2023-11-28 00:22:12,805][87424] Updated weights for policy 0, policy_version 6076 (0.0012) -[2023-11-28 00:22:12,859][87426] Updated weights for policy 1, policy_version 6060 (0.0010) -[2023-11-28 00:22:13,245][87426] Updated weights for policy 1, policy_version 6070 (0.0012) -[2023-11-28 00:22:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3104768. Throughput: 0: 2739.7, 1: 2717.3. Samples: 3120116. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 00:22:13,445][86177] Avg episode reward: [(0, '-724.260'), (1, '-609.370')] -[2023-11-28 00:22:13,624][87426] Updated weights for policy 1, policy_version 6080 (0.0010) -[2023-11-28 00:22:15,136][87424] Updated weights for policy 0, policy_version 6086 (0.0011) -[2023-11-28 00:22:15,506][87426] Updated weights for policy 1, policy_version 6090 (0.0009) -[2023-11-28 00:22:15,508][87424] Updated weights for policy 0, policy_version 6096 (0.0012) -[2023-11-28 00:22:15,880][87426] Updated weights for policy 1, policy_version 6100 (0.0011) -[2023-11-28 00:22:15,887][87424] Updated weights for policy 0, policy_version 6106 (0.0011) -[2023-11-28 00:22:16,264][87426] Updated weights for policy 1, policy_version 6110 (0.0010) -[2023-11-28 00:22:18,186][87424] Updated weights for policy 0, policy_version 6116 (0.0012) -[2023-11-28 00:22:18,242][87426] Updated weights for policy 1, policy_version 6120 (0.0009) -[2023-11-28 00:22:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 3129344. Throughput: 0: 2745.4, 1: 2723.6. Samples: 3144724. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 00:22:18,445][86177] Avg episode reward: [(0, '-734.950'), (1, '-625.190')] -[2023-11-28 00:22:18,558][87424] Updated weights for policy 0, policy_version 6126 (0.0011) -[2023-11-28 00:22:18,623][87426] Updated weights for policy 1, policy_version 6130 (0.0010) -[2023-11-28 00:22:18,934][87424] Updated weights for policy 0, policy_version 6136 (0.0011) -[2023-11-28 00:22:19,001][87426] Updated weights for policy 1, policy_version 6140 (0.0011) -[2023-11-28 00:22:19,139][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000006144_1572864.pth... -[2023-11-28 00:22:19,181][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000003584_917504.pth -[2023-11-28 00:22:19,237][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000006144_1572864.pth... -[2023-11-28 00:22:19,268][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000003584_917504.pth -[2023-11-28 00:22:21,203][87424] Updated weights for policy 0, policy_version 6146 (0.0011) -[2023-11-28 00:22:21,451][87426] Updated weights for policy 1, policy_version 6150 (0.0011) -[2023-11-28 00:22:21,586][87424] Updated weights for policy 0, policy_version 6156 (0.0010) -[2023-11-28 00:22:21,832][87426] Updated weights for policy 1, policy_version 6160 (0.0012) -[2023-11-28 00:22:21,969][87424] Updated weights for policy 0, policy_version 6166 (0.0010) -[2023-11-28 00:22:22,211][87426] Updated weights for policy 1, policy_version 6170 (0.0012) -[2023-11-28 00:22:22,360][87424] Updated weights for policy 0, policy_version 6176 (0.0011) -[2023-11-28 00:22:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3162112. Throughput: 0: 2725.2, 1: 2739.5. Samples: 3177812. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:22:23,445][86177] Avg episode reward: [(0, '-766.420'), (1, '-629.110')] -[2023-11-28 00:22:24,146][87424] Updated weights for policy 0, policy_version 6186 (0.0007) -[2023-11-28 00:22:24,533][87424] Updated weights for policy 0, policy_version 6196 (0.0007) -[2023-11-28 00:22:24,571][87426] Updated weights for policy 1, policy_version 6180 (0.0011) -[2023-11-28 00:22:24,921][87424] Updated weights for policy 0, policy_version 6206 (0.0008) -[2023-11-28 00:22:24,959][87426] Updated weights for policy 1, policy_version 6190 (0.0009) -[2023-11-28 00:22:25,332][87426] Updated weights for policy 1, policy_version 6200 (0.0008) -[2023-11-28 00:22:27,089][87424] Updated weights for policy 0, policy_version 6216 (0.0010) -[2023-11-28 00:22:27,475][87424] Updated weights for policy 0, policy_version 6226 (0.0010) -[2023-11-28 00:22:27,783][87426] Updated weights for policy 1, policy_version 6210 (0.0008) -[2023-11-28 00:22:27,866][87424] Updated weights for policy 0, policy_version 6236 (0.0008) -[2023-11-28 00:22:28,177][87426] Updated weights for policy 1, policy_version 6220 (0.0010) -[2023-11-28 00:22:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3186688. Throughput: 0: 2712.5, 1: 2719.4. Samples: 3201356. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:22:28,446][86177] Avg episode reward: [(0, '-763.430'), (1, '-625.810')] -[2023-11-28 00:22:28,555][87426] Updated weights for policy 1, policy_version 6230 (0.0007) -[2023-11-28 00:22:28,945][87426] Updated weights for policy 1, policy_version 6240 (0.0011) -[2023-11-28 00:22:29,710][87424] Updated weights for policy 0, policy_version 6246 (0.0008) -[2023-11-28 00:22:30,096][87424] Updated weights for policy 0, policy_version 6256 (0.0010) -[2023-11-28 00:22:30,482][87424] Updated weights for policy 0, policy_version 6266 (0.0011) -[2023-11-28 00:22:30,957][87426] Updated weights for policy 1, policy_version 6250 (0.0012) -[2023-11-28 00:22:31,339][87426] Updated weights for policy 1, policy_version 6260 (0.0012) -[2023-11-28 00:22:31,715][87426] Updated weights for policy 1, policy_version 6270 (0.0012) -[2023-11-28 00:22:32,614][87424] Updated weights for policy 0, policy_version 6276 (0.0008) -[2023-11-28 00:22:32,991][87424] Updated weights for policy 0, policy_version 6286 (0.0010) -[2023-11-28 00:22:33,380][87424] Updated weights for policy 0, policy_version 6296 (0.0008) -[2023-11-28 00:22:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 3211264. Throughput: 0: 2732.1, 1: 2713.7. Samples: 3226260. Policy #0 lag: (min: 31.0, avg: 36.4, max: 61.0) -[2023-11-28 00:22:33,445][86177] Avg episode reward: [(0, '-773.620'), (1, '-648.860')] -[2023-11-28 00:22:34,059][87426] Updated weights for policy 1, policy_version 6280 (0.0010) -[2023-11-28 00:22:34,439][87426] Updated weights for policy 1, policy_version 6290 (0.0011) -[2023-11-28 00:22:34,814][87426] Updated weights for policy 1, policy_version 6300 (0.0012) -[2023-11-28 00:22:35,200][87424] Updated weights for policy 0, policy_version 6306 (0.0009) -[2023-11-28 00:22:35,584][87424] Updated weights for policy 0, policy_version 6316 (0.0008) -[2023-11-28 00:22:35,978][87424] Updated weights for policy 0, policy_version 6326 (0.0008) -[2023-11-28 00:22:36,365][87424] Updated weights for policy 0, policy_version 6336 (0.0010) -[2023-11-28 00:22:37,251][87426] Updated weights for policy 1, policy_version 6310 (0.0011) -[2023-11-28 00:22:37,640][87426] Updated weights for policy 1, policy_version 6320 (0.0011) -[2023-11-28 00:22:38,015][87426] Updated weights for policy 1, policy_version 6330 (0.0012) -[2023-11-28 00:22:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 3244032. Throughput: 0: 2746.7, 1: 2714.1. Samples: 3259812. Policy #0 lag: (min: 31.0, avg: 36.4, max: 61.0) -[2023-11-28 00:22:38,445][86177] Avg episode reward: [(0, '-778.240'), (1, '-630.290')] -[2023-11-28 00:22:38,963][87424] Updated weights for policy 0, policy_version 6346 (0.0009) -[2023-11-28 00:22:39,348][87424] Updated weights for policy 0, policy_version 6356 (0.0010) -[2023-11-28 00:22:39,732][87424] Updated weights for policy 0, policy_version 6366 (0.0008) -[2023-11-28 00:22:40,024][87426] Updated weights for policy 1, policy_version 6340 (0.0011) -[2023-11-28 00:22:40,415][87426] Updated weights for policy 1, policy_version 6350 (0.0008) -[2023-11-28 00:22:40,785][87426] Updated weights for policy 1, policy_version 6360 (0.0008) -[2023-11-28 00:22:41,908][87424] Updated weights for policy 0, policy_version 6376 (0.0012) -[2023-11-28 00:22:42,293][87424] Updated weights for policy 0, policy_version 6386 (0.0012) -[2023-11-28 00:22:42,678][87424] Updated weights for policy 0, policy_version 6396 (0.0012) -[2023-11-28 00:22:42,735][87426] Updated weights for policy 1, policy_version 6370 (0.0011) -[2023-11-28 00:22:43,119][87426] Updated weights for policy 1, policy_version 6380 (0.0010) -[2023-11-28 00:22:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3268608. Throughput: 0: 2741.1, 1: 2735.9. Samples: 3284436. Policy #0 lag: (min: 6.0, avg: 14.2, max: 38.0) -[2023-11-28 00:22:43,445][86177] Avg episode reward: [(0, '-774.120'), (1, '-616.880')] -[2023-11-28 00:22:43,496][87426] Updated weights for policy 1, policy_version 6390 (0.0007) -[2023-11-28 00:22:43,874][87426] Updated weights for policy 1, policy_version 6400 (0.0007) -[2023-11-28 00:22:44,584][87424] Updated weights for policy 0, policy_version 6406 (0.0012) -[2023-11-28 00:22:44,961][87424] Updated weights for policy 0, policy_version 6416 (0.0012) -[2023-11-28 00:22:45,354][87424] Updated weights for policy 0, policy_version 6426 (0.0012) -[2023-11-28 00:22:46,178][87426] Updated weights for policy 1, policy_version 6410 (0.0012) -[2023-11-28 00:22:46,556][87426] Updated weights for policy 1, policy_version 6420 (0.0011) -[2023-11-28 00:22:46,933][87426] Updated weights for policy 1, policy_version 6430 (0.0011) -[2023-11-28 00:22:47,509][87424] Updated weights for policy 0, policy_version 6436 (0.0011) -[2023-11-28 00:22:47,885][87424] Updated weights for policy 0, policy_version 6446 (0.0009) -[2023-11-28 00:22:48,272][87424] Updated weights for policy 0, policy_version 6456 (0.0011) -[2023-11-28 00:22:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 3293184. Throughput: 0: 2732.6, 1: 2723.8. Samples: 3309244. Policy #0 lag: (min: 6.0, avg: 14.2, max: 38.0) -[2023-11-28 00:22:48,445][86177] Avg episode reward: [(0, '-733.990'), (1, '-612.390')] -[2023-11-28 00:22:48,796][87426] Updated weights for policy 1, policy_version 6440 (0.0011) -[2023-11-28 00:22:49,181][87426] Updated weights for policy 1, policy_version 6450 (0.0011) -[2023-11-28 00:22:49,561][87426] Updated weights for policy 1, policy_version 6460 (0.0011) -[2023-11-28 00:22:49,970][87424] Updated weights for policy 0, policy_version 6466 (0.0012) -[2023-11-28 00:22:50,354][87424] Updated weights for policy 0, policy_version 6476 (0.0012) -[2023-11-28 00:22:50,737][87424] Updated weights for policy 0, policy_version 6486 (0.0012) -[2023-11-28 00:22:51,117][87424] Updated weights for policy 0, policy_version 6496 (0.0012) -[2023-11-28 00:22:51,687][87426] Updated weights for policy 1, policy_version 6470 (0.0010) -[2023-11-28 00:22:52,071][87426] Updated weights for policy 1, policy_version 6480 (0.0008) -[2023-11-28 00:22:52,441][87426] Updated weights for policy 1, policy_version 6490 (0.0008) -[2023-11-28 00:22:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 3325952. Throughput: 0: 2747.4, 1: 2723.3. Samples: 3342216. Policy #0 lag: (min: 31.0, avg: 52.8, max: 95.0) -[2023-11-28 00:22:53,446][86177] Avg episode reward: [(0, '-700.330'), (1, '-597.930')] -[2023-11-28 00:22:53,663][87424] Updated weights for policy 0, policy_version 6506 (0.0010) -[2023-11-28 00:22:54,041][87424] Updated weights for policy 0, policy_version 6516 (0.0009) -[2023-11-28 00:22:54,420][87424] Updated weights for policy 0, policy_version 6526 (0.0008) -[2023-11-28 00:22:54,763][87426] Updated weights for policy 1, policy_version 6500 (0.0007) -[2023-11-28 00:22:55,146][87426] Updated weights for policy 1, policy_version 6510 (0.0007) -[2023-11-28 00:22:55,528][87426] Updated weights for policy 1, policy_version 6520 (0.0007) -[2023-11-28 00:22:56,958][87424] Updated weights for policy 0, policy_version 6536 (0.0008) -[2023-11-28 00:22:57,193][87426] Updated weights for policy 1, policy_version 6530 (0.0008) -[2023-11-28 00:22:57,347][87424] Updated weights for policy 0, policy_version 6546 (0.0007) -[2023-11-28 00:22:57,571][87426] Updated weights for policy 1, policy_version 6540 (0.0007) -[2023-11-28 00:22:57,731][87424] Updated weights for policy 0, policy_version 6556 (0.0007) -[2023-11-28 00:22:57,954][87426] Updated weights for policy 1, policy_version 6550 (0.0007) -[2023-11-28 00:22:58,344][87426] Updated weights for policy 1, policy_version 6560 (0.0007) -[2023-11-28 00:22:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 3358720. Throughput: 0: 2736.1, 1: 2745.9. Samples: 3366804. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 00:22:58,445][86177] Avg episode reward: [(0, '-692.440'), (1, '-584.810')] -[2023-11-28 00:22:58,445][87320] Saving new best policy, reward=-584.810! -[2023-11-28 00:22:59,868][87424] Updated weights for policy 0, policy_version 6566 (0.0011) -[2023-11-28 00:23:00,252][87424] Updated weights for policy 0, policy_version 6576 (0.0012) -[2023-11-28 00:23:00,626][87424] Updated weights for policy 0, policy_version 6586 (0.0011) -[2023-11-28 00:23:00,675][87426] Updated weights for policy 1, policy_version 6570 (0.0011) -[2023-11-28 00:23:01,049][87426] Updated weights for policy 1, policy_version 6580 (0.0011) -[2023-11-28 00:23:01,442][87426] Updated weights for policy 1, policy_version 6590 (0.0008) -[2023-11-28 00:23:03,020][87424] Updated weights for policy 0, policy_version 6596 (0.0011) -[2023-11-28 00:23:03,284][87426] Updated weights for policy 1, policy_version 6600 (0.0010) -[2023-11-28 00:23:03,408][87424] Updated weights for policy 0, policy_version 6606 (0.0010) -[2023-11-28 00:23:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 3375104. Throughput: 0: 2722.1, 1: 2731.1. Samples: 3390120. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 00:23:03,446][86177] Avg episode reward: [(0, '-695.470'), (1, '-584.030')] -[2023-11-28 00:23:03,664][87426] Updated weights for policy 1, policy_version 6610 (0.0012) -[2023-11-28 00:23:03,802][87424] Updated weights for policy 0, policy_version 6616 (0.0011) -[2023-11-28 00:23:04,036][87426] Updated weights for policy 1, policy_version 6620 (0.0011) -[2023-11-28 00:23:04,186][87320] Saving new best policy, reward=-584.030! -[2023-11-28 00:23:06,083][87426] Updated weights for policy 1, policy_version 6630 (0.0010) -[2023-11-28 00:23:06,217][87424] Updated weights for policy 0, policy_version 6626 (0.0009) -[2023-11-28 00:23:06,462][87426] Updated weights for policy 1, policy_version 6640 (0.0011) -[2023-11-28 00:23:06,593][87424] Updated weights for policy 0, policy_version 6636 (0.0012) -[2023-11-28 00:23:06,837][87426] Updated weights for policy 1, policy_version 6650 (0.0012) -[2023-11-28 00:23:06,973][87424] Updated weights for policy 0, policy_version 6646 (0.0012) -[2023-11-28 00:23:07,359][87424] Updated weights for policy 0, policy_version 6656 (0.0012) -[2023-11-28 00:23:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3407872. Throughput: 0: 2709.0, 1: 2739.8. Samples: 3423008. Policy #0 lag: (min: 31.0, avg: 43.8, max: 63.0) -[2023-11-28 00:23:08,445][86177] Avg episode reward: [(0, '-698.740'), (1, '-577.860')] -[2023-11-28 00:23:08,446][87320] Saving new best policy, reward=-577.860! -[2023-11-28 00:23:08,875][87426] Updated weights for policy 1, policy_version 6660 (0.0010) -[2023-11-28 00:23:09,254][87426] Updated weights for policy 1, policy_version 6670 (0.0007) -[2023-11-28 00:23:09,600][87424] Updated weights for policy 0, policy_version 6666 (0.0011) -[2023-11-28 00:23:09,640][87426] Updated weights for policy 1, policy_version 6680 (0.0009) -[2023-11-28 00:23:09,978][87424] Updated weights for policy 0, policy_version 6676 (0.0010) -[2023-11-28 00:23:10,359][87424] Updated weights for policy 0, policy_version 6686 (0.0009) -[2023-11-28 00:23:12,179][87426] Updated weights for policy 1, policy_version 6690 (0.0010) -[2023-11-28 00:23:12,379][87424] Updated weights for policy 0, policy_version 6696 (0.0010) -[2023-11-28 00:23:12,553][87426] Updated weights for policy 1, policy_version 6700 (0.0010) -[2023-11-28 00:23:12,766][87424] Updated weights for policy 0, policy_version 6706 (0.0012) -[2023-11-28 00:23:12,929][87426] Updated weights for policy 1, policy_version 6710 (0.0012) -[2023-11-28 00:23:13,149][87424] Updated weights for policy 0, policy_version 6716 (0.0011) -[2023-11-28 00:23:13,310][87426] Updated weights for policy 1, policy_version 6720 (0.0010) -[2023-11-28 00:23:13,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 3440640. Throughput: 0: 2704.3, 1: 2750.8. Samples: 3446832. Policy #0 lag: (min: 31.0, avg: 43.8, max: 63.0) -[2023-11-28 00:23:13,445][86177] Avg episode reward: [(0, '-705.670'), (1, '-583.130')] -[2023-11-28 00:23:15,001][87426] Updated weights for policy 1, policy_version 6730 (0.0012) -[2023-11-28 00:23:15,283][87424] Updated weights for policy 0, policy_version 6726 (0.0010) -[2023-11-28 00:23:15,380][87426] Updated weights for policy 1, policy_version 6740 (0.0009) -[2023-11-28 00:23:15,671][87424] Updated weights for policy 0, policy_version 6736 (0.0012) -[2023-11-28 00:23:15,755][87426] Updated weights for policy 1, policy_version 6750 (0.0009) -[2023-11-28 00:23:16,047][87424] Updated weights for policy 0, policy_version 6746 (0.0012) -[2023-11-28 00:23:18,037][87424] Updated weights for policy 0, policy_version 6756 (0.0010) -[2023-11-28 00:23:18,290][87426] Updated weights for policy 1, policy_version 6760 (0.0011) -[2023-11-28 00:23:18,419][87424] Updated weights for policy 0, policy_version 6766 (0.0007) -[2023-11-28 00:23:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 3457024. Throughput: 0: 2701.6, 1: 2772.1. Samples: 3472576. Policy #0 lag: (min: 6.0, avg: 8.2, max: 26.0) -[2023-11-28 00:23:18,445][86177] Avg episode reward: [(0, '-744.740'), (1, '-585.290')] -[2023-11-28 00:23:18,674][87426] Updated weights for policy 1, policy_version 6770 (0.0012) -[2023-11-28 00:23:18,792][87424] Updated weights for policy 0, policy_version 6776 (0.0008) -[2023-11-28 00:23:19,046][87426] Updated weights for policy 1, policy_version 6780 (0.0010) -[2023-11-28 00:23:20,846][87424] Updated weights for policy 0, policy_version 6786 (0.0010) -[2023-11-28 00:23:21,023][87426] Updated weights for policy 1, policy_version 6790 (0.0012) -[2023-11-28 00:23:21,230][87424] Updated weights for policy 0, policy_version 6796 (0.0010) -[2023-11-28 00:23:21,404][87426] Updated weights for policy 1, policy_version 6800 (0.0009) -[2023-11-28 00:23:21,610][87424] Updated weights for policy 0, policy_version 6806 (0.0008) -[2023-11-28 00:23:21,782][87426] Updated weights for policy 1, policy_version 6810 (0.0010) -[2023-11-28 00:23:21,994][87424] Updated weights for policy 0, policy_version 6816 (0.0010) -[2023-11-28 00:23:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 3489792. Throughput: 0: 2683.8, 1: 2765.8. Samples: 3505044. Policy #0 lag: (min: 6.0, avg: 8.2, max: 26.0) -[2023-11-28 00:23:23,445][86177] Avg episode reward: [(0, '-745.300'), (1, '-586.830')] -[2023-11-28 00:23:24,180][87426] Updated weights for policy 1, policy_version 6820 (0.0009) -[2023-11-28 00:23:24,261][87424] Updated weights for policy 0, policy_version 6826 (0.0009) -[2023-11-28 00:23:24,567][87426] Updated weights for policy 1, policy_version 6830 (0.0008) -[2023-11-28 00:23:24,651][87424] Updated weights for policy 0, policy_version 6836 (0.0008) -[2023-11-28 00:23:24,947][87426] Updated weights for policy 1, policy_version 6840 (0.0010) -[2023-11-28 00:23:25,032][87424] Updated weights for policy 0, policy_version 6846 (0.0011) -[2023-11-28 00:23:27,343][87424] Updated weights for policy 0, policy_version 6856 (0.0008) -[2023-11-28 00:23:27,348][87426] Updated weights for policy 1, policy_version 6850 (0.0009) -[2023-11-28 00:23:27,723][87426] Updated weights for policy 1, policy_version 6860 (0.0009) -[2023-11-28 00:23:27,725][87424] Updated weights for policy 0, policy_version 6866 (0.0007) -[2023-11-28 00:23:28,098][87426] Updated weights for policy 1, policy_version 6870 (0.0007) -[2023-11-28 00:23:28,109][87424] Updated weights for policy 0, policy_version 6876 (0.0007) -[2023-11-28 00:23:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 3514368. Throughput: 0: 2691.5, 1: 2753.2. Samples: 3529448. Policy #0 lag: (min: 14.0, avg: 18.7, max: 46.0) -[2023-11-28 00:23:28,445][86177] Avg episode reward: [(0, '-746.350'), (1, '-596.770')] -[2023-11-28 00:23:28,478][87426] Updated weights for policy 1, policy_version 6880 (0.0010) -[2023-11-28 00:23:29,771][87424] Updated weights for policy 0, policy_version 6886 (0.0010) -[2023-11-28 00:23:30,152][87424] Updated weights for policy 0, policy_version 6896 (0.0012) -[2023-11-28 00:23:30,543][87426] Updated weights for policy 1, policy_version 6890 (0.0008) -[2023-11-28 00:23:30,548][87424] Updated weights for policy 0, policy_version 6906 (0.0012) -[2023-11-28 00:23:30,925][87426] Updated weights for policy 1, policy_version 6900 (0.0008) -[2023-11-28 00:23:31,316][87426] Updated weights for policy 1, policy_version 6910 (0.0007) -[2023-11-28 00:23:32,912][87424] Updated weights for policy 0, policy_version 6916 (0.0012) -[2023-11-28 00:23:33,309][87424] Updated weights for policy 0, policy_version 6926 (0.0012) -[2023-11-28 00:23:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 3538944. Throughput: 0: 2709.8, 1: 2746.2. Samples: 3554764. Policy #0 lag: (min: 14.0, avg: 18.7, max: 46.0) -[2023-11-28 00:23:33,445][86177] Avg episode reward: [(0, '-778.770'), (1, '-590.650')] -[2023-11-28 00:23:33,685][87424] Updated weights for policy 0, policy_version 6936 (0.0012) -[2023-11-28 00:23:33,881][87426] Updated weights for policy 1, policy_version 6920 (0.0010) -[2023-11-28 00:23:34,276][87426] Updated weights for policy 1, policy_version 6930 (0.0011) -[2023-11-28 00:23:34,664][87426] Updated weights for policy 1, policy_version 6940 (0.0010) -[2023-11-28 00:23:36,223][87424] Updated weights for policy 0, policy_version 6946 (0.0010) -[2023-11-28 00:23:36,597][87424] Updated weights for policy 0, policy_version 6956 (0.0012) -[2023-11-28 00:23:36,980][87424] Updated weights for policy 0, policy_version 6966 (0.0008) -[2023-11-28 00:23:37,124][87426] Updated weights for policy 1, policy_version 6950 (0.0011) -[2023-11-28 00:23:37,352][87424] Updated weights for policy 0, policy_version 6976 (0.0010) -[2023-11-28 00:23:37,511][87426] Updated weights for policy 1, policy_version 6960 (0.0012) -[2023-11-28 00:23:37,879][87426] Updated weights for policy 1, policy_version 6970 (0.0012) -[2023-11-28 00:23:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 3571712. Throughput: 0: 2708.6, 1: 2703.2. Samples: 3585748. Policy #0 lag: (min: 11.0, avg: 39.2, max: 72.0) -[2023-11-28 00:23:38,445][86177] Avg episode reward: [(0, '-774.530'), (1, '-579.760')] -[2023-11-28 00:23:39,309][87424] Updated weights for policy 0, policy_version 6986 (0.0011) -[2023-11-28 00:23:39,692][87424] Updated weights for policy 0, policy_version 6996 (0.0011) -[2023-11-28 00:23:40,077][87424] Updated weights for policy 0, policy_version 7006 (0.0011) -[2023-11-28 00:23:40,354][87426] Updated weights for policy 1, policy_version 6980 (0.0012) -[2023-11-28 00:23:40,724][87426] Updated weights for policy 1, policy_version 6990 (0.0012) -[2023-11-28 00:23:41,106][87426] Updated weights for policy 1, policy_version 7000 (0.0012) -[2023-11-28 00:23:41,991][87424] Updated weights for policy 0, policy_version 7016 (0.0011) -[2023-11-28 00:23:42,373][87424] Updated weights for policy 0, policy_version 7026 (0.0012) -[2023-11-28 00:23:42,758][87424] Updated weights for policy 0, policy_version 7036 (0.0012) -[2023-11-28 00:23:43,280][87426] Updated weights for policy 1, policy_version 7010 (0.0008) -[2023-11-28 00:23:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3596288. Throughput: 0: 2739.6, 1: 2675.6. Samples: 3610492. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-11-28 00:23:43,445][86177] Avg episode reward: [(0, '-739.440'), (1, '-580.180')] -[2023-11-28 00:23:43,669][87426] Updated weights for policy 1, policy_version 7020 (0.0007) -[2023-11-28 00:23:44,050][87426] Updated weights for policy 1, policy_version 7030 (0.0007) -[2023-11-28 00:23:44,429][87426] Updated weights for policy 1, policy_version 7040 (0.0010) -[2023-11-28 00:23:44,788][87424] Updated weights for policy 0, policy_version 7046 (0.0010) -[2023-11-28 00:23:45,184][87424] Updated weights for policy 0, policy_version 7056 (0.0007) -[2023-11-28 00:23:45,558][87424] Updated weights for policy 0, policy_version 7066 (0.0008) -[2023-11-28 00:23:46,973][87426] Updated weights for policy 1, policy_version 7050 (0.0008) -[2023-11-28 00:23:47,352][87426] Updated weights for policy 1, policy_version 7060 (0.0007) -[2023-11-28 00:23:47,729][87426] Updated weights for policy 1, policy_version 7070 (0.0007) -[2023-11-28 00:23:48,037][87424] Updated weights for policy 0, policy_version 7076 (0.0009) -[2023-11-28 00:23:48,425][87424] Updated weights for policy 0, policy_version 7086 (0.0012) -[2023-11-28 00:23:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3620864. Throughput: 0: 2763.5, 1: 2695.3. Samples: 3635764. Policy #0 lag: (min: 31.0, avg: 44.1, max: 63.0) -[2023-11-28 00:23:48,445][86177] Avg episode reward: [(0, '-736.660'), (1, '-572.950')] -[2023-11-28 00:23:48,454][87320] Saving new best policy, reward=-572.950! -[2023-11-28 00:23:48,806][87424] Updated weights for policy 0, policy_version 7096 (0.0009) -[2023-11-28 00:23:49,489][87426] Updated weights for policy 1, policy_version 7080 (0.0011) -[2023-11-28 00:23:49,869][87426] Updated weights for policy 1, policy_version 7090 (0.0012) -[2023-11-28 00:23:50,248][87426] Updated weights for policy 1, policy_version 7100 (0.0012) -[2023-11-28 00:23:50,545][87424] Updated weights for policy 0, policy_version 7106 (0.0013) -[2023-11-28 00:23:50,934][87424] Updated weights for policy 0, policy_version 7116 (0.0012) -[2023-11-28 00:23:51,315][87424] Updated weights for policy 0, policy_version 7126 (0.0012) -[2023-11-28 00:23:51,687][87424] Updated weights for policy 0, policy_version 7136 (0.0012) -[2023-11-28 00:23:52,650][87426] Updated weights for policy 1, policy_version 7110 (0.0011) -[2023-11-28 00:23:53,035][87426] Updated weights for policy 1, policy_version 7120 (0.0011) -[2023-11-28 00:23:53,418][87426] Updated weights for policy 1, policy_version 7130 (0.0011) -[2023-11-28 00:23:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 3645440. Throughput: 0: 2794.1, 1: 2678.8. Samples: 3669288. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-11-28 00:23:53,445][86177] Avg episode reward: [(0, '-744.140'), (1, '-566.060')] -[2023-11-28 00:23:53,566][87424] Updated weights for policy 0, policy_version 7146 (0.0012) -[2023-11-28 00:23:53,636][87320] Saving new best policy, reward=-566.060! -[2023-11-28 00:23:53,957][87424] Updated weights for policy 0, policy_version 7156 (0.0010) -[2023-11-28 00:23:54,347][87424] Updated weights for policy 0, policy_version 7166 (0.0008) -[2023-11-28 00:23:55,988][87426] Updated weights for policy 1, policy_version 7140 (0.0008) -[2023-11-28 00:23:56,356][87426] Updated weights for policy 1, policy_version 7150 (0.0007) -[2023-11-28 00:23:56,739][87426] Updated weights for policy 1, policy_version 7160 (0.0011) -[2023-11-28 00:23:56,745][87424] Updated weights for policy 0, policy_version 7176 (0.0009) -[2023-11-28 00:23:57,121][87424] Updated weights for policy 0, policy_version 7186 (0.0012) -[2023-11-28 00:23:57,513][87424] Updated weights for policy 0, policy_version 7196 (0.0011) -[2023-11-28 00:23:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 3678208. Throughput: 0: 2785.8, 1: 2666.4. Samples: 3692180. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-11-28 00:23:58,445][86177] Avg episode reward: [(0, '-724.020'), (1, '-564.690')] -[2023-11-28 00:23:58,530][87426] Updated weights for policy 1, policy_version 7170 (0.0010) -[2023-11-28 00:23:58,918][87426] Updated weights for policy 1, policy_version 7180 (0.0007) -[2023-11-28 00:23:59,304][87426] Updated weights for policy 1, policy_version 7190 (0.0007) -[2023-11-28 00:23:59,596][87424] Updated weights for policy 0, policy_version 7206 (0.0012) -[2023-11-28 00:23:59,705][87320] Saving new best policy, reward=-564.690! -[2023-11-28 00:23:59,710][87426] Updated weights for policy 1, policy_version 7200 (0.0008) -[2023-11-28 00:23:59,989][87424] Updated weights for policy 0, policy_version 7216 (0.0012) -[2023-11-28 00:24:00,363][87424] Updated weights for policy 0, policy_version 7226 (0.0012) -[2023-11-28 00:24:01,525][87426] Updated weights for policy 1, policy_version 7210 (0.0011) -[2023-11-28 00:24:01,905][87426] Updated weights for policy 1, policy_version 7220 (0.0010) -[2023-11-28 00:24:02,298][87426] Updated weights for policy 1, policy_version 7230 (0.0010) -[2023-11-28 00:24:02,507][87424] Updated weights for policy 0, policy_version 7236 (0.0010) -[2023-11-28 00:24:02,888][87424] Updated weights for policy 0, policy_version 7246 (0.0007) -[2023-11-28 00:24:03,276][87424] Updated weights for policy 0, policy_version 7256 (0.0007) -[2023-11-28 00:24:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 3702784. Throughput: 0: 2762.2, 1: 2648.8. Samples: 3716072. Policy #0 lag: (min: 29.0, avg: 45.8, max: 78.0) -[2023-11-28 00:24:03,445][86177] Avg episode reward: [(0, '-733.190'), (1, '-566.200')] -[2023-11-28 00:24:04,712][87426] Updated weights for policy 1, policy_version 7240 (0.0011) -[2023-11-28 00:24:05,089][87426] Updated weights for policy 1, policy_version 7250 (0.0011) -[2023-11-28 00:24:05,462][87426] Updated weights for policy 1, policy_version 7260 (0.0009) -[2023-11-28 00:24:05,541][87424] Updated weights for policy 0, policy_version 7266 (0.0008) -[2023-11-28 00:24:05,923][87424] Updated weights for policy 0, policy_version 7276 (0.0010) -[2023-11-28 00:24:06,314][87424] Updated weights for policy 0, policy_version 7286 (0.0009) -[2023-11-28 00:24:06,695][87424] Updated weights for policy 0, policy_version 7296 (0.0010) -[2023-11-28 00:24:07,231][87426] Updated weights for policy 1, policy_version 7270 (0.0011) -[2023-11-28 00:24:07,611][87426] Updated weights for policy 1, policy_version 7280 (0.0011) -[2023-11-28 00:24:07,984][87426] Updated weights for policy 1, policy_version 7290 (0.0009) -[2023-11-28 00:24:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3735552. Throughput: 0: 2759.7, 1: 2661.9. Samples: 3749016. Policy #0 lag: (min: 29.0, avg: 45.8, max: 78.0) -[2023-11-28 00:24:08,445][86177] Avg episode reward: [(0, '-750.040'), (1, '-562.920')] -[2023-11-28 00:24:08,446][87320] Saving new best policy, reward=-562.920! -[2023-11-28 00:24:08,920][87424] Updated weights for policy 0, policy_version 7306 (0.0008) -[2023-11-28 00:24:09,305][87424] Updated weights for policy 0, policy_version 7316 (0.0010) -[2023-11-28 00:24:09,690][87424] Updated weights for policy 0, policy_version 7326 (0.0011) -[2023-11-28 00:24:10,218][87426] Updated weights for policy 1, policy_version 7300 (0.0009) -[2023-11-28 00:24:10,594][87426] Updated weights for policy 1, policy_version 7310 (0.0012) -[2023-11-28 00:24:10,975][87426] Updated weights for policy 1, policy_version 7320 (0.0012) -[2023-11-28 00:24:12,200][87424] Updated weights for policy 0, policy_version 7336 (0.0011) -[2023-11-28 00:24:12,586][87424] Updated weights for policy 0, policy_version 7346 (0.0012) -[2023-11-28 00:24:12,965][87424] Updated weights for policy 0, policy_version 7356 (0.0012) -[2023-11-28 00:24:13,335][87426] Updated weights for policy 1, policy_version 7330 (0.0011) -[2023-11-28 00:24:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 3760128. Throughput: 0: 2750.6, 1: 2656.6. Samples: 3772772. Policy #0 lag: (min: 31.0, avg: 55.9, max: 95.0) -[2023-11-28 00:24:13,445][86177] Avg episode reward: [(0, '-754.190'), (1, '-554.210')] -[2023-11-28 00:24:13,711][87426] Updated weights for policy 1, policy_version 7340 (0.0008) -[2023-11-28 00:24:14,084][87426] Updated weights for policy 1, policy_version 7350 (0.0008) -[2023-11-28 00:24:14,463][87320] Saving new best policy, reward=-554.210! -[2023-11-28 00:24:14,465][87426] Updated weights for policy 1, policy_version 7360 (0.0011) -[2023-11-28 00:24:15,512][87424] Updated weights for policy 0, policy_version 7366 (0.0012) -[2023-11-28 00:24:15,899][87424] Updated weights for policy 0, policy_version 7376 (0.0008) -[2023-11-28 00:24:16,284][87424] Updated weights for policy 0, policy_version 7386 (0.0010) -[2023-11-28 00:24:16,988][87426] Updated weights for policy 1, policy_version 7370 (0.0012) -[2023-11-28 00:24:17,369][87426] Updated weights for policy 1, policy_version 7380 (0.0012) -[2023-11-28 00:24:17,746][87426] Updated weights for policy 1, policy_version 7390 (0.0012) -[2023-11-28 00:24:18,112][87424] Updated weights for policy 0, policy_version 7396 (0.0011) -[2023-11-28 00:24:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3784704. Throughput: 0: 2696.4, 1: 2662.0. Samples: 3795892. Policy #0 lag: (min: 31.0, avg: 55.9, max: 95.0) -[2023-11-28 00:24:18,445][86177] Avg episode reward: [(0, '-758.730'), (1, '-557.510')] -[2023-11-28 00:24:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000007392_1892352.pth... -[2023-11-28 00:24:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000004864_1245184.pth -[2023-11-28 00:24:18,498][87424] Updated weights for policy 0, policy_version 7406 (0.0008) -[2023-11-28 00:24:18,879][87424] Updated weights for policy 0, policy_version 7416 (0.0008) -[2023-11-28 00:24:19,185][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000007424_1900544.pth... -[2023-11-28 00:24:19,219][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000004864_1245184.pth -[2023-11-28 00:24:19,983][87426] Updated weights for policy 1, policy_version 7400 (0.0010) -[2023-11-28 00:24:20,365][87426] Updated weights for policy 1, policy_version 7410 (0.0011) -[2023-11-28 00:24:20,740][87426] Updated weights for policy 1, policy_version 7420 (0.0011) -[2023-11-28 00:24:21,238][87424] Updated weights for policy 0, policy_version 7426 (0.0011) -[2023-11-28 00:24:21,616][87424] Updated weights for policy 0, policy_version 7436 (0.0012) -[2023-11-28 00:24:22,001][87424] Updated weights for policy 0, policy_version 7446 (0.0012) -[2023-11-28 00:24:22,390][87424] Updated weights for policy 0, policy_version 7456 (0.0012) -[2023-11-28 00:24:23,058][87426] Updated weights for policy 1, policy_version 7430 (0.0010) -[2023-11-28 00:24:23,440][87426] Updated weights for policy 1, policy_version 7440 (0.0010) -[2023-11-28 00:24:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 3809280. Throughput: 0: 2702.0, 1: 2684.2. Samples: 3828124. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 00:24:23,445][86177] Avg episode reward: [(0, '-743.820'), (1, '-554.430')] -[2023-11-28 00:24:23,825][87426] Updated weights for policy 1, policy_version 7450 (0.0008) -[2023-11-28 00:24:24,418][87424] Updated weights for policy 0, policy_version 7466 (0.0007) -[2023-11-28 00:24:24,801][87424] Updated weights for policy 0, policy_version 7476 (0.0007) -[2023-11-28 00:24:25,189][87424] Updated weights for policy 0, policy_version 7486 (0.0007) -[2023-11-28 00:24:26,103][87426] Updated weights for policy 1, policy_version 7460 (0.0008) -[2023-11-28 00:24:26,481][87426] Updated weights for policy 1, policy_version 7470 (0.0009) -[2023-11-28 00:24:26,860][87426] Updated weights for policy 1, policy_version 7480 (0.0007) -[2023-11-28 00:24:27,425][87424] Updated weights for policy 0, policy_version 7496 (0.0007) -[2023-11-28 00:24:27,806][87424] Updated weights for policy 0, policy_version 7506 (0.0007) -[2023-11-28 00:24:28,193][87424] Updated weights for policy 0, policy_version 7516 (0.0007) -[2023-11-28 00:24:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3842048. Throughput: 0: 2689.3, 1: 2695.9. Samples: 3852828. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 00:24:28,445][86177] Avg episode reward: [(0, '-735.520'), (1, '-552.980')] -[2023-11-28 00:24:28,446][87320] Saving new best policy, reward=-552.980! -[2023-11-28 00:24:29,057][87426] Updated weights for policy 1, policy_version 7490 (0.0011) -[2023-11-28 00:24:29,439][87426] Updated weights for policy 1, policy_version 7500 (0.0011) -[2023-11-28 00:24:29,822][87426] Updated weights for policy 1, policy_version 7510 (0.0012) -[2023-11-28 00:24:30,199][87426] Updated weights for policy 1, policy_version 7520 (0.0012) -[2023-11-28 00:24:30,412][87424] Updated weights for policy 0, policy_version 7526 (0.0010) -[2023-11-28 00:24:30,790][87424] Updated weights for policy 0, policy_version 7536 (0.0011) -[2023-11-28 00:24:31,172][87424] Updated weights for policy 0, policy_version 7546 (0.0008) -[2023-11-28 00:24:32,542][87426] Updated weights for policy 1, policy_version 7530 (0.0012) -[2023-11-28 00:24:32,918][87426] Updated weights for policy 1, policy_version 7540 (0.0012) -[2023-11-28 00:24:33,297][87426] Updated weights for policy 1, policy_version 7550 (0.0011) -[2023-11-28 00:24:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3866624. Throughput: 0: 2677.2, 1: 2692.3. Samples: 3877392. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 00:24:33,445][86177] Avg episode reward: [(0, '-692.460'), (1, '-550.550')] -[2023-11-28 00:24:33,454][87320] Saving new best policy, reward=-550.550! -[2023-11-28 00:24:33,723][87424] Updated weights for policy 0, policy_version 7556 (0.0008) -[2023-11-28 00:24:34,110][87424] Updated weights for policy 0, policy_version 7566 (0.0007) -[2023-11-28 00:24:34,512][87424] Updated weights for policy 0, policy_version 7576 (0.0008) -[2023-11-28 00:24:35,790][87426] Updated weights for policy 1, policy_version 7560 (0.0011) -[2023-11-28 00:24:36,167][87426] Updated weights for policy 1, policy_version 7570 (0.0012) -[2023-11-28 00:24:36,358][87424] Updated weights for policy 0, policy_version 7586 (0.0010) -[2023-11-28 00:24:36,545][87426] Updated weights for policy 1, policy_version 7580 (0.0012) -[2023-11-28 00:24:36,738][87424] Updated weights for policy 0, policy_version 7596 (0.0010) -[2023-11-28 00:24:37,125][87424] Updated weights for policy 0, policy_version 7606 (0.0011) -[2023-11-28 00:24:37,517][87424] Updated weights for policy 0, policy_version 7616 (0.0011) -[2023-11-28 00:24:38,438][87426] Updated weights for policy 1, policy_version 7590 (0.0011) -[2023-11-28 00:24:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 3891200. Throughput: 0: 2677.6, 1: 2672.9. Samples: 3910060. Policy #0 lag: (min: 29.0, avg: 53.1, max: 60.0) -[2023-11-28 00:24:38,445][86177] Avg episode reward: [(0, '-700.460'), (1, '-540.700')] -[2023-11-28 00:24:38,820][87426] Updated weights for policy 1, policy_version 7600 (0.0012) -[2023-11-28 00:24:39,197][87426] Updated weights for policy 1, policy_version 7610 (0.0011) -[2023-11-28 00:24:39,419][87320] Saving new best policy, reward=-540.700! -[2023-11-28 00:24:39,726][87424] Updated weights for policy 0, policy_version 7626 (0.0011) -[2023-11-28 00:24:40,106][87424] Updated weights for policy 0, policy_version 7636 (0.0010) -[2023-11-28 00:24:40,491][87424] Updated weights for policy 0, policy_version 7646 (0.0008) -[2023-11-28 00:24:41,132][87426] Updated weights for policy 1, policy_version 7620 (0.0012) -[2023-11-28 00:24:41,521][87426] Updated weights for policy 1, policy_version 7630 (0.0012) -[2023-11-28 00:24:41,895][87426] Updated weights for policy 1, policy_version 7640 (0.0010) -[2023-11-28 00:24:42,755][87424] Updated weights for policy 0, policy_version 7656 (0.0011) -[2023-11-28 00:24:43,136][87424] Updated weights for policy 0, policy_version 7666 (0.0011) -[2023-11-28 00:24:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 3915776. Throughput: 0: 2694.2, 1: 2712.3. Samples: 3935472. Policy #0 lag: (min: 29.0, avg: 53.1, max: 60.0) -[2023-11-28 00:24:43,445][86177] Avg episode reward: [(0, '-681.240'), (1, '-542.530')] -[2023-11-28 00:24:43,517][87424] Updated weights for policy 0, policy_version 7676 (0.0009) -[2023-11-28 00:24:43,894][87426] Updated weights for policy 1, policy_version 7650 (0.0012) -[2023-11-28 00:24:44,274][87426] Updated weights for policy 1, policy_version 7660 (0.0012) -[2023-11-28 00:24:44,653][87426] Updated weights for policy 1, policy_version 7670 (0.0012) -[2023-11-28 00:24:45,034][87426] Updated weights for policy 1, policy_version 7680 (0.0011) -[2023-11-28 00:24:45,356][87424] Updated weights for policy 0, policy_version 7686 (0.0010) -[2023-11-28 00:24:45,727][87424] Updated weights for policy 0, policy_version 7696 (0.0012) -[2023-11-28 00:24:46,114][87424] Updated weights for policy 0, policy_version 7706 (0.0011) -[2023-11-28 00:24:47,334][87426] Updated weights for policy 1, policy_version 7690 (0.0012) -[2023-11-28 00:24:47,711][87426] Updated weights for policy 1, policy_version 7700 (0.0011) -[2023-11-28 00:24:48,083][87426] Updated weights for policy 1, policy_version 7710 (0.0010) -[2023-11-28 00:24:48,195][87424] Updated weights for policy 0, policy_version 7716 (0.0010) -[2023-11-28 00:24:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 3948544. Throughput: 0: 2695.1, 1: 2714.2. Samples: 3959492. Policy #0 lag: (min: 14.0, avg: 36.0, max: 46.0) -[2023-11-28 00:24:48,445][86177] Avg episode reward: [(0, '-673.010'), (1, '-544.640')] -[2023-11-28 00:24:48,573][87424] Updated weights for policy 0, policy_version 7726 (0.0009) -[2023-11-28 00:24:48,961][87424] Updated weights for policy 0, policy_version 7736 (0.0012) -[2023-11-28 00:24:50,556][87426] Updated weights for policy 1, policy_version 7720 (0.0011) -[2023-11-28 00:24:50,814][87424] Updated weights for policy 0, policy_version 7746 (0.0010) -[2023-11-28 00:24:50,938][87426] Updated weights for policy 1, policy_version 7730 (0.0010) -[2023-11-28 00:24:51,198][87424] Updated weights for policy 0, policy_version 7756 (0.0011) -[2023-11-28 00:24:51,323][87426] Updated weights for policy 1, policy_version 7740 (0.0011) -[2023-11-28 00:24:51,589][87424] Updated weights for policy 0, policy_version 7766 (0.0011) -[2023-11-28 00:24:51,962][87424] Updated weights for policy 0, policy_version 7776 (0.0011) -[2023-11-28 00:24:53,302][87426] Updated weights for policy 1, policy_version 7750 (0.0009) -[2023-11-28 00:24:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 3973120. Throughput: 0: 2709.3, 1: 2673.7. Samples: 3991252. Policy #0 lag: (min: 14.0, avg: 36.0, max: 46.0) -[2023-11-28 00:24:53,445][86177] Avg episode reward: [(0, '-736.450'), (1, '-548.600')] -[2023-11-28 00:24:53,683][87426] Updated weights for policy 1, policy_version 7760 (0.0011) -[2023-11-28 00:24:54,002][87424] Updated weights for policy 0, policy_version 7786 (0.0012) -[2023-11-28 00:24:54,062][87426] Updated weights for policy 1, policy_version 7770 (0.0010) -[2023-11-28 00:24:54,376][87424] Updated weights for policy 0, policy_version 7796 (0.0009) -[2023-11-28 00:24:54,765][87424] Updated weights for policy 0, policy_version 7806 (0.0007) -[2023-11-28 00:24:56,568][87426] Updated weights for policy 1, policy_version 7780 (0.0012) -[2023-11-28 00:24:56,958][87426] Updated weights for policy 1, policy_version 7790 (0.0011) -[2023-11-28 00:24:57,245][87424] Updated weights for policy 0, policy_version 7816 (0.0009) -[2023-11-28 00:24:57,327][87426] Updated weights for policy 1, policy_version 7800 (0.0011) -[2023-11-28 00:24:57,630][87424] Updated weights for policy 0, policy_version 7826 (0.0008) -[2023-11-28 00:24:58,022][87424] Updated weights for policy 0, policy_version 7836 (0.0008) -[2023-11-28 00:24:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 4005888. Throughput: 0: 2715.6, 1: 2659.7. Samples: 4014664. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 00:24:58,445][86177] Avg episode reward: [(0, '-750.680'), (1, '-551.220')] -[2023-11-28 00:24:59,026][87426] Updated weights for policy 1, policy_version 7810 (0.0012) -[2023-11-28 00:24:59,415][87426] Updated weights for policy 1, policy_version 7820 (0.0007) -[2023-11-28 00:24:59,793][87426] Updated weights for policy 1, policy_version 7830 (0.0008) -[2023-11-28 00:25:00,168][87426] Updated weights for policy 1, policy_version 7840 (0.0008) -[2023-11-28 00:25:00,516][87424] Updated weights for policy 0, policy_version 7846 (0.0008) -[2023-11-28 00:25:00,900][87424] Updated weights for policy 0, policy_version 7856 (0.0009) -[2023-11-28 00:25:01,270][87424] Updated weights for policy 0, policy_version 7866 (0.0008) -[2023-11-28 00:25:02,521][87426] Updated weights for policy 1, policy_version 7850 (0.0011) -[2023-11-28 00:25:02,899][87426] Updated weights for policy 1, policy_version 7860 (0.0011) -[2023-11-28 00:25:03,279][87426] Updated weights for policy 1, policy_version 7870 (0.0009) -[2023-11-28 00:25:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4030464. Throughput: 0: 2726.8, 1: 2671.4. Samples: 4038812. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 00:25:03,445][86177] Avg episode reward: [(0, '-753.050'), (1, '-549.420')] -[2023-11-28 00:25:03,688][87424] Updated weights for policy 0, policy_version 7876 (0.0009) -[2023-11-28 00:25:04,074][87424] Updated weights for policy 0, policy_version 7886 (0.0011) -[2023-11-28 00:25:04,451][87424] Updated weights for policy 0, policy_version 7896 (0.0009) -[2023-11-28 00:25:05,068][87426] Updated weights for policy 1, policy_version 7880 (0.0011) -[2023-11-28 00:25:05,449][87426] Updated weights for policy 1, policy_version 7890 (0.0012) -[2023-11-28 00:25:05,830][87426] Updated weights for policy 1, policy_version 7900 (0.0012) -[2023-11-28 00:25:06,371][87424] Updated weights for policy 0, policy_version 7906 (0.0011) -[2023-11-28 00:25:06,754][87424] Updated weights for policy 0, policy_version 7916 (0.0011) -[2023-11-28 00:25:07,139][87424] Updated weights for policy 0, policy_version 7926 (0.0011) -[2023-11-28 00:25:07,527][87424] Updated weights for policy 0, policy_version 7936 (0.0010) -[2023-11-28 00:25:08,036][87426] Updated weights for policy 1, policy_version 7910 (0.0012) -[2023-11-28 00:25:08,408][87426] Updated weights for policy 1, policy_version 7920 (0.0011) -[2023-11-28 00:25:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 4055040. Throughput: 0: 2716.9, 1: 2712.8. Samples: 4072460. Policy #0 lag: (min: 31.0, avg: 33.0, max: 49.0) -[2023-11-28 00:25:08,445][86177] Avg episode reward: [(0, '-754.740'), (1, '-550.410')] -[2023-11-28 00:25:08,786][87426] Updated weights for policy 1, policy_version 7930 (0.0012) -[2023-11-28 00:25:09,773][87424] Updated weights for policy 0, policy_version 7946 (0.0012) -[2023-11-28 00:25:10,163][87424] Updated weights for policy 0, policy_version 7956 (0.0011) -[2023-11-28 00:25:10,554][87424] Updated weights for policy 0, policy_version 7966 (0.0012) -[2023-11-28 00:25:11,311][87426] Updated weights for policy 1, policy_version 7940 (0.0010) -[2023-11-28 00:25:11,690][87426] Updated weights for policy 1, policy_version 7950 (0.0009) -[2023-11-28 00:25:12,071][87426] Updated weights for policy 1, policy_version 7960 (0.0011) -[2023-11-28 00:25:13,015][87424] Updated weights for policy 0, policy_version 7976 (0.0012) -[2023-11-28 00:25:13,407][87424] Updated weights for policy 0, policy_version 7986 (0.0012) -[2023-11-28 00:25:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 4079616. Throughput: 0: 2708.1, 1: 2697.9. Samples: 4096096. Policy #0 lag: (min: 31.0, avg: 33.0, max: 49.0) -[2023-11-28 00:25:13,445][86177] Avg episode reward: [(0, '-761.620'), (1, '-542.800')] -[2023-11-28 00:25:13,784][87424] Updated weights for policy 0, policy_version 7996 (0.0012) -[2023-11-28 00:25:14,120][87426] Updated weights for policy 1, policy_version 7970 (0.0010) -[2023-11-28 00:25:14,500][87426] Updated weights for policy 1, policy_version 7980 (0.0007) -[2023-11-28 00:25:14,884][87426] Updated weights for policy 1, policy_version 7990 (0.0007) -[2023-11-28 00:25:15,272][87426] Updated weights for policy 1, policy_version 8000 (0.0009) -[2023-11-28 00:25:15,464][87424] Updated weights for policy 0, policy_version 8006 (0.0011) -[2023-11-28 00:25:15,844][87424] Updated weights for policy 0, policy_version 8016 (0.0008) -[2023-11-28 00:25:16,224][87424] Updated weights for policy 0, policy_version 8026 (0.0008) -[2023-11-28 00:25:17,743][87426] Updated weights for policy 1, policy_version 8010 (0.0007) -[2023-11-28 00:25:18,122][87426] Updated weights for policy 1, policy_version 8020 (0.0007) -[2023-11-28 00:25:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 4104192. Throughput: 0: 2716.5, 1: 2684.3. Samples: 4120428. Policy #0 lag: (min: 12.0, avg: 33.2, max: 57.0) -[2023-11-28 00:25:18,445][86177] Avg episode reward: [(0, '-703.270'), (1, '-537.490')] -[2023-11-28 00:25:18,505][87426] Updated weights for policy 1, policy_version 8030 (0.0008) -[2023-11-28 00:25:18,583][87320] Saving new best policy, reward=-537.490! -[2023-11-28 00:25:18,724][87424] Updated weights for policy 0, policy_version 8036 (0.0007) -[2023-11-28 00:25:19,136][87424] Updated weights for policy 0, policy_version 8046 (0.0012) -[2023-11-28 00:25:19,515][87424] Updated weights for policy 0, policy_version 8056 (0.0011) -[2023-11-28 00:25:20,792][87426] Updated weights for policy 1, policy_version 8040 (0.0010) -[2023-11-28 00:25:21,170][87426] Updated weights for policy 1, policy_version 8050 (0.0010) -[2023-11-28 00:25:21,558][87426] Updated weights for policy 1, policy_version 8060 (0.0011) -[2023-11-28 00:25:21,582][87424] Updated weights for policy 0, policy_version 8066 (0.0012) -[2023-11-28 00:25:21,973][87424] Updated weights for policy 0, policy_version 8076 (0.0012) -[2023-11-28 00:25:22,346][87424] Updated weights for policy 0, policy_version 8086 (0.0012) -[2023-11-28 00:25:22,731][87424] Updated weights for policy 0, policy_version 8096 (0.0012) -[2023-11-28 00:25:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 4136960. Throughput: 0: 2690.0, 1: 2678.9. Samples: 4151664. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 00:25:23,445][86177] Avg episode reward: [(0, '-682.160'), (1, '-543.440')] -[2023-11-28 00:25:23,814][87426] Updated weights for policy 1, policy_version 8070 (0.0011) -[2023-11-28 00:25:24,188][87426] Updated weights for policy 1, policy_version 8080 (0.0007) -[2023-11-28 00:25:24,568][87426] Updated weights for policy 1, policy_version 8090 (0.0010) -[2023-11-28 00:25:25,153][87424] Updated weights for policy 0, policy_version 8106 (0.0012) -[2023-11-28 00:25:25,529][87424] Updated weights for policy 0, policy_version 8116 (0.0012) -[2023-11-28 00:25:25,914][87424] Updated weights for policy 0, policy_version 8126 (0.0012) -[2023-11-28 00:25:26,561][87426] Updated weights for policy 1, policy_version 8100 (0.0012) -[2023-11-28 00:25:26,937][87426] Updated weights for policy 1, policy_version 8110 (0.0012) -[2023-11-28 00:25:27,314][87426] Updated weights for policy 1, policy_version 8120 (0.0011) -[2023-11-28 00:25:27,612][87424] Updated weights for policy 0, policy_version 8136 (0.0009) -[2023-11-28 00:25:28,003][87424] Updated weights for policy 0, policy_version 8146 (0.0009) -[2023-11-28 00:25:28,391][87424] Updated weights for policy 0, policy_version 8156 (0.0007) -[2023-11-28 00:25:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 4161536. Throughput: 0: 2692.8, 1: 2677.2. Samples: 4177120. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 00:25:28,445][86177] Avg episode reward: [(0, '-663.190'), (1, '-543.530')] -[2023-11-28 00:25:29,816][87426] Updated weights for policy 1, policy_version 8130 (0.0011) -[2023-11-28 00:25:30,194][87426] Updated weights for policy 1, policy_version 8140 (0.0011) -[2023-11-28 00:25:30,519][87424] Updated weights for policy 0, policy_version 8166 (0.0009) -[2023-11-28 00:25:30,572][87426] Updated weights for policy 1, policy_version 8150 (0.0012) -[2023-11-28 00:25:30,904][87424] Updated weights for policy 0, policy_version 8176 (0.0008) -[2023-11-28 00:25:30,963][87426] Updated weights for policy 1, policy_version 8160 (0.0012) -[2023-11-28 00:25:31,294][87424] Updated weights for policy 0, policy_version 8186 (0.0012) -[2023-11-28 00:25:32,994][87426] Updated weights for policy 1, policy_version 8170 (0.0011) -[2023-11-28 00:25:33,376][87426] Updated weights for policy 1, policy_version 8180 (0.0012) -[2023-11-28 00:25:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 4186112. Throughput: 0: 2720.8, 1: 2675.4. Samples: 4202320. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 00:25:33,445][86177] Avg episode reward: [(0, '-667.180'), (1, '-547.530')] -[2023-11-28 00:25:33,754][87426] Updated weights for policy 1, policy_version 8190 (0.0012) -[2023-11-28 00:25:33,824][87424] Updated weights for policy 0, policy_version 8196 (0.0011) -[2023-11-28 00:25:34,205][87424] Updated weights for policy 0, policy_version 8206 (0.0012) -[2023-11-28 00:25:34,591][87424] Updated weights for policy 0, policy_version 8216 (0.0012) -[2023-11-28 00:25:35,916][87426] Updated weights for policy 1, policy_version 8200 (0.0012) -[2023-11-28 00:25:36,295][87426] Updated weights for policy 1, policy_version 8210 (0.0012) -[2023-11-28 00:25:36,637][87424] Updated weights for policy 0, policy_version 8226 (0.0011) -[2023-11-28 00:25:36,675][87426] Updated weights for policy 1, policy_version 8220 (0.0012) -[2023-11-28 00:25:37,022][87424] Updated weights for policy 0, policy_version 8236 (0.0008) -[2023-11-28 00:25:37,406][87424] Updated weights for policy 0, policy_version 8246 (0.0008) -[2023-11-28 00:25:37,788][87424] Updated weights for policy 0, policy_version 8256 (0.0008) -[2023-11-28 00:25:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 4218880. Throughput: 0: 2685.7, 1: 2723.6. Samples: 4234672. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 00:25:38,445][86177] Avg episode reward: [(0, '-697.570'), (1, '-554.110')] -[2023-11-28 00:25:38,529][87426] Updated weights for policy 1, policy_version 8230 (0.0009) -[2023-11-28 00:25:38,914][87426] Updated weights for policy 1, policy_version 8240 (0.0008) -[2023-11-28 00:25:39,286][87426] Updated weights for policy 1, policy_version 8250 (0.0012) -[2023-11-28 00:25:39,970][87424] Updated weights for policy 0, policy_version 8266 (0.0009) -[2023-11-28 00:25:40,351][87424] Updated weights for policy 0, policy_version 8276 (0.0008) -[2023-11-28 00:25:40,732][87424] Updated weights for policy 0, policy_version 8286 (0.0008) -[2023-11-28 00:25:41,282][87426] Updated weights for policy 1, policy_version 8260 (0.0011) -[2023-11-28 00:25:41,659][87426] Updated weights for policy 1, policy_version 8270 (0.0011) -[2023-11-28 00:25:42,036][87426] Updated weights for policy 1, policy_version 8280 (0.0012) -[2023-11-28 00:25:43,112][87424] Updated weights for policy 0, policy_version 8296 (0.0011) -[2023-11-28 00:25:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4243456. Throughput: 0: 2693.8, 1: 2734.2. Samples: 4258924. Policy #0 lag: (min: 31.0, avg: 47.0, max: 72.0) -[2023-11-28 00:25:43,445][86177] Avg episode reward: [(0, '-692.800'), (1, '-551.290')] -[2023-11-28 00:25:43,495][87424] Updated weights for policy 0, policy_version 8306 (0.0011) -[2023-11-28 00:25:43,891][87424] Updated weights for policy 0, policy_version 8316 (0.0011) -[2023-11-28 00:25:44,416][87426] Updated weights for policy 1, policy_version 8290 (0.0010) -[2023-11-28 00:25:44,802][87426] Updated weights for policy 1, policy_version 8300 (0.0007) -[2023-11-28 00:25:45,186][87426] Updated weights for policy 1, policy_version 8310 (0.0007) -[2023-11-28 00:25:45,568][87426] Updated weights for policy 1, policy_version 8320 (0.0010) -[2023-11-28 00:25:46,024][87424] Updated weights for policy 0, policy_version 8326 (0.0011) -[2023-11-28 00:25:46,410][87424] Updated weights for policy 0, policy_version 8336 (0.0009) -[2023-11-28 00:25:46,793][87424] Updated weights for policy 0, policy_version 8346 (0.0008) -[2023-11-28 00:25:48,076][87426] Updated weights for policy 1, policy_version 8330 (0.0008) -[2023-11-28 00:25:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 4268032. Throughput: 0: 2714.8, 1: 2727.5. Samples: 4283720. Policy #0 lag: (min: 31.0, avg: 47.0, max: 72.0) -[2023-11-28 00:25:48,446][86177] Avg episode reward: [(0, '-694.700'), (1, '-544.210')] -[2023-11-28 00:25:48,462][87426] Updated weights for policy 1, policy_version 8340 (0.0009) -[2023-11-28 00:25:48,506][87424] Updated weights for policy 0, policy_version 8356 (0.0009) -[2023-11-28 00:25:48,837][87426] Updated weights for policy 1, policy_version 8350 (0.0008) -[2023-11-28 00:25:48,892][87424] Updated weights for policy 0, policy_version 8366 (0.0011) -[2023-11-28 00:25:49,263][87424] Updated weights for policy 0, policy_version 8376 (0.0012) -[2023-11-28 00:25:51,083][87426] Updated weights for policy 1, policy_version 8360 (0.0011) -[2023-11-28 00:25:51,464][87426] Updated weights for policy 1, policy_version 8370 (0.0012) -[2023-11-28 00:25:51,801][87424] Updated weights for policy 0, policy_version 8386 (0.0012) -[2023-11-28 00:25:51,840][87426] Updated weights for policy 1, policy_version 8380 (0.0012) -[2023-11-28 00:25:52,189][87424] Updated weights for policy 0, policy_version 8396 (0.0009) -[2023-11-28 00:25:52,560][87424] Updated weights for policy 0, policy_version 8406 (0.0012) -[2023-11-28 00:25:52,944][87424] Updated weights for policy 0, policy_version 8416 (0.0012) -[2023-11-28 00:25:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4300800. Throughput: 0: 2726.3, 1: 2691.1. Samples: 4316244. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 00:25:53,445][86177] Avg episode reward: [(0, '-725.930'), (1, '-541.490')] -[2023-11-28 00:25:53,895][87426] Updated weights for policy 1, policy_version 8390 (0.0012) -[2023-11-28 00:25:54,275][87426] Updated weights for policy 1, policy_version 8400 (0.0009) -[2023-11-28 00:25:54,666][87426] Updated weights for policy 1, policy_version 8410 (0.0011) -[2023-11-28 00:25:55,098][87424] Updated weights for policy 0, policy_version 8426 (0.0008) -[2023-11-28 00:25:55,483][87424] Updated weights for policy 0, policy_version 8436 (0.0008) -[2023-11-28 00:25:55,867][87424] Updated weights for policy 0, policy_version 8446 (0.0008) -[2023-11-28 00:25:56,544][87426] Updated weights for policy 1, policy_version 8420 (0.0012) -[2023-11-28 00:25:56,925][87426] Updated weights for policy 1, policy_version 8430 (0.0012) -[2023-11-28 00:25:57,313][87426] Updated weights for policy 1, policy_version 8440 (0.0012) -[2023-11-28 00:25:57,574][87424] Updated weights for policy 0, policy_version 8456 (0.0010) -[2023-11-28 00:25:57,963][87424] Updated weights for policy 0, policy_version 8466 (0.0012) -[2023-11-28 00:25:58,341][87424] Updated weights for policy 0, policy_version 8476 (0.0012) -[2023-11-28 00:25:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 4325376. Throughput: 0: 2739.5, 1: 2706.6. Samples: 4341168. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 00:25:58,445][86177] Avg episode reward: [(0, '-716.560'), (1, '-549.890')] -[2023-11-28 00:25:59,234][87426] Updated weights for policy 1, policy_version 8450 (0.0011) -[2023-11-28 00:25:59,600][87426] Updated weights for policy 1, policy_version 8460 (0.0011) -[2023-11-28 00:25:59,982][87426] Updated weights for policy 1, policy_version 8470 (0.0011) -[2023-11-28 00:26:00,357][87426] Updated weights for policy 1, policy_version 8480 (0.0011) -[2023-11-28 00:26:00,756][87424] Updated weights for policy 0, policy_version 8486 (0.0012) -[2023-11-28 00:26:01,153][87424] Updated weights for policy 0, policy_version 8496 (0.0012) -[2023-11-28 00:26:01,540][87424] Updated weights for policy 0, policy_version 8506 (0.0012) -[2023-11-28 00:26:02,797][87426] Updated weights for policy 1, policy_version 8490 (0.0012) -[2023-11-28 00:26:03,182][87426] Updated weights for policy 1, policy_version 8500 (0.0012) -[2023-11-28 00:26:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 4349952. Throughput: 0: 2746.3, 1: 2718.1. Samples: 4366328. Policy #0 lag: (min: 31.0, avg: 49.3, max: 77.0) -[2023-11-28 00:26:03,445][86177] Avg episode reward: [(0, '-697.880'), (1, '-543.080')] -[2023-11-28 00:26:03,543][87426] Updated weights for policy 1, policy_version 8510 (0.0011) -[2023-11-28 00:26:03,553][87424] Updated weights for policy 0, policy_version 8516 (0.0011) -[2023-11-28 00:26:03,934][87424] Updated weights for policy 0, policy_version 8526 (0.0012) -[2023-11-28 00:26:04,313][87424] Updated weights for policy 0, policy_version 8536 (0.0011) -[2023-11-28 00:26:05,456][87426] Updated weights for policy 1, policy_version 8520 (0.0009) -[2023-11-28 00:26:05,835][87426] Updated weights for policy 1, policy_version 8530 (0.0007) -[2023-11-28 00:26:06,218][87426] Updated weights for policy 1, policy_version 8540 (0.0007) -[2023-11-28 00:26:06,709][87424] Updated weights for policy 0, policy_version 8546 (0.0012) -[2023-11-28 00:26:07,092][87424] Updated weights for policy 0, policy_version 8556 (0.0012) -[2023-11-28 00:26:07,477][87424] Updated weights for policy 0, policy_version 8566 (0.0010) -[2023-11-28 00:26:07,859][87424] Updated weights for policy 0, policy_version 8576 (0.0011) -[2023-11-28 00:26:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4382720. Throughput: 0: 2760.0, 1: 2746.8. Samples: 4399472. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 00:26:08,445][86177] Avg episode reward: [(0, '-738.360'), (1, '-552.860')] -[2023-11-28 00:26:08,621][87426] Updated weights for policy 1, policy_version 8550 (0.0009) -[2023-11-28 00:26:09,005][87426] Updated weights for policy 1, policy_version 8560 (0.0010) -[2023-11-28 00:26:09,388][87426] Updated weights for policy 1, policy_version 8570 (0.0012) -[2023-11-28 00:26:09,941][87424] Updated weights for policy 0, policy_version 8586 (0.0010) -[2023-11-28 00:26:10,332][87424] Updated weights for policy 0, policy_version 8596 (0.0011) -[2023-11-28 00:26:10,704][87424] Updated weights for policy 0, policy_version 8606 (0.0012) -[2023-11-28 00:26:11,936][87426] Updated weights for policy 1, policy_version 8580 (0.0012) -[2023-11-28 00:26:12,313][87426] Updated weights for policy 1, policy_version 8590 (0.0011) -[2023-11-28 00:26:12,702][87426] Updated weights for policy 1, policy_version 8600 (0.0009) -[2023-11-28 00:26:12,987][87424] Updated weights for policy 0, policy_version 8616 (0.0012) -[2023-11-28 00:26:13,375][87424] Updated weights for policy 0, policy_version 8626 (0.0012) -[2023-11-28 00:26:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4407296. Throughput: 0: 2760.4, 1: 2705.4. Samples: 4423084. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 00:26:13,445][86177] Avg episode reward: [(0, '-740.090'), (1, '-560.580')] -[2023-11-28 00:26:13,760][87424] Updated weights for policy 0, policy_version 8636 (0.0012) -[2023-11-28 00:26:14,969][87426] Updated weights for policy 1, policy_version 8610 (0.0011) -[2023-11-28 00:26:15,365][87426] Updated weights for policy 1, policy_version 8620 (0.0012) -[2023-11-28 00:26:15,740][87426] Updated weights for policy 1, policy_version 8630 (0.0012) -[2023-11-28 00:26:15,810][87424] Updated weights for policy 0, policy_version 8646 (0.0012) -[2023-11-28 00:26:16,125][87426] Updated weights for policy 1, policy_version 8640 (0.0012) -[2023-11-28 00:26:16,206][87424] Updated weights for policy 0, policy_version 8656 (0.0012) -[2023-11-28 00:26:16,579][87424] Updated weights for policy 0, policy_version 8666 (0.0009) -[2023-11-28 00:26:18,103][87426] Updated weights for policy 1, policy_version 8650 (0.0012) -[2023-11-28 00:26:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 4431872. Throughput: 0: 2727.4, 1: 2727.7. Samples: 4447800. Policy #0 lag: (min: 15.0, avg: 33.1, max: 53.0) -[2023-11-28 00:26:18,445][86177] Avg episode reward: [(0, '-698.230'), (1, '-556.930')] -[2023-11-28 00:26:18,452][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000008672_2220032.pth... -[2023-11-28 00:26:18,485][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000006144_1572864.pth -[2023-11-28 00:26:18,486][87426] Updated weights for policy 1, policy_version 8660 (0.0011) -[2023-11-28 00:26:18,814][87424] Updated weights for policy 0, policy_version 8676 (0.0009) -[2023-11-28 00:26:18,867][87426] Updated weights for policy 1, policy_version 8670 (0.0011) -[2023-11-28 00:26:18,934][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000008672_2220032.pth... -[2023-11-28 00:26:18,979][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000006144_1572864.pth -[2023-11-28 00:26:19,194][87424] Updated weights for policy 0, policy_version 8686 (0.0009) -[2023-11-28 00:26:19,588][87424] Updated weights for policy 0, policy_version 8696 (0.0008) -[2023-11-28 00:26:21,247][87426] Updated weights for policy 1, policy_version 8680 (0.0011) -[2023-11-28 00:26:21,628][87426] Updated weights for policy 1, policy_version 8690 (0.0010) -[2023-11-28 00:26:21,789][87424] Updated weights for policy 0, policy_version 8706 (0.0012) -[2023-11-28 00:26:22,001][87426] Updated weights for policy 1, policy_version 8700 (0.0009) -[2023-11-28 00:26:22,174][87424] Updated weights for policy 0, policy_version 8716 (0.0008) -[2023-11-28 00:26:22,551][87424] Updated weights for policy 0, policy_version 8726 (0.0011) -[2023-11-28 00:26:22,948][87424] Updated weights for policy 0, policy_version 8736 (0.0012) -[2023-11-28 00:26:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4464640. Throughput: 0: 2747.9, 1: 2708.0. Samples: 4480188. Policy #0 lag: (min: 15.0, avg: 33.1, max: 53.0) -[2023-11-28 00:26:23,445][86177] Avg episode reward: [(0, '-682.830'), (1, '-556.580')] -[2023-11-28 00:26:24,254][87426] Updated weights for policy 1, policy_version 8710 (0.0011) -[2023-11-28 00:26:24,630][87426] Updated weights for policy 1, policy_version 8720 (0.0008) -[2023-11-28 00:26:25,010][87426] Updated weights for policy 1, policy_version 8730 (0.0008) -[2023-11-28 00:26:25,144][87424] Updated weights for policy 0, policy_version 8746 (0.0012) -[2023-11-28 00:26:25,518][87424] Updated weights for policy 0, policy_version 8756 (0.0012) -[2023-11-28 00:26:25,891][87424] Updated weights for policy 0, policy_version 8766 (0.0010) -[2023-11-28 00:26:26,648][87426] Updated weights for policy 1, policy_version 8740 (0.0008) -[2023-11-28 00:26:27,034][87426] Updated weights for policy 1, policy_version 8750 (0.0007) -[2023-11-28 00:26:27,417][87426] Updated weights for policy 1, policy_version 8760 (0.0008) -[2023-11-28 00:26:28,062][87424] Updated weights for policy 0, policy_version 8776 (0.0007) -[2023-11-28 00:26:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4489216. Throughput: 0: 2731.6, 1: 2737.3. Samples: 4505028. Policy #0 lag: (min: 28.0, avg: 43.4, max: 70.0) -[2023-11-28 00:26:28,446][86177] Avg episode reward: [(0, '-669.850'), (1, '-551.250')] -[2023-11-28 00:26:28,454][87424] Updated weights for policy 0, policy_version 8786 (0.0007) -[2023-11-28 00:26:28,839][87424] Updated weights for policy 0, policy_version 8796 (0.0007) -[2023-11-28 00:26:29,624][87426] Updated weights for policy 1, policy_version 8770 (0.0008) -[2023-11-28 00:26:29,999][87426] Updated weights for policy 1, policy_version 8780 (0.0009) -[2023-11-28 00:26:30,376][87426] Updated weights for policy 1, policy_version 8790 (0.0011) -[2023-11-28 00:26:30,596][87424] Updated weights for policy 0, policy_version 8806 (0.0011) -[2023-11-28 00:26:30,755][87426] Updated weights for policy 1, policy_version 8800 (0.0009) -[2023-11-28 00:26:30,970][87424] Updated weights for policy 0, policy_version 8816 (0.0010) -[2023-11-28 00:26:31,364][87424] Updated weights for policy 0, policy_version 8826 (0.0009) -[2023-11-28 00:26:33,281][87426] Updated weights for policy 1, policy_version 8810 (0.0011) -[2023-11-28 00:26:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 4513792. Throughput: 0: 2725.3, 1: 2730.1. Samples: 4529212. Policy #0 lag: (min: 28.0, avg: 43.4, max: 70.0) -[2023-11-28 00:26:33,445][86177] Avg episode reward: [(0, '-614.440'), (1, '-549.160')] -[2023-11-28 00:26:33,454][87281] Saving new best policy, reward=-614.440! -[2023-11-28 00:26:33,666][87426] Updated weights for policy 1, policy_version 8820 (0.0012) -[2023-11-28 00:26:33,775][87424] Updated weights for policy 0, policy_version 8836 (0.0012) -[2023-11-28 00:26:34,042][87426] Updated weights for policy 1, policy_version 8830 (0.0011) -[2023-11-28 00:26:34,156][87424] Updated weights for policy 0, policy_version 8846 (0.0012) -[2023-11-28 00:26:34,531][87424] Updated weights for policy 0, policy_version 8856 (0.0012) -[2023-11-28 00:26:35,968][87426] Updated weights for policy 1, policy_version 8840 (0.0011) -[2023-11-28 00:26:36,348][87426] Updated weights for policy 1, policy_version 8850 (0.0012) -[2023-11-28 00:26:36,405][87424] Updated weights for policy 0, policy_version 8866 (0.0011) -[2023-11-28 00:26:36,733][87426] Updated weights for policy 1, policy_version 8860 (0.0012) -[2023-11-28 00:26:36,789][87424] Updated weights for policy 0, policy_version 8876 (0.0010) -[2023-11-28 00:26:37,177][87424] Updated weights for policy 0, policy_version 8886 (0.0011) -[2023-11-28 00:26:37,548][87424] Updated weights for policy 0, policy_version 8896 (0.0012) -[2023-11-28 00:26:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4546560. Throughput: 0: 2751.3, 1: 2735.0. Samples: 4563128. Policy #0 lag: (min: 31.0, avg: 31.4, max: 39.0) -[2023-11-28 00:26:38,445][86177] Avg episode reward: [(0, '-597.010'), (1, '-542.370')] -[2023-11-28 00:26:38,446][87281] Saving new best policy, reward=-597.010! -[2023-11-28 00:26:38,969][87426] Updated weights for policy 1, policy_version 8870 (0.0011) -[2023-11-28 00:26:39,347][87426] Updated weights for policy 1, policy_version 8880 (0.0012) -[2023-11-28 00:26:39,480][87424] Updated weights for policy 0, policy_version 8906 (0.0010) -[2023-11-28 00:26:39,731][87426] Updated weights for policy 1, policy_version 8890 (0.0011) -[2023-11-28 00:26:39,852][87424] Updated weights for policy 0, policy_version 8916 (0.0011) -[2023-11-28 00:26:40,235][87424] Updated weights for policy 0, policy_version 8926 (0.0011) -[2023-11-28 00:26:41,787][87426] Updated weights for policy 1, policy_version 8900 (0.0011) -[2023-11-28 00:26:42,169][87426] Updated weights for policy 1, policy_version 8910 (0.0012) -[2023-11-28 00:26:42,559][87426] Updated weights for policy 1, policy_version 8920 (0.0012) -[2023-11-28 00:26:42,597][87424] Updated weights for policy 0, policy_version 8936 (0.0011) -[2023-11-28 00:26:42,974][87424] Updated weights for policy 0, policy_version 8946 (0.0010) -[2023-11-28 00:26:43,359][87424] Updated weights for policy 0, policy_version 8956 (0.0009) -[2023-11-28 00:26:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 4571136. Throughput: 0: 2747.5, 1: 2736.1. Samples: 4587928. Policy #0 lag: (min: 31.0, avg: 31.4, max: 39.0) -[2023-11-28 00:26:43,445][86177] Avg episode reward: [(0, '-592.750'), (1, '-561.390')] -[2023-11-28 00:26:43,517][87281] Saving new best policy, reward=-592.750! -[2023-11-28 00:26:44,482][87426] Updated weights for policy 1, policy_version 8930 (0.0012) -[2023-11-28 00:26:44,866][87426] Updated weights for policy 1, policy_version 8940 (0.0012) -[2023-11-28 00:26:45,257][87426] Updated weights for policy 1, policy_version 8950 (0.0011) -[2023-11-28 00:26:45,327][87424] Updated weights for policy 0, policy_version 8966 (0.0024) -[2023-11-28 00:26:45,634][87426] Updated weights for policy 1, policy_version 8960 (0.0009) -[2023-11-28 00:26:45,700][87424] Updated weights for policy 0, policy_version 8976 (0.0008) -[2023-11-28 00:26:46,083][87424] Updated weights for policy 0, policy_version 8986 (0.0009) -[2023-11-28 00:26:48,061][87426] Updated weights for policy 1, policy_version 8970 (0.0010) -[2023-11-28 00:26:48,399][87424] Updated weights for policy 0, policy_version 8996 (0.0008) -[2023-11-28 00:26:48,435][87426] Updated weights for policy 1, policy_version 8980 (0.0011) -[2023-11-28 00:26:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 4595712. Throughput: 0: 2750.4, 1: 2734.5. Samples: 4613148. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 00:26:48,445][86177] Avg episode reward: [(0, '-626.570'), (1, '-555.830')] -[2023-11-28 00:26:48,785][87424] Updated weights for policy 0, policy_version 9006 (0.0008) -[2023-11-28 00:26:48,816][87426] Updated weights for policy 1, policy_version 8990 (0.0012) -[2023-11-28 00:26:49,159][87424] Updated weights for policy 0, policy_version 9016 (0.0011) -[2023-11-28 00:26:50,767][87426] Updated weights for policy 1, policy_version 9000 (0.0012) -[2023-11-28 00:26:51,150][87426] Updated weights for policy 1, policy_version 9010 (0.0012) -[2023-11-28 00:26:51,181][87424] Updated weights for policy 0, policy_version 9026 (0.0012) -[2023-11-28 00:26:51,530][87426] Updated weights for policy 1, policy_version 9020 (0.0012) -[2023-11-28 00:26:51,563][87424] Updated weights for policy 0, policy_version 9036 (0.0012) -[2023-11-28 00:26:51,948][87424] Updated weights for policy 0, policy_version 9046 (0.0011) -[2023-11-28 00:26:52,333][87424] Updated weights for policy 0, policy_version 9056 (0.0011) -[2023-11-28 00:26:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4628480. Throughput: 0: 2757.1, 1: 2737.3. Samples: 4646720. Policy #0 lag: (min: 31.0, avg: 49.7, max: 70.0) -[2023-11-28 00:26:53,445][86177] Avg episode reward: [(0, '-653.900'), (1, '-555.660')] -[2023-11-28 00:26:53,748][87426] Updated weights for policy 1, policy_version 9030 (0.0012) -[2023-11-28 00:26:54,123][87426] Updated weights for policy 1, policy_version 9040 (0.0011) -[2023-11-28 00:26:54,288][87424] Updated weights for policy 0, policy_version 9066 (0.0008) -[2023-11-28 00:26:54,511][87426] Updated weights for policy 1, policy_version 9050 (0.0011) -[2023-11-28 00:26:54,670][87424] Updated weights for policy 0, policy_version 9076 (0.0010) -[2023-11-28 00:26:55,054][87424] Updated weights for policy 0, policy_version 9086 (0.0012) -[2023-11-28 00:26:56,946][87426] Updated weights for policy 1, policy_version 9060 (0.0012) -[2023-11-28 00:26:56,983][87424] Updated weights for policy 0, policy_version 9096 (0.0011) -[2023-11-28 00:26:57,330][87426] Updated weights for policy 1, policy_version 9070 (0.0007) -[2023-11-28 00:26:57,375][87424] Updated weights for policy 0, policy_version 9106 (0.0012) -[2023-11-28 00:26:57,710][87426] Updated weights for policy 1, policy_version 9080 (0.0007) -[2023-11-28 00:26:57,757][87424] Updated weights for policy 0, policy_version 9116 (0.0012) -[2023-11-28 00:26:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 4661248. Throughput: 0: 2759.7, 1: 2755.7. Samples: 4671280. Policy #0 lag: (min: 31.0, avg: 49.7, max: 70.0) -[2023-11-28 00:26:58,445][86177] Avg episode reward: [(0, '-658.400'), (1, '-560.440')] -[2023-11-28 00:26:59,443][87426] Updated weights for policy 1, policy_version 9090 (0.0011) -[2023-11-28 00:26:59,814][87426] Updated weights for policy 1, policy_version 9100 (0.0011) -[2023-11-28 00:26:59,871][87424] Updated weights for policy 0, policy_version 9126 (0.0011) -[2023-11-28 00:27:00,197][87426] Updated weights for policy 1, policy_version 9110 (0.0007) -[2023-11-28 00:27:00,252][87424] Updated weights for policy 0, policy_version 9136 (0.0012) -[2023-11-28 00:27:00,608][87426] Updated weights for policy 1, policy_version 9120 (0.0008) -[2023-11-28 00:27:00,637][87424] Updated weights for policy 0, policy_version 9146 (0.0012) -[2023-11-28 00:27:02,910][87426] Updated weights for policy 1, policy_version 9130 (0.0011) -[2023-11-28 00:27:03,121][87424] Updated weights for policy 0, policy_version 9156 (0.0011) -[2023-11-28 00:27:03,289][87426] Updated weights for policy 1, policy_version 9140 (0.0011) -[2023-11-28 00:27:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 4677632. Throughput: 0: 2783.0, 1: 2753.4. Samples: 4696940. Policy #0 lag: (min: 31.0, avg: 34.1, max: 53.0) -[2023-11-28 00:27:03,445][86177] Avg episode reward: [(0, '-669.950'), (1, '-539.400')] -[2023-11-28 00:27:03,518][87424] Updated weights for policy 0, policy_version 9166 (0.0011) -[2023-11-28 00:27:03,671][87426] Updated weights for policy 1, policy_version 9150 (0.0010) -[2023-11-28 00:27:03,886][87424] Updated weights for policy 0, policy_version 9176 (0.0011) -[2023-11-28 00:27:05,513][87426] Updated weights for policy 1, policy_version 9160 (0.0012) -[2023-11-28 00:27:05,888][87426] Updated weights for policy 1, policy_version 9170 (0.0011) -[2023-11-28 00:27:05,968][87424] Updated weights for policy 0, policy_version 9186 (0.0012) -[2023-11-28 00:27:06,274][87426] Updated weights for policy 1, policy_version 9180 (0.0008) -[2023-11-28 00:27:06,349][87424] Updated weights for policy 0, policy_version 9196 (0.0010) -[2023-11-28 00:27:06,730][87424] Updated weights for policy 0, policy_version 9206 (0.0008) -[2023-11-28 00:27:07,112][87424] Updated weights for policy 0, policy_version 9216 (0.0011) -[2023-11-28 00:27:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4710400. Throughput: 0: 2793.0, 1: 2757.0. Samples: 4729936. Policy #0 lag: (min: 31.0, avg: 34.1, max: 53.0) -[2023-11-28 00:27:08,445][86177] Avg episode reward: [(0, '-648.940'), (1, '-541.680')] -[2023-11-28 00:27:08,617][87426] Updated weights for policy 1, policy_version 9190 (0.0008) -[2023-11-28 00:27:09,002][87426] Updated weights for policy 1, policy_version 9200 (0.0011) -[2023-11-28 00:27:09,083][87424] Updated weights for policy 0, policy_version 9226 (0.0011) -[2023-11-28 00:27:09,380][87426] Updated weights for policy 1, policy_version 9210 (0.0011) -[2023-11-28 00:27:09,477][87424] Updated weights for policy 0, policy_version 9236 (0.0010) -[2023-11-28 00:27:09,857][87424] Updated weights for policy 0, policy_version 9246 (0.0008) -[2023-11-28 00:27:11,525][87426] Updated weights for policy 1, policy_version 9220 (0.0010) -[2023-11-28 00:27:11,899][87426] Updated weights for policy 1, policy_version 9230 (0.0010) -[2023-11-28 00:27:12,261][87424] Updated weights for policy 0, policy_version 9256 (0.0010) -[2023-11-28 00:27:12,280][87426] Updated weights for policy 1, policy_version 9240 (0.0015) -[2023-11-28 00:27:12,639][87424] Updated weights for policy 0, policy_version 9266 (0.0010) -[2023-11-28 00:27:13,023][87424] Updated weights for policy 0, policy_version 9276 (0.0010) -[2023-11-28 00:27:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 4743168. Throughput: 0: 2797.3, 1: 2722.3. Samples: 4753412. Policy #0 lag: (min: 31.0, avg: 49.5, max: 75.0) -[2023-11-28 00:27:13,445][86177] Avg episode reward: [(0, '-608.600'), (1, '-547.220')] -[2023-11-28 00:27:14,773][87426] Updated weights for policy 1, policy_version 9250 (0.0007) -[2023-11-28 00:27:14,858][87424] Updated weights for policy 0, policy_version 9286 (0.0011) -[2023-11-28 00:27:15,157][87426] Updated weights for policy 1, policy_version 9260 (0.0009) -[2023-11-28 00:27:15,243][87424] Updated weights for policy 0, policy_version 9296 (0.0012) -[2023-11-28 00:27:15,534][87426] Updated weights for policy 1, policy_version 9270 (0.0008) -[2023-11-28 00:27:15,626][87424] Updated weights for policy 0, policy_version 9306 (0.0011) -[2023-11-28 00:27:15,913][87426] Updated weights for policy 1, policy_version 9280 (0.0008) -[2023-11-28 00:27:17,282][87424] Updated weights for policy 0, policy_version 9316 (0.0011) -[2023-11-28 00:27:17,675][87424] Updated weights for policy 0, policy_version 9326 (0.0011) -[2023-11-28 00:27:17,825][87426] Updated weights for policy 1, policy_version 9290 (0.0012) -[2023-11-28 00:27:18,053][87424] Updated weights for policy 0, policy_version 9336 (0.0009) -[2023-11-28 00:27:18,210][87426] Updated weights for policy 1, policy_version 9300 (0.0009) -[2023-11-28 00:27:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 4767744. Throughput: 0: 2804.7, 1: 2733.1. Samples: 4778412. Policy #0 lag: (min: 31.0, avg: 49.5, max: 75.0) -[2023-11-28 00:27:18,445][86177] Avg episode reward: [(0, '-605.770'), (1, '-529.710')] -[2023-11-28 00:27:18,585][87426] Updated weights for policy 1, policy_version 9310 (0.0012) -[2023-11-28 00:27:18,655][87320] Saving new best policy, reward=-529.710! -[2023-11-28 00:27:20,282][87426] Updated weights for policy 1, policy_version 9320 (0.0011) -[2023-11-28 00:27:20,410][87424] Updated weights for policy 0, policy_version 9346 (0.0010) -[2023-11-28 00:27:20,668][87426] Updated weights for policy 1, policy_version 9330 (0.0010) -[2023-11-28 00:27:20,803][87424] Updated weights for policy 0, policy_version 9356 (0.0012) -[2023-11-28 00:27:21,039][87426] Updated weights for policy 1, policy_version 9340 (0.0010) -[2023-11-28 00:27:21,177][87424] Updated weights for policy 0, policy_version 9366 (0.0010) -[2023-11-28 00:27:21,565][87424] Updated weights for policy 0, policy_version 9376 (0.0012) -[2023-11-28 00:27:23,258][87426] Updated weights for policy 1, policy_version 9350 (0.0009) -[2023-11-28 00:27:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4792320. Throughput: 0: 2776.0, 1: 2742.8. Samples: 4811476. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 00:27:23,445][86177] Avg episode reward: [(0, '-604.310'), (1, '-570.930')] -[2023-11-28 00:27:23,631][87426] Updated weights for policy 1, policy_version 9360 (0.0010) -[2023-11-28 00:27:24,011][87426] Updated weights for policy 1, policy_version 9370 (0.0010) -[2023-11-28 00:27:24,174][87424] Updated weights for policy 0, policy_version 9386 (0.0010) -[2023-11-28 00:27:24,569][87424] Updated weights for policy 0, policy_version 9396 (0.0012) -[2023-11-28 00:27:24,941][87424] Updated weights for policy 0, policy_version 9406 (0.0009) -[2023-11-28 00:27:26,579][87426] Updated weights for policy 1, policy_version 9380 (0.0007) -[2023-11-28 00:27:26,964][87426] Updated weights for policy 1, policy_version 9390 (0.0007) -[2023-11-28 00:27:27,208][87424] Updated weights for policy 0, policy_version 9416 (0.0008) -[2023-11-28 00:27:27,351][87426] Updated weights for policy 1, policy_version 9400 (0.0010) -[2023-11-28 00:27:27,591][87424] Updated weights for policy 0, policy_version 9426 (0.0007) -[2023-11-28 00:27:27,977][87424] Updated weights for policy 0, policy_version 9436 (0.0008) -[2023-11-28 00:27:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 4825088. Throughput: 0: 2760.4, 1: 2755.6. Samples: 4836152. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 00:27:28,445][86177] Avg episode reward: [(0, '-595.200'), (1, '-585.910')] -[2023-11-28 00:27:29,232][87426] Updated weights for policy 1, policy_version 9410 (0.0011) -[2023-11-28 00:27:29,602][87426] Updated weights for policy 1, policy_version 9420 (0.0012) -[2023-11-28 00:27:29,976][87426] Updated weights for policy 1, policy_version 9430 (0.0010) -[2023-11-28 00:27:30,280][87424] Updated weights for policy 0, policy_version 9446 (0.0010) -[2023-11-28 00:27:30,357][87426] Updated weights for policy 1, policy_version 9440 (0.0008) -[2023-11-28 00:27:30,656][87424] Updated weights for policy 0, policy_version 9456 (0.0012) -[2023-11-28 00:27:31,038][87424] Updated weights for policy 0, policy_version 9466 (0.0012) -[2023-11-28 00:27:32,584][87426] Updated weights for policy 1, policy_version 9450 (0.0012) -[2023-11-28 00:27:32,958][87426] Updated weights for policy 1, policy_version 9460 (0.0011) -[2023-11-28 00:27:32,958][87424] Updated weights for policy 0, policy_version 9476 (0.0011) -[2023-11-28 00:27:33,345][87424] Updated weights for policy 0, policy_version 9486 (0.0012) -[2023-11-28 00:27:33,349][87426] Updated weights for policy 1, policy_version 9470 (0.0008) -[2023-11-28 00:27:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 4849664. Throughput: 0: 2728.8, 1: 2763.7. Samples: 4860312. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 00:27:33,445][86177] Avg episode reward: [(0, '-589.570'), (1, '-581.060')] -[2023-11-28 00:27:33,727][87424] Updated weights for policy 0, policy_version 9496 (0.0012) -[2023-11-28 00:27:34,019][87281] Saving new best policy, reward=-589.570! -[2023-11-28 00:27:35,093][87426] Updated weights for policy 1, policy_version 9480 (0.0009) -[2023-11-28 00:27:35,476][87426] Updated weights for policy 1, policy_version 9490 (0.0010) -[2023-11-28 00:27:35,862][87426] Updated weights for policy 1, policy_version 9500 (0.0007) -[2023-11-28 00:27:36,336][87424] Updated weights for policy 0, policy_version 9506 (0.0011) -[2023-11-28 00:27:36,715][87424] Updated weights for policy 0, policy_version 9516 (0.0008) -[2023-11-28 00:27:37,098][87424] Updated weights for policy 0, policy_version 9526 (0.0009) -[2023-11-28 00:27:37,483][87424] Updated weights for policy 0, policy_version 9536 (0.0008) -[2023-11-28 00:27:38,031][87426] Updated weights for policy 1, policy_version 9510 (0.0009) -[2023-11-28 00:27:38,413][87426] Updated weights for policy 1, policy_version 9520 (0.0010) -[2023-11-28 00:27:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4874240. Throughput: 0: 2710.0, 1: 2768.7. Samples: 4893264. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 00:27:38,445][86177] Avg episode reward: [(0, '-589.040'), (1, '-597.060')] -[2023-11-28 00:27:38,445][87281] Saving new best policy, reward=-589.040! -[2023-11-28 00:27:38,795][87426] Updated weights for policy 1, policy_version 9530 (0.0008) -[2023-11-28 00:27:39,574][87424] Updated weights for policy 0, policy_version 9546 (0.0011) -[2023-11-28 00:27:39,966][87424] Updated weights for policy 0, policy_version 9556 (0.0011) -[2023-11-28 00:27:40,349][87424] Updated weights for policy 0, policy_version 9566 (0.0008) -[2023-11-28 00:27:41,107][87426] Updated weights for policy 1, policy_version 9540 (0.0009) -[2023-11-28 00:27:41,479][87426] Updated weights for policy 1, policy_version 9550 (0.0011) -[2023-11-28 00:27:41,866][87426] Updated weights for policy 1, policy_version 9560 (0.0011) -[2023-11-28 00:27:42,795][87424] Updated weights for policy 0, policy_version 9576 (0.0008) -[2023-11-28 00:27:43,179][87424] Updated weights for policy 0, policy_version 9586 (0.0009) -[2023-11-28 00:27:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 4898816. Throughput: 0: 2703.7, 1: 2756.0. Samples: 4916968. Policy #0 lag: (min: 18.0, avg: 44.1, max: 50.0) -[2023-11-28 00:27:43,445][86177] Avg episode reward: [(0, '-602.700'), (1, '-556.710')] -[2023-11-28 00:27:43,566][87424] Updated weights for policy 0, policy_version 9596 (0.0010) -[2023-11-28 00:27:44,226][87426] Updated weights for policy 1, policy_version 9570 (0.0009) -[2023-11-28 00:27:44,611][87426] Updated weights for policy 1, policy_version 9580 (0.0008) -[2023-11-28 00:27:44,990][87426] Updated weights for policy 1, policy_version 9590 (0.0007) -[2023-11-28 00:27:45,374][87426] Updated weights for policy 1, policy_version 9600 (0.0008) -[2023-11-28 00:27:45,814][87424] Updated weights for policy 0, policy_version 9606 (0.0011) -[2023-11-28 00:27:46,192][87424] Updated weights for policy 0, policy_version 9616 (0.0012) -[2023-11-28 00:27:46,576][87424] Updated weights for policy 0, policy_version 9626 (0.0012) -[2023-11-28 00:27:47,604][87426] Updated weights for policy 1, policy_version 9610 (0.0010) -[2023-11-28 00:27:47,993][87426] Updated weights for policy 1, policy_version 9620 (0.0009) -[2023-11-28 00:27:48,222][87424] Updated weights for policy 0, policy_version 9636 (0.0012) -[2023-11-28 00:27:48,360][87426] Updated weights for policy 1, policy_version 9630 (0.0009) -[2023-11-28 00:27:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 4931584. Throughput: 0: 2688.0, 1: 2742.1. Samples: 4941296. Policy #0 lag: (min: 18.0, avg: 44.1, max: 50.0) -[2023-11-28 00:27:48,445][86177] Avg episode reward: [(0, '-602.410'), (1, '-537.730')] -[2023-11-28 00:27:48,600][87424] Updated weights for policy 0, policy_version 9646 (0.0010) -[2023-11-28 00:27:48,990][87424] Updated weights for policy 0, policy_version 9656 (0.0008) -[2023-11-28 00:27:50,314][87426] Updated weights for policy 1, policy_version 9640 (0.0011) -[2023-11-28 00:27:50,697][87426] Updated weights for policy 1, policy_version 9650 (0.0012) -[2023-11-28 00:27:51,076][87426] Updated weights for policy 1, policy_version 9660 (0.0012) -[2023-11-28 00:27:51,502][87424] Updated weights for policy 0, policy_version 9666 (0.0009) -[2023-11-28 00:27:51,877][87424] Updated weights for policy 0, policy_version 9676 (0.0009) -[2023-11-28 00:27:52,260][87424] Updated weights for policy 0, policy_version 9686 (0.0010) -[2023-11-28 00:27:52,642][87424] Updated weights for policy 0, policy_version 9696 (0.0012) -[2023-11-28 00:27:53,426][87426] Updated weights for policy 1, policy_version 9670 (0.0012) -[2023-11-28 00:27:53,448][86177] Fps is (10 sec: 5732.3, 60 sec: 5461.0, 300 sec: 5415.0). Total num frames: 4956160. Throughput: 0: 2671.7, 1: 2750.0. Samples: 4973932. Policy #0 lag: (min: 34.0, avg: 56.3, max: 73.0) -[2023-11-28 00:27:53,449][86177] Avg episode reward: [(0, '-602.310'), (1, '-535.440')] -[2023-11-28 00:27:53,809][87426] Updated weights for policy 1, policy_version 9680 (0.0012) -[2023-11-28 00:27:54,202][87426] Updated weights for policy 1, policy_version 9690 (0.0012) -[2023-11-28 00:27:54,758][87424] Updated weights for policy 0, policy_version 9706 (0.0011) -[2023-11-28 00:27:55,137][87424] Updated weights for policy 0, policy_version 9716 (0.0011) -[2023-11-28 00:27:55,525][87424] Updated weights for policy 0, policy_version 9726 (0.0012) -[2023-11-28 00:27:56,340][87426] Updated weights for policy 1, policy_version 9700 (0.0010) -[2023-11-28 00:27:56,715][87426] Updated weights for policy 1, policy_version 9710 (0.0007) -[2023-11-28 00:27:57,099][87426] Updated weights for policy 1, policy_version 9720 (0.0012) -[2023-11-28 00:27:57,496][87424] Updated weights for policy 0, policy_version 9736 (0.0011) -[2023-11-28 00:27:57,876][87424] Updated weights for policy 0, policy_version 9746 (0.0008) -[2023-11-28 00:27:58,270][87424] Updated weights for policy 0, policy_version 9756 (0.0012) -[2023-11-28 00:27:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 4988928. Throughput: 0: 2686.7, 1: 2772.9. Samples: 4999092. Policy #0 lag: (min: 31.0, avg: 51.5, max: 89.0) -[2023-11-28 00:27:58,445][86177] Avg episode reward: [(0, '-611.620'), (1, '-547.870')] -[2023-11-28 00:27:58,739][87426] Updated weights for policy 1, policy_version 9730 (0.0011) -[2023-11-28 00:27:59,117][87426] Updated weights for policy 1, policy_version 9740 (0.0012) -[2023-11-28 00:27:59,497][87426] Updated weights for policy 1, policy_version 9750 (0.0010) -[2023-11-28 00:27:59,883][87426] Updated weights for policy 1, policy_version 9760 (0.0008) -[2023-11-28 00:27:59,901][87424] Updated weights for policy 0, policy_version 9766 (0.0011) -[2023-11-28 00:28:00,295][87424] Updated weights for policy 0, policy_version 9776 (0.0010) -[2023-11-28 00:28:00,681][87424] Updated weights for policy 0, policy_version 9786 (0.0009) -[2023-11-28 00:28:02,286][87426] Updated weights for policy 1, policy_version 9770 (0.0012) -[2023-11-28 00:28:02,661][87426] Updated weights for policy 1, policy_version 9780 (0.0012) -[2023-11-28 00:28:02,771][87424] Updated weights for policy 0, policy_version 9796 (0.0012) -[2023-11-28 00:28:03,050][87426] Updated weights for policy 1, policy_version 9790 (0.0011) -[2023-11-28 00:28:03,156][87424] Updated weights for policy 0, policy_version 9806 (0.0010) -[2023-11-28 00:28:03,444][86177] Fps is (10 sec: 5736.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 5013504. Throughput: 0: 2705.0, 1: 2769.9. Samples: 5024780. Policy #0 lag: (min: 31.0, avg: 51.5, max: 89.0) -[2023-11-28 00:28:03,445][86177] Avg episode reward: [(0, '-611.140'), (1, '-548.710')] -[2023-11-28 00:28:03,537][87424] Updated weights for policy 0, policy_version 9816 (0.0008) -[2023-11-28 00:28:04,902][87426] Updated weights for policy 1, policy_version 9800 (0.0011) -[2023-11-28 00:28:05,284][87426] Updated weights for policy 1, policy_version 9810 (0.0010) -[2023-11-28 00:28:05,553][87424] Updated weights for policy 0, policy_version 9826 (0.0008) -[2023-11-28 00:28:05,664][87426] Updated weights for policy 1, policy_version 9820 (0.0007) -[2023-11-28 00:28:05,939][87424] Updated weights for policy 0, policy_version 9836 (0.0011) -[2023-11-28 00:28:06,321][87424] Updated weights for policy 0, policy_version 9846 (0.0012) -[2023-11-28 00:28:06,708][87424] Updated weights for policy 0, policy_version 9856 (0.0011) -[2023-11-28 00:28:08,133][87426] Updated weights for policy 1, policy_version 9830 (0.0009) -[2023-11-28 00:28:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 5038080. Throughput: 0: 2719.6, 1: 2780.1. Samples: 5058964. Policy #0 lag: (min: 31.0, avg: 51.5, max: 89.0) -[2023-11-28 00:28:08,445][86177] Avg episode reward: [(0, '-610.120'), (1, '-566.990')] -[2023-11-28 00:28:08,506][87426] Updated weights for policy 1, policy_version 9840 (0.0008) -[2023-11-28 00:28:08,629][87424] Updated weights for policy 0, policy_version 9866 (0.0009) -[2023-11-28 00:28:08,888][87426] Updated weights for policy 1, policy_version 9850 (0.0008) -[2023-11-28 00:28:09,020][87424] Updated weights for policy 0, policy_version 9876 (0.0008) -[2023-11-28 00:28:09,412][87424] Updated weights for policy 0, policy_version 9886 (0.0008) -[2023-11-28 00:28:10,913][87426] Updated weights for policy 1, policy_version 9860 (0.0011) -[2023-11-28 00:28:11,297][87426] Updated weights for policy 1, policy_version 9870 (0.0011) -[2023-11-28 00:28:11,660][87424] Updated weights for policy 0, policy_version 9896 (0.0009) -[2023-11-28 00:28:11,673][87426] Updated weights for policy 1, policy_version 9880 (0.0011) -[2023-11-28 00:28:12,042][87424] Updated weights for policy 0, policy_version 9906 (0.0011) -[2023-11-28 00:28:12,424][87424] Updated weights for policy 0, policy_version 9916 (0.0010) -[2023-11-28 00:28:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5070848. Throughput: 0: 2729.9, 1: 2760.6. Samples: 5083224. Policy #0 lag: (min: 26.0, avg: 41.2, max: 58.0) -[2023-11-28 00:28:13,445][86177] Avg episode reward: [(0, '-602.380'), (1, '-571.170')] -[2023-11-28 00:28:13,668][87426] Updated weights for policy 1, policy_version 9890 (0.0010) -[2023-11-28 00:28:14,048][87426] Updated weights for policy 1, policy_version 9900 (0.0012) -[2023-11-28 00:28:14,434][87426] Updated weights for policy 1, policy_version 9910 (0.0012) -[2023-11-28 00:28:14,809][87426] Updated weights for policy 1, policy_version 9920 (0.0012) -[2023-11-28 00:28:14,986][87424] Updated weights for policy 0, policy_version 9926 (0.0010) -[2023-11-28 00:28:15,379][87424] Updated weights for policy 0, policy_version 9936 (0.0011) -[2023-11-28 00:28:15,763][87424] Updated weights for policy 0, policy_version 9946 (0.0011) -[2023-11-28 00:28:16,773][87426] Updated weights for policy 1, policy_version 9930 (0.0012) -[2023-11-28 00:28:17,148][87426] Updated weights for policy 1, policy_version 9940 (0.0011) -[2023-11-28 00:28:17,484][87424] Updated weights for policy 0, policy_version 9956 (0.0012) -[2023-11-28 00:28:17,523][87426] Updated weights for policy 1, policy_version 9950 (0.0011) -[2023-11-28 00:28:17,859][87424] Updated weights for policy 0, policy_version 9966 (0.0012) -[2023-11-28 00:28:18,239][87424] Updated weights for policy 0, policy_version 9976 (0.0012) -[2023-11-28 00:28:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 5095424. Throughput: 0: 2747.1, 1: 2764.5. Samples: 5108336. Policy #0 lag: (min: 26.0, avg: 41.2, max: 58.0) -[2023-11-28 00:28:18,445][86177] Avg episode reward: [(0, '-598.760'), (1, '-558.440')] -[2023-11-28 00:28:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000009952_2547712.pth... -[2023-11-28 00:28:18,484][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000007392_1892352.pth -[2023-11-28 00:28:18,547][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000009984_2555904.pth... -[2023-11-28 00:28:18,577][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000007424_1900544.pth -[2023-11-28 00:28:19,481][87426] Updated weights for policy 1, policy_version 9960 (0.0011) -[2023-11-28 00:28:19,852][87426] Updated weights for policy 1, policy_version 9970 (0.0012) -[2023-11-28 00:28:20,233][87426] Updated weights for policy 1, policy_version 9980 (0.0012) -[2023-11-28 00:28:20,622][87424] Updated weights for policy 0, policy_version 9986 (0.0012) -[2023-11-28 00:28:21,009][87424] Updated weights for policy 0, policy_version 9996 (0.0009) -[2023-11-28 00:28:21,398][87424] Updated weights for policy 0, policy_version 10006 (0.0009) -[2023-11-28 00:28:21,787][87424] Updated weights for policy 0, policy_version 10016 (0.0010) -[2023-11-28 00:28:22,779][87426] Updated weights for policy 1, policy_version 9990 (0.0012) -[2023-11-28 00:28:23,167][87426] Updated weights for policy 1, policy_version 10000 (0.0012) -[2023-11-28 00:28:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 5120000. Throughput: 0: 2753.2, 1: 2735.0. Samples: 5140236. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 00:28:23,445][86177] Avg episode reward: [(0, '-590.900'), (1, '-573.890')] -[2023-11-28 00:28:23,536][87426] Updated weights for policy 1, policy_version 10010 (0.0012) -[2023-11-28 00:28:23,923][87424] Updated weights for policy 0, policy_version 10026 (0.0010) -[2023-11-28 00:28:24,307][87424] Updated weights for policy 0, policy_version 10036 (0.0007) -[2023-11-28 00:28:24,690][87424] Updated weights for policy 0, policy_version 10046 (0.0007) -[2023-11-28 00:28:25,615][87426] Updated weights for policy 1, policy_version 10020 (0.0011) -[2023-11-28 00:28:25,983][87426] Updated weights for policy 1, policy_version 10030 (0.0007) -[2023-11-28 00:28:26,359][87426] Updated weights for policy 1, policy_version 10040 (0.0007) -[2023-11-28 00:28:27,017][87424] Updated weights for policy 0, policy_version 10056 (0.0008) -[2023-11-28 00:28:27,400][87424] Updated weights for policy 0, policy_version 10066 (0.0008) -[2023-11-28 00:28:27,784][87424] Updated weights for policy 0, policy_version 10076 (0.0007) -[2023-11-28 00:28:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5152768. Throughput: 0: 2751.3, 1: 2753.8. Samples: 5164696. Policy #0 lag: (min: 4.0, avg: 20.6, max: 36.0) -[2023-11-28 00:28:28,445][86177] Avg episode reward: [(0, '-586.750'), (1, '-577.570')] -[2023-11-28 00:28:28,446][87281] Saving new best policy, reward=-586.750! -[2023-11-28 00:28:28,664][87426] Updated weights for policy 1, policy_version 10050 (0.0007) -[2023-11-28 00:28:29,039][87426] Updated weights for policy 1, policy_version 10060 (0.0008) -[2023-11-28 00:28:29,419][87426] Updated weights for policy 1, policy_version 10070 (0.0008) -[2023-11-28 00:28:29,804][87426] Updated weights for policy 1, policy_version 10080 (0.0008) -[2023-11-28 00:28:30,212][87424] Updated weights for policy 0, policy_version 10086 (0.0009) -[2023-11-28 00:28:30,601][87424] Updated weights for policy 0, policy_version 10096 (0.0008) -[2023-11-28 00:28:30,973][87424] Updated weights for policy 0, policy_version 10106 (0.0008) -[2023-11-28 00:28:32,269][87426] Updated weights for policy 1, policy_version 10090 (0.0010) -[2023-11-28 00:28:32,648][87426] Updated weights for policy 1, policy_version 10100 (0.0008) -[2023-11-28 00:28:32,973][87424] Updated weights for policy 0, policy_version 10116 (0.0009) -[2023-11-28 00:28:33,026][87426] Updated weights for policy 1, policy_version 10110 (0.0010) -[2023-11-28 00:28:33,359][87424] Updated weights for policy 0, policy_version 10126 (0.0011) -[2023-11-28 00:28:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 5177344. Throughput: 0: 2744.8, 1: 2747.7. Samples: 5188460. Policy #0 lag: (min: 4.0, avg: 20.6, max: 36.0) -[2023-11-28 00:28:33,445][86177] Avg episode reward: [(0, '-592.410'), (1, '-561.660')] -[2023-11-28 00:28:33,741][87424] Updated weights for policy 0, policy_version 10136 (0.0011) -[2023-11-28 00:28:35,174][87426] Updated weights for policy 1, policy_version 10120 (0.0011) -[2023-11-28 00:28:35,549][87426] Updated weights for policy 1, policy_version 10130 (0.0008) -[2023-11-28 00:28:35,904][87424] Updated weights for policy 0, policy_version 10146 (0.0010) -[2023-11-28 00:28:35,929][87426] Updated weights for policy 1, policy_version 10140 (0.0007) -[2023-11-28 00:28:36,295][87424] Updated weights for policy 0, policy_version 10156 (0.0007) -[2023-11-28 00:28:36,676][87424] Updated weights for policy 0, policy_version 10166 (0.0008) -[2023-11-28 00:28:37,063][87424] Updated weights for policy 0, policy_version 10176 (0.0008) -[2023-11-28 00:28:38,234][87426] Updated weights for policy 1, policy_version 10150 (0.0009) -[2023-11-28 00:28:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 5201920. Throughput: 0: 2777.2, 1: 2727.3. Samples: 5221616. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 00:28:38,445][86177] Avg episode reward: [(0, '-594.920'), (1, '-594.890')] -[2023-11-28 00:28:38,613][87426] Updated weights for policy 1, policy_version 10160 (0.0010) -[2023-11-28 00:28:38,974][87424] Updated weights for policy 0, policy_version 10186 (0.0009) -[2023-11-28 00:28:38,996][87426] Updated weights for policy 1, policy_version 10170 (0.0011) -[2023-11-28 00:28:39,364][87424] Updated weights for policy 0, policy_version 10196 (0.0012) -[2023-11-28 00:28:39,747][87424] Updated weights for policy 0, policy_version 10206 (0.0012) -[2023-11-28 00:28:41,415][87426] Updated weights for policy 1, policy_version 10180 (0.0012) -[2023-11-28 00:28:41,811][87426] Updated weights for policy 1, policy_version 10190 (0.0011) -[2023-11-28 00:28:42,176][87426] Updated weights for policy 1, policy_version 10200 (0.0010) -[2023-11-28 00:28:42,184][87424] Updated weights for policy 0, policy_version 10216 (0.0011) -[2023-11-28 00:28:42,566][87424] Updated weights for policy 0, policy_version 10226 (0.0009) -[2023-11-28 00:28:42,957][87424] Updated weights for policy 0, policy_version 10236 (0.0012) -[2023-11-28 00:28:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 5234688. Throughput: 0: 2765.2, 1: 2711.0. Samples: 5245520. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 00:28:43,445][86177] Avg episode reward: [(0, '-600.620'), (1, '-614.740')] -[2023-11-28 00:28:44,235][87426] Updated weights for policy 1, policy_version 10210 (0.0010) -[2023-11-28 00:28:44,615][87426] Updated weights for policy 1, policy_version 10220 (0.0007) -[2023-11-28 00:28:44,997][87426] Updated weights for policy 1, policy_version 10230 (0.0007) -[2023-11-28 00:28:45,191][87424] Updated weights for policy 0, policy_version 10246 (0.0010) -[2023-11-28 00:28:45,377][87426] Updated weights for policy 1, policy_version 10240 (0.0010) -[2023-11-28 00:28:45,573][87424] Updated weights for policy 0, policy_version 10256 (0.0007) -[2023-11-28 00:28:45,957][87424] Updated weights for policy 0, policy_version 10266 (0.0007) -[2023-11-28 00:28:47,195][87426] Updated weights for policy 1, policy_version 10250 (0.0011) -[2023-11-28 00:28:47,572][87426] Updated weights for policy 1, policy_version 10260 (0.0011) -[2023-11-28 00:28:47,954][87426] Updated weights for policy 1, policy_version 10270 (0.0008) -[2023-11-28 00:28:47,972][87424] Updated weights for policy 0, policy_version 10276 (0.0009) -[2023-11-28 00:28:48,357][87424] Updated weights for policy 0, policy_version 10286 (0.0012) -[2023-11-28 00:28:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5259264. Throughput: 0: 2728.1, 1: 2711.5. Samples: 5269560. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 00:28:48,445][86177] Avg episode reward: [(0, '-596.600'), (1, '-619.080')] -[2023-11-28 00:28:48,736][87424] Updated weights for policy 0, policy_version 10296 (0.0012) -[2023-11-28 00:28:50,388][87426] Updated weights for policy 1, policy_version 10280 (0.0008) -[2023-11-28 00:28:50,760][87426] Updated weights for policy 1, policy_version 10290 (0.0009) -[2023-11-28 00:28:50,785][87424] Updated weights for policy 0, policy_version 10306 (0.0011) -[2023-11-28 00:28:51,142][87426] Updated weights for policy 1, policy_version 10300 (0.0008) -[2023-11-28 00:28:51,170][87424] Updated weights for policy 0, policy_version 10316 (0.0011) -[2023-11-28 00:28:51,560][87424] Updated weights for policy 0, policy_version 10326 (0.0011) -[2023-11-28 00:28:51,935][87424] Updated weights for policy 0, policy_version 10336 (0.0012) -[2023-11-28 00:28:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.7, 300 sec: 5442.8). Total num frames: 5283840. Throughput: 0: 2716.4, 1: 2685.4. Samples: 5302044. Policy #0 lag: (min: 19.0, avg: 40.8, max: 51.0) -[2023-11-28 00:28:53,445][86177] Avg episode reward: [(0, '-590.830'), (1, '-656.300')] -[2023-11-28 00:28:53,611][87426] Updated weights for policy 1, policy_version 10310 (0.0010) -[2023-11-28 00:28:54,004][87426] Updated weights for policy 1, policy_version 10320 (0.0009) -[2023-11-28 00:28:54,197][87424] Updated weights for policy 0, policy_version 10346 (0.0008) -[2023-11-28 00:28:54,386][87426] Updated weights for policy 1, policy_version 10330 (0.0008) -[2023-11-28 00:28:54,587][87424] Updated weights for policy 0, policy_version 10356 (0.0011) -[2023-11-28 00:28:54,965][87424] Updated weights for policy 0, policy_version 10366 (0.0008) -[2023-11-28 00:28:56,849][87426] Updated weights for policy 1, policy_version 10340 (0.0010) -[2023-11-28 00:28:57,226][87426] Updated weights for policy 1, policy_version 10350 (0.0009) -[2023-11-28 00:28:57,304][87424] Updated weights for policy 0, policy_version 10376 (0.0010) -[2023-11-28 00:28:57,611][87426] Updated weights for policy 1, policy_version 10360 (0.0008) -[2023-11-28 00:28:57,694][87424] Updated weights for policy 0, policy_version 10386 (0.0012) -[2023-11-28 00:28:58,076][87424] Updated weights for policy 0, policy_version 10396 (0.0012) -[2023-11-28 00:28:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5316608. Throughput: 0: 2724.3, 1: 2678.0. Samples: 5326324. Policy #0 lag: (min: 26.0, avg: 51.9, max: 58.0) -[2023-11-28 00:28:58,445][86177] Avg episode reward: [(0, '-587.000'), (1, '-621.360')] -[2023-11-28 00:28:59,735][87426] Updated weights for policy 1, policy_version 10370 (0.0010) -[2023-11-28 00:28:59,983][87424] Updated weights for policy 0, policy_version 10406 (0.0010) -[2023-11-28 00:29:00,111][87426] Updated weights for policy 1, policy_version 10380 (0.0010) -[2023-11-28 00:29:00,362][87424] Updated weights for policy 0, policy_version 10416 (0.0009) -[2023-11-28 00:29:00,499][87426] Updated weights for policy 1, policy_version 10390 (0.0009) -[2023-11-28 00:29:00,750][87424] Updated weights for policy 0, policy_version 10426 (0.0009) -[2023-11-28 00:29:00,870][87426] Updated weights for policy 1, policy_version 10400 (0.0009) -[2023-11-28 00:29:02,373][87424] Updated weights for policy 0, policy_version 10436 (0.0011) -[2023-11-28 00:29:02,754][87424] Updated weights for policy 0, policy_version 10446 (0.0011) -[2023-11-28 00:29:03,149][87424] Updated weights for policy 0, policy_version 10456 (0.0011) -[2023-11-28 00:29:03,231][87426] Updated weights for policy 1, policy_version 10410 (0.0011) -[2023-11-28 00:29:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 5332992. Throughput: 0: 2753.1, 1: 2659.4. Samples: 5351896. Policy #0 lag: (min: 26.0, avg: 51.9, max: 58.0) -[2023-11-28 00:29:03,446][86177] Avg episode reward: [(0, '-592.470'), (1, '-608.070')] -[2023-11-28 00:29:03,601][87426] Updated weights for policy 1, policy_version 10420 (0.0011) -[2023-11-28 00:29:03,991][87426] Updated weights for policy 1, policy_version 10430 (0.0007) -[2023-11-28 00:29:05,037][87424] Updated weights for policy 0, policy_version 10466 (0.0010) -[2023-11-28 00:29:05,429][87424] Updated weights for policy 0, policy_version 10476 (0.0008) -[2023-11-28 00:29:05,812][87424] Updated weights for policy 0, policy_version 10486 (0.0007) -[2023-11-28 00:29:06,196][87424] Updated weights for policy 0, policy_version 10496 (0.0007) -[2023-11-28 00:29:06,528][87426] Updated weights for policy 1, policy_version 10440 (0.0007) -[2023-11-28 00:29:06,910][87426] Updated weights for policy 1, policy_version 10450 (0.0008) -[2023-11-28 00:29:07,298][87426] Updated weights for policy 1, policy_version 10460 (0.0009) -[2023-11-28 00:29:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 5365760. Throughput: 0: 2755.7, 1: 2643.3. Samples: 5383192. Policy #0 lag: (min: 26.0, avg: 51.9, max: 58.0) -[2023-11-28 00:29:08,445][86177] Avg episode reward: [(0, '-586.910'), (1, '-609.680')] -[2023-11-28 00:29:08,604][87424] Updated weights for policy 0, policy_version 10506 (0.0008) -[2023-11-28 00:29:09,006][87424] Updated weights for policy 0, policy_version 10516 (0.0009) -[2023-11-28 00:29:09,233][87426] Updated weights for policy 1, policy_version 10470 (0.0010) -[2023-11-28 00:29:09,391][87424] Updated weights for policy 0, policy_version 10526 (0.0009) -[2023-11-28 00:29:09,611][87426] Updated weights for policy 1, policy_version 10480 (0.0011) -[2023-11-28 00:29:09,990][87426] Updated weights for policy 1, policy_version 10490 (0.0012) -[2023-11-28 00:29:11,857][87424] Updated weights for policy 0, policy_version 10536 (0.0012) -[2023-11-28 00:29:12,233][87424] Updated weights for policy 0, policy_version 10546 (0.0011) -[2023-11-28 00:29:12,264][87426] Updated weights for policy 1, policy_version 10500 (0.0011) -[2023-11-28 00:29:12,626][87424] Updated weights for policy 0, policy_version 10556 (0.0009) -[2023-11-28 00:29:12,644][87426] Updated weights for policy 1, policy_version 10510 (0.0008) -[2023-11-28 00:29:13,029][87426] Updated weights for policy 1, policy_version 10520 (0.0010) -[2023-11-28 00:29:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5398528. Throughput: 0: 2754.0, 1: 2647.6. Samples: 5407764. Policy #0 lag: (min: 11.0, avg: 28.3, max: 43.0) -[2023-11-28 00:29:13,445][86177] Avg episode reward: [(0, '-584.310'), (1, '-547.070')] -[2023-11-28 00:29:13,446][87281] Saving new best policy, reward=-584.310! -[2023-11-28 00:29:14,693][87426] Updated weights for policy 1, policy_version 10530 (0.0008) -[2023-11-28 00:29:15,075][87426] Updated weights for policy 1, policy_version 10540 (0.0007) -[2023-11-28 00:29:15,184][87424] Updated weights for policy 0, policy_version 10566 (0.0010) -[2023-11-28 00:29:15,477][87426] Updated weights for policy 1, policy_version 10550 (0.0008) -[2023-11-28 00:29:15,566][87424] Updated weights for policy 0, policy_version 10576 (0.0008) -[2023-11-28 00:29:15,856][87426] Updated weights for policy 1, policy_version 10560 (0.0009) -[2023-11-28 00:29:15,949][87424] Updated weights for policy 0, policy_version 10586 (0.0009) -[2023-11-28 00:29:17,722][87424] Updated weights for policy 0, policy_version 10596 (0.0009) -[2023-11-28 00:29:18,039][87426] Updated weights for policy 1, policy_version 10570 (0.0011) -[2023-11-28 00:29:18,107][87424] Updated weights for policy 0, policy_version 10606 (0.0011) -[2023-11-28 00:29:18,410][87426] Updated weights for policy 1, policy_version 10580 (0.0010) -[2023-11-28 00:29:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 5414912. Throughput: 0: 2748.2, 1: 2664.3. Samples: 5432020. Policy #0 lag: (min: 11.0, avg: 28.3, max: 43.0) -[2023-11-28 00:29:18,445][86177] Avg episode reward: [(0, '-582.530'), (1, '-543.930')] -[2023-11-28 00:29:18,481][87424] Updated weights for policy 0, policy_version 10616 (0.0009) -[2023-11-28 00:29:18,786][87426] Updated weights for policy 1, policy_version 10590 (0.0012) -[2023-11-28 00:29:18,793][87281] Saving new best policy, reward=-582.530! -[2023-11-28 00:29:20,692][87424] Updated weights for policy 0, policy_version 10626 (0.0007) -[2023-11-28 00:29:20,954][87426] Updated weights for policy 1, policy_version 10600 (0.0011) -[2023-11-28 00:29:21,073][87424] Updated weights for policy 0, policy_version 10636 (0.0010) -[2023-11-28 00:29:21,335][87426] Updated weights for policy 1, policy_version 10610 (0.0010) -[2023-11-28 00:29:21,460][87424] Updated weights for policy 0, policy_version 10646 (0.0008) -[2023-11-28 00:29:21,716][87426] Updated weights for policy 1, policy_version 10620 (0.0011) -[2023-11-28 00:29:21,834][87424] Updated weights for policy 0, policy_version 10656 (0.0009) -[2023-11-28 00:29:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 5447680. Throughput: 0: 2726.4, 1: 2663.5. Samples: 5464160. Policy #0 lag: (min: 30.0, avg: 52.1, max: 70.0) -[2023-11-28 00:29:23,445][86177] Avg episode reward: [(0, '-590.430'), (1, '-541.990')] -[2023-11-28 00:29:23,869][87424] Updated weights for policy 0, policy_version 10666 (0.0008) -[2023-11-28 00:29:24,256][87424] Updated weights for policy 0, policy_version 10676 (0.0008) -[2023-11-28 00:29:24,311][87426] Updated weights for policy 1, policy_version 10630 (0.0009) -[2023-11-28 00:29:24,641][87424] Updated weights for policy 0, policy_version 10686 (0.0012) -[2023-11-28 00:29:24,691][87426] Updated weights for policy 1, policy_version 10640 (0.0007) -[2023-11-28 00:29:25,077][87426] Updated weights for policy 1, policy_version 10650 (0.0007) -[2023-11-28 00:29:26,709][87424] Updated weights for policy 0, policy_version 10696 (0.0011) -[2023-11-28 00:29:27,083][87424] Updated weights for policy 0, policy_version 10706 (0.0012) -[2023-11-28 00:29:27,413][87426] Updated weights for policy 1, policy_version 10660 (0.0008) -[2023-11-28 00:29:27,467][87424] Updated weights for policy 0, policy_version 10716 (0.0011) -[2023-11-28 00:29:27,790][87426] Updated weights for policy 1, policy_version 10670 (0.0008) -[2023-11-28 00:29:28,170][87426] Updated weights for policy 1, policy_version 10680 (0.0008) -[2023-11-28 00:29:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 5472256. Throughput: 0: 2731.8, 1: 2659.1. Samples: 5488112. Policy #0 lag: (min: 30.0, avg: 52.1, max: 70.0) -[2023-11-28 00:29:28,445][86177] Avg episode reward: [(0, '-596.520'), (1, '-538.360')] -[2023-11-28 00:29:29,332][87424] Updated weights for policy 0, policy_version 10726 (0.0012) -[2023-11-28 00:29:29,715][87424] Updated weights for policy 0, policy_version 10736 (0.0012) -[2023-11-28 00:29:30,005][87426] Updated weights for policy 1, policy_version 10690 (0.0008) -[2023-11-28 00:29:30,112][87424] Updated weights for policy 0, policy_version 10746 (0.0012) -[2023-11-28 00:29:30,378][87426] Updated weights for policy 1, policy_version 10700 (0.0011) -[2023-11-28 00:29:30,756][87426] Updated weights for policy 1, policy_version 10710 (0.0012) -[2023-11-28 00:29:31,135][87426] Updated weights for policy 1, policy_version 10720 (0.0012) -[2023-11-28 00:29:32,461][87424] Updated weights for policy 0, policy_version 10756 (0.0011) -[2023-11-28 00:29:32,843][87424] Updated weights for policy 0, policy_version 10766 (0.0012) -[2023-11-28 00:29:33,220][87424] Updated weights for policy 0, policy_version 10776 (0.0012) -[2023-11-28 00:29:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 5496832. Throughput: 0: 2737.4, 1: 2655.2. Samples: 5512228. Policy #0 lag: (min: 2.0, avg: 29.9, max: 52.0) -[2023-11-28 00:29:33,445][86177] Avg episode reward: [(0, '-639.140'), (1, '-572.120')] -[2023-11-28 00:29:33,611][87426] Updated weights for policy 1, policy_version 10730 (0.0010) -[2023-11-28 00:29:33,990][87426] Updated weights for policy 1, policy_version 10740 (0.0007) -[2023-11-28 00:29:34,365][87426] Updated weights for policy 1, policy_version 10750 (0.0007) -[2023-11-28 00:29:35,434][87424] Updated weights for policy 0, policy_version 10786 (0.0011) -[2023-11-28 00:29:35,817][87424] Updated weights for policy 0, policy_version 10796 (0.0008) -[2023-11-28 00:29:36,201][87424] Updated weights for policy 0, policy_version 10806 (0.0009) -[2023-11-28 00:29:36,409][87426] Updated weights for policy 1, policy_version 10760 (0.0010) -[2023-11-28 00:29:36,588][87424] Updated weights for policy 0, policy_version 10816 (0.0007) -[2023-11-28 00:29:36,797][87426] Updated weights for policy 1, policy_version 10770 (0.0010) -[2023-11-28 00:29:37,173][87426] Updated weights for policy 1, policy_version 10780 (0.0012) -[2023-11-28 00:29:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5529600. Throughput: 0: 2739.7, 1: 2660.8. Samples: 5545068. Policy #0 lag: (min: 2.0, avg: 29.9, max: 52.0) -[2023-11-28 00:29:38,445][86177] Avg episode reward: [(0, '-633.750'), (1, '-577.510')] -[2023-11-28 00:29:38,762][87424] Updated weights for policy 0, policy_version 10826 (0.0012) -[2023-11-28 00:29:39,146][87424] Updated weights for policy 0, policy_version 10836 (0.0012) -[2023-11-28 00:29:39,158][87426] Updated weights for policy 1, policy_version 10790 (0.0012) -[2023-11-28 00:29:39,518][87424] Updated weights for policy 0, policy_version 10846 (0.0011) -[2023-11-28 00:29:39,531][87426] Updated weights for policy 1, policy_version 10800 (0.0011) -[2023-11-28 00:29:39,920][87426] Updated weights for policy 1, policy_version 10810 (0.0009) -[2023-11-28 00:29:42,119][87424] Updated weights for policy 0, policy_version 10856 (0.0011) -[2023-11-28 00:29:42,365][87426] Updated weights for policy 1, policy_version 10820 (0.0012) -[2023-11-28 00:29:42,490][87424] Updated weights for policy 0, policy_version 10866 (0.0012) -[2023-11-28 00:29:42,743][87426] Updated weights for policy 1, policy_version 10830 (0.0011) -[2023-11-28 00:29:42,880][87424] Updated weights for policy 0, policy_version 10876 (0.0012) -[2023-11-28 00:29:43,133][87426] Updated weights for policy 1, policy_version 10840 (0.0012) -[2023-11-28 00:29:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5562368. Throughput: 0: 2729.8, 1: 2668.1. Samples: 5569228. Policy #0 lag: (min: 31.0, avg: 49.6, max: 63.0) -[2023-11-28 00:29:43,445][86177] Avg episode reward: [(0, '-613.810'), (1, '-590.810')] -[2023-11-28 00:29:44,686][87424] Updated weights for policy 0, policy_version 10886 (0.0011) -[2023-11-28 00:29:45,002][87426] Updated weights for policy 1, policy_version 10850 (0.0012) -[2023-11-28 00:29:45,069][87424] Updated weights for policy 0, policy_version 10896 (0.0012) -[2023-11-28 00:29:45,379][87426] Updated weights for policy 1, policy_version 10860 (0.0010) -[2023-11-28 00:29:45,452][87424] Updated weights for policy 0, policy_version 10906 (0.0011) -[2023-11-28 00:29:45,754][87426] Updated weights for policy 1, policy_version 10870 (0.0010) -[2023-11-28 00:29:46,139][87426] Updated weights for policy 1, policy_version 10880 (0.0011) -[2023-11-28 00:29:47,545][87424] Updated weights for policy 0, policy_version 10916 (0.0012) -[2023-11-28 00:29:47,932][87424] Updated weights for policy 0, policy_version 10926 (0.0011) -[2023-11-28 00:29:48,321][87424] Updated weights for policy 0, policy_version 10936 (0.0008) -[2023-11-28 00:29:48,401][87426] Updated weights for policy 1, policy_version 10890 (0.0012) -[2023-11-28 00:29:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 5578752. Throughput: 0: 2728.3, 1: 2679.5. Samples: 5595244. Policy #0 lag: (min: 31.0, avg: 49.6, max: 63.0) -[2023-11-28 00:29:48,445][86177] Avg episode reward: [(0, '-604.340'), (1, '-587.260')] -[2023-11-28 00:29:48,776][87426] Updated weights for policy 1, policy_version 10900 (0.0012) -[2023-11-28 00:29:49,153][87426] Updated weights for policy 1, policy_version 10910 (0.0009) -[2023-11-28 00:29:50,094][87424] Updated weights for policy 0, policy_version 10946 (0.0009) -[2023-11-28 00:29:50,477][87424] Updated weights for policy 0, policy_version 10956 (0.0012) -[2023-11-28 00:29:50,860][87424] Updated weights for policy 0, policy_version 10966 (0.0010) -[2023-11-28 00:29:51,167][87426] Updated weights for policy 1, policy_version 10920 (0.0010) -[2023-11-28 00:29:51,248][87424] Updated weights for policy 0, policy_version 10976 (0.0010) -[2023-11-28 00:29:51,546][87426] Updated weights for policy 1, policy_version 10930 (0.0008) -[2023-11-28 00:29:51,921][87426] Updated weights for policy 1, policy_version 10940 (0.0011) -[2023-11-28 00:29:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 5611520. Throughput: 0: 2722.5, 1: 2728.0. Samples: 5628464. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 00:29:53,445][86177] Avg episode reward: [(0, '-553.800'), (1, '-603.110')] -[2023-11-28 00:29:53,674][87424] Updated weights for policy 0, policy_version 10986 (0.0011) -[2023-11-28 00:29:54,053][87424] Updated weights for policy 0, policy_version 10996 (0.0010) -[2023-11-28 00:29:54,290][87426] Updated weights for policy 1, policy_version 10950 (0.0009) -[2023-11-28 00:29:54,426][87424] Updated weights for policy 0, policy_version 11006 (0.0011) -[2023-11-28 00:29:54,497][87281] Saving new best policy, reward=-553.800! -[2023-11-28 00:29:54,676][87426] Updated weights for policy 1, policy_version 10960 (0.0009) -[2023-11-28 00:29:55,043][87426] Updated weights for policy 1, policy_version 10970 (0.0008) -[2023-11-28 00:29:57,022][87424] Updated weights for policy 0, policy_version 11016 (0.0010) -[2023-11-28 00:29:57,100][87426] Updated weights for policy 1, policy_version 10980 (0.0009) -[2023-11-28 00:29:57,392][87424] Updated weights for policy 0, policy_version 11026 (0.0010) -[2023-11-28 00:29:57,481][87426] Updated weights for policy 1, policy_version 10990 (0.0011) -[2023-11-28 00:29:57,779][87424] Updated weights for policy 0, policy_version 11036 (0.0008) -[2023-11-28 00:29:57,861][87426] Updated weights for policy 1, policy_version 11000 (0.0011) -[2023-11-28 00:29:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5644288. Throughput: 0: 2703.3, 1: 2727.2. Samples: 5652136. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 00:29:58,445][86177] Avg episode reward: [(0, '-551.290'), (1, '-591.040')] -[2023-11-28 00:29:58,446][87281] Saving new best policy, reward=-551.290! -[2023-11-28 00:29:59,831][87426] Updated weights for policy 1, policy_version 11010 (0.0012) -[2023-11-28 00:29:59,974][87424] Updated weights for policy 0, policy_version 11046 (0.0008) -[2023-11-28 00:30:00,205][87426] Updated weights for policy 1, policy_version 11020 (0.0010) -[2023-11-28 00:30:00,357][87424] Updated weights for policy 0, policy_version 11056 (0.0008) -[2023-11-28 00:30:00,585][87426] Updated weights for policy 1, policy_version 11030 (0.0011) -[2023-11-28 00:30:00,745][87424] Updated weights for policy 0, policy_version 11066 (0.0011) -[2023-11-28 00:30:00,969][87426] Updated weights for policy 1, policy_version 11040 (0.0012) -[2023-11-28 00:30:02,823][87424] Updated weights for policy 0, policy_version 11076 (0.0010) -[2023-11-28 00:30:03,203][87424] Updated weights for policy 0, policy_version 11086 (0.0008) -[2023-11-28 00:30:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 5660672. Throughput: 0: 2766.3, 1: 2729.5. Samples: 5679332. Policy #0 lag: (min: 31.0, avg: 50.8, max: 63.0) -[2023-11-28 00:30:03,445][86177] Avg episode reward: [(0, '-553.120'), (1, '-604.030')] -[2023-11-28 00:30:03,493][87426] Updated weights for policy 1, policy_version 11050 (0.0011) -[2023-11-28 00:30:03,591][87424] Updated weights for policy 0, policy_version 11096 (0.0007) -[2023-11-28 00:30:03,880][87426] Updated weights for policy 1, policy_version 11060 (0.0011) -[2023-11-28 00:30:04,257][87426] Updated weights for policy 1, policy_version 11070 (0.0011) -[2023-11-28 00:30:05,788][87424] Updated weights for policy 0, policy_version 11106 (0.0008) -[2023-11-28 00:30:06,116][87426] Updated weights for policy 1, policy_version 11080 (0.0012) -[2023-11-28 00:30:06,169][87424] Updated weights for policy 0, policy_version 11116 (0.0011) -[2023-11-28 00:30:06,494][87426] Updated weights for policy 1, policy_version 11090 (0.0011) -[2023-11-28 00:30:06,547][87424] Updated weights for policy 0, policy_version 11126 (0.0012) -[2023-11-28 00:30:06,873][87426] Updated weights for policy 1, policy_version 11100 (0.0011) -[2023-11-28 00:30:06,926][87424] Updated weights for policy 0, policy_version 11136 (0.0011) -[2023-11-28 00:30:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5693440. Throughput: 0: 2782.1, 1: 2735.8. Samples: 5712468. Policy #0 lag: (min: 31.0, avg: 50.8, max: 63.0) -[2023-11-28 00:30:08,445][86177] Avg episode reward: [(0, '-567.650'), (1, '-597.470')] -[2023-11-28 00:30:08,610][87424] Updated weights for policy 0, policy_version 11146 (0.0012) -[2023-11-28 00:30:09,007][87424] Updated weights for policy 0, policy_version 11156 (0.0011) -[2023-11-28 00:30:09,187][87426] Updated weights for policy 1, policy_version 11110 (0.0011) -[2023-11-28 00:30:09,393][87424] Updated weights for policy 0, policy_version 11166 (0.0009) -[2023-11-28 00:30:09,567][87426] Updated weights for policy 1, policy_version 11120 (0.0012) -[2023-11-28 00:30:09,950][87426] Updated weights for policy 1, policy_version 11130 (0.0011) -[2023-11-28 00:30:11,920][87424] Updated weights for policy 0, policy_version 11176 (0.0011) -[2023-11-28 00:30:12,020][87426] Updated weights for policy 1, policy_version 11140 (0.0011) -[2023-11-28 00:30:12,315][87424] Updated weights for policy 0, policy_version 11186 (0.0011) -[2023-11-28 00:30:12,401][87426] Updated weights for policy 1, policy_version 11150 (0.0011) -[2023-11-28 00:30:12,697][87424] Updated weights for policy 0, policy_version 11196 (0.0011) -[2023-11-28 00:30:12,768][87426] Updated weights for policy 1, policy_version 11160 (0.0010) -[2023-11-28 00:30:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 5726208. Throughput: 0: 2774.1, 1: 2757.2. Samples: 5737024. Policy #0 lag: (min: 15.0, avg: 40.1, max: 62.0) -[2023-11-28 00:30:13,445][86177] Avg episode reward: [(0, '-568.330'), (1, '-605.860')] -[2023-11-28 00:30:15,013][87424] Updated weights for policy 0, policy_version 11206 (0.0011) -[2023-11-28 00:30:15,254][87426] Updated weights for policy 1, policy_version 11170 (0.0010) -[2023-11-28 00:30:15,396][87424] Updated weights for policy 0, policy_version 11216 (0.0010) -[2023-11-28 00:30:15,637][87426] Updated weights for policy 1, policy_version 11180 (0.0011) -[2023-11-28 00:30:15,786][87424] Updated weights for policy 0, policy_version 11226 (0.0012) -[2023-11-28 00:30:16,020][87426] Updated weights for policy 1, policy_version 11190 (0.0009) -[2023-11-28 00:30:16,392][87426] Updated weights for policy 1, policy_version 11200 (0.0007) -[2023-11-28 00:30:17,584][87424] Updated weights for policy 0, policy_version 11236 (0.0012) -[2023-11-28 00:30:17,966][87424] Updated weights for policy 0, policy_version 11246 (0.0009) -[2023-11-28 00:30:18,354][87424] Updated weights for policy 0, policy_version 11256 (0.0007) -[2023-11-28 00:30:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 5742592. Throughput: 0: 2787.5, 1: 2761.0. Samples: 5761908. Policy #0 lag: (min: 15.0, avg: 40.1, max: 62.0) -[2023-11-28 00:30:18,445][86177] Avg episode reward: [(0, '-575.360'), (1, '-665.680')] -[2023-11-28 00:30:18,655][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000011264_2883584.pth... -[2023-11-28 00:30:18,682][87426] Updated weights for policy 1, policy_version 11210 (0.0012) -[2023-11-28 00:30:18,696][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000008672_2220032.pth -[2023-11-28 00:30:19,060][87426] Updated weights for policy 1, policy_version 11220 (0.0012) -[2023-11-28 00:30:19,436][87426] Updated weights for policy 1, policy_version 11230 (0.0011) -[2023-11-28 00:30:19,512][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000011232_2875392.pth... -[2023-11-28 00:30:19,559][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000008672_2220032.pth -[2023-11-28 00:30:20,288][87424] Updated weights for policy 0, policy_version 11266 (0.0008) -[2023-11-28 00:30:20,666][87424] Updated weights for policy 0, policy_version 11276 (0.0011) -[2023-11-28 00:30:21,051][87424] Updated weights for policy 0, policy_version 11286 (0.0009) -[2023-11-28 00:30:21,431][87424] Updated weights for policy 0, policy_version 11296 (0.0011) -[2023-11-28 00:30:21,588][87426] Updated weights for policy 1, policy_version 11240 (0.0009) -[2023-11-28 00:30:21,967][87426] Updated weights for policy 1, policy_version 11250 (0.0011) -[2023-11-28 00:30:22,352][87426] Updated weights for policy 1, policy_version 11260 (0.0012) -[2023-11-28 00:30:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5775360. Throughput: 0: 2774.9, 1: 2747.5. Samples: 5793572. Policy #0 lag: (min: 15.0, avg: 40.1, max: 62.0) -[2023-11-28 00:30:23,445][86177] Avg episode reward: [(0, '-572.700'), (1, '-648.970')] -[2023-11-28 00:30:23,654][87424] Updated weights for policy 0, policy_version 11306 (0.0011) -[2023-11-28 00:30:24,039][87424] Updated weights for policy 0, policy_version 11316 (0.0011) -[2023-11-28 00:30:24,431][87424] Updated weights for policy 0, policy_version 11326 (0.0012) -[2023-11-28 00:30:24,783][87426] Updated weights for policy 1, policy_version 11270 (0.0010) -[2023-11-28 00:30:25,166][87426] Updated weights for policy 1, policy_version 11280 (0.0008) -[2023-11-28 00:30:25,549][87426] Updated weights for policy 1, policy_version 11290 (0.0012) -[2023-11-28 00:30:26,550][87424] Updated weights for policy 0, policy_version 11336 (0.0008) -[2023-11-28 00:30:26,929][87424] Updated weights for policy 0, policy_version 11346 (0.0008) -[2023-11-28 00:30:27,179][87426] Updated weights for policy 1, policy_version 11300 (0.0011) -[2023-11-28 00:30:27,307][87424] Updated weights for policy 0, policy_version 11356 (0.0010) -[2023-11-28 00:30:27,557][87426] Updated weights for policy 1, policy_version 11310 (0.0007) -[2023-11-28 00:30:27,939][87426] Updated weights for policy 1, policy_version 11320 (0.0011) -[2023-11-28 00:30:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 5808128. Throughput: 0: 2779.0, 1: 2742.6. Samples: 5817700. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 00:30:28,445][86177] Avg episode reward: [(0, '-562.160'), (1, '-622.690')] -[2023-11-28 00:30:28,846][87424] Updated weights for policy 0, policy_version 11366 (0.0010) -[2023-11-28 00:30:29,230][87424] Updated weights for policy 0, policy_version 11376 (0.0012) -[2023-11-28 00:30:29,621][87424] Updated weights for policy 0, policy_version 11386 (0.0011) -[2023-11-28 00:30:30,206][87426] Updated weights for policy 1, policy_version 11330 (0.0010) -[2023-11-28 00:30:30,590][87426] Updated weights for policy 1, policy_version 11340 (0.0010) -[2023-11-28 00:30:30,969][87426] Updated weights for policy 1, policy_version 11350 (0.0010) -[2023-11-28 00:30:31,355][87426] Updated weights for policy 1, policy_version 11360 (0.0008) -[2023-11-28 00:30:31,891][87424] Updated weights for policy 0, policy_version 11396 (0.0011) -[2023-11-28 00:30:32,273][87424] Updated weights for policy 0, policy_version 11406 (0.0009) -[2023-11-28 00:30:32,664][87424] Updated weights for policy 0, policy_version 11416 (0.0009) -[2023-11-28 00:30:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 5832704. Throughput: 0: 2771.0, 1: 2734.3. Samples: 5842984. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 00:30:33,445][86177] Avg episode reward: [(0, '-563.930'), (1, '-629.330')] -[2023-11-28 00:30:33,575][87426] Updated weights for policy 1, policy_version 11370 (0.0007) -[2023-11-28 00:30:33,957][87426] Updated weights for policy 1, policy_version 11380 (0.0008) -[2023-11-28 00:30:34,344][87426] Updated weights for policy 1, policy_version 11390 (0.0008) -[2023-11-28 00:30:35,068][87424] Updated weights for policy 0, policy_version 11426 (0.0010) -[2023-11-28 00:30:35,447][87424] Updated weights for policy 0, policy_version 11436 (0.0009) -[2023-11-28 00:30:35,829][87424] Updated weights for policy 0, policy_version 11446 (0.0010) -[2023-11-28 00:30:36,221][87424] Updated weights for policy 0, policy_version 11456 (0.0011) -[2023-11-28 00:30:36,286][87426] Updated weights for policy 1, policy_version 11400 (0.0007) -[2023-11-28 00:30:36,670][87426] Updated weights for policy 1, policy_version 11410 (0.0009) -[2023-11-28 00:30:37,051][87426] Updated weights for policy 1, policy_version 11420 (0.0008) -[2023-11-28 00:30:38,113][87424] Updated weights for policy 0, policy_version 11466 (0.0012) -[2023-11-28 00:30:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5857280. Throughput: 0: 2768.1, 1: 2724.5. Samples: 5875632. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 00:30:38,445][86177] Avg episode reward: [(0, '-569.480'), (1, '-621.050')] -[2023-11-28 00:30:38,485][87424] Updated weights for policy 0, policy_version 11476 (0.0012) -[2023-11-28 00:30:38,871][87424] Updated weights for policy 0, policy_version 11486 (0.0012) -[2023-11-28 00:30:39,033][87426] Updated weights for policy 1, policy_version 11430 (0.0010) -[2023-11-28 00:30:39,410][87426] Updated weights for policy 1, policy_version 11440 (0.0011) -[2023-11-28 00:30:39,789][87426] Updated weights for policy 1, policy_version 11450 (0.0011) -[2023-11-28 00:30:40,914][87424] Updated weights for policy 0, policy_version 11496 (0.0009) -[2023-11-28 00:30:41,300][87424] Updated weights for policy 0, policy_version 11506 (0.0009) -[2023-11-28 00:30:41,681][87424] Updated weights for policy 0, policy_version 11516 (0.0011) -[2023-11-28 00:30:41,874][87426] Updated weights for policy 1, policy_version 11460 (0.0011) -[2023-11-28 00:30:42,262][87426] Updated weights for policy 1, policy_version 11470 (0.0012) -[2023-11-28 00:30:42,636][87426] Updated weights for policy 1, policy_version 11480 (0.0011) -[2023-11-28 00:30:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 5890048. Throughput: 0: 2792.4, 1: 2742.2. Samples: 5901196. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 00:30:43,445][86177] Avg episode reward: [(0, '-585.450'), (1, '-581.990')] -[2023-11-28 00:30:43,590][87424] Updated weights for policy 0, policy_version 11526 (0.0010) -[2023-11-28 00:30:43,963][87424] Updated weights for policy 0, policy_version 11536 (0.0012) -[2023-11-28 00:30:44,352][87424] Updated weights for policy 0, policy_version 11546 (0.0008) -[2023-11-28 00:30:44,748][87426] Updated weights for policy 1, policy_version 11490 (0.0012) -[2023-11-28 00:30:45,122][87426] Updated weights for policy 1, policy_version 11500 (0.0012) -[2023-11-28 00:30:45,500][87426] Updated weights for policy 1, policy_version 11510 (0.0012) -[2023-11-28 00:30:45,871][87426] Updated weights for policy 1, policy_version 11520 (0.0012) -[2023-11-28 00:30:46,177][87424] Updated weights for policy 0, policy_version 11556 (0.0009) -[2023-11-28 00:30:46,559][87424] Updated weights for policy 0, policy_version 11566 (0.0011) -[2023-11-28 00:30:46,941][87424] Updated weights for policy 0, policy_version 11576 (0.0007) -[2023-11-28 00:30:48,010][87426] Updated weights for policy 1, policy_version 11530 (0.0011) -[2023-11-28 00:30:48,397][87426] Updated weights for policy 1, policy_version 11540 (0.0011) -[2023-11-28 00:30:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 5914624. Throughput: 0: 2742.9, 1: 2716.2. Samples: 5924992. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:30:48,445][86177] Avg episode reward: [(0, '-604.770'), (1, '-593.010')] -[2023-11-28 00:30:48,779][87426] Updated weights for policy 1, policy_version 11550 (0.0012) -[2023-11-28 00:30:49,416][87424] Updated weights for policy 0, policy_version 11586 (0.0008) -[2023-11-28 00:30:49,799][87424] Updated weights for policy 0, policy_version 11596 (0.0012) -[2023-11-28 00:30:50,195][87424] Updated weights for policy 0, policy_version 11606 (0.0010) -[2023-11-28 00:30:50,571][87424] Updated weights for policy 0, policy_version 11616 (0.0009) -[2023-11-28 00:30:50,707][87426] Updated weights for policy 1, policy_version 11560 (0.0009) -[2023-11-28 00:30:51,096][87426] Updated weights for policy 1, policy_version 11570 (0.0008) -[2023-11-28 00:30:51,480][87426] Updated weights for policy 1, policy_version 11580 (0.0008) -[2023-11-28 00:30:53,103][87424] Updated weights for policy 0, policy_version 11626 (0.0008) -[2023-11-28 00:30:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 5939200. Throughput: 0: 2702.0, 1: 2723.6. Samples: 5956620. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:30:53,445][86177] Avg episode reward: [(0, '-597.860'), (1, '-610.860')] -[2023-11-28 00:30:53,488][87424] Updated weights for policy 0, policy_version 11636 (0.0011) -[2023-11-28 00:30:53,865][87424] Updated weights for policy 0, policy_version 11646 (0.0012) -[2023-11-28 00:30:54,010][87426] Updated weights for policy 1, policy_version 11590 (0.0009) -[2023-11-28 00:30:54,395][87426] Updated weights for policy 1, policy_version 11600 (0.0007) -[2023-11-28 00:30:54,777][87426] Updated weights for policy 1, policy_version 11610 (0.0008) -[2023-11-28 00:30:56,438][87424] Updated weights for policy 0, policy_version 11656 (0.0010) -[2023-11-28 00:30:56,829][87424] Updated weights for policy 0, policy_version 11666 (0.0011) -[2023-11-28 00:30:57,167][87426] Updated weights for policy 1, policy_version 11620 (0.0010) -[2023-11-28 00:30:57,211][87424] Updated weights for policy 0, policy_version 11676 (0.0011) -[2023-11-28 00:30:57,546][87426] Updated weights for policy 1, policy_version 11630 (0.0007) -[2023-11-28 00:30:57,934][87426] Updated weights for policy 1, policy_version 11640 (0.0007) -[2023-11-28 00:30:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 5971968. Throughput: 0: 2721.0, 1: 2716.5. Samples: 5981712. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:30:58,445][86177] Avg episode reward: [(0, '-593.220'), (1, '-584.610')] -[2023-11-28 00:30:58,898][87424] Updated weights for policy 0, policy_version 11686 (0.0012) -[2023-11-28 00:30:59,287][87424] Updated weights for policy 0, policy_version 11696 (0.0011) -[2023-11-28 00:30:59,670][87424] Updated weights for policy 0, policy_version 11706 (0.0007) -[2023-11-28 00:30:59,988][87426] Updated weights for policy 1, policy_version 11650 (0.0008) -[2023-11-28 00:31:00,359][87426] Updated weights for policy 1, policy_version 11660 (0.0008) -[2023-11-28 00:31:00,737][87426] Updated weights for policy 1, policy_version 11670 (0.0010) -[2023-11-28 00:31:01,120][87426] Updated weights for policy 1, policy_version 11680 (0.0010) -[2023-11-28 00:31:01,884][87424] Updated weights for policy 0, policy_version 11716 (0.0010) -[2023-11-28 00:31:02,258][87424] Updated weights for policy 0, policy_version 11726 (0.0012) -[2023-11-28 00:31:02,638][87424] Updated weights for policy 0, policy_version 11736 (0.0012) -[2023-11-28 00:31:03,296][87426] Updated weights for policy 1, policy_version 11690 (0.0011) -[2023-11-28 00:31:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 5996544. Throughput: 0: 2734.5, 1: 2722.6. Samples: 6007476. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:31:03,445][86177] Avg episode reward: [(0, '-580.990'), (1, '-575.970')] -[2023-11-28 00:31:03,679][87426] Updated weights for policy 1, policy_version 11700 (0.0008) -[2023-11-28 00:31:04,058][87426] Updated weights for policy 1, policy_version 11710 (0.0007) -[2023-11-28 00:31:05,144][87424] Updated weights for policy 0, policy_version 11746 (0.0011) -[2023-11-28 00:31:05,535][87424] Updated weights for policy 0, policy_version 11756 (0.0009) -[2023-11-28 00:31:05,907][87424] Updated weights for policy 0, policy_version 11766 (0.0007) -[2023-11-28 00:31:06,289][87424] Updated weights for policy 0, policy_version 11776 (0.0008) -[2023-11-28 00:31:06,557][87426] Updated weights for policy 1, policy_version 11720 (0.0010) -[2023-11-28 00:31:06,942][87426] Updated weights for policy 1, policy_version 11730 (0.0012) -[2023-11-28 00:31:07,326][87426] Updated weights for policy 1, policy_version 11740 (0.0011) -[2023-11-28 00:31:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 6021120. Throughput: 0: 2727.4, 1: 2725.1. Samples: 6038932. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:31:08,445][86177] Avg episode reward: [(0, '-567.660'), (1, '-566.130')] -[2023-11-28 00:31:08,692][87424] Updated weights for policy 0, policy_version 11786 (0.0012) -[2023-11-28 00:31:09,078][87424] Updated weights for policy 0, policy_version 11796 (0.0011) -[2023-11-28 00:31:09,460][87424] Updated weights for policy 0, policy_version 11806 (0.0009) -[2023-11-28 00:31:09,769][87426] Updated weights for policy 1, policy_version 11750 (0.0011) -[2023-11-28 00:31:10,147][87426] Updated weights for policy 1, policy_version 11760 (0.0010) -[2023-11-28 00:31:10,527][87426] Updated weights for policy 1, policy_version 11770 (0.0008) -[2023-11-28 00:31:11,979][87424] Updated weights for policy 0, policy_version 11816 (0.0010) -[2023-11-28 00:31:12,365][87424] Updated weights for policy 0, policy_version 11826 (0.0009) -[2023-11-28 00:31:12,755][87424] Updated weights for policy 0, policy_version 11836 (0.0010) -[2023-11-28 00:31:12,859][87426] Updated weights for policy 1, policy_version 11780 (0.0009) -[2023-11-28 00:31:13,240][87426] Updated weights for policy 1, policy_version 11790 (0.0011) -[2023-11-28 00:31:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 6045696. Throughput: 0: 2727.4, 1: 2721.1. Samples: 6062884. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-11-28 00:31:13,445][86177] Avg episode reward: [(0, '-558.330'), (1, '-535.440')] -[2023-11-28 00:31:13,616][87426] Updated weights for policy 1, policy_version 11800 (0.0012) -[2023-11-28 00:31:14,508][87424] Updated weights for policy 0, policy_version 11846 (0.0011) -[2023-11-28 00:31:14,892][87424] Updated weights for policy 0, policy_version 11856 (0.0011) -[2023-11-28 00:31:15,302][87424] Updated weights for policy 0, policy_version 11866 (0.0009) -[2023-11-28 00:31:15,736][87426] Updated weights for policy 1, policy_version 11810 (0.0011) -[2023-11-28 00:31:16,104][87426] Updated weights for policy 1, policy_version 11820 (0.0009) -[2023-11-28 00:31:16,489][87426] Updated weights for policy 1, policy_version 11830 (0.0009) -[2023-11-28 00:31:16,866][87426] Updated weights for policy 1, policy_version 11840 (0.0011) -[2023-11-28 00:31:17,817][87424] Updated weights for policy 0, policy_version 11876 (0.0009) -[2023-11-28 00:31:18,203][87424] Updated weights for policy 0, policy_version 11886 (0.0007) -[2023-11-28 00:31:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6070272. Throughput: 0: 2710.8, 1: 2711.5. Samples: 6086984. Policy #0 lag: (min: 31.0, avg: 35.5, max: 63.0) -[2023-11-28 00:31:18,445][86177] Avg episode reward: [(0, '-559.360'), (1, '-539.910')] -[2023-11-28 00:31:18,590][87424] Updated weights for policy 0, policy_version 11896 (0.0007) -[2023-11-28 00:31:18,777][87426] Updated weights for policy 1, policy_version 11850 (0.0011) -[2023-11-28 00:31:19,157][87426] Updated weights for policy 1, policy_version 11860 (0.0009) -[2023-11-28 00:31:19,546][87426] Updated weights for policy 1, policy_version 11870 (0.0009) -[2023-11-28 00:31:20,764][87424] Updated weights for policy 0, policy_version 11906 (0.0010) -[2023-11-28 00:31:21,138][87424] Updated weights for policy 0, policy_version 11916 (0.0011) -[2023-11-28 00:31:21,451][87426] Updated weights for policy 1, policy_version 11880 (0.0011) -[2023-11-28 00:31:21,522][87424] Updated weights for policy 0, policy_version 11926 (0.0008) -[2023-11-28 00:31:21,827][87426] Updated weights for policy 1, policy_version 11890 (0.0010) -[2023-11-28 00:31:21,899][87424] Updated weights for policy 0, policy_version 11936 (0.0012) -[2023-11-28 00:31:22,229][87426] Updated weights for policy 1, policy_version 11900 (0.0011) -[2023-11-28 00:31:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 6103040. Throughput: 0: 2706.9, 1: 2704.8. Samples: 6119160. Policy #0 lag: (min: 33.0, avg: 36.7, max: 65.0) -[2023-11-28 00:31:23,446][86177] Avg episode reward: [(0, '-583.010'), (1, '-528.830')] -[2023-11-28 00:31:23,447][87320] Saving new best policy, reward=-528.830! -[2023-11-28 00:31:23,963][87424] Updated weights for policy 0, policy_version 11946 (0.0007) -[2023-11-28 00:31:24,350][87424] Updated weights for policy 0, policy_version 11956 (0.0007) -[2023-11-28 00:31:24,681][87426] Updated weights for policy 1, policy_version 11910 (0.0011) -[2023-11-28 00:31:24,733][87424] Updated weights for policy 0, policy_version 11966 (0.0007) -[2023-11-28 00:31:25,058][87426] Updated weights for policy 1, policy_version 11920 (0.0010) -[2023-11-28 00:31:25,443][87426] Updated weights for policy 1, policy_version 11930 (0.0012) -[2023-11-28 00:31:26,555][87424] Updated weights for policy 0, policy_version 11976 (0.0011) -[2023-11-28 00:31:26,938][87424] Updated weights for policy 0, policy_version 11986 (0.0012) -[2023-11-28 00:31:27,172][87426] Updated weights for policy 1, policy_version 11940 (0.0011) -[2023-11-28 00:31:27,325][87424] Updated weights for policy 0, policy_version 11996 (0.0011) -[2023-11-28 00:31:27,549][87426] Updated weights for policy 1, policy_version 11950 (0.0007) -[2023-11-28 00:31:27,933][87426] Updated weights for policy 1, policy_version 11960 (0.0008) -[2023-11-28 00:31:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 6135808. Throughput: 0: 2697.7, 1: 2704.0. Samples: 6144272. Policy #0 lag: (min: 33.0, avg: 36.7, max: 65.0) -[2023-11-28 00:31:28,445][86177] Avg episode reward: [(0, '-596.510'), (1, '-527.310')] -[2023-11-28 00:31:28,446][87320] Saving new best policy, reward=-527.310! -[2023-11-28 00:31:29,641][87424] Updated weights for policy 0, policy_version 12006 (0.0007) -[2023-11-28 00:31:30,025][87424] Updated weights for policy 0, policy_version 12016 (0.0008) -[2023-11-28 00:31:30,338][87426] Updated weights for policy 1, policy_version 11970 (0.0007) -[2023-11-28 00:31:30,415][87424] Updated weights for policy 0, policy_version 12026 (0.0007) -[2023-11-28 00:31:30,717][87426] Updated weights for policy 1, policy_version 11980 (0.0010) -[2023-11-28 00:31:31,096][87426] Updated weights for policy 1, policy_version 11990 (0.0010) -[2023-11-28 00:31:31,480][87426] Updated weights for policy 1, policy_version 12000 (0.0008) -[2023-11-28 00:31:32,541][87424] Updated weights for policy 0, policy_version 12036 (0.0010) -[2023-11-28 00:31:32,925][87424] Updated weights for policy 0, policy_version 12046 (0.0012) -[2023-11-28 00:31:33,304][87424] Updated weights for policy 0, policy_version 12056 (0.0012) -[2023-11-28 00:31:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 6152192. Throughput: 0: 2707.0, 1: 2706.2. Samples: 6168588. Policy #0 lag: (min: 33.0, avg: 36.7, max: 65.0) -[2023-11-28 00:31:33,445][86177] Avg episode reward: [(0, '-597.610'), (1, '-526.470')] -[2023-11-28 00:31:33,456][87320] Saving new best policy, reward=-526.470! -[2023-11-28 00:31:34,009][87426] Updated weights for policy 1, policy_version 12010 (0.0011) -[2023-11-28 00:31:34,403][87426] Updated weights for policy 1, policy_version 12020 (0.0012) -[2023-11-28 00:31:34,776][87426] Updated weights for policy 1, policy_version 12030 (0.0012) -[2023-11-28 00:31:35,651][87424] Updated weights for policy 0, policy_version 12066 (0.0009) -[2023-11-28 00:31:36,030][87424] Updated weights for policy 0, policy_version 12076 (0.0007) -[2023-11-28 00:31:36,409][87424] Updated weights for policy 0, policy_version 12086 (0.0008) -[2023-11-28 00:31:36,664][87426] Updated weights for policy 1, policy_version 12040 (0.0011) -[2023-11-28 00:31:36,793][87424] Updated weights for policy 0, policy_version 12096 (0.0011) -[2023-11-28 00:31:37,043][87426] Updated weights for policy 1, policy_version 12050 (0.0009) -[2023-11-28 00:31:37,425][87426] Updated weights for policy 1, policy_version 12060 (0.0012) -[2023-11-28 00:31:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 6184960. Throughput: 0: 2723.2, 1: 2700.0. Samples: 6200664. Policy #0 lag: (min: 13.0, avg: 35.6, max: 49.0) -[2023-11-28 00:31:38,445][86177] Avg episode reward: [(0, '-589.880'), (1, '-514.640')] -[2023-11-28 00:31:38,447][87320] Saving new best policy, reward=-514.640! -[2023-11-28 00:31:38,709][87424] Updated weights for policy 0, policy_version 12106 (0.0008) -[2023-11-28 00:31:39,095][87424] Updated weights for policy 0, policy_version 12116 (0.0008) -[2023-11-28 00:31:39,477][87424] Updated weights for policy 0, policy_version 12126 (0.0011) -[2023-11-28 00:31:39,841][87426] Updated weights for policy 1, policy_version 12070 (0.0010) -[2023-11-28 00:31:40,221][87426] Updated weights for policy 1, policy_version 12080 (0.0011) -[2023-11-28 00:31:40,604][87426] Updated weights for policy 1, policy_version 12090 (0.0010) -[2023-11-28 00:31:41,729][87424] Updated weights for policy 0, policy_version 12136 (0.0012) -[2023-11-28 00:31:42,110][87424] Updated weights for policy 0, policy_version 12146 (0.0011) -[2023-11-28 00:31:42,493][87424] Updated weights for policy 0, policy_version 12156 (0.0012) -[2023-11-28 00:31:43,151][87426] Updated weights for policy 1, policy_version 12100 (0.0011) -[2023-11-28 00:31:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 6209536. Throughput: 0: 2713.4, 1: 2669.8. Samples: 6223956. Policy #0 lag: (min: 13.0, avg: 35.6, max: 49.0) -[2023-11-28 00:31:43,445][86177] Avg episode reward: [(0, '-580.370'), (1, '-531.500')] -[2023-11-28 00:31:43,533][87426] Updated weights for policy 1, policy_version 12110 (0.0010) -[2023-11-28 00:31:43,901][87426] Updated weights for policy 1, policy_version 12120 (0.0010) -[2023-11-28 00:31:44,360][87424] Updated weights for policy 0, policy_version 12166 (0.0012) -[2023-11-28 00:31:44,738][87424] Updated weights for policy 0, policy_version 12176 (0.0011) -[2023-11-28 00:31:45,125][87424] Updated weights for policy 0, policy_version 12186 (0.0012) -[2023-11-28 00:31:46,369][87426] Updated weights for policy 1, policy_version 12130 (0.0011) -[2023-11-28 00:31:46,750][87426] Updated weights for policy 1, policy_version 12140 (0.0007) -[2023-11-28 00:31:47,145][87426] Updated weights for policy 1, policy_version 12150 (0.0007) -[2023-11-28 00:31:47,271][87424] Updated weights for policy 0, policy_version 12196 (0.0010) -[2023-11-28 00:31:47,524][87426] Updated weights for policy 1, policy_version 12160 (0.0007) -[2023-11-28 00:31:47,662][87424] Updated weights for policy 0, policy_version 12206 (0.0007) -[2023-11-28 00:31:48,052][87424] Updated weights for policy 0, policy_version 12216 (0.0008) -[2023-11-28 00:31:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 6242304. Throughput: 0: 2691.0, 1: 2659.2. Samples: 6248236. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-11-28 00:31:48,445][86177] Avg episode reward: [(0, '-547.300'), (1, '-553.630')] -[2023-11-28 00:31:48,456][87281] Saving new best policy, reward=-547.300! -[2023-11-28 00:31:49,983][87424] Updated weights for policy 0, policy_version 12226 (0.0010) -[2023-11-28 00:31:50,011][87426] Updated weights for policy 1, policy_version 12170 (0.0010) -[2023-11-28 00:31:50,372][87424] Updated weights for policy 0, policy_version 12236 (0.0008) -[2023-11-28 00:31:50,386][87426] Updated weights for policy 1, policy_version 12180 (0.0008) -[2023-11-28 00:31:50,744][87424] Updated weights for policy 0, policy_version 12246 (0.0008) -[2023-11-28 00:31:50,771][87426] Updated weights for policy 1, policy_version 12190 (0.0010) -[2023-11-28 00:31:51,134][87424] Updated weights for policy 0, policy_version 12256 (0.0008) -[2023-11-28 00:31:53,165][87424] Updated weights for policy 0, policy_version 12266 (0.0012) -[2023-11-28 00:31:53,290][87426] Updated weights for policy 1, policy_version 12200 (0.0011) -[2023-11-28 00:31:53,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 6258688. Throughput: 0: 2706.8, 1: 2653.8. Samples: 6280160. Policy #0 lag: (min: 31.0, avg: 37.6, max: 63.0) -[2023-11-28 00:31:53,446][86177] Avg episode reward: [(0, '-562.010'), (1, '-594.970')] -[2023-11-28 00:31:53,552][87424] Updated weights for policy 0, policy_version 12276 (0.0010) -[2023-11-28 00:31:53,664][87426] Updated weights for policy 1, policy_version 12210 (0.0012) -[2023-11-28 00:31:53,938][87424] Updated weights for policy 0, policy_version 12286 (0.0008) -[2023-11-28 00:31:54,039][87426] Updated weights for policy 1, policy_version 12220 (0.0012) -[2023-11-28 00:31:56,118][87424] Updated weights for policy 0, policy_version 12296 (0.0008) -[2023-11-28 00:31:56,509][87424] Updated weights for policy 0, policy_version 12306 (0.0008) -[2023-11-28 00:31:56,624][87426] Updated weights for policy 1, policy_version 12230 (0.0009) -[2023-11-28 00:31:56,905][87424] Updated weights for policy 0, policy_version 12316 (0.0009) -[2023-11-28 00:31:57,017][87426] Updated weights for policy 1, policy_version 12240 (0.0007) -[2023-11-28 00:31:57,405][87426] Updated weights for policy 1, policy_version 12250 (0.0007) -[2023-11-28 00:31:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 6291456. Throughput: 0: 2725.7, 1: 2643.4. Samples: 6304492. Policy #0 lag: (min: 27.0, avg: 37.4, max: 59.0) -[2023-11-28 00:31:58,445][86177] Avg episode reward: [(0, '-556.580'), (1, '-605.160')] -[2023-11-28 00:31:59,149][87424] Updated weights for policy 0, policy_version 12326 (0.0010) -[2023-11-28 00:31:59,538][87424] Updated weights for policy 0, policy_version 12336 (0.0009) -[2023-11-28 00:31:59,840][87426] Updated weights for policy 1, policy_version 12260 (0.0010) -[2023-11-28 00:31:59,919][87424] Updated weights for policy 0, policy_version 12346 (0.0010) -[2023-11-28 00:32:00,215][87426] Updated weights for policy 1, policy_version 12270 (0.0008) -[2023-11-28 00:32:00,593][87426] Updated weights for policy 1, policy_version 12280 (0.0010) -[2023-11-28 00:32:01,872][87424] Updated weights for policy 0, policy_version 12356 (0.0009) -[2023-11-28 00:32:02,253][87424] Updated weights for policy 0, policy_version 12366 (0.0012) -[2023-11-28 00:32:02,638][87424] Updated weights for policy 0, policy_version 12376 (0.0012) -[2023-11-28 00:32:02,946][87426] Updated weights for policy 1, policy_version 12290 (0.0009) -[2023-11-28 00:32:03,328][87426] Updated weights for policy 1, policy_version 12300 (0.0012) -[2023-11-28 00:32:03,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 6316032. Throughput: 0: 2748.4, 1: 2637.8. Samples: 6329364. Policy #0 lag: (min: 27.0, avg: 37.4, max: 59.0) -[2023-11-28 00:32:03,445][86177] Avg episode reward: [(0, '-557.810'), (1, '-644.720')] -[2023-11-28 00:32:03,711][87426] Updated weights for policy 1, policy_version 12310 (0.0012) -[2023-11-28 00:32:04,088][87426] Updated weights for policy 1, policy_version 12320 (0.0012) -[2023-11-28 00:32:05,134][87424] Updated weights for policy 0, policy_version 12386 (0.0011) -[2023-11-28 00:32:05,521][87424] Updated weights for policy 0, policy_version 12396 (0.0012) -[2023-11-28 00:32:05,898][87424] Updated weights for policy 0, policy_version 12406 (0.0009) -[2023-11-28 00:32:05,952][87426] Updated weights for policy 1, policy_version 12330 (0.0011) -[2023-11-28 00:32:06,286][87424] Updated weights for policy 0, policy_version 12416 (0.0009) -[2023-11-28 00:32:06,331][87426] Updated weights for policy 1, policy_version 12340 (0.0011) -[2023-11-28 00:32:06,724][87426] Updated weights for policy 1, policy_version 12350 (0.0011) -[2023-11-28 00:32:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 6340608. Throughput: 0: 2764.5, 1: 2643.6. Samples: 6362524. Policy #0 lag: (min: 27.0, avg: 37.4, max: 59.0) -[2023-11-28 00:32:08,445][86177] Avg episode reward: [(0, '-566.100'), (1, '-619.780')] -[2023-11-28 00:32:08,484][87426] Updated weights for policy 1, policy_version 12360 (0.0011) -[2023-11-28 00:32:08,758][87424] Updated weights for policy 0, policy_version 12426 (0.0009) -[2023-11-28 00:32:08,874][87426] Updated weights for policy 1, policy_version 12370 (0.0008) -[2023-11-28 00:32:09,139][87424] Updated weights for policy 0, policy_version 12436 (0.0009) -[2023-11-28 00:32:09,243][87426] Updated weights for policy 1, policy_version 12380 (0.0011) -[2023-11-28 00:32:09,526][87424] Updated weights for policy 0, policy_version 12446 (0.0008) -[2023-11-28 00:32:11,379][87424] Updated weights for policy 0, policy_version 12456 (0.0010) -[2023-11-28 00:32:11,511][87426] Updated weights for policy 1, policy_version 12390 (0.0010) -[2023-11-28 00:32:11,771][87424] Updated weights for policy 0, policy_version 12466 (0.0009) -[2023-11-28 00:32:11,891][87426] Updated weights for policy 1, policy_version 12400 (0.0010) -[2023-11-28 00:32:12,148][87424] Updated weights for policy 0, policy_version 12476 (0.0011) -[2023-11-28 00:32:12,272][87426] Updated weights for policy 1, policy_version 12410 (0.0011) -[2023-11-28 00:32:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6373376. Throughput: 0: 2775.0, 1: 2614.8. Samples: 6386816. Policy #0 lag: (min: 31.0, avg: 41.3, max: 64.0) -[2023-11-28 00:32:13,445][86177] Avg episode reward: [(0, '-562.390'), (1, '-576.920')] -[2023-11-28 00:32:14,224][87424] Updated weights for policy 0, policy_version 12486 (0.0009) -[2023-11-28 00:32:14,491][87426] Updated weights for policy 1, policy_version 12420 (0.0012) -[2023-11-28 00:32:14,608][87424] Updated weights for policy 0, policy_version 12496 (0.0007) -[2023-11-28 00:32:14,861][87426] Updated weights for policy 1, policy_version 12430 (0.0011) -[2023-11-28 00:32:14,997][87424] Updated weights for policy 0, policy_version 12506 (0.0012) -[2023-11-28 00:32:15,243][87426] Updated weights for policy 1, policy_version 12440 (0.0010) -[2023-11-28 00:32:17,105][87424] Updated weights for policy 0, policy_version 12516 (0.0011) -[2023-11-28 00:32:17,481][87424] Updated weights for policy 0, policy_version 12526 (0.0012) -[2023-11-28 00:32:17,754][87426] Updated weights for policy 1, policy_version 12450 (0.0012) -[2023-11-28 00:32:17,871][87424] Updated weights for policy 0, policy_version 12536 (0.0011) -[2023-11-28 00:32:18,132][87426] Updated weights for policy 1, policy_version 12460 (0.0010) -[2023-11-28 00:32:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6397952. Throughput: 0: 2781.2, 1: 2622.9. Samples: 6411776. Policy #0 lag: (min: 31.0, avg: 41.3, max: 64.0) -[2023-11-28 00:32:18,445][86177] Avg episode reward: [(0, '-559.930'), (1, '-583.170')] -[2023-11-28 00:32:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000012544_3211264.pth... -[2023-11-28 00:32:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000009984_2555904.pth -[2023-11-28 00:32:18,497][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000012544_3211264.pth -[2023-11-28 00:32:18,527][87426] Updated weights for policy 1, policy_version 12470 (0.0007) -[2023-11-28 00:32:18,897][87426] Updated weights for policy 1, policy_version 12480 (0.0008) -[2023-11-28 00:32:18,897][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000012480_3194880.pth... -[2023-11-28 00:32:18,946][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000009952_2547712.pth -[2023-11-28 00:32:18,953][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000012480_3194880.pth -[2023-11-28 00:32:20,074][87424] Updated weights for policy 0, policy_version 12546 (0.0010) -[2023-11-28 00:32:20,456][87424] Updated weights for policy 0, policy_version 12556 (0.0011) -[2023-11-28 00:32:20,834][87424] Updated weights for policy 0, policy_version 12566 (0.0012) -[2023-11-28 00:32:21,129][87426] Updated weights for policy 1, policy_version 12490 (0.0010) -[2023-11-28 00:32:21,215][87424] Updated weights for policy 0, policy_version 12576 (0.0011) -[2023-11-28 00:32:21,506][87426] Updated weights for policy 1, policy_version 12500 (0.0012) -[2023-11-28 00:32:21,885][87426] Updated weights for policy 1, policy_version 12510 (0.0012) -[2023-11-28 00:32:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 6422528. Throughput: 0: 2769.6, 1: 2613.1. Samples: 6442884. Policy #0 lag: (min: 12.0, avg: 31.4, max: 44.0) -[2023-11-28 00:32:23,445][86177] Avg episode reward: [(0, '-560.940'), (1, '-531.190')] -[2023-11-28 00:32:23,516][87424] Updated weights for policy 0, policy_version 12586 (0.0012) -[2023-11-28 00:32:23,903][87424] Updated weights for policy 0, policy_version 12596 (0.0011) -[2023-11-28 00:32:24,054][87426] Updated weights for policy 1, policy_version 12520 (0.0008) -[2023-11-28 00:32:24,291][87424] Updated weights for policy 0, policy_version 12606 (0.0011) -[2023-11-28 00:32:24,436][87426] Updated weights for policy 1, policy_version 12530 (0.0007) -[2023-11-28 00:32:24,825][87426] Updated weights for policy 1, policy_version 12540 (0.0007) -[2023-11-28 00:32:26,516][87424] Updated weights for policy 0, policy_version 12616 (0.0009) -[2023-11-28 00:32:26,569][87426] Updated weights for policy 1, policy_version 12550 (0.0010) -[2023-11-28 00:32:26,907][87424] Updated weights for policy 0, policy_version 12626 (0.0009) -[2023-11-28 00:32:26,951][87426] Updated weights for policy 1, policy_version 12560 (0.0011) -[2023-11-28 00:32:27,295][87424] Updated weights for policy 0, policy_version 12636 (0.0012) -[2023-11-28 00:32:27,335][87426] Updated weights for policy 1, policy_version 12570 (0.0012) -[2023-11-28 00:32:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 6455296. Throughput: 0: 2754.0, 1: 2645.2. Samples: 6466920. Policy #0 lag: (min: 12.0, avg: 31.4, max: 44.0) -[2023-11-28 00:32:28,445][86177] Avg episode reward: [(0, '-552.740'), (1, '-543.100')] -[2023-11-28 00:32:29,205][87424] Updated weights for policy 0, policy_version 12646 (0.0009) -[2023-11-28 00:32:29,479][87426] Updated weights for policy 1, policy_version 12580 (0.0011) -[2023-11-28 00:32:29,598][87424] Updated weights for policy 0, policy_version 12656 (0.0011) -[2023-11-28 00:32:29,851][87426] Updated weights for policy 1, policy_version 12590 (0.0008) -[2023-11-28 00:32:29,985][87424] Updated weights for policy 0, policy_version 12666 (0.0012) -[2023-11-28 00:32:30,236][87426] Updated weights for policy 1, policy_version 12600 (0.0011) -[2023-11-28 00:32:32,549][87424] Updated weights for policy 0, policy_version 12676 (0.0010) -[2023-11-28 00:32:32,558][87426] Updated weights for policy 1, policy_version 12610 (0.0011) -[2023-11-28 00:32:32,930][87424] Updated weights for policy 0, policy_version 12686 (0.0008) -[2023-11-28 00:32:32,931][87426] Updated weights for policy 1, policy_version 12620 (0.0011) -[2023-11-28 00:32:33,311][87426] Updated weights for policy 1, policy_version 12630 (0.0009) -[2023-11-28 00:32:33,311][87424] Updated weights for policy 0, policy_version 12696 (0.0008) -[2023-11-28 00:32:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 6471680. Throughput: 0: 2749.3, 1: 2655.8. Samples: 6491468. Policy #0 lag: (min: 12.0, avg: 31.4, max: 44.0) -[2023-11-28 00:32:33,445][86177] Avg episode reward: [(0, '-550.770'), (1, '-548.900')] -[2023-11-28 00:32:33,691][87426] Updated weights for policy 1, policy_version 12640 (0.0011) -[2023-11-28 00:32:35,338][87424] Updated weights for policy 0, policy_version 12706 (0.0008) -[2023-11-28 00:32:35,630][87426] Updated weights for policy 1, policy_version 12650 (0.0012) -[2023-11-28 00:32:35,723][87424] Updated weights for policy 0, policy_version 12716 (0.0009) -[2023-11-28 00:32:36,012][87426] Updated weights for policy 1, policy_version 12660 (0.0012) -[2023-11-28 00:32:36,105][87424] Updated weights for policy 0, policy_version 12726 (0.0008) -[2023-11-28 00:32:36,392][87426] Updated weights for policy 1, policy_version 12670 (0.0011) -[2023-11-28 00:32:36,490][87424] Updated weights for policy 0, policy_version 12736 (0.0011) -[2023-11-28 00:32:38,228][87424] Updated weights for policy 0, policy_version 12746 (0.0009) -[2023-11-28 00:32:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 6504448. Throughput: 0: 2736.0, 1: 2683.5. Samples: 6524036. Policy #0 lag: (min: 24.0, avg: 56.8, max: 88.0) -[2023-11-28 00:32:38,445][86177] Avg episode reward: [(0, '-566.110'), (1, '-560.170')] -[2023-11-28 00:32:38,586][87426] Updated weights for policy 1, policy_version 12680 (0.0011) -[2023-11-28 00:32:38,631][87424] Updated weights for policy 0, policy_version 12756 (0.0009) -[2023-11-28 00:32:38,969][87426] Updated weights for policy 1, policy_version 12690 (0.0011) -[2023-11-28 00:32:39,007][87424] Updated weights for policy 0, policy_version 12766 (0.0009) -[2023-11-28 00:32:39,362][87426] Updated weights for policy 1, policy_version 12700 (0.0011) -[2023-11-28 00:32:41,465][87424] Updated weights for policy 0, policy_version 12776 (0.0011) -[2023-11-28 00:32:41,848][87424] Updated weights for policy 0, policy_version 12786 (0.0011) -[2023-11-28 00:32:41,864][87426] Updated weights for policy 1, policy_version 12710 (0.0012) -[2023-11-28 00:32:42,235][87424] Updated weights for policy 0, policy_version 12796 (0.0011) -[2023-11-28 00:32:42,239][87426] Updated weights for policy 1, policy_version 12720 (0.0011) -[2023-11-28 00:32:42,620][87426] Updated weights for policy 1, policy_version 12730 (0.0012) -[2023-11-28 00:32:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6537216. Throughput: 0: 2705.6, 1: 2684.1. Samples: 6547028. Policy #0 lag: (min: 24.0, avg: 56.8, max: 88.0) -[2023-11-28 00:32:43,445][86177] Avg episode reward: [(0, '-570.650'), (1, '-571.870')] -[2023-11-28 00:32:44,665][87426] Updated weights for policy 1, policy_version 12740 (0.0011) -[2023-11-28 00:32:44,744][87424] Updated weights for policy 0, policy_version 12806 (0.0010) -[2023-11-28 00:32:45,046][87426] Updated weights for policy 1, policy_version 12750 (0.0012) -[2023-11-28 00:32:45,128][87424] Updated weights for policy 0, policy_version 12816 (0.0008) -[2023-11-28 00:32:45,427][87426] Updated weights for policy 1, policy_version 12760 (0.0011) -[2023-11-28 00:32:45,513][87424] Updated weights for policy 0, policy_version 12826 (0.0010) -[2023-11-28 00:32:47,281][87424] Updated weights for policy 0, policy_version 12836 (0.0011) -[2023-11-28 00:32:47,413][87426] Updated weights for policy 1, policy_version 12770 (0.0011) -[2023-11-28 00:32:47,671][87424] Updated weights for policy 0, policy_version 12846 (0.0012) -[2023-11-28 00:32:47,798][87426] Updated weights for policy 1, policy_version 12780 (0.0008) -[2023-11-28 00:32:48,072][87424] Updated weights for policy 0, policy_version 12856 (0.0011) -[2023-11-28 00:32:48,190][87426] Updated weights for policy 1, policy_version 12790 (0.0007) -[2023-11-28 00:32:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.9). Total num frames: 6561792. Throughput: 0: 2695.7, 1: 2710.1. Samples: 6572624. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 00:32:48,445][86177] Avg episode reward: [(0, '-567.220'), (1, '-579.010')] -[2023-11-28 00:32:48,571][87426] Updated weights for policy 1, policy_version 12800 (0.0008) -[2023-11-28 00:32:50,479][87424] Updated weights for policy 0, policy_version 12866 (0.0010) -[2023-11-28 00:32:50,614][87426] Updated weights for policy 1, policy_version 12810 (0.0008) -[2023-11-28 00:32:50,853][87424] Updated weights for policy 0, policy_version 12876 (0.0008) -[2023-11-28 00:32:50,997][87426] Updated weights for policy 1, policy_version 12820 (0.0008) -[2023-11-28 00:32:51,239][87424] Updated weights for policy 0, policy_version 12886 (0.0009) -[2023-11-28 00:32:51,377][87426] Updated weights for policy 1, policy_version 12830 (0.0009) -[2023-11-28 00:32:51,621][87424] Updated weights for policy 0, policy_version 12896 (0.0011) -[2023-11-28 00:32:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 6586368. Throughput: 0: 2694.6, 1: 2707.1. Samples: 6605600. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 00:32:53,445][86177] Avg episode reward: [(0, '-562.360'), (1, '-582.090')] -[2023-11-28 00:32:53,769][87426] Updated weights for policy 1, policy_version 12840 (0.0011) -[2023-11-28 00:32:53,799][87424] Updated weights for policy 0, policy_version 12906 (0.0012) -[2023-11-28 00:32:54,148][87426] Updated weights for policy 1, policy_version 12850 (0.0011) -[2023-11-28 00:32:54,192][87424] Updated weights for policy 0, policy_version 12916 (0.0010) -[2023-11-28 00:32:54,516][87426] Updated weights for policy 1, policy_version 12860 (0.0009) -[2023-11-28 00:32:54,572][87424] Updated weights for policy 0, policy_version 12926 (0.0008) -[2023-11-28 00:32:56,350][87424] Updated weights for policy 0, policy_version 12936 (0.0009) -[2023-11-28 00:32:56,731][87424] Updated weights for policy 0, policy_version 12946 (0.0008) -[2023-11-28 00:32:57,120][87424] Updated weights for policy 0, policy_version 12956 (0.0007) -[2023-11-28 00:32:57,159][87426] Updated weights for policy 1, policy_version 12870 (0.0010) -[2023-11-28 00:32:57,543][87426] Updated weights for policy 1, policy_version 12880 (0.0008) -[2023-11-28 00:32:57,924][87426] Updated weights for policy 1, policy_version 12890 (0.0008) -[2023-11-28 00:32:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6619136. Throughput: 0: 2712.9, 1: 2696.0. Samples: 6630216. Policy #0 lag: (min: 20.0, avg: 39.0, max: 65.0) -[2023-11-28 00:32:58,445][86177] Avg episode reward: [(0, '-555.580'), (1, '-573.290')] -[2023-11-28 00:32:58,750][87424] Updated weights for policy 0, policy_version 12966 (0.0008) -[2023-11-28 00:32:59,135][87424] Updated weights for policy 0, policy_version 12976 (0.0008) -[2023-11-28 00:32:59,520][87424] Updated weights for policy 0, policy_version 12986 (0.0007) -[2023-11-28 00:33:00,139][87426] Updated weights for policy 1, policy_version 12900 (0.0010) -[2023-11-28 00:33:00,517][87426] Updated weights for policy 1, policy_version 12910 (0.0011) -[2023-11-28 00:33:00,898][87426] Updated weights for policy 1, policy_version 12920 (0.0008) -[2023-11-28 00:33:01,645][87424] Updated weights for policy 0, policy_version 12996 (0.0009) -[2023-11-28 00:33:02,014][87424] Updated weights for policy 0, policy_version 13006 (0.0009) -[2023-11-28 00:33:02,401][87424] Updated weights for policy 0, policy_version 13016 (0.0011) -[2023-11-28 00:33:03,164][87426] Updated weights for policy 1, policy_version 12930 (0.0007) -[2023-11-28 00:33:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6643712. Throughput: 0: 2716.2, 1: 2710.0. Samples: 6655952. Policy #0 lag: (min: 20.0, avg: 39.0, max: 65.0) -[2023-11-28 00:33:03,445][86177] Avg episode reward: [(0, '-577.470'), (1, '-574.460')] -[2023-11-28 00:33:03,544][87426] Updated weights for policy 1, policy_version 12940 (0.0007) -[2023-11-28 00:33:03,931][87426] Updated weights for policy 1, policy_version 12950 (0.0007) -[2023-11-28 00:33:04,313][87426] Updated weights for policy 1, policy_version 12960 (0.0008) -[2023-11-28 00:33:04,787][87424] Updated weights for policy 0, policy_version 13026 (0.0012) -[2023-11-28 00:33:05,176][87424] Updated weights for policy 0, policy_version 13036 (0.0011) -[2023-11-28 00:33:05,552][87424] Updated weights for policy 0, policy_version 13046 (0.0011) -[2023-11-28 00:33:05,937][87424] Updated weights for policy 0, policy_version 13056 (0.0011) -[2023-11-28 00:33:06,675][87426] Updated weights for policy 1, policy_version 12970 (0.0012) -[2023-11-28 00:33:07,060][87426] Updated weights for policy 1, policy_version 12980 (0.0011) -[2023-11-28 00:33:07,434][87426] Updated weights for policy 1, policy_version 12990 (0.0012) -[2023-11-28 00:33:08,173][87424] Updated weights for policy 0, policy_version 13066 (0.0011) -[2023-11-28 00:33:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 6668288. Throughput: 0: 2730.8, 1: 2708.1. Samples: 6687632. Policy #0 lag: (min: 20.0, avg: 39.0, max: 65.0) -[2023-11-28 00:33:08,445][86177] Avg episode reward: [(0, '-568.460'), (1, '-587.890')] -[2023-11-28 00:33:08,553][87424] Updated weights for policy 0, policy_version 13076 (0.0012) -[2023-11-28 00:33:08,944][87424] Updated weights for policy 0, policy_version 13086 (0.0012) -[2023-11-28 00:33:09,209][87426] Updated weights for policy 1, policy_version 13000 (0.0012) -[2023-11-28 00:33:09,582][87426] Updated weights for policy 1, policy_version 13010 (0.0012) -[2023-11-28 00:33:09,971][87426] Updated weights for policy 1, policy_version 13020 (0.0010) -[2023-11-28 00:33:10,990][87424] Updated weights for policy 0, policy_version 13096 (0.0011) -[2023-11-28 00:33:11,370][87424] Updated weights for policy 0, policy_version 13106 (0.0012) -[2023-11-28 00:33:11,753][87424] Updated weights for policy 0, policy_version 13116 (0.0010) -[2023-11-28 00:33:12,421][87426] Updated weights for policy 1, policy_version 13030 (0.0010) -[2023-11-28 00:33:12,790][87426] Updated weights for policy 1, policy_version 13040 (0.0012) -[2023-11-28 00:33:13,178][87426] Updated weights for policy 1, policy_version 13050 (0.0012) -[2023-11-28 00:33:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6701056. Throughput: 0: 2744.8, 1: 2688.1. Samples: 6711400. Policy #0 lag: (min: 5.0, avg: 14.6, max: 37.0) -[2023-11-28 00:33:13,445][86177] Avg episode reward: [(0, '-589.510'), (1, '-584.560')] -[2023-11-28 00:33:14,185][87424] Updated weights for policy 0, policy_version 13126 (0.0012) -[2023-11-28 00:33:14,568][87424] Updated weights for policy 0, policy_version 13136 (0.0012) -[2023-11-28 00:33:14,952][87424] Updated weights for policy 0, policy_version 13146 (0.0008) -[2023-11-28 00:33:15,107][87426] Updated weights for policy 1, policy_version 13060 (0.0011) -[2023-11-28 00:33:15,476][87426] Updated weights for policy 1, policy_version 13070 (0.0010) -[2023-11-28 00:33:15,867][87426] Updated weights for policy 1, policy_version 13080 (0.0010) -[2023-11-28 00:33:16,952][87424] Updated weights for policy 0, policy_version 13156 (0.0009) -[2023-11-28 00:33:17,336][87424] Updated weights for policy 0, policy_version 13166 (0.0008) -[2023-11-28 00:33:17,718][87424] Updated weights for policy 0, policy_version 13176 (0.0010) -[2023-11-28 00:33:18,038][87426] Updated weights for policy 1, policy_version 13090 (0.0009) -[2023-11-28 00:33:18,416][87426] Updated weights for policy 1, policy_version 13100 (0.0011) -[2023-11-28 00:33:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6725632. Throughput: 0: 2758.0, 1: 2679.4. Samples: 6736152. Policy #0 lag: (min: 5.0, avg: 14.6, max: 37.0) -[2023-11-28 00:33:18,445][86177] Avg episode reward: [(0, '-595.070'), (1, '-568.050')] -[2023-11-28 00:33:18,797][87426] Updated weights for policy 1, policy_version 13110 (0.0008) -[2023-11-28 00:33:19,176][87426] Updated weights for policy 1, policy_version 13120 (0.0007) -[2023-11-28 00:33:19,414][87424] Updated weights for policy 0, policy_version 13186 (0.0010) -[2023-11-28 00:33:19,803][87424] Updated weights for policy 0, policy_version 13196 (0.0012) -[2023-11-28 00:33:20,187][87424] Updated weights for policy 0, policy_version 13206 (0.0012) -[2023-11-28 00:33:20,568][87424] Updated weights for policy 0, policy_version 13216 (0.0012) -[2023-11-28 00:33:21,247][87426] Updated weights for policy 1, policy_version 13130 (0.0011) -[2023-11-28 00:33:21,642][87426] Updated weights for policy 1, policy_version 13140 (0.0011) -[2023-11-28 00:33:22,026][87426] Updated weights for policy 1, policy_version 13150 (0.0012) -[2023-11-28 00:33:22,840][87424] Updated weights for policy 0, policy_version 13226 (0.0011) -[2023-11-28 00:33:23,235][87424] Updated weights for policy 0, policy_version 13236 (0.0012) -[2023-11-28 00:33:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 6750208. Throughput: 0: 2769.4, 1: 2690.5. Samples: 6769732. Policy #0 lag: (min: 14.0, avg: 43.2, max: 75.0) -[2023-11-28 00:33:23,445][86177] Avg episode reward: [(0, '-594.100'), (1, '-562.780')] -[2023-11-28 00:33:23,608][87424] Updated weights for policy 0, policy_version 13246 (0.0012) -[2023-11-28 00:33:24,002][87426] Updated weights for policy 1, policy_version 13160 (0.0012) -[2023-11-28 00:33:24,380][87426] Updated weights for policy 1, policy_version 13170 (0.0012) -[2023-11-28 00:33:24,750][87426] Updated weights for policy 1, policy_version 13180 (0.0011) -[2023-11-28 00:33:26,115][87424] Updated weights for policy 0, policy_version 13256 (0.0011) -[2023-11-28 00:33:26,500][87424] Updated weights for policy 0, policy_version 13266 (0.0011) -[2023-11-28 00:33:26,882][87424] Updated weights for policy 0, policy_version 13276 (0.0011) -[2023-11-28 00:33:27,194][87426] Updated weights for policy 1, policy_version 13190 (0.0012) -[2023-11-28 00:33:27,568][87426] Updated weights for policy 1, policy_version 13200 (0.0012) -[2023-11-28 00:33:27,950][87426] Updated weights for policy 1, policy_version 13210 (0.0011) -[2023-11-28 00:33:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6782976. Throughput: 0: 2779.8, 1: 2708.5. Samples: 6794004. Policy #0 lag: (min: 14.0, avg: 43.2, max: 75.0) -[2023-11-28 00:33:28,445][86177] Avg episode reward: [(0, '-573.670'), (1, '-538.440')] -[2023-11-28 00:33:28,834][87424] Updated weights for policy 0, policy_version 13286 (0.0008) -[2023-11-28 00:33:29,222][87424] Updated weights for policy 0, policy_version 13296 (0.0011) -[2023-11-28 00:33:29,590][87424] Updated weights for policy 0, policy_version 13306 (0.0011) -[2023-11-28 00:33:30,243][87426] Updated weights for policy 1, policy_version 13220 (0.0012) -[2023-11-28 00:33:30,630][87426] Updated weights for policy 1, policy_version 13230 (0.0008) -[2023-11-28 00:33:31,019][87426] Updated weights for policy 1, policy_version 13240 (0.0011) -[2023-11-28 00:33:31,992][87424] Updated weights for policy 0, policy_version 13316 (0.0011) -[2023-11-28 00:33:32,375][87424] Updated weights for policy 0, policy_version 13326 (0.0009) -[2023-11-28 00:33:32,755][87424] Updated weights for policy 0, policy_version 13336 (0.0011) -[2023-11-28 00:33:32,913][87426] Updated weights for policy 1, policy_version 13250 (0.0011) -[2023-11-28 00:33:33,299][87426] Updated weights for policy 1, policy_version 13260 (0.0007) -[2023-11-28 00:33:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 6807552. Throughput: 0: 2786.8, 1: 2696.1. Samples: 6819352. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 00:33:33,445][86177] Avg episode reward: [(0, '-607.990'), (1, '-542.500')] -[2023-11-28 00:33:33,678][87426] Updated weights for policy 1, policy_version 13270 (0.0007) -[2023-11-28 00:33:34,052][87426] Updated weights for policy 1, policy_version 13280 (0.0007) -[2023-11-28 00:33:34,779][87424] Updated weights for policy 0, policy_version 13346 (0.0012) -[2023-11-28 00:33:35,160][87424] Updated weights for policy 0, policy_version 13356 (0.0012) -[2023-11-28 00:33:35,542][87424] Updated weights for policy 0, policy_version 13366 (0.0012) -[2023-11-28 00:33:35,925][87424] Updated weights for policy 0, policy_version 13376 (0.0012) -[2023-11-28 00:33:36,134][87426] Updated weights for policy 1, policy_version 13290 (0.0008) -[2023-11-28 00:33:36,511][87426] Updated weights for policy 1, policy_version 13300 (0.0008) -[2023-11-28 00:33:36,891][87426] Updated weights for policy 1, policy_version 13310 (0.0011) -[2023-11-28 00:33:37,948][87424] Updated weights for policy 0, policy_version 13386 (0.0012) -[2023-11-28 00:33:38,320][87424] Updated weights for policy 0, policy_version 13396 (0.0012) -[2023-11-28 00:33:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 6832128. Throughput: 0: 2798.0, 1: 2685.1. Samples: 6852340. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 00:33:38,446][86177] Avg episode reward: [(0, '-575.430'), (1, '-542.660')] -[2023-11-28 00:33:38,706][87424] Updated weights for policy 0, policy_version 13406 (0.0012) -[2023-11-28 00:33:39,431][87426] Updated weights for policy 1, policy_version 13320 (0.0012) -[2023-11-28 00:33:39,811][87426] Updated weights for policy 1, policy_version 13330 (0.0011) -[2023-11-28 00:33:40,194][87426] Updated weights for policy 1, policy_version 13340 (0.0012) -[2023-11-28 00:33:41,037][87424] Updated weights for policy 0, policy_version 13416 (0.0009) -[2023-11-28 00:33:41,431][87424] Updated weights for policy 0, policy_version 13426 (0.0010) -[2023-11-28 00:33:41,799][87424] Updated weights for policy 0, policy_version 13436 (0.0012) -[2023-11-28 00:33:42,646][87426] Updated weights for policy 1, policy_version 13350 (0.0011) -[2023-11-28 00:33:43,027][87426] Updated weights for policy 1, policy_version 13360 (0.0010) -[2023-11-28 00:33:43,407][87426] Updated weights for policy 1, policy_version 13370 (0.0010) -[2023-11-28 00:33:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 6856704. Throughput: 0: 2770.1, 1: 2692.9. Samples: 6876052. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 00:33:43,445][86177] Avg episode reward: [(0, '-591.520'), (1, '-561.390')] -[2023-11-28 00:33:43,793][87424] Updated weights for policy 0, policy_version 13446 (0.0011) -[2023-11-28 00:33:44,172][87424] Updated weights for policy 0, policy_version 13456 (0.0011) -[2023-11-28 00:33:44,563][87424] Updated weights for policy 0, policy_version 13466 (0.0011) -[2023-11-28 00:33:45,253][87426] Updated weights for policy 1, policy_version 13380 (0.0009) -[2023-11-28 00:33:45,624][87426] Updated weights for policy 1, policy_version 13390 (0.0012) -[2023-11-28 00:33:46,007][87426] Updated weights for policy 1, policy_version 13400 (0.0012) -[2023-11-28 00:33:46,433][87424] Updated weights for policy 0, policy_version 13476 (0.0010) -[2023-11-28 00:33:46,821][87424] Updated weights for policy 0, policy_version 13486 (0.0009) -[2023-11-28 00:33:47,194][87424] Updated weights for policy 0, policy_version 13496 (0.0010) -[2023-11-28 00:33:48,300][87426] Updated weights for policy 1, policy_version 13410 (0.0011) -[2023-11-28 00:33:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6889472. Throughput: 0: 2756.4, 1: 2690.9. Samples: 6901084. Policy #0 lag: (min: 2.0, avg: 31.7, max: 54.0) -[2023-11-28 00:33:48,445][86177] Avg episode reward: [(0, '-591.610'), (1, '-560.330')] -[2023-11-28 00:33:48,674][87426] Updated weights for policy 1, policy_version 13420 (0.0012) -[2023-11-28 00:33:49,062][87426] Updated weights for policy 1, policy_version 13430 (0.0011) -[2023-11-28 00:33:49,434][87426] Updated weights for policy 1, policy_version 13440 (0.0012) -[2023-11-28 00:33:49,443][87424] Updated weights for policy 0, policy_version 13506 (0.0008) -[2023-11-28 00:33:49,830][87424] Updated weights for policy 0, policy_version 13516 (0.0012) -[2023-11-28 00:33:50,204][87424] Updated weights for policy 0, policy_version 13526 (0.0012) -[2023-11-28 00:33:50,581][87424] Updated weights for policy 0, policy_version 13536 (0.0012) -[2023-11-28 00:33:51,376][87426] Updated weights for policy 1, policy_version 13450 (0.0012) -[2023-11-28 00:33:51,756][87426] Updated weights for policy 1, policy_version 13460 (0.0012) -[2023-11-28 00:33:52,122][87426] Updated weights for policy 1, policy_version 13470 (0.0012) -[2023-11-28 00:33:52,874][87424] Updated weights for policy 0, policy_version 13546 (0.0012) -[2023-11-28 00:33:53,257][87424] Updated weights for policy 0, policy_version 13556 (0.0012) -[2023-11-28 00:33:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 6914048. Throughput: 0: 2765.9, 1: 2722.2. Samples: 6934596. Policy #0 lag: (min: 2.0, avg: 31.7, max: 54.0) -[2023-11-28 00:33:53,445][86177] Avg episode reward: [(0, '-615.560'), (1, '-563.510')] -[2023-11-28 00:33:53,642][87424] Updated weights for policy 0, policy_version 13566 (0.0012) -[2023-11-28 00:33:54,419][87426] Updated weights for policy 1, policy_version 13480 (0.0009) -[2023-11-28 00:33:54,802][87426] Updated weights for policy 1, policy_version 13490 (0.0008) -[2023-11-28 00:33:55,184][87426] Updated weights for policy 1, policy_version 13500 (0.0008) -[2023-11-28 00:33:55,838][87424] Updated weights for policy 0, policy_version 13576 (0.0012) -[2023-11-28 00:33:56,212][87424] Updated weights for policy 0, policy_version 13586 (0.0012) -[2023-11-28 00:33:56,594][87424] Updated weights for policy 0, policy_version 13596 (0.0012) -[2023-11-28 00:33:57,116][87426] Updated weights for policy 1, policy_version 13510 (0.0011) -[2023-11-28 00:33:57,492][87426] Updated weights for policy 1, policy_version 13520 (0.0011) -[2023-11-28 00:33:57,871][87426] Updated weights for policy 1, policy_version 13530 (0.0012) -[2023-11-28 00:33:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 6946816. Throughput: 0: 2770.3, 1: 2746.9. Samples: 6959676. Policy #0 lag: (min: 31.0, avg: 53.8, max: 95.0) -[2023-11-28 00:33:58,445][86177] Avg episode reward: [(0, '-610.840'), (1, '-553.630')] -[2023-11-28 00:33:58,547][87424] Updated weights for policy 0, policy_version 13606 (0.0010) -[2023-11-28 00:33:58,932][87424] Updated weights for policy 0, policy_version 13616 (0.0008) -[2023-11-28 00:33:59,324][87424] Updated weights for policy 0, policy_version 13626 (0.0011) -[2023-11-28 00:34:00,167][87426] Updated weights for policy 1, policy_version 13540 (0.0010) -[2023-11-28 00:34:00,535][87426] Updated weights for policy 1, policy_version 13550 (0.0009) -[2023-11-28 00:34:00,915][87426] Updated weights for policy 1, policy_version 13560 (0.0010) -[2023-11-28 00:34:01,538][87424] Updated weights for policy 0, policy_version 13636 (0.0010) -[2023-11-28 00:34:01,931][87424] Updated weights for policy 0, policy_version 13646 (0.0011) -[2023-11-28 00:34:02,310][87424] Updated weights for policy 0, policy_version 13656 (0.0012) -[2023-11-28 00:34:02,845][87426] Updated weights for policy 1, policy_version 13570 (0.0011) -[2023-11-28 00:34:03,223][87426] Updated weights for policy 1, policy_version 13580 (0.0009) -[2023-11-28 00:34:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 6971392. Throughput: 0: 2784.0, 1: 2762.1. Samples: 6985728. Policy #0 lag: (min: 31.0, avg: 53.8, max: 95.0) -[2023-11-28 00:34:03,445][86177] Avg episode reward: [(0, '-594.190'), (1, '-538.190')] -[2023-11-28 00:34:03,599][87426] Updated weights for policy 1, policy_version 13590 (0.0008) -[2023-11-28 00:34:03,980][87426] Updated weights for policy 1, policy_version 13600 (0.0009) -[2023-11-28 00:34:04,060][87424] Updated weights for policy 0, policy_version 13666 (0.0008) -[2023-11-28 00:34:04,443][87424] Updated weights for policy 0, policy_version 13676 (0.0008) -[2023-11-28 00:34:04,826][87424] Updated weights for policy 0, policy_version 13686 (0.0008) -[2023-11-28 00:34:05,208][87424] Updated weights for policy 0, policy_version 13696 (0.0008) -[2023-11-28 00:34:06,089][87426] Updated weights for policy 1, policy_version 13610 (0.0012) -[2023-11-28 00:34:06,469][87426] Updated weights for policy 1, policy_version 13620 (0.0012) -[2023-11-28 00:34:06,844][87426] Updated weights for policy 1, policy_version 13630 (0.0012) -[2023-11-28 00:34:07,522][87424] Updated weights for policy 0, policy_version 13706 (0.0012) -[2023-11-28 00:34:07,902][87424] Updated weights for policy 0, policy_version 13716 (0.0011) -[2023-11-28 00:34:08,282][87424] Updated weights for policy 0, policy_version 13726 (0.0012) -[2023-11-28 00:34:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 7004160. Throughput: 0: 2784.1, 1: 2744.2. Samples: 7018504. Policy #0 lag: (min: 2.0, avg: 26.3, max: 59.0) -[2023-11-28 00:34:08,445][86177] Avg episode reward: [(0, '-593.830'), (1, '-535.930')] -[2023-11-28 00:34:09,011][87426] Updated weights for policy 1, policy_version 13640 (0.0012) -[2023-11-28 00:34:09,397][87426] Updated weights for policy 1, policy_version 13650 (0.0012) -[2023-11-28 00:34:09,773][87426] Updated weights for policy 1, policy_version 13660 (0.0012) -[2023-11-28 00:34:10,155][87424] Updated weights for policy 0, policy_version 13736 (0.0012) -[2023-11-28 00:34:10,538][87424] Updated weights for policy 0, policy_version 13746 (0.0012) -[2023-11-28 00:34:10,925][87424] Updated weights for policy 0, policy_version 13756 (0.0011) -[2023-11-28 00:34:12,274][87426] Updated weights for policy 1, policy_version 13670 (0.0010) -[2023-11-28 00:34:12,640][87426] Updated weights for policy 1, policy_version 13680 (0.0010) -[2023-11-28 00:34:12,866][87424] Updated weights for policy 0, policy_version 13766 (0.0011) -[2023-11-28 00:34:13,026][87426] Updated weights for policy 1, policy_version 13690 (0.0011) -[2023-11-28 00:34:13,258][87424] Updated weights for policy 0, policy_version 13776 (0.0010) -[2023-11-28 00:34:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 7028736. Throughput: 0: 2788.3, 1: 2737.8. Samples: 7042676. Policy #0 lag: (min: 2.0, avg: 26.3, max: 59.0) -[2023-11-28 00:34:13,445][86177] Avg episode reward: [(0, '-540.310'), (1, '-519.870')] -[2023-11-28 00:34:13,639][87424] Updated weights for policy 0, policy_version 13786 (0.0007) -[2023-11-28 00:34:13,870][87281] Saving new best policy, reward=-540.310! -[2023-11-28 00:34:15,557][87426] Updated weights for policy 1, policy_version 13700 (0.0010) -[2023-11-28 00:34:15,937][87426] Updated weights for policy 1, policy_version 13710 (0.0011) -[2023-11-28 00:34:16,135][87424] Updated weights for policy 0, policy_version 13796 (0.0008) -[2023-11-28 00:34:16,328][87426] Updated weights for policy 1, policy_version 13720 (0.0009) -[2023-11-28 00:34:16,515][87424] Updated weights for policy 0, policy_version 13806 (0.0010) -[2023-11-28 00:34:16,892][87424] Updated weights for policy 0, policy_version 13816 (0.0011) -[2023-11-28 00:34:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7053312. Throughput: 0: 2779.3, 1: 2718.9. Samples: 7066772. Policy #0 lag: (min: 2.0, avg: 26.3, max: 59.0) -[2023-11-28 00:34:18,446][86177] Avg episode reward: [(0, '-583.480'), (1, '-537.040')] -[2023-11-28 00:34:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000013728_3514368.pth... -[2023-11-28 00:34:18,460][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000013824_3538944.pth... -[2023-11-28 00:34:18,494][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000011264_2883584.pth -[2023-11-28 00:34:18,497][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000011232_2875392.pth -[2023-11-28 00:34:18,795][87424] Updated weights for policy 0, policy_version 13826 (0.0008) -[2023-11-28 00:34:18,880][87426] Updated weights for policy 1, policy_version 13730 (0.0009) -[2023-11-28 00:34:19,178][87424] Updated weights for policy 0, policy_version 13836 (0.0012) -[2023-11-28 00:34:19,258][87426] Updated weights for policy 1, policy_version 13740 (0.0011) -[2023-11-28 00:34:19,555][87424] Updated weights for policy 0, policy_version 13846 (0.0009) -[2023-11-28 00:34:19,636][87426] Updated weights for policy 1, policy_version 13750 (0.0010) -[2023-11-28 00:34:19,939][87424] Updated weights for policy 0, policy_version 13856 (0.0008) -[2023-11-28 00:34:20,024][87426] Updated weights for policy 1, policy_version 13760 (0.0012) -[2023-11-28 00:34:21,797][87426] Updated weights for policy 1, policy_version 13770 (0.0012) -[2023-11-28 00:34:22,174][87426] Updated weights for policy 1, policy_version 13780 (0.0011) -[2023-11-28 00:34:22,271][87424] Updated weights for policy 0, policy_version 13866 (0.0011) -[2023-11-28 00:34:22,551][87426] Updated weights for policy 1, policy_version 13790 (0.0012) -[2023-11-28 00:34:22,647][87424] Updated weights for policy 0, policy_version 13876 (0.0011) -[2023-11-28 00:34:23,027][87424] Updated weights for policy 0, policy_version 13886 (0.0011) -[2023-11-28 00:34:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 7086080. Throughput: 0: 2768.4, 1: 2727.5. Samples: 7099652. Policy #0 lag: (min: 6.0, avg: 11.5, max: 37.0) -[2023-11-28 00:34:23,445][86177] Avg episode reward: [(0, '-581.420'), (1, '-532.820')] -[2023-11-28 00:34:24,666][87426] Updated weights for policy 1, policy_version 13800 (0.0010) -[2023-11-28 00:34:24,949][87424] Updated weights for policy 0, policy_version 13896 (0.0010) -[2023-11-28 00:34:25,051][87426] Updated weights for policy 1, policy_version 13810 (0.0011) -[2023-11-28 00:34:25,330][87424] Updated weights for policy 0, policy_version 13906 (0.0009) -[2023-11-28 00:34:25,424][87426] Updated weights for policy 1, policy_version 13820 (0.0009) -[2023-11-28 00:34:25,721][87424] Updated weights for policy 0, policy_version 13916 (0.0012) -[2023-11-28 00:34:27,785][87426] Updated weights for policy 1, policy_version 13830 (0.0008) -[2023-11-28 00:34:28,108][87424] Updated weights for policy 0, policy_version 13926 (0.0009) -[2023-11-28 00:34:28,153][87426] Updated weights for policy 1, policy_version 13840 (0.0009) -[2023-11-28 00:34:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 7102464. Throughput: 0: 2772.8, 1: 2747.0. Samples: 7124444. Policy #0 lag: (min: 6.0, avg: 11.5, max: 37.0) -[2023-11-28 00:34:28,445][86177] Avg episode reward: [(0, '-575.560'), (1, '-563.970')] -[2023-11-28 00:34:28,501][87424] Updated weights for policy 0, policy_version 13936 (0.0007) -[2023-11-28 00:34:28,543][87426] Updated weights for policy 1, policy_version 13850 (0.0012) -[2023-11-28 00:34:28,890][87424] Updated weights for policy 0, policy_version 13946 (0.0008) -[2023-11-28 00:34:30,361][87426] Updated weights for policy 1, policy_version 13860 (0.0010) -[2023-11-28 00:34:30,740][87426] Updated weights for policy 1, policy_version 13870 (0.0011) -[2023-11-28 00:34:30,882][87424] Updated weights for policy 0, policy_version 13956 (0.0010) -[2023-11-28 00:34:31,119][87426] Updated weights for policy 1, policy_version 13880 (0.0011) -[2023-11-28 00:34:31,269][87424] Updated weights for policy 0, policy_version 13966 (0.0009) -[2023-11-28 00:34:31,655][87424] Updated weights for policy 0, policy_version 13976 (0.0008) -[2023-11-28 00:34:33,045][87426] Updated weights for policy 1, policy_version 13890 (0.0012) -[2023-11-28 00:34:33,296][87424] Updated weights for policy 0, policy_version 13986 (0.0011) -[2023-11-28 00:34:33,424][87426] Updated weights for policy 1, policy_version 13900 (0.0012) -[2023-11-28 00:34:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7135232. Throughput: 0: 2768.7, 1: 2743.2. Samples: 7149120. Policy #0 lag: (min: 47.0, avg: 57.6, max: 82.0) -[2023-11-28 00:34:33,445][86177] Avg episode reward: [(0, '-577.390'), (1, '-571.920')] -[2023-11-28 00:34:33,682][87424] Updated weights for policy 0, policy_version 13996 (0.0012) -[2023-11-28 00:34:33,817][87426] Updated weights for policy 1, policy_version 13910 (0.0010) -[2023-11-28 00:34:34,060][87424] Updated weights for policy 0, policy_version 14006 (0.0009) -[2023-11-28 00:34:34,198][87426] Updated weights for policy 1, policy_version 13920 (0.0007) -[2023-11-28 00:34:34,444][87424] Updated weights for policy 0, policy_version 14016 (0.0007) -[2023-11-28 00:34:36,482][87426] Updated weights for policy 1, policy_version 13930 (0.0010) -[2023-11-28 00:34:36,557][87424] Updated weights for policy 0, policy_version 14026 (0.0012) -[2023-11-28 00:34:36,857][87426] Updated weights for policy 1, policy_version 13940 (0.0010) -[2023-11-28 00:34:36,946][87424] Updated weights for policy 0, policy_version 14036 (0.0012) -[2023-11-28 00:34:37,239][87426] Updated weights for policy 1, policy_version 13950 (0.0007) -[2023-11-28 00:34:37,325][87424] Updated weights for policy 0, policy_version 14046 (0.0011) -[2023-11-28 00:34:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 7168000. Throughput: 0: 2773.3, 1: 2739.0. Samples: 7182652. Policy #0 lag: (min: 47.0, avg: 57.6, max: 82.0) -[2023-11-28 00:34:38,445][86177] Avg episode reward: [(0, '-573.700'), (1, '-606.430')] -[2023-11-28 00:34:39,094][87424] Updated weights for policy 0, policy_version 14056 (0.0011) -[2023-11-28 00:34:39,220][87426] Updated weights for policy 1, policy_version 13960 (0.0009) -[2023-11-28 00:34:39,479][87424] Updated weights for policy 0, policy_version 14066 (0.0011) -[2023-11-28 00:34:39,600][87426] Updated weights for policy 1, policy_version 13970 (0.0011) -[2023-11-28 00:34:39,869][87424] Updated weights for policy 0, policy_version 14076 (0.0011) -[2023-11-28 00:34:39,975][87426] Updated weights for policy 1, policy_version 13980 (0.0010) -[2023-11-28 00:34:41,977][87426] Updated weights for policy 1, policy_version 13990 (0.0010) -[2023-11-28 00:34:42,126][87424] Updated weights for policy 0, policy_version 14086 (0.0011) -[2023-11-28 00:34:42,354][87426] Updated weights for policy 1, policy_version 14000 (0.0014) -[2023-11-28 00:34:42,507][87424] Updated weights for policy 0, policy_version 14096 (0.0011) -[2023-11-28 00:34:42,735][87426] Updated weights for policy 1, policy_version 14010 (0.0012) -[2023-11-28 00:34:42,891][87424] Updated weights for policy 0, policy_version 14106 (0.0009) -[2023-11-28 00:34:43,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5734.4, 300 sec: 5498.4). Total num frames: 7200768. Throughput: 0: 2772.1, 1: 2746.2. Samples: 7208000. Policy #0 lag: (min: 17.0, avg: 44.9, max: 76.0) -[2023-11-28 00:34:43,445][86177] Avg episode reward: [(0, '-577.370'), (1, '-577.730')] -[2023-11-28 00:34:45,141][87426] Updated weights for policy 1, policy_version 14020 (0.0010) -[2023-11-28 00:34:45,394][87424] Updated weights for policy 0, policy_version 14116 (0.0011) -[2023-11-28 00:34:45,508][87426] Updated weights for policy 1, policy_version 14030 (0.0009) -[2023-11-28 00:34:45,776][87424] Updated weights for policy 0, policy_version 14126 (0.0009) -[2023-11-28 00:34:45,893][87426] Updated weights for policy 1, policy_version 14040 (0.0009) -[2023-11-28 00:34:46,164][87424] Updated weights for policy 0, policy_version 14136 (0.0011) -[2023-11-28 00:34:47,693][87426] Updated weights for policy 1, policy_version 14050 (0.0008) -[2023-11-28 00:34:48,070][87426] Updated weights for policy 1, policy_version 14060 (0.0012) -[2023-11-28 00:34:48,194][87424] Updated weights for policy 0, policy_version 14146 (0.0008) -[2023-11-28 00:34:48,441][87426] Updated weights for policy 1, policy_version 14070 (0.0009) -[2023-11-28 00:34:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7217152. Throughput: 0: 2731.6, 1: 2725.1. Samples: 7231276. Policy #0 lag: (min: 17.0, avg: 44.9, max: 76.0) -[2023-11-28 00:34:48,445][86177] Avg episode reward: [(0, '-580.450'), (1, '-564.120')] -[2023-11-28 00:34:48,576][87424] Updated weights for policy 0, policy_version 14156 (0.0008) -[2023-11-28 00:34:48,825][87426] Updated weights for policy 1, policy_version 14080 (0.0007) -[2023-11-28 00:34:48,968][87424] Updated weights for policy 0, policy_version 14166 (0.0008) -[2023-11-28 00:34:49,343][87424] Updated weights for policy 0, policy_version 14176 (0.0008) -[2023-11-28 00:34:50,841][87426] Updated weights for policy 1, policy_version 14090 (0.0007) -[2023-11-28 00:34:51,222][87426] Updated weights for policy 1, policy_version 14100 (0.0008) -[2023-11-28 00:34:51,600][87426] Updated weights for policy 1, policy_version 14110 (0.0011) -[2023-11-28 00:34:51,622][87424] Updated weights for policy 0, policy_version 14186 (0.0009) -[2023-11-28 00:34:52,011][87424] Updated weights for policy 0, policy_version 14196 (0.0010) -[2023-11-28 00:34:52,390][87424] Updated weights for policy 0, policy_version 14206 (0.0010) -[2023-11-28 00:34:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 7249920. Throughput: 0: 2724.4, 1: 2732.6. Samples: 7264072. Policy #0 lag: (min: 17.0, avg: 44.9, max: 76.0) -[2023-11-28 00:34:53,445][86177] Avg episode reward: [(0, '-574.460'), (1, '-563.540')] -[2023-11-28 00:34:54,026][87426] Updated weights for policy 1, policy_version 14120 (0.0010) -[2023-11-28 00:34:54,407][87426] Updated weights for policy 1, policy_version 14130 (0.0007) -[2023-11-28 00:34:54,792][87426] Updated weights for policy 1, policy_version 14140 (0.0008) -[2023-11-28 00:34:54,805][87424] Updated weights for policy 0, policy_version 14216 (0.0010) -[2023-11-28 00:34:55,191][87424] Updated weights for policy 0, policy_version 14226 (0.0012) -[2023-11-28 00:34:55,573][87424] Updated weights for policy 0, policy_version 14236 (0.0012) -[2023-11-28 00:34:57,202][87426] Updated weights for policy 1, policy_version 14150 (0.0009) -[2023-11-28 00:34:57,569][87426] Updated weights for policy 1, policy_version 14160 (0.0009) -[2023-11-28 00:34:57,949][87426] Updated weights for policy 1, policy_version 14170 (0.0010) -[2023-11-28 00:34:57,966][87424] Updated weights for policy 0, policy_version 14246 (0.0012) -[2023-11-28 00:34:58,341][87424] Updated weights for policy 0, policy_version 14256 (0.0011) -[2023-11-28 00:34:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 7274496. Throughput: 0: 2714.3, 1: 2715.1. Samples: 7287000. Policy #0 lag: (min: 2.0, avg: 15.8, max: 34.0) -[2023-11-28 00:34:58,445][86177] Avg episode reward: [(0, '-536.180'), (1, '-508.270')] -[2023-11-28 00:34:58,445][87320] Saving new best policy, reward=-508.270! -[2023-11-28 00:34:58,721][87424] Updated weights for policy 0, policy_version 14266 (0.0011) -[2023-11-28 00:34:58,945][87281] Saving new best policy, reward=-536.180! -[2023-11-28 00:35:00,438][87426] Updated weights for policy 1, policy_version 14180 (0.0009) -[2023-11-28 00:35:00,827][87426] Updated weights for policy 1, policy_version 14190 (0.0011) -[2023-11-28 00:35:01,007][87424] Updated weights for policy 0, policy_version 14276 (0.0010) -[2023-11-28 00:35:01,211][87426] Updated weights for policy 1, policy_version 14200 (0.0009) -[2023-11-28 00:35:01,394][87424] Updated weights for policy 0, policy_version 14286 (0.0010) -[2023-11-28 00:35:01,768][87424] Updated weights for policy 0, policy_version 14296 (0.0009) -[2023-11-28 00:35:03,071][87426] Updated weights for policy 1, policy_version 14210 (0.0010) -[2023-11-28 00:35:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7299072. Throughput: 0: 2696.8, 1: 2728.5. Samples: 7310908. Policy #0 lag: (min: 2.0, avg: 15.8, max: 34.0) -[2023-11-28 00:35:03,445][86177] Avg episode reward: [(0, '-576.550'), (1, '-499.420')] -[2023-11-28 00:35:03,461][87426] Updated weights for policy 1, policy_version 14220 (0.0012) -[2023-11-28 00:35:03,837][87426] Updated weights for policy 1, policy_version 14230 (0.0011) -[2023-11-28 00:35:03,886][87424] Updated weights for policy 0, policy_version 14306 (0.0011) -[2023-11-28 00:35:04,219][87320] Saving new best policy, reward=-499.420! -[2023-11-28 00:35:04,225][87426] Updated weights for policy 1, policy_version 14240 (0.0011) -[2023-11-28 00:35:04,275][87424] Updated weights for policy 0, policy_version 14316 (0.0009) -[2023-11-28 00:35:04,662][87424] Updated weights for policy 0, policy_version 14326 (0.0011) -[2023-11-28 00:35:05,048][87424] Updated weights for policy 0, policy_version 14336 (0.0012) -[2023-11-28 00:35:06,395][87426] Updated weights for policy 1, policy_version 14250 (0.0012) -[2023-11-28 00:35:06,777][87426] Updated weights for policy 1, policy_version 14260 (0.0011) -[2023-11-28 00:35:07,152][87426] Updated weights for policy 1, policy_version 14270 (0.0012) -[2023-11-28 00:35:07,314][87424] Updated weights for policy 0, policy_version 14346 (0.0011) -[2023-11-28 00:35:07,698][87424] Updated weights for policy 0, policy_version 14356 (0.0012) -[2023-11-28 00:35:08,084][87424] Updated weights for policy 0, policy_version 14366 (0.0012) -[2023-11-28 00:35:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7331840. Throughput: 0: 2697.4, 1: 2737.2. Samples: 7344212. Policy #0 lag: (min: 27.0, avg: 42.2, max: 59.0) -[2023-11-28 00:35:08,445][86177] Avg episode reward: [(0, '-573.190'), (1, '-501.270')] -[2023-11-28 00:35:09,098][87426] Updated weights for policy 1, policy_version 14280 (0.0008) -[2023-11-28 00:35:09,483][87426] Updated weights for policy 1, policy_version 14290 (0.0008) -[2023-11-28 00:35:09,857][87426] Updated weights for policy 1, policy_version 14300 (0.0010) -[2023-11-28 00:35:10,448][87424] Updated weights for policy 0, policy_version 14376 (0.0010) -[2023-11-28 00:35:10,829][87424] Updated weights for policy 0, policy_version 14386 (0.0008) -[2023-11-28 00:35:11,212][87424] Updated weights for policy 0, policy_version 14396 (0.0010) -[2023-11-28 00:35:12,332][87426] Updated weights for policy 1, policy_version 14310 (0.0012) -[2023-11-28 00:35:12,701][87426] Updated weights for policy 1, policy_version 14320 (0.0011) -[2023-11-28 00:35:13,080][87426] Updated weights for policy 1, policy_version 14330 (0.0011) -[2023-11-28 00:35:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 7356416. Throughput: 0: 2688.3, 1: 2742.1. Samples: 7368812. Policy #0 lag: (min: 27.0, avg: 42.2, max: 59.0) -[2023-11-28 00:35:13,445][86177] Avg episode reward: [(0, '-581.700'), (1, '-502.560')] -[2023-11-28 00:35:13,767][87424] Updated weights for policy 0, policy_version 14406 (0.0010) -[2023-11-28 00:35:14,147][87424] Updated weights for policy 0, policy_version 14416 (0.0012) -[2023-11-28 00:35:14,532][87424] Updated weights for policy 0, policy_version 14426 (0.0012) -[2023-11-28 00:35:15,502][87426] Updated weights for policy 1, policy_version 14340 (0.0011) -[2023-11-28 00:35:15,877][87426] Updated weights for policy 1, policy_version 14350 (0.0012) -[2023-11-28 00:35:16,261][87426] Updated weights for policy 1, policy_version 14360 (0.0012) -[2023-11-28 00:35:16,729][87424] Updated weights for policy 0, policy_version 14436 (0.0010) -[2023-11-28 00:35:17,113][87424] Updated weights for policy 0, policy_version 14446 (0.0007) -[2023-11-28 00:35:17,497][87424] Updated weights for policy 0, policy_version 14456 (0.0007) -[2023-11-28 00:35:18,286][87426] Updated weights for policy 1, policy_version 14370 (0.0012) -[2023-11-28 00:35:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 7380992. Throughput: 0: 2675.5, 1: 2731.6. Samples: 7392436. Policy #0 lag: (min: 27.0, avg: 42.2, max: 59.0) -[2023-11-28 00:35:18,445][86177] Avg episode reward: [(0, '-598.040'), (1, '-503.790')] -[2023-11-28 00:35:18,660][87426] Updated weights for policy 1, policy_version 14380 (0.0012) -[2023-11-28 00:35:19,040][87426] Updated weights for policy 1, policy_version 14390 (0.0011) -[2023-11-28 00:35:19,417][87426] Updated weights for policy 1, policy_version 14400 (0.0011) -[2023-11-28 00:35:19,705][87424] Updated weights for policy 0, policy_version 14466 (0.0008) -[2023-11-28 00:35:20,081][87424] Updated weights for policy 0, policy_version 14476 (0.0011) -[2023-11-28 00:35:20,470][87424] Updated weights for policy 0, policy_version 14486 (0.0011) -[2023-11-28 00:35:20,853][87424] Updated weights for policy 0, policy_version 14496 (0.0012) -[2023-11-28 00:35:21,779][87426] Updated weights for policy 1, policy_version 14410 (0.0012) -[2023-11-28 00:35:22,159][87426] Updated weights for policy 1, policy_version 14420 (0.0012) -[2023-11-28 00:35:22,531][87426] Updated weights for policy 1, policy_version 14430 (0.0012) -[2023-11-28 00:35:23,125][87424] Updated weights for policy 0, policy_version 14506 (0.0009) -[2023-11-28 00:35:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 7405568. Throughput: 0: 2674.4, 1: 2713.2. Samples: 7425092. Policy #0 lag: (min: 31.0, avg: 48.7, max: 63.0) -[2023-11-28 00:35:23,445][86177] Avg episode reward: [(0, '-554.860'), (1, '-505.810')] -[2023-11-28 00:35:23,516][87424] Updated weights for policy 0, policy_version 14516 (0.0009) -[2023-11-28 00:35:23,895][87424] Updated weights for policy 0, policy_version 14526 (0.0011) -[2023-11-28 00:35:24,842][87426] Updated weights for policy 1, policy_version 14440 (0.0010) -[2023-11-28 00:35:25,229][87426] Updated weights for policy 1, policy_version 14450 (0.0009) -[2023-11-28 00:35:25,600][87424] Updated weights for policy 0, policy_version 14536 (0.0011) -[2023-11-28 00:35:25,608][87426] Updated weights for policy 1, policy_version 14460 (0.0009) -[2023-11-28 00:35:25,984][87424] Updated weights for policy 0, policy_version 14546 (0.0011) -[2023-11-28 00:35:26,372][87424] Updated weights for policy 0, policy_version 14556 (0.0012) -[2023-11-28 00:35:27,359][87426] Updated weights for policy 1, policy_version 14470 (0.0011) -[2023-11-28 00:35:27,734][87426] Updated weights for policy 1, policy_version 14480 (0.0012) -[2023-11-28 00:35:28,123][87426] Updated weights for policy 1, policy_version 14490 (0.0011) -[2023-11-28 00:35:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 7438336. Throughput: 0: 2678.8, 1: 2694.4. Samples: 7449796. Policy #0 lag: (min: 31.0, avg: 48.7, max: 63.0) -[2023-11-28 00:35:28,445][86177] Avg episode reward: [(0, '-553.110'), (1, '-508.430')] -[2023-11-28 00:35:28,562][87424] Updated weights for policy 0, policy_version 14566 (0.0012) -[2023-11-28 00:35:28,950][87424] Updated weights for policy 0, policy_version 14576 (0.0012) -[2023-11-28 00:35:29,324][87424] Updated weights for policy 0, policy_version 14586 (0.0011) -[2023-11-28 00:35:30,661][87426] Updated weights for policy 1, policy_version 14500 (0.0010) -[2023-11-28 00:35:31,043][87426] Updated weights for policy 1, policy_version 14510 (0.0007) -[2023-11-28 00:35:31,419][87426] Updated weights for policy 1, policy_version 14520 (0.0008) -[2023-11-28 00:35:31,687][87424] Updated weights for policy 0, policy_version 14596 (0.0009) -[2023-11-28 00:35:32,069][87424] Updated weights for policy 0, policy_version 14606 (0.0012) -[2023-11-28 00:35:32,455][87424] Updated weights for policy 0, policy_version 14616 (0.0012) -[2023-11-28 00:35:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7462912. Throughput: 0: 2716.3, 1: 2706.3. Samples: 7475296. Policy #0 lag: (min: 20.0, avg: 39.8, max: 56.0) -[2023-11-28 00:35:33,446][86177] Avg episode reward: [(0, '-558.210'), (1, '-526.900')] -[2023-11-28 00:35:34,005][87426] Updated weights for policy 1, policy_version 14530 (0.0008) -[2023-11-28 00:35:34,163][87424] Updated weights for policy 0, policy_version 14626 (0.0011) -[2023-11-28 00:35:34,378][87426] Updated weights for policy 1, policy_version 14540 (0.0007) -[2023-11-28 00:35:34,551][87424] Updated weights for policy 0, policy_version 14636 (0.0011) -[2023-11-28 00:35:34,755][87426] Updated weights for policy 1, policy_version 14550 (0.0009) -[2023-11-28 00:35:34,932][87424] Updated weights for policy 0, policy_version 14646 (0.0011) -[2023-11-28 00:35:35,139][87426] Updated weights for policy 1, policy_version 14560 (0.0010) -[2023-11-28 00:35:35,309][87424] Updated weights for policy 0, policy_version 14656 (0.0012) -[2023-11-28 00:35:36,951][87426] Updated weights for policy 1, policy_version 14570 (0.0009) -[2023-11-28 00:35:37,326][87426] Updated weights for policy 1, policy_version 14580 (0.0008) -[2023-11-28 00:35:37,367][87424] Updated weights for policy 0, policy_version 14666 (0.0011) -[2023-11-28 00:35:37,704][87426] Updated weights for policy 1, policy_version 14590 (0.0008) -[2023-11-28 00:35:37,750][87424] Updated weights for policy 0, policy_version 14676 (0.0011) -[2023-11-28 00:35:38,128][87424] Updated weights for policy 0, policy_version 14686 (0.0012) -[2023-11-28 00:35:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7495680. Throughput: 0: 2728.9, 1: 2691.4. Samples: 7507984. Policy #0 lag: (min: 20.0, avg: 39.8, max: 56.0) -[2023-11-28 00:35:38,445][86177] Avg episode reward: [(0, '-548.840'), (1, '-525.970')] -[2023-11-28 00:35:39,358][87426] Updated weights for policy 1, policy_version 14600 (0.0012) -[2023-11-28 00:35:39,732][87426] Updated weights for policy 1, policy_version 14610 (0.0012) -[2023-11-28 00:35:40,108][87426] Updated weights for policy 1, policy_version 14620 (0.0011) -[2023-11-28 00:35:40,209][87424] Updated weights for policy 0, policy_version 14696 (0.0011) -[2023-11-28 00:35:40,591][87424] Updated weights for policy 0, policy_version 14706 (0.0012) -[2023-11-28 00:35:40,975][87424] Updated weights for policy 0, policy_version 14716 (0.0012) -[2023-11-28 00:35:42,666][87426] Updated weights for policy 1, policy_version 14630 (0.0011) -[2023-11-28 00:35:43,040][87426] Updated weights for policy 1, policy_version 14640 (0.0011) -[2023-11-28 00:35:43,427][87426] Updated weights for policy 1, policy_version 14650 (0.0011) -[2023-11-28 00:35:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 7512064. Throughput: 0: 2730.0, 1: 2712.2. Samples: 7531896. Policy #0 lag: (min: 20.0, avg: 39.8, max: 56.0) -[2023-11-28 00:35:43,445][86177] Avg episode reward: [(0, '-551.100'), (1, '-523.600')] -[2023-11-28 00:35:43,577][87424] Updated weights for policy 0, policy_version 14726 (0.0012) -[2023-11-28 00:35:43,964][87424] Updated weights for policy 0, policy_version 14736 (0.0012) -[2023-11-28 00:35:44,347][87424] Updated weights for policy 0, policy_version 14746 (0.0012) -[2023-11-28 00:35:45,382][87426] Updated weights for policy 1, policy_version 14660 (0.0011) -[2023-11-28 00:35:45,765][87426] Updated weights for policy 1, policy_version 14670 (0.0012) -[2023-11-28 00:35:46,155][87426] Updated weights for policy 1, policy_version 14680 (0.0012) -[2023-11-28 00:35:46,936][87424] Updated weights for policy 0, policy_version 14756 (0.0011) -[2023-11-28 00:35:47,321][87424] Updated weights for policy 0, policy_version 14766 (0.0007) -[2023-11-28 00:35:47,702][87424] Updated weights for policy 0, policy_version 14776 (0.0007) -[2023-11-28 00:35:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7544832. Throughput: 0: 2715.4, 1: 2718.5. Samples: 7555432. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) -[2023-11-28 00:35:48,446][86177] Avg episode reward: [(0, '-560.890'), (1, '-524.940')] -[2023-11-28 00:35:48,607][87426] Updated weights for policy 1, policy_version 14690 (0.0010) -[2023-11-28 00:35:48,990][87426] Updated weights for policy 1, policy_version 14700 (0.0009) -[2023-11-28 00:35:49,367][87426] Updated weights for policy 1, policy_version 14710 (0.0012) -[2023-11-28 00:35:49,749][87426] Updated weights for policy 1, policy_version 14720 (0.0012) -[2023-11-28 00:35:50,123][87424] Updated weights for policy 0, policy_version 14786 (0.0008) -[2023-11-28 00:35:50,505][87424] Updated weights for policy 0, policy_version 14796 (0.0012) -[2023-11-28 00:35:50,888][87424] Updated weights for policy 0, policy_version 14806 (0.0012) -[2023-11-28 00:35:51,279][87424] Updated weights for policy 0, policy_version 14816 (0.0012) -[2023-11-28 00:35:52,346][87426] Updated weights for policy 1, policy_version 14730 (0.0012) -[2023-11-28 00:35:52,720][87426] Updated weights for policy 1, policy_version 14740 (0.0012) -[2023-11-28 00:35:53,103][87426] Updated weights for policy 1, policy_version 14750 (0.0012) -[2023-11-28 00:35:53,247][87424] Updated weights for policy 0, policy_version 14826 (0.0011) -[2023-11-28 00:35:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 7569408. Throughput: 0: 2691.8, 1: 2682.2. Samples: 7586044. Policy #0 lag: (min: 5.0, avg: 20.6, max: 37.0) -[2023-11-28 00:35:53,445][86177] Avg episode reward: [(0, '-566.720'), (1, '-506.890')] -[2023-11-28 00:35:53,635][87424] Updated weights for policy 0, policy_version 14836 (0.0012) -[2023-11-28 00:35:54,012][87424] Updated weights for policy 0, policy_version 14846 (0.0012) -[2023-11-28 00:35:55,710][87426] Updated weights for policy 1, policy_version 14760 (0.0008) -[2023-11-28 00:35:56,089][87426] Updated weights for policy 1, policy_version 14770 (0.0008) -[2023-11-28 00:35:56,362][87424] Updated weights for policy 0, policy_version 14856 (0.0008) -[2023-11-28 00:35:56,472][87426] Updated weights for policy 1, policy_version 14780 (0.0007) -[2023-11-28 00:35:56,735][87424] Updated weights for policy 0, policy_version 14866 (0.0007) -[2023-11-28 00:35:57,123][87424] Updated weights for policy 0, policy_version 14876 (0.0007) -[2023-11-28 00:35:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 7593984. Throughput: 0: 2690.5, 1: 2657.2. Samples: 7609460. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 00:35:58,445][86177] Avg episode reward: [(0, '-575.610'), (1, '-527.100')] -[2023-11-28 00:35:58,841][87426] Updated weights for policy 1, policy_version 14790 (0.0007) -[2023-11-28 00:35:59,220][87426] Updated weights for policy 1, policy_version 14800 (0.0012) -[2023-11-28 00:35:59,226][87424] Updated weights for policy 0, policy_version 14886 (0.0010) -[2023-11-28 00:35:59,593][87426] Updated weights for policy 1, policy_version 14810 (0.0011) -[2023-11-28 00:35:59,597][87424] Updated weights for policy 0, policy_version 14896 (0.0011) -[2023-11-28 00:35:59,983][87424] Updated weights for policy 0, policy_version 14906 (0.0009) -[2023-11-28 00:36:02,129][87426] Updated weights for policy 1, policy_version 14820 (0.0010) -[2023-11-28 00:36:02,236][87424] Updated weights for policy 0, policy_version 14916 (0.0009) -[2023-11-28 00:36:02,497][87426] Updated weights for policy 1, policy_version 14830 (0.0008) -[2023-11-28 00:36:02,612][87424] Updated weights for policy 0, policy_version 14926 (0.0011) -[2023-11-28 00:36:02,883][87426] Updated weights for policy 1, policy_version 14840 (0.0008) -[2023-11-28 00:36:03,007][87424] Updated weights for policy 0, policy_version 14936 (0.0008) -[2023-11-28 00:36:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7626752. Throughput: 0: 2693.7, 1: 2641.3. Samples: 7632512. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 00:36:03,445][86177] Avg episode reward: [(0, '-593.470'), (1, '-573.160')] -[2023-11-28 00:36:05,138][87424] Updated weights for policy 0, policy_version 14946 (0.0008) -[2023-11-28 00:36:05,471][87426] Updated weights for policy 1, policy_version 14850 (0.0008) -[2023-11-28 00:36:05,510][87424] Updated weights for policy 0, policy_version 14956 (0.0010) -[2023-11-28 00:36:05,853][87426] Updated weights for policy 1, policy_version 14860 (0.0008) -[2023-11-28 00:36:05,891][87424] Updated weights for policy 0, policy_version 14966 (0.0007) -[2023-11-28 00:36:06,237][87426] Updated weights for policy 1, policy_version 14870 (0.0008) -[2023-11-28 00:36:06,272][87424] Updated weights for policy 0, policy_version 14976 (0.0007) -[2023-11-28 00:36:06,614][87426] Updated weights for policy 1, policy_version 14880 (0.0007) -[2023-11-28 00:36:08,118][87424] Updated weights for policy 0, policy_version 14986 (0.0008) -[2023-11-28 00:36:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 7643136. Throughput: 0: 2703.6, 1: 2612.4. Samples: 7664312. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 00:36:08,445][86177] Avg episode reward: [(0, '-588.670'), (1, '-571.760')] -[2023-11-28 00:36:08,489][87424] Updated weights for policy 0, policy_version 14996 (0.0007) -[2023-11-28 00:36:08,877][87424] Updated weights for policy 0, policy_version 15006 (0.0008) -[2023-11-28 00:36:08,900][87426] Updated weights for policy 1, policy_version 14890 (0.0012) -[2023-11-28 00:36:09,282][87426] Updated weights for policy 1, policy_version 14900 (0.0012) -[2023-11-28 00:36:09,660][87426] Updated weights for policy 1, policy_version 14910 (0.0012) -[2023-11-28 00:36:10,949][87424] Updated weights for policy 0, policy_version 15016 (0.0010) -[2023-11-28 00:36:11,331][87424] Updated weights for policy 0, policy_version 15026 (0.0008) -[2023-11-28 00:36:11,711][87424] Updated weights for policy 0, policy_version 15036 (0.0009) -[2023-11-28 00:36:11,830][87426] Updated weights for policy 1, policy_version 14920 (0.0010) -[2023-11-28 00:36:12,213][87426] Updated weights for policy 1, policy_version 14930 (0.0009) -[2023-11-28 00:36:12,595][87426] Updated weights for policy 1, policy_version 14940 (0.0008) -[2023-11-28 00:36:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 7675904. Throughput: 0: 2682.1, 1: 2593.0. Samples: 7687172. Policy #0 lag: (min: 31.0, avg: 41.8, max: 63.0) -[2023-11-28 00:36:13,445][86177] Avg episode reward: [(0, '-586.430'), (1, '-575.220')] -[2023-11-28 00:36:14,322][87424] Updated weights for policy 0, policy_version 15046 (0.0009) -[2023-11-28 00:36:14,698][87424] Updated weights for policy 0, policy_version 15056 (0.0008) -[2023-11-28 00:36:14,980][87426] Updated weights for policy 1, policy_version 14950 (0.0008) -[2023-11-28 00:36:15,081][87424] Updated weights for policy 0, policy_version 15066 (0.0009) -[2023-11-28 00:36:15,351][87426] Updated weights for policy 1, policy_version 14960 (0.0009) -[2023-11-28 00:36:15,725][87426] Updated weights for policy 1, policy_version 14970 (0.0012) -[2023-11-28 00:36:17,459][87424] Updated weights for policy 0, policy_version 15076 (0.0011) -[2023-11-28 00:36:17,823][87426] Updated weights for policy 1, policy_version 14980 (0.0011) -[2023-11-28 00:36:17,839][87424] Updated weights for policy 0, policy_version 15086 (0.0012) -[2023-11-28 00:36:18,208][87426] Updated weights for policy 1, policy_version 14990 (0.0007) -[2023-11-28 00:36:18,220][87424] Updated weights for policy 0, policy_version 15096 (0.0008) -[2023-11-28 00:36:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.2, 300 sec: 5387.3). Total num frames: 7692288. Throughput: 0: 2634.8, 1: 2590.4. Samples: 7710432. Policy #0 lag: (min: 31.0, avg: 41.8, max: 63.0) -[2023-11-28 00:36:18,445][86177] Avg episode reward: [(0, '-583.100'), (1, '-560.620')] -[2023-11-28 00:36:18,524][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000015104_3866624.pth... -[2023-11-28 00:36:18,571][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000012544_3211264.pth -[2023-11-28 00:36:18,590][87426] Updated weights for policy 1, policy_version 15000 (0.0008) -[2023-11-28 00:36:18,892][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000015008_3842048.pth... -[2023-11-28 00:36:18,942][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000012480_3194880.pth -[2023-11-28 00:36:20,330][87426] Updated weights for policy 1, policy_version 15010 (0.0009) -[2023-11-28 00:36:20,683][87424] Updated weights for policy 0, policy_version 15106 (0.0010) -[2023-11-28 00:36:20,709][87426] Updated weights for policy 1, policy_version 15020 (0.0011) -[2023-11-28 00:36:21,057][87424] Updated weights for policy 0, policy_version 15116 (0.0012) -[2023-11-28 00:36:21,087][87426] Updated weights for policy 1, policy_version 15030 (0.0011) -[2023-11-28 00:36:21,438][87424] Updated weights for policy 0, policy_version 15126 (0.0011) -[2023-11-28 00:36:21,467][87426] Updated weights for policy 1, policy_version 15040 (0.0007) -[2023-11-28 00:36:21,819][87424] Updated weights for policy 0, policy_version 15136 (0.0011) -[2023-11-28 00:36:23,438][87426] Updated weights for policy 1, policy_version 15050 (0.0010) -[2023-11-28 00:36:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 7725056. Throughput: 0: 2621.3, 1: 2613.9. Samples: 7743568. Policy #0 lag: (min: 31.0, avg: 41.8, max: 63.0) -[2023-11-28 00:36:23,445][86177] Avg episode reward: [(0, '-603.370'), (1, '-511.260')] -[2023-11-28 00:36:23,815][87426] Updated weights for policy 1, policy_version 15060 (0.0011) -[2023-11-28 00:36:23,909][87424] Updated weights for policy 0, policy_version 15146 (0.0012) -[2023-11-28 00:36:24,206][87426] Updated weights for policy 1, policy_version 15070 (0.0008) -[2023-11-28 00:36:24,306][87424] Updated weights for policy 0, policy_version 15156 (0.0012) -[2023-11-28 00:36:24,683][87424] Updated weights for policy 0, policy_version 15166 (0.0012) -[2023-11-28 00:36:26,062][87426] Updated weights for policy 1, policy_version 15080 (0.0011) -[2023-11-28 00:36:26,430][87426] Updated weights for policy 1, policy_version 15090 (0.0011) -[2023-11-28 00:36:26,662][87424] Updated weights for policy 0, policy_version 15176 (0.0009) -[2023-11-28 00:36:26,817][87426] Updated weights for policy 1, policy_version 15100 (0.0010) -[2023-11-28 00:36:27,047][87424] Updated weights for policy 0, policy_version 15186 (0.0008) -[2023-11-28 00:36:27,432][87424] Updated weights for policy 0, policy_version 15196 (0.0008) -[2023-11-28 00:36:28,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 7757824. Throughput: 0: 2636.6, 1: 2654.4. Samples: 7769992. Policy #0 lag: (min: 31.0, avg: 50.2, max: 63.0) -[2023-11-28 00:36:28,445][86177] Avg episode reward: [(0, '-606.880'), (1, '-519.910')] -[2023-11-28 00:36:28,606][87426] Updated weights for policy 1, policy_version 15110 (0.0008) -[2023-11-28 00:36:28,989][87426] Updated weights for policy 1, policy_version 15120 (0.0009) -[2023-11-28 00:36:29,372][87426] Updated weights for policy 1, policy_version 15130 (0.0012) -[2023-11-28 00:36:29,587][87424] Updated weights for policy 0, policy_version 15206 (0.0009) -[2023-11-28 00:36:29,971][87424] Updated weights for policy 0, policy_version 15216 (0.0012) -[2023-11-28 00:36:30,354][87424] Updated weights for policy 0, policy_version 15226 (0.0012) -[2023-11-28 00:36:31,845][87426] Updated weights for policy 1, policy_version 15140 (0.0011) -[2023-11-28 00:36:32,219][87426] Updated weights for policy 1, policy_version 15150 (0.0011) -[2023-11-28 00:36:32,241][87424] Updated weights for policy 0, policy_version 15236 (0.0011) -[2023-11-28 00:36:32,597][87426] Updated weights for policy 1, policy_version 15160 (0.0011) -[2023-11-28 00:36:32,630][87424] Updated weights for policy 0, policy_version 15246 (0.0011) -[2023-11-28 00:36:33,008][87424] Updated weights for policy 0, policy_version 15256 (0.0008) -[2023-11-28 00:36:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7790592. Throughput: 0: 2679.7, 1: 2664.2. Samples: 7795908. Policy #0 lag: (min: 31.0, avg: 50.2, max: 63.0) -[2023-11-28 00:36:33,445][86177] Avg episode reward: [(0, '-602.580'), (1, '-533.480')] -[2023-11-28 00:36:34,413][87426] Updated weights for policy 1, policy_version 15170 (0.0011) -[2023-11-28 00:36:34,797][87426] Updated weights for policy 1, policy_version 15180 (0.0009) -[2023-11-28 00:36:35,168][87426] Updated weights for policy 1, policy_version 15190 (0.0011) -[2023-11-28 00:36:35,495][87424] Updated weights for policy 0, policy_version 15266 (0.0008) -[2023-11-28 00:36:35,552][87426] Updated weights for policy 1, policy_version 15200 (0.0009) -[2023-11-28 00:36:35,878][87424] Updated weights for policy 0, policy_version 15276 (0.0007) -[2023-11-28 00:36:36,256][87424] Updated weights for policy 0, policy_version 15286 (0.0010) -[2023-11-28 00:36:36,641][87424] Updated weights for policy 0, policy_version 15296 (0.0011) -[2023-11-28 00:36:37,979][87426] Updated weights for policy 1, policy_version 15210 (0.0007) -[2023-11-28 00:36:38,343][87426] Updated weights for policy 1, policy_version 15220 (0.0007) -[2023-11-28 00:36:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 7806976. Throughput: 0: 2694.0, 1: 2672.3. Samples: 7827524. Policy #0 lag: (min: 31.0, avg: 50.2, max: 63.0) -[2023-11-28 00:36:38,445][86177] Avg episode reward: [(0, '-606.740'), (1, '-543.460')] -[2023-11-28 00:36:38,726][87426] Updated weights for policy 1, policy_version 15230 (0.0007) -[2023-11-28 00:36:38,744][87424] Updated weights for policy 0, policy_version 15306 (0.0007) -[2023-11-28 00:36:39,134][87424] Updated weights for policy 0, policy_version 15316 (0.0008) -[2023-11-28 00:36:39,522][87424] Updated weights for policy 0, policy_version 15326 (0.0007) -[2023-11-28 00:36:41,312][87426] Updated weights for policy 1, policy_version 15240 (0.0011) -[2023-11-28 00:36:41,449][87424] Updated weights for policy 0, policy_version 15336 (0.0012) -[2023-11-28 00:36:41,685][87426] Updated weights for policy 1, policy_version 15250 (0.0011) -[2023-11-28 00:36:41,834][87424] Updated weights for policy 0, policy_version 15346 (0.0012) -[2023-11-28 00:36:42,060][87426] Updated weights for policy 1, policy_version 15260 (0.0011) -[2023-11-28 00:36:42,226][87424] Updated weights for policy 0, policy_version 15356 (0.0011) -[2023-11-28 00:36:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 7839744. Throughput: 0: 2705.5, 1: 2663.2. Samples: 7851052. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 00:36:43,445][86177] Avg episode reward: [(0, '-573.570'), (1, '-543.290')] -[2023-11-28 00:36:44,524][87426] Updated weights for policy 1, policy_version 15270 (0.0011) -[2023-11-28 00:36:44,811][87424] Updated weights for policy 0, policy_version 15366 (0.0010) -[2023-11-28 00:36:44,899][87426] Updated weights for policy 1, policy_version 15280 (0.0012) -[2023-11-28 00:36:45,195][87424] Updated weights for policy 0, policy_version 15376 (0.0010) -[2023-11-28 00:36:45,282][87426] Updated weights for policy 1, policy_version 15290 (0.0008) -[2023-11-28 00:36:45,583][87424] Updated weights for policy 0, policy_version 15386 (0.0008) -[2023-11-28 00:36:47,445][87426] Updated weights for policy 1, policy_version 15300 (0.0009) -[2023-11-28 00:36:47,821][87426] Updated weights for policy 1, policy_version 15310 (0.0007) -[2023-11-28 00:36:48,067][87424] Updated weights for policy 0, policy_version 15396 (0.0008) -[2023-11-28 00:36:48,201][87426] Updated weights for policy 1, policy_version 15320 (0.0007) -[2023-11-28 00:36:48,437][87424] Updated weights for policy 0, policy_version 15406 (0.0007) -[2023-11-28 00:36:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 7856128. Throughput: 0: 2685.4, 1: 2691.2. Samples: 7874460. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 00:36:48,445][86177] Avg episode reward: [(0, '-577.930'), (1, '-533.260')] -[2023-11-28 00:36:48,819][87424] Updated weights for policy 0, policy_version 15416 (0.0007) -[2023-11-28 00:36:50,688][87426] Updated weights for policy 1, policy_version 15330 (0.0008) -[2023-11-28 00:36:51,060][87426] Updated weights for policy 1, policy_version 15340 (0.0007) -[2023-11-28 00:36:51,357][87424] Updated weights for policy 0, policy_version 15426 (0.0009) -[2023-11-28 00:36:51,442][87426] Updated weights for policy 1, policy_version 15350 (0.0008) -[2023-11-28 00:36:51,740][87424] Updated weights for policy 0, policy_version 15436 (0.0010) -[2023-11-28 00:36:51,816][87426] Updated weights for policy 1, policy_version 15360 (0.0009) -[2023-11-28 00:36:52,125][87424] Updated weights for policy 0, policy_version 15446 (0.0008) -[2023-11-28 00:36:52,515][87424] Updated weights for policy 0, policy_version 15456 (0.0009) -[2023-11-28 00:36:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 7888896. Throughput: 0: 2641.5, 1: 2718.7. Samples: 7905520. Policy #0 lag: (min: 30.0, avg: 39.3, max: 62.0) -[2023-11-28 00:36:53,445][86177] Avg episode reward: [(0, '-579.380'), (1, '-522.040')] -[2023-11-28 00:36:53,983][87426] Updated weights for policy 1, policy_version 15370 (0.0011) -[2023-11-28 00:36:54,366][87426] Updated weights for policy 1, policy_version 15380 (0.0011) -[2023-11-28 00:36:54,565][87424] Updated weights for policy 0, policy_version 15466 (0.0011) -[2023-11-28 00:36:54,742][87426] Updated weights for policy 1, policy_version 15390 (0.0008) -[2023-11-28 00:36:54,951][87424] Updated weights for policy 0, policy_version 15476 (0.0011) -[2023-11-28 00:36:55,341][87424] Updated weights for policy 0, policy_version 15486 (0.0012) -[2023-11-28 00:36:56,898][87426] Updated weights for policy 1, policy_version 15400 (0.0011) -[2023-11-28 00:36:56,998][87424] Updated weights for policy 0, policy_version 15496 (0.0012) -[2023-11-28 00:36:57,273][87426] Updated weights for policy 1, policy_version 15410 (0.0011) -[2023-11-28 00:36:57,373][87424] Updated weights for policy 0, policy_version 15506 (0.0010) -[2023-11-28 00:36:57,654][87426] Updated weights for policy 1, policy_version 15420 (0.0009) -[2023-11-28 00:36:57,755][87424] Updated weights for policy 0, policy_version 15516 (0.0011) -[2023-11-28 00:36:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 7921664. Throughput: 0: 2661.5, 1: 2729.6. Samples: 7929772. Policy #0 lag: (min: 30.0, avg: 39.3, max: 62.0) -[2023-11-28 00:36:58,445][86177] Avg episode reward: [(0, '-581.220'), (1, '-512.590')] -[2023-11-28 00:36:59,707][87426] Updated weights for policy 1, policy_version 15430 (0.0007) -[2023-11-28 00:37:00,076][87424] Updated weights for policy 0, policy_version 15526 (0.0010) -[2023-11-28 00:37:00,084][87426] Updated weights for policy 1, policy_version 15440 (0.0010) -[2023-11-28 00:37:00,462][87424] Updated weights for policy 0, policy_version 15536 (0.0012) -[2023-11-28 00:37:00,467][87426] Updated weights for policy 1, policy_version 15450 (0.0011) -[2023-11-28 00:37:00,851][87424] Updated weights for policy 0, policy_version 15546 (0.0011) -[2023-11-28 00:37:02,294][87426] Updated weights for policy 1, policy_version 15460 (0.0011) -[2023-11-28 00:37:02,664][87426] Updated weights for policy 1, policy_version 15470 (0.0012) -[2023-11-28 00:37:03,050][87426] Updated weights for policy 1, policy_version 15480 (0.0009) -[2023-11-28 00:37:03,172][87424] Updated weights for policy 0, policy_version 15556 (0.0011) -[2023-11-28 00:37:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 7946240. Throughput: 0: 2706.4, 1: 2734.8. Samples: 7955284. Policy #0 lag: (min: 30.0, avg: 39.3, max: 62.0) -[2023-11-28 00:37:03,445][86177] Avg episode reward: [(0, '-579.710'), (1, '-521.170')] -[2023-11-28 00:37:03,552][87424] Updated weights for policy 0, policy_version 15566 (0.0012) -[2023-11-28 00:37:03,934][87424] Updated weights for policy 0, policy_version 15576 (0.0011) -[2023-11-28 00:37:05,519][87426] Updated weights for policy 1, policy_version 15490 (0.0008) -[2023-11-28 00:37:05,739][87424] Updated weights for policy 0, policy_version 15586 (0.0008) -[2023-11-28 00:37:05,899][87426] Updated weights for policy 1, policy_version 15500 (0.0007) -[2023-11-28 00:37:06,127][87424] Updated weights for policy 0, policy_version 15596 (0.0012) -[2023-11-28 00:37:06,276][87426] Updated weights for policy 1, policy_version 15510 (0.0007) -[2023-11-28 00:37:06,512][87424] Updated weights for policy 0, policy_version 15606 (0.0011) -[2023-11-28 00:37:06,668][87426] Updated weights for policy 1, policy_version 15520 (0.0008) -[2023-11-28 00:37:06,896][87424] Updated weights for policy 0, policy_version 15616 (0.0011) -[2023-11-28 00:37:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 7970816. Throughput: 0: 2732.3, 1: 2710.6. Samples: 7988496. Policy #0 lag: (min: 21.0, avg: 38.0, max: 53.0) -[2023-11-28 00:37:08,445][86177] Avg episode reward: [(0, '-584.850'), (1, '-525.520')] -[2023-11-28 00:37:08,913][87424] Updated weights for policy 0, policy_version 15626 (0.0011) -[2023-11-28 00:37:09,145][87426] Updated weights for policy 1, policy_version 15530 (0.0008) -[2023-11-28 00:37:09,288][87424] Updated weights for policy 0, policy_version 15636 (0.0010) -[2023-11-28 00:37:09,526][87426] Updated weights for policy 1, policy_version 15540 (0.0007) -[2023-11-28 00:37:09,670][87424] Updated weights for policy 0, policy_version 15646 (0.0009) -[2023-11-28 00:37:09,910][87426] Updated weights for policy 1, policy_version 15550 (0.0010) -[2023-11-28 00:37:11,650][87424] Updated weights for policy 0, policy_version 15656 (0.0011) -[2023-11-28 00:37:12,029][87424] Updated weights for policy 0, policy_version 15666 (0.0012) -[2023-11-28 00:37:12,289][87426] Updated weights for policy 1, policy_version 15560 (0.0010) -[2023-11-28 00:37:12,410][87424] Updated weights for policy 0, policy_version 15676 (0.0014) -[2023-11-28 00:37:12,670][87426] Updated weights for policy 1, policy_version 15570 (0.0007) -[2023-11-28 00:37:13,051][87426] Updated weights for policy 1, policy_version 15580 (0.0010) -[2023-11-28 00:37:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 8003584. Throughput: 0: 2724.7, 1: 2655.3. Samples: 8012092. Policy #0 lag: (min: 21.0, avg: 38.0, max: 53.0) -[2023-11-28 00:37:13,445][86177] Avg episode reward: [(0, '-607.880'), (1, '-520.540')] -[2023-11-28 00:37:14,259][87424] Updated weights for policy 0, policy_version 15686 (0.0012) -[2023-11-28 00:37:14,635][87424] Updated weights for policy 0, policy_version 15696 (0.0009) -[2023-11-28 00:37:15,029][87424] Updated weights for policy 0, policy_version 15706 (0.0008) -[2023-11-28 00:37:15,185][87426] Updated weights for policy 1, policy_version 15590 (0.0012) -[2023-11-28 00:37:15,564][87426] Updated weights for policy 1, policy_version 15600 (0.0011) -[2023-11-28 00:37:15,944][87426] Updated weights for policy 1, policy_version 15610 (0.0011) -[2023-11-28 00:37:17,206][87424] Updated weights for policy 0, policy_version 15716 (0.0009) -[2023-11-28 00:37:17,593][87424] Updated weights for policy 0, policy_version 15726 (0.0012) -[2023-11-28 00:37:17,973][87424] Updated weights for policy 0, policy_version 15736 (0.0012) -[2023-11-28 00:37:18,439][87426] Updated weights for policy 1, policy_version 15620 (0.0012) -[2023-11-28 00:37:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 8028160. Throughput: 0: 2709.0, 1: 2656.5. Samples: 8037356. Policy #0 lag: (min: 21.0, avg: 38.0, max: 53.0) -[2023-11-28 00:37:18,445][86177] Avg episode reward: [(0, '-604.820'), (1, '-522.930')] -[2023-11-28 00:37:18,824][87426] Updated weights for policy 1, policy_version 15630 (0.0012) -[2023-11-28 00:37:19,202][87426] Updated weights for policy 1, policy_version 15640 (0.0012) -[2023-11-28 00:37:20,533][87424] Updated weights for policy 0, policy_version 15746 (0.0012) -[2023-11-28 00:37:20,899][87426] Updated weights for policy 1, policy_version 15650 (0.0011) -[2023-11-28 00:37:20,923][87424] Updated weights for policy 0, policy_version 15756 (0.0010) -[2023-11-28 00:37:21,277][87426] Updated weights for policy 1, policy_version 15660 (0.0009) -[2023-11-28 00:37:21,307][87424] Updated weights for policy 0, policy_version 15766 (0.0010) -[2023-11-28 00:37:21,667][87426] Updated weights for policy 1, policy_version 15670 (0.0011) -[2023-11-28 00:37:21,684][87424] Updated weights for policy 0, policy_version 15776 (0.0011) -[2023-11-28 00:37:22,040][87426] Updated weights for policy 1, policy_version 15680 (0.0012) -[2023-11-28 00:37:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 8052736. Throughput: 0: 2719.5, 1: 2674.8. Samples: 8070264. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 00:37:23,445][86177] Avg episode reward: [(0, '-593.040'), (1, '-521.910')] -[2023-11-28 00:37:23,661][87424] Updated weights for policy 0, policy_version 15786 (0.0012) -[2023-11-28 00:37:24,050][87424] Updated weights for policy 0, policy_version 15796 (0.0009) -[2023-11-28 00:37:24,424][87424] Updated weights for policy 0, policy_version 15806 (0.0007) -[2023-11-28 00:37:24,490][87426] Updated weights for policy 1, policy_version 15690 (0.0010) -[2023-11-28 00:37:24,871][87426] Updated weights for policy 1, policy_version 15700 (0.0008) -[2023-11-28 00:37:25,261][87426] Updated weights for policy 1, policy_version 15710 (0.0008) -[2023-11-28 00:37:26,454][87424] Updated weights for policy 0, policy_version 15816 (0.0011) -[2023-11-28 00:37:26,831][87424] Updated weights for policy 0, policy_version 15826 (0.0012) -[2023-11-28 00:37:27,211][87424] Updated weights for policy 0, policy_version 15836 (0.0011) -[2023-11-28 00:37:27,263][87426] Updated weights for policy 1, policy_version 15720 (0.0011) -[2023-11-28 00:37:27,643][87426] Updated weights for policy 1, policy_version 15730 (0.0010) -[2023-11-28 00:37:28,021][87426] Updated weights for policy 1, policy_version 15740 (0.0007) -[2023-11-28 00:37:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 8085504. Throughput: 0: 2739.5, 1: 2699.1. Samples: 8095788. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 00:37:28,445][86177] Avg episode reward: [(0, '-594.210'), (1, '-522.180')] -[2023-11-28 00:37:29,653][87424] Updated weights for policy 0, policy_version 15846 (0.0010) -[2023-11-28 00:37:30,036][87424] Updated weights for policy 0, policy_version 15856 (0.0009) -[2023-11-28 00:37:30,423][87424] Updated weights for policy 0, policy_version 15866 (0.0009) -[2023-11-28 00:37:30,446][87426] Updated weights for policy 1, policy_version 15750 (0.0008) -[2023-11-28 00:37:30,821][87426] Updated weights for policy 1, policy_version 15760 (0.0008) -[2023-11-28 00:37:31,203][87426] Updated weights for policy 1, policy_version 15770 (0.0008) -[2023-11-28 00:37:32,526][87424] Updated weights for policy 0, policy_version 15876 (0.0010) -[2023-11-28 00:37:32,911][87424] Updated weights for policy 0, policy_version 15886 (0.0012) -[2023-11-28 00:37:33,294][87424] Updated weights for policy 0, policy_version 15896 (0.0008) -[2023-11-28 00:37:33,430][87426] Updated weights for policy 1, policy_version 15780 (0.0009) -[2023-11-28 00:37:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 8101888. Throughput: 0: 2780.5, 1: 2676.8. Samples: 8120040. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 00:37:33,445][86177] Avg episode reward: [(0, '-596.820'), (1, '-520.670')] -[2023-11-28 00:37:33,808][87426] Updated weights for policy 1, policy_version 15790 (0.0007) -[2023-11-28 00:37:34,190][87426] Updated weights for policy 1, policy_version 15800 (0.0007) -[2023-11-28 00:37:35,272][87424] Updated weights for policy 0, policy_version 15906 (0.0009) -[2023-11-28 00:37:35,655][87424] Updated weights for policy 0, policy_version 15916 (0.0012) -[2023-11-28 00:37:36,042][87424] Updated weights for policy 0, policy_version 15926 (0.0012) -[2023-11-28 00:37:36,420][87424] Updated weights for policy 0, policy_version 15936 (0.0011) -[2023-11-28 00:37:36,706][87426] Updated weights for policy 1, policy_version 15810 (0.0009) -[2023-11-28 00:37:37,077][87426] Updated weights for policy 1, policy_version 15820 (0.0007) -[2023-11-28 00:37:37,458][87426] Updated weights for policy 1, policy_version 15830 (0.0008) -[2023-11-28 00:37:37,845][87426] Updated weights for policy 1, policy_version 15840 (0.0011) -[2023-11-28 00:37:38,281][87424] Updated weights for policy 0, policy_version 15946 (0.0009) -[2023-11-28 00:37:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 8134656. Throughput: 0: 2820.4, 1: 2671.0. Samples: 8152636. Policy #0 lag: (min: 31.0, avg: 35.5, max: 59.0) -[2023-11-28 00:37:38,445][86177] Avg episode reward: [(0, '-592.350'), (1, '-530.170')] -[2023-11-28 00:37:38,672][87424] Updated weights for policy 0, policy_version 15956 (0.0008) -[2023-11-28 00:37:39,061][87424] Updated weights for policy 0, policy_version 15966 (0.0008) -[2023-11-28 00:37:39,659][87426] Updated weights for policy 1, policy_version 15850 (0.0011) -[2023-11-28 00:37:40,047][87426] Updated weights for policy 1, policy_version 15860 (0.0011) -[2023-11-28 00:37:40,430][87426] Updated weights for policy 1, policy_version 15870 (0.0012) -[2023-11-28 00:37:40,894][87424] Updated weights for policy 0, policy_version 15976 (0.0010) -[2023-11-28 00:37:41,276][87424] Updated weights for policy 0, policy_version 15986 (0.0008) -[2023-11-28 00:37:41,663][87424] Updated weights for policy 0, policy_version 15996 (0.0009) -[2023-11-28 00:37:42,850][87426] Updated weights for policy 1, policy_version 15880 (0.0012) -[2023-11-28 00:37:43,238][87426] Updated weights for policy 1, policy_version 15890 (0.0012) -[2023-11-28 00:37:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 8159232. Throughput: 0: 2816.1, 1: 2667.1. Samples: 8176516. Policy #0 lag: (min: 31.0, avg: 35.5, max: 59.0) -[2023-11-28 00:37:43,445][86177] Avg episode reward: [(0, '-597.350'), (1, '-534.780')] -[2023-11-28 00:37:43,606][87426] Updated weights for policy 1, policy_version 15900 (0.0012) -[2023-11-28 00:37:43,694][87424] Updated weights for policy 0, policy_version 16006 (0.0011) -[2023-11-28 00:37:44,067][87424] Updated weights for policy 0, policy_version 16016 (0.0012) -[2023-11-28 00:37:44,455][87424] Updated weights for policy 0, policy_version 16026 (0.0012) -[2023-11-28 00:37:45,829][87426] Updated weights for policy 1, policy_version 15910 (0.0011) -[2023-11-28 00:37:46,213][87426] Updated weights for policy 1, policy_version 15920 (0.0012) -[2023-11-28 00:37:46,587][87426] Updated weights for policy 1, policy_version 15930 (0.0009) -[2023-11-28 00:37:46,949][87424] Updated weights for policy 0, policy_version 16036 (0.0012) -[2023-11-28 00:37:47,343][87424] Updated weights for policy 0, policy_version 16046 (0.0009) -[2023-11-28 00:37:47,727][87424] Updated weights for policy 0, policy_version 16056 (0.0012) -[2023-11-28 00:37:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 8192000. Throughput: 0: 2792.7, 1: 2656.1. Samples: 8200480. Policy #0 lag: (min: 31.0, avg: 35.5, max: 59.0) -[2023-11-28 00:37:48,445][86177] Avg episode reward: [(0, '-595.550'), (1, '-571.690')] -[2023-11-28 00:37:49,143][87426] Updated weights for policy 1, policy_version 15940 (0.0009) -[2023-11-28 00:37:49,516][87426] Updated weights for policy 1, policy_version 15950 (0.0012) -[2023-11-28 00:37:49,889][87426] Updated weights for policy 1, policy_version 15960 (0.0011) -[2023-11-28 00:37:49,953][87424] Updated weights for policy 0, policy_version 16066 (0.0011) -[2023-11-28 00:37:50,328][87424] Updated weights for policy 0, policy_version 16076 (0.0011) -[2023-11-28 00:37:50,709][87424] Updated weights for policy 0, policy_version 16086 (0.0010) -[2023-11-28 00:37:51,100][87424] Updated weights for policy 0, policy_version 16096 (0.0010) -[2023-11-28 00:37:51,968][87426] Updated weights for policy 1, policy_version 15970 (0.0009) -[2023-11-28 00:37:52,353][87426] Updated weights for policy 1, policy_version 15980 (0.0009) -[2023-11-28 00:37:52,735][87426] Updated weights for policy 1, policy_version 15990 (0.0011) -[2023-11-28 00:37:53,113][87426] Updated weights for policy 1, policy_version 16000 (0.0008) -[2023-11-28 00:37:53,445][86177] Fps is (10 sec: 5734.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 8216576. Throughput: 0: 2746.7, 1: 2665.6. Samples: 8232056. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:37:53,446][86177] Avg episode reward: [(0, '-577.060'), (1, '-573.220')] -[2023-11-28 00:37:53,740][87424] Updated weights for policy 0, policy_version 16106 (0.0011) -[2023-11-28 00:37:54,125][87424] Updated weights for policy 0, policy_version 16116 (0.0012) -[2023-11-28 00:37:54,501][87424] Updated weights for policy 0, policy_version 16126 (0.0012) -[2023-11-28 00:37:55,160][87426] Updated weights for policy 1, policy_version 16010 (0.0009) -[2023-11-28 00:37:55,541][87426] Updated weights for policy 1, policy_version 16020 (0.0008) -[2023-11-28 00:37:55,930][87426] Updated weights for policy 1, policy_version 16030 (0.0007) -[2023-11-28 00:37:56,410][87424] Updated weights for policy 0, policy_version 16136 (0.0009) -[2023-11-28 00:37:56,796][87424] Updated weights for policy 0, policy_version 16146 (0.0008) -[2023-11-28 00:37:57,168][87424] Updated weights for policy 0, policy_version 16156 (0.0007) -[2023-11-28 00:37:58,051][87426] Updated weights for policy 1, policy_version 16040 (0.0008) -[2023-11-28 00:37:58,433][87426] Updated weights for policy 1, policy_version 16050 (0.0008) -[2023-11-28 00:37:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 8241152. Throughput: 0: 2750.6, 1: 2705.0. Samples: 8257592. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:37:58,445][86177] Avg episode reward: [(0, '-586.010'), (1, '-577.310')] -[2023-11-28 00:37:58,810][87426] Updated weights for policy 1, policy_version 16060 (0.0007) -[2023-11-28 00:37:59,588][87424] Updated weights for policy 0, policy_version 16166 (0.0008) -[2023-11-28 00:37:59,987][87424] Updated weights for policy 0, policy_version 16176 (0.0009) -[2023-11-28 00:38:00,374][87424] Updated weights for policy 0, policy_version 16186 (0.0007) -[2023-11-28 00:38:01,013][87426] Updated weights for policy 1, policy_version 16070 (0.0008) -[2023-11-28 00:38:01,390][87426] Updated weights for policy 1, policy_version 16080 (0.0007) -[2023-11-28 00:38:01,767][87426] Updated weights for policy 1, policy_version 16090 (0.0010) -[2023-11-28 00:38:02,859][87424] Updated weights for policy 0, policy_version 16196 (0.0009) -[2023-11-28 00:38:03,235][87424] Updated weights for policy 0, policy_version 16206 (0.0011) -[2023-11-28 00:38:03,444][86177] Fps is (10 sec: 4915.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 8265728. Throughput: 0: 2747.2, 1: 2686.5. Samples: 8281872. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:38:03,445][86177] Avg episode reward: [(0, '-579.460'), (1, '-576.400')] -[2023-11-28 00:38:03,621][87424] Updated weights for policy 0, policy_version 16216 (0.0007) -[2023-11-28 00:38:04,099][87426] Updated weights for policy 1, policy_version 16100 (0.0015) -[2023-11-28 00:38:04,479][87426] Updated weights for policy 1, policy_version 16110 (0.0012) -[2023-11-28 00:38:04,862][87426] Updated weights for policy 1, policy_version 16120 (0.0012) -[2023-11-28 00:38:05,455][87424] Updated weights for policy 0, policy_version 16226 (0.0008) -[2023-11-28 00:38:05,839][87424] Updated weights for policy 0, policy_version 16236 (0.0012) -[2023-11-28 00:38:06,223][87424] Updated weights for policy 0, policy_version 16246 (0.0011) -[2023-11-28 00:38:06,609][87424] Updated weights for policy 0, policy_version 16256 (0.0008) -[2023-11-28 00:38:06,653][87426] Updated weights for policy 1, policy_version 16130 (0.0012) -[2023-11-28 00:38:07,031][87426] Updated weights for policy 1, policy_version 16140 (0.0008) -[2023-11-28 00:38:07,413][87426] Updated weights for policy 1, policy_version 16150 (0.0010) -[2023-11-28 00:38:07,797][87426] Updated weights for policy 1, policy_version 16160 (0.0011) -[2023-11-28 00:38:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 8298496. Throughput: 0: 2736.5, 1: 2689.4. Samples: 8314432. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 00:38:08,445][86177] Avg episode reward: [(0, '-576.350'), (1, '-602.880')] -[2023-11-28 00:38:08,748][87424] Updated weights for policy 0, policy_version 16266 (0.0007) -[2023-11-28 00:38:09,131][87424] Updated weights for policy 0, policy_version 16276 (0.0008) -[2023-11-28 00:38:09,521][87424] Updated weights for policy 0, policy_version 16286 (0.0007) -[2023-11-28 00:38:10,054][87426] Updated weights for policy 1, policy_version 16170 (0.0010) -[2023-11-28 00:38:10,435][87426] Updated weights for policy 1, policy_version 16180 (0.0008) -[2023-11-28 00:38:10,814][87426] Updated weights for policy 1, policy_version 16190 (0.0008) -[2023-11-28 00:38:11,722][87424] Updated weights for policy 0, policy_version 16296 (0.0008) -[2023-11-28 00:38:12,108][87424] Updated weights for policy 0, policy_version 16306 (0.0011) -[2023-11-28 00:38:12,489][87424] Updated weights for policy 0, policy_version 16316 (0.0008) -[2023-11-28 00:38:12,932][87426] Updated weights for policy 1, policy_version 16200 (0.0009) -[2023-11-28 00:38:13,311][87426] Updated weights for policy 1, policy_version 16210 (0.0007) -[2023-11-28 00:38:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 8323072. Throughput: 0: 2701.3, 1: 2677.7. Samples: 8337844. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 00:38:13,445][86177] Avg episode reward: [(0, '-577.050'), (1, '-555.010')] -[2023-11-28 00:38:13,696][87426] Updated weights for policy 1, policy_version 16220 (0.0008) -[2023-11-28 00:38:15,104][87424] Updated weights for policy 0, policy_version 16326 (0.0009) -[2023-11-28 00:38:15,487][87424] Updated weights for policy 0, policy_version 16336 (0.0008) -[2023-11-28 00:38:15,749][87426] Updated weights for policy 1, policy_version 16230 (0.0010) -[2023-11-28 00:38:15,867][87424] Updated weights for policy 0, policy_version 16346 (0.0010) -[2023-11-28 00:38:16,127][87426] Updated weights for policy 1, policy_version 16240 (0.0008) -[2023-11-28 00:38:16,512][87426] Updated weights for policy 1, policy_version 16250 (0.0012) -[2023-11-28 00:38:18,258][87424] Updated weights for policy 0, policy_version 16356 (0.0009) -[2023-11-28 00:38:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 8347648. Throughput: 0: 2662.0, 1: 2702.6. Samples: 8361448. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 00:38:18,445][86177] Avg episode reward: [(0, '-580.690'), (1, '-597.790')] -[2023-11-28 00:38:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000016256_4161536.pth... -[2023-11-28 00:38:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000013728_3514368.pth -[2023-11-28 00:38:18,648][87424] Updated weights for policy 0, policy_version 16366 (0.0010) -[2023-11-28 00:38:18,910][87426] Updated weights for policy 1, policy_version 16260 (0.0010) -[2023-11-28 00:38:19,029][87424] Updated weights for policy 0, policy_version 16376 (0.0012) -[2023-11-28 00:38:19,290][87426] Updated weights for policy 1, policy_version 16270 (0.0011) -[2023-11-28 00:38:19,334][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000016384_4194304.pth... -[2023-11-28 00:38:19,378][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000013824_3538944.pth -[2023-11-28 00:38:19,675][87426] Updated weights for policy 1, policy_version 16280 (0.0012) -[2023-11-28 00:38:20,935][87424] Updated weights for policy 0, policy_version 16386 (0.0012) -[2023-11-28 00:38:21,327][87424] Updated weights for policy 0, policy_version 16396 (0.0012) -[2023-11-28 00:38:21,710][87424] Updated weights for policy 0, policy_version 16406 (0.0012) -[2023-11-28 00:38:21,880][87426] Updated weights for policy 1, policy_version 16290 (0.0011) -[2023-11-28 00:38:22,086][87424] Updated weights for policy 0, policy_version 16416 (0.0011) -[2023-11-28 00:38:22,260][87426] Updated weights for policy 1, policy_version 16300 (0.0010) -[2023-11-28 00:38:22,641][87426] Updated weights for policy 1, policy_version 16310 (0.0011) -[2023-11-28 00:38:23,017][87426] Updated weights for policy 1, policy_version 16320 (0.0010) -[2023-11-28 00:38:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 8380416. Throughput: 0: 2667.6, 1: 2721.7. Samples: 8395152. Policy #0 lag: (min: 9.0, avg: 35.2, max: 42.0) -[2023-11-28 00:38:23,445][86177] Avg episode reward: [(0, '-579.750'), (1, '-605.100')] -[2023-11-28 00:38:24,071][87424] Updated weights for policy 0, policy_version 16426 (0.0012) -[2023-11-28 00:38:24,459][87424] Updated weights for policy 0, policy_version 16436 (0.0011) -[2023-11-28 00:38:24,837][87424] Updated weights for policy 0, policy_version 16446 (0.0012) -[2023-11-28 00:38:24,865][87426] Updated weights for policy 1, policy_version 16330 (0.0011) -[2023-11-28 00:38:25,247][87426] Updated weights for policy 1, policy_version 16340 (0.0012) -[2023-11-28 00:38:25,619][87426] Updated weights for policy 1, policy_version 16350 (0.0012) -[2023-11-28 00:38:26,957][87424] Updated weights for policy 0, policy_version 16456 (0.0012) -[2023-11-28 00:38:27,344][87424] Updated weights for policy 0, policy_version 16466 (0.0012) -[2023-11-28 00:38:27,733][87424] Updated weights for policy 0, policy_version 16476 (0.0011) -[2023-11-28 00:38:27,952][87426] Updated weights for policy 1, policy_version 16360 (0.0009) -[2023-11-28 00:38:28,338][87426] Updated weights for policy 1, policy_version 16370 (0.0010) -[2023-11-28 00:38:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 8404992. Throughput: 0: 2670.2, 1: 2732.8. Samples: 8419652. Policy #0 lag: (min: 9.0, avg: 35.2, max: 42.0) -[2023-11-28 00:38:28,445][86177] Avg episode reward: [(0, '-578.760'), (1, '-665.450')] -[2023-11-28 00:38:28,709][87426] Updated weights for policy 1, policy_version 16380 (0.0007) -[2023-11-28 00:38:29,385][87424] Updated weights for policy 0, policy_version 16486 (0.0012) -[2023-11-28 00:38:29,770][87424] Updated weights for policy 0, policy_version 16496 (0.0012) -[2023-11-28 00:38:30,153][87424] Updated weights for policy 0, policy_version 16506 (0.0011) -[2023-11-28 00:38:30,519][87426] Updated weights for policy 1, policy_version 16390 (0.0012) -[2023-11-28 00:38:30,903][87426] Updated weights for policy 1, policy_version 16400 (0.0012) -[2023-11-28 00:38:31,287][87426] Updated weights for policy 1, policy_version 16410 (0.0012) -[2023-11-28 00:38:32,593][87424] Updated weights for policy 0, policy_version 16516 (0.0010) -[2023-11-28 00:38:32,975][87424] Updated weights for policy 0, policy_version 16526 (0.0010) -[2023-11-28 00:38:33,187][87426] Updated weights for policy 1, policy_version 16420 (0.0012) -[2023-11-28 00:38:33,358][87424] Updated weights for policy 0, policy_version 16536 (0.0009) -[2023-11-28 00:38:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 8429568. Throughput: 0: 2706.1, 1: 2746.1. Samples: 8445828. Policy #0 lag: (min: 9.0, avg: 35.2, max: 42.0) -[2023-11-28 00:38:33,445][86177] Avg episode reward: [(0, '-577.770'), (1, '-752.180')] -[2023-11-28 00:38:33,554][87426] Updated weights for policy 1, policy_version 16430 (0.0011) -[2023-11-28 00:38:33,933][87426] Updated weights for policy 1, policy_version 16440 (0.0012) -[2023-11-28 00:38:35,676][87424] Updated weights for policy 0, policy_version 16546 (0.0011) -[2023-11-28 00:38:36,057][87424] Updated weights for policy 0, policy_version 16556 (0.0011) -[2023-11-28 00:38:36,409][87426] Updated weights for policy 1, policy_version 16450 (0.0012) -[2023-11-28 00:38:36,443][87424] Updated weights for policy 0, policy_version 16566 (0.0010) -[2023-11-28 00:38:36,793][87426] Updated weights for policy 1, policy_version 16460 (0.0011) -[2023-11-28 00:38:36,814][87424] Updated weights for policy 0, policy_version 16576 (0.0009) -[2023-11-28 00:38:37,172][87426] Updated weights for policy 1, policy_version 16470 (0.0012) -[2023-11-28 00:38:37,554][87426] Updated weights for policy 1, policy_version 16480 (0.0012) -[2023-11-28 00:38:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 8462336. Throughput: 0: 2754.3, 1: 2729.6. Samples: 8478828. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 00:38:38,445][86177] Avg episode reward: [(0, '-577.820'), (1, '-748.610')] -[2023-11-28 00:38:38,651][87424] Updated weights for policy 0, policy_version 16586 (0.0012) -[2023-11-28 00:38:39,044][87424] Updated weights for policy 0, policy_version 16596 (0.0009) -[2023-11-28 00:38:39,419][87424] Updated weights for policy 0, policy_version 16606 (0.0010) -[2023-11-28 00:38:39,631][87426] Updated weights for policy 1, policy_version 16490 (0.0011) -[2023-11-28 00:38:40,004][87426] Updated weights for policy 1, policy_version 16500 (0.0011) -[2023-11-28 00:38:40,382][87426] Updated weights for policy 1, policy_version 16510 (0.0009) -[2023-11-28 00:38:41,250][87424] Updated weights for policy 0, policy_version 16616 (0.0012) -[2023-11-28 00:38:41,635][87424] Updated weights for policy 0, policy_version 16626 (0.0012) -[2023-11-28 00:38:42,015][87424] Updated weights for policy 0, policy_version 16636 (0.0012) -[2023-11-28 00:38:42,624][87426] Updated weights for policy 1, policy_version 16520 (0.0008) -[2023-11-28 00:38:43,004][87426] Updated weights for policy 1, policy_version 16530 (0.0008) -[2023-11-28 00:38:43,386][87426] Updated weights for policy 1, policy_version 16540 (0.0009) -[2023-11-28 00:38:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 8486912. Throughput: 0: 2758.1, 1: 2715.7. Samples: 8503912. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 00:38:43,445][86177] Avg episode reward: [(0, '-575.470'), (1, '-760.150')] -[2023-11-28 00:38:44,532][87424] Updated weights for policy 0, policy_version 16646 (0.0009) -[2023-11-28 00:38:44,913][87424] Updated weights for policy 0, policy_version 16656 (0.0009) -[2023-11-28 00:38:45,306][87424] Updated weights for policy 0, policy_version 16666 (0.0008) -[2023-11-28 00:38:45,657][87426] Updated weights for policy 1, policy_version 16550 (0.0010) -[2023-11-28 00:38:46,039][87426] Updated weights for policy 1, policy_version 16560 (0.0012) -[2023-11-28 00:38:46,414][87426] Updated weights for policy 1, policy_version 16570 (0.0012) -[2023-11-28 00:38:47,262][87424] Updated weights for policy 0, policy_version 16676 (0.0010) -[2023-11-28 00:38:47,647][87424] Updated weights for policy 0, policy_version 16686 (0.0010) -[2023-11-28 00:38:48,035][87424] Updated weights for policy 0, policy_version 16696 (0.0009) -[2023-11-28 00:38:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 8519680. Throughput: 0: 2753.2, 1: 2721.9. Samples: 8528248. Policy #0 lag: (min: 22.0, avg: 32.0, max: 54.0) -[2023-11-28 00:38:48,445][86177] Avg episode reward: [(0, '-579.240'), (1, '-747.170')] -[2023-11-28 00:38:48,567][87426] Updated weights for policy 1, policy_version 16580 (0.0010) -[2023-11-28 00:38:48,950][87426] Updated weights for policy 1, policy_version 16590 (0.0008) -[2023-11-28 00:38:49,336][87426] Updated weights for policy 1, policy_version 16600 (0.0008) -[2023-11-28 00:38:50,602][87424] Updated weights for policy 0, policy_version 16706 (0.0009) -[2023-11-28 00:38:50,980][87424] Updated weights for policy 0, policy_version 16716 (0.0012) -[2023-11-28 00:38:51,365][87424] Updated weights for policy 0, policy_version 16726 (0.0012) -[2023-11-28 00:38:51,701][87426] Updated weights for policy 1, policy_version 16610 (0.0008) -[2023-11-28 00:38:51,746][87424] Updated weights for policy 0, policy_version 16736 (0.0013) -[2023-11-28 00:38:52,075][87426] Updated weights for policy 1, policy_version 16620 (0.0011) -[2023-11-28 00:38:52,466][87426] Updated weights for policy 1, policy_version 16630 (0.0009) -[2023-11-28 00:38:52,840][87426] Updated weights for policy 1, policy_version 16640 (0.0010) -[2023-11-28 00:38:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 8544256. Throughput: 0: 2730.6, 1: 2730.2. Samples: 8560168. Policy #0 lag: (min: 22.0, avg: 32.0, max: 54.0) -[2023-11-28 00:38:53,446][86177] Avg episode reward: [(0, '-569.520'), (1, '-808.140')] -[2023-11-28 00:38:53,965][87424] Updated weights for policy 0, policy_version 16746 (0.0012) -[2023-11-28 00:38:54,348][87424] Updated weights for policy 0, policy_version 16756 (0.0010) -[2023-11-28 00:38:54,727][87424] Updated weights for policy 0, policy_version 16766 (0.0012) -[2023-11-28 00:38:54,967][87426] Updated weights for policy 1, policy_version 16650 (0.0011) -[2023-11-28 00:38:55,352][87426] Updated weights for policy 1, policy_version 16660 (0.0011) -[2023-11-28 00:38:55,738][87426] Updated weights for policy 1, policy_version 16670 (0.0011) -[2023-11-28 00:38:56,669][87424] Updated weights for policy 0, policy_version 16776 (0.0012) -[2023-11-28 00:38:57,043][87424] Updated weights for policy 0, policy_version 16786 (0.0012) -[2023-11-28 00:38:57,429][87424] Updated weights for policy 0, policy_version 16796 (0.0012) -[2023-11-28 00:38:57,878][87426] Updated weights for policy 1, policy_version 16680 (0.0012) -[2023-11-28 00:38:58,257][87426] Updated weights for policy 1, policy_version 16690 (0.0011) -[2023-11-28 00:38:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 8568832. Throughput: 0: 2737.7, 1: 2755.5. Samples: 8585036. Policy #0 lag: (min: 22.0, avg: 32.0, max: 54.0) -[2023-11-28 00:38:58,445][86177] Avg episode reward: [(0, '-587.630'), (1, '-729.670')] -[2023-11-28 00:38:58,652][87426] Updated weights for policy 1, policy_version 16700 (0.0011) -[2023-11-28 00:38:59,936][87424] Updated weights for policy 0, policy_version 16806 (0.0010) -[2023-11-28 00:39:00,323][87424] Updated weights for policy 0, policy_version 16816 (0.0007) -[2023-11-28 00:39:00,536][87426] Updated weights for policy 1, policy_version 16710 (0.0011) -[2023-11-28 00:39:00,708][87424] Updated weights for policy 0, policy_version 16826 (0.0008) -[2023-11-28 00:39:00,911][87426] Updated weights for policy 1, policy_version 16720 (0.0011) -[2023-11-28 00:39:01,295][87426] Updated weights for policy 1, policy_version 16730 (0.0012) -[2023-11-28 00:39:02,874][87424] Updated weights for policy 0, policy_version 16836 (0.0010) -[2023-11-28 00:39:03,258][87424] Updated weights for policy 0, policy_version 16846 (0.0012) -[2023-11-28 00:39:03,290][87426] Updated weights for policy 1, policy_version 16740 (0.0012) -[2023-11-28 00:39:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 8593408. Throughput: 0: 2775.7, 1: 2751.0. Samples: 8610152. Policy #0 lag: (min: 22.0, avg: 32.0, max: 54.0) -[2023-11-28 00:39:03,445][86177] Avg episode reward: [(0, '-564.250'), (1, '-738.720')] -[2023-11-28 00:39:03,643][87424] Updated weights for policy 0, policy_version 16856 (0.0011) -[2023-11-28 00:39:03,671][87426] Updated weights for policy 1, policy_version 16750 (0.0010) -[2023-11-28 00:39:04,048][87426] Updated weights for policy 1, policy_version 16760 (0.0012) -[2023-11-28 00:39:05,448][87424] Updated weights for policy 0, policy_version 16866 (0.0012) -[2023-11-28 00:39:05,820][87424] Updated weights for policy 0, policy_version 16876 (0.0009) -[2023-11-28 00:39:06,206][87424] Updated weights for policy 0, policy_version 16886 (0.0007) -[2023-11-28 00:39:06,355][87426] Updated weights for policy 1, policy_version 16770 (0.0012) -[2023-11-28 00:39:06,579][87424] Updated weights for policy 0, policy_version 16896 (0.0007) -[2023-11-28 00:39:06,732][87426] Updated weights for policy 1, policy_version 16780 (0.0009) -[2023-11-28 00:39:07,112][87426] Updated weights for policy 1, policy_version 16790 (0.0007) -[2023-11-28 00:39:07,496][87426] Updated weights for policy 1, policy_version 16800 (0.0007) -[2023-11-28 00:39:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 8626176. Throughput: 0: 2775.5, 1: 2738.3. Samples: 8643272. Policy #0 lag: (min: 31.0, avg: 48.2, max: 63.0) -[2023-11-28 00:39:08,445][86177] Avg episode reward: [(0, '-560.760'), (1, '-687.590')] -[2023-11-28 00:39:08,633][87424] Updated weights for policy 0, policy_version 16906 (0.0008) -[2023-11-28 00:39:09,021][87424] Updated weights for policy 0, policy_version 16916 (0.0010) -[2023-11-28 00:39:09,409][87424] Updated weights for policy 0, policy_version 16926 (0.0011) -[2023-11-28 00:39:09,769][87426] Updated weights for policy 1, policy_version 16810 (0.0012) -[2023-11-28 00:39:10,147][87426] Updated weights for policy 1, policy_version 16820 (0.0010) -[2023-11-28 00:39:10,527][87426] Updated weights for policy 1, policy_version 16830 (0.0008) -[2023-11-28 00:39:11,664][87424] Updated weights for policy 0, policy_version 16936 (0.0009) -[2023-11-28 00:39:12,048][87424] Updated weights for policy 0, policy_version 16946 (0.0012) -[2023-11-28 00:39:12,429][87424] Updated weights for policy 0, policy_version 16956 (0.0010) -[2023-11-28 00:39:12,623][87426] Updated weights for policy 1, policy_version 16840 (0.0010) -[2023-11-28 00:39:13,001][87426] Updated weights for policy 1, policy_version 16850 (0.0009) -[2023-11-28 00:39:13,387][87426] Updated weights for policy 1, policy_version 16860 (0.0008) -[2023-11-28 00:39:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 8650752. Throughput: 0: 2768.9, 1: 2744.6. Samples: 8667760. Policy #0 lag: (min: 31.0, avg: 48.2, max: 63.0) -[2023-11-28 00:39:13,445][86177] Avg episode reward: [(0, '-544.490'), (1, '-818.090')] -[2023-11-28 00:39:15,001][87424] Updated weights for policy 0, policy_version 16966 (0.0010) -[2023-11-28 00:39:15,089][87426] Updated weights for policy 1, policy_version 16870 (0.0010) -[2023-11-28 00:39:15,378][87424] Updated weights for policy 0, policy_version 16976 (0.0012) -[2023-11-28 00:39:15,468][87426] Updated weights for policy 1, policy_version 16880 (0.0011) -[2023-11-28 00:39:15,759][87424] Updated weights for policy 0, policy_version 16986 (0.0009) -[2023-11-28 00:39:15,845][87426] Updated weights for policy 1, policy_version 16890 (0.0011) -[2023-11-28 00:39:17,865][87424] Updated weights for policy 0, policy_version 16996 (0.0009) -[2023-11-28 00:39:18,243][87424] Updated weights for policy 0, policy_version 17006 (0.0012) -[2023-11-28 00:39:18,391][87426] Updated weights for policy 1, policy_version 16900 (0.0009) -[2023-11-28 00:39:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 8675328. Throughput: 0: 2718.0, 1: 2741.9. Samples: 8691520. Policy #0 lag: (min: 31.0, avg: 48.2, max: 63.0) -[2023-11-28 00:39:18,445][86177] Avg episode reward: [(0, '-528.480'), (1, '-780.980')] -[2023-11-28 00:39:18,632][87424] Updated weights for policy 0, policy_version 17016 (0.0011) -[2023-11-28 00:39:18,764][87426] Updated weights for policy 1, policy_version 16910 (0.0011) -[2023-11-28 00:39:18,932][87281] Saving new best policy, reward=-528.480! -[2023-11-28 00:39:19,140][87426] Updated weights for policy 1, policy_version 16920 (0.0011) -[2023-11-28 00:39:20,556][87424] Updated weights for policy 0, policy_version 17026 (0.0011) -[2023-11-28 00:39:20,940][87424] Updated weights for policy 0, policy_version 17036 (0.0012) -[2023-11-28 00:39:21,321][87424] Updated weights for policy 0, policy_version 17046 (0.0012) -[2023-11-28 00:39:21,467][87426] Updated weights for policy 1, policy_version 16930 (0.0011) -[2023-11-28 00:39:21,702][87424] Updated weights for policy 0, policy_version 17056 (0.0032) -[2023-11-28 00:39:21,852][87426] Updated weights for policy 1, policy_version 16940 (0.0011) -[2023-11-28 00:39:22,224][87426] Updated weights for policy 1, policy_version 16950 (0.0012) -[2023-11-28 00:39:22,606][87426] Updated weights for policy 1, policy_version 16960 (0.0008) -[2023-11-28 00:39:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 8708096. Throughput: 0: 2709.7, 1: 2745.3. Samples: 8724304. Policy #0 lag: (min: 7.0, avg: 18.0, max: 39.0) -[2023-11-28 00:39:23,445][86177] Avg episode reward: [(0, '-526.930'), (1, '-656.350')] -[2023-11-28 00:39:23,446][87281] Saving new best policy, reward=-526.930! -[2023-11-28 00:39:24,099][87424] Updated weights for policy 0, policy_version 17066 (0.0012) -[2023-11-28 00:39:24,483][87424] Updated weights for policy 0, policy_version 17076 (0.0012) -[2023-11-28 00:39:24,754][87426] Updated weights for policy 1, policy_version 16970 (0.0012) -[2023-11-28 00:39:24,868][87424] Updated weights for policy 0, policy_version 17086 (0.0012) -[2023-11-28 00:39:25,130][87426] Updated weights for policy 1, policy_version 16980 (0.0010) -[2023-11-28 00:39:25,510][87426] Updated weights for policy 1, policy_version 16990 (0.0007) -[2023-11-28 00:39:26,682][87424] Updated weights for policy 0, policy_version 17096 (0.0010) -[2023-11-28 00:39:27,065][87426] Updated weights for policy 1, policy_version 17000 (0.0010) -[2023-11-28 00:39:27,068][87424] Updated weights for policy 0, policy_version 17106 (0.0008) -[2023-11-28 00:39:27,449][87424] Updated weights for policy 0, policy_version 17116 (0.0012) -[2023-11-28 00:39:27,459][87426] Updated weights for policy 1, policy_version 17010 (0.0007) -[2023-11-28 00:39:27,846][87426] Updated weights for policy 1, policy_version 17020 (0.0007) -[2023-11-28 00:39:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 8740864. Throughput: 0: 2711.7, 1: 2754.5. Samples: 8749892. Policy #0 lag: (min: 7.0, avg: 18.0, max: 39.0) -[2023-11-28 00:39:28,445][86177] Avg episode reward: [(0, '-527.090'), (1, '-738.260')] -[2023-11-28 00:39:29,455][87424] Updated weights for policy 0, policy_version 17126 (0.0011) -[2023-11-28 00:39:29,830][87424] Updated weights for policy 0, policy_version 17136 (0.0011) -[2023-11-28 00:39:30,140][87426] Updated weights for policy 1, policy_version 17030 (0.0010) -[2023-11-28 00:39:30,214][87424] Updated weights for policy 0, policy_version 17146 (0.0011) -[2023-11-28 00:39:30,517][87426] Updated weights for policy 1, policy_version 17040 (0.0009) -[2023-11-28 00:39:30,896][87426] Updated weights for policy 1, policy_version 17050 (0.0007) -[2023-11-28 00:39:32,556][87424] Updated weights for policy 0, policy_version 17156 (0.0011) -[2023-11-28 00:39:32,929][87424] Updated weights for policy 0, policy_version 17166 (0.0008) -[2023-11-28 00:39:33,139][87426] Updated weights for policy 1, policy_version 17060 (0.0009) -[2023-11-28 00:39:33,311][87424] Updated weights for policy 0, policy_version 17176 (0.0007) -[2023-11-28 00:39:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 8757248. Throughput: 0: 2736.6, 1: 2768.7. Samples: 8775988. Policy #0 lag: (min: 7.0, avg: 18.0, max: 39.0) -[2023-11-28 00:39:33,445][86177] Avg episode reward: [(0, '-526.210'), (1, '-724.690')] -[2023-11-28 00:39:33,517][87426] Updated weights for policy 1, policy_version 17070 (0.0011) -[2023-11-28 00:39:33,621][87281] Saving new best policy, reward=-526.210! -[2023-11-28 00:39:33,893][87426] Updated weights for policy 1, policy_version 17080 (0.0008) -[2023-11-28 00:39:35,041][87424] Updated weights for policy 0, policy_version 17186 (0.0008) -[2023-11-28 00:39:35,423][87424] Updated weights for policy 0, policy_version 17196 (0.0012) -[2023-11-28 00:39:35,801][87424] Updated weights for policy 0, policy_version 17206 (0.0012) -[2023-11-28 00:39:36,196][87424] Updated weights for policy 0, policy_version 17216 (0.0012) -[2023-11-28 00:39:36,372][87426] Updated weights for policy 1, policy_version 17090 (0.0008) -[2023-11-28 00:39:36,755][87426] Updated weights for policy 1, policy_version 17100 (0.0010) -[2023-11-28 00:39:37,136][87426] Updated weights for policy 1, policy_version 17110 (0.0011) -[2023-11-28 00:39:37,516][87426] Updated weights for policy 1, policy_version 17120 (0.0008) -[2023-11-28 00:39:38,184][87424] Updated weights for policy 0, policy_version 17226 (0.0008) -[2023-11-28 00:39:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 8790016. Throughput: 0: 2789.0, 1: 2763.6. Samples: 8810036. Policy #0 lag: (min: 3.0, avg: 23.0, max: 53.0) -[2023-11-28 00:39:38,445][86177] Avg episode reward: [(0, '-597.430'), (1, '-660.940')] -[2023-11-28 00:39:38,567][87424] Updated weights for policy 0, policy_version 17236 (0.0007) -[2023-11-28 00:39:38,952][87424] Updated weights for policy 0, policy_version 17246 (0.0008) -[2023-11-28 00:39:39,335][87426] Updated weights for policy 1, policy_version 17130 (0.0012) -[2023-11-28 00:39:39,705][87426] Updated weights for policy 1, policy_version 17140 (0.0012) -[2023-11-28 00:39:40,077][87426] Updated weights for policy 1, policy_version 17150 (0.0012) -[2023-11-28 00:39:41,048][87424] Updated weights for policy 0, policy_version 17256 (0.0011) -[2023-11-28 00:39:41,432][87424] Updated weights for policy 0, policy_version 17266 (0.0009) -[2023-11-28 00:39:41,817][87424] Updated weights for policy 0, policy_version 17276 (0.0009) -[2023-11-28 00:39:42,590][87426] Updated weights for policy 1, policy_version 17160 (0.0010) -[2023-11-28 00:39:42,965][87426] Updated weights for policy 1, policy_version 17170 (0.0011) -[2023-11-28 00:39:43,340][87426] Updated weights for policy 1, policy_version 17180 (0.0010) -[2023-11-28 00:39:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 8814592. Throughput: 0: 2791.7, 1: 2718.3. Samples: 8832988. Policy #0 lag: (min: 3.0, avg: 23.0, max: 53.0) -[2023-11-28 00:39:43,445][86177] Avg episode reward: [(0, '-636.120'), (1, '-732.700')] -[2023-11-28 00:39:44,172][87424] Updated weights for policy 0, policy_version 17286 (0.0011) -[2023-11-28 00:39:44,554][87424] Updated weights for policy 0, policy_version 17296 (0.0012) -[2023-11-28 00:39:44,932][87424] Updated weights for policy 0, policy_version 17306 (0.0011) -[2023-11-28 00:39:45,109][87426] Updated weights for policy 1, policy_version 17190 (0.0012) -[2023-11-28 00:39:45,490][87426] Updated weights for policy 1, policy_version 17200 (0.0012) -[2023-11-28 00:39:45,872][87426] Updated weights for policy 1, policy_version 17210 (0.0011) -[2023-11-28 00:39:46,641][87424] Updated weights for policy 0, policy_version 17316 (0.0010) -[2023-11-28 00:39:47,023][87424] Updated weights for policy 0, policy_version 17326 (0.0007) -[2023-11-28 00:39:47,412][87424] Updated weights for policy 0, policy_version 17336 (0.0007) -[2023-11-28 00:39:48,033][87426] Updated weights for policy 1, policy_version 17220 (0.0010) -[2023-11-28 00:39:48,412][87426] Updated weights for policy 1, policy_version 17230 (0.0007) -[2023-11-28 00:39:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 8847360. Throughput: 0: 2804.7, 1: 2711.7. Samples: 8858392. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 00:39:48,445][86177] Avg episode reward: [(0, '-631.270'), (1, '-733.270')] -[2023-11-28 00:39:48,793][87426] Updated weights for policy 1, policy_version 17240 (0.0007) -[2023-11-28 00:39:49,749][87424] Updated weights for policy 0, policy_version 17346 (0.0008) -[2023-11-28 00:39:50,130][87424] Updated weights for policy 0, policy_version 17356 (0.0009) -[2023-11-28 00:39:50,517][87424] Updated weights for policy 0, policy_version 17366 (0.0009) -[2023-11-28 00:39:50,902][87424] Updated weights for policy 0, policy_version 17376 (0.0011) -[2023-11-28 00:39:51,334][87426] Updated weights for policy 1, policy_version 17250 (0.0009) -[2023-11-28 00:39:51,708][87426] Updated weights for policy 1, policy_version 17260 (0.0010) -[2023-11-28 00:39:52,088][87426] Updated weights for policy 1, policy_version 17270 (0.0010) -[2023-11-28 00:39:52,474][87426] Updated weights for policy 1, policy_version 17280 (0.0009) -[2023-11-28 00:39:53,394][87424] Updated weights for policy 0, policy_version 17386 (0.0011) -[2023-11-28 00:39:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 8871936. Throughput: 0: 2772.5, 1: 2732.1. Samples: 8890980. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 00:39:53,445][86177] Avg episode reward: [(0, '-645.910'), (1, '-702.490')] -[2023-11-28 00:39:53,783][87424] Updated weights for policy 0, policy_version 17396 (0.0011) -[2023-11-28 00:39:54,169][87424] Updated weights for policy 0, policy_version 17406 (0.0009) -[2023-11-28 00:39:54,874][87426] Updated weights for policy 1, policy_version 17290 (0.0009) -[2023-11-28 00:39:55,243][87426] Updated weights for policy 1, policy_version 17300 (0.0011) -[2023-11-28 00:39:55,617][87426] Updated weights for policy 1, policy_version 17310 (0.0012) -[2023-11-28 00:39:56,191][87424] Updated weights for policy 0, policy_version 17416 (0.0007) -[2023-11-28 00:39:56,564][87424] Updated weights for policy 0, policy_version 17426 (0.0008) -[2023-11-28 00:39:56,949][87424] Updated weights for policy 0, policy_version 17436 (0.0007) -[2023-11-28 00:39:57,455][87426] Updated weights for policy 1, policy_version 17320 (0.0012) -[2023-11-28 00:39:57,838][87426] Updated weights for policy 1, policy_version 17330 (0.0012) -[2023-11-28 00:39:58,219][87426] Updated weights for policy 1, policy_version 17340 (0.0011) -[2023-11-28 00:39:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 8904704. Throughput: 0: 2765.4, 1: 2721.9. Samples: 8914688. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 00:39:58,445][86177] Avg episode reward: [(0, '-577.320'), (1, '-782.560')] -[2023-11-28 00:39:58,970][87424] Updated weights for policy 0, policy_version 17446 (0.0010) -[2023-11-28 00:39:59,353][87424] Updated weights for policy 0, policy_version 17456 (0.0012) -[2023-11-28 00:39:59,741][87424] Updated weights for policy 0, policy_version 17466 (0.0012) -[2023-11-28 00:40:00,482][87426] Updated weights for policy 1, policy_version 17350 (0.0011) -[2023-11-28 00:40:00,855][87426] Updated weights for policy 1, policy_version 17360 (0.0010) -[2023-11-28 00:40:01,234][87426] Updated weights for policy 1, policy_version 17370 (0.0008) -[2023-11-28 00:40:02,290][87424] Updated weights for policy 0, policy_version 17476 (0.0012) -[2023-11-28 00:40:02,678][87424] Updated weights for policy 0, policy_version 17486 (0.0008) -[2023-11-28 00:40:03,081][87424] Updated weights for policy 0, policy_version 17496 (0.0009) -[2023-11-28 00:40:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 8929280. Throughput: 0: 2788.6, 1: 2730.6. Samples: 8939884. Policy #0 lag: (min: 17.0, avg: 41.4, max: 61.0) -[2023-11-28 00:40:03,445][86177] Avg episode reward: [(0, '-540.040'), (1, '-679.040')] -[2023-11-28 00:40:03,551][87426] Updated weights for policy 1, policy_version 17380 (0.0009) -[2023-11-28 00:40:03,932][87426] Updated weights for policy 1, policy_version 17390 (0.0012) -[2023-11-28 00:40:04,313][87426] Updated weights for policy 1, policy_version 17400 (0.0012) -[2023-11-28 00:40:04,810][87424] Updated weights for policy 0, policy_version 17506 (0.0012) -[2023-11-28 00:40:05,185][87424] Updated weights for policy 0, policy_version 17516 (0.0012) -[2023-11-28 00:40:05,562][87424] Updated weights for policy 0, policy_version 17526 (0.0012) -[2023-11-28 00:40:05,948][87424] Updated weights for policy 0, policy_version 17536 (0.0008) -[2023-11-28 00:40:06,638][87426] Updated weights for policy 1, policy_version 17410 (0.0009) -[2023-11-28 00:40:07,024][87426] Updated weights for policy 1, policy_version 17420 (0.0008) -[2023-11-28 00:40:07,392][87426] Updated weights for policy 1, policy_version 17430 (0.0008) -[2023-11-28 00:40:07,774][87426] Updated weights for policy 1, policy_version 17440 (0.0011) -[2023-11-28 00:40:08,083][87424] Updated weights for policy 0, policy_version 17546 (0.0011) -[2023-11-28 00:40:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 8953856. Throughput: 0: 2768.2, 1: 2736.7. Samples: 8972024. Policy #0 lag: (min: 17.0, avg: 41.4, max: 61.0) -[2023-11-28 00:40:08,445][86177] Avg episode reward: [(0, '-585.950'), (1, '-749.940')] -[2023-11-28 00:40:08,459][87424] Updated weights for policy 0, policy_version 17556 (0.0009) -[2023-11-28 00:40:08,839][87424] Updated weights for policy 0, policy_version 17566 (0.0007) -[2023-11-28 00:40:10,229][87426] Updated weights for policy 1, policy_version 17450 (0.0012) -[2023-11-28 00:40:10,607][87426] Updated weights for policy 1, policy_version 17460 (0.0012) -[2023-11-28 00:40:10,991][87426] Updated weights for policy 1, policy_version 17470 (0.0012) -[2023-11-28 00:40:11,273][87424] Updated weights for policy 0, policy_version 17576 (0.0010) -[2023-11-28 00:40:11,654][87424] Updated weights for policy 0, policy_version 17586 (0.0012) -[2023-11-28 00:40:12,039][87424] Updated weights for policy 0, policy_version 17596 (0.0012) -[2023-11-28 00:40:13,029][87426] Updated weights for policy 1, policy_version 17480 (0.0010) -[2023-11-28 00:40:13,403][87426] Updated weights for policy 1, policy_version 17490 (0.0007) -[2023-11-28 00:40:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 8978432. Throughput: 0: 2742.1, 1: 2710.9. Samples: 8995280. Policy #0 lag: (min: 17.0, avg: 41.4, max: 61.0) -[2023-11-28 00:40:13,445][86177] Avg episode reward: [(0, '-580.110'), (1, '-787.160')] -[2023-11-28 00:40:13,788][87426] Updated weights for policy 1, policy_version 17500 (0.0007) -[2023-11-28 00:40:14,279][87424] Updated weights for policy 0, policy_version 17606 (0.0009) -[2023-11-28 00:40:14,664][87424] Updated weights for policy 0, policy_version 17616 (0.0008) -[2023-11-28 00:40:15,045][87424] Updated weights for policy 0, policy_version 17626 (0.0007) -[2023-11-28 00:40:15,583][87426] Updated weights for policy 1, policy_version 17510 (0.0010) -[2023-11-28 00:40:15,960][87426] Updated weights for policy 1, policy_version 17520 (0.0010) -[2023-11-28 00:40:16,341][87426] Updated weights for policy 1, policy_version 17530 (0.0009) -[2023-11-28 00:40:17,481][87424] Updated weights for policy 0, policy_version 17636 (0.0009) -[2023-11-28 00:40:17,862][87424] Updated weights for policy 0, policy_version 17646 (0.0011) -[2023-11-28 00:40:18,244][87424] Updated weights for policy 0, policy_version 17656 (0.0012) -[2023-11-28 00:40:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 9003008. Throughput: 0: 2709.3, 1: 2687.6. Samples: 9018848. Policy #0 lag: (min: 17.0, avg: 41.4, max: 61.0) -[2023-11-28 00:40:18,445][86177] Avg episode reward: [(0, '-571.260'), (1, '-713.910')] -[2023-11-28 00:40:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000017536_4489216.pth... -[2023-11-28 00:40:18,489][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000015008_3842048.pth -[2023-11-28 00:40:18,553][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000017664_4521984.pth... -[2023-11-28 00:40:18,585][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000015104_3866624.pth -[2023-11-28 00:40:18,771][87426] Updated weights for policy 1, policy_version 17540 (0.0009) -[2023-11-28 00:40:19,165][87426] Updated weights for policy 1, policy_version 17550 (0.0010) -[2023-11-28 00:40:19,537][87426] Updated weights for policy 1, policy_version 17560 (0.0010) -[2023-11-28 00:40:20,296][87424] Updated weights for policy 0, policy_version 17666 (0.0011) -[2023-11-28 00:40:20,680][87424] Updated weights for policy 0, policy_version 17676 (0.0008) -[2023-11-28 00:40:21,068][87424] Updated weights for policy 0, policy_version 17686 (0.0009) -[2023-11-28 00:40:21,454][87424] Updated weights for policy 0, policy_version 17696 (0.0009) -[2023-11-28 00:40:21,995][87426] Updated weights for policy 1, policy_version 17570 (0.0009) -[2023-11-28 00:40:22,372][87426] Updated weights for policy 1, policy_version 17580 (0.0015) -[2023-11-28 00:40:22,756][87426] Updated weights for policy 1, policy_version 17590 (0.0011) -[2023-11-28 00:40:23,124][87426] Updated weights for policy 1, policy_version 17600 (0.0008) -[2023-11-28 00:40:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 9035776. Throughput: 0: 2677.9, 1: 2674.0. Samples: 9050868. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 00:40:23,445][86177] Avg episode reward: [(0, '-576.720'), (1, '-704.330')] -[2023-11-28 00:40:24,026][87424] Updated weights for policy 0, policy_version 17706 (0.0012) -[2023-11-28 00:40:24,411][87424] Updated weights for policy 0, policy_version 17716 (0.0012) -[2023-11-28 00:40:24,789][87424] Updated weights for policy 0, policy_version 17726 (0.0012) -[2023-11-28 00:40:25,741][87426] Updated weights for policy 1, policy_version 17610 (0.0008) -[2023-11-28 00:40:26,115][87426] Updated weights for policy 1, policy_version 17620 (0.0011) -[2023-11-28 00:40:26,490][87426] Updated weights for policy 1, policy_version 17630 (0.0011) -[2023-11-28 00:40:27,218][87424] Updated weights for policy 0, policy_version 17736 (0.0012) -[2023-11-28 00:40:27,594][87424] Updated weights for policy 0, policy_version 17746 (0.0011) -[2023-11-28 00:40:27,982][87424] Updated weights for policy 0, policy_version 17756 (0.0007) -[2023-11-28 00:40:28,239][87426] Updated weights for policy 1, policy_version 17640 (0.0012) -[2023-11-28 00:40:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 9060352. Throughput: 0: 2665.3, 1: 2730.4. Samples: 9075796. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 00:40:28,445][86177] Avg episode reward: [(0, '-594.600'), (1, '-640.480')] -[2023-11-28 00:40:28,623][87426] Updated weights for policy 1, policy_version 17650 (0.0011) -[2023-11-28 00:40:29,003][87426] Updated weights for policy 1, policy_version 17660 (0.0012) -[2023-11-28 00:40:30,211][87424] Updated weights for policy 0, policy_version 17766 (0.0010) -[2023-11-28 00:40:30,601][87424] Updated weights for policy 0, policy_version 17776 (0.0011) -[2023-11-28 00:40:30,972][87424] Updated weights for policy 0, policy_version 17786 (0.0012) -[2023-11-28 00:40:31,150][87426] Updated weights for policy 1, policy_version 17670 (0.0009) -[2023-11-28 00:40:31,530][87426] Updated weights for policy 1, policy_version 17680 (0.0011) -[2023-11-28 00:40:31,910][87426] Updated weights for policy 1, policy_version 17690 (0.0010) -[2023-11-28 00:40:32,788][87424] Updated weights for policy 0, policy_version 17796 (0.0011) -[2023-11-28 00:40:33,174][87424] Updated weights for policy 0, policy_version 17806 (0.0010) -[2023-11-28 00:40:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 9084928. Throughput: 0: 2642.2, 1: 2725.3. Samples: 9099932. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 00:40:33,445][86177] Avg episode reward: [(0, '-595.100'), (1, '-640.310')] -[2023-11-28 00:40:33,564][87424] Updated weights for policy 0, policy_version 17816 (0.0010) -[2023-11-28 00:40:34,211][87426] Updated weights for policy 1, policy_version 17700 (0.0008) -[2023-11-28 00:40:34,588][87426] Updated weights for policy 1, policy_version 17710 (0.0007) -[2023-11-28 00:40:34,972][87426] Updated weights for policy 1, policy_version 17720 (0.0009) -[2023-11-28 00:40:36,116][87424] Updated weights for policy 0, policy_version 17826 (0.0009) -[2023-11-28 00:40:36,512][87424] Updated weights for policy 0, policy_version 17836 (0.0007) -[2023-11-28 00:40:36,893][87424] Updated weights for policy 0, policy_version 17846 (0.0010) -[2023-11-28 00:40:37,283][87424] Updated weights for policy 0, policy_version 17856 (0.0012) -[2023-11-28 00:40:37,461][87426] Updated weights for policy 1, policy_version 17730 (0.0008) -[2023-11-28 00:40:37,837][87426] Updated weights for policy 1, policy_version 17740 (0.0012) -[2023-11-28 00:40:38,218][87426] Updated weights for policy 1, policy_version 17750 (0.0010) -[2023-11-28 00:40:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 9109504. Throughput: 0: 2642.4, 1: 2701.2. Samples: 9131444. Policy #0 lag: (min: 30.0, avg: 50.3, max: 76.0) -[2023-11-28 00:40:38,445][86177] Avg episode reward: [(0, '-609.570'), (1, '-651.720')] -[2023-11-28 00:40:38,605][87426] Updated weights for policy 1, policy_version 17760 (0.0008) -[2023-11-28 00:40:39,215][87424] Updated weights for policy 0, policy_version 17866 (0.0011) -[2023-11-28 00:40:39,597][87424] Updated weights for policy 0, policy_version 17876 (0.0011) -[2023-11-28 00:40:39,989][87424] Updated weights for policy 0, policy_version 17886 (0.0011) -[2023-11-28 00:40:40,921][87426] Updated weights for policy 1, policy_version 17770 (0.0011) -[2023-11-28 00:40:41,308][87426] Updated weights for policy 1, policy_version 17780 (0.0011) -[2023-11-28 00:40:41,690][87426] Updated weights for policy 1, policy_version 17790 (0.0011) -[2023-11-28 00:40:41,735][87424] Updated weights for policy 0, policy_version 17896 (0.0012) -[2023-11-28 00:40:42,113][87424] Updated weights for policy 0, policy_version 17906 (0.0012) -[2023-11-28 00:40:42,490][87424] Updated weights for policy 0, policy_version 17916 (0.0012) -[2023-11-28 00:40:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 9142272. Throughput: 0: 2657.3, 1: 2690.0. Samples: 9155320. Policy #0 lag: (min: 30.0, avg: 50.3, max: 76.0) -[2023-11-28 00:40:43,445][86177] Avg episode reward: [(0, '-606.660'), (1, '-627.740')] -[2023-11-28 00:40:43,838][87426] Updated weights for policy 1, policy_version 17800 (0.0011) -[2023-11-28 00:40:44,209][87426] Updated weights for policy 1, policy_version 17810 (0.0011) -[2023-11-28 00:40:44,587][87426] Updated weights for policy 1, policy_version 17820 (0.0012) -[2023-11-28 00:40:44,831][87424] Updated weights for policy 0, policy_version 17926 (0.0011) -[2023-11-28 00:40:45,215][87424] Updated weights for policy 0, policy_version 17936 (0.0009) -[2023-11-28 00:40:45,599][87424] Updated weights for policy 0, policy_version 17946 (0.0009) -[2023-11-28 00:40:46,913][87426] Updated weights for policy 1, policy_version 17830 (0.0009) -[2023-11-28 00:40:47,293][87426] Updated weights for policy 1, policy_version 17840 (0.0008) -[2023-11-28 00:40:47,668][87426] Updated weights for policy 1, policy_version 17850 (0.0007) -[2023-11-28 00:40:48,102][87424] Updated weights for policy 0, policy_version 17956 (0.0008) -[2023-11-28 00:40:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 9166848. Throughput: 0: 2660.4, 1: 2662.9. Samples: 9179432. Policy #0 lag: (min: 30.0, avg: 50.3, max: 76.0) -[2023-11-28 00:40:48,445][86177] Avg episode reward: [(0, '-640.360'), (1, '-612.500')] -[2023-11-28 00:40:48,483][87424] Updated weights for policy 0, policy_version 17966 (0.0008) -[2023-11-28 00:40:48,866][87424] Updated weights for policy 0, policy_version 17976 (0.0008) -[2023-11-28 00:40:49,927][87426] Updated weights for policy 1, policy_version 17860 (0.0008) -[2023-11-28 00:40:50,301][87426] Updated weights for policy 1, policy_version 17870 (0.0009) -[2023-11-28 00:40:50,677][87426] Updated weights for policy 1, policy_version 17880 (0.0011) -[2023-11-28 00:40:51,312][87424] Updated weights for policy 0, policy_version 17986 (0.0008) -[2023-11-28 00:40:51,692][87424] Updated weights for policy 0, policy_version 17996 (0.0008) -[2023-11-28 00:40:52,078][87424] Updated weights for policy 0, policy_version 18006 (0.0011) -[2023-11-28 00:40:52,455][87424] Updated weights for policy 0, policy_version 18016 (0.0011) -[2023-11-28 00:40:52,807][87426] Updated weights for policy 1, policy_version 17890 (0.0009) -[2023-11-28 00:40:53,191][87426] Updated weights for policy 1, policy_version 17900 (0.0011) -[2023-11-28 00:40:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 9191424. Throughput: 0: 2645.4, 1: 2658.0. Samples: 9210676. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-11-28 00:40:53,445][86177] Avg episode reward: [(0, '-641.190'), (1, '-631.890')] -[2023-11-28 00:40:53,573][87426] Updated weights for policy 1, policy_version 17910 (0.0011) -[2023-11-28 00:40:53,945][87426] Updated weights for policy 1, policy_version 17920 (0.0012) -[2023-11-28 00:40:54,748][87424] Updated weights for policy 0, policy_version 18026 (0.0009) -[2023-11-28 00:40:55,127][87424] Updated weights for policy 0, policy_version 18036 (0.0009) -[2023-11-28 00:40:55,513][87424] Updated weights for policy 0, policy_version 18046 (0.0012) -[2023-11-28 00:40:55,898][87426] Updated weights for policy 1, policy_version 17930 (0.0008) -[2023-11-28 00:40:56,287][87426] Updated weights for policy 1, policy_version 17940 (0.0007) -[2023-11-28 00:40:56,662][87426] Updated weights for policy 1, policy_version 17950 (0.0010) -[2023-11-28 00:40:57,828][87424] Updated weights for policy 0, policy_version 18056 (0.0012) -[2023-11-28 00:40:58,207][87424] Updated weights for policy 0, policy_version 18066 (0.0012) -[2023-11-28 00:40:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.2, 300 sec: 5387.3). Total num frames: 9216000. Throughput: 0: 2652.8, 1: 2699.8. Samples: 9236148. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-11-28 00:40:58,445][86177] Avg episode reward: [(0, '-598.280'), (1, '-630.250')] -[2023-11-28 00:40:58,587][87426] Updated weights for policy 1, policy_version 17960 (0.0008) -[2023-11-28 00:40:58,594][87424] Updated weights for policy 0, policy_version 18076 (0.0011) -[2023-11-28 00:40:58,965][87426] Updated weights for policy 1, policy_version 17970 (0.0009) -[2023-11-28 00:40:59,352][87426] Updated weights for policy 1, policy_version 17980 (0.0009) -[2023-11-28 00:41:00,632][87424] Updated weights for policy 0, policy_version 18086 (0.0008) -[2023-11-28 00:41:01,013][87424] Updated weights for policy 0, policy_version 18096 (0.0007) -[2023-11-28 00:41:01,399][87424] Updated weights for policy 0, policy_version 18106 (0.0008) -[2023-11-28 00:41:01,429][87426] Updated weights for policy 1, policy_version 17990 (0.0012) -[2023-11-28 00:41:01,803][87426] Updated weights for policy 1, policy_version 18000 (0.0011) -[2023-11-28 00:41:02,192][87426] Updated weights for policy 1, policy_version 18010 (0.0010) -[2023-11-28 00:41:03,429][87424] Updated weights for policy 0, policy_version 18116 (0.0010) -[2023-11-28 00:41:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 9248768. Throughput: 0: 2657.7, 1: 2710.1. Samples: 9260396. Policy #0 lag: (min: 31.0, avg: 34.7, max: 63.0) -[2023-11-28 00:41:03,445][86177] Avg episode reward: [(0, '-606.070'), (1, '-640.510')] -[2023-11-28 00:41:03,811][87424] Updated weights for policy 0, policy_version 18126 (0.0012) -[2023-11-28 00:41:04,193][87424] Updated weights for policy 0, policy_version 18136 (0.0011) -[2023-11-28 00:41:04,421][87426] Updated weights for policy 1, policy_version 18020 (0.0010) -[2023-11-28 00:41:04,807][87426] Updated weights for policy 1, policy_version 18030 (0.0011) -[2023-11-28 00:41:05,180][87426] Updated weights for policy 1, policy_version 18040 (0.0011) -[2023-11-28 00:41:06,691][87424] Updated weights for policy 0, policy_version 18146 (0.0009) -[2023-11-28 00:41:07,078][87424] Updated weights for policy 0, policy_version 18156 (0.0010) -[2023-11-28 00:41:07,344][87426] Updated weights for policy 1, policy_version 18050 (0.0011) -[2023-11-28 00:41:07,464][87424] Updated weights for policy 0, policy_version 18166 (0.0011) -[2023-11-28 00:41:07,718][87426] Updated weights for policy 1, policy_version 18060 (0.0007) -[2023-11-28 00:41:07,845][87424] Updated weights for policy 0, policy_version 18176 (0.0010) -[2023-11-28 00:41:08,107][87426] Updated weights for policy 1, policy_version 18070 (0.0008) -[2023-11-28 00:41:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 9273344. Throughput: 0: 2652.0, 1: 2719.6. Samples: 9292592. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:41:08,445][86177] Avg episode reward: [(0, '-566.910'), (1, '-635.300')] -[2023-11-28 00:41:08,480][87426] Updated weights for policy 1, policy_version 18080 (0.0012) -[2023-11-28 00:41:09,580][87424] Updated weights for policy 0, policy_version 18186 (0.0012) -[2023-11-28 00:41:09,957][87424] Updated weights for policy 0, policy_version 18196 (0.0012) -[2023-11-28 00:41:10,343][87424] Updated weights for policy 0, policy_version 18206 (0.0010) -[2023-11-28 00:41:10,498][87426] Updated weights for policy 1, policy_version 18090 (0.0012) -[2023-11-28 00:41:10,874][87426] Updated weights for policy 1, policy_version 18100 (0.0010) -[2023-11-28 00:41:11,255][87426] Updated weights for policy 1, policy_version 18110 (0.0009) -[2023-11-28 00:41:12,905][87424] Updated weights for policy 0, policy_version 18216 (0.0011) -[2023-11-28 00:41:13,292][87424] Updated weights for policy 0, policy_version 18226 (0.0009) -[2023-11-28 00:41:13,391][87426] Updated weights for policy 1, policy_version 18120 (0.0010) -[2023-11-28 00:41:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 9297920. Throughput: 0: 2666.2, 1: 2708.3. Samples: 9317652. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:41:13,445][86177] Avg episode reward: [(0, '-551.460'), (1, '-639.830')] -[2023-11-28 00:41:13,674][87424] Updated weights for policy 0, policy_version 18236 (0.0008) -[2023-11-28 00:41:13,769][87426] Updated weights for policy 1, policy_version 18130 (0.0012) -[2023-11-28 00:41:14,149][87426] Updated weights for policy 1, policy_version 18140 (0.0007) -[2023-11-28 00:41:15,572][87424] Updated weights for policy 0, policy_version 18246 (0.0010) -[2023-11-28 00:41:15,892][87426] Updated weights for policy 1, policy_version 18150 (0.0010) -[2023-11-28 00:41:15,956][87424] Updated weights for policy 0, policy_version 18256 (0.0011) -[2023-11-28 00:41:16,265][87426] Updated weights for policy 1, policy_version 18160 (0.0011) -[2023-11-28 00:41:16,346][87424] Updated weights for policy 0, policy_version 18266 (0.0011) -[2023-11-28 00:41:16,644][87426] Updated weights for policy 1, policy_version 18170 (0.0012) -[2023-11-28 00:41:18,406][87424] Updated weights for policy 0, policy_version 18276 (0.0011) -[2023-11-28 00:41:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9330688. Throughput: 0: 2666.5, 1: 2724.8. Samples: 9342540. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 00:41:18,445][86177] Avg episode reward: [(0, '-588.780'), (1, '-595.160')] -[2023-11-28 00:41:18,591][87426] Updated weights for policy 1, policy_version 18180 (0.0012) -[2023-11-28 00:41:18,795][87424] Updated weights for policy 0, policy_version 18286 (0.0011) -[2023-11-28 00:41:18,963][87426] Updated weights for policy 1, policy_version 18190 (0.0011) -[2023-11-28 00:41:19,176][87424] Updated weights for policy 0, policy_version 18296 (0.0012) -[2023-11-28 00:41:19,349][87426] Updated weights for policy 1, policy_version 18200 (0.0008) -[2023-11-28 00:41:21,096][87424] Updated weights for policy 0, policy_version 18306 (0.0011) -[2023-11-28 00:41:21,488][87424] Updated weights for policy 0, policy_version 18316 (0.0012) -[2023-11-28 00:41:21,660][87426] Updated weights for policy 1, policy_version 18210 (0.0009) -[2023-11-28 00:41:21,863][87424] Updated weights for policy 0, policy_version 18326 (0.0010) -[2023-11-28 00:41:22,033][87426] Updated weights for policy 1, policy_version 18220 (0.0014) -[2023-11-28 00:41:22,247][87424] Updated weights for policy 0, policy_version 18336 (0.0011) -[2023-11-28 00:41:22,412][87426] Updated weights for policy 1, policy_version 18230 (0.0009) -[2023-11-28 00:41:22,793][87426] Updated weights for policy 1, policy_version 18240 (0.0007) -[2023-11-28 00:41:23,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9363456. Throughput: 0: 2685.5, 1: 2735.5. Samples: 9375388. Policy #0 lag: (min: 31.0, avg: 53.4, max: 95.0) -[2023-11-28 00:41:23,445][86177] Avg episode reward: [(0, '-580.070'), (1, '-577.010')] -[2023-11-28 00:41:24,661][87424] Updated weights for policy 0, policy_version 18346 (0.0008) -[2023-11-28 00:41:25,041][87424] Updated weights for policy 0, policy_version 18356 (0.0008) -[2023-11-28 00:41:25,130][87426] Updated weights for policy 1, policy_version 18250 (0.0007) -[2023-11-28 00:41:25,423][87424] Updated weights for policy 0, policy_version 18366 (0.0007) -[2023-11-28 00:41:25,502][87426] Updated weights for policy 1, policy_version 18260 (0.0009) -[2023-11-28 00:41:25,890][87426] Updated weights for policy 1, policy_version 18270 (0.0007) -[2023-11-28 00:41:27,272][87424] Updated weights for policy 0, policy_version 18376 (0.0007) -[2023-11-28 00:41:27,651][87424] Updated weights for policy 0, policy_version 18386 (0.0007) -[2023-11-28 00:41:28,038][87424] Updated weights for policy 0, policy_version 18396 (0.0007) -[2023-11-28 00:41:28,371][87426] Updated weights for policy 1, policy_version 18280 (0.0007) -[2023-11-28 00:41:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 9388032. Throughput: 0: 2695.9, 1: 2746.2. Samples: 9400216. Policy #0 lag: (min: 31.0, avg: 53.4, max: 95.0) -[2023-11-28 00:41:28,445][86177] Avg episode reward: [(0, '-599.500'), (1, '-566.670')] -[2023-11-28 00:41:28,744][87426] Updated weights for policy 1, policy_version 18290 (0.0007) -[2023-11-28 00:41:29,130][87426] Updated weights for policy 1, policy_version 18300 (0.0008) -[2023-11-28 00:41:30,403][87424] Updated weights for policy 0, policy_version 18406 (0.0009) -[2023-11-28 00:41:30,786][87424] Updated weights for policy 0, policy_version 18416 (0.0009) -[2023-11-28 00:41:31,174][87424] Updated weights for policy 0, policy_version 18426 (0.0008) -[2023-11-28 00:41:31,182][87426] Updated weights for policy 1, policy_version 18310 (0.0010) -[2023-11-28 00:41:31,558][87426] Updated weights for policy 1, policy_version 18320 (0.0009) -[2023-11-28 00:41:31,942][87426] Updated weights for policy 1, policy_version 18330 (0.0011) -[2023-11-28 00:41:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9412608. Throughput: 0: 2687.6, 1: 2757.9. Samples: 9424480. Policy #0 lag: (min: 31.0, avg: 53.4, max: 95.0) -[2023-11-28 00:41:33,445][86177] Avg episode reward: [(0, '-601.490'), (1, '-564.480')] -[2023-11-28 00:41:33,657][87424] Updated weights for policy 0, policy_version 18436 (0.0009) -[2023-11-28 00:41:34,043][87424] Updated weights for policy 0, policy_version 18446 (0.0007) -[2023-11-28 00:41:34,373][87426] Updated weights for policy 1, policy_version 18340 (0.0009) -[2023-11-28 00:41:34,428][87424] Updated weights for policy 0, policy_version 18456 (0.0007) -[2023-11-28 00:41:34,748][87426] Updated weights for policy 1, policy_version 18350 (0.0008) -[2023-11-28 00:41:35,127][87426] Updated weights for policy 1, policy_version 18360 (0.0011) -[2023-11-28 00:41:36,821][87424] Updated weights for policy 0, policy_version 18466 (0.0008) -[2023-11-28 00:41:37,202][87424] Updated weights for policy 0, policy_version 18476 (0.0007) -[2023-11-28 00:41:37,375][87426] Updated weights for policy 1, policy_version 18370 (0.0010) -[2023-11-28 00:41:37,592][87424] Updated weights for policy 0, policy_version 18486 (0.0008) -[2023-11-28 00:41:37,757][87426] Updated weights for policy 1, policy_version 18380 (0.0010) -[2023-11-28 00:41:37,972][87424] Updated weights for policy 0, policy_version 18496 (0.0008) -[2023-11-28 00:41:38,139][87426] Updated weights for policy 1, policy_version 18390 (0.0008) -[2023-11-28 00:41:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 9437184. Throughput: 0: 2703.5, 1: 2755.6. Samples: 9456332. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 00:41:38,445][86177] Avg episode reward: [(0, '-603.250'), (1, '-598.960')] -[2023-11-28 00:41:38,518][87426] Updated weights for policy 1, policy_version 18400 (0.0008) -[2023-11-28 00:41:39,902][87424] Updated weights for policy 0, policy_version 18506 (0.0011) -[2023-11-28 00:41:40,250][87426] Updated weights for policy 1, policy_version 18410 (0.0010) -[2023-11-28 00:41:40,284][87424] Updated weights for policy 0, policy_version 18516 (0.0011) -[2023-11-28 00:41:40,635][87426] Updated weights for policy 1, policy_version 18420 (0.0011) -[2023-11-28 00:41:40,650][87424] Updated weights for policy 0, policy_version 18526 (0.0008) -[2023-11-28 00:41:41,011][87426] Updated weights for policy 1, policy_version 18430 (0.0012) -[2023-11-28 00:41:42,969][87424] Updated weights for policy 0, policy_version 18536 (0.0010) -[2023-11-28 00:41:43,350][87424] Updated weights for policy 0, policy_version 18546 (0.0008) -[2023-11-28 00:41:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 9461760. Throughput: 0: 2715.0, 1: 2710.8. Samples: 9480308. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 00:41:43,445][86177] Avg episode reward: [(0, '-558.050'), (1, '-607.330')] -[2023-11-28 00:41:43,644][87426] Updated weights for policy 1, policy_version 18440 (0.0009) -[2023-11-28 00:41:43,730][87424] Updated weights for policy 0, policy_version 18556 (0.0008) -[2023-11-28 00:41:44,038][87426] Updated weights for policy 1, policy_version 18450 (0.0009) -[2023-11-28 00:41:44,411][87426] Updated weights for policy 1, policy_version 18460 (0.0007) -[2023-11-28 00:41:45,740][87424] Updated weights for policy 0, policy_version 18566 (0.0010) -[2023-11-28 00:41:46,126][87424] Updated weights for policy 0, policy_version 18576 (0.0009) -[2023-11-28 00:41:46,511][87424] Updated weights for policy 0, policy_version 18586 (0.0008) -[2023-11-28 00:41:46,969][87426] Updated weights for policy 1, policy_version 18470 (0.0007) -[2023-11-28 00:41:47,355][87426] Updated weights for policy 1, policy_version 18480 (0.0007) -[2023-11-28 00:41:47,731][87426] Updated weights for policy 1, policy_version 18490 (0.0007) -[2023-11-28 00:41:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9494528. Throughput: 0: 2715.6, 1: 2710.0. Samples: 9504548. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 00:41:48,445][86177] Avg episode reward: [(0, '-629.180'), (1, '-604.250')] -[2023-11-28 00:41:48,783][87424] Updated weights for policy 0, policy_version 18596 (0.0009) -[2023-11-28 00:41:49,182][87424] Updated weights for policy 0, policy_version 18606 (0.0010) -[2023-11-28 00:41:49,556][87424] Updated weights for policy 0, policy_version 18616 (0.0011) -[2023-11-28 00:41:49,855][87426] Updated weights for policy 1, policy_version 18500 (0.0009) -[2023-11-28 00:41:50,230][87426] Updated weights for policy 1, policy_version 18510 (0.0012) -[2023-11-28 00:41:50,609][87426] Updated weights for policy 1, policy_version 18520 (0.0011) -[2023-11-28 00:41:51,535][87424] Updated weights for policy 0, policy_version 18626 (0.0010) -[2023-11-28 00:41:51,907][87424] Updated weights for policy 0, policy_version 18636 (0.0012) -[2023-11-28 00:41:52,303][87424] Updated weights for policy 0, policy_version 18646 (0.0013) -[2023-11-28 00:41:52,683][87424] Updated weights for policy 0, policy_version 18656 (0.0012) -[2023-11-28 00:41:52,851][87426] Updated weights for policy 1, policy_version 18530 (0.0011) -[2023-11-28 00:41:53,238][87426] Updated weights for policy 1, policy_version 18540 (0.0009) -[2023-11-28 00:41:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 9519104. Throughput: 0: 2735.4, 1: 2704.4. Samples: 9537380. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 00:41:53,445][86177] Avg episode reward: [(0, '-635.020'), (1, '-624.360')] -[2023-11-28 00:41:53,629][87426] Updated weights for policy 1, policy_version 18550 (0.0011) -[2023-11-28 00:41:54,010][87426] Updated weights for policy 1, policy_version 18560 (0.0012) -[2023-11-28 00:41:55,116][87424] Updated weights for policy 0, policy_version 18666 (0.0008) -[2023-11-28 00:41:55,499][87424] Updated weights for policy 0, policy_version 18676 (0.0007) -[2023-11-28 00:41:55,886][87424] Updated weights for policy 0, policy_version 18686 (0.0008) -[2023-11-28 00:41:56,348][87426] Updated weights for policy 1, policy_version 18570 (0.0012) -[2023-11-28 00:41:56,725][87426] Updated weights for policy 1, policy_version 18580 (0.0012) -[2023-11-28 00:41:57,109][87426] Updated weights for policy 1, policy_version 18590 (0.0012) -[2023-11-28 00:41:58,131][87424] Updated weights for policy 0, policy_version 18696 (0.0011) -[2023-11-28 00:41:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 9543680. Throughput: 0: 2732.1, 1: 2689.9. Samples: 9561640. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 00:41:58,446][86177] Avg episode reward: [(0, '-637.180'), (1, '-590.430')] -[2023-11-28 00:41:58,509][87424] Updated weights for policy 0, policy_version 18706 (0.0012) -[2023-11-28 00:41:58,822][87426] Updated weights for policy 1, policy_version 18600 (0.0008) -[2023-11-28 00:41:58,893][87424] Updated weights for policy 0, policy_version 18716 (0.0012) -[2023-11-28 00:41:59,205][87426] Updated weights for policy 1, policy_version 18610 (0.0012) -[2023-11-28 00:41:59,592][87426] Updated weights for policy 1, policy_version 18620 (0.0012) -[2023-11-28 00:42:01,157][87424] Updated weights for policy 0, policy_version 18726 (0.0009) -[2023-11-28 00:42:01,553][87424] Updated weights for policy 0, policy_version 18736 (0.0008) -[2023-11-28 00:42:01,924][87424] Updated weights for policy 0, policy_version 18746 (0.0010) -[2023-11-28 00:42:01,974][87426] Updated weights for policy 1, policy_version 18630 (0.0009) -[2023-11-28 00:42:02,348][87426] Updated weights for policy 1, policy_version 18640 (0.0009) -[2023-11-28 00:42:02,742][87426] Updated weights for policy 1, policy_version 18650 (0.0008) -[2023-11-28 00:42:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9576448. Throughput: 0: 2719.9, 1: 2689.0. Samples: 9585940. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 00:42:03,445][86177] Avg episode reward: [(0, '-627.710'), (1, '-610.490')] -[2023-11-28 00:42:03,988][87424] Updated weights for policy 0, policy_version 18756 (0.0009) -[2023-11-28 00:42:04,375][87424] Updated weights for policy 0, policy_version 18766 (0.0007) -[2023-11-28 00:42:04,767][87424] Updated weights for policy 0, policy_version 18776 (0.0010) -[2023-11-28 00:42:05,005][87426] Updated weights for policy 1, policy_version 18660 (0.0009) -[2023-11-28 00:42:05,377][87426] Updated weights for policy 1, policy_version 18670 (0.0011) -[2023-11-28 00:42:05,771][87426] Updated weights for policy 1, policy_version 18680 (0.0012) -[2023-11-28 00:42:07,056][87424] Updated weights for policy 0, policy_version 18786 (0.0011) -[2023-11-28 00:42:07,394][87426] Updated weights for policy 1, policy_version 18690 (0.0011) -[2023-11-28 00:42:07,427][87424] Updated weights for policy 0, policy_version 18796 (0.0012) -[2023-11-28 00:42:07,774][87426] Updated weights for policy 1, policy_version 18700 (0.0011) -[2023-11-28 00:42:07,813][87424] Updated weights for policy 0, policy_version 18806 (0.0012) -[2023-11-28 00:42:08,151][87426] Updated weights for policy 1, policy_version 18710 (0.0010) -[2023-11-28 00:42:08,200][87424] Updated weights for policy 0, policy_version 18816 (0.0012) -[2023-11-28 00:42:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 9601024. Throughput: 0: 2695.8, 1: 2688.7. Samples: 9617692. Policy #0 lag: (min: 31.0, avg: 46.9, max: 66.0) -[2023-11-28 00:42:08,445][86177] Avg episode reward: [(0, '-621.480'), (1, '-589.400')] -[2023-11-28 00:42:08,536][87426] Updated weights for policy 1, policy_version 18720 (0.0011) -[2023-11-28 00:42:10,242][87424] Updated weights for policy 0, policy_version 18826 (0.0012) -[2023-11-28 00:42:10,432][87426] Updated weights for policy 1, policy_version 18730 (0.0008) -[2023-11-28 00:42:10,617][87424] Updated weights for policy 0, policy_version 18836 (0.0011) -[2023-11-28 00:42:10,813][87426] Updated weights for policy 1, policy_version 18740 (0.0011) -[2023-11-28 00:42:10,998][87424] Updated weights for policy 0, policy_version 18846 (0.0011) -[2023-11-28 00:42:11,190][87426] Updated weights for policy 1, policy_version 18750 (0.0011) -[2023-11-28 00:42:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 9625600. Throughput: 0: 2686.8, 1: 2711.4. Samples: 9643132. Policy #0 lag: (min: 31.0, avg: 46.9, max: 66.0) -[2023-11-28 00:42:13,445][86177] Avg episode reward: [(0, '-588.240'), (1, '-604.910')] -[2023-11-28 00:42:13,527][87424] Updated weights for policy 0, policy_version 18856 (0.0008) -[2023-11-28 00:42:13,537][87426] Updated weights for policy 1, policy_version 18760 (0.0010) -[2023-11-28 00:42:13,912][87424] Updated weights for policy 0, policy_version 18866 (0.0008) -[2023-11-28 00:42:13,914][87426] Updated weights for policy 1, policy_version 18770 (0.0009) -[2023-11-28 00:42:14,295][87424] Updated weights for policy 0, policy_version 18876 (0.0007) -[2023-11-28 00:42:14,301][87426] Updated weights for policy 1, policy_version 18780 (0.0007) -[2023-11-28 00:42:16,615][87424] Updated weights for policy 0, policy_version 18886 (0.0010) -[2023-11-28 00:42:16,750][87426] Updated weights for policy 1, policy_version 18790 (0.0010) -[2023-11-28 00:42:17,007][87424] Updated weights for policy 0, policy_version 18896 (0.0010) -[2023-11-28 00:42:17,129][87426] Updated weights for policy 1, policy_version 18800 (0.0009) -[2023-11-28 00:42:17,389][87424] Updated weights for policy 0, policy_version 18906 (0.0010) -[2023-11-28 00:42:17,501][87426] Updated weights for policy 1, policy_version 18810 (0.0009) -[2023-11-28 00:42:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9658368. Throughput: 0: 2691.3, 1: 2697.0. Samples: 9666952. Policy #0 lag: (min: 31.0, avg: 46.9, max: 66.0) -[2023-11-28 00:42:18,445][86177] Avg episode reward: [(0, '-646.500'), (1, '-607.050')] -[2023-11-28 00:42:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000018912_4841472.pth... -[2023-11-28 00:42:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000018816_4816896.pth... -[2023-11-28 00:42:18,489][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000016384_4194304.pth -[2023-11-28 00:42:18,505][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000016256_4161536.pth -[2023-11-28 00:42:19,227][87424] Updated weights for policy 0, policy_version 18916 (0.0009) -[2023-11-28 00:42:19,603][87424] Updated weights for policy 0, policy_version 18926 (0.0011) -[2023-11-28 00:42:19,990][87424] Updated weights for policy 0, policy_version 18936 (0.0008) -[2023-11-28 00:42:20,020][87426] Updated weights for policy 1, policy_version 18820 (0.0009) -[2023-11-28 00:42:20,404][87426] Updated weights for policy 1, policy_version 18830 (0.0011) -[2023-11-28 00:42:20,778][87426] Updated weights for policy 1, policy_version 18840 (0.0011) -[2023-11-28 00:42:22,528][87424] Updated weights for policy 0, policy_version 18946 (0.0010) -[2023-11-28 00:42:22,905][87424] Updated weights for policy 0, policy_version 18956 (0.0010) -[2023-11-28 00:42:23,183][87426] Updated weights for policy 1, policy_version 18850 (0.0011) -[2023-11-28 00:42:23,286][87424] Updated weights for policy 0, policy_version 18966 (0.0011) -[2023-11-28 00:42:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 9674752. Throughput: 0: 2683.6, 1: 2682.5. Samples: 9697804. Policy #0 lag: (min: 19.0, avg: 47.1, max: 51.0) -[2023-11-28 00:42:23,445][86177] Avg episode reward: [(0, '-659.110'), (1, '-610.590')] -[2023-11-28 00:42:23,575][87426] Updated weights for policy 1, policy_version 18860 (0.0008) -[2023-11-28 00:42:23,670][87424] Updated weights for policy 0, policy_version 18976 (0.0011) -[2023-11-28 00:42:23,953][87426] Updated weights for policy 1, policy_version 18870 (0.0007) -[2023-11-28 00:42:24,337][87426] Updated weights for policy 1, policy_version 18880 (0.0007) -[2023-11-28 00:42:25,919][87424] Updated weights for policy 0, policy_version 18986 (0.0011) -[2023-11-28 00:42:26,303][87424] Updated weights for policy 0, policy_version 18996 (0.0012) -[2023-11-28 00:42:26,562][87426] Updated weights for policy 1, policy_version 18890 (0.0010) -[2023-11-28 00:42:26,690][87424] Updated weights for policy 0, policy_version 19006 (0.0012) -[2023-11-28 00:42:26,942][87426] Updated weights for policy 1, policy_version 18900 (0.0009) -[2023-11-28 00:42:27,320][87426] Updated weights for policy 1, policy_version 18910 (0.0007) -[2023-11-28 00:42:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 9707520. Throughput: 0: 2698.6, 1: 2695.6. Samples: 9723048. Policy #0 lag: (min: 19.0, avg: 47.1, max: 51.0) -[2023-11-28 00:42:28,445][86177] Avg episode reward: [(0, '-592.620'), (1, '-600.470')] -[2023-11-28 00:42:28,879][87424] Updated weights for policy 0, policy_version 19016 (0.0012) -[2023-11-28 00:42:29,265][87424] Updated weights for policy 0, policy_version 19026 (0.0012) -[2023-11-28 00:42:29,579][87426] Updated weights for policy 1, policy_version 18920 (0.0009) -[2023-11-28 00:42:29,649][87424] Updated weights for policy 0, policy_version 19036 (0.0010) -[2023-11-28 00:42:29,965][87426] Updated weights for policy 1, policy_version 18930 (0.0008) -[2023-11-28 00:42:30,352][87426] Updated weights for policy 1, policy_version 18940 (0.0012) -[2023-11-28 00:42:31,896][87424] Updated weights for policy 0, policy_version 19046 (0.0009) -[2023-11-28 00:42:32,271][87424] Updated weights for policy 0, policy_version 19056 (0.0012) -[2023-11-28 00:42:32,363][87426] Updated weights for policy 1, policy_version 18950 (0.0009) -[2023-11-28 00:42:32,651][87424] Updated weights for policy 0, policy_version 19066 (0.0009) -[2023-11-28 00:42:32,741][87426] Updated weights for policy 1, policy_version 18960 (0.0010) -[2023-11-28 00:42:33,121][87426] Updated weights for policy 1, policy_version 18970 (0.0008) -[2023-11-28 00:42:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9740288. Throughput: 0: 2704.8, 1: 2689.6. Samples: 9747296. Policy #0 lag: (min: 19.0, avg: 47.1, max: 51.0) -[2023-11-28 00:42:33,445][86177] Avg episode reward: [(0, '-594.510'), (1, '-581.200')] -[2023-11-28 00:42:34,530][87424] Updated weights for policy 0, policy_version 19076 (0.0008) -[2023-11-28 00:42:34,914][87424] Updated weights for policy 0, policy_version 19086 (0.0008) -[2023-11-28 00:42:35,302][87424] Updated weights for policy 0, policy_version 19096 (0.0009) -[2023-11-28 00:42:35,529][87426] Updated weights for policy 1, policy_version 18980 (0.0009) -[2023-11-28 00:42:35,908][87426] Updated weights for policy 1, policy_version 18990 (0.0011) -[2023-11-28 00:42:36,286][87426] Updated weights for policy 1, policy_version 19000 (0.0011) -[2023-11-28 00:42:37,149][87424] Updated weights for policy 0, policy_version 19106 (0.0010) -[2023-11-28 00:42:37,531][87424] Updated weights for policy 0, policy_version 19116 (0.0009) -[2023-11-28 00:42:37,910][87424] Updated weights for policy 0, policy_version 19126 (0.0007) -[2023-11-28 00:42:38,291][87424] Updated weights for policy 0, policy_version 19136 (0.0007) -[2023-11-28 00:42:38,388][87426] Updated weights for policy 1, policy_version 19010 (0.0011) -[2023-11-28 00:42:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9764864. Throughput: 0: 2719.9, 1: 2686.0. Samples: 9780644. Policy #0 lag: (min: 36.0, avg: 57.2, max: 75.0) -[2023-11-28 00:42:38,445][86177] Avg episode reward: [(0, '-577.770'), (1, '-559.570')] -[2023-11-28 00:42:38,771][87426] Updated weights for policy 1, policy_version 19020 (0.0012) -[2023-11-28 00:42:39,150][87426] Updated weights for policy 1, policy_version 19030 (0.0011) -[2023-11-28 00:42:39,530][87426] Updated weights for policy 1, policy_version 19040 (0.0007) -[2023-11-28 00:42:40,536][87424] Updated weights for policy 0, policy_version 19146 (0.0012) -[2023-11-28 00:42:40,916][87424] Updated weights for policy 0, policy_version 19156 (0.0012) -[2023-11-28 00:42:41,294][87424] Updated weights for policy 0, policy_version 19166 (0.0011) -[2023-11-28 00:42:41,594][87426] Updated weights for policy 1, policy_version 19050 (0.0012) -[2023-11-28 00:42:41,967][87426] Updated weights for policy 1, policy_version 19060 (0.0008) -[2023-11-28 00:42:42,344][87426] Updated weights for policy 1, policy_version 19070 (0.0010) -[2023-11-28 00:42:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 9789440. Throughput: 0: 2712.3, 1: 2692.2. Samples: 9804840. Policy #0 lag: (min: 36.0, avg: 57.2, max: 75.0) -[2023-11-28 00:42:43,445][86177] Avg episode reward: [(0, '-534.330'), (1, '-550.330')] -[2023-11-28 00:42:43,654][87424] Updated weights for policy 0, policy_version 19176 (0.0011) -[2023-11-28 00:42:44,048][87424] Updated weights for policy 0, policy_version 19186 (0.0012) -[2023-11-28 00:42:44,445][87424] Updated weights for policy 0, policy_version 19196 (0.0012) -[2023-11-28 00:42:44,487][87426] Updated weights for policy 1, policy_version 19080 (0.0010) -[2023-11-28 00:42:44,871][87426] Updated weights for policy 1, policy_version 19090 (0.0012) -[2023-11-28 00:42:45,246][87426] Updated weights for policy 1, policy_version 19100 (0.0009) -[2023-11-28 00:42:46,312][87424] Updated weights for policy 0, policy_version 19206 (0.0012) -[2023-11-28 00:42:46,696][87424] Updated weights for policy 0, policy_version 19216 (0.0012) -[2023-11-28 00:42:47,087][87424] Updated weights for policy 0, policy_version 19226 (0.0012) -[2023-11-28 00:42:47,219][87426] Updated weights for policy 1, policy_version 19110 (0.0011) -[2023-11-28 00:42:47,602][87426] Updated weights for policy 1, policy_version 19120 (0.0009) -[2023-11-28 00:42:47,982][87426] Updated weights for policy 1, policy_version 19130 (0.0012) -[2023-11-28 00:42:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9822208. Throughput: 0: 2730.9, 1: 2690.8. Samples: 9829916. Policy #0 lag: (min: 36.0, avg: 57.2, max: 75.0) -[2023-11-28 00:42:48,445][86177] Avg episode reward: [(0, '-579.050'), (1, '-589.250')] -[2023-11-28 00:42:49,453][87424] Updated weights for policy 0, policy_version 19236 (0.0012) -[2023-11-28 00:42:49,836][87424] Updated weights for policy 0, policy_version 19246 (0.0012) -[2023-11-28 00:42:50,217][87424] Updated weights for policy 0, policy_version 19256 (0.0012) -[2023-11-28 00:42:50,442][87426] Updated weights for policy 1, policy_version 19140 (0.0011) -[2023-11-28 00:42:50,822][87426] Updated weights for policy 1, policy_version 19150 (0.0008) -[2023-11-28 00:42:51,202][87426] Updated weights for policy 1, policy_version 19160 (0.0009) -[2023-11-28 00:42:52,751][87424] Updated weights for policy 0, policy_version 19266 (0.0011) -[2023-11-28 00:42:53,093][87426] Updated weights for policy 1, policy_version 19170 (0.0011) -[2023-11-28 00:42:53,141][87424] Updated weights for policy 0, policy_version 19276 (0.0011) -[2023-11-28 00:42:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 9838592. Throughput: 0: 2733.3, 1: 2697.0. Samples: 9862056. Policy #0 lag: (min: 31.0, avg: 33.5, max: 51.0) -[2023-11-28 00:42:53,445][86177] Avg episode reward: [(0, '-575.200'), (1, '-586.360')] -[2023-11-28 00:42:53,467][87426] Updated weights for policy 1, policy_version 19180 (0.0011) -[2023-11-28 00:42:53,516][87424] Updated weights for policy 0, policy_version 19286 (0.0011) -[2023-11-28 00:42:53,843][87426] Updated weights for policy 1, policy_version 19190 (0.0010) -[2023-11-28 00:42:53,896][87424] Updated weights for policy 0, policy_version 19296 (0.0010) -[2023-11-28 00:42:54,225][87426] Updated weights for policy 1, policy_version 19200 (0.0007) -[2023-11-28 00:42:56,056][87424] Updated weights for policy 0, policy_version 19306 (0.0007) -[2023-11-28 00:42:56,439][87424] Updated weights for policy 0, policy_version 19316 (0.0007) -[2023-11-28 00:42:56,761][87426] Updated weights for policy 1, policy_version 19210 (0.0010) -[2023-11-28 00:42:56,829][87424] Updated weights for policy 0, policy_version 19326 (0.0010) -[2023-11-28 00:42:57,145][87426] Updated weights for policy 1, policy_version 19220 (0.0008) -[2023-11-28 00:42:57,534][87426] Updated weights for policy 1, policy_version 19230 (0.0007) -[2023-11-28 00:42:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 9871360. Throughput: 0: 2712.1, 1: 2688.7. Samples: 9886168. Policy #0 lag: (min: 31.0, avg: 33.5, max: 51.0) -[2023-11-28 00:42:58,445][86177] Avg episode reward: [(0, '-576.250'), (1, '-574.160')] -[2023-11-28 00:42:59,331][87424] Updated weights for policy 0, policy_version 19336 (0.0011) -[2023-11-28 00:42:59,542][87426] Updated weights for policy 1, policy_version 19240 (0.0011) -[2023-11-28 00:42:59,712][87424] Updated weights for policy 0, policy_version 19346 (0.0011) -[2023-11-28 00:42:59,911][87426] Updated weights for policy 1, policy_version 19250 (0.0012) -[2023-11-28 00:43:00,099][87424] Updated weights for policy 0, policy_version 19356 (0.0011) -[2023-11-28 00:43:00,290][87426] Updated weights for policy 1, policy_version 19260 (0.0012) -[2023-11-28 00:43:01,912][87424] Updated weights for policy 0, policy_version 19366 (0.0010) -[2023-11-28 00:43:02,289][87424] Updated weights for policy 0, policy_version 19376 (0.0012) -[2023-11-28 00:43:02,468][87426] Updated weights for policy 1, policy_version 19270 (0.0010) -[2023-11-28 00:43:02,669][87424] Updated weights for policy 0, policy_version 19386 (0.0011) -[2023-11-28 00:43:02,843][87426] Updated weights for policy 1, policy_version 19280 (0.0010) -[2023-11-28 00:43:03,231][87426] Updated weights for policy 1, policy_version 19290 (0.0008) -[2023-11-28 00:43:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 9895936. Throughput: 0: 2728.9, 1: 2710.1. Samples: 9911704. Policy #0 lag: (min: 31.0, avg: 33.5, max: 51.0) -[2023-11-28 00:43:03,445][86177] Avg episode reward: [(0, '-582.890'), (1, '-564.100')] -[2023-11-28 00:43:04,483][87424] Updated weights for policy 0, policy_version 19396 (0.0011) -[2023-11-28 00:43:04,865][87424] Updated weights for policy 0, policy_version 19406 (0.0012) -[2023-11-28 00:43:05,252][87424] Updated weights for policy 0, policy_version 19416 (0.0011) -[2023-11-28 00:43:05,299][87426] Updated weights for policy 1, policy_version 19300 (0.0010) -[2023-11-28 00:43:05,673][87426] Updated weights for policy 1, policy_version 19310 (0.0010) -[2023-11-28 00:43:06,052][87426] Updated weights for policy 1, policy_version 19320 (0.0009) -[2023-11-28 00:43:07,730][87424] Updated weights for policy 0, policy_version 19426 (0.0010) -[2023-11-28 00:43:07,863][87426] Updated weights for policy 1, policy_version 19330 (0.0011) -[2023-11-28 00:43:08,114][87424] Updated weights for policy 0, policy_version 19436 (0.0008) -[2023-11-28 00:43:08,241][87426] Updated weights for policy 1, policy_version 19340 (0.0007) -[2023-11-28 00:43:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 9920512. Throughput: 0: 2739.0, 1: 2755.6. Samples: 9945060. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 00:43:08,445][86177] Avg episode reward: [(0, '-535.030'), (1, '-530.250')] -[2023-11-28 00:43:08,498][87424] Updated weights for policy 0, policy_version 19446 (0.0008) -[2023-11-28 00:43:08,622][87426] Updated weights for policy 1, policy_version 19350 (0.0010) -[2023-11-28 00:43:08,885][87424] Updated weights for policy 0, policy_version 19456 (0.0008) -[2023-11-28 00:43:09,002][87426] Updated weights for policy 1, policy_version 19360 (0.0008) -[2023-11-28 00:43:10,662][87424] Updated weights for policy 0, policy_version 19466 (0.0011) -[2023-11-28 00:43:10,943][87426] Updated weights for policy 1, policy_version 19370 (0.0008) -[2023-11-28 00:43:11,043][87424] Updated weights for policy 0, policy_version 19476 (0.0012) -[2023-11-28 00:43:11,320][87426] Updated weights for policy 1, policy_version 19380 (0.0009) -[2023-11-28 00:43:11,423][87424] Updated weights for policy 0, policy_version 19486 (0.0011) -[2023-11-28 00:43:11,698][87426] Updated weights for policy 1, policy_version 19390 (0.0009) -[2023-11-28 00:43:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9953280. Throughput: 0: 2721.7, 1: 2768.4. Samples: 9970100. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 00:43:13,445][86177] Avg episode reward: [(0, '-578.500'), (1, '-514.520')] -[2023-11-28 00:43:13,653][87424] Updated weights for policy 0, policy_version 19496 (0.0009) -[2023-11-28 00:43:13,817][87426] Updated weights for policy 1, policy_version 19400 (0.0012) -[2023-11-28 00:43:14,040][87424] Updated weights for policy 0, policy_version 19506 (0.0011) -[2023-11-28 00:43:14,197][87426] Updated weights for policy 1, policy_version 19410 (0.0012) -[2023-11-28 00:43:14,430][87424] Updated weights for policy 0, policy_version 19516 (0.0009) -[2023-11-28 00:43:14,576][87426] Updated weights for policy 1, policy_version 19420 (0.0012) -[2023-11-28 00:43:16,564][87424] Updated weights for policy 0, policy_version 19526 (0.0009) -[2023-11-28 00:43:16,864][87426] Updated weights for policy 1, policy_version 19430 (0.0010) -[2023-11-28 00:43:16,938][87424] Updated weights for policy 0, policy_version 19536 (0.0007) -[2023-11-28 00:43:17,245][87426] Updated weights for policy 1, policy_version 19440 (0.0007) -[2023-11-28 00:43:17,318][87424] Updated weights for policy 0, policy_version 19546 (0.0011) -[2023-11-28 00:43:17,625][87426] Updated weights for policy 1, policy_version 19450 (0.0011) -[2023-11-28 00:43:18,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 9986048. Throughput: 0: 2727.5, 1: 2777.3. Samples: 9995012. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 00:43:18,445][86177] Avg episode reward: [(0, '-565.980'), (1, '-517.280')] -[2023-11-28 00:43:19,233][87424] Updated weights for policy 0, policy_version 19556 (0.0011) -[2023-11-28 00:43:19,616][87424] Updated weights for policy 0, policy_version 19566 (0.0009) -[2023-11-28 00:43:19,848][87426] Updated weights for policy 1, policy_version 19460 (0.0011) -[2023-11-28 00:43:20,001][87424] Updated weights for policy 0, policy_version 19576 (0.0009) -[2023-11-28 00:43:20,235][87426] Updated weights for policy 1, policy_version 19470 (0.0009) -[2023-11-28 00:43:20,608][87426] Updated weights for policy 1, policy_version 19480 (0.0008) -[2023-11-28 00:43:22,483][87424] Updated weights for policy 0, policy_version 19586 (0.0010) -[2023-11-28 00:43:22,769][87426] Updated weights for policy 1, policy_version 19490 (0.0008) -[2023-11-28 00:43:22,866][87424] Updated weights for policy 0, policy_version 19596 (0.0010) -[2023-11-28 00:43:23,150][87426] Updated weights for policy 1, policy_version 19500 (0.0011) -[2023-11-28 00:43:23,249][87424] Updated weights for policy 0, policy_version 19606 (0.0013) -[2023-11-28 00:43:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 10002432. Throughput: 0: 2700.2, 1: 2775.8. Samples: 10027064. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 00:43:23,445][86177] Avg episode reward: [(0, '-569.270'), (1, '-516.000')] -[2023-11-28 00:43:23,543][87426] Updated weights for policy 1, policy_version 19510 (0.0009) -[2023-11-28 00:43:23,633][87424] Updated weights for policy 0, policy_version 19616 (0.0012) -[2023-11-28 00:43:23,915][87426] Updated weights for policy 1, policy_version 19520 (0.0011) -[2023-11-28 00:43:25,951][87424] Updated weights for policy 0, policy_version 19626 (0.0009) -[2023-11-28 00:43:26,123][87426] Updated weights for policy 1, policy_version 19530 (0.0011) -[2023-11-28 00:43:26,337][87424] Updated weights for policy 0, policy_version 19636 (0.0008) -[2023-11-28 00:43:26,504][87426] Updated weights for policy 1, policy_version 19540 (0.0012) -[2023-11-28 00:43:26,720][87424] Updated weights for policy 0, policy_version 19646 (0.0007) -[2023-11-28 00:43:26,887][87426] Updated weights for policy 1, policy_version 19550 (0.0012) -[2023-11-28 00:43:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 10035200. Throughput: 0: 2712.3, 1: 2770.2. Samples: 10051552. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 00:43:28,445][86177] Avg episode reward: [(0, '-583.410'), (1, '-514.180')] -[2023-11-28 00:43:28,560][87424] Updated weights for policy 0, policy_version 19656 (0.0011) -[2023-11-28 00:43:28,934][87424] Updated weights for policy 0, policy_version 19666 (0.0012) -[2023-11-28 00:43:29,264][87426] Updated weights for policy 1, policy_version 19560 (0.0011) -[2023-11-28 00:43:29,317][87424] Updated weights for policy 0, policy_version 19676 (0.0011) -[2023-11-28 00:43:29,645][87426] Updated weights for policy 1, policy_version 19570 (0.0011) -[2023-11-28 00:43:30,028][87426] Updated weights for policy 1, policy_version 19580 (0.0009) -[2023-11-28 00:43:31,428][87424] Updated weights for policy 0, policy_version 19686 (0.0007) -[2023-11-28 00:43:31,834][87424] Updated weights for policy 0, policy_version 19696 (0.0009) -[2023-11-28 00:43:32,210][87424] Updated weights for policy 0, policy_version 19706 (0.0010) -[2023-11-28 00:43:32,442][87426] Updated weights for policy 1, policy_version 19590 (0.0009) -[2023-11-28 00:43:32,821][87426] Updated weights for policy 1, policy_version 19600 (0.0011) -[2023-11-28 00:43:33,203][87426] Updated weights for policy 1, policy_version 19610 (0.0009) -[2023-11-28 00:43:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 10067968. Throughput: 0: 2724.2, 1: 2757.9. Samples: 10076612. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 00:43:33,445][86177] Avg episode reward: [(0, '-544.590'), (1, '-524.110')] -[2023-11-28 00:43:34,403][87424] Updated weights for policy 0, policy_version 19716 (0.0010) -[2023-11-28 00:43:34,788][87424] Updated weights for policy 0, policy_version 19726 (0.0008) -[2023-11-28 00:43:34,864][87426] Updated weights for policy 1, policy_version 19620 (0.0008) -[2023-11-28 00:43:35,167][87424] Updated weights for policy 0, policy_version 19736 (0.0010) -[2023-11-28 00:43:35,236][87426] Updated weights for policy 1, policy_version 19630 (0.0009) -[2023-11-28 00:43:35,614][87426] Updated weights for policy 1, policy_version 19640 (0.0011) -[2023-11-28 00:43:36,829][87424] Updated weights for policy 0, policy_version 19746 (0.0011) -[2023-11-28 00:43:37,214][87424] Updated weights for policy 0, policy_version 19756 (0.0012) -[2023-11-28 00:43:37,590][87424] Updated weights for policy 0, policy_version 19766 (0.0011) -[2023-11-28 00:43:37,867][87426] Updated weights for policy 1, policy_version 19650 (0.0011) -[2023-11-28 00:43:37,964][87424] Updated weights for policy 0, policy_version 19776 (0.0010) -[2023-11-28 00:43:38,244][87426] Updated weights for policy 1, policy_version 19660 (0.0011) -[2023-11-28 00:43:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 10092544. Throughput: 0: 2757.6, 1: 2763.6. Samples: 10110512. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 00:43:38,445][86177] Avg episode reward: [(0, '-567.780'), (1, '-526.910')] -[2023-11-28 00:43:38,625][87426] Updated weights for policy 1, policy_version 19670 (0.0010) -[2023-11-28 00:43:39,006][87426] Updated weights for policy 1, policy_version 19680 (0.0008) -[2023-11-28 00:43:39,725][87424] Updated weights for policy 0, policy_version 19786 (0.0007) -[2023-11-28 00:43:40,111][87424] Updated weights for policy 0, policy_version 19796 (0.0011) -[2023-11-28 00:43:40,492][87424] Updated weights for policy 0, policy_version 19806 (0.0010) -[2023-11-28 00:43:41,528][87426] Updated weights for policy 1, policy_version 19690 (0.0010) -[2023-11-28 00:43:41,903][87426] Updated weights for policy 1, policy_version 19700 (0.0011) -[2023-11-28 00:43:42,287][87426] Updated weights for policy 1, policy_version 19710 (0.0011) -[2023-11-28 00:43:42,982][87424] Updated weights for policy 0, policy_version 19816 (0.0011) -[2023-11-28 00:43:43,366][87424] Updated weights for policy 0, policy_version 19826 (0.0011) -[2023-11-28 00:43:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 10117120. Throughput: 0: 2763.5, 1: 2734.8. Samples: 10133592. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 00:43:43,445][86177] Avg episode reward: [(0, '-576.230'), (1, '-535.010')] -[2023-11-28 00:43:43,750][87424] Updated weights for policy 0, policy_version 19836 (0.0010) -[2023-11-28 00:43:44,206][87426] Updated weights for policy 1, policy_version 19720 (0.0011) -[2023-11-28 00:43:44,587][87426] Updated weights for policy 1, policy_version 19730 (0.0011) -[2023-11-28 00:43:44,967][87426] Updated weights for policy 1, policy_version 19740 (0.0012) -[2023-11-28 00:43:46,353][87424] Updated weights for policy 0, policy_version 19846 (0.0010) -[2023-11-28 00:43:46,737][87424] Updated weights for policy 0, policy_version 19856 (0.0012) -[2023-11-28 00:43:47,059][87426] Updated weights for policy 1, policy_version 19750 (0.0009) -[2023-11-28 00:43:47,110][87424] Updated weights for policy 0, policy_version 19866 (0.0010) -[2023-11-28 00:43:47,434][87426] Updated weights for policy 1, policy_version 19760 (0.0008) -[2023-11-28 00:43:47,814][87426] Updated weights for policy 1, policy_version 19770 (0.0008) -[2023-11-28 00:43:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 10149888. Throughput: 0: 2751.0, 1: 2720.5. Samples: 10157924. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 00:43:48,445][86177] Avg episode reward: [(0, '-580.020'), (1, '-534.520')] -[2023-11-28 00:43:49,638][87424] Updated weights for policy 0, policy_version 19876 (0.0007) -[2023-11-28 00:43:50,020][87424] Updated weights for policy 0, policy_version 19886 (0.0010) -[2023-11-28 00:43:50,135][87426] Updated weights for policy 1, policy_version 19780 (0.0010) -[2023-11-28 00:43:50,404][87424] Updated weights for policy 0, policy_version 19896 (0.0012) -[2023-11-28 00:43:50,503][87426] Updated weights for policy 1, policy_version 19790 (0.0010) -[2023-11-28 00:43:50,884][87426] Updated weights for policy 1, policy_version 19800 (0.0012) -[2023-11-28 00:43:52,728][87424] Updated weights for policy 0, policy_version 19906 (0.0009) -[2023-11-28 00:43:52,926][87426] Updated weights for policy 1, policy_version 19810 (0.0011) -[2023-11-28 00:43:53,108][87424] Updated weights for policy 0, policy_version 19916 (0.0011) -[2023-11-28 00:43:53,313][87426] Updated weights for policy 1, policy_version 19820 (0.0012) -[2023-11-28 00:43:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 10166272. Throughput: 0: 2733.5, 1: 2693.2. Samples: 10189260. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 00:43:53,445][86177] Avg episode reward: [(0, '-566.090'), (1, '-523.860')] -[2023-11-28 00:43:53,499][87424] Updated weights for policy 0, policy_version 19926 (0.0011) -[2023-11-28 00:43:53,693][87426] Updated weights for policy 1, policy_version 19830 (0.0012) -[2023-11-28 00:43:53,883][87424] Updated weights for policy 0, policy_version 19936 (0.0012) -[2023-11-28 00:43:54,068][87426] Updated weights for policy 1, policy_version 19840 (0.0012) -[2023-11-28 00:43:56,014][87424] Updated weights for policy 0, policy_version 19946 (0.0011) -[2023-11-28 00:43:56,394][87424] Updated weights for policy 0, policy_version 19956 (0.0010) -[2023-11-28 00:43:56,568][87426] Updated weights for policy 1, policy_version 19850 (0.0012) -[2023-11-28 00:43:56,777][87424] Updated weights for policy 0, policy_version 19966 (0.0007) -[2023-11-28 00:43:56,955][87426] Updated weights for policy 1, policy_version 19860 (0.0011) -[2023-11-28 00:43:57,332][87426] Updated weights for policy 1, policy_version 19870 (0.0007) -[2023-11-28 00:43:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 10199040. Throughput: 0: 2742.8, 1: 2683.2. Samples: 10214268. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 00:43:58,445][86177] Avg episode reward: [(0, '-557.920'), (1, '-527.950')] -[2023-11-28 00:43:58,958][87424] Updated weights for policy 0, policy_version 19976 (0.0009) -[2023-11-28 00:43:59,347][87424] Updated weights for policy 0, policy_version 19986 (0.0010) -[2023-11-28 00:43:59,696][87426] Updated weights for policy 1, policy_version 19880 (0.0008) -[2023-11-28 00:43:59,725][87424] Updated weights for policy 0, policy_version 19996 (0.0008) -[2023-11-28 00:44:00,072][87426] Updated weights for policy 1, policy_version 19890 (0.0011) -[2023-11-28 00:44:00,464][87426] Updated weights for policy 1, policy_version 19900 (0.0012) -[2023-11-28 00:44:01,690][87424] Updated weights for policy 0, policy_version 20006 (0.0009) -[2023-11-28 00:44:02,064][87424] Updated weights for policy 0, policy_version 20016 (0.0009) -[2023-11-28 00:44:02,447][87424] Updated weights for policy 0, policy_version 20026 (0.0009) -[2023-11-28 00:44:02,548][87426] Updated weights for policy 1, policy_version 19910 (0.0012) -[2023-11-28 00:44:02,922][87426] Updated weights for policy 1, policy_version 19920 (0.0012) -[2023-11-28 00:44:03,299][87426] Updated weights for policy 1, policy_version 19930 (0.0012) -[2023-11-28 00:44:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 10223616. Throughput: 0: 2746.3, 1: 2676.8. Samples: 10239052. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 00:44:03,445][86177] Avg episode reward: [(0, '-545.480'), (1, '-536.340')] -[2023-11-28 00:44:04,219][87424] Updated weights for policy 0, policy_version 20036 (0.0008) -[2023-11-28 00:44:04,603][87424] Updated weights for policy 0, policy_version 20046 (0.0011) -[2023-11-28 00:44:04,983][87424] Updated weights for policy 0, policy_version 20056 (0.0012) -[2023-11-28 00:44:05,148][87426] Updated weights for policy 1, policy_version 19940 (0.0010) -[2023-11-28 00:44:05,523][87426] Updated weights for policy 1, policy_version 19950 (0.0011) -[2023-11-28 00:44:05,894][87426] Updated weights for policy 1, policy_version 19960 (0.0012) -[2023-11-28 00:44:07,063][87424] Updated weights for policy 0, policy_version 20066 (0.0010) -[2023-11-28 00:44:07,442][87424] Updated weights for policy 0, policy_version 20076 (0.0012) -[2023-11-28 00:44:07,820][87424] Updated weights for policy 0, policy_version 20086 (0.0012) -[2023-11-28 00:44:08,216][87424] Updated weights for policy 0, policy_version 20096 (0.0012) -[2023-11-28 00:44:08,365][87426] Updated weights for policy 1, policy_version 19970 (0.0012) -[2023-11-28 00:44:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 10256384. Throughput: 0: 2765.9, 1: 2676.9. Samples: 10271992. Policy #0 lag: (min: 31.0, avg: 52.9, max: 77.0) -[2023-11-28 00:44:08,445][86177] Avg episode reward: [(0, '-543.840'), (1, '-532.140')] -[2023-11-28 00:44:08,745][87426] Updated weights for policy 1, policy_version 19980 (0.0011) -[2023-11-28 00:44:09,123][87426] Updated weights for policy 1, policy_version 19990 (0.0008) -[2023-11-28 00:44:09,506][87426] Updated weights for policy 1, policy_version 20000 (0.0007) -[2023-11-28 00:44:10,808][87424] Updated weights for policy 0, policy_version 20106 (0.0012) -[2023-11-28 00:44:11,197][87424] Updated weights for policy 0, policy_version 20116 (0.0012) -[2023-11-28 00:44:11,578][87424] Updated weights for policy 0, policy_version 20126 (0.0011) -[2023-11-28 00:44:11,618][87426] Updated weights for policy 1, policy_version 20010 (0.0012) -[2023-11-28 00:44:11,995][87426] Updated weights for policy 1, policy_version 20020 (0.0011) -[2023-11-28 00:44:12,372][87426] Updated weights for policy 1, policy_version 20030 (0.0009) -[2023-11-28 00:44:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 10280960. Throughput: 0: 2749.4, 1: 2676.4. Samples: 10295716. Policy #0 lag: (min: 31.0, avg: 52.9, max: 77.0) -[2023-11-28 00:44:13,445][86177] Avg episode reward: [(0, '-548.160'), (1, '-530.450')] -[2023-11-28 00:44:13,513][87424] Updated weights for policy 0, policy_version 20136 (0.0012) -[2023-11-28 00:44:13,894][87424] Updated weights for policy 0, policy_version 20146 (0.0012) -[2023-11-28 00:44:14,271][87424] Updated weights for policy 0, policy_version 20156 (0.0009) -[2023-11-28 00:44:14,571][87426] Updated weights for policy 1, policy_version 20040 (0.0008) -[2023-11-28 00:44:14,956][87426] Updated weights for policy 1, policy_version 20050 (0.0008) -[2023-11-28 00:44:15,327][87426] Updated weights for policy 1, policy_version 20060 (0.0010) -[2023-11-28 00:44:16,766][87424] Updated weights for policy 0, policy_version 20166 (0.0009) -[2023-11-28 00:44:17,146][87424] Updated weights for policy 0, policy_version 20176 (0.0007) -[2023-11-28 00:44:17,527][87424] Updated weights for policy 0, policy_version 20186 (0.0007) -[2023-11-28 00:44:17,864][87426] Updated weights for policy 1, policy_version 20070 (0.0010) -[2023-11-28 00:44:18,231][87426] Updated weights for policy 1, policy_version 20080 (0.0012) -[2023-11-28 00:44:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 10305536. Throughput: 0: 2713.5, 1: 2679.3. Samples: 10319288. Policy #0 lag: (min: 31.0, avg: 52.9, max: 77.0) -[2023-11-28 00:44:18,445][86177] Avg episode reward: [(0, '-534.550'), (1, '-519.340')] -[2023-11-28 00:44:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000020192_5169152.pth... -[2023-11-28 00:44:18,487][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000017664_4521984.pth -[2023-11-28 00:44:18,609][87426] Updated weights for policy 1, policy_version 20090 (0.0011) -[2023-11-28 00:44:18,836][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000020096_5144576.pth... -[2023-11-28 00:44:18,880][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000017536_4489216.pth -[2023-11-28 00:44:20,041][87424] Updated weights for policy 0, policy_version 20196 (0.0011) -[2023-11-28 00:44:20,421][87424] Updated weights for policy 0, policy_version 20206 (0.0010) -[2023-11-28 00:44:20,776][87426] Updated weights for policy 1, policy_version 20100 (0.0011) -[2023-11-28 00:44:20,810][87424] Updated weights for policy 0, policy_version 20216 (0.0011) -[2023-11-28 00:44:21,154][87426] Updated weights for policy 1, policy_version 20110 (0.0010) -[2023-11-28 00:44:21,533][87426] Updated weights for policy 1, policy_version 20120 (0.0010) -[2023-11-28 00:44:22,816][87424] Updated weights for policy 0, policy_version 20226 (0.0011) -[2023-11-28 00:44:23,206][87424] Updated weights for policy 0, policy_version 20236 (0.0008) -[2023-11-28 00:44:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 10330112. Throughput: 0: 2658.8, 1: 2664.7. Samples: 10350072. Policy #0 lag: (min: 31.0, avg: 52.9, max: 77.0) -[2023-11-28 00:44:23,445][86177] Avg episode reward: [(0, '-549.160'), (1, '-504.510')] -[2023-11-28 00:44:23,591][87424] Updated weights for policy 0, policy_version 20246 (0.0010) -[2023-11-28 00:44:23,930][87426] Updated weights for policy 1, policy_version 20130 (0.0009) -[2023-11-28 00:44:23,976][87424] Updated weights for policy 0, policy_version 20256 (0.0008) -[2023-11-28 00:44:24,323][87426] Updated weights for policy 1, policy_version 20140 (0.0007) -[2023-11-28 00:44:24,708][87426] Updated weights for policy 1, policy_version 20150 (0.0010) -[2023-11-28 00:44:25,090][87426] Updated weights for policy 1, policy_version 20160 (0.0009) -[2023-11-28 00:44:26,233][87424] Updated weights for policy 0, policy_version 20266 (0.0008) -[2023-11-28 00:44:26,623][87424] Updated weights for policy 0, policy_version 20276 (0.0007) -[2023-11-28 00:44:27,016][87424] Updated weights for policy 0, policy_version 20286 (0.0008) -[2023-11-28 00:44:27,570][87426] Updated weights for policy 1, policy_version 20170 (0.0008) -[2023-11-28 00:44:27,951][87426] Updated weights for policy 1, policy_version 20180 (0.0007) -[2023-11-28 00:44:28,319][87426] Updated weights for policy 1, policy_version 20190 (0.0007) -[2023-11-28 00:44:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 10362880. Throughput: 0: 2677.7, 1: 2660.1. Samples: 10373792. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-11-28 00:44:28,445][86177] Avg episode reward: [(0, '-564.100'), (1, '-506.360')] -[2023-11-28 00:44:29,326][87424] Updated weights for policy 0, policy_version 20296 (0.0008) -[2023-11-28 00:44:29,715][87424] Updated weights for policy 0, policy_version 20306 (0.0008) -[2023-11-28 00:44:30,089][87424] Updated weights for policy 0, policy_version 20316 (0.0009) -[2023-11-28 00:44:30,489][87426] Updated weights for policy 1, policy_version 20200 (0.0010) -[2023-11-28 00:44:30,864][87426] Updated weights for policy 1, policy_version 20210 (0.0012) -[2023-11-28 00:44:31,238][87426] Updated weights for policy 1, policy_version 20220 (0.0011) -[2023-11-28 00:44:32,410][87424] Updated weights for policy 0, policy_version 20326 (0.0008) -[2023-11-28 00:44:32,799][87424] Updated weights for policy 0, policy_version 20336 (0.0008) -[2023-11-28 00:44:33,178][87424] Updated weights for policy 0, policy_version 20346 (0.0009) -[2023-11-28 00:44:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 10387456. Throughput: 0: 2673.9, 1: 2659.4. Samples: 10397920. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-11-28 00:44:33,445][86177] Avg episode reward: [(0, '-584.140'), (1, '-508.350')] -[2023-11-28 00:44:33,601][87426] Updated weights for policy 1, policy_version 20230 (0.0011) -[2023-11-28 00:44:33,981][87426] Updated weights for policy 1, policy_version 20240 (0.0011) -[2023-11-28 00:44:34,372][87426] Updated weights for policy 1, policy_version 20250 (0.0011) -[2023-11-28 00:44:35,072][87424] Updated weights for policy 0, policy_version 20356 (0.0010) -[2023-11-28 00:44:35,457][87424] Updated weights for policy 0, policy_version 20366 (0.0007) -[2023-11-28 00:44:35,843][87424] Updated weights for policy 0, policy_version 20376 (0.0007) -[2023-11-28 00:44:36,833][87426] Updated weights for policy 1, policy_version 20260 (0.0012) -[2023-11-28 00:44:37,214][87426] Updated weights for policy 1, policy_version 20270 (0.0012) -[2023-11-28 00:44:37,586][87426] Updated weights for policy 1, policy_version 20280 (0.0012) -[2023-11-28 00:44:38,204][87424] Updated weights for policy 0, policy_version 20386 (0.0008) -[2023-11-28 00:44:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 10412032. Throughput: 0: 2708.6, 1: 2661.4. Samples: 10430912. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-11-28 00:44:38,445][86177] Avg episode reward: [(0, '-591.160'), (1, '-511.400')] -[2023-11-28 00:44:38,580][87424] Updated weights for policy 0, policy_version 20396 (0.0008) -[2023-11-28 00:44:38,964][87424] Updated weights for policy 0, policy_version 20406 (0.0008) -[2023-11-28 00:44:39,349][87424] Updated weights for policy 0, policy_version 20416 (0.0009) -[2023-11-28 00:44:39,553][87426] Updated weights for policy 1, policy_version 20290 (0.0012) -[2023-11-28 00:44:39,929][87426] Updated weights for policy 1, policy_version 20300 (0.0011) -[2023-11-28 00:44:40,311][87426] Updated weights for policy 1, policy_version 20310 (0.0009) -[2023-11-28 00:44:40,691][87426] Updated weights for policy 1, policy_version 20320 (0.0009) -[2023-11-28 00:44:41,258][87424] Updated weights for policy 0, policy_version 20426 (0.0012) -[2023-11-28 00:44:41,635][87424] Updated weights for policy 0, policy_version 20436 (0.0012) -[2023-11-28 00:44:42,021][87424] Updated weights for policy 0, policy_version 20446 (0.0012) -[2023-11-28 00:44:42,831][87426] Updated weights for policy 1, policy_version 20330 (0.0012) -[2023-11-28 00:44:43,213][87426] Updated weights for policy 1, policy_version 20340 (0.0012) -[2023-11-28 00:44:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 10436608. Throughput: 0: 2696.6, 1: 2657.5. Samples: 10455204. Policy #0 lag: (min: 11.0, avg: 32.5, max: 61.0) -[2023-11-28 00:44:43,445][86177] Avg episode reward: [(0, '-574.360'), (1, '-512.570')] -[2023-11-28 00:44:43,597][87426] Updated weights for policy 1, policy_version 20350 (0.0012) -[2023-11-28 00:44:44,216][87424] Updated weights for policy 0, policy_version 20456 (0.0009) -[2023-11-28 00:44:44,603][87424] Updated weights for policy 0, policy_version 20466 (0.0007) -[2023-11-28 00:44:44,980][87424] Updated weights for policy 0, policy_version 20476 (0.0008) -[2023-11-28 00:44:45,431][87426] Updated weights for policy 1, policy_version 20360 (0.0012) -[2023-11-28 00:44:45,804][87426] Updated weights for policy 1, policy_version 20370 (0.0012) -[2023-11-28 00:44:46,189][87426] Updated weights for policy 1, policy_version 20380 (0.0012) -[2023-11-28 00:44:47,248][87424] Updated weights for policy 0, policy_version 20486 (0.0008) -[2023-11-28 00:44:47,627][87424] Updated weights for policy 0, policy_version 20496 (0.0009) -[2023-11-28 00:44:48,020][87424] Updated weights for policy 0, policy_version 20506 (0.0012) -[2023-11-28 00:44:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 10469376. Throughput: 0: 2683.3, 1: 2654.8. Samples: 10479264. Policy #0 lag: (min: 11.0, avg: 32.5, max: 61.0) -[2023-11-28 00:44:48,445][86177] Avg episode reward: [(0, '-556.900'), (1, '-505.470')] -[2023-11-28 00:44:48,530][87426] Updated weights for policy 1, policy_version 20390 (0.0011) -[2023-11-28 00:44:48,912][87426] Updated weights for policy 1, policy_version 20400 (0.0009) -[2023-11-28 00:44:49,294][87426] Updated weights for policy 1, policy_version 20410 (0.0010) -[2023-11-28 00:44:50,417][87424] Updated weights for policy 0, policy_version 20516 (0.0012) -[2023-11-28 00:44:50,800][87424] Updated weights for policy 0, policy_version 20526 (0.0009) -[2023-11-28 00:44:51,178][87424] Updated weights for policy 0, policy_version 20536 (0.0009) -[2023-11-28 00:44:51,679][87426] Updated weights for policy 1, policy_version 20420 (0.0011) -[2023-11-28 00:44:52,051][87426] Updated weights for policy 1, policy_version 20430 (0.0010) -[2023-11-28 00:44:52,431][87426] Updated weights for policy 1, policy_version 20440 (0.0011) -[2023-11-28 00:44:53,276][87424] Updated weights for policy 0, policy_version 20546 (0.0010) -[2023-11-28 00:44:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 10493952. Throughput: 0: 2663.9, 1: 2664.4. Samples: 10511768. Policy #0 lag: (min: 11.0, avg: 32.5, max: 61.0) -[2023-11-28 00:44:53,445][86177] Avg episode reward: [(0, '-529.940'), (1, '-521.070')] -[2023-11-28 00:44:53,656][87424] Updated weights for policy 0, policy_version 20556 (0.0013) -[2023-11-28 00:44:54,043][87424] Updated weights for policy 0, policy_version 20566 (0.0012) -[2023-11-28 00:44:54,440][87424] Updated weights for policy 0, policy_version 20576 (0.0012) -[2023-11-28 00:44:54,867][87426] Updated weights for policy 1, policy_version 20450 (0.0011) -[2023-11-28 00:44:55,243][87426] Updated weights for policy 1, policy_version 20460 (0.0007) -[2023-11-28 00:44:55,621][87426] Updated weights for policy 1, policy_version 20470 (0.0007) -[2023-11-28 00:44:56,004][87426] Updated weights for policy 1, policy_version 20480 (0.0011) -[2023-11-28 00:44:56,331][87424] Updated weights for policy 0, policy_version 20586 (0.0008) -[2023-11-28 00:44:56,722][87424] Updated weights for policy 0, policy_version 20596 (0.0007) -[2023-11-28 00:44:57,094][87424] Updated weights for policy 0, policy_version 20606 (0.0009) -[2023-11-28 00:44:57,717][87426] Updated weights for policy 1, policy_version 20490 (0.0012) -[2023-11-28 00:44:58,094][87426] Updated weights for policy 1, policy_version 20500 (0.0009) -[2023-11-28 00:44:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 10518528. Throughput: 0: 2679.7, 1: 2661.8. Samples: 10536084. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:44:58,445][86177] Avg episode reward: [(0, '-562.480'), (1, '-518.490')] -[2023-11-28 00:44:58,478][87426] Updated weights for policy 1, policy_version 20510 (0.0007) -[2023-11-28 00:44:59,154][87424] Updated weights for policy 0, policy_version 20616 (0.0011) -[2023-11-28 00:44:59,535][87424] Updated weights for policy 0, policy_version 20626 (0.0010) -[2023-11-28 00:44:59,925][87424] Updated weights for policy 0, policy_version 20636 (0.0009) -[2023-11-28 00:45:00,965][87426] Updated weights for policy 1, policy_version 20520 (0.0011) -[2023-11-28 00:45:01,359][87426] Updated weights for policy 1, policy_version 20530 (0.0012) -[2023-11-28 00:45:01,732][87426] Updated weights for policy 1, policy_version 20540 (0.0012) -[2023-11-28 00:45:01,942][87424] Updated weights for policy 0, policy_version 20646 (0.0011) -[2023-11-28 00:45:02,324][87424] Updated weights for policy 0, policy_version 20656 (0.0008) -[2023-11-28 00:45:02,714][87424] Updated weights for policy 0, policy_version 20666 (0.0007) -[2023-11-28 00:45:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 10551296. Throughput: 0: 2714.8, 1: 2672.4. Samples: 10561712. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:45:03,445][86177] Avg episode reward: [(0, '-563.890'), (1, '-518.340')] -[2023-11-28 00:45:03,772][87426] Updated weights for policy 1, policy_version 20550 (0.0008) -[2023-11-28 00:45:04,161][87426] Updated weights for policy 1, policy_version 20560 (0.0007) -[2023-11-28 00:45:04,532][87426] Updated weights for policy 1, policy_version 20570 (0.0008) -[2023-11-28 00:45:05,206][87424] Updated weights for policy 0, policy_version 20676 (0.0011) -[2023-11-28 00:45:05,593][87424] Updated weights for policy 0, policy_version 20686 (0.0009) -[2023-11-28 00:45:05,974][87424] Updated weights for policy 0, policy_version 20696 (0.0007) -[2023-11-28 00:45:06,530][87426] Updated weights for policy 1, policy_version 20580 (0.0012) -[2023-11-28 00:45:06,918][87426] Updated weights for policy 1, policy_version 20590 (0.0012) -[2023-11-28 00:45:07,284][87426] Updated weights for policy 1, policy_version 20600 (0.0012) -[2023-11-28 00:45:08,409][87424] Updated weights for policy 0, policy_version 20706 (0.0009) -[2023-11-28 00:45:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 10575872. Throughput: 0: 2746.0, 1: 2670.3. Samples: 10593804. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 00:45:08,445][86177] Avg episode reward: [(0, '-559.010'), (1, '-519.940')] -[2023-11-28 00:45:08,790][87424] Updated weights for policy 0, policy_version 20716 (0.0012) -[2023-11-28 00:45:09,173][87424] Updated weights for policy 0, policy_version 20726 (0.0012) -[2023-11-28 00:45:09,442][87426] Updated weights for policy 1, policy_version 20610 (0.0012) -[2023-11-28 00:45:09,556][87424] Updated weights for policy 0, policy_version 20736 (0.0009) -[2023-11-28 00:45:09,827][87426] Updated weights for policy 1, policy_version 20620 (0.0012) -[2023-11-28 00:45:10,202][87426] Updated weights for policy 1, policy_version 20630 (0.0009) -[2023-11-28 00:45:10,576][87426] Updated weights for policy 1, policy_version 20640 (0.0012) -[2023-11-28 00:45:11,778][87424] Updated weights for policy 0, policy_version 20746 (0.0012) -[2023-11-28 00:45:12,155][87424] Updated weights for policy 0, policy_version 20756 (0.0010) -[2023-11-28 00:45:12,542][87424] Updated weights for policy 0, policy_version 20766 (0.0009) -[2023-11-28 00:45:12,743][87426] Updated weights for policy 1, policy_version 20650 (0.0008) -[2023-11-28 00:45:13,123][87426] Updated weights for policy 1, policy_version 20660 (0.0008) -[2023-11-28 00:45:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 10600448. Throughput: 0: 2723.2, 1: 2693.9. Samples: 10617560. Policy #0 lag: (min: 31.0, avg: 51.0, max: 90.0) -[2023-11-28 00:45:13,445][86177] Avg episode reward: [(0, '-557.340'), (1, '-515.720')] -[2023-11-28 00:45:13,510][87426] Updated weights for policy 1, policy_version 20670 (0.0007) -[2023-11-28 00:45:14,742][87424] Updated weights for policy 0, policy_version 20776 (0.0011) -[2023-11-28 00:45:15,125][87424] Updated weights for policy 0, policy_version 20786 (0.0012) -[2023-11-28 00:45:15,516][87424] Updated weights for policy 0, policy_version 20796 (0.0015) -[2023-11-28 00:45:15,602][87426] Updated weights for policy 1, policy_version 20680 (0.0011) -[2023-11-28 00:45:15,976][87426] Updated weights for policy 1, policy_version 20690 (0.0012) -[2023-11-28 00:45:16,358][87426] Updated weights for policy 1, policy_version 20700 (0.0011) -[2023-11-28 00:45:17,840][87424] Updated weights for policy 0, policy_version 20806 (0.0010) -[2023-11-28 00:45:18,224][87424] Updated weights for policy 0, policy_version 20816 (0.0008) -[2023-11-28 00:45:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 10625024. Throughput: 0: 2703.7, 1: 2712.3. Samples: 10641640. Policy #0 lag: (min: 31.0, avg: 51.0, max: 90.0) -[2023-11-28 00:45:18,445][86177] Avg episode reward: [(0, '-519.140'), (1, '-515.050')] -[2023-11-28 00:45:18,612][87424] Updated weights for policy 0, policy_version 20826 (0.0010) -[2023-11-28 00:45:18,840][87281] Saving new best policy, reward=-519.140! -[2023-11-28 00:45:18,920][87426] Updated weights for policy 1, policy_version 20710 (0.0010) -[2023-11-28 00:45:19,291][87426] Updated weights for policy 1, policy_version 20720 (0.0009) -[2023-11-28 00:45:19,674][87426] Updated weights for policy 1, policy_version 20730 (0.0009) -[2023-11-28 00:45:20,709][87424] Updated weights for policy 0, policy_version 20836 (0.0010) -[2023-11-28 00:45:21,103][87424] Updated weights for policy 0, policy_version 20846 (0.0012) -[2023-11-28 00:45:21,476][87424] Updated weights for policy 0, policy_version 20856 (0.0012) -[2023-11-28 00:45:22,120][87426] Updated weights for policy 1, policy_version 20740 (0.0010) -[2023-11-28 00:45:22,512][87426] Updated weights for policy 1, policy_version 20750 (0.0010) -[2023-11-28 00:45:22,888][87426] Updated weights for policy 1, policy_version 20760 (0.0009) -[2023-11-28 00:45:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 10657792. Throughput: 0: 2687.9, 1: 2707.2. Samples: 10673692. Policy #0 lag: (min: 31.0, avg: 51.0, max: 90.0) -[2023-11-28 00:45:23,446][86177] Avg episode reward: [(0, '-560.830'), (1, '-556.600')] -[2023-11-28 00:45:23,704][87424] Updated weights for policy 0, policy_version 20866 (0.0011) -[2023-11-28 00:45:24,081][87424] Updated weights for policy 0, policy_version 20876 (0.0012) -[2023-11-28 00:45:24,463][87424] Updated weights for policy 0, policy_version 20886 (0.0012) -[2023-11-28 00:45:24,845][87426] Updated weights for policy 1, policy_version 20770 (0.0011) -[2023-11-28 00:45:24,846][87424] Updated weights for policy 0, policy_version 20896 (0.0011) -[2023-11-28 00:45:25,227][87426] Updated weights for policy 1, policy_version 20780 (0.0008) -[2023-11-28 00:45:25,607][87426] Updated weights for policy 1, policy_version 20790 (0.0007) -[2023-11-28 00:45:25,991][87426] Updated weights for policy 1, policy_version 20800 (0.0007) -[2023-11-28 00:45:27,422][87424] Updated weights for policy 0, policy_version 20906 (0.0011) -[2023-11-28 00:45:27,820][87424] Updated weights for policy 0, policy_version 20916 (0.0011) -[2023-11-28 00:45:28,199][87424] Updated weights for policy 0, policy_version 20926 (0.0012) -[2023-11-28 00:45:28,214][87426] Updated weights for policy 1, policy_version 20810 (0.0010) -[2023-11-28 00:45:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 10682368. Throughput: 0: 2677.2, 1: 2725.3. Samples: 10698316. Policy #0 lag: (min: 19.0, avg: 42.8, max: 70.0) -[2023-11-28 00:45:28,445][86177] Avg episode reward: [(0, '-555.680'), (1, '-565.780')] -[2023-11-28 00:45:28,599][87426] Updated weights for policy 1, policy_version 20820 (0.0012) -[2023-11-28 00:45:28,993][87426] Updated weights for policy 1, policy_version 20830 (0.0012) -[2023-11-28 00:45:30,280][87424] Updated weights for policy 0, policy_version 20936 (0.0012) -[2023-11-28 00:45:30,657][87424] Updated weights for policy 0, policy_version 20946 (0.0012) -[2023-11-28 00:45:30,907][87426] Updated weights for policy 1, policy_version 20840 (0.0012) -[2023-11-28 00:45:31,043][87424] Updated weights for policy 0, policy_version 20956 (0.0012) -[2023-11-28 00:45:31,285][87426] Updated weights for policy 1, policy_version 20850 (0.0011) -[2023-11-28 00:45:31,666][87426] Updated weights for policy 1, policy_version 20860 (0.0012) -[2023-11-28 00:45:33,004][87424] Updated weights for policy 0, policy_version 20966 (0.0010) -[2023-11-28 00:45:33,381][87424] Updated weights for policy 0, policy_version 20976 (0.0008) -[2023-11-28 00:45:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 10706944. Throughput: 0: 2688.6, 1: 2733.8. Samples: 10723272. Policy #0 lag: (min: 19.0, avg: 42.8, max: 70.0) -[2023-11-28 00:45:33,445][86177] Avg episode reward: [(0, '-566.540'), (1, '-559.590')] -[2023-11-28 00:45:33,769][87424] Updated weights for policy 0, policy_version 20986 (0.0011) -[2023-11-28 00:45:34,162][87426] Updated weights for policy 1, policy_version 20870 (0.0011) -[2023-11-28 00:45:34,540][87426] Updated weights for policy 1, policy_version 20880 (0.0010) -[2023-11-28 00:45:34,919][87426] Updated weights for policy 1, policy_version 20890 (0.0008) -[2023-11-28 00:45:35,701][87424] Updated weights for policy 0, policy_version 20996 (0.0010) -[2023-11-28 00:45:36,084][87424] Updated weights for policy 0, policy_version 21006 (0.0007) -[2023-11-28 00:45:36,477][87424] Updated weights for policy 0, policy_version 21016 (0.0009) -[2023-11-28 00:45:36,786][87426] Updated weights for policy 1, policy_version 20900 (0.0010) -[2023-11-28 00:45:37,175][87426] Updated weights for policy 1, policy_version 20910 (0.0011) -[2023-11-28 00:45:37,548][87426] Updated weights for policy 1, policy_version 20920 (0.0011) -[2023-11-28 00:45:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 10739712. Throughput: 0: 2706.8, 1: 2711.5. Samples: 10755592. Policy #0 lag: (min: 19.0, avg: 42.8, max: 70.0) -[2023-11-28 00:45:38,445][86177] Avg episode reward: [(0, '-574.330'), (1, '-590.210')] -[2023-11-28 00:45:38,477][87424] Updated weights for policy 0, policy_version 21026 (0.0009) -[2023-11-28 00:45:38,858][87424] Updated weights for policy 0, policy_version 21036 (0.0008) -[2023-11-28 00:45:39,242][87424] Updated weights for policy 0, policy_version 21046 (0.0008) -[2023-11-28 00:45:39,331][87426] Updated weights for policy 1, policy_version 20930 (0.0011) -[2023-11-28 00:45:39,625][87424] Updated weights for policy 0, policy_version 21056 (0.0010) -[2023-11-28 00:45:39,718][87426] Updated weights for policy 1, policy_version 20940 (0.0009) -[2023-11-28 00:45:40,091][87426] Updated weights for policy 1, policy_version 20950 (0.0009) -[2023-11-28 00:45:40,466][87426] Updated weights for policy 1, policy_version 20960 (0.0009) -[2023-11-28 00:45:41,954][87424] Updated weights for policy 0, policy_version 21066 (0.0010) -[2023-11-28 00:45:42,341][87424] Updated weights for policy 0, policy_version 21076 (0.0009) -[2023-11-28 00:45:42,721][87424] Updated weights for policy 0, policy_version 21086 (0.0007) -[2023-11-28 00:45:42,834][87426] Updated weights for policy 1, policy_version 20970 (0.0012) -[2023-11-28 00:45:43,206][87426] Updated weights for policy 1, policy_version 20980 (0.0012) -[2023-11-28 00:45:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 10764288. Throughput: 0: 2699.9, 1: 2707.9. Samples: 10779436. Policy #0 lag: (min: 19.0, avg: 42.8, max: 70.0) -[2023-11-28 00:45:43,445][86177] Avg episode reward: [(0, '-538.420'), (1, '-562.050')] -[2023-11-28 00:45:43,589][87426] Updated weights for policy 1, policy_version 20990 (0.0009) -[2023-11-28 00:45:44,791][87424] Updated weights for policy 0, policy_version 21096 (0.0008) -[2023-11-28 00:45:45,175][87424] Updated weights for policy 0, policy_version 21106 (0.0009) -[2023-11-28 00:45:45,566][87424] Updated weights for policy 0, policy_version 21116 (0.0009) -[2023-11-28 00:45:46,180][87426] Updated weights for policy 1, policy_version 21000 (0.0009) -[2023-11-28 00:45:46,555][87426] Updated weights for policy 1, policy_version 21010 (0.0007) -[2023-11-28 00:45:46,929][87426] Updated weights for policy 1, policy_version 21020 (0.0007) -[2023-11-28 00:45:47,974][87424] Updated weights for policy 0, policy_version 21126 (0.0010) -[2023-11-28 00:45:48,354][87424] Updated weights for policy 0, policy_version 21136 (0.0012) -[2023-11-28 00:45:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 10788864. Throughput: 0: 2683.5, 1: 2681.9. Samples: 10803160. Policy #0 lag: (min: 27.0, avg: 51.9, max: 69.0) -[2023-11-28 00:45:48,445][86177] Avg episode reward: [(0, '-562.820'), (1, '-552.200')] -[2023-11-28 00:45:48,732][87424] Updated weights for policy 0, policy_version 21146 (0.0012) -[2023-11-28 00:45:49,421][87426] Updated weights for policy 1, policy_version 21030 (0.0009) -[2023-11-28 00:45:49,809][87426] Updated weights for policy 1, policy_version 21040 (0.0008) -[2023-11-28 00:45:50,193][87426] Updated weights for policy 1, policy_version 21050 (0.0008) -[2023-11-28 00:45:51,389][87424] Updated weights for policy 0, policy_version 21156 (0.0012) -[2023-11-28 00:45:51,781][87424] Updated weights for policy 0, policy_version 21166 (0.0011) -[2023-11-28 00:45:51,941][87426] Updated weights for policy 1, policy_version 21060 (0.0008) -[2023-11-28 00:45:52,162][87424] Updated weights for policy 0, policy_version 21176 (0.0012) -[2023-11-28 00:45:52,323][87426] Updated weights for policy 1, policy_version 21070 (0.0008) -[2023-11-28 00:45:52,713][87426] Updated weights for policy 1, policy_version 21080 (0.0008) -[2023-11-28 00:45:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 10821632. Throughput: 0: 2649.9, 1: 2693.4. Samples: 10834252. Policy #0 lag: (min: 27.0, avg: 51.9, max: 69.0) -[2023-11-28 00:45:53,445][86177] Avg episode reward: [(0, '-552.690'), (1, '-550.200')] -[2023-11-28 00:45:54,290][87424] Updated weights for policy 0, policy_version 21186 (0.0011) -[2023-11-28 00:45:54,665][87424] Updated weights for policy 0, policy_version 21196 (0.0012) -[2023-11-28 00:45:55,054][87424] Updated weights for policy 0, policy_version 21206 (0.0012) -[2023-11-28 00:45:55,161][87426] Updated weights for policy 1, policy_version 21090 (0.0011) -[2023-11-28 00:45:55,433][87424] Updated weights for policy 0, policy_version 21216 (0.0011) -[2023-11-28 00:45:55,545][87426] Updated weights for policy 1, policy_version 21100 (0.0007) -[2023-11-28 00:45:55,926][87426] Updated weights for policy 1, policy_version 21110 (0.0007) -[2023-11-28 00:45:56,310][87426] Updated weights for policy 1, policy_version 21120 (0.0008) -[2023-11-28 00:45:57,540][87424] Updated weights for policy 0, policy_version 21226 (0.0008) -[2023-11-28 00:45:57,929][87424] Updated weights for policy 0, policy_version 21236 (0.0008) -[2023-11-28 00:45:58,305][87424] Updated weights for policy 0, policy_version 21246 (0.0010) -[2023-11-28 00:45:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 10846208. Throughput: 0: 2660.2, 1: 2702.1. Samples: 10858864. Policy #0 lag: (min: 27.0, avg: 51.9, max: 69.0) -[2023-11-28 00:45:58,445][86177] Avg episode reward: [(0, '-536.060'), (1, '-524.560')] -[2023-11-28 00:45:58,628][87426] Updated weights for policy 1, policy_version 21130 (0.0007) -[2023-11-28 00:45:59,004][87426] Updated weights for policy 1, policy_version 21140 (0.0009) -[2023-11-28 00:45:59,380][87426] Updated weights for policy 1, policy_version 21150 (0.0012) -[2023-11-28 00:46:00,253][87424] Updated weights for policy 0, policy_version 21256 (0.0012) -[2023-11-28 00:46:00,637][87424] Updated weights for policy 0, policy_version 21266 (0.0012) -[2023-11-28 00:46:01,029][87424] Updated weights for policy 0, policy_version 21276 (0.0012) -[2023-11-28 00:46:01,441][87426] Updated weights for policy 1, policy_version 21160 (0.0012) -[2023-11-28 00:46:01,831][87426] Updated weights for policy 1, policy_version 21170 (0.0012) -[2023-11-28 00:46:02,220][87426] Updated weights for policy 1, policy_version 21180 (0.0012) -[2023-11-28 00:46:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 10870784. Throughput: 0: 2696.9, 1: 2693.2. Samples: 10884192. Policy #0 lag: (min: 31.0, avg: 35.9, max: 58.0) -[2023-11-28 00:46:03,445][86177] Avg episode reward: [(0, '-526.780'), (1, '-562.670')] -[2023-11-28 00:46:03,506][87424] Updated weights for policy 0, policy_version 21286 (0.0011) -[2023-11-28 00:46:03,892][87424] Updated weights for policy 0, policy_version 21296 (0.0012) -[2023-11-28 00:46:04,044][87426] Updated weights for policy 1, policy_version 21190 (0.0012) -[2023-11-28 00:46:04,269][87424] Updated weights for policy 0, policy_version 21306 (0.0011) -[2023-11-28 00:46:04,418][87426] Updated weights for policy 1, policy_version 21200 (0.0010) -[2023-11-28 00:46:04,803][87426] Updated weights for policy 1, policy_version 21210 (0.0008) -[2023-11-28 00:46:06,555][87424] Updated weights for policy 0, policy_version 21316 (0.0011) -[2023-11-28 00:46:06,947][87424] Updated weights for policy 0, policy_version 21326 (0.0012) -[2023-11-28 00:46:07,324][87424] Updated weights for policy 0, policy_version 21336 (0.0011) -[2023-11-28 00:46:07,330][87426] Updated weights for policy 1, policy_version 21220 (0.0011) -[2023-11-28 00:46:07,709][87426] Updated weights for policy 1, policy_version 21230 (0.0012) -[2023-11-28 00:46:08,097][87426] Updated weights for policy 1, policy_version 21240 (0.0012) -[2023-11-28 00:46:08,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 10903552. Throughput: 0: 2688.4, 1: 2710.1. Samples: 10916624. Policy #0 lag: (min: 31.0, avg: 35.9, max: 58.0) -[2023-11-28 00:46:08,446][86177] Avg episode reward: [(0, '-502.370'), (1, '-584.250')] -[2023-11-28 00:46:08,447][87281] Saving new best policy, reward=-502.370! -[2023-11-28 00:46:09,521][87424] Updated weights for policy 0, policy_version 21346 (0.0008) -[2023-11-28 00:46:09,904][87424] Updated weights for policy 0, policy_version 21356 (0.0011) -[2023-11-28 00:46:10,295][87424] Updated weights for policy 0, policy_version 21366 (0.0010) -[2023-11-28 00:46:10,678][87424] Updated weights for policy 0, policy_version 21376 (0.0011) -[2023-11-28 00:46:10,698][87426] Updated weights for policy 1, policy_version 21250 (0.0010) -[2023-11-28 00:46:11,075][87426] Updated weights for policy 1, policy_version 21260 (0.0011) -[2023-11-28 00:46:11,461][87426] Updated weights for policy 1, policy_version 21270 (0.0012) -[2023-11-28 00:46:11,836][87426] Updated weights for policy 1, policy_version 21280 (0.0012) -[2023-11-28 00:46:13,073][87424] Updated weights for policy 0, policy_version 21386 (0.0012) -[2023-11-28 00:46:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 10919936. Throughput: 0: 2694.1, 1: 2681.8. Samples: 10940232. Policy #0 lag: (min: 31.0, avg: 35.9, max: 58.0) -[2023-11-28 00:46:13,445][86177] Avg episode reward: [(0, '-515.970'), (1, '-591.360')] -[2023-11-28 00:46:13,462][87424] Updated weights for policy 0, policy_version 21396 (0.0011) -[2023-11-28 00:46:13,833][87424] Updated weights for policy 0, policy_version 21406 (0.0010) -[2023-11-28 00:46:13,844][87426] Updated weights for policy 1, policy_version 21290 (0.0009) -[2023-11-28 00:46:14,223][87426] Updated weights for policy 1, policy_version 21300 (0.0007) -[2023-11-28 00:46:14,604][87426] Updated weights for policy 1, policy_version 21310 (0.0008) -[2023-11-28 00:46:15,915][87424] Updated weights for policy 0, policy_version 21416 (0.0011) -[2023-11-28 00:46:16,295][87424] Updated weights for policy 0, policy_version 21426 (0.0012) -[2023-11-28 00:46:16,673][87424] Updated weights for policy 0, policy_version 21436 (0.0011) -[2023-11-28 00:46:16,727][87426] Updated weights for policy 1, policy_version 21320 (0.0008) -[2023-11-28 00:46:17,105][87426] Updated weights for policy 1, policy_version 21330 (0.0008) -[2023-11-28 00:46:17,501][87426] Updated weights for policy 1, policy_version 21340 (0.0009) -[2023-11-28 00:46:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 10952704. Throughput: 0: 2673.4, 1: 2692.1. Samples: 10964720. Policy #0 lag: (min: 31.0, avg: 52.5, max: 70.0) -[2023-11-28 00:46:18,445][86177] Avg episode reward: [(0, '-518.280'), (1, '-589.900')] -[2023-11-28 00:46:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000021440_5488640.pth... -[2023-11-28 00:46:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000021344_5464064.pth... -[2023-11-28 00:46:18,487][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000018912_4841472.pth -[2023-11-28 00:46:18,499][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000018816_4816896.pth -[2023-11-28 00:46:19,165][87424] Updated weights for policy 0, policy_version 21446 (0.0011) -[2023-11-28 00:46:19,539][87424] Updated weights for policy 0, policy_version 21456 (0.0012) -[2023-11-28 00:46:19,920][87424] Updated weights for policy 0, policy_version 21466 (0.0012) -[2023-11-28 00:46:20,079][87426] Updated weights for policy 1, policy_version 21350 (0.0011) -[2023-11-28 00:46:20,454][87426] Updated weights for policy 1, policy_version 21360 (0.0011) -[2023-11-28 00:46:20,833][87426] Updated weights for policy 1, policy_version 21370 (0.0007) -[2023-11-28 00:46:22,482][87424] Updated weights for policy 0, policy_version 21476 (0.0011) -[2023-11-28 00:46:22,866][87424] Updated weights for policy 0, policy_version 21486 (0.0012) -[2023-11-28 00:46:23,250][87424] Updated weights for policy 0, policy_version 21496 (0.0011) -[2023-11-28 00:46:23,298][87426] Updated weights for policy 1, policy_version 21380 (0.0009) -[2023-11-28 00:46:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 10969088. Throughput: 0: 2630.0, 1: 2687.6. Samples: 10994888. Policy #0 lag: (min: 31.0, avg: 52.5, max: 70.0) -[2023-11-28 00:46:23,445][86177] Avg episode reward: [(0, '-526.190'), (1, '-548.260')] -[2023-11-28 00:46:23,685][87426] Updated weights for policy 1, policy_version 21390 (0.0010) -[2023-11-28 00:46:24,065][87426] Updated weights for policy 1, policy_version 21400 (0.0012) -[2023-11-28 00:46:25,065][87424] Updated weights for policy 0, policy_version 21506 (0.0011) -[2023-11-28 00:46:25,448][87424] Updated weights for policy 0, policy_version 21516 (0.0008) -[2023-11-28 00:46:25,831][87424] Updated weights for policy 0, policy_version 21526 (0.0007) -[2023-11-28 00:46:25,898][87426] Updated weights for policy 1, policy_version 21410 (0.0011) -[2023-11-28 00:46:26,212][87424] Updated weights for policy 0, policy_version 21536 (0.0008) -[2023-11-28 00:46:26,274][87426] Updated weights for policy 1, policy_version 21420 (0.0008) -[2023-11-28 00:46:26,654][87426] Updated weights for policy 1, policy_version 21430 (0.0011) -[2023-11-28 00:46:27,030][87426] Updated weights for policy 1, policy_version 21440 (0.0012) -[2023-11-28 00:46:27,836][87424] Updated weights for policy 0, policy_version 21546 (0.0010) -[2023-11-28 00:46:28,223][87424] Updated weights for policy 0, policy_version 21556 (0.0012) -[2023-11-28 00:46:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 11001856. Throughput: 0: 2649.7, 1: 2690.7. Samples: 11019752. Policy #0 lag: (min: 31.0, avg: 52.5, max: 70.0) -[2023-11-28 00:46:28,445][86177] Avg episode reward: [(0, '-560.250'), (1, '-533.330')] -[2023-11-28 00:46:28,602][87424] Updated weights for policy 0, policy_version 21566 (0.0012) -[2023-11-28 00:46:28,731][87426] Updated weights for policy 1, policy_version 21450 (0.0011) -[2023-11-28 00:46:29,108][87426] Updated weights for policy 1, policy_version 21460 (0.0009) -[2023-11-28 00:46:29,489][87426] Updated weights for policy 1, policy_version 21470 (0.0007) -[2023-11-28 00:46:31,025][87424] Updated weights for policy 0, policy_version 21576 (0.0012) -[2023-11-28 00:46:31,408][87424] Updated weights for policy 0, policy_version 21586 (0.0011) -[2023-11-28 00:46:31,733][87426] Updated weights for policy 1, policy_version 21480 (0.0009) -[2023-11-28 00:46:31,790][87424] Updated weights for policy 0, policy_version 21596 (0.0011) -[2023-11-28 00:46:32,113][87426] Updated weights for policy 1, policy_version 21490 (0.0009) -[2023-11-28 00:46:32,498][87426] Updated weights for policy 1, policy_version 21500 (0.0011) -[2023-11-28 00:46:33,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 11034624. Throughput: 0: 2663.7, 1: 2720.8. Samples: 11045464. Policy #0 lag: (min: 31.0, avg: 52.5, max: 70.0) -[2023-11-28 00:46:33,445][86177] Avg episode reward: [(0, '-555.160'), (1, '-538.660')] -[2023-11-28 00:46:34,354][87424] Updated weights for policy 0, policy_version 21606 (0.0009) -[2023-11-28 00:46:34,584][87426] Updated weights for policy 1, policy_version 21510 (0.0011) -[2023-11-28 00:46:34,736][87424] Updated weights for policy 0, policy_version 21616 (0.0012) -[2023-11-28 00:46:34,961][87426] Updated weights for policy 1, policy_version 21520 (0.0011) -[2023-11-28 00:46:35,119][87424] Updated weights for policy 0, policy_version 21626 (0.0009) -[2023-11-28 00:46:35,345][87426] Updated weights for policy 1, policy_version 21530 (0.0011) -[2023-11-28 00:46:36,968][87424] Updated weights for policy 0, policy_version 21636 (0.0010) -[2023-11-28 00:46:37,348][87424] Updated weights for policy 0, policy_version 21646 (0.0012) -[2023-11-28 00:46:37,732][87424] Updated weights for policy 0, policy_version 21656 (0.0012) -[2023-11-28 00:46:37,734][87426] Updated weights for policy 1, policy_version 21540 (0.0011) -[2023-11-28 00:46:38,118][87426] Updated weights for policy 1, policy_version 21550 (0.0011) -[2023-11-28 00:46:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 11059200. Throughput: 0: 2708.4, 1: 2714.9. Samples: 11078296. Policy #0 lag: (min: 5.0, avg: 26.5, max: 37.0) -[2023-11-28 00:46:38,445][86177] Avg episode reward: [(0, '-551.080'), (1, '-535.200')] -[2023-11-28 00:46:38,498][87426] Updated weights for policy 1, policy_version 21560 (0.0009) -[2023-11-28 00:46:39,499][87424] Updated weights for policy 0, policy_version 21666 (0.0012) -[2023-11-28 00:46:39,880][87424] Updated weights for policy 0, policy_version 21676 (0.0012) -[2023-11-28 00:46:40,262][87424] Updated weights for policy 0, policy_version 21686 (0.0012) -[2023-11-28 00:46:40,430][87426] Updated weights for policy 1, policy_version 21570 (0.0015) -[2023-11-28 00:46:40,649][87424] Updated weights for policy 0, policy_version 21696 (0.0011) -[2023-11-28 00:46:40,811][87426] Updated weights for policy 1, policy_version 21580 (0.0011) -[2023-11-28 00:46:41,202][87426] Updated weights for policy 1, policy_version 21590 (0.0011) -[2023-11-28 00:46:41,575][87426] Updated weights for policy 1, policy_version 21600 (0.0010) -[2023-11-28 00:46:43,086][87424] Updated weights for policy 0, policy_version 21706 (0.0012) -[2023-11-28 00:46:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 11083776. Throughput: 0: 2711.6, 1: 2705.2. Samples: 11102616. Policy #0 lag: (min: 5.0, avg: 26.5, max: 37.0) -[2023-11-28 00:46:43,445][86177] Avg episode reward: [(0, '-543.170'), (1, '-589.200')] -[2023-11-28 00:46:43,473][87424] Updated weights for policy 0, policy_version 21716 (0.0010) -[2023-11-28 00:46:43,856][87424] Updated weights for policy 0, policy_version 21726 (0.0008) -[2023-11-28 00:46:44,098][87426] Updated weights for policy 1, policy_version 21610 (0.0009) -[2023-11-28 00:46:44,489][87426] Updated weights for policy 1, policy_version 21620 (0.0007) -[2023-11-28 00:46:44,874][87426] Updated weights for policy 1, policy_version 21630 (0.0011) -[2023-11-28 00:46:46,380][87424] Updated weights for policy 0, policy_version 21736 (0.0008) -[2023-11-28 00:46:46,585][87426] Updated weights for policy 1, policy_version 21640 (0.0011) -[2023-11-28 00:46:46,767][87424] Updated weights for policy 0, policy_version 21746 (0.0007) -[2023-11-28 00:46:46,969][87426] Updated weights for policy 1, policy_version 21650 (0.0012) -[2023-11-28 00:46:47,152][87424] Updated weights for policy 0, policy_version 21756 (0.0008) -[2023-11-28 00:46:47,347][87426] Updated weights for policy 1, policy_version 21660 (0.0011) -[2023-11-28 00:46:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 11116544. Throughput: 0: 2697.0, 1: 2707.7. Samples: 11127404. Policy #0 lag: (min: 5.0, avg: 26.5, max: 37.0) -[2023-11-28 00:46:48,445][86177] Avg episode reward: [(0, '-541.130'), (1, '-586.500')] -[2023-11-28 00:46:49,065][87424] Updated weights for policy 0, policy_version 21766 (0.0010) -[2023-11-28 00:46:49,461][87424] Updated weights for policy 0, policy_version 21776 (0.0011) -[2023-11-28 00:46:49,683][87426] Updated weights for policy 1, policy_version 21670 (0.0011) -[2023-11-28 00:46:49,846][87424] Updated weights for policy 0, policy_version 21786 (0.0011) -[2023-11-28 00:46:50,063][87426] Updated weights for policy 1, policy_version 21680 (0.0009) -[2023-11-28 00:46:50,453][87426] Updated weights for policy 1, policy_version 21690 (0.0009) -[2023-11-28 00:46:52,023][87424] Updated weights for policy 0, policy_version 21796 (0.0009) -[2023-11-28 00:46:52,191][87426] Updated weights for policy 1, policy_version 21700 (0.0011) -[2023-11-28 00:46:52,407][87424] Updated weights for policy 0, policy_version 21806 (0.0011) -[2023-11-28 00:46:52,565][87426] Updated weights for policy 1, policy_version 21710 (0.0010) -[2023-11-28 00:46:52,789][87424] Updated weights for policy 0, policy_version 21816 (0.0008) -[2023-11-28 00:46:52,938][87426] Updated weights for policy 1, policy_version 21720 (0.0008) -[2023-11-28 00:46:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 11149312. Throughput: 0: 2707.3, 1: 2715.3. Samples: 11160640. Policy #0 lag: (min: 31.0, avg: 48.4, max: 75.0) -[2023-11-28 00:46:53,445][86177] Avg episode reward: [(0, '-515.050'), (1, '-584.530')] -[2023-11-28 00:46:54,685][87424] Updated weights for policy 0, policy_version 21826 (0.0010) -[2023-11-28 00:46:55,050][87426] Updated weights for policy 1, policy_version 21730 (0.0011) -[2023-11-28 00:46:55,076][87424] Updated weights for policy 0, policy_version 21836 (0.0012) -[2023-11-28 00:46:55,417][87426] Updated weights for policy 1, policy_version 21740 (0.0012) -[2023-11-28 00:46:55,466][87424] Updated weights for policy 0, policy_version 21846 (0.0009) -[2023-11-28 00:46:55,804][87426] Updated weights for policy 1, policy_version 21750 (0.0011) -[2023-11-28 00:46:55,844][87424] Updated weights for policy 0, policy_version 21856 (0.0007) -[2023-11-28 00:46:56,181][87426] Updated weights for policy 1, policy_version 21760 (0.0011) -[2023-11-28 00:46:58,116][87424] Updated weights for policy 0, policy_version 21866 (0.0011) -[2023-11-28 00:46:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 11165696. Throughput: 0: 2703.4, 1: 2725.7. Samples: 11184540. Policy #0 lag: (min: 31.0, avg: 48.4, max: 75.0) -[2023-11-28 00:46:58,445][86177] Avg episode reward: [(0, '-523.610'), (1, '-585.260')] -[2023-11-28 00:46:58,505][87424] Updated weights for policy 0, policy_version 21876 (0.0009) -[2023-11-28 00:46:58,784][87426] Updated weights for policy 1, policy_version 21770 (0.0012) -[2023-11-28 00:46:58,891][87424] Updated weights for policy 0, policy_version 21886 (0.0009) -[2023-11-28 00:46:59,167][87426] Updated weights for policy 1, policy_version 21780 (0.0011) -[2023-11-28 00:46:59,545][87426] Updated weights for policy 1, policy_version 21790 (0.0011) -[2023-11-28 00:47:01,291][87424] Updated weights for policy 0, policy_version 21896 (0.0011) -[2023-11-28 00:47:01,638][87426] Updated weights for policy 1, policy_version 21800 (0.0011) -[2023-11-28 00:47:01,673][87424] Updated weights for policy 0, policy_version 21906 (0.0012) -[2023-11-28 00:47:02,012][87426] Updated weights for policy 1, policy_version 21810 (0.0009) -[2023-11-28 00:47:02,057][87424] Updated weights for policy 0, policy_version 21916 (0.0011) -[2023-11-28 00:47:02,386][87426] Updated weights for policy 1, policy_version 21820 (0.0008) -[2023-11-28 00:47:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 11198464. Throughput: 0: 2717.1, 1: 2718.9. Samples: 11209340. Policy #0 lag: (min: 31.0, avg: 48.4, max: 75.0) -[2023-11-28 00:47:03,445][86177] Avg episode reward: [(0, '-561.330'), (1, '-539.270')] -[2023-11-28 00:47:03,941][87424] Updated weights for policy 0, policy_version 21926 (0.0009) -[2023-11-28 00:47:04,024][87426] Updated weights for policy 1, policy_version 21830 (0.0007) -[2023-11-28 00:47:04,317][87424] Updated weights for policy 0, policy_version 21936 (0.0008) -[2023-11-28 00:47:04,409][87426] Updated weights for policy 1, policy_version 21840 (0.0010) -[2023-11-28 00:47:04,705][87424] Updated weights for policy 0, policy_version 21946 (0.0010) -[2023-11-28 00:47:04,786][87426] Updated weights for policy 1, policy_version 21850 (0.0009) -[2023-11-28 00:47:06,583][87424] Updated weights for policy 0, policy_version 21956 (0.0008) -[2023-11-28 00:47:06,965][87424] Updated weights for policy 0, policy_version 21966 (0.0010) -[2023-11-28 00:47:07,145][87426] Updated weights for policy 1, policy_version 21860 (0.0009) -[2023-11-28 00:47:07,345][87424] Updated weights for policy 0, policy_version 21976 (0.0012) -[2023-11-28 00:47:07,517][87426] Updated weights for policy 1, policy_version 21870 (0.0011) -[2023-11-28 00:47:07,904][87426] Updated weights for policy 1, policy_version 21880 (0.0007) -[2023-11-28 00:47:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 11231232. Throughput: 0: 2735.5, 1: 2738.5. Samples: 11241216. Policy #0 lag: (min: 31.0, avg: 48.4, max: 75.0) -[2023-11-28 00:47:08,445][86177] Avg episode reward: [(0, '-565.490'), (1, '-544.050')] -[2023-11-28 00:47:09,810][87424] Updated weights for policy 0, policy_version 21986 (0.0011) -[2023-11-28 00:47:10,198][87424] Updated weights for policy 0, policy_version 21996 (0.0011) -[2023-11-28 00:47:10,332][87426] Updated weights for policy 1, policy_version 21890 (0.0008) -[2023-11-28 00:47:10,584][87424] Updated weights for policy 0, policy_version 22006 (0.0009) -[2023-11-28 00:47:10,704][87426] Updated weights for policy 1, policy_version 21900 (0.0008) -[2023-11-28 00:47:10,963][87424] Updated weights for policy 0, policy_version 22016 (0.0010) -[2023-11-28 00:47:11,084][87426] Updated weights for policy 1, policy_version 21910 (0.0008) -[2023-11-28 00:47:11,470][87426] Updated weights for policy 1, policy_version 21920 (0.0011) -[2023-11-28 00:47:13,215][87424] Updated weights for policy 0, policy_version 22026 (0.0011) -[2023-11-28 00:47:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 11247616. Throughput: 0: 2745.3, 1: 2722.1. Samples: 11265788. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-11-28 00:47:13,445][86177] Avg episode reward: [(0, '-564.760'), (1, '-535.840')] -[2023-11-28 00:47:13,597][87424] Updated weights for policy 0, policy_version 22036 (0.0009) -[2023-11-28 00:47:13,958][87426] Updated weights for policy 1, policy_version 21930 (0.0010) -[2023-11-28 00:47:13,985][87424] Updated weights for policy 0, policy_version 22046 (0.0009) -[2023-11-28 00:47:14,340][87426] Updated weights for policy 1, policy_version 21940 (0.0009) -[2023-11-28 00:47:14,727][87426] Updated weights for policy 1, policy_version 21950 (0.0007) -[2023-11-28 00:47:16,262][87424] Updated weights for policy 0, policy_version 22056 (0.0011) -[2023-11-28 00:47:16,640][87424] Updated weights for policy 0, policy_version 22066 (0.0012) -[2023-11-28 00:47:16,949][87426] Updated weights for policy 1, policy_version 21960 (0.0008) -[2023-11-28 00:47:17,029][87424] Updated weights for policy 0, policy_version 22076 (0.0011) -[2023-11-28 00:47:17,323][87426] Updated weights for policy 1, policy_version 21970 (0.0008) -[2023-11-28 00:47:17,713][87426] Updated weights for policy 1, policy_version 21980 (0.0007) -[2023-11-28 00:47:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 11280384. Throughput: 0: 2714.4, 1: 2693.1. Samples: 11288804. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-11-28 00:47:18,445][86177] Avg episode reward: [(0, '-535.690'), (1, '-535.130')] -[2023-11-28 00:47:19,019][87424] Updated weights for policy 0, policy_version 22086 (0.0010) -[2023-11-28 00:47:19,401][87424] Updated weights for policy 0, policy_version 22096 (0.0007) -[2023-11-28 00:47:19,787][87424] Updated weights for policy 0, policy_version 22106 (0.0010) -[2023-11-28 00:47:20,195][87426] Updated weights for policy 1, policy_version 21990 (0.0009) -[2023-11-28 00:47:20,561][87426] Updated weights for policy 1, policy_version 22000 (0.0011) -[2023-11-28 00:47:20,945][87426] Updated weights for policy 1, policy_version 22010 (0.0012) -[2023-11-28 00:47:22,047][87424] Updated weights for policy 0, policy_version 22116 (0.0010) -[2023-11-28 00:47:22,434][87424] Updated weights for policy 0, policy_version 22126 (0.0012) -[2023-11-28 00:47:22,812][87424] Updated weights for policy 0, policy_version 22136 (0.0012) -[2023-11-28 00:47:23,272][87426] Updated weights for policy 1, policy_version 22020 (0.0010) -[2023-11-28 00:47:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 11304960. Throughput: 0: 2712.2, 1: 2696.3. Samples: 11321676. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-11-28 00:47:23,445][86177] Avg episode reward: [(0, '-551.620'), (1, '-547.720')] -[2023-11-28 00:47:23,647][87426] Updated weights for policy 1, policy_version 22030 (0.0007) -[2023-11-28 00:47:24,023][87426] Updated weights for policy 1, policy_version 22040 (0.0007) -[2023-11-28 00:47:25,391][87424] Updated weights for policy 0, policy_version 22146 (0.0012) -[2023-11-28 00:47:25,766][87424] Updated weights for policy 0, policy_version 22156 (0.0012) -[2023-11-28 00:47:26,019][87426] Updated weights for policy 1, policy_version 22050 (0.0008) -[2023-11-28 00:47:26,146][87424] Updated weights for policy 0, policy_version 22166 (0.0012) -[2023-11-28 00:47:26,397][87426] Updated weights for policy 1, policy_version 22060 (0.0008) -[2023-11-28 00:47:26,530][87424] Updated weights for policy 0, policy_version 22176 (0.0011) -[2023-11-28 00:47:26,787][87426] Updated weights for policy 1, policy_version 22070 (0.0007) -[2023-11-28 00:47:27,174][87426] Updated weights for policy 1, policy_version 22080 (0.0009) -[2023-11-28 00:47:28,434][87424] Updated weights for policy 0, policy_version 22186 (0.0012) -[2023-11-28 00:47:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 11329536. Throughput: 0: 2702.0, 1: 2737.9. Samples: 11347412. Policy #0 lag: (min: 31.0, avg: 31.0, max: 33.0) -[2023-11-28 00:47:28,445][86177] Avg episode reward: [(0, '-546.940'), (1, '-541.940')] -[2023-11-28 00:47:28,821][87424] Updated weights for policy 0, policy_version 22196 (0.0011) -[2023-11-28 00:47:28,899][87426] Updated weights for policy 1, policy_version 22090 (0.0008) -[2023-11-28 00:47:29,209][87424] Updated weights for policy 0, policy_version 22206 (0.0012) -[2023-11-28 00:47:29,267][87426] Updated weights for policy 1, policy_version 22100 (0.0011) -[2023-11-28 00:47:29,644][87426] Updated weights for policy 1, policy_version 22110 (0.0012) -[2023-11-28 00:47:30,934][87424] Updated weights for policy 0, policy_version 22216 (0.0011) -[2023-11-28 00:47:31,328][87424] Updated weights for policy 0, policy_version 22226 (0.0012) -[2023-11-28 00:47:31,704][87424] Updated weights for policy 0, policy_version 22236 (0.0011) -[2023-11-28 00:47:31,751][87426] Updated weights for policy 1, policy_version 22120 (0.0011) -[2023-11-28 00:47:32,132][87426] Updated weights for policy 1, policy_version 22130 (0.0009) -[2023-11-28 00:47:32,511][87426] Updated weights for policy 1, policy_version 22140 (0.0009) -[2023-11-28 00:47:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 11362304. Throughput: 0: 2719.3, 1: 2736.1. Samples: 11372896. Policy #0 lag: (min: 31.0, avg: 53.5, max: 95.0) -[2023-11-28 00:47:33,445][86177] Avg episode reward: [(0, '-541.810'), (1, '-541.990')] -[2023-11-28 00:47:34,035][87424] Updated weights for policy 0, policy_version 22246 (0.0010) -[2023-11-28 00:47:34,436][87424] Updated weights for policy 0, policy_version 22256 (0.0011) -[2023-11-28 00:47:34,766][87426] Updated weights for policy 1, policy_version 22150 (0.0008) -[2023-11-28 00:47:34,809][87424] Updated weights for policy 0, policy_version 22266 (0.0011) -[2023-11-28 00:47:35,138][87426] Updated weights for policy 1, policy_version 22160 (0.0009) -[2023-11-28 00:47:35,521][87426] Updated weights for policy 1, policy_version 22170 (0.0009) -[2023-11-28 00:47:37,205][87424] Updated weights for policy 0, policy_version 22276 (0.0009) -[2023-11-28 00:47:37,583][87424] Updated weights for policy 0, policy_version 22286 (0.0010) -[2023-11-28 00:47:37,685][87426] Updated weights for policy 1, policy_version 22180 (0.0008) -[2023-11-28 00:47:37,971][87424] Updated weights for policy 0, policy_version 22296 (0.0011) -[2023-11-28 00:47:38,064][87426] Updated weights for policy 1, policy_version 22190 (0.0007) -[2023-11-28 00:47:38,441][87426] Updated weights for policy 1, policy_version 22200 (0.0007) -[2023-11-28 00:47:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 11386880. Throughput: 0: 2691.2, 1: 2724.3. Samples: 11404336. Policy #0 lag: (min: 31.0, avg: 53.5, max: 95.0) -[2023-11-28 00:47:38,445][86177] Avg episode reward: [(0, '-534.140'), (1, '-545.240')] -[2023-11-28 00:47:40,243][87424] Updated weights for policy 0, policy_version 22306 (0.0011) -[2023-11-28 00:47:40,621][87424] Updated weights for policy 0, policy_version 22316 (0.0011) -[2023-11-28 00:47:40,770][87426] Updated weights for policy 1, policy_version 22210 (0.0008) -[2023-11-28 00:47:41,009][87424] Updated weights for policy 0, policy_version 22326 (0.0008) -[2023-11-28 00:47:41,139][87426] Updated weights for policy 1, policy_version 22220 (0.0011) -[2023-11-28 00:47:41,399][87424] Updated weights for policy 0, policy_version 22336 (0.0007) -[2023-11-28 00:47:41,519][87426] Updated weights for policy 1, policy_version 22230 (0.0012) -[2023-11-28 00:47:41,901][87426] Updated weights for policy 1, policy_version 22240 (0.0011) -[2023-11-28 00:47:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 11411456. Throughput: 0: 2707.9, 1: 2707.7. Samples: 11428244. Policy #0 lag: (min: 31.0, avg: 53.5, max: 95.0) -[2023-11-28 00:47:43,445][86177] Avg episode reward: [(0, '-516.570'), (1, '-540.080')] -[2023-11-28 00:47:43,863][87424] Updated weights for policy 0, policy_version 22346 (0.0008) -[2023-11-28 00:47:44,245][87424] Updated weights for policy 0, policy_version 22356 (0.0009) -[2023-11-28 00:47:44,279][87426] Updated weights for policy 1, policy_version 22250 (0.0009) -[2023-11-28 00:47:44,630][87424] Updated weights for policy 0, policy_version 22366 (0.0007) -[2023-11-28 00:47:44,664][87426] Updated weights for policy 1, policy_version 22260 (0.0007) -[2023-11-28 00:47:45,040][87426] Updated weights for policy 1, policy_version 22270 (0.0011) -[2023-11-28 00:47:46,309][87424] Updated weights for policy 0, policy_version 22376 (0.0008) -[2023-11-28 00:47:46,694][87424] Updated weights for policy 0, policy_version 22386 (0.0007) -[2023-11-28 00:47:46,803][87426] Updated weights for policy 1, policy_version 22280 (0.0012) -[2023-11-28 00:47:47,078][87424] Updated weights for policy 0, policy_version 22396 (0.0008) -[2023-11-28 00:47:47,183][87426] Updated weights for policy 1, policy_version 22290 (0.0011) -[2023-11-28 00:47:47,567][87426] Updated weights for policy 1, policy_version 22300 (0.0012) -[2023-11-28 00:47:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 11444224. Throughput: 0: 2710.7, 1: 2708.0. Samples: 11453184. Policy #0 lag: (min: 28.0, avg: 49.1, max: 55.0) -[2023-11-28 00:47:48,445][86177] Avg episode reward: [(0, '-514.070'), (1, '-542.840')] -[2023-11-28 00:47:48,914][87424] Updated weights for policy 0, policy_version 22406 (0.0008) -[2023-11-28 00:47:49,303][87424] Updated weights for policy 0, policy_version 22416 (0.0009) -[2023-11-28 00:47:49,689][87424] Updated weights for policy 0, policy_version 22426 (0.0011) -[2023-11-28 00:47:49,789][87426] Updated weights for policy 1, policy_version 22310 (0.0012) -[2023-11-28 00:47:50,167][87426] Updated weights for policy 1, policy_version 22320 (0.0012) -[2023-11-28 00:47:50,552][87426] Updated weights for policy 1, policy_version 22330 (0.0011) -[2023-11-28 00:47:51,641][87424] Updated weights for policy 0, policy_version 22436 (0.0014) -[2023-11-28 00:47:52,024][87424] Updated weights for policy 0, policy_version 22446 (0.0012) -[2023-11-28 00:47:52,404][87424] Updated weights for policy 0, policy_version 22456 (0.0012) -[2023-11-28 00:47:52,705][87426] Updated weights for policy 1, policy_version 22340 (0.0011) -[2023-11-28 00:47:53,082][87426] Updated weights for policy 1, policy_version 22350 (0.0009) -[2023-11-28 00:47:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 11468800. Throughput: 0: 2740.8, 1: 2714.7. Samples: 11486712. Policy #0 lag: (min: 28.0, avg: 49.1, max: 55.0) -[2023-11-28 00:47:53,445][86177] Avg episode reward: [(0, '-571.960'), (1, '-554.260')] -[2023-11-28 00:47:53,464][87426] Updated weights for policy 1, policy_version 22360 (0.0011) -[2023-11-28 00:47:54,573][87424] Updated weights for policy 0, policy_version 22466 (0.0011) -[2023-11-28 00:47:54,957][87424] Updated weights for policy 0, policy_version 22476 (0.0012) -[2023-11-28 00:47:55,339][87424] Updated weights for policy 0, policy_version 22486 (0.0012) -[2023-11-28 00:47:55,564][87426] Updated weights for policy 1, policy_version 22370 (0.0010) -[2023-11-28 00:47:55,728][87424] Updated weights for policy 0, policy_version 22496 (0.0011) -[2023-11-28 00:47:55,936][87426] Updated weights for policy 1, policy_version 22380 (0.0011) -[2023-11-28 00:47:56,318][87426] Updated weights for policy 1, policy_version 22390 (0.0012) -[2023-11-28 00:47:56,698][87426] Updated weights for policy 1, policy_version 22400 (0.0012) -[2023-11-28 00:47:57,729][87424] Updated weights for policy 0, policy_version 22506 (0.0011) -[2023-11-28 00:47:58,117][87424] Updated weights for policy 0, policy_version 22516 (0.0011) -[2023-11-28 00:47:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 11493376. Throughput: 0: 2719.8, 1: 2757.5. Samples: 11512268. Policy #0 lag: (min: 28.0, avg: 49.1, max: 55.0) -[2023-11-28 00:47:58,445][86177] Avg episode reward: [(0, '-568.180'), (1, '-554.850')] -[2023-11-28 00:47:58,499][87424] Updated weights for policy 0, policy_version 22526 (0.0011) -[2023-11-28 00:47:59,174][87426] Updated weights for policy 1, policy_version 22410 (0.0008) -[2023-11-28 00:47:59,561][87426] Updated weights for policy 1, policy_version 22420 (0.0007) -[2023-11-28 00:47:59,928][87426] Updated weights for policy 1, policy_version 22430 (0.0010) -[2023-11-28 00:48:00,726][87424] Updated weights for policy 0, policy_version 22536 (0.0012) -[2023-11-28 00:48:01,117][87424] Updated weights for policy 0, policy_version 22546 (0.0013) -[2023-11-28 00:48:01,508][87424] Updated weights for policy 0, policy_version 22556 (0.0011) -[2023-11-28 00:48:01,647][87426] Updated weights for policy 1, policy_version 22440 (0.0009) -[2023-11-28 00:48:02,022][87426] Updated weights for policy 1, policy_version 22450 (0.0010) -[2023-11-28 00:48:02,406][87426] Updated weights for policy 1, policy_version 22460 (0.0009) -[2023-11-28 00:48:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 11526144. Throughput: 0: 2753.5, 1: 2792.8. Samples: 11538388. Policy #0 lag: (min: 28.0, avg: 49.1, max: 55.0) -[2023-11-28 00:48:03,445][86177] Avg episode reward: [(0, '-601.250'), (1, '-542.070')] -[2023-11-28 00:48:03,590][87424] Updated weights for policy 0, policy_version 22566 (0.0011) -[2023-11-28 00:48:03,974][87424] Updated weights for policy 0, policy_version 22576 (0.0012) -[2023-11-28 00:48:04,372][87424] Updated weights for policy 0, policy_version 22586 (0.0012) -[2023-11-28 00:48:04,836][87426] Updated weights for policy 1, policy_version 22470 (0.0010) -[2023-11-28 00:48:05,221][87426] Updated weights for policy 1, policy_version 22480 (0.0008) -[2023-11-28 00:48:05,603][87426] Updated weights for policy 1, policy_version 22490 (0.0011) -[2023-11-28 00:48:06,358][87424] Updated weights for policy 0, policy_version 22596 (0.0012) -[2023-11-28 00:48:06,741][87424] Updated weights for policy 0, policy_version 22606 (0.0011) -[2023-11-28 00:48:07,125][87424] Updated weights for policy 0, policy_version 22616 (0.0012) -[2023-11-28 00:48:08,047][87426] Updated weights for policy 1, policy_version 22500 (0.0010) -[2023-11-28 00:48:08,427][87426] Updated weights for policy 1, policy_version 22510 (0.0012) -[2023-11-28 00:48:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 11550720. Throughput: 0: 2753.3, 1: 2777.5. Samples: 11570564. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 00:48:08,445][86177] Avg episode reward: [(0, '-599.810'), (1, '-540.860')] -[2023-11-28 00:48:08,801][87426] Updated weights for policy 1, policy_version 22520 (0.0012) -[2023-11-28 00:48:09,002][87424] Updated weights for policy 0, policy_version 22626 (0.0011) -[2023-11-28 00:48:09,386][87424] Updated weights for policy 0, policy_version 22636 (0.0011) -[2023-11-28 00:48:09,771][87424] Updated weights for policy 0, policy_version 22646 (0.0011) -[2023-11-28 00:48:10,155][87424] Updated weights for policy 0, policy_version 22656 (0.0012) -[2023-11-28 00:48:11,013][87426] Updated weights for policy 1, policy_version 22530 (0.0012) -[2023-11-28 00:48:11,397][87426] Updated weights for policy 1, policy_version 22540 (0.0007) -[2023-11-28 00:48:11,772][87426] Updated weights for policy 1, policy_version 22550 (0.0009) -[2023-11-28 00:48:12,157][87426] Updated weights for policy 1, policy_version 22560 (0.0011) -[2023-11-28 00:48:12,425][87424] Updated weights for policy 0, policy_version 22666 (0.0012) -[2023-11-28 00:48:12,810][87424] Updated weights for policy 0, policy_version 22676 (0.0010) -[2023-11-28 00:48:13,185][87424] Updated weights for policy 0, policy_version 22686 (0.0010) -[2023-11-28 00:48:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 11583488. Throughput: 0: 2780.0, 1: 2735.3. Samples: 11595600. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 00:48:13,445][86177] Avg episode reward: [(0, '-557.740'), (1, '-536.340')] -[2023-11-28 00:48:14,280][87426] Updated weights for policy 1, policy_version 22570 (0.0011) -[2023-11-28 00:48:14,679][87426] Updated weights for policy 1, policy_version 22580 (0.0010) -[2023-11-28 00:48:15,062][87426] Updated weights for policy 1, policy_version 22590 (0.0011) -[2023-11-28 00:48:15,695][87424] Updated weights for policy 0, policy_version 22696 (0.0011) -[2023-11-28 00:48:16,074][87424] Updated weights for policy 0, policy_version 22706 (0.0012) -[2023-11-28 00:48:16,462][87424] Updated weights for policy 0, policy_version 22716 (0.0012) -[2023-11-28 00:48:16,823][87426] Updated weights for policy 1, policy_version 22600 (0.0007) -[2023-11-28 00:48:17,206][87426] Updated weights for policy 1, policy_version 22610 (0.0007) -[2023-11-28 00:48:17,589][87426] Updated weights for policy 1, policy_version 22620 (0.0009) -[2023-11-28 00:48:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 11608064. Throughput: 0: 2743.6, 1: 2734.9. Samples: 11619428. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 00:48:18,445][86177] Avg episode reward: [(0, '-542.640'), (1, '-568.190')] -[2023-11-28 00:48:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000022624_5791744.pth... -[2023-11-28 00:48:18,485][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000020096_5144576.pth -[2023-11-28 00:48:18,558][87424] Updated weights for policy 0, policy_version 22726 (0.0010) -[2023-11-28 00:48:18,946][87424] Updated weights for policy 0, policy_version 22736 (0.0009) -[2023-11-28 00:48:19,321][87424] Updated weights for policy 0, policy_version 22746 (0.0010) -[2023-11-28 00:48:19,375][87426] Updated weights for policy 1, policy_version 22630 (0.0011) -[2023-11-28 00:48:19,549][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000022752_5824512.pth... -[2023-11-28 00:48:19,581][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000020192_5169152.pth -[2023-11-28 00:48:19,751][87426] Updated weights for policy 1, policy_version 22640 (0.0011) -[2023-11-28 00:48:20,139][87426] Updated weights for policy 1, policy_version 22650 (0.0010) -[2023-11-28 00:48:21,475][87424] Updated weights for policy 0, policy_version 22756 (0.0009) -[2023-11-28 00:48:21,869][87424] Updated weights for policy 0, policy_version 22766 (0.0012) -[2023-11-28 00:48:22,242][87424] Updated weights for policy 0, policy_version 22776 (0.0011) -[2023-11-28 00:48:22,534][87426] Updated weights for policy 1, policy_version 22660 (0.0010) -[2023-11-28 00:48:22,910][87426] Updated weights for policy 1, policy_version 22670 (0.0011) -[2023-11-28 00:48:23,290][87426] Updated weights for policy 1, policy_version 22680 (0.0011) -[2023-11-28 00:48:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 11632640. Throughput: 0: 2766.5, 1: 2719.5. Samples: 11651204. Policy #0 lag: (min: 14.0, avg: 29.0, max: 46.0) -[2023-11-28 00:48:23,445][86177] Avg episode reward: [(0, '-530.160'), (1, '-583.110')] -[2023-11-28 00:48:24,206][87424] Updated weights for policy 0, policy_version 22786 (0.0010) -[2023-11-28 00:48:24,592][87424] Updated weights for policy 0, policy_version 22796 (0.0007) -[2023-11-28 00:48:24,998][87424] Updated weights for policy 0, policy_version 22806 (0.0007) -[2023-11-28 00:48:25,378][87424] Updated weights for policy 0, policy_version 22816 (0.0007) -[2023-11-28 00:48:25,850][87426] Updated weights for policy 1, policy_version 22690 (0.0012) -[2023-11-28 00:48:26,228][87426] Updated weights for policy 1, policy_version 22700 (0.0012) -[2023-11-28 00:48:26,615][87426] Updated weights for policy 1, policy_version 22710 (0.0008) -[2023-11-28 00:48:26,991][87426] Updated weights for policy 1, policy_version 22720 (0.0008) -[2023-11-28 00:48:27,494][87424] Updated weights for policy 0, policy_version 22826 (0.0007) -[2023-11-28 00:48:27,877][87424] Updated weights for policy 0, policy_version 22836 (0.0007) -[2023-11-28 00:48:28,261][87424] Updated weights for policy 0, policy_version 22846 (0.0007) -[2023-11-28 00:48:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 11665408. Throughput: 0: 2784.8, 1: 2714.1. Samples: 11675692. Policy #0 lag: (min: 14.0, avg: 29.0, max: 46.0) -[2023-11-28 00:48:28,445][86177] Avg episode reward: [(0, '-528.080'), (1, '-589.180')] -[2023-11-28 00:48:29,372][87426] Updated weights for policy 1, policy_version 22730 (0.0011) -[2023-11-28 00:48:29,748][87426] Updated weights for policy 1, policy_version 22740 (0.0010) -[2023-11-28 00:48:30,136][87426] Updated weights for policy 1, policy_version 22750 (0.0010) -[2023-11-28 00:48:30,314][87424] Updated weights for policy 0, policy_version 22856 (0.0010) -[2023-11-28 00:48:30,702][87424] Updated weights for policy 0, policy_version 22866 (0.0012) -[2023-11-28 00:48:31,083][87424] Updated weights for policy 0, policy_version 22876 (0.0010) -[2023-11-28 00:48:31,982][87426] Updated weights for policy 1, policy_version 22760 (0.0011) -[2023-11-28 00:48:32,361][87426] Updated weights for policy 1, policy_version 22770 (0.0012) -[2023-11-28 00:48:32,739][87426] Updated weights for policy 1, policy_version 22780 (0.0012) -[2023-11-28 00:48:33,323][87424] Updated weights for policy 0, policy_version 22886 (0.0010) -[2023-11-28 00:48:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 11689984. Throughput: 0: 2798.1, 1: 2703.7. Samples: 11700764. Policy #0 lag: (min: 14.0, avg: 29.0, max: 46.0) -[2023-11-28 00:48:33,445][86177] Avg episode reward: [(0, '-530.660'), (1, '-584.810')] -[2023-11-28 00:48:33,703][87424] Updated weights for policy 0, policy_version 22896 (0.0012) -[2023-11-28 00:48:34,095][87424] Updated weights for policy 0, policy_version 22906 (0.0011) -[2023-11-28 00:48:35,326][87426] Updated weights for policy 1, policy_version 22790 (0.0011) -[2023-11-28 00:48:35,714][87426] Updated weights for policy 1, policy_version 22800 (0.0012) -[2023-11-28 00:48:35,755][87424] Updated weights for policy 0, policy_version 22916 (0.0011) -[2023-11-28 00:48:36,094][87426] Updated weights for policy 1, policy_version 22810 (0.0011) -[2023-11-28 00:48:36,146][87424] Updated weights for policy 0, policy_version 22926 (0.0009) -[2023-11-28 00:48:36,527][87424] Updated weights for policy 0, policy_version 22936 (0.0008) -[2023-11-28 00:48:38,432][87424] Updated weights for policy 0, policy_version 22946 (0.0009) -[2023-11-28 00:48:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 11714560. Throughput: 0: 2783.8, 1: 2689.6. Samples: 11733016. Policy #0 lag: (min: 14.0, avg: 29.0, max: 46.0) -[2023-11-28 00:48:38,445][86177] Avg episode reward: [(0, '-531.480'), (1, '-586.940')] -[2023-11-28 00:48:38,567][87426] Updated weights for policy 1, policy_version 22820 (0.0011) -[2023-11-28 00:48:38,822][87424] Updated weights for policy 0, policy_version 22956 (0.0012) -[2023-11-28 00:48:38,940][87426] Updated weights for policy 1, policy_version 22830 (0.0012) -[2023-11-28 00:48:39,198][87424] Updated weights for policy 0, policy_version 22966 (0.0011) -[2023-11-28 00:48:39,313][87426] Updated weights for policy 1, policy_version 22840 (0.0012) -[2023-11-28 00:48:39,590][87424] Updated weights for policy 0, policy_version 22976 (0.0010) -[2023-11-28 00:48:41,374][87426] Updated weights for policy 1, policy_version 22850 (0.0011) -[2023-11-28 00:48:41,748][87426] Updated weights for policy 1, policy_version 22860 (0.0010) -[2023-11-28 00:48:42,052][87424] Updated weights for policy 0, policy_version 22986 (0.0009) -[2023-11-28 00:48:42,118][87426] Updated weights for policy 1, policy_version 22870 (0.0012) -[2023-11-28 00:48:42,435][87424] Updated weights for policy 0, policy_version 22996 (0.0011) -[2023-11-28 00:48:42,501][87426] Updated weights for policy 1, policy_version 22880 (0.0012) -[2023-11-28 00:48:42,818][87424] Updated weights for policy 0, policy_version 23006 (0.0011) -[2023-11-28 00:48:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 11747328. Throughput: 0: 2780.7, 1: 2655.0. Samples: 11756876. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 00:48:43,445][86177] Avg episode reward: [(0, '-535.750'), (1, '-535.400')] -[2023-11-28 00:48:44,806][87426] Updated weights for policy 1, policy_version 22890 (0.0010) -[2023-11-28 00:48:44,895][87424] Updated weights for policy 0, policy_version 23016 (0.0009) -[2023-11-28 00:48:45,201][87426] Updated weights for policy 1, policy_version 22900 (0.0008) -[2023-11-28 00:48:45,278][87424] Updated weights for policy 0, policy_version 23026 (0.0012) -[2023-11-28 00:48:45,581][87426] Updated weights for policy 1, policy_version 22910 (0.0011) -[2023-11-28 00:48:45,659][87424] Updated weights for policy 0, policy_version 23036 (0.0010) -[2023-11-28 00:48:47,840][87424] Updated weights for policy 0, policy_version 23046 (0.0009) -[2023-11-28 00:48:48,028][87426] Updated weights for policy 1, policy_version 22920 (0.0011) -[2023-11-28 00:48:48,225][87424] Updated weights for policy 0, policy_version 23056 (0.0009) -[2023-11-28 00:48:48,403][87426] Updated weights for policy 1, policy_version 22930 (0.0012) -[2023-11-28 00:48:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 11763712. Throughput: 0: 2757.8, 1: 2637.0. Samples: 11781152. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 00:48:48,445][86177] Avg episode reward: [(0, '-541.140'), (1, '-537.200')] -[2023-11-28 00:48:48,613][87424] Updated weights for policy 0, policy_version 23066 (0.0011) -[2023-11-28 00:48:48,784][87426] Updated weights for policy 1, policy_version 22940 (0.0010) -[2023-11-28 00:48:50,828][87426] Updated weights for policy 1, policy_version 22950 (0.0011) -[2023-11-28 00:48:50,846][87424] Updated weights for policy 0, policy_version 23076 (0.0010) -[2023-11-28 00:48:51,213][87426] Updated weights for policy 1, policy_version 22960 (0.0009) -[2023-11-28 00:48:51,227][87424] Updated weights for policy 0, policy_version 23086 (0.0009) -[2023-11-28 00:48:51,599][87426] Updated weights for policy 1, policy_version 22970 (0.0008) -[2023-11-28 00:48:51,611][87424] Updated weights for policy 0, policy_version 23096 (0.0011) -[2023-11-28 00:48:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 11796480. Throughput: 0: 2747.0, 1: 2634.1. Samples: 11812716. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 00:48:53,445][86177] Avg episode reward: [(0, '-562.510'), (1, '-546.220')] -[2023-11-28 00:48:53,461][87424] Updated weights for policy 0, policy_version 23106 (0.0011) -[2023-11-28 00:48:53,836][87426] Updated weights for policy 1, policy_version 22980 (0.0010) -[2023-11-28 00:48:53,840][87424] Updated weights for policy 0, policy_version 23116 (0.0011) -[2023-11-28 00:48:54,217][87426] Updated weights for policy 1, policy_version 22990 (0.0011) -[2023-11-28 00:48:54,230][87424] Updated weights for policy 0, policy_version 23126 (0.0008) -[2023-11-28 00:48:54,598][87426] Updated weights for policy 1, policy_version 23000 (0.0011) -[2023-11-28 00:48:54,602][87424] Updated weights for policy 0, policy_version 23136 (0.0007) -[2023-11-28 00:48:57,043][87426] Updated weights for policy 1, policy_version 23010 (0.0008) -[2023-11-28 00:48:57,189][87424] Updated weights for policy 0, policy_version 23146 (0.0011) -[2023-11-28 00:48:57,411][87426] Updated weights for policy 1, policy_version 23020 (0.0009) -[2023-11-28 00:48:57,576][87424] Updated weights for policy 0, policy_version 23156 (0.0011) -[2023-11-28 00:48:57,799][87426] Updated weights for policy 1, policy_version 23030 (0.0007) -[2023-11-28 00:48:57,952][87424] Updated weights for policy 0, policy_version 23166 (0.0012) -[2023-11-28 00:48:58,173][87426] Updated weights for policy 1, policy_version 23040 (0.0008) -[2023-11-28 00:48:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 11829248. Throughput: 0: 2742.7, 1: 2636.3. Samples: 11837652. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 00:48:58,445][86177] Avg episode reward: [(0, '-586.320'), (1, '-541.390')] -[2023-11-28 00:49:00,228][87424] Updated weights for policy 0, policy_version 23176 (0.0011) -[2023-11-28 00:49:00,336][87426] Updated weights for policy 1, policy_version 23050 (0.0008) -[2023-11-28 00:49:00,611][87424] Updated weights for policy 0, policy_version 23186 (0.0010) -[2023-11-28 00:49:00,725][87426] Updated weights for policy 1, policy_version 23060 (0.0008) -[2023-11-28 00:49:00,992][87424] Updated weights for policy 0, policy_version 23196 (0.0011) -[2023-11-28 00:49:01,102][87426] Updated weights for policy 1, policy_version 23070 (0.0008) -[2023-11-28 00:49:03,171][87424] Updated weights for policy 0, policy_version 23206 (0.0011) -[2023-11-28 00:49:03,285][87426] Updated weights for policy 1, policy_version 23080 (0.0010) -[2023-11-28 00:49:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 11845632. Throughput: 0: 2764.5, 1: 2631.7. Samples: 11862260. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 00:49:03,445][86177] Avg episode reward: [(0, '-592.300'), (1, '-557.220')] -[2023-11-28 00:49:03,555][87424] Updated weights for policy 0, policy_version 23216 (0.0010) -[2023-11-28 00:49:03,657][87426] Updated weights for policy 1, policy_version 23090 (0.0008) -[2023-11-28 00:49:03,939][87424] Updated weights for policy 0, policy_version 23226 (0.0008) -[2023-11-28 00:49:04,039][87426] Updated weights for policy 1, policy_version 23100 (0.0008) -[2023-11-28 00:49:06,419][87424] Updated weights for policy 0, policy_version 23236 (0.0008) -[2023-11-28 00:49:06,485][87426] Updated weights for policy 1, policy_version 23110 (0.0010) -[2023-11-28 00:49:06,798][87424] Updated weights for policy 0, policy_version 23246 (0.0010) -[2023-11-28 00:49:06,859][87426] Updated weights for policy 1, policy_version 23120 (0.0011) -[2023-11-28 00:49:07,179][87424] Updated weights for policy 0, policy_version 23256 (0.0007) -[2023-11-28 00:49:07,244][87426] Updated weights for policy 1, policy_version 23130 (0.0012) -[2023-11-28 00:49:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 11878400. Throughput: 0: 2756.0, 1: 2639.7. Samples: 11894008. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 00:49:08,445][86177] Avg episode reward: [(0, '-594.840'), (1, '-560.750')] -[2023-11-28 00:49:08,934][87426] Updated weights for policy 1, policy_version 23140 (0.0010) -[2023-11-28 00:49:09,050][87424] Updated weights for policy 0, policy_version 23266 (0.0011) -[2023-11-28 00:49:09,307][87426] Updated weights for policy 1, policy_version 23150 (0.0012) -[2023-11-28 00:49:09,439][87424] Updated weights for policy 0, policy_version 23276 (0.0010) -[2023-11-28 00:49:09,685][87426] Updated weights for policy 1, policy_version 23160 (0.0011) -[2023-11-28 00:49:09,826][87424] Updated weights for policy 0, policy_version 23286 (0.0012) -[2023-11-28 00:49:10,201][87424] Updated weights for policy 0, policy_version 23296 (0.0011) -[2023-11-28 00:49:12,267][87426] Updated weights for policy 1, policy_version 23170 (0.0011) -[2023-11-28 00:49:12,646][87426] Updated weights for policy 1, policy_version 23180 (0.0010) -[2023-11-28 00:49:12,673][87424] Updated weights for policy 0, policy_version 23306 (0.0012) -[2023-11-28 00:49:13,023][87426] Updated weights for policy 1, policy_version 23190 (0.0011) -[2023-11-28 00:49:13,050][87424] Updated weights for policy 0, policy_version 23316 (0.0011) -[2023-11-28 00:49:13,400][87426] Updated weights for policy 1, policy_version 23200 (0.0009) -[2023-11-28 00:49:13,437][87424] Updated weights for policy 0, policy_version 23326 (0.0012) -[2023-11-28 00:49:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 11902976. Throughput: 0: 2745.0, 1: 2680.2. Samples: 11919824. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 00:49:13,445][86177] Avg episode reward: [(0, '-584.870'), (1, '-544.730')] -[2023-11-28 00:49:15,201][87424] Updated weights for policy 0, policy_version 23336 (0.0011) -[2023-11-28 00:49:15,342][87426] Updated weights for policy 1, policy_version 23210 (0.0008) -[2023-11-28 00:49:15,592][87424] Updated weights for policy 0, policy_version 23346 (0.0011) -[2023-11-28 00:49:15,732][87426] Updated weights for policy 1, policy_version 23220 (0.0010) -[2023-11-28 00:49:15,971][87424] Updated weights for policy 0, policy_version 23356 (0.0010) -[2023-11-28 00:49:16,101][87426] Updated weights for policy 1, policy_version 23230 (0.0011) -[2023-11-28 00:49:17,976][87426] Updated weights for policy 1, policy_version 23240 (0.0011) -[2023-11-28 00:49:18,012][87424] Updated weights for policy 0, policy_version 23366 (0.0007) -[2023-11-28 00:49:18,358][87426] Updated weights for policy 1, policy_version 23250 (0.0012) -[2023-11-28 00:49:18,394][87424] Updated weights for policy 0, policy_version 23376 (0.0008) -[2023-11-28 00:49:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 11927552. Throughput: 0: 2734.1, 1: 2676.9. Samples: 11944260. Policy #0 lag: (min: 31.0, avg: 48.4, max: 63.0) -[2023-11-28 00:49:18,445][86177] Avg episode reward: [(0, '-571.190'), (1, '-555.840')] -[2023-11-28 00:49:18,729][87426] Updated weights for policy 1, policy_version 23260 (0.0009) -[2023-11-28 00:49:18,782][87424] Updated weights for policy 0, policy_version 23386 (0.0011) -[2023-11-28 00:49:20,747][87426] Updated weights for policy 1, policy_version 23270 (0.0010) -[2023-11-28 00:49:20,902][87424] Updated weights for policy 0, policy_version 23396 (0.0012) -[2023-11-28 00:49:21,123][87426] Updated weights for policy 1, policy_version 23280 (0.0012) -[2023-11-28 00:49:21,285][87424] Updated weights for policy 0, policy_version 23406 (0.0012) -[2023-11-28 00:49:21,513][87426] Updated weights for policy 1, policy_version 23290 (0.0008) -[2023-11-28 00:49:21,665][87424] Updated weights for policy 0, policy_version 23416 (0.0009) -[2023-11-28 00:49:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 11960320. Throughput: 0: 2729.9, 1: 2689.8. Samples: 11976900. Policy #0 lag: (min: 31.0, avg: 48.4, max: 63.0) -[2023-11-28 00:49:23,445][86177] Avg episode reward: [(0, '-553.690'), (1, '-547.420')] -[2023-11-28 00:49:23,740][87426] Updated weights for policy 1, policy_version 23300 (0.0009) -[2023-11-28 00:49:24,132][87426] Updated weights for policy 1, policy_version 23310 (0.0010) -[2023-11-28 00:49:24,136][87424] Updated weights for policy 0, policy_version 23426 (0.0010) -[2023-11-28 00:49:24,510][87426] Updated weights for policy 1, policy_version 23320 (0.0007) -[2023-11-28 00:49:24,520][87424] Updated weights for policy 0, policy_version 23436 (0.0007) -[2023-11-28 00:49:24,900][87424] Updated weights for policy 0, policy_version 23446 (0.0008) -[2023-11-28 00:49:25,284][87424] Updated weights for policy 0, policy_version 23456 (0.0009) -[2023-11-28 00:49:27,020][87426] Updated weights for policy 1, policy_version 23330 (0.0007) -[2023-11-28 00:49:27,393][87426] Updated weights for policy 1, policy_version 23340 (0.0007) -[2023-11-28 00:49:27,590][87424] Updated weights for policy 0, policy_version 23466 (0.0007) -[2023-11-28 00:49:27,768][87426] Updated weights for policy 1, policy_version 23350 (0.0009) -[2023-11-28 00:49:27,974][87424] Updated weights for policy 0, policy_version 23476 (0.0007) -[2023-11-28 00:49:28,149][87426] Updated weights for policy 1, policy_version 23360 (0.0008) -[2023-11-28 00:49:28,356][87424] Updated weights for policy 0, policy_version 23486 (0.0008) -[2023-11-28 00:49:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 11993088. Throughput: 0: 2736.2, 1: 2702.2. Samples: 12001604. Policy #0 lag: (min: 31.0, avg: 48.4, max: 63.0) -[2023-11-28 00:49:28,445][86177] Avg episode reward: [(0, '-552.940'), (1, '-561.880')] -[2023-11-28 00:49:30,304][87424] Updated weights for policy 0, policy_version 23496 (0.0010) -[2023-11-28 00:49:30,570][87426] Updated weights for policy 1, policy_version 23370 (0.0008) -[2023-11-28 00:49:30,676][87424] Updated weights for policy 0, policy_version 23506 (0.0011) -[2023-11-28 00:49:30,956][87426] Updated weights for policy 1, policy_version 23380 (0.0008) -[2023-11-28 00:49:31,061][87424] Updated weights for policy 0, policy_version 23516 (0.0011) -[2023-11-28 00:49:31,342][87426] Updated weights for policy 1, policy_version 23390 (0.0007) -[2023-11-28 00:49:33,232][87424] Updated weights for policy 0, policy_version 23526 (0.0010) -[2023-11-28 00:49:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 12009472. Throughput: 0: 2732.9, 1: 2695.4. Samples: 12025424. Policy #0 lag: (min: 31.0, avg: 48.4, max: 63.0) -[2023-11-28 00:49:33,445][86177] Avg episode reward: [(0, '-547.580'), (1, '-551.720')] -[2023-11-28 00:49:33,618][87424] Updated weights for policy 0, policy_version 23536 (0.0009) -[2023-11-28 00:49:33,838][87426] Updated weights for policy 1, policy_version 23400 (0.0007) -[2023-11-28 00:49:34,004][87424] Updated weights for policy 0, policy_version 23546 (0.0007) -[2023-11-28 00:49:34,214][87426] Updated weights for policy 1, policy_version 23410 (0.0009) -[2023-11-28 00:49:34,596][87426] Updated weights for policy 1, policy_version 23420 (0.0007) -[2023-11-28 00:49:36,058][87424] Updated weights for policy 0, policy_version 23556 (0.0008) -[2023-11-28 00:49:36,446][87424] Updated weights for policy 0, policy_version 23566 (0.0010) -[2023-11-28 00:49:36,670][87426] Updated weights for policy 1, policy_version 23430 (0.0008) -[2023-11-28 00:49:36,838][87424] Updated weights for policy 0, policy_version 23576 (0.0012) -[2023-11-28 00:49:37,044][87426] Updated weights for policy 1, policy_version 23440 (0.0007) -[2023-11-28 00:49:37,423][87426] Updated weights for policy 1, policy_version 23450 (0.0007) -[2023-11-28 00:49:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12042240. Throughput: 0: 2743.8, 1: 2703.8. Samples: 12057860. Policy #0 lag: (min: 1.0, avg: 33.8, max: 65.0) -[2023-11-28 00:49:38,445][86177] Avg episode reward: [(0, '-552.740'), (1, '-542.760')] -[2023-11-28 00:49:38,952][87424] Updated weights for policy 0, policy_version 23586 (0.0011) -[2023-11-28 00:49:39,338][87424] Updated weights for policy 0, policy_version 23596 (0.0009) -[2023-11-28 00:49:39,732][87424] Updated weights for policy 0, policy_version 23606 (0.0008) -[2023-11-28 00:49:39,844][87426] Updated weights for policy 1, policy_version 23460 (0.0009) -[2023-11-28 00:49:40,101][87424] Updated weights for policy 0, policy_version 23616 (0.0011) -[2023-11-28 00:49:40,215][87426] Updated weights for policy 1, policy_version 23470 (0.0009) -[2023-11-28 00:49:40,592][87426] Updated weights for policy 1, policy_version 23480 (0.0009) -[2023-11-28 00:49:42,296][87424] Updated weights for policy 0, policy_version 23626 (0.0011) -[2023-11-28 00:49:42,646][87426] Updated weights for policy 1, policy_version 23490 (0.0009) -[2023-11-28 00:49:42,682][87424] Updated weights for policy 0, policy_version 23636 (0.0009) -[2023-11-28 00:49:43,024][87426] Updated weights for policy 1, policy_version 23500 (0.0011) -[2023-11-28 00:49:43,074][87424] Updated weights for policy 0, policy_version 23646 (0.0009) -[2023-11-28 00:49:43,410][87426] Updated weights for policy 1, policy_version 23510 (0.0011) -[2023-11-28 00:49:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 12066816. Throughput: 0: 2728.4, 1: 2688.0. Samples: 12081392. Policy #0 lag: (min: 1.0, avg: 33.8, max: 65.0) -[2023-11-28 00:49:43,445][86177] Avg episode reward: [(0, '-538.690'), (1, '-539.850')] -[2023-11-28 00:49:43,790][87426] Updated weights for policy 1, policy_version 23520 (0.0012) -[2023-11-28 00:49:45,441][87424] Updated weights for policy 0, policy_version 23656 (0.0011) -[2023-11-28 00:49:45,824][87424] Updated weights for policy 0, policy_version 23666 (0.0011) -[2023-11-28 00:49:46,192][87426] Updated weights for policy 1, policy_version 23530 (0.0011) -[2023-11-28 00:49:46,210][87424] Updated weights for policy 0, policy_version 23676 (0.0011) -[2023-11-28 00:49:46,573][87426] Updated weights for policy 1, policy_version 23540 (0.0012) -[2023-11-28 00:49:46,935][87426] Updated weights for policy 1, policy_version 23550 (0.0012) -[2023-11-28 00:49:48,116][87424] Updated weights for policy 0, policy_version 23686 (0.0007) -[2023-11-28 00:49:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 12091392. Throughput: 0: 2717.6, 1: 2702.9. Samples: 12106184. Policy #0 lag: (min: 1.0, avg: 33.8, max: 65.0) -[2023-11-28 00:49:48,445][86177] Avg episode reward: [(0, '-528.920'), (1, '-527.310')] -[2023-11-28 00:49:48,501][87424] Updated weights for policy 0, policy_version 23696 (0.0008) -[2023-11-28 00:49:48,861][87426] Updated weights for policy 1, policy_version 23560 (0.0012) -[2023-11-28 00:49:48,896][87424] Updated weights for policy 0, policy_version 23706 (0.0008) -[2023-11-28 00:49:49,246][87426] Updated weights for policy 1, policy_version 23570 (0.0011) -[2023-11-28 00:49:49,628][87426] Updated weights for policy 1, policy_version 23580 (0.0012) -[2023-11-28 00:49:50,826][87424] Updated weights for policy 0, policy_version 23716 (0.0012) -[2023-11-28 00:49:51,214][87424] Updated weights for policy 0, policy_version 23726 (0.0012) -[2023-11-28 00:49:51,606][87424] Updated weights for policy 0, policy_version 23736 (0.0012) -[2023-11-28 00:49:52,078][87426] Updated weights for policy 1, policy_version 23590 (0.0012) -[2023-11-28 00:49:52,465][87426] Updated weights for policy 1, policy_version 23600 (0.0011) -[2023-11-28 00:49:52,833][87426] Updated weights for policy 1, policy_version 23610 (0.0012) -[2023-11-28 00:49:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12124160. Throughput: 0: 2718.0, 1: 2705.6. Samples: 12138072. Policy #0 lag: (min: 14.0, avg: 28.2, max: 46.0) -[2023-11-28 00:49:53,445][86177] Avg episode reward: [(0, '-526.670'), (1, '-527.420')] -[2023-11-28 00:49:54,112][87424] Updated weights for policy 0, policy_version 23746 (0.0011) -[2023-11-28 00:49:54,487][87424] Updated weights for policy 0, policy_version 23756 (0.0007) -[2023-11-28 00:49:54,882][87424] Updated weights for policy 0, policy_version 23766 (0.0007) -[2023-11-28 00:49:54,976][87426] Updated weights for policy 1, policy_version 23620 (0.0011) -[2023-11-28 00:49:55,269][87424] Updated weights for policy 0, policy_version 23776 (0.0008) -[2023-11-28 00:49:55,355][87426] Updated weights for policy 1, policy_version 23630 (0.0012) -[2023-11-28 00:49:55,722][87426] Updated weights for policy 1, policy_version 23640 (0.0011) -[2023-11-28 00:49:57,549][87426] Updated weights for policy 1, policy_version 23650 (0.0012) -[2023-11-28 00:49:57,615][87424] Updated weights for policy 0, policy_version 23786 (0.0009) -[2023-11-28 00:49:57,931][87426] Updated weights for policy 1, policy_version 23660 (0.0011) -[2023-11-28 00:49:57,998][87424] Updated weights for policy 0, policy_version 23796 (0.0008) -[2023-11-28 00:49:58,313][87426] Updated weights for policy 1, policy_version 23670 (0.0011) -[2023-11-28 00:49:58,385][87424] Updated weights for policy 0, policy_version 23806 (0.0010) -[2023-11-28 00:49:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 12140544. Throughput: 0: 2693.6, 1: 2682.7. Samples: 12161756. Policy #0 lag: (min: 14.0, avg: 28.2, max: 46.0) -[2023-11-28 00:49:58,445][86177] Avg episode reward: [(0, '-517.310'), (1, '-530.170')] -[2023-11-28 00:49:58,697][87426] Updated weights for policy 1, policy_version 23680 (0.0010) -[2023-11-28 00:50:00,667][87424] Updated weights for policy 0, policy_version 23816 (0.0010) -[2023-11-28 00:50:00,937][87426] Updated weights for policy 1, policy_version 23690 (0.0008) -[2023-11-28 00:50:01,049][87424] Updated weights for policy 0, policy_version 23826 (0.0008) -[2023-11-28 00:50:01,316][87426] Updated weights for policy 1, policy_version 23700 (0.0007) -[2023-11-28 00:50:01,435][87424] Updated weights for policy 0, policy_version 23836 (0.0007) -[2023-11-28 00:50:01,706][87426] Updated weights for policy 1, policy_version 23710 (0.0009) -[2023-11-28 00:50:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 12173312. Throughput: 0: 2678.8, 1: 2701.2. Samples: 12186360. Policy #0 lag: (min: 14.0, avg: 28.2, max: 46.0) -[2023-11-28 00:50:03,445][86177] Avg episode reward: [(0, '-518.200'), (1, '-558.510')] -[2023-11-28 00:50:03,841][87424] Updated weights for policy 0, policy_version 23846 (0.0009) -[2023-11-28 00:50:04,023][87426] Updated weights for policy 1, policy_version 23720 (0.0008) -[2023-11-28 00:50:04,236][87424] Updated weights for policy 0, policy_version 23856 (0.0012) -[2023-11-28 00:50:04,407][87426] Updated weights for policy 1, policy_version 23730 (0.0008) -[2023-11-28 00:50:04,606][87424] Updated weights for policy 0, policy_version 23866 (0.0009) -[2023-11-28 00:50:04,794][87426] Updated weights for policy 1, policy_version 23740 (0.0010) -[2023-11-28 00:50:06,583][87426] Updated weights for policy 1, policy_version 23750 (0.0011) -[2023-11-28 00:50:06,616][87424] Updated weights for policy 0, policy_version 23876 (0.0010) -[2023-11-28 00:50:06,965][87426] Updated weights for policy 1, policy_version 23760 (0.0008) -[2023-11-28 00:50:07,000][87424] Updated weights for policy 0, policy_version 23886 (0.0011) -[2023-11-28 00:50:07,349][87426] Updated weights for policy 1, policy_version 23770 (0.0011) -[2023-11-28 00:50:07,384][87424] Updated weights for policy 0, policy_version 23896 (0.0009) -[2023-11-28 00:50:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12206080. Throughput: 0: 2679.0, 1: 2683.5. Samples: 12218212. Policy #0 lag: (min: 14.0, avg: 28.2, max: 46.0) -[2023-11-28 00:50:08,445][86177] Avg episode reward: [(0, '-519.970'), (1, '-556.450')] -[2023-11-28 00:50:09,529][87424] Updated weights for policy 0, policy_version 23906 (0.0011) -[2023-11-28 00:50:09,579][87426] Updated weights for policy 1, policy_version 23780 (0.0011) -[2023-11-28 00:50:09,918][87424] Updated weights for policy 0, policy_version 23916 (0.0014) -[2023-11-28 00:50:09,963][87426] Updated weights for policy 1, policy_version 23790 (0.0011) -[2023-11-28 00:50:10,291][87424] Updated weights for policy 0, policy_version 23926 (0.0012) -[2023-11-28 00:50:10,345][87426] Updated weights for policy 1, policy_version 23800 (0.0011) -[2023-11-28 00:50:10,670][87424] Updated weights for policy 0, policy_version 23936 (0.0012) -[2023-11-28 00:50:12,922][87426] Updated weights for policy 1, policy_version 23810 (0.0012) -[2023-11-28 00:50:13,027][87424] Updated weights for policy 0, policy_version 23946 (0.0012) -[2023-11-28 00:50:13,304][87426] Updated weights for policy 1, policy_version 23820 (0.0010) -[2023-11-28 00:50:13,414][87424] Updated weights for policy 0, policy_version 23956 (0.0012) -[2023-11-28 00:50:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 12222464. Throughput: 0: 2673.2, 1: 2696.9. Samples: 12243260. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-11-28 00:50:13,445][86177] Avg episode reward: [(0, '-521.140'), (1, '-554.390')] -[2023-11-28 00:50:13,674][87426] Updated weights for policy 1, policy_version 23830 (0.0009) -[2023-11-28 00:50:13,797][87424] Updated weights for policy 0, policy_version 23966 (0.0010) -[2023-11-28 00:50:14,056][87426] Updated weights for policy 1, policy_version 23840 (0.0007) -[2023-11-28 00:50:15,838][87424] Updated weights for policy 0, policy_version 23976 (0.0011) -[2023-11-28 00:50:15,953][87426] Updated weights for policy 1, policy_version 23850 (0.0011) -[2023-11-28 00:50:16,218][87424] Updated weights for policy 0, policy_version 23986 (0.0010) -[2023-11-28 00:50:16,336][87426] Updated weights for policy 1, policy_version 23860 (0.0010) -[2023-11-28 00:50:16,608][87424] Updated weights for policy 0, policy_version 23996 (0.0008) -[2023-11-28 00:50:16,718][87426] Updated weights for policy 1, policy_version 23870 (0.0007) -[2023-11-28 00:50:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 12255232. Throughput: 0: 2692.3, 1: 2710.7. Samples: 12268556. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-11-28 00:50:18,445][86177] Avg episode reward: [(0, '-564.840'), (1, '-552.000')] -[2023-11-28 00:50:18,452][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000023872_6111232.pth... -[2023-11-28 00:50:18,500][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000021344_5464064.pth -[2023-11-28 00:50:18,625][87424] Updated weights for policy 0, policy_version 24006 (0.0010) -[2023-11-28 00:50:19,004][87424] Updated weights for policy 0, policy_version 24016 (0.0010) -[2023-11-28 00:50:19,025][87426] Updated weights for policy 1, policy_version 23880 (0.0011) -[2023-11-28 00:50:19,389][87424] Updated weights for policy 0, policy_version 24026 (0.0007) -[2023-11-28 00:50:19,405][87426] Updated weights for policy 1, policy_version 23890 (0.0012) -[2023-11-28 00:50:19,613][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000024032_6152192.pth... -[2023-11-28 00:50:19,650][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000021440_5488640.pth -[2023-11-28 00:50:19,792][87426] Updated weights for policy 1, policy_version 23900 (0.0008) -[2023-11-28 00:50:21,724][87426] Updated weights for policy 1, policy_version 23910 (0.0010) -[2023-11-28 00:50:21,725][87424] Updated weights for policy 0, policy_version 24036 (0.0015) -[2023-11-28 00:50:22,108][87424] Updated weights for policy 0, policy_version 24046 (0.0011) -[2023-11-28 00:50:22,113][87426] Updated weights for policy 1, policy_version 23920 (0.0013) -[2023-11-28 00:50:22,494][87424] Updated weights for policy 0, policy_version 24056 (0.0012) -[2023-11-28 00:50:22,497][87426] Updated weights for policy 1, policy_version 23930 (0.0010) -[2023-11-28 00:50:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12288000. Throughput: 0: 2669.0, 1: 2719.8. Samples: 12300356. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-11-28 00:50:23,445][86177] Avg episode reward: [(0, '-569.790'), (1, '-514.720')] -[2023-11-28 00:50:24,594][87426] Updated weights for policy 1, policy_version 23940 (0.0009) -[2023-11-28 00:50:24,980][87426] Updated weights for policy 1, policy_version 23950 (0.0008) -[2023-11-28 00:50:25,059][87424] Updated weights for policy 0, policy_version 24066 (0.0011) -[2023-11-28 00:50:25,354][87426] Updated weights for policy 1, policy_version 23960 (0.0009) -[2023-11-28 00:50:25,438][87424] Updated weights for policy 0, policy_version 24076 (0.0010) -[2023-11-28 00:50:25,816][87424] Updated weights for policy 0, policy_version 24086 (0.0011) -[2023-11-28 00:50:26,196][87424] Updated weights for policy 0, policy_version 24096 (0.0011) -[2023-11-28 00:50:27,233][87426] Updated weights for policy 1, policy_version 23970 (0.0008) -[2023-11-28 00:50:27,606][87426] Updated weights for policy 1, policy_version 23980 (0.0008) -[2023-11-28 00:50:27,983][87426] Updated weights for policy 1, policy_version 23990 (0.0007) -[2023-11-28 00:50:28,100][87424] Updated weights for policy 0, policy_version 24106 (0.0011) -[2023-11-28 00:50:28,370][87426] Updated weights for policy 1, policy_version 24000 (0.0007) -[2023-11-28 00:50:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 12312576. Throughput: 0: 2670.0, 1: 2763.5. Samples: 12325900. Policy #0 lag: (min: 15.0, avg: 22.8, max: 47.0) -[2023-11-28 00:50:28,445][86177] Avg episode reward: [(0, '-565.370'), (1, '-515.820')] -[2023-11-28 00:50:28,477][87424] Updated weights for policy 0, policy_version 24116 (0.0009) -[2023-11-28 00:50:28,867][87424] Updated weights for policy 0, policy_version 24126 (0.0008) -[2023-11-28 00:50:30,811][87426] Updated weights for policy 1, policy_version 24010 (0.0011) -[2023-11-28 00:50:31,147][87424] Updated weights for policy 0, policy_version 24136 (0.0011) -[2023-11-28 00:50:31,182][87426] Updated weights for policy 1, policy_version 24020 (0.0008) -[2023-11-28 00:50:31,534][87424] Updated weights for policy 0, policy_version 24146 (0.0012) -[2023-11-28 00:50:31,569][87426] Updated weights for policy 1, policy_version 24030 (0.0009) -[2023-11-28 00:50:31,913][87424] Updated weights for policy 0, policy_version 24156 (0.0010) -[2023-11-28 00:50:33,305][87426] Updated weights for policy 1, policy_version 24040 (0.0008) -[2023-11-28 00:50:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 12337152. Throughput: 0: 2701.9, 1: 2752.4. Samples: 12351632. Policy #0 lag: (min: 7.0, avg: 26.3, max: 53.0) -[2023-11-28 00:50:33,445][86177] Avg episode reward: [(0, '-561.440'), (1, '-517.550')] -[2023-11-28 00:50:33,683][87426] Updated weights for policy 1, policy_version 24050 (0.0007) -[2023-11-28 00:50:33,761][87424] Updated weights for policy 0, policy_version 24166 (0.0009) -[2023-11-28 00:50:34,075][87426] Updated weights for policy 1, policy_version 24060 (0.0007) -[2023-11-28 00:50:34,149][87424] Updated weights for policy 0, policy_version 24176 (0.0011) -[2023-11-28 00:50:34,543][87424] Updated weights for policy 0, policy_version 24186 (0.0012) -[2023-11-28 00:50:35,900][87426] Updated weights for policy 1, policy_version 24070 (0.0009) -[2023-11-28 00:50:36,280][87426] Updated weights for policy 1, policy_version 24080 (0.0007) -[2023-11-28 00:50:36,410][87424] Updated weights for policy 0, policy_version 24196 (0.0012) -[2023-11-28 00:50:36,662][87426] Updated weights for policy 1, policy_version 24090 (0.0008) -[2023-11-28 00:50:36,789][87424] Updated weights for policy 0, policy_version 24206 (0.0011) -[2023-11-28 00:50:37,162][87424] Updated weights for policy 0, policy_version 24216 (0.0009) -[2023-11-28 00:50:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12369920. Throughput: 0: 2722.5, 1: 2757.8. Samples: 12384684. Policy #0 lag: (min: 7.0, avg: 26.3, max: 53.0) -[2023-11-28 00:50:38,445][86177] Avg episode reward: [(0, '-556.670'), (1, '-513.560')] -[2023-11-28 00:50:39,218][87426] Updated weights for policy 1, policy_version 24100 (0.0010) -[2023-11-28 00:50:39,597][87426] Updated weights for policy 1, policy_version 24110 (0.0012) -[2023-11-28 00:50:39,645][87424] Updated weights for policy 0, policy_version 24226 (0.0009) -[2023-11-28 00:50:39,974][87426] Updated weights for policy 1, policy_version 24120 (0.0011) -[2023-11-28 00:50:40,027][87424] Updated weights for policy 0, policy_version 24236 (0.0012) -[2023-11-28 00:50:40,412][87424] Updated weights for policy 0, policy_version 24246 (0.0009) -[2023-11-28 00:50:40,795][87424] Updated weights for policy 0, policy_version 24256 (0.0012) -[2023-11-28 00:50:42,558][87426] Updated weights for policy 1, policy_version 24130 (0.0011) -[2023-11-28 00:50:42,942][87426] Updated weights for policy 1, policy_version 24140 (0.0010) -[2023-11-28 00:50:43,021][87424] Updated weights for policy 0, policy_version 24266 (0.0010) -[2023-11-28 00:50:43,316][87426] Updated weights for policy 1, policy_version 24150 (0.0008) -[2023-11-28 00:50:43,403][87424] Updated weights for policy 0, policy_version 24276 (0.0008) -[2023-11-28 00:50:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 12386304. Throughput: 0: 2752.3, 1: 2730.0. Samples: 12408460. Policy #0 lag: (min: 7.0, avg: 26.3, max: 53.0) -[2023-11-28 00:50:43,445][86177] Avg episode reward: [(0, '-554.340'), (1, '-517.390')] -[2023-11-28 00:50:43,695][87426] Updated weights for policy 1, policy_version 24160 (0.0009) -[2023-11-28 00:50:43,789][87424] Updated weights for policy 0, policy_version 24286 (0.0007) -[2023-11-28 00:50:45,594][87424] Updated weights for policy 0, policy_version 24296 (0.0009) -[2023-11-28 00:50:45,984][87424] Updated weights for policy 0, policy_version 24306 (0.0012) -[2023-11-28 00:50:46,102][87426] Updated weights for policy 1, policy_version 24170 (0.0012) -[2023-11-28 00:50:46,367][87424] Updated weights for policy 0, policy_version 24316 (0.0010) -[2023-11-28 00:50:46,487][87426] Updated weights for policy 1, policy_version 24180 (0.0011) -[2023-11-28 00:50:46,866][87426] Updated weights for policy 1, policy_version 24190 (0.0011) -[2023-11-28 00:50:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 12419072. Throughput: 0: 2762.7, 1: 2716.8. Samples: 12432940. Policy #0 lag: (min: 38.0, avg: 46.5, max: 73.0) -[2023-11-28 00:50:48,446][86177] Avg episode reward: [(0, '-624.820'), (1, '-514.820')] -[2023-11-28 00:50:48,530][87426] Updated weights for policy 1, policy_version 24200 (0.0008) -[2023-11-28 00:50:48,627][87424] Updated weights for policy 0, policy_version 24326 (0.0008) -[2023-11-28 00:50:48,919][87426] Updated weights for policy 1, policy_version 24210 (0.0011) -[2023-11-28 00:50:49,018][87424] Updated weights for policy 0, policy_version 24336 (0.0008) -[2023-11-28 00:50:49,285][87426] Updated weights for policy 1, policy_version 24220 (0.0011) -[2023-11-28 00:50:49,391][87424] Updated weights for policy 0, policy_version 24346 (0.0011) -[2023-11-28 00:50:51,238][87426] Updated weights for policy 1, policy_version 24230 (0.0011) -[2023-11-28 00:50:51,620][87426] Updated weights for policy 1, policy_version 24240 (0.0016) -[2023-11-28 00:50:51,697][87424] Updated weights for policy 0, policy_version 24356 (0.0011) -[2023-11-28 00:50:51,995][87426] Updated weights for policy 1, policy_version 24250 (0.0012) -[2023-11-28 00:50:52,080][87424] Updated weights for policy 0, policy_version 24366 (0.0010) -[2023-11-28 00:50:52,462][87424] Updated weights for policy 0, policy_version 24376 (0.0012) -[2023-11-28 00:50:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12451840. Throughput: 0: 2754.1, 1: 2751.1. Samples: 12465948. Policy #0 lag: (min: 38.0, avg: 46.5, max: 73.0) -[2023-11-28 00:50:53,445][86177] Avg episode reward: [(0, '-588.610'), (1, '-535.350')] -[2023-11-28 00:50:54,447][87424] Updated weights for policy 0, policy_version 24386 (0.0012) -[2023-11-28 00:50:54,532][87426] Updated weights for policy 1, policy_version 24260 (0.0011) -[2023-11-28 00:50:54,834][87424] Updated weights for policy 0, policy_version 24396 (0.0012) -[2023-11-28 00:50:54,912][87426] Updated weights for policy 1, policy_version 24270 (0.0011) -[2023-11-28 00:50:55,217][87424] Updated weights for policy 0, policy_version 24406 (0.0012) -[2023-11-28 00:50:55,294][87426] Updated weights for policy 1, policy_version 24280 (0.0010) -[2023-11-28 00:50:55,608][87424] Updated weights for policy 0, policy_version 24416 (0.0012) -[2023-11-28 00:50:57,111][87426] Updated weights for policy 1, policy_version 24290 (0.0011) -[2023-11-28 00:50:57,407][87424] Updated weights for policy 0, policy_version 24426 (0.0009) -[2023-11-28 00:50:57,490][87426] Updated weights for policy 1, policy_version 24300 (0.0011) -[2023-11-28 00:50:57,798][87424] Updated weights for policy 0, policy_version 24436 (0.0010) -[2023-11-28 00:50:57,867][87426] Updated weights for policy 1, policy_version 24310 (0.0011) -[2023-11-28 00:50:58,192][87424] Updated weights for policy 0, policy_version 24446 (0.0012) -[2023-11-28 00:50:58,259][87426] Updated weights for policy 1, policy_version 24320 (0.0007) -[2023-11-28 00:50:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5734.4, 300 sec: 5470.6). Total num frames: 12484608. Throughput: 0: 2756.6, 1: 2746.3. Samples: 12490892. Policy #0 lag: (min: 38.0, avg: 46.5, max: 73.0) -[2023-11-28 00:50:58,445][86177] Avg episode reward: [(0, '-606.310'), (1, '-582.420')] -[2023-11-28 00:51:00,658][87424] Updated weights for policy 0, policy_version 24456 (0.0009) -[2023-11-28 00:51:00,769][87426] Updated weights for policy 1, policy_version 24330 (0.0012) -[2023-11-28 00:51:01,050][87424] Updated weights for policy 0, policy_version 24466 (0.0008) -[2023-11-28 00:51:01,138][87426] Updated weights for policy 1, policy_version 24340 (0.0011) -[2023-11-28 00:51:01,428][87424] Updated weights for policy 0, policy_version 24476 (0.0008) -[2023-11-28 00:51:01,513][87426] Updated weights for policy 1, policy_version 24350 (0.0011) -[2023-11-28 00:51:03,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 12500992. Throughput: 0: 2757.1, 1: 2723.4. Samples: 12515180. Policy #0 lag: (min: 38.0, avg: 46.5, max: 73.0) -[2023-11-28 00:51:03,445][86177] Avg episode reward: [(0, '-604.460'), (1, '-618.690')] -[2023-11-28 00:51:03,722][87426] Updated weights for policy 1, policy_version 24360 (0.0011) -[2023-11-28 00:51:03,897][87424] Updated weights for policy 0, policy_version 24486 (0.0009) -[2023-11-28 00:51:04,102][87426] Updated weights for policy 1, policy_version 24370 (0.0010) -[2023-11-28 00:51:04,273][87424] Updated weights for policy 0, policy_version 24496 (0.0012) -[2023-11-28 00:51:04,486][87426] Updated weights for policy 1, policy_version 24380 (0.0008) -[2023-11-28 00:51:04,657][87424] Updated weights for policy 0, policy_version 24506 (0.0009) -[2023-11-28 00:51:06,533][87424] Updated weights for policy 0, policy_version 24516 (0.0012) -[2023-11-28 00:51:06,800][87426] Updated weights for policy 1, policy_version 24390 (0.0010) -[2023-11-28 00:51:06,919][87424] Updated weights for policy 0, policy_version 24526 (0.0011) -[2023-11-28 00:51:07,177][87426] Updated weights for policy 1, policy_version 24400 (0.0010) -[2023-11-28 00:51:07,307][87424] Updated weights for policy 0, policy_version 24536 (0.0009) -[2023-11-28 00:51:07,559][87426] Updated weights for policy 1, policy_version 24410 (0.0011) -[2023-11-28 00:51:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12533760. Throughput: 0: 2753.1, 1: 2716.9. Samples: 12546504. Policy #0 lag: (min: 20.0, avg: 40.4, max: 52.0) -[2023-11-28 00:51:08,445][86177] Avg episode reward: [(0, '-540.000'), (1, '-618.900')] -[2023-11-28 00:51:09,481][87426] Updated weights for policy 1, policy_version 24420 (0.0012) -[2023-11-28 00:51:09,855][87426] Updated weights for policy 1, policy_version 24430 (0.0011) -[2023-11-28 00:51:09,925][87424] Updated weights for policy 0, policy_version 24546 (0.0011) -[2023-11-28 00:51:10,233][87426] Updated weights for policy 1, policy_version 24440 (0.0011) -[2023-11-28 00:51:10,307][87424] Updated weights for policy 0, policy_version 24556 (0.0008) -[2023-11-28 00:51:10,696][87424] Updated weights for policy 0, policy_version 24566 (0.0009) -[2023-11-28 00:51:11,078][87424] Updated weights for policy 0, policy_version 24576 (0.0010) -[2023-11-28 00:51:12,823][87426] Updated weights for policy 1, policy_version 24450 (0.0011) -[2023-11-28 00:51:13,036][87424] Updated weights for policy 0, policy_version 24586 (0.0010) -[2023-11-28 00:51:13,199][87426] Updated weights for policy 1, policy_version 24460 (0.0010) -[2023-11-28 00:51:13,423][87424] Updated weights for policy 0, policy_version 24596 (0.0012) -[2023-11-28 00:51:13,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 12550144. Throughput: 0: 2757.4, 1: 2683.7. Samples: 12570752. Policy #0 lag: (min: 20.0, avg: 40.4, max: 52.0) -[2023-11-28 00:51:13,445][86177] Avg episode reward: [(0, '-541.030'), (1, '-607.350')] -[2023-11-28 00:51:13,583][87426] Updated weights for policy 1, policy_version 24470 (0.0011) -[2023-11-28 00:51:13,797][87424] Updated weights for policy 0, policy_version 24606 (0.0011) -[2023-11-28 00:51:13,964][87426] Updated weights for policy 1, policy_version 24480 (0.0009) -[2023-11-28 00:51:15,929][87426] Updated weights for policy 1, policy_version 24490 (0.0012) -[2023-11-28 00:51:16,241][87424] Updated weights for policy 0, policy_version 24616 (0.0012) -[2023-11-28 00:51:16,309][87426] Updated weights for policy 1, policy_version 24500 (0.0008) -[2023-11-28 00:51:16,624][87424] Updated weights for policy 0, policy_version 24626 (0.0012) -[2023-11-28 00:51:16,693][87426] Updated weights for policy 1, policy_version 24510 (0.0007) -[2023-11-28 00:51:17,007][87424] Updated weights for policy 0, policy_version 24636 (0.0012) -[2023-11-28 00:51:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12582912. Throughput: 0: 2707.0, 1: 2699.5. Samples: 12594924. Policy #0 lag: (min: 20.0, avg: 40.4, max: 52.0) -[2023-11-28 00:51:18,445][86177] Avg episode reward: [(0, '-542.560'), (1, '-559.630')] -[2023-11-28 00:51:18,740][87424] Updated weights for policy 0, policy_version 24646 (0.0010) -[2023-11-28 00:51:18,793][87426] Updated weights for policy 1, policy_version 24520 (0.0010) -[2023-11-28 00:51:19,116][87424] Updated weights for policy 0, policy_version 24656 (0.0010) -[2023-11-28 00:51:19,181][87426] Updated weights for policy 1, policy_version 24530 (0.0008) -[2023-11-28 00:51:19,506][87424] Updated weights for policy 0, policy_version 24666 (0.0012) -[2023-11-28 00:51:19,555][87426] Updated weights for policy 1, policy_version 24540 (0.0008) -[2023-11-28 00:51:21,667][87424] Updated weights for policy 0, policy_version 24676 (0.0012) -[2023-11-28 00:51:21,925][87426] Updated weights for policy 1, policy_version 24550 (0.0009) -[2023-11-28 00:51:22,051][87424] Updated weights for policy 0, policy_version 24686 (0.0011) -[2023-11-28 00:51:22,305][87426] Updated weights for policy 1, policy_version 24560 (0.0010) -[2023-11-28 00:51:22,435][87424] Updated weights for policy 0, policy_version 24696 (0.0011) -[2023-11-28 00:51:22,682][87426] Updated weights for policy 1, policy_version 24570 (0.0011) -[2023-11-28 00:51:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 12615680. Throughput: 0: 2698.9, 1: 2684.0. Samples: 12626916. Policy #0 lag: (min: 11.0, avg: 30.6, max: 56.0) -[2023-11-28 00:51:23,445][86177] Avg episode reward: [(0, '-529.010'), (1, '-531.100')] -[2023-11-28 00:51:24,540][87424] Updated weights for policy 0, policy_version 24706 (0.0010) -[2023-11-28 00:51:24,910][87426] Updated weights for policy 1, policy_version 24580 (0.0010) -[2023-11-28 00:51:24,925][87424] Updated weights for policy 0, policy_version 24716 (0.0009) -[2023-11-28 00:51:25,292][87426] Updated weights for policy 1, policy_version 24590 (0.0010) -[2023-11-28 00:51:25,302][87424] Updated weights for policy 0, policy_version 24726 (0.0008) -[2023-11-28 00:51:25,662][87426] Updated weights for policy 1, policy_version 24600 (0.0010) -[2023-11-28 00:51:25,694][87424] Updated weights for policy 0, policy_version 24736 (0.0012) -[2023-11-28 00:51:27,819][87424] Updated weights for policy 0, policy_version 24746 (0.0011) -[2023-11-28 00:51:28,197][87426] Updated weights for policy 1, policy_version 24610 (0.0012) -[2023-11-28 00:51:28,198][87424] Updated weights for policy 0, policy_version 24756 (0.0007) -[2023-11-28 00:51:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 12632064. Throughput: 0: 2682.0, 1: 2718.7. Samples: 12651488. Policy #0 lag: (min: 11.0, avg: 30.6, max: 56.0) -[2023-11-28 00:51:28,445][86177] Avg episode reward: [(0, '-533.010'), (1, '-529.660')] -[2023-11-28 00:51:28,570][87426] Updated weights for policy 1, policy_version 24620 (0.0011) -[2023-11-28 00:51:28,580][87424] Updated weights for policy 0, policy_version 24766 (0.0007) -[2023-11-28 00:51:28,948][87426] Updated weights for policy 1, policy_version 24630 (0.0012) -[2023-11-28 00:51:29,335][87426] Updated weights for policy 1, policy_version 24640 (0.0012) -[2023-11-28 00:51:30,802][87424] Updated weights for policy 0, policy_version 24776 (0.0008) -[2023-11-28 00:51:31,198][87424] Updated weights for policy 0, policy_version 24786 (0.0009) -[2023-11-28 00:51:31,575][87424] Updated weights for policy 0, policy_version 24796 (0.0012) -[2023-11-28 00:51:31,770][87426] Updated weights for policy 1, policy_version 24650 (0.0011) -[2023-11-28 00:51:32,159][87426] Updated weights for policy 1, policy_version 24660 (0.0010) -[2023-11-28 00:51:32,534][87426] Updated weights for policy 1, policy_version 24670 (0.0011) -[2023-11-28 00:51:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12664832. Throughput: 0: 2689.4, 1: 2721.8. Samples: 12676444. Policy #0 lag: (min: 11.0, avg: 30.6, max: 56.0) -[2023-11-28 00:51:33,445][86177] Avg episode reward: [(0, '-530.040'), (1, '-565.070')] -[2023-11-28 00:51:34,144][87424] Updated weights for policy 0, policy_version 24806 (0.0010) -[2023-11-28 00:51:34,533][87424] Updated weights for policy 0, policy_version 24816 (0.0007) -[2023-11-28 00:51:34,563][87426] Updated weights for policy 1, policy_version 24680 (0.0009) -[2023-11-28 00:51:34,912][87424] Updated weights for policy 0, policy_version 24826 (0.0011) -[2023-11-28 00:51:34,936][87426] Updated weights for policy 1, policy_version 24690 (0.0010) -[2023-11-28 00:51:35,317][87426] Updated weights for policy 1, policy_version 24700 (0.0010) -[2023-11-28 00:51:37,019][87424] Updated weights for policy 0, policy_version 24836 (0.0012) -[2023-11-28 00:51:37,414][87424] Updated weights for policy 0, policy_version 24846 (0.0012) -[2023-11-28 00:51:37,683][87426] Updated weights for policy 1, policy_version 24710 (0.0010) -[2023-11-28 00:51:37,797][87424] Updated weights for policy 0, policy_version 24856 (0.0011) -[2023-11-28 00:51:38,064][87426] Updated weights for policy 1, policy_version 24720 (0.0011) -[2023-11-28 00:51:38,442][87426] Updated weights for policy 1, policy_version 24730 (0.0012) -[2023-11-28 00:51:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 12689408. Throughput: 0: 2690.7, 1: 2713.1. Samples: 12709116. Policy #0 lag: (min: 11.0, avg: 30.6, max: 56.0) -[2023-11-28 00:51:38,445][86177] Avg episode reward: [(0, '-541.610'), (1, '-578.710')] -[2023-11-28 00:51:39,965][87424] Updated weights for policy 0, policy_version 24866 (0.0012) -[2023-11-28 00:51:40,301][87426] Updated weights for policy 1, policy_version 24740 (0.0012) -[2023-11-28 00:51:40,353][87424] Updated weights for policy 0, policy_version 24876 (0.0011) -[2023-11-28 00:51:40,689][87426] Updated weights for policy 1, policy_version 24750 (0.0017) -[2023-11-28 00:51:40,739][87424] Updated weights for policy 0, policy_version 24886 (0.0011) -[2023-11-28 00:51:41,062][87426] Updated weights for policy 1, policy_version 24760 (0.0010) -[2023-11-28 00:51:41,118][87424] Updated weights for policy 0, policy_version 24896 (0.0008) -[2023-11-28 00:51:43,360][87426] Updated weights for policy 1, policy_version 24770 (0.0010) -[2023-11-28 00:51:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 12713984. Throughput: 0: 2695.8, 1: 2693.6. Samples: 12733416. Policy #0 lag: (min: 28.0, avg: 51.2, max: 71.0) -[2023-11-28 00:51:43,445][86177] Avg episode reward: [(0, '-541.840'), (1, '-570.360')] -[2023-11-28 00:51:43,445][87424] Updated weights for policy 0, policy_version 24906 (0.0009) -[2023-11-28 00:51:43,737][87426] Updated weights for policy 1, policy_version 24780 (0.0011) -[2023-11-28 00:51:43,827][87424] Updated weights for policy 0, policy_version 24916 (0.0008) -[2023-11-28 00:51:44,112][87426] Updated weights for policy 1, policy_version 24790 (0.0007) -[2023-11-28 00:51:44,212][87424] Updated weights for policy 0, policy_version 24926 (0.0008) -[2023-11-28 00:51:44,486][87426] Updated weights for policy 1, policy_version 24800 (0.0008) -[2023-11-28 00:51:46,110][87426] Updated weights for policy 1, policy_version 24810 (0.0012) -[2023-11-28 00:51:46,364][87424] Updated weights for policy 0, policy_version 24936 (0.0007) -[2023-11-28 00:51:46,494][87426] Updated weights for policy 1, policy_version 24820 (0.0012) -[2023-11-28 00:51:46,748][87424] Updated weights for policy 0, policy_version 24946 (0.0007) -[2023-11-28 00:51:46,879][87426] Updated weights for policy 1, policy_version 24830 (0.0011) -[2023-11-28 00:51:47,135][87424] Updated weights for policy 0, policy_version 24956 (0.0007) -[2023-11-28 00:51:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 12746752. Throughput: 0: 2673.5, 1: 2707.0. Samples: 12757300. Policy #0 lag: (min: 28.0, avg: 51.2, max: 71.0) -[2023-11-28 00:51:48,445][86177] Avg episode reward: [(0, '-540.060'), (1, '-569.410')] -[2023-11-28 00:51:48,702][87426] Updated weights for policy 1, policy_version 24840 (0.0011) -[2023-11-28 00:51:49,101][87426] Updated weights for policy 1, policy_version 24850 (0.0011) -[2023-11-28 00:51:49,477][87426] Updated weights for policy 1, policy_version 24860 (0.0011) -[2023-11-28 00:51:49,568][87424] Updated weights for policy 0, policy_version 24966 (0.0010) -[2023-11-28 00:51:49,956][87424] Updated weights for policy 0, policy_version 24976 (0.0009) -[2023-11-28 00:51:50,347][87424] Updated weights for policy 0, policy_version 24986 (0.0007) -[2023-11-28 00:51:51,907][87426] Updated weights for policy 1, policy_version 24870 (0.0010) -[2023-11-28 00:51:52,284][87426] Updated weights for policy 1, policy_version 24880 (0.0011) -[2023-11-28 00:51:52,664][87426] Updated weights for policy 1, policy_version 24890 (0.0012) -[2023-11-28 00:51:52,694][87424] Updated weights for policy 0, policy_version 24996 (0.0011) -[2023-11-28 00:51:53,081][87424] Updated weights for policy 0, policy_version 25006 (0.0010) -[2023-11-28 00:51:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 12771328. Throughput: 0: 2669.2, 1: 2739.1. Samples: 12789876. Policy #0 lag: (min: 28.0, avg: 51.2, max: 71.0) -[2023-11-28 00:51:53,445][86177] Avg episode reward: [(0, '-550.290'), (1, '-572.130')] -[2023-11-28 00:51:53,468][87424] Updated weights for policy 0, policy_version 25016 (0.0011) -[2023-11-28 00:51:54,720][87426] Updated weights for policy 1, policy_version 24900 (0.0012) -[2023-11-28 00:51:55,103][87426] Updated weights for policy 1, policy_version 24910 (0.0011) -[2023-11-28 00:51:55,434][87424] Updated weights for policy 0, policy_version 25026 (0.0010) -[2023-11-28 00:51:55,486][87426] Updated weights for policy 1, policy_version 24920 (0.0012) -[2023-11-28 00:51:55,820][87424] Updated weights for policy 0, policy_version 25036 (0.0007) -[2023-11-28 00:51:56,205][87424] Updated weights for policy 0, policy_version 25046 (0.0008) -[2023-11-28 00:51:56,588][87424] Updated weights for policy 0, policy_version 25056 (0.0007) -[2023-11-28 00:51:57,991][87426] Updated weights for policy 1, policy_version 24930 (0.0011) -[2023-11-28 00:51:58,365][87426] Updated weights for policy 1, policy_version 24940 (0.0011) -[2023-11-28 00:51:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 12795904. Throughput: 0: 2677.7, 1: 2740.8. Samples: 12814584. Policy #0 lag: (min: 28.0, avg: 51.2, max: 71.0) -[2023-11-28 00:51:58,445][86177] Avg episode reward: [(0, '-540.760'), (1, '-617.970')] -[2023-11-28 00:51:58,473][87424] Updated weights for policy 0, policy_version 25066 (0.0009) -[2023-11-28 00:51:58,756][87426] Updated weights for policy 1, policy_version 24950 (0.0010) -[2023-11-28 00:51:58,849][87424] Updated weights for policy 0, policy_version 25076 (0.0008) -[2023-11-28 00:51:59,125][87426] Updated weights for policy 1, policy_version 24960 (0.0007) -[2023-11-28 00:51:59,234][87424] Updated weights for policy 0, policy_version 25086 (0.0008) -[2023-11-28 00:52:01,552][87424] Updated weights for policy 0, policy_version 25096 (0.0011) -[2023-11-28 00:52:01,712][87426] Updated weights for policy 1, policy_version 24970 (0.0008) -[2023-11-28 00:52:01,930][87424] Updated weights for policy 0, policy_version 25106 (0.0009) -[2023-11-28 00:52:02,093][87426] Updated weights for policy 1, policy_version 24980 (0.0009) -[2023-11-28 00:52:02,315][87424] Updated weights for policy 0, policy_version 25116 (0.0011) -[2023-11-28 00:52:02,467][87426] Updated weights for policy 1, policy_version 24990 (0.0008) -[2023-11-28 00:52:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 12828672. Throughput: 0: 2686.0, 1: 2710.1. Samples: 12837752. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 00:52:03,445][86177] Avg episode reward: [(0, '-538.380'), (1, '-622.790')] -[2023-11-28 00:52:04,498][87424] Updated weights for policy 0, policy_version 25126 (0.0011) -[2023-11-28 00:52:04,877][87426] Updated weights for policy 1, policy_version 25000 (0.0011) -[2023-11-28 00:52:04,879][87424] Updated weights for policy 0, policy_version 25136 (0.0011) -[2023-11-28 00:52:05,258][87426] Updated weights for policy 1, policy_version 25010 (0.0010) -[2023-11-28 00:52:05,266][87424] Updated weights for policy 0, policy_version 25146 (0.0011) -[2023-11-28 00:52:05,636][87426] Updated weights for policy 1, policy_version 25020 (0.0009) -[2023-11-28 00:52:07,855][87424] Updated weights for policy 0, policy_version 25156 (0.0007) -[2023-11-28 00:52:08,122][87426] Updated weights for policy 1, policy_version 25030 (0.0010) -[2023-11-28 00:52:08,233][87424] Updated weights for policy 0, policy_version 25166 (0.0009) -[2023-11-28 00:52:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 12845056. Throughput: 0: 2707.5, 1: 2706.7. Samples: 12870552. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 00:52:08,445][86177] Avg episode reward: [(0, '-525.580'), (1, '-635.690')] -[2023-11-28 00:52:08,504][87426] Updated weights for policy 1, policy_version 25040 (0.0009) -[2023-11-28 00:52:08,633][87424] Updated weights for policy 0, policy_version 25176 (0.0009) -[2023-11-28 00:52:08,887][87426] Updated weights for policy 1, policy_version 25050 (0.0008) -[2023-11-28 00:52:10,832][87424] Updated weights for policy 0, policy_version 25186 (0.0009) -[2023-11-28 00:52:11,036][87426] Updated weights for policy 1, policy_version 25060 (0.0010) -[2023-11-28 00:52:11,217][87424] Updated weights for policy 0, policy_version 25196 (0.0011) -[2023-11-28 00:52:11,414][87426] Updated weights for policy 1, policy_version 25070 (0.0009) -[2023-11-28 00:52:11,603][87424] Updated weights for policy 0, policy_version 25206 (0.0011) -[2023-11-28 00:52:11,793][87426] Updated weights for policy 1, policy_version 25080 (0.0010) -[2023-11-28 00:52:11,988][87424] Updated weights for policy 0, policy_version 25216 (0.0009) -[2023-11-28 00:52:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 12877824. Throughput: 0: 2707.0, 1: 2698.0. Samples: 12894716. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 00:52:13,445][86177] Avg episode reward: [(0, '-527.340'), (1, '-632.890')] -[2023-11-28 00:52:14,043][87424] Updated weights for policy 0, policy_version 25226 (0.0012) -[2023-11-28 00:52:14,044][87426] Updated weights for policy 1, policy_version 25090 (0.0012) -[2023-11-28 00:52:14,424][87426] Updated weights for policy 1, policy_version 25100 (0.0011) -[2023-11-28 00:52:14,436][87424] Updated weights for policy 0, policy_version 25236 (0.0010) -[2023-11-28 00:52:14,805][87426] Updated weights for policy 1, policy_version 25110 (0.0011) -[2023-11-28 00:52:14,815][87424] Updated weights for policy 0, policy_version 25246 (0.0010) -[2023-11-28 00:52:15,187][87426] Updated weights for policy 1, policy_version 25120 (0.0011) -[2023-11-28 00:52:16,537][87424] Updated weights for policy 0, policy_version 25256 (0.0011) -[2023-11-28 00:52:16,919][87424] Updated weights for policy 0, policy_version 25266 (0.0012) -[2023-11-28 00:52:17,267][87426] Updated weights for policy 1, policy_version 25130 (0.0008) -[2023-11-28 00:52:17,303][87424] Updated weights for policy 0, policy_version 25276 (0.0011) -[2023-11-28 00:52:17,646][87426] Updated weights for policy 1, policy_version 25140 (0.0007) -[2023-11-28 00:52:18,031][87426] Updated weights for policy 1, policy_version 25150 (0.0008) -[2023-11-28 00:52:18,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12910592. Throughput: 0: 2687.6, 1: 2697.3. Samples: 12918768. Policy #0 lag: (min: 6.0, avg: 29.7, max: 70.0) -[2023-11-28 00:52:18,445][86177] Avg episode reward: [(0, '-528.350'), (1, '-573.910')] -[2023-11-28 00:52:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000025152_6438912.pth... -[2023-11-28 00:52:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000025280_6471680.pth... -[2023-11-28 00:52:18,490][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000022752_5824512.pth -[2023-11-28 00:52:18,491][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000022624_5791744.pth -[2023-11-28 00:52:18,495][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000025280_6471680.pth -[2023-11-28 00:52:18,498][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000025152_6438912.pth -[2023-11-28 00:52:19,712][87424] Updated weights for policy 0, policy_version 25286 (0.0012) -[2023-11-28 00:52:20,087][87424] Updated weights for policy 0, policy_version 25296 (0.0010) -[2023-11-28 00:52:20,474][87424] Updated weights for policy 0, policy_version 25306 (0.0010) -[2023-11-28 00:52:20,519][87426] Updated weights for policy 1, policy_version 25160 (0.0008) -[2023-11-28 00:52:20,900][87426] Updated weights for policy 1, policy_version 25170 (0.0008) -[2023-11-28 00:52:21,282][87426] Updated weights for policy 1, policy_version 25180 (0.0011) -[2023-11-28 00:52:22,930][87424] Updated weights for policy 0, policy_version 25316 (0.0011) -[2023-11-28 00:52:23,302][87424] Updated weights for policy 0, policy_version 25326 (0.0012) -[2023-11-28 00:52:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 12926976. Throughput: 0: 2678.9, 1: 2682.5. Samples: 12950380. Policy #0 lag: (min: 6.0, avg: 29.7, max: 70.0) -[2023-11-28 00:52:23,445][86177] Avg episode reward: [(0, '-539.420'), (1, '-562.470')] -[2023-11-28 00:52:23,684][87424] Updated weights for policy 0, policy_version 25336 (0.0010) -[2023-11-28 00:52:23,703][87426] Updated weights for policy 1, policy_version 25190 (0.0010) -[2023-11-28 00:52:24,091][87426] Updated weights for policy 1, policy_version 25200 (0.0010) -[2023-11-28 00:52:24,480][87426] Updated weights for policy 1, policy_version 25210 (0.0007) -[2023-11-28 00:52:25,973][87426] Updated weights for policy 1, policy_version 25220 (0.0008) -[2023-11-28 00:52:25,982][87424] Updated weights for policy 0, policy_version 25346 (0.0010) -[2023-11-28 00:52:26,350][87426] Updated weights for policy 1, policy_version 25230 (0.0007) -[2023-11-28 00:52:26,360][87424] Updated weights for policy 0, policy_version 25356 (0.0007) -[2023-11-28 00:52:26,733][87426] Updated weights for policy 1, policy_version 25240 (0.0008) -[2023-11-28 00:52:26,743][87424] Updated weights for policy 0, policy_version 25366 (0.0007) -[2023-11-28 00:52:27,136][87424] Updated weights for policy 0, policy_version 25376 (0.0007) -[2023-11-28 00:52:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 12959744. Throughput: 0: 2666.7, 1: 2718.8. Samples: 12975768. Policy #0 lag: (min: 6.0, avg: 29.7, max: 70.0) -[2023-11-28 00:52:28,445][86177] Avg episode reward: [(0, '-542.540'), (1, '-562.420')] -[2023-11-28 00:52:28,513][87426] Updated weights for policy 1, policy_version 25250 (0.0008) -[2023-11-28 00:52:28,893][87426] Updated weights for policy 1, policy_version 25260 (0.0009) -[2023-11-28 00:52:29,275][87426] Updated weights for policy 1, policy_version 25270 (0.0008) -[2023-11-28 00:52:29,390][87424] Updated weights for policy 0, policy_version 25386 (0.0011) -[2023-11-28 00:52:29,646][87426] Updated weights for policy 1, policy_version 25280 (0.0010) -[2023-11-28 00:52:29,768][87424] Updated weights for policy 0, policy_version 25396 (0.0012) -[2023-11-28 00:52:30,145][87424] Updated weights for policy 0, policy_version 25406 (0.0010) -[2023-11-28 00:52:31,352][87426] Updated weights for policy 1, policy_version 25290 (0.0012) -[2023-11-28 00:52:31,732][87426] Updated weights for policy 1, policy_version 25300 (0.0012) -[2023-11-28 00:52:32,110][87426] Updated weights for policy 1, policy_version 25310 (0.0011) -[2023-11-28 00:52:32,391][87424] Updated weights for policy 0, policy_version 25416 (0.0010) -[2023-11-28 00:52:32,777][87424] Updated weights for policy 0, policy_version 25426 (0.0012) -[2023-11-28 00:52:33,158][87424] Updated weights for policy 0, policy_version 25436 (0.0012) -[2023-11-28 00:52:33,445][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 12992512. Throughput: 0: 2680.4, 1: 2738.6. Samples: 13001156. Policy #0 lag: (min: 6.0, avg: 29.7, max: 70.0) -[2023-11-28 00:52:33,446][86177] Avg episode reward: [(0, '-549.530'), (1, '-573.740')] -[2023-11-28 00:52:33,918][87426] Updated weights for policy 1, policy_version 25320 (0.0011) -[2023-11-28 00:52:34,304][87426] Updated weights for policy 1, policy_version 25330 (0.0012) -[2023-11-28 00:52:34,685][87426] Updated weights for policy 1, policy_version 25340 (0.0012) -[2023-11-28 00:52:35,456][87424] Updated weights for policy 0, policy_version 25446 (0.0011) -[2023-11-28 00:52:35,842][87424] Updated weights for policy 0, policy_version 25456 (0.0011) -[2023-11-28 00:52:36,232][87424] Updated weights for policy 0, policy_version 25466 (0.0011) -[2023-11-28 00:52:36,981][87426] Updated weights for policy 1, policy_version 25350 (0.0012) -[2023-11-28 00:52:37,365][87426] Updated weights for policy 1, policy_version 25360 (0.0012) -[2023-11-28 00:52:37,744][87426] Updated weights for policy 1, policy_version 25370 (0.0011) -[2023-11-28 00:52:37,933][87424] Updated weights for policy 0, policy_version 25476 (0.0011) -[2023-11-28 00:52:38,316][87424] Updated weights for policy 0, policy_version 25486 (0.0012) -[2023-11-28 00:52:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13017088. Throughput: 0: 2729.2, 1: 2709.6. Samples: 13034620. Policy #0 lag: (min: 28.0, avg: 50.8, max: 60.0) -[2023-11-28 00:52:38,445][86177] Avg episode reward: [(0, '-548.950'), (1, '-594.590')] -[2023-11-28 00:52:38,701][87424] Updated weights for policy 0, policy_version 25496 (0.0012) -[2023-11-28 00:52:39,581][87426] Updated weights for policy 1, policy_version 25380 (0.0011) -[2023-11-28 00:52:39,964][87426] Updated weights for policy 1, policy_version 25390 (0.0012) -[2023-11-28 00:52:40,345][87426] Updated weights for policy 1, policy_version 25400 (0.0010) -[2023-11-28 00:52:40,901][87424] Updated weights for policy 0, policy_version 25506 (0.0011) -[2023-11-28 00:52:41,295][87424] Updated weights for policy 0, policy_version 25516 (0.0008) -[2023-11-28 00:52:41,673][87424] Updated weights for policy 0, policy_version 25526 (0.0009) -[2023-11-28 00:52:42,054][87424] Updated weights for policy 0, policy_version 25536 (0.0012) -[2023-11-28 00:52:42,803][87426] Updated weights for policy 1, policy_version 25410 (0.0011) -[2023-11-28 00:52:43,170][87426] Updated weights for policy 1, policy_version 25420 (0.0012) -[2023-11-28 00:52:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 13041664. Throughput: 0: 2718.5, 1: 2714.9. Samples: 13059088. Policy #0 lag: (min: 28.0, avg: 50.8, max: 60.0) -[2023-11-28 00:52:43,445][86177] Avg episode reward: [(0, '-557.970'), (1, '-590.960')] -[2023-11-28 00:52:43,551][87426] Updated weights for policy 1, policy_version 25430 (0.0010) -[2023-11-28 00:52:43,934][87426] Updated weights for policy 1, policy_version 25440 (0.0010) -[2023-11-28 00:52:44,311][87424] Updated weights for policy 0, policy_version 25546 (0.0008) -[2023-11-28 00:52:44,701][87424] Updated weights for policy 0, policy_version 25556 (0.0008) -[2023-11-28 00:52:45,078][87424] Updated weights for policy 0, policy_version 25566 (0.0008) -[2023-11-28 00:52:45,996][87426] Updated weights for policy 1, policy_version 25450 (0.0012) -[2023-11-28 00:52:46,375][87426] Updated weights for policy 1, policy_version 25460 (0.0012) -[2023-11-28 00:52:46,764][87426] Updated weights for policy 1, policy_version 25470 (0.0011) -[2023-11-28 00:52:47,088][87424] Updated weights for policy 0, policy_version 25576 (0.0010) -[2023-11-28 00:52:47,476][87424] Updated weights for policy 0, policy_version 25586 (0.0010) -[2023-11-28 00:52:47,854][87424] Updated weights for policy 0, policy_version 25596 (0.0009) -[2023-11-28 00:52:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13074432. Throughput: 0: 2755.2, 1: 2732.3. Samples: 13084688. Policy #0 lag: (min: 28.0, avg: 50.8, max: 60.0) -[2023-11-28 00:52:48,445][86177] Avg episode reward: [(0, '-566.420'), (1, '-611.850')] -[2023-11-28 00:52:48,530][87426] Updated weights for policy 1, policy_version 25480 (0.0008) -[2023-11-28 00:52:48,907][87426] Updated weights for policy 1, policy_version 25490 (0.0009) -[2023-11-28 00:52:49,290][87426] Updated weights for policy 1, policy_version 25500 (0.0010) -[2023-11-28 00:52:49,539][87424] Updated weights for policy 0, policy_version 25606 (0.0010) -[2023-11-28 00:52:49,922][87424] Updated weights for policy 0, policy_version 25616 (0.0012) -[2023-11-28 00:52:50,312][87424] Updated weights for policy 0, policy_version 25626 (0.0012) -[2023-11-28 00:52:51,731][87426] Updated weights for policy 1, policy_version 25510 (0.0010) -[2023-11-28 00:52:52,122][87426] Updated weights for policy 1, policy_version 25520 (0.0008) -[2023-11-28 00:52:52,503][87426] Updated weights for policy 1, policy_version 25530 (0.0009) -[2023-11-28 00:52:52,807][87424] Updated weights for policy 0, policy_version 25636 (0.0011) -[2023-11-28 00:52:53,193][87424] Updated weights for policy 0, policy_version 25646 (0.0012) -[2023-11-28 00:52:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13099008. Throughput: 0: 2737.8, 1: 2752.3. Samples: 13117604. Policy #0 lag: (min: 28.0, avg: 50.8, max: 60.0) -[2023-11-28 00:52:53,445][86177] Avg episode reward: [(0, '-559.890'), (1, '-636.840')] -[2023-11-28 00:52:53,585][87424] Updated weights for policy 0, policy_version 25656 (0.0010) -[2023-11-28 00:52:55,077][87426] Updated weights for policy 1, policy_version 25540 (0.0010) -[2023-11-28 00:52:55,456][87426] Updated weights for policy 1, policy_version 25550 (0.0012) -[2023-11-28 00:52:55,587][87424] Updated weights for policy 0, policy_version 25666 (0.0009) -[2023-11-28 00:52:55,839][87426] Updated weights for policy 1, policy_version 25560 (0.0012) -[2023-11-28 00:52:55,969][87424] Updated weights for policy 0, policy_version 25676 (0.0007) -[2023-11-28 00:52:56,358][87424] Updated weights for policy 0, policy_version 25686 (0.0007) -[2023-11-28 00:52:56,744][87424] Updated weights for policy 0, policy_version 25696 (0.0007) -[2023-11-28 00:52:57,889][87426] Updated weights for policy 1, policy_version 25570 (0.0012) -[2023-11-28 00:52:58,277][87426] Updated weights for policy 1, policy_version 25580 (0.0010) -[2023-11-28 00:52:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 13123584. Throughput: 0: 2746.6, 1: 2766.8. Samples: 13142816. Policy #0 lag: (min: 31.0, avg: 51.0, max: 94.0) -[2023-11-28 00:52:58,445][86177] Avg episode reward: [(0, '-566.790'), (1, '-606.370')] -[2023-11-28 00:52:58,662][87426] Updated weights for policy 1, policy_version 25590 (0.0011) -[2023-11-28 00:52:59,005][87424] Updated weights for policy 0, policy_version 25706 (0.0008) -[2023-11-28 00:52:59,030][87426] Updated weights for policy 1, policy_version 25600 (0.0011) -[2023-11-28 00:52:59,394][87424] Updated weights for policy 0, policy_version 25716 (0.0012) -[2023-11-28 00:52:59,770][87424] Updated weights for policy 0, policy_version 25726 (0.0012) -[2023-11-28 00:53:01,346][87426] Updated weights for policy 1, policy_version 25610 (0.0012) -[2023-11-28 00:53:01,723][87426] Updated weights for policy 1, policy_version 25620 (0.0009) -[2023-11-28 00:53:01,867][87424] Updated weights for policy 0, policy_version 25736 (0.0009) -[2023-11-28 00:53:02,094][87426] Updated weights for policy 1, policy_version 25630 (0.0010) -[2023-11-28 00:53:02,251][87424] Updated weights for policy 0, policy_version 25746 (0.0011) -[2023-11-28 00:53:02,641][87424] Updated weights for policy 0, policy_version 25756 (0.0012) -[2023-11-28 00:53:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13156352. Throughput: 0: 2753.6, 1: 2766.4. Samples: 13167168. Policy #0 lag: (min: 31.0, avg: 51.0, max: 94.0) -[2023-11-28 00:53:03,445][86177] Avg episode reward: [(0, '-551.560'), (1, '-608.500')] -[2023-11-28 00:53:03,942][87426] Updated weights for policy 1, policy_version 25640 (0.0010) -[2023-11-28 00:53:04,324][87426] Updated weights for policy 1, policy_version 25650 (0.0009) -[2023-11-28 00:53:04,401][87424] Updated weights for policy 0, policy_version 25766 (0.0010) -[2023-11-28 00:53:04,697][87426] Updated weights for policy 1, policy_version 25660 (0.0010) -[2023-11-28 00:53:04,783][87424] Updated weights for policy 0, policy_version 25776 (0.0011) -[2023-11-28 00:53:05,171][87424] Updated weights for policy 0, policy_version 25786 (0.0011) -[2023-11-28 00:53:06,934][87426] Updated weights for policy 1, policy_version 25670 (0.0012) -[2023-11-28 00:53:07,295][87424] Updated weights for policy 0, policy_version 25796 (0.0009) -[2023-11-28 00:53:07,318][87426] Updated weights for policy 1, policy_version 25680 (0.0012) -[2023-11-28 00:53:07,681][87424] Updated weights for policy 0, policy_version 25806 (0.0008) -[2023-11-28 00:53:07,691][87426] Updated weights for policy 1, policy_version 25690 (0.0011) -[2023-11-28 00:53:08,065][87424] Updated weights for policy 0, policy_version 25816 (0.0009) -[2023-11-28 00:53:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5734.4, 300 sec: 5442.8). Total num frames: 13189120. Throughput: 0: 2783.8, 1: 2773.5. Samples: 13200460. Policy #0 lag: (min: 31.0, avg: 51.0, max: 94.0) -[2023-11-28 00:53:08,445][86177] Avg episode reward: [(0, '-546.820'), (1, '-648.560')] -[2023-11-28 00:53:10,014][87424] Updated weights for policy 0, policy_version 25826 (0.0009) -[2023-11-28 00:53:10,084][87426] Updated weights for policy 1, policy_version 25700 (0.0011) -[2023-11-28 00:53:10,394][87424] Updated weights for policy 0, policy_version 25836 (0.0011) -[2023-11-28 00:53:10,455][87426] Updated weights for policy 1, policy_version 25710 (0.0011) -[2023-11-28 00:53:10,775][87424] Updated weights for policy 0, policy_version 25846 (0.0011) -[2023-11-28 00:53:10,835][87426] Updated weights for policy 1, policy_version 25720 (0.0010) -[2023-11-28 00:53:11,160][87424] Updated weights for policy 0, policy_version 25856 (0.0009) -[2023-11-28 00:53:13,331][87426] Updated weights for policy 1, policy_version 25730 (0.0009) -[2023-11-28 00:53:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 13205504. Throughput: 0: 2785.7, 1: 2729.2. Samples: 13223936. Policy #0 lag: (min: 31.0, avg: 51.0, max: 94.0) -[2023-11-28 00:53:13,445][86177] Avg episode reward: [(0, '-540.600'), (1, '-593.910')] -[2023-11-28 00:53:13,480][87424] Updated weights for policy 0, policy_version 25866 (0.0011) -[2023-11-28 00:53:13,700][87426] Updated weights for policy 1, policy_version 25740 (0.0010) -[2023-11-28 00:53:13,862][87424] Updated weights for policy 0, policy_version 25876 (0.0011) -[2023-11-28 00:53:14,073][87426] Updated weights for policy 1, policy_version 25750 (0.0011) -[2023-11-28 00:53:14,244][87424] Updated weights for policy 0, policy_version 25886 (0.0008) -[2023-11-28 00:53:14,452][87426] Updated weights for policy 1, policy_version 25760 (0.0011) -[2023-11-28 00:53:16,688][87424] Updated weights for policy 0, policy_version 25896 (0.0010) -[2023-11-28 00:53:16,823][87426] Updated weights for policy 1, policy_version 25770 (0.0008) -[2023-11-28 00:53:17,077][87424] Updated weights for policy 0, policy_version 25906 (0.0010) -[2023-11-28 00:53:17,201][87426] Updated weights for policy 1, policy_version 25780 (0.0007) -[2023-11-28 00:53:17,464][87424] Updated weights for policy 0, policy_version 25916 (0.0008) -[2023-11-28 00:53:17,592][87426] Updated weights for policy 1, policy_version 25790 (0.0007) -[2023-11-28 00:53:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13238272. Throughput: 0: 2780.8, 1: 2717.7. Samples: 13248588. Policy #0 lag: (min: 14.0, avg: 38.0, max: 46.0) -[2023-11-28 00:53:18,445][86177] Avg episode reward: [(0, '-542.250'), (1, '-639.500')] -[2023-11-28 00:53:19,440][87424] Updated weights for policy 0, policy_version 25926 (0.0010) -[2023-11-28 00:53:19,828][87424] Updated weights for policy 0, policy_version 25936 (0.0011) -[2023-11-28 00:53:20,049][87426] Updated weights for policy 1, policy_version 25800 (0.0010) -[2023-11-28 00:53:20,208][87424] Updated weights for policy 0, policy_version 25946 (0.0011) -[2023-11-28 00:53:20,440][87426] Updated weights for policy 1, policy_version 25810 (0.0009) -[2023-11-28 00:53:20,809][87426] Updated weights for policy 1, policy_version 25820 (0.0011) -[2023-11-28 00:53:22,759][87424] Updated weights for policy 0, policy_version 25956 (0.0010) -[2023-11-28 00:53:22,991][87426] Updated weights for policy 1, policy_version 25830 (0.0010) -[2023-11-28 00:53:23,138][87424] Updated weights for policy 0, policy_version 25966 (0.0011) -[2023-11-28 00:53:23,369][87426] Updated weights for policy 1, policy_version 25840 (0.0010) -[2023-11-28 00:53:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 13254656. Throughput: 0: 2747.1, 1: 2704.3. Samples: 13279932. Policy #0 lag: (min: 14.0, avg: 38.0, max: 46.0) -[2023-11-28 00:53:23,445][86177] Avg episode reward: [(0, '-540.820'), (1, '-632.610')] -[2023-11-28 00:53:23,521][87424] Updated weights for policy 0, policy_version 25976 (0.0010) -[2023-11-28 00:53:23,747][87426] Updated weights for policy 1, policy_version 25850 (0.0011) -[2023-11-28 00:53:25,543][87424] Updated weights for policy 0, policy_version 25986 (0.0010) -[2023-11-28 00:53:25,721][87426] Updated weights for policy 1, policy_version 25860 (0.0010) -[2023-11-28 00:53:25,922][87424] Updated weights for policy 0, policy_version 25996 (0.0008) -[2023-11-28 00:53:26,097][87426] Updated weights for policy 1, policy_version 25870 (0.0007) -[2023-11-28 00:53:26,309][87424] Updated weights for policy 0, policy_version 26006 (0.0007) -[2023-11-28 00:53:26,481][87426] Updated weights for policy 1, policy_version 25880 (0.0009) -[2023-11-28 00:53:26,690][87424] Updated weights for policy 0, policy_version 26016 (0.0007) -[2023-11-28 00:53:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 13287424. Throughput: 0: 2759.5, 1: 2687.8. Samples: 13304216. Policy #0 lag: (min: 14.0, avg: 38.0, max: 46.0) -[2023-11-28 00:53:28,445][86177] Avg episode reward: [(0, '-545.580'), (1, '-599.050')] -[2023-11-28 00:53:28,614][87424] Updated weights for policy 0, policy_version 26026 (0.0011) -[2023-11-28 00:53:28,977][87426] Updated weights for policy 1, policy_version 25890 (0.0011) -[2023-11-28 00:53:29,003][87424] Updated weights for policy 0, policy_version 26036 (0.0008) -[2023-11-28 00:53:29,361][87426] Updated weights for policy 1, policy_version 25900 (0.0011) -[2023-11-28 00:53:29,386][87424] Updated weights for policy 0, policy_version 26046 (0.0008) -[2023-11-28 00:53:29,743][87426] Updated weights for policy 1, policy_version 25910 (0.0012) -[2023-11-28 00:53:30,117][87426] Updated weights for policy 1, policy_version 25920 (0.0012) -[2023-11-28 00:53:31,206][87424] Updated weights for policy 0, policy_version 26056 (0.0011) -[2023-11-28 00:53:31,597][87424] Updated weights for policy 0, policy_version 26066 (0.0012) -[2023-11-28 00:53:31,978][87424] Updated weights for policy 0, policy_version 26076 (0.0011) -[2023-11-28 00:53:32,137][87426] Updated weights for policy 1, policy_version 25930 (0.0010) -[2023-11-28 00:53:32,518][87426] Updated weights for policy 1, policy_version 25940 (0.0012) -[2023-11-28 00:53:32,887][87426] Updated weights for policy 1, policy_version 25950 (0.0012) -[2023-11-28 00:53:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 13320192. Throughput: 0: 2742.7, 1: 2686.2. Samples: 13328988. Policy #0 lag: (min: 14.0, avg: 38.0, max: 46.0) -[2023-11-28 00:53:33,445][86177] Avg episode reward: [(0, '-546.670'), (1, '-580.880')] -[2023-11-28 00:53:34,480][87424] Updated weights for policy 0, policy_version 26086 (0.0010) -[2023-11-28 00:53:34,558][87426] Updated weights for policy 1, policy_version 25960 (0.0012) -[2023-11-28 00:53:34,868][87424] Updated weights for policy 0, policy_version 26096 (0.0010) -[2023-11-28 00:53:34,939][87426] Updated weights for policy 1, policy_version 25970 (0.0011) -[2023-11-28 00:53:35,246][87424] Updated weights for policy 0, policy_version 26106 (0.0010) -[2023-11-28 00:53:35,321][87426] Updated weights for policy 1, policy_version 25980 (0.0009) -[2023-11-28 00:53:37,098][87426] Updated weights for policy 1, policy_version 25990 (0.0011) -[2023-11-28 00:53:37,222][87424] Updated weights for policy 0, policy_version 26116 (0.0012) -[2023-11-28 00:53:37,479][87426] Updated weights for policy 1, policy_version 26000 (0.0008) -[2023-11-28 00:53:37,611][87424] Updated weights for policy 0, policy_version 26126 (0.0012) -[2023-11-28 00:53:37,850][87426] Updated weights for policy 1, policy_version 26010 (0.0008) -[2023-11-28 00:53:37,988][87424] Updated weights for policy 0, policy_version 26136 (0.0012) -[2023-11-28 00:53:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 13352960. Throughput: 0: 2754.7, 1: 2704.2. Samples: 13363252. Policy #0 lag: (min: 31.0, avg: 47.7, max: 71.0) -[2023-11-28 00:53:38,445][86177] Avg episode reward: [(0, '-535.960'), (1, '-541.480')] -[2023-11-28 00:53:39,691][87426] Updated weights for policy 1, policy_version 26020 (0.0012) -[2023-11-28 00:53:40,075][87426] Updated weights for policy 1, policy_version 26030 (0.0011) -[2023-11-28 00:53:40,447][87426] Updated weights for policy 1, policy_version 26040 (0.0010) -[2023-11-28 00:53:40,535][87424] Updated weights for policy 0, policy_version 26146 (0.0011) -[2023-11-28 00:53:40,920][87424] Updated weights for policy 0, policy_version 26156 (0.0008) -[2023-11-28 00:53:41,298][87424] Updated weights for policy 0, policy_version 26166 (0.0008) -[2023-11-28 00:53:41,683][87424] Updated weights for policy 0, policy_version 26176 (0.0008) -[2023-11-28 00:53:42,286][87426] Updated weights for policy 1, policy_version 26050 (0.0010) -[2023-11-28 00:53:42,662][87426] Updated weights for policy 1, policy_version 26060 (0.0007) -[2023-11-28 00:53:43,040][87426] Updated weights for policy 1, policy_version 26070 (0.0009) -[2023-11-28 00:53:43,417][87426] Updated weights for policy 1, policy_version 26080 (0.0012) -[2023-11-28 00:53:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 13377536. Throughput: 0: 2734.9, 1: 2704.1. Samples: 13387572. Policy #0 lag: (min: 31.0, avg: 47.7, max: 71.0) -[2023-11-28 00:53:43,445][86177] Avg episode reward: [(0, '-538.260'), (1, '-560.720')] -[2023-11-28 00:53:43,714][87424] Updated weights for policy 0, policy_version 26186 (0.0007) -[2023-11-28 00:53:44,099][87424] Updated weights for policy 0, policy_version 26196 (0.0009) -[2023-11-28 00:53:44,484][87424] Updated weights for policy 0, policy_version 26206 (0.0010) -[2023-11-28 00:53:45,957][87426] Updated weights for policy 1, policy_version 26090 (0.0011) -[2023-11-28 00:53:46,325][87426] Updated weights for policy 1, policy_version 26100 (0.0011) -[2023-11-28 00:53:46,714][87426] Updated weights for policy 1, policy_version 26110 (0.0011) -[2023-11-28 00:53:46,912][87424] Updated weights for policy 0, policy_version 26216 (0.0008) -[2023-11-28 00:53:47,296][87424] Updated weights for policy 0, policy_version 26226 (0.0007) -[2023-11-28 00:53:47,687][87424] Updated weights for policy 0, policy_version 26236 (0.0007) -[2023-11-28 00:53:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13402112. Throughput: 0: 2725.1, 1: 2711.1. Samples: 13411796. Policy #0 lag: (min: 31.0, avg: 47.7, max: 71.0) -[2023-11-28 00:53:48,445][86177] Avg episode reward: [(0, '-529.750'), (1, '-561.050')] -[2023-11-28 00:53:49,308][87426] Updated weights for policy 1, policy_version 26120 (0.0012) -[2023-11-28 00:53:49,685][87426] Updated weights for policy 1, policy_version 26130 (0.0012) -[2023-11-28 00:53:50,051][87424] Updated weights for policy 0, policy_version 26246 (0.0010) -[2023-11-28 00:53:50,062][87426] Updated weights for policy 1, policy_version 26140 (0.0010) -[2023-11-28 00:53:50,435][87424] Updated weights for policy 0, policy_version 26256 (0.0010) -[2023-11-28 00:53:50,822][87424] Updated weights for policy 0, policy_version 26266 (0.0009) -[2023-11-28 00:53:52,518][87426] Updated weights for policy 1, policy_version 26150 (0.0009) -[2023-11-28 00:53:52,898][87426] Updated weights for policy 1, policy_version 26160 (0.0011) -[2023-11-28 00:53:53,009][87424] Updated weights for policy 0, policy_version 26276 (0.0012) -[2023-11-28 00:53:53,276][87426] Updated weights for policy 1, policy_version 26170 (0.0009) -[2023-11-28 00:53:53,403][87424] Updated weights for policy 0, policy_version 26286 (0.0011) -[2023-11-28 00:53:53,444][86177] Fps is (10 sec: 4096.0, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 13418496. Throughput: 0: 2718.0, 1: 2698.7. Samples: 13444208. Policy #0 lag: (min: 31.0, avg: 47.7, max: 71.0) -[2023-11-28 00:53:53,445][86177] Avg episode reward: [(0, '-535.600'), (1, '-556.380')] -[2023-11-28 00:53:53,788][87424] Updated weights for policy 0, policy_version 26296 (0.0012) -[2023-11-28 00:53:55,766][87424] Updated weights for policy 0, policy_version 26306 (0.0012) -[2023-11-28 00:53:55,857][87426] Updated weights for policy 1, policy_version 26180 (0.0008) -[2023-11-28 00:53:56,150][87424] Updated weights for policy 0, policy_version 26316 (0.0012) -[2023-11-28 00:53:56,237][87426] Updated weights for policy 1, policy_version 26190 (0.0008) -[2023-11-28 00:53:56,530][87424] Updated weights for policy 0, policy_version 26326 (0.0011) -[2023-11-28 00:53:56,623][87426] Updated weights for policy 1, policy_version 26200 (0.0007) -[2023-11-28 00:53:56,910][87424] Updated weights for policy 0, policy_version 26336 (0.0011) -[2023-11-28 00:53:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13451264. Throughput: 0: 2727.6, 1: 2690.8. Samples: 13467760. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 00:53:58,445][86177] Avg episode reward: [(0, '-549.740'), (1, '-636.870')] -[2023-11-28 00:53:58,725][87424] Updated weights for policy 0, policy_version 26346 (0.0007) -[2023-11-28 00:53:59,058][87426] Updated weights for policy 1, policy_version 26210 (0.0008) -[2023-11-28 00:53:59,117][87424] Updated weights for policy 0, policy_version 26356 (0.0010) -[2023-11-28 00:53:59,450][87426] Updated weights for policy 1, policy_version 26220 (0.0011) -[2023-11-28 00:53:59,496][87424] Updated weights for policy 0, policy_version 26366 (0.0012) -[2023-11-28 00:53:59,825][87426] Updated weights for policy 1, policy_version 26230 (0.0008) -[2023-11-28 00:54:00,197][87426] Updated weights for policy 1, policy_version 26240 (0.0009) -[2023-11-28 00:54:01,322][87424] Updated weights for policy 0, policy_version 26376 (0.0011) -[2023-11-28 00:54:01,707][87424] Updated weights for policy 0, policy_version 26386 (0.0011) -[2023-11-28 00:54:02,091][87424] Updated weights for policy 0, policy_version 26396 (0.0012) -[2023-11-28 00:54:02,715][87426] Updated weights for policy 1, policy_version 26250 (0.0007) -[2023-11-28 00:54:03,092][87426] Updated weights for policy 1, policy_version 26260 (0.0011) -[2023-11-28 00:54:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 13475840. Throughput: 0: 2735.8, 1: 2673.7. Samples: 13492016. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 00:54:03,445][86177] Avg episode reward: [(0, '-546.160'), (1, '-638.820')] -[2023-11-28 00:54:03,470][87426] Updated weights for policy 1, policy_version 26270 (0.0012) -[2023-11-28 00:54:03,998][87424] Updated weights for policy 0, policy_version 26406 (0.0011) -[2023-11-28 00:54:04,380][87424] Updated weights for policy 0, policy_version 26416 (0.0008) -[2023-11-28 00:54:04,759][87424] Updated weights for policy 0, policy_version 26426 (0.0007) -[2023-11-28 00:54:05,542][87426] Updated weights for policy 1, policy_version 26280 (0.0011) -[2023-11-28 00:54:05,919][87426] Updated weights for policy 1, policy_version 26290 (0.0010) -[2023-11-28 00:54:06,307][87426] Updated weights for policy 1, policy_version 26300 (0.0007) -[2023-11-28 00:54:06,556][87424] Updated weights for policy 0, policy_version 26436 (0.0008) -[2023-11-28 00:54:06,947][87424] Updated weights for policy 0, policy_version 26446 (0.0008) -[2023-11-28 00:54:07,329][87424] Updated weights for policy 0, policy_version 26456 (0.0011) -[2023-11-28 00:54:08,341][87426] Updated weights for policy 1, policy_version 26310 (0.0009) -[2023-11-28 00:54:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13508608. Throughput: 0: 2739.4, 1: 2692.2. Samples: 13524352. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 00:54:08,445][86177] Avg episode reward: [(0, '-554.090'), (1, '-636.700')] -[2023-11-28 00:54:08,718][87426] Updated weights for policy 1, policy_version 26320 (0.0009) -[2023-11-28 00:54:09,097][87426] Updated weights for policy 1, policy_version 26330 (0.0011) -[2023-11-28 00:54:09,907][87424] Updated weights for policy 0, policy_version 26466 (0.0011) -[2023-11-28 00:54:10,285][87424] Updated weights for policy 0, policy_version 26476 (0.0012) -[2023-11-28 00:54:10,674][87424] Updated weights for policy 0, policy_version 26486 (0.0010) -[2023-11-28 00:54:11,054][87424] Updated weights for policy 0, policy_version 26496 (0.0010) -[2023-11-28 00:54:11,475][87426] Updated weights for policy 1, policy_version 26340 (0.0011) -[2023-11-28 00:54:11,857][87426] Updated weights for policy 1, policy_version 26350 (0.0011) -[2023-11-28 00:54:12,237][87426] Updated weights for policy 1, policy_version 26360 (0.0012) -[2023-11-28 00:54:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13533184. Throughput: 0: 2741.2, 1: 2693.2. Samples: 13548768. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 00:54:13,445][86177] Avg episode reward: [(0, '-545.680'), (1, '-648.150')] -[2023-11-28 00:54:13,596][87424] Updated weights for policy 0, policy_version 26506 (0.0010) -[2023-11-28 00:54:13,985][87424] Updated weights for policy 0, policy_version 26516 (0.0007) -[2023-11-28 00:54:14,279][87426] Updated weights for policy 1, policy_version 26370 (0.0011) -[2023-11-28 00:54:14,367][87424] Updated weights for policy 0, policy_version 26526 (0.0007) -[2023-11-28 00:54:14,662][87426] Updated weights for policy 1, policy_version 26380 (0.0008) -[2023-11-28 00:54:15,045][87426] Updated weights for policy 1, policy_version 26390 (0.0007) -[2023-11-28 00:54:15,428][87426] Updated weights for policy 1, policy_version 26400 (0.0012) -[2023-11-28 00:54:16,117][87424] Updated weights for policy 0, policy_version 26536 (0.0011) -[2023-11-28 00:54:16,495][87424] Updated weights for policy 0, policy_version 26546 (0.0012) -[2023-11-28 00:54:16,880][87424] Updated weights for policy 0, policy_version 26556 (0.0012) -[2023-11-28 00:54:17,355][87426] Updated weights for policy 1, policy_version 26410 (0.0012) -[2023-11-28 00:54:17,744][87426] Updated weights for policy 1, policy_version 26420 (0.0012) -[2023-11-28 00:54:18,141][87426] Updated weights for policy 1, policy_version 26430 (0.0011) -[2023-11-28 00:54:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13565952. Throughput: 0: 2742.4, 1: 2694.9. Samples: 13573668. Policy #0 lag: (min: 31.0, avg: 49.2, max: 63.0) -[2023-11-28 00:54:18,445][86177] Avg episode reward: [(0, '-530.960'), (1, '-647.870')] -[2023-11-28 00:54:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000026560_6799360.pth... -[2023-11-28 00:54:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000026432_6766592.pth... -[2023-11-28 00:54:18,486][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000023872_6111232.pth -[2023-11-28 00:54:18,486][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000024032_6152192.pth -[2023-11-28 00:54:19,311][87424] Updated weights for policy 0, policy_version 26566 (0.0012) -[2023-11-28 00:54:19,692][87424] Updated weights for policy 0, policy_version 26576 (0.0010) -[2023-11-28 00:54:20,071][87424] Updated weights for policy 0, policy_version 26586 (0.0012) -[2023-11-28 00:54:20,458][87426] Updated weights for policy 1, policy_version 26440 (0.0010) -[2023-11-28 00:54:20,840][87426] Updated weights for policy 1, policy_version 26450 (0.0011) -[2023-11-28 00:54:21,220][87426] Updated weights for policy 1, policy_version 26460 (0.0010) -[2023-11-28 00:54:21,950][87424] Updated weights for policy 0, policy_version 26596 (0.0012) -[2023-11-28 00:54:22,360][87424] Updated weights for policy 0, policy_version 26606 (0.0012) -[2023-11-28 00:54:22,728][87424] Updated weights for policy 0, policy_version 26616 (0.0012) -[2023-11-28 00:54:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 13590528. Throughput: 0: 2708.4, 1: 2675.9. Samples: 13605544. Policy #0 lag: (min: 31.0, avg: 49.2, max: 63.0) -[2023-11-28 00:54:23,445][86177] Avg episode reward: [(0, '-531.640'), (1, '-644.760')] -[2023-11-28 00:54:23,468][87426] Updated weights for policy 1, policy_version 26470 (0.0011) -[2023-11-28 00:54:23,839][87426] Updated weights for policy 1, policy_version 26480 (0.0009) -[2023-11-28 00:54:24,222][87426] Updated weights for policy 1, policy_version 26490 (0.0009) -[2023-11-28 00:54:24,820][87424] Updated weights for policy 0, policy_version 26626 (0.0012) -[2023-11-28 00:54:25,194][87424] Updated weights for policy 0, policy_version 26636 (0.0012) -[2023-11-28 00:54:25,585][87424] Updated weights for policy 0, policy_version 26646 (0.0011) -[2023-11-28 00:54:25,969][87424] Updated weights for policy 0, policy_version 26656 (0.0012) -[2023-11-28 00:54:26,399][87426] Updated weights for policy 1, policy_version 26500 (0.0010) -[2023-11-28 00:54:26,784][87426] Updated weights for policy 1, policy_version 26510 (0.0009) -[2023-11-28 00:54:27,162][87426] Updated weights for policy 1, policy_version 26520 (0.0007) -[2023-11-28 00:54:28,048][87424] Updated weights for policy 0, policy_version 26666 (0.0012) -[2023-11-28 00:54:28,432][87424] Updated weights for policy 0, policy_version 26676 (0.0012) -[2023-11-28 00:54:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13615104. Throughput: 0: 2715.2, 1: 2664.1. Samples: 13629640. Policy #0 lag: (min: 31.0, avg: 49.2, max: 63.0) -[2023-11-28 00:54:28,445][86177] Avg episode reward: [(0, '-520.840'), (1, '-657.780')] -[2023-11-28 00:54:28,825][87424] Updated weights for policy 0, policy_version 26686 (0.0012) -[2023-11-28 00:54:29,394][87426] Updated weights for policy 1, policy_version 26530 (0.0009) -[2023-11-28 00:54:29,775][87426] Updated weights for policy 1, policy_version 26540 (0.0010) -[2023-11-28 00:54:30,152][87426] Updated weights for policy 1, policy_version 26550 (0.0008) -[2023-11-28 00:54:30,576][87426] Updated weights for policy 1, policy_version 26560 (0.0010) -[2023-11-28 00:54:30,834][87424] Updated weights for policy 0, policy_version 26696 (0.0008) -[2023-11-28 00:54:31,215][87424] Updated weights for policy 0, policy_version 26706 (0.0008) -[2023-11-28 00:54:31,597][87424] Updated weights for policy 0, policy_version 26716 (0.0007) -[2023-11-28 00:54:32,879][87426] Updated weights for policy 1, policy_version 26570 (0.0008) -[2023-11-28 00:54:33,257][87426] Updated weights for policy 1, policy_version 26580 (0.0008) -[2023-11-28 00:54:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 13639680. Throughput: 0: 2740.8, 1: 2663.7. Samples: 13655000. Policy #0 lag: (min: 31.0, avg: 49.2, max: 63.0) -[2023-11-28 00:54:33,445][86177] Avg episode reward: [(0, '-530.130'), (1, '-661.310')] -[2023-11-28 00:54:33,649][87426] Updated weights for policy 1, policy_version 26590 (0.0008) -[2023-11-28 00:54:33,671][87424] Updated weights for policy 0, policy_version 26726 (0.0010) -[2023-11-28 00:54:34,052][87424] Updated weights for policy 0, policy_version 26736 (0.0012) -[2023-11-28 00:54:34,433][87424] Updated weights for policy 0, policy_version 26746 (0.0011) -[2023-11-28 00:54:35,678][87426] Updated weights for policy 1, policy_version 26600 (0.0011) -[2023-11-28 00:54:36,054][87426] Updated weights for policy 1, policy_version 26610 (0.0012) -[2023-11-28 00:54:36,361][87424] Updated weights for policy 0, policy_version 26756 (0.0010) -[2023-11-28 00:54:36,438][87426] Updated weights for policy 1, policy_version 26620 (0.0010) -[2023-11-28 00:54:36,744][87424] Updated weights for policy 0, policy_version 26766 (0.0011) -[2023-11-28 00:54:37,123][87424] Updated weights for policy 0, policy_version 26776 (0.0012) -[2023-11-28 00:54:38,095][87426] Updated weights for policy 1, policy_version 26630 (0.0010) -[2023-11-28 00:54:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13672448. Throughput: 0: 2729.5, 1: 2689.5. Samples: 13688064. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) -[2023-11-28 00:54:38,445][86177] Avg episode reward: [(0, '-524.830'), (1, '-611.740')] -[2023-11-28 00:54:38,471][87426] Updated weights for policy 1, policy_version 26640 (0.0012) -[2023-11-28 00:54:38,853][87426] Updated weights for policy 1, policy_version 26650 (0.0011) -[2023-11-28 00:54:39,661][87424] Updated weights for policy 0, policy_version 26786 (0.0010) -[2023-11-28 00:54:40,031][87424] Updated weights for policy 0, policy_version 26796 (0.0009) -[2023-11-28 00:54:40,408][87424] Updated weights for policy 0, policy_version 26806 (0.0012) -[2023-11-28 00:54:40,796][87424] Updated weights for policy 0, policy_version 26816 (0.0012) -[2023-11-28 00:54:41,293][87426] Updated weights for policy 1, policy_version 26660 (0.0011) -[2023-11-28 00:54:41,675][87426] Updated weights for policy 1, policy_version 26670 (0.0012) -[2023-11-28 00:54:42,053][87426] Updated weights for policy 1, policy_version 26680 (0.0012) -[2023-11-28 00:54:43,053][87424] Updated weights for policy 0, policy_version 26826 (0.0012) -[2023-11-28 00:54:43,438][87424] Updated weights for policy 0, policy_version 26836 (0.0012) -[2023-11-28 00:54:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13697024. Throughput: 0: 2709.8, 1: 2705.2. Samples: 13711432. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) -[2023-11-28 00:54:43,445][86177] Avg episode reward: [(0, '-519.430'), (1, '-578.770')] -[2023-11-28 00:54:43,830][87424] Updated weights for policy 0, policy_version 26846 (0.0012) -[2023-11-28 00:54:44,631][87426] Updated weights for policy 1, policy_version 26690 (0.0011) -[2023-11-28 00:54:45,023][87426] Updated weights for policy 1, policy_version 26700 (0.0007) -[2023-11-28 00:54:45,408][87426] Updated weights for policy 1, policy_version 26710 (0.0009) -[2023-11-28 00:54:45,785][87426] Updated weights for policy 1, policy_version 26720 (0.0011) -[2023-11-28 00:54:46,055][87424] Updated weights for policy 0, policy_version 26856 (0.0010) -[2023-11-28 00:54:46,440][87424] Updated weights for policy 0, policy_version 26866 (0.0009) -[2023-11-28 00:54:46,842][87424] Updated weights for policy 0, policy_version 26876 (0.0010) -[2023-11-28 00:54:48,310][87426] Updated weights for policy 1, policy_version 26730 (0.0011) -[2023-11-28 00:54:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 13721600. Throughput: 0: 2721.2, 1: 2713.3. Samples: 13736568. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) -[2023-11-28 00:54:48,445][86177] Avg episode reward: [(0, '-516.500'), (1, '-565.180')] -[2023-11-28 00:54:48,680][87426] Updated weights for policy 1, policy_version 26740 (0.0009) -[2023-11-28 00:54:49,064][87426] Updated weights for policy 1, policy_version 26750 (0.0008) -[2023-11-28 00:54:49,374][87424] Updated weights for policy 0, policy_version 26886 (0.0009) -[2023-11-28 00:54:49,756][87424] Updated weights for policy 0, policy_version 26896 (0.0010) -[2023-11-28 00:54:50,139][87424] Updated weights for policy 0, policy_version 26906 (0.0009) -[2023-11-28 00:54:51,382][87426] Updated weights for policy 1, policy_version 26760 (0.0011) -[2023-11-28 00:54:51,768][87426] Updated weights for policy 1, policy_version 26770 (0.0012) -[2023-11-28 00:54:52,026][87424] Updated weights for policy 0, policy_version 26916 (0.0009) -[2023-11-28 00:54:52,142][87426] Updated weights for policy 1, policy_version 26780 (0.0011) -[2023-11-28 00:54:52,410][87424] Updated weights for policy 0, policy_version 26926 (0.0011) -[2023-11-28 00:54:52,788][87424] Updated weights for policy 0, policy_version 26936 (0.0012) -[2023-11-28 00:54:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 13754368. Throughput: 0: 2721.4, 1: 2677.6. Samples: 13767308. Policy #0 lag: (min: 22.0, avg: 29.8, max: 54.0) -[2023-11-28 00:54:53,445][86177] Avg episode reward: [(0, '-513.060'), (1, '-567.060')] -[2023-11-28 00:54:54,241][87426] Updated weights for policy 1, policy_version 26790 (0.0009) -[2023-11-28 00:54:54,620][87426] Updated weights for policy 1, policy_version 26800 (0.0009) -[2023-11-28 00:54:55,001][87426] Updated weights for policy 1, policy_version 26810 (0.0009) -[2023-11-28 00:54:55,304][87424] Updated weights for policy 0, policy_version 26946 (0.0011) -[2023-11-28 00:54:55,688][87424] Updated weights for policy 0, policy_version 26956 (0.0009) -[2023-11-28 00:54:56,072][87424] Updated weights for policy 0, policy_version 26966 (0.0010) -[2023-11-28 00:54:56,463][87424] Updated weights for policy 0, policy_version 26976 (0.0008) -[2023-11-28 00:54:56,981][87426] Updated weights for policy 1, policy_version 26820 (0.0008) -[2023-11-28 00:54:57,354][87426] Updated weights for policy 1, policy_version 26830 (0.0007) -[2023-11-28 00:54:57,736][87426] Updated weights for policy 1, policy_version 26840 (0.0008) -[2023-11-28 00:54:58,248][87424] Updated weights for policy 0, policy_version 26986 (0.0008) -[2023-11-28 00:54:58,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13778944. Throughput: 0: 2697.6, 1: 2702.1. Samples: 13791756. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 00:54:58,446][86177] Avg episode reward: [(0, '-515.810'), (1, '-565.720')] -[2023-11-28 00:54:58,629][87424] Updated weights for policy 0, policy_version 26996 (0.0008) -[2023-11-28 00:54:59,011][87424] Updated weights for policy 0, policy_version 27006 (0.0008) -[2023-11-28 00:55:00,037][87426] Updated weights for policy 1, policy_version 26850 (0.0007) -[2023-11-28 00:55:00,415][87426] Updated weights for policy 1, policy_version 26860 (0.0008) -[2023-11-28 00:55:00,799][87426] Updated weights for policy 1, policy_version 26870 (0.0007) -[2023-11-28 00:55:01,182][87426] Updated weights for policy 1, policy_version 26880 (0.0008) -[2023-11-28 00:55:01,344][87424] Updated weights for policy 0, policy_version 27016 (0.0011) -[2023-11-28 00:55:01,725][87424] Updated weights for policy 0, policy_version 27026 (0.0012) -[2023-11-28 00:55:02,106][87424] Updated weights for policy 0, policy_version 27036 (0.0012) -[2023-11-28 00:55:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 13803520. Throughput: 0: 2675.0, 1: 2698.1. Samples: 13815460. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 00:55:03,445][86177] Avg episode reward: [(0, '-528.000'), (1, '-563.560')] -[2023-11-28 00:55:03,492][87426] Updated weights for policy 1, policy_version 26890 (0.0011) -[2023-11-28 00:55:03,875][87426] Updated weights for policy 1, policy_version 26900 (0.0012) -[2023-11-28 00:55:04,258][87426] Updated weights for policy 1, policy_version 26910 (0.0012) -[2023-11-28 00:55:04,431][87424] Updated weights for policy 0, policy_version 27046 (0.0012) -[2023-11-28 00:55:04,820][87424] Updated weights for policy 0, policy_version 27056 (0.0012) -[2023-11-28 00:55:05,200][87424] Updated weights for policy 0, policy_version 27066 (0.0012) -[2023-11-28 00:55:05,836][87426] Updated weights for policy 1, policy_version 26920 (0.0008) -[2023-11-28 00:55:06,215][87426] Updated weights for policy 1, policy_version 26930 (0.0007) -[2023-11-28 00:55:06,590][87426] Updated weights for policy 1, policy_version 26940 (0.0007) -[2023-11-28 00:55:07,485][87424] Updated weights for policy 0, policy_version 27076 (0.0012) -[2023-11-28 00:55:07,875][87424] Updated weights for policy 0, policy_version 27086 (0.0012) -[2023-11-28 00:55:08,255][87424] Updated weights for policy 0, policy_version 27096 (0.0012) -[2023-11-28 00:55:08,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13828096. Throughput: 0: 2700.4, 1: 2686.9. Samples: 13847968. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 00:55:08,445][86177] Avg episode reward: [(0, '-538.960'), (1, '-568.250')] -[2023-11-28 00:55:08,852][87426] Updated weights for policy 1, policy_version 26950 (0.0010) -[2023-11-28 00:55:09,231][87426] Updated weights for policy 1, policy_version 26960 (0.0011) -[2023-11-28 00:55:09,610][87426] Updated weights for policy 1, policy_version 26970 (0.0012) -[2023-11-28 00:55:10,470][87424] Updated weights for policy 0, policy_version 27106 (0.0011) -[2023-11-28 00:55:10,851][87424] Updated weights for policy 0, policy_version 27116 (0.0011) -[2023-11-28 00:55:11,240][87424] Updated weights for policy 0, policy_version 27126 (0.0011) -[2023-11-28 00:55:11,593][87426] Updated weights for policy 1, policy_version 26980 (0.0012) -[2023-11-28 00:55:11,616][87424] Updated weights for policy 0, policy_version 27136 (0.0012) -[2023-11-28 00:55:11,965][87426] Updated weights for policy 1, policy_version 26990 (0.0012) -[2023-11-28 00:55:12,346][87426] Updated weights for policy 1, policy_version 27000 (0.0012) -[2023-11-28 00:55:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13860864. Throughput: 0: 2706.0, 1: 2690.8. Samples: 13872496. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 00:55:13,445][86177] Avg episode reward: [(0, '-537.820'), (1, '-570.060')] -[2023-11-28 00:55:14,083][87424] Updated weights for policy 0, policy_version 27146 (0.0007) -[2023-11-28 00:55:14,465][87424] Updated weights for policy 0, policy_version 27156 (0.0008) -[2023-11-28 00:55:14,615][87426] Updated weights for policy 1, policy_version 27010 (0.0010) -[2023-11-28 00:55:14,848][87424] Updated weights for policy 0, policy_version 27166 (0.0009) -[2023-11-28 00:55:15,003][87426] Updated weights for policy 1, policy_version 27020 (0.0011) -[2023-11-28 00:55:15,371][87426] Updated weights for policy 1, policy_version 27030 (0.0011) -[2023-11-28 00:55:15,751][87426] Updated weights for policy 1, policy_version 27040 (0.0010) -[2023-11-28 00:55:17,100][87424] Updated weights for policy 0, policy_version 27176 (0.0009) -[2023-11-28 00:55:17,486][87424] Updated weights for policy 0, policy_version 27186 (0.0011) -[2023-11-28 00:55:17,870][87424] Updated weights for policy 0, policy_version 27196 (0.0010) -[2023-11-28 00:55:18,090][87426] Updated weights for policy 1, policy_version 27050 (0.0009) -[2023-11-28 00:55:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 13885440. Throughput: 0: 2702.4, 1: 2696.8. Samples: 13897964. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 00:55:18,445][86177] Avg episode reward: [(0, '-537.550'), (1, '-562.910')] -[2023-11-28 00:55:18,481][87426] Updated weights for policy 1, policy_version 27060 (0.0007) -[2023-11-28 00:55:18,851][87426] Updated weights for policy 1, policy_version 27070 (0.0009) -[2023-11-28 00:55:19,938][87424] Updated weights for policy 0, policy_version 27206 (0.0009) -[2023-11-28 00:55:20,316][87424] Updated weights for policy 0, policy_version 27216 (0.0011) -[2023-11-28 00:55:20,714][87424] Updated weights for policy 0, policy_version 27226 (0.0009) -[2023-11-28 00:55:20,843][87426] Updated weights for policy 1, policy_version 27080 (0.0012) -[2023-11-28 00:55:21,221][87426] Updated weights for policy 1, policy_version 27090 (0.0012) -[2023-11-28 00:55:21,605][87426] Updated weights for policy 1, policy_version 27100 (0.0012) -[2023-11-28 00:55:23,279][87424] Updated weights for policy 0, policy_version 27236 (0.0009) -[2023-11-28 00:55:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 13910016. Throughput: 0: 2718.2, 1: 2678.4. Samples: 13930912. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 00:55:23,445][86177] Avg episode reward: [(0, '-532.390'), (1, '-572.640')] -[2023-11-28 00:55:23,658][87424] Updated weights for policy 0, policy_version 27246 (0.0012) -[2023-11-28 00:55:23,958][87426] Updated weights for policy 1, policy_version 27110 (0.0010) -[2023-11-28 00:55:24,048][87424] Updated weights for policy 0, policy_version 27256 (0.0011) -[2023-11-28 00:55:24,340][87426] Updated weights for policy 1, policy_version 27120 (0.0007) -[2023-11-28 00:55:24,719][87426] Updated weights for policy 1, policy_version 27130 (0.0007) -[2023-11-28 00:55:26,162][87424] Updated weights for policy 0, policy_version 27266 (0.0011) -[2023-11-28 00:55:26,543][87424] Updated weights for policy 0, policy_version 27276 (0.0008) -[2023-11-28 00:55:26,935][87424] Updated weights for policy 0, policy_version 27286 (0.0009) -[2023-11-28 00:55:27,009][87426] Updated weights for policy 1, policy_version 27140 (0.0009) -[2023-11-28 00:55:27,319][87424] Updated weights for policy 0, policy_version 27296 (0.0010) -[2023-11-28 00:55:27,387][87426] Updated weights for policy 1, policy_version 27150 (0.0011) -[2023-11-28 00:55:27,765][87426] Updated weights for policy 1, policy_version 27160 (0.0009) -[2023-11-28 00:55:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 13942784. Throughput: 0: 2720.9, 1: 2690.5. Samples: 13954944. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 00:55:28,445][86177] Avg episode reward: [(0, '-515.310'), (1, '-557.170')] -[2023-11-28 00:55:28,998][87424] Updated weights for policy 0, policy_version 27306 (0.0011) -[2023-11-28 00:55:29,377][87424] Updated weights for policy 0, policy_version 27316 (0.0012) -[2023-11-28 00:55:29,762][87424] Updated weights for policy 0, policy_version 27326 (0.0012) -[2023-11-28 00:55:30,097][87426] Updated weights for policy 1, policy_version 27170 (0.0008) -[2023-11-28 00:55:30,479][87426] Updated weights for policy 1, policy_version 27180 (0.0011) -[2023-11-28 00:55:30,857][87426] Updated weights for policy 1, policy_version 27190 (0.0010) -[2023-11-28 00:55:31,228][87426] Updated weights for policy 1, policy_version 27200 (0.0012) -[2023-11-28 00:55:32,350][87424] Updated weights for policy 0, policy_version 27336 (0.0011) -[2023-11-28 00:55:32,751][87424] Updated weights for policy 0, policy_version 27346 (0.0012) -[2023-11-28 00:55:33,126][87424] Updated weights for policy 0, policy_version 27356 (0.0012) -[2023-11-28 00:55:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 13967360. Throughput: 0: 2710.5, 1: 2677.1. Samples: 13979008. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 00:55:33,445][86177] Avg episode reward: [(0, '-516.440'), (1, '-537.150')] -[2023-11-28 00:55:33,596][87426] Updated weights for policy 1, policy_version 27210 (0.0012) -[2023-11-28 00:55:33,975][87426] Updated weights for policy 1, policy_version 27220 (0.0012) -[2023-11-28 00:55:34,365][87426] Updated weights for policy 1, policy_version 27230 (0.0011) -[2023-11-28 00:55:34,776][87424] Updated weights for policy 0, policy_version 27366 (0.0012) -[2023-11-28 00:55:35,159][87424] Updated weights for policy 0, policy_version 27376 (0.0011) -[2023-11-28 00:55:35,548][87424] Updated weights for policy 0, policy_version 27386 (0.0012) -[2023-11-28 00:55:36,409][87426] Updated weights for policy 1, policy_version 27240 (0.0012) -[2023-11-28 00:55:36,785][87426] Updated weights for policy 1, policy_version 27250 (0.0012) -[2023-11-28 00:55:37,167][87426] Updated weights for policy 1, policy_version 27260 (0.0012) -[2023-11-28 00:55:37,508][87424] Updated weights for policy 0, policy_version 27396 (0.0012) -[2023-11-28 00:55:37,899][87424] Updated weights for policy 0, policy_version 27406 (0.0012) -[2023-11-28 00:55:38,289][87424] Updated weights for policy 0, policy_version 27416 (0.0012) -[2023-11-28 00:55:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 13991936. Throughput: 0: 2722.3, 1: 2701.2. Samples: 14011368. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 00:55:38,445][86177] Avg episode reward: [(0, '-515.200'), (1, '-533.660')] -[2023-11-28 00:55:39,756][87426] Updated weights for policy 1, policy_version 27270 (0.0010) -[2023-11-28 00:55:40,137][87426] Updated weights for policy 1, policy_version 27280 (0.0011) -[2023-11-28 00:55:40,524][87426] Updated weights for policy 1, policy_version 27290 (0.0011) -[2023-11-28 00:55:40,722][87424] Updated weights for policy 0, policy_version 27426 (0.0012) -[2023-11-28 00:55:41,096][87424] Updated weights for policy 0, policy_version 27436 (0.0012) -[2023-11-28 00:55:41,477][87424] Updated weights for policy 0, policy_version 27446 (0.0012) -[2023-11-28 00:55:41,867][87424] Updated weights for policy 0, policy_version 27456 (0.0011) -[2023-11-28 00:55:42,379][87426] Updated weights for policy 1, policy_version 27300 (0.0012) -[2023-11-28 00:55:42,760][87426] Updated weights for policy 1, policy_version 27310 (0.0012) -[2023-11-28 00:55:43,133][87426] Updated weights for policy 1, policy_version 27320 (0.0012) -[2023-11-28 00:55:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 14024704. Throughput: 0: 2725.4, 1: 2687.0. Samples: 14035312. Policy #0 lag: (min: 31.0, avg: 51.9, max: 77.0) -[2023-11-28 00:55:43,445][86177] Avg episode reward: [(0, '-513.810'), (1, '-520.320')] -[2023-11-28 00:55:43,912][87424] Updated weights for policy 0, policy_version 27466 (0.0012) -[2023-11-28 00:55:44,293][87424] Updated weights for policy 0, policy_version 27476 (0.0007) -[2023-11-28 00:55:44,678][87424] Updated weights for policy 0, policy_version 27486 (0.0008) -[2023-11-28 00:55:45,530][87426] Updated weights for policy 1, policy_version 27330 (0.0012) -[2023-11-28 00:55:45,912][87426] Updated weights for policy 1, policy_version 27340 (0.0012) -[2023-11-28 00:55:46,289][87426] Updated weights for policy 1, policy_version 27350 (0.0012) -[2023-11-28 00:55:46,670][87426] Updated weights for policy 1, policy_version 27360 (0.0012) -[2023-11-28 00:55:46,969][87424] Updated weights for policy 0, policy_version 27496 (0.0011) -[2023-11-28 00:55:47,354][87424] Updated weights for policy 0, policy_version 27506 (0.0008) -[2023-11-28 00:55:47,735][87424] Updated weights for policy 0, policy_version 27516 (0.0010) -[2023-11-28 00:55:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 14049280. Throughput: 0: 2745.3, 1: 2694.5. Samples: 14060252. Policy #0 lag: (min: 31.0, avg: 51.9, max: 77.0) -[2023-11-28 00:55:48,445][86177] Avg episode reward: [(0, '-514.670'), (1, '-520.690')] -[2023-11-28 00:55:49,129][87426] Updated weights for policy 1, policy_version 27370 (0.0011) -[2023-11-28 00:55:49,510][87426] Updated weights for policy 1, policy_version 27380 (0.0012) -[2023-11-28 00:55:49,891][87426] Updated weights for policy 1, policy_version 27390 (0.0009) -[2023-11-28 00:55:49,897][87424] Updated weights for policy 0, policy_version 27526 (0.0009) -[2023-11-28 00:55:50,275][87424] Updated weights for policy 0, policy_version 27536 (0.0008) -[2023-11-28 00:55:50,658][87424] Updated weights for policy 0, policy_version 27546 (0.0011) -[2023-11-28 00:55:52,108][87426] Updated weights for policy 1, policy_version 27400 (0.0010) -[2023-11-28 00:55:52,488][87426] Updated weights for policy 1, policy_version 27410 (0.0009) -[2023-11-28 00:55:52,850][87424] Updated weights for policy 0, policy_version 27556 (0.0012) -[2023-11-28 00:55:52,867][87426] Updated weights for policy 1, policy_version 27420 (0.0012) -[2023-11-28 00:55:53,241][87424] Updated weights for policy 0, policy_version 27566 (0.0012) -[2023-11-28 00:55:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 14073856. Throughput: 0: 2713.7, 1: 2682.4. Samples: 14090792. Policy #0 lag: (min: 31.0, avg: 51.9, max: 77.0) -[2023-11-28 00:55:53,445][86177] Avg episode reward: [(0, '-515.900'), (1, '-529.400')] -[2023-11-28 00:55:53,609][87424] Updated weights for policy 0, policy_version 27576 (0.0012) -[2023-11-28 00:55:55,408][87426] Updated weights for policy 1, policy_version 27430 (0.0012) -[2023-11-28 00:55:55,788][87426] Updated weights for policy 1, policy_version 27440 (0.0012) -[2023-11-28 00:55:56,177][87426] Updated weights for policy 1, policy_version 27450 (0.0012) -[2023-11-28 00:55:56,354][87424] Updated weights for policy 0, policy_version 27586 (0.0012) -[2023-11-28 00:55:56,745][87424] Updated weights for policy 0, policy_version 27596 (0.0012) -[2023-11-28 00:55:57,133][87424] Updated weights for policy 0, policy_version 27606 (0.0012) -[2023-11-28 00:55:57,517][87424] Updated weights for policy 0, policy_version 27616 (0.0008) -[2023-11-28 00:55:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 14098432. Throughput: 0: 2688.5, 1: 2662.8. Samples: 14113308. Policy #0 lag: (min: 31.0, avg: 51.9, max: 77.0) -[2023-11-28 00:55:58,445][86177] Avg episode reward: [(0, '-522.410'), (1, '-520.880')] -[2023-11-28 00:55:58,806][87426] Updated weights for policy 1, policy_version 27460 (0.0012) -[2023-11-28 00:55:59,174][87426] Updated weights for policy 1, policy_version 27470 (0.0011) -[2023-11-28 00:55:59,555][87426] Updated weights for policy 1, policy_version 27480 (0.0012) -[2023-11-28 00:55:59,973][87424] Updated weights for policy 0, policy_version 27626 (0.0012) -[2023-11-28 00:56:00,345][87424] Updated weights for policy 0, policy_version 27636 (0.0012) -[2023-11-28 00:56:00,733][87424] Updated weights for policy 0, policy_version 27646 (0.0009) -[2023-11-28 00:56:02,184][87426] Updated weights for policy 1, policy_version 27490 (0.0011) -[2023-11-28 00:56:02,565][87426] Updated weights for policy 1, policy_version 27500 (0.0011) -[2023-11-28 00:56:02,942][87426] Updated weights for policy 1, policy_version 27510 (0.0012) -[2023-11-28 00:56:03,234][87424] Updated weights for policy 0, policy_version 27656 (0.0010) -[2023-11-28 00:56:03,319][87426] Updated weights for policy 1, policy_version 27520 (0.0011) -[2023-11-28 00:56:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 14123008. Throughput: 0: 2652.9, 1: 2632.0. Samples: 14135784. Policy #0 lag: (min: 30.0, avg: 48.6, max: 55.0) -[2023-11-28 00:56:03,445][86177] Avg episode reward: [(0, '-525.370'), (1, '-520.940')] -[2023-11-28 00:56:03,618][87424] Updated weights for policy 0, policy_version 27666 (0.0008) -[2023-11-28 00:56:03,999][87424] Updated weights for policy 0, policy_version 27676 (0.0009) -[2023-11-28 00:56:05,527][87426] Updated weights for policy 1, policy_version 27530 (0.0011) -[2023-11-28 00:56:05,910][87426] Updated weights for policy 1, policy_version 27540 (0.0011) -[2023-11-28 00:56:06,172][87424] Updated weights for policy 0, policy_version 27686 (0.0011) -[2023-11-28 00:56:06,284][87426] Updated weights for policy 1, policy_version 27550 (0.0009) -[2023-11-28 00:56:06,555][87424] Updated weights for policy 0, policy_version 27696 (0.0012) -[2023-11-28 00:56:06,934][87424] Updated weights for policy 0, policy_version 27706 (0.0011) -[2023-11-28 00:56:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 14147584. Throughput: 0: 2613.9, 1: 2611.8. Samples: 14166068. Policy #0 lag: (min: 30.0, avg: 48.6, max: 55.0) -[2023-11-28 00:56:08,445][86177] Avg episode reward: [(0, '-523.530'), (1, '-528.670')] -[2023-11-28 00:56:08,859][87426] Updated weights for policy 1, policy_version 27560 (0.0011) -[2023-11-28 00:56:09,238][87426] Updated weights for policy 1, policy_version 27570 (0.0012) -[2023-11-28 00:56:09,511][87424] Updated weights for policy 0, policy_version 27716 (0.0011) -[2023-11-28 00:56:09,618][87426] Updated weights for policy 1, policy_version 27580 (0.0012) -[2023-11-28 00:56:09,897][87424] Updated weights for policy 0, policy_version 27726 (0.0011) -[2023-11-28 00:56:10,297][87424] Updated weights for policy 0, policy_version 27736 (0.0011) -[2023-11-28 00:56:12,007][87426] Updated weights for policy 1, policy_version 27590 (0.0017) -[2023-11-28 00:56:12,405][87426] Updated weights for policy 1, policy_version 27600 (0.0012) -[2023-11-28 00:56:12,787][87426] Updated weights for policy 1, policy_version 27610 (0.0012) -[2023-11-28 00:56:13,033][87424] Updated weights for policy 0, policy_version 27746 (0.0011) -[2023-11-28 00:56:13,429][87424] Updated weights for policy 0, policy_version 27756 (0.0012) -[2023-11-28 00:56:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 14172160. Throughput: 0: 2600.6, 1: 2561.4. Samples: 14187236. Policy #0 lag: (min: 30.0, avg: 48.6, max: 55.0) -[2023-11-28 00:56:13,445][86177] Avg episode reward: [(0, '-528.170'), (1, '-520.450')] -[2023-11-28 00:56:13,802][87424] Updated weights for policy 0, policy_version 27766 (0.0012) -[2023-11-28 00:56:14,182][87424] Updated weights for policy 0, policy_version 27776 (0.0012) -[2023-11-28 00:56:15,382][87426] Updated weights for policy 1, policy_version 27620 (0.0013) -[2023-11-28 00:56:15,759][87426] Updated weights for policy 1, policy_version 27630 (0.0012) -[2023-11-28 00:56:16,142][87426] Updated weights for policy 1, policy_version 27640 (0.0010) -[2023-11-28 00:56:16,936][87424] Updated weights for policy 0, policy_version 27786 (0.0009) -[2023-11-28 00:56:17,309][87424] Updated weights for policy 0, policy_version 27796 (0.0009) -[2023-11-28 00:56:17,701][87424] Updated weights for policy 0, policy_version 27806 (0.0009) -[2023-11-28 00:56:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 14196736. Throughput: 0: 2559.4, 1: 2559.9. Samples: 14209376. Policy #0 lag: (min: 30.0, avg: 48.6, max: 55.0) -[2023-11-28 00:56:18,445][86177] Avg episode reward: [(0, '-526.970'), (1, '-515.710')] -[2023-11-28 00:56:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000027808_7118848.pth... -[2023-11-28 00:56:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000027648_7077888.pth... -[2023-11-28 00:56:18,491][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000025152_6438912.pth -[2023-11-28 00:56:18,508][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000025280_6471680.pth -[2023-11-28 00:56:18,749][87426] Updated weights for policy 1, policy_version 27650 (0.0010) -[2023-11-28 00:56:19,126][87426] Updated weights for policy 1, policy_version 27660 (0.0011) -[2023-11-28 00:56:19,511][87426] Updated weights for policy 1, policy_version 27670 (0.0011) -[2023-11-28 00:56:19,883][87426] Updated weights for policy 1, policy_version 27680 (0.0011) -[2023-11-28 00:56:20,041][87424] Updated weights for policy 0, policy_version 27816 (0.0011) -[2023-11-28 00:56:20,436][87424] Updated weights for policy 0, policy_version 27826 (0.0011) -[2023-11-28 00:56:20,806][87424] Updated weights for policy 0, policy_version 27836 (0.0010) -[2023-11-28 00:56:22,420][87426] Updated weights for policy 1, policy_version 27690 (0.0010) -[2023-11-28 00:56:22,796][87426] Updated weights for policy 1, policy_version 27700 (0.0012) -[2023-11-28 00:56:23,171][87426] Updated weights for policy 1, policy_version 27710 (0.0011) -[2023-11-28 00:56:23,240][87424] Updated weights for policy 0, policy_version 27846 (0.0011) -[2023-11-28 00:56:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 14221312. Throughput: 0: 2544.4, 1: 2539.0. Samples: 14240120. Policy #0 lag: (min: 19.0, avg: 35.4, max: 45.0) -[2023-11-28 00:56:23,445][86177] Avg episode reward: [(0, '-531.170'), (1, '-514.640')] -[2023-11-28 00:56:23,618][87424] Updated weights for policy 0, policy_version 27856 (0.0009) -[2023-11-28 00:56:24,002][87424] Updated weights for policy 0, policy_version 27866 (0.0010) -[2023-11-28 00:56:25,360][87426] Updated weights for policy 1, policy_version 27720 (0.0012) -[2023-11-28 00:56:25,741][87426] Updated weights for policy 1, policy_version 27730 (0.0012) -[2023-11-28 00:56:26,114][87426] Updated weights for policy 1, policy_version 27740 (0.0012) -[2023-11-28 00:56:26,281][87424] Updated weights for policy 0, policy_version 27876 (0.0012) -[2023-11-28 00:56:26,666][87424] Updated weights for policy 0, policy_version 27886 (0.0012) -[2023-11-28 00:56:27,044][87424] Updated weights for policy 0, policy_version 27896 (0.0011) -[2023-11-28 00:56:28,199][87426] Updated weights for policy 1, policy_version 27750 (0.0011) -[2023-11-28 00:56:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5359.5). Total num frames: 14245888. Throughput: 0: 2546.1, 1: 2551.4. Samples: 14264700. Policy #0 lag: (min: 19.0, avg: 35.4, max: 45.0) -[2023-11-28 00:56:28,445][86177] Avg episode reward: [(0, '-532.020'), (1, '-501.430')] -[2023-11-28 00:56:28,581][87426] Updated weights for policy 1, policy_version 27760 (0.0010) -[2023-11-28 00:56:28,880][87424] Updated weights for policy 0, policy_version 27906 (0.0011) -[2023-11-28 00:56:28,957][87426] Updated weights for policy 1, policy_version 27770 (0.0008) -[2023-11-28 00:56:29,264][87424] Updated weights for policy 0, policy_version 27916 (0.0010) -[2023-11-28 00:56:29,641][87424] Updated weights for policy 0, policy_version 27926 (0.0010) -[2023-11-28 00:56:30,024][87424] Updated weights for policy 0, policy_version 27936 (0.0010) -[2023-11-28 00:56:31,205][87426] Updated weights for policy 1, policy_version 27780 (0.0009) -[2023-11-28 00:56:31,587][87426] Updated weights for policy 1, policy_version 27790 (0.0011) -[2023-11-28 00:56:31,965][87426] Updated weights for policy 1, policy_version 27800 (0.0011) -[2023-11-28 00:56:32,414][87424] Updated weights for policy 0, policy_version 27946 (0.0010) -[2023-11-28 00:56:32,794][87424] Updated weights for policy 0, policy_version 27956 (0.0011) -[2023-11-28 00:56:33,180][87424] Updated weights for policy 0, policy_version 27966 (0.0011) -[2023-11-28 00:56:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 14278656. Throughput: 0: 2516.6, 1: 2538.0. Samples: 14287712. Policy #0 lag: (min: 19.0, avg: 35.4, max: 45.0) -[2023-11-28 00:56:33,445][86177] Avg episode reward: [(0, '-524.840'), (1, '-497.380')] -[2023-11-28 00:56:33,456][87320] Saving new best policy, reward=-497.380! -[2023-11-28 00:56:33,783][87426] Updated weights for policy 1, policy_version 27810 (0.0009) -[2023-11-28 00:56:34,160][87426] Updated weights for policy 1, policy_version 27820 (0.0008) -[2023-11-28 00:56:34,546][87426] Updated weights for policy 1, policy_version 27830 (0.0008) -[2023-11-28 00:56:34,935][87426] Updated weights for policy 1, policy_version 27840 (0.0012) -[2023-11-28 00:56:35,400][87424] Updated weights for policy 0, policy_version 27976 (0.0010) -[2023-11-28 00:56:35,782][87424] Updated weights for policy 0, policy_version 27986 (0.0010) -[2023-11-28 00:56:36,171][87424] Updated weights for policy 0, policy_version 27996 (0.0009) -[2023-11-28 00:56:37,023][87426] Updated weights for policy 1, policy_version 27850 (0.0009) -[2023-11-28 00:56:37,403][87426] Updated weights for policy 1, policy_version 27860 (0.0012) -[2023-11-28 00:56:37,778][87426] Updated weights for policy 1, policy_version 27870 (0.0012) -[2023-11-28 00:56:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 14303232. Throughput: 0: 2524.7, 1: 2538.2. Samples: 14318624. Policy #0 lag: (min: 19.0, avg: 35.4, max: 45.0) -[2023-11-28 00:56:38,445][86177] Avg episode reward: [(0, '-519.350'), (1, '-499.040')] -[2023-11-28 00:56:38,488][87424] Updated weights for policy 0, policy_version 28006 (0.0011) -[2023-11-28 00:56:38,869][87424] Updated weights for policy 0, policy_version 28016 (0.0012) -[2023-11-28 00:56:39,268][87424] Updated weights for policy 0, policy_version 28026 (0.0012) -[2023-11-28 00:56:40,389][87426] Updated weights for policy 1, policy_version 27880 (0.0012) -[2023-11-28 00:56:40,770][87426] Updated weights for policy 1, policy_version 27890 (0.0012) -[2023-11-28 00:56:41,150][87426] Updated weights for policy 1, policy_version 27900 (0.0011) -[2023-11-28 00:56:41,260][87424] Updated weights for policy 0, policy_version 28036 (0.0011) -[2023-11-28 00:56:41,653][87424] Updated weights for policy 0, policy_version 28046 (0.0011) -[2023-11-28 00:56:42,036][87424] Updated weights for policy 0, policy_version 28056 (0.0010) -[2023-11-28 00:56:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5359.5). Total num frames: 14327808. Throughput: 0: 2550.6, 1: 2551.0. Samples: 14342880. Policy #0 lag: (min: 31.0, avg: 48.6, max: 65.0) -[2023-11-28 00:56:43,445][86177] Avg episode reward: [(0, '-513.660'), (1, '-498.670')] -[2023-11-28 00:56:43,785][87426] Updated weights for policy 1, policy_version 27910 (0.0012) -[2023-11-28 00:56:44,164][87426] Updated weights for policy 1, policy_version 27920 (0.0012) -[2023-11-28 00:56:44,519][87424] Updated weights for policy 0, policy_version 28066 (0.0010) -[2023-11-28 00:56:44,543][87426] Updated weights for policy 1, policy_version 27930 (0.0011) -[2023-11-28 00:56:44,904][87424] Updated weights for policy 0, policy_version 28076 (0.0011) -[2023-11-28 00:56:45,280][87424] Updated weights for policy 0, policy_version 28086 (0.0012) -[2023-11-28 00:56:45,659][87424] Updated weights for policy 0, policy_version 28096 (0.0012) -[2023-11-28 00:56:47,131][87426] Updated weights for policy 1, policy_version 27940 (0.0011) -[2023-11-28 00:56:47,527][87426] Updated weights for policy 1, policy_version 27950 (0.0012) -[2023-11-28 00:56:47,531][87424] Updated weights for policy 0, policy_version 28106 (0.0008) -[2023-11-28 00:56:47,896][87426] Updated weights for policy 1, policy_version 27960 (0.0012) -[2023-11-28 00:56:47,909][87424] Updated weights for policy 0, policy_version 28116 (0.0008) -[2023-11-28 00:56:48,285][87424] Updated weights for policy 0, policy_version 28126 (0.0008) -[2023-11-28 00:56:48,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5188.2, 300 sec: 5387.3). Total num frames: 14360576. Throughput: 0: 2568.5, 1: 2557.2. Samples: 14366444. Policy #0 lag: (min: 31.0, avg: 48.6, max: 65.0) -[2023-11-28 00:56:48,446][86177] Avg episode reward: [(0, '-516.890'), (1, '-499.430')] -[2023-11-28 00:56:49,518][87426] Updated weights for policy 1, policy_version 27970 (0.0011) -[2023-11-28 00:56:49,920][87426] Updated weights for policy 1, policy_version 27980 (0.0013) -[2023-11-28 00:56:50,298][87426] Updated weights for policy 1, policy_version 27990 (0.0010) -[2023-11-28 00:56:50,425][87424] Updated weights for policy 0, policy_version 28136 (0.0011) -[2023-11-28 00:56:50,670][87426] Updated weights for policy 1, policy_version 28000 (0.0011) -[2023-11-28 00:56:50,805][87424] Updated weights for policy 0, policy_version 28146 (0.0012) -[2023-11-28 00:56:51,198][87424] Updated weights for policy 0, policy_version 28156 (0.0009) -[2023-11-28 00:56:53,000][87426] Updated weights for policy 1, policy_version 28010 (0.0010) -[2023-11-28 00:56:53,378][87426] Updated weights for policy 1, policy_version 28020 (0.0012) -[2023-11-28 00:56:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5359.5). Total num frames: 14376960. Throughput: 0: 2598.1, 1: 2581.2. Samples: 14399136. Policy #0 lag: (min: 31.0, avg: 48.6, max: 65.0) -[2023-11-28 00:56:53,445][86177] Avg episode reward: [(0, '-518.290'), (1, '-501.670')] -[2023-11-28 00:56:53,502][87424] Updated weights for policy 0, policy_version 28166 (0.0010) -[2023-11-28 00:56:53,774][87426] Updated weights for policy 1, policy_version 28030 (0.0011) -[2023-11-28 00:56:53,879][87424] Updated weights for policy 0, policy_version 28176 (0.0009) -[2023-11-28 00:56:54,268][87424] Updated weights for policy 0, policy_version 28186 (0.0007) -[2023-11-28 00:56:55,486][87426] Updated weights for policy 1, policy_version 28040 (0.0009) -[2023-11-28 00:56:55,865][87426] Updated weights for policy 1, policy_version 28050 (0.0007) -[2023-11-28 00:56:56,245][87426] Updated weights for policy 1, policy_version 28060 (0.0008) -[2023-11-28 00:56:56,722][87424] Updated weights for policy 0, policy_version 28196 (0.0007) -[2023-11-28 00:56:57,098][87424] Updated weights for policy 0, policy_version 28206 (0.0012) -[2023-11-28 00:56:57,475][87424] Updated weights for policy 0, policy_version 28216 (0.0011) -[2023-11-28 00:56:58,183][87426] Updated weights for policy 1, policy_version 28070 (0.0009) -[2023-11-28 00:56:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 14409728. Throughput: 0: 2620.5, 1: 2616.5. Samples: 14422904. Policy #0 lag: (min: 31.0, avg: 48.6, max: 65.0) -[2023-11-28 00:56:58,445][86177] Avg episode reward: [(0, '-516.850'), (1, '-524.510')] -[2023-11-28 00:56:58,564][87426] Updated weights for policy 1, policy_version 28080 (0.0007) -[2023-11-28 00:56:58,944][87426] Updated weights for policy 1, policy_version 28090 (0.0007) -[2023-11-28 00:56:59,978][87424] Updated weights for policy 0, policy_version 28226 (0.0007) -[2023-11-28 00:57:00,366][87424] Updated weights for policy 0, policy_version 28236 (0.0008) -[2023-11-28 00:57:00,750][87424] Updated weights for policy 0, policy_version 28246 (0.0010) -[2023-11-28 00:57:01,129][87424] Updated weights for policy 0, policy_version 28256 (0.0012) -[2023-11-28 00:57:01,172][87426] Updated weights for policy 1, policy_version 28100 (0.0008) -[2023-11-28 00:57:01,548][87426] Updated weights for policy 1, policy_version 28110 (0.0012) -[2023-11-28 00:57:01,925][87426] Updated weights for policy 1, policy_version 28120 (0.0012) -[2023-11-28 00:57:02,899][87424] Updated weights for policy 0, policy_version 28266 (0.0012) -[2023-11-28 00:57:03,286][87424] Updated weights for policy 0, policy_version 28276 (0.0012) -[2023-11-28 00:57:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 14434304. Throughput: 0: 2651.2, 1: 2644.4. Samples: 14447680. Policy #0 lag: (min: 26.0, avg: 52.3, max: 58.0) -[2023-11-28 00:57:03,445][86177] Avg episode reward: [(0, '-512.960'), (1, '-522.490')] -[2023-11-28 00:57:03,665][87424] Updated weights for policy 0, policy_version 28286 (0.0012) -[2023-11-28 00:57:03,841][87426] Updated weights for policy 1, policy_version 28130 (0.0011) -[2023-11-28 00:57:04,220][87426] Updated weights for policy 1, policy_version 28140 (0.0007) -[2023-11-28 00:57:04,600][87426] Updated weights for policy 1, policy_version 28150 (0.0008) -[2023-11-28 00:57:04,980][87426] Updated weights for policy 1, policy_version 28160 (0.0007) -[2023-11-28 00:57:05,919][87424] Updated weights for policy 0, policy_version 28296 (0.0011) -[2023-11-28 00:57:06,300][87424] Updated weights for policy 0, policy_version 28306 (0.0012) -[2023-11-28 00:57:06,680][87424] Updated weights for policy 0, policy_version 28316 (0.0012) -[2023-11-28 00:57:07,327][87426] Updated weights for policy 1, policy_version 28170 (0.0011) -[2023-11-28 00:57:07,710][87426] Updated weights for policy 1, policy_version 28180 (0.0010) -[2023-11-28 00:57:08,077][87426] Updated weights for policy 1, policy_version 28190 (0.0010) -[2023-11-28 00:57:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 14467072. Throughput: 0: 2663.6, 1: 2684.2. Samples: 14480772. Policy #0 lag: (min: 26.0, avg: 52.3, max: 58.0) -[2023-11-28 00:57:08,445][86177] Avg episode reward: [(0, '-509.880'), (1, '-526.530')] -[2023-11-28 00:57:09,242][87424] Updated weights for policy 0, policy_version 28326 (0.0010) -[2023-11-28 00:57:09,633][87424] Updated weights for policy 0, policy_version 28336 (0.0010) -[2023-11-28 00:57:09,853][87426] Updated weights for policy 1, policy_version 28200 (0.0010) -[2023-11-28 00:57:10,008][87424] Updated weights for policy 0, policy_version 28346 (0.0011) -[2023-11-28 00:57:10,219][87426] Updated weights for policy 1, policy_version 28210 (0.0011) -[2023-11-28 00:57:10,607][87426] Updated weights for policy 1, policy_version 28220 (0.0009) -[2023-11-28 00:57:12,035][87424] Updated weights for policy 0, policy_version 28356 (0.0011) -[2023-11-28 00:57:12,421][87424] Updated weights for policy 0, policy_version 28366 (0.0012) -[2023-11-28 00:57:12,802][87424] Updated weights for policy 0, policy_version 28376 (0.0011) -[2023-11-28 00:57:12,893][87426] Updated weights for policy 1, policy_version 28230 (0.0010) -[2023-11-28 00:57:13,277][87426] Updated weights for policy 1, policy_version 28240 (0.0011) -[2023-11-28 00:57:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 14491648. Throughput: 0: 2658.4, 1: 2694.7. Samples: 14505588. Policy #0 lag: (min: 26.0, avg: 52.3, max: 58.0) -[2023-11-28 00:57:13,445][86177] Avg episode reward: [(0, '-507.220'), (1, '-529.010')] -[2023-11-28 00:57:13,653][87426] Updated weights for policy 1, policy_version 28250 (0.0012) -[2023-11-28 00:57:14,791][87424] Updated weights for policy 0, policy_version 28386 (0.0011) -[2023-11-28 00:57:15,188][87424] Updated weights for policy 0, policy_version 28396 (0.0012) -[2023-11-28 00:57:15,564][87424] Updated weights for policy 0, policy_version 28406 (0.0011) -[2023-11-28 00:57:15,938][87424] Updated weights for policy 0, policy_version 28416 (0.0011) -[2023-11-28 00:57:16,269][87426] Updated weights for policy 1, policy_version 28260 (0.0010) -[2023-11-28 00:57:16,639][87426] Updated weights for policy 1, policy_version 28270 (0.0007) -[2023-11-28 00:57:17,038][87426] Updated weights for policy 1, policy_version 28280 (0.0008) -[2023-11-28 00:57:18,431][87424] Updated weights for policy 0, policy_version 28426 (0.0007) -[2023-11-28 00:57:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 14516224. Throughput: 0: 2683.6, 1: 2682.5. Samples: 14529184. Policy #0 lag: (min: 26.0, avg: 52.3, max: 58.0) -[2023-11-28 00:57:18,445][86177] Avg episode reward: [(0, '-518.210'), (1, '-550.730')] -[2023-11-28 00:57:18,822][87424] Updated weights for policy 0, policy_version 28436 (0.0008) -[2023-11-28 00:57:19,035][87426] Updated weights for policy 1, policy_version 28290 (0.0008) -[2023-11-28 00:57:19,212][87424] Updated weights for policy 0, policy_version 28446 (0.0011) -[2023-11-28 00:57:19,408][87426] Updated weights for policy 1, policy_version 28300 (0.0010) -[2023-11-28 00:57:19,784][87426] Updated weights for policy 1, policy_version 28310 (0.0012) -[2023-11-28 00:57:20,165][87426] Updated weights for policy 1, policy_version 28320 (0.0009) -[2023-11-28 00:57:21,204][87424] Updated weights for policy 0, policy_version 28456 (0.0011) -[2023-11-28 00:57:21,573][87424] Updated weights for policy 0, policy_version 28466 (0.0012) -[2023-11-28 00:57:21,960][87424] Updated weights for policy 0, policy_version 28476 (0.0012) -[2023-11-28 00:57:22,612][87426] Updated weights for policy 1, policy_version 28330 (0.0012) -[2023-11-28 00:57:22,988][87426] Updated weights for policy 1, policy_version 28340 (0.0012) -[2023-11-28 00:57:23,374][87426] Updated weights for policy 1, policy_version 28350 (0.0012) -[2023-11-28 00:57:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 14548992. Throughput: 0: 2707.8, 1: 2690.3. Samples: 14561540. Policy #0 lag: (min: 31.0, avg: 54.2, max: 95.0) -[2023-11-28 00:57:23,446][86177] Avg episode reward: [(0, '-520.640'), (1, '-551.440')] -[2023-11-28 00:57:23,947][87424] Updated weights for policy 0, policy_version 28486 (0.0012) -[2023-11-28 00:57:24,340][87424] Updated weights for policy 0, policy_version 28496 (0.0011) -[2023-11-28 00:57:24,714][87424] Updated weights for policy 0, policy_version 28506 (0.0009) -[2023-11-28 00:57:25,997][87426] Updated weights for policy 1, policy_version 28360 (0.0010) -[2023-11-28 00:57:26,383][87426] Updated weights for policy 1, policy_version 28370 (0.0009) -[2023-11-28 00:57:26,768][87426] Updated weights for policy 1, policy_version 28380 (0.0008) -[2023-11-28 00:57:27,131][87424] Updated weights for policy 0, policy_version 28516 (0.0009) -[2023-11-28 00:57:27,513][87424] Updated weights for policy 0, policy_version 28526 (0.0011) -[2023-11-28 00:57:27,909][87424] Updated weights for policy 0, policy_version 28536 (0.0012) -[2023-11-28 00:57:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 14573568. Throughput: 0: 2706.7, 1: 2705.7. Samples: 14586436. Policy #0 lag: (min: 31.0, avg: 54.2, max: 95.0) -[2023-11-28 00:57:28,445][86177] Avg episode reward: [(0, '-519.430'), (1, '-552.860')] -[2023-11-28 00:57:28,471][87426] Updated weights for policy 1, policy_version 28390 (0.0007) -[2023-11-28 00:57:28,861][87426] Updated weights for policy 1, policy_version 28400 (0.0007) -[2023-11-28 00:57:29,241][87426] Updated weights for policy 1, policy_version 28410 (0.0007) -[2023-11-28 00:57:30,000][87424] Updated weights for policy 0, policy_version 28546 (0.0012) -[2023-11-28 00:57:30,377][87424] Updated weights for policy 0, policy_version 28556 (0.0012) -[2023-11-28 00:57:30,763][87424] Updated weights for policy 0, policy_version 28566 (0.0008) -[2023-11-28 00:57:31,147][87424] Updated weights for policy 0, policy_version 28576 (0.0008) -[2023-11-28 00:57:31,300][87426] Updated weights for policy 1, policy_version 28420 (0.0008) -[2023-11-28 00:57:31,681][87426] Updated weights for policy 1, policy_version 28430 (0.0008) -[2023-11-28 00:57:32,057][87426] Updated weights for policy 1, policy_version 28440 (0.0011) -[2023-11-28 00:57:33,130][87424] Updated weights for policy 0, policy_version 28586 (0.0009) -[2023-11-28 00:57:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 14598144. Throughput: 0: 2708.8, 1: 2725.8. Samples: 14611000. Policy #0 lag: (min: 31.0, avg: 54.2, max: 95.0) -[2023-11-28 00:57:33,445][86177] Avg episode reward: [(0, '-520.350'), (1, '-553.310')] -[2023-11-28 00:57:33,515][87424] Updated weights for policy 0, policy_version 28596 (0.0010) -[2023-11-28 00:57:33,885][87424] Updated weights for policy 0, policy_version 28606 (0.0012) -[2023-11-28 00:57:34,422][87426] Updated weights for policy 1, policy_version 28450 (0.0010) -[2023-11-28 00:57:34,794][87426] Updated weights for policy 1, policy_version 28460 (0.0008) -[2023-11-28 00:57:35,176][87426] Updated weights for policy 1, policy_version 28470 (0.0010) -[2023-11-28 00:57:35,553][87426] Updated weights for policy 1, policy_version 28480 (0.0010) -[2023-11-28 00:57:36,442][87424] Updated weights for policy 0, policy_version 28616 (0.0011) -[2023-11-28 00:57:36,826][87424] Updated weights for policy 0, policy_version 28626 (0.0008) -[2023-11-28 00:57:37,189][87426] Updated weights for policy 1, policy_version 28490 (0.0009) -[2023-11-28 00:57:37,210][87424] Updated weights for policy 0, policy_version 28636 (0.0009) -[2023-11-28 00:57:37,566][87426] Updated weights for policy 1, policy_version 28500 (0.0011) -[2023-11-28 00:57:37,941][87426] Updated weights for policy 1, policy_version 28510 (0.0012) -[2023-11-28 00:57:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 14630912. Throughput: 0: 2691.5, 1: 2739.5. Samples: 14643532. Policy #0 lag: (min: 31.0, avg: 54.2, max: 95.0) -[2023-11-28 00:57:38,446][86177] Avg episode reward: [(0, '-520.640'), (1, '-512.740')] -[2023-11-28 00:57:39,021][87424] Updated weights for policy 0, policy_version 28646 (0.0009) -[2023-11-28 00:57:39,404][87424] Updated weights for policy 0, policy_version 28656 (0.0011) -[2023-11-28 00:57:39,787][87424] Updated weights for policy 0, policy_version 28666 (0.0010) -[2023-11-28 00:57:40,434][87426] Updated weights for policy 1, policy_version 28520 (0.0009) -[2023-11-28 00:57:40,810][87426] Updated weights for policy 1, policy_version 28530 (0.0008) -[2023-11-28 00:57:41,189][87426] Updated weights for policy 1, policy_version 28540 (0.0018) -[2023-11-28 00:57:41,714][87424] Updated weights for policy 0, policy_version 28676 (0.0010) -[2023-11-28 00:57:42,106][87424] Updated weights for policy 0, policy_version 28686 (0.0010) -[2023-11-28 00:57:42,482][87424] Updated weights for policy 0, policy_version 28696 (0.0010) -[2023-11-28 00:57:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 14655488. Throughput: 0: 2707.6, 1: 2748.7. Samples: 14668436. Policy #0 lag: (min: 31.0, avg: 49.6, max: 79.0) -[2023-11-28 00:57:43,445][87426] Updated weights for policy 1, policy_version 28550 (0.0012) -[2023-11-28 00:57:43,445][86177] Avg episode reward: [(0, '-517.540'), (1, '-509.490')] -[2023-11-28 00:57:43,834][87426] Updated weights for policy 1, policy_version 28560 (0.0011) -[2023-11-28 00:57:44,215][87426] Updated weights for policy 1, policy_version 28570 (0.0011) -[2023-11-28 00:57:44,886][87424] Updated weights for policy 0, policy_version 28706 (0.0009) -[2023-11-28 00:57:45,262][87424] Updated weights for policy 0, policy_version 28716 (0.0012) -[2023-11-28 00:57:45,646][87424] Updated weights for policy 0, policy_version 28726 (0.0012) -[2023-11-28 00:57:46,023][87424] Updated weights for policy 0, policy_version 28736 (0.0012) -[2023-11-28 00:57:46,565][87426] Updated weights for policy 1, policy_version 28580 (0.0010) -[2023-11-28 00:57:46,944][87426] Updated weights for policy 1, policy_version 28590 (0.0007) -[2023-11-28 00:57:47,327][87426] Updated weights for policy 1, policy_version 28600 (0.0007) -[2023-11-28 00:57:48,183][87424] Updated weights for policy 0, policy_version 28746 (0.0007) -[2023-11-28 00:57:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 14680064. Throughput: 0: 2690.9, 1: 2759.7. Samples: 14692960. Policy #0 lag: (min: 31.0, avg: 49.6, max: 79.0) -[2023-11-28 00:57:48,445][86177] Avg episode reward: [(0, '-507.350'), (1, '-507.430')] -[2023-11-28 00:57:48,572][87424] Updated weights for policy 0, policy_version 28756 (0.0007) -[2023-11-28 00:57:48,955][87424] Updated weights for policy 0, policy_version 28766 (0.0008) -[2023-11-28 00:57:49,654][87426] Updated weights for policy 1, policy_version 28610 (0.0008) -[2023-11-28 00:57:50,032][87426] Updated weights for policy 1, policy_version 28620 (0.0012) -[2023-11-28 00:57:50,407][87426] Updated weights for policy 1, policy_version 28630 (0.0012) -[2023-11-28 00:57:50,786][87426] Updated weights for policy 1, policy_version 28640 (0.0011) -[2023-11-28 00:57:50,796][87424] Updated weights for policy 0, policy_version 28776 (0.0011) -[2023-11-28 00:57:51,174][87424] Updated weights for policy 0, policy_version 28786 (0.0012) -[2023-11-28 00:57:51,557][87424] Updated weights for policy 0, policy_version 28796 (0.0012) -[2023-11-28 00:57:52,681][87426] Updated weights for policy 1, policy_version 28650 (0.0012) -[2023-11-28 00:57:53,060][87426] Updated weights for policy 1, policy_version 28660 (0.0011) -[2023-11-28 00:57:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 14704640. Throughput: 0: 2703.5, 1: 2730.3. Samples: 14725292. Policy #0 lag: (min: 31.0, avg: 49.6, max: 79.0) -[2023-11-28 00:57:53,445][86177] Avg episode reward: [(0, '-549.730'), (1, '-506.500')] -[2023-11-28 00:57:53,456][87426] Updated weights for policy 1, policy_version 28670 (0.0010) -[2023-11-28 00:57:54,081][87424] Updated weights for policy 0, policy_version 28806 (0.0012) -[2023-11-28 00:57:54,469][87424] Updated weights for policy 0, policy_version 28816 (0.0010) -[2023-11-28 00:57:54,854][87424] Updated weights for policy 0, policy_version 28826 (0.0010) -[2023-11-28 00:57:55,776][87426] Updated weights for policy 1, policy_version 28680 (0.0008) -[2023-11-28 00:57:56,164][87426] Updated weights for policy 1, policy_version 28690 (0.0011) -[2023-11-28 00:57:56,537][87426] Updated weights for policy 1, policy_version 28700 (0.0011) -[2023-11-28 00:57:56,832][87424] Updated weights for policy 0, policy_version 28836 (0.0009) -[2023-11-28 00:57:57,214][87424] Updated weights for policy 0, policy_version 28846 (0.0012) -[2023-11-28 00:57:57,599][87424] Updated weights for policy 0, policy_version 28856 (0.0011) -[2023-11-28 00:57:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 14737408. Throughput: 0: 2716.7, 1: 2738.9. Samples: 14751092. Policy #0 lag: (min: 31.0, avg: 49.6, max: 79.0) -[2023-11-28 00:57:58,445][86177] Avg episode reward: [(0, '-553.180'), (1, '-511.900')] -[2023-11-28 00:57:58,539][87426] Updated weights for policy 1, policy_version 28710 (0.0009) -[2023-11-28 00:57:58,924][87426] Updated weights for policy 1, policy_version 28720 (0.0009) -[2023-11-28 00:57:59,296][87426] Updated weights for policy 1, policy_version 28730 (0.0009) -[2023-11-28 00:57:59,794][87424] Updated weights for policy 0, policy_version 28866 (0.0012) -[2023-11-28 00:58:00,181][87424] Updated weights for policy 0, policy_version 28876 (0.0012) -[2023-11-28 00:58:00,560][87424] Updated weights for policy 0, policy_version 28886 (0.0012) -[2023-11-28 00:58:00,933][87424] Updated weights for policy 0, policy_version 28896 (0.0012) -[2023-11-28 00:58:01,219][87426] Updated weights for policy 1, policy_version 28740 (0.0010) -[2023-11-28 00:58:01,596][87426] Updated weights for policy 1, policy_version 28750 (0.0008) -[2023-11-28 00:58:01,976][87426] Updated weights for policy 1, policy_version 28760 (0.0010) -[2023-11-28 00:58:03,257][87424] Updated weights for policy 0, policy_version 28906 (0.0012) -[2023-11-28 00:58:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 14761984. Throughput: 0: 2734.9, 1: 2775.3. Samples: 14777144. Policy #0 lag: (min: 31.0, avg: 49.6, max: 79.0) -[2023-11-28 00:58:03,445][86177] Avg episode reward: [(0, '-560.250'), (1, '-520.960')] -[2023-11-28 00:58:03,640][87424] Updated weights for policy 0, policy_version 28916 (0.0009) -[2023-11-28 00:58:03,809][87426] Updated weights for policy 1, policy_version 28770 (0.0010) -[2023-11-28 00:58:04,023][87424] Updated weights for policy 0, policy_version 28926 (0.0010) -[2023-11-28 00:58:04,191][87426] Updated weights for policy 1, policy_version 28780 (0.0011) -[2023-11-28 00:58:04,568][87426] Updated weights for policy 1, policy_version 28790 (0.0012) -[2023-11-28 00:58:04,943][87426] Updated weights for policy 1, policy_version 28800 (0.0012) -[2023-11-28 00:58:05,931][87424] Updated weights for policy 0, policy_version 28936 (0.0011) -[2023-11-28 00:58:06,330][87424] Updated weights for policy 0, policy_version 28946 (0.0012) -[2023-11-28 00:58:06,632][87426] Updated weights for policy 1, policy_version 28810 (0.0012) -[2023-11-28 00:58:06,707][87424] Updated weights for policy 0, policy_version 28956 (0.0010) -[2023-11-28 00:58:07,011][87426] Updated weights for policy 1, policy_version 28820 (0.0007) -[2023-11-28 00:58:07,401][87426] Updated weights for policy 1, policy_version 28830 (0.0010) -[2023-11-28 00:58:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 14794752. Throughput: 0: 2746.9, 1: 2803.6. Samples: 14811308. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-11-28 00:58:08,445][86177] Avg episode reward: [(0, '-570.420'), (1, '-519.400')] -[2023-11-28 00:58:08,868][87424] Updated weights for policy 0, policy_version 28966 (0.0010) -[2023-11-28 00:58:09,261][87424] Updated weights for policy 0, policy_version 28976 (0.0008) -[2023-11-28 00:58:09,470][87426] Updated weights for policy 1, policy_version 28840 (0.0008) -[2023-11-28 00:58:09,640][87424] Updated weights for policy 0, policy_version 28986 (0.0008) -[2023-11-28 00:58:09,862][87426] Updated weights for policy 1, policy_version 28850 (0.0008) -[2023-11-28 00:58:10,236][87426] Updated weights for policy 1, policy_version 28860 (0.0008) -[2023-11-28 00:58:11,981][87424] Updated weights for policy 0, policy_version 28996 (0.0010) -[2023-11-28 00:58:12,377][87424] Updated weights for policy 0, policy_version 29006 (0.0011) -[2023-11-28 00:58:12,546][87426] Updated weights for policy 1, policy_version 28870 (0.0010) -[2023-11-28 00:58:12,754][87424] Updated weights for policy 0, policy_version 29016 (0.0011) -[2023-11-28 00:58:12,927][87426] Updated weights for policy 1, policy_version 28880 (0.0012) -[2023-11-28 00:58:13,310][87426] Updated weights for policy 1, policy_version 28890 (0.0011) -[2023-11-28 00:58:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 14819328. Throughput: 0: 2742.3, 1: 2818.4. Samples: 14836668. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-11-28 00:58:13,445][86177] Avg episode reward: [(0, '-536.560'), (1, '-516.710')] -[2023-11-28 00:58:14,819][87424] Updated weights for policy 0, policy_version 29026 (0.0011) -[2023-11-28 00:58:15,206][87424] Updated weights for policy 0, policy_version 29036 (0.0012) -[2023-11-28 00:58:15,218][87426] Updated weights for policy 1, policy_version 28900 (0.0012) -[2023-11-28 00:58:15,590][87426] Updated weights for policy 1, policy_version 28910 (0.0011) -[2023-11-28 00:58:15,591][87424] Updated weights for policy 0, policy_version 29046 (0.0008) -[2023-11-28 00:58:15,969][87426] Updated weights for policy 1, policy_version 28920 (0.0011) -[2023-11-28 00:58:15,973][87424] Updated weights for policy 0, policy_version 29056 (0.0010) -[2023-11-28 00:58:17,936][87426] Updated weights for policy 1, policy_version 28930 (0.0011) -[2023-11-28 00:58:17,986][87424] Updated weights for policy 0, policy_version 29066 (0.0011) -[2023-11-28 00:58:18,311][87426] Updated weights for policy 1, policy_version 28940 (0.0009) -[2023-11-28 00:58:18,368][87424] Updated weights for policy 0, policy_version 29076 (0.0009) -[2023-11-28 00:58:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 14843904. Throughput: 0: 2745.6, 1: 2804.7. Samples: 14860764. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-11-28 00:58:18,446][86177] Avg episode reward: [(0, '-543.290'), (1, '-515.770')] -[2023-11-28 00:58:18,684][87426] Updated weights for policy 1, policy_version 28950 (0.0007) -[2023-11-28 00:58:18,766][87424] Updated weights for policy 0, policy_version 29086 (0.0008) -[2023-11-28 00:58:18,832][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000029088_7446528.pth... -[2023-11-28 00:58:18,879][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000026560_6799360.pth -[2023-11-28 00:58:19,085][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000028960_7413760.pth... -[2023-11-28 00:58:19,087][87426] Updated weights for policy 1, policy_version 28960 (0.0009) -[2023-11-28 00:58:19,133][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000026432_6766592.pth -[2023-11-28 00:58:21,212][87424] Updated weights for policy 0, policy_version 29096 (0.0010) -[2023-11-28 00:58:21,251][87426] Updated weights for policy 1, policy_version 28970 (0.0010) -[2023-11-28 00:58:21,595][87424] Updated weights for policy 0, policy_version 29106 (0.0010) -[2023-11-28 00:58:21,622][87426] Updated weights for policy 1, policy_version 28980 (0.0011) -[2023-11-28 00:58:21,982][87424] Updated weights for policy 0, policy_version 29116 (0.0010) -[2023-11-28 00:58:22,007][87426] Updated weights for policy 1, policy_version 28990 (0.0011) -[2023-11-28 00:58:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 14876672. Throughput: 0: 2753.5, 1: 2798.1. Samples: 14893352. Policy #0 lag: (min: 31.0, avg: 37.8, max: 63.0) -[2023-11-28 00:58:23,445][86177] Avg episode reward: [(0, '-539.860'), (1, '-511.990')] -[2023-11-28 00:58:24,262][87424] Updated weights for policy 0, policy_version 29126 (0.0011) -[2023-11-28 00:58:24,403][87426] Updated weights for policy 1, policy_version 29000 (0.0009) -[2023-11-28 00:58:24,644][87424] Updated weights for policy 0, policy_version 29136 (0.0012) -[2023-11-28 00:58:24,779][87426] Updated weights for policy 1, policy_version 29010 (0.0010) -[2023-11-28 00:58:25,028][87424] Updated weights for policy 0, policy_version 29146 (0.0012) -[2023-11-28 00:58:25,163][87426] Updated weights for policy 1, policy_version 29020 (0.0010) -[2023-11-28 00:58:27,009][87424] Updated weights for policy 0, policy_version 29156 (0.0011) -[2023-11-28 00:58:27,384][87424] Updated weights for policy 0, policy_version 29166 (0.0011) -[2023-11-28 00:58:27,691][87426] Updated weights for policy 1, policy_version 29030 (0.0008) -[2023-11-28 00:58:27,766][87424] Updated weights for policy 0, policy_version 29176 (0.0008) -[2023-11-28 00:58:28,072][87426] Updated weights for policy 1, policy_version 29040 (0.0007) -[2023-11-28 00:58:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 14901248. Throughput: 0: 2742.7, 1: 2807.1. Samples: 14918176. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 00:58:28,445][86177] Avg episode reward: [(0, '-564.610'), (1, '-515.860')] -[2023-11-28 00:58:28,456][87426] Updated weights for policy 1, policy_version 29050 (0.0008) -[2023-11-28 00:58:29,681][87424] Updated weights for policy 0, policy_version 29186 (0.0009) -[2023-11-28 00:58:30,064][87424] Updated weights for policy 0, policy_version 29196 (0.0009) -[2023-11-28 00:58:30,443][87426] Updated weights for policy 1, policy_version 29060 (0.0009) -[2023-11-28 00:58:30,454][87424] Updated weights for policy 0, policy_version 29206 (0.0008) -[2023-11-28 00:58:30,824][87426] Updated weights for policy 1, policy_version 29070 (0.0011) -[2023-11-28 00:58:30,826][87424] Updated weights for policy 0, policy_version 29216 (0.0012) -[2023-11-28 00:58:31,206][87426] Updated weights for policy 1, policy_version 29080 (0.0012) -[2023-11-28 00:58:32,675][87424] Updated weights for policy 0, policy_version 29226 (0.0012) -[2023-11-28 00:58:33,065][87424] Updated weights for policy 0, policy_version 29236 (0.0012) -[2023-11-28 00:58:33,071][87426] Updated weights for policy 1, policy_version 29090 (0.0011) -[2023-11-28 00:58:33,441][87426] Updated weights for policy 1, policy_version 29100 (0.0010) -[2023-11-28 00:58:33,443][87424] Updated weights for policy 0, policy_version 29246 (0.0012) -[2023-11-28 00:58:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 14925824. Throughput: 0: 2790.5, 1: 2789.1. Samples: 14944040. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 00:58:33,445][86177] Avg episode reward: [(0, '-575.320'), (1, '-517.870')] -[2023-11-28 00:58:33,819][87426] Updated weights for policy 1, policy_version 29110 (0.0012) -[2023-11-28 00:58:34,198][87426] Updated weights for policy 1, policy_version 29120 (0.0012) -[2023-11-28 00:58:35,419][87424] Updated weights for policy 0, policy_version 29256 (0.0012) -[2023-11-28 00:58:35,801][87424] Updated weights for policy 0, policy_version 29266 (0.0012) -[2023-11-28 00:58:36,192][87424] Updated weights for policy 0, policy_version 29276 (0.0008) -[2023-11-28 00:58:36,703][87426] Updated weights for policy 1, policy_version 29130 (0.0008) -[2023-11-28 00:58:37,082][87426] Updated weights for policy 1, policy_version 29140 (0.0007) -[2023-11-28 00:58:37,461][87426] Updated weights for policy 1, policy_version 29150 (0.0008) -[2023-11-28 00:58:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5359.5). Total num frames: 14958592. Throughput: 0: 2776.4, 1: 2797.6. Samples: 14976120. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 00:58:38,445][86177] Avg episode reward: [(0, '-576.130'), (1, '-536.810')] -[2023-11-28 00:58:38,755][87424] Updated weights for policy 0, policy_version 29286 (0.0008) -[2023-11-28 00:58:39,143][87424] Updated weights for policy 0, policy_version 29296 (0.0012) -[2023-11-28 00:58:39,530][87424] Updated weights for policy 0, policy_version 29306 (0.0011) -[2023-11-28 00:58:39,784][87426] Updated weights for policy 1, policy_version 29160 (0.0008) -[2023-11-28 00:58:40,165][87426] Updated weights for policy 1, policy_version 29170 (0.0008) -[2023-11-28 00:58:40,545][87426] Updated weights for policy 1, policy_version 29180 (0.0009) -[2023-11-28 00:58:42,045][87424] Updated weights for policy 0, policy_version 29316 (0.0009) -[2023-11-28 00:58:42,440][87424] Updated weights for policy 0, policy_version 29326 (0.0010) -[2023-11-28 00:58:42,817][87424] Updated weights for policy 0, policy_version 29336 (0.0012) -[2023-11-28 00:58:42,987][87426] Updated weights for policy 1, policy_version 29190 (0.0009) -[2023-11-28 00:58:43,365][87426] Updated weights for policy 1, policy_version 29200 (0.0010) -[2023-11-28 00:58:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 14983168. Throughput: 0: 2754.9, 1: 2765.0. Samples: 14999488. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 00:58:43,445][86177] Avg episode reward: [(0, '-576.080'), (1, '-540.610')] -[2023-11-28 00:58:43,755][87426] Updated weights for policy 1, policy_version 29210 (0.0010) -[2023-11-28 00:58:44,568][87424] Updated weights for policy 0, policy_version 29346 (0.0011) -[2023-11-28 00:58:44,951][87424] Updated weights for policy 0, policy_version 29356 (0.0011) -[2023-11-28 00:58:45,338][87424] Updated weights for policy 0, policy_version 29366 (0.0010) -[2023-11-28 00:58:45,545][87426] Updated weights for policy 1, policy_version 29220 (0.0012) -[2023-11-28 00:58:45,714][87424] Updated weights for policy 0, policy_version 29376 (0.0011) -[2023-11-28 00:58:45,918][87426] Updated weights for policy 1, policy_version 29230 (0.0011) -[2023-11-28 00:58:46,299][87426] Updated weights for policy 1, policy_version 29240 (0.0010) -[2023-11-28 00:58:47,910][87424] Updated weights for policy 0, policy_version 29386 (0.0012) -[2023-11-28 00:58:48,292][87424] Updated weights for policy 0, policy_version 29396 (0.0012) -[2023-11-28 00:58:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 15007744. Throughput: 0: 2741.9, 1: 2747.5. Samples: 15024168. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 00:58:48,446][86177] Avg episode reward: [(0, '-566.950'), (1, '-537.820')] -[2023-11-28 00:58:48,480][87426] Updated weights for policy 1, policy_version 29250 (0.0007) -[2023-11-28 00:58:48,668][87424] Updated weights for policy 0, policy_version 29406 (0.0011) -[2023-11-28 00:58:48,868][87426] Updated weights for policy 1, policy_version 29260 (0.0011) -[2023-11-28 00:58:49,235][87426] Updated weights for policy 1, policy_version 29270 (0.0010) -[2023-11-28 00:58:49,617][87426] Updated weights for policy 1, policy_version 29280 (0.0010) -[2023-11-28 00:58:50,907][87424] Updated weights for policy 0, policy_version 29416 (0.0011) -[2023-11-28 00:58:51,304][87424] Updated weights for policy 0, policy_version 29426 (0.0011) -[2023-11-28 00:58:51,555][87426] Updated weights for policy 1, policy_version 29290 (0.0012) -[2023-11-28 00:58:51,681][87424] Updated weights for policy 0, policy_version 29436 (0.0010) -[2023-11-28 00:58:51,935][87426] Updated weights for policy 1, policy_version 29300 (0.0011) -[2023-11-28 00:58:52,317][87426] Updated weights for policy 1, policy_version 29310 (0.0010) -[2023-11-28 00:58:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 15040512. Throughput: 0: 2717.2, 1: 2743.9. Samples: 15057060. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 00:58:53,445][86177] Avg episode reward: [(0, '-601.050'), (1, '-550.880')] -[2023-11-28 00:58:54,081][87424] Updated weights for policy 0, policy_version 29446 (0.0009) -[2023-11-28 00:58:54,450][87424] Updated weights for policy 0, policy_version 29456 (0.0007) -[2023-11-28 00:58:54,834][87424] Updated weights for policy 0, policy_version 29466 (0.0009) -[2023-11-28 00:58:54,894][87426] Updated weights for policy 1, policy_version 29320 (0.0011) -[2023-11-28 00:58:55,278][87426] Updated weights for policy 1, policy_version 29330 (0.0011) -[2023-11-28 00:58:55,651][87426] Updated weights for policy 1, policy_version 29340 (0.0012) -[2023-11-28 00:58:56,976][87424] Updated weights for policy 0, policy_version 29476 (0.0012) -[2023-11-28 00:58:57,368][87424] Updated weights for policy 0, policy_version 29486 (0.0012) -[2023-11-28 00:58:57,758][87424] Updated weights for policy 0, policy_version 29496 (0.0010) -[2023-11-28 00:58:57,944][87426] Updated weights for policy 1, policy_version 29350 (0.0008) -[2023-11-28 00:58:58,323][87426] Updated weights for policy 1, policy_version 29360 (0.0007) -[2023-11-28 00:58:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 15065088. Throughput: 0: 2714.8, 1: 2713.5. Samples: 15080940. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 00:58:58,445][86177] Avg episode reward: [(0, '-587.330'), (1, '-549.440')] -[2023-11-28 00:58:58,702][87426] Updated weights for policy 1, policy_version 29370 (0.0007) -[2023-11-28 00:58:59,731][87424] Updated weights for policy 0, policy_version 29506 (0.0008) -[2023-11-28 00:59:00,123][87424] Updated weights for policy 0, policy_version 29516 (0.0008) -[2023-11-28 00:59:00,533][87424] Updated weights for policy 0, policy_version 29526 (0.0007) -[2023-11-28 00:59:00,905][87424] Updated weights for policy 0, policy_version 29536 (0.0009) -[2023-11-28 00:59:01,209][87426] Updated weights for policy 1, policy_version 29380 (0.0009) -[2023-11-28 00:59:01,590][87426] Updated weights for policy 1, policy_version 29390 (0.0008) -[2023-11-28 00:59:01,970][87426] Updated weights for policy 1, policy_version 29400 (0.0010) -[2023-11-28 00:59:03,397][87424] Updated weights for policy 0, policy_version 29546 (0.0012) -[2023-11-28 00:59:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 15089664. Throughput: 0: 2734.6, 1: 2708.2. Samples: 15105688. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 00:59:03,445][86177] Avg episode reward: [(0, '-585.440'), (1, '-535.760')] -[2023-11-28 00:59:03,778][87424] Updated weights for policy 0, policy_version 29556 (0.0012) -[2023-11-28 00:59:03,890][87426] Updated weights for policy 1, policy_version 29410 (0.0009) -[2023-11-28 00:59:04,158][87424] Updated weights for policy 0, policy_version 29566 (0.0011) -[2023-11-28 00:59:04,266][87426] Updated weights for policy 1, policy_version 29420 (0.0009) -[2023-11-28 00:59:04,652][87426] Updated weights for policy 1, policy_version 29430 (0.0010) -[2023-11-28 00:59:05,029][87426] Updated weights for policy 1, policy_version 29440 (0.0011) -[2023-11-28 00:59:06,686][87424] Updated weights for policy 0, policy_version 29576 (0.0011) -[2023-11-28 00:59:07,060][87424] Updated weights for policy 0, policy_version 29586 (0.0009) -[2023-11-28 00:59:07,446][87424] Updated weights for policy 0, policy_version 29596 (0.0008) -[2023-11-28 00:59:07,492][87426] Updated weights for policy 1, policy_version 29450 (0.0011) -[2023-11-28 00:59:07,874][87426] Updated weights for policy 1, policy_version 29460 (0.0008) -[2023-11-28 00:59:08,264][87426] Updated weights for policy 1, policy_version 29470 (0.0011) -[2023-11-28 00:59:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 15122432. Throughput: 0: 2724.8, 1: 2684.9. Samples: 15136788. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:59:08,445][86177] Avg episode reward: [(0, '-575.530'), (1, '-534.490')] -[2023-11-28 00:59:09,165][87424] Updated weights for policy 0, policy_version 29606 (0.0011) -[2023-11-28 00:59:09,544][87424] Updated weights for policy 0, policy_version 29616 (0.0012) -[2023-11-28 00:59:09,932][87424] Updated weights for policy 0, policy_version 29626 (0.0011) -[2023-11-28 00:59:09,961][87426] Updated weights for policy 1, policy_version 29480 (0.0011) -[2023-11-28 00:59:10,349][87426] Updated weights for policy 1, policy_version 29490 (0.0008) -[2023-11-28 00:59:10,726][87426] Updated weights for policy 1, policy_version 29500 (0.0009) -[2023-11-28 00:59:12,426][87424] Updated weights for policy 0, policy_version 29636 (0.0012) -[2023-11-28 00:59:12,820][87424] Updated weights for policy 0, policy_version 29646 (0.0011) -[2023-11-28 00:59:13,142][87426] Updated weights for policy 1, policy_version 29510 (0.0009) -[2023-11-28 00:59:13,204][87424] Updated weights for policy 0, policy_version 29656 (0.0012) -[2023-11-28 00:59:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 15138816. Throughput: 0: 2719.7, 1: 2683.5. Samples: 15161320. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:59:13,445][86177] Avg episode reward: [(0, '-542.470'), (1, '-531.050')] -[2023-11-28 00:59:13,526][87426] Updated weights for policy 1, policy_version 29520 (0.0011) -[2023-11-28 00:59:13,905][87426] Updated weights for policy 1, policy_version 29530 (0.0012) -[2023-11-28 00:59:15,413][87424] Updated weights for policy 0, policy_version 29666 (0.0012) -[2023-11-28 00:59:15,800][87424] Updated weights for policy 0, policy_version 29676 (0.0011) -[2023-11-28 00:59:15,823][87426] Updated weights for policy 1, policy_version 29540 (0.0011) -[2023-11-28 00:59:16,171][87424] Updated weights for policy 0, policy_version 29686 (0.0012) -[2023-11-28 00:59:16,202][87426] Updated weights for policy 1, policy_version 29550 (0.0012) -[2023-11-28 00:59:16,549][87424] Updated weights for policy 0, policy_version 29696 (0.0008) -[2023-11-28 00:59:16,578][87426] Updated weights for policy 1, policy_version 29560 (0.0012) -[2023-11-28 00:59:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 15171584. Throughput: 0: 2677.5, 1: 2697.7. Samples: 15185924. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:59:18,445][86177] Avg episode reward: [(0, '-546.730'), (1, '-525.210')] -[2023-11-28 00:59:18,646][87424] Updated weights for policy 0, policy_version 29706 (0.0011) -[2023-11-28 00:59:18,876][87426] Updated weights for policy 1, policy_version 29570 (0.0008) -[2023-11-28 00:59:19,020][87424] Updated weights for policy 0, policy_version 29716 (0.0011) -[2023-11-28 00:59:19,253][87426] Updated weights for policy 1, policy_version 29580 (0.0009) -[2023-11-28 00:59:19,402][87424] Updated weights for policy 0, policy_version 29726 (0.0012) -[2023-11-28 00:59:19,627][87426] Updated weights for policy 1, policy_version 29590 (0.0011) -[2023-11-28 00:59:20,007][87426] Updated weights for policy 1, policy_version 29600 (0.0009) -[2023-11-28 00:59:21,714][87424] Updated weights for policy 0, policy_version 29736 (0.0012) -[2023-11-28 00:59:22,096][87424] Updated weights for policy 0, policy_version 29746 (0.0011) -[2023-11-28 00:59:22,261][87426] Updated weights for policy 1, policy_version 29610 (0.0012) -[2023-11-28 00:59:22,484][87424] Updated weights for policy 0, policy_version 29756 (0.0010) -[2023-11-28 00:59:22,637][87426] Updated weights for policy 1, policy_version 29620 (0.0011) -[2023-11-28 00:59:23,018][87426] Updated weights for policy 1, policy_version 29630 (0.0012) -[2023-11-28 00:59:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 15204352. Throughput: 0: 2663.3, 1: 2709.5. Samples: 15217896. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:59:23,445][86177] Avg episode reward: [(0, '-544.920'), (1, '-524.810')] -[2023-11-28 00:59:24,838][87426] Updated weights for policy 1, policy_version 29640 (0.0009) -[2023-11-28 00:59:24,980][87424] Updated weights for policy 0, policy_version 29766 (0.0010) -[2023-11-28 00:59:25,224][87426] Updated weights for policy 1, policy_version 29650 (0.0008) -[2023-11-28 00:59:25,374][87424] Updated weights for policy 0, policy_version 29776 (0.0011) -[2023-11-28 00:59:25,611][87426] Updated weights for policy 1, policy_version 29660 (0.0007) -[2023-11-28 00:59:25,764][87424] Updated weights for policy 0, policy_version 29786 (0.0012) -[2023-11-28 00:59:27,667][87424] Updated weights for policy 0, policy_version 29796 (0.0012) -[2023-11-28 00:59:28,056][87424] Updated weights for policy 0, policy_version 29806 (0.0011) -[2023-11-28 00:59:28,136][87426] Updated weights for policy 1, policy_version 29670 (0.0009) -[2023-11-28 00:59:28,423][87424] Updated weights for policy 0, policy_version 29816 (0.0008) -[2023-11-28 00:59:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15220736. Throughput: 0: 2665.5, 1: 2709.5. Samples: 15241364. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 00:59:28,445][86177] Avg episode reward: [(0, '-530.180'), (1, '-530.740')] -[2023-11-28 00:59:28,503][87426] Updated weights for policy 1, policy_version 29680 (0.0007) -[2023-11-28 00:59:28,881][87426] Updated weights for policy 1, policy_version 29690 (0.0008) -[2023-11-28 00:59:30,864][87424] Updated weights for policy 0, policy_version 29826 (0.0008) -[2023-11-28 00:59:30,897][87426] Updated weights for policy 1, policy_version 29700 (0.0010) -[2023-11-28 00:59:31,237][87424] Updated weights for policy 0, policy_version 29836 (0.0011) -[2023-11-28 00:59:31,277][87426] Updated weights for policy 1, policy_version 29710 (0.0007) -[2023-11-28 00:59:31,625][87424] Updated weights for policy 0, policy_version 29846 (0.0012) -[2023-11-28 00:59:31,659][87426] Updated weights for policy 1, policy_version 29720 (0.0007) -[2023-11-28 00:59:32,003][87424] Updated weights for policy 0, policy_version 29856 (0.0010) -[2023-11-28 00:59:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 15253504. Throughput: 0: 2675.6, 1: 2717.2. Samples: 15266848. Policy #0 lag: (min: 5.0, avg: 28.9, max: 38.0) -[2023-11-28 00:59:33,446][86177] Avg episode reward: [(0, '-525.610'), (1, '-528.740')] -[2023-11-28 00:59:34,027][87426] Updated weights for policy 1, policy_version 29730 (0.0012) -[2023-11-28 00:59:34,202][87424] Updated weights for policy 0, policy_version 29866 (0.0011) -[2023-11-28 00:59:34,414][87426] Updated weights for policy 1, policy_version 29740 (0.0011) -[2023-11-28 00:59:34,591][87424] Updated weights for policy 0, policy_version 29876 (0.0012) -[2023-11-28 00:59:34,792][87426] Updated weights for policy 1, policy_version 29750 (0.0012) -[2023-11-28 00:59:34,992][87424] Updated weights for policy 0, policy_version 29886 (0.0010) -[2023-11-28 00:59:35,170][87426] Updated weights for policy 1, policy_version 29760 (0.0011) -[2023-11-28 00:59:36,623][87424] Updated weights for policy 0, policy_version 29896 (0.0009) -[2023-11-28 00:59:37,010][87424] Updated weights for policy 0, policy_version 29906 (0.0011) -[2023-11-28 00:59:37,397][87424] Updated weights for policy 0, policy_version 29916 (0.0011) -[2023-11-28 00:59:37,716][87426] Updated weights for policy 1, policy_version 29770 (0.0009) -[2023-11-28 00:59:38,101][87426] Updated weights for policy 1, policy_version 29780 (0.0008) -[2023-11-28 00:59:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15278080. Throughput: 0: 2679.0, 1: 2682.5. Samples: 15298328. Policy #0 lag: (min: 5.0, avg: 28.9, max: 38.0) -[2023-11-28 00:59:38,445][86177] Avg episode reward: [(0, '-527.770'), (1, '-528.240')] -[2023-11-28 00:59:38,478][87426] Updated weights for policy 1, policy_version 29790 (0.0009) -[2023-11-28 00:59:39,975][87424] Updated weights for policy 0, policy_version 29926 (0.0009) -[2023-11-28 00:59:40,358][87424] Updated weights for policy 0, policy_version 29936 (0.0009) -[2023-11-28 00:59:40,742][87424] Updated weights for policy 0, policy_version 29946 (0.0010) -[2023-11-28 00:59:40,833][87426] Updated weights for policy 1, policy_version 29800 (0.0010) -[2023-11-28 00:59:41,217][87426] Updated weights for policy 1, policy_version 29810 (0.0011) -[2023-11-28 00:59:41,588][87426] Updated weights for policy 1, policy_version 29820 (0.0011) -[2023-11-28 00:59:43,276][87424] Updated weights for policy 0, policy_version 29956 (0.0010) -[2023-11-28 00:59:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15302656. Throughput: 0: 2678.8, 1: 2665.2. Samples: 15321420. Policy #0 lag: (min: 5.0, avg: 28.9, max: 38.0) -[2023-11-28 00:59:43,445][86177] Avg episode reward: [(0, '-529.150'), (1, '-526.920')] -[2023-11-28 00:59:43,649][87424] Updated weights for policy 0, policy_version 29966 (0.0010) -[2023-11-28 00:59:43,989][87426] Updated weights for policy 1, policy_version 29830 (0.0009) -[2023-11-28 00:59:44,034][87424] Updated weights for policy 0, policy_version 29976 (0.0007) -[2023-11-28 00:59:44,367][87426] Updated weights for policy 1, policy_version 29840 (0.0007) -[2023-11-28 00:59:44,744][87426] Updated weights for policy 1, policy_version 29850 (0.0007) -[2023-11-28 00:59:46,036][87424] Updated weights for policy 0, policy_version 29986 (0.0008) -[2023-11-28 00:59:46,415][87424] Updated weights for policy 0, policy_version 29996 (0.0012) -[2023-11-28 00:59:46,637][87426] Updated weights for policy 1, policy_version 29860 (0.0010) -[2023-11-28 00:59:46,802][87424] Updated weights for policy 0, policy_version 30006 (0.0011) -[2023-11-28 00:59:47,016][87426] Updated weights for policy 1, policy_version 29870 (0.0010) -[2023-11-28 00:59:47,185][87424] Updated weights for policy 0, policy_version 30016 (0.0008) -[2023-11-28 00:59:47,403][87426] Updated weights for policy 1, policy_version 29880 (0.0011) -[2023-11-28 00:59:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 15335424. Throughput: 0: 2659.6, 1: 2670.8. Samples: 15345556. Policy #0 lag: (min: 5.0, avg: 28.9, max: 38.0) -[2023-11-28 00:59:48,445][86177] Avg episode reward: [(0, '-535.980'), (1, '-524.250')] -[2023-11-28 00:59:49,303][87426] Updated weights for policy 1, policy_version 29890 (0.0011) -[2023-11-28 00:59:49,322][87424] Updated weights for policy 0, policy_version 30026 (0.0012) -[2023-11-28 00:59:49,683][87426] Updated weights for policy 1, policy_version 29900 (0.0011) -[2023-11-28 00:59:49,712][87424] Updated weights for policy 0, policy_version 30036 (0.0011) -[2023-11-28 00:59:50,068][87426] Updated weights for policy 1, policy_version 29910 (0.0010) -[2023-11-28 00:59:50,089][87424] Updated weights for policy 0, policy_version 30046 (0.0009) -[2023-11-28 00:59:50,469][87426] Updated weights for policy 1, policy_version 29920 (0.0011) -[2023-11-28 00:59:52,208][87424] Updated weights for policy 0, policy_version 30056 (0.0011) -[2023-11-28 00:59:52,599][87424] Updated weights for policy 0, policy_version 30066 (0.0009) -[2023-11-28 00:59:52,980][87424] Updated weights for policy 0, policy_version 30076 (0.0010) -[2023-11-28 00:59:52,996][87426] Updated weights for policy 1, policy_version 29930 (0.0009) -[2023-11-28 00:59:53,379][87426] Updated weights for policy 1, policy_version 29940 (0.0012) -[2023-11-28 00:59:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15360000. Throughput: 0: 2662.0, 1: 2671.7. Samples: 15376804. Policy #0 lag: (min: 14.0, avg: 17.6, max: 37.0) -[2023-11-28 00:59:53,445][86177] Avg episode reward: [(0, '-540.450'), (1, '-524.810')] -[2023-11-28 00:59:53,761][87426] Updated weights for policy 1, policy_version 29950 (0.0011) -[2023-11-28 00:59:54,957][87424] Updated weights for policy 0, policy_version 30086 (0.0010) -[2023-11-28 00:59:55,334][87424] Updated weights for policy 0, policy_version 30096 (0.0009) -[2023-11-28 00:59:55,730][87424] Updated weights for policy 0, policy_version 30106 (0.0007) -[2023-11-28 00:59:56,310][87426] Updated weights for policy 1, policy_version 29960 (0.0009) -[2023-11-28 00:59:56,693][87426] Updated weights for policy 1, policy_version 29970 (0.0007) -[2023-11-28 00:59:57,076][87426] Updated weights for policy 1, policy_version 29980 (0.0007) -[2023-11-28 00:59:57,694][87424] Updated weights for policy 0, policy_version 30116 (0.0008) -[2023-11-28 00:59:58,068][87424] Updated weights for policy 0, policy_version 30126 (0.0008) -[2023-11-28 00:59:58,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15384576. Throughput: 0: 2674.6, 1: 2635.9. Samples: 15400292. Policy #0 lag: (min: 14.0, avg: 17.6, max: 37.0) -[2023-11-28 00:59:58,445][86177] Avg episode reward: [(0, '-541.030'), (1, '-524.350')] -[2023-11-28 00:59:58,454][87424] Updated weights for policy 0, policy_version 30136 (0.0008) -[2023-11-28 00:59:59,514][87426] Updated weights for policy 1, policy_version 29990 (0.0010) -[2023-11-28 00:59:59,886][87426] Updated weights for policy 1, policy_version 30000 (0.0010) -[2023-11-28 01:00:00,267][87426] Updated weights for policy 1, policy_version 30010 (0.0011) -[2023-11-28 01:00:00,860][87424] Updated weights for policy 0, policy_version 30146 (0.0008) -[2023-11-28 01:00:01,240][87424] Updated weights for policy 0, policy_version 30156 (0.0010) -[2023-11-28 01:00:01,625][87424] Updated weights for policy 0, policy_version 30166 (0.0008) -[2023-11-28 01:00:02,007][87424] Updated weights for policy 0, policy_version 30176 (0.0010) -[2023-11-28 01:00:02,828][87426] Updated weights for policy 1, policy_version 30020 (0.0012) -[2023-11-28 01:00:03,206][87426] Updated weights for policy 1, policy_version 30030 (0.0011) -[2023-11-28 01:00:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15409152. Throughput: 0: 2694.4, 1: 2612.5. Samples: 15424732. Policy #0 lag: (min: 14.0, avg: 17.6, max: 37.0) -[2023-11-28 01:00:03,445][86177] Avg episode reward: [(0, '-535.460'), (1, '-563.140')] -[2023-11-28 01:00:03,583][87426] Updated weights for policy 1, policy_version 30040 (0.0011) -[2023-11-28 01:00:04,422][87424] Updated weights for policy 0, policy_version 30186 (0.0009) -[2023-11-28 01:00:04,806][87424] Updated weights for policy 0, policy_version 30196 (0.0010) -[2023-11-28 01:00:05,195][87424] Updated weights for policy 0, policy_version 30206 (0.0012) -[2023-11-28 01:00:05,523][87426] Updated weights for policy 1, policy_version 30050 (0.0011) -[2023-11-28 01:00:05,901][87426] Updated weights for policy 1, policy_version 30060 (0.0008) -[2023-11-28 01:00:06,288][87426] Updated weights for policy 1, policy_version 30070 (0.0007) -[2023-11-28 01:00:06,664][87426] Updated weights for policy 1, policy_version 30080 (0.0008) -[2023-11-28 01:00:07,471][87424] Updated weights for policy 0, policy_version 30216 (0.0010) -[2023-11-28 01:00:07,844][87424] Updated weights for policy 0, policy_version 30226 (0.0009) -[2023-11-28 01:00:08,233][87424] Updated weights for policy 0, policy_version 30236 (0.0008) -[2023-11-28 01:00:08,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15441920. Throughput: 0: 2714.7, 1: 2621.4. Samples: 15458020. Policy #0 lag: (min: 14.0, avg: 17.6, max: 37.0) -[2023-11-28 01:00:08,445][86177] Avg episode reward: [(0, '-529.970'), (1, '-560.520')] -[2023-11-28 01:00:09,008][87426] Updated weights for policy 1, policy_version 30090 (0.0008) -[2023-11-28 01:00:09,387][87426] Updated weights for policy 1, policy_version 30100 (0.0007) -[2023-11-28 01:00:09,771][87426] Updated weights for policy 1, policy_version 30110 (0.0008) -[2023-11-28 01:00:10,179][87424] Updated weights for policy 0, policy_version 30246 (0.0011) -[2023-11-28 01:00:10,552][87424] Updated weights for policy 0, policy_version 30256 (0.0013) -[2023-11-28 01:00:10,935][87424] Updated weights for policy 0, policy_version 30266 (0.0008) -[2023-11-28 01:00:11,707][87426] Updated weights for policy 1, policy_version 30120 (0.0011) -[2023-11-28 01:00:12,091][87426] Updated weights for policy 1, policy_version 30130 (0.0012) -[2023-11-28 01:00:12,462][87426] Updated weights for policy 1, policy_version 30140 (0.0012) -[2023-11-28 01:00:13,036][87424] Updated weights for policy 0, policy_version 30276 (0.0009) -[2023-11-28 01:00:13,427][87424] Updated weights for policy 0, policy_version 30286 (0.0011) -[2023-11-28 01:00:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 15466496. Throughput: 0: 2737.4, 1: 2611.6. Samples: 15482068. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 01:00:13,445][86177] Avg episode reward: [(0, '-524.070'), (1, '-562.890')] -[2023-11-28 01:00:13,810][87424] Updated weights for policy 0, policy_version 30296 (0.0010) -[2023-11-28 01:00:14,843][87426] Updated weights for policy 1, policy_version 30150 (0.0009) -[2023-11-28 01:00:15,221][87426] Updated weights for policy 1, policy_version 30160 (0.0010) -[2023-11-28 01:00:15,597][87426] Updated weights for policy 1, policy_version 30170 (0.0011) -[2023-11-28 01:00:15,938][87424] Updated weights for policy 0, policy_version 30306 (0.0010) -[2023-11-28 01:00:16,319][87424] Updated weights for policy 0, policy_version 30316 (0.0012) -[2023-11-28 01:00:16,715][87424] Updated weights for policy 0, policy_version 30326 (0.0012) -[2023-11-28 01:00:17,093][87424] Updated weights for policy 0, policy_version 30336 (0.0009) -[2023-11-28 01:00:17,294][87426] Updated weights for policy 1, policy_version 30180 (0.0011) -[2023-11-28 01:00:17,676][87426] Updated weights for policy 1, policy_version 30190 (0.0010) -[2023-11-28 01:00:18,053][87426] Updated weights for policy 1, policy_version 30200 (0.0011) -[2023-11-28 01:00:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 15499264. Throughput: 0: 2719.5, 1: 2610.8. Samples: 15506708. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 01:00:18,445][86177] Avg episode reward: [(0, '-532.710'), (1, '-560.600')] -[2023-11-28 01:00:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000030208_7733248.pth... -[2023-11-28 01:00:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000027648_7077888.pth -[2023-11-28 01:00:18,844][87424] Updated weights for policy 0, policy_version 30346 (0.0009) -[2023-11-28 01:00:19,225][87424] Updated weights for policy 0, policy_version 30356 (0.0011) -[2023-11-28 01:00:19,607][87424] Updated weights for policy 0, policy_version 30366 (0.0017) -[2023-11-28 01:00:19,680][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000030368_7774208.pth... -[2023-11-28 01:00:19,727][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000027808_7118848.pth -[2023-11-28 01:00:20,527][87426] Updated weights for policy 1, policy_version 30210 (0.0011) -[2023-11-28 01:00:20,905][87426] Updated weights for policy 1, policy_version 30220 (0.0010) -[2023-11-28 01:00:21,286][87426] Updated weights for policy 1, policy_version 30230 (0.0011) -[2023-11-28 01:00:21,663][87426] Updated weights for policy 1, policy_version 30240 (0.0012) -[2023-11-28 01:00:22,006][87424] Updated weights for policy 0, policy_version 30376 (0.0011) -[2023-11-28 01:00:22,390][87424] Updated weights for policy 0, policy_version 30386 (0.0010) -[2023-11-28 01:00:22,774][87424] Updated weights for policy 0, policy_version 30396 (0.0010) -[2023-11-28 01:00:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15523840. Throughput: 0: 2710.3, 1: 2617.9. Samples: 15538100. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 01:00:23,445][86177] Avg episode reward: [(0, '-538.340'), (1, '-567.110')] -[2023-11-28 01:00:24,146][87426] Updated weights for policy 1, policy_version 30250 (0.0012) -[2023-11-28 01:00:24,525][87426] Updated weights for policy 1, policy_version 30260 (0.0011) -[2023-11-28 01:00:24,741][87424] Updated weights for policy 0, policy_version 30406 (0.0015) -[2023-11-28 01:00:24,904][87426] Updated weights for policy 1, policy_version 30270 (0.0008) -[2023-11-28 01:00:25,121][87424] Updated weights for policy 0, policy_version 30416 (0.0011) -[2023-11-28 01:00:25,504][87424] Updated weights for policy 0, policy_version 30426 (0.0007) -[2023-11-28 01:00:26,682][87426] Updated weights for policy 1, policy_version 30280 (0.0011) -[2023-11-28 01:00:27,057][87426] Updated weights for policy 1, policy_version 30290 (0.0011) -[2023-11-28 01:00:27,443][87426] Updated weights for policy 1, policy_version 30300 (0.0012) -[2023-11-28 01:00:27,986][87424] Updated weights for policy 0, policy_version 30436 (0.0009) -[2023-11-28 01:00:28,378][87424] Updated weights for policy 0, policy_version 30446 (0.0010) -[2023-11-28 01:00:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 15548416. Throughput: 0: 2706.9, 1: 2655.1. Samples: 15562712. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 01:00:28,445][86177] Avg episode reward: [(0, '-540.390'), (1, '-533.600')] -[2023-11-28 01:00:28,757][87424] Updated weights for policy 0, policy_version 30456 (0.0007) -[2023-11-28 01:00:29,485][87426] Updated weights for policy 1, policy_version 30310 (0.0012) -[2023-11-28 01:00:29,865][87426] Updated weights for policy 1, policy_version 30320 (0.0011) -[2023-11-28 01:00:30,250][87426] Updated weights for policy 1, policy_version 30330 (0.0011) -[2023-11-28 01:00:31,069][87424] Updated weights for policy 0, policy_version 30466 (0.0008) -[2023-11-28 01:00:31,447][87424] Updated weights for policy 0, policy_version 30476 (0.0012) -[2023-11-28 01:00:31,841][87424] Updated weights for policy 0, policy_version 30486 (0.0012) -[2023-11-28 01:00:32,216][87424] Updated weights for policy 0, policy_version 30496 (0.0012) -[2023-11-28 01:00:32,614][87426] Updated weights for policy 1, policy_version 30340 (0.0011) -[2023-11-28 01:00:32,995][87426] Updated weights for policy 1, policy_version 30350 (0.0009) -[2023-11-28 01:00:33,373][87426] Updated weights for policy 1, policy_version 30360 (0.0008) -[2023-11-28 01:00:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15572992. Throughput: 0: 2721.3, 1: 2660.5. Samples: 15587740. Policy #0 lag: (min: 30.0, avg: 50.5, max: 62.0) -[2023-11-28 01:00:33,445][86177] Avg episode reward: [(0, '-541.980'), (1, '-535.760')] -[2023-11-28 01:00:34,451][87424] Updated weights for policy 0, policy_version 30506 (0.0009) -[2023-11-28 01:00:34,835][87424] Updated weights for policy 0, policy_version 30516 (0.0008) -[2023-11-28 01:00:35,217][87424] Updated weights for policy 0, policy_version 30526 (0.0007) -[2023-11-28 01:00:35,918][87426] Updated weights for policy 1, policy_version 30370 (0.0007) -[2023-11-28 01:00:36,288][87426] Updated weights for policy 1, policy_version 30380 (0.0007) -[2023-11-28 01:00:36,670][87426] Updated weights for policy 1, policy_version 30390 (0.0008) -[2023-11-28 01:00:37,041][87426] Updated weights for policy 1, policy_version 30400 (0.0011) -[2023-11-28 01:00:37,387][87424] Updated weights for policy 0, policy_version 30536 (0.0011) -[2023-11-28 01:00:37,776][87424] Updated weights for policy 0, policy_version 30546 (0.0012) -[2023-11-28 01:00:38,148][87424] Updated weights for policy 0, policy_version 30556 (0.0012) -[2023-11-28 01:00:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 15605760. Throughput: 0: 2732.8, 1: 2659.2. Samples: 15619444. Policy #0 lag: (min: 30.0, avg: 50.5, max: 62.0) -[2023-11-28 01:00:38,445][86177] Avg episode reward: [(0, '-535.660'), (1, '-582.610')] -[2023-11-28 01:00:38,951][87426] Updated weights for policy 1, policy_version 30410 (0.0010) -[2023-11-28 01:00:39,328][87426] Updated weights for policy 1, policy_version 30420 (0.0012) -[2023-11-28 01:00:39,707][87426] Updated weights for policy 1, policy_version 30430 (0.0008) -[2023-11-28 01:00:40,558][87424] Updated weights for policy 0, policy_version 30566 (0.0012) -[2023-11-28 01:00:40,940][87424] Updated weights for policy 0, policy_version 30576 (0.0012) -[2023-11-28 01:00:41,316][87424] Updated weights for policy 0, policy_version 30586 (0.0012) -[2023-11-28 01:00:42,174][87426] Updated weights for policy 1, policy_version 30440 (0.0009) -[2023-11-28 01:00:42,560][87426] Updated weights for policy 1, policy_version 30450 (0.0009) -[2023-11-28 01:00:42,942][87426] Updated weights for policy 1, policy_version 30460 (0.0010) -[2023-11-28 01:00:43,438][87424] Updated weights for policy 0, policy_version 30596 (0.0011) -[2023-11-28 01:00:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 15630336. Throughput: 0: 2706.2, 1: 2687.8. Samples: 15643016. Policy #0 lag: (min: 30.0, avg: 50.5, max: 62.0) -[2023-11-28 01:00:43,445][86177] Avg episode reward: [(0, '-530.960'), (1, '-580.910')] -[2023-11-28 01:00:43,822][87424] Updated weights for policy 0, policy_version 30606 (0.0011) -[2023-11-28 01:00:44,199][87424] Updated weights for policy 0, policy_version 30616 (0.0011) -[2023-11-28 01:00:45,428][87426] Updated weights for policy 1, policy_version 30470 (0.0008) -[2023-11-28 01:00:45,799][87426] Updated weights for policy 1, policy_version 30480 (0.0011) -[2023-11-28 01:00:46,185][87426] Updated weights for policy 1, policy_version 30490 (0.0010) -[2023-11-28 01:00:46,646][87424] Updated weights for policy 0, policy_version 30626 (0.0011) -[2023-11-28 01:00:47,028][87424] Updated weights for policy 0, policy_version 30636 (0.0011) -[2023-11-28 01:00:47,420][87424] Updated weights for policy 0, policy_version 30646 (0.0011) -[2023-11-28 01:00:47,795][87424] Updated weights for policy 0, policy_version 30656 (0.0007) -[2023-11-28 01:00:48,342][87426] Updated weights for policy 1, policy_version 30500 (0.0009) -[2023-11-28 01:00:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15654912. Throughput: 0: 2693.2, 1: 2684.4. Samples: 15666728. Policy #0 lag: (min: 30.0, avg: 50.5, max: 62.0) -[2023-11-28 01:00:48,445][86177] Avg episode reward: [(0, '-529.050'), (1, '-584.150')] -[2023-11-28 01:00:48,728][87426] Updated weights for policy 1, policy_version 30510 (0.0010) -[2023-11-28 01:00:49,098][87426] Updated weights for policy 1, policy_version 30520 (0.0010) -[2023-11-28 01:00:49,518][87424] Updated weights for policy 0, policy_version 30666 (0.0011) -[2023-11-28 01:00:49,899][87424] Updated weights for policy 0, policy_version 30676 (0.0012) -[2023-11-28 01:00:50,287][87424] Updated weights for policy 0, policy_version 30686 (0.0012) -[2023-11-28 01:00:51,331][87426] Updated weights for policy 1, policy_version 30530 (0.0010) -[2023-11-28 01:00:51,702][87426] Updated weights for policy 1, policy_version 30540 (0.0011) -[2023-11-28 01:00:52,079][87426] Updated weights for policy 1, policy_version 30550 (0.0010) -[2023-11-28 01:00:52,456][87426] Updated weights for policy 1, policy_version 30560 (0.0009) -[2023-11-28 01:00:52,521][87424] Updated weights for policy 0, policy_version 30696 (0.0011) -[2023-11-28 01:00:52,911][87424] Updated weights for policy 0, policy_version 30706 (0.0011) -[2023-11-28 01:00:53,301][87424] Updated weights for policy 0, policy_version 30716 (0.0011) -[2023-11-28 01:00:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15679488. Throughput: 0: 2674.4, 1: 2679.5. Samples: 15698944. Policy #0 lag: (min: 30.0, avg: 50.5, max: 62.0) -[2023-11-28 01:00:53,445][86177] Avg episode reward: [(0, '-528.350'), (1, '-583.840')] -[2023-11-28 01:00:54,800][87426] Updated weights for policy 1, policy_version 30570 (0.0011) -[2023-11-28 01:00:55,179][87426] Updated weights for policy 1, policy_version 30580 (0.0011) -[2023-11-28 01:00:55,567][87426] Updated weights for policy 1, policy_version 30590 (0.0011) -[2023-11-28 01:00:55,804][87424] Updated weights for policy 0, policy_version 30726 (0.0012) -[2023-11-28 01:00:56,191][87424] Updated weights for policy 0, policy_version 30736 (0.0012) -[2023-11-28 01:00:56,573][87424] Updated weights for policy 0, policy_version 30746 (0.0012) -[2023-11-28 01:00:57,593][87426] Updated weights for policy 1, policy_version 30600 (0.0009) -[2023-11-28 01:00:57,970][87426] Updated weights for policy 1, policy_version 30610 (0.0008) -[2023-11-28 01:00:58,356][87426] Updated weights for policy 1, policy_version 30620 (0.0009) -[2023-11-28 01:00:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 15704064. Throughput: 0: 2689.5, 1: 2714.9. Samples: 15725268. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 01:00:58,445][86177] Avg episode reward: [(0, '-536.470'), (1, '-582.740')] -[2023-11-28 01:00:58,846][87424] Updated weights for policy 0, policy_version 30756 (0.0011) -[2023-11-28 01:00:59,232][87424] Updated weights for policy 0, policy_version 30766 (0.0012) -[2023-11-28 01:00:59,610][87424] Updated weights for policy 0, policy_version 30776 (0.0011) -[2023-11-28 01:01:00,234][87426] Updated weights for policy 1, policy_version 30630 (0.0010) -[2023-11-28 01:01:00,606][87426] Updated weights for policy 1, policy_version 30640 (0.0011) -[2023-11-28 01:01:00,983][87426] Updated weights for policy 1, policy_version 30650 (0.0011) -[2023-11-28 01:01:01,684][87424] Updated weights for policy 0, policy_version 30786 (0.0012) -[2023-11-28 01:01:02,069][87424] Updated weights for policy 0, policy_version 30796 (0.0009) -[2023-11-28 01:01:02,447][87424] Updated weights for policy 0, policy_version 30806 (0.0008) -[2023-11-28 01:01:02,829][87424] Updated weights for policy 0, policy_version 30816 (0.0010) -[2023-11-28 01:01:03,265][87426] Updated weights for policy 1, policy_version 30660 (0.0010) -[2023-11-28 01:01:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 15736832. Throughput: 0: 2718.0, 1: 2701.9. Samples: 15750604. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 01:01:03,445][86177] Avg episode reward: [(0, '-540.430'), (1, '-535.850')] -[2023-11-28 01:01:03,651][87426] Updated weights for policy 1, policy_version 30670 (0.0008) -[2023-11-28 01:01:04,019][87426] Updated weights for policy 1, policy_version 30680 (0.0012) -[2023-11-28 01:01:04,645][87424] Updated weights for policy 0, policy_version 30826 (0.0012) -[2023-11-28 01:01:05,019][87424] Updated weights for policy 0, policy_version 30836 (0.0012) -[2023-11-28 01:01:05,401][87424] Updated weights for policy 0, policy_version 30846 (0.0011) -[2023-11-28 01:01:06,211][87426] Updated weights for policy 1, policy_version 30690 (0.0012) -[2023-11-28 01:01:06,585][87426] Updated weights for policy 1, policy_version 30700 (0.0011) -[2023-11-28 01:01:06,956][87426] Updated weights for policy 1, policy_version 30710 (0.0012) -[2023-11-28 01:01:07,333][87426] Updated weights for policy 1, policy_version 30720 (0.0012) -[2023-11-28 01:01:07,369][87424] Updated weights for policy 0, policy_version 30856 (0.0009) -[2023-11-28 01:01:07,754][87424] Updated weights for policy 0, policy_version 30866 (0.0012) -[2023-11-28 01:01:08,134][87424] Updated weights for policy 0, policy_version 30876 (0.0012) -[2023-11-28 01:01:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 15769600. Throughput: 0: 2727.5, 1: 2725.3. Samples: 15783476. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 01:01:08,445][86177] Avg episode reward: [(0, '-548.540'), (1, '-572.750')] -[2023-11-28 01:01:09,161][87426] Updated weights for policy 1, policy_version 30730 (0.0011) -[2023-11-28 01:01:09,541][87426] Updated weights for policy 1, policy_version 30740 (0.0007) -[2023-11-28 01:01:09,923][87426] Updated weights for policy 1, policy_version 30750 (0.0008) -[2023-11-28 01:01:10,112][87424] Updated weights for policy 0, policy_version 30886 (0.0012) -[2023-11-28 01:01:10,497][87424] Updated weights for policy 0, policy_version 30896 (0.0012) -[2023-11-28 01:01:10,884][87424] Updated weights for policy 0, policy_version 30906 (0.0012) -[2023-11-28 01:01:12,321][87426] Updated weights for policy 1, policy_version 30760 (0.0010) -[2023-11-28 01:01:12,696][87426] Updated weights for policy 1, policy_version 30770 (0.0009) -[2023-11-28 01:01:13,084][87426] Updated weights for policy 1, policy_version 30780 (0.0010) -[2023-11-28 01:01:13,438][87424] Updated weights for policy 0, policy_version 30916 (0.0008) -[2023-11-28 01:01:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 15794176. Throughput: 0: 2734.3, 1: 2718.0. Samples: 15808064. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 01:01:13,445][86177] Avg episode reward: [(0, '-553.330'), (1, '-600.820')] -[2023-11-28 01:01:13,821][87424] Updated weights for policy 0, policy_version 30926 (0.0008) -[2023-11-28 01:01:14,206][87424] Updated weights for policy 0, policy_version 30936 (0.0008) -[2023-11-28 01:01:15,614][87426] Updated weights for policy 1, policy_version 30790 (0.0011) -[2023-11-28 01:01:15,994][87426] Updated weights for policy 1, policy_version 30800 (0.0011) -[2023-11-28 01:01:16,383][87426] Updated weights for policy 1, policy_version 30810 (0.0011) -[2023-11-28 01:01:16,710][87424] Updated weights for policy 0, policy_version 30946 (0.0008) -[2023-11-28 01:01:17,108][87424] Updated weights for policy 0, policy_version 30956 (0.0007) -[2023-11-28 01:01:17,487][87424] Updated weights for policy 0, policy_version 30966 (0.0008) -[2023-11-28 01:01:17,869][87424] Updated weights for policy 0, policy_version 30976 (0.0008) -[2023-11-28 01:01:18,336][87426] Updated weights for policy 1, policy_version 30820 (0.0011) -[2023-11-28 01:01:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 15818752. Throughput: 0: 2691.7, 1: 2718.7. Samples: 15831208. Policy #0 lag: (min: 13.0, avg: 32.2, max: 45.0) -[2023-11-28 01:01:18,445][86177] Avg episode reward: [(0, '-531.940'), (1, '-600.930')] -[2023-11-28 01:01:18,717][87426] Updated weights for policy 1, policy_version 30830 (0.0011) -[2023-11-28 01:01:19,091][87426] Updated weights for policy 1, policy_version 30840 (0.0012) -[2023-11-28 01:01:20,383][87424] Updated weights for policy 0, policy_version 30986 (0.0012) -[2023-11-28 01:01:20,763][87424] Updated weights for policy 0, policy_version 30996 (0.0012) -[2023-11-28 01:01:21,146][87424] Updated weights for policy 0, policy_version 31006 (0.0012) -[2023-11-28 01:01:21,264][87426] Updated weights for policy 1, policy_version 30850 (0.0012) -[2023-11-28 01:01:21,635][87426] Updated weights for policy 1, policy_version 30860 (0.0012) -[2023-11-28 01:01:22,019][87426] Updated weights for policy 1, policy_version 30870 (0.0009) -[2023-11-28 01:01:22,399][87426] Updated weights for policy 1, policy_version 30880 (0.0011) -[2023-11-28 01:01:23,242][87424] Updated weights for policy 0, policy_version 31016 (0.0009) -[2023-11-28 01:01:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 15843328. Throughput: 0: 2669.1, 1: 2746.8. Samples: 15863156. Policy #0 lag: (min: 13.0, avg: 32.2, max: 45.0) -[2023-11-28 01:01:23,445][86177] Avg episode reward: [(0, '-539.190'), (1, '-655.770')] -[2023-11-28 01:01:23,627][87424] Updated weights for policy 0, policy_version 31026 (0.0008) -[2023-11-28 01:01:24,012][87424] Updated weights for policy 0, policy_version 31036 (0.0008) -[2023-11-28 01:01:24,338][87426] Updated weights for policy 1, policy_version 30890 (0.0012) -[2023-11-28 01:01:24,712][87426] Updated weights for policy 1, policy_version 30900 (0.0012) -[2023-11-28 01:01:25,088][87426] Updated weights for policy 1, policy_version 30910 (0.0012) -[2023-11-28 01:01:26,306][87424] Updated weights for policy 0, policy_version 31046 (0.0007) -[2023-11-28 01:01:26,698][87424] Updated weights for policy 0, policy_version 31056 (0.0009) -[2023-11-28 01:01:27,077][87424] Updated weights for policy 0, policy_version 31066 (0.0009) -[2023-11-28 01:01:27,114][87426] Updated weights for policy 1, policy_version 30920 (0.0009) -[2023-11-28 01:01:27,493][87426] Updated weights for policy 1, policy_version 30930 (0.0008) -[2023-11-28 01:01:27,882][87426] Updated weights for policy 1, policy_version 30940 (0.0007) -[2023-11-28 01:01:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 15876096. Throughput: 0: 2691.8, 1: 2746.2. Samples: 15887728. Policy #0 lag: (min: 13.0, avg: 32.2, max: 45.0) -[2023-11-28 01:01:28,445][86177] Avg episode reward: [(0, '-543.640'), (1, '-659.400')] -[2023-11-28 01:01:28,915][87424] Updated weights for policy 0, policy_version 31076 (0.0008) -[2023-11-28 01:01:29,302][87424] Updated weights for policy 0, policy_version 31086 (0.0008) -[2023-11-28 01:01:29,483][87426] Updated weights for policy 1, policy_version 30950 (0.0009) -[2023-11-28 01:01:29,672][87424] Updated weights for policy 0, policy_version 31096 (0.0007) -[2023-11-28 01:01:29,861][87426] Updated weights for policy 1, policy_version 30960 (0.0010) -[2023-11-28 01:01:30,244][87426] Updated weights for policy 1, policy_version 30970 (0.0012) -[2023-11-28 01:01:31,968][87426] Updated weights for policy 1, policy_version 30980 (0.0010) -[2023-11-28 01:01:32,075][87424] Updated weights for policy 0, policy_version 31106 (0.0009) -[2023-11-28 01:01:32,351][87426] Updated weights for policy 1, policy_version 30990 (0.0010) -[2023-11-28 01:01:32,448][87424] Updated weights for policy 0, policy_version 31116 (0.0010) -[2023-11-28 01:01:32,722][87426] Updated weights for policy 1, policy_version 31000 (0.0011) -[2023-11-28 01:01:32,826][87424] Updated weights for policy 0, policy_version 31126 (0.0009) -[2023-11-28 01:01:33,213][87424] Updated weights for policy 0, policy_version 31136 (0.0008) -[2023-11-28 01:01:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 15908864. Throughput: 0: 2684.8, 1: 2762.9. Samples: 15911876. Policy #0 lag: (min: 13.0, avg: 32.2, max: 45.0) -[2023-11-28 01:01:33,445][86177] Avg episode reward: [(0, '-538.920'), (1, '-672.080')] -[2023-11-28 01:01:35,074][87426] Updated weights for policy 1, policy_version 31010 (0.0011) -[2023-11-28 01:01:35,273][87424] Updated weights for policy 0, policy_version 31146 (0.0007) -[2023-11-28 01:01:35,465][87426] Updated weights for policy 1, policy_version 31020 (0.0007) -[2023-11-28 01:01:35,657][87424] Updated weights for policy 0, policy_version 31156 (0.0008) -[2023-11-28 01:01:35,833][87426] Updated weights for policy 1, policy_version 31030 (0.0010) -[2023-11-28 01:01:36,043][87424] Updated weights for policy 0, policy_version 31166 (0.0009) -[2023-11-28 01:01:36,202][87426] Updated weights for policy 1, policy_version 31040 (0.0012) -[2023-11-28 01:01:38,428][87424] Updated weights for policy 0, policy_version 31176 (0.0011) -[2023-11-28 01:01:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 15925248. Throughput: 0: 2704.7, 1: 2771.7. Samples: 15945384. Policy #0 lag: (min: 13.0, avg: 32.2, max: 45.0) -[2023-11-28 01:01:38,445][86177] Avg episode reward: [(0, '-558.600'), (1, '-693.820')] -[2023-11-28 01:01:38,805][87424] Updated weights for policy 0, policy_version 31186 (0.0010) -[2023-11-28 01:01:38,815][87426] Updated weights for policy 1, policy_version 31050 (0.0010) -[2023-11-28 01:01:39,187][87424] Updated weights for policy 0, policy_version 31196 (0.0011) -[2023-11-28 01:01:39,193][87426] Updated weights for policy 1, policy_version 31060 (0.0011) -[2023-11-28 01:01:39,571][87426] Updated weights for policy 1, policy_version 31070 (0.0011) -[2023-11-28 01:01:41,393][87424] Updated weights for policy 0, policy_version 31206 (0.0011) -[2023-11-28 01:01:41,726][87426] Updated weights for policy 1, policy_version 31080 (0.0011) -[2023-11-28 01:01:41,782][87424] Updated weights for policy 0, policy_version 31216 (0.0011) -[2023-11-28 01:01:42,104][87426] Updated weights for policy 1, policy_version 31090 (0.0011) -[2023-11-28 01:01:42,149][87424] Updated weights for policy 0, policy_version 31226 (0.0011) -[2023-11-28 01:01:42,489][87426] Updated weights for policy 1, policy_version 31100 (0.0010) -[2023-11-28 01:01:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 15958016. Throughput: 0: 2692.1, 1: 2736.3. Samples: 15969544. Policy #0 lag: (min: 31.0, avg: 50.4, max: 84.0) -[2023-11-28 01:01:43,445][86177] Avg episode reward: [(0, '-548.990'), (1, '-704.670')] -[2023-11-28 01:01:44,230][87424] Updated weights for policy 0, policy_version 31236 (0.0010) -[2023-11-28 01:01:44,600][87424] Updated weights for policy 0, policy_version 31246 (0.0008) -[2023-11-28 01:01:44,712][87426] Updated weights for policy 1, policy_version 31110 (0.0010) -[2023-11-28 01:01:44,990][87424] Updated weights for policy 0, policy_version 31256 (0.0008) -[2023-11-28 01:01:45,096][87426] Updated weights for policy 1, policy_version 31120 (0.0010) -[2023-11-28 01:01:45,473][87426] Updated weights for policy 1, policy_version 31130 (0.0007) -[2023-11-28 01:01:47,015][87424] Updated weights for policy 0, policy_version 31266 (0.0007) -[2023-11-28 01:01:47,389][87424] Updated weights for policy 0, policy_version 31276 (0.0008) -[2023-11-28 01:01:47,775][87424] Updated weights for policy 0, policy_version 31286 (0.0008) -[2023-11-28 01:01:47,987][87426] Updated weights for policy 1, policy_version 31140 (0.0009) -[2023-11-28 01:01:48,168][87424] Updated weights for policy 0, policy_version 31296 (0.0011) -[2023-11-28 01:01:48,365][87426] Updated weights for policy 1, policy_version 31150 (0.0012) -[2023-11-28 01:01:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 15982592. Throughput: 0: 2652.6, 1: 2736.0. Samples: 15993092. Policy #0 lag: (min: 31.0, avg: 50.4, max: 84.0) -[2023-11-28 01:01:48,446][86177] Avg episode reward: [(0, '-586.120'), (1, '-694.850')] -[2023-11-28 01:01:48,754][87426] Updated weights for policy 1, policy_version 31160 (0.0012) -[2023-11-28 01:01:50,720][87424] Updated weights for policy 0, policy_version 31306 (0.0008) -[2023-11-28 01:01:50,920][87426] Updated weights for policy 1, policy_version 31170 (0.0010) -[2023-11-28 01:01:51,101][87424] Updated weights for policy 0, policy_version 31316 (0.0009) -[2023-11-28 01:01:51,295][87426] Updated weights for policy 1, policy_version 31180 (0.0010) -[2023-11-28 01:01:51,490][87424] Updated weights for policy 0, policy_version 31326 (0.0011) -[2023-11-28 01:01:51,682][87426] Updated weights for policy 1, policy_version 31190 (0.0011) -[2023-11-28 01:01:52,052][87426] Updated weights for policy 1, policy_version 31200 (0.0009) -[2023-11-28 01:01:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 16007168. Throughput: 0: 2644.0, 1: 2714.3. Samples: 16024600. Policy #0 lag: (min: 31.0, avg: 50.4, max: 84.0) -[2023-11-28 01:01:53,445][86177] Avg episode reward: [(0, '-595.740'), (1, '-689.150')] -[2023-11-28 01:01:53,661][87424] Updated weights for policy 0, policy_version 31336 (0.0010) -[2023-11-28 01:01:54,052][87424] Updated weights for policy 0, policy_version 31346 (0.0009) -[2023-11-28 01:01:54,122][87426] Updated weights for policy 1, policy_version 31210 (0.0009) -[2023-11-28 01:01:54,425][87424] Updated weights for policy 0, policy_version 31356 (0.0008) -[2023-11-28 01:01:54,501][87426] Updated weights for policy 1, policy_version 31220 (0.0010) -[2023-11-28 01:01:54,873][87426] Updated weights for policy 1, policy_version 31230 (0.0012) -[2023-11-28 01:01:56,504][87424] Updated weights for policy 0, policy_version 31366 (0.0009) -[2023-11-28 01:01:56,892][87424] Updated weights for policy 0, policy_version 31376 (0.0007) -[2023-11-28 01:01:57,274][87424] Updated weights for policy 0, policy_version 31386 (0.0007) -[2023-11-28 01:01:57,404][87426] Updated weights for policy 1, policy_version 31240 (0.0012) -[2023-11-28 01:01:57,785][87426] Updated weights for policy 1, policy_version 31250 (0.0011) -[2023-11-28 01:01:58,163][87426] Updated weights for policy 1, policy_version 31260 (0.0011) -[2023-11-28 01:01:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 16039936. Throughput: 0: 2650.1, 1: 2718.3. Samples: 16049644. Policy #0 lag: (min: 31.0, avg: 50.4, max: 84.0) -[2023-11-28 01:01:58,445][86177] Avg episode reward: [(0, '-576.540'), (1, '-748.630')] -[2023-11-28 01:01:59,536][87424] Updated weights for policy 0, policy_version 31396 (0.0008) -[2023-11-28 01:01:59,918][87424] Updated weights for policy 0, policy_version 31406 (0.0009) -[2023-11-28 01:02:00,304][87424] Updated weights for policy 0, policy_version 31416 (0.0007) -[2023-11-28 01:02:00,675][87426] Updated weights for policy 1, policy_version 31270 (0.0009) -[2023-11-28 01:02:01,059][87426] Updated weights for policy 1, policy_version 31280 (0.0008) -[2023-11-28 01:02:01,445][87426] Updated weights for policy 1, policy_version 31290 (0.0008) -[2023-11-28 01:02:02,469][87424] Updated weights for policy 0, policy_version 31426 (0.0011) -[2023-11-28 01:02:02,848][87424] Updated weights for policy 0, policy_version 31436 (0.0010) -[2023-11-28 01:02:03,235][87424] Updated weights for policy 0, policy_version 31446 (0.0008) -[2023-11-28 01:02:03,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 16056320. Throughput: 0: 2685.9, 1: 2711.2. Samples: 16074080. Policy #0 lag: (min: 31.0, avg: 50.4, max: 84.0) -[2023-11-28 01:02:03,446][86177] Avg episode reward: [(0, '-571.990'), (1, '-732.410')] -[2023-11-28 01:02:03,497][87426] Updated weights for policy 1, policy_version 31300 (0.0008) -[2023-11-28 01:02:03,626][87424] Updated weights for policy 0, policy_version 31456 (0.0008) -[2023-11-28 01:02:03,870][87426] Updated weights for policy 1, policy_version 31310 (0.0010) -[2023-11-28 01:02:04,255][87426] Updated weights for policy 1, policy_version 31320 (0.0007) -[2023-11-28 01:02:05,666][87424] Updated weights for policy 0, policy_version 31466 (0.0010) -[2023-11-28 01:02:05,849][87426] Updated weights for policy 1, policy_version 31330 (0.0009) -[2023-11-28 01:02:06,057][87424] Updated weights for policy 0, policy_version 31476 (0.0008) -[2023-11-28 01:02:06,243][87426] Updated weights for policy 1, policy_version 31340 (0.0010) -[2023-11-28 01:02:06,433][87424] Updated weights for policy 0, policy_version 31486 (0.0012) -[2023-11-28 01:02:06,614][87426] Updated weights for policy 1, policy_version 31350 (0.0007) -[2023-11-28 01:02:06,993][87426] Updated weights for policy 1, policy_version 31360 (0.0008) -[2023-11-28 01:02:08,340][87424] Updated weights for policy 0, policy_version 31496 (0.0012) -[2023-11-28 01:02:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 16089088. Throughput: 0: 2706.8, 1: 2692.6. Samples: 16106128. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 01:02:08,445][86177] Avg episode reward: [(0, '-570.810'), (1, '-673.140')] -[2023-11-28 01:02:08,712][87424] Updated weights for policy 0, policy_version 31506 (0.0012) -[2023-11-28 01:02:09,098][87424] Updated weights for policy 0, policy_version 31516 (0.0012) -[2023-11-28 01:02:09,375][87426] Updated weights for policy 1, policy_version 31370 (0.0012) -[2023-11-28 01:02:09,756][87426] Updated weights for policy 1, policy_version 31380 (0.0012) -[2023-11-28 01:02:10,136][87426] Updated weights for policy 1, policy_version 31390 (0.0012) -[2023-11-28 01:02:11,568][87424] Updated weights for policy 0, policy_version 31526 (0.0012) -[2023-11-28 01:02:11,951][87424] Updated weights for policy 0, policy_version 31536 (0.0010) -[2023-11-28 01:02:12,340][87424] Updated weights for policy 0, policy_version 31546 (0.0010) -[2023-11-28 01:02:12,774][87426] Updated weights for policy 1, policy_version 31400 (0.0011) -[2023-11-28 01:02:13,142][87426] Updated weights for policy 1, policy_version 31410 (0.0008) -[2023-11-28 01:02:13,444][86177] Fps is (10 sec: 5734.7, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 16113664. Throughput: 0: 2705.9, 1: 2685.3. Samples: 16130332. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 01:02:13,445][86177] Avg episode reward: [(0, '-573.010'), (1, '-669.020')] -[2023-11-28 01:02:13,536][87426] Updated weights for policy 1, policy_version 31420 (0.0007) -[2023-11-28 01:02:14,966][87424] Updated weights for policy 0, policy_version 31556 (0.0011) -[2023-11-28 01:02:15,348][87424] Updated weights for policy 0, policy_version 31566 (0.0009) -[2023-11-28 01:02:15,732][87424] Updated weights for policy 0, policy_version 31576 (0.0011) -[2023-11-28 01:02:15,885][87426] Updated weights for policy 1, policy_version 31430 (0.0008) -[2023-11-28 01:02:16,256][87426] Updated weights for policy 1, policy_version 31440 (0.0008) -[2023-11-28 01:02:16,632][87426] Updated weights for policy 1, policy_version 31450 (0.0007) -[2023-11-28 01:02:17,484][87424] Updated weights for policy 0, policy_version 31586 (0.0011) -[2023-11-28 01:02:17,863][87424] Updated weights for policy 0, policy_version 31596 (0.0012) -[2023-11-28 01:02:18,269][87424] Updated weights for policy 0, policy_version 31606 (0.0012) -[2023-11-28 01:02:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 16138240. Throughput: 0: 2697.9, 1: 2683.7. Samples: 16154048. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 01:02:18,445][86177] Avg episode reward: [(0, '-563.620'), (1, '-610.070')] -[2023-11-28 01:02:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000031456_8052736.pth... -[2023-11-28 01:02:18,496][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000028960_7413760.pth -[2023-11-28 01:02:18,636][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000031616_8093696.pth... -[2023-11-28 01:02:18,638][87424] Updated weights for policy 0, policy_version 31616 (0.0012) -[2023-11-28 01:02:18,666][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000029088_7446528.pth -[2023-11-28 01:02:18,993][87426] Updated weights for policy 1, policy_version 31460 (0.0009) -[2023-11-28 01:02:19,377][87426] Updated weights for policy 1, policy_version 31470 (0.0011) -[2023-11-28 01:02:19,753][87426] Updated weights for policy 1, policy_version 31480 (0.0011) -[2023-11-28 01:02:21,046][87424] Updated weights for policy 0, policy_version 31626 (0.0011) -[2023-11-28 01:02:21,426][87424] Updated weights for policy 0, policy_version 31636 (0.0016) -[2023-11-28 01:02:21,772][87426] Updated weights for policy 1, policy_version 31490 (0.0011) -[2023-11-28 01:02:21,810][87424] Updated weights for policy 0, policy_version 31646 (0.0010) -[2023-11-28 01:02:22,159][87426] Updated weights for policy 1, policy_version 31500 (0.0011) -[2023-11-28 01:02:22,540][87426] Updated weights for policy 1, policy_version 31510 (0.0012) -[2023-11-28 01:02:22,910][87426] Updated weights for policy 1, policy_version 31520 (0.0012) -[2023-11-28 01:02:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 16171008. Throughput: 0: 2671.5, 1: 2642.3. Samples: 16184504. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 01:02:23,446][86177] Avg episode reward: [(0, '-574.480'), (1, '-625.730')] -[2023-11-28 01:02:24,447][87424] Updated weights for policy 0, policy_version 31656 (0.0008) -[2023-11-28 01:02:24,643][87426] Updated weights for policy 1, policy_version 31530 (0.0011) -[2023-11-28 01:02:24,829][87424] Updated weights for policy 0, policy_version 31666 (0.0010) -[2023-11-28 01:02:25,025][87426] Updated weights for policy 1, policy_version 31540 (0.0007) -[2023-11-28 01:02:25,212][87424] Updated weights for policy 0, policy_version 31676 (0.0011) -[2023-11-28 01:02:25,404][87426] Updated weights for policy 1, policy_version 31550 (0.0007) -[2023-11-28 01:02:27,414][87424] Updated weights for policy 0, policy_version 31686 (0.0011) -[2023-11-28 01:02:27,794][87424] Updated weights for policy 0, policy_version 31696 (0.0011) -[2023-11-28 01:02:27,794][87426] Updated weights for policy 1, policy_version 31560 (0.0010) -[2023-11-28 01:02:28,176][87426] Updated weights for policy 1, policy_version 31570 (0.0007) -[2023-11-28 01:02:28,189][87424] Updated weights for policy 0, policy_version 31706 (0.0008) -[2023-11-28 01:02:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 16195584. Throughput: 0: 2655.2, 1: 2669.8. Samples: 16209168. Policy #0 lag: (min: 31.0, avg: 43.9, max: 63.0) -[2023-11-28 01:02:28,445][86177] Avg episode reward: [(0, '-533.670'), (1, '-632.900')] -[2023-11-28 01:02:28,561][87426] Updated weights for policy 1, policy_version 31580 (0.0007) -[2023-11-28 01:02:29,944][87424] Updated weights for policy 0, policy_version 31716 (0.0008) -[2023-11-28 01:02:30,327][87424] Updated weights for policy 0, policy_version 31726 (0.0008) -[2023-11-28 01:02:30,710][87424] Updated weights for policy 0, policy_version 31736 (0.0011) -[2023-11-28 01:02:31,123][87426] Updated weights for policy 1, policy_version 31590 (0.0010) -[2023-11-28 01:02:31,508][87426] Updated weights for policy 1, policy_version 31600 (0.0010) -[2023-11-28 01:02:31,883][87426] Updated weights for policy 1, policy_version 31610 (0.0011) -[2023-11-28 01:02:33,231][87424] Updated weights for policy 0, policy_version 31746 (0.0011) -[2023-11-28 01:02:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 16220160. Throughput: 0: 2686.2, 1: 2668.7. Samples: 16234064. Policy #0 lag: (min: 31.0, avg: 43.9, max: 63.0) -[2023-11-28 01:02:33,445][86177] Avg episode reward: [(0, '-542.550'), (1, '-607.720')] -[2023-11-28 01:02:33,609][87424] Updated weights for policy 0, policy_version 31756 (0.0010) -[2023-11-28 01:02:33,995][87424] Updated weights for policy 0, policy_version 31766 (0.0010) -[2023-11-28 01:02:34,361][87426] Updated weights for policy 1, policy_version 31620 (0.0011) -[2023-11-28 01:02:34,381][87424] Updated weights for policy 0, policy_version 31776 (0.0012) -[2023-11-28 01:02:34,752][87426] Updated weights for policy 1, policy_version 31630 (0.0008) -[2023-11-28 01:02:35,123][87426] Updated weights for policy 1, policy_version 31640 (0.0010) -[2023-11-28 01:02:36,188][87424] Updated weights for policy 0, policy_version 31786 (0.0012) -[2023-11-28 01:02:36,574][87424] Updated weights for policy 0, policy_version 31796 (0.0012) -[2023-11-28 01:02:36,889][87426] Updated weights for policy 1, policy_version 31650 (0.0010) -[2023-11-28 01:02:36,953][87424] Updated weights for policy 0, policy_version 31806 (0.0012) -[2023-11-28 01:02:37,271][87426] Updated weights for policy 1, policy_version 31660 (0.0012) -[2023-11-28 01:02:37,641][87426] Updated weights for policy 1, policy_version 31670 (0.0011) -[2023-11-28 01:02:38,024][87426] Updated weights for policy 1, policy_version 31680 (0.0009) -[2023-11-28 01:02:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 16252928. Throughput: 0: 2717.2, 1: 2697.0. Samples: 16268236. Policy #0 lag: (min: 31.0, avg: 43.9, max: 63.0) -[2023-11-28 01:02:38,445][86177] Avg episode reward: [(0, '-534.690'), (1, '-606.830')] -[2023-11-28 01:02:38,824][87424] Updated weights for policy 0, policy_version 31816 (0.0009) -[2023-11-28 01:02:39,215][87424] Updated weights for policy 0, policy_version 31826 (0.0008) -[2023-11-28 01:02:39,591][87424] Updated weights for policy 0, policy_version 31836 (0.0008) -[2023-11-28 01:02:40,335][87426] Updated weights for policy 1, policy_version 31690 (0.0012) -[2023-11-28 01:02:40,717][87426] Updated weights for policy 1, policy_version 31700 (0.0011) -[2023-11-28 01:02:41,092][87426] Updated weights for policy 1, policy_version 31710 (0.0012) -[2023-11-28 01:02:41,473][87424] Updated weights for policy 0, policy_version 31846 (0.0011) -[2023-11-28 01:02:41,877][87424] Updated weights for policy 0, policy_version 31856 (0.0011) -[2023-11-28 01:02:42,253][87424] Updated weights for policy 0, policy_version 31866 (0.0012) -[2023-11-28 01:02:43,264][87426] Updated weights for policy 1, policy_version 31720 (0.0012) -[2023-11-28 01:02:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 16277504. Throughput: 0: 2720.2, 1: 2675.8. Samples: 16292464. Policy #0 lag: (min: 31.0, avg: 43.9, max: 63.0) -[2023-11-28 01:02:43,445][86177] Avg episode reward: [(0, '-531.120'), (1, '-548.350')] -[2023-11-28 01:02:43,637][87426] Updated weights for policy 1, policy_version 31730 (0.0007) -[2023-11-28 01:02:44,040][87426] Updated weights for policy 1, policy_version 31740 (0.0008) -[2023-11-28 01:02:44,195][87424] Updated weights for policy 0, policy_version 31876 (0.0010) -[2023-11-28 01:02:44,585][87424] Updated weights for policy 0, policy_version 31886 (0.0011) -[2023-11-28 01:02:44,960][87424] Updated weights for policy 0, policy_version 31896 (0.0011) -[2023-11-28 01:02:45,793][87426] Updated weights for policy 1, policy_version 31750 (0.0009) -[2023-11-28 01:02:46,163][87426] Updated weights for policy 1, policy_version 31760 (0.0007) -[2023-11-28 01:02:46,548][87426] Updated weights for policy 1, policy_version 31770 (0.0007) -[2023-11-28 01:02:47,419][87424] Updated weights for policy 0, policy_version 31906 (0.0012) -[2023-11-28 01:02:47,793][87424] Updated weights for policy 0, policy_version 31916 (0.0012) -[2023-11-28 01:02:48,192][87424] Updated weights for policy 0, policy_version 31926 (0.0011) -[2023-11-28 01:02:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 16302080. Throughput: 0: 2723.3, 1: 2685.0. Samples: 16317452. Policy #0 lag: (min: 31.0, avg: 43.9, max: 63.0) -[2023-11-28 01:02:48,445][86177] Avg episode reward: [(0, '-535.940'), (1, '-550.890')] -[2023-11-28 01:02:48,573][87424] Updated weights for policy 0, policy_version 31936 (0.0008) -[2023-11-28 01:02:48,870][87426] Updated weights for policy 1, policy_version 31780 (0.0008) -[2023-11-28 01:02:49,255][87426] Updated weights for policy 1, policy_version 31790 (0.0008) -[2023-11-28 01:02:49,631][87426] Updated weights for policy 1, policy_version 31800 (0.0009) -[2023-11-28 01:02:51,185][87424] Updated weights for policy 0, policy_version 31946 (0.0011) -[2023-11-28 01:02:51,580][87424] Updated weights for policy 0, policy_version 31956 (0.0012) -[2023-11-28 01:02:51,759][87426] Updated weights for policy 1, policy_version 31810 (0.0012) -[2023-11-28 01:02:51,954][87424] Updated weights for policy 0, policy_version 31966 (0.0011) -[2023-11-28 01:02:52,141][87426] Updated weights for policy 1, policy_version 31820 (0.0009) -[2023-11-28 01:02:52,522][87426] Updated weights for policy 1, policy_version 31830 (0.0008) -[2023-11-28 01:02:52,909][87426] Updated weights for policy 1, policy_version 31840 (0.0008) -[2023-11-28 01:02:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 16334848. Throughput: 0: 2694.4, 1: 2687.2. Samples: 16348300. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 01:02:53,445][86177] Avg episode reward: [(0, '-534.150'), (1, '-536.750')] -[2023-11-28 01:02:54,469][87424] Updated weights for policy 0, policy_version 31976 (0.0008) -[2023-11-28 01:02:54,854][87424] Updated weights for policy 0, policy_version 31986 (0.0008) -[2023-11-28 01:02:55,243][87424] Updated weights for policy 0, policy_version 31996 (0.0007) -[2023-11-28 01:02:55,410][87426] Updated weights for policy 1, policy_version 31850 (0.0011) -[2023-11-28 01:02:55,790][87426] Updated weights for policy 1, policy_version 31860 (0.0008) -[2023-11-28 01:02:56,153][87426] Updated weights for policy 1, policy_version 31870 (0.0011) -[2023-11-28 01:02:57,702][87424] Updated weights for policy 0, policy_version 32006 (0.0007) -[2023-11-28 01:02:58,093][87424] Updated weights for policy 0, policy_version 32016 (0.0007) -[2023-11-28 01:02:58,228][87426] Updated weights for policy 1, policy_version 31880 (0.0010) -[2023-11-28 01:02:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 16351232. Throughput: 0: 2671.0, 1: 2711.0. Samples: 16372524. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 01:02:58,445][86177] Avg episode reward: [(0, '-534.520'), (1, '-538.450')] -[2023-11-28 01:02:58,469][87424] Updated weights for policy 0, policy_version 32026 (0.0010) -[2023-11-28 01:02:58,607][87426] Updated weights for policy 1, policy_version 31890 (0.0007) -[2023-11-28 01:02:58,987][87426] Updated weights for policy 1, policy_version 31900 (0.0009) -[2023-11-28 01:03:00,873][87424] Updated weights for policy 0, policy_version 32036 (0.0011) -[2023-11-28 01:03:00,978][87426] Updated weights for policy 1, policy_version 31910 (0.0010) -[2023-11-28 01:03:01,253][87424] Updated weights for policy 0, policy_version 32046 (0.0008) -[2023-11-28 01:03:01,352][87426] Updated weights for policy 1, policy_version 31920 (0.0011) -[2023-11-28 01:03:01,622][87424] Updated weights for policy 0, policy_version 32056 (0.0011) -[2023-11-28 01:03:01,742][87426] Updated weights for policy 1, policy_version 31930 (0.0008) -[2023-11-28 01:03:03,414][87424] Updated weights for policy 0, policy_version 32066 (0.0012) -[2023-11-28 01:03:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 16384000. Throughput: 0: 2685.8, 1: 2703.8. Samples: 16396580. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 01:03:03,445][86177] Avg episode reward: [(0, '-523.620'), (1, '-536.950')] -[2023-11-28 01:03:03,796][87424] Updated weights for policy 0, policy_version 32076 (0.0012) -[2023-11-28 01:03:03,805][87426] Updated weights for policy 1, policy_version 31940 (0.0010) -[2023-11-28 01:03:04,177][87424] Updated weights for policy 0, policy_version 32086 (0.0010) -[2023-11-28 01:03:04,186][87426] Updated weights for policy 1, policy_version 31950 (0.0007) -[2023-11-28 01:03:04,561][87424] Updated weights for policy 0, policy_version 32096 (0.0008) -[2023-11-28 01:03:04,572][87426] Updated weights for policy 1, policy_version 31960 (0.0010) -[2023-11-28 01:03:06,658][87424] Updated weights for policy 0, policy_version 32106 (0.0012) -[2023-11-28 01:03:06,709][87426] Updated weights for policy 1, policy_version 31970 (0.0011) -[2023-11-28 01:03:07,042][87424] Updated weights for policy 0, policy_version 32116 (0.0011) -[2023-11-28 01:03:07,088][87426] Updated weights for policy 1, policy_version 31980 (0.0009) -[2023-11-28 01:03:07,422][87424] Updated weights for policy 0, policy_version 32126 (0.0011) -[2023-11-28 01:03:07,474][87426] Updated weights for policy 1, policy_version 31990 (0.0011) -[2023-11-28 01:03:07,838][87426] Updated weights for policy 1, policy_version 32000 (0.0012) -[2023-11-28 01:03:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 16416768. Throughput: 0: 2710.5, 1: 2731.2. Samples: 16429380. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 01:03:08,446][86177] Avg episode reward: [(0, '-506.440'), (1, '-533.680')] -[2023-11-28 01:03:09,089][87424] Updated weights for policy 0, policy_version 32136 (0.0011) -[2023-11-28 01:03:09,475][87424] Updated weights for policy 0, policy_version 32146 (0.0012) -[2023-11-28 01:03:09,863][87424] Updated weights for policy 0, policy_version 32156 (0.0011) -[2023-11-28 01:03:09,985][87426] Updated weights for policy 1, policy_version 32010 (0.0011) -[2023-11-28 01:03:10,366][87426] Updated weights for policy 1, policy_version 32020 (0.0009) -[2023-11-28 01:03:10,750][87426] Updated weights for policy 1, policy_version 32030 (0.0011) -[2023-11-28 01:03:12,300][87424] Updated weights for policy 0, policy_version 32166 (0.0011) -[2023-11-28 01:03:12,587][87426] Updated weights for policy 1, policy_version 32040 (0.0011) -[2023-11-28 01:03:12,672][87424] Updated weights for policy 0, policy_version 32176 (0.0012) -[2023-11-28 01:03:12,961][87426] Updated weights for policy 1, policy_version 32050 (0.0011) -[2023-11-28 01:03:13,055][87424] Updated weights for policy 0, policy_version 32186 (0.0011) -[2023-11-28 01:03:13,341][87426] Updated weights for policy 1, policy_version 32060 (0.0011) -[2023-11-28 01:03:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 16441344. Throughput: 0: 2715.5, 1: 2738.4. Samples: 16454592. Policy #0 lag: (min: 31.0, avg: 47.0, max: 65.0) -[2023-11-28 01:03:13,445][86177] Avg episode reward: [(0, '-516.560'), (1, '-551.330')] -[2023-11-28 01:03:15,516][87424] Updated weights for policy 0, policy_version 32196 (0.0012) -[2023-11-28 01:03:15,773][87426] Updated weights for policy 1, policy_version 32070 (0.0011) -[2023-11-28 01:03:15,901][87424] Updated weights for policy 0, policy_version 32206 (0.0012) -[2023-11-28 01:03:16,146][87426] Updated weights for policy 1, policy_version 32080 (0.0012) -[2023-11-28 01:03:16,281][87424] Updated weights for policy 0, policy_version 32216 (0.0011) -[2023-11-28 01:03:16,535][87426] Updated weights for policy 1, policy_version 32090 (0.0011) -[2023-11-28 01:03:18,325][87426] Updated weights for policy 1, policy_version 32100 (0.0012) -[2023-11-28 01:03:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 16465920. Throughput: 0: 2680.5, 1: 2758.1. Samples: 16478804. Policy #0 lag: (min: 31.0, avg: 47.0, max: 65.0) -[2023-11-28 01:03:18,445][86177] Avg episode reward: [(0, '-512.730'), (1, '-550.440')] -[2023-11-28 01:03:18,489][87424] Updated weights for policy 0, policy_version 32226 (0.0011) -[2023-11-28 01:03:18,703][87426] Updated weights for policy 1, policy_version 32110 (0.0011) -[2023-11-28 01:03:18,861][87424] Updated weights for policy 0, policy_version 32236 (0.0008) -[2023-11-28 01:03:19,088][87426] Updated weights for policy 1, policy_version 32120 (0.0011) -[2023-11-28 01:03:19,245][87424] Updated weights for policy 0, policy_version 32246 (0.0011) -[2023-11-28 01:03:19,632][87424] Updated weights for policy 0, policy_version 32256 (0.0012) -[2023-11-28 01:03:21,642][87426] Updated weights for policy 1, policy_version 32130 (0.0009) -[2023-11-28 01:03:21,644][87424] Updated weights for policy 0, policy_version 32266 (0.0009) -[2023-11-28 01:03:22,023][87426] Updated weights for policy 1, policy_version 32140 (0.0011) -[2023-11-28 01:03:22,043][87424] Updated weights for policy 0, policy_version 32276 (0.0010) -[2023-11-28 01:03:22,402][87426] Updated weights for policy 1, policy_version 32150 (0.0011) -[2023-11-28 01:03:22,423][87424] Updated weights for policy 0, policy_version 32286 (0.0011) -[2023-11-28 01:03:22,776][87426] Updated weights for policy 1, policy_version 32160 (0.0012) -[2023-11-28 01:03:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 16498688. Throughput: 0: 2669.8, 1: 2746.7. Samples: 16511980. Policy #0 lag: (min: 31.0, avg: 47.0, max: 65.0) -[2023-11-28 01:03:23,445][86177] Avg episode reward: [(0, '-513.990'), (1, '-589.580')] -[2023-11-28 01:03:24,793][87424] Updated weights for policy 0, policy_version 32296 (0.0011) -[2023-11-28 01:03:24,853][87426] Updated weights for policy 1, policy_version 32170 (0.0011) -[2023-11-28 01:03:25,167][87424] Updated weights for policy 0, policy_version 32306 (0.0011) -[2023-11-28 01:03:25,224][87426] Updated weights for policy 1, policy_version 32180 (0.0012) -[2023-11-28 01:03:25,557][87424] Updated weights for policy 0, policy_version 32316 (0.0007) -[2023-11-28 01:03:25,604][87426] Updated weights for policy 1, policy_version 32190 (0.0011) -[2023-11-28 01:03:27,531][87426] Updated weights for policy 1, policy_version 32200 (0.0011) -[2023-11-28 01:03:27,901][87426] Updated weights for policy 1, policy_version 32210 (0.0012) -[2023-11-28 01:03:27,952][87424] Updated weights for policy 0, policy_version 32326 (0.0009) -[2023-11-28 01:03:28,285][87426] Updated weights for policy 1, policy_version 32220 (0.0011) -[2023-11-28 01:03:28,341][87424] Updated weights for policy 0, policy_version 32336 (0.0012) -[2023-11-28 01:03:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 16523264. Throughput: 0: 2663.1, 1: 2794.5. Samples: 16538056. Policy #0 lag: (min: 31.0, avg: 47.0, max: 65.0) -[2023-11-28 01:03:28,446][86177] Avg episode reward: [(0, '-516.600'), (1, '-584.400')] -[2023-11-28 01:03:28,716][87424] Updated weights for policy 0, policy_version 32346 (0.0012) -[2023-11-28 01:03:30,618][87424] Updated weights for policy 0, policy_version 32356 (0.0011) -[2023-11-28 01:03:30,728][87426] Updated weights for policy 1, policy_version 32230 (0.0012) -[2023-11-28 01:03:30,999][87424] Updated weights for policy 0, policy_version 32366 (0.0011) -[2023-11-28 01:03:31,109][87426] Updated weights for policy 1, policy_version 32240 (0.0011) -[2023-11-28 01:03:31,383][87424] Updated weights for policy 0, policy_version 32376 (0.0009) -[2023-11-28 01:03:31,488][87426] Updated weights for policy 1, policy_version 32250 (0.0012) -[2023-11-28 01:03:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 16547840. Throughput: 0: 2655.4, 1: 2783.6. Samples: 16562208. Policy #0 lag: (min: 31.0, avg: 47.0, max: 65.0) -[2023-11-28 01:03:33,445][86177] Avg episode reward: [(0, '-510.010'), (1, '-568.420')] -[2023-11-28 01:03:33,682][87424] Updated weights for policy 0, policy_version 32386 (0.0011) -[2023-11-28 01:03:33,886][87426] Updated weights for policy 1, policy_version 32260 (0.0011) -[2023-11-28 01:03:34,057][87424] Updated weights for policy 0, policy_version 32396 (0.0009) -[2023-11-28 01:03:34,265][87426] Updated weights for policy 1, policy_version 32270 (0.0011) -[2023-11-28 01:03:34,438][87424] Updated weights for policy 0, policy_version 32406 (0.0007) -[2023-11-28 01:03:34,637][87426] Updated weights for policy 1, policy_version 32280 (0.0011) -[2023-11-28 01:03:34,820][87424] Updated weights for policy 0, policy_version 32416 (0.0008) -[2023-11-28 01:03:36,614][87426] Updated weights for policy 1, policy_version 32290 (0.0012) -[2023-11-28 01:03:36,936][87424] Updated weights for policy 0, policy_version 32426 (0.0011) -[2023-11-28 01:03:36,992][87426] Updated weights for policy 1, policy_version 32300 (0.0012) -[2023-11-28 01:03:37,317][87424] Updated weights for policy 0, policy_version 32436 (0.0011) -[2023-11-28 01:03:37,376][87426] Updated weights for policy 1, policy_version 32310 (0.0011) -[2023-11-28 01:03:37,705][87424] Updated weights for policy 0, policy_version 32446 (0.0011) -[2023-11-28 01:03:37,749][87426] Updated weights for policy 1, policy_version 32320 (0.0011) -[2023-11-28 01:03:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 16580608. Throughput: 0: 2678.0, 1: 2787.6. Samples: 16594252. Policy #0 lag: (min: 31.0, avg: 54.0, max: 82.0) -[2023-11-28 01:03:38,445][86177] Avg episode reward: [(0, '-513.180'), (1, '-560.140')] -[2023-11-28 01:03:39,535][87426] Updated weights for policy 1, policy_version 32330 (0.0011) -[2023-11-28 01:03:39,595][87424] Updated weights for policy 0, policy_version 32456 (0.0011) -[2023-11-28 01:03:39,906][87426] Updated weights for policy 1, policy_version 32340 (0.0011) -[2023-11-28 01:03:39,974][87424] Updated weights for policy 0, policy_version 32466 (0.0012) -[2023-11-28 01:03:40,286][87426] Updated weights for policy 1, policy_version 32350 (0.0012) -[2023-11-28 01:03:40,362][87424] Updated weights for policy 0, policy_version 32476 (0.0009) -[2023-11-28 01:03:42,534][87426] Updated weights for policy 1, policy_version 32360 (0.0010) -[2023-11-28 01:03:42,656][87424] Updated weights for policy 0, policy_version 32486 (0.0012) -[2023-11-28 01:03:42,918][87426] Updated weights for policy 1, policy_version 32370 (0.0008) -[2023-11-28 01:03:43,036][87424] Updated weights for policy 0, policy_version 32496 (0.0012) -[2023-11-28 01:03:43,294][87426] Updated weights for policy 1, policy_version 32380 (0.0010) -[2023-11-28 01:03:43,417][87424] Updated weights for policy 0, policy_version 32506 (0.0012) -[2023-11-28 01:03:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 16596992. Throughput: 0: 2713.1, 1: 2787.4. Samples: 16620048. Policy #0 lag: (min: 31.0, avg: 54.0, max: 82.0) -[2023-11-28 01:03:43,445][86177] Avg episode reward: [(0, '-516.260'), (1, '-517.480')] -[2023-11-28 01:03:45,428][87426] Updated weights for policy 1, policy_version 32390 (0.0017) -[2023-11-28 01:03:45,551][87424] Updated weights for policy 0, policy_version 32516 (0.0012) -[2023-11-28 01:03:45,805][87426] Updated weights for policy 1, policy_version 32400 (0.0009) -[2023-11-28 01:03:45,934][87424] Updated weights for policy 0, policy_version 32526 (0.0012) -[2023-11-28 01:03:46,187][87426] Updated weights for policy 1, policy_version 32410 (0.0010) -[2023-11-28 01:03:46,322][87424] Updated weights for policy 0, policy_version 32536 (0.0012) -[2023-11-28 01:03:48,099][87426] Updated weights for policy 1, policy_version 32420 (0.0011) -[2023-11-28 01:03:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 16629760. Throughput: 0: 2737.7, 1: 2784.0. Samples: 16645056. Policy #0 lag: (min: 31.0, avg: 54.0, max: 82.0) -[2023-11-28 01:03:48,445][86177] Avg episode reward: [(0, '-518.330'), (1, '-515.560')] -[2023-11-28 01:03:48,482][87426] Updated weights for policy 1, policy_version 32430 (0.0011) -[2023-11-28 01:03:48,568][87424] Updated weights for policy 0, policy_version 32546 (0.0012) -[2023-11-28 01:03:48,864][87426] Updated weights for policy 1, policy_version 32440 (0.0009) -[2023-11-28 01:03:48,951][87424] Updated weights for policy 0, policy_version 32556 (0.0011) -[2023-11-28 01:03:49,332][87424] Updated weights for policy 0, policy_version 32566 (0.0012) -[2023-11-28 01:03:49,714][87424] Updated weights for policy 0, policy_version 32576 (0.0011) -[2023-11-28 01:03:51,030][87426] Updated weights for policy 1, policy_version 32450 (0.0010) -[2023-11-28 01:03:51,407][87426] Updated weights for policy 1, policy_version 32460 (0.0010) -[2023-11-28 01:03:51,725][87424] Updated weights for policy 0, policy_version 32586 (0.0011) -[2023-11-28 01:03:51,791][87426] Updated weights for policy 1, policy_version 32470 (0.0011) -[2023-11-28 01:03:52,099][87424] Updated weights for policy 0, policy_version 32596 (0.0010) -[2023-11-28 01:03:52,167][87426] Updated weights for policy 1, policy_version 32480 (0.0008) -[2023-11-28 01:03:52,487][87424] Updated weights for policy 0, policy_version 32606 (0.0009) -[2023-11-28 01:03:53,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 16662528. Throughput: 0: 2744.5, 1: 2796.1. Samples: 16678708. Policy #0 lag: (min: 31.0, avg: 54.0, max: 82.0) -[2023-11-28 01:03:53,445][86177] Avg episode reward: [(0, '-508.050'), (1, '-509.810')] -[2023-11-28 01:03:54,426][87426] Updated weights for policy 1, policy_version 32490 (0.0008) -[2023-11-28 01:03:54,803][87426] Updated weights for policy 1, policy_version 32500 (0.0007) -[2023-11-28 01:03:54,861][87424] Updated weights for policy 0, policy_version 32616 (0.0007) -[2023-11-28 01:03:55,186][87426] Updated weights for policy 1, policy_version 32510 (0.0010) -[2023-11-28 01:03:55,244][87424] Updated weights for policy 0, policy_version 32626 (0.0007) -[2023-11-28 01:03:55,628][87424] Updated weights for policy 0, policy_version 32636 (0.0008) -[2023-11-28 01:03:57,264][87426] Updated weights for policy 1, policy_version 32520 (0.0009) -[2023-11-28 01:03:57,645][87426] Updated weights for policy 1, policy_version 32530 (0.0008) -[2023-11-28 01:03:57,943][87424] Updated weights for policy 0, policy_version 32646 (0.0007) -[2023-11-28 01:03:58,036][87426] Updated weights for policy 1, policy_version 32540 (0.0009) -[2023-11-28 01:03:58,315][87424] Updated weights for policy 0, policy_version 32656 (0.0010) -[2023-11-28 01:03:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 16687104. Throughput: 0: 2733.3, 1: 2777.2. Samples: 16702560. Policy #0 lag: (min: 31.0, avg: 54.0, max: 82.0) -[2023-11-28 01:03:58,445][86177] Avg episode reward: [(0, '-501.160'), (1, '-513.750')] -[2023-11-28 01:03:58,698][87424] Updated weights for policy 0, policy_version 32666 (0.0012) -[2023-11-28 01:03:58,922][87281] Saving new best policy, reward=-501.160! -[2023-11-28 01:04:00,378][87426] Updated weights for policy 1, policy_version 32550 (0.0011) -[2023-11-28 01:04:00,754][87426] Updated weights for policy 1, policy_version 32560 (0.0011) -[2023-11-28 01:04:00,801][87424] Updated weights for policy 0, policy_version 32676 (0.0014) -[2023-11-28 01:04:01,127][87426] Updated weights for policy 1, policy_version 32570 (0.0012) -[2023-11-28 01:04:01,181][87424] Updated weights for policy 0, policy_version 32686 (0.0011) -[2023-11-28 01:04:01,560][87424] Updated weights for policy 0, policy_version 32696 (0.0008) -[2023-11-28 01:04:03,255][87426] Updated weights for policy 1, policy_version 32580 (0.0011) -[2023-11-28 01:04:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 16711680. Throughput: 0: 2743.5, 1: 2755.6. Samples: 16726260. Policy #0 lag: (min: 31.0, avg: 52.4, max: 89.0) -[2023-11-28 01:04:03,445][86177] Avg episode reward: [(0, '-500.510'), (1, '-522.840')] -[2023-11-28 01:04:03,458][87281] Saving new best policy, reward=-500.510! -[2023-11-28 01:04:03,635][87426] Updated weights for policy 1, policy_version 32590 (0.0011) -[2023-11-28 01:04:03,676][87424] Updated weights for policy 0, policy_version 32706 (0.0010) -[2023-11-28 01:04:04,008][87426] Updated weights for policy 1, policy_version 32600 (0.0010) -[2023-11-28 01:04:04,062][87424] Updated weights for policy 0, policy_version 32716 (0.0010) -[2023-11-28 01:04:04,442][87424] Updated weights for policy 0, policy_version 32726 (0.0010) -[2023-11-28 01:04:04,823][87424] Updated weights for policy 0, policy_version 32736 (0.0012) -[2023-11-28 01:04:05,771][87426] Updated weights for policy 1, policy_version 32610 (0.0009) -[2023-11-28 01:04:06,148][87426] Updated weights for policy 1, policy_version 32620 (0.0012) -[2023-11-28 01:04:06,518][87426] Updated weights for policy 1, policy_version 32630 (0.0011) -[2023-11-28 01:04:06,655][87424] Updated weights for policy 0, policy_version 32746 (0.0012) -[2023-11-28 01:04:06,898][87426] Updated weights for policy 1, policy_version 32640 (0.0007) -[2023-11-28 01:04:07,042][87424] Updated weights for policy 0, policy_version 32756 (0.0012) -[2023-11-28 01:04:07,420][87424] Updated weights for policy 0, policy_version 32766 (0.0012) -[2023-11-28 01:04:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 16744448. Throughput: 0: 2759.9, 1: 2762.6. Samples: 16760492. Policy #0 lag: (min: 31.0, avg: 52.4, max: 89.0) -[2023-11-28 01:04:08,445][86177] Avg episode reward: [(0, '-501.410'), (1, '-522.420')] -[2023-11-28 01:04:08,997][87426] Updated weights for policy 1, policy_version 32650 (0.0011) -[2023-11-28 01:04:09,173][87424] Updated weights for policy 0, policy_version 32776 (0.0012) -[2023-11-28 01:04:09,367][87426] Updated weights for policy 1, policy_version 32660 (0.0011) -[2023-11-28 01:04:09,553][87424] Updated weights for policy 0, policy_version 32786 (0.0012) -[2023-11-28 01:04:09,747][87426] Updated weights for policy 1, policy_version 32670 (0.0011) -[2023-11-28 01:04:09,948][87424] Updated weights for policy 0, policy_version 32796 (0.0016) -[2023-11-28 01:04:11,723][87426] Updated weights for policy 1, policy_version 32680 (0.0011) -[2023-11-28 01:04:11,781][87424] Updated weights for policy 0, policy_version 32806 (0.0010) -[2023-11-28 01:04:12,101][87426] Updated weights for policy 1, policy_version 32690 (0.0009) -[2023-11-28 01:04:12,164][87424] Updated weights for policy 0, policy_version 32816 (0.0012) -[2023-11-28 01:04:12,468][87426] Updated weights for policy 1, policy_version 32700 (0.0011) -[2023-11-28 01:04:12,551][87424] Updated weights for policy 0, policy_version 32826 (0.0011) -[2023-11-28 01:04:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 16777216. Throughput: 0: 2763.8, 1: 2733.6. Samples: 16785440. Policy #0 lag: (min: 31.0, avg: 52.4, max: 89.0) -[2023-11-28 01:04:13,445][86177] Avg episode reward: [(0, '-504.220'), (1, '-520.920')] -[2023-11-28 01:04:14,549][87426] Updated weights for policy 1, policy_version 32710 (0.0011) -[2023-11-28 01:04:14,737][87424] Updated weights for policy 0, policy_version 32836 (0.0011) -[2023-11-28 01:04:14,934][87426] Updated weights for policy 1, policy_version 32720 (0.0012) -[2023-11-28 01:04:15,115][87424] Updated weights for policy 0, policy_version 32846 (0.0012) -[2023-11-28 01:04:15,311][87426] Updated weights for policy 1, policy_version 32730 (0.0012) -[2023-11-28 01:04:15,496][87424] Updated weights for policy 0, policy_version 32856 (0.0010) -[2023-11-28 01:04:17,827][87426] Updated weights for policy 1, policy_version 32740 (0.0011) -[2023-11-28 01:04:17,936][87424] Updated weights for policy 0, policy_version 32866 (0.0009) -[2023-11-28 01:04:18,196][87426] Updated weights for policy 1, policy_version 32750 (0.0012) -[2023-11-28 01:04:18,316][87424] Updated weights for policy 0, policy_version 32876 (0.0010) -[2023-11-28 01:04:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 16793600. Throughput: 0: 2768.7, 1: 2740.5. Samples: 16810124. Policy #0 lag: (min: 31.0, avg: 52.4, max: 89.0) -[2023-11-28 01:04:18,445][86177] Avg episode reward: [(0, '-506.320'), (1, '-514.990')] -[2023-11-28 01:04:18,577][87426] Updated weights for policy 1, policy_version 32760 (0.0010) -[2023-11-28 01:04:18,699][87424] Updated weights for policy 0, policy_version 32886 (0.0011) -[2023-11-28 01:04:18,877][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000032768_8388608.pth... -[2023-11-28 01:04:18,924][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000030208_7733248.pth -[2023-11-28 01:04:19,084][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000032896_8421376.pth... -[2023-11-28 01:04:19,086][87424] Updated weights for policy 0, policy_version 32896 (0.0012) -[2023-11-28 01:04:19,114][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000030368_7774208.pth -[2023-11-28 01:04:21,062][87426] Updated weights for policy 1, policy_version 32770 (0.0009) -[2023-11-28 01:04:21,354][87424] Updated weights for policy 0, policy_version 32906 (0.0012) -[2023-11-28 01:04:21,449][87426] Updated weights for policy 1, policy_version 32780 (0.0011) -[2023-11-28 01:04:21,729][87424] Updated weights for policy 0, policy_version 32916 (0.0012) -[2023-11-28 01:04:21,826][87426] Updated weights for policy 1, policy_version 32790 (0.0010) -[2023-11-28 01:04:22,114][87424] Updated weights for policy 0, policy_version 32926 (0.0011) -[2023-11-28 01:04:22,210][87426] Updated weights for policy 1, policy_version 32800 (0.0012) -[2023-11-28 01:04:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 16826368. Throughput: 0: 2769.2, 1: 2722.9. Samples: 16841392. Policy #0 lag: (min: 31.0, avg: 52.4, max: 89.0) -[2023-11-28 01:04:23,445][86177] Avg episode reward: [(0, '-506.500'), (1, '-509.510')] -[2023-11-28 01:04:24,283][87424] Updated weights for policy 0, policy_version 32936 (0.0011) -[2023-11-28 01:04:24,321][87426] Updated weights for policy 1, policy_version 32810 (0.0011) -[2023-11-28 01:04:24,669][87424] Updated weights for policy 0, policy_version 32946 (0.0008) -[2023-11-28 01:04:24,700][87426] Updated weights for policy 1, policy_version 32820 (0.0011) -[2023-11-28 01:04:25,048][87424] Updated weights for policy 0, policy_version 32956 (0.0009) -[2023-11-28 01:04:25,080][87426] Updated weights for policy 1, policy_version 32830 (0.0011) -[2023-11-28 01:04:27,453][87426] Updated weights for policy 1, policy_version 32840 (0.0012) -[2023-11-28 01:04:27,462][87424] Updated weights for policy 0, policy_version 32966 (0.0010) -[2023-11-28 01:04:27,845][87426] Updated weights for policy 1, policy_version 32850 (0.0011) -[2023-11-28 01:04:27,851][87424] Updated weights for policy 0, policy_version 32976 (0.0008) -[2023-11-28 01:04:28,225][87426] Updated weights for policy 1, policy_version 32860 (0.0011) -[2023-11-28 01:04:28,249][87424] Updated weights for policy 0, policy_version 32986 (0.0010) -[2023-11-28 01:04:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 16850944. Throughput: 0: 2747.3, 1: 2717.3. Samples: 16865956. Policy #0 lag: (min: 6.0, avg: 15.1, max: 38.0) -[2023-11-28 01:04:28,445][86177] Avg episode reward: [(0, '-505.520'), (1, '-506.160')] -[2023-11-28 01:04:30,420][87424] Updated weights for policy 0, policy_version 32996 (0.0009) -[2023-11-28 01:04:30,658][87426] Updated weights for policy 1, policy_version 32870 (0.0011) -[2023-11-28 01:04:30,809][87424] Updated weights for policy 0, policy_version 33006 (0.0012) -[2023-11-28 01:04:31,052][87426] Updated weights for policy 1, policy_version 32880 (0.0010) -[2023-11-28 01:04:31,188][87424] Updated weights for policy 0, policy_version 33016 (0.0012) -[2023-11-28 01:04:31,427][87426] Updated weights for policy 1, policy_version 32890 (0.0009) -[2023-11-28 01:04:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 16875520. Throughput: 0: 2707.6, 1: 2712.6. Samples: 16888964. Policy #0 lag: (min: 6.0, avg: 15.1, max: 38.0) -[2023-11-28 01:04:33,445][86177] Avg episode reward: [(0, '-503.930'), (1, '-507.030')] -[2023-11-28 01:04:33,541][87424] Updated weights for policy 0, policy_version 33026 (0.0010) -[2023-11-28 01:04:33,632][87426] Updated weights for policy 1, policy_version 32900 (0.0010) -[2023-11-28 01:04:33,928][87424] Updated weights for policy 0, policy_version 33036 (0.0008) -[2023-11-28 01:04:34,011][87426] Updated weights for policy 1, policy_version 32910 (0.0007) -[2023-11-28 01:04:34,303][87424] Updated weights for policy 0, policy_version 33046 (0.0008) -[2023-11-28 01:04:34,391][87426] Updated weights for policy 1, policy_version 32920 (0.0007) -[2023-11-28 01:04:34,694][87424] Updated weights for policy 0, policy_version 33056 (0.0008) -[2023-11-28 01:04:36,696][87424] Updated weights for policy 0, policy_version 33066 (0.0010) -[2023-11-28 01:04:36,749][87426] Updated weights for policy 1, policy_version 32930 (0.0008) -[2023-11-28 01:04:37,080][87424] Updated weights for policy 0, policy_version 33076 (0.0011) -[2023-11-28 01:04:37,125][87426] Updated weights for policy 1, policy_version 32940 (0.0009) -[2023-11-28 01:04:37,464][87424] Updated weights for policy 0, policy_version 33086 (0.0008) -[2023-11-28 01:04:37,506][87426] Updated weights for policy 1, policy_version 32950 (0.0008) -[2023-11-28 01:04:37,882][87426] Updated weights for policy 1, policy_version 32960 (0.0007) -[2023-11-28 01:04:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 16908288. Throughput: 0: 2702.8, 1: 2703.8. Samples: 16922004. Policy #0 lag: (min: 6.0, avg: 15.1, max: 38.0) -[2023-11-28 01:04:38,445][86177] Avg episode reward: [(0, '-505.210'), (1, '-509.510')] -[2023-11-28 01:04:39,570][87426] Updated weights for policy 1, policy_version 32970 (0.0010) -[2023-11-28 01:04:39,933][87424] Updated weights for policy 0, policy_version 33096 (0.0010) -[2023-11-28 01:04:39,947][87426] Updated weights for policy 1, policy_version 32980 (0.0009) -[2023-11-28 01:04:40,318][87424] Updated weights for policy 0, policy_version 33106 (0.0011) -[2023-11-28 01:04:40,330][87426] Updated weights for policy 1, policy_version 32990 (0.0008) -[2023-11-28 01:04:40,701][87424] Updated weights for policy 0, policy_version 33116 (0.0009) -[2023-11-28 01:04:42,023][87426] Updated weights for policy 1, policy_version 33000 (0.0009) -[2023-11-28 01:04:42,410][87426] Updated weights for policy 1, policy_version 33010 (0.0009) -[2023-11-28 01:04:42,786][87426] Updated weights for policy 1, policy_version 33020 (0.0008) -[2023-11-28 01:04:42,973][87424] Updated weights for policy 0, policy_version 33126 (0.0011) -[2023-11-28 01:04:43,357][87424] Updated weights for policy 0, policy_version 33136 (0.0012) -[2023-11-28 01:04:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 16932864. Throughput: 0: 2696.6, 1: 2717.1. Samples: 16946180. Policy #0 lag: (min: 6.0, avg: 15.1, max: 38.0) -[2023-11-28 01:04:43,445][86177] Avg episode reward: [(0, '-504.820'), (1, '-509.860')] -[2023-11-28 01:04:43,740][87424] Updated weights for policy 0, policy_version 33146 (0.0012) -[2023-11-28 01:04:45,250][87426] Updated weights for policy 1, policy_version 33030 (0.0010) -[2023-11-28 01:04:45,632][87426] Updated weights for policy 1, policy_version 33040 (0.0014) -[2023-11-28 01:04:45,876][87424] Updated weights for policy 0, policy_version 33156 (0.0011) -[2023-11-28 01:04:46,019][87426] Updated weights for policy 1, policy_version 33050 (0.0011) -[2023-11-28 01:04:46,264][87424] Updated weights for policy 0, policy_version 33166 (0.0010) -[2023-11-28 01:04:46,658][87424] Updated weights for policy 0, policy_version 33176 (0.0008) -[2023-11-28 01:04:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 16957440. Throughput: 0: 2709.7, 1: 2710.0. Samples: 16970144. Policy #0 lag: (min: 19.0, avg: 27.9, max: 51.0) -[2023-11-28 01:04:48,445][86177] Avg episode reward: [(0, '-504.160'), (1, '-514.540')] -[2023-11-28 01:04:48,451][87424] Updated weights for policy 0, policy_version 33186 (0.0008) -[2023-11-28 01:04:48,518][87426] Updated weights for policy 1, policy_version 33060 (0.0011) -[2023-11-28 01:04:48,835][87424] Updated weights for policy 0, policy_version 33196 (0.0008) -[2023-11-28 01:04:48,899][87426] Updated weights for policy 1, policy_version 33070 (0.0008) -[2023-11-28 01:04:49,218][87424] Updated weights for policy 0, policy_version 33206 (0.0011) -[2023-11-28 01:04:49,279][87426] Updated weights for policy 1, policy_version 33080 (0.0010) -[2023-11-28 01:04:49,596][87424] Updated weights for policy 0, policy_version 33216 (0.0012) -[2023-11-28 01:04:51,671][87426] Updated weights for policy 1, policy_version 33090 (0.0010) -[2023-11-28 01:04:51,831][87424] Updated weights for policy 0, policy_version 33226 (0.0012) -[2023-11-28 01:04:52,050][87426] Updated weights for policy 1, policy_version 33100 (0.0010) -[2023-11-28 01:04:52,215][87424] Updated weights for policy 0, policy_version 33236 (0.0009) -[2023-11-28 01:04:52,438][87426] Updated weights for policy 1, policy_version 33110 (0.0009) -[2023-11-28 01:04:52,602][87424] Updated weights for policy 0, policy_version 33246 (0.0010) -[2023-11-28 01:04:52,810][87426] Updated weights for policy 1, policy_version 33120 (0.0008) -[2023-11-28 01:04:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 16990208. Throughput: 0: 2693.7, 1: 2713.3. Samples: 17003808. Policy #0 lag: (min: 19.0, avg: 27.9, max: 51.0) -[2023-11-28 01:04:53,445][86177] Avg episode reward: [(0, '-506.240'), (1, '-519.330')] -[2023-11-28 01:04:54,863][87426] Updated weights for policy 1, policy_version 33130 (0.0012) -[2023-11-28 01:04:55,148][87424] Updated weights for policy 0, policy_version 33256 (0.0011) -[2023-11-28 01:04:55,235][87426] Updated weights for policy 1, policy_version 33140 (0.0010) -[2023-11-28 01:04:55,534][87424] Updated weights for policy 0, policy_version 33266 (0.0010) -[2023-11-28 01:04:55,611][87426] Updated weights for policy 1, policy_version 33150 (0.0011) -[2023-11-28 01:04:55,919][87424] Updated weights for policy 0, policy_version 33276 (0.0008) -[2023-11-28 01:04:57,426][87426] Updated weights for policy 1, policy_version 33160 (0.0012) -[2023-11-28 01:04:57,795][87426] Updated weights for policy 1, policy_version 33170 (0.0012) -[2023-11-28 01:04:58,177][87426] Updated weights for policy 1, policy_version 33180 (0.0012) -[2023-11-28 01:04:58,415][87424] Updated weights for policy 0, policy_version 33286 (0.0008) -[2023-11-28 01:04:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 17014784. Throughput: 0: 2683.3, 1: 2720.8. Samples: 17028624. Policy #0 lag: (min: 19.0, avg: 27.9, max: 51.0) -[2023-11-28 01:04:58,445][86177] Avg episode reward: [(0, '-504.170'), (1, '-518.830')] -[2023-11-28 01:04:58,803][87424] Updated weights for policy 0, policy_version 33296 (0.0007) -[2023-11-28 01:04:59,191][87424] Updated weights for policy 0, policy_version 33306 (0.0008) -[2023-11-28 01:05:00,524][87426] Updated weights for policy 1, policy_version 33190 (0.0011) -[2023-11-28 01:05:00,895][87426] Updated weights for policy 1, policy_version 33200 (0.0008) -[2023-11-28 01:05:01,039][87424] Updated weights for policy 0, policy_version 33316 (0.0007) -[2023-11-28 01:05:01,274][87426] Updated weights for policy 1, policy_version 33210 (0.0008) -[2023-11-28 01:05:01,428][87424] Updated weights for policy 0, policy_version 33326 (0.0007) -[2023-11-28 01:05:01,817][87424] Updated weights for policy 0, policy_version 33336 (0.0008) -[2023-11-28 01:05:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 17039360. Throughput: 0: 2689.3, 1: 2713.0. Samples: 17053228. Policy #0 lag: (min: 19.0, avg: 27.9, max: 51.0) -[2023-11-28 01:05:03,445][86177] Avg episode reward: [(0, '-505.780'), (1, '-512.100')] -[2023-11-28 01:05:03,683][87426] Updated weights for policy 1, policy_version 33220 (0.0009) -[2023-11-28 01:05:04,062][87426] Updated weights for policy 1, policy_version 33230 (0.0007) -[2023-11-28 01:05:04,153][87424] Updated weights for policy 0, policy_version 33346 (0.0011) -[2023-11-28 01:05:04,455][87426] Updated weights for policy 1, policy_version 33240 (0.0010) -[2023-11-28 01:05:04,538][87424] Updated weights for policy 0, policy_version 33356 (0.0012) -[2023-11-28 01:05:04,931][87424] Updated weights for policy 0, policy_version 33366 (0.0012) -[2023-11-28 01:05:05,303][87424] Updated weights for policy 0, policy_version 33376 (0.0012) -[2023-11-28 01:05:06,343][87426] Updated weights for policy 1, policy_version 33250 (0.0012) -[2023-11-28 01:05:06,720][87426] Updated weights for policy 1, policy_version 33260 (0.0011) -[2023-11-28 01:05:07,099][87426] Updated weights for policy 1, policy_version 33270 (0.0011) -[2023-11-28 01:05:07,215][87424] Updated weights for policy 0, policy_version 33386 (0.0010) -[2023-11-28 01:05:07,480][87426] Updated weights for policy 1, policy_version 33280 (0.0011) -[2023-11-28 01:05:07,605][87424] Updated weights for policy 0, policy_version 33396 (0.0012) -[2023-11-28 01:05:07,993][87424] Updated weights for policy 0, policy_version 33406 (0.0012) -[2023-11-28 01:05:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 17072128. Throughput: 0: 2697.4, 1: 2745.1. Samples: 17086304. Policy #0 lag: (min: 19.0, avg: 27.9, max: 51.0) -[2023-11-28 01:05:08,445][86177] Avg episode reward: [(0, '-503.530'), (1, '-508.620')] -[2023-11-28 01:05:09,554][87426] Updated weights for policy 1, policy_version 33290 (0.0012) -[2023-11-28 01:05:09,723][87424] Updated weights for policy 0, policy_version 33416 (0.0011) -[2023-11-28 01:05:09,928][87426] Updated weights for policy 1, policy_version 33300 (0.0011) -[2023-11-28 01:05:10,109][87424] Updated weights for policy 0, policy_version 33426 (0.0012) -[2023-11-28 01:05:10,305][87426] Updated weights for policy 1, policy_version 33310 (0.0011) -[2023-11-28 01:05:10,486][87424] Updated weights for policy 0, policy_version 33436 (0.0011) -[2023-11-28 01:05:12,683][87426] Updated weights for policy 1, policy_version 33320 (0.0012) -[2023-11-28 01:05:12,835][87424] Updated weights for policy 0, policy_version 33446 (0.0011) -[2023-11-28 01:05:13,073][87426] Updated weights for policy 1, policy_version 33330 (0.0010) -[2023-11-28 01:05:13,208][87424] Updated weights for policy 0, policy_version 33456 (0.0008) -[2023-11-28 01:05:13,444][87426] Updated weights for policy 1, policy_version 33340 (0.0007) -[2023-11-28 01:05:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 17088512. Throughput: 0: 2689.2, 1: 2735.6. Samples: 17110076. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 01:05:13,445][86177] Avg episode reward: [(0, '-515.840'), (1, '-498.870')] -[2023-11-28 01:05:13,590][87424] Updated weights for policy 0, policy_version 33466 (0.0007) -[2023-11-28 01:05:15,065][87426] Updated weights for policy 1, policy_version 33350 (0.0007) -[2023-11-28 01:05:15,443][87426] Updated weights for policy 1, policy_version 33360 (0.0009) -[2023-11-28 01:05:15,819][87426] Updated weights for policy 1, policy_version 33370 (0.0011) -[2023-11-28 01:05:15,891][87424] Updated weights for policy 0, policy_version 33476 (0.0008) -[2023-11-28 01:05:16,274][87424] Updated weights for policy 0, policy_version 33486 (0.0008) -[2023-11-28 01:05:16,647][87424] Updated weights for policy 0, policy_version 33496 (0.0009) -[2023-11-28 01:05:17,923][87426] Updated weights for policy 1, policy_version 33380 (0.0011) -[2023-11-28 01:05:18,314][87426] Updated weights for policy 1, policy_version 33390 (0.0012) -[2023-11-28 01:05:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 17121280. Throughput: 0: 2728.9, 1: 2748.4. Samples: 17135444. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 01:05:18,446][86177] Avg episode reward: [(0, '-515.590'), (1, '-498.460')] -[2023-11-28 01:05:18,685][87426] Updated weights for policy 1, policy_version 33400 (0.0012) -[2023-11-28 01:05:19,161][87424] Updated weights for policy 0, policy_version 33506 (0.0007) -[2023-11-28 01:05:19,544][87424] Updated weights for policy 0, policy_version 33516 (0.0008) -[2023-11-28 01:05:19,933][87424] Updated weights for policy 0, policy_version 33526 (0.0008) -[2023-11-28 01:05:20,307][87424] Updated weights for policy 0, policy_version 33536 (0.0010) -[2023-11-28 01:05:21,302][87426] Updated weights for policy 1, policy_version 33410 (0.0012) -[2023-11-28 01:05:21,684][87426] Updated weights for policy 1, policy_version 33420 (0.0012) -[2023-11-28 01:05:22,056][87426] Updated weights for policy 1, policy_version 33430 (0.0011) -[2023-11-28 01:05:22,269][87424] Updated weights for policy 0, policy_version 33546 (0.0013) -[2023-11-28 01:05:22,430][87426] Updated weights for policy 1, policy_version 33440 (0.0012) -[2023-11-28 01:05:22,653][87424] Updated weights for policy 0, policy_version 33556 (0.0012) -[2023-11-28 01:05:23,047][87424] Updated weights for policy 0, policy_version 33566 (0.0010) -[2023-11-28 01:05:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 17154048. Throughput: 0: 2700.4, 1: 2727.7. Samples: 17166272. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 01:05:23,445][86177] Avg episode reward: [(0, '-513.100'), (1, '-497.630')] -[2023-11-28 01:05:25,012][87426] Updated weights for policy 1, policy_version 33450 (0.0008) -[2023-11-28 01:05:25,403][87424] Updated weights for policy 0, policy_version 33576 (0.0009) -[2023-11-28 01:05:25,404][87426] Updated weights for policy 1, policy_version 33460 (0.0009) -[2023-11-28 01:05:25,765][87426] Updated weights for policy 1, policy_version 33470 (0.0008) -[2023-11-28 01:05:25,779][87424] Updated weights for policy 0, policy_version 33586 (0.0012) -[2023-11-28 01:05:26,160][87424] Updated weights for policy 0, policy_version 33596 (0.0008) -[2023-11-28 01:05:28,140][87426] Updated weights for policy 1, policy_version 33480 (0.0008) -[2023-11-28 01:05:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 17170432. Throughput: 0: 2714.3, 1: 2708.9. Samples: 17190224. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 01:05:28,445][86177] Avg episode reward: [(0, '-515.580'), (1, '-503.970')] -[2023-11-28 01:05:28,485][87424] Updated weights for policy 0, policy_version 33606 (0.0008) -[2023-11-28 01:05:28,520][87426] Updated weights for policy 1, policy_version 33490 (0.0007) -[2023-11-28 01:05:28,876][87424] Updated weights for policy 0, policy_version 33616 (0.0008) -[2023-11-28 01:05:28,911][87426] Updated weights for policy 1, policy_version 33500 (0.0007) -[2023-11-28 01:05:29,261][87424] Updated weights for policy 0, policy_version 33626 (0.0010) -[2023-11-28 01:05:31,281][87424] Updated weights for policy 0, policy_version 33636 (0.0008) -[2023-11-28 01:05:31,311][87426] Updated weights for policy 1, policy_version 33510 (0.0009) -[2023-11-28 01:05:31,678][87424] Updated weights for policy 0, policy_version 33646 (0.0011) -[2023-11-28 01:05:31,689][87426] Updated weights for policy 1, policy_version 33520 (0.0011) -[2023-11-28 01:05:32,049][87424] Updated weights for policy 0, policy_version 33656 (0.0012) -[2023-11-28 01:05:32,071][87426] Updated weights for policy 1, policy_version 33530 (0.0011) -[2023-11-28 01:05:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 17203200. Throughput: 0: 2714.8, 1: 2716.4. Samples: 17214548. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 01:05:33,445][86177] Avg episode reward: [(0, '-504.980'), (1, '-506.580')] -[2023-11-28 01:05:34,228][87424] Updated weights for policy 0, policy_version 33666 (0.0012) -[2023-11-28 01:05:34,314][87426] Updated weights for policy 1, policy_version 33540 (0.0011) -[2023-11-28 01:05:34,615][87424] Updated weights for policy 0, policy_version 33676 (0.0012) -[2023-11-28 01:05:34,684][87426] Updated weights for policy 1, policy_version 33550 (0.0011) -[2023-11-28 01:05:34,997][87424] Updated weights for policy 0, policy_version 33686 (0.0011) -[2023-11-28 01:05:35,063][87426] Updated weights for policy 1, policy_version 33560 (0.0012) -[2023-11-28 01:05:35,388][87424] Updated weights for policy 0, policy_version 33696 (0.0011) -[2023-11-28 01:05:37,067][87424] Updated weights for policy 0, policy_version 33706 (0.0010) -[2023-11-28 01:05:37,131][87426] Updated weights for policy 1, policy_version 33570 (0.0012) -[2023-11-28 01:05:37,450][87424] Updated weights for policy 0, policy_version 33716 (0.0010) -[2023-11-28 01:05:37,509][87426] Updated weights for policy 1, policy_version 33580 (0.0012) -[2023-11-28 01:05:37,835][87424] Updated weights for policy 0, policy_version 33726 (0.0012) -[2023-11-28 01:05:37,894][87426] Updated weights for policy 1, policy_version 33590 (0.0010) -[2023-11-28 01:05:38,266][87426] Updated weights for policy 1, policy_version 33600 (0.0012) -[2023-11-28 01:05:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 17235968. Throughput: 0: 2716.6, 1: 2703.3. Samples: 17247704. Policy #0 lag: (min: 31.0, avg: 32.9, max: 50.0) -[2023-11-28 01:05:38,445][86177] Avg episode reward: [(0, '-523.240'), (1, '-545.250')] -[2023-11-28 01:05:40,149][87424] Updated weights for policy 0, policy_version 33736 (0.0011) -[2023-11-28 01:05:40,200][87426] Updated weights for policy 1, policy_version 33610 (0.0009) -[2023-11-28 01:05:40,527][87424] Updated weights for policy 0, policy_version 33746 (0.0012) -[2023-11-28 01:05:40,582][87426] Updated weights for policy 1, policy_version 33620 (0.0010) -[2023-11-28 01:05:40,914][87424] Updated weights for policy 0, policy_version 33756 (0.0009) -[2023-11-28 01:05:40,959][87426] Updated weights for policy 1, policy_version 33630 (0.0008) -[2023-11-28 01:05:42,910][87424] Updated weights for policy 0, policy_version 33766 (0.0011) -[2023-11-28 01:05:43,286][87424] Updated weights for policy 0, policy_version 33776 (0.0011) -[2023-11-28 01:05:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 17252352. Throughput: 0: 2733.9, 1: 2682.1. Samples: 17272344. Policy #0 lag: (min: 31.0, avg: 32.9, max: 50.0) -[2023-11-28 01:05:43,446][86177] Avg episode reward: [(0, '-524.040'), (1, '-545.930')] -[2023-11-28 01:05:43,480][87426] Updated weights for policy 1, policy_version 33640 (0.0010) -[2023-11-28 01:05:43,673][87424] Updated weights for policy 0, policy_version 33786 (0.0010) -[2023-11-28 01:05:43,856][87426] Updated weights for policy 1, policy_version 33650 (0.0009) -[2023-11-28 01:05:44,234][87426] Updated weights for policy 1, policy_version 33660 (0.0007) -[2023-11-28 01:05:45,696][87424] Updated weights for policy 0, policy_version 33796 (0.0010) -[2023-11-28 01:05:46,080][87424] Updated weights for policy 0, policy_version 33806 (0.0011) -[2023-11-28 01:05:46,465][87424] Updated weights for policy 0, policy_version 33816 (0.0008) -[2023-11-28 01:05:46,616][87426] Updated weights for policy 1, policy_version 33670 (0.0008) -[2023-11-28 01:05:47,000][87426] Updated weights for policy 1, policy_version 33680 (0.0011) -[2023-11-28 01:05:47,375][87426] Updated weights for policy 1, policy_version 33690 (0.0012) -[2023-11-28 01:05:48,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 17285120. Throughput: 0: 2723.2, 1: 2688.5. Samples: 17296756. Policy #0 lag: (min: 31.0, avg: 32.9, max: 50.0) -[2023-11-28 01:05:48,446][86177] Avg episode reward: [(0, '-536.040'), (1, '-544.960')] -[2023-11-28 01:05:48,840][87424] Updated weights for policy 0, policy_version 33826 (0.0009) -[2023-11-28 01:05:49,131][87426] Updated weights for policy 1, policy_version 33700 (0.0012) -[2023-11-28 01:05:49,221][87424] Updated weights for policy 0, policy_version 33836 (0.0011) -[2023-11-28 01:05:49,509][87426] Updated weights for policy 1, policy_version 33710 (0.0010) -[2023-11-28 01:05:49,608][87424] Updated weights for policy 0, policy_version 33846 (0.0012) -[2023-11-28 01:05:49,886][87426] Updated weights for policy 1, policy_version 33720 (0.0012) -[2023-11-28 01:05:49,984][87424] Updated weights for policy 0, policy_version 33856 (0.0011) -[2023-11-28 01:05:51,847][87424] Updated weights for policy 0, policy_version 33866 (0.0012) -[2023-11-28 01:05:52,225][87424] Updated weights for policy 0, policy_version 33876 (0.0011) -[2023-11-28 01:05:52,366][87426] Updated weights for policy 1, policy_version 33730 (0.0008) -[2023-11-28 01:05:52,604][87424] Updated weights for policy 0, policy_version 33886 (0.0008) -[2023-11-28 01:05:52,745][87426] Updated weights for policy 1, policy_version 33740 (0.0010) -[2023-11-28 01:05:53,134][87426] Updated weights for policy 1, policy_version 33750 (0.0011) -[2023-11-28 01:05:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 17309696. Throughput: 0: 2726.6, 1: 2670.8. Samples: 17329188. Policy #0 lag: (min: 31.0, avg: 32.9, max: 50.0) -[2023-11-28 01:05:53,445][86177] Avg episode reward: [(0, '-536.360'), (1, '-552.540')] -[2023-11-28 01:05:53,517][87426] Updated weights for policy 1, policy_version 33760 (0.0010) -[2023-11-28 01:05:54,969][87424] Updated weights for policy 0, policy_version 33896 (0.0011) -[2023-11-28 01:05:55,350][87424] Updated weights for policy 0, policy_version 33906 (0.0012) -[2023-11-28 01:05:55,724][87424] Updated weights for policy 0, policy_version 33916 (0.0012) -[2023-11-28 01:05:55,726][87426] Updated weights for policy 1, policy_version 33770 (0.0012) -[2023-11-28 01:05:56,107][87426] Updated weights for policy 1, policy_version 33780 (0.0011) -[2023-11-28 01:05:56,496][87426] Updated weights for policy 1, policy_version 33790 (0.0009) -[2023-11-28 01:05:57,800][87424] Updated weights for policy 0, policy_version 33926 (0.0009) -[2023-11-28 01:05:58,188][87424] Updated weights for policy 0, policy_version 33936 (0.0008) -[2023-11-28 01:05:58,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 17334272. Throughput: 0: 2751.4, 1: 2668.3. Samples: 17353960. Policy #0 lag: (min: 31.0, avg: 32.9, max: 50.0) -[2023-11-28 01:05:58,446][86177] Avg episode reward: [(0, '-518.130'), (1, '-513.320')] -[2023-11-28 01:05:58,571][87424] Updated weights for policy 0, policy_version 33946 (0.0011) -[2023-11-28 01:05:58,966][87426] Updated weights for policy 1, policy_version 33800 (0.0011) -[2023-11-28 01:05:59,336][87426] Updated weights for policy 1, policy_version 33810 (0.0012) -[2023-11-28 01:05:59,714][87426] Updated weights for policy 1, policy_version 33820 (0.0012) -[2023-11-28 01:06:00,328][87424] Updated weights for policy 0, policy_version 33956 (0.0011) -[2023-11-28 01:06:00,722][87424] Updated weights for policy 0, policy_version 33966 (0.0009) -[2023-11-28 01:06:01,090][87424] Updated weights for policy 0, policy_version 33976 (0.0007) -[2023-11-28 01:06:02,283][87426] Updated weights for policy 1, policy_version 33830 (0.0011) -[2023-11-28 01:06:02,663][87426] Updated weights for policy 1, policy_version 33840 (0.0007) -[2023-11-28 01:06:03,040][87426] Updated weights for policy 1, policy_version 33850 (0.0009) -[2023-11-28 01:06:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 17367040. Throughput: 0: 2771.0, 1: 2651.9. Samples: 17379472. Policy #0 lag: (min: 24.0, avg: 32.4, max: 43.0) -[2023-11-28 01:06:03,445][86177] Avg episode reward: [(0, '-507.320'), (1, '-525.750')] -[2023-11-28 01:06:03,560][87424] Updated weights for policy 0, policy_version 33986 (0.0009) -[2023-11-28 01:06:03,938][87424] Updated weights for policy 0, policy_version 33996 (0.0011) -[2023-11-28 01:06:04,311][87424] Updated weights for policy 0, policy_version 34006 (0.0010) -[2023-11-28 01:06:04,692][87424] Updated weights for policy 0, policy_version 34016 (0.0008) -[2023-11-28 01:06:05,530][87426] Updated weights for policy 1, policy_version 33860 (0.0009) -[2023-11-28 01:06:05,910][87426] Updated weights for policy 1, policy_version 33870 (0.0012) -[2023-11-28 01:06:06,285][87426] Updated weights for policy 1, policy_version 33880 (0.0012) -[2023-11-28 01:06:06,936][87424] Updated weights for policy 0, policy_version 34026 (0.0009) -[2023-11-28 01:06:07,320][87424] Updated weights for policy 0, policy_version 34036 (0.0008) -[2023-11-28 01:06:07,706][87424] Updated weights for policy 0, policy_version 34046 (0.0008) -[2023-11-28 01:06:08,088][87426] Updated weights for policy 1, policy_version 33890 (0.0011) -[2023-11-28 01:06:08,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 17391616. Throughput: 0: 2781.9, 1: 2635.9. Samples: 17410072. Policy #0 lag: (min: 24.0, avg: 32.4, max: 43.0) -[2023-11-28 01:06:08,445][86177] Avg episode reward: [(0, '-508.460'), (1, '-524.940')] -[2023-11-28 01:06:08,472][87426] Updated weights for policy 1, policy_version 33900 (0.0009) -[2023-11-28 01:06:08,853][87426] Updated weights for policy 1, policy_version 33910 (0.0008) -[2023-11-28 01:06:09,245][87426] Updated weights for policy 1, policy_version 33920 (0.0009) -[2023-11-28 01:06:10,089][87424] Updated weights for policy 0, policy_version 34056 (0.0011) -[2023-11-28 01:06:10,473][87424] Updated weights for policy 0, policy_version 34066 (0.0010) -[2023-11-28 01:06:10,857][87424] Updated weights for policy 0, policy_version 34076 (0.0009) -[2023-11-28 01:06:11,237][87426] Updated weights for policy 1, policy_version 33930 (0.0011) -[2023-11-28 01:06:11,607][87426] Updated weights for policy 1, policy_version 33940 (0.0010) -[2023-11-28 01:06:12,011][87426] Updated weights for policy 1, policy_version 33950 (0.0010) -[2023-11-28 01:06:13,351][87424] Updated weights for policy 0, policy_version 34086 (0.0009) -[2023-11-28 01:06:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 17416192. Throughput: 0: 2766.3, 1: 2634.1. Samples: 17433244. Policy #0 lag: (min: 24.0, avg: 32.4, max: 43.0) -[2023-11-28 01:06:13,445][86177] Avg episode reward: [(0, '-506.770'), (1, '-515.270')] -[2023-11-28 01:06:13,734][87424] Updated weights for policy 0, policy_version 34096 (0.0009) -[2023-11-28 01:06:14,114][87424] Updated weights for policy 0, policy_version 34106 (0.0007) -[2023-11-28 01:06:14,502][87426] Updated weights for policy 1, policy_version 33960 (0.0011) -[2023-11-28 01:06:14,890][87426] Updated weights for policy 1, policy_version 33970 (0.0011) -[2023-11-28 01:06:15,285][87426] Updated weights for policy 1, policy_version 33980 (0.0011) -[2023-11-28 01:06:16,506][87424] Updated weights for policy 0, policy_version 34116 (0.0009) -[2023-11-28 01:06:16,891][87424] Updated weights for policy 0, policy_version 34126 (0.0008) -[2023-11-28 01:06:17,275][87424] Updated weights for policy 0, policy_version 34136 (0.0007) -[2023-11-28 01:06:17,799][87426] Updated weights for policy 1, policy_version 33990 (0.0008) -[2023-11-28 01:06:18,176][87426] Updated weights for policy 1, policy_version 34000 (0.0007) -[2023-11-28 01:06:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 17440768. Throughput: 0: 2748.2, 1: 2643.6. Samples: 17457180. Policy #0 lag: (min: 24.0, avg: 32.4, max: 43.0) -[2023-11-28 01:06:18,445][86177] Avg episode reward: [(0, '-513.930'), (1, '-538.850')] -[2023-11-28 01:06:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000034144_8740864.pth... -[2023-11-28 01:06:18,493][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000031616_8093696.pth -[2023-11-28 01:06:18,561][87426] Updated weights for policy 1, policy_version 34010 (0.0007) -[2023-11-28 01:06:18,791][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000034016_8708096.pth... -[2023-11-28 01:06:18,822][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000031456_8052736.pth -[2023-11-28 01:06:19,023][87424] Updated weights for policy 0, policy_version 34146 (0.0008) -[2023-11-28 01:06:19,403][87424] Updated weights for policy 0, policy_version 34156 (0.0008) -[2023-11-28 01:06:19,788][87424] Updated weights for policy 0, policy_version 34166 (0.0008) -[2023-11-28 01:06:20,175][87424] Updated weights for policy 0, policy_version 34176 (0.0009) -[2023-11-28 01:06:21,094][87426] Updated weights for policy 1, policy_version 34020 (0.0009) -[2023-11-28 01:06:21,476][87426] Updated weights for policy 1, policy_version 34030 (0.0011) -[2023-11-28 01:06:21,857][87426] Updated weights for policy 1, policy_version 34040 (0.0012) -[2023-11-28 01:06:22,022][87424] Updated weights for policy 0, policy_version 34186 (0.0012) -[2023-11-28 01:06:22,412][87424] Updated weights for policy 0, policy_version 34196 (0.0011) -[2023-11-28 01:06:22,798][87424] Updated weights for policy 0, policy_version 34206 (0.0012) -[2023-11-28 01:06:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 17473536. Throughput: 0: 2744.5, 1: 2614.6. Samples: 17488864. Policy #0 lag: (min: 14.0, avg: 37.0, max: 78.0) -[2023-11-28 01:06:23,445][86177] Avg episode reward: [(0, '-510.390'), (1, '-532.930')] -[2023-11-28 01:06:24,436][87426] Updated weights for policy 1, policy_version 34050 (0.0011) -[2023-11-28 01:06:24,817][87426] Updated weights for policy 1, policy_version 34060 (0.0008) -[2023-11-28 01:06:25,195][87426] Updated weights for policy 1, policy_version 34070 (0.0012) -[2023-11-28 01:06:25,351][87424] Updated weights for policy 0, policy_version 34216 (0.0008) -[2023-11-28 01:06:25,568][87426] Updated weights for policy 1, policy_version 34080 (0.0012) -[2023-11-28 01:06:25,727][87424] Updated weights for policy 0, policy_version 34226 (0.0008) -[2023-11-28 01:06:26,112][87424] Updated weights for policy 0, policy_version 34236 (0.0007) -[2023-11-28 01:06:27,296][87426] Updated weights for policy 1, policy_version 34090 (0.0011) -[2023-11-28 01:06:27,667][87426] Updated weights for policy 1, policy_version 34100 (0.0011) -[2023-11-28 01:06:28,049][87426] Updated weights for policy 1, policy_version 34110 (0.0012) -[2023-11-28 01:06:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 17498112. Throughput: 0: 2729.5, 1: 2626.1. Samples: 17513348. Policy #0 lag: (min: 14.0, avg: 37.0, max: 78.0) -[2023-11-28 01:06:28,445][86177] Avg episode reward: [(0, '-510.330'), (1, '-533.500')] -[2023-11-28 01:06:28,596][87424] Updated weights for policy 0, policy_version 34246 (0.0010) -[2023-11-28 01:06:28,981][87424] Updated weights for policy 0, policy_version 34256 (0.0012) -[2023-11-28 01:06:29,372][87424] Updated weights for policy 0, policy_version 34266 (0.0012) -[2023-11-28 01:06:29,789][87426] Updated weights for policy 1, policy_version 34120 (0.0009) -[2023-11-28 01:06:30,171][87426] Updated weights for policy 1, policy_version 34130 (0.0010) -[2023-11-28 01:06:30,560][87426] Updated weights for policy 1, policy_version 34140 (0.0011) -[2023-11-28 01:06:31,612][87424] Updated weights for policy 0, policy_version 34276 (0.0012) -[2023-11-28 01:06:31,989][87424] Updated weights for policy 0, policy_version 34286 (0.0012) -[2023-11-28 01:06:32,376][87424] Updated weights for policy 0, policy_version 34296 (0.0012) -[2023-11-28 01:06:32,887][87426] Updated weights for policy 1, policy_version 34150 (0.0012) -[2023-11-28 01:06:33,266][87426] Updated weights for policy 1, policy_version 34160 (0.0012) -[2023-11-28 01:06:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 17522688. Throughput: 0: 2706.5, 1: 2636.0. Samples: 17537168. Policy #0 lag: (min: 14.0, avg: 37.0, max: 78.0) -[2023-11-28 01:06:33,445][86177] Avg episode reward: [(0, '-513.350'), (1, '-535.180')] -[2023-11-28 01:06:33,652][87426] Updated weights for policy 1, policy_version 34170 (0.0012) -[2023-11-28 01:06:34,545][87424] Updated weights for policy 0, policy_version 34306 (0.0011) -[2023-11-28 01:06:34,923][87424] Updated weights for policy 0, policy_version 34316 (0.0010) -[2023-11-28 01:06:35,308][87424] Updated weights for policy 0, policy_version 34326 (0.0011) -[2023-11-28 01:06:35,689][87424] Updated weights for policy 0, policy_version 34336 (0.0008) -[2023-11-28 01:06:35,745][87426] Updated weights for policy 1, policy_version 34180 (0.0012) -[2023-11-28 01:06:36,124][87426] Updated weights for policy 1, policy_version 34190 (0.0010) -[2023-11-28 01:06:36,502][87426] Updated weights for policy 1, policy_version 34200 (0.0007) -[2023-11-28 01:06:37,607][87424] Updated weights for policy 0, policy_version 34346 (0.0012) -[2023-11-28 01:06:37,993][87424] Updated weights for policy 0, policy_version 34356 (0.0012) -[2023-11-28 01:06:38,368][87424] Updated weights for policy 0, policy_version 34366 (0.0012) -[2023-11-28 01:06:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 17555456. Throughput: 0: 2710.0, 1: 2624.9. Samples: 17569256. Policy #0 lag: (min: 14.0, avg: 37.0, max: 78.0) -[2023-11-28 01:06:38,445][86177] Avg episode reward: [(0, '-508.490'), (1, '-542.470')] -[2023-11-28 01:06:38,666][87426] Updated weights for policy 1, policy_version 34210 (0.0011) -[2023-11-28 01:06:39,052][87426] Updated weights for policy 1, policy_version 34220 (0.0012) -[2023-11-28 01:06:39,436][87426] Updated weights for policy 1, policy_version 34230 (0.0011) -[2023-11-28 01:06:39,811][87426] Updated weights for policy 1, policy_version 34240 (0.0012) -[2023-11-28 01:06:40,865][87424] Updated weights for policy 0, policy_version 34376 (0.0009) -[2023-11-28 01:06:41,245][87424] Updated weights for policy 0, policy_version 34386 (0.0008) -[2023-11-28 01:06:41,636][87424] Updated weights for policy 0, policy_version 34396 (0.0008) -[2023-11-28 01:06:42,384][87426] Updated weights for policy 1, policy_version 34250 (0.0010) -[2023-11-28 01:06:42,764][87426] Updated weights for policy 1, policy_version 34260 (0.0011) -[2023-11-28 01:06:43,133][87426] Updated weights for policy 1, policy_version 34270 (0.0012) -[2023-11-28 01:06:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 17580032. Throughput: 0: 2682.9, 1: 2619.0. Samples: 17592544. Policy #0 lag: (min: 14.0, avg: 37.0, max: 78.0) -[2023-11-28 01:06:43,446][86177] Avg episode reward: [(0, '-515.660'), (1, '-544.450')] -[2023-11-28 01:06:43,545][87424] Updated weights for policy 0, policy_version 34406 (0.0010) -[2023-11-28 01:06:43,934][87424] Updated weights for policy 0, policy_version 34416 (0.0009) -[2023-11-28 01:06:44,315][87424] Updated weights for policy 0, policy_version 34426 (0.0010) -[2023-11-28 01:06:45,578][87426] Updated weights for policy 1, policy_version 34280 (0.0012) -[2023-11-28 01:06:45,950][87426] Updated weights for policy 1, policy_version 34290 (0.0012) -[2023-11-28 01:06:46,325][87426] Updated weights for policy 1, policy_version 34300 (0.0012) -[2023-11-28 01:06:46,673][87424] Updated weights for policy 0, policy_version 34436 (0.0011) -[2023-11-28 01:06:47,056][87424] Updated weights for policy 0, policy_version 34446 (0.0009) -[2023-11-28 01:06:47,452][87424] Updated weights for policy 0, policy_version 34456 (0.0008) -[2023-11-28 01:06:48,202][87426] Updated weights for policy 1, policy_version 34310 (0.0011) -[2023-11-28 01:06:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 17604608. Throughput: 0: 2635.5, 1: 2630.6. Samples: 17616448. Policy #0 lag: (min: 20.0, avg: 43.1, max: 61.0) -[2023-11-28 01:06:48,446][86177] Avg episode reward: [(0, '-526.020'), (1, '-539.740')] -[2023-11-28 01:06:48,579][87426] Updated weights for policy 1, policy_version 34320 (0.0010) -[2023-11-28 01:06:48,956][87426] Updated weights for policy 1, policy_version 34330 (0.0010) -[2023-11-28 01:06:49,399][87424] Updated weights for policy 0, policy_version 34466 (0.0008) -[2023-11-28 01:06:49,779][87424] Updated weights for policy 0, policy_version 34476 (0.0012) -[2023-11-28 01:06:50,159][87424] Updated weights for policy 0, policy_version 34486 (0.0010) -[2023-11-28 01:06:50,538][87424] Updated weights for policy 0, policy_version 34496 (0.0010) -[2023-11-28 01:06:51,517][87426] Updated weights for policy 1, policy_version 34340 (0.0008) -[2023-11-28 01:06:51,902][87426] Updated weights for policy 1, policy_version 34350 (0.0012) -[2023-11-28 01:06:52,293][87426] Updated weights for policy 1, policy_version 34360 (0.0009) -[2023-11-28 01:06:53,092][87424] Updated weights for policy 0, policy_version 34506 (0.0012) -[2023-11-28 01:06:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 17629184. Throughput: 0: 2634.1, 1: 2652.0. Samples: 17647948. Policy #0 lag: (min: 20.0, avg: 43.1, max: 61.0) -[2023-11-28 01:06:53,445][86177] Avg episode reward: [(0, '-521.050'), (1, '-540.800')] -[2023-11-28 01:06:53,481][87424] Updated weights for policy 0, policy_version 34516 (0.0012) -[2023-11-28 01:06:53,859][87424] Updated weights for policy 0, policy_version 34526 (0.0012) -[2023-11-28 01:06:54,301][87426] Updated weights for policy 1, policy_version 34370 (0.0011) -[2023-11-28 01:06:54,678][87426] Updated weights for policy 1, policy_version 34380 (0.0007) -[2023-11-28 01:06:55,062][87426] Updated weights for policy 1, policy_version 34390 (0.0007) -[2023-11-28 01:06:55,443][87426] Updated weights for policy 1, policy_version 34400 (0.0007) -[2023-11-28 01:06:56,461][87424] Updated weights for policy 0, policy_version 34536 (0.0012) -[2023-11-28 01:06:56,839][87424] Updated weights for policy 0, policy_version 34546 (0.0011) -[2023-11-28 01:06:57,226][87424] Updated weights for policy 0, policy_version 34556 (0.0007) -[2023-11-28 01:06:57,759][87426] Updated weights for policy 1, policy_version 34410 (0.0011) -[2023-11-28 01:06:58,144][87426] Updated weights for policy 1, policy_version 34420 (0.0012) -[2023-11-28 01:06:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 17653760. Throughput: 0: 2644.3, 1: 2669.5. Samples: 17672364. Policy #0 lag: (min: 20.0, avg: 43.1, max: 61.0) -[2023-11-28 01:06:58,445][86177] Avg episode reward: [(0, '-517.720'), (1, '-507.720')] -[2023-11-28 01:06:58,525][87426] Updated weights for policy 1, policy_version 34430 (0.0011) -[2023-11-28 01:06:59,360][87424] Updated weights for policy 0, policy_version 34566 (0.0010) -[2023-11-28 01:06:59,743][87424] Updated weights for policy 0, policy_version 34576 (0.0012) -[2023-11-28 01:07:00,127][87424] Updated weights for policy 0, policy_version 34586 (0.0012) -[2023-11-28 01:07:00,365][87426] Updated weights for policy 1, policy_version 34440 (0.0011) -[2023-11-28 01:07:00,750][87426] Updated weights for policy 1, policy_version 34450 (0.0010) -[2023-11-28 01:07:01,130][87426] Updated weights for policy 1, policy_version 34460 (0.0012) -[2023-11-28 01:07:02,601][87424] Updated weights for policy 0, policy_version 34596 (0.0010) -[2023-11-28 01:07:02,985][87424] Updated weights for policy 0, policy_version 34606 (0.0010) -[2023-11-28 01:07:03,123][87426] Updated weights for policy 1, policy_version 34470 (0.0011) -[2023-11-28 01:07:03,362][87424] Updated weights for policy 0, policy_version 34616 (0.0008) -[2023-11-28 01:07:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 17678336. Throughput: 0: 2653.2, 1: 2675.9. Samples: 17696988. Policy #0 lag: (min: 20.0, avg: 43.1, max: 61.0) -[2023-11-28 01:07:03,445][86177] Avg episode reward: [(0, '-513.280'), (1, '-498.150')] -[2023-11-28 01:07:03,502][87426] Updated weights for policy 1, policy_version 34480 (0.0011) -[2023-11-28 01:07:03,886][87426] Updated weights for policy 1, policy_version 34490 (0.0007) -[2023-11-28 01:07:05,320][87424] Updated weights for policy 0, policy_version 34626 (0.0008) -[2023-11-28 01:07:05,713][87424] Updated weights for policy 0, policy_version 34636 (0.0008) -[2023-11-28 01:07:06,089][87424] Updated weights for policy 0, policy_version 34646 (0.0008) -[2023-11-28 01:07:06,282][87426] Updated weights for policy 1, policy_version 34500 (0.0007) -[2023-11-28 01:07:06,473][87424] Updated weights for policy 0, policy_version 34656 (0.0008) -[2023-11-28 01:07:06,660][87426] Updated weights for policy 1, policy_version 34510 (0.0008) -[2023-11-28 01:07:07,041][87426] Updated weights for policy 1, policy_version 34520 (0.0012) -[2023-11-28 01:07:08,285][87424] Updated weights for policy 0, policy_version 34666 (0.0012) -[2023-11-28 01:07:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 17711104. Throughput: 0: 2652.3, 1: 2713.5. Samples: 17730328. Policy #0 lag: (min: 20.0, avg: 43.1, max: 61.0) -[2023-11-28 01:07:08,445][86177] Avg episode reward: [(0, '-507.220'), (1, '-500.730')] -[2023-11-28 01:07:08,668][87424] Updated weights for policy 0, policy_version 34676 (0.0011) -[2023-11-28 01:07:08,849][87426] Updated weights for policy 1, policy_version 34530 (0.0012) -[2023-11-28 01:07:09,063][87424] Updated weights for policy 0, policy_version 34686 (0.0012) -[2023-11-28 01:07:09,220][87426] Updated weights for policy 1, policy_version 34540 (0.0011) -[2023-11-28 01:07:09,598][87426] Updated weights for policy 1, policy_version 34550 (0.0012) -[2023-11-28 01:07:09,973][87426] Updated weights for policy 1, policy_version 34560 (0.0012) -[2023-11-28 01:07:11,305][87424] Updated weights for policy 0, policy_version 34696 (0.0011) -[2023-11-28 01:07:11,687][87424] Updated weights for policy 0, policy_version 34706 (0.0010) -[2023-11-28 01:07:12,066][87424] Updated weights for policy 0, policy_version 34716 (0.0010) -[2023-11-28 01:07:12,160][87426] Updated weights for policy 1, policy_version 34570 (0.0011) -[2023-11-28 01:07:12,543][87426] Updated weights for policy 1, policy_version 34580 (0.0010) -[2023-11-28 01:07:12,923][87426] Updated weights for policy 1, policy_version 34590 (0.0009) -[2023-11-28 01:07:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 17743872. Throughput: 0: 2658.4, 1: 2719.0. Samples: 17755332. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 01:07:13,445][86177] Avg episode reward: [(0, '-509.620'), (1, '-503.580')] -[2023-11-28 01:07:14,487][87424] Updated weights for policy 0, policy_version 34726 (0.0009) -[2023-11-28 01:07:14,871][87424] Updated weights for policy 0, policy_version 34736 (0.0007) -[2023-11-28 01:07:15,065][87426] Updated weights for policy 1, policy_version 34600 (0.0010) -[2023-11-28 01:07:15,255][87424] Updated weights for policy 0, policy_version 34746 (0.0009) -[2023-11-28 01:07:15,442][87426] Updated weights for policy 1, policy_version 34610 (0.0010) -[2023-11-28 01:07:15,825][87426] Updated weights for policy 1, policy_version 34620 (0.0008) -[2023-11-28 01:07:17,310][87424] Updated weights for policy 0, policy_version 34756 (0.0010) -[2023-11-28 01:07:17,692][87424] Updated weights for policy 0, policy_version 34766 (0.0010) -[2023-11-28 01:07:17,864][87426] Updated weights for policy 1, policy_version 34630 (0.0007) -[2023-11-28 01:07:18,090][87424] Updated weights for policy 0, policy_version 34776 (0.0012) -[2023-11-28 01:07:18,227][87426] Updated weights for policy 1, policy_version 34640 (0.0011) -[2023-11-28 01:07:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 17768448. Throughput: 0: 2677.1, 1: 2717.3. Samples: 17779916. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 01:07:18,445][86177] Avg episode reward: [(0, '-515.540'), (1, '-500.530')] -[2023-11-28 01:07:18,609][87426] Updated weights for policy 1, policy_version 34650 (0.0007) -[2023-11-28 01:07:20,384][87426] Updated weights for policy 1, policy_version 34660 (0.0008) -[2023-11-28 01:07:20,657][87424] Updated weights for policy 0, policy_version 34786 (0.0008) -[2023-11-28 01:07:20,764][87426] Updated weights for policy 1, policy_version 34670 (0.0009) -[2023-11-28 01:07:21,036][87424] Updated weights for policy 0, policy_version 34796 (0.0010) -[2023-11-28 01:07:21,139][87426] Updated weights for policy 1, policy_version 34680 (0.0011) -[2023-11-28 01:07:21,420][87424] Updated weights for policy 0, policy_version 34806 (0.0012) -[2023-11-28 01:07:21,804][87424] Updated weights for policy 0, policy_version 34816 (0.0011) -[2023-11-28 01:07:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 17793024. Throughput: 0: 2644.2, 1: 2742.0. Samples: 17811636. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 01:07:23,445][86177] Avg episode reward: [(0, '-515.240'), (1, '-507.390')] -[2023-11-28 01:07:23,648][87426] Updated weights for policy 1, policy_version 34690 (0.0009) -[2023-11-28 01:07:23,813][87424] Updated weights for policy 0, policy_version 34826 (0.0011) -[2023-11-28 01:07:24,021][87426] Updated weights for policy 1, policy_version 34700 (0.0007) -[2023-11-28 01:07:24,187][87424] Updated weights for policy 0, policy_version 34836 (0.0012) -[2023-11-28 01:07:24,403][87426] Updated weights for policy 1, policy_version 34710 (0.0009) -[2023-11-28 01:07:24,567][87424] Updated weights for policy 0, policy_version 34846 (0.0008) -[2023-11-28 01:07:24,781][87426] Updated weights for policy 1, policy_version 34720 (0.0011) -[2023-11-28 01:07:26,872][87426] Updated weights for policy 1, policy_version 34730 (0.0011) -[2023-11-28 01:07:26,949][87424] Updated weights for policy 0, policy_version 34856 (0.0008) -[2023-11-28 01:07:27,251][87426] Updated weights for policy 1, policy_version 34740 (0.0009) -[2023-11-28 01:07:27,340][87424] Updated weights for policy 0, policy_version 34866 (0.0008) -[2023-11-28 01:07:27,635][87426] Updated weights for policy 1, policy_version 34750 (0.0011) -[2023-11-28 01:07:27,725][87424] Updated weights for policy 0, policy_version 34876 (0.0011) -[2023-11-28 01:07:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 17825792. Throughput: 0: 2655.8, 1: 2762.8. Samples: 17836380. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 01:07:28,445][86177] Avg episode reward: [(0, '-512.650'), (1, '-505.100')] -[2023-11-28 01:07:29,728][87424] Updated weights for policy 0, policy_version 34886 (0.0008) -[2023-11-28 01:07:29,814][87426] Updated weights for policy 1, policy_version 34760 (0.0009) -[2023-11-28 01:07:30,114][87424] Updated weights for policy 0, policy_version 34896 (0.0011) -[2023-11-28 01:07:30,197][87426] Updated weights for policy 1, policy_version 34770 (0.0010) -[2023-11-28 01:07:30,494][87424] Updated weights for policy 0, policy_version 34906 (0.0011) -[2023-11-28 01:07:30,581][87426] Updated weights for policy 1, policy_version 34780 (0.0010) -[2023-11-28 01:07:32,834][87426] Updated weights for policy 1, policy_version 34790 (0.0010) -[2023-11-28 01:07:32,922][87424] Updated weights for policy 0, policy_version 34916 (0.0009) -[2023-11-28 01:07:33,220][87426] Updated weights for policy 1, policy_version 34800 (0.0011) -[2023-11-28 01:07:33,313][87424] Updated weights for policy 0, policy_version 34926 (0.0010) -[2023-11-28 01:07:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 17842176. Throughput: 0: 2663.1, 1: 2760.6. Samples: 17860512. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 01:07:33,445][86177] Avg episode reward: [(0, '-510.320'), (1, '-502.970')] -[2023-11-28 01:07:33,597][87426] Updated weights for policy 1, policy_version 34810 (0.0010) -[2023-11-28 01:07:33,690][87424] Updated weights for policy 0, policy_version 34936 (0.0010) -[2023-11-28 01:07:35,638][87424] Updated weights for policy 0, policy_version 34946 (0.0012) -[2023-11-28 01:07:35,985][87426] Updated weights for policy 1, policy_version 34820 (0.0010) -[2023-11-28 01:07:36,014][87424] Updated weights for policy 0, policy_version 34956 (0.0012) -[2023-11-28 01:07:36,368][87426] Updated weights for policy 1, policy_version 34830 (0.0007) -[2023-11-28 01:07:36,396][87424] Updated weights for policy 0, policy_version 34966 (0.0011) -[2023-11-28 01:07:36,755][87426] Updated weights for policy 1, policy_version 34840 (0.0009) -[2023-11-28 01:07:36,781][87424] Updated weights for policy 0, policy_version 34976 (0.0011) -[2023-11-28 01:07:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 17874944. Throughput: 0: 2684.2, 1: 2751.9. Samples: 17892572. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:07:38,445][86177] Avg episode reward: [(0, '-508.450'), (1, '-507.050')] -[2023-11-28 01:07:38,829][87424] Updated weights for policy 0, policy_version 34986 (0.0012) -[2023-11-28 01:07:39,211][87424] Updated weights for policy 0, policy_version 34996 (0.0011) -[2023-11-28 01:07:39,279][87426] Updated weights for policy 1, policy_version 34850 (0.0010) -[2023-11-28 01:07:39,610][87424] Updated weights for policy 0, policy_version 35006 (0.0011) -[2023-11-28 01:07:39,667][87426] Updated weights for policy 1, policy_version 34860 (0.0008) -[2023-11-28 01:07:40,040][87426] Updated weights for policy 1, policy_version 34870 (0.0010) -[2023-11-28 01:07:40,421][87426] Updated weights for policy 1, policy_version 34880 (0.0011) -[2023-11-28 01:07:41,560][87424] Updated weights for policy 0, policy_version 35016 (0.0009) -[2023-11-28 01:07:41,938][87424] Updated weights for policy 0, policy_version 35026 (0.0011) -[2023-11-28 01:07:42,319][87424] Updated weights for policy 0, policy_version 35036 (0.0009) -[2023-11-28 01:07:42,893][87426] Updated weights for policy 1, policy_version 34890 (0.0009) -[2023-11-28 01:07:43,274][87426] Updated weights for policy 1, policy_version 34900 (0.0008) -[2023-11-28 01:07:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 17899520. Throughput: 0: 2696.1, 1: 2719.7. Samples: 17916072. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:07:43,445][86177] Avg episode reward: [(0, '-509.340'), (1, '-507.900')] -[2023-11-28 01:07:43,656][87426] Updated weights for policy 1, policy_version 34910 (0.0010) -[2023-11-28 01:07:44,863][87424] Updated weights for policy 0, policy_version 35046 (0.0010) -[2023-11-28 01:07:45,253][87424] Updated weights for policy 0, policy_version 35056 (0.0012) -[2023-11-28 01:07:45,635][87424] Updated weights for policy 0, policy_version 35066 (0.0012) -[2023-11-28 01:07:46,114][87426] Updated weights for policy 1, policy_version 34920 (0.0008) -[2023-11-28 01:07:46,498][87426] Updated weights for policy 1, policy_version 34930 (0.0007) -[2023-11-28 01:07:46,884][87426] Updated weights for policy 1, policy_version 34940 (0.0007) -[2023-11-28 01:07:47,430][87424] Updated weights for policy 0, policy_version 35076 (0.0011) -[2023-11-28 01:07:47,810][87424] Updated weights for policy 0, policy_version 35086 (0.0010) -[2023-11-28 01:07:48,194][87424] Updated weights for policy 0, policy_version 35096 (0.0008) -[2023-11-28 01:07:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 17924096. Throughput: 0: 2706.1, 1: 2710.5. Samples: 17940736. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:07:48,445][86177] Avg episode reward: [(0, '-505.710'), (1, '-512.850')] -[2023-11-28 01:07:48,953][87426] Updated weights for policy 1, policy_version 34950 (0.0010) -[2023-11-28 01:07:49,333][87426] Updated weights for policy 1, policy_version 34960 (0.0008) -[2023-11-28 01:07:49,716][87426] Updated weights for policy 1, policy_version 34970 (0.0007) -[2023-11-28 01:07:50,044][87424] Updated weights for policy 0, policy_version 35106 (0.0010) -[2023-11-28 01:07:50,434][87424] Updated weights for policy 0, policy_version 35116 (0.0008) -[2023-11-28 01:07:50,810][87424] Updated weights for policy 0, policy_version 35126 (0.0009) -[2023-11-28 01:07:51,196][87424] Updated weights for policy 0, policy_version 35136 (0.0008) -[2023-11-28 01:07:51,972][87426] Updated weights for policy 1, policy_version 34980 (0.0010) -[2023-11-28 01:07:52,340][87426] Updated weights for policy 1, policy_version 34990 (0.0012) -[2023-11-28 01:07:52,715][87426] Updated weights for policy 1, policy_version 35000 (0.0011) -[2023-11-28 01:07:53,446][86177] Fps is (10 sec: 5733.4, 60 sec: 5461.2, 300 sec: 5442.8). Total num frames: 17956864. Throughput: 0: 2682.1, 1: 2682.1. Samples: 17971728. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:07:53,447][86177] Avg episode reward: [(0, '-505.500'), (1, '-515.000')] -[2023-11-28 01:07:53,734][87424] Updated weights for policy 0, policy_version 35146 (0.0012) -[2023-11-28 01:07:54,123][87424] Updated weights for policy 0, policy_version 35156 (0.0012) -[2023-11-28 01:07:54,506][87424] Updated weights for policy 0, policy_version 35166 (0.0011) -[2023-11-28 01:07:55,244][87426] Updated weights for policy 1, policy_version 35010 (0.0011) -[2023-11-28 01:07:55,628][87426] Updated weights for policy 1, policy_version 35020 (0.0007) -[2023-11-28 01:07:56,008][87426] Updated weights for policy 1, policy_version 35030 (0.0007) -[2023-11-28 01:07:56,385][87426] Updated weights for policy 1, policy_version 35040 (0.0007) -[2023-11-28 01:07:56,993][87424] Updated weights for policy 0, policy_version 35176 (0.0009) -[2023-11-28 01:07:57,381][87424] Updated weights for policy 0, policy_version 35186 (0.0008) -[2023-11-28 01:07:57,759][87424] Updated weights for policy 0, policy_version 35196 (0.0007) -[2023-11-28 01:07:58,153][87426] Updated weights for policy 1, policy_version 35050 (0.0011) -[2023-11-28 01:07:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 17981440. Throughput: 0: 2673.3, 1: 2667.1. Samples: 17995652. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:07:58,445][86177] Avg episode reward: [(0, '-509.940'), (1, '-509.380')] -[2023-11-28 01:07:58,538][87426] Updated weights for policy 1, policy_version 35060 (0.0011) -[2023-11-28 01:07:58,921][87426] Updated weights for policy 1, policy_version 35070 (0.0012) -[2023-11-28 01:07:59,765][87424] Updated weights for policy 0, policy_version 35206 (0.0010) -[2023-11-28 01:08:00,139][87424] Updated weights for policy 0, policy_version 35216 (0.0012) -[2023-11-28 01:08:00,519][87424] Updated weights for policy 0, policy_version 35226 (0.0011) -[2023-11-28 01:08:00,964][87426] Updated weights for policy 1, policy_version 35080 (0.0012) -[2023-11-28 01:08:01,345][87426] Updated weights for policy 1, policy_version 35090 (0.0012) -[2023-11-28 01:08:01,724][87426] Updated weights for policy 1, policy_version 35100 (0.0012) -[2023-11-28 01:08:02,633][87424] Updated weights for policy 0, policy_version 35236 (0.0009) -[2023-11-28 01:08:03,018][87424] Updated weights for policy 0, policy_version 35246 (0.0012) -[2023-11-28 01:08:03,409][87424] Updated weights for policy 0, policy_version 35256 (0.0012) -[2023-11-28 01:08:03,444][86177] Fps is (10 sec: 4916.0, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 18006016. Throughput: 0: 2695.8, 1: 2664.6. Samples: 18021136. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:08:03,446][86177] Avg episode reward: [(0, '-538.900'), (1, '-518.290')] -[2023-11-28 01:08:04,084][87426] Updated weights for policy 1, policy_version 35110 (0.0011) -[2023-11-28 01:08:04,464][87426] Updated weights for policy 1, policy_version 35120 (0.0009) -[2023-11-28 01:08:04,842][87426] Updated weights for policy 1, policy_version 35130 (0.0011) -[2023-11-28 01:08:05,831][87424] Updated weights for policy 0, policy_version 35266 (0.0009) -[2023-11-28 01:08:06,213][87424] Updated weights for policy 0, policy_version 35276 (0.0012) -[2023-11-28 01:08:06,599][87424] Updated weights for policy 0, policy_version 35286 (0.0010) -[2023-11-28 01:08:06,768][87426] Updated weights for policy 1, policy_version 35140 (0.0011) -[2023-11-28 01:08:06,976][87424] Updated weights for policy 0, policy_version 35296 (0.0011) -[2023-11-28 01:08:07,151][87426] Updated weights for policy 1, policy_version 35150 (0.0011) -[2023-11-28 01:08:07,529][87426] Updated weights for policy 1, policy_version 35160 (0.0010) -[2023-11-28 01:08:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 18038784. Throughput: 0: 2729.0, 1: 2649.4. Samples: 18053664. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:08:08,446][86177] Avg episode reward: [(0, '-576.780'), (1, '-514.740')] -[2023-11-28 01:08:09,336][87424] Updated weights for policy 0, policy_version 35306 (0.0012) -[2023-11-28 01:08:09,712][87424] Updated weights for policy 0, policy_version 35316 (0.0012) -[2023-11-28 01:08:09,969][87426] Updated weights for policy 1, policy_version 35170 (0.0009) -[2023-11-28 01:08:10,096][87424] Updated weights for policy 0, policy_version 35326 (0.0011) -[2023-11-28 01:08:10,351][87426] Updated weights for policy 1, policy_version 35180 (0.0012) -[2023-11-28 01:08:10,730][87426] Updated weights for policy 1, policy_version 35190 (0.0012) -[2023-11-28 01:08:11,098][87426] Updated weights for policy 1, policy_version 35200 (0.0012) -[2023-11-28 01:08:12,073][87424] Updated weights for policy 0, policy_version 35336 (0.0012) -[2023-11-28 01:08:12,461][87424] Updated weights for policy 0, policy_version 35346 (0.0012) -[2023-11-28 01:08:12,841][87424] Updated weights for policy 0, policy_version 35356 (0.0012) -[2023-11-28 01:08:13,377][87426] Updated weights for policy 1, policy_version 35210 (0.0008) -[2023-11-28 01:08:13,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 18063360. Throughput: 0: 2717.6, 1: 2644.4. Samples: 18077668. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:08:13,445][86177] Avg episode reward: [(0, '-568.540'), (1, '-512.280')] -[2023-11-28 01:08:13,765][87426] Updated weights for policy 1, policy_version 35220 (0.0009) -[2023-11-28 01:08:14,148][87426] Updated weights for policy 1, policy_version 35230 (0.0012) -[2023-11-28 01:08:15,063][87424] Updated weights for policy 0, policy_version 35366 (0.0012) -[2023-11-28 01:08:15,447][87424] Updated weights for policy 0, policy_version 35376 (0.0011) -[2023-11-28 01:08:15,827][87424] Updated weights for policy 0, policy_version 35386 (0.0011) -[2023-11-28 01:08:16,310][87426] Updated weights for policy 1, policy_version 35240 (0.0012) -[2023-11-28 01:08:16,686][87426] Updated weights for policy 1, policy_version 35250 (0.0012) -[2023-11-28 01:08:17,060][87426] Updated weights for policy 1, policy_version 35260 (0.0012) -[2023-11-28 01:08:17,859][87424] Updated weights for policy 0, policy_version 35396 (0.0012) -[2023-11-28 01:08:18,252][87424] Updated weights for policy 0, policy_version 35406 (0.0011) -[2023-11-28 01:08:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 18087936. Throughput: 0: 2722.3, 1: 2637.9. Samples: 18101720. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:08:18,445][86177] Avg episode reward: [(0, '-560.450'), (1, '-510.120')] -[2023-11-28 01:08:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000035264_9027584.pth... -[2023-11-28 01:08:18,505][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000032768_8388608.pth -[2023-11-28 01:08:18,635][87424] Updated weights for policy 0, policy_version 35416 (0.0007) -[2023-11-28 01:08:18,939][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000035424_9068544.pth... -[2023-11-28 01:08:18,984][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000032896_8421376.pth -[2023-11-28 01:08:18,987][87426] Updated weights for policy 1, policy_version 35270 (0.0010) -[2023-11-28 01:08:19,371][87426] Updated weights for policy 1, policy_version 35280 (0.0008) -[2023-11-28 01:08:19,762][87426] Updated weights for policy 1, policy_version 35290 (0.0008) -[2023-11-28 01:08:21,109][87424] Updated weights for policy 0, policy_version 35426 (0.0009) -[2023-11-28 01:08:21,487][87424] Updated weights for policy 0, policy_version 35436 (0.0009) -[2023-11-28 01:08:21,872][87424] Updated weights for policy 0, policy_version 35446 (0.0009) -[2023-11-28 01:08:22,133][87426] Updated weights for policy 1, policy_version 35300 (0.0009) -[2023-11-28 01:08:22,254][87424] Updated weights for policy 0, policy_version 35456 (0.0009) -[2023-11-28 01:08:22,512][87426] Updated weights for policy 1, policy_version 35310 (0.0010) -[2023-11-28 01:08:22,902][87426] Updated weights for policy 1, policy_version 35320 (0.0011) -[2023-11-28 01:08:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 18120704. Throughput: 0: 2709.5, 1: 2652.2. Samples: 18133848. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:08:23,445][86177] Avg episode reward: [(0, '-546.270'), (1, '-503.730')] -[2023-11-28 01:08:24,350][87424] Updated weights for policy 0, policy_version 35466 (0.0012) -[2023-11-28 01:08:24,736][87424] Updated weights for policy 0, policy_version 35476 (0.0012) -[2023-11-28 01:08:25,120][87424] Updated weights for policy 0, policy_version 35486 (0.0012) -[2023-11-28 01:08:25,420][87426] Updated weights for policy 1, policy_version 35330 (0.0010) -[2023-11-28 01:08:25,805][87426] Updated weights for policy 1, policy_version 35340 (0.0007) -[2023-11-28 01:08:26,176][87426] Updated weights for policy 1, policy_version 35350 (0.0007) -[2023-11-28 01:08:26,554][87426] Updated weights for policy 1, policy_version 35360 (0.0008) -[2023-11-28 01:08:27,535][87424] Updated weights for policy 0, policy_version 35496 (0.0008) -[2023-11-28 01:08:27,931][87424] Updated weights for policy 0, policy_version 35506 (0.0007) -[2023-11-28 01:08:28,313][87424] Updated weights for policy 0, policy_version 35516 (0.0008) -[2023-11-28 01:08:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 18137088. Throughput: 0: 2701.8, 1: 2666.1. Samples: 18157624. Policy #0 lag: (min: 13.0, avg: 35.7, max: 77.0) -[2023-11-28 01:08:28,445][86177] Avg episode reward: [(0, '-514.600'), (1, '-502.510')] -[2023-11-28 01:08:28,610][87426] Updated weights for policy 1, policy_version 35370 (0.0009) -[2023-11-28 01:08:28,995][87426] Updated weights for policy 1, policy_version 35380 (0.0008) -[2023-11-28 01:08:29,369][87426] Updated weights for policy 1, policy_version 35390 (0.0008) -[2023-11-28 01:08:30,509][87424] Updated weights for policy 0, policy_version 35526 (0.0009) -[2023-11-28 01:08:30,893][87424] Updated weights for policy 0, policy_version 35536 (0.0010) -[2023-11-28 01:08:31,288][87424] Updated weights for policy 0, policy_version 35546 (0.0012) -[2023-11-28 01:08:31,582][87426] Updated weights for policy 1, policy_version 35400 (0.0010) -[2023-11-28 01:08:31,962][87426] Updated weights for policy 1, policy_version 35410 (0.0012) -[2023-11-28 01:08:32,332][87426] Updated weights for policy 1, policy_version 35420 (0.0012) -[2023-11-28 01:08:33,423][87424] Updated weights for policy 0, policy_version 35556 (0.0012) -[2023-11-28 01:08:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 18169856. Throughput: 0: 2696.0, 1: 2667.5. Samples: 18182092. Policy #0 lag: (min: 13.0, avg: 35.7, max: 77.0) -[2023-11-28 01:08:33,445][86177] Avg episode reward: [(0, '-517.170'), (1, '-504.710')] -[2023-11-28 01:08:33,807][87424] Updated weights for policy 0, policy_version 35566 (0.0010) -[2023-11-28 01:08:34,196][87424] Updated weights for policy 0, policy_version 35576 (0.0009) -[2023-11-28 01:08:34,457][87426] Updated weights for policy 1, policy_version 35430 (0.0009) -[2023-11-28 01:08:34,838][87426] Updated weights for policy 1, policy_version 35440 (0.0008) -[2023-11-28 01:08:35,223][87426] Updated weights for policy 1, policy_version 35450 (0.0009) -[2023-11-28 01:08:36,743][87424] Updated weights for policy 0, policy_version 35586 (0.0010) -[2023-11-28 01:08:37,132][87424] Updated weights for policy 0, policy_version 35596 (0.0012) -[2023-11-28 01:08:37,362][87426] Updated weights for policy 1, policy_version 35460 (0.0009) -[2023-11-28 01:08:37,517][87424] Updated weights for policy 0, policy_version 35606 (0.0011) -[2023-11-28 01:08:37,751][87426] Updated weights for policy 1, policy_version 35470 (0.0010) -[2023-11-28 01:08:37,890][87424] Updated weights for policy 0, policy_version 35616 (0.0010) -[2023-11-28 01:08:38,126][87426] Updated weights for policy 1, policy_version 35480 (0.0012) -[2023-11-28 01:08:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 18202624. Throughput: 0: 2699.7, 1: 2686.9. Samples: 18214112. Policy #0 lag: (min: 13.0, avg: 35.7, max: 77.0) -[2023-11-28 01:08:38,445][86177] Avg episode reward: [(0, '-517.480'), (1, '-504.880')] -[2023-11-28 01:08:39,940][87424] Updated weights for policy 0, policy_version 35626 (0.0010) -[2023-11-28 01:08:40,327][87424] Updated weights for policy 0, policy_version 35636 (0.0011) -[2023-11-28 01:08:40,646][87426] Updated weights for policy 1, policy_version 35490 (0.0011) -[2023-11-28 01:08:40,718][87424] Updated weights for policy 0, policy_version 35646 (0.0011) -[2023-11-28 01:08:41,030][87426] Updated weights for policy 1, policy_version 35500 (0.0012) -[2023-11-28 01:08:41,403][87426] Updated weights for policy 1, policy_version 35510 (0.0009) -[2023-11-28 01:08:41,777][87426] Updated weights for policy 1, policy_version 35520 (0.0009) -[2023-11-28 01:08:43,033][87424] Updated weights for policy 0, policy_version 35656 (0.0011) -[2023-11-28 01:08:43,422][87424] Updated weights for policy 0, policy_version 35666 (0.0011) -[2023-11-28 01:08:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 18219008. Throughput: 0: 2715.3, 1: 2670.1. Samples: 18237996. Policy #0 lag: (min: 13.0, avg: 35.7, max: 77.0) -[2023-11-28 01:08:43,445][86177] Avg episode reward: [(0, '-520.150'), (1, '-501.450')] -[2023-11-28 01:08:43,797][87424] Updated weights for policy 0, policy_version 35676 (0.0011) -[2023-11-28 01:08:44,029][87426] Updated weights for policy 1, policy_version 35530 (0.0009) -[2023-11-28 01:08:44,411][87426] Updated weights for policy 1, policy_version 35540 (0.0009) -[2023-11-28 01:08:44,788][87426] Updated weights for policy 1, policy_version 35550 (0.0009) -[2023-11-28 01:08:45,771][87424] Updated weights for policy 0, policy_version 35686 (0.0010) -[2023-11-28 01:08:46,167][87424] Updated weights for policy 0, policy_version 35696 (0.0010) -[2023-11-28 01:08:46,540][87424] Updated weights for policy 0, policy_version 35706 (0.0007) -[2023-11-28 01:08:46,932][87426] Updated weights for policy 1, policy_version 35560 (0.0011) -[2023-11-28 01:08:47,302][87426] Updated weights for policy 1, policy_version 35570 (0.0012) -[2023-11-28 01:08:47,681][87426] Updated weights for policy 1, policy_version 35580 (0.0010) -[2023-11-28 01:08:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 18251776. Throughput: 0: 2688.5, 1: 2672.3. Samples: 18262372. Policy #0 lag: (min: 13.0, avg: 35.7, max: 77.0) -[2023-11-28 01:08:48,446][86177] Avg episode reward: [(0, '-513.020'), (1, '-508.100')] -[2023-11-28 01:08:48,940][87424] Updated weights for policy 0, policy_version 35716 (0.0009) -[2023-11-28 01:08:49,329][87424] Updated weights for policy 0, policy_version 35726 (0.0012) -[2023-11-28 01:08:49,711][87424] Updated weights for policy 0, policy_version 35736 (0.0012) -[2023-11-28 01:08:49,765][87426] Updated weights for policy 1, policy_version 35590 (0.0012) -[2023-11-28 01:08:50,137][87426] Updated weights for policy 1, policy_version 35600 (0.0011) -[2023-11-28 01:08:50,517][87426] Updated weights for policy 1, policy_version 35610 (0.0011) -[2023-11-28 01:08:51,684][87424] Updated weights for policy 0, policy_version 35746 (0.0012) -[2023-11-28 01:08:52,060][87424] Updated weights for policy 0, policy_version 35756 (0.0013) -[2023-11-28 01:08:52,435][87424] Updated weights for policy 0, policy_version 35766 (0.0012) -[2023-11-28 01:08:52,819][87424] Updated weights for policy 0, policy_version 35776 (0.0012) -[2023-11-28 01:08:53,064][87426] Updated weights for policy 1, policy_version 35620 (0.0009) -[2023-11-28 01:08:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5325.0, 300 sec: 5387.3). Total num frames: 18276352. Throughput: 0: 2686.0, 1: 2666.1. Samples: 18294504. Policy #0 lag: (min: 31.0, avg: 31.3, max: 39.0) -[2023-11-28 01:08:53,445][86177] Avg episode reward: [(0, '-506.160'), (1, '-513.390')] -[2023-11-28 01:08:53,446][87426] Updated weights for policy 1, policy_version 35630 (0.0011) -[2023-11-28 01:08:53,824][87426] Updated weights for policy 1, policy_version 35640 (0.0011) -[2023-11-28 01:08:55,177][87424] Updated weights for policy 0, policy_version 35786 (0.0012) -[2023-11-28 01:08:55,557][87424] Updated weights for policy 0, policy_version 35796 (0.0012) -[2023-11-28 01:08:55,685][87426] Updated weights for policy 1, policy_version 35650 (0.0011) -[2023-11-28 01:08:55,936][87424] Updated weights for policy 0, policy_version 35806 (0.0011) -[2023-11-28 01:08:56,059][87426] Updated weights for policy 1, policy_version 35660 (0.0011) -[2023-11-28 01:08:56,438][87426] Updated weights for policy 1, policy_version 35670 (0.0012) -[2023-11-28 01:08:56,817][87426] Updated weights for policy 1, policy_version 35680 (0.0012) -[2023-11-28 01:08:57,809][87424] Updated weights for policy 0, policy_version 35816 (0.0012) -[2023-11-28 01:08:58,184][87424] Updated weights for policy 0, policy_version 35826 (0.0012) -[2023-11-28 01:08:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 18300928. Throughput: 0: 2696.8, 1: 2670.4. Samples: 18319192. Policy #0 lag: (min: 31.0, avg: 31.3, max: 39.0) -[2023-11-28 01:08:58,445][86177] Avg episode reward: [(0, '-512.210'), (1, '-526.540')] -[2023-11-28 01:08:58,566][87424] Updated weights for policy 0, policy_version 35836 (0.0012) -[2023-11-28 01:08:59,398][87426] Updated weights for policy 1, policy_version 35690 (0.0012) -[2023-11-28 01:08:59,771][87426] Updated weights for policy 1, policy_version 35700 (0.0012) -[2023-11-28 01:09:00,145][87426] Updated weights for policy 1, policy_version 35710 (0.0011) -[2023-11-28 01:09:00,272][87424] Updated weights for policy 0, policy_version 35846 (0.0011) -[2023-11-28 01:09:00,658][87424] Updated weights for policy 0, policy_version 35856 (0.0010) -[2023-11-28 01:09:01,044][87424] Updated weights for policy 0, policy_version 35866 (0.0012) -[2023-11-28 01:09:02,641][87426] Updated weights for policy 1, policy_version 35720 (0.0008) -[2023-11-28 01:09:03,019][87426] Updated weights for policy 1, policy_version 35730 (0.0010) -[2023-11-28 01:09:03,062][87424] Updated weights for policy 0, policy_version 35876 (0.0012) -[2023-11-28 01:09:03,400][87426] Updated weights for policy 1, policy_version 35740 (0.0010) -[2023-11-28 01:09:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 18325504. Throughput: 0: 2717.0, 1: 2675.4. Samples: 18344376. Policy #0 lag: (min: 31.0, avg: 31.3, max: 39.0) -[2023-11-28 01:09:03,445][86177] Avg episode reward: [(0, '-533.350'), (1, '-530.220')] -[2023-11-28 01:09:03,453][87424] Updated weights for policy 0, policy_version 35886 (0.0011) -[2023-11-28 01:09:03,837][87424] Updated weights for policy 0, policy_version 35896 (0.0011) -[2023-11-28 01:09:05,681][87424] Updated weights for policy 0, policy_version 35906 (0.0011) -[2023-11-28 01:09:05,771][87426] Updated weights for policy 1, policy_version 35750 (0.0010) -[2023-11-28 01:09:06,060][87424] Updated weights for policy 0, policy_version 35916 (0.0012) -[2023-11-28 01:09:06,150][87426] Updated weights for policy 1, policy_version 35760 (0.0011) -[2023-11-28 01:09:06,440][87424] Updated weights for policy 0, policy_version 35926 (0.0012) -[2023-11-28 01:09:06,531][87426] Updated weights for policy 1, policy_version 35770 (0.0012) -[2023-11-28 01:09:06,822][87424] Updated weights for policy 0, policy_version 35936 (0.0012) -[2023-11-28 01:09:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 18358272. Throughput: 0: 2745.6, 1: 2671.6. Samples: 18377620. Policy #0 lag: (min: 31.0, avg: 31.3, max: 39.0) -[2023-11-28 01:09:08,445][86177] Avg episode reward: [(0, '-534.870'), (1, '-527.090')] -[2023-11-28 01:09:08,559][87424] Updated weights for policy 0, policy_version 35946 (0.0008) -[2023-11-28 01:09:08,782][87426] Updated weights for policy 1, policy_version 35780 (0.0011) -[2023-11-28 01:09:08,941][87424] Updated weights for policy 0, policy_version 35956 (0.0010) -[2023-11-28 01:09:09,160][87426] Updated weights for policy 1, policy_version 35790 (0.0010) -[2023-11-28 01:09:09,327][87424] Updated weights for policy 0, policy_version 35966 (0.0010) -[2023-11-28 01:09:09,548][87426] Updated weights for policy 1, policy_version 35800 (0.0012) -[2023-11-28 01:09:11,469][87424] Updated weights for policy 0, policy_version 35976 (0.0012) -[2023-11-28 01:09:11,864][87424] Updated weights for policy 0, policy_version 35986 (0.0012) -[2023-11-28 01:09:11,977][87426] Updated weights for policy 1, policy_version 35810 (0.0010) -[2023-11-28 01:09:12,241][87424] Updated weights for policy 0, policy_version 35996 (0.0011) -[2023-11-28 01:09:12,354][87426] Updated weights for policy 1, policy_version 35820 (0.0012) -[2023-11-28 01:09:12,733][87426] Updated weights for policy 1, policy_version 35830 (0.0012) -[2023-11-28 01:09:13,107][87426] Updated weights for policy 1, policy_version 35840 (0.0011) -[2023-11-28 01:09:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 18391040. Throughput: 0: 2750.8, 1: 2679.5. Samples: 18401992. Policy #0 lag: (min: 31.0, avg: 31.3, max: 39.0) -[2023-11-28 01:09:13,445][86177] Avg episode reward: [(0, '-537.120'), (1, '-522.310')] -[2023-11-28 01:09:14,841][87424] Updated weights for policy 0, policy_version 36006 (0.0012) -[2023-11-28 01:09:15,130][87426] Updated weights for policy 1, policy_version 35850 (0.0010) -[2023-11-28 01:09:15,220][87424] Updated weights for policy 0, policy_version 36016 (0.0012) -[2023-11-28 01:09:15,516][87426] Updated weights for policy 1, policy_version 35860 (0.0011) -[2023-11-28 01:09:15,607][87424] Updated weights for policy 0, policy_version 36026 (0.0011) -[2023-11-28 01:09:15,887][87426] Updated weights for policy 1, policy_version 35870 (0.0012) -[2023-11-28 01:09:17,585][87424] Updated weights for policy 0, policy_version 36036 (0.0011) -[2023-11-28 01:09:17,882][87426] Updated weights for policy 1, policy_version 35880 (0.0011) -[2023-11-28 01:09:17,964][87424] Updated weights for policy 0, policy_version 36046 (0.0010) -[2023-11-28 01:09:18,270][87426] Updated weights for policy 1, policy_version 35890 (0.0011) -[2023-11-28 01:09:18,345][87424] Updated weights for policy 0, policy_version 36056 (0.0011) -[2023-11-28 01:09:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 18407424. Throughput: 0: 2746.3, 1: 2687.8. Samples: 18426628. Policy #0 lag: (min: 24.0, avg: 46.4, max: 56.0) -[2023-11-28 01:09:18,445][86177] Avg episode reward: [(0, '-515.690'), (1, '-517.780')] -[2023-11-28 01:09:18,642][87426] Updated weights for policy 1, policy_version 35900 (0.0011) -[2023-11-28 01:09:20,424][87424] Updated weights for policy 0, policy_version 36066 (0.0010) -[2023-11-28 01:09:20,809][87424] Updated weights for policy 0, policy_version 36076 (0.0011) -[2023-11-28 01:09:21,196][87424] Updated weights for policy 0, policy_version 36086 (0.0012) -[2023-11-28 01:09:21,204][87426] Updated weights for policy 1, policy_version 35910 (0.0010) -[2023-11-28 01:09:21,580][87426] Updated weights for policy 1, policy_version 35920 (0.0011) -[2023-11-28 01:09:21,583][87424] Updated weights for policy 0, policy_version 36096 (0.0012) -[2023-11-28 01:09:21,970][87426] Updated weights for policy 1, policy_version 35930 (0.0011) -[2023-11-28 01:09:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 18440192. Throughput: 0: 2781.5, 1: 2673.2. Samples: 18459576. Policy #0 lag: (min: 24.0, avg: 46.4, max: 56.0) -[2023-11-28 01:09:23,445][86177] Avg episode reward: [(0, '-503.260'), (1, '-515.840')] -[2023-11-28 01:09:23,647][87424] Updated weights for policy 0, policy_version 36106 (0.0008) -[2023-11-28 01:09:24,045][87424] Updated weights for policy 0, policy_version 36116 (0.0008) -[2023-11-28 01:09:24,418][87424] Updated weights for policy 0, policy_version 36126 (0.0007) -[2023-11-28 01:09:24,569][87426] Updated weights for policy 1, policy_version 35940 (0.0010) -[2023-11-28 01:09:24,951][87426] Updated weights for policy 1, policy_version 35950 (0.0007) -[2023-11-28 01:09:25,336][87426] Updated weights for policy 1, policy_version 35960 (0.0007) -[2023-11-28 01:09:26,869][87424] Updated weights for policy 0, policy_version 36136 (0.0007) -[2023-11-28 01:09:27,127][87426] Updated weights for policy 1, policy_version 35970 (0.0007) -[2023-11-28 01:09:27,252][87424] Updated weights for policy 0, policy_version 36146 (0.0009) -[2023-11-28 01:09:27,521][87426] Updated weights for policy 1, policy_version 35980 (0.0007) -[2023-11-28 01:09:27,643][87424] Updated weights for policy 0, policy_version 36156 (0.0011) -[2023-11-28 01:09:27,892][87426] Updated weights for policy 1, policy_version 35990 (0.0007) -[2023-11-28 01:09:28,264][87426] Updated weights for policy 1, policy_version 36000 (0.0007) -[2023-11-28 01:09:28,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 18472960. Throughput: 0: 2760.5, 1: 2679.0. Samples: 18482776. Policy #0 lag: (min: 24.0, avg: 46.4, max: 56.0) -[2023-11-28 01:09:28,445][86177] Avg episode reward: [(0, '-536.290'), (1, '-521.520')] -[2023-11-28 01:09:29,448][87424] Updated weights for policy 0, policy_version 36166 (0.0008) -[2023-11-28 01:09:29,839][87424] Updated weights for policy 0, policy_version 36176 (0.0008) -[2023-11-28 01:09:30,217][87424] Updated weights for policy 0, policy_version 36186 (0.0008) -[2023-11-28 01:09:30,650][87426] Updated weights for policy 1, policy_version 36010 (0.0012) -[2023-11-28 01:09:31,022][87426] Updated weights for policy 1, policy_version 36020 (0.0012) -[2023-11-28 01:09:31,399][87426] Updated weights for policy 1, policy_version 36030 (0.0012) -[2023-11-28 01:09:32,701][87424] Updated weights for policy 0, policy_version 36196 (0.0009) -[2023-11-28 01:09:33,078][87424] Updated weights for policy 0, policy_version 36206 (0.0009) -[2023-11-28 01:09:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 18489344. Throughput: 0: 2766.2, 1: 2654.4. Samples: 18506300. Policy #0 lag: (min: 24.0, avg: 46.4, max: 56.0) -[2023-11-28 01:09:33,445][86177] Avg episode reward: [(0, '-540.040'), (1, '-521.580')] -[2023-11-28 01:09:33,460][87424] Updated weights for policy 0, policy_version 36216 (0.0008) -[2023-11-28 01:09:33,566][87426] Updated weights for policy 1, policy_version 36040 (0.0008) -[2023-11-28 01:09:33,946][87426] Updated weights for policy 1, policy_version 36050 (0.0007) -[2023-11-28 01:09:34,325][87426] Updated weights for policy 1, policy_version 36060 (0.0007) -[2023-11-28 01:09:35,579][87424] Updated weights for policy 0, policy_version 36226 (0.0008) -[2023-11-28 01:09:35,963][87424] Updated weights for policy 0, policy_version 36236 (0.0011) -[2023-11-28 01:09:36,193][87426] Updated weights for policy 1, policy_version 36070 (0.0010) -[2023-11-28 01:09:36,349][87424] Updated weights for policy 0, policy_version 36246 (0.0011) -[2023-11-28 01:09:36,570][87426] Updated weights for policy 1, policy_version 36080 (0.0010) -[2023-11-28 01:09:36,719][87424] Updated weights for policy 0, policy_version 36256 (0.0009) -[2023-11-28 01:09:36,950][87426] Updated weights for policy 1, policy_version 36090 (0.0009) -[2023-11-28 01:09:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 18522112. Throughput: 0: 2775.6, 1: 2661.0. Samples: 18539152. Policy #0 lag: (min: 24.0, avg: 46.4, max: 56.0) -[2023-11-28 01:09:38,445][86177] Avg episode reward: [(0, '-539.610'), (1, '-509.240')] -[2023-11-28 01:09:38,618][87424] Updated weights for policy 0, policy_version 36266 (0.0012) -[2023-11-28 01:09:39,011][87424] Updated weights for policy 0, policy_version 36276 (0.0012) -[2023-11-28 01:09:39,393][87424] Updated weights for policy 0, policy_version 36286 (0.0012) -[2023-11-28 01:09:39,420][87426] Updated weights for policy 1, policy_version 36100 (0.0008) -[2023-11-28 01:09:39,788][87426] Updated weights for policy 1, policy_version 36110 (0.0010) -[2023-11-28 01:09:40,167][87426] Updated weights for policy 1, policy_version 36120 (0.0011) -[2023-11-28 01:09:41,522][87424] Updated weights for policy 0, policy_version 36296 (0.0009) -[2023-11-28 01:09:41,908][87424] Updated weights for policy 0, policy_version 36306 (0.0011) -[2023-11-28 01:09:42,239][87426] Updated weights for policy 1, policy_version 36130 (0.0011) -[2023-11-28 01:09:42,290][87424] Updated weights for policy 0, policy_version 36316 (0.0012) -[2023-11-28 01:09:42,617][87426] Updated weights for policy 1, policy_version 36140 (0.0011) -[2023-11-28 01:09:42,995][87426] Updated weights for policy 1, policy_version 36150 (0.0010) -[2023-11-28 01:09:43,377][87426] Updated weights for policy 1, policy_version 36160 (0.0010) -[2023-11-28 01:09:43,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 18554880. Throughput: 0: 2786.7, 1: 2660.0. Samples: 18564292. Policy #0 lag: (min: 24.0, avg: 46.4, max: 62.0) -[2023-11-28 01:09:43,445][86177] Avg episode reward: [(0, '-561.370'), (1, '-508.080')] -[2023-11-28 01:09:44,282][87424] Updated weights for policy 0, policy_version 36326 (0.0012) -[2023-11-28 01:09:44,657][87424] Updated weights for policy 0, policy_version 36336 (0.0012) -[2023-11-28 01:09:45,046][87424] Updated weights for policy 0, policy_version 36346 (0.0009) -[2023-11-28 01:09:45,146][87426] Updated weights for policy 1, policy_version 36170 (0.0009) -[2023-11-28 01:09:45,525][87426] Updated weights for policy 1, policy_version 36180 (0.0011) -[2023-11-28 01:09:45,914][87426] Updated weights for policy 1, policy_version 36190 (0.0010) -[2023-11-28 01:09:47,505][87424] Updated weights for policy 0, policy_version 36356 (0.0007) -[2023-11-28 01:09:47,879][87424] Updated weights for policy 0, policy_version 36366 (0.0008) -[2023-11-28 01:09:48,175][87426] Updated weights for policy 1, policy_version 36200 (0.0010) -[2023-11-28 01:09:48,256][87424] Updated weights for policy 0, policy_version 36376 (0.0009) -[2023-11-28 01:09:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 18571264. Throughput: 0: 2756.7, 1: 2674.7. Samples: 18588788. Policy #0 lag: (min: 24.0, avg: 46.4, max: 62.0) -[2023-11-28 01:09:48,445][86177] Avg episode reward: [(0, '-524.090'), (1, '-500.840')] -[2023-11-28 01:09:48,549][87426] Updated weights for policy 1, policy_version 36210 (0.0012) -[2023-11-28 01:09:48,944][87426] Updated weights for policy 1, policy_version 36220 (0.0012) -[2023-11-28 01:09:50,501][87424] Updated weights for policy 0, policy_version 36386 (0.0011) -[2023-11-28 01:09:50,879][87424] Updated weights for policy 0, policy_version 36396 (0.0012) -[2023-11-28 01:09:51,230][87426] Updated weights for policy 1, policy_version 36230 (0.0012) -[2023-11-28 01:09:51,258][87424] Updated weights for policy 0, policy_version 36406 (0.0012) -[2023-11-28 01:09:51,600][87426] Updated weights for policy 1, policy_version 36240 (0.0009) -[2023-11-28 01:09:51,640][87424] Updated weights for policy 0, policy_version 36416 (0.0010) -[2023-11-28 01:09:51,987][87426] Updated weights for policy 1, policy_version 36250 (0.0012) -[2023-11-28 01:09:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 18604032. Throughput: 0: 2717.4, 1: 2690.9. Samples: 18620996. Policy #0 lag: (min: 24.0, avg: 46.4, max: 62.0) -[2023-11-28 01:09:53,445][86177] Avg episode reward: [(0, '-520.800'), (1, '-499.420')] -[2023-11-28 01:09:53,856][87424] Updated weights for policy 0, policy_version 36426 (0.0012) -[2023-11-28 01:09:54,077][87426] Updated weights for policy 1, policy_version 36260 (0.0012) -[2023-11-28 01:09:54,240][87424] Updated weights for policy 0, policy_version 36436 (0.0012) -[2023-11-28 01:09:54,464][87426] Updated weights for policy 1, policy_version 36270 (0.0012) -[2023-11-28 01:09:54,619][87424] Updated weights for policy 0, policy_version 36446 (0.0011) -[2023-11-28 01:09:54,836][87426] Updated weights for policy 1, policy_version 36280 (0.0010) -[2023-11-28 01:09:56,816][87424] Updated weights for policy 0, policy_version 36456 (0.0009) -[2023-11-28 01:09:56,869][87426] Updated weights for policy 1, policy_version 36290 (0.0011) -[2023-11-28 01:09:57,203][87424] Updated weights for policy 0, policy_version 36466 (0.0008) -[2023-11-28 01:09:57,247][87426] Updated weights for policy 1, policy_version 36300 (0.0007) -[2023-11-28 01:09:57,585][87424] Updated weights for policy 0, policy_version 36476 (0.0009) -[2023-11-28 01:09:57,629][87426] Updated weights for policy 1, policy_version 36310 (0.0010) -[2023-11-28 01:09:57,993][87426] Updated weights for policy 1, policy_version 36320 (0.0012) -[2023-11-28 01:09:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 18636800. Throughput: 0: 2727.0, 1: 2697.1. Samples: 18646080. Policy #0 lag: (min: 24.0, avg: 46.4, max: 62.0) -[2023-11-28 01:09:58,446][86177] Avg episode reward: [(0, '-501.880'), (1, '-499.430')] -[2023-11-28 01:09:59,711][87424] Updated weights for policy 0, policy_version 36486 (0.0008) -[2023-11-28 01:10:00,095][87424] Updated weights for policy 0, policy_version 36496 (0.0011) -[2023-11-28 01:10:00,357][87426] Updated weights for policy 1, policy_version 36330 (0.0011) -[2023-11-28 01:10:00,477][87424] Updated weights for policy 0, policy_version 36506 (0.0011) -[2023-11-28 01:10:00,733][87426] Updated weights for policy 1, policy_version 36340 (0.0011) -[2023-11-28 01:10:01,108][87426] Updated weights for policy 1, policy_version 36350 (0.0011) -[2023-11-28 01:10:03,011][87424] Updated weights for policy 0, policy_version 36516 (0.0009) -[2023-11-28 01:10:03,340][87426] Updated weights for policy 1, policy_version 36360 (0.0011) -[2023-11-28 01:10:03,396][87424] Updated weights for policy 0, policy_version 36526 (0.0011) -[2023-11-28 01:10:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 18653184. Throughput: 0: 2737.9, 1: 2681.5. Samples: 18670500. Policy #0 lag: (min: 24.0, avg: 46.4, max: 62.0) -[2023-11-28 01:10:03,445][86177] Avg episode reward: [(0, '-501.340'), (1, '-495.570')] -[2023-11-28 01:10:03,711][87426] Updated weights for policy 1, policy_version 36370 (0.0011) -[2023-11-28 01:10:03,786][87424] Updated weights for policy 0, policy_version 36536 (0.0009) -[2023-11-28 01:10:04,089][87426] Updated weights for policy 1, policy_version 36380 (0.0008) -[2023-11-28 01:10:04,237][87320] Saving new best policy, reward=-495.570! -[2023-11-28 01:10:06,080][87426] Updated weights for policy 1, policy_version 36390 (0.0009) -[2023-11-28 01:10:06,394][87424] Updated weights for policy 0, policy_version 36546 (0.0011) -[2023-11-28 01:10:06,464][87426] Updated weights for policy 1, policy_version 36400 (0.0011) -[2023-11-28 01:10:06,789][87424] Updated weights for policy 0, policy_version 36556 (0.0008) -[2023-11-28 01:10:06,835][87426] Updated weights for policy 1, policy_version 36410 (0.0010) -[2023-11-28 01:10:07,172][87424] Updated weights for policy 0, policy_version 36566 (0.0010) -[2023-11-28 01:10:07,551][87424] Updated weights for policy 0, policy_version 36576 (0.0012) -[2023-11-28 01:10:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 18685952. Throughput: 0: 2700.4, 1: 2703.8. Samples: 18702764. Policy #0 lag: (min: 31.0, avg: 50.5, max: 79.0) -[2023-11-28 01:10:08,445][86177] Avg episode reward: [(0, '-506.120'), (1, '-500.470')] -[2023-11-28 01:10:09,244][87426] Updated weights for policy 1, policy_version 36420 (0.0010) -[2023-11-28 01:10:09,378][87424] Updated weights for policy 0, policy_version 36586 (0.0009) -[2023-11-28 01:10:09,620][87426] Updated weights for policy 1, policy_version 36430 (0.0009) -[2023-11-28 01:10:09,761][87424] Updated weights for policy 0, policy_version 36596 (0.0009) -[2023-11-28 01:10:09,997][87426] Updated weights for policy 1, policy_version 36440 (0.0013) -[2023-11-28 01:10:10,132][87424] Updated weights for policy 0, policy_version 36606 (0.0011) -[2023-11-28 01:10:11,869][87424] Updated weights for policy 0, policy_version 36616 (0.0011) -[2023-11-28 01:10:12,081][87426] Updated weights for policy 1, policy_version 36450 (0.0011) -[2023-11-28 01:10:12,256][87424] Updated weights for policy 0, policy_version 36626 (0.0012) -[2023-11-28 01:10:12,455][87426] Updated weights for policy 1, policy_version 36460 (0.0011) -[2023-11-28 01:10:12,635][87424] Updated weights for policy 0, policy_version 36636 (0.0011) -[2023-11-28 01:10:12,829][87426] Updated weights for policy 1, policy_version 36470 (0.0010) -[2023-11-28 01:10:13,206][87426] Updated weights for policy 1, policy_version 36480 (0.0009) -[2023-11-28 01:10:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 18718720. Throughput: 0: 2713.2, 1: 2709.0. Samples: 18726772. Policy #0 lag: (min: 31.0, avg: 50.5, max: 79.0) -[2023-11-28 01:10:13,445][86177] Avg episode reward: [(0, '-507.860'), (1, '-504.220')] -[2023-11-28 01:10:14,877][87424] Updated weights for policy 0, policy_version 36646 (0.0011) -[2023-11-28 01:10:15,199][87426] Updated weights for policy 1, policy_version 36490 (0.0012) -[2023-11-28 01:10:15,257][87424] Updated weights for policy 0, policy_version 36656 (0.0012) -[2023-11-28 01:10:15,578][87426] Updated weights for policy 1, policy_version 36500 (0.0011) -[2023-11-28 01:10:15,635][87424] Updated weights for policy 0, policy_version 36666 (0.0011) -[2023-11-28 01:10:15,951][87426] Updated weights for policy 1, policy_version 36510 (0.0011) -[2023-11-28 01:10:17,714][87426] Updated weights for policy 1, policy_version 36520 (0.0010) -[2023-11-28 01:10:17,855][87424] Updated weights for policy 0, policy_version 36676 (0.0009) -[2023-11-28 01:10:18,094][87426] Updated weights for policy 1, policy_version 36530 (0.0007) -[2023-11-28 01:10:18,234][87424] Updated weights for policy 0, policy_version 36686 (0.0011) -[2023-11-28 01:10:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 18735104. Throughput: 0: 2715.5, 1: 2738.5. Samples: 18751728. Policy #0 lag: (min: 31.0, avg: 50.5, max: 79.0) -[2023-11-28 01:10:18,445][86177] Avg episode reward: [(0, '-508.210'), (1, '-501.700')] -[2023-11-28 01:10:18,476][87426] Updated weights for policy 1, policy_version 36540 (0.0007) -[2023-11-28 01:10:18,613][87424] Updated weights for policy 0, policy_version 36696 (0.0008) -[2023-11-28 01:10:18,627][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000036544_9355264.pth... -[2023-11-28 01:10:18,673][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000034016_8708096.pth -[2023-11-28 01:10:18,912][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000036704_9396224.pth... -[2023-11-28 01:10:18,957][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000034144_8740864.pth -[2023-11-28 01:10:20,829][87426] Updated weights for policy 1, policy_version 36550 (0.0008) -[2023-11-28 01:10:20,845][87424] Updated weights for policy 0, policy_version 36706 (0.0009) -[2023-11-28 01:10:21,205][87426] Updated weights for policy 1, policy_version 36560 (0.0010) -[2023-11-28 01:10:21,237][87424] Updated weights for policy 0, policy_version 36716 (0.0012) -[2023-11-28 01:10:21,587][87426] Updated weights for policy 1, policy_version 36570 (0.0010) -[2023-11-28 01:10:21,619][87424] Updated weights for policy 0, policy_version 36726 (0.0011) -[2023-11-28 01:10:22,004][87424] Updated weights for policy 0, policy_version 36736 (0.0012) -[2023-11-28 01:10:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 18767872. Throughput: 0: 2709.4, 1: 2750.8. Samples: 18784860. Policy #0 lag: (min: 31.0, avg: 50.5, max: 79.0) -[2023-11-28 01:10:23,445][86177] Avg episode reward: [(0, '-508.620'), (1, '-505.740')] -[2023-11-28 01:10:23,869][87426] Updated weights for policy 1, policy_version 36580 (0.0011) -[2023-11-28 01:10:24,253][87426] Updated weights for policy 1, policy_version 36590 (0.0008) -[2023-11-28 01:10:24,269][87424] Updated weights for policy 0, policy_version 36746 (0.0012) -[2023-11-28 01:10:24,627][87426] Updated weights for policy 1, policy_version 36600 (0.0007) -[2023-11-28 01:10:24,639][87424] Updated weights for policy 0, policy_version 36756 (0.0011) -[2023-11-28 01:10:25,016][87424] Updated weights for policy 0, policy_version 36766 (0.0011) -[2023-11-28 01:10:26,786][87426] Updated weights for policy 1, policy_version 36610 (0.0008) -[2023-11-28 01:10:26,792][87424] Updated weights for policy 0, policy_version 36776 (0.0011) -[2023-11-28 01:10:27,170][87426] Updated weights for policy 1, policy_version 36620 (0.0011) -[2023-11-28 01:10:27,180][87424] Updated weights for policy 0, policy_version 36786 (0.0011) -[2023-11-28 01:10:27,544][87426] Updated weights for policy 1, policy_version 36630 (0.0012) -[2023-11-28 01:10:27,565][87424] Updated weights for policy 0, policy_version 36796 (0.0011) -[2023-11-28 01:10:27,920][87426] Updated weights for policy 1, policy_version 36640 (0.0012) -[2023-11-28 01:10:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 18800640. Throughput: 0: 2713.6, 1: 2748.7. Samples: 18810096. Policy #0 lag: (min: 31.0, avg: 50.5, max: 79.0) -[2023-11-28 01:10:28,445][86177] Avg episode reward: [(0, '-504.990'), (1, '-546.810')] -[2023-11-28 01:10:29,748][87424] Updated weights for policy 0, policy_version 36806 (0.0011) -[2023-11-28 01:10:29,964][87426] Updated weights for policy 1, policy_version 36650 (0.0012) -[2023-11-28 01:10:30,123][87424] Updated weights for policy 0, policy_version 36816 (0.0008) -[2023-11-28 01:10:30,347][87426] Updated weights for policy 1, policy_version 36660 (0.0010) -[2023-11-28 01:10:30,503][87424] Updated weights for policy 0, policy_version 36826 (0.0009) -[2023-11-28 01:10:30,729][87426] Updated weights for policy 1, policy_version 36670 (0.0010) -[2023-11-28 01:10:32,768][87424] Updated weights for policy 0, policy_version 36836 (0.0012) -[2023-11-28 01:10:33,129][87426] Updated weights for policy 1, policy_version 36680 (0.0009) -[2023-11-28 01:10:33,153][87424] Updated weights for policy 0, policy_version 36846 (0.0012) -[2023-11-28 01:10:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 18817024. Throughput: 0: 2734.2, 1: 2735.6. Samples: 18834932. Policy #0 lag: (min: 31.0, avg: 50.5, max: 79.0) -[2023-11-28 01:10:33,445][86177] Avg episode reward: [(0, '-503.110'), (1, '-546.110')] -[2023-11-28 01:10:33,511][87426] Updated weights for policy 1, policy_version 36690 (0.0009) -[2023-11-28 01:10:33,530][87424] Updated weights for policy 0, policy_version 36856 (0.0012) -[2023-11-28 01:10:33,884][87426] Updated weights for policy 1, policy_version 36700 (0.0011) -[2023-11-28 01:10:35,456][87424] Updated weights for policy 0, policy_version 36866 (0.0012) -[2023-11-28 01:10:35,832][87424] Updated weights for policy 0, policy_version 36876 (0.0012) -[2023-11-28 01:10:36,217][87424] Updated weights for policy 0, policy_version 36886 (0.0012) -[2023-11-28 01:10:36,229][87426] Updated weights for policy 1, policy_version 36710 (0.0011) -[2023-11-28 01:10:36,598][87424] Updated weights for policy 0, policy_version 36896 (0.0010) -[2023-11-28 01:10:36,614][87426] Updated weights for policy 1, policy_version 36720 (0.0012) -[2023-11-28 01:10:36,988][87426] Updated weights for policy 1, policy_version 36730 (0.0012) -[2023-11-28 01:10:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 18849792. Throughput: 0: 2763.0, 1: 2700.5. Samples: 18866856. Policy #0 lag: (min: 31.0, avg: 35.8, max: 59.0) -[2023-11-28 01:10:38,445][86177] Avg episode reward: [(0, '-509.540'), (1, '-544.340')] -[2023-11-28 01:10:38,965][87424] Updated weights for policy 0, policy_version 36906 (0.0010) -[2023-11-28 01:10:39,351][87424] Updated weights for policy 0, policy_version 36916 (0.0008) -[2023-11-28 01:10:39,506][87426] Updated weights for policy 1, policy_version 36740 (0.0011) -[2023-11-28 01:10:39,737][87424] Updated weights for policy 0, policy_version 36926 (0.0008) -[2023-11-28 01:10:39,893][87426] Updated weights for policy 1, policy_version 36750 (0.0011) -[2023-11-28 01:10:40,266][87426] Updated weights for policy 1, policy_version 36760 (0.0008) -[2023-11-28 01:10:41,969][87424] Updated weights for policy 0, policy_version 36936 (0.0011) -[2023-11-28 01:10:42,316][87426] Updated weights for policy 1, policy_version 36770 (0.0009) -[2023-11-28 01:10:42,356][87424] Updated weights for policy 0, policy_version 36946 (0.0011) -[2023-11-28 01:10:42,700][87426] Updated weights for policy 1, policy_version 36780 (0.0008) -[2023-11-28 01:10:42,726][87424] Updated weights for policy 0, policy_version 36956 (0.0011) -[2023-11-28 01:10:43,065][87426] Updated weights for policy 1, policy_version 36790 (0.0010) -[2023-11-28 01:10:43,440][87426] Updated weights for policy 1, policy_version 36800 (0.0010) -[2023-11-28 01:10:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 18882560. Throughput: 0: 2750.2, 1: 2697.5. Samples: 18891228. Policy #0 lag: (min: 31.0, avg: 35.8, max: 59.0) -[2023-11-28 01:10:43,445][86177] Avg episode reward: [(0, '-516.770'), (1, '-540.170')] -[2023-11-28 01:10:44,780][87424] Updated weights for policy 0, policy_version 36966 (0.0011) -[2023-11-28 01:10:45,154][87424] Updated weights for policy 0, policy_version 36976 (0.0011) -[2023-11-28 01:10:45,365][87426] Updated weights for policy 1, policy_version 36810 (0.0011) -[2023-11-28 01:10:45,539][87424] Updated weights for policy 0, policy_version 36986 (0.0012) -[2023-11-28 01:10:45,742][87426] Updated weights for policy 1, policy_version 36820 (0.0008) -[2023-11-28 01:10:46,122][87426] Updated weights for policy 1, policy_version 36830 (0.0007) -[2023-11-28 01:10:47,918][87424] Updated weights for policy 0, policy_version 36996 (0.0012) -[2023-11-28 01:10:47,994][87426] Updated weights for policy 1, policy_version 36840 (0.0007) -[2023-11-28 01:10:48,307][87424] Updated weights for policy 0, policy_version 37006 (0.0011) -[2023-11-28 01:10:48,376][87426] Updated weights for policy 1, policy_version 36850 (0.0007) -[2023-11-28 01:10:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 18898944. Throughput: 0: 2726.9, 1: 2721.3. Samples: 18915668. Policy #0 lag: (min: 31.0, avg: 35.8, max: 59.0) -[2023-11-28 01:10:48,445][86177] Avg episode reward: [(0, '-516.000'), (1, '-496.680')] -[2023-11-28 01:10:48,687][87424] Updated weights for policy 0, policy_version 37016 (0.0011) -[2023-11-28 01:10:48,757][87426] Updated weights for policy 1, policy_version 36860 (0.0007) -[2023-11-28 01:10:50,956][87424] Updated weights for policy 0, policy_version 37026 (0.0011) -[2023-11-28 01:10:51,291][87426] Updated weights for policy 1, policy_version 36870 (0.0010) -[2023-11-28 01:10:51,344][87424] Updated weights for policy 0, policy_version 37036 (0.0011) -[2023-11-28 01:10:51,660][87426] Updated weights for policy 1, policy_version 36880 (0.0011) -[2023-11-28 01:10:51,719][87424] Updated weights for policy 0, policy_version 37046 (0.0010) -[2023-11-28 01:10:52,043][87426] Updated weights for policy 1, policy_version 36890 (0.0011) -[2023-11-28 01:10:52,098][87424] Updated weights for policy 0, policy_version 37056 (0.0011) -[2023-11-28 01:10:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 18931712. Throughput: 0: 2739.1, 1: 2722.0. Samples: 18948512. Policy #0 lag: (min: 31.0, avg: 35.8, max: 59.0) -[2023-11-28 01:10:53,445][86177] Avg episode reward: [(0, '-512.030'), (1, '-525.570')] -[2023-11-28 01:10:54,180][87426] Updated weights for policy 1, policy_version 36900 (0.0011) -[2023-11-28 01:10:54,446][87424] Updated weights for policy 0, policy_version 37066 (0.0012) -[2023-11-28 01:10:54,564][87426] Updated weights for policy 1, policy_version 36910 (0.0011) -[2023-11-28 01:10:54,832][87424] Updated weights for policy 0, policy_version 37076 (0.0011) -[2023-11-28 01:10:54,941][87426] Updated weights for policy 1, policy_version 36920 (0.0011) -[2023-11-28 01:10:55,215][87424] Updated weights for policy 0, policy_version 37086 (0.0009) -[2023-11-28 01:10:56,846][87424] Updated weights for policy 0, policy_version 37096 (0.0008) -[2023-11-28 01:10:57,229][87424] Updated weights for policy 0, policy_version 37106 (0.0007) -[2023-11-28 01:10:57,538][87426] Updated weights for policy 1, policy_version 36930 (0.0012) -[2023-11-28 01:10:57,613][87424] Updated weights for policy 0, policy_version 37116 (0.0007) -[2023-11-28 01:10:57,926][87426] Updated weights for policy 1, policy_version 36940 (0.0012) -[2023-11-28 01:10:58,310][87426] Updated weights for policy 1, policy_version 36950 (0.0012) -[2023-11-28 01:10:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 18956288. Throughput: 0: 2740.9, 1: 2725.3. Samples: 18972752. Policy #0 lag: (min: 31.0, avg: 35.8, max: 59.0) -[2023-11-28 01:10:58,445][86177] Avg episode reward: [(0, '-507.450'), (1, '-558.800')] -[2023-11-28 01:10:58,685][87426] Updated weights for policy 1, policy_version 36960 (0.0012) -[2023-11-28 01:10:59,567][87424] Updated weights for policy 0, policy_version 37126 (0.0007) -[2023-11-28 01:10:59,944][87424] Updated weights for policy 0, policy_version 37136 (0.0009) -[2023-11-28 01:11:00,335][87424] Updated weights for policy 0, policy_version 37146 (0.0012) -[2023-11-28 01:11:00,757][87426] Updated weights for policy 1, policy_version 36970 (0.0008) -[2023-11-28 01:11:01,138][87426] Updated weights for policy 1, policy_version 36980 (0.0007) -[2023-11-28 01:11:01,522][87426] Updated weights for policy 1, policy_version 36990 (0.0007) -[2023-11-28 01:11:02,262][87424] Updated weights for policy 0, policy_version 37156 (0.0011) -[2023-11-28 01:11:02,646][87424] Updated weights for policy 0, policy_version 37166 (0.0011) -[2023-11-28 01:11:03,030][87424] Updated weights for policy 0, policy_version 37176 (0.0011) -[2023-11-28 01:11:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 18989056. Throughput: 0: 2775.9, 1: 2718.7. Samples: 18998984. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 01:11:03,445][86177] Avg episode reward: [(0, '-497.550'), (1, '-559.290')] -[2023-11-28 01:11:03,454][87281] Saving new best policy, reward=-497.550! -[2023-11-28 01:11:04,042][87426] Updated weights for policy 1, policy_version 37000 (0.0008) -[2023-11-28 01:11:04,439][87426] Updated weights for policy 1, policy_version 37010 (0.0008) -[2023-11-28 01:11:04,811][87426] Updated weights for policy 1, policy_version 37020 (0.0008) -[2023-11-28 01:11:05,574][87424] Updated weights for policy 0, policy_version 37186 (0.0011) -[2023-11-28 01:11:05,952][87424] Updated weights for policy 0, policy_version 37196 (0.0010) -[2023-11-28 01:11:06,340][87424] Updated weights for policy 0, policy_version 37206 (0.0007) -[2023-11-28 01:11:06,609][87426] Updated weights for policy 1, policy_version 37030 (0.0008) -[2023-11-28 01:11:06,712][87424] Updated weights for policy 0, policy_version 37216 (0.0008) -[2023-11-28 01:11:06,987][87426] Updated weights for policy 1, policy_version 37040 (0.0012) -[2023-11-28 01:11:07,372][87426] Updated weights for policy 1, policy_version 37050 (0.0012) -[2023-11-28 01:11:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 19013632. Throughput: 0: 2753.0, 1: 2700.0. Samples: 19030244. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 01:11:08,445][86177] Avg episode reward: [(0, '-499.680'), (1, '-560.740')] -[2023-11-28 01:11:08,964][87424] Updated weights for policy 0, policy_version 37226 (0.0008) -[2023-11-28 01:11:09,340][87424] Updated weights for policy 0, policy_version 37236 (0.0011) -[2023-11-28 01:11:09,447][87426] Updated weights for policy 1, policy_version 37060 (0.0011) -[2023-11-28 01:11:09,725][87424] Updated weights for policy 0, policy_version 37246 (0.0012) -[2023-11-28 01:11:09,829][87426] Updated weights for policy 1, policy_version 37070 (0.0011) -[2023-11-28 01:11:10,201][87426] Updated weights for policy 1, policy_version 37080 (0.0012) -[2023-11-28 01:11:11,752][87424] Updated weights for policy 0, policy_version 37256 (0.0012) -[2023-11-28 01:11:12,128][87424] Updated weights for policy 0, policy_version 37266 (0.0009) -[2023-11-28 01:11:12,511][87424] Updated weights for policy 0, policy_version 37276 (0.0012) -[2023-11-28 01:11:12,757][87426] Updated weights for policy 1, policy_version 37090 (0.0012) -[2023-11-28 01:11:13,142][87426] Updated weights for policy 1, policy_version 37100 (0.0012) -[2023-11-28 01:11:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 19038208. Throughput: 0: 2737.9, 1: 2696.2. Samples: 19054628. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 01:11:13,445][86177] Avg episode reward: [(0, '-503.330'), (1, '-534.730')] -[2023-11-28 01:11:13,528][87426] Updated weights for policy 1, policy_version 37110 (0.0011) -[2023-11-28 01:11:13,906][87426] Updated weights for policy 1, policy_version 37120 (0.0011) -[2023-11-28 01:11:14,903][87424] Updated weights for policy 0, policy_version 37286 (0.0012) -[2023-11-28 01:11:15,283][87424] Updated weights for policy 0, policy_version 37296 (0.0011) -[2023-11-28 01:11:15,670][87424] Updated weights for policy 0, policy_version 37306 (0.0011) -[2023-11-28 01:11:15,731][87426] Updated weights for policy 1, policy_version 37130 (0.0009) -[2023-11-28 01:11:16,118][87426] Updated weights for policy 1, policy_version 37140 (0.0011) -[2023-11-28 01:11:16,495][87426] Updated weights for policy 1, policy_version 37150 (0.0012) -[2023-11-28 01:11:17,408][87424] Updated weights for policy 0, policy_version 37316 (0.0010) -[2023-11-28 01:11:17,790][87424] Updated weights for policy 0, policy_version 37326 (0.0007) -[2023-11-28 01:11:18,174][87424] Updated weights for policy 0, policy_version 37336 (0.0008) -[2023-11-28 01:11:18,390][87426] Updated weights for policy 1, policy_version 37160 (0.0012) -[2023-11-28 01:11:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 19062784. Throughput: 0: 2735.5, 1: 2707.8. Samples: 19079880. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 01:11:18,445][86177] Avg episode reward: [(0, '-501.930'), (1, '-505.710')] -[2023-11-28 01:11:18,763][87426] Updated weights for policy 1, policy_version 37170 (0.0012) -[2023-11-28 01:11:19,143][87426] Updated weights for policy 1, policy_version 37180 (0.0012) -[2023-11-28 01:11:20,251][87424] Updated weights for policy 0, policy_version 37346 (0.0008) -[2023-11-28 01:11:20,630][87424] Updated weights for policy 0, policy_version 37356 (0.0011) -[2023-11-28 01:11:21,014][87424] Updated weights for policy 0, policy_version 37366 (0.0010) -[2023-11-28 01:11:21,272][87426] Updated weights for policy 1, policy_version 37190 (0.0012) -[2023-11-28 01:11:21,393][87424] Updated weights for policy 0, policy_version 37376 (0.0011) -[2023-11-28 01:11:21,662][87426] Updated weights for policy 1, policy_version 37200 (0.0011) -[2023-11-28 01:11:22,041][87426] Updated weights for policy 1, policy_version 37210 (0.0010) -[2023-11-28 01:11:23,226][87424] Updated weights for policy 0, policy_version 37386 (0.0010) -[2023-11-28 01:11:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 19095552. Throughput: 0: 2734.6, 1: 2736.7. Samples: 19113064. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 01:11:23,445][86177] Avg episode reward: [(0, '-502.010'), (1, '-507.220')] -[2023-11-28 01:11:23,613][87424] Updated weights for policy 0, policy_version 37396 (0.0011) -[2023-11-28 01:11:23,895][87426] Updated weights for policy 1, policy_version 37220 (0.0011) -[2023-11-28 01:11:23,999][87424] Updated weights for policy 0, policy_version 37406 (0.0010) -[2023-11-28 01:11:24,268][87426] Updated weights for policy 1, policy_version 37230 (0.0007) -[2023-11-28 01:11:24,643][87426] Updated weights for policy 1, policy_version 37240 (0.0007) -[2023-11-28 01:11:26,545][87424] Updated weights for policy 0, policy_version 37416 (0.0010) -[2023-11-28 01:11:26,925][87424] Updated weights for policy 0, policy_version 37426 (0.0011) -[2023-11-28 01:11:26,963][87426] Updated weights for policy 1, policy_version 37250 (0.0009) -[2023-11-28 01:11:27,304][87424] Updated weights for policy 0, policy_version 37436 (0.0008) -[2023-11-28 01:11:27,336][87426] Updated weights for policy 1, policy_version 37260 (0.0009) -[2023-11-28 01:11:27,716][87426] Updated weights for policy 1, policy_version 37270 (0.0008) -[2023-11-28 01:11:28,106][87426] Updated weights for policy 1, policy_version 37280 (0.0007) -[2023-11-28 01:11:28,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 19128320. Throughput: 0: 2736.3, 1: 2728.9. Samples: 19137160. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 01:11:28,445][86177] Avg episode reward: [(0, '-501.220'), (1, '-512.970')] -[2023-11-28 01:11:29,856][87424] Updated weights for policy 0, policy_version 37446 (0.0010) -[2023-11-28 01:11:30,239][87424] Updated weights for policy 0, policy_version 37456 (0.0012) -[2023-11-28 01:11:30,545][87426] Updated weights for policy 1, policy_version 37290 (0.0012) -[2023-11-28 01:11:30,619][87424] Updated weights for policy 0, policy_version 37466 (0.0009) -[2023-11-28 01:11:30,924][87426] Updated weights for policy 1, policy_version 37300 (0.0012) -[2023-11-28 01:11:31,301][87426] Updated weights for policy 1, policy_version 37310 (0.0010) -[2023-11-28 01:11:32,700][87424] Updated weights for policy 0, policy_version 37476 (0.0009) -[2023-11-28 01:11:33,073][87424] Updated weights for policy 0, policy_version 37486 (0.0010) -[2023-11-28 01:11:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 19144704. Throughput: 0: 2781.8, 1: 2709.3. Samples: 19162772. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 01:11:33,446][86177] Avg episode reward: [(0, '-498.460'), (1, '-514.090')] -[2023-11-28 01:11:33,457][87424] Updated weights for policy 0, policy_version 37496 (0.0010) -[2023-11-28 01:11:33,470][87426] Updated weights for policy 1, policy_version 37320 (0.0010) -[2023-11-28 01:11:33,842][87426] Updated weights for policy 1, policy_version 37330 (0.0011) -[2023-11-28 01:11:34,214][87426] Updated weights for policy 1, policy_version 37340 (0.0012) -[2023-11-28 01:11:35,284][87424] Updated weights for policy 0, policy_version 37506 (0.0011) -[2023-11-28 01:11:35,677][87424] Updated weights for policy 0, policy_version 37516 (0.0012) -[2023-11-28 01:11:36,055][87424] Updated weights for policy 0, policy_version 37526 (0.0012) -[2023-11-28 01:11:36,151][87426] Updated weights for policy 1, policy_version 37350 (0.0012) -[2023-11-28 01:11:36,437][87424] Updated weights for policy 0, policy_version 37536 (0.0012) -[2023-11-28 01:11:36,531][87426] Updated weights for policy 1, policy_version 37360 (0.0012) -[2023-11-28 01:11:36,922][87426] Updated weights for policy 1, policy_version 37370 (0.0012) -[2023-11-28 01:11:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 19177472. Throughput: 0: 2785.0, 1: 2710.0. Samples: 19195784. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 01:11:38,445][86177] Avg episode reward: [(0, '-499.390'), (1, '-516.500')] -[2023-11-28 01:11:38,811][87426] Updated weights for policy 1, policy_version 37380 (0.0010) -[2023-11-28 01:11:38,821][87424] Updated weights for policy 0, policy_version 37546 (0.0008) -[2023-11-28 01:11:39,189][87426] Updated weights for policy 1, policy_version 37390 (0.0008) -[2023-11-28 01:11:39,211][87424] Updated weights for policy 0, policy_version 37556 (0.0012) -[2023-11-28 01:11:39,567][87426] Updated weights for policy 1, policy_version 37400 (0.0010) -[2023-11-28 01:11:39,585][87424] Updated weights for policy 0, policy_version 37566 (0.0008) -[2023-11-28 01:11:41,552][87426] Updated weights for policy 1, policy_version 37410 (0.0008) -[2023-11-28 01:11:41,695][87424] Updated weights for policy 0, policy_version 37576 (0.0011) -[2023-11-28 01:11:41,929][87426] Updated weights for policy 1, policy_version 37420 (0.0011) -[2023-11-28 01:11:42,084][87424] Updated weights for policy 0, policy_version 37586 (0.0010) -[2023-11-28 01:11:42,307][87426] Updated weights for policy 1, policy_version 37430 (0.0010) -[2023-11-28 01:11:42,465][87424] Updated weights for policy 0, policy_version 37596 (0.0012) -[2023-11-28 01:11:42,689][87426] Updated weights for policy 1, policy_version 37440 (0.0010) -[2023-11-28 01:11:43,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 19210240. Throughput: 0: 2783.3, 1: 2733.6. Samples: 19221012. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 01:11:43,445][86177] Avg episode reward: [(0, '-539.120'), (1, '-515.760')] -[2023-11-28 01:11:44,836][87426] Updated weights for policy 1, policy_version 37450 (0.0009) -[2023-11-28 01:11:44,933][87424] Updated weights for policy 0, policy_version 37606 (0.0011) -[2023-11-28 01:11:45,224][87426] Updated weights for policy 1, policy_version 37460 (0.0012) -[2023-11-28 01:11:45,322][87424] Updated weights for policy 0, policy_version 37616 (0.0011) -[2023-11-28 01:11:45,605][87426] Updated weights for policy 1, policy_version 37470 (0.0009) -[2023-11-28 01:11:45,696][87424] Updated weights for policy 0, policy_version 37626 (0.0008) -[2023-11-28 01:11:47,537][87424] Updated weights for policy 0, policy_version 37636 (0.0010) -[2023-11-28 01:11:47,920][87424] Updated weights for policy 0, policy_version 37646 (0.0009) -[2023-11-28 01:11:48,070][87426] Updated weights for policy 1, policy_version 37480 (0.0008) -[2023-11-28 01:11:48,304][87424] Updated weights for policy 0, policy_version 37656 (0.0008) -[2023-11-28 01:11:48,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 19226624. Throughput: 0: 2731.9, 1: 2723.9. Samples: 19244496. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 01:11:48,446][86177] Avg episode reward: [(0, '-538.770'), (1, '-507.560')] -[2023-11-28 01:11:48,455][87426] Updated weights for policy 1, policy_version 37490 (0.0009) -[2023-11-28 01:11:48,839][87426] Updated weights for policy 1, policy_version 37500 (0.0011) -[2023-11-28 01:11:50,392][87424] Updated weights for policy 0, policy_version 37666 (0.0009) -[2023-11-28 01:11:50,777][87424] Updated weights for policy 0, policy_version 37676 (0.0012) -[2023-11-28 01:11:50,986][87426] Updated weights for policy 1, policy_version 37510 (0.0012) -[2023-11-28 01:11:51,149][87424] Updated weights for policy 0, policy_version 37686 (0.0011) -[2023-11-28 01:11:51,367][87426] Updated weights for policy 1, policy_version 37520 (0.0011) -[2023-11-28 01:11:51,531][87424] Updated weights for policy 0, policy_version 37696 (0.0011) -[2023-11-28 01:11:51,750][87426] Updated weights for policy 1, policy_version 37530 (0.0012) -[2023-11-28 01:11:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 19259392. Throughput: 0: 2746.9, 1: 2739.6. Samples: 19277132. Policy #0 lag: (min: 31.0, avg: 45.2, max: 63.0) -[2023-11-28 01:11:53,445][86177] Avg episode reward: [(0, '-547.410'), (1, '-507.890')] -[2023-11-28 01:11:53,942][87424] Updated weights for policy 0, policy_version 37706 (0.0009) -[2023-11-28 01:11:54,061][87426] Updated weights for policy 1, policy_version 37540 (0.0012) -[2023-11-28 01:11:54,329][87424] Updated weights for policy 0, policy_version 37716 (0.0008) -[2023-11-28 01:11:54,441][87426] Updated weights for policy 1, policy_version 37550 (0.0010) -[2023-11-28 01:11:54,709][87424] Updated weights for policy 0, policy_version 37726 (0.0008) -[2023-11-28 01:11:54,817][87426] Updated weights for policy 1, policy_version 37560 (0.0009) -[2023-11-28 01:11:56,674][87424] Updated weights for policy 0, policy_version 37736 (0.0009) -[2023-11-28 01:11:57,056][87426] Updated weights for policy 1, policy_version 37570 (0.0009) -[2023-11-28 01:11:57,061][87424] Updated weights for policy 0, policy_version 37746 (0.0008) -[2023-11-28 01:11:57,435][87426] Updated weights for policy 1, policy_version 37580 (0.0010) -[2023-11-28 01:11:57,444][87424] Updated weights for policy 0, policy_version 37756 (0.0007) -[2023-11-28 01:11:57,803][87426] Updated weights for policy 1, policy_version 37590 (0.0009) -[2023-11-28 01:11:58,185][87426] Updated weights for policy 1, policy_version 37600 (0.0008) -[2023-11-28 01:11:58,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 19292160. Throughput: 0: 2761.2, 1: 2731.3. Samples: 19301788. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-11-28 01:11:58,445][86177] Avg episode reward: [(0, '-552.020'), (1, '-502.660')] -[2023-11-28 01:11:58,966][87424] Updated weights for policy 0, policy_version 37766 (0.0008) -[2023-11-28 01:11:59,354][87424] Updated weights for policy 0, policy_version 37776 (0.0008) -[2023-11-28 01:11:59,737][87424] Updated weights for policy 0, policy_version 37786 (0.0007) -[2023-11-28 01:12:00,285][87426] Updated weights for policy 1, policy_version 37610 (0.0010) -[2023-11-28 01:12:00,666][87426] Updated weights for policy 1, policy_version 37620 (0.0011) -[2023-11-28 01:12:01,042][87426] Updated weights for policy 1, policy_version 37630 (0.0010) -[2023-11-28 01:12:01,631][87424] Updated weights for policy 0, policy_version 37796 (0.0009) -[2023-11-28 01:12:02,008][87424] Updated weights for policy 0, policy_version 37806 (0.0010) -[2023-11-28 01:12:02,393][87424] Updated weights for policy 0, policy_version 37816 (0.0008) -[2023-11-28 01:12:03,412][87426] Updated weights for policy 1, policy_version 37640 (0.0011) -[2023-11-28 01:12:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 19316736. Throughput: 0: 2781.7, 1: 2725.7. Samples: 19327712. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-11-28 01:12:03,445][86177] Avg episode reward: [(0, '-514.480'), (1, '-501.250')] -[2023-11-28 01:12:03,796][87426] Updated weights for policy 1, policy_version 37650 (0.0012) -[2023-11-28 01:12:04,169][87426] Updated weights for policy 1, policy_version 37660 (0.0012) -[2023-11-28 01:12:04,428][87424] Updated weights for policy 0, policy_version 37826 (0.0009) -[2023-11-28 01:12:04,801][87424] Updated weights for policy 0, policy_version 37836 (0.0012) -[2023-11-28 01:12:05,182][87424] Updated weights for policy 0, policy_version 37846 (0.0012) -[2023-11-28 01:12:05,566][87424] Updated weights for policy 0, policy_version 37856 (0.0012) -[2023-11-28 01:12:06,615][87426] Updated weights for policy 1, policy_version 37670 (0.0010) -[2023-11-28 01:12:06,990][87426] Updated weights for policy 1, policy_version 37680 (0.0009) -[2023-11-28 01:12:07,368][87426] Updated weights for policy 1, policy_version 37690 (0.0010) -[2023-11-28 01:12:07,912][87424] Updated weights for policy 0, policy_version 37866 (0.0012) -[2023-11-28 01:12:08,299][87424] Updated weights for policy 0, policy_version 37876 (0.0012) -[2023-11-28 01:12:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 19341312. Throughput: 0: 2787.2, 1: 2714.0. Samples: 19360620. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-11-28 01:12:08,445][86177] Avg episode reward: [(0, '-529.700'), (1, '-504.160')] -[2023-11-28 01:12:08,681][87424] Updated weights for policy 0, policy_version 37886 (0.0012) -[2023-11-28 01:12:09,369][87426] Updated weights for policy 1, policy_version 37700 (0.0009) -[2023-11-28 01:12:09,744][87426] Updated weights for policy 1, policy_version 37710 (0.0011) -[2023-11-28 01:12:10,119][87426] Updated weights for policy 1, policy_version 37720 (0.0012) -[2023-11-28 01:12:10,543][87424] Updated weights for policy 0, policy_version 37896 (0.0009) -[2023-11-28 01:12:10,924][87424] Updated weights for policy 0, policy_version 37906 (0.0009) -[2023-11-28 01:12:11,319][87424] Updated weights for policy 0, policy_version 37916 (0.0009) -[2023-11-28 01:12:12,746][87426] Updated weights for policy 1, policy_version 37730 (0.0012) -[2023-11-28 01:12:13,134][87426] Updated weights for policy 1, policy_version 37740 (0.0012) -[2023-11-28 01:12:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 19365888. Throughput: 0: 2790.7, 1: 2720.0. Samples: 19385140. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-11-28 01:12:13,445][86177] Avg episode reward: [(0, '-526.040'), (1, '-504.270')] -[2023-11-28 01:12:13,503][87426] Updated weights for policy 1, policy_version 37750 (0.0011) -[2023-11-28 01:12:13,634][87424] Updated weights for policy 0, policy_version 37926 (0.0011) -[2023-11-28 01:12:13,882][87426] Updated weights for policy 1, policy_version 37760 (0.0011) -[2023-11-28 01:12:14,015][87424] Updated weights for policy 0, policy_version 37936 (0.0012) -[2023-11-28 01:12:14,389][87424] Updated weights for policy 0, policy_version 37946 (0.0012) -[2023-11-28 01:12:15,608][87426] Updated weights for policy 1, policy_version 37770 (0.0012) -[2023-11-28 01:12:15,985][87426] Updated weights for policy 1, policy_version 37780 (0.0012) -[2023-11-28 01:12:16,374][87426] Updated weights for policy 1, policy_version 37790 (0.0012) -[2023-11-28 01:12:16,726][87424] Updated weights for policy 0, policy_version 37956 (0.0012) -[2023-11-28 01:12:17,112][87424] Updated weights for policy 0, policy_version 37966 (0.0011) -[2023-11-28 01:12:17,489][87424] Updated weights for policy 0, policy_version 37976 (0.0012) -[2023-11-28 01:12:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 19398656. Throughput: 0: 2748.5, 1: 2733.3. Samples: 19409456. Policy #0 lag: (min: 7.0, avg: 14.4, max: 39.0) -[2023-11-28 01:12:18,445][86177] Avg episode reward: [(0, '-541.750'), (1, '-507.310')] -[2023-11-28 01:12:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000037984_9723904.pth... -[2023-11-28 01:12:18,487][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000035424_9068544.pth -[2023-11-28 01:12:18,491][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000037984_9723904.pth -[2023-11-28 01:12:18,685][87426] Updated weights for policy 1, policy_version 37800 (0.0009) -[2023-11-28 01:12:19,065][87426] Updated weights for policy 1, policy_version 37810 (0.0009) -[2023-11-28 01:12:19,193][87424] Updated weights for policy 0, policy_version 37986 (0.0011) -[2023-11-28 01:12:19,445][87426] Updated weights for policy 1, policy_version 37820 (0.0008) -[2023-11-28 01:12:19,576][87424] Updated weights for policy 0, policy_version 37996 (0.0012) -[2023-11-28 01:12:19,597][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000037824_9682944.pth... -[2023-11-28 01:12:19,644][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000035264_9027584.pth -[2023-11-28 01:12:19,651][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000037824_9682944.pth -[2023-11-28 01:12:19,971][87424] Updated weights for policy 0, policy_version 38006 (0.0012) -[2023-11-28 01:12:20,354][87424] Updated weights for policy 0, policy_version 38016 (0.0012) -[2023-11-28 01:12:21,529][87426] Updated weights for policy 1, policy_version 37830 (0.0009) -[2023-11-28 01:12:21,902][87426] Updated weights for policy 1, policy_version 37840 (0.0012) -[2023-11-28 01:12:22,275][87426] Updated weights for policy 1, policy_version 37850 (0.0012) -[2023-11-28 01:12:22,958][87424] Updated weights for policy 0, policy_version 38026 (0.0012) -[2023-11-28 01:12:23,351][87424] Updated weights for policy 0, policy_version 38036 (0.0012) -[2023-11-28 01:12:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 19423232. Throughput: 0: 2740.1, 1: 2738.8. Samples: 19442332. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 01:12:23,445][86177] Avg episode reward: [(0, '-545.810'), (1, '-506.750')] -[2023-11-28 01:12:23,740][87424] Updated weights for policy 0, policy_version 38046 (0.0012) -[2023-11-28 01:12:24,192][87426] Updated weights for policy 1, policy_version 37860 (0.0010) -[2023-11-28 01:12:24,576][87426] Updated weights for policy 1, policy_version 37870 (0.0008) -[2023-11-28 01:12:24,951][87426] Updated weights for policy 1, policy_version 37880 (0.0008) -[2023-11-28 01:12:25,614][87424] Updated weights for policy 0, policy_version 38056 (0.0011) -[2023-11-28 01:12:26,009][87424] Updated weights for policy 0, policy_version 38066 (0.0011) -[2023-11-28 01:12:26,385][87424] Updated weights for policy 0, policy_version 38076 (0.0012) -[2023-11-28 01:12:27,357][87426] Updated weights for policy 1, policy_version 37890 (0.0008) -[2023-11-28 01:12:27,745][87426] Updated weights for policy 1, policy_version 37900 (0.0010) -[2023-11-28 01:12:28,132][87426] Updated weights for policy 1, policy_version 37910 (0.0011) -[2023-11-28 01:12:28,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 19447808. Throughput: 0: 2737.8, 1: 2733.1. Samples: 19467208. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 01:12:28,446][86177] Avg episode reward: [(0, '-544.450'), (1, '-502.540')] -[2023-11-28 01:12:28,508][87426] Updated weights for policy 1, policy_version 37920 (0.0012) -[2023-11-28 01:12:28,788][87424] Updated weights for policy 0, policy_version 38086 (0.0012) -[2023-11-28 01:12:29,175][87424] Updated weights for policy 0, policy_version 38096 (0.0012) -[2023-11-28 01:12:29,564][87424] Updated weights for policy 0, policy_version 38106 (0.0010) -[2023-11-28 01:12:30,585][87426] Updated weights for policy 1, policy_version 37930 (0.0011) -[2023-11-28 01:12:30,951][87426] Updated weights for policy 1, policy_version 37940 (0.0012) -[2023-11-28 01:12:31,331][87426] Updated weights for policy 1, policy_version 37950 (0.0012) -[2023-11-28 01:12:31,820][87424] Updated weights for policy 0, policy_version 38116 (0.0009) -[2023-11-28 01:12:32,207][87424] Updated weights for policy 0, policy_version 38126 (0.0009) -[2023-11-28 01:12:32,581][87424] Updated weights for policy 0, policy_version 38136 (0.0009) -[2023-11-28 01:12:33,423][87426] Updated weights for policy 1, policy_version 37960 (0.0010) -[2023-11-28 01:12:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 19480576. Throughput: 0: 2772.8, 1: 2739.7. Samples: 19492556. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 01:12:33,445][86177] Avg episode reward: [(0, '-546.400'), (1, '-504.550')] -[2023-11-28 01:12:33,814][87426] Updated weights for policy 1, policy_version 37970 (0.0011) -[2023-11-28 01:12:34,185][87426] Updated weights for policy 1, policy_version 37980 (0.0012) -[2023-11-28 01:12:34,780][87424] Updated weights for policy 0, policy_version 38146 (0.0009) -[2023-11-28 01:12:35,162][87424] Updated weights for policy 0, policy_version 38156 (0.0012) -[2023-11-28 01:12:35,542][87424] Updated weights for policy 0, policy_version 38166 (0.0012) -[2023-11-28 01:12:35,922][87424] Updated weights for policy 0, policy_version 38176 (0.0009) -[2023-11-28 01:12:36,672][87426] Updated weights for policy 1, policy_version 37990 (0.0012) -[2023-11-28 01:12:37,053][87426] Updated weights for policy 1, policy_version 38000 (0.0011) -[2023-11-28 01:12:37,433][87426] Updated weights for policy 1, policy_version 38010 (0.0011) -[2023-11-28 01:12:38,138][87424] Updated weights for policy 0, policy_version 38186 (0.0007) -[2023-11-28 01:12:38,444][86177] Fps is (10 sec: 5734.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 19505152. Throughput: 0: 2779.3, 1: 2724.8. Samples: 19524816. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 01:12:38,445][86177] Avg episode reward: [(0, '-539.990'), (1, '-500.200')] -[2023-11-28 01:12:38,521][87424] Updated weights for policy 0, policy_version 38196 (0.0008) -[2023-11-28 01:12:38,903][87424] Updated weights for policy 0, policy_version 38206 (0.0008) -[2023-11-28 01:12:39,765][87426] Updated weights for policy 1, policy_version 38020 (0.0009) -[2023-11-28 01:12:40,147][87426] Updated weights for policy 1, policy_version 38030 (0.0012) -[2023-11-28 01:12:40,532][87426] Updated weights for policy 1, policy_version 38040 (0.0010) -[2023-11-28 01:12:41,376][87424] Updated weights for policy 0, policy_version 38216 (0.0011) -[2023-11-28 01:12:41,749][87424] Updated weights for policy 0, policy_version 38226 (0.0009) -[2023-11-28 01:12:42,129][87424] Updated weights for policy 0, policy_version 38236 (0.0011) -[2023-11-28 01:12:42,650][87426] Updated weights for policy 1, policy_version 38050 (0.0008) -[2023-11-28 01:12:43,019][87426] Updated weights for policy 1, policy_version 38060 (0.0010) -[2023-11-28 01:12:43,405][87426] Updated weights for policy 1, policy_version 38070 (0.0011) -[2023-11-28 01:12:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 19529728. Throughput: 0: 2755.8, 1: 2738.0. Samples: 19549012. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 01:12:43,445][86177] Avg episode reward: [(0, '-539.820'), (1, '-505.830')] -[2023-11-28 01:12:43,778][87426] Updated weights for policy 1, policy_version 38080 (0.0009) -[2023-11-28 01:12:44,370][87424] Updated weights for policy 0, policy_version 38246 (0.0011) -[2023-11-28 01:12:44,755][87424] Updated weights for policy 0, policy_version 38256 (0.0008) -[2023-11-28 01:12:45,145][87424] Updated weights for policy 0, policy_version 38266 (0.0009) -[2023-11-28 01:12:45,808][87426] Updated weights for policy 1, policy_version 38090 (0.0010) -[2023-11-28 01:12:46,183][87426] Updated weights for policy 1, policy_version 38100 (0.0011) -[2023-11-28 01:12:46,554][87426] Updated weights for policy 1, policy_version 38110 (0.0012) -[2023-11-28 01:12:47,127][87424] Updated weights for policy 0, policy_version 38276 (0.0009) -[2023-11-28 01:12:47,515][87424] Updated weights for policy 0, policy_version 38286 (0.0007) -[2023-11-28 01:12:47,889][87424] Updated weights for policy 0, policy_version 38296 (0.0007) -[2023-11-28 01:12:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.9). Total num frames: 19562496. Throughput: 0: 2717.4, 1: 2735.6. Samples: 19573100. Policy #0 lag: (min: 31.0, avg: 50.8, max: 73.0) -[2023-11-28 01:12:48,445][86177] Avg episode reward: [(0, '-534.830'), (1, '-507.220')] -[2023-11-28 01:12:48,577][87426] Updated weights for policy 1, policy_version 38120 (0.0012) -[2023-11-28 01:12:48,953][87426] Updated weights for policy 1, policy_version 38130 (0.0012) -[2023-11-28 01:12:49,336][87426] Updated weights for policy 1, policy_version 38140 (0.0010) -[2023-11-28 01:12:50,156][87424] Updated weights for policy 0, policy_version 38306 (0.0015) -[2023-11-28 01:12:50,529][87424] Updated weights for policy 0, policy_version 38316 (0.0014) -[2023-11-28 01:12:50,911][87424] Updated weights for policy 0, policy_version 38326 (0.0009) -[2023-11-28 01:12:51,294][87424] Updated weights for policy 0, policy_version 38336 (0.0010) -[2023-11-28 01:12:51,445][87426] Updated weights for policy 1, policy_version 38150 (0.0009) -[2023-11-28 01:12:51,823][87426] Updated weights for policy 1, policy_version 38160 (0.0012) -[2023-11-28 01:12:52,200][87426] Updated weights for policy 1, policy_version 38170 (0.0010) -[2023-11-28 01:12:53,430][87424] Updated weights for policy 0, policy_version 38346 (0.0012) -[2023-11-28 01:12:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 19587072. Throughput: 0: 2698.9, 1: 2743.7. Samples: 19605536. Policy #0 lag: (min: 31.0, avg: 50.8, max: 73.0) -[2023-11-28 01:12:53,445][86177] Avg episode reward: [(0, '-531.240'), (1, '-503.150')] -[2023-11-28 01:12:53,809][87424] Updated weights for policy 0, policy_version 38356 (0.0010) -[2023-11-28 01:12:54,191][87424] Updated weights for policy 0, policy_version 38366 (0.0007) -[2023-11-28 01:12:54,527][87426] Updated weights for policy 1, policy_version 38180 (0.0012) -[2023-11-28 01:12:54,906][87426] Updated weights for policy 1, policy_version 38190 (0.0010) -[2023-11-28 01:12:55,285][87426] Updated weights for policy 1, policy_version 38200 (0.0007) -[2023-11-28 01:12:56,209][87424] Updated weights for policy 0, policy_version 38376 (0.0011) -[2023-11-28 01:12:56,598][87424] Updated weights for policy 0, policy_version 38386 (0.0012) -[2023-11-28 01:12:56,971][87424] Updated weights for policy 0, policy_version 38396 (0.0012) -[2023-11-28 01:12:57,185][87426] Updated weights for policy 1, policy_version 38210 (0.0008) -[2023-11-28 01:12:57,584][87426] Updated weights for policy 1, policy_version 38220 (0.0012) -[2023-11-28 01:12:57,959][87426] Updated weights for policy 1, policy_version 38230 (0.0012) -[2023-11-28 01:12:58,324][87426] Updated weights for policy 1, policy_version 38240 (0.0012) -[2023-11-28 01:12:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 19619840. Throughput: 0: 2690.0, 1: 2760.8. Samples: 19630424. Policy #0 lag: (min: 31.0, avg: 50.8, max: 73.0) -[2023-11-28 01:12:58,445][86177] Avg episode reward: [(0, '-539.780'), (1, '-499.340')] -[2023-11-28 01:12:59,297][87424] Updated weights for policy 0, policy_version 38406 (0.0012) -[2023-11-28 01:12:59,683][87424] Updated weights for policy 0, policy_version 38416 (0.0012) -[2023-11-28 01:13:00,059][87424] Updated weights for policy 0, policy_version 38426 (0.0011) -[2023-11-28 01:13:00,306][87426] Updated weights for policy 1, policy_version 38250 (0.0008) -[2023-11-28 01:13:00,679][87426] Updated weights for policy 1, policy_version 38260 (0.0010) -[2023-11-28 01:13:01,057][87426] Updated weights for policy 1, policy_version 38270 (0.0009) -[2023-11-28 01:13:02,441][87424] Updated weights for policy 0, policy_version 38436 (0.0008) -[2023-11-28 01:13:02,823][87424] Updated weights for policy 0, policy_version 38446 (0.0008) -[2023-11-28 01:13:03,206][87424] Updated weights for policy 0, policy_version 38456 (0.0010) -[2023-11-28 01:13:03,322][87426] Updated weights for policy 1, policy_version 38280 (0.0009) -[2023-11-28 01:13:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 19636224. Throughput: 0: 2687.6, 1: 2751.7. Samples: 19654224. Policy #0 lag: (min: 31.0, avg: 50.8, max: 73.0) -[2023-11-28 01:13:03,445][86177] Avg episode reward: [(0, '-543.120'), (1, '-498.250')] -[2023-11-28 01:13:03,702][87426] Updated weights for policy 1, policy_version 38290 (0.0007) -[2023-11-28 01:13:04,082][87426] Updated weights for policy 1, policy_version 38300 (0.0007) -[2023-11-28 01:13:05,336][87424] Updated weights for policy 0, policy_version 38466 (0.0012) -[2023-11-28 01:13:05,712][87424] Updated weights for policy 0, policy_version 38476 (0.0012) -[2023-11-28 01:13:05,962][87426] Updated weights for policy 1, policy_version 38310 (0.0007) -[2023-11-28 01:13:06,097][87424] Updated weights for policy 0, policy_version 38486 (0.0011) -[2023-11-28 01:13:06,334][87426] Updated weights for policy 1, policy_version 38320 (0.0012) -[2023-11-28 01:13:06,480][87424] Updated weights for policy 0, policy_version 38496 (0.0011) -[2023-11-28 01:13:06,723][87426] Updated weights for policy 1, policy_version 38330 (0.0012) -[2023-11-28 01:13:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 19668992. Throughput: 0: 2689.5, 1: 2731.6. Samples: 19686284. Policy #0 lag: (min: 31.0, avg: 50.8, max: 73.0) -[2023-11-28 01:13:08,445][86177] Avg episode reward: [(0, '-559.320'), (1, '-511.820')] -[2023-11-28 01:13:08,748][87426] Updated weights for policy 1, policy_version 38340 (0.0010) -[2023-11-28 01:13:08,910][87424] Updated weights for policy 0, policy_version 38506 (0.0012) -[2023-11-28 01:13:09,128][87426] Updated weights for policy 1, policy_version 38350 (0.0010) -[2023-11-28 01:13:09,296][87424] Updated weights for policy 0, policy_version 38516 (0.0011) -[2023-11-28 01:13:09,521][87426] Updated weights for policy 1, policy_version 38360 (0.0011) -[2023-11-28 01:13:09,681][87424] Updated weights for policy 0, policy_version 38526 (0.0010) -[2023-11-28 01:13:11,787][87426] Updated weights for policy 1, policy_version 38370 (0.0009) -[2023-11-28 01:13:12,058][87424] Updated weights for policy 0, policy_version 38536 (0.0010) -[2023-11-28 01:13:12,163][87426] Updated weights for policy 1, policy_version 38380 (0.0018) -[2023-11-28 01:13:12,434][87424] Updated weights for policy 0, policy_version 38546 (0.0010) -[2023-11-28 01:13:12,539][87426] Updated weights for policy 1, policy_version 38390 (0.0010) -[2023-11-28 01:13:12,819][87424] Updated weights for policy 0, policy_version 38556 (0.0008) -[2023-11-28 01:13:12,921][87426] Updated weights for policy 1, policy_version 38400 (0.0011) -[2023-11-28 01:13:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 19701760. Throughput: 0: 2677.8, 1: 2718.2. Samples: 19710028. Policy #0 lag: (min: 31.0, avg: 50.8, max: 73.0) -[2023-11-28 01:13:13,445][86177] Avg episode reward: [(0, '-550.460'), (1, '-524.290')] -[2023-11-28 01:13:15,188][87424] Updated weights for policy 0, policy_version 38566 (0.0008) -[2023-11-28 01:13:15,284][87426] Updated weights for policy 1, policy_version 38410 (0.0010) -[2023-11-28 01:13:15,570][87424] Updated weights for policy 0, policy_version 38576 (0.0008) -[2023-11-28 01:13:15,656][87426] Updated weights for policy 1, policy_version 38420 (0.0008) -[2023-11-28 01:13:15,952][87424] Updated weights for policy 0, policy_version 38586 (0.0008) -[2023-11-28 01:13:16,040][87426] Updated weights for policy 1, policy_version 38430 (0.0008) -[2023-11-28 01:13:17,728][87424] Updated weights for policy 0, policy_version 38596 (0.0008) -[2023-11-28 01:13:18,009][87426] Updated weights for policy 1, policy_version 38440 (0.0010) -[2023-11-28 01:13:18,114][87424] Updated weights for policy 0, policy_version 38606 (0.0007) -[2023-11-28 01:13:18,390][87426] Updated weights for policy 1, policy_version 38450 (0.0011) -[2023-11-28 01:13:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 19718144. Throughput: 0: 2645.5, 1: 2733.2. Samples: 19734600. Policy #0 lag: (min: 22.0, avg: 46.0, max: 86.0) -[2023-11-28 01:13:18,445][86177] Avg episode reward: [(0, '-571.010'), (1, '-530.610')] -[2023-11-28 01:13:18,498][87424] Updated weights for policy 0, policy_version 38616 (0.0008) -[2023-11-28 01:13:18,763][87426] Updated weights for policy 1, policy_version 38460 (0.0011) -[2023-11-28 01:13:20,807][87424] Updated weights for policy 0, policy_version 38626 (0.0007) -[2023-11-28 01:13:21,197][87424] Updated weights for policy 0, policy_version 38636 (0.0010) -[2023-11-28 01:13:21,287][87426] Updated weights for policy 1, policy_version 38470 (0.0011) -[2023-11-28 01:13:21,589][87424] Updated weights for policy 0, policy_version 38646 (0.0011) -[2023-11-28 01:13:21,661][87426] Updated weights for policy 1, policy_version 38480 (0.0012) -[2023-11-28 01:13:21,968][87424] Updated weights for policy 0, policy_version 38656 (0.0010) -[2023-11-28 01:13:22,037][87426] Updated weights for policy 1, policy_version 38490 (0.0011) -[2023-11-28 01:13:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 19750912. Throughput: 0: 2628.3, 1: 2742.9. Samples: 19766520. Policy #0 lag: (min: 22.0, avg: 46.0, max: 86.0) -[2023-11-28 01:13:23,445][86177] Avg episode reward: [(0, '-563.150'), (1, '-528.410')] -[2023-11-28 01:13:24,159][87426] Updated weights for policy 1, policy_version 38500 (0.0011) -[2023-11-28 01:13:24,516][87424] Updated weights for policy 0, policy_version 38666 (0.0010) -[2023-11-28 01:13:24,541][87426] Updated weights for policy 1, policy_version 38510 (0.0011) -[2023-11-28 01:13:24,898][87424] Updated weights for policy 0, policy_version 38676 (0.0007) -[2023-11-28 01:13:24,930][87426] Updated weights for policy 1, policy_version 38520 (0.0011) -[2023-11-28 01:13:25,288][87424] Updated weights for policy 0, policy_version 38686 (0.0007) -[2023-11-28 01:13:26,552][87426] Updated weights for policy 1, policy_version 38530 (0.0012) -[2023-11-28 01:13:26,935][87426] Updated weights for policy 1, policy_version 38540 (0.0010) -[2023-11-28 01:13:27,303][87426] Updated weights for policy 1, policy_version 38550 (0.0009) -[2023-11-28 01:13:27,529][87424] Updated weights for policy 0, policy_version 38696 (0.0009) -[2023-11-28 01:13:27,684][87426] Updated weights for policy 1, policy_version 38560 (0.0010) -[2023-11-28 01:13:27,912][87424] Updated weights for policy 0, policy_version 38706 (0.0010) -[2023-11-28 01:13:28,301][87424] Updated weights for policy 0, policy_version 38716 (0.0009) -[2023-11-28 01:13:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 19775488. Throughput: 0: 2631.3, 1: 2758.4. Samples: 19791548. Policy #0 lag: (min: 22.0, avg: 46.0, max: 86.0) -[2023-11-28 01:13:28,445][86177] Avg episode reward: [(0, '-545.140'), (1, '-507.650')] -[2023-11-28 01:13:29,845][87426] Updated weights for policy 1, policy_version 38570 (0.0012) -[2023-11-28 01:13:30,226][87426] Updated weights for policy 1, policy_version 38580 (0.0009) -[2023-11-28 01:13:30,602][87426] Updated weights for policy 1, policy_version 38590 (0.0010) -[2023-11-28 01:13:30,850][87424] Updated weights for policy 0, policy_version 38726 (0.0011) -[2023-11-28 01:13:31,239][87424] Updated weights for policy 0, policy_version 38736 (0.0012) -[2023-11-28 01:13:31,626][87424] Updated weights for policy 0, policy_version 38746 (0.0008) -[2023-11-28 01:13:32,782][87426] Updated weights for policy 1, policy_version 38600 (0.0011) -[2023-11-28 01:13:33,152][87426] Updated weights for policy 1, policy_version 38610 (0.0011) -[2023-11-28 01:13:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 19800064. Throughput: 0: 2621.4, 1: 2766.6. Samples: 19815560. Policy #0 lag: (min: 22.0, avg: 46.0, max: 86.0) -[2023-11-28 01:13:33,445][86177] Avg episode reward: [(0, '-541.190'), (1, '-507.070')] -[2023-11-28 01:13:33,542][87426] Updated weights for policy 1, policy_version 38620 (0.0011) -[2023-11-28 01:13:34,113][87424] Updated weights for policy 0, policy_version 38756 (0.0011) -[2023-11-28 01:13:34,494][87424] Updated weights for policy 0, policy_version 38766 (0.0012) -[2023-11-28 01:13:34,886][87424] Updated weights for policy 0, policy_version 38776 (0.0011) -[2023-11-28 01:13:35,275][87426] Updated weights for policy 1, policy_version 38630 (0.0010) -[2023-11-28 01:13:35,649][87426] Updated weights for policy 1, policy_version 38640 (0.0009) -[2023-11-28 01:13:36,021][87426] Updated weights for policy 1, policy_version 38650 (0.0011) -[2023-11-28 01:13:36,731][87424] Updated weights for policy 0, policy_version 38786 (0.0011) -[2023-11-28 01:13:37,122][87424] Updated weights for policy 0, policy_version 38796 (0.0012) -[2023-11-28 01:13:37,499][87424] Updated weights for policy 0, policy_version 38806 (0.0012) -[2023-11-28 01:13:37,877][87424] Updated weights for policy 0, policy_version 38816 (0.0011) -[2023-11-28 01:13:38,409][87426] Updated weights for policy 1, policy_version 38660 (0.0011) -[2023-11-28 01:13:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 19832832. Throughput: 0: 2614.5, 1: 2793.9. Samples: 19848916. Policy #0 lag: (min: 22.0, avg: 46.0, max: 86.0) -[2023-11-28 01:13:38,445][86177] Avg episode reward: [(0, '-518.600'), (1, '-510.350')] -[2023-11-28 01:13:38,783][87426] Updated weights for policy 1, policy_version 38670 (0.0012) -[2023-11-28 01:13:39,163][87426] Updated weights for policy 1, policy_version 38680 (0.0012) -[2023-11-28 01:13:40,011][87424] Updated weights for policy 0, policy_version 38826 (0.0011) -[2023-11-28 01:13:40,402][87424] Updated weights for policy 0, policy_version 38836 (0.0008) -[2023-11-28 01:13:40,790][87424] Updated weights for policy 0, policy_version 38846 (0.0011) -[2023-11-28 01:13:41,542][87426] Updated weights for policy 1, policy_version 38690 (0.0012) -[2023-11-28 01:13:41,935][87426] Updated weights for policy 1, policy_version 38700 (0.0010) -[2023-11-28 01:13:42,304][87426] Updated weights for policy 1, policy_version 38710 (0.0011) -[2023-11-28 01:13:42,686][87426] Updated weights for policy 1, policy_version 38720 (0.0008) -[2023-11-28 01:13:43,300][87424] Updated weights for policy 0, policy_version 38856 (0.0009) -[2023-11-28 01:13:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 19857408. Throughput: 0: 2619.5, 1: 2758.4. Samples: 19872428. Policy #0 lag: (min: 22.0, avg: 46.0, max: 86.0) -[2023-11-28 01:13:43,445][86177] Avg episode reward: [(0, '-519.410'), (1, '-517.680')] -[2023-11-28 01:13:43,687][87424] Updated weights for policy 0, policy_version 38866 (0.0007) -[2023-11-28 01:13:44,067][87424] Updated weights for policy 0, policy_version 38876 (0.0007) -[2023-11-28 01:13:45,184][87426] Updated weights for policy 1, policy_version 38730 (0.0012) -[2023-11-28 01:13:45,561][87426] Updated weights for policy 1, policy_version 38740 (0.0012) -[2023-11-28 01:13:45,944][87426] Updated weights for policy 1, policy_version 38750 (0.0011) -[2023-11-28 01:13:46,427][87424] Updated weights for policy 0, policy_version 38886 (0.0009) -[2023-11-28 01:13:46,794][87424] Updated weights for policy 0, policy_version 38896 (0.0008) -[2023-11-28 01:13:47,174][87424] Updated weights for policy 0, policy_version 38906 (0.0007) -[2023-11-28 01:13:47,690][87426] Updated weights for policy 1, policy_version 38760 (0.0008) -[2023-11-28 01:13:48,074][87426] Updated weights for policy 1, policy_version 38770 (0.0007) -[2023-11-28 01:13:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 19881984. Throughput: 0: 2625.3, 1: 2755.8. Samples: 19896376. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:13:48,445][86177] Avg episode reward: [(0, '-527.740'), (1, '-542.990')] -[2023-11-28 01:13:48,466][87426] Updated weights for policy 1, policy_version 38780 (0.0010) -[2023-11-28 01:13:49,328][87424] Updated weights for policy 0, policy_version 38916 (0.0009) -[2023-11-28 01:13:49,721][87424] Updated weights for policy 0, policy_version 38926 (0.0012) -[2023-11-28 01:13:50,091][87424] Updated weights for policy 0, policy_version 38936 (0.0012) -[2023-11-28 01:13:50,774][87426] Updated weights for policy 1, policy_version 38790 (0.0010) -[2023-11-28 01:13:51,154][87426] Updated weights for policy 1, policy_version 38800 (0.0008) -[2023-11-28 01:13:51,535][87426] Updated weights for policy 1, policy_version 38810 (0.0008) -[2023-11-28 01:13:52,668][87424] Updated weights for policy 0, policy_version 38946 (0.0012) -[2023-11-28 01:13:53,044][87424] Updated weights for policy 0, policy_version 38956 (0.0011) -[2023-11-28 01:13:53,432][87424] Updated weights for policy 0, policy_version 38966 (0.0011) -[2023-11-28 01:13:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 19906560. Throughput: 0: 2619.7, 1: 2766.1. Samples: 19928648. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:13:53,445][86177] Avg episode reward: [(0, '-527.280'), (1, '-555.580')] -[2023-11-28 01:13:53,734][87426] Updated weights for policy 1, policy_version 38820 (0.0010) -[2023-11-28 01:13:53,817][87424] Updated weights for policy 0, policy_version 38976 (0.0012) -[2023-11-28 01:13:54,112][87426] Updated weights for policy 1, policy_version 38830 (0.0008) -[2023-11-28 01:13:54,495][87426] Updated weights for policy 1, policy_version 38840 (0.0007) -[2023-11-28 01:13:55,753][87424] Updated weights for policy 0, policy_version 38986 (0.0008) -[2023-11-28 01:13:56,141][87424] Updated weights for policy 0, policy_version 38996 (0.0008) -[2023-11-28 01:13:56,523][87424] Updated weights for policy 0, policy_version 39006 (0.0008) -[2023-11-28 01:13:57,021][87426] Updated weights for policy 1, policy_version 38850 (0.0007) -[2023-11-28 01:13:57,414][87426] Updated weights for policy 1, policy_version 38860 (0.0008) -[2023-11-28 01:13:57,795][87426] Updated weights for policy 1, policy_version 38870 (0.0009) -[2023-11-28 01:13:58,179][87426] Updated weights for policy 1, policy_version 38880 (0.0008) -[2023-11-28 01:13:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 19939328. Throughput: 0: 2633.2, 1: 2754.6. Samples: 19952476. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:13:58,445][86177] Avg episode reward: [(0, '-523.170'), (1, '-557.920')] -[2023-11-28 01:13:58,674][87424] Updated weights for policy 0, policy_version 39016 (0.0010) -[2023-11-28 01:13:59,055][87424] Updated weights for policy 0, policy_version 39026 (0.0010) -[2023-11-28 01:13:59,439][87424] Updated weights for policy 0, policy_version 39036 (0.0011) -[2023-11-28 01:14:00,442][87426] Updated weights for policy 1, policy_version 38890 (0.0011) -[2023-11-28 01:14:00,813][87426] Updated weights for policy 1, policy_version 38900 (0.0008) -[2023-11-28 01:14:01,201][87426] Updated weights for policy 1, policy_version 38910 (0.0007) -[2023-11-28 01:14:01,890][87424] Updated weights for policy 0, policy_version 39046 (0.0012) -[2023-11-28 01:14:02,274][87424] Updated weights for policy 0, policy_version 39056 (0.0012) -[2023-11-28 01:14:02,651][87424] Updated weights for policy 0, policy_version 39066 (0.0010) -[2023-11-28 01:14:03,362][87426] Updated weights for policy 1, policy_version 38920 (0.0009) -[2023-11-28 01:14:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 19963904. Throughput: 0: 2649.6, 1: 2738.5. Samples: 19977064. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:14:03,445][86177] Avg episode reward: [(0, '-517.170'), (1, '-571.070')] -[2023-11-28 01:14:03,742][87426] Updated weights for policy 1, policy_version 38930 (0.0007) -[2023-11-28 01:14:04,118][87426] Updated weights for policy 1, policy_version 38940 (0.0007) -[2023-11-28 01:14:04,527][87424] Updated weights for policy 0, policy_version 39076 (0.0009) -[2023-11-28 01:14:04,910][87424] Updated weights for policy 0, policy_version 39086 (0.0010) -[2023-11-28 01:14:05,279][87424] Updated weights for policy 0, policy_version 39096 (0.0012) -[2023-11-28 01:14:06,662][87426] Updated weights for policy 1, policy_version 38950 (0.0009) -[2023-11-28 01:14:07,044][87426] Updated weights for policy 1, policy_version 38960 (0.0008) -[2023-11-28 01:14:07,429][87426] Updated weights for policy 1, policy_version 38970 (0.0011) -[2023-11-28 01:14:07,719][87424] Updated weights for policy 0, policy_version 39106 (0.0011) -[2023-11-28 01:14:08,102][87424] Updated weights for policy 0, policy_version 39116 (0.0007) -[2023-11-28 01:14:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 19988480. Throughput: 0: 2667.8, 1: 2722.3. Samples: 20009076. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:14:08,445][86177] Avg episode reward: [(0, '-514.290'), (1, '-549.780')] -[2023-11-28 01:14:08,481][87424] Updated weights for policy 0, policy_version 39126 (0.0007) -[2023-11-28 01:14:08,867][87424] Updated weights for policy 0, policy_version 39136 (0.0008) -[2023-11-28 01:14:09,499][87426] Updated weights for policy 1, policy_version 38980 (0.0011) -[2023-11-28 01:14:09,876][87426] Updated weights for policy 1, policy_version 38990 (0.0012) -[2023-11-28 01:14:10,253][87426] Updated weights for policy 1, policy_version 39000 (0.0008) -[2023-11-28 01:14:11,312][87424] Updated weights for policy 0, policy_version 39146 (0.0012) -[2023-11-28 01:14:11,699][87424] Updated weights for policy 0, policy_version 39156 (0.0012) -[2023-11-28 01:14:12,079][87424] Updated weights for policy 0, policy_version 39166 (0.0012) -[2023-11-28 01:14:12,086][87426] Updated weights for policy 1, policy_version 39010 (0.0010) -[2023-11-28 01:14:12,456][87426] Updated weights for policy 1, policy_version 39020 (0.0010) -[2023-11-28 01:14:12,834][87426] Updated weights for policy 1, policy_version 39030 (0.0008) -[2023-11-28 01:14:13,220][87426] Updated weights for policy 1, policy_version 39040 (0.0010) -[2023-11-28 01:14:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 20021248. Throughput: 0: 2666.0, 1: 2704.1. Samples: 20033200. Policy #0 lag: (min: 42.0, avg: 49.6, max: 73.0) -[2023-11-28 01:14:13,445][86177] Avg episode reward: [(0, '-509.680'), (1, '-539.760')] -[2023-11-28 01:14:13,897][87424] Updated weights for policy 0, policy_version 39176 (0.0009) -[2023-11-28 01:14:14,279][87424] Updated weights for policy 0, policy_version 39186 (0.0007) -[2023-11-28 01:14:14,673][87424] Updated weights for policy 0, policy_version 39196 (0.0007) -[2023-11-28 01:14:15,702][87426] Updated weights for policy 1, policy_version 39050 (0.0012) -[2023-11-28 01:14:16,093][87426] Updated weights for policy 1, policy_version 39060 (0.0009) -[2023-11-28 01:14:16,466][87426] Updated weights for policy 1, policy_version 39070 (0.0008) -[2023-11-28 01:14:16,837][87424] Updated weights for policy 0, policy_version 39206 (0.0010) -[2023-11-28 01:14:17,220][87424] Updated weights for policy 0, policy_version 39216 (0.0012) -[2023-11-28 01:14:17,600][87424] Updated weights for policy 0, policy_version 39226 (0.0012) -[2023-11-28 01:14:18,316][87426] Updated weights for policy 1, policy_version 39080 (0.0007) -[2023-11-28 01:14:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20045824. Throughput: 0: 2677.2, 1: 2696.6. Samples: 20057380. Policy #0 lag: (min: 42.0, avg: 49.6, max: 73.0) -[2023-11-28 01:14:18,445][86177] Avg episode reward: [(0, '-522.550'), (1, '-545.070')] -[2023-11-28 01:14:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000039232_10043392.pth... -[2023-11-28 01:14:18,506][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000036704_9396224.pth -[2023-11-28 01:14:18,691][87426] Updated weights for policy 1, policy_version 39090 (0.0010) -[2023-11-28 01:14:19,073][87426] Updated weights for policy 1, policy_version 39100 (0.0010) -[2023-11-28 01:14:19,215][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000039104_10010624.pth... -[2023-11-28 01:14:19,256][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000036544_9355264.pth -[2023-11-28 01:14:19,669][87424] Updated weights for policy 0, policy_version 39236 (0.0011) -[2023-11-28 01:14:20,061][87424] Updated weights for policy 0, policy_version 39246 (0.0010) -[2023-11-28 01:14:20,432][87424] Updated weights for policy 0, policy_version 39256 (0.0009) -[2023-11-28 01:14:21,409][87426] Updated weights for policy 1, policy_version 39110 (0.0011) -[2023-11-28 01:14:21,790][87426] Updated weights for policy 1, policy_version 39120 (0.0012) -[2023-11-28 01:14:22,174][87426] Updated weights for policy 1, policy_version 39130 (0.0009) -[2023-11-28 01:14:22,908][87424] Updated weights for policy 0, policy_version 39266 (0.0010) -[2023-11-28 01:14:23,290][87424] Updated weights for policy 0, policy_version 39276 (0.0011) -[2023-11-28 01:14:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 20070400. Throughput: 0: 2690.0, 1: 2666.2. Samples: 20089944. Policy #0 lag: (min: 42.0, avg: 49.6, max: 73.0) -[2023-11-28 01:14:23,445][86177] Avg episode reward: [(0, '-519.440'), (1, '-537.360')] -[2023-11-28 01:14:23,673][87424] Updated weights for policy 0, policy_version 39286 (0.0009) -[2023-11-28 01:14:24,058][87424] Updated weights for policy 0, policy_version 39296 (0.0011) -[2023-11-28 01:14:24,697][87426] Updated weights for policy 1, policy_version 39140 (0.0010) -[2023-11-28 01:14:25,080][87426] Updated weights for policy 1, policy_version 39150 (0.0011) -[2023-11-28 01:14:25,468][87426] Updated weights for policy 1, policy_version 39160 (0.0012) -[2023-11-28 01:14:25,739][87424] Updated weights for policy 0, policy_version 39306 (0.0010) -[2023-11-28 01:14:26,131][87424] Updated weights for policy 0, policy_version 39316 (0.0008) -[2023-11-28 01:14:26,519][87424] Updated weights for policy 0, policy_version 39326 (0.0008) -[2023-11-28 01:14:27,205][87426] Updated weights for policy 1, policy_version 39170 (0.0010) -[2023-11-28 01:14:27,585][87426] Updated weights for policy 1, policy_version 39180 (0.0008) -[2023-11-28 01:14:27,978][87426] Updated weights for policy 1, policy_version 39190 (0.0007) -[2023-11-28 01:14:28,209][87424] Updated weights for policy 0, policy_version 39336 (0.0007) -[2023-11-28 01:14:28,357][87426] Updated weights for policy 1, policy_version 39200 (0.0009) -[2023-11-28 01:14:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 20103168. Throughput: 0: 2701.7, 1: 2675.4. Samples: 20114396. Policy #0 lag: (min: 42.0, avg: 49.6, max: 73.0) -[2023-11-28 01:14:28,445][86177] Avg episode reward: [(0, '-524.720'), (1, '-539.930')] -[2023-11-28 01:14:28,596][87424] Updated weights for policy 0, policy_version 39346 (0.0007) -[2023-11-28 01:14:28,981][87424] Updated weights for policy 0, policy_version 39356 (0.0009) -[2023-11-28 01:14:30,773][87426] Updated weights for policy 1, policy_version 39210 (0.0010) -[2023-11-28 01:14:31,017][87424] Updated weights for policy 0, policy_version 39366 (0.0010) -[2023-11-28 01:14:31,154][87426] Updated weights for policy 1, policy_version 39220 (0.0012) -[2023-11-28 01:14:31,405][87424] Updated weights for policy 0, policy_version 39376 (0.0011) -[2023-11-28 01:14:31,527][87426] Updated weights for policy 1, policy_version 39230 (0.0012) -[2023-11-28 01:14:31,784][87424] Updated weights for policy 0, policy_version 39386 (0.0012) -[2023-11-28 01:14:33,407][87426] Updated weights for policy 1, policy_version 39240 (0.0008) -[2023-11-28 01:14:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20127744. Throughput: 0: 2733.2, 1: 2687.8. Samples: 20140324. Policy #0 lag: (min: 42.0, avg: 49.6, max: 73.0) -[2023-11-28 01:14:33,445][86177] Avg episode reward: [(0, '-532.740'), (1, '-537.340')] -[2023-11-28 01:14:33,774][87426] Updated weights for policy 1, policy_version 39250 (0.0007) -[2023-11-28 01:14:34,152][87426] Updated weights for policy 1, policy_version 39260 (0.0007) -[2023-11-28 01:14:34,209][87424] Updated weights for policy 0, policy_version 39396 (0.0010) -[2023-11-28 01:14:34,595][87424] Updated weights for policy 0, policy_version 39406 (0.0011) -[2023-11-28 01:14:34,976][87424] Updated weights for policy 0, policy_version 39416 (0.0011) -[2023-11-28 01:14:36,282][87426] Updated weights for policy 1, policy_version 39270 (0.0008) -[2023-11-28 01:14:36,659][87426] Updated weights for policy 1, policy_version 39280 (0.0008) -[2023-11-28 01:14:37,045][87426] Updated weights for policy 1, policy_version 39290 (0.0009) -[2023-11-28 01:14:37,380][87424] Updated weights for policy 0, policy_version 39426 (0.0012) -[2023-11-28 01:14:37,765][87424] Updated weights for policy 0, policy_version 39436 (0.0012) -[2023-11-28 01:14:38,150][87424] Updated weights for policy 0, policy_version 39446 (0.0008) -[2023-11-28 01:14:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 20152320. Throughput: 0: 2721.9, 1: 2678.2. Samples: 20171652. Policy #0 lag: (min: 42.0, avg: 49.6, max: 73.0) -[2023-11-28 01:14:38,445][86177] Avg episode reward: [(0, '-529.830'), (1, '-540.670')] -[2023-11-28 01:14:38,522][87424] Updated weights for policy 0, policy_version 39456 (0.0011) -[2023-11-28 01:14:39,133][87426] Updated weights for policy 1, policy_version 39300 (0.0011) -[2023-11-28 01:14:39,514][87426] Updated weights for policy 1, policy_version 39310 (0.0011) -[2023-11-28 01:14:39,890][87426] Updated weights for policy 1, policy_version 39320 (0.0008) -[2023-11-28 01:14:41,070][87424] Updated weights for policy 0, policy_version 39466 (0.0010) -[2023-11-28 01:14:41,452][87424] Updated weights for policy 0, policy_version 39476 (0.0012) -[2023-11-28 01:14:41,831][87424] Updated weights for policy 0, policy_version 39486 (0.0012) -[2023-11-28 01:14:41,958][87426] Updated weights for policy 1, policy_version 39330 (0.0009) -[2023-11-28 01:14:42,338][87426] Updated weights for policy 1, policy_version 39340 (0.0011) -[2023-11-28 01:14:42,713][87426] Updated weights for policy 1, policy_version 39350 (0.0009) -[2023-11-28 01:14:43,092][87426] Updated weights for policy 1, policy_version 39360 (0.0010) -[2023-11-28 01:14:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 20185088. Throughput: 0: 2713.3, 1: 2717.2. Samples: 20196852. Policy #0 lag: (min: 3.0, avg: 17.6, max: 35.0) -[2023-11-28 01:14:43,446][86177] Avg episode reward: [(0, '-529.210'), (1, '-546.750')] -[2023-11-28 01:14:44,391][87424] Updated weights for policy 0, policy_version 39496 (0.0010) -[2023-11-28 01:14:44,771][87424] Updated weights for policy 0, policy_version 39506 (0.0009) -[2023-11-28 01:14:44,832][87426] Updated weights for policy 1, policy_version 39370 (0.0009) -[2023-11-28 01:14:45,150][87424] Updated weights for policy 0, policy_version 39516 (0.0011) -[2023-11-28 01:14:45,210][87426] Updated weights for policy 1, policy_version 39380 (0.0012) -[2023-11-28 01:14:45,590][87426] Updated weights for policy 1, policy_version 39390 (0.0012) -[2023-11-28 01:14:46,949][87424] Updated weights for policy 0, policy_version 39526 (0.0008) -[2023-11-28 01:14:47,341][87424] Updated weights for policy 0, policy_version 39536 (0.0007) -[2023-11-28 01:14:47,728][87424] Updated weights for policy 0, policy_version 39546 (0.0008) -[2023-11-28 01:14:48,061][87426] Updated weights for policy 1, policy_version 39400 (0.0009) -[2023-11-28 01:14:48,437][87426] Updated weights for policy 1, policy_version 39410 (0.0008) -[2023-11-28 01:14:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20209664. Throughput: 0: 2695.4, 1: 2729.2. Samples: 20221172. Policy #0 lag: (min: 3.0, avg: 17.6, max: 35.0) -[2023-11-28 01:14:48,445][86177] Avg episode reward: [(0, '-518.900'), (1, '-551.620')] -[2023-11-28 01:14:48,807][87426] Updated weights for policy 1, policy_version 39420 (0.0012) -[2023-11-28 01:14:49,980][87424] Updated weights for policy 0, policy_version 39556 (0.0011) -[2023-11-28 01:14:50,357][87424] Updated weights for policy 0, policy_version 39566 (0.0012) -[2023-11-28 01:14:50,731][87424] Updated weights for policy 0, policy_version 39576 (0.0012) -[2023-11-28 01:14:51,044][87426] Updated weights for policy 1, policy_version 39430 (0.0012) -[2023-11-28 01:14:51,414][87426] Updated weights for policy 1, policy_version 39440 (0.0012) -[2023-11-28 01:14:51,790][87426] Updated weights for policy 1, policy_version 39450 (0.0012) -[2023-11-28 01:14:52,837][87424] Updated weights for policy 0, policy_version 39586 (0.0009) -[2023-11-28 01:14:53,221][87424] Updated weights for policy 0, policy_version 39596 (0.0009) -[2023-11-28 01:14:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 20234240. Throughput: 0: 2678.0, 1: 2739.4. Samples: 20252860. Policy #0 lag: (min: 3.0, avg: 17.6, max: 35.0) -[2023-11-28 01:14:53,445][86177] Avg episode reward: [(0, '-513.330'), (1, '-549.840')] -[2023-11-28 01:14:53,617][87424] Updated weights for policy 0, policy_version 39606 (0.0011) -[2023-11-28 01:14:53,928][87426] Updated weights for policy 1, policy_version 39460 (0.0012) -[2023-11-28 01:14:53,993][87424] Updated weights for policy 0, policy_version 39616 (0.0011) -[2023-11-28 01:14:54,315][87426] Updated weights for policy 1, policy_version 39470 (0.0012) -[2023-11-28 01:14:54,705][87426] Updated weights for policy 1, policy_version 39480 (0.0012) -[2023-11-28 01:14:56,250][87424] Updated weights for policy 0, policy_version 39626 (0.0011) -[2023-11-28 01:14:56,644][87424] Updated weights for policy 0, policy_version 39636 (0.0011) -[2023-11-28 01:14:56,746][87426] Updated weights for policy 1, policy_version 39490 (0.0012) -[2023-11-28 01:14:57,021][87424] Updated weights for policy 0, policy_version 39646 (0.0011) -[2023-11-28 01:14:57,136][87426] Updated weights for policy 1, policy_version 39500 (0.0012) -[2023-11-28 01:14:57,516][87426] Updated weights for policy 1, policy_version 39510 (0.0012) -[2023-11-28 01:14:57,898][87426] Updated weights for policy 1, policy_version 39520 (0.0011) -[2023-11-28 01:14:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 20267008. Throughput: 0: 2684.9, 1: 2734.0. Samples: 20277048. Policy #0 lag: (min: 3.0, avg: 17.6, max: 35.0) -[2023-11-28 01:14:58,445][86177] Avg episode reward: [(0, '-502.260'), (1, '-539.440')] -[2023-11-28 01:14:59,124][87424] Updated weights for policy 0, policy_version 39656 (0.0010) -[2023-11-28 01:14:59,506][87424] Updated weights for policy 0, policy_version 39666 (0.0011) -[2023-11-28 01:14:59,903][87424] Updated weights for policy 0, policy_version 39676 (0.0011) -[2023-11-28 01:15:00,053][87426] Updated weights for policy 1, policy_version 39530 (0.0010) -[2023-11-28 01:15:00,438][87426] Updated weights for policy 1, policy_version 39540 (0.0008) -[2023-11-28 01:15:00,815][87426] Updated weights for policy 1, policy_version 39550 (0.0009) -[2023-11-28 01:15:02,381][87424] Updated weights for policy 0, policy_version 39686 (0.0011) -[2023-11-28 01:15:02,752][87424] Updated weights for policy 0, policy_version 39696 (0.0011) -[2023-11-28 01:15:02,773][87426] Updated weights for policy 1, policy_version 39560 (0.0009) -[2023-11-28 01:15:03,133][87424] Updated weights for policy 0, policy_version 39706 (0.0012) -[2023-11-28 01:15:03,150][87426] Updated weights for policy 1, policy_version 39570 (0.0008) -[2023-11-28 01:15:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20291584. Throughput: 0: 2688.4, 1: 2742.3. Samples: 20301760. Policy #0 lag: (min: 3.0, avg: 17.6, max: 35.0) -[2023-11-28 01:15:03,445][86177] Avg episode reward: [(0, '-501.850'), (1, '-519.890')] -[2023-11-28 01:15:03,527][87426] Updated weights for policy 1, policy_version 39580 (0.0011) -[2023-11-28 01:15:05,737][87424] Updated weights for policy 0, policy_version 39716 (0.0009) -[2023-11-28 01:15:05,758][87426] Updated weights for policy 1, policy_version 39590 (0.0010) -[2023-11-28 01:15:06,118][87424] Updated weights for policy 0, policy_version 39726 (0.0008) -[2023-11-28 01:15:06,142][87426] Updated weights for policy 1, policy_version 39600 (0.0007) -[2023-11-28 01:15:06,497][87424] Updated weights for policy 0, policy_version 39736 (0.0007) -[2023-11-28 01:15:06,531][87426] Updated weights for policy 1, policy_version 39610 (0.0008) -[2023-11-28 01:15:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 20316160. Throughput: 0: 2662.2, 1: 2745.8. Samples: 20333304. Policy #0 lag: (min: 12.0, avg: 30.9, max: 44.0) -[2023-11-28 01:15:08,445][86177] Avg episode reward: [(0, '-516.110'), (1, '-510.890')] -[2023-11-28 01:15:08,771][87426] Updated weights for policy 1, policy_version 39620 (0.0010) -[2023-11-28 01:15:09,052][87424] Updated weights for policy 0, policy_version 39746 (0.0009) -[2023-11-28 01:15:09,143][87426] Updated weights for policy 1, policy_version 39630 (0.0012) -[2023-11-28 01:15:09,435][87424] Updated weights for policy 0, policy_version 39756 (0.0012) -[2023-11-28 01:15:09,518][87426] Updated weights for policy 1, policy_version 39640 (0.0011) -[2023-11-28 01:15:09,817][87424] Updated weights for policy 0, policy_version 39766 (0.0011) -[2023-11-28 01:15:10,201][87424] Updated weights for policy 0, policy_version 39776 (0.0011) -[2023-11-28 01:15:11,993][87426] Updated weights for policy 1, policy_version 39650 (0.0011) -[2023-11-28 01:15:12,306][87424] Updated weights for policy 0, policy_version 39786 (0.0011) -[2023-11-28 01:15:12,377][87426] Updated weights for policy 1, policy_version 39660 (0.0011) -[2023-11-28 01:15:12,692][87424] Updated weights for policy 0, policy_version 39796 (0.0009) -[2023-11-28 01:15:12,751][87426] Updated weights for policy 1, policy_version 39670 (0.0009) -[2023-11-28 01:15:13,075][87424] Updated weights for policy 0, policy_version 39806 (0.0011) -[2023-11-28 01:15:13,124][87426] Updated weights for policy 1, policy_version 39680 (0.0011) -[2023-11-28 01:15:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 20348928. Throughput: 0: 2644.2, 1: 2747.6. Samples: 20357024. Policy #0 lag: (min: 12.0, avg: 30.9, max: 44.0) -[2023-11-28 01:15:13,445][86177] Avg episode reward: [(0, '-516.340'), (1, '-510.100')] -[2023-11-28 01:15:14,849][87424] Updated weights for policy 0, policy_version 39816 (0.0012) -[2023-11-28 01:15:15,239][87424] Updated weights for policy 0, policy_version 39826 (0.0012) -[2023-11-28 01:15:15,417][87426] Updated weights for policy 1, policy_version 39690 (0.0012) -[2023-11-28 01:15:15,605][87424] Updated weights for policy 0, policy_version 39836 (0.0011) -[2023-11-28 01:15:15,800][87426] Updated weights for policy 1, policy_version 39700 (0.0012) -[2023-11-28 01:15:16,175][87426] Updated weights for policy 1, policy_version 39710 (0.0012) -[2023-11-28 01:15:17,502][87424] Updated weights for policy 0, policy_version 39846 (0.0012) -[2023-11-28 01:15:17,884][87424] Updated weights for policy 0, policy_version 39856 (0.0012) -[2023-11-28 01:15:18,264][87424] Updated weights for policy 0, policy_version 39866 (0.0012) -[2023-11-28 01:15:18,413][87426] Updated weights for policy 1, policy_version 39720 (0.0008) -[2023-11-28 01:15:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 20365312. Throughput: 0: 2628.3, 1: 2742.2. Samples: 20381996. Policy #0 lag: (min: 12.0, avg: 30.9, max: 44.0) -[2023-11-28 01:15:18,446][86177] Avg episode reward: [(0, '-517.320'), (1, '-521.580')] -[2023-11-28 01:15:18,801][87426] Updated weights for policy 1, policy_version 39730 (0.0008) -[2023-11-28 01:15:19,195][87426] Updated weights for policy 1, policy_version 39740 (0.0008) -[2023-11-28 01:15:20,423][87424] Updated weights for policy 0, policy_version 39876 (0.0012) -[2023-11-28 01:15:20,805][87424] Updated weights for policy 0, policy_version 39886 (0.0019) -[2023-11-28 01:15:21,130][87426] Updated weights for policy 1, policy_version 39750 (0.0009) -[2023-11-28 01:15:21,186][87424] Updated weights for policy 0, policy_version 39896 (0.0012) -[2023-11-28 01:15:21,514][87426] Updated weights for policy 1, policy_version 39760 (0.0009) -[2023-11-28 01:15:21,894][87426] Updated weights for policy 1, policy_version 39770 (0.0012) -[2023-11-28 01:15:23,244][87424] Updated weights for policy 0, policy_version 39906 (0.0011) -[2023-11-28 01:15:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 20398080. Throughput: 0: 2671.6, 1: 2756.1. Samples: 20415900. Policy #0 lag: (min: 12.0, avg: 30.9, max: 44.0) -[2023-11-28 01:15:23,445][86177] Avg episode reward: [(0, '-522.520'), (1, '-535.250')] -[2023-11-28 01:15:23,628][87424] Updated weights for policy 0, policy_version 39916 (0.0008) -[2023-11-28 01:15:24,011][87424] Updated weights for policy 0, policy_version 39926 (0.0008) -[2023-11-28 01:15:24,259][87426] Updated weights for policy 1, policy_version 39780 (0.0010) -[2023-11-28 01:15:24,394][87424] Updated weights for policy 0, policy_version 39936 (0.0012) -[2023-11-28 01:15:24,643][87426] Updated weights for policy 1, policy_version 39790 (0.0008) -[2023-11-28 01:15:25,013][87426] Updated weights for policy 1, policy_version 39800 (0.0008) -[2023-11-28 01:15:26,371][87424] Updated weights for policy 0, policy_version 39946 (0.0011) -[2023-11-28 01:15:26,754][87424] Updated weights for policy 0, policy_version 39956 (0.0012) -[2023-11-28 01:15:27,144][87424] Updated weights for policy 0, policy_version 39966 (0.0012) -[2023-11-28 01:15:27,446][87426] Updated weights for policy 1, policy_version 39810 (0.0008) -[2023-11-28 01:15:27,827][87426] Updated weights for policy 1, policy_version 39820 (0.0009) -[2023-11-28 01:15:28,203][87426] Updated weights for policy 1, policy_version 39830 (0.0007) -[2023-11-28 01:15:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 20422656. Throughput: 0: 2692.8, 1: 2734.2. Samples: 20441068. Policy #0 lag: (min: 12.0, avg: 30.9, max: 44.0) -[2023-11-28 01:15:28,445][86177] Avg episode reward: [(0, '-507.000'), (1, '-537.230')] -[2023-11-28 01:15:28,588][87426] Updated weights for policy 1, policy_version 39840 (0.0009) -[2023-11-28 01:15:28,779][87424] Updated weights for policy 0, policy_version 39976 (0.0012) -[2023-11-28 01:15:29,154][87424] Updated weights for policy 0, policy_version 39986 (0.0012) -[2023-11-28 01:15:29,547][87424] Updated weights for policy 0, policy_version 39996 (0.0012) -[2023-11-28 01:15:30,501][87426] Updated weights for policy 1, policy_version 39850 (0.0012) -[2023-11-28 01:15:30,880][87426] Updated weights for policy 1, policy_version 39860 (0.0011) -[2023-11-28 01:15:31,278][87426] Updated weights for policy 1, policy_version 39870 (0.0012) -[2023-11-28 01:15:32,090][87424] Updated weights for policy 0, policy_version 40006 (0.0012) -[2023-11-28 01:15:32,477][87424] Updated weights for policy 0, policy_version 40016 (0.0012) -[2023-11-28 01:15:32,865][87424] Updated weights for policy 0, policy_version 40026 (0.0012) -[2023-11-28 01:15:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20455424. Throughput: 0: 2717.2, 1: 2719.4. Samples: 20465816. Policy #0 lag: (min: 20.0, avg: 33.0, max: 52.0) -[2023-11-28 01:15:33,445][86177] Avg episode reward: [(0, '-516.160'), (1, '-536.620')] -[2023-11-28 01:15:33,638][87426] Updated weights for policy 1, policy_version 39880 (0.0012) -[2023-11-28 01:15:34,021][87426] Updated weights for policy 1, policy_version 39890 (0.0012) -[2023-11-28 01:15:34,391][87426] Updated weights for policy 1, policy_version 39900 (0.0012) -[2023-11-28 01:15:34,911][87424] Updated weights for policy 0, policy_version 40036 (0.0011) -[2023-11-28 01:15:35,300][87424] Updated weights for policy 0, policy_version 40046 (0.0011) -[2023-11-28 01:15:35,674][87424] Updated weights for policy 0, policy_version 40056 (0.0011) -[2023-11-28 01:15:36,265][87426] Updated weights for policy 1, policy_version 39910 (0.0008) -[2023-11-28 01:15:36,643][87426] Updated weights for policy 1, policy_version 39920 (0.0008) -[2023-11-28 01:15:37,025][87426] Updated weights for policy 1, policy_version 39930 (0.0010) -[2023-11-28 01:15:38,199][87424] Updated weights for policy 0, policy_version 40066 (0.0012) -[2023-11-28 01:15:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 20480000. Throughput: 0: 2729.3, 1: 2751.0. Samples: 20499476. Policy #0 lag: (min: 20.0, avg: 33.0, max: 52.0) -[2023-11-28 01:15:38,445][86177] Avg episode reward: [(0, '-516.400'), (1, '-545.060')] -[2023-11-28 01:15:38,580][87424] Updated weights for policy 0, policy_version 40076 (0.0010) -[2023-11-28 01:15:38,614][87426] Updated weights for policy 1, policy_version 39940 (0.0009) -[2023-11-28 01:15:38,972][87424] Updated weights for policy 0, policy_version 40086 (0.0008) -[2023-11-28 01:15:38,991][87426] Updated weights for policy 1, policy_version 39950 (0.0011) -[2023-11-28 01:15:39,349][87424] Updated weights for policy 0, policy_version 40096 (0.0008) -[2023-11-28 01:15:39,371][87426] Updated weights for policy 1, policy_version 39960 (0.0011) -[2023-11-28 01:15:41,622][87426] Updated weights for policy 1, policy_version 39970 (0.0012) -[2023-11-28 01:15:41,798][87424] Updated weights for policy 0, policy_version 40106 (0.0010) -[2023-11-28 01:15:41,990][87426] Updated weights for policy 1, policy_version 39980 (0.0010) -[2023-11-28 01:15:42,175][87424] Updated weights for policy 0, policy_version 40116 (0.0010) -[2023-11-28 01:15:42,360][87426] Updated weights for policy 1, policy_version 39990 (0.0012) -[2023-11-28 01:15:42,552][87424] Updated weights for policy 0, policy_version 40126 (0.0011) -[2023-11-28 01:15:42,742][87426] Updated weights for policy 1, policy_version 40000 (0.0011) -[2023-11-28 01:15:43,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 20512768. Throughput: 0: 2716.7, 1: 2755.3. Samples: 20523288. Policy #0 lag: (min: 20.0, avg: 33.0, max: 52.0) -[2023-11-28 01:15:43,446][86177] Avg episode reward: [(0, '-525.540'), (1, '-537.060')] -[2023-11-28 01:15:44,755][87426] Updated weights for policy 1, policy_version 40010 (0.0011) -[2023-11-28 01:15:45,057][87424] Updated weights for policy 0, policy_version 40136 (0.0011) -[2023-11-28 01:15:45,135][87426] Updated weights for policy 1, policy_version 40020 (0.0011) -[2023-11-28 01:15:45,439][87424] Updated weights for policy 0, policy_version 40146 (0.0010) -[2023-11-28 01:15:45,521][87426] Updated weights for policy 1, policy_version 40030 (0.0011) -[2023-11-28 01:15:45,825][87424] Updated weights for policy 0, policy_version 40156 (0.0008) -[2023-11-28 01:15:47,393][87426] Updated weights for policy 1, policy_version 40040 (0.0011) -[2023-11-28 01:15:47,770][87426] Updated weights for policy 1, policy_version 40050 (0.0011) -[2023-11-28 01:15:48,038][87424] Updated weights for policy 0, policy_version 40166 (0.0010) -[2023-11-28 01:15:48,149][87426] Updated weights for policy 1, policy_version 40060 (0.0011) -[2023-11-28 01:15:48,415][87424] Updated weights for policy 0, policy_version 40176 (0.0011) -[2023-11-28 01:15:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20537344. Throughput: 0: 2690.3, 1: 2758.5. Samples: 20546956. Policy #0 lag: (min: 20.0, avg: 33.0, max: 52.0) -[2023-11-28 01:15:48,445][86177] Avg episode reward: [(0, '-530.300'), (1, '-539.730')] -[2023-11-28 01:15:48,796][87424] Updated weights for policy 0, policy_version 40186 (0.0008) -[2023-11-28 01:15:50,017][87426] Updated weights for policy 1, policy_version 40070 (0.0011) -[2023-11-28 01:15:50,399][87426] Updated weights for policy 1, policy_version 40080 (0.0010) -[2023-11-28 01:15:50,780][87426] Updated weights for policy 1, policy_version 40090 (0.0008) -[2023-11-28 01:15:51,117][87424] Updated weights for policy 0, policy_version 40196 (0.0009) -[2023-11-28 01:15:51,499][87424] Updated weights for policy 0, policy_version 40206 (0.0011) -[2023-11-28 01:15:51,884][87424] Updated weights for policy 0, policy_version 40216 (0.0011) -[2023-11-28 01:15:53,285][87426] Updated weights for policy 1, policy_version 40100 (0.0009) -[2023-11-28 01:15:53,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20561920. Throughput: 0: 2698.2, 1: 2756.8. Samples: 20578780. Policy #0 lag: (min: 20.0, avg: 33.0, max: 52.0) -[2023-11-28 01:15:53,445][86177] Avg episode reward: [(0, '-531.320'), (1, '-544.330')] -[2023-11-28 01:15:53,674][87426] Updated weights for policy 1, policy_version 40110 (0.0011) -[2023-11-28 01:15:53,976][87424] Updated weights for policy 0, policy_version 40226 (0.0009) -[2023-11-28 01:15:54,045][87426] Updated weights for policy 1, policy_version 40120 (0.0011) -[2023-11-28 01:15:54,354][87424] Updated weights for policy 0, policy_version 40236 (0.0012) -[2023-11-28 01:15:54,734][87424] Updated weights for policy 0, policy_version 40246 (0.0012) -[2023-11-28 01:15:55,118][87424] Updated weights for policy 0, policy_version 40256 (0.0012) -[2023-11-28 01:15:56,662][87426] Updated weights for policy 1, policy_version 40130 (0.0010) -[2023-11-28 01:15:57,046][87426] Updated weights for policy 1, policy_version 40140 (0.0011) -[2023-11-28 01:15:57,316][87424] Updated weights for policy 0, policy_version 40266 (0.0012) -[2023-11-28 01:15:57,425][87426] Updated weights for policy 1, policy_version 40150 (0.0009) -[2023-11-28 01:15:57,697][87424] Updated weights for policy 0, policy_version 40276 (0.0011) -[2023-11-28 01:15:57,813][87426] Updated weights for policy 1, policy_version 40160 (0.0008) -[2023-11-28 01:15:58,090][87424] Updated weights for policy 0, policy_version 40286 (0.0012) -[2023-11-28 01:15:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20594688. Throughput: 0: 2710.7, 1: 2748.6. Samples: 20602692. Policy #0 lag: (min: 20.0, avg: 33.0, max: 52.0) -[2023-11-28 01:15:58,445][86177] Avg episode reward: [(0, '-520.830'), (1, '-539.850')] -[2023-11-28 01:15:59,848][87426] Updated weights for policy 1, policy_version 40170 (0.0011) -[2023-11-28 01:16:00,198][87424] Updated weights for policy 0, policy_version 40296 (0.0011) -[2023-11-28 01:16:00,232][87426] Updated weights for policy 1, policy_version 40180 (0.0011) -[2023-11-28 01:16:00,584][87424] Updated weights for policy 0, policy_version 40306 (0.0009) -[2023-11-28 01:16:00,614][87426] Updated weights for policy 1, policy_version 40190 (0.0011) -[2023-11-28 01:16:00,969][87424] Updated weights for policy 0, policy_version 40316 (0.0008) -[2023-11-28 01:16:02,807][87424] Updated weights for policy 0, policy_version 40326 (0.0010) -[2023-11-28 01:16:02,809][87426] Updated weights for policy 1, policy_version 40200 (0.0009) -[2023-11-28 01:16:03,180][87426] Updated weights for policy 1, policy_version 40210 (0.0010) -[2023-11-28 01:16:03,187][87424] Updated weights for policy 0, policy_version 40336 (0.0011) -[2023-11-28 01:16:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 20611072. Throughput: 0: 2733.9, 1: 2732.4. Samples: 20627976. Policy #0 lag: (min: 13.0, avg: 32.8, max: 56.0) -[2023-11-28 01:16:03,445][86177] Avg episode reward: [(0, '-520.270'), (1, '-532.610')] -[2023-11-28 01:16:03,568][87424] Updated weights for policy 0, policy_version 40346 (0.0011) -[2023-11-28 01:16:03,570][87426] Updated weights for policy 1, policy_version 40220 (0.0008) -[2023-11-28 01:16:05,590][87424] Updated weights for policy 0, policy_version 40356 (0.0011) -[2023-11-28 01:16:05,601][87426] Updated weights for policy 1, policy_version 40230 (0.0009) -[2023-11-28 01:16:05,970][87424] Updated weights for policy 0, policy_version 40366 (0.0008) -[2023-11-28 01:16:05,971][87426] Updated weights for policy 1, policy_version 40240 (0.0010) -[2023-11-28 01:16:06,346][87424] Updated weights for policy 0, policy_version 40376 (0.0007) -[2023-11-28 01:16:06,354][87426] Updated weights for policy 1, policy_version 40250 (0.0011) -[2023-11-28 01:16:08,176][87424] Updated weights for policy 0, policy_version 40386 (0.0008) -[2023-11-28 01:16:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20643840. Throughput: 0: 2735.3, 1: 2699.6. Samples: 20660472. Policy #0 lag: (min: 13.0, avg: 32.8, max: 56.0) -[2023-11-28 01:16:08,445][86177] Avg episode reward: [(0, '-519.570'), (1, '-526.990')] -[2023-11-28 01:16:08,572][87424] Updated weights for policy 0, policy_version 40396 (0.0008) -[2023-11-28 01:16:08,883][87426] Updated weights for policy 1, policy_version 40260 (0.0012) -[2023-11-28 01:16:08,948][87424] Updated weights for policy 0, policy_version 40406 (0.0012) -[2023-11-28 01:16:09,261][87426] Updated weights for policy 1, policy_version 40270 (0.0008) -[2023-11-28 01:16:09,337][87424] Updated weights for policy 0, policy_version 40416 (0.0009) -[2023-11-28 01:16:09,641][87426] Updated weights for policy 1, policy_version 40280 (0.0007) -[2023-11-28 01:16:11,808][87424] Updated weights for policy 0, policy_version 40426 (0.0010) -[2023-11-28 01:16:12,059][87426] Updated weights for policy 1, policy_version 40290 (0.0010) -[2023-11-28 01:16:12,193][87424] Updated weights for policy 0, policy_version 40436 (0.0012) -[2023-11-28 01:16:12,435][87426] Updated weights for policy 1, policy_version 40300 (0.0012) -[2023-11-28 01:16:12,575][87424] Updated weights for policy 0, policy_version 40446 (0.0012) -[2023-11-28 01:16:12,813][87426] Updated weights for policy 1, policy_version 40310 (0.0011) -[2023-11-28 01:16:13,202][87426] Updated weights for policy 1, policy_version 40320 (0.0012) -[2023-11-28 01:16:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 20676608. Throughput: 0: 2713.3, 1: 2669.3. Samples: 20683288. Policy #0 lag: (min: 13.0, avg: 32.8, max: 56.0) -[2023-11-28 01:16:13,446][86177] Avg episode reward: [(0, '-517.660'), (1, '-553.200')] -[2023-11-28 01:16:14,371][87424] Updated weights for policy 0, policy_version 40456 (0.0012) -[2023-11-28 01:16:14,747][87424] Updated weights for policy 0, policy_version 40466 (0.0012) -[2023-11-28 01:16:15,140][87424] Updated weights for policy 0, policy_version 40476 (0.0012) -[2023-11-28 01:16:15,706][87426] Updated weights for policy 1, policy_version 40330 (0.0008) -[2023-11-28 01:16:16,089][87426] Updated weights for policy 1, policy_version 40340 (0.0010) -[2023-11-28 01:16:16,474][87426] Updated weights for policy 1, policy_version 40350 (0.0012) -[2023-11-28 01:16:16,816][87424] Updated weights for policy 0, policy_version 40486 (0.0009) -[2023-11-28 01:16:17,199][87424] Updated weights for policy 0, policy_version 40496 (0.0008) -[2023-11-28 01:16:17,590][87424] Updated weights for policy 0, policy_version 40506 (0.0008) -[2023-11-28 01:16:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 20701184. Throughput: 0: 2724.9, 1: 2683.7. Samples: 20709204. Policy #0 lag: (min: 13.0, avg: 32.8, max: 56.0) -[2023-11-28 01:16:18,445][86177] Avg episode reward: [(0, '-566.790'), (1, '-533.170')] -[2023-11-28 01:16:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000040512_10371072.pth... -[2023-11-28 01:16:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000040352_10330112.pth... -[2023-11-28 01:16:18,493][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000037984_9723904.pth -[2023-11-28 01:16:18,509][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000037824_9682944.pth -[2023-11-28 01:16:18,950][87426] Updated weights for policy 1, policy_version 40360 (0.0010) -[2023-11-28 01:16:19,327][87426] Updated weights for policy 1, policy_version 40370 (0.0008) -[2023-11-28 01:16:19,718][87426] Updated weights for policy 1, policy_version 40380 (0.0007) -[2023-11-28 01:16:20,005][87424] Updated weights for policy 0, policy_version 40516 (0.0008) -[2023-11-28 01:16:20,384][87424] Updated weights for policy 0, policy_version 40526 (0.0010) -[2023-11-28 01:16:20,773][87424] Updated weights for policy 0, policy_version 40536 (0.0008) -[2023-11-28 01:16:22,240][87426] Updated weights for policy 1, policy_version 40390 (0.0010) -[2023-11-28 01:16:22,618][87426] Updated weights for policy 1, policy_version 40400 (0.0009) -[2023-11-28 01:16:22,780][87424] Updated weights for policy 0, policy_version 40546 (0.0008) -[2023-11-28 01:16:22,995][87426] Updated weights for policy 1, policy_version 40410 (0.0010) -[2023-11-28 01:16:23,164][87424] Updated weights for policy 0, policy_version 40556 (0.0010) -[2023-11-28 01:16:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 20725760. Throughput: 0: 2736.0, 1: 2640.3. Samples: 20741408. Policy #0 lag: (min: 13.0, avg: 32.8, max: 56.0) -[2023-11-28 01:16:23,445][86177] Avg episode reward: [(0, '-567.290'), (1, '-530.920')] -[2023-11-28 01:16:23,541][87424] Updated weights for policy 0, policy_version 40566 (0.0011) -[2023-11-28 01:16:23,918][87424] Updated weights for policy 0, policy_version 40576 (0.0011) -[2023-11-28 01:16:25,589][87426] Updated weights for policy 1, policy_version 40420 (0.0012) -[2023-11-28 01:16:25,966][87426] Updated weights for policy 1, policy_version 40430 (0.0008) -[2023-11-28 01:16:26,294][87424] Updated weights for policy 0, policy_version 40586 (0.0008) -[2023-11-28 01:16:26,340][87426] Updated weights for policy 1, policy_version 40440 (0.0010) -[2023-11-28 01:16:26,680][87424] Updated weights for policy 0, policy_version 40596 (0.0008) -[2023-11-28 01:16:27,077][87424] Updated weights for policy 0, policy_version 40606 (0.0007) -[2023-11-28 01:16:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20750336. Throughput: 0: 2758.4, 1: 2631.2. Samples: 20765820. Policy #0 lag: (min: 14.0, avg: 27.7, max: 46.0) -[2023-11-28 01:16:28,445][86177] Avg episode reward: [(0, '-561.780'), (1, '-527.530')] -[2023-11-28 01:16:28,738][87426] Updated weights for policy 1, policy_version 40450 (0.0011) -[2023-11-28 01:16:29,114][87426] Updated weights for policy 1, policy_version 40460 (0.0012) -[2023-11-28 01:16:29,418][87424] Updated weights for policy 0, policy_version 40616 (0.0011) -[2023-11-28 01:16:29,495][87426] Updated weights for policy 1, policy_version 40470 (0.0012) -[2023-11-28 01:16:29,801][87424] Updated weights for policy 0, policy_version 40626 (0.0009) -[2023-11-28 01:16:29,871][87426] Updated weights for policy 1, policy_version 40480 (0.0011) -[2023-11-28 01:16:30,188][87424] Updated weights for policy 0, policy_version 40636 (0.0008) -[2023-11-28 01:16:31,498][87426] Updated weights for policy 1, policy_version 40490 (0.0012) -[2023-11-28 01:16:31,883][87426] Updated weights for policy 1, policy_version 40500 (0.0011) -[2023-11-28 01:16:32,268][87426] Updated weights for policy 1, policy_version 40510 (0.0011) -[2023-11-28 01:16:32,539][87424] Updated weights for policy 0, policy_version 40646 (0.0010) -[2023-11-28 01:16:32,925][87424] Updated weights for policy 0, policy_version 40656 (0.0012) -[2023-11-28 01:16:33,307][87424] Updated weights for policy 0, policy_version 40666 (0.0012) -[2023-11-28 01:16:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 20774912. Throughput: 0: 2775.5, 1: 2617.6. Samples: 20789644. Policy #0 lag: (min: 14.0, avg: 27.7, max: 46.0) -[2023-11-28 01:16:33,446][86177] Avg episode reward: [(0, '-565.370'), (1, '-506.820')] -[2023-11-28 01:16:34,524][87426] Updated weights for policy 1, policy_version 40520 (0.0011) -[2023-11-28 01:16:34,916][87426] Updated weights for policy 1, policy_version 40530 (0.0012) -[2023-11-28 01:16:35,290][87426] Updated weights for policy 1, policy_version 40540 (0.0008) -[2023-11-28 01:16:35,837][87424] Updated weights for policy 0, policy_version 40676 (0.0010) -[2023-11-28 01:16:36,216][87424] Updated weights for policy 0, policy_version 40686 (0.0008) -[2023-11-28 01:16:36,598][87424] Updated weights for policy 0, policy_version 40696 (0.0009) -[2023-11-28 01:16:37,179][87426] Updated weights for policy 1, policy_version 40550 (0.0011) -[2023-11-28 01:16:37,555][87426] Updated weights for policy 1, policy_version 40560 (0.0011) -[2023-11-28 01:16:37,934][87426] Updated weights for policy 1, policy_version 40570 (0.0012) -[2023-11-28 01:16:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 20807680. Throughput: 0: 2770.6, 1: 2642.4. Samples: 20822364. Policy #0 lag: (min: 14.0, avg: 27.7, max: 46.0) -[2023-11-28 01:16:38,445][86177] Avg episode reward: [(0, '-578.130'), (1, '-508.330')] -[2023-11-28 01:16:39,149][87424] Updated weights for policy 0, policy_version 40706 (0.0009) -[2023-11-28 01:16:39,539][87424] Updated weights for policy 0, policy_version 40716 (0.0012) -[2023-11-28 01:16:39,897][87426] Updated weights for policy 1, policy_version 40580 (0.0011) -[2023-11-28 01:16:39,914][87424] Updated weights for policy 0, policy_version 40726 (0.0011) -[2023-11-28 01:16:40,268][87426] Updated weights for policy 1, policy_version 40590 (0.0008) -[2023-11-28 01:16:40,297][87424] Updated weights for policy 0, policy_version 40736 (0.0011) -[2023-11-28 01:16:40,659][87426] Updated weights for policy 1, policy_version 40600 (0.0009) -[2023-11-28 01:16:42,756][87424] Updated weights for policy 0, policy_version 40746 (0.0012) -[2023-11-28 01:16:42,949][87426] Updated weights for policy 1, policy_version 40610 (0.0011) -[2023-11-28 01:16:43,132][87424] Updated weights for policy 0, policy_version 40756 (0.0011) -[2023-11-28 01:16:43,326][87426] Updated weights for policy 1, policy_version 40620 (0.0011) -[2023-11-28 01:16:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 20824064. Throughput: 0: 2744.1, 1: 2653.0. Samples: 20845560. Policy #0 lag: (min: 14.0, avg: 27.7, max: 46.0) -[2023-11-28 01:16:43,445][86177] Avg episode reward: [(0, '-550.420'), (1, '-550.750')] -[2023-11-28 01:16:43,510][87424] Updated weights for policy 0, policy_version 40766 (0.0009) -[2023-11-28 01:16:43,705][87426] Updated weights for policy 1, policy_version 40630 (0.0011) -[2023-11-28 01:16:44,093][87426] Updated weights for policy 1, policy_version 40640 (0.0012) -[2023-11-28 01:16:45,348][87424] Updated weights for policy 0, policy_version 40776 (0.0011) -[2023-11-28 01:16:45,726][87424] Updated weights for policy 0, policy_version 40786 (0.0011) -[2023-11-28 01:16:46,105][87424] Updated weights for policy 0, policy_version 40796 (0.0011) -[2023-11-28 01:16:46,306][87426] Updated weights for policy 1, policy_version 40650 (0.0009) -[2023-11-28 01:16:46,698][87426] Updated weights for policy 1, policy_version 40660 (0.0009) -[2023-11-28 01:16:47,066][87426] Updated weights for policy 1, policy_version 40670 (0.0008) -[2023-11-28 01:16:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 20856832. Throughput: 0: 2710.8, 1: 2679.9. Samples: 20870556. Policy #0 lag: (min: 14.0, avg: 27.7, max: 46.0) -[2023-11-28 01:16:48,445][86177] Avg episode reward: [(0, '-578.840'), (1, '-554.400')] -[2023-11-28 01:16:48,496][87424] Updated weights for policy 0, policy_version 40806 (0.0010) -[2023-11-28 01:16:48,871][87424] Updated weights for policy 0, policy_version 40816 (0.0011) -[2023-11-28 01:16:48,953][87426] Updated weights for policy 1, policy_version 40680 (0.0010) -[2023-11-28 01:16:49,258][87424] Updated weights for policy 0, policy_version 40826 (0.0012) -[2023-11-28 01:16:49,330][87426] Updated weights for policy 1, policy_version 40690 (0.0010) -[2023-11-28 01:16:49,717][87426] Updated weights for policy 1, policy_version 40700 (0.0009) -[2023-11-28 01:16:51,432][87424] Updated weights for policy 0, policy_version 40836 (0.0012) -[2023-11-28 01:16:51,744][87426] Updated weights for policy 1, policy_version 40710 (0.0010) -[2023-11-28 01:16:51,821][87424] Updated weights for policy 0, policy_version 40846 (0.0011) -[2023-11-28 01:16:52,114][87426] Updated weights for policy 1, policy_version 40720 (0.0010) -[2023-11-28 01:16:52,189][87424] Updated weights for policy 0, policy_version 40856 (0.0012) -[2023-11-28 01:16:52,500][87426] Updated weights for policy 1, policy_version 40730 (0.0012) -[2023-11-28 01:16:53,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 20889600. Throughput: 0: 2674.9, 1: 2725.3. Samples: 20903480. Policy #0 lag: (min: 14.0, avg: 27.7, max: 46.0) -[2023-11-28 01:16:53,445][86177] Avg episode reward: [(0, '-577.290'), (1, '-551.710')] -[2023-11-28 01:16:54,716][87426] Updated weights for policy 1, policy_version 40740 (0.0010) -[2023-11-28 01:16:54,809][87424] Updated weights for policy 0, policy_version 40866 (0.0009) -[2023-11-28 01:16:55,092][87426] Updated weights for policy 1, policy_version 40750 (0.0011) -[2023-11-28 01:16:55,182][87424] Updated weights for policy 0, policy_version 40876 (0.0012) -[2023-11-28 01:16:55,466][87426] Updated weights for policy 1, policy_version 40760 (0.0010) -[2023-11-28 01:16:55,570][87424] Updated weights for policy 0, policy_version 40886 (0.0009) -[2023-11-28 01:16:55,956][87424] Updated weights for policy 0, policy_version 40896 (0.0007) -[2023-11-28 01:16:57,536][87426] Updated weights for policy 1, policy_version 40770 (0.0011) -[2023-11-28 01:16:57,911][87426] Updated weights for policy 1, policy_version 40780 (0.0009) -[2023-11-28 01:16:58,292][87426] Updated weights for policy 1, policy_version 40790 (0.0010) -[2023-11-28 01:16:58,353][87424] Updated weights for policy 0, policy_version 40906 (0.0012) -[2023-11-28 01:16:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 20905984. Throughput: 0: 2676.4, 1: 2752.5. Samples: 20927592. Policy #0 lag: (min: 29.0, avg: 40.0, max: 65.0) -[2023-11-28 01:16:58,445][86177] Avg episode reward: [(0, '-553.420'), (1, '-504.800')] -[2023-11-28 01:16:58,676][87426] Updated weights for policy 1, policy_version 40800 (0.0008) -[2023-11-28 01:16:58,752][87424] Updated weights for policy 0, policy_version 40916 (0.0011) -[2023-11-28 01:16:59,130][87424] Updated weights for policy 0, policy_version 40926 (0.0011) -[2023-11-28 01:17:00,814][87424] Updated weights for policy 0, policy_version 40936 (0.0009) -[2023-11-28 01:17:01,062][87426] Updated weights for policy 1, policy_version 40810 (0.0010) -[2023-11-28 01:17:01,198][87424] Updated weights for policy 0, policy_version 40946 (0.0008) -[2023-11-28 01:17:01,448][87426] Updated weights for policy 1, policy_version 40820 (0.0008) -[2023-11-28 01:17:01,581][87424] Updated weights for policy 0, policy_version 40956 (0.0008) -[2023-11-28 01:17:01,822][87426] Updated weights for policy 1, policy_version 40830 (0.0010) -[2023-11-28 01:17:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 20938752. Throughput: 0: 2647.5, 1: 2731.6. Samples: 20951260. Policy #0 lag: (min: 29.0, avg: 40.0, max: 65.0) -[2023-11-28 01:17:03,445][86177] Avg episode reward: [(0, '-541.640'), (1, '-500.480')] -[2023-11-28 01:17:03,879][87424] Updated weights for policy 0, policy_version 40966 (0.0008) -[2023-11-28 01:17:04,056][87426] Updated weights for policy 1, policy_version 40840 (0.0013) -[2023-11-28 01:17:04,263][87424] Updated weights for policy 0, policy_version 40976 (0.0007) -[2023-11-28 01:17:04,438][87426] Updated weights for policy 1, policy_version 40850 (0.0012) -[2023-11-28 01:17:04,648][87424] Updated weights for policy 0, policy_version 40986 (0.0010) -[2023-11-28 01:17:04,811][87426] Updated weights for policy 1, policy_version 40860 (0.0010) -[2023-11-28 01:17:06,438][87424] Updated weights for policy 0, policy_version 40996 (0.0011) -[2023-11-28 01:17:06,602][87426] Updated weights for policy 1, policy_version 40870 (0.0011) -[2023-11-28 01:17:06,818][87424] Updated weights for policy 0, policy_version 41006 (0.0011) -[2023-11-28 01:17:06,976][87426] Updated weights for policy 1, policy_version 40880 (0.0009) -[2023-11-28 01:17:07,201][87424] Updated weights for policy 0, policy_version 41016 (0.0012) -[2023-11-28 01:17:07,362][87426] Updated weights for policy 1, policy_version 40890 (0.0010) -[2023-11-28 01:17:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 20971520. Throughput: 0: 2648.3, 1: 2758.1. Samples: 20984696. Policy #0 lag: (min: 29.0, avg: 40.0, max: 65.0) -[2023-11-28 01:17:08,445][86177] Avg episode reward: [(0, '-513.960'), (1, '-516.330')] -[2023-11-28 01:17:09,122][87424] Updated weights for policy 0, policy_version 41026 (0.0010) -[2023-11-28 01:17:09,444][87426] Updated weights for policy 1, policy_version 40900 (0.0012) -[2023-11-28 01:17:09,500][87424] Updated weights for policy 0, policy_version 41036 (0.0012) -[2023-11-28 01:17:09,827][87426] Updated weights for policy 1, policy_version 40910 (0.0011) -[2023-11-28 01:17:09,891][87424] Updated weights for policy 0, policy_version 41046 (0.0011) -[2023-11-28 01:17:10,198][87426] Updated weights for policy 1, policy_version 40920 (0.0012) -[2023-11-28 01:17:10,262][87424] Updated weights for policy 0, policy_version 41056 (0.0011) -[2023-11-28 01:17:12,090][87426] Updated weights for policy 1, policy_version 40930 (0.0011) -[2023-11-28 01:17:12,104][87424] Updated weights for policy 0, policy_version 41066 (0.0012) -[2023-11-28 01:17:12,472][87426] Updated weights for policy 1, policy_version 40940 (0.0011) -[2023-11-28 01:17:12,482][87424] Updated weights for policy 0, policy_version 41076 (0.0011) -[2023-11-28 01:17:12,852][87426] Updated weights for policy 1, policy_version 40950 (0.0011) -[2023-11-28 01:17:12,856][87424] Updated weights for policy 0, policy_version 41086 (0.0010) -[2023-11-28 01:17:13,231][87426] Updated weights for policy 1, policy_version 40960 (0.0010) -[2023-11-28 01:17:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 21004288. Throughput: 0: 2641.4, 1: 2763.7. Samples: 21009052. Policy #0 lag: (min: 29.0, avg: 40.0, max: 65.0) -[2023-11-28 01:17:13,445][86177] Avg episode reward: [(0, '-512.450'), (1, '-515.830')] -[2023-11-28 01:17:15,255][87424] Updated weights for policy 0, policy_version 41096 (0.0012) -[2023-11-28 01:17:15,635][87424] Updated weights for policy 0, policy_version 41106 (0.0011) -[2023-11-28 01:17:15,823][87426] Updated weights for policy 1, policy_version 40970 (0.0012) -[2023-11-28 01:17:16,014][87424] Updated weights for policy 0, policy_version 41116 (0.0011) -[2023-11-28 01:17:16,202][87426] Updated weights for policy 1, policy_version 40980 (0.0011) -[2023-11-28 01:17:16,590][87426] Updated weights for policy 1, policy_version 40990 (0.0012) -[2023-11-28 01:17:18,414][87424] Updated weights for policy 0, policy_version 41126 (0.0011) -[2023-11-28 01:17:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 21020672. Throughput: 0: 2647.9, 1: 2777.8. Samples: 21033800. Policy #0 lag: (min: 29.0, avg: 40.0, max: 65.0) -[2023-11-28 01:17:18,445][86177] Avg episode reward: [(0, '-512.990'), (1, '-529.370')] -[2023-11-28 01:17:18,655][87426] Updated weights for policy 1, policy_version 41000 (0.0012) -[2023-11-28 01:17:18,798][87424] Updated weights for policy 0, policy_version 41136 (0.0012) -[2023-11-28 01:17:19,040][87426] Updated weights for policy 1, policy_version 41010 (0.0011) -[2023-11-28 01:17:19,193][87424] Updated weights for policy 0, policy_version 41146 (0.0012) -[2023-11-28 01:17:19,415][87426] Updated weights for policy 1, policy_version 41020 (0.0011) -[2023-11-28 01:17:21,512][87426] Updated weights for policy 1, policy_version 41030 (0.0012) -[2023-11-28 01:17:21,779][87424] Updated weights for policy 0, policy_version 41156 (0.0011) -[2023-11-28 01:17:21,891][87426] Updated weights for policy 1, policy_version 41040 (0.0010) -[2023-11-28 01:17:22,167][87424] Updated weights for policy 0, policy_version 41166 (0.0011) -[2023-11-28 01:17:22,267][87426] Updated weights for policy 1, policy_version 41050 (0.0012) -[2023-11-28 01:17:22,549][87424] Updated weights for policy 0, policy_version 41176 (0.0011) -[2023-11-28 01:17:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 21053440. Throughput: 0: 2668.7, 1: 2754.7. Samples: 21066416. Policy #0 lag: (min: 15.0, avg: 33.3, max: 47.0) -[2023-11-28 01:17:23,445][86177] Avg episode reward: [(0, '-517.350'), (1, '-512.980')] -[2023-11-28 01:17:24,522][87426] Updated weights for policy 1, policy_version 41060 (0.0011) -[2023-11-28 01:17:24,902][87426] Updated weights for policy 1, policy_version 41070 (0.0009) -[2023-11-28 01:17:25,053][87424] Updated weights for policy 0, policy_version 41186 (0.0012) -[2023-11-28 01:17:25,279][87426] Updated weights for policy 1, policy_version 41080 (0.0009) -[2023-11-28 01:17:25,433][87424] Updated weights for policy 0, policy_version 41196 (0.0011) -[2023-11-28 01:17:25,802][87424] Updated weights for policy 0, policy_version 41206 (0.0012) -[2023-11-28 01:17:26,174][87424] Updated weights for policy 0, policy_version 41216 (0.0012) -[2023-11-28 01:17:27,532][87426] Updated weights for policy 1, policy_version 41090 (0.0011) -[2023-11-28 01:17:27,913][87426] Updated weights for policy 1, policy_version 41100 (0.0011) -[2023-11-28 01:17:28,299][87424] Updated weights for policy 0, policy_version 41226 (0.0011) -[2023-11-28 01:17:28,304][87426] Updated weights for policy 1, policy_version 41110 (0.0011) -[2023-11-28 01:17:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 21069824. Throughput: 0: 2670.7, 1: 2783.1. Samples: 21090984. Policy #0 lag: (min: 15.0, avg: 33.3, max: 47.0) -[2023-11-28 01:17:28,445][86177] Avg episode reward: [(0, '-513.060'), (1, '-525.940')] -[2023-11-28 01:17:28,680][87426] Updated weights for policy 1, policy_version 41120 (0.0009) -[2023-11-28 01:17:28,684][87424] Updated weights for policy 0, policy_version 41236 (0.0011) -[2023-11-28 01:17:29,069][87424] Updated weights for policy 0, policy_version 41246 (0.0012) -[2023-11-28 01:17:30,755][87426] Updated weights for policy 1, policy_version 41130 (0.0009) -[2023-11-28 01:17:30,966][87424] Updated weights for policy 0, policy_version 41256 (0.0012) -[2023-11-28 01:17:31,136][87426] Updated weights for policy 1, policy_version 41140 (0.0008) -[2023-11-28 01:17:31,359][87424] Updated weights for policy 0, policy_version 41266 (0.0012) -[2023-11-28 01:17:31,515][87426] Updated weights for policy 1, policy_version 41150 (0.0010) -[2023-11-28 01:17:31,746][87424] Updated weights for policy 0, policy_version 41276 (0.0011) -[2023-11-28 01:17:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 21102592. Throughput: 0: 2682.8, 1: 2770.3. Samples: 21115948. Policy #0 lag: (min: 15.0, avg: 33.3, max: 47.0) -[2023-11-28 01:17:33,445][86177] Avg episode reward: [(0, '-513.050'), (1, '-529.030')] -[2023-11-28 01:17:33,785][87424] Updated weights for policy 0, policy_version 41286 (0.0008) -[2023-11-28 01:17:33,807][87426] Updated weights for policy 1, policy_version 41160 (0.0012) -[2023-11-28 01:17:34,168][87424] Updated weights for policy 0, policy_version 41296 (0.0010) -[2023-11-28 01:17:34,187][87426] Updated weights for policy 1, policy_version 41170 (0.0009) -[2023-11-28 01:17:34,555][87424] Updated weights for policy 0, policy_version 41306 (0.0012) -[2023-11-28 01:17:34,565][87426] Updated weights for policy 1, policy_version 41180 (0.0007) -[2023-11-28 01:17:36,212][87424] Updated weights for policy 0, policy_version 41316 (0.0012) -[2023-11-28 01:17:36,546][87426] Updated weights for policy 1, policy_version 41190 (0.0009) -[2023-11-28 01:17:36,580][87424] Updated weights for policy 0, policy_version 41326 (0.0010) -[2023-11-28 01:17:36,929][87426] Updated weights for policy 1, policy_version 41200 (0.0008) -[2023-11-28 01:17:36,961][87424] Updated weights for policy 0, policy_version 41336 (0.0010) -[2023-11-28 01:17:37,306][87426] Updated weights for policy 1, policy_version 41210 (0.0010) -[2023-11-28 01:17:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 21135360. Throughput: 0: 2714.4, 1: 2739.0. Samples: 21148884. Policy #0 lag: (min: 15.0, avg: 33.3, max: 47.0) -[2023-11-28 01:17:38,445][86177] Avg episode reward: [(0, '-511.230'), (1, '-519.520')] -[2023-11-28 01:17:39,445][87424] Updated weights for policy 0, policy_version 41346 (0.0011) -[2023-11-28 01:17:39,709][87426] Updated weights for policy 1, policy_version 41220 (0.0010) -[2023-11-28 01:17:39,820][87424] Updated weights for policy 0, policy_version 41356 (0.0012) -[2023-11-28 01:17:40,090][87426] Updated weights for policy 1, policy_version 41230 (0.0011) -[2023-11-28 01:17:40,211][87424] Updated weights for policy 0, policy_version 41366 (0.0011) -[2023-11-28 01:17:40,469][87426] Updated weights for policy 1, policy_version 41240 (0.0011) -[2023-11-28 01:17:40,584][87424] Updated weights for policy 0, policy_version 41376 (0.0012) -[2023-11-28 01:17:42,907][87424] Updated weights for policy 0, policy_version 41386 (0.0010) -[2023-11-28 01:17:42,970][87426] Updated weights for policy 1, policy_version 41250 (0.0012) -[2023-11-28 01:17:43,297][87424] Updated weights for policy 0, policy_version 41396 (0.0011) -[2023-11-28 01:17:43,348][87426] Updated weights for policy 1, policy_version 41260 (0.0011) -[2023-11-28 01:17:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 21151744. Throughput: 0: 2730.7, 1: 2727.8. Samples: 21173224. Policy #0 lag: (min: 15.0, avg: 33.3, max: 47.0) -[2023-11-28 01:17:43,445][86177] Avg episode reward: [(0, '-554.880'), (1, '-521.750')] -[2023-11-28 01:17:43,671][87424] Updated weights for policy 0, policy_version 41406 (0.0011) -[2023-11-28 01:17:43,729][87426] Updated weights for policy 1, policy_version 41270 (0.0012) -[2023-11-28 01:17:44,106][87426] Updated weights for policy 1, policy_version 41280 (0.0012) -[2023-11-28 01:17:45,878][87424] Updated weights for policy 0, policy_version 41416 (0.0012) -[2023-11-28 01:17:45,903][87426] Updated weights for policy 1, policy_version 41290 (0.0012) -[2023-11-28 01:17:46,258][87424] Updated weights for policy 0, policy_version 41426 (0.0011) -[2023-11-28 01:17:46,277][87426] Updated weights for policy 1, policy_version 41300 (0.0012) -[2023-11-28 01:17:46,651][87424] Updated weights for policy 0, policy_version 41436 (0.0011) -[2023-11-28 01:17:46,656][87426] Updated weights for policy 1, policy_version 41310 (0.0012) -[2023-11-28 01:17:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21184512. Throughput: 0: 2741.0, 1: 2743.5. Samples: 21198060. Policy #0 lag: (min: 15.0, avg: 33.3, max: 47.0) -[2023-11-28 01:17:48,445][86177] Avg episode reward: [(0, '-575.100'), (1, '-517.840')] -[2023-11-28 01:17:48,610][87426] Updated weights for policy 1, policy_version 41320 (0.0009) -[2023-11-28 01:17:48,927][87424] Updated weights for policy 0, policy_version 41446 (0.0011) -[2023-11-28 01:17:48,987][87426] Updated weights for policy 1, policy_version 41330 (0.0010) -[2023-11-28 01:17:49,313][87424] Updated weights for policy 0, policy_version 41456 (0.0011) -[2023-11-28 01:17:49,369][87426] Updated weights for policy 1, policy_version 41340 (0.0012) -[2023-11-28 01:17:49,688][87424] Updated weights for policy 0, policy_version 41466 (0.0012) -[2023-11-28 01:17:51,484][87426] Updated weights for policy 1, policy_version 41350 (0.0011) -[2023-11-28 01:17:51,858][87426] Updated weights for policy 1, policy_version 41360 (0.0010) -[2023-11-28 01:17:51,965][87424] Updated weights for policy 0, policy_version 41476 (0.0011) -[2023-11-28 01:17:52,236][87426] Updated weights for policy 1, policy_version 41370 (0.0011) -[2023-11-28 01:17:52,342][87424] Updated weights for policy 0, policy_version 41486 (0.0008) -[2023-11-28 01:17:52,734][87424] Updated weights for policy 0, policy_version 41496 (0.0009) -[2023-11-28 01:17:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21217280. Throughput: 0: 2729.0, 1: 2744.3. Samples: 21230992. Policy #0 lag: (min: 31.0, avg: 44.7, max: 72.0) -[2023-11-28 01:17:53,445][86177] Avg episode reward: [(0, '-633.070'), (1, '-522.190')] -[2023-11-28 01:17:54,523][87426] Updated weights for policy 1, policy_version 41380 (0.0011) -[2023-11-28 01:17:54,905][87426] Updated weights for policy 1, policy_version 41390 (0.0012) -[2023-11-28 01:17:54,992][87424] Updated weights for policy 0, policy_version 41506 (0.0011) -[2023-11-28 01:17:55,284][87426] Updated weights for policy 1, policy_version 41400 (0.0008) -[2023-11-28 01:17:55,380][87424] Updated weights for policy 0, policy_version 41516 (0.0011) -[2023-11-28 01:17:55,754][87424] Updated weights for policy 0, policy_version 41526 (0.0011) -[2023-11-28 01:17:56,135][87424] Updated weights for policy 0, policy_version 41536 (0.0011) -[2023-11-28 01:17:57,128][87426] Updated weights for policy 1, policy_version 41410 (0.0008) -[2023-11-28 01:17:57,504][87426] Updated weights for policy 1, policy_version 41420 (0.0010) -[2023-11-28 01:17:57,840][87424] Updated weights for policy 0, policy_version 41546 (0.0011) -[2023-11-28 01:17:57,882][87426] Updated weights for policy 1, policy_version 41430 (0.0011) -[2023-11-28 01:17:58,222][87424] Updated weights for policy 0, policy_version 41556 (0.0012) -[2023-11-28 01:17:58,255][87426] Updated weights for policy 1, policy_version 41440 (0.0010) -[2023-11-28 01:17:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 21241856. Throughput: 0: 2731.6, 1: 2755.1. Samples: 21255952. Policy #0 lag: (min: 31.0, avg: 44.7, max: 72.0) -[2023-11-28 01:17:58,445][86177] Avg episode reward: [(0, '-652.940'), (1, '-518.910')] -[2023-11-28 01:17:58,610][87424] Updated weights for policy 0, policy_version 41566 (0.0012) -[2023-11-28 01:18:00,608][87426] Updated weights for policy 1, policy_version 41450 (0.0010) -[2023-11-28 01:18:00,839][87424] Updated weights for policy 0, policy_version 41576 (0.0008) -[2023-11-28 01:18:00,975][87426] Updated weights for policy 1, policy_version 41460 (0.0010) -[2023-11-28 01:18:01,227][87424] Updated weights for policy 0, policy_version 41586 (0.0008) -[2023-11-28 01:18:01,355][87426] Updated weights for policy 1, policy_version 41470 (0.0008) -[2023-11-28 01:18:01,611][87424] Updated weights for policy 0, policy_version 41596 (0.0008) -[2023-11-28 01:18:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21266432. Throughput: 0: 2739.3, 1: 2722.4. Samples: 21279576. Policy #0 lag: (min: 31.0, avg: 44.7, max: 72.0) -[2023-11-28 01:18:03,445][86177] Avg episode reward: [(0, '-648.480'), (1, '-531.160')] -[2023-11-28 01:18:03,558][87426] Updated weights for policy 1, policy_version 41480 (0.0010) -[2023-11-28 01:18:03,666][87424] Updated weights for policy 0, policy_version 41606 (0.0010) -[2023-11-28 01:18:03,942][87426] Updated weights for policy 1, policy_version 41490 (0.0010) -[2023-11-28 01:18:04,053][87424] Updated weights for policy 0, policy_version 41616 (0.0010) -[2023-11-28 01:18:04,324][87426] Updated weights for policy 1, policy_version 41500 (0.0011) -[2023-11-28 01:18:04,449][87424] Updated weights for policy 0, policy_version 41626 (0.0011) -[2023-11-28 01:18:06,246][87426] Updated weights for policy 1, policy_version 41510 (0.0012) -[2023-11-28 01:18:06,618][87426] Updated weights for policy 1, policy_version 41520 (0.0012) -[2023-11-28 01:18:06,888][87424] Updated weights for policy 0, policy_version 41636 (0.0012) -[2023-11-28 01:18:07,002][87426] Updated weights for policy 1, policy_version 41530 (0.0011) -[2023-11-28 01:18:07,279][87424] Updated weights for policy 0, policy_version 41646 (0.0011) -[2023-11-28 01:18:07,660][87424] Updated weights for policy 0, policy_version 41656 (0.0012) -[2023-11-28 01:18:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21299200. Throughput: 0: 2729.5, 1: 2743.5. Samples: 21312700. Policy #0 lag: (min: 31.0, avg: 44.7, max: 72.0) -[2023-11-28 01:18:08,445][86177] Avg episode reward: [(0, '-618.110'), (1, '-525.530')] -[2023-11-28 01:18:09,169][87426] Updated weights for policy 1, policy_version 41540 (0.0011) -[2023-11-28 01:18:09,539][87426] Updated weights for policy 1, policy_version 41550 (0.0011) -[2023-11-28 01:18:09,613][87424] Updated weights for policy 0, policy_version 41666 (0.0011) -[2023-11-28 01:18:09,922][87426] Updated weights for policy 1, policy_version 41560 (0.0011) -[2023-11-28 01:18:10,002][87424] Updated weights for policy 0, policy_version 41676 (0.0010) -[2023-11-28 01:18:10,383][87424] Updated weights for policy 0, policy_version 41686 (0.0010) -[2023-11-28 01:18:10,757][87424] Updated weights for policy 0, policy_version 41696 (0.0011) -[2023-11-28 01:18:12,292][87426] Updated weights for policy 1, policy_version 41570 (0.0011) -[2023-11-28 01:18:12,682][87426] Updated weights for policy 1, policy_version 41580 (0.0012) -[2023-11-28 01:18:13,065][87426] Updated weights for policy 1, policy_version 41590 (0.0011) -[2023-11-28 01:18:13,112][87424] Updated weights for policy 0, policy_version 41706 (0.0012) -[2023-11-28 01:18:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 21315584. Throughput: 0: 2750.7, 1: 2703.0. Samples: 21336400. Policy #0 lag: (min: 31.0, avg: 44.7, max: 72.0) -[2023-11-28 01:18:13,445][86177] Avg episode reward: [(0, '-617.180'), (1, '-523.050')] -[2023-11-28 01:18:13,450][87426] Updated weights for policy 1, policy_version 41600 (0.0010) -[2023-11-28 01:18:13,498][87424] Updated weights for policy 0, policy_version 41716 (0.0011) -[2023-11-28 01:18:13,882][87424] Updated weights for policy 0, policy_version 41726 (0.0012) -[2023-11-28 01:18:15,815][87426] Updated weights for policy 1, policy_version 41610 (0.0012) -[2023-11-28 01:18:16,191][87426] Updated weights for policy 1, policy_version 41620 (0.0012) -[2023-11-28 01:18:16,407][87424] Updated weights for policy 0, policy_version 41736 (0.0010) -[2023-11-28 01:18:16,573][87426] Updated weights for policy 1, policy_version 41630 (0.0012) -[2023-11-28 01:18:16,800][87424] Updated weights for policy 0, policy_version 41746 (0.0007) -[2023-11-28 01:18:17,187][87424] Updated weights for policy 0, policy_version 41756 (0.0007) -[2023-11-28 01:18:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 21348352. Throughput: 0: 2725.9, 1: 2711.5. Samples: 21360632. Policy #0 lag: (min: 25.0, avg: 46.2, max: 61.0) -[2023-11-28 01:18:18,446][86177] Avg episode reward: [(0, '-557.970'), (1, '-548.970')] -[2023-11-28 01:18:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000041632_10657792.pth... -[2023-11-28 01:18:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000041760_10690560.pth... -[2023-11-28 01:18:18,488][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000039104_10010624.pth -[2023-11-28 01:18:18,495][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000039232_10043392.pth -[2023-11-28 01:18:18,963][87426] Updated weights for policy 1, policy_version 41640 (0.0011) -[2023-11-28 01:18:19,279][87424] Updated weights for policy 0, policy_version 41766 (0.0010) -[2023-11-28 01:18:19,343][87426] Updated weights for policy 1, policy_version 41650 (0.0009) -[2023-11-28 01:18:19,659][87424] Updated weights for policy 0, policy_version 41776 (0.0010) -[2023-11-28 01:18:19,722][87426] Updated weights for policy 1, policy_version 41660 (0.0011) -[2023-11-28 01:18:20,041][87424] Updated weights for policy 0, policy_version 41786 (0.0011) -[2023-11-28 01:18:22,179][87426] Updated weights for policy 1, policy_version 41670 (0.0011) -[2023-11-28 01:18:22,417][87424] Updated weights for policy 0, policy_version 41796 (0.0012) -[2023-11-28 01:18:22,558][87426] Updated weights for policy 1, policy_version 41680 (0.0011) -[2023-11-28 01:18:22,793][87424] Updated weights for policy 0, policy_version 41806 (0.0012) -[2023-11-28 01:18:22,932][87426] Updated weights for policy 1, policy_version 41690 (0.0009) -[2023-11-28 01:18:23,176][87424] Updated weights for policy 0, policy_version 41816 (0.0011) -[2023-11-28 01:18:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 21372928. Throughput: 0: 2702.6, 1: 2723.4. Samples: 21393052. Policy #0 lag: (min: 25.0, avg: 46.2, max: 61.0) -[2023-11-28 01:18:23,445][86177] Avg episode reward: [(0, '-567.450'), (1, '-540.920')] -[2023-11-28 01:18:25,065][87424] Updated weights for policy 0, policy_version 41826 (0.0011) -[2023-11-28 01:18:25,127][87426] Updated weights for policy 1, policy_version 41700 (0.0009) -[2023-11-28 01:18:25,452][87424] Updated weights for policy 0, policy_version 41836 (0.0011) -[2023-11-28 01:18:25,506][87426] Updated weights for policy 1, policy_version 41710 (0.0012) -[2023-11-28 01:18:25,830][87424] Updated weights for policy 0, policy_version 41846 (0.0011) -[2023-11-28 01:18:25,897][87426] Updated weights for policy 1, policy_version 41720 (0.0012) -[2023-11-28 01:18:26,214][87424] Updated weights for policy 0, policy_version 41856 (0.0012) -[2023-11-28 01:18:28,041][87424] Updated weights for policy 0, policy_version 41866 (0.0012) -[2023-11-28 01:18:28,162][87426] Updated weights for policy 1, policy_version 41730 (0.0011) -[2023-11-28 01:18:28,429][87424] Updated weights for policy 0, policy_version 41876 (0.0011) -[2023-11-28 01:18:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21397504. Throughput: 0: 2702.0, 1: 2724.8. Samples: 21417428. Policy #0 lag: (min: 25.0, avg: 46.2, max: 61.0) -[2023-11-28 01:18:28,445][86177] Avg episode reward: [(0, '-568.070'), (1, '-533.730')] -[2023-11-28 01:18:28,545][87426] Updated weights for policy 1, policy_version 41740 (0.0011) -[2023-11-28 01:18:28,798][87424] Updated weights for policy 0, policy_version 41886 (0.0011) -[2023-11-28 01:18:28,922][87426] Updated weights for policy 1, policy_version 41750 (0.0011) -[2023-11-28 01:18:29,308][87426] Updated weights for policy 1, policy_version 41760 (0.0007) -[2023-11-28 01:18:31,289][87426] Updated weights for policy 1, policy_version 41770 (0.0007) -[2023-11-28 01:18:31,383][87424] Updated weights for policy 0, policy_version 41896 (0.0009) -[2023-11-28 01:18:31,667][87426] Updated weights for policy 1, policy_version 41780 (0.0010) -[2023-11-28 01:18:31,758][87424] Updated weights for policy 0, policy_version 41906 (0.0012) -[2023-11-28 01:18:32,038][87426] Updated weights for policy 1, policy_version 41790 (0.0011) -[2023-11-28 01:18:32,139][87424] Updated weights for policy 0, policy_version 41916 (0.0012) -[2023-11-28 01:18:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21430272. Throughput: 0: 2691.8, 1: 2714.4. Samples: 21441340. Policy #0 lag: (min: 25.0, avg: 46.2, max: 61.0) -[2023-11-28 01:18:33,445][86177] Avg episode reward: [(0, '-572.150'), (1, '-521.540')] -[2023-11-28 01:18:34,098][87424] Updated weights for policy 0, policy_version 41926 (0.0011) -[2023-11-28 01:18:34,359][87426] Updated weights for policy 1, policy_version 41800 (0.0010) -[2023-11-28 01:18:34,472][87424] Updated weights for policy 0, policy_version 41936 (0.0010) -[2023-11-28 01:18:34,742][87426] Updated weights for policy 1, policy_version 41810 (0.0012) -[2023-11-28 01:18:34,849][87424] Updated weights for policy 0, policy_version 41946 (0.0008) -[2023-11-28 01:18:35,125][87426] Updated weights for policy 1, policy_version 41820 (0.0012) -[2023-11-28 01:18:36,826][87426] Updated weights for policy 1, policy_version 41830 (0.0012) -[2023-11-28 01:18:37,163][87424] Updated weights for policy 0, policy_version 41956 (0.0009) -[2023-11-28 01:18:37,203][87426] Updated weights for policy 1, policy_version 41840 (0.0011) -[2023-11-28 01:18:37,551][87424] Updated weights for policy 0, policy_version 41966 (0.0009) -[2023-11-28 01:18:37,580][87426] Updated weights for policy 1, policy_version 41850 (0.0011) -[2023-11-28 01:18:37,922][87424] Updated weights for policy 0, policy_version 41976 (0.0010) -[2023-11-28 01:18:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 21463040. Throughput: 0: 2695.6, 1: 2754.2. Samples: 21476236. Policy #0 lag: (min: 25.0, avg: 46.2, max: 61.0) -[2023-11-28 01:18:38,445][86177] Avg episode reward: [(0, '-614.020'), (1, '-507.260')] -[2023-11-28 01:18:39,400][87426] Updated weights for policy 1, policy_version 41860 (0.0008) -[2023-11-28 01:18:39,697][87424] Updated weights for policy 0, policy_version 41986 (0.0008) -[2023-11-28 01:18:39,782][87426] Updated weights for policy 1, policy_version 41870 (0.0009) -[2023-11-28 01:18:40,076][87424] Updated weights for policy 0, policy_version 41996 (0.0012) -[2023-11-28 01:18:40,158][87426] Updated weights for policy 1, policy_version 41880 (0.0010) -[2023-11-28 01:18:40,447][87424] Updated weights for policy 0, policy_version 42006 (0.0010) -[2023-11-28 01:18:40,829][87424] Updated weights for policy 0, policy_version 42016 (0.0008) -[2023-11-28 01:18:42,424][87426] Updated weights for policy 1, policy_version 41890 (0.0011) -[2023-11-28 01:18:42,806][87426] Updated weights for policy 1, policy_version 41900 (0.0010) -[2023-11-28 01:18:43,199][87426] Updated weights for policy 1, policy_version 41910 (0.0011) -[2023-11-28 01:18:43,307][87424] Updated weights for policy 0, policy_version 42026 (0.0010) -[2023-11-28 01:18:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21479424. Throughput: 0: 2689.8, 1: 2753.3. Samples: 21500892. Policy #0 lag: (min: 25.0, avg: 46.2, max: 61.0) -[2023-11-28 01:18:43,445][86177] Avg episode reward: [(0, '-586.660'), (1, '-512.960')] -[2023-11-28 01:18:43,575][87426] Updated weights for policy 1, policy_version 41920 (0.0011) -[2023-11-28 01:18:43,689][87424] Updated weights for policy 0, policy_version 42036 (0.0010) -[2023-11-28 01:18:44,078][87424] Updated weights for policy 0, policy_version 42046 (0.0012) -[2023-11-28 01:18:45,578][87426] Updated weights for policy 1, policy_version 41930 (0.0010) -[2023-11-28 01:18:45,959][87426] Updated weights for policy 1, policy_version 41940 (0.0011) -[2023-11-28 01:18:46,341][87426] Updated weights for policy 1, policy_version 41950 (0.0008) -[2023-11-28 01:18:46,610][87424] Updated weights for policy 0, policy_version 42056 (0.0011) -[2023-11-28 01:18:46,997][87424] Updated weights for policy 0, policy_version 42066 (0.0012) -[2023-11-28 01:18:47,381][87424] Updated weights for policy 0, policy_version 42076 (0.0012) -[2023-11-28 01:18:48,427][87426] Updated weights for policy 1, policy_version 41960 (0.0011) -[2023-11-28 01:18:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 21512192. Throughput: 0: 2676.7, 1: 2760.8. Samples: 21524264. Policy #0 lag: (min: 31.0, avg: 48.5, max: 63.0) -[2023-11-28 01:18:48,445][86177] Avg episode reward: [(0, '-664.420'), (1, '-523.480')] -[2023-11-28 01:18:48,795][87426] Updated weights for policy 1, policy_version 41970 (0.0012) -[2023-11-28 01:18:49,192][87426] Updated weights for policy 1, policy_version 41980 (0.0010) -[2023-11-28 01:18:49,594][87424] Updated weights for policy 0, policy_version 42086 (0.0012) -[2023-11-28 01:18:49,973][87424] Updated weights for policy 0, policy_version 42096 (0.0010) -[2023-11-28 01:18:50,373][87424] Updated weights for policy 0, policy_version 42106 (0.0008) -[2023-11-28 01:18:51,206][87426] Updated weights for policy 1, policy_version 41990 (0.0009) -[2023-11-28 01:18:51,583][87426] Updated weights for policy 1, policy_version 42000 (0.0012) -[2023-11-28 01:18:51,967][87426] Updated weights for policy 1, policy_version 42010 (0.0012) -[2023-11-28 01:18:52,432][87424] Updated weights for policy 0, policy_version 42116 (0.0008) -[2023-11-28 01:18:52,807][87424] Updated weights for policy 0, policy_version 42126 (0.0011) -[2023-11-28 01:18:53,188][87424] Updated weights for policy 0, policy_version 42136 (0.0010) -[2023-11-28 01:18:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 21536768. Throughput: 0: 2674.2, 1: 2743.6. Samples: 21556500. Policy #0 lag: (min: 31.0, avg: 48.5, max: 63.0) -[2023-11-28 01:18:53,445][86177] Avg episode reward: [(0, '-664.130'), (1, '-527.550')] -[2023-11-28 01:18:54,309][87426] Updated weights for policy 1, policy_version 42020 (0.0011) -[2023-11-28 01:18:54,692][87426] Updated weights for policy 1, policy_version 42030 (0.0011) -[2023-11-28 01:18:55,072][87426] Updated weights for policy 1, policy_version 42040 (0.0009) -[2023-11-28 01:18:55,514][87424] Updated weights for policy 0, policy_version 42146 (0.0011) -[2023-11-28 01:18:55,904][87424] Updated weights for policy 0, policy_version 42156 (0.0012) -[2023-11-28 01:18:56,288][87424] Updated weights for policy 0, policy_version 42166 (0.0011) -[2023-11-28 01:18:56,672][87424] Updated weights for policy 0, policy_version 42176 (0.0012) -[2023-11-28 01:18:57,426][87426] Updated weights for policy 1, policy_version 42050 (0.0008) -[2023-11-28 01:18:57,803][87426] Updated weights for policy 1, policy_version 42060 (0.0010) -[2023-11-28 01:18:58,179][87426] Updated weights for policy 1, policy_version 42070 (0.0011) -[2023-11-28 01:18:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 21561344. Throughput: 0: 2685.9, 1: 2753.0. Samples: 21581148. Policy #0 lag: (min: 31.0, avg: 48.5, max: 63.0) -[2023-11-28 01:18:58,445][86177] Avg episode reward: [(0, '-649.150'), (1, '-535.520')] -[2023-11-28 01:18:58,558][87426] Updated weights for policy 1, policy_version 42080 (0.0011) -[2023-11-28 01:18:58,671][87424] Updated weights for policy 0, policy_version 42186 (0.0012) -[2023-11-28 01:18:59,049][87424] Updated weights for policy 0, policy_version 42196 (0.0010) -[2023-11-28 01:18:59,432][87424] Updated weights for policy 0, policy_version 42206 (0.0008) -[2023-11-28 01:19:00,972][87426] Updated weights for policy 1, policy_version 42090 (0.0012) -[2023-11-28 01:19:01,228][87424] Updated weights for policy 0, policy_version 42216 (0.0008) -[2023-11-28 01:19:01,353][87426] Updated weights for policy 1, policy_version 42100 (0.0012) -[2023-11-28 01:19:01,613][87424] Updated weights for policy 0, policy_version 42226 (0.0008) -[2023-11-28 01:19:01,737][87426] Updated weights for policy 1, policy_version 42110 (0.0011) -[2023-11-28 01:19:01,987][87424] Updated weights for policy 0, policy_version 42236 (0.0011) -[2023-11-28 01:19:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 21594112. Throughput: 0: 2737.3, 1: 2729.7. Samples: 21606644. Policy #0 lag: (min: 31.0, avg: 48.5, max: 63.0) -[2023-11-28 01:19:03,445][86177] Avg episode reward: [(0, '-692.610'), (1, '-534.270')] -[2023-11-28 01:19:03,663][87426] Updated weights for policy 1, policy_version 42120 (0.0010) -[2023-11-28 01:19:04,006][87424] Updated weights for policy 0, policy_version 42246 (0.0010) -[2023-11-28 01:19:04,052][87426] Updated weights for policy 1, policy_version 42130 (0.0011) -[2023-11-28 01:19:04,393][87424] Updated weights for policy 0, policy_version 42256 (0.0008) -[2023-11-28 01:19:04,428][87426] Updated weights for policy 1, policy_version 42140 (0.0011) -[2023-11-28 01:19:04,775][87424] Updated weights for policy 0, policy_version 42266 (0.0008) -[2023-11-28 01:19:06,830][87426] Updated weights for policy 1, policy_version 42150 (0.0011) -[2023-11-28 01:19:07,208][87426] Updated weights for policy 1, policy_version 42160 (0.0011) -[2023-11-28 01:19:07,266][87424] Updated weights for policy 0, policy_version 42276 (0.0009) -[2023-11-28 01:19:07,587][87426] Updated weights for policy 1, policy_version 42170 (0.0012) -[2023-11-28 01:19:07,648][87424] Updated weights for policy 0, policy_version 42286 (0.0011) -[2023-11-28 01:19:08,032][87424] Updated weights for policy 0, policy_version 42296 (0.0012) -[2023-11-28 01:19:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 21626880. Throughput: 0: 2761.7, 1: 2724.8. Samples: 21639944. Policy #0 lag: (min: 31.0, avg: 48.5, max: 63.0) -[2023-11-28 01:19:08,445][86177] Avg episode reward: [(0, '-652.540'), (1, '-530.120')] -[2023-11-28 01:19:09,966][87426] Updated weights for policy 1, policy_version 42180 (0.0011) -[2023-11-28 01:19:10,144][87424] Updated weights for policy 0, policy_version 42306 (0.0011) -[2023-11-28 01:19:10,339][87426] Updated weights for policy 1, policy_version 42190 (0.0009) -[2023-11-28 01:19:10,530][87424] Updated weights for policy 0, policy_version 42316 (0.0009) -[2023-11-28 01:19:10,723][87426] Updated weights for policy 1, policy_version 42200 (0.0011) -[2023-11-28 01:19:10,914][87424] Updated weights for policy 0, policy_version 42326 (0.0010) -[2023-11-28 01:19:11,286][87424] Updated weights for policy 0, policy_version 42336 (0.0012) -[2023-11-28 01:19:12,618][87426] Updated weights for policy 1, policy_version 42210 (0.0011) -[2023-11-28 01:19:12,993][87426] Updated weights for policy 1, policy_version 42220 (0.0012) -[2023-11-28 01:19:13,348][87424] Updated weights for policy 0, policy_version 42346 (0.0012) -[2023-11-28 01:19:13,376][87426] Updated weights for policy 1, policy_version 42230 (0.0012) -[2023-11-28 01:19:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21643264. Throughput: 0: 2738.2, 1: 2734.1. Samples: 21663684. Policy #0 lag: (min: 31.0, avg: 48.5, max: 63.0) -[2023-11-28 01:19:13,445][86177] Avg episode reward: [(0, '-618.220'), (1, '-528.390')] -[2023-11-28 01:19:13,738][87424] Updated weights for policy 0, policy_version 42356 (0.0009) -[2023-11-28 01:19:13,747][87426] Updated weights for policy 1, policy_version 42240 (0.0011) -[2023-11-28 01:19:14,115][87424] Updated weights for policy 0, policy_version 42366 (0.0011) -[2023-11-28 01:19:16,109][87424] Updated weights for policy 0, policy_version 42376 (0.0012) -[2023-11-28 01:19:16,172][87426] Updated weights for policy 1, policy_version 42250 (0.0012) -[2023-11-28 01:19:16,489][87424] Updated weights for policy 0, policy_version 42386 (0.0012) -[2023-11-28 01:19:16,542][87426] Updated weights for policy 1, policy_version 42260 (0.0011) -[2023-11-28 01:19:16,867][87424] Updated weights for policy 0, policy_version 42396 (0.0011) -[2023-11-28 01:19:16,925][87426] Updated weights for policy 1, policy_version 42270 (0.0009) -[2023-11-28 01:19:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 21676032. Throughput: 0: 2737.2, 1: 2744.6. Samples: 21688024. Policy #0 lag: (min: 2.0, avg: 31.5, max: 59.0) -[2023-11-28 01:19:18,445][86177] Avg episode reward: [(0, '-596.050'), (1, '-516.160')] -[2023-11-28 01:19:18,889][87424] Updated weights for policy 0, policy_version 42406 (0.0010) -[2023-11-28 01:19:19,128][87426] Updated weights for policy 1, policy_version 42280 (0.0010) -[2023-11-28 01:19:19,266][87424] Updated weights for policy 0, policy_version 42416 (0.0009) -[2023-11-28 01:19:19,507][87426] Updated weights for policy 1, policy_version 42290 (0.0011) -[2023-11-28 01:19:19,651][87424] Updated weights for policy 0, policy_version 42426 (0.0007) -[2023-11-28 01:19:19,875][87426] Updated weights for policy 1, policy_version 42300 (0.0011) -[2023-11-28 01:19:21,709][87424] Updated weights for policy 0, policy_version 42436 (0.0011) -[2023-11-28 01:19:22,095][87424] Updated weights for policy 0, policy_version 42446 (0.0012) -[2023-11-28 01:19:22,312][87426] Updated weights for policy 1, policy_version 42310 (0.0011) -[2023-11-28 01:19:22,489][87424] Updated weights for policy 0, policy_version 42456 (0.0011) -[2023-11-28 01:19:22,681][87426] Updated weights for policy 1, policy_version 42320 (0.0010) -[2023-11-28 01:19:23,065][87426] Updated weights for policy 1, policy_version 42330 (0.0012) -[2023-11-28 01:19:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 21708800. Throughput: 0: 2738.0, 1: 2694.8. Samples: 21720708. Policy #0 lag: (min: 2.0, avg: 31.5, max: 59.0) -[2023-11-28 01:19:23,445][86177] Avg episode reward: [(0, '-550.550'), (1, '-512.500')] -[2023-11-28 01:19:24,466][87424] Updated weights for policy 0, policy_version 42466 (0.0011) -[2023-11-28 01:19:24,845][87424] Updated weights for policy 0, policy_version 42476 (0.0009) -[2023-11-28 01:19:25,230][87424] Updated weights for policy 0, policy_version 42486 (0.0009) -[2023-11-28 01:19:25,264][87426] Updated weights for policy 1, policy_version 42340 (0.0011) -[2023-11-28 01:19:25,623][87424] Updated weights for policy 0, policy_version 42496 (0.0008) -[2023-11-28 01:19:25,645][87426] Updated weights for policy 1, policy_version 42350 (0.0011) -[2023-11-28 01:19:26,039][87426] Updated weights for policy 1, policy_version 42360 (0.0007) -[2023-11-28 01:19:27,991][87424] Updated weights for policy 0, policy_version 42506 (0.0007) -[2023-11-28 01:19:28,382][87424] Updated weights for policy 0, policy_version 42516 (0.0007) -[2023-11-28 01:19:28,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 21725184. Throughput: 0: 2747.9, 1: 2661.8. Samples: 21744332. Policy #0 lag: (min: 2.0, avg: 31.5, max: 59.0) -[2023-11-28 01:19:28,446][86177] Avg episode reward: [(0, '-596.950'), (1, '-515.020')] -[2023-11-28 01:19:28,512][87426] Updated weights for policy 1, policy_version 42370 (0.0007) -[2023-11-28 01:19:28,755][87424] Updated weights for policy 0, policy_version 42526 (0.0008) -[2023-11-28 01:19:28,882][87426] Updated weights for policy 1, policy_version 42380 (0.0010) -[2023-11-28 01:19:29,255][87426] Updated weights for policy 1, policy_version 42390 (0.0008) -[2023-11-28 01:19:29,638][87426] Updated weights for policy 1, policy_version 42400 (0.0009) -[2023-11-28 01:19:30,975][87424] Updated weights for policy 0, policy_version 42536 (0.0011) -[2023-11-28 01:19:31,360][87424] Updated weights for policy 0, policy_version 42546 (0.0012) -[2023-11-28 01:19:31,746][87424] Updated weights for policy 0, policy_version 42556 (0.0009) -[2023-11-28 01:19:31,943][87426] Updated weights for policy 1, policy_version 42410 (0.0010) -[2023-11-28 01:19:32,328][87426] Updated weights for policy 1, policy_version 42420 (0.0009) -[2023-11-28 01:19:32,712][87426] Updated weights for policy 1, policy_version 42430 (0.0012) -[2023-11-28 01:19:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 21757952. Throughput: 0: 2773.9, 1: 2670.1. Samples: 21769244. Policy #0 lag: (min: 2.0, avg: 31.5, max: 59.0) -[2023-11-28 01:19:33,445][86177] Avg episode reward: [(0, '-560.390'), (1, '-534.110')] -[2023-11-28 01:19:33,894][87424] Updated weights for policy 0, policy_version 42566 (0.0011) -[2023-11-28 01:19:34,276][87424] Updated weights for policy 0, policy_version 42576 (0.0008) -[2023-11-28 01:19:34,518][87426] Updated weights for policy 1, policy_version 42440 (0.0011) -[2023-11-28 01:19:34,650][87424] Updated weights for policy 0, policy_version 42586 (0.0007) -[2023-11-28 01:19:34,887][87426] Updated weights for policy 1, policy_version 42450 (0.0009) -[2023-11-28 01:19:35,268][87426] Updated weights for policy 1, policy_version 42460 (0.0010) -[2023-11-28 01:19:36,766][87424] Updated weights for policy 0, policy_version 42596 (0.0010) -[2023-11-28 01:19:37,150][87424] Updated weights for policy 0, policy_version 42606 (0.0008) -[2023-11-28 01:19:37,541][87424] Updated weights for policy 0, policy_version 42616 (0.0008) -[2023-11-28 01:19:37,838][87426] Updated weights for policy 1, policy_version 42470 (0.0011) -[2023-11-28 01:19:38,229][87426] Updated weights for policy 1, policy_version 42480 (0.0012) -[2023-11-28 01:19:38,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 21782528. Throughput: 0: 2783.4, 1: 2659.7. Samples: 21801440. Policy #0 lag: (min: 2.0, avg: 31.5, max: 59.0) -[2023-11-28 01:19:38,445][86177] Avg episode reward: [(0, '-581.420'), (1, '-528.050')] -[2023-11-28 01:19:38,610][87426] Updated weights for policy 1, policy_version 42490 (0.0011) -[2023-11-28 01:19:40,077][87424] Updated weights for policy 0, policy_version 42626 (0.0007) -[2023-11-28 01:19:40,464][87424] Updated weights for policy 0, policy_version 42636 (0.0009) -[2023-11-28 01:19:40,842][87424] Updated weights for policy 0, policy_version 42646 (0.0009) -[2023-11-28 01:19:41,137][87426] Updated weights for policy 1, policy_version 42500 (0.0012) -[2023-11-28 01:19:41,227][87424] Updated weights for policy 0, policy_version 42656 (0.0008) -[2023-11-28 01:19:41,518][87426] Updated weights for policy 1, policy_version 42510 (0.0011) -[2023-11-28 01:19:41,901][87426] Updated weights for policy 1, policy_version 42520 (0.0009) -[2023-11-28 01:19:43,213][87424] Updated weights for policy 0, policy_version 42666 (0.0010) -[2023-11-28 01:19:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21807104. Throughput: 0: 2756.3, 1: 2644.4. Samples: 21824184. Policy #0 lag: (min: 2.0, avg: 31.5, max: 59.0) -[2023-11-28 01:19:43,445][86177] Avg episode reward: [(0, '-684.060'), (1, '-528.050')] -[2023-11-28 01:19:43,590][87424] Updated weights for policy 0, policy_version 42676 (0.0010) -[2023-11-28 01:19:43,959][87424] Updated weights for policy 0, policy_version 42686 (0.0011) -[2023-11-28 01:19:44,392][87426] Updated weights for policy 1, policy_version 42530 (0.0010) -[2023-11-28 01:19:44,772][87426] Updated weights for policy 1, policy_version 42540 (0.0010) -[2023-11-28 01:19:45,153][87426] Updated weights for policy 1, policy_version 42550 (0.0009) -[2023-11-28 01:19:45,525][87426] Updated weights for policy 1, policy_version 42560 (0.0011) -[2023-11-28 01:19:46,069][87424] Updated weights for policy 0, policy_version 42696 (0.0009) -[2023-11-28 01:19:46,456][87424] Updated weights for policy 0, policy_version 42706 (0.0008) -[2023-11-28 01:19:46,839][87424] Updated weights for policy 0, policy_version 42716 (0.0008) -[2023-11-28 01:19:47,593][87426] Updated weights for policy 1, policy_version 42570 (0.0012) -[2023-11-28 01:19:47,973][87426] Updated weights for policy 1, policy_version 42580 (0.0012) -[2023-11-28 01:19:48,362][87426] Updated weights for policy 1, policy_version 42590 (0.0010) -[2023-11-28 01:19:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 21839872. Throughput: 0: 2710.1, 1: 2649.0. Samples: 21847804. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:19:48,445][86177] Avg episode reward: [(0, '-636.450'), (1, '-532.940')] -[2023-11-28 01:19:49,312][87424] Updated weights for policy 0, policy_version 42726 (0.0007) -[2023-11-28 01:19:49,697][87424] Updated weights for policy 0, policy_version 42736 (0.0007) -[2023-11-28 01:19:50,079][87424] Updated weights for policy 0, policy_version 42746 (0.0009) -[2023-11-28 01:19:50,665][87426] Updated weights for policy 1, policy_version 42600 (0.0007) -[2023-11-28 01:19:51,049][87426] Updated weights for policy 1, policy_version 42610 (0.0007) -[2023-11-28 01:19:51,427][87426] Updated weights for policy 1, policy_version 42620 (0.0011) -[2023-11-28 01:19:52,282][87424] Updated weights for policy 0, policy_version 42756 (0.0009) -[2023-11-28 01:19:52,651][87424] Updated weights for policy 0, policy_version 42766 (0.0009) -[2023-11-28 01:19:53,034][87424] Updated weights for policy 0, policy_version 42776 (0.0009) -[2023-11-28 01:19:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 21864448. Throughput: 0: 2681.2, 1: 2638.8. Samples: 21879344. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:19:53,445][86177] Avg episode reward: [(0, '-668.050'), (1, '-526.840')] -[2023-11-28 01:19:53,749][87426] Updated weights for policy 1, policy_version 42630 (0.0010) -[2023-11-28 01:19:54,128][87426] Updated weights for policy 1, policy_version 42640 (0.0008) -[2023-11-28 01:19:54,515][87426] Updated weights for policy 1, policy_version 42650 (0.0010) -[2023-11-28 01:19:55,037][87424] Updated weights for policy 0, policy_version 42786 (0.0011) -[2023-11-28 01:19:55,424][87424] Updated weights for policy 0, policy_version 42796 (0.0007) -[2023-11-28 01:19:55,807][87424] Updated weights for policy 0, policy_version 42806 (0.0007) -[2023-11-28 01:19:56,186][87424] Updated weights for policy 0, policy_version 42816 (0.0010) -[2023-11-28 01:19:56,455][87426] Updated weights for policy 1, policy_version 42660 (0.0011) -[2023-11-28 01:19:56,838][87426] Updated weights for policy 1, policy_version 42670 (0.0011) -[2023-11-28 01:19:57,220][87426] Updated weights for policy 1, policy_version 42680 (0.0012) -[2023-11-28 01:19:58,050][87424] Updated weights for policy 0, policy_version 42826 (0.0011) -[2023-11-28 01:19:58,435][87424] Updated weights for policy 0, policy_version 42836 (0.0012) -[2023-11-28 01:19:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 21889024. Throughput: 0: 2699.3, 1: 2638.6. Samples: 21903888. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:19:58,446][86177] Avg episode reward: [(0, '-685.740'), (1, '-529.950')] -[2023-11-28 01:19:58,817][87424] Updated weights for policy 0, policy_version 42846 (0.0012) -[2023-11-28 01:19:59,180][87426] Updated weights for policy 1, policy_version 42690 (0.0010) -[2023-11-28 01:19:59,561][87426] Updated weights for policy 1, policy_version 42700 (0.0010) -[2023-11-28 01:19:59,952][87426] Updated weights for policy 1, policy_version 42710 (0.0009) -[2023-11-28 01:20:00,326][87426] Updated weights for policy 1, policy_version 42720 (0.0012) -[2023-11-28 01:20:00,993][87424] Updated weights for policy 0, policy_version 42856 (0.0012) -[2023-11-28 01:20:01,378][87424] Updated weights for policy 0, policy_version 42866 (0.0012) -[2023-11-28 01:20:01,764][87424] Updated weights for policy 0, policy_version 42876 (0.0012) -[2023-11-28 01:20:02,767][87426] Updated weights for policy 1, policy_version 42730 (0.0011) -[2023-11-28 01:20:03,149][87426] Updated weights for policy 1, policy_version 42740 (0.0008) -[2023-11-28 01:20:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 21913600. Throughput: 0: 2724.2, 1: 2635.3. Samples: 21929200. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:20:03,445][86177] Avg episode reward: [(0, '-610.970'), (1, '-558.310')] -[2023-11-28 01:20:03,530][87426] Updated weights for policy 1, policy_version 42750 (0.0007) -[2023-11-28 01:20:03,821][87424] Updated weights for policy 0, policy_version 42886 (0.0009) -[2023-11-28 01:20:04,203][87424] Updated weights for policy 0, policy_version 42896 (0.0007) -[2023-11-28 01:20:04,591][87424] Updated weights for policy 0, policy_version 42906 (0.0007) -[2023-11-28 01:20:05,744][87426] Updated weights for policy 1, policy_version 42760 (0.0009) -[2023-11-28 01:20:06,121][87426] Updated weights for policy 1, policy_version 42770 (0.0007) -[2023-11-28 01:20:06,506][87426] Updated weights for policy 1, policy_version 42780 (0.0007) -[2023-11-28 01:20:06,986][87424] Updated weights for policy 0, policy_version 42916 (0.0010) -[2023-11-28 01:20:07,372][87424] Updated weights for policy 0, policy_version 42926 (0.0009) -[2023-11-28 01:20:07,751][87424] Updated weights for policy 0, policy_version 42936 (0.0009) -[2023-11-28 01:20:08,411][87426] Updated weights for policy 1, policy_version 42790 (0.0010) -[2023-11-28 01:20:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 21946368. Throughput: 0: 2712.1, 1: 2646.0. Samples: 21961820. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:20:08,445][86177] Avg episode reward: [(0, '-611.900'), (1, '-570.920')] -[2023-11-28 01:20:08,790][87426] Updated weights for policy 1, policy_version 42800 (0.0012) -[2023-11-28 01:20:09,168][87426] Updated weights for policy 1, policy_version 42810 (0.0010) -[2023-11-28 01:20:10,008][87424] Updated weights for policy 0, policy_version 42946 (0.0008) -[2023-11-28 01:20:10,387][87424] Updated weights for policy 0, policy_version 42956 (0.0012) -[2023-11-28 01:20:10,769][87424] Updated weights for policy 0, policy_version 42966 (0.0012) -[2023-11-28 01:20:11,156][87424] Updated weights for policy 0, policy_version 42976 (0.0012) -[2023-11-28 01:20:11,673][87426] Updated weights for policy 1, policy_version 42820 (0.0009) -[2023-11-28 01:20:12,050][87426] Updated weights for policy 1, policy_version 42830 (0.0012) -[2023-11-28 01:20:12,433][87426] Updated weights for policy 1, policy_version 42840 (0.0011) -[2023-11-28 01:20:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 21970944. Throughput: 0: 2698.2, 1: 2648.6. Samples: 21984932. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:20:13,445][86177] Avg episode reward: [(0, '-586.450'), (1, '-555.800')] -[2023-11-28 01:20:13,705][87424] Updated weights for policy 0, policy_version 42986 (0.0008) -[2023-11-28 01:20:14,087][87424] Updated weights for policy 0, policy_version 42996 (0.0008) -[2023-11-28 01:20:14,481][87424] Updated weights for policy 0, policy_version 43006 (0.0007) -[2023-11-28 01:20:14,825][87426] Updated weights for policy 1, policy_version 42850 (0.0011) -[2023-11-28 01:20:15,203][87426] Updated weights for policy 1, policy_version 42860 (0.0009) -[2023-11-28 01:20:15,600][87426] Updated weights for policy 1, policy_version 42870 (0.0011) -[2023-11-28 01:20:15,969][87426] Updated weights for policy 1, policy_version 42880 (0.0008) -[2023-11-28 01:20:16,602][87424] Updated weights for policy 0, policy_version 43016 (0.0011) -[2023-11-28 01:20:16,988][87424] Updated weights for policy 0, policy_version 43026 (0.0012) -[2023-11-28 01:20:17,370][87424] Updated weights for policy 0, policy_version 43036 (0.0012) -[2023-11-28 01:20:17,999][87426] Updated weights for policy 1, policy_version 42890 (0.0012) -[2023-11-28 01:20:18,374][87426] Updated weights for policy 1, policy_version 42900 (0.0012) -[2023-11-28 01:20:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 21995520. Throughput: 0: 2685.6, 1: 2646.0. Samples: 22009164. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 01:20:18,445][86177] Avg episode reward: [(0, '-573.760'), (1, '-569.350')] -[2023-11-28 01:20:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000043040_11018240.pth... -[2023-11-28 01:20:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000040512_10371072.pth -[2023-11-28 01:20:18,763][87426] Updated weights for policy 1, policy_version 42910 (0.0012) -[2023-11-28 01:20:18,828][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000042912_10985472.pth... -[2023-11-28 01:20:18,871][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000040352_10330112.pth -[2023-11-28 01:20:19,110][87424] Updated weights for policy 0, policy_version 43046 (0.0012) -[2023-11-28 01:20:19,499][87424] Updated weights for policy 0, policy_version 43056 (0.0012) -[2023-11-28 01:20:19,879][87424] Updated weights for policy 0, policy_version 43066 (0.0012) -[2023-11-28 01:20:21,111][87426] Updated weights for policy 1, policy_version 42920 (0.0012) -[2023-11-28 01:20:21,485][87426] Updated weights for policy 1, policy_version 42930 (0.0009) -[2023-11-28 01:20:21,864][87426] Updated weights for policy 1, policy_version 42940 (0.0011) -[2023-11-28 01:20:22,362][87424] Updated weights for policy 0, policy_version 43076 (0.0012) -[2023-11-28 01:20:22,747][87424] Updated weights for policy 0, policy_version 43086 (0.0012) -[2023-11-28 01:20:23,135][87424] Updated weights for policy 0, policy_version 43096 (0.0010) -[2023-11-28 01:20:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 22028288. Throughput: 0: 2690.4, 1: 2673.0. Samples: 22042792. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 01:20:23,446][86177] Avg episode reward: [(0, '-553.070'), (1, '-530.600')] -[2023-11-28 01:20:23,885][87426] Updated weights for policy 1, policy_version 42950 (0.0012) -[2023-11-28 01:20:24,254][87426] Updated weights for policy 1, policy_version 42960 (0.0012) -[2023-11-28 01:20:24,637][87426] Updated weights for policy 1, policy_version 42970 (0.0008) -[2023-11-28 01:20:25,239][87424] Updated weights for policy 0, policy_version 43106 (0.0010) -[2023-11-28 01:20:25,619][87424] Updated weights for policy 0, policy_version 43116 (0.0012) -[2023-11-28 01:20:25,996][87424] Updated weights for policy 0, policy_version 43126 (0.0012) -[2023-11-28 01:20:26,389][87424] Updated weights for policy 0, policy_version 43136 (0.0012) -[2023-11-28 01:20:27,068][87426] Updated weights for policy 1, policy_version 42980 (0.0009) -[2023-11-28 01:20:27,453][87426] Updated weights for policy 1, policy_version 42990 (0.0008) -[2023-11-28 01:20:27,848][87426] Updated weights for policy 1, policy_version 43000 (0.0007) -[2023-11-28 01:20:28,261][87424] Updated weights for policy 0, policy_version 43146 (0.0012) -[2023-11-28 01:20:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 22052864. Throughput: 0: 2708.0, 1: 2688.1. Samples: 22067008. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 01:20:28,446][86177] Avg episode reward: [(0, '-567.560'), (1, '-520.420')] -[2023-11-28 01:20:28,649][87424] Updated weights for policy 0, policy_version 43156 (0.0010) -[2023-11-28 01:20:29,041][87424] Updated weights for policy 0, policy_version 43166 (0.0012) -[2023-11-28 01:20:29,675][87426] Updated weights for policy 1, policy_version 43010 (0.0010) -[2023-11-28 01:20:30,051][87426] Updated weights for policy 1, policy_version 43020 (0.0010) -[2023-11-28 01:20:30,432][87426] Updated weights for policy 1, policy_version 43030 (0.0011) -[2023-11-28 01:20:30,805][87426] Updated weights for policy 1, policy_version 43040 (0.0008) -[2023-11-28 01:20:31,025][87424] Updated weights for policy 0, policy_version 43176 (0.0011) -[2023-11-28 01:20:31,400][87424] Updated weights for policy 0, policy_version 43186 (0.0008) -[2023-11-28 01:20:31,785][87424] Updated weights for policy 0, policy_version 43196 (0.0010) -[2023-11-28 01:20:33,091][87426] Updated weights for policy 1, policy_version 43050 (0.0011) -[2023-11-28 01:20:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 22077440. Throughput: 0: 2723.8, 1: 2696.4. Samples: 22091716. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 01:20:33,445][86177] Avg episode reward: [(0, '-560.470'), (1, '-529.140')] -[2023-11-28 01:20:33,469][87426] Updated weights for policy 1, policy_version 43060 (0.0012) -[2023-11-28 01:20:33,855][87426] Updated weights for policy 1, policy_version 43070 (0.0011) -[2023-11-28 01:20:33,999][87424] Updated weights for policy 0, policy_version 43206 (0.0008) -[2023-11-28 01:20:34,394][87424] Updated weights for policy 0, policy_version 43216 (0.0007) -[2023-11-28 01:20:34,775][87424] Updated weights for policy 0, policy_version 43226 (0.0008) -[2023-11-28 01:20:35,811][87426] Updated weights for policy 1, policy_version 43080 (0.0012) -[2023-11-28 01:20:36,184][87426] Updated weights for policy 1, policy_version 43090 (0.0012) -[2023-11-28 01:20:36,562][87426] Updated weights for policy 1, policy_version 43100 (0.0012) -[2023-11-28 01:20:37,043][87424] Updated weights for policy 0, policy_version 43236 (0.0007) -[2023-11-28 01:20:37,428][87424] Updated weights for policy 0, policy_version 43246 (0.0009) -[2023-11-28 01:20:37,810][87424] Updated weights for policy 0, policy_version 43256 (0.0008) -[2023-11-28 01:20:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 22110208. Throughput: 0: 2743.9, 1: 2719.6. Samples: 22125204. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 01:20:38,445][86177] Avg episode reward: [(0, '-535.730'), (1, '-541.920')] -[2023-11-28 01:20:38,914][87426] Updated weights for policy 1, policy_version 43110 (0.0010) -[2023-11-28 01:20:39,291][87426] Updated weights for policy 1, policy_version 43120 (0.0011) -[2023-11-28 01:20:39,674][87426] Updated weights for policy 1, policy_version 43130 (0.0011) -[2023-11-28 01:20:39,852][87424] Updated weights for policy 0, policy_version 43266 (0.0008) -[2023-11-28 01:20:40,238][87424] Updated weights for policy 0, policy_version 43276 (0.0012) -[2023-11-28 01:20:40,616][87424] Updated weights for policy 0, policy_version 43286 (0.0012) -[2023-11-28 01:20:40,994][87424] Updated weights for policy 0, policy_version 43296 (0.0008) -[2023-11-28 01:20:42,068][87426] Updated weights for policy 1, policy_version 43140 (0.0010) -[2023-11-28 01:20:42,443][87426] Updated weights for policy 1, policy_version 43150 (0.0011) -[2023-11-28 01:20:42,825][87426] Updated weights for policy 1, policy_version 43160 (0.0011) -[2023-11-28 01:20:43,131][87424] Updated weights for policy 0, policy_version 43306 (0.0011) -[2023-11-28 01:20:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 22134784. Throughput: 0: 2747.2, 1: 2706.8. Samples: 22149316. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 01:20:43,445][86177] Avg episode reward: [(0, '-534.580'), (1, '-545.340')] -[2023-11-28 01:20:43,513][87424] Updated weights for policy 0, policy_version 43316 (0.0008) -[2023-11-28 01:20:43,900][87424] Updated weights for policy 0, policy_version 43326 (0.0008) -[2023-11-28 01:20:45,299][87426] Updated weights for policy 1, policy_version 43170 (0.0010) -[2023-11-28 01:20:45,674][87426] Updated weights for policy 1, policy_version 43180 (0.0007) -[2023-11-28 01:20:45,882][87424] Updated weights for policy 0, policy_version 43336 (0.0011) -[2023-11-28 01:20:46,049][87426] Updated weights for policy 1, policy_version 43190 (0.0007) -[2023-11-28 01:20:46,265][87424] Updated weights for policy 0, policy_version 43346 (0.0009) -[2023-11-28 01:20:46,429][87426] Updated weights for policy 1, policy_version 43200 (0.0007) -[2023-11-28 01:20:46,648][87424] Updated weights for policy 0, policy_version 43356 (0.0009) -[2023-11-28 01:20:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 22159360. Throughput: 0: 2728.8, 1: 2704.3. Samples: 22173688. Policy #0 lag: (min: 31.0, avg: 36.0, max: 62.0) -[2023-11-28 01:20:48,445][86177] Avg episode reward: [(0, '-516.260'), (1, '-542.150')] -[2023-11-28 01:20:48,678][87426] Updated weights for policy 1, policy_version 43210 (0.0009) -[2023-11-28 01:20:49,052][87426] Updated weights for policy 1, policy_version 43220 (0.0009) -[2023-11-28 01:20:49,089][87424] Updated weights for policy 0, policy_version 43366 (0.0011) -[2023-11-28 01:20:49,430][87426] Updated weights for policy 1, policy_version 43230 (0.0010) -[2023-11-28 01:20:49,475][87424] Updated weights for policy 0, policy_version 43376 (0.0011) -[2023-11-28 01:20:49,856][87424] Updated weights for policy 0, policy_version 43386 (0.0010) -[2023-11-28 01:20:51,430][87426] Updated weights for policy 1, policy_version 43240 (0.0007) -[2023-11-28 01:20:51,817][87426] Updated weights for policy 1, policy_version 43250 (0.0009) -[2023-11-28 01:20:52,013][87424] Updated weights for policy 0, policy_version 43396 (0.0010) -[2023-11-28 01:20:52,196][87426] Updated weights for policy 1, policy_version 43260 (0.0010) -[2023-11-28 01:20:52,405][87424] Updated weights for policy 0, policy_version 43406 (0.0011) -[2023-11-28 01:20:52,789][87424] Updated weights for policy 0, policy_version 43416 (0.0010) -[2023-11-28 01:20:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 22192128. Throughput: 0: 2717.2, 1: 2686.5. Samples: 22204984. Policy #0 lag: (min: 31.0, avg: 36.0, max: 62.0) -[2023-11-28 01:20:53,445][86177] Avg episode reward: [(0, '-509.670'), (1, '-536.790')] -[2023-11-28 01:20:54,585][87426] Updated weights for policy 1, policy_version 43270 (0.0008) -[2023-11-28 01:20:54,963][87426] Updated weights for policy 1, policy_version 43280 (0.0009) -[2023-11-28 01:20:55,067][87424] Updated weights for policy 0, policy_version 43426 (0.0010) -[2023-11-28 01:20:55,344][87426] Updated weights for policy 1, policy_version 43290 (0.0008) -[2023-11-28 01:20:55,450][87424] Updated weights for policy 0, policy_version 43436 (0.0011) -[2023-11-28 01:20:55,832][87424] Updated weights for policy 0, policy_version 43446 (0.0008) -[2023-11-28 01:20:56,220][87424] Updated weights for policy 0, policy_version 43456 (0.0012) -[2023-11-28 01:20:57,062][87426] Updated weights for policy 1, policy_version 43300 (0.0008) -[2023-11-28 01:20:57,436][87426] Updated weights for policy 1, policy_version 43310 (0.0008) -[2023-11-28 01:20:57,819][87426] Updated weights for policy 1, policy_version 43320 (0.0011) -[2023-11-28 01:20:58,183][87424] Updated weights for policy 0, policy_version 43466 (0.0011) -[2023-11-28 01:20:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 22216704. Throughput: 0: 2727.8, 1: 2713.2. Samples: 22229780. Policy #0 lag: (min: 31.0, avg: 36.0, max: 62.0) -[2023-11-28 01:20:58,445][86177] Avg episode reward: [(0, '-513.850'), (1, '-521.620')] -[2023-11-28 01:20:58,577][87424] Updated weights for policy 0, policy_version 43476 (0.0011) -[2023-11-28 01:20:58,949][87424] Updated weights for policy 0, policy_version 43486 (0.0011) -[2023-11-28 01:21:00,122][87426] Updated weights for policy 1, policy_version 43330 (0.0010) -[2023-11-28 01:21:00,500][87426] Updated weights for policy 1, policy_version 43340 (0.0012) -[2023-11-28 01:21:00,882][87426] Updated weights for policy 1, policy_version 43350 (0.0012) -[2023-11-28 01:21:01,258][87426] Updated weights for policy 1, policy_version 43360 (0.0011) -[2023-11-28 01:21:01,332][87424] Updated weights for policy 0, policy_version 43496 (0.0008) -[2023-11-28 01:21:01,726][87424] Updated weights for policy 0, policy_version 43506 (0.0008) -[2023-11-28 01:21:02,109][87424] Updated weights for policy 0, policy_version 43516 (0.0010) -[2023-11-28 01:21:03,341][87426] Updated weights for policy 1, policy_version 43370 (0.0011) -[2023-11-28 01:21:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 22241280. Throughput: 0: 2733.4, 1: 2725.1. Samples: 22254796. Policy #0 lag: (min: 31.0, avg: 36.0, max: 62.0) -[2023-11-28 01:21:03,445][86177] Avg episode reward: [(0, '-519.950'), (1, '-522.980')] -[2023-11-28 01:21:03,720][87426] Updated weights for policy 1, policy_version 43380 (0.0012) -[2023-11-28 01:21:04,088][87426] Updated weights for policy 1, policy_version 43390 (0.0012) -[2023-11-28 01:21:04,151][87424] Updated weights for policy 0, policy_version 43526 (0.0011) -[2023-11-28 01:21:04,532][87424] Updated weights for policy 0, policy_version 43536 (0.0009) -[2023-11-28 01:21:04,914][87424] Updated weights for policy 0, policy_version 43546 (0.0012) -[2023-11-28 01:21:06,079][87426] Updated weights for policy 1, policy_version 43400 (0.0011) -[2023-11-28 01:21:06,456][87426] Updated weights for policy 1, policy_version 43410 (0.0008) -[2023-11-28 01:21:06,835][87426] Updated weights for policy 1, policy_version 43420 (0.0009) -[2023-11-28 01:21:07,173][87424] Updated weights for policy 0, policy_version 43556 (0.0012) -[2023-11-28 01:21:07,559][87424] Updated weights for policy 0, policy_version 43566 (0.0011) -[2023-11-28 01:21:07,949][87424] Updated weights for policy 0, policy_version 43576 (0.0008) -[2023-11-28 01:21:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 22274048. Throughput: 0: 2747.0, 1: 2709.7. Samples: 22288344. Policy #0 lag: (min: 31.0, avg: 36.0, max: 62.0) -[2023-11-28 01:21:08,445][86177] Avg episode reward: [(0, '-516.300'), (1, '-543.240')] -[2023-11-28 01:21:08,910][87426] Updated weights for policy 1, policy_version 43430 (0.0010) -[2023-11-28 01:21:09,289][87426] Updated weights for policy 1, policy_version 43440 (0.0009) -[2023-11-28 01:21:09,671][87426] Updated weights for policy 1, policy_version 43450 (0.0011) -[2023-11-28 01:21:10,041][87424] Updated weights for policy 0, policy_version 43586 (0.0009) -[2023-11-28 01:21:10,426][87424] Updated weights for policy 0, policy_version 43596 (0.0010) -[2023-11-28 01:21:10,806][87424] Updated weights for policy 0, policy_version 43606 (0.0008) -[2023-11-28 01:21:11,194][87424] Updated weights for policy 0, policy_version 43616 (0.0007) -[2023-11-28 01:21:11,765][87426] Updated weights for policy 1, policy_version 43460 (0.0011) -[2023-11-28 01:21:12,142][87426] Updated weights for policy 1, policy_version 43470 (0.0009) -[2023-11-28 01:21:12,519][87426] Updated weights for policy 1, policy_version 43480 (0.0008) -[2023-11-28 01:21:13,305][87424] Updated weights for policy 0, policy_version 43626 (0.0008) -[2023-11-28 01:21:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 22298624. Throughput: 0: 2753.2, 1: 2722.1. Samples: 22313396. Policy #0 lag: (min: 31.0, avg: 36.0, max: 62.0) -[2023-11-28 01:21:13,445][86177] Avg episode reward: [(0, '-518.130'), (1, '-537.600')] -[2023-11-28 01:21:13,694][87424] Updated weights for policy 0, policy_version 43636 (0.0011) -[2023-11-28 01:21:14,073][87424] Updated weights for policy 0, policy_version 43646 (0.0012) -[2023-11-28 01:21:15,020][87426] Updated weights for policy 1, policy_version 43490 (0.0009) -[2023-11-28 01:21:15,395][87426] Updated weights for policy 1, policy_version 43500 (0.0010) -[2023-11-28 01:21:15,771][87426] Updated weights for policy 1, policy_version 43510 (0.0011) -[2023-11-28 01:21:16,148][87426] Updated weights for policy 1, policy_version 43520 (0.0011) -[2023-11-28 01:21:16,292][87424] Updated weights for policy 0, policy_version 43656 (0.0010) -[2023-11-28 01:21:16,672][87424] Updated weights for policy 0, policy_version 43666 (0.0007) -[2023-11-28 01:21:17,055][87424] Updated weights for policy 0, policy_version 43676 (0.0007) -[2023-11-28 01:21:17,898][87426] Updated weights for policy 1, policy_version 43530 (0.0009) -[2023-11-28 01:21:18,279][87426] Updated weights for policy 1, policy_version 43540 (0.0007) -[2023-11-28 01:21:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 22323200. Throughput: 0: 2749.7, 1: 2722.1. Samples: 22337948. Policy #0 lag: (min: 27.0, avg: 48.2, max: 59.0) -[2023-11-28 01:21:18,445][86177] Avg episode reward: [(0, '-511.260'), (1, '-530.630')] -[2023-11-28 01:21:18,662][87426] Updated weights for policy 1, policy_version 43550 (0.0008) -[2023-11-28 01:21:19,405][87424] Updated weights for policy 0, policy_version 43686 (0.0007) -[2023-11-28 01:21:19,790][87424] Updated weights for policy 0, policy_version 43696 (0.0008) -[2023-11-28 01:21:20,162][87424] Updated weights for policy 0, policy_version 43706 (0.0009) -[2023-11-28 01:21:20,902][87426] Updated weights for policy 1, policy_version 43560 (0.0007) -[2023-11-28 01:21:21,283][87426] Updated weights for policy 1, policy_version 43570 (0.0009) -[2023-11-28 01:21:21,673][87426] Updated weights for policy 1, policy_version 43580 (0.0008) -[2023-11-28 01:21:22,479][87424] Updated weights for policy 0, policy_version 43716 (0.0010) -[2023-11-28 01:21:22,854][87424] Updated weights for policy 0, policy_version 43726 (0.0012) -[2023-11-28 01:21:23,247][87424] Updated weights for policy 0, policy_version 43736 (0.0012) -[2023-11-28 01:21:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 22347776. Throughput: 0: 2722.2, 1: 2720.8. Samples: 22370140. Policy #0 lag: (min: 27.0, avg: 48.2, max: 59.0) -[2023-11-28 01:21:23,445][86177] Avg episode reward: [(0, '-506.410'), (1, '-529.920')] -[2023-11-28 01:21:24,024][87426] Updated weights for policy 1, policy_version 43590 (0.0010) -[2023-11-28 01:21:24,401][87426] Updated weights for policy 1, policy_version 43600 (0.0007) -[2023-11-28 01:21:24,782][87426] Updated weights for policy 1, policy_version 43610 (0.0007) -[2023-11-28 01:21:25,140][87424] Updated weights for policy 0, policy_version 43746 (0.0012) -[2023-11-28 01:21:25,527][87424] Updated weights for policy 0, policy_version 43756 (0.0011) -[2023-11-28 01:21:25,910][87424] Updated weights for policy 0, policy_version 43766 (0.0012) -[2023-11-28 01:21:26,293][87424] Updated weights for policy 0, policy_version 43776 (0.0011) -[2023-11-28 01:21:27,214][87426] Updated weights for policy 1, policy_version 43620 (0.0009) -[2023-11-28 01:21:27,598][87426] Updated weights for policy 1, policy_version 43630 (0.0011) -[2023-11-28 01:21:27,931][87424] Updated weights for policy 0, policy_version 43786 (0.0011) -[2023-11-28 01:21:27,975][87426] Updated weights for policy 1, policy_version 43640 (0.0011) -[2023-11-28 01:21:28,324][87424] Updated weights for policy 0, policy_version 43796 (0.0011) -[2023-11-28 01:21:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 22380544. Throughput: 0: 2728.6, 1: 2720.6. Samples: 22394532. Policy #0 lag: (min: 27.0, avg: 48.2, max: 59.0) -[2023-11-28 01:21:28,445][86177] Avg episode reward: [(0, '-507.960'), (1, '-513.000')] -[2023-11-28 01:21:28,700][87424] Updated weights for policy 0, policy_version 43806 (0.0011) -[2023-11-28 01:21:29,801][87426] Updated weights for policy 1, policy_version 43650 (0.0012) -[2023-11-28 01:21:30,185][87426] Updated weights for policy 1, policy_version 43660 (0.0011) -[2023-11-28 01:21:30,467][87424] Updated weights for policy 0, policy_version 43816 (0.0012) -[2023-11-28 01:21:30,564][87426] Updated weights for policy 1, policy_version 43670 (0.0010) -[2023-11-28 01:21:30,845][87424] Updated weights for policy 0, policy_version 43826 (0.0011) -[2023-11-28 01:21:30,941][87426] Updated weights for policy 1, policy_version 43680 (0.0010) -[2023-11-28 01:21:31,229][87424] Updated weights for policy 0, policy_version 43836 (0.0009) -[2023-11-28 01:21:32,839][87426] Updated weights for policy 1, policy_version 43690 (0.0011) -[2023-11-28 01:21:33,226][87426] Updated weights for policy 1, policy_version 43700 (0.0008) -[2023-11-28 01:21:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 22405120. Throughput: 0: 2750.4, 1: 2743.2. Samples: 22420900. Policy #0 lag: (min: 27.0, avg: 48.2, max: 59.0) -[2023-11-28 01:21:33,445][86177] Avg episode reward: [(0, '-505.170'), (1, '-510.590')] -[2023-11-28 01:21:33,597][87426] Updated weights for policy 1, policy_version 43710 (0.0007) -[2023-11-28 01:21:33,811][87424] Updated weights for policy 0, policy_version 43846 (0.0008) -[2023-11-28 01:21:34,194][87424] Updated weights for policy 0, policy_version 43856 (0.0007) -[2023-11-28 01:21:34,579][87424] Updated weights for policy 0, policy_version 43866 (0.0007) -[2023-11-28 01:21:36,094][87426] Updated weights for policy 1, policy_version 43720 (0.0009) -[2023-11-28 01:21:36,478][87426] Updated weights for policy 1, policy_version 43730 (0.0008) -[2023-11-28 01:21:36,858][87426] Updated weights for policy 1, policy_version 43740 (0.0010) -[2023-11-28 01:21:37,097][87424] Updated weights for policy 0, policy_version 43876 (0.0010) -[2023-11-28 01:21:37,473][87424] Updated weights for policy 0, policy_version 43886 (0.0011) -[2023-11-28 01:21:37,858][87424] Updated weights for policy 0, policy_version 43896 (0.0010) -[2023-11-28 01:21:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 22437888. Throughput: 0: 2751.9, 1: 2745.2. Samples: 22452356. Policy #0 lag: (min: 27.0, avg: 48.2, max: 59.0) -[2023-11-28 01:21:38,445][86177] Avg episode reward: [(0, '-503.750'), (1, '-503.630')] -[2023-11-28 01:21:39,000][87426] Updated weights for policy 1, policy_version 43750 (0.0010) -[2023-11-28 01:21:39,381][87426] Updated weights for policy 1, policy_version 43760 (0.0009) -[2023-11-28 01:21:39,762][87426] Updated weights for policy 1, policy_version 43770 (0.0010) -[2023-11-28 01:21:40,410][87424] Updated weights for policy 0, policy_version 43906 (0.0008) -[2023-11-28 01:21:40,787][87424] Updated weights for policy 0, policy_version 43916 (0.0012) -[2023-11-28 01:21:41,176][87424] Updated weights for policy 0, policy_version 43926 (0.0012) -[2023-11-28 01:21:41,559][87424] Updated weights for policy 0, policy_version 43936 (0.0012) -[2023-11-28 01:21:41,720][87426] Updated weights for policy 1, policy_version 43780 (0.0009) -[2023-11-28 01:21:42,103][87426] Updated weights for policy 1, policy_version 43790 (0.0010) -[2023-11-28 01:21:42,486][87426] Updated weights for policy 1, policy_version 43800 (0.0010) -[2023-11-28 01:21:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 22462464. Throughput: 0: 2732.3, 1: 2749.8. Samples: 22476472. Policy #0 lag: (min: 27.0, avg: 48.2, max: 59.0) -[2023-11-28 01:21:43,445][86177] Avg episode reward: [(0, '-506.560'), (1, '-501.550')] -[2023-11-28 01:21:43,672][87424] Updated weights for policy 0, policy_version 43946 (0.0009) -[2023-11-28 01:21:44,051][87424] Updated weights for policy 0, policy_version 43956 (0.0010) -[2023-11-28 01:21:44,432][87424] Updated weights for policy 0, policy_version 43966 (0.0007) -[2023-11-28 01:21:44,589][87426] Updated weights for policy 1, policy_version 43810 (0.0011) -[2023-11-28 01:21:44,966][87426] Updated weights for policy 1, policy_version 43820 (0.0008) -[2023-11-28 01:21:45,343][87426] Updated weights for policy 1, policy_version 43830 (0.0008) -[2023-11-28 01:21:45,723][87426] Updated weights for policy 1, policy_version 43840 (0.0008) -[2023-11-28 01:21:46,692][87424] Updated weights for policy 0, policy_version 43976 (0.0010) -[2023-11-28 01:21:47,087][87424] Updated weights for policy 0, policy_version 43986 (0.0008) -[2023-11-28 01:21:47,459][87424] Updated weights for policy 0, policy_version 43996 (0.0008) -[2023-11-28 01:21:47,986][87426] Updated weights for policy 1, policy_version 43850 (0.0008) -[2023-11-28 01:21:48,366][87426] Updated weights for policy 1, policy_version 43860 (0.0007) -[2023-11-28 01:21:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 22487040. Throughput: 0: 2730.3, 1: 2753.2. Samples: 22501556. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:21:48,445][86177] Avg episode reward: [(0, '-507.840'), (1, '-504.690')] -[2023-11-28 01:21:48,746][87426] Updated weights for policy 1, policy_version 43870 (0.0007) -[2023-11-28 01:21:49,464][87424] Updated weights for policy 0, policy_version 44006 (0.0011) -[2023-11-28 01:21:49,839][87424] Updated weights for policy 0, policy_version 44016 (0.0012) -[2023-11-28 01:21:50,216][87424] Updated weights for policy 0, policy_version 44026 (0.0011) -[2023-11-28 01:21:50,550][87426] Updated weights for policy 1, policy_version 43880 (0.0011) -[2023-11-28 01:21:50,929][87426] Updated weights for policy 1, policy_version 43890 (0.0012) -[2023-11-28 01:21:51,316][87426] Updated weights for policy 1, policy_version 43900 (0.0012) -[2023-11-28 01:21:52,402][87424] Updated weights for policy 0, policy_version 44036 (0.0009) -[2023-11-28 01:21:52,790][87424] Updated weights for policy 0, policy_version 44046 (0.0008) -[2023-11-28 01:21:53,164][87424] Updated weights for policy 0, policy_version 44056 (0.0009) -[2023-11-28 01:21:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 22511616. Throughput: 0: 2716.6, 1: 2751.2. Samples: 22534396. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:21:53,445][86177] Avg episode reward: [(0, '-510.670'), (1, '-504.370')] -[2023-11-28 01:21:53,935][87426] Updated weights for policy 1, policy_version 43910 (0.0012) -[2023-11-28 01:21:54,311][87426] Updated weights for policy 1, policy_version 43920 (0.0012) -[2023-11-28 01:21:54,691][87426] Updated weights for policy 1, policy_version 43930 (0.0011) -[2023-11-28 01:21:55,466][87424] Updated weights for policy 0, policy_version 44066 (0.0012) -[2023-11-28 01:21:55,857][87424] Updated weights for policy 0, policy_version 44076 (0.0009) -[2023-11-28 01:21:56,238][87424] Updated weights for policy 0, policy_version 44086 (0.0007) -[2023-11-28 01:21:56,626][87424] Updated weights for policy 0, policy_version 44096 (0.0007) -[2023-11-28 01:21:56,689][87426] Updated weights for policy 1, policy_version 43940 (0.0007) -[2023-11-28 01:21:57,067][87426] Updated weights for policy 1, policy_version 43950 (0.0008) -[2023-11-28 01:21:57,451][87426] Updated weights for policy 1, policy_version 43960 (0.0007) -[2023-11-28 01:21:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 22544384. Throughput: 0: 2714.0, 1: 2756.8. Samples: 22559580. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:21:58,445][86177] Avg episode reward: [(0, '-522.570'), (1, '-498.560')] -[2023-11-28 01:21:59,056][87424] Updated weights for policy 0, policy_version 44106 (0.0010) -[2023-11-28 01:21:59,115][87426] Updated weights for policy 1, policy_version 43970 (0.0008) -[2023-11-28 01:21:59,445][87424] Updated weights for policy 0, policy_version 44116 (0.0009) -[2023-11-28 01:21:59,497][87426] Updated weights for policy 1, policy_version 43980 (0.0011) -[2023-11-28 01:21:59,835][87424] Updated weights for policy 0, policy_version 44126 (0.0008) -[2023-11-28 01:21:59,876][87426] Updated weights for policy 1, policy_version 43990 (0.0012) -[2023-11-28 01:22:00,257][87426] Updated weights for policy 1, policy_version 44000 (0.0011) -[2023-11-28 01:22:01,960][87424] Updated weights for policy 0, policy_version 44136 (0.0010) -[2023-11-28 01:22:02,297][87426] Updated weights for policy 1, policy_version 44010 (0.0011) -[2023-11-28 01:22:02,349][87424] Updated weights for policy 0, policy_version 44146 (0.0010) -[2023-11-28 01:22:02,680][87426] Updated weights for policy 1, policy_version 44020 (0.0008) -[2023-11-28 01:22:02,731][87424] Updated weights for policy 0, policy_version 44156 (0.0010) -[2023-11-28 01:22:03,060][87426] Updated weights for policy 1, policy_version 44030 (0.0008) -[2023-11-28 01:22:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 22577152. Throughput: 0: 2715.4, 1: 2770.9. Samples: 22584832. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:22:03,445][86177] Avg episode reward: [(0, '-523.330'), (1, '-493.730')] -[2023-11-28 01:22:03,456][87320] Saving new best policy, reward=-493.730! -[2023-11-28 01:22:05,260][87424] Updated weights for policy 0, policy_version 44166 (0.0009) -[2023-11-28 01:22:05,430][87426] Updated weights for policy 1, policy_version 44040 (0.0007) -[2023-11-28 01:22:05,659][87424] Updated weights for policy 0, policy_version 44176 (0.0009) -[2023-11-28 01:22:05,814][87426] Updated weights for policy 1, policy_version 44050 (0.0007) -[2023-11-28 01:22:06,033][87424] Updated weights for policy 0, policy_version 44186 (0.0011) -[2023-11-28 01:22:06,190][87426] Updated weights for policy 1, policy_version 44060 (0.0007) -[2023-11-28 01:22:07,869][87426] Updated weights for policy 1, policy_version 44070 (0.0010) -[2023-11-28 01:22:08,244][87426] Updated weights for policy 1, policy_version 44080 (0.0011) -[2023-11-28 01:22:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 22593536. Throughput: 0: 2706.9, 1: 2782.8. Samples: 22617176. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:22:08,445][86177] Avg episode reward: [(0, '-526.890'), (1, '-495.930')] -[2023-11-28 01:22:08,596][87424] Updated weights for policy 0, policy_version 44196 (0.0010) -[2023-11-28 01:22:08,616][87426] Updated weights for policy 1, policy_version 44090 (0.0011) -[2023-11-28 01:22:08,968][87424] Updated weights for policy 0, policy_version 44206 (0.0012) -[2023-11-28 01:22:09,343][87424] Updated weights for policy 0, policy_version 44216 (0.0011) -[2023-11-28 01:22:10,900][87426] Updated weights for policy 1, policy_version 44100 (0.0010) -[2023-11-28 01:22:11,281][87426] Updated weights for policy 1, policy_version 44110 (0.0008) -[2023-11-28 01:22:11,298][87424] Updated weights for policy 0, policy_version 44226 (0.0011) -[2023-11-28 01:22:11,669][87426] Updated weights for policy 1, policy_version 44120 (0.0011) -[2023-11-28 01:22:11,679][87424] Updated weights for policy 0, policy_version 44236 (0.0009) -[2023-11-28 01:22:12,055][87424] Updated weights for policy 0, policy_version 44246 (0.0011) -[2023-11-28 01:22:12,437][87424] Updated weights for policy 0, policy_version 44256 (0.0010) -[2023-11-28 01:22:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 22626304. Throughput: 0: 2686.8, 1: 2795.6. Samples: 22641236. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:22:13,445][86177] Avg episode reward: [(0, '-527.540'), (1, '-499.660')] -[2023-11-28 01:22:13,555][87426] Updated weights for policy 1, policy_version 44130 (0.0011) -[2023-11-28 01:22:13,934][87426] Updated weights for policy 1, policy_version 44140 (0.0007) -[2023-11-28 01:22:14,313][87426] Updated weights for policy 1, policy_version 44150 (0.0007) -[2023-11-28 01:22:14,616][87424] Updated weights for policy 0, policy_version 44266 (0.0007) -[2023-11-28 01:22:14,705][87426] Updated weights for policy 1, policy_version 44160 (0.0008) -[2023-11-28 01:22:14,999][87424] Updated weights for policy 0, policy_version 44276 (0.0009) -[2023-11-28 01:22:15,381][87424] Updated weights for policy 0, policy_version 44286 (0.0007) -[2023-11-28 01:22:16,981][87426] Updated weights for policy 1, policy_version 44170 (0.0012) -[2023-11-28 01:22:17,340][87424] Updated weights for policy 0, policy_version 44296 (0.0011) -[2023-11-28 01:22:17,365][87426] Updated weights for policy 1, policy_version 44180 (0.0011) -[2023-11-28 01:22:17,718][87424] Updated weights for policy 0, policy_version 44306 (0.0011) -[2023-11-28 01:22:17,742][87426] Updated weights for policy 1, policy_version 44190 (0.0012) -[2023-11-28 01:22:18,096][87424] Updated weights for policy 0, policy_version 44316 (0.0011) -[2023-11-28 01:22:18,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 22659072. Throughput: 0: 2665.8, 1: 2771.5. Samples: 22665580. Policy #0 lag: (min: 22.0, avg: 37.0, max: 64.0) -[2023-11-28 01:22:18,445][86177] Avg episode reward: [(0, '-520.980'), (1, '-512.710')] -[2023-11-28 01:22:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000044192_11313152.pth... -[2023-11-28 01:22:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000044320_11345920.pth... -[2023-11-28 01:22:18,494][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000041632_10657792.pth -[2023-11-28 01:22:18,494][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000041760_10690560.pth -[2023-11-28 01:22:20,285][87426] Updated weights for policy 1, policy_version 44200 (0.0010) -[2023-11-28 01:22:20,608][87424] Updated weights for policy 0, policy_version 44326 (0.0012) -[2023-11-28 01:22:20,670][87426] Updated weights for policy 1, policy_version 44210 (0.0008) -[2023-11-28 01:22:20,988][87424] Updated weights for policy 0, policy_version 44336 (0.0012) -[2023-11-28 01:22:21,057][87426] Updated weights for policy 1, policy_version 44220 (0.0009) -[2023-11-28 01:22:21,374][87424] Updated weights for policy 0, policy_version 44346 (0.0011) -[2023-11-28 01:22:23,157][87426] Updated weights for policy 1, policy_version 44230 (0.0010) -[2023-11-28 01:22:23,389][87424] Updated weights for policy 0, policy_version 44356 (0.0010) -[2023-11-28 01:22:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 22675456. Throughput: 0: 2665.1, 1: 2779.6. Samples: 22697364. Policy #0 lag: (min: 22.0, avg: 37.0, max: 64.0) -[2023-11-28 01:22:23,445][86177] Avg episode reward: [(0, '-518.330'), (1, '-511.930')] -[2023-11-28 01:22:23,540][87426] Updated weights for policy 1, policy_version 44240 (0.0011) -[2023-11-28 01:22:23,770][87424] Updated weights for policy 0, policy_version 44366 (0.0012) -[2023-11-28 01:22:23,914][87426] Updated weights for policy 1, policy_version 44250 (0.0008) -[2023-11-28 01:22:24,146][87424] Updated weights for policy 0, policy_version 44376 (0.0012) -[2023-11-28 01:22:25,589][87426] Updated weights for policy 1, policy_version 44260 (0.0010) -[2023-11-28 01:22:25,972][87426] Updated weights for policy 1, policy_version 44270 (0.0012) -[2023-11-28 01:22:26,346][87426] Updated weights for policy 1, policy_version 44280 (0.0012) -[2023-11-28 01:22:26,688][87424] Updated weights for policy 0, policy_version 44386 (0.0012) -[2023-11-28 01:22:27,063][87424] Updated weights for policy 0, policy_version 44396 (0.0011) -[2023-11-28 01:22:27,440][87424] Updated weights for policy 0, policy_version 44406 (0.0011) -[2023-11-28 01:22:27,825][87424] Updated weights for policy 0, policy_version 44416 (0.0007) -[2023-11-28 01:22:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 22708224. Throughput: 0: 2672.0, 1: 2791.6. Samples: 22722336. Policy #0 lag: (min: 22.0, avg: 37.0, max: 64.0) -[2023-11-28 01:22:28,445][86177] Avg episode reward: [(0, '-515.910'), (1, '-514.740')] -[2023-11-28 01:22:28,492][87426] Updated weights for policy 1, policy_version 44290 (0.0010) -[2023-11-28 01:22:28,865][87426] Updated weights for policy 1, policy_version 44300 (0.0008) -[2023-11-28 01:22:29,247][87426] Updated weights for policy 1, policy_version 44310 (0.0010) -[2023-11-28 01:22:29,629][87426] Updated weights for policy 1, policy_version 44320 (0.0008) -[2023-11-28 01:22:29,915][87424] Updated weights for policy 0, policy_version 44426 (0.0009) -[2023-11-28 01:22:30,285][87424] Updated weights for policy 0, policy_version 44436 (0.0008) -[2023-11-28 01:22:30,664][87424] Updated weights for policy 0, policy_version 44446 (0.0011) -[2023-11-28 01:22:31,626][87426] Updated weights for policy 1, policy_version 44330 (0.0011) -[2023-11-28 01:22:31,999][87426] Updated weights for policy 1, policy_version 44340 (0.0010) -[2023-11-28 01:22:32,378][87426] Updated weights for policy 1, policy_version 44350 (0.0010) -[2023-11-28 01:22:32,537][87424] Updated weights for policy 0, policy_version 44456 (0.0011) -[2023-11-28 01:22:32,930][87424] Updated weights for policy 0, policy_version 44466 (0.0012) -[2023-11-28 01:22:33,310][87424] Updated weights for policy 0, policy_version 44476 (0.0012) -[2023-11-28 01:22:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 22732800. Throughput: 0: 2673.2, 1: 2774.9. Samples: 22746724. Policy #0 lag: (min: 22.0, avg: 37.0, max: 64.0) -[2023-11-28 01:22:33,445][86177] Avg episode reward: [(0, '-513.260'), (1, '-512.380')] -[2023-11-28 01:22:34,431][87426] Updated weights for policy 1, policy_version 44360 (0.0011) -[2023-11-28 01:22:34,819][87426] Updated weights for policy 1, policy_version 44370 (0.0011) -[2023-11-28 01:22:35,195][87426] Updated weights for policy 1, policy_version 44380 (0.0011) -[2023-11-28 01:22:35,278][87424] Updated weights for policy 0, policy_version 44486 (0.0012) -[2023-11-28 01:22:35,653][87424] Updated weights for policy 0, policy_version 44496 (0.0011) -[2023-11-28 01:22:36,047][87424] Updated weights for policy 0, policy_version 44506 (0.0007) -[2023-11-28 01:22:37,603][87426] Updated weights for policy 1, policy_version 44390 (0.0011) -[2023-11-28 01:22:37,943][87424] Updated weights for policy 0, policy_version 44516 (0.0007) -[2023-11-28 01:22:37,976][87426] Updated weights for policy 1, policy_version 44400 (0.0011) -[2023-11-28 01:22:38,327][87424] Updated weights for policy 0, policy_version 44526 (0.0008) -[2023-11-28 01:22:38,367][87426] Updated weights for policy 1, policy_version 44410 (0.0011) -[2023-11-28 01:22:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 22757376. Throughput: 0: 2665.2, 1: 2788.0. Samples: 22779792. Policy #0 lag: (min: 22.0, avg: 37.0, max: 64.0) -[2023-11-28 01:22:38,445][86177] Avg episode reward: [(0, '-516.050'), (1, '-500.910')] -[2023-11-28 01:22:38,713][87424] Updated weights for policy 0, policy_version 44536 (0.0008) -[2023-11-28 01:22:40,782][87426] Updated weights for policy 1, policy_version 44420 (0.0012) -[2023-11-28 01:22:41,154][87426] Updated weights for policy 1, policy_version 44430 (0.0011) -[2023-11-28 01:22:41,206][87424] Updated weights for policy 0, policy_version 44546 (0.0008) -[2023-11-28 01:22:41,535][87426] Updated weights for policy 1, policy_version 44440 (0.0012) -[2023-11-28 01:22:41,596][87424] Updated weights for policy 0, policy_version 44556 (0.0009) -[2023-11-28 01:22:41,977][87424] Updated weights for policy 0, policy_version 44566 (0.0010) -[2023-11-28 01:22:42,360][87424] Updated weights for policy 0, policy_version 44576 (0.0012) -[2023-11-28 01:22:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 22790144. Throughput: 0: 2648.2, 1: 2766.1. Samples: 22803220. Policy #0 lag: (min: 22.0, avg: 37.0, max: 64.0) -[2023-11-28 01:22:43,445][86177] Avg episode reward: [(0, '-513.440'), (1, '-502.420')] -[2023-11-28 01:22:44,102][87426] Updated weights for policy 1, policy_version 44450 (0.0011) -[2023-11-28 01:22:44,490][87426] Updated weights for policy 1, policy_version 44460 (0.0012) -[2023-11-28 01:22:44,840][87424] Updated weights for policy 0, policy_version 44586 (0.0008) -[2023-11-28 01:22:44,867][87426] Updated weights for policy 1, policy_version 44470 (0.0012) -[2023-11-28 01:22:45,219][87424] Updated weights for policy 0, policy_version 44596 (0.0007) -[2023-11-28 01:22:45,238][87426] Updated weights for policy 1, policy_version 44480 (0.0011) -[2023-11-28 01:22:45,602][87424] Updated weights for policy 0, policy_version 44606 (0.0008) -[2023-11-28 01:22:47,049][87426] Updated weights for policy 1, policy_version 44490 (0.0010) -[2023-11-28 01:22:47,439][87426] Updated weights for policy 1, policy_version 44500 (0.0008) -[2023-11-28 01:22:47,814][87426] Updated weights for policy 1, policy_version 44510 (0.0009) -[2023-11-28 01:22:47,916][87424] Updated weights for policy 0, policy_version 44616 (0.0011) -[2023-11-28 01:22:48,300][87424] Updated weights for policy 0, policy_version 44626 (0.0011) -[2023-11-28 01:22:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 22814720. Throughput: 0: 2630.8, 1: 2762.7. Samples: 22827540. Policy #0 lag: (min: 6.0, avg: 20.7, max: 38.0) -[2023-11-28 01:22:48,445][86177] Avg episode reward: [(0, '-552.820'), (1, '-502.950')] -[2023-11-28 01:22:48,680][87424] Updated weights for policy 0, policy_version 44636 (0.0010) -[2023-11-28 01:22:50,184][87426] Updated weights for policy 1, policy_version 44520 (0.0011) -[2023-11-28 01:22:50,567][87426] Updated weights for policy 1, policy_version 44530 (0.0010) -[2023-11-28 01:22:50,943][87426] Updated weights for policy 1, policy_version 44540 (0.0008) -[2023-11-28 01:22:51,275][87424] Updated weights for policy 0, policy_version 44646 (0.0009) -[2023-11-28 01:22:51,663][87424] Updated weights for policy 0, policy_version 44656 (0.0010) -[2023-11-28 01:22:52,047][87424] Updated weights for policy 0, policy_version 44666 (0.0012) -[2023-11-28 01:22:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 22839296. Throughput: 0: 2646.1, 1: 2719.1. Samples: 22858612. Policy #0 lag: (min: 6.0, avg: 20.7, max: 38.0) -[2023-11-28 01:22:53,445][86177] Avg episode reward: [(0, '-557.470'), (1, '-506.600')] -[2023-11-28 01:22:53,572][87426] Updated weights for policy 1, policy_version 44550 (0.0011) -[2023-11-28 01:22:53,941][87426] Updated weights for policy 1, policy_version 44560 (0.0012) -[2023-11-28 01:22:54,307][87424] Updated weights for policy 0, policy_version 44676 (0.0012) -[2023-11-28 01:22:54,328][87426] Updated weights for policy 1, policy_version 44570 (0.0011) -[2023-11-28 01:22:54,696][87424] Updated weights for policy 0, policy_version 44686 (0.0012) -[2023-11-28 01:22:55,076][87424] Updated weights for policy 0, policy_version 44696 (0.0012) -[2023-11-28 01:22:56,095][87426] Updated weights for policy 1, policy_version 44580 (0.0009) -[2023-11-28 01:22:56,479][87426] Updated weights for policy 1, policy_version 44590 (0.0012) -[2023-11-28 01:22:56,846][87426] Updated weights for policy 1, policy_version 44600 (0.0011) -[2023-11-28 01:22:57,104][87424] Updated weights for policy 0, policy_version 44706 (0.0011) -[2023-11-28 01:22:57,482][87424] Updated weights for policy 0, policy_version 44716 (0.0011) -[2023-11-28 01:22:57,865][87424] Updated weights for policy 0, policy_version 44726 (0.0012) -[2023-11-28 01:22:58,245][87424] Updated weights for policy 0, policy_version 44736 (0.0012) -[2023-11-28 01:22:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 22872064. Throughput: 0: 2658.1, 1: 2746.4. Samples: 22884440. Policy #0 lag: (min: 6.0, avg: 20.7, max: 38.0) -[2023-11-28 01:22:58,445][86177] Avg episode reward: [(0, '-589.580'), (1, '-537.960')] -[2023-11-28 01:22:58,762][87426] Updated weights for policy 1, policy_version 44610 (0.0011) -[2023-11-28 01:22:59,141][87426] Updated weights for policy 1, policy_version 44620 (0.0011) -[2023-11-28 01:22:59,524][87426] Updated weights for policy 1, policy_version 44630 (0.0008) -[2023-11-28 01:22:59,902][87426] Updated weights for policy 1, policy_version 44640 (0.0009) -[2023-11-28 01:23:00,452][87424] Updated weights for policy 0, policy_version 44746 (0.0011) -[2023-11-28 01:23:00,836][87424] Updated weights for policy 0, policy_version 44756 (0.0012) -[2023-11-28 01:23:01,229][87424] Updated weights for policy 0, policy_version 44766 (0.0012) -[2023-11-28 01:23:01,937][87426] Updated weights for policy 1, policy_version 44650 (0.0012) -[2023-11-28 01:23:02,318][87426] Updated weights for policy 1, policy_version 44660 (0.0012) -[2023-11-28 01:23:02,696][87426] Updated weights for policy 1, policy_version 44670 (0.0012) -[2023-11-28 01:23:03,287][87424] Updated weights for policy 0, policy_version 44776 (0.0011) -[2023-11-28 01:23:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 22896640. Throughput: 0: 2671.6, 1: 2756.5. Samples: 22909840. Policy #0 lag: (min: 6.0, avg: 20.7, max: 38.0) -[2023-11-28 01:23:03,445][86177] Avg episode reward: [(0, '-605.740'), (1, '-540.000')] -[2023-11-28 01:23:03,663][87424] Updated weights for policy 0, policy_version 44786 (0.0012) -[2023-11-28 01:23:04,052][87424] Updated weights for policy 0, policy_version 44796 (0.0012) -[2023-11-28 01:23:04,991][87426] Updated weights for policy 1, policy_version 44680 (0.0011) -[2023-11-28 01:23:05,367][87426] Updated weights for policy 1, policy_version 44690 (0.0009) -[2023-11-28 01:23:05,755][87426] Updated weights for policy 1, policy_version 44700 (0.0007) -[2023-11-28 01:23:05,839][87424] Updated weights for policy 0, policy_version 44806 (0.0010) -[2023-11-28 01:23:06,217][87424] Updated weights for policy 0, policy_version 44816 (0.0010) -[2023-11-28 01:23:06,604][87424] Updated weights for policy 0, policy_version 44826 (0.0010) -[2023-11-28 01:23:08,011][87426] Updated weights for policy 1, policy_version 44710 (0.0010) -[2023-11-28 01:23:08,388][87426] Updated weights for policy 1, policy_version 44720 (0.0012) -[2023-11-28 01:23:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 22921216. Throughput: 0: 2704.4, 1: 2739.5. Samples: 22942340. Policy #0 lag: (min: 6.0, avg: 20.7, max: 38.0) -[2023-11-28 01:23:08,446][86177] Avg episode reward: [(0, '-588.730'), (1, '-540.890')] -[2023-11-28 01:23:08,775][87426] Updated weights for policy 1, policy_version 44730 (0.0011) -[2023-11-28 01:23:08,815][87424] Updated weights for policy 0, policy_version 44836 (0.0008) -[2023-11-28 01:23:09,203][87424] Updated weights for policy 0, policy_version 44846 (0.0012) -[2023-11-28 01:23:09,588][87424] Updated weights for policy 0, policy_version 44856 (0.0012) -[2023-11-28 01:23:11,122][87426] Updated weights for policy 1, policy_version 44740 (0.0010) -[2023-11-28 01:23:11,510][87426] Updated weights for policy 1, policy_version 44750 (0.0008) -[2023-11-28 01:23:11,594][87424] Updated weights for policy 0, policy_version 44866 (0.0012) -[2023-11-28 01:23:11,879][87426] Updated weights for policy 1, policy_version 44760 (0.0010) -[2023-11-28 01:23:11,978][87424] Updated weights for policy 0, policy_version 44876 (0.0011) -[2023-11-28 01:23:12,352][87424] Updated weights for policy 0, policy_version 44886 (0.0011) -[2023-11-28 01:23:12,737][87424] Updated weights for policy 0, policy_version 44896 (0.0011) -[2023-11-28 01:23:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 22953984. Throughput: 0: 2709.9, 1: 2717.8. Samples: 22966580. Policy #0 lag: (min: 6.0, avg: 20.7, max: 38.0) -[2023-11-28 01:23:13,446][86177] Avg episode reward: [(0, '-629.940'), (1, '-549.960')] -[2023-11-28 01:23:13,862][87426] Updated weights for policy 1, policy_version 44770 (0.0008) -[2023-11-28 01:23:14,242][87426] Updated weights for policy 1, policy_version 44780 (0.0007) -[2023-11-28 01:23:14,622][87426] Updated weights for policy 1, policy_version 44790 (0.0007) -[2023-11-28 01:23:15,003][87426] Updated weights for policy 1, policy_version 44800 (0.0008) -[2023-11-28 01:23:15,210][87424] Updated weights for policy 0, policy_version 44906 (0.0012) -[2023-11-28 01:23:15,592][87424] Updated weights for policy 0, policy_version 44916 (0.0012) -[2023-11-28 01:23:15,968][87424] Updated weights for policy 0, policy_version 44926 (0.0010) -[2023-11-28 01:23:17,363][87426] Updated weights for policy 1, policy_version 44810 (0.0011) -[2023-11-28 01:23:17,743][87426] Updated weights for policy 1, policy_version 44820 (0.0011) -[2023-11-28 01:23:17,853][87424] Updated weights for policy 0, policy_version 44936 (0.0008) -[2023-11-28 01:23:18,129][87426] Updated weights for policy 1, policy_version 44830 (0.0007) -[2023-11-28 01:23:18,239][87424] Updated weights for policy 0, policy_version 44946 (0.0008) -[2023-11-28 01:23:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 22978560. Throughput: 0: 2692.0, 1: 2726.4. Samples: 22990552. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:23:18,446][86177] Avg episode reward: [(0, '-589.720'), (1, '-524.860')] -[2023-11-28 01:23:18,623][87424] Updated weights for policy 0, policy_version 44956 (0.0008) -[2023-11-28 01:23:20,583][87426] Updated weights for policy 1, policy_version 44840 (0.0009) -[2023-11-28 01:23:20,786][87424] Updated weights for policy 0, policy_version 44966 (0.0010) -[2023-11-28 01:23:20,953][87426] Updated weights for policy 1, policy_version 44850 (0.0007) -[2023-11-28 01:23:21,168][87424] Updated weights for policy 0, policy_version 44976 (0.0012) -[2023-11-28 01:23:21,330][87426] Updated weights for policy 1, policy_version 44860 (0.0011) -[2023-11-28 01:23:21,560][87424] Updated weights for policy 0, policy_version 44986 (0.0011) -[2023-11-28 01:23:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23003136. Throughput: 0: 2706.4, 1: 2684.5. Samples: 23022384. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:23:23,445][86177] Avg episode reward: [(0, '-549.540'), (1, '-530.230')] -[2023-11-28 01:23:23,803][87426] Updated weights for policy 1, policy_version 44870 (0.0010) -[2023-11-28 01:23:23,809][87424] Updated weights for policy 0, policy_version 44996 (0.0011) -[2023-11-28 01:23:24,183][87426] Updated weights for policy 1, policy_version 44880 (0.0008) -[2023-11-28 01:23:24,194][87424] Updated weights for policy 0, policy_version 45006 (0.0009) -[2023-11-28 01:23:24,567][87426] Updated weights for policy 1, policy_version 44890 (0.0007) -[2023-11-28 01:23:24,574][87424] Updated weights for policy 0, policy_version 45016 (0.0008) -[2023-11-28 01:23:26,661][87426] Updated weights for policy 1, policy_version 44900 (0.0009) -[2023-11-28 01:23:27,036][87426] Updated weights for policy 1, policy_version 44910 (0.0012) -[2023-11-28 01:23:27,061][87424] Updated weights for policy 0, policy_version 45026 (0.0008) -[2023-11-28 01:23:27,413][87426] Updated weights for policy 1, policy_version 44920 (0.0011) -[2023-11-28 01:23:27,448][87424] Updated weights for policy 0, policy_version 45036 (0.0008) -[2023-11-28 01:23:27,837][87424] Updated weights for policy 0, policy_version 45046 (0.0007) -[2023-11-28 01:23:28,220][87424] Updated weights for policy 0, policy_version 45056 (0.0008) -[2023-11-28 01:23:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23035904. Throughput: 0: 2718.1, 1: 2698.6. Samples: 23046972. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:23:28,445][86177] Avg episode reward: [(0, '-549.190'), (1, '-552.180')] -[2023-11-28 01:23:29,340][87426] Updated weights for policy 1, policy_version 44930 (0.0010) -[2023-11-28 01:23:29,719][87426] Updated weights for policy 1, policy_version 44940 (0.0011) -[2023-11-28 01:23:30,100][87426] Updated weights for policy 1, policy_version 44950 (0.0012) -[2023-11-28 01:23:30,477][87426] Updated weights for policy 1, policy_version 44960 (0.0011) -[2023-11-28 01:23:30,709][87424] Updated weights for policy 0, policy_version 45066 (0.0009) -[2023-11-28 01:23:31,088][87424] Updated weights for policy 0, policy_version 45076 (0.0008) -[2023-11-28 01:23:31,467][87424] Updated weights for policy 0, policy_version 45086 (0.0008) -[2023-11-28 01:23:32,785][87426] Updated weights for policy 1, policy_version 44970 (0.0012) -[2023-11-28 01:23:33,155][87426] Updated weights for policy 1, policy_version 44980 (0.0010) -[2023-11-28 01:23:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 23052288. Throughput: 0: 2706.8, 1: 2695.1. Samples: 23070628. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:23:33,445][86177] Avg episode reward: [(0, '-497.990'), (1, '-539.770')] -[2023-11-28 01:23:33,477][87424] Updated weights for policy 0, policy_version 45096 (0.0011) -[2023-11-28 01:23:33,536][87426] Updated weights for policy 1, policy_version 44990 (0.0009) -[2023-11-28 01:23:33,863][87424] Updated weights for policy 0, policy_version 45106 (0.0012) -[2023-11-28 01:23:34,257][87424] Updated weights for policy 0, policy_version 45116 (0.0012) -[2023-11-28 01:23:35,262][87426] Updated weights for policy 1, policy_version 45000 (0.0011) -[2023-11-28 01:23:35,640][87426] Updated weights for policy 1, policy_version 45010 (0.0012) -[2023-11-28 01:23:36,016][87426] Updated weights for policy 1, policy_version 45020 (0.0009) -[2023-11-28 01:23:36,633][87424] Updated weights for policy 0, policy_version 45126 (0.0012) -[2023-11-28 01:23:37,004][87424] Updated weights for policy 0, policy_version 45136 (0.0012) -[2023-11-28 01:23:37,392][87424] Updated weights for policy 0, policy_version 45146 (0.0012) -[2023-11-28 01:23:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23085056. Throughput: 0: 2707.0, 1: 2712.4. Samples: 23102488. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:23:38,445][86177] Avg episode reward: [(0, '-515.830'), (1, '-535.030')] -[2023-11-28 01:23:38,586][87426] Updated weights for policy 1, policy_version 45030 (0.0010) -[2023-11-28 01:23:38,966][87426] Updated weights for policy 1, policy_version 45040 (0.0011) -[2023-11-28 01:23:39,335][87426] Updated weights for policy 1, policy_version 45050 (0.0011) -[2023-11-28 01:23:39,443][87424] Updated weights for policy 0, policy_version 45156 (0.0010) -[2023-11-28 01:23:39,827][87424] Updated weights for policy 0, policy_version 45166 (0.0010) -[2023-11-28 01:23:40,208][87424] Updated weights for policy 0, policy_version 45176 (0.0012) -[2023-11-28 01:23:41,191][87426] Updated weights for policy 1, policy_version 45060 (0.0012) -[2023-11-28 01:23:41,565][87426] Updated weights for policy 1, policy_version 45070 (0.0012) -[2023-11-28 01:23:41,946][87426] Updated weights for policy 1, policy_version 45080 (0.0011) -[2023-11-28 01:23:42,358][87424] Updated weights for policy 0, policy_version 45186 (0.0011) -[2023-11-28 01:23:42,751][87424] Updated weights for policy 0, policy_version 45196 (0.0009) -[2023-11-28 01:23:43,131][87424] Updated weights for policy 0, policy_version 45206 (0.0012) -[2023-11-28 01:23:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 23109632. Throughput: 0: 2703.6, 1: 2659.8. Samples: 23125792. Policy #0 lag: (min: 31.0, avg: 43.3, max: 63.0) -[2023-11-28 01:23:43,445][86177] Avg episode reward: [(0, '-517.180'), (1, '-535.560')] -[2023-11-28 01:23:43,517][87424] Updated weights for policy 0, policy_version 45216 (0.0012) -[2023-11-28 01:23:44,678][87426] Updated weights for policy 1, policy_version 45090 (0.0011) -[2023-11-28 01:23:45,059][87426] Updated weights for policy 1, policy_version 45100 (0.0007) -[2023-11-28 01:23:45,438][87426] Updated weights for policy 1, policy_version 45110 (0.0010) -[2023-11-28 01:23:45,512][87424] Updated weights for policy 0, policy_version 45226 (0.0011) -[2023-11-28 01:23:45,814][87426] Updated weights for policy 1, policy_version 45120 (0.0008) -[2023-11-28 01:23:45,891][87424] Updated weights for policy 0, policy_version 45236 (0.0011) -[2023-11-28 01:23:46,276][87424] Updated weights for policy 0, policy_version 45246 (0.0012) -[2023-11-28 01:23:48,130][87424] Updated weights for policy 0, policy_version 45256 (0.0010) -[2023-11-28 01:23:48,336][87426] Updated weights for policy 1, policy_version 45130 (0.0011) -[2023-11-28 01:23:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 23134208. Throughput: 0: 2708.6, 1: 2644.2. Samples: 23150716. Policy #0 lag: (min: 31.0, avg: 34.7, max: 57.0) -[2023-11-28 01:23:48,445][86177] Avg episode reward: [(0, '-584.580'), (1, '-535.420')] -[2023-11-28 01:23:48,519][87424] Updated weights for policy 0, policy_version 45266 (0.0010) -[2023-11-28 01:23:48,713][87426] Updated weights for policy 1, policy_version 45140 (0.0009) -[2023-11-28 01:23:48,896][87424] Updated weights for policy 0, policy_version 45276 (0.0011) -[2023-11-28 01:23:49,089][87426] Updated weights for policy 1, policy_version 45150 (0.0011) -[2023-11-28 01:23:50,914][87426] Updated weights for policy 1, policy_version 45160 (0.0011) -[2023-11-28 01:23:51,091][87424] Updated weights for policy 0, policy_version 45286 (0.0011) -[2023-11-28 01:23:51,289][87426] Updated weights for policy 1, policy_version 45170 (0.0011) -[2023-11-28 01:23:51,463][87424] Updated weights for policy 0, policy_version 45296 (0.0012) -[2023-11-28 01:23:51,669][87426] Updated weights for policy 1, policy_version 45180 (0.0010) -[2023-11-28 01:23:51,842][87424] Updated weights for policy 0, policy_version 45306 (0.0011) -[2023-11-28 01:23:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23166976. Throughput: 0: 2706.0, 1: 2645.6. Samples: 23183160. Policy #0 lag: (min: 31.0, avg: 34.7, max: 57.0) -[2023-11-28 01:23:53,445][86177] Avg episode reward: [(0, '-619.390'), (1, '-520.400')] -[2023-11-28 01:23:54,226][87426] Updated weights for policy 1, policy_version 45190 (0.0010) -[2023-11-28 01:23:54,387][87424] Updated weights for policy 0, policy_version 45316 (0.0010) -[2023-11-28 01:23:54,618][87426] Updated weights for policy 1, policy_version 45200 (0.0011) -[2023-11-28 01:23:54,779][87424] Updated weights for policy 0, policy_version 45326 (0.0008) -[2023-11-28 01:23:55,004][87426] Updated weights for policy 1, policy_version 45210 (0.0011) -[2023-11-28 01:23:55,169][87424] Updated weights for policy 0, policy_version 45336 (0.0009) -[2023-11-28 01:23:56,929][87424] Updated weights for policy 0, policy_version 45346 (0.0012) -[2023-11-28 01:23:57,095][87426] Updated weights for policy 1, policy_version 45220 (0.0011) -[2023-11-28 01:23:57,319][87424] Updated weights for policy 0, policy_version 45356 (0.0010) -[2023-11-28 01:23:57,473][87426] Updated weights for policy 1, policy_version 45230 (0.0009) -[2023-11-28 01:23:57,704][87424] Updated weights for policy 0, policy_version 45366 (0.0009) -[2023-11-28 01:23:57,857][87426] Updated weights for policy 1, policy_version 45240 (0.0012) -[2023-11-28 01:23:58,085][87424] Updated weights for policy 0, policy_version 45376 (0.0011) -[2023-11-28 01:23:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23199744. Throughput: 0: 2705.8, 1: 2657.4. Samples: 23207924. Policy #0 lag: (min: 31.0, avg: 34.7, max: 57.0) -[2023-11-28 01:23:58,445][86177] Avg episode reward: [(0, '-603.730'), (1, '-566.880')] -[2023-11-28 01:23:59,671][87426] Updated weights for policy 1, policy_version 45250 (0.0011) -[2023-11-28 01:24:00,049][87426] Updated weights for policy 1, policy_version 45260 (0.0010) -[2023-11-28 01:24:00,144][87424] Updated weights for policy 0, policy_version 45386 (0.0010) -[2023-11-28 01:24:00,427][87426] Updated weights for policy 1, policy_version 45270 (0.0008) -[2023-11-28 01:24:00,542][87424] Updated weights for policy 0, policy_version 45396 (0.0012) -[2023-11-28 01:24:00,808][87426] Updated weights for policy 1, policy_version 45280 (0.0007) -[2023-11-28 01:24:00,921][87424] Updated weights for policy 0, policy_version 45406 (0.0012) -[2023-11-28 01:24:02,795][87426] Updated weights for policy 1, policy_version 45290 (0.0012) -[2023-11-28 01:24:03,164][87426] Updated weights for policy 1, policy_version 45300 (0.0012) -[2023-11-28 01:24:03,247][87424] Updated weights for policy 0, policy_version 45416 (0.0008) -[2023-11-28 01:24:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 23216128. Throughput: 0: 2720.5, 1: 2657.3. Samples: 23232552. Policy #0 lag: (min: 31.0, avg: 34.7, max: 57.0) -[2023-11-28 01:24:03,445][86177] Avg episode reward: [(0, '-605.370'), (1, '-572.030')] -[2023-11-28 01:24:03,541][87426] Updated weights for policy 1, policy_version 45310 (0.0011) -[2023-11-28 01:24:03,628][87424] Updated weights for policy 0, policy_version 45426 (0.0009) -[2023-11-28 01:24:04,003][87424] Updated weights for policy 0, policy_version 45436 (0.0009) -[2023-11-28 01:24:05,860][87426] Updated weights for policy 1, policy_version 45320 (0.0009) -[2023-11-28 01:24:05,995][87424] Updated weights for policy 0, policy_version 45446 (0.0009) -[2023-11-28 01:24:06,245][87426] Updated weights for policy 1, policy_version 45330 (0.0010) -[2023-11-28 01:24:06,399][87424] Updated weights for policy 0, policy_version 45456 (0.0012) -[2023-11-28 01:24:06,632][87426] Updated weights for policy 1, policy_version 45340 (0.0008) -[2023-11-28 01:24:06,779][87424] Updated weights for policy 0, policy_version 45466 (0.0011) -[2023-11-28 01:24:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 23248896. Throughput: 0: 2705.2, 1: 2665.1. Samples: 23264048. Policy #0 lag: (min: 31.0, avg: 34.7, max: 57.0) -[2023-11-28 01:24:08,445][86177] Avg episode reward: [(0, '-547.160'), (1, '-568.100')] -[2023-11-28 01:24:08,996][87424] Updated weights for policy 0, policy_version 45476 (0.0010) -[2023-11-28 01:24:09,121][87426] Updated weights for policy 1, policy_version 45350 (0.0011) -[2023-11-28 01:24:09,378][87424] Updated weights for policy 0, policy_version 45486 (0.0008) -[2023-11-28 01:24:09,498][87426] Updated weights for policy 1, policy_version 45360 (0.0010) -[2023-11-28 01:24:09,761][87424] Updated weights for policy 0, policy_version 45496 (0.0008) -[2023-11-28 01:24:09,886][87426] Updated weights for policy 1, policy_version 45370 (0.0008) -[2023-11-28 01:24:12,157][87424] Updated weights for policy 0, policy_version 45506 (0.0011) -[2023-11-28 01:24:12,388][87426] Updated weights for policy 1, policy_version 45380 (0.0009) -[2023-11-28 01:24:12,537][87424] Updated weights for policy 0, policy_version 45516 (0.0012) -[2023-11-28 01:24:12,769][87426] Updated weights for policy 1, policy_version 45390 (0.0011) -[2023-11-28 01:24:12,912][87424] Updated weights for policy 0, policy_version 45526 (0.0010) -[2023-11-28 01:24:13,151][87426] Updated weights for policy 1, policy_version 45400 (0.0011) -[2023-11-28 01:24:13,296][87424] Updated weights for policy 0, policy_version 45536 (0.0007) -[2023-11-28 01:24:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 23273472. Throughput: 0: 2712.6, 1: 2644.3. Samples: 23288032. Policy #0 lag: (min: 31.0, avg: 34.7, max: 57.0) -[2023-11-28 01:24:13,445][86177] Avg episode reward: [(0, '-513.420'), (1, '-568.920')] -[2023-11-28 01:24:15,257][87424] Updated weights for policy 0, policy_version 45546 (0.0012) -[2023-11-28 01:24:15,561][87426] Updated weights for policy 1, policy_version 45410 (0.0012) -[2023-11-28 01:24:15,636][87424] Updated weights for policy 0, policy_version 45556 (0.0010) -[2023-11-28 01:24:15,941][87426] Updated weights for policy 1, policy_version 45420 (0.0010) -[2023-11-28 01:24:16,017][87424] Updated weights for policy 0, policy_version 45566 (0.0007) -[2023-11-28 01:24:16,319][87426] Updated weights for policy 1, policy_version 45430 (0.0008) -[2023-11-28 01:24:16,698][87426] Updated weights for policy 1, policy_version 45440 (0.0007) -[2023-11-28 01:24:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 23298048. Throughput: 0: 2744.9, 1: 2644.1. Samples: 23313136. Policy #0 lag: (min: 31.0, avg: 49.4, max: 63.0) -[2023-11-28 01:24:18,446][86177] Avg episode reward: [(0, '-512.410'), (1, '-529.830')] -[2023-11-28 01:24:18,570][87424] Updated weights for policy 0, policy_version 45576 (0.0007) -[2023-11-28 01:24:18,715][87426] Updated weights for policy 1, policy_version 45450 (0.0012) -[2023-11-28 01:24:18,963][87424] Updated weights for policy 0, policy_version 45586 (0.0012) -[2023-11-28 01:24:19,099][87426] Updated weights for policy 1, policy_version 45460 (0.0011) -[2023-11-28 01:24:19,338][87424] Updated weights for policy 0, policy_version 45596 (0.0009) -[2023-11-28 01:24:19,477][87426] Updated weights for policy 1, policy_version 45470 (0.0011) -[2023-11-28 01:24:19,489][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000045600_11673600.pth... -[2023-11-28 01:24:19,520][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000043040_11018240.pth -[2023-11-28 01:24:19,546][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000045472_11640832.pth... -[2023-11-28 01:24:19,579][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000042912_10985472.pth -[2023-11-28 01:24:21,653][87426] Updated weights for policy 1, policy_version 45480 (0.0009) -[2023-11-28 01:24:21,844][87424] Updated weights for policy 0, policy_version 45606 (0.0010) -[2023-11-28 01:24:22,032][87426] Updated weights for policy 1, policy_version 45490 (0.0011) -[2023-11-28 01:24:22,227][87424] Updated weights for policy 0, policy_version 45616 (0.0011) -[2023-11-28 01:24:22,406][87426] Updated weights for policy 1, policy_version 45500 (0.0011) -[2023-11-28 01:24:22,611][87424] Updated weights for policy 0, policy_version 45626 (0.0009) -[2023-11-28 01:24:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23330816. Throughput: 0: 2730.8, 1: 2647.3. Samples: 23344500. Policy #0 lag: (min: 31.0, avg: 49.4, max: 63.0) -[2023-11-28 01:24:23,445][86177] Avg episode reward: [(0, '-513.190'), (1, '-540.470')] -[2023-11-28 01:24:24,721][87424] Updated weights for policy 0, policy_version 45636 (0.0009) -[2023-11-28 01:24:24,880][87426] Updated weights for policy 1, policy_version 45510 (0.0012) -[2023-11-28 01:24:25,105][87424] Updated weights for policy 0, policy_version 45646 (0.0008) -[2023-11-28 01:24:25,251][87426] Updated weights for policy 1, policy_version 45520 (0.0012) -[2023-11-28 01:24:25,495][87424] Updated weights for policy 0, policy_version 45656 (0.0009) -[2023-11-28 01:24:25,627][87426] Updated weights for policy 1, policy_version 45530 (0.0009) -[2023-11-28 01:24:27,482][87424] Updated weights for policy 0, policy_version 45666 (0.0011) -[2023-11-28 01:24:27,875][87424] Updated weights for policy 0, policy_version 45676 (0.0008) -[2023-11-28 01:24:28,016][87426] Updated weights for policy 1, policy_version 45540 (0.0008) -[2023-11-28 01:24:28,272][87424] Updated weights for policy 0, policy_version 45686 (0.0012) -[2023-11-28 01:24:28,409][87426] Updated weights for policy 1, policy_version 45550 (0.0011) -[2023-11-28 01:24:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 23347200. Throughput: 0: 2734.0, 1: 2674.6. Samples: 23369180. Policy #0 lag: (min: 31.0, avg: 49.4, max: 63.0) -[2023-11-28 01:24:28,445][86177] Avg episode reward: [(0, '-506.800'), (1, '-540.950')] -[2023-11-28 01:24:28,642][87424] Updated weights for policy 0, policy_version 45696 (0.0010) -[2023-11-28 01:24:28,801][87426] Updated weights for policy 1, policy_version 45560 (0.0008) -[2023-11-28 01:24:30,749][87424] Updated weights for policy 0, policy_version 45706 (0.0012) -[2023-11-28 01:24:31,132][87424] Updated weights for policy 0, policy_version 45716 (0.0011) -[2023-11-28 01:24:31,200][87426] Updated weights for policy 1, policy_version 45570 (0.0009) -[2023-11-28 01:24:31,513][87424] Updated weights for policy 0, policy_version 45726 (0.0012) -[2023-11-28 01:24:31,580][87426] Updated weights for policy 1, policy_version 45580 (0.0008) -[2023-11-28 01:24:31,959][87426] Updated weights for policy 1, policy_version 45590 (0.0010) -[2023-11-28 01:24:32,340][87426] Updated weights for policy 1, policy_version 45600 (0.0009) -[2023-11-28 01:24:33,351][87424] Updated weights for policy 0, policy_version 45736 (0.0008) -[2023-11-28 01:24:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 23379968. Throughput: 0: 2725.2, 1: 2665.7. Samples: 23393308. Policy #0 lag: (min: 31.0, avg: 49.4, max: 63.0) -[2023-11-28 01:24:33,445][86177] Avg episode reward: [(0, '-526.080'), (1, '-538.790')] -[2023-11-28 01:24:33,731][87424] Updated weights for policy 0, policy_version 45746 (0.0008) -[2023-11-28 01:24:34,118][87424] Updated weights for policy 0, policy_version 45756 (0.0009) -[2023-11-28 01:24:34,288][87426] Updated weights for policy 1, policy_version 45610 (0.0008) -[2023-11-28 01:24:34,670][87426] Updated weights for policy 1, policy_version 45620 (0.0008) -[2023-11-28 01:24:35,052][87426] Updated weights for policy 1, policy_version 45630 (0.0008) -[2023-11-28 01:24:36,659][87424] Updated weights for policy 0, policy_version 45766 (0.0012) -[2023-11-28 01:24:37,035][87424] Updated weights for policy 0, policy_version 45776 (0.0011) -[2023-11-28 01:24:37,192][87426] Updated weights for policy 1, policy_version 45640 (0.0011) -[2023-11-28 01:24:37,417][87424] Updated weights for policy 0, policy_version 45786 (0.0010) -[2023-11-28 01:24:37,569][87426] Updated weights for policy 1, policy_version 45650 (0.0012) -[2023-11-28 01:24:37,942][87426] Updated weights for policy 1, policy_version 45660 (0.0011) -[2023-11-28 01:24:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23412736. Throughput: 0: 2711.0, 1: 2680.7. Samples: 23425788. Policy #0 lag: (min: 31.0, avg: 49.4, max: 63.0) -[2023-11-28 01:24:38,445][86177] Avg episode reward: [(0, '-540.140'), (1, '-516.550')] -[2023-11-28 01:24:39,617][87424] Updated weights for policy 0, policy_version 45796 (0.0009) -[2023-11-28 01:24:40,001][87424] Updated weights for policy 0, policy_version 45806 (0.0012) -[2023-11-28 01:24:40,199][87426] Updated weights for policy 1, policy_version 45670 (0.0011) -[2023-11-28 01:24:40,382][87424] Updated weights for policy 0, policy_version 45816 (0.0011) -[2023-11-28 01:24:40,575][87426] Updated weights for policy 1, policy_version 45680 (0.0010) -[2023-11-28 01:24:40,955][87426] Updated weights for policy 1, policy_version 45690 (0.0007) -[2023-11-28 01:24:42,925][87424] Updated weights for policy 0, policy_version 45826 (0.0011) -[2023-11-28 01:24:43,079][87426] Updated weights for policy 1, policy_version 45700 (0.0009) -[2023-11-28 01:24:43,305][87424] Updated weights for policy 0, policy_version 45836 (0.0010) -[2023-11-28 01:24:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 23429120. Throughput: 0: 2708.5, 1: 2670.8. Samples: 23449996. Policy #0 lag: (min: 31.0, avg: 49.4, max: 63.0) -[2023-11-28 01:24:43,445][86177] Avg episode reward: [(0, '-560.880'), (1, '-505.990')] -[2023-11-28 01:24:43,457][87426] Updated weights for policy 1, policy_version 45710 (0.0011) -[2023-11-28 01:24:43,690][87424] Updated weights for policy 0, policy_version 45846 (0.0009) -[2023-11-28 01:24:43,839][87426] Updated weights for policy 1, policy_version 45720 (0.0011) -[2023-11-28 01:24:44,077][87424] Updated weights for policy 0, policy_version 45856 (0.0011) -[2023-11-28 01:24:45,919][87424] Updated weights for policy 0, policy_version 45866 (0.0012) -[2023-11-28 01:24:45,982][87426] Updated weights for policy 1, policy_version 45730 (0.0011) -[2023-11-28 01:24:46,306][87424] Updated weights for policy 0, policy_version 45876 (0.0012) -[2023-11-28 01:24:46,361][87426] Updated weights for policy 1, policy_version 45740 (0.0012) -[2023-11-28 01:24:46,691][87424] Updated weights for policy 0, policy_version 45886 (0.0011) -[2023-11-28 01:24:46,730][87426] Updated weights for policy 1, policy_version 45750 (0.0012) -[2023-11-28 01:24:47,106][87426] Updated weights for policy 1, policy_version 45760 (0.0012) -[2023-11-28 01:24:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 23461888. Throughput: 0: 2711.6, 1: 2673.3. Samples: 23474876. Policy #0 lag: (min: 10.0, avg: 31.3, max: 44.0) -[2023-11-28 01:24:48,446][86177] Avg episode reward: [(0, '-573.990'), (1, '-500.000')] -[2023-11-28 01:24:48,447][87424] Updated weights for policy 0, policy_version 45896 (0.0011) -[2023-11-28 01:24:48,837][87424] Updated weights for policy 0, policy_version 45906 (0.0011) -[2023-11-28 01:24:48,951][87426] Updated weights for policy 1, policy_version 45770 (0.0012) -[2023-11-28 01:24:49,213][87424] Updated weights for policy 0, policy_version 45916 (0.0011) -[2023-11-28 01:24:49,331][87426] Updated weights for policy 1, policy_version 45780 (0.0011) -[2023-11-28 01:24:49,707][87426] Updated weights for policy 1, policy_version 45790 (0.0011) -[2023-11-28 01:24:51,550][87424] Updated weights for policy 0, policy_version 45926 (0.0011) -[2023-11-28 01:24:51,929][87424] Updated weights for policy 0, policy_version 45936 (0.0012) -[2023-11-28 01:24:52,284][87426] Updated weights for policy 1, policy_version 45800 (0.0011) -[2023-11-28 01:24:52,318][87424] Updated weights for policy 0, policy_version 45946 (0.0011) -[2023-11-28 01:24:52,664][87426] Updated weights for policy 1, policy_version 45810 (0.0008) -[2023-11-28 01:24:53,046][87426] Updated weights for policy 1, policy_version 45820 (0.0011) -[2023-11-28 01:24:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23494656. Throughput: 0: 2720.4, 1: 2704.1. Samples: 23508152. Policy #0 lag: (min: 10.0, avg: 31.3, max: 44.0) -[2023-11-28 01:24:53,445][86177] Avg episode reward: [(0, '-553.630'), (1, '-510.320')] -[2023-11-28 01:24:54,526][87424] Updated weights for policy 0, policy_version 45956 (0.0010) -[2023-11-28 01:24:54,908][87424] Updated weights for policy 0, policy_version 45966 (0.0008) -[2023-11-28 01:24:55,286][87426] Updated weights for policy 1, policy_version 45830 (0.0009) -[2023-11-28 01:24:55,294][87424] Updated weights for policy 0, policy_version 45976 (0.0008) -[2023-11-28 01:24:55,669][87426] Updated weights for policy 1, policy_version 45840 (0.0007) -[2023-11-28 01:24:56,049][87426] Updated weights for policy 1, policy_version 45850 (0.0007) -[2023-11-28 01:24:57,143][87424] Updated weights for policy 0, policy_version 45986 (0.0007) -[2023-11-28 01:24:57,525][87424] Updated weights for policy 0, policy_version 45996 (0.0009) -[2023-11-28 01:24:57,919][87424] Updated weights for policy 0, policy_version 46006 (0.0009) -[2023-11-28 01:24:58,090][87426] Updated weights for policy 1, policy_version 45860 (0.0009) -[2023-11-28 01:24:58,295][87424] Updated weights for policy 0, policy_version 46016 (0.0007) -[2023-11-28 01:24:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 23519232. Throughput: 0: 2704.4, 1: 2718.1. Samples: 23532044. Policy #0 lag: (min: 10.0, avg: 31.3, max: 44.0) -[2023-11-28 01:24:58,446][86177] Avg episode reward: [(0, '-543.170'), (1, '-512.610')] -[2023-11-28 01:24:58,474][87426] Updated weights for policy 1, policy_version 45870 (0.0012) -[2023-11-28 01:24:58,850][87426] Updated weights for policy 1, policy_version 45880 (0.0012) -[2023-11-28 01:25:00,547][87424] Updated weights for policy 0, policy_version 46026 (0.0010) -[2023-11-28 01:25:00,935][87424] Updated weights for policy 0, policy_version 46036 (0.0012) -[2023-11-28 01:25:01,313][87424] Updated weights for policy 0, policy_version 46046 (0.0011) -[2023-11-28 01:25:01,325][87426] Updated weights for policy 1, policy_version 45890 (0.0009) -[2023-11-28 01:25:01,700][87426] Updated weights for policy 1, policy_version 45900 (0.0012) -[2023-11-28 01:25:02,079][87426] Updated weights for policy 1, policy_version 45910 (0.0009) -[2023-11-28 01:25:02,458][87426] Updated weights for policy 1, policy_version 45920 (0.0011) -[2023-11-28 01:25:03,192][87424] Updated weights for policy 0, policy_version 46056 (0.0012) -[2023-11-28 01:25:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 23543808. Throughput: 0: 2689.3, 1: 2706.4. Samples: 23555940. Policy #0 lag: (min: 10.0, avg: 31.3, max: 44.0) -[2023-11-28 01:25:03,446][86177] Avg episode reward: [(0, '-513.020'), (1, '-511.980')] -[2023-11-28 01:25:03,580][87424] Updated weights for policy 0, policy_version 46066 (0.0012) -[2023-11-28 01:25:03,977][87424] Updated weights for policy 0, policy_version 46076 (0.0009) -[2023-11-28 01:25:04,521][87426] Updated weights for policy 1, policy_version 45930 (0.0011) -[2023-11-28 01:25:04,898][87426] Updated weights for policy 1, policy_version 45940 (0.0007) -[2023-11-28 01:25:05,276][87426] Updated weights for policy 1, policy_version 45950 (0.0008) -[2023-11-28 01:25:06,088][87424] Updated weights for policy 0, policy_version 46086 (0.0007) -[2023-11-28 01:25:06,475][87424] Updated weights for policy 0, policy_version 46096 (0.0007) -[2023-11-28 01:25:06,864][87424] Updated weights for policy 0, policy_version 46106 (0.0010) -[2023-11-28 01:25:07,708][87426] Updated weights for policy 1, policy_version 45960 (0.0008) -[2023-11-28 01:25:08,087][87426] Updated weights for policy 1, policy_version 45970 (0.0007) -[2023-11-28 01:25:08,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 23568384. Throughput: 0: 2736.8, 1: 2704.7. Samples: 23589368. Policy #0 lag: (min: 10.0, avg: 31.3, max: 44.0) -[2023-11-28 01:25:08,446][86177] Avg episode reward: [(0, '-511.510'), (1, '-512.240')] -[2023-11-28 01:25:08,467][87426] Updated weights for policy 1, policy_version 45980 (0.0007) -[2023-11-28 01:25:08,719][87424] Updated weights for policy 0, policy_version 46116 (0.0011) -[2023-11-28 01:25:09,111][87424] Updated weights for policy 0, policy_version 46126 (0.0012) -[2023-11-28 01:25:09,487][87424] Updated weights for policy 0, policy_version 46136 (0.0012) -[2023-11-28 01:25:10,624][87426] Updated weights for policy 1, policy_version 45990 (0.0008) -[2023-11-28 01:25:10,991][87426] Updated weights for policy 1, policy_version 46000 (0.0008) -[2023-11-28 01:25:11,375][87426] Updated weights for policy 1, policy_version 46010 (0.0008) -[2023-11-28 01:25:12,033][87424] Updated weights for policy 0, policy_version 46146 (0.0011) -[2023-11-28 01:25:12,421][87424] Updated weights for policy 0, policy_version 46156 (0.0009) -[2023-11-28 01:25:12,806][87424] Updated weights for policy 0, policy_version 46166 (0.0010) -[2023-11-28 01:25:13,194][87424] Updated weights for policy 0, policy_version 46176 (0.0009) -[2023-11-28 01:25:13,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23601152. Throughput: 0: 2731.4, 1: 2682.6. Samples: 23612808. Policy #0 lag: (min: 10.0, avg: 31.3, max: 44.0) -[2023-11-28 01:25:13,445][86177] Avg episode reward: [(0, '-508.290'), (1, '-501.250')] -[2023-11-28 01:25:13,743][87426] Updated weights for policy 1, policy_version 46020 (0.0010) -[2023-11-28 01:25:14,130][87426] Updated weights for policy 1, policy_version 46030 (0.0012) -[2023-11-28 01:25:14,499][87426] Updated weights for policy 1, policy_version 46040 (0.0012) -[2023-11-28 01:25:15,627][87424] Updated weights for policy 0, policy_version 46186 (0.0011) -[2023-11-28 01:25:16,010][87424] Updated weights for policy 0, policy_version 46196 (0.0011) -[2023-11-28 01:25:16,389][87424] Updated weights for policy 0, policy_version 46206 (0.0008) -[2023-11-28 01:25:16,479][87426] Updated weights for policy 1, policy_version 46050 (0.0012) -[2023-11-28 01:25:16,855][87426] Updated weights for policy 1, policy_version 46060 (0.0012) -[2023-11-28 01:25:17,230][87426] Updated weights for policy 1, policy_version 46070 (0.0012) -[2023-11-28 01:25:17,601][87426] Updated weights for policy 1, policy_version 46080 (0.0012) -[2023-11-28 01:25:18,171][87424] Updated weights for policy 0, policy_version 46216 (0.0007) -[2023-11-28 01:25:18,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 23625728. Throughput: 0: 2710.3, 1: 2692.6. Samples: 23636440. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 01:25:18,445][86177] Avg episode reward: [(0, '-540.870'), (1, '-498.740')] -[2023-11-28 01:25:18,553][87424] Updated weights for policy 0, policy_version 46226 (0.0008) -[2023-11-28 01:25:18,923][87424] Updated weights for policy 0, policy_version 46236 (0.0008) -[2023-11-28 01:25:19,968][87426] Updated weights for policy 1, policy_version 46090 (0.0009) -[2023-11-28 01:25:20,348][87426] Updated weights for policy 1, policy_version 46100 (0.0011) -[2023-11-28 01:25:20,725][87426] Updated weights for policy 1, policy_version 46110 (0.0009) -[2023-11-28 01:25:21,387][87424] Updated weights for policy 0, policy_version 46246 (0.0010) -[2023-11-28 01:25:21,767][87424] Updated weights for policy 0, policy_version 46256 (0.0012) -[2023-11-28 01:25:22,154][87424] Updated weights for policy 0, policy_version 46266 (0.0012) -[2023-11-28 01:25:23,034][87426] Updated weights for policy 1, policy_version 46120 (0.0011) -[2023-11-28 01:25:23,413][87426] Updated weights for policy 1, policy_version 46130 (0.0008) -[2023-11-28 01:25:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 23650304. Throughput: 0: 2712.2, 1: 2685.2. Samples: 23668672. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 01:25:23,445][86177] Avg episode reward: [(0, '-551.540'), (1, '-498.100')] -[2023-11-28 01:25:23,791][87426] Updated weights for policy 1, policy_version 46140 (0.0011) -[2023-11-28 01:25:24,814][87424] Updated weights for policy 0, policy_version 46276 (0.0012) -[2023-11-28 01:25:25,194][87424] Updated weights for policy 0, policy_version 46286 (0.0012) -[2023-11-28 01:25:25,566][87426] Updated weights for policy 1, policy_version 46150 (0.0009) -[2023-11-28 01:25:25,575][87424] Updated weights for policy 0, policy_version 46296 (0.0008) -[2023-11-28 01:25:25,948][87426] Updated weights for policy 1, policy_version 46160 (0.0010) -[2023-11-28 01:25:26,329][87426] Updated weights for policy 1, policy_version 46170 (0.0011) -[2023-11-28 01:25:27,903][87424] Updated weights for policy 0, policy_version 46306 (0.0008) -[2023-11-28 01:25:27,992][87426] Updated weights for policy 1, policy_version 46180 (0.0011) -[2023-11-28 01:25:28,286][87424] Updated weights for policy 0, policy_version 46316 (0.0007) -[2023-11-28 01:25:28,382][87426] Updated weights for policy 1, policy_version 46190 (0.0012) -[2023-11-28 01:25:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 23674880. Throughput: 0: 2714.3, 1: 2708.9. Samples: 23694040. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 01:25:28,446][86177] Avg episode reward: [(0, '-546.460'), (1, '-498.580')] -[2023-11-28 01:25:28,677][87424] Updated weights for policy 0, policy_version 46326 (0.0008) -[2023-11-28 01:25:28,759][87426] Updated weights for policy 1, policy_version 46200 (0.0011) -[2023-11-28 01:25:29,061][87424] Updated weights for policy 0, policy_version 46336 (0.0011) -[2023-11-28 01:25:31,056][87426] Updated weights for policy 1, policy_version 46210 (0.0011) -[2023-11-28 01:25:31,321][87424] Updated weights for policy 0, policy_version 46346 (0.0008) -[2023-11-28 01:25:31,436][87426] Updated weights for policy 1, policy_version 46220 (0.0007) -[2023-11-28 01:25:31,704][87424] Updated weights for policy 0, policy_version 46356 (0.0009) -[2023-11-28 01:25:31,810][87426] Updated weights for policy 1, policy_version 46230 (0.0011) -[2023-11-28 01:25:32,090][87424] Updated weights for policy 0, policy_version 46366 (0.0010) -[2023-11-28 01:25:32,198][87426] Updated weights for policy 1, policy_version 46240 (0.0010) -[2023-11-28 01:25:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 23707648. Throughput: 0: 2706.8, 1: 2719.1. Samples: 23719040. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 01:25:33,446][86177] Avg episode reward: [(0, '-541.040'), (1, '-499.030')] -[2023-11-28 01:25:34,156][87426] Updated weights for policy 1, policy_version 46250 (0.0008) -[2023-11-28 01:25:34,314][87424] Updated weights for policy 0, policy_version 46376 (0.0011) -[2023-11-28 01:25:34,529][87426] Updated weights for policy 1, policy_version 46260 (0.0007) -[2023-11-28 01:25:34,703][87424] Updated weights for policy 0, policy_version 46386 (0.0010) -[2023-11-28 01:25:34,913][87426] Updated weights for policy 1, policy_version 46270 (0.0008) -[2023-11-28 01:25:35,090][87424] Updated weights for policy 0, policy_version 46396 (0.0010) -[2023-11-28 01:25:36,718][87424] Updated weights for policy 0, policy_version 46406 (0.0010) -[2023-11-28 01:25:37,102][87424] Updated weights for policy 0, policy_version 46416 (0.0011) -[2023-11-28 01:25:37,183][87426] Updated weights for policy 1, policy_version 46280 (0.0009) -[2023-11-28 01:25:37,490][87424] Updated weights for policy 0, policy_version 46426 (0.0010) -[2023-11-28 01:25:37,566][87426] Updated weights for policy 1, policy_version 46290 (0.0012) -[2023-11-28 01:25:37,946][87426] Updated weights for policy 1, policy_version 46300 (0.0012) -[2023-11-28 01:25:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23740416. Throughput: 0: 2718.2, 1: 2720.4. Samples: 23752888. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 01:25:38,445][86177] Avg episode reward: [(0, '-536.910'), (1, '-515.430')] -[2023-11-28 01:25:39,531][87424] Updated weights for policy 0, policy_version 46436 (0.0009) -[2023-11-28 01:25:39,588][87426] Updated weights for policy 1, policy_version 46310 (0.0010) -[2023-11-28 01:25:39,918][87424] Updated weights for policy 0, policy_version 46446 (0.0011) -[2023-11-28 01:25:39,966][87426] Updated weights for policy 1, policy_version 46320 (0.0009) -[2023-11-28 01:25:40,297][87424] Updated weights for policy 0, policy_version 46456 (0.0012) -[2023-11-28 01:25:40,345][87426] Updated weights for policy 1, policy_version 46330 (0.0010) -[2023-11-28 01:25:42,388][87424] Updated weights for policy 0, policy_version 46466 (0.0011) -[2023-11-28 01:25:42,784][87424] Updated weights for policy 0, policy_version 46476 (0.0008) -[2023-11-28 01:25:42,795][87426] Updated weights for policy 1, policy_version 46340 (0.0011) -[2023-11-28 01:25:43,162][87426] Updated weights for policy 1, policy_version 46350 (0.0011) -[2023-11-28 01:25:43,164][87424] Updated weights for policy 0, policy_version 46486 (0.0008) -[2023-11-28 01:25:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 23756800. Throughput: 0: 2714.3, 1: 2728.5. Samples: 23776968. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 01:25:43,445][86177] Avg episode reward: [(0, '-528.200'), (1, '-518.800')] -[2023-11-28 01:25:43,540][87426] Updated weights for policy 1, policy_version 46360 (0.0011) -[2023-11-28 01:25:43,549][87424] Updated weights for policy 0, policy_version 46496 (0.0010) -[2023-11-28 01:25:45,519][87424] Updated weights for policy 0, policy_version 46506 (0.0011) -[2023-11-28 01:25:45,601][87426] Updated weights for policy 1, policy_version 46370 (0.0011) -[2023-11-28 01:25:45,909][87424] Updated weights for policy 0, policy_version 46516 (0.0009) -[2023-11-28 01:25:45,971][87426] Updated weights for policy 1, policy_version 46380 (0.0009) -[2023-11-28 01:25:46,291][87424] Updated weights for policy 0, policy_version 46526 (0.0010) -[2023-11-28 01:25:46,355][87426] Updated weights for policy 1, policy_version 46390 (0.0011) -[2023-11-28 01:25:46,740][87426] Updated weights for policy 1, policy_version 46400 (0.0010) -[2023-11-28 01:25:47,958][87424] Updated weights for policy 0, policy_version 46536 (0.0011) -[2023-11-28 01:25:48,342][87424] Updated weights for policy 0, policy_version 46546 (0.0012) -[2023-11-28 01:25:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 23789568. Throughput: 0: 2736.5, 1: 2732.5. Samples: 23802044. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 01:25:48,445][86177] Avg episode reward: [(0, '-539.720'), (1, '-523.010')] -[2023-11-28 01:25:48,724][87424] Updated weights for policy 0, policy_version 46556 (0.0009) -[2023-11-28 01:25:48,777][87426] Updated weights for policy 1, policy_version 46410 (0.0010) -[2023-11-28 01:25:49,160][87426] Updated weights for policy 1, policy_version 46420 (0.0011) -[2023-11-28 01:25:49,549][87426] Updated weights for policy 1, policy_version 46430 (0.0011) -[2023-11-28 01:25:50,980][87424] Updated weights for policy 0, policy_version 46566 (0.0011) -[2023-11-28 01:25:51,365][87424] Updated weights for policy 0, policy_version 46576 (0.0008) -[2023-11-28 01:25:51,754][87424] Updated weights for policy 0, policy_version 46586 (0.0010) -[2023-11-28 01:25:51,969][87426] Updated weights for policy 1, policy_version 46440 (0.0008) -[2023-11-28 01:25:52,350][87426] Updated weights for policy 1, policy_version 46450 (0.0008) -[2023-11-28 01:25:52,723][87426] Updated weights for policy 1, policy_version 46460 (0.0007) -[2023-11-28 01:25:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23822336. Throughput: 0: 2730.8, 1: 2739.4. Samples: 23835524. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 01:25:53,445][86177] Avg episode reward: [(0, '-538.900'), (1, '-523.830')] -[2023-11-28 01:25:54,301][87424] Updated weights for policy 0, policy_version 46596 (0.0009) -[2023-11-28 01:25:54,686][87424] Updated weights for policy 0, policy_version 46606 (0.0007) -[2023-11-28 01:25:54,880][87426] Updated weights for policy 1, policy_version 46470 (0.0010) -[2023-11-28 01:25:55,081][87424] Updated weights for policy 0, policy_version 46616 (0.0007) -[2023-11-28 01:25:55,262][87426] Updated weights for policy 1, policy_version 46480 (0.0012) -[2023-11-28 01:25:55,632][87426] Updated weights for policy 1, policy_version 46490 (0.0010) -[2023-11-28 01:25:57,346][87424] Updated weights for policy 0, policy_version 46626 (0.0008) -[2023-11-28 01:25:57,722][87424] Updated weights for policy 0, policy_version 46636 (0.0011) -[2023-11-28 01:25:57,881][87426] Updated weights for policy 1, policy_version 46500 (0.0011) -[2023-11-28 01:25:58,098][87424] Updated weights for policy 0, policy_version 46646 (0.0008) -[2023-11-28 01:25:58,253][87426] Updated weights for policy 1, policy_version 46510 (0.0009) -[2023-11-28 01:25:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 23838720. Throughput: 0: 2726.8, 1: 2778.7. Samples: 23860552. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 01:25:58,445][86177] Avg episode reward: [(0, '-537.570'), (1, '-512.690')] -[2023-11-28 01:25:58,479][87424] Updated weights for policy 0, policy_version 46656 (0.0008) -[2023-11-28 01:25:58,635][87426] Updated weights for policy 1, policy_version 46520 (0.0011) -[2023-11-28 01:26:00,464][87426] Updated weights for policy 1, policy_version 46530 (0.0012) -[2023-11-28 01:26:00,563][87424] Updated weights for policy 0, policy_version 46666 (0.0012) -[2023-11-28 01:26:00,837][87426] Updated weights for policy 1, policy_version 46540 (0.0011) -[2023-11-28 01:26:00,944][87424] Updated weights for policy 0, policy_version 46676 (0.0011) -[2023-11-28 01:26:01,220][87426] Updated weights for policy 1, policy_version 46550 (0.0011) -[2023-11-28 01:26:01,323][87424] Updated weights for policy 0, policy_version 46686 (0.0011) -[2023-11-28 01:26:01,593][87426] Updated weights for policy 1, policy_version 46560 (0.0011) -[2023-11-28 01:26:03,421][87424] Updated weights for policy 0, policy_version 46696 (0.0011) -[2023-11-28 01:26:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 23871488. Throughput: 0: 2733.5, 1: 2795.5. Samples: 23885244. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 01:26:03,445][86177] Avg episode reward: [(0, '-504.530'), (1, '-509.560')] -[2023-11-28 01:26:03,805][87424] Updated weights for policy 0, policy_version 46706 (0.0010) -[2023-11-28 01:26:03,832][87426] Updated weights for policy 1, policy_version 46570 (0.0011) -[2023-11-28 01:26:04,183][87424] Updated weights for policy 0, policy_version 46716 (0.0009) -[2023-11-28 01:26:04,204][87426] Updated weights for policy 1, policy_version 46580 (0.0011) -[2023-11-28 01:26:04,588][87426] Updated weights for policy 1, policy_version 46590 (0.0012) -[2023-11-28 01:26:06,587][87424] Updated weights for policy 0, policy_version 46726 (0.0011) -[2023-11-28 01:26:06,967][87424] Updated weights for policy 0, policy_version 46736 (0.0008) -[2023-11-28 01:26:07,046][87426] Updated weights for policy 1, policy_version 46600 (0.0010) -[2023-11-28 01:26:07,353][87424] Updated weights for policy 0, policy_version 46746 (0.0009) -[2023-11-28 01:26:07,417][87426] Updated weights for policy 1, policy_version 46610 (0.0010) -[2023-11-28 01:26:07,801][87426] Updated weights for policy 1, policy_version 46620 (0.0007) -[2023-11-28 01:26:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 23904256. Throughput: 0: 2738.6, 1: 2785.9. Samples: 23917272. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 01:26:08,445][86177] Avg episode reward: [(0, '-529.960'), (1, '-509.410')] -[2023-11-28 01:26:09,433][87424] Updated weights for policy 0, policy_version 46756 (0.0010) -[2023-11-28 01:26:09,822][87424] Updated weights for policy 0, policy_version 46766 (0.0010) -[2023-11-28 01:26:09,906][87426] Updated weights for policy 1, policy_version 46630 (0.0009) -[2023-11-28 01:26:10,196][87424] Updated weights for policy 0, policy_version 46776 (0.0013) -[2023-11-28 01:26:10,281][87426] Updated weights for policy 1, policy_version 46640 (0.0011) -[2023-11-28 01:26:10,655][87426] Updated weights for policy 1, policy_version 46650 (0.0011) -[2023-11-28 01:26:12,384][87424] Updated weights for policy 0, policy_version 46786 (0.0011) -[2023-11-28 01:26:12,773][87424] Updated weights for policy 0, policy_version 46796 (0.0011) -[2023-11-28 01:26:12,964][87426] Updated weights for policy 1, policy_version 46660 (0.0011) -[2023-11-28 01:26:13,149][87424] Updated weights for policy 0, policy_version 46806 (0.0010) -[2023-11-28 01:26:13,338][87426] Updated weights for policy 1, policy_version 46670 (0.0012) -[2023-11-28 01:26:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 23920640. Throughput: 0: 2741.8, 1: 2747.9. Samples: 23941076. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 01:26:13,445][86177] Avg episode reward: [(0, '-533.340'), (1, '-509.120')] -[2023-11-28 01:26:13,528][87424] Updated weights for policy 0, policy_version 46816 (0.0008) -[2023-11-28 01:26:13,724][87426] Updated weights for policy 1, policy_version 46680 (0.0011) -[2023-11-28 01:26:15,666][87426] Updated weights for policy 1, policy_version 46690 (0.0012) -[2023-11-28 01:26:15,847][87424] Updated weights for policy 0, policy_version 46826 (0.0011) -[2023-11-28 01:26:16,045][87426] Updated weights for policy 1, policy_version 46700 (0.0011) -[2023-11-28 01:26:16,226][87424] Updated weights for policy 0, policy_version 46836 (0.0012) -[2023-11-28 01:26:16,422][87426] Updated weights for policy 1, policy_version 46710 (0.0012) -[2023-11-28 01:26:16,611][87424] Updated weights for policy 0, policy_version 46846 (0.0012) -[2023-11-28 01:26:16,801][87426] Updated weights for policy 1, policy_version 46720 (0.0011) -[2023-11-28 01:26:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 23953408. Throughput: 0: 2737.6, 1: 2746.5. Samples: 23965824. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 01:26:18,445][86177] Avg episode reward: [(0, '-574.890'), (1, '-510.270')] -[2023-11-28 01:26:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000046720_11960320.pth... -[2023-11-28 01:26:18,458][87424] Updated weights for policy 0, policy_version 46856 (0.0012) -[2023-11-28 01:26:18,495][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000044192_11313152.pth -[2023-11-28 01:26:18,838][87424] Updated weights for policy 0, policy_version 46866 (0.0012) -[2023-11-28 01:26:19,190][87426] Updated weights for policy 1, policy_version 46730 (0.0011) -[2023-11-28 01:26:19,232][87424] Updated weights for policy 0, policy_version 46876 (0.0012) -[2023-11-28 01:26:19,377][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000046880_12001280.pth... -[2023-11-28 01:26:19,424][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000044320_11345920.pth -[2023-11-28 01:26:19,568][87426] Updated weights for policy 1, policy_version 46740 (0.0011) -[2023-11-28 01:26:19,944][87426] Updated weights for policy 1, policy_version 46750 (0.0012) -[2023-11-28 01:26:21,659][87424] Updated weights for policy 0, policy_version 46886 (0.0012) -[2023-11-28 01:26:22,057][87424] Updated weights for policy 0, policy_version 46896 (0.0012) -[2023-11-28 01:26:22,372][87426] Updated weights for policy 1, policy_version 46760 (0.0011) -[2023-11-28 01:26:22,436][87424] Updated weights for policy 0, policy_version 46906 (0.0009) -[2023-11-28 01:26:22,745][87426] Updated weights for policy 1, policy_version 46770 (0.0010) -[2023-11-28 01:26:23,121][87426] Updated weights for policy 1, policy_version 46780 (0.0010) -[2023-11-28 01:26:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 23986176. Throughput: 0: 2733.1, 1: 2728.9. Samples: 23998676. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-11-28 01:26:23,445][86177] Avg episode reward: [(0, '-571.350'), (1, '-509.370')] -[2023-11-28 01:26:24,789][87424] Updated weights for policy 0, policy_version 46916 (0.0009) -[2023-11-28 01:26:25,124][87426] Updated weights for policy 1, policy_version 46790 (0.0010) -[2023-11-28 01:26:25,166][87424] Updated weights for policy 0, policy_version 46926 (0.0010) -[2023-11-28 01:26:25,501][87426] Updated weights for policy 1, policy_version 46800 (0.0011) -[2023-11-28 01:26:25,544][87424] Updated weights for policy 0, policy_version 46936 (0.0011) -[2023-11-28 01:26:25,883][87426] Updated weights for policy 1, policy_version 46810 (0.0012) -[2023-11-28 01:26:27,403][87424] Updated weights for policy 0, policy_version 46946 (0.0011) -[2023-11-28 01:26:27,794][87424] Updated weights for policy 0, policy_version 46956 (0.0008) -[2023-11-28 01:26:28,166][87424] Updated weights for policy 0, policy_version 46966 (0.0008) -[2023-11-28 01:26:28,436][87426] Updated weights for policy 1, policy_version 46820 (0.0011) -[2023-11-28 01:26:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 24002560. Throughput: 0: 2737.6, 1: 2714.8. Samples: 24022328. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-11-28 01:26:28,445][86177] Avg episode reward: [(0, '-544.740'), (1, '-509.890')] -[2023-11-28 01:26:28,557][87424] Updated weights for policy 0, policy_version 46976 (0.0009) -[2023-11-28 01:26:28,815][87426] Updated weights for policy 1, policy_version 46830 (0.0008) -[2023-11-28 01:26:29,193][87426] Updated weights for policy 1, policy_version 46840 (0.0011) -[2023-11-28 01:26:30,705][87424] Updated weights for policy 0, policy_version 46986 (0.0009) -[2023-11-28 01:26:30,996][87426] Updated weights for policy 1, policy_version 46850 (0.0010) -[2023-11-28 01:26:31,092][87424] Updated weights for policy 0, policy_version 46996 (0.0008) -[2023-11-28 01:26:31,358][87426] Updated weights for policy 1, policy_version 46860 (0.0007) -[2023-11-28 01:26:31,483][87424] Updated weights for policy 0, policy_version 47006 (0.0007) -[2023-11-28 01:26:31,733][87426] Updated weights for policy 1, policy_version 46870 (0.0009) -[2023-11-28 01:26:32,110][87426] Updated weights for policy 1, policy_version 46880 (0.0008) -[2023-11-28 01:26:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 24035328. Throughput: 0: 2734.1, 1: 2712.3. Samples: 24047132. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-11-28 01:26:33,446][86177] Avg episode reward: [(0, '-540.640'), (1, '-508.400')] -[2023-11-28 01:26:33,723][87424] Updated weights for policy 0, policy_version 47016 (0.0008) -[2023-11-28 01:26:34,102][87424] Updated weights for policy 0, policy_version 47026 (0.0010) -[2023-11-28 01:26:34,493][87424] Updated weights for policy 0, policy_version 47036 (0.0008) -[2023-11-28 01:26:34,514][87426] Updated weights for policy 1, policy_version 46890 (0.0010) -[2023-11-28 01:26:34,893][87426] Updated weights for policy 1, policy_version 46900 (0.0012) -[2023-11-28 01:26:35,269][87426] Updated weights for policy 1, policy_version 46910 (0.0012) -[2023-11-28 01:26:36,666][87424] Updated weights for policy 0, policy_version 47046 (0.0010) -[2023-11-28 01:26:37,053][87424] Updated weights for policy 0, policy_version 47056 (0.0012) -[2023-11-28 01:26:37,316][87426] Updated weights for policy 1, policy_version 46920 (0.0012) -[2023-11-28 01:26:37,425][87424] Updated weights for policy 0, policy_version 47066 (0.0009) -[2023-11-28 01:26:37,696][87426] Updated weights for policy 1, policy_version 46930 (0.0012) -[2023-11-28 01:26:38,081][87426] Updated weights for policy 1, policy_version 46940 (0.0012) -[2023-11-28 01:26:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24068096. Throughput: 0: 2698.7, 1: 2703.1. Samples: 24078608. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-11-28 01:26:38,445][86177] Avg episode reward: [(0, '-497.420'), (1, '-505.890')] -[2023-11-28 01:26:38,447][87281] Saving new best policy, reward=-497.420! -[2023-11-28 01:26:39,364][87424] Updated weights for policy 0, policy_version 47076 (0.0010) -[2023-11-28 01:26:39,743][87424] Updated weights for policy 0, policy_version 47086 (0.0012) -[2023-11-28 01:26:40,126][87424] Updated weights for policy 0, policy_version 47096 (0.0011) -[2023-11-28 01:26:40,136][87426] Updated weights for policy 1, policy_version 46950 (0.0012) -[2023-11-28 01:26:40,523][87426] Updated weights for policy 1, policy_version 46960 (0.0012) -[2023-11-28 01:26:40,900][87426] Updated weights for policy 1, policy_version 46970 (0.0011) -[2023-11-28 01:26:42,141][87424] Updated weights for policy 0, policy_version 47106 (0.0010) -[2023-11-28 01:26:42,522][87424] Updated weights for policy 0, policy_version 47116 (0.0011) -[2023-11-28 01:26:42,903][87424] Updated weights for policy 0, policy_version 47126 (0.0011) -[2023-11-28 01:26:43,287][87424] Updated weights for policy 0, policy_version 47136 (0.0011) -[2023-11-28 01:26:43,432][87426] Updated weights for policy 1, policy_version 46980 (0.0010) -[2023-11-28 01:26:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 24092672. Throughput: 0: 2720.4, 1: 2702.2. Samples: 24104572. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-11-28 01:26:43,445][86177] Avg episode reward: [(0, '-509.550'), (1, '-505.880')] -[2023-11-28 01:26:43,813][87426] Updated weights for policy 1, policy_version 46990 (0.0012) -[2023-11-28 01:26:44,185][87426] Updated weights for policy 1, policy_version 47000 (0.0012) -[2023-11-28 01:26:45,374][87424] Updated weights for policy 0, policy_version 47146 (0.0009) -[2023-11-28 01:26:45,761][87424] Updated weights for policy 0, policy_version 47156 (0.0009) -[2023-11-28 01:26:46,015][87426] Updated weights for policy 1, policy_version 47010 (0.0011) -[2023-11-28 01:26:46,148][87424] Updated weights for policy 0, policy_version 47166 (0.0012) -[2023-11-28 01:26:46,388][87426] Updated weights for policy 1, policy_version 47020 (0.0011) -[2023-11-28 01:26:46,769][87426] Updated weights for policy 1, policy_version 47030 (0.0012) -[2023-11-28 01:26:47,145][87426] Updated weights for policy 1, policy_version 47040 (0.0012) -[2023-11-28 01:26:48,184][87424] Updated weights for policy 0, policy_version 47176 (0.0011) -[2023-11-28 01:26:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24117248. Throughput: 0: 2751.6, 1: 2705.5. Samples: 24130816. Policy #0 lag: (min: 31.0, avg: 41.1, max: 63.0) -[2023-11-28 01:26:48,446][86177] Avg episode reward: [(0, '-515.830'), (1, '-506.250')] -[2023-11-28 01:26:48,559][87424] Updated weights for policy 0, policy_version 47186 (0.0011) -[2023-11-28 01:26:48,941][87424] Updated weights for policy 0, policy_version 47196 (0.0010) -[2023-11-28 01:26:48,980][87426] Updated weights for policy 1, policy_version 47050 (0.0010) -[2023-11-28 01:26:49,361][87426] Updated weights for policy 1, policy_version 47060 (0.0011) -[2023-11-28 01:26:49,729][87426] Updated weights for policy 1, policy_version 47070 (0.0012) -[2023-11-28 01:26:51,337][87424] Updated weights for policy 0, policy_version 47206 (0.0011) -[2023-11-28 01:26:51,721][87424] Updated weights for policy 0, policy_version 47216 (0.0010) -[2023-11-28 01:26:51,970][87426] Updated weights for policy 1, policy_version 47080 (0.0011) -[2023-11-28 01:26:52,108][87424] Updated weights for policy 0, policy_version 47226 (0.0009) -[2023-11-28 01:26:52,359][87426] Updated weights for policy 1, policy_version 47090 (0.0012) -[2023-11-28 01:26:52,743][87426] Updated weights for policy 1, policy_version 47100 (0.0011) -[2023-11-28 01:26:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24150016. Throughput: 0: 2757.4, 1: 2729.5. Samples: 24164184. Policy #0 lag: (min: 10.0, avg: 38.9, max: 64.0) -[2023-11-28 01:26:53,445][86177] Avg episode reward: [(0, '-529.390'), (1, '-505.360')] -[2023-11-28 01:26:53,909][87424] Updated weights for policy 0, policy_version 47236 (0.0011) -[2023-11-28 01:26:54,296][87424] Updated weights for policy 0, policy_version 47246 (0.0012) -[2023-11-28 01:26:54,683][87424] Updated weights for policy 0, policy_version 47256 (0.0012) -[2023-11-28 01:26:55,293][87426] Updated weights for policy 1, policy_version 47110 (0.0011) -[2023-11-28 01:26:55,679][87426] Updated weights for policy 1, policy_version 47120 (0.0010) -[2023-11-28 01:26:56,046][87426] Updated weights for policy 1, policy_version 47130 (0.0009) -[2023-11-28 01:26:56,614][87424] Updated weights for policy 0, policy_version 47266 (0.0012) -[2023-11-28 01:26:57,000][87424] Updated weights for policy 0, policy_version 47276 (0.0012) -[2023-11-28 01:26:57,376][87424] Updated weights for policy 0, policy_version 47286 (0.0011) -[2023-11-28 01:26:57,764][87424] Updated weights for policy 0, policy_version 47296 (0.0011) -[2023-11-28 01:26:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 24174592. Throughput: 0: 2754.3, 1: 2758.7. Samples: 24189160. Policy #0 lag: (min: 10.0, avg: 38.9, max: 64.0) -[2023-11-28 01:26:58,445][86177] Avg episode reward: [(0, '-527.860'), (1, '-505.020')] -[2023-11-28 01:26:58,480][87426] Updated weights for policy 1, policy_version 47140 (0.0007) -[2023-11-28 01:26:58,860][87426] Updated weights for policy 1, policy_version 47150 (0.0008) -[2023-11-28 01:26:59,236][87426] Updated weights for policy 1, policy_version 47160 (0.0007) -[2023-11-28 01:27:00,197][87424] Updated weights for policy 0, policy_version 47306 (0.0008) -[2023-11-28 01:27:00,578][87424] Updated weights for policy 0, policy_version 47316 (0.0008) -[2023-11-28 01:27:00,966][87424] Updated weights for policy 0, policy_version 47326 (0.0009) -[2023-11-28 01:27:01,278][87426] Updated weights for policy 1, policy_version 47170 (0.0008) -[2023-11-28 01:27:01,656][87426] Updated weights for policy 1, policy_version 47180 (0.0011) -[2023-11-28 01:27:02,032][87426] Updated weights for policy 1, policy_version 47190 (0.0011) -[2023-11-28 01:27:02,412][87426] Updated weights for policy 1, policy_version 47200 (0.0011) -[2023-11-28 01:27:03,368][87424] Updated weights for policy 0, policy_version 47336 (0.0008) -[2023-11-28 01:27:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24199168. Throughput: 0: 2748.1, 1: 2749.6. Samples: 24213220. Policy #0 lag: (min: 10.0, avg: 38.9, max: 64.0) -[2023-11-28 01:27:03,445][86177] Avg episode reward: [(0, '-522.230'), (1, '-505.560')] -[2023-11-28 01:27:03,746][87424] Updated weights for policy 0, policy_version 47346 (0.0007) -[2023-11-28 01:27:04,129][87424] Updated weights for policy 0, policy_version 47356 (0.0008) -[2023-11-28 01:27:04,416][87426] Updated weights for policy 1, policy_version 47210 (0.0012) -[2023-11-28 01:27:04,803][87426] Updated weights for policy 1, policy_version 47220 (0.0012) -[2023-11-28 01:27:05,184][87426] Updated weights for policy 1, policy_version 47230 (0.0009) -[2023-11-28 01:27:06,591][87424] Updated weights for policy 0, policy_version 47366 (0.0010) -[2023-11-28 01:27:06,788][87426] Updated weights for policy 1, policy_version 47240 (0.0011) -[2023-11-28 01:27:06,971][87424] Updated weights for policy 0, policy_version 47376 (0.0011) -[2023-11-28 01:27:07,164][87426] Updated weights for policy 1, policy_version 47250 (0.0012) -[2023-11-28 01:27:07,354][87424] Updated weights for policy 0, policy_version 47386 (0.0010) -[2023-11-28 01:27:07,543][87426] Updated weights for policy 1, policy_version 47260 (0.0011) -[2023-11-28 01:27:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24231936. Throughput: 0: 2725.0, 1: 2753.7. Samples: 24245216. Policy #0 lag: (min: 10.0, avg: 38.9, max: 64.0) -[2023-11-28 01:27:08,445][86177] Avg episode reward: [(0, '-519.560'), (1, '-507.890')] -[2023-11-28 01:27:09,159][87424] Updated weights for policy 0, policy_version 47396 (0.0010) -[2023-11-28 01:27:09,541][87424] Updated weights for policy 0, policy_version 47406 (0.0008) -[2023-11-28 01:27:09,930][87424] Updated weights for policy 0, policy_version 47416 (0.0011) -[2023-11-28 01:27:10,046][87426] Updated weights for policy 1, policy_version 47270 (0.0010) -[2023-11-28 01:27:10,437][87426] Updated weights for policy 1, policy_version 47280 (0.0008) -[2023-11-28 01:27:10,802][87426] Updated weights for policy 1, policy_version 47290 (0.0011) -[2023-11-28 01:27:12,538][87424] Updated weights for policy 0, policy_version 47426 (0.0010) -[2023-11-28 01:27:12,919][87424] Updated weights for policy 0, policy_version 47436 (0.0011) -[2023-11-28 01:27:13,275][87426] Updated weights for policy 1, policy_version 47300 (0.0012) -[2023-11-28 01:27:13,300][87424] Updated weights for policy 0, policy_version 47446 (0.0012) -[2023-11-28 01:27:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 24248320. Throughput: 0: 2728.1, 1: 2769.0. Samples: 24269696. Policy #0 lag: (min: 10.0, avg: 38.9, max: 64.0) -[2023-11-28 01:27:13,445][86177] Avg episode reward: [(0, '-511.930'), (1, '-510.340')] -[2023-11-28 01:27:13,649][87426] Updated weights for policy 1, policy_version 47310 (0.0009) -[2023-11-28 01:27:13,686][87424] Updated weights for policy 0, policy_version 47456 (0.0012) -[2023-11-28 01:27:14,030][87426] Updated weights for policy 1, policy_version 47320 (0.0009) -[2023-11-28 01:27:15,843][87426] Updated weights for policy 1, policy_version 47330 (0.0010) -[2023-11-28 01:27:16,222][87426] Updated weights for policy 1, policy_version 47340 (0.0010) -[2023-11-28 01:27:16,312][87424] Updated weights for policy 0, policy_version 47466 (0.0008) -[2023-11-28 01:27:16,612][87426] Updated weights for policy 1, policy_version 47350 (0.0008) -[2023-11-28 01:27:16,695][87424] Updated weights for policy 0, policy_version 47476 (0.0011) -[2023-11-28 01:27:16,988][87426] Updated weights for policy 1, policy_version 47360 (0.0007) -[2023-11-28 01:27:17,072][87424] Updated weights for policy 0, policy_version 47486 (0.0010) -[2023-11-28 01:27:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24281088. Throughput: 0: 2692.8, 1: 2760.4. Samples: 24292524. Policy #0 lag: (min: 10.0, avg: 38.9, max: 64.0) -[2023-11-28 01:27:18,445][86177] Avg episode reward: [(0, '-521.810'), (1, '-506.170')] -[2023-11-28 01:27:18,763][87426] Updated weights for policy 1, policy_version 47370 (0.0007) -[2023-11-28 01:27:19,147][87426] Updated weights for policy 1, policy_version 47380 (0.0009) -[2023-11-28 01:27:19,437][87424] Updated weights for policy 0, policy_version 47496 (0.0009) -[2023-11-28 01:27:19,525][87426] Updated weights for policy 1, policy_version 47390 (0.0012) -[2023-11-28 01:27:19,821][87424] Updated weights for policy 0, policy_version 47506 (0.0009) -[2023-11-28 01:27:20,196][87424] Updated weights for policy 0, policy_version 47516 (0.0011) -[2023-11-28 01:27:21,927][87426] Updated weights for policy 1, policy_version 47400 (0.0017) -[2023-11-28 01:27:22,216][87424] Updated weights for policy 0, policy_version 47526 (0.0011) -[2023-11-28 01:27:22,295][87426] Updated weights for policy 1, policy_version 47410 (0.0011) -[2023-11-28 01:27:22,592][87424] Updated weights for policy 0, policy_version 47536 (0.0008) -[2023-11-28 01:27:22,681][87426] Updated weights for policy 1, policy_version 47420 (0.0011) -[2023-11-28 01:27:22,984][87424] Updated weights for policy 0, policy_version 47546 (0.0010) -[2023-11-28 01:27:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24313856. Throughput: 0: 2700.4, 1: 2767.4. Samples: 24324656. Policy #0 lag: (min: 29.0, avg: 48.9, max: 67.0) -[2023-11-28 01:27:23,445][86177] Avg episode reward: [(0, '-519.850'), (1, '-518.510')] -[2023-11-28 01:27:24,982][87426] Updated weights for policy 1, policy_version 47430 (0.0010) -[2023-11-28 01:27:25,241][87424] Updated weights for policy 0, policy_version 47556 (0.0012) -[2023-11-28 01:27:25,359][87426] Updated weights for policy 1, policy_version 47440 (0.0008) -[2023-11-28 01:27:25,622][87424] Updated weights for policy 0, policy_version 47566 (0.0012) -[2023-11-28 01:27:25,748][87426] Updated weights for policy 1, policy_version 47450 (0.0007) -[2023-11-28 01:27:26,006][87424] Updated weights for policy 0, policy_version 47576 (0.0011) -[2023-11-28 01:27:27,829][87424] Updated weights for policy 0, policy_version 47586 (0.0007) -[2023-11-28 01:27:27,834][87426] Updated weights for policy 1, policy_version 47460 (0.0007) -[2023-11-28 01:27:28,205][87424] Updated weights for policy 0, policy_version 47596 (0.0009) -[2023-11-28 01:27:28,212][87426] Updated weights for policy 1, policy_version 47470 (0.0007) -[2023-11-28 01:27:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 24330240. Throughput: 0: 2701.9, 1: 2736.2. Samples: 24349284. Policy #0 lag: (min: 29.0, avg: 48.9, max: 67.0) -[2023-11-28 01:27:28,445][86177] Avg episode reward: [(0, '-515.290'), (1, '-531.730')] -[2023-11-28 01:27:28,587][87424] Updated weights for policy 0, policy_version 47606 (0.0009) -[2023-11-28 01:27:28,597][87426] Updated weights for policy 1, policy_version 47480 (0.0008) -[2023-11-28 01:27:28,970][87424] Updated weights for policy 0, policy_version 47616 (0.0009) -[2023-11-28 01:27:30,383][87426] Updated weights for policy 1, policy_version 47490 (0.0008) -[2023-11-28 01:27:30,759][87426] Updated weights for policy 1, policy_version 47500 (0.0012) -[2023-11-28 01:27:31,134][87426] Updated weights for policy 1, policy_version 47510 (0.0010) -[2023-11-28 01:27:31,191][87424] Updated weights for policy 0, policy_version 47626 (0.0010) -[2023-11-28 01:27:31,505][87426] Updated weights for policy 1, policy_version 47520 (0.0011) -[2023-11-28 01:27:31,584][87424] Updated weights for policy 0, policy_version 47636 (0.0010) -[2023-11-28 01:27:31,954][87424] Updated weights for policy 0, policy_version 47646 (0.0011) -[2023-11-28 01:27:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 24363008. Throughput: 0: 2668.7, 1: 2717.0. Samples: 24373172. Policy #0 lag: (min: 29.0, avg: 48.9, max: 67.0) -[2023-11-28 01:27:33,445][86177] Avg episode reward: [(0, '-522.730'), (1, '-545.310')] -[2023-11-28 01:27:33,975][87426] Updated weights for policy 1, policy_version 47530 (0.0012) -[2023-11-28 01:27:34,364][87426] Updated weights for policy 1, policy_version 47540 (0.0011) -[2023-11-28 01:27:34,383][87424] Updated weights for policy 0, policy_version 47656 (0.0010) -[2023-11-28 01:27:34,744][87426] Updated weights for policy 1, policy_version 47550 (0.0011) -[2023-11-28 01:27:34,763][87424] Updated weights for policy 0, policy_version 47666 (0.0011) -[2023-11-28 01:27:35,145][87424] Updated weights for policy 0, policy_version 47676 (0.0012) -[2023-11-28 01:27:36,601][87426] Updated weights for policy 1, policy_version 47560 (0.0010) -[2023-11-28 01:27:36,975][87426] Updated weights for policy 1, policy_version 47570 (0.0011) -[2023-11-28 01:27:37,048][87424] Updated weights for policy 0, policy_version 47686 (0.0011) -[2023-11-28 01:27:37,365][87426] Updated weights for policy 1, policy_version 47580 (0.0011) -[2023-11-28 01:27:37,427][87424] Updated weights for policy 0, policy_version 47696 (0.0010) -[2023-11-28 01:27:37,810][87424] Updated weights for policy 0, policy_version 47706 (0.0010) -[2023-11-28 01:27:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 24395776. Throughput: 0: 2669.2, 1: 2740.5. Samples: 24407620. Policy #0 lag: (min: 29.0, avg: 48.9, max: 67.0) -[2023-11-28 01:27:38,445][86177] Avg episode reward: [(0, '-523.520'), (1, '-547.100')] -[2023-11-28 01:27:39,453][87426] Updated weights for policy 1, policy_version 47590 (0.0011) -[2023-11-28 01:27:39,827][87426] Updated weights for policy 1, policy_version 47600 (0.0012) -[2023-11-28 01:27:40,212][87426] Updated weights for policy 1, policy_version 47610 (0.0012) -[2023-11-28 01:27:40,291][87424] Updated weights for policy 0, policy_version 47716 (0.0011) -[2023-11-28 01:27:40,668][87424] Updated weights for policy 0, policy_version 47726 (0.0012) -[2023-11-28 01:27:41,061][87424] Updated weights for policy 0, policy_version 47736 (0.0012) -[2023-11-28 01:27:42,587][87426] Updated weights for policy 1, policy_version 47620 (0.0011) -[2023-11-28 01:27:42,971][87426] Updated weights for policy 1, policy_version 47630 (0.0010) -[2023-11-28 01:27:43,347][87426] Updated weights for policy 1, policy_version 47640 (0.0009) -[2023-11-28 01:27:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 24412160. Throughput: 0: 2655.9, 1: 2717.8. Samples: 24430976. Policy #0 lag: (min: 29.0, avg: 48.9, max: 67.0) -[2023-11-28 01:27:43,445][86177] Avg episode reward: [(0, '-533.740'), (1, '-533.640')] -[2023-11-28 01:27:43,457][87424] Updated weights for policy 0, policy_version 47746 (0.0012) -[2023-11-28 01:27:43,845][87424] Updated weights for policy 0, policy_version 47756 (0.0012) -[2023-11-28 01:27:44,231][87424] Updated weights for policy 0, policy_version 47766 (0.0012) -[2023-11-28 01:27:44,609][87424] Updated weights for policy 0, policy_version 47776 (0.0012) -[2023-11-28 01:27:45,720][87426] Updated weights for policy 1, policy_version 47650 (0.0011) -[2023-11-28 01:27:46,107][87426] Updated weights for policy 1, policy_version 47660 (0.0012) -[2023-11-28 01:27:46,324][87424] Updated weights for policy 0, policy_version 47786 (0.0012) -[2023-11-28 01:27:46,479][87426] Updated weights for policy 1, policy_version 47670 (0.0012) -[2023-11-28 01:27:46,713][87424] Updated weights for policy 0, policy_version 47796 (0.0010) -[2023-11-28 01:27:46,851][87426] Updated weights for policy 1, policy_version 47680 (0.0012) -[2023-11-28 01:27:47,098][87424] Updated weights for policy 0, policy_version 47806 (0.0011) -[2023-11-28 01:27:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24444928. Throughput: 0: 2689.9, 1: 2732.5. Samples: 24457228. Policy #0 lag: (min: 29.0, avg: 48.9, max: 67.0) -[2023-11-28 01:27:48,445][86177] Avg episode reward: [(0, '-526.590'), (1, '-517.360')] -[2023-11-28 01:27:49,203][87426] Updated weights for policy 1, policy_version 47690 (0.0012) -[2023-11-28 01:27:49,577][87424] Updated weights for policy 0, policy_version 47816 (0.0011) -[2023-11-28 01:27:49,583][87426] Updated weights for policy 1, policy_version 47700 (0.0012) -[2023-11-28 01:27:49,957][87424] Updated weights for policy 0, policy_version 47826 (0.0010) -[2023-11-28 01:27:49,961][87426] Updated weights for policy 1, policy_version 47710 (0.0011) -[2023-11-28 01:27:50,338][87424] Updated weights for policy 0, policy_version 47836 (0.0011) -[2023-11-28 01:27:51,774][87426] Updated weights for policy 1, policy_version 47720 (0.0011) -[2023-11-28 01:27:52,154][87426] Updated weights for policy 1, policy_version 47730 (0.0012) -[2023-11-28 01:27:52,530][87426] Updated weights for policy 1, policy_version 47740 (0.0011) -[2023-11-28 01:27:52,606][87424] Updated weights for policy 0, policy_version 47846 (0.0009) -[2023-11-28 01:27:52,995][87424] Updated weights for policy 0, policy_version 47856 (0.0012) -[2023-11-28 01:27:53,379][87424] Updated weights for policy 0, policy_version 47866 (0.0011) -[2023-11-28 01:27:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 24469504. Throughput: 0: 2674.7, 1: 2732.7. Samples: 24488548. Policy #0 lag: (min: 29.0, avg: 48.9, max: 67.0) -[2023-11-28 01:27:53,445][86177] Avg episode reward: [(0, '-519.670'), (1, '-507.430')] -[2023-11-28 01:27:54,714][87426] Updated weights for policy 1, policy_version 47750 (0.0009) -[2023-11-28 01:27:55,083][87426] Updated weights for policy 1, policy_version 47760 (0.0007) -[2023-11-28 01:27:55,470][87426] Updated weights for policy 1, policy_version 47770 (0.0008) -[2023-11-28 01:27:55,549][87424] Updated weights for policy 0, policy_version 47876 (0.0012) -[2023-11-28 01:27:55,921][87424] Updated weights for policy 0, policy_version 47886 (0.0012) -[2023-11-28 01:27:56,306][87424] Updated weights for policy 0, policy_version 47896 (0.0012) -[2023-11-28 01:27:57,730][87426] Updated weights for policy 1, policy_version 47780 (0.0007) -[2023-11-28 01:27:58,116][87426] Updated weights for policy 1, policy_version 47790 (0.0007) -[2023-11-28 01:27:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 24494080. Throughput: 0: 2679.6, 1: 2731.6. Samples: 24513200. Policy #0 lag: (min: 20.0, avg: 39.5, max: 52.0) -[2023-11-28 01:27:58,445][86177] Avg episode reward: [(0, '-523.260'), (1, '-509.810')] -[2023-11-28 01:27:58,488][87426] Updated weights for policy 1, policy_version 47800 (0.0007) -[2023-11-28 01:27:58,495][87424] Updated weights for policy 0, policy_version 47906 (0.0011) -[2023-11-28 01:27:58,876][87424] Updated weights for policy 0, policy_version 47916 (0.0009) -[2023-11-28 01:27:59,242][87424] Updated weights for policy 0, policy_version 47926 (0.0011) -[2023-11-28 01:27:59,625][87424] Updated weights for policy 0, policy_version 47936 (0.0012) -[2023-11-28 01:28:00,499][87426] Updated weights for policy 1, policy_version 47810 (0.0007) -[2023-11-28 01:28:00,879][87426] Updated weights for policy 1, policy_version 47820 (0.0007) -[2023-11-28 01:28:01,256][87426] Updated weights for policy 1, policy_version 47830 (0.0007) -[2023-11-28 01:28:01,640][87426] Updated weights for policy 1, policy_version 47840 (0.0008) -[2023-11-28 01:28:02,165][87424] Updated weights for policy 0, policy_version 47946 (0.0011) -[2023-11-28 01:28:02,547][87424] Updated weights for policy 0, policy_version 47956 (0.0011) -[2023-11-28 01:28:02,948][87424] Updated weights for policy 0, policy_version 47966 (0.0011) -[2023-11-28 01:28:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24526848. Throughput: 0: 2701.2, 1: 2740.3. Samples: 24537388. Policy #0 lag: (min: 20.0, avg: 39.5, max: 52.0) -[2023-11-28 01:28:03,445][86177] Avg episode reward: [(0, '-513.910'), (1, '-512.970')] -[2023-11-28 01:28:04,129][87426] Updated weights for policy 1, policy_version 47850 (0.0012) -[2023-11-28 01:28:04,506][87426] Updated weights for policy 1, policy_version 47860 (0.0012) -[2023-11-28 01:28:04,888][87426] Updated weights for policy 1, policy_version 47870 (0.0012) -[2023-11-28 01:28:05,290][87424] Updated weights for policy 0, policy_version 47976 (0.0011) -[2023-11-28 01:28:05,676][87424] Updated weights for policy 0, policy_version 47986 (0.0011) -[2023-11-28 01:28:06,055][87424] Updated weights for policy 0, policy_version 47996 (0.0012) -[2023-11-28 01:28:06,821][87426] Updated weights for policy 1, policy_version 47880 (0.0009) -[2023-11-28 01:28:07,200][87426] Updated weights for policy 1, policy_version 47890 (0.0010) -[2023-11-28 01:28:07,580][87426] Updated weights for policy 1, policy_version 47900 (0.0011) -[2023-11-28 01:28:08,219][87424] Updated weights for policy 0, policy_version 48006 (0.0010) -[2023-11-28 01:28:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 24551424. Throughput: 0: 2702.8, 1: 2741.1. Samples: 24569628. Policy #0 lag: (min: 20.0, avg: 39.5, max: 52.0) -[2023-11-28 01:28:08,445][86177] Avg episode reward: [(0, '-520.820'), (1, '-520.280')] -[2023-11-28 01:28:08,603][87424] Updated weights for policy 0, policy_version 48016 (0.0007) -[2023-11-28 01:28:08,987][87424] Updated weights for policy 0, policy_version 48026 (0.0007) -[2023-11-28 01:28:09,512][87426] Updated weights for policy 1, policy_version 47910 (0.0011) -[2023-11-28 01:28:09,894][87426] Updated weights for policy 1, policy_version 47920 (0.0011) -[2023-11-28 01:28:10,274][87426] Updated weights for policy 1, policy_version 47930 (0.0011) -[2023-11-28 01:28:11,352][87424] Updated weights for policy 0, policy_version 48036 (0.0008) -[2023-11-28 01:28:11,737][87424] Updated weights for policy 0, policy_version 48046 (0.0010) -[2023-11-28 01:28:12,126][87424] Updated weights for policy 0, policy_version 48056 (0.0009) -[2023-11-28 01:28:12,803][87426] Updated weights for policy 1, policy_version 47940 (0.0010) -[2023-11-28 01:28:13,185][87426] Updated weights for policy 1, policy_version 47950 (0.0011) -[2023-11-28 01:28:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 24576000. Throughput: 0: 2691.4, 1: 2744.1. Samples: 24593880. Policy #0 lag: (min: 20.0, avg: 39.5, max: 52.0) -[2023-11-28 01:28:13,445][86177] Avg episode reward: [(0, '-522.210'), (1, '-518.170')] -[2023-11-28 01:28:13,567][87426] Updated weights for policy 1, policy_version 47960 (0.0011) -[2023-11-28 01:28:14,210][87424] Updated weights for policy 0, policy_version 48066 (0.0012) -[2023-11-28 01:28:14,588][87424] Updated weights for policy 0, policy_version 48076 (0.0012) -[2023-11-28 01:28:14,974][87424] Updated weights for policy 0, policy_version 48086 (0.0012) -[2023-11-28 01:28:15,349][87424] Updated weights for policy 0, policy_version 48096 (0.0012) -[2023-11-28 01:28:15,364][87426] Updated weights for policy 1, policy_version 47970 (0.0011) -[2023-11-28 01:28:15,745][87426] Updated weights for policy 1, policy_version 47980 (0.0011) -[2023-11-28 01:28:16,127][87426] Updated weights for policy 1, policy_version 47990 (0.0009) -[2023-11-28 01:28:16,512][87426] Updated weights for policy 1, policy_version 48000 (0.0011) -[2023-11-28 01:28:17,396][87424] Updated weights for policy 0, policy_version 48106 (0.0008) -[2023-11-28 01:28:17,782][87424] Updated weights for policy 0, policy_version 48116 (0.0008) -[2023-11-28 01:28:18,163][87424] Updated weights for policy 0, policy_version 48126 (0.0012) -[2023-11-28 01:28:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24608768. Throughput: 0: 2699.1, 1: 2753.2. Samples: 24618528. Policy #0 lag: (min: 20.0, avg: 39.5, max: 52.0) -[2023-11-28 01:28:18,446][86177] Avg episode reward: [(0, '-536.470'), (1, '-514.120')] -[2023-11-28 01:28:18,461][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000048128_12320768.pth... -[2023-11-28 01:28:18,462][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000048000_12288000.pth... -[2023-11-28 01:28:18,497][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000045600_11673600.pth -[2023-11-28 01:28:18,510][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000045472_11640832.pth -[2023-11-28 01:28:19,031][87426] Updated weights for policy 1, policy_version 48010 (0.0012) -[2023-11-28 01:28:19,410][87426] Updated weights for policy 1, policy_version 48020 (0.0012) -[2023-11-28 01:28:19,792][87426] Updated weights for policy 1, policy_version 48030 (0.0011) -[2023-11-28 01:28:20,674][87424] Updated weights for policy 0, policy_version 48136 (0.0009) -[2023-11-28 01:28:21,063][87424] Updated weights for policy 0, policy_version 48146 (0.0007) -[2023-11-28 01:28:21,446][87424] Updated weights for policy 0, policy_version 48156 (0.0009) -[2023-11-28 01:28:21,758][87426] Updated weights for policy 1, policy_version 48040 (0.0012) -[2023-11-28 01:28:22,139][87426] Updated weights for policy 1, policy_version 48050 (0.0013) -[2023-11-28 01:28:22,525][87426] Updated weights for policy 1, policy_version 48060 (0.0012) -[2023-11-28 01:28:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 24633344. Throughput: 0: 2674.9, 1: 2715.1. Samples: 24650172. Policy #0 lag: (min: 20.0, avg: 39.5, max: 52.0) -[2023-11-28 01:28:23,445][86177] Avg episode reward: [(0, '-536.450'), (1, '-499.220')] -[2023-11-28 01:28:23,515][87424] Updated weights for policy 0, policy_version 48166 (0.0012) -[2023-11-28 01:28:23,895][87424] Updated weights for policy 0, policy_version 48176 (0.0012) -[2023-11-28 01:28:24,278][87424] Updated weights for policy 0, policy_version 48186 (0.0012) -[2023-11-28 01:28:25,007][87426] Updated weights for policy 1, policy_version 48070 (0.0011) -[2023-11-28 01:28:25,390][87426] Updated weights for policy 1, policy_version 48080 (0.0008) -[2023-11-28 01:28:25,769][87426] Updated weights for policy 1, policy_version 48090 (0.0009) -[2023-11-28 01:28:26,543][87424] Updated weights for policy 0, policy_version 48196 (0.0010) -[2023-11-28 01:28:26,939][87424] Updated weights for policy 0, policy_version 48206 (0.0008) -[2023-11-28 01:28:27,321][87424] Updated weights for policy 0, policy_version 48216 (0.0011) -[2023-11-28 01:28:27,804][87426] Updated weights for policy 1, policy_version 48100 (0.0008) -[2023-11-28 01:28:28,166][87426] Updated weights for policy 1, policy_version 48110 (0.0007) -[2023-11-28 01:28:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24657920. Throughput: 0: 2691.6, 1: 2717.4. Samples: 24674384. Policy #0 lag: (min: 40.0, avg: 55.3, max: 83.0) -[2023-11-28 01:28:28,445][86177] Avg episode reward: [(0, '-542.380'), (1, '-500.240')] -[2023-11-28 01:28:28,545][87426] Updated weights for policy 1, policy_version 48120 (0.0011) -[2023-11-28 01:28:29,285][87424] Updated weights for policy 0, policy_version 48226 (0.0011) -[2023-11-28 01:28:29,679][87424] Updated weights for policy 0, policy_version 48236 (0.0010) -[2023-11-28 01:28:30,060][87424] Updated weights for policy 0, policy_version 48246 (0.0010) -[2023-11-28 01:28:30,446][87424] Updated weights for policy 0, policy_version 48256 (0.0011) -[2023-11-28 01:28:31,016][87426] Updated weights for policy 1, policy_version 48130 (0.0012) -[2023-11-28 01:28:31,392][87426] Updated weights for policy 1, policy_version 48140 (0.0007) -[2023-11-28 01:28:31,775][87426] Updated weights for policy 1, policy_version 48150 (0.0009) -[2023-11-28 01:28:32,153][87426] Updated weights for policy 1, policy_version 48160 (0.0012) -[2023-11-28 01:28:33,001][87424] Updated weights for policy 0, policy_version 48266 (0.0009) -[2023-11-28 01:28:33,385][87424] Updated weights for policy 0, policy_version 48276 (0.0011) -[2023-11-28 01:28:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 24682496. Throughput: 0: 2663.5, 1: 2689.4. Samples: 24698108. Policy #0 lag: (min: 40.0, avg: 55.3, max: 83.0) -[2023-11-28 01:28:33,445][86177] Avg episode reward: [(0, '-541.420'), (1, '-498.240')] -[2023-11-28 01:28:33,777][87424] Updated weights for policy 0, policy_version 48286 (0.0009) -[2023-11-28 01:28:34,374][87426] Updated weights for policy 1, policy_version 48170 (0.0007) -[2023-11-28 01:28:34,758][87426] Updated weights for policy 1, policy_version 48180 (0.0008) -[2023-11-28 01:28:35,138][87426] Updated weights for policy 1, policy_version 48190 (0.0010) -[2023-11-28 01:28:35,835][87424] Updated weights for policy 0, policy_version 48296 (0.0008) -[2023-11-28 01:28:36,214][87424] Updated weights for policy 0, policy_version 48306 (0.0008) -[2023-11-28 01:28:36,604][87424] Updated weights for policy 0, policy_version 48316 (0.0008) -[2023-11-28 01:28:37,269][87426] Updated weights for policy 1, policy_version 48200 (0.0008) -[2023-11-28 01:28:37,658][87426] Updated weights for policy 1, policy_version 48210 (0.0008) -[2023-11-28 01:28:38,032][87426] Updated weights for policy 1, policy_version 48220 (0.0007) -[2023-11-28 01:28:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 24715264. Throughput: 0: 2676.2, 1: 2689.9. Samples: 24730020. Policy #0 lag: (min: 40.0, avg: 55.3, max: 83.0) -[2023-11-28 01:28:38,445][86177] Avg episode reward: [(0, '-522.390'), (1, '-500.680')] -[2023-11-28 01:28:38,896][87424] Updated weights for policy 0, policy_version 48326 (0.0008) -[2023-11-28 01:28:39,280][87424] Updated weights for policy 0, policy_version 48336 (0.0010) -[2023-11-28 01:28:39,658][87424] Updated weights for policy 0, policy_version 48346 (0.0010) -[2023-11-28 01:28:40,458][87426] Updated weights for policy 1, policy_version 48230 (0.0008) -[2023-11-28 01:28:40,847][87426] Updated weights for policy 1, policy_version 48240 (0.0008) -[2023-11-28 01:28:41,220][87426] Updated weights for policy 1, policy_version 48250 (0.0011) -[2023-11-28 01:28:41,588][87424] Updated weights for policy 0, policy_version 48356 (0.0011) -[2023-11-28 01:28:41,964][87424] Updated weights for policy 0, policy_version 48366 (0.0012) -[2023-11-28 01:28:42,351][87424] Updated weights for policy 0, policy_version 48376 (0.0011) -[2023-11-28 01:28:43,388][87426] Updated weights for policy 1, policy_version 48260 (0.0010) -[2023-11-28 01:28:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24739840. Throughput: 0: 2666.3, 1: 2663.5. Samples: 24753040. Policy #0 lag: (min: 40.0, avg: 55.3, max: 83.0) -[2023-11-28 01:28:43,445][86177] Avg episode reward: [(0, '-527.800'), (1, '-502.340')] -[2023-11-28 01:28:43,772][87426] Updated weights for policy 1, policy_version 48270 (0.0012) -[2023-11-28 01:28:44,147][87426] Updated weights for policy 1, policy_version 48280 (0.0011) -[2023-11-28 01:28:44,393][87424] Updated weights for policy 0, policy_version 48386 (0.0008) -[2023-11-28 01:28:44,760][87424] Updated weights for policy 0, policy_version 48396 (0.0011) -[2023-11-28 01:28:45,157][87424] Updated weights for policy 0, policy_version 48406 (0.0007) -[2023-11-28 01:28:45,532][87424] Updated weights for policy 0, policy_version 48416 (0.0008) -[2023-11-28 01:28:46,659][87426] Updated weights for policy 1, policy_version 48290 (0.0011) -[2023-11-28 01:28:47,040][87426] Updated weights for policy 1, policy_version 48300 (0.0008) -[2023-11-28 01:28:47,419][87426] Updated weights for policy 1, policy_version 48310 (0.0007) -[2023-11-28 01:28:47,461][87424] Updated weights for policy 0, policy_version 48426 (0.0012) -[2023-11-28 01:28:47,800][87426] Updated weights for policy 1, policy_version 48320 (0.0009) -[2023-11-28 01:28:47,840][87424] Updated weights for policy 0, policy_version 48436 (0.0011) -[2023-11-28 01:28:48,216][87424] Updated weights for policy 0, policy_version 48446 (0.0012) -[2023-11-28 01:28:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 24772608. Throughput: 0: 2671.7, 1: 2675.6. Samples: 24778020. Policy #0 lag: (min: 40.0, avg: 55.3, max: 83.0) -[2023-11-28 01:28:48,445][86177] Avg episode reward: [(0, '-515.510'), (1, '-500.370')] -[2023-11-28 01:28:49,866][87426] Updated weights for policy 1, policy_version 48330 (0.0008) -[2023-11-28 01:28:50,246][87426] Updated weights for policy 1, policy_version 48340 (0.0008) -[2023-11-28 01:28:50,594][87424] Updated weights for policy 0, policy_version 48456 (0.0012) -[2023-11-28 01:28:50,624][87426] Updated weights for policy 1, policy_version 48350 (0.0009) -[2023-11-28 01:28:50,966][87424] Updated weights for policy 0, policy_version 48466 (0.0011) -[2023-11-28 01:28:51,348][87424] Updated weights for policy 0, policy_version 48476 (0.0008) -[2023-11-28 01:28:52,429][87426] Updated weights for policy 1, policy_version 48360 (0.0010) -[2023-11-28 01:28:52,794][87426] Updated weights for policy 1, policy_version 48370 (0.0008) -[2023-11-28 01:28:53,184][87426] Updated weights for policy 1, policy_version 48380 (0.0010) -[2023-11-28 01:28:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 24797184. Throughput: 0: 2672.4, 1: 2673.2. Samples: 24810184. Policy #0 lag: (min: 40.0, avg: 55.3, max: 83.0) -[2023-11-28 01:28:53,445][86177] Avg episode reward: [(0, '-538.690'), (1, '-501.340')] -[2023-11-28 01:28:53,553][87424] Updated weights for policy 0, policy_version 48486 (0.0009) -[2023-11-28 01:28:53,939][87424] Updated weights for policy 0, policy_version 48496 (0.0010) -[2023-11-28 01:28:54,319][87424] Updated weights for policy 0, policy_version 48506 (0.0010) -[2023-11-28 01:28:55,327][87426] Updated weights for policy 1, policy_version 48390 (0.0012) -[2023-11-28 01:28:55,702][87426] Updated weights for policy 1, policy_version 48400 (0.0008) -[2023-11-28 01:28:56,092][87426] Updated weights for policy 1, policy_version 48410 (0.0007) -[2023-11-28 01:28:56,797][87424] Updated weights for policy 0, policy_version 48516 (0.0009) -[2023-11-28 01:28:57,182][87424] Updated weights for policy 0, policy_version 48526 (0.0012) -[2023-11-28 01:28:57,553][87424] Updated weights for policy 0, policy_version 48536 (0.0012) -[2023-11-28 01:28:58,270][87426] Updated weights for policy 1, policy_version 48420 (0.0008) -[2023-11-28 01:28:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24821760. Throughput: 0: 2658.4, 1: 2678.3. Samples: 24834032. Policy #0 lag: (min: 40.0, avg: 55.3, max: 83.0) -[2023-11-28 01:28:58,445][86177] Avg episode reward: [(0, '-545.780'), (1, '-499.290')] -[2023-11-28 01:28:58,648][87426] Updated weights for policy 1, policy_version 48430 (0.0007) -[2023-11-28 01:28:59,028][87426] Updated weights for policy 1, policy_version 48440 (0.0008) -[2023-11-28 01:28:59,535][87424] Updated weights for policy 0, policy_version 48546 (0.0012) -[2023-11-28 01:28:59,919][87424] Updated weights for policy 0, policy_version 48556 (0.0012) -[2023-11-28 01:29:00,305][87424] Updated weights for policy 0, policy_version 48566 (0.0012) -[2023-11-28 01:29:00,683][87424] Updated weights for policy 0, policy_version 48576 (0.0012) -[2023-11-28 01:29:01,538][87426] Updated weights for policy 1, policy_version 48450 (0.0007) -[2023-11-28 01:29:01,924][87426] Updated weights for policy 1, policy_version 48460 (0.0010) -[2023-11-28 01:29:02,306][87426] Updated weights for policy 1, policy_version 48470 (0.0012) -[2023-11-28 01:29:02,674][87426] Updated weights for policy 1, policy_version 48480 (0.0012) -[2023-11-28 01:29:03,079][87424] Updated weights for policy 0, policy_version 48586 (0.0012) -[2023-11-28 01:29:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 24846336. Throughput: 0: 2667.3, 1: 2665.1. Samples: 24858484. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 01:29:03,445][86177] Avg episode reward: [(0, '-534.030'), (1, '-497.260')] -[2023-11-28 01:29:03,469][87424] Updated weights for policy 0, policy_version 48596 (0.0012) -[2023-11-28 01:29:03,840][87424] Updated weights for policy 0, policy_version 48606 (0.0010) -[2023-11-28 01:29:04,948][87426] Updated weights for policy 1, policy_version 48490 (0.0008) -[2023-11-28 01:29:05,330][87426] Updated weights for policy 1, policy_version 48500 (0.0007) -[2023-11-28 01:29:05,715][87426] Updated weights for policy 1, policy_version 48510 (0.0007) -[2023-11-28 01:29:05,746][87424] Updated weights for policy 0, policy_version 48616 (0.0009) -[2023-11-28 01:29:06,133][87424] Updated weights for policy 0, policy_version 48626 (0.0007) -[2023-11-28 01:29:06,513][87424] Updated weights for policy 0, policy_version 48636 (0.0007) -[2023-11-28 01:29:07,553][87426] Updated weights for policy 1, policy_version 48520 (0.0008) -[2023-11-28 01:29:07,922][87426] Updated weights for policy 1, policy_version 48530 (0.0007) -[2023-11-28 01:29:08,303][87426] Updated weights for policy 1, policy_version 48540 (0.0008) -[2023-11-28 01:29:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 24870912. Throughput: 0: 2691.6, 1: 2682.8. Samples: 24892016. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 01:29:08,445][86177] Avg episode reward: [(0, '-512.780'), (1, '-496.850')] -[2023-11-28 01:29:09,006][87424] Updated weights for policy 0, policy_version 48646 (0.0011) -[2023-11-28 01:29:09,383][87424] Updated weights for policy 0, policy_version 48656 (0.0012) -[2023-11-28 01:29:09,760][87424] Updated weights for policy 0, policy_version 48666 (0.0011) -[2023-11-28 01:29:10,702][87426] Updated weights for policy 1, policy_version 48550 (0.0010) -[2023-11-28 01:29:11,089][87426] Updated weights for policy 1, policy_version 48560 (0.0016) -[2023-11-28 01:29:11,456][87426] Updated weights for policy 1, policy_version 48570 (0.0009) -[2023-11-28 01:29:12,074][87424] Updated weights for policy 0, policy_version 48676 (0.0012) -[2023-11-28 01:29:12,463][87424] Updated weights for policy 0, policy_version 48686 (0.0012) -[2023-11-28 01:29:12,850][87424] Updated weights for policy 0, policy_version 48696 (0.0012) -[2023-11-28 01:29:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24903680. Throughput: 0: 2689.8, 1: 2686.0. Samples: 24916296. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 01:29:13,446][86177] Avg episode reward: [(0, '-513.000'), (1, '-498.170')] -[2023-11-28 01:29:13,725][87426] Updated weights for policy 1, policy_version 48580 (0.0010) -[2023-11-28 01:29:14,106][87426] Updated weights for policy 1, policy_version 48590 (0.0011) -[2023-11-28 01:29:14,487][87426] Updated weights for policy 1, policy_version 48600 (0.0012) -[2023-11-28 01:29:14,690][87424] Updated weights for policy 0, policy_version 48706 (0.0012) -[2023-11-28 01:29:15,072][87424] Updated weights for policy 0, policy_version 48716 (0.0012) -[2023-11-28 01:29:15,455][87424] Updated weights for policy 0, policy_version 48726 (0.0011) -[2023-11-28 01:29:15,833][87424] Updated weights for policy 0, policy_version 48736 (0.0012) -[2023-11-28 01:29:16,850][87426] Updated weights for policy 1, policy_version 48610 (0.0012) -[2023-11-28 01:29:17,221][87426] Updated weights for policy 1, policy_version 48620 (0.0010) -[2023-11-28 01:29:17,598][87426] Updated weights for policy 1, policy_version 48630 (0.0007) -[2023-11-28 01:29:17,985][87426] Updated weights for policy 1, policy_version 48640 (0.0008) -[2023-11-28 01:29:18,307][87424] Updated weights for policy 0, policy_version 48746 (0.0009) -[2023-11-28 01:29:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 24928256. Throughput: 0: 2707.1, 1: 2703.5. Samples: 24941584. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 01:29:18,445][86177] Avg episode reward: [(0, '-503.040'), (1, '-496.490')] -[2023-11-28 01:29:18,686][87424] Updated weights for policy 0, policy_version 48756 (0.0008) -[2023-11-28 01:29:19,069][87424] Updated weights for policy 0, policy_version 48766 (0.0008) -[2023-11-28 01:29:20,446][87426] Updated weights for policy 1, policy_version 48650 (0.0012) -[2023-11-28 01:29:20,818][87424] Updated weights for policy 0, policy_version 48776 (0.0009) -[2023-11-28 01:29:20,824][87426] Updated weights for policy 1, policy_version 48660 (0.0012) -[2023-11-28 01:29:21,204][87424] Updated weights for policy 0, policy_version 48786 (0.0009) -[2023-11-28 01:29:21,213][87426] Updated weights for policy 1, policy_version 48670 (0.0012) -[2023-11-28 01:29:21,598][87424] Updated weights for policy 0, policy_version 48796 (0.0009) -[2023-11-28 01:29:23,249][87426] Updated weights for policy 1, policy_version 48680 (0.0012) -[2023-11-28 01:29:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 24952832. Throughput: 0: 2733.1, 1: 2690.4. Samples: 24974080. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 01:29:23,445][86177] Avg episode reward: [(0, '-501.080'), (1, '-496.990')] -[2023-11-28 01:29:23,485][87424] Updated weights for policy 0, policy_version 48806 (0.0011) -[2023-11-28 01:29:23,623][87426] Updated weights for policy 1, policy_version 48690 (0.0011) -[2023-11-28 01:29:23,868][87424] Updated weights for policy 0, policy_version 48816 (0.0012) -[2023-11-28 01:29:24,004][87426] Updated weights for policy 1, policy_version 48700 (0.0011) -[2023-11-28 01:29:24,250][87424] Updated weights for policy 0, policy_version 48826 (0.0012) -[2023-11-28 01:29:26,332][87426] Updated weights for policy 1, policy_version 48710 (0.0012) -[2023-11-28 01:29:26,715][87426] Updated weights for policy 1, policy_version 48720 (0.0011) -[2023-11-28 01:29:26,797][87424] Updated weights for policy 0, policy_version 48836 (0.0010) -[2023-11-28 01:29:27,088][87426] Updated weights for policy 1, policy_version 48730 (0.0011) -[2023-11-28 01:29:27,175][87424] Updated weights for policy 0, policy_version 48846 (0.0011) -[2023-11-28 01:29:27,557][87424] Updated weights for policy 0, policy_version 48856 (0.0007) -[2023-11-28 01:29:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 24985600. Throughput: 0: 2738.8, 1: 2720.3. Samples: 24998700. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 01:29:28,445][86177] Avg episode reward: [(0, '-500.920'), (1, '-497.380')] -[2023-11-28 01:29:29,212][87426] Updated weights for policy 1, policy_version 48740 (0.0011) -[2023-11-28 01:29:29,588][87426] Updated weights for policy 1, policy_version 48750 (0.0010) -[2023-11-28 01:29:29,965][87426] Updated weights for policy 1, policy_version 48760 (0.0009) -[2023-11-28 01:29:30,123][87424] Updated weights for policy 0, policy_version 48866 (0.0008) -[2023-11-28 01:29:30,506][87424] Updated weights for policy 0, policy_version 48876 (0.0010) -[2023-11-28 01:29:30,886][87424] Updated weights for policy 0, policy_version 48886 (0.0010) -[2023-11-28 01:29:31,261][87424] Updated weights for policy 0, policy_version 48896 (0.0010) -[2023-11-28 01:29:31,717][87426] Updated weights for policy 1, policy_version 48770 (0.0012) -[2023-11-28 01:29:32,095][87426] Updated weights for policy 1, policy_version 48780 (0.0009) -[2023-11-28 01:29:32,472][87426] Updated weights for policy 1, policy_version 48790 (0.0011) -[2023-11-28 01:29:32,852][87426] Updated weights for policy 1, policy_version 48800 (0.0010) -[2023-11-28 01:29:33,291][87424] Updated weights for policy 0, policy_version 48906 (0.0012) -[2023-11-28 01:29:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 25010176. Throughput: 0: 2721.3, 1: 2714.0. Samples: 25022612. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 01:29:33,445][86177] Avg episode reward: [(0, '-500.720'), (1, '-495.740')] -[2023-11-28 01:29:33,683][87424] Updated weights for policy 0, policy_version 48916 (0.0012) -[2023-11-28 01:29:34,080][87424] Updated weights for policy 0, policy_version 48926 (0.0012) -[2023-11-28 01:29:35,398][87426] Updated weights for policy 1, policy_version 48810 (0.0012) -[2023-11-28 01:29:35,780][87426] Updated weights for policy 1, policy_version 48820 (0.0011) -[2023-11-28 01:29:35,953][87424] Updated weights for policy 0, policy_version 48936 (0.0009) -[2023-11-28 01:29:36,154][87426] Updated weights for policy 1, policy_version 48830 (0.0008) -[2023-11-28 01:29:36,337][87424] Updated weights for policy 0, policy_version 48946 (0.0007) -[2023-11-28 01:29:36,724][87424] Updated weights for policy 0, policy_version 48956 (0.0007) -[2023-11-28 01:29:38,166][87426] Updated weights for policy 1, policy_version 48840 (0.0011) -[2023-11-28 01:29:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 25034752. Throughput: 0: 2730.5, 1: 2696.0. Samples: 25054376. Policy #0 lag: (min: 14.0, avg: 29.7, max: 46.0) -[2023-11-28 01:29:38,445][86177] Avg episode reward: [(0, '-501.350'), (1, '-524.090')] -[2023-11-28 01:29:38,536][87426] Updated weights for policy 1, policy_version 48850 (0.0012) -[2023-11-28 01:29:38,912][87426] Updated weights for policy 1, policy_version 48860 (0.0010) -[2023-11-28 01:29:38,960][87424] Updated weights for policy 0, policy_version 48966 (0.0010) -[2023-11-28 01:29:39,356][87424] Updated weights for policy 0, policy_version 48976 (0.0012) -[2023-11-28 01:29:39,741][87424] Updated weights for policy 0, policy_version 48986 (0.0012) -[2023-11-28 01:29:41,211][87426] Updated weights for policy 1, policy_version 48870 (0.0007) -[2023-11-28 01:29:41,591][87426] Updated weights for policy 1, policy_version 48880 (0.0008) -[2023-11-28 01:29:41,978][87426] Updated weights for policy 1, policy_version 48890 (0.0010) -[2023-11-28 01:29:42,316][87424] Updated weights for policy 0, policy_version 48996 (0.0011) -[2023-11-28 01:29:42,698][87424] Updated weights for policy 0, policy_version 49006 (0.0008) -[2023-11-28 01:29:43,081][87424] Updated weights for policy 0, policy_version 49016 (0.0009) -[2023-11-28 01:29:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 25067520. Throughput: 0: 2728.8, 1: 2696.0. Samples: 25078148. Policy #0 lag: (min: 14.0, avg: 29.7, max: 46.0) -[2023-11-28 01:29:43,445][86177] Avg episode reward: [(0, '-502.440'), (1, '-525.360')] -[2023-11-28 01:29:44,155][87426] Updated weights for policy 1, policy_version 48900 (0.0011) -[2023-11-28 01:29:44,535][87426] Updated weights for policy 1, policy_version 48910 (0.0008) -[2023-11-28 01:29:44,916][87426] Updated weights for policy 1, policy_version 48920 (0.0011) -[2023-11-28 01:29:45,160][87424] Updated weights for policy 0, policy_version 49026 (0.0010) -[2023-11-28 01:29:45,557][87424] Updated weights for policy 0, policy_version 49036 (0.0009) -[2023-11-28 01:29:45,953][87424] Updated weights for policy 0, policy_version 49046 (0.0008) -[2023-11-28 01:29:46,328][87424] Updated weights for policy 0, policy_version 49056 (0.0007) -[2023-11-28 01:29:47,080][87426] Updated weights for policy 1, policy_version 48930 (0.0011) -[2023-11-28 01:29:47,462][87426] Updated weights for policy 1, policy_version 48940 (0.0007) -[2023-11-28 01:29:47,846][87426] Updated weights for policy 1, policy_version 48950 (0.0007) -[2023-11-28 01:29:48,065][87424] Updated weights for policy 0, policy_version 49066 (0.0008) -[2023-11-28 01:29:48,234][87426] Updated weights for policy 1, policy_version 48960 (0.0009) -[2023-11-28 01:29:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 25092096. Throughput: 0: 2710.5, 1: 2706.3. Samples: 25102240. Policy #0 lag: (min: 14.0, avg: 29.7, max: 46.0) -[2023-11-28 01:29:48,445][86177] Avg episode reward: [(0, '-499.850'), (1, '-528.870')] -[2023-11-28 01:29:48,446][87424] Updated weights for policy 0, policy_version 49076 (0.0007) -[2023-11-28 01:29:48,831][87424] Updated weights for policy 0, policy_version 49086 (0.0008) -[2023-11-28 01:29:50,704][87426] Updated weights for policy 1, policy_version 48970 (0.0011) -[2023-11-28 01:29:50,951][87424] Updated weights for policy 0, policy_version 49096 (0.0010) -[2023-11-28 01:29:51,089][87426] Updated weights for policy 1, policy_version 48980 (0.0009) -[2023-11-28 01:29:51,329][87424] Updated weights for policy 0, policy_version 49106 (0.0012) -[2023-11-28 01:29:51,460][87426] Updated weights for policy 1, policy_version 48990 (0.0011) -[2023-11-28 01:29:51,710][87424] Updated weights for policy 0, policy_version 49116 (0.0012) -[2023-11-28 01:29:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 25116672. Throughput: 0: 2725.3, 1: 2679.6. Samples: 25135240. Policy #0 lag: (min: 14.0, avg: 29.7, max: 46.0) -[2023-11-28 01:29:53,445][86177] Avg episode reward: [(0, '-505.840'), (1, '-526.900')] -[2023-11-28 01:29:53,625][87426] Updated weights for policy 1, policy_version 49000 (0.0013) -[2023-11-28 01:29:53,829][87424] Updated weights for policy 0, policy_version 49126 (0.0010) -[2023-11-28 01:29:54,015][87426] Updated weights for policy 1, policy_version 49010 (0.0011) -[2023-11-28 01:29:54,212][87424] Updated weights for policy 0, policy_version 49136 (0.0008) -[2023-11-28 01:29:54,382][87426] Updated weights for policy 1, policy_version 49020 (0.0011) -[2023-11-28 01:29:54,602][87424] Updated weights for policy 0, policy_version 49146 (0.0007) -[2023-11-28 01:29:56,594][87424] Updated weights for policy 0, policy_version 49156 (0.0007) -[2023-11-28 01:29:56,608][87426] Updated weights for policy 1, policy_version 49030 (0.0011) -[2023-11-28 01:29:56,978][87424] Updated weights for policy 0, policy_version 49166 (0.0007) -[2023-11-28 01:29:56,992][87426] Updated weights for policy 1, policy_version 49040 (0.0011) -[2023-11-28 01:29:57,361][87426] Updated weights for policy 1, policy_version 49050 (0.0012) -[2023-11-28 01:29:57,363][87424] Updated weights for policy 0, policy_version 49176 (0.0007) -[2023-11-28 01:29:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 25149440. Throughput: 0: 2738.7, 1: 2677.8. Samples: 25160036. Policy #0 lag: (min: 14.0, avg: 29.7, max: 46.0) -[2023-11-28 01:29:58,445][86177] Avg episode reward: [(0, '-503.650'), (1, '-503.300')] -[2023-11-28 01:29:59,755][87426] Updated weights for policy 1, policy_version 49060 (0.0012) -[2023-11-28 01:29:59,882][87424] Updated weights for policy 0, policy_version 49186 (0.0008) -[2023-11-28 01:30:00,130][87426] Updated weights for policy 1, policy_version 49070 (0.0012) -[2023-11-28 01:30:00,270][87424] Updated weights for policy 0, policy_version 49196 (0.0012) -[2023-11-28 01:30:00,499][87426] Updated weights for policy 1, policy_version 49080 (0.0012) -[2023-11-28 01:30:00,642][87424] Updated weights for policy 0, policy_version 49206 (0.0010) -[2023-11-28 01:30:01,025][87424] Updated weights for policy 0, policy_version 49216 (0.0007) -[2023-11-28 01:30:02,367][87426] Updated weights for policy 1, policy_version 49090 (0.0011) -[2023-11-28 01:30:02,748][87426] Updated weights for policy 1, policy_version 49100 (0.0010) -[2023-11-28 01:30:03,131][87426] Updated weights for policy 1, policy_version 49110 (0.0011) -[2023-11-28 01:30:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 25165824. Throughput: 0: 2693.0, 1: 2672.4. Samples: 25183024. Policy #0 lag: (min: 14.0, avg: 29.7, max: 46.0) -[2023-11-28 01:30:03,445][86177] Avg episode reward: [(0, '-507.840'), (1, '-502.670')] -[2023-11-28 01:30:03,504][87426] Updated weights for policy 1, policy_version 49120 (0.0010) -[2023-11-28 01:30:03,582][87424] Updated weights for policy 0, policy_version 49226 (0.0012) -[2023-11-28 01:30:03,972][87424] Updated weights for policy 0, policy_version 49236 (0.0011) -[2023-11-28 01:30:04,355][87424] Updated weights for policy 0, policy_version 49246 (0.0012) -[2023-11-28 01:30:05,388][87426] Updated weights for policy 1, policy_version 49130 (0.0007) -[2023-11-28 01:30:05,774][87426] Updated weights for policy 1, policy_version 49140 (0.0007) -[2023-11-28 01:30:06,165][87426] Updated weights for policy 1, policy_version 49150 (0.0007) -[2023-11-28 01:30:06,690][87424] Updated weights for policy 0, policy_version 49256 (0.0010) -[2023-11-28 01:30:07,071][87424] Updated weights for policy 0, policy_version 49266 (0.0012) -[2023-11-28 01:30:07,457][87424] Updated weights for policy 0, policy_version 49276 (0.0012) -[2023-11-28 01:30:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 25198592. Throughput: 0: 2671.7, 1: 2690.2. Samples: 25215364. Policy #0 lag: (min: 21.0, avg: 41.2, max: 53.0) -[2023-11-28 01:30:08,445][86177] Avg episode reward: [(0, '-506.370'), (1, '-499.020')] -[2023-11-28 01:30:08,568][87426] Updated weights for policy 1, policy_version 49160 (0.0008) -[2023-11-28 01:30:08,951][87426] Updated weights for policy 1, policy_version 49170 (0.0009) -[2023-11-28 01:30:09,331][87426] Updated weights for policy 1, policy_version 49180 (0.0011) -[2023-11-28 01:30:09,608][87424] Updated weights for policy 0, policy_version 49286 (0.0012) -[2023-11-28 01:30:09,991][87424] Updated weights for policy 0, policy_version 49296 (0.0012) -[2023-11-28 01:30:10,376][87424] Updated weights for policy 0, policy_version 49306 (0.0012) -[2023-11-28 01:30:11,649][87426] Updated weights for policy 1, policy_version 49190 (0.0011) -[2023-11-28 01:30:12,023][87426] Updated weights for policy 1, policy_version 49200 (0.0011) -[2023-11-28 01:30:12,400][87426] Updated weights for policy 1, policy_version 49210 (0.0011) -[2023-11-28 01:30:12,544][87424] Updated weights for policy 0, policy_version 49316 (0.0010) -[2023-11-28 01:30:12,921][87424] Updated weights for policy 0, policy_version 49326 (0.0008) -[2023-11-28 01:30:13,309][87424] Updated weights for policy 0, policy_version 49336 (0.0011) -[2023-11-28 01:30:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 25223168. Throughput: 0: 2660.1, 1: 2681.2. Samples: 25239056. Policy #0 lag: (min: 21.0, avg: 41.2, max: 53.0) -[2023-11-28 01:30:13,445][86177] Avg episode reward: [(0, '-498.260'), (1, '-498.660')] -[2023-11-28 01:30:14,929][87426] Updated weights for policy 1, policy_version 49220 (0.0010) -[2023-11-28 01:30:15,309][87426] Updated weights for policy 1, policy_version 49230 (0.0011) -[2023-11-28 01:30:15,550][87424] Updated weights for policy 0, policy_version 49346 (0.0009) -[2023-11-28 01:30:15,682][87426] Updated weights for policy 1, policy_version 49240 (0.0011) -[2023-11-28 01:30:15,929][87424] Updated weights for policy 0, policy_version 49356 (0.0011) -[2023-11-28 01:30:16,311][87424] Updated weights for policy 0, policy_version 49366 (0.0012) -[2023-11-28 01:30:16,696][87424] Updated weights for policy 0, policy_version 49376 (0.0008) -[2023-11-28 01:30:17,485][87426] Updated weights for policy 1, policy_version 49250 (0.0011) -[2023-11-28 01:30:17,848][87426] Updated weights for policy 1, policy_version 49260 (0.0012) -[2023-11-28 01:30:18,220][87426] Updated weights for policy 1, policy_version 49270 (0.0012) -[2023-11-28 01:30:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 25247744. Throughput: 0: 2669.6, 1: 2683.1. Samples: 25263484. Policy #0 lag: (min: 21.0, avg: 41.2, max: 53.0) -[2023-11-28 01:30:18,445][86177] Avg episode reward: [(0, '-507.420'), (1, '-498.310')] -[2023-11-28 01:30:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000049376_12640256.pth... -[2023-11-28 01:30:18,484][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000046880_12001280.pth -[2023-11-28 01:30:18,591][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000049280_12615680.pth... -[2023-11-28 01:30:18,593][87426] Updated weights for policy 1, policy_version 49280 (0.0012) -[2023-11-28 01:30:18,622][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000046720_11960320.pth -[2023-11-28 01:30:19,096][87424] Updated weights for policy 0, policy_version 49386 (0.0011) -[2023-11-28 01:30:19,481][87424] Updated weights for policy 0, policy_version 49396 (0.0011) -[2023-11-28 01:30:19,863][87424] Updated weights for policy 0, policy_version 49406 (0.0010) -[2023-11-28 01:30:20,966][87426] Updated weights for policy 1, policy_version 49290 (0.0010) -[2023-11-28 01:30:21,344][87426] Updated weights for policy 1, policy_version 49300 (0.0009) -[2023-11-28 01:30:21,721][87426] Updated weights for policy 1, policy_version 49310 (0.0008) -[2023-11-28 01:30:22,328][87424] Updated weights for policy 0, policy_version 49416 (0.0010) -[2023-11-28 01:30:22,706][87424] Updated weights for policy 0, policy_version 49426 (0.0008) -[2023-11-28 01:30:23,088][87424] Updated weights for policy 0, policy_version 49436 (0.0008) -[2023-11-28 01:30:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 25280512. Throughput: 0: 2654.6, 1: 2710.0. Samples: 25295784. Policy #0 lag: (min: 21.0, avg: 41.2, max: 53.0) -[2023-11-28 01:30:23,445][86177] Avg episode reward: [(0, '-502.240'), (1, '-505.390')] -[2023-11-28 01:30:24,041][87426] Updated weights for policy 1, policy_version 49320 (0.0011) -[2023-11-28 01:30:24,429][87426] Updated weights for policy 1, policy_version 49330 (0.0011) -[2023-11-28 01:30:24,814][87426] Updated weights for policy 1, policy_version 49340 (0.0011) -[2023-11-28 01:30:25,407][87424] Updated weights for policy 0, policy_version 49446 (0.0007) -[2023-11-28 01:30:25,781][87424] Updated weights for policy 0, policy_version 49456 (0.0007) -[2023-11-28 01:30:26,176][87424] Updated weights for policy 0, policy_version 49466 (0.0007) -[2023-11-28 01:30:27,068][87426] Updated weights for policy 1, policy_version 49350 (0.0011) -[2023-11-28 01:30:27,462][87426] Updated weights for policy 1, policy_version 49360 (0.0012) -[2023-11-28 01:30:27,828][87426] Updated weights for policy 1, policy_version 49370 (0.0011) -[2023-11-28 01:30:28,433][87424] Updated weights for policy 0, policy_version 49476 (0.0007) -[2023-11-28 01:30:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 25305088. Throughput: 0: 2650.3, 1: 2699.3. Samples: 25318880. Policy #0 lag: (min: 21.0, avg: 41.2, max: 53.0) -[2023-11-28 01:30:28,446][86177] Avg episode reward: [(0, '-506.050'), (1, '-515.860')] -[2023-11-28 01:30:28,825][87424] Updated weights for policy 0, policy_version 49486 (0.0008) -[2023-11-28 01:30:29,213][87424] Updated weights for policy 0, policy_version 49496 (0.0011) -[2023-11-28 01:30:29,562][87426] Updated weights for policy 1, policy_version 49380 (0.0011) -[2023-11-28 01:30:29,953][87426] Updated weights for policy 1, policy_version 49390 (0.0009) -[2023-11-28 01:30:30,328][87426] Updated weights for policy 1, policy_version 49400 (0.0007) -[2023-11-28 01:30:31,253][87424] Updated weights for policy 0, policy_version 49506 (0.0012) -[2023-11-28 01:30:31,631][87424] Updated weights for policy 0, policy_version 49516 (0.0012) -[2023-11-28 01:30:32,001][87424] Updated weights for policy 0, policy_version 49526 (0.0012) -[2023-11-28 01:30:32,377][87424] Updated weights for policy 0, policy_version 49536 (0.0011) -[2023-11-28 01:30:32,452][87426] Updated weights for policy 1, policy_version 49410 (0.0010) -[2023-11-28 01:30:32,828][87426] Updated weights for policy 1, policy_version 49420 (0.0008) -[2023-11-28 01:30:33,215][87426] Updated weights for policy 1, policy_version 49430 (0.0008) -[2023-11-28 01:30:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 25329664. Throughput: 0: 2662.5, 1: 2693.2. Samples: 25343248. Policy #0 lag: (min: 21.0, avg: 41.2, max: 53.0) -[2023-11-28 01:30:33,445][86177] Avg episode reward: [(0, '-508.770'), (1, '-514.670')] -[2023-11-28 01:30:33,597][87426] Updated weights for policy 1, policy_version 49440 (0.0008) -[2023-11-28 01:30:34,819][87424] Updated weights for policy 0, policy_version 49546 (0.0011) -[2023-11-28 01:30:35,196][87424] Updated weights for policy 0, policy_version 49556 (0.0009) -[2023-11-28 01:30:35,413][87426] Updated weights for policy 1, policy_version 49450 (0.0008) -[2023-11-28 01:30:35,578][87424] Updated weights for policy 0, policy_version 49566 (0.0008) -[2023-11-28 01:30:35,796][87426] Updated weights for policy 1, policy_version 49460 (0.0010) -[2023-11-28 01:30:36,176][87426] Updated weights for policy 1, policy_version 49470 (0.0010) -[2023-11-28 01:30:37,707][87424] Updated weights for policy 0, policy_version 49576 (0.0008) -[2023-11-28 01:30:38,094][87424] Updated weights for policy 0, policy_version 49586 (0.0008) -[2023-11-28 01:30:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 25354240. Throughput: 0: 2640.3, 1: 2724.7. Samples: 25376664. Policy #0 lag: (min: 21.0, avg: 41.2, max: 53.0) -[2023-11-28 01:30:38,446][86177] Avg episode reward: [(0, '-501.290'), (1, '-520.150')] -[2023-11-28 01:30:38,466][87426] Updated weights for policy 1, policy_version 49480 (0.0007) -[2023-11-28 01:30:38,475][87424] Updated weights for policy 0, policy_version 49596 (0.0007) -[2023-11-28 01:30:38,851][87426] Updated weights for policy 1, policy_version 49490 (0.0009) -[2023-11-28 01:30:39,221][87426] Updated weights for policy 1, policy_version 49500 (0.0010) -[2023-11-28 01:30:40,475][87424] Updated weights for policy 0, policy_version 49606 (0.0010) -[2023-11-28 01:30:40,853][87424] Updated weights for policy 0, policy_version 49616 (0.0008) -[2023-11-28 01:30:41,236][87424] Updated weights for policy 0, policy_version 49626 (0.0008) -[2023-11-28 01:30:41,325][87426] Updated weights for policy 1, policy_version 49510 (0.0011) -[2023-11-28 01:30:41,702][87426] Updated weights for policy 1, policy_version 49520 (0.0009) -[2023-11-28 01:30:42,078][87426] Updated weights for policy 1, policy_version 49530 (0.0009) -[2023-11-28 01:30:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 25387008. Throughput: 0: 2622.6, 1: 2712.7. Samples: 25400124. Policy #0 lag: (min: 31.0, avg: 50.1, max: 85.0) -[2023-11-28 01:30:43,445][86177] Avg episode reward: [(0, '-499.300'), (1, '-545.480')] -[2023-11-28 01:30:43,631][87424] Updated weights for policy 0, policy_version 49636 (0.0009) -[2023-11-28 01:30:44,012][87424] Updated weights for policy 0, policy_version 49646 (0.0007) -[2023-11-28 01:30:44,394][87424] Updated weights for policy 0, policy_version 49656 (0.0009) -[2023-11-28 01:30:44,477][87426] Updated weights for policy 1, policy_version 49540 (0.0010) -[2023-11-28 01:30:44,862][87426] Updated weights for policy 1, policy_version 49550 (0.0012) -[2023-11-28 01:30:45,232][87426] Updated weights for policy 1, policy_version 49560 (0.0011) -[2023-11-28 01:30:46,463][87424] Updated weights for policy 0, policy_version 49666 (0.0011) -[2023-11-28 01:30:46,840][87424] Updated weights for policy 0, policy_version 49676 (0.0012) -[2023-11-28 01:30:47,213][87424] Updated weights for policy 0, policy_version 49686 (0.0011) -[2023-11-28 01:30:47,514][87426] Updated weights for policy 1, policy_version 49570 (0.0011) -[2023-11-28 01:30:47,594][87424] Updated weights for policy 0, policy_version 49696 (0.0007) -[2023-11-28 01:30:47,893][87426] Updated weights for policy 1, policy_version 49580 (0.0011) -[2023-11-28 01:30:48,284][87426] Updated weights for policy 1, policy_version 49590 (0.0012) -[2023-11-28 01:30:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 25411584. Throughput: 0: 2651.9, 1: 2721.7. Samples: 25424836. Policy #0 lag: (min: 31.0, avg: 50.1, max: 85.0) -[2023-11-28 01:30:48,445][86177] Avg episode reward: [(0, '-495.940'), (1, '-524.730')] -[2023-11-28 01:30:48,454][87281] Saving new best policy, reward=-495.940! -[2023-11-28 01:30:48,666][87426] Updated weights for policy 1, policy_version 49600 (0.0012) -[2023-11-28 01:30:49,938][87424] Updated weights for policy 0, policy_version 49706 (0.0012) -[2023-11-28 01:30:50,329][87424] Updated weights for policy 0, policy_version 49716 (0.0008) -[2023-11-28 01:30:50,711][87424] Updated weights for policy 0, policy_version 49726 (0.0008) -[2023-11-28 01:30:51,106][87426] Updated weights for policy 1, policy_version 49610 (0.0012) -[2023-11-28 01:30:51,476][87426] Updated weights for policy 1, policy_version 49620 (0.0011) -[2023-11-28 01:30:51,855][87426] Updated weights for policy 1, policy_version 49630 (0.0012) -[2023-11-28 01:30:52,887][87424] Updated weights for policy 0, policy_version 49736 (0.0009) -[2023-11-28 01:30:53,273][87424] Updated weights for policy 0, policy_version 49746 (0.0011) -[2023-11-28 01:30:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 25436160. Throughput: 0: 2650.1, 1: 2723.7. Samples: 25457188. Policy #0 lag: (min: 31.0, avg: 50.1, max: 85.0) -[2023-11-28 01:30:53,445][86177] Avg episode reward: [(0, '-494.740'), (1, '-529.030')] -[2023-11-28 01:30:53,660][87424] Updated weights for policy 0, policy_version 49756 (0.0010) -[2023-11-28 01:30:53,807][87281] Saving new best policy, reward=-494.740! -[2023-11-28 01:30:53,834][87426] Updated weights for policy 1, policy_version 49640 (0.0010) -[2023-11-28 01:30:54,214][87426] Updated weights for policy 1, policy_version 49650 (0.0007) -[2023-11-28 01:30:54,592][87426] Updated weights for policy 1, policy_version 49660 (0.0007) -[2023-11-28 01:30:56,138][87424] Updated weights for policy 0, policy_version 49766 (0.0010) -[2023-11-28 01:30:56,525][87424] Updated weights for policy 0, policy_version 49776 (0.0009) -[2023-11-28 01:30:56,748][87426] Updated weights for policy 1, policy_version 49670 (0.0010) -[2023-11-28 01:30:56,909][87424] Updated weights for policy 0, policy_version 49786 (0.0007) -[2023-11-28 01:30:57,126][87426] Updated weights for policy 1, policy_version 49680 (0.0012) -[2023-11-28 01:30:57,512][87426] Updated weights for policy 1, policy_version 49690 (0.0012) -[2023-11-28 01:30:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 25468928. Throughput: 0: 2646.2, 1: 2739.7. Samples: 25481424. Policy #0 lag: (min: 31.0, avg: 50.1, max: 85.0) -[2023-11-28 01:30:58,446][86177] Avg episode reward: [(0, '-496.830'), (1, '-524.140')] -[2023-11-28 01:30:59,270][87424] Updated weights for policy 0, policy_version 49796 (0.0008) -[2023-11-28 01:30:59,518][87426] Updated weights for policy 1, policy_version 49700 (0.0011) -[2023-11-28 01:30:59,655][87424] Updated weights for policy 0, policy_version 49806 (0.0009) -[2023-11-28 01:30:59,902][87426] Updated weights for policy 1, policy_version 49710 (0.0011) -[2023-11-28 01:31:00,039][87424] Updated weights for policy 0, policy_version 49816 (0.0009) -[2023-11-28 01:31:00,267][87426] Updated weights for policy 1, policy_version 49720 (0.0010) -[2023-11-28 01:31:02,142][87426] Updated weights for policy 1, policy_version 49730 (0.0012) -[2023-11-28 01:31:02,276][87424] Updated weights for policy 0, policy_version 49826 (0.0008) -[2023-11-28 01:31:02,519][87426] Updated weights for policy 1, policy_version 49740 (0.0011) -[2023-11-28 01:31:02,656][87424] Updated weights for policy 0, policy_version 49836 (0.0008) -[2023-11-28 01:31:02,893][87426] Updated weights for policy 1, policy_version 49750 (0.0012) -[2023-11-28 01:31:03,042][87424] Updated weights for policy 0, policy_version 49846 (0.0010) -[2023-11-28 01:31:03,269][87426] Updated weights for policy 1, policy_version 49760 (0.0009) -[2023-11-28 01:31:03,427][87424] Updated weights for policy 0, policy_version 49856 (0.0007) -[2023-11-28 01:31:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 25501696. Throughput: 0: 2650.9, 1: 2746.9. Samples: 25506388. Policy #0 lag: (min: 31.0, avg: 50.1, max: 85.0) -[2023-11-28 01:31:03,445][86177] Avg episode reward: [(0, '-499.860'), (1, '-500.320')] -[2023-11-28 01:31:05,353][87426] Updated weights for policy 1, policy_version 49770 (0.0009) -[2023-11-28 01:31:05,386][87424] Updated weights for policy 0, policy_version 49866 (0.0009) -[2023-11-28 01:31:05,736][87426] Updated weights for policy 1, policy_version 49780 (0.0007) -[2023-11-28 01:31:05,771][87424] Updated weights for policy 0, policy_version 49876 (0.0007) -[2023-11-28 01:31:06,120][87426] Updated weights for policy 1, policy_version 49790 (0.0007) -[2023-11-28 01:31:06,152][87424] Updated weights for policy 0, policy_version 49886 (0.0008) -[2023-11-28 01:31:08,092][87424] Updated weights for policy 0, policy_version 49896 (0.0008) -[2023-11-28 01:31:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 25518080. Throughput: 0: 2683.0, 1: 2729.2. Samples: 25539332. Policy #0 lag: (min: 31.0, avg: 50.1, max: 85.0) -[2023-11-28 01:31:08,445][86177] Avg episode reward: [(0, '-500.180'), (1, '-501.780')] -[2023-11-28 01:31:08,470][87424] Updated weights for policy 0, policy_version 49906 (0.0010) -[2023-11-28 01:31:08,488][87426] Updated weights for policy 1, policy_version 49800 (0.0010) -[2023-11-28 01:31:08,851][87424] Updated weights for policy 0, policy_version 49916 (0.0008) -[2023-11-28 01:31:08,868][87426] Updated weights for policy 1, policy_version 49810 (0.0011) -[2023-11-28 01:31:09,250][87426] Updated weights for policy 1, policy_version 49820 (0.0010) -[2023-11-28 01:31:11,161][87424] Updated weights for policy 0, policy_version 49926 (0.0008) -[2023-11-28 01:31:11,543][87424] Updated weights for policy 0, policy_version 49936 (0.0010) -[2023-11-28 01:31:11,743][87426] Updated weights for policy 1, policy_version 49830 (0.0010) -[2023-11-28 01:31:11,929][87424] Updated weights for policy 0, policy_version 49946 (0.0009) -[2023-11-28 01:31:12,125][87426] Updated weights for policy 1, policy_version 49840 (0.0011) -[2023-11-28 01:31:12,503][87426] Updated weights for policy 1, policy_version 49850 (0.0012) -[2023-11-28 01:31:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 25550848. Throughput: 0: 2687.6, 1: 2728.5. Samples: 25562604. Policy #0 lag: (min: 31.0, avg: 50.1, max: 85.0) -[2023-11-28 01:31:13,445][86177] Avg episode reward: [(0, '-502.950'), (1, '-503.410')] -[2023-11-28 01:31:14,644][87424] Updated weights for policy 0, policy_version 49956 (0.0009) -[2023-11-28 01:31:14,838][87426] Updated weights for policy 1, policy_version 49860 (0.0009) -[2023-11-28 01:31:15,037][87424] Updated weights for policy 0, policy_version 49966 (0.0010) -[2023-11-28 01:31:15,220][87426] Updated weights for policy 1, policy_version 49870 (0.0009) -[2023-11-28 01:31:15,417][87424] Updated weights for policy 0, policy_version 49976 (0.0010) -[2023-11-28 01:31:15,593][87426] Updated weights for policy 1, policy_version 49880 (0.0011) -[2023-11-28 01:31:17,323][87424] Updated weights for policy 0, policy_version 49986 (0.0011) -[2023-11-28 01:31:17,548][87426] Updated weights for policy 1, policy_version 49890 (0.0011) -[2023-11-28 01:31:17,704][87424] Updated weights for policy 0, policy_version 49996 (0.0011) -[2023-11-28 01:31:17,930][87426] Updated weights for policy 1, policy_version 49900 (0.0011) -[2023-11-28 01:31:18,083][87424] Updated weights for policy 0, policy_version 50006 (0.0007) -[2023-11-28 01:31:18,304][87426] Updated weights for policy 1, policy_version 49910 (0.0008) -[2023-11-28 01:31:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 25567232. Throughput: 0: 2703.3, 1: 2736.9. Samples: 25588056. Policy #0 lag: (min: 11.0, avg: 36.7, max: 48.0) -[2023-11-28 01:31:18,445][86177] Avg episode reward: [(0, '-501.590'), (1, '-598.660')] -[2023-11-28 01:31:18,475][87424] Updated weights for policy 0, policy_version 50016 (0.0010) -[2023-11-28 01:31:18,689][87426] Updated weights for policy 1, policy_version 49920 (0.0011) -[2023-11-28 01:31:20,164][87424] Updated weights for policy 0, policy_version 50026 (0.0011) -[2023-11-28 01:31:20,495][87426] Updated weights for policy 1, policy_version 49930 (0.0009) -[2023-11-28 01:31:20,544][87424] Updated weights for policy 0, policy_version 50036 (0.0012) -[2023-11-28 01:31:20,875][87426] Updated weights for policy 1, policy_version 49940 (0.0007) -[2023-11-28 01:31:20,934][87424] Updated weights for policy 0, policy_version 50046 (0.0011) -[2023-11-28 01:31:21,249][87426] Updated weights for policy 1, policy_version 49950 (0.0010) -[2023-11-28 01:31:23,318][87424] Updated weights for policy 0, policy_version 50056 (0.0011) -[2023-11-28 01:31:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 25600000. Throughput: 0: 2702.2, 1: 2745.9. Samples: 25621828. Policy #0 lag: (min: 11.0, avg: 36.7, max: 48.0) -[2023-11-28 01:31:23,445][86177] Avg episode reward: [(0, '-501.340'), (1, '-599.100')] -[2023-11-28 01:31:23,501][87426] Updated weights for policy 1, policy_version 49960 (0.0010) -[2023-11-28 01:31:23,700][87424] Updated weights for policy 0, policy_version 50066 (0.0010) -[2023-11-28 01:31:23,877][87426] Updated weights for policy 1, policy_version 49970 (0.0012) -[2023-11-28 01:31:24,084][87424] Updated weights for policy 0, policy_version 50076 (0.0011) -[2023-11-28 01:31:24,257][87426] Updated weights for policy 1, policy_version 49980 (0.0011) -[2023-11-28 01:31:25,951][87424] Updated weights for policy 0, policy_version 50086 (0.0009) -[2023-11-28 01:31:26,344][87424] Updated weights for policy 0, policy_version 50096 (0.0011) -[2023-11-28 01:31:26,571][87426] Updated weights for policy 1, policy_version 49990 (0.0009) -[2023-11-28 01:31:26,727][87424] Updated weights for policy 0, policy_version 50106 (0.0010) -[2023-11-28 01:31:26,943][87426] Updated weights for policy 1, policy_version 50000 (0.0007) -[2023-11-28 01:31:27,323][87426] Updated weights for policy 1, policy_version 50010 (0.0007) -[2023-11-28 01:31:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 25632768. Throughput: 0: 2710.0, 1: 2746.9. Samples: 25645688. Policy #0 lag: (min: 11.0, avg: 36.7, max: 48.0) -[2023-11-28 01:31:28,445][86177] Avg episode reward: [(0, '-512.110'), (1, '-601.620')] -[2023-11-28 01:31:29,046][87424] Updated weights for policy 0, policy_version 50116 (0.0009) -[2023-11-28 01:31:29,441][87424] Updated weights for policy 0, policy_version 50126 (0.0012) -[2023-11-28 01:31:29,760][87426] Updated weights for policy 1, policy_version 50020 (0.0008) -[2023-11-28 01:31:29,820][87424] Updated weights for policy 0, policy_version 50136 (0.0012) -[2023-11-28 01:31:30,133][87426] Updated weights for policy 1, policy_version 50030 (0.0010) -[2023-11-28 01:31:30,519][87426] Updated weights for policy 1, policy_version 50040 (0.0008) -[2023-11-28 01:31:31,913][87424] Updated weights for policy 0, policy_version 50146 (0.0011) -[2023-11-28 01:31:32,299][87424] Updated weights for policy 0, policy_version 50156 (0.0012) -[2023-11-28 01:31:32,333][87426] Updated weights for policy 1, policy_version 50050 (0.0008) -[2023-11-28 01:31:32,677][87424] Updated weights for policy 0, policy_version 50166 (0.0011) -[2023-11-28 01:31:32,709][87426] Updated weights for policy 1, policy_version 50060 (0.0009) -[2023-11-28 01:31:33,051][87424] Updated weights for policy 0, policy_version 50176 (0.0009) -[2023-11-28 01:31:33,084][87426] Updated weights for policy 1, policy_version 50070 (0.0008) -[2023-11-28 01:31:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 25657344. Throughput: 0: 2713.9, 1: 2741.1. Samples: 25670316. Policy #0 lag: (min: 11.0, avg: 36.7, max: 48.0) -[2023-11-28 01:31:33,446][86177] Avg episode reward: [(0, '-517.310'), (1, '-535.730')] -[2023-11-28 01:31:33,468][87426] Updated weights for policy 1, policy_version 50080 (0.0009) -[2023-11-28 01:31:35,037][87424] Updated weights for policy 0, policy_version 50186 (0.0012) -[2023-11-28 01:31:35,413][87424] Updated weights for policy 0, policy_version 50196 (0.0012) -[2023-11-28 01:31:35,796][87424] Updated weights for policy 0, policy_version 50206 (0.0009) -[2023-11-28 01:31:35,940][87426] Updated weights for policy 1, policy_version 50090 (0.0009) -[2023-11-28 01:31:36,321][87426] Updated weights for policy 1, policy_version 50100 (0.0007) -[2023-11-28 01:31:36,709][87426] Updated weights for policy 1, policy_version 50110 (0.0008) -[2023-11-28 01:31:37,837][87424] Updated weights for policy 0, policy_version 50216 (0.0011) -[2023-11-28 01:31:38,214][87424] Updated weights for policy 0, policy_version 50226 (0.0011) -[2023-11-28 01:31:38,443][87426] Updated weights for policy 1, policy_version 50120 (0.0011) -[2023-11-28 01:31:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 25681920. Throughput: 0: 2717.3, 1: 2755.6. Samples: 25703468. Policy #0 lag: (min: 11.0, avg: 36.7, max: 48.0) -[2023-11-28 01:31:38,445][86177] Avg episode reward: [(0, '-532.720'), (1, '-536.870')] -[2023-11-28 01:31:38,596][87424] Updated weights for policy 0, policy_version 50236 (0.0010) -[2023-11-28 01:31:38,828][87426] Updated weights for policy 1, policy_version 50130 (0.0012) -[2023-11-28 01:31:39,189][87426] Updated weights for policy 1, policy_version 50140 (0.0012) -[2023-11-28 01:31:40,488][87424] Updated weights for policy 0, policy_version 50246 (0.0010) -[2023-11-28 01:31:40,865][87424] Updated weights for policy 0, policy_version 50256 (0.0012) -[2023-11-28 01:31:41,246][87424] Updated weights for policy 0, policy_version 50266 (0.0012) -[2023-11-28 01:31:41,477][87426] Updated weights for policy 1, policy_version 50150 (0.0012) -[2023-11-28 01:31:41,876][87426] Updated weights for policy 1, policy_version 50160 (0.0011) -[2023-11-28 01:31:42,259][87426] Updated weights for policy 1, policy_version 50170 (0.0010) -[2023-11-28 01:31:43,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 25714688. Throughput: 0: 2734.4, 1: 2729.0. Samples: 25727276. Policy #0 lag: (min: 11.0, avg: 36.7, max: 48.0) -[2023-11-28 01:31:43,446][86177] Avg episode reward: [(0, '-529.220'), (1, '-536.690')] -[2023-11-28 01:31:43,549][87424] Updated weights for policy 0, policy_version 50276 (0.0011) -[2023-11-28 01:31:43,937][87424] Updated weights for policy 0, policy_version 50286 (0.0012) -[2023-11-28 01:31:44,328][87424] Updated weights for policy 0, policy_version 50296 (0.0012) -[2023-11-28 01:31:44,728][87426] Updated weights for policy 1, policy_version 50180 (0.0011) -[2023-11-28 01:31:45,099][87426] Updated weights for policy 1, policy_version 50190 (0.0012) -[2023-11-28 01:31:45,485][87426] Updated weights for policy 1, policy_version 50200 (0.0011) -[2023-11-28 01:31:46,403][87424] Updated weights for policy 0, policy_version 50306 (0.0012) -[2023-11-28 01:31:46,804][87424] Updated weights for policy 0, policy_version 50316 (0.0012) -[2023-11-28 01:31:47,190][87424] Updated weights for policy 0, policy_version 50326 (0.0011) -[2023-11-28 01:31:47,575][87424] Updated weights for policy 0, policy_version 50336 (0.0008) -[2023-11-28 01:31:47,624][87426] Updated weights for policy 1, policy_version 50210 (0.0011) -[2023-11-28 01:31:47,999][87426] Updated weights for policy 1, policy_version 50220 (0.0011) -[2023-11-28 01:31:48,384][87426] Updated weights for policy 1, policy_version 50230 (0.0012) -[2023-11-28 01:31:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 25739264. Throughput: 0: 2744.6, 1: 2711.3. Samples: 25751904. Policy #0 lag: (min: 18.0, avg: 36.0, max: 50.0) -[2023-11-28 01:31:48,446][86177] Avg episode reward: [(0, '-521.300'), (1, '-570.340')] -[2023-11-28 01:31:48,767][87426] Updated weights for policy 1, policy_version 50240 (0.0012) -[2023-11-28 01:31:49,745][87424] Updated weights for policy 0, policy_version 50346 (0.0012) -[2023-11-28 01:31:50,125][87424] Updated weights for policy 0, policy_version 50356 (0.0012) -[2023-11-28 01:31:50,511][87424] Updated weights for policy 0, policy_version 50366 (0.0011) -[2023-11-28 01:31:50,884][87426] Updated weights for policy 1, policy_version 50250 (0.0012) -[2023-11-28 01:31:51,264][87426] Updated weights for policy 1, policy_version 50260 (0.0012) -[2023-11-28 01:31:51,640][87426] Updated weights for policy 1, policy_version 50270 (0.0012) -[2023-11-28 01:31:52,868][87424] Updated weights for policy 0, policy_version 50376 (0.0008) -[2023-11-28 01:31:53,254][87424] Updated weights for policy 0, policy_version 50386 (0.0009) -[2023-11-28 01:31:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 25763840. Throughput: 0: 2741.5, 1: 2748.2. Samples: 25786368. Policy #0 lag: (min: 18.0, avg: 36.0, max: 50.0) -[2023-11-28 01:31:53,445][86177] Avg episode reward: [(0, '-519.700'), (1, '-560.940')] -[2023-11-28 01:31:53,572][87426] Updated weights for policy 1, policy_version 50280 (0.0011) -[2023-11-28 01:31:53,633][87424] Updated weights for policy 0, policy_version 50396 (0.0010) -[2023-11-28 01:31:53,951][87426] Updated weights for policy 1, policy_version 50290 (0.0012) -[2023-11-28 01:31:54,323][87426] Updated weights for policy 1, policy_version 50300 (0.0011) -[2023-11-28 01:31:55,501][87424] Updated weights for policy 0, policy_version 50406 (0.0011) -[2023-11-28 01:31:55,881][87424] Updated weights for policy 0, policy_version 50416 (0.0012) -[2023-11-28 01:31:56,265][87424] Updated weights for policy 0, policy_version 50426 (0.0012) -[2023-11-28 01:31:56,399][87426] Updated weights for policy 1, policy_version 50310 (0.0009) -[2023-11-28 01:31:56,778][87426] Updated weights for policy 1, policy_version 50320 (0.0007) -[2023-11-28 01:31:57,162][87426] Updated weights for policy 1, policy_version 50330 (0.0007) -[2023-11-28 01:31:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 25796608. Throughput: 0: 2745.4, 1: 2783.2. Samples: 25811392. Policy #0 lag: (min: 18.0, avg: 36.0, max: 50.0) -[2023-11-28 01:31:58,445][86177] Avg episode reward: [(0, '-518.100'), (1, '-561.220')] -[2023-11-28 01:31:58,586][87424] Updated weights for policy 0, policy_version 50436 (0.0012) -[2023-11-28 01:31:58,784][87426] Updated weights for policy 1, policy_version 50340 (0.0009) -[2023-11-28 01:31:58,962][87424] Updated weights for policy 0, policy_version 50446 (0.0012) -[2023-11-28 01:31:59,156][87426] Updated weights for policy 1, policy_version 50350 (0.0010) -[2023-11-28 01:31:59,341][87424] Updated weights for policy 0, policy_version 50456 (0.0011) -[2023-11-28 01:31:59,535][87426] Updated weights for policy 1, policy_version 50360 (0.0010) -[2023-11-28 01:32:01,330][87424] Updated weights for policy 0, policy_version 50466 (0.0012) -[2023-11-28 01:32:01,711][87424] Updated weights for policy 0, policy_version 50476 (0.0012) -[2023-11-28 01:32:02,004][87426] Updated weights for policy 1, policy_version 50370 (0.0011) -[2023-11-28 01:32:02,089][87424] Updated weights for policy 0, policy_version 50486 (0.0012) -[2023-11-28 01:32:02,379][87426] Updated weights for policy 1, policy_version 50380 (0.0009) -[2023-11-28 01:32:02,465][87424] Updated weights for policy 0, policy_version 50496 (0.0011) -[2023-11-28 01:32:02,754][87426] Updated weights for policy 1, policy_version 50390 (0.0007) -[2023-11-28 01:32:03,135][87426] Updated weights for policy 1, policy_version 50400 (0.0008) -[2023-11-28 01:32:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 25829376. Throughput: 0: 2746.6, 1: 2768.4. Samples: 25836228. Policy #0 lag: (min: 18.0, avg: 36.0, max: 50.0) -[2023-11-28 01:32:03,445][86177] Avg episode reward: [(0, '-519.820'), (1, '-521.560')] -[2023-11-28 01:32:04,691][87424] Updated weights for policy 0, policy_version 50506 (0.0012) -[2023-11-28 01:32:05,074][87424] Updated weights for policy 0, policy_version 50516 (0.0011) -[2023-11-28 01:32:05,174][87426] Updated weights for policy 1, policy_version 50410 (0.0011) -[2023-11-28 01:32:05,459][87424] Updated weights for policy 0, policy_version 50526 (0.0012) -[2023-11-28 01:32:05,549][87426] Updated weights for policy 1, policy_version 50420 (0.0012) -[2023-11-28 01:32:05,917][87426] Updated weights for policy 1, policy_version 50430 (0.0012) -[2023-11-28 01:32:07,918][87424] Updated weights for policy 0, policy_version 50536 (0.0012) -[2023-11-28 01:32:08,203][87426] Updated weights for policy 1, policy_version 50440 (0.0008) -[2023-11-28 01:32:08,305][87424] Updated weights for policy 0, policy_version 50546 (0.0012) -[2023-11-28 01:32:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 25845760. Throughput: 0: 2740.8, 1: 2756.1. Samples: 25869188. Policy #0 lag: (min: 18.0, avg: 36.0, max: 50.0) -[2023-11-28 01:32:08,445][86177] Avg episode reward: [(0, '-511.520'), (1, '-532.070')] -[2023-11-28 01:32:08,587][87426] Updated weights for policy 1, policy_version 50450 (0.0007) -[2023-11-28 01:32:08,687][87424] Updated weights for policy 0, policy_version 50556 (0.0012) -[2023-11-28 01:32:08,967][87426] Updated weights for policy 1, policy_version 50460 (0.0008) -[2023-11-28 01:32:11,014][87424] Updated weights for policy 0, policy_version 50566 (0.0009) -[2023-11-28 01:32:11,369][87426] Updated weights for policy 1, policy_version 50470 (0.0010) -[2023-11-28 01:32:11,395][87424] Updated weights for policy 0, policy_version 50576 (0.0011) -[2023-11-28 01:32:11,744][87426] Updated weights for policy 1, policy_version 50480 (0.0011) -[2023-11-28 01:32:11,801][87424] Updated weights for policy 0, policy_version 50586 (0.0010) -[2023-11-28 01:32:12,125][87426] Updated weights for policy 1, policy_version 50490 (0.0011) -[2023-11-28 01:32:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 25878528. Throughput: 0: 2736.3, 1: 2763.1. Samples: 25893160. Policy #0 lag: (min: 18.0, avg: 36.0, max: 50.0) -[2023-11-28 01:32:13,445][86177] Avg episode reward: [(0, '-504.300'), (1, '-503.210')] -[2023-11-28 01:32:13,865][87424] Updated weights for policy 0, policy_version 50596 (0.0011) -[2023-11-28 01:32:14,247][87424] Updated weights for policy 0, policy_version 50606 (0.0012) -[2023-11-28 01:32:14,415][87426] Updated weights for policy 1, policy_version 50500 (0.0012) -[2023-11-28 01:32:14,620][87424] Updated weights for policy 0, policy_version 50616 (0.0010) -[2023-11-28 01:32:14,786][87426] Updated weights for policy 1, policy_version 50510 (0.0012) -[2023-11-28 01:32:15,162][87426] Updated weights for policy 1, policy_version 50520 (0.0010) -[2023-11-28 01:32:16,651][87424] Updated weights for policy 0, policy_version 50626 (0.0011) -[2023-11-28 01:32:17,036][87424] Updated weights for policy 0, policy_version 50636 (0.0010) -[2023-11-28 01:32:17,413][87424] Updated weights for policy 0, policy_version 50646 (0.0007) -[2023-11-28 01:32:17,430][87426] Updated weights for policy 1, policy_version 50530 (0.0011) -[2023-11-28 01:32:17,799][87424] Updated weights for policy 0, policy_version 50656 (0.0008) -[2023-11-28 01:32:17,810][87426] Updated weights for policy 1, policy_version 50540 (0.0010) -[2023-11-28 01:32:18,187][87426] Updated weights for policy 1, policy_version 50550 (0.0007) -[2023-11-28 01:32:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 25903104. Throughput: 0: 2739.2, 1: 2753.0. Samples: 25917464. Policy #0 lag: (min: 18.0, avg: 36.0, max: 50.0) -[2023-11-28 01:32:18,445][86177] Avg episode reward: [(0, '-501.550'), (1, '-504.170')] -[2023-11-28 01:32:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000050656_12967936.pth... -[2023-11-28 01:32:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000048128_12320768.pth -[2023-11-28 01:32:18,508][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000050656_12967936.pth -[2023-11-28 01:32:18,565][87426] Updated weights for policy 1, policy_version 50560 (0.0009) -[2023-11-28 01:32:18,566][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000050560_12943360.pth... -[2023-11-28 01:32:18,613][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000048000_12288000.pth -[2023-11-28 01:32:18,620][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000050560_12943360.pth -[2023-11-28 01:32:20,078][87424] Updated weights for policy 0, policy_version 50666 (0.0012) -[2023-11-28 01:32:20,451][87424] Updated weights for policy 0, policy_version 50676 (0.0010) -[2023-11-28 01:32:20,654][87426] Updated weights for policy 1, policy_version 50570 (0.0012) -[2023-11-28 01:32:20,839][87424] Updated weights for policy 0, policy_version 50686 (0.0008) -[2023-11-28 01:32:21,032][87426] Updated weights for policy 1, policy_version 50580 (0.0011) -[2023-11-28 01:32:21,413][87426] Updated weights for policy 1, policy_version 50590 (0.0012) -[2023-11-28 01:32:22,978][87424] Updated weights for policy 0, policy_version 50696 (0.0010) -[2023-11-28 01:32:23,356][87424] Updated weights for policy 0, policy_version 50706 (0.0009) -[2023-11-28 01:32:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 25927680. Throughput: 0: 2752.8, 1: 2732.2. Samples: 25950292. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:32:23,445][86177] Avg episode reward: [(0, '-500.350'), (1, '-506.270')] -[2023-11-28 01:32:23,745][87424] Updated weights for policy 0, policy_version 50716 (0.0008) -[2023-11-28 01:32:23,875][87426] Updated weights for policy 1, policy_version 50600 (0.0012) -[2023-11-28 01:32:24,262][87426] Updated weights for policy 1, policy_version 50610 (0.0012) -[2023-11-28 01:32:24,640][87426] Updated weights for policy 1, policy_version 50620 (0.0012) -[2023-11-28 01:32:26,028][87424] Updated weights for policy 0, policy_version 50726 (0.0010) -[2023-11-28 01:32:26,415][87424] Updated weights for policy 0, policy_version 50736 (0.0012) -[2023-11-28 01:32:26,610][87426] Updated weights for policy 1, policy_version 50630 (0.0011) -[2023-11-28 01:32:26,803][87424] Updated weights for policy 0, policy_version 50746 (0.0011) -[2023-11-28 01:32:26,999][87426] Updated weights for policy 1, policy_version 50640 (0.0012) -[2023-11-28 01:32:27,380][87426] Updated weights for policy 1, policy_version 50650 (0.0011) -[2023-11-28 01:32:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 25960448. Throughput: 0: 2764.5, 1: 2769.3. Samples: 25976300. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:32:28,445][86177] Avg episode reward: [(0, '-502.000'), (1, '-500.300')] -[2023-11-28 01:32:28,536][87424] Updated weights for policy 0, policy_version 50756 (0.0009) -[2023-11-28 01:32:28,916][87424] Updated weights for policy 0, policy_version 50766 (0.0008) -[2023-11-28 01:32:29,302][87424] Updated weights for policy 0, policy_version 50776 (0.0012) -[2023-11-28 01:32:29,316][87426] Updated weights for policy 1, policy_version 50660 (0.0010) -[2023-11-28 01:32:29,697][87426] Updated weights for policy 1, policy_version 50670 (0.0007) -[2023-11-28 01:32:30,081][87426] Updated weights for policy 1, policy_version 50680 (0.0009) -[2023-11-28 01:32:31,347][87424] Updated weights for policy 0, policy_version 50786 (0.0010) -[2023-11-28 01:32:31,731][87424] Updated weights for policy 0, policy_version 50796 (0.0008) -[2023-11-28 01:32:31,972][87426] Updated weights for policy 1, policy_version 50690 (0.0010) -[2023-11-28 01:32:32,108][87424] Updated weights for policy 0, policy_version 50806 (0.0011) -[2023-11-28 01:32:32,340][87426] Updated weights for policy 1, policy_version 50700 (0.0009) -[2023-11-28 01:32:32,492][87424] Updated weights for policy 0, policy_version 50816 (0.0011) -[2023-11-28 01:32:32,718][87426] Updated weights for policy 1, policy_version 50710 (0.0011) -[2023-11-28 01:32:33,086][87426] Updated weights for policy 1, policy_version 50720 (0.0011) -[2023-11-28 01:32:33,445][86177] Fps is (10 sec: 6553.3, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 25993216. Throughput: 0: 2761.0, 1: 2788.4. Samples: 26001628. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:32:33,446][86177] Avg episode reward: [(0, '-544.990'), (1, '-501.610')] -[2023-11-28 01:32:34,389][87424] Updated weights for policy 0, policy_version 50826 (0.0008) -[2023-11-28 01:32:34,782][87424] Updated weights for policy 0, policy_version 50836 (0.0008) -[2023-11-28 01:32:34,825][87426] Updated weights for policy 1, policy_version 50730 (0.0010) -[2023-11-28 01:32:35,155][87424] Updated weights for policy 0, policy_version 50846 (0.0008) -[2023-11-28 01:32:35,199][87426] Updated weights for policy 1, policy_version 50740 (0.0012) -[2023-11-28 01:32:35,583][87426] Updated weights for policy 1, policy_version 50750 (0.0012) -[2023-11-28 01:32:37,464][87424] Updated weights for policy 0, policy_version 50856 (0.0011) -[2023-11-28 01:32:37,850][87424] Updated weights for policy 0, policy_version 50866 (0.0016) -[2023-11-28 01:32:38,099][87426] Updated weights for policy 1, policy_version 50760 (0.0012) -[2023-11-28 01:32:38,230][87424] Updated weights for policy 0, policy_version 50876 (0.0012) -[2023-11-28 01:32:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 26017792. Throughput: 0: 2737.2, 1: 2771.8. Samples: 26034276. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:32:38,445][86177] Avg episode reward: [(0, '-545.880'), (1, '-500.880')] -[2023-11-28 01:32:38,478][87426] Updated weights for policy 1, policy_version 50770 (0.0012) -[2023-11-28 01:32:38,860][87426] Updated weights for policy 1, policy_version 50780 (0.0012) -[2023-11-28 01:32:40,088][87424] Updated weights for policy 0, policy_version 50886 (0.0010) -[2023-11-28 01:32:40,469][87424] Updated weights for policy 0, policy_version 50896 (0.0009) -[2023-11-28 01:32:40,844][87424] Updated weights for policy 0, policy_version 50906 (0.0011) -[2023-11-28 01:32:41,113][87426] Updated weights for policy 1, policy_version 50790 (0.0012) -[2023-11-28 01:32:41,485][87426] Updated weights for policy 1, policy_version 50800 (0.0012) -[2023-11-28 01:32:41,862][87426] Updated weights for policy 1, policy_version 50810 (0.0012) -[2023-11-28 01:32:43,242][87424] Updated weights for policy 0, policy_version 50916 (0.0011) -[2023-11-28 01:32:43,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 26042368. Throughput: 0: 2750.9, 1: 2731.4. Samples: 26058092. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:32:43,445][86177] Avg episode reward: [(0, '-545.110'), (1, '-503.160')] -[2023-11-28 01:32:43,630][87424] Updated weights for policy 0, policy_version 50926 (0.0012) -[2023-11-28 01:32:44,011][87424] Updated weights for policy 0, policy_version 50936 (0.0012) -[2023-11-28 01:32:44,209][87426] Updated weights for policy 1, policy_version 50820 (0.0008) -[2023-11-28 01:32:44,591][87426] Updated weights for policy 1, policy_version 50830 (0.0007) -[2023-11-28 01:32:44,971][87426] Updated weights for policy 1, policy_version 50840 (0.0007) -[2023-11-28 01:32:46,132][87424] Updated weights for policy 0, policy_version 50946 (0.0011) -[2023-11-28 01:32:46,522][87424] Updated weights for policy 0, policy_version 50956 (0.0012) -[2023-11-28 01:32:46,905][87424] Updated weights for policy 0, policy_version 50966 (0.0010) -[2023-11-28 01:32:47,261][87426] Updated weights for policy 1, policy_version 50850 (0.0011) -[2023-11-28 01:32:47,281][87424] Updated weights for policy 0, policy_version 50976 (0.0014) -[2023-11-28 01:32:47,631][87426] Updated weights for policy 1, policy_version 50860 (0.0012) -[2023-11-28 01:32:48,009][87426] Updated weights for policy 1, policy_version 50870 (0.0012) -[2023-11-28 01:32:48,379][87426] Updated weights for policy 1, policy_version 50880 (0.0012) -[2023-11-28 01:32:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 26075136. Throughput: 0: 2753.1, 1: 2742.3. Samples: 26083520. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:32:48,445][86177] Avg episode reward: [(0, '-584.800'), (1, '-518.190')] -[2023-11-28 01:32:49,166][87424] Updated weights for policy 0, policy_version 50986 (0.0011) -[2023-11-28 01:32:49,550][87424] Updated weights for policy 0, policy_version 50996 (0.0010) -[2023-11-28 01:32:49,936][87424] Updated weights for policy 0, policy_version 51006 (0.0011) -[2023-11-28 01:32:50,467][87426] Updated weights for policy 1, policy_version 50890 (0.0012) -[2023-11-28 01:32:50,841][87426] Updated weights for policy 1, policy_version 50900 (0.0011) -[2023-11-28 01:32:51,238][87426] Updated weights for policy 1, policy_version 50910 (0.0010) -[2023-11-28 01:32:52,174][87424] Updated weights for policy 0, policy_version 51016 (0.0012) -[2023-11-28 01:32:52,566][87424] Updated weights for policy 0, policy_version 51026 (0.0012) -[2023-11-28 01:32:52,946][87424] Updated weights for policy 0, policy_version 51036 (0.0012) -[2023-11-28 01:32:53,422][87426] Updated weights for policy 1, policy_version 50920 (0.0011) -[2023-11-28 01:32:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 26099712. Throughput: 0: 2761.5, 1: 2724.7. Samples: 26116068. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:32:53,445][86177] Avg episode reward: [(0, '-545.730'), (1, '-526.990')] -[2023-11-28 01:32:53,803][87426] Updated weights for policy 1, policy_version 50930 (0.0009) -[2023-11-28 01:32:54,185][87426] Updated weights for policy 1, policy_version 50940 (0.0009) -[2023-11-28 01:32:54,935][87424] Updated weights for policy 0, policy_version 51046 (0.0011) -[2023-11-28 01:32:55,325][87424] Updated weights for policy 0, policy_version 51056 (0.0010) -[2023-11-28 01:32:55,706][87424] Updated weights for policy 0, policy_version 51066 (0.0007) -[2023-11-28 01:32:55,970][87426] Updated weights for policy 1, policy_version 50950 (0.0007) -[2023-11-28 01:32:56,354][87426] Updated weights for policy 1, policy_version 50960 (0.0009) -[2023-11-28 01:32:56,740][87426] Updated weights for policy 1, policy_version 50970 (0.0010) -[2023-11-28 01:32:57,657][87424] Updated weights for policy 0, policy_version 51076 (0.0010) -[2023-11-28 01:32:58,036][87424] Updated weights for policy 0, policy_version 51086 (0.0011) -[2023-11-28 01:32:58,415][87424] Updated weights for policy 0, policy_version 51096 (0.0012) -[2023-11-28 01:32:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 26124288. Throughput: 0: 2778.8, 1: 2768.9. Samples: 26142808. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-11-28 01:32:58,445][86177] Avg episode reward: [(0, '-545.650'), (1, '-524.180')] -[2023-11-28 01:32:58,607][87426] Updated weights for policy 1, policy_version 50980 (0.0010) -[2023-11-28 01:32:58,990][87426] Updated weights for policy 1, policy_version 50990 (0.0008) -[2023-11-28 01:32:59,365][87426] Updated weights for policy 1, policy_version 51000 (0.0007) -[2023-11-28 01:33:00,903][87424] Updated weights for policy 0, policy_version 51106 (0.0010) -[2023-11-28 01:33:01,288][87424] Updated weights for policy 0, policy_version 51116 (0.0010) -[2023-11-28 01:33:01,418][87426] Updated weights for policy 1, policy_version 51010 (0.0009) -[2023-11-28 01:33:01,677][87424] Updated weights for policy 0, policy_version 51126 (0.0009) -[2023-11-28 01:33:01,805][87426] Updated weights for policy 1, policy_version 51020 (0.0010) -[2023-11-28 01:33:02,065][87424] Updated weights for policy 0, policy_version 51136 (0.0012) -[2023-11-28 01:33:02,184][87426] Updated weights for policy 1, policy_version 51030 (0.0011) -[2023-11-28 01:33:02,555][87426] Updated weights for policy 1, policy_version 51040 (0.0008) -[2023-11-28 01:33:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26157056. Throughput: 0: 2775.6, 1: 2777.1. Samples: 26167336. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-11-28 01:33:03,445][86177] Avg episode reward: [(0, '-549.230'), (1, '-556.630')] -[2023-11-28 01:33:04,045][87424] Updated weights for policy 0, policy_version 51146 (0.0008) -[2023-11-28 01:33:04,440][87424] Updated weights for policy 0, policy_version 51156 (0.0011) -[2023-11-28 01:33:04,829][87424] Updated weights for policy 0, policy_version 51166 (0.0011) -[2023-11-28 01:33:04,925][87426] Updated weights for policy 1, policy_version 51050 (0.0011) -[2023-11-28 01:33:05,301][87426] Updated weights for policy 1, policy_version 51060 (0.0012) -[2023-11-28 01:33:05,695][87426] Updated weights for policy 1, policy_version 51070 (0.0009) -[2023-11-28 01:33:06,833][87424] Updated weights for policy 0, policy_version 51176 (0.0014) -[2023-11-28 01:33:07,212][87424] Updated weights for policy 0, policy_version 51186 (0.0011) -[2023-11-28 01:33:07,596][87424] Updated weights for policy 0, policy_version 51196 (0.0012) -[2023-11-28 01:33:08,037][87426] Updated weights for policy 1, policy_version 51080 (0.0012) -[2023-11-28 01:33:08,420][87426] Updated weights for policy 1, policy_version 51090 (0.0009) -[2023-11-28 01:33:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 26181632. Throughput: 0: 2772.3, 1: 2764.2. Samples: 26199432. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-11-28 01:33:08,446][86177] Avg episode reward: [(0, '-513.570'), (1, '-539.490')] -[2023-11-28 01:33:08,795][87426] Updated weights for policy 1, policy_version 51100 (0.0007) -[2023-11-28 01:33:10,158][87424] Updated weights for policy 0, policy_version 51206 (0.0011) -[2023-11-28 01:33:10,535][87424] Updated weights for policy 0, policy_version 51216 (0.0012) -[2023-11-28 01:33:10,860][87426] Updated weights for policy 1, policy_version 51110 (0.0011) -[2023-11-28 01:33:10,913][87424] Updated weights for policy 0, policy_version 51226 (0.0011) -[2023-11-28 01:33:11,226][87426] Updated weights for policy 1, policy_version 51120 (0.0012) -[2023-11-28 01:33:11,615][87426] Updated weights for policy 1, policy_version 51130 (0.0012) -[2023-11-28 01:33:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 26206208. Throughput: 0: 2752.5, 1: 2723.7. Samples: 26222728. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-11-28 01:33:13,445][86177] Avg episode reward: [(0, '-526.320'), (1, '-529.930')] -[2023-11-28 01:33:13,503][87424] Updated weights for policy 0, policy_version 51236 (0.0012) -[2023-11-28 01:33:13,880][87424] Updated weights for policy 0, policy_version 51246 (0.0009) -[2023-11-28 01:33:14,124][87426] Updated weights for policy 1, policy_version 51140 (0.0009) -[2023-11-28 01:33:14,268][87424] Updated weights for policy 0, policy_version 51256 (0.0008) -[2023-11-28 01:33:14,507][87426] Updated weights for policy 1, policy_version 51150 (0.0008) -[2023-11-28 01:33:14,891][87426] Updated weights for policy 1, policy_version 51160 (0.0008) -[2023-11-28 01:33:16,541][87424] Updated weights for policy 0, policy_version 51266 (0.0009) -[2023-11-28 01:33:16,916][87424] Updated weights for policy 0, policy_version 51276 (0.0012) -[2023-11-28 01:33:17,013][87426] Updated weights for policy 1, policy_version 51170 (0.0009) -[2023-11-28 01:33:17,297][87424] Updated weights for policy 0, policy_version 51286 (0.0011) -[2023-11-28 01:33:17,392][87426] Updated weights for policy 1, policy_version 51180 (0.0011) -[2023-11-28 01:33:17,677][87424] Updated weights for policy 0, policy_version 51296 (0.0011) -[2023-11-28 01:33:17,759][87426] Updated weights for policy 1, policy_version 51190 (0.0011) -[2023-11-28 01:33:18,135][87426] Updated weights for policy 1, policy_version 51200 (0.0012) -[2023-11-28 01:33:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 26238976. Throughput: 0: 2728.0, 1: 2717.7. Samples: 26246684. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-11-28 01:33:18,445][86177] Avg episode reward: [(0, '-532.970'), (1, '-538.300')] -[2023-11-28 01:33:19,867][87424] Updated weights for policy 0, policy_version 51306 (0.0010) -[2023-11-28 01:33:19,975][87426] Updated weights for policy 1, policy_version 51210 (0.0010) -[2023-11-28 01:33:20,260][87424] Updated weights for policy 0, policy_version 51316 (0.0010) -[2023-11-28 01:33:20,347][87426] Updated weights for policy 1, policy_version 51220 (0.0010) -[2023-11-28 01:33:20,632][87424] Updated weights for policy 0, policy_version 51326 (0.0011) -[2023-11-28 01:33:20,728][87426] Updated weights for policy 1, policy_version 51230 (0.0011) -[2023-11-28 01:33:22,738][87424] Updated weights for policy 0, policy_version 51336 (0.0012) -[2023-11-28 01:33:23,121][87424] Updated weights for policy 0, policy_version 51346 (0.0011) -[2023-11-28 01:33:23,187][87426] Updated weights for policy 1, policy_version 51240 (0.0011) -[2023-11-28 01:33:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 26255360. Throughput: 0: 2738.8, 1: 2713.2. Samples: 26279612. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-11-28 01:33:23,445][86177] Avg episode reward: [(0, '-536.470'), (1, '-515.490')] -[2023-11-28 01:33:23,503][87424] Updated weights for policy 0, policy_version 51356 (0.0012) -[2023-11-28 01:33:23,563][87426] Updated weights for policy 1, policy_version 51250 (0.0010) -[2023-11-28 01:33:23,936][87426] Updated weights for policy 1, policy_version 51260 (0.0011) -[2023-11-28 01:33:25,363][87424] Updated weights for policy 0, policy_version 51366 (0.0010) -[2023-11-28 01:33:25,745][87424] Updated weights for policy 0, policy_version 51376 (0.0010) -[2023-11-28 01:33:25,982][87426] Updated weights for policy 1, policy_version 51270 (0.0010) -[2023-11-28 01:33:26,128][87424] Updated weights for policy 0, policy_version 51386 (0.0011) -[2023-11-28 01:33:26,361][87426] Updated weights for policy 1, policy_version 51280 (0.0012) -[2023-11-28 01:33:26,753][87426] Updated weights for policy 1, policy_version 51290 (0.0008) -[2023-11-28 01:33:28,310][87424] Updated weights for policy 0, policy_version 51396 (0.0012) -[2023-11-28 01:33:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26288128. Throughput: 0: 2733.6, 1: 2753.4. Samples: 26305008. Policy #0 lag: (min: 31.0, avg: 37.3, max: 63.0) -[2023-11-28 01:33:28,445][86177] Avg episode reward: [(0, '-531.030'), (1, '-545.250')] -[2023-11-28 01:33:28,688][87424] Updated weights for policy 0, policy_version 51406 (0.0009) -[2023-11-28 01:33:28,744][87426] Updated weights for policy 1, policy_version 51300 (0.0009) -[2023-11-28 01:33:29,070][87424] Updated weights for policy 0, policy_version 51416 (0.0008) -[2023-11-28 01:33:29,114][87426] Updated weights for policy 1, policy_version 51310 (0.0011) -[2023-11-28 01:33:29,496][87426] Updated weights for policy 1, policy_version 51320 (0.0010) -[2023-11-28 01:33:31,028][87424] Updated weights for policy 0, policy_version 51426 (0.0011) -[2023-11-28 01:33:31,408][87424] Updated weights for policy 0, policy_version 51436 (0.0012) -[2023-11-28 01:33:31,586][87426] Updated weights for policy 1, policy_version 51330 (0.0010) -[2023-11-28 01:33:31,787][87424] Updated weights for policy 0, policy_version 51446 (0.0011) -[2023-11-28 01:33:31,973][87426] Updated weights for policy 1, policy_version 51340 (0.0011) -[2023-11-28 01:33:32,168][87424] Updated weights for policy 0, policy_version 51456 (0.0012) -[2023-11-28 01:33:32,347][87426] Updated weights for policy 1, policy_version 51350 (0.0010) -[2023-11-28 01:33:32,729][87426] Updated weights for policy 1, policy_version 51360 (0.0011) -[2023-11-28 01:33:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 26320896. Throughput: 0: 2732.6, 1: 2753.9. Samples: 26330412. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-11-28 01:33:33,445][86177] Avg episode reward: [(0, '-524.970'), (1, '-556.750')] -[2023-11-28 01:33:34,312][87424] Updated weights for policy 0, policy_version 51466 (0.0008) -[2023-11-28 01:33:34,689][87424] Updated weights for policy 0, policy_version 51476 (0.0010) -[2023-11-28 01:33:34,865][87426] Updated weights for policy 1, policy_version 51370 (0.0010) -[2023-11-28 01:33:35,073][87424] Updated weights for policy 0, policy_version 51486 (0.0008) -[2023-11-28 01:33:35,235][87426] Updated weights for policy 1, policy_version 51380 (0.0009) -[2023-11-28 01:33:35,614][87426] Updated weights for policy 1, policy_version 51390 (0.0012) -[2023-11-28 01:33:37,366][87424] Updated weights for policy 0, policy_version 51496 (0.0008) -[2023-11-28 01:33:37,753][87424] Updated weights for policy 0, policy_version 51506 (0.0010) -[2023-11-28 01:33:37,823][87426] Updated weights for policy 1, policy_version 51400 (0.0010) -[2023-11-28 01:33:38,131][87424] Updated weights for policy 0, policy_version 51516 (0.0011) -[2023-11-28 01:33:38,218][87426] Updated weights for policy 1, policy_version 51410 (0.0008) -[2023-11-28 01:33:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26345472. Throughput: 0: 2732.3, 1: 2770.0. Samples: 26363672. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-11-28 01:33:38,445][86177] Avg episode reward: [(0, '-524.750'), (1, '-572.300')] -[2023-11-28 01:33:38,586][87426] Updated weights for policy 1, policy_version 51420 (0.0012) -[2023-11-28 01:33:39,836][87424] Updated weights for policy 0, policy_version 51526 (0.0010) -[2023-11-28 01:33:40,205][87424] Updated weights for policy 0, policy_version 51536 (0.0011) -[2023-11-28 01:33:40,584][87424] Updated weights for policy 0, policy_version 51546 (0.0011) -[2023-11-28 01:33:41,047][87426] Updated weights for policy 1, policy_version 51430 (0.0011) -[2023-11-28 01:33:41,430][87426] Updated weights for policy 1, policy_version 51440 (0.0008) -[2023-11-28 01:33:41,814][87426] Updated weights for policy 1, policy_version 51450 (0.0010) -[2023-11-28 01:33:43,189][87424] Updated weights for policy 0, policy_version 51556 (0.0011) -[2023-11-28 01:33:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 26370048. Throughput: 0: 2707.4, 1: 2710.6. Samples: 26386616. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-11-28 01:33:43,445][86177] Avg episode reward: [(0, '-522.960'), (1, '-562.730')] -[2023-11-28 01:33:43,563][87424] Updated weights for policy 0, policy_version 51566 (0.0012) -[2023-11-28 01:33:43,787][87426] Updated weights for policy 1, policy_version 51460 (0.0010) -[2023-11-28 01:33:43,943][87424] Updated weights for policy 0, policy_version 51576 (0.0011) -[2023-11-28 01:33:44,167][87426] Updated weights for policy 1, policy_version 51470 (0.0011) -[2023-11-28 01:33:44,546][87426] Updated weights for policy 1, policy_version 51480 (0.0012) -[2023-11-28 01:33:46,333][87424] Updated weights for policy 0, policy_version 51586 (0.0008) -[2023-11-28 01:33:46,704][87424] Updated weights for policy 0, policy_version 51596 (0.0012) -[2023-11-28 01:33:47,062][87426] Updated weights for policy 1, policy_version 51490 (0.0012) -[2023-11-28 01:33:47,097][87424] Updated weights for policy 0, policy_version 51606 (0.0011) -[2023-11-28 01:33:47,439][87426] Updated weights for policy 1, policy_version 51500 (0.0008) -[2023-11-28 01:33:47,475][87424] Updated weights for policy 0, policy_version 51616 (0.0012) -[2023-11-28 01:33:47,818][87426] Updated weights for policy 1, policy_version 51510 (0.0008) -[2023-11-28 01:33:48,198][87426] Updated weights for policy 1, policy_version 51520 (0.0007) -[2023-11-28 01:33:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26402816. Throughput: 0: 2710.2, 1: 2701.4. Samples: 26410860. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-11-28 01:33:48,445][86177] Avg episode reward: [(0, '-530.510'), (1, '-524.510')] -[2023-11-28 01:33:49,670][87424] Updated weights for policy 0, policy_version 51626 (0.0011) -[2023-11-28 01:33:50,054][87424] Updated weights for policy 0, policy_version 51636 (0.0012) -[2023-11-28 01:33:50,443][87424] Updated weights for policy 0, policy_version 51646 (0.0012) -[2023-11-28 01:33:50,735][87426] Updated weights for policy 1, policy_version 51530 (0.0010) -[2023-11-28 01:33:51,110][87426] Updated weights for policy 1, policy_version 51540 (0.0012) -[2023-11-28 01:33:51,489][87426] Updated weights for policy 1, policy_version 51550 (0.0011) -[2023-11-28 01:33:52,585][87424] Updated weights for policy 0, policy_version 51656 (0.0009) -[2023-11-28 01:33:52,956][87424] Updated weights for policy 0, policy_version 51666 (0.0008) -[2023-11-28 01:33:53,346][87424] Updated weights for policy 0, policy_version 51676 (0.0009) -[2023-11-28 01:33:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 26419200. Throughput: 0: 2702.5, 1: 2706.7. Samples: 26442844. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-11-28 01:33:53,445][86177] Avg episode reward: [(0, '-535.330'), (1, '-531.390')] -[2023-11-28 01:33:53,986][87426] Updated weights for policy 1, policy_version 51560 (0.0011) -[2023-11-28 01:33:54,360][87426] Updated weights for policy 1, policy_version 51570 (0.0009) -[2023-11-28 01:33:54,740][87426] Updated weights for policy 1, policy_version 51580 (0.0009) -[2023-11-28 01:33:55,565][87424] Updated weights for policy 0, policy_version 51686 (0.0012) -[2023-11-28 01:33:55,951][87424] Updated weights for policy 0, policy_version 51696 (0.0012) -[2023-11-28 01:33:56,327][87424] Updated weights for policy 0, policy_version 51706 (0.0011) -[2023-11-28 01:33:56,468][87426] Updated weights for policy 1, policy_version 51590 (0.0007) -[2023-11-28 01:33:56,849][87426] Updated weights for policy 1, policy_version 51600 (0.0007) -[2023-11-28 01:33:57,237][87426] Updated weights for policy 1, policy_version 51610 (0.0008) -[2023-11-28 01:33:58,350][87424] Updated weights for policy 0, policy_version 51716 (0.0010) -[2023-11-28 01:33:58,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26451968. Throughput: 0: 2705.0, 1: 2723.0. Samples: 26466988. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-11-28 01:33:58,446][86177] Avg episode reward: [(0, '-533.500'), (1, '-520.930')] -[2023-11-28 01:33:58,741][87424] Updated weights for policy 0, policy_version 51726 (0.0008) -[2023-11-28 01:33:58,780][87426] Updated weights for policy 1, policy_version 51620 (0.0010) -[2023-11-28 01:33:59,116][87424] Updated weights for policy 0, policy_version 51736 (0.0009) -[2023-11-28 01:33:59,152][87426] Updated weights for policy 1, policy_version 51630 (0.0011) -[2023-11-28 01:33:59,527][87426] Updated weights for policy 1, policy_version 51640 (0.0012) -[2023-11-28 01:34:01,385][87424] Updated weights for policy 0, policy_version 51746 (0.0008) -[2023-11-28 01:34:01,765][87424] Updated weights for policy 0, policy_version 51756 (0.0008) -[2023-11-28 01:34:01,908][87426] Updated weights for policy 1, policy_version 51650 (0.0011) -[2023-11-28 01:34:02,142][87424] Updated weights for policy 0, policy_version 51766 (0.0011) -[2023-11-28 01:34:02,285][87426] Updated weights for policy 1, policy_version 51660 (0.0011) -[2023-11-28 01:34:02,522][87424] Updated weights for policy 0, policy_version 51776 (0.0010) -[2023-11-28 01:34:02,669][87426] Updated weights for policy 1, policy_version 51670 (0.0011) -[2023-11-28 01:34:03,041][87426] Updated weights for policy 1, policy_version 51680 (0.0012) -[2023-11-28 01:34:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 26484736. Throughput: 0: 2733.6, 1: 2715.0. Samples: 26491872. Policy #0 lag: (min: 31.0, avg: 42.2, max: 63.0) -[2023-11-28 01:34:03,445][86177] Avg episode reward: [(0, '-533.970'), (1, '-553.160')] -[2023-11-28 01:34:04,373][87424] Updated weights for policy 0, policy_version 51786 (0.0011) -[2023-11-28 01:34:04,756][87424] Updated weights for policy 0, policy_version 51796 (0.0012) -[2023-11-28 01:34:05,130][87426] Updated weights for policy 1, policy_version 51690 (0.0011) -[2023-11-28 01:34:05,137][87424] Updated weights for policy 0, policy_version 51806 (0.0011) -[2023-11-28 01:34:05,508][87426] Updated weights for policy 1, policy_version 51700 (0.0007) -[2023-11-28 01:34:05,889][87426] Updated weights for policy 1, policy_version 51710 (0.0008) -[2023-11-28 01:34:07,133][87424] Updated weights for policy 0, policy_version 51816 (0.0012) -[2023-11-28 01:34:07,518][87424] Updated weights for policy 0, policy_version 51826 (0.0012) -[2023-11-28 01:34:07,836][87426] Updated weights for policy 1, policy_version 51720 (0.0011) -[2023-11-28 01:34:07,910][87424] Updated weights for policy 0, policy_version 51836 (0.0012) -[2023-11-28 01:34:08,212][87426] Updated weights for policy 1, policy_version 51730 (0.0008) -[2023-11-28 01:34:08,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26509312. Throughput: 0: 2749.2, 1: 2719.4. Samples: 26525700. Policy #0 lag: (min: 5.0, avg: 16.6, max: 37.0) -[2023-11-28 01:34:08,445][86177] Avg episode reward: [(0, '-528.370'), (1, '-549.200')] -[2023-11-28 01:34:08,584][87426] Updated weights for policy 1, policy_version 51740 (0.0010) -[2023-11-28 01:34:09,929][87424] Updated weights for policy 0, policy_version 51846 (0.0012) -[2023-11-28 01:34:10,316][87424] Updated weights for policy 0, policy_version 51856 (0.0012) -[2023-11-28 01:34:10,700][87424] Updated weights for policy 0, policy_version 51866 (0.0012) -[2023-11-28 01:34:11,148][87426] Updated weights for policy 1, policy_version 51750 (0.0010) -[2023-11-28 01:34:11,529][87426] Updated weights for policy 1, policy_version 51760 (0.0008) -[2023-11-28 01:34:11,910][87426] Updated weights for policy 1, policy_version 51770 (0.0018) -[2023-11-28 01:34:12,775][87424] Updated weights for policy 0, policy_version 51876 (0.0011) -[2023-11-28 01:34:13,155][87424] Updated weights for policy 0, policy_version 51886 (0.0012) -[2023-11-28 01:34:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26533888. Throughput: 0: 2750.9, 1: 2691.5. Samples: 26549916. Policy #0 lag: (min: 5.0, avg: 16.6, max: 37.0) -[2023-11-28 01:34:13,445][86177] Avg episode reward: [(0, '-523.000'), (1, '-544.970')] -[2023-11-28 01:34:13,530][87424] Updated weights for policy 0, policy_version 51896 (0.0012) -[2023-11-28 01:34:14,205][87426] Updated weights for policy 1, policy_version 51780 (0.0010) -[2023-11-28 01:34:14,593][87426] Updated weights for policy 1, policy_version 51790 (0.0009) -[2023-11-28 01:34:14,975][87426] Updated weights for policy 1, policy_version 51800 (0.0008) -[2023-11-28 01:34:15,845][87424] Updated weights for policy 0, policy_version 51906 (0.0012) -[2023-11-28 01:34:16,223][87424] Updated weights for policy 0, policy_version 51916 (0.0008) -[2023-11-28 01:34:16,618][87424] Updated weights for policy 0, policy_version 51926 (0.0008) -[2023-11-28 01:34:16,991][87424] Updated weights for policy 0, policy_version 51936 (0.0007) -[2023-11-28 01:34:17,358][87426] Updated weights for policy 1, policy_version 51810 (0.0010) -[2023-11-28 01:34:17,743][87426] Updated weights for policy 1, policy_version 51820 (0.0012) -[2023-11-28 01:34:18,123][87426] Updated weights for policy 1, policy_version 51830 (0.0012) -[2023-11-28 01:34:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 26558464. Throughput: 0: 2740.4, 1: 2697.2. Samples: 26575108. Policy #0 lag: (min: 5.0, avg: 16.6, max: 37.0) -[2023-11-28 01:34:18,445][86177] Avg episode reward: [(0, '-519.180'), (1, '-533.790')] -[2023-11-28 01:34:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000051936_13295616.pth... -[2023-11-28 01:34:18,487][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000051840_13271040.pth... -[2023-11-28 01:34:18,489][87426] Updated weights for policy 1, policy_version 51840 (0.0013) -[2023-11-28 01:34:18,502][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000049376_12640256.pth -[2023-11-28 01:34:18,534][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000049280_12615680.pth -[2023-11-28 01:34:19,386][87424] Updated weights for policy 0, policy_version 51946 (0.0012) -[2023-11-28 01:34:19,776][87424] Updated weights for policy 0, policy_version 51956 (0.0012) -[2023-11-28 01:34:20,146][87424] Updated weights for policy 0, policy_version 51966 (0.0012) -[2023-11-28 01:34:20,264][87426] Updated weights for policy 1, policy_version 51850 (0.0011) -[2023-11-28 01:34:20,651][87426] Updated weights for policy 1, policy_version 51860 (0.0008) -[2023-11-28 01:34:21,030][87426] Updated weights for policy 1, policy_version 51870 (0.0008) -[2023-11-28 01:34:22,592][87424] Updated weights for policy 0, policy_version 51976 (0.0012) -[2023-11-28 01:34:22,981][87424] Updated weights for policy 0, policy_version 51986 (0.0010) -[2023-11-28 01:34:23,351][87424] Updated weights for policy 0, policy_version 51996 (0.0008) -[2023-11-28 01:34:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 26583040. Throughput: 0: 2711.9, 1: 2690.3. Samples: 26606772. Policy #0 lag: (min: 5.0, avg: 16.6, max: 37.0) -[2023-11-28 01:34:23,445][86177] Avg episode reward: [(0, '-526.290'), (1, '-506.690')] -[2023-11-28 01:34:23,483][87426] Updated weights for policy 1, policy_version 51880 (0.0007) -[2023-11-28 01:34:23,868][87426] Updated weights for policy 1, policy_version 51890 (0.0008) -[2023-11-28 01:34:24,240][87426] Updated weights for policy 1, policy_version 51900 (0.0008) -[2023-11-28 01:34:25,181][87424] Updated weights for policy 0, policy_version 52006 (0.0010) -[2023-11-28 01:34:25,575][87424] Updated weights for policy 0, policy_version 52016 (0.0009) -[2023-11-28 01:34:25,958][87424] Updated weights for policy 0, policy_version 52026 (0.0007) -[2023-11-28 01:34:26,782][87426] Updated weights for policy 1, policy_version 51910 (0.0007) -[2023-11-28 01:34:27,164][87426] Updated weights for policy 1, policy_version 51920 (0.0007) -[2023-11-28 01:34:27,553][87426] Updated weights for policy 1, policy_version 51930 (0.0007) -[2023-11-28 01:34:28,256][87424] Updated weights for policy 0, policy_version 52036 (0.0007) -[2023-11-28 01:34:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26615808. Throughput: 0: 2728.7, 1: 2693.6. Samples: 26630620. Policy #0 lag: (min: 5.0, avg: 16.6, max: 37.0) -[2023-11-28 01:34:28,445][86177] Avg episode reward: [(0, '-531.380'), (1, '-509.870')] -[2023-11-28 01:34:28,644][87424] Updated weights for policy 0, policy_version 52046 (0.0008) -[2023-11-28 01:34:29,046][87424] Updated weights for policy 0, policy_version 52056 (0.0009) -[2023-11-28 01:34:29,522][87426] Updated weights for policy 1, policy_version 51940 (0.0009) -[2023-11-28 01:34:29,912][87426] Updated weights for policy 1, policy_version 51950 (0.0011) -[2023-11-28 01:34:30,281][87426] Updated weights for policy 1, policy_version 51960 (0.0008) -[2023-11-28 01:34:30,737][87424] Updated weights for policy 0, policy_version 52066 (0.0008) -[2023-11-28 01:34:31,124][87424] Updated weights for policy 0, policy_version 52076 (0.0007) -[2023-11-28 01:34:31,511][87424] Updated weights for policy 0, policy_version 52086 (0.0009) -[2023-11-28 01:34:31,890][87424] Updated weights for policy 0, policy_version 52096 (0.0012) -[2023-11-28 01:34:32,334][87426] Updated weights for policy 1, policy_version 51970 (0.0010) -[2023-11-28 01:34:32,713][87426] Updated weights for policy 1, policy_version 51980 (0.0012) -[2023-11-28 01:34:33,095][87426] Updated weights for policy 1, policy_version 51990 (0.0012) -[2023-11-28 01:34:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 26640384. Throughput: 0: 2746.8, 1: 2692.6. Samples: 26655632. Policy #0 lag: (min: 5.0, avg: 16.6, max: 37.0) -[2023-11-28 01:34:33,445][86177] Avg episode reward: [(0, '-532.980'), (1, '-509.990')] -[2023-11-28 01:34:33,481][87426] Updated weights for policy 1, policy_version 52000 (0.0008) -[2023-11-28 01:34:33,966][87424] Updated weights for policy 0, policy_version 52106 (0.0012) -[2023-11-28 01:34:34,345][87424] Updated weights for policy 0, policy_version 52116 (0.0012) -[2023-11-28 01:34:34,730][87424] Updated weights for policy 0, policy_version 52126 (0.0011) -[2023-11-28 01:34:35,331][87426] Updated weights for policy 1, policy_version 52010 (0.0012) -[2023-11-28 01:34:35,704][87426] Updated weights for policy 1, policy_version 52020 (0.0012) -[2023-11-28 01:34:36,083][87426] Updated weights for policy 1, policy_version 52030 (0.0008) -[2023-11-28 01:34:36,711][87424] Updated weights for policy 0, policy_version 52136 (0.0010) -[2023-11-28 01:34:37,094][87424] Updated weights for policy 0, policy_version 52146 (0.0011) -[2023-11-28 01:34:37,476][87424] Updated weights for policy 0, policy_version 52156 (0.0010) -[2023-11-28 01:34:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26673152. Throughput: 0: 2757.2, 1: 2712.4. Samples: 26688976. Policy #0 lag: (min: 5.0, avg: 16.6, max: 37.0) -[2023-11-28 01:34:38,445][86177] Avg episode reward: [(0, '-524.640'), (1, '-512.760')] -[2023-11-28 01:34:38,515][87426] Updated weights for policy 1, policy_version 52040 (0.0011) -[2023-11-28 01:34:38,886][87426] Updated weights for policy 1, policy_version 52050 (0.0012) -[2023-11-28 01:34:39,272][87426] Updated weights for policy 1, policy_version 52060 (0.0012) -[2023-11-28 01:34:39,644][87424] Updated weights for policy 0, policy_version 52166 (0.0010) -[2023-11-28 01:34:40,027][87424] Updated weights for policy 0, policy_version 52176 (0.0010) -[2023-11-28 01:34:40,416][87424] Updated weights for policy 0, policy_version 52186 (0.0008) -[2023-11-28 01:34:41,813][87426] Updated weights for policy 1, policy_version 52070 (0.0011) -[2023-11-28 01:34:42,201][87426] Updated weights for policy 1, policy_version 52080 (0.0008) -[2023-11-28 01:34:42,580][87426] Updated weights for policy 1, policy_version 52090 (0.0012) -[2023-11-28 01:34:42,933][87424] Updated weights for policy 0, policy_version 52196 (0.0012) -[2023-11-28 01:34:43,319][87424] Updated weights for policy 0, policy_version 52206 (0.0012) -[2023-11-28 01:34:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26697728. Throughput: 0: 2760.5, 1: 2703.0. Samples: 26712840. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 01:34:43,445][86177] Avg episode reward: [(0, '-527.560'), (1, '-506.370')] -[2023-11-28 01:34:43,701][87424] Updated weights for policy 0, policy_version 52216 (0.0011) -[2023-11-28 01:34:44,350][87426] Updated weights for policy 1, policy_version 52100 (0.0010) -[2023-11-28 01:34:44,737][87426] Updated weights for policy 1, policy_version 52110 (0.0012) -[2023-11-28 01:34:45,102][87426] Updated weights for policy 1, policy_version 52120 (0.0012) -[2023-11-28 01:34:46,343][87424] Updated weights for policy 0, policy_version 52226 (0.0011) -[2023-11-28 01:34:46,730][87424] Updated weights for policy 0, policy_version 52236 (0.0012) -[2023-11-28 01:34:46,910][87426] Updated weights for policy 1, policy_version 52130 (0.0012) -[2023-11-28 01:34:47,113][87424] Updated weights for policy 0, policy_version 52246 (0.0012) -[2023-11-28 01:34:47,293][87426] Updated weights for policy 1, policy_version 52140 (0.0012) -[2023-11-28 01:34:47,487][87424] Updated weights for policy 0, policy_version 52256 (0.0010) -[2023-11-28 01:34:47,663][87426] Updated weights for policy 1, policy_version 52150 (0.0011) -[2023-11-28 01:34:48,047][87426] Updated weights for policy 1, policy_version 52160 (0.0007) -[2023-11-28 01:34:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 26730496. Throughput: 0: 2731.7, 1: 2714.9. Samples: 26736972. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 01:34:48,446][86177] Avg episode reward: [(0, '-519.870'), (1, '-514.050')] -[2023-11-28 01:34:49,448][87424] Updated weights for policy 0, policy_version 52266 (0.0011) -[2023-11-28 01:34:49,836][87424] Updated weights for policy 0, policy_version 52276 (0.0012) -[2023-11-28 01:34:50,215][87424] Updated weights for policy 0, policy_version 52286 (0.0011) -[2023-11-28 01:34:50,469][87426] Updated weights for policy 1, policy_version 52170 (0.0011) -[2023-11-28 01:34:50,843][87426] Updated weights for policy 1, policy_version 52180 (0.0012) -[2023-11-28 01:34:51,226][87426] Updated weights for policy 1, policy_version 52190 (0.0012) -[2023-11-28 01:34:52,477][87424] Updated weights for policy 0, policy_version 52296 (0.0011) -[2023-11-28 01:34:52,858][87424] Updated weights for policy 0, policy_version 52306 (0.0010) -[2023-11-28 01:34:53,255][87424] Updated weights for policy 0, policy_version 52316 (0.0012) -[2023-11-28 01:34:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 26755072. Throughput: 0: 2707.4, 1: 2695.6. Samples: 26768836. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 01:34:53,445][86177] Avg episode reward: [(0, '-516.430'), (1, '-513.780')] -[2023-11-28 01:34:53,579][87426] Updated weights for policy 1, policy_version 52200 (0.0010) -[2023-11-28 01:34:53,955][87426] Updated weights for policy 1, policy_version 52210 (0.0010) -[2023-11-28 01:34:54,339][87426] Updated weights for policy 1, policy_version 52220 (0.0012) -[2023-11-28 01:34:55,811][87424] Updated weights for policy 0, policy_version 52326 (0.0011) -[2023-11-28 01:34:56,199][87424] Updated weights for policy 0, policy_version 52336 (0.0012) -[2023-11-28 01:34:56,591][87424] Updated weights for policy 0, policy_version 52346 (0.0011) -[2023-11-28 01:34:56,631][87426] Updated weights for policy 1, policy_version 52230 (0.0012) -[2023-11-28 01:34:57,007][87426] Updated weights for policy 1, policy_version 52240 (0.0012) -[2023-11-28 01:34:57,385][87426] Updated weights for policy 1, policy_version 52250 (0.0012) -[2023-11-28 01:34:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 26779648. Throughput: 0: 2689.1, 1: 2709.2. Samples: 26792836. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 01:34:58,445][86177] Avg episode reward: [(0, '-522.740'), (1, '-516.810')] -[2023-11-28 01:34:58,495][87424] Updated weights for policy 0, policy_version 52356 (0.0008) -[2023-11-28 01:34:58,876][87424] Updated weights for policy 0, policy_version 52366 (0.0008) -[2023-11-28 01:34:59,257][87424] Updated weights for policy 0, policy_version 52376 (0.0008) -[2023-11-28 01:34:59,603][87426] Updated weights for policy 1, policy_version 52260 (0.0011) -[2023-11-28 01:34:59,981][87426] Updated weights for policy 1, policy_version 52270 (0.0010) -[2023-11-28 01:35:00,360][87426] Updated weights for policy 1, policy_version 52280 (0.0011) -[2023-11-28 01:35:01,637][87424] Updated weights for policy 0, policy_version 52386 (0.0009) -[2023-11-28 01:35:02,007][87424] Updated weights for policy 0, policy_version 52396 (0.0009) -[2023-11-28 01:35:02,387][87424] Updated weights for policy 0, policy_version 52406 (0.0008) -[2023-11-28 01:35:02,511][87426] Updated weights for policy 1, policy_version 52290 (0.0009) -[2023-11-28 01:35:02,772][87424] Updated weights for policy 0, policy_version 52416 (0.0008) -[2023-11-28 01:35:02,885][87426] Updated weights for policy 1, policy_version 52300 (0.0011) -[2023-11-28 01:35:03,269][87426] Updated weights for policy 1, policy_version 52310 (0.0011) -[2023-11-28 01:35:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 26804224. Throughput: 0: 2706.2, 1: 2705.4. Samples: 26818632. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 01:35:03,445][86177] Avg episode reward: [(0, '-520.540'), (1, '-530.470')] -[2023-11-28 01:35:03,641][87426] Updated weights for policy 1, policy_version 52320 (0.0012) -[2023-11-28 01:35:05,094][87424] Updated weights for policy 0, policy_version 52426 (0.0011) -[2023-11-28 01:35:05,470][87424] Updated weights for policy 0, policy_version 52436 (0.0011) -[2023-11-28 01:35:05,857][87424] Updated weights for policy 0, policy_version 52446 (0.0012) -[2023-11-28 01:35:05,912][87426] Updated weights for policy 1, policy_version 52330 (0.0011) -[2023-11-28 01:35:06,291][87426] Updated weights for policy 1, policy_version 52340 (0.0012) -[2023-11-28 01:35:06,670][87426] Updated weights for policy 1, policy_version 52350 (0.0011) -[2023-11-28 01:35:07,532][87424] Updated weights for policy 0, policy_version 52456 (0.0011) -[2023-11-28 01:35:07,920][87424] Updated weights for policy 0, policy_version 52466 (0.0009) -[2023-11-28 01:35:08,299][87424] Updated weights for policy 0, policy_version 52476 (0.0009) -[2023-11-28 01:35:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 26828800. Throughput: 0: 2737.1, 1: 2716.3. Samples: 26852172. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 01:35:08,445][86177] Avg episode reward: [(0, '-533.420'), (1, '-523.960')] -[2023-11-28 01:35:09,128][87426] Updated weights for policy 1, policy_version 52360 (0.0010) -[2023-11-28 01:35:09,510][87426] Updated weights for policy 1, policy_version 52370 (0.0008) -[2023-11-28 01:35:09,896][87426] Updated weights for policy 1, policy_version 52380 (0.0012) -[2023-11-28 01:35:09,980][87424] Updated weights for policy 0, policy_version 52486 (0.0013) -[2023-11-28 01:35:10,375][87424] Updated weights for policy 0, policy_version 52496 (0.0010) -[2023-11-28 01:35:10,757][87424] Updated weights for policy 0, policy_version 52506 (0.0012) -[2023-11-28 01:35:12,126][87426] Updated weights for policy 1, policy_version 52390 (0.0011) -[2023-11-28 01:35:12,501][87426] Updated weights for policy 1, policy_version 52400 (0.0011) -[2023-11-28 01:35:12,881][87426] Updated weights for policy 1, policy_version 52410 (0.0011) -[2023-11-28 01:35:13,266][87424] Updated weights for policy 0, policy_version 52516 (0.0012) -[2023-11-28 01:35:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 26861568. Throughput: 0: 2731.8, 1: 2714.9. Samples: 26875720. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 01:35:13,445][86177] Avg episode reward: [(0, '-532.870'), (1, '-540.570')] -[2023-11-28 01:35:13,637][87424] Updated weights for policy 0, policy_version 52526 (0.0011) -[2023-11-28 01:35:14,019][87424] Updated weights for policy 0, policy_version 52536 (0.0008) -[2023-11-28 01:35:14,547][87426] Updated weights for policy 1, policy_version 52420 (0.0012) -[2023-11-28 01:35:14,929][87426] Updated weights for policy 1, policy_version 52430 (0.0011) -[2023-11-28 01:35:15,303][87426] Updated weights for policy 1, policy_version 52440 (0.0010) -[2023-11-28 01:35:16,193][87424] Updated weights for policy 0, policy_version 52546 (0.0009) -[2023-11-28 01:35:16,564][87424] Updated weights for policy 0, policy_version 52556 (0.0012) -[2023-11-28 01:35:16,945][87424] Updated weights for policy 0, policy_version 52566 (0.0012) -[2023-11-28 01:35:17,320][87424] Updated weights for policy 0, policy_version 52576 (0.0012) -[2023-11-28 01:35:17,742][87426] Updated weights for policy 1, policy_version 52450 (0.0010) -[2023-11-28 01:35:18,127][87426] Updated weights for policy 1, policy_version 52460 (0.0012) -[2023-11-28 01:35:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 26886144. Throughput: 0: 2708.6, 1: 2711.9. Samples: 26899556. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:35:18,445][86177] Avg episode reward: [(0, '-535.650'), (1, '-550.920')] -[2023-11-28 01:35:18,505][87426] Updated weights for policy 1, policy_version 52470 (0.0012) -[2023-11-28 01:35:18,912][87426] Updated weights for policy 1, policy_version 52480 (0.0012) -[2023-11-28 01:35:19,082][87424] Updated weights for policy 0, policy_version 52586 (0.0010) -[2023-11-28 01:35:19,474][87424] Updated weights for policy 0, policy_version 52596 (0.0011) -[2023-11-28 01:35:19,844][87424] Updated weights for policy 0, policy_version 52606 (0.0009) -[2023-11-28 01:35:20,764][87426] Updated weights for policy 1, policy_version 52490 (0.0011) -[2023-11-28 01:35:21,148][87426] Updated weights for policy 1, policy_version 52500 (0.0011) -[2023-11-28 01:35:21,527][87426] Updated weights for policy 1, policy_version 52510 (0.0011) -[2023-11-28 01:35:22,147][87424] Updated weights for policy 0, policy_version 52616 (0.0009) -[2023-11-28 01:35:22,533][87424] Updated weights for policy 0, policy_version 52626 (0.0009) -[2023-11-28 01:35:22,913][87424] Updated weights for policy 0, policy_version 52636 (0.0011) -[2023-11-28 01:35:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 26918912. Throughput: 0: 2706.2, 1: 2688.9. Samples: 26931756. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:35:23,445][86177] Avg episode reward: [(0, '-537.630'), (1, '-551.070')] -[2023-11-28 01:35:24,208][87426] Updated weights for policy 1, policy_version 52520 (0.0012) -[2023-11-28 01:35:24,581][87426] Updated weights for policy 1, policy_version 52530 (0.0012) -[2023-11-28 01:35:24,966][87426] Updated weights for policy 1, policy_version 52540 (0.0011) -[2023-11-28 01:35:25,039][87424] Updated weights for policy 0, policy_version 52646 (0.0010) -[2023-11-28 01:35:25,419][87424] Updated weights for policy 0, policy_version 52656 (0.0012) -[2023-11-28 01:35:25,805][87424] Updated weights for policy 0, policy_version 52666 (0.0012) -[2023-11-28 01:35:26,716][87426] Updated weights for policy 1, policy_version 52550 (0.0009) -[2023-11-28 01:35:27,108][87426] Updated weights for policy 1, policy_version 52560 (0.0008) -[2023-11-28 01:35:27,492][87426] Updated weights for policy 1, policy_version 52570 (0.0007) -[2023-11-28 01:35:28,319][87424] Updated weights for policy 0, policy_version 52676 (0.0010) -[2023-11-28 01:35:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 26943488. Throughput: 0: 2714.8, 1: 2694.7. Samples: 26956268. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:35:28,445][86177] Avg episode reward: [(0, '-527.320'), (1, '-576.880')] -[2023-11-28 01:35:28,709][87424] Updated weights for policy 0, policy_version 52686 (0.0008) -[2023-11-28 01:35:29,091][87424] Updated weights for policy 0, policy_version 52696 (0.0010) -[2023-11-28 01:35:29,813][87426] Updated weights for policy 1, policy_version 52580 (0.0008) -[2023-11-28 01:35:30,187][87426] Updated weights for policy 1, policy_version 52590 (0.0011) -[2023-11-28 01:35:30,565][87426] Updated weights for policy 1, policy_version 52600 (0.0011) -[2023-11-28 01:35:30,862][87424] Updated weights for policy 0, policy_version 52706 (0.0011) -[2023-11-28 01:35:31,245][87424] Updated weights for policy 0, policy_version 52716 (0.0012) -[2023-11-28 01:35:31,632][87424] Updated weights for policy 0, policy_version 52726 (0.0012) -[2023-11-28 01:35:32,015][87424] Updated weights for policy 0, policy_version 52736 (0.0012) -[2023-11-28 01:35:32,682][87426] Updated weights for policy 1, policy_version 52610 (0.0010) -[2023-11-28 01:35:33,064][87426] Updated weights for policy 1, policy_version 52620 (0.0008) -[2023-11-28 01:35:33,439][87426] Updated weights for policy 1, policy_version 52630 (0.0007) -[2023-11-28 01:35:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 26968064. Throughput: 0: 2721.3, 1: 2675.6. Samples: 26979832. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:35:33,445][86177] Avg episode reward: [(0, '-524.760'), (1, '-557.590')] -[2023-11-28 01:35:33,820][87426] Updated weights for policy 1, policy_version 52640 (0.0009) -[2023-11-28 01:35:34,440][87424] Updated weights for policy 0, policy_version 52746 (0.0012) -[2023-11-28 01:35:34,818][87424] Updated weights for policy 0, policy_version 52756 (0.0012) -[2023-11-28 01:35:35,198][87424] Updated weights for policy 0, policy_version 52766 (0.0011) -[2023-11-28 01:35:35,781][87426] Updated weights for policy 1, policy_version 52650 (0.0010) -[2023-11-28 01:35:36,160][87426] Updated weights for policy 1, policy_version 52660 (0.0007) -[2023-11-28 01:35:36,541][87426] Updated weights for policy 1, policy_version 52670 (0.0007) -[2023-11-28 01:35:37,315][87424] Updated weights for policy 0, policy_version 52776 (0.0012) -[2023-11-28 01:35:37,690][87424] Updated weights for policy 0, policy_version 52786 (0.0011) -[2023-11-28 01:35:38,073][87424] Updated weights for policy 0, policy_version 52796 (0.0011) -[2023-11-28 01:35:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 27000832. Throughput: 0: 2735.3, 1: 2694.7. Samples: 27013184. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:35:38,445][86177] Avg episode reward: [(0, '-511.490'), (1, '-550.070')] -[2023-11-28 01:35:38,750][87426] Updated weights for policy 1, policy_version 52680 (0.0011) -[2023-11-28 01:35:39,133][87426] Updated weights for policy 1, policy_version 52690 (0.0011) -[2023-11-28 01:35:39,507][87426] Updated weights for policy 1, policy_version 52700 (0.0011) -[2023-11-28 01:35:40,552][87424] Updated weights for policy 0, policy_version 52806 (0.0011) -[2023-11-28 01:35:40,926][87424] Updated weights for policy 0, policy_version 52816 (0.0012) -[2023-11-28 01:35:41,306][87424] Updated weights for policy 0, policy_version 52826 (0.0011) -[2023-11-28 01:35:41,860][87426] Updated weights for policy 1, policy_version 52710 (0.0011) -[2023-11-28 01:35:42,238][87426] Updated weights for policy 1, policy_version 52720 (0.0012) -[2023-11-28 01:35:42,622][87426] Updated weights for policy 1, policy_version 52730 (0.0010) -[2023-11-28 01:35:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 27025408. Throughput: 0: 2752.6, 1: 2688.8. Samples: 27037700. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:35:43,445][86177] Avg episode reward: [(0, '-510.120'), (1, '-527.050')] -[2023-11-28 01:35:43,450][87424] Updated weights for policy 0, policy_version 52836 (0.0012) -[2023-11-28 01:35:43,842][87424] Updated weights for policy 0, policy_version 52846 (0.0012) -[2023-11-28 01:35:44,225][87424] Updated weights for policy 0, policy_version 52856 (0.0012) -[2023-11-28 01:35:45,216][87426] Updated weights for policy 1, policy_version 52740 (0.0009) -[2023-11-28 01:35:45,607][87426] Updated weights for policy 1, policy_version 52750 (0.0012) -[2023-11-28 01:35:45,983][87426] Updated weights for policy 1, policy_version 52760 (0.0012) -[2023-11-28 01:35:46,182][87424] Updated weights for policy 0, policy_version 52866 (0.0012) -[2023-11-28 01:35:46,562][87424] Updated weights for policy 0, policy_version 52876 (0.0011) -[2023-11-28 01:35:46,942][87424] Updated weights for policy 0, policy_version 52886 (0.0009) -[2023-11-28 01:35:47,325][87424] Updated weights for policy 0, policy_version 52896 (0.0008) -[2023-11-28 01:35:48,277][87426] Updated weights for policy 1, policy_version 52770 (0.0010) -[2023-11-28 01:35:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 27049984. Throughput: 0: 2724.1, 1: 2708.2. Samples: 27063084. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 01:35:48,445][86177] Avg episode reward: [(0, '-534.380'), (1, '-510.140')] -[2023-11-28 01:35:48,657][87426] Updated weights for policy 1, policy_version 52780 (0.0007) -[2023-11-28 01:35:49,040][87426] Updated weights for policy 1, policy_version 52790 (0.0010) -[2023-11-28 01:35:49,411][87426] Updated weights for policy 1, policy_version 52800 (0.0011) -[2023-11-28 01:35:49,873][87424] Updated weights for policy 0, policy_version 52906 (0.0011) -[2023-11-28 01:35:50,262][87424] Updated weights for policy 0, policy_version 52916 (0.0012) -[2023-11-28 01:35:50,645][87424] Updated weights for policy 0, policy_version 52926 (0.0008) -[2023-11-28 01:35:51,747][87426] Updated weights for policy 1, policy_version 52810 (0.0012) -[2023-11-28 01:35:52,124][87426] Updated weights for policy 1, policy_version 52820 (0.0011) -[2023-11-28 01:35:52,510][87426] Updated weights for policy 1, policy_version 52830 (0.0010) -[2023-11-28 01:35:52,703][87424] Updated weights for policy 0, policy_version 52936 (0.0010) -[2023-11-28 01:35:53,086][87424] Updated weights for policy 0, policy_version 52946 (0.0011) -[2023-11-28 01:35:53,445][86177] Fps is (10 sec: 4914.9, 60 sec: 5324.7, 300 sec: 5442.8). Total num frames: 27074560. Throughput: 0: 2704.1, 1: 2687.7. Samples: 27094804. Policy #0 lag: (min: 1.0, avg: 30.4, max: 62.0) -[2023-11-28 01:35:53,446][86177] Avg episode reward: [(0, '-534.130'), (1, '-513.350')] -[2023-11-28 01:35:53,469][87424] Updated weights for policy 0, policy_version 52956 (0.0011) -[2023-11-28 01:35:54,896][87426] Updated weights for policy 1, policy_version 52840 (0.0007) -[2023-11-28 01:35:55,274][87426] Updated weights for policy 1, policy_version 52850 (0.0008) -[2023-11-28 01:35:55,660][87426] Updated weights for policy 1, policy_version 52860 (0.0007) -[2023-11-28 01:35:56,009][87424] Updated weights for policy 0, policy_version 52966 (0.0008) -[2023-11-28 01:35:56,395][87424] Updated weights for policy 0, policy_version 52976 (0.0007) -[2023-11-28 01:35:56,776][87424] Updated weights for policy 0, policy_version 52986 (0.0007) -[2023-11-28 01:35:57,612][87426] Updated weights for policy 1, policy_version 52870 (0.0007) -[2023-11-28 01:35:57,991][87426] Updated weights for policy 1, policy_version 52880 (0.0008) -[2023-11-28 01:35:58,365][87426] Updated weights for policy 1, policy_version 52890 (0.0007) -[2023-11-28 01:35:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 27099136. Throughput: 0: 2709.8, 1: 2703.2. Samples: 27119304. Policy #0 lag: (min: 1.0, avg: 30.4, max: 62.0) -[2023-11-28 01:35:58,446][86177] Avg episode reward: [(0, '-541.110'), (1, '-511.920')] -[2023-11-28 01:35:58,829][87424] Updated weights for policy 0, policy_version 52996 (0.0009) -[2023-11-28 01:35:59,210][87424] Updated weights for policy 0, policy_version 53006 (0.0011) -[2023-11-28 01:35:59,599][87424] Updated weights for policy 0, policy_version 53016 (0.0012) -[2023-11-28 01:36:00,152][87426] Updated weights for policy 1, policy_version 52900 (0.0009) -[2023-11-28 01:36:00,523][87426] Updated weights for policy 1, policy_version 52910 (0.0012) -[2023-11-28 01:36:00,897][87426] Updated weights for policy 1, policy_version 52920 (0.0012) -[2023-11-28 01:36:01,875][87424] Updated weights for policy 0, policy_version 53026 (0.0011) -[2023-11-28 01:36:02,255][87424] Updated weights for policy 0, policy_version 53036 (0.0011) -[2023-11-28 01:36:02,634][87424] Updated weights for policy 0, policy_version 53046 (0.0010) -[2023-11-28 01:36:03,024][87424] Updated weights for policy 0, policy_version 53056 (0.0008) -[2023-11-28 01:36:03,250][87426] Updated weights for policy 1, policy_version 52930 (0.0012) -[2023-11-28 01:36:03,444][86177] Fps is (10 sec: 5734.8, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 27131904. Throughput: 0: 2725.9, 1: 2709.0. Samples: 27144124. Policy #0 lag: (min: 1.0, avg: 30.4, max: 62.0) -[2023-11-28 01:36:03,445][86177] Avg episode reward: [(0, '-545.030'), (1, '-512.790')] -[2023-11-28 01:36:03,628][87426] Updated weights for policy 1, policy_version 52940 (0.0012) -[2023-11-28 01:36:04,005][87426] Updated weights for policy 1, policy_version 52950 (0.0012) -[2023-11-28 01:36:04,384][87426] Updated weights for policy 1, policy_version 52960 (0.0010) -[2023-11-28 01:36:05,461][87424] Updated weights for policy 0, policy_version 53066 (0.0009) -[2023-11-28 01:36:05,839][87424] Updated weights for policy 0, policy_version 53076 (0.0009) -[2023-11-28 01:36:06,222][87424] Updated weights for policy 0, policy_version 53086 (0.0008) -[2023-11-28 01:36:06,613][87426] Updated weights for policy 1, policy_version 52970 (0.0011) -[2023-11-28 01:36:06,995][87426] Updated weights for policy 1, policy_version 52980 (0.0008) -[2023-11-28 01:36:07,374][87426] Updated weights for policy 1, policy_version 52990 (0.0011) -[2023-11-28 01:36:08,171][87424] Updated weights for policy 0, policy_version 53096 (0.0011) -[2023-11-28 01:36:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 27156480. Throughput: 0: 2711.5, 1: 2734.9. Samples: 27176844. Policy #0 lag: (min: 1.0, avg: 30.4, max: 62.0) -[2023-11-28 01:36:08,446][86177] Avg episode reward: [(0, '-543.520'), (1, '-533.980')] -[2023-11-28 01:36:08,567][87424] Updated weights for policy 0, policy_version 53106 (0.0011) -[2023-11-28 01:36:08,956][87424] Updated weights for policy 0, policy_version 53116 (0.0012) -[2023-11-28 01:36:09,804][87426] Updated weights for policy 1, policy_version 53000 (0.0012) -[2023-11-28 01:36:10,178][87426] Updated weights for policy 1, policy_version 53010 (0.0012) -[2023-11-28 01:36:10,554][87426] Updated weights for policy 1, policy_version 53020 (0.0012) -[2023-11-28 01:36:10,693][87424] Updated weights for policy 0, policy_version 53126 (0.0011) -[2023-11-28 01:36:11,082][87424] Updated weights for policy 0, policy_version 53136 (0.0012) -[2023-11-28 01:36:11,464][87424] Updated weights for policy 0, policy_version 53146 (0.0012) -[2023-11-28 01:36:12,482][87426] Updated weights for policy 1, policy_version 53030 (0.0009) -[2023-11-28 01:36:12,853][87426] Updated weights for policy 1, policy_version 53040 (0.0010) -[2023-11-28 01:36:13,234][87426] Updated weights for policy 1, policy_version 53050 (0.0008) -[2023-11-28 01:36:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 27181056. Throughput: 0: 2700.2, 1: 2734.3. Samples: 27200820. Policy #0 lag: (min: 1.0, avg: 30.4, max: 62.0) -[2023-11-28 01:36:13,445][86177] Avg episode reward: [(0, '-557.950'), (1, '-530.220')] -[2023-11-28 01:36:13,906][87424] Updated weights for policy 0, policy_version 53156 (0.0010) -[2023-11-28 01:36:14,282][87424] Updated weights for policy 0, policy_version 53166 (0.0008) -[2023-11-28 01:36:14,660][87424] Updated weights for policy 0, policy_version 53176 (0.0008) -[2023-11-28 01:36:15,687][87426] Updated weights for policy 1, policy_version 53060 (0.0007) -[2023-11-28 01:36:16,064][87426] Updated weights for policy 1, policy_version 53070 (0.0011) -[2023-11-28 01:36:16,442][87426] Updated weights for policy 1, policy_version 53080 (0.0010) -[2023-11-28 01:36:16,782][87424] Updated weights for policy 0, policy_version 53186 (0.0009) -[2023-11-28 01:36:17,163][87424] Updated weights for policy 0, policy_version 53196 (0.0012) -[2023-11-28 01:36:17,559][87424] Updated weights for policy 0, policy_version 53206 (0.0012) -[2023-11-28 01:36:17,937][87424] Updated weights for policy 0, policy_version 53216 (0.0012) -[2023-11-28 01:36:18,340][87426] Updated weights for policy 1, policy_version 53090 (0.0011) -[2023-11-28 01:36:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 27213824. Throughput: 0: 2708.7, 1: 2722.1. Samples: 27224220. Policy #0 lag: (min: 1.0, avg: 30.4, max: 62.0) -[2023-11-28 01:36:18,445][86177] Avg episode reward: [(0, '-563.380'), (1, '-521.580')] -[2023-11-28 01:36:18,460][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000053216_13623296.pth... -[2023-11-28 01:36:18,495][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000050656_12967936.pth -[2023-11-28 01:36:18,716][87426] Updated weights for policy 1, policy_version 53100 (0.0010) -[2023-11-28 01:36:19,091][87426] Updated weights for policy 1, policy_version 53110 (0.0009) -[2023-11-28 01:36:19,471][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000053120_13598720.pth... -[2023-11-28 01:36:19,472][87426] Updated weights for policy 1, policy_version 53120 (0.0010) -[2023-11-28 01:36:19,507][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000050560_12943360.pth -[2023-11-28 01:36:20,295][87424] Updated weights for policy 0, policy_version 53226 (0.0008) -[2023-11-28 01:36:20,669][87424] Updated weights for policy 0, policy_version 53236 (0.0009) -[2023-11-28 01:36:21,052][87424] Updated weights for policy 0, policy_version 53246 (0.0008) -[2023-11-28 01:36:21,648][87426] Updated weights for policy 1, policy_version 53130 (0.0010) -[2023-11-28 01:36:22,025][87426] Updated weights for policy 1, policy_version 53140 (0.0011) -[2023-11-28 01:36:22,394][87426] Updated weights for policy 1, policy_version 53150 (0.0011) -[2023-11-28 01:36:23,050][87424] Updated weights for policy 0, policy_version 53256 (0.0011) -[2023-11-28 01:36:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 27238400. Throughput: 0: 2689.1, 1: 2713.4. Samples: 27256296. Policy #0 lag: (min: 1.0, avg: 30.4, max: 62.0) -[2023-11-28 01:36:23,445][86177] Avg episode reward: [(0, '-569.070'), (1, '-522.330')] -[2023-11-28 01:36:23,448][87424] Updated weights for policy 0, policy_version 53266 (0.0012) -[2023-11-28 01:36:23,820][87424] Updated weights for policy 0, policy_version 53276 (0.0012) -[2023-11-28 01:36:24,488][87426] Updated weights for policy 1, policy_version 53160 (0.0010) -[2023-11-28 01:36:24,873][87426] Updated weights for policy 1, policy_version 53170 (0.0012) -[2023-11-28 01:36:25,249][87426] Updated weights for policy 1, policy_version 53180 (0.0011) -[2023-11-28 01:36:25,956][87424] Updated weights for policy 0, policy_version 53286 (0.0010) -[2023-11-28 01:36:26,334][87424] Updated weights for policy 0, policy_version 53296 (0.0012) -[2023-11-28 01:36:26,726][87424] Updated weights for policy 0, policy_version 53306 (0.0011) -[2023-11-28 01:36:27,833][87426] Updated weights for policy 1, policy_version 53190 (0.0009) -[2023-11-28 01:36:28,216][87426] Updated weights for policy 1, policy_version 53200 (0.0008) -[2023-11-28 01:36:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 27262976. Throughput: 0: 2683.7, 1: 2735.2. Samples: 27281552. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 01:36:28,445][86177] Avg episode reward: [(0, '-554.780'), (1, '-500.880')] -[2023-11-28 01:36:28,599][87426] Updated weights for policy 1, policy_version 53210 (0.0008) -[2023-11-28 01:36:29,131][87424] Updated weights for policy 0, policy_version 53316 (0.0010) -[2023-11-28 01:36:29,520][87424] Updated weights for policy 0, policy_version 53326 (0.0007) -[2023-11-28 01:36:29,906][87424] Updated weights for policy 0, policy_version 53336 (0.0009) -[2023-11-28 01:36:30,902][87426] Updated weights for policy 1, policy_version 53220 (0.0010) -[2023-11-28 01:36:31,283][87426] Updated weights for policy 1, policy_version 53230 (0.0008) -[2023-11-28 01:36:31,672][87426] Updated weights for policy 1, policy_version 53240 (0.0008) -[2023-11-28 01:36:32,382][87424] Updated weights for policy 0, policy_version 53346 (0.0008) -[2023-11-28 01:36:32,764][87424] Updated weights for policy 0, policy_version 53356 (0.0008) -[2023-11-28 01:36:33,148][87424] Updated weights for policy 0, policy_version 53366 (0.0008) -[2023-11-28 01:36:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 27287552. Throughput: 0: 2672.9, 1: 2717.6. Samples: 27305656. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 01:36:33,445][86177] Avg episode reward: [(0, '-543.740'), (1, '-501.180')] -[2023-11-28 01:36:33,543][87424] Updated weights for policy 0, policy_version 53376 (0.0008) -[2023-11-28 01:36:33,953][87426] Updated weights for policy 1, policy_version 53250 (0.0009) -[2023-11-28 01:36:34,328][87426] Updated weights for policy 1, policy_version 53260 (0.0008) -[2023-11-28 01:36:34,700][87426] Updated weights for policy 1, policy_version 53270 (0.0008) -[2023-11-28 01:36:35,079][87426] Updated weights for policy 1, policy_version 53280 (0.0008) -[2023-11-28 01:36:35,382][87424] Updated weights for policy 0, policy_version 53386 (0.0008) -[2023-11-28 01:36:35,763][87424] Updated weights for policy 0, policy_version 53396 (0.0008) -[2023-11-28 01:36:36,154][87424] Updated weights for policy 0, policy_version 53406 (0.0008) -[2023-11-28 01:36:37,071][87426] Updated weights for policy 1, policy_version 53290 (0.0010) -[2023-11-28 01:36:37,447][87426] Updated weights for policy 1, policy_version 53300 (0.0008) -[2023-11-28 01:36:37,830][87426] Updated weights for policy 1, policy_version 53310 (0.0007) -[2023-11-28 01:36:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 27320320. Throughput: 0: 2670.3, 1: 2703.3. Samples: 27336612. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 01:36:38,445][86177] Avg episode reward: [(0, '-526.660'), (1, '-502.910')] -[2023-11-28 01:36:38,551][87424] Updated weights for policy 0, policy_version 53416 (0.0011) -[2023-11-28 01:36:38,937][87424] Updated weights for policy 0, policy_version 53426 (0.0012) -[2023-11-28 01:36:39,326][87424] Updated weights for policy 0, policy_version 53436 (0.0012) -[2023-11-28 01:36:40,018][87426] Updated weights for policy 1, policy_version 53320 (0.0011) -[2023-11-28 01:36:40,397][87426] Updated weights for policy 1, policy_version 53330 (0.0012) -[2023-11-28 01:36:40,783][87426] Updated weights for policy 1, policy_version 53340 (0.0012) -[2023-11-28 01:36:41,594][87424] Updated weights for policy 0, policy_version 53446 (0.0011) -[2023-11-28 01:36:41,994][87424] Updated weights for policy 0, policy_version 53456 (0.0012) -[2023-11-28 01:36:42,378][87424] Updated weights for policy 0, policy_version 53466 (0.0012) -[2023-11-28 01:36:43,178][87426] Updated weights for policy 1, policy_version 53350 (0.0012) -[2023-11-28 01:36:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 27344896. Throughput: 0: 2664.3, 1: 2696.7. Samples: 27360548. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 01:36:43,445][86177] Avg episode reward: [(0, '-561.400'), (1, '-503.310')] -[2023-11-28 01:36:43,549][87426] Updated weights for policy 1, policy_version 53360 (0.0012) -[2023-11-28 01:36:43,934][87426] Updated weights for policy 1, policy_version 53370 (0.0012) -[2023-11-28 01:36:44,302][87424] Updated weights for policy 0, policy_version 53476 (0.0011) -[2023-11-28 01:36:44,686][87424] Updated weights for policy 0, policy_version 53486 (0.0012) -[2023-11-28 01:36:45,070][87424] Updated weights for policy 0, policy_version 53496 (0.0011) -[2023-11-28 01:36:45,729][87426] Updated weights for policy 1, policy_version 53380 (0.0011) -[2023-11-28 01:36:46,118][87426] Updated weights for policy 1, policy_version 53390 (0.0012) -[2023-11-28 01:36:46,489][87426] Updated weights for policy 1, policy_version 53400 (0.0010) -[2023-11-28 01:36:47,422][87424] Updated weights for policy 0, policy_version 53506 (0.0011) -[2023-11-28 01:36:47,801][87424] Updated weights for policy 0, policy_version 53516 (0.0012) -[2023-11-28 01:36:48,189][87424] Updated weights for policy 0, policy_version 53526 (0.0012) -[2023-11-28 01:36:48,444][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 27369472. Throughput: 0: 2665.3, 1: 2693.5. Samples: 27385272. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 01:36:48,446][86177] Avg episode reward: [(0, '-564.780'), (1, '-509.220')] -[2023-11-28 01:36:48,563][87424] Updated weights for policy 0, policy_version 53536 (0.0012) -[2023-11-28 01:36:48,955][87426] Updated weights for policy 1, policy_version 53410 (0.0008) -[2023-11-28 01:36:49,337][87426] Updated weights for policy 1, policy_version 53420 (0.0012) -[2023-11-28 01:36:49,713][87426] Updated weights for policy 1, policy_version 53430 (0.0011) -[2023-11-28 01:36:50,083][87426] Updated weights for policy 1, policy_version 53440 (0.0012) -[2023-11-28 01:36:51,211][87424] Updated weights for policy 0, policy_version 53546 (0.0012) -[2023-11-28 01:36:51,603][87424] Updated weights for policy 0, policy_version 53556 (0.0012) -[2023-11-28 01:36:51,980][87424] Updated weights for policy 0, policy_version 53566 (0.0011) -[2023-11-28 01:36:52,127][87426] Updated weights for policy 1, policy_version 53450 (0.0012) -[2023-11-28 01:36:52,499][87426] Updated weights for policy 1, policy_version 53460 (0.0012) -[2023-11-28 01:36:52,895][87426] Updated weights for policy 1, policy_version 53470 (0.0012) -[2023-11-28 01:36:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 27402240. Throughput: 0: 2644.2, 1: 2680.4. Samples: 27416452. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 01:36:53,445][86177] Avg episode reward: [(0, '-562.190'), (1, '-510.840')] -[2023-11-28 01:36:54,191][87424] Updated weights for policy 0, policy_version 53576 (0.0011) -[2023-11-28 01:36:54,575][87424] Updated weights for policy 0, policy_version 53586 (0.0011) -[2023-11-28 01:36:54,959][87424] Updated weights for policy 0, policy_version 53596 (0.0009) -[2023-11-28 01:36:55,287][87426] Updated weights for policy 1, policy_version 53480 (0.0010) -[2023-11-28 01:36:55,665][87426] Updated weights for policy 1, policy_version 53490 (0.0007) -[2023-11-28 01:36:56,048][87426] Updated weights for policy 1, policy_version 53500 (0.0010) -[2023-11-28 01:36:57,287][87424] Updated weights for policy 0, policy_version 53606 (0.0009) -[2023-11-28 01:36:57,667][87424] Updated weights for policy 0, policy_version 53616 (0.0008) -[2023-11-28 01:36:57,938][87426] Updated weights for policy 1, policy_version 53510 (0.0011) -[2023-11-28 01:36:58,048][87424] Updated weights for policy 0, policy_version 53626 (0.0008) -[2023-11-28 01:36:58,316][87426] Updated weights for policy 1, policy_version 53520 (0.0009) -[2023-11-28 01:36:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 27426816. Throughput: 0: 2643.6, 1: 2683.6. Samples: 27440540. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 01:36:58,446][86177] Avg episode reward: [(0, '-551.720'), (1, '-523.730')] -[2023-11-28 01:36:58,699][87426] Updated weights for policy 1, policy_version 53530 (0.0008) -[2023-11-28 01:36:59,878][87424] Updated weights for policy 0, policy_version 53636 (0.0008) -[2023-11-28 01:37:00,269][87424] Updated weights for policy 0, policy_version 53646 (0.0008) -[2023-11-28 01:37:00,660][87424] Updated weights for policy 0, policy_version 53656 (0.0009) -[2023-11-28 01:37:00,731][87426] Updated weights for policy 1, policy_version 53540 (0.0008) -[2023-11-28 01:37:01,113][87426] Updated weights for policy 1, policy_version 53550 (0.0008) -[2023-11-28 01:37:01,487][87426] Updated weights for policy 1, policy_version 53560 (0.0008) -[2023-11-28 01:37:03,028][87424] Updated weights for policy 0, policy_version 53666 (0.0008) -[2023-11-28 01:37:03,408][87424] Updated weights for policy 0, policy_version 53676 (0.0008) -[2023-11-28 01:37:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 27451392. Throughput: 0: 2642.8, 1: 2702.5. Samples: 27464756. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 01:37:03,445][86177] Avg episode reward: [(0, '-565.000'), (1, '-528.200')] -[2023-11-28 01:37:03,727][87426] Updated weights for policy 1, policy_version 53570 (0.0010) -[2023-11-28 01:37:03,786][87424] Updated weights for policy 0, policy_version 53686 (0.0012) -[2023-11-28 01:37:04,094][87426] Updated weights for policy 1, policy_version 53580 (0.0012) -[2023-11-28 01:37:04,171][87424] Updated weights for policy 0, policy_version 53696 (0.0011) -[2023-11-28 01:37:04,480][87426] Updated weights for policy 1, policy_version 53590 (0.0011) -[2023-11-28 01:37:04,844][87426] Updated weights for policy 1, policy_version 53600 (0.0012) -[2023-11-28 01:37:06,644][87424] Updated weights for policy 0, policy_version 53706 (0.0009) -[2023-11-28 01:37:07,028][87424] Updated weights for policy 0, policy_version 53716 (0.0008) -[2023-11-28 01:37:07,312][87426] Updated weights for policy 1, policy_version 53610 (0.0012) -[2023-11-28 01:37:07,411][87424] Updated weights for policy 0, policy_version 53726 (0.0009) -[2023-11-28 01:37:07,690][87426] Updated weights for policy 1, policy_version 53620 (0.0012) -[2023-11-28 01:37:08,069][87426] Updated weights for policy 1, policy_version 53630 (0.0012) -[2023-11-28 01:37:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 27484160. Throughput: 0: 2658.3, 1: 2693.5. Samples: 27497128. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 01:37:08,445][86177] Avg episode reward: [(0, '-549.540'), (1, '-518.860')] -[2023-11-28 01:37:09,611][87424] Updated weights for policy 0, policy_version 53736 (0.0008) -[2023-11-28 01:37:09,999][87424] Updated weights for policy 0, policy_version 53746 (0.0010) -[2023-11-28 01:37:10,383][87424] Updated weights for policy 0, policy_version 53756 (0.0009) -[2023-11-28 01:37:10,519][87426] Updated weights for policy 1, policy_version 53640 (0.0012) -[2023-11-28 01:37:10,894][87426] Updated weights for policy 1, policy_version 53650 (0.0011) -[2023-11-28 01:37:11,274][87426] Updated weights for policy 1, policy_version 53660 (0.0011) -[2023-11-28 01:37:12,973][87424] Updated weights for policy 0, policy_version 53766 (0.0010) -[2023-11-28 01:37:13,358][87424] Updated weights for policy 0, policy_version 53776 (0.0011) -[2023-11-28 01:37:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 27500544. Throughput: 0: 2649.4, 1: 2663.5. Samples: 27520632. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 01:37:13,445][86177] Avg episode reward: [(0, '-550.200'), (1, '-515.020')] -[2023-11-28 01:37:13,574][87426] Updated weights for policy 1, policy_version 53670 (0.0009) -[2023-11-28 01:37:13,732][87424] Updated weights for policy 0, policy_version 53786 (0.0009) -[2023-11-28 01:37:13,955][87426] Updated weights for policy 1, policy_version 53680 (0.0008) -[2023-11-28 01:37:14,339][87426] Updated weights for policy 1, policy_version 53690 (0.0007) -[2023-11-28 01:37:15,802][87424] Updated weights for policy 0, policy_version 53796 (0.0009) -[2023-11-28 01:37:16,187][87424] Updated weights for policy 0, policy_version 53806 (0.0012) -[2023-11-28 01:37:16,368][87426] Updated weights for policy 1, policy_version 53700 (0.0007) -[2023-11-28 01:37:16,565][87424] Updated weights for policy 0, policy_version 53816 (0.0012) -[2023-11-28 01:37:16,750][87426] Updated weights for policy 1, policy_version 53710 (0.0007) -[2023-11-28 01:37:17,134][87426] Updated weights for policy 1, policy_version 53720 (0.0007) -[2023-11-28 01:37:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 27533312. Throughput: 0: 2642.8, 1: 2649.3. Samples: 27543804. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 01:37:18,445][86177] Avg episode reward: [(0, '-548.430'), (1, '-503.190')] -[2023-11-28 01:37:18,516][87424] Updated weights for policy 0, policy_version 53826 (0.0011) -[2023-11-28 01:37:18,895][87424] Updated weights for policy 0, policy_version 53836 (0.0011) -[2023-11-28 01:37:19,278][87424] Updated weights for policy 0, policy_version 53846 (0.0012) -[2023-11-28 01:37:19,566][87426] Updated weights for policy 1, policy_version 53730 (0.0008) -[2023-11-28 01:37:19,664][87424] Updated weights for policy 0, policy_version 53856 (0.0012) -[2023-11-28 01:37:19,947][87426] Updated weights for policy 1, policy_version 53740 (0.0010) -[2023-11-28 01:37:20,322][87426] Updated weights for policy 1, policy_version 53750 (0.0010) -[2023-11-28 01:37:20,703][87426] Updated weights for policy 1, policy_version 53760 (0.0009) -[2023-11-28 01:37:21,827][87424] Updated weights for policy 0, policy_version 53866 (0.0011) -[2023-11-28 01:37:22,214][87424] Updated weights for policy 0, policy_version 53876 (0.0011) -[2023-11-28 01:37:22,592][87424] Updated weights for policy 0, policy_version 53886 (0.0011) -[2023-11-28 01:37:22,981][87426] Updated weights for policy 1, policy_version 53770 (0.0012) -[2023-11-28 01:37:23,358][87426] Updated weights for policy 1, policy_version 53780 (0.0011) -[2023-11-28 01:37:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 27557888. Throughput: 0: 2679.5, 1: 2645.8. Samples: 27576248. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 01:37:23,445][86177] Avg episode reward: [(0, '-496.500'), (1, '-516.610')] -[2023-11-28 01:37:23,737][87426] Updated weights for policy 1, policy_version 53790 (0.0012) -[2023-11-28 01:37:24,511][87424] Updated weights for policy 0, policy_version 53896 (0.0009) -[2023-11-28 01:37:24,898][87424] Updated weights for policy 0, policy_version 53906 (0.0012) -[2023-11-28 01:37:25,277][87424] Updated weights for policy 0, policy_version 53916 (0.0012) -[2023-11-28 01:37:25,746][87426] Updated weights for policy 1, policy_version 53800 (0.0010) -[2023-11-28 01:37:26,139][87426] Updated weights for policy 1, policy_version 53810 (0.0011) -[2023-11-28 01:37:26,519][87426] Updated weights for policy 1, policy_version 53820 (0.0011) -[2023-11-28 01:37:27,816][87424] Updated weights for policy 0, policy_version 53926 (0.0009) -[2023-11-28 01:37:28,191][87424] Updated weights for policy 0, policy_version 53936 (0.0007) -[2023-11-28 01:37:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 27582464. Throughput: 0: 2670.4, 1: 2679.7. Samples: 27601304. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 01:37:28,445][86177] Avg episode reward: [(0, '-538.150'), (1, '-517.990')] -[2023-11-28 01:37:28,558][87424] Updated weights for policy 0, policy_version 53946 (0.0008) -[2023-11-28 01:37:28,904][87426] Updated weights for policy 1, policy_version 53830 (0.0011) -[2023-11-28 01:37:29,288][87426] Updated weights for policy 1, policy_version 53840 (0.0010) -[2023-11-28 01:37:29,669][87426] Updated weights for policy 1, policy_version 53850 (0.0010) -[2023-11-28 01:37:31,013][87424] Updated weights for policy 0, policy_version 53956 (0.0009) -[2023-11-28 01:37:31,384][87424] Updated weights for policy 0, policy_version 53966 (0.0012) -[2023-11-28 01:37:31,573][87426] Updated weights for policy 1, policy_version 53860 (0.0011) -[2023-11-28 01:37:31,767][87424] Updated weights for policy 0, policy_version 53976 (0.0011) -[2023-11-28 01:37:31,960][87426] Updated weights for policy 1, policy_version 53870 (0.0010) -[2023-11-28 01:37:32,334][87426] Updated weights for policy 1, policy_version 53880 (0.0010) -[2023-11-28 01:37:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 27615232. Throughput: 0: 2637.7, 1: 2701.3. Samples: 27625528. Policy #0 lag: (min: 31.0, avg: 31.5, max: 41.0) -[2023-11-28 01:37:33,446][86177] Avg episode reward: [(0, '-556.200'), (1, '-516.440')] -[2023-11-28 01:37:34,148][87426] Updated weights for policy 1, policy_version 53890 (0.0011) -[2023-11-28 01:37:34,169][87424] Updated weights for policy 0, policy_version 53986 (0.0011) -[2023-11-28 01:37:34,530][87426] Updated weights for policy 1, policy_version 53900 (0.0008) -[2023-11-28 01:37:34,552][87424] Updated weights for policy 0, policy_version 53996 (0.0012) -[2023-11-28 01:37:34,906][87426] Updated weights for policy 1, policy_version 53910 (0.0009) -[2023-11-28 01:37:34,935][87424] Updated weights for policy 0, policy_version 54006 (0.0008) -[2023-11-28 01:37:35,283][87426] Updated weights for policy 1, policy_version 53920 (0.0012) -[2023-11-28 01:37:35,326][87424] Updated weights for policy 0, policy_version 54016 (0.0007) -[2023-11-28 01:37:37,059][87424] Updated weights for policy 0, policy_version 54026 (0.0012) -[2023-11-28 01:37:37,439][87424] Updated weights for policy 0, policy_version 54036 (0.0012) -[2023-11-28 01:37:37,527][87426] Updated weights for policy 1, policy_version 53930 (0.0008) -[2023-11-28 01:37:37,820][87424] Updated weights for policy 0, policy_version 54046 (0.0011) -[2023-11-28 01:37:37,899][87426] Updated weights for policy 1, policy_version 53940 (0.0008) -[2023-11-28 01:37:38,281][87426] Updated weights for policy 1, policy_version 53950 (0.0007) -[2023-11-28 01:37:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 27648000. Throughput: 0: 2681.3, 1: 2700.2. Samples: 27658620. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:37:38,445][86177] Avg episode reward: [(0, '-604.980'), (1, '-512.810')] -[2023-11-28 01:37:40,176][87426] Updated weights for policy 1, policy_version 53960 (0.0010) -[2023-11-28 01:37:40,313][87424] Updated weights for policy 0, policy_version 54056 (0.0010) -[2023-11-28 01:37:40,562][87426] Updated weights for policy 1, policy_version 53970 (0.0011) -[2023-11-28 01:37:40,699][87424] Updated weights for policy 0, policy_version 54066 (0.0013) -[2023-11-28 01:37:40,944][87426] Updated weights for policy 1, policy_version 53980 (0.0009) -[2023-11-28 01:37:41,075][87424] Updated weights for policy 0, policy_version 54076 (0.0008) -[2023-11-28 01:37:43,355][87426] Updated weights for policy 1, policy_version 53990 (0.0010) -[2023-11-28 01:37:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 27664384. Throughput: 0: 2666.9, 1: 2711.8. Samples: 27682580. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:37:43,445][86177] Avg episode reward: [(0, '-598.060'), (1, '-500.090')] -[2023-11-28 01:37:43,720][87424] Updated weights for policy 0, policy_version 54086 (0.0009) -[2023-11-28 01:37:43,727][87426] Updated weights for policy 1, policy_version 54000 (0.0011) -[2023-11-28 01:37:44,100][87426] Updated weights for policy 1, policy_version 54010 (0.0011) -[2023-11-28 01:37:44,109][87424] Updated weights for policy 0, policy_version 54096 (0.0010) -[2023-11-28 01:37:44,496][87424] Updated weights for policy 0, policy_version 54106 (0.0011) -[2023-11-28 01:37:46,073][87426] Updated weights for policy 1, policy_version 54020 (0.0010) -[2023-11-28 01:37:46,455][87426] Updated weights for policy 1, policy_version 54030 (0.0012) -[2023-11-28 01:37:46,817][87426] Updated weights for policy 1, policy_version 54040 (0.0012) -[2023-11-28 01:37:46,900][87424] Updated weights for policy 0, policy_version 54116 (0.0012) -[2023-11-28 01:37:47,279][87424] Updated weights for policy 0, policy_version 54126 (0.0009) -[2023-11-28 01:37:47,659][87424] Updated weights for policy 0, policy_version 54136 (0.0010) -[2023-11-28 01:37:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 27697152. Throughput: 0: 2654.5, 1: 2715.5. Samples: 27706404. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:37:48,445][86177] Avg episode reward: [(0, '-568.530'), (1, '-504.520')] -[2023-11-28 01:37:48,916][87426] Updated weights for policy 1, policy_version 54050 (0.0012) -[2023-11-28 01:37:49,294][87426] Updated weights for policy 1, policy_version 54060 (0.0012) -[2023-11-28 01:37:49,667][87426] Updated weights for policy 1, policy_version 54070 (0.0012) -[2023-11-28 01:37:50,003][87424] Updated weights for policy 0, policy_version 54146 (0.0008) -[2023-11-28 01:37:50,052][87426] Updated weights for policy 1, policy_version 54080 (0.0012) -[2023-11-28 01:37:50,376][87424] Updated weights for policy 0, policy_version 54156 (0.0011) -[2023-11-28 01:37:50,754][87424] Updated weights for policy 0, policy_version 54166 (0.0009) -[2023-11-28 01:37:51,139][87424] Updated weights for policy 0, policy_version 54176 (0.0008) -[2023-11-28 01:37:52,550][87426] Updated weights for policy 1, policy_version 54090 (0.0009) -[2023-11-28 01:37:52,932][87426] Updated weights for policy 1, policy_version 54100 (0.0008) -[2023-11-28 01:37:53,299][87426] Updated weights for policy 1, policy_version 54110 (0.0009) -[2023-11-28 01:37:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 27721728. Throughput: 0: 2632.4, 1: 2722.2. Samples: 27738088. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:37:53,445][86177] Avg episode reward: [(0, '-547.870'), (1, '-507.270')] -[2023-11-28 01:37:53,501][87424] Updated weights for policy 0, policy_version 54186 (0.0011) -[2023-11-28 01:37:53,882][87424] Updated weights for policy 0, policy_version 54196 (0.0010) -[2023-11-28 01:37:54,262][87424] Updated weights for policy 0, policy_version 54206 (0.0008) -[2023-11-28 01:37:55,259][87426] Updated weights for policy 1, policy_version 54120 (0.0011) -[2023-11-28 01:37:55,634][87426] Updated weights for policy 1, policy_version 54130 (0.0011) -[2023-11-28 01:37:56,017][87426] Updated weights for policy 1, policy_version 54140 (0.0007) -[2023-11-28 01:37:56,169][87424] Updated weights for policy 0, policy_version 54216 (0.0010) -[2023-11-28 01:37:56,551][87424] Updated weights for policy 0, policy_version 54226 (0.0008) -[2023-11-28 01:37:56,933][87424] Updated weights for policy 0, policy_version 54236 (0.0008) -[2023-11-28 01:37:58,213][87426] Updated weights for policy 1, policy_version 54150 (0.0010) -[2023-11-28 01:37:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 27746304. Throughput: 0: 2638.8, 1: 2752.3. Samples: 27763228. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:37:58,445][86177] Avg episode reward: [(0, '-500.680'), (1, '-498.500')] -[2023-11-28 01:37:58,586][87426] Updated weights for policy 1, policy_version 54160 (0.0012) -[2023-11-28 01:37:58,676][87424] Updated weights for policy 0, policy_version 54246 (0.0010) -[2023-11-28 01:37:58,965][87426] Updated weights for policy 1, policy_version 54170 (0.0011) -[2023-11-28 01:37:59,058][87424] Updated weights for policy 0, policy_version 54256 (0.0010) -[2023-11-28 01:37:59,438][87424] Updated weights for policy 0, policy_version 54266 (0.0011) -[2023-11-28 01:38:01,339][87426] Updated weights for policy 1, policy_version 54180 (0.0012) -[2023-11-28 01:38:01,572][87424] Updated weights for policy 0, policy_version 54276 (0.0011) -[2023-11-28 01:38:01,716][87426] Updated weights for policy 1, policy_version 54190 (0.0008) -[2023-11-28 01:38:01,956][87424] Updated weights for policy 0, policy_version 54286 (0.0011) -[2023-11-28 01:38:02,095][87426] Updated weights for policy 1, policy_version 54200 (0.0011) -[2023-11-28 01:38:02,329][87424] Updated weights for policy 0, policy_version 54296 (0.0012) -[2023-11-28 01:38:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 27779072. Throughput: 0: 2681.6, 1: 2744.3. Samples: 27787968. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:38:03,446][86177] Avg episode reward: [(0, '-512.790'), (1, '-501.340')] -[2023-11-28 01:38:04,200][87426] Updated weights for policy 1, policy_version 54210 (0.0008) -[2023-11-28 01:38:04,578][87426] Updated weights for policy 1, policy_version 54220 (0.0007) -[2023-11-28 01:38:04,790][87424] Updated weights for policy 0, policy_version 54306 (0.0011) -[2023-11-28 01:38:04,960][87426] Updated weights for policy 1, policy_version 54230 (0.0011) -[2023-11-28 01:38:05,175][87424] Updated weights for policy 0, policy_version 54316 (0.0008) -[2023-11-28 01:38:05,352][87426] Updated weights for policy 1, policy_version 54240 (0.0010) -[2023-11-28 01:38:05,552][87424] Updated weights for policy 0, policy_version 54326 (0.0010) -[2023-11-28 01:38:05,937][87424] Updated weights for policy 0, policy_version 54336 (0.0010) -[2023-11-28 01:38:07,831][87426] Updated weights for policy 1, policy_version 54250 (0.0009) -[2023-11-28 01:38:08,113][87424] Updated weights for policy 0, policy_version 54346 (0.0012) -[2023-11-28 01:38:08,214][87426] Updated weights for policy 1, policy_version 54260 (0.0010) -[2023-11-28 01:38:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 27795456. Throughput: 0: 2667.8, 1: 2766.6. Samples: 27820796. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 01:38:08,445][86177] Avg episode reward: [(0, '-512.260'), (1, '-497.510')] -[2023-11-28 01:38:08,500][87424] Updated weights for policy 0, policy_version 54356 (0.0012) -[2023-11-28 01:38:08,592][87426] Updated weights for policy 1, policy_version 54270 (0.0008) -[2023-11-28 01:38:08,879][87424] Updated weights for policy 0, policy_version 54366 (0.0012) -[2023-11-28 01:38:10,509][87426] Updated weights for policy 1, policy_version 54280 (0.0011) -[2023-11-28 01:38:10,777][87424] Updated weights for policy 0, policy_version 54376 (0.0012) -[2023-11-28 01:38:10,890][87426] Updated weights for policy 1, policy_version 54290 (0.0009) -[2023-11-28 01:38:11,158][87424] Updated weights for policy 0, policy_version 54386 (0.0012) -[2023-11-28 01:38:11,263][87426] Updated weights for policy 1, policy_version 54300 (0.0010) -[2023-11-28 01:38:11,552][87424] Updated weights for policy 0, policy_version 54396 (0.0011) -[2023-11-28 01:38:13,431][87426] Updated weights for policy 1, policy_version 54310 (0.0011) -[2023-11-28 01:38:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 27828224. Throughput: 0: 2671.7, 1: 2750.9. Samples: 27845324. Policy #0 lag: (min: 4.0, avg: 30.1, max: 54.0) -[2023-11-28 01:38:13,445][86177] Avg episode reward: [(0, '-556.590'), (1, '-499.490')] -[2023-11-28 01:38:13,814][87426] Updated weights for policy 1, policy_version 54320 (0.0007) -[2023-11-28 01:38:14,123][87424] Updated weights for policy 0, policy_version 54406 (0.0012) -[2023-11-28 01:38:14,203][87426] Updated weights for policy 1, policy_version 54330 (0.0008) -[2023-11-28 01:38:14,508][87424] Updated weights for policy 0, policy_version 54416 (0.0012) -[2023-11-28 01:38:14,882][87424] Updated weights for policy 0, policy_version 54426 (0.0012) -[2023-11-28 01:38:16,203][87426] Updated weights for policy 1, policy_version 54340 (0.0009) -[2023-11-28 01:38:16,582][87426] Updated weights for policy 1, policy_version 54350 (0.0011) -[2023-11-28 01:38:16,959][87426] Updated weights for policy 1, policy_version 54360 (0.0011) -[2023-11-28 01:38:17,507][87424] Updated weights for policy 0, policy_version 54436 (0.0010) -[2023-11-28 01:38:17,887][87424] Updated weights for policy 0, policy_version 54446 (0.0007) -[2023-11-28 01:38:18,264][87424] Updated weights for policy 0, policy_version 54456 (0.0007) -[2023-11-28 01:38:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 27852800. Throughput: 0: 2658.0, 1: 2741.3. Samples: 27868492. Policy #0 lag: (min: 4.0, avg: 30.1, max: 54.0) -[2023-11-28 01:38:18,445][86177] Avg episode reward: [(0, '-541.860'), (1, '-499.590')] -[2023-11-28 01:38:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000054368_13918208.pth... -[2023-11-28 01:38:18,502][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000051840_13271040.pth -[2023-11-28 01:38:18,567][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000054464_13942784.pth... -[2023-11-28 01:38:18,597][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000051936_13295616.pth -[2023-11-28 01:38:19,522][87426] Updated weights for policy 1, policy_version 54370 (0.0008) -[2023-11-28 01:38:19,910][87426] Updated weights for policy 1, policy_version 54380 (0.0010) -[2023-11-28 01:38:20,288][87426] Updated weights for policy 1, policy_version 54390 (0.0008) -[2023-11-28 01:38:20,668][87426] Updated weights for policy 1, policy_version 54400 (0.0009) -[2023-11-28 01:38:20,806][87424] Updated weights for policy 0, policy_version 54466 (0.0008) -[2023-11-28 01:38:21,191][87424] Updated weights for policy 0, policy_version 54476 (0.0012) -[2023-11-28 01:38:21,564][87424] Updated weights for policy 0, policy_version 54486 (0.0012) -[2023-11-28 01:38:21,951][87424] Updated weights for policy 0, policy_version 54496 (0.0012) -[2023-11-28 01:38:22,693][87426] Updated weights for policy 1, policy_version 54410 (0.0011) -[2023-11-28 01:38:23,071][87426] Updated weights for policy 1, policy_version 54420 (0.0012) -[2023-11-28 01:38:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 27877376. Throughput: 0: 2625.1, 1: 2726.8. Samples: 27899456. Policy #0 lag: (min: 4.0, avg: 30.1, max: 54.0) -[2023-11-28 01:38:23,445][86177] Avg episode reward: [(0, '-541.040'), (1, '-498.310')] -[2023-11-28 01:38:23,461][87426] Updated weights for policy 1, policy_version 54430 (0.0011) -[2023-11-28 01:38:23,905][87424] Updated weights for policy 0, policy_version 54506 (0.0012) -[2023-11-28 01:38:24,271][87424] Updated weights for policy 0, policy_version 54516 (0.0010) -[2023-11-28 01:38:24,660][87424] Updated weights for policy 0, policy_version 54526 (0.0007) -[2023-11-28 01:38:25,803][87426] Updated weights for policy 1, policy_version 54440 (0.0012) -[2023-11-28 01:38:26,187][87426] Updated weights for policy 1, policy_version 54450 (0.0012) -[2023-11-28 01:38:26,581][87426] Updated weights for policy 1, policy_version 54460 (0.0011) -[2023-11-28 01:38:27,083][87424] Updated weights for policy 0, policy_version 54536 (0.0011) -[2023-11-28 01:38:27,480][87424] Updated weights for policy 0, policy_version 54546 (0.0012) -[2023-11-28 01:38:27,863][87424] Updated weights for policy 0, policy_version 54556 (0.0012) -[2023-11-28 01:38:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 27910144. Throughput: 0: 2645.0, 1: 2722.3. Samples: 27924108. Policy #0 lag: (min: 4.0, avg: 30.1, max: 54.0) -[2023-11-28 01:38:28,446][86177] Avg episode reward: [(0, '-541.380'), (1, '-498.630')] -[2023-11-28 01:38:28,875][87426] Updated weights for policy 1, policy_version 54470 (0.0010) -[2023-11-28 01:38:29,256][87426] Updated weights for policy 1, policy_version 54480 (0.0008) -[2023-11-28 01:38:29,638][87426] Updated weights for policy 1, policy_version 54490 (0.0007) -[2023-11-28 01:38:29,900][87424] Updated weights for policy 0, policy_version 54566 (0.0012) -[2023-11-28 01:38:30,274][87424] Updated weights for policy 0, policy_version 54576 (0.0012) -[2023-11-28 01:38:30,646][87424] Updated weights for policy 0, policy_version 54586 (0.0012) -[2023-11-28 01:38:31,945][87426] Updated weights for policy 1, policy_version 54500 (0.0010) -[2023-11-28 01:38:32,328][87426] Updated weights for policy 1, policy_version 54510 (0.0012) -[2023-11-28 01:38:32,706][87426] Updated weights for policy 1, policy_version 54520 (0.0012) -[2023-11-28 01:38:33,296][87424] Updated weights for policy 0, policy_version 54596 (0.0012) -[2023-11-28 01:38:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 27934720. Throughput: 0: 2655.9, 1: 2714.6. Samples: 27948076. Policy #0 lag: (min: 4.0, avg: 30.1, max: 54.0) -[2023-11-28 01:38:33,445][86177] Avg episode reward: [(0, '-498.630'), (1, '-498.280')] -[2023-11-28 01:38:33,681][87424] Updated weights for policy 0, policy_version 54606 (0.0012) -[2023-11-28 01:38:34,061][87424] Updated weights for policy 0, policy_version 54616 (0.0008) -[2023-11-28 01:38:34,598][87426] Updated weights for policy 1, policy_version 54530 (0.0012) -[2023-11-28 01:38:34,971][87426] Updated weights for policy 1, policy_version 54540 (0.0012) -[2023-11-28 01:38:35,351][87426] Updated weights for policy 1, policy_version 54550 (0.0012) -[2023-11-28 01:38:35,733][87426] Updated weights for policy 1, policy_version 54560 (0.0011) -[2023-11-28 01:38:35,967][87424] Updated weights for policy 0, policy_version 54626 (0.0008) -[2023-11-28 01:38:36,363][87424] Updated weights for policy 0, policy_version 54636 (0.0012) -[2023-11-28 01:38:36,748][87424] Updated weights for policy 0, policy_version 54646 (0.0010) -[2023-11-28 01:38:37,128][87424] Updated weights for policy 0, policy_version 54656 (0.0008) -[2023-11-28 01:38:37,685][87426] Updated weights for policy 1, policy_version 54570 (0.0010) -[2023-11-28 01:38:38,065][87426] Updated weights for policy 1, policy_version 54580 (0.0009) -[2023-11-28 01:38:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 27959296. Throughput: 0: 2668.4, 1: 2734.8. Samples: 27981236. Policy #0 lag: (min: 4.0, avg: 30.1, max: 54.0) -[2023-11-28 01:38:38,445][86177] Avg episode reward: [(0, '-499.790'), (1, '-505.470')] -[2023-11-28 01:38:38,447][87426] Updated weights for policy 1, policy_version 54590 (0.0011) -[2023-11-28 01:38:39,275][87424] Updated weights for policy 0, policy_version 54666 (0.0012) -[2023-11-28 01:38:39,663][87424] Updated weights for policy 0, policy_version 54676 (0.0011) -[2023-11-28 01:38:40,050][87424] Updated weights for policy 0, policy_version 54686 (0.0011) -[2023-11-28 01:38:40,237][87426] Updated weights for policy 1, policy_version 54600 (0.0009) -[2023-11-28 01:38:40,623][87426] Updated weights for policy 1, policy_version 54610 (0.0009) -[2023-11-28 01:38:41,001][87426] Updated weights for policy 1, policy_version 54620 (0.0008) -[2023-11-28 01:38:42,644][87424] Updated weights for policy 0, policy_version 54696 (0.0011) -[2023-11-28 01:38:43,026][87424] Updated weights for policy 0, policy_version 54706 (0.0010) -[2023-11-28 01:38:43,400][87424] Updated weights for policy 0, policy_version 54716 (0.0011) -[2023-11-28 01:38:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 27983872. Throughput: 0: 2656.4, 1: 2700.8. Samples: 28004300. Policy #0 lag: (min: 4.0, avg: 30.1, max: 54.0) -[2023-11-28 01:38:43,445][86177] Avg episode reward: [(0, '-505.500'), (1, '-506.170')] -[2023-11-28 01:38:43,457][87426] Updated weights for policy 1, policy_version 54630 (0.0012) -[2023-11-28 01:38:43,839][87426] Updated weights for policy 1, policy_version 54640 (0.0011) -[2023-11-28 01:38:44,222][87426] Updated weights for policy 1, policy_version 54650 (0.0008) -[2023-11-28 01:38:45,137][87424] Updated weights for policy 0, policy_version 54726 (0.0010) -[2023-11-28 01:38:45,518][87424] Updated weights for policy 0, policy_version 54736 (0.0011) -[2023-11-28 01:38:45,907][87424] Updated weights for policy 0, policy_version 54746 (0.0011) -[2023-11-28 01:38:46,718][87426] Updated weights for policy 1, policy_version 54660 (0.0007) -[2023-11-28 01:38:47,102][87426] Updated weights for policy 1, policy_version 54670 (0.0010) -[2023-11-28 01:38:47,472][87426] Updated weights for policy 1, policy_version 54680 (0.0009) -[2023-11-28 01:38:47,954][87424] Updated weights for policy 0, policy_version 54756 (0.0012) -[2023-11-28 01:38:48,335][87424] Updated weights for policy 0, policy_version 54766 (0.0012) -[2023-11-28 01:38:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 28016640. Throughput: 0: 2630.2, 1: 2710.3. Samples: 28028292. Policy #0 lag: (min: 13.0, avg: 28.3, max: 45.0) -[2023-11-28 01:38:48,445][86177] Avg episode reward: [(0, '-527.300'), (1, '-509.600')] -[2023-11-28 01:38:48,723][87424] Updated weights for policy 0, policy_version 54776 (0.0012) -[2023-11-28 01:38:49,235][87426] Updated weights for policy 1, policy_version 54690 (0.0011) -[2023-11-28 01:38:49,618][87426] Updated weights for policy 1, policy_version 54700 (0.0012) -[2023-11-28 01:38:49,996][87426] Updated weights for policy 1, policy_version 54710 (0.0012) -[2023-11-28 01:38:50,388][87426] Updated weights for policy 1, policy_version 54720 (0.0012) -[2023-11-28 01:38:51,217][87424] Updated weights for policy 0, policy_version 54786 (0.0010) -[2023-11-28 01:38:51,599][87424] Updated weights for policy 0, policy_version 54796 (0.0009) -[2023-11-28 01:38:51,988][87424] Updated weights for policy 0, policy_version 54806 (0.0011) -[2023-11-28 01:38:52,364][87424] Updated weights for policy 0, policy_version 54816 (0.0012) -[2023-11-28 01:38:52,901][87426] Updated weights for policy 1, policy_version 54730 (0.0009) -[2023-11-28 01:38:53,279][87426] Updated weights for policy 1, policy_version 54740 (0.0011) -[2023-11-28 01:38:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 28041216. Throughput: 0: 2617.9, 1: 2732.6. Samples: 28061568. Policy #0 lag: (min: 13.0, avg: 28.3, max: 45.0) -[2023-11-28 01:38:53,445][86177] Avg episode reward: [(0, '-534.870'), (1, '-513.450')] -[2023-11-28 01:38:53,656][87426] Updated weights for policy 1, policy_version 54750 (0.0013) -[2023-11-28 01:38:54,520][87424] Updated weights for policy 0, policy_version 54826 (0.0010) -[2023-11-28 01:38:54,896][87424] Updated weights for policy 0, policy_version 54836 (0.0008) -[2023-11-28 01:38:55,276][87424] Updated weights for policy 0, policy_version 54846 (0.0008) -[2023-11-28 01:38:55,789][87426] Updated weights for policy 1, policy_version 54760 (0.0009) -[2023-11-28 01:38:56,162][87426] Updated weights for policy 1, policy_version 54770 (0.0007) -[2023-11-28 01:38:56,544][87426] Updated weights for policy 1, policy_version 54780 (0.0007) -[2023-11-28 01:38:57,478][87424] Updated weights for policy 0, policy_version 54856 (0.0011) -[2023-11-28 01:38:57,868][87424] Updated weights for policy 0, policy_version 54866 (0.0012) -[2023-11-28 01:38:58,256][87424] Updated weights for policy 0, policy_version 54876 (0.0012) -[2023-11-28 01:38:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28073984. Throughput: 0: 2622.2, 1: 2715.5. Samples: 28085524. Policy #0 lag: (min: 13.0, avg: 28.3, max: 45.0) -[2023-11-28 01:38:58,445][86177] Avg episode reward: [(0, '-536.610'), (1, '-535.360')] -[2023-11-28 01:38:58,599][87426] Updated weights for policy 1, policy_version 54790 (0.0007) -[2023-11-28 01:38:58,977][87426] Updated weights for policy 1, policy_version 54800 (0.0009) -[2023-11-28 01:38:59,362][87426] Updated weights for policy 1, policy_version 54810 (0.0010) -[2023-11-28 01:38:59,979][87424] Updated weights for policy 0, policy_version 54886 (0.0010) -[2023-11-28 01:39:00,363][87424] Updated weights for policy 0, policy_version 54896 (0.0008) -[2023-11-28 01:39:00,759][87424] Updated weights for policy 0, policy_version 54906 (0.0010) -[2023-11-28 01:39:01,708][87426] Updated weights for policy 1, policy_version 54820 (0.0010) -[2023-11-28 01:39:02,092][87426] Updated weights for policy 1, policy_version 54830 (0.0012) -[2023-11-28 01:39:02,467][87426] Updated weights for policy 1, policy_version 54840 (0.0009) -[2023-11-28 01:39:03,021][87424] Updated weights for policy 0, policy_version 54916 (0.0009) -[2023-11-28 01:39:03,409][87424] Updated weights for policy 0, policy_version 54926 (0.0007) -[2023-11-28 01:39:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 28098560. Throughput: 0: 2659.8, 1: 2720.4. Samples: 28110604. Policy #0 lag: (min: 13.0, avg: 28.3, max: 45.0) -[2023-11-28 01:39:03,446][86177] Avg episode reward: [(0, '-529.440'), (1, '-539.340')] -[2023-11-28 01:39:03,791][87424] Updated weights for policy 0, policy_version 54936 (0.0007) -[2023-11-28 01:39:04,960][87426] Updated weights for policy 1, policy_version 54850 (0.0007) -[2023-11-28 01:39:05,340][87426] Updated weights for policy 1, policy_version 54860 (0.0008) -[2023-11-28 01:39:05,721][87426] Updated weights for policy 1, policy_version 54870 (0.0007) -[2023-11-28 01:39:06,051][87424] Updated weights for policy 0, policy_version 54946 (0.0008) -[2023-11-28 01:39:06,098][87426] Updated weights for policy 1, policy_version 54880 (0.0011) -[2023-11-28 01:39:06,426][87424] Updated weights for policy 0, policy_version 54956 (0.0011) -[2023-11-28 01:39:06,806][87424] Updated weights for policy 0, policy_version 54966 (0.0012) -[2023-11-28 01:39:07,186][87424] Updated weights for policy 0, policy_version 54976 (0.0012) -[2023-11-28 01:39:07,968][87426] Updated weights for policy 1, policy_version 54890 (0.0012) -[2023-11-28 01:39:08,352][87426] Updated weights for policy 1, policy_version 54900 (0.0012) -[2023-11-28 01:39:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28123136. Throughput: 0: 2665.3, 1: 2744.2. Samples: 28142884. Policy #0 lag: (min: 13.0, avg: 28.3, max: 45.0) -[2023-11-28 01:39:08,445][86177] Avg episode reward: [(0, '-536.420'), (1, '-537.580')] -[2023-11-28 01:39:08,725][87426] Updated weights for policy 1, policy_version 54910 (0.0012) -[2023-11-28 01:39:09,605][87424] Updated weights for policy 0, policy_version 54986 (0.0011) -[2023-11-28 01:39:09,981][87424] Updated weights for policy 0, policy_version 54996 (0.0009) -[2023-11-28 01:39:10,361][87424] Updated weights for policy 0, policy_version 55006 (0.0008) -[2023-11-28 01:39:11,259][87426] Updated weights for policy 1, policy_version 54920 (0.0011) -[2023-11-28 01:39:11,643][87426] Updated weights for policy 1, policy_version 54930 (0.0008) -[2023-11-28 01:39:12,026][87426] Updated weights for policy 1, policy_version 54940 (0.0008) -[2023-11-28 01:39:12,851][87424] Updated weights for policy 0, policy_version 55016 (0.0010) -[2023-11-28 01:39:13,231][87424] Updated weights for policy 0, policy_version 55026 (0.0011) -[2023-11-28 01:39:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 28147712. Throughput: 0: 2678.7, 1: 2722.0. Samples: 28167136. Policy #0 lag: (min: 13.0, avg: 28.3, max: 45.0) -[2023-11-28 01:39:13,445][86177] Avg episode reward: [(0, '-552.000'), (1, '-548.600')] -[2023-11-28 01:39:13,629][87424] Updated weights for policy 0, policy_version 55036 (0.0011) -[2023-11-28 01:39:14,284][87426] Updated weights for policy 1, policy_version 54950 (0.0011) -[2023-11-28 01:39:14,659][87426] Updated weights for policy 1, policy_version 54960 (0.0012) -[2023-11-28 01:39:15,040][87426] Updated weights for policy 1, policy_version 54970 (0.0012) -[2023-11-28 01:39:15,721][87424] Updated weights for policy 0, policy_version 55046 (0.0009) -[2023-11-28 01:39:16,109][87424] Updated weights for policy 0, policy_version 55056 (0.0012) -[2023-11-28 01:39:16,498][87424] Updated weights for policy 0, policy_version 55066 (0.0012) -[2023-11-28 01:39:17,076][87426] Updated weights for policy 1, policy_version 54980 (0.0012) -[2023-11-28 01:39:17,449][87426] Updated weights for policy 1, policy_version 54990 (0.0011) -[2023-11-28 01:39:17,828][87426] Updated weights for policy 1, policy_version 55000 (0.0011) -[2023-11-28 01:39:18,176][87424] Updated weights for policy 0, policy_version 55076 (0.0012) -[2023-11-28 01:39:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 28180480. Throughput: 0: 2678.6, 1: 2729.7. Samples: 28191448. Policy #0 lag: (min: 13.0, avg: 28.3, max: 45.0) -[2023-11-28 01:39:18,445][86177] Avg episode reward: [(0, '-552.630'), (1, '-520.320')] -[2023-11-28 01:39:18,550][87424] Updated weights for policy 0, policy_version 55086 (0.0010) -[2023-11-28 01:39:18,934][87424] Updated weights for policy 0, policy_version 55096 (0.0008) -[2023-11-28 01:39:19,635][87426] Updated weights for policy 1, policy_version 55010 (0.0011) -[2023-11-28 01:39:20,017][87426] Updated weights for policy 1, policy_version 55020 (0.0010) -[2023-11-28 01:39:20,400][87426] Updated weights for policy 1, policy_version 55030 (0.0011) -[2023-11-28 01:39:20,779][87426] Updated weights for policy 1, policy_version 55040 (0.0010) -[2023-11-28 01:39:21,210][87424] Updated weights for policy 0, policy_version 55106 (0.0011) -[2023-11-28 01:39:21,595][87424] Updated weights for policy 0, policy_version 55116 (0.0010) -[2023-11-28 01:39:21,970][87424] Updated weights for policy 0, policy_version 55126 (0.0012) -[2023-11-28 01:39:22,361][87424] Updated weights for policy 0, policy_version 55136 (0.0012) -[2023-11-28 01:39:23,160][87426] Updated weights for policy 1, policy_version 55050 (0.0011) -[2023-11-28 01:39:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28205056. Throughput: 0: 2696.0, 1: 2703.7. Samples: 28224224. Policy #0 lag: (min: 8.0, avg: 38.2, max: 72.0) -[2023-11-28 01:39:23,445][86177] Avg episode reward: [(0, '-556.400'), (1, '-522.690')] -[2023-11-28 01:39:23,534][87426] Updated weights for policy 1, policy_version 55060 (0.0009) -[2023-11-28 01:39:23,914][87426] Updated weights for policy 1, policy_version 55070 (0.0009) -[2023-11-28 01:39:24,752][87424] Updated weights for policy 0, policy_version 55146 (0.0012) -[2023-11-28 01:39:25,132][87424] Updated weights for policy 0, policy_version 55156 (0.0011) -[2023-11-28 01:39:25,512][87424] Updated weights for policy 0, policy_version 55166 (0.0009) -[2023-11-28 01:39:25,794][87426] Updated weights for policy 1, policy_version 55080 (0.0008) -[2023-11-28 01:39:26,177][87426] Updated weights for policy 1, policy_version 55090 (0.0007) -[2023-11-28 01:39:26,557][87426] Updated weights for policy 1, policy_version 55100 (0.0007) -[2023-11-28 01:39:27,850][87424] Updated weights for policy 0, policy_version 55176 (0.0011) -[2023-11-28 01:39:28,245][87426] Updated weights for policy 1, policy_version 55110 (0.0008) -[2023-11-28 01:39:28,247][87424] Updated weights for policy 0, policy_version 55186 (0.0011) -[2023-11-28 01:39:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 28229632. Throughput: 0: 2719.6, 1: 2725.5. Samples: 28249328. Policy #0 lag: (min: 8.0, avg: 38.2, max: 72.0) -[2023-11-28 01:39:28,445][86177] Avg episode reward: [(0, '-528.840'), (1, '-529.050')] -[2023-11-28 01:39:28,620][87424] Updated weights for policy 0, policy_version 55196 (0.0011) -[2023-11-28 01:39:28,631][87426] Updated weights for policy 1, policy_version 55120 (0.0009) -[2023-11-28 01:39:29,009][87426] Updated weights for policy 1, policy_version 55130 (0.0008) -[2023-11-28 01:39:30,362][87424] Updated weights for policy 0, policy_version 55206 (0.0012) -[2023-11-28 01:39:30,745][87424] Updated weights for policy 0, policy_version 55216 (0.0012) -[2023-11-28 01:39:31,120][87424] Updated weights for policy 0, policy_version 55226 (0.0012) -[2023-11-28 01:39:31,277][87426] Updated weights for policy 1, policy_version 55140 (0.0010) -[2023-11-28 01:39:31,662][87426] Updated weights for policy 1, policy_version 55150 (0.0011) -[2023-11-28 01:39:32,042][87426] Updated weights for policy 1, policy_version 55160 (0.0012) -[2023-11-28 01:39:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28262400. Throughput: 0: 2738.9, 1: 2734.7. Samples: 28274604. Policy #0 lag: (min: 8.0, avg: 38.2, max: 72.0) -[2023-11-28 01:39:33,445][86177] Avg episode reward: [(0, '-518.240'), (1, '-516.250')] -[2023-11-28 01:39:33,602][87424] Updated weights for policy 0, policy_version 55236 (0.0010) -[2023-11-28 01:39:33,981][87424] Updated weights for policy 0, policy_version 55246 (0.0009) -[2023-11-28 01:39:34,366][87426] Updated weights for policy 1, policy_version 55170 (0.0012) -[2023-11-28 01:39:34,367][87424] Updated weights for policy 0, policy_version 55256 (0.0010) -[2023-11-28 01:39:34,738][87426] Updated weights for policy 1, policy_version 55180 (0.0010) -[2023-11-28 01:39:35,114][87426] Updated weights for policy 1, policy_version 55190 (0.0007) -[2023-11-28 01:39:35,504][87426] Updated weights for policy 1, policy_version 55200 (0.0010) -[2023-11-28 01:39:36,875][87424] Updated weights for policy 0, policy_version 55266 (0.0009) -[2023-11-28 01:39:37,254][87424] Updated weights for policy 0, policy_version 55276 (0.0011) -[2023-11-28 01:39:37,641][87426] Updated weights for policy 1, policy_version 55210 (0.0011) -[2023-11-28 01:39:37,646][87424] Updated weights for policy 0, policy_version 55286 (0.0008) -[2023-11-28 01:39:38,019][87426] Updated weights for policy 1, policy_version 55220 (0.0011) -[2023-11-28 01:39:38,027][87424] Updated weights for policy 0, policy_version 55296 (0.0007) -[2023-11-28 01:39:38,405][87426] Updated weights for policy 1, policy_version 55230 (0.0011) -[2023-11-28 01:39:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28286976. Throughput: 0: 2726.1, 1: 2704.7. Samples: 28305956. Policy #0 lag: (min: 8.0, avg: 38.2, max: 72.0) -[2023-11-28 01:39:38,445][86177] Avg episode reward: [(0, '-527.790'), (1, '-526.220')] -[2023-11-28 01:39:39,986][87424] Updated weights for policy 0, policy_version 55306 (0.0009) -[2023-11-28 01:39:40,369][87424] Updated weights for policy 0, policy_version 55316 (0.0009) -[2023-11-28 01:39:40,695][87426] Updated weights for policy 1, policy_version 55240 (0.0010) -[2023-11-28 01:39:40,743][87424] Updated weights for policy 0, policy_version 55326 (0.0011) -[2023-11-28 01:39:41,074][87426] Updated weights for policy 1, policy_version 55250 (0.0008) -[2023-11-28 01:39:41,455][87426] Updated weights for policy 1, policy_version 55260 (0.0007) -[2023-11-28 01:39:43,006][87424] Updated weights for policy 0, policy_version 55336 (0.0009) -[2023-11-28 01:39:43,399][87424] Updated weights for policy 0, policy_version 55346 (0.0009) -[2023-11-28 01:39:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 28311552. Throughput: 0: 2737.7, 1: 2699.7. Samples: 28330208. Policy #0 lag: (min: 8.0, avg: 38.2, max: 72.0) -[2023-11-28 01:39:43,446][86177] Avg episode reward: [(0, '-533.030'), (1, '-514.510')] -[2023-11-28 01:39:43,773][87424] Updated weights for policy 0, policy_version 55356 (0.0009) -[2023-11-28 01:39:43,877][87426] Updated weights for policy 1, policy_version 55270 (0.0010) -[2023-11-28 01:39:44,262][87426] Updated weights for policy 1, policy_version 55280 (0.0011) -[2023-11-28 01:39:44,640][87426] Updated weights for policy 1, policy_version 55290 (0.0011) -[2023-11-28 01:39:46,185][87424] Updated weights for policy 0, policy_version 55366 (0.0010) -[2023-11-28 01:39:46,552][87426] Updated weights for policy 1, policy_version 55300 (0.0011) -[2023-11-28 01:39:46,569][87424] Updated weights for policy 0, policy_version 55376 (0.0012) -[2023-11-28 01:39:46,929][87426] Updated weights for policy 1, policy_version 55310 (0.0008) -[2023-11-28 01:39:46,957][87424] Updated weights for policy 0, policy_version 55386 (0.0010) -[2023-11-28 01:39:47,304][87426] Updated weights for policy 1, policy_version 55320 (0.0012) -[2023-11-28 01:39:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28344320. Throughput: 0: 2725.6, 1: 2686.9. Samples: 28354164. Policy #0 lag: (min: 8.0, avg: 38.2, max: 72.0) -[2023-11-28 01:39:48,445][86177] Avg episode reward: [(0, '-528.440'), (1, '-522.530')] -[2023-11-28 01:39:48,903][87424] Updated weights for policy 0, policy_version 55396 (0.0010) -[2023-11-28 01:39:49,278][87424] Updated weights for policy 0, policy_version 55406 (0.0011) -[2023-11-28 01:39:49,396][87426] Updated weights for policy 1, policy_version 55330 (0.0010) -[2023-11-28 01:39:49,662][87424] Updated weights for policy 0, policy_version 55416 (0.0011) -[2023-11-28 01:39:49,774][87426] Updated weights for policy 1, policy_version 55340 (0.0010) -[2023-11-28 01:39:50,159][87426] Updated weights for policy 1, policy_version 55350 (0.0010) -[2023-11-28 01:39:50,533][87426] Updated weights for policy 1, policy_version 55360 (0.0011) -[2023-11-28 01:39:51,995][87424] Updated weights for policy 0, policy_version 55426 (0.0012) -[2023-11-28 01:39:52,381][87424] Updated weights for policy 0, policy_version 55436 (0.0011) -[2023-11-28 01:39:52,764][87424] Updated weights for policy 0, policy_version 55446 (0.0010) -[2023-11-28 01:39:52,789][87426] Updated weights for policy 1, policy_version 55370 (0.0011) -[2023-11-28 01:39:53,147][87424] Updated weights for policy 0, policy_version 55456 (0.0010) -[2023-11-28 01:39:53,170][87426] Updated weights for policy 1, policy_version 55380 (0.0012) -[2023-11-28 01:39:53,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28368896. Throughput: 0: 2722.6, 1: 2704.3. Samples: 28387100. Policy #0 lag: (min: 8.0, avg: 38.2, max: 72.0) -[2023-11-28 01:39:53,445][86177] Avg episode reward: [(0, '-534.560'), (1, '-529.560')] -[2023-11-28 01:39:53,556][87426] Updated weights for policy 1, policy_version 55390 (0.0012) -[2023-11-28 01:39:55,050][87424] Updated weights for policy 0, policy_version 55466 (0.0011) -[2023-11-28 01:39:55,426][87424] Updated weights for policy 0, policy_version 55476 (0.0008) -[2023-11-28 01:39:55,806][87424] Updated weights for policy 0, policy_version 55486 (0.0012) -[2023-11-28 01:39:56,152][87426] Updated weights for policy 1, policy_version 55400 (0.0010) -[2023-11-28 01:39:56,531][87426] Updated weights for policy 1, policy_version 55410 (0.0011) -[2023-11-28 01:39:56,914][87426] Updated weights for policy 1, policy_version 55420 (0.0012) -[2023-11-28 01:39:57,462][87424] Updated weights for policy 0, policy_version 55496 (0.0011) -[2023-11-28 01:39:57,834][87424] Updated weights for policy 0, policy_version 55506 (0.0011) -[2023-11-28 01:39:58,218][87424] Updated weights for policy 0, policy_version 55516 (0.0011) -[2023-11-28 01:39:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 28401664. Throughput: 0: 2708.7, 1: 2710.8. Samples: 28411016. Policy #0 lag: (min: 23.0, avg: 38.1, max: 60.0) -[2023-11-28 01:39:58,445][86177] Avg episode reward: [(0, '-547.160'), (1, '-520.100')] -[2023-11-28 01:39:58,873][87426] Updated weights for policy 1, policy_version 55430 (0.0012) -[2023-11-28 01:39:59,257][87426] Updated weights for policy 1, policy_version 55440 (0.0011) -[2023-11-28 01:39:59,633][87426] Updated weights for policy 1, policy_version 55450 (0.0012) -[2023-11-28 01:40:00,399][87424] Updated weights for policy 0, policy_version 55526 (0.0010) -[2023-11-28 01:40:00,792][87424] Updated weights for policy 0, policy_version 55536 (0.0012) -[2023-11-28 01:40:01,167][87424] Updated weights for policy 0, policy_version 55546 (0.0012) -[2023-11-28 01:40:01,508][87426] Updated weights for policy 1, policy_version 55460 (0.0012) -[2023-11-28 01:40:01,895][87426] Updated weights for policy 1, policy_version 55470 (0.0012) -[2023-11-28 01:40:02,268][87426] Updated weights for policy 1, policy_version 55480 (0.0011) -[2023-11-28 01:40:03,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 28426240. Throughput: 0: 2742.0, 1: 2713.7. Samples: 28436956. Policy #0 lag: (min: 23.0, avg: 38.1, max: 60.0) -[2023-11-28 01:40:03,445][86177] Avg episode reward: [(0, '-540.190'), (1, '-516.470')] -[2023-11-28 01:40:03,551][87424] Updated weights for policy 0, policy_version 55556 (0.0009) -[2023-11-28 01:40:03,927][87424] Updated weights for policy 0, policy_version 55566 (0.0011) -[2023-11-28 01:40:04,303][87424] Updated weights for policy 0, policy_version 55576 (0.0007) -[2023-11-28 01:40:04,800][87426] Updated weights for policy 1, policy_version 55490 (0.0011) -[2023-11-28 01:40:05,172][87426] Updated weights for policy 1, policy_version 55500 (0.0011) -[2023-11-28 01:40:05,550][87426] Updated weights for policy 1, policy_version 55510 (0.0012) -[2023-11-28 01:40:05,931][87426] Updated weights for policy 1, policy_version 55520 (0.0011) -[2023-11-28 01:40:06,401][87424] Updated weights for policy 0, policy_version 55586 (0.0008) -[2023-11-28 01:40:06,794][87424] Updated weights for policy 0, policy_version 55596 (0.0012) -[2023-11-28 01:40:07,163][87424] Updated weights for policy 0, policy_version 55606 (0.0012) -[2023-11-28 01:40:07,544][87424] Updated weights for policy 0, policy_version 55616 (0.0011) -[2023-11-28 01:40:08,146][87426] Updated weights for policy 1, policy_version 55530 (0.0009) -[2023-11-28 01:40:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28450816. Throughput: 0: 2750.4, 1: 2727.0. Samples: 28470708. Policy #0 lag: (min: 23.0, avg: 38.1, max: 60.0) -[2023-11-28 01:40:08,445][86177] Avg episode reward: [(0, '-539.420'), (1, '-509.700')] -[2023-11-28 01:40:08,528][87426] Updated weights for policy 1, policy_version 55540 (0.0008) -[2023-11-28 01:40:08,910][87426] Updated weights for policy 1, policy_version 55550 (0.0008) -[2023-11-28 01:40:09,393][87424] Updated weights for policy 0, policy_version 55626 (0.0011) -[2023-11-28 01:40:09,777][87424] Updated weights for policy 0, policy_version 55636 (0.0011) -[2023-11-28 01:40:10,162][87424] Updated weights for policy 0, policy_version 55646 (0.0011) -[2023-11-28 01:40:11,103][87426] Updated weights for policy 1, policy_version 55560 (0.0011) -[2023-11-28 01:40:11,474][87426] Updated weights for policy 1, policy_version 55570 (0.0012) -[2023-11-28 01:40:11,855][87426] Updated weights for policy 1, policy_version 55580 (0.0012) -[2023-11-28 01:40:12,332][87424] Updated weights for policy 0, policy_version 55656 (0.0011) -[2023-11-28 01:40:12,718][87424] Updated weights for policy 0, policy_version 55666 (0.0011) -[2023-11-28 01:40:13,111][87424] Updated weights for policy 0, policy_version 55676 (0.0010) -[2023-11-28 01:40:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 28483584. Throughput: 0: 2759.3, 1: 2715.5. Samples: 28495692. Policy #0 lag: (min: 23.0, avg: 38.1, max: 60.0) -[2023-11-28 01:40:13,445][86177] Avg episode reward: [(0, '-535.610'), (1, '-507.730')] -[2023-11-28 01:40:13,821][87426] Updated weights for policy 1, policy_version 55590 (0.0009) -[2023-11-28 01:40:14,206][87426] Updated weights for policy 1, policy_version 55600 (0.0008) -[2023-11-28 01:40:14,586][87426] Updated weights for policy 1, policy_version 55610 (0.0012) -[2023-11-28 01:40:15,210][87424] Updated weights for policy 0, policy_version 55686 (0.0009) -[2023-11-28 01:40:15,604][87424] Updated weights for policy 0, policy_version 55696 (0.0009) -[2023-11-28 01:40:15,990][87424] Updated weights for policy 0, policy_version 55706 (0.0010) -[2023-11-28 01:40:16,858][87426] Updated weights for policy 1, policy_version 55620 (0.0012) -[2023-11-28 01:40:17,235][87426] Updated weights for policy 1, policy_version 55630 (0.0012) -[2023-11-28 01:40:17,617][87426] Updated weights for policy 1, policy_version 55640 (0.0011) -[2023-11-28 01:40:18,393][87424] Updated weights for policy 0, policy_version 55716 (0.0009) -[2023-11-28 01:40:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28508160. Throughput: 0: 2746.3, 1: 2720.9. Samples: 28520628. Policy #0 lag: (min: 23.0, avg: 38.1, max: 60.0) -[2023-11-28 01:40:18,445][86177] Avg episode reward: [(0, '-513.610'), (1, '-507.180')] -[2023-11-28 01:40:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000055648_14245888.pth... -[2023-11-28 01:40:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000053120_13598720.pth -[2023-11-28 01:40:18,775][87424] Updated weights for policy 0, policy_version 55726 (0.0011) -[2023-11-28 01:40:19,173][87424] Updated weights for policy 0, policy_version 55736 (0.0011) -[2023-11-28 01:40:19,471][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000055744_14270464.pth... -[2023-11-28 01:40:19,511][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000053216_13623296.pth -[2023-11-28 01:40:19,674][87426] Updated weights for policy 1, policy_version 55650 (0.0011) -[2023-11-28 01:40:20,049][87426] Updated weights for policy 1, policy_version 55660 (0.0011) -[2023-11-28 01:40:20,425][87426] Updated weights for policy 1, policy_version 55670 (0.0011) -[2023-11-28 01:40:20,799][87426] Updated weights for policy 1, policy_version 55680 (0.0011) -[2023-11-28 01:40:21,174][87424] Updated weights for policy 0, policy_version 55746 (0.0011) -[2023-11-28 01:40:21,550][87424] Updated weights for policy 0, policy_version 55756 (0.0012) -[2023-11-28 01:40:21,930][87424] Updated weights for policy 0, policy_version 55766 (0.0016) -[2023-11-28 01:40:22,305][87424] Updated weights for policy 0, policy_version 55776 (0.0011) -[2023-11-28 01:40:22,993][87426] Updated weights for policy 1, policy_version 55690 (0.0012) -[2023-11-28 01:40:23,366][87426] Updated weights for policy 1, policy_version 55700 (0.0011) -[2023-11-28 01:40:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28532736. Throughput: 0: 2755.1, 1: 2730.9. Samples: 28552828. Policy #0 lag: (min: 23.0, avg: 38.1, max: 60.0) -[2023-11-28 01:40:23,445][86177] Avg episode reward: [(0, '-517.530'), (1, '-511.690')] -[2023-11-28 01:40:23,755][87426] Updated weights for policy 1, policy_version 55710 (0.0012) -[2023-11-28 01:40:24,817][87424] Updated weights for policy 0, policy_version 55786 (0.0012) -[2023-11-28 01:40:25,201][87424] Updated weights for policy 0, policy_version 55796 (0.0011) -[2023-11-28 01:40:25,586][87424] Updated weights for policy 0, policy_version 55806 (0.0007) -[2023-11-28 01:40:26,025][87426] Updated weights for policy 1, policy_version 55720 (0.0009) -[2023-11-28 01:40:26,405][87426] Updated weights for policy 1, policy_version 55730 (0.0007) -[2023-11-28 01:40:26,784][87426] Updated weights for policy 1, policy_version 55740 (0.0007) -[2023-11-28 01:40:27,380][87424] Updated weights for policy 0, policy_version 55816 (0.0008) -[2023-11-28 01:40:27,763][87424] Updated weights for policy 0, policy_version 55826 (0.0007) -[2023-11-28 01:40:28,142][87424] Updated weights for policy 0, policy_version 55836 (0.0007) -[2023-11-28 01:40:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 28565504. Throughput: 0: 2754.9, 1: 2754.7. Samples: 28578136. Policy #0 lag: (min: 23.0, avg: 38.1, max: 60.0) -[2023-11-28 01:40:28,445][86177] Avg episode reward: [(0, '-521.830'), (1, '-507.670')] -[2023-11-28 01:40:28,771][87426] Updated weights for policy 1, policy_version 55750 (0.0010) -[2023-11-28 01:40:29,148][87426] Updated weights for policy 1, policy_version 55760 (0.0011) -[2023-11-28 01:40:29,529][87426] Updated weights for policy 1, policy_version 55770 (0.0012) -[2023-11-28 01:40:29,856][87424] Updated weights for policy 0, policy_version 55846 (0.0010) -[2023-11-28 01:40:30,238][87424] Updated weights for policy 0, policy_version 55856 (0.0012) -[2023-11-28 01:40:30,620][87424] Updated weights for policy 0, policy_version 55866 (0.0012) -[2023-11-28 01:40:31,761][87426] Updated weights for policy 1, policy_version 55780 (0.0011) -[2023-11-28 01:40:32,154][87426] Updated weights for policy 1, policy_version 55790 (0.0010) -[2023-11-28 01:40:32,530][87426] Updated weights for policy 1, policy_version 55800 (0.0011) -[2023-11-28 01:40:32,942][87424] Updated weights for policy 0, policy_version 55876 (0.0011) -[2023-11-28 01:40:33,330][87424] Updated weights for policy 0, policy_version 55886 (0.0012) -[2023-11-28 01:40:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28590080. Throughput: 0: 2770.8, 1: 2762.3. Samples: 28603152. Policy #0 lag: (min: 23.0, avg: 38.1, max: 60.0) -[2023-11-28 01:40:33,446][86177] Avg episode reward: [(0, '-521.870'), (1, '-504.070')] -[2023-11-28 01:40:33,712][87424] Updated weights for policy 0, policy_version 55896 (0.0012) -[2023-11-28 01:40:34,473][87426] Updated weights for policy 1, policy_version 55810 (0.0011) -[2023-11-28 01:40:34,849][87426] Updated weights for policy 1, policy_version 55820 (0.0010) -[2023-11-28 01:40:35,238][87426] Updated weights for policy 1, policy_version 55830 (0.0009) -[2023-11-28 01:40:35,571][87424] Updated weights for policy 0, policy_version 55906 (0.0009) -[2023-11-28 01:40:35,605][87426] Updated weights for policy 1, policy_version 55840 (0.0007) -[2023-11-28 01:40:35,953][87424] Updated weights for policy 0, policy_version 55916 (0.0012) -[2023-11-28 01:40:36,336][87424] Updated weights for policy 0, policy_version 55926 (0.0012) -[2023-11-28 01:40:36,711][87424] Updated weights for policy 0, policy_version 55936 (0.0012) -[2023-11-28 01:40:37,780][87426] Updated weights for policy 1, policy_version 55850 (0.0007) -[2023-11-28 01:40:38,159][87426] Updated weights for policy 1, policy_version 55860 (0.0007) -[2023-11-28 01:40:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 28614656. Throughput: 0: 2779.9, 1: 2751.7. Samples: 28636024. Policy #0 lag: (min: 31.0, avg: 33.6, max: 52.0) -[2023-11-28 01:40:38,445][86177] Avg episode reward: [(0, '-522.310'), (1, '-501.850')] -[2023-11-28 01:40:38,547][87426] Updated weights for policy 1, policy_version 55870 (0.0007) -[2023-11-28 01:40:39,264][87424] Updated weights for policy 0, policy_version 55946 (0.0012) -[2023-11-28 01:40:39,647][87424] Updated weights for policy 0, policy_version 55956 (0.0012) -[2023-11-28 01:40:40,037][87424] Updated weights for policy 0, policy_version 55966 (0.0012) -[2023-11-28 01:40:40,368][87426] Updated weights for policy 1, policy_version 55880 (0.0011) -[2023-11-28 01:40:40,746][87426] Updated weights for policy 1, policy_version 55890 (0.0011) -[2023-11-28 01:40:41,124][87426] Updated weights for policy 1, policy_version 55900 (0.0012) -[2023-11-28 01:40:42,162][87424] Updated weights for policy 0, policy_version 55976 (0.0010) -[2023-11-28 01:40:42,549][87424] Updated weights for policy 0, policy_version 55986 (0.0011) -[2023-11-28 01:40:42,923][87424] Updated weights for policy 0, policy_version 55996 (0.0015) -[2023-11-28 01:40:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 28647424. Throughput: 0: 2766.7, 1: 2761.4. Samples: 28659780. Policy #0 lag: (min: 31.0, avg: 33.6, max: 52.0) -[2023-11-28 01:40:43,446][86177] Avg episode reward: [(0, '-529.110'), (1, '-499.590')] -[2023-11-28 01:40:43,578][87426] Updated weights for policy 1, policy_version 55910 (0.0010) -[2023-11-28 01:40:43,958][87426] Updated weights for policy 1, policy_version 55920 (0.0007) -[2023-11-28 01:40:44,349][87426] Updated weights for policy 1, policy_version 55930 (0.0007) -[2023-11-28 01:40:45,457][87424] Updated weights for policy 0, policy_version 56006 (0.0010) -[2023-11-28 01:40:45,826][87424] Updated weights for policy 0, policy_version 56016 (0.0012) -[2023-11-28 01:40:46,205][87424] Updated weights for policy 0, policy_version 56026 (0.0012) -[2023-11-28 01:40:46,880][87426] Updated weights for policy 1, policy_version 55940 (0.0008) -[2023-11-28 01:40:47,253][87426] Updated weights for policy 1, policy_version 55950 (0.0008) -[2023-11-28 01:40:47,635][87426] Updated weights for policy 1, policy_version 55960 (0.0007) -[2023-11-28 01:40:47,971][87424] Updated weights for policy 0, policy_version 56036 (0.0012) -[2023-11-28 01:40:48,366][87424] Updated weights for policy 0, policy_version 56046 (0.0012) -[2023-11-28 01:40:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 28672000. Throughput: 0: 2715.8, 1: 2746.6. Samples: 28682764. Policy #0 lag: (min: 31.0, avg: 33.6, max: 52.0) -[2023-11-28 01:40:48,445][86177] Avg episode reward: [(0, '-528.250'), (1, '-503.790')] -[2023-11-28 01:40:48,746][87424] Updated weights for policy 0, policy_version 56056 (0.0012) -[2023-11-28 01:40:49,531][87426] Updated weights for policy 1, policy_version 55970 (0.0008) -[2023-11-28 01:40:49,914][87426] Updated weights for policy 1, policy_version 55980 (0.0012) -[2023-11-28 01:40:50,292][87426] Updated weights for policy 1, policy_version 55990 (0.0012) -[2023-11-28 01:40:50,657][87424] Updated weights for policy 0, policy_version 56066 (0.0012) -[2023-11-28 01:40:50,667][87426] Updated weights for policy 1, policy_version 56000 (0.0012) -[2023-11-28 01:40:51,035][87424] Updated weights for policy 0, policy_version 56076 (0.0012) -[2023-11-28 01:40:51,417][87424] Updated weights for policy 0, policy_version 56086 (0.0012) -[2023-11-28 01:40:51,802][87424] Updated weights for policy 0, policy_version 56096 (0.0010) -[2023-11-28 01:40:53,125][87426] Updated weights for policy 1, policy_version 56010 (0.0012) -[2023-11-28 01:40:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 28696576. Throughput: 0: 2710.0, 1: 2733.6. Samples: 28715668. Policy #0 lag: (min: 31.0, avg: 33.6, max: 52.0) -[2023-11-28 01:40:53,445][86177] Avg episode reward: [(0, '-523.020'), (1, '-508.470')] -[2023-11-28 01:40:53,508][87426] Updated weights for policy 1, policy_version 56020 (0.0011) -[2023-11-28 01:40:53,883][87426] Updated weights for policy 1, policy_version 56030 (0.0012) -[2023-11-28 01:40:54,150][87424] Updated weights for policy 0, policy_version 56106 (0.0010) -[2023-11-28 01:40:54,522][87424] Updated weights for policy 0, policy_version 56116 (0.0007) -[2023-11-28 01:40:54,913][87424] Updated weights for policy 0, policy_version 56126 (0.0010) -[2023-11-28 01:40:56,111][87426] Updated weights for policy 1, policy_version 56040 (0.0008) -[2023-11-28 01:40:56,490][87426] Updated weights for policy 1, policy_version 56050 (0.0007) -[2023-11-28 01:40:56,867][87426] Updated weights for policy 1, policy_version 56060 (0.0007) -[2023-11-28 01:40:56,934][87424] Updated weights for policy 0, policy_version 56136 (0.0010) -[2023-11-28 01:40:57,316][87424] Updated weights for policy 0, policy_version 56146 (0.0009) -[2023-11-28 01:40:57,710][87424] Updated weights for policy 0, policy_version 56156 (0.0010) -[2023-11-28 01:40:58,391][87426] Updated weights for policy 1, policy_version 56070 (0.0010) -[2023-11-28 01:40:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 28729344. Throughput: 0: 2692.9, 1: 2752.9. Samples: 28740752. Policy #0 lag: (min: 31.0, avg: 33.6, max: 52.0) -[2023-11-28 01:40:58,445][86177] Avg episode reward: [(0, '-520.640'), (1, '-507.970')] -[2023-11-28 01:40:58,770][87426] Updated weights for policy 1, policy_version 56080 (0.0011) -[2023-11-28 01:40:59,155][87426] Updated weights for policy 1, policy_version 56090 (0.0007) -[2023-11-28 01:40:59,894][87424] Updated weights for policy 0, policy_version 56166 (0.0012) -[2023-11-28 01:41:00,275][87424] Updated weights for policy 0, policy_version 56176 (0.0012) -[2023-11-28 01:41:00,661][87424] Updated weights for policy 0, policy_version 56186 (0.0011) -[2023-11-28 01:41:01,558][87426] Updated weights for policy 1, policy_version 56100 (0.0009) -[2023-11-28 01:41:01,939][87426] Updated weights for policy 1, policy_version 56110 (0.0011) -[2023-11-28 01:41:02,314][87426] Updated weights for policy 1, policy_version 56120 (0.0011) -[2023-11-28 01:41:03,180][87424] Updated weights for policy 0, policy_version 56196 (0.0009) -[2023-11-28 01:41:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 28753920. Throughput: 0: 2698.0, 1: 2751.6. Samples: 28765860. Policy #0 lag: (min: 31.0, avg: 33.6, max: 52.0) -[2023-11-28 01:41:03,445][86177] Avg episode reward: [(0, '-508.680'), (1, '-506.610')] -[2023-11-28 01:41:03,564][87424] Updated weights for policy 0, policy_version 56206 (0.0008) -[2023-11-28 01:41:03,948][87424] Updated weights for policy 0, policy_version 56216 (0.0008) -[2023-11-28 01:41:04,858][87426] Updated weights for policy 1, policy_version 56130 (0.0008) -[2023-11-28 01:41:05,228][87426] Updated weights for policy 1, policy_version 56140 (0.0010) -[2023-11-28 01:41:05,602][87426] Updated weights for policy 1, policy_version 56150 (0.0011) -[2023-11-28 01:41:05,986][87426] Updated weights for policy 1, policy_version 56160 (0.0007) -[2023-11-28 01:41:06,315][87424] Updated weights for policy 0, policy_version 56226 (0.0008) -[2023-11-28 01:41:06,693][87424] Updated weights for policy 0, policy_version 56236 (0.0008) -[2023-11-28 01:41:07,093][87424] Updated weights for policy 0, policy_version 56246 (0.0009) -[2023-11-28 01:41:07,466][87424] Updated weights for policy 0, policy_version 56256 (0.0008) -[2023-11-28 01:41:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 28778496. Throughput: 0: 2704.0, 1: 2712.5. Samples: 28796572. Policy #0 lag: (min: 31.0, avg: 33.6, max: 52.0) -[2023-11-28 01:41:08,445][86177] Avg episode reward: [(0, '-520.020'), (1, '-506.020')] -[2023-11-28 01:41:08,487][87426] Updated weights for policy 1, policy_version 56170 (0.0007) -[2023-11-28 01:41:08,874][87426] Updated weights for policy 1, policy_version 56180 (0.0008) -[2023-11-28 01:41:09,246][87426] Updated weights for policy 1, policy_version 56190 (0.0011) -[2023-11-28 01:41:09,398][87424] Updated weights for policy 0, policy_version 56266 (0.0008) -[2023-11-28 01:41:09,784][87424] Updated weights for policy 0, policy_version 56276 (0.0008) -[2023-11-28 01:41:10,164][87424] Updated weights for policy 0, policy_version 56286 (0.0008) -[2023-11-28 01:41:11,244][87426] Updated weights for policy 1, policy_version 56200 (0.0011) -[2023-11-28 01:41:11,642][87426] Updated weights for policy 1, policy_version 56210 (0.0011) -[2023-11-28 01:41:12,021][87426] Updated weights for policy 1, policy_version 56220 (0.0012) -[2023-11-28 01:41:12,635][87424] Updated weights for policy 0, policy_version 56296 (0.0008) -[2023-11-28 01:41:13,021][87424] Updated weights for policy 0, policy_version 56306 (0.0009) -[2023-11-28 01:41:13,401][87424] Updated weights for policy 0, policy_version 56316 (0.0009) -[2023-11-28 01:41:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 28803072. Throughput: 0: 2688.5, 1: 2675.8. Samples: 28819528. Policy #0 lag: (min: 11.0, avg: 34.8, max: 43.0) -[2023-11-28 01:41:13,445][86177] Avg episode reward: [(0, '-520.680'), (1, '-504.640')] -[2023-11-28 01:41:13,967][87426] Updated weights for policy 1, policy_version 56230 (0.0009) -[2023-11-28 01:41:14,340][87426] Updated weights for policy 1, policy_version 56240 (0.0007) -[2023-11-28 01:41:14,725][87426] Updated weights for policy 1, policy_version 56250 (0.0008) -[2023-11-28 01:41:15,062][87424] Updated weights for policy 0, policy_version 56326 (0.0012) -[2023-11-28 01:41:15,442][87424] Updated weights for policy 0, policy_version 56336 (0.0012) -[2023-11-28 01:41:15,825][87424] Updated weights for policy 0, policy_version 56346 (0.0009) -[2023-11-28 01:41:17,094][87426] Updated weights for policy 1, policy_version 56260 (0.0009) -[2023-11-28 01:41:17,468][87426] Updated weights for policy 1, policy_version 56270 (0.0009) -[2023-11-28 01:41:17,842][87426] Updated weights for policy 1, policy_version 56280 (0.0012) -[2023-11-28 01:41:18,279][87424] Updated weights for policy 0, policy_version 56356 (0.0008) -[2023-11-28 01:41:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 28835840. Throughput: 0: 2700.5, 1: 2671.0. Samples: 28844872. Policy #0 lag: (min: 11.0, avg: 34.8, max: 43.0) -[2023-11-28 01:41:18,445][86177] Avg episode reward: [(0, '-521.830'), (1, '-511.210')] -[2023-11-28 01:41:18,665][87424] Updated weights for policy 0, policy_version 56366 (0.0009) -[2023-11-28 01:41:19,041][87424] Updated weights for policy 0, policy_version 56376 (0.0010) -[2023-11-28 01:41:20,271][87426] Updated weights for policy 1, policy_version 56290 (0.0011) -[2023-11-28 01:41:20,650][87426] Updated weights for policy 1, policy_version 56300 (0.0010) -[2023-11-28 01:41:21,034][87426] Updated weights for policy 1, policy_version 56310 (0.0012) -[2023-11-28 01:41:21,414][87426] Updated weights for policy 1, policy_version 56320 (0.0009) -[2023-11-28 01:41:21,568][87424] Updated weights for policy 0, policy_version 56386 (0.0011) -[2023-11-28 01:41:21,965][87424] Updated weights for policy 0, policy_version 56396 (0.0009) -[2023-11-28 01:41:22,342][87424] Updated weights for policy 0, policy_version 56406 (0.0009) -[2023-11-28 01:41:22,726][87424] Updated weights for policy 0, policy_version 56416 (0.0008) -[2023-11-28 01:41:23,401][87426] Updated weights for policy 1, policy_version 56330 (0.0007) -[2023-11-28 01:41:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 28860416. Throughput: 0: 2671.0, 1: 2661.9. Samples: 28876004. Policy #0 lag: (min: 11.0, avg: 34.8, max: 43.0) -[2023-11-28 01:41:23,445][86177] Avg episode reward: [(0, '-517.570'), (1, '-510.980')] -[2023-11-28 01:41:23,779][87426] Updated weights for policy 1, policy_version 56340 (0.0007) -[2023-11-28 01:41:24,161][87426] Updated weights for policy 1, policy_version 56350 (0.0009) -[2023-11-28 01:41:25,229][87424] Updated weights for policy 0, policy_version 56426 (0.0012) -[2023-11-28 01:41:25,621][87424] Updated weights for policy 0, policy_version 56436 (0.0012) -[2023-11-28 01:41:25,868][87426] Updated weights for policy 1, policy_version 56360 (0.0012) -[2023-11-28 01:41:26,000][87424] Updated weights for policy 0, policy_version 56446 (0.0012) -[2023-11-28 01:41:26,250][87426] Updated weights for policy 1, policy_version 56370 (0.0011) -[2023-11-28 01:41:26,617][87426] Updated weights for policy 1, policy_version 56380 (0.0012) -[2023-11-28 01:41:28,196][87424] Updated weights for policy 0, policy_version 56456 (0.0009) -[2023-11-28 01:41:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 28884992. Throughput: 0: 2667.1, 1: 2676.4. Samples: 28900240. Policy #0 lag: (min: 11.0, avg: 34.8, max: 43.0) -[2023-11-28 01:41:28,445][86177] Avg episode reward: [(0, '-508.050'), (1, '-512.270')] -[2023-11-28 01:41:28,590][87424] Updated weights for policy 0, policy_version 56466 (0.0008) -[2023-11-28 01:41:28,975][87424] Updated weights for policy 0, policy_version 56476 (0.0008) -[2023-11-28 01:41:29,064][87426] Updated weights for policy 1, policy_version 56390 (0.0012) -[2023-11-28 01:41:29,440][87426] Updated weights for policy 1, policy_version 56400 (0.0009) -[2023-11-28 01:41:29,825][87426] Updated weights for policy 1, policy_version 56410 (0.0008) -[2023-11-28 01:41:31,247][87424] Updated weights for policy 0, policy_version 56486 (0.0008) -[2023-11-28 01:41:31,638][87424] Updated weights for policy 0, policy_version 56496 (0.0009) -[2023-11-28 01:41:32,011][87424] Updated weights for policy 0, policy_version 56506 (0.0012) -[2023-11-28 01:41:32,393][87426] Updated weights for policy 1, policy_version 56420 (0.0012) -[2023-11-28 01:41:32,775][87426] Updated weights for policy 1, policy_version 56430 (0.0012) -[2023-11-28 01:41:33,133][87426] Updated weights for policy 1, policy_version 56440 (0.0012) -[2023-11-28 01:41:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 28917760. Throughput: 0: 2715.8, 1: 2678.1. Samples: 28925492. Policy #0 lag: (min: 11.0, avg: 34.8, max: 43.0) -[2023-11-28 01:41:33,445][86177] Avg episode reward: [(0, '-514.870'), (1, '-511.900')] -[2023-11-28 01:41:34,360][87424] Updated weights for policy 0, policy_version 56516 (0.0009) -[2023-11-28 01:41:34,748][87424] Updated weights for policy 0, policy_version 56526 (0.0010) -[2023-11-28 01:41:35,043][87426] Updated weights for policy 1, policy_version 56450 (0.0009) -[2023-11-28 01:41:35,129][87424] Updated weights for policy 0, policy_version 56536 (0.0010) -[2023-11-28 01:41:35,428][87426] Updated weights for policy 1, policy_version 56460 (0.0012) -[2023-11-28 01:41:35,814][87426] Updated weights for policy 1, policy_version 56470 (0.0012) -[2023-11-28 01:41:36,204][87426] Updated weights for policy 1, policy_version 56480 (0.0012) -[2023-11-28 01:41:37,123][87424] Updated weights for policy 0, policy_version 56546 (0.0010) -[2023-11-28 01:41:37,510][87424] Updated weights for policy 0, policy_version 56556 (0.0010) -[2023-11-28 01:41:37,890][87424] Updated weights for policy 0, policy_version 56566 (0.0011) -[2023-11-28 01:41:38,275][87424] Updated weights for policy 0, policy_version 56576 (0.0008) -[2023-11-28 01:41:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 28942336. Throughput: 0: 2688.0, 1: 2681.8. Samples: 28957308. Policy #0 lag: (min: 11.0, avg: 34.8, max: 43.0) -[2023-11-28 01:41:38,445][86177] Avg episode reward: [(0, '-513.850'), (1, '-510.730')] -[2023-11-28 01:41:38,717][87426] Updated weights for policy 1, policy_version 56490 (0.0007) -[2023-11-28 01:41:39,101][87426] Updated weights for policy 1, policy_version 56500 (0.0009) -[2023-11-28 01:41:39,479][87426] Updated weights for policy 1, policy_version 56510 (0.0008) -[2023-11-28 01:41:40,731][87424] Updated weights for policy 0, policy_version 56586 (0.0008) -[2023-11-28 01:41:41,116][87424] Updated weights for policy 0, policy_version 56596 (0.0008) -[2023-11-28 01:41:41,502][87424] Updated weights for policy 0, policy_version 56606 (0.0011) -[2023-11-28 01:41:41,725][87426] Updated weights for policy 1, policy_version 56520 (0.0008) -[2023-11-28 01:41:42,119][87426] Updated weights for policy 1, policy_version 56530 (0.0010) -[2023-11-28 01:41:42,498][87426] Updated weights for policy 1, policy_version 56540 (0.0010) -[2023-11-28 01:41:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 28966912. Throughput: 0: 2684.9, 1: 2662.8. Samples: 28981400. Policy #0 lag: (min: 11.0, avg: 34.8, max: 43.0) -[2023-11-28 01:41:43,445][86177] Avg episode reward: [(0, '-525.180'), (1, '-519.150')] -[2023-11-28 01:41:43,725][87424] Updated weights for policy 0, policy_version 56616 (0.0011) -[2023-11-28 01:41:44,101][87424] Updated weights for policy 0, policy_version 56626 (0.0012) -[2023-11-28 01:41:44,498][87426] Updated weights for policy 1, policy_version 56550 (0.0009) -[2023-11-28 01:41:44,500][87424] Updated weights for policy 0, policy_version 56636 (0.0011) -[2023-11-28 01:41:44,885][87426] Updated weights for policy 1, policy_version 56560 (0.0007) -[2023-11-28 01:41:45,261][87426] Updated weights for policy 1, policy_version 56570 (0.0007) -[2023-11-28 01:41:46,880][87424] Updated weights for policy 0, policy_version 56646 (0.0008) -[2023-11-28 01:41:47,269][87424] Updated weights for policy 0, policy_version 56656 (0.0007) -[2023-11-28 01:41:47,660][87424] Updated weights for policy 0, policy_version 56666 (0.0008) -[2023-11-28 01:41:47,695][87426] Updated weights for policy 1, policy_version 56580 (0.0009) -[2023-11-28 01:41:48,076][87426] Updated weights for policy 1, policy_version 56590 (0.0008) -[2023-11-28 01:41:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 28991488. Throughput: 0: 2645.6, 1: 2657.2. Samples: 29004488. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:41:48,445][86177] Avg episode reward: [(0, '-524.150'), (1, '-518.890')] -[2023-11-28 01:41:48,463][87426] Updated weights for policy 1, policy_version 56600 (0.0010) -[2023-11-28 01:41:49,777][87424] Updated weights for policy 0, policy_version 56676 (0.0009) -[2023-11-28 01:41:50,155][87424] Updated weights for policy 0, policy_version 56686 (0.0012) -[2023-11-28 01:41:50,429][87426] Updated weights for policy 1, policy_version 56610 (0.0011) -[2023-11-28 01:41:50,538][87424] Updated weights for policy 0, policy_version 56696 (0.0010) -[2023-11-28 01:41:50,811][87426] Updated weights for policy 1, policy_version 56620 (0.0011) -[2023-11-28 01:41:51,187][87426] Updated weights for policy 1, policy_version 56630 (0.0011) -[2023-11-28 01:41:51,567][87426] Updated weights for policy 1, policy_version 56640 (0.0012) -[2023-11-28 01:41:52,777][87424] Updated weights for policy 0, policy_version 56706 (0.0010) -[2023-11-28 01:41:53,153][87424] Updated weights for policy 0, policy_version 56716 (0.0012) -[2023-11-28 01:41:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 29016064. Throughput: 0: 2655.4, 1: 2678.6. Samples: 29036600. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:41:53,445][86177] Avg episode reward: [(0, '-519.320'), (1, '-543.550')] -[2023-11-28 01:41:53,534][87424] Updated weights for policy 0, policy_version 56726 (0.0012) -[2023-11-28 01:41:53,915][87424] Updated weights for policy 0, policy_version 56736 (0.0010) -[2023-11-28 01:41:54,028][87426] Updated weights for policy 1, policy_version 56650 (0.0012) -[2023-11-28 01:41:54,413][87426] Updated weights for policy 1, policy_version 56660 (0.0012) -[2023-11-28 01:41:54,791][87426] Updated weights for policy 1, policy_version 56670 (0.0012) -[2023-11-28 01:41:55,932][87424] Updated weights for policy 0, policy_version 56746 (0.0012) -[2023-11-28 01:41:56,314][87424] Updated weights for policy 0, policy_version 56756 (0.0012) -[2023-11-28 01:41:56,705][87424] Updated weights for policy 0, policy_version 56766 (0.0012) -[2023-11-28 01:41:57,119][87426] Updated weights for policy 1, policy_version 56680 (0.0008) -[2023-11-28 01:41:57,503][87426] Updated weights for policy 1, policy_version 56690 (0.0007) -[2023-11-28 01:41:57,886][87426] Updated weights for policy 1, policy_version 56700 (0.0011) -[2023-11-28 01:41:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 29048832. Throughput: 0: 2657.9, 1: 2706.1. Samples: 29060908. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:41:58,446][86177] Avg episode reward: [(0, '-560.160'), (1, '-544.550')] -[2023-11-28 01:41:58,542][87424] Updated weights for policy 0, policy_version 56776 (0.0009) -[2023-11-28 01:41:58,929][87424] Updated weights for policy 0, policy_version 56786 (0.0008) -[2023-11-28 01:41:59,312][87424] Updated weights for policy 0, policy_version 56796 (0.0008) -[2023-11-28 01:41:59,895][87426] Updated weights for policy 1, policy_version 56710 (0.0011) -[2023-11-28 01:42:00,278][87426] Updated weights for policy 1, policy_version 56720 (0.0011) -[2023-11-28 01:42:00,666][87426] Updated weights for policy 1, policy_version 56730 (0.0010) -[2023-11-28 01:42:01,751][87424] Updated weights for policy 0, policy_version 56806 (0.0008) -[2023-11-28 01:42:02,135][87424] Updated weights for policy 0, policy_version 56816 (0.0009) -[2023-11-28 01:42:02,516][87424] Updated weights for policy 0, policy_version 56826 (0.0009) -[2023-11-28 01:42:02,709][87426] Updated weights for policy 1, policy_version 56740 (0.0008) -[2023-11-28 01:42:03,088][87426] Updated weights for policy 1, policy_version 56750 (0.0009) -[2023-11-28 01:42:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 29073408. Throughput: 0: 2615.8, 1: 2713.2. Samples: 29084676. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:42:03,445][86177] Avg episode reward: [(0, '-547.790'), (1, '-538.170')] -[2023-11-28 01:42:03,466][87426] Updated weights for policy 1, policy_version 56760 (0.0008) -[2023-11-28 01:42:04,665][87424] Updated weights for policy 0, policy_version 56836 (0.0009) -[2023-11-28 01:42:05,046][87424] Updated weights for policy 0, policy_version 56846 (0.0012) -[2023-11-28 01:42:05,429][87424] Updated weights for policy 0, policy_version 56856 (0.0012) -[2023-11-28 01:42:05,556][87426] Updated weights for policy 1, policy_version 56770 (0.0008) -[2023-11-28 01:42:05,936][87426] Updated weights for policy 1, policy_version 56780 (0.0008) -[2023-11-28 01:42:06,313][87426] Updated weights for policy 1, policy_version 56790 (0.0007) -[2023-11-28 01:42:06,691][87426] Updated weights for policy 1, policy_version 56800 (0.0008) -[2023-11-28 01:42:07,163][87424] Updated weights for policy 0, policy_version 56866 (0.0011) -[2023-11-28 01:42:07,549][87424] Updated weights for policy 0, policy_version 56876 (0.0011) -[2023-11-28 01:42:07,933][87424] Updated weights for policy 0, policy_version 56886 (0.0010) -[2023-11-28 01:42:08,317][87424] Updated weights for policy 0, policy_version 56896 (0.0009) -[2023-11-28 01:42:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 29106176. Throughput: 0: 2673.9, 1: 2708.4. Samples: 29118204. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:42:08,445][86177] Avg episode reward: [(0, '-541.490'), (1, '-519.590')] -[2023-11-28 01:42:09,158][87426] Updated weights for policy 1, policy_version 56810 (0.0008) -[2023-11-28 01:42:09,537][87426] Updated weights for policy 1, policy_version 56820 (0.0008) -[2023-11-28 01:42:09,916][87426] Updated weights for policy 1, policy_version 56830 (0.0011) -[2023-11-28 01:42:10,415][87424] Updated weights for policy 0, policy_version 56906 (0.0012) -[2023-11-28 01:42:10,802][87424] Updated weights for policy 0, policy_version 56916 (0.0012) -[2023-11-28 01:42:11,174][87424] Updated weights for policy 0, policy_version 56926 (0.0012) -[2023-11-28 01:42:11,840][87426] Updated weights for policy 1, policy_version 56840 (0.0010) -[2023-11-28 01:42:12,215][87426] Updated weights for policy 1, policy_version 56850 (0.0010) -[2023-11-28 01:42:12,588][87426] Updated weights for policy 1, policy_version 56860 (0.0012) -[2023-11-28 01:42:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 29130752. Throughput: 0: 2700.7, 1: 2690.6. Samples: 29142848. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:42:13,445][86177] Avg episode reward: [(0, '-535.700'), (1, '-523.580')] -[2023-11-28 01:42:13,676][87424] Updated weights for policy 0, policy_version 56936 (0.0009) -[2023-11-28 01:42:14,060][87424] Updated weights for policy 0, policy_version 56946 (0.0008) -[2023-11-28 01:42:14,451][87424] Updated weights for policy 0, policy_version 56956 (0.0011) -[2023-11-28 01:42:14,838][87426] Updated weights for policy 1, policy_version 56870 (0.0010) -[2023-11-28 01:42:15,218][87426] Updated weights for policy 1, policy_version 56880 (0.0007) -[2023-11-28 01:42:15,592][87426] Updated weights for policy 1, policy_version 56890 (0.0008) -[2023-11-28 01:42:17,000][87424] Updated weights for policy 0, policy_version 56966 (0.0010) -[2023-11-28 01:42:17,390][87424] Updated weights for policy 0, policy_version 56976 (0.0008) -[2023-11-28 01:42:17,720][87426] Updated weights for policy 1, policy_version 56900 (0.0007) -[2023-11-28 01:42:17,781][87424] Updated weights for policy 0, policy_version 56986 (0.0007) -[2023-11-28 01:42:18,098][87426] Updated weights for policy 1, policy_version 56910 (0.0010) -[2023-11-28 01:42:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 29155328. Throughput: 0: 2668.3, 1: 2709.5. Samples: 29167492. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:42:18,445][86177] Avg episode reward: [(0, '-508.170'), (1, '-522.380')] -[2023-11-28 01:42:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000056992_14589952.pth... -[2023-11-28 01:42:18,476][87426] Updated weights for policy 1, policy_version 56920 (0.0007) -[2023-11-28 01:42:18,495][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000054464_13942784.pth -[2023-11-28 01:42:18,779][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000056928_14573568.pth... -[2023-11-28 01:42:18,810][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000054368_13918208.pth -[2023-11-28 01:42:20,194][87424] Updated weights for policy 0, policy_version 56996 (0.0010) -[2023-11-28 01:42:20,574][87424] Updated weights for policy 0, policy_version 57006 (0.0012) -[2023-11-28 01:42:20,784][87426] Updated weights for policy 1, policy_version 56930 (0.0009) -[2023-11-28 01:42:20,956][87424] Updated weights for policy 0, policy_version 57016 (0.0011) -[2023-11-28 01:42:21,189][87426] Updated weights for policy 1, policy_version 56940 (0.0011) -[2023-11-28 01:42:21,567][87426] Updated weights for policy 1, policy_version 56950 (0.0012) -[2023-11-28 01:42:21,940][87426] Updated weights for policy 1, policy_version 56960 (0.0012) -[2023-11-28 01:42:23,302][87424] Updated weights for policy 0, policy_version 57026 (0.0011) -[2023-11-28 01:42:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 29179904. Throughput: 0: 2672.4, 1: 2715.1. Samples: 29199748. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:42:23,445][86177] Avg episode reward: [(0, '-508.020'), (1, '-522.970')] -[2023-11-28 01:42:23,682][87424] Updated weights for policy 0, policy_version 57036 (0.0007) -[2023-11-28 01:42:24,027][87426] Updated weights for policy 1, policy_version 56970 (0.0009) -[2023-11-28 01:42:24,064][87424] Updated weights for policy 0, policy_version 57046 (0.0008) -[2023-11-28 01:42:24,408][87426] Updated weights for policy 1, policy_version 56980 (0.0007) -[2023-11-28 01:42:24,458][87424] Updated weights for policy 0, policy_version 57056 (0.0011) -[2023-11-28 01:42:24,806][87426] Updated weights for policy 1, policy_version 56990 (0.0007) -[2023-11-28 01:42:26,685][87424] Updated weights for policy 0, policy_version 57066 (0.0012) -[2023-11-28 01:42:26,833][87426] Updated weights for policy 1, policy_version 57000 (0.0010) -[2023-11-28 01:42:27,069][87424] Updated weights for policy 0, policy_version 57076 (0.0012) -[2023-11-28 01:42:27,224][87426] Updated weights for policy 1, policy_version 57010 (0.0009) -[2023-11-28 01:42:27,451][87424] Updated weights for policy 0, policy_version 57086 (0.0012) -[2023-11-28 01:42:27,605][87426] Updated weights for policy 1, policy_version 57020 (0.0008) -[2023-11-28 01:42:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 29212672. Throughput: 0: 2679.8, 1: 2727.7. Samples: 29224740. Policy #0 lag: (min: 16.0, avg: 40.5, max: 48.0) -[2023-11-28 01:42:28,445][86177] Avg episode reward: [(0, '-509.110'), (1, '-528.240')] -[2023-11-28 01:42:29,389][87424] Updated weights for policy 0, policy_version 57096 (0.0011) -[2023-11-28 01:42:29,788][87424] Updated weights for policy 0, policy_version 57106 (0.0011) -[2023-11-28 01:42:29,892][87426] Updated weights for policy 1, policy_version 57030 (0.0010) -[2023-11-28 01:42:30,160][87424] Updated weights for policy 0, policy_version 57116 (0.0016) -[2023-11-28 01:42:30,270][87426] Updated weights for policy 1, policy_version 57040 (0.0009) -[2023-11-28 01:42:30,652][87426] Updated weights for policy 1, policy_version 57050 (0.0009) -[2023-11-28 01:42:32,237][87424] Updated weights for policy 0, policy_version 57126 (0.0008) -[2023-11-28 01:42:32,524][87426] Updated weights for policy 1, policy_version 57060 (0.0010) -[2023-11-28 01:42:32,629][87424] Updated weights for policy 0, policy_version 57136 (0.0010) -[2023-11-28 01:42:32,910][87426] Updated weights for policy 1, policy_version 57070 (0.0011) -[2023-11-28 01:42:33,002][87424] Updated weights for policy 0, policy_version 57146 (0.0010) -[2023-11-28 01:42:33,280][87426] Updated weights for policy 1, policy_version 57080 (0.0012) -[2023-11-28 01:42:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 29237248. Throughput: 0: 2720.8, 1: 2728.5. Samples: 29249704. Policy #0 lag: (min: 16.0, avg: 40.5, max: 48.0) -[2023-11-28 01:42:33,445][86177] Avg episode reward: [(0, '-507.220'), (1, '-518.160')] -[2023-11-28 01:42:35,004][87424] Updated weights for policy 0, policy_version 57156 (0.0008) -[2023-11-28 01:42:35,176][87426] Updated weights for policy 1, policy_version 57090 (0.0012) -[2023-11-28 01:42:35,381][87424] Updated weights for policy 0, policy_version 57166 (0.0010) -[2023-11-28 01:42:35,557][87426] Updated weights for policy 1, policy_version 57100 (0.0011) -[2023-11-28 01:42:35,764][87424] Updated weights for policy 0, policy_version 57176 (0.0007) -[2023-11-28 01:42:35,939][87426] Updated weights for policy 1, policy_version 57110 (0.0011) -[2023-11-28 01:42:36,317][87426] Updated weights for policy 1, policy_version 57120 (0.0012) -[2023-11-28 01:42:38,174][87424] Updated weights for policy 0, policy_version 57186 (0.0009) -[2023-11-28 01:42:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 29261824. Throughput: 0: 2710.9, 1: 2772.5. Samples: 29283356. Policy #0 lag: (min: 16.0, avg: 40.5, max: 48.0) -[2023-11-28 01:42:38,445][86177] Avg episode reward: [(0, '-551.110'), (1, '-517.500')] -[2023-11-28 01:42:38,552][87424] Updated weights for policy 0, policy_version 57196 (0.0009) -[2023-11-28 01:42:38,768][87426] Updated weights for policy 1, policy_version 57130 (0.0011) -[2023-11-28 01:42:38,941][87424] Updated weights for policy 0, policy_version 57206 (0.0009) -[2023-11-28 01:42:39,143][87426] Updated weights for policy 1, policy_version 57140 (0.0010) -[2023-11-28 01:42:39,321][87424] Updated weights for policy 0, policy_version 57216 (0.0011) -[2023-11-28 01:42:39,521][87426] Updated weights for policy 1, policy_version 57150 (0.0010) -[2023-11-28 01:42:41,807][87424] Updated weights for policy 0, policy_version 57226 (0.0011) -[2023-11-28 01:42:42,047][87426] Updated weights for policy 1, policy_version 57160 (0.0010) -[2023-11-28 01:42:42,191][87424] Updated weights for policy 0, policy_version 57236 (0.0011) -[2023-11-28 01:42:42,424][87426] Updated weights for policy 1, policy_version 57170 (0.0011) -[2023-11-28 01:42:42,572][87424] Updated weights for policy 0, policy_version 57246 (0.0011) -[2023-11-28 01:42:42,801][87426] Updated weights for policy 1, policy_version 57180 (0.0012) -[2023-11-28 01:42:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 29294592. Throughput: 0: 2707.2, 1: 2746.3. Samples: 29306316. Policy #0 lag: (min: 16.0, avg: 40.5, max: 48.0) -[2023-11-28 01:42:43,446][86177] Avg episode reward: [(0, '-553.210'), (1, '-512.860')] -[2023-11-28 01:42:44,663][87424] Updated weights for policy 0, policy_version 57256 (0.0009) -[2023-11-28 01:42:44,926][87426] Updated weights for policy 1, policy_version 57190 (0.0011) -[2023-11-28 01:42:45,042][87424] Updated weights for policy 0, policy_version 57266 (0.0009) -[2023-11-28 01:42:45,296][87426] Updated weights for policy 1, policy_version 57200 (0.0012) -[2023-11-28 01:42:45,421][87424] Updated weights for policy 0, policy_version 57276 (0.0010) -[2023-11-28 01:42:45,677][87426] Updated weights for policy 1, policy_version 57210 (0.0012) -[2023-11-28 01:42:47,349][87424] Updated weights for policy 0, policy_version 57286 (0.0012) -[2023-11-28 01:42:47,736][87424] Updated weights for policy 0, policy_version 57296 (0.0012) -[2023-11-28 01:42:47,929][87426] Updated weights for policy 1, policy_version 57220 (0.0012) -[2023-11-28 01:42:48,111][87424] Updated weights for policy 0, policy_version 57306 (0.0011) -[2023-11-28 01:42:48,302][87426] Updated weights for policy 1, policy_version 57230 (0.0012) -[2023-11-28 01:42:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 29319168. Throughput: 0: 2744.7, 1: 2730.7. Samples: 29331072. Policy #0 lag: (min: 16.0, avg: 40.5, max: 48.0) -[2023-11-28 01:42:48,446][86177] Avg episode reward: [(0, '-551.530'), (1, '-510.590')] -[2023-11-28 01:42:48,689][87426] Updated weights for policy 1, policy_version 57240 (0.0012) -[2023-11-28 01:42:50,459][87424] Updated weights for policy 0, policy_version 57316 (0.0010) -[2023-11-28 01:42:50,764][87426] Updated weights for policy 1, policy_version 57250 (0.0012) -[2023-11-28 01:42:50,842][87424] Updated weights for policy 0, policy_version 57326 (0.0009) -[2023-11-28 01:42:51,146][87426] Updated weights for policy 1, policy_version 57260 (0.0011) -[2023-11-28 01:42:51,225][87424] Updated weights for policy 0, policy_version 57336 (0.0009) -[2023-11-28 01:42:51,519][87426] Updated weights for policy 1, policy_version 57270 (0.0011) -[2023-11-28 01:42:51,903][87426] Updated weights for policy 1, policy_version 57280 (0.0010) -[2023-11-28 01:42:53,422][87424] Updated weights for policy 0, policy_version 57346 (0.0009) -[2023-11-28 01:42:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 29343744. Throughput: 0: 2717.2, 1: 2730.0. Samples: 29363328. Policy #0 lag: (min: 16.0, avg: 40.5, max: 48.0) -[2023-11-28 01:42:53,445][86177] Avg episode reward: [(0, '-561.450'), (1, '-507.650')] -[2023-11-28 01:42:53,800][87424] Updated weights for policy 0, policy_version 57356 (0.0012) -[2023-11-28 01:42:54,173][87424] Updated weights for policy 0, policy_version 57366 (0.0012) -[2023-11-28 01:42:54,372][87426] Updated weights for policy 1, policy_version 57290 (0.0010) -[2023-11-28 01:42:54,562][87424] Updated weights for policy 0, policy_version 57376 (0.0011) -[2023-11-28 01:42:54,753][87426] Updated weights for policy 1, policy_version 57300 (0.0011) -[2023-11-28 01:42:55,132][87426] Updated weights for policy 1, policy_version 57310 (0.0011) -[2023-11-28 01:42:56,578][87424] Updated weights for policy 0, policy_version 57386 (0.0012) -[2023-11-28 01:42:56,961][87424] Updated weights for policy 0, policy_version 57396 (0.0011) -[2023-11-28 01:42:57,347][87424] Updated weights for policy 0, policy_version 57406 (0.0012) -[2023-11-28 01:42:57,550][87426] Updated weights for policy 1, policy_version 57320 (0.0009) -[2023-11-28 01:42:57,940][87426] Updated weights for policy 1, policy_version 57330 (0.0008) -[2023-11-28 01:42:58,332][87426] Updated weights for policy 1, policy_version 57340 (0.0007) -[2023-11-28 01:42:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 29368320. Throughput: 0: 2720.6, 1: 2735.1. Samples: 29388356. Policy #0 lag: (min: 16.0, avg: 40.5, max: 48.0) -[2023-11-28 01:42:58,445][86177] Avg episode reward: [(0, '-527.900'), (1, '-509.670')] -[2023-11-28 01:42:59,178][87424] Updated weights for policy 0, policy_version 57416 (0.0012) -[2023-11-28 01:42:59,560][87424] Updated weights for policy 0, policy_version 57426 (0.0012) -[2023-11-28 01:42:59,937][87424] Updated weights for policy 0, policy_version 57436 (0.0011) -[2023-11-28 01:43:00,045][87426] Updated weights for policy 1, policy_version 57350 (0.0008) -[2023-11-28 01:43:00,430][87426] Updated weights for policy 1, policy_version 57360 (0.0012) -[2023-11-28 01:43:00,803][87426] Updated weights for policy 1, policy_version 57370 (0.0012) -[2023-11-28 01:43:02,220][87424] Updated weights for policy 0, policy_version 57446 (0.0012) -[2023-11-28 01:43:02,603][87424] Updated weights for policy 0, policy_version 57456 (0.0011) -[2023-11-28 01:43:02,636][87426] Updated weights for policy 1, policy_version 57380 (0.0010) -[2023-11-28 01:43:02,986][87424] Updated weights for policy 0, policy_version 57466 (0.0011) -[2023-11-28 01:43:03,025][87426] Updated weights for policy 1, policy_version 57390 (0.0009) -[2023-11-28 01:43:03,399][87426] Updated weights for policy 1, policy_version 57400 (0.0008) -[2023-11-28 01:43:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 29401088. Throughput: 0: 2744.1, 1: 2738.1. Samples: 29414192. Policy #0 lag: (min: 22.0, avg: 41.8, max: 86.0) -[2023-11-28 01:43:03,445][86177] Avg episode reward: [(0, '-529.220'), (1, '-509.640')] -[2023-11-28 01:43:05,270][87424] Updated weights for policy 0, policy_version 57476 (0.0010) -[2023-11-28 01:43:05,543][87426] Updated weights for policy 1, policy_version 57410 (0.0008) -[2023-11-28 01:43:05,651][87424] Updated weights for policy 0, policy_version 57486 (0.0011) -[2023-11-28 01:43:05,928][87426] Updated weights for policy 1, policy_version 57420 (0.0011) -[2023-11-28 01:43:06,031][87424] Updated weights for policy 0, policy_version 57496 (0.0011) -[2023-11-28 01:43:06,298][87426] Updated weights for policy 1, policy_version 57430 (0.0011) -[2023-11-28 01:43:06,691][87426] Updated weights for policy 1, policy_version 57440 (0.0012) -[2023-11-28 01:43:08,324][87424] Updated weights for policy 0, policy_version 57506 (0.0008) -[2023-11-28 01:43:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 29425664. Throughput: 0: 2731.5, 1: 2734.1. Samples: 29445700. Policy #0 lag: (min: 22.0, avg: 41.8, max: 86.0) -[2023-11-28 01:43:08,445][86177] Avg episode reward: [(0, '-530.160'), (1, '-512.100')] -[2023-11-28 01:43:08,703][87424] Updated weights for policy 0, policy_version 57516 (0.0008) -[2023-11-28 01:43:09,082][87424] Updated weights for policy 0, policy_version 57526 (0.0010) -[2023-11-28 01:43:09,110][87426] Updated weights for policy 1, policy_version 57450 (0.0011) -[2023-11-28 01:43:09,464][87424] Updated weights for policy 0, policy_version 57536 (0.0011) -[2023-11-28 01:43:09,495][87426] Updated weights for policy 1, policy_version 57460 (0.0010) -[2023-11-28 01:43:09,876][87426] Updated weights for policy 1, policy_version 57470 (0.0012) -[2023-11-28 01:43:11,473][87424] Updated weights for policy 0, policy_version 57546 (0.0011) -[2023-11-28 01:43:11,855][87424] Updated weights for policy 0, policy_version 57556 (0.0010) -[2023-11-28 01:43:12,236][87424] Updated weights for policy 0, policy_version 57566 (0.0009) -[2023-11-28 01:43:12,425][87426] Updated weights for policy 1, policy_version 57480 (0.0012) -[2023-11-28 01:43:12,808][87426] Updated weights for policy 1, policy_version 57490 (0.0012) -[2023-11-28 01:43:13,182][87426] Updated weights for policy 1, policy_version 57500 (0.0011) -[2023-11-28 01:43:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 29458432. Throughput: 0: 2729.1, 1: 2689.7. Samples: 29468584. Policy #0 lag: (min: 22.0, avg: 41.8, max: 86.0) -[2023-11-28 01:43:13,445][86177] Avg episode reward: [(0, '-520.690'), (1, '-513.870')] -[2023-11-28 01:43:14,622][87424] Updated weights for policy 0, policy_version 57576 (0.0008) -[2023-11-28 01:43:15,010][87424] Updated weights for policy 0, policy_version 57586 (0.0008) -[2023-11-28 01:43:15,394][87424] Updated weights for policy 0, policy_version 57596 (0.0008) -[2023-11-28 01:43:15,539][87426] Updated weights for policy 1, policy_version 57510 (0.0010) -[2023-11-28 01:43:15,921][87426] Updated weights for policy 1, policy_version 57520 (0.0007) -[2023-11-28 01:43:16,314][87426] Updated weights for policy 1, policy_version 57530 (0.0007) -[2023-11-28 01:43:17,696][87424] Updated weights for policy 0, policy_version 57606 (0.0009) -[2023-11-28 01:43:18,069][87424] Updated weights for policy 0, policy_version 57616 (0.0009) -[2023-11-28 01:43:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 29474816. Throughput: 0: 2710.6, 1: 2691.8. Samples: 29492812. Policy #0 lag: (min: 22.0, avg: 41.8, max: 86.0) -[2023-11-28 01:43:18,445][86177] Avg episode reward: [(0, '-503.270'), (1, '-508.130')] -[2023-11-28 01:43:18,458][87424] Updated weights for policy 0, policy_version 57626 (0.0010) -[2023-11-28 01:43:18,823][87426] Updated weights for policy 1, policy_version 57540 (0.0007) -[2023-11-28 01:43:19,206][87426] Updated weights for policy 1, policy_version 57550 (0.0007) -[2023-11-28 01:43:19,586][87426] Updated weights for policy 1, policy_version 57560 (0.0007) -[2023-11-28 01:43:20,968][87424] Updated weights for policy 0, policy_version 57636 (0.0009) -[2023-11-28 01:43:21,363][87424] Updated weights for policy 0, policy_version 57646 (0.0012) -[2023-11-28 01:43:21,744][87424] Updated weights for policy 0, policy_version 57656 (0.0011) -[2023-11-28 01:43:22,064][87426] Updated weights for policy 1, policy_version 57570 (0.0009) -[2023-11-28 01:43:22,444][87426] Updated weights for policy 1, policy_version 57580 (0.0009) -[2023-11-28 01:43:22,834][87426] Updated weights for policy 1, policy_version 57590 (0.0008) -[2023-11-28 01:43:23,206][87426] Updated weights for policy 1, policy_version 57600 (0.0008) -[2023-11-28 01:43:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 29507584. Throughput: 0: 2683.6, 1: 2628.8. Samples: 29522412. Policy #0 lag: (min: 22.0, avg: 41.8, max: 86.0) -[2023-11-28 01:43:23,445][86177] Avg episode reward: [(0, '-524.220'), (1, '-512.030')] -[2023-11-28 01:43:23,974][87424] Updated weights for policy 0, policy_version 57666 (0.0011) -[2023-11-28 01:43:24,356][87424] Updated weights for policy 0, policy_version 57676 (0.0012) -[2023-11-28 01:43:24,738][87424] Updated weights for policy 0, policy_version 57686 (0.0012) -[2023-11-28 01:43:25,117][87424] Updated weights for policy 0, policy_version 57696 (0.0010) -[2023-11-28 01:43:25,329][87426] Updated weights for policy 1, policy_version 57610 (0.0012) -[2023-11-28 01:43:25,730][87426] Updated weights for policy 1, policy_version 57620 (0.0012) -[2023-11-28 01:43:26,114][87426] Updated weights for policy 1, policy_version 57630 (0.0012) -[2023-11-28 01:43:27,272][87424] Updated weights for policy 0, policy_version 57706 (0.0011) -[2023-11-28 01:43:27,665][87424] Updated weights for policy 0, policy_version 57716 (0.0011) -[2023-11-28 01:43:27,789][87426] Updated weights for policy 1, policy_version 57640 (0.0009) -[2023-11-28 01:43:28,051][87424] Updated weights for policy 0, policy_version 57726 (0.0009) -[2023-11-28 01:43:28,173][87426] Updated weights for policy 1, policy_version 57650 (0.0009) -[2023-11-28 01:43:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 29532160. Throughput: 0: 2689.0, 1: 2662.9. Samples: 29547148. Policy #0 lag: (min: 22.0, avg: 41.8, max: 86.0) -[2023-11-28 01:43:28,445][86177] Avg episode reward: [(0, '-564.760'), (1, '-505.870')] -[2023-11-28 01:43:28,556][87426] Updated weights for policy 1, policy_version 57660 (0.0012) -[2023-11-28 01:43:30,192][87424] Updated weights for policy 0, policy_version 57736 (0.0011) -[2023-11-28 01:43:30,577][87424] Updated weights for policy 0, policy_version 57746 (0.0011) -[2023-11-28 01:43:30,635][87426] Updated weights for policy 1, policy_version 57670 (0.0011) -[2023-11-28 01:43:30,960][87424] Updated weights for policy 0, policy_version 57756 (0.0011) -[2023-11-28 01:43:31,008][87426] Updated weights for policy 1, policy_version 57680 (0.0010) -[2023-11-28 01:43:31,384][87426] Updated weights for policy 1, policy_version 57690 (0.0010) -[2023-11-28 01:43:33,386][87424] Updated weights for policy 0, policy_version 57766 (0.0009) -[2023-11-28 01:43:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 29556736. Throughput: 0: 2662.9, 1: 2674.4. Samples: 29571252. Policy #0 lag: (min: 22.0, avg: 41.8, max: 86.0) -[2023-11-28 01:43:33,446][86177] Avg episode reward: [(0, '-566.360'), (1, '-509.850')] -[2023-11-28 01:43:33,738][87426] Updated weights for policy 1, policy_version 57700 (0.0011) -[2023-11-28 01:43:33,778][87424] Updated weights for policy 0, policy_version 57776 (0.0009) -[2023-11-28 01:43:34,120][87426] Updated weights for policy 1, policy_version 57710 (0.0012) -[2023-11-28 01:43:34,155][87424] Updated weights for policy 0, policy_version 57786 (0.0009) -[2023-11-28 01:43:34,498][87426] Updated weights for policy 1, policy_version 57720 (0.0010) -[2023-11-28 01:43:36,398][87426] Updated weights for policy 1, policy_version 57730 (0.0009) -[2023-11-28 01:43:36,503][87424] Updated weights for policy 0, policy_version 57796 (0.0010) -[2023-11-28 01:43:36,778][87426] Updated weights for policy 1, policy_version 57740 (0.0009) -[2023-11-28 01:43:36,886][87424] Updated weights for policy 0, policy_version 57806 (0.0012) -[2023-11-28 01:43:37,159][87426] Updated weights for policy 1, policy_version 57750 (0.0007) -[2023-11-28 01:43:37,281][87424] Updated weights for policy 0, policy_version 57816 (0.0012) -[2023-11-28 01:43:37,541][87426] Updated weights for policy 1, policy_version 57760 (0.0009) -[2023-11-28 01:43:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 29589504. Throughput: 0: 2663.3, 1: 2670.6. Samples: 29603352. Policy #0 lag: (min: 22.0, avg: 41.8, max: 86.0) -[2023-11-28 01:43:38,445][86177] Avg episode reward: [(0, '-567.090'), (1, '-510.520')] -[2023-11-28 01:43:39,247][87424] Updated weights for policy 0, policy_version 57826 (0.0012) -[2023-11-28 01:43:39,632][87424] Updated weights for policy 0, policy_version 57836 (0.0012) -[2023-11-28 01:43:39,759][87426] Updated weights for policy 1, policy_version 57770 (0.0011) -[2023-11-28 01:43:40,014][87424] Updated weights for policy 0, policy_version 57846 (0.0011) -[2023-11-28 01:43:40,133][87426] Updated weights for policy 1, policy_version 57780 (0.0011) -[2023-11-28 01:43:40,392][87424] Updated weights for policy 0, policy_version 57856 (0.0011) -[2023-11-28 01:43:40,522][87426] Updated weights for policy 1, policy_version 57790 (0.0011) -[2023-11-28 01:43:42,813][87424] Updated weights for policy 0, policy_version 57866 (0.0011) -[2023-11-28 01:43:42,816][87426] Updated weights for policy 1, policy_version 57800 (0.0010) -[2023-11-28 01:43:43,188][87426] Updated weights for policy 1, policy_version 57810 (0.0008) -[2023-11-28 01:43:43,189][87424] Updated weights for policy 0, policy_version 57876 (0.0010) -[2023-11-28 01:43:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 29605888. Throughput: 0: 2648.1, 1: 2677.0. Samples: 29627984. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 01:43:43,445][86177] Avg episode reward: [(0, '-546.200'), (1, '-511.000')] -[2023-11-28 01:43:43,563][87426] Updated weights for policy 1, policy_version 57820 (0.0008) -[2023-11-28 01:43:43,583][87424] Updated weights for policy 0, policy_version 57886 (0.0008) -[2023-11-28 01:43:45,625][87426] Updated weights for policy 1, policy_version 57830 (0.0011) -[2023-11-28 01:43:45,736][87424] Updated weights for policy 0, policy_version 57896 (0.0011) -[2023-11-28 01:43:46,005][87426] Updated weights for policy 1, policy_version 57840 (0.0011) -[2023-11-28 01:43:46,119][87424] Updated weights for policy 0, policy_version 57906 (0.0011) -[2023-11-28 01:43:46,384][87426] Updated weights for policy 1, policy_version 57850 (0.0009) -[2023-11-28 01:43:46,500][87424] Updated weights for policy 0, policy_version 57916 (0.0007) -[2023-11-28 01:43:48,268][87426] Updated weights for policy 1, policy_version 57860 (0.0011) -[2023-11-28 01:43:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 29638656. Throughput: 0: 2618.4, 1: 2665.2. Samples: 29651952. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 01:43:48,445][86177] Avg episode reward: [(0, '-519.010'), (1, '-510.850')] -[2023-11-28 01:43:48,646][87426] Updated weights for policy 1, policy_version 57870 (0.0010) -[2023-11-28 01:43:48,972][87424] Updated weights for policy 0, policy_version 57926 (0.0008) -[2023-11-28 01:43:49,022][87426] Updated weights for policy 1, policy_version 57880 (0.0009) -[2023-11-28 01:43:49,359][87424] Updated weights for policy 0, policy_version 57936 (0.0011) -[2023-11-28 01:43:49,744][87424] Updated weights for policy 0, policy_version 57946 (0.0012) -[2023-11-28 01:43:51,539][87426] Updated weights for policy 1, policy_version 57890 (0.0010) -[2023-11-28 01:43:51,921][87426] Updated weights for policy 1, policy_version 57900 (0.0008) -[2023-11-28 01:43:52,276][87424] Updated weights for policy 0, policy_version 57956 (0.0013) -[2023-11-28 01:43:52,296][87426] Updated weights for policy 1, policy_version 57910 (0.0012) -[2023-11-28 01:43:52,659][87424] Updated weights for policy 0, policy_version 57966 (0.0008) -[2023-11-28 01:43:52,677][87426] Updated weights for policy 1, policy_version 57920 (0.0008) -[2023-11-28 01:43:53,038][87424] Updated weights for policy 0, policy_version 57976 (0.0008) -[2023-11-28 01:43:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 29671424. Throughput: 0: 2627.3, 1: 2682.6. Samples: 29684644. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 01:43:53,445][86177] Avg episode reward: [(0, '-518.540'), (1, '-508.190')] -[2023-11-28 01:43:54,643][87426] Updated weights for policy 1, policy_version 57930 (0.0009) -[2023-11-28 01:43:55,037][87426] Updated weights for policy 1, policy_version 57940 (0.0007) -[2023-11-28 01:43:55,415][87426] Updated weights for policy 1, policy_version 57950 (0.0008) -[2023-11-28 01:43:55,598][87424] Updated weights for policy 0, policy_version 57986 (0.0010) -[2023-11-28 01:43:55,983][87424] Updated weights for policy 0, policy_version 57996 (0.0012) -[2023-11-28 01:43:56,364][87424] Updated weights for policy 0, policy_version 58006 (0.0012) -[2023-11-28 01:43:56,759][87424] Updated weights for policy 0, policy_version 58016 (0.0008) -[2023-11-28 01:43:57,431][87426] Updated weights for policy 1, policy_version 57960 (0.0008) -[2023-11-28 01:43:57,813][87426] Updated weights for policy 1, policy_version 57970 (0.0008) -[2023-11-28 01:43:58,190][87426] Updated weights for policy 1, policy_version 57980 (0.0007) -[2023-11-28 01:43:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 29696000. Throughput: 0: 2606.9, 1: 2717.4. Samples: 29708180. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 01:43:58,445][86177] Avg episode reward: [(0, '-527.430'), (1, '-504.350')] -[2023-11-28 01:43:59,188][87424] Updated weights for policy 0, policy_version 58026 (0.0008) -[2023-11-28 01:43:59,579][87424] Updated weights for policy 0, policy_version 58036 (0.0008) -[2023-11-28 01:43:59,955][87424] Updated weights for policy 0, policy_version 58046 (0.0009) -[2023-11-28 01:44:00,601][87426] Updated weights for policy 1, policy_version 57990 (0.0010) -[2023-11-28 01:44:00,986][87426] Updated weights for policy 1, policy_version 58000 (0.0011) -[2023-11-28 01:44:01,377][87426] Updated weights for policy 1, policy_version 58010 (0.0011) -[2023-11-28 01:44:01,785][87424] Updated weights for policy 0, policy_version 58056 (0.0009) -[2023-11-28 01:44:02,166][87424] Updated weights for policy 0, policy_version 58066 (0.0013) -[2023-11-28 01:44:02,549][87424] Updated weights for policy 0, policy_version 58076 (0.0008) -[2023-11-28 01:44:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 29720576. Throughput: 0: 2597.8, 1: 2701.1. Samples: 29731260. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 01:44:03,445][86177] Avg episode reward: [(0, '-524.180'), (1, '-501.340')] -[2023-11-28 01:44:03,690][87426] Updated weights for policy 1, policy_version 58020 (0.0011) -[2023-11-28 01:44:04,071][87426] Updated weights for policy 1, policy_version 58030 (0.0008) -[2023-11-28 01:44:04,452][87426] Updated weights for policy 1, policy_version 58040 (0.0010) -[2023-11-28 01:44:04,688][87424] Updated weights for policy 0, policy_version 58086 (0.0010) -[2023-11-28 01:44:05,076][87424] Updated weights for policy 0, policy_version 58096 (0.0008) -[2023-11-28 01:44:05,476][87424] Updated weights for policy 0, policy_version 58106 (0.0009) -[2023-11-28 01:44:06,810][87426] Updated weights for policy 1, policy_version 58050 (0.0011) -[2023-11-28 01:44:07,189][87426] Updated weights for policy 1, policy_version 58060 (0.0012) -[2023-11-28 01:44:07,527][87424] Updated weights for policy 0, policy_version 58116 (0.0010) -[2023-11-28 01:44:07,563][87426] Updated weights for policy 1, policy_version 58070 (0.0011) -[2023-11-28 01:44:07,911][87424] Updated weights for policy 0, policy_version 58126 (0.0010) -[2023-11-28 01:44:07,944][87426] Updated weights for policy 1, policy_version 58080 (0.0011) -[2023-11-28 01:44:08,287][87424] Updated weights for policy 0, policy_version 58136 (0.0008) -[2023-11-28 01:44:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 29745152. Throughput: 0: 2648.9, 1: 2733.2. Samples: 29764608. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 01:44:08,445][86177] Avg episode reward: [(0, '-534.920'), (1, '-498.940')] -[2023-11-28 01:44:10,112][87426] Updated weights for policy 1, policy_version 58090 (0.0008) -[2023-11-28 01:44:10,500][87426] Updated weights for policy 1, policy_version 58100 (0.0009) -[2023-11-28 01:44:10,501][87424] Updated weights for policy 0, policy_version 58146 (0.0008) -[2023-11-28 01:44:10,877][87424] Updated weights for policy 0, policy_version 58156 (0.0011) -[2023-11-28 01:44:10,886][87426] Updated weights for policy 1, policy_version 58110 (0.0012) -[2023-11-28 01:44:11,260][87424] Updated weights for policy 0, policy_version 58166 (0.0012) -[2023-11-28 01:44:11,635][87424] Updated weights for policy 0, policy_version 58176 (0.0012) -[2023-11-28 01:44:13,214][87426] Updated weights for policy 1, policy_version 58120 (0.0008) -[2023-11-28 01:44:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 29769728. Throughput: 0: 2641.5, 1: 2714.4. Samples: 29788164. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 01:44:13,445][86177] Avg episode reward: [(0, '-533.430'), (1, '-504.680')] -[2023-11-28 01:44:13,594][87426] Updated weights for policy 1, policy_version 58130 (0.0007) -[2023-11-28 01:44:13,656][87424] Updated weights for policy 0, policy_version 58186 (0.0012) -[2023-11-28 01:44:13,971][87426] Updated weights for policy 1, policy_version 58140 (0.0007) -[2023-11-28 01:44:14,043][87424] Updated weights for policy 0, policy_version 58196 (0.0011) -[2023-11-28 01:44:14,421][87424] Updated weights for policy 0, policy_version 58206 (0.0011) -[2023-11-28 01:44:16,067][87426] Updated weights for policy 1, policy_version 58150 (0.0007) -[2023-11-28 01:44:16,452][87426] Updated weights for policy 1, policy_version 58160 (0.0010) -[2023-11-28 01:44:16,838][87426] Updated weights for policy 1, policy_version 58170 (0.0011) -[2023-11-28 01:44:16,934][87424] Updated weights for policy 0, policy_version 58216 (0.0008) -[2023-11-28 01:44:17,309][87424] Updated weights for policy 0, policy_version 58226 (0.0007) -[2023-11-28 01:44:17,694][87424] Updated weights for policy 0, policy_version 58236 (0.0008) -[2023-11-28 01:44:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 29802496. Throughput: 0: 2649.8, 1: 2716.3. Samples: 29812724. Policy #0 lag: (min: 40.0, avg: 63.4, max: 90.0) -[2023-11-28 01:44:18,445][86177] Avg episode reward: [(0, '-523.620'), (1, '-508.900')] -[2023-11-28 01:44:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000058176_14893056.pth... -[2023-11-28 01:44:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000058240_14909440.pth... -[2023-11-28 01:44:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000055648_14245888.pth -[2023-11-28 01:44:18,493][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000055744_14270464.pth -[2023-11-28 01:44:19,251][87426] Updated weights for policy 1, policy_version 58180 (0.0009) -[2023-11-28 01:44:19,629][87426] Updated weights for policy 1, policy_version 58190 (0.0012) -[2023-11-28 01:44:20,007][87426] Updated weights for policy 1, policy_version 58200 (0.0011) -[2023-11-28 01:44:20,065][87424] Updated weights for policy 0, policy_version 58246 (0.0008) -[2023-11-28 01:44:20,445][87424] Updated weights for policy 0, policy_version 58256 (0.0011) -[2023-11-28 01:44:20,817][87424] Updated weights for policy 0, policy_version 58266 (0.0011) -[2023-11-28 01:44:22,531][87426] Updated weights for policy 1, policy_version 58210 (0.0011) -[2023-11-28 01:44:22,910][87426] Updated weights for policy 1, policy_version 58220 (0.0012) -[2023-11-28 01:44:23,097][87424] Updated weights for policy 0, policy_version 58276 (0.0009) -[2023-11-28 01:44:23,295][87426] Updated weights for policy 1, policy_version 58230 (0.0011) -[2023-11-28 01:44:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 29818880. Throughput: 0: 2636.2, 1: 2709.0. Samples: 29843884. Policy #0 lag: (min: 40.0, avg: 63.4, max: 90.0) -[2023-11-28 01:44:23,445][86177] Avg episode reward: [(0, '-515.970'), (1, '-519.110')] -[2023-11-28 01:44:23,476][87424] Updated weights for policy 0, policy_version 58286 (0.0011) -[2023-11-28 01:44:23,666][87426] Updated weights for policy 1, policy_version 58240 (0.0012) -[2023-11-28 01:44:23,868][87424] Updated weights for policy 0, policy_version 58296 (0.0009) -[2023-11-28 01:44:26,020][87426] Updated weights for policy 1, policy_version 58250 (0.0011) -[2023-11-28 01:44:26,076][87424] Updated weights for policy 0, policy_version 58306 (0.0009) -[2023-11-28 01:44:26,407][87426] Updated weights for policy 1, policy_version 58260 (0.0012) -[2023-11-28 01:44:26,461][87424] Updated weights for policy 0, policy_version 58316 (0.0007) -[2023-11-28 01:44:26,796][87426] Updated weights for policy 1, policy_version 58270 (0.0011) -[2023-11-28 01:44:26,852][87424] Updated weights for policy 0, policy_version 58326 (0.0008) -[2023-11-28 01:44:27,229][87424] Updated weights for policy 0, policy_version 58336 (0.0012) -[2023-11-28 01:44:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 29851648. Throughput: 0: 2632.8, 1: 2717.5. Samples: 29868748. Policy #0 lag: (min: 40.0, avg: 63.4, max: 90.0) -[2023-11-28 01:44:28,445][86177] Avg episode reward: [(0, '-504.030'), (1, '-517.400')] -[2023-11-28 01:44:28,599][87426] Updated weights for policy 1, policy_version 58280 (0.0012) -[2023-11-28 01:44:28,981][87426] Updated weights for policy 1, policy_version 58290 (0.0009) -[2023-11-28 01:44:29,073][87424] Updated weights for policy 0, policy_version 58346 (0.0012) -[2023-11-28 01:44:29,365][87426] Updated weights for policy 1, policy_version 58300 (0.0010) -[2023-11-28 01:44:29,455][87424] Updated weights for policy 0, policy_version 58356 (0.0010) -[2023-11-28 01:44:29,838][87424] Updated weights for policy 0, policy_version 58366 (0.0008) -[2023-11-28 01:44:31,334][87426] Updated weights for policy 1, policy_version 58310 (0.0011) -[2023-11-28 01:44:31,718][87426] Updated weights for policy 1, policy_version 58320 (0.0010) -[2023-11-28 01:44:31,766][87424] Updated weights for policy 0, policy_version 58376 (0.0011) -[2023-11-28 01:44:32,089][87426] Updated weights for policy 1, policy_version 58330 (0.0010) -[2023-11-28 01:44:32,145][87424] Updated weights for policy 0, policy_version 58386 (0.0011) -[2023-11-28 01:44:32,520][87424] Updated weights for policy 0, policy_version 58396 (0.0009) -[2023-11-28 01:44:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 29884416. Throughput: 0: 2669.2, 1: 2721.4. Samples: 29894532. Policy #0 lag: (min: 40.0, avg: 63.4, max: 90.0) -[2023-11-28 01:44:33,445][86177] Avg episode reward: [(0, '-509.070'), (1, '-511.530')] -[2023-11-28 01:44:34,462][87426] Updated weights for policy 1, policy_version 58340 (0.0010) -[2023-11-28 01:44:34,510][87424] Updated weights for policy 0, policy_version 58406 (0.0008) -[2023-11-28 01:44:34,842][87426] Updated weights for policy 1, policy_version 58350 (0.0009) -[2023-11-28 01:44:34,891][87424] Updated weights for policy 0, policy_version 58416 (0.0010) -[2023-11-28 01:44:35,228][87426] Updated weights for policy 1, policy_version 58360 (0.0012) -[2023-11-28 01:44:35,274][87424] Updated weights for policy 0, policy_version 58426 (0.0010) -[2023-11-28 01:44:37,239][87426] Updated weights for policy 1, policy_version 58370 (0.0012) -[2023-11-28 01:44:37,501][87424] Updated weights for policy 0, policy_version 58436 (0.0010) -[2023-11-28 01:44:37,610][87426] Updated weights for policy 1, policy_version 58380 (0.0011) -[2023-11-28 01:44:37,885][87424] Updated weights for policy 0, policy_version 58446 (0.0009) -[2023-11-28 01:44:37,992][87426] Updated weights for policy 1, policy_version 58390 (0.0012) -[2023-11-28 01:44:38,271][87424] Updated weights for policy 0, policy_version 58456 (0.0008) -[2023-11-28 01:44:38,386][87426] Updated weights for policy 1, policy_version 58400 (0.0011) -[2023-11-28 01:44:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 29908992. Throughput: 0: 2696.8, 1: 2698.0. Samples: 29927408. Policy #0 lag: (min: 40.0, avg: 63.4, max: 90.0) -[2023-11-28 01:44:38,445][86177] Avg episode reward: [(0, '-508.910'), (1, '-511.360')] -[2023-11-28 01:44:40,594][87424] Updated weights for policy 0, policy_version 58466 (0.0008) -[2023-11-28 01:44:40,884][87426] Updated weights for policy 1, policy_version 58410 (0.0009) -[2023-11-28 01:44:40,972][87424] Updated weights for policy 0, policy_version 58476 (0.0012) -[2023-11-28 01:44:41,253][87426] Updated weights for policy 1, policy_version 58420 (0.0008) -[2023-11-28 01:44:41,350][87424] Updated weights for policy 0, policy_version 58486 (0.0010) -[2023-11-28 01:44:41,633][87426] Updated weights for policy 1, policy_version 58430 (0.0009) -[2023-11-28 01:44:41,736][87424] Updated weights for policy 0, policy_version 58496 (0.0009) -[2023-11-28 01:44:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 29933568. Throughput: 0: 2701.5, 1: 2689.6. Samples: 29950780. Policy #0 lag: (min: 40.0, avg: 63.4, max: 90.0) -[2023-11-28 01:44:43,445][86177] Avg episode reward: [(0, '-510.120'), (1, '-502.140')] -[2023-11-28 01:44:43,745][87426] Updated weights for policy 1, policy_version 58440 (0.0011) -[2023-11-28 01:44:43,849][87424] Updated weights for policy 0, policy_version 58506 (0.0011) -[2023-11-28 01:44:44,133][87426] Updated weights for policy 1, policy_version 58450 (0.0012) -[2023-11-28 01:44:44,233][87424] Updated weights for policy 0, policy_version 58516 (0.0009) -[2023-11-28 01:44:44,528][87426] Updated weights for policy 1, policy_version 58460 (0.0012) -[2023-11-28 01:44:44,625][87424] Updated weights for policy 0, policy_version 58526 (0.0007) -[2023-11-28 01:44:46,068][87426] Updated weights for policy 1, policy_version 58470 (0.0012) -[2023-11-28 01:44:46,446][87426] Updated weights for policy 1, policy_version 58480 (0.0008) -[2023-11-28 01:44:46,827][87426] Updated weights for policy 1, policy_version 58490 (0.0009) -[2023-11-28 01:44:47,027][87424] Updated weights for policy 0, policy_version 58536 (0.0008) -[2023-11-28 01:44:47,412][87424] Updated weights for policy 0, policy_version 58546 (0.0009) -[2023-11-28 01:44:47,797][87424] Updated weights for policy 0, policy_version 58556 (0.0009) -[2023-11-28 01:44:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 29966336. Throughput: 0: 2702.7, 1: 2720.9. Samples: 29975320. Policy #0 lag: (min: 40.0, avg: 63.4, max: 90.0) -[2023-11-28 01:44:48,445][86177] Avg episode reward: [(0, '-508.490'), (1, '-501.980')] -[2023-11-28 01:44:48,792][87426] Updated weights for policy 1, policy_version 58500 (0.0011) -[2023-11-28 01:44:49,163][87426] Updated weights for policy 1, policy_version 58510 (0.0011) -[2023-11-28 01:44:49,538][87426] Updated weights for policy 1, policy_version 58520 (0.0011) -[2023-11-28 01:44:49,633][87424] Updated weights for policy 0, policy_version 58566 (0.0010) -[2023-11-28 01:44:50,014][87424] Updated weights for policy 0, policy_version 58576 (0.0010) -[2023-11-28 01:44:50,399][87424] Updated weights for policy 0, policy_version 58586 (0.0011) -[2023-11-28 01:44:51,606][87426] Updated weights for policy 1, policy_version 58530 (0.0011) -[2023-11-28 01:44:51,981][87426] Updated weights for policy 1, policy_version 58540 (0.0009) -[2023-11-28 01:44:52,361][87426] Updated weights for policy 1, policy_version 58550 (0.0010) -[2023-11-28 01:44:52,730][87426] Updated weights for policy 1, policy_version 58560 (0.0011) -[2023-11-28 01:44:52,873][87424] Updated weights for policy 0, policy_version 58596 (0.0009) -[2023-11-28 01:44:53,259][87424] Updated weights for policy 0, policy_version 58606 (0.0010) -[2023-11-28 01:44:53,446][86177] Fps is (10 sec: 5733.7, 60 sec: 5324.7, 300 sec: 5387.3). Total num frames: 29990912. Throughput: 0: 2689.0, 1: 2726.3. Samples: 30008304. Policy #0 lag: (min: 40.0, avg: 63.4, max: 90.0) -[2023-11-28 01:44:53,446][86177] Avg episode reward: [(0, '-506.820'), (1, '-500.130')] -[2023-11-28 01:44:53,644][87424] Updated weights for policy 0, policy_version 58616 (0.0009) -[2023-11-28 01:44:55,239][87426] Updated weights for policy 1, policy_version 58570 (0.0012) -[2023-11-28 01:44:55,626][87426] Updated weights for policy 1, policy_version 58580 (0.0012) -[2023-11-28 01:44:56,007][87426] Updated weights for policy 1, policy_version 58590 (0.0012) -[2023-11-28 01:44:56,125][87424] Updated weights for policy 0, policy_version 58626 (0.0011) -[2023-11-28 01:44:56,508][87424] Updated weights for policy 0, policy_version 58636 (0.0012) -[2023-11-28 01:44:56,890][87424] Updated weights for policy 0, policy_version 58646 (0.0008) -[2023-11-28 01:44:57,271][87424] Updated weights for policy 0, policy_version 58656 (0.0009) -[2023-11-28 01:44:57,875][87426] Updated weights for policy 1, policy_version 58600 (0.0012) -[2023-11-28 01:44:58,249][87426] Updated weights for policy 1, policy_version 58610 (0.0008) -[2023-11-28 01:44:58,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 30015488. Throughput: 0: 2692.6, 1: 2735.4. Samples: 30032424. Policy #0 lag: (min: 26.0, avg: 50.5, max: 58.0) -[2023-11-28 01:44:58,446][86177] Avg episode reward: [(0, '-516.630'), (1, '-499.040')] -[2023-11-28 01:44:58,631][87426] Updated weights for policy 1, policy_version 58620 (0.0008) -[2023-11-28 01:44:59,446][87424] Updated weights for policy 0, policy_version 58666 (0.0008) -[2023-11-28 01:44:59,831][87424] Updated weights for policy 0, policy_version 58676 (0.0009) -[2023-11-28 01:45:00,212][87424] Updated weights for policy 0, policy_version 58686 (0.0012) -[2023-11-28 01:45:00,825][87426] Updated weights for policy 1, policy_version 58630 (0.0007) -[2023-11-28 01:45:01,215][87426] Updated weights for policy 1, policy_version 58640 (0.0008) -[2023-11-28 01:45:01,609][87426] Updated weights for policy 1, policy_version 58650 (0.0011) -[2023-11-28 01:45:02,110][87424] Updated weights for policy 0, policy_version 58696 (0.0012) -[2023-11-28 01:45:02,488][87424] Updated weights for policy 0, policy_version 58706 (0.0009) -[2023-11-28 01:45:02,877][87424] Updated weights for policy 0, policy_version 58716 (0.0008) -[2023-11-28 01:45:03,444][86177] Fps is (10 sec: 5735.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 30048256. Throughput: 0: 2709.4, 1: 2731.6. Samples: 30057568. Policy #0 lag: (min: 26.0, avg: 50.5, max: 58.0) -[2023-11-28 01:45:03,445][86177] Avg episode reward: [(0, '-527.870'), (1, '-497.680')] -[2023-11-28 01:45:03,677][87426] Updated weights for policy 1, policy_version 58660 (0.0012) -[2023-11-28 01:45:04,052][87426] Updated weights for policy 1, policy_version 58670 (0.0011) -[2023-11-28 01:45:04,432][87426] Updated weights for policy 1, policy_version 58680 (0.0012) -[2023-11-28 01:45:04,723][87424] Updated weights for policy 0, policy_version 58726 (0.0010) -[2023-11-28 01:45:05,092][87424] Updated weights for policy 0, policy_version 58736 (0.0012) -[2023-11-28 01:45:05,471][87424] Updated weights for policy 0, policy_version 58746 (0.0012) -[2023-11-28 01:45:06,744][87426] Updated weights for policy 1, policy_version 58690 (0.0011) -[2023-11-28 01:45:07,119][87426] Updated weights for policy 1, policy_version 58700 (0.0011) -[2023-11-28 01:45:07,420][87424] Updated weights for policy 0, policy_version 58756 (0.0012) -[2023-11-28 01:45:07,494][87426] Updated weights for policy 1, policy_version 58710 (0.0011) -[2023-11-28 01:45:07,808][87424] Updated weights for policy 0, policy_version 58766 (0.0012) -[2023-11-28 01:45:07,870][87426] Updated weights for policy 1, policy_version 58720 (0.0012) -[2023-11-28 01:45:08,183][87424] Updated weights for policy 0, policy_version 58776 (0.0012) -[2023-11-28 01:45:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30072832. Throughput: 0: 2737.9, 1: 2741.1. Samples: 30090444. Policy #0 lag: (min: 26.0, avg: 50.5, max: 58.0) -[2023-11-28 01:45:08,445][86177] Avg episode reward: [(0, '-529.860'), (1, '-498.590')] -[2023-11-28 01:45:10,020][87424] Updated weights for policy 0, policy_version 58786 (0.0012) -[2023-11-28 01:45:10,242][87426] Updated weights for policy 1, policy_version 58730 (0.0009) -[2023-11-28 01:45:10,415][87424] Updated weights for policy 0, policy_version 58796 (0.0010) -[2023-11-28 01:45:10,619][87426] Updated weights for policy 1, policy_version 58740 (0.0010) -[2023-11-28 01:45:10,793][87424] Updated weights for policy 0, policy_version 58806 (0.0011) -[2023-11-28 01:45:11,005][87426] Updated weights for policy 1, policy_version 58750 (0.0011) -[2023-11-28 01:45:11,177][87424] Updated weights for policy 0, policy_version 58816 (0.0010) -[2023-11-28 01:45:13,310][87426] Updated weights for policy 1, policy_version 58760 (0.0012) -[2023-11-28 01:45:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30097408. Throughput: 0: 2747.4, 1: 2713.0. Samples: 30114464. Policy #0 lag: (min: 26.0, avg: 50.5, max: 58.0) -[2023-11-28 01:45:13,445][86177] Avg episode reward: [(0, '-530.390'), (1, '-498.680')] -[2023-11-28 01:45:13,665][87424] Updated weights for policy 0, policy_version 58826 (0.0008) -[2023-11-28 01:45:13,689][87426] Updated weights for policy 1, policy_version 58770 (0.0012) -[2023-11-28 01:45:14,046][87424] Updated weights for policy 0, policy_version 58836 (0.0007) -[2023-11-28 01:45:14,077][87426] Updated weights for policy 1, policy_version 58780 (0.0009) -[2023-11-28 01:45:14,427][87424] Updated weights for policy 0, policy_version 58846 (0.0008) -[2023-11-28 01:45:16,583][87424] Updated weights for policy 0, policy_version 58856 (0.0011) -[2023-11-28 01:45:16,641][87426] Updated weights for policy 1, policy_version 58790 (0.0009) -[2023-11-28 01:45:16,962][87424] Updated weights for policy 0, policy_version 58866 (0.0012) -[2023-11-28 01:45:17,017][87426] Updated weights for policy 1, policy_version 58800 (0.0007) -[2023-11-28 01:45:17,344][87424] Updated weights for policy 0, policy_version 58876 (0.0010) -[2023-11-28 01:45:17,401][87426] Updated weights for policy 1, policy_version 58810 (0.0009) -[2023-11-28 01:45:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30130176. Throughput: 0: 2730.6, 1: 2715.0. Samples: 30139584. Policy #0 lag: (min: 26.0, avg: 50.5, max: 58.0) -[2023-11-28 01:45:18,445][86177] Avg episode reward: [(0, '-532.350'), (1, '-500.400')] -[2023-11-28 01:45:19,463][87426] Updated weights for policy 1, policy_version 58820 (0.0008) -[2023-11-28 01:45:19,615][87424] Updated weights for policy 0, policy_version 58886 (0.0007) -[2023-11-28 01:45:19,850][87426] Updated weights for policy 1, policy_version 58830 (0.0010) -[2023-11-28 01:45:19,995][87424] Updated weights for policy 0, policy_version 58896 (0.0008) -[2023-11-28 01:45:20,230][87426] Updated weights for policy 1, policy_version 58840 (0.0011) -[2023-11-28 01:45:20,381][87424] Updated weights for policy 0, policy_version 58906 (0.0009) -[2023-11-28 01:45:22,547][87426] Updated weights for policy 1, policy_version 58850 (0.0012) -[2023-11-28 01:45:22,655][87424] Updated weights for policy 0, policy_version 58916 (0.0014) -[2023-11-28 01:45:22,928][87426] Updated weights for policy 1, policy_version 58860 (0.0012) -[2023-11-28 01:45:23,041][87424] Updated weights for policy 0, policy_version 58926 (0.0012) -[2023-11-28 01:45:23,300][87426] Updated weights for policy 1, policy_version 58870 (0.0011) -[2023-11-28 01:45:23,424][87424] Updated weights for policy 0, policy_version 58936 (0.0012) -[2023-11-28 01:45:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 30146560. Throughput: 0: 2704.4, 1: 2706.6. Samples: 30170900. Policy #0 lag: (min: 26.0, avg: 50.5, max: 58.0) -[2023-11-28 01:45:23,445][86177] Avg episode reward: [(0, '-519.900'), (1, '-502.200')] -[2023-11-28 01:45:23,681][87426] Updated weights for policy 1, policy_version 58880 (0.0010) -[2023-11-28 01:45:25,393][87424] Updated weights for policy 0, policy_version 58946 (0.0011) -[2023-11-28 01:45:25,769][87426] Updated weights for policy 1, policy_version 58890 (0.0012) -[2023-11-28 01:45:25,783][87424] Updated weights for policy 0, policy_version 58956 (0.0011) -[2023-11-28 01:45:26,139][87426] Updated weights for policy 1, policy_version 58900 (0.0011) -[2023-11-28 01:45:26,157][87424] Updated weights for policy 0, policy_version 58966 (0.0012) -[2023-11-28 01:45:26,518][87426] Updated weights for policy 1, policy_version 58910 (0.0011) -[2023-11-28 01:45:26,534][87424] Updated weights for policy 0, policy_version 58976 (0.0007) -[2023-11-28 01:45:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30179328. Throughput: 0: 2724.8, 1: 2707.5. Samples: 30195232. Policy #0 lag: (min: 26.0, avg: 50.5, max: 58.0) -[2023-11-28 01:45:28,446][86177] Avg episode reward: [(0, '-517.860'), (1, '-508.700')] -[2023-11-28 01:45:28,914][87426] Updated weights for policy 1, policy_version 58920 (0.0009) -[2023-11-28 01:45:29,064][87424] Updated weights for policy 0, policy_version 58986 (0.0011) -[2023-11-28 01:45:29,290][87426] Updated weights for policy 1, policy_version 58930 (0.0008) -[2023-11-28 01:45:29,437][87424] Updated weights for policy 0, policy_version 58996 (0.0011) -[2023-11-28 01:45:29,669][87426] Updated weights for policy 1, policy_version 58940 (0.0009) -[2023-11-28 01:45:29,816][87424] Updated weights for policy 0, policy_version 59006 (0.0012) -[2023-11-28 01:45:31,734][87426] Updated weights for policy 1, policy_version 58950 (0.0012) -[2023-11-28 01:45:32,026][87424] Updated weights for policy 0, policy_version 59016 (0.0012) -[2023-11-28 01:45:32,112][87426] Updated weights for policy 1, policy_version 58960 (0.0009) -[2023-11-28 01:45:32,411][87424] Updated weights for policy 0, policy_version 59026 (0.0011) -[2023-11-28 01:45:32,492][87426] Updated weights for policy 1, policy_version 58970 (0.0010) -[2023-11-28 01:45:32,795][87424] Updated weights for policy 0, policy_version 59036 (0.0012) -[2023-11-28 01:45:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30212096. Throughput: 0: 2753.5, 1: 2691.0. Samples: 30220324. Policy #0 lag: (min: 26.0, avg: 50.5, max: 58.0) -[2023-11-28 01:45:33,445][86177] Avg episode reward: [(0, '-515.080'), (1, '-510.690')] -[2023-11-28 01:45:34,524][87426] Updated weights for policy 1, policy_version 58980 (0.0011) -[2023-11-28 01:45:34,572][87424] Updated weights for policy 0, policy_version 59046 (0.0012) -[2023-11-28 01:45:34,912][87426] Updated weights for policy 1, policy_version 58990 (0.0012) -[2023-11-28 01:45:34,955][87424] Updated weights for policy 0, policy_version 59056 (0.0012) -[2023-11-28 01:45:35,284][87426] Updated weights for policy 1, policy_version 59000 (0.0012) -[2023-11-28 01:45:35,346][87424] Updated weights for policy 0, policy_version 59066 (0.0012) -[2023-11-28 01:45:37,003][87424] Updated weights for policy 0, policy_version 59076 (0.0012) -[2023-11-28 01:45:37,385][87424] Updated weights for policy 0, policy_version 59086 (0.0012) -[2023-11-28 01:45:37,751][87426] Updated weights for policy 1, policy_version 59010 (0.0012) -[2023-11-28 01:45:37,764][87424] Updated weights for policy 0, policy_version 59096 (0.0012) -[2023-11-28 01:45:38,124][87426] Updated weights for policy 1, policy_version 59020 (0.0011) -[2023-11-28 01:45:38,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30236672. Throughput: 0: 2760.9, 1: 2720.4. Samples: 30254956. Policy #0 lag: (min: 28.0, avg: 33.5, max: 44.0) -[2023-11-28 01:45:38,445][86177] Avg episode reward: [(0, '-536.390'), (1, '-513.080')] -[2023-11-28 01:45:38,504][87426] Updated weights for policy 1, policy_version 59030 (0.0012) -[2023-11-28 01:45:38,883][87426] Updated weights for policy 1, policy_version 59040 (0.0011) -[2023-11-28 01:45:40,262][87424] Updated weights for policy 0, policy_version 59106 (0.0012) -[2023-11-28 01:45:40,644][87424] Updated weights for policy 0, policy_version 59116 (0.0011) -[2023-11-28 01:45:40,742][87426] Updated weights for policy 1, policy_version 59050 (0.0011) -[2023-11-28 01:45:41,029][87424] Updated weights for policy 0, policy_version 59126 (0.0012) -[2023-11-28 01:45:41,122][87426] Updated weights for policy 1, policy_version 59060 (0.0009) -[2023-11-28 01:45:41,403][87424] Updated weights for policy 0, policy_version 59136 (0.0010) -[2023-11-28 01:45:41,501][87426] Updated weights for policy 1, policy_version 59070 (0.0010) -[2023-11-28 01:45:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30261248. Throughput: 0: 2775.4, 1: 2712.8. Samples: 30279392. Policy #0 lag: (min: 28.0, avg: 33.5, max: 44.0) -[2023-11-28 01:45:43,445][86177] Avg episode reward: [(0, '-537.990'), (1, '-502.920')] -[2023-11-28 01:45:43,553][87426] Updated weights for policy 1, policy_version 59080 (0.0009) -[2023-11-28 01:45:43,674][87424] Updated weights for policy 0, policy_version 59146 (0.0008) -[2023-11-28 01:45:43,934][87426] Updated weights for policy 1, policy_version 59090 (0.0008) -[2023-11-28 01:45:44,061][87424] Updated weights for policy 0, policy_version 59156 (0.0007) -[2023-11-28 01:45:44,315][87426] Updated weights for policy 1, policy_version 59100 (0.0007) -[2023-11-28 01:45:44,451][87424] Updated weights for policy 0, policy_version 59166 (0.0008) -[2023-11-28 01:45:46,817][87426] Updated weights for policy 1, policy_version 59110 (0.0008) -[2023-11-28 01:45:46,880][87424] Updated weights for policy 0, policy_version 59176 (0.0011) -[2023-11-28 01:45:47,197][87426] Updated weights for policy 1, policy_version 59120 (0.0008) -[2023-11-28 01:45:47,267][87424] Updated weights for policy 0, policy_version 59186 (0.0008) -[2023-11-28 01:45:47,576][87426] Updated weights for policy 1, policy_version 59130 (0.0008) -[2023-11-28 01:45:47,657][87424] Updated weights for policy 0, policy_version 59196 (0.0007) -[2023-11-28 01:45:48,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 30294016. Throughput: 0: 2749.0, 1: 2704.0. Samples: 30302952. Policy #0 lag: (min: 28.0, avg: 33.5, max: 44.0) -[2023-11-28 01:45:48,446][86177] Avg episode reward: [(0, '-551.370'), (1, '-505.070')] -[2023-11-28 01:45:49,441][87426] Updated weights for policy 1, policy_version 59140 (0.0009) -[2023-11-28 01:45:49,689][87424] Updated weights for policy 0, policy_version 59206 (0.0008) -[2023-11-28 01:45:49,828][87426] Updated weights for policy 1, policy_version 59150 (0.0009) -[2023-11-28 01:45:50,068][87424] Updated weights for policy 0, policy_version 59216 (0.0011) -[2023-11-28 01:45:50,208][87426] Updated weights for policy 1, policy_version 59160 (0.0010) -[2023-11-28 01:45:50,456][87424] Updated weights for policy 0, policy_version 59226 (0.0012) -[2023-11-28 01:45:52,602][87426] Updated weights for policy 1, policy_version 59170 (0.0010) -[2023-11-28 01:45:52,960][87424] Updated weights for policy 0, policy_version 59236 (0.0009) -[2023-11-28 01:45:52,984][87426] Updated weights for policy 1, policy_version 59180 (0.0012) -[2023-11-28 01:45:53,343][87424] Updated weights for policy 0, policy_version 59246 (0.0011) -[2023-11-28 01:45:53,370][87426] Updated weights for policy 1, policy_version 59190 (0.0011) -[2023-11-28 01:45:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.9, 300 sec: 5359.5). Total num frames: 30310400. Throughput: 0: 2730.1, 1: 2709.9. Samples: 30335240. Policy #0 lag: (min: 28.0, avg: 33.5, max: 44.0) -[2023-11-28 01:45:53,445][86177] Avg episode reward: [(0, '-552.850'), (1, '-508.640')] -[2023-11-28 01:45:53,734][87424] Updated weights for policy 0, policy_version 59256 (0.0010) -[2023-11-28 01:45:53,750][87426] Updated weights for policy 1, policy_version 59200 (0.0011) -[2023-11-28 01:45:55,845][87426] Updated weights for policy 1, policy_version 59210 (0.0009) -[2023-11-28 01:45:56,228][87426] Updated weights for policy 1, policy_version 59220 (0.0007) -[2023-11-28 01:45:56,372][87424] Updated weights for policy 0, policy_version 59266 (0.0010) -[2023-11-28 01:45:56,606][87426] Updated weights for policy 1, policy_version 59230 (0.0008) -[2023-11-28 01:45:56,758][87424] Updated weights for policy 0, policy_version 59276 (0.0008) -[2023-11-28 01:45:57,141][87424] Updated weights for policy 0, policy_version 59286 (0.0007) -[2023-11-28 01:45:57,522][87424] Updated weights for policy 0, policy_version 59296 (0.0007) -[2023-11-28 01:45:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 30343168. Throughput: 0: 2705.7, 1: 2719.8. Samples: 30358612. Policy #0 lag: (min: 28.0, avg: 33.5, max: 44.0) -[2023-11-28 01:45:58,446][86177] Avg episode reward: [(0, '-555.480'), (1, '-507.040')] -[2023-11-28 01:45:58,730][87426] Updated weights for policy 1, policy_version 59240 (0.0011) -[2023-11-28 01:45:59,111][87426] Updated weights for policy 1, policy_version 59250 (0.0012) -[2023-11-28 01:45:59,482][87426] Updated weights for policy 1, policy_version 59260 (0.0012) -[2023-11-28 01:45:59,955][87424] Updated weights for policy 0, policy_version 59306 (0.0009) -[2023-11-28 01:46:00,341][87424] Updated weights for policy 0, policy_version 59316 (0.0009) -[2023-11-28 01:46:00,731][87424] Updated weights for policy 0, policy_version 59326 (0.0011) -[2023-11-28 01:46:01,495][87426] Updated weights for policy 1, policy_version 59270 (0.0009) -[2023-11-28 01:46:01,873][87426] Updated weights for policy 1, policy_version 59280 (0.0008) -[2023-11-28 01:46:02,262][87426] Updated weights for policy 1, policy_version 59290 (0.0008) -[2023-11-28 01:46:02,713][87424] Updated weights for policy 0, policy_version 59336 (0.0012) -[2023-11-28 01:46:03,090][87424] Updated weights for policy 0, policy_version 59346 (0.0012) -[2023-11-28 01:46:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 30367744. Throughput: 0: 2687.6, 1: 2698.1. Samples: 30381944. Policy #0 lag: (min: 28.0, avg: 33.5, max: 44.0) -[2023-11-28 01:46:03,445][86177] Avg episode reward: [(0, '-564.340'), (1, '-508.160')] -[2023-11-28 01:46:03,471][87424] Updated weights for policy 0, policy_version 59356 (0.0012) -[2023-11-28 01:46:04,602][87426] Updated weights for policy 1, policy_version 59300 (0.0011) -[2023-11-28 01:46:04,981][87426] Updated weights for policy 1, policy_version 59310 (0.0011) -[2023-11-28 01:46:05,360][87426] Updated weights for policy 1, policy_version 59320 (0.0011) -[2023-11-28 01:46:06,017][87424] Updated weights for policy 0, policy_version 59366 (0.0012) -[2023-11-28 01:46:06,406][87424] Updated weights for policy 0, policy_version 59376 (0.0012) -[2023-11-28 01:46:06,789][87424] Updated weights for policy 0, policy_version 59386 (0.0012) -[2023-11-28 01:46:07,930][87426] Updated weights for policy 1, policy_version 59330 (0.0011) -[2023-11-28 01:46:08,302][87426] Updated weights for policy 1, policy_version 59340 (0.0012) -[2023-11-28 01:46:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 30392320. Throughput: 0: 2695.4, 1: 2698.6. Samples: 30413628. Policy #0 lag: (min: 28.0, avg: 33.5, max: 44.0) -[2023-11-28 01:46:08,445][86177] Avg episode reward: [(0, '-572.210'), (1, '-516.320')] -[2023-11-28 01:46:08,680][87426] Updated weights for policy 1, policy_version 59350 (0.0010) -[2023-11-28 01:46:08,705][87424] Updated weights for policy 0, policy_version 59396 (0.0012) -[2023-11-28 01:46:09,060][87426] Updated weights for policy 1, policy_version 59360 (0.0008) -[2023-11-28 01:46:09,083][87424] Updated weights for policy 0, policy_version 59406 (0.0012) -[2023-11-28 01:46:09,465][87424] Updated weights for policy 0, policy_version 59416 (0.0012) -[2023-11-28 01:46:11,265][87426] Updated weights for policy 1, policy_version 59370 (0.0007) -[2023-11-28 01:46:11,491][87424] Updated weights for policy 0, policy_version 59426 (0.0012) -[2023-11-28 01:46:11,644][87426] Updated weights for policy 1, policy_version 59380 (0.0009) -[2023-11-28 01:46:11,871][87424] Updated weights for policy 0, policy_version 59436 (0.0011) -[2023-11-28 01:46:12,026][87426] Updated weights for policy 1, policy_version 59390 (0.0011) -[2023-11-28 01:46:12,249][87424] Updated weights for policy 0, policy_version 59446 (0.0009) -[2023-11-28 01:46:12,637][87424] Updated weights for policy 0, policy_version 59456 (0.0008) -[2023-11-28 01:46:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30425088. Throughput: 0: 2703.9, 1: 2691.7. Samples: 30438036. Policy #0 lag: (min: 31.0, avg: 47.7, max: 63.0) -[2023-11-28 01:46:13,445][86177] Avg episode reward: [(0, '-563.360'), (1, '-515.960')] -[2023-11-28 01:46:14,120][87426] Updated weights for policy 1, policy_version 59400 (0.0012) -[2023-11-28 01:46:14,501][87426] Updated weights for policy 1, policy_version 59410 (0.0011) -[2023-11-28 01:46:14,810][87424] Updated weights for policy 0, policy_version 59466 (0.0011) -[2023-11-28 01:46:14,869][87426] Updated weights for policy 1, policy_version 59420 (0.0010) -[2023-11-28 01:46:15,185][87424] Updated weights for policy 0, policy_version 59476 (0.0012) -[2023-11-28 01:46:15,566][87424] Updated weights for policy 0, policy_version 59486 (0.0012) -[2023-11-28 01:46:17,299][87426] Updated weights for policy 1, policy_version 59430 (0.0008) -[2023-11-28 01:46:17,457][87424] Updated weights for policy 0, policy_version 59496 (0.0011) -[2023-11-28 01:46:17,678][87426] Updated weights for policy 1, policy_version 59440 (0.0010) -[2023-11-28 01:46:17,829][87424] Updated weights for policy 0, policy_version 59506 (0.0011) -[2023-11-28 01:46:18,060][87426] Updated weights for policy 1, policy_version 59450 (0.0012) -[2023-11-28 01:46:18,218][87424] Updated weights for policy 0, policy_version 59516 (0.0011) -[2023-11-28 01:46:18,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 30457856. Throughput: 0: 2697.8, 1: 2682.8. Samples: 30462452. Policy #0 lag: (min: 31.0, avg: 47.7, max: 63.0) -[2023-11-28 01:46:18,446][86177] Avg episode reward: [(0, '-544.540'), (1, '-523.340')] -[2023-11-28 01:46:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000059456_15220736.pth... -[2023-11-28 01:46:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000059520_15237120.pth... -[2023-11-28 01:46:18,488][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000056928_14573568.pth -[2023-11-28 01:46:18,494][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000056992_14589952.pth -[2023-11-28 01:46:19,977][87424] Updated weights for policy 0, policy_version 59526 (0.0011) -[2023-11-28 01:46:20,223][87426] Updated weights for policy 1, policy_version 59460 (0.0011) -[2023-11-28 01:46:20,356][87424] Updated weights for policy 0, policy_version 59536 (0.0009) -[2023-11-28 01:46:20,598][87426] Updated weights for policy 1, policy_version 59470 (0.0011) -[2023-11-28 01:46:20,735][87424] Updated weights for policy 0, policy_version 59546 (0.0010) -[2023-11-28 01:46:20,976][87426] Updated weights for policy 1, policy_version 59480 (0.0012) -[2023-11-28 01:46:22,773][87424] Updated weights for policy 0, policy_version 59556 (0.0011) -[2023-11-28 01:46:23,152][87424] Updated weights for policy 0, policy_version 59566 (0.0008) -[2023-11-28 01:46:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30474240. Throughput: 0: 2697.9, 1: 2640.8. Samples: 30495200. Policy #0 lag: (min: 31.0, avg: 47.7, max: 63.0) -[2023-11-28 01:46:23,445][86177] Avg episode reward: [(0, '-524.750'), (1, '-532.760')] -[2023-11-28 01:46:23,527][87426] Updated weights for policy 1, policy_version 59490 (0.0011) -[2023-11-28 01:46:23,542][87424] Updated weights for policy 0, policy_version 59576 (0.0007) -[2023-11-28 01:46:23,894][87426] Updated weights for policy 1, policy_version 59500 (0.0007) -[2023-11-28 01:46:24,275][87426] Updated weights for policy 1, policy_version 59510 (0.0008) -[2023-11-28 01:46:24,651][87426] Updated weights for policy 1, policy_version 59520 (0.0007) -[2023-11-28 01:46:25,932][87424] Updated weights for policy 0, policy_version 59586 (0.0008) -[2023-11-28 01:46:26,315][87424] Updated weights for policy 0, policy_version 59596 (0.0009) -[2023-11-28 01:46:26,694][87424] Updated weights for policy 0, policy_version 59606 (0.0010) -[2023-11-28 01:46:26,834][87426] Updated weights for policy 1, policy_version 59530 (0.0008) -[2023-11-28 01:46:27,071][87424] Updated weights for policy 0, policy_version 59616 (0.0007) -[2023-11-28 01:46:27,223][87426] Updated weights for policy 1, policy_version 59540 (0.0007) -[2023-11-28 01:46:27,603][87426] Updated weights for policy 1, policy_version 59550 (0.0007) -[2023-11-28 01:46:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30507008. Throughput: 0: 2681.4, 1: 2635.5. Samples: 30518652. Policy #0 lag: (min: 31.0, avg: 47.7, max: 63.0) -[2023-11-28 01:46:28,445][86177] Avg episode reward: [(0, '-504.720'), (1, '-537.980')] -[2023-11-28 01:46:28,998][87424] Updated weights for policy 0, policy_version 59626 (0.0012) -[2023-11-28 01:46:29,370][87424] Updated weights for policy 0, policy_version 59636 (0.0012) -[2023-11-28 01:46:29,747][87424] Updated weights for policy 0, policy_version 59646 (0.0011) -[2023-11-28 01:46:29,948][87426] Updated weights for policy 1, policy_version 59560 (0.0010) -[2023-11-28 01:46:30,327][87426] Updated weights for policy 1, policy_version 59570 (0.0010) -[2023-11-28 01:46:30,708][87426] Updated weights for policy 1, policy_version 59580 (0.0008) -[2023-11-28 01:46:32,036][87424] Updated weights for policy 0, policy_version 59656 (0.0011) -[2023-11-28 01:46:32,421][87424] Updated weights for policy 0, policy_version 59666 (0.0011) -[2023-11-28 01:46:32,805][87424] Updated weights for policy 0, policy_version 59676 (0.0011) -[2023-11-28 01:46:32,888][87426] Updated weights for policy 1, policy_version 59590 (0.0009) -[2023-11-28 01:46:33,270][87426] Updated weights for policy 1, policy_version 59600 (0.0012) -[2023-11-28 01:46:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 30531584. Throughput: 0: 2705.8, 1: 2640.3. Samples: 30543524. Policy #0 lag: (min: 31.0, avg: 47.7, max: 63.0) -[2023-11-28 01:46:33,445][86177] Avg episode reward: [(0, '-504.730'), (1, '-532.540')] -[2023-11-28 01:46:33,637][87426] Updated weights for policy 1, policy_version 59610 (0.0012) -[2023-11-28 01:46:34,540][87424] Updated weights for policy 0, policy_version 59686 (0.0011) -[2023-11-28 01:46:34,926][87424] Updated weights for policy 0, policy_version 59696 (0.0011) -[2023-11-28 01:46:35,311][87424] Updated weights for policy 0, policy_version 59706 (0.0012) -[2023-11-28 01:46:35,823][87426] Updated weights for policy 1, policy_version 59620 (0.0012) -[2023-11-28 01:46:36,199][87426] Updated weights for policy 1, policy_version 59630 (0.0012) -[2023-11-28 01:46:36,580][87426] Updated weights for policy 1, policy_version 59640 (0.0012) -[2023-11-28 01:46:37,252][87424] Updated weights for policy 0, policy_version 59716 (0.0011) -[2023-11-28 01:46:37,624][87424] Updated weights for policy 0, policy_version 59726 (0.0009) -[2023-11-28 01:46:38,002][87424] Updated weights for policy 0, policy_version 59736 (0.0007) -[2023-11-28 01:46:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30564352. Throughput: 0: 2751.0, 1: 2637.2. Samples: 30577708. Policy #0 lag: (min: 31.0, avg: 47.7, max: 63.0) -[2023-11-28 01:46:38,445][86177] Avg episode reward: [(0, '-584.780'), (1, '-522.580')] -[2023-11-28 01:46:38,649][87426] Updated weights for policy 1, policy_version 59650 (0.0011) -[2023-11-28 01:46:39,027][87426] Updated weights for policy 1, policy_version 59660 (0.0011) -[2023-11-28 01:46:39,410][87426] Updated weights for policy 1, policy_version 59670 (0.0011) -[2023-11-28 01:46:39,792][87426] Updated weights for policy 1, policy_version 59680 (0.0008) -[2023-11-28 01:46:40,057][87424] Updated weights for policy 0, policy_version 59746 (0.0008) -[2023-11-28 01:46:40,437][87424] Updated weights for policy 0, policy_version 59756 (0.0012) -[2023-11-28 01:46:40,814][87424] Updated weights for policy 0, policy_version 59766 (0.0012) -[2023-11-28 01:46:41,196][87424] Updated weights for policy 0, policy_version 59776 (0.0012) -[2023-11-28 01:46:41,817][87426] Updated weights for policy 1, policy_version 59690 (0.0012) -[2023-11-28 01:46:42,195][87426] Updated weights for policy 1, policy_version 59700 (0.0010) -[2023-11-28 01:46:42,588][87426] Updated weights for policy 1, policy_version 59710 (0.0012) -[2023-11-28 01:46:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30588928. Throughput: 0: 2774.2, 1: 2644.0. Samples: 30602432. Policy #0 lag: (min: 31.0, avg: 47.7, max: 63.0) -[2023-11-28 01:46:43,445][86177] Avg episode reward: [(0, '-587.050'), (1, '-519.320')] -[2023-11-28 01:46:43,467][87424] Updated weights for policy 0, policy_version 59786 (0.0011) -[2023-11-28 01:46:43,849][87424] Updated weights for policy 0, policy_version 59796 (0.0009) -[2023-11-28 01:46:44,234][87424] Updated weights for policy 0, policy_version 59806 (0.0008) -[2023-11-28 01:46:45,035][87426] Updated weights for policy 1, policy_version 59720 (0.0009) -[2023-11-28 01:46:45,418][87426] Updated weights for policy 1, policy_version 59730 (0.0010) -[2023-11-28 01:46:45,796][87426] Updated weights for policy 1, policy_version 59740 (0.0012) -[2023-11-28 01:46:46,677][87424] Updated weights for policy 0, policy_version 59816 (0.0011) -[2023-11-28 01:46:47,056][87424] Updated weights for policy 0, policy_version 59826 (0.0012) -[2023-11-28 01:46:47,435][87424] Updated weights for policy 0, policy_version 59836 (0.0010) -[2023-11-28 01:46:48,119][87426] Updated weights for policy 1, policy_version 59750 (0.0011) -[2023-11-28 01:46:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 30613504. Throughput: 0: 2797.8, 1: 2646.6. Samples: 30626940. Policy #0 lag: (min: 31.0, avg: 47.7, max: 63.0) -[2023-11-28 01:46:48,445][86177] Avg episode reward: [(0, '-595.370'), (1, '-514.400')] -[2023-11-28 01:46:48,499][87426] Updated weights for policy 1, policy_version 59760 (0.0011) -[2023-11-28 01:46:48,882][87426] Updated weights for policy 1, policy_version 59770 (0.0011) -[2023-11-28 01:46:49,533][87424] Updated weights for policy 0, policy_version 59846 (0.0009) -[2023-11-28 01:46:49,915][87424] Updated weights for policy 0, policy_version 59856 (0.0011) -[2023-11-28 01:46:50,306][87424] Updated weights for policy 0, policy_version 59866 (0.0011) -[2023-11-28 01:46:50,754][87426] Updated weights for policy 1, policy_version 59780 (0.0012) -[2023-11-28 01:46:51,141][87426] Updated weights for policy 1, policy_version 59790 (0.0012) -[2023-11-28 01:46:51,518][87426] Updated weights for policy 1, policy_version 59800 (0.0012) -[2023-11-28 01:46:52,592][87424] Updated weights for policy 0, policy_version 59876 (0.0011) -[2023-11-28 01:46:52,984][87424] Updated weights for policy 0, policy_version 59886 (0.0010) -[2023-11-28 01:46:53,372][87424] Updated weights for policy 0, policy_version 59896 (0.0011) -[2023-11-28 01:46:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30638080. Throughput: 0: 2796.7, 1: 2672.8. Samples: 30659756. Policy #0 lag: (min: 31.0, avg: 47.7, max: 63.0) -[2023-11-28 01:46:53,445][86177] Avg episode reward: [(0, '-595.040'), (1, '-513.440')] -[2023-11-28 01:46:53,924][87426] Updated weights for policy 1, policy_version 59810 (0.0012) -[2023-11-28 01:46:54,308][87426] Updated weights for policy 1, policy_version 59820 (0.0009) -[2023-11-28 01:46:54,688][87426] Updated weights for policy 1, policy_version 59830 (0.0007) -[2023-11-28 01:46:55,079][87426] Updated weights for policy 1, policy_version 59840 (0.0007) -[2023-11-28 01:46:55,490][87424] Updated weights for policy 0, policy_version 59906 (0.0011) -[2023-11-28 01:46:55,869][87424] Updated weights for policy 0, policy_version 59916 (0.0012) -[2023-11-28 01:46:56,262][87424] Updated weights for policy 0, policy_version 59926 (0.0012) -[2023-11-28 01:46:56,634][87424] Updated weights for policy 0, policy_version 59936 (0.0012) -[2023-11-28 01:46:57,255][87426] Updated weights for policy 1, policy_version 59850 (0.0008) -[2023-11-28 01:46:57,623][87426] Updated weights for policy 1, policy_version 59860 (0.0007) -[2023-11-28 01:46:58,003][87426] Updated weights for policy 1, policy_version 59870 (0.0008) -[2023-11-28 01:46:58,356][87424] Updated weights for policy 0, policy_version 59946 (0.0012) -[2023-11-28 01:46:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 30670848. Throughput: 0: 2770.9, 1: 2697.4. Samples: 30684112. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 01:46:58,445][86177] Avg episode reward: [(0, '-551.790'), (1, '-523.650')] -[2023-11-28 01:46:58,732][87424] Updated weights for policy 0, policy_version 59956 (0.0012) -[2023-11-28 01:46:59,115][87424] Updated weights for policy 0, policy_version 59966 (0.0012) -[2023-11-28 01:46:59,740][87426] Updated weights for policy 1, policy_version 59880 (0.0011) -[2023-11-28 01:47:00,114][87426] Updated weights for policy 1, policy_version 59890 (0.0011) -[2023-11-28 01:47:00,507][87426] Updated weights for policy 1, policy_version 59900 (0.0011) -[2023-11-28 01:47:01,463][87424] Updated weights for policy 0, policy_version 59976 (0.0010) -[2023-11-28 01:47:01,854][87424] Updated weights for policy 0, policy_version 59986 (0.0009) -[2023-11-28 01:47:02,229][87424] Updated weights for policy 0, policy_version 59996 (0.0009) -[2023-11-28 01:47:02,812][87426] Updated weights for policy 1, policy_version 59910 (0.0010) -[2023-11-28 01:47:03,190][87426] Updated weights for policy 1, policy_version 59920 (0.0012) -[2023-11-28 01:47:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 30695424. Throughput: 0: 2776.9, 1: 2703.8. Samples: 30709084. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 01:47:03,445][86177] Avg episode reward: [(0, '-565.380'), (1, '-515.020')] -[2023-11-28 01:47:03,572][87426] Updated weights for policy 1, policy_version 59930 (0.0012) -[2023-11-28 01:47:04,112][87424] Updated weights for policy 0, policy_version 60006 (0.0011) -[2023-11-28 01:47:04,491][87424] Updated weights for policy 0, policy_version 60016 (0.0009) -[2023-11-28 01:47:04,874][87424] Updated weights for policy 0, policy_version 60026 (0.0011) -[2023-11-28 01:47:05,513][87426] Updated weights for policy 1, policy_version 59940 (0.0012) -[2023-11-28 01:47:05,906][87426] Updated weights for policy 1, policy_version 59950 (0.0012) -[2023-11-28 01:47:06,288][87426] Updated weights for policy 1, policy_version 59960 (0.0012) -[2023-11-28 01:47:06,787][87424] Updated weights for policy 0, policy_version 60036 (0.0011) -[2023-11-28 01:47:07,170][87424] Updated weights for policy 0, policy_version 60046 (0.0012) -[2023-11-28 01:47:07,550][87424] Updated weights for policy 0, policy_version 60056 (0.0012) -[2023-11-28 01:47:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 30728192. Throughput: 0: 2786.1, 1: 2713.3. Samples: 30742676. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 01:47:08,445][86177] Avg episode reward: [(0, '-561.980'), (1, '-522.970')] -[2023-11-28 01:47:08,788][87426] Updated weights for policy 1, policy_version 59970 (0.0012) -[2023-11-28 01:47:09,165][87426] Updated weights for policy 1, policy_version 59980 (0.0012) -[2023-11-28 01:47:09,559][87426] Updated weights for policy 1, policy_version 59990 (0.0012) -[2023-11-28 01:47:09,926][87426] Updated weights for policy 1, policy_version 60000 (0.0012) -[2023-11-28 01:47:09,968][87424] Updated weights for policy 0, policy_version 60066 (0.0012) -[2023-11-28 01:47:10,349][87424] Updated weights for policy 0, policy_version 60076 (0.0012) -[2023-11-28 01:47:10,728][87424] Updated weights for policy 0, policy_version 60086 (0.0010) -[2023-11-28 01:47:11,109][87424] Updated weights for policy 0, policy_version 60096 (0.0007) -[2023-11-28 01:47:12,173][87426] Updated weights for policy 1, policy_version 60010 (0.0010) -[2023-11-28 01:47:12,559][87426] Updated weights for policy 1, policy_version 60020 (0.0010) -[2023-11-28 01:47:12,934][87426] Updated weights for policy 1, policy_version 60030 (0.0010) -[2023-11-28 01:47:13,320][87424] Updated weights for policy 0, policy_version 60106 (0.0012) -[2023-11-28 01:47:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30752768. Throughput: 0: 2798.9, 1: 2732.3. Samples: 30767556. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 01:47:13,445][86177] Avg episode reward: [(0, '-563.850'), (1, '-521.010')] -[2023-11-28 01:47:13,708][87424] Updated weights for policy 0, policy_version 60116 (0.0012) -[2023-11-28 01:47:14,086][87424] Updated weights for policy 0, policy_version 60126 (0.0011) -[2023-11-28 01:47:15,437][87426] Updated weights for policy 1, policy_version 60040 (0.0009) -[2023-11-28 01:47:15,811][87426] Updated weights for policy 1, policy_version 60050 (0.0008) -[2023-11-28 01:47:16,197][87426] Updated weights for policy 1, policy_version 60060 (0.0008) -[2023-11-28 01:47:16,517][87424] Updated weights for policy 0, policy_version 60136 (0.0012) -[2023-11-28 01:47:16,901][87424] Updated weights for policy 0, policy_version 60146 (0.0011) -[2023-11-28 01:47:17,281][87424] Updated weights for policy 0, policy_version 60156 (0.0012) -[2023-11-28 01:47:17,804][87426] Updated weights for policy 1, policy_version 60070 (0.0009) -[2023-11-28 01:47:18,182][87426] Updated weights for policy 1, policy_version 60080 (0.0008) -[2023-11-28 01:47:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 30777344. Throughput: 0: 2793.0, 1: 2736.5. Samples: 30792352. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 01:47:18,445][86177] Avg episode reward: [(0, '-584.190'), (1, '-512.090')] -[2023-11-28 01:47:18,570][87426] Updated weights for policy 1, policy_version 60090 (0.0009) -[2023-11-28 01:47:19,364][87424] Updated weights for policy 0, policy_version 60166 (0.0012) -[2023-11-28 01:47:19,745][87424] Updated weights for policy 0, policy_version 60176 (0.0011) -[2023-11-28 01:47:20,136][87424] Updated weights for policy 0, policy_version 60186 (0.0012) -[2023-11-28 01:47:20,509][87426] Updated weights for policy 1, policy_version 60100 (0.0011) -[2023-11-28 01:47:20,886][87426] Updated weights for policy 1, policy_version 60110 (0.0009) -[2023-11-28 01:47:21,274][87426] Updated weights for policy 1, policy_version 60120 (0.0009) -[2023-11-28 01:47:22,089][87424] Updated weights for policy 0, policy_version 60196 (0.0010) -[2023-11-28 01:47:22,478][87424] Updated weights for policy 0, policy_version 60206 (0.0009) -[2023-11-28 01:47:22,863][87424] Updated weights for policy 0, policy_version 60216 (0.0009) -[2023-11-28 01:47:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 30810112. Throughput: 0: 2768.6, 1: 2742.6. Samples: 30825712. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 01:47:23,445][86177] Avg episode reward: [(0, '-582.000'), (1, '-518.550')] -[2023-11-28 01:47:23,699][87426] Updated weights for policy 1, policy_version 60130 (0.0011) -[2023-11-28 01:47:24,074][87426] Updated weights for policy 1, policy_version 60140 (0.0009) -[2023-11-28 01:47:24,460][87426] Updated weights for policy 1, policy_version 60150 (0.0007) -[2023-11-28 01:47:24,759][87424] Updated weights for policy 0, policy_version 60226 (0.0008) -[2023-11-28 01:47:24,840][87426] Updated weights for policy 1, policy_version 60160 (0.0008) -[2023-11-28 01:47:25,137][87424] Updated weights for policy 0, policy_version 60236 (0.0008) -[2023-11-28 01:47:25,526][87424] Updated weights for policy 0, policy_version 60246 (0.0008) -[2023-11-28 01:47:25,909][87424] Updated weights for policy 0, policy_version 60256 (0.0008) -[2023-11-28 01:47:27,229][87426] Updated weights for policy 1, policy_version 60170 (0.0012) -[2023-11-28 01:47:27,597][87426] Updated weights for policy 1, policy_version 60180 (0.0012) -[2023-11-28 01:47:27,980][87426] Updated weights for policy 1, policy_version 60190 (0.0012) -[2023-11-28 01:47:28,183][87424] Updated weights for policy 0, policy_version 60266 (0.0012) -[2023-11-28 01:47:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 30834688. Throughput: 0: 2760.8, 1: 2719.1. Samples: 30849028. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 01:47:28,445][86177] Avg episode reward: [(0, '-621.800'), (1, '-513.480')] -[2023-11-28 01:47:28,568][87424] Updated weights for policy 0, policy_version 60276 (0.0012) -[2023-11-28 01:47:28,953][87424] Updated weights for policy 0, policy_version 60286 (0.0012) -[2023-11-28 01:47:30,024][87426] Updated weights for policy 1, policy_version 60200 (0.0010) -[2023-11-28 01:47:30,415][87426] Updated weights for policy 1, policy_version 60210 (0.0010) -[2023-11-28 01:47:30,746][87424] Updated weights for policy 0, policy_version 60296 (0.0008) -[2023-11-28 01:47:30,790][87426] Updated weights for policy 1, policy_version 60220 (0.0010) -[2023-11-28 01:47:31,127][87424] Updated weights for policy 0, policy_version 60306 (0.0008) -[2023-11-28 01:47:31,503][87424] Updated weights for policy 0, policy_version 60316 (0.0009) -[2023-11-28 01:47:33,225][87426] Updated weights for policy 1, policy_version 60230 (0.0008) -[2023-11-28 01:47:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30859264. Throughput: 0: 2755.5, 1: 2748.5. Samples: 30874620. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 01:47:33,445][86177] Avg episode reward: [(0, '-623.250'), (1, '-512.760')] -[2023-11-28 01:47:33,563][87424] Updated weights for policy 0, policy_version 60326 (0.0008) -[2023-11-28 01:47:33,603][87426] Updated weights for policy 1, policy_version 60240 (0.0007) -[2023-11-28 01:47:33,942][87424] Updated weights for policy 0, policy_version 60336 (0.0007) -[2023-11-28 01:47:33,989][87426] Updated weights for policy 1, policy_version 60250 (0.0007) -[2023-11-28 01:47:34,325][87424] Updated weights for policy 0, policy_version 60346 (0.0007) -[2023-11-28 01:47:36,243][87426] Updated weights for policy 1, policy_version 60260 (0.0009) -[2023-11-28 01:47:36,611][87426] Updated weights for policy 1, policy_version 60270 (0.0012) -[2023-11-28 01:47:36,707][87424] Updated weights for policy 0, policy_version 60356 (0.0010) -[2023-11-28 01:47:36,990][87426] Updated weights for policy 1, policy_version 60280 (0.0012) -[2023-11-28 01:47:37,094][87424] Updated weights for policy 0, policy_version 60366 (0.0010) -[2023-11-28 01:47:37,480][87424] Updated weights for policy 0, policy_version 60376 (0.0011) -[2023-11-28 01:47:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30892032. Throughput: 0: 2771.0, 1: 2718.0. Samples: 30906764. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:47:38,445][86177] Avg episode reward: [(0, '-634.120'), (1, '-512.110')] -[2023-11-28 01:47:38,819][87426] Updated weights for policy 1, policy_version 60290 (0.0008) -[2023-11-28 01:47:39,200][87426] Updated weights for policy 1, policy_version 60300 (0.0012) -[2023-11-28 01:47:39,585][87426] Updated weights for policy 1, policy_version 60310 (0.0012) -[2023-11-28 01:47:39,958][87426] Updated weights for policy 1, policy_version 60320 (0.0011) -[2023-11-28 01:47:40,035][87424] Updated weights for policy 0, policy_version 60386 (0.0012) -[2023-11-28 01:47:40,410][87424] Updated weights for policy 0, policy_version 60396 (0.0012) -[2023-11-28 01:47:40,790][87424] Updated weights for policy 0, policy_version 60406 (0.0012) -[2023-11-28 01:47:41,175][87424] Updated weights for policy 0, policy_version 60416 (0.0012) -[2023-11-28 01:47:41,963][87426] Updated weights for policy 1, policy_version 60330 (0.0012) -[2023-11-28 01:47:42,342][87426] Updated weights for policy 1, policy_version 60340 (0.0012) -[2023-11-28 01:47:42,722][87426] Updated weights for policy 1, policy_version 60350 (0.0012) -[2023-11-28 01:47:43,212][87424] Updated weights for policy 0, policy_version 60426 (0.0009) -[2023-11-28 01:47:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30916608. Throughput: 0: 2776.0, 1: 2723.3. Samples: 30931580. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:47:43,446][86177] Avg episode reward: [(0, '-672.920'), (1, '-506.260')] -[2023-11-28 01:47:43,595][87424] Updated weights for policy 0, policy_version 60436 (0.0009) -[2023-11-28 01:47:43,983][87424] Updated weights for policy 0, policy_version 60446 (0.0009) -[2023-11-28 01:47:44,798][87426] Updated weights for policy 1, policy_version 60360 (0.0012) -[2023-11-28 01:47:45,177][87426] Updated weights for policy 1, policy_version 60370 (0.0012) -[2023-11-28 01:47:45,547][87426] Updated weights for policy 1, policy_version 60380 (0.0012) -[2023-11-28 01:47:46,385][87424] Updated weights for policy 0, policy_version 60456 (0.0007) -[2023-11-28 01:47:46,776][87424] Updated weights for policy 0, policy_version 60466 (0.0008) -[2023-11-28 01:47:47,151][87424] Updated weights for policy 0, policy_version 60476 (0.0007) -[2023-11-28 01:47:47,962][87426] Updated weights for policy 1, policy_version 60390 (0.0009) -[2023-11-28 01:47:48,337][87426] Updated weights for policy 1, policy_version 60400 (0.0008) -[2023-11-28 01:47:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30941184. Throughput: 0: 2768.9, 1: 2724.6. Samples: 30956292. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:47:48,445][86177] Avg episode reward: [(0, '-694.980'), (1, '-507.940')] -[2023-11-28 01:47:48,723][87426] Updated weights for policy 1, policy_version 60410 (0.0007) -[2023-11-28 01:47:49,021][87424] Updated weights for policy 0, policy_version 60486 (0.0008) -[2023-11-28 01:47:49,402][87424] Updated weights for policy 0, policy_version 60496 (0.0008) -[2023-11-28 01:47:49,779][87424] Updated weights for policy 0, policy_version 60506 (0.0008) -[2023-11-28 01:47:50,962][87426] Updated weights for policy 1, policy_version 60420 (0.0010) -[2023-11-28 01:47:51,346][87426] Updated weights for policy 1, policy_version 60430 (0.0012) -[2023-11-28 01:47:51,727][87426] Updated weights for policy 1, policy_version 60440 (0.0012) -[2023-11-28 01:47:52,023][87424] Updated weights for policy 0, policy_version 60516 (0.0010) -[2023-11-28 01:47:52,410][87424] Updated weights for policy 0, policy_version 60526 (0.0008) -[2023-11-28 01:47:52,800][87424] Updated weights for policy 0, policy_version 60536 (0.0008) -[2023-11-28 01:47:53,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 30973952. Throughput: 0: 2737.7, 1: 2705.3. Samples: 30987608. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:47:53,445][86177] Avg episode reward: [(0, '-757.150'), (1, '-506.220')] -[2023-11-28 01:47:54,189][87426] Updated weights for policy 1, policy_version 60450 (0.0010) -[2023-11-28 01:47:54,571][87426] Updated weights for policy 1, policy_version 60460 (0.0010) -[2023-11-28 01:47:54,953][87426] Updated weights for policy 1, policy_version 60470 (0.0008) -[2023-11-28 01:47:54,996][87424] Updated weights for policy 0, policy_version 60546 (0.0012) -[2023-11-28 01:47:55,333][87426] Updated weights for policy 1, policy_version 60480 (0.0009) -[2023-11-28 01:47:55,369][87424] Updated weights for policy 0, policy_version 60556 (0.0008) -[2023-11-28 01:47:55,747][87424] Updated weights for policy 0, policy_version 60566 (0.0007) -[2023-11-28 01:47:56,132][87424] Updated weights for policy 0, policy_version 60576 (0.0008) -[2023-11-28 01:47:57,312][87426] Updated weights for policy 1, policy_version 60490 (0.0012) -[2023-11-28 01:47:57,690][87426] Updated weights for policy 1, policy_version 60500 (0.0009) -[2023-11-28 01:47:57,789][87424] Updated weights for policy 0, policy_version 60586 (0.0008) -[2023-11-28 01:47:58,069][87426] Updated weights for policy 1, policy_version 60510 (0.0007) -[2023-11-28 01:47:58,173][87424] Updated weights for policy 0, policy_version 60596 (0.0008) -[2023-11-28 01:47:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 30998528. Throughput: 0: 2743.5, 1: 2697.6. Samples: 31012404. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:47:58,445][86177] Avg episode reward: [(0, '-798.630'), (1, '-515.650')] -[2023-11-28 01:47:58,561][87424] Updated weights for policy 0, policy_version 60606 (0.0007) -[2023-11-28 01:48:00,196][87426] Updated weights for policy 1, policy_version 60520 (0.0011) -[2023-11-28 01:48:00,571][87426] Updated weights for policy 1, policy_version 60530 (0.0011) -[2023-11-28 01:48:00,812][87424] Updated weights for policy 0, policy_version 60616 (0.0011) -[2023-11-28 01:48:00,948][87426] Updated weights for policy 1, policy_version 60540 (0.0010) -[2023-11-28 01:48:01,190][87424] Updated weights for policy 0, policy_version 60626 (0.0011) -[2023-11-28 01:48:01,575][87424] Updated weights for policy 0, policy_version 60636 (0.0012) -[2023-11-28 01:48:03,264][87426] Updated weights for policy 1, policy_version 60550 (0.0011) -[2023-11-28 01:48:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 31023104. Throughput: 0: 2734.4, 1: 2694.1. Samples: 31036636. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:48:03,445][86177] Avg episode reward: [(0, '-852.430'), (1, '-523.590')] -[2023-11-28 01:48:03,636][87426] Updated weights for policy 1, policy_version 60560 (0.0011) -[2023-11-28 01:48:03,989][87424] Updated weights for policy 0, policy_version 60646 (0.0011) -[2023-11-28 01:48:04,021][87426] Updated weights for policy 1, policy_version 60570 (0.0011) -[2023-11-28 01:48:04,376][87424] Updated weights for policy 0, policy_version 60656 (0.0012) -[2023-11-28 01:48:04,766][87424] Updated weights for policy 0, policy_version 60666 (0.0012) -[2023-11-28 01:48:06,035][87426] Updated weights for policy 1, policy_version 60580 (0.0009) -[2023-11-28 01:48:06,417][87426] Updated weights for policy 1, policy_version 60590 (0.0012) -[2023-11-28 01:48:06,590][87424] Updated weights for policy 0, policy_version 60676 (0.0012) -[2023-11-28 01:48:06,798][87426] Updated weights for policy 1, policy_version 60600 (0.0011) -[2023-11-28 01:48:06,969][87424] Updated weights for policy 0, policy_version 60686 (0.0011) -[2023-11-28 01:48:07,350][87424] Updated weights for policy 0, policy_version 60696 (0.0011) -[2023-11-28 01:48:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 31055872. Throughput: 0: 2719.7, 1: 2701.0. Samples: 31069644. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:48:08,445][86177] Avg episode reward: [(0, '-893.700'), (1, '-527.660')] -[2023-11-28 01:48:09,246][87426] Updated weights for policy 1, policy_version 60610 (0.0012) -[2023-11-28 01:48:09,563][87424] Updated weights for policy 0, policy_version 60706 (0.0012) -[2023-11-28 01:48:09,623][87426] Updated weights for policy 1, policy_version 60620 (0.0010) -[2023-11-28 01:48:09,951][87424] Updated weights for policy 0, policy_version 60716 (0.0011) -[2023-11-28 01:48:09,999][87426] Updated weights for policy 1, policy_version 60630 (0.0011) -[2023-11-28 01:48:10,338][87424] Updated weights for policy 0, policy_version 60726 (0.0010) -[2023-11-28 01:48:10,379][87426] Updated weights for policy 1, policy_version 60640 (0.0010) -[2023-11-28 01:48:10,721][87424] Updated weights for policy 0, policy_version 60736 (0.0008) -[2023-11-28 01:48:12,378][87426] Updated weights for policy 1, policy_version 60650 (0.0011) -[2023-11-28 01:48:12,757][87426] Updated weights for policy 1, policy_version 60660 (0.0007) -[2023-11-28 01:48:13,150][87426] Updated weights for policy 1, policy_version 60670 (0.0009) -[2023-11-28 01:48:13,193][87424] Updated weights for policy 0, policy_version 60746 (0.0008) -[2023-11-28 01:48:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31080448. Throughput: 0: 2735.3, 1: 2732.4. Samples: 31095072. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 01:48:13,445][86177] Avg episode reward: [(0, '-914.070'), (1, '-532.640')] -[2023-11-28 01:48:13,582][87424] Updated weights for policy 0, policy_version 60756 (0.0012) -[2023-11-28 01:48:13,963][87424] Updated weights for policy 0, policy_version 60766 (0.0012) -[2023-11-28 01:48:15,087][87426] Updated weights for policy 1, policy_version 60680 (0.0008) -[2023-11-28 01:48:15,464][87426] Updated weights for policy 1, policy_version 60690 (0.0010) -[2023-11-28 01:48:15,705][87424] Updated weights for policy 0, policy_version 60776 (0.0011) -[2023-11-28 01:48:15,839][87426] Updated weights for policy 1, policy_version 60700 (0.0011) -[2023-11-28 01:48:16,087][87424] Updated weights for policy 0, policy_version 60786 (0.0012) -[2023-11-28 01:48:16,463][87424] Updated weights for policy 0, policy_version 60796 (0.0010) -[2023-11-28 01:48:18,323][87426] Updated weights for policy 1, policy_version 60710 (0.0009) -[2023-11-28 01:48:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 31105024. Throughput: 0: 2723.8, 1: 2723.6. Samples: 31119756. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 01:48:18,446][86177] Avg episode reward: [(0, '-1026.980'), (1, '-527.150')] -[2023-11-28 01:48:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000060800_15564800.pth... -[2023-11-28 01:48:18,494][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000058240_14909440.pth -[2023-11-28 01:48:18,717][87426] Updated weights for policy 1, policy_version 60720 (0.0007) -[2023-11-28 01:48:19,065][87424] Updated weights for policy 0, policy_version 60806 (0.0009) -[2023-11-28 01:48:19,090][87426] Updated weights for policy 1, policy_version 60730 (0.0009) -[2023-11-28 01:48:19,316][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000060736_15548416.pth... -[2023-11-28 01:48:19,365][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000058176_14893056.pth -[2023-11-28 01:48:19,451][87424] Updated weights for policy 0, policy_version 60816 (0.0012) -[2023-11-28 01:48:19,829][87424] Updated weights for policy 0, policy_version 60826 (0.0012) -[2023-11-28 01:48:21,153][87426] Updated weights for policy 1, policy_version 60740 (0.0011) -[2023-11-28 01:48:21,538][87426] Updated weights for policy 1, policy_version 60750 (0.0008) -[2023-11-28 01:48:21,934][87426] Updated weights for policy 1, policy_version 60760 (0.0011) -[2023-11-28 01:48:22,118][87424] Updated weights for policy 0, policy_version 60836 (0.0011) -[2023-11-28 01:48:22,495][87424] Updated weights for policy 0, policy_version 60846 (0.0016) -[2023-11-28 01:48:22,883][87424] Updated weights for policy 0, policy_version 60856 (0.0011) -[2023-11-28 01:48:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31137792. Throughput: 0: 2694.1, 1: 2734.3. Samples: 31151044. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 01:48:23,445][86177] Avg episode reward: [(0, '-989.560'), (1, '-510.040')] -[2023-11-28 01:48:23,893][87426] Updated weights for policy 1, policy_version 60770 (0.0012) -[2023-11-28 01:48:24,272][87426] Updated weights for policy 1, policy_version 60780 (0.0012) -[2023-11-28 01:48:24,656][87426] Updated weights for policy 1, policy_version 60790 (0.0012) -[2023-11-28 01:48:25,040][87426] Updated weights for policy 1, policy_version 60800 (0.0012) -[2023-11-28 01:48:25,238][87424] Updated weights for policy 0, policy_version 60866 (0.0007) -[2023-11-28 01:48:25,618][87424] Updated weights for policy 0, policy_version 60876 (0.0007) -[2023-11-28 01:48:25,997][87424] Updated weights for policy 0, policy_version 60886 (0.0011) -[2023-11-28 01:48:26,388][87424] Updated weights for policy 0, policy_version 60896 (0.0010) -[2023-11-28 01:48:27,076][87426] Updated weights for policy 1, policy_version 60810 (0.0011) -[2023-11-28 01:48:27,458][87426] Updated weights for policy 1, policy_version 60820 (0.0011) -[2023-11-28 01:48:27,827][87426] Updated weights for policy 1, policy_version 60830 (0.0011) -[2023-11-28 01:48:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31162368. Throughput: 0: 2704.7, 1: 2735.7. Samples: 31176396. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 01:48:28,445][86177] Avg episode reward: [(0, '-1010.600'), (1, '-507.930')] -[2023-11-28 01:48:28,768][87424] Updated weights for policy 0, policy_version 60906 (0.0010) -[2023-11-28 01:48:29,165][87424] Updated weights for policy 0, policy_version 60916 (0.0008) -[2023-11-28 01:48:29,545][87424] Updated weights for policy 0, policy_version 60926 (0.0007) -[2023-11-28 01:48:29,880][87426] Updated weights for policy 1, policy_version 60840 (0.0009) -[2023-11-28 01:48:30,268][87426] Updated weights for policy 1, policy_version 60850 (0.0007) -[2023-11-28 01:48:30,648][87426] Updated weights for policy 1, policy_version 60860 (0.0008) -[2023-11-28 01:48:31,665][87424] Updated weights for policy 0, policy_version 60936 (0.0011) -[2023-11-28 01:48:32,055][87424] Updated weights for policy 0, policy_version 60946 (0.0012) -[2023-11-28 01:48:32,433][87424] Updated weights for policy 0, policy_version 60956 (0.0012) -[2023-11-28 01:48:32,934][87426] Updated weights for policy 1, policy_version 60870 (0.0010) -[2023-11-28 01:48:33,326][87426] Updated weights for policy 1, policy_version 60880 (0.0012) -[2023-11-28 01:48:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 31186944. Throughput: 0: 2685.8, 1: 2741.9. Samples: 31200540. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 01:48:33,446][86177] Avg episode reward: [(0, '-1029.490'), (1, '-502.070')] -[2023-11-28 01:48:33,695][87426] Updated weights for policy 1, policy_version 60890 (0.0012) -[2023-11-28 01:48:34,591][87424] Updated weights for policy 0, policy_version 60966 (0.0009) -[2023-11-28 01:48:34,974][87424] Updated weights for policy 0, policy_version 60976 (0.0008) -[2023-11-28 01:48:35,359][87424] Updated weights for policy 0, policy_version 60986 (0.0008) -[2023-11-28 01:48:35,384][87426] Updated weights for policy 1, policy_version 60900 (0.0012) -[2023-11-28 01:48:35,776][87426] Updated weights for policy 1, policy_version 60910 (0.0011) -[2023-11-28 01:48:36,154][87426] Updated weights for policy 1, policy_version 60920 (0.0007) -[2023-11-28 01:48:37,669][87424] Updated weights for policy 0, policy_version 60996 (0.0009) -[2023-11-28 01:48:38,041][87424] Updated weights for policy 0, policy_version 61006 (0.0011) -[2023-11-28 01:48:38,428][87424] Updated weights for policy 0, policy_version 61016 (0.0008) -[2023-11-28 01:48:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 31211520. Throughput: 0: 2687.6, 1: 2763.5. Samples: 31232904. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 01:48:38,445][86177] Avg episode reward: [(0, '-932.060'), (1, '-501.800')] -[2023-11-28 01:48:38,611][87426] Updated weights for policy 1, policy_version 60930 (0.0007) -[2023-11-28 01:48:38,982][87426] Updated weights for policy 1, policy_version 60940 (0.0008) -[2023-11-28 01:48:39,361][87426] Updated weights for policy 1, policy_version 60950 (0.0008) -[2023-11-28 01:48:39,745][87426] Updated weights for policy 1, policy_version 60960 (0.0008) -[2023-11-28 01:48:40,682][87424] Updated weights for policy 0, policy_version 61026 (0.0011) -[2023-11-28 01:48:41,068][87424] Updated weights for policy 0, policy_version 61036 (0.0012) -[2023-11-28 01:48:41,451][87424] Updated weights for policy 0, policy_version 61046 (0.0010) -[2023-11-28 01:48:41,840][87424] Updated weights for policy 0, policy_version 61056 (0.0010) -[2023-11-28 01:48:42,272][87426] Updated weights for policy 1, policy_version 60970 (0.0012) -[2023-11-28 01:48:42,648][87426] Updated weights for policy 1, policy_version 60980 (0.0012) -[2023-11-28 01:48:43,028][87426] Updated weights for policy 1, policy_version 60990 (0.0011) -[2023-11-28 01:48:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31244288. Throughput: 0: 2670.9, 1: 2730.5. Samples: 31255468. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 01:48:43,446][86177] Avg episode reward: [(0, '-951.690'), (1, '-501.470')] -[2023-11-28 01:48:43,880][87424] Updated weights for policy 0, policy_version 61066 (0.0009) -[2023-11-28 01:48:44,272][87424] Updated weights for policy 0, policy_version 61076 (0.0011) -[2023-11-28 01:48:44,668][87424] Updated weights for policy 0, policy_version 61086 (0.0011) -[2023-11-28 01:48:45,560][87426] Updated weights for policy 1, policy_version 61000 (0.0008) -[2023-11-28 01:48:45,943][87426] Updated weights for policy 1, policy_version 61010 (0.0007) -[2023-11-28 01:48:46,322][87426] Updated weights for policy 1, policy_version 61020 (0.0007) -[2023-11-28 01:48:46,806][87424] Updated weights for policy 0, policy_version 61096 (0.0010) -[2023-11-28 01:48:47,187][87424] Updated weights for policy 0, policy_version 61106 (0.0007) -[2023-11-28 01:48:47,569][87424] Updated weights for policy 0, policy_version 61116 (0.0008) -[2023-11-28 01:48:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 31268864. Throughput: 0: 2674.8, 1: 2718.8. Samples: 31279344. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 01:48:48,445][86177] Avg episode reward: [(0, '-1043.360'), (1, '-504.460')] -[2023-11-28 01:48:48,774][87426] Updated weights for policy 1, policy_version 61030 (0.0010) -[2023-11-28 01:48:49,149][87426] Updated weights for policy 1, policy_version 61040 (0.0011) -[2023-11-28 01:48:49,534][87426] Updated weights for policy 1, policy_version 61050 (0.0012) -[2023-11-28 01:48:50,087][87424] Updated weights for policy 0, policy_version 61126 (0.0011) -[2023-11-28 01:48:50,472][87424] Updated weights for policy 0, policy_version 61136 (0.0012) -[2023-11-28 01:48:50,851][87424] Updated weights for policy 0, policy_version 61146 (0.0012) -[2023-11-28 01:48:51,295][87426] Updated weights for policy 1, policy_version 61060 (0.0011) -[2023-11-28 01:48:51,674][87426] Updated weights for policy 1, policy_version 61070 (0.0012) -[2023-11-28 01:48:52,057][87426] Updated weights for policy 1, policy_version 61080 (0.0011) -[2023-11-28 01:48:53,205][87424] Updated weights for policy 0, policy_version 61156 (0.0012) -[2023-11-28 01:48:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 31293440. Throughput: 0: 2672.7, 1: 2706.0. Samples: 31311688. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 01:48:53,445][86177] Avg episode reward: [(0, '-953.950'), (1, '-506.360')] -[2023-11-28 01:48:53,596][87424] Updated weights for policy 0, policy_version 61166 (0.0012) -[2023-11-28 01:48:53,973][87424] Updated weights for policy 0, policy_version 61176 (0.0011) -[2023-11-28 01:48:54,318][87426] Updated weights for policy 1, policy_version 61090 (0.0010) -[2023-11-28 01:48:54,701][87426] Updated weights for policy 1, policy_version 61100 (0.0007) -[2023-11-28 01:48:55,080][87426] Updated weights for policy 1, policy_version 61110 (0.0008) -[2023-11-28 01:48:55,467][87426] Updated weights for policy 1, policy_version 61120 (0.0008) -[2023-11-28 01:48:55,818][87424] Updated weights for policy 0, policy_version 61186 (0.0011) -[2023-11-28 01:48:56,204][87424] Updated weights for policy 0, policy_version 61196 (0.0012) -[2023-11-28 01:48:56,593][87424] Updated weights for policy 0, policy_version 61206 (0.0012) -[2023-11-28 01:48:56,973][87424] Updated weights for policy 0, policy_version 61216 (0.0012) -[2023-11-28 01:48:57,808][87426] Updated weights for policy 1, policy_version 61130 (0.0012) -[2023-11-28 01:48:58,183][87426] Updated weights for policy 1, policy_version 61140 (0.0012) -[2023-11-28 01:48:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 31318016. Throughput: 0: 2659.2, 1: 2698.3. Samples: 31336160. Policy #0 lag: (min: 3.0, avg: 21.5, max: 35.0) -[2023-11-28 01:48:58,445][86177] Avg episode reward: [(0, '-969.230'), (1, '-508.510')] -[2023-11-28 01:48:58,560][87426] Updated weights for policy 1, policy_version 61150 (0.0011) -[2023-11-28 01:48:59,159][87424] Updated weights for policy 0, policy_version 61226 (0.0010) -[2023-11-28 01:48:59,542][87424] Updated weights for policy 0, policy_version 61236 (0.0012) -[2023-11-28 01:48:59,918][87424] Updated weights for policy 0, policy_version 61246 (0.0009) -[2023-11-28 01:49:00,302][87426] Updated weights for policy 1, policy_version 61160 (0.0009) -[2023-11-28 01:49:00,680][87426] Updated weights for policy 1, policy_version 61170 (0.0008) -[2023-11-28 01:49:01,057][87426] Updated weights for policy 1, policy_version 61180 (0.0010) -[2023-11-28 01:49:01,970][87424] Updated weights for policy 0, policy_version 61256 (0.0012) -[2023-11-28 01:49:02,353][87424] Updated weights for policy 0, policy_version 61266 (0.0012) -[2023-11-28 01:49:02,740][87424] Updated weights for policy 0, policy_version 61276 (0.0012) -[2023-11-28 01:49:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31350784. Throughput: 0: 2694.6, 1: 2685.5. Samples: 31361860. Policy #0 lag: (min: 3.0, avg: 21.5, max: 35.0) -[2023-11-28 01:49:03,445][86177] Avg episode reward: [(0, '-1024.500'), (1, '-502.420')] -[2023-11-28 01:49:03,565][87426] Updated weights for policy 1, policy_version 61190 (0.0010) -[2023-11-28 01:49:03,941][87426] Updated weights for policy 1, policy_version 61200 (0.0007) -[2023-11-28 01:49:04,329][87426] Updated weights for policy 1, policy_version 61210 (0.0010) -[2023-11-28 01:49:04,752][87424] Updated weights for policy 0, policy_version 61286 (0.0012) -[2023-11-28 01:49:05,136][87424] Updated weights for policy 0, policy_version 61296 (0.0012) -[2023-11-28 01:49:05,506][87424] Updated weights for policy 0, policy_version 61306 (0.0012) -[2023-11-28 01:49:06,407][87426] Updated weights for policy 1, policy_version 61220 (0.0012) -[2023-11-28 01:49:06,788][87426] Updated weights for policy 1, policy_version 61230 (0.0012) -[2023-11-28 01:49:07,171][87426] Updated weights for policy 1, policy_version 61240 (0.0012) -[2023-11-28 01:49:07,871][87424] Updated weights for policy 0, policy_version 61316 (0.0012) -[2023-11-28 01:49:08,256][87424] Updated weights for policy 0, policy_version 61326 (0.0012) -[2023-11-28 01:49:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 31375360. Throughput: 0: 2700.4, 1: 2723.4. Samples: 31395116. Policy #0 lag: (min: 3.0, avg: 21.5, max: 35.0) -[2023-11-28 01:49:08,445][86177] Avg episode reward: [(0, '-1103.190'), (1, '-502.950')] -[2023-11-28 01:49:08,630][87424] Updated weights for policy 0, policy_version 61336 (0.0012) -[2023-11-28 01:49:09,078][87426] Updated weights for policy 1, policy_version 61250 (0.0009) -[2023-11-28 01:49:09,457][87426] Updated weights for policy 1, policy_version 61260 (0.0010) -[2023-11-28 01:49:09,833][87426] Updated weights for policy 1, policy_version 61270 (0.0009) -[2023-11-28 01:49:10,215][87426] Updated weights for policy 1, policy_version 61280 (0.0010) -[2023-11-28 01:49:10,492][87424] Updated weights for policy 0, policy_version 61346 (0.0012) -[2023-11-28 01:49:10,873][87424] Updated weights for policy 0, policy_version 61356 (0.0012) -[2023-11-28 01:49:11,257][87424] Updated weights for policy 0, policy_version 61366 (0.0012) -[2023-11-28 01:49:11,638][87424] Updated weights for policy 0, policy_version 61376 (0.0012) -[2023-11-28 01:49:12,393][87426] Updated weights for policy 1, policy_version 61290 (0.0009) -[2023-11-28 01:49:12,777][87426] Updated weights for policy 1, policy_version 61300 (0.0011) -[2023-11-28 01:49:13,152][87426] Updated weights for policy 1, policy_version 61310 (0.0010) -[2023-11-28 01:49:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31408128. Throughput: 0: 2695.5, 1: 2712.6. Samples: 31419760. Policy #0 lag: (min: 3.0, avg: 21.5, max: 35.0) -[2023-11-28 01:49:13,445][86177] Avg episode reward: [(0, '-1027.750'), (1, '-511.200')] -[2023-11-28 01:49:13,811][87424] Updated weights for policy 0, policy_version 61386 (0.0012) -[2023-11-28 01:49:14,203][87424] Updated weights for policy 0, policy_version 61396 (0.0012) -[2023-11-28 01:49:14,594][87424] Updated weights for policy 0, policy_version 61406 (0.0012) -[2023-11-28 01:49:15,088][87426] Updated weights for policy 1, policy_version 61320 (0.0011) -[2023-11-28 01:49:15,474][87426] Updated weights for policy 1, policy_version 61330 (0.0012) -[2023-11-28 01:49:15,854][87426] Updated weights for policy 1, policy_version 61340 (0.0012) -[2023-11-28 01:49:17,040][87424] Updated weights for policy 0, policy_version 61416 (0.0012) -[2023-11-28 01:49:17,438][87424] Updated weights for policy 0, policy_version 61426 (0.0013) -[2023-11-28 01:49:17,819][87426] Updated weights for policy 1, policy_version 61350 (0.0011) -[2023-11-28 01:49:17,827][87424] Updated weights for policy 0, policy_version 61436 (0.0009) -[2023-11-28 01:49:18,200][87426] Updated weights for policy 1, policy_version 61360 (0.0012) -[2023-11-28 01:49:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 31432704. Throughput: 0: 2704.5, 1: 2722.4. Samples: 31444752. Policy #0 lag: (min: 3.0, avg: 21.5, max: 35.0) -[2023-11-28 01:49:18,446][86177] Avg episode reward: [(0, '-987.350'), (1, '-507.320')] -[2023-11-28 01:49:18,580][87426] Updated weights for policy 1, policy_version 61370 (0.0012) -[2023-11-28 01:49:20,344][87424] Updated weights for policy 0, policy_version 61446 (0.0010) -[2023-11-28 01:49:20,393][87426] Updated weights for policy 1, policy_version 61380 (0.0009) -[2023-11-28 01:49:20,726][87424] Updated weights for policy 0, policy_version 61456 (0.0011) -[2023-11-28 01:49:20,775][87426] Updated weights for policy 1, policy_version 61390 (0.0011) -[2023-11-28 01:49:21,107][87424] Updated weights for policy 0, policy_version 61466 (0.0010) -[2023-11-28 01:49:21,159][87426] Updated weights for policy 1, policy_version 61400 (0.0011) -[2023-11-28 01:49:23,274][87424] Updated weights for policy 0, policy_version 61476 (0.0008) -[2023-11-28 01:49:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 31457280. Throughput: 0: 2725.4, 1: 2726.7. Samples: 31478252. Policy #0 lag: (min: 3.0, avg: 21.5, max: 35.0) -[2023-11-28 01:49:23,445][86177] Avg episode reward: [(0, '-907.720'), (1, '-511.940')] -[2023-11-28 01:49:23,629][87426] Updated weights for policy 1, policy_version 61410 (0.0011) -[2023-11-28 01:49:23,665][87424] Updated weights for policy 0, policy_version 61486 (0.0009) -[2023-11-28 01:49:24,007][87426] Updated weights for policy 1, policy_version 61420 (0.0010) -[2023-11-28 01:49:24,040][87424] Updated weights for policy 0, policy_version 61496 (0.0010) -[2023-11-28 01:49:24,390][87426] Updated weights for policy 1, policy_version 61430 (0.0010) -[2023-11-28 01:49:24,768][87426] Updated weights for policy 1, policy_version 61440 (0.0012) -[2023-11-28 01:49:26,071][87424] Updated weights for policy 0, policy_version 61506 (0.0010) -[2023-11-28 01:49:26,455][87424] Updated weights for policy 0, policy_version 61516 (0.0007) -[2023-11-28 01:49:26,718][87426] Updated weights for policy 1, policy_version 61450 (0.0010) -[2023-11-28 01:49:26,832][87424] Updated weights for policy 0, policy_version 61526 (0.0007) -[2023-11-28 01:49:27,097][87426] Updated weights for policy 1, policy_version 61460 (0.0009) -[2023-11-28 01:49:27,215][87424] Updated weights for policy 0, policy_version 61536 (0.0010) -[2023-11-28 01:49:27,482][87426] Updated weights for policy 1, policy_version 61470 (0.0008) -[2023-11-28 01:49:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31490048. Throughput: 0: 2726.7, 1: 2783.7. Samples: 31503436. Policy #0 lag: (min: 3.0, avg: 21.5, max: 35.0) -[2023-11-28 01:49:28,445][86177] Avg episode reward: [(0, '-845.560'), (1, '-511.180')] -[2023-11-28 01:49:29,001][87426] Updated weights for policy 1, policy_version 61480 (0.0011) -[2023-11-28 01:49:29,385][87426] Updated weights for policy 1, policy_version 61490 (0.0011) -[2023-11-28 01:49:29,438][87424] Updated weights for policy 0, policy_version 61546 (0.0012) -[2023-11-28 01:49:29,766][87426] Updated weights for policy 1, policy_version 61500 (0.0010) -[2023-11-28 01:49:29,832][87424] Updated weights for policy 0, policy_version 61556 (0.0010) -[2023-11-28 01:49:30,213][87424] Updated weights for policy 0, policy_version 61566 (0.0011) -[2023-11-28 01:49:32,043][87426] Updated weights for policy 1, policy_version 61510 (0.0012) -[2023-11-28 01:49:32,186][87424] Updated weights for policy 0, policy_version 61576 (0.0011) -[2023-11-28 01:49:32,420][87426] Updated weights for policy 1, policy_version 61520 (0.0012) -[2023-11-28 01:49:32,577][87424] Updated weights for policy 0, policy_version 61586 (0.0010) -[2023-11-28 01:49:32,798][87426] Updated weights for policy 1, policy_version 61530 (0.0009) -[2023-11-28 01:49:32,960][87424] Updated weights for policy 0, policy_version 61596 (0.0010) -[2023-11-28 01:49:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 31522816. Throughput: 0: 2713.0, 1: 2799.4. Samples: 31527400. Policy #0 lag: (min: 31.0, avg: 49.7, max: 68.0) -[2023-11-28 01:49:33,445][86177] Avg episode reward: [(0, '-805.290'), (1, '-508.480')] -[2023-11-28 01:49:34,855][87424] Updated weights for policy 0, policy_version 61606 (0.0012) -[2023-11-28 01:49:35,240][87424] Updated weights for policy 0, policy_version 61616 (0.0011) -[2023-11-28 01:49:35,383][87426] Updated weights for policy 1, policy_version 61540 (0.0009) -[2023-11-28 01:49:35,620][87424] Updated weights for policy 0, policy_version 61626 (0.0008) -[2023-11-28 01:49:35,776][87426] Updated weights for policy 1, policy_version 61550 (0.0011) -[2023-11-28 01:49:36,159][87426] Updated weights for policy 1, policy_version 61560 (0.0012) -[2023-11-28 01:49:37,449][87424] Updated weights for policy 0, policy_version 61636 (0.0008) -[2023-11-28 01:49:37,842][87424] Updated weights for policy 0, policy_version 61646 (0.0007) -[2023-11-28 01:49:38,219][87424] Updated weights for policy 0, policy_version 61656 (0.0009) -[2023-11-28 01:49:38,227][87426] Updated weights for policy 1, policy_version 61570 (0.0012) -[2023-11-28 01:49:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31539200. Throughput: 0: 2734.7, 1: 2779.4. Samples: 31559820. Policy #0 lag: (min: 31.0, avg: 49.7, max: 68.0) -[2023-11-28 01:49:38,445][86177] Avg episode reward: [(0, '-766.070'), (1, '-512.670')] -[2023-11-28 01:49:38,616][87426] Updated weights for policy 1, policy_version 61580 (0.0009) -[2023-11-28 01:49:38,995][87426] Updated weights for policy 1, policy_version 61590 (0.0009) -[2023-11-28 01:49:39,372][87426] Updated weights for policy 1, policy_version 61600 (0.0012) -[2023-11-28 01:49:40,774][87424] Updated weights for policy 0, policy_version 61666 (0.0010) -[2023-11-28 01:49:41,161][87424] Updated weights for policy 0, policy_version 61676 (0.0008) -[2023-11-28 01:49:41,529][87426] Updated weights for policy 1, policy_version 61610 (0.0012) -[2023-11-28 01:49:41,561][87424] Updated weights for policy 0, policy_version 61686 (0.0008) -[2023-11-28 01:49:41,912][87426] Updated weights for policy 1, policy_version 61620 (0.0010) -[2023-11-28 01:49:41,943][87424] Updated weights for policy 0, policy_version 61696 (0.0009) -[2023-11-28 01:49:42,285][87426] Updated weights for policy 1, policy_version 61630 (0.0011) -[2023-11-28 01:49:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31571968. Throughput: 0: 2737.8, 1: 2768.7. Samples: 31583952. Policy #0 lag: (min: 31.0, avg: 49.7, max: 68.0) -[2023-11-28 01:49:43,445][86177] Avg episode reward: [(0, '-805.230'), (1, '-507.630')] -[2023-11-28 01:49:44,359][87424] Updated weights for policy 0, policy_version 61706 (0.0012) -[2023-11-28 01:49:44,559][87426] Updated weights for policy 1, policy_version 61640 (0.0010) -[2023-11-28 01:49:44,744][87424] Updated weights for policy 0, policy_version 61716 (0.0009) -[2023-11-28 01:49:44,936][87426] Updated weights for policy 1, policy_version 61650 (0.0008) -[2023-11-28 01:49:45,129][87424] Updated weights for policy 0, policy_version 61726 (0.0008) -[2023-11-28 01:49:45,313][87426] Updated weights for policy 1, policy_version 61660 (0.0008) -[2023-11-28 01:49:47,034][87426] Updated weights for policy 1, policy_version 61670 (0.0011) -[2023-11-28 01:49:47,415][87426] Updated weights for policy 1, policy_version 61680 (0.0010) -[2023-11-28 01:49:47,612][87424] Updated weights for policy 0, policy_version 61736 (0.0011) -[2023-11-28 01:49:47,801][87426] Updated weights for policy 1, policy_version 61690 (0.0007) -[2023-11-28 01:49:47,992][87424] Updated weights for policy 0, policy_version 61746 (0.0012) -[2023-11-28 01:49:48,375][87424] Updated weights for policy 0, policy_version 61756 (0.0011) -[2023-11-28 01:49:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31596544. Throughput: 0: 2705.6, 1: 2778.8. Samples: 31608660. Policy #0 lag: (min: 31.0, avg: 49.7, max: 68.0) -[2023-11-28 01:49:48,446][86177] Avg episode reward: [(0, '-765.100'), (1, '-507.770')] -[2023-11-28 01:49:50,159][87426] Updated weights for policy 1, policy_version 61700 (0.0009) -[2023-11-28 01:49:50,205][87424] Updated weights for policy 0, policy_version 61766 (0.0011) -[2023-11-28 01:49:50,550][87426] Updated weights for policy 1, policy_version 61710 (0.0010) -[2023-11-28 01:49:50,597][87424] Updated weights for policy 0, policy_version 61776 (0.0010) -[2023-11-28 01:49:50,920][87426] Updated weights for policy 1, policy_version 61720 (0.0008) -[2023-11-28 01:49:50,979][87424] Updated weights for policy 0, policy_version 61786 (0.0011) -[2023-11-28 01:49:52,779][87424] Updated weights for policy 0, policy_version 61796 (0.0010) -[2023-11-28 01:49:53,161][87424] Updated weights for policy 0, policy_version 61806 (0.0011) -[2023-11-28 01:49:53,448][86177] Fps is (10 sec: 4913.4, 60 sec: 5461.0, 300 sec: 5442.8). Total num frames: 31621120. Throughput: 0: 2730.4, 1: 2740.6. Samples: 31641328. Policy #0 lag: (min: 31.0, avg: 49.7, max: 68.0) -[2023-11-28 01:49:53,449][86177] Avg episode reward: [(0, '-705.180'), (1, '-502.740')] -[2023-11-28 01:49:53,508][87426] Updated weights for policy 1, policy_version 61730 (0.0010) -[2023-11-28 01:49:53,553][87424] Updated weights for policy 0, policy_version 61816 (0.0010) -[2023-11-28 01:49:53,873][87426] Updated weights for policy 1, policy_version 61740 (0.0012) -[2023-11-28 01:49:54,260][87426] Updated weights for policy 1, policy_version 61750 (0.0011) -[2023-11-28 01:49:54,631][87426] Updated weights for policy 1, policy_version 61760 (0.0011) -[2023-11-28 01:49:55,793][87424] Updated weights for policy 0, policy_version 61826 (0.0011) -[2023-11-28 01:49:56,166][87424] Updated weights for policy 0, policy_version 61836 (0.0011) -[2023-11-28 01:49:56,500][87426] Updated weights for policy 1, policy_version 61770 (0.0008) -[2023-11-28 01:49:56,542][87424] Updated weights for policy 0, policy_version 61846 (0.0010) -[2023-11-28 01:49:56,884][87426] Updated weights for policy 1, policy_version 61780 (0.0008) -[2023-11-28 01:49:56,924][87424] Updated weights for policy 0, policy_version 61856 (0.0011) -[2023-11-28 01:49:57,267][87426] Updated weights for policy 1, policy_version 61790 (0.0007) -[2023-11-28 01:49:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 31653888. Throughput: 0: 2740.6, 1: 2735.1. Samples: 31666168. Policy #0 lag: (min: 31.0, avg: 49.7, max: 68.0) -[2023-11-28 01:49:58,445][86177] Avg episode reward: [(0, '-661.060'), (1, '-498.170')] -[2023-11-28 01:49:58,850][87424] Updated weights for policy 0, policy_version 61866 (0.0009) -[2023-11-28 01:49:59,230][87424] Updated weights for policy 0, policy_version 61876 (0.0011) -[2023-11-28 01:49:59,413][87426] Updated weights for policy 1, policy_version 61800 (0.0008) -[2023-11-28 01:49:59,623][87424] Updated weights for policy 0, policy_version 61886 (0.0011) -[2023-11-28 01:49:59,801][87426] Updated weights for policy 1, policy_version 61810 (0.0008) -[2023-11-28 01:50:00,177][87426] Updated weights for policy 1, policy_version 61820 (0.0010) -[2023-11-28 01:50:01,804][87424] Updated weights for policy 0, policy_version 61896 (0.0011) -[2023-11-28 01:50:02,191][87424] Updated weights for policy 0, policy_version 61906 (0.0011) -[2023-11-28 01:50:02,578][87424] Updated weights for policy 0, policy_version 61916 (0.0010) -[2023-11-28 01:50:02,584][87426] Updated weights for policy 1, policy_version 61830 (0.0010) -[2023-11-28 01:50:02,961][87426] Updated weights for policy 1, policy_version 61840 (0.0008) -[2023-11-28 01:50:03,347][87426] Updated weights for policy 1, policy_version 61850 (0.0007) -[2023-11-28 01:50:03,444][86177] Fps is (10 sec: 5736.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31678464. Throughput: 0: 2734.4, 1: 2720.4. Samples: 31690216. Policy #0 lag: (min: 31.0, avg: 49.7, max: 68.0) -[2023-11-28 01:50:03,445][86177] Avg episode reward: [(0, '-702.420'), (1, '-497.120')] -[2023-11-28 01:50:04,619][87424] Updated weights for policy 0, policy_version 61926 (0.0010) -[2023-11-28 01:50:05,009][87424] Updated weights for policy 0, policy_version 61936 (0.0012) -[2023-11-28 01:50:05,376][87424] Updated weights for policy 0, policy_version 61946 (0.0011) -[2023-11-28 01:50:05,439][87426] Updated weights for policy 1, policy_version 61860 (0.0008) -[2023-11-28 01:50:05,821][87426] Updated weights for policy 1, policy_version 61870 (0.0012) -[2023-11-28 01:50:06,195][87426] Updated weights for policy 1, policy_version 61880 (0.0012) -[2023-11-28 01:50:07,876][87424] Updated weights for policy 0, policy_version 61956 (0.0012) -[2023-11-28 01:50:08,123][87426] Updated weights for policy 1, policy_version 61890 (0.0011) -[2023-11-28 01:50:08,255][87424] Updated weights for policy 0, policy_version 61966 (0.0011) -[2023-11-28 01:50:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31703040. Throughput: 0: 2732.8, 1: 2725.0. Samples: 31723852. Policy #0 lag: (min: 31.0, avg: 49.7, max: 68.0) -[2023-11-28 01:50:08,445][86177] Avg episode reward: [(0, '-742.610'), (1, '-496.010')] -[2023-11-28 01:50:08,504][87426] Updated weights for policy 1, policy_version 61900 (0.0011) -[2023-11-28 01:50:08,644][87424] Updated weights for policy 0, policy_version 61976 (0.0008) -[2023-11-28 01:50:08,877][87426] Updated weights for policy 1, policy_version 61910 (0.0012) -[2023-11-28 01:50:09,258][87426] Updated weights for policy 1, policy_version 61920 (0.0009) -[2023-11-28 01:50:11,014][87424] Updated weights for policy 0, policy_version 61986 (0.0008) -[2023-11-28 01:50:11,329][87426] Updated weights for policy 1, policy_version 61930 (0.0011) -[2023-11-28 01:50:11,401][87424] Updated weights for policy 0, policy_version 61996 (0.0012) -[2023-11-28 01:50:11,699][87426] Updated weights for policy 1, policy_version 61940 (0.0011) -[2023-11-28 01:50:11,786][87424] Updated weights for policy 0, policy_version 62006 (0.0012) -[2023-11-28 01:50:12,075][87426] Updated weights for policy 1, policy_version 61950 (0.0011) -[2023-11-28 01:50:12,162][87424] Updated weights for policy 0, policy_version 62016 (0.0010) -[2023-11-28 01:50:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31735808. Throughput: 0: 2738.6, 1: 2701.5. Samples: 31748240. Policy #0 lag: (min: 31.0, avg: 49.7, max: 68.0) -[2023-11-28 01:50:13,445][86177] Avg episode reward: [(0, '-764.380'), (1, '-501.480')] -[2023-11-28 01:50:14,297][87424] Updated weights for policy 0, policy_version 62026 (0.0012) -[2023-11-28 01:50:14,660][87426] Updated weights for policy 1, policy_version 61960 (0.0011) -[2023-11-28 01:50:14,691][87424] Updated weights for policy 0, policy_version 62036 (0.0011) -[2023-11-28 01:50:15,038][87426] Updated weights for policy 1, policy_version 61970 (0.0011) -[2023-11-28 01:50:15,067][87424] Updated weights for policy 0, policy_version 62046 (0.0013) -[2023-11-28 01:50:15,425][87426] Updated weights for policy 1, policy_version 61980 (0.0011) -[2023-11-28 01:50:17,055][87424] Updated weights for policy 0, policy_version 62056 (0.0009) -[2023-11-28 01:50:17,435][87424] Updated weights for policy 0, policy_version 62066 (0.0010) -[2023-11-28 01:50:17,825][87424] Updated weights for policy 0, policy_version 62076 (0.0008) -[2023-11-28 01:50:17,931][87426] Updated weights for policy 1, policy_version 61990 (0.0009) -[2023-11-28 01:50:18,319][87426] Updated weights for policy 1, policy_version 62000 (0.0007) -[2023-11-28 01:50:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 31760384. Throughput: 0: 2760.4, 1: 2710.8. Samples: 31773604. Policy #0 lag: (min: 26.0, avg: 52.9, max: 58.0) -[2023-11-28 01:50:18,445][86177] Avg episode reward: [(0, '-729.180'), (1, '-504.340')] -[2023-11-28 01:50:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000062080_15892480.pth... -[2023-11-28 01:50:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000059520_15237120.pth -[2023-11-28 01:50:18,701][87426] Updated weights for policy 1, policy_version 62010 (0.0007) -[2023-11-28 01:50:18,927][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000062016_15876096.pth... -[2023-11-28 01:50:18,958][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000059456_15220736.pth -[2023-11-28 01:50:19,584][87424] Updated weights for policy 0, policy_version 62086 (0.0011) -[2023-11-28 01:50:19,962][87424] Updated weights for policy 0, policy_version 62096 (0.0011) -[2023-11-28 01:50:20,351][87424] Updated weights for policy 0, policy_version 62106 (0.0012) -[2023-11-28 01:50:20,832][87426] Updated weights for policy 1, policy_version 62020 (0.0010) -[2023-11-28 01:50:21,209][87426] Updated weights for policy 1, policy_version 62030 (0.0011) -[2023-11-28 01:50:21,602][87426] Updated weights for policy 1, policy_version 62040 (0.0012) -[2023-11-28 01:50:22,067][87424] Updated weights for policy 0, policy_version 62116 (0.0011) -[2023-11-28 01:50:22,447][87424] Updated weights for policy 0, policy_version 62126 (0.0013) -[2023-11-28 01:50:22,831][87424] Updated weights for policy 0, policy_version 62136 (0.0009) -[2023-11-28 01:50:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 31793152. Throughput: 0: 2741.5, 1: 2727.5. Samples: 31805924. Policy #0 lag: (min: 26.0, avg: 52.9, max: 58.0) -[2023-11-28 01:50:23,445][86177] Avg episode reward: [(0, '-710.490'), (1, '-504.580')] -[2023-11-28 01:50:23,597][87426] Updated weights for policy 1, policy_version 62050 (0.0011) -[2023-11-28 01:50:23,978][87426] Updated weights for policy 1, policy_version 62060 (0.0008) -[2023-11-28 01:50:24,357][87426] Updated weights for policy 1, policy_version 62070 (0.0007) -[2023-11-28 01:50:24,733][87426] Updated weights for policy 1, policy_version 62080 (0.0008) -[2023-11-28 01:50:25,388][87424] Updated weights for policy 0, policy_version 62146 (0.0009) -[2023-11-28 01:50:25,769][87424] Updated weights for policy 0, policy_version 62156 (0.0008) -[2023-11-28 01:50:26,152][87424] Updated weights for policy 0, policy_version 62166 (0.0007) -[2023-11-28 01:50:26,524][87424] Updated weights for policy 0, policy_version 62176 (0.0008) -[2023-11-28 01:50:26,958][87426] Updated weights for policy 1, policy_version 62090 (0.0012) -[2023-11-28 01:50:27,342][87426] Updated weights for policy 1, policy_version 62100 (0.0012) -[2023-11-28 01:50:27,719][87426] Updated weights for policy 1, policy_version 62110 (0.0010) -[2023-11-28 01:50:28,160][87424] Updated weights for policy 0, policy_version 62186 (0.0008) -[2023-11-28 01:50:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31817728. Throughput: 0: 2752.5, 1: 2747.4. Samples: 31831448. Policy #0 lag: (min: 26.0, avg: 52.9, max: 58.0) -[2023-11-28 01:50:28,445][86177] Avg episode reward: [(0, '-586.390'), (1, '-520.000')] -[2023-11-28 01:50:28,538][87424] Updated weights for policy 0, policy_version 62196 (0.0008) -[2023-11-28 01:50:28,928][87424] Updated weights for policy 0, policy_version 62206 (0.0008) -[2023-11-28 01:50:29,823][87426] Updated weights for policy 1, policy_version 62120 (0.0009) -[2023-11-28 01:50:30,201][87426] Updated weights for policy 1, policy_version 62130 (0.0008) -[2023-11-28 01:50:30,580][87426] Updated weights for policy 1, policy_version 62140 (0.0008) -[2023-11-28 01:50:31,224][87424] Updated weights for policy 0, policy_version 62216 (0.0011) -[2023-11-28 01:50:31,624][87424] Updated weights for policy 0, policy_version 62226 (0.0012) -[2023-11-28 01:50:32,001][87424] Updated weights for policy 0, policy_version 62236 (0.0012) -[2023-11-28 01:50:32,680][87426] Updated weights for policy 1, policy_version 62150 (0.0009) -[2023-11-28 01:50:33,058][87426] Updated weights for policy 1, policy_version 62160 (0.0009) -[2023-11-28 01:50:33,439][87426] Updated weights for policy 1, policy_version 62170 (0.0011) -[2023-11-28 01:50:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 31842304. Throughput: 0: 2759.2, 1: 2740.8. Samples: 31856160. Policy #0 lag: (min: 26.0, avg: 52.9, max: 58.0) -[2023-11-28 01:50:33,445][86177] Avg episode reward: [(0, '-548.510'), (1, '-530.270')] -[2023-11-28 01:50:34,512][87424] Updated weights for policy 0, policy_version 62246 (0.0012) -[2023-11-28 01:50:34,901][87424] Updated weights for policy 0, policy_version 62256 (0.0012) -[2023-11-28 01:50:35,280][87424] Updated weights for policy 0, policy_version 62266 (0.0012) -[2023-11-28 01:50:35,487][87426] Updated weights for policy 1, policy_version 62180 (0.0011) -[2023-11-28 01:50:35,862][87426] Updated weights for policy 1, policy_version 62190 (0.0007) -[2023-11-28 01:50:36,243][87426] Updated weights for policy 1, policy_version 62200 (0.0007) -[2023-11-28 01:50:37,514][87424] Updated weights for policy 0, policy_version 62276 (0.0012) -[2023-11-28 01:50:37,893][87424] Updated weights for policy 0, policy_version 62286 (0.0012) -[2023-11-28 01:50:38,277][87424] Updated weights for policy 0, policy_version 62296 (0.0012) -[2023-11-28 01:50:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31866880. Throughput: 0: 2750.1, 1: 2741.0. Samples: 31888408. Policy #0 lag: (min: 26.0, avg: 52.9, max: 58.0) -[2023-11-28 01:50:38,445][86177] Avg episode reward: [(0, '-546.810'), (1, '-533.070')] -[2023-11-28 01:50:38,618][87426] Updated weights for policy 1, policy_version 62210 (0.0007) -[2023-11-28 01:50:39,007][87426] Updated weights for policy 1, policy_version 62220 (0.0009) -[2023-11-28 01:50:39,376][87426] Updated weights for policy 1, policy_version 62230 (0.0011) -[2023-11-28 01:50:39,756][87426] Updated weights for policy 1, policy_version 62240 (0.0010) -[2023-11-28 01:50:40,372][87424] Updated weights for policy 0, policy_version 62306 (0.0012) -[2023-11-28 01:50:40,748][87424] Updated weights for policy 0, policy_version 62316 (0.0011) -[2023-11-28 01:50:41,129][87424] Updated weights for policy 0, policy_version 62326 (0.0012) -[2023-11-28 01:50:41,514][87424] Updated weights for policy 0, policy_version 62336 (0.0012) -[2023-11-28 01:50:41,771][87426] Updated weights for policy 1, policy_version 62250 (0.0011) -[2023-11-28 01:50:42,155][87426] Updated weights for policy 1, policy_version 62260 (0.0009) -[2023-11-28 01:50:42,541][87426] Updated weights for policy 1, policy_version 62270 (0.0010) -[2023-11-28 01:50:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 31899648. Throughput: 0: 2746.6, 1: 2740.6. Samples: 31913092. Policy #0 lag: (min: 26.0, avg: 52.9, max: 58.0) -[2023-11-28 01:50:43,446][86177] Avg episode reward: [(0, '-621.600'), (1, '-545.810')] -[2023-11-28 01:50:43,949][87424] Updated weights for policy 0, policy_version 62346 (0.0012) -[2023-11-28 01:50:44,330][87424] Updated weights for policy 0, policy_version 62356 (0.0012) -[2023-11-28 01:50:44,714][87424] Updated weights for policy 0, policy_version 62366 (0.0011) -[2023-11-28 01:50:44,831][87426] Updated weights for policy 1, policy_version 62280 (0.0011) -[2023-11-28 01:50:45,214][87426] Updated weights for policy 1, policy_version 62290 (0.0011) -[2023-11-28 01:50:45,593][87426] Updated weights for policy 1, policy_version 62300 (0.0008) -[2023-11-28 01:50:46,716][87424] Updated weights for policy 0, policy_version 62376 (0.0008) -[2023-11-28 01:50:47,094][87424] Updated weights for policy 0, policy_version 62386 (0.0007) -[2023-11-28 01:50:47,488][87424] Updated weights for policy 0, policy_version 62396 (0.0007) -[2023-11-28 01:50:47,576][87426] Updated weights for policy 1, policy_version 62310 (0.0010) -[2023-11-28 01:50:47,965][87426] Updated weights for policy 1, policy_version 62320 (0.0011) -[2023-11-28 01:50:48,343][87426] Updated weights for policy 1, policy_version 62330 (0.0009) -[2023-11-28 01:50:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 31924224. Throughput: 0: 2760.6, 1: 2736.1. Samples: 31937568. Policy #0 lag: (min: 26.0, avg: 52.9, max: 58.0) -[2023-11-28 01:50:48,445][86177] Avg episode reward: [(0, '-621.830'), (1, '-529.430')] -[2023-11-28 01:50:49,893][87424] Updated weights for policy 0, policy_version 62406 (0.0010) -[2023-11-28 01:50:50,265][87424] Updated weights for policy 0, policy_version 62416 (0.0011) -[2023-11-28 01:50:50,598][87426] Updated weights for policy 1, policy_version 62340 (0.0009) -[2023-11-28 01:50:50,644][87424] Updated weights for policy 0, policy_version 62426 (0.0010) -[2023-11-28 01:50:50,971][87426] Updated weights for policy 1, policy_version 62350 (0.0012) -[2023-11-28 01:50:51,353][87426] Updated weights for policy 1, policy_version 62360 (0.0012) -[2023-11-28 01:50:52,648][87424] Updated weights for policy 0, policy_version 62436 (0.0010) -[2023-11-28 01:50:53,031][87424] Updated weights for policy 0, policy_version 62446 (0.0012) -[2023-11-28 01:50:53,383][87426] Updated weights for policy 1, policy_version 62370 (0.0011) -[2023-11-28 01:50:53,419][87424] Updated weights for policy 0, policy_version 62456 (0.0011) -[2023-11-28 01:50:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.7, 300 sec: 5442.8). Total num frames: 31948800. Throughput: 0: 2742.3, 1: 2722.9. Samples: 31969788. Policy #0 lag: (min: 26.0, avg: 52.9, max: 58.0) -[2023-11-28 01:50:53,445][86177] Avg episode reward: [(0, '-711.490'), (1, '-554.190')] -[2023-11-28 01:50:53,765][87426] Updated weights for policy 1, policy_version 62380 (0.0011) -[2023-11-28 01:50:54,155][87426] Updated weights for policy 1, policy_version 62390 (0.0009) -[2023-11-28 01:50:54,526][87426] Updated weights for policy 1, policy_version 62400 (0.0011) -[2023-11-28 01:50:55,609][87424] Updated weights for policy 0, policy_version 62466 (0.0011) -[2023-11-28 01:50:55,993][87424] Updated weights for policy 0, policy_version 62476 (0.0012) -[2023-11-28 01:50:56,372][87424] Updated weights for policy 0, policy_version 62486 (0.0011) -[2023-11-28 01:50:56,727][87426] Updated weights for policy 1, policy_version 62410 (0.0008) -[2023-11-28 01:50:56,775][87424] Updated weights for policy 0, policy_version 62496 (0.0008) -[2023-11-28 01:50:57,107][87426] Updated weights for policy 1, policy_version 62420 (0.0008) -[2023-11-28 01:50:57,493][87426] Updated weights for policy 1, policy_version 62430 (0.0008) -[2023-11-28 01:50:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 31981568. Throughput: 0: 2749.5, 1: 2735.4. Samples: 31995060. Policy #0 lag: (min: 31.0, avg: 34.4, max: 58.0) -[2023-11-28 01:50:58,445][86177] Avg episode reward: [(0, '-744.580'), (1, '-548.150')] -[2023-11-28 01:50:58,610][87424] Updated weights for policy 0, policy_version 62506 (0.0010) -[2023-11-28 01:50:58,995][87424] Updated weights for policy 0, policy_version 62516 (0.0010) -[2023-11-28 01:50:59,381][87424] Updated weights for policy 0, policy_version 62526 (0.0009) -[2023-11-28 01:50:59,614][87426] Updated weights for policy 1, policy_version 62440 (0.0011) -[2023-11-28 01:50:59,987][87426] Updated weights for policy 1, policy_version 62450 (0.0012) -[2023-11-28 01:51:00,367][87426] Updated weights for policy 1, policy_version 62460 (0.0011) -[2023-11-28 01:51:01,594][87424] Updated weights for policy 0, policy_version 62536 (0.0011) -[2023-11-28 01:51:01,980][87424] Updated weights for policy 0, policy_version 62546 (0.0010) -[2023-11-28 01:51:02,352][87424] Updated weights for policy 0, policy_version 62556 (0.0011) -[2023-11-28 01:51:02,404][87426] Updated weights for policy 1, policy_version 62470 (0.0011) -[2023-11-28 01:51:02,787][87426] Updated weights for policy 1, policy_version 62480 (0.0011) -[2023-11-28 01:51:03,166][87426] Updated weights for policy 1, policy_version 62490 (0.0012) -[2023-11-28 01:51:03,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 32014336. Throughput: 0: 2735.9, 1: 2732.0. Samples: 32019660. Policy #0 lag: (min: 31.0, avg: 34.4, max: 58.0) -[2023-11-28 01:51:03,445][86177] Avg episode reward: [(0, '-747.980'), (1, '-546.860')] -[2023-11-28 01:51:04,513][87424] Updated weights for policy 0, policy_version 62566 (0.0012) -[2023-11-28 01:51:04,897][87424] Updated weights for policy 0, policy_version 62576 (0.0012) -[2023-11-28 01:51:05,270][87424] Updated weights for policy 0, policy_version 62586 (0.0012) -[2023-11-28 01:51:05,579][87426] Updated weights for policy 1, policy_version 62500 (0.0012) -[2023-11-28 01:51:05,953][87426] Updated weights for policy 1, policy_version 62510 (0.0012) -[2023-11-28 01:51:06,328][87426] Updated weights for policy 1, policy_version 62520 (0.0008) -[2023-11-28 01:51:07,658][87424] Updated weights for policy 0, policy_version 62596 (0.0010) -[2023-11-28 01:51:08,040][87424] Updated weights for policy 0, policy_version 62606 (0.0011) -[2023-11-28 01:51:08,432][87424] Updated weights for policy 0, policy_version 62616 (0.0009) -[2023-11-28 01:51:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32030720. Throughput: 0: 2734.4, 1: 2731.8. Samples: 32051904. Policy #0 lag: (min: 31.0, avg: 34.4, max: 58.0) -[2023-11-28 01:51:08,445][86177] Avg episode reward: [(0, '-684.850'), (1, '-547.920')] -[2023-11-28 01:51:08,499][87426] Updated weights for policy 1, policy_version 62530 (0.0012) -[2023-11-28 01:51:08,878][87426] Updated weights for policy 1, policy_version 62540 (0.0009) -[2023-11-28 01:51:09,255][87426] Updated weights for policy 1, policy_version 62550 (0.0012) -[2023-11-28 01:51:09,639][87426] Updated weights for policy 1, policy_version 62560 (0.0012) -[2023-11-28 01:51:10,547][87424] Updated weights for policy 0, policy_version 62626 (0.0009) -[2023-11-28 01:51:10,924][87424] Updated weights for policy 0, policy_version 62636 (0.0009) -[2023-11-28 01:51:11,313][87424] Updated weights for policy 0, policy_version 62646 (0.0008) -[2023-11-28 01:51:11,701][87424] Updated weights for policy 0, policy_version 62656 (0.0010) -[2023-11-28 01:51:11,983][87426] Updated weights for policy 1, policy_version 62570 (0.0011) -[2023-11-28 01:51:12,364][87426] Updated weights for policy 1, policy_version 62580 (0.0009) -[2023-11-28 01:51:12,746][87426] Updated weights for policy 1, policy_version 62590 (0.0012) -[2023-11-28 01:51:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32063488. Throughput: 0: 2733.2, 1: 2723.6. Samples: 32077000. Policy #0 lag: (min: 31.0, avg: 34.4, max: 58.0) -[2023-11-28 01:51:13,445][86177] Avg episode reward: [(0, '-739.660'), (1, '-511.100')] -[2023-11-28 01:51:13,765][87424] Updated weights for policy 0, policy_version 62666 (0.0008) -[2023-11-28 01:51:14,146][87424] Updated weights for policy 0, policy_version 62676 (0.0007) -[2023-11-28 01:51:14,527][87424] Updated weights for policy 0, policy_version 62686 (0.0008) -[2023-11-28 01:51:15,121][87426] Updated weights for policy 1, policy_version 62600 (0.0014) -[2023-11-28 01:51:15,501][87426] Updated weights for policy 1, policy_version 62610 (0.0011) -[2023-11-28 01:51:15,879][87426] Updated weights for policy 1, policy_version 62620 (0.0012) -[2023-11-28 01:51:16,302][87424] Updated weights for policy 0, policy_version 62696 (0.0011) -[2023-11-28 01:51:16,687][87424] Updated weights for policy 0, policy_version 62706 (0.0012) -[2023-11-28 01:51:17,066][87424] Updated weights for policy 0, policy_version 62716 (0.0012) -[2023-11-28 01:51:17,727][87426] Updated weights for policy 1, policy_version 62630 (0.0009) -[2023-11-28 01:51:18,108][87426] Updated weights for policy 1, policy_version 62640 (0.0007) -[2023-11-28 01:51:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32088064. Throughput: 0: 2739.0, 1: 2720.9. Samples: 32101856. Policy #0 lag: (min: 31.0, avg: 34.4, max: 58.0) -[2023-11-28 01:51:18,445][86177] Avg episode reward: [(0, '-639.040'), (1, '-510.830')] -[2023-11-28 01:51:18,501][87426] Updated weights for policy 1, policy_version 62650 (0.0007) -[2023-11-28 01:51:19,448][87424] Updated weights for policy 0, policy_version 62726 (0.0012) -[2023-11-28 01:51:19,830][87424] Updated weights for policy 0, policy_version 62736 (0.0011) -[2023-11-28 01:51:20,225][87424] Updated weights for policy 0, policy_version 62746 (0.0011) -[2023-11-28 01:51:20,622][87426] Updated weights for policy 1, policy_version 62660 (0.0008) -[2023-11-28 01:51:20,994][87426] Updated weights for policy 1, policy_version 62670 (0.0007) -[2023-11-28 01:51:21,375][87426] Updated weights for policy 1, policy_version 62680 (0.0010) -[2023-11-28 01:51:22,392][87424] Updated weights for policy 0, policy_version 62756 (0.0012) -[2023-11-28 01:51:22,769][87424] Updated weights for policy 0, policy_version 62766 (0.0012) -[2023-11-28 01:51:23,153][87424] Updated weights for policy 0, policy_version 62776 (0.0009) -[2023-11-28 01:51:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32112640. Throughput: 0: 2748.4, 1: 2744.7. Samples: 32135600. Policy #0 lag: (min: 31.0, avg: 34.4, max: 58.0) -[2023-11-28 01:51:23,445][86177] Avg episode reward: [(0, '-626.600'), (1, '-576.830')] -[2023-11-28 01:51:23,860][87426] Updated weights for policy 1, policy_version 62690 (0.0011) -[2023-11-28 01:51:24,242][87426] Updated weights for policy 1, policy_version 62700 (0.0007) -[2023-11-28 01:51:24,621][87426] Updated weights for policy 1, policy_version 62710 (0.0007) -[2023-11-28 01:51:24,997][87426] Updated weights for policy 1, policy_version 62720 (0.0008) -[2023-11-28 01:51:25,730][87424] Updated weights for policy 0, policy_version 62786 (0.0007) -[2023-11-28 01:51:26,114][87424] Updated weights for policy 0, policy_version 62796 (0.0008) -[2023-11-28 01:51:26,498][87424] Updated weights for policy 0, policy_version 62806 (0.0007) -[2023-11-28 01:51:26,846][87426] Updated weights for policy 1, policy_version 62730 (0.0007) -[2023-11-28 01:51:26,885][87424] Updated weights for policy 0, policy_version 62816 (0.0007) -[2023-11-28 01:51:27,220][87426] Updated weights for policy 1, policy_version 62740 (0.0007) -[2023-11-28 01:51:27,597][87426] Updated weights for policy 1, policy_version 62750 (0.0007) -[2023-11-28 01:51:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32145408. Throughput: 0: 2740.4, 1: 2741.7. Samples: 32159784. Policy #0 lag: (min: 31.0, avg: 34.4, max: 58.0) -[2023-11-28 01:51:28,445][86177] Avg episode reward: [(0, '-624.280'), (1, '-578.060')] -[2023-11-28 01:51:28,658][87424] Updated weights for policy 0, policy_version 62826 (0.0012) -[2023-11-28 01:51:29,042][87424] Updated weights for policy 0, policy_version 62836 (0.0012) -[2023-11-28 01:51:29,433][87424] Updated weights for policy 0, policy_version 62846 (0.0011) -[2023-11-28 01:51:29,743][87426] Updated weights for policy 1, policy_version 62760 (0.0010) -[2023-11-28 01:51:30,120][87426] Updated weights for policy 1, policy_version 62770 (0.0008) -[2023-11-28 01:51:30,501][87426] Updated weights for policy 1, policy_version 62780 (0.0008) -[2023-11-28 01:51:31,183][87424] Updated weights for policy 0, policy_version 62856 (0.0011) -[2023-11-28 01:51:31,571][87424] Updated weights for policy 0, policy_version 62866 (0.0008) -[2023-11-28 01:51:31,946][87424] Updated weights for policy 0, policy_version 62876 (0.0011) -[2023-11-28 01:51:32,543][87426] Updated weights for policy 1, policy_version 62790 (0.0007) -[2023-11-28 01:51:32,915][87426] Updated weights for policy 1, policy_version 62800 (0.0008) -[2023-11-28 01:51:33,306][87426] Updated weights for policy 1, policy_version 62810 (0.0007) -[2023-11-28 01:51:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32169984. Throughput: 0: 2746.0, 1: 2745.2. Samples: 32184672. Policy #0 lag: (min: 31.0, avg: 34.4, max: 58.0) -[2023-11-28 01:51:33,445][86177] Avg episode reward: [(0, '-621.400'), (1, '-574.420')] -[2023-11-28 01:51:34,420][87424] Updated weights for policy 0, policy_version 62886 (0.0012) -[2023-11-28 01:51:34,801][87424] Updated weights for policy 0, policy_version 62896 (0.0012) -[2023-11-28 01:51:35,187][87424] Updated weights for policy 0, policy_version 62906 (0.0012) -[2023-11-28 01:51:35,487][87426] Updated weights for policy 1, policy_version 62820 (0.0011) -[2023-11-28 01:51:35,863][87426] Updated weights for policy 1, policy_version 62830 (0.0011) -[2023-11-28 01:51:36,248][87426] Updated weights for policy 1, policy_version 62840 (0.0011) -[2023-11-28 01:51:37,560][87424] Updated weights for policy 0, policy_version 62916 (0.0011) -[2023-11-28 01:51:37,944][87424] Updated weights for policy 0, policy_version 62926 (0.0012) -[2023-11-28 01:51:38,331][87424] Updated weights for policy 0, policy_version 62936 (0.0012) -[2023-11-28 01:51:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32194560. Throughput: 0: 2723.6, 1: 2751.8. Samples: 32216180. Policy #0 lag: (min: 31.0, avg: 34.4, max: 58.0) -[2023-11-28 01:51:38,445][86177] Avg episode reward: [(0, '-603.610'), (1, '-572.540')] -[2023-11-28 01:51:38,744][87426] Updated weights for policy 1, policy_version 62850 (0.0010) -[2023-11-28 01:51:39,134][87426] Updated weights for policy 1, policy_version 62860 (0.0011) -[2023-11-28 01:51:39,519][87426] Updated weights for policy 1, policy_version 62870 (0.0011) -[2023-11-28 01:51:39,900][87426] Updated weights for policy 1, policy_version 62880 (0.0011) -[2023-11-28 01:51:40,163][87424] Updated weights for policy 0, policy_version 62946 (0.0011) -[2023-11-28 01:51:40,541][87424] Updated weights for policy 0, policy_version 62956 (0.0011) -[2023-11-28 01:51:40,930][87424] Updated weights for policy 0, policy_version 62966 (0.0011) -[2023-11-28 01:51:41,313][87424] Updated weights for policy 0, policy_version 62976 (0.0011) -[2023-11-28 01:51:42,384][87426] Updated weights for policy 1, policy_version 62890 (0.0011) -[2023-11-28 01:51:42,766][87426] Updated weights for policy 1, policy_version 62900 (0.0012) -[2023-11-28 01:51:43,145][87426] Updated weights for policy 1, policy_version 62910 (0.0011) -[2023-11-28 01:51:43,380][87424] Updated weights for policy 0, policy_version 62986 (0.0009) -[2023-11-28 01:51:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32227328. Throughput: 0: 2713.1, 1: 2734.2. Samples: 32240188. Policy #0 lag: (min: 21.0, avg: 36.4, max: 53.0) -[2023-11-28 01:51:43,445][86177] Avg episode reward: [(0, '-566.150'), (1, '-574.900')] -[2023-11-28 01:51:43,779][87424] Updated weights for policy 0, policy_version 62996 (0.0011) -[2023-11-28 01:51:44,161][87424] Updated weights for policy 0, policy_version 63006 (0.0012) -[2023-11-28 01:51:44,984][87426] Updated weights for policy 1, policy_version 62920 (0.0011) -[2023-11-28 01:51:45,363][87426] Updated weights for policy 1, policy_version 62930 (0.0012) -[2023-11-28 01:51:45,735][87426] Updated weights for policy 1, policy_version 62940 (0.0012) -[2023-11-28 01:51:46,091][87424] Updated weights for policy 0, policy_version 63016 (0.0010) -[2023-11-28 01:51:46,478][87424] Updated weights for policy 0, policy_version 63026 (0.0007) -[2023-11-28 01:51:46,862][87424] Updated weights for policy 0, policy_version 63036 (0.0008) -[2023-11-28 01:51:48,047][87426] Updated weights for policy 1, policy_version 62950 (0.0012) -[2023-11-28 01:51:48,431][87426] Updated weights for policy 1, policy_version 62960 (0.0011) -[2023-11-28 01:51:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32251904. Throughput: 0: 2723.8, 1: 2720.3. Samples: 32264644. Policy #0 lag: (min: 21.0, avg: 36.4, max: 53.0) -[2023-11-28 01:51:48,445][86177] Avg episode reward: [(0, '-646.010'), (1, '-515.460')] -[2023-11-28 01:51:48,802][87426] Updated weights for policy 1, policy_version 62970 (0.0010) -[2023-11-28 01:51:49,216][87424] Updated weights for policy 0, policy_version 63046 (0.0010) -[2023-11-28 01:51:49,587][87424] Updated weights for policy 0, policy_version 63056 (0.0011) -[2023-11-28 01:51:49,972][87424] Updated weights for policy 0, policy_version 63066 (0.0009) -[2023-11-28 01:51:50,975][87426] Updated weights for policy 1, policy_version 62980 (0.0010) -[2023-11-28 01:51:51,351][87426] Updated weights for policy 1, policy_version 62990 (0.0009) -[2023-11-28 01:51:51,732][87426] Updated weights for policy 1, policy_version 63000 (0.0011) -[2023-11-28 01:51:51,892][87424] Updated weights for policy 0, policy_version 63076 (0.0011) -[2023-11-28 01:51:52,288][87424] Updated weights for policy 0, policy_version 63086 (0.0009) -[2023-11-28 01:51:52,671][87424] Updated weights for policy 0, policy_version 63096 (0.0007) -[2023-11-28 01:51:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 32284672. Throughput: 0: 2740.8, 1: 2726.7. Samples: 32297940. Policy #0 lag: (min: 21.0, avg: 36.4, max: 53.0) -[2023-11-28 01:51:53,445][86177] Avg episode reward: [(0, '-645.660'), (1, '-514.850')] -[2023-11-28 01:51:53,869][87426] Updated weights for policy 1, policy_version 63010 (0.0011) -[2023-11-28 01:51:54,246][87426] Updated weights for policy 1, policy_version 63020 (0.0009) -[2023-11-28 01:51:54,624][87426] Updated weights for policy 1, policy_version 63030 (0.0007) -[2023-11-28 01:51:54,662][87424] Updated weights for policy 0, policy_version 63106 (0.0008) -[2023-11-28 01:51:55,005][87426] Updated weights for policy 1, policy_version 63040 (0.0008) -[2023-11-28 01:51:55,043][87424] Updated weights for policy 0, policy_version 63116 (0.0011) -[2023-11-28 01:51:55,422][87424] Updated weights for policy 0, policy_version 63126 (0.0007) -[2023-11-28 01:51:55,804][87424] Updated weights for policy 0, policy_version 63136 (0.0008) -[2023-11-28 01:51:56,926][87426] Updated weights for policy 1, policy_version 63050 (0.0011) -[2023-11-28 01:51:57,310][87426] Updated weights for policy 1, policy_version 63060 (0.0008) -[2023-11-28 01:51:57,688][87426] Updated weights for policy 1, policy_version 63070 (0.0009) -[2023-11-28 01:51:57,904][87424] Updated weights for policy 0, policy_version 63146 (0.0012) -[2023-11-28 01:51:58,288][87424] Updated weights for policy 0, policy_version 63156 (0.0011) -[2023-11-28 01:51:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32309248. Throughput: 0: 2724.8, 1: 2742.4. Samples: 32323024. Policy #0 lag: (min: 21.0, avg: 36.4, max: 53.0) -[2023-11-28 01:51:58,445][86177] Avg episode reward: [(0, '-676.790'), (1, '-515.030')] -[2023-11-28 01:51:58,673][87424] Updated weights for policy 0, policy_version 63166 (0.0012) -[2023-11-28 01:51:59,537][87426] Updated weights for policy 1, policy_version 63080 (0.0012) -[2023-11-28 01:51:59,929][87426] Updated weights for policy 1, policy_version 63090 (0.0012) -[2023-11-28 01:52:00,301][87426] Updated weights for policy 1, policy_version 63100 (0.0012) -[2023-11-28 01:52:01,055][87424] Updated weights for policy 0, policy_version 63176 (0.0012) -[2023-11-28 01:52:01,454][87424] Updated weights for policy 0, policy_version 63186 (0.0012) -[2023-11-28 01:52:01,836][87424] Updated weights for policy 0, policy_version 63196 (0.0011) -[2023-11-28 01:52:02,621][87426] Updated weights for policy 1, policy_version 63110 (0.0009) -[2023-11-28 01:52:02,997][87426] Updated weights for policy 1, policy_version 63120 (0.0008) -[2023-11-28 01:52:03,378][87426] Updated weights for policy 1, policy_version 63130 (0.0009) -[2023-11-28 01:52:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32333824. Throughput: 0: 2719.1, 1: 2750.6. Samples: 32347992. Policy #0 lag: (min: 21.0, avg: 36.4, max: 53.0) -[2023-11-28 01:52:03,445][86177] Avg episode reward: [(0, '-658.570'), (1, '-505.660')] -[2023-11-28 01:52:04,227][87424] Updated weights for policy 0, policy_version 63206 (0.0011) -[2023-11-28 01:52:04,608][87424] Updated weights for policy 0, policy_version 63216 (0.0008) -[2023-11-28 01:52:04,987][87424] Updated weights for policy 0, policy_version 63226 (0.0008) -[2023-11-28 01:52:05,189][87426] Updated weights for policy 1, policy_version 63140 (0.0009) -[2023-11-28 01:52:05,578][87426] Updated weights for policy 1, policy_version 63150 (0.0010) -[2023-11-28 01:52:05,961][87426] Updated weights for policy 1, policy_version 63160 (0.0007) -[2023-11-28 01:52:06,686][87424] Updated weights for policy 0, policy_version 63236 (0.0008) -[2023-11-28 01:52:07,060][87424] Updated weights for policy 0, policy_version 63246 (0.0011) -[2023-11-28 01:52:07,443][87424] Updated weights for policy 0, policy_version 63256 (0.0012) -[2023-11-28 01:52:08,255][87426] Updated weights for policy 1, policy_version 63170 (0.0008) -[2023-11-28 01:52:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 32366592. Throughput: 0: 2719.1, 1: 2735.1. Samples: 32381040. Policy #0 lag: (min: 21.0, avg: 36.4, max: 53.0) -[2023-11-28 01:52:08,445][86177] Avg episode reward: [(0, '-684.910'), (1, '-551.010')] -[2023-11-28 01:52:08,630][87426] Updated weights for policy 1, policy_version 63180 (0.0012) -[2023-11-28 01:52:09,008][87426] Updated weights for policy 1, policy_version 63190 (0.0011) -[2023-11-28 01:52:09,384][87426] Updated weights for policy 1, policy_version 63200 (0.0012) -[2023-11-28 01:52:09,950][87424] Updated weights for policy 0, policy_version 63266 (0.0011) -[2023-11-28 01:52:10,325][87424] Updated weights for policy 0, policy_version 63276 (0.0012) -[2023-11-28 01:52:10,717][87424] Updated weights for policy 0, policy_version 63286 (0.0013) -[2023-11-28 01:52:11,095][87424] Updated weights for policy 0, policy_version 63296 (0.0011) -[2023-11-28 01:52:11,370][87426] Updated weights for policy 1, policy_version 63210 (0.0011) -[2023-11-28 01:52:11,745][87426] Updated weights for policy 1, policy_version 63220 (0.0012) -[2023-11-28 01:52:12,124][87426] Updated weights for policy 1, policy_version 63230 (0.0010) -[2023-11-28 01:52:13,306][87424] Updated weights for policy 0, policy_version 63306 (0.0007) -[2023-11-28 01:52:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32391168. Throughput: 0: 2721.0, 1: 2748.8. Samples: 32405924. Policy #0 lag: (min: 21.0, avg: 36.4, max: 53.0) -[2023-11-28 01:52:13,445][86177] Avg episode reward: [(0, '-671.570'), (1, '-622.760')] -[2023-11-28 01:52:13,692][87424] Updated weights for policy 0, policy_version 63316 (0.0008) -[2023-11-28 01:52:14,077][87424] Updated weights for policy 0, policy_version 63326 (0.0010) -[2023-11-28 01:52:14,674][87426] Updated weights for policy 1, policy_version 63240 (0.0008) -[2023-11-28 01:52:15,049][87426] Updated weights for policy 1, policy_version 63250 (0.0008) -[2023-11-28 01:52:15,438][87426] Updated weights for policy 1, policy_version 63260 (0.0007) -[2023-11-28 01:52:16,581][87424] Updated weights for policy 0, policy_version 63336 (0.0007) -[2023-11-28 01:52:16,967][87424] Updated weights for policy 0, policy_version 63346 (0.0007) -[2023-11-28 01:52:17,355][87424] Updated weights for policy 0, policy_version 63356 (0.0008) -[2023-11-28 01:52:17,961][87426] Updated weights for policy 1, policy_version 63270 (0.0008) -[2023-11-28 01:52:18,343][87426] Updated weights for policy 1, policy_version 63280 (0.0007) -[2023-11-28 01:52:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32415744. Throughput: 0: 2701.2, 1: 2732.2. Samples: 32429172. Policy #0 lag: (min: 21.0, avg: 36.4, max: 53.0) -[2023-11-28 01:52:18,445][86177] Avg episode reward: [(0, '-631.610'), (1, '-709.660')] -[2023-11-28 01:52:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000063360_16220160.pth... -[2023-11-28 01:52:18,490][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000060800_15564800.pth -[2023-11-28 01:52:18,495][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000063360_16220160.pth -[2023-11-28 01:52:18,730][87426] Updated weights for policy 1, policy_version 63290 (0.0007) -[2023-11-28 01:52:18,948][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000063296_16203776.pth... -[2023-11-28 01:52:18,996][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000060736_15548416.pth -[2023-11-28 01:52:19,004][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000063296_16203776.pth -[2023-11-28 01:52:19,859][87424] Updated weights for policy 0, policy_version 63366 (0.0010) -[2023-11-28 01:52:20,238][87424] Updated weights for policy 0, policy_version 63376 (0.0012) -[2023-11-28 01:52:20,624][87424] Updated weights for policy 0, policy_version 63386 (0.0011) -[2023-11-28 01:52:20,707][87426] Updated weights for policy 1, policy_version 63300 (0.0009) -[2023-11-28 01:52:21,086][87426] Updated weights for policy 1, policy_version 63310 (0.0009) -[2023-11-28 01:52:21,469][87426] Updated weights for policy 1, policy_version 63320 (0.0008) -[2023-11-28 01:52:22,763][87424] Updated weights for policy 0, policy_version 63396 (0.0011) -[2023-11-28 01:52:23,133][87424] Updated weights for policy 0, policy_version 63406 (0.0012) -[2023-11-28 01:52:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32440320. Throughput: 0: 2711.1, 1: 2724.5. Samples: 32460784. Policy #0 lag: (min: 6.0, avg: 18.9, max: 38.0) -[2023-11-28 01:52:23,445][86177] Avg episode reward: [(0, '-665.560'), (1, '-706.000')] -[2023-11-28 01:52:23,513][87424] Updated weights for policy 0, policy_version 63416 (0.0012) -[2023-11-28 01:52:23,546][87426] Updated weights for policy 1, policy_version 63330 (0.0009) -[2023-11-28 01:52:23,930][87426] Updated weights for policy 1, policy_version 63340 (0.0010) -[2023-11-28 01:52:24,307][87426] Updated weights for policy 1, policy_version 63350 (0.0011) -[2023-11-28 01:52:24,689][87426] Updated weights for policy 1, policy_version 63360 (0.0012) -[2023-11-28 01:52:25,442][87424] Updated weights for policy 0, policy_version 63426 (0.0010) -[2023-11-28 01:52:25,836][87424] Updated weights for policy 0, policy_version 63436 (0.0011) -[2023-11-28 01:52:26,211][87424] Updated weights for policy 0, policy_version 63446 (0.0011) -[2023-11-28 01:52:26,594][87424] Updated weights for policy 0, policy_version 63456 (0.0012) -[2023-11-28 01:52:26,971][87426] Updated weights for policy 1, policy_version 63370 (0.0012) -[2023-11-28 01:52:27,354][87426] Updated weights for policy 1, policy_version 63380 (0.0012) -[2023-11-28 01:52:27,742][87426] Updated weights for policy 1, policy_version 63390 (0.0011) -[2023-11-28 01:52:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32473088. Throughput: 0: 2736.0, 1: 2757.4. Samples: 32487392. Policy #0 lag: (min: 6.0, avg: 18.9, max: 38.0) -[2023-11-28 01:52:28,445][86177] Avg episode reward: [(0, '-697.220'), (1, '-654.910')] -[2023-11-28 01:52:28,572][87424] Updated weights for policy 0, policy_version 63466 (0.0011) -[2023-11-28 01:52:28,950][87424] Updated weights for policy 0, policy_version 63476 (0.0011) -[2023-11-28 01:52:29,329][87424] Updated weights for policy 0, policy_version 63486 (0.0009) -[2023-11-28 01:52:30,047][87426] Updated weights for policy 1, policy_version 63400 (0.0011) -[2023-11-28 01:52:30,448][87426] Updated weights for policy 1, policy_version 63410 (0.0008) -[2023-11-28 01:52:30,831][87426] Updated weights for policy 1, policy_version 63420 (0.0008) -[2023-11-28 01:52:31,383][87424] Updated weights for policy 0, policy_version 63496 (0.0008) -[2023-11-28 01:52:31,761][87424] Updated weights for policy 0, policy_version 63506 (0.0008) -[2023-11-28 01:52:32,144][87424] Updated weights for policy 0, policy_version 63516 (0.0011) -[2023-11-28 01:52:32,904][87426] Updated weights for policy 1, policy_version 63430 (0.0008) -[2023-11-28 01:52:33,279][87426] Updated weights for policy 1, policy_version 63440 (0.0007) -[2023-11-28 01:52:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32497664. Throughput: 0: 2750.1, 1: 2749.5. Samples: 32512128. Policy #0 lag: (min: 6.0, avg: 18.9, max: 38.0) -[2023-11-28 01:52:33,445][86177] Avg episode reward: [(0, '-690.710'), (1, '-582.580')] -[2023-11-28 01:52:33,660][87426] Updated weights for policy 1, policy_version 63450 (0.0007) -[2023-11-28 01:52:34,356][87424] Updated weights for policy 0, policy_version 63526 (0.0009) -[2023-11-28 01:52:34,745][87424] Updated weights for policy 0, policy_version 63536 (0.0009) -[2023-11-28 01:52:35,120][87424] Updated weights for policy 0, policy_version 63546 (0.0009) -[2023-11-28 01:52:35,491][87426] Updated weights for policy 1, policy_version 63460 (0.0009) -[2023-11-28 01:52:35,872][87426] Updated weights for policy 1, policy_version 63470 (0.0012) -[2023-11-28 01:52:36,258][87426] Updated weights for policy 1, policy_version 63480 (0.0012) -[2023-11-28 01:52:37,666][87424] Updated weights for policy 0, policy_version 63556 (0.0010) -[2023-11-28 01:52:38,036][87424] Updated weights for policy 0, policy_version 63566 (0.0010) -[2023-11-28 01:52:38,423][87424] Updated weights for policy 0, policy_version 63576 (0.0010) -[2023-11-28 01:52:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32522240. Throughput: 0: 2736.5, 1: 2743.5. Samples: 32544540. Policy #0 lag: (min: 6.0, avg: 18.9, max: 38.0) -[2023-11-28 01:52:38,445][86177] Avg episode reward: [(0, '-672.510'), (1, '-538.940')] -[2023-11-28 01:52:38,760][87426] Updated weights for policy 1, policy_version 63490 (0.0010) -[2023-11-28 01:52:39,147][87426] Updated weights for policy 1, policy_version 63500 (0.0012) -[2023-11-28 01:52:39,515][87426] Updated weights for policy 1, policy_version 63510 (0.0012) -[2023-11-28 01:52:39,894][87426] Updated weights for policy 1, policy_version 63520 (0.0012) -[2023-11-28 01:52:40,751][87424] Updated weights for policy 0, policy_version 63586 (0.0011) -[2023-11-28 01:52:41,138][87424] Updated weights for policy 0, policy_version 63596 (0.0012) -[2023-11-28 01:52:41,509][87424] Updated weights for policy 0, policy_version 63606 (0.0012) -[2023-11-28 01:52:41,894][87424] Updated weights for policy 0, policy_version 63616 (0.0010) -[2023-11-28 01:52:42,039][87426] Updated weights for policy 1, policy_version 63530 (0.0011) -[2023-11-28 01:52:42,420][87426] Updated weights for policy 1, policy_version 63540 (0.0010) -[2023-11-28 01:52:42,804][87426] Updated weights for policy 1, policy_version 63550 (0.0008) -[2023-11-28 01:52:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32555008. Throughput: 0: 2748.6, 1: 2711.0. Samples: 32568708. Policy #0 lag: (min: 6.0, avg: 18.9, max: 38.0) -[2023-11-28 01:52:43,445][86177] Avg episode reward: [(0, '-825.330'), (1, '-539.100')] -[2023-11-28 01:52:44,254][87424] Updated weights for policy 0, policy_version 63626 (0.0010) -[2023-11-28 01:52:44,640][87424] Updated weights for policy 0, policy_version 63636 (0.0011) -[2023-11-28 01:52:44,993][87426] Updated weights for policy 1, policy_version 63560 (0.0010) -[2023-11-28 01:52:45,024][87424] Updated weights for policy 0, policy_version 63646 (0.0008) -[2023-11-28 01:52:45,370][87426] Updated weights for policy 1, policy_version 63570 (0.0011) -[2023-11-28 01:52:45,750][87426] Updated weights for policy 1, policy_version 63580 (0.0011) -[2023-11-28 01:52:46,835][87424] Updated weights for policy 0, policy_version 63656 (0.0009) -[2023-11-28 01:52:47,213][87424] Updated weights for policy 0, policy_version 63666 (0.0012) -[2023-11-28 01:52:47,592][87424] Updated weights for policy 0, policy_version 63676 (0.0012) -[2023-11-28 01:52:47,777][87426] Updated weights for policy 1, policy_version 63590 (0.0009) -[2023-11-28 01:52:48,158][87426] Updated weights for policy 1, policy_version 63600 (0.0010) -[2023-11-28 01:52:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32579584. Throughput: 0: 2736.0, 1: 2700.9. Samples: 32592652. Policy #0 lag: (min: 6.0, avg: 18.9, max: 38.0) -[2023-11-28 01:52:48,445][86177] Avg episode reward: [(0, '-855.080'), (1, '-548.880')] -[2023-11-28 01:52:48,549][87426] Updated weights for policy 1, policy_version 63610 (0.0007) -[2023-11-28 01:52:50,165][87424] Updated weights for policy 0, policy_version 63686 (0.0009) -[2023-11-28 01:52:50,548][87424] Updated weights for policy 0, policy_version 63696 (0.0009) -[2023-11-28 01:52:50,939][87424] Updated weights for policy 0, policy_version 63706 (0.0008) -[2023-11-28 01:52:50,987][87426] Updated weights for policy 1, policy_version 63620 (0.0009) -[2023-11-28 01:52:51,367][87426] Updated weights for policy 1, policy_version 63630 (0.0011) -[2023-11-28 01:52:51,741][87426] Updated weights for policy 1, policy_version 63640 (0.0011) -[2023-11-28 01:52:53,387][87424] Updated weights for policy 0, policy_version 63716 (0.0010) -[2023-11-28 01:52:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32604160. Throughput: 0: 2721.3, 1: 2690.1. Samples: 32624552. Policy #0 lag: (min: 6.0, avg: 18.9, max: 38.0) -[2023-11-28 01:52:53,445][86177] Avg episode reward: [(0, '-814.190'), (1, '-546.250')] -[2023-11-28 01:52:53,761][87424] Updated weights for policy 0, policy_version 63726 (0.0012) -[2023-11-28 01:52:54,140][87424] Updated weights for policy 0, policy_version 63736 (0.0012) -[2023-11-28 01:52:54,183][87426] Updated weights for policy 1, policy_version 63650 (0.0011) -[2023-11-28 01:52:54,569][87426] Updated weights for policy 1, policy_version 63660 (0.0007) -[2023-11-28 01:52:54,946][87426] Updated weights for policy 1, policy_version 63670 (0.0010) -[2023-11-28 01:52:55,331][87426] Updated weights for policy 1, policy_version 63680 (0.0007) -[2023-11-28 01:52:55,970][87424] Updated weights for policy 0, policy_version 63746 (0.0010) -[2023-11-28 01:52:56,354][87424] Updated weights for policy 0, policy_version 63756 (0.0010) -[2023-11-28 01:52:56,733][87424] Updated weights for policy 0, policy_version 63766 (0.0008) -[2023-11-28 01:52:57,104][87424] Updated weights for policy 0, policy_version 63776 (0.0008) -[2023-11-28 01:52:57,750][87426] Updated weights for policy 1, policy_version 63690 (0.0010) -[2023-11-28 01:52:58,131][87426] Updated weights for policy 1, policy_version 63700 (0.0009) -[2023-11-28 01:52:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32628736. Throughput: 0: 2724.4, 1: 2672.7. Samples: 32648792. Policy #0 lag: (min: 6.0, avg: 18.9, max: 38.0) -[2023-11-28 01:52:58,446][86177] Avg episode reward: [(0, '-763.950'), (1, '-511.310')] -[2023-11-28 01:52:58,517][87426] Updated weights for policy 1, policy_version 63710 (0.0007) -[2023-11-28 01:52:58,892][87424] Updated weights for policy 0, policy_version 63786 (0.0012) -[2023-11-28 01:52:59,270][87424] Updated weights for policy 0, policy_version 63796 (0.0011) -[2023-11-28 01:52:59,655][87424] Updated weights for policy 0, policy_version 63806 (0.0008) -[2023-11-28 01:53:00,381][87426] Updated weights for policy 1, policy_version 63720 (0.0010) -[2023-11-28 01:53:00,751][87426] Updated weights for policy 1, policy_version 63730 (0.0011) -[2023-11-28 01:53:01,131][87426] Updated weights for policy 1, policy_version 63740 (0.0011) -[2023-11-28 01:53:02,103][87424] Updated weights for policy 0, policy_version 63816 (0.0010) -[2023-11-28 01:53:02,487][87424] Updated weights for policy 0, policy_version 63826 (0.0010) -[2023-11-28 01:53:02,868][87424] Updated weights for policy 0, policy_version 63836 (0.0008) -[2023-11-28 01:53:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32661504. Throughput: 0: 2721.8, 1: 2681.3. Samples: 32672308. Policy #0 lag: (min: 25.0, avg: 48.8, max: 74.0) -[2023-11-28 01:53:03,445][86177] Avg episode reward: [(0, '-738.270'), (1, '-510.510')] -[2023-11-28 01:53:03,608][87426] Updated weights for policy 1, policy_version 63750 (0.0011) -[2023-11-28 01:53:03,988][87426] Updated weights for policy 1, policy_version 63760 (0.0011) -[2023-11-28 01:53:04,362][87426] Updated weights for policy 1, policy_version 63770 (0.0011) -[2023-11-28 01:53:05,378][87424] Updated weights for policy 0, policy_version 63846 (0.0008) -[2023-11-28 01:53:05,764][87424] Updated weights for policy 0, policy_version 63856 (0.0008) -[2023-11-28 01:53:06,143][87424] Updated weights for policy 0, policy_version 63866 (0.0008) -[2023-11-28 01:53:06,906][87426] Updated weights for policy 1, policy_version 63780 (0.0008) -[2023-11-28 01:53:07,290][87426] Updated weights for policy 1, policy_version 63790 (0.0007) -[2023-11-28 01:53:07,669][87426] Updated weights for policy 1, policy_version 63800 (0.0007) -[2023-11-28 01:53:08,259][87424] Updated weights for policy 0, policy_version 63876 (0.0009) -[2023-11-28 01:53:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32686080. Throughput: 0: 2726.4, 1: 2676.4. Samples: 32703908. Policy #0 lag: (min: 25.0, avg: 48.8, max: 74.0) -[2023-11-28 01:53:08,445][86177] Avg episode reward: [(0, '-627.450'), (1, '-553.720')] -[2023-11-28 01:53:08,641][87424] Updated weights for policy 0, policy_version 63886 (0.0007) -[2023-11-28 01:53:09,024][87424] Updated weights for policy 0, policy_version 63896 (0.0009) -[2023-11-28 01:53:09,513][87426] Updated weights for policy 1, policy_version 63810 (0.0008) -[2023-11-28 01:53:09,893][87426] Updated weights for policy 1, policy_version 63820 (0.0012) -[2023-11-28 01:53:10,284][87426] Updated weights for policy 1, policy_version 63830 (0.0008) -[2023-11-28 01:53:10,662][87426] Updated weights for policy 1, policy_version 63840 (0.0008) -[2023-11-28 01:53:11,436][87424] Updated weights for policy 0, policy_version 63906 (0.0009) -[2023-11-28 01:53:11,816][87424] Updated weights for policy 0, policy_version 63916 (0.0011) -[2023-11-28 01:53:12,196][87424] Updated weights for policy 0, policy_version 63926 (0.0012) -[2023-11-28 01:53:12,578][87424] Updated weights for policy 0, policy_version 63936 (0.0011) -[2023-11-28 01:53:12,936][87426] Updated weights for policy 1, policy_version 63850 (0.0011) -[2023-11-28 01:53:13,310][87426] Updated weights for policy 1, policy_version 63860 (0.0008) -[2023-11-28 01:53:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32710656. Throughput: 0: 2709.6, 1: 2636.0. Samples: 32727944. Policy #0 lag: (min: 25.0, avg: 48.8, max: 74.0) -[2023-11-28 01:53:13,445][86177] Avg episode reward: [(0, '-591.260'), (1, '-570.740')] -[2023-11-28 01:53:13,690][87426] Updated weights for policy 1, policy_version 63870 (0.0007) -[2023-11-28 01:53:14,391][87424] Updated weights for policy 0, policy_version 63946 (0.0012) -[2023-11-28 01:53:14,763][87424] Updated weights for policy 0, policy_version 63956 (0.0012) -[2023-11-28 01:53:15,146][87424] Updated weights for policy 0, policy_version 63966 (0.0012) -[2023-11-28 01:53:16,042][87426] Updated weights for policy 1, policy_version 63880 (0.0009) -[2023-11-28 01:53:16,430][87426] Updated weights for policy 1, policy_version 63890 (0.0007) -[2023-11-28 01:53:16,812][87426] Updated weights for policy 1, policy_version 63900 (0.0007) -[2023-11-28 01:53:17,680][87424] Updated weights for policy 0, policy_version 63976 (0.0008) -[2023-11-28 01:53:18,062][87424] Updated weights for policy 0, policy_version 63986 (0.0007) -[2023-11-28 01:53:18,441][87424] Updated weights for policy 0, policy_version 63996 (0.0007) -[2023-11-28 01:53:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 32735232. Throughput: 0: 2683.9, 1: 2651.1. Samples: 32752204. Policy #0 lag: (min: 25.0, avg: 48.8, max: 74.0) -[2023-11-28 01:53:18,445][86177] Avg episode reward: [(0, '-657.400'), (1, '-572.440')] -[2023-11-28 01:53:18,669][87426] Updated weights for policy 1, policy_version 63910 (0.0008) -[2023-11-28 01:53:19,055][87426] Updated weights for policy 1, policy_version 63920 (0.0008) -[2023-11-28 01:53:19,441][87426] Updated weights for policy 1, policy_version 63930 (0.0007) -[2023-11-28 01:53:20,899][87424] Updated weights for policy 0, policy_version 64006 (0.0010) -[2023-11-28 01:53:21,283][87424] Updated weights for policy 0, policy_version 64016 (0.0011) -[2023-11-28 01:53:21,532][87426] Updated weights for policy 1, policy_version 63940 (0.0009) -[2023-11-28 01:53:21,664][87424] Updated weights for policy 0, policy_version 64026 (0.0009) -[2023-11-28 01:53:21,907][87426] Updated weights for policy 1, policy_version 63950 (0.0011) -[2023-11-28 01:53:22,282][87426] Updated weights for policy 1, policy_version 63960 (0.0012) -[2023-11-28 01:53:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32768000. Throughput: 0: 2664.6, 1: 2657.6. Samples: 32784040. Policy #0 lag: (min: 25.0, avg: 48.8, max: 74.0) -[2023-11-28 01:53:23,446][86177] Avg episode reward: [(0, '-670.440'), (1, '-583.300')] -[2023-11-28 01:53:23,705][87424] Updated weights for policy 0, policy_version 64036 (0.0011) -[2023-11-28 01:53:24,084][87424] Updated weights for policy 0, policy_version 64046 (0.0010) -[2023-11-28 01:53:24,465][87424] Updated weights for policy 0, policy_version 64056 (0.0009) -[2023-11-28 01:53:24,546][87426] Updated weights for policy 1, policy_version 63970 (0.0012) -[2023-11-28 01:53:24,924][87426] Updated weights for policy 1, policy_version 63980 (0.0009) -[2023-11-28 01:53:25,312][87426] Updated weights for policy 1, policy_version 63990 (0.0011) -[2023-11-28 01:53:25,697][87426] Updated weights for policy 1, policy_version 64000 (0.0012) -[2023-11-28 01:53:26,691][87424] Updated weights for policy 0, policy_version 64066 (0.0009) -[2023-11-28 01:53:27,078][87424] Updated weights for policy 0, policy_version 64076 (0.0008) -[2023-11-28 01:53:27,464][87424] Updated weights for policy 0, policy_version 64086 (0.0011) -[2023-11-28 01:53:27,806][87426] Updated weights for policy 1, policy_version 64010 (0.0009) -[2023-11-28 01:53:27,839][87424] Updated weights for policy 0, policy_version 64096 (0.0009) -[2023-11-28 01:53:28,180][87426] Updated weights for policy 1, policy_version 64020 (0.0011) -[2023-11-28 01:53:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32792576. Throughput: 0: 2656.0, 1: 2679.0. Samples: 32808784. Policy #0 lag: (min: 25.0, avg: 48.8, max: 74.0) -[2023-11-28 01:53:28,445][86177] Avg episode reward: [(0, '-593.650'), (1, '-541.040')] -[2023-11-28 01:53:28,556][87426] Updated weights for policy 1, policy_version 64030 (0.0012) -[2023-11-28 01:53:29,631][87424] Updated weights for policy 0, policy_version 64106 (0.0012) -[2023-11-28 01:53:30,008][87424] Updated weights for policy 0, policy_version 64116 (0.0012) -[2023-11-28 01:53:30,399][87424] Updated weights for policy 0, policy_version 64126 (0.0012) -[2023-11-28 01:53:30,445][87426] Updated weights for policy 1, policy_version 64040 (0.0009) -[2023-11-28 01:53:30,831][87426] Updated weights for policy 1, policy_version 64050 (0.0011) -[2023-11-28 01:53:31,208][87426] Updated weights for policy 1, policy_version 64060 (0.0010) -[2023-11-28 01:53:32,440][87424] Updated weights for policy 0, policy_version 64136 (0.0009) -[2023-11-28 01:53:32,823][87424] Updated weights for policy 0, policy_version 64146 (0.0008) -[2023-11-28 01:53:33,209][87424] Updated weights for policy 0, policy_version 64156 (0.0009) -[2023-11-28 01:53:33,422][87426] Updated weights for policy 1, policy_version 64070 (0.0009) -[2023-11-28 01:53:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32825344. Throughput: 0: 2661.2, 1: 2689.8. Samples: 32833448. Policy #0 lag: (min: 25.0, avg: 48.8, max: 74.0) -[2023-11-28 01:53:33,445][86177] Avg episode reward: [(0, '-629.180'), (1, '-532.360')] -[2023-11-28 01:53:33,805][87426] Updated weights for policy 1, policy_version 64080 (0.0007) -[2023-11-28 01:53:34,181][87426] Updated weights for policy 1, policy_version 64090 (0.0007) -[2023-11-28 01:53:35,572][87424] Updated weights for policy 0, policy_version 64166 (0.0010) -[2023-11-28 01:53:35,954][87424] Updated weights for policy 0, policy_version 64176 (0.0012) -[2023-11-28 01:53:36,328][87424] Updated weights for policy 0, policy_version 64186 (0.0012) -[2023-11-28 01:53:36,485][87426] Updated weights for policy 1, policy_version 64100 (0.0007) -[2023-11-28 01:53:36,870][87426] Updated weights for policy 1, policy_version 64110 (0.0008) -[2023-11-28 01:53:37,256][87426] Updated weights for policy 1, policy_version 64120 (0.0008) -[2023-11-28 01:53:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32849920. Throughput: 0: 2669.1, 1: 2701.2. Samples: 32866212. Policy #0 lag: (min: 25.0, avg: 48.8, max: 74.0) -[2023-11-28 01:53:38,445][86177] Avg episode reward: [(0, '-624.200'), (1, '-528.170')] -[2023-11-28 01:53:38,837][87424] Updated weights for policy 0, policy_version 64196 (0.0011) -[2023-11-28 01:53:39,216][87424] Updated weights for policy 0, policy_version 64206 (0.0009) -[2023-11-28 01:53:39,597][87424] Updated weights for policy 0, policy_version 64216 (0.0012) -[2023-11-28 01:53:39,653][87426] Updated weights for policy 1, policy_version 64130 (0.0008) -[2023-11-28 01:53:40,039][87426] Updated weights for policy 1, policy_version 64140 (0.0016) -[2023-11-28 01:53:40,417][87426] Updated weights for policy 1, policy_version 64150 (0.0012) -[2023-11-28 01:53:40,797][87426] Updated weights for policy 1, policy_version 64160 (0.0009) -[2023-11-28 01:53:41,975][87424] Updated weights for policy 0, policy_version 64226 (0.0010) -[2023-11-28 01:53:42,361][87424] Updated weights for policy 0, policy_version 64236 (0.0010) -[2023-11-28 01:53:42,750][87424] Updated weights for policy 0, policy_version 64246 (0.0011) -[2023-11-28 01:53:42,926][87426] Updated weights for policy 1, policy_version 64170 (0.0012) -[2023-11-28 01:53:43,135][87424] Updated weights for policy 0, policy_version 64256 (0.0011) -[2023-11-28 01:53:43,303][87426] Updated weights for policy 1, policy_version 64180 (0.0012) -[2023-11-28 01:53:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32874496. Throughput: 0: 2655.8, 1: 2703.0. Samples: 32889940. Policy #0 lag: (min: 45.0, avg: 59.6, max: 81.0) -[2023-11-28 01:53:43,446][86177] Avg episode reward: [(0, '-554.360'), (1, '-536.720')] -[2023-11-28 01:53:43,682][87426] Updated weights for policy 1, policy_version 64190 (0.0009) -[2023-11-28 01:53:45,647][87424] Updated weights for policy 0, policy_version 64266 (0.0011) -[2023-11-28 01:53:45,817][87426] Updated weights for policy 1, policy_version 64200 (0.0011) -[2023-11-28 01:53:46,036][87424] Updated weights for policy 0, policy_version 64276 (0.0012) -[2023-11-28 01:53:46,200][87426] Updated weights for policy 1, policy_version 64210 (0.0012) -[2023-11-28 01:53:46,413][87424] Updated weights for policy 0, policy_version 64286 (0.0010) -[2023-11-28 01:53:46,573][87426] Updated weights for policy 1, policy_version 64220 (0.0009) -[2023-11-28 01:53:48,386][87426] Updated weights for policy 1, policy_version 64230 (0.0010) -[2023-11-28 01:53:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32899072. Throughput: 0: 2645.2, 1: 2725.4. Samples: 32913984. Policy #0 lag: (min: 45.0, avg: 59.6, max: 81.0) -[2023-11-28 01:53:48,445][86177] Avg episode reward: [(0, '-603.630'), (1, '-519.040')] -[2023-11-28 01:53:48,498][87424] Updated weights for policy 0, policy_version 64296 (0.0012) -[2023-11-28 01:53:48,768][87426] Updated weights for policy 1, policy_version 64240 (0.0008) -[2023-11-28 01:53:48,877][87424] Updated weights for policy 0, policy_version 64306 (0.0012) -[2023-11-28 01:53:49,147][87426] Updated weights for policy 1, policy_version 64250 (0.0010) -[2023-11-28 01:53:49,261][87424] Updated weights for policy 0, policy_version 64316 (0.0011) -[2023-11-28 01:53:51,444][87424] Updated weights for policy 0, policy_version 64326 (0.0009) -[2023-11-28 01:53:51,470][87426] Updated weights for policy 1, policy_version 64260 (0.0009) -[2023-11-28 01:53:51,813][87424] Updated weights for policy 0, policy_version 64336 (0.0010) -[2023-11-28 01:53:51,850][87426] Updated weights for policy 1, policy_version 64270 (0.0009) -[2023-11-28 01:53:52,192][87424] Updated weights for policy 0, policy_version 64346 (0.0011) -[2023-11-28 01:53:52,229][87426] Updated weights for policy 1, policy_version 64280 (0.0011) -[2023-11-28 01:53:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 32931840. Throughput: 0: 2651.7, 1: 2731.9. Samples: 32946172. Policy #0 lag: (min: 45.0, avg: 59.6, max: 81.0) -[2023-11-28 01:53:53,445][86177] Avg episode reward: [(0, '-598.530'), (1, '-543.400')] -[2023-11-28 01:53:54,528][87426] Updated weights for policy 1, policy_version 64290 (0.0012) -[2023-11-28 01:53:54,715][87424] Updated weights for policy 0, policy_version 64356 (0.0011) -[2023-11-28 01:53:54,898][87426] Updated weights for policy 1, policy_version 64300 (0.0011) -[2023-11-28 01:53:55,103][87424] Updated weights for policy 0, policy_version 64366 (0.0012) -[2023-11-28 01:53:55,279][87426] Updated weights for policy 1, policy_version 64310 (0.0010) -[2023-11-28 01:53:55,486][87424] Updated weights for policy 0, policy_version 64376 (0.0012) -[2023-11-28 01:53:55,660][87426] Updated weights for policy 1, policy_version 64320 (0.0008) -[2023-11-28 01:53:57,358][87424] Updated weights for policy 0, policy_version 64386 (0.0011) -[2023-11-28 01:53:57,506][87426] Updated weights for policy 1, policy_version 64330 (0.0012) -[2023-11-28 01:53:57,740][87424] Updated weights for policy 0, policy_version 64396 (0.0007) -[2023-11-28 01:53:57,883][87426] Updated weights for policy 1, policy_version 64340 (0.0011) -[2023-11-28 01:53:58,134][87424] Updated weights for policy 0, policy_version 64406 (0.0011) -[2023-11-28 01:53:58,270][87426] Updated weights for policy 1, policy_version 64350 (0.0008) -[2023-11-28 01:53:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 32956416. Throughput: 0: 2632.0, 1: 2745.3. Samples: 32969924. Policy #0 lag: (min: 45.0, avg: 59.6, max: 81.0) -[2023-11-28 01:53:58,445][86177] Avg episode reward: [(0, '-595.550'), (1, '-554.610')] -[2023-11-28 01:53:58,507][87424] Updated weights for policy 0, policy_version 64416 (0.0010) -[2023-11-28 01:54:00,615][87424] Updated weights for policy 0, policy_version 64426 (0.0012) -[2023-11-28 01:54:00,772][87426] Updated weights for policy 1, policy_version 64360 (0.0010) -[2023-11-28 01:54:01,018][87424] Updated weights for policy 0, policy_version 64436 (0.0012) -[2023-11-28 01:54:01,144][87426] Updated weights for policy 1, policy_version 64370 (0.0011) -[2023-11-28 01:54:01,396][87424] Updated weights for policy 0, policy_version 64446 (0.0011) -[2023-11-28 01:54:01,518][87426] Updated weights for policy 1, policy_version 64380 (0.0009) -[2023-11-28 01:54:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 32980992. Throughput: 0: 2646.4, 1: 2740.9. Samples: 32994632. Policy #0 lag: (min: 45.0, avg: 59.6, max: 81.0) -[2023-11-28 01:54:03,445][86177] Avg episode reward: [(0, '-637.210'), (1, '-544.600')] -[2023-11-28 01:54:03,538][87424] Updated weights for policy 0, policy_version 64456 (0.0008) -[2023-11-28 01:54:03,930][87424] Updated weights for policy 0, policy_version 64466 (0.0008) -[2023-11-28 01:54:04,047][87426] Updated weights for policy 1, policy_version 64390 (0.0010) -[2023-11-28 01:54:04,309][87424] Updated weights for policy 0, policy_version 64476 (0.0007) -[2023-11-28 01:54:04,426][87426] Updated weights for policy 1, policy_version 64400 (0.0010) -[2023-11-28 01:54:04,808][87426] Updated weights for policy 1, policy_version 64410 (0.0010) -[2023-11-28 01:54:06,568][87424] Updated weights for policy 0, policy_version 64486 (0.0009) -[2023-11-28 01:54:06,939][87426] Updated weights for policy 1, policy_version 64420 (0.0011) -[2023-11-28 01:54:06,951][87424] Updated weights for policy 0, policy_version 64496 (0.0010) -[2023-11-28 01:54:07,319][87426] Updated weights for policy 1, policy_version 64430 (0.0011) -[2023-11-28 01:54:07,334][87424] Updated weights for policy 0, policy_version 64506 (0.0008) -[2023-11-28 01:54:07,697][87426] Updated weights for policy 1, policy_version 64440 (0.0008) -[2023-11-28 01:54:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 33013760. Throughput: 0: 2675.8, 1: 2726.3. Samples: 33027136. Policy #0 lag: (min: 45.0, avg: 59.6, max: 81.0) -[2023-11-28 01:54:08,445][86177] Avg episode reward: [(0, '-642.910'), (1, '-560.920')] -[2023-11-28 01:54:09,749][87424] Updated weights for policy 0, policy_version 64516 (0.0011) -[2023-11-28 01:54:09,831][87426] Updated weights for policy 1, policy_version 64450 (0.0008) -[2023-11-28 01:54:10,117][87424] Updated weights for policy 0, policy_version 64526 (0.0011) -[2023-11-28 01:54:10,214][87426] Updated weights for policy 1, policy_version 64460 (0.0009) -[2023-11-28 01:54:10,506][87424] Updated weights for policy 0, policy_version 64536 (0.0010) -[2023-11-28 01:54:10,597][87426] Updated weights for policy 1, policy_version 64470 (0.0008) -[2023-11-28 01:54:10,969][87426] Updated weights for policy 1, policy_version 64480 (0.0007) -[2023-11-28 01:54:12,910][87424] Updated weights for policy 0, policy_version 64546 (0.0012) -[2023-11-28 01:54:13,299][87424] Updated weights for policy 0, policy_version 64556 (0.0011) -[2023-11-28 01:54:13,408][87426] Updated weights for policy 1, policy_version 64490 (0.0008) -[2023-11-28 01:54:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 33030144. Throughput: 0: 2671.1, 1: 2705.9. Samples: 33050748. Policy #0 lag: (min: 45.0, avg: 59.6, max: 81.0) -[2023-11-28 01:54:13,445][86177] Avg episode reward: [(0, '-623.080'), (1, '-524.320')] -[2023-11-28 01:54:13,678][87424] Updated weights for policy 0, policy_version 64566 (0.0011) -[2023-11-28 01:54:13,791][87426] Updated weights for policy 1, policy_version 64500 (0.0007) -[2023-11-28 01:54:14,061][87424] Updated weights for policy 0, policy_version 64576 (0.0010) -[2023-11-28 01:54:14,177][87426] Updated weights for policy 1, policy_version 64510 (0.0009) -[2023-11-28 01:54:16,107][87424] Updated weights for policy 0, policy_version 64586 (0.0010) -[2023-11-28 01:54:16,488][87424] Updated weights for policy 0, policy_version 64596 (0.0007) -[2023-11-28 01:54:16,641][87426] Updated weights for policy 1, policy_version 64520 (0.0008) -[2023-11-28 01:54:16,865][87424] Updated weights for policy 0, policy_version 64606 (0.0008) -[2023-11-28 01:54:17,011][87426] Updated weights for policy 1, policy_version 64530 (0.0011) -[2023-11-28 01:54:17,383][87426] Updated weights for policy 1, policy_version 64540 (0.0012) -[2023-11-28 01:54:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 33062912. Throughput: 0: 2651.3, 1: 2681.9. Samples: 33073440. Policy #0 lag: (min: 45.0, avg: 59.6, max: 81.0) -[2023-11-28 01:54:18,445][86177] Avg episode reward: [(0, '-588.340'), (1, '-537.100')] -[2023-11-28 01:54:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000064544_16523264.pth... -[2023-11-28 01:54:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000064608_16539648.pth... -[2023-11-28 01:54:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000062016_15876096.pth -[2023-11-28 01:54:18,496][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000062080_15892480.pth -[2023-11-28 01:54:19,050][87424] Updated weights for policy 0, policy_version 64616 (0.0010) -[2023-11-28 01:54:19,437][87424] Updated weights for policy 0, policy_version 64626 (0.0010) -[2023-11-28 01:54:19,615][87426] Updated weights for policy 1, policy_version 64550 (0.0011) -[2023-11-28 01:54:19,828][87424] Updated weights for policy 0, policy_version 64636 (0.0011) -[2023-11-28 01:54:19,995][87426] Updated weights for policy 1, policy_version 64560 (0.0012) -[2023-11-28 01:54:20,376][87426] Updated weights for policy 1, policy_version 64570 (0.0012) -[2023-11-28 01:54:21,572][87424] Updated weights for policy 0, policy_version 64646 (0.0009) -[2023-11-28 01:54:21,953][87424] Updated weights for policy 0, policy_version 64656 (0.0009) -[2023-11-28 01:54:22,334][87424] Updated weights for policy 0, policy_version 64666 (0.0010) -[2023-11-28 01:54:22,848][87426] Updated weights for policy 1, policy_version 64580 (0.0011) -[2023-11-28 01:54:23,229][87426] Updated weights for policy 1, policy_version 64590 (0.0011) -[2023-11-28 01:54:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 33087488. Throughput: 0: 2636.9, 1: 2650.8. Samples: 33104160. Policy #0 lag: (min: 45.0, avg: 59.6, max: 81.0) -[2023-11-28 01:54:23,445][86177] Avg episode reward: [(0, '-590.880'), (1, '-541.340')] -[2023-11-28 01:54:23,610][87426] Updated weights for policy 1, policy_version 64600 (0.0010) -[2023-11-28 01:54:24,720][87424] Updated weights for policy 0, policy_version 64676 (0.0012) -[2023-11-28 01:54:25,103][87424] Updated weights for policy 0, policy_version 64686 (0.0012) -[2023-11-28 01:54:25,483][87424] Updated weights for policy 0, policy_version 64696 (0.0011) -[2023-11-28 01:54:26,040][87426] Updated weights for policy 1, policy_version 64610 (0.0009) -[2023-11-28 01:54:26,421][87426] Updated weights for policy 1, policy_version 64620 (0.0008) -[2023-11-28 01:54:26,802][87426] Updated weights for policy 1, policy_version 64630 (0.0012) -[2023-11-28 01:54:27,178][87426] Updated weights for policy 1, policy_version 64640 (0.0012) -[2023-11-28 01:54:27,991][87424] Updated weights for policy 0, policy_version 64706 (0.0011) -[2023-11-28 01:54:28,382][87424] Updated weights for policy 0, policy_version 64716 (0.0011) -[2023-11-28 01:54:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 33112064. Throughput: 0: 2650.3, 1: 2677.9. Samples: 33129712. Policy #0 lag: (min: 31.0, avg: 52.9, max: 91.0) -[2023-11-28 01:54:28,446][86177] Avg episode reward: [(0, '-707.940'), (1, '-539.510')] -[2023-11-28 01:54:28,765][87424] Updated weights for policy 0, policy_version 64726 (0.0012) -[2023-11-28 01:54:28,811][87426] Updated weights for policy 1, policy_version 64650 (0.0011) -[2023-11-28 01:54:29,156][87424] Updated weights for policy 0, policy_version 64736 (0.0009) -[2023-11-28 01:54:29,192][87426] Updated weights for policy 1, policy_version 64660 (0.0012) -[2023-11-28 01:54:29,576][87426] Updated weights for policy 1, policy_version 64670 (0.0012) -[2023-11-28 01:54:31,284][87424] Updated weights for policy 0, policy_version 64746 (0.0012) -[2023-11-28 01:54:31,657][87424] Updated weights for policy 0, policy_version 64756 (0.0012) -[2023-11-28 01:54:32,039][87424] Updated weights for policy 0, policy_version 64766 (0.0011) -[2023-11-28 01:54:32,116][87426] Updated weights for policy 1, policy_version 64680 (0.0010) -[2023-11-28 01:54:32,490][87426] Updated weights for policy 1, policy_version 64690 (0.0008) -[2023-11-28 01:54:32,869][87426] Updated weights for policy 1, policy_version 64700 (0.0008) -[2023-11-28 01:54:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 33144832. Throughput: 0: 2693.4, 1: 2655.5. Samples: 33154684. Policy #0 lag: (min: 31.0, avg: 52.9, max: 91.0) -[2023-11-28 01:54:33,445][86177] Avg episode reward: [(0, '-721.850'), (1, '-532.700')] -[2023-11-28 01:54:34,003][87424] Updated weights for policy 0, policy_version 64776 (0.0011) -[2023-11-28 01:54:34,384][87424] Updated weights for policy 0, policy_version 64786 (0.0012) -[2023-11-28 01:54:34,637][87426] Updated weights for policy 1, policy_version 64710 (0.0009) -[2023-11-28 01:54:34,767][87424] Updated weights for policy 0, policy_version 64796 (0.0012) -[2023-11-28 01:54:35,017][87426] Updated weights for policy 1, policy_version 64720 (0.0008) -[2023-11-28 01:54:35,398][87426] Updated weights for policy 1, policy_version 64730 (0.0009) -[2023-11-28 01:54:36,599][87424] Updated weights for policy 0, policy_version 64806 (0.0012) -[2023-11-28 01:54:36,972][87424] Updated weights for policy 0, policy_version 64816 (0.0008) -[2023-11-28 01:54:37,354][87424] Updated weights for policy 0, policy_version 64826 (0.0008) -[2023-11-28 01:54:37,497][87426] Updated weights for policy 1, policy_version 64740 (0.0009) -[2023-11-28 01:54:37,878][87426] Updated weights for policy 1, policy_version 64750 (0.0011) -[2023-11-28 01:54:38,257][87426] Updated weights for policy 1, policy_version 64760 (0.0012) -[2023-11-28 01:54:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 33169408. Throughput: 0: 2680.1, 1: 2676.3. Samples: 33187208. Policy #0 lag: (min: 31.0, avg: 52.9, max: 91.0) -[2023-11-28 01:54:38,445][86177] Avg episode reward: [(0, '-788.880'), (1, '-522.460')] -[2023-11-28 01:54:39,814][87424] Updated weights for policy 0, policy_version 64836 (0.0012) -[2023-11-28 01:54:40,199][87424] Updated weights for policy 0, policy_version 64846 (0.0011) -[2023-11-28 01:54:40,575][87424] Updated weights for policy 0, policy_version 64856 (0.0009) -[2023-11-28 01:54:40,680][87426] Updated weights for policy 1, policy_version 64770 (0.0012) -[2023-11-28 01:54:41,067][87426] Updated weights for policy 1, policy_version 64780 (0.0012) -[2023-11-28 01:54:41,451][87426] Updated weights for policy 1, policy_version 64790 (0.0012) -[2023-11-28 01:54:41,817][87426] Updated weights for policy 1, policy_version 64800 (0.0012) -[2023-11-28 01:54:43,209][87424] Updated weights for policy 0, policy_version 64866 (0.0010) -[2023-11-28 01:54:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 33193984. Throughput: 0: 2696.5, 1: 2655.3. Samples: 33210756. Policy #0 lag: (min: 31.0, avg: 52.9, max: 91.0) -[2023-11-28 01:54:43,445][86177] Avg episode reward: [(0, '-804.680'), (1, '-520.210')] -[2023-11-28 01:54:43,589][87424] Updated weights for policy 0, policy_version 64876 (0.0012) -[2023-11-28 01:54:43,972][87426] Updated weights for policy 1, policy_version 64810 (0.0011) -[2023-11-28 01:54:43,974][87424] Updated weights for policy 0, policy_version 64886 (0.0008) -[2023-11-28 01:54:44,345][87426] Updated weights for policy 1, policy_version 64820 (0.0010) -[2023-11-28 01:54:44,358][87424] Updated weights for policy 0, policy_version 64896 (0.0008) -[2023-11-28 01:54:44,725][87426] Updated weights for policy 1, policy_version 64830 (0.0012) -[2023-11-28 01:54:46,209][87424] Updated weights for policy 0, policy_version 64906 (0.0007) -[2023-11-28 01:54:46,597][87424] Updated weights for policy 0, policy_version 64916 (0.0009) -[2023-11-28 01:54:47,002][87424] Updated weights for policy 0, policy_version 64926 (0.0010) -[2023-11-28 01:54:47,148][87426] Updated weights for policy 1, policy_version 64840 (0.0008) -[2023-11-28 01:54:47,531][87426] Updated weights for policy 1, policy_version 64850 (0.0011) -[2023-11-28 01:54:47,913][87426] Updated weights for policy 1, policy_version 64860 (0.0011) -[2023-11-28 01:54:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.9). Total num frames: 33226752. Throughput: 0: 2709.0, 1: 2645.0. Samples: 33235560. Policy #0 lag: (min: 31.0, avg: 52.9, max: 91.0) -[2023-11-28 01:54:48,445][86177] Avg episode reward: [(0, '-769.940'), (1, '-504.940')] -[2023-11-28 01:54:48,640][87424] Updated weights for policy 0, policy_version 64936 (0.0012) -[2023-11-28 01:54:49,014][87424] Updated weights for policy 0, policy_version 64946 (0.0012) -[2023-11-28 01:54:49,401][87424] Updated weights for policy 0, policy_version 64956 (0.0012) -[2023-11-28 01:54:49,923][87426] Updated weights for policy 1, policy_version 64870 (0.0010) -[2023-11-28 01:54:50,309][87426] Updated weights for policy 1, policy_version 64880 (0.0010) -[2023-11-28 01:54:50,693][87426] Updated weights for policy 1, policy_version 64890 (0.0012) -[2023-11-28 01:54:51,863][87424] Updated weights for policy 0, policy_version 64966 (0.0012) -[2023-11-28 01:54:52,242][87424] Updated weights for policy 0, policy_version 64976 (0.0012) -[2023-11-28 01:54:52,620][87424] Updated weights for policy 0, policy_version 64986 (0.0011) -[2023-11-28 01:54:52,787][87426] Updated weights for policy 1, policy_version 64900 (0.0011) -[2023-11-28 01:54:53,167][87426] Updated weights for policy 1, policy_version 64910 (0.0012) -[2023-11-28 01:54:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 33251328. Throughput: 0: 2709.4, 1: 2659.9. Samples: 33268756. Policy #0 lag: (min: 31.0, avg: 52.9, max: 91.0) -[2023-11-28 01:54:53,445][86177] Avg episode reward: [(0, '-729.650'), (1, '-500.120')] -[2023-11-28 01:54:53,543][87426] Updated weights for policy 1, policy_version 64920 (0.0009) -[2023-11-28 01:54:55,076][87424] Updated weights for policy 0, policy_version 64996 (0.0010) -[2023-11-28 01:54:55,450][87424] Updated weights for policy 0, policy_version 65006 (0.0012) -[2023-11-28 01:54:55,831][87424] Updated weights for policy 0, policy_version 65016 (0.0012) -[2023-11-28 01:54:56,006][87426] Updated weights for policy 1, policy_version 64930 (0.0010) -[2023-11-28 01:54:56,377][87426] Updated weights for policy 1, policy_version 64940 (0.0011) -[2023-11-28 01:54:56,757][87426] Updated weights for policy 1, policy_version 64950 (0.0011) -[2023-11-28 01:54:57,134][87426] Updated weights for policy 1, policy_version 64960 (0.0012) -[2023-11-28 01:54:57,516][87424] Updated weights for policy 0, policy_version 65026 (0.0012) -[2023-11-28 01:54:57,894][87424] Updated weights for policy 0, policy_version 65036 (0.0012) -[2023-11-28 01:54:58,277][87424] Updated weights for policy 0, policy_version 65046 (0.0011) -[2023-11-28 01:54:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 33275904. Throughput: 0: 2701.5, 1: 2664.3. Samples: 33292208. Policy #0 lag: (min: 31.0, avg: 52.9, max: 91.0) -[2023-11-28 01:54:58,445][86177] Avg episode reward: [(0, '-676.340'), (1, '-498.390')] -[2023-11-28 01:54:58,653][87424] Updated weights for policy 0, policy_version 65056 (0.0011) -[2023-11-28 01:54:59,671][87426] Updated weights for policy 1, policy_version 64970 (0.0011) -[2023-11-28 01:55:00,050][87426] Updated weights for policy 1, policy_version 64980 (0.0009) -[2023-11-28 01:55:00,424][87426] Updated weights for policy 1, policy_version 64990 (0.0008) -[2023-11-28 01:55:00,532][87424] Updated weights for policy 0, policy_version 65066 (0.0011) -[2023-11-28 01:55:00,917][87424] Updated weights for policy 0, policy_version 65076 (0.0009) -[2023-11-28 01:55:01,297][87424] Updated weights for policy 0, policy_version 65086 (0.0008) -[2023-11-28 01:55:02,631][87426] Updated weights for policy 1, policy_version 65000 (0.0012) -[2023-11-28 01:55:03,008][87426] Updated weights for policy 1, policy_version 65010 (0.0012) -[2023-11-28 01:55:03,383][87426] Updated weights for policy 1, policy_version 65020 (0.0010) -[2023-11-28 01:55:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 33300480. Throughput: 0: 2749.1, 1: 2675.1. Samples: 33317528. Policy #0 lag: (min: 31.0, avg: 52.9, max: 91.0) -[2023-11-28 01:55:03,445][86177] Avg episode reward: [(0, '-635.790'), (1, '-537.650')] -[2023-11-28 01:55:03,499][87424] Updated weights for policy 0, policy_version 65096 (0.0011) -[2023-11-28 01:55:03,875][87424] Updated weights for policy 0, policy_version 65106 (0.0012) -[2023-11-28 01:55:04,249][87424] Updated weights for policy 0, policy_version 65116 (0.0011) -[2023-11-28 01:55:05,494][87426] Updated weights for policy 1, policy_version 65030 (0.0010) -[2023-11-28 01:55:05,872][87426] Updated weights for policy 1, policy_version 65040 (0.0007) -[2023-11-28 01:55:06,254][87426] Updated weights for policy 1, policy_version 65050 (0.0007) -[2023-11-28 01:55:06,290][87424] Updated weights for policy 0, policy_version 65126 (0.0011) -[2023-11-28 01:55:06,678][87424] Updated weights for policy 0, policy_version 65136 (0.0008) -[2023-11-28 01:55:07,063][87424] Updated weights for policy 0, policy_version 65146 (0.0011) -[2023-11-28 01:55:08,120][87426] Updated weights for policy 1, policy_version 65060 (0.0008) -[2023-11-28 01:55:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 33333248. Throughput: 0: 2769.1, 1: 2718.8. Samples: 33351112. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:55:08,445][86177] Avg episode reward: [(0, '-592.400'), (1, '-536.200')] -[2023-11-28 01:55:08,498][87426] Updated weights for policy 1, policy_version 65070 (0.0009) -[2023-11-28 01:55:08,876][87426] Updated weights for policy 1, policy_version 65080 (0.0011) -[2023-11-28 01:55:09,565][87424] Updated weights for policy 0, policy_version 65156 (0.0011) -[2023-11-28 01:55:09,945][87424] Updated weights for policy 0, policy_version 65166 (0.0009) -[2023-11-28 01:55:10,336][87424] Updated weights for policy 0, policy_version 65176 (0.0011) -[2023-11-28 01:55:11,185][87426] Updated weights for policy 1, policy_version 65090 (0.0011) -[2023-11-28 01:55:11,562][87426] Updated weights for policy 1, policy_version 65100 (0.0012) -[2023-11-28 01:55:11,934][87426] Updated weights for policy 1, policy_version 65110 (0.0012) -[2023-11-28 01:55:12,313][87426] Updated weights for policy 1, policy_version 65120 (0.0010) -[2023-11-28 01:55:12,506][87424] Updated weights for policy 0, policy_version 65186 (0.0009) -[2023-11-28 01:55:12,890][87424] Updated weights for policy 0, policy_version 65196 (0.0014) -[2023-11-28 01:55:13,269][87424] Updated weights for policy 0, policy_version 65206 (0.0009) -[2023-11-28 01:55:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 33357824. Throughput: 0: 2762.0, 1: 2691.7. Samples: 33375128. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:55:13,445][86177] Avg episode reward: [(0, '-581.380'), (1, '-537.720')] -[2023-11-28 01:55:13,650][87424] Updated weights for policy 0, policy_version 65216 (0.0007) -[2023-11-28 01:55:14,331][87426] Updated weights for policy 1, policy_version 65130 (0.0012) -[2023-11-28 01:55:14,709][87426] Updated weights for policy 1, policy_version 65140 (0.0012) -[2023-11-28 01:55:15,086][87426] Updated weights for policy 1, policy_version 65150 (0.0012) -[2023-11-28 01:55:15,571][87424] Updated weights for policy 0, policy_version 65226 (0.0012) -[2023-11-28 01:55:15,955][87424] Updated weights for policy 0, policy_version 65236 (0.0012) -[2023-11-28 01:55:16,329][87424] Updated weights for policy 0, policy_version 65246 (0.0012) -[2023-11-28 01:55:17,385][87426] Updated weights for policy 1, policy_version 65160 (0.0012) -[2023-11-28 01:55:17,774][87426] Updated weights for policy 1, policy_version 65170 (0.0011) -[2023-11-28 01:55:18,148][87426] Updated weights for policy 1, policy_version 65180 (0.0009) -[2023-11-28 01:55:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 33390592. Throughput: 0: 2741.1, 1: 2703.2. Samples: 33399680. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:55:18,445][86177] Avg episode reward: [(0, '-588.560'), (1, '-535.300')] -[2023-11-28 01:55:18,533][87424] Updated weights for policy 0, policy_version 65256 (0.0009) -[2023-11-28 01:55:18,914][87424] Updated weights for policy 0, policy_version 65266 (0.0008) -[2023-11-28 01:55:19,295][87424] Updated weights for policy 0, policy_version 65276 (0.0011) -[2023-11-28 01:55:20,564][87426] Updated weights for policy 1, policy_version 65190 (0.0008) -[2023-11-28 01:55:20,943][87426] Updated weights for policy 1, policy_version 65200 (0.0008) -[2023-11-28 01:55:21,330][87426] Updated weights for policy 1, policy_version 65210 (0.0010) -[2023-11-28 01:55:21,762][87424] Updated weights for policy 0, policy_version 65286 (0.0010) -[2023-11-28 01:55:22,143][87424] Updated weights for policy 0, policy_version 65296 (0.0009) -[2023-11-28 01:55:22,529][87424] Updated weights for policy 0, policy_version 65306 (0.0010) -[2023-11-28 01:55:23,413][87426] Updated weights for policy 1, policy_version 65220 (0.0011) -[2023-11-28 01:55:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 33415168. Throughput: 0: 2764.5, 1: 2677.5. Samples: 33432100. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:55:23,445][86177] Avg episode reward: [(0, '-578.290'), (1, '-500.600')] -[2023-11-28 01:55:23,784][87426] Updated weights for policy 1, policy_version 65230 (0.0012) -[2023-11-28 01:55:24,162][87426] Updated weights for policy 1, policy_version 65240 (0.0012) -[2023-11-28 01:55:24,362][87424] Updated weights for policy 0, policy_version 65316 (0.0011) -[2023-11-28 01:55:24,739][87424] Updated weights for policy 0, policy_version 65326 (0.0012) -[2023-11-28 01:55:25,115][87424] Updated weights for policy 0, policy_version 65336 (0.0009) -[2023-11-28 01:55:26,118][87426] Updated weights for policy 1, policy_version 65250 (0.0009) -[2023-11-28 01:55:26,503][87426] Updated weights for policy 1, policy_version 65260 (0.0007) -[2023-11-28 01:55:26,891][87426] Updated weights for policy 1, policy_version 65270 (0.0007) -[2023-11-28 01:55:26,918][87424] Updated weights for policy 0, policy_version 65346 (0.0008) -[2023-11-28 01:55:27,282][87426] Updated weights for policy 1, policy_version 65280 (0.0007) -[2023-11-28 01:55:27,300][87424] Updated weights for policy 0, policy_version 65356 (0.0012) -[2023-11-28 01:55:27,674][87424] Updated weights for policy 0, policy_version 65366 (0.0010) -[2023-11-28 01:55:28,053][87424] Updated weights for policy 0, policy_version 65376 (0.0008) -[2023-11-28 01:55:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 33447936. Throughput: 0: 2773.7, 1: 2714.5. Samples: 33457724. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:55:28,445][86177] Avg episode reward: [(0, '-572.020'), (1, '-510.170')] -[2023-11-28 01:55:29,162][87426] Updated weights for policy 1, policy_version 65290 (0.0007) -[2023-11-28 01:55:29,548][87426] Updated weights for policy 1, policy_version 65300 (0.0007) -[2023-11-28 01:55:29,921][87426] Updated weights for policy 1, policy_version 65310 (0.0010) -[2023-11-28 01:55:29,942][87424] Updated weights for policy 0, policy_version 65386 (0.0011) -[2023-11-28 01:55:30,323][87424] Updated weights for policy 0, policy_version 65396 (0.0011) -[2023-11-28 01:55:30,703][87424] Updated weights for policy 0, policy_version 65406 (0.0012) -[2023-11-28 01:55:32,365][87426] Updated weights for policy 1, policy_version 65320 (0.0012) -[2023-11-28 01:55:32,672][87424] Updated weights for policy 0, policy_version 65416 (0.0011) -[2023-11-28 01:55:32,738][87426] Updated weights for policy 1, policy_version 65330 (0.0011) -[2023-11-28 01:55:33,067][87424] Updated weights for policy 0, policy_version 65426 (0.0012) -[2023-11-28 01:55:33,115][87426] Updated weights for policy 1, policy_version 65340 (0.0012) -[2023-11-28 01:55:33,442][87424] Updated weights for policy 0, policy_version 65436 (0.0012) -[2023-11-28 01:55:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 33472512. Throughput: 0: 2785.2, 1: 2742.3. Samples: 33484300. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:55:33,446][86177] Avg episode reward: [(0, '-556.010'), (1, '-511.880')] -[2023-11-28 01:55:35,257][87426] Updated weights for policy 1, policy_version 65350 (0.0009) -[2023-11-28 01:55:35,638][87426] Updated weights for policy 1, policy_version 65360 (0.0008) -[2023-11-28 01:55:35,668][87424] Updated weights for policy 0, policy_version 65446 (0.0010) -[2023-11-28 01:55:36,016][87426] Updated weights for policy 1, policy_version 65370 (0.0007) -[2023-11-28 01:55:36,047][87424] Updated weights for policy 0, policy_version 65456 (0.0012) -[2023-11-28 01:55:36,431][87424] Updated weights for policy 0, policy_version 65466 (0.0011) -[2023-11-28 01:55:37,624][87426] Updated weights for policy 1, policy_version 65380 (0.0009) -[2023-11-28 01:55:37,997][87426] Updated weights for policy 1, policy_version 65390 (0.0007) -[2023-11-28 01:55:38,386][87426] Updated weights for policy 1, policy_version 65400 (0.0008) -[2023-11-28 01:55:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 33497088. Throughput: 0: 2787.6, 1: 2743.9. Samples: 33517672. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:55:38,445][86177] Avg episode reward: [(0, '-576.660'), (1, '-511.860')] -[2023-11-28 01:55:38,904][87424] Updated weights for policy 0, policy_version 65476 (0.0011) -[2023-11-28 01:55:39,296][87424] Updated weights for policy 0, policy_version 65486 (0.0011) -[2023-11-28 01:55:39,669][87424] Updated weights for policy 0, policy_version 65496 (0.0012) -[2023-11-28 01:55:40,754][87426] Updated weights for policy 1, policy_version 65410 (0.0011) -[2023-11-28 01:55:41,133][87426] Updated weights for policy 1, policy_version 65420 (0.0011) -[2023-11-28 01:55:41,501][87426] Updated weights for policy 1, policy_version 65430 (0.0010) -[2023-11-28 01:55:41,893][87426] Updated weights for policy 1, policy_version 65440 (0.0012) -[2023-11-28 01:55:42,088][87424] Updated weights for policy 0, policy_version 65506 (0.0011) -[2023-11-28 01:55:42,467][87424] Updated weights for policy 0, policy_version 65516 (0.0008) -[2023-11-28 01:55:42,844][87424] Updated weights for policy 0, policy_version 65526 (0.0009) -[2023-11-28 01:55:43,229][87424] Updated weights for policy 0, policy_version 65536 (0.0008) -[2023-11-28 01:55:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 33529856. Throughput: 0: 2806.7, 1: 2739.2. Samples: 33541772. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:55:43,445][86177] Avg episode reward: [(0, '-567.560'), (1, '-512.850')] -[2023-11-28 01:55:44,074][87426] Updated weights for policy 1, policy_version 65450 (0.0010) -[2023-11-28 01:55:44,454][87426] Updated weights for policy 1, policy_version 65460 (0.0007) -[2023-11-28 01:55:44,843][87426] Updated weights for policy 1, policy_version 65470 (0.0010) -[2023-11-28 01:55:45,000][87424] Updated weights for policy 0, policy_version 65546 (0.0008) -[2023-11-28 01:55:45,382][87424] Updated weights for policy 0, policy_version 65556 (0.0008) -[2023-11-28 01:55:45,767][87424] Updated weights for policy 0, policy_version 65566 (0.0008) -[2023-11-28 01:55:47,253][87426] Updated weights for policy 1, policy_version 65480 (0.0011) -[2023-11-28 01:55:47,633][87426] Updated weights for policy 1, policy_version 65490 (0.0012) -[2023-11-28 01:55:48,018][87426] Updated weights for policy 1, policy_version 65500 (0.0012) -[2023-11-28 01:55:48,243][87424] Updated weights for policy 0, policy_version 65576 (0.0011) -[2023-11-28 01:55:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 33554432. Throughput: 0: 2770.8, 1: 2737.2. Samples: 33565388. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 01:55:48,445][86177] Avg episode reward: [(0, '-558.240'), (1, '-505.720')] -[2023-11-28 01:55:48,629][87424] Updated weights for policy 0, policy_version 65586 (0.0011) -[2023-11-28 01:55:49,010][87424] Updated weights for policy 0, policy_version 65596 (0.0010) -[2023-11-28 01:55:50,137][87426] Updated weights for policy 1, policy_version 65510 (0.0012) -[2023-11-28 01:55:50,515][87426] Updated weights for policy 1, policy_version 65520 (0.0012) -[2023-11-28 01:55:50,890][87426] Updated weights for policy 1, policy_version 65530 (0.0012) -[2023-11-28 01:55:51,402][87424] Updated weights for policy 0, policy_version 65606 (0.0010) -[2023-11-28 01:55:51,787][87424] Updated weights for policy 0, policy_version 65616 (0.0011) -[2023-11-28 01:55:52,166][87424] Updated weights for policy 0, policy_version 65626 (0.0011) -[2023-11-28 01:55:52,981][87426] Updated weights for policy 1, policy_version 65540 (0.0011) -[2023-11-28 01:55:53,371][87426] Updated weights for policy 1, policy_version 65550 (0.0012) -[2023-11-28 01:55:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 33579008. Throughput: 0: 2736.0, 1: 2728.5. Samples: 33597016. Policy #0 lag: (min: 6.0, avg: 15.7, max: 38.0) -[2023-11-28 01:55:53,445][86177] Avg episode reward: [(0, '-597.990'), (1, '-503.470')] -[2023-11-28 01:55:53,740][87426] Updated weights for policy 1, policy_version 65560 (0.0012) -[2023-11-28 01:55:54,398][87424] Updated weights for policy 0, policy_version 65636 (0.0012) -[2023-11-28 01:55:54,781][87424] Updated weights for policy 0, policy_version 65646 (0.0008) -[2023-11-28 01:55:55,159][87424] Updated weights for policy 0, policy_version 65656 (0.0008) -[2023-11-28 01:55:56,112][87426] Updated weights for policy 1, policy_version 65570 (0.0011) -[2023-11-28 01:55:56,486][87426] Updated weights for policy 1, policy_version 65580 (0.0007) -[2023-11-28 01:55:56,874][87426] Updated weights for policy 1, policy_version 65590 (0.0007) -[2023-11-28 01:55:57,255][87426] Updated weights for policy 1, policy_version 65600 (0.0007) -[2023-11-28 01:55:57,526][87424] Updated weights for policy 0, policy_version 65666 (0.0008) -[2023-11-28 01:55:57,921][87424] Updated weights for policy 0, policy_version 65676 (0.0007) -[2023-11-28 01:55:58,305][87424] Updated weights for policy 0, policy_version 65686 (0.0008) -[2023-11-28 01:55:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 33603584. Throughput: 0: 2738.7, 1: 2720.1. Samples: 33620772. Policy #0 lag: (min: 6.0, avg: 15.7, max: 38.0) -[2023-11-28 01:55:58,445][86177] Avg episode reward: [(0, '-571.800'), (1, '-508.290')] -[2023-11-28 01:55:58,692][87424] Updated weights for policy 0, policy_version 65696 (0.0007) -[2023-11-28 01:55:59,485][87426] Updated weights for policy 1, policy_version 65610 (0.0007) -[2023-11-28 01:55:59,865][87426] Updated weights for policy 1, policy_version 65620 (0.0009) -[2023-11-28 01:56:00,254][87426] Updated weights for policy 1, policy_version 65630 (0.0008) -[2023-11-28 01:56:01,184][87424] Updated weights for policy 0, policy_version 65706 (0.0008) -[2023-11-28 01:56:01,569][87424] Updated weights for policy 0, policy_version 65716 (0.0008) -[2023-11-28 01:56:01,950][87424] Updated weights for policy 0, policy_version 65726 (0.0010) -[2023-11-28 01:56:02,805][87426] Updated weights for policy 1, policy_version 65640 (0.0012) -[2023-11-28 01:56:03,184][87426] Updated weights for policy 1, policy_version 65650 (0.0008) -[2023-11-28 01:56:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 33628160. Throughput: 0: 2717.4, 1: 2701.6. Samples: 33643536. Policy #0 lag: (min: 6.0, avg: 15.7, max: 38.0) -[2023-11-28 01:56:03,445][86177] Avg episode reward: [(0, '-580.550'), (1, '-506.140')] -[2023-11-28 01:56:03,566][87426] Updated weights for policy 1, policy_version 65660 (0.0008) -[2023-11-28 01:56:03,925][87424] Updated weights for policy 0, policy_version 65736 (0.0010) -[2023-11-28 01:56:04,318][87424] Updated weights for policy 0, policy_version 65746 (0.0008) -[2023-11-28 01:56:04,703][87424] Updated weights for policy 0, policy_version 65756 (0.0010) -[2023-11-28 01:56:05,793][87426] Updated weights for policy 1, policy_version 65670 (0.0010) -[2023-11-28 01:56:06,178][87426] Updated weights for policy 1, policy_version 65680 (0.0009) -[2023-11-28 01:56:06,554][87426] Updated weights for policy 1, policy_version 65690 (0.0012) -[2023-11-28 01:56:06,791][87424] Updated weights for policy 0, policy_version 65766 (0.0011) -[2023-11-28 01:56:07,166][87424] Updated weights for policy 0, policy_version 65776 (0.0011) -[2023-11-28 01:56:07,554][87424] Updated weights for policy 0, policy_version 65786 (0.0012) -[2023-11-28 01:56:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 33660928. Throughput: 0: 2730.1, 1: 2695.1. Samples: 33676236. Policy #0 lag: (min: 6.0, avg: 15.7, max: 38.0) -[2023-11-28 01:56:08,445][86177] Avg episode reward: [(0, '-612.740'), (1, '-501.690')] -[2023-11-28 01:56:08,868][87426] Updated weights for policy 1, policy_version 65700 (0.0011) -[2023-11-28 01:56:09,248][87426] Updated weights for policy 1, policy_version 65710 (0.0012) -[2023-11-28 01:56:09,359][87424] Updated weights for policy 0, policy_version 65796 (0.0011) -[2023-11-28 01:56:09,629][87426] Updated weights for policy 1, policy_version 65720 (0.0012) -[2023-11-28 01:56:09,734][87424] Updated weights for policy 0, policy_version 65806 (0.0010) -[2023-11-28 01:56:10,134][87424] Updated weights for policy 0, policy_version 65816 (0.0012) -[2023-11-28 01:56:12,203][87426] Updated weights for policy 1, policy_version 65730 (0.0011) -[2023-11-28 01:56:12,576][87426] Updated weights for policy 1, policy_version 65740 (0.0011) -[2023-11-28 01:56:12,585][87424] Updated weights for policy 0, policy_version 65826 (0.0011) -[2023-11-28 01:56:12,950][87426] Updated weights for policy 1, policy_version 65750 (0.0010) -[2023-11-28 01:56:12,959][87424] Updated weights for policy 0, policy_version 65836 (0.0012) -[2023-11-28 01:56:13,336][87426] Updated weights for policy 1, policy_version 65760 (0.0011) -[2023-11-28 01:56:13,343][87424] Updated weights for policy 0, policy_version 65846 (0.0012) -[2023-11-28 01:56:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 33685504. Throughput: 0: 2717.9, 1: 2665.7. Samples: 33699984. Policy #0 lag: (min: 6.0, avg: 15.7, max: 38.0) -[2023-11-28 01:56:13,445][86177] Avg episode reward: [(0, '-567.060'), (1, '-507.330')] -[2023-11-28 01:56:13,724][87424] Updated weights for policy 0, policy_version 65856 (0.0009) -[2023-11-28 01:56:15,692][87424] Updated weights for policy 0, policy_version 65866 (0.0012) -[2023-11-28 01:56:15,755][87426] Updated weights for policy 1, policy_version 65770 (0.0010) -[2023-11-28 01:56:16,073][87424] Updated weights for policy 0, policy_version 65876 (0.0012) -[2023-11-28 01:56:16,147][87426] Updated weights for policy 1, policy_version 65780 (0.0008) -[2023-11-28 01:56:16,459][87424] Updated weights for policy 0, policy_version 65886 (0.0009) -[2023-11-28 01:56:16,509][87426] Updated weights for policy 1, policy_version 65790 (0.0011) -[2023-11-28 01:56:18,336][87426] Updated weights for policy 1, policy_version 65800 (0.0012) -[2023-11-28 01:56:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 33710080. Throughput: 0: 2685.6, 1: 2658.8. Samples: 33724796. Policy #0 lag: (min: 6.0, avg: 15.7, max: 38.0) -[2023-11-28 01:56:18,445][86177] Avg episode reward: [(0, '-566.730'), (1, '-507.260')] -[2023-11-28 01:56:18,682][87424] Updated weights for policy 0, policy_version 65896 (0.0011) -[2023-11-28 01:56:18,712][87426] Updated weights for policy 1, policy_version 65810 (0.0009) -[2023-11-28 01:56:19,066][87424] Updated weights for policy 0, policy_version 65906 (0.0012) -[2023-11-28 01:56:19,088][87426] Updated weights for policy 1, policy_version 65820 (0.0009) -[2023-11-28 01:56:19,241][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000065824_16850944.pth... -[2023-11-28 01:56:19,286][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000063296_16203776.pth -[2023-11-28 01:56:19,446][87424] Updated weights for policy 0, policy_version 65916 (0.0011) -[2023-11-28 01:56:19,603][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000065920_16875520.pth... -[2023-11-28 01:56:19,651][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000063360_16220160.pth -[2023-11-28 01:56:21,370][87426] Updated weights for policy 1, policy_version 65830 (0.0009) -[2023-11-28 01:56:21,731][87424] Updated weights for policy 0, policy_version 65926 (0.0010) -[2023-11-28 01:56:21,758][87426] Updated weights for policy 1, policy_version 65840 (0.0009) -[2023-11-28 01:56:22,115][87424] Updated weights for policy 0, policy_version 65936 (0.0009) -[2023-11-28 01:56:22,133][87426] Updated weights for policy 1, policy_version 65850 (0.0011) -[2023-11-28 01:56:22,499][87424] Updated weights for policy 0, policy_version 65946 (0.0011) -[2023-11-28 01:56:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 33742848. Throughput: 0: 2663.6, 1: 2642.9. Samples: 33756464. Policy #0 lag: (min: 6.0, avg: 15.7, max: 38.0) -[2023-11-28 01:56:23,445][86177] Avg episode reward: [(0, '-566.420'), (1, '-505.570')] -[2023-11-28 01:56:24,661][87424] Updated weights for policy 0, policy_version 65956 (0.0011) -[2023-11-28 01:56:24,750][87426] Updated weights for policy 1, policy_version 65860 (0.0011) -[2023-11-28 01:56:25,053][87424] Updated weights for policy 0, policy_version 65966 (0.0010) -[2023-11-28 01:56:25,138][87426] Updated weights for policy 1, policy_version 65870 (0.0011) -[2023-11-28 01:56:25,427][87424] Updated weights for policy 0, policy_version 65976 (0.0010) -[2023-11-28 01:56:25,513][87426] Updated weights for policy 1, policy_version 65880 (0.0009) -[2023-11-28 01:56:27,094][87426] Updated weights for policy 1, policy_version 65890 (0.0008) -[2023-11-28 01:56:27,474][87426] Updated weights for policy 1, policy_version 65900 (0.0007) -[2023-11-28 01:56:27,613][87424] Updated weights for policy 0, policy_version 65986 (0.0010) -[2023-11-28 01:56:27,852][87426] Updated weights for policy 1, policy_version 65910 (0.0007) -[2023-11-28 01:56:27,995][87424] Updated weights for policy 0, policy_version 65996 (0.0007) -[2023-11-28 01:56:28,236][87426] Updated weights for policy 1, policy_version 65920 (0.0007) -[2023-11-28 01:56:28,385][87424] Updated weights for policy 0, policy_version 66006 (0.0007) -[2023-11-28 01:56:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 33767424. Throughput: 0: 2654.6, 1: 2663.3. Samples: 33781076. Policy #0 lag: (min: 6.0, avg: 15.7, max: 38.0) -[2023-11-28 01:56:28,445][86177] Avg episode reward: [(0, '-565.700'), (1, '-504.630')] -[2023-11-28 01:56:28,773][87424] Updated weights for policy 0, policy_version 66016 (0.0007) -[2023-11-28 01:56:30,674][87426] Updated weights for policy 1, policy_version 65930 (0.0009) -[2023-11-28 01:56:31,060][87426] Updated weights for policy 1, policy_version 65940 (0.0011) -[2023-11-28 01:56:31,163][87424] Updated weights for policy 0, policy_version 66026 (0.0008) -[2023-11-28 01:56:31,434][87426] Updated weights for policy 1, policy_version 65950 (0.0009) -[2023-11-28 01:56:31,563][87424] Updated weights for policy 0, policy_version 66036 (0.0011) -[2023-11-28 01:56:31,941][87424] Updated weights for policy 0, policy_version 66046 (0.0012) -[2023-11-28 01:56:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 33792000. Throughput: 0: 2647.4, 1: 2662.0. Samples: 33804308. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 01:56:33,445][86177] Avg episode reward: [(0, '-561.910'), (1, '-503.310')] -[2023-11-28 01:56:34,051][87426] Updated weights for policy 1, policy_version 65960 (0.0008) -[2023-11-28 01:56:34,434][87426] Updated weights for policy 1, policy_version 65970 (0.0007) -[2023-11-28 01:56:34,450][87424] Updated weights for policy 0, policy_version 66056 (0.0012) -[2023-11-28 01:56:34,808][87426] Updated weights for policy 1, policy_version 65980 (0.0008) -[2023-11-28 01:56:34,830][87424] Updated weights for policy 0, policy_version 66066 (0.0011) -[2023-11-28 01:56:35,214][87424] Updated weights for policy 0, policy_version 66076 (0.0008) -[2023-11-28 01:56:37,179][87426] Updated weights for policy 1, policy_version 65990 (0.0010) -[2023-11-28 01:56:37,565][87426] Updated weights for policy 1, policy_version 66000 (0.0011) -[2023-11-28 01:56:37,635][87424] Updated weights for policy 0, policy_version 66086 (0.0009) -[2023-11-28 01:56:37,936][87426] Updated weights for policy 1, policy_version 66010 (0.0009) -[2023-11-28 01:56:38,016][87424] Updated weights for policy 0, policy_version 66096 (0.0007) -[2023-11-28 01:56:38,399][87424] Updated weights for policy 0, policy_version 66106 (0.0011) -[2023-11-28 01:56:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 33816576. Throughput: 0: 2689.7, 1: 2640.1. Samples: 33836856. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 01:56:38,445][86177] Avg episode reward: [(0, '-560.050'), (1, '-501.510')] -[2023-11-28 01:56:39,550][87426] Updated weights for policy 1, policy_version 66020 (0.0009) -[2023-11-28 01:56:39,935][87426] Updated weights for policy 1, policy_version 66030 (0.0009) -[2023-11-28 01:56:40,312][87426] Updated weights for policy 1, policy_version 66040 (0.0011) -[2023-11-28 01:56:40,773][87424] Updated weights for policy 0, policy_version 66116 (0.0009) -[2023-11-28 01:56:41,153][87424] Updated weights for policy 0, policy_version 66126 (0.0012) -[2023-11-28 01:56:41,532][87424] Updated weights for policy 0, policy_version 66136 (0.0012) -[2023-11-28 01:56:42,848][87426] Updated weights for policy 1, policy_version 66050 (0.0012) -[2023-11-28 01:56:43,227][87426] Updated weights for policy 1, policy_version 66060 (0.0008) -[2023-11-28 01:56:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 33841152. Throughput: 0: 2680.1, 1: 2648.0. Samples: 33860536. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 01:56:43,445][86177] Avg episode reward: [(0, '-519.070'), (1, '-503.310')] -[2023-11-28 01:56:43,613][87426] Updated weights for policy 1, policy_version 66070 (0.0008) -[2023-11-28 01:56:43,730][87424] Updated weights for policy 0, policy_version 66146 (0.0011) -[2023-11-28 01:56:43,981][87426] Updated weights for policy 1, policy_version 66080 (0.0011) -[2023-11-28 01:56:44,120][87424] Updated weights for policy 0, policy_version 66156 (0.0012) -[2023-11-28 01:56:44,513][87424] Updated weights for policy 0, policy_version 66166 (0.0012) -[2023-11-28 01:56:44,884][87424] Updated weights for policy 0, policy_version 66176 (0.0012) -[2023-11-28 01:56:45,875][87426] Updated weights for policy 1, policy_version 66090 (0.0009) -[2023-11-28 01:56:46,262][87426] Updated weights for policy 1, policy_version 66100 (0.0009) -[2023-11-28 01:56:46,636][87426] Updated weights for policy 1, policy_version 66110 (0.0008) -[2023-11-28 01:56:46,768][87424] Updated weights for policy 0, policy_version 66186 (0.0012) -[2023-11-28 01:56:47,148][87424] Updated weights for policy 0, policy_version 66196 (0.0012) -[2023-11-28 01:56:47,532][87424] Updated weights for policy 0, policy_version 66206 (0.0012) -[2023-11-28 01:56:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 33873920. Throughput: 0: 2697.5, 1: 2671.4. Samples: 33885136. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 01:56:48,445][86177] Avg episode reward: [(0, '-533.810'), (1, '-498.530')] -[2023-11-28 01:56:48,692][87426] Updated weights for policy 1, policy_version 66120 (0.0009) -[2023-11-28 01:56:49,071][87426] Updated weights for policy 1, policy_version 66130 (0.0011) -[2023-11-28 01:56:49,145][87424] Updated weights for policy 0, policy_version 66216 (0.0010) -[2023-11-28 01:56:49,451][87426] Updated weights for policy 1, policy_version 66140 (0.0009) -[2023-11-28 01:56:49,533][87424] Updated weights for policy 0, policy_version 66226 (0.0012) -[2023-11-28 01:56:49,920][87424] Updated weights for policy 0, policy_version 66236 (0.0012) -[2023-11-28 01:56:51,516][87426] Updated weights for policy 1, policy_version 66150 (0.0008) -[2023-11-28 01:56:51,889][87426] Updated weights for policy 1, policy_version 66160 (0.0011) -[2023-11-28 01:56:52,267][87426] Updated weights for policy 1, policy_version 66170 (0.0011) -[2023-11-28 01:56:52,409][87424] Updated weights for policy 0, policy_version 66246 (0.0010) -[2023-11-28 01:56:52,778][87424] Updated weights for policy 0, policy_version 66256 (0.0010) -[2023-11-28 01:56:53,162][87424] Updated weights for policy 0, policy_version 66266 (0.0011) -[2023-11-28 01:56:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 33906688. Throughput: 0: 2696.7, 1: 2675.3. Samples: 33917976. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 01:56:53,445][86177] Avg episode reward: [(0, '-529.320'), (1, '-512.950')] -[2023-11-28 01:56:54,339][87426] Updated weights for policy 1, policy_version 66180 (0.0011) -[2023-11-28 01:56:54,710][87426] Updated weights for policy 1, policy_version 66190 (0.0007) -[2023-11-28 01:56:55,088][87426] Updated weights for policy 1, policy_version 66200 (0.0008) -[2023-11-28 01:56:55,308][87424] Updated weights for policy 0, policy_version 66276 (0.0012) -[2023-11-28 01:56:55,700][87424] Updated weights for policy 0, policy_version 66286 (0.0011) -[2023-11-28 01:56:56,084][87424] Updated weights for policy 0, policy_version 66296 (0.0012) -[2023-11-28 01:56:57,403][87426] Updated weights for policy 1, policy_version 66210 (0.0007) -[2023-11-28 01:56:57,789][87426] Updated weights for policy 1, policy_version 66220 (0.0007) -[2023-11-28 01:56:57,864][87424] Updated weights for policy 0, policy_version 66306 (0.0011) -[2023-11-28 01:56:58,157][87426] Updated weights for policy 1, policy_version 66230 (0.0007) -[2023-11-28 01:56:58,247][87424] Updated weights for policy 0, policy_version 66316 (0.0007) -[2023-11-28 01:56:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 33923072. Throughput: 0: 2694.2, 1: 2686.0. Samples: 33942096. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 01:56:58,445][86177] Avg episode reward: [(0, '-527.680'), (1, '-514.220')] -[2023-11-28 01:56:58,541][87426] Updated weights for policy 1, policy_version 66240 (0.0007) -[2023-11-28 01:56:58,643][87424] Updated weights for policy 0, policy_version 66326 (0.0008) -[2023-11-28 01:56:59,020][87424] Updated weights for policy 0, policy_version 66336 (0.0012) -[2023-11-28 01:57:00,470][87426] Updated weights for policy 1, policy_version 66250 (0.0010) -[2023-11-28 01:57:00,737][87424] Updated weights for policy 0, policy_version 66346 (0.0010) -[2023-11-28 01:57:00,842][87426] Updated weights for policy 1, policy_version 66260 (0.0012) -[2023-11-28 01:57:01,128][87424] Updated weights for policy 0, policy_version 66356 (0.0011) -[2023-11-28 01:57:01,218][87426] Updated weights for policy 1, policy_version 66270 (0.0008) -[2023-11-28 01:57:01,501][87424] Updated weights for policy 0, policy_version 66366 (0.0011) -[2023-11-28 01:57:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 33955840. Throughput: 0: 2697.0, 1: 2686.3. Samples: 33967044. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 01:57:03,445][86177] Avg episode reward: [(0, '-524.960'), (1, '-511.560')] -[2023-11-28 01:57:03,683][87426] Updated weights for policy 1, policy_version 66280 (0.0011) -[2023-11-28 01:57:03,933][87424] Updated weights for policy 0, policy_version 66376 (0.0012) -[2023-11-28 01:57:04,054][87426] Updated weights for policy 1, policy_version 66290 (0.0011) -[2023-11-28 01:57:04,317][87424] Updated weights for policy 0, policy_version 66386 (0.0011) -[2023-11-28 01:57:04,438][87426] Updated weights for policy 1, policy_version 66300 (0.0011) -[2023-11-28 01:57:04,698][87424] Updated weights for policy 0, policy_version 66396 (0.0011) -[2023-11-28 01:57:06,656][87424] Updated weights for policy 0, policy_version 66406 (0.0012) -[2023-11-28 01:57:06,889][87426] Updated weights for policy 1, policy_version 66310 (0.0010) -[2023-11-28 01:57:07,032][87424] Updated weights for policy 0, policy_version 66416 (0.0009) -[2023-11-28 01:57:07,270][87426] Updated weights for policy 1, policy_version 66320 (0.0010) -[2023-11-28 01:57:07,425][87424] Updated weights for policy 0, policy_version 66426 (0.0007) -[2023-11-28 01:57:07,647][87426] Updated weights for policy 1, policy_version 66330 (0.0008) -[2023-11-28 01:57:08,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 33988608. Throughput: 0: 2728.6, 1: 2714.4. Samples: 34001400. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 01:57:08,446][86177] Avg episode reward: [(0, '-528.500'), (1, '-516.260')] -[2023-11-28 01:57:09,832][87424] Updated weights for policy 0, policy_version 66436 (0.0008) -[2023-11-28 01:57:10,194][87426] Updated weights for policy 1, policy_version 66340 (0.0009) -[2023-11-28 01:57:10,205][87424] Updated weights for policy 0, policy_version 66446 (0.0011) -[2023-11-28 01:57:10,573][87426] Updated weights for policy 1, policy_version 66350 (0.0011) -[2023-11-28 01:57:10,588][87424] Updated weights for policy 0, policy_version 66456 (0.0011) -[2023-11-28 01:57:10,949][87426] Updated weights for policy 1, policy_version 66360 (0.0010) -[2023-11-28 01:57:12,673][87424] Updated weights for policy 0, policy_version 66466 (0.0011) -[2023-11-28 01:57:13,045][87424] Updated weights for policy 0, policy_version 66476 (0.0012) -[2023-11-28 01:57:13,137][87426] Updated weights for policy 1, policy_version 66370 (0.0011) -[2023-11-28 01:57:13,426][87424] Updated weights for policy 0, policy_version 66486 (0.0011) -[2023-11-28 01:57:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 34004992. Throughput: 0: 2747.6, 1: 2692.6. Samples: 34025884. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 01:57:13,445][86177] Avg episode reward: [(0, '-527.370'), (1, '-502.590')] -[2023-11-28 01:57:13,515][87426] Updated weights for policy 1, policy_version 66380 (0.0007) -[2023-11-28 01:57:13,809][87424] Updated weights for policy 0, policy_version 66496 (0.0009) -[2023-11-28 01:57:13,902][87426] Updated weights for policy 1, policy_version 66390 (0.0007) -[2023-11-28 01:57:14,281][87426] Updated weights for policy 1, policy_version 66400 (0.0007) -[2023-11-28 01:57:16,039][87426] Updated weights for policy 1, policy_version 66410 (0.0010) -[2023-11-28 01:57:16,409][87424] Updated weights for policy 0, policy_version 66506 (0.0011) -[2023-11-28 01:57:16,421][87426] Updated weights for policy 1, policy_version 66420 (0.0007) -[2023-11-28 01:57:16,795][87424] Updated weights for policy 0, policy_version 66516 (0.0009) -[2023-11-28 01:57:16,810][87426] Updated weights for policy 1, policy_version 66430 (0.0008) -[2023-11-28 01:57:17,176][87424] Updated weights for policy 0, policy_version 66526 (0.0010) -[2023-11-28 01:57:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 34037760. Throughput: 0: 2765.2, 1: 2698.2. Samples: 34050164. Policy #0 lag: (min: 18.0, avg: 44.0, max: 50.0) -[2023-11-28 01:57:18,445][86177] Avg episode reward: [(0, '-530.810'), (1, '-503.140')] -[2023-11-28 01:57:18,905][87424] Updated weights for policy 0, policy_version 66536 (0.0011) -[2023-11-28 01:57:19,291][87424] Updated weights for policy 0, policy_version 66546 (0.0012) -[2023-11-28 01:57:19,298][87426] Updated weights for policy 1, policy_version 66440 (0.0010) -[2023-11-28 01:57:19,673][87426] Updated weights for policy 1, policy_version 66450 (0.0012) -[2023-11-28 01:57:19,690][87424] Updated weights for policy 0, policy_version 66556 (0.0012) -[2023-11-28 01:57:20,054][87426] Updated weights for policy 1, policy_version 66460 (0.0011) -[2023-11-28 01:57:22,022][87426] Updated weights for policy 1, policy_version 66470 (0.0011) -[2023-11-28 01:57:22,190][87424] Updated weights for policy 0, policy_version 66566 (0.0011) -[2023-11-28 01:57:22,397][87426] Updated weights for policy 1, policy_version 66480 (0.0009) -[2023-11-28 01:57:22,570][87424] Updated weights for policy 0, policy_version 66576 (0.0011) -[2023-11-28 01:57:22,775][87426] Updated weights for policy 1, policy_version 66490 (0.0009) -[2023-11-28 01:57:22,944][87424] Updated weights for policy 0, policy_version 66586 (0.0012) -[2023-11-28 01:57:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 34070528. Throughput: 0: 2750.2, 1: 2740.4. Samples: 34083932. Policy #0 lag: (min: 18.0, avg: 44.0, max: 50.0) -[2023-11-28 01:57:23,445][86177] Avg episode reward: [(0, '-531.260'), (1, '-505.460')] -[2023-11-28 01:57:24,571][87426] Updated weights for policy 1, policy_version 66500 (0.0010) -[2023-11-28 01:57:24,949][87426] Updated weights for policy 1, policy_version 66510 (0.0011) -[2023-11-28 01:57:25,169][87424] Updated weights for policy 0, policy_version 66596 (0.0012) -[2023-11-28 01:57:25,325][87426] Updated weights for policy 1, policy_version 66520 (0.0008) -[2023-11-28 01:57:25,555][87424] Updated weights for policy 0, policy_version 66606 (0.0012) -[2023-11-28 01:57:25,944][87424] Updated weights for policy 0, policy_version 66616 (0.0012) -[2023-11-28 01:57:26,970][87426] Updated weights for policy 1, policy_version 66530 (0.0008) -[2023-11-28 01:57:27,352][87426] Updated weights for policy 1, policy_version 66540 (0.0012) -[2023-11-28 01:57:27,714][87424] Updated weights for policy 0, policy_version 66626 (0.0012) -[2023-11-28 01:57:27,740][87426] Updated weights for policy 1, policy_version 66550 (0.0011) -[2023-11-28 01:57:28,097][87424] Updated weights for policy 0, policy_version 66636 (0.0011) -[2023-11-28 01:57:28,113][87426] Updated weights for policy 1, policy_version 66560 (0.0011) -[2023-11-28 01:57:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 34095104. Throughput: 0: 2756.3, 1: 2751.6. Samples: 34108388. Policy #0 lag: (min: 18.0, avg: 44.0, max: 50.0) -[2023-11-28 01:57:28,445][86177] Avg episode reward: [(0, '-510.020'), (1, '-500.110')] -[2023-11-28 01:57:28,489][87424] Updated weights for policy 0, policy_version 66646 (0.0011) -[2023-11-28 01:57:28,865][87424] Updated weights for policy 0, policy_version 66656 (0.0012) -[2023-11-28 01:57:30,147][87426] Updated weights for policy 1, policy_version 66570 (0.0012) -[2023-11-28 01:57:30,518][87426] Updated weights for policy 1, policy_version 66580 (0.0012) -[2023-11-28 01:57:30,747][87424] Updated weights for policy 0, policy_version 66666 (0.0012) -[2023-11-28 01:57:30,888][87426] Updated weights for policy 1, policy_version 66590 (0.0011) -[2023-11-28 01:57:31,130][87424] Updated weights for policy 0, policy_version 66676 (0.0010) -[2023-11-28 01:57:31,519][87424] Updated weights for policy 0, policy_version 66686 (0.0007) -[2023-11-28 01:57:33,208][87426] Updated weights for policy 1, policy_version 66600 (0.0008) -[2023-11-28 01:57:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 34119680. Throughput: 0: 2780.6, 1: 2763.9. Samples: 34134640. Policy #0 lag: (min: 18.0, avg: 44.0, max: 50.0) -[2023-11-28 01:57:33,445][86177] Avg episode reward: [(0, '-524.470'), (1, '-501.570')] -[2023-11-28 01:57:33,595][87426] Updated weights for policy 1, policy_version 66610 (0.0007) -[2023-11-28 01:57:33,974][87426] Updated weights for policy 1, policy_version 66620 (0.0007) -[2023-11-28 01:57:34,016][87424] Updated weights for policy 0, policy_version 66696 (0.0008) -[2023-11-28 01:57:34,393][87424] Updated weights for policy 0, policy_version 66706 (0.0011) -[2023-11-28 01:57:34,771][87424] Updated weights for policy 0, policy_version 66716 (0.0012) -[2023-11-28 01:57:36,331][87426] Updated weights for policy 1, policy_version 66630 (0.0010) -[2023-11-28 01:57:36,701][87426] Updated weights for policy 1, policy_version 66640 (0.0010) -[2023-11-28 01:57:37,037][87424] Updated weights for policy 0, policy_version 66726 (0.0012) -[2023-11-28 01:57:37,081][87426] Updated weights for policy 1, policy_version 66650 (0.0011) -[2023-11-28 01:57:37,415][87424] Updated weights for policy 0, policy_version 66736 (0.0008) -[2023-11-28 01:57:37,808][87424] Updated weights for policy 0, policy_version 66746 (0.0008) -[2023-11-28 01:57:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 34152448. Throughput: 0: 2759.2, 1: 2791.6. Samples: 34167764. Policy #0 lag: (min: 18.0, avg: 44.0, max: 50.0) -[2023-11-28 01:57:38,445][86177] Avg episode reward: [(0, '-520.550'), (1, '-501.040')] -[2023-11-28 01:57:38,971][87426] Updated weights for policy 1, policy_version 66660 (0.0011) -[2023-11-28 01:57:39,362][87426] Updated weights for policy 1, policy_version 66670 (0.0011) -[2023-11-28 01:57:39,746][87426] Updated weights for policy 1, policy_version 66680 (0.0011) -[2023-11-28 01:57:40,215][87424] Updated weights for policy 0, policy_version 66756 (0.0008) -[2023-11-28 01:57:40,602][87424] Updated weights for policy 0, policy_version 66766 (0.0008) -[2023-11-28 01:57:40,983][87424] Updated weights for policy 0, policy_version 66776 (0.0008) -[2023-11-28 01:57:42,168][87426] Updated weights for policy 1, policy_version 66690 (0.0010) -[2023-11-28 01:57:42,548][87426] Updated weights for policy 1, policy_version 66700 (0.0011) -[2023-11-28 01:57:42,920][87426] Updated weights for policy 1, policy_version 66710 (0.0012) -[2023-11-28 01:57:42,982][87424] Updated weights for policy 0, policy_version 66786 (0.0009) -[2023-11-28 01:57:43,294][87426] Updated weights for policy 1, policy_version 66720 (0.0010) -[2023-11-28 01:57:43,358][87424] Updated weights for policy 0, policy_version 66796 (0.0011) -[2023-11-28 01:57:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 34177024. Throughput: 0: 2776.5, 1: 2769.4. Samples: 34191664. Policy #0 lag: (min: 18.0, avg: 44.0, max: 50.0) -[2023-11-28 01:57:43,445][86177] Avg episode reward: [(0, '-525.730'), (1, '-500.840')] -[2023-11-28 01:57:43,736][87424] Updated weights for policy 0, policy_version 66806 (0.0009) -[2023-11-28 01:57:44,115][87424] Updated weights for policy 0, policy_version 66816 (0.0007) -[2023-11-28 01:57:45,768][87426] Updated weights for policy 1, policy_version 66730 (0.0010) -[2023-11-28 01:57:45,776][87424] Updated weights for policy 0, policy_version 66826 (0.0011) -[2023-11-28 01:57:46,153][87426] Updated weights for policy 1, policy_version 66740 (0.0010) -[2023-11-28 01:57:46,165][87424] Updated weights for policy 0, policy_version 66836 (0.0011) -[2023-11-28 01:57:46,528][87426] Updated weights for policy 1, policy_version 66750 (0.0010) -[2023-11-28 01:57:46,545][87424] Updated weights for policy 0, policy_version 66846 (0.0008) -[2023-11-28 01:57:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 34201600. Throughput: 0: 2770.0, 1: 2750.5. Samples: 34215464. Policy #0 lag: (min: 18.0, avg: 44.0, max: 50.0) -[2023-11-28 01:57:48,445][86177] Avg episode reward: [(0, '-529.980'), (1, '-504.190')] -[2023-11-28 01:57:48,533][87424] Updated weights for policy 0, policy_version 66856 (0.0011) -[2023-11-28 01:57:48,919][87424] Updated weights for policy 0, policy_version 66866 (0.0011) -[2023-11-28 01:57:49,076][87426] Updated weights for policy 1, policy_version 66760 (0.0011) -[2023-11-28 01:57:49,292][87424] Updated weights for policy 0, policy_version 66876 (0.0011) -[2023-11-28 01:57:49,448][87426] Updated weights for policy 1, policy_version 66770 (0.0011) -[2023-11-28 01:57:49,829][87426] Updated weights for policy 1, policy_version 66780 (0.0012) -[2023-11-28 01:57:51,358][87424] Updated weights for policy 0, policy_version 66886 (0.0011) -[2023-11-28 01:57:51,750][87424] Updated weights for policy 0, policy_version 66896 (0.0011) -[2023-11-28 01:57:52,067][87426] Updated weights for policy 1, policy_version 66790 (0.0011) -[2023-11-28 01:57:52,125][87424] Updated weights for policy 0, policy_version 66906 (0.0011) -[2023-11-28 01:57:52,434][87426] Updated weights for policy 1, policy_version 66800 (0.0012) -[2023-11-28 01:57:52,814][87426] Updated weights for policy 1, policy_version 66810 (0.0012) -[2023-11-28 01:57:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34234368. Throughput: 0: 2742.3, 1: 2726.9. Samples: 34247512. Policy #0 lag: (min: 18.0, avg: 44.0, max: 50.0) -[2023-11-28 01:57:53,445][86177] Avg episode reward: [(0, '-533.260'), (1, '-507.300')] -[2023-11-28 01:57:54,717][87424] Updated weights for policy 0, policy_version 66916 (0.0011) -[2023-11-28 01:57:55,069][87426] Updated weights for policy 1, policy_version 66820 (0.0008) -[2023-11-28 01:57:55,101][87424] Updated weights for policy 0, policy_version 66926 (0.0011) -[2023-11-28 01:57:55,447][87426] Updated weights for policy 1, policy_version 66830 (0.0009) -[2023-11-28 01:57:55,476][87424] Updated weights for policy 0, policy_version 66936 (0.0012) -[2023-11-28 01:57:55,829][87426] Updated weights for policy 1, policy_version 66840 (0.0011) -[2023-11-28 01:57:57,528][87426] Updated weights for policy 1, policy_version 66850 (0.0010) -[2023-11-28 01:57:57,755][87424] Updated weights for policy 0, policy_version 66946 (0.0011) -[2023-11-28 01:57:57,908][87426] Updated weights for policy 1, policy_version 66860 (0.0007) -[2023-11-28 01:57:58,143][87424] Updated weights for policy 0, policy_version 66956 (0.0011) -[2023-11-28 01:57:58,292][87426] Updated weights for policy 1, policy_version 66870 (0.0010) -[2023-11-28 01:57:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 34250752. Throughput: 0: 2710.3, 1: 2743.5. Samples: 34271308. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 01:57:58,445][86177] Avg episode reward: [(0, '-540.030'), (1, '-506.590')] -[2023-11-28 01:57:58,524][87424] Updated weights for policy 0, policy_version 66966 (0.0011) -[2023-11-28 01:57:58,678][87426] Updated weights for policy 1, policy_version 66880 (0.0011) -[2023-11-28 01:57:58,906][87424] Updated weights for policy 0, policy_version 66976 (0.0011) -[2023-11-28 01:58:00,531][87426] Updated weights for policy 1, policy_version 66890 (0.0011) -[2023-11-28 01:58:00,906][87426] Updated weights for policy 1, policy_version 66900 (0.0010) -[2023-11-28 01:58:01,283][87426] Updated weights for policy 1, policy_version 66910 (0.0007) -[2023-11-28 01:58:01,424][87424] Updated weights for policy 0, policy_version 66986 (0.0008) -[2023-11-28 01:58:01,814][87424] Updated weights for policy 0, policy_version 66996 (0.0009) -[2023-11-28 01:58:02,211][87424] Updated weights for policy 0, policy_version 67006 (0.0011) -[2023-11-28 01:58:03,151][87426] Updated weights for policy 1, policy_version 66920 (0.0011) -[2023-11-28 01:58:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 34283520. Throughput: 0: 2715.6, 1: 2756.4. Samples: 34296404. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 01:58:03,445][86177] Avg episode reward: [(0, '-541.590'), (1, '-500.340')] -[2023-11-28 01:58:03,533][87426] Updated weights for policy 1, policy_version 66930 (0.0010) -[2023-11-28 01:58:03,909][87426] Updated weights for policy 1, policy_version 66940 (0.0007) -[2023-11-28 01:58:04,049][87424] Updated weights for policy 0, policy_version 67016 (0.0009) -[2023-11-28 01:58:04,452][87424] Updated weights for policy 0, policy_version 67026 (0.0007) -[2023-11-28 01:58:04,835][87424] Updated weights for policy 0, policy_version 67036 (0.0008) -[2023-11-28 01:58:06,025][87426] Updated weights for policy 1, policy_version 66950 (0.0010) -[2023-11-28 01:58:06,417][87426] Updated weights for policy 1, policy_version 66960 (0.0012) -[2023-11-28 01:58:06,818][87426] Updated weights for policy 1, policy_version 66970 (0.0014) -[2023-11-28 01:58:06,830][87424] Updated weights for policy 0, policy_version 67046 (0.0010) -[2023-11-28 01:58:07,209][87424] Updated weights for policy 0, policy_version 67056 (0.0009) -[2023-11-28 01:58:07,595][87424] Updated weights for policy 0, policy_version 67066 (0.0008) -[2023-11-28 01:58:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34316288. Throughput: 0: 2731.5, 1: 2736.8. Samples: 34330004. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 01:58:08,445][86177] Avg episode reward: [(0, '-536.010'), (1, '-499.720')] -[2023-11-28 01:58:09,335][87426] Updated weights for policy 1, policy_version 66980 (0.0008) -[2023-11-28 01:58:09,535][87424] Updated weights for policy 0, policy_version 67076 (0.0009) -[2023-11-28 01:58:09,710][87426] Updated weights for policy 1, policy_version 66990 (0.0010) -[2023-11-28 01:58:09,917][87424] Updated weights for policy 0, policy_version 67086 (0.0010) -[2023-11-28 01:58:10,096][87426] Updated weights for policy 1, policy_version 67000 (0.0009) -[2023-11-28 01:58:10,306][87424] Updated weights for policy 0, policy_version 67096 (0.0011) -[2023-11-28 01:58:12,134][87424] Updated weights for policy 0, policy_version 67106 (0.0010) -[2023-11-28 01:58:12,503][87424] Updated weights for policy 0, policy_version 67116 (0.0011) -[2023-11-28 01:58:12,639][87426] Updated weights for policy 1, policy_version 67010 (0.0009) -[2023-11-28 01:58:12,886][87424] Updated weights for policy 0, policy_version 67126 (0.0012) -[2023-11-28 01:58:13,017][87426] Updated weights for policy 1, policy_version 67020 (0.0011) -[2023-11-28 01:58:13,272][87424] Updated weights for policy 0, policy_version 67136 (0.0010) -[2023-11-28 01:58:13,393][87426] Updated weights for policy 1, policy_version 67030 (0.0007) -[2023-11-28 01:58:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 34340864. Throughput: 0: 2744.0, 1: 2712.3. Samples: 34353920. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 01:58:13,445][86177] Avg episode reward: [(0, '-521.520'), (1, '-496.980')] -[2023-11-28 01:58:13,773][87426] Updated weights for policy 1, policy_version 67040 (0.0008) -[2023-11-28 01:58:15,564][87426] Updated weights for policy 1, policy_version 67050 (0.0011) -[2023-11-28 01:58:15,762][87424] Updated weights for policy 0, policy_version 67146 (0.0012) -[2023-11-28 01:58:15,942][87426] Updated weights for policy 1, policy_version 67060 (0.0011) -[2023-11-28 01:58:16,147][87424] Updated weights for policy 0, policy_version 67156 (0.0011) -[2023-11-28 01:58:16,321][87426] Updated weights for policy 1, policy_version 67070 (0.0008) -[2023-11-28 01:58:16,525][87424] Updated weights for policy 0, policy_version 67166 (0.0012) -[2023-11-28 01:58:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 34365440. Throughput: 0: 2719.0, 1: 2711.2. Samples: 34379000. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 01:58:18,445][86177] Avg episode reward: [(0, '-516.710'), (1, '-498.320')] -[2023-11-28 01:58:18,677][87424] Updated weights for policy 0, policy_version 67176 (0.0008) -[2023-11-28 01:58:18,732][87426] Updated weights for policy 1, policy_version 67080 (0.0010) -[2023-11-28 01:58:19,059][87424] Updated weights for policy 0, policy_version 67186 (0.0008) -[2023-11-28 01:58:19,113][87426] Updated weights for policy 1, policy_version 67090 (0.0009) -[2023-11-28 01:58:19,441][87424] Updated weights for policy 0, policy_version 67196 (0.0008) -[2023-11-28 01:58:19,489][87426] Updated weights for policy 1, policy_version 67100 (0.0012) -[2023-11-28 01:58:19,591][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000067200_17203200.pth... -[2023-11-28 01:58:19,621][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000064608_16539648.pth -[2023-11-28 01:58:19,642][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000067104_17178624.pth... -[2023-11-28 01:58:19,689][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000064544_16523264.pth -[2023-11-28 01:58:21,716][87424] Updated weights for policy 0, policy_version 67206 (0.0012) -[2023-11-28 01:58:21,772][87426] Updated weights for policy 1, policy_version 67110 (0.0011) -[2023-11-28 01:58:22,099][87424] Updated weights for policy 0, policy_version 67216 (0.0011) -[2023-11-28 01:58:22,143][87426] Updated weights for policy 1, policy_version 67120 (0.0012) -[2023-11-28 01:58:22,488][87424] Updated weights for policy 0, policy_version 67226 (0.0012) -[2023-11-28 01:58:22,532][87426] Updated weights for policy 1, policy_version 67130 (0.0011) -[2023-11-28 01:58:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34398208. Throughput: 0: 2735.9, 1: 2683.2. Samples: 34411624. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 01:58:23,445][86177] Avg episode reward: [(0, '-522.900'), (1, '-502.360')] -[2023-11-28 01:58:24,584][87424] Updated weights for policy 0, policy_version 67236 (0.0012) -[2023-11-28 01:58:24,912][87426] Updated weights for policy 1, policy_version 67140 (0.0011) -[2023-11-28 01:58:24,973][87424] Updated weights for policy 0, policy_version 67246 (0.0011) -[2023-11-28 01:58:25,284][87426] Updated weights for policy 1, policy_version 67150 (0.0010) -[2023-11-28 01:58:25,356][87424] Updated weights for policy 0, policy_version 67256 (0.0011) -[2023-11-28 01:58:25,662][87426] Updated weights for policy 1, policy_version 67160 (0.0008) -[2023-11-28 01:58:27,282][87426] Updated weights for policy 1, policy_version 67170 (0.0008) -[2023-11-28 01:58:27,445][87424] Updated weights for policy 0, policy_version 67266 (0.0009) -[2023-11-28 01:58:27,658][87426] Updated weights for policy 1, policy_version 67180 (0.0008) -[2023-11-28 01:58:27,838][87424] Updated weights for policy 0, policy_version 67276 (0.0007) -[2023-11-28 01:58:28,043][87426] Updated weights for policy 1, policy_version 67190 (0.0007) -[2023-11-28 01:58:28,224][87424] Updated weights for policy 0, policy_version 67286 (0.0007) -[2023-11-28 01:58:28,426][87426] Updated weights for policy 1, policy_version 67200 (0.0007) -[2023-11-28 01:58:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 34422784. Throughput: 0: 2726.8, 1: 2728.7. Samples: 34437160. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 01:58:28,445][86177] Avg episode reward: [(0, '-550.070'), (1, '-501.130')] -[2023-11-28 01:58:28,611][87424] Updated weights for policy 0, policy_version 67296 (0.0008) -[2023-11-28 01:58:30,669][87426] Updated weights for policy 1, policy_version 67210 (0.0010) -[2023-11-28 01:58:30,968][87424] Updated weights for policy 0, policy_version 67306 (0.0009) -[2023-11-28 01:58:31,054][87426] Updated weights for policy 1, policy_version 67220 (0.0010) -[2023-11-28 01:58:31,347][87424] Updated weights for policy 0, policy_version 67316 (0.0010) -[2023-11-28 01:58:31,437][87426] Updated weights for policy 1, policy_version 67230 (0.0011) -[2023-11-28 01:58:31,724][87424] Updated weights for policy 0, policy_version 67326 (0.0011) -[2023-11-28 01:58:33,367][87426] Updated weights for policy 1, policy_version 67240 (0.0011) -[2023-11-28 01:58:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 34447360. Throughput: 0: 2708.8, 1: 2745.2. Samples: 34460896. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 01:58:33,445][86177] Avg episode reward: [(0, '-545.680'), (1, '-505.400')] -[2023-11-28 01:58:33,745][87426] Updated weights for policy 1, policy_version 67250 (0.0012) -[2023-11-28 01:58:34,120][87426] Updated weights for policy 1, policy_version 67260 (0.0010) -[2023-11-28 01:58:34,157][87424] Updated weights for policy 0, policy_version 67336 (0.0012) -[2023-11-28 01:58:34,535][87424] Updated weights for policy 0, policy_version 67346 (0.0011) -[2023-11-28 01:58:34,916][87424] Updated weights for policy 0, policy_version 67356 (0.0012) -[2023-11-28 01:58:36,413][87426] Updated weights for policy 1, policy_version 67270 (0.0012) -[2023-11-28 01:58:36,789][87426] Updated weights for policy 1, policy_version 67280 (0.0011) -[2023-11-28 01:58:37,051][87424] Updated weights for policy 0, policy_version 67366 (0.0010) -[2023-11-28 01:58:37,173][87426] Updated weights for policy 1, policy_version 67290 (0.0008) -[2023-11-28 01:58:37,437][87424] Updated weights for policy 0, policy_version 67376 (0.0007) -[2023-11-28 01:58:37,812][87424] Updated weights for policy 0, policy_version 67386 (0.0009) -[2023-11-28 01:58:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34480128. Throughput: 0: 2713.3, 1: 2754.2. Samples: 34493548. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 01:58:38,445][86177] Avg episode reward: [(0, '-561.300'), (1, '-509.740')] -[2023-11-28 01:58:39,179][87426] Updated weights for policy 1, policy_version 67300 (0.0009) -[2023-11-28 01:58:39,555][87426] Updated weights for policy 1, policy_version 67310 (0.0011) -[2023-11-28 01:58:39,938][87426] Updated weights for policy 1, policy_version 67320 (0.0010) -[2023-11-28 01:58:40,025][87424] Updated weights for policy 0, policy_version 67396 (0.0009) -[2023-11-28 01:58:40,411][87424] Updated weights for policy 0, policy_version 67406 (0.0012) -[2023-11-28 01:58:40,797][87424] Updated weights for policy 0, policy_version 67416 (0.0011) -[2023-11-28 01:58:42,155][87426] Updated weights for policy 1, policy_version 67330 (0.0012) -[2023-11-28 01:58:42,533][87426] Updated weights for policy 1, policy_version 67340 (0.0012) -[2023-11-28 01:58:42,818][87424] Updated weights for policy 0, policy_version 67426 (0.0011) -[2023-11-28 01:58:42,898][87426] Updated weights for policy 1, policy_version 67350 (0.0011) -[2023-11-28 01:58:43,190][87424] Updated weights for policy 0, policy_version 67436 (0.0011) -[2023-11-28 01:58:43,272][87426] Updated weights for policy 1, policy_version 67360 (0.0011) -[2023-11-28 01:58:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34504704. Throughput: 0: 2734.4, 1: 2741.5. Samples: 34517724. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 01:58:43,445][86177] Avg episode reward: [(0, '-555.170'), (1, '-505.210')] -[2023-11-28 01:58:43,574][87424] Updated weights for policy 0, policy_version 67446 (0.0011) -[2023-11-28 01:58:43,956][87424] Updated weights for policy 0, policy_version 67456 (0.0010) -[2023-11-28 01:58:45,130][87426] Updated weights for policy 1, policy_version 67370 (0.0012) -[2023-11-28 01:58:45,506][87426] Updated weights for policy 1, policy_version 67380 (0.0012) -[2023-11-28 01:58:45,882][87426] Updated weights for policy 1, policy_version 67390 (0.0009) -[2023-11-28 01:58:46,107][87424] Updated weights for policy 0, policy_version 67466 (0.0010) -[2023-11-28 01:58:46,499][87424] Updated weights for policy 0, policy_version 67476 (0.0007) -[2023-11-28 01:58:46,889][87424] Updated weights for policy 0, policy_version 67486 (0.0008) -[2023-11-28 01:58:48,366][87426] Updated weights for policy 1, policy_version 67400 (0.0011) -[2023-11-28 01:58:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 34529280. Throughput: 0: 2735.2, 1: 2731.4. Samples: 34542400. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 01:58:48,445][86177] Avg episode reward: [(0, '-536.940'), (1, '-505.160')] -[2023-11-28 01:58:48,746][87426] Updated weights for policy 1, policy_version 67410 (0.0012) -[2023-11-28 01:58:48,999][87424] Updated weights for policy 0, policy_version 67496 (0.0011) -[2023-11-28 01:58:49,127][87426] Updated weights for policy 1, policy_version 67420 (0.0012) -[2023-11-28 01:58:49,379][87424] Updated weights for policy 0, policy_version 67506 (0.0012) -[2023-11-28 01:58:49,764][87424] Updated weights for policy 0, policy_version 67516 (0.0012) -[2023-11-28 01:58:51,653][87426] Updated weights for policy 1, policy_version 67430 (0.0010) -[2023-11-28 01:58:52,042][87426] Updated weights for policy 1, policy_version 67440 (0.0011) -[2023-11-28 01:58:52,201][87424] Updated weights for policy 0, policy_version 67526 (0.0010) -[2023-11-28 01:58:52,427][87426] Updated weights for policy 1, policy_version 67450 (0.0011) -[2023-11-28 01:58:52,586][87424] Updated weights for policy 0, policy_version 67536 (0.0012) -[2023-11-28 01:58:52,967][87424] Updated weights for policy 0, policy_version 67546 (0.0012) -[2023-11-28 01:58:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34562048. Throughput: 0: 2712.4, 1: 2717.8. Samples: 34574360. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 01:58:53,445][86177] Avg episode reward: [(0, '-553.240'), (1, '-505.040')] -[2023-11-28 01:58:54,495][87426] Updated weights for policy 1, policy_version 67460 (0.0011) -[2023-11-28 01:58:54,880][87426] Updated weights for policy 1, policy_version 67470 (0.0012) -[2023-11-28 01:58:55,023][87424] Updated weights for policy 0, policy_version 67556 (0.0011) -[2023-11-28 01:58:55,255][87426] Updated weights for policy 1, policy_version 67480 (0.0011) -[2023-11-28 01:58:55,420][87424] Updated weights for policy 0, policy_version 67566 (0.0009) -[2023-11-28 01:58:55,798][87424] Updated weights for policy 0, policy_version 67576 (0.0007) -[2023-11-28 01:58:57,352][87426] Updated weights for policy 1, policy_version 67490 (0.0011) -[2023-11-28 01:58:57,718][87424] Updated weights for policy 0, policy_version 67586 (0.0008) -[2023-11-28 01:58:57,734][87426] Updated weights for policy 1, policy_version 67500 (0.0008) -[2023-11-28 01:58:58,098][87424] Updated weights for policy 0, policy_version 67596 (0.0011) -[2023-11-28 01:58:58,114][87426] Updated weights for policy 1, policy_version 67510 (0.0009) -[2023-11-28 01:58:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 34578432. Throughput: 0: 2699.3, 1: 2762.0. Samples: 34599680. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 01:58:58,445][86177] Avg episode reward: [(0, '-548.420'), (1, '-500.710')] -[2023-11-28 01:58:58,485][87424] Updated weights for policy 0, policy_version 67606 (0.0012) -[2023-11-28 01:58:58,496][87426] Updated weights for policy 1, policy_version 67520 (0.0007) -[2023-11-28 01:58:58,869][87424] Updated weights for policy 0, policy_version 67616 (0.0012) -[2023-11-28 01:59:00,743][87426] Updated weights for policy 1, policy_version 67530 (0.0012) -[2023-11-28 01:59:01,117][87426] Updated weights for policy 1, policy_version 67540 (0.0012) -[2023-11-28 01:59:01,225][87424] Updated weights for policy 0, policy_version 67626 (0.0012) -[2023-11-28 01:59:01,486][87426] Updated weights for policy 1, policy_version 67550 (0.0011) -[2023-11-28 01:59:01,606][87424] Updated weights for policy 0, policy_version 67636 (0.0011) -[2023-11-28 01:59:01,988][87424] Updated weights for policy 0, policy_version 67646 (0.0010) -[2023-11-28 01:59:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 34611200. Throughput: 0: 2719.9, 1: 2729.9. Samples: 34624244. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 01:59:03,446][86177] Avg episode reward: [(0, '-583.120'), (1, '-501.950')] -[2023-11-28 01:59:03,934][87426] Updated weights for policy 1, policy_version 67560 (0.0008) -[2023-11-28 01:59:04,312][87426] Updated weights for policy 1, policy_version 67570 (0.0008) -[2023-11-28 01:59:04,318][87424] Updated weights for policy 0, policy_version 67656 (0.0011) -[2023-11-28 01:59:04,682][87426] Updated weights for policy 1, policy_version 67580 (0.0010) -[2023-11-28 01:59:04,705][87424] Updated weights for policy 0, policy_version 67666 (0.0011) -[2023-11-28 01:59:05,082][87424] Updated weights for policy 0, policy_version 67676 (0.0012) -[2023-11-28 01:59:06,467][87426] Updated weights for policy 1, policy_version 67590 (0.0009) -[2023-11-28 01:59:06,846][87426] Updated weights for policy 1, policy_version 67600 (0.0008) -[2023-11-28 01:59:07,224][87426] Updated weights for policy 1, policy_version 67610 (0.0008) -[2023-11-28 01:59:07,519][87424] Updated weights for policy 0, policy_version 67686 (0.0012) -[2023-11-28 01:59:07,901][87424] Updated weights for policy 0, policy_version 67696 (0.0012) -[2023-11-28 01:59:08,285][87424] Updated weights for policy 0, policy_version 67706 (0.0012) -[2023-11-28 01:59:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 34635776. Throughput: 0: 2688.6, 1: 2760.0. Samples: 34656812. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 01:59:08,445][86177] Avg episode reward: [(0, '-578.600'), (1, '-496.780')] -[2023-11-28 01:59:09,062][87426] Updated weights for policy 1, policy_version 67620 (0.0011) -[2023-11-28 01:59:09,441][87426] Updated weights for policy 1, policy_version 67630 (0.0011) -[2023-11-28 01:59:09,826][87426] Updated weights for policy 1, policy_version 67640 (0.0012) -[2023-11-28 01:59:10,433][87424] Updated weights for policy 0, policy_version 67716 (0.0012) -[2023-11-28 01:59:10,816][87424] Updated weights for policy 0, policy_version 67726 (0.0012) -[2023-11-28 01:59:11,197][87424] Updated weights for policy 0, policy_version 67736 (0.0012) -[2023-11-28 01:59:12,347][87426] Updated weights for policy 1, policy_version 67650 (0.0011) -[2023-11-28 01:59:12,721][87426] Updated weights for policy 1, policy_version 67660 (0.0011) -[2023-11-28 01:59:13,094][87426] Updated weights for policy 1, policy_version 67670 (0.0011) -[2023-11-28 01:59:13,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.7, 300 sec: 5415.0). Total num frames: 34660352. Throughput: 0: 2676.1, 1: 2734.2. Samples: 34680624. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 01:59:13,446][86177] Avg episode reward: [(0, '-579.640'), (1, '-498.380')] -[2023-11-28 01:59:13,470][87426] Updated weights for policy 1, policy_version 67680 (0.0012) -[2023-11-28 01:59:13,589][87424] Updated weights for policy 0, policy_version 67746 (0.0011) -[2023-11-28 01:59:13,964][87424] Updated weights for policy 0, policy_version 67756 (0.0011) -[2023-11-28 01:59:14,355][87424] Updated weights for policy 0, policy_version 67766 (0.0012) -[2023-11-28 01:59:14,728][87424] Updated weights for policy 0, policy_version 67776 (0.0009) -[2023-11-28 01:59:15,541][87426] Updated weights for policy 1, policy_version 67690 (0.0009) -[2023-11-28 01:59:15,925][87426] Updated weights for policy 1, policy_version 67700 (0.0008) -[2023-11-28 01:59:16,304][87426] Updated weights for policy 1, policy_version 67710 (0.0008) -[2023-11-28 01:59:17,203][87424] Updated weights for policy 0, policy_version 67786 (0.0011) -[2023-11-28 01:59:17,585][87424] Updated weights for policy 0, policy_version 67796 (0.0011) -[2023-11-28 01:59:17,973][87424] Updated weights for policy 0, policy_version 67806 (0.0008) -[2023-11-28 01:59:18,376][87426] Updated weights for policy 1, policy_version 67720 (0.0010) -[2023-11-28 01:59:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34693120. Throughput: 0: 2690.2, 1: 2738.7. Samples: 34705196. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 01:59:18,445][86177] Avg episode reward: [(0, '-588.560'), (1, '-498.820')] -[2023-11-28 01:59:18,747][87426] Updated weights for policy 1, policy_version 67730 (0.0010) -[2023-11-28 01:59:19,128][87426] Updated weights for policy 1, policy_version 67740 (0.0010) -[2023-11-28 01:59:19,897][87424] Updated weights for policy 0, policy_version 67816 (0.0010) -[2023-11-28 01:59:20,280][87424] Updated weights for policy 0, policy_version 67826 (0.0010) -[2023-11-28 01:59:20,664][87424] Updated weights for policy 0, policy_version 67836 (0.0011) -[2023-11-28 01:59:21,716][87426] Updated weights for policy 1, policy_version 67750 (0.0011) -[2023-11-28 01:59:22,092][87426] Updated weights for policy 1, policy_version 67760 (0.0012) -[2023-11-28 01:59:22,469][87426] Updated weights for policy 1, policy_version 67770 (0.0012) -[2023-11-28 01:59:22,895][87424] Updated weights for policy 0, policy_version 67846 (0.0011) -[2023-11-28 01:59:23,288][87424] Updated weights for policy 0, policy_version 67856 (0.0011) -[2023-11-28 01:59:23,444][86177] Fps is (10 sec: 5734.8, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 34717696. Throughput: 0: 2684.6, 1: 2712.0. Samples: 34736396. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 01:59:23,445][86177] Avg episode reward: [(0, '-552.060'), (1, '-497.480')] -[2023-11-28 01:59:23,668][87424] Updated weights for policy 0, policy_version 67866 (0.0011) -[2023-11-28 01:59:24,304][87426] Updated weights for policy 1, policy_version 67780 (0.0010) -[2023-11-28 01:59:24,682][87426] Updated weights for policy 1, policy_version 67790 (0.0007) -[2023-11-28 01:59:25,061][87426] Updated weights for policy 1, policy_version 67800 (0.0007) -[2023-11-28 01:59:25,345][87424] Updated weights for policy 0, policy_version 67876 (0.0011) -[2023-11-28 01:59:25,725][87424] Updated weights for policy 0, policy_version 67886 (0.0011) -[2023-11-28 01:59:26,099][87424] Updated weights for policy 0, policy_version 67896 (0.0012) -[2023-11-28 01:59:27,014][87426] Updated weights for policy 1, policy_version 67810 (0.0008) -[2023-11-28 01:59:27,398][87426] Updated weights for policy 1, policy_version 67820 (0.0010) -[2023-11-28 01:59:27,762][87426] Updated weights for policy 1, policy_version 67830 (0.0012) -[2023-11-28 01:59:28,093][87424] Updated weights for policy 0, policy_version 67906 (0.0012) -[2023-11-28 01:59:28,139][87426] Updated weights for policy 1, policy_version 67840 (0.0009) -[2023-11-28 01:59:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34750464. Throughput: 0: 2687.6, 1: 2719.4. Samples: 34761036. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-11-28 01:59:28,445][86177] Avg episode reward: [(0, '-559.450'), (1, '-496.580')] -[2023-11-28 01:59:28,479][87424] Updated weights for policy 0, policy_version 67916 (0.0012) -[2023-11-28 01:59:28,873][87424] Updated weights for policy 0, policy_version 67926 (0.0012) -[2023-11-28 01:59:29,253][87424] Updated weights for policy 0, policy_version 67936 (0.0012) -[2023-11-28 01:59:30,659][87426] Updated weights for policy 1, policy_version 67850 (0.0010) -[2023-11-28 01:59:31,035][87426] Updated weights for policy 1, policy_version 67860 (0.0011) -[2023-11-28 01:59:31,252][87424] Updated weights for policy 0, policy_version 67946 (0.0011) -[2023-11-28 01:59:31,418][87426] Updated weights for policy 1, policy_version 67870 (0.0007) -[2023-11-28 01:59:31,644][87424] Updated weights for policy 0, policy_version 67956 (0.0012) -[2023-11-28 01:59:32,019][87424] Updated weights for policy 0, policy_version 67966 (0.0012) -[2023-11-28 01:59:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34775040. Throughput: 0: 2706.0, 1: 2710.0. Samples: 34786124. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-11-28 01:59:33,445][86177] Avg episode reward: [(0, '-552.270'), (1, '-494.600')] -[2023-11-28 01:59:33,845][87426] Updated weights for policy 1, policy_version 67880 (0.0011) -[2023-11-28 01:59:34,130][87424] Updated weights for policy 0, policy_version 67976 (0.0008) -[2023-11-28 01:59:34,226][87426] Updated weights for policy 1, policy_version 67890 (0.0007) -[2023-11-28 01:59:34,511][87424] Updated weights for policy 0, policy_version 67986 (0.0007) -[2023-11-28 01:59:34,608][87426] Updated weights for policy 1, policy_version 67900 (0.0007) -[2023-11-28 01:59:34,892][87424] Updated weights for policy 0, policy_version 67996 (0.0010) -[2023-11-28 01:59:36,643][87424] Updated weights for policy 0, policy_version 68006 (0.0009) -[2023-11-28 01:59:37,029][87424] Updated weights for policy 0, policy_version 68016 (0.0008) -[2023-11-28 01:59:37,218][87426] Updated weights for policy 1, policy_version 67910 (0.0010) -[2023-11-28 01:59:37,414][87424] Updated weights for policy 0, policy_version 68026 (0.0008) -[2023-11-28 01:59:37,597][87426] Updated weights for policy 1, policy_version 67920 (0.0011) -[2023-11-28 01:59:37,973][87426] Updated weights for policy 1, policy_version 67930 (0.0011) -[2023-11-28 01:59:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 34807808. Throughput: 0: 2732.6, 1: 2718.2. Samples: 34819648. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-11-28 01:59:38,445][86177] Avg episode reward: [(0, '-555.630'), (1, '-494.800')] -[2023-11-28 01:59:39,667][87424] Updated weights for policy 0, policy_version 68036 (0.0009) -[2023-11-28 01:59:39,718][87426] Updated weights for policy 1, policy_version 67940 (0.0012) -[2023-11-28 01:59:40,049][87424] Updated weights for policy 0, policy_version 68046 (0.0009) -[2023-11-28 01:59:40,093][87426] Updated weights for policy 1, policy_version 67950 (0.0011) -[2023-11-28 01:59:40,442][87424] Updated weights for policy 0, policy_version 68056 (0.0008) -[2023-11-28 01:59:40,470][87426] Updated weights for policy 1, policy_version 67960 (0.0012) -[2023-11-28 01:59:42,816][87424] Updated weights for policy 0, policy_version 68066 (0.0009) -[2023-11-28 01:59:42,950][87426] Updated weights for policy 1, policy_version 67970 (0.0011) -[2023-11-28 01:59:43,198][87424] Updated weights for policy 0, policy_version 68076 (0.0008) -[2023-11-28 01:59:43,320][87426] Updated weights for policy 1, policy_version 67980 (0.0012) -[2023-11-28 01:59:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 34824192. Throughput: 0: 2735.1, 1: 2673.4. Samples: 34843064. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-11-28 01:59:43,445][86177] Avg episode reward: [(0, '-537.200'), (1, '-495.080')] -[2023-11-28 01:59:43,585][87424] Updated weights for policy 0, policy_version 68086 (0.0010) -[2023-11-28 01:59:43,697][87426] Updated weights for policy 1, policy_version 67990 (0.0012) -[2023-11-28 01:59:43,970][87424] Updated weights for policy 0, policy_version 68096 (0.0011) -[2023-11-28 01:59:44,074][87426] Updated weights for policy 1, policy_version 68000 (0.0011) -[2023-11-28 01:59:45,919][87424] Updated weights for policy 0, policy_version 68106 (0.0012) -[2023-11-28 01:59:46,309][87424] Updated weights for policy 0, policy_version 68116 (0.0011) -[2023-11-28 01:59:46,523][87426] Updated weights for policy 1, policy_version 68010 (0.0007) -[2023-11-28 01:59:46,698][87424] Updated weights for policy 0, policy_version 68126 (0.0008) -[2023-11-28 01:59:46,900][87426] Updated weights for policy 1, policy_version 68020 (0.0008) -[2023-11-28 01:59:47,299][87426] Updated weights for policy 1, policy_version 68030 (0.0008) -[2023-11-28 01:59:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34856960. Throughput: 0: 2724.6, 1: 2693.8. Samples: 34868072. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-11-28 01:59:48,445][86177] Avg episode reward: [(0, '-562.190'), (1, '-506.990')] -[2023-11-28 01:59:48,963][87424] Updated weights for policy 0, policy_version 68136 (0.0011) -[2023-11-28 01:59:49,343][87424] Updated weights for policy 0, policy_version 68146 (0.0012) -[2023-11-28 01:59:49,362][87426] Updated weights for policy 1, policy_version 68040 (0.0011) -[2023-11-28 01:59:49,728][87424] Updated weights for policy 0, policy_version 68156 (0.0009) -[2023-11-28 01:59:49,740][87426] Updated weights for policy 1, policy_version 68050 (0.0011) -[2023-11-28 01:59:50,131][87426] Updated weights for policy 1, policy_version 68060 (0.0012) -[2023-11-28 01:59:51,684][87424] Updated weights for policy 0, policy_version 68166 (0.0013) -[2023-11-28 01:59:52,072][87424] Updated weights for policy 0, policy_version 68176 (0.0011) -[2023-11-28 01:59:52,385][87426] Updated weights for policy 1, policy_version 68070 (0.0009) -[2023-11-28 01:59:52,454][87424] Updated weights for policy 0, policy_version 68186 (0.0012) -[2023-11-28 01:59:52,762][87426] Updated weights for policy 1, policy_version 68080 (0.0008) -[2023-11-28 01:59:53,147][87426] Updated weights for policy 1, policy_version 68090 (0.0008) -[2023-11-28 01:59:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 34889728. Throughput: 0: 2757.7, 1: 2666.9. Samples: 34900920. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-11-28 01:59:53,445][86177] Avg episode reward: [(0, '-602.110'), (1, '-508.090')] -[2023-11-28 01:59:54,861][87424] Updated weights for policy 0, policy_version 68196 (0.0011) -[2023-11-28 01:59:55,244][87424] Updated weights for policy 0, policy_version 68206 (0.0008) -[2023-11-28 01:59:55,417][87426] Updated weights for policy 1, policy_version 68100 (0.0011) -[2023-11-28 01:59:55,631][87424] Updated weights for policy 0, policy_version 68216 (0.0007) -[2023-11-28 01:59:55,795][87426] Updated weights for policy 1, policy_version 68110 (0.0008) -[2023-11-28 01:59:56,171][87426] Updated weights for policy 1, policy_version 68120 (0.0012) -[2023-11-28 01:59:57,563][87424] Updated weights for policy 0, policy_version 68226 (0.0008) -[2023-11-28 01:59:57,941][87424] Updated weights for policy 0, policy_version 68236 (0.0012) -[2023-11-28 01:59:58,097][87426] Updated weights for policy 1, policy_version 68130 (0.0011) -[2023-11-28 01:59:58,337][87424] Updated weights for policy 0, policy_version 68246 (0.0012) -[2023-11-28 01:59:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34906112. Throughput: 0: 2774.6, 1: 2673.6. Samples: 34925788. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-11-28 01:59:58,445][86177] Avg episode reward: [(0, '-613.160'), (1, '-509.360')] -[2023-11-28 01:59:58,474][87426] Updated weights for policy 1, policy_version 68140 (0.0011) -[2023-11-28 01:59:58,712][87424] Updated weights for policy 0, policy_version 68256 (0.0011) -[2023-11-28 01:59:58,851][87426] Updated weights for policy 1, policy_version 68150 (0.0012) -[2023-11-28 01:59:59,230][87426] Updated weights for policy 1, policy_version 68160 (0.0011) -[2023-11-28 02:00:00,676][87424] Updated weights for policy 0, policy_version 68266 (0.0012) -[2023-11-28 02:00:01,071][87424] Updated weights for policy 0, policy_version 68276 (0.0012) -[2023-11-28 02:00:01,449][87424] Updated weights for policy 0, policy_version 68286 (0.0011) -[2023-11-28 02:00:01,610][87426] Updated weights for policy 1, policy_version 68170 (0.0010) -[2023-11-28 02:00:01,982][87426] Updated weights for policy 1, policy_version 68180 (0.0011) -[2023-11-28 02:00:02,362][87426] Updated weights for policy 1, policy_version 68190 (0.0010) -[2023-11-28 02:00:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 34938880. Throughput: 0: 2796.2, 1: 2661.2. Samples: 34950780. Policy #0 lag: (min: 31.0, avg: 46.9, max: 63.0) -[2023-11-28 02:00:03,445][86177] Avg episode reward: [(0, '-613.600'), (1, '-512.300')] -[2023-11-28 02:00:03,775][87424] Updated weights for policy 0, policy_version 68296 (0.0012) -[2023-11-28 02:00:04,157][87424] Updated weights for policy 0, policy_version 68306 (0.0011) -[2023-11-28 02:00:04,429][87426] Updated weights for policy 1, policy_version 68200 (0.0008) -[2023-11-28 02:00:04,532][87424] Updated weights for policy 0, policy_version 68316 (0.0009) -[2023-11-28 02:00:04,815][87426] Updated weights for policy 1, policy_version 68210 (0.0008) -[2023-11-28 02:00:05,188][87426] Updated weights for policy 1, policy_version 68220 (0.0008) -[2023-11-28 02:00:06,827][87426] Updated weights for policy 1, policy_version 68230 (0.0008) -[2023-11-28 02:00:07,065][87424] Updated weights for policy 0, policy_version 68326 (0.0011) -[2023-11-28 02:00:07,220][87426] Updated weights for policy 1, policy_version 68240 (0.0009) -[2023-11-28 02:00:07,455][87424] Updated weights for policy 0, policy_version 68336 (0.0012) -[2023-11-28 02:00:07,588][87426] Updated weights for policy 1, policy_version 68250 (0.0011) -[2023-11-28 02:00:07,836][87424] Updated weights for policy 0, policy_version 68346 (0.0010) -[2023-11-28 02:00:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 34971648. Throughput: 0: 2799.5, 1: 2707.5. Samples: 34984212. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:08,445][86177] Avg episode reward: [(0, '-602.800'), (1, '-500.720')] -[2023-11-28 02:00:09,386][87426] Updated weights for policy 1, policy_version 68260 (0.0010) -[2023-11-28 02:00:09,767][87426] Updated weights for policy 1, policy_version 68270 (0.0008) -[2023-11-28 02:00:10,147][87426] Updated weights for policy 1, policy_version 68280 (0.0010) -[2023-11-28 02:00:10,169][87424] Updated weights for policy 0, policy_version 68356 (0.0012) -[2023-11-28 02:00:10,558][87424] Updated weights for policy 0, policy_version 68366 (0.0012) -[2023-11-28 02:00:10,935][87424] Updated weights for policy 0, policy_version 68376 (0.0011) -[2023-11-28 02:00:12,192][87426] Updated weights for policy 1, policy_version 68290 (0.0012) -[2023-11-28 02:00:12,571][87426] Updated weights for policy 1, policy_version 68300 (0.0012) -[2023-11-28 02:00:12,964][87426] Updated weights for policy 1, policy_version 68310 (0.0011) -[2023-11-28 02:00:13,013][87424] Updated weights for policy 0, policy_version 68386 (0.0011) -[2023-11-28 02:00:13,346][87426] Updated weights for policy 1, policy_version 68320 (0.0009) -[2023-11-28 02:00:13,388][87424] Updated weights for policy 0, policy_version 68396 (0.0010) -[2023-11-28 02:00:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 34996224. Throughput: 0: 2783.1, 1: 2728.8. Samples: 35009072. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:13,445][86177] Avg episode reward: [(0, '-571.750'), (1, '-498.810')] -[2023-11-28 02:00:13,771][87424] Updated weights for policy 0, policy_version 68406 (0.0012) -[2023-11-28 02:00:14,156][87424] Updated weights for policy 0, policy_version 68416 (0.0011) -[2023-11-28 02:00:15,639][87426] Updated weights for policy 1, policy_version 68330 (0.0012) -[2023-11-28 02:00:15,969][87424] Updated weights for policy 0, policy_version 68426 (0.0011) -[2023-11-28 02:00:16,019][87426] Updated weights for policy 1, policy_version 68340 (0.0011) -[2023-11-28 02:00:16,360][87424] Updated weights for policy 0, policy_version 68436 (0.0008) -[2023-11-28 02:00:16,402][87426] Updated weights for policy 1, policy_version 68350 (0.0012) -[2023-11-28 02:00:16,744][87424] Updated weights for policy 0, policy_version 68446 (0.0008) -[2023-11-28 02:00:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35020800. Throughput: 0: 2775.9, 1: 2731.9. Samples: 35033976. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:18,445][86177] Avg episode reward: [(0, '-617.320'), (1, '-503.710')] -[2023-11-28 02:00:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000068448_17522688.pth... -[2023-11-28 02:00:18,493][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000065920_16875520.pth -[2023-11-28 02:00:18,522][87426] Updated weights for policy 1, policy_version 68360 (0.0007) -[2023-11-28 02:00:18,901][87426] Updated weights for policy 1, policy_version 68370 (0.0008) -[2023-11-28 02:00:19,099][87424] Updated weights for policy 0, policy_version 68456 (0.0008) -[2023-11-28 02:00:19,279][87426] Updated weights for policy 1, policy_version 68380 (0.0009) -[2023-11-28 02:00:19,429][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000068384_17506304.pth... -[2023-11-28 02:00:19,460][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000065824_16850944.pth -[2023-11-28 02:00:19,486][87424] Updated weights for policy 0, policy_version 68466 (0.0010) -[2023-11-28 02:00:19,868][87424] Updated weights for policy 0, policy_version 68476 (0.0012) -[2023-11-28 02:00:21,681][87426] Updated weights for policy 1, policy_version 68390 (0.0012) -[2023-11-28 02:00:21,795][87424] Updated weights for policy 0, policy_version 68486 (0.0011) -[2023-11-28 02:00:22,059][87426] Updated weights for policy 1, policy_version 68400 (0.0010) -[2023-11-28 02:00:22,183][87424] Updated weights for policy 0, policy_version 68496 (0.0010) -[2023-11-28 02:00:22,442][87426] Updated weights for policy 1, policy_version 68410 (0.0009) -[2023-11-28 02:00:22,569][87424] Updated weights for policy 0, policy_version 68506 (0.0009) -[2023-11-28 02:00:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 35053568. Throughput: 0: 2741.1, 1: 2733.4. Samples: 35066000. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:23,445][86177] Avg episode reward: [(0, '-627.080'), (1, '-502.250')] -[2023-11-28 02:00:24,812][87424] Updated weights for policy 0, policy_version 68516 (0.0010) -[2023-11-28 02:00:25,074][87426] Updated weights for policy 1, policy_version 68420 (0.0010) -[2023-11-28 02:00:25,198][87424] Updated weights for policy 0, policy_version 68526 (0.0012) -[2023-11-28 02:00:25,452][87426] Updated weights for policy 1, policy_version 68430 (0.0009) -[2023-11-28 02:00:25,577][87424] Updated weights for policy 0, policy_version 68536 (0.0011) -[2023-11-28 02:00:25,841][87426] Updated weights for policy 1, policy_version 68440 (0.0008) -[2023-11-28 02:00:27,728][87426] Updated weights for policy 1, policy_version 68450 (0.0008) -[2023-11-28 02:00:28,087][87424] Updated weights for policy 0, policy_version 68546 (0.0010) -[2023-11-28 02:00:28,107][87426] Updated weights for policy 1, policy_version 68460 (0.0012) -[2023-11-28 02:00:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 35069952. Throughput: 0: 2742.5, 1: 2764.3. Samples: 35090868. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:28,445][86177] Avg episode reward: [(0, '-629.570'), (1, '-504.870')] -[2023-11-28 02:00:28,467][87424] Updated weights for policy 0, policy_version 68556 (0.0007) -[2023-11-28 02:00:28,487][87426] Updated weights for policy 1, policy_version 68470 (0.0012) -[2023-11-28 02:00:28,851][87424] Updated weights for policy 0, policy_version 68566 (0.0008) -[2023-11-28 02:00:28,862][87426] Updated weights for policy 1, policy_version 68480 (0.0011) -[2023-11-28 02:00:29,235][87424] Updated weights for policy 0, policy_version 68576 (0.0010) -[2023-11-28 02:00:30,940][87426] Updated weights for policy 1, policy_version 68490 (0.0009) -[2023-11-28 02:00:31,323][87426] Updated weights for policy 1, policy_version 68500 (0.0009) -[2023-11-28 02:00:31,325][87424] Updated weights for policy 0, policy_version 68586 (0.0011) -[2023-11-28 02:00:31,704][87426] Updated weights for policy 1, policy_version 68510 (0.0009) -[2023-11-28 02:00:31,715][87424] Updated weights for policy 0, policy_version 68596 (0.0010) -[2023-11-28 02:00:32,087][87424] Updated weights for policy 0, policy_version 68606 (0.0009) -[2023-11-28 02:00:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35102720. Throughput: 0: 2730.9, 1: 2767.4. Samples: 35115496. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:33,445][86177] Avg episode reward: [(0, '-596.740'), (1, '-503.650')] -[2023-11-28 02:00:33,869][87426] Updated weights for policy 1, policy_version 68520 (0.0011) -[2023-11-28 02:00:34,080][87424] Updated weights for policy 0, policy_version 68616 (0.0011) -[2023-11-28 02:00:34,242][87426] Updated weights for policy 1, policy_version 68530 (0.0011) -[2023-11-28 02:00:34,479][87424] Updated weights for policy 0, policy_version 68626 (0.0012) -[2023-11-28 02:00:34,633][87426] Updated weights for policy 1, policy_version 68540 (0.0011) -[2023-11-28 02:00:34,853][87424] Updated weights for policy 0, policy_version 68636 (0.0008) -[2023-11-28 02:00:36,580][87426] Updated weights for policy 1, policy_version 68550 (0.0010) -[2023-11-28 02:00:36,967][87426] Updated weights for policy 1, policy_version 68560 (0.0010) -[2023-11-28 02:00:37,271][87424] Updated weights for policy 0, policy_version 68646 (0.0010) -[2023-11-28 02:00:37,343][87426] Updated weights for policy 1, policy_version 68570 (0.0009) -[2023-11-28 02:00:37,656][87424] Updated weights for policy 0, policy_version 68656 (0.0011) -[2023-11-28 02:00:38,042][87424] Updated weights for policy 0, policy_version 68666 (0.0007) -[2023-11-28 02:00:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35135488. Throughput: 0: 2709.1, 1: 2794.8. Samples: 35148600. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:38,445][86177] Avg episode reward: [(0, '-565.620'), (1, '-494.420')] -[2023-11-28 02:00:39,503][87426] Updated weights for policy 1, policy_version 68580 (0.0010) -[2023-11-28 02:00:39,888][87426] Updated weights for policy 1, policy_version 68590 (0.0009) -[2023-11-28 02:00:40,264][87426] Updated weights for policy 1, policy_version 68600 (0.0010) -[2023-11-28 02:00:40,409][87424] Updated weights for policy 0, policy_version 68676 (0.0009) -[2023-11-28 02:00:40,780][87424] Updated weights for policy 0, policy_version 68686 (0.0010) -[2023-11-28 02:00:41,163][87424] Updated weights for policy 0, policy_version 68696 (0.0011) -[2023-11-28 02:00:42,703][87426] Updated weights for policy 1, policy_version 68610 (0.0010) -[2023-11-28 02:00:43,079][87426] Updated weights for policy 1, policy_version 68620 (0.0010) -[2023-11-28 02:00:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 35151872. Throughput: 0: 2692.6, 1: 2772.7. Samples: 35171728. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:43,445][86177] Avg episode reward: [(0, '-606.340'), (1, '-499.510')] -[2023-11-28 02:00:43,455][87426] Updated weights for policy 1, policy_version 68630 (0.0009) -[2023-11-28 02:00:43,769][87424] Updated weights for policy 0, policy_version 68706 (0.0011) -[2023-11-28 02:00:43,835][87426] Updated weights for policy 1, policy_version 68640 (0.0010) -[2023-11-28 02:00:44,160][87424] Updated weights for policy 0, policy_version 68716 (0.0012) -[2023-11-28 02:00:44,540][87424] Updated weights for policy 0, policy_version 68726 (0.0012) -[2023-11-28 02:00:44,923][87424] Updated weights for policy 0, policy_version 68736 (0.0011) -[2023-11-28 02:00:45,610][87426] Updated weights for policy 1, policy_version 68650 (0.0010) -[2023-11-28 02:00:45,991][87426] Updated weights for policy 1, policy_version 68660 (0.0009) -[2023-11-28 02:00:46,377][87426] Updated weights for policy 1, policy_version 68670 (0.0007) -[2023-11-28 02:00:46,852][87424] Updated weights for policy 0, policy_version 68746 (0.0012) -[2023-11-28 02:00:47,228][87424] Updated weights for policy 0, policy_version 68756 (0.0012) -[2023-11-28 02:00:47,600][87424] Updated weights for policy 0, policy_version 68766 (0.0012) -[2023-11-28 02:00:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35184640. Throughput: 0: 2677.5, 1: 2769.0. Samples: 35195872. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:48,446][86177] Avg episode reward: [(0, '-597.910'), (1, '-504.720')] -[2023-11-28 02:00:48,651][87426] Updated weights for policy 1, policy_version 68680 (0.0011) -[2023-11-28 02:00:49,041][87426] Updated weights for policy 1, policy_version 68690 (0.0012) -[2023-11-28 02:00:49,416][87426] Updated weights for policy 1, policy_version 68700 (0.0012) -[2023-11-28 02:00:49,754][87424] Updated weights for policy 0, policy_version 68776 (0.0012) -[2023-11-28 02:00:50,146][87424] Updated weights for policy 0, policy_version 68786 (0.0010) -[2023-11-28 02:00:50,527][87424] Updated weights for policy 0, policy_version 68796 (0.0010) -[2023-11-28 02:00:51,928][87426] Updated weights for policy 1, policy_version 68710 (0.0012) -[2023-11-28 02:00:52,304][87426] Updated weights for policy 1, policy_version 68720 (0.0012) -[2023-11-28 02:00:52,694][87426] Updated weights for policy 1, policy_version 68730 (0.0009) -[2023-11-28 02:00:52,969][87424] Updated weights for policy 0, policy_version 68806 (0.0012) -[2023-11-28 02:00:53,352][87424] Updated weights for policy 0, policy_version 68816 (0.0010) -[2023-11-28 02:00:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 35209216. Throughput: 0: 2663.2, 1: 2731.2. Samples: 35226960. Policy #0 lag: (min: 22.0, avg: 30.1, max: 54.0) -[2023-11-28 02:00:53,446][86177] Avg episode reward: [(0, '-596.580'), (1, '-509.240')] -[2023-11-28 02:00:53,732][87424] Updated weights for policy 0, policy_version 68826 (0.0012) -[2023-11-28 02:00:54,899][87426] Updated weights for policy 1, policy_version 68740 (0.0011) -[2023-11-28 02:00:55,281][87426] Updated weights for policy 1, policy_version 68750 (0.0010) -[2023-11-28 02:00:55,673][87426] Updated weights for policy 1, policy_version 68760 (0.0010) -[2023-11-28 02:00:55,810][87424] Updated weights for policy 0, policy_version 68836 (0.0012) -[2023-11-28 02:00:56,199][87424] Updated weights for policy 0, policy_version 68846 (0.0012) -[2023-11-28 02:00:56,577][87424] Updated weights for policy 0, policy_version 68856 (0.0012) -[2023-11-28 02:00:57,601][87426] Updated weights for policy 1, policy_version 68770 (0.0010) -[2023-11-28 02:00:57,982][87426] Updated weights for policy 1, policy_version 68780 (0.0012) -[2023-11-28 02:00:58,335][87424] Updated weights for policy 0, policy_version 68866 (0.0012) -[2023-11-28 02:00:58,361][87426] Updated weights for policy 1, policy_version 68790 (0.0011) -[2023-11-28 02:00:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35233792. Throughput: 0: 2674.5, 1: 2722.5. Samples: 35251936. Policy #0 lag: (min: 19.0, avg: 44.7, max: 63.0) -[2023-11-28 02:00:58,445][86177] Avg episode reward: [(0, '-617.740'), (1, '-522.050')] -[2023-11-28 02:00:58,729][87424] Updated weights for policy 0, policy_version 68876 (0.0011) -[2023-11-28 02:00:58,737][87426] Updated weights for policy 1, policy_version 68800 (0.0007) -[2023-11-28 02:00:59,112][87424] Updated weights for policy 0, policy_version 68886 (0.0012) -[2023-11-28 02:00:59,496][87424] Updated weights for policy 0, policy_version 68896 (0.0011) -[2023-11-28 02:01:01,202][87426] Updated weights for policy 1, policy_version 68810 (0.0011) -[2023-11-28 02:01:01,581][87426] Updated weights for policy 1, policy_version 68820 (0.0007) -[2023-11-28 02:01:01,942][87424] Updated weights for policy 0, policy_version 68906 (0.0010) -[2023-11-28 02:01:01,959][87426] Updated weights for policy 1, policy_version 68830 (0.0009) -[2023-11-28 02:01:02,323][87424] Updated weights for policy 0, policy_version 68916 (0.0012) -[2023-11-28 02:01:02,699][87424] Updated weights for policy 0, policy_version 68926 (0.0012) -[2023-11-28 02:01:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35266560. Throughput: 0: 2671.4, 1: 2728.3. Samples: 35276960. Policy #0 lag: (min: 19.0, avg: 44.7, max: 63.0) -[2023-11-28 02:01:03,445][86177] Avg episode reward: [(0, '-546.480'), (1, '-517.240')] -[2023-11-28 02:01:03,820][87426] Updated weights for policy 1, policy_version 68840 (0.0008) -[2023-11-28 02:01:04,198][87426] Updated weights for policy 1, policy_version 68850 (0.0010) -[2023-11-28 02:01:04,581][87426] Updated weights for policy 1, policy_version 68860 (0.0010) -[2023-11-28 02:01:04,622][87424] Updated weights for policy 0, policy_version 68936 (0.0012) -[2023-11-28 02:01:05,004][87424] Updated weights for policy 0, policy_version 68946 (0.0012) -[2023-11-28 02:01:05,385][87424] Updated weights for policy 0, policy_version 68956 (0.0012) -[2023-11-28 02:01:06,639][87426] Updated weights for policy 1, policy_version 68870 (0.0011) -[2023-11-28 02:01:07,021][87426] Updated weights for policy 1, policy_version 68880 (0.0011) -[2023-11-28 02:01:07,400][87426] Updated weights for policy 1, policy_version 68890 (0.0012) -[2023-11-28 02:01:07,477][87424] Updated weights for policy 0, policy_version 68966 (0.0012) -[2023-11-28 02:01:07,858][87424] Updated weights for policy 0, policy_version 68976 (0.0012) -[2023-11-28 02:01:08,242][87424] Updated weights for policy 0, policy_version 68986 (0.0011) -[2023-11-28 02:01:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 35291136. Throughput: 0: 2704.9, 1: 2748.2. Samples: 35311388. Policy #0 lag: (min: 19.0, avg: 44.7, max: 63.0) -[2023-11-28 02:01:08,445][86177] Avg episode reward: [(0, '-544.210'), (1, '-518.750')] -[2023-11-28 02:01:09,318][87426] Updated weights for policy 1, policy_version 68900 (0.0012) -[2023-11-28 02:01:09,704][87426] Updated weights for policy 1, policy_version 68910 (0.0012) -[2023-11-28 02:01:10,092][87426] Updated weights for policy 1, policy_version 68920 (0.0012) -[2023-11-28 02:01:10,115][87424] Updated weights for policy 0, policy_version 68996 (0.0011) -[2023-11-28 02:01:10,493][87424] Updated weights for policy 0, policy_version 69006 (0.0011) -[2023-11-28 02:01:10,882][87424] Updated weights for policy 0, policy_version 69016 (0.0012) -[2023-11-28 02:01:11,832][87426] Updated weights for policy 1, policy_version 68930 (0.0011) -[2023-11-28 02:01:12,213][87426] Updated weights for policy 1, policy_version 68940 (0.0012) -[2023-11-28 02:01:12,596][87426] Updated weights for policy 1, policy_version 68950 (0.0012) -[2023-11-28 02:01:12,968][87426] Updated weights for policy 1, policy_version 68960 (0.0012) -[2023-11-28 02:01:13,068][87424] Updated weights for policy 0, policy_version 69026 (0.0012) -[2023-11-28 02:01:13,440][87424] Updated weights for policy 0, policy_version 69036 (0.0012) -[2023-11-28 02:01:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 35323904. Throughput: 0: 2712.0, 1: 2753.3. Samples: 35336808. Policy #0 lag: (min: 19.0, avg: 44.7, max: 63.0) -[2023-11-28 02:01:13,445][86177] Avg episode reward: [(0, '-545.310'), (1, '-515.270')] -[2023-11-28 02:01:13,826][87424] Updated weights for policy 0, policy_version 69046 (0.0011) -[2023-11-28 02:01:14,216][87424] Updated weights for policy 0, policy_version 69056 (0.0011) -[2023-11-28 02:01:15,518][87426] Updated weights for policy 1, policy_version 68970 (0.0008) -[2023-11-28 02:01:15,883][87426] Updated weights for policy 1, policy_version 68980 (0.0008) -[2023-11-28 02:01:16,264][87426] Updated weights for policy 1, policy_version 68990 (0.0008) -[2023-11-28 02:01:16,647][87424] Updated weights for policy 0, policy_version 69066 (0.0011) -[2023-11-28 02:01:17,033][87424] Updated weights for policy 0, policy_version 69076 (0.0012) -[2023-11-28 02:01:17,421][87424] Updated weights for policy 0, policy_version 69086 (0.0012) -[2023-11-28 02:01:18,432][87426] Updated weights for policy 1, policy_version 69000 (0.0011) -[2023-11-28 02:01:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35348480. Throughput: 0: 2711.8, 1: 2745.8. Samples: 35361088. Policy #0 lag: (min: 19.0, avg: 44.7, max: 63.0) -[2023-11-28 02:01:18,445][86177] Avg episode reward: [(0, '-524.410'), (1, '-504.380')] -[2023-11-28 02:01:18,811][87426] Updated weights for policy 1, policy_version 69010 (0.0012) -[2023-11-28 02:01:19,199][87426] Updated weights for policy 1, policy_version 69020 (0.0011) -[2023-11-28 02:01:19,628][87424] Updated weights for policy 0, policy_version 69096 (0.0008) -[2023-11-28 02:01:20,008][87424] Updated weights for policy 0, policy_version 69106 (0.0010) -[2023-11-28 02:01:20,393][87424] Updated weights for policy 0, policy_version 69116 (0.0008) -[2023-11-28 02:01:21,671][87426] Updated weights for policy 1, policy_version 69030 (0.0010) -[2023-11-28 02:01:22,048][87426] Updated weights for policy 1, policy_version 69040 (0.0009) -[2023-11-28 02:01:22,433][87426] Updated weights for policy 1, policy_version 69050 (0.0011) -[2023-11-28 02:01:22,791][87424] Updated weights for policy 0, policy_version 69126 (0.0010) -[2023-11-28 02:01:23,177][87424] Updated weights for policy 0, policy_version 69136 (0.0012) -[2023-11-28 02:01:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 35373056. Throughput: 0: 2718.1, 1: 2701.0. Samples: 35392460. Policy #0 lag: (min: 19.0, avg: 44.7, max: 63.0) -[2023-11-28 02:01:23,445][86177] Avg episode reward: [(0, '-524.240'), (1, '-506.760')] -[2023-11-28 02:01:23,558][87424] Updated weights for policy 0, policy_version 69146 (0.0012) -[2023-11-28 02:01:24,679][87426] Updated weights for policy 1, policy_version 69060 (0.0012) -[2023-11-28 02:01:25,052][87426] Updated weights for policy 1, policy_version 69070 (0.0011) -[2023-11-28 02:01:25,230][87424] Updated weights for policy 0, policy_version 69156 (0.0012) -[2023-11-28 02:01:25,432][87426] Updated weights for policy 1, policy_version 69080 (0.0011) -[2023-11-28 02:01:25,625][87424] Updated weights for policy 0, policy_version 69166 (0.0011) -[2023-11-28 02:01:26,011][87424] Updated weights for policy 0, policy_version 69176 (0.0011) -[2023-11-28 02:01:27,626][87426] Updated weights for policy 1, policy_version 69090 (0.0009) -[2023-11-28 02:01:27,875][87424] Updated weights for policy 0, policy_version 69186 (0.0009) -[2023-11-28 02:01:28,007][87426] Updated weights for policy 1, policy_version 69100 (0.0007) -[2023-11-28 02:01:28,260][87424] Updated weights for policy 0, policy_version 69196 (0.0008) -[2023-11-28 02:01:28,372][87426] Updated weights for policy 1, policy_version 69110 (0.0009) -[2023-11-28 02:01:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35397632. Throughput: 0: 2730.6, 1: 2721.8. Samples: 35417084. Policy #0 lag: (min: 19.0, avg: 44.7, max: 63.0) -[2023-11-28 02:01:28,445][86177] Avg episode reward: [(0, '-528.310'), (1, '-540.670')] -[2023-11-28 02:01:28,640][87424] Updated weights for policy 0, policy_version 69206 (0.0009) -[2023-11-28 02:01:28,749][87426] Updated weights for policy 1, policy_version 69120 (0.0010) -[2023-11-28 02:01:29,024][87424] Updated weights for policy 0, policy_version 69216 (0.0011) -[2023-11-28 02:01:30,623][87426] Updated weights for policy 1, policy_version 69130 (0.0012) -[2023-11-28 02:01:30,993][87426] Updated weights for policy 1, policy_version 69140 (0.0009) -[2023-11-28 02:01:31,379][87426] Updated weights for policy 1, policy_version 69150 (0.0007) -[2023-11-28 02:01:31,471][87424] Updated weights for policy 0, policy_version 69226 (0.0007) -[2023-11-28 02:01:31,866][87424] Updated weights for policy 0, policy_version 69236 (0.0010) -[2023-11-28 02:01:32,251][87424] Updated weights for policy 0, policy_version 69246 (0.0011) -[2023-11-28 02:01:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 35430400. Throughput: 0: 2707.4, 1: 2746.1. Samples: 35441276. Policy #0 lag: (min: 19.0, avg: 44.7, max: 63.0) -[2023-11-28 02:01:33,445][86177] Avg episode reward: [(0, '-537.330'), (1, '-556.440')] -[2023-11-28 02:01:33,687][87426] Updated weights for policy 1, policy_version 69160 (0.0011) -[2023-11-28 02:01:34,074][87426] Updated weights for policy 1, policy_version 69170 (0.0012) -[2023-11-28 02:01:34,456][87426] Updated weights for policy 1, policy_version 69180 (0.0012) -[2023-11-28 02:01:34,825][87424] Updated weights for policy 0, policy_version 69256 (0.0010) -[2023-11-28 02:01:35,208][87424] Updated weights for policy 0, policy_version 69266 (0.0011) -[2023-11-28 02:01:35,582][87424] Updated weights for policy 0, policy_version 69276 (0.0007) -[2023-11-28 02:01:36,909][87426] Updated weights for policy 1, policy_version 69190 (0.0012) -[2023-11-28 02:01:37,286][87426] Updated weights for policy 1, policy_version 69200 (0.0012) -[2023-11-28 02:01:37,666][87426] Updated weights for policy 1, policy_version 69210 (0.0011) -[2023-11-28 02:01:37,990][87424] Updated weights for policy 0, policy_version 69286 (0.0010) -[2023-11-28 02:01:38,381][87424] Updated weights for policy 0, policy_version 69296 (0.0012) -[2023-11-28 02:01:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 35454976. Throughput: 0: 2726.2, 1: 2762.2. Samples: 35473940. Policy #0 lag: (min: 19.0, avg: 44.7, max: 63.0) -[2023-11-28 02:01:38,445][86177] Avg episode reward: [(0, '-534.740'), (1, '-576.930')] -[2023-11-28 02:01:38,766][87424] Updated weights for policy 0, policy_version 69306 (0.0010) -[2023-11-28 02:01:39,577][87426] Updated weights for policy 1, policy_version 69220 (0.0012) -[2023-11-28 02:01:39,965][87426] Updated weights for policy 1, policy_version 69230 (0.0012) -[2023-11-28 02:01:40,334][87426] Updated weights for policy 1, policy_version 69240 (0.0011) -[2023-11-28 02:01:40,925][87424] Updated weights for policy 0, policy_version 69316 (0.0011) -[2023-11-28 02:01:41,312][87424] Updated weights for policy 0, policy_version 69326 (0.0012) -[2023-11-28 02:01:41,693][87424] Updated weights for policy 0, policy_version 69336 (0.0012) -[2023-11-28 02:01:42,295][87426] Updated weights for policy 1, policy_version 69250 (0.0012) -[2023-11-28 02:01:42,672][87426] Updated weights for policy 1, policy_version 69260 (0.0012) -[2023-11-28 02:01:43,049][87426] Updated weights for policy 1, policy_version 69270 (0.0012) -[2023-11-28 02:01:43,421][87426] Updated weights for policy 1, policy_version 69280 (0.0012) -[2023-11-28 02:01:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 35487744. Throughput: 0: 2735.9, 1: 2754.0. Samples: 35498980. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 02:01:43,445][86177] Avg episode reward: [(0, '-550.920'), (1, '-599.180')] -[2023-11-28 02:01:43,710][87424] Updated weights for policy 0, policy_version 69346 (0.0012) -[2023-11-28 02:01:44,098][87424] Updated weights for policy 0, policy_version 69356 (0.0009) -[2023-11-28 02:01:44,474][87424] Updated weights for policy 0, policy_version 69366 (0.0008) -[2023-11-28 02:01:44,858][87424] Updated weights for policy 0, policy_version 69376 (0.0010) -[2023-11-28 02:01:45,675][87426] Updated weights for policy 1, policy_version 69290 (0.0008) -[2023-11-28 02:01:46,055][87426] Updated weights for policy 1, policy_version 69300 (0.0009) -[2023-11-28 02:01:46,430][87426] Updated weights for policy 1, policy_version 69310 (0.0012) -[2023-11-28 02:01:47,190][87424] Updated weights for policy 0, policy_version 69386 (0.0012) -[2023-11-28 02:01:47,560][87424] Updated weights for policy 0, policy_version 69396 (0.0012) -[2023-11-28 02:01:47,945][87424] Updated weights for policy 0, policy_version 69406 (0.0012) -[2023-11-28 02:01:48,340][87426] Updated weights for policy 1, policy_version 69320 (0.0011) -[2023-11-28 02:01:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 35512320. Throughput: 0: 2716.4, 1: 2767.8. Samples: 35523752. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 02:01:48,445][86177] Avg episode reward: [(0, '-574.000'), (1, '-628.340')] -[2023-11-28 02:01:48,716][87426] Updated weights for policy 1, policy_version 69330 (0.0011) -[2023-11-28 02:01:49,096][87426] Updated weights for policy 1, policy_version 69340 (0.0011) -[2023-11-28 02:01:49,748][87424] Updated weights for policy 0, policy_version 69416 (0.0010) -[2023-11-28 02:01:50,124][87424] Updated weights for policy 0, policy_version 69426 (0.0012) -[2023-11-28 02:01:50,506][87424] Updated weights for policy 0, policy_version 69436 (0.0012) -[2023-11-28 02:01:51,409][87426] Updated weights for policy 1, policy_version 69350 (0.0012) -[2023-11-28 02:01:51,780][87426] Updated weights for policy 1, policy_version 69360 (0.0012) -[2023-11-28 02:01:52,167][87426] Updated weights for policy 1, policy_version 69370 (0.0012) -[2023-11-28 02:01:52,836][87424] Updated weights for policy 0, policy_version 69446 (0.0012) -[2023-11-28 02:01:53,220][87424] Updated weights for policy 0, policy_version 69456 (0.0011) -[2023-11-28 02:01:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 35536896. Throughput: 0: 2700.2, 1: 2736.3. Samples: 35556028. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 02:01:53,445][86177] Avg episode reward: [(0, '-564.870'), (1, '-600.610')] -[2023-11-28 02:01:53,602][87424] Updated weights for policy 0, policy_version 69466 (0.0012) -[2023-11-28 02:01:54,663][87426] Updated weights for policy 1, policy_version 69380 (0.0011) -[2023-11-28 02:01:55,044][87426] Updated weights for policy 1, policy_version 69390 (0.0011) -[2023-11-28 02:01:55,436][87426] Updated weights for policy 1, policy_version 69400 (0.0011) -[2023-11-28 02:01:56,201][87424] Updated weights for policy 0, policy_version 69476 (0.0009) -[2023-11-28 02:01:56,608][87424] Updated weights for policy 0, policy_version 69486 (0.0007) -[2023-11-28 02:01:56,979][87424] Updated weights for policy 0, policy_version 69496 (0.0007) -[2023-11-28 02:01:57,433][87426] Updated weights for policy 1, policy_version 69410 (0.0010) -[2023-11-28 02:01:57,810][87426] Updated weights for policy 1, policy_version 69420 (0.0012) -[2023-11-28 02:01:58,193][87426] Updated weights for policy 1, policy_version 69430 (0.0012) -[2023-11-28 02:01:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35561472. Throughput: 0: 2671.0, 1: 2725.8. Samples: 35579664. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 02:01:58,445][86177] Avg episode reward: [(0, '-565.940'), (1, '-602.950')] -[2023-11-28 02:01:58,574][87426] Updated weights for policy 1, policy_version 69440 (0.0012) -[2023-11-28 02:01:59,294][87424] Updated weights for policy 0, policy_version 69506 (0.0007) -[2023-11-28 02:01:59,675][87424] Updated weights for policy 0, policy_version 69516 (0.0008) -[2023-11-28 02:02:00,057][87424] Updated weights for policy 0, policy_version 69526 (0.0009) -[2023-11-28 02:02:00,442][87424] Updated weights for policy 0, policy_version 69536 (0.0008) -[2023-11-28 02:02:01,033][87426] Updated weights for policy 1, policy_version 69450 (0.0010) -[2023-11-28 02:02:01,406][87426] Updated weights for policy 1, policy_version 69460 (0.0008) -[2023-11-28 02:02:01,789][87426] Updated weights for policy 1, policy_version 69470 (0.0010) -[2023-11-28 02:02:02,349][87424] Updated weights for policy 0, policy_version 69546 (0.0011) -[2023-11-28 02:02:02,728][87424] Updated weights for policy 0, policy_version 69556 (0.0011) -[2023-11-28 02:02:03,105][87424] Updated weights for policy 0, policy_version 69566 (0.0011) -[2023-11-28 02:02:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35594240. Throughput: 0: 2663.2, 1: 2706.2. Samples: 35602712. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 02:02:03,445][86177] Avg episode reward: [(0, '-550.470'), (1, '-601.930')] -[2023-11-28 02:02:03,629][87426] Updated weights for policy 1, policy_version 69480 (0.0012) -[2023-11-28 02:02:04,007][87426] Updated weights for policy 1, policy_version 69490 (0.0012) -[2023-11-28 02:02:04,381][87426] Updated weights for policy 1, policy_version 69500 (0.0012) -[2023-11-28 02:02:05,621][87424] Updated weights for policy 0, policy_version 69576 (0.0008) -[2023-11-28 02:02:06,019][87424] Updated weights for policy 0, policy_version 69586 (0.0008) -[2023-11-28 02:02:06,407][87424] Updated weights for policy 0, policy_version 69596 (0.0008) -[2023-11-28 02:02:06,874][87426] Updated weights for policy 1, policy_version 69510 (0.0012) -[2023-11-28 02:02:07,250][87426] Updated weights for policy 1, policy_version 69520 (0.0012) -[2023-11-28 02:02:07,633][87426] Updated weights for policy 1, policy_version 69530 (0.0012) -[2023-11-28 02:02:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 35618816. Throughput: 0: 2642.0, 1: 2744.0. Samples: 35634832. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 02:02:08,445][86177] Avg episode reward: [(0, '-553.120'), (1, '-629.900')] -[2023-11-28 02:02:08,754][87424] Updated weights for policy 0, policy_version 69606 (0.0008) -[2023-11-28 02:02:09,139][87424] Updated weights for policy 0, policy_version 69616 (0.0009) -[2023-11-28 02:02:09,341][87426] Updated weights for policy 1, policy_version 69540 (0.0012) -[2023-11-28 02:02:09,521][87424] Updated weights for policy 0, policy_version 69626 (0.0008) -[2023-11-28 02:02:09,720][87426] Updated weights for policy 1, policy_version 69550 (0.0011) -[2023-11-28 02:02:10,097][87426] Updated weights for policy 1, policy_version 69560 (0.0010) -[2023-11-28 02:02:11,646][87424] Updated weights for policy 0, policy_version 69636 (0.0012) -[2023-11-28 02:02:12,031][87424] Updated weights for policy 0, policy_version 69646 (0.0012) -[2023-11-28 02:02:12,253][87426] Updated weights for policy 1, policy_version 69570 (0.0011) -[2023-11-28 02:02:12,409][87424] Updated weights for policy 0, policy_version 69656 (0.0009) -[2023-11-28 02:02:12,631][87426] Updated weights for policy 1, policy_version 69580 (0.0009) -[2023-11-28 02:02:13,015][87426] Updated weights for policy 1, policy_version 69590 (0.0009) -[2023-11-28 02:02:13,386][87426] Updated weights for policy 1, policy_version 69600 (0.0011) -[2023-11-28 02:02:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 35651584. Throughput: 0: 2638.1, 1: 2765.2. Samples: 35660232. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 02:02:13,445][86177] Avg episode reward: [(0, '-529.800'), (1, '-636.420')] -[2023-11-28 02:02:14,896][87424] Updated weights for policy 0, policy_version 69666 (0.0008) -[2023-11-28 02:02:15,073][87426] Updated weights for policy 1, policy_version 69610 (0.0008) -[2023-11-28 02:02:15,282][87424] Updated weights for policy 0, policy_version 69676 (0.0007) -[2023-11-28 02:02:15,471][87426] Updated weights for policy 1, policy_version 69620 (0.0010) -[2023-11-28 02:02:15,667][87424] Updated weights for policy 0, policy_version 69686 (0.0010) -[2023-11-28 02:02:15,849][87426] Updated weights for policy 1, policy_version 69630 (0.0011) -[2023-11-28 02:02:16,047][87424] Updated weights for policy 0, policy_version 69696 (0.0010) -[2023-11-28 02:02:18,029][87426] Updated weights for policy 1, policy_version 69640 (0.0010) -[2023-11-28 02:02:18,407][87426] Updated weights for policy 1, policy_version 69650 (0.0008) -[2023-11-28 02:02:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 35667968. Throughput: 0: 2643.1, 1: 2753.3. Samples: 35684116. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 02:02:18,445][86177] Avg episode reward: [(0, '-529.610'), (1, '-662.650')] -[2023-11-28 02:02:18,579][87424] Updated weights for policy 0, policy_version 69706 (0.0007) -[2023-11-28 02:02:18,791][87426] Updated weights for policy 1, policy_version 69660 (0.0009) -[2023-11-28 02:02:18,938][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000069664_17833984.pth... -[2023-11-28 02:02:18,969][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000067104_17178624.pth -[2023-11-28 02:02:18,973][87424] Updated weights for policy 0, policy_version 69716 (0.0009) -[2023-11-28 02:02:19,362][87424] Updated weights for policy 0, policy_version 69726 (0.0012) -[2023-11-28 02:02:19,432][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000069728_17850368.pth... -[2023-11-28 02:02:19,465][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000067200_17203200.pth -[2023-11-28 02:02:20,772][87426] Updated weights for policy 1, policy_version 69670 (0.0012) -[2023-11-28 02:02:21,140][87426] Updated weights for policy 1, policy_version 69680 (0.0012) -[2023-11-28 02:02:21,517][87426] Updated weights for policy 1, policy_version 69690 (0.0011) -[2023-11-28 02:02:21,629][87424] Updated weights for policy 0, policy_version 69736 (0.0011) -[2023-11-28 02:02:22,016][87424] Updated weights for policy 0, policy_version 69746 (0.0010) -[2023-11-28 02:02:22,403][87424] Updated weights for policy 0, policy_version 69756 (0.0010) -[2023-11-28 02:02:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35700736. Throughput: 0: 2641.7, 1: 2746.0. Samples: 35716388. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 02:02:23,445][86177] Avg episode reward: [(0, '-527.650'), (1, '-679.610')] -[2023-11-28 02:02:24,108][87426] Updated weights for policy 1, policy_version 69700 (0.0009) -[2023-11-28 02:02:24,418][87424] Updated weights for policy 0, policy_version 69766 (0.0011) -[2023-11-28 02:02:24,491][87426] Updated weights for policy 1, policy_version 69710 (0.0007) -[2023-11-28 02:02:24,791][87424] Updated weights for policy 0, policy_version 69776 (0.0011) -[2023-11-28 02:02:24,880][87426] Updated weights for policy 1, policy_version 69720 (0.0010) -[2023-11-28 02:02:25,182][87424] Updated weights for policy 0, policy_version 69786 (0.0011) -[2023-11-28 02:02:26,793][87424] Updated weights for policy 0, policy_version 69796 (0.0012) -[2023-11-28 02:02:27,184][87424] Updated weights for policy 0, policy_version 69806 (0.0012) -[2023-11-28 02:02:27,426][87426] Updated weights for policy 1, policy_version 69730 (0.0009) -[2023-11-28 02:02:27,574][87424] Updated weights for policy 0, policy_version 69816 (0.0011) -[2023-11-28 02:02:27,804][87426] Updated weights for policy 1, policy_version 69740 (0.0011) -[2023-11-28 02:02:28,201][87426] Updated weights for policy 1, policy_version 69750 (0.0011) -[2023-11-28 02:02:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35725312. Throughput: 0: 2642.5, 1: 2732.1. Samples: 35740836. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 02:02:28,445][86177] Avg episode reward: [(0, '-539.070'), (1, '-663.840')] -[2023-11-28 02:02:28,575][87426] Updated weights for policy 1, policy_version 69760 (0.0012) -[2023-11-28 02:02:30,086][87424] Updated weights for policy 0, policy_version 69826 (0.0012) -[2023-11-28 02:02:30,472][87424] Updated weights for policy 0, policy_version 69836 (0.0008) -[2023-11-28 02:02:30,545][87426] Updated weights for policy 1, policy_version 69770 (0.0010) -[2023-11-28 02:02:30,849][87424] Updated weights for policy 0, policy_version 69846 (0.0011) -[2023-11-28 02:02:30,931][87426] Updated weights for policy 1, policy_version 69780 (0.0011) -[2023-11-28 02:02:31,234][87424] Updated weights for policy 0, policy_version 69856 (0.0011) -[2023-11-28 02:02:31,306][87426] Updated weights for policy 1, policy_version 69790 (0.0011) -[2023-11-28 02:02:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 35749888. Throughput: 0: 2651.6, 1: 2722.2. Samples: 35765572. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 02:02:33,445][86177] Avg episode reward: [(0, '-541.180'), (1, '-595.620')] -[2023-11-28 02:02:33,447][87424] Updated weights for policy 0, policy_version 69866 (0.0012) -[2023-11-28 02:02:33,618][87426] Updated weights for policy 1, policy_version 69800 (0.0011) -[2023-11-28 02:02:33,832][87424] Updated weights for policy 0, policy_version 69876 (0.0011) -[2023-11-28 02:02:34,000][87426] Updated weights for policy 1, policy_version 69810 (0.0012) -[2023-11-28 02:02:34,203][87424] Updated weights for policy 0, policy_version 69886 (0.0007) -[2023-11-28 02:02:34,377][87426] Updated weights for policy 1, policy_version 69820 (0.0012) -[2023-11-28 02:02:36,291][87424] Updated weights for policy 0, policy_version 69896 (0.0011) -[2023-11-28 02:02:36,683][87424] Updated weights for policy 0, policy_version 69906 (0.0012) -[2023-11-28 02:02:36,843][87426] Updated weights for policy 1, policy_version 69830 (0.0011) -[2023-11-28 02:02:37,054][87424] Updated weights for policy 0, policy_version 69916 (0.0010) -[2023-11-28 02:02:37,222][87426] Updated weights for policy 1, policy_version 69840 (0.0011) -[2023-11-28 02:02:37,605][87426] Updated weights for policy 1, policy_version 69850 (0.0012) -[2023-11-28 02:02:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 35782656. Throughput: 0: 2653.2, 1: 2729.9. Samples: 35798264. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 02:02:38,445][86177] Avg episode reward: [(0, '-543.030'), (1, '-583.580')] -[2023-11-28 02:02:39,023][87424] Updated weights for policy 0, policy_version 69926 (0.0011) -[2023-11-28 02:02:39,401][87424] Updated weights for policy 0, policy_version 69936 (0.0010) -[2023-11-28 02:02:39,801][87424] Updated weights for policy 0, policy_version 69946 (0.0010) -[2023-11-28 02:02:39,812][87426] Updated weights for policy 1, policy_version 69860 (0.0011) -[2023-11-28 02:02:40,197][87426] Updated weights for policy 1, policy_version 69870 (0.0011) -[2023-11-28 02:02:40,575][87426] Updated weights for policy 1, policy_version 69880 (0.0012) -[2023-11-28 02:02:42,004][87424] Updated weights for policy 0, policy_version 69956 (0.0011) -[2023-11-28 02:02:42,416][87424] Updated weights for policy 0, policy_version 69966 (0.0008) -[2023-11-28 02:02:42,790][87424] Updated weights for policy 0, policy_version 69976 (0.0011) -[2023-11-28 02:02:42,794][87426] Updated weights for policy 1, policy_version 69890 (0.0012) -[2023-11-28 02:02:43,167][87426] Updated weights for policy 1, policy_version 69900 (0.0008) -[2023-11-28 02:02:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 35807232. Throughput: 0: 2684.3, 1: 2703.1. Samples: 35822100. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 02:02:43,445][86177] Avg episode reward: [(0, '-544.440'), (1, '-566.540')] -[2023-11-28 02:02:43,546][87426] Updated weights for policy 1, policy_version 69910 (0.0008) -[2023-11-28 02:02:43,932][87426] Updated weights for policy 1, policy_version 69920 (0.0008) -[2023-11-28 02:02:45,041][87424] Updated weights for policy 0, policy_version 69986 (0.0011) -[2023-11-28 02:02:45,438][87424] Updated weights for policy 0, policy_version 69996 (0.0011) -[2023-11-28 02:02:45,743][87426] Updated weights for policy 1, policy_version 69930 (0.0011) -[2023-11-28 02:02:45,823][87424] Updated weights for policy 0, policy_version 70006 (0.0012) -[2023-11-28 02:02:46,122][87426] Updated weights for policy 1, policy_version 69940 (0.0012) -[2023-11-28 02:02:46,196][87424] Updated weights for policy 0, policy_version 70016 (0.0009) -[2023-11-28 02:02:46,493][87426] Updated weights for policy 1, policy_version 69950 (0.0010) -[2023-11-28 02:02:48,113][87424] Updated weights for policy 0, policy_version 70026 (0.0007) -[2023-11-28 02:02:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 35831808. Throughput: 0: 2716.2, 1: 2722.8. Samples: 35847464. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 02:02:48,445][86177] Avg episode reward: [(0, '-590.160'), (1, '-559.260')] -[2023-11-28 02:02:48,501][87424] Updated weights for policy 0, policy_version 70036 (0.0007) -[2023-11-28 02:02:48,876][87424] Updated weights for policy 0, policy_version 70046 (0.0009) -[2023-11-28 02:02:49,074][87426] Updated weights for policy 1, policy_version 69960 (0.0010) -[2023-11-28 02:02:49,445][87426] Updated weights for policy 1, policy_version 69970 (0.0008) -[2023-11-28 02:02:49,829][87426] Updated weights for policy 1, policy_version 69980 (0.0012) -[2023-11-28 02:02:50,945][87424] Updated weights for policy 0, policy_version 70056 (0.0008) -[2023-11-28 02:02:51,335][87424] Updated weights for policy 0, policy_version 70066 (0.0009) -[2023-11-28 02:02:51,715][87424] Updated weights for policy 0, policy_version 70076 (0.0011) -[2023-11-28 02:02:52,337][87426] Updated weights for policy 1, policy_version 69990 (0.0011) -[2023-11-28 02:02:52,716][87426] Updated weights for policy 1, policy_version 70000 (0.0009) -[2023-11-28 02:02:53,085][87426] Updated weights for policy 1, policy_version 70010 (0.0009) -[2023-11-28 02:02:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 35864576. Throughput: 0: 2764.6, 1: 2688.8. Samples: 35880236. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 02:02:53,445][86177] Avg episode reward: [(0, '-578.800'), (1, '-559.470')] -[2023-11-28 02:02:53,956][87424] Updated weights for policy 0, policy_version 70086 (0.0009) -[2023-11-28 02:02:54,335][87424] Updated weights for policy 0, policy_version 70096 (0.0010) -[2023-11-28 02:02:54,717][87424] Updated weights for policy 0, policy_version 70106 (0.0007) -[2023-11-28 02:02:55,683][87426] Updated weights for policy 1, policy_version 70020 (0.0010) -[2023-11-28 02:02:56,059][87426] Updated weights for policy 1, policy_version 70030 (0.0009) -[2023-11-28 02:02:56,451][87426] Updated weights for policy 1, policy_version 70040 (0.0007) -[2023-11-28 02:02:56,720][87424] Updated weights for policy 0, policy_version 70116 (0.0008) -[2023-11-28 02:02:57,105][87424] Updated weights for policy 0, policy_version 70126 (0.0008) -[2023-11-28 02:02:57,489][87424] Updated weights for policy 0, policy_version 70136 (0.0007) -[2023-11-28 02:02:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35889152. Throughput: 0: 2758.4, 1: 2632.0. Samples: 35902800. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 02:02:58,445][86177] Avg episode reward: [(0, '-600.220'), (1, '-581.110')] -[2023-11-28 02:02:58,910][87426] Updated weights for policy 1, policy_version 70050 (0.0008) -[2023-11-28 02:02:59,094][87424] Updated weights for policy 0, policy_version 70146 (0.0008) -[2023-11-28 02:02:59,286][87426] Updated weights for policy 1, policy_version 70060 (0.0009) -[2023-11-28 02:02:59,475][87424] Updated weights for policy 0, policy_version 70156 (0.0011) -[2023-11-28 02:02:59,667][87426] Updated weights for policy 1, policy_version 70070 (0.0010) -[2023-11-28 02:02:59,863][87424] Updated weights for policy 0, policy_version 70166 (0.0010) -[2023-11-28 02:03:00,049][87426] Updated weights for policy 1, policy_version 70080 (0.0010) -[2023-11-28 02:03:00,241][87424] Updated weights for policy 0, policy_version 70176 (0.0008) -[2023-11-28 02:03:02,110][87424] Updated weights for policy 0, policy_version 70186 (0.0012) -[2023-11-28 02:03:02,496][87424] Updated weights for policy 0, policy_version 70196 (0.0011) -[2023-11-28 02:03:02,525][87426] Updated weights for policy 1, policy_version 70090 (0.0009) -[2023-11-28 02:03:02,870][87424] Updated weights for policy 0, policy_version 70206 (0.0012) -[2023-11-28 02:03:02,896][87426] Updated weights for policy 1, policy_version 70100 (0.0010) -[2023-11-28 02:03:03,282][87426] Updated weights for policy 1, policy_version 70110 (0.0012) -[2023-11-28 02:03:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 35921920. Throughput: 0: 2798.4, 1: 2606.8. Samples: 35927352. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 02:03:03,445][86177] Avg episode reward: [(0, '-595.160'), (1, '-593.940')] -[2023-11-28 02:03:04,662][87424] Updated weights for policy 0, policy_version 70216 (0.0010) -[2023-11-28 02:03:05,051][87424] Updated weights for policy 0, policy_version 70226 (0.0010) -[2023-11-28 02:03:05,143][87426] Updated weights for policy 1, policy_version 70120 (0.0011) -[2023-11-28 02:03:05,440][87424] Updated weights for policy 0, policy_version 70236 (0.0010) -[2023-11-28 02:03:05,523][87426] Updated weights for policy 1, policy_version 70130 (0.0010) -[2023-11-28 02:03:05,909][87426] Updated weights for policy 1, policy_version 70140 (0.0008) -[2023-11-28 02:03:07,869][87424] Updated weights for policy 0, policy_version 70246 (0.0010) -[2023-11-28 02:03:08,252][87424] Updated weights for policy 0, policy_version 70256 (0.0011) -[2023-11-28 02:03:08,287][87426] Updated weights for policy 1, policy_version 70150 (0.0010) -[2023-11-28 02:03:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 35938304. Throughput: 0: 2821.1, 1: 2602.0. Samples: 35960424. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 02:03:08,445][86177] Avg episode reward: [(0, '-539.930'), (1, '-596.120')] -[2023-11-28 02:03:08,648][87424] Updated weights for policy 0, policy_version 70266 (0.0011) -[2023-11-28 02:03:08,678][87426] Updated weights for policy 1, policy_version 70160 (0.0012) -[2023-11-28 02:03:09,060][87426] Updated weights for policy 1, policy_version 70170 (0.0010) -[2023-11-28 02:03:10,598][87424] Updated weights for policy 0, policy_version 70276 (0.0009) -[2023-11-28 02:03:10,989][87424] Updated weights for policy 0, policy_version 70286 (0.0007) -[2023-11-28 02:03:11,382][87424] Updated weights for policy 0, policy_version 70296 (0.0011) -[2023-11-28 02:03:11,503][87426] Updated weights for policy 1, policy_version 70180 (0.0010) -[2023-11-28 02:03:11,886][87426] Updated weights for policy 1, policy_version 70190 (0.0011) -[2023-11-28 02:03:12,256][87426] Updated weights for policy 1, policy_version 70200 (0.0012) -[2023-11-28 02:03:13,362][87424] Updated weights for policy 0, policy_version 70306 (0.0009) -[2023-11-28 02:03:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 35971072. Throughput: 0: 2819.9, 1: 2591.9. Samples: 35984368. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 02:03:13,445][86177] Avg episode reward: [(0, '-555.450'), (1, '-610.230')] -[2023-11-28 02:03:13,748][87424] Updated weights for policy 0, policy_version 70316 (0.0012) -[2023-11-28 02:03:14,128][87424] Updated weights for policy 0, policy_version 70326 (0.0012) -[2023-11-28 02:03:14,507][87424] Updated weights for policy 0, policy_version 70336 (0.0011) -[2023-11-28 02:03:14,535][87426] Updated weights for policy 1, policy_version 70210 (0.0011) -[2023-11-28 02:03:14,907][87426] Updated weights for policy 1, policy_version 70220 (0.0007) -[2023-11-28 02:03:15,289][87426] Updated weights for policy 1, policy_version 70230 (0.0010) -[2023-11-28 02:03:15,664][87426] Updated weights for policy 1, policy_version 70240 (0.0008) -[2023-11-28 02:03:16,760][87424] Updated weights for policy 0, policy_version 70346 (0.0007) -[2023-11-28 02:03:17,150][87424] Updated weights for policy 0, policy_version 70356 (0.0007) -[2023-11-28 02:03:17,529][87424] Updated weights for policy 0, policy_version 70366 (0.0008) -[2023-11-28 02:03:18,179][87426] Updated weights for policy 1, policy_version 70250 (0.0012) -[2023-11-28 02:03:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 35995648. Throughput: 0: 2816.5, 1: 2579.2. Samples: 36008380. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 02:03:18,446][86177] Avg episode reward: [(0, '-560.270'), (1, '-605.150')] -[2023-11-28 02:03:18,560][87426] Updated weights for policy 1, policy_version 70260 (0.0012) -[2023-11-28 02:03:18,940][87426] Updated weights for policy 1, policy_version 70270 (0.0012) -[2023-11-28 02:03:19,900][87424] Updated weights for policy 0, policy_version 70376 (0.0011) -[2023-11-28 02:03:20,281][87424] Updated weights for policy 0, policy_version 70386 (0.0012) -[2023-11-28 02:03:20,664][87424] Updated weights for policy 0, policy_version 70396 (0.0013) -[2023-11-28 02:03:21,037][87426] Updated weights for policy 1, policy_version 70280 (0.0011) -[2023-11-28 02:03:21,424][87426] Updated weights for policy 1, policy_version 70290 (0.0012) -[2023-11-28 02:03:21,796][87426] Updated weights for policy 1, policy_version 70300 (0.0012) -[2023-11-28 02:03:22,906][87424] Updated weights for policy 0, policy_version 70406 (0.0011) -[2023-11-28 02:03:23,282][87424] Updated weights for policy 0, policy_version 70416 (0.0009) -[2023-11-28 02:03:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 36020224. Throughput: 0: 2802.7, 1: 2574.3. Samples: 36040228. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 02:03:23,445][86177] Avg episode reward: [(0, '-539.370'), (1, '-612.100')] -[2023-11-28 02:03:23,670][87424] Updated weights for policy 0, policy_version 70426 (0.0008) -[2023-11-28 02:03:23,969][87426] Updated weights for policy 1, policy_version 70310 (0.0010) -[2023-11-28 02:03:24,344][87426] Updated weights for policy 1, policy_version 70320 (0.0007) -[2023-11-28 02:03:24,724][87426] Updated weights for policy 1, policy_version 70330 (0.0010) -[2023-11-28 02:03:25,917][87424] Updated weights for policy 0, policy_version 70436 (0.0010) -[2023-11-28 02:03:26,296][87424] Updated weights for policy 0, policy_version 70446 (0.0011) -[2023-11-28 02:03:26,672][87424] Updated weights for policy 0, policy_version 70456 (0.0012) -[2023-11-28 02:03:26,798][87426] Updated weights for policy 1, policy_version 70340 (0.0010) -[2023-11-28 02:03:27,175][87426] Updated weights for policy 1, policy_version 70350 (0.0012) -[2023-11-28 02:03:27,569][87426] Updated weights for policy 1, policy_version 70360 (0.0008) -[2023-11-28 02:03:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 36052992. Throughput: 0: 2816.5, 1: 2590.0. Samples: 36065396. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 02:03:28,445][86177] Avg episode reward: [(0, '-580.130'), (1, '-601.170')] -[2023-11-28 02:03:28,933][87424] Updated weights for policy 0, policy_version 70466 (0.0009) -[2023-11-28 02:03:29,315][87424] Updated weights for policy 0, policy_version 70476 (0.0007) -[2023-11-28 02:03:29,509][87426] Updated weights for policy 1, policy_version 70370 (0.0008) -[2023-11-28 02:03:29,697][87424] Updated weights for policy 0, policy_version 70486 (0.0007) -[2023-11-28 02:03:29,886][87426] Updated weights for policy 1, policy_version 70380 (0.0008) -[2023-11-28 02:03:30,087][87424] Updated weights for policy 0, policy_version 70496 (0.0011) -[2023-11-28 02:03:30,268][87426] Updated weights for policy 1, policy_version 70390 (0.0011) -[2023-11-28 02:03:30,655][87426] Updated weights for policy 1, policy_version 70400 (0.0012) -[2023-11-28 02:03:31,955][87424] Updated weights for policy 0, policy_version 70506 (0.0012) -[2023-11-28 02:03:32,330][87424] Updated weights for policy 0, policy_version 70516 (0.0012) -[2023-11-28 02:03:32,716][87424] Updated weights for policy 0, policy_version 70526 (0.0011) -[2023-11-28 02:03:33,076][87426] Updated weights for policy 1, policy_version 70410 (0.0012) -[2023-11-28 02:03:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 36077568. Throughput: 0: 2809.1, 1: 2586.7. Samples: 36090276. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 02:03:33,445][86177] Avg episode reward: [(0, '-606.320'), (1, '-624.080')] -[2023-11-28 02:03:33,466][87426] Updated weights for policy 1, policy_version 70420 (0.0011) -[2023-11-28 02:03:33,854][87426] Updated weights for policy 1, policy_version 70430 (0.0012) -[2023-11-28 02:03:34,399][87424] Updated weights for policy 0, policy_version 70536 (0.0012) -[2023-11-28 02:03:34,778][87424] Updated weights for policy 0, policy_version 70546 (0.0010) -[2023-11-28 02:03:35,169][87424] Updated weights for policy 0, policy_version 70556 (0.0010) -[2023-11-28 02:03:35,761][87426] Updated weights for policy 1, policy_version 70440 (0.0012) -[2023-11-28 02:03:36,142][87426] Updated weights for policy 1, policy_version 70450 (0.0011) -[2023-11-28 02:03:36,527][87426] Updated weights for policy 1, policy_version 70460 (0.0012) -[2023-11-28 02:03:37,374][87424] Updated weights for policy 0, policy_version 70566 (0.0011) -[2023-11-28 02:03:37,751][87424] Updated weights for policy 0, policy_version 70576 (0.0009) -[2023-11-28 02:03:38,146][87424] Updated weights for policy 0, policy_version 70586 (0.0009) -[2023-11-28 02:03:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 36110336. Throughput: 0: 2788.6, 1: 2613.2. Samples: 36123316. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 02:03:38,445][86177] Avg episode reward: [(0, '-640.130'), (1, '-659.590')] -[2023-11-28 02:03:38,885][87426] Updated weights for policy 1, policy_version 70470 (0.0011) -[2023-11-28 02:03:39,255][87426] Updated weights for policy 1, policy_version 70480 (0.0012) -[2023-11-28 02:03:39,642][87426] Updated weights for policy 1, policy_version 70490 (0.0012) -[2023-11-28 02:03:40,083][87424] Updated weights for policy 0, policy_version 70596 (0.0009) -[2023-11-28 02:03:40,471][87424] Updated weights for policy 0, policy_version 70606 (0.0011) -[2023-11-28 02:03:40,860][87424] Updated weights for policy 0, policy_version 70616 (0.0011) -[2023-11-28 02:03:42,170][87426] Updated weights for policy 1, policy_version 70500 (0.0012) -[2023-11-28 02:03:42,540][87426] Updated weights for policy 1, policy_version 70510 (0.0011) -[2023-11-28 02:03:42,914][87426] Updated weights for policy 1, policy_version 70520 (0.0011) -[2023-11-28 02:03:42,981][87424] Updated weights for policy 0, policy_version 70626 (0.0012) -[2023-11-28 02:03:43,366][87424] Updated weights for policy 0, policy_version 70636 (0.0010) -[2023-11-28 02:03:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 36134912. Throughput: 0: 2778.8, 1: 2639.2. Samples: 36146612. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 02:03:43,445][86177] Avg episode reward: [(0, '-638.110'), (1, '-624.430')] -[2023-11-28 02:03:43,743][87424] Updated weights for policy 0, policy_version 70646 (0.0007) -[2023-11-28 02:03:44,128][87424] Updated weights for policy 0, policy_version 70656 (0.0007) -[2023-11-28 02:03:45,435][87426] Updated weights for policy 1, policy_version 70530 (0.0010) -[2023-11-28 02:03:45,816][87426] Updated weights for policy 1, policy_version 70540 (0.0007) -[2023-11-28 02:03:46,197][87426] Updated weights for policy 1, policy_version 70550 (0.0008) -[2023-11-28 02:03:46,576][87426] Updated weights for policy 1, policy_version 70560 (0.0010) -[2023-11-28 02:03:46,662][87424] Updated weights for policy 0, policy_version 70666 (0.0012) -[2023-11-28 02:03:47,050][87424] Updated weights for policy 0, policy_version 70676 (0.0012) -[2023-11-28 02:03:47,432][87424] Updated weights for policy 0, policy_version 70686 (0.0012) -[2023-11-28 02:03:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 36159488. Throughput: 0: 2780.3, 1: 2660.0. Samples: 36172164. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 02:03:48,445][86177] Avg episode reward: [(0, '-621.820'), (1, '-564.160')] -[2023-11-28 02:03:48,541][87426] Updated weights for policy 1, policy_version 70570 (0.0010) -[2023-11-28 02:03:48,933][87426] Updated weights for policy 1, policy_version 70580 (0.0009) -[2023-11-28 02:03:49,318][87426] Updated weights for policy 1, policy_version 70590 (0.0011) -[2023-11-28 02:03:49,479][87424] Updated weights for policy 0, policy_version 70696 (0.0010) -[2023-11-28 02:03:49,871][87424] Updated weights for policy 0, policy_version 70706 (0.0007) -[2023-11-28 02:03:50,241][87424] Updated weights for policy 0, policy_version 70716 (0.0008) -[2023-11-28 02:03:51,677][87426] Updated weights for policy 1, policy_version 70600 (0.0009) -[2023-11-28 02:03:52,065][87426] Updated weights for policy 1, policy_version 70610 (0.0011) -[2023-11-28 02:03:52,445][87426] Updated weights for policy 1, policy_version 70620 (0.0010) -[2023-11-28 02:03:52,820][87424] Updated weights for policy 0, policy_version 70726 (0.0011) -[2023-11-28 02:03:53,208][87424] Updated weights for policy 0, policy_version 70736 (0.0008) -[2023-11-28 02:03:53,445][86177] Fps is (10 sec: 4914.9, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 36184064. Throughput: 0: 2754.1, 1: 2661.9. Samples: 36204148. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 02:03:53,446][86177] Avg episode reward: [(0, '-669.110'), (1, '-548.040')] -[2023-11-28 02:03:53,602][87424] Updated weights for policy 0, policy_version 70746 (0.0011) -[2023-11-28 02:03:54,782][87426] Updated weights for policy 1, policy_version 70630 (0.0010) -[2023-11-28 02:03:55,162][87426] Updated weights for policy 1, policy_version 70640 (0.0011) -[2023-11-28 02:03:55,379][87424] Updated weights for policy 0, policy_version 70756 (0.0011) -[2023-11-28 02:03:55,539][87426] Updated weights for policy 1, policy_version 70650 (0.0011) -[2023-11-28 02:03:55,760][87424] Updated weights for policy 0, policy_version 70766 (0.0011) -[2023-11-28 02:03:56,136][87424] Updated weights for policy 0, policy_version 70776 (0.0009) -[2023-11-28 02:03:57,402][87426] Updated weights for policy 1, policy_version 70660 (0.0011) -[2023-11-28 02:03:57,788][87426] Updated weights for policy 1, policy_version 70670 (0.0011) -[2023-11-28 02:03:58,174][87426] Updated weights for policy 1, policy_version 70680 (0.0011) -[2023-11-28 02:03:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 36208640. Throughput: 0: 2749.1, 1: 2695.3. Samples: 36229364. Policy #0 lag: (min: 31.0, avg: 48.1, max: 63.0) -[2023-11-28 02:03:58,446][86177] Avg episode reward: [(0, '-688.830'), (1, '-507.790')] -[2023-11-28 02:03:58,625][87424] Updated weights for policy 0, policy_version 70786 (0.0011) -[2023-11-28 02:03:59,012][87424] Updated weights for policy 0, policy_version 70796 (0.0011) -[2023-11-28 02:03:59,395][87424] Updated weights for policy 0, policy_version 70806 (0.0008) -[2023-11-28 02:03:59,780][87424] Updated weights for policy 0, policy_version 70816 (0.0011) -[2023-11-28 02:04:00,158][87426] Updated weights for policy 1, policy_version 70690 (0.0011) -[2023-11-28 02:04:00,535][87426] Updated weights for policy 1, policy_version 70700 (0.0012) -[2023-11-28 02:04:00,921][87426] Updated weights for policy 1, policy_version 70710 (0.0012) -[2023-11-28 02:04:01,302][87426] Updated weights for policy 1, policy_version 70720 (0.0012) -[2023-11-28 02:04:01,704][87424] Updated weights for policy 0, policy_version 70826 (0.0011) -[2023-11-28 02:04:02,086][87424] Updated weights for policy 0, policy_version 70836 (0.0010) -[2023-11-28 02:04:02,469][87424] Updated weights for policy 0, policy_version 70846 (0.0012) -[2023-11-28 02:04:03,128][87426] Updated weights for policy 1, policy_version 70730 (0.0008) -[2023-11-28 02:04:03,445][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 36241408. Throughput: 0: 2750.2, 1: 2706.6. Samples: 36253936. Policy #0 lag: (min: 31.0, avg: 48.1, max: 63.0) -[2023-11-28 02:04:03,446][86177] Avg episode reward: [(0, '-647.290'), (1, '-509.830')] -[2023-11-28 02:04:03,505][87426] Updated weights for policy 1, policy_version 70740 (0.0008) -[2023-11-28 02:04:03,891][87426] Updated weights for policy 1, policy_version 70750 (0.0007) -[2023-11-28 02:04:04,563][87424] Updated weights for policy 0, policy_version 70856 (0.0011) -[2023-11-28 02:04:04,937][87424] Updated weights for policy 0, policy_version 70866 (0.0012) -[2023-11-28 02:04:05,326][87424] Updated weights for policy 0, policy_version 70876 (0.0012) -[2023-11-28 02:04:06,074][87426] Updated weights for policy 1, policy_version 70760 (0.0011) -[2023-11-28 02:04:06,458][87426] Updated weights for policy 1, policy_version 70770 (0.0012) -[2023-11-28 02:04:06,847][87426] Updated weights for policy 1, policy_version 70780 (0.0009) -[2023-11-28 02:04:07,635][87424] Updated weights for policy 0, policy_version 70886 (0.0011) -[2023-11-28 02:04:08,015][87424] Updated weights for policy 0, policy_version 70896 (0.0012) -[2023-11-28 02:04:08,402][87424] Updated weights for policy 0, policy_version 70906 (0.0011) -[2023-11-28 02:04:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 36265984. Throughput: 0: 2755.1, 1: 2715.8. Samples: 36286420. Policy #0 lag: (min: 31.0, avg: 48.1, max: 63.0) -[2023-11-28 02:04:08,445][86177] Avg episode reward: [(0, '-651.110'), (1, '-517.600')] -[2023-11-28 02:04:09,310][87426] Updated weights for policy 1, policy_version 70790 (0.0010) -[2023-11-28 02:04:09,688][87426] Updated weights for policy 1, policy_version 70800 (0.0011) -[2023-11-28 02:04:10,069][87426] Updated weights for policy 1, policy_version 70810 (0.0012) -[2023-11-28 02:04:10,370][87424] Updated weights for policy 0, policy_version 70916 (0.0011) -[2023-11-28 02:04:10,753][87424] Updated weights for policy 0, policy_version 70926 (0.0011) -[2023-11-28 02:04:11,139][87424] Updated weights for policy 0, policy_version 70936 (0.0012) -[2023-11-28 02:04:12,513][87426] Updated weights for policy 1, policy_version 70820 (0.0012) -[2023-11-28 02:04:12,899][87426] Updated weights for policy 1, policy_version 70830 (0.0012) -[2023-11-28 02:04:13,273][87426] Updated weights for policy 1, policy_version 70840 (0.0012) -[2023-11-28 02:04:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 36290560. Throughput: 0: 2718.8, 1: 2710.8. Samples: 36309728. Policy #0 lag: (min: 31.0, avg: 48.1, max: 63.0) -[2023-11-28 02:04:13,445][86177] Avg episode reward: [(0, '-638.000'), (1, '-520.420')] -[2023-11-28 02:04:13,739][87424] Updated weights for policy 0, policy_version 70946 (0.0009) -[2023-11-28 02:04:14,128][87424] Updated weights for policy 0, policy_version 70956 (0.0012) -[2023-11-28 02:04:14,513][87424] Updated weights for policy 0, policy_version 70966 (0.0012) -[2023-11-28 02:04:14,894][87424] Updated weights for policy 0, policy_version 70976 (0.0012) -[2023-11-28 02:04:15,242][87426] Updated weights for policy 1, policy_version 70850 (0.0012) -[2023-11-28 02:04:15,627][87426] Updated weights for policy 1, policy_version 70860 (0.0012) -[2023-11-28 02:04:16,003][87426] Updated weights for policy 1, policy_version 70870 (0.0010) -[2023-11-28 02:04:16,379][87426] Updated weights for policy 1, policy_version 70880 (0.0008) -[2023-11-28 02:04:16,959][87424] Updated weights for policy 0, policy_version 70986 (0.0008) -[2023-11-28 02:04:17,343][87424] Updated weights for policy 0, policy_version 70996 (0.0007) -[2023-11-28 02:04:17,730][87424] Updated weights for policy 0, policy_version 71006 (0.0007) -[2023-11-28 02:04:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 36323328. Throughput: 0: 2700.6, 1: 2722.9. Samples: 36334336. Policy #0 lag: (min: 31.0, avg: 48.1, max: 63.0) -[2023-11-28 02:04:18,445][86177] Avg episode reward: [(0, '-594.040'), (1, '-519.580')] -[2023-11-28 02:04:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000071008_18178048.pth... -[2023-11-28 02:04:18,455][87426] Updated weights for policy 1, policy_version 70890 (0.0010) -[2023-11-28 02:04:18,488][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000068448_17522688.pth -[2023-11-28 02:04:18,845][87426] Updated weights for policy 1, policy_version 70900 (0.0008) -[2023-11-28 02:04:19,219][87426] Updated weights for policy 1, policy_version 70910 (0.0011) -[2023-11-28 02:04:19,286][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000070912_18153472.pth... -[2023-11-28 02:04:19,325][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000068384_17506304.pth -[2023-11-28 02:04:19,833][87424] Updated weights for policy 0, policy_version 71016 (0.0011) -[2023-11-28 02:04:20,208][87424] Updated weights for policy 0, policy_version 71026 (0.0012) -[2023-11-28 02:04:20,582][87424] Updated weights for policy 0, policy_version 71036 (0.0010) -[2023-11-28 02:04:21,678][87426] Updated weights for policy 1, policy_version 70920 (0.0012) -[2023-11-28 02:04:22,052][87426] Updated weights for policy 1, policy_version 70930 (0.0012) -[2023-11-28 02:04:22,427][87426] Updated weights for policy 1, policy_version 70940 (0.0011) -[2023-11-28 02:04:22,610][87424] Updated weights for policy 0, policy_version 71046 (0.0008) -[2023-11-28 02:04:22,992][87424] Updated weights for policy 0, policy_version 71056 (0.0008) -[2023-11-28 02:04:23,382][87424] Updated weights for policy 0, policy_version 71066 (0.0010) -[2023-11-28 02:04:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 36347904. Throughput: 0: 2702.0, 1: 2700.4. Samples: 36366428. Policy #0 lag: (min: 31.0, avg: 48.1, max: 63.0) -[2023-11-28 02:04:23,445][86177] Avg episode reward: [(0, '-647.100'), (1, '-516.220')] -[2023-11-28 02:04:24,333][87426] Updated weights for policy 1, policy_version 70950 (0.0010) -[2023-11-28 02:04:24,705][87426] Updated weights for policy 1, policy_version 70960 (0.0012) -[2023-11-28 02:04:25,094][87426] Updated weights for policy 1, policy_version 70970 (0.0012) -[2023-11-28 02:04:25,912][87424] Updated weights for policy 0, policy_version 71076 (0.0008) -[2023-11-28 02:04:26,300][87424] Updated weights for policy 0, policy_version 71086 (0.0007) -[2023-11-28 02:04:26,686][87424] Updated weights for policy 0, policy_version 71096 (0.0009) -[2023-11-28 02:04:27,331][87426] Updated weights for policy 1, policy_version 70980 (0.0011) -[2023-11-28 02:04:27,714][87426] Updated weights for policy 1, policy_version 70990 (0.0007) -[2023-11-28 02:04:28,096][87426] Updated weights for policy 1, policy_version 71000 (0.0007) -[2023-11-28 02:04:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 36380672. Throughput: 0: 2711.6, 1: 2732.7. Samples: 36391608. Policy #0 lag: (min: 31.0, avg: 48.1, max: 63.0) -[2023-11-28 02:04:28,445][86177] Avg episode reward: [(0, '-680.570'), (1, '-523.290')] -[2023-11-28 02:04:28,983][87424] Updated weights for policy 0, policy_version 71106 (0.0010) -[2023-11-28 02:04:29,373][87424] Updated weights for policy 0, policy_version 71116 (0.0010) -[2023-11-28 02:04:29,750][87424] Updated weights for policy 0, policy_version 71126 (0.0012) -[2023-11-28 02:04:30,130][87424] Updated weights for policy 0, policy_version 71136 (0.0012) -[2023-11-28 02:04:30,559][87426] Updated weights for policy 1, policy_version 71010 (0.0008) -[2023-11-28 02:04:30,948][87426] Updated weights for policy 1, policy_version 71020 (0.0011) -[2023-11-28 02:04:31,326][87426] Updated weights for policy 1, policy_version 71030 (0.0012) -[2023-11-28 02:04:31,699][87426] Updated weights for policy 1, policy_version 71040 (0.0011) -[2023-11-28 02:04:32,101][87424] Updated weights for policy 0, policy_version 71146 (0.0010) -[2023-11-28 02:04:32,491][87424] Updated weights for policy 0, policy_version 71156 (0.0011) -[2023-11-28 02:04:32,871][87424] Updated weights for policy 0, policy_version 71166 (0.0012) -[2023-11-28 02:04:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 36405248. Throughput: 0: 2694.4, 1: 2716.1. Samples: 36415636. Policy #0 lag: (min: 31.0, avg: 48.1, max: 63.0) -[2023-11-28 02:04:33,446][86177] Avg episode reward: [(0, '-681.730'), (1, '-530.760')] -[2023-11-28 02:04:34,105][87426] Updated weights for policy 1, policy_version 71050 (0.0012) -[2023-11-28 02:04:34,487][87426] Updated weights for policy 1, policy_version 71060 (0.0011) -[2023-11-28 02:04:34,791][87424] Updated weights for policy 0, policy_version 71176 (0.0011) -[2023-11-28 02:04:34,875][87426] Updated weights for policy 1, policy_version 71070 (0.0011) -[2023-11-28 02:04:35,172][87424] Updated weights for policy 0, policy_version 71186 (0.0011) -[2023-11-28 02:04:35,565][87424] Updated weights for policy 0, policy_version 71196 (0.0012) -[2023-11-28 02:04:36,653][87426] Updated weights for policy 1, policy_version 71080 (0.0011) -[2023-11-28 02:04:37,039][87426] Updated weights for policy 1, policy_version 71090 (0.0011) -[2023-11-28 02:04:37,415][87426] Updated weights for policy 1, policy_version 71100 (0.0010) -[2023-11-28 02:04:37,930][87424] Updated weights for policy 0, policy_version 71206 (0.0011) -[2023-11-28 02:04:38,318][87424] Updated weights for policy 0, policy_version 71216 (0.0012) -[2023-11-28 02:04:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 36429824. Throughput: 0: 2704.5, 1: 2725.4. Samples: 36448488. Policy #0 lag: (min: 31.0, avg: 48.1, max: 63.0) -[2023-11-28 02:04:38,445][86177] Avg episode reward: [(0, '-623.720'), (1, '-557.020')] -[2023-11-28 02:04:38,692][87424] Updated weights for policy 0, policy_version 71226 (0.0012) -[2023-11-28 02:04:39,428][87426] Updated weights for policy 1, policy_version 71110 (0.0009) -[2023-11-28 02:04:39,813][87426] Updated weights for policy 1, policy_version 71120 (0.0011) -[2023-11-28 02:04:40,190][87426] Updated weights for policy 1, policy_version 71130 (0.0011) -[2023-11-28 02:04:40,890][87424] Updated weights for policy 0, policy_version 71236 (0.0012) -[2023-11-28 02:04:41,277][87424] Updated weights for policy 0, policy_version 71246 (0.0011) -[2023-11-28 02:04:41,675][87424] Updated weights for policy 0, policy_version 71256 (0.0010) -[2023-11-28 02:04:42,687][87426] Updated weights for policy 1, policy_version 71140 (0.0011) -[2023-11-28 02:04:43,064][87426] Updated weights for policy 1, policy_version 71150 (0.0011) -[2023-11-28 02:04:43,443][87426] Updated weights for policy 1, policy_version 71160 (0.0012) -[2023-11-28 02:04:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 36454400. Throughput: 0: 2702.3, 1: 2694.5. Samples: 36472220. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 02:04:43,445][86177] Avg episode reward: [(0, '-615.090'), (1, '-558.720')] -[2023-11-28 02:04:44,211][87424] Updated weights for policy 0, policy_version 71266 (0.0011) -[2023-11-28 02:04:44,596][87424] Updated weights for policy 0, policy_version 71276 (0.0008) -[2023-11-28 02:04:44,974][87424] Updated weights for policy 0, policy_version 71286 (0.0008) -[2023-11-28 02:04:45,172][87426] Updated weights for policy 1, policy_version 71170 (0.0012) -[2023-11-28 02:04:45,358][87424] Updated weights for policy 0, policy_version 71296 (0.0008) -[2023-11-28 02:04:45,554][87426] Updated weights for policy 1, policy_version 71180 (0.0011) -[2023-11-28 02:04:45,930][87426] Updated weights for policy 1, policy_version 71190 (0.0009) -[2023-11-28 02:04:46,314][87426] Updated weights for policy 1, policy_version 71200 (0.0007) -[2023-11-28 02:04:47,344][87424] Updated weights for policy 0, policy_version 71306 (0.0011) -[2023-11-28 02:04:47,726][87424] Updated weights for policy 0, policy_version 71316 (0.0011) -[2023-11-28 02:04:48,114][87424] Updated weights for policy 0, policy_version 71326 (0.0012) -[2023-11-28 02:04:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 36487168. Throughput: 0: 2701.8, 1: 2710.0. Samples: 36497464. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 02:04:48,445][86177] Avg episode reward: [(0, '-618.060'), (1, '-540.140')] -[2023-11-28 02:04:48,644][87426] Updated weights for policy 1, policy_version 71210 (0.0012) -[2023-11-28 02:04:49,023][87426] Updated weights for policy 1, policy_version 71220 (0.0012) -[2023-11-28 02:04:49,400][87426] Updated weights for policy 1, policy_version 71230 (0.0011) -[2023-11-28 02:04:49,756][87424] Updated weights for policy 0, policy_version 71336 (0.0012) -[2023-11-28 02:04:50,135][87424] Updated weights for policy 0, policy_version 71346 (0.0009) -[2023-11-28 02:04:50,518][87424] Updated weights for policy 0, policy_version 71356 (0.0009) -[2023-11-28 02:04:51,809][87426] Updated weights for policy 1, policy_version 71240 (0.0010) -[2023-11-28 02:04:52,187][87426] Updated weights for policy 1, policy_version 71250 (0.0011) -[2023-11-28 02:04:52,562][87426] Updated weights for policy 1, policy_version 71260 (0.0011) -[2023-11-28 02:04:52,585][87424] Updated weights for policy 0, policy_version 71366 (0.0010) -[2023-11-28 02:04:52,977][87424] Updated weights for policy 0, policy_version 71376 (0.0011) -[2023-11-28 02:04:53,357][87424] Updated weights for policy 0, policy_version 71386 (0.0011) -[2023-11-28 02:04:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 36511744. Throughput: 0: 2717.4, 1: 2691.0. Samples: 36529800. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 02:04:53,445][86177] Avg episode reward: [(0, '-607.910'), (1, '-527.500')] -[2023-11-28 02:04:54,785][87426] Updated weights for policy 1, policy_version 71270 (0.0009) -[2023-11-28 02:04:55,169][87426] Updated weights for policy 1, policy_version 71280 (0.0008) -[2023-11-28 02:04:55,415][87424] Updated weights for policy 0, policy_version 71396 (0.0011) -[2023-11-28 02:04:55,558][87426] Updated weights for policy 1, policy_version 71290 (0.0010) -[2023-11-28 02:04:55,800][87424] Updated weights for policy 0, policy_version 71406 (0.0009) -[2023-11-28 02:04:56,184][87424] Updated weights for policy 0, policy_version 71416 (0.0008) -[2023-11-28 02:04:57,376][87426] Updated weights for policy 1, policy_version 71300 (0.0011) -[2023-11-28 02:04:57,762][87426] Updated weights for policy 1, policy_version 71310 (0.0012) -[2023-11-28 02:04:58,139][87426] Updated weights for policy 1, policy_version 71320 (0.0011) -[2023-11-28 02:04:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 36544512. Throughput: 0: 2747.2, 1: 2717.7. Samples: 36555648. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 02:04:58,445][86177] Avg episode reward: [(0, '-609.190'), (1, '-535.880')] -[2023-11-28 02:04:58,664][87424] Updated weights for policy 0, policy_version 71426 (0.0007) -[2023-11-28 02:04:59,044][87424] Updated weights for policy 0, policy_version 71436 (0.0008) -[2023-11-28 02:04:59,431][87424] Updated weights for policy 0, policy_version 71446 (0.0008) -[2023-11-28 02:04:59,811][87424] Updated weights for policy 0, policy_version 71456 (0.0009) -[2023-11-28 02:05:00,423][87426] Updated weights for policy 1, policy_version 71330 (0.0012) -[2023-11-28 02:05:00,801][87426] Updated weights for policy 1, policy_version 71340 (0.0007) -[2023-11-28 02:05:01,183][87426] Updated weights for policy 1, policy_version 71350 (0.0007) -[2023-11-28 02:05:01,567][87426] Updated weights for policy 1, policy_version 71360 (0.0008) -[2023-11-28 02:05:01,794][87424] Updated weights for policy 0, policy_version 71466 (0.0010) -[2023-11-28 02:05:02,166][87424] Updated weights for policy 0, policy_version 71476 (0.0011) -[2023-11-28 02:05:02,556][87424] Updated weights for policy 0, policy_version 71486 (0.0008) -[2023-11-28 02:05:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 36569088. Throughput: 0: 2766.0, 1: 2700.0. Samples: 36580304. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 02:05:03,445][86177] Avg episode reward: [(0, '-636.350'), (1, '-533.040')] -[2023-11-28 02:05:03,990][87426] Updated weights for policy 1, policy_version 71370 (0.0011) -[2023-11-28 02:05:04,377][87426] Updated weights for policy 1, policy_version 71380 (0.0008) -[2023-11-28 02:05:04,748][87426] Updated weights for policy 1, policy_version 71390 (0.0009) -[2023-11-28 02:05:04,854][87424] Updated weights for policy 0, policy_version 71496 (0.0010) -[2023-11-28 02:05:05,237][87424] Updated weights for policy 0, policy_version 71506 (0.0011) -[2023-11-28 02:05:05,629][87424] Updated weights for policy 0, policy_version 71516 (0.0011) -[2023-11-28 02:05:06,600][87426] Updated weights for policy 1, policy_version 71400 (0.0008) -[2023-11-28 02:05:06,971][87426] Updated weights for policy 1, policy_version 71410 (0.0011) -[2023-11-28 02:05:07,347][87426] Updated weights for policy 1, policy_version 71420 (0.0011) -[2023-11-28 02:05:07,801][87424] Updated weights for policy 0, policy_version 71526 (0.0012) -[2023-11-28 02:05:08,169][87424] Updated weights for policy 0, policy_version 71536 (0.0012) -[2023-11-28 02:05:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 36593664. Throughput: 0: 2779.9, 1: 2723.6. Samples: 36614088. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 02:05:08,445][86177] Avg episode reward: [(0, '-668.820'), (1, '-551.410')] -[2023-11-28 02:05:08,549][87424] Updated weights for policy 0, policy_version 71546 (0.0012) -[2023-11-28 02:05:09,717][87426] Updated weights for policy 1, policy_version 71430 (0.0010) -[2023-11-28 02:05:10,097][87426] Updated weights for policy 1, policy_version 71440 (0.0011) -[2023-11-28 02:05:10,484][87426] Updated weights for policy 1, policy_version 71450 (0.0012) -[2023-11-28 02:05:10,602][87424] Updated weights for policy 0, policy_version 71556 (0.0012) -[2023-11-28 02:05:10,989][87424] Updated weights for policy 0, policy_version 71566 (0.0012) -[2023-11-28 02:05:11,369][87424] Updated weights for policy 0, policy_version 71576 (0.0009) -[2023-11-28 02:05:13,068][87426] Updated weights for policy 1, policy_version 71460 (0.0010) -[2023-11-28 02:05:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 36618240. Throughput: 0: 2781.7, 1: 2693.2. Samples: 36637976. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 02:05:13,445][86177] Avg episode reward: [(0, '-672.200'), (1, '-537.600')] -[2023-11-28 02:05:13,447][87426] Updated weights for policy 1, policy_version 71470 (0.0011) -[2023-11-28 02:05:13,535][87424] Updated weights for policy 0, policy_version 71586 (0.0009) -[2023-11-28 02:05:13,821][87426] Updated weights for policy 1, policy_version 71480 (0.0010) -[2023-11-28 02:05:13,921][87424] Updated weights for policy 0, policy_version 71596 (0.0008) -[2023-11-28 02:05:14,300][87424] Updated weights for policy 0, policy_version 71606 (0.0012) -[2023-11-28 02:05:14,694][87424] Updated weights for policy 0, policy_version 71616 (0.0012) -[2023-11-28 02:05:15,921][87426] Updated weights for policy 1, policy_version 71490 (0.0012) -[2023-11-28 02:05:16,300][87426] Updated weights for policy 1, policy_version 71500 (0.0012) -[2023-11-28 02:05:16,316][87424] Updated weights for policy 0, policy_version 71626 (0.0008) -[2023-11-28 02:05:16,682][87426] Updated weights for policy 1, policy_version 71510 (0.0012) -[2023-11-28 02:05:16,699][87424] Updated weights for policy 0, policy_version 71636 (0.0008) -[2023-11-28 02:05:17,069][87426] Updated weights for policy 1, policy_version 71520 (0.0007) -[2023-11-28 02:05:17,086][87424] Updated weights for policy 0, policy_version 71646 (0.0007) -[2023-11-28 02:05:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 36651008. Throughput: 0: 2773.9, 1: 2725.6. Samples: 36663112. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 02:05:18,445][86177] Avg episode reward: [(0, '-629.800'), (1, '-525.130')] -[2023-11-28 02:05:18,990][87426] Updated weights for policy 1, policy_version 71530 (0.0008) -[2023-11-28 02:05:19,223][87424] Updated weights for policy 0, policy_version 71656 (0.0011) -[2023-11-28 02:05:19,368][87426] Updated weights for policy 1, policy_version 71540 (0.0007) -[2023-11-28 02:05:19,612][87424] Updated weights for policy 0, policy_version 71666 (0.0012) -[2023-11-28 02:05:19,760][87426] Updated weights for policy 1, policy_version 71550 (0.0008) -[2023-11-28 02:05:19,984][87424] Updated weights for policy 0, policy_version 71676 (0.0012) -[2023-11-28 02:05:22,081][87424] Updated weights for policy 0, policy_version 71686 (0.0011) -[2023-11-28 02:05:22,263][87426] Updated weights for policy 1, policy_version 71560 (0.0008) -[2023-11-28 02:05:22,461][87424] Updated weights for policy 0, policy_version 71696 (0.0011) -[2023-11-28 02:05:22,643][87426] Updated weights for policy 1, policy_version 71570 (0.0011) -[2023-11-28 02:05:22,848][87424] Updated weights for policy 0, policy_version 71706 (0.0009) -[2023-11-28 02:05:23,025][87426] Updated weights for policy 1, policy_version 71580 (0.0012) -[2023-11-28 02:05:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 36683776. Throughput: 0: 2770.1, 1: 2718.8. Samples: 36695492. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 02:05:23,445][86177] Avg episode reward: [(0, '-634.720'), (1, '-524.170')] -[2023-11-28 02:05:24,960][87426] Updated weights for policy 1, policy_version 71590 (0.0009) -[2023-11-28 02:05:25,088][87424] Updated weights for policy 0, policy_version 71716 (0.0010) -[2023-11-28 02:05:25,347][87426] Updated weights for policy 1, policy_version 71600 (0.0011) -[2023-11-28 02:05:25,479][87424] Updated weights for policy 0, policy_version 71726 (0.0012) -[2023-11-28 02:05:25,731][87426] Updated weights for policy 1, policy_version 71610 (0.0011) -[2023-11-28 02:05:25,858][87424] Updated weights for policy 0, policy_version 71736 (0.0012) -[2023-11-28 02:05:27,780][87424] Updated weights for policy 0, policy_version 71746 (0.0009) -[2023-11-28 02:05:28,133][87426] Updated weights for policy 1, policy_version 71620 (0.0011) -[2023-11-28 02:05:28,166][87424] Updated weights for policy 0, policy_version 71756 (0.0012) -[2023-11-28 02:05:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 36700160. Throughput: 0: 2771.0, 1: 2743.2. Samples: 36720360. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:05:28,445][86177] Avg episode reward: [(0, '-630.860'), (1, '-506.110')] -[2023-11-28 02:05:28,522][87426] Updated weights for policy 1, policy_version 71630 (0.0011) -[2023-11-28 02:05:28,554][87424] Updated weights for policy 0, policy_version 71766 (0.0010) -[2023-11-28 02:05:28,895][87426] Updated weights for policy 1, policy_version 71640 (0.0011) -[2023-11-28 02:05:28,923][87424] Updated weights for policy 0, policy_version 71776 (0.0009) -[2023-11-28 02:05:31,267][87424] Updated weights for policy 0, policy_version 71786 (0.0011) -[2023-11-28 02:05:31,318][87426] Updated weights for policy 1, policy_version 71650 (0.0012) -[2023-11-28 02:05:31,653][87424] Updated weights for policy 0, policy_version 71796 (0.0011) -[2023-11-28 02:05:31,711][87426] Updated weights for policy 1, policy_version 71660 (0.0009) -[2023-11-28 02:05:32,029][87424] Updated weights for policy 0, policy_version 71806 (0.0011) -[2023-11-28 02:05:32,086][87426] Updated weights for policy 1, policy_version 71670 (0.0012) -[2023-11-28 02:05:32,451][87426] Updated weights for policy 1, policy_version 71680 (0.0012) -[2023-11-28 02:05:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 36732928. Throughput: 0: 2773.8, 1: 2716.7. Samples: 36744536. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:05:33,445][86177] Avg episode reward: [(0, '-605.440'), (1, '-500.850')] -[2023-11-28 02:05:34,332][87426] Updated weights for policy 1, policy_version 71690 (0.0009) -[2023-11-28 02:05:34,469][87424] Updated weights for policy 0, policy_version 71816 (0.0011) -[2023-11-28 02:05:34,722][87426] Updated weights for policy 1, policy_version 71700 (0.0011) -[2023-11-28 02:05:34,856][87424] Updated weights for policy 0, policy_version 71826 (0.0012) -[2023-11-28 02:05:35,093][87426] Updated weights for policy 1, policy_version 71710 (0.0010) -[2023-11-28 02:05:35,233][87424] Updated weights for policy 0, policy_version 71836 (0.0010) -[2023-11-28 02:05:37,150][87426] Updated weights for policy 1, policy_version 71720 (0.0012) -[2023-11-28 02:05:37,176][87424] Updated weights for policy 0, policy_version 71846 (0.0010) -[2023-11-28 02:05:37,527][87426] Updated weights for policy 1, policy_version 71730 (0.0010) -[2023-11-28 02:05:37,573][87424] Updated weights for policy 0, policy_version 71856 (0.0010) -[2023-11-28 02:05:37,905][87426] Updated weights for policy 1, policy_version 71740 (0.0011) -[2023-11-28 02:05:37,947][87424] Updated weights for policy 0, policy_version 71866 (0.0008) -[2023-11-28 02:05:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 36765696. Throughput: 0: 2779.0, 1: 2754.8. Samples: 36778820. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:05:38,445][86177] Avg episode reward: [(0, '-619.450'), (1, '-498.060')] -[2023-11-28 02:05:39,915][87426] Updated weights for policy 1, policy_version 71750 (0.0012) -[2023-11-28 02:05:40,248][87424] Updated weights for policy 0, policy_version 71876 (0.0009) -[2023-11-28 02:05:40,290][87426] Updated weights for policy 1, policy_version 71760 (0.0011) -[2023-11-28 02:05:40,630][87424] Updated weights for policy 0, policy_version 71886 (0.0011) -[2023-11-28 02:05:40,667][87426] Updated weights for policy 1, policy_version 71770 (0.0012) -[2023-11-28 02:05:41,005][87424] Updated weights for policy 0, policy_version 71896 (0.0011) -[2023-11-28 02:05:43,067][87424] Updated weights for policy 0, policy_version 71906 (0.0011) -[2023-11-28 02:05:43,198][87426] Updated weights for policy 1, policy_version 71780 (0.0011) -[2023-11-28 02:05:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 36782080. Throughput: 0: 2772.5, 1: 2723.4. Samples: 36802964. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:05:43,445][86177] Avg episode reward: [(0, '-617.170'), (1, '-499.670')] -[2023-11-28 02:05:43,449][87424] Updated weights for policy 0, policy_version 71916 (0.0011) -[2023-11-28 02:05:43,572][87426] Updated weights for policy 1, policy_version 71790 (0.0011) -[2023-11-28 02:05:43,838][87424] Updated weights for policy 0, policy_version 71926 (0.0011) -[2023-11-28 02:05:43,946][87426] Updated weights for policy 1, policy_version 71800 (0.0009) -[2023-11-28 02:05:44,215][87424] Updated weights for policy 0, policy_version 71936 (0.0011) -[2023-11-28 02:05:45,701][87426] Updated weights for policy 1, policy_version 71810 (0.0008) -[2023-11-28 02:05:46,091][87426] Updated weights for policy 1, policy_version 71820 (0.0011) -[2023-11-28 02:05:46,371][87424] Updated weights for policy 0, policy_version 71946 (0.0008) -[2023-11-28 02:05:46,462][87426] Updated weights for policy 1, policy_version 71830 (0.0011) -[2023-11-28 02:05:46,755][87424] Updated weights for policy 0, policy_version 71956 (0.0008) -[2023-11-28 02:05:46,836][87426] Updated weights for policy 1, policy_version 71840 (0.0012) -[2023-11-28 02:05:47,139][87424] Updated weights for policy 0, policy_version 71966 (0.0007) -[2023-11-28 02:05:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 36814848. Throughput: 0: 2765.5, 1: 2743.6. Samples: 36828212. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:05:48,445][86177] Avg episode reward: [(0, '-637.990'), (1, '-502.630')] -[2023-11-28 02:05:48,906][87426] Updated weights for policy 1, policy_version 71850 (0.0012) -[2023-11-28 02:05:49,283][87426] Updated weights for policy 1, policy_version 71860 (0.0011) -[2023-11-28 02:05:49,370][87424] Updated weights for policy 0, policy_version 71976 (0.0010) -[2023-11-28 02:05:49,655][87426] Updated weights for policy 1, policy_version 71870 (0.0008) -[2023-11-28 02:05:49,754][87424] Updated weights for policy 0, policy_version 71986 (0.0010) -[2023-11-28 02:05:50,148][87424] Updated weights for policy 0, policy_version 71996 (0.0009) -[2023-11-28 02:05:51,824][87426] Updated weights for policy 1, policy_version 71880 (0.0012) -[2023-11-28 02:05:52,202][87426] Updated weights for policy 1, policy_version 71890 (0.0011) -[2023-11-28 02:05:52,520][87424] Updated weights for policy 0, policy_version 72006 (0.0011) -[2023-11-28 02:05:52,583][87426] Updated weights for policy 1, policy_version 71900 (0.0011) -[2023-11-28 02:05:52,914][87424] Updated weights for policy 0, policy_version 72016 (0.0012) -[2023-11-28 02:05:53,295][87424] Updated weights for policy 0, policy_version 72026 (0.0012) -[2023-11-28 02:05:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 36839424. Throughput: 0: 2731.8, 1: 2732.7. Samples: 36859992. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:05:53,445][86177] Avg episode reward: [(0, '-710.490'), (1, '-520.980')] -[2023-11-28 02:05:55,130][87426] Updated weights for policy 1, policy_version 71910 (0.0011) -[2023-11-28 02:05:55,512][87424] Updated weights for policy 0, policy_version 72036 (0.0010) -[2023-11-28 02:05:55,513][87426] Updated weights for policy 1, policy_version 71920 (0.0009) -[2023-11-28 02:05:55,900][87426] Updated weights for policy 1, policy_version 71930 (0.0007) -[2023-11-28 02:05:55,908][87424] Updated weights for policy 0, policy_version 72046 (0.0007) -[2023-11-28 02:05:56,279][87424] Updated weights for policy 0, policy_version 72056 (0.0008) -[2023-11-28 02:05:57,670][87426] Updated weights for policy 1, policy_version 71940 (0.0010) -[2023-11-28 02:05:58,015][87424] Updated weights for policy 0, policy_version 72066 (0.0008) -[2023-11-28 02:05:58,050][87426] Updated weights for policy 1, policy_version 71950 (0.0008) -[2023-11-28 02:05:58,399][87424] Updated weights for policy 0, policy_version 72076 (0.0012) -[2023-11-28 02:05:58,425][87426] Updated weights for policy 1, policy_version 71960 (0.0008) -[2023-11-28 02:05:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 36864000. Throughput: 0: 2731.1, 1: 2769.4. Samples: 36885500. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:05:58,445][86177] Avg episode reward: [(0, '-777.600'), (1, '-519.260')] -[2023-11-28 02:05:58,781][87424] Updated weights for policy 0, policy_version 72086 (0.0012) -[2023-11-28 02:05:59,163][87424] Updated weights for policy 0, policy_version 72096 (0.0011) -[2023-11-28 02:06:00,698][87426] Updated weights for policy 1, policy_version 71970 (0.0011) -[2023-11-28 02:06:01,020][87424] Updated weights for policy 0, policy_version 72106 (0.0011) -[2023-11-28 02:06:01,077][87426] Updated weights for policy 1, policy_version 71980 (0.0008) -[2023-11-28 02:06:01,407][87424] Updated weights for policy 0, policy_version 72116 (0.0012) -[2023-11-28 02:06:01,462][87426] Updated weights for policy 1, policy_version 71990 (0.0007) -[2023-11-28 02:06:01,792][87424] Updated weights for policy 0, policy_version 72126 (0.0012) -[2023-11-28 02:06:01,842][87426] Updated weights for policy 1, policy_version 72000 (0.0011) -[2023-11-28 02:06:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 36896768. Throughput: 0: 2721.3, 1: 2747.7. Samples: 36909220. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:06:03,445][86177] Avg episode reward: [(0, '-776.520'), (1, '-518.430')] -[2023-11-28 02:06:04,165][87426] Updated weights for policy 1, policy_version 72010 (0.0012) -[2023-11-28 02:06:04,402][87424] Updated weights for policy 0, policy_version 72136 (0.0009) -[2023-11-28 02:06:04,536][87426] Updated weights for policy 1, policy_version 72020 (0.0011) -[2023-11-28 02:06:04,794][87424] Updated weights for policy 0, policy_version 72146 (0.0009) -[2023-11-28 02:06:04,908][87426] Updated weights for policy 1, policy_version 72030 (0.0012) -[2023-11-28 02:06:05,172][87424] Updated weights for policy 0, policy_version 72156 (0.0011) -[2023-11-28 02:06:06,624][87426] Updated weights for policy 1, policy_version 72040 (0.0009) -[2023-11-28 02:06:06,997][87426] Updated weights for policy 1, policy_version 72050 (0.0008) -[2023-11-28 02:06:07,199][87424] Updated weights for policy 0, policy_version 72166 (0.0012) -[2023-11-28 02:06:07,380][87426] Updated weights for policy 1, policy_version 72060 (0.0010) -[2023-11-28 02:06:07,571][87424] Updated weights for policy 0, policy_version 72176 (0.0012) -[2023-11-28 02:06:07,963][87424] Updated weights for policy 0, policy_version 72186 (0.0012) -[2023-11-28 02:06:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 36929536. Throughput: 0: 2732.4, 1: 2738.8. Samples: 36941696. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:06:08,445][86177] Avg episode reward: [(0, '-748.960'), (1, '-526.330')] -[2023-11-28 02:06:09,042][87426] Updated weights for policy 1, policy_version 72070 (0.0010) -[2023-11-28 02:06:09,422][87426] Updated weights for policy 1, policy_version 72080 (0.0008) -[2023-11-28 02:06:09,694][87424] Updated weights for policy 0, policy_version 72196 (0.0011) -[2023-11-28 02:06:09,802][87426] Updated weights for policy 1, policy_version 72090 (0.0008) -[2023-11-28 02:06:10,075][87424] Updated weights for policy 0, policy_version 72206 (0.0011) -[2023-11-28 02:06:10,457][87424] Updated weights for policy 0, policy_version 72216 (0.0011) -[2023-11-28 02:06:12,320][87426] Updated weights for policy 1, policy_version 72100 (0.0010) -[2023-11-28 02:06:12,702][87426] Updated weights for policy 1, policy_version 72110 (0.0011) -[2023-11-28 02:06:12,989][87424] Updated weights for policy 0, policy_version 72226 (0.0008) -[2023-11-28 02:06:13,088][87426] Updated weights for policy 1, policy_version 72120 (0.0011) -[2023-11-28 02:06:13,373][87424] Updated weights for policy 0, policy_version 72236 (0.0008) -[2023-11-28 02:06:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 36954112. Throughput: 0: 2719.9, 1: 2735.7. Samples: 36965864. Policy #0 lag: (min: 45.0, avg: 61.7, max: 71.0) -[2023-11-28 02:06:13,445][86177] Avg episode reward: [(0, '-776.210'), (1, '-508.630')] -[2023-11-28 02:06:13,754][87424] Updated weights for policy 0, policy_version 72246 (0.0008) -[2023-11-28 02:06:14,141][87424] Updated weights for policy 0, policy_version 72256 (0.0007) -[2023-11-28 02:06:15,132][87426] Updated weights for policy 1, policy_version 72130 (0.0012) -[2023-11-28 02:06:15,513][87426] Updated weights for policy 1, policy_version 72140 (0.0011) -[2023-11-28 02:06:15,896][87426] Updated weights for policy 1, policy_version 72150 (0.0012) -[2023-11-28 02:06:16,274][87426] Updated weights for policy 1, policy_version 72160 (0.0012) -[2023-11-28 02:06:16,497][87424] Updated weights for policy 0, policy_version 72266 (0.0007) -[2023-11-28 02:06:16,875][87424] Updated weights for policy 0, policy_version 72276 (0.0007) -[2023-11-28 02:06:17,260][87424] Updated weights for policy 0, policy_version 72286 (0.0008) -[2023-11-28 02:06:18,281][87426] Updated weights for policy 1, policy_version 72170 (0.0012) -[2023-11-28 02:06:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 36978688. Throughput: 0: 2704.9, 1: 2747.0. Samples: 36989872. Policy #0 lag: (min: 6.0, avg: 11.7, max: 38.0) -[2023-11-28 02:06:18,446][86177] Avg episode reward: [(0, '-789.680'), (1, '-513.480')] -[2023-11-28 02:06:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000072288_18505728.pth... -[2023-11-28 02:06:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000069728_17850368.pth -[2023-11-28 02:06:18,674][87426] Updated weights for policy 1, policy_version 72180 (0.0012) -[2023-11-28 02:06:19,042][87424] Updated weights for policy 0, policy_version 72296 (0.0011) -[2023-11-28 02:06:19,044][87426] Updated weights for policy 1, policy_version 72190 (0.0011) -[2023-11-28 02:06:19,118][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000072192_18481152.pth... -[2023-11-28 02:06:19,149][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000069664_17833984.pth -[2023-11-28 02:06:19,417][87424] Updated weights for policy 0, policy_version 72306 (0.0010) -[2023-11-28 02:06:19,802][87424] Updated weights for policy 0, policy_version 72316 (0.0008) -[2023-11-28 02:06:21,384][87426] Updated weights for policy 1, policy_version 72200 (0.0012) -[2023-11-28 02:06:21,765][87426] Updated weights for policy 1, policy_version 72210 (0.0009) -[2023-11-28 02:06:22,138][87426] Updated weights for policy 1, policy_version 72220 (0.0011) -[2023-11-28 02:06:22,267][87424] Updated weights for policy 0, policy_version 72326 (0.0011) -[2023-11-28 02:06:22,643][87424] Updated weights for policy 0, policy_version 72336 (0.0008) -[2023-11-28 02:06:23,029][87424] Updated weights for policy 0, policy_version 72346 (0.0009) -[2023-11-28 02:06:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 37011456. Throughput: 0: 2668.8, 1: 2716.7. Samples: 37021168. Policy #0 lag: (min: 6.0, avg: 11.7, max: 38.0) -[2023-11-28 02:06:23,445][86177] Avg episode reward: [(0, '-793.020'), (1, '-515.380')] -[2023-11-28 02:06:24,401][87426] Updated weights for policy 1, policy_version 72230 (0.0009) -[2023-11-28 02:06:24,787][87426] Updated weights for policy 1, policy_version 72240 (0.0007) -[2023-11-28 02:06:25,166][87426] Updated weights for policy 1, policy_version 72250 (0.0008) -[2023-11-28 02:06:25,643][87424] Updated weights for policy 0, policy_version 72356 (0.0007) -[2023-11-28 02:06:26,022][87424] Updated weights for policy 0, policy_version 72366 (0.0009) -[2023-11-28 02:06:26,413][87424] Updated weights for policy 0, policy_version 72376 (0.0012) -[2023-11-28 02:06:27,421][87426] Updated weights for policy 1, policy_version 72260 (0.0009) -[2023-11-28 02:06:27,806][87426] Updated weights for policy 1, policy_version 72270 (0.0012) -[2023-11-28 02:06:28,181][87426] Updated weights for policy 1, policy_version 72280 (0.0007) -[2023-11-28 02:06:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 37027840. Throughput: 0: 2658.0, 1: 2741.8. Samples: 37045956. Policy #0 lag: (min: 6.0, avg: 11.7, max: 38.0) -[2023-11-28 02:06:28,445][86177] Avg episode reward: [(0, '-777.910'), (1, '-507.700')] -[2023-11-28 02:06:28,927][87424] Updated weights for policy 0, policy_version 72386 (0.0012) -[2023-11-28 02:06:29,301][87424] Updated weights for policy 0, policy_version 72396 (0.0011) -[2023-11-28 02:06:29,686][87424] Updated weights for policy 0, policy_version 72406 (0.0011) -[2023-11-28 02:06:30,067][87424] Updated weights for policy 0, policy_version 72416 (0.0010) -[2023-11-28 02:06:30,709][87426] Updated weights for policy 1, policy_version 72290 (0.0008) -[2023-11-28 02:06:31,089][87426] Updated weights for policy 1, policy_version 72300 (0.0012) -[2023-11-28 02:06:31,469][87426] Updated weights for policy 1, policy_version 72310 (0.0011) -[2023-11-28 02:06:31,850][87426] Updated weights for policy 1, policy_version 72320 (0.0011) -[2023-11-28 02:06:32,303][87424] Updated weights for policy 0, policy_version 72426 (0.0011) -[2023-11-28 02:06:32,677][87424] Updated weights for policy 0, policy_version 72436 (0.0010) -[2023-11-28 02:06:33,059][87424] Updated weights for policy 0, policy_version 72446 (0.0010) -[2023-11-28 02:06:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37060608. Throughput: 0: 2686.0, 1: 2723.0. Samples: 37071616. Policy #0 lag: (min: 6.0, avg: 11.7, max: 38.0) -[2023-11-28 02:06:33,445][86177] Avg episode reward: [(0, '-750.500'), (1, '-507.620')] -[2023-11-28 02:06:34,305][87426] Updated weights for policy 1, policy_version 72330 (0.0007) -[2023-11-28 02:06:34,684][87426] Updated weights for policy 1, policy_version 72340 (0.0010) -[2023-11-28 02:06:35,072][87426] Updated weights for policy 1, policy_version 72350 (0.0010) -[2023-11-28 02:06:35,205][87424] Updated weights for policy 0, policy_version 72456 (0.0010) -[2023-11-28 02:06:35,593][87424] Updated weights for policy 0, policy_version 72466 (0.0012) -[2023-11-28 02:06:35,982][87424] Updated weights for policy 0, policy_version 72476 (0.0012) -[2023-11-28 02:06:36,824][87426] Updated weights for policy 1, policy_version 72360 (0.0011) -[2023-11-28 02:06:37,200][87426] Updated weights for policy 1, policy_version 72370 (0.0011) -[2023-11-28 02:06:37,580][87426] Updated weights for policy 1, policy_version 72380 (0.0012) -[2023-11-28 02:06:37,936][87424] Updated weights for policy 0, policy_version 72486 (0.0012) -[2023-11-28 02:06:38,313][87424] Updated weights for policy 0, policy_version 72496 (0.0010) -[2023-11-28 02:06:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 37085184. Throughput: 0: 2715.6, 1: 2720.3. Samples: 37104608. Policy #0 lag: (min: 6.0, avg: 11.7, max: 38.0) -[2023-11-28 02:06:38,445][86177] Avg episode reward: [(0, '-809.490'), (1, '-499.490')] -[2023-11-28 02:06:38,697][87424] Updated weights for policy 0, policy_version 72506 (0.0010) -[2023-11-28 02:06:39,592][87426] Updated weights for policy 1, policy_version 72390 (0.0011) -[2023-11-28 02:06:39,962][87426] Updated weights for policy 1, policy_version 72400 (0.0011) -[2023-11-28 02:06:40,340][87426] Updated weights for policy 1, policy_version 72410 (0.0010) -[2023-11-28 02:06:40,712][87424] Updated weights for policy 0, policy_version 72516 (0.0010) -[2023-11-28 02:06:41,088][87424] Updated weights for policy 0, policy_version 72526 (0.0012) -[2023-11-28 02:06:41,475][87424] Updated weights for policy 0, policy_version 72536 (0.0011) -[2023-11-28 02:06:42,915][87426] Updated weights for policy 1, policy_version 72420 (0.0011) -[2023-11-28 02:06:43,295][87426] Updated weights for policy 1, policy_version 72430 (0.0012) -[2023-11-28 02:06:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 37109760. Throughput: 0: 2728.4, 1: 2685.1. Samples: 37129104. Policy #0 lag: (min: 6.0, avg: 11.7, max: 38.0) -[2023-11-28 02:06:43,445][86177] Avg episode reward: [(0, '-745.060'), (1, '-508.500')] -[2023-11-28 02:06:43,667][87426] Updated weights for policy 1, policy_version 72440 (0.0012) -[2023-11-28 02:06:43,824][87424] Updated weights for policy 0, policy_version 72546 (0.0010) -[2023-11-28 02:06:44,205][87424] Updated weights for policy 0, policy_version 72556 (0.0007) -[2023-11-28 02:06:44,581][87424] Updated weights for policy 0, policy_version 72566 (0.0007) -[2023-11-28 02:06:44,960][87424] Updated weights for policy 0, policy_version 72576 (0.0008) -[2023-11-28 02:06:45,873][87426] Updated weights for policy 1, policy_version 72450 (0.0011) -[2023-11-28 02:06:46,244][87426] Updated weights for policy 1, policy_version 72460 (0.0012) -[2023-11-28 02:06:46,629][87426] Updated weights for policy 1, policy_version 72470 (0.0011) -[2023-11-28 02:06:47,017][87426] Updated weights for policy 1, policy_version 72480 (0.0007) -[2023-11-28 02:06:47,403][87424] Updated weights for policy 0, policy_version 72586 (0.0012) -[2023-11-28 02:06:47,782][87424] Updated weights for policy 0, policy_version 72596 (0.0009) -[2023-11-28 02:06:48,161][87424] Updated weights for policy 0, policy_version 72606 (0.0007) -[2023-11-28 02:06:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37142528. Throughput: 0: 2721.2, 1: 2700.1. Samples: 37153180. Policy #0 lag: (min: 6.0, avg: 11.7, max: 38.0) -[2023-11-28 02:06:48,445][86177] Avg episode reward: [(0, '-752.110'), (1, '-527.050')] -[2023-11-28 02:06:49,125][87426] Updated weights for policy 1, policy_version 72490 (0.0008) -[2023-11-28 02:06:49,512][87426] Updated weights for policy 1, policy_version 72500 (0.0007) -[2023-11-28 02:06:49,898][87426] Updated weights for policy 1, policy_version 72510 (0.0008) -[2023-11-28 02:06:50,579][87424] Updated weights for policy 0, policy_version 72616 (0.0008) -[2023-11-28 02:06:50,974][87424] Updated weights for policy 0, policy_version 72626 (0.0009) -[2023-11-28 02:06:51,348][87424] Updated weights for policy 0, policy_version 72636 (0.0008) -[2023-11-28 02:06:52,437][87426] Updated weights for policy 1, policy_version 72520 (0.0009) -[2023-11-28 02:06:52,813][87426] Updated weights for policy 1, policy_version 72530 (0.0011) -[2023-11-28 02:06:53,194][87426] Updated weights for policy 1, policy_version 72540 (0.0011) -[2023-11-28 02:06:53,197][87424] Updated weights for policy 0, policy_version 72646 (0.0010) -[2023-11-28 02:06:53,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37167104. Throughput: 0: 2691.6, 1: 2692.3. Samples: 37183976. Policy #0 lag: (min: 6.0, avg: 11.7, max: 38.0) -[2023-11-28 02:06:53,445][86177] Avg episode reward: [(0, '-739.350'), (1, '-540.960')] -[2023-11-28 02:06:53,580][87424] Updated weights for policy 0, policy_version 72656 (0.0011) -[2023-11-28 02:06:53,963][87424] Updated weights for policy 0, policy_version 72666 (0.0011) -[2023-11-28 02:06:55,520][87426] Updated weights for policy 1, policy_version 72550 (0.0011) -[2023-11-28 02:06:55,776][87424] Updated weights for policy 0, policy_version 72676 (0.0010) -[2023-11-28 02:06:55,886][87426] Updated weights for policy 1, policy_version 72560 (0.0010) -[2023-11-28 02:06:56,155][87424] Updated weights for policy 0, policy_version 72686 (0.0008) -[2023-11-28 02:06:56,260][87426] Updated weights for policy 1, policy_version 72570 (0.0011) -[2023-11-28 02:06:56,536][87424] Updated weights for policy 0, policy_version 72696 (0.0007) -[2023-11-28 02:06:58,332][87426] Updated weights for policy 1, policy_version 72580 (0.0010) -[2023-11-28 02:06:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 37191680. Throughput: 0: 2709.0, 1: 2701.7. Samples: 37209344. Policy #0 lag: (min: 6.0, avg: 11.7, max: 38.0) -[2023-11-28 02:06:58,445][86177] Avg episode reward: [(0, '-698.090'), (1, '-549.240')] -[2023-11-28 02:06:58,706][87426] Updated weights for policy 1, policy_version 72590 (0.0012) -[2023-11-28 02:06:58,748][87424] Updated weights for policy 0, policy_version 72706 (0.0007) -[2023-11-28 02:06:59,077][87426] Updated weights for policy 1, policy_version 72600 (0.0010) -[2023-11-28 02:06:59,126][87424] Updated weights for policy 0, policy_version 72716 (0.0009) -[2023-11-28 02:06:59,507][87424] Updated weights for policy 0, policy_version 72726 (0.0010) -[2023-11-28 02:06:59,890][87424] Updated weights for policy 0, policy_version 72736 (0.0008) -[2023-11-28 02:07:00,967][87426] Updated weights for policy 1, policy_version 72610 (0.0012) -[2023-11-28 02:07:01,351][87426] Updated weights for policy 1, policy_version 72620 (0.0012) -[2023-11-28 02:07:01,728][87426] Updated weights for policy 1, policy_version 72630 (0.0012) -[2023-11-28 02:07:02,100][87426] Updated weights for policy 1, policy_version 72640 (0.0012) -[2023-11-28 02:07:02,193][87424] Updated weights for policy 0, policy_version 72746 (0.0010) -[2023-11-28 02:07:02,580][87424] Updated weights for policy 0, policy_version 72756 (0.0008) -[2023-11-28 02:07:02,957][87424] Updated weights for policy 0, policy_version 72766 (0.0009) -[2023-11-28 02:07:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37224448. Throughput: 0: 2700.7, 1: 2706.2. Samples: 37233184. Policy #0 lag: (min: 19.0, avg: 39.9, max: 51.0) -[2023-11-28 02:07:03,445][86177] Avg episode reward: [(0, '-647.860'), (1, '-531.640')] -[2023-11-28 02:07:04,398][87426] Updated weights for policy 1, policy_version 72650 (0.0011) -[2023-11-28 02:07:04,785][87426] Updated weights for policy 1, policy_version 72660 (0.0008) -[2023-11-28 02:07:04,873][87424] Updated weights for policy 0, policy_version 72776 (0.0009) -[2023-11-28 02:07:05,159][87426] Updated weights for policy 1, policy_version 72670 (0.0012) -[2023-11-28 02:07:05,258][87424] Updated weights for policy 0, policy_version 72786 (0.0011) -[2023-11-28 02:07:05,642][87424] Updated weights for policy 0, policy_version 72796 (0.0011) -[2023-11-28 02:07:06,867][87426] Updated weights for policy 1, policy_version 72680 (0.0012) -[2023-11-28 02:07:07,247][87426] Updated weights for policy 1, policy_version 72690 (0.0011) -[2023-11-28 02:07:07,623][87426] Updated weights for policy 1, policy_version 72700 (0.0009) -[2023-11-28 02:07:08,050][87424] Updated weights for policy 0, policy_version 72806 (0.0010) -[2023-11-28 02:07:08,437][87424] Updated weights for policy 0, policy_version 72816 (0.0011) -[2023-11-28 02:07:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 37249024. Throughput: 0: 2728.8, 1: 2709.0. Samples: 37265868. Policy #0 lag: (min: 19.0, avg: 39.9, max: 51.0) -[2023-11-28 02:07:08,445][86177] Avg episode reward: [(0, '-692.870'), (1, '-534.400')] -[2023-11-28 02:07:08,816][87424] Updated weights for policy 0, policy_version 72826 (0.0012) -[2023-11-28 02:07:10,123][87426] Updated weights for policy 1, policy_version 72710 (0.0010) -[2023-11-28 02:07:10,501][87426] Updated weights for policy 1, policy_version 72720 (0.0009) -[2023-11-28 02:07:10,890][87426] Updated weights for policy 1, policy_version 72730 (0.0008) -[2023-11-28 02:07:10,976][87424] Updated weights for policy 0, policy_version 72836 (0.0012) -[2023-11-28 02:07:11,358][87424] Updated weights for policy 0, policy_version 72846 (0.0012) -[2023-11-28 02:07:11,741][87424] Updated weights for policy 0, policy_version 72856 (0.0011) -[2023-11-28 02:07:12,983][87426] Updated weights for policy 1, policy_version 72740 (0.0010) -[2023-11-28 02:07:13,367][87426] Updated weights for policy 1, policy_version 72750 (0.0011) -[2023-11-28 02:07:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 37273600. Throughput: 0: 2740.7, 1: 2700.6. Samples: 37290816. Policy #0 lag: (min: 19.0, avg: 39.9, max: 51.0) -[2023-11-28 02:07:13,445][86177] Avg episode reward: [(0, '-717.140'), (1, '-522.180')] -[2023-11-28 02:07:13,737][87426] Updated weights for policy 1, policy_version 72760 (0.0011) -[2023-11-28 02:07:13,762][87424] Updated weights for policy 0, policy_version 72866 (0.0012) -[2023-11-28 02:07:14,141][87424] Updated weights for policy 0, policy_version 72876 (0.0008) -[2023-11-28 02:07:14,531][87424] Updated weights for policy 0, policy_version 72886 (0.0007) -[2023-11-28 02:07:14,913][87424] Updated weights for policy 0, policy_version 72896 (0.0010) -[2023-11-28 02:07:16,224][87426] Updated weights for policy 1, policy_version 72770 (0.0012) -[2023-11-28 02:07:16,605][87426] Updated weights for policy 1, policy_version 72780 (0.0012) -[2023-11-28 02:07:16,995][87426] Updated weights for policy 1, policy_version 72790 (0.0012) -[2023-11-28 02:07:17,342][87424] Updated weights for policy 0, policy_version 72906 (0.0012) -[2023-11-28 02:07:17,375][87426] Updated weights for policy 1, policy_version 72800 (0.0012) -[2023-11-28 02:07:17,718][87424] Updated weights for policy 0, policy_version 72916 (0.0012) -[2023-11-28 02:07:18,108][87424] Updated weights for policy 0, policy_version 72926 (0.0012) -[2023-11-28 02:07:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 37306368. Throughput: 0: 2685.8, 1: 2722.3. Samples: 37314980. Policy #0 lag: (min: 19.0, avg: 39.9, max: 51.0) -[2023-11-28 02:07:18,445][86177] Avg episode reward: [(0, '-754.900'), (1, '-528.280')] -[2023-11-28 02:07:19,223][87426] Updated weights for policy 1, policy_version 72810 (0.0012) -[2023-11-28 02:07:19,604][87426] Updated weights for policy 1, policy_version 72820 (0.0011) -[2023-11-28 02:07:19,987][87426] Updated weights for policy 1, policy_version 72830 (0.0011) -[2023-11-28 02:07:20,542][87424] Updated weights for policy 0, policy_version 72936 (0.0010) -[2023-11-28 02:07:20,926][87424] Updated weights for policy 0, policy_version 72946 (0.0007) -[2023-11-28 02:07:21,309][87424] Updated weights for policy 0, policy_version 72956 (0.0008) -[2023-11-28 02:07:22,558][87426] Updated weights for policy 1, policy_version 72840 (0.0011) -[2023-11-28 02:07:22,935][87426] Updated weights for policy 1, policy_version 72850 (0.0011) -[2023-11-28 02:07:23,311][87426] Updated weights for policy 1, policy_version 72860 (0.0011) -[2023-11-28 02:07:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 37322752. Throughput: 0: 2655.0, 1: 2714.9. Samples: 37346256. Policy #0 lag: (min: 19.0, avg: 39.9, max: 51.0) -[2023-11-28 02:07:23,445][86177] Avg episode reward: [(0, '-742.750'), (1, '-521.900')] -[2023-11-28 02:07:23,819][87424] Updated weights for policy 0, policy_version 72966 (0.0010) -[2023-11-28 02:07:24,210][87424] Updated weights for policy 0, policy_version 72976 (0.0012) -[2023-11-28 02:07:24,585][87424] Updated weights for policy 0, policy_version 72986 (0.0012) -[2023-11-28 02:07:25,608][87426] Updated weights for policy 1, policy_version 72870 (0.0009) -[2023-11-28 02:07:25,992][87426] Updated weights for policy 1, policy_version 72880 (0.0007) -[2023-11-28 02:07:26,375][87426] Updated weights for policy 1, policy_version 72890 (0.0009) -[2023-11-28 02:07:27,091][87424] Updated weights for policy 0, policy_version 72996 (0.0012) -[2023-11-28 02:07:27,471][87424] Updated weights for policy 0, policy_version 73006 (0.0011) -[2023-11-28 02:07:27,852][87424] Updated weights for policy 0, policy_version 73016 (0.0012) -[2023-11-28 02:07:28,277][87426] Updated weights for policy 1, policy_version 72900 (0.0010) -[2023-11-28 02:07:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37355520. Throughput: 0: 2641.2, 1: 2722.1. Samples: 37370456. Policy #0 lag: (min: 19.0, avg: 39.9, max: 51.0) -[2023-11-28 02:07:28,445][86177] Avg episode reward: [(0, '-708.460'), (1, '-518.050')] -[2023-11-28 02:07:28,663][87426] Updated weights for policy 1, policy_version 72910 (0.0007) -[2023-11-28 02:07:29,045][87426] Updated weights for policy 1, policy_version 72920 (0.0008) -[2023-11-28 02:07:29,558][87424] Updated weights for policy 0, policy_version 73026 (0.0011) -[2023-11-28 02:07:29,942][87424] Updated weights for policy 0, policy_version 73036 (0.0009) -[2023-11-28 02:07:30,333][87424] Updated weights for policy 0, policy_version 73046 (0.0007) -[2023-11-28 02:07:30,709][87424] Updated weights for policy 0, policy_version 73056 (0.0011) -[2023-11-28 02:07:31,399][87426] Updated weights for policy 1, policy_version 72930 (0.0008) -[2023-11-28 02:07:31,775][87426] Updated weights for policy 1, policy_version 72940 (0.0011) -[2023-11-28 02:07:32,163][87426] Updated weights for policy 1, policy_version 72950 (0.0012) -[2023-11-28 02:07:32,544][87426] Updated weights for policy 1, policy_version 72960 (0.0011) -[2023-11-28 02:07:32,655][87424] Updated weights for policy 0, policy_version 73066 (0.0010) -[2023-11-28 02:07:33,039][87424] Updated weights for policy 0, policy_version 73076 (0.0012) -[2023-11-28 02:07:33,420][87424] Updated weights for policy 0, policy_version 73086 (0.0012) -[2023-11-28 02:07:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 37380096. Throughput: 0: 2685.7, 1: 2709.4. Samples: 37395960. Policy #0 lag: (min: 19.0, avg: 39.9, max: 51.0) -[2023-11-28 02:07:33,445][86177] Avg episode reward: [(0, '-634.840'), (1, '-502.350')] -[2023-11-28 02:07:34,871][87426] Updated weights for policy 1, policy_version 72970 (0.0012) -[2023-11-28 02:07:35,083][87424] Updated weights for policy 0, policy_version 73096 (0.0011) -[2023-11-28 02:07:35,241][87426] Updated weights for policy 1, policy_version 72980 (0.0012) -[2023-11-28 02:07:35,474][87424] Updated weights for policy 0, policy_version 73106 (0.0011) -[2023-11-28 02:07:35,625][87426] Updated weights for policy 1, policy_version 72990 (0.0012) -[2023-11-28 02:07:35,849][87424] Updated weights for policy 0, policy_version 73116 (0.0011) -[2023-11-28 02:07:37,594][87426] Updated weights for policy 1, policy_version 73000 (0.0011) -[2023-11-28 02:07:37,983][87426] Updated weights for policy 1, policy_version 73010 (0.0012) -[2023-11-28 02:07:38,353][87424] Updated weights for policy 0, policy_version 73126 (0.0009) -[2023-11-28 02:07:38,358][87426] Updated weights for policy 1, policy_version 73020 (0.0010) -[2023-11-28 02:07:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 37404672. Throughput: 0: 2713.9, 1: 2733.6. Samples: 37429112. Policy #0 lag: (min: 19.0, avg: 39.9, max: 51.0) -[2023-11-28 02:07:38,445][86177] Avg episode reward: [(0, '-593.710'), (1, '-508.550')] -[2023-11-28 02:07:38,737][87424] Updated weights for policy 0, policy_version 73136 (0.0008) -[2023-11-28 02:07:39,132][87424] Updated weights for policy 0, policy_version 73146 (0.0010) -[2023-11-28 02:07:40,506][87426] Updated weights for policy 1, policy_version 73030 (0.0011) -[2023-11-28 02:07:40,876][87426] Updated weights for policy 1, policy_version 73040 (0.0010) -[2023-11-28 02:07:41,254][87426] Updated weights for policy 1, policy_version 73050 (0.0011) -[2023-11-28 02:07:41,458][87424] Updated weights for policy 0, policy_version 73156 (0.0011) -[2023-11-28 02:07:41,827][87424] Updated weights for policy 0, policy_version 73166 (0.0012) -[2023-11-28 02:07:42,211][87424] Updated weights for policy 0, policy_version 73176 (0.0012) -[2023-11-28 02:07:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37437440. Throughput: 0: 2700.2, 1: 2715.5. Samples: 37453048. Policy #0 lag: (min: 19.0, avg: 39.9, max: 51.0) -[2023-11-28 02:07:43,446][86177] Avg episode reward: [(0, '-563.010'), (1, '-509.200')] -[2023-11-28 02:07:43,502][87426] Updated weights for policy 1, policy_version 73060 (0.0009) -[2023-11-28 02:07:43,886][87426] Updated weights for policy 1, policy_version 73070 (0.0007) -[2023-11-28 02:07:44,267][87426] Updated weights for policy 1, policy_version 73080 (0.0007) -[2023-11-28 02:07:44,682][87424] Updated weights for policy 0, policy_version 73186 (0.0008) -[2023-11-28 02:07:45,065][87424] Updated weights for policy 0, policy_version 73196 (0.0008) -[2023-11-28 02:07:45,448][87424] Updated weights for policy 0, policy_version 73206 (0.0008) -[2023-11-28 02:07:45,838][87424] Updated weights for policy 0, policy_version 73216 (0.0008) -[2023-11-28 02:07:46,764][87426] Updated weights for policy 1, policy_version 73090 (0.0008) -[2023-11-28 02:07:47,135][87426] Updated weights for policy 1, policy_version 73100 (0.0010) -[2023-11-28 02:07:47,526][87426] Updated weights for policy 1, policy_version 73110 (0.0008) -[2023-11-28 02:07:47,761][87424] Updated weights for policy 0, policy_version 73226 (0.0011) -[2023-11-28 02:07:47,897][87426] Updated weights for policy 1, policy_version 73120 (0.0010) -[2023-11-28 02:07:48,140][87424] Updated weights for policy 0, policy_version 73236 (0.0009) -[2023-11-28 02:07:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 37462016. Throughput: 0: 2712.4, 1: 2696.7. Samples: 37476596. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:07:48,445][86177] Avg episode reward: [(0, '-545.030'), (1, '-509.000')] -[2023-11-28 02:07:48,523][87424] Updated weights for policy 0, policy_version 73246 (0.0010) -[2023-11-28 02:07:49,670][87426] Updated weights for policy 1, policy_version 73130 (0.0009) -[2023-11-28 02:07:50,066][87426] Updated weights for policy 1, policy_version 73140 (0.0011) -[2023-11-28 02:07:50,445][87426] Updated weights for policy 1, policy_version 73150 (0.0010) -[2023-11-28 02:07:50,496][87424] Updated weights for policy 0, policy_version 73256 (0.0010) -[2023-11-28 02:07:50,888][87424] Updated weights for policy 0, policy_version 73266 (0.0010) -[2023-11-28 02:07:51,268][87424] Updated weights for policy 0, policy_version 73276 (0.0010) -[2023-11-28 02:07:52,828][87426] Updated weights for policy 1, policy_version 73160 (0.0011) -[2023-11-28 02:07:53,209][87426] Updated weights for policy 1, policy_version 73170 (0.0011) -[2023-11-28 02:07:53,448][86177] Fps is (10 sec: 4913.4, 60 sec: 5324.5, 300 sec: 5415.0). Total num frames: 37486592. Throughput: 0: 2701.6, 1: 2713.3. Samples: 37509556. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:07:53,449][86177] Avg episode reward: [(0, '-558.630'), (1, '-512.660')] -[2023-11-28 02:07:53,593][87426] Updated weights for policy 1, policy_version 73180 (0.0010) -[2023-11-28 02:07:53,665][87424] Updated weights for policy 0, policy_version 73286 (0.0009) -[2023-11-28 02:07:54,050][87424] Updated weights for policy 0, policy_version 73296 (0.0009) -[2023-11-28 02:07:54,431][87424] Updated weights for policy 0, policy_version 73306 (0.0007) -[2023-11-28 02:07:55,875][87426] Updated weights for policy 1, policy_version 73190 (0.0009) -[2023-11-28 02:07:56,258][87426] Updated weights for policy 1, policy_version 73200 (0.0008) -[2023-11-28 02:07:56,595][87424] Updated weights for policy 0, policy_version 73316 (0.0007) -[2023-11-28 02:07:56,638][87426] Updated weights for policy 1, policy_version 73210 (0.0007) -[2023-11-28 02:07:56,982][87424] Updated weights for policy 0, policy_version 73326 (0.0007) -[2023-11-28 02:07:57,374][87424] Updated weights for policy 0, policy_version 73336 (0.0007) -[2023-11-28 02:07:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 37519360. Throughput: 0: 2684.6, 1: 2700.2. Samples: 37533132. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:07:58,445][86177] Avg episode reward: [(0, '-613.970'), (1, '-520.010')] -[2023-11-28 02:07:58,946][87426] Updated weights for policy 1, policy_version 73220 (0.0009) -[2023-11-28 02:07:59,323][87426] Updated weights for policy 1, policy_version 73230 (0.0012) -[2023-11-28 02:07:59,694][87426] Updated weights for policy 1, policy_version 73240 (0.0011) -[2023-11-28 02:07:59,780][87424] Updated weights for policy 0, policy_version 73346 (0.0008) -[2023-11-28 02:08:00,153][87424] Updated weights for policy 0, policy_version 73356 (0.0009) -[2023-11-28 02:08:00,539][87424] Updated weights for policy 0, policy_version 73366 (0.0009) -[2023-11-28 02:08:00,920][87424] Updated weights for policy 0, policy_version 73376 (0.0008) -[2023-11-28 02:08:01,978][87426] Updated weights for policy 1, policy_version 73250 (0.0010) -[2023-11-28 02:08:02,363][87426] Updated weights for policy 1, policy_version 73260 (0.0009) -[2023-11-28 02:08:02,740][87426] Updated weights for policy 1, policy_version 73270 (0.0011) -[2023-11-28 02:08:02,944][87424] Updated weights for policy 0, policy_version 73386 (0.0010) -[2023-11-28 02:08:03,116][87426] Updated weights for policy 1, policy_version 73280 (0.0011) -[2023-11-28 02:08:03,335][87424] Updated weights for policy 0, policy_version 73396 (0.0012) -[2023-11-28 02:08:03,444][86177] Fps is (10 sec: 5736.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 37543936. Throughput: 0: 2706.5, 1: 2675.8. Samples: 37557184. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:08:03,445][86177] Avg episode reward: [(0, '-611.290'), (1, '-519.310')] -[2023-11-28 02:08:03,709][87424] Updated weights for policy 0, policy_version 73406 (0.0011) -[2023-11-28 02:08:05,110][87426] Updated weights for policy 1, policy_version 73290 (0.0008) -[2023-11-28 02:08:05,490][87426] Updated weights for policy 1, policy_version 73300 (0.0008) -[2023-11-28 02:08:05,870][87426] Updated weights for policy 1, policy_version 73310 (0.0007) -[2023-11-28 02:08:05,928][87424] Updated weights for policy 0, policy_version 73416 (0.0009) -[2023-11-28 02:08:06,314][87424] Updated weights for policy 0, policy_version 73426 (0.0008) -[2023-11-28 02:08:06,695][87424] Updated weights for policy 0, policy_version 73436 (0.0008) -[2023-11-28 02:08:08,115][87426] Updated weights for policy 1, policy_version 73320 (0.0007) -[2023-11-28 02:08:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 37568512. Throughput: 0: 2699.0, 1: 2690.5. Samples: 37588784. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:08:08,445][86177] Avg episode reward: [(0, '-667.240'), (1, '-517.940')] -[2023-11-28 02:08:08,508][87426] Updated weights for policy 1, policy_version 73330 (0.0008) -[2023-11-28 02:08:08,884][87426] Updated weights for policy 1, policy_version 73340 (0.0008) -[2023-11-28 02:08:09,186][87424] Updated weights for policy 0, policy_version 73446 (0.0008) -[2023-11-28 02:08:09,570][87424] Updated weights for policy 0, policy_version 73456 (0.0008) -[2023-11-28 02:08:09,959][87424] Updated weights for policy 0, policy_version 73466 (0.0009) -[2023-11-28 02:08:11,257][87426] Updated weights for policy 1, policy_version 73350 (0.0012) -[2023-11-28 02:08:11,631][87426] Updated weights for policy 1, policy_version 73360 (0.0012) -[2023-11-28 02:08:12,005][87426] Updated weights for policy 1, policy_version 73370 (0.0012) -[2023-11-28 02:08:12,293][87424] Updated weights for policy 0, policy_version 73476 (0.0012) -[2023-11-28 02:08:12,670][87424] Updated weights for policy 0, policy_version 73486 (0.0012) -[2023-11-28 02:08:13,055][87424] Updated weights for policy 0, policy_version 73496 (0.0012) -[2023-11-28 02:08:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37601280. Throughput: 0: 2692.4, 1: 2697.5. Samples: 37613004. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:08:13,445][86177] Avg episode reward: [(0, '-647.660'), (1, '-520.920')] -[2023-11-28 02:08:13,946][87426] Updated weights for policy 1, policy_version 73380 (0.0009) -[2023-11-28 02:08:14,334][87426] Updated weights for policy 1, policy_version 73390 (0.0011) -[2023-11-28 02:08:14,693][87424] Updated weights for policy 0, policy_version 73506 (0.0011) -[2023-11-28 02:08:14,701][87426] Updated weights for policy 1, policy_version 73400 (0.0010) -[2023-11-28 02:08:15,078][87424] Updated weights for policy 0, policy_version 73516 (0.0009) -[2023-11-28 02:08:15,457][87424] Updated weights for policy 0, policy_version 73526 (0.0008) -[2023-11-28 02:08:15,837][87424] Updated weights for policy 0, policy_version 73536 (0.0007) -[2023-11-28 02:08:17,073][87426] Updated weights for policy 1, policy_version 73410 (0.0012) -[2023-11-28 02:08:17,452][87426] Updated weights for policy 1, policy_version 73420 (0.0011) -[2023-11-28 02:08:17,837][87426] Updated weights for policy 1, policy_version 73430 (0.0012) -[2023-11-28 02:08:18,102][87424] Updated weights for policy 0, policy_version 73546 (0.0012) -[2023-11-28 02:08:18,212][87426] Updated weights for policy 1, policy_version 73440 (0.0007) -[2023-11-28 02:08:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 37625856. Throughput: 0: 2672.5, 1: 2688.3. Samples: 37637196. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:08:18,445][86177] Avg episode reward: [(0, '-635.580'), (1, '-506.010')] -[2023-11-28 02:08:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000073440_18800640.pth... -[2023-11-28 02:08:18,479][87424] Updated weights for policy 0, policy_version 73556 (0.0011) -[2023-11-28 02:08:18,500][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000070912_18153472.pth -[2023-11-28 02:08:18,872][87424] Updated weights for policy 0, policy_version 73566 (0.0011) -[2023-11-28 02:08:18,935][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000073568_18833408.pth... -[2023-11-28 02:08:18,985][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000071008_18178048.pth -[2023-11-28 02:08:20,374][87426] Updated weights for policy 1, policy_version 73450 (0.0012) -[2023-11-28 02:08:20,748][87426] Updated weights for policy 1, policy_version 73460 (0.0012) -[2023-11-28 02:08:21,132][87426] Updated weights for policy 1, policy_version 73470 (0.0009) -[2023-11-28 02:08:21,490][87424] Updated weights for policy 0, policy_version 73576 (0.0012) -[2023-11-28 02:08:21,869][87424] Updated weights for policy 0, policy_version 73586 (0.0012) -[2023-11-28 02:08:22,259][87424] Updated weights for policy 0, policy_version 73596 (0.0012) -[2023-11-28 02:08:23,354][87426] Updated weights for policy 1, policy_version 73480 (0.0008) -[2023-11-28 02:08:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 37650432. Throughput: 0: 2657.9, 1: 2672.7. Samples: 37668988. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:08:23,445][86177] Avg episode reward: [(0, '-617.290'), (1, '-511.560')] -[2023-11-28 02:08:23,739][87426] Updated weights for policy 1, policy_version 73490 (0.0008) -[2023-11-28 02:08:24,119][87426] Updated weights for policy 1, policy_version 73500 (0.0008) -[2023-11-28 02:08:24,380][87424] Updated weights for policy 0, policy_version 73606 (0.0012) -[2023-11-28 02:08:24,766][87424] Updated weights for policy 0, policy_version 73616 (0.0012) -[2023-11-28 02:08:25,150][87424] Updated weights for policy 0, policy_version 73626 (0.0012) -[2023-11-28 02:08:25,882][87426] Updated weights for policy 1, policy_version 73510 (0.0009) -[2023-11-28 02:08:26,255][87426] Updated weights for policy 1, policy_version 73520 (0.0007) -[2023-11-28 02:08:26,632][87426] Updated weights for policy 1, policy_version 73530 (0.0007) -[2023-11-28 02:08:27,573][87424] Updated weights for policy 0, policy_version 73636 (0.0010) -[2023-11-28 02:08:27,968][87424] Updated weights for policy 0, policy_version 73646 (0.0008) -[2023-11-28 02:08:28,354][87424] Updated weights for policy 0, policy_version 73656 (0.0009) -[2023-11-28 02:08:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 37675008. Throughput: 0: 2664.4, 1: 2702.2. Samples: 37694544. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:08:28,445][86177] Avg episode reward: [(0, '-673.340'), (1, '-538.180')] -[2023-11-28 02:08:28,853][87426] Updated weights for policy 1, policy_version 73540 (0.0008) -[2023-11-28 02:08:29,234][87426] Updated weights for policy 1, policy_version 73550 (0.0010) -[2023-11-28 02:08:29,615][87426] Updated weights for policy 1, policy_version 73560 (0.0007) -[2023-11-28 02:08:30,490][87424] Updated weights for policy 0, policy_version 73666 (0.0008) -[2023-11-28 02:08:30,870][87424] Updated weights for policy 0, policy_version 73676 (0.0012) -[2023-11-28 02:08:31,256][87424] Updated weights for policy 0, policy_version 73686 (0.0012) -[2023-11-28 02:08:31,640][87424] Updated weights for policy 0, policy_version 73696 (0.0012) -[2023-11-28 02:08:31,910][87426] Updated weights for policy 1, policy_version 73570 (0.0010) -[2023-11-28 02:08:32,296][87426] Updated weights for policy 1, policy_version 73580 (0.0009) -[2023-11-28 02:08:32,670][87426] Updated weights for policy 1, policy_version 73590 (0.0008) -[2023-11-28 02:08:33,052][87426] Updated weights for policy 1, policy_version 73600 (0.0008) -[2023-11-28 02:08:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 37707776. Throughput: 0: 2656.3, 1: 2712.4. Samples: 37718184. Policy #0 lag: (min: 31.0, avg: 35.0, max: 63.0) -[2023-11-28 02:08:33,445][86177] Avg episode reward: [(0, '-644.840'), (1, '-578.930')] -[2023-11-28 02:08:33,916][87424] Updated weights for policy 0, policy_version 73706 (0.0012) -[2023-11-28 02:08:34,291][87424] Updated weights for policy 0, policy_version 73716 (0.0012) -[2023-11-28 02:08:34,689][87424] Updated weights for policy 0, policy_version 73726 (0.0012) -[2023-11-28 02:08:35,464][87426] Updated weights for policy 1, policy_version 73610 (0.0011) -[2023-11-28 02:08:35,843][87426] Updated weights for policy 1, policy_version 73620 (0.0012) -[2023-11-28 02:08:36,228][87426] Updated weights for policy 1, policy_version 73630 (0.0012) -[2023-11-28 02:08:36,631][87424] Updated weights for policy 0, policy_version 73736 (0.0013) -[2023-11-28 02:08:37,014][87424] Updated weights for policy 0, policy_version 73746 (0.0012) -[2023-11-28 02:08:37,392][87424] Updated weights for policy 0, policy_version 73756 (0.0009) -[2023-11-28 02:08:38,210][87426] Updated weights for policy 1, policy_version 73640 (0.0008) -[2023-11-28 02:08:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 37732352. Throughput: 0: 2652.6, 1: 2697.5. Samples: 37750292. Policy #0 lag: (min: 3.0, avg: 23.7, max: 35.0) -[2023-11-28 02:08:38,445][86177] Avg episode reward: [(0, '-668.100'), (1, '-581.230')] -[2023-11-28 02:08:38,594][87426] Updated weights for policy 1, policy_version 73650 (0.0007) -[2023-11-28 02:08:38,974][87426] Updated weights for policy 1, policy_version 73660 (0.0008) -[2023-11-28 02:08:39,467][87424] Updated weights for policy 0, policy_version 73766 (0.0010) -[2023-11-28 02:08:39,855][87424] Updated weights for policy 0, policy_version 73776 (0.0011) -[2023-11-28 02:08:40,236][87424] Updated weights for policy 0, policy_version 73786 (0.0012) -[2023-11-28 02:08:41,059][87426] Updated weights for policy 1, policy_version 73670 (0.0008) -[2023-11-28 02:08:41,438][87426] Updated weights for policy 1, policy_version 73680 (0.0007) -[2023-11-28 02:08:41,819][87426] Updated weights for policy 1, policy_version 73690 (0.0011) -[2023-11-28 02:08:42,424][87424] Updated weights for policy 0, policy_version 73796 (0.0016) -[2023-11-28 02:08:42,823][87424] Updated weights for policy 0, policy_version 73806 (0.0012) -[2023-11-28 02:08:43,198][87424] Updated weights for policy 0, policy_version 73816 (0.0010) -[2023-11-28 02:08:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 37756928. Throughput: 0: 2653.2, 1: 2697.6. Samples: 37773916. Policy #0 lag: (min: 3.0, avg: 23.7, max: 35.0) -[2023-11-28 02:08:43,446][86177] Avg episode reward: [(0, '-683.860'), (1, '-579.440')] -[2023-11-28 02:08:44,366][87426] Updated weights for policy 1, policy_version 73700 (0.0011) -[2023-11-28 02:08:44,742][87426] Updated weights for policy 1, policy_version 73710 (0.0007) -[2023-11-28 02:08:45,126][87426] Updated weights for policy 1, policy_version 73720 (0.0007) -[2023-11-28 02:08:45,497][87424] Updated weights for policy 0, policy_version 73826 (0.0008) -[2023-11-28 02:08:45,879][87424] Updated weights for policy 0, policy_version 73836 (0.0012) -[2023-11-28 02:08:46,254][87424] Updated weights for policy 0, policy_version 73846 (0.0012) -[2023-11-28 02:08:46,638][87424] Updated weights for policy 0, policy_version 73856 (0.0009) -[2023-11-28 02:08:47,293][87426] Updated weights for policy 1, policy_version 73730 (0.0010) -[2023-11-28 02:08:47,665][87426] Updated weights for policy 1, policy_version 73740 (0.0012) -[2023-11-28 02:08:48,046][87426] Updated weights for policy 1, policy_version 73750 (0.0012) -[2023-11-28 02:08:48,417][87426] Updated weights for policy 1, policy_version 73760 (0.0012) -[2023-11-28 02:08:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37789696. Throughput: 0: 2656.8, 1: 2693.2. Samples: 37797936. Policy #0 lag: (min: 3.0, avg: 23.7, max: 35.0) -[2023-11-28 02:08:48,445][86177] Avg episode reward: [(0, '-695.800'), (1, '-583.140')] -[2023-11-28 02:08:49,055][87424] Updated weights for policy 0, policy_version 73866 (0.0008) -[2023-11-28 02:08:49,435][87424] Updated weights for policy 0, policy_version 73876 (0.0008) -[2023-11-28 02:08:49,819][87424] Updated weights for policy 0, policy_version 73886 (0.0008) -[2023-11-28 02:08:50,430][87426] Updated weights for policy 1, policy_version 73770 (0.0009) -[2023-11-28 02:08:50,798][87426] Updated weights for policy 1, policy_version 73780 (0.0008) -[2023-11-28 02:08:51,180][87426] Updated weights for policy 1, policy_version 73790 (0.0009) -[2023-11-28 02:08:52,254][87424] Updated weights for policy 0, policy_version 73896 (0.0012) -[2023-11-28 02:08:52,632][87424] Updated weights for policy 0, policy_version 73906 (0.0012) -[2023-11-28 02:08:53,018][87424] Updated weights for policy 0, policy_version 73916 (0.0011) -[2023-11-28 02:08:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.7, 300 sec: 5442.8). Total num frames: 37814272. Throughput: 0: 2682.3, 1: 2687.5. Samples: 37830424. Policy #0 lag: (min: 3.0, avg: 23.7, max: 35.0) -[2023-11-28 02:08:53,445][86177] Avg episode reward: [(0, '-640.720'), (1, '-544.890')] -[2023-11-28 02:08:53,720][87426] Updated weights for policy 1, policy_version 73800 (0.0010) -[2023-11-28 02:08:54,106][87426] Updated weights for policy 1, policy_version 73810 (0.0011) -[2023-11-28 02:08:54,486][87426] Updated weights for policy 1, policy_version 73820 (0.0012) -[2023-11-28 02:08:55,549][87424] Updated weights for policy 0, policy_version 73926 (0.0011) -[2023-11-28 02:08:55,932][87424] Updated weights for policy 0, policy_version 73936 (0.0011) -[2023-11-28 02:08:56,313][87424] Updated weights for policy 0, policy_version 73946 (0.0012) -[2023-11-28 02:08:56,481][87426] Updated weights for policy 1, policy_version 73830 (0.0011) -[2023-11-28 02:08:56,867][87426] Updated weights for policy 1, policy_version 73840 (0.0012) -[2023-11-28 02:08:57,241][87426] Updated weights for policy 1, policy_version 73850 (0.0012) -[2023-11-28 02:08:58,036][87424] Updated weights for policy 0, policy_version 73956 (0.0012) -[2023-11-28 02:08:58,422][87424] Updated weights for policy 0, policy_version 73966 (0.0012) -[2023-11-28 02:08:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 37838848. Throughput: 0: 2685.1, 1: 2718.1. Samples: 37856148. Policy #0 lag: (min: 3.0, avg: 23.7, max: 35.0) -[2023-11-28 02:08:58,445][86177] Avg episode reward: [(0, '-612.410'), (1, '-557.510')] -[2023-11-28 02:08:58,798][87424] Updated weights for policy 0, policy_version 73976 (0.0012) -[2023-11-28 02:08:59,090][87426] Updated weights for policy 1, policy_version 73860 (0.0011) -[2023-11-28 02:08:59,476][87426] Updated weights for policy 1, policy_version 73870 (0.0012) -[2023-11-28 02:08:59,853][87426] Updated weights for policy 1, policy_version 73880 (0.0012) -[2023-11-28 02:09:00,737][87424] Updated weights for policy 0, policy_version 73986 (0.0011) -[2023-11-28 02:09:01,128][87424] Updated weights for policy 0, policy_version 73996 (0.0012) -[2023-11-28 02:09:01,512][87424] Updated weights for policy 0, policy_version 74006 (0.0011) -[2023-11-28 02:09:01,793][87426] Updated weights for policy 1, policy_version 73890 (0.0012) -[2023-11-28 02:09:01,896][87424] Updated weights for policy 0, policy_version 74016 (0.0010) -[2023-11-28 02:09:02,176][87426] Updated weights for policy 1, policy_version 73900 (0.0011) -[2023-11-28 02:09:02,545][87426] Updated weights for policy 1, policy_version 73910 (0.0008) -[2023-11-28 02:09:02,929][87426] Updated weights for policy 1, policy_version 73920 (0.0009) -[2023-11-28 02:09:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37871616. Throughput: 0: 2711.2, 1: 2736.6. Samples: 37882348. Policy #0 lag: (min: 3.0, avg: 23.7, max: 35.0) -[2023-11-28 02:09:03,445][86177] Avg episode reward: [(0, '-598.600'), (1, '-574.900')] -[2023-11-28 02:09:04,281][87424] Updated weights for policy 0, policy_version 74026 (0.0007) -[2023-11-28 02:09:04,675][87424] Updated weights for policy 0, policy_version 74036 (0.0009) -[2023-11-28 02:09:05,047][87424] Updated weights for policy 0, policy_version 74046 (0.0009) -[2023-11-28 02:09:05,142][87426] Updated weights for policy 1, policy_version 73930 (0.0012) -[2023-11-28 02:09:05,522][87426] Updated weights for policy 1, policy_version 73940 (0.0008) -[2023-11-28 02:09:05,901][87426] Updated weights for policy 1, policy_version 73950 (0.0010) -[2023-11-28 02:09:07,030][87424] Updated weights for policy 0, policy_version 74056 (0.0010) -[2023-11-28 02:09:07,414][87424] Updated weights for policy 0, policy_version 74066 (0.0008) -[2023-11-28 02:09:07,798][87424] Updated weights for policy 0, policy_version 74076 (0.0009) -[2023-11-28 02:09:07,885][87426] Updated weights for policy 1, policy_version 73960 (0.0011) -[2023-11-28 02:09:08,263][87426] Updated weights for policy 1, policy_version 73970 (0.0012) -[2023-11-28 02:09:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37896192. Throughput: 0: 2701.2, 1: 2755.2. Samples: 37914528. Policy #0 lag: (min: 3.0, avg: 23.7, max: 35.0) -[2023-11-28 02:09:08,445][86177] Avg episode reward: [(0, '-580.450'), (1, '-562.120')] -[2023-11-28 02:09:08,655][87426] Updated weights for policy 1, policy_version 73980 (0.0008) -[2023-11-28 02:09:09,493][87424] Updated weights for policy 0, policy_version 74086 (0.0011) -[2023-11-28 02:09:09,882][87424] Updated weights for policy 0, policy_version 74096 (0.0011) -[2023-11-28 02:09:10,262][87424] Updated weights for policy 0, policy_version 74106 (0.0012) -[2023-11-28 02:09:10,997][87426] Updated weights for policy 1, policy_version 73990 (0.0008) -[2023-11-28 02:09:11,381][87426] Updated weights for policy 1, policy_version 74000 (0.0009) -[2023-11-28 02:09:11,766][87426] Updated weights for policy 1, policy_version 74010 (0.0011) -[2023-11-28 02:09:12,828][87424] Updated weights for policy 0, policy_version 74116 (0.0011) -[2023-11-28 02:09:13,215][87424] Updated weights for policy 0, policy_version 74126 (0.0012) -[2023-11-28 02:09:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 37920768. Throughput: 0: 2701.9, 1: 2696.7. Samples: 37937480. Policy #0 lag: (min: 3.0, avg: 23.7, max: 35.0) -[2023-11-28 02:09:13,445][86177] Avg episode reward: [(0, '-575.550'), (1, '-547.000')] -[2023-11-28 02:09:13,607][87424] Updated weights for policy 0, policy_version 74136 (0.0012) -[2023-11-28 02:09:14,265][87426] Updated weights for policy 1, policy_version 74020 (0.0011) -[2023-11-28 02:09:14,652][87426] Updated weights for policy 1, policy_version 74030 (0.0011) -[2023-11-28 02:09:15,029][87426] Updated weights for policy 1, policy_version 74040 (0.0012) -[2023-11-28 02:09:15,415][87424] Updated weights for policy 0, policy_version 74146 (0.0012) -[2023-11-28 02:09:15,794][87424] Updated weights for policy 0, policy_version 74156 (0.0012) -[2023-11-28 02:09:16,178][87424] Updated weights for policy 0, policy_version 74166 (0.0009) -[2023-11-28 02:09:16,564][87424] Updated weights for policy 0, policy_version 74176 (0.0008) -[2023-11-28 02:09:16,884][87426] Updated weights for policy 1, policy_version 74050 (0.0012) -[2023-11-28 02:09:17,269][87426] Updated weights for policy 1, policy_version 74060 (0.0010) -[2023-11-28 02:09:17,648][87426] Updated weights for policy 1, policy_version 74070 (0.0007) -[2023-11-28 02:09:18,028][87426] Updated weights for policy 1, policy_version 74080 (0.0007) -[2023-11-28 02:09:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 37953536. Throughput: 0: 2721.2, 1: 2705.1. Samples: 37962368. Policy #0 lag: (min: 3.0, avg: 23.7, max: 35.0) -[2023-11-28 02:09:18,445][86177] Avg episode reward: [(0, '-579.310'), (1, '-557.100')] -[2023-11-28 02:09:18,658][87424] Updated weights for policy 0, policy_version 74186 (0.0008) -[2023-11-28 02:09:19,040][87424] Updated weights for policy 0, policy_version 74196 (0.0009) -[2023-11-28 02:09:19,435][87424] Updated weights for policy 0, policy_version 74206 (0.0011) -[2023-11-28 02:09:20,223][87426] Updated weights for policy 1, policy_version 74090 (0.0008) -[2023-11-28 02:09:20,618][87426] Updated weights for policy 1, policy_version 74100 (0.0010) -[2023-11-28 02:09:20,994][87426] Updated weights for policy 1, policy_version 74110 (0.0012) -[2023-11-28 02:09:21,989][87424] Updated weights for policy 0, policy_version 74216 (0.0011) -[2023-11-28 02:09:22,366][87424] Updated weights for policy 0, policy_version 74226 (0.0012) -[2023-11-28 02:09:22,751][87424] Updated weights for policy 0, policy_version 74236 (0.0012) -[2023-11-28 02:09:23,339][87426] Updated weights for policy 1, policy_version 74120 (0.0010) -[2023-11-28 02:09:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 37978112. Throughput: 0: 2701.3, 1: 2712.3. Samples: 37993904. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:09:23,445][86177] Avg episode reward: [(0, '-562.770'), (1, '-539.200')] -[2023-11-28 02:09:23,716][87426] Updated weights for policy 1, policy_version 74130 (0.0007) -[2023-11-28 02:09:24,095][87426] Updated weights for policy 1, policy_version 74140 (0.0009) -[2023-11-28 02:09:25,420][87424] Updated weights for policy 0, policy_version 74246 (0.0012) -[2023-11-28 02:09:25,808][87424] Updated weights for policy 0, policy_version 74256 (0.0010) -[2023-11-28 02:09:26,191][87424] Updated weights for policy 0, policy_version 74266 (0.0010) -[2023-11-28 02:09:26,282][87426] Updated weights for policy 1, policy_version 74150 (0.0011) -[2023-11-28 02:09:26,666][87426] Updated weights for policy 1, policy_version 74160 (0.0012) -[2023-11-28 02:09:27,048][87426] Updated weights for policy 1, policy_version 74170 (0.0012) -[2023-11-28 02:09:28,397][87424] Updated weights for policy 0, policy_version 74276 (0.0008) -[2023-11-28 02:09:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 38002688. Throughput: 0: 2709.3, 1: 2747.7. Samples: 38019484. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:09:28,445][86177] Avg episode reward: [(0, '-561.300'), (1, '-543.680')] -[2023-11-28 02:09:28,785][87424] Updated weights for policy 0, policy_version 74286 (0.0008) -[2023-11-28 02:09:28,815][87426] Updated weights for policy 1, policy_version 74180 (0.0010) -[2023-11-28 02:09:29,173][87424] Updated weights for policy 0, policy_version 74296 (0.0008) -[2023-11-28 02:09:29,195][87426] Updated weights for policy 1, policy_version 74190 (0.0011) -[2023-11-28 02:09:29,579][87426] Updated weights for policy 1, policy_version 74200 (0.0011) -[2023-11-28 02:09:31,155][87424] Updated weights for policy 0, policy_version 74306 (0.0011) -[2023-11-28 02:09:31,525][87424] Updated weights for policy 0, policy_version 74316 (0.0011) -[2023-11-28 02:09:31,909][87424] Updated weights for policy 0, policy_version 74326 (0.0011) -[2023-11-28 02:09:32,047][87426] Updated weights for policy 1, policy_version 74210 (0.0010) -[2023-11-28 02:09:32,293][87424] Updated weights for policy 0, policy_version 74336 (0.0011) -[2023-11-28 02:09:32,433][87426] Updated weights for policy 1, policy_version 74220 (0.0011) -[2023-11-28 02:09:32,812][87426] Updated weights for policy 1, policy_version 74230 (0.0010) -[2023-11-28 02:09:33,194][87426] Updated weights for policy 1, policy_version 74240 (0.0008) -[2023-11-28 02:09:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 38035456. Throughput: 0: 2727.5, 1: 2749.2. Samples: 38044388. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:09:33,445][86177] Avg episode reward: [(0, '-558.180'), (1, '-560.360')] -[2023-11-28 02:09:34,687][87424] Updated weights for policy 0, policy_version 74346 (0.0011) -[2023-11-28 02:09:35,041][87424] Updated weights for policy 0, policy_version 74356 (0.0009) -[2023-11-28 02:09:35,407][87426] Updated weights for policy 1, policy_version 74250 (0.0010) -[2023-11-28 02:09:35,424][87424] Updated weights for policy 0, policy_version 74366 (0.0009) -[2023-11-28 02:09:35,784][87426] Updated weights for policy 1, policy_version 74260 (0.0008) -[2023-11-28 02:09:36,170][87426] Updated weights for policy 1, policy_version 74270 (0.0007) -[2023-11-28 02:09:37,367][87424] Updated weights for policy 0, policy_version 74376 (0.0011) -[2023-11-28 02:09:37,752][87424] Updated weights for policy 0, policy_version 74386 (0.0010) -[2023-11-28 02:09:38,132][87424] Updated weights for policy 0, policy_version 74396 (0.0008) -[2023-11-28 02:09:38,414][87426] Updated weights for policy 1, policy_version 74280 (0.0008) -[2023-11-28 02:09:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 38060032. Throughput: 0: 2718.3, 1: 2736.6. Samples: 38075896. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:09:38,445][86177] Avg episode reward: [(0, '-556.990'), (1, '-551.210')] -[2023-11-28 02:09:38,797][87426] Updated weights for policy 1, policy_version 74290 (0.0008) -[2023-11-28 02:09:39,199][87426] Updated weights for policy 1, policy_version 74300 (0.0010) -[2023-11-28 02:09:40,427][87424] Updated weights for policy 0, policy_version 74406 (0.0008) -[2023-11-28 02:09:40,812][87424] Updated weights for policy 0, policy_version 74416 (0.0008) -[2023-11-28 02:09:41,200][87424] Updated weights for policy 0, policy_version 74426 (0.0008) -[2023-11-28 02:09:41,651][87426] Updated weights for policy 1, policy_version 74310 (0.0011) -[2023-11-28 02:09:42,024][87426] Updated weights for policy 1, policy_version 74320 (0.0013) -[2023-11-28 02:09:42,405][87426] Updated weights for policy 1, policy_version 74330 (0.0008) -[2023-11-28 02:09:43,349][87424] Updated weights for policy 0, policy_version 74436 (0.0009) -[2023-11-28 02:09:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 38084608. Throughput: 0: 2710.4, 1: 2697.1. Samples: 38099484. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:09:43,445][86177] Avg episode reward: [(0, '-557.820'), (1, '-552.210')] -[2023-11-28 02:09:43,727][87424] Updated weights for policy 0, policy_version 74446 (0.0010) -[2023-11-28 02:09:44,120][87424] Updated weights for policy 0, policy_version 74456 (0.0011) -[2023-11-28 02:09:44,274][87426] Updated weights for policy 1, policy_version 74340 (0.0008) -[2023-11-28 02:09:44,660][87426] Updated weights for policy 1, policy_version 74350 (0.0008) -[2023-11-28 02:09:45,040][87426] Updated weights for policy 1, policy_version 74360 (0.0007) -[2023-11-28 02:09:46,155][87424] Updated weights for policy 0, policy_version 74466 (0.0011) -[2023-11-28 02:09:46,545][87424] Updated weights for policy 0, policy_version 74476 (0.0012) -[2023-11-28 02:09:46,926][87424] Updated weights for policy 0, policy_version 74486 (0.0012) -[2023-11-28 02:09:47,283][87426] Updated weights for policy 1, policy_version 74370 (0.0009) -[2023-11-28 02:09:47,302][87424] Updated weights for policy 0, policy_version 74496 (0.0011) -[2023-11-28 02:09:47,658][87426] Updated weights for policy 1, policy_version 74380 (0.0009) -[2023-11-28 02:09:48,033][87426] Updated weights for policy 1, policy_version 74390 (0.0007) -[2023-11-28 02:09:48,420][87426] Updated weights for policy 1, policy_version 74400 (0.0007) -[2023-11-28 02:09:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 38117376. Throughput: 0: 2663.1, 1: 2696.0. Samples: 38123508. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:09:48,445][86177] Avg episode reward: [(0, '-549.670'), (1, '-542.000')] -[2023-11-28 02:09:49,263][87424] Updated weights for policy 0, policy_version 74506 (0.0012) -[2023-11-28 02:09:49,646][87424] Updated weights for policy 0, policy_version 74516 (0.0011) -[2023-11-28 02:09:50,025][87424] Updated weights for policy 0, policy_version 74526 (0.0011) -[2023-11-28 02:09:50,491][87426] Updated weights for policy 1, policy_version 74410 (0.0011) -[2023-11-28 02:09:50,876][87426] Updated weights for policy 1, policy_version 74420 (0.0011) -[2023-11-28 02:09:51,257][87426] Updated weights for policy 1, policy_version 74430 (0.0012) -[2023-11-28 02:09:52,629][87424] Updated weights for policy 0, policy_version 74536 (0.0012) -[2023-11-28 02:09:53,003][87424] Updated weights for policy 0, policy_version 74546 (0.0011) -[2023-11-28 02:09:53,389][87424] Updated weights for policy 0, policy_version 74556 (0.0011) -[2023-11-28 02:09:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 38133760. Throughput: 0: 2656.8, 1: 2692.5. Samples: 38155248. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:09:53,445][86177] Avg episode reward: [(0, '-594.110'), (1, '-525.650')] -[2023-11-28 02:09:53,547][87426] Updated weights for policy 1, policy_version 74440 (0.0009) -[2023-11-28 02:09:53,926][87426] Updated weights for policy 1, policy_version 74450 (0.0009) -[2023-11-28 02:09:54,310][87426] Updated weights for policy 1, policy_version 74460 (0.0007) -[2023-11-28 02:09:55,941][87424] Updated weights for policy 0, policy_version 74566 (0.0008) -[2023-11-28 02:09:56,336][87424] Updated weights for policy 0, policy_version 74576 (0.0008) -[2023-11-28 02:09:56,429][87426] Updated weights for policy 1, policy_version 74470 (0.0008) -[2023-11-28 02:09:56,719][87424] Updated weights for policy 0, policy_version 74586 (0.0007) -[2023-11-28 02:09:56,819][87426] Updated weights for policy 1, policy_version 74480 (0.0007) -[2023-11-28 02:09:57,198][87426] Updated weights for policy 1, policy_version 74490 (0.0007) -[2023-11-28 02:09:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 38166528. Throughput: 0: 2639.8, 1: 2747.6. Samples: 38179912. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:09:58,445][86177] Avg episode reward: [(0, '-589.010'), (1, '-510.560')] -[2023-11-28 02:09:59,206][87424] Updated weights for policy 0, policy_version 74596 (0.0010) -[2023-11-28 02:09:59,296][87426] Updated weights for policy 1, policy_version 74500 (0.0008) -[2023-11-28 02:09:59,588][87424] Updated weights for policy 0, policy_version 74606 (0.0011) -[2023-11-28 02:09:59,675][87426] Updated weights for policy 1, policy_version 74510 (0.0008) -[2023-11-28 02:09:59,973][87424] Updated weights for policy 0, policy_version 74616 (0.0011) -[2023-11-28 02:10:00,057][87426] Updated weights for policy 1, policy_version 74520 (0.0010) -[2023-11-28 02:10:01,832][87426] Updated weights for policy 1, policy_version 74530 (0.0012) -[2023-11-28 02:10:02,209][87426] Updated weights for policy 1, policy_version 74540 (0.0011) -[2023-11-28 02:10:02,504][87424] Updated weights for policy 0, policy_version 74626 (0.0011) -[2023-11-28 02:10:02,594][87426] Updated weights for policy 1, policy_version 74550 (0.0011) -[2023-11-28 02:10:02,880][87424] Updated weights for policy 0, policy_version 74636 (0.0009) -[2023-11-28 02:10:02,975][87426] Updated weights for policy 1, policy_version 74560 (0.0011) -[2023-11-28 02:10:03,275][87424] Updated weights for policy 0, policy_version 74646 (0.0012) -[2023-11-28 02:10:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 38191104. Throughput: 0: 2629.8, 1: 2738.3. Samples: 38203932. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:10:03,445][86177] Avg episode reward: [(0, '-575.230'), (1, '-515.970')] -[2023-11-28 02:10:03,652][87424] Updated weights for policy 0, policy_version 74656 (0.0012) -[2023-11-28 02:10:05,035][87426] Updated weights for policy 1, policy_version 74570 (0.0012) -[2023-11-28 02:10:05,418][87426] Updated weights for policy 1, policy_version 74580 (0.0011) -[2023-11-28 02:10:05,800][87426] Updated weights for policy 1, policy_version 74590 (0.0011) -[2023-11-28 02:10:06,105][87424] Updated weights for policy 0, policy_version 74666 (0.0007) -[2023-11-28 02:10:06,493][87424] Updated weights for policy 0, policy_version 74676 (0.0008) -[2023-11-28 02:10:06,868][87424] Updated weights for policy 0, policy_version 74686 (0.0011) -[2023-11-28 02:10:08,049][87426] Updated weights for policy 1, policy_version 74600 (0.0012) -[2023-11-28 02:10:08,421][87426] Updated weights for policy 1, policy_version 74610 (0.0011) -[2023-11-28 02:10:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 38215680. Throughput: 0: 2659.2, 1: 2751.5. Samples: 38237384. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 02:10:08,445][86177] Avg episode reward: [(0, '-583.050'), (1, '-513.250')] -[2023-11-28 02:10:08,553][87424] Updated weights for policy 0, policy_version 74696 (0.0011) -[2023-11-28 02:10:08,804][87426] Updated weights for policy 1, policy_version 74620 (0.0007) -[2023-11-28 02:10:08,938][87424] Updated weights for policy 0, policy_version 74706 (0.0008) -[2023-11-28 02:10:09,322][87424] Updated weights for policy 0, policy_version 74716 (0.0007) -[2023-11-28 02:10:10,926][87426] Updated weights for policy 1, policy_version 74630 (0.0011) -[2023-11-28 02:10:11,192][87424] Updated weights for policy 0, policy_version 74726 (0.0009) -[2023-11-28 02:10:11,315][87426] Updated weights for policy 1, policy_version 74640 (0.0011) -[2023-11-28 02:10:11,567][87424] Updated weights for policy 0, policy_version 74736 (0.0008) -[2023-11-28 02:10:11,681][87426] Updated weights for policy 1, policy_version 74650 (0.0011) -[2023-11-28 02:10:11,948][87424] Updated weights for policy 0, policy_version 74746 (0.0012) -[2023-11-28 02:10:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 38248448. Throughput: 0: 2661.5, 1: 2734.5. Samples: 38262304. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:13,445][86177] Avg episode reward: [(0, '-536.690'), (1, '-519.980')] -[2023-11-28 02:10:13,759][87426] Updated weights for policy 1, policy_version 74660 (0.0009) -[2023-11-28 02:10:14,140][87426] Updated weights for policy 1, policy_version 74670 (0.0008) -[2023-11-28 02:10:14,259][87424] Updated weights for policy 0, policy_version 74756 (0.0012) -[2023-11-28 02:10:14,525][87426] Updated weights for policy 1, policy_version 74680 (0.0009) -[2023-11-28 02:10:14,646][87424] Updated weights for policy 0, policy_version 74766 (0.0011) -[2023-11-28 02:10:15,029][87424] Updated weights for policy 0, policy_version 74776 (0.0011) -[2023-11-28 02:10:16,922][87426] Updated weights for policy 1, policy_version 74690 (0.0008) -[2023-11-28 02:10:17,207][87424] Updated weights for policy 0, policy_version 74786 (0.0011) -[2023-11-28 02:10:17,304][87426] Updated weights for policy 1, policy_version 74700 (0.0012) -[2023-11-28 02:10:17,604][87424] Updated weights for policy 0, policy_version 74796 (0.0008) -[2023-11-28 02:10:17,679][87426] Updated weights for policy 1, policy_version 74710 (0.0011) -[2023-11-28 02:10:17,973][87424] Updated weights for policy 0, policy_version 74806 (0.0010) -[2023-11-28 02:10:18,051][87426] Updated weights for policy 1, policy_version 74720 (0.0011) -[2023-11-28 02:10:18,358][87424] Updated weights for policy 0, policy_version 74816 (0.0011) -[2023-11-28 02:10:18,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 38281216. Throughput: 0: 2640.5, 1: 2733.1. Samples: 38286204. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:18,446][86177] Avg episode reward: [(0, '-531.180'), (1, '-522.680')] -[2023-11-28 02:10:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000074816_19152896.pth... -[2023-11-28 02:10:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000074720_19128320.pth... -[2023-11-28 02:10:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000072192_18481152.pth -[2023-11-28 02:10:18,506][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000072288_18505728.pth -[2023-11-28 02:10:20,558][87426] Updated weights for policy 1, policy_version 74730 (0.0011) -[2023-11-28 02:10:20,782][87424] Updated weights for policy 0, policy_version 74826 (0.0011) -[2023-11-28 02:10:20,934][87426] Updated weights for policy 1, policy_version 74740 (0.0008) -[2023-11-28 02:10:21,166][87424] Updated weights for policy 0, policy_version 74836 (0.0011) -[2023-11-28 02:10:21,316][87426] Updated weights for policy 1, policy_version 74750 (0.0008) -[2023-11-28 02:10:21,559][87424] Updated weights for policy 0, policy_version 74846 (0.0011) -[2023-11-28 02:10:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 38297600. Throughput: 0: 2641.9, 1: 2736.4. Samples: 38317916. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:23,445][86177] Avg episode reward: [(0, '-575.120'), (1, '-523.960')] -[2023-11-28 02:10:23,545][87426] Updated weights for policy 1, policy_version 74760 (0.0011) -[2023-11-28 02:10:23,811][87424] Updated weights for policy 0, policy_version 74856 (0.0011) -[2023-11-28 02:10:23,914][87426] Updated weights for policy 1, policy_version 74770 (0.0011) -[2023-11-28 02:10:24,196][87424] Updated weights for policy 0, policy_version 74866 (0.0011) -[2023-11-28 02:10:24,296][87426] Updated weights for policy 1, policy_version 74780 (0.0011) -[2023-11-28 02:10:24,571][87424] Updated weights for policy 0, policy_version 74876 (0.0011) -[2023-11-28 02:10:26,308][87424] Updated weights for policy 0, policy_version 74886 (0.0012) -[2023-11-28 02:10:26,476][87426] Updated weights for policy 1, policy_version 74790 (0.0011) -[2023-11-28 02:10:26,691][87424] Updated weights for policy 0, policy_version 74896 (0.0011) -[2023-11-28 02:10:26,854][87426] Updated weights for policy 1, policy_version 74800 (0.0011) -[2023-11-28 02:10:27,077][87424] Updated weights for policy 0, policy_version 74906 (0.0012) -[2023-11-28 02:10:27,233][87426] Updated weights for policy 1, policy_version 74810 (0.0011) -[2023-11-28 02:10:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 38330368. Throughput: 0: 2664.0, 1: 2752.3. Samples: 38343216. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:28,445][86177] Avg episode reward: [(0, '-586.420'), (1, '-513.820')] -[2023-11-28 02:10:28,770][87424] Updated weights for policy 0, policy_version 74916 (0.0011) -[2023-11-28 02:10:29,043][87426] Updated weights for policy 1, policy_version 74820 (0.0011) -[2023-11-28 02:10:29,154][87424] Updated weights for policy 0, policy_version 74926 (0.0009) -[2023-11-28 02:10:29,425][87426] Updated weights for policy 1, policy_version 74830 (0.0011) -[2023-11-28 02:10:29,546][87424] Updated weights for policy 0, policy_version 74936 (0.0009) -[2023-11-28 02:10:29,800][87426] Updated weights for policy 1, policy_version 74840 (0.0011) -[2023-11-28 02:10:31,547][87424] Updated weights for policy 0, policy_version 74946 (0.0008) -[2023-11-28 02:10:31,698][87426] Updated weights for policy 1, policy_version 74850 (0.0011) -[2023-11-28 02:10:31,928][87424] Updated weights for policy 0, policy_version 74956 (0.0012) -[2023-11-28 02:10:32,086][87426] Updated weights for policy 1, policy_version 74860 (0.0010) -[2023-11-28 02:10:32,325][87424] Updated weights for policy 0, policy_version 74966 (0.0012) -[2023-11-28 02:10:32,469][87426] Updated weights for policy 1, policy_version 74870 (0.0010) -[2023-11-28 02:10:32,709][87424] Updated weights for policy 0, policy_version 74976 (0.0009) -[2023-11-28 02:10:32,839][87426] Updated weights for policy 1, policy_version 74880 (0.0011) -[2023-11-28 02:10:33,445][86177] Fps is (10 sec: 6553.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 38363136. Throughput: 0: 2720.8, 1: 2761.7. Samples: 38370220. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:33,446][86177] Avg episode reward: [(0, '-600.220'), (1, '-515.290')] -[2023-11-28 02:10:34,613][87424] Updated weights for policy 0, policy_version 74986 (0.0009) -[2023-11-28 02:10:35,000][87424] Updated weights for policy 0, policy_version 74996 (0.0009) -[2023-11-28 02:10:35,311][87426] Updated weights for policy 1, policy_version 74890 (0.0012) -[2023-11-28 02:10:35,378][87424] Updated weights for policy 0, policy_version 75006 (0.0007) -[2023-11-28 02:10:35,686][87426] Updated weights for policy 1, policy_version 74900 (0.0010) -[2023-11-28 02:10:36,069][87426] Updated weights for policy 1, policy_version 74910 (0.0008) -[2023-11-28 02:10:37,791][87424] Updated weights for policy 0, policy_version 75016 (0.0008) -[2023-11-28 02:10:38,181][87424] Updated weights for policy 0, policy_version 75026 (0.0008) -[2023-11-28 02:10:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 38379520. Throughput: 0: 2772.6, 1: 2765.5. Samples: 38404464. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:38,445][86177] Avg episode reward: [(0, '-560.460'), (1, '-533.310')] -[2023-11-28 02:10:38,511][87426] Updated weights for policy 1, policy_version 74920 (0.0008) -[2023-11-28 02:10:38,568][87424] Updated weights for policy 0, policy_version 75036 (0.0007) -[2023-11-28 02:10:38,887][87426] Updated weights for policy 1, policy_version 74930 (0.0008) -[2023-11-28 02:10:39,272][87426] Updated weights for policy 1, policy_version 74940 (0.0011) -[2023-11-28 02:10:40,381][87424] Updated weights for policy 0, policy_version 75046 (0.0009) -[2023-11-28 02:10:40,757][87424] Updated weights for policy 0, policy_version 75056 (0.0012) -[2023-11-28 02:10:41,145][87424] Updated weights for policy 0, policy_version 75066 (0.0012) -[2023-11-28 02:10:41,788][87426] Updated weights for policy 1, policy_version 74950 (0.0011) -[2023-11-28 02:10:42,183][87426] Updated weights for policy 1, policy_version 74960 (0.0010) -[2023-11-28 02:10:42,566][87426] Updated weights for policy 1, policy_version 74970 (0.0012) -[2023-11-28 02:10:43,229][87424] Updated weights for policy 0, policy_version 75076 (0.0012) -[2023-11-28 02:10:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 38412288. Throughput: 0: 2786.7, 1: 2717.4. Samples: 38427600. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:43,446][86177] Avg episode reward: [(0, '-566.520'), (1, '-550.300')] -[2023-11-28 02:10:43,617][87424] Updated weights for policy 0, policy_version 75086 (0.0012) -[2023-11-28 02:10:43,992][87424] Updated weights for policy 0, policy_version 75096 (0.0012) -[2023-11-28 02:10:44,488][87426] Updated weights for policy 1, policy_version 74980 (0.0012) -[2023-11-28 02:10:44,868][87426] Updated weights for policy 1, policy_version 74990 (0.0012) -[2023-11-28 02:10:45,244][87426] Updated weights for policy 1, policy_version 75000 (0.0012) -[2023-11-28 02:10:46,222][87424] Updated weights for policy 0, policy_version 75106 (0.0012) -[2023-11-28 02:10:46,613][87424] Updated weights for policy 0, policy_version 75116 (0.0010) -[2023-11-28 02:10:46,989][87424] Updated weights for policy 0, policy_version 75126 (0.0007) -[2023-11-28 02:10:47,001][87426] Updated weights for policy 1, policy_version 75010 (0.0012) -[2023-11-28 02:10:47,372][87424] Updated weights for policy 0, policy_version 75136 (0.0010) -[2023-11-28 02:10:47,383][87426] Updated weights for policy 1, policy_version 75020 (0.0012) -[2023-11-28 02:10:47,764][87426] Updated weights for policy 1, policy_version 75030 (0.0007) -[2023-11-28 02:10:48,146][87426] Updated weights for policy 1, policy_version 75040 (0.0009) -[2023-11-28 02:10:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 38445056. Throughput: 0: 2803.8, 1: 2733.4. Samples: 38453108. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:48,445][86177] Avg episode reward: [(0, '-561.730'), (1, '-566.400')] -[2023-11-28 02:10:49,403][87424] Updated weights for policy 0, policy_version 75146 (0.0008) -[2023-11-28 02:10:49,786][87424] Updated weights for policy 0, policy_version 75156 (0.0008) -[2023-11-28 02:10:50,169][87424] Updated weights for policy 0, policy_version 75166 (0.0008) -[2023-11-28 02:10:50,607][87426] Updated weights for policy 1, policy_version 75050 (0.0010) -[2023-11-28 02:10:50,986][87426] Updated weights for policy 1, policy_version 75060 (0.0012) -[2023-11-28 02:10:51,370][87426] Updated weights for policy 1, policy_version 75070 (0.0011) -[2023-11-28 02:10:52,511][87424] Updated weights for policy 0, policy_version 75176 (0.0009) -[2023-11-28 02:10:52,895][87424] Updated weights for policy 0, policy_version 75186 (0.0009) -[2023-11-28 02:10:53,282][87424] Updated weights for policy 0, policy_version 75196 (0.0011) -[2023-11-28 02:10:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 38469632. Throughput: 0: 2821.5, 1: 2714.3. Samples: 38486496. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:53,445][86177] Avg episode reward: [(0, '-559.030'), (1, '-588.020')] -[2023-11-28 02:10:53,588][87426] Updated weights for policy 1, policy_version 75080 (0.0011) -[2023-11-28 02:10:53,960][87426] Updated weights for policy 1, policy_version 75090 (0.0010) -[2023-11-28 02:10:54,347][87426] Updated weights for policy 1, policy_version 75100 (0.0010) -[2023-11-28 02:10:55,216][87424] Updated weights for policy 0, policy_version 75206 (0.0011) -[2023-11-28 02:10:55,609][87424] Updated weights for policy 0, policy_version 75216 (0.0011) -[2023-11-28 02:10:55,975][87424] Updated weights for policy 0, policy_version 75226 (0.0012) -[2023-11-28 02:10:57,019][87426] Updated weights for policy 1, policy_version 75110 (0.0008) -[2023-11-28 02:10:57,410][87426] Updated weights for policy 1, policy_version 75120 (0.0008) -[2023-11-28 02:10:57,794][87426] Updated weights for policy 1, policy_version 75130 (0.0007) -[2023-11-28 02:10:58,401][87424] Updated weights for policy 0, policy_version 75236 (0.0012) -[2023-11-28 02:10:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 38494208. Throughput: 0: 2812.2, 1: 2680.3. Samples: 38509468. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 02:10:58,445][86177] Avg episode reward: [(0, '-549.910'), (1, '-559.220')] -[2023-11-28 02:10:58,787][87424] Updated weights for policy 0, policy_version 75246 (0.0011) -[2023-11-28 02:10:59,176][87424] Updated weights for policy 0, policy_version 75256 (0.0011) -[2023-11-28 02:10:59,776][87426] Updated weights for policy 1, policy_version 75140 (0.0009) -[2023-11-28 02:11:00,161][87426] Updated weights for policy 1, policy_version 75150 (0.0012) -[2023-11-28 02:11:00,529][87426] Updated weights for policy 1, policy_version 75160 (0.0012) -[2023-11-28 02:11:00,966][87424] Updated weights for policy 0, policy_version 75266 (0.0011) -[2023-11-28 02:11:01,355][87424] Updated weights for policy 0, policy_version 75276 (0.0011) -[2023-11-28 02:11:01,727][87424] Updated weights for policy 0, policy_version 75286 (0.0011) -[2023-11-28 02:11:02,114][87424] Updated weights for policy 0, policy_version 75296 (0.0009) -[2023-11-28 02:11:03,127][87426] Updated weights for policy 1, policy_version 75170 (0.0011) -[2023-11-28 02:11:03,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 38518784. Throughput: 0: 2816.8, 1: 2683.9. Samples: 38533736. Policy #0 lag: (min: 35.0, avg: 51.9, max: 80.0) -[2023-11-28 02:11:03,446][86177] Avg episode reward: [(0, '-537.640'), (1, '-551.900')] -[2023-11-28 02:11:03,504][87426] Updated weights for policy 1, policy_version 75180 (0.0011) -[2023-11-28 02:11:03,886][87426] Updated weights for policy 1, policy_version 75190 (0.0012) -[2023-11-28 02:11:03,903][87424] Updated weights for policy 0, policy_version 75306 (0.0011) -[2023-11-28 02:11:04,261][87426] Updated weights for policy 1, policy_version 75200 (0.0011) -[2023-11-28 02:11:04,284][87424] Updated weights for policy 0, policy_version 75316 (0.0011) -[2023-11-28 02:11:04,662][87424] Updated weights for policy 0, policy_version 75326 (0.0009) -[2023-11-28 02:11:06,080][87426] Updated weights for policy 1, policy_version 75210 (0.0012) -[2023-11-28 02:11:06,460][87426] Updated weights for policy 1, policy_version 75220 (0.0012) -[2023-11-28 02:11:06,834][87426] Updated weights for policy 1, policy_version 75230 (0.0011) -[2023-11-28 02:11:07,150][87424] Updated weights for policy 0, policy_version 75336 (0.0011) -[2023-11-28 02:11:07,531][87424] Updated weights for policy 0, policy_version 75346 (0.0011) -[2023-11-28 02:11:07,914][87424] Updated weights for policy 0, policy_version 75356 (0.0007) -[2023-11-28 02:11:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 38551552. Throughput: 0: 2807.3, 1: 2698.0. Samples: 38565656. Policy #0 lag: (min: 35.0, avg: 51.9, max: 80.0) -[2023-11-28 02:11:08,446][86177] Avg episode reward: [(0, '-529.690'), (1, '-535.670')] -[2023-11-28 02:11:09,311][87426] Updated weights for policy 1, policy_version 75240 (0.0011) -[2023-11-28 02:11:09,695][87426] Updated weights for policy 1, policy_version 75250 (0.0012) -[2023-11-28 02:11:10,070][87426] Updated weights for policy 1, policy_version 75260 (0.0009) -[2023-11-28 02:11:10,101][87424] Updated weights for policy 0, policy_version 75366 (0.0009) -[2023-11-28 02:11:10,493][87424] Updated weights for policy 0, policy_version 75376 (0.0011) -[2023-11-28 02:11:10,867][87424] Updated weights for policy 0, policy_version 75386 (0.0011) -[2023-11-28 02:11:11,853][87426] Updated weights for policy 1, policy_version 75270 (0.0010) -[2023-11-28 02:11:12,231][87426] Updated weights for policy 1, policy_version 75280 (0.0010) -[2023-11-28 02:11:12,613][87426] Updated weights for policy 1, policy_version 75290 (0.0009) -[2023-11-28 02:11:13,366][87424] Updated weights for policy 0, policy_version 75396 (0.0010) -[2023-11-28 02:11:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 38576128. Throughput: 0: 2795.5, 1: 2669.1. Samples: 38589124. Policy #0 lag: (min: 35.0, avg: 51.9, max: 80.0) -[2023-11-28 02:11:13,445][86177] Avg episode reward: [(0, '-519.170'), (1, '-520.570')] -[2023-11-28 02:11:13,748][87424] Updated weights for policy 0, policy_version 75406 (0.0012) -[2023-11-28 02:11:14,135][87424] Updated weights for policy 0, policy_version 75416 (0.0012) -[2023-11-28 02:11:15,236][87426] Updated weights for policy 1, policy_version 75300 (0.0009) -[2023-11-28 02:11:15,613][87426] Updated weights for policy 1, policy_version 75310 (0.0010) -[2023-11-28 02:11:15,994][87426] Updated weights for policy 1, policy_version 75320 (0.0011) -[2023-11-28 02:11:16,704][87424] Updated weights for policy 0, policy_version 75426 (0.0011) -[2023-11-28 02:11:17,082][87424] Updated weights for policy 0, policy_version 75436 (0.0008) -[2023-11-28 02:11:17,465][87424] Updated weights for policy 0, policy_version 75446 (0.0008) -[2023-11-28 02:11:17,848][87424] Updated weights for policy 0, policy_version 75456 (0.0008) -[2023-11-28 02:11:18,412][87426] Updated weights for policy 1, policy_version 75330 (0.0008) -[2023-11-28 02:11:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 38600704. Throughput: 0: 2736.7, 1: 2642.8. Samples: 38612296. Policy #0 lag: (min: 35.0, avg: 51.9, max: 80.0) -[2023-11-28 02:11:18,445][86177] Avg episode reward: [(0, '-533.870'), (1, '-520.070')] -[2023-11-28 02:11:18,795][87426] Updated weights for policy 1, policy_version 75340 (0.0008) -[2023-11-28 02:11:19,175][87426] Updated weights for policy 1, policy_version 75350 (0.0008) -[2023-11-28 02:11:19,558][87426] Updated weights for policy 1, policy_version 75360 (0.0008) -[2023-11-28 02:11:19,809][87424] Updated weights for policy 0, policy_version 75466 (0.0012) -[2023-11-28 02:11:20,191][87424] Updated weights for policy 0, policy_version 75476 (0.0012) -[2023-11-28 02:11:20,579][87424] Updated weights for policy 0, policy_version 75486 (0.0012) -[2023-11-28 02:11:21,649][87426] Updated weights for policy 1, policy_version 75370 (0.0012) -[2023-11-28 02:11:22,025][87426] Updated weights for policy 1, policy_version 75380 (0.0012) -[2023-11-28 02:11:22,412][87426] Updated weights for policy 1, policy_version 75390 (0.0011) -[2023-11-28 02:11:22,886][87424] Updated weights for policy 0, policy_version 75496 (0.0012) -[2023-11-28 02:11:23,272][87424] Updated weights for policy 0, policy_version 75506 (0.0010) -[2023-11-28 02:11:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 38625280. Throughput: 0: 2691.0, 1: 2635.0. Samples: 38644136. Policy #0 lag: (min: 35.0, avg: 51.9, max: 80.0) -[2023-11-28 02:11:23,445][86177] Avg episode reward: [(0, '-533.240'), (1, '-528.810')] -[2023-11-28 02:11:23,664][87424] Updated weights for policy 0, policy_version 75516 (0.0010) -[2023-11-28 02:11:24,481][87426] Updated weights for policy 1, policy_version 75400 (0.0012) -[2023-11-28 02:11:24,858][87426] Updated weights for policy 1, policy_version 75410 (0.0012) -[2023-11-28 02:11:25,241][87426] Updated weights for policy 1, policy_version 75420 (0.0012) -[2023-11-28 02:11:25,658][87424] Updated weights for policy 0, policy_version 75526 (0.0010) -[2023-11-28 02:11:26,039][87424] Updated weights for policy 0, policy_version 75536 (0.0012) -[2023-11-28 02:11:26,421][87424] Updated weights for policy 0, policy_version 75546 (0.0012) -[2023-11-28 02:11:27,163][87426] Updated weights for policy 1, policy_version 75430 (0.0012) -[2023-11-28 02:11:27,546][87426] Updated weights for policy 1, policy_version 75440 (0.0011) -[2023-11-28 02:11:27,914][87426] Updated weights for policy 1, policy_version 75450 (0.0012) -[2023-11-28 02:11:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 38658048. Throughput: 0: 2696.6, 1: 2683.3. Samples: 38669696. Policy #0 lag: (min: 35.0, avg: 51.9, max: 80.0) -[2023-11-28 02:11:28,445][86177] Avg episode reward: [(0, '-550.020'), (1, '-531.140')] -[2023-11-28 02:11:28,651][87424] Updated weights for policy 0, policy_version 75556 (0.0012) -[2023-11-28 02:11:29,033][87424] Updated weights for policy 0, policy_version 75566 (0.0010) -[2023-11-28 02:11:29,421][87424] Updated weights for policy 0, policy_version 75576 (0.0011) -[2023-11-28 02:11:29,743][87426] Updated weights for policy 1, policy_version 75460 (0.0012) -[2023-11-28 02:11:30,127][87426] Updated weights for policy 1, policy_version 75470 (0.0012) -[2023-11-28 02:11:30,500][87426] Updated weights for policy 1, policy_version 75480 (0.0011) -[2023-11-28 02:11:31,281][87424] Updated weights for policy 0, policy_version 75586 (0.0010) -[2023-11-28 02:11:31,674][87424] Updated weights for policy 0, policy_version 75596 (0.0008) -[2023-11-28 02:11:32,048][87424] Updated weights for policy 0, policy_version 75606 (0.0008) -[2023-11-28 02:11:32,432][87424] Updated weights for policy 0, policy_version 75616 (0.0010) -[2023-11-28 02:11:32,737][87426] Updated weights for policy 1, policy_version 75490 (0.0010) -[2023-11-28 02:11:33,112][87426] Updated weights for policy 1, policy_version 75500 (0.0008) -[2023-11-28 02:11:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 38682624. Throughput: 0: 2715.3, 1: 2678.8. Samples: 38695840. Policy #0 lag: (min: 35.0, avg: 51.9, max: 80.0) -[2023-11-28 02:11:33,445][86177] Avg episode reward: [(0, '-557.550'), (1, '-535.920')] -[2023-11-28 02:11:33,492][87426] Updated weights for policy 1, policy_version 75510 (0.0007) -[2023-11-28 02:11:33,879][87426] Updated weights for policy 1, policy_version 75520 (0.0007) -[2023-11-28 02:11:34,478][87424] Updated weights for policy 0, policy_version 75626 (0.0008) -[2023-11-28 02:11:34,851][87424] Updated weights for policy 0, policy_version 75636 (0.0008) -[2023-11-28 02:11:35,232][87424] Updated weights for policy 0, policy_version 75646 (0.0008) -[2023-11-28 02:11:36,119][87426] Updated weights for policy 1, policy_version 75530 (0.0012) -[2023-11-28 02:11:36,486][87426] Updated weights for policy 1, policy_version 75540 (0.0012) -[2023-11-28 02:11:36,863][87426] Updated weights for policy 1, policy_version 75550 (0.0011) -[2023-11-28 02:11:37,376][87424] Updated weights for policy 0, policy_version 75656 (0.0011) -[2023-11-28 02:11:37,760][87424] Updated weights for policy 0, policy_version 75666 (0.0012) -[2023-11-28 02:11:38,134][87424] Updated weights for policy 0, policy_version 75676 (0.0011) -[2023-11-28 02:11:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 38715392. Throughput: 0: 2688.5, 1: 2664.4. Samples: 38727376. Policy #0 lag: (min: 35.0, avg: 51.9, max: 80.0) -[2023-11-28 02:11:38,445][86177] Avg episode reward: [(0, '-567.590'), (1, '-518.500')] -[2023-11-28 02:11:39,493][87426] Updated weights for policy 1, policy_version 75560 (0.0008) -[2023-11-28 02:11:39,874][87426] Updated weights for policy 1, policy_version 75570 (0.0008) -[2023-11-28 02:11:40,256][87426] Updated weights for policy 1, policy_version 75580 (0.0010) -[2023-11-28 02:11:40,582][87424] Updated weights for policy 0, policy_version 75686 (0.0010) -[2023-11-28 02:11:40,956][87424] Updated weights for policy 0, policy_version 75696 (0.0011) -[2023-11-28 02:11:41,337][87424] Updated weights for policy 0, policy_version 75706 (0.0009) -[2023-11-28 02:11:42,470][87426] Updated weights for policy 1, policy_version 75590 (0.0009) -[2023-11-28 02:11:42,840][87426] Updated weights for policy 1, policy_version 75600 (0.0007) -[2023-11-28 02:11:43,219][87426] Updated weights for policy 1, policy_version 75610 (0.0012) -[2023-11-28 02:11:43,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 38739968. Throughput: 0: 2674.0, 1: 2697.6. Samples: 38751192. Policy #0 lag: (min: 35.0, avg: 51.9, max: 80.0) -[2023-11-28 02:11:43,446][86177] Avg episode reward: [(0, '-552.120'), (1, '-512.120')] -[2023-11-28 02:11:43,767][87424] Updated weights for policy 0, policy_version 75716 (0.0009) -[2023-11-28 02:11:44,146][87424] Updated weights for policy 0, policy_version 75726 (0.0009) -[2023-11-28 02:11:44,528][87424] Updated weights for policy 0, policy_version 75736 (0.0007) -[2023-11-28 02:11:45,187][87426] Updated weights for policy 1, policy_version 75620 (0.0012) -[2023-11-28 02:11:45,560][87426] Updated weights for policy 1, policy_version 75630 (0.0009) -[2023-11-28 02:11:45,938][87426] Updated weights for policy 1, policy_version 75640 (0.0007) -[2023-11-28 02:11:46,948][87424] Updated weights for policy 0, policy_version 75746 (0.0010) -[2023-11-28 02:11:47,330][87424] Updated weights for policy 0, policy_version 75756 (0.0009) -[2023-11-28 02:11:47,708][87424] Updated weights for policy 0, policy_version 75766 (0.0009) -[2023-11-28 02:11:48,099][87424] Updated weights for policy 0, policy_version 75776 (0.0008) -[2023-11-28 02:11:48,125][87426] Updated weights for policy 1, policy_version 75650 (0.0008) -[2023-11-28 02:11:48,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 38764544. Throughput: 0: 2654.5, 1: 2706.2. Samples: 38774968. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:11:48,446][86177] Avg episode reward: [(0, '-538.780'), (1, '-522.420')] -[2023-11-28 02:11:48,499][87426] Updated weights for policy 1, policy_version 75660 (0.0011) -[2023-11-28 02:11:48,876][87426] Updated weights for policy 1, policy_version 75670 (0.0012) -[2023-11-28 02:11:49,254][87426] Updated weights for policy 1, policy_version 75680 (0.0011) -[2023-11-28 02:11:50,467][87424] Updated weights for policy 0, policy_version 75786 (0.0011) -[2023-11-28 02:11:50,852][87424] Updated weights for policy 0, policy_version 75796 (0.0009) -[2023-11-28 02:11:51,237][87424] Updated weights for policy 0, policy_version 75806 (0.0009) -[2023-11-28 02:11:51,577][87426] Updated weights for policy 1, policy_version 75690 (0.0011) -[2023-11-28 02:11:51,963][87426] Updated weights for policy 1, policy_version 75700 (0.0009) -[2023-11-28 02:11:52,352][87426] Updated weights for policy 1, policy_version 75710 (0.0011) -[2023-11-28 02:11:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 38789120. Throughput: 0: 2649.6, 1: 2703.6. Samples: 38806548. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:11:53,445][86177] Avg episode reward: [(0, '-530.940'), (1, '-521.130')] -[2023-11-28 02:11:53,729][87424] Updated weights for policy 0, policy_version 75816 (0.0012) -[2023-11-28 02:11:54,108][87424] Updated weights for policy 0, policy_version 75826 (0.0009) -[2023-11-28 02:11:54,485][87424] Updated weights for policy 0, policy_version 75836 (0.0007) -[2023-11-28 02:11:54,652][87426] Updated weights for policy 1, policy_version 75720 (0.0011) -[2023-11-28 02:11:55,039][87426] Updated weights for policy 1, policy_version 75730 (0.0012) -[2023-11-28 02:11:55,416][87426] Updated weights for policy 1, policy_version 75740 (0.0008) -[2023-11-28 02:11:56,839][87424] Updated weights for policy 0, policy_version 75846 (0.0008) -[2023-11-28 02:11:57,214][87424] Updated weights for policy 0, policy_version 75856 (0.0007) -[2023-11-28 02:11:57,582][87426] Updated weights for policy 1, policy_version 75750 (0.0008) -[2023-11-28 02:11:57,594][87424] Updated weights for policy 0, policy_version 75866 (0.0008) -[2023-11-28 02:11:57,958][87426] Updated weights for policy 1, policy_version 75760 (0.0009) -[2023-11-28 02:11:58,348][87426] Updated weights for policy 1, policy_version 75770 (0.0012) -[2023-11-28 02:11:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 38813696. Throughput: 0: 2643.7, 1: 2730.0. Samples: 38830936. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:11:58,445][86177] Avg episode reward: [(0, '-530.440'), (1, '-519.030')] -[2023-11-28 02:11:59,540][87424] Updated weights for policy 0, policy_version 75876 (0.0007) -[2023-11-28 02:11:59,931][87424] Updated weights for policy 0, policy_version 75886 (0.0009) -[2023-11-28 02:11:59,965][87426] Updated weights for policy 1, policy_version 75780 (0.0011) -[2023-11-28 02:12:00,312][87424] Updated weights for policy 0, policy_version 75896 (0.0011) -[2023-11-28 02:12:00,342][87426] Updated weights for policy 1, policy_version 75790 (0.0011) -[2023-11-28 02:12:00,714][87426] Updated weights for policy 1, policy_version 75800 (0.0011) -[2023-11-28 02:12:02,779][87424] Updated weights for policy 0, policy_version 75906 (0.0010) -[2023-11-28 02:12:03,161][87424] Updated weights for policy 0, policy_version 75916 (0.0014) -[2023-11-28 02:12:03,315][87426] Updated weights for policy 1, policy_version 75810 (0.0011) -[2023-11-28 02:12:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 38838272. Throughput: 0: 2659.9, 1: 2730.0. Samples: 38854840. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:12:03,445][86177] Avg episode reward: [(0, '-533.950'), (1, '-518.360')] -[2023-11-28 02:12:03,543][87424] Updated weights for policy 0, policy_version 75926 (0.0010) -[2023-11-28 02:12:03,694][87426] Updated weights for policy 1, policy_version 75820 (0.0011) -[2023-11-28 02:12:03,932][87424] Updated weights for policy 0, policy_version 75936 (0.0012) -[2023-11-28 02:12:04,065][87426] Updated weights for policy 1, policy_version 75830 (0.0007) -[2023-11-28 02:12:04,447][87426] Updated weights for policy 1, policy_version 75840 (0.0007) -[2023-11-28 02:12:06,042][87424] Updated weights for policy 0, policy_version 75946 (0.0012) -[2023-11-28 02:12:06,419][87424] Updated weights for policy 0, policy_version 75956 (0.0012) -[2023-11-28 02:12:06,797][87424] Updated weights for policy 0, policy_version 75966 (0.0010) -[2023-11-28 02:12:06,904][87426] Updated weights for policy 1, policy_version 75850 (0.0012) -[2023-11-28 02:12:07,290][87426] Updated weights for policy 1, policy_version 75860 (0.0011) -[2023-11-28 02:12:07,664][87426] Updated weights for policy 1, policy_version 75870 (0.0012) -[2023-11-28 02:12:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 38871040. Throughput: 0: 2671.4, 1: 2723.5. Samples: 38886904. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:12:08,445][86177] Avg episode reward: [(0, '-534.330'), (1, '-512.920')] -[2023-11-28 02:12:09,443][87424] Updated weights for policy 0, policy_version 75976 (0.0012) -[2023-11-28 02:12:09,738][87426] Updated weights for policy 1, policy_version 75880 (0.0011) -[2023-11-28 02:12:09,814][87424] Updated weights for policy 0, policy_version 75986 (0.0011) -[2023-11-28 02:12:10,120][87426] Updated weights for policy 1, policy_version 75890 (0.0011) -[2023-11-28 02:12:10,204][87424] Updated weights for policy 0, policy_version 75996 (0.0012) -[2023-11-28 02:12:10,494][87426] Updated weights for policy 1, policy_version 75900 (0.0011) -[2023-11-28 02:12:12,122][87424] Updated weights for policy 0, policy_version 76006 (0.0011) -[2023-11-28 02:12:12,505][87424] Updated weights for policy 0, policy_version 76016 (0.0010) -[2023-11-28 02:12:12,891][87424] Updated weights for policy 0, policy_version 76026 (0.0011) -[2023-11-28 02:12:13,117][87426] Updated weights for policy 1, policy_version 75910 (0.0012) -[2023-11-28 02:12:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 38895616. Throughput: 0: 2664.4, 1: 2680.1. Samples: 38910200. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:12:13,445][86177] Avg episode reward: [(0, '-537.400'), (1, '-548.640')] -[2023-11-28 02:12:13,491][87426] Updated weights for policy 1, policy_version 75920 (0.0012) -[2023-11-28 02:12:13,871][87426] Updated weights for policy 1, policy_version 75930 (0.0012) -[2023-11-28 02:12:14,805][87424] Updated weights for policy 0, policy_version 76036 (0.0012) -[2023-11-28 02:12:15,194][87424] Updated weights for policy 0, policy_version 76046 (0.0012) -[2023-11-28 02:12:15,566][87424] Updated weights for policy 0, policy_version 76056 (0.0012) -[2023-11-28 02:12:16,114][87426] Updated weights for policy 1, policy_version 75940 (0.0012) -[2023-11-28 02:12:16,492][87426] Updated weights for policy 1, policy_version 75950 (0.0012) -[2023-11-28 02:12:16,871][87426] Updated weights for policy 1, policy_version 75960 (0.0012) -[2023-11-28 02:12:17,578][87424] Updated weights for policy 0, policy_version 76066 (0.0011) -[2023-11-28 02:12:17,959][87424] Updated weights for policy 0, policy_version 76076 (0.0008) -[2023-11-28 02:12:18,349][87424] Updated weights for policy 0, policy_version 76086 (0.0011) -[2023-11-28 02:12:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 38920192. Throughput: 0: 2647.1, 1: 2673.1. Samples: 38935248. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:12:18,445][86177] Avg episode reward: [(0, '-531.490'), (1, '-556.630')] -[2023-11-28 02:12:18,475][87426] Updated weights for policy 1, policy_version 75970 (0.0012) -[2023-11-28 02:12:18,722][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000076096_19480576.pth... -[2023-11-28 02:12:18,729][87424] Updated weights for policy 0, policy_version 76096 (0.0012) -[2023-11-28 02:12:18,763][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000073568_18833408.pth -[2023-11-28 02:12:18,769][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000076096_19480576.pth -[2023-11-28 02:12:18,858][87426] Updated weights for policy 1, policy_version 75980 (0.0012) -[2023-11-28 02:12:19,237][87426] Updated weights for policy 1, policy_version 75990 (0.0009) -[2023-11-28 02:12:19,625][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000076000_19456000.pth... -[2023-11-28 02:12:19,626][87426] Updated weights for policy 1, policy_version 76000 (0.0008) -[2023-11-28 02:12:19,671][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000073440_18800640.pth -[2023-11-28 02:12:19,678][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000076000_19456000.pth -[2023-11-28 02:12:21,198][87424] Updated weights for policy 0, policy_version 76106 (0.0011) -[2023-11-28 02:12:21,589][87424] Updated weights for policy 0, policy_version 76116 (0.0011) -[2023-11-28 02:12:21,911][87426] Updated weights for policy 1, policy_version 76010 (0.0010) -[2023-11-28 02:12:21,962][87424] Updated weights for policy 0, policy_version 76126 (0.0012) -[2023-11-28 02:12:22,283][87426] Updated weights for policy 1, policy_version 76020 (0.0012) -[2023-11-28 02:12:22,661][87426] Updated weights for policy 1, policy_version 76030 (0.0009) -[2023-11-28 02:12:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 38952960. Throughput: 0: 2636.0, 1: 2686.3. Samples: 38966880. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:12:23,445][86177] Avg episode reward: [(0, '-530.930'), (1, '-554.990')] -[2023-11-28 02:12:24,486][87424] Updated weights for policy 0, policy_version 76136 (0.0012) -[2023-11-28 02:12:24,861][87424] Updated weights for policy 0, policy_version 76146 (0.0012) -[2023-11-28 02:12:24,948][87426] Updated weights for policy 1, policy_version 76040 (0.0009) -[2023-11-28 02:12:25,247][87424] Updated weights for policy 0, policy_version 76156 (0.0010) -[2023-11-28 02:12:25,325][87426] Updated weights for policy 1, policy_version 76050 (0.0010) -[2023-11-28 02:12:25,699][87426] Updated weights for policy 1, policy_version 76060 (0.0012) -[2023-11-28 02:12:27,597][87424] Updated weights for policy 0, policy_version 76166 (0.0010) -[2023-11-28 02:12:27,977][87424] Updated weights for policy 0, policy_version 76176 (0.0011) -[2023-11-28 02:12:28,211][87426] Updated weights for policy 1, policy_version 76070 (0.0010) -[2023-11-28 02:12:28,357][87424] Updated weights for policy 0, policy_version 76186 (0.0012) -[2023-11-28 02:12:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 38969344. Throughput: 0: 2654.4, 1: 2667.5. Samples: 38990676. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:12:28,445][86177] Avg episode reward: [(0, '-588.570'), (1, '-548.700')] -[2023-11-28 02:12:28,577][87426] Updated weights for policy 1, policy_version 76080 (0.0010) -[2023-11-28 02:12:28,959][87426] Updated weights for policy 1, policy_version 76090 (0.0008) -[2023-11-28 02:12:30,218][87424] Updated weights for policy 0, policy_version 76196 (0.0009) -[2023-11-28 02:12:30,605][87424] Updated weights for policy 0, policy_version 76206 (0.0009) -[2023-11-28 02:12:30,999][87424] Updated weights for policy 0, policy_version 76216 (0.0010) -[2023-11-28 02:12:31,541][87426] Updated weights for policy 1, policy_version 76100 (0.0012) -[2023-11-28 02:12:31,926][87426] Updated weights for policy 1, policy_version 76110 (0.0011) -[2023-11-28 02:12:32,311][87426] Updated weights for policy 1, policy_version 76120 (0.0009) -[2023-11-28 02:12:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 39002112. Throughput: 0: 2663.9, 1: 2658.4. Samples: 39014472. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 02:12:33,445][86177] Avg episode reward: [(0, '-579.380'), (1, '-517.970')] -[2023-11-28 02:12:33,476][87424] Updated weights for policy 0, policy_version 76226 (0.0009) -[2023-11-28 02:12:33,863][87424] Updated weights for policy 0, policy_version 76236 (0.0010) -[2023-11-28 02:12:34,252][87424] Updated weights for policy 0, policy_version 76246 (0.0008) -[2023-11-28 02:12:34,541][87426] Updated weights for policy 1, policy_version 76130 (0.0008) -[2023-11-28 02:12:34,634][87424] Updated weights for policy 0, policy_version 76256 (0.0011) -[2023-11-28 02:12:34,917][87426] Updated weights for policy 1, policy_version 76140 (0.0008) -[2023-11-28 02:12:35,312][87426] Updated weights for policy 1, policy_version 76150 (0.0010) -[2023-11-28 02:12:35,688][87426] Updated weights for policy 1, policy_version 76160 (0.0010) -[2023-11-28 02:12:36,791][87424] Updated weights for policy 0, policy_version 76266 (0.0008) -[2023-11-28 02:12:37,180][87424] Updated weights for policy 0, policy_version 76276 (0.0009) -[2023-11-28 02:12:37,571][87424] Updated weights for policy 0, policy_version 76286 (0.0010) -[2023-11-28 02:12:37,830][87426] Updated weights for policy 1, policy_version 76170 (0.0011) -[2023-11-28 02:12:38,207][87426] Updated weights for policy 1, policy_version 76180 (0.0012) -[2023-11-28 02:12:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 39026688. Throughput: 0: 2672.5, 1: 2665.9. Samples: 39046772. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:12:38,445][86177] Avg episode reward: [(0, '-576.280'), (1, '-526.670')] -[2023-11-28 02:12:38,588][87426] Updated weights for policy 1, policy_version 76190 (0.0012) -[2023-11-28 02:12:39,877][87424] Updated weights for policy 0, policy_version 76296 (0.0012) -[2023-11-28 02:12:40,263][87424] Updated weights for policy 0, policy_version 76306 (0.0012) -[2023-11-28 02:12:40,651][87424] Updated weights for policy 0, policy_version 76316 (0.0011) -[2023-11-28 02:12:40,960][87426] Updated weights for policy 1, policy_version 76200 (0.0012) -[2023-11-28 02:12:41,343][87426] Updated weights for policy 1, policy_version 76210 (0.0012) -[2023-11-28 02:12:41,723][87426] Updated weights for policy 1, policy_version 76220 (0.0012) -[2023-11-28 02:12:42,948][87424] Updated weights for policy 0, policy_version 76326 (0.0011) -[2023-11-28 02:12:43,335][87424] Updated weights for policy 0, policy_version 76336 (0.0008) -[2023-11-28 02:12:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 39051264. Throughput: 0: 2681.1, 1: 2643.3. Samples: 39070532. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:12:43,445][86177] Avg episode reward: [(0, '-573.450'), (1, '-527.570')] -[2023-11-28 02:12:43,646][87426] Updated weights for policy 1, policy_version 76230 (0.0011) -[2023-11-28 02:12:43,724][87424] Updated weights for policy 0, policy_version 76346 (0.0008) -[2023-11-28 02:12:44,035][87426] Updated weights for policy 1, policy_version 76240 (0.0011) -[2023-11-28 02:12:44,422][87426] Updated weights for policy 1, policy_version 76250 (0.0012) -[2023-11-28 02:12:45,995][87424] Updated weights for policy 0, policy_version 76356 (0.0007) -[2023-11-28 02:12:46,378][87424] Updated weights for policy 0, policy_version 76366 (0.0007) -[2023-11-28 02:12:46,760][87424] Updated weights for policy 0, policy_version 76376 (0.0009) -[2023-11-28 02:12:46,877][87426] Updated weights for policy 1, policy_version 76260 (0.0012) -[2023-11-28 02:12:47,258][87426] Updated weights for policy 1, policy_version 76270 (0.0011) -[2023-11-28 02:12:47,641][87426] Updated weights for policy 1, policy_version 76280 (0.0012) -[2023-11-28 02:12:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 39084032. Throughput: 0: 2676.3, 1: 2646.1. Samples: 39094348. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:12:48,445][86177] Avg episode reward: [(0, '-510.670'), (1, '-530.760')] -[2023-11-28 02:12:48,797][87424] Updated weights for policy 0, policy_version 76386 (0.0011) -[2023-11-28 02:12:49,179][87424] Updated weights for policy 0, policy_version 76396 (0.0012) -[2023-11-28 02:12:49,558][87424] Updated weights for policy 0, policy_version 76406 (0.0012) -[2023-11-28 02:12:49,938][87424] Updated weights for policy 0, policy_version 76416 (0.0010) -[2023-11-28 02:12:50,090][87426] Updated weights for policy 1, policy_version 76290 (0.0011) -[2023-11-28 02:12:50,473][87426] Updated weights for policy 1, policy_version 76300 (0.0011) -[2023-11-28 02:12:50,846][87426] Updated weights for policy 1, policy_version 76310 (0.0010) -[2023-11-28 02:12:51,223][87426] Updated weights for policy 1, policy_version 76320 (0.0011) -[2023-11-28 02:12:52,420][87424] Updated weights for policy 0, policy_version 76426 (0.0011) -[2023-11-28 02:12:52,808][87424] Updated weights for policy 0, policy_version 76436 (0.0011) -[2023-11-28 02:12:53,183][87424] Updated weights for policy 0, policy_version 76446 (0.0012) -[2023-11-28 02:12:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 39108608. Throughput: 0: 2656.4, 1: 2636.7. Samples: 39125096. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:12:53,445][86177] Avg episode reward: [(0, '-546.030'), (1, '-530.460')] -[2023-11-28 02:12:53,523][87426] Updated weights for policy 1, policy_version 76330 (0.0012) -[2023-11-28 02:12:53,890][87426] Updated weights for policy 1, policy_version 76340 (0.0012) -[2023-11-28 02:12:54,270][87426] Updated weights for policy 1, policy_version 76350 (0.0010) -[2023-11-28 02:12:55,273][87424] Updated weights for policy 0, policy_version 76456 (0.0011) -[2023-11-28 02:12:55,657][87424] Updated weights for policy 0, policy_version 76466 (0.0012) -[2023-11-28 02:12:56,039][87424] Updated weights for policy 0, policy_version 76476 (0.0012) -[2023-11-28 02:12:56,549][87426] Updated weights for policy 1, policy_version 76360 (0.0011) -[2023-11-28 02:12:56,925][87426] Updated weights for policy 1, policy_version 76370 (0.0012) -[2023-11-28 02:12:57,296][87426] Updated weights for policy 1, policy_version 76380 (0.0010) -[2023-11-28 02:12:58,215][87424] Updated weights for policy 0, policy_version 76486 (0.0011) -[2023-11-28 02:12:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 39133184. Throughput: 0: 2647.8, 1: 2657.3. Samples: 39148932. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:12:58,445][86177] Avg episode reward: [(0, '-543.380'), (1, '-516.580')] -[2023-11-28 02:12:58,608][87424] Updated weights for policy 0, policy_version 76496 (0.0011) -[2023-11-28 02:12:58,986][87424] Updated weights for policy 0, policy_version 76506 (0.0011) -[2023-11-28 02:12:59,369][87426] Updated weights for policy 1, policy_version 76390 (0.0008) -[2023-11-28 02:12:59,758][87426] Updated weights for policy 1, policy_version 76400 (0.0008) -[2023-11-28 02:13:00,144][87426] Updated weights for policy 1, policy_version 76410 (0.0011) -[2023-11-28 02:13:00,963][87424] Updated weights for policy 0, policy_version 76516 (0.0010) -[2023-11-28 02:13:01,338][87424] Updated weights for policy 0, policy_version 76526 (0.0012) -[2023-11-28 02:13:01,730][87424] Updated weights for policy 0, policy_version 76536 (0.0012) -[2023-11-28 02:13:02,061][87426] Updated weights for policy 1, policy_version 76420 (0.0012) -[2023-11-28 02:13:02,431][87426] Updated weights for policy 1, policy_version 76430 (0.0012) -[2023-11-28 02:13:02,811][87426] Updated weights for policy 1, policy_version 76440 (0.0011) -[2023-11-28 02:13:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 39165952. Throughput: 0: 2657.4, 1: 2656.5. Samples: 39174372. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:13:03,445][86177] Avg episode reward: [(0, '-538.680'), (1, '-523.730')] -[2023-11-28 02:13:04,255][87424] Updated weights for policy 0, policy_version 76546 (0.0014) -[2023-11-28 02:13:04,635][87424] Updated weights for policy 0, policy_version 76556 (0.0010) -[2023-11-28 02:13:05,021][87424] Updated weights for policy 0, policy_version 76566 (0.0011) -[2023-11-28 02:13:05,100][87426] Updated weights for policy 1, policy_version 76450 (0.0011) -[2023-11-28 02:13:05,397][87424] Updated weights for policy 0, policy_version 76576 (0.0011) -[2023-11-28 02:13:05,484][87426] Updated weights for policy 1, policy_version 76460 (0.0011) -[2023-11-28 02:13:05,868][87426] Updated weights for policy 1, policy_version 76470 (0.0007) -[2023-11-28 02:13:06,253][87426] Updated weights for policy 1, policy_version 76480 (0.0009) -[2023-11-28 02:13:07,531][87424] Updated weights for policy 0, policy_version 76586 (0.0012) -[2023-11-28 02:13:07,914][87424] Updated weights for policy 0, policy_version 76596 (0.0012) -[2023-11-28 02:13:08,292][87424] Updated weights for policy 0, policy_version 76606 (0.0011) -[2023-11-28 02:13:08,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 39190528. Throughput: 0: 2676.4, 1: 2670.1. Samples: 39207476. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:13:08,446][86177] Avg episode reward: [(0, '-570.920'), (1, '-523.620')] -[2023-11-28 02:13:08,592][87426] Updated weights for policy 1, policy_version 76490 (0.0008) -[2023-11-28 02:13:08,973][87426] Updated weights for policy 1, policy_version 76500 (0.0010) -[2023-11-28 02:13:09,348][87426] Updated weights for policy 1, policy_version 76510 (0.0012) -[2023-11-28 02:13:10,183][87424] Updated weights for policy 0, policy_version 76616 (0.0012) -[2023-11-28 02:13:10,568][87424] Updated weights for policy 0, policy_version 76626 (0.0011) -[2023-11-28 02:13:10,946][87424] Updated weights for policy 0, policy_version 76636 (0.0009) -[2023-11-28 02:13:11,474][87426] Updated weights for policy 1, policy_version 76520 (0.0012) -[2023-11-28 02:13:11,861][87426] Updated weights for policy 1, policy_version 76530 (0.0010) -[2023-11-28 02:13:12,246][87426] Updated weights for policy 1, policy_version 76540 (0.0011) -[2023-11-28 02:13:13,208][87424] Updated weights for policy 0, policy_version 76646 (0.0012) -[2023-11-28 02:13:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 39215104. Throughput: 0: 2680.2, 1: 2683.5. Samples: 39232040. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:13:13,445][86177] Avg episode reward: [(0, '-553.270'), (1, '-510.700')] -[2023-11-28 02:13:13,586][87424] Updated weights for policy 0, policy_version 76656 (0.0012) -[2023-11-28 02:13:13,967][87424] Updated weights for policy 0, policy_version 76666 (0.0012) -[2023-11-28 02:13:14,535][87426] Updated weights for policy 1, policy_version 76550 (0.0009) -[2023-11-28 02:13:14,918][87426] Updated weights for policy 1, policy_version 76560 (0.0008) -[2023-11-28 02:13:15,293][87426] Updated weights for policy 1, policy_version 76570 (0.0008) -[2023-11-28 02:13:16,463][87424] Updated weights for policy 0, policy_version 76676 (0.0012) -[2023-11-28 02:13:16,847][87424] Updated weights for policy 0, policy_version 76686 (0.0010) -[2023-11-28 02:13:17,229][87424] Updated weights for policy 0, policy_version 76696 (0.0010) -[2023-11-28 02:13:17,315][87426] Updated weights for policy 1, policy_version 76580 (0.0011) -[2023-11-28 02:13:17,699][87426] Updated weights for policy 1, policy_version 76590 (0.0007) -[2023-11-28 02:13:18,079][87426] Updated weights for policy 1, policy_version 76600 (0.0007) -[2023-11-28 02:13:18,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 39247872. Throughput: 0: 2675.5, 1: 2699.4. Samples: 39256348. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:13:18,446][86177] Avg episode reward: [(0, '-558.850'), (1, '-512.300')] -[2023-11-28 02:13:19,420][87424] Updated weights for policy 0, policy_version 76706 (0.0008) -[2023-11-28 02:13:19,806][87424] Updated weights for policy 0, policy_version 76716 (0.0012) -[2023-11-28 02:13:20,015][87426] Updated weights for policy 1, policy_version 76610 (0.0009) -[2023-11-28 02:13:20,189][87424] Updated weights for policy 0, policy_version 76726 (0.0011) -[2023-11-28 02:13:20,395][87426] Updated weights for policy 1, policy_version 76620 (0.0011) -[2023-11-28 02:13:20,568][87424] Updated weights for policy 0, policy_version 76736 (0.0011) -[2023-11-28 02:13:20,776][87426] Updated weights for policy 1, policy_version 76630 (0.0009) -[2023-11-28 02:13:21,158][87426] Updated weights for policy 1, policy_version 76640 (0.0010) -[2023-11-28 02:13:22,578][87424] Updated weights for policy 0, policy_version 76746 (0.0011) -[2023-11-28 02:13:22,963][87424] Updated weights for policy 0, policy_version 76756 (0.0012) -[2023-11-28 02:13:23,354][87424] Updated weights for policy 0, policy_version 76766 (0.0011) -[2023-11-28 02:13:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 39272448. Throughput: 0: 2681.8, 1: 2696.3. Samples: 39288784. Policy #0 lag: (min: 31.0, avg: 34.0, max: 56.0) -[2023-11-28 02:13:23,445][86177] Avg episode reward: [(0, '-557.200'), (1, '-507.680')] -[2023-11-28 02:13:23,465][87426] Updated weights for policy 1, policy_version 76650 (0.0011) -[2023-11-28 02:13:23,838][87426] Updated weights for policy 1, policy_version 76660 (0.0009) -[2023-11-28 02:13:24,216][87426] Updated weights for policy 1, policy_version 76670 (0.0009) -[2023-11-28 02:13:25,174][87424] Updated weights for policy 0, policy_version 76776 (0.0011) -[2023-11-28 02:13:25,562][87424] Updated weights for policy 0, policy_version 76786 (0.0008) -[2023-11-28 02:13:25,950][87424] Updated weights for policy 0, policy_version 76796 (0.0007) -[2023-11-28 02:13:25,996][87426] Updated weights for policy 1, policy_version 76680 (0.0011) -[2023-11-28 02:13:26,377][87426] Updated weights for policy 1, policy_version 76690 (0.0012) -[2023-11-28 02:13:26,756][87426] Updated weights for policy 1, policy_version 76700 (0.0012) -[2023-11-28 02:13:28,024][87424] Updated weights for policy 0, policy_version 76806 (0.0007) -[2023-11-28 02:13:28,406][87426] Updated weights for policy 1, policy_version 76710 (0.0011) -[2023-11-28 02:13:28,416][87424] Updated weights for policy 0, policy_version 76816 (0.0009) -[2023-11-28 02:13:28,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 39297024. Throughput: 0: 2687.5, 1: 2733.0. Samples: 39314452. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:13:28,446][86177] Avg episode reward: [(0, '-516.900'), (1, '-521.050')] -[2023-11-28 02:13:28,782][87426] Updated weights for policy 1, policy_version 76720 (0.0011) -[2023-11-28 02:13:28,801][87424] Updated weights for policy 0, policy_version 76826 (0.0008) -[2023-11-28 02:13:29,167][87426] Updated weights for policy 1, policy_version 76730 (0.0008) -[2023-11-28 02:13:31,116][87424] Updated weights for policy 0, policy_version 76836 (0.0008) -[2023-11-28 02:13:31,506][87424] Updated weights for policy 0, policy_version 76846 (0.0007) -[2023-11-28 02:13:31,603][87426] Updated weights for policy 1, policy_version 76740 (0.0008) -[2023-11-28 02:13:31,888][87424] Updated weights for policy 0, policy_version 76856 (0.0009) -[2023-11-28 02:13:31,977][87426] Updated weights for policy 1, policy_version 76750 (0.0011) -[2023-11-28 02:13:32,363][87426] Updated weights for policy 1, policy_version 76760 (0.0010) -[2023-11-28 02:13:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 39329792. Throughput: 0: 2693.4, 1: 2734.0. Samples: 39338584. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:13:33,445][86177] Avg episode reward: [(0, '-512.790'), (1, '-525.620')] -[2023-11-28 02:13:33,753][87424] Updated weights for policy 0, policy_version 76866 (0.0009) -[2023-11-28 02:13:34,139][87424] Updated weights for policy 0, policy_version 76876 (0.0012) -[2023-11-28 02:13:34,515][87424] Updated weights for policy 0, policy_version 76886 (0.0011) -[2023-11-28 02:13:34,590][87426] Updated weights for policy 1, policy_version 76770 (0.0012) -[2023-11-28 02:13:34,895][87424] Updated weights for policy 0, policy_version 76896 (0.0011) -[2023-11-28 02:13:34,965][87426] Updated weights for policy 1, policy_version 76780 (0.0010) -[2023-11-28 02:13:35,347][87426] Updated weights for policy 1, policy_version 76790 (0.0011) -[2023-11-28 02:13:35,717][87426] Updated weights for policy 1, policy_version 76800 (0.0012) -[2023-11-28 02:13:36,973][87424] Updated weights for policy 0, policy_version 76906 (0.0011) -[2023-11-28 02:13:37,368][87424] Updated weights for policy 0, policy_version 76916 (0.0008) -[2023-11-28 02:13:37,743][87424] Updated weights for policy 0, policy_version 76926 (0.0008) -[2023-11-28 02:13:37,780][87426] Updated weights for policy 1, policy_version 76810 (0.0008) -[2023-11-28 02:13:38,154][87426] Updated weights for policy 1, policy_version 76820 (0.0008) -[2023-11-28 02:13:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 39354368. Throughput: 0: 2718.7, 1: 2741.7. Samples: 39370816. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:13:38,446][86177] Avg episode reward: [(0, '-518.300'), (1, '-537.960')] -[2023-11-28 02:13:38,546][87426] Updated weights for policy 1, policy_version 76830 (0.0010) -[2023-11-28 02:13:40,273][87424] Updated weights for policy 0, policy_version 76936 (0.0011) -[2023-11-28 02:13:40,655][87424] Updated weights for policy 0, policy_version 76946 (0.0009) -[2023-11-28 02:13:41,037][87424] Updated weights for policy 0, policy_version 76956 (0.0010) -[2023-11-28 02:13:41,170][87426] Updated weights for policy 1, policy_version 76840 (0.0010) -[2023-11-28 02:13:41,552][87426] Updated weights for policy 1, policy_version 76850 (0.0010) -[2023-11-28 02:13:41,932][87426] Updated weights for policy 1, policy_version 76860 (0.0010) -[2023-11-28 02:13:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 39378944. Throughput: 0: 2723.8, 1: 2727.9. Samples: 39394260. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:13:43,445][86177] Avg episode reward: [(0, '-517.780'), (1, '-539.060')] -[2023-11-28 02:13:43,560][87424] Updated weights for policy 0, policy_version 76966 (0.0010) -[2023-11-28 02:13:43,934][87424] Updated weights for policy 0, policy_version 76976 (0.0012) -[2023-11-28 02:13:44,067][87426] Updated weights for policy 1, policy_version 76870 (0.0009) -[2023-11-28 02:13:44,319][87424] Updated weights for policy 0, policy_version 76986 (0.0011) -[2023-11-28 02:13:44,445][87426] Updated weights for policy 1, policy_version 76880 (0.0011) -[2023-11-28 02:13:44,813][87426] Updated weights for policy 1, policy_version 76890 (0.0011) -[2023-11-28 02:13:46,561][87424] Updated weights for policy 0, policy_version 76996 (0.0010) -[2023-11-28 02:13:46,943][87424] Updated weights for policy 0, policy_version 77006 (0.0007) -[2023-11-28 02:13:47,182][87426] Updated weights for policy 1, policy_version 76900 (0.0012) -[2023-11-28 02:13:47,318][87424] Updated weights for policy 0, policy_version 77016 (0.0011) -[2023-11-28 02:13:47,561][87426] Updated weights for policy 1, policy_version 76910 (0.0012) -[2023-11-28 02:13:47,937][87426] Updated weights for policy 1, policy_version 76920 (0.0011) -[2023-11-28 02:13:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 39411712. Throughput: 0: 2719.5, 1: 2730.1. Samples: 39419604. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:13:48,445][86177] Avg episode reward: [(0, '-529.710'), (1, '-524.410')] -[2023-11-28 02:13:49,136][87424] Updated weights for policy 0, policy_version 77026 (0.0011) -[2023-11-28 02:13:49,522][87424] Updated weights for policy 0, policy_version 77036 (0.0008) -[2023-11-28 02:13:49,910][87424] Updated weights for policy 0, policy_version 77046 (0.0008) -[2023-11-28 02:13:50,066][87426] Updated weights for policy 1, policy_version 76930 (0.0010) -[2023-11-28 02:13:50,290][87424] Updated weights for policy 0, policy_version 77056 (0.0012) -[2023-11-28 02:13:50,465][87426] Updated weights for policy 1, policy_version 76940 (0.0009) -[2023-11-28 02:13:50,829][87426] Updated weights for policy 1, policy_version 76950 (0.0007) -[2023-11-28 02:13:51,208][87426] Updated weights for policy 1, policy_version 76960 (0.0009) -[2023-11-28 02:13:52,344][87424] Updated weights for policy 0, policy_version 77066 (0.0012) -[2023-11-28 02:13:52,724][87424] Updated weights for policy 0, policy_version 77076 (0.0012) -[2023-11-28 02:13:53,107][87424] Updated weights for policy 0, policy_version 77086 (0.0012) -[2023-11-28 02:13:53,193][87426] Updated weights for policy 1, policy_version 76970 (0.0011) -[2023-11-28 02:13:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 39436288. Throughput: 0: 2725.2, 1: 2715.5. Samples: 39452304. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:13:53,445][86177] Avg episode reward: [(0, '-543.720'), (1, '-523.300')] -[2023-11-28 02:13:53,560][87426] Updated weights for policy 1, policy_version 76980 (0.0011) -[2023-11-28 02:13:53,946][87426] Updated weights for policy 1, policy_version 76990 (0.0011) -[2023-11-28 02:13:55,166][87424] Updated weights for policy 0, policy_version 77096 (0.0011) -[2023-11-28 02:13:55,550][87424] Updated weights for policy 0, policy_version 77106 (0.0008) -[2023-11-28 02:13:55,941][87424] Updated weights for policy 0, policy_version 77116 (0.0007) -[2023-11-28 02:13:56,466][87426] Updated weights for policy 1, policy_version 77000 (0.0007) -[2023-11-28 02:13:56,845][87426] Updated weights for policy 1, policy_version 77010 (0.0008) -[2023-11-28 02:13:57,231][87426] Updated weights for policy 1, policy_version 77020 (0.0007) -[2023-11-28 02:13:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 39460864. Throughput: 0: 2708.3, 1: 2719.1. Samples: 39476272. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:13:58,446][86177] Avg episode reward: [(0, '-542.110'), (1, '-509.970')] -[2023-11-28 02:13:58,491][87424] Updated weights for policy 0, policy_version 77126 (0.0010) -[2023-11-28 02:13:58,890][87424] Updated weights for policy 0, policy_version 77136 (0.0012) -[2023-11-28 02:13:59,186][87426] Updated weights for policy 1, policy_version 77030 (0.0010) -[2023-11-28 02:13:59,271][87424] Updated weights for policy 0, policy_version 77146 (0.0009) -[2023-11-28 02:13:59,549][87426] Updated weights for policy 1, policy_version 77040 (0.0012) -[2023-11-28 02:13:59,933][87426] Updated weights for policy 1, policy_version 77050 (0.0012) -[2023-11-28 02:14:01,229][87424] Updated weights for policy 0, policy_version 77156 (0.0009) -[2023-11-28 02:14:01,617][87424] Updated weights for policy 0, policy_version 77166 (0.0012) -[2023-11-28 02:14:02,006][87424] Updated weights for policy 0, policy_version 77176 (0.0011) -[2023-11-28 02:14:02,165][87426] Updated weights for policy 1, policy_version 77060 (0.0012) -[2023-11-28 02:14:02,542][87426] Updated weights for policy 1, policy_version 77070 (0.0011) -[2023-11-28 02:14:02,915][87426] Updated weights for policy 1, policy_version 77080 (0.0012) -[2023-11-28 02:14:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 39493632. Throughput: 0: 2733.4, 1: 2716.3. Samples: 39501584. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:14:03,446][86177] Avg episode reward: [(0, '-552.800'), (1, '-508.990')] -[2023-11-28 02:14:04,492][87424] Updated weights for policy 0, policy_version 77186 (0.0011) -[2023-11-28 02:14:04,816][87426] Updated weights for policy 1, policy_version 77090 (0.0012) -[2023-11-28 02:14:04,867][87424] Updated weights for policy 0, policy_version 77196 (0.0011) -[2023-11-28 02:14:05,189][87426] Updated weights for policy 1, policy_version 77100 (0.0012) -[2023-11-28 02:14:05,252][87424] Updated weights for policy 0, policy_version 77206 (0.0011) -[2023-11-28 02:14:05,566][87426] Updated weights for policy 1, policy_version 77110 (0.0012) -[2023-11-28 02:14:05,630][87424] Updated weights for policy 0, policy_version 77216 (0.0007) -[2023-11-28 02:14:05,941][87426] Updated weights for policy 1, policy_version 77120 (0.0012) -[2023-11-28 02:14:07,625][87424] Updated weights for policy 0, policy_version 77226 (0.0011) -[2023-11-28 02:14:08,003][87424] Updated weights for policy 0, policy_version 77236 (0.0008) -[2023-11-28 02:14:08,139][87426] Updated weights for policy 1, policy_version 77130 (0.0009) -[2023-11-28 02:14:08,385][87424] Updated weights for policy 0, policy_version 77246 (0.0009) -[2023-11-28 02:14:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 39510016. Throughput: 0: 2723.0, 1: 2746.0. Samples: 39534888. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:14:08,445][86177] Avg episode reward: [(0, '-541.620'), (1, '-512.040')] -[2023-11-28 02:14:08,524][87426] Updated weights for policy 1, policy_version 77140 (0.0010) -[2023-11-28 02:14:08,903][87426] Updated weights for policy 1, policy_version 77150 (0.0010) -[2023-11-28 02:14:10,873][87424] Updated weights for policy 0, policy_version 77256 (0.0012) -[2023-11-28 02:14:11,020][87426] Updated weights for policy 1, policy_version 77160 (0.0009) -[2023-11-28 02:14:11,255][87424] Updated weights for policy 0, policy_version 77266 (0.0010) -[2023-11-28 02:14:11,399][87426] Updated weights for policy 1, policy_version 77170 (0.0010) -[2023-11-28 02:14:11,637][87424] Updated weights for policy 0, policy_version 77276 (0.0011) -[2023-11-28 02:14:11,778][87426] Updated weights for policy 1, policy_version 77180 (0.0012) -[2023-11-28 02:14:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 39542784. Throughput: 0: 2723.0, 1: 2702.8. Samples: 39558608. Policy #0 lag: (min: 31.0, avg: 52.2, max: 91.0) -[2023-11-28 02:14:13,445][86177] Avg episode reward: [(0, '-522.000'), (1, '-513.130')] -[2023-11-28 02:14:14,004][87424] Updated weights for policy 0, policy_version 77286 (0.0010) -[2023-11-28 02:14:14,381][87424] Updated weights for policy 0, policy_version 77296 (0.0007) -[2023-11-28 02:14:14,435][87426] Updated weights for policy 1, policy_version 77190 (0.0012) -[2023-11-28 02:14:14,776][87424] Updated weights for policy 0, policy_version 77306 (0.0007) -[2023-11-28 02:14:14,810][87426] Updated weights for policy 1, policy_version 77200 (0.0011) -[2023-11-28 02:14:15,196][87426] Updated weights for policy 1, policy_version 77210 (0.0011) -[2023-11-28 02:14:16,693][87424] Updated weights for policy 0, policy_version 77316 (0.0009) -[2023-11-28 02:14:17,071][87424] Updated weights for policy 0, policy_version 77326 (0.0012) -[2023-11-28 02:14:17,326][87426] Updated weights for policy 1, policy_version 77220 (0.0010) -[2023-11-28 02:14:17,454][87424] Updated weights for policy 0, policy_version 77336 (0.0011) -[2023-11-28 02:14:17,702][87426] Updated weights for policy 1, policy_version 77230 (0.0007) -[2023-11-28 02:14:18,079][87426] Updated weights for policy 1, policy_version 77240 (0.0007) -[2023-11-28 02:14:18,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 39575552. Throughput: 0: 2725.6, 1: 2705.2. Samples: 39582972. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:14:18,445][86177] Avg episode reward: [(0, '-507.400'), (1, '-508.790')] -[2023-11-28 02:14:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000077344_19800064.pth... -[2023-11-28 02:14:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000077248_19775488.pth... -[2023-11-28 02:14:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000074720_19128320.pth -[2023-11-28 02:14:18,496][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000074816_19152896.pth -[2023-11-28 02:14:19,996][87424] Updated weights for policy 0, policy_version 77346 (0.0008) -[2023-11-28 02:14:20,374][87424] Updated weights for policy 0, policy_version 77356 (0.0011) -[2023-11-28 02:14:20,413][87426] Updated weights for policy 1, policy_version 77250 (0.0008) -[2023-11-28 02:14:20,758][87424] Updated weights for policy 0, policy_version 77366 (0.0012) -[2023-11-28 02:14:20,790][87426] Updated weights for policy 1, policy_version 77260 (0.0009) -[2023-11-28 02:14:21,143][87424] Updated weights for policy 0, policy_version 77376 (0.0012) -[2023-11-28 02:14:21,170][87426] Updated weights for policy 1, policy_version 77270 (0.0008) -[2023-11-28 02:14:21,551][87426] Updated weights for policy 1, policy_version 77280 (0.0008) -[2023-11-28 02:14:23,266][87424] Updated weights for policy 0, policy_version 77386 (0.0011) -[2023-11-28 02:14:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 39591936. Throughput: 0: 2710.6, 1: 2702.7. Samples: 39614412. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:14:23,445][86177] Avg episode reward: [(0, '-513.370'), (1, '-509.260')] -[2023-11-28 02:14:23,653][87424] Updated weights for policy 0, policy_version 77396 (0.0007) -[2023-11-28 02:14:23,971][87426] Updated weights for policy 1, policy_version 77290 (0.0012) -[2023-11-28 02:14:24,034][87424] Updated weights for policy 0, policy_version 77406 (0.0008) -[2023-11-28 02:14:24,345][87426] Updated weights for policy 1, policy_version 77300 (0.0012) -[2023-11-28 02:14:24,722][87426] Updated weights for policy 1, policy_version 77310 (0.0012) -[2023-11-28 02:14:26,162][87424] Updated weights for policy 0, policy_version 77416 (0.0008) -[2023-11-28 02:14:26,545][87424] Updated weights for policy 0, policy_version 77426 (0.0011) -[2023-11-28 02:14:26,795][87426] Updated weights for policy 1, policy_version 77320 (0.0012) -[2023-11-28 02:14:26,928][87424] Updated weights for policy 0, policy_version 77436 (0.0012) -[2023-11-28 02:14:27,169][87426] Updated weights for policy 1, policy_version 77330 (0.0011) -[2023-11-28 02:14:27,547][87426] Updated weights for policy 1, policy_version 77340 (0.0012) -[2023-11-28 02:14:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 39624704. Throughput: 0: 2724.3, 1: 2713.3. Samples: 39638952. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:14:28,445][86177] Avg episode reward: [(0, '-510.200'), (1, '-505.770')] -[2023-11-28 02:14:28,511][87424] Updated weights for policy 0, policy_version 77446 (0.0009) -[2023-11-28 02:14:28,896][87424] Updated weights for policy 0, policy_version 77456 (0.0008) -[2023-11-28 02:14:29,282][87424] Updated weights for policy 0, policy_version 77466 (0.0011) -[2023-11-28 02:14:29,599][87426] Updated weights for policy 1, policy_version 77350 (0.0010) -[2023-11-28 02:14:29,986][87426] Updated weights for policy 1, policy_version 77360 (0.0009) -[2023-11-28 02:14:30,357][87426] Updated weights for policy 1, policy_version 77370 (0.0011) -[2023-11-28 02:14:31,680][87424] Updated weights for policy 0, policy_version 77476 (0.0011) -[2023-11-28 02:14:32,048][87424] Updated weights for policy 0, policy_version 77486 (0.0011) -[2023-11-28 02:14:32,179][87426] Updated weights for policy 1, policy_version 77380 (0.0009) -[2023-11-28 02:14:32,437][87424] Updated weights for policy 0, policy_version 77496 (0.0011) -[2023-11-28 02:14:32,561][87426] Updated weights for policy 1, policy_version 77390 (0.0010) -[2023-11-28 02:14:32,936][87426] Updated weights for policy 1, policy_version 77400 (0.0012) -[2023-11-28 02:14:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 39657472. Throughput: 0: 2704.8, 1: 2725.8. Samples: 39663980. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:14:33,445][86177] Avg episode reward: [(0, '-508.320'), (1, '-508.400')] -[2023-11-28 02:14:34,207][87424] Updated weights for policy 0, policy_version 77506 (0.0010) -[2023-11-28 02:14:34,594][87424] Updated weights for policy 0, policy_version 77516 (0.0007) -[2023-11-28 02:14:34,982][87424] Updated weights for policy 0, policy_version 77526 (0.0011) -[2023-11-28 02:14:35,306][87426] Updated weights for policy 1, policy_version 77410 (0.0012) -[2023-11-28 02:14:35,358][87424] Updated weights for policy 0, policy_version 77536 (0.0012) -[2023-11-28 02:14:35,686][87426] Updated weights for policy 1, policy_version 77420 (0.0008) -[2023-11-28 02:14:36,066][87426] Updated weights for policy 1, policy_version 77430 (0.0007) -[2023-11-28 02:14:36,443][87426] Updated weights for policy 1, policy_version 77440 (0.0007) -[2023-11-28 02:14:37,705][87424] Updated weights for policy 0, policy_version 77546 (0.0008) -[2023-11-28 02:14:38,089][87424] Updated weights for policy 0, policy_version 77556 (0.0009) -[2023-11-28 02:14:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 39673856. Throughput: 0: 2687.6, 1: 2732.1. Samples: 39696192. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:14:38,445][86177] Avg episode reward: [(0, '-495.240'), (1, '-524.770')] -[2023-11-28 02:14:38,471][87424] Updated weights for policy 0, policy_version 77566 (0.0012) -[2023-11-28 02:14:38,485][87426] Updated weights for policy 1, policy_version 77450 (0.0012) -[2023-11-28 02:14:38,870][87426] Updated weights for policy 1, policy_version 77460 (0.0012) -[2023-11-28 02:14:39,252][87426] Updated weights for policy 1, policy_version 77470 (0.0010) -[2023-11-28 02:14:40,746][87424] Updated weights for policy 0, policy_version 77576 (0.0008) -[2023-11-28 02:14:41,116][87424] Updated weights for policy 0, policy_version 77586 (0.0008) -[2023-11-28 02:14:41,501][87424] Updated weights for policy 0, policy_version 77596 (0.0009) -[2023-11-28 02:14:41,525][87426] Updated weights for policy 1, policy_version 77480 (0.0010) -[2023-11-28 02:14:41,912][87426] Updated weights for policy 1, policy_version 77490 (0.0011) -[2023-11-28 02:14:42,290][87426] Updated weights for policy 1, policy_version 77500 (0.0011) -[2023-11-28 02:14:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 39706624. Throughput: 0: 2707.9, 1: 2717.0. Samples: 39720392. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:14:43,445][86177] Avg episode reward: [(0, '-496.950'), (1, '-523.200')] -[2023-11-28 02:14:43,521][87424] Updated weights for policy 0, policy_version 77606 (0.0009) -[2023-11-28 02:14:43,902][87424] Updated weights for policy 0, policy_version 77616 (0.0010) -[2023-11-28 02:14:44,238][87426] Updated weights for policy 1, policy_version 77510 (0.0011) -[2023-11-28 02:14:44,277][87424] Updated weights for policy 0, policy_version 77626 (0.0011) -[2023-11-28 02:14:44,620][87426] Updated weights for policy 1, policy_version 77520 (0.0008) -[2023-11-28 02:14:45,001][87426] Updated weights for policy 1, policy_version 77530 (0.0011) -[2023-11-28 02:14:46,353][87424] Updated weights for policy 0, policy_version 77636 (0.0009) -[2023-11-28 02:14:46,735][87424] Updated weights for policy 0, policy_version 77646 (0.0008) -[2023-11-28 02:14:47,110][87424] Updated weights for policy 0, policy_version 77656 (0.0009) -[2023-11-28 02:14:47,479][87426] Updated weights for policy 1, policy_version 77540 (0.0008) -[2023-11-28 02:14:47,873][87426] Updated weights for policy 1, policy_version 77550 (0.0007) -[2023-11-28 02:14:48,251][87426] Updated weights for policy 1, policy_version 77560 (0.0010) -[2023-11-28 02:14:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 39731200. Throughput: 0: 2693.3, 1: 2710.8. Samples: 39744768. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:14:48,446][86177] Avg episode reward: [(0, '-502.410'), (1, '-532.370')] -[2023-11-28 02:14:49,611][87424] Updated weights for policy 0, policy_version 77666 (0.0011) -[2023-11-28 02:14:49,990][87424] Updated weights for policy 0, policy_version 77676 (0.0012) -[2023-11-28 02:14:50,364][87424] Updated weights for policy 0, policy_version 77686 (0.0012) -[2023-11-28 02:14:50,703][87426] Updated weights for policy 1, policy_version 77570 (0.0010) -[2023-11-28 02:14:50,740][87424] Updated weights for policy 0, policy_version 77696 (0.0012) -[2023-11-28 02:14:51,082][87426] Updated weights for policy 1, policy_version 77580 (0.0011) -[2023-11-28 02:14:51,469][87426] Updated weights for policy 1, policy_version 77590 (0.0010) -[2023-11-28 02:14:51,843][87426] Updated weights for policy 1, policy_version 77600 (0.0009) -[2023-11-28 02:14:53,094][87424] Updated weights for policy 0, policy_version 77706 (0.0012) -[2023-11-28 02:14:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 39755776. Throughput: 0: 2715.6, 1: 2682.6. Samples: 39777808. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:14:53,445][86177] Avg episode reward: [(0, '-502.490'), (1, '-528.730')] -[2023-11-28 02:14:53,472][87424] Updated weights for policy 0, policy_version 77716 (0.0010) -[2023-11-28 02:14:53,853][87424] Updated weights for policy 0, policy_version 77726 (0.0011) -[2023-11-28 02:14:53,951][87426] Updated weights for policy 1, policy_version 77610 (0.0010) -[2023-11-28 02:14:54,334][87426] Updated weights for policy 1, policy_version 77620 (0.0007) -[2023-11-28 02:14:54,721][87426] Updated weights for policy 1, policy_version 77630 (0.0009) -[2023-11-28 02:14:56,090][87424] Updated weights for policy 0, policy_version 77736 (0.0008) -[2023-11-28 02:14:56,476][87424] Updated weights for policy 0, policy_version 77746 (0.0007) -[2023-11-28 02:14:56,854][87424] Updated weights for policy 0, policy_version 77756 (0.0009) -[2023-11-28 02:14:57,119][87426] Updated weights for policy 1, policy_version 77640 (0.0011) -[2023-11-28 02:14:57,495][87426] Updated weights for policy 1, policy_version 77650 (0.0008) -[2023-11-28 02:14:57,870][87426] Updated weights for policy 1, policy_version 77660 (0.0009) -[2023-11-28 02:14:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 39788544. Throughput: 0: 2722.7, 1: 2689.1. Samples: 39802136. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:14:58,445][86177] Avg episode reward: [(0, '-506.500'), (1, '-530.510')] -[2023-11-28 02:14:58,755][87424] Updated weights for policy 0, policy_version 77766 (0.0011) -[2023-11-28 02:14:59,141][87424] Updated weights for policy 0, policy_version 77776 (0.0012) -[2023-11-28 02:14:59,524][87424] Updated weights for policy 0, policy_version 77786 (0.0012) -[2023-11-28 02:14:59,769][87426] Updated weights for policy 1, policy_version 77670 (0.0011) -[2023-11-28 02:15:00,148][87426] Updated weights for policy 1, policy_version 77680 (0.0012) -[2023-11-28 02:15:00,522][87426] Updated weights for policy 1, policy_version 77690 (0.0012) -[2023-11-28 02:15:01,854][87424] Updated weights for policy 0, policy_version 77796 (0.0011) -[2023-11-28 02:15:02,240][87424] Updated weights for policy 0, policy_version 77806 (0.0012) -[2023-11-28 02:15:02,526][87426] Updated weights for policy 1, policy_version 77700 (0.0011) -[2023-11-28 02:15:02,623][87424] Updated weights for policy 0, policy_version 77816 (0.0012) -[2023-11-28 02:15:02,910][87426] Updated weights for policy 1, policy_version 77710 (0.0009) -[2023-11-28 02:15:03,281][87426] Updated weights for policy 1, policy_version 77720 (0.0008) -[2023-11-28 02:15:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 39813120. Throughput: 0: 2736.2, 1: 2711.4. Samples: 39828112. Policy #0 lag: (min: 31.0, avg: 51.4, max: 81.0) -[2023-11-28 02:15:03,446][86177] Avg episode reward: [(0, '-502.310'), (1, '-538.780')] -[2023-11-28 02:15:05,035][87424] Updated weights for policy 0, policy_version 77826 (0.0009) -[2023-11-28 02:15:05,416][87424] Updated weights for policy 0, policy_version 77836 (0.0011) -[2023-11-28 02:15:05,465][87426] Updated weights for policy 1, policy_version 77730 (0.0008) -[2023-11-28 02:15:05,805][87424] Updated weights for policy 0, policy_version 77846 (0.0008) -[2023-11-28 02:15:05,840][87426] Updated weights for policy 1, policy_version 77740 (0.0009) -[2023-11-28 02:15:06,192][87424] Updated weights for policy 0, policy_version 77856 (0.0007) -[2023-11-28 02:15:06,217][87426] Updated weights for policy 1, policy_version 77750 (0.0007) -[2023-11-28 02:15:06,601][87426] Updated weights for policy 1, policy_version 77760 (0.0007) -[2023-11-28 02:15:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 39837696. Throughput: 0: 2725.6, 1: 2736.1. Samples: 39860188. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:08,446][86177] Avg episode reward: [(0, '-505.960'), (1, '-526.970')] -[2023-11-28 02:15:08,502][87424] Updated weights for policy 0, policy_version 77866 (0.0007) -[2023-11-28 02:15:08,889][87424] Updated weights for policy 0, policy_version 77876 (0.0009) -[2023-11-28 02:15:08,937][87426] Updated weights for policy 1, policy_version 77770 (0.0011) -[2023-11-28 02:15:09,260][87424] Updated weights for policy 0, policy_version 77886 (0.0011) -[2023-11-28 02:15:09,314][87426] Updated weights for policy 1, policy_version 77780 (0.0008) -[2023-11-28 02:15:09,691][87426] Updated weights for policy 1, policy_version 77790 (0.0011) -[2023-11-28 02:15:11,552][87424] Updated weights for policy 0, policy_version 77896 (0.0009) -[2023-11-28 02:15:11,739][87426] Updated weights for policy 1, policy_version 77800 (0.0010) -[2023-11-28 02:15:11,943][87424] Updated weights for policy 0, policy_version 77906 (0.0012) -[2023-11-28 02:15:12,129][87426] Updated weights for policy 1, policy_version 77810 (0.0010) -[2023-11-28 02:15:12,330][87424] Updated weights for policy 0, policy_version 77916 (0.0010) -[2023-11-28 02:15:12,503][87426] Updated weights for policy 1, policy_version 77820 (0.0010) -[2023-11-28 02:15:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 39870464. Throughput: 0: 2706.1, 1: 2735.3. Samples: 39883816. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:13,445][86177] Avg episode reward: [(0, '-506.320'), (1, '-537.860')] -[2023-11-28 02:15:14,352][87424] Updated weights for policy 0, policy_version 77926 (0.0010) -[2023-11-28 02:15:14,736][87424] Updated weights for policy 0, policy_version 77936 (0.0008) -[2023-11-28 02:15:14,915][87426] Updated weights for policy 1, policy_version 77830 (0.0011) -[2023-11-28 02:15:15,120][87424] Updated weights for policy 0, policy_version 77946 (0.0008) -[2023-11-28 02:15:15,300][87426] Updated weights for policy 1, policy_version 77840 (0.0011) -[2023-11-28 02:15:15,680][87426] Updated weights for policy 1, policy_version 77850 (0.0011) -[2023-11-28 02:15:17,062][87424] Updated weights for policy 0, policy_version 77956 (0.0010) -[2023-11-28 02:15:17,434][87426] Updated weights for policy 1, policy_version 77860 (0.0012) -[2023-11-28 02:15:17,443][87424] Updated weights for policy 0, policy_version 77966 (0.0011) -[2023-11-28 02:15:17,808][87426] Updated weights for policy 1, policy_version 77870 (0.0011) -[2023-11-28 02:15:17,838][87424] Updated weights for policy 0, policy_version 77976 (0.0012) -[2023-11-28 02:15:18,185][87426] Updated weights for policy 1, policy_version 77880 (0.0012) -[2023-11-28 02:15:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 39895040. Throughput: 0: 2709.6, 1: 2722.3. Samples: 39908416. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:18,445][86177] Avg episode reward: [(0, '-506.110'), (1, '-522.400')] -[2023-11-28 02:15:19,902][87424] Updated weights for policy 0, policy_version 77986 (0.0009) -[2023-11-28 02:15:20,280][87424] Updated weights for policy 0, policy_version 77996 (0.0012) -[2023-11-28 02:15:20,342][87426] Updated weights for policy 1, policy_version 77890 (0.0012) -[2023-11-28 02:15:20,661][87424] Updated weights for policy 0, policy_version 78006 (0.0010) -[2023-11-28 02:15:20,729][87426] Updated weights for policy 1, policy_version 77900 (0.0011) -[2023-11-28 02:15:21,046][87424] Updated weights for policy 0, policy_version 78016 (0.0009) -[2023-11-28 02:15:21,098][87426] Updated weights for policy 1, policy_version 77910 (0.0011) -[2023-11-28 02:15:21,482][87426] Updated weights for policy 1, policy_version 77920 (0.0012) -[2023-11-28 02:15:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 39919616. Throughput: 0: 2718.0, 1: 2712.9. Samples: 39940580. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:23,445][86177] Avg episode reward: [(0, '-503.830'), (1, '-518.220')] -[2023-11-28 02:15:23,519][87424] Updated weights for policy 0, policy_version 78026 (0.0009) -[2023-11-28 02:15:23,876][87426] Updated weights for policy 1, policy_version 77930 (0.0010) -[2023-11-28 02:15:23,901][87424] Updated weights for policy 0, policy_version 78036 (0.0011) -[2023-11-28 02:15:24,261][87426] Updated weights for policy 1, policy_version 77940 (0.0007) -[2023-11-28 02:15:24,283][87424] Updated weights for policy 0, policy_version 78046 (0.0008) -[2023-11-28 02:15:24,633][87426] Updated weights for policy 1, policy_version 77950 (0.0009) -[2023-11-28 02:15:26,255][87424] Updated weights for policy 0, policy_version 78056 (0.0011) -[2023-11-28 02:15:26,645][87424] Updated weights for policy 0, policy_version 78066 (0.0012) -[2023-11-28 02:15:27,030][87424] Updated weights for policy 0, policy_version 78076 (0.0010) -[2023-11-28 02:15:27,086][87426] Updated weights for policy 1, policy_version 77960 (0.0009) -[2023-11-28 02:15:27,478][87426] Updated weights for policy 1, policy_version 77970 (0.0007) -[2023-11-28 02:15:27,853][87426] Updated weights for policy 1, policy_version 77980 (0.0008) -[2023-11-28 02:15:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 39952384. Throughput: 0: 2711.2, 1: 2726.7. Samples: 39965096. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:28,445][86177] Avg episode reward: [(0, '-498.760'), (1, '-546.840')] -[2023-11-28 02:15:29,291][87424] Updated weights for policy 0, policy_version 78086 (0.0010) -[2023-11-28 02:15:29,556][87426] Updated weights for policy 1, policy_version 77990 (0.0009) -[2023-11-28 02:15:29,665][87424] Updated weights for policy 0, policy_version 78096 (0.0011) -[2023-11-28 02:15:29,931][87426] Updated weights for policy 1, policy_version 78000 (0.0011) -[2023-11-28 02:15:30,049][87424] Updated weights for policy 0, policy_version 78106 (0.0011) -[2023-11-28 02:15:30,310][87426] Updated weights for policy 1, policy_version 78010 (0.0011) -[2023-11-28 02:15:32,381][87424] Updated weights for policy 0, policy_version 78116 (0.0014) -[2023-11-28 02:15:32,767][87424] Updated weights for policy 0, policy_version 78126 (0.0010) -[2023-11-28 02:15:32,781][87426] Updated weights for policy 1, policy_version 78020 (0.0010) -[2023-11-28 02:15:33,153][87424] Updated weights for policy 0, policy_version 78136 (0.0009) -[2023-11-28 02:15:33,155][87426] Updated weights for policy 1, policy_version 78030 (0.0009) -[2023-11-28 02:15:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 39968768. Throughput: 0: 2703.5, 1: 2736.8. Samples: 39989580. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:33,445][86177] Avg episode reward: [(0, '-505.220'), (1, '-545.570')] -[2023-11-28 02:15:33,536][87426] Updated weights for policy 1, policy_version 78040 (0.0008) -[2023-11-28 02:15:34,870][87424] Updated weights for policy 0, policy_version 78146 (0.0011) -[2023-11-28 02:15:35,250][87424] Updated weights for policy 0, policy_version 78156 (0.0012) -[2023-11-28 02:15:35,646][87424] Updated weights for policy 0, policy_version 78166 (0.0012) -[2023-11-28 02:15:36,025][87424] Updated weights for policy 0, policy_version 78176 (0.0012) -[2023-11-28 02:15:36,091][87426] Updated weights for policy 1, policy_version 78050 (0.0008) -[2023-11-28 02:15:36,463][87426] Updated weights for policy 1, policy_version 78060 (0.0009) -[2023-11-28 02:15:36,856][87426] Updated weights for policy 1, policy_version 78070 (0.0010) -[2023-11-28 02:15:37,234][87426] Updated weights for policy 1, policy_version 78080 (0.0012) -[2023-11-28 02:15:37,815][87424] Updated weights for policy 0, policy_version 78186 (0.0012) -[2023-11-28 02:15:38,197][87424] Updated weights for policy 0, policy_version 78196 (0.0012) -[2023-11-28 02:15:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 40001536. Throughput: 0: 2708.7, 1: 2726.9. Samples: 40022412. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:38,445][86177] Avg episode reward: [(0, '-501.790'), (1, '-544.550')] -[2023-11-28 02:15:38,577][87424] Updated weights for policy 0, policy_version 78206 (0.0012) -[2023-11-28 02:15:38,979][87426] Updated weights for policy 1, policy_version 78090 (0.0009) -[2023-11-28 02:15:39,355][87426] Updated weights for policy 1, policy_version 78100 (0.0011) -[2023-11-28 02:15:39,726][87426] Updated weights for policy 1, policy_version 78110 (0.0011) -[2023-11-28 02:15:41,025][87424] Updated weights for policy 0, policy_version 78216 (0.0011) -[2023-11-28 02:15:41,406][87424] Updated weights for policy 0, policy_version 78226 (0.0010) -[2023-11-28 02:15:41,796][87424] Updated weights for policy 0, policy_version 78236 (0.0011) -[2023-11-28 02:15:42,287][87426] Updated weights for policy 1, policy_version 78120 (0.0009) -[2023-11-28 02:15:42,660][87426] Updated weights for policy 1, policy_version 78130 (0.0012) -[2023-11-28 02:15:43,041][87426] Updated weights for policy 1, policy_version 78140 (0.0011) -[2023-11-28 02:15:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 40034304. Throughput: 0: 2686.8, 1: 2726.8. Samples: 40045748. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:43,445][86177] Avg episode reward: [(0, '-505.100'), (1, '-541.650')] -[2023-11-28 02:15:43,917][87424] Updated weights for policy 0, policy_version 78246 (0.0012) -[2023-11-28 02:15:44,295][87424] Updated weights for policy 0, policy_version 78256 (0.0010) -[2023-11-28 02:15:44,679][87424] Updated weights for policy 0, policy_version 78266 (0.0010) -[2023-11-28 02:15:45,170][87426] Updated weights for policy 1, policy_version 78150 (0.0008) -[2023-11-28 02:15:45,537][87426] Updated weights for policy 1, policy_version 78160 (0.0010) -[2023-11-28 02:15:45,915][87426] Updated weights for policy 1, policy_version 78170 (0.0012) -[2023-11-28 02:15:47,187][87424] Updated weights for policy 0, policy_version 78276 (0.0009) -[2023-11-28 02:15:47,568][87424] Updated weights for policy 0, policy_version 78286 (0.0009) -[2023-11-28 02:15:47,644][87426] Updated weights for policy 1, policy_version 78180 (0.0010) -[2023-11-28 02:15:47,952][87424] Updated weights for policy 0, policy_version 78296 (0.0007) -[2023-11-28 02:15:48,016][87426] Updated weights for policy 1, policy_version 78190 (0.0009) -[2023-11-28 02:15:48,396][87426] Updated weights for policy 1, policy_version 78200 (0.0007) -[2023-11-28 02:15:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 40058880. Throughput: 0: 2646.7, 1: 2705.0. Samples: 40068936. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:48,445][86177] Avg episode reward: [(0, '-506.960'), (1, '-511.280')] -[2023-11-28 02:15:50,501][87424] Updated weights for policy 0, policy_version 78306 (0.0007) -[2023-11-28 02:15:50,565][87426] Updated weights for policy 1, policy_version 78210 (0.0009) -[2023-11-28 02:15:50,878][87424] Updated weights for policy 0, policy_version 78316 (0.0007) -[2023-11-28 02:15:50,947][87426] Updated weights for policy 1, policy_version 78220 (0.0007) -[2023-11-28 02:15:51,259][87424] Updated weights for policy 0, policy_version 78326 (0.0008) -[2023-11-28 02:15:51,322][87426] Updated weights for policy 1, policy_version 78230 (0.0010) -[2023-11-28 02:15:51,641][87424] Updated weights for policy 0, policy_version 78336 (0.0008) -[2023-11-28 02:15:51,704][87426] Updated weights for policy 1, policy_version 78240 (0.0011) -[2023-11-28 02:15:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 40083456. Throughput: 0: 2655.6, 1: 2689.9. Samples: 40100732. Policy #0 lag: (min: 31.0, avg: 51.4, max: 75.0) -[2023-11-28 02:15:53,445][86177] Avg episode reward: [(0, '-503.400'), (1, '-514.110')] -[2023-11-28 02:15:53,781][87426] Updated weights for policy 1, policy_version 78250 (0.0012) -[2023-11-28 02:15:54,103][87424] Updated weights for policy 0, policy_version 78346 (0.0011) -[2023-11-28 02:15:54,168][87426] Updated weights for policy 1, policy_version 78260 (0.0009) -[2023-11-28 02:15:54,481][87424] Updated weights for policy 0, policy_version 78356 (0.0011) -[2023-11-28 02:15:54,549][87426] Updated weights for policy 1, policy_version 78270 (0.0007) -[2023-11-28 02:15:54,868][87424] Updated weights for policy 0, policy_version 78366 (0.0011) -[2023-11-28 02:15:56,901][87424] Updated weights for policy 0, policy_version 78376 (0.0010) -[2023-11-28 02:15:56,942][87426] Updated weights for policy 1, policy_version 78280 (0.0010) -[2023-11-28 02:15:57,276][87424] Updated weights for policy 0, policy_version 78386 (0.0010) -[2023-11-28 02:15:57,326][87426] Updated weights for policy 1, policy_version 78290 (0.0010) -[2023-11-28 02:15:57,655][87424] Updated weights for policy 0, policy_version 78396 (0.0008) -[2023-11-28 02:15:57,688][87426] Updated weights for policy 1, policy_version 78300 (0.0011) -[2023-11-28 02:15:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 40116224. Throughput: 0: 2674.2, 1: 2695.1. Samples: 40125436. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:15:58,445][86177] Avg episode reward: [(0, '-505.440'), (1, '-514.850')] -[2023-11-28 02:15:59,723][87424] Updated weights for policy 0, policy_version 78406 (0.0010) -[2023-11-28 02:15:59,821][87426] Updated weights for policy 1, policy_version 78310 (0.0011) -[2023-11-28 02:16:00,100][87424] Updated weights for policy 0, policy_version 78416 (0.0010) -[2023-11-28 02:16:00,190][87426] Updated weights for policy 1, policy_version 78320 (0.0011) -[2023-11-28 02:16:00,483][87424] Updated weights for policy 0, policy_version 78426 (0.0010) -[2023-11-28 02:16:00,566][87426] Updated weights for policy 1, policy_version 78330 (0.0009) -[2023-11-28 02:16:03,003][87424] Updated weights for policy 0, policy_version 78436 (0.0011) -[2023-11-28 02:16:03,093][87426] Updated weights for policy 1, policy_version 78340 (0.0009) -[2023-11-28 02:16:03,382][87424] Updated weights for policy 0, policy_version 78446 (0.0009) -[2023-11-28 02:16:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 40132608. Throughput: 0: 2672.2, 1: 2692.5. Samples: 40149828. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:16:03,445][86177] Avg episode reward: [(0, '-514.380'), (1, '-514.660')] -[2023-11-28 02:16:03,471][87426] Updated weights for policy 1, policy_version 78350 (0.0011) -[2023-11-28 02:16:03,774][87424] Updated weights for policy 0, policy_version 78456 (0.0009) -[2023-11-28 02:16:03,854][87426] Updated weights for policy 1, policy_version 78360 (0.0008) -[2023-11-28 02:16:05,823][87424] Updated weights for policy 0, policy_version 78466 (0.0009) -[2023-11-28 02:16:06,006][87426] Updated weights for policy 1, policy_version 78370 (0.0007) -[2023-11-28 02:16:06,206][87424] Updated weights for policy 0, policy_version 78476 (0.0012) -[2023-11-28 02:16:06,387][87426] Updated weights for policy 1, policy_version 78380 (0.0007) -[2023-11-28 02:16:06,580][87424] Updated weights for policy 0, policy_version 78486 (0.0012) -[2023-11-28 02:16:06,768][87426] Updated weights for policy 1, policy_version 78390 (0.0008) -[2023-11-28 02:16:06,962][87424] Updated weights for policy 0, policy_version 78496 (0.0012) -[2023-11-28 02:16:07,151][87426] Updated weights for policy 1, policy_version 78400 (0.0008) -[2023-11-28 02:16:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 40165376. Throughput: 0: 2680.5, 1: 2680.3. Samples: 40181820. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:16:08,445][86177] Avg episode reward: [(0, '-516.160'), (1, '-557.450')] -[2023-11-28 02:16:09,298][87424] Updated weights for policy 0, policy_version 78506 (0.0010) -[2023-11-28 02:16:09,476][87426] Updated weights for policy 1, policy_version 78410 (0.0012) -[2023-11-28 02:16:09,682][87424] Updated weights for policy 0, policy_version 78516 (0.0007) -[2023-11-28 02:16:09,849][87426] Updated weights for policy 1, policy_version 78420 (0.0011) -[2023-11-28 02:16:10,074][87424] Updated weights for policy 0, policy_version 78526 (0.0012) -[2023-11-28 02:16:10,241][87426] Updated weights for policy 1, policy_version 78430 (0.0011) -[2023-11-28 02:16:12,051][87426] Updated weights for policy 1, policy_version 78440 (0.0011) -[2023-11-28 02:16:12,429][87424] Updated weights for policy 0, policy_version 78536 (0.0009) -[2023-11-28 02:16:12,429][87426] Updated weights for policy 1, policy_version 78450 (0.0011) -[2023-11-28 02:16:12,812][87426] Updated weights for policy 1, policy_version 78460 (0.0008) -[2023-11-28 02:16:12,812][87424] Updated weights for policy 0, policy_version 78546 (0.0010) -[2023-11-28 02:16:13,193][87424] Updated weights for policy 0, policy_version 78556 (0.0012) -[2023-11-28 02:16:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 40198144. Throughput: 0: 2679.1, 1: 2674.4. Samples: 40206004. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:16:13,445][86177] Avg episode reward: [(0, '-515.560'), (1, '-553.390')] -[2023-11-28 02:16:14,978][87424] Updated weights for policy 0, policy_version 78566 (0.0012) -[2023-11-28 02:16:15,286][87426] Updated weights for policy 1, policy_version 78470 (0.0011) -[2023-11-28 02:16:15,364][87424] Updated weights for policy 0, policy_version 78576 (0.0010) -[2023-11-28 02:16:15,665][87426] Updated weights for policy 1, policy_version 78480 (0.0012) -[2023-11-28 02:16:15,743][87424] Updated weights for policy 0, policy_version 78586 (0.0012) -[2023-11-28 02:16:16,049][87426] Updated weights for policy 1, policy_version 78490 (0.0011) -[2023-11-28 02:16:17,915][87424] Updated weights for policy 0, policy_version 78596 (0.0012) -[2023-11-28 02:16:17,947][87426] Updated weights for policy 1, policy_version 78500 (0.0010) -[2023-11-28 02:16:18,296][87424] Updated weights for policy 0, policy_version 78606 (0.0009) -[2023-11-28 02:16:18,327][87426] Updated weights for policy 1, policy_version 78510 (0.0010) -[2023-11-28 02:16:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 40214528. Throughput: 0: 2681.4, 1: 2662.8. Samples: 40230068. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:16:18,445][86177] Avg episode reward: [(0, '-518.810'), (1, '-563.090')] -[2023-11-28 02:16:18,676][87424] Updated weights for policy 0, policy_version 78616 (0.0012) -[2023-11-28 02:16:18,705][87426] Updated weights for policy 1, policy_version 78520 (0.0010) -[2023-11-28 02:16:18,976][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000078624_20127744.pth... -[2023-11-28 02:16:19,007][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000078528_20103168.pth... -[2023-11-28 02:16:19,007][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000076096_19480576.pth -[2023-11-28 02:16:19,037][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000076000_19456000.pth -[2023-11-28 02:16:20,974][87424] Updated weights for policy 0, policy_version 78626 (0.0010) -[2023-11-28 02:16:21,138][87426] Updated weights for policy 1, policy_version 78530 (0.0011) -[2023-11-28 02:16:21,374][87424] Updated weights for policy 0, policy_version 78636 (0.0010) -[2023-11-28 02:16:21,520][87426] Updated weights for policy 1, policy_version 78540 (0.0008) -[2023-11-28 02:16:21,745][87424] Updated weights for policy 0, policy_version 78646 (0.0011) -[2023-11-28 02:16:21,910][87426] Updated weights for policy 1, policy_version 78550 (0.0010) -[2023-11-28 02:16:22,126][87424] Updated weights for policy 0, policy_version 78656 (0.0012) -[2023-11-28 02:16:22,277][87426] Updated weights for policy 1, policy_version 78560 (0.0011) -[2023-11-28 02:16:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 40247296. Throughput: 0: 2677.1, 1: 2673.2. Samples: 40263172. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:16:23,445][86177] Avg episode reward: [(0, '-507.450'), (1, '-585.140')] -[2023-11-28 02:16:24,108][87424] Updated weights for policy 0, policy_version 78666 (0.0008) -[2023-11-28 02:16:24,489][87424] Updated weights for policy 0, policy_version 78676 (0.0011) -[2023-11-28 02:16:24,806][87426] Updated weights for policy 1, policy_version 78570 (0.0008) -[2023-11-28 02:16:24,881][87424] Updated weights for policy 0, policy_version 78686 (0.0009) -[2023-11-28 02:16:25,182][87426] Updated weights for policy 1, policy_version 78580 (0.0011) -[2023-11-28 02:16:25,572][87426] Updated weights for policy 1, policy_version 78590 (0.0011) -[2023-11-28 02:16:26,805][87424] Updated weights for policy 0, policy_version 78696 (0.0011) -[2023-11-28 02:16:27,173][87424] Updated weights for policy 0, policy_version 78706 (0.0010) -[2023-11-28 02:16:27,562][87424] Updated weights for policy 0, policy_version 78716 (0.0009) -[2023-11-28 02:16:27,860][87426] Updated weights for policy 1, policy_version 78600 (0.0008) -[2023-11-28 02:16:28,232][87426] Updated weights for policy 1, policy_version 78610 (0.0011) -[2023-11-28 02:16:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 40271872. Throughput: 0: 2706.4, 1: 2697.1. Samples: 40288904. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:16:28,445][86177] Avg episode reward: [(0, '-512.330'), (1, '-540.380')] -[2023-11-28 02:16:28,604][87426] Updated weights for policy 1, policy_version 78620 (0.0012) -[2023-11-28 02:16:29,344][87424] Updated weights for policy 0, policy_version 78726 (0.0012) -[2023-11-28 02:16:29,723][87424] Updated weights for policy 0, policy_version 78736 (0.0012) -[2023-11-28 02:16:30,105][87424] Updated weights for policy 0, policy_version 78746 (0.0011) -[2023-11-28 02:16:30,459][87426] Updated weights for policy 1, policy_version 78630 (0.0012) -[2023-11-28 02:16:30,847][87426] Updated weights for policy 1, policy_version 78640 (0.0009) -[2023-11-28 02:16:31,217][87426] Updated weights for policy 1, policy_version 78650 (0.0007) -[2023-11-28 02:16:32,356][87424] Updated weights for policy 0, policy_version 78756 (0.0010) -[2023-11-28 02:16:32,741][87424] Updated weights for policy 0, policy_version 78766 (0.0007) -[2023-11-28 02:16:33,133][87424] Updated weights for policy 0, policy_version 78776 (0.0009) -[2023-11-28 02:16:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 40304640. Throughput: 0: 2766.4, 1: 2710.0. Samples: 40315376. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:16:33,445][86177] Avg episode reward: [(0, '-511.440'), (1, '-549.240')] -[2023-11-28 02:16:33,675][87426] Updated weights for policy 1, policy_version 78660 (0.0009) -[2023-11-28 02:16:34,054][87426] Updated weights for policy 1, policy_version 78670 (0.0011) -[2023-11-28 02:16:34,427][87426] Updated weights for policy 1, policy_version 78680 (0.0008) -[2023-11-28 02:16:34,841][87424] Updated weights for policy 0, policy_version 78786 (0.0011) -[2023-11-28 02:16:35,214][87424] Updated weights for policy 0, policy_version 78796 (0.0012) -[2023-11-28 02:16:35,608][87424] Updated weights for policy 0, policy_version 78806 (0.0012) -[2023-11-28 02:16:35,996][87424] Updated weights for policy 0, policy_version 78816 (0.0012) -[2023-11-28 02:16:36,472][87426] Updated weights for policy 1, policy_version 78690 (0.0009) -[2023-11-28 02:16:36,849][87426] Updated weights for policy 1, policy_version 78700 (0.0012) -[2023-11-28 02:16:37,232][87426] Updated weights for policy 1, policy_version 78710 (0.0010) -[2023-11-28 02:16:37,619][87426] Updated weights for policy 1, policy_version 78720 (0.0010) -[2023-11-28 02:16:38,179][87424] Updated weights for policy 0, policy_version 78826 (0.0010) -[2023-11-28 02:16:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 40329216. Throughput: 0: 2806.9, 1: 2717.7. Samples: 40349336. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:16:38,445][86177] Avg episode reward: [(0, '-509.830'), (1, '-537.080')] -[2023-11-28 02:16:38,558][87424] Updated weights for policy 0, policy_version 78836 (0.0008) -[2023-11-28 02:16:38,935][87424] Updated weights for policy 0, policy_version 78846 (0.0009) -[2023-11-28 02:16:39,503][87426] Updated weights for policy 1, policy_version 78730 (0.0008) -[2023-11-28 02:16:39,909][87426] Updated weights for policy 1, policy_version 78740 (0.0009) -[2023-11-28 02:16:40,283][87426] Updated weights for policy 1, policy_version 78750 (0.0009) -[2023-11-28 02:16:40,896][87424] Updated weights for policy 0, policy_version 78856 (0.0011) -[2023-11-28 02:16:41,287][87424] Updated weights for policy 0, policy_version 78866 (0.0010) -[2023-11-28 02:16:41,659][87424] Updated weights for policy 0, policy_version 78876 (0.0008) -[2023-11-28 02:16:42,554][87426] Updated weights for policy 1, policy_version 78760 (0.0011) -[2023-11-28 02:16:42,934][87426] Updated weights for policy 1, policy_version 78770 (0.0012) -[2023-11-28 02:16:43,312][87426] Updated weights for policy 1, policy_version 78780 (0.0012) -[2023-11-28 02:16:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 40353792. Throughput: 0: 2795.5, 1: 2707.9. Samples: 40373088. Policy #0 lag: (min: 6.0, avg: 25.1, max: 38.0) -[2023-11-28 02:16:43,445][86177] Avg episode reward: [(0, '-509.100'), (1, '-522.660')] -[2023-11-28 02:16:43,988][87424] Updated weights for policy 0, policy_version 78886 (0.0011) -[2023-11-28 02:16:44,381][87424] Updated weights for policy 0, policy_version 78896 (0.0012) -[2023-11-28 02:16:44,759][87424] Updated weights for policy 0, policy_version 78906 (0.0012) -[2023-11-28 02:16:45,896][87426] Updated weights for policy 1, policy_version 78790 (0.0012) -[2023-11-28 02:16:46,276][87426] Updated weights for policy 1, policy_version 78800 (0.0011) -[2023-11-28 02:16:46,648][87426] Updated weights for policy 1, policy_version 78810 (0.0011) -[2023-11-28 02:16:46,665][87424] Updated weights for policy 0, policy_version 78916 (0.0012) -[2023-11-28 02:16:47,043][87424] Updated weights for policy 0, policy_version 78926 (0.0011) -[2023-11-28 02:16:47,422][87424] Updated weights for policy 0, policy_version 78936 (0.0011) -[2023-11-28 02:16:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 40386560. Throughput: 0: 2799.3, 1: 2690.3. Samples: 40396860. Policy #0 lag: (min: 7.0, avg: 12.5, max: 39.0) -[2023-11-28 02:16:48,445][86177] Avg episode reward: [(0, '-500.530'), (1, '-521.620')] -[2023-11-28 02:16:48,754][87426] Updated weights for policy 1, policy_version 78820 (0.0009) -[2023-11-28 02:16:49,139][87426] Updated weights for policy 1, policy_version 78830 (0.0011) -[2023-11-28 02:16:49,330][87424] Updated weights for policy 0, policy_version 78946 (0.0012) -[2023-11-28 02:16:49,517][87426] Updated weights for policy 1, policy_version 78840 (0.0010) -[2023-11-28 02:16:49,711][87424] Updated weights for policy 0, policy_version 78956 (0.0012) -[2023-11-28 02:16:50,094][87424] Updated weights for policy 0, policy_version 78966 (0.0012) -[2023-11-28 02:16:50,478][87424] Updated weights for policy 0, policy_version 78976 (0.0011) -[2023-11-28 02:16:51,707][87426] Updated weights for policy 1, policy_version 78850 (0.0011) -[2023-11-28 02:16:52,082][87426] Updated weights for policy 1, policy_version 78860 (0.0011) -[2023-11-28 02:16:52,454][87426] Updated weights for policy 1, policy_version 78870 (0.0011) -[2023-11-28 02:16:52,836][87426] Updated weights for policy 1, policy_version 78880 (0.0010) -[2023-11-28 02:16:52,915][87424] Updated weights for policy 0, policy_version 78986 (0.0012) -[2023-11-28 02:16:53,296][87424] Updated weights for policy 0, policy_version 78996 (0.0012) -[2023-11-28 02:16:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 40411136. Throughput: 0: 2785.0, 1: 2713.8. Samples: 40429264. Policy #0 lag: (min: 7.0, avg: 12.5, max: 39.0) -[2023-11-28 02:16:53,445][86177] Avg episode reward: [(0, '-501.520'), (1, '-515.350')] -[2023-11-28 02:16:53,673][87424] Updated weights for policy 0, policy_version 79006 (0.0016) -[2023-11-28 02:16:55,291][87426] Updated weights for policy 1, policy_version 78890 (0.0008) -[2023-11-28 02:16:55,673][87426] Updated weights for policy 1, policy_version 78900 (0.0008) -[2023-11-28 02:16:56,051][87426] Updated weights for policy 1, policy_version 78910 (0.0008) -[2023-11-28 02:16:56,097][87424] Updated weights for policy 0, policy_version 79016 (0.0008) -[2023-11-28 02:16:56,486][87424] Updated weights for policy 0, policy_version 79026 (0.0009) -[2023-11-28 02:16:56,875][87424] Updated weights for policy 0, policy_version 79036 (0.0007) -[2023-11-28 02:16:58,028][87426] Updated weights for policy 1, policy_version 78920 (0.0007) -[2023-11-28 02:16:58,404][87426] Updated weights for policy 1, policy_version 78930 (0.0007) -[2023-11-28 02:16:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 40435712. Throughput: 0: 2794.7, 1: 2707.2. Samples: 40453588. Policy #0 lag: (min: 7.0, avg: 12.5, max: 39.0) -[2023-11-28 02:16:58,445][86177] Avg episode reward: [(0, '-503.360'), (1, '-524.630')] -[2023-11-28 02:16:58,607][87424] Updated weights for policy 0, policy_version 79046 (0.0008) -[2023-11-28 02:16:58,782][87426] Updated weights for policy 1, policy_version 78940 (0.0011) -[2023-11-28 02:16:58,978][87424] Updated weights for policy 0, policy_version 79056 (0.0011) -[2023-11-28 02:16:59,361][87424] Updated weights for policy 0, policy_version 79066 (0.0011) -[2023-11-28 02:17:00,755][87426] Updated weights for policy 1, policy_version 78950 (0.0010) -[2023-11-28 02:17:01,128][87426] Updated weights for policy 1, policy_version 78960 (0.0008) -[2023-11-28 02:17:01,400][87424] Updated weights for policy 0, policy_version 79076 (0.0010) -[2023-11-28 02:17:01,510][87426] Updated weights for policy 1, policy_version 78970 (0.0008) -[2023-11-28 02:17:01,783][87424] Updated weights for policy 0, policy_version 79086 (0.0010) -[2023-11-28 02:17:02,171][87424] Updated weights for policy 0, policy_version 79096 (0.0012) -[2023-11-28 02:17:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 40468480. Throughput: 0: 2797.6, 1: 2709.3. Samples: 40477876. Policy #0 lag: (min: 7.0, avg: 12.5, max: 39.0) -[2023-11-28 02:17:03,445][86177] Avg episode reward: [(0, '-509.110'), (1, '-518.620')] -[2023-11-28 02:17:03,531][87426] Updated weights for policy 1, policy_version 78980 (0.0012) -[2023-11-28 02:17:03,911][87426] Updated weights for policy 1, policy_version 78990 (0.0011) -[2023-11-28 02:17:04,285][87426] Updated weights for policy 1, policy_version 79000 (0.0010) -[2023-11-28 02:17:04,528][87424] Updated weights for policy 0, policy_version 79106 (0.0011) -[2023-11-28 02:17:04,907][87424] Updated weights for policy 0, policy_version 79116 (0.0011) -[2023-11-28 02:17:05,292][87424] Updated weights for policy 0, policy_version 79126 (0.0008) -[2023-11-28 02:17:05,671][87424] Updated weights for policy 0, policy_version 79136 (0.0007) -[2023-11-28 02:17:06,222][87426] Updated weights for policy 1, policy_version 79010 (0.0008) -[2023-11-28 02:17:06,599][87426] Updated weights for policy 1, policy_version 79020 (0.0008) -[2023-11-28 02:17:06,976][87426] Updated weights for policy 1, policy_version 79030 (0.0012) -[2023-11-28 02:17:07,354][87426] Updated weights for policy 1, policy_version 79040 (0.0012) -[2023-11-28 02:17:07,570][87424] Updated weights for policy 0, policy_version 79146 (0.0008) -[2023-11-28 02:17:07,954][87424] Updated weights for policy 0, policy_version 79156 (0.0011) -[2023-11-28 02:17:08,329][87424] Updated weights for policy 0, policy_version 79166 (0.0009) -[2023-11-28 02:17:08,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 40501248. Throughput: 0: 2798.6, 1: 2715.3. Samples: 40511296. Policy #0 lag: (min: 7.0, avg: 12.5, max: 39.0) -[2023-11-28 02:17:08,446][86177] Avg episode reward: [(0, '-509.630'), (1, '-529.770')] -[2023-11-28 02:17:09,166][87426] Updated weights for policy 1, policy_version 79050 (0.0010) -[2023-11-28 02:17:09,548][87426] Updated weights for policy 1, policy_version 79060 (0.0010) -[2023-11-28 02:17:09,928][87426] Updated weights for policy 1, policy_version 79070 (0.0011) -[2023-11-28 02:17:10,848][87424] Updated weights for policy 0, policy_version 79176 (0.0010) -[2023-11-28 02:17:11,234][87424] Updated weights for policy 0, policy_version 79186 (0.0011) -[2023-11-28 02:17:11,629][87424] Updated weights for policy 0, policy_version 79196 (0.0007) -[2023-11-28 02:17:12,353][87426] Updated weights for policy 1, policy_version 79080 (0.0009) -[2023-11-28 02:17:12,740][87426] Updated weights for policy 1, policy_version 79090 (0.0008) -[2023-11-28 02:17:13,117][87426] Updated weights for policy 1, policy_version 79100 (0.0010) -[2023-11-28 02:17:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 40525824. Throughput: 0: 2771.5, 1: 2690.5. Samples: 40534692. Policy #0 lag: (min: 7.0, avg: 12.5, max: 39.0) -[2023-11-28 02:17:13,445][86177] Avg episode reward: [(0, '-517.100'), (1, '-530.530')] -[2023-11-28 02:17:13,750][87424] Updated weights for policy 0, policy_version 79206 (0.0011) -[2023-11-28 02:17:14,122][87424] Updated weights for policy 0, policy_version 79216 (0.0011) -[2023-11-28 02:17:14,497][87424] Updated weights for policy 0, policy_version 79226 (0.0008) -[2023-11-28 02:17:15,653][87426] Updated weights for policy 1, policy_version 79110 (0.0011) -[2023-11-28 02:17:16,029][87426] Updated weights for policy 1, policy_version 79120 (0.0012) -[2023-11-28 02:17:16,396][87426] Updated weights for policy 1, policy_version 79130 (0.0010) -[2023-11-28 02:17:17,068][87424] Updated weights for policy 0, policy_version 79236 (0.0009) -[2023-11-28 02:17:17,442][87424] Updated weights for policy 0, policy_version 79246 (0.0010) -[2023-11-28 02:17:17,825][87424] Updated weights for policy 0, policy_version 79256 (0.0008) -[2023-11-28 02:17:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 40550400. Throughput: 0: 2717.4, 1: 2674.3. Samples: 40558004. Policy #0 lag: (min: 7.0, avg: 12.5, max: 39.0) -[2023-11-28 02:17:18,445][86177] Avg episode reward: [(0, '-521.010'), (1, '-522.270')] -[2023-11-28 02:17:18,737][87426] Updated weights for policy 1, policy_version 79140 (0.0011) -[2023-11-28 02:17:19,121][87426] Updated weights for policy 1, policy_version 79150 (0.0009) -[2023-11-28 02:17:19,507][87426] Updated weights for policy 1, policy_version 79160 (0.0008) -[2023-11-28 02:17:20,124][87424] Updated weights for policy 0, policy_version 79266 (0.0011) -[2023-11-28 02:17:20,508][87424] Updated weights for policy 0, policy_version 79276 (0.0010) -[2023-11-28 02:17:20,902][87424] Updated weights for policy 0, policy_version 79286 (0.0012) -[2023-11-28 02:17:21,268][87424] Updated weights for policy 0, policy_version 79296 (0.0011) -[2023-11-28 02:17:21,522][87426] Updated weights for policy 1, policy_version 79170 (0.0010) -[2023-11-28 02:17:21,913][87426] Updated weights for policy 1, policy_version 79180 (0.0012) -[2023-11-28 02:17:22,279][87426] Updated weights for policy 1, policy_version 79190 (0.0009) -[2023-11-28 02:17:22,655][87426] Updated weights for policy 1, policy_version 79200 (0.0010) -[2023-11-28 02:17:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 40574976. Throughput: 0: 2679.4, 1: 2661.9. Samples: 40589692. Policy #0 lag: (min: 7.0, avg: 12.5, max: 39.0) -[2023-11-28 02:17:23,445][86177] Avg episode reward: [(0, '-518.000'), (1, '-524.490')] -[2023-11-28 02:17:23,675][87424] Updated weights for policy 0, policy_version 79306 (0.0011) -[2023-11-28 02:17:24,064][87424] Updated weights for policy 0, policy_version 79316 (0.0011) -[2023-11-28 02:17:24,456][87424] Updated weights for policy 0, policy_version 79326 (0.0011) -[2023-11-28 02:17:25,240][87426] Updated weights for policy 1, policy_version 79210 (0.0008) -[2023-11-28 02:17:25,623][87426] Updated weights for policy 1, policy_version 79220 (0.0007) -[2023-11-28 02:17:26,007][87426] Updated weights for policy 1, policy_version 79230 (0.0007) -[2023-11-28 02:17:26,803][87424] Updated weights for policy 0, policy_version 79336 (0.0008) -[2023-11-28 02:17:27,190][87424] Updated weights for policy 0, policy_version 79346 (0.0007) -[2023-11-28 02:17:27,559][87424] Updated weights for policy 0, policy_version 79356 (0.0007) -[2023-11-28 02:17:27,830][87426] Updated weights for policy 1, policy_version 79240 (0.0010) -[2023-11-28 02:17:28,209][87426] Updated weights for policy 1, policy_version 79250 (0.0009) -[2023-11-28 02:17:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 40599552. Throughput: 0: 2686.3, 1: 2673.4. Samples: 40614276. Policy #0 lag: (min: 7.0, avg: 12.5, max: 39.0) -[2023-11-28 02:17:28,445][86177] Avg episode reward: [(0, '-541.630'), (1, '-520.700')] -[2023-11-28 02:17:28,591][87426] Updated weights for policy 1, policy_version 79260 (0.0011) -[2023-11-28 02:17:29,767][87424] Updated weights for policy 0, policy_version 79366 (0.0008) -[2023-11-28 02:17:30,143][87424] Updated weights for policy 0, policy_version 79376 (0.0008) -[2023-11-28 02:17:30,523][87424] Updated weights for policy 0, policy_version 79386 (0.0014) -[2023-11-28 02:17:30,936][87426] Updated weights for policy 1, policy_version 79270 (0.0011) -[2023-11-28 02:17:31,315][87426] Updated weights for policy 1, policy_version 79280 (0.0008) -[2023-11-28 02:17:31,686][87426] Updated weights for policy 1, policy_version 79290 (0.0008) -[2023-11-28 02:17:32,338][87424] Updated weights for policy 0, policy_version 79396 (0.0010) -[2023-11-28 02:17:32,729][87424] Updated weights for policy 0, policy_version 79406 (0.0011) -[2023-11-28 02:17:33,108][87424] Updated weights for policy 0, policy_version 79416 (0.0012) -[2023-11-28 02:17:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 40632320. Throughput: 0: 2700.0, 1: 2687.8. Samples: 40639312. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:17:33,445][86177] Avg episode reward: [(0, '-536.080'), (1, '-513.290')] -[2023-11-28 02:17:34,119][87426] Updated weights for policy 1, policy_version 79300 (0.0011) -[2023-11-28 02:17:34,499][87426] Updated weights for policy 1, policy_version 79310 (0.0012) -[2023-11-28 02:17:34,883][87426] Updated weights for policy 1, policy_version 79320 (0.0011) -[2023-11-28 02:17:34,926][87424] Updated weights for policy 0, policy_version 79426 (0.0011) -[2023-11-28 02:17:35,314][87424] Updated weights for policy 0, policy_version 79436 (0.0012) -[2023-11-28 02:17:35,704][87424] Updated weights for policy 0, policy_version 79446 (0.0010) -[2023-11-28 02:17:36,083][87424] Updated weights for policy 0, policy_version 79456 (0.0007) -[2023-11-28 02:17:37,491][87426] Updated weights for policy 1, policy_version 79330 (0.0011) -[2023-11-28 02:17:37,871][87426] Updated weights for policy 1, policy_version 79340 (0.0012) -[2023-11-28 02:17:38,250][87426] Updated weights for policy 1, policy_version 79350 (0.0012) -[2023-11-28 02:17:38,304][87424] Updated weights for policy 0, policy_version 79466 (0.0009) -[2023-11-28 02:17:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 40648704. Throughput: 0: 2730.1, 1: 2720.1. Samples: 40674520. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:17:38,445][86177] Avg episode reward: [(0, '-537.130'), (1, '-547.920')] -[2023-11-28 02:17:38,629][87426] Updated weights for policy 1, policy_version 79360 (0.0011) -[2023-11-28 02:17:38,689][87424] Updated weights for policy 0, policy_version 79476 (0.0011) -[2023-11-28 02:17:39,081][87424] Updated weights for policy 0, policy_version 79486 (0.0011) -[2023-11-28 02:17:40,512][87426] Updated weights for policy 1, policy_version 79370 (0.0012) -[2023-11-28 02:17:40,890][87426] Updated weights for policy 1, policy_version 79380 (0.0012) -[2023-11-28 02:17:41,216][87424] Updated weights for policy 0, policy_version 79496 (0.0011) -[2023-11-28 02:17:41,263][87426] Updated weights for policy 1, policy_version 79390 (0.0011) -[2023-11-28 02:17:41,601][87424] Updated weights for policy 0, policy_version 79506 (0.0008) -[2023-11-28 02:17:41,978][87424] Updated weights for policy 0, policy_version 79516 (0.0012) -[2023-11-28 02:17:43,332][87426] Updated weights for policy 1, policy_version 79400 (0.0011) -[2023-11-28 02:17:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 40681472. Throughput: 0: 2723.7, 1: 2731.2. Samples: 40699060. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:17:43,445][86177] Avg episode reward: [(0, '-527.690'), (1, '-573.810')] -[2023-11-28 02:17:43,714][87426] Updated weights for policy 1, policy_version 79410 (0.0010) -[2023-11-28 02:17:43,844][87424] Updated weights for policy 0, policy_version 79526 (0.0012) -[2023-11-28 02:17:44,090][87426] Updated weights for policy 1, policy_version 79420 (0.0011) -[2023-11-28 02:17:44,221][87424] Updated weights for policy 0, policy_version 79536 (0.0009) -[2023-11-28 02:17:44,602][87424] Updated weights for policy 0, policy_version 79546 (0.0008) -[2023-11-28 02:17:46,153][87426] Updated weights for policy 1, policy_version 79430 (0.0010) -[2023-11-28 02:17:46,524][87426] Updated weights for policy 1, policy_version 79440 (0.0011) -[2023-11-28 02:17:46,701][87424] Updated weights for policy 0, policy_version 79556 (0.0012) -[2023-11-28 02:17:46,902][87426] Updated weights for policy 1, policy_version 79450 (0.0007) -[2023-11-28 02:17:47,082][87424] Updated weights for policy 0, policy_version 79566 (0.0008) -[2023-11-28 02:17:47,459][87424] Updated weights for policy 0, policy_version 79576 (0.0009) -[2023-11-28 02:17:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 40714240. Throughput: 0: 2732.5, 1: 2725.4. Samples: 40723484. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:17:48,445][86177] Avg episode reward: [(0, '-517.390'), (1, '-579.220')] -[2023-11-28 02:17:49,019][87426] Updated weights for policy 1, policy_version 79460 (0.0009) -[2023-11-28 02:17:49,401][87426] Updated weights for policy 1, policy_version 79470 (0.0012) -[2023-11-28 02:17:49,575][87424] Updated weights for policy 0, policy_version 79586 (0.0011) -[2023-11-28 02:17:49,772][87426] Updated weights for policy 1, policy_version 79480 (0.0011) -[2023-11-28 02:17:49,945][87424] Updated weights for policy 0, policy_version 79596 (0.0012) -[2023-11-28 02:17:50,331][87424] Updated weights for policy 0, policy_version 79606 (0.0008) -[2023-11-28 02:17:50,713][87424] Updated weights for policy 0, policy_version 79616 (0.0015) -[2023-11-28 02:17:51,693][87426] Updated weights for policy 1, policy_version 79490 (0.0011) -[2023-11-28 02:17:52,065][87426] Updated weights for policy 1, policy_version 79500 (0.0009) -[2023-11-28 02:17:52,440][87426] Updated weights for policy 1, policy_version 79510 (0.0009) -[2023-11-28 02:17:52,824][87426] Updated weights for policy 1, policy_version 79520 (0.0008) -[2023-11-28 02:17:53,049][87424] Updated weights for policy 0, policy_version 79626 (0.0009) -[2023-11-28 02:17:53,438][87424] Updated weights for policy 0, policy_version 79636 (0.0010) -[2023-11-28 02:17:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 40738816. Throughput: 0: 2717.3, 1: 2715.5. Samples: 40755768. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:17:53,445][86177] Avg episode reward: [(0, '-520.170'), (1, '-589.780')] -[2023-11-28 02:17:53,825][87424] Updated weights for policy 0, policy_version 79646 (0.0008) -[2023-11-28 02:17:54,886][87426] Updated weights for policy 1, policy_version 79530 (0.0012) -[2023-11-28 02:17:55,270][87426] Updated weights for policy 1, policy_version 79540 (0.0007) -[2023-11-28 02:17:55,640][87426] Updated weights for policy 1, policy_version 79550 (0.0007) -[2023-11-28 02:17:56,303][87424] Updated weights for policy 0, policy_version 79656 (0.0007) -[2023-11-28 02:17:56,690][87424] Updated weights for policy 0, policy_version 79666 (0.0008) -[2023-11-28 02:17:57,063][87424] Updated weights for policy 0, policy_version 79676 (0.0007) -[2023-11-28 02:17:57,933][87426] Updated weights for policy 1, policy_version 79560 (0.0011) -[2023-11-28 02:17:58,305][87426] Updated weights for policy 1, policy_version 79570 (0.0012) -[2023-11-28 02:17:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 40763392. Throughput: 0: 2725.2, 1: 2711.9. Samples: 40779364. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:17:58,445][86177] Avg episode reward: [(0, '-512.700'), (1, '-556.360')] -[2023-11-28 02:17:58,681][87426] Updated weights for policy 1, policy_version 79580 (0.0012) -[2023-11-28 02:17:59,452][87424] Updated weights for policy 0, policy_version 79686 (0.0009) -[2023-11-28 02:17:59,834][87424] Updated weights for policy 0, policy_version 79696 (0.0009) -[2023-11-28 02:18:00,225][87424] Updated weights for policy 0, policy_version 79706 (0.0011) -[2023-11-28 02:18:01,144][87426] Updated weights for policy 1, policy_version 79590 (0.0012) -[2023-11-28 02:18:01,515][87426] Updated weights for policy 1, policy_version 79600 (0.0011) -[2023-11-28 02:18:01,893][87426] Updated weights for policy 1, policy_version 79610 (0.0010) -[2023-11-28 02:18:02,099][87424] Updated weights for policy 0, policy_version 79716 (0.0011) -[2023-11-28 02:18:02,484][87424] Updated weights for policy 0, policy_version 79726 (0.0011) -[2023-11-28 02:18:02,856][87424] Updated weights for policy 0, policy_version 79736 (0.0011) -[2023-11-28 02:18:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 40796160. Throughput: 0: 2774.6, 1: 2718.3. Samples: 40805184. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:18:03,445][86177] Avg episode reward: [(0, '-514.280'), (1, '-538.230')] -[2023-11-28 02:18:04,168][87426] Updated weights for policy 1, policy_version 79620 (0.0007) -[2023-11-28 02:18:04,546][87426] Updated weights for policy 1, policy_version 79630 (0.0010) -[2023-11-28 02:18:04,621][87424] Updated weights for policy 0, policy_version 79746 (0.0011) -[2023-11-28 02:18:04,920][87426] Updated weights for policy 1, policy_version 79640 (0.0011) -[2023-11-28 02:18:05,010][87424] Updated weights for policy 0, policy_version 79756 (0.0010) -[2023-11-28 02:18:05,383][87424] Updated weights for policy 0, policy_version 79766 (0.0011) -[2023-11-28 02:18:05,764][87424] Updated weights for policy 0, policy_version 79776 (0.0012) -[2023-11-28 02:18:06,982][87426] Updated weights for policy 1, policy_version 79650 (0.0012) -[2023-11-28 02:18:07,367][87426] Updated weights for policy 1, policy_version 79660 (0.0012) -[2023-11-28 02:18:07,739][87426] Updated weights for policy 1, policy_version 79670 (0.0011) -[2023-11-28 02:18:08,016][87424] Updated weights for policy 0, policy_version 79786 (0.0011) -[2023-11-28 02:18:08,117][87426] Updated weights for policy 1, policy_version 79680 (0.0011) -[2023-11-28 02:18:08,396][87424] Updated weights for policy 0, policy_version 79796 (0.0009) -[2023-11-28 02:18:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 40820736. Throughput: 0: 2804.1, 1: 2740.3. Samples: 40839192. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:18:08,445][86177] Avg episode reward: [(0, '-510.450'), (1, '-533.310')] -[2023-11-28 02:18:08,794][87424] Updated weights for policy 0, policy_version 79806 (0.0010) -[2023-11-28 02:18:10,116][87426] Updated weights for policy 1, policy_version 79690 (0.0012) -[2023-11-28 02:18:10,492][87426] Updated weights for policy 1, policy_version 79700 (0.0012) -[2023-11-28 02:18:10,868][87426] Updated weights for policy 1, policy_version 79710 (0.0011) -[2023-11-28 02:18:11,069][87424] Updated weights for policy 0, policy_version 79816 (0.0012) -[2023-11-28 02:18:11,448][87424] Updated weights for policy 0, policy_version 79826 (0.0012) -[2023-11-28 02:18:11,835][87424] Updated weights for policy 0, policy_version 79836 (0.0012) -[2023-11-28 02:18:13,257][87426] Updated weights for policy 1, policy_version 79720 (0.0012) -[2023-11-28 02:18:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 40845312. Throughput: 0: 2791.6, 1: 2739.0. Samples: 40863156. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:18:13,445][86177] Avg episode reward: [(0, '-516.150'), (1, '-531.330')] -[2023-11-28 02:18:13,636][87426] Updated weights for policy 1, policy_version 79730 (0.0011) -[2023-11-28 02:18:14,006][87426] Updated weights for policy 1, policy_version 79740 (0.0010) -[2023-11-28 02:18:14,069][87424] Updated weights for policy 0, policy_version 79846 (0.0012) -[2023-11-28 02:18:14,463][87424] Updated weights for policy 0, policy_version 79856 (0.0012) -[2023-11-28 02:18:14,840][87424] Updated weights for policy 0, policy_version 79866 (0.0012) -[2023-11-28 02:18:16,435][87426] Updated weights for policy 1, policy_version 79750 (0.0012) -[2023-11-28 02:18:16,813][87426] Updated weights for policy 1, policy_version 79760 (0.0011) -[2023-11-28 02:18:16,941][87424] Updated weights for policy 0, policy_version 79876 (0.0011) -[2023-11-28 02:18:17,197][87426] Updated weights for policy 1, policy_version 79770 (0.0012) -[2023-11-28 02:18:17,327][87424] Updated weights for policy 0, policy_version 79886 (0.0008) -[2023-11-28 02:18:17,710][87424] Updated weights for policy 0, policy_version 79896 (0.0010) -[2023-11-28 02:18:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 40878080. Throughput: 0: 2769.5, 1: 2744.7. Samples: 40887452. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:18:18,445][86177] Avg episode reward: [(0, '-517.060'), (1, '-529.410')] -[2023-11-28 02:18:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000079904_20455424.pth... -[2023-11-28 02:18:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000079776_20422656.pth... -[2023-11-28 02:18:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000077344_19800064.pth -[2023-11-28 02:18:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000077248_19775488.pth -[2023-11-28 02:18:19,093][87426] Updated weights for policy 1, policy_version 79780 (0.0010) -[2023-11-28 02:18:19,463][87426] Updated weights for policy 1, policy_version 79790 (0.0008) -[2023-11-28 02:18:19,849][87426] Updated weights for policy 1, policy_version 79800 (0.0011) -[2023-11-28 02:18:19,861][87424] Updated weights for policy 0, policy_version 79906 (0.0012) -[2023-11-28 02:18:20,237][87424] Updated weights for policy 0, policy_version 79916 (0.0010) -[2023-11-28 02:18:20,619][87424] Updated weights for policy 0, policy_version 79926 (0.0009) -[2023-11-28 02:18:21,001][87424] Updated weights for policy 0, policy_version 79936 (0.0010) -[2023-11-28 02:18:22,372][87426] Updated weights for policy 1, policy_version 79810 (0.0011) -[2023-11-28 02:18:22,750][87426] Updated weights for policy 1, policy_version 79820 (0.0012) -[2023-11-28 02:18:22,969][87424] Updated weights for policy 0, policy_version 79946 (0.0011) -[2023-11-28 02:18:23,129][87426] Updated weights for policy 1, policy_version 79830 (0.0011) -[2023-11-28 02:18:23,341][87424] Updated weights for policy 0, policy_version 79956 (0.0012) -[2023-11-28 02:18:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 40894464. Throughput: 0: 2736.1, 1: 2694.4. Samples: 40918892. Policy #0 lag: (min: 18.0, avg: 48.4, max: 81.0) -[2023-11-28 02:18:23,446][86177] Avg episode reward: [(0, '-515.470'), (1, '-522.460')] -[2023-11-28 02:18:23,508][87426] Updated weights for policy 1, policy_version 79840 (0.0010) -[2023-11-28 02:18:23,728][87424] Updated weights for policy 0, policy_version 79966 (0.0012) -[2023-11-28 02:18:25,645][87426] Updated weights for policy 1, policy_version 79850 (0.0008) -[2023-11-28 02:18:26,031][87426] Updated weights for policy 1, policy_version 79860 (0.0008) -[2023-11-28 02:18:26,245][87424] Updated weights for policy 0, policy_version 79976 (0.0012) -[2023-11-28 02:18:26,406][87426] Updated weights for policy 1, policy_version 79870 (0.0008) -[2023-11-28 02:18:26,620][87424] Updated weights for policy 0, policy_version 79986 (0.0011) -[2023-11-28 02:18:27,005][87424] Updated weights for policy 0, policy_version 79996 (0.0012) -[2023-11-28 02:18:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 40927232. Throughput: 0: 2718.6, 1: 2686.7. Samples: 40942296. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:18:28,445][86177] Avg episode reward: [(0, '-516.190'), (1, '-531.880')] -[2023-11-28 02:18:28,727][87426] Updated weights for policy 1, policy_version 79880 (0.0011) -[2023-11-28 02:18:29,039][87424] Updated weights for policy 0, policy_version 80006 (0.0012) -[2023-11-28 02:18:29,120][87426] Updated weights for policy 1, policy_version 79890 (0.0011) -[2023-11-28 02:18:29,418][87424] Updated weights for policy 0, policy_version 80016 (0.0011) -[2023-11-28 02:18:29,494][87426] Updated weights for policy 1, policy_version 79900 (0.0010) -[2023-11-28 02:18:29,801][87424] Updated weights for policy 0, policy_version 80026 (0.0011) -[2023-11-28 02:18:31,393][87426] Updated weights for policy 1, policy_version 79910 (0.0010) -[2023-11-28 02:18:31,775][87426] Updated weights for policy 1, policy_version 79920 (0.0009) -[2023-11-28 02:18:32,159][87426] Updated weights for policy 1, policy_version 79930 (0.0009) -[2023-11-28 02:18:32,298][87424] Updated weights for policy 0, policy_version 80036 (0.0011) -[2023-11-28 02:18:32,676][87424] Updated weights for policy 0, policy_version 80046 (0.0012) -[2023-11-28 02:18:33,059][87424] Updated weights for policy 0, policy_version 80056 (0.0012) -[2023-11-28 02:18:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 40960000. Throughput: 0: 2706.2, 1: 2689.9. Samples: 40966308. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:18:33,445][86177] Avg episode reward: [(0, '-510.350'), (1, '-537.050')] -[2023-11-28 02:18:34,231][87426] Updated weights for policy 1, policy_version 79940 (0.0011) -[2023-11-28 02:18:34,616][87426] Updated weights for policy 1, policy_version 79950 (0.0012) -[2023-11-28 02:18:34,968][87424] Updated weights for policy 0, policy_version 80066 (0.0012) -[2023-11-28 02:18:34,992][87426] Updated weights for policy 1, policy_version 79960 (0.0012) -[2023-11-28 02:18:35,348][87424] Updated weights for policy 0, policy_version 80076 (0.0012) -[2023-11-28 02:18:35,735][87424] Updated weights for policy 0, policy_version 80086 (0.0012) -[2023-11-28 02:18:36,116][87424] Updated weights for policy 0, policy_version 80096 (0.0012) -[2023-11-28 02:18:37,396][87426] Updated weights for policy 1, policy_version 79970 (0.0012) -[2023-11-28 02:18:37,780][87426] Updated weights for policy 1, policy_version 79980 (0.0012) -[2023-11-28 02:18:38,168][87426] Updated weights for policy 1, policy_version 79990 (0.0009) -[2023-11-28 02:18:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 40976384. Throughput: 0: 2714.3, 1: 2715.0. Samples: 41000088. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:18:38,445][86177] Avg episode reward: [(0, '-509.760'), (1, '-540.240')] -[2023-11-28 02:18:38,550][87426] Updated weights for policy 1, policy_version 80000 (0.0008) -[2023-11-28 02:18:38,550][87424] Updated weights for policy 0, policy_version 80106 (0.0007) -[2023-11-28 02:18:38,940][87424] Updated weights for policy 0, policy_version 80116 (0.0008) -[2023-11-28 02:18:39,316][87424] Updated weights for policy 0, policy_version 80126 (0.0011) -[2023-11-28 02:18:40,893][87426] Updated weights for policy 1, policy_version 80010 (0.0009) -[2023-11-28 02:18:41,272][87426] Updated weights for policy 1, policy_version 80020 (0.0010) -[2023-11-28 02:18:41,655][87426] Updated weights for policy 1, policy_version 80030 (0.0011) -[2023-11-28 02:18:41,848][87424] Updated weights for policy 0, policy_version 80136 (0.0010) -[2023-11-28 02:18:42,229][87424] Updated weights for policy 0, policy_version 80146 (0.0010) -[2023-11-28 02:18:42,616][87424] Updated weights for policy 0, policy_version 80156 (0.0011) -[2023-11-28 02:18:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 41009152. Throughput: 0: 2717.6, 1: 2720.2. Samples: 41024064. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:18:43,445][86177] Avg episode reward: [(0, '-514.840'), (1, '-535.560')] -[2023-11-28 02:18:43,543][87426] Updated weights for policy 1, policy_version 80040 (0.0010) -[2023-11-28 02:18:43,924][87426] Updated weights for policy 1, policy_version 80050 (0.0009) -[2023-11-28 02:18:44,303][87426] Updated weights for policy 1, policy_version 80060 (0.0007) -[2023-11-28 02:18:44,834][87424] Updated weights for policy 0, policy_version 80166 (0.0011) -[2023-11-28 02:18:45,217][87424] Updated weights for policy 0, policy_version 80176 (0.0012) -[2023-11-28 02:18:45,602][87424] Updated weights for policy 0, policy_version 80186 (0.0012) -[2023-11-28 02:18:46,329][87426] Updated weights for policy 1, policy_version 80070 (0.0010) -[2023-11-28 02:18:46,715][87426] Updated weights for policy 1, policy_version 80080 (0.0010) -[2023-11-28 02:18:47,091][87426] Updated weights for policy 1, policy_version 80090 (0.0012) -[2023-11-28 02:18:47,356][87424] Updated weights for policy 0, policy_version 80196 (0.0011) -[2023-11-28 02:18:47,734][87424] Updated weights for policy 0, policy_version 80206 (0.0012) -[2023-11-28 02:18:48,112][87424] Updated weights for policy 0, policy_version 80216 (0.0012) -[2023-11-28 02:18:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41041920. Throughput: 0: 2677.8, 1: 2719.2. Samples: 41048048. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:18:48,445][86177] Avg episode reward: [(0, '-516.980'), (1, '-526.690')] -[2023-11-28 02:18:49,285][87426] Updated weights for policy 1, policy_version 80100 (0.0011) -[2023-11-28 02:18:49,677][87426] Updated weights for policy 1, policy_version 80110 (0.0012) -[2023-11-28 02:18:49,909][87424] Updated weights for policy 0, policy_version 80226 (0.0012) -[2023-11-28 02:18:50,051][87426] Updated weights for policy 1, policy_version 80120 (0.0010) -[2023-11-28 02:18:50,299][87424] Updated weights for policy 0, policy_version 80236 (0.0011) -[2023-11-28 02:18:50,673][87424] Updated weights for policy 0, policy_version 80246 (0.0012) -[2023-11-28 02:18:51,047][87424] Updated weights for policy 0, policy_version 80256 (0.0012) -[2023-11-28 02:18:52,225][87426] Updated weights for policy 1, policy_version 80130 (0.0010) -[2023-11-28 02:18:52,611][87426] Updated weights for policy 1, policy_version 80140 (0.0012) -[2023-11-28 02:18:52,988][87426] Updated weights for policy 1, policy_version 80150 (0.0012) -[2023-11-28 02:18:53,372][87426] Updated weights for policy 1, policy_version 80160 (0.0012) -[2023-11-28 02:18:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41066496. Throughput: 0: 2658.8, 1: 2711.2. Samples: 41080844. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:18:53,445][86177] Avg episode reward: [(0, '-517.730'), (1, '-543.630')] -[2023-11-28 02:18:53,521][87424] Updated weights for policy 0, policy_version 80266 (0.0013) -[2023-11-28 02:18:53,908][87424] Updated weights for policy 0, policy_version 80276 (0.0012) -[2023-11-28 02:18:54,283][87424] Updated weights for policy 0, policy_version 80286 (0.0008) -[2023-11-28 02:18:55,881][87426] Updated weights for policy 1, policy_version 80170 (0.0012) -[2023-11-28 02:18:56,257][87426] Updated weights for policy 1, policy_version 80180 (0.0012) -[2023-11-28 02:18:56,646][87426] Updated weights for policy 1, policy_version 80190 (0.0012) -[2023-11-28 02:18:56,783][87424] Updated weights for policy 0, policy_version 80296 (0.0010) -[2023-11-28 02:18:57,168][87424] Updated weights for policy 0, policy_version 80306 (0.0012) -[2023-11-28 02:18:57,538][87424] Updated weights for policy 0, policy_version 80316 (0.0012) -[2023-11-28 02:18:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 41091072. Throughput: 0: 2677.8, 1: 2714.6. Samples: 41105812. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:18:58,445][86177] Avg episode reward: [(0, '-512.420'), (1, '-562.210')] -[2023-11-28 02:18:58,928][87426] Updated weights for policy 1, policy_version 80200 (0.0011) -[2023-11-28 02:18:59,308][87426] Updated weights for policy 1, policy_version 80210 (0.0012) -[2023-11-28 02:18:59,615][87424] Updated weights for policy 0, policy_version 80326 (0.0012) -[2023-11-28 02:18:59,693][87426] Updated weights for policy 1, policy_version 80220 (0.0012) -[2023-11-28 02:19:00,005][87424] Updated weights for policy 0, policy_version 80336 (0.0012) -[2023-11-28 02:19:00,389][87424] Updated weights for policy 0, policy_version 80346 (0.0012) -[2023-11-28 02:19:01,863][87426] Updated weights for policy 1, policy_version 80230 (0.0009) -[2023-11-28 02:19:02,240][87426] Updated weights for policy 1, policy_version 80240 (0.0009) -[2023-11-28 02:19:02,483][87424] Updated weights for policy 0, policy_version 80356 (0.0012) -[2023-11-28 02:19:02,624][87426] Updated weights for policy 1, policy_version 80250 (0.0007) -[2023-11-28 02:19:02,865][87424] Updated weights for policy 0, policy_version 80366 (0.0011) -[2023-11-28 02:19:03,249][87424] Updated weights for policy 0, policy_version 80376 (0.0011) -[2023-11-28 02:19:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 41115648. Throughput: 0: 2694.1, 1: 2712.5. Samples: 41130744. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:19:03,445][86177] Avg episode reward: [(0, '-512.740'), (1, '-566.280')] -[2023-11-28 02:19:04,743][87426] Updated weights for policy 1, policy_version 80260 (0.0010) -[2023-11-28 02:19:05,125][87426] Updated weights for policy 1, policy_version 80270 (0.0012) -[2023-11-28 02:19:05,481][87424] Updated weights for policy 0, policy_version 80386 (0.0012) -[2023-11-28 02:19:05,505][87426] Updated weights for policy 1, policy_version 80280 (0.0012) -[2023-11-28 02:19:05,872][87424] Updated weights for policy 0, policy_version 80396 (0.0011) -[2023-11-28 02:19:06,252][87424] Updated weights for policy 0, policy_version 80406 (0.0012) -[2023-11-28 02:19:06,631][87424] Updated weights for policy 0, policy_version 80416 (0.0012) -[2023-11-28 02:19:07,375][87426] Updated weights for policy 1, policy_version 80290 (0.0008) -[2023-11-28 02:19:07,740][87426] Updated weights for policy 1, policy_version 80300 (0.0011) -[2023-11-28 02:19:08,118][87426] Updated weights for policy 1, policy_version 80310 (0.0012) -[2023-11-28 02:19:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 41140224. Throughput: 0: 2716.8, 1: 2750.9. Samples: 41164940. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:19:08,445][86177] Avg episode reward: [(0, '-519.790'), (1, '-530.290')] -[2023-11-28 02:19:08,495][87426] Updated weights for policy 1, policy_version 80320 (0.0009) -[2023-11-28 02:19:08,617][87424] Updated weights for policy 0, policy_version 80426 (0.0011) -[2023-11-28 02:19:09,005][87424] Updated weights for policy 0, policy_version 80436 (0.0011) -[2023-11-28 02:19:09,386][87424] Updated weights for policy 0, policy_version 80446 (0.0012) -[2023-11-28 02:19:10,329][87426] Updated weights for policy 1, policy_version 80330 (0.0009) -[2023-11-28 02:19:10,702][87426] Updated weights for policy 1, policy_version 80340 (0.0009) -[2023-11-28 02:19:11,080][87426] Updated weights for policy 1, policy_version 80350 (0.0008) -[2023-11-28 02:19:11,798][87424] Updated weights for policy 0, policy_version 80456 (0.0011) -[2023-11-28 02:19:12,172][87424] Updated weights for policy 0, policy_version 80466 (0.0011) -[2023-11-28 02:19:12,558][87424] Updated weights for policy 0, policy_version 80476 (0.0008) -[2023-11-28 02:19:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 41172992. Throughput: 0: 2733.1, 1: 2756.4. Samples: 41189320. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 02:19:13,445][86177] Avg episode reward: [(0, '-517.490'), (1, '-554.590')] -[2023-11-28 02:19:13,561][87426] Updated weights for policy 1, policy_version 80360 (0.0012) -[2023-11-28 02:19:13,945][87426] Updated weights for policy 1, policy_version 80370 (0.0009) -[2023-11-28 02:19:14,320][87426] Updated weights for policy 1, policy_version 80380 (0.0007) -[2023-11-28 02:19:14,520][87424] Updated weights for policy 0, policy_version 80486 (0.0009) -[2023-11-28 02:19:14,901][87424] Updated weights for policy 0, policy_version 80496 (0.0011) -[2023-11-28 02:19:15,287][87424] Updated weights for policy 0, policy_version 80506 (0.0010) -[2023-11-28 02:19:16,843][87426] Updated weights for policy 1, policy_version 80390 (0.0010) -[2023-11-28 02:19:17,059][87424] Updated weights for policy 0, policy_version 80516 (0.0009) -[2023-11-28 02:19:17,230][87426] Updated weights for policy 1, policy_version 80400 (0.0009) -[2023-11-28 02:19:17,441][87424] Updated weights for policy 0, policy_version 80526 (0.0012) -[2023-11-28 02:19:17,607][87426] Updated weights for policy 1, policy_version 80410 (0.0010) -[2023-11-28 02:19:17,828][87424] Updated weights for policy 0, policy_version 80536 (0.0011) -[2023-11-28 02:19:18,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 41205760. Throughput: 0: 2768.1, 1: 2754.3. Samples: 41214816. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:19:18,445][86177] Avg episode reward: [(0, '-517.710'), (1, '-547.340')] -[2023-11-28 02:19:19,291][87426] Updated weights for policy 1, policy_version 80420 (0.0010) -[2023-11-28 02:19:19,670][87426] Updated weights for policy 1, policy_version 80430 (0.0010) -[2023-11-28 02:19:19,872][87424] Updated weights for policy 0, policy_version 80546 (0.0012) -[2023-11-28 02:19:20,057][87426] Updated weights for policy 1, policy_version 80440 (0.0012) -[2023-11-28 02:19:20,256][87424] Updated weights for policy 0, policy_version 80556 (0.0011) -[2023-11-28 02:19:20,640][87424] Updated weights for policy 0, policy_version 80566 (0.0012) -[2023-11-28 02:19:21,013][87424] Updated weights for policy 0, policy_version 80576 (0.0012) -[2023-11-28 02:19:22,235][87426] Updated weights for policy 1, policy_version 80450 (0.0011) -[2023-11-28 02:19:22,615][87426] Updated weights for policy 1, policy_version 80460 (0.0012) -[2023-11-28 02:19:22,985][87426] Updated weights for policy 1, policy_version 80470 (0.0012) -[2023-11-28 02:19:23,071][87424] Updated weights for policy 0, policy_version 80586 (0.0012) -[2023-11-28 02:19:23,364][87426] Updated weights for policy 1, policy_version 80480 (0.0011) -[2023-11-28 02:19:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 41230336. Throughput: 0: 2755.8, 1: 2732.1. Samples: 41247044. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:19:23,445][86177] Avg episode reward: [(0, '-543.260'), (1, '-545.060')] -[2023-11-28 02:19:23,461][87424] Updated weights for policy 0, policy_version 80596 (0.0012) -[2023-11-28 02:19:23,840][87424] Updated weights for policy 0, policy_version 80606 (0.0008) -[2023-11-28 02:19:25,778][87426] Updated weights for policy 1, policy_version 80490 (0.0011) -[2023-11-28 02:19:26,083][87424] Updated weights for policy 0, policy_version 80616 (0.0010) -[2023-11-28 02:19:26,160][87426] Updated weights for policy 1, policy_version 80500 (0.0011) -[2023-11-28 02:19:26,454][87424] Updated weights for policy 0, policy_version 80626 (0.0011) -[2023-11-28 02:19:26,543][87426] Updated weights for policy 1, policy_version 80510 (0.0010) -[2023-11-28 02:19:26,846][87424] Updated weights for policy 0, policy_version 80636 (0.0007) -[2023-11-28 02:19:28,344][87426] Updated weights for policy 1, policy_version 80520 (0.0011) -[2023-11-28 02:19:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 41254912. Throughput: 0: 2774.4, 1: 2752.3. Samples: 41272764. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:19:28,445][86177] Avg episode reward: [(0, '-534.640'), (1, '-547.170')] -[2023-11-28 02:19:28,726][87426] Updated weights for policy 1, policy_version 80530 (0.0011) -[2023-11-28 02:19:28,894][87424] Updated weights for policy 0, policy_version 80646 (0.0010) -[2023-11-28 02:19:29,108][87426] Updated weights for policy 1, policy_version 80540 (0.0011) -[2023-11-28 02:19:29,277][87424] Updated weights for policy 0, policy_version 80656 (0.0007) -[2023-11-28 02:19:29,666][87424] Updated weights for policy 0, policy_version 80666 (0.0008) -[2023-11-28 02:19:31,188][87426] Updated weights for policy 1, policy_version 80550 (0.0012) -[2023-11-28 02:19:31,486][87424] Updated weights for policy 0, policy_version 80676 (0.0008) -[2023-11-28 02:19:31,571][87426] Updated weights for policy 1, policy_version 80560 (0.0011) -[2023-11-28 02:19:31,872][87424] Updated weights for policy 0, policy_version 80686 (0.0009) -[2023-11-28 02:19:31,944][87426] Updated weights for policy 1, policy_version 80570 (0.0011) -[2023-11-28 02:19:32,249][87424] Updated weights for policy 0, policy_version 80696 (0.0010) -[2023-11-28 02:19:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 41287680. Throughput: 0: 2766.6, 1: 2749.2. Samples: 41296256. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:19:33,445][86177] Avg episode reward: [(0, '-530.090'), (1, '-507.200')] -[2023-11-28 02:19:34,471][87426] Updated weights for policy 1, policy_version 80580 (0.0011) -[2023-11-28 02:19:34,490][87424] Updated weights for policy 0, policy_version 80706 (0.0012) -[2023-11-28 02:19:34,855][87426] Updated weights for policy 1, policy_version 80590 (0.0011) -[2023-11-28 02:19:34,865][87424] Updated weights for policy 0, policy_version 80716 (0.0010) -[2023-11-28 02:19:35,226][87426] Updated weights for policy 1, policy_version 80600 (0.0010) -[2023-11-28 02:19:35,246][87424] Updated weights for policy 0, policy_version 80726 (0.0009) -[2023-11-28 02:19:35,628][87424] Updated weights for policy 0, policy_version 80736 (0.0007) -[2023-11-28 02:19:37,021][87426] Updated weights for policy 1, policy_version 80610 (0.0011) -[2023-11-28 02:19:37,399][87426] Updated weights for policy 1, policy_version 80620 (0.0008) -[2023-11-28 02:19:37,783][87426] Updated weights for policy 1, policy_version 80630 (0.0011) -[2023-11-28 02:19:38,112][87424] Updated weights for policy 0, policy_version 80746 (0.0010) -[2023-11-28 02:19:38,160][87426] Updated weights for policy 1, policy_version 80640 (0.0011) -[2023-11-28 02:19:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 41312256. Throughput: 0: 2777.5, 1: 2739.5. Samples: 41329108. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:19:38,445][86177] Avg episode reward: [(0, '-509.460'), (1, '-503.890')] -[2023-11-28 02:19:38,496][87424] Updated weights for policy 0, policy_version 80756 (0.0008) -[2023-11-28 02:19:38,894][87424] Updated weights for policy 0, policy_version 80766 (0.0007) -[2023-11-28 02:19:40,024][87426] Updated weights for policy 1, policy_version 80650 (0.0012) -[2023-11-28 02:19:40,404][87426] Updated weights for policy 1, policy_version 80660 (0.0010) -[2023-11-28 02:19:40,781][87426] Updated weights for policy 1, policy_version 80670 (0.0008) -[2023-11-28 02:19:41,154][87424] Updated weights for policy 0, policy_version 80776 (0.0008) -[2023-11-28 02:19:41,534][87424] Updated weights for policy 0, policy_version 80786 (0.0011) -[2023-11-28 02:19:41,941][87424] Updated weights for policy 0, policy_version 80796 (0.0010) -[2023-11-28 02:19:43,221][87426] Updated weights for policy 1, policy_version 80680 (0.0008) -[2023-11-28 02:19:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41336832. Throughput: 0: 2763.6, 1: 2727.5. Samples: 41352912. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:19:43,445][86177] Avg episode reward: [(0, '-512.290'), (1, '-506.180')] -[2023-11-28 02:19:43,591][87426] Updated weights for policy 1, policy_version 80690 (0.0011) -[2023-11-28 02:19:43,965][87426] Updated weights for policy 1, policy_version 80700 (0.0007) -[2023-11-28 02:19:44,234][87424] Updated weights for policy 0, policy_version 80806 (0.0008) -[2023-11-28 02:19:44,618][87424] Updated weights for policy 0, policy_version 80816 (0.0007) -[2023-11-28 02:19:45,000][87424] Updated weights for policy 0, policy_version 80826 (0.0007) -[2023-11-28 02:19:46,512][87426] Updated weights for policy 1, policy_version 80710 (0.0007) -[2023-11-28 02:19:46,891][87426] Updated weights for policy 1, policy_version 80720 (0.0007) -[2023-11-28 02:19:47,275][87426] Updated weights for policy 1, policy_version 80730 (0.0008) -[2023-11-28 02:19:47,492][87424] Updated weights for policy 0, policy_version 80836 (0.0007) -[2023-11-28 02:19:47,872][87424] Updated weights for policy 0, policy_version 80846 (0.0008) -[2023-11-28 02:19:48,270][87424] Updated weights for policy 0, policy_version 80856 (0.0007) -[2023-11-28 02:19:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 41361408. Throughput: 0: 2737.6, 1: 2711.7. Samples: 41375964. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:19:48,445][86177] Avg episode reward: [(0, '-512.710'), (1, '-505.150')] -[2023-11-28 02:19:49,853][87426] Updated weights for policy 1, policy_version 80740 (0.0009) -[2023-11-28 02:19:50,226][87426] Updated weights for policy 1, policy_version 80750 (0.0012) -[2023-11-28 02:19:50,297][87424] Updated weights for policy 0, policy_version 80866 (0.0008) -[2023-11-28 02:19:50,608][87426] Updated weights for policy 1, policy_version 80760 (0.0012) -[2023-11-28 02:19:50,683][87424] Updated weights for policy 0, policy_version 80876 (0.0012) -[2023-11-28 02:19:51,068][87424] Updated weights for policy 0, policy_version 80886 (0.0012) -[2023-11-28 02:19:51,443][87424] Updated weights for policy 0, policy_version 80896 (0.0012) -[2023-11-28 02:19:53,168][87426] Updated weights for policy 1, policy_version 80770 (0.0011) -[2023-11-28 02:19:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 41385984. Throughput: 0: 2721.2, 1: 2668.7. Samples: 41407484. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:19:53,445][86177] Avg episode reward: [(0, '-515.670'), (1, '-510.490')] -[2023-11-28 02:19:53,542][87426] Updated weights for policy 1, policy_version 80780 (0.0010) -[2023-11-28 02:19:53,749][87424] Updated weights for policy 0, policy_version 80906 (0.0011) -[2023-11-28 02:19:53,931][87426] Updated weights for policy 1, policy_version 80790 (0.0010) -[2023-11-28 02:19:54,139][87424] Updated weights for policy 0, policy_version 80916 (0.0009) -[2023-11-28 02:19:54,302][87426] Updated weights for policy 1, policy_version 80800 (0.0009) -[2023-11-28 02:19:54,513][87424] Updated weights for policy 0, policy_version 80926 (0.0011) -[2023-11-28 02:19:56,785][87426] Updated weights for policy 1, policy_version 80810 (0.0011) -[2023-11-28 02:19:56,880][87424] Updated weights for policy 0, policy_version 80936 (0.0012) -[2023-11-28 02:19:57,159][87426] Updated weights for policy 1, policy_version 80820 (0.0011) -[2023-11-28 02:19:57,257][87424] Updated weights for policy 0, policy_version 80946 (0.0010) -[2023-11-28 02:19:57,538][87426] Updated weights for policy 1, policy_version 80830 (0.0011) -[2023-11-28 02:19:57,643][87424] Updated weights for policy 0, policy_version 80956 (0.0011) -[2023-11-28 02:19:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41418752. Throughput: 0: 2713.8, 1: 2659.4. Samples: 41431112. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:19:58,445][86177] Avg episode reward: [(0, '-508.880'), (1, '-511.790')] -[2023-11-28 02:19:59,602][87424] Updated weights for policy 0, policy_version 80966 (0.0012) -[2023-11-28 02:19:59,993][87424] Updated weights for policy 0, policy_version 80976 (0.0011) -[2023-11-28 02:20:00,024][87426] Updated weights for policy 1, policy_version 80840 (0.0011) -[2023-11-28 02:20:00,378][87424] Updated weights for policy 0, policy_version 80986 (0.0011) -[2023-11-28 02:20:00,400][87426] Updated weights for policy 1, policy_version 80850 (0.0011) -[2023-11-28 02:20:00,793][87426] Updated weights for policy 1, policy_version 80860 (0.0011) -[2023-11-28 02:20:02,447][87424] Updated weights for policy 0, policy_version 80996 (0.0012) -[2023-11-28 02:20:02,828][87424] Updated weights for policy 0, policy_version 81006 (0.0012) -[2023-11-28 02:20:02,952][87426] Updated weights for policy 1, policy_version 80870 (0.0011) -[2023-11-28 02:20:03,206][87424] Updated weights for policy 0, policy_version 81016 (0.0009) -[2023-11-28 02:20:03,336][87426] Updated weights for policy 1, policy_version 80880 (0.0011) -[2023-11-28 02:20:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 41435136. Throughput: 0: 2708.3, 1: 2656.1. Samples: 41456212. Policy #0 lag: (min: 36.0, avg: 45.1, max: 73.0) -[2023-11-28 02:20:03,445][86177] Avg episode reward: [(0, '-506.850'), (1, '-518.560')] -[2023-11-28 02:20:03,721][87426] Updated weights for policy 1, policy_version 80890 (0.0012) -[2023-11-28 02:20:05,021][87424] Updated weights for policy 0, policy_version 81026 (0.0011) -[2023-11-28 02:20:05,401][87424] Updated weights for policy 0, policy_version 81036 (0.0010) -[2023-11-28 02:20:05,475][87426] Updated weights for policy 1, policy_version 80900 (0.0010) -[2023-11-28 02:20:05,784][87424] Updated weights for policy 0, policy_version 81046 (0.0011) -[2023-11-28 02:20:05,850][87426] Updated weights for policy 1, policy_version 80910 (0.0009) -[2023-11-28 02:20:06,171][87424] Updated weights for policy 0, policy_version 81056 (0.0011) -[2023-11-28 02:20:06,230][87426] Updated weights for policy 1, policy_version 80920 (0.0009) -[2023-11-28 02:20:08,010][87424] Updated weights for policy 0, policy_version 81066 (0.0007) -[2023-11-28 02:20:08,396][87424] Updated weights for policy 0, policy_version 81076 (0.0007) -[2023-11-28 02:20:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 41467904. Throughput: 0: 2723.5, 1: 2659.2. Samples: 41489264. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:08,445][86177] Avg episode reward: [(0, '-507.240'), (1, '-559.150')] -[2023-11-28 02:20:08,537][87426] Updated weights for policy 1, policy_version 80930 (0.0008) -[2023-11-28 02:20:08,777][87424] Updated weights for policy 0, policy_version 81086 (0.0010) -[2023-11-28 02:20:08,912][87426] Updated weights for policy 1, policy_version 80940 (0.0012) -[2023-11-28 02:20:09,290][87426] Updated weights for policy 1, policy_version 80950 (0.0011) -[2023-11-28 02:20:09,663][87426] Updated weights for policy 1, policy_version 80960 (0.0012) -[2023-11-28 02:20:10,641][87424] Updated weights for policy 0, policy_version 81096 (0.0012) -[2023-11-28 02:20:11,013][87424] Updated weights for policy 0, policy_version 81106 (0.0011) -[2023-11-28 02:20:11,413][87424] Updated weights for policy 0, policy_version 81116 (0.0009) -[2023-11-28 02:20:12,216][87426] Updated weights for policy 1, policy_version 80970 (0.0012) -[2023-11-28 02:20:12,602][87426] Updated weights for policy 1, policy_version 80980 (0.0012) -[2023-11-28 02:20:12,977][87426] Updated weights for policy 1, policy_version 80990 (0.0012) -[2023-11-28 02:20:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41500672. Throughput: 0: 2710.5, 1: 2638.8. Samples: 41513480. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:13,445][86177] Avg episode reward: [(0, '-513.860'), (1, '-557.710')] -[2023-11-28 02:20:13,935][87424] Updated weights for policy 0, policy_version 81126 (0.0010) -[2023-11-28 02:20:14,316][87424] Updated weights for policy 0, policy_version 81136 (0.0009) -[2023-11-28 02:20:14,702][87424] Updated weights for policy 0, policy_version 81146 (0.0007) -[2023-11-28 02:20:15,100][87426] Updated weights for policy 1, policy_version 81000 (0.0012) -[2023-11-28 02:20:15,476][87426] Updated weights for policy 1, policy_version 81010 (0.0012) -[2023-11-28 02:20:15,853][87426] Updated weights for policy 1, policy_version 81020 (0.0011) -[2023-11-28 02:20:17,171][87424] Updated weights for policy 0, policy_version 81156 (0.0009) -[2023-11-28 02:20:17,559][87424] Updated weights for policy 0, policy_version 81166 (0.0012) -[2023-11-28 02:20:17,941][87424] Updated weights for policy 0, policy_version 81176 (0.0012) -[2023-11-28 02:20:18,030][87426] Updated weights for policy 1, policy_version 81030 (0.0009) -[2023-11-28 02:20:18,400][87426] Updated weights for policy 1, policy_version 81040 (0.0008) -[2023-11-28 02:20:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 41525248. Throughput: 0: 2716.6, 1: 2654.4. Samples: 41537952. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:18,445][86177] Avg episode reward: [(0, '-511.810'), (1, '-594.800')] -[2023-11-28 02:20:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000081184_20783104.pth... -[2023-11-28 02:20:18,499][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000078624_20127744.pth -[2023-11-28 02:20:18,780][87426] Updated weights for policy 1, policy_version 81050 (0.0009) -[2023-11-28 02:20:19,008][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000081056_20750336.pth... -[2023-11-28 02:20:19,056][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000078528_20103168.pth -[2023-11-28 02:20:19,996][87424] Updated weights for policy 0, policy_version 81186 (0.0010) -[2023-11-28 02:20:20,388][87424] Updated weights for policy 0, policy_version 81196 (0.0009) -[2023-11-28 02:20:20,758][87424] Updated weights for policy 0, policy_version 81206 (0.0010) -[2023-11-28 02:20:20,984][87426] Updated weights for policy 1, policy_version 81060 (0.0011) -[2023-11-28 02:20:21,139][87424] Updated weights for policy 0, policy_version 81216 (0.0011) -[2023-11-28 02:20:21,373][87426] Updated weights for policy 1, policy_version 81070 (0.0012) -[2023-11-28 02:20:21,737][87426] Updated weights for policy 1, policy_version 81080 (0.0012) -[2023-11-28 02:20:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 41549824. Throughput: 0: 2705.2, 1: 2645.7. Samples: 41569900. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:23,445][86177] Avg episode reward: [(0, '-512.320'), (1, '-590.690')] -[2023-11-28 02:20:23,666][87424] Updated weights for policy 0, policy_version 81226 (0.0009) -[2023-11-28 02:20:23,673][87426] Updated weights for policy 1, policy_version 81090 (0.0011) -[2023-11-28 02:20:24,047][87424] Updated weights for policy 0, policy_version 81236 (0.0010) -[2023-11-28 02:20:24,059][87426] Updated weights for policy 1, policy_version 81100 (0.0008) -[2023-11-28 02:20:24,429][87424] Updated weights for policy 0, policy_version 81246 (0.0007) -[2023-11-28 02:20:24,438][87426] Updated weights for policy 1, policy_version 81110 (0.0008) -[2023-11-28 02:20:24,810][87426] Updated weights for policy 1, policy_version 81120 (0.0008) -[2023-11-28 02:20:26,752][87424] Updated weights for policy 0, policy_version 81256 (0.0008) -[2023-11-28 02:20:27,015][87426] Updated weights for policy 1, policy_version 81130 (0.0011) -[2023-11-28 02:20:27,126][87424] Updated weights for policy 0, policy_version 81266 (0.0007) -[2023-11-28 02:20:27,404][87426] Updated weights for policy 1, policy_version 81140 (0.0007) -[2023-11-28 02:20:27,505][87424] Updated weights for policy 0, policy_version 81276 (0.0008) -[2023-11-28 02:20:27,792][87426] Updated weights for policy 1, policy_version 81150 (0.0007) -[2023-11-28 02:20:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 41582592. Throughput: 0: 2704.8, 1: 2662.8. Samples: 41594456. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:28,445][86177] Avg episode reward: [(0, '-506.890'), (1, '-546.000')] -[2023-11-28 02:20:29,455][87426] Updated weights for policy 1, policy_version 81160 (0.0011) -[2023-11-28 02:20:29,465][87424] Updated weights for policy 0, policy_version 81286 (0.0010) -[2023-11-28 02:20:29,833][87426] Updated weights for policy 1, policy_version 81170 (0.0012) -[2023-11-28 02:20:29,846][87424] Updated weights for policy 0, policy_version 81296 (0.0012) -[2023-11-28 02:20:30,211][87426] Updated weights for policy 1, policy_version 81180 (0.0011) -[2023-11-28 02:20:30,221][87424] Updated weights for policy 0, policy_version 81306 (0.0011) -[2023-11-28 02:20:32,487][87424] Updated weights for policy 0, policy_version 81316 (0.0009) -[2023-11-28 02:20:32,657][87426] Updated weights for policy 1, policy_version 81190 (0.0010) -[2023-11-28 02:20:32,873][87424] Updated weights for policy 0, policy_version 81326 (0.0008) -[2023-11-28 02:20:33,036][87426] Updated weights for policy 1, policy_version 81200 (0.0011) -[2023-11-28 02:20:33,252][87424] Updated weights for policy 0, policy_version 81336 (0.0011) -[2023-11-28 02:20:33,407][87426] Updated weights for policy 1, policy_version 81210 (0.0010) -[2023-11-28 02:20:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 41598976. Throughput: 0: 2720.5, 1: 2665.5. Samples: 41618336. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:33,445][86177] Avg episode reward: [(0, '-504.930'), (1, '-551.560')] -[2023-11-28 02:20:35,133][87424] Updated weights for policy 0, policy_version 81346 (0.0009) -[2023-11-28 02:20:35,523][87424] Updated weights for policy 0, policy_version 81356 (0.0008) -[2023-11-28 02:20:35,795][87426] Updated weights for policy 1, policy_version 81220 (0.0011) -[2023-11-28 02:20:35,904][87424] Updated weights for policy 0, policy_version 81366 (0.0008) -[2023-11-28 02:20:36,173][87426] Updated weights for policy 1, policy_version 81230 (0.0011) -[2023-11-28 02:20:36,282][87424] Updated weights for policy 0, policy_version 81376 (0.0008) -[2023-11-28 02:20:36,548][87426] Updated weights for policy 1, policy_version 81240 (0.0012) -[2023-11-28 02:20:38,371][87424] Updated weights for policy 0, policy_version 81386 (0.0009) -[2023-11-28 02:20:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 41631744. Throughput: 0: 2752.4, 1: 2693.6. Samples: 41652552. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:38,445][86177] Avg episode reward: [(0, '-507.500'), (1, '-515.180')] -[2023-11-28 02:20:38,696][87426] Updated weights for policy 1, policy_version 81250 (0.0023) -[2023-11-28 02:20:38,770][87424] Updated weights for policy 0, policy_version 81396 (0.0010) -[2023-11-28 02:20:39,077][87426] Updated weights for policy 1, policy_version 81260 (0.0011) -[2023-11-28 02:20:39,151][87424] Updated weights for policy 0, policy_version 81406 (0.0011) -[2023-11-28 02:20:39,454][87426] Updated weights for policy 1, policy_version 81270 (0.0011) -[2023-11-28 02:20:39,827][87426] Updated weights for policy 1, policy_version 81280 (0.0011) -[2023-11-28 02:20:41,160][87424] Updated weights for policy 0, policy_version 81416 (0.0012) -[2023-11-28 02:20:41,540][87424] Updated weights for policy 0, policy_version 81426 (0.0011) -[2023-11-28 02:20:41,830][87426] Updated weights for policy 1, policy_version 81290 (0.0008) -[2023-11-28 02:20:41,923][87424] Updated weights for policy 0, policy_version 81436 (0.0010) -[2023-11-28 02:20:42,197][87426] Updated weights for policy 1, policy_version 81300 (0.0010) -[2023-11-28 02:20:42,583][87426] Updated weights for policy 1, policy_version 81310 (0.0011) -[2023-11-28 02:20:43,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41664512. Throughput: 0: 2759.6, 1: 2707.0. Samples: 41677112. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:43,445][86177] Avg episode reward: [(0, '-521.260'), (1, '-524.550')] -[2023-11-28 02:20:44,172][87424] Updated weights for policy 0, policy_version 81446 (0.0011) -[2023-11-28 02:20:44,557][87424] Updated weights for policy 0, policy_version 81456 (0.0011) -[2023-11-28 02:20:44,817][87426] Updated weights for policy 1, policy_version 81320 (0.0008) -[2023-11-28 02:20:44,934][87424] Updated weights for policy 0, policy_version 81466 (0.0011) -[2023-11-28 02:20:45,202][87426] Updated weights for policy 1, policy_version 81330 (0.0011) -[2023-11-28 02:20:45,589][87426] Updated weights for policy 1, policy_version 81340 (0.0008) -[2023-11-28 02:20:46,996][87424] Updated weights for policy 0, policy_version 81476 (0.0009) -[2023-11-28 02:20:47,393][87424] Updated weights for policy 0, policy_version 81486 (0.0012) -[2023-11-28 02:20:47,676][87426] Updated weights for policy 1, policy_version 81350 (0.0008) -[2023-11-28 02:20:47,784][87424] Updated weights for policy 0, policy_version 81496 (0.0011) -[2023-11-28 02:20:48,061][87426] Updated weights for policy 1, policy_version 81360 (0.0007) -[2023-11-28 02:20:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41689088. Throughput: 0: 2741.0, 1: 2715.5. Samples: 41701752. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:48,445][86177] Avg episode reward: [(0, '-522.180'), (1, '-524.460')] -[2023-11-28 02:20:48,448][87426] Updated weights for policy 1, policy_version 81370 (0.0007) -[2023-11-28 02:20:49,622][87424] Updated weights for policy 0, policy_version 81506 (0.0011) -[2023-11-28 02:20:50,007][87424] Updated weights for policy 0, policy_version 81516 (0.0012) -[2023-11-28 02:20:50,390][87424] Updated weights for policy 0, policy_version 81526 (0.0011) -[2023-11-28 02:20:50,582][87426] Updated weights for policy 1, policy_version 81380 (0.0009) -[2023-11-28 02:20:50,772][87424] Updated weights for policy 0, policy_version 81536 (0.0010) -[2023-11-28 02:20:50,949][87426] Updated weights for policy 1, policy_version 81390 (0.0012) -[2023-11-28 02:20:51,327][87426] Updated weights for policy 1, policy_version 81400 (0.0011) -[2023-11-28 02:20:53,168][87424] Updated weights for policy 0, policy_version 81546 (0.0009) -[2023-11-28 02:20:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 41713664. Throughput: 0: 2732.5, 1: 2698.6. Samples: 41733660. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 02:20:53,445][86177] Avg episode reward: [(0, '-517.610'), (1, '-523.670')] -[2023-11-28 02:20:53,559][87424] Updated weights for policy 0, policy_version 81556 (0.0012) -[2023-11-28 02:20:53,806][87426] Updated weights for policy 1, policy_version 81410 (0.0011) -[2023-11-28 02:20:53,948][87424] Updated weights for policy 0, policy_version 81566 (0.0010) -[2023-11-28 02:20:54,191][87426] Updated weights for policy 1, policy_version 81420 (0.0007) -[2023-11-28 02:20:54,564][87426] Updated weights for policy 1, policy_version 81430 (0.0009) -[2023-11-28 02:20:54,949][87426] Updated weights for policy 1, policy_version 81440 (0.0007) -[2023-11-28 02:20:56,344][87424] Updated weights for policy 0, policy_version 81576 (0.0011) -[2023-11-28 02:20:56,741][87424] Updated weights for policy 0, policy_version 81586 (0.0010) -[2023-11-28 02:20:57,126][87424] Updated weights for policy 0, policy_version 81596 (0.0011) -[2023-11-28 02:20:57,393][87426] Updated weights for policy 1, policy_version 81450 (0.0007) -[2023-11-28 02:20:57,774][87426] Updated weights for policy 1, policy_version 81460 (0.0009) -[2023-11-28 02:20:58,149][87426] Updated weights for policy 1, policy_version 81470 (0.0012) -[2023-11-28 02:20:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 41746432. Throughput: 0: 2714.8, 1: 2679.6. Samples: 41756232. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:20:58,445][86177] Avg episode reward: [(0, '-510.940'), (1, '-535.650')] -[2023-11-28 02:20:59,129][87424] Updated weights for policy 0, policy_version 81606 (0.0009) -[2023-11-28 02:20:59,515][87424] Updated weights for policy 0, policy_version 81616 (0.0012) -[2023-11-28 02:20:59,898][87424] Updated weights for policy 0, policy_version 81626 (0.0012) -[2023-11-28 02:21:00,513][87426] Updated weights for policy 1, policy_version 81480 (0.0015) -[2023-11-28 02:21:00,898][87426] Updated weights for policy 1, policy_version 81490 (0.0011) -[2023-11-28 02:21:01,273][87426] Updated weights for policy 1, policy_version 81500 (0.0012) -[2023-11-28 02:21:01,760][87424] Updated weights for policy 0, policy_version 81636 (0.0012) -[2023-11-28 02:21:02,145][87424] Updated weights for policy 0, policy_version 81646 (0.0011) -[2023-11-28 02:21:02,540][87424] Updated weights for policy 0, policy_version 81656 (0.0012) -[2023-11-28 02:21:03,288][87426] Updated weights for policy 1, policy_version 81510 (0.0012) -[2023-11-28 02:21:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 41771008. Throughput: 0: 2754.9, 1: 2658.0. Samples: 41781536. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:21:03,445][86177] Avg episode reward: [(0, '-508.470'), (1, '-523.830')] -[2023-11-28 02:21:03,674][87426] Updated weights for policy 1, policy_version 81520 (0.0012) -[2023-11-28 02:21:04,049][87426] Updated weights for policy 1, policy_version 81530 (0.0012) -[2023-11-28 02:21:05,061][87424] Updated weights for policy 0, policy_version 81666 (0.0012) -[2023-11-28 02:21:05,443][87424] Updated weights for policy 0, policy_version 81676 (0.0012) -[2023-11-28 02:21:05,813][87424] Updated weights for policy 0, policy_version 81686 (0.0011) -[2023-11-28 02:21:05,933][87426] Updated weights for policy 1, policy_version 81540 (0.0012) -[2023-11-28 02:21:06,202][87424] Updated weights for policy 0, policy_version 81696 (0.0008) -[2023-11-28 02:21:06,300][87426] Updated weights for policy 1, policy_version 81550 (0.0011) -[2023-11-28 02:21:06,684][87426] Updated weights for policy 1, policy_version 81560 (0.0012) -[2023-11-28 02:21:08,257][87424] Updated weights for policy 0, policy_version 81706 (0.0012) -[2023-11-28 02:21:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 41795584. Throughput: 0: 2757.2, 1: 2697.2. Samples: 41815344. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:21:08,445][86177] Avg episode reward: [(0, '-512.750'), (1, '-525.480')] -[2023-11-28 02:21:08,563][87426] Updated weights for policy 1, policy_version 81570 (0.0011) -[2023-11-28 02:21:08,644][87424] Updated weights for policy 0, policy_version 81716 (0.0012) -[2023-11-28 02:21:08,937][87426] Updated weights for policy 1, policy_version 81580 (0.0010) -[2023-11-28 02:21:09,014][87424] Updated weights for policy 0, policy_version 81726 (0.0012) -[2023-11-28 02:21:09,319][87426] Updated weights for policy 1, policy_version 81590 (0.0012) -[2023-11-28 02:21:09,700][87426] Updated weights for policy 1, policy_version 81600 (0.0012) -[2023-11-28 02:21:11,135][87424] Updated weights for policy 0, policy_version 81736 (0.0008) -[2023-11-28 02:21:11,510][87424] Updated weights for policy 0, policy_version 81746 (0.0007) -[2023-11-28 02:21:11,714][87426] Updated weights for policy 1, policy_version 81610 (0.0010) -[2023-11-28 02:21:11,896][87424] Updated weights for policy 0, policy_version 81756 (0.0010) -[2023-11-28 02:21:12,095][87426] Updated weights for policy 1, policy_version 81620 (0.0008) -[2023-11-28 02:21:12,480][87426] Updated weights for policy 1, policy_version 81630 (0.0008) -[2023-11-28 02:21:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 41828352. Throughput: 0: 2761.0, 1: 2695.0. Samples: 41839976. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:21:13,445][86177] Avg episode reward: [(0, '-516.690'), (1, '-517.860')] -[2023-11-28 02:21:14,260][87424] Updated weights for policy 0, policy_version 81766 (0.0009) -[2023-11-28 02:21:14,646][87424] Updated weights for policy 0, policy_version 81776 (0.0008) -[2023-11-28 02:21:14,947][87426] Updated weights for policy 1, policy_version 81640 (0.0008) -[2023-11-28 02:21:15,028][87424] Updated weights for policy 0, policy_version 81786 (0.0012) -[2023-11-28 02:21:15,324][87426] Updated weights for policy 1, policy_version 81650 (0.0008) -[2023-11-28 02:21:15,704][87426] Updated weights for policy 1, policy_version 81660 (0.0009) -[2023-11-28 02:21:17,167][87424] Updated weights for policy 0, policy_version 81796 (0.0011) -[2023-11-28 02:21:17,558][87424] Updated weights for policy 0, policy_version 81806 (0.0012) -[2023-11-28 02:21:17,796][87426] Updated weights for policy 1, policy_version 81670 (0.0010) -[2023-11-28 02:21:17,929][87424] Updated weights for policy 0, policy_version 81816 (0.0012) -[2023-11-28 02:21:18,178][87426] Updated weights for policy 1, policy_version 81680 (0.0012) -[2023-11-28 02:21:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41852928. Throughput: 0: 2737.1, 1: 2714.5. Samples: 41863656. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:21:18,445][86177] Avg episode reward: [(0, '-526.840'), (1, '-516.630')] -[2023-11-28 02:21:18,561][87426] Updated weights for policy 1, policy_version 81690 (0.0012) -[2023-11-28 02:21:20,337][87424] Updated weights for policy 0, policy_version 81826 (0.0011) -[2023-11-28 02:21:20,725][87424] Updated weights for policy 0, policy_version 81836 (0.0011) -[2023-11-28 02:21:20,734][87426] Updated weights for policy 1, policy_version 81700 (0.0009) -[2023-11-28 02:21:21,105][87424] Updated weights for policy 0, policy_version 81846 (0.0011) -[2023-11-28 02:21:21,110][87426] Updated weights for policy 1, policy_version 81710 (0.0009) -[2023-11-28 02:21:21,482][87426] Updated weights for policy 1, policy_version 81720 (0.0010) -[2023-11-28 02:21:21,489][87424] Updated weights for policy 0, policy_version 81856 (0.0012) -[2023-11-28 02:21:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41877504. Throughput: 0: 2714.7, 1: 2698.8. Samples: 41896164. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:21:23,445][86177] Avg episode reward: [(0, '-539.650'), (1, '-523.410')] -[2023-11-28 02:21:23,954][87424] Updated weights for policy 0, policy_version 81866 (0.0009) -[2023-11-28 02:21:23,985][87426] Updated weights for policy 1, policy_version 81730 (0.0012) -[2023-11-28 02:21:24,328][87424] Updated weights for policy 0, policy_version 81876 (0.0008) -[2023-11-28 02:21:24,367][87426] Updated weights for policy 1, policy_version 81740 (0.0011) -[2023-11-28 02:21:24,714][87424] Updated weights for policy 0, policy_version 81886 (0.0008) -[2023-11-28 02:21:24,744][87426] Updated weights for policy 1, policy_version 81750 (0.0011) -[2023-11-28 02:21:25,122][87426] Updated weights for policy 1, policy_version 81760 (0.0011) -[2023-11-28 02:21:26,967][87426] Updated weights for policy 1, policy_version 81770 (0.0011) -[2023-11-28 02:21:27,035][87424] Updated weights for policy 0, policy_version 81896 (0.0009) -[2023-11-28 02:21:27,345][87426] Updated weights for policy 1, policy_version 81780 (0.0012) -[2023-11-28 02:21:27,412][87424] Updated weights for policy 0, policy_version 81906 (0.0007) -[2023-11-28 02:21:27,727][87426] Updated weights for policy 1, policy_version 81790 (0.0011) -[2023-11-28 02:21:27,795][87424] Updated weights for policy 0, policy_version 81916 (0.0007) -[2023-11-28 02:21:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41910272. Throughput: 0: 2706.5, 1: 2711.0. Samples: 41920900. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:21:28,446][86177] Avg episode reward: [(0, '-534.970'), (1, '-538.930')] -[2023-11-28 02:21:29,570][87424] Updated weights for policy 0, policy_version 81926 (0.0009) -[2023-11-28 02:21:29,950][87424] Updated weights for policy 0, policy_version 81936 (0.0012) -[2023-11-28 02:21:29,990][87426] Updated weights for policy 1, policy_version 81800 (0.0011) -[2023-11-28 02:21:30,325][87424] Updated weights for policy 0, policy_version 81946 (0.0009) -[2023-11-28 02:21:30,367][87426] Updated weights for policy 1, policy_version 81810 (0.0011) -[2023-11-28 02:21:30,739][87426] Updated weights for policy 1, policy_version 81820 (0.0012) -[2023-11-28 02:21:32,348][87424] Updated weights for policy 0, policy_version 81956 (0.0010) -[2023-11-28 02:21:32,727][87424] Updated weights for policy 0, policy_version 81966 (0.0010) -[2023-11-28 02:21:32,767][87426] Updated weights for policy 1, policy_version 81830 (0.0011) -[2023-11-28 02:21:33,107][87424] Updated weights for policy 0, policy_version 81976 (0.0010) -[2023-11-28 02:21:33,146][87426] Updated weights for policy 1, policy_version 81840 (0.0011) -[2023-11-28 02:21:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 41934848. Throughput: 0: 2707.4, 1: 2722.1. Samples: 41946080. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:21:33,445][86177] Avg episode reward: [(0, '-532.550'), (1, '-569.110')] -[2023-11-28 02:21:33,520][87426] Updated weights for policy 1, policy_version 81850 (0.0012) -[2023-11-28 02:21:34,901][87424] Updated weights for policy 0, policy_version 81986 (0.0011) -[2023-11-28 02:21:35,285][87424] Updated weights for policy 0, policy_version 81996 (0.0011) -[2023-11-28 02:21:35,649][87424] Updated weights for policy 0, policy_version 82006 (0.0011) -[2023-11-28 02:21:36,011][87426] Updated weights for policy 1, policy_version 81860 (0.0008) -[2023-11-28 02:21:36,027][87424] Updated weights for policy 0, policy_version 82016 (0.0011) -[2023-11-28 02:21:36,395][87426] Updated weights for policy 1, policy_version 81870 (0.0008) -[2023-11-28 02:21:36,775][87426] Updated weights for policy 1, policy_version 81880 (0.0008) -[2023-11-28 02:21:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41959424. Throughput: 0: 2720.0, 1: 2745.1. Samples: 41979592. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:21:38,445][86177] Avg episode reward: [(0, '-522.490'), (1, '-570.930')] -[2023-11-28 02:21:38,475][87426] Updated weights for policy 1, policy_version 81890 (0.0010) -[2023-11-28 02:21:38,614][87424] Updated weights for policy 0, policy_version 82026 (0.0012) -[2023-11-28 02:21:38,855][87426] Updated weights for policy 1, policy_version 81900 (0.0012) -[2023-11-28 02:21:38,999][87424] Updated weights for policy 0, policy_version 82036 (0.0011) -[2023-11-28 02:21:39,229][87426] Updated weights for policy 1, policy_version 81910 (0.0010) -[2023-11-28 02:21:39,389][87424] Updated weights for policy 0, policy_version 82046 (0.0011) -[2023-11-28 02:21:39,609][87426] Updated weights for policy 1, policy_version 81920 (0.0009) -[2023-11-28 02:21:41,745][87424] Updated weights for policy 0, policy_version 82056 (0.0010) -[2023-11-28 02:21:41,767][87426] Updated weights for policy 1, policy_version 81930 (0.0008) -[2023-11-28 02:21:42,126][87424] Updated weights for policy 0, policy_version 82066 (0.0011) -[2023-11-28 02:21:42,151][87426] Updated weights for policy 1, policy_version 81940 (0.0009) -[2023-11-28 02:21:42,509][87424] Updated weights for policy 0, policy_version 82076 (0.0010) -[2023-11-28 02:21:42,529][87426] Updated weights for policy 1, policy_version 81950 (0.0011) -[2023-11-28 02:21:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 41992192. Throughput: 0: 2722.1, 1: 2794.0. Samples: 42004460. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 02:21:43,445][86177] Avg episode reward: [(0, '-508.540'), (1, '-570.660')] -[2023-11-28 02:21:44,250][87424] Updated weights for policy 0, policy_version 82086 (0.0009) -[2023-11-28 02:21:44,405][87426] Updated weights for policy 1, policy_version 81960 (0.0010) -[2023-11-28 02:21:44,635][87424] Updated weights for policy 0, policy_version 82096 (0.0007) -[2023-11-28 02:21:44,795][87426] Updated weights for policy 1, policy_version 81970 (0.0007) -[2023-11-28 02:21:45,016][87424] Updated weights for policy 0, policy_version 82106 (0.0010) -[2023-11-28 02:21:45,169][87426] Updated weights for policy 1, policy_version 81980 (0.0007) -[2023-11-28 02:21:46,883][87426] Updated weights for policy 1, policy_version 81990 (0.0010) -[2023-11-28 02:21:47,211][87424] Updated weights for policy 0, policy_version 82116 (0.0010) -[2023-11-28 02:21:47,268][87426] Updated weights for policy 1, policy_version 82000 (0.0012) -[2023-11-28 02:21:47,599][87424] Updated weights for policy 0, policy_version 82126 (0.0010) -[2023-11-28 02:21:47,640][87426] Updated weights for policy 1, policy_version 82010 (0.0008) -[2023-11-28 02:21:47,989][87424] Updated weights for policy 0, policy_version 82136 (0.0011) -[2023-11-28 02:21:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 42024960. Throughput: 0: 2691.5, 1: 2832.3. Samples: 42030108. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:21:48,445][86177] Avg episode reward: [(0, '-511.700'), (1, '-564.740')] -[2023-11-28 02:21:49,998][87426] Updated weights for policy 1, policy_version 82020 (0.0010) -[2023-11-28 02:21:50,238][87424] Updated weights for policy 0, policy_version 82146 (0.0011) -[2023-11-28 02:21:50,379][87426] Updated weights for policy 1, policy_version 82030 (0.0011) -[2023-11-28 02:21:50,631][87424] Updated weights for policy 0, policy_version 82156 (0.0009) -[2023-11-28 02:21:50,761][87426] Updated weights for policy 1, policy_version 82040 (0.0008) -[2023-11-28 02:21:51,005][87424] Updated weights for policy 0, policy_version 82166 (0.0010) -[2023-11-28 02:21:51,382][87424] Updated weights for policy 0, policy_version 82176 (0.0008) -[2023-11-28 02:21:52,903][87426] Updated weights for policy 1, policy_version 82050 (0.0008) -[2023-11-28 02:21:53,270][87426] Updated weights for policy 1, policy_version 82060 (0.0012) -[2023-11-28 02:21:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42041344. Throughput: 0: 2679.2, 1: 2808.4. Samples: 42062288. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:21:53,445][86177] Avg episode reward: [(0, '-509.130'), (1, '-522.450')] -[2023-11-28 02:21:53,649][87426] Updated weights for policy 1, policy_version 82070 (0.0011) -[2023-11-28 02:21:53,807][87424] Updated weights for policy 0, policy_version 82186 (0.0011) -[2023-11-28 02:21:54,027][87426] Updated weights for policy 1, policy_version 82080 (0.0011) -[2023-11-28 02:21:54,188][87424] Updated weights for policy 0, policy_version 82196 (0.0008) -[2023-11-28 02:21:54,572][87424] Updated weights for policy 0, policy_version 82206 (0.0007) -[2023-11-28 02:21:55,837][87426] Updated weights for policy 1, policy_version 82090 (0.0007) -[2023-11-28 02:21:56,223][87426] Updated weights for policy 1, policy_version 82100 (0.0007) -[2023-11-28 02:21:56,606][87426] Updated weights for policy 1, policy_version 82110 (0.0007) -[2023-11-28 02:21:56,811][87424] Updated weights for policy 0, policy_version 82216 (0.0008) -[2023-11-28 02:21:57,193][87424] Updated weights for policy 0, policy_version 82226 (0.0007) -[2023-11-28 02:21:57,573][87424] Updated weights for policy 0, policy_version 82236 (0.0010) -[2023-11-28 02:21:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42074112. Throughput: 0: 2680.4, 1: 2808.3. Samples: 42086968. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:21:58,445][86177] Avg episode reward: [(0, '-509.400'), (1, '-534.850')] -[2023-11-28 02:21:58,944][87426] Updated weights for policy 1, policy_version 82120 (0.0008) -[2023-11-28 02:21:59,285][87424] Updated weights for policy 0, policy_version 82246 (0.0012) -[2023-11-28 02:21:59,320][87426] Updated weights for policy 1, policy_version 82130 (0.0008) -[2023-11-28 02:21:59,669][87424] Updated weights for policy 0, policy_version 82256 (0.0011) -[2023-11-28 02:21:59,702][87426] Updated weights for policy 1, policy_version 82140 (0.0007) -[2023-11-28 02:22:00,047][87424] Updated weights for policy 0, policy_version 82266 (0.0012) -[2023-11-28 02:22:02,043][87424] Updated weights for policy 0, policy_version 82276 (0.0012) -[2023-11-28 02:22:02,185][87426] Updated weights for policy 1, policy_version 82150 (0.0009) -[2023-11-28 02:22:02,413][87424] Updated weights for policy 0, policy_version 82286 (0.0011) -[2023-11-28 02:22:02,566][87426] Updated weights for policy 1, policy_version 82160 (0.0010) -[2023-11-28 02:22:02,801][87424] Updated weights for policy 0, policy_version 82296 (0.0010) -[2023-11-28 02:22:02,945][87426] Updated weights for policy 1, policy_version 82170 (0.0010) -[2023-11-28 02:22:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 42106880. Throughput: 0: 2724.8, 1: 2788.6. Samples: 42111760. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:22:03,445][86177] Avg episode reward: [(0, '-515.070'), (1, '-525.310')] -[2023-11-28 02:22:04,785][87426] Updated weights for policy 1, policy_version 82180 (0.0011) -[2023-11-28 02:22:05,000][87424] Updated weights for policy 0, policy_version 82306 (0.0011) -[2023-11-28 02:22:05,172][87426] Updated weights for policy 1, policy_version 82190 (0.0012) -[2023-11-28 02:22:05,383][87424] Updated weights for policy 0, policy_version 82316 (0.0011) -[2023-11-28 02:22:05,556][87426] Updated weights for policy 1, policy_version 82200 (0.0011) -[2023-11-28 02:22:05,760][87424] Updated weights for policy 0, policy_version 82326 (0.0010) -[2023-11-28 02:22:06,145][87424] Updated weights for policy 0, policy_version 82336 (0.0007) -[2023-11-28 02:22:07,759][87426] Updated weights for policy 1, policy_version 82210 (0.0011) -[2023-11-28 02:22:08,134][87426] Updated weights for policy 1, policy_version 82220 (0.0011) -[2023-11-28 02:22:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 42123264. Throughput: 0: 2700.6, 1: 2814.2. Samples: 42144332. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:22:08,445][86177] Avg episode reward: [(0, '-505.750'), (1, '-513.430')] -[2023-11-28 02:22:08,509][87426] Updated weights for policy 1, policy_version 82230 (0.0008) -[2023-11-28 02:22:08,590][87424] Updated weights for policy 0, policy_version 82346 (0.0012) -[2023-11-28 02:22:08,888][87426] Updated weights for policy 1, policy_version 82240 (0.0011) -[2023-11-28 02:22:08,975][87424] Updated weights for policy 0, policy_version 82356 (0.0012) -[2023-11-28 02:22:09,350][87424] Updated weights for policy 0, policy_version 82366 (0.0011) -[2023-11-28 02:22:11,414][87426] Updated weights for policy 1, policy_version 82250 (0.0011) -[2023-11-28 02:22:11,794][87426] Updated weights for policy 1, policy_version 82260 (0.0012) -[2023-11-28 02:22:11,974][87424] Updated weights for policy 0, policy_version 82376 (0.0011) -[2023-11-28 02:22:12,176][87426] Updated weights for policy 1, policy_version 82270 (0.0011) -[2023-11-28 02:22:12,354][87424] Updated weights for policy 0, policy_version 82386 (0.0010) -[2023-11-28 02:22:12,752][87424] Updated weights for policy 0, policy_version 82396 (0.0008) -[2023-11-28 02:22:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42156032. Throughput: 0: 2696.5, 1: 2780.4. Samples: 42167356. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:22:13,445][86177] Avg episode reward: [(0, '-507.080'), (1, '-522.250')] -[2023-11-28 02:22:14,300][87426] Updated weights for policy 1, policy_version 82280 (0.0012) -[2023-11-28 02:22:14,680][87426] Updated weights for policy 1, policy_version 82290 (0.0012) -[2023-11-28 02:22:15,059][87426] Updated weights for policy 1, policy_version 82300 (0.0012) -[2023-11-28 02:22:15,299][87424] Updated weights for policy 0, policy_version 82406 (0.0009) -[2023-11-28 02:22:15,683][87424] Updated weights for policy 0, policy_version 82416 (0.0011) -[2023-11-28 02:22:16,076][87424] Updated weights for policy 0, policy_version 82426 (0.0011) -[2023-11-28 02:22:17,028][87426] Updated weights for policy 1, policy_version 82310 (0.0009) -[2023-11-28 02:22:17,410][87426] Updated weights for policy 1, policy_version 82320 (0.0007) -[2023-11-28 02:22:17,793][87426] Updated weights for policy 1, policy_version 82330 (0.0007) -[2023-11-28 02:22:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42180608. Throughput: 0: 2678.5, 1: 2769.1. Samples: 42191220. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:22:18,445][86177] Avg episode reward: [(0, '-517.010'), (1, '-545.300')] -[2023-11-28 02:22:18,452][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000082336_21078016.pth... -[2023-11-28 02:22:18,485][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000079776_20422656.pth -[2023-11-28 02:22:18,597][87424] Updated weights for policy 0, policy_version 82436 (0.0008) -[2023-11-28 02:22:18,981][87424] Updated weights for policy 0, policy_version 82446 (0.0009) -[2023-11-28 02:22:19,368][87424] Updated weights for policy 0, policy_version 82456 (0.0008) -[2023-11-28 02:22:19,674][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000082464_21110784.pth... -[2023-11-28 02:22:19,721][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000079904_20455424.pth -[2023-11-28 02:22:20,219][87426] Updated weights for policy 1, policy_version 82340 (0.0008) -[2023-11-28 02:22:20,591][87426] Updated weights for policy 1, policy_version 82350 (0.0011) -[2023-11-28 02:22:20,976][87426] Updated weights for policy 1, policy_version 82360 (0.0008) -[2023-11-28 02:22:21,307][87424] Updated weights for policy 0, policy_version 82466 (0.0008) -[2023-11-28 02:22:21,692][87424] Updated weights for policy 0, policy_version 82476 (0.0012) -[2023-11-28 02:22:22,070][87424] Updated weights for policy 0, policy_version 82486 (0.0011) -[2023-11-28 02:22:22,456][87424] Updated weights for policy 0, policy_version 82496 (0.0010) -[2023-11-28 02:22:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42205184. Throughput: 0: 2662.0, 1: 2733.1. Samples: 42222376. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:22:23,446][86177] Avg episode reward: [(0, '-511.850'), (1, '-546.990')] -[2023-11-28 02:22:23,622][87426] Updated weights for policy 1, policy_version 82370 (0.0009) -[2023-11-28 02:22:24,002][87426] Updated weights for policy 1, policy_version 82380 (0.0011) -[2023-11-28 02:22:24,386][87426] Updated weights for policy 1, policy_version 82390 (0.0012) -[2023-11-28 02:22:24,430][87424] Updated weights for policy 0, policy_version 82506 (0.0011) -[2023-11-28 02:22:24,762][87426] Updated weights for policy 1, policy_version 82400 (0.0008) -[2023-11-28 02:22:24,816][87424] Updated weights for policy 0, policy_version 82516 (0.0011) -[2023-11-28 02:22:25,193][87424] Updated weights for policy 0, policy_version 82526 (0.0012) -[2023-11-28 02:22:26,521][87426] Updated weights for policy 1, policy_version 82410 (0.0007) -[2023-11-28 02:22:26,912][87426] Updated weights for policy 1, policy_version 82420 (0.0007) -[2023-11-28 02:22:27,224][87424] Updated weights for policy 0, policy_version 82536 (0.0012) -[2023-11-28 02:22:27,301][87426] Updated weights for policy 1, policy_version 82430 (0.0007) -[2023-11-28 02:22:27,609][87424] Updated weights for policy 0, policy_version 82546 (0.0008) -[2023-11-28 02:22:27,995][87424] Updated weights for policy 0, policy_version 82556 (0.0007) -[2023-11-28 02:22:28,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42237952. Throughput: 0: 2678.6, 1: 2730.0. Samples: 42247848. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:22:28,446][86177] Avg episode reward: [(0, '-517.590'), (1, '-549.700')] -[2023-11-28 02:22:29,529][87426] Updated weights for policy 1, policy_version 82440 (0.0011) -[2023-11-28 02:22:29,905][87426] Updated weights for policy 1, policy_version 82450 (0.0011) -[2023-11-28 02:22:30,255][87424] Updated weights for policy 0, policy_version 82566 (0.0008) -[2023-11-28 02:22:30,285][87426] Updated weights for policy 1, policy_version 82460 (0.0012) -[2023-11-28 02:22:30,643][87424] Updated weights for policy 0, policy_version 82576 (0.0008) -[2023-11-28 02:22:31,025][87424] Updated weights for policy 0, policy_version 82586 (0.0007) -[2023-11-28 02:22:32,784][87426] Updated weights for policy 1, policy_version 82470 (0.0011) -[2023-11-28 02:22:33,070][87424] Updated weights for policy 0, policy_version 82596 (0.0008) -[2023-11-28 02:22:33,155][87426] Updated weights for policy 1, policy_version 82480 (0.0012) -[2023-11-28 02:22:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 42254336. Throughput: 0: 2691.3, 1: 2713.1. Samples: 42273304. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:22:33,445][86177] Avg episode reward: [(0, '-517.020'), (1, '-545.440')] -[2023-11-28 02:22:33,451][87424] Updated weights for policy 0, policy_version 82606 (0.0008) -[2023-11-28 02:22:33,531][87426] Updated weights for policy 1, policy_version 82490 (0.0012) -[2023-11-28 02:22:33,835][87424] Updated weights for policy 0, policy_version 82616 (0.0007) -[2023-11-28 02:22:35,711][87424] Updated weights for policy 0, policy_version 82626 (0.0008) -[2023-11-28 02:22:35,893][87426] Updated weights for policy 1, policy_version 82500 (0.0011) -[2023-11-28 02:22:36,088][87424] Updated weights for policy 0, policy_version 82636 (0.0012) -[2023-11-28 02:22:36,271][87426] Updated weights for policy 1, policy_version 82510 (0.0008) -[2023-11-28 02:22:36,471][87424] Updated weights for policy 0, policy_version 82646 (0.0012) -[2023-11-28 02:22:36,660][87426] Updated weights for policy 1, policy_version 82520 (0.0008) -[2023-11-28 02:22:36,851][87424] Updated weights for policy 0, policy_version 82656 (0.0012) -[2023-11-28 02:22:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42287104. Throughput: 0: 2706.8, 1: 2713.5. Samples: 42306200. Policy #0 lag: (min: 2.0, avg: 25.7, max: 47.0) -[2023-11-28 02:22:38,445][86177] Avg episode reward: [(0, '-510.990'), (1, '-512.760')] -[2023-11-28 02:22:38,473][87426] Updated weights for policy 1, policy_version 82530 (0.0011) -[2023-11-28 02:22:38,849][87426] Updated weights for policy 1, policy_version 82540 (0.0008) -[2023-11-28 02:22:39,202][87424] Updated weights for policy 0, policy_version 82666 (0.0011) -[2023-11-28 02:22:39,235][87426] Updated weights for policy 1, policy_version 82550 (0.0008) -[2023-11-28 02:22:39,586][87424] Updated weights for policy 0, policy_version 82676 (0.0012) -[2023-11-28 02:22:39,610][87426] Updated weights for policy 1, policy_version 82560 (0.0008) -[2023-11-28 02:22:39,967][87424] Updated weights for policy 0, policy_version 82686 (0.0011) -[2023-11-28 02:22:41,768][87426] Updated weights for policy 1, policy_version 82570 (0.0011) -[2023-11-28 02:22:42,016][87424] Updated weights for policy 0, policy_version 82696 (0.0012) -[2023-11-28 02:22:42,144][87426] Updated weights for policy 1, policy_version 82580 (0.0009) -[2023-11-28 02:22:42,389][87424] Updated weights for policy 0, policy_version 82706 (0.0010) -[2023-11-28 02:22:42,521][87426] Updated weights for policy 1, policy_version 82590 (0.0012) -[2023-11-28 02:22:42,772][87424] Updated weights for policy 0, policy_version 82716 (0.0008) -[2023-11-28 02:22:43,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42319872. Throughput: 0: 2703.7, 1: 2700.4. Samples: 42330156. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:22:43,445][86177] Avg episode reward: [(0, '-508.210'), (1, '-513.110')] -[2023-11-28 02:22:44,854][87424] Updated weights for policy 0, policy_version 82726 (0.0008) -[2023-11-28 02:22:45,097][87426] Updated weights for policy 1, policy_version 82600 (0.0010) -[2023-11-28 02:22:45,238][87424] Updated weights for policy 0, policy_version 82736 (0.0008) -[2023-11-28 02:22:45,481][87426] Updated weights for policy 1, policy_version 82610 (0.0010) -[2023-11-28 02:22:45,624][87424] Updated weights for policy 0, policy_version 82746 (0.0012) -[2023-11-28 02:22:45,851][87426] Updated weights for policy 1, policy_version 82620 (0.0011) -[2023-11-28 02:22:47,712][87426] Updated weights for policy 1, policy_version 82630 (0.0008) -[2023-11-28 02:22:47,749][87424] Updated weights for policy 0, policy_version 82756 (0.0012) -[2023-11-28 02:22:48,103][87426] Updated weights for policy 1, policy_version 82640 (0.0007) -[2023-11-28 02:22:48,135][87424] Updated weights for policy 0, policy_version 82766 (0.0012) -[2023-11-28 02:22:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 42336256. Throughput: 0: 2700.1, 1: 2705.2. Samples: 42354996. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:22:48,445][86177] Avg episode reward: [(0, '-503.840'), (1, '-510.270')] -[2023-11-28 02:22:48,475][87426] Updated weights for policy 1, policy_version 82650 (0.0009) -[2023-11-28 02:22:48,519][87424] Updated weights for policy 0, policy_version 82776 (0.0011) -[2023-11-28 02:22:50,460][87424] Updated weights for policy 0, policy_version 82786 (0.0011) -[2023-11-28 02:22:50,490][87426] Updated weights for policy 1, policy_version 82660 (0.0009) -[2023-11-28 02:22:50,853][87424] Updated weights for policy 0, policy_version 82796 (0.0012) -[2023-11-28 02:22:50,866][87426] Updated weights for policy 1, policy_version 82670 (0.0010) -[2023-11-28 02:22:51,238][87424] Updated weights for policy 0, policy_version 82806 (0.0012) -[2023-11-28 02:22:51,242][87426] Updated weights for policy 1, policy_version 82680 (0.0009) -[2023-11-28 02:22:51,615][87424] Updated weights for policy 0, policy_version 82816 (0.0012) -[2023-11-28 02:22:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42369024. Throughput: 0: 2735.1, 1: 2701.0. Samples: 42388956. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:22:53,445][86177] Avg episode reward: [(0, '-502.370'), (1, '-513.310')] -[2023-11-28 02:22:53,727][87426] Updated weights for policy 1, policy_version 82690 (0.0008) -[2023-11-28 02:22:53,856][87424] Updated weights for policy 0, policy_version 82826 (0.0012) -[2023-11-28 02:22:54,099][87426] Updated weights for policy 1, policy_version 82700 (0.0009) -[2023-11-28 02:22:54,240][87424] Updated weights for policy 0, policy_version 82836 (0.0010) -[2023-11-28 02:22:54,481][87426] Updated weights for policy 1, policy_version 82710 (0.0009) -[2023-11-28 02:22:54,623][87424] Updated weights for policy 0, policy_version 82846 (0.0011) -[2023-11-28 02:22:54,852][87426] Updated weights for policy 1, policy_version 82720 (0.0007) -[2023-11-28 02:22:56,974][87426] Updated weights for policy 1, policy_version 82730 (0.0008) -[2023-11-28 02:22:57,167][87424] Updated weights for policy 0, policy_version 82856 (0.0010) -[2023-11-28 02:22:57,355][87426] Updated weights for policy 1, policy_version 82740 (0.0008) -[2023-11-28 02:22:57,558][87424] Updated weights for policy 0, policy_version 82866 (0.0007) -[2023-11-28 02:22:57,733][87426] Updated weights for policy 1, policy_version 82750 (0.0007) -[2023-11-28 02:22:57,935][87424] Updated weights for policy 0, policy_version 82876 (0.0007) -[2023-11-28 02:22:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42401792. Throughput: 0: 2744.4, 1: 2709.9. Samples: 42412796. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:22:58,445][86177] Avg episode reward: [(0, '-503.280'), (1, '-527.000')] -[2023-11-28 02:23:00,109][87424] Updated weights for policy 0, policy_version 82886 (0.0010) -[2023-11-28 02:23:00,131][87426] Updated weights for policy 1, policy_version 82760 (0.0010) -[2023-11-28 02:23:00,486][87424] Updated weights for policy 0, policy_version 82896 (0.0011) -[2023-11-28 02:23:00,507][87426] Updated weights for policy 1, policy_version 82770 (0.0012) -[2023-11-28 02:23:00,875][87424] Updated weights for policy 0, policy_version 82906 (0.0011) -[2023-11-28 02:23:00,888][87426] Updated weights for policy 1, policy_version 82780 (0.0009) -[2023-11-28 02:23:03,020][87424] Updated weights for policy 0, policy_version 82916 (0.0011) -[2023-11-28 02:23:03,130][87426] Updated weights for policy 1, policy_version 82790 (0.0009) -[2023-11-28 02:23:03,406][87424] Updated weights for policy 0, policy_version 82926 (0.0011) -[2023-11-28 02:23:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 42418176. Throughput: 0: 2752.5, 1: 2704.3. Samples: 42436776. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:23:03,445][86177] Avg episode reward: [(0, '-539.730'), (1, '-535.100')] -[2023-11-28 02:23:03,507][87426] Updated weights for policy 1, policy_version 82800 (0.0009) -[2023-11-28 02:23:03,785][87424] Updated weights for policy 0, policy_version 82936 (0.0008) -[2023-11-28 02:23:03,887][87426] Updated weights for policy 1, policy_version 82810 (0.0010) -[2023-11-28 02:23:05,835][87424] Updated weights for policy 0, policy_version 82946 (0.0009) -[2023-11-28 02:23:05,840][87426] Updated weights for policy 1, policy_version 82820 (0.0011) -[2023-11-28 02:23:06,210][87424] Updated weights for policy 0, policy_version 82956 (0.0007) -[2023-11-28 02:23:06,212][87426] Updated weights for policy 1, policy_version 82830 (0.0012) -[2023-11-28 02:23:06,600][87426] Updated weights for policy 1, policy_version 82840 (0.0012) -[2023-11-28 02:23:06,600][87424] Updated weights for policy 0, policy_version 82966 (0.0007) -[2023-11-28 02:23:06,979][87424] Updated weights for policy 0, policy_version 82976 (0.0009) -[2023-11-28 02:23:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42450944. Throughput: 0: 2763.7, 1: 2725.5. Samples: 42469388. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:23:08,445][86177] Avg episode reward: [(0, '-538.790'), (1, '-552.230')] -[2023-11-28 02:23:08,587][87426] Updated weights for policy 1, policy_version 82850 (0.0012) -[2023-11-28 02:23:08,955][87426] Updated weights for policy 1, policy_version 82860 (0.0011) -[2023-11-28 02:23:09,087][87424] Updated weights for policy 0, policy_version 82986 (0.0012) -[2023-11-28 02:23:09,345][87426] Updated weights for policy 1, policy_version 82870 (0.0012) -[2023-11-28 02:23:09,467][87424] Updated weights for policy 0, policy_version 82996 (0.0012) -[2023-11-28 02:23:09,717][87426] Updated weights for policy 1, policy_version 82880 (0.0011) -[2023-11-28 02:23:09,855][87424] Updated weights for policy 0, policy_version 83006 (0.0012) -[2023-11-28 02:23:11,721][87426] Updated weights for policy 1, policy_version 82890 (0.0009) -[2023-11-28 02:23:11,885][87424] Updated weights for policy 0, policy_version 83016 (0.0011) -[2023-11-28 02:23:12,094][87426] Updated weights for policy 1, policy_version 82900 (0.0011) -[2023-11-28 02:23:12,281][87424] Updated weights for policy 0, policy_version 83026 (0.0012) -[2023-11-28 02:23:12,474][87426] Updated weights for policy 1, policy_version 82910 (0.0011) -[2023-11-28 02:23:12,654][87424] Updated weights for policy 0, policy_version 83036 (0.0011) -[2023-11-28 02:23:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42483712. Throughput: 0: 2757.9, 1: 2726.0. Samples: 42494620. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:23:13,445][86177] Avg episode reward: [(0, '-572.040'), (1, '-550.190')] -[2023-11-28 02:23:14,695][87426] Updated weights for policy 1, policy_version 82920 (0.0008) -[2023-11-28 02:23:14,719][87424] Updated weights for policy 0, policy_version 83046 (0.0010) -[2023-11-28 02:23:15,072][87426] Updated weights for policy 1, policy_version 82930 (0.0011) -[2023-11-28 02:23:15,112][87424] Updated weights for policy 0, policy_version 83056 (0.0008) -[2023-11-28 02:23:15,453][87426] Updated weights for policy 1, policy_version 82940 (0.0010) -[2023-11-28 02:23:15,483][87424] Updated weights for policy 0, policy_version 83066 (0.0009) -[2023-11-28 02:23:17,399][87424] Updated weights for policy 0, policy_version 83076 (0.0011) -[2023-11-28 02:23:17,625][87426] Updated weights for policy 1, policy_version 82950 (0.0010) -[2023-11-28 02:23:17,773][87424] Updated weights for policy 0, policy_version 83086 (0.0010) -[2023-11-28 02:23:17,999][87426] Updated weights for policy 1, policy_version 82960 (0.0009) -[2023-11-28 02:23:18,157][87424] Updated weights for policy 0, policy_version 83096 (0.0010) -[2023-11-28 02:23:18,382][87426] Updated weights for policy 1, policy_version 82970 (0.0009) -[2023-11-28 02:23:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 42500096. Throughput: 0: 2771.5, 1: 2714.6. Samples: 42520184. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:23:18,446][86177] Avg episode reward: [(0, '-572.590'), (1, '-529.340')] -[2023-11-28 02:23:20,619][87426] Updated weights for policy 1, policy_version 82980 (0.0009) -[2023-11-28 02:23:20,695][87424] Updated weights for policy 0, policy_version 83106 (0.0008) -[2023-11-28 02:23:20,994][87426] Updated weights for policy 1, policy_version 82990 (0.0011) -[2023-11-28 02:23:21,090][87424] Updated weights for policy 0, policy_version 83116 (0.0008) -[2023-11-28 02:23:21,366][87426] Updated weights for policy 1, policy_version 83000 (0.0012) -[2023-11-28 02:23:21,465][87424] Updated weights for policy 0, policy_version 83126 (0.0010) -[2023-11-28 02:23:21,847][87424] Updated weights for policy 0, policy_version 83136 (0.0009) -[2023-11-28 02:23:23,376][87426] Updated weights for policy 1, policy_version 83010 (0.0012) -[2023-11-28 02:23:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42532864. Throughput: 0: 2742.0, 1: 2700.2. Samples: 42551096. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:23:23,445][86177] Avg episode reward: [(0, '-549.300'), (1, '-523.200')] -[2023-11-28 02:23:23,758][87426] Updated weights for policy 1, policy_version 83020 (0.0012) -[2023-11-28 02:23:24,125][87426] Updated weights for policy 1, policy_version 83030 (0.0010) -[2023-11-28 02:23:24,329][87424] Updated weights for policy 0, policy_version 83146 (0.0007) -[2023-11-28 02:23:24,502][87426] Updated weights for policy 1, policy_version 83040 (0.0007) -[2023-11-28 02:23:24,710][87424] Updated weights for policy 0, policy_version 83156 (0.0008) -[2023-11-28 02:23:25,091][87424] Updated weights for policy 0, policy_version 83166 (0.0007) -[2023-11-28 02:23:26,997][87426] Updated weights for policy 1, policy_version 83050 (0.0009) -[2023-11-28 02:23:27,371][87426] Updated weights for policy 1, policy_version 83060 (0.0011) -[2023-11-28 02:23:27,519][87424] Updated weights for policy 0, policy_version 83176 (0.0010) -[2023-11-28 02:23:27,745][87426] Updated weights for policy 1, policy_version 83070 (0.0008) -[2023-11-28 02:23:27,899][87424] Updated weights for policy 0, policy_version 83186 (0.0011) -[2023-11-28 02:23:28,289][87424] Updated weights for policy 0, policy_version 83196 (0.0012) -[2023-11-28 02:23:28,445][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42565632. Throughput: 0: 2730.5, 1: 2684.5. Samples: 42573832. Policy #0 lag: (min: 4.0, avg: 21.5, max: 36.0) -[2023-11-28 02:23:28,446][86177] Avg episode reward: [(0, '-551.560'), (1, '-516.620')] -[2023-11-28 02:23:30,084][87424] Updated weights for policy 0, policy_version 83206 (0.0012) -[2023-11-28 02:23:30,221][87426] Updated weights for policy 1, policy_version 83080 (0.0009) -[2023-11-28 02:23:30,456][87424] Updated weights for policy 0, policy_version 83216 (0.0010) -[2023-11-28 02:23:30,600][87426] Updated weights for policy 1, policy_version 83090 (0.0011) -[2023-11-28 02:23:30,846][87424] Updated weights for policy 0, policy_version 83226 (0.0008) -[2023-11-28 02:23:30,974][87426] Updated weights for policy 1, policy_version 83100 (0.0011) -[2023-11-28 02:23:32,894][87424] Updated weights for policy 0, policy_version 83236 (0.0009) -[2023-11-28 02:23:32,941][87426] Updated weights for policy 1, policy_version 83110 (0.0009) -[2023-11-28 02:23:33,272][87424] Updated weights for policy 0, policy_version 83246 (0.0012) -[2023-11-28 02:23:33,324][87426] Updated weights for policy 1, policy_version 83120 (0.0011) -[2023-11-28 02:23:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42582016. Throughput: 0: 2740.7, 1: 2690.1. Samples: 42599384. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:23:33,445][86177] Avg episode reward: [(0, '-515.930'), (1, '-508.290')] -[2023-11-28 02:23:33,658][87424] Updated weights for policy 0, policy_version 83256 (0.0011) -[2023-11-28 02:23:33,699][87426] Updated weights for policy 1, policy_version 83130 (0.0008) -[2023-11-28 02:23:35,585][87426] Updated weights for policy 1, policy_version 83140 (0.0007) -[2023-11-28 02:23:35,970][87426] Updated weights for policy 1, policy_version 83150 (0.0010) -[2023-11-28 02:23:36,124][87424] Updated weights for policy 0, policy_version 83266 (0.0008) -[2023-11-28 02:23:36,347][87426] Updated weights for policy 1, policy_version 83160 (0.0008) -[2023-11-28 02:23:36,506][87424] Updated weights for policy 0, policy_version 83276 (0.0008) -[2023-11-28 02:23:36,893][87424] Updated weights for policy 0, policy_version 83286 (0.0009) -[2023-11-28 02:23:37,267][87424] Updated weights for policy 0, policy_version 83296 (0.0012) -[2023-11-28 02:23:38,278][87426] Updated weights for policy 1, policy_version 83170 (0.0009) -[2023-11-28 02:23:38,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 42614784. Throughput: 0: 2709.0, 1: 2687.3. Samples: 42631788. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:23:38,445][86177] Avg episode reward: [(0, '-516.650'), (1, '-515.120')] -[2023-11-28 02:23:38,660][87426] Updated weights for policy 1, policy_version 83180 (0.0012) -[2023-11-28 02:23:39,033][87426] Updated weights for policy 1, policy_version 83190 (0.0011) -[2023-11-28 02:23:39,403][87426] Updated weights for policy 1, policy_version 83200 (0.0011) -[2023-11-28 02:23:39,667][87424] Updated weights for policy 0, policy_version 83306 (0.0011) -[2023-11-28 02:23:40,048][87424] Updated weights for policy 0, policy_version 83316 (0.0016) -[2023-11-28 02:23:40,429][87424] Updated weights for policy 0, policy_version 83326 (0.0012) -[2023-11-28 02:23:41,605][87426] Updated weights for policy 1, policy_version 83210 (0.0012) -[2023-11-28 02:23:41,994][87426] Updated weights for policy 1, policy_version 83220 (0.0012) -[2023-11-28 02:23:42,371][87426] Updated weights for policy 1, policy_version 83230 (0.0010) -[2023-11-28 02:23:42,889][87424] Updated weights for policy 0, policy_version 83336 (0.0010) -[2023-11-28 02:23:43,278][87424] Updated weights for policy 0, policy_version 83346 (0.0009) -[2023-11-28 02:23:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 42639360. Throughput: 0: 2702.4, 1: 2708.4. Samples: 42656280. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:23:43,445][86177] Avg episode reward: [(0, '-526.630'), (1, '-531.100')] -[2023-11-28 02:23:43,666][87424] Updated weights for policy 0, policy_version 83356 (0.0008) -[2023-11-28 02:23:44,385][87426] Updated weights for policy 1, policy_version 83240 (0.0011) -[2023-11-28 02:23:44,769][87426] Updated weights for policy 1, policy_version 83250 (0.0012) -[2023-11-28 02:23:45,163][87426] Updated weights for policy 1, policy_version 83260 (0.0011) -[2023-11-28 02:23:46,124][87424] Updated weights for policy 0, policy_version 83366 (0.0007) -[2023-11-28 02:23:46,519][87424] Updated weights for policy 0, policy_version 83376 (0.0008) -[2023-11-28 02:23:46,903][87424] Updated weights for policy 0, policy_version 83386 (0.0007) -[2023-11-28 02:23:47,158][87426] Updated weights for policy 1, policy_version 83270 (0.0011) -[2023-11-28 02:23:47,532][87426] Updated weights for policy 1, policy_version 83280 (0.0012) -[2023-11-28 02:23:47,921][87426] Updated weights for policy 1, policy_version 83290 (0.0012) -[2023-11-28 02:23:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 42672128. Throughput: 0: 2689.6, 1: 2732.4. Samples: 42680768. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:23:48,445][86177] Avg episode reward: [(0, '-555.460'), (1, '-530.640')] -[2023-11-28 02:23:48,625][87424] Updated weights for policy 0, policy_version 83396 (0.0009) -[2023-11-28 02:23:49,010][87424] Updated weights for policy 0, policy_version 83406 (0.0009) -[2023-11-28 02:23:49,396][87424] Updated weights for policy 0, policy_version 83416 (0.0011) -[2023-11-28 02:23:50,372][87426] Updated weights for policy 1, policy_version 83300 (0.0012) -[2023-11-28 02:23:50,752][87426] Updated weights for policy 1, policy_version 83310 (0.0012) -[2023-11-28 02:23:51,137][87426] Updated weights for policy 1, policy_version 83320 (0.0012) -[2023-11-28 02:23:51,740][87424] Updated weights for policy 0, policy_version 83426 (0.0012) -[2023-11-28 02:23:52,124][87424] Updated weights for policy 0, policy_version 83436 (0.0012) -[2023-11-28 02:23:52,507][87424] Updated weights for policy 0, policy_version 83446 (0.0012) -[2023-11-28 02:23:52,885][87424] Updated weights for policy 0, policy_version 83456 (0.0012) -[2023-11-28 02:23:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42696704. Throughput: 0: 2681.9, 1: 2730.5. Samples: 42712944. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:23:53,445][86177] Avg episode reward: [(0, '-583.820'), (1, '-525.270')] -[2023-11-28 02:23:53,582][87426] Updated weights for policy 1, policy_version 83330 (0.0011) -[2023-11-28 02:23:53,963][87426] Updated weights for policy 1, policy_version 83340 (0.0011) -[2023-11-28 02:23:54,349][87426] Updated weights for policy 1, policy_version 83350 (0.0012) -[2023-11-28 02:23:54,720][87426] Updated weights for policy 1, policy_version 83360 (0.0011) -[2023-11-28 02:23:55,106][87424] Updated weights for policy 0, policy_version 83466 (0.0012) -[2023-11-28 02:23:55,478][87424] Updated weights for policy 0, policy_version 83476 (0.0012) -[2023-11-28 02:23:55,868][87424] Updated weights for policy 0, policy_version 83486 (0.0011) -[2023-11-28 02:23:56,693][87426] Updated weights for policy 1, policy_version 83370 (0.0011) -[2023-11-28 02:23:57,077][87426] Updated weights for policy 1, policy_version 83380 (0.0011) -[2023-11-28 02:23:57,445][87426] Updated weights for policy 1, policy_version 83390 (0.0012) -[2023-11-28 02:23:58,130][87424] Updated weights for policy 0, policy_version 83496 (0.0011) -[2023-11-28 02:23:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 42721280. Throughput: 0: 2672.4, 1: 2744.4. Samples: 42738380. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:23:58,445][86177] Avg episode reward: [(0, '-603.630'), (1, '-520.450')] -[2023-11-28 02:23:58,524][87424] Updated weights for policy 0, policy_version 83506 (0.0011) -[2023-11-28 02:23:58,904][87424] Updated weights for policy 0, policy_version 83516 (0.0007) -[2023-11-28 02:23:59,196][87426] Updated weights for policy 1, policy_version 83400 (0.0012) -[2023-11-28 02:23:59,584][87426] Updated weights for policy 1, policy_version 83410 (0.0012) -[2023-11-28 02:23:59,967][87426] Updated weights for policy 1, policy_version 83420 (0.0012) -[2023-11-28 02:24:01,102][87424] Updated weights for policy 0, policy_version 83526 (0.0011) -[2023-11-28 02:24:01,484][87424] Updated weights for policy 0, policy_version 83536 (0.0011) -[2023-11-28 02:24:01,866][87424] Updated weights for policy 0, policy_version 83546 (0.0009) -[2023-11-28 02:24:02,273][87426] Updated weights for policy 1, policy_version 83430 (0.0012) -[2023-11-28 02:24:02,655][87426] Updated weights for policy 1, policy_version 83440 (0.0008) -[2023-11-28 02:24:03,029][87426] Updated weights for policy 1, policy_version 83450 (0.0009) -[2023-11-28 02:24:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 42754048. Throughput: 0: 2650.9, 1: 2761.5. Samples: 42763740. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:24:03,445][86177] Avg episode reward: [(0, '-587.420'), (1, '-501.400')] -[2023-11-28 02:24:04,149][87424] Updated weights for policy 0, policy_version 83556 (0.0011) -[2023-11-28 02:24:04,529][87424] Updated weights for policy 0, policy_version 83566 (0.0010) -[2023-11-28 02:24:04,916][87424] Updated weights for policy 0, policy_version 83576 (0.0009) -[2023-11-28 02:24:05,004][87426] Updated weights for policy 1, policy_version 83460 (0.0009) -[2023-11-28 02:24:05,375][87426] Updated weights for policy 1, policy_version 83470 (0.0009) -[2023-11-28 02:24:05,758][87426] Updated weights for policy 1, policy_version 83480 (0.0009) -[2023-11-28 02:24:07,204][87424] Updated weights for policy 0, policy_version 83586 (0.0011) -[2023-11-28 02:24:07,587][87424] Updated weights for policy 0, policy_version 83596 (0.0012) -[2023-11-28 02:24:07,965][87424] Updated weights for policy 0, policy_version 83606 (0.0012) -[2023-11-28 02:24:08,232][87426] Updated weights for policy 1, policy_version 83490 (0.0009) -[2023-11-28 02:24:08,344][87424] Updated weights for policy 0, policy_version 83616 (0.0012) -[2023-11-28 02:24:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 42778624. Throughput: 0: 2670.7, 1: 2763.5. Samples: 42795636. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:24:08,446][86177] Avg episode reward: [(0, '-564.690'), (1, '-501.790')] -[2023-11-28 02:24:08,616][87426] Updated weights for policy 1, policy_version 83500 (0.0011) -[2023-11-28 02:24:08,985][87426] Updated weights for policy 1, policy_version 83510 (0.0012) -[2023-11-28 02:24:09,359][87426] Updated weights for policy 1, policy_version 83520 (0.0012) -[2023-11-28 02:24:10,195][87424] Updated weights for policy 0, policy_version 83626 (0.0010) -[2023-11-28 02:24:10,576][87424] Updated weights for policy 0, policy_version 83636 (0.0010) -[2023-11-28 02:24:10,963][87424] Updated weights for policy 0, policy_version 83646 (0.0007) -[2023-11-28 02:24:11,992][87426] Updated weights for policy 1, policy_version 83530 (0.0009) -[2023-11-28 02:24:12,371][87426] Updated weights for policy 1, policy_version 83540 (0.0009) -[2023-11-28 02:24:12,749][87426] Updated weights for policy 1, policy_version 83550 (0.0008) -[2023-11-28 02:24:13,135][87424] Updated weights for policy 0, policy_version 83656 (0.0012) -[2023-11-28 02:24:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 42803200. Throughput: 0: 2683.7, 1: 2772.4. Samples: 42819356. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:24:13,445][86177] Avg episode reward: [(0, '-545.270'), (1, '-537.510')] -[2023-11-28 02:24:13,518][87424] Updated weights for policy 0, policy_version 83666 (0.0012) -[2023-11-28 02:24:13,904][87424] Updated weights for policy 0, policy_version 83676 (0.0012) -[2023-11-28 02:24:15,347][87426] Updated weights for policy 1, policy_version 83560 (0.0009) -[2023-11-28 02:24:15,731][87426] Updated weights for policy 1, policy_version 83570 (0.0011) -[2023-11-28 02:24:16,118][87426] Updated weights for policy 1, policy_version 83580 (0.0009) -[2023-11-28 02:24:16,501][87424] Updated weights for policy 0, policy_version 83686 (0.0012) -[2023-11-28 02:24:16,865][87424] Updated weights for policy 0, policy_version 83696 (0.0012) -[2023-11-28 02:24:17,247][87424] Updated weights for policy 0, policy_version 83706 (0.0012) -[2023-11-28 02:24:17,858][87426] Updated weights for policy 1, policy_version 83590 (0.0010) -[2023-11-28 02:24:18,238][87426] Updated weights for policy 1, policy_version 83600 (0.0009) -[2023-11-28 02:24:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 42827776. Throughput: 0: 2623.8, 1: 2768.0. Samples: 42842016. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:24:18,445][86177] Avg episode reward: [(0, '-541.420'), (1, '-539.050')] -[2023-11-28 02:24:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000083712_21430272.pth... -[2023-11-28 02:24:18,485][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000081184_20783104.pth -[2023-11-28 02:24:18,616][87426] Updated weights for policy 1, policy_version 83610 (0.0009) -[2023-11-28 02:24:18,844][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000083616_21405696.pth... -[2023-11-28 02:24:18,887][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000081056_20750336.pth -[2023-11-28 02:24:19,848][87424] Updated weights for policy 0, policy_version 83716 (0.0011) -[2023-11-28 02:24:20,233][87424] Updated weights for policy 0, policy_version 83726 (0.0011) -[2023-11-28 02:24:20,622][87424] Updated weights for policy 0, policy_version 83736 (0.0008) -[2023-11-28 02:24:20,987][87426] Updated weights for policy 1, policy_version 83620 (0.0009) -[2023-11-28 02:24:21,365][87426] Updated weights for policy 1, policy_version 83630 (0.0011) -[2023-11-28 02:24:21,737][87426] Updated weights for policy 1, policy_version 83640 (0.0012) -[2023-11-28 02:24:22,920][87424] Updated weights for policy 0, policy_version 83746 (0.0010) -[2023-11-28 02:24:23,303][87424] Updated weights for policy 0, policy_version 83756 (0.0011) -[2023-11-28 02:24:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 42852352. Throughput: 0: 2628.7, 1: 2746.4. Samples: 42873668. Policy #0 lag: (min: 31.0, avg: 53.0, max: 90.0) -[2023-11-28 02:24:23,445][86177] Avg episode reward: [(0, '-545.900'), (1, '-537.150')] -[2023-11-28 02:24:23,682][87424] Updated weights for policy 0, policy_version 83766 (0.0008) -[2023-11-28 02:24:24,067][87424] Updated weights for policy 0, policy_version 83776 (0.0012) -[2023-11-28 02:24:24,249][87426] Updated weights for policy 1, policy_version 83650 (0.0012) -[2023-11-28 02:24:24,633][87426] Updated weights for policy 1, policy_version 83660 (0.0012) -[2023-11-28 02:24:25,021][87426] Updated weights for policy 1, policy_version 83670 (0.0012) -[2023-11-28 02:24:25,396][87426] Updated weights for policy 1, policy_version 83680 (0.0012) -[2023-11-28 02:24:26,218][87424] Updated weights for policy 0, policy_version 83786 (0.0012) -[2023-11-28 02:24:26,602][87424] Updated weights for policy 0, policy_version 83796 (0.0011) -[2023-11-28 02:24:26,979][87424] Updated weights for policy 0, policy_version 83806 (0.0011) -[2023-11-28 02:24:27,165][87426] Updated weights for policy 1, policy_version 83690 (0.0007) -[2023-11-28 02:24:27,558][87426] Updated weights for policy 1, policy_version 83700 (0.0010) -[2023-11-28 02:24:27,947][87426] Updated weights for policy 1, policy_version 83710 (0.0011) -[2023-11-28 02:24:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 42885120. Throughput: 0: 2629.1, 1: 2735.7. Samples: 42897696. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:24:28,445][86177] Avg episode reward: [(0, '-553.510'), (1, '-576.280')] -[2023-11-28 02:24:28,930][87424] Updated weights for policy 0, policy_version 83816 (0.0011) -[2023-11-28 02:24:29,300][87424] Updated weights for policy 0, policy_version 83826 (0.0011) -[2023-11-28 02:24:29,694][87424] Updated weights for policy 0, policy_version 83836 (0.0011) -[2023-11-28 02:24:30,259][87426] Updated weights for policy 1, policy_version 83720 (0.0011) -[2023-11-28 02:24:30,643][87426] Updated weights for policy 1, policy_version 83730 (0.0012) -[2023-11-28 02:24:31,018][87426] Updated weights for policy 1, policy_version 83740 (0.0012) -[2023-11-28 02:24:31,698][87424] Updated weights for policy 0, policy_version 83846 (0.0011) -[2023-11-28 02:24:32,078][87424] Updated weights for policy 0, policy_version 83856 (0.0011) -[2023-11-28 02:24:32,464][87424] Updated weights for policy 0, policy_version 83866 (0.0011) -[2023-11-28 02:24:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 42909696. Throughput: 0: 2653.1, 1: 2725.3. Samples: 42922796. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:24:33,445][86177] Avg episode reward: [(0, '-556.570'), (1, '-562.260')] -[2023-11-28 02:24:33,503][87426] Updated weights for policy 1, policy_version 83750 (0.0009) -[2023-11-28 02:24:33,881][87426] Updated weights for policy 1, policy_version 83760 (0.0009) -[2023-11-28 02:24:34,267][87426] Updated weights for policy 1, policy_version 83770 (0.0007) -[2023-11-28 02:24:34,791][87424] Updated weights for policy 0, policy_version 83876 (0.0010) -[2023-11-28 02:24:35,182][87424] Updated weights for policy 0, policy_version 83886 (0.0009) -[2023-11-28 02:24:35,555][87424] Updated weights for policy 0, policy_version 83896 (0.0010) -[2023-11-28 02:24:36,038][87426] Updated weights for policy 1, policy_version 83780 (0.0009) -[2023-11-28 02:24:36,424][87426] Updated weights for policy 1, policy_version 83790 (0.0012) -[2023-11-28 02:24:36,808][87426] Updated weights for policy 1, policy_version 83800 (0.0012) -[2023-11-28 02:24:37,622][87424] Updated weights for policy 0, policy_version 83906 (0.0008) -[2023-11-28 02:24:37,999][87424] Updated weights for policy 0, policy_version 83916 (0.0011) -[2023-11-28 02:24:38,382][87424] Updated weights for policy 0, policy_version 83926 (0.0011) -[2023-11-28 02:24:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 42934272. Throughput: 0: 2650.5, 1: 2711.7. Samples: 42954244. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:24:38,445][86177] Avg episode reward: [(0, '-536.180'), (1, '-562.180')] -[2023-11-28 02:24:38,772][87424] Updated weights for policy 0, policy_version 83936 (0.0011) -[2023-11-28 02:24:39,430][87426] Updated weights for policy 1, policy_version 83810 (0.0012) -[2023-11-28 02:24:39,806][87426] Updated weights for policy 1, policy_version 83820 (0.0012) -[2023-11-28 02:24:40,185][87426] Updated weights for policy 1, policy_version 83830 (0.0011) -[2023-11-28 02:24:40,563][87426] Updated weights for policy 1, policy_version 83840 (0.0010) -[2023-11-28 02:24:40,733][87424] Updated weights for policy 0, policy_version 83946 (0.0008) -[2023-11-28 02:24:41,109][87424] Updated weights for policy 0, policy_version 83956 (0.0008) -[2023-11-28 02:24:41,497][87424] Updated weights for policy 0, policy_version 83966 (0.0007) -[2023-11-28 02:24:43,173][87426] Updated weights for policy 1, policy_version 83850 (0.0012) -[2023-11-28 02:24:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 42958848. Throughput: 0: 2651.8, 1: 2660.5. Samples: 42977436. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:24:43,445][86177] Avg episode reward: [(0, '-533.970'), (1, '-529.770')] -[2023-11-28 02:24:43,560][87426] Updated weights for policy 1, policy_version 83860 (0.0012) -[2023-11-28 02:24:43,932][87426] Updated weights for policy 1, policy_version 83870 (0.0012) -[2023-11-28 02:24:44,124][87424] Updated weights for policy 0, policy_version 83976 (0.0011) -[2023-11-28 02:24:44,497][87424] Updated weights for policy 0, policy_version 83986 (0.0012) -[2023-11-28 02:24:44,881][87424] Updated weights for policy 0, policy_version 83996 (0.0012) -[2023-11-28 02:24:45,702][87426] Updated weights for policy 1, policy_version 83880 (0.0012) -[2023-11-28 02:24:46,074][87426] Updated weights for policy 1, policy_version 83890 (0.0011) -[2023-11-28 02:24:46,448][87426] Updated weights for policy 1, policy_version 83900 (0.0011) -[2023-11-28 02:24:47,392][87424] Updated weights for policy 0, policy_version 84006 (0.0012) -[2023-11-28 02:24:47,779][87424] Updated weights for policy 0, policy_version 84016 (0.0012) -[2023-11-28 02:24:48,173][87424] Updated weights for policy 0, policy_version 84026 (0.0009) -[2023-11-28 02:24:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 42991616. Throughput: 0: 2628.1, 1: 2642.6. Samples: 43000920. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:24:48,445][86177] Avg episode reward: [(0, '-544.940'), (1, '-552.680')] -[2023-11-28 02:24:48,654][87426] Updated weights for policy 1, policy_version 83910 (0.0012) -[2023-11-28 02:24:49,032][87426] Updated weights for policy 1, policy_version 83920 (0.0012) -[2023-11-28 02:24:49,413][87426] Updated weights for policy 1, policy_version 83930 (0.0012) -[2023-11-28 02:24:50,216][87424] Updated weights for policy 0, policy_version 84036 (0.0010) -[2023-11-28 02:24:50,601][87424] Updated weights for policy 0, policy_version 84046 (0.0012) -[2023-11-28 02:24:50,992][87424] Updated weights for policy 0, policy_version 84056 (0.0012) -[2023-11-28 02:24:51,613][87426] Updated weights for policy 1, policy_version 83940 (0.0011) -[2023-11-28 02:24:51,990][87426] Updated weights for policy 1, policy_version 83950 (0.0011) -[2023-11-28 02:24:52,371][87426] Updated weights for policy 1, policy_version 83960 (0.0009) -[2023-11-28 02:24:53,196][87424] Updated weights for policy 0, policy_version 84066 (0.0012) -[2023-11-28 02:24:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 43016192. Throughput: 0: 2641.5, 1: 2654.9. Samples: 43033976. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:24:53,445][86177] Avg episode reward: [(0, '-538.900'), (1, '-533.450')] -[2023-11-28 02:24:53,581][87424] Updated weights for policy 0, policy_version 84076 (0.0011) -[2023-11-28 02:24:53,958][87424] Updated weights for policy 0, policy_version 84086 (0.0012) -[2023-11-28 02:24:54,346][87424] Updated weights for policy 0, policy_version 84096 (0.0011) -[2023-11-28 02:24:54,526][87426] Updated weights for policy 1, policy_version 83970 (0.0012) -[2023-11-28 02:24:54,900][87426] Updated weights for policy 1, policy_version 83980 (0.0012) -[2023-11-28 02:24:55,278][87426] Updated weights for policy 1, policy_version 83990 (0.0012) -[2023-11-28 02:24:55,649][87426] Updated weights for policy 1, policy_version 84000 (0.0012) -[2023-11-28 02:24:56,363][87424] Updated weights for policy 0, policy_version 84106 (0.0009) -[2023-11-28 02:24:56,754][87424] Updated weights for policy 0, policy_version 84116 (0.0007) -[2023-11-28 02:24:57,122][87424] Updated weights for policy 0, policy_version 84126 (0.0010) -[2023-11-28 02:24:58,195][87426] Updated weights for policy 1, policy_version 84010 (0.0012) -[2023-11-28 02:24:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 43040768. Throughput: 0: 2658.6, 1: 2662.1. Samples: 43058788. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:24:58,445][86177] Avg episode reward: [(0, '-534.790'), (1, '-534.200')] -[2023-11-28 02:24:58,573][87426] Updated weights for policy 1, policy_version 84020 (0.0011) -[2023-11-28 02:24:58,952][87426] Updated weights for policy 1, policy_version 84030 (0.0012) -[2023-11-28 02:24:59,125][87424] Updated weights for policy 0, policy_version 84136 (0.0009) -[2023-11-28 02:24:59,515][87424] Updated weights for policy 0, policy_version 84146 (0.0007) -[2023-11-28 02:24:59,886][87424] Updated weights for policy 0, policy_version 84156 (0.0008) -[2023-11-28 02:25:01,155][87426] Updated weights for policy 1, policy_version 84040 (0.0012) -[2023-11-28 02:25:01,523][87426] Updated weights for policy 1, policy_version 84050 (0.0011) -[2023-11-28 02:25:01,903][87426] Updated weights for policy 1, policy_version 84060 (0.0010) -[2023-11-28 02:25:01,913][87424] Updated weights for policy 0, policy_version 84166 (0.0010) -[2023-11-28 02:25:02,308][87424] Updated weights for policy 0, policy_version 84176 (0.0011) -[2023-11-28 02:25:02,688][87424] Updated weights for policy 0, policy_version 84186 (0.0011) -[2023-11-28 02:25:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 43073536. Throughput: 0: 2698.9, 1: 2665.0. Samples: 43083392. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:25:03,445][86177] Avg episode reward: [(0, '-530.490'), (1, '-527.870')] -[2023-11-28 02:25:04,403][87426] Updated weights for policy 1, policy_version 84070 (0.0010) -[2023-11-28 02:25:04,560][87424] Updated weights for policy 0, policy_version 84196 (0.0011) -[2023-11-28 02:25:04,780][87426] Updated weights for policy 1, policy_version 84080 (0.0009) -[2023-11-28 02:25:04,942][87424] Updated weights for policy 0, policy_version 84206 (0.0009) -[2023-11-28 02:25:05,163][87426] Updated weights for policy 1, policy_version 84090 (0.0010) -[2023-11-28 02:25:05,319][87424] Updated weights for policy 0, policy_version 84216 (0.0011) -[2023-11-28 02:25:07,174][87426] Updated weights for policy 1, policy_version 84100 (0.0009) -[2023-11-28 02:25:07,556][87426] Updated weights for policy 1, policy_version 84110 (0.0010) -[2023-11-28 02:25:07,770][87424] Updated weights for policy 0, policy_version 84226 (0.0011) -[2023-11-28 02:25:07,924][87426] Updated weights for policy 1, policy_version 84120 (0.0012) -[2023-11-28 02:25:08,143][87424] Updated weights for policy 0, policy_version 84236 (0.0009) -[2023-11-28 02:25:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 43098112. Throughput: 0: 2715.3, 1: 2675.3. Samples: 43116244. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:25:08,445][86177] Avg episode reward: [(0, '-519.750'), (1, '-510.680')] -[2023-11-28 02:25:08,528][87424] Updated weights for policy 0, policy_version 84246 (0.0012) -[2023-11-28 02:25:08,917][87424] Updated weights for policy 0, policy_version 84256 (0.0011) -[2023-11-28 02:25:10,055][87426] Updated weights for policy 1, policy_version 84130 (0.0011) -[2023-11-28 02:25:10,444][87426] Updated weights for policy 1, policy_version 84140 (0.0012) -[2023-11-28 02:25:10,821][87426] Updated weights for policy 1, policy_version 84150 (0.0012) -[2023-11-28 02:25:11,146][87424] Updated weights for policy 0, policy_version 84266 (0.0011) -[2023-11-28 02:25:11,200][87426] Updated weights for policy 1, policy_version 84160 (0.0012) -[2023-11-28 02:25:11,539][87424] Updated weights for policy 0, policy_version 84276 (0.0012) -[2023-11-28 02:25:11,921][87424] Updated weights for policy 0, policy_version 84286 (0.0012) -[2023-11-28 02:25:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 43122688. Throughput: 0: 2726.3, 1: 2672.4. Samples: 43140636. Policy #0 lag: (min: 3.0, avg: 31.8, max: 50.0) -[2023-11-28 02:25:13,445][86177] Avg episode reward: [(0, '-520.590'), (1, '-517.520')] -[2023-11-28 02:25:13,522][87426] Updated weights for policy 1, policy_version 84170 (0.0008) -[2023-11-28 02:25:13,897][87426] Updated weights for policy 1, policy_version 84180 (0.0007) -[2023-11-28 02:25:14,280][87426] Updated weights for policy 1, policy_version 84190 (0.0009) -[2023-11-28 02:25:14,372][87424] Updated weights for policy 0, policy_version 84296 (0.0008) -[2023-11-28 02:25:14,745][87424] Updated weights for policy 0, policy_version 84306 (0.0008) -[2023-11-28 02:25:15,128][87424] Updated weights for policy 0, policy_version 84316 (0.0008) -[2023-11-28 02:25:16,508][87426] Updated weights for policy 1, policy_version 84200 (0.0009) -[2023-11-28 02:25:16,894][87426] Updated weights for policy 1, policy_version 84210 (0.0008) -[2023-11-28 02:25:17,146][87424] Updated weights for policy 0, policy_version 84326 (0.0007) -[2023-11-28 02:25:17,265][87426] Updated weights for policy 1, policy_version 84220 (0.0008) -[2023-11-28 02:25:17,519][87424] Updated weights for policy 0, policy_version 84336 (0.0007) -[2023-11-28 02:25:17,904][87424] Updated weights for policy 0, policy_version 84346 (0.0007) -[2023-11-28 02:25:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43155456. Throughput: 0: 2701.3, 1: 2670.3. Samples: 43164520. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:25:18,445][86177] Avg episode reward: [(0, '-533.690'), (1, '-519.200')] -[2023-11-28 02:25:19,088][87426] Updated weights for policy 1, policy_version 84230 (0.0009) -[2023-11-28 02:25:19,456][87426] Updated weights for policy 1, policy_version 84240 (0.0009) -[2023-11-28 02:25:19,836][87426] Updated weights for policy 1, policy_version 84250 (0.0009) -[2023-11-28 02:25:20,323][87424] Updated weights for policy 0, policy_version 84356 (0.0009) -[2023-11-28 02:25:20,706][87424] Updated weights for policy 0, policy_version 84366 (0.0011) -[2023-11-28 02:25:21,084][87424] Updated weights for policy 0, policy_version 84376 (0.0012) -[2023-11-28 02:25:21,833][87426] Updated weights for policy 1, policy_version 84260 (0.0011) -[2023-11-28 02:25:22,214][87426] Updated weights for policy 1, policy_version 84270 (0.0012) -[2023-11-28 02:25:22,596][87426] Updated weights for policy 1, policy_version 84280 (0.0012) -[2023-11-28 02:25:23,254][87424] Updated weights for policy 0, policy_version 84386 (0.0012) -[2023-11-28 02:25:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 43180032. Throughput: 0: 2692.4, 1: 2691.7. Samples: 43196532. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:25:23,445][86177] Avg episode reward: [(0, '-555.610'), (1, '-518.110')] -[2023-11-28 02:25:23,638][87424] Updated weights for policy 0, policy_version 84396 (0.0010) -[2023-11-28 02:25:24,016][87424] Updated weights for policy 0, policy_version 84406 (0.0008) -[2023-11-28 02:25:24,403][87424] Updated weights for policy 0, policy_version 84416 (0.0010) -[2023-11-28 02:25:24,901][87426] Updated weights for policy 1, policy_version 84290 (0.0012) -[2023-11-28 02:25:25,290][87426] Updated weights for policy 1, policy_version 84300 (0.0012) -[2023-11-28 02:25:25,669][87426] Updated weights for policy 1, policy_version 84310 (0.0012) -[2023-11-28 02:25:26,037][87426] Updated weights for policy 1, policy_version 84320 (0.0012) -[2023-11-28 02:25:26,323][87424] Updated weights for policy 0, policy_version 84426 (0.0008) -[2023-11-28 02:25:26,705][87424] Updated weights for policy 0, policy_version 84436 (0.0009) -[2023-11-28 02:25:27,086][87424] Updated weights for policy 0, policy_version 84446 (0.0008) -[2023-11-28 02:25:28,367][87426] Updated weights for policy 1, policy_version 84330 (0.0007) -[2023-11-28 02:25:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 43204608. Throughput: 0: 2711.8, 1: 2717.7. Samples: 43221764. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:25:28,445][86177] Avg episode reward: [(0, '-591.780'), (1, '-515.530')] -[2023-11-28 02:25:28,746][87426] Updated weights for policy 1, policy_version 84340 (0.0007) -[2023-11-28 02:25:29,125][87426] Updated weights for policy 1, policy_version 84350 (0.0010) -[2023-11-28 02:25:29,234][87424] Updated weights for policy 0, policy_version 84456 (0.0010) -[2023-11-28 02:25:29,614][87424] Updated weights for policy 0, policy_version 84466 (0.0012) -[2023-11-28 02:25:30,004][87424] Updated weights for policy 0, policy_version 84476 (0.0012) -[2023-11-28 02:25:31,281][87426] Updated weights for policy 1, policy_version 84360 (0.0009) -[2023-11-28 02:25:31,666][87426] Updated weights for policy 1, policy_version 84370 (0.0010) -[2023-11-28 02:25:32,049][87426] Updated weights for policy 1, policy_version 84380 (0.0008) -[2023-11-28 02:25:32,417][87424] Updated weights for policy 0, policy_version 84486 (0.0010) -[2023-11-28 02:25:32,797][87424] Updated weights for policy 0, policy_version 84496 (0.0010) -[2023-11-28 02:25:33,181][87424] Updated weights for policy 0, policy_version 84506 (0.0011) -[2023-11-28 02:25:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43237376. Throughput: 0: 2754.5, 1: 2731.1. Samples: 43247772. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:25:33,445][86177] Avg episode reward: [(0, '-588.260'), (1, '-523.260')] -[2023-11-28 02:25:33,858][87426] Updated weights for policy 1, policy_version 84390 (0.0011) -[2023-11-28 02:25:34,233][87426] Updated weights for policy 1, policy_version 84400 (0.0011) -[2023-11-28 02:25:34,605][87426] Updated weights for policy 1, policy_version 84410 (0.0007) -[2023-11-28 02:25:35,161][87424] Updated weights for policy 0, policy_version 84516 (0.0012) -[2023-11-28 02:25:35,535][87424] Updated weights for policy 0, policy_version 84526 (0.0010) -[2023-11-28 02:25:35,914][87424] Updated weights for policy 0, policy_version 84536 (0.0007) -[2023-11-28 02:25:36,915][87426] Updated weights for policy 1, policy_version 84420 (0.0009) -[2023-11-28 02:25:37,287][87426] Updated weights for policy 1, policy_version 84430 (0.0008) -[2023-11-28 02:25:37,667][87426] Updated weights for policy 1, policy_version 84440 (0.0007) -[2023-11-28 02:25:37,812][87424] Updated weights for policy 0, policy_version 84546 (0.0008) -[2023-11-28 02:25:38,191][87424] Updated weights for policy 0, policy_version 84556 (0.0011) -[2023-11-28 02:25:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 43261952. Throughput: 0: 2752.2, 1: 2727.9. Samples: 43280580. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:25:38,445][86177] Avg episode reward: [(0, '-582.520'), (1, '-526.610')] -[2023-11-28 02:25:38,576][87424] Updated weights for policy 0, policy_version 84566 (0.0012) -[2023-11-28 02:25:38,945][87424] Updated weights for policy 0, policy_version 84576 (0.0012) -[2023-11-28 02:25:39,635][87426] Updated weights for policy 1, policy_version 84450 (0.0009) -[2023-11-28 02:25:40,017][87426] Updated weights for policy 1, policy_version 84460 (0.0012) -[2023-11-28 02:25:40,391][87426] Updated weights for policy 1, policy_version 84470 (0.0012) -[2023-11-28 02:25:40,774][87426] Updated weights for policy 1, policy_version 84480 (0.0012) -[2023-11-28 02:25:41,220][87424] Updated weights for policy 0, policy_version 84586 (0.0008) -[2023-11-28 02:25:41,598][87424] Updated weights for policy 0, policy_version 84596 (0.0008) -[2023-11-28 02:25:41,980][87424] Updated weights for policy 0, policy_version 84606 (0.0010) -[2023-11-28 02:25:43,055][87426] Updated weights for policy 1, policy_version 84490 (0.0011) -[2023-11-28 02:25:43,436][87426] Updated weights for policy 1, policy_version 84500 (0.0010) -[2023-11-28 02:25:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 43286528. Throughput: 0: 2740.0, 1: 2729.4. Samples: 43304912. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:25:43,445][86177] Avg episode reward: [(0, '-573.970'), (1, '-530.980')] -[2023-11-28 02:25:43,818][87426] Updated weights for policy 1, policy_version 84510 (0.0009) -[2023-11-28 02:25:44,198][87424] Updated weights for policy 0, policy_version 84616 (0.0008) -[2023-11-28 02:25:44,582][87424] Updated weights for policy 0, policy_version 84626 (0.0007) -[2023-11-28 02:25:44,962][87424] Updated weights for policy 0, policy_version 84636 (0.0008) -[2023-11-28 02:25:45,654][87426] Updated weights for policy 1, policy_version 84520 (0.0012) -[2023-11-28 02:25:46,021][87426] Updated weights for policy 1, policy_version 84530 (0.0012) -[2023-11-28 02:25:46,410][87426] Updated weights for policy 1, policy_version 84540 (0.0012) -[2023-11-28 02:25:47,122][87424] Updated weights for policy 0, policy_version 84646 (0.0008) -[2023-11-28 02:25:47,504][87424] Updated weights for policy 0, policy_version 84656 (0.0010) -[2023-11-28 02:25:47,881][87424] Updated weights for policy 0, policy_version 84666 (0.0008) -[2023-11-28 02:25:48,223][87426] Updated weights for policy 1, policy_version 84550 (0.0009) -[2023-11-28 02:25:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43319296. Throughput: 0: 2733.1, 1: 2736.3. Samples: 43329512. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:25:48,445][86177] Avg episode reward: [(0, '-537.330'), (1, '-585.900')] -[2023-11-28 02:25:48,610][87426] Updated weights for policy 1, policy_version 84560 (0.0007) -[2023-11-28 02:25:48,992][87426] Updated weights for policy 1, policy_version 84570 (0.0009) -[2023-11-28 02:25:49,978][87424] Updated weights for policy 0, policy_version 84676 (0.0011) -[2023-11-28 02:25:50,350][87424] Updated weights for policy 0, policy_version 84686 (0.0012) -[2023-11-28 02:25:50,730][87424] Updated weights for policy 0, policy_version 84696 (0.0010) -[2023-11-28 02:25:51,087][87426] Updated weights for policy 1, policy_version 84580 (0.0011) -[2023-11-28 02:25:51,457][87426] Updated weights for policy 1, policy_version 84590 (0.0012) -[2023-11-28 02:25:51,833][87426] Updated weights for policy 1, policy_version 84600 (0.0011) -[2023-11-28 02:25:53,088][87424] Updated weights for policy 0, policy_version 84706 (0.0008) -[2023-11-28 02:25:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 43343872. Throughput: 0: 2718.3, 1: 2769.3. Samples: 43363188. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:25:53,445][86177] Avg episode reward: [(0, '-543.740'), (1, '-569.220')] -[2023-11-28 02:25:53,466][87424] Updated weights for policy 0, policy_version 84716 (0.0012) -[2023-11-28 02:25:53,725][87426] Updated weights for policy 1, policy_version 84610 (0.0010) -[2023-11-28 02:25:53,846][87424] Updated weights for policy 0, policy_version 84726 (0.0012) -[2023-11-28 02:25:54,108][87426] Updated weights for policy 1, policy_version 84620 (0.0010) -[2023-11-28 02:25:54,231][87424] Updated weights for policy 0, policy_version 84736 (0.0011) -[2023-11-28 02:25:54,487][87426] Updated weights for policy 1, policy_version 84630 (0.0008) -[2023-11-28 02:25:54,873][87426] Updated weights for policy 1, policy_version 84640 (0.0008) -[2023-11-28 02:25:56,196][87424] Updated weights for policy 0, policy_version 84746 (0.0012) -[2023-11-28 02:25:56,582][87424] Updated weights for policy 0, policy_version 84756 (0.0011) -[2023-11-28 02:25:56,954][87424] Updated weights for policy 0, policy_version 84766 (0.0012) -[2023-11-28 02:25:56,990][87426] Updated weights for policy 1, policy_version 84650 (0.0011) -[2023-11-28 02:25:57,365][87426] Updated weights for policy 1, policy_version 84660 (0.0012) -[2023-11-28 02:25:57,732][87426] Updated weights for policy 1, policy_version 84670 (0.0012) -[2023-11-28 02:25:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 43376640. Throughput: 0: 2718.4, 1: 2778.3. Samples: 43387988. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:25:58,445][86177] Avg episode reward: [(0, '-541.260'), (1, '-565.280')] -[2023-11-28 02:25:58,695][87424] Updated weights for policy 0, policy_version 84776 (0.0012) -[2023-11-28 02:25:59,079][87424] Updated weights for policy 0, policy_version 84786 (0.0012) -[2023-11-28 02:25:59,465][87424] Updated weights for policy 0, policy_version 84796 (0.0012) -[2023-11-28 02:26:00,175][87426] Updated weights for policy 1, policy_version 84680 (0.0012) -[2023-11-28 02:26:00,558][87426] Updated weights for policy 1, policy_version 84690 (0.0011) -[2023-11-28 02:26:00,942][87426] Updated weights for policy 1, policy_version 84700 (0.0010) -[2023-11-28 02:26:01,789][87424] Updated weights for policy 0, policy_version 84806 (0.0011) -[2023-11-28 02:26:02,192][87424] Updated weights for policy 0, policy_version 84816 (0.0008) -[2023-11-28 02:26:02,568][87424] Updated weights for policy 0, policy_version 84826 (0.0008) -[2023-11-28 02:26:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43401216. Throughput: 0: 2771.1, 1: 2759.7. Samples: 43413408. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:26:03,445][86177] Avg episode reward: [(0, '-517.520'), (1, '-567.530')] -[2023-11-28 02:26:03,497][87426] Updated weights for policy 1, policy_version 84710 (0.0010) -[2023-11-28 02:26:03,875][87426] Updated weights for policy 1, policy_version 84720 (0.0012) -[2023-11-28 02:26:04,259][87426] Updated weights for policy 1, policy_version 84730 (0.0012) -[2023-11-28 02:26:04,779][87424] Updated weights for policy 0, policy_version 84836 (0.0009) -[2023-11-28 02:26:05,165][87424] Updated weights for policy 0, policy_version 84846 (0.0011) -[2023-11-28 02:26:05,550][87424] Updated weights for policy 0, policy_version 84856 (0.0010) -[2023-11-28 02:26:06,556][87426] Updated weights for policy 1, policy_version 84740 (0.0012) -[2023-11-28 02:26:06,943][87426] Updated weights for policy 1, policy_version 84750 (0.0012) -[2023-11-28 02:26:07,309][87426] Updated weights for policy 1, policy_version 84760 (0.0012) -[2023-11-28 02:26:08,040][87424] Updated weights for policy 0, policy_version 84866 (0.0010) -[2023-11-28 02:26:08,422][87424] Updated weights for policy 0, policy_version 84876 (0.0009) -[2023-11-28 02:26:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 43425792. Throughput: 0: 2791.1, 1: 2743.2. Samples: 43445576. Policy #0 lag: (min: 19.0, avg: 47.2, max: 83.0) -[2023-11-28 02:26:08,445][86177] Avg episode reward: [(0, '-546.780'), (1, '-522.170')] -[2023-11-28 02:26:08,812][87424] Updated weights for policy 0, policy_version 84886 (0.0012) -[2023-11-28 02:26:09,200][87424] Updated weights for policy 0, policy_version 84896 (0.0012) -[2023-11-28 02:26:09,303][87426] Updated weights for policy 1, policy_version 84770 (0.0011) -[2023-11-28 02:26:09,682][87426] Updated weights for policy 1, policy_version 84780 (0.0008) -[2023-11-28 02:26:10,061][87426] Updated weights for policy 1, policy_version 84790 (0.0011) -[2023-11-28 02:26:10,437][87426] Updated weights for policy 1, policy_version 84800 (0.0012) -[2023-11-28 02:26:11,170][87424] Updated weights for policy 0, policy_version 84906 (0.0011) -[2023-11-28 02:26:11,547][87424] Updated weights for policy 0, policy_version 84916 (0.0012) -[2023-11-28 02:26:11,933][87424] Updated weights for policy 0, policy_version 84926 (0.0011) -[2023-11-28 02:26:12,687][87426] Updated weights for policy 1, policy_version 84810 (0.0012) -[2023-11-28 02:26:13,070][87426] Updated weights for policy 1, policy_version 84820 (0.0011) -[2023-11-28 02:26:13,443][87426] Updated weights for policy 1, policy_version 84830 (0.0011) -[2023-11-28 02:26:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 43450368. Throughput: 0: 2788.3, 1: 2737.9. Samples: 43470440. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:13,445][86177] Avg episode reward: [(0, '-543.820'), (1, '-516.760')] -[2023-11-28 02:26:14,236][87424] Updated weights for policy 0, policy_version 84936 (0.0008) -[2023-11-28 02:26:14,624][87424] Updated weights for policy 0, policy_version 84946 (0.0007) -[2023-11-28 02:26:15,003][87424] Updated weights for policy 0, policy_version 84956 (0.0008) -[2023-11-28 02:26:15,444][87426] Updated weights for policy 1, policy_version 84840 (0.0012) -[2023-11-28 02:26:15,820][87426] Updated weights for policy 1, policy_version 84850 (0.0012) -[2023-11-28 02:26:16,204][87426] Updated weights for policy 1, policy_version 84860 (0.0012) -[2023-11-28 02:26:17,200][87424] Updated weights for policy 0, policy_version 84966 (0.0010) -[2023-11-28 02:26:17,592][87424] Updated weights for policy 0, policy_version 84976 (0.0012) -[2023-11-28 02:26:17,972][87424] Updated weights for policy 0, policy_version 84986 (0.0012) -[2023-11-28 02:26:18,005][87426] Updated weights for policy 1, policy_version 84870 (0.0011) -[2023-11-28 02:26:18,386][87426] Updated weights for policy 1, policy_version 84880 (0.0008) -[2023-11-28 02:26:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43483136. Throughput: 0: 2772.7, 1: 2737.4. Samples: 43495728. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:18,445][86177] Avg episode reward: [(0, '-556.350'), (1, '-546.710')] -[2023-11-28 02:26:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000084992_21757952.pth... -[2023-11-28 02:26:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000082464_21110784.pth -[2023-11-28 02:26:18,762][87426] Updated weights for policy 1, policy_version 84890 (0.0007) -[2023-11-28 02:26:18,990][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000084896_21733376.pth... -[2023-11-28 02:26:19,027][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000082336_21078016.pth -[2023-11-28 02:26:19,843][87424] Updated weights for policy 0, policy_version 84996 (0.0012) -[2023-11-28 02:26:20,222][87424] Updated weights for policy 0, policy_version 85006 (0.0012) -[2023-11-28 02:26:20,598][87424] Updated weights for policy 0, policy_version 85016 (0.0012) -[2023-11-28 02:26:21,098][87426] Updated weights for policy 1, policy_version 84900 (0.0009) -[2023-11-28 02:26:21,464][87426] Updated weights for policy 1, policy_version 84910 (0.0007) -[2023-11-28 02:26:21,846][87426] Updated weights for policy 1, policy_version 84920 (0.0011) -[2023-11-28 02:26:23,000][87424] Updated weights for policy 0, policy_version 85026 (0.0012) -[2023-11-28 02:26:23,376][87424] Updated weights for policy 0, policy_version 85036 (0.0012) -[2023-11-28 02:26:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 43507712. Throughput: 0: 2761.0, 1: 2735.6. Samples: 43527928. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:23,445][86177] Avg episode reward: [(0, '-595.320'), (1, '-547.550')] -[2023-11-28 02:26:23,760][87424] Updated weights for policy 0, policy_version 85046 (0.0012) -[2023-11-28 02:26:23,923][87426] Updated weights for policy 1, policy_version 84930 (0.0012) -[2023-11-28 02:26:24,142][87424] Updated weights for policy 0, policy_version 85056 (0.0011) -[2023-11-28 02:26:24,304][87426] Updated weights for policy 1, policy_version 84940 (0.0012) -[2023-11-28 02:26:24,678][87426] Updated weights for policy 1, policy_version 84950 (0.0011) -[2023-11-28 02:26:25,055][87426] Updated weights for policy 1, policy_version 84960 (0.0007) -[2023-11-28 02:26:26,030][87424] Updated weights for policy 0, policy_version 85066 (0.0012) -[2023-11-28 02:26:26,407][87424] Updated weights for policy 0, policy_version 85076 (0.0008) -[2023-11-28 02:26:26,793][87424] Updated weights for policy 0, policy_version 85086 (0.0007) -[2023-11-28 02:26:27,409][87426] Updated weights for policy 1, policy_version 84970 (0.0010) -[2023-11-28 02:26:27,781][87426] Updated weights for policy 1, policy_version 84980 (0.0009) -[2023-11-28 02:26:28,162][87426] Updated weights for policy 1, policy_version 84990 (0.0007) -[2023-11-28 02:26:28,408][87424] Updated weights for policy 0, policy_version 85096 (0.0009) -[2023-11-28 02:26:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 43540480. Throughput: 0: 2759.1, 1: 2748.9. Samples: 43552772. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:28,445][86177] Avg episode reward: [(0, '-573.820'), (1, '-565.100')] -[2023-11-28 02:26:28,796][87424] Updated weights for policy 0, policy_version 85106 (0.0010) -[2023-11-28 02:26:29,183][87424] Updated weights for policy 0, policy_version 85116 (0.0011) -[2023-11-28 02:26:30,271][87426] Updated weights for policy 1, policy_version 85000 (0.0010) -[2023-11-28 02:26:30,644][87426] Updated weights for policy 1, policy_version 85010 (0.0010) -[2023-11-28 02:26:31,031][87426] Updated weights for policy 1, policy_version 85020 (0.0011) -[2023-11-28 02:26:31,123][87424] Updated weights for policy 0, policy_version 85126 (0.0011) -[2023-11-28 02:26:31,511][87424] Updated weights for policy 0, policy_version 85136 (0.0011) -[2023-11-28 02:26:31,887][87424] Updated weights for policy 0, policy_version 85146 (0.0012) -[2023-11-28 02:26:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43565056. Throughput: 0: 2773.1, 1: 2754.3. Samples: 43578244. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:33,445][86177] Avg episode reward: [(0, '-565.500'), (1, '-540.550')] -[2023-11-28 02:26:33,497][87426] Updated weights for policy 1, policy_version 85030 (0.0011) -[2023-11-28 02:26:33,886][87426] Updated weights for policy 1, policy_version 85040 (0.0007) -[2023-11-28 02:26:34,193][87424] Updated weights for policy 0, policy_version 85156 (0.0010) -[2023-11-28 02:26:34,254][87426] Updated weights for policy 1, policy_version 85050 (0.0008) -[2023-11-28 02:26:34,579][87424] Updated weights for policy 0, policy_version 85166 (0.0008) -[2023-11-28 02:26:34,957][87424] Updated weights for policy 0, policy_version 85176 (0.0008) -[2023-11-28 02:26:36,252][87426] Updated weights for policy 1, policy_version 85060 (0.0010) -[2023-11-28 02:26:36,634][87426] Updated weights for policy 1, policy_version 85070 (0.0009) -[2023-11-28 02:26:37,011][87426] Updated weights for policy 1, policy_version 85080 (0.0012) -[2023-11-28 02:26:37,159][87424] Updated weights for policy 0, policy_version 85186 (0.0008) -[2023-11-28 02:26:37,550][87424] Updated weights for policy 0, policy_version 85196 (0.0011) -[2023-11-28 02:26:37,927][87424] Updated weights for policy 0, policy_version 85206 (0.0012) -[2023-11-28 02:26:38,312][87424] Updated weights for policy 0, policy_version 85216 (0.0012) -[2023-11-28 02:26:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 43597824. Throughput: 0: 2779.7, 1: 2722.9. Samples: 43610804. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:38,445][86177] Avg episode reward: [(0, '-635.670'), (1, '-537.900')] -[2023-11-28 02:26:38,869][87426] Updated weights for policy 1, policy_version 85090 (0.0011) -[2023-11-28 02:26:39,241][87426] Updated weights for policy 1, policy_version 85100 (0.0007) -[2023-11-28 02:26:39,623][87426] Updated weights for policy 1, policy_version 85110 (0.0007) -[2023-11-28 02:26:39,997][87426] Updated weights for policy 1, policy_version 85120 (0.0014) -[2023-11-28 02:26:40,650][87424] Updated weights for policy 0, policy_version 85226 (0.0012) -[2023-11-28 02:26:41,033][87424] Updated weights for policy 0, policy_version 85236 (0.0012) -[2023-11-28 02:26:41,418][87424] Updated weights for policy 0, policy_version 85246 (0.0012) -[2023-11-28 02:26:42,172][87426] Updated weights for policy 1, policy_version 85130 (0.0009) -[2023-11-28 02:26:42,539][87426] Updated weights for policy 1, policy_version 85140 (0.0008) -[2023-11-28 02:26:42,927][87426] Updated weights for policy 1, policy_version 85150 (0.0008) -[2023-11-28 02:26:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 43622400. Throughput: 0: 2764.7, 1: 2729.1. Samples: 43635208. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:43,445][86177] Avg episode reward: [(0, '-597.310'), (1, '-521.520')] -[2023-11-28 02:26:43,713][87424] Updated weights for policy 0, policy_version 85256 (0.0009) -[2023-11-28 02:26:44,097][87424] Updated weights for policy 0, policy_version 85266 (0.0008) -[2023-11-28 02:26:44,474][87424] Updated weights for policy 0, policy_version 85276 (0.0007) -[2023-11-28 02:26:45,049][87426] Updated weights for policy 1, policy_version 85160 (0.0007) -[2023-11-28 02:26:45,424][87426] Updated weights for policy 1, policy_version 85170 (0.0008) -[2023-11-28 02:26:45,800][87426] Updated weights for policy 1, policy_version 85180 (0.0008) -[2023-11-28 02:26:46,305][87424] Updated weights for policy 0, policy_version 85286 (0.0009) -[2023-11-28 02:26:46,684][87424] Updated weights for policy 0, policy_version 85296 (0.0012) -[2023-11-28 02:26:47,063][87424] Updated weights for policy 0, policy_version 85306 (0.0010) -[2023-11-28 02:26:47,729][87426] Updated weights for policy 1, policy_version 85190 (0.0007) -[2023-11-28 02:26:48,116][87426] Updated weights for policy 1, policy_version 85200 (0.0007) -[2023-11-28 02:26:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43646976. Throughput: 0: 2706.3, 1: 2744.1. Samples: 43658676. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:48,445][86177] Avg episode reward: [(0, '-590.400'), (1, '-518.340')] -[2023-11-28 02:26:48,505][87426] Updated weights for policy 1, policy_version 85210 (0.0007) -[2023-11-28 02:26:49,558][87424] Updated weights for policy 0, policy_version 85316 (0.0009) -[2023-11-28 02:26:49,932][87424] Updated weights for policy 0, policy_version 85326 (0.0010) -[2023-11-28 02:26:50,292][87426] Updated weights for policy 1, policy_version 85220 (0.0008) -[2023-11-28 02:26:50,313][87424] Updated weights for policy 0, policy_version 85336 (0.0011) -[2023-11-28 02:26:50,664][87426] Updated weights for policy 1, policy_version 85230 (0.0008) -[2023-11-28 02:26:51,047][87426] Updated weights for policy 1, policy_version 85240 (0.0008) -[2023-11-28 02:26:52,635][87424] Updated weights for policy 0, policy_version 85346 (0.0012) -[2023-11-28 02:26:53,014][87424] Updated weights for policy 0, policy_version 85356 (0.0010) -[2023-11-28 02:26:53,399][87424] Updated weights for policy 0, policy_version 85366 (0.0012) -[2023-11-28 02:26:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 43671552. Throughput: 0: 2684.3, 1: 2764.6. Samples: 43690776. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:53,445][86177] Avg episode reward: [(0, '-626.830'), (1, '-517.320')] -[2023-11-28 02:26:53,551][87426] Updated weights for policy 1, policy_version 85250 (0.0009) -[2023-11-28 02:26:53,778][87424] Updated weights for policy 0, policy_version 85376 (0.0011) -[2023-11-28 02:26:53,931][87426] Updated weights for policy 1, policy_version 85260 (0.0011) -[2023-11-28 02:26:54,311][87426] Updated weights for policy 1, policy_version 85270 (0.0010) -[2023-11-28 02:26:54,709][87426] Updated weights for policy 1, policy_version 85280 (0.0008) -[2023-11-28 02:26:56,198][87424] Updated weights for policy 0, policy_version 85386 (0.0008) -[2023-11-28 02:26:56,590][87424] Updated weights for policy 0, policy_version 85396 (0.0008) -[2023-11-28 02:26:56,981][87424] Updated weights for policy 0, policy_version 85406 (0.0008) -[2023-11-28 02:26:57,304][87426] Updated weights for policy 1, policy_version 85290 (0.0009) -[2023-11-28 02:26:57,692][87426] Updated weights for policy 1, policy_version 85300 (0.0008) -[2023-11-28 02:26:58,075][87426] Updated weights for policy 1, policy_version 85310 (0.0008) -[2023-11-28 02:26:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 43704320. Throughput: 0: 2667.1, 1: 2743.8. Samples: 43713932. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:26:58,445][86177] Avg episode reward: [(0, '-550.370'), (1, '-525.310')] -[2023-11-28 02:26:59,322][87424] Updated weights for policy 0, policy_version 85416 (0.0012) -[2023-11-28 02:26:59,701][87424] Updated weights for policy 0, policy_version 85426 (0.0012) -[2023-11-28 02:27:00,086][87424] Updated weights for policy 0, policy_version 85436 (0.0011) -[2023-11-28 02:27:00,238][87426] Updated weights for policy 1, policy_version 85320 (0.0011) -[2023-11-28 02:27:00,607][87426] Updated weights for policy 1, policy_version 85330 (0.0011) -[2023-11-28 02:27:01,004][87426] Updated weights for policy 1, policy_version 85340 (0.0010) -[2023-11-28 02:27:02,598][87424] Updated weights for policy 0, policy_version 85446 (0.0012) -[2023-11-28 02:27:02,986][87424] Updated weights for policy 0, policy_version 85456 (0.0011) -[2023-11-28 02:27:03,141][87426] Updated weights for policy 1, policy_version 85350 (0.0009) -[2023-11-28 02:27:03,367][87424] Updated weights for policy 0, policy_version 85466 (0.0011) -[2023-11-28 02:27:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 43720704. Throughput: 0: 2667.7, 1: 2743.2. Samples: 43739220. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:27:03,445][86177] Avg episode reward: [(0, '-545.480'), (1, '-524.680')] -[2023-11-28 02:27:03,524][87426] Updated weights for policy 1, policy_version 85360 (0.0012) -[2023-11-28 02:27:03,916][87426] Updated weights for policy 1, policy_version 85370 (0.0012) -[2023-11-28 02:27:05,266][87424] Updated weights for policy 0, policy_version 85476 (0.0011) -[2023-11-28 02:27:05,650][87424] Updated weights for policy 0, policy_version 85486 (0.0012) -[2023-11-28 02:27:05,992][87426] Updated weights for policy 1, policy_version 85380 (0.0010) -[2023-11-28 02:27:06,028][87424] Updated weights for policy 0, policy_version 85496 (0.0012) -[2023-11-28 02:27:06,373][87426] Updated weights for policy 1, policy_version 85390 (0.0007) -[2023-11-28 02:27:06,753][87426] Updated weights for policy 1, policy_version 85400 (0.0008) -[2023-11-28 02:27:07,844][87424] Updated weights for policy 0, policy_version 85506 (0.0011) -[2023-11-28 02:27:08,226][87424] Updated weights for policy 0, policy_version 85516 (0.0011) -[2023-11-28 02:27:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 43753472. Throughput: 0: 2686.4, 1: 2752.2. Samples: 43772664. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:08,445][86177] Avg episode reward: [(0, '-507.840'), (1, '-526.220')] -[2023-11-28 02:27:08,611][87424] Updated weights for policy 0, policy_version 85526 (0.0009) -[2023-11-28 02:27:09,002][87424] Updated weights for policy 0, policy_version 85536 (0.0010) -[2023-11-28 02:27:09,085][87426] Updated weights for policy 1, policy_version 85410 (0.0008) -[2023-11-28 02:27:09,464][87426] Updated weights for policy 1, policy_version 85420 (0.0007) -[2023-11-28 02:27:09,844][87426] Updated weights for policy 1, policy_version 85430 (0.0008) -[2023-11-28 02:27:10,228][87426] Updated weights for policy 1, policy_version 85440 (0.0010) -[2023-11-28 02:27:11,375][87424] Updated weights for policy 0, policy_version 85546 (0.0011) -[2023-11-28 02:27:11,755][87424] Updated weights for policy 0, policy_version 85556 (0.0012) -[2023-11-28 02:27:12,143][87424] Updated weights for policy 0, policy_version 85566 (0.0012) -[2023-11-28 02:27:12,595][87426] Updated weights for policy 1, policy_version 85450 (0.0011) -[2023-11-28 02:27:12,977][87426] Updated weights for policy 1, policy_version 85460 (0.0012) -[2023-11-28 02:27:13,363][87426] Updated weights for policy 1, policy_version 85470 (0.0012) -[2023-11-28 02:27:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 43786240. Throughput: 0: 2682.1, 1: 2716.0. Samples: 43795688. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:13,445][86177] Avg episode reward: [(0, '-515.790'), (1, '-527.530')] -[2023-11-28 02:27:14,231][87424] Updated weights for policy 0, policy_version 85576 (0.0012) -[2023-11-28 02:27:14,599][87424] Updated weights for policy 0, policy_version 85586 (0.0011) -[2023-11-28 02:27:14,978][87424] Updated weights for policy 0, policy_version 85596 (0.0012) -[2023-11-28 02:27:15,898][87426] Updated weights for policy 1, policy_version 85480 (0.0012) -[2023-11-28 02:27:16,267][87426] Updated weights for policy 1, policy_version 85490 (0.0011) -[2023-11-28 02:27:16,646][87426] Updated weights for policy 1, policy_version 85500 (0.0012) -[2023-11-28 02:27:16,897][87424] Updated weights for policy 0, policy_version 85606 (0.0009) -[2023-11-28 02:27:17,281][87424] Updated weights for policy 0, policy_version 85616 (0.0008) -[2023-11-28 02:27:17,664][87424] Updated weights for policy 0, policy_version 85626 (0.0009) -[2023-11-28 02:27:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43810816. Throughput: 0: 2692.3, 1: 2706.5. Samples: 43821188. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:18,445][86177] Avg episode reward: [(0, '-510.130'), (1, '-520.530')] -[2023-11-28 02:27:18,577][87426] Updated weights for policy 1, policy_version 85510 (0.0010) -[2023-11-28 02:27:18,960][87426] Updated weights for policy 1, policy_version 85520 (0.0008) -[2023-11-28 02:27:19,334][87426] Updated weights for policy 1, policy_version 85530 (0.0007) -[2023-11-28 02:27:19,862][87424] Updated weights for policy 0, policy_version 85636 (0.0008) -[2023-11-28 02:27:20,247][87424] Updated weights for policy 0, policy_version 85646 (0.0008) -[2023-11-28 02:27:20,635][87424] Updated weights for policy 0, policy_version 85656 (0.0010) -[2023-11-28 02:27:21,539][87426] Updated weights for policy 1, policy_version 85540 (0.0009) -[2023-11-28 02:27:21,914][87426] Updated weights for policy 1, policy_version 85550 (0.0012) -[2023-11-28 02:27:22,297][87426] Updated weights for policy 1, policy_version 85560 (0.0012) -[2023-11-28 02:27:22,577][87424] Updated weights for policy 0, policy_version 85666 (0.0010) -[2023-11-28 02:27:22,959][87424] Updated weights for policy 0, policy_version 85676 (0.0008) -[2023-11-28 02:27:23,350][87424] Updated weights for policy 0, policy_version 85686 (0.0010) -[2023-11-28 02:27:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 43835392. Throughput: 0: 2694.4, 1: 2706.9. Samples: 43853864. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:23,445][86177] Avg episode reward: [(0, '-511.420'), (1, '-551.480')] -[2023-11-28 02:27:23,727][87424] Updated weights for policy 0, policy_version 85696 (0.0011) -[2023-11-28 02:27:24,778][87426] Updated weights for policy 1, policy_version 85570 (0.0012) -[2023-11-28 02:27:25,153][87426] Updated weights for policy 1, policy_version 85580 (0.0009) -[2023-11-28 02:27:25,471][87424] Updated weights for policy 0, policy_version 85706 (0.0011) -[2023-11-28 02:27:25,532][87426] Updated weights for policy 1, policy_version 85590 (0.0007) -[2023-11-28 02:27:25,855][87424] Updated weights for policy 0, policy_version 85716 (0.0008) -[2023-11-28 02:27:25,915][87426] Updated weights for policy 1, policy_version 85600 (0.0007) -[2023-11-28 02:27:26,254][87424] Updated weights for policy 0, policy_version 85726 (0.0010) -[2023-11-28 02:27:27,550][87426] Updated weights for policy 1, policy_version 85610 (0.0010) -[2023-11-28 02:27:27,930][87426] Updated weights for policy 1, policy_version 85620 (0.0008) -[2023-11-28 02:27:28,317][87426] Updated weights for policy 1, policy_version 85630 (0.0008) -[2023-11-28 02:27:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 43868160. Throughput: 0: 2729.5, 1: 2697.7. Samples: 43879432. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:28,445][86177] Avg episode reward: [(0, '-522.130'), (1, '-610.310')] -[2023-11-28 02:27:28,684][87424] Updated weights for policy 0, policy_version 85736 (0.0012) -[2023-11-28 02:27:29,079][87424] Updated weights for policy 0, policy_version 85746 (0.0011) -[2023-11-28 02:27:29,459][87424] Updated weights for policy 0, policy_version 85756 (0.0012) -[2023-11-28 02:27:30,710][87426] Updated weights for policy 1, policy_version 85640 (0.0008) -[2023-11-28 02:27:31,095][87426] Updated weights for policy 1, policy_version 85650 (0.0008) -[2023-11-28 02:27:31,215][87424] Updated weights for policy 0, policy_version 85766 (0.0011) -[2023-11-28 02:27:31,472][87426] Updated weights for policy 1, policy_version 85660 (0.0007) -[2023-11-28 02:27:31,592][87424] Updated weights for policy 0, policy_version 85776 (0.0012) -[2023-11-28 02:27:31,981][87424] Updated weights for policy 0, policy_version 85786 (0.0010) -[2023-11-28 02:27:33,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43892736. Throughput: 0: 2767.3, 1: 2686.6. Samples: 43904104. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:33,446][86177] Avg episode reward: [(0, '-514.780'), (1, '-607.200')] -[2023-11-28 02:27:33,734][87426] Updated weights for policy 1, policy_version 85670 (0.0008) -[2023-11-28 02:27:34,093][87424] Updated weights for policy 0, policy_version 85796 (0.0010) -[2023-11-28 02:27:34,110][87426] Updated weights for policy 1, policy_version 85680 (0.0007) -[2023-11-28 02:27:34,476][87424] Updated weights for policy 0, policy_version 85806 (0.0012) -[2023-11-28 02:27:34,483][87426] Updated weights for policy 1, policy_version 85690 (0.0007) -[2023-11-28 02:27:34,868][87424] Updated weights for policy 0, policy_version 85816 (0.0011) -[2023-11-28 02:27:36,808][87424] Updated weights for policy 0, policy_version 85826 (0.0008) -[2023-11-28 02:27:36,943][87426] Updated weights for policy 1, policy_version 85700 (0.0010) -[2023-11-28 02:27:37,193][87424] Updated weights for policy 0, policy_version 85836 (0.0012) -[2023-11-28 02:27:37,323][87426] Updated weights for policy 1, policy_version 85710 (0.0012) -[2023-11-28 02:27:37,565][87424] Updated weights for policy 0, policy_version 85846 (0.0009) -[2023-11-28 02:27:37,698][87426] Updated weights for policy 1, policy_version 85720 (0.0011) -[2023-11-28 02:27:37,951][87424] Updated weights for policy 0, policy_version 85856 (0.0009) -[2023-11-28 02:27:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43925504. Throughput: 0: 2777.0, 1: 2673.5. Samples: 43936048. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:38,446][86177] Avg episode reward: [(0, '-508.810'), (1, '-607.400')] -[2023-11-28 02:27:40,263][87426] Updated weights for policy 1, policy_version 85730 (0.0010) -[2023-11-28 02:27:40,462][87424] Updated weights for policy 0, policy_version 85866 (0.0011) -[2023-11-28 02:27:40,646][87426] Updated weights for policy 1, policy_version 85740 (0.0011) -[2023-11-28 02:27:40,854][87424] Updated weights for policy 0, policy_version 85876 (0.0008) -[2023-11-28 02:27:41,024][87426] Updated weights for policy 1, policy_version 85750 (0.0011) -[2023-11-28 02:27:41,227][87424] Updated weights for policy 0, policy_version 85886 (0.0009) -[2023-11-28 02:27:41,401][87426] Updated weights for policy 1, policy_version 85760 (0.0012) -[2023-11-28 02:27:43,339][87424] Updated weights for policy 0, policy_version 85896 (0.0009) -[2023-11-28 02:27:43,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 43941888. Throughput: 0: 2773.8, 1: 2687.7. Samples: 43959700. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:43,445][86177] Avg episode reward: [(0, '-506.490'), (1, '-575.140')] -[2023-11-28 02:27:43,628][87426] Updated weights for policy 1, policy_version 85770 (0.0009) -[2023-11-28 02:27:43,723][87424] Updated weights for policy 0, policy_version 85906 (0.0012) -[2023-11-28 02:27:44,011][87426] Updated weights for policy 1, policy_version 85780 (0.0007) -[2023-11-28 02:27:44,105][87424] Updated weights for policy 0, policy_version 85916 (0.0011) -[2023-11-28 02:27:44,391][87426] Updated weights for policy 1, policy_version 85790 (0.0007) -[2023-11-28 02:27:46,610][87424] Updated weights for policy 0, policy_version 85926 (0.0011) -[2023-11-28 02:27:46,636][87426] Updated weights for policy 1, policy_version 85800 (0.0007) -[2023-11-28 02:27:46,996][87424] Updated weights for policy 0, policy_version 85936 (0.0011) -[2023-11-28 02:27:47,018][87426] Updated weights for policy 1, policy_version 85810 (0.0007) -[2023-11-28 02:27:47,375][87424] Updated weights for policy 0, policy_version 85946 (0.0012) -[2023-11-28 02:27:47,396][87426] Updated weights for policy 1, policy_version 85820 (0.0008) -[2023-11-28 02:27:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 43974656. Throughput: 0: 2765.3, 1: 2676.6. Samples: 43984108. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:48,445][86177] Avg episode reward: [(0, '-502.810'), (1, '-508.770')] -[2023-11-28 02:27:49,146][87426] Updated weights for policy 1, policy_version 85830 (0.0011) -[2023-11-28 02:27:49,382][87424] Updated weights for policy 0, policy_version 85956 (0.0010) -[2023-11-28 02:27:49,522][87426] Updated weights for policy 1, policy_version 85840 (0.0011) -[2023-11-28 02:27:49,767][87424] Updated weights for policy 0, policy_version 85966 (0.0010) -[2023-11-28 02:27:49,902][87426] Updated weights for policy 1, policy_version 85850 (0.0012) -[2023-11-28 02:27:50,165][87424] Updated weights for policy 0, policy_version 85976 (0.0011) -[2023-11-28 02:27:52,051][87426] Updated weights for policy 1, policy_version 85860 (0.0010) -[2023-11-28 02:27:52,426][87426] Updated weights for policy 1, policy_version 85870 (0.0008) -[2023-11-28 02:27:52,674][87424] Updated weights for policy 0, policy_version 85986 (0.0011) -[2023-11-28 02:27:52,806][87426] Updated weights for policy 1, policy_version 85880 (0.0011) -[2023-11-28 02:27:53,054][87424] Updated weights for policy 0, policy_version 85996 (0.0009) -[2023-11-28 02:27:53,437][87424] Updated weights for policy 0, policy_version 86006 (0.0009) -[2023-11-28 02:27:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 43999232. Throughput: 0: 2745.5, 1: 2677.4. Samples: 44016696. Policy #0 lag: (min: 30.0, avg: 47.2, max: 62.0) -[2023-11-28 02:27:53,445][86177] Avg episode reward: [(0, '-503.550'), (1, '-508.060')] -[2023-11-28 02:27:53,821][87424] Updated weights for policy 0, policy_version 86016 (0.0010) -[2023-11-28 02:27:54,694][87426] Updated weights for policy 1, policy_version 85890 (0.0012) -[2023-11-28 02:27:55,076][87426] Updated weights for policy 1, policy_version 85900 (0.0011) -[2023-11-28 02:27:55,447][87426] Updated weights for policy 1, policy_version 85910 (0.0012) -[2023-11-28 02:27:55,825][87426] Updated weights for policy 1, policy_version 85920 (0.0008) -[2023-11-28 02:27:56,384][87424] Updated weights for policy 0, policy_version 86026 (0.0012) -[2023-11-28 02:27:56,764][87424] Updated weights for policy 0, policy_version 86036 (0.0012) -[2023-11-28 02:27:57,148][87424] Updated weights for policy 0, policy_version 86046 (0.0012) -[2023-11-28 02:27:57,518][87426] Updated weights for policy 1, policy_version 85930 (0.0007) -[2023-11-28 02:27:57,902][87426] Updated weights for policy 1, policy_version 85940 (0.0007) -[2023-11-28 02:27:58,277][87426] Updated weights for policy 1, policy_version 85950 (0.0007) -[2023-11-28 02:27:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 44032000. Throughput: 0: 2737.5, 1: 2708.3. Samples: 44040748. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:27:58,445][86177] Avg episode reward: [(0, '-503.460'), (1, '-533.670')] -[2023-11-28 02:27:59,405][87424] Updated weights for policy 0, policy_version 86056 (0.0011) -[2023-11-28 02:27:59,789][87424] Updated weights for policy 0, policy_version 86066 (0.0012) -[2023-11-28 02:28:00,168][87424] Updated weights for policy 0, policy_version 86076 (0.0012) -[2023-11-28 02:28:00,745][87426] Updated weights for policy 1, policy_version 85960 (0.0011) -[2023-11-28 02:28:01,132][87426] Updated weights for policy 1, policy_version 85970 (0.0012) -[2023-11-28 02:28:01,508][87426] Updated weights for policy 1, policy_version 85980 (0.0012) -[2023-11-28 02:28:02,472][87424] Updated weights for policy 0, policy_version 86086 (0.0012) -[2023-11-28 02:28:02,857][87424] Updated weights for policy 0, policy_version 86096 (0.0012) -[2023-11-28 02:28:03,233][87424] Updated weights for policy 0, policy_version 86106 (0.0012) -[2023-11-28 02:28:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 44048384. Throughput: 0: 2706.9, 1: 2699.7. Samples: 44064484. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:03,445][86177] Avg episode reward: [(0, '-508.180'), (1, '-547.260')] -[2023-11-28 02:28:03,564][87426] Updated weights for policy 1, policy_version 85990 (0.0012) -[2023-11-28 02:28:03,941][87426] Updated weights for policy 1, policy_version 86000 (0.0012) -[2023-11-28 02:28:04,310][87426] Updated weights for policy 1, policy_version 86010 (0.0012) -[2023-11-28 02:28:05,131][87424] Updated weights for policy 0, policy_version 86116 (0.0012) -[2023-11-28 02:28:05,514][87424] Updated weights for policy 0, policy_version 86126 (0.0011) -[2023-11-28 02:28:05,902][87424] Updated weights for policy 0, policy_version 86136 (0.0011) -[2023-11-28 02:28:06,771][87426] Updated weights for policy 1, policy_version 86020 (0.0012) -[2023-11-28 02:28:07,141][87426] Updated weights for policy 1, policy_version 86030 (0.0012) -[2023-11-28 02:28:07,515][87426] Updated weights for policy 1, policy_version 86040 (0.0012) -[2023-11-28 02:28:07,939][87424] Updated weights for policy 0, policy_version 86146 (0.0011) -[2023-11-28 02:28:08,328][87424] Updated weights for policy 0, policy_version 86156 (0.0012) -[2023-11-28 02:28:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 44081152. Throughput: 0: 2729.1, 1: 2686.7. Samples: 44097576. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:08,446][86177] Avg episode reward: [(0, '-545.770'), (1, '-550.870')] -[2023-11-28 02:28:08,706][87424] Updated weights for policy 0, policy_version 86166 (0.0012) -[2023-11-28 02:28:09,081][87424] Updated weights for policy 0, policy_version 86176 (0.0012) -[2023-11-28 02:28:09,432][87426] Updated weights for policy 1, policy_version 86050 (0.0011) -[2023-11-28 02:28:09,816][87426] Updated weights for policy 1, policy_version 86060 (0.0008) -[2023-11-28 02:28:10,191][87426] Updated weights for policy 1, policy_version 86070 (0.0008) -[2023-11-28 02:28:10,573][87426] Updated weights for policy 1, policy_version 86080 (0.0009) -[2023-11-28 02:28:11,481][87424] Updated weights for policy 0, policy_version 86186 (0.0012) -[2023-11-28 02:28:11,863][87424] Updated weights for policy 0, policy_version 86196 (0.0011) -[2023-11-28 02:28:12,268][87424] Updated weights for policy 0, policy_version 86206 (0.0012) -[2023-11-28 02:28:12,899][87426] Updated weights for policy 1, policy_version 86090 (0.0012) -[2023-11-28 02:28:13,288][87426] Updated weights for policy 1, policy_version 86100 (0.0008) -[2023-11-28 02:28:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 44105728. Throughput: 0: 2698.4, 1: 2679.6. Samples: 44121440. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:13,445][86177] Avg episode reward: [(0, '-547.070'), (1, '-580.360')] -[2023-11-28 02:28:13,658][87426] Updated weights for policy 1, policy_version 86110 (0.0008) -[2023-11-28 02:28:14,204][87424] Updated weights for policy 0, policy_version 86216 (0.0012) -[2023-11-28 02:28:14,593][87424] Updated weights for policy 0, policy_version 86226 (0.0012) -[2023-11-28 02:28:14,970][87424] Updated weights for policy 0, policy_version 86236 (0.0012) -[2023-11-28 02:28:16,090][87426] Updated weights for policy 1, policy_version 86120 (0.0008) -[2023-11-28 02:28:16,470][87426] Updated weights for policy 1, policy_version 86130 (0.0007) -[2023-11-28 02:28:16,846][87426] Updated weights for policy 1, policy_version 86140 (0.0007) -[2023-11-28 02:28:17,098][87424] Updated weights for policy 0, policy_version 86246 (0.0009) -[2023-11-28 02:28:17,487][87424] Updated weights for policy 0, policy_version 86256 (0.0007) -[2023-11-28 02:28:17,868][87424] Updated weights for policy 0, policy_version 86266 (0.0007) -[2023-11-28 02:28:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44138496. Throughput: 0: 2695.1, 1: 2673.1. Samples: 44145672. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:18,446][86177] Avg episode reward: [(0, '-554.260'), (1, '-571.220')] -[2023-11-28 02:28:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000086272_22085632.pth... -[2023-11-28 02:28:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000086144_22052864.pth... -[2023-11-28 02:28:18,495][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000083616_21405696.pth -[2023-11-28 02:28:18,505][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000083712_21430272.pth -[2023-11-28 02:28:19,352][87426] Updated weights for policy 1, policy_version 86150 (0.0010) -[2023-11-28 02:28:19,725][87426] Updated weights for policy 1, policy_version 86160 (0.0012) -[2023-11-28 02:28:19,902][87424] Updated weights for policy 0, policy_version 86276 (0.0009) -[2023-11-28 02:28:20,108][87426] Updated weights for policy 1, policy_version 86170 (0.0011) -[2023-11-28 02:28:20,286][87424] Updated weights for policy 0, policy_version 86286 (0.0011) -[2023-11-28 02:28:20,664][87424] Updated weights for policy 0, policy_version 86296 (0.0011) -[2023-11-28 02:28:22,397][87426] Updated weights for policy 1, policy_version 86180 (0.0009) -[2023-11-28 02:28:22,776][87426] Updated weights for policy 1, policy_version 86190 (0.0012) -[2023-11-28 02:28:23,149][87426] Updated weights for policy 1, policy_version 86200 (0.0011) -[2023-11-28 02:28:23,170][87424] Updated weights for policy 0, policy_version 86306 (0.0012) -[2023-11-28 02:28:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 44154880. Throughput: 0: 2699.0, 1: 2662.2. Samples: 44177304. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:23,445][86177] Avg episode reward: [(0, '-550.920'), (1, '-562.570')] -[2023-11-28 02:28:23,557][87424] Updated weights for policy 0, policy_version 86316 (0.0011) -[2023-11-28 02:28:23,939][87424] Updated weights for policy 0, policy_version 86326 (0.0012) -[2023-11-28 02:28:24,317][87424] Updated weights for policy 0, policy_version 86336 (0.0008) -[2023-11-28 02:28:25,257][87426] Updated weights for policy 1, policy_version 86210 (0.0009) -[2023-11-28 02:28:25,641][87426] Updated weights for policy 1, policy_version 86220 (0.0007) -[2023-11-28 02:28:26,033][87426] Updated weights for policy 1, policy_version 86230 (0.0008) -[2023-11-28 02:28:26,407][87426] Updated weights for policy 1, policy_version 86240 (0.0012) -[2023-11-28 02:28:26,865][87424] Updated weights for policy 0, policy_version 86346 (0.0008) -[2023-11-28 02:28:27,255][87424] Updated weights for policy 0, policy_version 86356 (0.0007) -[2023-11-28 02:28:27,642][87424] Updated weights for policy 0, policy_version 86366 (0.0011) -[2023-11-28 02:28:28,423][87426] Updated weights for policy 1, policy_version 86250 (0.0012) -[2023-11-28 02:28:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 44187648. Throughput: 0: 2700.7, 1: 2702.3. Samples: 44202836. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:28,445][86177] Avg episode reward: [(0, '-508.360'), (1, '-558.420')] -[2023-11-28 02:28:28,803][87426] Updated weights for policy 1, policy_version 86260 (0.0011) -[2023-11-28 02:28:29,186][87426] Updated weights for policy 1, policy_version 86270 (0.0009) -[2023-11-28 02:28:29,507][87424] Updated weights for policy 0, policy_version 86376 (0.0011) -[2023-11-28 02:28:29,889][87424] Updated weights for policy 0, policy_version 86386 (0.0011) -[2023-11-28 02:28:30,278][87424] Updated weights for policy 0, policy_version 86396 (0.0011) -[2023-11-28 02:28:31,312][87426] Updated weights for policy 1, policy_version 86280 (0.0010) -[2023-11-28 02:28:31,690][87426] Updated weights for policy 1, policy_version 86290 (0.0008) -[2023-11-28 02:28:32,070][87426] Updated weights for policy 1, policy_version 86300 (0.0010) -[2023-11-28 02:28:32,296][87424] Updated weights for policy 0, policy_version 86406 (0.0010) -[2023-11-28 02:28:32,680][87424] Updated weights for policy 0, policy_version 86416 (0.0010) -[2023-11-28 02:28:33,071][87424] Updated weights for policy 0, policy_version 86426 (0.0009) -[2023-11-28 02:28:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 44220416. Throughput: 0: 2708.6, 1: 2699.2. Samples: 44227460. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:33,445][86177] Avg episode reward: [(0, '-509.660'), (1, '-527.880')] -[2023-11-28 02:28:34,584][87426] Updated weights for policy 1, policy_version 86310 (0.0010) -[2023-11-28 02:28:34,960][87426] Updated weights for policy 1, policy_version 86320 (0.0010) -[2023-11-28 02:28:35,338][87426] Updated weights for policy 1, policy_version 86330 (0.0011) -[2023-11-28 02:28:35,358][87424] Updated weights for policy 0, policy_version 86436 (0.0008) -[2023-11-28 02:28:35,750][87424] Updated weights for policy 0, policy_version 86446 (0.0011) -[2023-11-28 02:28:36,120][87424] Updated weights for policy 0, policy_version 86456 (0.0012) -[2023-11-28 02:28:37,422][87426] Updated weights for policy 1, policy_version 86340 (0.0010) -[2023-11-28 02:28:37,794][87426] Updated weights for policy 1, policy_version 86350 (0.0012) -[2023-11-28 02:28:38,170][87426] Updated weights for policy 1, policy_version 86360 (0.0012) -[2023-11-28 02:28:38,198][87424] Updated weights for policy 0, policy_version 86466 (0.0011) -[2023-11-28 02:28:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 44236800. Throughput: 0: 2703.3, 1: 2683.2. Samples: 44259088. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:38,445][86177] Avg episode reward: [(0, '-501.110'), (1, '-546.180')] -[2023-11-28 02:28:38,580][87424] Updated weights for policy 0, policy_version 86476 (0.0011) -[2023-11-28 02:28:38,961][87424] Updated weights for policy 0, policy_version 86486 (0.0009) -[2023-11-28 02:28:39,344][87424] Updated weights for policy 0, policy_version 86496 (0.0008) -[2023-11-28 02:28:40,607][87426] Updated weights for policy 1, policy_version 86370 (0.0011) -[2023-11-28 02:28:40,988][87426] Updated weights for policy 1, policy_version 86380 (0.0012) -[2023-11-28 02:28:41,374][87426] Updated weights for policy 1, policy_version 86390 (0.0012) -[2023-11-28 02:28:41,767][87426] Updated weights for policy 1, policy_version 86400 (0.0010) -[2023-11-28 02:28:41,776][87424] Updated weights for policy 0, policy_version 86506 (0.0011) -[2023-11-28 02:28:42,166][87424] Updated weights for policy 0, policy_version 86516 (0.0012) -[2023-11-28 02:28:42,546][87424] Updated weights for policy 0, policy_version 86526 (0.0009) -[2023-11-28 02:28:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 44269568. Throughput: 0: 2703.7, 1: 2666.5. Samples: 44282408. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:43,445][86177] Avg episode reward: [(0, '-506.550'), (1, '-549.060')] -[2023-11-28 02:28:43,964][87426] Updated weights for policy 1, policy_version 86410 (0.0007) -[2023-11-28 02:28:44,347][87426] Updated weights for policy 1, policy_version 86420 (0.0008) -[2023-11-28 02:28:44,741][87426] Updated weights for policy 1, policy_version 86430 (0.0008) -[2023-11-28 02:28:44,742][87424] Updated weights for policy 0, policy_version 86536 (0.0011) -[2023-11-28 02:28:45,127][87424] Updated weights for policy 0, policy_version 86546 (0.0008) -[2023-11-28 02:28:45,524][87424] Updated weights for policy 0, policy_version 86556 (0.0009) -[2023-11-28 02:28:46,746][87426] Updated weights for policy 1, policy_version 86440 (0.0009) -[2023-11-28 02:28:47,123][87426] Updated weights for policy 1, policy_version 86450 (0.0009) -[2023-11-28 02:28:47,163][87424] Updated weights for policy 0, policy_version 86566 (0.0010) -[2023-11-28 02:28:47,514][87426] Updated weights for policy 1, policy_version 86460 (0.0010) -[2023-11-28 02:28:47,549][87424] Updated weights for policy 0, policy_version 86576 (0.0007) -[2023-11-28 02:28:47,943][87424] Updated weights for policy 0, policy_version 86586 (0.0007) -[2023-11-28 02:28:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44302336. Throughput: 0: 2708.4, 1: 2686.8. Samples: 44307268. Policy #0 lag: (min: 31.0, avg: 44.5, max: 63.0) -[2023-11-28 02:28:48,445][86177] Avg episode reward: [(0, '-507.330'), (1, '-543.100')] -[2023-11-28 02:28:49,702][87426] Updated weights for policy 1, policy_version 86470 (0.0007) -[2023-11-28 02:28:50,088][87426] Updated weights for policy 1, policy_version 86480 (0.0008) -[2023-11-28 02:28:50,392][87424] Updated weights for policy 0, policy_version 86596 (0.0009) -[2023-11-28 02:28:50,469][87426] Updated weights for policy 1, policy_version 86490 (0.0008) -[2023-11-28 02:28:50,771][87424] Updated weights for policy 0, policy_version 86606 (0.0010) -[2023-11-28 02:28:51,146][87424] Updated weights for policy 0, policy_version 86616 (0.0010) -[2023-11-28 02:28:52,925][87426] Updated weights for policy 1, policy_version 86500 (0.0009) -[2023-11-28 02:28:53,313][87426] Updated weights for policy 1, policy_version 86510 (0.0012) -[2023-11-28 02:28:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 44318720. Throughput: 0: 2666.0, 1: 2686.8. Samples: 44338448. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:28:53,445][86177] Avg episode reward: [(0, '-513.210'), (1, '-545.870')] -[2023-11-28 02:28:53,588][87424] Updated weights for policy 0, policy_version 86626 (0.0008) -[2023-11-28 02:28:53,682][87426] Updated weights for policy 1, policy_version 86520 (0.0009) -[2023-11-28 02:28:53,968][87424] Updated weights for policy 0, policy_version 86636 (0.0009) -[2023-11-28 02:28:54,356][87424] Updated weights for policy 0, policy_version 86646 (0.0008) -[2023-11-28 02:28:54,740][87424] Updated weights for policy 0, policy_version 86656 (0.0011) -[2023-11-28 02:28:55,913][87426] Updated weights for policy 1, policy_version 86530 (0.0010) -[2023-11-28 02:28:56,287][87426] Updated weights for policy 1, policy_version 86540 (0.0012) -[2023-11-28 02:28:56,657][87426] Updated weights for policy 1, policy_version 86550 (0.0011) -[2023-11-28 02:28:56,815][87424] Updated weights for policy 0, policy_version 86666 (0.0009) -[2023-11-28 02:28:57,038][87426] Updated weights for policy 1, policy_version 86560 (0.0007) -[2023-11-28 02:28:57,204][87424] Updated weights for policy 0, policy_version 86676 (0.0008) -[2023-11-28 02:28:57,597][87424] Updated weights for policy 0, policy_version 86686 (0.0012) -[2023-11-28 02:28:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 44351488. Throughput: 0: 2670.9, 1: 2726.3. Samples: 44364316. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:28:58,445][86177] Avg episode reward: [(0, '-514.400'), (1, '-513.440')] -[2023-11-28 02:28:58,642][87426] Updated weights for policy 1, policy_version 86570 (0.0008) -[2023-11-28 02:28:59,021][87426] Updated weights for policy 1, policy_version 86580 (0.0008) -[2023-11-28 02:28:59,402][87426] Updated weights for policy 1, policy_version 86590 (0.0007) -[2023-11-28 02:28:59,836][87424] Updated weights for policy 0, policy_version 86696 (0.0009) -[2023-11-28 02:29:00,220][87424] Updated weights for policy 0, policy_version 86706 (0.0009) -[2023-11-28 02:29:00,610][87424] Updated weights for policy 0, policy_version 86716 (0.0010) -[2023-11-28 02:29:01,471][87426] Updated weights for policy 1, policy_version 86600 (0.0008) -[2023-11-28 02:29:01,851][87426] Updated weights for policy 1, policy_version 86610 (0.0010) -[2023-11-28 02:29:02,228][87426] Updated weights for policy 1, policy_version 86620 (0.0008) -[2023-11-28 02:29:03,163][87424] Updated weights for policy 0, policy_version 86726 (0.0008) -[2023-11-28 02:29:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 44376064. Throughput: 0: 2666.0, 1: 2742.5. Samples: 44389052. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:29:03,445][86177] Avg episode reward: [(0, '-506.800'), (1, '-516.750')] -[2023-11-28 02:29:03,556][87424] Updated weights for policy 0, policy_version 86736 (0.0010) -[2023-11-28 02:29:03,927][87424] Updated weights for policy 0, policy_version 86746 (0.0008) -[2023-11-28 02:29:04,833][87426] Updated weights for policy 1, policy_version 86630 (0.0009) -[2023-11-28 02:29:05,212][87426] Updated weights for policy 1, policy_version 86640 (0.0011) -[2023-11-28 02:29:05,592][87426] Updated weights for policy 1, policy_version 86650 (0.0010) -[2023-11-28 02:29:06,389][87424] Updated weights for policy 0, policy_version 86756 (0.0007) -[2023-11-28 02:29:06,774][87424] Updated weights for policy 0, policy_version 86766 (0.0009) -[2023-11-28 02:29:07,157][87424] Updated weights for policy 0, policy_version 86776 (0.0011) -[2023-11-28 02:29:08,024][87426] Updated weights for policy 1, policy_version 86660 (0.0009) -[2023-11-28 02:29:08,405][87426] Updated weights for policy 1, policy_version 86670 (0.0011) -[2023-11-28 02:29:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 44400640. Throughput: 0: 2646.0, 1: 2764.4. Samples: 44420772. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:29:08,445][86177] Avg episode reward: [(0, '-540.330'), (1, '-518.360')] -[2023-11-28 02:29:08,786][87426] Updated weights for policy 1, policy_version 86680 (0.0012) -[2023-11-28 02:29:08,820][87424] Updated weights for policy 0, policy_version 86786 (0.0009) -[2023-11-28 02:29:09,198][87424] Updated weights for policy 0, policy_version 86796 (0.0011) -[2023-11-28 02:29:09,576][87424] Updated weights for policy 0, policy_version 86806 (0.0012) -[2023-11-28 02:29:09,958][87424] Updated weights for policy 0, policy_version 86816 (0.0012) -[2023-11-28 02:29:10,694][87426] Updated weights for policy 1, policy_version 86690 (0.0012) -[2023-11-28 02:29:11,076][87426] Updated weights for policy 1, policy_version 86700 (0.0008) -[2023-11-28 02:29:11,459][87426] Updated weights for policy 1, policy_version 86710 (0.0007) -[2023-11-28 02:29:11,838][87426] Updated weights for policy 1, policy_version 86720 (0.0009) -[2023-11-28 02:29:12,334][87424] Updated weights for policy 0, policy_version 86826 (0.0012) -[2023-11-28 02:29:12,712][87424] Updated weights for policy 0, policy_version 86836 (0.0012) -[2023-11-28 02:29:13,103][87424] Updated weights for policy 0, policy_version 86846 (0.0012) -[2023-11-28 02:29:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44433408. Throughput: 0: 2668.0, 1: 2730.8. Samples: 44445784. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:29:13,445][86177] Avg episode reward: [(0, '-543.440'), (1, '-515.280')] -[2023-11-28 02:29:14,158][87426] Updated weights for policy 1, policy_version 86730 (0.0008) -[2023-11-28 02:29:14,533][87426] Updated weights for policy 1, policy_version 86740 (0.0007) -[2023-11-28 02:29:14,913][87426] Updated weights for policy 1, policy_version 86750 (0.0009) -[2023-11-28 02:29:15,167][87424] Updated weights for policy 0, policy_version 86856 (0.0009) -[2023-11-28 02:29:15,548][87424] Updated weights for policy 0, policy_version 86866 (0.0008) -[2023-11-28 02:29:15,929][87424] Updated weights for policy 0, policy_version 86876 (0.0009) -[2023-11-28 02:29:17,423][87426] Updated weights for policy 1, policy_version 86760 (0.0007) -[2023-11-28 02:29:17,807][87426] Updated weights for policy 1, policy_version 86770 (0.0010) -[2023-11-28 02:29:18,184][87426] Updated weights for policy 1, policy_version 86780 (0.0008) -[2023-11-28 02:29:18,247][87424] Updated weights for policy 0, policy_version 86886 (0.0008) -[2023-11-28 02:29:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 44457984. Throughput: 0: 2640.7, 1: 2729.7. Samples: 44469128. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:29:18,445][86177] Avg episode reward: [(0, '-598.460'), (1, '-524.360')] -[2023-11-28 02:29:18,633][87424] Updated weights for policy 0, policy_version 86896 (0.0009) -[2023-11-28 02:29:19,034][87424] Updated weights for policy 0, policy_version 86906 (0.0010) -[2023-11-28 02:29:20,722][87426] Updated weights for policy 1, policy_version 86790 (0.0007) -[2023-11-28 02:29:21,018][87424] Updated weights for policy 0, policy_version 86916 (0.0010) -[2023-11-28 02:29:21,100][87426] Updated weights for policy 1, policy_version 86800 (0.0008) -[2023-11-28 02:29:21,396][87424] Updated weights for policy 0, policy_version 86926 (0.0008) -[2023-11-28 02:29:21,487][87426] Updated weights for policy 1, policy_version 86810 (0.0011) -[2023-11-28 02:29:21,786][87424] Updated weights for policy 0, policy_version 86936 (0.0011) -[2023-11-28 02:29:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 44482560. Throughput: 0: 2673.2, 1: 2708.9. Samples: 44501280. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:29:23,445][86177] Avg episode reward: [(0, '-596.110'), (1, '-517.390')] -[2023-11-28 02:29:23,479][87426] Updated weights for policy 1, policy_version 86820 (0.0010) -[2023-11-28 02:29:23,767][87424] Updated weights for policy 0, policy_version 86946 (0.0012) -[2023-11-28 02:29:23,860][87426] Updated weights for policy 1, policy_version 86830 (0.0009) -[2023-11-28 02:29:24,150][87424] Updated weights for policy 0, policy_version 86956 (0.0011) -[2023-11-28 02:29:24,235][87426] Updated weights for policy 1, policy_version 86840 (0.0011) -[2023-11-28 02:29:24,532][87424] Updated weights for policy 0, policy_version 86966 (0.0011) -[2023-11-28 02:29:24,905][87424] Updated weights for policy 0, policy_version 86976 (0.0012) -[2023-11-28 02:29:26,506][87426] Updated weights for policy 1, policy_version 86850 (0.0010) -[2023-11-28 02:29:26,885][87426] Updated weights for policy 1, policy_version 86860 (0.0011) -[2023-11-28 02:29:27,041][87424] Updated weights for policy 0, policy_version 86986 (0.0008) -[2023-11-28 02:29:27,263][87426] Updated weights for policy 1, policy_version 86870 (0.0011) -[2023-11-28 02:29:27,430][87424] Updated weights for policy 0, policy_version 86996 (0.0011) -[2023-11-28 02:29:27,647][87426] Updated weights for policy 1, policy_version 86880 (0.0012) -[2023-11-28 02:29:27,821][87424] Updated weights for policy 0, policy_version 87006 (0.0012) -[2023-11-28 02:29:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44515328. Throughput: 0: 2688.6, 1: 2735.5. Samples: 44526492. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:29:28,445][86177] Avg episode reward: [(0, '-555.290'), (1, '-509.480')] -[2023-11-28 02:29:29,309][87426] Updated weights for policy 1, policy_version 86890 (0.0012) -[2023-11-28 02:29:29,686][87426] Updated weights for policy 1, policy_version 86900 (0.0012) -[2023-11-28 02:29:30,074][87426] Updated weights for policy 1, policy_version 86910 (0.0011) -[2023-11-28 02:29:30,259][87424] Updated weights for policy 0, policy_version 87016 (0.0011) -[2023-11-28 02:29:30,642][87424] Updated weights for policy 0, policy_version 87026 (0.0009) -[2023-11-28 02:29:31,035][87424] Updated weights for policy 0, policy_version 87036 (0.0009) -[2023-11-28 02:29:32,224][87426] Updated weights for policy 1, policy_version 86920 (0.0011) -[2023-11-28 02:29:32,607][87426] Updated weights for policy 1, policy_version 86930 (0.0009) -[2023-11-28 02:29:32,914][87424] Updated weights for policy 0, policy_version 87046 (0.0012) -[2023-11-28 02:29:32,982][87426] Updated weights for policy 1, policy_version 86940 (0.0011) -[2023-11-28 02:29:33,287][87424] Updated weights for policy 0, policy_version 87056 (0.0011) -[2023-11-28 02:29:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 44539904. Throughput: 0: 2722.8, 1: 2730.0. Samples: 44552644. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:29:33,445][86177] Avg episode reward: [(0, '-520.850'), (1, '-514.000')] -[2023-11-28 02:29:33,665][87424] Updated weights for policy 0, policy_version 87066 (0.0012) -[2023-11-28 02:29:34,714][87426] Updated weights for policy 1, policy_version 86950 (0.0009) -[2023-11-28 02:29:35,091][87426] Updated weights for policy 1, policy_version 86960 (0.0012) -[2023-11-28 02:29:35,472][87426] Updated weights for policy 1, policy_version 86970 (0.0011) -[2023-11-28 02:29:35,702][87424] Updated weights for policy 0, policy_version 87076 (0.0011) -[2023-11-28 02:29:36,086][87424] Updated weights for policy 0, policy_version 87086 (0.0012) -[2023-11-28 02:29:36,474][87424] Updated weights for policy 0, policy_version 87096 (0.0012) -[2023-11-28 02:29:37,595][87426] Updated weights for policy 1, policy_version 86980 (0.0011) -[2023-11-28 02:29:37,965][87426] Updated weights for policy 1, policy_version 86990 (0.0012) -[2023-11-28 02:29:38,347][87426] Updated weights for policy 1, policy_version 87000 (0.0012) -[2023-11-28 02:29:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44564480. Throughput: 0: 2740.4, 1: 2749.7. Samples: 44585500. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:29:38,445][86177] Avg episode reward: [(0, '-546.690'), (1, '-505.700')] -[2023-11-28 02:29:38,823][87424] Updated weights for policy 0, policy_version 87106 (0.0011) -[2023-11-28 02:29:39,201][87424] Updated weights for policy 0, policy_version 87116 (0.0010) -[2023-11-28 02:29:39,584][87424] Updated weights for policy 0, policy_version 87126 (0.0008) -[2023-11-28 02:29:39,968][87424] Updated weights for policy 0, policy_version 87136 (0.0009) -[2023-11-28 02:29:40,785][87426] Updated weights for policy 1, policy_version 87010 (0.0012) -[2023-11-28 02:29:41,166][87426] Updated weights for policy 1, policy_version 87020 (0.0012) -[2023-11-28 02:29:41,540][87426] Updated weights for policy 1, policy_version 87030 (0.0012) -[2023-11-28 02:29:41,922][87426] Updated weights for policy 1, policy_version 87040 (0.0010) -[2023-11-28 02:29:42,114][87424] Updated weights for policy 0, policy_version 87146 (0.0012) -[2023-11-28 02:29:42,496][87424] Updated weights for policy 0, policy_version 87156 (0.0012) -[2023-11-28 02:29:42,871][87424] Updated weights for policy 0, policy_version 87166 (0.0012) -[2023-11-28 02:29:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44597248. Throughput: 0: 2735.1, 1: 2713.1. Samples: 44609484. Policy #0 lag: (min: 26.0, avg: 45.2, max: 58.0) -[2023-11-28 02:29:43,445][86177] Avg episode reward: [(0, '-547.000'), (1, '-519.920')] -[2023-11-28 02:29:44,120][87426] Updated weights for policy 1, policy_version 87050 (0.0007) -[2023-11-28 02:29:44,496][87426] Updated weights for policy 1, policy_version 87060 (0.0010) -[2023-11-28 02:29:44,882][87426] Updated weights for policy 1, policy_version 87070 (0.0012) -[2023-11-28 02:29:44,913][87424] Updated weights for policy 0, policy_version 87176 (0.0009) -[2023-11-28 02:29:45,298][87424] Updated weights for policy 0, policy_version 87186 (0.0008) -[2023-11-28 02:29:45,681][87424] Updated weights for policy 0, policy_version 87196 (0.0009) -[2023-11-28 02:29:47,260][87426] Updated weights for policy 1, policy_version 87080 (0.0008) -[2023-11-28 02:29:47,640][87426] Updated weights for policy 1, policy_version 87090 (0.0009) -[2023-11-28 02:29:48,023][87426] Updated weights for policy 1, policy_version 87100 (0.0012) -[2023-11-28 02:29:48,082][87424] Updated weights for policy 0, policy_version 87206 (0.0009) -[2023-11-28 02:29:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 44621824. Throughput: 0: 2728.4, 1: 2705.2. Samples: 44633568. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:29:48,445][86177] Avg episode reward: [(0, '-553.580'), (1, '-520.320')] -[2023-11-28 02:29:48,467][87424] Updated weights for policy 0, policy_version 87216 (0.0012) -[2023-11-28 02:29:48,852][87424] Updated weights for policy 0, policy_version 87226 (0.0012) -[2023-11-28 02:29:50,237][87426] Updated weights for policy 1, policy_version 87110 (0.0009) -[2023-11-28 02:29:50,613][87426] Updated weights for policy 1, policy_version 87120 (0.0010) -[2023-11-28 02:29:50,988][87426] Updated weights for policy 1, policy_version 87130 (0.0012) -[2023-11-28 02:29:51,105][87424] Updated weights for policy 0, policy_version 87236 (0.0012) -[2023-11-28 02:29:51,479][87424] Updated weights for policy 0, policy_version 87246 (0.0009) -[2023-11-28 02:29:51,863][87424] Updated weights for policy 0, policy_version 87256 (0.0010) -[2023-11-28 02:29:53,142][87426] Updated weights for policy 1, policy_version 87140 (0.0008) -[2023-11-28 02:29:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44646400. Throughput: 0: 2741.7, 1: 2701.8. Samples: 44665728. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:29:53,445][86177] Avg episode reward: [(0, '-550.370'), (1, '-530.350')] -[2023-11-28 02:29:53,521][87426] Updated weights for policy 1, policy_version 87150 (0.0010) -[2023-11-28 02:29:53,898][87426] Updated weights for policy 1, policy_version 87160 (0.0010) -[2023-11-28 02:29:54,335][87424] Updated weights for policy 0, policy_version 87266 (0.0009) -[2023-11-28 02:29:54,716][87424] Updated weights for policy 0, policy_version 87276 (0.0012) -[2023-11-28 02:29:55,092][87424] Updated weights for policy 0, policy_version 87286 (0.0012) -[2023-11-28 02:29:55,473][87424] Updated weights for policy 0, policy_version 87296 (0.0012) -[2023-11-28 02:29:55,886][87426] Updated weights for policy 1, policy_version 87170 (0.0009) -[2023-11-28 02:29:56,253][87426] Updated weights for policy 1, policy_version 87180 (0.0012) -[2023-11-28 02:29:56,629][87426] Updated weights for policy 1, policy_version 87190 (0.0011) -[2023-11-28 02:29:57,000][87426] Updated weights for policy 1, policy_version 87200 (0.0008) -[2023-11-28 02:29:57,679][87424] Updated weights for policy 0, policy_version 87306 (0.0011) -[2023-11-28 02:29:58,065][87424] Updated weights for policy 0, policy_version 87316 (0.0011) -[2023-11-28 02:29:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 44670976. Throughput: 0: 2723.1, 1: 2691.7. Samples: 44689452. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:29:58,445][86177] Avg episode reward: [(0, '-508.040'), (1, '-530.430')] -[2023-11-28 02:29:58,458][87424] Updated weights for policy 0, policy_version 87326 (0.0012) -[2023-11-28 02:29:59,483][87426] Updated weights for policy 1, policy_version 87210 (0.0012) -[2023-11-28 02:29:59,863][87426] Updated weights for policy 1, policy_version 87220 (0.0011) -[2023-11-28 02:30:00,242][87426] Updated weights for policy 1, policy_version 87230 (0.0011) -[2023-11-28 02:30:00,414][87424] Updated weights for policy 0, policy_version 87336 (0.0009) -[2023-11-28 02:30:00,799][87424] Updated weights for policy 0, policy_version 87346 (0.0008) -[2023-11-28 02:30:01,181][87424] Updated weights for policy 0, policy_version 87356 (0.0007) -[2023-11-28 02:30:02,462][87426] Updated weights for policy 1, policy_version 87240 (0.0008) -[2023-11-28 02:30:02,844][87426] Updated weights for policy 1, policy_version 87250 (0.0007) -[2023-11-28 02:30:03,228][87426] Updated weights for policy 1, policy_version 87260 (0.0010) -[2023-11-28 02:30:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44703744. Throughput: 0: 2762.7, 1: 2692.4. Samples: 44714608. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:30:03,445][86177] Avg episode reward: [(0, '-509.310'), (1, '-515.970')] -[2023-11-28 02:30:03,564][87424] Updated weights for policy 0, policy_version 87366 (0.0008) -[2023-11-28 02:30:03,963][87424] Updated weights for policy 0, policy_version 87376 (0.0008) -[2023-11-28 02:30:04,347][87424] Updated weights for policy 0, policy_version 87386 (0.0008) -[2023-11-28 02:30:05,135][87426] Updated weights for policy 1, policy_version 87270 (0.0011) -[2023-11-28 02:30:05,526][87426] Updated weights for policy 1, policy_version 87280 (0.0012) -[2023-11-28 02:30:05,916][87426] Updated weights for policy 1, policy_version 87290 (0.0012) -[2023-11-28 02:30:06,862][87424] Updated weights for policy 0, policy_version 87396 (0.0010) -[2023-11-28 02:30:07,242][87424] Updated weights for policy 0, policy_version 87406 (0.0012) -[2023-11-28 02:30:07,628][87424] Updated weights for policy 0, policy_version 87416 (0.0012) -[2023-11-28 02:30:07,760][87426] Updated weights for policy 1, policy_version 87300 (0.0011) -[2023-11-28 02:30:08,140][87426] Updated weights for policy 1, policy_version 87310 (0.0007) -[2023-11-28 02:30:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44728320. Throughput: 0: 2720.3, 1: 2757.1. Samples: 44747764. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:30:08,446][86177] Avg episode reward: [(0, '-507.270'), (1, '-504.780')] -[2023-11-28 02:30:08,527][87426] Updated weights for policy 1, policy_version 87320 (0.0011) -[2023-11-28 02:30:10,174][87424] Updated weights for policy 0, policy_version 87426 (0.0011) -[2023-11-28 02:30:10,249][87426] Updated weights for policy 1, policy_version 87330 (0.0012) -[2023-11-28 02:30:10,554][87424] Updated weights for policy 0, policy_version 87436 (0.0011) -[2023-11-28 02:30:10,623][87426] Updated weights for policy 1, policy_version 87340 (0.0011) -[2023-11-28 02:30:10,935][87424] Updated weights for policy 0, policy_version 87446 (0.0011) -[2023-11-28 02:30:10,998][87426] Updated weights for policy 1, policy_version 87350 (0.0008) -[2023-11-28 02:30:11,321][87424] Updated weights for policy 0, policy_version 87456 (0.0008) -[2023-11-28 02:30:11,363][87426] Updated weights for policy 1, policy_version 87360 (0.0012) -[2023-11-28 02:30:13,224][87424] Updated weights for policy 0, policy_version 87466 (0.0011) -[2023-11-28 02:30:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 44752896. Throughput: 0: 2714.8, 1: 2740.2. Samples: 44771964. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:30:13,445][86177] Avg episode reward: [(0, '-510.990'), (1, '-503.770')] -[2023-11-28 02:30:13,538][87426] Updated weights for policy 1, policy_version 87370 (0.0009) -[2023-11-28 02:30:13,605][87424] Updated weights for policy 0, policy_version 87476 (0.0009) -[2023-11-28 02:30:13,909][87426] Updated weights for policy 1, policy_version 87380 (0.0007) -[2023-11-28 02:30:13,994][87424] Updated weights for policy 0, policy_version 87486 (0.0007) -[2023-11-28 02:30:14,293][87426] Updated weights for policy 1, policy_version 87390 (0.0008) -[2023-11-28 02:30:15,631][87424] Updated weights for policy 0, policy_version 87496 (0.0011) -[2023-11-28 02:30:16,015][87424] Updated weights for policy 0, policy_version 87506 (0.0012) -[2023-11-28 02:30:16,391][87424] Updated weights for policy 0, policy_version 87516 (0.0012) -[2023-11-28 02:30:16,786][87426] Updated weights for policy 1, policy_version 87400 (0.0011) -[2023-11-28 02:30:17,174][87426] Updated weights for policy 1, policy_version 87410 (0.0011) -[2023-11-28 02:30:17,556][87426] Updated weights for policy 1, policy_version 87420 (0.0012) -[2023-11-28 02:30:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44785664. Throughput: 0: 2677.1, 1: 2747.5. Samples: 44796748. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:30:18,445][86177] Avg episode reward: [(0, '-512.090'), (1, '-502.460')] -[2023-11-28 02:30:18,452][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000087520_22405120.pth... -[2023-11-28 02:30:18,452][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000087424_22380544.pth... -[2023-11-28 02:30:18,502][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000084896_21733376.pth -[2023-11-28 02:30:18,505][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000084992_21757952.pth -[2023-11-28 02:30:18,867][87424] Updated weights for policy 0, policy_version 87526 (0.0012) -[2023-11-28 02:30:19,250][87424] Updated weights for policy 0, policy_version 87536 (0.0012) -[2023-11-28 02:30:19,472][87426] Updated weights for policy 1, policy_version 87430 (0.0012) -[2023-11-28 02:30:19,637][87424] Updated weights for policy 0, policy_version 87546 (0.0011) -[2023-11-28 02:30:19,854][87426] Updated weights for policy 1, policy_version 87440 (0.0011) -[2023-11-28 02:30:20,229][87426] Updated weights for policy 1, policy_version 87450 (0.0012) -[2023-11-28 02:30:21,851][87424] Updated weights for policy 0, policy_version 87556 (0.0012) -[2023-11-28 02:30:22,236][87424] Updated weights for policy 0, policy_version 87566 (0.0011) -[2023-11-28 02:30:22,517][87426] Updated weights for policy 1, policy_version 87460 (0.0011) -[2023-11-28 02:30:22,616][87424] Updated weights for policy 0, policy_version 87576 (0.0011) -[2023-11-28 02:30:22,889][87426] Updated weights for policy 1, policy_version 87470 (0.0012) -[2023-11-28 02:30:23,267][87426] Updated weights for policy 1, policy_version 87480 (0.0012) -[2023-11-28 02:30:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44810240. Throughput: 0: 2698.8, 1: 2726.1. Samples: 44829624. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:30:23,445][86177] Avg episode reward: [(0, '-506.740'), (1, '-503.240')] -[2023-11-28 02:30:24,496][87424] Updated weights for policy 0, policy_version 87586 (0.0011) -[2023-11-28 02:30:24,887][87424] Updated weights for policy 0, policy_version 87596 (0.0012) -[2023-11-28 02:30:25,268][87424] Updated weights for policy 0, policy_version 87606 (0.0012) -[2023-11-28 02:30:25,544][87426] Updated weights for policy 1, policy_version 87490 (0.0012) -[2023-11-28 02:30:25,655][87424] Updated weights for policy 0, policy_version 87616 (0.0012) -[2023-11-28 02:30:25,926][87426] Updated weights for policy 1, policy_version 87500 (0.0012) -[2023-11-28 02:30:26,292][87426] Updated weights for policy 1, policy_version 87510 (0.0012) -[2023-11-28 02:30:26,666][87426] Updated weights for policy 1, policy_version 87520 (0.0012) -[2023-11-28 02:30:27,608][87424] Updated weights for policy 0, policy_version 87626 (0.0008) -[2023-11-28 02:30:27,991][87424] Updated weights for policy 0, policy_version 87636 (0.0011) -[2023-11-28 02:30:28,392][87424] Updated weights for policy 0, policy_version 87646 (0.0011) -[2023-11-28 02:30:28,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 44834816. Throughput: 0: 2711.5, 1: 2736.2. Samples: 44854636. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:30:28,446][86177] Avg episode reward: [(0, '-507.090'), (1, '-502.180')] -[2023-11-28 02:30:28,587][87426] Updated weights for policy 1, policy_version 87530 (0.0009) -[2023-11-28 02:30:28,973][87426] Updated weights for policy 1, policy_version 87540 (0.0011) -[2023-11-28 02:30:29,358][87426] Updated weights for policy 1, policy_version 87550 (0.0010) -[2023-11-28 02:30:30,721][87424] Updated weights for policy 0, policy_version 87656 (0.0011) -[2023-11-28 02:30:31,102][87424] Updated weights for policy 0, policy_version 87666 (0.0012) -[2023-11-28 02:30:31,492][87424] Updated weights for policy 0, policy_version 87676 (0.0011) -[2023-11-28 02:30:31,804][87426] Updated weights for policy 1, policy_version 87560 (0.0011) -[2023-11-28 02:30:32,187][87426] Updated weights for policy 1, policy_version 87570 (0.0010) -[2023-11-28 02:30:32,574][87426] Updated weights for policy 1, policy_version 87580 (0.0011) -[2023-11-28 02:30:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44867584. Throughput: 0: 2708.5, 1: 2733.6. Samples: 44878464. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:30:33,445][86177] Avg episode reward: [(0, '-505.390'), (1, '-528.450')] -[2023-11-28 02:30:33,456][87424] Updated weights for policy 0, policy_version 87686 (0.0012) -[2023-11-28 02:30:33,828][87424] Updated weights for policy 0, policy_version 87696 (0.0012) -[2023-11-28 02:30:34,216][87424] Updated weights for policy 0, policy_version 87706 (0.0012) -[2023-11-28 02:30:34,837][87426] Updated weights for policy 1, policy_version 87590 (0.0011) -[2023-11-28 02:30:35,222][87426] Updated weights for policy 1, policy_version 87600 (0.0012) -[2023-11-28 02:30:35,595][87426] Updated weights for policy 1, policy_version 87610 (0.0012) -[2023-11-28 02:30:36,319][87424] Updated weights for policy 0, policy_version 87716 (0.0012) -[2023-11-28 02:30:36,706][87424] Updated weights for policy 0, policy_version 87726 (0.0012) -[2023-11-28 02:30:37,079][87424] Updated weights for policy 0, policy_version 87736 (0.0012) -[2023-11-28 02:30:37,484][87426] Updated weights for policy 1, policy_version 87620 (0.0010) -[2023-11-28 02:30:37,863][87426] Updated weights for policy 1, policy_version 87630 (0.0007) -[2023-11-28 02:30:38,252][87426] Updated weights for policy 1, policy_version 87640 (0.0009) -[2023-11-28 02:30:38,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44892160. Throughput: 0: 2732.8, 1: 2746.5. Samples: 44912296. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 02:30:38,445][86177] Avg episode reward: [(0, '-503.780'), (1, '-533.120')] -[2023-11-28 02:30:39,203][87424] Updated weights for policy 0, policy_version 87746 (0.0011) -[2023-11-28 02:30:39,581][87424] Updated weights for policy 0, policy_version 87756 (0.0008) -[2023-11-28 02:30:39,972][87424] Updated weights for policy 0, policy_version 87766 (0.0010) -[2023-11-28 02:30:40,369][87424] Updated weights for policy 0, policy_version 87776 (0.0011) -[2023-11-28 02:30:40,433][87426] Updated weights for policy 1, policy_version 87650 (0.0008) -[2023-11-28 02:30:40,811][87426] Updated weights for policy 1, policy_version 87660 (0.0010) -[2023-11-28 02:30:41,188][87426] Updated weights for policy 1, policy_version 87670 (0.0009) -[2023-11-28 02:30:41,572][87426] Updated weights for policy 1, policy_version 87680 (0.0012) -[2023-11-28 02:30:42,503][87424] Updated weights for policy 0, policy_version 87786 (0.0012) -[2023-11-28 02:30:42,881][87424] Updated weights for policy 0, policy_version 87796 (0.0012) -[2023-11-28 02:30:43,262][87424] Updated weights for policy 0, policy_version 87806 (0.0012) -[2023-11-28 02:30:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44924928. Throughput: 0: 2744.5, 1: 2760.0. Samples: 44937156. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:30:43,445][86177] Avg episode reward: [(0, '-505.800'), (1, '-533.550')] -[2023-11-28 02:30:43,500][87426] Updated weights for policy 1, policy_version 87690 (0.0009) -[2023-11-28 02:30:43,883][87426] Updated weights for policy 1, policy_version 87700 (0.0011) -[2023-11-28 02:30:44,266][87426] Updated weights for policy 1, policy_version 87710 (0.0011) -[2023-11-28 02:30:45,359][87424] Updated weights for policy 0, policy_version 87816 (0.0010) -[2023-11-28 02:30:45,735][87424] Updated weights for policy 0, policy_version 87826 (0.0011) -[2023-11-28 02:30:46,116][87424] Updated weights for policy 0, policy_version 87836 (0.0011) -[2023-11-28 02:30:46,661][87426] Updated weights for policy 1, policy_version 87720 (0.0011) -[2023-11-28 02:30:47,046][87426] Updated weights for policy 1, policy_version 87730 (0.0012) -[2023-11-28 02:30:47,422][87426] Updated weights for policy 1, policy_version 87740 (0.0012) -[2023-11-28 02:30:48,156][87424] Updated weights for policy 0, policy_version 87846 (0.0009) -[2023-11-28 02:30:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 44949504. Throughput: 0: 2728.5, 1: 2762.2. Samples: 44961692. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:30:48,445][86177] Avg episode reward: [(0, '-500.760'), (1, '-533.370')] -[2023-11-28 02:30:48,535][87424] Updated weights for policy 0, policy_version 87856 (0.0008) -[2023-11-28 02:30:48,919][87424] Updated weights for policy 0, policy_version 87866 (0.0008) -[2023-11-28 02:30:49,239][87426] Updated weights for policy 1, policy_version 87750 (0.0012) -[2023-11-28 02:30:49,623][87426] Updated weights for policy 1, policy_version 87760 (0.0011) -[2023-11-28 02:30:50,004][87426] Updated weights for policy 1, policy_version 87770 (0.0010) -[2023-11-28 02:30:51,218][87424] Updated weights for policy 0, policy_version 87876 (0.0011) -[2023-11-28 02:30:51,605][87424] Updated weights for policy 0, policy_version 87886 (0.0012) -[2023-11-28 02:30:51,973][87424] Updated weights for policy 0, policy_version 87896 (0.0011) -[2023-11-28 02:30:52,209][87426] Updated weights for policy 1, policy_version 87780 (0.0011) -[2023-11-28 02:30:52,588][87426] Updated weights for policy 1, policy_version 87790 (0.0010) -[2023-11-28 02:30:52,961][87426] Updated weights for policy 1, policy_version 87800 (0.0012) -[2023-11-28 02:30:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 44982272. Throughput: 0: 2758.7, 1: 2728.4. Samples: 44994680. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:30:53,445][86177] Avg episode reward: [(0, '-505.560'), (1, '-523.050')] -[2023-11-28 02:30:54,193][87424] Updated weights for policy 0, policy_version 87906 (0.0010) -[2023-11-28 02:30:54,577][87424] Updated weights for policy 0, policy_version 87916 (0.0012) -[2023-11-28 02:30:54,934][87426] Updated weights for policy 1, policy_version 87810 (0.0011) -[2023-11-28 02:30:54,963][87424] Updated weights for policy 0, policy_version 87926 (0.0012) -[2023-11-28 02:30:55,309][87426] Updated weights for policy 1, policy_version 87820 (0.0007) -[2023-11-28 02:30:55,343][87424] Updated weights for policy 0, policy_version 87936 (0.0008) -[2023-11-28 02:30:55,695][87426] Updated weights for policy 1, policy_version 87830 (0.0009) -[2023-11-28 02:30:56,072][87426] Updated weights for policy 1, policy_version 87840 (0.0010) -[2023-11-28 02:30:57,379][87424] Updated weights for policy 0, policy_version 87946 (0.0011) -[2023-11-28 02:30:57,768][87424] Updated weights for policy 0, policy_version 87956 (0.0010) -[2023-11-28 02:30:58,149][87424] Updated weights for policy 0, policy_version 87966 (0.0008) -[2023-11-28 02:30:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 45006848. Throughput: 0: 2763.7, 1: 2742.9. Samples: 45019764. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:30:58,446][86177] Avg episode reward: [(0, '-508.770'), (1, '-529.130')] -[2023-11-28 02:30:58,473][87426] Updated weights for policy 1, policy_version 87850 (0.0007) -[2023-11-28 02:30:58,857][87426] Updated weights for policy 1, policy_version 87860 (0.0008) -[2023-11-28 02:30:59,230][87426] Updated weights for policy 1, policy_version 87870 (0.0008) -[2023-11-28 02:31:00,305][87424] Updated weights for policy 0, policy_version 87976 (0.0012) -[2023-11-28 02:31:00,685][87424] Updated weights for policy 0, policy_version 87986 (0.0012) -[2023-11-28 02:31:01,039][87426] Updated weights for policy 1, policy_version 87880 (0.0010) -[2023-11-28 02:31:01,066][87424] Updated weights for policy 0, policy_version 87996 (0.0008) -[2023-11-28 02:31:01,421][87426] Updated weights for policy 1, policy_version 87890 (0.0007) -[2023-11-28 02:31:01,804][87426] Updated weights for policy 1, policy_version 87900 (0.0009) -[2023-11-28 02:31:03,313][87424] Updated weights for policy 0, policy_version 88006 (0.0010) -[2023-11-28 02:31:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45031424. Throughput: 0: 2760.5, 1: 2740.5. Samples: 45044296. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:31:03,445][86177] Avg episode reward: [(0, '-509.650'), (1, '-541.600')] -[2023-11-28 02:31:03,691][87424] Updated weights for policy 0, policy_version 88016 (0.0012) -[2023-11-28 02:31:04,067][87424] Updated weights for policy 0, policy_version 88026 (0.0012) -[2023-11-28 02:31:04,331][87426] Updated weights for policy 1, policy_version 87910 (0.0010) -[2023-11-28 02:31:04,715][87426] Updated weights for policy 1, policy_version 87920 (0.0012) -[2023-11-28 02:31:05,091][87426] Updated weights for policy 1, policy_version 87930 (0.0011) -[2023-11-28 02:31:06,335][87424] Updated weights for policy 0, policy_version 88036 (0.0012) -[2023-11-28 02:31:06,719][87424] Updated weights for policy 0, policy_version 88046 (0.0011) -[2023-11-28 02:31:06,876][87426] Updated weights for policy 1, policy_version 87940 (0.0011) -[2023-11-28 02:31:07,102][87424] Updated weights for policy 0, policy_version 88056 (0.0011) -[2023-11-28 02:31:07,264][87426] Updated weights for policy 1, policy_version 87950 (0.0009) -[2023-11-28 02:31:07,647][87426] Updated weights for policy 1, policy_version 87960 (0.0008) -[2023-11-28 02:31:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 45064192. Throughput: 0: 2735.9, 1: 2765.2. Samples: 45077176. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:31:08,445][86177] Avg episode reward: [(0, '-507.360'), (1, '-543.460')] -[2023-11-28 02:31:09,180][87424] Updated weights for policy 0, policy_version 88066 (0.0011) -[2023-11-28 02:31:09,553][87424] Updated weights for policy 0, policy_version 88076 (0.0011) -[2023-11-28 02:31:09,936][87424] Updated weights for policy 0, policy_version 88086 (0.0010) -[2023-11-28 02:31:10,155][87426] Updated weights for policy 1, policy_version 87970 (0.0009) -[2023-11-28 02:31:10,317][87424] Updated weights for policy 0, policy_version 88096 (0.0009) -[2023-11-28 02:31:10,540][87426] Updated weights for policy 1, policy_version 87980 (0.0011) -[2023-11-28 02:31:10,920][87426] Updated weights for policy 1, policy_version 87990 (0.0011) -[2023-11-28 02:31:11,291][87426] Updated weights for policy 1, policy_version 88000 (0.0010) -[2023-11-28 02:31:12,481][87424] Updated weights for policy 0, policy_version 88106 (0.0011) -[2023-11-28 02:31:12,867][87424] Updated weights for policy 0, policy_version 88116 (0.0012) -[2023-11-28 02:31:13,257][87424] Updated weights for policy 0, policy_version 88126 (0.0010) -[2023-11-28 02:31:13,334][87426] Updated weights for policy 1, policy_version 88010 (0.0012) -[2023-11-28 02:31:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 45088768. Throughput: 0: 2735.5, 1: 2738.1. Samples: 45100944. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:31:13,445][86177] Avg episode reward: [(0, '-505.860'), (1, '-527.380')] -[2023-11-28 02:31:13,714][87426] Updated weights for policy 1, policy_version 88020 (0.0011) -[2023-11-28 02:31:14,100][87426] Updated weights for policy 1, policy_version 88030 (0.0012) -[2023-11-28 02:31:15,461][87424] Updated weights for policy 0, policy_version 88136 (0.0011) -[2023-11-28 02:31:15,842][87424] Updated weights for policy 0, policy_version 88146 (0.0012) -[2023-11-28 02:31:16,179][87426] Updated weights for policy 1, policy_version 88040 (0.0010) -[2023-11-28 02:31:16,232][87424] Updated weights for policy 0, policy_version 88156 (0.0012) -[2023-11-28 02:31:16,572][87426] Updated weights for policy 1, policy_version 88050 (0.0007) -[2023-11-28 02:31:16,950][87426] Updated weights for policy 1, policy_version 88060 (0.0007) -[2023-11-28 02:31:18,359][87424] Updated weights for policy 0, policy_version 88166 (0.0012) -[2023-11-28 02:31:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45113344. Throughput: 0: 2742.2, 1: 2751.8. Samples: 45125696. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:31:18,446][86177] Avg episode reward: [(0, '-509.790'), (1, '-529.380')] -[2023-11-28 02:31:18,743][87424] Updated weights for policy 0, policy_version 88176 (0.0008) -[2023-11-28 02:31:19,083][87426] Updated weights for policy 1, policy_version 88070 (0.0010) -[2023-11-28 02:31:19,124][87424] Updated weights for policy 0, policy_version 88186 (0.0012) -[2023-11-28 02:31:19,468][87426] Updated weights for policy 1, policy_version 88080 (0.0010) -[2023-11-28 02:31:19,852][87426] Updated weights for policy 1, policy_version 88090 (0.0010) -[2023-11-28 02:31:20,929][87424] Updated weights for policy 0, policy_version 88196 (0.0012) -[2023-11-28 02:31:21,321][87424] Updated weights for policy 0, policy_version 88206 (0.0012) -[2023-11-28 02:31:21,696][87424] Updated weights for policy 0, policy_version 88216 (0.0012) -[2023-11-28 02:31:22,134][87426] Updated weights for policy 1, policy_version 88100 (0.0010) -[2023-11-28 02:31:22,505][87426] Updated weights for policy 1, policy_version 88110 (0.0010) -[2023-11-28 02:31:22,884][87426] Updated weights for policy 1, policy_version 88120 (0.0011) -[2023-11-28 02:31:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 45146112. Throughput: 0: 2727.1, 1: 2738.0. Samples: 45158228. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:31:23,445][86177] Avg episode reward: [(0, '-549.270'), (1, '-530.970')] -[2023-11-28 02:31:24,155][87424] Updated weights for policy 0, policy_version 88226 (0.0012) -[2023-11-28 02:31:24,538][87424] Updated weights for policy 0, policy_version 88236 (0.0012) -[2023-11-28 02:31:24,925][87424] Updated weights for policy 0, policy_version 88246 (0.0012) -[2023-11-28 02:31:25,129][87426] Updated weights for policy 1, policy_version 88130 (0.0012) -[2023-11-28 02:31:25,311][87424] Updated weights for policy 0, policy_version 88256 (0.0012) -[2023-11-28 02:31:25,505][87426] Updated weights for policy 1, policy_version 88140 (0.0012) -[2023-11-28 02:31:25,884][87426] Updated weights for policy 1, policy_version 88150 (0.0012) -[2023-11-28 02:31:26,262][87426] Updated weights for policy 1, policy_version 88160 (0.0011) -[2023-11-28 02:31:27,053][87424] Updated weights for policy 0, policy_version 88266 (0.0012) -[2023-11-28 02:31:27,429][87424] Updated weights for policy 0, policy_version 88276 (0.0008) -[2023-11-28 02:31:27,816][87424] Updated weights for policy 0, policy_version 88286 (0.0007) -[2023-11-28 02:31:27,939][87426] Updated weights for policy 1, policy_version 88170 (0.0011) -[2023-11-28 02:31:28,318][87426] Updated weights for policy 1, policy_version 88180 (0.0012) -[2023-11-28 02:31:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 45170688. Throughput: 0: 2739.0, 1: 2731.5. Samples: 45183328. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:31:28,445][86177] Avg episode reward: [(0, '-555.050'), (1, '-534.500')] -[2023-11-28 02:31:28,701][87426] Updated weights for policy 1, policy_version 88190 (0.0012) -[2023-11-28 02:31:29,589][87424] Updated weights for policy 0, policy_version 88296 (0.0011) -[2023-11-28 02:31:29,978][87424] Updated weights for policy 0, policy_version 88306 (0.0012) -[2023-11-28 02:31:30,350][87424] Updated weights for policy 0, policy_version 88316 (0.0012) -[2023-11-28 02:31:31,217][87426] Updated weights for policy 1, policy_version 88200 (0.0010) -[2023-11-28 02:31:31,601][87426] Updated weights for policy 1, policy_version 88210 (0.0010) -[2023-11-28 02:31:31,985][87426] Updated weights for policy 1, policy_version 88220 (0.0011) -[2023-11-28 02:31:32,357][87424] Updated weights for policy 0, policy_version 88326 (0.0010) -[2023-11-28 02:31:32,737][87424] Updated weights for policy 0, policy_version 88336 (0.0011) -[2023-11-28 02:31:33,114][87424] Updated weights for policy 0, policy_version 88346 (0.0009) -[2023-11-28 02:31:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 45203456. Throughput: 0: 2756.5, 1: 2738.4. Samples: 45208964. Policy #0 lag: (min: 31.0, avg: 35.2, max: 61.0) -[2023-11-28 02:31:33,445][86177] Avg episode reward: [(0, '-553.890'), (1, '-536.440')] -[2023-11-28 02:31:34,150][87426] Updated weights for policy 1, policy_version 88230 (0.0009) -[2023-11-28 02:31:34,525][87426] Updated weights for policy 1, policy_version 88240 (0.0011) -[2023-11-28 02:31:34,902][87426] Updated weights for policy 1, policy_version 88250 (0.0010) -[2023-11-28 02:31:35,273][87424] Updated weights for policy 0, policy_version 88356 (0.0011) -[2023-11-28 02:31:35,650][87424] Updated weights for policy 0, policy_version 88366 (0.0009) -[2023-11-28 02:31:36,031][87424] Updated weights for policy 0, policy_version 88376 (0.0007) -[2023-11-28 02:31:37,440][87426] Updated weights for policy 1, policy_version 88260 (0.0010) -[2023-11-28 02:31:37,815][87426] Updated weights for policy 1, policy_version 88270 (0.0012) -[2023-11-28 02:31:38,192][87426] Updated weights for policy 1, policy_version 88280 (0.0012) -[2023-11-28 02:31:38,397][87424] Updated weights for policy 0, policy_version 88386 (0.0008) -[2023-11-28 02:31:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 45219840. Throughput: 0: 2763.7, 1: 2741.0. Samples: 45242392. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:31:38,445][86177] Avg episode reward: [(0, '-551.530'), (1, '-541.750')] -[2023-11-28 02:31:38,781][87424] Updated weights for policy 0, policy_version 88396 (0.0009) -[2023-11-28 02:31:39,169][87424] Updated weights for policy 0, policy_version 88406 (0.0008) -[2023-11-28 02:31:39,551][87424] Updated weights for policy 0, policy_version 88416 (0.0010) -[2023-11-28 02:31:40,250][87426] Updated weights for policy 1, policy_version 88290 (0.0011) -[2023-11-28 02:31:40,632][87426] Updated weights for policy 1, policy_version 88300 (0.0009) -[2023-11-28 02:31:41,012][87426] Updated weights for policy 1, policy_version 88310 (0.0008) -[2023-11-28 02:31:41,392][87426] Updated weights for policy 1, policy_version 88320 (0.0010) -[2023-11-28 02:31:41,498][87424] Updated weights for policy 0, policy_version 88426 (0.0007) -[2023-11-28 02:31:41,884][87424] Updated weights for policy 0, policy_version 88436 (0.0010) -[2023-11-28 02:31:42,268][87424] Updated weights for policy 0, policy_version 88446 (0.0011) -[2023-11-28 02:31:43,191][87426] Updated weights for policy 1, policy_version 88330 (0.0009) -[2023-11-28 02:31:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45252608. Throughput: 0: 2770.7, 1: 2723.7. Samples: 45267008. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:31:43,445][86177] Avg episode reward: [(0, '-554.670'), (1, '-518.390')] -[2023-11-28 02:31:43,576][87426] Updated weights for policy 1, policy_version 88340 (0.0007) -[2023-11-28 02:31:43,952][87426] Updated weights for policy 1, policy_version 88350 (0.0009) -[2023-11-28 02:31:44,058][87424] Updated weights for policy 0, policy_version 88456 (0.0010) -[2023-11-28 02:31:44,450][87424] Updated weights for policy 0, policy_version 88466 (0.0012) -[2023-11-28 02:31:44,828][87424] Updated weights for policy 0, policy_version 88476 (0.0012) -[2023-11-28 02:31:45,910][87426] Updated weights for policy 1, policy_version 88360 (0.0008) -[2023-11-28 02:31:46,287][87426] Updated weights for policy 1, policy_version 88370 (0.0007) -[2023-11-28 02:31:46,673][87426] Updated weights for policy 1, policy_version 88380 (0.0008) -[2023-11-28 02:31:47,382][87424] Updated weights for policy 0, policy_version 88486 (0.0009) -[2023-11-28 02:31:47,772][87424] Updated weights for policy 0, policy_version 88496 (0.0008) -[2023-11-28 02:31:48,149][87424] Updated weights for policy 0, policy_version 88506 (0.0007) -[2023-11-28 02:31:48,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 45285376. Throughput: 0: 2755.4, 1: 2737.9. Samples: 45291492. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:31:48,446][86177] Avg episode reward: [(0, '-558.820'), (1, '-518.580')] -[2023-11-28 02:31:48,529][87426] Updated weights for policy 1, policy_version 88390 (0.0010) -[2023-11-28 02:31:48,909][87426] Updated weights for policy 1, policy_version 88400 (0.0011) -[2023-11-28 02:31:49,282][87426] Updated weights for policy 1, policy_version 88410 (0.0008) -[2023-11-28 02:31:50,670][87424] Updated weights for policy 0, policy_version 88516 (0.0009) -[2023-11-28 02:31:51,048][87424] Updated weights for policy 0, policy_version 88526 (0.0011) -[2023-11-28 02:31:51,432][87424] Updated weights for policy 0, policy_version 88536 (0.0009) -[2023-11-28 02:31:51,630][87426] Updated weights for policy 1, policy_version 88420 (0.0009) -[2023-11-28 02:31:52,008][87426] Updated weights for policy 1, policy_version 88430 (0.0011) -[2023-11-28 02:31:52,386][87426] Updated weights for policy 1, policy_version 88440 (0.0010) -[2023-11-28 02:31:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45309952. Throughput: 0: 2745.1, 1: 2729.5. Samples: 45323532. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:31:53,445][86177] Avg episode reward: [(0, '-554.150'), (1, '-517.370')] -[2023-11-28 02:31:53,514][87424] Updated weights for policy 0, policy_version 88546 (0.0011) -[2023-11-28 02:31:53,891][87424] Updated weights for policy 0, policy_version 88556 (0.0011) -[2023-11-28 02:31:54,284][87424] Updated weights for policy 0, policy_version 88566 (0.0012) -[2023-11-28 02:31:54,660][87424] Updated weights for policy 0, policy_version 88576 (0.0012) -[2023-11-28 02:31:54,765][87426] Updated weights for policy 1, policy_version 88450 (0.0011) -[2023-11-28 02:31:55,142][87426] Updated weights for policy 1, policy_version 88460 (0.0007) -[2023-11-28 02:31:55,533][87426] Updated weights for policy 1, policy_version 88470 (0.0007) -[2023-11-28 02:31:55,920][87426] Updated weights for policy 1, policy_version 88480 (0.0007) -[2023-11-28 02:31:56,729][87424] Updated weights for policy 0, policy_version 88586 (0.0012) -[2023-11-28 02:31:57,106][87424] Updated weights for policy 0, policy_version 88596 (0.0012) -[2023-11-28 02:31:57,497][87424] Updated weights for policy 0, policy_version 88606 (0.0011) -[2023-11-28 02:31:57,805][87426] Updated weights for policy 1, policy_version 88490 (0.0007) -[2023-11-28 02:31:58,179][87426] Updated weights for policy 1, policy_version 88500 (0.0007) -[2023-11-28 02:31:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 45334528. Throughput: 0: 2740.2, 1: 2749.5. Samples: 45347980. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:31:58,445][86177] Avg episode reward: [(0, '-563.810'), (1, '-527.790')] -[2023-11-28 02:31:58,568][87426] Updated weights for policy 1, policy_version 88510 (0.0008) -[2023-11-28 02:31:59,841][87424] Updated weights for policy 0, policy_version 88616 (0.0011) -[2023-11-28 02:32:00,216][87424] Updated weights for policy 0, policy_version 88626 (0.0011) -[2023-11-28 02:32:00,616][87424] Updated weights for policy 0, policy_version 88636 (0.0012) -[2023-11-28 02:32:01,080][87426] Updated weights for policy 1, policy_version 88520 (0.0011) -[2023-11-28 02:32:01,455][87426] Updated weights for policy 1, policy_version 88530 (0.0011) -[2023-11-28 02:32:01,839][87426] Updated weights for policy 1, policy_version 88540 (0.0011) -[2023-11-28 02:32:02,888][87424] Updated weights for policy 0, policy_version 88646 (0.0012) -[2023-11-28 02:32:03,266][87424] Updated weights for policy 0, policy_version 88656 (0.0012) -[2023-11-28 02:32:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45359104. Throughput: 0: 2754.2, 1: 2745.6. Samples: 45373188. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:32:03,445][86177] Avg episode reward: [(0, '-598.730'), (1, '-525.060')] -[2023-11-28 02:32:03,649][87424] Updated weights for policy 0, policy_version 88666 (0.0011) -[2023-11-28 02:32:03,918][87426] Updated weights for policy 1, policy_version 88550 (0.0010) -[2023-11-28 02:32:04,298][87426] Updated weights for policy 1, policy_version 88560 (0.0011) -[2023-11-28 02:32:04,675][87426] Updated weights for policy 1, policy_version 88570 (0.0011) -[2023-11-28 02:32:05,875][87424] Updated weights for policy 0, policy_version 88676 (0.0010) -[2023-11-28 02:32:06,259][87424] Updated weights for policy 0, policy_version 88686 (0.0011) -[2023-11-28 02:32:06,634][87424] Updated weights for policy 0, policy_version 88696 (0.0009) -[2023-11-28 02:32:07,198][87426] Updated weights for policy 1, policy_version 88580 (0.0009) -[2023-11-28 02:32:07,586][87426] Updated weights for policy 1, policy_version 88590 (0.0007) -[2023-11-28 02:32:07,966][87426] Updated weights for policy 1, policy_version 88600 (0.0008) -[2023-11-28 02:32:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45391872. Throughput: 0: 2751.6, 1: 2733.0. Samples: 45405036. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:32:08,445][86177] Avg episode reward: [(0, '-590.810'), (1, '-521.080')] -[2023-11-28 02:32:08,603][87424] Updated weights for policy 0, policy_version 88706 (0.0008) -[2023-11-28 02:32:08,975][87424] Updated weights for policy 0, policy_version 88716 (0.0011) -[2023-11-28 02:32:09,368][87424] Updated weights for policy 0, policy_version 88726 (0.0008) -[2023-11-28 02:32:09,745][87424] Updated weights for policy 0, policy_version 88736 (0.0008) -[2023-11-28 02:32:10,380][87426] Updated weights for policy 1, policy_version 88610 (0.0009) -[2023-11-28 02:32:10,759][87426] Updated weights for policy 1, policy_version 88620 (0.0012) -[2023-11-28 02:32:11,147][87426] Updated weights for policy 1, policy_version 88630 (0.0011) -[2023-11-28 02:32:11,527][87426] Updated weights for policy 1, policy_version 88640 (0.0012) -[2023-11-28 02:32:12,230][87424] Updated weights for policy 0, policy_version 88746 (0.0009) -[2023-11-28 02:32:12,617][87424] Updated weights for policy 0, policy_version 88756 (0.0011) -[2023-11-28 02:32:13,004][87424] Updated weights for policy 0, policy_version 88766 (0.0009) -[2023-11-28 02:32:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45416448. Throughput: 0: 2724.4, 1: 2726.9. Samples: 45428640. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:32:13,445][86177] Avg episode reward: [(0, '-554.050'), (1, '-518.640')] -[2023-11-28 02:32:14,094][87426] Updated weights for policy 1, policy_version 88650 (0.0008) -[2023-11-28 02:32:14,477][87426] Updated weights for policy 1, policy_version 88660 (0.0007) -[2023-11-28 02:32:14,877][87426] Updated weights for policy 1, policy_version 88670 (0.0007) -[2023-11-28 02:32:15,098][87424] Updated weights for policy 0, policy_version 88776 (0.0011) -[2023-11-28 02:32:15,473][87424] Updated weights for policy 0, policy_version 88786 (0.0012) -[2023-11-28 02:32:15,853][87424] Updated weights for policy 0, policy_version 88796 (0.0012) -[2023-11-28 02:32:17,408][87426] Updated weights for policy 1, policy_version 88680 (0.0011) -[2023-11-28 02:32:17,784][87426] Updated weights for policy 1, policy_version 88690 (0.0012) -[2023-11-28 02:32:18,150][87424] Updated weights for policy 0, policy_version 88806 (0.0009) -[2023-11-28 02:32:18,163][87426] Updated weights for policy 1, policy_version 88700 (0.0011) -[2023-11-28 02:32:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45441024. Throughput: 0: 2703.7, 1: 2714.6. Samples: 45452788. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:32:18,446][86177] Avg episode reward: [(0, '-555.610'), (1, '-499.530')] -[2023-11-28 02:32:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000088704_22708224.pth... -[2023-11-28 02:32:18,494][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000086144_22052864.pth -[2023-11-28 02:32:18,500][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000088704_22708224.pth -[2023-11-28 02:32:18,525][87424] Updated weights for policy 0, policy_version 88816 (0.0007) -[2023-11-28 02:32:18,908][87424] Updated weights for policy 0, policy_version 88826 (0.0008) -[2023-11-28 02:32:19,134][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000088832_22740992.pth... -[2023-11-28 02:32:19,180][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000086272_22085632.pth -[2023-11-28 02:32:19,187][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000088832_22740992.pth -[2023-11-28 02:32:20,115][87426] Updated weights for policy 1, policy_version 88710 (0.0012) -[2023-11-28 02:32:20,488][87426] Updated weights for policy 1, policy_version 88720 (0.0012) -[2023-11-28 02:32:20,873][87426] Updated weights for policy 1, policy_version 88730 (0.0011) -[2023-11-28 02:32:20,957][87424] Updated weights for policy 0, policy_version 88836 (0.0011) -[2023-11-28 02:32:21,334][87424] Updated weights for policy 0, policy_version 88846 (0.0011) -[2023-11-28 02:32:21,715][87424] Updated weights for policy 0, policy_version 88856 (0.0011) -[2023-11-28 02:32:23,215][87426] Updated weights for policy 1, policy_version 88740 (0.0010) -[2023-11-28 02:32:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 45465600. Throughput: 0: 2694.3, 1: 2695.1. Samples: 45484916. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:32:23,445][86177] Avg episode reward: [(0, '-513.950'), (1, '-499.890')] -[2023-11-28 02:32:23,590][87426] Updated weights for policy 1, policy_version 88750 (0.0008) -[2023-11-28 02:32:23,885][87424] Updated weights for policy 0, policy_version 88866 (0.0011) -[2023-11-28 02:32:23,970][87426] Updated weights for policy 1, policy_version 88760 (0.0007) -[2023-11-28 02:32:24,260][87424] Updated weights for policy 0, policy_version 88876 (0.0012) -[2023-11-28 02:32:24,645][87424] Updated weights for policy 0, policy_version 88886 (0.0012) -[2023-11-28 02:32:25,028][87424] Updated weights for policy 0, policy_version 88896 (0.0011) -[2023-11-28 02:32:25,964][87426] Updated weights for policy 1, policy_version 88770 (0.0009) -[2023-11-28 02:32:26,350][87426] Updated weights for policy 1, policy_version 88780 (0.0012) -[2023-11-28 02:32:26,730][87426] Updated weights for policy 1, policy_version 88790 (0.0009) -[2023-11-28 02:32:26,959][87424] Updated weights for policy 0, policy_version 88906 (0.0008) -[2023-11-28 02:32:27,110][87426] Updated weights for policy 1, policy_version 88800 (0.0009) -[2023-11-28 02:32:27,339][87424] Updated weights for policy 0, policy_version 88916 (0.0012) -[2023-11-28 02:32:27,714][87424] Updated weights for policy 0, policy_version 88926 (0.0010) -[2023-11-28 02:32:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45498368. Throughput: 0: 2700.8, 1: 2735.1. Samples: 45511624. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:32:28,445][86177] Avg episode reward: [(0, '-538.060'), (1, '-496.170')] -[2023-11-28 02:32:29,083][87426] Updated weights for policy 1, policy_version 88810 (0.0008) -[2023-11-28 02:32:29,456][87426] Updated weights for policy 1, policy_version 88820 (0.0009) -[2023-11-28 02:32:29,792][87424] Updated weights for policy 0, policy_version 88936 (0.0011) -[2023-11-28 02:32:29,843][87426] Updated weights for policy 1, policy_version 88830 (0.0008) -[2023-11-28 02:32:30,160][87424] Updated weights for policy 0, policy_version 88946 (0.0012) -[2023-11-28 02:32:30,544][87424] Updated weights for policy 0, policy_version 88956 (0.0012) -[2023-11-28 02:32:31,577][87426] Updated weights for policy 1, policy_version 88840 (0.0009) -[2023-11-28 02:32:31,960][87426] Updated weights for policy 1, policy_version 88850 (0.0011) -[2023-11-28 02:32:32,339][87426] Updated weights for policy 1, policy_version 88860 (0.0011) -[2023-11-28 02:32:32,865][87424] Updated weights for policy 0, policy_version 88966 (0.0011) -[2023-11-28 02:32:33,247][87424] Updated weights for policy 0, policy_version 88976 (0.0012) -[2023-11-28 02:32:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 45522944. Throughput: 0: 2731.9, 1: 2736.9. Samples: 45537588. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:32:33,445][86177] Avg episode reward: [(0, '-538.880'), (1, '-502.050')] -[2023-11-28 02:32:33,633][87424] Updated weights for policy 0, policy_version 88986 (0.0012) -[2023-11-28 02:32:34,381][87426] Updated weights for policy 1, policy_version 88870 (0.0009) -[2023-11-28 02:32:34,763][87426] Updated weights for policy 1, policy_version 88880 (0.0008) -[2023-11-28 02:32:35,145][87426] Updated weights for policy 1, policy_version 88890 (0.0008) -[2023-11-28 02:32:35,592][87424] Updated weights for policy 0, policy_version 88996 (0.0010) -[2023-11-28 02:32:35,972][87424] Updated weights for policy 0, policy_version 89006 (0.0010) -[2023-11-28 02:32:36,351][87424] Updated weights for policy 0, policy_version 89016 (0.0010) -[2023-11-28 02:32:37,396][87426] Updated weights for policy 1, policy_version 88900 (0.0009) -[2023-11-28 02:32:37,781][87426] Updated weights for policy 1, policy_version 88910 (0.0011) -[2023-11-28 02:32:38,154][87426] Updated weights for policy 1, policy_version 88920 (0.0012) -[2023-11-28 02:32:38,351][87424] Updated weights for policy 0, policy_version 89026 (0.0010) -[2023-11-28 02:32:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45547520. Throughput: 0: 2766.7, 1: 2726.1. Samples: 45570708. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:32:38,445][86177] Avg episode reward: [(0, '-528.170'), (1, '-509.360')] -[2023-11-28 02:32:38,727][87424] Updated weights for policy 0, policy_version 89036 (0.0011) -[2023-11-28 02:32:39,106][87424] Updated weights for policy 0, policy_version 89046 (0.0007) -[2023-11-28 02:32:39,488][87424] Updated weights for policy 0, policy_version 89056 (0.0010) -[2023-11-28 02:32:40,228][87426] Updated weights for policy 1, policy_version 88930 (0.0012) -[2023-11-28 02:32:40,605][87426] Updated weights for policy 1, policy_version 88940 (0.0012) -[2023-11-28 02:32:40,976][87426] Updated weights for policy 1, policy_version 88950 (0.0012) -[2023-11-28 02:32:41,353][87426] Updated weights for policy 1, policy_version 88960 (0.0012) -[2023-11-28 02:32:41,607][87424] Updated weights for policy 0, policy_version 89066 (0.0012) -[2023-11-28 02:32:41,987][87424] Updated weights for policy 0, policy_version 89076 (0.0011) -[2023-11-28 02:32:42,380][87424] Updated weights for policy 0, policy_version 89086 (0.0012) -[2023-11-28 02:32:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45580288. Throughput: 0: 2775.5, 1: 2702.1. Samples: 45594468. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:32:43,445][86177] Avg episode reward: [(0, '-527.150'), (1, '-510.800')] -[2023-11-28 02:32:43,732][87426] Updated weights for policy 1, policy_version 88970 (0.0012) -[2023-11-28 02:32:44,110][87426] Updated weights for policy 1, policy_version 88980 (0.0012) -[2023-11-28 02:32:44,491][87426] Updated weights for policy 1, policy_version 88990 (0.0011) -[2023-11-28 02:32:44,639][87424] Updated weights for policy 0, policy_version 89096 (0.0008) -[2023-11-28 02:32:45,023][87424] Updated weights for policy 0, policy_version 89106 (0.0007) -[2023-11-28 02:32:45,407][87424] Updated weights for policy 0, policy_version 89116 (0.0008) -[2023-11-28 02:32:46,988][87426] Updated weights for policy 1, policy_version 89000 (0.0009) -[2023-11-28 02:32:47,333][87424] Updated weights for policy 0, policy_version 89126 (0.0011) -[2023-11-28 02:32:47,362][87426] Updated weights for policy 1, policy_version 89010 (0.0007) -[2023-11-28 02:32:47,717][87424] Updated weights for policy 0, policy_version 89136 (0.0010) -[2023-11-28 02:32:47,745][87426] Updated weights for policy 1, policy_version 89020 (0.0007) -[2023-11-28 02:32:48,127][87424] Updated weights for policy 0, policy_version 89146 (0.0007) -[2023-11-28 02:32:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 45613056. Throughput: 0: 2779.7, 1: 2689.3. Samples: 45619292. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:32:48,445][86177] Avg episode reward: [(0, '-502.540'), (1, '-517.230')] -[2023-11-28 02:32:50,158][87426] Updated weights for policy 1, policy_version 89030 (0.0009) -[2023-11-28 02:32:50,262][87424] Updated weights for policy 0, policy_version 89156 (0.0009) -[2023-11-28 02:32:50,543][87426] Updated weights for policy 1, policy_version 89040 (0.0010) -[2023-11-28 02:32:50,646][87424] Updated weights for policy 0, policy_version 89166 (0.0010) -[2023-11-28 02:32:50,919][87426] Updated weights for policy 1, policy_version 89050 (0.0008) -[2023-11-28 02:32:51,027][87424] Updated weights for policy 0, policy_version 89176 (0.0011) -[2023-11-28 02:32:52,840][87426] Updated weights for policy 1, policy_version 89060 (0.0009) -[2023-11-28 02:32:53,075][87424] Updated weights for policy 0, policy_version 89186 (0.0010) -[2023-11-28 02:32:53,231][87426] Updated weights for policy 1, policy_version 89070 (0.0012) -[2023-11-28 02:32:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 45629440. Throughput: 0: 2790.0, 1: 2712.3. Samples: 45652640. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:32:53,445][86177] Avg episode reward: [(0, '-517.970'), (1, '-521.750')] -[2023-11-28 02:32:53,463][87424] Updated weights for policy 0, policy_version 89196 (0.0010) -[2023-11-28 02:32:53,610][87426] Updated weights for policy 1, policy_version 89080 (0.0011) -[2023-11-28 02:32:53,847][87424] Updated weights for policy 0, policy_version 89206 (0.0012) -[2023-11-28 02:32:54,231][87424] Updated weights for policy 0, policy_version 89216 (0.0007) -[2023-11-28 02:32:55,609][87426] Updated weights for policy 1, policy_version 89090 (0.0009) -[2023-11-28 02:32:55,985][87426] Updated weights for policy 1, policy_version 89100 (0.0008) -[2023-11-28 02:32:56,369][87426] Updated weights for policy 1, policy_version 89110 (0.0007) -[2023-11-28 02:32:56,524][87424] Updated weights for policy 0, policy_version 89226 (0.0011) -[2023-11-28 02:32:56,747][87426] Updated weights for policy 1, policy_version 89120 (0.0007) -[2023-11-28 02:32:56,910][87424] Updated weights for policy 0, policy_version 89236 (0.0011) -[2023-11-28 02:32:57,296][87424] Updated weights for policy 0, policy_version 89246 (0.0012) -[2023-11-28 02:32:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 45662208. Throughput: 0: 2792.7, 1: 2736.7. Samples: 45677464. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:32:58,446][86177] Avg episode reward: [(0, '-537.050'), (1, '-516.350')] -[2023-11-28 02:32:58,963][87426] Updated weights for policy 1, policy_version 89130 (0.0008) -[2023-11-28 02:32:59,347][87426] Updated weights for policy 1, policy_version 89140 (0.0007) -[2023-11-28 02:32:59,656][87424] Updated weights for policy 0, policy_version 89256 (0.0012) -[2023-11-28 02:32:59,728][87426] Updated weights for policy 1, policy_version 89150 (0.0011) -[2023-11-28 02:33:00,046][87424] Updated weights for policy 0, policy_version 89266 (0.0010) -[2023-11-28 02:33:00,422][87424] Updated weights for policy 0, policy_version 89276 (0.0008) -[2023-11-28 02:33:02,037][87426] Updated weights for policy 1, policy_version 89160 (0.0010) -[2023-11-28 02:33:02,413][87426] Updated weights for policy 1, policy_version 89170 (0.0009) -[2023-11-28 02:33:02,794][87426] Updated weights for policy 1, policy_version 89180 (0.0007) -[2023-11-28 02:33:02,922][87424] Updated weights for policy 0, policy_version 89286 (0.0010) -[2023-11-28 02:33:03,305][87424] Updated weights for policy 0, policy_version 89296 (0.0007) -[2023-11-28 02:33:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45686784. Throughput: 0: 2782.4, 1: 2742.6. Samples: 45701412. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:33:03,445][86177] Avg episode reward: [(0, '-533.920'), (1, '-552.270')] -[2023-11-28 02:33:03,687][87424] Updated weights for policy 0, policy_version 89306 (0.0008) -[2023-11-28 02:33:04,580][87426] Updated weights for policy 1, policy_version 89190 (0.0008) -[2023-11-28 02:33:04,951][87426] Updated weights for policy 1, policy_version 89200 (0.0009) -[2023-11-28 02:33:05,330][87426] Updated weights for policy 1, policy_version 89210 (0.0007) -[2023-11-28 02:33:05,856][87424] Updated weights for policy 0, policy_version 89316 (0.0009) -[2023-11-28 02:33:06,244][87424] Updated weights for policy 0, policy_version 89326 (0.0012) -[2023-11-28 02:33:06,630][87424] Updated weights for policy 0, policy_version 89336 (0.0011) -[2023-11-28 02:33:07,685][87426] Updated weights for policy 1, policy_version 89220 (0.0008) -[2023-11-28 02:33:08,060][87426] Updated weights for policy 1, policy_version 89230 (0.0011) -[2023-11-28 02:33:08,442][87426] Updated weights for policy 1, policy_version 89240 (0.0009) -[2023-11-28 02:33:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 45711360. Throughput: 0: 2767.1, 1: 2755.1. Samples: 45733416. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:33:08,445][86177] Avg episode reward: [(0, '-531.150'), (1, '-550.420')] -[2023-11-28 02:33:09,038][87424] Updated weights for policy 0, policy_version 89346 (0.0010) -[2023-11-28 02:33:09,418][87424] Updated weights for policy 0, policy_version 89356 (0.0007) -[2023-11-28 02:33:09,801][87424] Updated weights for policy 0, policy_version 89366 (0.0010) -[2023-11-28 02:33:10,192][87424] Updated weights for policy 0, policy_version 89376 (0.0012) -[2023-11-28 02:33:10,964][87426] Updated weights for policy 1, policy_version 89250 (0.0008) -[2023-11-28 02:33:11,349][87426] Updated weights for policy 1, policy_version 89260 (0.0010) -[2023-11-28 02:33:11,725][87426] Updated weights for policy 1, policy_version 89270 (0.0010) -[2023-11-28 02:33:12,042][87424] Updated weights for policy 0, policy_version 89386 (0.0011) -[2023-11-28 02:33:12,103][87426] Updated weights for policy 1, policy_version 89280 (0.0011) -[2023-11-28 02:33:12,433][87424] Updated weights for policy 0, policy_version 89396 (0.0011) -[2023-11-28 02:33:12,808][87424] Updated weights for policy 0, policy_version 89406 (0.0009) -[2023-11-28 02:33:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45744128. Throughput: 0: 2753.4, 1: 2705.1. Samples: 45757256. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:33:13,446][86177] Avg episode reward: [(0, '-518.820'), (1, '-552.940')] -[2023-11-28 02:33:14,014][87426] Updated weights for policy 1, policy_version 89290 (0.0008) -[2023-11-28 02:33:14,387][87426] Updated weights for policy 1, policy_version 89300 (0.0007) -[2023-11-28 02:33:14,767][87426] Updated weights for policy 1, policy_version 89310 (0.0008) -[2023-11-28 02:33:14,982][87424] Updated weights for policy 0, policy_version 89416 (0.0008) -[2023-11-28 02:33:15,364][87424] Updated weights for policy 0, policy_version 89426 (0.0008) -[2023-11-28 02:33:15,754][87424] Updated weights for policy 0, policy_version 89436 (0.0010) -[2023-11-28 02:33:17,298][87426] Updated weights for policy 1, policy_version 89320 (0.0008) -[2023-11-28 02:33:17,682][87426] Updated weights for policy 1, policy_version 89330 (0.0007) -[2023-11-28 02:33:18,063][87426] Updated weights for policy 1, policy_version 89340 (0.0007) -[2023-11-28 02:33:18,171][87424] Updated weights for policy 0, policy_version 89446 (0.0008) -[2023-11-28 02:33:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 45768704. Throughput: 0: 2740.7, 1: 2662.4. Samples: 45780728. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:33:18,445][86177] Avg episode reward: [(0, '-502.100'), (1, '-554.270')] -[2023-11-28 02:33:18,559][87424] Updated weights for policy 0, policy_version 89456 (0.0007) -[2023-11-28 02:33:18,944][87424] Updated weights for policy 0, policy_version 89466 (0.0008) -[2023-11-28 02:33:20,229][87426] Updated weights for policy 1, policy_version 89350 (0.0008) -[2023-11-28 02:33:20,608][87426] Updated weights for policy 1, policy_version 89360 (0.0009) -[2023-11-28 02:33:20,880][87424] Updated weights for policy 0, policy_version 89476 (0.0009) -[2023-11-28 02:33:20,979][87426] Updated weights for policy 1, policy_version 89370 (0.0012) -[2023-11-28 02:33:21,264][87424] Updated weights for policy 0, policy_version 89486 (0.0008) -[2023-11-28 02:33:21,649][87424] Updated weights for policy 0, policy_version 89496 (0.0008) -[2023-11-28 02:33:23,382][87426] Updated weights for policy 1, policy_version 89380 (0.0012) -[2023-11-28 02:33:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45793280. Throughput: 0: 2716.9, 1: 2663.2. Samples: 45812812. Policy #0 lag: (min: 6.0, avg: 31.6, max: 60.0) -[2023-11-28 02:33:23,445][86177] Avg episode reward: [(0, '-503.250'), (1, '-521.380')] -[2023-11-28 02:33:23,756][87426] Updated weights for policy 1, policy_version 89390 (0.0012) -[2023-11-28 02:33:23,975][87424] Updated weights for policy 0, policy_version 89506 (0.0010) -[2023-11-28 02:33:24,149][87426] Updated weights for policy 1, policy_version 89400 (0.0011) -[2023-11-28 02:33:24,362][87424] Updated weights for policy 0, policy_version 89516 (0.0012) -[2023-11-28 02:33:24,755][87424] Updated weights for policy 0, policy_version 89526 (0.0011) -[2023-11-28 02:33:25,128][87424] Updated weights for policy 0, policy_version 89536 (0.0012) -[2023-11-28 02:33:26,605][87426] Updated weights for policy 1, policy_version 89410 (0.0011) -[2023-11-28 02:33:26,988][87426] Updated weights for policy 1, policy_version 89420 (0.0012) -[2023-11-28 02:33:27,282][87424] Updated weights for policy 0, policy_version 89546 (0.0010) -[2023-11-28 02:33:27,369][87426] Updated weights for policy 1, policy_version 89430 (0.0012) -[2023-11-28 02:33:27,668][87424] Updated weights for policy 0, policy_version 89556 (0.0011) -[2023-11-28 02:33:27,742][87426] Updated weights for policy 1, policy_version 89440 (0.0011) -[2023-11-28 02:33:28,056][87424] Updated weights for policy 0, policy_version 89566 (0.0012) -[2023-11-28 02:33:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45826048. Throughput: 0: 2707.1, 1: 2689.8. Samples: 45837328. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:33:28,445][86177] Avg episode reward: [(0, '-506.100'), (1, '-521.340')] -[2023-11-28 02:33:29,525][87426] Updated weights for policy 1, policy_version 89450 (0.0012) -[2023-11-28 02:33:29,901][87426] Updated weights for policy 1, policy_version 89460 (0.0011) -[2023-11-28 02:33:29,944][87424] Updated weights for policy 0, policy_version 89576 (0.0011) -[2023-11-28 02:33:30,285][87426] Updated weights for policy 1, policy_version 89470 (0.0008) -[2023-11-28 02:33:30,329][87424] Updated weights for policy 0, policy_version 89586 (0.0012) -[2023-11-28 02:33:30,727][87424] Updated weights for policy 0, policy_version 89596 (0.0012) -[2023-11-28 02:33:32,172][87426] Updated weights for policy 1, policy_version 89480 (0.0010) -[2023-11-28 02:33:32,552][87426] Updated weights for policy 1, policy_version 89490 (0.0010) -[2023-11-28 02:33:32,590][87424] Updated weights for policy 0, policy_version 89606 (0.0012) -[2023-11-28 02:33:32,936][87426] Updated weights for policy 1, policy_version 89500 (0.0009) -[2023-11-28 02:33:32,959][87424] Updated weights for policy 0, policy_version 89616 (0.0011) -[2023-11-28 02:33:33,342][87424] Updated weights for policy 0, policy_version 89626 (0.0012) -[2023-11-28 02:33:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 45850624. Throughput: 0: 2693.0, 1: 2718.9. Samples: 45862828. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:33:33,445][86177] Avg episode reward: [(0, '-510.880'), (1, '-520.290')] -[2023-11-28 02:33:35,242][87426] Updated weights for policy 1, policy_version 89510 (0.0011) -[2023-11-28 02:33:35,361][87424] Updated weights for policy 0, policy_version 89636 (0.0010) -[2023-11-28 02:33:35,623][87426] Updated weights for policy 1, policy_version 89520 (0.0009) -[2023-11-28 02:33:35,744][87424] Updated weights for policy 0, policy_version 89646 (0.0008) -[2023-11-28 02:33:36,009][87426] Updated weights for policy 1, policy_version 89530 (0.0007) -[2023-11-28 02:33:36,121][87424] Updated weights for policy 0, policy_version 89656 (0.0010) -[2023-11-28 02:33:38,268][87424] Updated weights for policy 0, policy_version 89666 (0.0011) -[2023-11-28 02:33:38,299][87426] Updated weights for policy 1, policy_version 89540 (0.0009) -[2023-11-28 02:33:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45875200. Throughput: 0: 2697.8, 1: 2717.7. Samples: 45896336. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:33:38,445][86177] Avg episode reward: [(0, '-517.610'), (1, '-524.000')] -[2023-11-28 02:33:38,650][87424] Updated weights for policy 0, policy_version 89676 (0.0009) -[2023-11-28 02:33:38,689][87426] Updated weights for policy 1, policy_version 89550 (0.0009) -[2023-11-28 02:33:39,040][87424] Updated weights for policy 0, policy_version 89686 (0.0012) -[2023-11-28 02:33:39,057][87426] Updated weights for policy 1, policy_version 89560 (0.0009) -[2023-11-28 02:33:39,416][87424] Updated weights for policy 0, policy_version 89696 (0.0011) -[2023-11-28 02:33:41,435][87426] Updated weights for policy 1, policy_version 89570 (0.0011) -[2023-11-28 02:33:41,723][87424] Updated weights for policy 0, policy_version 89706 (0.0012) -[2023-11-28 02:33:41,813][87426] Updated weights for policy 1, policy_version 89580 (0.0011) -[2023-11-28 02:33:42,117][87424] Updated weights for policy 0, policy_version 89716 (0.0016) -[2023-11-28 02:33:42,196][87426] Updated weights for policy 1, policy_version 89590 (0.0011) -[2023-11-28 02:33:42,498][87424] Updated weights for policy 0, policy_version 89726 (0.0011) -[2023-11-28 02:33:42,579][87426] Updated weights for policy 1, policy_version 89600 (0.0010) -[2023-11-28 02:33:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45907968. Throughput: 0: 2708.9, 1: 2698.5. Samples: 45920796. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:33:43,445][86177] Avg episode reward: [(0, '-523.120'), (1, '-546.780')] -[2023-11-28 02:33:44,665][87426] Updated weights for policy 1, policy_version 89610 (0.0011) -[2023-11-28 02:33:44,697][87424] Updated weights for policy 0, policy_version 89736 (0.0009) -[2023-11-28 02:33:45,044][87426] Updated weights for policy 1, policy_version 89620 (0.0012) -[2023-11-28 02:33:45,083][87424] Updated weights for policy 0, policy_version 89746 (0.0007) -[2023-11-28 02:33:45,415][87426] Updated weights for policy 1, policy_version 89630 (0.0011) -[2023-11-28 02:33:45,456][87424] Updated weights for policy 0, policy_version 89756 (0.0008) -[2023-11-28 02:33:47,181][87426] Updated weights for policy 1, policy_version 89640 (0.0010) -[2023-11-28 02:33:47,376][87424] Updated weights for policy 0, policy_version 89766 (0.0010) -[2023-11-28 02:33:47,561][87426] Updated weights for policy 1, policy_version 89650 (0.0011) -[2023-11-28 02:33:47,759][87424] Updated weights for policy 0, policy_version 89776 (0.0008) -[2023-11-28 02:33:47,943][87426] Updated weights for policy 1, policy_version 89660 (0.0010) -[2023-11-28 02:33:48,150][87424] Updated weights for policy 0, policy_version 89786 (0.0009) -[2023-11-28 02:33:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 45940736. Throughput: 0: 2714.4, 1: 2702.9. Samples: 45945192. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:33:48,445][86177] Avg episode reward: [(0, '-520.870'), (1, '-541.430')] -[2023-11-28 02:33:50,417][87426] Updated weights for policy 1, policy_version 89670 (0.0009) -[2023-11-28 02:33:50,713][87424] Updated weights for policy 0, policy_version 89796 (0.0010) -[2023-11-28 02:33:50,796][87426] Updated weights for policy 1, policy_version 89680 (0.0012) -[2023-11-28 02:33:51,102][87424] Updated weights for policy 0, policy_version 89806 (0.0010) -[2023-11-28 02:33:51,177][87426] Updated weights for policy 1, policy_version 89690 (0.0010) -[2023-11-28 02:33:51,478][87424] Updated weights for policy 0, policy_version 89816 (0.0012) -[2023-11-28 02:33:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 45957120. Throughput: 0: 2715.0, 1: 2696.2. Samples: 45976920. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:33:53,445][86177] Avg episode reward: [(0, '-525.560'), (1, '-549.070')] -[2023-11-28 02:33:53,565][87426] Updated weights for policy 1, policy_version 89700 (0.0011) -[2023-11-28 02:33:53,794][87424] Updated weights for policy 0, policy_version 89826 (0.0010) -[2023-11-28 02:33:53,944][87426] Updated weights for policy 1, policy_version 89710 (0.0018) -[2023-11-28 02:33:54,176][87424] Updated weights for policy 0, policy_version 89836 (0.0012) -[2023-11-28 02:33:54,322][87426] Updated weights for policy 1, policy_version 89720 (0.0009) -[2023-11-28 02:33:54,562][87424] Updated weights for policy 0, policy_version 89846 (0.0008) -[2023-11-28 02:33:54,943][87424] Updated weights for policy 0, policy_version 89856 (0.0008) -[2023-11-28 02:33:56,338][87426] Updated weights for policy 1, policy_version 89730 (0.0008) -[2023-11-28 02:33:56,716][87426] Updated weights for policy 1, policy_version 89740 (0.0012) -[2023-11-28 02:33:57,091][87426] Updated weights for policy 1, policy_version 89750 (0.0012) -[2023-11-28 02:33:57,460][87426] Updated weights for policy 1, policy_version 89760 (0.0012) -[2023-11-28 02:33:57,476][87424] Updated weights for policy 0, policy_version 89866 (0.0007) -[2023-11-28 02:33:57,861][87424] Updated weights for policy 0, policy_version 89876 (0.0008) -[2023-11-28 02:33:58,241][87424] Updated weights for policy 0, policy_version 89886 (0.0007) -[2023-11-28 02:33:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 45989888. Throughput: 0: 2699.7, 1: 2732.6. Samples: 46001712. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:33:58,446][86177] Avg episode reward: [(0, '-515.950'), (1, '-546.150')] -[2023-11-28 02:33:59,615][87426] Updated weights for policy 1, policy_version 89770 (0.0008) -[2023-11-28 02:34:00,001][87426] Updated weights for policy 1, policy_version 89780 (0.0008) -[2023-11-28 02:34:00,353][87424] Updated weights for policy 0, policy_version 89896 (0.0011) -[2023-11-28 02:34:00,391][87426] Updated weights for policy 1, policy_version 89790 (0.0010) -[2023-11-28 02:34:00,718][87424] Updated weights for policy 0, policy_version 89906 (0.0012) -[2023-11-28 02:34:01,097][87424] Updated weights for policy 0, policy_version 89916 (0.0011) -[2023-11-28 02:34:02,691][87426] Updated weights for policy 1, policy_version 89800 (0.0009) -[2023-11-28 02:34:03,063][87426] Updated weights for policy 1, policy_version 89810 (0.0010) -[2023-11-28 02:34:03,385][87424] Updated weights for policy 0, policy_version 89926 (0.0012) -[2023-11-28 02:34:03,440][87426] Updated weights for policy 1, policy_version 89820 (0.0012) -[2023-11-28 02:34:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 46006272. Throughput: 0: 2689.2, 1: 2746.1. Samples: 46025316. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:34:03,445][86177] Avg episode reward: [(0, '-537.650'), (1, '-524.640')] -[2023-11-28 02:34:03,767][87424] Updated weights for policy 0, policy_version 89936 (0.0009) -[2023-11-28 02:34:04,155][87424] Updated weights for policy 0, policy_version 89946 (0.0007) -[2023-11-28 02:34:05,288][87426] Updated weights for policy 1, policy_version 89830 (0.0012) -[2023-11-28 02:34:05,666][87426] Updated weights for policy 1, policy_version 89840 (0.0012) -[2023-11-28 02:34:06,047][87426] Updated weights for policy 1, policy_version 89850 (0.0009) -[2023-11-28 02:34:06,414][87424] Updated weights for policy 0, policy_version 89956 (0.0009) -[2023-11-28 02:34:06,802][87424] Updated weights for policy 0, policy_version 89966 (0.0012) -[2023-11-28 02:34:07,177][87424] Updated weights for policy 0, policy_version 89976 (0.0012) -[2023-11-28 02:34:07,899][87426] Updated weights for policy 1, policy_version 89860 (0.0009) -[2023-11-28 02:34:08,273][87426] Updated weights for policy 1, policy_version 89870 (0.0012) -[2023-11-28 02:34:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 46039040. Throughput: 0: 2697.2, 1: 2759.9. Samples: 46058380. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:34:08,446][86177] Avg episode reward: [(0, '-541.000'), (1, '-521.160')] -[2023-11-28 02:34:08,652][87426] Updated weights for policy 1, policy_version 89880 (0.0008) -[2023-11-28 02:34:09,221][87424] Updated weights for policy 0, policy_version 89986 (0.0012) -[2023-11-28 02:34:09,609][87424] Updated weights for policy 0, policy_version 89996 (0.0012) -[2023-11-28 02:34:09,992][87424] Updated weights for policy 0, policy_version 90006 (0.0012) -[2023-11-28 02:34:10,375][87424] Updated weights for policy 0, policy_version 90016 (0.0012) -[2023-11-28 02:34:11,033][87426] Updated weights for policy 1, policy_version 89890 (0.0010) -[2023-11-28 02:34:11,424][87426] Updated weights for policy 1, policy_version 89900 (0.0011) -[2023-11-28 02:34:11,793][87426] Updated weights for policy 1, policy_version 89910 (0.0010) -[2023-11-28 02:34:12,174][87426] Updated weights for policy 1, policy_version 89920 (0.0012) -[2023-11-28 02:34:12,338][87424] Updated weights for policy 0, policy_version 90026 (0.0010) -[2023-11-28 02:34:12,712][87424] Updated weights for policy 0, policy_version 90036 (0.0011) -[2023-11-28 02:34:13,098][87424] Updated weights for policy 0, policy_version 90046 (0.0010) -[2023-11-28 02:34:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46071808. Throughput: 0: 2707.3, 1: 2723.8. Samples: 46081728. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:34:13,445][86177] Avg episode reward: [(0, '-540.360'), (1, '-502.910')] -[2023-11-28 02:34:14,684][87426] Updated weights for policy 1, policy_version 89930 (0.0007) -[2023-11-28 02:34:15,074][87426] Updated weights for policy 1, policy_version 89940 (0.0008) -[2023-11-28 02:34:15,456][87426] Updated weights for policy 1, policy_version 89950 (0.0011) -[2023-11-28 02:34:15,638][87424] Updated weights for policy 0, policy_version 90056 (0.0012) -[2023-11-28 02:34:16,020][87424] Updated weights for policy 0, policy_version 90066 (0.0012) -[2023-11-28 02:34:16,422][87424] Updated weights for policy 0, policy_version 90076 (0.0012) -[2023-11-28 02:34:17,455][87426] Updated weights for policy 1, policy_version 89960 (0.0009) -[2023-11-28 02:34:17,831][87426] Updated weights for policy 1, policy_version 89970 (0.0007) -[2023-11-28 02:34:18,118][87424] Updated weights for policy 0, policy_version 90086 (0.0012) -[2023-11-28 02:34:18,209][87426] Updated weights for policy 1, policy_version 89980 (0.0010) -[2023-11-28 02:34:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46096384. Throughput: 0: 2701.9, 1: 2711.5. Samples: 46106428. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:34:18,446][86177] Avg episode reward: [(0, '-540.840'), (1, '-515.600')] -[2023-11-28 02:34:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000089984_23035904.pth... -[2023-11-28 02:34:18,499][87424] Updated weights for policy 0, policy_version 90096 (0.0012) -[2023-11-28 02:34:18,506][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000087424_22380544.pth -[2023-11-28 02:34:18,881][87424] Updated weights for policy 0, policy_version 90106 (0.0012) -[2023-11-28 02:34:19,109][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000090112_23068672.pth... -[2023-11-28 02:34:19,141][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000087520_22405120.pth -[2023-11-28 02:34:19,906][87426] Updated weights for policy 1, policy_version 89990 (0.0009) -[2023-11-28 02:34:20,289][87426] Updated weights for policy 1, policy_version 90000 (0.0008) -[2023-11-28 02:34:20,662][87426] Updated weights for policy 1, policy_version 90010 (0.0010) -[2023-11-28 02:34:21,177][87424] Updated weights for policy 0, policy_version 90116 (0.0010) -[2023-11-28 02:34:21,561][87424] Updated weights for policy 0, policy_version 90126 (0.0008) -[2023-11-28 02:34:21,946][87424] Updated weights for policy 0, policy_version 90136 (0.0010) -[2023-11-28 02:34:23,219][87426] Updated weights for policy 1, policy_version 90020 (0.0009) -[2023-11-28 02:34:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 46120960. Throughput: 0: 2684.2, 1: 2715.9. Samples: 46139340. Policy #0 lag: (min: 43.0, avg: 57.9, max: 81.0) -[2023-11-28 02:34:23,445][86177] Avg episode reward: [(0, '-517.540'), (1, '-516.550')] -[2023-11-28 02:34:23,607][87426] Updated weights for policy 1, policy_version 90030 (0.0008) -[2023-11-28 02:34:23,823][87424] Updated weights for policy 0, policy_version 90146 (0.0009) -[2023-11-28 02:34:23,985][87426] Updated weights for policy 1, policy_version 90040 (0.0008) -[2023-11-28 02:34:24,200][87424] Updated weights for policy 0, policy_version 90156 (0.0012) -[2023-11-28 02:34:24,580][87424] Updated weights for policy 0, policy_version 90166 (0.0011) -[2023-11-28 02:34:24,972][87424] Updated weights for policy 0, policy_version 90176 (0.0008) -[2023-11-28 02:34:26,061][87426] Updated weights for policy 1, policy_version 90050 (0.0009) -[2023-11-28 02:34:26,453][87426] Updated weights for policy 1, policy_version 90060 (0.0012) -[2023-11-28 02:34:26,835][87426] Updated weights for policy 1, policy_version 90070 (0.0011) -[2023-11-28 02:34:26,930][87424] Updated weights for policy 0, policy_version 90186 (0.0011) -[2023-11-28 02:34:27,213][87426] Updated weights for policy 1, policy_version 90080 (0.0012) -[2023-11-28 02:34:27,316][87424] Updated weights for policy 0, policy_version 90196 (0.0012) -[2023-11-28 02:34:27,713][87424] Updated weights for policy 0, policy_version 90206 (0.0011) -[2023-11-28 02:34:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46153728. Throughput: 0: 2684.0, 1: 2733.2. Samples: 46164572. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:34:28,445][86177] Avg episode reward: [(0, '-515.130'), (1, '-520.070')] -[2023-11-28 02:34:29,244][87426] Updated weights for policy 1, policy_version 90090 (0.0011) -[2023-11-28 02:34:29,622][87426] Updated weights for policy 1, policy_version 90100 (0.0011) -[2023-11-28 02:34:30,003][87426] Updated weights for policy 1, policy_version 90110 (0.0012) -[2023-11-28 02:34:30,194][87424] Updated weights for policy 0, policy_version 90216 (0.0012) -[2023-11-28 02:34:30,583][87424] Updated weights for policy 0, policy_version 90226 (0.0012) -[2023-11-28 02:34:30,956][87424] Updated weights for policy 0, policy_version 90236 (0.0012) -[2023-11-28 02:34:32,118][87426] Updated weights for policy 1, policy_version 90120 (0.0010) -[2023-11-28 02:34:32,500][87426] Updated weights for policy 1, policy_version 90130 (0.0009) -[2023-11-28 02:34:32,857][87424] Updated weights for policy 0, policy_version 90246 (0.0011) -[2023-11-28 02:34:32,875][87426] Updated weights for policy 1, policy_version 90140 (0.0010) -[2023-11-28 02:34:33,243][87424] Updated weights for policy 0, policy_version 90256 (0.0011) -[2023-11-28 02:34:33,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46178304. Throughput: 0: 2697.3, 1: 2732.2. Samples: 46189520. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:34:33,446][86177] Avg episode reward: [(0, '-500.810'), (1, '-529.060')] -[2023-11-28 02:34:33,630][87424] Updated weights for policy 0, policy_version 90266 (0.0010) -[2023-11-28 02:34:34,548][87426] Updated weights for policy 1, policy_version 90150 (0.0012) -[2023-11-28 02:34:34,931][87426] Updated weights for policy 1, policy_version 90160 (0.0011) -[2023-11-28 02:34:35,311][87426] Updated weights for policy 1, policy_version 90170 (0.0011) -[2023-11-28 02:34:35,659][87424] Updated weights for policy 0, policy_version 90276 (0.0008) -[2023-11-28 02:34:36,042][87424] Updated weights for policy 0, policy_version 90286 (0.0008) -[2023-11-28 02:34:36,427][87424] Updated weights for policy 0, policy_version 90296 (0.0008) -[2023-11-28 02:34:37,405][87426] Updated weights for policy 1, policy_version 90180 (0.0012) -[2023-11-28 02:34:37,777][87426] Updated weights for policy 1, policy_version 90190 (0.0012) -[2023-11-28 02:34:38,144][87426] Updated weights for policy 1, policy_version 90200 (0.0012) -[2023-11-28 02:34:38,351][87424] Updated weights for policy 0, policy_version 90306 (0.0010) -[2023-11-28 02:34:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 46211072. Throughput: 0: 2736.9, 1: 2768.9. Samples: 46224680. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:34:38,445][86177] Avg episode reward: [(0, '-500.920'), (1, '-516.470')] -[2023-11-28 02:34:38,740][87424] Updated weights for policy 0, policy_version 90316 (0.0010) -[2023-11-28 02:34:39,136][87424] Updated weights for policy 0, policy_version 90326 (0.0011) -[2023-11-28 02:34:39,512][87424] Updated weights for policy 0, policy_version 90336 (0.0012) -[2023-11-28 02:34:40,655][87426] Updated weights for policy 1, policy_version 90210 (0.0011) -[2023-11-28 02:34:41,031][87426] Updated weights for policy 1, policy_version 90220 (0.0007) -[2023-11-28 02:34:41,421][87426] Updated weights for policy 1, policy_version 90230 (0.0008) -[2023-11-28 02:34:41,784][87424] Updated weights for policy 0, policy_version 90346 (0.0011) -[2023-11-28 02:34:41,788][87426] Updated weights for policy 1, policy_version 90240 (0.0010) -[2023-11-28 02:34:42,170][87424] Updated weights for policy 0, policy_version 90356 (0.0011) -[2023-11-28 02:34:42,547][87424] Updated weights for policy 0, policy_version 90366 (0.0012) -[2023-11-28 02:34:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46235648. Throughput: 0: 2750.9, 1: 2748.6. Samples: 46249192. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:34:43,445][86177] Avg episode reward: [(0, '-507.700'), (1, '-515.700')] -[2023-11-28 02:34:44,158][87426] Updated weights for policy 1, policy_version 90250 (0.0012) -[2023-11-28 02:34:44,534][87426] Updated weights for policy 1, policy_version 90260 (0.0011) -[2023-11-28 02:34:44,699][87424] Updated weights for policy 0, policy_version 90376 (0.0010) -[2023-11-28 02:34:44,918][87426] Updated weights for policy 1, policy_version 90270 (0.0011) -[2023-11-28 02:34:45,090][87424] Updated weights for policy 0, policy_version 90386 (0.0008) -[2023-11-28 02:34:45,460][87424] Updated weights for policy 0, policy_version 90396 (0.0008) -[2023-11-28 02:34:46,857][87426] Updated weights for policy 1, policy_version 90280 (0.0012) -[2023-11-28 02:34:47,200][87424] Updated weights for policy 0, policy_version 90406 (0.0008) -[2023-11-28 02:34:47,234][87426] Updated weights for policy 1, policy_version 90290 (0.0011) -[2023-11-28 02:34:47,584][87424] Updated weights for policy 0, policy_version 90416 (0.0007) -[2023-11-28 02:34:47,618][87426] Updated weights for policy 1, policy_version 90300 (0.0011) -[2023-11-28 02:34:47,982][87424] Updated weights for policy 0, policy_version 90426 (0.0007) -[2023-11-28 02:34:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 46268416. Throughput: 0: 2798.6, 1: 2754.2. Samples: 46275192. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:34:48,445][86177] Avg episode reward: [(0, '-510.320'), (1, '-510.490')] -[2023-11-28 02:34:50,124][87426] Updated weights for policy 1, policy_version 90310 (0.0011) -[2023-11-28 02:34:50,259][87424] Updated weights for policy 0, policy_version 90436 (0.0007) -[2023-11-28 02:34:50,516][87426] Updated weights for policy 1, policy_version 90320 (0.0011) -[2023-11-28 02:34:50,654][87424] Updated weights for policy 0, policy_version 90446 (0.0010) -[2023-11-28 02:34:50,884][87426] Updated weights for policy 1, policy_version 90330 (0.0011) -[2023-11-28 02:34:51,028][87424] Updated weights for policy 0, policy_version 90456 (0.0008) -[2023-11-28 02:34:52,699][87426] Updated weights for policy 1, policy_version 90340 (0.0009) -[2023-11-28 02:34:53,082][87426] Updated weights for policy 1, policy_version 90350 (0.0011) -[2023-11-28 02:34:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46284800. Throughput: 0: 2781.9, 1: 2749.2. Samples: 46307276. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:34:53,445][86177] Avg episode reward: [(0, '-510.900'), (1, '-509.020')] -[2023-11-28 02:34:53,454][87426] Updated weights for policy 1, policy_version 90360 (0.0012) -[2023-11-28 02:34:53,545][87424] Updated weights for policy 0, policy_version 90466 (0.0008) -[2023-11-28 02:34:53,932][87424] Updated weights for policy 0, policy_version 90476 (0.0011) -[2023-11-28 02:34:54,313][87424] Updated weights for policy 0, policy_version 90486 (0.0007) -[2023-11-28 02:34:54,700][87424] Updated weights for policy 0, policy_version 90496 (0.0008) -[2023-11-28 02:34:55,979][87426] Updated weights for policy 1, policy_version 90370 (0.0012) -[2023-11-28 02:34:56,361][87426] Updated weights for policy 1, policy_version 90380 (0.0011) -[2023-11-28 02:34:56,738][87426] Updated weights for policy 1, policy_version 90390 (0.0010) -[2023-11-28 02:34:57,095][87424] Updated weights for policy 0, policy_version 90506 (0.0011) -[2023-11-28 02:34:57,113][87426] Updated weights for policy 1, policy_version 90400 (0.0011) -[2023-11-28 02:34:57,478][87424] Updated weights for policy 0, policy_version 90516 (0.0012) -[2023-11-28 02:34:57,851][87424] Updated weights for policy 0, policy_version 90526 (0.0012) -[2023-11-28 02:34:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46317568. Throughput: 0: 2758.1, 1: 2815.4. Samples: 46332536. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:34:58,445][86177] Avg episode reward: [(0, '-507.740'), (1, '-518.830')] -[2023-11-28 02:34:58,834][87426] Updated weights for policy 1, policy_version 90410 (0.0012) -[2023-11-28 02:34:59,226][87426] Updated weights for policy 1, policy_version 90420 (0.0008) -[2023-11-28 02:34:59,516][87424] Updated weights for policy 0, policy_version 90536 (0.0010) -[2023-11-28 02:34:59,593][87426] Updated weights for policy 1, policy_version 90430 (0.0009) -[2023-11-28 02:34:59,899][87424] Updated weights for policy 0, policy_version 90546 (0.0010) -[2023-11-28 02:35:00,288][87424] Updated weights for policy 0, policy_version 90556 (0.0011) -[2023-11-28 02:35:01,775][87426] Updated weights for policy 1, policy_version 90440 (0.0011) -[2023-11-28 02:35:02,149][87426] Updated weights for policy 1, policy_version 90450 (0.0011) -[2023-11-28 02:35:02,360][87424] Updated weights for policy 0, policy_version 90566 (0.0010) -[2023-11-28 02:35:02,529][87426] Updated weights for policy 1, policy_version 90460 (0.0012) -[2023-11-28 02:35:02,761][87424] Updated weights for policy 0, policy_version 90576 (0.0010) -[2023-11-28 02:35:03,135][87424] Updated weights for policy 0, policy_version 90586 (0.0010) -[2023-11-28 02:35:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5498.4). Total num frames: 46350336. Throughput: 0: 2794.2, 1: 2810.9. Samples: 46358660. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:35:03,445][86177] Avg episode reward: [(0, '-504.470'), (1, '-526.200')] -[2023-11-28 02:35:04,295][87426] Updated weights for policy 1, policy_version 90470 (0.0012) -[2023-11-28 02:35:04,670][87426] Updated weights for policy 1, policy_version 90480 (0.0012) -[2023-11-28 02:35:05,048][87426] Updated weights for policy 1, policy_version 90490 (0.0010) -[2023-11-28 02:35:05,073][87424] Updated weights for policy 0, policy_version 90596 (0.0011) -[2023-11-28 02:35:05,455][87424] Updated weights for policy 0, policy_version 90606 (0.0012) -[2023-11-28 02:35:05,835][87424] Updated weights for policy 0, policy_version 90616 (0.0011) -[2023-11-28 02:35:07,187][87426] Updated weights for policy 1, policy_version 90500 (0.0010) -[2023-11-28 02:35:07,567][87426] Updated weights for policy 1, policy_version 90510 (0.0012) -[2023-11-28 02:35:07,952][87426] Updated weights for policy 1, policy_version 90520 (0.0012) -[2023-11-28 02:35:08,121][87424] Updated weights for policy 0, policy_version 90626 (0.0008) -[2023-11-28 02:35:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 46374912. Throughput: 0: 2808.4, 1: 2806.9. Samples: 46392028. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:35:08,445][86177] Avg episode reward: [(0, '-505.220'), (1, '-522.480')] -[2023-11-28 02:35:08,509][87424] Updated weights for policy 0, policy_version 90636 (0.0011) -[2023-11-28 02:35:08,884][87424] Updated weights for policy 0, policy_version 90646 (0.0012) -[2023-11-28 02:35:09,270][87424] Updated weights for policy 0, policy_version 90656 (0.0012) -[2023-11-28 02:35:09,956][87426] Updated weights for policy 1, policy_version 90530 (0.0011) -[2023-11-28 02:35:10,341][87426] Updated weights for policy 1, policy_version 90540 (0.0010) -[2023-11-28 02:35:10,722][87426] Updated weights for policy 1, policy_version 90550 (0.0012) -[2023-11-28 02:35:11,092][87426] Updated weights for policy 1, policy_version 90560 (0.0011) -[2023-11-28 02:35:11,381][87424] Updated weights for policy 0, policy_version 90666 (0.0008) -[2023-11-28 02:35:11,771][87424] Updated weights for policy 0, policy_version 90676 (0.0010) -[2023-11-28 02:35:12,152][87424] Updated weights for policy 0, policy_version 90686 (0.0010) -[2023-11-28 02:35:13,277][87426] Updated weights for policy 1, policy_version 90570 (0.0011) -[2023-11-28 02:35:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46399488. Throughput: 0: 2806.4, 1: 2794.8. Samples: 46416624. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:35:13,445][86177] Avg episode reward: [(0, '-506.100'), (1, '-520.210')] -[2023-11-28 02:35:13,653][87426] Updated weights for policy 1, policy_version 90580 (0.0010) -[2023-11-28 02:35:14,030][87426] Updated weights for policy 1, policy_version 90590 (0.0009) -[2023-11-28 02:35:14,390][87424] Updated weights for policy 0, policy_version 90696 (0.0009) -[2023-11-28 02:35:14,771][87424] Updated weights for policy 0, policy_version 90706 (0.0008) -[2023-11-28 02:35:15,151][87424] Updated weights for policy 0, policy_version 90716 (0.0007) -[2023-11-28 02:35:16,530][87426] Updated weights for policy 1, policy_version 90600 (0.0007) -[2023-11-28 02:35:16,925][87426] Updated weights for policy 1, policy_version 90610 (0.0010) -[2023-11-28 02:35:17,302][87426] Updated weights for policy 1, policy_version 90620 (0.0011) -[2023-11-28 02:35:17,622][87424] Updated weights for policy 0, policy_version 90726 (0.0008) -[2023-11-28 02:35:17,999][87424] Updated weights for policy 0, policy_version 90736 (0.0010) -[2023-11-28 02:35:18,394][87424] Updated weights for policy 0, policy_version 90746 (0.0010) -[2023-11-28 02:35:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 46424064. Throughput: 0: 2771.8, 1: 2791.3. Samples: 46439860. Policy #0 lag: (min: 31.0, avg: 51.8, max: 88.0) -[2023-11-28 02:35:18,445][86177] Avg episode reward: [(0, '-505.830'), (1, '-535.450')] -[2023-11-28 02:35:19,750][87426] Updated weights for policy 1, policy_version 90630 (0.0012) -[2023-11-28 02:35:20,123][87426] Updated weights for policy 1, policy_version 90640 (0.0012) -[2023-11-28 02:35:20,502][87426] Updated weights for policy 1, policy_version 90650 (0.0012) -[2023-11-28 02:35:20,675][87424] Updated weights for policy 0, policy_version 90756 (0.0011) -[2023-11-28 02:35:21,056][87424] Updated weights for policy 0, policy_version 90766 (0.0008) -[2023-11-28 02:35:21,442][87424] Updated weights for policy 0, policy_version 90776 (0.0008) -[2023-11-28 02:35:22,780][87426] Updated weights for policy 1, policy_version 90660 (0.0011) -[2023-11-28 02:35:23,159][87426] Updated weights for policy 1, policy_version 90670 (0.0011) -[2023-11-28 02:35:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46448640. Throughput: 0: 2733.1, 1: 2737.1. Samples: 46470840. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:35:23,445][86177] Avg episode reward: [(0, '-501.520'), (1, '-527.090')] -[2023-11-28 02:35:23,539][87426] Updated weights for policy 1, policy_version 90680 (0.0012) -[2023-11-28 02:35:23,955][87424] Updated weights for policy 0, policy_version 90786 (0.0010) -[2023-11-28 02:35:24,338][87424] Updated weights for policy 0, policy_version 90796 (0.0010) -[2023-11-28 02:35:24,717][87424] Updated weights for policy 0, policy_version 90806 (0.0008) -[2023-11-28 02:35:25,096][87424] Updated weights for policy 0, policy_version 90816 (0.0008) -[2023-11-28 02:35:25,820][87426] Updated weights for policy 1, policy_version 90690 (0.0011) -[2023-11-28 02:35:26,204][87426] Updated weights for policy 1, policy_version 90700 (0.0009) -[2023-11-28 02:35:26,593][87426] Updated weights for policy 1, policy_version 90710 (0.0012) -[2023-11-28 02:35:26,973][87426] Updated weights for policy 1, policy_version 90720 (0.0011) -[2023-11-28 02:35:27,626][87424] Updated weights for policy 0, policy_version 90826 (0.0007) -[2023-11-28 02:35:28,008][87424] Updated weights for policy 0, policy_version 90836 (0.0009) -[2023-11-28 02:35:28,394][87424] Updated weights for policy 0, policy_version 90846 (0.0011) -[2023-11-28 02:35:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 46473216. Throughput: 0: 2726.8, 1: 2734.1. Samples: 46494936. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:35:28,446][86177] Avg episode reward: [(0, '-499.560'), (1, '-534.140')] -[2023-11-28 02:35:28,985][87426] Updated weights for policy 1, policy_version 90730 (0.0008) -[2023-11-28 02:35:29,355][87426] Updated weights for policy 1, policy_version 90740 (0.0007) -[2023-11-28 02:35:29,745][87426] Updated weights for policy 1, policy_version 90750 (0.0008) -[2023-11-28 02:35:30,902][87424] Updated weights for policy 0, policy_version 90856 (0.0009) -[2023-11-28 02:35:31,285][87424] Updated weights for policy 0, policy_version 90866 (0.0010) -[2023-11-28 02:35:31,563][87426] Updated weights for policy 1, policy_version 90760 (0.0010) -[2023-11-28 02:35:31,670][87424] Updated weights for policy 0, policy_version 90876 (0.0010) -[2023-11-28 02:35:31,942][87426] Updated weights for policy 1, policy_version 90770 (0.0010) -[2023-11-28 02:35:32,318][87426] Updated weights for policy 1, policy_version 90780 (0.0008) -[2023-11-28 02:35:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46505984. Throughput: 0: 2661.9, 1: 2743.5. Samples: 46518436. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:35:33,446][86177] Avg episode reward: [(0, '-498.360'), (1, '-540.110')] -[2023-11-28 02:35:33,866][87424] Updated weights for policy 0, policy_version 90886 (0.0010) -[2023-11-28 02:35:34,248][87424] Updated weights for policy 0, policy_version 90896 (0.0012) -[2023-11-28 02:35:34,631][87424] Updated weights for policy 0, policy_version 90906 (0.0012) -[2023-11-28 02:35:34,639][87426] Updated weights for policy 1, policy_version 90790 (0.0008) -[2023-11-28 02:35:35,013][87426] Updated weights for policy 1, policy_version 90800 (0.0008) -[2023-11-28 02:35:35,392][87426] Updated weights for policy 1, policy_version 90810 (0.0008) -[2023-11-28 02:35:36,709][87424] Updated weights for policy 0, policy_version 90916 (0.0011) -[2023-11-28 02:35:37,087][87424] Updated weights for policy 0, policy_version 90926 (0.0008) -[2023-11-28 02:35:37,271][87426] Updated weights for policy 1, policy_version 90820 (0.0008) -[2023-11-28 02:35:37,472][87424] Updated weights for policy 0, policy_version 90936 (0.0010) -[2023-11-28 02:35:37,653][87426] Updated weights for policy 1, policy_version 90830 (0.0011) -[2023-11-28 02:35:38,032][87426] Updated weights for policy 1, policy_version 90840 (0.0012) -[2023-11-28 02:35:38,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46538752. Throughput: 0: 2671.2, 1: 2757.9. Samples: 46551584. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:35:38,445][86177] Avg episode reward: [(0, '-501.390'), (1, '-521.860')] -[2023-11-28 02:35:39,504][87424] Updated weights for policy 0, policy_version 90946 (0.0008) -[2023-11-28 02:35:39,884][87424] Updated weights for policy 0, policy_version 90956 (0.0009) -[2023-11-28 02:35:40,100][87426] Updated weights for policy 1, policy_version 90850 (0.0011) -[2023-11-28 02:35:40,266][87424] Updated weights for policy 0, policy_version 90966 (0.0011) -[2023-11-28 02:35:40,485][87426] Updated weights for policy 1, policy_version 90860 (0.0012) -[2023-11-28 02:35:40,651][87424] Updated weights for policy 0, policy_version 90976 (0.0011) -[2023-11-28 02:35:40,851][87426] Updated weights for policy 1, policy_version 90870 (0.0011) -[2023-11-28 02:35:41,229][87426] Updated weights for policy 1, policy_version 90880 (0.0012) -[2023-11-28 02:35:43,172][87424] Updated weights for policy 0, policy_version 90986 (0.0011) -[2023-11-28 02:35:43,389][87426] Updated weights for policy 1, policy_version 90890 (0.0011) -[2023-11-28 02:35:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 46555136. Throughput: 0: 2692.6, 1: 2718.5. Samples: 46576036. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:35:43,446][86177] Avg episode reward: [(0, '-503.450'), (1, '-524.430')] -[2023-11-28 02:35:43,541][87424] Updated weights for policy 0, policy_version 90996 (0.0012) -[2023-11-28 02:35:43,769][87426] Updated weights for policy 1, policy_version 90900 (0.0012) -[2023-11-28 02:35:43,928][87424] Updated weights for policy 0, policy_version 91006 (0.0012) -[2023-11-28 02:35:44,146][87426] Updated weights for policy 1, policy_version 90910 (0.0011) -[2023-11-28 02:35:45,639][87424] Updated weights for policy 0, policy_version 91016 (0.0012) -[2023-11-28 02:35:46,013][87424] Updated weights for policy 0, policy_version 91026 (0.0012) -[2023-11-28 02:35:46,401][87424] Updated weights for policy 0, policy_version 91036 (0.0011) -[2023-11-28 02:35:46,626][87426] Updated weights for policy 1, policy_version 90920 (0.0012) -[2023-11-28 02:35:47,005][87426] Updated weights for policy 1, policy_version 90930 (0.0011) -[2023-11-28 02:35:47,388][87426] Updated weights for policy 1, policy_version 90940 (0.0007) -[2023-11-28 02:35:48,111][87424] Updated weights for policy 0, policy_version 91046 (0.0009) -[2023-11-28 02:35:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 46587904. Throughput: 0: 2657.0, 1: 2711.9. Samples: 46600260. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:35:48,445][86177] Avg episode reward: [(0, '-505.640'), (1, '-519.270')] -[2023-11-28 02:35:48,497][87424] Updated weights for policy 0, policy_version 91056 (0.0007) -[2023-11-28 02:35:48,889][87424] Updated weights for policy 0, policy_version 91066 (0.0008) -[2023-11-28 02:35:49,876][87426] Updated weights for policy 1, policy_version 90950 (0.0009) -[2023-11-28 02:35:50,255][87426] Updated weights for policy 1, policy_version 90960 (0.0008) -[2023-11-28 02:35:50,633][87426] Updated weights for policy 1, policy_version 90970 (0.0010) -[2023-11-28 02:35:51,229][87424] Updated weights for policy 0, policy_version 91076 (0.0010) -[2023-11-28 02:35:51,611][87424] Updated weights for policy 0, policy_version 91086 (0.0009) -[2023-11-28 02:35:51,996][87424] Updated weights for policy 0, policy_version 91096 (0.0012) -[2023-11-28 02:35:52,849][87426] Updated weights for policy 1, policy_version 90980 (0.0010) -[2023-11-28 02:35:53,232][87426] Updated weights for policy 1, policy_version 90990 (0.0012) -[2023-11-28 02:35:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 46612480. Throughput: 0: 2663.4, 1: 2690.8. Samples: 46632968. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:35:53,445][86177] Avg episode reward: [(0, '-506.240'), (1, '-506.560')] -[2023-11-28 02:35:53,608][87426] Updated weights for policy 1, policy_version 91000 (0.0010) -[2023-11-28 02:35:54,237][87424] Updated weights for policy 0, policy_version 91106 (0.0011) -[2023-11-28 02:35:54,615][87424] Updated weights for policy 0, policy_version 91116 (0.0007) -[2023-11-28 02:35:55,002][87424] Updated weights for policy 0, policy_version 91126 (0.0008) -[2023-11-28 02:35:55,383][87424] Updated weights for policy 0, policy_version 91136 (0.0008) -[2023-11-28 02:35:55,586][87426] Updated weights for policy 1, policy_version 91010 (0.0009) -[2023-11-28 02:35:55,963][87426] Updated weights for policy 1, policy_version 91020 (0.0011) -[2023-11-28 02:35:56,335][87426] Updated weights for policy 1, policy_version 91030 (0.0012) -[2023-11-28 02:35:56,705][87426] Updated weights for policy 1, policy_version 91040 (0.0012) -[2023-11-28 02:35:57,280][87424] Updated weights for policy 0, policy_version 91146 (0.0012) -[2023-11-28 02:35:57,670][87424] Updated weights for policy 0, policy_version 91156 (0.0012) -[2023-11-28 02:35:58,063][87424] Updated weights for policy 0, policy_version 91166 (0.0008) -[2023-11-28 02:35:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46645248. Throughput: 0: 2655.6, 1: 2694.2. Samples: 46657364. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:35:58,445][86177] Avg episode reward: [(0, '-505.030'), (1, '-511.580')] -[2023-11-28 02:35:59,239][87426] Updated weights for policy 1, policy_version 91050 (0.0009) -[2023-11-28 02:35:59,622][87426] Updated weights for policy 1, policy_version 91060 (0.0012) -[2023-11-28 02:35:59,994][87426] Updated weights for policy 1, policy_version 91070 (0.0011) -[2023-11-28 02:36:00,123][87424] Updated weights for policy 0, policy_version 91176 (0.0010) -[2023-11-28 02:36:00,511][87424] Updated weights for policy 0, policy_version 91186 (0.0008) -[2023-11-28 02:36:00,902][87424] Updated weights for policy 0, policy_version 91196 (0.0008) -[2023-11-28 02:36:02,353][87426] Updated weights for policy 1, policy_version 91080 (0.0012) -[2023-11-28 02:36:02,736][87426] Updated weights for policy 1, policy_version 91090 (0.0012) -[2023-11-28 02:36:03,112][87426] Updated weights for policy 1, policy_version 91100 (0.0011) -[2023-11-28 02:36:03,286][87424] Updated weights for policy 0, policy_version 91206 (0.0010) -[2023-11-28 02:36:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 46669824. Throughput: 0: 2693.6, 1: 2696.7. Samples: 46682424. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:36:03,445][86177] Avg episode reward: [(0, '-507.110'), (1, '-520.110')] -[2023-11-28 02:36:03,676][87424] Updated weights for policy 0, policy_version 91216 (0.0011) -[2023-11-28 02:36:04,060][87424] Updated weights for policy 0, policy_version 91226 (0.0007) -[2023-11-28 02:36:04,973][87426] Updated weights for policy 1, policy_version 91110 (0.0008) -[2023-11-28 02:36:05,355][87426] Updated weights for policy 1, policy_version 91120 (0.0008) -[2023-11-28 02:36:05,719][87426] Updated weights for policy 1, policy_version 91130 (0.0008) -[2023-11-28 02:36:06,128][87424] Updated weights for policy 0, policy_version 91236 (0.0009) -[2023-11-28 02:36:06,507][87424] Updated weights for policy 0, policy_version 91246 (0.0011) -[2023-11-28 02:36:06,898][87424] Updated weights for policy 0, policy_version 91256 (0.0009) -[2023-11-28 02:36:08,024][87426] Updated weights for policy 1, policy_version 91140 (0.0009) -[2023-11-28 02:36:08,404][87426] Updated weights for policy 1, policy_version 91150 (0.0012) -[2023-11-28 02:36:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 46694400. Throughput: 0: 2691.2, 1: 2718.8. Samples: 46714292. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:36:08,445][86177] Avg episode reward: [(0, '-507.490'), (1, '-532.350')] -[2023-11-28 02:36:08,777][87426] Updated weights for policy 1, policy_version 91160 (0.0012) -[2023-11-28 02:36:09,252][87424] Updated weights for policy 0, policy_version 91266 (0.0011) -[2023-11-28 02:36:09,640][87424] Updated weights for policy 0, policy_version 91276 (0.0009) -[2023-11-28 02:36:10,026][87424] Updated weights for policy 0, policy_version 91286 (0.0009) -[2023-11-28 02:36:10,410][87424] Updated weights for policy 0, policy_version 91296 (0.0009) -[2023-11-28 02:36:11,041][87426] Updated weights for policy 1, policy_version 91170 (0.0012) -[2023-11-28 02:36:11,424][87426] Updated weights for policy 1, policy_version 91180 (0.0012) -[2023-11-28 02:36:11,800][87426] Updated weights for policy 1, policy_version 91190 (0.0011) -[2023-11-28 02:36:12,176][87426] Updated weights for policy 1, policy_version 91200 (0.0012) -[2023-11-28 02:36:12,737][87424] Updated weights for policy 0, policy_version 91306 (0.0011) -[2023-11-28 02:36:13,123][87424] Updated weights for policy 0, policy_version 91316 (0.0012) -[2023-11-28 02:36:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 46718976. Throughput: 0: 2696.0, 1: 2717.3. Samples: 46738536. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:36:13,445][86177] Avg episode reward: [(0, '-508.260'), (1, '-545.700')] -[2023-11-28 02:36:13,502][87424] Updated weights for policy 0, policy_version 91326 (0.0012) -[2023-11-28 02:36:14,341][87426] Updated weights for policy 1, policy_version 91210 (0.0012) -[2023-11-28 02:36:14,724][87426] Updated weights for policy 1, policy_version 91220 (0.0012) -[2023-11-28 02:36:15,101][87426] Updated weights for policy 1, policy_version 91230 (0.0009) -[2023-11-28 02:36:15,345][87424] Updated weights for policy 0, policy_version 91336 (0.0010) -[2023-11-28 02:36:15,728][87424] Updated weights for policy 0, policy_version 91346 (0.0008) -[2023-11-28 02:36:16,117][87424] Updated weights for policy 0, policy_version 91356 (0.0007) -[2023-11-28 02:36:17,305][87426] Updated weights for policy 1, policy_version 91240 (0.0011) -[2023-11-28 02:36:17,689][87426] Updated weights for policy 1, policy_version 91250 (0.0010) -[2023-11-28 02:36:18,068][87426] Updated weights for policy 1, policy_version 91260 (0.0007) -[2023-11-28 02:36:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 46751744. Throughput: 0: 2734.2, 1: 2715.9. Samples: 46763692. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:36:18,445][86177] Avg episode reward: [(0, '-517.220'), (1, '-547.110')] -[2023-11-28 02:36:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000091264_23363584.pth... -[2023-11-28 02:36:18,466][87424] Updated weights for policy 0, policy_version 91366 (0.0010) -[2023-11-28 02:36:18,501][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000088704_22708224.pth -[2023-11-28 02:36:18,849][87424] Updated weights for policy 0, policy_version 91376 (0.0008) -[2023-11-28 02:36:19,236][87424] Updated weights for policy 0, policy_version 91386 (0.0009) -[2023-11-28 02:36:19,470][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000091392_23396352.pth... -[2023-11-28 02:36:19,513][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000088832_22740992.pth -[2023-11-28 02:36:19,790][87426] Updated weights for policy 1, policy_version 91270 (0.0009) -[2023-11-28 02:36:20,168][87426] Updated weights for policy 1, policy_version 91280 (0.0011) -[2023-11-28 02:36:20,543][87426] Updated weights for policy 1, policy_version 91290 (0.0010) -[2023-11-28 02:36:21,210][87424] Updated weights for policy 0, policy_version 91396 (0.0009) -[2023-11-28 02:36:21,592][87424] Updated weights for policy 0, policy_version 91406 (0.0011) -[2023-11-28 02:36:21,982][87424] Updated weights for policy 0, policy_version 91416 (0.0012) -[2023-11-28 02:36:23,040][87426] Updated weights for policy 1, policy_version 91300 (0.0009) -[2023-11-28 02:36:23,421][87426] Updated weights for policy 1, policy_version 91310 (0.0011) -[2023-11-28 02:36:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 46776320. Throughput: 0: 2728.8, 1: 2693.1. Samples: 46795568. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:36:23,445][86177] Avg episode reward: [(0, '-510.070'), (1, '-556.780')] -[2023-11-28 02:36:23,795][87426] Updated weights for policy 1, policy_version 91320 (0.0011) -[2023-11-28 02:36:24,350][87424] Updated weights for policy 0, policy_version 91426 (0.0012) -[2023-11-28 02:36:24,735][87424] Updated weights for policy 0, policy_version 91436 (0.0012) -[2023-11-28 02:36:25,109][87424] Updated weights for policy 0, policy_version 91446 (0.0012) -[2023-11-28 02:36:25,492][87424] Updated weights for policy 0, policy_version 91456 (0.0012) -[2023-11-28 02:36:25,821][87426] Updated weights for policy 1, policy_version 91330 (0.0012) -[2023-11-28 02:36:26,195][87426] Updated weights for policy 1, policy_version 91340 (0.0012) -[2023-11-28 02:36:26,578][87426] Updated weights for policy 1, policy_version 91350 (0.0011) -[2023-11-28 02:36:26,947][87426] Updated weights for policy 1, policy_version 91360 (0.0008) -[2023-11-28 02:36:27,600][87424] Updated weights for policy 0, policy_version 91466 (0.0012) -[2023-11-28 02:36:27,992][87424] Updated weights for policy 0, policy_version 91476 (0.0012) -[2023-11-28 02:36:28,386][87424] Updated weights for policy 0, policy_version 91486 (0.0012) -[2023-11-28 02:36:28,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 46800896. Throughput: 0: 2724.9, 1: 2714.7. Samples: 46820816. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:36:28,446][86177] Avg episode reward: [(0, '-522.760'), (1, '-528.530')] -[2023-11-28 02:36:29,217][87426] Updated weights for policy 1, policy_version 91370 (0.0011) -[2023-11-28 02:36:29,594][87426] Updated weights for policy 1, policy_version 91380 (0.0011) -[2023-11-28 02:36:29,977][87426] Updated weights for policy 1, policy_version 91390 (0.0011) -[2023-11-28 02:36:30,830][87424] Updated weights for policy 0, policy_version 91496 (0.0011) -[2023-11-28 02:36:31,210][87424] Updated weights for policy 0, policy_version 91506 (0.0012) -[2023-11-28 02:36:31,604][87424] Updated weights for policy 0, policy_version 91516 (0.0012) -[2023-11-28 02:36:31,757][87426] Updated weights for policy 1, policy_version 91400 (0.0012) -[2023-11-28 02:36:32,141][87426] Updated weights for policy 1, policy_version 91410 (0.0009) -[2023-11-28 02:36:32,517][87426] Updated weights for policy 1, policy_version 91420 (0.0008) -[2023-11-28 02:36:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 46833664. Throughput: 0: 2721.8, 1: 2733.5. Samples: 46845748. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:36:33,445][86177] Avg episode reward: [(0, '-522.570'), (1, '-522.270')] -[2023-11-28 02:36:33,592][87424] Updated weights for policy 0, policy_version 91526 (0.0011) -[2023-11-28 02:36:33,971][87424] Updated weights for policy 0, policy_version 91536 (0.0011) -[2023-11-28 02:36:34,356][87424] Updated weights for policy 0, policy_version 91546 (0.0012) -[2023-11-28 02:36:34,562][87426] Updated weights for policy 1, policy_version 91430 (0.0008) -[2023-11-28 02:36:34,944][87426] Updated weights for policy 1, policy_version 91440 (0.0008) -[2023-11-28 02:36:35,325][87426] Updated weights for policy 1, policy_version 91450 (0.0010) -[2023-11-28 02:36:36,605][87424] Updated weights for policy 0, policy_version 91556 (0.0012) -[2023-11-28 02:36:36,989][87424] Updated weights for policy 0, policy_version 91566 (0.0011) -[2023-11-28 02:36:37,104][87426] Updated weights for policy 1, policy_version 91460 (0.0009) -[2023-11-28 02:36:37,362][87424] Updated weights for policy 0, policy_version 91576 (0.0012) -[2023-11-28 02:36:37,478][87426] Updated weights for policy 1, policy_version 91470 (0.0008) -[2023-11-28 02:36:37,859][87426] Updated weights for policy 1, policy_version 91480 (0.0012) -[2023-11-28 02:36:38,444][86177] Fps is (10 sec: 6553.9, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 46866432. Throughput: 0: 2714.1, 1: 2747.4. Samples: 46878736. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:36:38,445][86177] Avg episode reward: [(0, '-515.470'), (1, '-523.980')] -[2023-11-28 02:36:39,226][87424] Updated weights for policy 0, policy_version 91586 (0.0011) -[2023-11-28 02:36:39,618][87424] Updated weights for policy 0, policy_version 91596 (0.0012) -[2023-11-28 02:36:39,992][87424] Updated weights for policy 0, policy_version 91606 (0.0012) -[2023-11-28 02:36:40,227][87426] Updated weights for policy 1, policy_version 91490 (0.0011) -[2023-11-28 02:36:40,370][87424] Updated weights for policy 0, policy_version 91616 (0.0011) -[2023-11-28 02:36:40,607][87426] Updated weights for policy 1, policy_version 91500 (0.0008) -[2023-11-28 02:36:40,993][87426] Updated weights for policy 1, policy_version 91510 (0.0008) -[2023-11-28 02:36:41,364][87426] Updated weights for policy 1, policy_version 91520 (0.0007) -[2023-11-28 02:36:42,785][87424] Updated weights for policy 0, policy_version 91626 (0.0012) -[2023-11-28 02:36:43,170][87424] Updated weights for policy 0, policy_version 91636 (0.0012) -[2023-11-28 02:36:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 46882816. Throughput: 0: 2718.5, 1: 2730.6. Samples: 46902572. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:36:43,445][86177] Avg episode reward: [(0, '-515.810'), (1, '-509.040')] -[2023-11-28 02:36:43,538][87424] Updated weights for policy 0, policy_version 91646 (0.0011) -[2023-11-28 02:36:43,893][87426] Updated weights for policy 1, policy_version 91530 (0.0008) -[2023-11-28 02:36:44,276][87426] Updated weights for policy 1, policy_version 91540 (0.0007) -[2023-11-28 02:36:44,655][87426] Updated weights for policy 1, policy_version 91550 (0.0008) -[2023-11-28 02:36:45,300][87424] Updated weights for policy 0, policy_version 91656 (0.0012) -[2023-11-28 02:36:45,683][87424] Updated weights for policy 0, policy_version 91666 (0.0012) -[2023-11-28 02:36:46,074][87424] Updated weights for policy 0, policy_version 91676 (0.0012) -[2023-11-28 02:36:46,826][87426] Updated weights for policy 1, policy_version 91560 (0.0008) -[2023-11-28 02:36:47,211][87426] Updated weights for policy 1, policy_version 91570 (0.0007) -[2023-11-28 02:36:47,581][87426] Updated weights for policy 1, policy_version 91580 (0.0007) -[2023-11-28 02:36:48,212][87424] Updated weights for policy 0, policy_version 91686 (0.0009) -[2023-11-28 02:36:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 46915584. Throughput: 0: 2709.7, 1: 2714.1. Samples: 46926496. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:36:48,446][86177] Avg episode reward: [(0, '-505.580'), (1, '-507.610')] -[2023-11-28 02:36:48,603][87424] Updated weights for policy 0, policy_version 91696 (0.0008) -[2023-11-28 02:36:48,978][87424] Updated weights for policy 0, policy_version 91706 (0.0008) -[2023-11-28 02:36:49,781][87426] Updated weights for policy 1, policy_version 91590 (0.0010) -[2023-11-28 02:36:50,152][87426] Updated weights for policy 1, policy_version 91600 (0.0009) -[2023-11-28 02:36:50,530][87426] Updated weights for policy 1, policy_version 91610 (0.0009) -[2023-11-28 02:36:50,987][87424] Updated weights for policy 0, policy_version 91716 (0.0008) -[2023-11-28 02:36:51,365][87424] Updated weights for policy 0, policy_version 91726 (0.0010) -[2023-11-28 02:36:51,746][87424] Updated weights for policy 0, policy_version 91736 (0.0012) -[2023-11-28 02:36:52,528][87426] Updated weights for policy 1, policy_version 91620 (0.0011) -[2023-11-28 02:36:52,906][87426] Updated weights for policy 1, policy_version 91630 (0.0012) -[2023-11-28 02:36:53,298][87426] Updated weights for policy 1, policy_version 91640 (0.0012) -[2023-11-28 02:36:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 46940160. Throughput: 0: 2722.8, 1: 2722.4. Samples: 46959324. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:36:53,445][86177] Avg episode reward: [(0, '-505.680'), (1, '-503.790')] -[2023-11-28 02:36:54,313][87424] Updated weights for policy 0, policy_version 91746 (0.0011) -[2023-11-28 02:36:54,702][87424] Updated weights for policy 0, policy_version 91756 (0.0008) -[2023-11-28 02:36:55,084][87424] Updated weights for policy 0, policy_version 91766 (0.0007) -[2023-11-28 02:36:55,479][87424] Updated weights for policy 0, policy_version 91776 (0.0008) -[2023-11-28 02:36:55,630][87426] Updated weights for policy 1, policy_version 91650 (0.0012) -[2023-11-28 02:36:56,001][87426] Updated weights for policy 1, policy_version 91660 (0.0008) -[2023-11-28 02:36:56,375][87426] Updated weights for policy 1, policy_version 91670 (0.0007) -[2023-11-28 02:36:56,755][87426] Updated weights for policy 1, policy_version 91680 (0.0010) -[2023-11-28 02:36:57,883][87424] Updated weights for policy 0, policy_version 91786 (0.0008) -[2023-11-28 02:36:58,271][87424] Updated weights for policy 0, policy_version 91796 (0.0008) -[2023-11-28 02:36:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 46964736. Throughput: 0: 2716.0, 1: 2744.5. Samples: 46984260. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:36:58,445][86177] Avg episode reward: [(0, '-510.550'), (1, '-509.000')] -[2023-11-28 02:36:58,656][87424] Updated weights for policy 0, policy_version 91806 (0.0010) -[2023-11-28 02:36:58,769][87426] Updated weights for policy 1, policy_version 91690 (0.0012) -[2023-11-28 02:36:59,150][87426] Updated weights for policy 1, policy_version 91700 (0.0009) -[2023-11-28 02:36:59,531][87426] Updated weights for policy 1, policy_version 91710 (0.0007) -[2023-11-28 02:37:00,704][87424] Updated weights for policy 0, policy_version 91816 (0.0010) -[2023-11-28 02:37:01,093][87424] Updated weights for policy 0, policy_version 91826 (0.0011) -[2023-11-28 02:37:01,487][87424] Updated weights for policy 0, policy_version 91836 (0.0009) -[2023-11-28 02:37:01,515][87426] Updated weights for policy 1, policy_version 91720 (0.0008) -[2023-11-28 02:37:01,893][87426] Updated weights for policy 1, policy_version 91730 (0.0009) -[2023-11-28 02:37:02,276][87426] Updated weights for policy 1, policy_version 91740 (0.0008) -[2023-11-28 02:37:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 46997504. Throughput: 0: 2711.1, 1: 2737.1. Samples: 47008864. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:37:03,446][86177] Avg episode reward: [(0, '-510.800'), (1, '-505.740')] -[2023-11-28 02:37:03,563][87424] Updated weights for policy 0, policy_version 91846 (0.0008) -[2023-11-28 02:37:03,945][87424] Updated weights for policy 0, policy_version 91856 (0.0008) -[2023-11-28 02:37:04,337][87424] Updated weights for policy 0, policy_version 91866 (0.0008) -[2023-11-28 02:37:04,793][87426] Updated weights for policy 1, policy_version 91750 (0.0008) -[2023-11-28 02:37:05,168][87426] Updated weights for policy 1, policy_version 91760 (0.0008) -[2023-11-28 02:37:05,558][87426] Updated weights for policy 1, policy_version 91770 (0.0011) -[2023-11-28 02:37:06,407][87424] Updated weights for policy 0, policy_version 91876 (0.0011) -[2023-11-28 02:37:06,783][87424] Updated weights for policy 0, policy_version 91886 (0.0012) -[2023-11-28 02:37:07,161][87424] Updated weights for policy 0, policy_version 91896 (0.0012) -[2023-11-28 02:37:07,714][87426] Updated weights for policy 1, policy_version 91780 (0.0008) -[2023-11-28 02:37:08,097][87426] Updated weights for policy 1, policy_version 91790 (0.0010) -[2023-11-28 02:37:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 47022080. Throughput: 0: 2712.0, 1: 2732.1. Samples: 47040552. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:37:08,445][86177] Avg episode reward: [(0, '-501.840'), (1, '-512.370')] -[2023-11-28 02:37:08,472][87426] Updated weights for policy 1, policy_version 91800 (0.0011) -[2023-11-28 02:37:09,513][87424] Updated weights for policy 0, policy_version 91906 (0.0011) -[2023-11-28 02:37:09,899][87424] Updated weights for policy 0, policy_version 91916 (0.0008) -[2023-11-28 02:37:10,289][87424] Updated weights for policy 0, policy_version 91926 (0.0011) -[2023-11-28 02:37:10,468][87426] Updated weights for policy 1, policy_version 91810 (0.0009) -[2023-11-28 02:37:10,674][87424] Updated weights for policy 0, policy_version 91936 (0.0010) -[2023-11-28 02:37:10,838][87426] Updated weights for policy 1, policy_version 91820 (0.0008) -[2023-11-28 02:37:11,218][87426] Updated weights for policy 1, policy_version 91830 (0.0012) -[2023-11-28 02:37:11,604][87426] Updated weights for policy 1, policy_version 91840 (0.0011) -[2023-11-28 02:37:13,067][87424] Updated weights for policy 0, policy_version 91946 (0.0010) -[2023-11-28 02:37:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 47046656. Throughput: 0: 2714.2, 1: 2715.8. Samples: 47065160. Policy #0 lag: (min: 31.0, avg: 47.7, max: 67.0) -[2023-11-28 02:37:13,445][86177] Avg episode reward: [(0, '-502.050'), (1, '-511.540')] -[2023-11-28 02:37:13,445][87424] Updated weights for policy 0, policy_version 91956 (0.0008) -[2023-11-28 02:37:13,833][87424] Updated weights for policy 0, policy_version 91966 (0.0008) -[2023-11-28 02:37:13,902][87426] Updated weights for policy 1, policy_version 91850 (0.0012) -[2023-11-28 02:37:14,276][87426] Updated weights for policy 1, policy_version 91860 (0.0008) -[2023-11-28 02:37:14,660][87426] Updated weights for policy 1, policy_version 91870 (0.0009) -[2023-11-28 02:37:16,318][87424] Updated weights for policy 0, policy_version 91976 (0.0010) -[2023-11-28 02:37:16,705][87424] Updated weights for policy 0, policy_version 91986 (0.0012) -[2023-11-28 02:37:16,731][87426] Updated weights for policy 1, policy_version 91880 (0.0010) -[2023-11-28 02:37:17,097][87424] Updated weights for policy 0, policy_version 91996 (0.0012) -[2023-11-28 02:37:17,110][87426] Updated weights for policy 1, policy_version 91890 (0.0011) -[2023-11-28 02:37:17,499][87426] Updated weights for policy 1, policy_version 91900 (0.0012) -[2023-11-28 02:37:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 47079424. Throughput: 0: 2684.2, 1: 2708.2. Samples: 47088404. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:37:18,445][86177] Avg episode reward: [(0, '-498.900'), (1, '-521.990')] -[2023-11-28 02:37:18,834][87424] Updated weights for policy 0, policy_version 92006 (0.0009) -[2023-11-28 02:37:19,213][87424] Updated weights for policy 0, policy_version 92016 (0.0011) -[2023-11-28 02:37:19,596][87424] Updated weights for policy 0, policy_version 92026 (0.0011) -[2023-11-28 02:37:20,058][87426] Updated weights for policy 1, policy_version 91910 (0.0012) -[2023-11-28 02:37:20,439][87426] Updated weights for policy 1, policy_version 91920 (0.0012) -[2023-11-28 02:37:20,826][87426] Updated weights for policy 1, policy_version 91930 (0.0012) -[2023-11-28 02:37:22,050][87424] Updated weights for policy 0, policy_version 92036 (0.0015) -[2023-11-28 02:37:22,430][87424] Updated weights for policy 0, policy_version 92046 (0.0013) -[2023-11-28 02:37:22,820][87424] Updated weights for policy 0, policy_version 92056 (0.0012) -[2023-11-28 02:37:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 47104000. Throughput: 0: 2681.0, 1: 2690.0. Samples: 47120432. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:37:23,445][86177] Avg episode reward: [(0, '-512.720'), (1, '-541.290')] -[2023-11-28 02:37:23,494][87426] Updated weights for policy 1, policy_version 91940 (0.0012) -[2023-11-28 02:37:23,869][87426] Updated weights for policy 1, policy_version 91950 (0.0011) -[2023-11-28 02:37:24,238][87426] Updated weights for policy 1, policy_version 91960 (0.0010) -[2023-11-28 02:37:24,848][87424] Updated weights for policy 0, policy_version 92066 (0.0010) -[2023-11-28 02:37:25,233][87424] Updated weights for policy 0, policy_version 92076 (0.0008) -[2023-11-28 02:37:25,609][87424] Updated weights for policy 0, policy_version 92086 (0.0007) -[2023-11-28 02:37:25,994][87424] Updated weights for policy 0, policy_version 92096 (0.0009) -[2023-11-28 02:37:26,059][87426] Updated weights for policy 1, policy_version 91970 (0.0007) -[2023-11-28 02:37:26,429][87426] Updated weights for policy 1, policy_version 91980 (0.0008) -[2023-11-28 02:37:26,809][87426] Updated weights for policy 1, policy_version 91990 (0.0008) -[2023-11-28 02:37:27,188][87426] Updated weights for policy 1, policy_version 92000 (0.0008) -[2023-11-28 02:37:27,961][87424] Updated weights for policy 0, policy_version 92106 (0.0008) -[2023-11-28 02:37:28,347][87424] Updated weights for policy 0, policy_version 92116 (0.0007) -[2023-11-28 02:37:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 47128576. Throughput: 0: 2689.7, 1: 2702.6. Samples: 47145224. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:37:28,445][86177] Avg episode reward: [(0, '-520.000'), (1, '-534.350')] -[2023-11-28 02:37:28,719][87424] Updated weights for policy 0, policy_version 92126 (0.0011) -[2023-11-28 02:37:28,833][87426] Updated weights for policy 1, policy_version 92010 (0.0007) -[2023-11-28 02:37:29,201][87426] Updated weights for policy 1, policy_version 92020 (0.0008) -[2023-11-28 02:37:29,583][87426] Updated weights for policy 1, policy_version 92030 (0.0010) -[2023-11-28 02:37:30,906][87424] Updated weights for policy 0, policy_version 92136 (0.0009) -[2023-11-28 02:37:31,291][87424] Updated weights for policy 0, policy_version 92146 (0.0008) -[2023-11-28 02:37:31,675][87424] Updated weights for policy 0, policy_version 92156 (0.0008) -[2023-11-28 02:37:31,972][87426] Updated weights for policy 1, policy_version 92040 (0.0010) -[2023-11-28 02:37:32,351][87426] Updated weights for policy 1, policy_version 92050 (0.0009) -[2023-11-28 02:37:32,733][87426] Updated weights for policy 1, policy_version 92060 (0.0007) -[2023-11-28 02:37:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 47161344. Throughput: 0: 2690.9, 1: 2711.1. Samples: 47169588. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:37:33,445][86177] Avg episode reward: [(0, '-524.040'), (1, '-536.370')] -[2023-11-28 02:37:34,074][87424] Updated weights for policy 0, policy_version 92166 (0.0009) -[2023-11-28 02:37:34,455][87424] Updated weights for policy 0, policy_version 92176 (0.0007) -[2023-11-28 02:37:34,835][87424] Updated weights for policy 0, policy_version 92186 (0.0008) -[2023-11-28 02:37:35,135][87426] Updated weights for policy 1, policy_version 92070 (0.0009) -[2023-11-28 02:37:35,512][87426] Updated weights for policy 1, policy_version 92080 (0.0007) -[2023-11-28 02:37:35,887][87426] Updated weights for policy 1, policy_version 92090 (0.0007) -[2023-11-28 02:37:37,145][87424] Updated weights for policy 0, policy_version 92196 (0.0009) -[2023-11-28 02:37:37,539][87424] Updated weights for policy 0, policy_version 92206 (0.0012) -[2023-11-28 02:37:37,909][87424] Updated weights for policy 0, policy_version 92216 (0.0012) -[2023-11-28 02:37:38,419][87426] Updated weights for policy 1, policy_version 92100 (0.0009) -[2023-11-28 02:37:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 47185920. Throughput: 0: 2694.7, 1: 2675.4. Samples: 47200976. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:37:38,445][86177] Avg episode reward: [(0, '-526.800'), (1, '-557.170')] -[2023-11-28 02:37:38,794][87426] Updated weights for policy 1, policy_version 92110 (0.0011) -[2023-11-28 02:37:39,173][87426] Updated weights for policy 1, policy_version 92120 (0.0011) -[2023-11-28 02:37:39,921][87424] Updated weights for policy 0, policy_version 92226 (0.0010) -[2023-11-28 02:37:40,309][87424] Updated weights for policy 0, policy_version 92236 (0.0012) -[2023-11-28 02:37:40,691][87424] Updated weights for policy 0, policy_version 92246 (0.0012) -[2023-11-28 02:37:41,082][87424] Updated weights for policy 0, policy_version 92256 (0.0012) -[2023-11-28 02:37:41,242][87426] Updated weights for policy 1, policy_version 92130 (0.0010) -[2023-11-28 02:37:41,620][87426] Updated weights for policy 1, policy_version 92140 (0.0008) -[2023-11-28 02:37:42,006][87426] Updated weights for policy 1, policy_version 92150 (0.0009) -[2023-11-28 02:37:42,386][87426] Updated weights for policy 1, policy_version 92160 (0.0009) -[2023-11-28 02:37:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 47210496. Throughput: 0: 2691.7, 1: 2639.9. Samples: 47224180. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:37:43,445][86177] Avg episode reward: [(0, '-510.930'), (1, '-547.940')] -[2023-11-28 02:37:43,699][87424] Updated weights for policy 0, policy_version 92266 (0.0012) -[2023-11-28 02:37:44,082][87424] Updated weights for policy 0, policy_version 92276 (0.0012) -[2023-11-28 02:37:44,468][87424] Updated weights for policy 0, policy_version 92286 (0.0012) -[2023-11-28 02:37:44,667][87426] Updated weights for policy 1, policy_version 92170 (0.0007) -[2023-11-28 02:37:45,047][87426] Updated weights for policy 1, policy_version 92180 (0.0007) -[2023-11-28 02:37:45,423][87426] Updated weights for policy 1, policy_version 92190 (0.0008) -[2023-11-28 02:37:47,012][87424] Updated weights for policy 0, policy_version 92296 (0.0011) -[2023-11-28 02:37:47,385][87424] Updated weights for policy 0, policy_version 92306 (0.0012) -[2023-11-28 02:37:47,778][87424] Updated weights for policy 0, policy_version 92316 (0.0012) -[2023-11-28 02:37:47,847][87426] Updated weights for policy 1, policy_version 92200 (0.0008) -[2023-11-28 02:37:48,231][87426] Updated weights for policy 1, policy_version 92210 (0.0007) -[2023-11-28 02:37:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 47235072. Throughput: 0: 2669.8, 1: 2635.1. Samples: 47247584. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:37:48,446][86177] Avg episode reward: [(0, '-507.750'), (1, '-547.900')] -[2023-11-28 02:37:48,615][87426] Updated weights for policy 1, policy_version 92220 (0.0007) -[2023-11-28 02:37:49,552][87424] Updated weights for policy 0, policy_version 92326 (0.0012) -[2023-11-28 02:37:49,927][87424] Updated weights for policy 0, policy_version 92336 (0.0012) -[2023-11-28 02:37:50,322][87424] Updated weights for policy 0, policy_version 92346 (0.0012) -[2023-11-28 02:37:51,126][87426] Updated weights for policy 1, policy_version 92230 (0.0010) -[2023-11-28 02:37:51,514][87426] Updated weights for policy 1, policy_version 92240 (0.0012) -[2023-11-28 02:37:51,901][87426] Updated weights for policy 1, policy_version 92250 (0.0012) -[2023-11-28 02:37:52,285][87424] Updated weights for policy 0, policy_version 92356 (0.0011) -[2023-11-28 02:37:52,670][87424] Updated weights for policy 0, policy_version 92366 (0.0008) -[2023-11-28 02:37:53,047][87424] Updated weights for policy 0, policy_version 92376 (0.0008) -[2023-11-28 02:37:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 47267840. Throughput: 0: 2664.8, 1: 2645.5. Samples: 47279516. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:37:53,445][86177] Avg episode reward: [(0, '-504.890'), (1, '-547.270')] -[2023-11-28 02:37:53,821][87426] Updated weights for policy 1, policy_version 92260 (0.0011) -[2023-11-28 02:37:54,197][87426] Updated weights for policy 1, policy_version 92270 (0.0009) -[2023-11-28 02:37:54,580][87426] Updated weights for policy 1, policy_version 92280 (0.0010) -[2023-11-28 02:37:55,512][87424] Updated weights for policy 0, policy_version 92386 (0.0011) -[2023-11-28 02:37:55,901][87424] Updated weights for policy 0, policy_version 92396 (0.0012) -[2023-11-28 02:37:56,274][87424] Updated weights for policy 0, policy_version 92406 (0.0012) -[2023-11-28 02:37:56,294][87426] Updated weights for policy 1, policy_version 92290 (0.0009) -[2023-11-28 02:37:56,653][87424] Updated weights for policy 0, policy_version 92416 (0.0012) -[2023-11-28 02:37:56,667][87426] Updated weights for policy 1, policy_version 92300 (0.0011) -[2023-11-28 02:37:57,054][87426] Updated weights for policy 1, policy_version 92310 (0.0012) -[2023-11-28 02:37:57,428][87426] Updated weights for policy 1, policy_version 92320 (0.0012) -[2023-11-28 02:37:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 47292416. Throughput: 0: 2653.3, 1: 2627.9. Samples: 47302816. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:37:58,445][86177] Avg episode reward: [(0, '-503.670'), (1, '-542.220')] -[2023-11-28 02:37:58,605][87424] Updated weights for policy 0, policy_version 92426 (0.0012) -[2023-11-28 02:37:58,994][87424] Updated weights for policy 0, policy_version 92436 (0.0012) -[2023-11-28 02:37:59,381][87424] Updated weights for policy 0, policy_version 92446 (0.0011) -[2023-11-28 02:37:59,943][87426] Updated weights for policy 1, policy_version 92330 (0.0012) -[2023-11-28 02:38:00,330][87426] Updated weights for policy 1, policy_version 92340 (0.0012) -[2023-11-28 02:38:00,708][87426] Updated weights for policy 1, policy_version 92350 (0.0012) -[2023-11-28 02:38:01,399][87424] Updated weights for policy 0, policy_version 92456 (0.0011) -[2023-11-28 02:38:01,780][87424] Updated weights for policy 0, policy_version 92466 (0.0008) -[2023-11-28 02:38:02,159][87424] Updated weights for policy 0, policy_version 92476 (0.0009) -[2023-11-28 02:38:02,819][87426] Updated weights for policy 1, policy_version 92360 (0.0009) -[2023-11-28 02:38:03,205][87426] Updated weights for policy 1, policy_version 92370 (0.0010) -[2023-11-28 02:38:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 47316992. Throughput: 0: 2711.6, 1: 2629.2. Samples: 47328736. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:38:03,445][86177] Avg episode reward: [(0, '-504.010'), (1, '-509.410')] -[2023-11-28 02:38:03,583][87426] Updated weights for policy 1, policy_version 92380 (0.0011) -[2023-11-28 02:38:04,574][87424] Updated weights for policy 0, policy_version 92486 (0.0009) -[2023-11-28 02:38:04,947][87424] Updated weights for policy 0, policy_version 92496 (0.0007) -[2023-11-28 02:38:05,330][87424] Updated weights for policy 0, policy_version 92506 (0.0007) -[2023-11-28 02:38:06,042][87426] Updated weights for policy 1, policy_version 92390 (0.0010) -[2023-11-28 02:38:06,419][87426] Updated weights for policy 1, policy_version 92400 (0.0007) -[2023-11-28 02:38:06,811][87426] Updated weights for policy 1, policy_version 92410 (0.0009) -[2023-11-28 02:38:07,380][87424] Updated weights for policy 0, policy_version 92516 (0.0009) -[2023-11-28 02:38:07,762][87424] Updated weights for policy 0, policy_version 92526 (0.0010) -[2023-11-28 02:38:08,143][87424] Updated weights for policy 0, policy_version 92536 (0.0009) -[2023-11-28 02:38:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 47341568. Throughput: 0: 2729.2, 1: 2645.3. Samples: 47362288. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:38:08,445][86177] Avg episode reward: [(0, '-501.560'), (1, '-509.080')] -[2023-11-28 02:38:08,601][87426] Updated weights for policy 1, policy_version 92420 (0.0010) -[2023-11-28 02:38:08,986][87426] Updated weights for policy 1, policy_version 92430 (0.0008) -[2023-11-28 02:38:09,368][87426] Updated weights for policy 1, policy_version 92440 (0.0012) -[2023-11-28 02:38:10,524][87424] Updated weights for policy 0, policy_version 92546 (0.0012) -[2023-11-28 02:38:10,903][87424] Updated weights for policy 0, policy_version 92556 (0.0011) -[2023-11-28 02:38:11,287][87424] Updated weights for policy 0, policy_version 92566 (0.0011) -[2023-11-28 02:38:11,676][87424] Updated weights for policy 0, policy_version 92576 (0.0012) -[2023-11-28 02:38:11,708][87426] Updated weights for policy 1, policy_version 92450 (0.0011) -[2023-11-28 02:38:12,081][87426] Updated weights for policy 1, policy_version 92460 (0.0012) -[2023-11-28 02:38:12,467][87426] Updated weights for policy 1, policy_version 92470 (0.0012) -[2023-11-28 02:38:12,838][87426] Updated weights for policy 1, policy_version 92480 (0.0012) -[2023-11-28 02:38:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 47374336. Throughput: 0: 2708.8, 1: 2656.5. Samples: 47386664. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 02:38:13,445][86177] Avg episode reward: [(0, '-504.090'), (1, '-518.830')] -[2023-11-28 02:38:13,631][87424] Updated weights for policy 0, policy_version 92586 (0.0011) -[2023-11-28 02:38:14,006][87424] Updated weights for policy 0, policy_version 92596 (0.0011) -[2023-11-28 02:38:14,385][87424] Updated weights for policy 0, policy_version 92606 (0.0012) -[2023-11-28 02:38:15,221][87426] Updated weights for policy 1, policy_version 92490 (0.0009) -[2023-11-28 02:38:15,600][87426] Updated weights for policy 1, policy_version 92500 (0.0009) -[2023-11-28 02:38:15,978][87426] Updated weights for policy 1, policy_version 92510 (0.0008) -[2023-11-28 02:38:16,746][87424] Updated weights for policy 0, policy_version 92616 (0.0008) -[2023-11-28 02:38:17,129][87424] Updated weights for policy 0, policy_version 92626 (0.0008) -[2023-11-28 02:38:17,507][87424] Updated weights for policy 0, policy_version 92636 (0.0011) -[2023-11-28 02:38:18,053][87426] Updated weights for policy 1, policy_version 92520 (0.0011) -[2023-11-28 02:38:18,441][87426] Updated weights for policy 1, policy_version 92530 (0.0012) -[2023-11-28 02:38:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 47398912. Throughput: 0: 2705.1, 1: 2675.4. Samples: 47411716. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:38:18,446][86177] Avg episode reward: [(0, '-507.490'), (1, '-557.360')] -[2023-11-28 02:38:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000092640_23715840.pth... -[2023-11-28 02:38:18,493][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000090112_23068672.pth -[2023-11-28 02:38:18,828][87426] Updated weights for policy 1, policy_version 92540 (0.0011) -[2023-11-28 02:38:18,973][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000092544_23691264.pth... -[2023-11-28 02:38:19,005][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000089984_23035904.pth -[2023-11-28 02:38:19,458][87424] Updated weights for policy 0, policy_version 92646 (0.0012) -[2023-11-28 02:38:19,837][87424] Updated weights for policy 0, policy_version 92656 (0.0011) -[2023-11-28 02:38:20,223][87424] Updated weights for policy 0, policy_version 92666 (0.0012) -[2023-11-28 02:38:21,188][87426] Updated weights for policy 1, policy_version 92550 (0.0011) -[2023-11-28 02:38:21,564][87426] Updated weights for policy 1, policy_version 92560 (0.0012) -[2023-11-28 02:38:21,944][87426] Updated weights for policy 1, policy_version 92570 (0.0010) -[2023-11-28 02:38:22,790][87424] Updated weights for policy 0, policy_version 92676 (0.0012) -[2023-11-28 02:38:23,175][87424] Updated weights for policy 0, policy_version 92686 (0.0009) -[2023-11-28 02:38:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 47423488. Throughput: 0: 2679.6, 1: 2685.8. Samples: 47442416. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:38:23,445][86177] Avg episode reward: [(0, '-539.880'), (1, '-567.940')] -[2023-11-28 02:38:23,557][87424] Updated weights for policy 0, policy_version 92696 (0.0011) -[2023-11-28 02:38:24,401][87426] Updated weights for policy 1, policy_version 92580 (0.0011) -[2023-11-28 02:38:24,777][87426] Updated weights for policy 1, policy_version 92590 (0.0012) -[2023-11-28 02:38:25,159][87426] Updated weights for policy 1, policy_version 92600 (0.0012) -[2023-11-28 02:38:25,713][87424] Updated weights for policy 0, policy_version 92706 (0.0009) -[2023-11-28 02:38:26,093][87424] Updated weights for policy 0, policy_version 92716 (0.0012) -[2023-11-28 02:38:26,478][87424] Updated weights for policy 0, policy_version 92726 (0.0011) -[2023-11-28 02:38:26,862][87424] Updated weights for policy 0, policy_version 92736 (0.0011) -[2023-11-28 02:38:26,949][87426] Updated weights for policy 1, policy_version 92610 (0.0011) -[2023-11-28 02:38:27,332][87426] Updated weights for policy 1, policy_version 92620 (0.0008) -[2023-11-28 02:38:27,705][87426] Updated weights for policy 1, policy_version 92630 (0.0009) -[2023-11-28 02:38:28,087][87426] Updated weights for policy 1, policy_version 92640 (0.0011) -[2023-11-28 02:38:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 47456256. Throughput: 0: 2693.6, 1: 2714.6. Samples: 47467548. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:38:28,445][86177] Avg episode reward: [(0, '-544.680'), (1, '-608.200')] -[2023-11-28 02:38:28,645][87424] Updated weights for policy 0, policy_version 92746 (0.0009) -[2023-11-28 02:38:29,024][87424] Updated weights for policy 0, policy_version 92756 (0.0008) -[2023-11-28 02:38:29,411][87424] Updated weights for policy 0, policy_version 92766 (0.0007) -[2023-11-28 02:38:30,382][87426] Updated weights for policy 1, policy_version 92650 (0.0011) -[2023-11-28 02:38:30,762][87426] Updated weights for policy 1, policy_version 92660 (0.0011) -[2023-11-28 02:38:31,142][87426] Updated weights for policy 1, policy_version 92670 (0.0011) -[2023-11-28 02:38:31,714][87424] Updated weights for policy 0, policy_version 92776 (0.0011) -[2023-11-28 02:38:32,102][87424] Updated weights for policy 0, policy_version 92786 (0.0008) -[2023-11-28 02:38:32,478][87424] Updated weights for policy 0, policy_version 92796 (0.0009) -[2023-11-28 02:38:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 47480832. Throughput: 0: 2719.9, 1: 2716.5. Samples: 47492224. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:38:33,445][86177] Avg episode reward: [(0, '-542.450'), (1, '-611.760')] -[2023-11-28 02:38:33,492][87426] Updated weights for policy 1, policy_version 92680 (0.0008) -[2023-11-28 02:38:33,873][87426] Updated weights for policy 1, policy_version 92690 (0.0010) -[2023-11-28 02:38:34,253][87426] Updated weights for policy 1, policy_version 92700 (0.0011) -[2023-11-28 02:38:34,688][87424] Updated weights for policy 0, policy_version 92806 (0.0008) -[2023-11-28 02:38:35,075][87424] Updated weights for policy 0, policy_version 92816 (0.0011) -[2023-11-28 02:38:35,459][87424] Updated weights for policy 0, policy_version 92826 (0.0010) -[2023-11-28 02:38:36,036][87426] Updated weights for policy 1, policy_version 92710 (0.0011) -[2023-11-28 02:38:36,408][87426] Updated weights for policy 1, policy_version 92720 (0.0012) -[2023-11-28 02:38:36,785][87426] Updated weights for policy 1, policy_version 92730 (0.0010) -[2023-11-28 02:38:37,399][87424] Updated weights for policy 0, policy_version 92836 (0.0012) -[2023-11-28 02:38:37,781][87424] Updated weights for policy 0, policy_version 92846 (0.0012) -[2023-11-28 02:38:38,160][87424] Updated weights for policy 0, policy_version 92856 (0.0010) -[2023-11-28 02:38:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 47505408. Throughput: 0: 2748.8, 1: 2720.4. Samples: 47525632. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:38:38,445][86177] Avg episode reward: [(0, '-537.870'), (1, '-591.260')] -[2023-11-28 02:38:39,102][87426] Updated weights for policy 1, policy_version 92740 (0.0009) -[2023-11-28 02:38:39,478][87426] Updated weights for policy 1, policy_version 92750 (0.0012) -[2023-11-28 02:38:39,852][87426] Updated weights for policy 1, policy_version 92760 (0.0012) -[2023-11-28 02:38:40,431][87424] Updated weights for policy 0, policy_version 92866 (0.0008) -[2023-11-28 02:38:40,813][87424] Updated weights for policy 0, policy_version 92876 (0.0008) -[2023-11-28 02:38:41,199][87424] Updated weights for policy 0, policy_version 92886 (0.0008) -[2023-11-28 02:38:41,591][87424] Updated weights for policy 0, policy_version 92896 (0.0009) -[2023-11-28 02:38:42,121][87426] Updated weights for policy 1, policy_version 92770 (0.0010) -[2023-11-28 02:38:42,503][87426] Updated weights for policy 1, policy_version 92780 (0.0011) -[2023-11-28 02:38:42,879][87426] Updated weights for policy 1, policy_version 92790 (0.0010) -[2023-11-28 02:38:43,256][87426] Updated weights for policy 1, policy_version 92800 (0.0010) -[2023-11-28 02:38:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 47538176. Throughput: 0: 2748.3, 1: 2730.6. Samples: 47549364. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:38:43,445][86177] Avg episode reward: [(0, '-507.140'), (1, '-581.490')] -[2023-11-28 02:38:43,824][87424] Updated weights for policy 0, policy_version 92906 (0.0012) -[2023-11-28 02:38:44,208][87424] Updated weights for policy 0, policy_version 92916 (0.0012) -[2023-11-28 02:38:44,587][87424] Updated weights for policy 0, policy_version 92926 (0.0012) -[2023-11-28 02:38:45,210][87426] Updated weights for policy 1, policy_version 92810 (0.0011) -[2023-11-28 02:38:45,591][87426] Updated weights for policy 1, policy_version 92820 (0.0011) -[2023-11-28 02:38:45,974][87426] Updated weights for policy 1, policy_version 92830 (0.0012) -[2023-11-28 02:38:46,820][87424] Updated weights for policy 0, policy_version 92936 (0.0012) -[2023-11-28 02:38:47,213][87424] Updated weights for policy 0, policy_version 92946 (0.0012) -[2023-11-28 02:38:47,594][87424] Updated weights for policy 0, policy_version 92956 (0.0012) -[2023-11-28 02:38:48,006][87426] Updated weights for policy 1, policy_version 92840 (0.0011) -[2023-11-28 02:38:48,378][87426] Updated weights for policy 1, policy_version 92850 (0.0008) -[2023-11-28 02:38:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 47562752. Throughput: 0: 2722.7, 1: 2732.2. Samples: 47574204. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:38:48,445][86177] Avg episode reward: [(0, '-496.640'), (1, '-565.210')] -[2023-11-28 02:38:48,754][87426] Updated weights for policy 1, policy_version 92860 (0.0007) -[2023-11-28 02:38:50,154][87424] Updated weights for policy 0, policy_version 92966 (0.0010) -[2023-11-28 02:38:50,532][87424] Updated weights for policy 0, policy_version 92976 (0.0009) -[2023-11-28 02:38:50,908][87424] Updated weights for policy 0, policy_version 92986 (0.0008) -[2023-11-28 02:38:51,143][87426] Updated weights for policy 1, policy_version 92870 (0.0011) -[2023-11-28 02:38:51,510][87426] Updated weights for policy 1, policy_version 92880 (0.0012) -[2023-11-28 02:38:51,888][87426] Updated weights for policy 1, policy_version 92890 (0.0012) -[2023-11-28 02:38:53,270][87424] Updated weights for policy 0, policy_version 92996 (0.0010) -[2023-11-28 02:38:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 47587328. Throughput: 0: 2674.0, 1: 2722.0. Samples: 47605112. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:38:53,445][86177] Avg episode reward: [(0, '-500.360'), (1, '-561.010')] -[2023-11-28 02:38:53,656][87424] Updated weights for policy 0, policy_version 93006 (0.0011) -[2023-11-28 02:38:54,040][87424] Updated weights for policy 0, policy_version 93016 (0.0012) -[2023-11-28 02:38:54,506][87426] Updated weights for policy 1, policy_version 92900 (0.0009) -[2023-11-28 02:38:54,898][87426] Updated weights for policy 1, policy_version 92910 (0.0007) -[2023-11-28 02:38:55,279][87426] Updated weights for policy 1, policy_version 92920 (0.0007) -[2023-11-28 02:38:56,137][87424] Updated weights for policy 0, policy_version 93026 (0.0012) -[2023-11-28 02:38:56,532][87424] Updated weights for policy 0, policy_version 93036 (0.0012) -[2023-11-28 02:38:56,930][87424] Updated weights for policy 0, policy_version 93046 (0.0010) -[2023-11-28 02:38:57,309][87424] Updated weights for policy 0, policy_version 93056 (0.0008) -[2023-11-28 02:38:57,737][87426] Updated weights for policy 1, policy_version 92930 (0.0008) -[2023-11-28 02:38:58,114][87426] Updated weights for policy 1, policy_version 92940 (0.0007) -[2023-11-28 02:38:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 47611904. Throughput: 0: 2685.6, 1: 2696.3. Samples: 47628852. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:38:58,446][86177] Avg episode reward: [(0, '-501.920'), (1, '-577.270')] -[2023-11-28 02:38:58,492][87426] Updated weights for policy 1, policy_version 92950 (0.0007) -[2023-11-28 02:38:58,881][87426] Updated weights for policy 1, policy_version 92960 (0.0010) -[2023-11-28 02:38:59,531][87424] Updated weights for policy 0, policy_version 93066 (0.0007) -[2023-11-28 02:38:59,916][87424] Updated weights for policy 0, policy_version 93076 (0.0008) -[2023-11-28 02:39:00,302][87424] Updated weights for policy 0, policy_version 93086 (0.0010) -[2023-11-28 02:39:01,305][87426] Updated weights for policy 1, policy_version 92970 (0.0008) -[2023-11-28 02:39:01,679][87426] Updated weights for policy 1, policy_version 92980 (0.0009) -[2023-11-28 02:39:02,065][87426] Updated weights for policy 1, policy_version 92990 (0.0009) -[2023-11-28 02:39:02,647][87424] Updated weights for policy 0, policy_version 93096 (0.0012) -[2023-11-28 02:39:03,043][87424] Updated weights for policy 0, policy_version 93106 (0.0010) -[2023-11-28 02:39:03,424][87424] Updated weights for policy 0, policy_version 93116 (0.0012) -[2023-11-28 02:39:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 47636480. Throughput: 0: 2662.3, 1: 2686.7. Samples: 47652420. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:39:03,445][86177] Avg episode reward: [(0, '-506.060'), (1, '-584.540')] -[2023-11-28 02:39:04,414][87426] Updated weights for policy 1, policy_version 93000 (0.0011) -[2023-11-28 02:39:04,786][87426] Updated weights for policy 1, policy_version 93010 (0.0012) -[2023-11-28 02:39:05,167][87426] Updated weights for policy 1, policy_version 93020 (0.0012) -[2023-11-28 02:39:05,471][87424] Updated weights for policy 0, policy_version 93126 (0.0009) -[2023-11-28 02:39:05,856][87424] Updated weights for policy 0, policy_version 93136 (0.0007) -[2023-11-28 02:39:06,234][87424] Updated weights for policy 0, policy_version 93146 (0.0007) -[2023-11-28 02:39:07,165][87426] Updated weights for policy 1, policy_version 93030 (0.0010) -[2023-11-28 02:39:07,547][87426] Updated weights for policy 1, policy_version 93040 (0.0011) -[2023-11-28 02:39:07,932][87426] Updated weights for policy 1, policy_version 93050 (0.0011) -[2023-11-28 02:39:08,400][87424] Updated weights for policy 0, policy_version 93156 (0.0008) -[2023-11-28 02:39:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 47669248. Throughput: 0: 2696.4, 1: 2696.1. Samples: 47685076. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 02:39:08,445][86177] Avg episode reward: [(0, '-506.960'), (1, '-568.700')] -[2023-11-28 02:39:08,790][87424] Updated weights for policy 0, policy_version 93166 (0.0010) -[2023-11-28 02:39:09,171][87424] Updated weights for policy 0, policy_version 93176 (0.0011) -[2023-11-28 02:39:10,198][87426] Updated weights for policy 1, policy_version 93060 (0.0008) -[2023-11-28 02:39:10,590][87426] Updated weights for policy 1, policy_version 93070 (0.0008) -[2023-11-28 02:39:10,959][87426] Updated weights for policy 1, policy_version 93080 (0.0009) -[2023-11-28 02:39:11,586][87424] Updated weights for policy 0, policy_version 93186 (0.0011) -[2023-11-28 02:39:11,978][87424] Updated weights for policy 0, policy_version 93196 (0.0012) -[2023-11-28 02:39:12,357][87424] Updated weights for policy 0, policy_version 93206 (0.0012) -[2023-11-28 02:39:12,752][87424] Updated weights for policy 0, policy_version 93216 (0.0012) -[2023-11-28 02:39:12,880][87426] Updated weights for policy 1, policy_version 93090 (0.0008) -[2023-11-28 02:39:13,251][87426] Updated weights for policy 1, policy_version 93100 (0.0011) -[2023-11-28 02:39:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 47693824. Throughput: 0: 2692.6, 1: 2702.6. Samples: 47710332. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:13,446][86177] Avg episode reward: [(0, '-506.870'), (1, '-595.720')] -[2023-11-28 02:39:13,635][87426] Updated weights for policy 1, policy_version 93110 (0.0012) -[2023-11-28 02:39:14,010][87426] Updated weights for policy 1, policy_version 93120 (0.0011) -[2023-11-28 02:39:14,661][87424] Updated weights for policy 0, policy_version 93226 (0.0007) -[2023-11-28 02:39:15,039][87424] Updated weights for policy 0, policy_version 93236 (0.0007) -[2023-11-28 02:39:15,423][87424] Updated weights for policy 0, policy_version 93246 (0.0008) -[2023-11-28 02:39:16,236][87426] Updated weights for policy 1, policy_version 93130 (0.0012) -[2023-11-28 02:39:16,628][87426] Updated weights for policy 1, policy_version 93140 (0.0012) -[2023-11-28 02:39:16,996][87426] Updated weights for policy 1, policy_version 93150 (0.0012) -[2023-11-28 02:39:17,510][87424] Updated weights for policy 0, policy_version 93256 (0.0007) -[2023-11-28 02:39:17,903][87424] Updated weights for policy 0, policy_version 93266 (0.0010) -[2023-11-28 02:39:18,286][87424] Updated weights for policy 0, policy_version 93276 (0.0010) -[2023-11-28 02:39:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 47726592. Throughput: 0: 2693.8, 1: 2694.5. Samples: 47734696. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:18,445][86177] Avg episode reward: [(0, '-498.070'), (1, '-551.380')] -[2023-11-28 02:39:19,557][87426] Updated weights for policy 1, policy_version 93160 (0.0011) -[2023-11-28 02:39:19,926][87426] Updated weights for policy 1, policy_version 93170 (0.0010) -[2023-11-28 02:39:20,225][87424] Updated weights for policy 0, policy_version 93286 (0.0010) -[2023-11-28 02:39:20,311][87426] Updated weights for policy 1, policy_version 93180 (0.0011) -[2023-11-28 02:39:20,609][87424] Updated weights for policy 0, policy_version 93296 (0.0011) -[2023-11-28 02:39:21,007][87424] Updated weights for policy 0, policy_version 93306 (0.0009) -[2023-11-28 02:39:22,703][87426] Updated weights for policy 1, policy_version 93190 (0.0010) -[2023-11-28 02:39:23,085][87426] Updated weights for policy 1, policy_version 93200 (0.0010) -[2023-11-28 02:39:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 47742976. Throughput: 0: 2668.8, 1: 2663.2. Samples: 47765572. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:23,445][86177] Avg episode reward: [(0, '-491.360'), (1, '-552.450')] -[2023-11-28 02:39:23,466][87426] Updated weights for policy 1, policy_version 93210 (0.0011) -[2023-11-28 02:39:23,480][87424] Updated weights for policy 0, policy_version 93316 (0.0011) -[2023-11-28 02:39:23,865][87424] Updated weights for policy 0, policy_version 93326 (0.0008) -[2023-11-28 02:39:24,245][87424] Updated weights for policy 0, policy_version 93336 (0.0007) -[2023-11-28 02:39:24,555][87281] Saving new best policy, reward=-491.360! -[2023-11-28 02:39:25,925][87426] Updated weights for policy 1, policy_version 93220 (0.0010) -[2023-11-28 02:39:26,257][87424] Updated weights for policy 0, policy_version 93346 (0.0008) -[2023-11-28 02:39:26,296][87426] Updated weights for policy 1, policy_version 93230 (0.0009) -[2023-11-28 02:39:26,642][87424] Updated weights for policy 0, policy_version 93356 (0.0012) -[2023-11-28 02:39:26,678][87426] Updated weights for policy 1, policy_version 93240 (0.0007) -[2023-11-28 02:39:27,017][87424] Updated weights for policy 0, policy_version 93366 (0.0010) -[2023-11-28 02:39:27,401][87424] Updated weights for policy 0, policy_version 93376 (0.0007) -[2023-11-28 02:39:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 47775744. Throughput: 0: 2681.0, 1: 2642.9. Samples: 47788940. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:28,445][86177] Avg episode reward: [(0, '-491.370'), (1, '-551.250')] -[2023-11-28 02:39:28,989][87426] Updated weights for policy 1, policy_version 93250 (0.0008) -[2023-11-28 02:39:29,365][87426] Updated weights for policy 1, policy_version 93260 (0.0008) -[2023-11-28 02:39:29,744][87426] Updated weights for policy 1, policy_version 93270 (0.0007) -[2023-11-28 02:39:29,903][87424] Updated weights for policy 0, policy_version 93386 (0.0008) -[2023-11-28 02:39:30,125][87426] Updated weights for policy 1, policy_version 93280 (0.0010) -[2023-11-28 02:39:30,287][87424] Updated weights for policy 0, policy_version 93396 (0.0012) -[2023-11-28 02:39:30,664][87424] Updated weights for policy 0, policy_version 93406 (0.0012) -[2023-11-28 02:39:31,990][87426] Updated weights for policy 1, policy_version 93290 (0.0012) -[2023-11-28 02:39:32,368][87426] Updated weights for policy 1, policy_version 93300 (0.0012) -[2023-11-28 02:39:32,754][87426] Updated weights for policy 1, policy_version 93310 (0.0011) -[2023-11-28 02:39:33,068][87424] Updated weights for policy 0, policy_version 93416 (0.0011) -[2023-11-28 02:39:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 47800320. Throughput: 0: 2667.8, 1: 2642.8. Samples: 47813180. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:33,445][86177] Avg episode reward: [(0, '-494.900'), (1, '-529.990')] -[2023-11-28 02:39:33,452][87424] Updated weights for policy 0, policy_version 93426 (0.0012) -[2023-11-28 02:39:33,830][87424] Updated weights for policy 0, policy_version 93436 (0.0012) -[2023-11-28 02:39:35,126][87426] Updated weights for policy 1, policy_version 93320 (0.0011) -[2023-11-28 02:39:35,511][87426] Updated weights for policy 1, policy_version 93330 (0.0012) -[2023-11-28 02:39:35,891][87426] Updated weights for policy 1, policy_version 93340 (0.0009) -[2023-11-28 02:39:36,233][87424] Updated weights for policy 0, policy_version 93446 (0.0009) -[2023-11-28 02:39:36,622][87424] Updated weights for policy 0, policy_version 93456 (0.0010) -[2023-11-28 02:39:37,006][87424] Updated weights for policy 0, policy_version 93466 (0.0012) -[2023-11-28 02:39:37,906][87426] Updated weights for policy 1, policy_version 93350 (0.0010) -[2023-11-28 02:39:38,283][87426] Updated weights for policy 1, policy_version 93360 (0.0012) -[2023-11-28 02:39:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 47824896. Throughput: 0: 2679.4, 1: 2657.4. Samples: 47845268. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:38,445][86177] Avg episode reward: [(0, '-496.550'), (1, '-533.250')] -[2023-11-28 02:39:38,668][87426] Updated weights for policy 1, policy_version 93370 (0.0011) -[2023-11-28 02:39:39,001][87424] Updated weights for policy 0, policy_version 93476 (0.0012) -[2023-11-28 02:39:39,385][87424] Updated weights for policy 0, policy_version 93486 (0.0012) -[2023-11-28 02:39:39,767][87424] Updated weights for policy 0, policy_version 93496 (0.0011) -[2023-11-28 02:39:40,281][87426] Updated weights for policy 1, policy_version 93380 (0.0010) -[2023-11-28 02:39:40,651][87426] Updated weights for policy 1, policy_version 93390 (0.0011) -[2023-11-28 02:39:41,032][87426] Updated weights for policy 1, policy_version 93400 (0.0012) -[2023-11-28 02:39:42,264][87424] Updated weights for policy 0, policy_version 93506 (0.0014) -[2023-11-28 02:39:42,642][87424] Updated weights for policy 0, policy_version 93516 (0.0011) -[2023-11-28 02:39:43,022][87424] Updated weights for policy 0, policy_version 93526 (0.0011) -[2023-11-28 02:39:43,402][87424] Updated weights for policy 0, policy_version 93536 (0.0011) -[2023-11-28 02:39:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 47857664. Throughput: 0: 2672.7, 1: 2663.1. Samples: 47868964. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:43,445][86177] Avg episode reward: [(0, '-496.700'), (1, '-529.760')] -[2023-11-28 02:39:43,598][87426] Updated weights for policy 1, policy_version 93410 (0.0008) -[2023-11-28 02:39:43,977][87426] Updated weights for policy 1, policy_version 93420 (0.0007) -[2023-11-28 02:39:44,352][87426] Updated weights for policy 1, policy_version 93430 (0.0007) -[2023-11-28 02:39:44,732][87426] Updated weights for policy 1, policy_version 93440 (0.0008) -[2023-11-28 02:39:46,042][87424] Updated weights for policy 0, policy_version 93546 (0.0008) -[2023-11-28 02:39:46,432][87424] Updated weights for policy 0, policy_version 93556 (0.0007) -[2023-11-28 02:39:46,821][87424] Updated weights for policy 0, policy_version 93566 (0.0007) -[2023-11-28 02:39:47,195][87426] Updated weights for policy 1, policy_version 93450 (0.0008) -[2023-11-28 02:39:47,579][87426] Updated weights for policy 1, policy_version 93460 (0.0008) -[2023-11-28 02:39:47,966][87426] Updated weights for policy 1, policy_version 93470 (0.0007) -[2023-11-28 02:39:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 47882240. Throughput: 0: 2674.3, 1: 2645.9. Samples: 47891828. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:48,445][86177] Avg episode reward: [(0, '-498.810'), (1, '-537.850')] -[2023-11-28 02:39:48,701][87424] Updated weights for policy 0, policy_version 93576 (0.0009) -[2023-11-28 02:39:49,088][87424] Updated weights for policy 0, policy_version 93586 (0.0011) -[2023-11-28 02:39:49,466][87424] Updated weights for policy 0, policy_version 93596 (0.0011) -[2023-11-28 02:39:50,462][87426] Updated weights for policy 1, policy_version 93480 (0.0010) -[2023-11-28 02:39:50,842][87426] Updated weights for policy 1, policy_version 93490 (0.0012) -[2023-11-28 02:39:51,223][87426] Updated weights for policy 1, policy_version 93500 (0.0011) -[2023-11-28 02:39:51,345][87424] Updated weights for policy 0, policy_version 93606 (0.0012) -[2023-11-28 02:39:51,730][87424] Updated weights for policy 0, policy_version 93616 (0.0012) -[2023-11-28 02:39:52,111][87424] Updated weights for policy 0, policy_version 93626 (0.0011) -[2023-11-28 02:39:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 47906816. Throughput: 0: 2664.0, 1: 2637.4. Samples: 47923640. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:53,445][86177] Avg episode reward: [(0, '-495.390'), (1, '-535.130')] -[2023-11-28 02:39:53,633][87426] Updated weights for policy 1, policy_version 93510 (0.0012) -[2023-11-28 02:39:54,011][87426] Updated weights for policy 1, policy_version 93520 (0.0012) -[2023-11-28 02:39:54,392][87426] Updated weights for policy 1, policy_version 93530 (0.0012) -[2023-11-28 02:39:54,469][87424] Updated weights for policy 0, policy_version 93636 (0.0010) -[2023-11-28 02:39:54,852][87424] Updated weights for policy 0, policy_version 93646 (0.0008) -[2023-11-28 02:39:55,224][87424] Updated weights for policy 0, policy_version 93656 (0.0008) -[2023-11-28 02:39:56,507][87426] Updated weights for policy 1, policy_version 93540 (0.0012) -[2023-11-28 02:39:56,884][87426] Updated weights for policy 1, policy_version 93550 (0.0012) -[2023-11-28 02:39:57,012][87424] Updated weights for policy 0, policy_version 93666 (0.0008) -[2023-11-28 02:39:57,259][87426] Updated weights for policy 1, policy_version 93560 (0.0011) -[2023-11-28 02:39:57,400][87424] Updated weights for policy 0, policy_version 93676 (0.0009) -[2023-11-28 02:39:57,788][87424] Updated weights for policy 0, policy_version 93686 (0.0011) -[2023-11-28 02:39:58,166][87424] Updated weights for policy 0, policy_version 93696 (0.0012) -[2023-11-28 02:39:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 47939584. Throughput: 0: 2664.5, 1: 2630.4. Samples: 47948600. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:39:58,445][86177] Avg episode reward: [(0, '-494.410'), (1, '-533.300')] -[2023-11-28 02:39:59,243][87426] Updated weights for policy 1, policy_version 93570 (0.0012) -[2023-11-28 02:39:59,634][87426] Updated weights for policy 1, policy_version 93580 (0.0012) -[2023-11-28 02:40:00,016][87426] Updated weights for policy 1, policy_version 93590 (0.0010) -[2023-11-28 02:40:00,384][87424] Updated weights for policy 0, policy_version 93706 (0.0012) -[2023-11-28 02:40:00,391][87426] Updated weights for policy 1, policy_version 93600 (0.0010) -[2023-11-28 02:40:00,780][87424] Updated weights for policy 0, policy_version 93716 (0.0012) -[2023-11-28 02:40:01,160][87424] Updated weights for policy 0, policy_version 93726 (0.0008) -[2023-11-28 02:40:02,722][87426] Updated weights for policy 1, policy_version 93610 (0.0012) -[2023-11-28 02:40:03,102][87426] Updated weights for policy 1, policy_version 93620 (0.0010) -[2023-11-28 02:40:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 47955968. Throughput: 0: 2665.9, 1: 2647.6. Samples: 47973804. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:40:03,445][86177] Avg episode reward: [(0, '-493.190'), (1, '-542.460')] -[2023-11-28 02:40:03,498][87426] Updated weights for policy 1, policy_version 93630 (0.0009) -[2023-11-28 02:40:03,628][87424] Updated weights for policy 0, policy_version 93736 (0.0010) -[2023-11-28 02:40:04,011][87424] Updated weights for policy 0, policy_version 93746 (0.0008) -[2023-11-28 02:40:04,399][87424] Updated weights for policy 0, policy_version 93756 (0.0010) -[2023-11-28 02:40:05,873][87426] Updated weights for policy 1, policy_version 93640 (0.0008) -[2023-11-28 02:40:06,259][87426] Updated weights for policy 1, policy_version 93650 (0.0007) -[2023-11-28 02:40:06,449][87424] Updated weights for policy 0, policy_version 93766 (0.0012) -[2023-11-28 02:40:06,641][87426] Updated weights for policy 1, policy_version 93660 (0.0008) -[2023-11-28 02:40:06,836][87424] Updated weights for policy 0, policy_version 93776 (0.0012) -[2023-11-28 02:40:07,218][87424] Updated weights for policy 0, policy_version 93786 (0.0011) -[2023-11-28 02:40:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 47988736. Throughput: 0: 2671.5, 1: 2671.5. Samples: 48006012. Policy #0 lag: (min: 26.0, avg: 52.8, max: 75.0) -[2023-11-28 02:40:08,446][86177] Avg episode reward: [(0, '-492.800'), (1, '-541.430')] -[2023-11-28 02:40:08,801][87426] Updated weights for policy 1, policy_version 93670 (0.0011) -[2023-11-28 02:40:09,177][87426] Updated weights for policy 1, policy_version 93680 (0.0011) -[2023-11-28 02:40:09,327][87424] Updated weights for policy 0, policy_version 93796 (0.0012) -[2023-11-28 02:40:09,560][87426] Updated weights for policy 1, policy_version 93690 (0.0011) -[2023-11-28 02:40:09,715][87424] Updated weights for policy 0, policy_version 93806 (0.0012) -[2023-11-28 02:40:10,096][87424] Updated weights for policy 0, policy_version 93816 (0.0012) -[2023-11-28 02:40:11,718][87426] Updated weights for policy 1, policy_version 93700 (0.0011) -[2023-11-28 02:40:12,086][87426] Updated weights for policy 1, policy_version 93710 (0.0010) -[2023-11-28 02:40:12,189][87424] Updated weights for policy 0, policy_version 93826 (0.0012) -[2023-11-28 02:40:12,463][87426] Updated weights for policy 1, policy_version 93720 (0.0009) -[2023-11-28 02:40:12,571][87424] Updated weights for policy 0, policy_version 93836 (0.0009) -[2023-11-28 02:40:12,956][87424] Updated weights for policy 0, policy_version 93846 (0.0009) -[2023-11-28 02:40:13,335][87424] Updated weights for policy 0, policy_version 93856 (0.0008) -[2023-11-28 02:40:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 48021504. Throughput: 0: 2679.2, 1: 2678.6. Samples: 48030040. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:13,445][86177] Avg episode reward: [(0, '-496.900'), (1, '-534.680')] -[2023-11-28 02:40:14,566][87426] Updated weights for policy 1, policy_version 93730 (0.0011) -[2023-11-28 02:40:14,943][87426] Updated weights for policy 1, policy_version 93740 (0.0011) -[2023-11-28 02:40:15,117][87424] Updated weights for policy 0, policy_version 93866 (0.0008) -[2023-11-28 02:40:15,312][87426] Updated weights for policy 1, policy_version 93750 (0.0009) -[2023-11-28 02:40:15,503][87424] Updated weights for policy 0, policy_version 93876 (0.0010) -[2023-11-28 02:40:15,692][87426] Updated weights for policy 1, policy_version 93760 (0.0010) -[2023-11-28 02:40:15,891][87424] Updated weights for policy 0, policy_version 93886 (0.0010) -[2023-11-28 02:40:17,612][87426] Updated weights for policy 1, policy_version 93770 (0.0010) -[2023-11-28 02:40:17,992][87426] Updated weights for policy 1, policy_version 93780 (0.0007) -[2023-11-28 02:40:18,018][87424] Updated weights for policy 0, policy_version 93896 (0.0010) -[2023-11-28 02:40:18,378][87426] Updated weights for policy 1, policy_version 93790 (0.0008) -[2023-11-28 02:40:18,399][87424] Updated weights for policy 0, policy_version 93906 (0.0007) -[2023-11-28 02:40:18,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 48046080. Throughput: 0: 2710.1, 1: 2673.1. Samples: 48055424. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:18,445][86177] Avg episode reward: [(0, '-501.920'), (1, '-535.080')] -[2023-11-28 02:40:18,452][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000093792_24010752.pth... -[2023-11-28 02:40:18,484][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000091264_23363584.pth -[2023-11-28 02:40:18,777][87424] Updated weights for policy 0, policy_version 93916 (0.0008) -[2023-11-28 02:40:18,931][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000093920_24043520.pth... -[2023-11-28 02:40:18,963][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000091392_23396352.pth -[2023-11-28 02:40:20,850][87426] Updated weights for policy 1, policy_version 93800 (0.0011) -[2023-11-28 02:40:21,197][87424] Updated weights for policy 0, policy_version 93926 (0.0010) -[2023-11-28 02:40:21,233][87426] Updated weights for policy 1, policy_version 93810 (0.0012) -[2023-11-28 02:40:21,581][87424] Updated weights for policy 0, policy_version 93936 (0.0010) -[2023-11-28 02:40:21,613][87426] Updated weights for policy 1, policy_version 93820 (0.0010) -[2023-11-28 02:40:21,967][87424] Updated weights for policy 0, policy_version 93946 (0.0012) -[2023-11-28 02:40:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 48070656. Throughput: 0: 2721.5, 1: 2657.3. Samples: 48087316. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:23,445][86177] Avg episode reward: [(0, '-501.980'), (1, '-527.220')] -[2023-11-28 02:40:24,103][87426] Updated weights for policy 1, policy_version 93830 (0.0011) -[2023-11-28 02:40:24,209][87424] Updated weights for policy 0, policy_version 93956 (0.0010) -[2023-11-28 02:40:24,472][87426] Updated weights for policy 1, policy_version 93840 (0.0009) -[2023-11-28 02:40:24,607][87424] Updated weights for policy 0, policy_version 93966 (0.0011) -[2023-11-28 02:40:24,854][87426] Updated weights for policy 1, policy_version 93850 (0.0007) -[2023-11-28 02:40:24,990][87424] Updated weights for policy 0, policy_version 93976 (0.0012) -[2023-11-28 02:40:27,221][87424] Updated weights for policy 0, policy_version 93986 (0.0012) -[2023-11-28 02:40:27,351][87426] Updated weights for policy 1, policy_version 93860 (0.0010) -[2023-11-28 02:40:27,604][87424] Updated weights for policy 0, policy_version 93996 (0.0012) -[2023-11-28 02:40:27,733][87426] Updated weights for policy 1, policy_version 93870 (0.0011) -[2023-11-28 02:40:27,990][87424] Updated weights for policy 0, policy_version 94006 (0.0011) -[2023-11-28 02:40:28,106][87426] Updated weights for policy 1, policy_version 93880 (0.0012) -[2023-11-28 02:40:28,366][87424] Updated weights for policy 0, policy_version 94016 (0.0010) -[2023-11-28 02:40:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 48103424. Throughput: 0: 2721.2, 1: 2682.0. Samples: 48112108. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:28,445][86177] Avg episode reward: [(0, '-503.010'), (1, '-521.940')] -[2023-11-28 02:40:30,253][87426] Updated weights for policy 1, policy_version 93890 (0.0011) -[2023-11-28 02:40:30,632][87426] Updated weights for policy 1, policy_version 93900 (0.0009) -[2023-11-28 02:40:30,753][87424] Updated weights for policy 0, policy_version 94026 (0.0012) -[2023-11-28 02:40:31,011][87426] Updated weights for policy 1, policy_version 93910 (0.0007) -[2023-11-28 02:40:31,137][87424] Updated weights for policy 0, policy_version 94036 (0.0012) -[2023-11-28 02:40:31,392][87426] Updated weights for policy 1, policy_version 93920 (0.0007) -[2023-11-28 02:40:31,522][87424] Updated weights for policy 0, policy_version 94046 (0.0012) -[2023-11-28 02:40:33,381][87426] Updated weights for policy 1, policy_version 93930 (0.0008) -[2023-11-28 02:40:33,431][87424] Updated weights for policy 0, policy_version 94056 (0.0008) -[2023-11-28 02:40:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 48119808. Throughput: 0: 2750.6, 1: 2706.9. Samples: 48137416. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:33,445][86177] Avg episode reward: [(0, '-507.800'), (1, '-517.240')] -[2023-11-28 02:40:33,764][87426] Updated weights for policy 1, policy_version 93940 (0.0007) -[2023-11-28 02:40:33,818][87424] Updated weights for policy 0, policy_version 94066 (0.0008) -[2023-11-28 02:40:34,140][87426] Updated weights for policy 1, policy_version 93950 (0.0007) -[2023-11-28 02:40:34,202][87424] Updated weights for policy 0, policy_version 94076 (0.0007) -[2023-11-28 02:40:36,269][87424] Updated weights for policy 0, policy_version 94086 (0.0010) -[2023-11-28 02:40:36,451][87426] Updated weights for policy 1, policy_version 93960 (0.0011) -[2023-11-28 02:40:36,664][87424] Updated weights for policy 0, policy_version 94096 (0.0009) -[2023-11-28 02:40:36,825][87426] Updated weights for policy 1, policy_version 93970 (0.0010) -[2023-11-28 02:40:37,043][87424] Updated weights for policy 0, policy_version 94106 (0.0011) -[2023-11-28 02:40:37,205][87426] Updated weights for policy 1, policy_version 93980 (0.0007) -[2023-11-28 02:40:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 48152576. Throughput: 0: 2743.7, 1: 2698.8. Samples: 48168556. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:38,445][86177] Avg episode reward: [(0, '-504.880'), (1, '-518.860')] -[2023-11-28 02:40:39,174][87426] Updated weights for policy 1, policy_version 93990 (0.0011) -[2023-11-28 02:40:39,456][87424] Updated weights for policy 0, policy_version 94116 (0.0011) -[2023-11-28 02:40:39,554][87426] Updated weights for policy 1, policy_version 94000 (0.0010) -[2023-11-28 02:40:39,849][87424] Updated weights for policy 0, policy_version 94126 (0.0009) -[2023-11-28 02:40:39,936][87426] Updated weights for policy 1, policy_version 94010 (0.0009) -[2023-11-28 02:40:40,236][87424] Updated weights for policy 0, policy_version 94136 (0.0011) -[2023-11-28 02:40:42,083][87424] Updated weights for policy 0, policy_version 94146 (0.0011) -[2023-11-28 02:40:42,370][87426] Updated weights for policy 1, policy_version 94020 (0.0010) -[2023-11-28 02:40:42,468][87424] Updated weights for policy 0, policy_version 94156 (0.0011) -[2023-11-28 02:40:42,745][87426] Updated weights for policy 1, policy_version 94030 (0.0010) -[2023-11-28 02:40:42,843][87424] Updated weights for policy 0, policy_version 94166 (0.0011) -[2023-11-28 02:40:43,134][87426] Updated weights for policy 1, policy_version 94040 (0.0012) -[2023-11-28 02:40:43,224][87424] Updated weights for policy 0, policy_version 94176 (0.0011) -[2023-11-28 02:40:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 48185344. Throughput: 0: 2737.4, 1: 2690.2. Samples: 48192844. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:43,445][86177] Avg episode reward: [(0, '-511.020'), (1, '-517.730')] -[2023-11-28 02:40:45,284][87424] Updated weights for policy 0, policy_version 94186 (0.0010) -[2023-11-28 02:40:45,439][87426] Updated weights for policy 1, policy_version 94050 (0.0011) -[2023-11-28 02:40:45,678][87424] Updated weights for policy 0, policy_version 94196 (0.0011) -[2023-11-28 02:40:45,815][87426] Updated weights for policy 1, policy_version 94060 (0.0010) -[2023-11-28 02:40:46,057][87424] Updated weights for policy 0, policy_version 94206 (0.0011) -[2023-11-28 02:40:46,197][87426] Updated weights for policy 1, policy_version 94070 (0.0011) -[2023-11-28 02:40:46,582][87426] Updated weights for policy 1, policy_version 94080 (0.0011) -[2023-11-28 02:40:48,067][87424] Updated weights for policy 0, policy_version 94216 (0.0012) -[2023-11-28 02:40:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48201728. Throughput: 0: 2745.7, 1: 2666.9. Samples: 48217372. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:48,446][86177] Avg episode reward: [(0, '-514.260'), (1, '-528.360')] -[2023-11-28 02:40:48,450][87424] Updated weights for policy 0, policy_version 94226 (0.0012) -[2023-11-28 02:40:48,486][87426] Updated weights for policy 1, policy_version 94090 (0.0011) -[2023-11-28 02:40:48,829][87424] Updated weights for policy 0, policy_version 94236 (0.0011) -[2023-11-28 02:40:48,865][87426] Updated weights for policy 1, policy_version 94100 (0.0010) -[2023-11-28 02:40:49,245][87426] Updated weights for policy 1, policy_version 94110 (0.0011) -[2023-11-28 02:40:50,934][87424] Updated weights for policy 0, policy_version 94246 (0.0011) -[2023-11-28 02:40:51,316][87424] Updated weights for policy 0, policy_version 94256 (0.0011) -[2023-11-28 02:40:51,698][87424] Updated weights for policy 0, policy_version 94266 (0.0012) -[2023-11-28 02:40:51,752][87426] Updated weights for policy 1, policy_version 94120 (0.0011) -[2023-11-28 02:40:52,131][87426] Updated weights for policy 1, policy_version 94130 (0.0009) -[2023-11-28 02:40:52,510][87426] Updated weights for policy 1, policy_version 94140 (0.0011) -[2023-11-28 02:40:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48234496. Throughput: 0: 2766.1, 1: 2651.3. Samples: 48249792. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:53,445][86177] Avg episode reward: [(0, '-525.910'), (1, '-534.050')] -[2023-11-28 02:40:53,845][87424] Updated weights for policy 0, policy_version 94276 (0.0012) -[2023-11-28 02:40:54,236][87424] Updated weights for policy 0, policy_version 94286 (0.0008) -[2023-11-28 02:40:54,615][87424] Updated weights for policy 0, policy_version 94296 (0.0007) -[2023-11-28 02:40:54,912][87426] Updated weights for policy 1, policy_version 94150 (0.0009) -[2023-11-28 02:40:55,297][87426] Updated weights for policy 1, policy_version 94160 (0.0007) -[2023-11-28 02:40:55,677][87426] Updated weights for policy 1, policy_version 94170 (0.0008) -[2023-11-28 02:40:56,751][87424] Updated weights for policy 0, policy_version 94306 (0.0008) -[2023-11-28 02:40:57,129][87424] Updated weights for policy 0, policy_version 94316 (0.0008) -[2023-11-28 02:40:57,504][87424] Updated weights for policy 0, policy_version 94326 (0.0007) -[2023-11-28 02:40:57,887][87424] Updated weights for policy 0, policy_version 94336 (0.0008) -[2023-11-28 02:40:58,026][87426] Updated weights for policy 1, policy_version 94180 (0.0009) -[2023-11-28 02:40:58,396][87426] Updated weights for policy 1, policy_version 94190 (0.0012) -[2023-11-28 02:40:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48259072. Throughput: 0: 2757.8, 1: 2648.2. Samples: 48273308. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:40:58,445][86177] Avg episode reward: [(0, '-527.010'), (1, '-540.340')] -[2023-11-28 02:40:58,774][87426] Updated weights for policy 1, policy_version 94200 (0.0012) -[2023-11-28 02:40:59,758][87424] Updated weights for policy 0, policy_version 94346 (0.0012) -[2023-11-28 02:41:00,145][87424] Updated weights for policy 0, policy_version 94356 (0.0010) -[2023-11-28 02:41:00,524][87424] Updated weights for policy 0, policy_version 94366 (0.0012) -[2023-11-28 02:41:01,108][87426] Updated weights for policy 1, policy_version 94210 (0.0012) -[2023-11-28 02:41:01,489][87426] Updated weights for policy 1, policy_version 94220 (0.0011) -[2023-11-28 02:41:01,873][87426] Updated weights for policy 1, policy_version 94230 (0.0009) -[2023-11-28 02:41:02,249][87426] Updated weights for policy 1, policy_version 94240 (0.0012) -[2023-11-28 02:41:02,883][87424] Updated weights for policy 0, policy_version 94376 (0.0009) -[2023-11-28 02:41:03,264][87424] Updated weights for policy 0, policy_version 94386 (0.0009) -[2023-11-28 02:41:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48283648. Throughput: 0: 2747.6, 1: 2655.8. Samples: 48298576. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:41:03,445][86177] Avg episode reward: [(0, '-520.620'), (1, '-540.770')] -[2023-11-28 02:41:03,656][87424] Updated weights for policy 0, policy_version 94396 (0.0008) -[2023-11-28 02:41:04,652][87426] Updated weights for policy 1, policy_version 94250 (0.0010) -[2023-11-28 02:41:05,032][87426] Updated weights for policy 1, policy_version 94260 (0.0011) -[2023-11-28 02:41:05,413][87426] Updated weights for policy 1, policy_version 94270 (0.0009) -[2023-11-28 02:41:05,992][87424] Updated weights for policy 0, policy_version 94406 (0.0008) -[2023-11-28 02:41:06,372][87424] Updated weights for policy 0, policy_version 94416 (0.0008) -[2023-11-28 02:41:06,759][87424] Updated weights for policy 0, policy_version 94426 (0.0009) -[2023-11-28 02:41:07,584][87426] Updated weights for policy 1, policy_version 94280 (0.0011) -[2023-11-28 02:41:07,973][87426] Updated weights for policy 1, policy_version 94290 (0.0012) -[2023-11-28 02:41:08,357][87426] Updated weights for policy 1, policy_version 94300 (0.0012) -[2023-11-28 02:41:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48308224. Throughput: 0: 2758.1, 1: 2667.1. Samples: 48331452. Policy #0 lag: (min: 27.0, avg: 55.9, max: 91.0) -[2023-11-28 02:41:08,445][86177] Avg episode reward: [(0, '-519.050'), (1, '-535.410')] -[2023-11-28 02:41:09,048][87424] Updated weights for policy 0, policy_version 94436 (0.0011) -[2023-11-28 02:41:09,434][87424] Updated weights for policy 0, policy_version 94446 (0.0010) -[2023-11-28 02:41:09,827][87424] Updated weights for policy 0, policy_version 94456 (0.0011) -[2023-11-28 02:41:10,594][87426] Updated weights for policy 1, policy_version 94310 (0.0011) -[2023-11-28 02:41:10,971][87426] Updated weights for policy 1, policy_version 94320 (0.0011) -[2023-11-28 02:41:11,355][87426] Updated weights for policy 1, policy_version 94330 (0.0010) -[2023-11-28 02:41:11,835][87424] Updated weights for policy 0, policy_version 94466 (0.0009) -[2023-11-28 02:41:12,235][87424] Updated weights for policy 0, policy_version 94476 (0.0011) -[2023-11-28 02:41:12,624][87424] Updated weights for policy 0, policy_version 94486 (0.0012) -[2023-11-28 02:41:13,001][87424] Updated weights for policy 0, policy_version 94496 (0.0012) -[2023-11-28 02:41:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48340992. Throughput: 0: 2766.4, 1: 2632.1. Samples: 48355040. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:13,445][86177] Avg episode reward: [(0, '-497.730'), (1, '-547.250')] -[2023-11-28 02:41:13,591][87426] Updated weights for policy 1, policy_version 94340 (0.0009) -[2023-11-28 02:41:13,962][87426] Updated weights for policy 1, policy_version 94350 (0.0007) -[2023-11-28 02:41:14,340][87426] Updated weights for policy 1, policy_version 94360 (0.0010) -[2023-11-28 02:41:15,001][87424] Updated weights for policy 0, policy_version 94506 (0.0012) -[2023-11-28 02:41:15,382][87424] Updated weights for policy 0, policy_version 94516 (0.0012) -[2023-11-28 02:41:15,766][87424] Updated weights for policy 0, policy_version 94526 (0.0011) -[2023-11-28 02:41:16,667][87426] Updated weights for policy 1, policy_version 94370 (0.0011) -[2023-11-28 02:41:17,047][87426] Updated weights for policy 1, policy_version 94380 (0.0007) -[2023-11-28 02:41:17,432][87426] Updated weights for policy 1, policy_version 94390 (0.0008) -[2023-11-28 02:41:17,590][87424] Updated weights for policy 0, policy_version 94536 (0.0008) -[2023-11-28 02:41:17,806][87426] Updated weights for policy 1, policy_version 94400 (0.0007) -[2023-11-28 02:41:17,973][87424] Updated weights for policy 0, policy_version 94546 (0.0010) -[2023-11-28 02:41:18,355][87424] Updated weights for policy 0, policy_version 94556 (0.0007) -[2023-11-28 02:41:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48365568. Throughput: 0: 2775.4, 1: 2609.5. Samples: 48379736. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:18,445][86177] Avg episode reward: [(0, '-502.260'), (1, '-552.990')] -[2023-11-28 02:41:20,227][87426] Updated weights for policy 1, policy_version 94410 (0.0012) -[2023-11-28 02:41:20,607][87426] Updated weights for policy 1, policy_version 94420 (0.0012) -[2023-11-28 02:41:20,856][87424] Updated weights for policy 0, policy_version 94566 (0.0009) -[2023-11-28 02:41:20,988][87426] Updated weights for policy 1, policy_version 94430 (0.0011) -[2023-11-28 02:41:21,236][87424] Updated weights for policy 0, policy_version 94576 (0.0011) -[2023-11-28 02:41:21,610][87424] Updated weights for policy 0, policy_version 94586 (0.0012) -[2023-11-28 02:41:23,327][87426] Updated weights for policy 1, policy_version 94440 (0.0011) -[2023-11-28 02:41:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48390144. Throughput: 0: 2762.8, 1: 2605.3. Samples: 48410124. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:23,445][86177] Avg episode reward: [(0, '-506.630'), (1, '-562.510')] -[2023-11-28 02:41:23,717][87426] Updated weights for policy 1, policy_version 94450 (0.0012) -[2023-11-28 02:41:24,090][87426] Updated weights for policy 1, policy_version 94460 (0.0011) -[2023-11-28 02:41:24,143][87424] Updated weights for policy 0, policy_version 94596 (0.0010) -[2023-11-28 02:41:24,530][87424] Updated weights for policy 0, policy_version 94606 (0.0008) -[2023-11-28 02:41:24,926][87424] Updated weights for policy 0, policy_version 94616 (0.0008) -[2023-11-28 02:41:26,031][87426] Updated weights for policy 1, policy_version 94470 (0.0009) -[2023-11-28 02:41:26,412][87426] Updated weights for policy 1, policy_version 94480 (0.0008) -[2023-11-28 02:41:26,783][87426] Updated weights for policy 1, policy_version 94490 (0.0008) -[2023-11-28 02:41:27,101][87424] Updated weights for policy 0, policy_version 94626 (0.0008) -[2023-11-28 02:41:27,483][87424] Updated weights for policy 0, policy_version 94636 (0.0011) -[2023-11-28 02:41:27,850][87424] Updated weights for policy 0, policy_version 94646 (0.0012) -[2023-11-28 02:41:28,240][87424] Updated weights for policy 0, policy_version 94656 (0.0011) -[2023-11-28 02:41:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48422912. Throughput: 0: 2772.9, 1: 2622.9. Samples: 48435656. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:28,445][86177] Avg episode reward: [(0, '-515.050'), (1, '-574.550')] -[2023-11-28 02:41:28,568][87426] Updated weights for policy 1, policy_version 94500 (0.0009) -[2023-11-28 02:41:28,951][87426] Updated weights for policy 1, policy_version 94510 (0.0011) -[2023-11-28 02:41:29,330][87426] Updated weights for policy 1, policy_version 94520 (0.0008) -[2023-11-28 02:41:30,169][87424] Updated weights for policy 0, policy_version 94666 (0.0011) -[2023-11-28 02:41:30,550][87424] Updated weights for policy 0, policy_version 94676 (0.0011) -[2023-11-28 02:41:30,929][87424] Updated weights for policy 0, policy_version 94686 (0.0007) -[2023-11-28 02:41:31,684][87426] Updated weights for policy 1, policy_version 94530 (0.0011) -[2023-11-28 02:41:32,059][87426] Updated weights for policy 1, policy_version 94540 (0.0009) -[2023-11-28 02:41:32,445][87426] Updated weights for policy 1, policy_version 94550 (0.0009) -[2023-11-28 02:41:32,809][87426] Updated weights for policy 1, policy_version 94560 (0.0009) -[2023-11-28 02:41:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 48447488. Throughput: 0: 2754.7, 1: 2634.2. Samples: 48459868. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:33,445][86177] Avg episode reward: [(0, '-514.550'), (1, '-559.400')] -[2023-11-28 02:41:33,483][87424] Updated weights for policy 0, policy_version 94696 (0.0007) -[2023-11-28 02:41:33,870][87424] Updated weights for policy 0, policy_version 94706 (0.0011) -[2023-11-28 02:41:34,236][87424] Updated weights for policy 0, policy_version 94716 (0.0012) -[2023-11-28 02:41:35,061][87426] Updated weights for policy 1, policy_version 94570 (0.0011) -[2023-11-28 02:41:35,442][87426] Updated weights for policy 1, policy_version 94580 (0.0012) -[2023-11-28 02:41:35,817][87426] Updated weights for policy 1, policy_version 94590 (0.0011) -[2023-11-28 02:41:36,214][87424] Updated weights for policy 0, policy_version 94726 (0.0011) -[2023-11-28 02:41:36,606][87424] Updated weights for policy 0, policy_version 94736 (0.0007) -[2023-11-28 02:41:36,979][87424] Updated weights for policy 0, policy_version 94746 (0.0010) -[2023-11-28 02:41:37,914][87426] Updated weights for policy 1, policy_version 94600 (0.0012) -[2023-11-28 02:41:38,286][87426] Updated weights for policy 1, policy_version 94610 (0.0012) -[2023-11-28 02:41:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48472064. Throughput: 0: 2727.2, 1: 2659.1. Samples: 48492176. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:38,445][86177] Avg episode reward: [(0, '-506.800'), (1, '-548.420')] -[2023-11-28 02:41:38,665][87426] Updated weights for policy 1, policy_version 94620 (0.0008) -[2023-11-28 02:41:38,841][87424] Updated weights for policy 0, policy_version 94756 (0.0011) -[2023-11-28 02:41:39,218][87424] Updated weights for policy 0, policy_version 94766 (0.0011) -[2023-11-28 02:41:39,602][87424] Updated weights for policy 0, policy_version 94776 (0.0011) -[2023-11-28 02:41:41,029][87426] Updated weights for policy 1, policy_version 94630 (0.0010) -[2023-11-28 02:41:41,401][87426] Updated weights for policy 1, policy_version 94640 (0.0012) -[2023-11-28 02:41:41,789][87426] Updated weights for policy 1, policy_version 94650 (0.0011) -[2023-11-28 02:41:42,050][87424] Updated weights for policy 0, policy_version 94786 (0.0011) -[2023-11-28 02:41:42,439][87424] Updated weights for policy 0, policy_version 94796 (0.0012) -[2023-11-28 02:41:42,827][87424] Updated weights for policy 0, policy_version 94806 (0.0012) -[2023-11-28 02:41:43,196][87424] Updated weights for policy 0, policy_version 94816 (0.0009) -[2023-11-28 02:41:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48504832. Throughput: 0: 2737.4, 1: 2659.3. Samples: 48516160. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:43,445][86177] Avg episode reward: [(0, '-506.170'), (1, '-547.180')] -[2023-11-28 02:41:44,359][87426] Updated weights for policy 1, policy_version 94660 (0.0011) -[2023-11-28 02:41:44,742][87426] Updated weights for policy 1, policy_version 94670 (0.0012) -[2023-11-28 02:41:45,114][87426] Updated weights for policy 1, policy_version 94680 (0.0012) -[2023-11-28 02:41:45,709][87424] Updated weights for policy 0, policy_version 94826 (0.0008) -[2023-11-28 02:41:46,089][87424] Updated weights for policy 0, policy_version 94836 (0.0008) -[2023-11-28 02:41:46,468][87424] Updated weights for policy 0, policy_version 94846 (0.0007) -[2023-11-28 02:41:47,545][87426] Updated weights for policy 1, policy_version 94690 (0.0010) -[2023-11-28 02:41:47,924][87426] Updated weights for policy 1, policy_version 94700 (0.0011) -[2023-11-28 02:41:48,300][87426] Updated weights for policy 1, policy_version 94710 (0.0010) -[2023-11-28 02:41:48,327][87424] Updated weights for policy 0, policy_version 94856 (0.0010) -[2023-11-28 02:41:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 48521216. Throughput: 0: 2707.5, 1: 2645.7. Samples: 48539472. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:48,446][86177] Avg episode reward: [(0, '-497.430'), (1, '-529.210')] -[2023-11-28 02:41:48,683][87426] Updated weights for policy 1, policy_version 94720 (0.0011) -[2023-11-28 02:41:48,717][87424] Updated weights for policy 0, policy_version 94866 (0.0008) -[2023-11-28 02:41:49,105][87424] Updated weights for policy 0, policy_version 94876 (0.0010) -[2023-11-28 02:41:50,647][87426] Updated weights for policy 1, policy_version 94730 (0.0009) -[2023-11-28 02:41:51,011][87426] Updated weights for policy 1, policy_version 94740 (0.0011) -[2023-11-28 02:41:51,252][87424] Updated weights for policy 0, policy_version 94886 (0.0011) -[2023-11-28 02:41:51,388][87426] Updated weights for policy 1, policy_version 94750 (0.0010) -[2023-11-28 02:41:51,636][87424] Updated weights for policy 0, policy_version 94896 (0.0011) -[2023-11-28 02:41:52,019][87424] Updated weights for policy 0, policy_version 94906 (0.0011) -[2023-11-28 02:41:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48553984. Throughput: 0: 2711.5, 1: 2641.5. Samples: 48572336. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:53,445][86177] Avg episode reward: [(0, '-501.000'), (1, '-524.660')] -[2023-11-28 02:41:53,478][87426] Updated weights for policy 1, policy_version 94760 (0.0010) -[2023-11-28 02:41:53,865][87426] Updated weights for policy 1, policy_version 94770 (0.0010) -[2023-11-28 02:41:53,988][87424] Updated weights for policy 0, policy_version 94916 (0.0009) -[2023-11-28 02:41:54,241][87426] Updated weights for policy 1, policy_version 94780 (0.0008) -[2023-11-28 02:41:54,368][87424] Updated weights for policy 0, policy_version 94926 (0.0009) -[2023-11-28 02:41:54,751][87424] Updated weights for policy 0, policy_version 94936 (0.0010) -[2023-11-28 02:41:56,580][87426] Updated weights for policy 1, policy_version 94790 (0.0008) -[2023-11-28 02:41:56,962][87426] Updated weights for policy 1, policy_version 94800 (0.0007) -[2023-11-28 02:41:57,253][87424] Updated weights for policy 0, policy_version 94946 (0.0011) -[2023-11-28 02:41:57,341][87426] Updated weights for policy 1, policy_version 94810 (0.0007) -[2023-11-28 02:41:57,645][87424] Updated weights for policy 0, policy_version 94956 (0.0008) -[2023-11-28 02:41:58,021][87424] Updated weights for policy 0, policy_version 94966 (0.0008) -[2023-11-28 02:41:58,406][87424] Updated weights for policy 0, policy_version 94976 (0.0007) -[2023-11-28 02:41:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48586752. Throughput: 0: 2710.4, 1: 2664.3. Samples: 48596900. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:41:58,445][86177] Avg episode reward: [(0, '-502.900'), (1, '-512.560')] -[2023-11-28 02:41:59,494][87426] Updated weights for policy 1, policy_version 94820 (0.0009) -[2023-11-28 02:41:59,865][87426] Updated weights for policy 1, policy_version 94830 (0.0012) -[2023-11-28 02:42:00,247][87426] Updated weights for policy 1, policy_version 94840 (0.0011) -[2023-11-28 02:42:00,444][87424] Updated weights for policy 0, policy_version 94986 (0.0009) -[2023-11-28 02:42:00,823][87424] Updated weights for policy 0, policy_version 94996 (0.0011) -[2023-11-28 02:42:01,201][87424] Updated weights for policy 0, policy_version 95006 (0.0011) -[2023-11-28 02:42:02,769][87426] Updated weights for policy 1, policy_version 94850 (0.0011) -[2023-11-28 02:42:03,139][87424] Updated weights for policy 0, policy_version 95016 (0.0012) -[2023-11-28 02:42:03,151][87426] Updated weights for policy 1, policy_version 94860 (0.0008) -[2023-11-28 02:42:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 48603136. Throughput: 0: 2702.2, 1: 2664.3. Samples: 48621228. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:42:03,445][86177] Avg episode reward: [(0, '-508.800'), (1, '-545.210')] -[2023-11-28 02:42:03,521][87426] Updated weights for policy 1, policy_version 94870 (0.0007) -[2023-11-28 02:42:03,522][87424] Updated weights for policy 0, policy_version 95026 (0.0011) -[2023-11-28 02:42:03,901][87426] Updated weights for policy 1, policy_version 94880 (0.0007) -[2023-11-28 02:42:03,915][87424] Updated weights for policy 0, policy_version 95036 (0.0008) -[2023-11-28 02:42:05,742][87424] Updated weights for policy 0, policy_version 95046 (0.0008) -[2023-11-28 02:42:06,066][87426] Updated weights for policy 1, policy_version 94890 (0.0008) -[2023-11-28 02:42:06,109][87424] Updated weights for policy 0, policy_version 95056 (0.0009) -[2023-11-28 02:42:06,451][87426] Updated weights for policy 1, policy_version 94900 (0.0007) -[2023-11-28 02:42:06,496][87424] Updated weights for policy 0, policy_version 95066 (0.0012) -[2023-11-28 02:42:06,834][87426] Updated weights for policy 1, policy_version 94910 (0.0008) -[2023-11-28 02:42:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48635904. Throughput: 0: 2734.0, 1: 2673.7. Samples: 48653472. Policy #0 lag: (min: 30.0, avg: 48.1, max: 50.0) -[2023-11-28 02:42:08,445][86177] Avg episode reward: [(0, '-506.910'), (1, '-540.030')] -[2023-11-28 02:42:08,619][87424] Updated weights for policy 0, policy_version 95076 (0.0011) -[2023-11-28 02:42:09,006][87424] Updated weights for policy 0, policy_version 95086 (0.0010) -[2023-11-28 02:42:09,258][87426] Updated weights for policy 1, policy_version 94920 (0.0008) -[2023-11-28 02:42:09,384][87424] Updated weights for policy 0, policy_version 95096 (0.0011) -[2023-11-28 02:42:09,635][87426] Updated weights for policy 1, policy_version 94930 (0.0012) -[2023-11-28 02:42:10,018][87426] Updated weights for policy 1, policy_version 94940 (0.0011) -[2023-11-28 02:42:11,260][87424] Updated weights for policy 0, policy_version 95106 (0.0009) -[2023-11-28 02:42:11,639][87424] Updated weights for policy 0, policy_version 95116 (0.0011) -[2023-11-28 02:42:12,022][87424] Updated weights for policy 0, policy_version 95126 (0.0010) -[2023-11-28 02:42:12,404][87424] Updated weights for policy 0, policy_version 95136 (0.0012) -[2023-11-28 02:42:12,598][87426] Updated weights for policy 1, policy_version 94950 (0.0008) -[2023-11-28 02:42:12,978][87426] Updated weights for policy 1, policy_version 94960 (0.0009) -[2023-11-28 02:42:13,349][87426] Updated weights for policy 1, policy_version 94970 (0.0012) -[2023-11-28 02:42:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 48660480. Throughput: 0: 2736.4, 1: 2629.1. Samples: 48677104. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:13,445][86177] Avg episode reward: [(0, '-505.880'), (1, '-552.850')] -[2023-11-28 02:42:14,787][87424] Updated weights for policy 0, policy_version 95146 (0.0008) -[2023-11-28 02:42:15,169][87424] Updated weights for policy 0, policy_version 95156 (0.0008) -[2023-11-28 02:42:15,551][87424] Updated weights for policy 0, policy_version 95166 (0.0008) -[2023-11-28 02:42:15,945][87426] Updated weights for policy 1, policy_version 94980 (0.0012) -[2023-11-28 02:42:16,334][87426] Updated weights for policy 1, policy_version 94990 (0.0012) -[2023-11-28 02:42:16,718][87426] Updated weights for policy 1, policy_version 95000 (0.0012) -[2023-11-28 02:42:17,230][87424] Updated weights for policy 0, policy_version 95176 (0.0008) -[2023-11-28 02:42:17,608][87424] Updated weights for policy 0, policy_version 95186 (0.0010) -[2023-11-28 02:42:17,989][87424] Updated weights for policy 0, policy_version 95196 (0.0010) -[2023-11-28 02:42:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48693248. Throughput: 0: 2753.2, 1: 2628.0. Samples: 48702024. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:18,445][86177] Avg episode reward: [(0, '-504.800'), (1, '-555.690')] -[2023-11-28 02:42:18,451][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000095200_24371200.pth... -[2023-11-28 02:42:18,472][87426] Updated weights for policy 1, policy_version 95010 (0.0011) -[2023-11-28 02:42:18,499][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000092640_23715840.pth -[2023-11-28 02:42:18,835][87426] Updated weights for policy 1, policy_version 95020 (0.0011) -[2023-11-28 02:42:19,217][87426] Updated weights for policy 1, policy_version 95030 (0.0012) -[2023-11-28 02:42:19,592][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000095040_24330240.pth... -[2023-11-28 02:42:19,594][87426] Updated weights for policy 1, policy_version 95040 (0.0011) -[2023-11-28 02:42:19,622][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000092544_23691264.pth -[2023-11-28 02:42:19,664][87424] Updated weights for policy 0, policy_version 95206 (0.0007) -[2023-11-28 02:42:20,052][87424] Updated weights for policy 0, policy_version 95216 (0.0009) -[2023-11-28 02:42:20,439][87424] Updated weights for policy 0, policy_version 95226 (0.0009) -[2023-11-28 02:42:21,551][87426] Updated weights for policy 1, policy_version 95050 (0.0011) -[2023-11-28 02:42:21,929][87426] Updated weights for policy 1, policy_version 95060 (0.0010) -[2023-11-28 02:42:22,306][87426] Updated weights for policy 1, policy_version 95070 (0.0011) -[2023-11-28 02:42:22,800][87424] Updated weights for policy 0, policy_version 95236 (0.0012) -[2023-11-28 02:42:23,189][87424] Updated weights for policy 0, policy_version 95246 (0.0009) -[2023-11-28 02:42:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48717824. Throughput: 0: 2776.4, 1: 2615.7. Samples: 48734820. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:23,445][86177] Avg episode reward: [(0, '-501.620'), (1, '-532.560')] -[2023-11-28 02:42:23,564][87424] Updated weights for policy 0, policy_version 95256 (0.0009) -[2023-11-28 02:42:24,499][87426] Updated weights for policy 1, policy_version 95080 (0.0008) -[2023-11-28 02:42:24,876][87426] Updated weights for policy 1, policy_version 95090 (0.0007) -[2023-11-28 02:42:25,255][87426] Updated weights for policy 1, policy_version 95100 (0.0008) -[2023-11-28 02:42:25,581][87424] Updated weights for policy 0, policy_version 95266 (0.0009) -[2023-11-28 02:42:25,974][87424] Updated weights for policy 0, policy_version 95276 (0.0011) -[2023-11-28 02:42:26,357][87424] Updated weights for policy 0, policy_version 95286 (0.0011) -[2023-11-28 02:42:26,745][87424] Updated weights for policy 0, policy_version 95296 (0.0012) -[2023-11-28 02:42:27,566][87426] Updated weights for policy 1, policy_version 95110 (0.0010) -[2023-11-28 02:42:27,938][87426] Updated weights for policy 1, policy_version 95120 (0.0008) -[2023-11-28 02:42:28,328][87426] Updated weights for policy 1, policy_version 95130 (0.0007) -[2023-11-28 02:42:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 48742400. Throughput: 0: 2770.1, 1: 2658.8. Samples: 48760460. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:28,445][86177] Avg episode reward: [(0, '-499.310'), (1, '-544.270')] -[2023-11-28 02:42:29,082][87424] Updated weights for policy 0, policy_version 95306 (0.0009) -[2023-11-28 02:42:29,473][87424] Updated weights for policy 0, policy_version 95316 (0.0007) -[2023-11-28 02:42:29,854][87424] Updated weights for policy 0, policy_version 95326 (0.0008) -[2023-11-28 02:42:30,841][87426] Updated weights for policy 1, policy_version 95140 (0.0009) -[2023-11-28 02:42:31,212][87426] Updated weights for policy 1, policy_version 95150 (0.0012) -[2023-11-28 02:42:31,584][87424] Updated weights for policy 0, policy_version 95336 (0.0009) -[2023-11-28 02:42:31,590][87426] Updated weights for policy 1, policy_version 95160 (0.0011) -[2023-11-28 02:42:31,967][87424] Updated weights for policy 0, policy_version 95346 (0.0010) -[2023-11-28 02:42:32,348][87424] Updated weights for policy 0, policy_version 95356 (0.0008) -[2023-11-28 02:42:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48775168. Throughput: 0: 2829.2, 1: 2657.2. Samples: 48786356. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:33,445][86177] Avg episode reward: [(0, '-502.600'), (1, '-532.440')] -[2023-11-28 02:42:34,074][87426] Updated weights for policy 1, policy_version 95170 (0.0011) -[2023-11-28 02:42:34,455][87426] Updated weights for policy 1, policy_version 95180 (0.0009) -[2023-11-28 02:42:34,630][87424] Updated weights for policy 0, policy_version 95366 (0.0009) -[2023-11-28 02:42:34,833][87426] Updated weights for policy 1, policy_version 95190 (0.0008) -[2023-11-28 02:42:35,020][87424] Updated weights for policy 0, policy_version 95376 (0.0011) -[2023-11-28 02:42:35,211][87426] Updated weights for policy 1, policy_version 95200 (0.0010) -[2023-11-28 02:42:35,394][87424] Updated weights for policy 0, policy_version 95386 (0.0008) -[2023-11-28 02:42:37,018][87426] Updated weights for policy 1, policy_version 95210 (0.0011) -[2023-11-28 02:42:37,392][87426] Updated weights for policy 1, policy_version 95220 (0.0008) -[2023-11-28 02:42:37,436][87424] Updated weights for policy 0, policy_version 95396 (0.0010) -[2023-11-28 02:42:37,772][87426] Updated weights for policy 1, policy_version 95230 (0.0012) -[2023-11-28 02:42:37,815][87424] Updated weights for policy 0, policy_version 95406 (0.0011) -[2023-11-28 02:42:38,196][87424] Updated weights for policy 0, policy_version 95416 (0.0008) -[2023-11-28 02:42:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48799744. Throughput: 0: 2844.2, 1: 2663.9. Samples: 48820200. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:38,446][86177] Avg episode reward: [(0, '-501.780'), (1, '-533.590')] -[2023-11-28 02:42:39,360][87426] Updated weights for policy 1, policy_version 95240 (0.0012) -[2023-11-28 02:42:39,734][87426] Updated weights for policy 1, policy_version 95250 (0.0011) -[2023-11-28 02:42:40,108][87426] Updated weights for policy 1, policy_version 95260 (0.0012) -[2023-11-28 02:42:40,670][87424] Updated weights for policy 0, policy_version 95426 (0.0008) -[2023-11-28 02:42:41,054][87424] Updated weights for policy 0, policy_version 95436 (0.0012) -[2023-11-28 02:42:41,428][87424] Updated weights for policy 0, policy_version 95446 (0.0011) -[2023-11-28 02:42:41,808][87424] Updated weights for policy 0, policy_version 95456 (0.0022) -[2023-11-28 02:42:42,505][87426] Updated weights for policy 1, policy_version 95270 (0.0009) -[2023-11-28 02:42:42,894][87426] Updated weights for policy 1, policy_version 95280 (0.0009) -[2023-11-28 02:42:43,270][87426] Updated weights for policy 1, policy_version 95290 (0.0012) -[2023-11-28 02:42:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48824320. Throughput: 0: 2828.0, 1: 2653.8. Samples: 48843580. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:43,445][86177] Avg episode reward: [(0, '-505.350'), (1, '-565.410')] -[2023-11-28 02:42:44,440][87424] Updated weights for policy 0, policy_version 95466 (0.0012) -[2023-11-28 02:42:44,823][87424] Updated weights for policy 0, policy_version 95476 (0.0012) -[2023-11-28 02:42:45,204][87424] Updated weights for policy 0, policy_version 95486 (0.0011) -[2023-11-28 02:42:45,728][87426] Updated weights for policy 1, policy_version 95300 (0.0012) -[2023-11-28 02:42:46,099][87426] Updated weights for policy 1, policy_version 95310 (0.0012) -[2023-11-28 02:42:46,474][87426] Updated weights for policy 1, policy_version 95320 (0.0012) -[2023-11-28 02:42:47,474][87424] Updated weights for policy 0, policy_version 95496 (0.0011) -[2023-11-28 02:42:47,864][87424] Updated weights for policy 0, policy_version 95506 (0.0009) -[2023-11-28 02:42:48,235][87424] Updated weights for policy 0, policy_version 95516 (0.0010) -[2023-11-28 02:42:48,364][87426] Updated weights for policy 1, policy_version 95330 (0.0011) -[2023-11-28 02:42:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 48857088. Throughput: 0: 2797.9, 1: 2675.5. Samples: 48867536. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:48,445][86177] Avg episode reward: [(0, '-501.350'), (1, '-559.830')] -[2023-11-28 02:42:48,742][87426] Updated weights for policy 1, policy_version 95340 (0.0008) -[2023-11-28 02:42:49,124][87426] Updated weights for policy 1, policy_version 95350 (0.0011) -[2023-11-28 02:42:49,501][87426] Updated weights for policy 1, policy_version 95360 (0.0012) -[2023-11-28 02:42:50,186][87424] Updated weights for policy 0, policy_version 95526 (0.0012) -[2023-11-28 02:42:50,561][87424] Updated weights for policy 0, policy_version 95536 (0.0011) -[2023-11-28 02:42:50,944][87424] Updated weights for policy 0, policy_version 95546 (0.0011) -[2023-11-28 02:42:51,954][87426] Updated weights for policy 1, policy_version 95370 (0.0010) -[2023-11-28 02:42:52,353][87426] Updated weights for policy 1, policy_version 95380 (0.0011) -[2023-11-28 02:42:52,727][87426] Updated weights for policy 1, policy_version 95390 (0.0012) -[2023-11-28 02:42:53,233][87424] Updated weights for policy 0, policy_version 95556 (0.0011) -[2023-11-28 02:42:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48881664. Throughput: 0: 2789.3, 1: 2695.3. Samples: 48900280. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:53,445][86177] Avg episode reward: [(0, '-498.230'), (1, '-555.280')] -[2023-11-28 02:42:53,633][87424] Updated weights for policy 0, policy_version 95566 (0.0012) -[2023-11-28 02:42:54,012][87424] Updated weights for policy 0, policy_version 95576 (0.0010) -[2023-11-28 02:42:54,782][87426] Updated weights for policy 1, policy_version 95400 (0.0009) -[2023-11-28 02:42:55,159][87426] Updated weights for policy 1, policy_version 95410 (0.0008) -[2023-11-28 02:42:55,539][87426] Updated weights for policy 1, policy_version 95420 (0.0007) -[2023-11-28 02:42:56,377][87424] Updated weights for policy 0, policy_version 95586 (0.0012) -[2023-11-28 02:42:56,758][87424] Updated weights for policy 0, policy_version 95596 (0.0012) -[2023-11-28 02:42:57,138][87424] Updated weights for policy 0, policy_version 95606 (0.0012) -[2023-11-28 02:42:57,520][87424] Updated weights for policy 0, policy_version 95616 (0.0010) -[2023-11-28 02:42:57,868][87426] Updated weights for policy 1, policy_version 95430 (0.0010) -[2023-11-28 02:42:58,251][87426] Updated weights for policy 1, policy_version 95440 (0.0012) -[2023-11-28 02:42:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 48906240. Throughput: 0: 2768.7, 1: 2741.6. Samples: 48925068. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:42:58,445][86177] Avg episode reward: [(0, '-498.230'), (1, '-557.070')] -[2023-11-28 02:42:58,635][87426] Updated weights for policy 1, policy_version 95450 (0.0012) -[2023-11-28 02:42:59,475][87424] Updated weights for policy 0, policy_version 95626 (0.0010) -[2023-11-28 02:42:59,861][87424] Updated weights for policy 0, policy_version 95636 (0.0012) -[2023-11-28 02:43:00,245][87424] Updated weights for policy 0, policy_version 95646 (0.0011) -[2023-11-28 02:43:00,901][87426] Updated weights for policy 1, policy_version 95460 (0.0012) -[2023-11-28 02:43:01,275][87426] Updated weights for policy 1, policy_version 95470 (0.0012) -[2023-11-28 02:43:01,657][87426] Updated weights for policy 1, policy_version 95480 (0.0012) -[2023-11-28 02:43:02,483][87424] Updated weights for policy 0, policy_version 95656 (0.0011) -[2023-11-28 02:43:02,866][87424] Updated weights for policy 0, policy_version 95666 (0.0010) -[2023-11-28 02:43:03,247][87424] Updated weights for policy 0, policy_version 95676 (0.0010) -[2023-11-28 02:43:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 48939008. Throughput: 0: 2763.7, 1: 2745.1. Samples: 48949920. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:43:03,445][86177] Avg episode reward: [(0, '-497.830'), (1, '-524.420')] -[2023-11-28 02:43:03,848][87426] Updated weights for policy 1, policy_version 95490 (0.0011) -[2023-11-28 02:43:04,225][87426] Updated weights for policy 1, policy_version 95500 (0.0012) -[2023-11-28 02:43:04,605][87426] Updated weights for policy 1, policy_version 95510 (0.0009) -[2023-11-28 02:43:04,984][87426] Updated weights for policy 1, policy_version 95520 (0.0011) -[2023-11-28 02:43:05,006][87424] Updated weights for policy 0, policy_version 95686 (0.0008) -[2023-11-28 02:43:05,384][87424] Updated weights for policy 0, policy_version 95696 (0.0012) -[2023-11-28 02:43:05,764][87424] Updated weights for policy 0, policy_version 95706 (0.0011) -[2023-11-28 02:43:06,766][87426] Updated weights for policy 1, policy_version 95530 (0.0012) -[2023-11-28 02:43:07,146][87426] Updated weights for policy 1, policy_version 95540 (0.0012) -[2023-11-28 02:43:07,418][87424] Updated weights for policy 0, policy_version 95716 (0.0012) -[2023-11-28 02:43:07,520][87426] Updated weights for policy 1, policy_version 95550 (0.0011) -[2023-11-28 02:43:07,804][87424] Updated weights for policy 0, policy_version 95726 (0.0012) -[2023-11-28 02:43:08,178][87424] Updated weights for policy 0, policy_version 95736 (0.0011) -[2023-11-28 02:43:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 48963584. Throughput: 0: 2775.7, 1: 2743.7. Samples: 48983196. Policy #0 lag: (min: 31.0, avg: 45.1, max: 63.0) -[2023-11-28 02:43:08,445][86177] Avg episode reward: [(0, '-498.750'), (1, '-527.660')] -[2023-11-28 02:43:09,828][87426] Updated weights for policy 1, policy_version 95560 (0.0010) -[2023-11-28 02:43:10,205][87426] Updated weights for policy 1, policy_version 95570 (0.0011) -[2023-11-28 02:43:10,251][87424] Updated weights for policy 0, policy_version 95746 (0.0011) -[2023-11-28 02:43:10,597][87426] Updated weights for policy 1, policy_version 95580 (0.0012) -[2023-11-28 02:43:10,639][87424] Updated weights for policy 0, policy_version 95756 (0.0011) -[2023-11-28 02:43:11,015][87424] Updated weights for policy 0, policy_version 95766 (0.0011) -[2023-11-28 02:43:11,401][87424] Updated weights for policy 0, policy_version 95776 (0.0012) -[2023-11-28 02:43:12,463][87426] Updated weights for policy 1, policy_version 95590 (0.0012) -[2023-11-28 02:43:12,837][87426] Updated weights for policy 1, policy_version 95600 (0.0012) -[2023-11-28 02:43:13,216][87426] Updated weights for policy 1, policy_version 95610 (0.0009) -[2023-11-28 02:43:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 48996352. Throughput: 0: 2753.5, 1: 2731.7. Samples: 49007296. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:13,445][86177] Avg episode reward: [(0, '-508.660'), (1, '-536.570')] -[2023-11-28 02:43:13,696][87424] Updated weights for policy 0, policy_version 95786 (0.0012) -[2023-11-28 02:43:14,068][87424] Updated weights for policy 0, policy_version 95796 (0.0012) -[2023-11-28 02:43:14,449][87424] Updated weights for policy 0, policy_version 95806 (0.0010) -[2023-11-28 02:43:15,148][87426] Updated weights for policy 1, policy_version 95620 (0.0010) -[2023-11-28 02:43:15,512][87426] Updated weights for policy 1, policy_version 95630 (0.0012) -[2023-11-28 02:43:15,906][87426] Updated weights for policy 1, policy_version 95640 (0.0011) -[2023-11-28 02:43:16,994][87424] Updated weights for policy 0, policy_version 95816 (0.0012) -[2023-11-28 02:43:17,379][87424] Updated weights for policy 0, policy_version 95826 (0.0012) -[2023-11-28 02:43:17,769][87424] Updated weights for policy 0, policy_version 95836 (0.0012) -[2023-11-28 02:43:18,155][87426] Updated weights for policy 1, policy_version 95650 (0.0011) -[2023-11-28 02:43:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 49020928. Throughput: 0: 2718.0, 1: 2755.6. Samples: 49032672. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:18,445][86177] Avg episode reward: [(0, '-512.790'), (1, '-527.450')] -[2023-11-28 02:43:18,537][87426] Updated weights for policy 1, policy_version 95660 (0.0012) -[2023-11-28 02:43:18,910][87426] Updated weights for policy 1, policy_version 95670 (0.0012) -[2023-11-28 02:43:19,281][87426] Updated weights for policy 1, policy_version 95680 (0.0012) -[2023-11-28 02:43:20,287][87424] Updated weights for policy 0, policy_version 95846 (0.0012) -[2023-11-28 02:43:20,668][87424] Updated weights for policy 0, policy_version 95856 (0.0009) -[2023-11-28 02:43:21,047][87424] Updated weights for policy 0, policy_version 95866 (0.0010) -[2023-11-28 02:43:21,301][87426] Updated weights for policy 1, policy_version 95690 (0.0012) -[2023-11-28 02:43:21,685][87426] Updated weights for policy 1, policy_version 95700 (0.0011) -[2023-11-28 02:43:22,063][87426] Updated weights for policy 1, policy_version 95710 (0.0011) -[2023-11-28 02:43:23,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 49045504. Throughput: 0: 2671.3, 1: 2751.1. Samples: 49064208. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:23,446][86177] Avg episode reward: [(0, '-514.690'), (1, '-535.100')] -[2023-11-28 02:43:23,544][87424] Updated weights for policy 0, policy_version 95876 (0.0012) -[2023-11-28 02:43:23,932][87424] Updated weights for policy 0, policy_version 95886 (0.0011) -[2023-11-28 02:43:24,174][87426] Updated weights for policy 1, policy_version 95720 (0.0011) -[2023-11-28 02:43:24,309][87424] Updated weights for policy 0, policy_version 95896 (0.0011) -[2023-11-28 02:43:24,554][87426] Updated weights for policy 1, policy_version 95730 (0.0012) -[2023-11-28 02:43:24,935][87426] Updated weights for policy 1, policy_version 95740 (0.0011) -[2023-11-28 02:43:26,577][87424] Updated weights for policy 0, policy_version 95906 (0.0007) -[2023-11-28 02:43:26,972][87424] Updated weights for policy 0, policy_version 95916 (0.0007) -[2023-11-28 02:43:27,127][87426] Updated weights for policy 1, policy_version 95750 (0.0011) -[2023-11-28 02:43:27,352][87424] Updated weights for policy 0, policy_version 95926 (0.0007) -[2023-11-28 02:43:27,503][87426] Updated weights for policy 1, policy_version 95760 (0.0010) -[2023-11-28 02:43:27,735][87424] Updated weights for policy 0, policy_version 95936 (0.0007) -[2023-11-28 02:43:27,884][87426] Updated weights for policy 1, policy_version 95770 (0.0007) -[2023-11-28 02:43:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 49078272. Throughput: 0: 2687.3, 1: 2770.4. Samples: 49089176. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:28,445][86177] Avg episode reward: [(0, '-517.860'), (1, '-528.140')] -[2023-11-28 02:43:29,258][87424] Updated weights for policy 0, policy_version 95946 (0.0008) -[2023-11-28 02:43:29,634][87424] Updated weights for policy 0, policy_version 95956 (0.0010) -[2023-11-28 02:43:29,958][87426] Updated weights for policy 1, policy_version 95780 (0.0007) -[2023-11-28 02:43:30,019][87424] Updated weights for policy 0, policy_version 95966 (0.0008) -[2023-11-28 02:43:30,344][87426] Updated weights for policy 1, policy_version 95790 (0.0007) -[2023-11-28 02:43:30,727][87426] Updated weights for policy 1, policy_version 95800 (0.0008) -[2023-11-28 02:43:32,066][87424] Updated weights for policy 0, policy_version 95976 (0.0009) -[2023-11-28 02:43:32,449][87424] Updated weights for policy 0, policy_version 95986 (0.0012) -[2023-11-28 02:43:32,657][87426] Updated weights for policy 1, policy_version 95810 (0.0008) -[2023-11-28 02:43:32,826][87424] Updated weights for policy 0, policy_version 95996 (0.0011) -[2023-11-28 02:43:33,036][87426] Updated weights for policy 1, policy_version 95820 (0.0011) -[2023-11-28 02:43:33,419][87426] Updated weights for policy 1, policy_version 95830 (0.0011) -[2023-11-28 02:43:33,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 49102848. Throughput: 0: 2729.1, 1: 2773.2. Samples: 49115136. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:33,445][86177] Avg episode reward: [(0, '-514.210'), (1, '-516.960')] -[2023-11-28 02:43:33,802][87426] Updated weights for policy 1, policy_version 95840 (0.0010) -[2023-11-28 02:43:34,868][87424] Updated weights for policy 0, policy_version 96006 (0.0011) -[2023-11-28 02:43:35,253][87424] Updated weights for policy 0, policy_version 96016 (0.0012) -[2023-11-28 02:43:35,636][87424] Updated weights for policy 0, policy_version 96026 (0.0012) -[2023-11-28 02:43:35,859][87426] Updated weights for policy 1, policy_version 95850 (0.0008) -[2023-11-28 02:43:36,239][87426] Updated weights for policy 1, policy_version 95860 (0.0007) -[2023-11-28 02:43:36,615][87426] Updated weights for policy 1, policy_version 95870 (0.0007) -[2023-11-28 02:43:37,754][87424] Updated weights for policy 0, policy_version 96036 (0.0012) -[2023-11-28 02:43:38,128][87424] Updated weights for policy 0, policy_version 96046 (0.0012) -[2023-11-28 02:43:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 49127424. Throughput: 0: 2739.3, 1: 2782.5. Samples: 49148760. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:38,446][86177] Avg episode reward: [(0, '-510.060'), (1, '-515.040')] -[2023-11-28 02:43:38,511][87424] Updated weights for policy 0, policy_version 96056 (0.0011) -[2023-11-28 02:43:38,667][87426] Updated weights for policy 1, policy_version 95880 (0.0012) -[2023-11-28 02:43:39,049][87426] Updated weights for policy 1, policy_version 95890 (0.0012) -[2023-11-28 02:43:39,428][87426] Updated weights for policy 1, policy_version 95900 (0.0011) -[2023-11-28 02:43:41,132][87424] Updated weights for policy 0, policy_version 96066 (0.0008) -[2023-11-28 02:43:41,506][87424] Updated weights for policy 0, policy_version 96076 (0.0012) -[2023-11-28 02:43:41,810][87426] Updated weights for policy 1, policy_version 95910 (0.0009) -[2023-11-28 02:43:41,891][87424] Updated weights for policy 0, policy_version 96086 (0.0012) -[2023-11-28 02:43:42,184][87426] Updated weights for policy 1, policy_version 95920 (0.0009) -[2023-11-28 02:43:42,274][87424] Updated weights for policy 0, policy_version 96096 (0.0010) -[2023-11-28 02:43:42,570][87426] Updated weights for policy 1, policy_version 95930 (0.0011) -[2023-11-28 02:43:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 49160192. Throughput: 0: 2738.5, 1: 2748.4. Samples: 49171980. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:43,445][86177] Avg episode reward: [(0, '-507.360'), (1, '-537.720')] -[2023-11-28 02:43:44,304][87424] Updated weights for policy 0, policy_version 96106 (0.0008) -[2023-11-28 02:43:44,691][87424] Updated weights for policy 0, policy_version 96116 (0.0009) -[2023-11-28 02:43:44,715][87426] Updated weights for policy 1, policy_version 95940 (0.0010) -[2023-11-28 02:43:45,072][87424] Updated weights for policy 0, policy_version 96126 (0.0008) -[2023-11-28 02:43:45,094][87426] Updated weights for policy 1, policy_version 95950 (0.0007) -[2023-11-28 02:43:45,476][87426] Updated weights for policy 1, policy_version 95960 (0.0009) -[2023-11-28 02:43:47,273][87424] Updated weights for policy 0, policy_version 96136 (0.0012) -[2023-11-28 02:43:47,663][87424] Updated weights for policy 0, policy_version 96146 (0.0011) -[2023-11-28 02:43:47,672][87426] Updated weights for policy 1, policy_version 95970 (0.0009) -[2023-11-28 02:43:48,050][87424] Updated weights for policy 0, policy_version 96156 (0.0011) -[2023-11-28 02:43:48,058][87426] Updated weights for policy 1, policy_version 95980 (0.0011) -[2023-11-28 02:43:48,432][87426] Updated weights for policy 1, policy_version 95990 (0.0010) -[2023-11-28 02:43:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 49184768. Throughput: 0: 2735.1, 1: 2757.7. Samples: 49197096. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:48,445][86177] Avg episode reward: [(0, '-498.010'), (1, '-533.110')] -[2023-11-28 02:43:48,811][87426] Updated weights for policy 1, policy_version 96000 (0.0007) -[2023-11-28 02:43:50,214][87424] Updated weights for policy 0, policy_version 96166 (0.0009) -[2023-11-28 02:43:50,601][87424] Updated weights for policy 0, policy_version 96176 (0.0009) -[2023-11-28 02:43:50,985][87424] Updated weights for policy 0, policy_version 96186 (0.0008) -[2023-11-28 02:43:51,236][87426] Updated weights for policy 1, policy_version 96010 (0.0012) -[2023-11-28 02:43:51,622][87426] Updated weights for policy 1, policy_version 96020 (0.0012) -[2023-11-28 02:43:51,996][87426] Updated weights for policy 1, policy_version 96030 (0.0012) -[2023-11-28 02:43:53,289][87424] Updated weights for policy 0, policy_version 96196 (0.0010) -[2023-11-28 02:43:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 49209344. Throughput: 0: 2705.3, 1: 2759.2. Samples: 49229100. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:53,445][86177] Avg episode reward: [(0, '-501.190'), (1, '-541.810')] -[2023-11-28 02:43:53,677][87424] Updated weights for policy 0, policy_version 96206 (0.0011) -[2023-11-28 02:43:54,057][87424] Updated weights for policy 0, policy_version 96216 (0.0009) -[2023-11-28 02:43:54,263][87426] Updated weights for policy 1, policy_version 96040 (0.0011) -[2023-11-28 02:43:54,642][87426] Updated weights for policy 1, policy_version 96050 (0.0012) -[2023-11-28 02:43:55,006][87426] Updated weights for policy 1, policy_version 96060 (0.0012) -[2023-11-28 02:43:56,550][87424] Updated weights for policy 0, policy_version 96226 (0.0008) -[2023-11-28 02:43:56,867][87426] Updated weights for policy 1, policy_version 96070 (0.0012) -[2023-11-28 02:43:56,944][87424] Updated weights for policy 0, policy_version 96236 (0.0009) -[2023-11-28 02:43:57,244][87426] Updated weights for policy 1, policy_version 96080 (0.0011) -[2023-11-28 02:43:57,323][87424] Updated weights for policy 0, policy_version 96246 (0.0007) -[2023-11-28 02:43:57,625][87426] Updated weights for policy 1, policy_version 96090 (0.0010) -[2023-11-28 02:43:57,717][87424] Updated weights for policy 0, policy_version 96256 (0.0007) -[2023-11-28 02:43:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 49242112. Throughput: 0: 2708.7, 1: 2773.6. Samples: 49254000. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:43:58,445][86177] Avg episode reward: [(0, '-507.490'), (1, '-544.670')] -[2023-11-28 02:43:59,828][87424] Updated weights for policy 0, policy_version 96266 (0.0009) -[2023-11-28 02:43:59,879][87426] Updated weights for policy 1, policy_version 96100 (0.0011) -[2023-11-28 02:44:00,210][87424] Updated weights for policy 0, policy_version 96276 (0.0011) -[2023-11-28 02:44:00,267][87426] Updated weights for policy 1, policy_version 96110 (0.0011) -[2023-11-28 02:44:00,595][87424] Updated weights for policy 0, policy_version 96286 (0.0008) -[2023-11-28 02:44:00,640][87426] Updated weights for policy 1, policy_version 96120 (0.0011) -[2023-11-28 02:44:02,273][87424] Updated weights for policy 0, policy_version 96296 (0.0009) -[2023-11-28 02:44:02,659][87424] Updated weights for policy 0, policy_version 96306 (0.0011) -[2023-11-28 02:44:03,059][87424] Updated weights for policy 0, policy_version 96316 (0.0010) -[2023-11-28 02:44:03,080][87426] Updated weights for policy 1, policy_version 96130 (0.0011) -[2023-11-28 02:44:03,444][87426] Updated weights for policy 1, policy_version 96140 (0.0009) -[2023-11-28 02:44:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 49266688. Throughput: 0: 2707.9, 1: 2736.7. Samples: 49277680. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:44:03,445][86177] Avg episode reward: [(0, '-506.210'), (1, '-516.800')] -[2023-11-28 02:44:03,831][87426] Updated weights for policy 1, policy_version 96150 (0.0007) -[2023-11-28 02:44:04,215][87426] Updated weights for policy 1, policy_version 96160 (0.0007) -[2023-11-28 02:44:05,457][87424] Updated weights for policy 0, policy_version 96326 (0.0008) -[2023-11-28 02:44:05,846][87424] Updated weights for policy 0, policy_version 96336 (0.0010) -[2023-11-28 02:44:06,222][87424] Updated weights for policy 0, policy_version 96346 (0.0011) -[2023-11-28 02:44:06,577][87426] Updated weights for policy 1, policy_version 96170 (0.0012) -[2023-11-28 02:44:06,964][87426] Updated weights for policy 1, policy_version 96180 (0.0012) -[2023-11-28 02:44:07,338][87426] Updated weights for policy 1, policy_version 96190 (0.0012) -[2023-11-28 02:44:08,379][87424] Updated weights for policy 0, policy_version 96356 (0.0010) -[2023-11-28 02:44:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 49291264. Throughput: 0: 2727.6, 1: 2723.7. Samples: 49309512. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:44:08,445][86177] Avg episode reward: [(0, '-506.940'), (1, '-556.330')] -[2023-11-28 02:44:08,770][87424] Updated weights for policy 0, policy_version 96366 (0.0007) -[2023-11-28 02:44:09,148][87424] Updated weights for policy 0, policy_version 96376 (0.0011) -[2023-11-28 02:44:09,911][87426] Updated weights for policy 1, policy_version 96200 (0.0012) -[2023-11-28 02:44:10,291][87426] Updated weights for policy 1, policy_version 96210 (0.0012) -[2023-11-28 02:44:10,677][87426] Updated weights for policy 1, policy_version 96220 (0.0012) -[2023-11-28 02:44:11,250][87424] Updated weights for policy 0, policy_version 96386 (0.0012) -[2023-11-28 02:44:11,637][87424] Updated weights for policy 0, policy_version 96396 (0.0012) -[2023-11-28 02:44:12,020][87424] Updated weights for policy 0, policy_version 96406 (0.0012) -[2023-11-28 02:44:12,394][87424] Updated weights for policy 0, policy_version 96416 (0.0010) -[2023-11-28 02:44:13,174][87426] Updated weights for policy 1, policy_version 96230 (0.0011) -[2023-11-28 02:44:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 49315840. Throughput: 0: 2726.7, 1: 2707.8. Samples: 49333732. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:13,446][86177] Avg episode reward: [(0, '-504.890'), (1, '-554.650')] -[2023-11-28 02:44:13,557][87426] Updated weights for policy 1, policy_version 96240 (0.0008) -[2023-11-28 02:44:13,942][87426] Updated weights for policy 1, policy_version 96250 (0.0007) -[2023-11-28 02:44:14,596][87424] Updated weights for policy 0, policy_version 96426 (0.0010) -[2023-11-28 02:44:14,991][87424] Updated weights for policy 0, policy_version 96436 (0.0011) -[2023-11-28 02:44:15,374][87424] Updated weights for policy 0, policy_version 96446 (0.0012) -[2023-11-28 02:44:16,125][87426] Updated weights for policy 1, policy_version 96260 (0.0009) -[2023-11-28 02:44:16,504][87426] Updated weights for policy 1, policy_version 96270 (0.0012) -[2023-11-28 02:44:16,882][87426] Updated weights for policy 1, policy_version 96280 (0.0012) -[2023-11-28 02:44:17,374][87424] Updated weights for policy 0, policy_version 96456 (0.0011) -[2023-11-28 02:44:17,763][87424] Updated weights for policy 0, policy_version 96466 (0.0012) -[2023-11-28 02:44:18,142][87424] Updated weights for policy 0, policy_version 96476 (0.0011) -[2023-11-28 02:44:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 49348608. Throughput: 0: 2690.4, 1: 2691.5. Samples: 49357324. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:18,446][86177] Avg episode reward: [(0, '-498.070'), (1, '-563.660')] -[2023-11-28 02:44:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000096288_24649728.pth... -[2023-11-28 02:44:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000096480_24698880.pth... -[2023-11-28 02:44:18,493][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000093792_24010752.pth -[2023-11-28 02:44:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000093920_24043520.pth -[2023-11-28 02:44:18,702][87426] Updated weights for policy 1, policy_version 96290 (0.0010) -[2023-11-28 02:44:19,093][87426] Updated weights for policy 1, policy_version 96300 (0.0008) -[2023-11-28 02:44:19,461][87426] Updated weights for policy 1, policy_version 96310 (0.0008) -[2023-11-28 02:44:19,846][87426] Updated weights for policy 1, policy_version 96320 (0.0008) -[2023-11-28 02:44:20,460][87424] Updated weights for policy 0, policy_version 96486 (0.0010) -[2023-11-28 02:44:20,841][87424] Updated weights for policy 0, policy_version 96496 (0.0012) -[2023-11-28 02:44:21,220][87424] Updated weights for policy 0, policy_version 96506 (0.0012) -[2023-11-28 02:44:22,157][87426] Updated weights for policy 1, policy_version 96330 (0.0009) -[2023-11-28 02:44:22,538][87426] Updated weights for policy 1, policy_version 96340 (0.0012) -[2023-11-28 02:44:22,908][87426] Updated weights for policy 1, policy_version 96350 (0.0012) -[2023-11-28 02:44:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 49373184. Throughput: 0: 2652.0, 1: 2694.9. Samples: 49389368. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:23,445][86177] Avg episode reward: [(0, '-497.790'), (1, '-565.800')] -[2023-11-28 02:44:23,638][87424] Updated weights for policy 0, policy_version 96516 (0.0012) -[2023-11-28 02:44:24,014][87424] Updated weights for policy 0, policy_version 96526 (0.0012) -[2023-11-28 02:44:24,399][87424] Updated weights for policy 0, policy_version 96536 (0.0012) -[2023-11-28 02:44:25,048][87426] Updated weights for policy 1, policy_version 96360 (0.0010) -[2023-11-28 02:44:25,432][87426] Updated weights for policy 1, policy_version 96370 (0.0008) -[2023-11-28 02:44:25,812][87426] Updated weights for policy 1, policy_version 96380 (0.0010) -[2023-11-28 02:44:26,424][87424] Updated weights for policy 0, policy_version 96546 (0.0011) -[2023-11-28 02:44:26,802][87424] Updated weights for policy 0, policy_version 96556 (0.0011) -[2023-11-28 02:44:27,183][87424] Updated weights for policy 0, policy_version 96566 (0.0009) -[2023-11-28 02:44:27,563][87424] Updated weights for policy 0, policy_version 96576 (0.0007) -[2023-11-28 02:44:27,911][87426] Updated weights for policy 1, policy_version 96390 (0.0009) -[2023-11-28 02:44:28,292][87426] Updated weights for policy 1, policy_version 96400 (0.0007) -[2023-11-28 02:44:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 49397760. Throughput: 0: 2669.1, 1: 2701.5. Samples: 49413656. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:28,445][86177] Avg episode reward: [(0, '-499.210'), (1, '-538.910')] -[2023-11-28 02:44:28,668][87426] Updated weights for policy 1, policy_version 96410 (0.0007) -[2023-11-28 02:44:30,000][87424] Updated weights for policy 0, policy_version 96586 (0.0011) -[2023-11-28 02:44:30,373][87424] Updated weights for policy 0, policy_version 96596 (0.0011) -[2023-11-28 02:44:30,755][87424] Updated weights for policy 0, policy_version 96606 (0.0008) -[2023-11-28 02:44:31,008][87426] Updated weights for policy 1, policy_version 96420 (0.0008) -[2023-11-28 02:44:31,389][87426] Updated weights for policy 1, policy_version 96430 (0.0007) -[2023-11-28 02:44:31,762][87426] Updated weights for policy 1, policy_version 96440 (0.0009) -[2023-11-28 02:44:33,323][87424] Updated weights for policy 0, policy_version 96616 (0.0010) -[2023-11-28 02:44:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 49422336. Throughput: 0: 2650.8, 1: 2689.2. Samples: 49437396. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:33,445][86177] Avg episode reward: [(0, '-512.360'), (1, '-542.620')] -[2023-11-28 02:44:33,696][87424] Updated weights for policy 0, policy_version 96626 (0.0009) -[2023-11-28 02:44:34,077][87424] Updated weights for policy 0, policy_version 96636 (0.0007) -[2023-11-28 02:44:34,099][87426] Updated weights for policy 1, policy_version 96450 (0.0008) -[2023-11-28 02:44:34,475][87426] Updated weights for policy 1, policy_version 96460 (0.0010) -[2023-11-28 02:44:34,856][87426] Updated weights for policy 1, policy_version 96470 (0.0010) -[2023-11-28 02:44:35,238][87426] Updated weights for policy 1, policy_version 96480 (0.0009) -[2023-11-28 02:44:36,426][87424] Updated weights for policy 0, policy_version 96646 (0.0007) -[2023-11-28 02:44:36,811][87424] Updated weights for policy 0, policy_version 96656 (0.0007) -[2023-11-28 02:44:37,193][87424] Updated weights for policy 0, policy_version 96666 (0.0008) -[2023-11-28 02:44:37,580][87426] Updated weights for policy 1, policy_version 96490 (0.0011) -[2023-11-28 02:44:37,963][87426] Updated weights for policy 1, policy_version 96500 (0.0012) -[2023-11-28 02:44:38,350][87426] Updated weights for policy 1, policy_version 96510 (0.0011) -[2023-11-28 02:44:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 49455104. Throughput: 0: 2655.8, 1: 2678.0. Samples: 49469124. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:38,445][86177] Avg episode reward: [(0, '-511.650'), (1, '-525.790')] -[2023-11-28 02:44:38,916][87424] Updated weights for policy 0, policy_version 96676 (0.0011) -[2023-11-28 02:44:39,299][87424] Updated weights for policy 0, policy_version 96686 (0.0007) -[2023-11-28 02:44:39,681][87424] Updated weights for policy 0, policy_version 96696 (0.0008) -[2023-11-28 02:44:40,592][87426] Updated weights for policy 1, policy_version 96520 (0.0011) -[2023-11-28 02:44:40,978][87426] Updated weights for policy 1, policy_version 96530 (0.0012) -[2023-11-28 02:44:41,344][87426] Updated weights for policy 1, policy_version 96540 (0.0012) -[2023-11-28 02:44:41,932][87424] Updated weights for policy 0, policy_version 96706 (0.0011) -[2023-11-28 02:44:42,307][87424] Updated weights for policy 0, policy_version 96716 (0.0010) -[2023-11-28 02:44:42,693][87424] Updated weights for policy 0, policy_version 96726 (0.0012) -[2023-11-28 02:44:43,072][87424] Updated weights for policy 0, policy_version 96736 (0.0011) -[2023-11-28 02:44:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 49479680. Throughput: 0: 2667.4, 1: 2644.0. Samples: 49493012. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:43,445][86177] Avg episode reward: [(0, '-505.810'), (1, '-524.870')] -[2023-11-28 02:44:43,497][87426] Updated weights for policy 1, policy_version 96550 (0.0011) -[2023-11-28 02:44:43,878][87426] Updated weights for policy 1, policy_version 96560 (0.0009) -[2023-11-28 02:44:44,265][87426] Updated weights for policy 1, policy_version 96570 (0.0007) -[2023-11-28 02:44:44,964][87424] Updated weights for policy 0, policy_version 96746 (0.0012) -[2023-11-28 02:44:45,333][87424] Updated weights for policy 0, policy_version 96756 (0.0012) -[2023-11-28 02:44:45,720][87424] Updated weights for policy 0, policy_version 96766 (0.0012) -[2023-11-28 02:44:46,617][87426] Updated weights for policy 1, policy_version 96580 (0.0009) -[2023-11-28 02:44:46,991][87426] Updated weights for policy 1, policy_version 96590 (0.0008) -[2023-11-28 02:44:47,368][87426] Updated weights for policy 1, policy_version 96600 (0.0007) -[2023-11-28 02:44:47,902][87424] Updated weights for policy 0, policy_version 96776 (0.0009) -[2023-11-28 02:44:48,288][87424] Updated weights for policy 0, policy_version 96786 (0.0008) -[2023-11-28 02:44:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 49504256. Throughput: 0: 2699.5, 1: 2661.9. Samples: 49518944. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:48,445][86177] Avg episode reward: [(0, '-502.740'), (1, '-526.610')] -[2023-11-28 02:44:48,680][87424] Updated weights for policy 0, policy_version 96796 (0.0008) -[2023-11-28 02:44:49,939][87426] Updated weights for policy 1, policy_version 96610 (0.0008) -[2023-11-28 02:44:50,316][87426] Updated weights for policy 1, policy_version 96620 (0.0007) -[2023-11-28 02:44:50,693][87426] Updated weights for policy 1, policy_version 96630 (0.0008) -[2023-11-28 02:44:51,067][87426] Updated weights for policy 1, policy_version 96640 (0.0008) -[2023-11-28 02:44:51,093][87424] Updated weights for policy 0, policy_version 96806 (0.0010) -[2023-11-28 02:44:51,472][87424] Updated weights for policy 0, policy_version 96816 (0.0010) -[2023-11-28 02:44:51,852][87424] Updated weights for policy 0, policy_version 96826 (0.0010) -[2023-11-28 02:44:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 49528832. Throughput: 0: 2700.7, 1: 2644.4. Samples: 49550044. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:53,445][86177] Avg episode reward: [(0, '-494.820'), (1, '-536.600')] -[2023-11-28 02:44:53,535][87426] Updated weights for policy 1, policy_version 96650 (0.0011) -[2023-11-28 02:44:53,911][87426] Updated weights for policy 1, policy_version 96660 (0.0011) -[2023-11-28 02:44:54,053][87424] Updated weights for policy 0, policy_version 96836 (0.0010) -[2023-11-28 02:44:54,289][87426] Updated weights for policy 1, policy_version 96670 (0.0009) -[2023-11-28 02:44:54,443][87424] Updated weights for policy 0, policy_version 96846 (0.0012) -[2023-11-28 02:44:54,820][87424] Updated weights for policy 0, policy_version 96856 (0.0008) -[2023-11-28 02:44:56,285][87426] Updated weights for policy 1, policy_version 96680 (0.0011) -[2023-11-28 02:44:56,542][87424] Updated weights for policy 0, policy_version 96866 (0.0008) -[2023-11-28 02:44:56,663][87426] Updated weights for policy 1, policy_version 96690 (0.0012) -[2023-11-28 02:44:56,927][87424] Updated weights for policy 0, policy_version 96876 (0.0012) -[2023-11-28 02:44:57,039][87426] Updated weights for policy 1, policy_version 96700 (0.0012) -[2023-11-28 02:44:57,299][87424] Updated weights for policy 0, policy_version 96886 (0.0011) -[2023-11-28 02:44:57,683][87424] Updated weights for policy 0, policy_version 96896 (0.0011) -[2023-11-28 02:44:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 49561600. Throughput: 0: 2701.9, 1: 2664.5. Samples: 49575216. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:44:58,445][86177] Avg episode reward: [(0, '-496.420'), (1, '-538.020')] -[2023-11-28 02:44:58,794][87426] Updated weights for policy 1, policy_version 96710 (0.0011) -[2023-11-28 02:44:59,172][87426] Updated weights for policy 1, policy_version 96720 (0.0012) -[2023-11-28 02:44:59,561][87426] Updated weights for policy 1, policy_version 96730 (0.0011) -[2023-11-28 02:45:00,104][87424] Updated weights for policy 0, policy_version 96906 (0.0010) -[2023-11-28 02:45:00,492][87424] Updated weights for policy 0, policy_version 96916 (0.0009) -[2023-11-28 02:45:00,867][87424] Updated weights for policy 0, policy_version 96926 (0.0012) -[2023-11-28 02:45:01,832][87426] Updated weights for policy 1, policy_version 96740 (0.0011) -[2023-11-28 02:45:02,209][87426] Updated weights for policy 1, policy_version 96750 (0.0010) -[2023-11-28 02:45:02,592][87426] Updated weights for policy 1, policy_version 96760 (0.0008) -[2023-11-28 02:45:03,149][87424] Updated weights for policy 0, policy_version 96936 (0.0011) -[2023-11-28 02:45:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 49586176. Throughput: 0: 2726.6, 1: 2674.5. Samples: 49600372. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:45:03,445][86177] Avg episode reward: [(0, '-495.350'), (1, '-538.750')] -[2023-11-28 02:45:03,535][87424] Updated weights for policy 0, policy_version 96946 (0.0012) -[2023-11-28 02:45:03,907][87424] Updated weights for policy 0, policy_version 96956 (0.0011) -[2023-11-28 02:45:05,152][87426] Updated weights for policy 1, policy_version 96770 (0.0008) -[2023-11-28 02:45:05,525][87426] Updated weights for policy 1, policy_version 96780 (0.0008) -[2023-11-28 02:45:05,853][87424] Updated weights for policy 0, policy_version 96966 (0.0009) -[2023-11-28 02:45:05,909][87426] Updated weights for policy 1, policy_version 96790 (0.0007) -[2023-11-28 02:45:06,231][87424] Updated weights for policy 0, policy_version 96976 (0.0008) -[2023-11-28 02:45:06,293][87426] Updated weights for policy 1, policy_version 96800 (0.0007) -[2023-11-28 02:45:06,635][87424] Updated weights for policy 0, policy_version 96986 (0.0008) -[2023-11-28 02:45:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 49610752. Throughput: 0: 2741.4, 1: 2629.7. Samples: 49631068. Policy #0 lag: (min: 19.0, avg: 32.0, max: 44.0) -[2023-11-28 02:45:08,445][86177] Avg episode reward: [(0, '-494.390'), (1, '-524.980')] -[2023-11-28 02:45:08,519][87424] Updated weights for policy 0, policy_version 96996 (0.0011) -[2023-11-28 02:45:08,838][87426] Updated weights for policy 1, policy_version 96810 (0.0009) -[2023-11-28 02:45:08,909][87424] Updated weights for policy 0, policy_version 97006 (0.0012) -[2023-11-28 02:45:09,218][87426] Updated weights for policy 1, policy_version 96820 (0.0011) -[2023-11-28 02:45:09,297][87424] Updated weights for policy 0, policy_version 97016 (0.0011) -[2023-11-28 02:45:09,604][87426] Updated weights for policy 1, policy_version 96830 (0.0012) -[2023-11-28 02:45:11,633][87424] Updated weights for policy 0, policy_version 97026 (0.0009) -[2023-11-28 02:45:12,016][87424] Updated weights for policy 0, policy_version 97036 (0.0011) -[2023-11-28 02:45:12,017][87426] Updated weights for policy 1, policy_version 96840 (0.0010) -[2023-11-28 02:45:12,392][87424] Updated weights for policy 0, policy_version 97046 (0.0009) -[2023-11-28 02:45:12,392][87426] Updated weights for policy 1, policy_version 96850 (0.0010) -[2023-11-28 02:45:12,775][87424] Updated weights for policy 0, policy_version 97056 (0.0008) -[2023-11-28 02:45:12,776][87426] Updated weights for policy 1, policy_version 96860 (0.0011) -[2023-11-28 02:45:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 49643520. Throughput: 0: 2732.6, 1: 2607.4. Samples: 49653956. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:13,445][86177] Avg episode reward: [(0, '-491.660'), (1, '-509.750')] -[2023-11-28 02:45:14,858][87424] Updated weights for policy 0, policy_version 97066 (0.0008) -[2023-11-28 02:45:15,251][87424] Updated weights for policy 0, policy_version 97076 (0.0009) -[2023-11-28 02:45:15,313][87426] Updated weights for policy 1, policy_version 96870 (0.0010) -[2023-11-28 02:45:15,627][87424] Updated weights for policy 0, policy_version 97086 (0.0008) -[2023-11-28 02:45:15,694][87426] Updated weights for policy 1, policy_version 96880 (0.0009) -[2023-11-28 02:45:16,070][87426] Updated weights for policy 1, policy_version 96890 (0.0010) -[2023-11-28 02:45:17,783][87426] Updated weights for policy 1, policy_version 96900 (0.0009) -[2023-11-28 02:45:18,073][87424] Updated weights for policy 0, policy_version 97096 (0.0008) -[2023-11-28 02:45:18,157][87426] Updated weights for policy 1, policy_version 96910 (0.0011) -[2023-11-28 02:45:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 49659904. Throughput: 0: 2762.0, 1: 2594.2. Samples: 49678428. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:18,445][86177] Avg episode reward: [(0, '-491.440'), (1, '-512.440')] -[2023-11-28 02:45:18,458][87424] Updated weights for policy 0, policy_version 97106 (0.0008) -[2023-11-28 02:45:18,532][87426] Updated weights for policy 1, policy_version 96920 (0.0011) -[2023-11-28 02:45:18,833][87424] Updated weights for policy 0, policy_version 97116 (0.0011) -[2023-11-28 02:45:20,299][87426] Updated weights for policy 1, policy_version 96930 (0.0009) -[2023-11-28 02:45:20,683][87426] Updated weights for policy 1, policy_version 96940 (0.0012) -[2023-11-28 02:45:21,065][87426] Updated weights for policy 1, policy_version 96950 (0.0012) -[2023-11-28 02:45:21,149][87424] Updated weights for policy 0, policy_version 97126 (0.0012) -[2023-11-28 02:45:21,449][87426] Updated weights for policy 1, policy_version 96960 (0.0013) -[2023-11-28 02:45:21,526][87424] Updated weights for policy 0, policy_version 97136 (0.0010) -[2023-11-28 02:45:21,913][87424] Updated weights for policy 0, policy_version 97146 (0.0012) -[2023-11-28 02:45:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 49692672. Throughput: 0: 2762.2, 1: 2632.5. Samples: 49711884. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:23,445][86177] Avg episode reward: [(0, '-510.560'), (1, '-510.100')] -[2023-11-28 02:45:23,798][87426] Updated weights for policy 1, policy_version 96970 (0.0012) -[2023-11-28 02:45:24,007][87424] Updated weights for policy 0, policy_version 97156 (0.0012) -[2023-11-28 02:45:24,179][87426] Updated weights for policy 1, policy_version 96980 (0.0011) -[2023-11-28 02:45:24,391][87424] Updated weights for policy 0, policy_version 97166 (0.0012) -[2023-11-28 02:45:24,561][87426] Updated weights for policy 1, policy_version 96990 (0.0011) -[2023-11-28 02:45:24,769][87424] Updated weights for policy 0, policy_version 97176 (0.0011) -[2023-11-28 02:45:26,872][87426] Updated weights for policy 1, policy_version 97000 (0.0008) -[2023-11-28 02:45:26,893][87424] Updated weights for policy 0, policy_version 97186 (0.0012) -[2023-11-28 02:45:27,259][87426] Updated weights for policy 1, policy_version 97010 (0.0011) -[2023-11-28 02:45:27,276][87424] Updated weights for policy 0, policy_version 97196 (0.0011) -[2023-11-28 02:45:27,634][87426] Updated weights for policy 1, policy_version 97020 (0.0011) -[2023-11-28 02:45:27,661][87424] Updated weights for policy 0, policy_version 97206 (0.0012) -[2023-11-28 02:45:28,033][87424] Updated weights for policy 0, policy_version 97216 (0.0012) -[2023-11-28 02:45:28,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 49725440. Throughput: 0: 2761.5, 1: 2667.0. Samples: 49737296. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:28,446][86177] Avg episode reward: [(0, '-516.130'), (1, '-510.820')] -[2023-11-28 02:45:29,399][87426] Updated weights for policy 1, policy_version 97030 (0.0011) -[2023-11-28 02:45:29,771][87424] Updated weights for policy 0, policy_version 97226 (0.0012) -[2023-11-28 02:45:29,785][87426] Updated weights for policy 1, policy_version 97040 (0.0009) -[2023-11-28 02:45:30,152][87424] Updated weights for policy 0, policy_version 97236 (0.0009) -[2023-11-28 02:45:30,166][87426] Updated weights for policy 1, policy_version 97050 (0.0008) -[2023-11-28 02:45:30,533][87424] Updated weights for policy 0, policy_version 97246 (0.0009) -[2023-11-28 02:45:32,629][87426] Updated weights for policy 1, policy_version 97060 (0.0008) -[2023-11-28 02:45:32,977][87424] Updated weights for policy 0, policy_version 97256 (0.0011) -[2023-11-28 02:45:33,009][87426] Updated weights for policy 1, policy_version 97070 (0.0008) -[2023-11-28 02:45:33,364][87424] Updated weights for policy 0, policy_version 97266 (0.0012) -[2023-11-28 02:45:33,399][87426] Updated weights for policy 1, policy_version 97080 (0.0007) -[2023-11-28 02:45:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 49741824. Throughput: 0: 2726.1, 1: 2669.9. Samples: 49761760. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:33,445][86177] Avg episode reward: [(0, '-521.400'), (1, '-505.460')] -[2023-11-28 02:45:33,736][87424] Updated weights for policy 0, policy_version 97276 (0.0009) -[2023-11-28 02:45:35,318][87426] Updated weights for policy 1, policy_version 97090 (0.0008) -[2023-11-28 02:45:35,693][87426] Updated weights for policy 1, policy_version 97100 (0.0011) -[2023-11-28 02:45:35,724][87424] Updated weights for policy 0, policy_version 97286 (0.0008) -[2023-11-28 02:45:36,079][87426] Updated weights for policy 1, policy_version 97110 (0.0012) -[2023-11-28 02:45:36,106][87424] Updated weights for policy 0, policy_version 97296 (0.0007) -[2023-11-28 02:45:36,472][87426] Updated weights for policy 1, policy_version 97120 (0.0012) -[2023-11-28 02:45:36,492][87424] Updated weights for policy 0, policy_version 97306 (0.0007) -[2023-11-28 02:45:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 49774592. Throughput: 0: 2745.0, 1: 2702.1. Samples: 49795164. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:38,445][86177] Avg episode reward: [(0, '-521.910'), (1, '-513.810')] -[2023-11-28 02:45:38,823][87424] Updated weights for policy 0, policy_version 97316 (0.0008) -[2023-11-28 02:45:39,002][87426] Updated weights for policy 1, policy_version 97130 (0.0012) -[2023-11-28 02:45:39,214][87424] Updated weights for policy 0, policy_version 97326 (0.0008) -[2023-11-28 02:45:39,379][87426] Updated weights for policy 1, policy_version 97140 (0.0015) -[2023-11-28 02:45:39,588][87424] Updated weights for policy 0, policy_version 97336 (0.0009) -[2023-11-28 02:45:39,785][87426] Updated weights for policy 1, policy_version 97150 (0.0008) -[2023-11-28 02:45:41,530][87424] Updated weights for policy 0, policy_version 97346 (0.0010) -[2023-11-28 02:45:41,636][87426] Updated weights for policy 1, policy_version 97160 (0.0009) -[2023-11-28 02:45:41,906][87424] Updated weights for policy 0, policy_version 97356 (0.0013) -[2023-11-28 02:45:42,026][87426] Updated weights for policy 1, policy_version 97170 (0.0012) -[2023-11-28 02:45:42,280][87424] Updated weights for policy 0, policy_version 97366 (0.0010) -[2023-11-28 02:45:42,397][87426] Updated weights for policy 1, policy_version 97180 (0.0010) -[2023-11-28 02:45:42,664][87424] Updated weights for policy 0, policy_version 97376 (0.0011) -[2023-11-28 02:45:43,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 49807360. Throughput: 0: 2740.9, 1: 2691.3. Samples: 49819664. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:43,445][86177] Avg episode reward: [(0, '-501.230'), (1, '-514.680')] -[2023-11-28 02:45:44,725][87426] Updated weights for policy 1, policy_version 97190 (0.0012) -[2023-11-28 02:45:45,076][87424] Updated weights for policy 0, policy_version 97386 (0.0008) -[2023-11-28 02:45:45,108][87426] Updated weights for policy 1, policy_version 97200 (0.0009) -[2023-11-28 02:45:45,465][87424] Updated weights for policy 0, policy_version 97396 (0.0009) -[2023-11-28 02:45:45,490][87426] Updated weights for policy 1, policy_version 97210 (0.0010) -[2023-11-28 02:45:45,849][87424] Updated weights for policy 0, policy_version 97406 (0.0009) -[2023-11-28 02:45:47,537][87426] Updated weights for policy 1, policy_version 97220 (0.0010) -[2023-11-28 02:45:47,880][87424] Updated weights for policy 0, policy_version 97416 (0.0011) -[2023-11-28 02:45:47,921][87426] Updated weights for policy 1, policy_version 97230 (0.0007) -[2023-11-28 02:45:48,267][87424] Updated weights for policy 0, policy_version 97426 (0.0010) -[2023-11-28 02:45:48,298][87426] Updated weights for policy 1, policy_version 97240 (0.0007) -[2023-11-28 02:45:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 49823744. Throughput: 0: 2716.8, 1: 2689.1. Samples: 49843636. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:48,445][86177] Avg episode reward: [(0, '-501.860'), (1, '-522.120')] -[2023-11-28 02:45:48,656][87424] Updated weights for policy 0, policy_version 97436 (0.0007) -[2023-11-28 02:45:50,694][87426] Updated weights for policy 1, policy_version 97250 (0.0008) -[2023-11-28 02:45:51,069][87426] Updated weights for policy 1, policy_version 97260 (0.0009) -[2023-11-28 02:45:51,096][87424] Updated weights for policy 0, policy_version 97446 (0.0010) -[2023-11-28 02:45:51,446][87426] Updated weights for policy 1, policy_version 97270 (0.0008) -[2023-11-28 02:45:51,475][87424] Updated weights for policy 0, policy_version 97456 (0.0012) -[2023-11-28 02:45:51,827][87426] Updated weights for policy 1, policy_version 97280 (0.0009) -[2023-11-28 02:45:51,860][87424] Updated weights for policy 0, policy_version 97466 (0.0011) -[2023-11-28 02:45:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 49856512. Throughput: 0: 2703.2, 1: 2715.1. Samples: 49874892. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:53,445][86177] Avg episode reward: [(0, '-503.570'), (1, '-521.900')] -[2023-11-28 02:45:54,048][87424] Updated weights for policy 0, policy_version 97476 (0.0012) -[2023-11-28 02:45:54,387][87426] Updated weights for policy 1, policy_version 97290 (0.0009) -[2023-11-28 02:45:54,422][87424] Updated weights for policy 0, policy_version 97486 (0.0009) -[2023-11-28 02:45:54,776][87426] Updated weights for policy 1, policy_version 97300 (0.0010) -[2023-11-28 02:45:54,807][87424] Updated weights for policy 0, policy_version 97496 (0.0008) -[2023-11-28 02:45:55,157][87426] Updated weights for policy 1, policy_version 97310 (0.0009) -[2023-11-28 02:45:57,119][87426] Updated weights for policy 1, policy_version 97320 (0.0009) -[2023-11-28 02:45:57,197][87424] Updated weights for policy 0, policy_version 97506 (0.0008) -[2023-11-28 02:45:57,497][87426] Updated weights for policy 1, policy_version 97330 (0.0007) -[2023-11-28 02:45:57,582][87424] Updated weights for policy 0, policy_version 97516 (0.0008) -[2023-11-28 02:45:57,878][87426] Updated weights for policy 1, policy_version 97340 (0.0010) -[2023-11-28 02:45:57,965][87424] Updated weights for policy 0, policy_version 97526 (0.0010) -[2023-11-28 02:45:58,347][87424] Updated weights for policy 0, policy_version 97536 (0.0012) -[2023-11-28 02:45:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 49889280. Throughput: 0: 2714.5, 1: 2740.3. Samples: 49899420. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:45:58,445][86177] Avg episode reward: [(0, '-502.430'), (1, '-515.090')] -[2023-11-28 02:45:59,667][87426] Updated weights for policy 1, policy_version 97350 (0.0010) -[2023-11-28 02:46:00,045][87424] Updated weights for policy 0, policy_version 97546 (0.0011) -[2023-11-28 02:46:00,046][87426] Updated weights for policy 1, policy_version 97360 (0.0010) -[2023-11-28 02:46:00,428][87424] Updated weights for policy 0, policy_version 97556 (0.0011) -[2023-11-28 02:46:00,430][87426] Updated weights for policy 1, policy_version 97370 (0.0008) -[2023-11-28 02:46:00,820][87424] Updated weights for policy 0, policy_version 97566 (0.0012) -[2023-11-28 02:46:02,391][87426] Updated weights for policy 1, policy_version 97380 (0.0010) -[2023-11-28 02:46:02,774][87426] Updated weights for policy 1, policy_version 97390 (0.0012) -[2023-11-28 02:46:03,118][87424] Updated weights for policy 0, policy_version 97576 (0.0012) -[2023-11-28 02:46:03,153][87426] Updated weights for policy 1, policy_version 97400 (0.0011) -[2023-11-28 02:46:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 49905664. Throughput: 0: 2700.9, 1: 2766.3. Samples: 49924452. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:46:03,445][86177] Avg episode reward: [(0, '-504.860'), (1, '-518.770')] -[2023-11-28 02:46:03,500][87424] Updated weights for policy 0, policy_version 97586 (0.0011) -[2023-11-28 02:46:03,882][87424] Updated weights for policy 0, policy_version 97596 (0.0012) -[2023-11-28 02:46:04,945][87426] Updated weights for policy 1, policy_version 97410 (0.0012) -[2023-11-28 02:46:05,323][87426] Updated weights for policy 1, policy_version 97420 (0.0012) -[2023-11-28 02:46:05,706][87426] Updated weights for policy 1, policy_version 97430 (0.0012) -[2023-11-28 02:46:05,984][87424] Updated weights for policy 0, policy_version 97606 (0.0012) -[2023-11-28 02:46:06,087][87426] Updated weights for policy 1, policy_version 97440 (0.0012) -[2023-11-28 02:46:06,364][87424] Updated weights for policy 0, policy_version 97616 (0.0012) -[2023-11-28 02:46:06,748][87424] Updated weights for policy 0, policy_version 97626 (0.0011) -[2023-11-28 02:46:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 49938432. Throughput: 0: 2729.9, 1: 2778.4. Samples: 49959760. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 02:46:08,445][86177] Avg episode reward: [(0, '-503.420'), (1, '-514.770')] -[2023-11-28 02:46:08,556][87426] Updated weights for policy 1, policy_version 97450 (0.0012) -[2023-11-28 02:46:08,831][87424] Updated weights for policy 0, policy_version 97636 (0.0011) -[2023-11-28 02:46:08,943][87426] Updated weights for policy 1, policy_version 97460 (0.0010) -[2023-11-28 02:46:09,207][87424] Updated weights for policy 0, policy_version 97646 (0.0011) -[2023-11-28 02:46:09,319][87426] Updated weights for policy 1, policy_version 97470 (0.0007) -[2023-11-28 02:46:09,590][87424] Updated weights for policy 0, policy_version 97656 (0.0012) -[2023-11-28 02:46:11,344][87426] Updated weights for policy 1, policy_version 97480 (0.0009) -[2023-11-28 02:46:11,507][87424] Updated weights for policy 0, policy_version 97666 (0.0011) -[2023-11-28 02:46:11,721][87426] Updated weights for policy 1, policy_version 97490 (0.0011) -[2023-11-28 02:46:11,887][87424] Updated weights for policy 0, policy_version 97676 (0.0012) -[2023-11-28 02:46:12,101][87426] Updated weights for policy 1, policy_version 97500 (0.0011) -[2023-11-28 02:46:12,268][87424] Updated weights for policy 0, policy_version 97686 (0.0012) -[2023-11-28 02:46:12,648][87424] Updated weights for policy 0, policy_version 97696 (0.0012) -[2023-11-28 02:46:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 49971200. Throughput: 0: 2738.6, 1: 2763.4. Samples: 49984884. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:13,445][86177] Avg episode reward: [(0, '-497.590'), (1, '-526.750')] -[2023-11-28 02:46:14,172][87426] Updated weights for policy 1, policy_version 97510 (0.0011) -[2023-11-28 02:46:14,550][87426] Updated weights for policy 1, policy_version 97520 (0.0012) -[2023-11-28 02:46:14,930][87426] Updated weights for policy 1, policy_version 97530 (0.0010) -[2023-11-28 02:46:15,140][87424] Updated weights for policy 0, policy_version 97706 (0.0012) -[2023-11-28 02:46:15,529][87424] Updated weights for policy 0, policy_version 97716 (0.0011) -[2023-11-28 02:46:15,914][87424] Updated weights for policy 0, policy_version 97726 (0.0011) -[2023-11-28 02:46:16,825][87426] Updated weights for policy 1, policy_version 97540 (0.0011) -[2023-11-28 02:46:17,210][87426] Updated weights for policy 1, policy_version 97550 (0.0011) -[2023-11-28 02:46:17,585][87426] Updated weights for policy 1, policy_version 97560 (0.0011) -[2023-11-28 02:46:17,930][87424] Updated weights for policy 0, policy_version 97736 (0.0010) -[2023-11-28 02:46:18,322][87424] Updated weights for policy 0, policy_version 97746 (0.0007) -[2023-11-28 02:46:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 49995776. Throughput: 0: 2739.0, 1: 2767.6. Samples: 50009556. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:18,445][86177] Avg episode reward: [(0, '-498.130'), (1, '-528.240')] -[2023-11-28 02:46:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000097568_24977408.pth... -[2023-11-28 02:46:18,486][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000095040_24330240.pth -[2023-11-28 02:46:18,707][87424] Updated weights for policy 0, policy_version 97756 (0.0007) -[2023-11-28 02:46:18,861][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000097760_25026560.pth... -[2023-11-28 02:46:18,910][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000095200_24371200.pth -[2023-11-28 02:46:19,934][87426] Updated weights for policy 1, policy_version 97570 (0.0012) -[2023-11-28 02:46:20,317][87426] Updated weights for policy 1, policy_version 97580 (0.0012) -[2023-11-28 02:46:20,693][87426] Updated weights for policy 1, policy_version 97590 (0.0011) -[2023-11-28 02:46:20,792][87424] Updated weights for policy 0, policy_version 97766 (0.0008) -[2023-11-28 02:46:21,071][87426] Updated weights for policy 1, policy_version 97600 (0.0010) -[2023-11-28 02:46:21,178][87424] Updated weights for policy 0, policy_version 97776 (0.0011) -[2023-11-28 02:46:21,565][87424] Updated weights for policy 0, policy_version 97786 (0.0015) -[2023-11-28 02:46:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 50020352. Throughput: 0: 2723.5, 1: 2773.6. Samples: 50042532. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:23,445][86177] Avg episode reward: [(0, '-499.500'), (1, '-527.790')] -[2023-11-28 02:46:23,736][87426] Updated weights for policy 1, policy_version 97610 (0.0011) -[2023-11-28 02:46:23,754][87424] Updated weights for policy 0, policy_version 97796 (0.0011) -[2023-11-28 02:46:24,128][87426] Updated weights for policy 1, policy_version 97620 (0.0008) -[2023-11-28 02:46:24,138][87424] Updated weights for policy 0, policy_version 97806 (0.0012) -[2023-11-28 02:46:24,497][87426] Updated weights for policy 1, policy_version 97630 (0.0009) -[2023-11-28 02:46:24,516][87424] Updated weights for policy 0, policy_version 97816 (0.0011) -[2023-11-28 02:46:26,252][87426] Updated weights for policy 1, policy_version 97640 (0.0007) -[2023-11-28 02:46:26,631][87426] Updated weights for policy 1, policy_version 97650 (0.0008) -[2023-11-28 02:46:26,634][87424] Updated weights for policy 0, policy_version 97826 (0.0008) -[2023-11-28 02:46:27,009][87424] Updated weights for policy 0, policy_version 97836 (0.0007) -[2023-11-28 02:46:27,019][87426] Updated weights for policy 1, policy_version 97660 (0.0011) -[2023-11-28 02:46:27,388][87424] Updated weights for policy 0, policy_version 97846 (0.0008) -[2023-11-28 02:46:27,766][87424] Updated weights for policy 0, policy_version 97856 (0.0007) -[2023-11-28 02:46:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 50053120. Throughput: 0: 2732.4, 1: 2762.1. Samples: 50066912. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:28,445][86177] Avg episode reward: [(0, '-498.870'), (1, '-543.530')] -[2023-11-28 02:46:28,588][87426] Updated weights for policy 1, policy_version 97670 (0.0009) -[2023-11-28 02:46:28,967][87426] Updated weights for policy 1, policy_version 97680 (0.0008) -[2023-11-28 02:46:29,356][87426] Updated weights for policy 1, policy_version 97690 (0.0008) -[2023-11-28 02:46:29,711][87424] Updated weights for policy 0, policy_version 97866 (0.0012) -[2023-11-28 02:46:30,093][87424] Updated weights for policy 0, policy_version 97876 (0.0009) -[2023-11-28 02:46:30,478][87424] Updated weights for policy 0, policy_version 97886 (0.0010) -[2023-11-28 02:46:31,805][87426] Updated weights for policy 1, policy_version 97700 (0.0011) -[2023-11-28 02:46:32,182][87426] Updated weights for policy 1, policy_version 97710 (0.0009) -[2023-11-28 02:46:32,434][87424] Updated weights for policy 0, policy_version 97896 (0.0010) -[2023-11-28 02:46:32,564][87426] Updated weights for policy 1, policy_version 97720 (0.0011) -[2023-11-28 02:46:32,814][87424] Updated weights for policy 0, policy_version 97906 (0.0011) -[2023-11-28 02:46:33,203][87424] Updated weights for policy 0, policy_version 97916 (0.0012) -[2023-11-28 02:46:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5470.6). Total num frames: 50085888. Throughput: 0: 2760.4, 1: 2768.6. Samples: 50092444. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:33,445][86177] Avg episode reward: [(0, '-511.120'), (1, '-545.510')] -[2023-11-28 02:46:34,905][87426] Updated weights for policy 1, policy_version 97730 (0.0009) -[2023-11-28 02:46:35,280][87426] Updated weights for policy 1, policy_version 97740 (0.0011) -[2023-11-28 02:46:35,363][87424] Updated weights for policy 0, policy_version 97926 (0.0011) -[2023-11-28 02:46:35,666][87426] Updated weights for policy 1, policy_version 97750 (0.0011) -[2023-11-28 02:46:35,743][87424] Updated weights for policy 0, policy_version 97936 (0.0008) -[2023-11-28 02:46:36,045][87426] Updated weights for policy 1, policy_version 97760 (0.0011) -[2023-11-28 02:46:36,126][87424] Updated weights for policy 0, policy_version 97946 (0.0008) -[2023-11-28 02:46:38,060][87424] Updated weights for policy 0, policy_version 97956 (0.0007) -[2023-11-28 02:46:38,125][87426] Updated weights for policy 1, policy_version 97770 (0.0011) -[2023-11-28 02:46:38,444][87424] Updated weights for policy 0, policy_version 97966 (0.0009) -[2023-11-28 02:46:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 50102272. Throughput: 0: 2811.1, 1: 2784.7. Samples: 50126704. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:38,445][86177] Avg episode reward: [(0, '-515.510'), (1, '-543.230')] -[2023-11-28 02:46:38,491][87426] Updated weights for policy 1, policy_version 97780 (0.0011) -[2023-11-28 02:46:38,836][87424] Updated weights for policy 0, policy_version 97976 (0.0011) -[2023-11-28 02:46:38,883][87426] Updated weights for policy 1, policy_version 97790 (0.0011) -[2023-11-28 02:46:40,754][87424] Updated weights for policy 0, policy_version 97986 (0.0012) -[2023-11-28 02:46:41,138][87424] Updated weights for policy 0, policy_version 97996 (0.0011) -[2023-11-28 02:46:41,143][87426] Updated weights for policy 1, policy_version 97800 (0.0009) -[2023-11-28 02:46:41,516][87426] Updated weights for policy 1, policy_version 97810 (0.0007) -[2023-11-28 02:46:41,533][87424] Updated weights for policy 0, policy_version 98006 (0.0012) -[2023-11-28 02:46:41,895][87426] Updated weights for policy 1, policy_version 97820 (0.0010) -[2023-11-28 02:46:41,922][87424] Updated weights for policy 0, policy_version 98016 (0.0011) -[2023-11-28 02:46:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 50135040. Throughput: 0: 2806.2, 1: 2766.3. Samples: 50150184. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:43,445][86177] Avg episode reward: [(0, '-514.830'), (1, '-540.610')] -[2023-11-28 02:46:44,075][87426] Updated weights for policy 1, policy_version 97830 (0.0010) -[2023-11-28 02:46:44,188][87424] Updated weights for policy 0, policy_version 98026 (0.0011) -[2023-11-28 02:46:44,458][87426] Updated weights for policy 1, policy_version 97840 (0.0009) -[2023-11-28 02:46:44,575][87424] Updated weights for policy 0, policy_version 98036 (0.0011) -[2023-11-28 02:46:44,837][87426] Updated weights for policy 1, policy_version 97850 (0.0011) -[2023-11-28 02:46:44,959][87424] Updated weights for policy 0, policy_version 98046 (0.0011) -[2023-11-28 02:46:47,081][87426] Updated weights for policy 1, policy_version 97860 (0.0010) -[2023-11-28 02:46:47,395][87424] Updated weights for policy 0, policy_version 98056 (0.0010) -[2023-11-28 02:46:47,458][87426] Updated weights for policy 1, policy_version 97870 (0.0007) -[2023-11-28 02:46:47,776][87424] Updated weights for policy 0, policy_version 98066 (0.0008) -[2023-11-28 02:46:47,847][87426] Updated weights for policy 1, policy_version 97880 (0.0007) -[2023-11-28 02:46:48,164][87424] Updated weights for policy 0, policy_version 98076 (0.0007) -[2023-11-28 02:46:48,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5734.4, 300 sec: 5470.6). Total num frames: 50167808. Throughput: 0: 2796.9, 1: 2755.9. Samples: 50174328. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:48,445][86177] Avg episode reward: [(0, '-502.360'), (1, '-536.330')] -[2023-11-28 02:46:49,927][87426] Updated weights for policy 1, policy_version 97890 (0.0008) -[2023-11-28 02:46:50,305][87426] Updated weights for policy 1, policy_version 97900 (0.0008) -[2023-11-28 02:46:50,659][87424] Updated weights for policy 0, policy_version 98086 (0.0009) -[2023-11-28 02:46:50,684][87426] Updated weights for policy 1, policy_version 97910 (0.0010) -[2023-11-28 02:46:51,031][87424] Updated weights for policy 0, policy_version 98096 (0.0010) -[2023-11-28 02:46:51,064][87426] Updated weights for policy 1, policy_version 97920 (0.0011) -[2023-11-28 02:46:51,417][87424] Updated weights for policy 0, policy_version 98106 (0.0012) -[2023-11-28 02:46:52,979][87426] Updated weights for policy 1, policy_version 97930 (0.0010) -[2023-11-28 02:46:53,356][87426] Updated weights for policy 1, policy_version 97940 (0.0009) -[2023-11-28 02:46:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 50184192. Throughput: 0: 2753.2, 1: 2734.0. Samples: 50206684. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:53,445][86177] Avg episode reward: [(0, '-502.520'), (1, '-531.870')] -[2023-11-28 02:46:53,456][87424] Updated weights for policy 0, policy_version 98116 (0.0012) -[2023-11-28 02:46:53,731][87426] Updated weights for policy 1, policy_version 97950 (0.0011) -[2023-11-28 02:46:53,839][87424] Updated weights for policy 0, policy_version 98126 (0.0010) -[2023-11-28 02:46:54,224][87424] Updated weights for policy 0, policy_version 98136 (0.0009) -[2023-11-28 02:46:56,241][87426] Updated weights for policy 1, policy_version 97960 (0.0008) -[2023-11-28 02:46:56,622][87426] Updated weights for policy 1, policy_version 97970 (0.0008) -[2023-11-28 02:46:56,689][87424] Updated weights for policy 0, policy_version 98146 (0.0008) -[2023-11-28 02:46:56,999][87426] Updated weights for policy 1, policy_version 97980 (0.0008) -[2023-11-28 02:46:57,080][87424] Updated weights for policy 0, policy_version 98156 (0.0008) -[2023-11-28 02:46:57,459][87424] Updated weights for policy 0, policy_version 98166 (0.0007) -[2023-11-28 02:46:57,836][87424] Updated weights for policy 0, policy_version 98176 (0.0009) -[2023-11-28 02:46:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 50216960. Throughput: 0: 2737.3, 1: 2701.2. Samples: 50229620. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:46:58,445][86177] Avg episode reward: [(0, '-493.940'), (1, '-553.230')] -[2023-11-28 02:46:59,446][87426] Updated weights for policy 1, policy_version 97990 (0.0010) -[2023-11-28 02:46:59,823][87426] Updated weights for policy 1, policy_version 98000 (0.0010) -[2023-11-28 02:47:00,030][87424] Updated weights for policy 0, policy_version 98186 (0.0009) -[2023-11-28 02:47:00,208][87426] Updated weights for policy 1, policy_version 98010 (0.0011) -[2023-11-28 02:47:00,410][87424] Updated weights for policy 0, policy_version 98196 (0.0008) -[2023-11-28 02:47:00,800][87424] Updated weights for policy 0, policy_version 98206 (0.0010) -[2023-11-28 02:47:02,755][87426] Updated weights for policy 1, policy_version 98020 (0.0011) -[2023-11-28 02:47:02,919][87424] Updated weights for policy 0, policy_version 98216 (0.0011) -[2023-11-28 02:47:03,134][87426] Updated weights for policy 1, policy_version 98030 (0.0009) -[2023-11-28 02:47:03,308][87424] Updated weights for policy 0, policy_version 98226 (0.0011) -[2023-11-28 02:47:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 50233344. Throughput: 0: 2718.7, 1: 2695.5. Samples: 50253192. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:47:03,445][86177] Avg episode reward: [(0, '-495.040'), (1, '-554.610')] -[2023-11-28 02:47:03,517][87426] Updated weights for policy 1, policy_version 98040 (0.0008) -[2023-11-28 02:47:03,693][87424] Updated weights for policy 0, policy_version 98236 (0.0011) -[2023-11-28 02:47:05,278][87426] Updated weights for policy 1, policy_version 98050 (0.0010) -[2023-11-28 02:47:05,644][87426] Updated weights for policy 1, policy_version 98060 (0.0007) -[2023-11-28 02:47:05,807][87424] Updated weights for policy 0, policy_version 98246 (0.0012) -[2023-11-28 02:47:06,018][87426] Updated weights for policy 1, policy_version 98070 (0.0007) -[2023-11-28 02:47:06,186][87424] Updated weights for policy 0, policy_version 98256 (0.0012) -[2023-11-28 02:47:06,397][87426] Updated weights for policy 1, policy_version 98080 (0.0008) -[2023-11-28 02:47:06,564][87424] Updated weights for policy 0, policy_version 98266 (0.0008) -[2023-11-28 02:47:08,123][87426] Updated weights for policy 1, policy_version 98090 (0.0012) -[2023-11-28 02:47:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 50266112. Throughput: 0: 2707.5, 1: 2711.8. Samples: 50286400. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:47:08,445][86177] Avg episode reward: [(0, '-498.060'), (1, '-543.650')] -[2023-11-28 02:47:08,497][87426] Updated weights for policy 1, policy_version 98100 (0.0012) -[2023-11-28 02:47:08,876][87426] Updated weights for policy 1, policy_version 98110 (0.0012) -[2023-11-28 02:47:08,937][87424] Updated weights for policy 0, policy_version 98276 (0.0011) -[2023-11-28 02:47:09,316][87424] Updated weights for policy 0, policy_version 98286 (0.0012) -[2023-11-28 02:47:09,694][87424] Updated weights for policy 0, policy_version 98296 (0.0012) -[2023-11-28 02:47:11,039][87426] Updated weights for policy 1, policy_version 98120 (0.0011) -[2023-11-28 02:47:11,418][87426] Updated weights for policy 1, policy_version 98130 (0.0012) -[2023-11-28 02:47:11,795][87426] Updated weights for policy 1, policy_version 98140 (0.0012) -[2023-11-28 02:47:12,330][87424] Updated weights for policy 0, policy_version 98306 (0.0011) -[2023-11-28 02:47:12,701][87424] Updated weights for policy 0, policy_version 98316 (0.0012) -[2023-11-28 02:47:13,089][87424] Updated weights for policy 0, policy_version 98326 (0.0011) -[2023-11-28 02:47:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 50290688. Throughput: 0: 2702.9, 1: 2710.0. Samples: 50310496. Policy #0 lag: (min: 31.0, avg: 33.3, max: 50.0) -[2023-11-28 02:47:13,445][86177] Avg episode reward: [(0, '-497.660'), (1, '-534.300')] -[2023-11-28 02:47:13,473][87424] Updated weights for policy 0, policy_version 98336 (0.0011) -[2023-11-28 02:47:14,058][87426] Updated weights for policy 1, policy_version 98150 (0.0009) -[2023-11-28 02:47:14,428][87426] Updated weights for policy 1, policy_version 98160 (0.0007) -[2023-11-28 02:47:14,815][87426] Updated weights for policy 1, policy_version 98170 (0.0007) -[2023-11-28 02:47:15,953][87424] Updated weights for policy 0, policy_version 98346 (0.0008) -[2023-11-28 02:47:16,335][87424] Updated weights for policy 0, policy_version 98356 (0.0008) -[2023-11-28 02:47:16,718][87424] Updated weights for policy 0, policy_version 98366 (0.0007) -[2023-11-28 02:47:17,125][87426] Updated weights for policy 1, policy_version 98180 (0.0008) -[2023-11-28 02:47:17,503][87426] Updated weights for policy 1, policy_version 98190 (0.0008) -[2023-11-28 02:47:17,890][87426] Updated weights for policy 1, policy_version 98200 (0.0008) -[2023-11-28 02:47:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 50323456. Throughput: 0: 2663.6, 1: 2692.5. Samples: 50333472. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:47:18,446][86177] Avg episode reward: [(0, '-500.870'), (1, '-516.880')] -[2023-11-28 02:47:19,007][87424] Updated weights for policy 0, policy_version 98376 (0.0012) -[2023-11-28 02:47:19,393][87424] Updated weights for policy 0, policy_version 98386 (0.0012) -[2023-11-28 02:47:19,770][87424] Updated weights for policy 0, policy_version 98396 (0.0010) -[2023-11-28 02:47:19,859][87426] Updated weights for policy 1, policy_version 98210 (0.0008) -[2023-11-28 02:47:20,237][87426] Updated weights for policy 1, policy_version 98220 (0.0012) -[2023-11-28 02:47:20,619][87426] Updated weights for policy 1, policy_version 98230 (0.0012) -[2023-11-28 02:47:20,995][87426] Updated weights for policy 1, policy_version 98240 (0.0012) -[2023-11-28 02:47:21,863][87424] Updated weights for policy 0, policy_version 98406 (0.0010) -[2023-11-28 02:47:22,249][87424] Updated weights for policy 0, policy_version 98416 (0.0012) -[2023-11-28 02:47:22,618][87424] Updated weights for policy 0, policy_version 98426 (0.0012) -[2023-11-28 02:47:23,169][87426] Updated weights for policy 1, policy_version 98250 (0.0010) -[2023-11-28 02:47:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 50348032. Throughput: 0: 2622.9, 1: 2686.1. Samples: 50365612. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:47:23,445][86177] Avg episode reward: [(0, '-504.750'), (1, '-520.980')] -[2023-11-28 02:47:23,550][87426] Updated weights for policy 1, policy_version 98260 (0.0008) -[2023-11-28 02:47:23,937][87426] Updated weights for policy 1, policy_version 98270 (0.0011) -[2023-11-28 02:47:24,616][87424] Updated weights for policy 0, policy_version 98436 (0.0012) -[2023-11-28 02:47:24,995][87424] Updated weights for policy 0, policy_version 98446 (0.0012) -[2023-11-28 02:47:25,382][87424] Updated weights for policy 0, policy_version 98456 (0.0012) -[2023-11-28 02:47:26,048][87426] Updated weights for policy 1, policy_version 98280 (0.0009) -[2023-11-28 02:47:26,440][87426] Updated weights for policy 1, policy_version 98290 (0.0011) -[2023-11-28 02:47:26,825][87426] Updated weights for policy 1, policy_version 98300 (0.0011) -[2023-11-28 02:47:27,314][87424] Updated weights for policy 0, policy_version 98466 (0.0012) -[2023-11-28 02:47:27,691][87424] Updated weights for policy 0, policy_version 98476 (0.0012) -[2023-11-28 02:47:28,066][87424] Updated weights for policy 0, policy_version 98486 (0.0012) -[2023-11-28 02:47:28,440][87424] Updated weights for policy 0, policy_version 98496 (0.0012) -[2023-11-28 02:47:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 50380800. Throughput: 0: 2639.7, 1: 2731.2. Samples: 50391876. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:47:28,445][86177] Avg episode reward: [(0, '-506.240'), (1, '-518.950')] -[2023-11-28 02:47:28,997][87426] Updated weights for policy 1, policy_version 98310 (0.0010) -[2023-11-28 02:47:29,377][87426] Updated weights for policy 1, policy_version 98320 (0.0011) -[2023-11-28 02:47:29,752][87426] Updated weights for policy 1, policy_version 98330 (0.0011) -[2023-11-28 02:47:30,932][87424] Updated weights for policy 0, policy_version 98506 (0.0012) -[2023-11-28 02:47:31,312][87424] Updated weights for policy 0, policy_version 98516 (0.0012) -[2023-11-28 02:47:31,693][87424] Updated weights for policy 0, policy_version 98526 (0.0012) -[2023-11-28 02:47:31,922][87426] Updated weights for policy 1, policy_version 98340 (0.0012) -[2023-11-28 02:47:32,313][87426] Updated weights for policy 1, policy_version 98350 (0.0017) -[2023-11-28 02:47:32,686][87426] Updated weights for policy 1, policy_version 98360 (0.0009) -[2023-11-28 02:47:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 50405376. Throughput: 0: 2631.6, 1: 2745.0. Samples: 50416272. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:47:33,445][86177] Avg episode reward: [(0, '-505.530'), (1, '-524.790')] -[2023-11-28 02:47:33,681][87424] Updated weights for policy 0, policy_version 98536 (0.0012) -[2023-11-28 02:47:34,064][87424] Updated weights for policy 0, policy_version 98546 (0.0012) -[2023-11-28 02:47:34,448][87424] Updated weights for policy 0, policy_version 98556 (0.0012) -[2023-11-28 02:47:34,696][87426] Updated weights for policy 1, policy_version 98370 (0.0009) -[2023-11-28 02:47:35,076][87426] Updated weights for policy 1, policy_version 98380 (0.0008) -[2023-11-28 02:47:35,457][87426] Updated weights for policy 1, policy_version 98390 (0.0011) -[2023-11-28 02:47:35,839][87426] Updated weights for policy 1, policy_version 98400 (0.0012) -[2023-11-28 02:47:36,348][87424] Updated weights for policy 0, policy_version 98566 (0.0010) -[2023-11-28 02:47:36,727][87424] Updated weights for policy 0, policy_version 98576 (0.0008) -[2023-11-28 02:47:37,121][87424] Updated weights for policy 0, policy_version 98586 (0.0008) -[2023-11-28 02:47:37,484][87426] Updated weights for policy 1, policy_version 98410 (0.0012) -[2023-11-28 02:47:37,866][87426] Updated weights for policy 1, policy_version 98420 (0.0010) -[2023-11-28 02:47:38,241][87426] Updated weights for policy 1, policy_version 98430 (0.0007) -[2023-11-28 02:47:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 50438144. Throughput: 0: 2654.8, 1: 2762.8. Samples: 50450480. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:47:38,445][86177] Avg episode reward: [(0, '-500.850'), (1, '-526.640')] -[2023-11-28 02:47:39,510][87424] Updated weights for policy 0, policy_version 98596 (0.0009) -[2023-11-28 02:47:39,903][87424] Updated weights for policy 0, policy_version 98606 (0.0011) -[2023-11-28 02:47:40,283][87424] Updated weights for policy 0, policy_version 98616 (0.0008) -[2023-11-28 02:47:40,640][87426] Updated weights for policy 1, policy_version 98440 (0.0010) -[2023-11-28 02:47:41,026][87426] Updated weights for policy 1, policy_version 98450 (0.0008) -[2023-11-28 02:47:41,404][87426] Updated weights for policy 1, policy_version 98460 (0.0009) -[2023-11-28 02:47:42,451][87424] Updated weights for policy 0, policy_version 98626 (0.0010) -[2023-11-28 02:47:42,837][87424] Updated weights for policy 0, policy_version 98636 (0.0012) -[2023-11-28 02:47:43,218][87424] Updated weights for policy 0, policy_version 98646 (0.0012) -[2023-11-28 02:47:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 50454528. Throughput: 0: 2657.7, 1: 2757.7. Samples: 50473312. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:47:43,445][86177] Avg episode reward: [(0, '-496.890'), (1, '-539.640')] -[2023-11-28 02:47:43,597][87424] Updated weights for policy 0, policy_version 98656 (0.0010) -[2023-11-28 02:47:44,030][87426] Updated weights for policy 1, policy_version 98470 (0.0012) -[2023-11-28 02:47:44,401][87426] Updated weights for policy 1, policy_version 98480 (0.0012) -[2023-11-28 02:47:44,784][87426] Updated weights for policy 1, policy_version 98490 (0.0012) -[2023-11-28 02:47:45,421][87424] Updated weights for policy 0, policy_version 98666 (0.0010) -[2023-11-28 02:47:45,797][87424] Updated weights for policy 0, policy_version 98676 (0.0011) -[2023-11-28 02:47:46,187][87424] Updated weights for policy 0, policy_version 98686 (0.0010) -[2023-11-28 02:47:47,306][87426] Updated weights for policy 1, policy_version 98500 (0.0010) -[2023-11-28 02:47:47,676][87426] Updated weights for policy 1, policy_version 98510 (0.0007) -[2023-11-28 02:47:48,046][87424] Updated weights for policy 0, policy_version 98696 (0.0008) -[2023-11-28 02:47:48,057][87426] Updated weights for policy 1, policy_version 98520 (0.0008) -[2023-11-28 02:47:48,433][87424] Updated weights for policy 0, policy_version 98706 (0.0007) -[2023-11-28 02:47:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 50487296. Throughput: 0: 2699.9, 1: 2740.2. Samples: 50497996. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:47:48,446][86177] Avg episode reward: [(0, '-497.490'), (1, '-548.270')] -[2023-11-28 02:47:48,816][87424] Updated weights for policy 0, policy_version 98716 (0.0008) -[2023-11-28 02:47:49,882][87426] Updated weights for policy 1, policy_version 98530 (0.0011) -[2023-11-28 02:47:50,258][87426] Updated weights for policy 1, policy_version 98540 (0.0007) -[2023-11-28 02:47:50,646][87426] Updated weights for policy 1, policy_version 98550 (0.0009) -[2023-11-28 02:47:51,019][87426] Updated weights for policy 1, policy_version 98560 (0.0010) -[2023-11-28 02:47:51,155][87424] Updated weights for policy 0, policy_version 98726 (0.0009) -[2023-11-28 02:47:51,541][87424] Updated weights for policy 0, policy_version 98736 (0.0011) -[2023-11-28 02:47:51,930][87424] Updated weights for policy 0, policy_version 98746 (0.0011) -[2023-11-28 02:47:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 50511872. Throughput: 0: 2702.7, 1: 2701.2. Samples: 50529576. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:47:53,445][86177] Avg episode reward: [(0, '-498.010'), (1, '-541.070')] -[2023-11-28 02:47:53,521][87426] Updated weights for policy 1, policy_version 98570 (0.0011) -[2023-11-28 02:47:53,895][87426] Updated weights for policy 1, policy_version 98580 (0.0010) -[2023-11-28 02:47:54,277][87426] Updated weights for policy 1, policy_version 98590 (0.0007) -[2023-11-28 02:47:54,339][87424] Updated weights for policy 0, policy_version 98756 (0.0011) -[2023-11-28 02:47:54,720][87424] Updated weights for policy 0, policy_version 98766 (0.0012) -[2023-11-28 02:47:55,099][87424] Updated weights for policy 0, policy_version 98776 (0.0012) -[2023-11-28 02:47:56,604][87426] Updated weights for policy 1, policy_version 98600 (0.0008) -[2023-11-28 02:47:56,984][87426] Updated weights for policy 1, policy_version 98610 (0.0007) -[2023-11-28 02:47:57,363][87426] Updated weights for policy 1, policy_version 98620 (0.0007) -[2023-11-28 02:47:57,681][87424] Updated weights for policy 0, policy_version 98786 (0.0012) -[2023-11-28 02:47:58,062][87424] Updated weights for policy 0, policy_version 98796 (0.0007) -[2023-11-28 02:47:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 50536448. Throughput: 0: 2698.9, 1: 2695.7. Samples: 50553256. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:47:58,445][86177] Avg episode reward: [(0, '-499.850'), (1, '-535.730')] -[2023-11-28 02:47:58,457][87424] Updated weights for policy 0, policy_version 98806 (0.0011) -[2023-11-28 02:47:58,840][87424] Updated weights for policy 0, policy_version 98816 (0.0012) -[2023-11-28 02:47:59,818][87426] Updated weights for policy 1, policy_version 98630 (0.0010) -[2023-11-28 02:48:00,198][87426] Updated weights for policy 1, policy_version 98640 (0.0012) -[2023-11-28 02:48:00,590][87426] Updated weights for policy 1, policy_version 98650 (0.0009) -[2023-11-28 02:48:00,692][87424] Updated weights for policy 0, policy_version 98826 (0.0015) -[2023-11-28 02:48:01,074][87424] Updated weights for policy 0, policy_version 98836 (0.0008) -[2023-11-28 02:48:01,462][87424] Updated weights for policy 0, policy_version 98846 (0.0007) -[2023-11-28 02:48:02,669][87426] Updated weights for policy 1, policy_version 98660 (0.0009) -[2023-11-28 02:48:03,051][87426] Updated weights for policy 1, policy_version 98670 (0.0008) -[2023-11-28 02:48:03,429][87426] Updated weights for policy 1, policy_version 98680 (0.0008) -[2023-11-28 02:48:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 50561024. Throughput: 0: 2736.6, 1: 2700.4. Samples: 50578132. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:48:03,445][86177] Avg episode reward: [(0, '-497.220'), (1, '-530.770')] -[2023-11-28 02:48:03,508][87424] Updated weights for policy 0, policy_version 98856 (0.0009) -[2023-11-28 02:48:03,887][87424] Updated weights for policy 0, policy_version 98866 (0.0007) -[2023-11-28 02:48:04,268][87424] Updated weights for policy 0, policy_version 98876 (0.0007) -[2023-11-28 02:48:05,890][87426] Updated weights for policy 1, policy_version 98690 (0.0007) -[2023-11-28 02:48:06,264][87426] Updated weights for policy 1, policy_version 98700 (0.0007) -[2023-11-28 02:48:06,394][87424] Updated weights for policy 0, policy_version 98886 (0.0008) -[2023-11-28 02:48:06,649][87426] Updated weights for policy 1, policy_version 98710 (0.0008) -[2023-11-28 02:48:06,768][87424] Updated weights for policy 0, policy_version 98896 (0.0009) -[2023-11-28 02:48:07,027][87426] Updated weights for policy 1, policy_version 98720 (0.0012) -[2023-11-28 02:48:07,151][87424] Updated weights for policy 0, policy_version 98906 (0.0011) -[2023-11-28 02:48:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 50593792. Throughput: 0: 2738.7, 1: 2688.9. Samples: 50609852. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:48:08,445][86177] Avg episode reward: [(0, '-496.570'), (1, '-522.820')] -[2023-11-28 02:48:08,839][87424] Updated weights for policy 0, policy_version 98916 (0.0011) -[2023-11-28 02:48:09,191][87426] Updated weights for policy 1, policy_version 98730 (0.0010) -[2023-11-28 02:48:09,220][87424] Updated weights for policy 0, policy_version 98926 (0.0008) -[2023-11-28 02:48:09,575][87426] Updated weights for policy 1, policy_version 98740 (0.0012) -[2023-11-28 02:48:09,607][87424] Updated weights for policy 0, policy_version 98936 (0.0008) -[2023-11-28 02:48:09,954][87426] Updated weights for policy 1, policy_version 98750 (0.0011) -[2023-11-28 02:48:11,854][87424] Updated weights for policy 0, policy_version 98946 (0.0010) -[2023-11-28 02:48:12,241][87424] Updated weights for policy 0, policy_version 98956 (0.0010) -[2023-11-28 02:48:12,475][87426] Updated weights for policy 1, policy_version 98760 (0.0011) -[2023-11-28 02:48:12,623][87424] Updated weights for policy 0, policy_version 98966 (0.0009) -[2023-11-28 02:48:12,850][87426] Updated weights for policy 1, policy_version 98770 (0.0011) -[2023-11-28 02:48:13,012][87424] Updated weights for policy 0, policy_version 98976 (0.0010) -[2023-11-28 02:48:13,261][87426] Updated weights for policy 1, policy_version 98780 (0.0012) -[2023-11-28 02:48:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 50626560. Throughput: 0: 2722.4, 1: 2635.1. Samples: 50632964. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 02:48:13,445][86177] Avg episode reward: [(0, '-495.780'), (1, '-524.180')] -[2023-11-28 02:48:15,139][87426] Updated weights for policy 1, policy_version 98790 (0.0011) -[2023-11-28 02:48:15,454][87424] Updated weights for policy 0, policy_version 98986 (0.0009) -[2023-11-28 02:48:15,514][87426] Updated weights for policy 1, policy_version 98800 (0.0011) -[2023-11-28 02:48:15,834][87424] Updated weights for policy 0, policy_version 98996 (0.0008) -[2023-11-28 02:48:15,898][87426] Updated weights for policy 1, policy_version 98810 (0.0012) -[2023-11-28 02:48:16,223][87424] Updated weights for policy 0, policy_version 99006 (0.0010) -[2023-11-28 02:48:17,566][87426] Updated weights for policy 1, policy_version 98820 (0.0010) -[2023-11-28 02:48:17,941][87426] Updated weights for policy 1, policy_version 98830 (0.0010) -[2023-11-28 02:48:18,318][87426] Updated weights for policy 1, policy_version 98840 (0.0008) -[2023-11-28 02:48:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 50642944. Throughput: 0: 2738.8, 1: 2634.7. Samples: 50658080. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:48:18,445][86177] Avg episode reward: [(0, '-501.500'), (1, '-527.870')] -[2023-11-28 02:48:18,559][87424] Updated weights for policy 0, policy_version 99016 (0.0011) -[2023-11-28 02:48:18,623][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000098848_25305088.pth... -[2023-11-28 02:48:18,669][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000096288_24649728.pth -[2023-11-28 02:48:18,937][87424] Updated weights for policy 0, policy_version 99026 (0.0011) -[2023-11-28 02:48:19,329][87424] Updated weights for policy 0, policy_version 99036 (0.0008) -[2023-11-28 02:48:19,470][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000099040_25354240.pth... -[2023-11-28 02:48:19,517][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000096480_24698880.pth -[2023-11-28 02:48:20,581][87426] Updated weights for policy 1, policy_version 98850 (0.0009) -[2023-11-28 02:48:20,955][87426] Updated weights for policy 1, policy_version 98860 (0.0008) -[2023-11-28 02:48:21,330][87426] Updated weights for policy 1, policy_version 98870 (0.0008) -[2023-11-28 02:48:21,709][87426] Updated weights for policy 1, policy_version 98880 (0.0010) -[2023-11-28 02:48:21,815][87424] Updated weights for policy 0, policy_version 99046 (0.0008) -[2023-11-28 02:48:22,192][87424] Updated weights for policy 0, policy_version 99056 (0.0009) -[2023-11-28 02:48:22,575][87424] Updated weights for policy 0, policy_version 99066 (0.0008) -[2023-11-28 02:48:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 50675712. Throughput: 0: 2717.9, 1: 2625.8. Samples: 50690944. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:48:23,445][86177] Avg episode reward: [(0, '-499.160'), (1, '-515.020')] -[2023-11-28 02:48:23,849][87426] Updated weights for policy 1, policy_version 98890 (0.0012) -[2023-11-28 02:48:24,221][87426] Updated weights for policy 1, policy_version 98900 (0.0012) -[2023-11-28 02:48:24,601][87426] Updated weights for policy 1, policy_version 98910 (0.0009) -[2023-11-28 02:48:24,630][87424] Updated weights for policy 0, policy_version 99076 (0.0010) -[2023-11-28 02:48:25,012][87424] Updated weights for policy 0, policy_version 99086 (0.0012) -[2023-11-28 02:48:25,394][87424] Updated weights for policy 0, policy_version 99096 (0.0008) -[2023-11-28 02:48:27,077][87426] Updated weights for policy 1, policy_version 98920 (0.0011) -[2023-11-28 02:48:27,456][87426] Updated weights for policy 1, policy_version 98930 (0.0012) -[2023-11-28 02:48:27,489][87424] Updated weights for policy 0, policy_version 99106 (0.0009) -[2023-11-28 02:48:27,826][87426] Updated weights for policy 1, policy_version 98940 (0.0012) -[2023-11-28 02:48:27,870][87424] Updated weights for policy 0, policy_version 99116 (0.0011) -[2023-11-28 02:48:28,245][87424] Updated weights for policy 0, policy_version 99126 (0.0007) -[2023-11-28 02:48:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 50700288. Throughput: 0: 2722.6, 1: 2654.8. Samples: 50715292. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:48:28,445][86177] Avg episode reward: [(0, '-499.570'), (1, '-532.510')] -[2023-11-28 02:48:28,626][87424] Updated weights for policy 0, policy_version 99136 (0.0008) -[2023-11-28 02:48:29,954][87426] Updated weights for policy 1, policy_version 98950 (0.0008) -[2023-11-28 02:48:30,336][87426] Updated weights for policy 1, policy_version 98960 (0.0007) -[2023-11-28 02:48:30,717][87426] Updated weights for policy 1, policy_version 98970 (0.0009) -[2023-11-28 02:48:30,979][87424] Updated weights for policy 0, policy_version 99146 (0.0010) -[2023-11-28 02:48:31,364][87424] Updated weights for policy 0, policy_version 99156 (0.0012) -[2023-11-28 02:48:31,742][87424] Updated weights for policy 0, policy_version 99166 (0.0012) -[2023-11-28 02:48:33,120][87426] Updated weights for policy 1, policy_version 98980 (0.0009) -[2023-11-28 02:48:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 50724864. Throughput: 0: 2699.4, 1: 2674.3. Samples: 50739812. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:48:33,445][86177] Avg episode reward: [(0, '-502.660'), (1, '-542.040')] -[2023-11-28 02:48:33,498][87426] Updated weights for policy 1, policy_version 98990 (0.0007) -[2023-11-28 02:48:33,874][87426] Updated weights for policy 1, policy_version 99000 (0.0008) -[2023-11-28 02:48:33,990][87424] Updated weights for policy 0, policy_version 99176 (0.0011) -[2023-11-28 02:48:34,376][87424] Updated weights for policy 0, policy_version 99186 (0.0008) -[2023-11-28 02:48:34,754][87424] Updated weights for policy 0, policy_version 99196 (0.0009) -[2023-11-28 02:48:35,824][87426] Updated weights for policy 1, policy_version 99010 (0.0008) -[2023-11-28 02:48:36,205][87426] Updated weights for policy 1, policy_version 99020 (0.0012) -[2023-11-28 02:48:36,582][87426] Updated weights for policy 1, policy_version 99030 (0.0011) -[2023-11-28 02:48:36,962][87426] Updated weights for policy 1, policy_version 99040 (0.0011) -[2023-11-28 02:48:37,216][87424] Updated weights for policy 0, policy_version 99206 (0.0010) -[2023-11-28 02:48:37,602][87424] Updated weights for policy 0, policy_version 99216 (0.0011) -[2023-11-28 02:48:37,987][87424] Updated weights for policy 0, policy_version 99226 (0.0007) -[2023-11-28 02:48:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 50757632. Throughput: 0: 2698.9, 1: 2695.8. Samples: 50772340. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:48:38,445][86177] Avg episode reward: [(0, '-498.420'), (1, '-545.150')] -[2023-11-28 02:48:39,020][87426] Updated weights for policy 1, policy_version 99050 (0.0012) -[2023-11-28 02:48:39,393][87426] Updated weights for policy 1, policy_version 99060 (0.0011) -[2023-11-28 02:48:39,776][87426] Updated weights for policy 1, policy_version 99070 (0.0012) -[2023-11-28 02:48:40,417][87424] Updated weights for policy 0, policy_version 99236 (0.0009) -[2023-11-28 02:48:40,810][87424] Updated weights for policy 0, policy_version 99246 (0.0010) -[2023-11-28 02:48:41,195][87424] Updated weights for policy 0, policy_version 99256 (0.0008) -[2023-11-28 02:48:41,954][87426] Updated weights for policy 1, policy_version 99080 (0.0012) -[2023-11-28 02:48:42,327][87426] Updated weights for policy 1, policy_version 99090 (0.0011) -[2023-11-28 02:48:42,709][87426] Updated weights for policy 1, policy_version 99100 (0.0011) -[2023-11-28 02:48:43,301][87424] Updated weights for policy 0, policy_version 99266 (0.0008) -[2023-11-28 02:48:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 50782208. Throughput: 0: 2706.0, 1: 2711.3. Samples: 50797036. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:48:43,445][86177] Avg episode reward: [(0, '-503.360'), (1, '-542.980')] -[2023-11-28 02:48:43,683][87424] Updated weights for policy 0, policy_version 99276 (0.0010) -[2023-11-28 02:48:44,074][87424] Updated weights for policy 0, policy_version 99286 (0.0007) -[2023-11-28 02:48:44,446][87424] Updated weights for policy 0, policy_version 99296 (0.0007) -[2023-11-28 02:48:45,143][87426] Updated weights for policy 1, policy_version 99110 (0.0011) -[2023-11-28 02:48:45,518][87426] Updated weights for policy 1, policy_version 99120 (0.0012) -[2023-11-28 02:48:45,897][87426] Updated weights for policy 1, policy_version 99130 (0.0011) -[2023-11-28 02:48:46,735][87424] Updated weights for policy 0, policy_version 99306 (0.0012) -[2023-11-28 02:48:47,108][87424] Updated weights for policy 0, policy_version 99316 (0.0012) -[2023-11-28 02:48:47,493][87424] Updated weights for policy 0, policy_version 99326 (0.0012) -[2023-11-28 02:48:47,826][87426] Updated weights for policy 1, policy_version 99140 (0.0012) -[2023-11-28 02:48:48,204][87426] Updated weights for policy 1, policy_version 99150 (0.0012) -[2023-11-28 02:48:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 50806784. Throughput: 0: 2678.2, 1: 2716.8. Samples: 50820908. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:48:48,446][86177] Avg episode reward: [(0, '-503.450'), (1, '-577.270')] -[2023-11-28 02:48:48,576][87426] Updated weights for policy 1, policy_version 99160 (0.0011) -[2023-11-28 02:48:49,441][87424] Updated weights for policy 0, policy_version 99336 (0.0008) -[2023-11-28 02:48:49,828][87424] Updated weights for policy 0, policy_version 99346 (0.0009) -[2023-11-28 02:48:50,207][87424] Updated weights for policy 0, policy_version 99356 (0.0008) -[2023-11-28 02:48:50,887][87426] Updated weights for policy 1, policy_version 99170 (0.0009) -[2023-11-28 02:48:51,251][87426] Updated weights for policy 1, policy_version 99180 (0.0012) -[2023-11-28 02:48:51,625][87426] Updated weights for policy 1, policy_version 99190 (0.0012) -[2023-11-28 02:48:52,001][87426] Updated weights for policy 1, policy_version 99200 (0.0012) -[2023-11-28 02:48:52,181][87424] Updated weights for policy 0, policy_version 99366 (0.0010) -[2023-11-28 02:48:52,551][87424] Updated weights for policy 0, policy_version 99376 (0.0012) -[2023-11-28 02:48:52,933][87424] Updated weights for policy 0, policy_version 99386 (0.0009) -[2023-11-28 02:48:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 50839552. Throughput: 0: 2681.2, 1: 2719.8. Samples: 50852900. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:48:53,445][86177] Avg episode reward: [(0, '-500.110'), (1, '-602.980')] -[2023-11-28 02:48:54,246][87426] Updated weights for policy 1, policy_version 99210 (0.0007) -[2023-11-28 02:48:54,623][87426] Updated weights for policy 1, policy_version 99220 (0.0007) -[2023-11-28 02:48:55,008][87426] Updated weights for policy 1, policy_version 99230 (0.0007) -[2023-11-28 02:48:55,341][87424] Updated weights for policy 0, policy_version 99396 (0.0010) -[2023-11-28 02:48:55,736][87424] Updated weights for policy 0, policy_version 99406 (0.0007) -[2023-11-28 02:48:56,114][87424] Updated weights for policy 0, policy_version 99416 (0.0007) -[2023-11-28 02:48:57,417][87426] Updated weights for policy 1, policy_version 99240 (0.0008) -[2023-11-28 02:48:57,799][87426] Updated weights for policy 1, policy_version 99250 (0.0011) -[2023-11-28 02:48:58,183][87426] Updated weights for policy 1, policy_version 99260 (0.0011) -[2023-11-28 02:48:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 50864128. Throughput: 0: 2667.4, 1: 2731.7. Samples: 50875924. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:48:58,445][86177] Avg episode reward: [(0, '-492.340'), (1, '-595.140')] -[2023-11-28 02:48:58,626][87424] Updated weights for policy 0, policy_version 99426 (0.0007) -[2023-11-28 02:48:59,009][87424] Updated weights for policy 0, policy_version 99436 (0.0009) -[2023-11-28 02:48:59,403][87424] Updated weights for policy 0, policy_version 99446 (0.0010) -[2023-11-28 02:48:59,781][87424] Updated weights for policy 0, policy_version 99456 (0.0010) -[2023-11-28 02:49:00,675][87426] Updated weights for policy 1, policy_version 99270 (0.0011) -[2023-11-28 02:49:01,057][87426] Updated weights for policy 1, policy_version 99280 (0.0011) -[2023-11-28 02:49:01,431][87426] Updated weights for policy 1, policy_version 99290 (0.0011) -[2023-11-28 02:49:02,197][87424] Updated weights for policy 0, policy_version 99466 (0.0008) -[2023-11-28 02:49:02,581][87424] Updated weights for policy 0, policy_version 99476 (0.0009) -[2023-11-28 02:49:02,972][87424] Updated weights for policy 0, policy_version 99486 (0.0010) -[2023-11-28 02:49:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 50888704. Throughput: 0: 2650.4, 1: 2699.8. Samples: 50898840. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:49:03,445][86177] Avg episode reward: [(0, '-493.810'), (1, '-595.170')] -[2023-11-28 02:49:03,919][87426] Updated weights for policy 1, policy_version 99300 (0.0011) -[2023-11-28 02:49:04,295][87426] Updated weights for policy 1, policy_version 99310 (0.0011) -[2023-11-28 02:49:04,678][87426] Updated weights for policy 1, policy_version 99320 (0.0012) -[2023-11-28 02:49:04,843][87424] Updated weights for policy 0, policy_version 99496 (0.0010) -[2023-11-28 02:49:05,221][87424] Updated weights for policy 0, policy_version 99506 (0.0011) -[2023-11-28 02:49:05,598][87424] Updated weights for policy 0, policy_version 99516 (0.0012) -[2023-11-28 02:49:06,441][87426] Updated weights for policy 1, policy_version 99330 (0.0010) -[2023-11-28 02:49:06,820][87426] Updated weights for policy 1, policy_version 99340 (0.0008) -[2023-11-28 02:49:07,202][87426] Updated weights for policy 1, policy_version 99350 (0.0009) -[2023-11-28 02:49:07,578][87426] Updated weights for policy 1, policy_version 99360 (0.0008) -[2023-11-28 02:49:07,853][87424] Updated weights for policy 0, policy_version 99526 (0.0009) -[2023-11-28 02:49:08,240][87424] Updated weights for policy 0, policy_version 99536 (0.0007) -[2023-11-28 02:49:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 50913280. Throughput: 0: 2662.7, 1: 2695.6. Samples: 50932064. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:49:08,445][86177] Avg episode reward: [(0, '-492.930'), (1, '-539.910')] -[2023-11-28 02:49:08,619][87424] Updated weights for policy 0, policy_version 99546 (0.0007) -[2023-11-28 02:49:09,906][87426] Updated weights for policy 1, policy_version 99370 (0.0011) -[2023-11-28 02:49:10,285][87426] Updated weights for policy 1, policy_version 99380 (0.0012) -[2023-11-28 02:49:10,657][87424] Updated weights for policy 0, policy_version 99556 (0.0010) -[2023-11-28 02:49:10,658][87426] Updated weights for policy 1, policy_version 99390 (0.0010) -[2023-11-28 02:49:11,035][87424] Updated weights for policy 0, policy_version 99566 (0.0011) -[2023-11-28 02:49:11,418][87424] Updated weights for policy 0, policy_version 99576 (0.0009) -[2023-11-28 02:49:12,871][87426] Updated weights for policy 1, policy_version 99400 (0.0012) -[2023-11-28 02:49:13,246][87426] Updated weights for policy 1, policy_version 99410 (0.0009) -[2023-11-28 02:49:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 50937856. Throughput: 0: 2658.2, 1: 2689.2. Samples: 50955928. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 02:49:13,445][86177] Avg episode reward: [(0, '-493.880'), (1, '-505.380')] -[2023-11-28 02:49:13,630][87426] Updated weights for policy 1, policy_version 99420 (0.0008) -[2023-11-28 02:49:13,683][87424] Updated weights for policy 0, policy_version 99586 (0.0010) -[2023-11-28 02:49:14,063][87424] Updated weights for policy 0, policy_version 99596 (0.0012) -[2023-11-28 02:49:14,448][87424] Updated weights for policy 0, policy_version 99606 (0.0012) -[2023-11-28 02:49:14,831][87424] Updated weights for policy 0, policy_version 99616 (0.0012) -[2023-11-28 02:49:15,897][87426] Updated weights for policy 1, policy_version 99430 (0.0010) -[2023-11-28 02:49:16,273][87426] Updated weights for policy 1, policy_version 99440 (0.0009) -[2023-11-28 02:49:16,650][87426] Updated weights for policy 1, policy_version 99450 (0.0007) -[2023-11-28 02:49:17,272][87424] Updated weights for policy 0, policy_version 99626 (0.0012) -[2023-11-28 02:49:17,652][87424] Updated weights for policy 0, policy_version 99636 (0.0008) -[2023-11-28 02:49:18,038][87424] Updated weights for policy 0, policy_version 99646 (0.0009) -[2023-11-28 02:49:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 50970624. Throughput: 0: 2668.5, 1: 2681.3. Samples: 50980548. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:49:18,445][86177] Avg episode reward: [(0, '-495.190'), (1, '-509.510')] -[2023-11-28 02:49:18,925][87426] Updated weights for policy 1, policy_version 99460 (0.0009) -[2023-11-28 02:49:19,296][87426] Updated weights for policy 1, policy_version 99470 (0.0012) -[2023-11-28 02:49:19,677][87426] Updated weights for policy 1, policy_version 99480 (0.0011) -[2023-11-28 02:49:20,026][87424] Updated weights for policy 0, policy_version 99656 (0.0011) -[2023-11-28 02:49:20,410][87424] Updated weights for policy 0, policy_version 99666 (0.0012) -[2023-11-28 02:49:20,784][87424] Updated weights for policy 0, policy_version 99676 (0.0011) -[2023-11-28 02:49:21,770][87426] Updated weights for policy 1, policy_version 99490 (0.0011) -[2023-11-28 02:49:22,157][87426] Updated weights for policy 1, policy_version 99500 (0.0012) -[2023-11-28 02:49:22,534][87426] Updated weights for policy 1, policy_version 99510 (0.0012) -[2023-11-28 02:49:22,904][87426] Updated weights for policy 1, policy_version 99520 (0.0011) -[2023-11-28 02:49:23,013][87424] Updated weights for policy 0, policy_version 99686 (0.0011) -[2023-11-28 02:49:23,390][87424] Updated weights for policy 0, policy_version 99696 (0.0011) -[2023-11-28 02:49:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 50995200. Throughput: 0: 2685.2, 1: 2663.5. Samples: 51013028. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:49:23,445][86177] Avg episode reward: [(0, '-495.190'), (1, '-527.680')] -[2023-11-28 02:49:23,769][87424] Updated weights for policy 0, policy_version 99706 (0.0012) -[2023-11-28 02:49:25,540][87426] Updated weights for policy 1, policy_version 99530 (0.0007) -[2023-11-28 02:49:25,614][87424] Updated weights for policy 0, policy_version 99716 (0.0012) -[2023-11-28 02:49:25,923][87426] Updated weights for policy 1, policy_version 99540 (0.0009) -[2023-11-28 02:49:25,993][87424] Updated weights for policy 0, policy_version 99726 (0.0008) -[2023-11-28 02:49:26,296][87426] Updated weights for policy 1, policy_version 99550 (0.0011) -[2023-11-28 02:49:26,378][87424] Updated weights for policy 0, policy_version 99736 (0.0007) -[2023-11-28 02:49:28,066][87424] Updated weights for policy 0, policy_version 99746 (0.0008) -[2023-11-28 02:49:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 51019776. Throughput: 0: 2694.1, 1: 2638.0. Samples: 51036980. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:49:28,445][86177] Avg episode reward: [(0, '-500.520'), (1, '-532.380')] -[2023-11-28 02:49:28,449][87424] Updated weights for policy 0, policy_version 99756 (0.0007) -[2023-11-28 02:49:28,804][87426] Updated weights for policy 1, policy_version 99560 (0.0008) -[2023-11-28 02:49:28,834][87424] Updated weights for policy 0, policy_version 99766 (0.0009) -[2023-11-28 02:49:29,178][87426] Updated weights for policy 1, policy_version 99570 (0.0010) -[2023-11-28 02:49:29,218][87424] Updated weights for policy 0, policy_version 99776 (0.0010) -[2023-11-28 02:49:29,550][87426] Updated weights for policy 1, policy_version 99580 (0.0011) -[2023-11-28 02:49:31,511][87426] Updated weights for policy 1, policy_version 99590 (0.0007) -[2023-11-28 02:49:31,528][87424] Updated weights for policy 0, policy_version 99786 (0.0011) -[2023-11-28 02:49:31,910][87426] Updated weights for policy 1, policy_version 99600 (0.0011) -[2023-11-28 02:49:31,915][87424] Updated weights for policy 0, policy_version 99796 (0.0010) -[2023-11-28 02:49:32,280][87426] Updated weights for policy 1, policy_version 99610 (0.0011) -[2023-11-28 02:49:32,289][87424] Updated weights for policy 0, policy_version 99806 (0.0010) -[2023-11-28 02:49:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 51052544. Throughput: 0: 2724.5, 1: 2631.5. Samples: 51061928. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:49:33,445][86177] Avg episode reward: [(0, '-503.260'), (1, '-533.590')] -[2023-11-28 02:49:34,154][87424] Updated weights for policy 0, policy_version 99816 (0.0009) -[2023-11-28 02:49:34,545][87424] Updated weights for policy 0, policy_version 99826 (0.0007) -[2023-11-28 02:49:34,788][87426] Updated weights for policy 1, policy_version 99620 (0.0009) -[2023-11-28 02:49:34,930][87424] Updated weights for policy 0, policy_version 99836 (0.0010) -[2023-11-28 02:49:35,167][87426] Updated weights for policy 1, policy_version 99630 (0.0010) -[2023-11-28 02:49:35,541][87426] Updated weights for policy 1, policy_version 99640 (0.0012) -[2023-11-28 02:49:36,705][87424] Updated weights for policy 0, policy_version 99846 (0.0011) -[2023-11-28 02:49:37,088][87424] Updated weights for policy 0, policy_version 99856 (0.0012) -[2023-11-28 02:49:37,478][87424] Updated weights for policy 0, policy_version 99866 (0.0012) -[2023-11-28 02:49:37,656][87426] Updated weights for policy 1, policy_version 99650 (0.0012) -[2023-11-28 02:49:38,032][87426] Updated weights for policy 1, policy_version 99660 (0.0012) -[2023-11-28 02:49:38,413][87426] Updated weights for policy 1, policy_version 99670 (0.0012) -[2023-11-28 02:49:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 51077120. Throughput: 0: 2756.2, 1: 2633.6. Samples: 51095440. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:49:38,445][86177] Avg episode reward: [(0, '-506.800'), (1, '-534.120')] -[2023-11-28 02:49:38,788][87426] Updated weights for policy 1, policy_version 99680 (0.0011) -[2023-11-28 02:49:39,190][87424] Updated weights for policy 0, policy_version 99876 (0.0012) -[2023-11-28 02:49:39,569][87424] Updated weights for policy 0, policy_version 99886 (0.0011) -[2023-11-28 02:49:39,951][87424] Updated weights for policy 0, policy_version 99896 (0.0010) -[2023-11-28 02:49:41,156][87426] Updated weights for policy 1, policy_version 99690 (0.0012) -[2023-11-28 02:49:41,532][87426] Updated weights for policy 1, policy_version 99700 (0.0012) -[2023-11-28 02:49:41,910][87426] Updated weights for policy 1, policy_version 99710 (0.0012) -[2023-11-28 02:49:42,111][87424] Updated weights for policy 0, policy_version 99906 (0.0012) -[2023-11-28 02:49:42,490][87424] Updated weights for policy 0, policy_version 99916 (0.0011) -[2023-11-28 02:49:42,879][87424] Updated weights for policy 0, policy_version 99926 (0.0008) -[2023-11-28 02:49:43,256][87424] Updated weights for policy 0, policy_version 99936 (0.0011) -[2023-11-28 02:49:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 51109888. Throughput: 0: 2771.7, 1: 2645.1. Samples: 51119680. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:49:43,445][86177] Avg episode reward: [(0, '-505.450'), (1, '-522.760')] -[2023-11-28 02:49:44,020][87426] Updated weights for policy 1, policy_version 99720 (0.0012) -[2023-11-28 02:49:44,399][87426] Updated weights for policy 1, policy_version 99730 (0.0012) -[2023-11-28 02:49:44,783][87426] Updated weights for policy 1, policy_version 99740 (0.0012) -[2023-11-28 02:49:45,478][87424] Updated weights for policy 0, policy_version 99946 (0.0010) -[2023-11-28 02:49:45,873][87424] Updated weights for policy 0, policy_version 99956 (0.0008) -[2023-11-28 02:49:46,254][87424] Updated weights for policy 0, policy_version 99966 (0.0009) -[2023-11-28 02:49:47,100][87426] Updated weights for policy 1, policy_version 99750 (0.0009) -[2023-11-28 02:49:47,484][87426] Updated weights for policy 1, policy_version 99760 (0.0008) -[2023-11-28 02:49:47,869][87426] Updated weights for policy 1, policy_version 99770 (0.0007) -[2023-11-28 02:49:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 51134464. Throughput: 0: 2810.6, 1: 2660.9. Samples: 51145056. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:49:48,445][86177] Avg episode reward: [(0, '-505.640'), (1, '-521.200')] -[2023-11-28 02:49:48,699][87424] Updated weights for policy 0, policy_version 99976 (0.0008) -[2023-11-28 02:49:49,078][87424] Updated weights for policy 0, policy_version 99986 (0.0008) -[2023-11-28 02:49:49,461][87424] Updated weights for policy 0, policy_version 99996 (0.0007) -[2023-11-28 02:49:50,241][87426] Updated weights for policy 1, policy_version 99780 (0.0009) -[2023-11-28 02:49:50,626][87426] Updated weights for policy 1, policy_version 99790 (0.0012) -[2023-11-28 02:49:50,995][87426] Updated weights for policy 1, policy_version 99800 (0.0012) -[2023-11-28 02:49:51,418][87424] Updated weights for policy 0, policy_version 100006 (0.0010) -[2023-11-28 02:49:51,805][87424] Updated weights for policy 0, policy_version 100016 (0.0012) -[2023-11-28 02:49:52,189][87424] Updated weights for policy 0, policy_version 100026 (0.0012) -[2023-11-28 02:49:53,208][87426] Updated weights for policy 1, policy_version 99810 (0.0012) -[2023-11-28 02:49:53,445][86177] Fps is (10 sec: 4914.8, 60 sec: 5324.7, 300 sec: 5415.0). Total num frames: 51159040. Throughput: 0: 2793.9, 1: 2628.3. Samples: 51176068. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:49:53,446][86177] Avg episode reward: [(0, '-507.630'), (1, '-562.270')] -[2023-11-28 02:49:53,586][87426] Updated weights for policy 1, policy_version 99820 (0.0012) -[2023-11-28 02:49:53,970][87426] Updated weights for policy 1, policy_version 99830 (0.0012) -[2023-11-28 02:49:54,358][87426] Updated weights for policy 1, policy_version 99840 (0.0012) -[2023-11-28 02:49:54,664][87424] Updated weights for policy 0, policy_version 100036 (0.0012) -[2023-11-28 02:49:55,049][87424] Updated weights for policy 0, policy_version 100046 (0.0012) -[2023-11-28 02:49:55,429][87424] Updated weights for policy 0, policy_version 100056 (0.0010) -[2023-11-28 02:49:56,526][87426] Updated weights for policy 1, policy_version 99850 (0.0009) -[2023-11-28 02:49:56,905][87426] Updated weights for policy 1, policy_version 99860 (0.0012) -[2023-11-28 02:49:57,278][87426] Updated weights for policy 1, policy_version 99870 (0.0012) -[2023-11-28 02:49:57,466][87424] Updated weights for policy 0, policy_version 100066 (0.0009) -[2023-11-28 02:49:57,855][87424] Updated weights for policy 0, policy_version 100076 (0.0012) -[2023-11-28 02:49:58,238][87424] Updated weights for policy 0, policy_version 100086 (0.0012) -[2023-11-28 02:49:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 51183616. Throughput: 0: 2799.7, 1: 2639.7. Samples: 51200704. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:49:58,445][86177] Avg episode reward: [(0, '-507.920'), (1, '-555.040')] -[2023-11-28 02:49:58,638][87424] Updated weights for policy 0, policy_version 100096 (0.0012) -[2023-11-28 02:49:59,299][87426] Updated weights for policy 1, policy_version 99880 (0.0011) -[2023-11-28 02:49:59,678][87426] Updated weights for policy 1, policy_version 99890 (0.0012) -[2023-11-28 02:50:00,060][87426] Updated weights for policy 1, policy_version 99900 (0.0011) -[2023-11-28 02:50:00,856][87424] Updated weights for policy 0, policy_version 100106 (0.0007) -[2023-11-28 02:50:01,235][87424] Updated weights for policy 0, policy_version 100116 (0.0008) -[2023-11-28 02:50:01,621][87424] Updated weights for policy 0, policy_version 100126 (0.0008) -[2023-11-28 02:50:02,321][87426] Updated weights for policy 1, policy_version 99910 (0.0011) -[2023-11-28 02:50:02,687][87426] Updated weights for policy 1, policy_version 99920 (0.0009) -[2023-11-28 02:50:03,062][87426] Updated weights for policy 1, policy_version 99930 (0.0009) -[2023-11-28 02:50:03,444][86177] Fps is (10 sec: 5735.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 51216384. Throughput: 0: 2791.4, 1: 2645.2. Samples: 51225192. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:50:03,445][86177] Avg episode reward: [(0, '-506.410'), (1, '-552.400')] -[2023-11-28 02:50:04,177][87424] Updated weights for policy 0, policy_version 100136 (0.0011) -[2023-11-28 02:50:04,558][87424] Updated weights for policy 0, policy_version 100146 (0.0011) -[2023-11-28 02:50:04,956][87424] Updated weights for policy 0, policy_version 100156 (0.0012) -[2023-11-28 02:50:05,063][87426] Updated weights for policy 1, policy_version 99940 (0.0010) -[2023-11-28 02:50:05,437][87426] Updated weights for policy 1, policy_version 99950 (0.0011) -[2023-11-28 02:50:05,816][87426] Updated weights for policy 1, policy_version 99960 (0.0008) -[2023-11-28 02:50:07,446][87424] Updated weights for policy 0, policy_version 100166 (0.0011) -[2023-11-28 02:50:07,838][87424] Updated weights for policy 0, policy_version 100176 (0.0011) -[2023-11-28 02:50:08,206][87424] Updated weights for policy 0, policy_version 100186 (0.0010) -[2023-11-28 02:50:08,271][87426] Updated weights for policy 1, policy_version 99970 (0.0008) -[2023-11-28 02:50:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 51240960. Throughput: 0: 2755.6, 1: 2656.0. Samples: 51256548. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:50:08,445][86177] Avg episode reward: [(0, '-504.670'), (1, '-557.370')] -[2023-11-28 02:50:08,645][87426] Updated weights for policy 1, policy_version 99980 (0.0009) -[2023-11-28 02:50:09,038][87426] Updated weights for policy 1, policy_version 99990 (0.0008) -[2023-11-28 02:50:09,414][87426] Updated weights for policy 1, policy_version 100000 (0.0007) -[2023-11-28 02:50:10,354][87424] Updated weights for policy 0, policy_version 100196 (0.0009) -[2023-11-28 02:50:10,730][87424] Updated weights for policy 0, policy_version 100206 (0.0011) -[2023-11-28 02:50:11,112][87424] Updated weights for policy 0, policy_version 100216 (0.0012) -[2023-11-28 02:50:11,946][87426] Updated weights for policy 1, policy_version 100010 (0.0011) -[2023-11-28 02:50:12,327][87426] Updated weights for policy 1, policy_version 100020 (0.0009) -[2023-11-28 02:50:12,711][87426] Updated weights for policy 1, policy_version 100030 (0.0007) -[2023-11-28 02:50:13,349][87424] Updated weights for policy 0, policy_version 100226 (0.0011) -[2023-11-28 02:50:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 51265536. Throughput: 0: 2747.3, 1: 2653.2. Samples: 51280000. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:50:13,445][86177] Avg episode reward: [(0, '-502.710'), (1, '-516.230')] -[2023-11-28 02:50:13,732][87424] Updated weights for policy 0, policy_version 100236 (0.0008) -[2023-11-28 02:50:14,113][87424] Updated weights for policy 0, policy_version 100246 (0.0008) -[2023-11-28 02:50:14,501][87424] Updated weights for policy 0, policy_version 100256 (0.0008) -[2023-11-28 02:50:14,779][87426] Updated weights for policy 1, policy_version 100040 (0.0011) -[2023-11-28 02:50:15,160][87426] Updated weights for policy 1, policy_version 100050 (0.0011) -[2023-11-28 02:50:15,538][87426] Updated weights for policy 1, policy_version 100060 (0.0009) -[2023-11-28 02:50:16,198][87424] Updated weights for policy 0, policy_version 100266 (0.0011) -[2023-11-28 02:50:16,593][87424] Updated weights for policy 0, policy_version 100276 (0.0012) -[2023-11-28 02:50:16,979][87424] Updated weights for policy 0, policy_version 100286 (0.0009) -[2023-11-28 02:50:17,582][87426] Updated weights for policy 1, policy_version 100070 (0.0007) -[2023-11-28 02:50:17,960][87426] Updated weights for policy 1, policy_version 100080 (0.0007) -[2023-11-28 02:50:18,340][87426] Updated weights for policy 1, policy_version 100090 (0.0007) -[2023-11-28 02:50:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 51290112. Throughput: 0: 2733.6, 1: 2659.5. Samples: 51304616. Policy #0 lag: (min: 23.0, avg: 41.4, max: 63.0) -[2023-11-28 02:50:18,445][86177] Avg episode reward: [(0, '-500.090'), (1, '-531.720')] -[2023-11-28 02:50:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000100288_25673728.pth... -[2023-11-28 02:50:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000097760_25026560.pth -[2023-11-28 02:50:18,565][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000100096_25624576.pth... -[2023-11-28 02:50:18,614][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000097568_24977408.pth -[2023-11-28 02:50:19,502][87424] Updated weights for policy 0, policy_version 100296 (0.0010) -[2023-11-28 02:50:19,884][87424] Updated weights for policy 0, policy_version 100306 (0.0009) -[2023-11-28 02:50:20,185][87426] Updated weights for policy 1, policy_version 100100 (0.0009) -[2023-11-28 02:50:20,264][87424] Updated weights for policy 0, policy_version 100316 (0.0012) -[2023-11-28 02:50:20,564][87426] Updated weights for policy 1, policy_version 100110 (0.0011) -[2023-11-28 02:50:20,949][87426] Updated weights for policy 1, policy_version 100120 (0.0008) -[2023-11-28 02:50:22,838][87424] Updated weights for policy 0, policy_version 100326 (0.0011) -[2023-11-28 02:50:23,221][87424] Updated weights for policy 0, policy_version 100336 (0.0012) -[2023-11-28 02:50:23,411][87426] Updated weights for policy 1, policy_version 100130 (0.0010) -[2023-11-28 02:50:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 51314688. Throughput: 0: 2696.6, 1: 2665.2. Samples: 51336724. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:50:23,445][86177] Avg episode reward: [(0, '-502.060'), (1, '-530.480')] -[2023-11-28 02:50:23,605][87424] Updated weights for policy 0, policy_version 100346 (0.0012) -[2023-11-28 02:50:23,783][87426] Updated weights for policy 1, policy_version 100140 (0.0012) -[2023-11-28 02:50:24,164][87426] Updated weights for policy 1, policy_version 100150 (0.0007) -[2023-11-28 02:50:24,548][87426] Updated weights for policy 1, policy_version 100160 (0.0008) -[2023-11-28 02:50:25,617][87424] Updated weights for policy 0, policy_version 100356 (0.0012) -[2023-11-28 02:50:26,005][87424] Updated weights for policy 0, policy_version 100366 (0.0012) -[2023-11-28 02:50:26,393][87424] Updated weights for policy 0, policy_version 100376 (0.0012) -[2023-11-28 02:50:26,671][87426] Updated weights for policy 1, policy_version 100170 (0.0009) -[2023-11-28 02:50:27,047][87426] Updated weights for policy 1, policy_version 100180 (0.0007) -[2023-11-28 02:50:27,434][87426] Updated weights for policy 1, policy_version 100190 (0.0007) -[2023-11-28 02:50:28,224][87424] Updated weights for policy 0, policy_version 100386 (0.0009) -[2023-11-28 02:50:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 51347456. Throughput: 0: 2691.5, 1: 2668.4. Samples: 51360876. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:50:28,445][86177] Avg episode reward: [(0, '-501.640'), (1, '-519.970')] -[2023-11-28 02:50:28,616][87424] Updated weights for policy 0, policy_version 100396 (0.0012) -[2023-11-28 02:50:29,005][87424] Updated weights for policy 0, policy_version 100406 (0.0008) -[2023-11-28 02:50:29,396][87424] Updated weights for policy 0, policy_version 100416 (0.0007) -[2023-11-28 02:50:29,722][87426] Updated weights for policy 1, policy_version 100200 (0.0008) -[2023-11-28 02:50:30,107][87426] Updated weights for policy 1, policy_version 100210 (0.0008) -[2023-11-28 02:50:30,502][87426] Updated weights for policy 1, policy_version 100220 (0.0008) -[2023-11-28 02:50:31,489][87424] Updated weights for policy 0, policy_version 100426 (0.0012) -[2023-11-28 02:50:31,867][87424] Updated weights for policy 0, policy_version 100436 (0.0012) -[2023-11-28 02:50:32,246][87424] Updated weights for policy 0, policy_version 100446 (0.0012) -[2023-11-28 02:50:32,733][87426] Updated weights for policy 1, policy_version 100230 (0.0010) -[2023-11-28 02:50:33,107][87426] Updated weights for policy 1, policy_version 100240 (0.0011) -[2023-11-28 02:50:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 51372032. Throughput: 0: 2656.3, 1: 2666.5. Samples: 51384584. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:50:33,446][86177] Avg episode reward: [(0, '-499.880'), (1, '-518.870')] -[2023-11-28 02:50:33,493][87426] Updated weights for policy 1, policy_version 100250 (0.0011) -[2023-11-28 02:50:34,809][87424] Updated weights for policy 0, policy_version 100456 (0.0012) -[2023-11-28 02:50:35,190][87424] Updated weights for policy 0, policy_version 100466 (0.0012) -[2023-11-28 02:50:35,566][87424] Updated weights for policy 0, policy_version 100476 (0.0009) -[2023-11-28 02:50:35,724][87426] Updated weights for policy 1, policy_version 100260 (0.0011) -[2023-11-28 02:50:36,106][87426] Updated weights for policy 1, policy_version 100270 (0.0007) -[2023-11-28 02:50:36,492][87426] Updated weights for policy 1, policy_version 100280 (0.0007) -[2023-11-28 02:50:37,656][87424] Updated weights for policy 0, policy_version 100486 (0.0010) -[2023-11-28 02:50:38,041][87424] Updated weights for policy 0, policy_version 100496 (0.0012) -[2023-11-28 02:50:38,419][87424] Updated weights for policy 0, policy_version 100506 (0.0012) -[2023-11-28 02:50:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 51396608. Throughput: 0: 2669.8, 1: 2686.1. Samples: 51417080. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:50:38,445][86177] Avg episode reward: [(0, '-496.790'), (1, '-517.630')] -[2023-11-28 02:50:39,016][87426] Updated weights for policy 1, policy_version 100290 (0.0010) -[2023-11-28 02:50:39,389][87426] Updated weights for policy 1, policy_version 100300 (0.0010) -[2023-11-28 02:50:39,769][87426] Updated weights for policy 1, policy_version 100310 (0.0011) -[2023-11-28 02:50:40,153][87426] Updated weights for policy 1, policy_version 100320 (0.0010) -[2023-11-28 02:50:40,509][87424] Updated weights for policy 0, policy_version 100516 (0.0011) -[2023-11-28 02:50:40,893][87424] Updated weights for policy 0, policy_version 100526 (0.0011) -[2023-11-28 02:50:41,274][87424] Updated weights for policy 0, policy_version 100536 (0.0011) -[2023-11-28 02:50:42,314][87426] Updated weights for policy 1, policy_version 100330 (0.0012) -[2023-11-28 02:50:42,692][87426] Updated weights for policy 1, policy_version 100340 (0.0011) -[2023-11-28 02:50:43,074][87426] Updated weights for policy 1, policy_version 100350 (0.0010) -[2023-11-28 02:50:43,410][87424] Updated weights for policy 0, policy_version 100546 (0.0011) -[2023-11-28 02:50:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 51429376. Throughput: 0: 2679.8, 1: 2655.7. Samples: 51440804. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:50:43,445][86177] Avg episode reward: [(0, '-497.330'), (1, '-521.990')] -[2023-11-28 02:50:43,793][87424] Updated weights for policy 0, policy_version 100556 (0.0007) -[2023-11-28 02:50:44,175][87424] Updated weights for policy 0, policy_version 100566 (0.0007) -[2023-11-28 02:50:44,554][87424] Updated weights for policy 0, policy_version 100576 (0.0007) -[2023-11-28 02:50:45,687][87426] Updated weights for policy 1, policy_version 100360 (0.0011) -[2023-11-28 02:50:46,054][87426] Updated weights for policy 1, policy_version 100370 (0.0012) -[2023-11-28 02:50:46,436][87426] Updated weights for policy 1, policy_version 100380 (0.0011) -[2023-11-28 02:50:46,937][87424] Updated weights for policy 0, policy_version 100586 (0.0012) -[2023-11-28 02:50:47,318][87424] Updated weights for policy 0, policy_version 100596 (0.0012) -[2023-11-28 02:50:47,700][87424] Updated weights for policy 0, policy_version 100606 (0.0012) -[2023-11-28 02:50:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 51453952. Throughput: 0: 2678.8, 1: 2656.1. Samples: 51465260. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:50:48,445][86177] Avg episode reward: [(0, '-495.330'), (1, '-518.850')] -[2023-11-28 02:50:48,794][87426] Updated weights for policy 1, policy_version 100390 (0.0012) -[2023-11-28 02:50:49,178][87426] Updated weights for policy 1, policy_version 100400 (0.0011) -[2023-11-28 02:50:49,555][87426] Updated weights for policy 1, policy_version 100410 (0.0012) -[2023-11-28 02:50:49,654][87424] Updated weights for policy 0, policy_version 100616 (0.0008) -[2023-11-28 02:50:50,039][87424] Updated weights for policy 0, policy_version 100626 (0.0010) -[2023-11-28 02:50:50,424][87424] Updated weights for policy 0, policy_version 100636 (0.0012) -[2023-11-28 02:50:51,636][87426] Updated weights for policy 1, policy_version 100420 (0.0012) -[2023-11-28 02:50:52,014][87426] Updated weights for policy 1, policy_version 100430 (0.0012) -[2023-11-28 02:50:52,387][87426] Updated weights for policy 1, policy_version 100440 (0.0010) -[2023-11-28 02:50:52,495][87424] Updated weights for policy 0, policy_version 100646 (0.0009) -[2023-11-28 02:50:52,878][87424] Updated weights for policy 0, policy_version 100656 (0.0008) -[2023-11-28 02:50:53,262][87424] Updated weights for policy 0, policy_version 100666 (0.0009) -[2023-11-28 02:50:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.9, 300 sec: 5387.3). Total num frames: 51478528. Throughput: 0: 2700.7, 1: 2677.7. Samples: 51498576. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:50:53,445][86177] Avg episode reward: [(0, '-498.980'), (1, '-556.380')] -[2023-11-28 02:50:54,450][87426] Updated weights for policy 1, policy_version 100450 (0.0011) -[2023-11-28 02:50:54,833][87426] Updated weights for policy 1, policy_version 100460 (0.0009) -[2023-11-28 02:50:55,202][87426] Updated weights for policy 1, policy_version 100470 (0.0009) -[2023-11-28 02:50:55,505][87424] Updated weights for policy 0, policy_version 100676 (0.0011) -[2023-11-28 02:50:55,576][87426] Updated weights for policy 1, policy_version 100480 (0.0011) -[2023-11-28 02:50:55,884][87424] Updated weights for policy 0, policy_version 100686 (0.0012) -[2023-11-28 02:50:56,263][87424] Updated weights for policy 0, policy_version 100696 (0.0012) -[2023-11-28 02:50:57,508][87426] Updated weights for policy 1, policy_version 100490 (0.0012) -[2023-11-28 02:50:57,888][87426] Updated weights for policy 1, policy_version 100500 (0.0012) -[2023-11-28 02:50:58,272][87426] Updated weights for policy 1, policy_version 100510 (0.0011) -[2023-11-28 02:50:58,279][87424] Updated weights for policy 0, policy_version 100706 (0.0011) -[2023-11-28 02:50:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 51511296. Throughput: 0: 2698.2, 1: 2703.1. Samples: 51523060. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:50:58,445][86177] Avg episode reward: [(0, '-501.750'), (1, '-535.670')] -[2023-11-28 02:50:58,654][87424] Updated weights for policy 0, policy_version 100716 (0.0008) -[2023-11-28 02:50:59,043][87424] Updated weights for policy 0, policy_version 100726 (0.0008) -[2023-11-28 02:50:59,423][87424] Updated weights for policy 0, policy_version 100736 (0.0010) -[2023-11-28 02:51:00,648][87426] Updated weights for policy 1, policy_version 100520 (0.0011) -[2023-11-28 02:51:01,036][87426] Updated weights for policy 1, policy_version 100530 (0.0011) -[2023-11-28 02:51:01,285][87424] Updated weights for policy 0, policy_version 100746 (0.0010) -[2023-11-28 02:51:01,416][87426] Updated weights for policy 1, policy_version 100540 (0.0011) -[2023-11-28 02:51:01,659][87424] Updated weights for policy 0, policy_version 100756 (0.0010) -[2023-11-28 02:51:02,039][87424] Updated weights for policy 0, policy_version 100766 (0.0011) -[2023-11-28 02:51:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 51535872. Throughput: 0: 2709.6, 1: 2695.1. Samples: 51547828. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:51:03,445][86177] Avg episode reward: [(0, '-503.650'), (1, '-538.290')] -[2023-11-28 02:51:03,890][87426] Updated weights for policy 1, policy_version 100550 (0.0011) -[2023-11-28 02:51:04,260][87426] Updated weights for policy 1, policy_version 100560 (0.0011) -[2023-11-28 02:51:04,459][87424] Updated weights for policy 0, policy_version 100776 (0.0011) -[2023-11-28 02:51:04,639][87426] Updated weights for policy 1, policy_version 100570 (0.0011) -[2023-11-28 02:51:04,841][87424] Updated weights for policy 0, policy_version 100786 (0.0010) -[2023-11-28 02:51:05,231][87424] Updated weights for policy 0, policy_version 100796 (0.0008) -[2023-11-28 02:51:06,900][87426] Updated weights for policy 1, policy_version 100580 (0.0012) -[2023-11-28 02:51:07,279][87426] Updated weights for policy 1, policy_version 100590 (0.0011) -[2023-11-28 02:51:07,649][87426] Updated weights for policy 1, policy_version 100600 (0.0012) -[2023-11-28 02:51:07,777][87424] Updated weights for policy 0, policy_version 100806 (0.0008) -[2023-11-28 02:51:08,164][87424] Updated weights for policy 0, policy_version 100816 (0.0009) -[2023-11-28 02:51:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 51560448. Throughput: 0: 2717.2, 1: 2682.9. Samples: 51579728. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:51:08,445][86177] Avg episode reward: [(0, '-504.650'), (1, '-549.090')] -[2023-11-28 02:51:08,548][87424] Updated weights for policy 0, policy_version 100826 (0.0008) -[2023-11-28 02:51:09,513][87426] Updated weights for policy 1, policy_version 100610 (0.0011) -[2023-11-28 02:51:09,893][87426] Updated weights for policy 1, policy_version 100620 (0.0011) -[2023-11-28 02:51:10,272][87426] Updated weights for policy 1, policy_version 100630 (0.0012) -[2023-11-28 02:51:10,654][87426] Updated weights for policy 1, policy_version 100640 (0.0009) -[2023-11-28 02:51:10,752][87424] Updated weights for policy 0, policy_version 100836 (0.0009) -[2023-11-28 02:51:11,134][87424] Updated weights for policy 0, policy_version 100846 (0.0012) -[2023-11-28 02:51:11,518][87424] Updated weights for policy 0, policy_version 100856 (0.0012) -[2023-11-28 02:51:13,040][87426] Updated weights for policy 1, policy_version 100650 (0.0011) -[2023-11-28 02:51:13,407][87426] Updated weights for policy 1, policy_version 100660 (0.0012) -[2023-11-28 02:51:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 51585024. Throughput: 0: 2709.1, 1: 2661.8. Samples: 51602564. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:51:13,445][86177] Avg episode reward: [(0, '-496.650'), (1, '-508.790')] -[2023-11-28 02:51:13,539][87424] Updated weights for policy 0, policy_version 100866 (0.0010) -[2023-11-28 02:51:13,785][87426] Updated weights for policy 1, policy_version 100670 (0.0011) -[2023-11-28 02:51:13,920][87424] Updated weights for policy 0, policy_version 100876 (0.0011) -[2023-11-28 02:51:14,296][87424] Updated weights for policy 0, policy_version 100886 (0.0011) -[2023-11-28 02:51:14,691][87424] Updated weights for policy 0, policy_version 100896 (0.0010) -[2023-11-28 02:51:16,351][87426] Updated weights for policy 1, policy_version 100680 (0.0011) -[2023-11-28 02:51:16,722][87426] Updated weights for policy 1, policy_version 100690 (0.0012) -[2023-11-28 02:51:17,046][87424] Updated weights for policy 0, policy_version 100906 (0.0007) -[2023-11-28 02:51:17,101][87426] Updated weights for policy 1, policy_version 100700 (0.0011) -[2023-11-28 02:51:17,434][87424] Updated weights for policy 0, policy_version 100916 (0.0009) -[2023-11-28 02:51:17,817][87424] Updated weights for policy 0, policy_version 100926 (0.0008) -[2023-11-28 02:51:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 51617792. Throughput: 0: 2719.7, 1: 2670.0. Samples: 51627116. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:51:18,445][86177] Avg episode reward: [(0, '-499.080'), (1, '-509.840')] -[2023-11-28 02:51:18,773][87426] Updated weights for policy 1, policy_version 100710 (0.0012) -[2023-11-28 02:51:19,150][87426] Updated weights for policy 1, policy_version 100720 (0.0010) -[2023-11-28 02:51:19,529][87426] Updated weights for policy 1, policy_version 100730 (0.0011) -[2023-11-28 02:51:19,954][87424] Updated weights for policy 0, policy_version 100936 (0.0009) -[2023-11-28 02:51:20,328][87424] Updated weights for policy 0, policy_version 100946 (0.0012) -[2023-11-28 02:51:20,703][87424] Updated weights for policy 0, policy_version 100956 (0.0012) -[2023-11-28 02:51:21,889][87426] Updated weights for policy 1, policy_version 100740 (0.0011) -[2023-11-28 02:51:22,262][87426] Updated weights for policy 1, policy_version 100750 (0.0012) -[2023-11-28 02:51:22,649][87426] Updated weights for policy 1, policy_version 100760 (0.0011) -[2023-11-28 02:51:23,000][87424] Updated weights for policy 0, policy_version 100966 (0.0012) -[2023-11-28 02:51:23,373][87424] Updated weights for policy 0, policy_version 100976 (0.0012) -[2023-11-28 02:51:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 51642368. Throughput: 0: 2712.5, 1: 2652.2. Samples: 51658492. Policy #0 lag: (min: 31.0, avg: 51.9, max: 92.0) -[2023-11-28 02:51:23,445][86177] Avg episode reward: [(0, '-497.960'), (1, '-511.370')] -[2023-11-28 02:51:23,753][87424] Updated weights for policy 0, policy_version 100986 (0.0012) -[2023-11-28 02:51:24,763][87426] Updated weights for policy 1, policy_version 100770 (0.0008) -[2023-11-28 02:51:25,144][87426] Updated weights for policy 1, policy_version 100780 (0.0007) -[2023-11-28 02:51:25,526][87426] Updated weights for policy 1, policy_version 100790 (0.0007) -[2023-11-28 02:51:25,903][87426] Updated weights for policy 1, policy_version 100800 (0.0007) -[2023-11-28 02:51:26,080][87424] Updated weights for policy 0, policy_version 100996 (0.0010) -[2023-11-28 02:51:26,459][87424] Updated weights for policy 0, policy_version 101006 (0.0007) -[2023-11-28 02:51:26,843][87424] Updated weights for policy 0, policy_version 101016 (0.0008) -[2023-11-28 02:51:28,325][87426] Updated weights for policy 1, policy_version 100810 (0.0011) -[2023-11-28 02:51:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 51666944. Throughput: 0: 2702.7, 1: 2676.2. Samples: 51682852. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:51:28,445][86177] Avg episode reward: [(0, '-497.960'), (1, '-516.260')] -[2023-11-28 02:51:28,703][87426] Updated weights for policy 1, policy_version 100820 (0.0011) -[2023-11-28 02:51:29,051][87424] Updated weights for policy 0, policy_version 101026 (0.0008) -[2023-11-28 02:51:29,097][87426] Updated weights for policy 1, policy_version 100830 (0.0009) -[2023-11-28 02:51:29,428][87424] Updated weights for policy 0, policy_version 101036 (0.0007) -[2023-11-28 02:51:29,817][87424] Updated weights for policy 0, policy_version 101046 (0.0008) -[2023-11-28 02:51:30,191][87424] Updated weights for policy 0, policy_version 101056 (0.0008) -[2023-11-28 02:51:31,576][87426] Updated weights for policy 1, policy_version 100840 (0.0011) -[2023-11-28 02:51:31,955][87426] Updated weights for policy 1, policy_version 100850 (0.0010) -[2023-11-28 02:51:32,301][87424] Updated weights for policy 0, policy_version 101066 (0.0012) -[2023-11-28 02:51:32,336][87426] Updated weights for policy 1, policy_version 100860 (0.0011) -[2023-11-28 02:51:32,677][87424] Updated weights for policy 0, policy_version 101076 (0.0012) -[2023-11-28 02:51:33,063][87424] Updated weights for policy 0, policy_version 101086 (0.0012) -[2023-11-28 02:51:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 51699712. Throughput: 0: 2704.8, 1: 2674.7. Samples: 51707336. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:51:33,445][86177] Avg episode reward: [(0, '-495.920'), (1, '-528.200')] -[2023-11-28 02:51:34,812][87426] Updated weights for policy 1, policy_version 100870 (0.0011) -[2023-11-28 02:51:35,012][87424] Updated weights for policy 0, policy_version 101096 (0.0011) -[2023-11-28 02:51:35,191][87426] Updated weights for policy 1, policy_version 100880 (0.0011) -[2023-11-28 02:51:35,398][87424] Updated weights for policy 0, policy_version 101106 (0.0012) -[2023-11-28 02:51:35,576][87426] Updated weights for policy 1, policy_version 100890 (0.0010) -[2023-11-28 02:51:35,776][87424] Updated weights for policy 0, policy_version 101116 (0.0010) -[2023-11-28 02:51:37,542][87424] Updated weights for policy 0, policy_version 101126 (0.0009) -[2023-11-28 02:51:37,660][87426] Updated weights for policy 1, policy_version 100900 (0.0012) -[2023-11-28 02:51:37,928][87424] Updated weights for policy 0, policy_version 101136 (0.0012) -[2023-11-28 02:51:38,044][87426] Updated weights for policy 1, policy_version 100910 (0.0011) -[2023-11-28 02:51:38,315][87424] Updated weights for policy 0, policy_version 101146 (0.0012) -[2023-11-28 02:51:38,415][87426] Updated weights for policy 1, policy_version 100920 (0.0011) -[2023-11-28 02:51:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 51716096. Throughput: 0: 2741.7, 1: 2661.8. Samples: 51741732. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:51:38,445][86177] Avg episode reward: [(0, '-492.910'), (1, '-527.670')] -[2023-11-28 02:51:40,285][87424] Updated weights for policy 0, policy_version 101156 (0.0010) -[2023-11-28 02:51:40,669][87424] Updated weights for policy 0, policy_version 101166 (0.0008) -[2023-11-28 02:51:40,963][87426] Updated weights for policy 1, policy_version 100930 (0.0010) -[2023-11-28 02:51:41,058][87424] Updated weights for policy 0, policy_version 101176 (0.0009) -[2023-11-28 02:51:41,353][87426] Updated weights for policy 1, policy_version 100940 (0.0010) -[2023-11-28 02:51:41,735][87426] Updated weights for policy 1, policy_version 100950 (0.0010) -[2023-11-28 02:51:42,110][87426] Updated weights for policy 1, policy_version 100960 (0.0012) -[2023-11-28 02:51:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 51748864. Throughput: 0: 2756.0, 1: 2654.8. Samples: 51766544. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:51:43,445][86177] Avg episode reward: [(0, '-500.550'), (1, '-528.600')] -[2023-11-28 02:51:43,582][87424] Updated weights for policy 0, policy_version 101186 (0.0010) -[2023-11-28 02:51:43,958][87424] Updated weights for policy 0, policy_version 101196 (0.0012) -[2023-11-28 02:51:44,171][87426] Updated weights for policy 1, policy_version 100970 (0.0008) -[2023-11-28 02:51:44,341][87424] Updated weights for policy 0, policy_version 101206 (0.0011) -[2023-11-28 02:51:44,554][87426] Updated weights for policy 1, policy_version 100980 (0.0007) -[2023-11-28 02:51:44,728][87424] Updated weights for policy 0, policy_version 101216 (0.0009) -[2023-11-28 02:51:44,924][87426] Updated weights for policy 1, policy_version 100990 (0.0007) -[2023-11-28 02:51:46,581][87424] Updated weights for policy 0, policy_version 101226 (0.0008) -[2023-11-28 02:51:46,957][87424] Updated weights for policy 0, policy_version 101236 (0.0007) -[2023-11-28 02:51:47,262][87426] Updated weights for policy 1, policy_version 101000 (0.0009) -[2023-11-28 02:51:47,339][87424] Updated weights for policy 0, policy_version 101246 (0.0009) -[2023-11-28 02:51:47,653][87426] Updated weights for policy 1, policy_version 101010 (0.0012) -[2023-11-28 02:51:48,030][87426] Updated weights for policy 1, policy_version 101020 (0.0007) -[2023-11-28 02:51:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 51781632. Throughput: 0: 2728.3, 1: 2652.8. Samples: 51789980. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:51:48,446][86177] Avg episode reward: [(0, '-502.390'), (1, '-512.000')] -[2023-11-28 02:51:49,486][87424] Updated weights for policy 0, policy_version 101256 (0.0008) -[2023-11-28 02:51:49,870][87424] Updated weights for policy 0, policy_version 101266 (0.0009) -[2023-11-28 02:51:50,254][87424] Updated weights for policy 0, policy_version 101276 (0.0010) -[2023-11-28 02:51:50,316][87426] Updated weights for policy 1, policy_version 101030 (0.0008) -[2023-11-28 02:51:50,681][87426] Updated weights for policy 1, policy_version 101040 (0.0010) -[2023-11-28 02:51:51,058][87426] Updated weights for policy 1, policy_version 101050 (0.0010) -[2023-11-28 02:51:52,773][87424] Updated weights for policy 0, policy_version 101286 (0.0010) -[2023-11-28 02:51:53,154][87424] Updated weights for policy 0, policy_version 101296 (0.0012) -[2023-11-28 02:51:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 51798016. Throughput: 0: 2705.4, 1: 2647.8. Samples: 51820624. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:51:53,445][86177] Avg episode reward: [(0, '-509.520'), (1, '-500.300')] -[2023-11-28 02:51:53,487][87426] Updated weights for policy 1, policy_version 101060 (0.0011) -[2023-11-28 02:51:53,534][87424] Updated weights for policy 0, policy_version 101306 (0.0012) -[2023-11-28 02:51:53,863][87426] Updated weights for policy 1, policy_version 101070 (0.0009) -[2023-11-28 02:51:54,245][87426] Updated weights for policy 1, policy_version 101080 (0.0009) -[2023-11-28 02:51:55,998][87424] Updated weights for policy 0, policy_version 101316 (0.0012) -[2023-11-28 02:51:56,373][87424] Updated weights for policy 0, policy_version 101326 (0.0012) -[2023-11-28 02:51:56,531][87426] Updated weights for policy 1, policy_version 101090 (0.0007) -[2023-11-28 02:51:56,760][87424] Updated weights for policy 0, policy_version 101336 (0.0009) -[2023-11-28 02:51:56,905][87426] Updated weights for policy 1, policy_version 101100 (0.0009) -[2023-11-28 02:51:57,283][87426] Updated weights for policy 1, policy_version 101110 (0.0009) -[2023-11-28 02:51:57,667][87426] Updated weights for policy 1, policy_version 101120 (0.0007) -[2023-11-28 02:51:58,385][87424] Updated weights for policy 0, policy_version 101346 (0.0009) -[2023-11-28 02:51:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 51830784. Throughput: 0: 2734.9, 1: 2649.3. Samples: 51844852. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:51:58,445][86177] Avg episode reward: [(0, '-512.640'), (1, '-497.870')] -[2023-11-28 02:51:58,780][87424] Updated weights for policy 0, policy_version 101356 (0.0012) -[2023-11-28 02:51:59,160][87424] Updated weights for policy 0, policy_version 101366 (0.0011) -[2023-11-28 02:51:59,246][87426] Updated weights for policy 1, policy_version 101130 (0.0011) -[2023-11-28 02:51:59,532][87424] Updated weights for policy 0, policy_version 101376 (0.0012) -[2023-11-28 02:51:59,625][87426] Updated weights for policy 1, policy_version 101140 (0.0009) -[2023-11-28 02:51:59,997][87426] Updated weights for policy 1, policy_version 101150 (0.0008) -[2023-11-28 02:52:01,718][87426] Updated weights for policy 1, policy_version 101160 (0.0010) -[2023-11-28 02:52:02,023][87424] Updated weights for policy 0, policy_version 101386 (0.0010) -[2023-11-28 02:52:02,095][87426] Updated weights for policy 1, policy_version 101170 (0.0012) -[2023-11-28 02:52:02,409][87424] Updated weights for policy 0, policy_version 101396 (0.0010) -[2023-11-28 02:52:02,477][87426] Updated weights for policy 1, policy_version 101180 (0.0011) -[2023-11-28 02:52:02,793][87424] Updated weights for policy 0, policy_version 101406 (0.0008) -[2023-11-28 02:52:03,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 51863552. Throughput: 0: 2732.4, 1: 2643.7. Samples: 51869044. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:52:03,445][86177] Avg episode reward: [(0, '-505.320'), (1, '-499.280')] -[2023-11-28 02:52:04,973][87426] Updated weights for policy 1, policy_version 101190 (0.0012) -[2023-11-28 02:52:05,189][87424] Updated weights for policy 0, policy_version 101416 (0.0011) -[2023-11-28 02:52:05,352][87426] Updated weights for policy 1, policy_version 101200 (0.0012) -[2023-11-28 02:52:05,568][87424] Updated weights for policy 0, policy_version 101426 (0.0011) -[2023-11-28 02:52:05,739][87426] Updated weights for policy 1, policy_version 101210 (0.0011) -[2023-11-28 02:52:05,958][87424] Updated weights for policy 0, policy_version 101436 (0.0011) -[2023-11-28 02:52:08,158][87426] Updated weights for policy 1, policy_version 101220 (0.0011) -[2023-11-28 02:52:08,251][87424] Updated weights for policy 0, policy_version 101446 (0.0009) -[2023-11-28 02:52:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 51879936. Throughput: 0: 2748.1, 1: 2646.8. Samples: 51901264. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:52:08,445][86177] Avg episode reward: [(0, '-505.620'), (1, '-498.380')] -[2023-11-28 02:52:08,537][87426] Updated weights for policy 1, policy_version 101230 (0.0012) -[2023-11-28 02:52:08,633][87424] Updated weights for policy 0, policy_version 101456 (0.0009) -[2023-11-28 02:52:08,915][87426] Updated weights for policy 1, policy_version 101240 (0.0012) -[2023-11-28 02:52:09,013][87424] Updated weights for policy 0, policy_version 101466 (0.0010) -[2023-11-28 02:52:10,877][87426] Updated weights for policy 1, policy_version 101250 (0.0011) -[2023-11-28 02:52:11,258][87426] Updated weights for policy 1, policy_version 101260 (0.0011) -[2023-11-28 02:52:11,328][87424] Updated weights for policy 0, policy_version 101476 (0.0010) -[2023-11-28 02:52:11,637][87426] Updated weights for policy 1, policy_version 101270 (0.0011) -[2023-11-28 02:52:11,715][87424] Updated weights for policy 0, policy_version 101486 (0.0011) -[2023-11-28 02:52:12,015][87426] Updated weights for policy 1, policy_version 101280 (0.0011) -[2023-11-28 02:52:12,099][87424] Updated weights for policy 0, policy_version 101496 (0.0011) -[2023-11-28 02:52:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 51912704. Throughput: 0: 2743.2, 1: 2649.3. Samples: 51925516. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:52:13,445][86177] Avg episode reward: [(0, '-502.020'), (1, '-508.990')] -[2023-11-28 02:52:14,189][87424] Updated weights for policy 0, policy_version 101506 (0.0010) -[2023-11-28 02:52:14,541][87426] Updated weights for policy 1, policy_version 101290 (0.0012) -[2023-11-28 02:52:14,575][87424] Updated weights for policy 0, policy_version 101516 (0.0008) -[2023-11-28 02:52:14,928][87426] Updated weights for policy 1, policy_version 101300 (0.0012) -[2023-11-28 02:52:14,959][87424] Updated weights for policy 0, policy_version 101526 (0.0007) -[2023-11-28 02:52:15,309][87426] Updated weights for policy 1, policy_version 101310 (0.0011) -[2023-11-28 02:52:15,335][87424] Updated weights for policy 0, policy_version 101536 (0.0008) -[2023-11-28 02:52:17,406][87424] Updated weights for policy 0, policy_version 101546 (0.0012) -[2023-11-28 02:52:17,706][87426] Updated weights for policy 1, policy_version 101320 (0.0011) -[2023-11-28 02:52:17,788][87424] Updated weights for policy 0, policy_version 101556 (0.0012) -[2023-11-28 02:52:18,083][87426] Updated weights for policy 1, policy_version 101330 (0.0008) -[2023-11-28 02:52:18,160][87424] Updated weights for policy 0, policy_version 101566 (0.0008) -[2023-11-28 02:52:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 51937280. Throughput: 0: 2748.8, 1: 2654.5. Samples: 51950484. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:52:18,445][86177] Avg episode reward: [(0, '-504.070'), (1, '-511.900')] -[2023-11-28 02:52:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000101568_26001408.pth... -[2023-11-28 02:52:18,471][87426] Updated weights for policy 1, policy_version 101340 (0.0008) -[2023-11-28 02:52:18,486][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000099040_25354240.pth -[2023-11-28 02:52:18,490][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000101568_26001408.pth -[2023-11-28 02:52:18,623][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000101344_25944064.pth... -[2023-11-28 02:52:18,653][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000098848_25305088.pth -[2023-11-28 02:52:18,658][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000101344_25944064.pth -[2023-11-28 02:52:20,603][87426] Updated weights for policy 1, policy_version 101350 (0.0009) -[2023-11-28 02:52:20,706][87424] Updated weights for policy 0, policy_version 101576 (0.0012) -[2023-11-28 02:52:20,983][87426] Updated weights for policy 1, policy_version 101360 (0.0010) -[2023-11-28 02:52:21,089][87424] Updated weights for policy 0, policy_version 101586 (0.0008) -[2023-11-28 02:52:21,362][87426] Updated weights for policy 1, policy_version 101370 (0.0010) -[2023-11-28 02:52:21,470][87424] Updated weights for policy 0, policy_version 101596 (0.0011) -[2023-11-28 02:52:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 51961856. Throughput: 0: 2683.4, 1: 2661.2. Samples: 51982236. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 02:52:23,445][86177] Avg episode reward: [(0, '-500.920'), (1, '-522.310')] -[2023-11-28 02:52:23,566][87426] Updated weights for policy 1, policy_version 101380 (0.0008) -[2023-11-28 02:52:23,941][87426] Updated weights for policy 1, policy_version 101390 (0.0009) -[2023-11-28 02:52:24,063][87424] Updated weights for policy 0, policy_version 101606 (0.0009) -[2023-11-28 02:52:24,323][87426] Updated weights for policy 1, policy_version 101400 (0.0010) -[2023-11-28 02:52:24,445][87424] Updated weights for policy 0, policy_version 101616 (0.0008) -[2023-11-28 02:52:24,838][87424] Updated weights for policy 0, policy_version 101626 (0.0008) -[2023-11-28 02:52:26,363][87426] Updated weights for policy 1, policy_version 101410 (0.0009) -[2023-11-28 02:52:26,747][87426] Updated weights for policy 1, policy_version 101420 (0.0007) -[2023-11-28 02:52:27,094][87424] Updated weights for policy 0, policy_version 101636 (0.0008) -[2023-11-28 02:52:27,127][87426] Updated weights for policy 1, policy_version 101430 (0.0009) -[2023-11-28 02:52:27,482][87424] Updated weights for policy 0, policy_version 101646 (0.0010) -[2023-11-28 02:52:27,511][87426] Updated weights for policy 1, policy_version 101440 (0.0007) -[2023-11-28 02:52:27,869][87424] Updated weights for policy 0, policy_version 101656 (0.0007) -[2023-11-28 02:52:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 51994624. Throughput: 0: 2659.2, 1: 2684.6. Samples: 52007016. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:52:28,445][86177] Avg episode reward: [(0, '-504.590'), (1, '-519.650')] -[2023-11-28 02:52:29,228][87426] Updated weights for policy 1, policy_version 101450 (0.0008) -[2023-11-28 02:52:29,603][87426] Updated weights for policy 1, policy_version 101460 (0.0007) -[2023-11-28 02:52:29,941][87424] Updated weights for policy 0, policy_version 101666 (0.0008) -[2023-11-28 02:52:29,997][87426] Updated weights for policy 1, policy_version 101470 (0.0010) -[2023-11-28 02:52:30,315][87424] Updated weights for policy 0, policy_version 101676 (0.0012) -[2023-11-28 02:52:30,701][87424] Updated weights for policy 0, policy_version 101686 (0.0012) -[2023-11-28 02:52:31,085][87424] Updated weights for policy 0, policy_version 101696 (0.0012) -[2023-11-28 02:52:32,038][87426] Updated weights for policy 1, policy_version 101480 (0.0010) -[2023-11-28 02:52:32,417][87426] Updated weights for policy 1, policy_version 101490 (0.0010) -[2023-11-28 02:52:32,800][87426] Updated weights for policy 1, policy_version 101500 (0.0009) -[2023-11-28 02:52:33,382][87424] Updated weights for policy 0, policy_version 101706 (0.0012) -[2023-11-28 02:52:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 52019200. Throughput: 0: 2650.3, 1: 2700.1. Samples: 52030748. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:52:33,445][86177] Avg episode reward: [(0, '-510.570'), (1, '-515.860')] -[2023-11-28 02:52:33,764][87424] Updated weights for policy 0, policy_version 101716 (0.0010) -[2023-11-28 02:52:34,155][87424] Updated weights for policy 0, policy_version 101726 (0.0009) -[2023-11-28 02:52:34,724][87426] Updated weights for policy 1, policy_version 101510 (0.0011) -[2023-11-28 02:52:35,097][87426] Updated weights for policy 1, policy_version 101520 (0.0012) -[2023-11-28 02:52:35,478][87426] Updated weights for policy 1, policy_version 101530 (0.0011) -[2023-11-28 02:52:36,267][87424] Updated weights for policy 0, policy_version 101736 (0.0008) -[2023-11-28 02:52:36,650][87424] Updated weights for policy 0, policy_version 101746 (0.0008) -[2023-11-28 02:52:37,030][87424] Updated weights for policy 0, policy_version 101756 (0.0012) -[2023-11-28 02:52:37,667][87426] Updated weights for policy 1, policy_version 101540 (0.0012) -[2023-11-28 02:52:38,047][87426] Updated weights for policy 1, policy_version 101550 (0.0012) -[2023-11-28 02:52:38,432][87426] Updated weights for policy 1, policy_version 101560 (0.0012) -[2023-11-28 02:52:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52043776. Throughput: 0: 2688.5, 1: 2735.3. Samples: 52064696. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:52:38,445][86177] Avg episode reward: [(0, '-511.780'), (1, '-528.880')] -[2023-11-28 02:52:39,162][87424] Updated weights for policy 0, policy_version 101766 (0.0012) -[2023-11-28 02:52:39,553][87424] Updated weights for policy 0, policy_version 101776 (0.0012) -[2023-11-28 02:52:39,933][87424] Updated weights for policy 0, policy_version 101786 (0.0015) -[2023-11-28 02:52:40,836][87426] Updated weights for policy 1, policy_version 101570 (0.0011) -[2023-11-28 02:52:41,217][87426] Updated weights for policy 1, policy_version 101580 (0.0011) -[2023-11-28 02:52:41,611][87426] Updated weights for policy 1, policy_version 101590 (0.0010) -[2023-11-28 02:52:41,980][87426] Updated weights for policy 1, policy_version 101600 (0.0009) -[2023-11-28 02:52:42,363][87424] Updated weights for policy 0, policy_version 101796 (0.0011) -[2023-11-28 02:52:42,745][87424] Updated weights for policy 0, policy_version 101806 (0.0012) -[2023-11-28 02:52:43,125][87424] Updated weights for policy 0, policy_version 101816 (0.0012) -[2023-11-28 02:52:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52076544. Throughput: 0: 2675.5, 1: 2734.7. Samples: 52088308. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:52:43,445][86177] Avg episode reward: [(0, '-511.710'), (1, '-518.460')] -[2023-11-28 02:52:44,296][87426] Updated weights for policy 1, policy_version 101610 (0.0011) -[2023-11-28 02:52:44,679][87426] Updated weights for policy 1, policy_version 101620 (0.0008) -[2023-11-28 02:52:45,070][87426] Updated weights for policy 1, policy_version 101630 (0.0007) -[2023-11-28 02:52:45,186][87424] Updated weights for policy 0, policy_version 101826 (0.0012) -[2023-11-28 02:52:45,562][87424] Updated weights for policy 0, policy_version 101836 (0.0012) -[2023-11-28 02:52:45,940][87424] Updated weights for policy 0, policy_version 101846 (0.0012) -[2023-11-28 02:52:46,324][87424] Updated weights for policy 0, policy_version 101856 (0.0011) -[2023-11-28 02:52:47,519][87426] Updated weights for policy 1, policy_version 101640 (0.0011) -[2023-11-28 02:52:47,887][87426] Updated weights for policy 1, policy_version 101650 (0.0011) -[2023-11-28 02:52:48,277][87426] Updated weights for policy 1, policy_version 101660 (0.0011) -[2023-11-28 02:52:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 52101120. Throughput: 0: 2672.2, 1: 2734.6. Samples: 52112348. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:52:48,445][86177] Avg episode reward: [(0, '-501.680'), (1, '-522.290')] -[2023-11-28 02:52:48,552][87424] Updated weights for policy 0, policy_version 101866 (0.0008) -[2023-11-28 02:52:48,938][87424] Updated weights for policy 0, policy_version 101876 (0.0008) -[2023-11-28 02:52:49,320][87424] Updated weights for policy 0, policy_version 101886 (0.0007) -[2023-11-28 02:52:50,018][87426] Updated weights for policy 1, policy_version 101670 (0.0009) -[2023-11-28 02:52:50,394][87426] Updated weights for policy 1, policy_version 101680 (0.0011) -[2023-11-28 02:52:50,776][87426] Updated weights for policy 1, policy_version 101690 (0.0009) -[2023-11-28 02:52:51,610][87424] Updated weights for policy 0, policy_version 101896 (0.0009) -[2023-11-28 02:52:51,992][87424] Updated weights for policy 0, policy_version 101906 (0.0010) -[2023-11-28 02:52:52,371][87424] Updated weights for policy 0, policy_version 101916 (0.0010) -[2023-11-28 02:52:52,861][87426] Updated weights for policy 1, policy_version 101700 (0.0008) -[2023-11-28 02:52:53,251][87426] Updated weights for policy 1, policy_version 101710 (0.0008) -[2023-11-28 02:52:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52125696. Throughput: 0: 2660.3, 1: 2757.3. Samples: 52145056. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:52:53,445][86177] Avg episode reward: [(0, '-496.130'), (1, '-528.270')] -[2023-11-28 02:52:53,624][87426] Updated weights for policy 1, policy_version 101720 (0.0012) -[2023-11-28 02:52:54,928][87424] Updated weights for policy 0, policy_version 101926 (0.0010) -[2023-11-28 02:52:55,305][87424] Updated weights for policy 0, policy_version 101936 (0.0011) -[2023-11-28 02:52:55,689][87424] Updated weights for policy 0, policy_version 101946 (0.0007) -[2023-11-28 02:52:56,035][87426] Updated weights for policy 1, policy_version 101730 (0.0012) -[2023-11-28 02:52:56,427][87426] Updated weights for policy 1, policy_version 101740 (0.0012) -[2023-11-28 02:52:56,806][87426] Updated weights for policy 1, policy_version 101750 (0.0012) -[2023-11-28 02:52:57,177][87426] Updated weights for policy 1, policy_version 101760 (0.0011) -[2023-11-28 02:52:57,881][87424] Updated weights for policy 0, policy_version 101956 (0.0008) -[2023-11-28 02:52:58,267][87424] Updated weights for policy 0, policy_version 101966 (0.0007) -[2023-11-28 02:52:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 52150272. Throughput: 0: 2665.3, 1: 2749.7. Samples: 52169192. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:52:58,446][86177] Avg episode reward: [(0, '-496.610'), (1, '-516.350')] -[2023-11-28 02:52:58,651][87424] Updated weights for policy 0, policy_version 101976 (0.0009) -[2023-11-28 02:52:59,593][87426] Updated weights for policy 1, policy_version 101770 (0.0008) -[2023-11-28 02:52:59,975][87426] Updated weights for policy 1, policy_version 101780 (0.0010) -[2023-11-28 02:53:00,357][87426] Updated weights for policy 1, policy_version 101790 (0.0012) -[2023-11-28 02:53:00,706][87424] Updated weights for policy 0, policy_version 101986 (0.0012) -[2023-11-28 02:53:01,093][87424] Updated weights for policy 0, policy_version 101996 (0.0012) -[2023-11-28 02:53:01,476][87424] Updated weights for policy 0, policy_version 102006 (0.0012) -[2023-11-28 02:53:01,854][87424] Updated weights for policy 0, policy_version 102016 (0.0010) -[2023-11-28 02:53:02,339][87426] Updated weights for policy 1, policy_version 101800 (0.0011) -[2023-11-28 02:53:02,708][87426] Updated weights for policy 1, policy_version 101810 (0.0012) -[2023-11-28 02:53:03,090][87426] Updated weights for policy 1, policy_version 101820 (0.0012) -[2023-11-28 02:53:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 52183040. Throughput: 0: 2659.4, 1: 2753.9. Samples: 52194080. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:53:03,445][86177] Avg episode reward: [(0, '-494.300'), (1, '-521.940')] -[2023-11-28 02:53:03,842][87424] Updated weights for policy 0, policy_version 102026 (0.0012) -[2023-11-28 02:53:04,230][87424] Updated weights for policy 0, policy_version 102036 (0.0012) -[2023-11-28 02:53:04,614][87424] Updated weights for policy 0, policy_version 102046 (0.0012) -[2023-11-28 02:53:05,043][87426] Updated weights for policy 1, policy_version 101830 (0.0012) -[2023-11-28 02:53:05,414][87426] Updated weights for policy 1, policy_version 101840 (0.0012) -[2023-11-28 02:53:05,793][87426] Updated weights for policy 1, policy_version 101850 (0.0012) -[2023-11-28 02:53:06,348][87424] Updated weights for policy 0, policy_version 102056 (0.0012) -[2023-11-28 02:53:06,732][87424] Updated weights for policy 0, policy_version 102066 (0.0011) -[2023-11-28 02:53:07,109][87424] Updated weights for policy 0, policy_version 102076 (0.0012) -[2023-11-28 02:53:08,100][87426] Updated weights for policy 1, policy_version 101860 (0.0010) -[2023-11-28 02:53:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 52207616. Throughput: 0: 2673.1, 1: 2762.2. Samples: 52226824. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:53:08,445][86177] Avg episode reward: [(0, '-495.680'), (1, '-514.410')] -[2023-11-28 02:53:08,468][87426] Updated weights for policy 1, policy_version 101870 (0.0008) -[2023-11-28 02:53:08,790][87424] Updated weights for policy 0, policy_version 102086 (0.0010) -[2023-11-28 02:53:08,846][87426] Updated weights for policy 1, policy_version 101880 (0.0009) -[2023-11-28 02:53:09,180][87424] Updated weights for policy 0, policy_version 102096 (0.0011) -[2023-11-28 02:53:09,561][87424] Updated weights for policy 0, policy_version 102106 (0.0011) -[2023-11-28 02:53:11,132][87426] Updated weights for policy 1, policy_version 101890 (0.0008) -[2023-11-28 02:53:11,509][87426] Updated weights for policy 1, policy_version 101900 (0.0009) -[2023-11-28 02:53:11,812][87424] Updated weights for policy 0, policy_version 102116 (0.0012) -[2023-11-28 02:53:11,888][87426] Updated weights for policy 1, policy_version 101910 (0.0012) -[2023-11-28 02:53:12,194][87424] Updated weights for policy 0, policy_version 102126 (0.0012) -[2023-11-28 02:53:12,266][87426] Updated weights for policy 1, policy_version 101920 (0.0013) -[2023-11-28 02:53:12,577][87424] Updated weights for policy 0, policy_version 102136 (0.0011) -[2023-11-28 02:53:13,445][86177] Fps is (10 sec: 5734.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 52240384. Throughput: 0: 2671.7, 1: 2741.8. Samples: 52250628. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:53:13,446][86177] Avg episode reward: [(0, '-496.970'), (1, '-510.320')] -[2023-11-28 02:53:14,457][87426] Updated weights for policy 1, policy_version 101930 (0.0011) -[2023-11-28 02:53:14,678][87424] Updated weights for policy 0, policy_version 102146 (0.0011) -[2023-11-28 02:53:14,844][87426] Updated weights for policy 1, policy_version 101940 (0.0011) -[2023-11-28 02:53:15,054][87424] Updated weights for policy 0, policy_version 102156 (0.0011) -[2023-11-28 02:53:15,220][87426] Updated weights for policy 1, policy_version 101950 (0.0011) -[2023-11-28 02:53:15,417][87424] Updated weights for policy 0, policy_version 102166 (0.0012) -[2023-11-28 02:53:15,797][87424] Updated weights for policy 0, policy_version 102176 (0.0012) -[2023-11-28 02:53:17,167][87426] Updated weights for policy 1, policy_version 101960 (0.0011) -[2023-11-28 02:53:17,549][87426] Updated weights for policy 1, policy_version 101970 (0.0011) -[2023-11-28 02:53:17,933][87426] Updated weights for policy 1, policy_version 101980 (0.0011) -[2023-11-28 02:53:18,056][87424] Updated weights for policy 0, policy_version 102186 (0.0011) -[2023-11-28 02:53:18,441][87424] Updated weights for policy 0, policy_version 102196 (0.0009) -[2023-11-28 02:53:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52264960. Throughput: 0: 2686.9, 1: 2733.0. Samples: 52274644. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:53:18,445][86177] Avg episode reward: [(0, '-493.460'), (1, '-503.860')] -[2023-11-28 02:53:18,831][87424] Updated weights for policy 0, policy_version 102206 (0.0007) -[2023-11-28 02:53:20,057][87426] Updated weights for policy 1, policy_version 101990 (0.0010) -[2023-11-28 02:53:20,433][87426] Updated weights for policy 1, policy_version 102000 (0.0008) -[2023-11-28 02:53:20,815][87426] Updated weights for policy 1, policy_version 102010 (0.0008) -[2023-11-28 02:53:21,081][87424] Updated weights for policy 0, policy_version 102216 (0.0009) -[2023-11-28 02:53:21,463][87424] Updated weights for policy 0, policy_version 102226 (0.0008) -[2023-11-28 02:53:21,853][87424] Updated weights for policy 0, policy_version 102236 (0.0011) -[2023-11-28 02:53:22,964][87426] Updated weights for policy 1, policy_version 102020 (0.0008) -[2023-11-28 02:53:23,349][87426] Updated weights for policy 1, policy_version 102030 (0.0010) -[2023-11-28 02:53:23,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52289536. Throughput: 0: 2676.8, 1: 2713.8. Samples: 52307272. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:53:23,445][86177] Avg episode reward: [(0, '-514.490'), (1, '-495.500')] -[2023-11-28 02:53:23,730][87426] Updated weights for policy 1, policy_version 102040 (0.0011) -[2023-11-28 02:53:24,310][87424] Updated weights for policy 0, policy_version 102246 (0.0010) -[2023-11-28 02:53:24,695][87424] Updated weights for policy 0, policy_version 102256 (0.0008) -[2023-11-28 02:53:25,082][87424] Updated weights for policy 0, policy_version 102266 (0.0008) -[2023-11-28 02:53:26,210][87426] Updated weights for policy 1, policy_version 102050 (0.0008) -[2023-11-28 02:53:26,574][87426] Updated weights for policy 1, policy_version 102060 (0.0012) -[2023-11-28 02:53:26,958][87426] Updated weights for policy 1, policy_version 102070 (0.0012) -[2023-11-28 02:53:27,110][87424] Updated weights for policy 0, policy_version 102276 (0.0008) -[2023-11-28 02:53:27,324][87426] Updated weights for policy 1, policy_version 102080 (0.0012) -[2023-11-28 02:53:27,501][87424] Updated weights for policy 0, policy_version 102286 (0.0009) -[2023-11-28 02:53:27,876][87424] Updated weights for policy 0, policy_version 102296 (0.0011) -[2023-11-28 02:53:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 52322304. Throughput: 0: 2686.0, 1: 2720.2. Samples: 52331584. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 02:53:28,445][86177] Avg episode reward: [(0, '-557.820'), (1, '-507.100')] -[2023-11-28 02:53:29,286][87426] Updated weights for policy 1, policy_version 102090 (0.0012) -[2023-11-28 02:53:29,666][87426] Updated weights for policy 1, policy_version 102100 (0.0011) -[2023-11-28 02:53:29,742][87424] Updated weights for policy 0, policy_version 102306 (0.0012) -[2023-11-28 02:53:30,045][87426] Updated weights for policy 1, policy_version 102110 (0.0010) -[2023-11-28 02:53:30,121][87424] Updated weights for policy 0, policy_version 102316 (0.0011) -[2023-11-28 02:53:30,515][87424] Updated weights for policy 0, policy_version 102326 (0.0012) -[2023-11-28 02:53:30,881][87424] Updated weights for policy 0, policy_version 102336 (0.0012) -[2023-11-28 02:53:32,565][87426] Updated weights for policy 1, policy_version 102120 (0.0011) -[2023-11-28 02:53:32,947][87426] Updated weights for policy 1, policy_version 102130 (0.0011) -[2023-11-28 02:53:32,992][87424] Updated weights for policy 0, policy_version 102346 (0.0011) -[2023-11-28 02:53:33,325][87426] Updated weights for policy 1, policy_version 102140 (0.0008) -[2023-11-28 02:53:33,374][87424] Updated weights for policy 0, policy_version 102356 (0.0008) -[2023-11-28 02:53:33,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 52338688. Throughput: 0: 2696.6, 1: 2728.5. Samples: 52356480. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:53:33,446][86177] Avg episode reward: [(0, '-557.770'), (1, '-508.170')] -[2023-11-28 02:53:33,756][87424] Updated weights for policy 0, policy_version 102366 (0.0007) -[2023-11-28 02:53:35,255][87426] Updated weights for policy 1, policy_version 102150 (0.0012) -[2023-11-28 02:53:35,626][87426] Updated weights for policy 1, policy_version 102160 (0.0008) -[2023-11-28 02:53:35,701][87424] Updated weights for policy 0, policy_version 102376 (0.0009) -[2023-11-28 02:53:36,007][87426] Updated weights for policy 1, policy_version 102170 (0.0010) -[2023-11-28 02:53:36,085][87424] Updated weights for policy 0, policy_version 102386 (0.0008) -[2023-11-28 02:53:36,469][87424] Updated weights for policy 0, policy_version 102396 (0.0008) -[2023-11-28 02:53:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52371456. Throughput: 0: 2702.9, 1: 2717.3. Samples: 52388960. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:53:38,445][86177] Avg episode reward: [(0, '-555.840'), (1, '-508.080')] -[2023-11-28 02:53:38,565][87426] Updated weights for policy 1, policy_version 102180 (0.0011) -[2023-11-28 02:53:38,858][87424] Updated weights for policy 0, policy_version 102406 (0.0009) -[2023-11-28 02:53:38,944][87426] Updated weights for policy 1, policy_version 102190 (0.0010) -[2023-11-28 02:53:39,243][87424] Updated weights for policy 0, policy_version 102416 (0.0012) -[2023-11-28 02:53:39,321][87426] Updated weights for policy 1, policy_version 102200 (0.0009) -[2023-11-28 02:53:39,627][87424] Updated weights for policy 0, policy_version 102426 (0.0012) -[2023-11-28 02:53:41,803][87426] Updated weights for policy 1, policy_version 102210 (0.0011) -[2023-11-28 02:53:42,103][87424] Updated weights for policy 0, policy_version 102436 (0.0012) -[2023-11-28 02:53:42,181][87426] Updated weights for policy 1, policy_version 102220 (0.0011) -[2023-11-28 02:53:42,484][87424] Updated weights for policy 0, policy_version 102446 (0.0009) -[2023-11-28 02:53:42,558][87426] Updated weights for policy 1, policy_version 102230 (0.0009) -[2023-11-28 02:53:42,868][87424] Updated weights for policy 0, policy_version 102456 (0.0008) -[2023-11-28 02:53:42,937][87426] Updated weights for policy 1, policy_version 102240 (0.0009) -[2023-11-28 02:53:43,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 52404224. Throughput: 0: 2688.8, 1: 2700.4. Samples: 52411704. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:53:43,445][86177] Avg episode reward: [(0, '-496.900'), (1, '-510.110')] -[2023-11-28 02:53:45,371][87426] Updated weights for policy 1, policy_version 102250 (0.0010) -[2023-11-28 02:53:45,430][87424] Updated weights for policy 0, policy_version 102466 (0.0009) -[2023-11-28 02:53:45,741][87426] Updated weights for policy 1, policy_version 102260 (0.0010) -[2023-11-28 02:53:45,817][87424] Updated weights for policy 0, policy_version 102476 (0.0011) -[2023-11-28 02:53:46,130][87426] Updated weights for policy 1, policy_version 102270 (0.0007) -[2023-11-28 02:53:46,196][87424] Updated weights for policy 0, policy_version 102486 (0.0011) -[2023-11-28 02:53:46,571][87424] Updated weights for policy 0, policy_version 102496 (0.0010) -[2023-11-28 02:53:47,691][87426] Updated weights for policy 1, policy_version 102280 (0.0007) -[2023-11-28 02:53:48,070][87426] Updated weights for policy 1, policy_version 102290 (0.0007) -[2023-11-28 02:53:48,404][87424] Updated weights for policy 0, policy_version 102506 (0.0011) -[2023-11-28 02:53:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 52420608. Throughput: 0: 2692.7, 1: 2707.5. Samples: 52437088. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:53:48,445][86177] Avg episode reward: [(0, '-491.550'), (1, '-522.330')] -[2023-11-28 02:53:48,458][87426] Updated weights for policy 1, policy_version 102300 (0.0007) -[2023-11-28 02:53:48,794][87424] Updated weights for policy 0, policy_version 102516 (0.0012) -[2023-11-28 02:53:49,164][87424] Updated weights for policy 0, policy_version 102526 (0.0012) -[2023-11-28 02:53:50,361][87426] Updated weights for policy 1, policy_version 102310 (0.0011) -[2023-11-28 02:53:50,743][87426] Updated weights for policy 1, policy_version 102320 (0.0011) -[2023-11-28 02:53:51,122][87426] Updated weights for policy 1, policy_version 102330 (0.0011) -[2023-11-28 02:53:51,501][87424] Updated weights for policy 0, policy_version 102536 (0.0008) -[2023-11-28 02:53:51,887][87424] Updated weights for policy 0, policy_version 102546 (0.0009) -[2023-11-28 02:53:52,266][87424] Updated weights for policy 0, policy_version 102556 (0.0009) -[2023-11-28 02:53:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52453376. Throughput: 0: 2726.9, 1: 2680.2. Samples: 52470144. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:53:53,445][86177] Avg episode reward: [(0, '-494.490'), (1, '-522.070')] -[2023-11-28 02:53:53,499][87426] Updated weights for policy 1, policy_version 102340 (0.0011) -[2023-11-28 02:53:53,884][87426] Updated weights for policy 1, policy_version 102350 (0.0010) -[2023-11-28 02:53:54,263][87426] Updated weights for policy 1, policy_version 102360 (0.0008) -[2023-11-28 02:53:54,266][87424] Updated weights for policy 0, policy_version 102566 (0.0010) -[2023-11-28 02:53:54,647][87424] Updated weights for policy 0, policy_version 102576 (0.0012) -[2023-11-28 02:53:55,038][87424] Updated weights for policy 0, policy_version 102586 (0.0012) -[2023-11-28 02:53:56,419][87426] Updated weights for policy 1, policy_version 102370 (0.0010) -[2023-11-28 02:53:56,804][87426] Updated weights for policy 1, policy_version 102380 (0.0012) -[2023-11-28 02:53:57,176][87426] Updated weights for policy 1, policy_version 102390 (0.0012) -[2023-11-28 02:53:57,447][87424] Updated weights for policy 0, policy_version 102596 (0.0012) -[2023-11-28 02:53:57,543][87426] Updated weights for policy 1, policy_version 102400 (0.0011) -[2023-11-28 02:53:57,824][87424] Updated weights for policy 0, policy_version 102606 (0.0012) -[2023-11-28 02:53:58,203][87424] Updated weights for policy 0, policy_version 102616 (0.0011) -[2023-11-28 02:53:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52477952. Throughput: 0: 2731.6, 1: 2699.2. Samples: 52495012. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:53:58,446][86177] Avg episode reward: [(0, '-496.850'), (1, '-531.140')] -[2023-11-28 02:54:00,003][87426] Updated weights for policy 1, policy_version 102410 (0.0009) -[2023-11-28 02:54:00,223][87424] Updated weights for policy 0, policy_version 102626 (0.0012) -[2023-11-28 02:54:00,385][87426] Updated weights for policy 1, policy_version 102420 (0.0011) -[2023-11-28 02:54:00,608][87424] Updated weights for policy 0, policy_version 102636 (0.0011) -[2023-11-28 02:54:00,754][87426] Updated weights for policy 1, policy_version 102430 (0.0011) -[2023-11-28 02:54:00,985][87424] Updated weights for policy 0, policy_version 102646 (0.0011) -[2023-11-28 02:54:01,360][87424] Updated weights for policy 0, policy_version 102656 (0.0012) -[2023-11-28 02:54:02,790][87426] Updated weights for policy 1, policy_version 102440 (0.0009) -[2023-11-28 02:54:03,172][87426] Updated weights for policy 1, policy_version 102450 (0.0008) -[2023-11-28 02:54:03,243][87424] Updated weights for policy 0, policy_version 102666 (0.0008) -[2023-11-28 02:54:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 52502528. Throughput: 0: 2733.1, 1: 2711.4. Samples: 52519644. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:54:03,445][86177] Avg episode reward: [(0, '-499.220'), (1, '-531.190')] -[2023-11-28 02:54:03,555][87426] Updated weights for policy 1, policy_version 102460 (0.0007) -[2023-11-28 02:54:03,615][87424] Updated weights for policy 0, policy_version 102676 (0.0008) -[2023-11-28 02:54:04,013][87424] Updated weights for policy 0, policy_version 102686 (0.0009) -[2023-11-28 02:54:05,444][87426] Updated weights for policy 1, policy_version 102470 (0.0010) -[2023-11-28 02:54:05,825][87426] Updated weights for policy 1, policy_version 102480 (0.0009) -[2023-11-28 02:54:06,203][87426] Updated weights for policy 1, policy_version 102490 (0.0011) -[2023-11-28 02:54:06,381][87424] Updated weights for policy 0, policy_version 102696 (0.0011) -[2023-11-28 02:54:06,766][87424] Updated weights for policy 0, policy_version 102706 (0.0012) -[2023-11-28 02:54:07,146][87424] Updated weights for policy 0, policy_version 102716 (0.0011) -[2023-11-28 02:54:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 52535296. Throughput: 0: 2748.4, 1: 2713.8. Samples: 52553068. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:54:08,445][86177] Avg episode reward: [(0, '-499.030'), (1, '-522.800')] -[2023-11-28 02:54:08,679][87426] Updated weights for policy 1, policy_version 102500 (0.0009) -[2023-11-28 02:54:09,057][87426] Updated weights for policy 1, policy_version 102510 (0.0011) -[2023-11-28 02:54:09,231][87424] Updated weights for policy 0, policy_version 102726 (0.0012) -[2023-11-28 02:54:09,435][87426] Updated weights for policy 1, policy_version 102520 (0.0011) -[2023-11-28 02:54:09,614][87424] Updated weights for policy 0, policy_version 102736 (0.0012) -[2023-11-28 02:54:09,998][87424] Updated weights for policy 0, policy_version 102746 (0.0012) -[2023-11-28 02:54:11,623][87426] Updated weights for policy 1, policy_version 102530 (0.0012) -[2023-11-28 02:54:11,994][87424] Updated weights for policy 0, policy_version 102756 (0.0011) -[2023-11-28 02:54:12,003][87426] Updated weights for policy 1, policy_version 102540 (0.0011) -[2023-11-28 02:54:12,372][87424] Updated weights for policy 0, policy_version 102766 (0.0011) -[2023-11-28 02:54:12,383][87426] Updated weights for policy 1, policy_version 102550 (0.0010) -[2023-11-28 02:54:12,755][87426] Updated weights for policy 1, policy_version 102560 (0.0010) -[2023-11-28 02:54:12,763][87424] Updated weights for policy 0, policy_version 102776 (0.0010) -[2023-11-28 02:54:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 52568064. Throughput: 0: 2741.7, 1: 2715.8. Samples: 52577172. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:54:13,445][86177] Avg episode reward: [(0, '-492.630'), (1, '-521.960')] -[2023-11-28 02:54:14,653][87426] Updated weights for policy 1, policy_version 102570 (0.0009) -[2023-11-28 02:54:14,772][87424] Updated weights for policy 0, policy_version 102786 (0.0011) -[2023-11-28 02:54:15,036][87426] Updated weights for policy 1, policy_version 102580 (0.0010) -[2023-11-28 02:54:15,149][87424] Updated weights for policy 0, policy_version 102796 (0.0009) -[2023-11-28 02:54:15,419][87426] Updated weights for policy 1, policy_version 102590 (0.0011) -[2023-11-28 02:54:15,535][87424] Updated weights for policy 0, policy_version 102806 (0.0009) -[2023-11-28 02:54:15,916][87424] Updated weights for policy 0, policy_version 102816 (0.0008) -[2023-11-28 02:54:17,721][87424] Updated weights for policy 0, policy_version 102826 (0.0009) -[2023-11-28 02:54:17,838][87426] Updated weights for policy 1, policy_version 102600 (0.0012) -[2023-11-28 02:54:18,114][87424] Updated weights for policy 0, policy_version 102836 (0.0010) -[2023-11-28 02:54:18,223][87426] Updated weights for policy 1, policy_version 102610 (0.0011) -[2023-11-28 02:54:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 52584448. Throughput: 0: 2742.2, 1: 2716.1. Samples: 52602104. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:54:18,445][86177] Avg episode reward: [(0, '-493.250'), (1, '-515.890')] -[2023-11-28 02:54:18,507][87424] Updated weights for policy 0, policy_version 102846 (0.0012) -[2023-11-28 02:54:18,578][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000102848_26329088.pth... -[2023-11-28 02:54:18,611][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000100288_25673728.pth -[2023-11-28 02:54:18,613][87426] Updated weights for policy 1, policy_version 102620 (0.0011) -[2023-11-28 02:54:18,754][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000102624_26271744.pth... -[2023-11-28 02:54:18,801][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000100096_25624576.pth -[2023-11-28 02:54:20,858][87424] Updated weights for policy 0, policy_version 102856 (0.0009) -[2023-11-28 02:54:20,992][87426] Updated weights for policy 1, policy_version 102630 (0.0009) -[2023-11-28 02:54:21,248][87424] Updated weights for policy 0, policy_version 102866 (0.0010) -[2023-11-28 02:54:21,372][87426] Updated weights for policy 1, policy_version 102640 (0.0009) -[2023-11-28 02:54:21,628][87424] Updated weights for policy 0, policy_version 102876 (0.0011) -[2023-11-28 02:54:21,753][87426] Updated weights for policy 1, policy_version 102650 (0.0009) -[2023-11-28 02:54:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 52617216. Throughput: 0: 2761.7, 1: 2699.6. Samples: 52634720. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:54:23,445][86177] Avg episode reward: [(0, '-493.990'), (1, '-511.650')] -[2023-11-28 02:54:23,865][87424] Updated weights for policy 0, policy_version 102886 (0.0008) -[2023-11-28 02:54:24,256][87424] Updated weights for policy 0, policy_version 102896 (0.0008) -[2023-11-28 02:54:24,287][87426] Updated weights for policy 1, policy_version 102660 (0.0010) -[2023-11-28 02:54:24,630][87424] Updated weights for policy 0, policy_version 102906 (0.0008) -[2023-11-28 02:54:24,654][87426] Updated weights for policy 1, policy_version 102670 (0.0011) -[2023-11-28 02:54:25,031][87426] Updated weights for policy 1, policy_version 102680 (0.0011) -[2023-11-28 02:54:26,879][87424] Updated weights for policy 0, policy_version 102916 (0.0008) -[2023-11-28 02:54:27,260][87424] Updated weights for policy 0, policy_version 102926 (0.0007) -[2023-11-28 02:54:27,388][87426] Updated weights for policy 1, policy_version 102690 (0.0010) -[2023-11-28 02:54:27,642][87424] Updated weights for policy 0, policy_version 102936 (0.0008) -[2023-11-28 02:54:27,766][87426] Updated weights for policy 1, policy_version 102700 (0.0007) -[2023-11-28 02:54:28,147][87426] Updated weights for policy 1, policy_version 102710 (0.0007) -[2023-11-28 02:54:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 52641792. Throughput: 0: 2776.4, 1: 2713.5. Samples: 52658752. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:54:28,445][86177] Avg episode reward: [(0, '-494.400'), (1, '-514.520')] -[2023-11-28 02:54:28,533][87426] Updated weights for policy 1, policy_version 102720 (0.0008) -[2023-11-28 02:54:30,046][87424] Updated weights for policy 0, policy_version 102946 (0.0008) -[2023-11-28 02:54:30,434][87424] Updated weights for policy 0, policy_version 102956 (0.0012) -[2023-11-28 02:54:30,443][87426] Updated weights for policy 1, policy_version 102730 (0.0011) -[2023-11-28 02:54:30,819][87426] Updated weights for policy 1, policy_version 102740 (0.0012) -[2023-11-28 02:54:30,837][87424] Updated weights for policy 0, policy_version 102966 (0.0008) -[2023-11-28 02:54:31,195][87426] Updated weights for policy 1, policy_version 102750 (0.0012) -[2023-11-28 02:54:31,217][87424] Updated weights for policy 0, policy_version 102976 (0.0011) -[2023-11-28 02:54:33,273][87424] Updated weights for policy 0, policy_version 102986 (0.0011) -[2023-11-28 02:54:33,399][87426] Updated weights for policy 1, policy_version 102760 (0.0012) -[2023-11-28 02:54:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 52666368. Throughput: 0: 2765.1, 1: 2692.7. Samples: 52682688. Policy #0 lag: (min: 21.0, avg: 46.6, max: 64.0) -[2023-11-28 02:54:33,445][86177] Avg episode reward: [(0, '-497.630'), (1, '-497.040')] -[2023-11-28 02:54:33,664][87424] Updated weights for policy 0, policy_version 102996 (0.0011) -[2023-11-28 02:54:33,776][87426] Updated weights for policy 1, policy_version 102770 (0.0012) -[2023-11-28 02:54:34,045][87424] Updated weights for policy 0, policy_version 103006 (0.0009) -[2023-11-28 02:54:34,164][87426] Updated weights for policy 1, policy_version 102780 (0.0011) -[2023-11-28 02:54:36,151][87424] Updated weights for policy 0, policy_version 103016 (0.0011) -[2023-11-28 02:54:36,161][87426] Updated weights for policy 1, policy_version 102790 (0.0012) -[2023-11-28 02:54:36,530][87426] Updated weights for policy 1, policy_version 102800 (0.0010) -[2023-11-28 02:54:36,531][87424] Updated weights for policy 0, policy_version 103026 (0.0010) -[2023-11-28 02:54:36,907][87426] Updated weights for policy 1, policy_version 102810 (0.0011) -[2023-11-28 02:54:36,919][87424] Updated weights for policy 0, policy_version 103036 (0.0010) -[2023-11-28 02:54:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52699136. Throughput: 0: 2741.8, 1: 2713.5. Samples: 52715632. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:54:38,445][86177] Avg episode reward: [(0, '-497.540'), (1, '-502.190')] -[2023-11-28 02:54:39,035][87424] Updated weights for policy 0, policy_version 103046 (0.0011) -[2023-11-28 02:54:39,375][87426] Updated weights for policy 1, policy_version 102820 (0.0011) -[2023-11-28 02:54:39,421][87424] Updated weights for policy 0, policy_version 103056 (0.0012) -[2023-11-28 02:54:39,753][87426] Updated weights for policy 1, policy_version 102830 (0.0010) -[2023-11-28 02:54:39,799][87424] Updated weights for policy 0, policy_version 103066 (0.0012) -[2023-11-28 02:54:40,137][87426] Updated weights for policy 1, policy_version 102840 (0.0011) -[2023-11-28 02:54:42,091][87426] Updated weights for policy 1, policy_version 102850 (0.0010) -[2023-11-28 02:54:42,144][87424] Updated weights for policy 0, policy_version 103076 (0.0010) -[2023-11-28 02:54:42,469][87426] Updated weights for policy 1, policy_version 102860 (0.0011) -[2023-11-28 02:54:42,522][87424] Updated weights for policy 0, policy_version 103086 (0.0010) -[2023-11-28 02:54:42,848][87426] Updated weights for policy 1, policy_version 102870 (0.0012) -[2023-11-28 02:54:42,903][87424] Updated weights for policy 0, policy_version 103096 (0.0009) -[2023-11-28 02:54:43,230][87426] Updated weights for policy 1, policy_version 102880 (0.0012) -[2023-11-28 02:54:43,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 52731904. Throughput: 0: 2741.8, 1: 2700.4. Samples: 52739912. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:54:43,445][86177] Avg episode reward: [(0, '-495.780'), (1, '-507.190')] -[2023-11-28 02:54:44,977][87424] Updated weights for policy 0, policy_version 103106 (0.0010) -[2023-11-28 02:54:45,148][87426] Updated weights for policy 1, policy_version 102890 (0.0012) -[2023-11-28 02:54:45,360][87424] Updated weights for policy 0, policy_version 103116 (0.0012) -[2023-11-28 02:54:45,531][87426] Updated weights for policy 1, policy_version 102900 (0.0012) -[2023-11-28 02:54:45,742][87424] Updated weights for policy 0, policy_version 103126 (0.0011) -[2023-11-28 02:54:45,909][87426] Updated weights for policy 1, policy_version 102910 (0.0010) -[2023-11-28 02:54:46,120][87424] Updated weights for policy 0, policy_version 103136 (0.0012) -[2023-11-28 02:54:48,246][87426] Updated weights for policy 1, policy_version 102920 (0.0011) -[2023-11-28 02:54:48,369][87424] Updated weights for policy 0, policy_version 103146 (0.0008) -[2023-11-28 02:54:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52748288. Throughput: 0: 2742.8, 1: 2705.2. Samples: 52764804. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:54:48,445][86177] Avg episode reward: [(0, '-498.140'), (1, '-517.810')] -[2023-11-28 02:54:48,629][87426] Updated weights for policy 1, policy_version 102930 (0.0011) -[2023-11-28 02:54:48,757][87424] Updated weights for policy 0, policy_version 103156 (0.0007) -[2023-11-28 02:54:49,011][87426] Updated weights for policy 1, policy_version 102940 (0.0015) -[2023-11-28 02:54:49,136][87424] Updated weights for policy 0, policy_version 103166 (0.0009) -[2023-11-28 02:54:51,184][87424] Updated weights for policy 0, policy_version 103176 (0.0011) -[2023-11-28 02:54:51,410][87426] Updated weights for policy 1, policy_version 102950 (0.0011) -[2023-11-28 02:54:51,561][87424] Updated weights for policy 0, policy_version 103186 (0.0011) -[2023-11-28 02:54:51,781][87426] Updated weights for policy 1, policy_version 102960 (0.0011) -[2023-11-28 02:54:51,944][87424] Updated weights for policy 0, policy_version 103196 (0.0009) -[2023-11-28 02:54:52,158][87426] Updated weights for policy 1, policy_version 102970 (0.0009) -[2023-11-28 02:54:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 52781056. Throughput: 0: 2731.5, 1: 2701.7. Samples: 52797560. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:54:53,445][86177] Avg episode reward: [(0, '-501.150'), (1, '-520.740')] -[2023-11-28 02:54:54,129][87426] Updated weights for policy 1, policy_version 102980 (0.0010) -[2023-11-28 02:54:54,468][87424] Updated weights for policy 0, policy_version 103206 (0.0008) -[2023-11-28 02:54:54,505][87426] Updated weights for policy 1, policy_version 102990 (0.0011) -[2023-11-28 02:54:54,863][87424] Updated weights for policy 0, policy_version 103216 (0.0007) -[2023-11-28 02:54:54,894][87426] Updated weights for policy 1, policy_version 103000 (0.0011) -[2023-11-28 02:54:55,238][87424] Updated weights for policy 0, policy_version 103226 (0.0008) -[2023-11-28 02:54:56,754][87426] Updated weights for policy 1, policy_version 103010 (0.0011) -[2023-11-28 02:54:57,135][87426] Updated weights for policy 1, policy_version 103020 (0.0008) -[2023-11-28 02:54:57,296][87424] Updated weights for policy 0, policy_version 103236 (0.0011) -[2023-11-28 02:54:57,514][87426] Updated weights for policy 1, policy_version 103030 (0.0008) -[2023-11-28 02:54:57,680][87424] Updated weights for policy 0, policy_version 103246 (0.0007) -[2023-11-28 02:54:57,887][87426] Updated weights for policy 1, policy_version 103040 (0.0011) -[2023-11-28 02:54:58,066][87424] Updated weights for policy 0, policy_version 103256 (0.0007) -[2023-11-28 02:54:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 52813824. Throughput: 0: 2720.0, 1: 2741.9. Samples: 52822960. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:54:58,445][86177] Avg episode reward: [(0, '-499.570'), (1, '-514.090')] -[2023-11-28 02:54:59,966][87426] Updated weights for policy 1, policy_version 103050 (0.0012) -[2023-11-28 02:55:00,258][87424] Updated weights for policy 0, policy_version 103266 (0.0008) -[2023-11-28 02:55:00,350][87426] Updated weights for policy 1, policy_version 103060 (0.0012) -[2023-11-28 02:55:00,642][87424] Updated weights for policy 0, policy_version 103276 (0.0012) -[2023-11-28 02:55:00,718][87426] Updated weights for policy 1, policy_version 103070 (0.0008) -[2023-11-28 02:55:01,022][87424] Updated weights for policy 0, policy_version 103286 (0.0008) -[2023-11-28 02:55:01,405][87424] Updated weights for policy 0, policy_version 103296 (0.0007) -[2023-11-28 02:55:02,906][87426] Updated weights for policy 1, policy_version 103080 (0.0009) -[2023-11-28 02:55:03,282][87426] Updated weights for policy 1, policy_version 103090 (0.0011) -[2023-11-28 02:55:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 52830208. Throughput: 0: 2724.8, 1: 2732.5. Samples: 52847680. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:55:03,445][86177] Avg episode reward: [(0, '-506.790'), (1, '-516.750')] -[2023-11-28 02:55:03,670][87426] Updated weights for policy 1, policy_version 103100 (0.0011) -[2023-11-28 02:55:03,802][87424] Updated weights for policy 0, policy_version 103306 (0.0011) -[2023-11-28 02:55:04,184][87424] Updated weights for policy 0, policy_version 103316 (0.0008) -[2023-11-28 02:55:04,568][87424] Updated weights for policy 0, policy_version 103326 (0.0009) -[2023-11-28 02:55:05,534][87426] Updated weights for policy 1, policy_version 103110 (0.0011) -[2023-11-28 02:55:05,916][87426] Updated weights for policy 1, policy_version 103120 (0.0012) -[2023-11-28 02:55:06,310][87426] Updated weights for policy 1, policy_version 103130 (0.0012) -[2023-11-28 02:55:06,835][87424] Updated weights for policy 0, policy_version 103336 (0.0010) -[2023-11-28 02:55:07,209][87424] Updated weights for policy 0, policy_version 103346 (0.0011) -[2023-11-28 02:55:07,594][87424] Updated weights for policy 0, policy_version 103356 (0.0011) -[2023-11-28 02:55:08,422][87426] Updated weights for policy 1, policy_version 103140 (0.0011) -[2023-11-28 02:55:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 52862976. Throughput: 0: 2677.4, 1: 2759.9. Samples: 52879400. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:55:08,445][86177] Avg episode reward: [(0, '-501.250'), (1, '-518.290')] -[2023-11-28 02:55:08,804][87426] Updated weights for policy 1, policy_version 103150 (0.0012) -[2023-11-28 02:55:09,185][87426] Updated weights for policy 1, policy_version 103160 (0.0011) -[2023-11-28 02:55:09,812][87424] Updated weights for policy 0, policy_version 103366 (0.0012) -[2023-11-28 02:55:10,195][87424] Updated weights for policy 0, policy_version 103376 (0.0009) -[2023-11-28 02:55:10,585][87424] Updated weights for policy 0, policy_version 103386 (0.0012) -[2023-11-28 02:55:11,668][87426] Updated weights for policy 1, policy_version 103170 (0.0014) -[2023-11-28 02:55:12,052][87426] Updated weights for policy 1, policy_version 103180 (0.0012) -[2023-11-28 02:55:12,424][87426] Updated weights for policy 1, policy_version 103190 (0.0010) -[2023-11-28 02:55:12,805][87426] Updated weights for policy 1, policy_version 103200 (0.0010) -[2023-11-28 02:55:12,873][87424] Updated weights for policy 0, policy_version 103396 (0.0010) -[2023-11-28 02:55:13,264][87424] Updated weights for policy 0, policy_version 103406 (0.0008) -[2023-11-28 02:55:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 52887552. Throughput: 0: 2678.9, 1: 2749.2. Samples: 52903016. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:55:13,445][86177] Avg episode reward: [(0, '-498.790'), (1, '-520.990')] -[2023-11-28 02:55:13,636][87424] Updated weights for policy 0, policy_version 103416 (0.0008) -[2023-11-28 02:55:15,348][87426] Updated weights for policy 1, policy_version 103210 (0.0008) -[2023-11-28 02:55:15,720][87426] Updated weights for policy 1, policy_version 103220 (0.0010) -[2023-11-28 02:55:15,831][87424] Updated weights for policy 0, policy_version 103426 (0.0007) -[2023-11-28 02:55:16,102][87426] Updated weights for policy 1, policy_version 103230 (0.0008) -[2023-11-28 02:55:16,219][87424] Updated weights for policy 0, policy_version 103436 (0.0008) -[2023-11-28 02:55:16,598][87424] Updated weights for policy 0, policy_version 103446 (0.0012) -[2023-11-28 02:55:16,982][87424] Updated weights for policy 0, policy_version 103456 (0.0012) -[2023-11-28 02:55:18,229][87426] Updated weights for policy 1, policy_version 103240 (0.0011) -[2023-11-28 02:55:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 52912128. Throughput: 0: 2671.6, 1: 2736.4. Samples: 52926052. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:55:18,445][86177] Avg episode reward: [(0, '-499.990'), (1, '-525.120')] -[2023-11-28 02:55:18,611][87426] Updated weights for policy 1, policy_version 103250 (0.0012) -[2023-11-28 02:55:18,992][87426] Updated weights for policy 1, policy_version 103260 (0.0012) -[2023-11-28 02:55:19,447][87424] Updated weights for policy 0, policy_version 103466 (0.0012) -[2023-11-28 02:55:19,832][87424] Updated weights for policy 0, policy_version 103476 (0.0011) -[2023-11-28 02:55:20,215][87424] Updated weights for policy 0, policy_version 103486 (0.0008) -[2023-11-28 02:55:20,982][87426] Updated weights for policy 1, policy_version 103270 (0.0010) -[2023-11-28 02:55:21,355][87426] Updated weights for policy 1, policy_version 103280 (0.0012) -[2023-11-28 02:55:21,741][87426] Updated weights for policy 1, policy_version 103290 (0.0014) -[2023-11-28 02:55:22,413][87424] Updated weights for policy 0, policy_version 103496 (0.0009) -[2023-11-28 02:55:22,785][87424] Updated weights for policy 0, policy_version 103506 (0.0008) -[2023-11-28 02:55:23,169][87424] Updated weights for policy 0, policy_version 103516 (0.0008) -[2023-11-28 02:55:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 52944896. Throughput: 0: 2685.3, 1: 2709.3. Samples: 52958388. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:55:23,445][86177] Avg episode reward: [(0, '-495.680'), (1, '-516.010')] -[2023-11-28 02:55:24,182][87426] Updated weights for policy 1, policy_version 103300 (0.0011) -[2023-11-28 02:55:24,553][87426] Updated weights for policy 1, policy_version 103310 (0.0008) -[2023-11-28 02:55:24,934][87426] Updated weights for policy 1, policy_version 103320 (0.0007) -[2023-11-28 02:55:24,986][87424] Updated weights for policy 0, policy_version 103526 (0.0010) -[2023-11-28 02:55:25,379][87424] Updated weights for policy 0, policy_version 103536 (0.0011) -[2023-11-28 02:55:25,753][87424] Updated weights for policy 0, policy_version 103546 (0.0012) -[2023-11-28 02:55:27,083][87426] Updated weights for policy 1, policy_version 103330 (0.0010) -[2023-11-28 02:55:27,458][87426] Updated weights for policy 1, policy_version 103340 (0.0008) -[2023-11-28 02:55:27,847][87426] Updated weights for policy 1, policy_version 103350 (0.0008) -[2023-11-28 02:55:27,851][87424] Updated weights for policy 0, policy_version 103556 (0.0010) -[2023-11-28 02:55:28,234][87426] Updated weights for policy 1, policy_version 103360 (0.0008) -[2023-11-28 02:55:28,237][87424] Updated weights for policy 0, policy_version 103566 (0.0007) -[2023-11-28 02:55:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 52969472. Throughput: 0: 2701.0, 1: 2721.3. Samples: 52983916. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:55:28,445][86177] Avg episode reward: [(0, '-496.820'), (1, '-522.530')] -[2023-11-28 02:55:28,631][87424] Updated weights for policy 0, policy_version 103576 (0.0007) -[2023-11-28 02:55:30,604][87426] Updated weights for policy 1, policy_version 103370 (0.0009) -[2023-11-28 02:55:30,942][87424] Updated weights for policy 0, policy_version 103586 (0.0008) -[2023-11-28 02:55:30,979][87426] Updated weights for policy 1, policy_version 103380 (0.0010) -[2023-11-28 02:55:31,331][87424] Updated weights for policy 0, policy_version 103596 (0.0007) -[2023-11-28 02:55:31,363][87426] Updated weights for policy 1, policy_version 103390 (0.0011) -[2023-11-28 02:55:31,713][87424] Updated weights for policy 0, policy_version 103606 (0.0009) -[2023-11-28 02:55:32,085][87424] Updated weights for policy 0, policy_version 103616 (0.0012) -[2023-11-28 02:55:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 52994048. Throughput: 0: 2708.2, 1: 2685.3. Samples: 53007512. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 02:55:33,445][86177] Avg episode reward: [(0, '-498.490'), (1, '-517.130')] -[2023-11-28 02:55:33,575][87426] Updated weights for policy 1, policy_version 103400 (0.0012) -[2023-11-28 02:55:33,967][87426] Updated weights for policy 1, policy_version 103410 (0.0012) -[2023-11-28 02:55:34,086][87424] Updated weights for policy 0, policy_version 103626 (0.0010) -[2023-11-28 02:55:34,339][87426] Updated weights for policy 1, policy_version 103420 (0.0011) -[2023-11-28 02:55:34,473][87424] Updated weights for policy 0, policy_version 103636 (0.0007) -[2023-11-28 02:55:34,848][87424] Updated weights for policy 0, policy_version 103646 (0.0009) -[2023-11-28 02:55:36,462][87426] Updated weights for policy 1, policy_version 103430 (0.0012) -[2023-11-28 02:55:36,846][87426] Updated weights for policy 1, policy_version 103440 (0.0011) -[2023-11-28 02:55:37,157][87424] Updated weights for policy 0, policy_version 103656 (0.0011) -[2023-11-28 02:55:37,226][87426] Updated weights for policy 1, policy_version 103450 (0.0011) -[2023-11-28 02:55:37,540][87424] Updated weights for policy 0, policy_version 103666 (0.0012) -[2023-11-28 02:55:37,914][87424] Updated weights for policy 0, policy_version 103676 (0.0012) -[2023-11-28 02:55:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 53026816. Throughput: 0: 2700.4, 1: 2696.7. Samples: 53040428. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:55:38,445][86177] Avg episode reward: [(0, '-504.570'), (1, '-512.600')] -[2023-11-28 02:55:39,390][87426] Updated weights for policy 1, policy_version 103460 (0.0010) -[2023-11-28 02:55:39,676][87424] Updated weights for policy 0, policy_version 103686 (0.0010) -[2023-11-28 02:55:39,772][87426] Updated weights for policy 1, policy_version 103470 (0.0011) -[2023-11-28 02:55:40,056][87424] Updated weights for policy 0, policy_version 103696 (0.0011) -[2023-11-28 02:55:40,155][87426] Updated weights for policy 1, policy_version 103480 (0.0011) -[2023-11-28 02:55:40,439][87424] Updated weights for policy 0, policy_version 103706 (0.0011) -[2023-11-28 02:55:42,530][87426] Updated weights for policy 1, policy_version 103490 (0.0011) -[2023-11-28 02:55:42,641][87424] Updated weights for policy 0, policy_version 103716 (0.0011) -[2023-11-28 02:55:42,910][87426] Updated weights for policy 1, policy_version 103500 (0.0012) -[2023-11-28 02:55:43,029][87424] Updated weights for policy 0, policy_version 103726 (0.0012) -[2023-11-28 02:55:43,289][87426] Updated weights for policy 1, policy_version 103510 (0.0012) -[2023-11-28 02:55:43,411][87424] Updated weights for policy 0, policy_version 103736 (0.0011) -[2023-11-28 02:55:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 53043200. Throughput: 0: 2707.0, 1: 2661.1. Samples: 53064524. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:55:43,445][86177] Avg episode reward: [(0, '-529.410'), (1, '-508.490')] -[2023-11-28 02:55:43,661][87426] Updated weights for policy 1, policy_version 103520 (0.0012) -[2023-11-28 02:55:45,598][87426] Updated weights for policy 1, policy_version 103530 (0.0011) -[2023-11-28 02:55:45,985][87426] Updated weights for policy 1, policy_version 103540 (0.0012) -[2023-11-28 02:55:45,993][87424] Updated weights for policy 0, policy_version 103746 (0.0012) -[2023-11-28 02:55:46,355][87426] Updated weights for policy 1, policy_version 103550 (0.0012) -[2023-11-28 02:55:46,380][87424] Updated weights for policy 0, policy_version 103756 (0.0010) -[2023-11-28 02:55:46,759][87424] Updated weights for policy 0, policy_version 103766 (0.0009) -[2023-11-28 02:55:47,139][87424] Updated weights for policy 0, policy_version 103776 (0.0012) -[2023-11-28 02:55:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 53075968. Throughput: 0: 2698.1, 1: 2676.6. Samples: 53089544. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:55:48,445][86177] Avg episode reward: [(0, '-528.920'), (1, '-497.040')] -[2023-11-28 02:55:48,774][87426] Updated weights for policy 1, policy_version 103560 (0.0012) -[2023-11-28 02:55:49,155][87426] Updated weights for policy 1, policy_version 103570 (0.0016) -[2023-11-28 02:55:49,534][87426] Updated weights for policy 1, policy_version 103580 (0.0012) -[2023-11-28 02:55:49,653][87424] Updated weights for policy 0, policy_version 103786 (0.0011) -[2023-11-28 02:55:50,036][87424] Updated weights for policy 0, policy_version 103796 (0.0010) -[2023-11-28 02:55:50,414][87424] Updated weights for policy 0, policy_version 103806 (0.0008) -[2023-11-28 02:55:51,561][87426] Updated weights for policy 1, policy_version 103590 (0.0012) -[2023-11-28 02:55:51,929][87426] Updated weights for policy 1, policy_version 103600 (0.0010) -[2023-11-28 02:55:52,316][87426] Updated weights for policy 1, policy_version 103610 (0.0014) -[2023-11-28 02:55:52,349][87424] Updated weights for policy 0, policy_version 103816 (0.0009) -[2023-11-28 02:55:52,725][87424] Updated weights for policy 0, policy_version 103826 (0.0011) -[2023-11-28 02:55:53,105][87424] Updated weights for policy 0, policy_version 103836 (0.0011) -[2023-11-28 02:55:53,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 53108736. Throughput: 0: 2714.1, 1: 2674.0. Samples: 53121864. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:55:53,445][86177] Avg episode reward: [(0, '-524.170'), (1, '-525.660')] -[2023-11-28 02:55:54,687][87426] Updated weights for policy 1, policy_version 103620 (0.0008) -[2023-11-28 02:55:55,071][87426] Updated weights for policy 1, policy_version 103630 (0.0008) -[2023-11-28 02:55:55,079][87424] Updated weights for policy 0, policy_version 103846 (0.0011) -[2023-11-28 02:55:55,441][87426] Updated weights for policy 1, policy_version 103640 (0.0011) -[2023-11-28 02:55:55,463][87424] Updated weights for policy 0, policy_version 103856 (0.0010) -[2023-11-28 02:55:55,848][87424] Updated weights for policy 0, policy_version 103866 (0.0010) -[2023-11-28 02:55:57,378][87426] Updated weights for policy 1, policy_version 103650 (0.0012) -[2023-11-28 02:55:57,619][87424] Updated weights for policy 0, policy_version 103876 (0.0011) -[2023-11-28 02:55:57,746][87426] Updated weights for policy 1, policy_version 103660 (0.0010) -[2023-11-28 02:55:57,994][87424] Updated weights for policy 0, policy_version 103886 (0.0010) -[2023-11-28 02:55:58,127][87426] Updated weights for policy 1, policy_version 103670 (0.0011) -[2023-11-28 02:55:58,385][87424] Updated weights for policy 0, policy_version 103896 (0.0007) -[2023-11-28 02:55:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 53125120. Throughput: 0: 2707.7, 1: 2705.9. Samples: 53146628. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:55:58,445][86177] Avg episode reward: [(0, '-520.890'), (1, '-529.790')] -[2023-11-28 02:55:58,507][87426] Updated weights for policy 1, policy_version 103680 (0.0011) -[2023-11-28 02:56:00,722][87426] Updated weights for policy 1, policy_version 103690 (0.0009) -[2023-11-28 02:56:00,772][87424] Updated weights for policy 0, policy_version 103906 (0.0007) -[2023-11-28 02:56:01,100][87426] Updated weights for policy 1, policy_version 103700 (0.0008) -[2023-11-28 02:56:01,148][87424] Updated weights for policy 0, policy_version 103916 (0.0009) -[2023-11-28 02:56:01,482][87426] Updated weights for policy 1, policy_version 103710 (0.0011) -[2023-11-28 02:56:01,525][87424] Updated weights for policy 0, policy_version 103926 (0.0011) -[2023-11-28 02:56:01,906][87424] Updated weights for policy 0, policy_version 103936 (0.0009) -[2023-11-28 02:56:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 53157888. Throughput: 0: 2722.5, 1: 2728.0. Samples: 53171324. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:56:03,445][86177] Avg episode reward: [(0, '-500.260'), (1, '-528.110')] -[2023-11-28 02:56:03,562][87426] Updated weights for policy 1, policy_version 103720 (0.0012) -[2023-11-28 02:56:03,923][87426] Updated weights for policy 1, policy_version 103730 (0.0011) -[2023-11-28 02:56:04,033][87424] Updated weights for policy 0, policy_version 103946 (0.0007) -[2023-11-28 02:56:04,308][87426] Updated weights for policy 1, policy_version 103740 (0.0008) -[2023-11-28 02:56:04,428][87424] Updated weights for policy 0, policy_version 103956 (0.0007) -[2023-11-28 02:56:04,814][87424] Updated weights for policy 0, policy_version 103966 (0.0009) -[2023-11-28 02:56:06,823][87426] Updated weights for policy 1, policy_version 103750 (0.0012) -[2023-11-28 02:56:06,897][87424] Updated weights for policy 0, policy_version 103976 (0.0011) -[2023-11-28 02:56:07,202][87426] Updated weights for policy 1, policy_version 103760 (0.0012) -[2023-11-28 02:56:07,278][87424] Updated weights for policy 0, policy_version 103986 (0.0009) -[2023-11-28 02:56:07,581][87426] Updated weights for policy 1, policy_version 103770 (0.0009) -[2023-11-28 02:56:07,669][87424] Updated weights for policy 0, policy_version 103996 (0.0008) -[2023-11-28 02:56:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53190656. Throughput: 0: 2734.6, 1: 2725.8. Samples: 53204104. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:56:08,445][86177] Avg episode reward: [(0, '-499.040'), (1, '-533.520')] -[2023-11-28 02:56:09,383][87424] Updated weights for policy 0, policy_version 104006 (0.0010) -[2023-11-28 02:56:09,568][87426] Updated weights for policy 1, policy_version 103780 (0.0009) -[2023-11-28 02:56:09,760][87424] Updated weights for policy 0, policy_version 104016 (0.0011) -[2023-11-28 02:56:09,945][87426] Updated weights for policy 1, policy_version 103790 (0.0011) -[2023-11-28 02:56:10,147][87424] Updated weights for policy 0, policy_version 104026 (0.0010) -[2023-11-28 02:56:10,328][87426] Updated weights for policy 1, policy_version 103800 (0.0012) -[2023-11-28 02:56:12,499][87424] Updated weights for policy 0, policy_version 104036 (0.0011) -[2023-11-28 02:56:12,686][87426] Updated weights for policy 1, policy_version 103810 (0.0012) -[2023-11-28 02:56:12,880][87424] Updated weights for policy 0, policy_version 104046 (0.0010) -[2023-11-28 02:56:13,060][87426] Updated weights for policy 1, policy_version 103820 (0.0011) -[2023-11-28 02:56:13,265][87424] Updated weights for policy 0, policy_version 104056 (0.0009) -[2023-11-28 02:56:13,439][87426] Updated weights for policy 1, policy_version 103830 (0.0009) -[2023-11-28 02:56:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 53207040. Throughput: 0: 2734.0, 1: 2690.2. Samples: 53228008. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:56:13,445][86177] Avg episode reward: [(0, '-498.850'), (1, '-503.580')] -[2023-11-28 02:56:13,822][87426] Updated weights for policy 1, policy_version 103840 (0.0008) -[2023-11-28 02:56:15,257][87424] Updated weights for policy 0, policy_version 104066 (0.0012) -[2023-11-28 02:56:15,475][87426] Updated weights for policy 1, policy_version 103850 (0.0010) -[2023-11-28 02:56:15,627][87424] Updated weights for policy 0, policy_version 104076 (0.0011) -[2023-11-28 02:56:15,859][87426] Updated weights for policy 1, policy_version 103860 (0.0011) -[2023-11-28 02:56:16,015][87424] Updated weights for policy 0, policy_version 104086 (0.0012) -[2023-11-28 02:56:16,245][87426] Updated weights for policy 1, policy_version 103870 (0.0012) -[2023-11-28 02:56:16,392][87424] Updated weights for policy 0, policy_version 104096 (0.0011) -[2023-11-28 02:56:18,092][87424] Updated weights for policy 0, policy_version 104106 (0.0011) -[2023-11-28 02:56:18,297][87426] Updated weights for policy 1, policy_version 103880 (0.0012) -[2023-11-28 02:56:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 53239808. Throughput: 0: 2754.0, 1: 2705.1. Samples: 53253172. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:56:18,445][86177] Avg episode reward: [(0, '-507.430'), (1, '-501.330')] -[2023-11-28 02:56:18,487][87424] Updated weights for policy 0, policy_version 104116 (0.0009) -[2023-11-28 02:56:18,678][87426] Updated weights for policy 1, policy_version 103890 (0.0012) -[2023-11-28 02:56:18,867][87424] Updated weights for policy 0, policy_version 104126 (0.0008) -[2023-11-28 02:56:18,940][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000104128_26656768.pth... -[2023-11-28 02:56:18,971][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000101568_26001408.pth -[2023-11-28 02:56:19,060][87426] Updated weights for policy 1, policy_version 103900 (0.0009) -[2023-11-28 02:56:19,212][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000103904_26599424.pth... -[2023-11-28 02:56:19,259][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000101344_25944064.pth -[2023-11-28 02:56:21,077][87424] Updated weights for policy 0, policy_version 104136 (0.0008) -[2023-11-28 02:56:21,476][87424] Updated weights for policy 0, policy_version 104146 (0.0011) -[2023-11-28 02:56:21,596][87426] Updated weights for policy 1, policy_version 103910 (0.0009) -[2023-11-28 02:56:21,859][87424] Updated weights for policy 0, policy_version 104156 (0.0011) -[2023-11-28 02:56:21,973][87426] Updated weights for policy 1, policy_version 103920 (0.0012) -[2023-11-28 02:56:22,353][87426] Updated weights for policy 1, policy_version 103930 (0.0010) -[2023-11-28 02:56:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53272576. Throughput: 0: 2753.9, 1: 2715.8. Samples: 53286564. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:56:23,445][86177] Avg episode reward: [(0, '-508.330'), (1, '-503.260')] -[2023-11-28 02:56:24,060][87424] Updated weights for policy 0, policy_version 104166 (0.0011) -[2023-11-28 02:56:24,440][87424] Updated weights for policy 0, policy_version 104176 (0.0012) -[2023-11-28 02:56:24,828][87424] Updated weights for policy 0, policy_version 104186 (0.0011) -[2023-11-28 02:56:24,880][87426] Updated weights for policy 1, policy_version 103940 (0.0010) -[2023-11-28 02:56:25,263][87426] Updated weights for policy 1, policy_version 103950 (0.0010) -[2023-11-28 02:56:25,646][87426] Updated weights for policy 1, policy_version 103960 (0.0007) -[2023-11-28 02:56:27,036][87424] Updated weights for policy 0, policy_version 104196 (0.0008) -[2023-11-28 02:56:27,415][87424] Updated weights for policy 0, policy_version 104206 (0.0007) -[2023-11-28 02:56:27,437][87426] Updated weights for policy 1, policy_version 103970 (0.0007) -[2023-11-28 02:56:27,806][87424] Updated weights for policy 0, policy_version 104216 (0.0007) -[2023-11-28 02:56:27,818][87426] Updated weights for policy 1, policy_version 103980 (0.0007) -[2023-11-28 02:56:28,202][87426] Updated weights for policy 1, policy_version 103990 (0.0007) -[2023-11-28 02:56:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 53297152. Throughput: 0: 2750.3, 1: 2735.7. Samples: 53311396. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:56:28,445][86177] Avg episode reward: [(0, '-511.260'), (1, '-505.650')] -[2023-11-28 02:56:28,577][87426] Updated weights for policy 1, policy_version 104000 (0.0007) -[2023-11-28 02:56:29,701][87424] Updated weights for policy 0, policy_version 104226 (0.0009) -[2023-11-28 02:56:30,090][87424] Updated weights for policy 0, policy_version 104236 (0.0010) -[2023-11-28 02:56:30,163][87426] Updated weights for policy 1, policy_version 104010 (0.0009) -[2023-11-28 02:56:30,460][87424] Updated weights for policy 0, policy_version 104246 (0.0008) -[2023-11-28 02:56:30,538][87426] Updated weights for policy 1, policy_version 104020 (0.0009) -[2023-11-28 02:56:30,843][87424] Updated weights for policy 0, policy_version 104256 (0.0012) -[2023-11-28 02:56:30,915][87426] Updated weights for policy 1, policy_version 104030 (0.0012) -[2023-11-28 02:56:33,148][87426] Updated weights for policy 1, policy_version 104040 (0.0011) -[2023-11-28 02:56:33,393][87424] Updated weights for policy 0, policy_version 104266 (0.0011) -[2023-11-28 02:56:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53321728. Throughput: 0: 2755.8, 1: 2727.9. Samples: 53336312. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:56:33,445][86177] Avg episode reward: [(0, '-511.680'), (1, '-507.250')] -[2023-11-28 02:56:33,517][87426] Updated weights for policy 1, policy_version 104050 (0.0011) -[2023-11-28 02:56:33,778][87424] Updated weights for policy 0, policy_version 104276 (0.0011) -[2023-11-28 02:56:33,903][87426] Updated weights for policy 1, policy_version 104060 (0.0008) -[2023-11-28 02:56:34,167][87424] Updated weights for policy 0, policy_version 104286 (0.0012) -[2023-11-28 02:56:36,113][87424] Updated weights for policy 0, policy_version 104296 (0.0011) -[2023-11-28 02:56:36,310][87426] Updated weights for policy 1, policy_version 104070 (0.0008) -[2023-11-28 02:56:36,504][87424] Updated weights for policy 0, policy_version 104306 (0.0008) -[2023-11-28 02:56:36,694][87426] Updated weights for policy 1, policy_version 104080 (0.0011) -[2023-11-28 02:56:36,900][87424] Updated weights for policy 0, policy_version 104316 (0.0010) -[2023-11-28 02:56:37,070][87426] Updated weights for policy 1, policy_version 104090 (0.0011) -[2023-11-28 02:56:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53354496. Throughput: 0: 2788.3, 1: 2713.1. Samples: 53369424. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 02:56:38,445][86177] Avg episode reward: [(0, '-501.870'), (1, '-510.220')] -[2023-11-28 02:56:38,864][87424] Updated weights for policy 0, policy_version 104326 (0.0012) -[2023-11-28 02:56:39,243][87424] Updated weights for policy 0, policy_version 104336 (0.0011) -[2023-11-28 02:56:39,277][87426] Updated weights for policy 1, policy_version 104100 (0.0010) -[2023-11-28 02:56:39,645][87424] Updated weights for policy 0, policy_version 104346 (0.0012) -[2023-11-28 02:56:39,655][87426] Updated weights for policy 1, policy_version 104110 (0.0008) -[2023-11-28 02:56:40,035][87426] Updated weights for policy 1, policy_version 104120 (0.0011) -[2023-11-28 02:56:41,892][87424] Updated weights for policy 0, policy_version 104356 (0.0011) -[2023-11-28 02:56:42,276][87424] Updated weights for policy 0, policy_version 104366 (0.0010) -[2023-11-28 02:56:42,366][87426] Updated weights for policy 1, policy_version 104130 (0.0011) -[2023-11-28 02:56:42,647][87424] Updated weights for policy 0, policy_version 104376 (0.0008) -[2023-11-28 02:56:42,737][87426] Updated weights for policy 1, policy_version 104140 (0.0012) -[2023-11-28 02:56:43,119][87426] Updated weights for policy 1, policy_version 104150 (0.0011) -[2023-11-28 02:56:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 53379072. Throughput: 0: 2804.5, 1: 2698.4. Samples: 53394260. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:56:43,445][86177] Avg episode reward: [(0, '-502.920'), (1, '-509.030')] -[2023-11-28 02:56:43,500][87426] Updated weights for policy 1, policy_version 104160 (0.0012) -[2023-11-28 02:56:45,131][87424] Updated weights for policy 0, policy_version 104386 (0.0010) -[2023-11-28 02:56:45,520][87424] Updated weights for policy 0, policy_version 104396 (0.0009) -[2023-11-28 02:56:45,554][87426] Updated weights for policy 1, policy_version 104170 (0.0010) -[2023-11-28 02:56:45,894][87424] Updated weights for policy 0, policy_version 104406 (0.0007) -[2023-11-28 02:56:45,935][87426] Updated weights for policy 1, policy_version 104180 (0.0010) -[2023-11-28 02:56:46,283][87424] Updated weights for policy 0, policy_version 104416 (0.0008) -[2023-11-28 02:56:46,311][87426] Updated weights for policy 1, policy_version 104190 (0.0008) -[2023-11-28 02:56:48,356][87424] Updated weights for policy 0, policy_version 104426 (0.0009) -[2023-11-28 02:56:48,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53403648. Throughput: 0: 2790.5, 1: 2703.6. Samples: 53418560. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:56:48,446][86177] Avg episode reward: [(0, '-502.520'), (1, '-498.330')] -[2023-11-28 02:56:48,687][87426] Updated weights for policy 1, policy_version 104200 (0.0009) -[2023-11-28 02:56:48,733][87424] Updated weights for policy 0, policy_version 104436 (0.0010) -[2023-11-28 02:56:49,065][87426] Updated weights for policy 1, policy_version 104210 (0.0011) -[2023-11-28 02:56:49,113][87424] Updated weights for policy 0, policy_version 104446 (0.0011) -[2023-11-28 02:56:49,450][87426] Updated weights for policy 1, policy_version 104220 (0.0011) -[2023-11-28 02:56:51,194][87424] Updated weights for policy 0, policy_version 104456 (0.0008) -[2023-11-28 02:56:51,572][87424] Updated weights for policy 0, policy_version 104466 (0.0009) -[2023-11-28 02:56:51,793][87426] Updated weights for policy 1, policy_version 104230 (0.0011) -[2023-11-28 02:56:51,960][87424] Updated weights for policy 0, policy_version 104476 (0.0010) -[2023-11-28 02:56:52,164][87426] Updated weights for policy 1, policy_version 104240 (0.0011) -[2023-11-28 02:56:52,539][87426] Updated weights for policy 1, policy_version 104250 (0.0009) -[2023-11-28 02:56:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53436416. Throughput: 0: 2779.7, 1: 2702.2. Samples: 53450792. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:56:53,445][86177] Avg episode reward: [(0, '-520.310'), (1, '-493.410')] -[2023-11-28 02:56:53,446][87320] Saving new best policy, reward=-493.410! -[2023-11-28 02:56:54,308][87424] Updated weights for policy 0, policy_version 104486 (0.0009) -[2023-11-28 02:56:54,705][87424] Updated weights for policy 0, policy_version 104496 (0.0008) -[2023-11-28 02:56:54,712][87426] Updated weights for policy 1, policy_version 104260 (0.0008) -[2023-11-28 02:56:55,080][87424] Updated weights for policy 0, policy_version 104506 (0.0010) -[2023-11-28 02:56:55,087][87426] Updated weights for policy 1, policy_version 104270 (0.0012) -[2023-11-28 02:56:55,463][87426] Updated weights for policy 1, policy_version 104280 (0.0011) -[2023-11-28 02:56:57,184][87424] Updated weights for policy 0, policy_version 104516 (0.0008) -[2023-11-28 02:56:57,565][87424] Updated weights for policy 0, policy_version 104526 (0.0007) -[2023-11-28 02:56:57,834][87426] Updated weights for policy 1, policy_version 104290 (0.0012) -[2023-11-28 02:56:57,940][87424] Updated weights for policy 0, policy_version 104536 (0.0007) -[2023-11-28 02:56:58,205][87426] Updated weights for policy 1, policy_version 104300 (0.0011) -[2023-11-28 02:56:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 53460992. Throughput: 0: 2760.7, 1: 2721.2. Samples: 53474696. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:56:58,446][86177] Avg episode reward: [(0, '-521.080'), (1, '-491.830')] -[2023-11-28 02:56:58,589][87426] Updated weights for policy 1, policy_version 104310 (0.0012) -[2023-11-28 02:56:58,962][87320] Saving new best policy, reward=-491.830! -[2023-11-28 02:56:58,965][87426] Updated weights for policy 1, policy_version 104320 (0.0012) -[2023-11-28 02:56:59,889][87424] Updated weights for policy 0, policy_version 104546 (0.0008) -[2023-11-28 02:57:00,266][87424] Updated weights for policy 0, policy_version 104556 (0.0008) -[2023-11-28 02:57:00,647][87424] Updated weights for policy 0, policy_version 104566 (0.0010) -[2023-11-28 02:57:01,028][87424] Updated weights for policy 0, policy_version 104576 (0.0009) -[2023-11-28 02:57:01,094][87426] Updated weights for policy 1, policy_version 104330 (0.0011) -[2023-11-28 02:57:01,463][87426] Updated weights for policy 1, policy_version 104340 (0.0012) -[2023-11-28 02:57:01,851][87426] Updated weights for policy 1, policy_version 104350 (0.0012) -[2023-11-28 02:57:03,091][87424] Updated weights for policy 0, policy_version 104586 (0.0009) -[2023-11-28 02:57:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53485568. Throughput: 0: 2753.5, 1: 2718.4. Samples: 53499408. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:57:03,445][86177] Avg episode reward: [(0, '-524.020'), (1, '-492.170')] -[2023-11-28 02:57:03,467][87424] Updated weights for policy 0, policy_version 104596 (0.0007) -[2023-11-28 02:57:03,863][87424] Updated weights for policy 0, policy_version 104606 (0.0008) -[2023-11-28 02:57:03,863][87426] Updated weights for policy 1, policy_version 104360 (0.0011) -[2023-11-28 02:57:04,242][87426] Updated weights for policy 1, policy_version 104370 (0.0008) -[2023-11-28 02:57:04,623][87426] Updated weights for policy 1, policy_version 104380 (0.0010) -[2023-11-28 02:57:05,714][87424] Updated weights for policy 0, policy_version 104616 (0.0008) -[2023-11-28 02:57:06,109][87424] Updated weights for policy 0, policy_version 104626 (0.0007) -[2023-11-28 02:57:06,487][87424] Updated weights for policy 0, policy_version 104636 (0.0007) -[2023-11-28 02:57:06,747][87426] Updated weights for policy 1, policy_version 104390 (0.0011) -[2023-11-28 02:57:07,121][87426] Updated weights for policy 1, policy_version 104400 (0.0010) -[2023-11-28 02:57:07,499][87426] Updated weights for policy 1, policy_version 104410 (0.0007) -[2023-11-28 02:57:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53518336. Throughput: 0: 2774.6, 1: 2707.2. Samples: 53533244. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:57:08,445][86177] Avg episode reward: [(0, '-524.480'), (1, '-495.250')] -[2023-11-28 02:57:08,658][87424] Updated weights for policy 0, policy_version 104646 (0.0010) -[2023-11-28 02:57:09,039][87424] Updated weights for policy 0, policy_version 104656 (0.0011) -[2023-11-28 02:57:09,432][87424] Updated weights for policy 0, policy_version 104666 (0.0012) -[2023-11-28 02:57:09,698][87426] Updated weights for policy 1, policy_version 104420 (0.0011) -[2023-11-28 02:57:10,082][87426] Updated weights for policy 1, policy_version 104430 (0.0011) -[2023-11-28 02:57:10,461][87426] Updated weights for policy 1, policy_version 104440 (0.0012) -[2023-11-28 02:57:11,675][87424] Updated weights for policy 0, policy_version 104676 (0.0011) -[2023-11-28 02:57:12,051][87424] Updated weights for policy 0, policy_version 104686 (0.0011) -[2023-11-28 02:57:12,440][87424] Updated weights for policy 0, policy_version 104696 (0.0010) -[2023-11-28 02:57:12,715][87426] Updated weights for policy 1, policy_version 104450 (0.0011) -[2023-11-28 02:57:13,092][87426] Updated weights for policy 1, policy_version 104460 (0.0011) -[2023-11-28 02:57:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 53542912. Throughput: 0: 2774.0, 1: 2695.4. Samples: 53557520. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:57:13,445][86177] Avg episode reward: [(0, '-504.310'), (1, '-494.720')] -[2023-11-28 02:57:13,475][87426] Updated weights for policy 1, policy_version 104470 (0.0009) -[2023-11-28 02:57:13,860][87426] Updated weights for policy 1, policy_version 104480 (0.0010) -[2023-11-28 02:57:14,419][87424] Updated weights for policy 0, policy_version 104706 (0.0011) -[2023-11-28 02:57:14,792][87424] Updated weights for policy 0, policy_version 104716 (0.0012) -[2023-11-28 02:57:15,165][87424] Updated weights for policy 0, policy_version 104726 (0.0012) -[2023-11-28 02:57:15,546][87424] Updated weights for policy 0, policy_version 104736 (0.0012) -[2023-11-28 02:57:16,173][87426] Updated weights for policy 1, policy_version 104490 (0.0012) -[2023-11-28 02:57:16,545][87426] Updated weights for policy 1, policy_version 104500 (0.0012) -[2023-11-28 02:57:16,923][87426] Updated weights for policy 1, policy_version 104510 (0.0012) -[2023-11-28 02:57:18,085][87424] Updated weights for policy 0, policy_version 104746 (0.0012) -[2023-11-28 02:57:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53567488. Throughput: 0: 2755.3, 1: 2698.9. Samples: 53581752. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:57:18,445][86177] Avg episode reward: [(0, '-502.690'), (1, '-497.830')] -[2023-11-28 02:57:18,464][87424] Updated weights for policy 0, policy_version 104756 (0.0012) -[2023-11-28 02:57:18,763][87426] Updated weights for policy 1, policy_version 104520 (0.0011) -[2023-11-28 02:57:18,848][87424] Updated weights for policy 0, policy_version 104766 (0.0011) -[2023-11-28 02:57:19,134][87426] Updated weights for policy 1, policy_version 104530 (0.0010) -[2023-11-28 02:57:19,512][87426] Updated weights for policy 1, policy_version 104540 (0.0008) -[2023-11-28 02:57:21,154][87424] Updated weights for policy 0, policy_version 104776 (0.0012) -[2023-11-28 02:57:21,544][87424] Updated weights for policy 0, policy_version 104786 (0.0012) -[2023-11-28 02:57:21,916][87426] Updated weights for policy 1, policy_version 104550 (0.0009) -[2023-11-28 02:57:21,920][87424] Updated weights for policy 0, policy_version 104796 (0.0011) -[2023-11-28 02:57:22,281][87426] Updated weights for policy 1, policy_version 104560 (0.0012) -[2023-11-28 02:57:22,660][87426] Updated weights for policy 1, policy_version 104570 (0.0008) -[2023-11-28 02:57:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53600256. Throughput: 0: 2723.0, 1: 2716.3. Samples: 53614192. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:57:23,446][86177] Avg episode reward: [(0, '-503.860'), (1, '-495.550')] -[2023-11-28 02:57:24,206][87424] Updated weights for policy 0, policy_version 104806 (0.0011) -[2023-11-28 02:57:24,584][87424] Updated weights for policy 0, policy_version 104816 (0.0011) -[2023-11-28 02:57:24,803][87426] Updated weights for policy 1, policy_version 104580 (0.0010) -[2023-11-28 02:57:24,971][87424] Updated weights for policy 0, policy_version 104826 (0.0012) -[2023-11-28 02:57:25,183][87426] Updated weights for policy 1, policy_version 104590 (0.0008) -[2023-11-28 02:57:25,564][87426] Updated weights for policy 1, policy_version 104600 (0.0011) -[2023-11-28 02:57:27,098][87424] Updated weights for policy 0, policy_version 104836 (0.0010) -[2023-11-28 02:57:27,394][87426] Updated weights for policy 1, policy_version 104610 (0.0011) -[2023-11-28 02:57:27,472][87424] Updated weights for policy 0, policy_version 104846 (0.0010) -[2023-11-28 02:57:27,773][87426] Updated weights for policy 1, policy_version 104620 (0.0010) -[2023-11-28 02:57:27,867][87424] Updated weights for policy 0, policy_version 104856 (0.0008) -[2023-11-28 02:57:28,159][87426] Updated weights for policy 1, policy_version 104630 (0.0012) -[2023-11-28 02:57:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53624832. Throughput: 0: 2708.1, 1: 2751.0. Samples: 53639920. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:57:28,445][86177] Avg episode reward: [(0, '-503.930'), (1, '-492.810')] -[2023-11-28 02:57:28,534][87426] Updated weights for policy 1, policy_version 104640 (0.0012) -[2023-11-28 02:57:29,525][87424] Updated weights for policy 0, policy_version 104866 (0.0008) -[2023-11-28 02:57:29,905][87424] Updated weights for policy 0, policy_version 104876 (0.0012) -[2023-11-28 02:57:30,290][87424] Updated weights for policy 0, policy_version 104886 (0.0010) -[2023-11-28 02:57:30,676][87424] Updated weights for policy 0, policy_version 104896 (0.0009) -[2023-11-28 02:57:30,808][87426] Updated weights for policy 1, policy_version 104650 (0.0016) -[2023-11-28 02:57:31,184][87426] Updated weights for policy 1, policy_version 104660 (0.0012) -[2023-11-28 02:57:31,565][87426] Updated weights for policy 1, policy_version 104670 (0.0011) -[2023-11-28 02:57:33,028][87424] Updated weights for policy 0, policy_version 104906 (0.0011) -[2023-11-28 02:57:33,415][87424] Updated weights for policy 0, policy_version 104916 (0.0011) -[2023-11-28 02:57:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53649408. Throughput: 0: 2747.5, 1: 2729.8. Samples: 53665036. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:57:33,445][86177] Avg episode reward: [(0, '-505.100'), (1, '-493.540')] -[2023-11-28 02:57:33,803][87424] Updated weights for policy 0, policy_version 104926 (0.0011) -[2023-11-28 02:57:34,171][87426] Updated weights for policy 1, policy_version 104680 (0.0008) -[2023-11-28 02:57:34,551][87426] Updated weights for policy 1, policy_version 104690 (0.0009) -[2023-11-28 02:57:34,929][87426] Updated weights for policy 1, policy_version 104700 (0.0008) -[2023-11-28 02:57:35,830][87424] Updated weights for policy 0, policy_version 104936 (0.0008) -[2023-11-28 02:57:36,219][87424] Updated weights for policy 0, policy_version 104946 (0.0010) -[2023-11-28 02:57:36,601][87424] Updated weights for policy 0, policy_version 104956 (0.0008) -[2023-11-28 02:57:36,692][87426] Updated weights for policy 1, policy_version 104710 (0.0008) -[2023-11-28 02:57:37,071][87426] Updated weights for policy 1, policy_version 104720 (0.0010) -[2023-11-28 02:57:37,446][87426] Updated weights for policy 1, policy_version 104730 (0.0010) -[2023-11-28 02:57:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53682176. Throughput: 0: 2733.5, 1: 2750.3. Samples: 53697564. Policy #0 lag: (min: 29.0, avg: 50.0, max: 62.0) -[2023-11-28 02:57:38,445][86177] Avg episode reward: [(0, '-506.260'), (1, '-492.820')] -[2023-11-28 02:57:39,018][87424] Updated weights for policy 0, policy_version 104966 (0.0010) -[2023-11-28 02:57:39,400][87424] Updated weights for policy 0, policy_version 104976 (0.0012) -[2023-11-28 02:57:39,783][87424] Updated weights for policy 0, policy_version 104986 (0.0011) -[2023-11-28 02:57:39,813][87426] Updated weights for policy 1, policy_version 104740 (0.0009) -[2023-11-28 02:57:40,211][87426] Updated weights for policy 1, policy_version 104750 (0.0008) -[2023-11-28 02:57:40,581][87426] Updated weights for policy 1, policy_version 104760 (0.0009) -[2023-11-28 02:57:41,586][87424] Updated weights for policy 0, policy_version 104996 (0.0010) -[2023-11-28 02:57:41,969][87424] Updated weights for policy 0, policy_version 105006 (0.0010) -[2023-11-28 02:57:42,362][87424] Updated weights for policy 0, policy_version 105016 (0.0010) -[2023-11-28 02:57:42,388][87426] Updated weights for policy 1, policy_version 104770 (0.0010) -[2023-11-28 02:57:42,774][87426] Updated weights for policy 1, policy_version 104780 (0.0010) -[2023-11-28 02:57:43,158][87426] Updated weights for policy 1, policy_version 104790 (0.0012) -[2023-11-28 02:57:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53706752. Throughput: 0: 2739.2, 1: 2737.6. Samples: 53721152. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:57:43,445][86177] Avg episode reward: [(0, '-500.320'), (1, '-494.610')] -[2023-11-28 02:57:43,529][87426] Updated weights for policy 1, policy_version 104800 (0.0012) -[2023-11-28 02:57:44,873][87424] Updated weights for policy 0, policy_version 105026 (0.0011) -[2023-11-28 02:57:45,250][87424] Updated weights for policy 0, policy_version 105036 (0.0012) -[2023-11-28 02:57:45,633][87424] Updated weights for policy 0, policy_version 105046 (0.0012) -[2023-11-28 02:57:45,877][87426] Updated weights for policy 1, policy_version 104810 (0.0012) -[2023-11-28 02:57:46,016][87424] Updated weights for policy 0, policy_version 105056 (0.0012) -[2023-11-28 02:57:46,255][87426] Updated weights for policy 1, policy_version 104820 (0.0012) -[2023-11-28 02:57:46,632][87426] Updated weights for policy 1, policy_version 104830 (0.0012) -[2023-11-28 02:57:48,122][87424] Updated weights for policy 0, policy_version 105066 (0.0012) -[2023-11-28 02:57:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 53731328. Throughput: 0: 2727.2, 1: 2738.1. Samples: 53745344. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:57:48,445][86177] Avg episode reward: [(0, '-500.950'), (1, '-500.270')] -[2023-11-28 02:57:48,508][87424] Updated weights for policy 0, policy_version 105076 (0.0012) -[2023-11-28 02:57:48,914][87424] Updated weights for policy 0, policy_version 105086 (0.0011) -[2023-11-28 02:57:49,256][87426] Updated weights for policy 1, policy_version 104840 (0.0012) -[2023-11-28 02:57:49,631][87426] Updated weights for policy 1, policy_version 104850 (0.0010) -[2023-11-28 02:57:50,010][87426] Updated weights for policy 1, policy_version 104860 (0.0011) -[2023-11-28 02:57:51,181][87424] Updated weights for policy 0, policy_version 105096 (0.0009) -[2023-11-28 02:57:51,561][87424] Updated weights for policy 0, policy_version 105106 (0.0008) -[2023-11-28 02:57:51,947][87424] Updated weights for policy 0, policy_version 105116 (0.0009) -[2023-11-28 02:57:52,300][87426] Updated weights for policy 1, policy_version 104870 (0.0011) -[2023-11-28 02:57:52,680][87426] Updated weights for policy 1, policy_version 104880 (0.0012) -[2023-11-28 02:57:53,063][87426] Updated weights for policy 1, policy_version 104890 (0.0011) -[2023-11-28 02:57:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 53764096. Throughput: 0: 2711.6, 1: 2737.4. Samples: 53778452. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:57:53,445][86177] Avg episode reward: [(0, '-508.170'), (1, '-503.030')] -[2023-11-28 02:57:54,030][87424] Updated weights for policy 0, policy_version 105126 (0.0012) -[2023-11-28 02:57:54,413][87424] Updated weights for policy 0, policy_version 105136 (0.0012) -[2023-11-28 02:57:54,789][87424] Updated weights for policy 0, policy_version 105146 (0.0012) -[2023-11-28 02:57:55,540][87426] Updated weights for policy 1, policy_version 104900 (0.0010) -[2023-11-28 02:57:55,923][87426] Updated weights for policy 1, policy_version 104910 (0.0012) -[2023-11-28 02:57:56,302][87426] Updated weights for policy 1, policy_version 104920 (0.0012) -[2023-11-28 02:57:57,225][87424] Updated weights for policy 0, policy_version 105156 (0.0012) -[2023-11-28 02:57:57,615][87424] Updated weights for policy 0, policy_version 105166 (0.0012) -[2023-11-28 02:57:57,982][87424] Updated weights for policy 0, policy_version 105176 (0.0012) -[2023-11-28 02:57:58,362][87426] Updated weights for policy 1, policy_version 104930 (0.0011) -[2023-11-28 02:57:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53788672. Throughput: 0: 2706.9, 1: 2740.8. Samples: 53802668. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:57:58,445][86177] Avg episode reward: [(0, '-509.330'), (1, '-503.970')] -[2023-11-28 02:57:58,746][87426] Updated weights for policy 1, policy_version 104940 (0.0007) -[2023-11-28 02:57:59,130][87426] Updated weights for policy 1, policy_version 104950 (0.0010) -[2023-11-28 02:57:59,517][87426] Updated weights for policy 1, policy_version 104960 (0.0010) -[2023-11-28 02:58:00,308][87424] Updated weights for policy 0, policy_version 105186 (0.0012) -[2023-11-28 02:58:00,692][87424] Updated weights for policy 0, policy_version 105196 (0.0009) -[2023-11-28 02:58:01,087][87424] Updated weights for policy 0, policy_version 105206 (0.0008) -[2023-11-28 02:58:01,474][87424] Updated weights for policy 0, policy_version 105216 (0.0007) -[2023-11-28 02:58:01,869][87426] Updated weights for policy 1, policy_version 104970 (0.0010) -[2023-11-28 02:58:02,258][87426] Updated weights for policy 1, policy_version 104980 (0.0011) -[2023-11-28 02:58:02,633][87426] Updated weights for policy 1, policy_version 104990 (0.0012) -[2023-11-28 02:58:03,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53813248. Throughput: 0: 2716.9, 1: 2717.8. Samples: 53826312. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:58:03,446][86177] Avg episode reward: [(0, '-518.260'), (1, '-546.690')] -[2023-11-28 02:58:03,727][87424] Updated weights for policy 0, policy_version 105226 (0.0011) -[2023-11-28 02:58:04,116][87424] Updated weights for policy 0, policy_version 105236 (0.0012) -[2023-11-28 02:58:04,493][87424] Updated weights for policy 0, policy_version 105246 (0.0010) -[2023-11-28 02:58:05,085][87426] Updated weights for policy 1, policy_version 105000 (0.0011) -[2023-11-28 02:58:05,465][87426] Updated weights for policy 1, policy_version 105010 (0.0012) -[2023-11-28 02:58:05,838][87426] Updated weights for policy 1, policy_version 105020 (0.0011) -[2023-11-28 02:58:06,765][87424] Updated weights for policy 0, policy_version 105256 (0.0010) -[2023-11-28 02:58:07,147][87424] Updated weights for policy 0, policy_version 105266 (0.0011) -[2023-11-28 02:58:07,530][87424] Updated weights for policy 0, policy_version 105276 (0.0011) -[2023-11-28 02:58:07,663][87426] Updated weights for policy 1, policy_version 105030 (0.0011) -[2023-11-28 02:58:08,044][87426] Updated weights for policy 1, policy_version 105040 (0.0007) -[2023-11-28 02:58:08,421][87426] Updated weights for policy 1, policy_version 105050 (0.0010) -[2023-11-28 02:58:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 53837824. Throughput: 0: 2707.1, 1: 2719.3. Samples: 53858380. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:58:08,445][86177] Avg episode reward: [(0, '-533.730'), (1, '-543.260')] -[2023-11-28 02:58:10,065][87424] Updated weights for policy 0, policy_version 105286 (0.0010) -[2023-11-28 02:58:10,128][87426] Updated weights for policy 1, policy_version 105060 (0.0011) -[2023-11-28 02:58:10,440][87424] Updated weights for policy 0, policy_version 105296 (0.0009) -[2023-11-28 02:58:10,496][87426] Updated weights for policy 1, policy_version 105070 (0.0010) -[2023-11-28 02:58:10,816][87424] Updated weights for policy 0, policy_version 105306 (0.0009) -[2023-11-28 02:58:10,875][87426] Updated weights for policy 1, policy_version 105080 (0.0008) -[2023-11-28 02:58:13,053][87424] Updated weights for policy 0, policy_version 105316 (0.0009) -[2023-11-28 02:58:13,305][87426] Updated weights for policy 1, policy_version 105090 (0.0009) -[2023-11-28 02:58:13,433][87424] Updated weights for policy 0, policy_version 105326 (0.0011) -[2023-11-28 02:58:13,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 53862400. Throughput: 0: 2699.7, 1: 2690.6. Samples: 53882484. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:58:13,445][86177] Avg episode reward: [(0, '-525.470'), (1, '-547.780')] -[2023-11-28 02:58:13,674][87426] Updated weights for policy 1, policy_version 105100 (0.0009) -[2023-11-28 02:58:13,817][87424] Updated weights for policy 0, policy_version 105336 (0.0011) -[2023-11-28 02:58:14,053][87426] Updated weights for policy 1, policy_version 105110 (0.0009) -[2023-11-28 02:58:14,429][87426] Updated weights for policy 1, policy_version 105120 (0.0007) -[2023-11-28 02:58:16,024][87424] Updated weights for policy 0, policy_version 105346 (0.0012) -[2023-11-28 02:58:16,287][87426] Updated weights for policy 1, policy_version 105130 (0.0012) -[2023-11-28 02:58:16,402][87424] Updated weights for policy 0, policy_version 105356 (0.0011) -[2023-11-28 02:58:16,677][87426] Updated weights for policy 1, policy_version 105140 (0.0012) -[2023-11-28 02:58:16,781][87424] Updated weights for policy 0, policy_version 105366 (0.0008) -[2023-11-28 02:58:17,057][87426] Updated weights for policy 1, policy_version 105150 (0.0012) -[2023-11-28 02:58:17,175][87424] Updated weights for policy 0, policy_version 105376 (0.0007) -[2023-11-28 02:58:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 53895168. Throughput: 0: 2659.2, 1: 2710.4. Samples: 53906668. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:58:18,445][86177] Avg episode reward: [(0, '-520.970'), (1, '-546.820')] -[2023-11-28 02:58:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000105152_26918912.pth... -[2023-11-28 02:58:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000105376_26976256.pth... -[2023-11-28 02:58:18,485][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000102624_26271744.pth -[2023-11-28 02:58:18,502][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000102848_26329088.pth -[2023-11-28 02:58:19,245][87426] Updated weights for policy 1, policy_version 105160 (0.0012) -[2023-11-28 02:58:19,264][87424] Updated weights for policy 0, policy_version 105386 (0.0010) -[2023-11-28 02:58:19,620][87426] Updated weights for policy 1, policy_version 105170 (0.0012) -[2023-11-28 02:58:19,646][87424] Updated weights for policy 0, policy_version 105396 (0.0010) -[2023-11-28 02:58:19,992][87426] Updated weights for policy 1, policy_version 105180 (0.0012) -[2023-11-28 02:58:20,024][87424] Updated weights for policy 0, policy_version 105406 (0.0011) -[2023-11-28 02:58:22,520][87426] Updated weights for policy 1, policy_version 105190 (0.0011) -[2023-11-28 02:58:22,526][87424] Updated weights for policy 0, policy_version 105416 (0.0012) -[2023-11-28 02:58:22,894][87426] Updated weights for policy 1, policy_version 105200 (0.0011) -[2023-11-28 02:58:22,908][87424] Updated weights for policy 0, policy_version 105426 (0.0012) -[2023-11-28 02:58:23,279][87426] Updated weights for policy 1, policy_version 105210 (0.0011) -[2023-11-28 02:58:23,292][87424] Updated weights for policy 0, policy_version 105436 (0.0011) -[2023-11-28 02:58:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 53919744. Throughput: 0: 2665.5, 1: 2696.4. Samples: 53938848. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:58:23,445][86177] Avg episode reward: [(0, '-515.750'), (1, '-550.860')] -[2023-11-28 02:58:25,103][87426] Updated weights for policy 1, policy_version 105220 (0.0010) -[2023-11-28 02:58:25,248][87424] Updated weights for policy 0, policy_version 105446 (0.0010) -[2023-11-28 02:58:25,492][87426] Updated weights for policy 1, policy_version 105230 (0.0007) -[2023-11-28 02:58:25,640][87424] Updated weights for policy 0, policy_version 105456 (0.0007) -[2023-11-28 02:58:25,883][87426] Updated weights for policy 1, policy_version 105240 (0.0007) -[2023-11-28 02:58:26,035][87424] Updated weights for policy 0, policy_version 105466 (0.0007) -[2023-11-28 02:58:27,914][87426] Updated weights for policy 1, policy_version 105250 (0.0008) -[2023-11-28 02:58:28,123][87424] Updated weights for policy 0, policy_version 105476 (0.0009) -[2023-11-28 02:58:28,299][87426] Updated weights for policy 1, policy_version 105260 (0.0011) -[2023-11-28 02:58:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 53944320. Throughput: 0: 2670.0, 1: 2732.9. Samples: 53964284. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:58:28,445][86177] Avg episode reward: [(0, '-498.290'), (1, '-522.480')] -[2023-11-28 02:58:28,501][87424] Updated weights for policy 0, policy_version 105486 (0.0009) -[2023-11-28 02:58:28,679][87426] Updated weights for policy 1, policy_version 105270 (0.0012) -[2023-11-28 02:58:28,882][87424] Updated weights for policy 0, policy_version 105496 (0.0008) -[2023-11-28 02:58:29,055][87426] Updated weights for policy 1, policy_version 105280 (0.0012) -[2023-11-28 02:58:30,892][87424] Updated weights for policy 0, policy_version 105506 (0.0009) -[2023-11-28 02:58:31,120][87426] Updated weights for policy 1, policy_version 105290 (0.0008) -[2023-11-28 02:58:31,271][87424] Updated weights for policy 0, policy_version 105516 (0.0011) -[2023-11-28 02:58:31,509][87426] Updated weights for policy 1, policy_version 105300 (0.0007) -[2023-11-28 02:58:31,651][87424] Updated weights for policy 0, policy_version 105526 (0.0010) -[2023-11-28 02:58:31,878][87426] Updated weights for policy 1, policy_version 105310 (0.0009) -[2023-11-28 02:58:32,036][87424] Updated weights for policy 0, policy_version 105536 (0.0010) -[2023-11-28 02:58:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 53977088. Throughput: 0: 2651.7, 1: 2741.4. Samples: 53988036. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:58:33,445][86177] Avg episode reward: [(0, '-500.390'), (1, '-520.320')] -[2023-11-28 02:58:34,301][87426] Updated weights for policy 1, policy_version 105320 (0.0009) -[2023-11-28 02:58:34,619][87424] Updated weights for policy 0, policy_version 105546 (0.0012) -[2023-11-28 02:58:34,683][87426] Updated weights for policy 1, policy_version 105330 (0.0011) -[2023-11-28 02:58:35,007][87424] Updated weights for policy 0, policy_version 105556 (0.0011) -[2023-11-28 02:58:35,061][87426] Updated weights for policy 1, policy_version 105340 (0.0011) -[2023-11-28 02:58:35,383][87424] Updated weights for policy 0, policy_version 105566 (0.0010) -[2023-11-28 02:58:37,096][87426] Updated weights for policy 1, policy_version 105350 (0.0011) -[2023-11-28 02:58:37,448][87424] Updated weights for policy 0, policy_version 105576 (0.0009) -[2023-11-28 02:58:37,475][87426] Updated weights for policy 1, policy_version 105360 (0.0011) -[2023-11-28 02:58:37,838][87424] Updated weights for policy 0, policy_version 105586 (0.0011) -[2023-11-28 02:58:37,864][87426] Updated weights for policy 1, policy_version 105370 (0.0012) -[2023-11-28 02:58:38,214][87424] Updated weights for policy 0, policy_version 105596 (0.0011) -[2023-11-28 02:58:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54009856. Throughput: 0: 2631.7, 1: 2738.5. Samples: 54020112. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:58:38,445][86177] Avg episode reward: [(0, '-495.930'), (1, '-561.030')] -[2023-11-28 02:58:39,916][87426] Updated weights for policy 1, policy_version 105380 (0.0012) -[2023-11-28 02:58:40,295][87426] Updated weights for policy 1, policy_version 105390 (0.0011) -[2023-11-28 02:58:40,393][87424] Updated weights for policy 0, policy_version 105606 (0.0011) -[2023-11-28 02:58:40,674][87426] Updated weights for policy 1, policy_version 105400 (0.0010) -[2023-11-28 02:58:40,788][87424] Updated weights for policy 0, policy_version 105616 (0.0011) -[2023-11-28 02:58:41,161][87424] Updated weights for policy 0, policy_version 105626 (0.0008) -[2023-11-28 02:58:43,006][87426] Updated weights for policy 1, policy_version 105410 (0.0013) -[2023-11-28 02:58:43,381][87426] Updated weights for policy 1, policy_version 105420 (0.0012) -[2023-11-28 02:58:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 54026240. Throughput: 0: 2647.1, 1: 2733.0. Samples: 54044772. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 02:58:43,445][86177] Avg episode reward: [(0, '-493.640'), (1, '-622.590')] -[2023-11-28 02:58:43,632][87424] Updated weights for policy 0, policy_version 105636 (0.0011) -[2023-11-28 02:58:43,754][87426] Updated weights for policy 1, policy_version 105430 (0.0010) -[2023-11-28 02:58:44,023][87424] Updated weights for policy 0, policy_version 105646 (0.0010) -[2023-11-28 02:58:44,132][87426] Updated weights for policy 1, policy_version 105440 (0.0011) -[2023-11-28 02:58:44,403][87424] Updated weights for policy 0, policy_version 105656 (0.0007) -[2023-11-28 02:58:46,751][87424] Updated weights for policy 0, policy_version 105666 (0.0008) -[2023-11-28 02:58:46,799][87426] Updated weights for policy 1, policy_version 105450 (0.0008) -[2023-11-28 02:58:47,126][87424] Updated weights for policy 0, policy_version 105676 (0.0011) -[2023-11-28 02:58:47,171][87426] Updated weights for policy 1, policy_version 105460 (0.0008) -[2023-11-28 02:58:47,510][87424] Updated weights for policy 0, policy_version 105686 (0.0007) -[2023-11-28 02:58:47,548][87426] Updated weights for policy 1, policy_version 105470 (0.0008) -[2023-11-28 02:58:47,898][87424] Updated weights for policy 0, policy_version 105696 (0.0007) -[2023-11-28 02:58:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54059008. Throughput: 0: 2630.1, 1: 2752.0. Samples: 54068504. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:58:48,445][86177] Avg episode reward: [(0, '-492.500'), (1, '-606.670')] -[2023-11-28 02:58:49,575][87426] Updated weights for policy 1, policy_version 105480 (0.0008) -[2023-11-28 02:58:49,944][87424] Updated weights for policy 0, policy_version 105706 (0.0011) -[2023-11-28 02:58:49,957][87426] Updated weights for policy 1, policy_version 105490 (0.0010) -[2023-11-28 02:58:50,324][87424] Updated weights for policy 0, policy_version 105716 (0.0011) -[2023-11-28 02:58:50,330][87426] Updated weights for policy 1, policy_version 105500 (0.0011) -[2023-11-28 02:58:50,711][87424] Updated weights for policy 0, policy_version 105726 (0.0012) -[2023-11-28 02:58:52,789][87426] Updated weights for policy 1, policy_version 105510 (0.0010) -[2023-11-28 02:58:53,013][87424] Updated weights for policy 0, policy_version 105736 (0.0012) -[2023-11-28 02:58:53,174][87426] Updated weights for policy 1, policy_version 105520 (0.0010) -[2023-11-28 02:58:53,390][87424] Updated weights for policy 0, policy_version 105746 (0.0012) -[2023-11-28 02:58:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 54075392. Throughput: 0: 2650.0, 1: 2730.0. Samples: 54100480. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:58:53,445][86177] Avg episode reward: [(0, '-492.750'), (1, '-615.470')] -[2023-11-28 02:58:53,551][87426] Updated weights for policy 1, policy_version 105530 (0.0009) -[2023-11-28 02:58:53,776][87424] Updated weights for policy 0, policy_version 105756 (0.0010) -[2023-11-28 02:58:55,456][87426] Updated weights for policy 1, policy_version 105540 (0.0011) -[2023-11-28 02:58:55,838][87426] Updated weights for policy 1, policy_version 105550 (0.0012) -[2023-11-28 02:58:56,171][87424] Updated weights for policy 0, policy_version 105766 (0.0008) -[2023-11-28 02:58:56,219][87426] Updated weights for policy 1, policy_version 105560 (0.0012) -[2023-11-28 02:58:56,557][87424] Updated weights for policy 0, policy_version 105776 (0.0008) -[2023-11-28 02:58:56,944][87424] Updated weights for policy 0, policy_version 105786 (0.0007) -[2023-11-28 02:58:58,027][87426] Updated weights for policy 1, policy_version 105570 (0.0010) -[2023-11-28 02:58:58,414][87426] Updated weights for policy 1, policy_version 105580 (0.0007) -[2023-11-28 02:58:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 54108160. Throughput: 0: 2651.3, 1: 2727.8. Samples: 54124544. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:58:58,445][86177] Avg episode reward: [(0, '-494.910'), (1, '-573.130')] -[2023-11-28 02:58:58,793][87426] Updated weights for policy 1, policy_version 105590 (0.0008) -[2023-11-28 02:58:58,875][87424] Updated weights for policy 0, policy_version 105796 (0.0012) -[2023-11-28 02:58:59,170][87426] Updated weights for policy 1, policy_version 105600 (0.0010) -[2023-11-28 02:58:59,248][87424] Updated weights for policy 0, policy_version 105806 (0.0012) -[2023-11-28 02:58:59,630][87424] Updated weights for policy 0, policy_version 105816 (0.0011) -[2023-11-28 02:59:01,086][87426] Updated weights for policy 1, policy_version 105610 (0.0012) -[2023-11-28 02:59:01,464][87426] Updated weights for policy 1, policy_version 105620 (0.0012) -[2023-11-28 02:59:01,695][87424] Updated weights for policy 0, policy_version 105826 (0.0011) -[2023-11-28 02:59:01,842][87426] Updated weights for policy 1, policy_version 105630 (0.0012) -[2023-11-28 02:59:02,076][87424] Updated weights for policy 0, policy_version 105836 (0.0010) -[2023-11-28 02:59:02,461][87424] Updated weights for policy 0, policy_version 105846 (0.0012) -[2023-11-28 02:59:02,845][87424] Updated weights for policy 0, policy_version 105856 (0.0012) -[2023-11-28 02:59:03,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 54140928. Throughput: 0: 2678.0, 1: 2726.6. Samples: 54149876. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:59:03,445][86177] Avg episode reward: [(0, '-494.530'), (1, '-588.500')] -[2023-11-28 02:59:04,232][87426] Updated weights for policy 1, policy_version 105640 (0.0011) -[2023-11-28 02:59:04,614][87426] Updated weights for policy 1, policy_version 105650 (0.0011) -[2023-11-28 02:59:04,996][87426] Updated weights for policy 1, policy_version 105660 (0.0012) -[2023-11-28 02:59:05,388][87424] Updated weights for policy 0, policy_version 105866 (0.0009) -[2023-11-28 02:59:05,766][87424] Updated weights for policy 0, policy_version 105876 (0.0008) -[2023-11-28 02:59:06,145][87424] Updated weights for policy 0, policy_version 105886 (0.0007) -[2023-11-28 02:59:07,091][87426] Updated weights for policy 1, policy_version 105670 (0.0011) -[2023-11-28 02:59:07,468][87426] Updated weights for policy 1, policy_version 105680 (0.0011) -[2023-11-28 02:59:07,854][87426] Updated weights for policy 1, policy_version 105690 (0.0012) -[2023-11-28 02:59:08,243][87424] Updated weights for policy 0, policy_version 105896 (0.0009) -[2023-11-28 02:59:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 54165504. Throughput: 0: 2653.9, 1: 2739.1. Samples: 54181532. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:59:08,445][86177] Avg episode reward: [(0, '-495.890'), (1, '-572.940')] -[2023-11-28 02:59:08,625][87424] Updated weights for policy 0, policy_version 105906 (0.0008) -[2023-11-28 02:59:09,013][87424] Updated weights for policy 0, policy_version 105916 (0.0009) -[2023-11-28 02:59:09,626][87426] Updated weights for policy 1, policy_version 105700 (0.0011) -[2023-11-28 02:59:10,008][87426] Updated weights for policy 1, policy_version 105710 (0.0011) -[2023-11-28 02:59:10,378][87426] Updated weights for policy 1, policy_version 105720 (0.0012) -[2023-11-28 02:59:11,606][87424] Updated weights for policy 0, policy_version 105926 (0.0011) -[2023-11-28 02:59:11,990][87424] Updated weights for policy 0, policy_version 105936 (0.0011) -[2023-11-28 02:59:12,371][87424] Updated weights for policy 0, policy_version 105946 (0.0012) -[2023-11-28 02:59:12,483][87426] Updated weights for policy 1, policy_version 105730 (0.0011) -[2023-11-28 02:59:12,863][87426] Updated weights for policy 1, policy_version 105740 (0.0008) -[2023-11-28 02:59:13,247][87426] Updated weights for policy 1, policy_version 105750 (0.0010) -[2023-11-28 02:59:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54190080. Throughput: 0: 2658.7, 1: 2720.1. Samples: 54206328. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:59:13,445][86177] Avg episode reward: [(0, '-497.920'), (1, '-604.460')] -[2023-11-28 02:59:13,625][87426] Updated weights for policy 1, policy_version 105760 (0.0012) -[2023-11-28 02:59:14,602][87424] Updated weights for policy 0, policy_version 105956 (0.0011) -[2023-11-28 02:59:14,991][87424] Updated weights for policy 0, policy_version 105966 (0.0012) -[2023-11-28 02:59:15,366][87424] Updated weights for policy 0, policy_version 105976 (0.0011) -[2023-11-28 02:59:15,737][87426] Updated weights for policy 1, policy_version 105770 (0.0011) -[2023-11-28 02:59:16,126][87426] Updated weights for policy 1, policy_version 105780 (0.0010) -[2023-11-28 02:59:16,504][87426] Updated weights for policy 1, policy_version 105790 (0.0012) -[2023-11-28 02:59:17,563][87424] Updated weights for policy 0, policy_version 105986 (0.0009) -[2023-11-28 02:59:17,940][87424] Updated weights for policy 0, policy_version 105996 (0.0010) -[2023-11-28 02:59:18,324][87424] Updated weights for policy 0, policy_version 106006 (0.0012) -[2023-11-28 02:59:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 54214656. Throughput: 0: 2673.5, 1: 2746.3. Samples: 54231928. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:59:18,445][86177] Avg episode reward: [(0, '-500.350'), (1, '-616.890')] -[2023-11-28 02:59:18,712][87424] Updated weights for policy 0, policy_version 106016 (0.0010) -[2023-11-28 02:59:18,779][87426] Updated weights for policy 1, policy_version 105800 (0.0008) -[2023-11-28 02:59:19,166][87426] Updated weights for policy 1, policy_version 105810 (0.0008) -[2023-11-28 02:59:19,533][87426] Updated weights for policy 1, policy_version 105820 (0.0008) -[2023-11-28 02:59:21,142][87424] Updated weights for policy 0, policy_version 106026 (0.0009) -[2023-11-28 02:59:21,408][87426] Updated weights for policy 1, policy_version 105830 (0.0007) -[2023-11-28 02:59:21,524][87424] Updated weights for policy 0, policy_version 106036 (0.0010) -[2023-11-28 02:59:21,788][87426] Updated weights for policy 1, policy_version 105840 (0.0009) -[2023-11-28 02:59:21,908][87424] Updated weights for policy 0, policy_version 106046 (0.0011) -[2023-11-28 02:59:22,173][87426] Updated weights for policy 1, policy_version 105850 (0.0011) -[2023-11-28 02:59:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54247424. Throughput: 0: 2687.8, 1: 2733.7. Samples: 54264080. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:59:23,445][86177] Avg episode reward: [(0, '-509.560'), (1, '-688.910')] -[2023-11-28 02:59:23,874][87424] Updated weights for policy 0, policy_version 106056 (0.0012) -[2023-11-28 02:59:24,257][87424] Updated weights for policy 0, policy_version 106066 (0.0009) -[2023-11-28 02:59:24,651][87424] Updated weights for policy 0, policy_version 106076 (0.0011) -[2023-11-28 02:59:24,751][87426] Updated weights for policy 1, policy_version 105860 (0.0011) -[2023-11-28 02:59:25,126][87426] Updated weights for policy 1, policy_version 105870 (0.0007) -[2023-11-28 02:59:25,514][87426] Updated weights for policy 1, policy_version 105880 (0.0008) -[2023-11-28 02:59:26,416][87424] Updated weights for policy 0, policy_version 106086 (0.0009) -[2023-11-28 02:59:26,801][87424] Updated weights for policy 0, policy_version 106096 (0.0010) -[2023-11-28 02:59:27,183][87424] Updated weights for policy 0, policy_version 106106 (0.0008) -[2023-11-28 02:59:27,879][87426] Updated weights for policy 1, policy_version 105890 (0.0011) -[2023-11-28 02:59:28,265][87426] Updated weights for policy 1, policy_version 105900 (0.0012) -[2023-11-28 02:59:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54272000. Throughput: 0: 2686.8, 1: 2718.8. Samples: 54288020. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:59:28,445][86177] Avg episode reward: [(0, '-506.050'), (1, '-729.360')] -[2023-11-28 02:59:28,637][87426] Updated weights for policy 1, policy_version 105910 (0.0009) -[2023-11-28 02:59:29,017][87426] Updated weights for policy 1, policy_version 105920 (0.0009) -[2023-11-28 02:59:29,064][87424] Updated weights for policy 0, policy_version 106116 (0.0009) -[2023-11-28 02:59:29,435][87424] Updated weights for policy 0, policy_version 106126 (0.0012) -[2023-11-28 02:59:29,822][87424] Updated weights for policy 0, policy_version 106136 (0.0012) -[2023-11-28 02:59:31,329][87426] Updated weights for policy 1, policy_version 105930 (0.0012) -[2023-11-28 02:59:31,693][87426] Updated weights for policy 1, policy_version 105940 (0.0012) -[2023-11-28 02:59:31,864][87424] Updated weights for policy 0, policy_version 106146 (0.0011) -[2023-11-28 02:59:32,079][87426] Updated weights for policy 1, policy_version 105950 (0.0012) -[2023-11-28 02:59:32,242][87424] Updated weights for policy 0, policy_version 106156 (0.0012) -[2023-11-28 02:59:32,625][87424] Updated weights for policy 0, policy_version 106166 (0.0012) -[2023-11-28 02:59:33,010][87424] Updated weights for policy 0, policy_version 106176 (0.0011) -[2023-11-28 02:59:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54304768. Throughput: 0: 2730.3, 1: 2721.2. Samples: 54313820. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:59:33,445][86177] Avg episode reward: [(0, '-506.430'), (1, '-666.040')] -[2023-11-28 02:59:34,365][87426] Updated weights for policy 1, policy_version 105960 (0.0011) -[2023-11-28 02:59:34,755][87426] Updated weights for policy 1, policy_version 105970 (0.0010) -[2023-11-28 02:59:35,021][87424] Updated weights for policy 0, policy_version 106186 (0.0011) -[2023-11-28 02:59:35,144][87426] Updated weights for policy 1, policy_version 105980 (0.0010) -[2023-11-28 02:59:35,413][87424] Updated weights for policy 0, policy_version 106196 (0.0012) -[2023-11-28 02:59:35,790][87424] Updated weights for policy 0, policy_version 106206 (0.0012) -[2023-11-28 02:59:36,877][87426] Updated weights for policy 1, policy_version 105990 (0.0011) -[2023-11-28 02:59:37,249][87426] Updated weights for policy 1, policy_version 106000 (0.0012) -[2023-11-28 02:59:37,628][87426] Updated weights for policy 1, policy_version 106010 (0.0011) -[2023-11-28 02:59:38,171][87424] Updated weights for policy 0, policy_version 106216 (0.0012) -[2023-11-28 02:59:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 54329344. Throughput: 0: 2732.5, 1: 2737.9. Samples: 54346652. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:59:38,445][86177] Avg episode reward: [(0, '-511.200'), (1, '-688.040')] -[2023-11-28 02:59:38,545][87424] Updated weights for policy 0, policy_version 106226 (0.0012) -[2023-11-28 02:59:38,937][87424] Updated weights for policy 0, policy_version 106236 (0.0012) -[2023-11-28 02:59:39,749][87426] Updated weights for policy 1, policy_version 106020 (0.0012) -[2023-11-28 02:59:40,116][87426] Updated weights for policy 1, policy_version 106030 (0.0012) -[2023-11-28 02:59:40,493][87426] Updated weights for policy 1, policy_version 106040 (0.0011) -[2023-11-28 02:59:40,996][87424] Updated weights for policy 0, policy_version 106246 (0.0011) -[2023-11-28 02:59:41,377][87424] Updated weights for policy 0, policy_version 106256 (0.0009) -[2023-11-28 02:59:41,771][87424] Updated weights for policy 0, policy_version 106266 (0.0010) -[2023-11-28 02:59:42,619][87426] Updated weights for policy 1, policy_version 106050 (0.0011) -[2023-11-28 02:59:42,998][87426] Updated weights for policy 1, policy_version 106060 (0.0011) -[2023-11-28 02:59:43,386][87426] Updated weights for policy 1, policy_version 106070 (0.0012) -[2023-11-28 02:59:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54353920. Throughput: 0: 2728.3, 1: 2754.7. Samples: 54371276. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 02:59:43,445][86177] Avg episode reward: [(0, '-505.730'), (1, '-628.050')] -[2023-11-28 02:59:43,759][87426] Updated weights for policy 1, policy_version 106080 (0.0011) -[2023-11-28 02:59:44,127][87424] Updated weights for policy 0, policy_version 106276 (0.0010) -[2023-11-28 02:59:44,503][87424] Updated weights for policy 0, policy_version 106286 (0.0012) -[2023-11-28 02:59:44,885][87424] Updated weights for policy 0, policy_version 106296 (0.0012) -[2023-11-28 02:59:46,236][87426] Updated weights for policy 1, policy_version 106090 (0.0012) -[2023-11-28 02:59:46,606][87426] Updated weights for policy 1, policy_version 106100 (0.0011) -[2023-11-28 02:59:46,960][87424] Updated weights for policy 0, policy_version 106306 (0.0011) -[2023-11-28 02:59:46,990][87426] Updated weights for policy 1, policy_version 106110 (0.0011) -[2023-11-28 02:59:47,344][87424] Updated weights for policy 0, policy_version 106316 (0.0009) -[2023-11-28 02:59:47,718][87424] Updated weights for policy 0, policy_version 106326 (0.0012) -[2023-11-28 02:59:48,102][87424] Updated weights for policy 0, policy_version 106336 (0.0012) -[2023-11-28 02:59:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54386688. Throughput: 0: 2729.7, 1: 2728.6. Samples: 54395500. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 02:59:48,445][86177] Avg episode reward: [(0, '-503.730'), (1, '-569.190')] -[2023-11-28 02:59:48,734][87426] Updated weights for policy 1, policy_version 106120 (0.0011) -[2023-11-28 02:59:49,107][87426] Updated weights for policy 1, policy_version 106130 (0.0011) -[2023-11-28 02:59:49,490][87426] Updated weights for policy 1, policy_version 106140 (0.0011) -[2023-11-28 02:59:50,115][87424] Updated weights for policy 0, policy_version 106346 (0.0010) -[2023-11-28 02:59:50,490][87424] Updated weights for policy 0, policy_version 106356 (0.0009) -[2023-11-28 02:59:50,873][87424] Updated weights for policy 0, policy_version 106366 (0.0011) -[2023-11-28 02:59:51,930][87426] Updated weights for policy 1, policy_version 106150 (0.0011) -[2023-11-28 02:59:52,305][87426] Updated weights for policy 1, policy_version 106160 (0.0014) -[2023-11-28 02:59:52,693][87426] Updated weights for policy 1, policy_version 106170 (0.0007) -[2023-11-28 02:59:53,193][87424] Updated weights for policy 0, policy_version 106376 (0.0009) -[2023-11-28 02:59:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 54411264. Throughput: 0: 2752.1, 1: 2727.2. Samples: 54428100. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 02:59:53,445][86177] Avg episode reward: [(0, '-500.700'), (1, '-563.800')] -[2023-11-28 02:59:53,575][87424] Updated weights for policy 0, policy_version 106386 (0.0010) -[2023-11-28 02:59:53,961][87424] Updated weights for policy 0, policy_version 106396 (0.0009) -[2023-11-28 02:59:54,982][87426] Updated weights for policy 1, policy_version 106180 (0.0010) -[2023-11-28 02:59:55,363][87426] Updated weights for policy 1, policy_version 106190 (0.0011) -[2023-11-28 02:59:55,734][87426] Updated weights for policy 1, policy_version 106200 (0.0010) -[2023-11-28 02:59:56,215][87424] Updated weights for policy 0, policy_version 106406 (0.0010) -[2023-11-28 02:59:56,601][87424] Updated weights for policy 0, policy_version 106416 (0.0012) -[2023-11-28 02:59:56,990][87424] Updated weights for policy 0, policy_version 106426 (0.0012) -[2023-11-28 02:59:57,812][87426] Updated weights for policy 1, policy_version 106210 (0.0011) -[2023-11-28 02:59:58,185][87426] Updated weights for policy 1, policy_version 106220 (0.0012) -[2023-11-28 02:59:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54435840. Throughput: 0: 2737.9, 1: 2726.8. Samples: 54452240. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 02:59:58,445][86177] Avg episode reward: [(0, '-504.120'), (1, '-508.080')] -[2023-11-28 02:59:58,567][87426] Updated weights for policy 1, policy_version 106230 (0.0012) -[2023-11-28 02:59:58,942][87426] Updated weights for policy 1, policy_version 106240 (0.0011) -[2023-11-28 02:59:59,311][87424] Updated weights for policy 0, policy_version 106436 (0.0011) -[2023-11-28 02:59:59,696][87424] Updated weights for policy 0, policy_version 106446 (0.0010) -[2023-11-28 03:00:00,080][87424] Updated weights for policy 0, policy_version 106456 (0.0009) -[2023-11-28 03:00:00,686][87426] Updated weights for policy 1, policy_version 106250 (0.0012) -[2023-11-28 03:00:01,061][87426] Updated weights for policy 1, policy_version 106260 (0.0011) -[2023-11-28 03:00:01,441][87426] Updated weights for policy 1, policy_version 106270 (0.0012) -[2023-11-28 03:00:02,006][87424] Updated weights for policy 0, policy_version 106466 (0.0008) -[2023-11-28 03:00:02,387][87424] Updated weights for policy 0, policy_version 106476 (0.0009) -[2023-11-28 03:00:02,765][87424] Updated weights for policy 0, policy_version 106486 (0.0009) -[2023-11-28 03:00:03,159][87424] Updated weights for policy 0, policy_version 106496 (0.0009) -[2023-11-28 03:00:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54468608. Throughput: 0: 2750.3, 1: 2696.4. Samples: 54477028. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:03,445][86177] Avg episode reward: [(0, '-504.850'), (1, '-510.400')] -[2023-11-28 03:00:04,013][87426] Updated weights for policy 1, policy_version 106280 (0.0012) -[2023-11-28 03:00:04,400][87426] Updated weights for policy 1, policy_version 106290 (0.0012) -[2023-11-28 03:00:04,775][87426] Updated weights for policy 1, policy_version 106300 (0.0011) -[2023-11-28 03:00:05,128][87424] Updated weights for policy 0, policy_version 106506 (0.0008) -[2023-11-28 03:00:05,501][87424] Updated weights for policy 0, policy_version 106516 (0.0008) -[2023-11-28 03:00:05,889][87424] Updated weights for policy 0, policy_version 106526 (0.0008) -[2023-11-28 03:00:07,159][87426] Updated weights for policy 1, policy_version 106310 (0.0011) -[2023-11-28 03:00:07,536][87426] Updated weights for policy 1, policy_version 106320 (0.0012) -[2023-11-28 03:00:07,921][87426] Updated weights for policy 1, policy_version 106330 (0.0012) -[2023-11-28 03:00:08,046][87424] Updated weights for policy 0, policy_version 106536 (0.0007) -[2023-11-28 03:00:08,436][87424] Updated weights for policy 0, policy_version 106546 (0.0007) -[2023-11-28 03:00:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54493184. Throughput: 0: 2762.9, 1: 2707.8. Samples: 54510264. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:08,445][86177] Avg episode reward: [(0, '-507.010'), (1, '-510.970')] -[2023-11-28 03:00:08,820][87424] Updated weights for policy 0, policy_version 106556 (0.0007) -[2023-11-28 03:00:09,866][87426] Updated weights for policy 1, policy_version 106340 (0.0011) -[2023-11-28 03:00:10,245][87426] Updated weights for policy 1, policy_version 106350 (0.0012) -[2023-11-28 03:00:10,628][87426] Updated weights for policy 1, policy_version 106360 (0.0016) -[2023-11-28 03:00:10,982][87424] Updated weights for policy 0, policy_version 106566 (0.0010) -[2023-11-28 03:00:11,357][87424] Updated weights for policy 0, policy_version 106576 (0.0012) -[2023-11-28 03:00:11,738][87424] Updated weights for policy 0, policy_version 106586 (0.0012) -[2023-11-28 03:00:12,807][87426] Updated weights for policy 1, policy_version 106370 (0.0010) -[2023-11-28 03:00:13,194][87426] Updated weights for policy 1, policy_version 106380 (0.0012) -[2023-11-28 03:00:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54517760. Throughput: 0: 2751.8, 1: 2724.9. Samples: 54534472. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:13,445][86177] Avg episode reward: [(0, '-508.990'), (1, '-529.900')] -[2023-11-28 03:00:13,564][87426] Updated weights for policy 1, policy_version 106390 (0.0012) -[2023-11-28 03:00:13,920][87424] Updated weights for policy 0, policy_version 106596 (0.0012) -[2023-11-28 03:00:13,942][87426] Updated weights for policy 1, policy_version 106400 (0.0012) -[2023-11-28 03:00:14,298][87424] Updated weights for policy 0, policy_version 106606 (0.0009) -[2023-11-28 03:00:14,695][87424] Updated weights for policy 0, policy_version 106616 (0.0009) -[2023-11-28 03:00:15,683][87426] Updated weights for policy 1, policy_version 106410 (0.0012) -[2023-11-28 03:00:16,059][87426] Updated weights for policy 1, policy_version 106420 (0.0012) -[2023-11-28 03:00:16,425][87426] Updated weights for policy 1, policy_version 106430 (0.0010) -[2023-11-28 03:00:16,531][87424] Updated weights for policy 0, policy_version 106626 (0.0012) -[2023-11-28 03:00:16,918][87424] Updated weights for policy 0, policy_version 106636 (0.0011) -[2023-11-28 03:00:17,303][87424] Updated weights for policy 0, policy_version 106646 (0.0012) -[2023-11-28 03:00:17,687][87424] Updated weights for policy 0, policy_version 106656 (0.0009) -[2023-11-28 03:00:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 54550528. Throughput: 0: 2742.7, 1: 2740.3. Samples: 54560560. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:18,445][86177] Avg episode reward: [(0, '-503.190'), (1, '-528.220')] -[2023-11-28 03:00:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000106656_27303936.pth... -[2023-11-28 03:00:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000104128_26656768.pth -[2023-11-28 03:00:18,564][87426] Updated weights for policy 1, policy_version 106440 (0.0011) -[2023-11-28 03:00:18,936][87426] Updated weights for policy 1, policy_version 106450 (0.0012) -[2023-11-28 03:00:19,310][87426] Updated weights for policy 1, policy_version 106460 (0.0010) -[2023-11-28 03:00:19,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000106464_27254784.pth... -[2023-11-28 03:00:19,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000103904_26599424.pth -[2023-11-28 03:00:19,519][87424] Updated weights for policy 0, policy_version 106666 (0.0008) -[2023-11-28 03:00:19,903][87424] Updated weights for policy 0, policy_version 106676 (0.0009) -[2023-11-28 03:00:20,284][87424] Updated weights for policy 0, policy_version 106686 (0.0011) -[2023-11-28 03:00:21,791][87426] Updated weights for policy 1, policy_version 106470 (0.0011) -[2023-11-28 03:00:22,183][87426] Updated weights for policy 1, policy_version 106480 (0.0010) -[2023-11-28 03:00:22,561][87426] Updated weights for policy 1, policy_version 106490 (0.0011) -[2023-11-28 03:00:22,570][87424] Updated weights for policy 0, policy_version 106696 (0.0010) -[2023-11-28 03:00:22,957][87424] Updated weights for policy 0, policy_version 106706 (0.0009) -[2023-11-28 03:00:23,334][87424] Updated weights for policy 0, policy_version 106716 (0.0008) -[2023-11-28 03:00:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54575104. Throughput: 0: 2742.1, 1: 2729.8. Samples: 54592888. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:23,446][86177] Avg episode reward: [(0, '-506.410'), (1, '-524.830')] -[2023-11-28 03:00:24,708][87426] Updated weights for policy 1, policy_version 106500 (0.0010) -[2023-11-28 03:00:25,094][87426] Updated weights for policy 1, policy_version 106510 (0.0008) -[2023-11-28 03:00:25,472][87426] Updated weights for policy 1, policy_version 106520 (0.0009) -[2023-11-28 03:00:25,529][87424] Updated weights for policy 0, policy_version 106726 (0.0010) -[2023-11-28 03:00:25,906][87424] Updated weights for policy 0, policy_version 106736 (0.0011) -[2023-11-28 03:00:26,286][87424] Updated weights for policy 0, policy_version 106746 (0.0012) -[2023-11-28 03:00:27,398][87426] Updated weights for policy 1, policy_version 106530 (0.0008) -[2023-11-28 03:00:27,785][87426] Updated weights for policy 1, policy_version 106540 (0.0012) -[2023-11-28 03:00:28,152][87426] Updated weights for policy 1, policy_version 106550 (0.0011) -[2023-11-28 03:00:28,339][87424] Updated weights for policy 0, policy_version 106756 (0.0012) -[2023-11-28 03:00:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54599680. Throughput: 0: 2749.1, 1: 2729.4. Samples: 54617808. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:28,445][86177] Avg episode reward: [(0, '-510.080'), (1, '-529.860')] -[2023-11-28 03:00:28,529][87426] Updated weights for policy 1, policy_version 106560 (0.0008) -[2023-11-28 03:00:28,719][87424] Updated weights for policy 0, policy_version 106766 (0.0011) -[2023-11-28 03:00:29,104][87424] Updated weights for policy 0, policy_version 106776 (0.0012) -[2023-11-28 03:00:30,606][87426] Updated weights for policy 1, policy_version 106570 (0.0012) -[2023-11-28 03:00:30,991][87426] Updated weights for policy 1, policy_version 106580 (0.0012) -[2023-11-28 03:00:31,352][87424] Updated weights for policy 0, policy_version 106786 (0.0011) -[2023-11-28 03:00:31,365][87426] Updated weights for policy 1, policy_version 106590 (0.0012) -[2023-11-28 03:00:31,739][87424] Updated weights for policy 0, policy_version 106796 (0.0009) -[2023-11-28 03:00:32,125][87424] Updated weights for policy 0, policy_version 106806 (0.0009) -[2023-11-28 03:00:32,506][87424] Updated weights for policy 0, policy_version 106816 (0.0008) -[2023-11-28 03:00:33,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54632448. Throughput: 0: 2759.5, 1: 2760.6. Samples: 54643908. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:33,446][86177] Avg episode reward: [(0, '-513.580'), (1, '-506.120')] -[2023-11-28 03:00:33,770][87426] Updated weights for policy 1, policy_version 106600 (0.0009) -[2023-11-28 03:00:34,151][87426] Updated weights for policy 1, policy_version 106610 (0.0011) -[2023-11-28 03:00:34,523][87426] Updated weights for policy 1, policy_version 106620 (0.0012) -[2023-11-28 03:00:34,748][87424] Updated weights for policy 0, policy_version 106826 (0.0011) -[2023-11-28 03:00:35,122][87424] Updated weights for policy 0, policy_version 106836 (0.0007) -[2023-11-28 03:00:35,505][87424] Updated weights for policy 0, policy_version 106846 (0.0008) -[2023-11-28 03:00:36,974][87426] Updated weights for policy 1, policy_version 106630 (0.0012) -[2023-11-28 03:00:37,346][87426] Updated weights for policy 1, policy_version 106640 (0.0011) -[2023-11-28 03:00:37,544][87424] Updated weights for policy 0, policy_version 106856 (0.0009) -[2023-11-28 03:00:37,724][87426] Updated weights for policy 1, policy_version 106650 (0.0011) -[2023-11-28 03:00:37,922][87424] Updated weights for policy 0, policy_version 106866 (0.0009) -[2023-11-28 03:00:38,314][87424] Updated weights for policy 0, policy_version 106876 (0.0008) -[2023-11-28 03:00:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 54657024. Throughput: 0: 2771.4, 1: 2754.8. Samples: 54676780. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:38,445][86177] Avg episode reward: [(0, '-513.200'), (1, '-516.960')] -[2023-11-28 03:00:39,923][87426] Updated weights for policy 1, policy_version 106660 (0.0012) -[2023-11-28 03:00:40,300][87426] Updated weights for policy 1, policy_version 106670 (0.0012) -[2023-11-28 03:00:40,554][87424] Updated weights for policy 0, policy_version 106886 (0.0010) -[2023-11-28 03:00:40,670][87426] Updated weights for policy 1, policy_version 106680 (0.0012) -[2023-11-28 03:00:40,948][87424] Updated weights for policy 0, policy_version 106896 (0.0011) -[2023-11-28 03:00:41,321][87424] Updated weights for policy 0, policy_version 106906 (0.0012) -[2023-11-28 03:00:43,102][87426] Updated weights for policy 1, policy_version 106690 (0.0011) -[2023-11-28 03:00:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54681600. Throughput: 0: 2785.3, 1: 2752.9. Samples: 54701460. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:43,445][86177] Avg episode reward: [(0, '-513.680'), (1, '-515.260')] -[2023-11-28 03:00:43,489][87426] Updated weights for policy 1, policy_version 106700 (0.0008) -[2023-11-28 03:00:43,673][87424] Updated weights for policy 0, policy_version 106916 (0.0010) -[2023-11-28 03:00:43,867][87426] Updated weights for policy 1, policy_version 106710 (0.0008) -[2023-11-28 03:00:44,048][87424] Updated weights for policy 0, policy_version 106926 (0.0008) -[2023-11-28 03:00:44,237][87426] Updated weights for policy 1, policy_version 106720 (0.0009) -[2023-11-28 03:00:44,429][87424] Updated weights for policy 0, policy_version 106936 (0.0007) -[2023-11-28 03:00:46,260][87426] Updated weights for policy 1, policy_version 106730 (0.0012) -[2023-11-28 03:00:46,636][87426] Updated weights for policy 1, policy_version 106740 (0.0012) -[2023-11-28 03:00:46,866][87424] Updated weights for policy 0, policy_version 106946 (0.0008) -[2023-11-28 03:00:47,027][87426] Updated weights for policy 1, policy_version 106750 (0.0012) -[2023-11-28 03:00:47,253][87424] Updated weights for policy 0, policy_version 106956 (0.0008) -[2023-11-28 03:00:47,634][87424] Updated weights for policy 0, policy_version 106966 (0.0007) -[2023-11-28 03:00:48,022][87424] Updated weights for policy 0, policy_version 106976 (0.0010) -[2023-11-28 03:00:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54714368. Throughput: 0: 2761.7, 1: 2750.0. Samples: 54725056. Policy #0 lag: (min: 47.0, avg: 60.4, max: 89.0) -[2023-11-28 03:00:48,445][86177] Avg episode reward: [(0, '-525.270'), (1, '-518.600')] -[2023-11-28 03:00:49,348][87426] Updated weights for policy 1, policy_version 106760 (0.0008) -[2023-11-28 03:00:49,729][87426] Updated weights for policy 1, policy_version 106770 (0.0009) -[2023-11-28 03:00:50,105][87426] Updated weights for policy 1, policy_version 106780 (0.0009) -[2023-11-28 03:00:50,120][87424] Updated weights for policy 0, policy_version 106986 (0.0012) -[2023-11-28 03:00:50,501][87424] Updated weights for policy 0, policy_version 106996 (0.0012) -[2023-11-28 03:00:50,875][87424] Updated weights for policy 0, policy_version 107006 (0.0012) -[2023-11-28 03:00:52,014][87426] Updated weights for policy 1, policy_version 106790 (0.0010) -[2023-11-28 03:00:52,388][87426] Updated weights for policy 1, policy_version 106800 (0.0013) -[2023-11-28 03:00:52,774][87426] Updated weights for policy 1, policy_version 106810 (0.0012) -[2023-11-28 03:00:53,286][87424] Updated weights for policy 0, policy_version 107016 (0.0009) -[2023-11-28 03:00:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 54738944. Throughput: 0: 2742.0, 1: 2741.2. Samples: 54757004. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:00:53,445][86177] Avg episode reward: [(0, '-525.410'), (1, '-522.820')] -[2023-11-28 03:00:53,668][87424] Updated weights for policy 0, policy_version 107026 (0.0010) -[2023-11-28 03:00:54,051][87424] Updated weights for policy 0, policy_version 107036 (0.0008) -[2023-11-28 03:00:54,844][87426] Updated weights for policy 1, policy_version 106820 (0.0011) -[2023-11-28 03:00:55,228][87426] Updated weights for policy 1, policy_version 106830 (0.0011) -[2023-11-28 03:00:55,612][87426] Updated weights for policy 1, policy_version 106840 (0.0011) -[2023-11-28 03:00:56,264][87424] Updated weights for policy 0, policy_version 107046 (0.0010) -[2023-11-28 03:00:56,653][87424] Updated weights for policy 0, policy_version 107056 (0.0010) -[2023-11-28 03:00:57,027][87424] Updated weights for policy 0, policy_version 107066 (0.0007) -[2023-11-28 03:00:58,010][87426] Updated weights for policy 1, policy_version 106850 (0.0012) -[2023-11-28 03:00:58,387][87426] Updated weights for policy 1, policy_version 106860 (0.0011) -[2023-11-28 03:00:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54763520. Throughput: 0: 2735.6, 1: 2730.8. Samples: 54780464. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:00:58,445][86177] Avg episode reward: [(0, '-547.020'), (1, '-502.520')] -[2023-11-28 03:00:58,766][87424] Updated weights for policy 0, policy_version 107076 (0.0009) -[2023-11-28 03:00:58,778][87426] Updated weights for policy 1, policy_version 106870 (0.0011) -[2023-11-28 03:00:59,150][87426] Updated weights for policy 1, policy_version 106880 (0.0011) -[2023-11-28 03:00:59,151][87424] Updated weights for policy 0, policy_version 107086 (0.0012) -[2023-11-28 03:00:59,532][87424] Updated weights for policy 0, policy_version 107096 (0.0012) -[2023-11-28 03:01:01,017][87426] Updated weights for policy 1, policy_version 106890 (0.0008) -[2023-11-28 03:01:01,404][87426] Updated weights for policy 1, policy_version 106900 (0.0012) -[2023-11-28 03:01:01,595][87424] Updated weights for policy 0, policy_version 107106 (0.0011) -[2023-11-28 03:01:01,781][87426] Updated weights for policy 1, policy_version 106910 (0.0012) -[2023-11-28 03:01:01,986][87424] Updated weights for policy 0, policy_version 107116 (0.0012) -[2023-11-28 03:01:02,361][87424] Updated weights for policy 0, policy_version 107126 (0.0012) -[2023-11-28 03:01:02,741][87424] Updated weights for policy 0, policy_version 107136 (0.0012) -[2023-11-28 03:01:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54796288. Throughput: 0: 2721.3, 1: 2726.2. Samples: 54805700. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:03,445][86177] Avg episode reward: [(0, '-550.990'), (1, '-506.020')] -[2023-11-28 03:01:03,691][87426] Updated weights for policy 1, policy_version 106920 (0.0012) -[2023-11-28 03:01:04,067][87426] Updated weights for policy 1, policy_version 106930 (0.0011) -[2023-11-28 03:01:04,448][87426] Updated weights for policy 1, policy_version 106940 (0.0011) -[2023-11-28 03:01:05,193][87424] Updated weights for policy 0, policy_version 107146 (0.0009) -[2023-11-28 03:01:05,573][87424] Updated weights for policy 0, policy_version 107156 (0.0007) -[2023-11-28 03:01:05,959][87424] Updated weights for policy 0, policy_version 107166 (0.0007) -[2023-11-28 03:01:06,917][87426] Updated weights for policy 1, policy_version 106950 (0.0009) -[2023-11-28 03:01:07,285][87426] Updated weights for policy 1, policy_version 106960 (0.0008) -[2023-11-28 03:01:07,664][87426] Updated weights for policy 1, policy_version 106970 (0.0008) -[2023-11-28 03:01:08,179][87424] Updated weights for policy 0, policy_version 107176 (0.0011) -[2023-11-28 03:01:08,445][86177] Fps is (10 sec: 5734.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 54820864. Throughput: 0: 2706.6, 1: 2758.0. Samples: 54838800. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:08,446][86177] Avg episode reward: [(0, '-536.290'), (1, '-503.710')] -[2023-11-28 03:01:08,573][87424] Updated weights for policy 0, policy_version 107186 (0.0012) -[2023-11-28 03:01:08,942][87424] Updated weights for policy 0, policy_version 107196 (0.0011) -[2023-11-28 03:01:10,138][87426] Updated weights for policy 1, policy_version 106980 (0.0009) -[2023-11-28 03:01:10,518][87426] Updated weights for policy 1, policy_version 106990 (0.0009) -[2023-11-28 03:01:10,928][87426] Updated weights for policy 1, policy_version 107000 (0.0010) -[2023-11-28 03:01:11,198][87424] Updated weights for policy 0, policy_version 107206 (0.0011) -[2023-11-28 03:01:11,593][87424] Updated weights for policy 0, policy_version 107216 (0.0008) -[2023-11-28 03:01:11,974][87424] Updated weights for policy 0, policy_version 107226 (0.0010) -[2023-11-28 03:01:12,880][87426] Updated weights for policy 1, policy_version 107010 (0.0010) -[2023-11-28 03:01:13,254][87426] Updated weights for policy 1, policy_version 107020 (0.0009) -[2023-11-28 03:01:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54845440. Throughput: 0: 2701.9, 1: 2719.0. Samples: 54861748. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:13,445][86177] Avg episode reward: [(0, '-535.450'), (1, '-500.180')] -[2023-11-28 03:01:13,638][87426] Updated weights for policy 1, policy_version 107030 (0.0010) -[2023-11-28 03:01:14,009][87426] Updated weights for policy 1, policy_version 107040 (0.0012) -[2023-11-28 03:01:14,543][87424] Updated weights for policy 0, policy_version 107236 (0.0010) -[2023-11-28 03:01:14,925][87424] Updated weights for policy 0, policy_version 107246 (0.0008) -[2023-11-28 03:01:15,305][87424] Updated weights for policy 0, policy_version 107256 (0.0008) -[2023-11-28 03:01:15,935][87426] Updated weights for policy 1, policy_version 107050 (0.0012) -[2023-11-28 03:01:16,314][87426] Updated weights for policy 1, policy_version 107060 (0.0012) -[2023-11-28 03:01:16,691][87426] Updated weights for policy 1, policy_version 107070 (0.0011) -[2023-11-28 03:01:17,192][87424] Updated weights for policy 0, policy_version 107266 (0.0008) -[2023-11-28 03:01:17,591][87424] Updated weights for policy 0, policy_version 107276 (0.0011) -[2023-11-28 03:01:17,967][87424] Updated weights for policy 0, policy_version 107286 (0.0008) -[2023-11-28 03:01:18,348][87424] Updated weights for policy 0, policy_version 107296 (0.0008) -[2023-11-28 03:01:18,402][87426] Updated weights for policy 1, policy_version 107080 (0.0011) -[2023-11-28 03:01:18,445][86177] Fps is (10 sec: 5734.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54878208. Throughput: 0: 2677.8, 1: 2724.7. Samples: 54887020. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:18,446][86177] Avg episode reward: [(0, '-520.220'), (1, '-499.050')] -[2023-11-28 03:01:18,772][87426] Updated weights for policy 1, policy_version 107090 (0.0012) -[2023-11-28 03:01:19,152][87426] Updated weights for policy 1, policy_version 107100 (0.0012) -[2023-11-28 03:01:20,652][87424] Updated weights for policy 0, policy_version 107306 (0.0011) -[2023-11-28 03:01:21,033][87424] Updated weights for policy 0, policy_version 107316 (0.0009) -[2023-11-28 03:01:21,410][87426] Updated weights for policy 1, policy_version 107110 (0.0011) -[2023-11-28 03:01:21,412][87424] Updated weights for policy 0, policy_version 107326 (0.0008) -[2023-11-28 03:01:21,791][87426] Updated weights for policy 1, policy_version 107120 (0.0009) -[2023-11-28 03:01:22,178][87426] Updated weights for policy 1, policy_version 107130 (0.0009) -[2023-11-28 03:01:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54902784. Throughput: 0: 2647.0, 1: 2739.8. Samples: 54919188. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:23,445][86177] Avg episode reward: [(0, '-521.360'), (1, '-499.680')] -[2023-11-28 03:01:23,949][87424] Updated weights for policy 0, policy_version 107336 (0.0007) -[2023-11-28 03:01:24,334][87424] Updated weights for policy 0, policy_version 107346 (0.0007) -[2023-11-28 03:01:24,655][87426] Updated weights for policy 1, policy_version 107140 (0.0010) -[2023-11-28 03:01:24,717][87424] Updated weights for policy 0, policy_version 107356 (0.0008) -[2023-11-28 03:01:25,037][87426] Updated weights for policy 1, policy_version 107150 (0.0008) -[2023-11-28 03:01:25,413][87426] Updated weights for policy 1, policy_version 107160 (0.0008) -[2023-11-28 03:01:27,253][87424] Updated weights for policy 0, policy_version 107366 (0.0010) -[2023-11-28 03:01:27,629][87424] Updated weights for policy 0, policy_version 107376 (0.0008) -[2023-11-28 03:01:27,654][87426] Updated weights for policy 1, policy_version 107170 (0.0010) -[2023-11-28 03:01:28,012][87424] Updated weights for policy 0, policy_version 107386 (0.0008) -[2023-11-28 03:01:28,037][87426] Updated weights for policy 1, policy_version 107180 (0.0007) -[2023-11-28 03:01:28,420][87426] Updated weights for policy 1, policy_version 107190 (0.0009) -[2023-11-28 03:01:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54927360. Throughput: 0: 2628.2, 1: 2738.5. Samples: 54942960. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:28,445][86177] Avg episode reward: [(0, '-523.100'), (1, '-503.400')] -[2023-11-28 03:01:28,797][87426] Updated weights for policy 1, policy_version 107200 (0.0011) -[2023-11-28 03:01:30,476][87424] Updated weights for policy 0, policy_version 107396 (0.0009) -[2023-11-28 03:01:30,574][87426] Updated weights for policy 1, policy_version 107210 (0.0012) -[2023-11-28 03:01:30,857][87424] Updated weights for policy 0, policy_version 107406 (0.0012) -[2023-11-28 03:01:30,942][87426] Updated weights for policy 1, policy_version 107220 (0.0009) -[2023-11-28 03:01:31,227][87424] Updated weights for policy 0, policy_version 107416 (0.0012) -[2023-11-28 03:01:31,332][87426] Updated weights for policy 1, policy_version 107230 (0.0007) -[2023-11-28 03:01:33,092][87426] Updated weights for policy 1, policy_version 107240 (0.0011) -[2023-11-28 03:01:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 54951936. Throughput: 0: 2620.3, 1: 2748.4. Samples: 54966652. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:33,446][86177] Avg episode reward: [(0, '-522.160'), (1, '-503.560')] -[2023-11-28 03:01:33,471][87426] Updated weights for policy 1, policy_version 107250 (0.0012) -[2023-11-28 03:01:33,837][87424] Updated weights for policy 0, policy_version 107426 (0.0012) -[2023-11-28 03:01:33,856][87426] Updated weights for policy 1, policy_version 107260 (0.0011) -[2023-11-28 03:01:34,215][87424] Updated weights for policy 0, policy_version 107436 (0.0012) -[2023-11-28 03:01:34,605][87424] Updated weights for policy 0, policy_version 107446 (0.0012) -[2023-11-28 03:01:34,987][87424] Updated weights for policy 0, policy_version 107456 (0.0008) -[2023-11-28 03:01:36,198][87426] Updated weights for policy 1, policy_version 107270 (0.0011) -[2023-11-28 03:01:36,586][87426] Updated weights for policy 1, policy_version 107280 (0.0012) -[2023-11-28 03:01:36,973][87426] Updated weights for policy 1, policy_version 107290 (0.0012) -[2023-11-28 03:01:37,310][87424] Updated weights for policy 0, policy_version 107466 (0.0012) -[2023-11-28 03:01:37,700][87424] Updated weights for policy 0, policy_version 107476 (0.0011) -[2023-11-28 03:01:38,083][87424] Updated weights for policy 0, policy_version 107486 (0.0011) -[2023-11-28 03:01:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 54984704. Throughput: 0: 2601.9, 1: 2768.9. Samples: 54998692. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:38,445][86177] Avg episode reward: [(0, '-518.150'), (1, '-503.170')] -[2023-11-28 03:01:39,570][87426] Updated weights for policy 1, policy_version 107300 (0.0012) -[2023-11-28 03:01:39,746][87424] Updated weights for policy 0, policy_version 107496 (0.0009) -[2023-11-28 03:01:39,950][87426] Updated weights for policy 1, policy_version 107310 (0.0010) -[2023-11-28 03:01:40,129][87424] Updated weights for policy 0, policy_version 107506 (0.0009) -[2023-11-28 03:01:40,327][87426] Updated weights for policy 1, policy_version 107320 (0.0009) -[2023-11-28 03:01:40,514][87424] Updated weights for policy 0, policy_version 107516 (0.0009) -[2023-11-28 03:01:42,862][87426] Updated weights for policy 1, policy_version 107330 (0.0011) -[2023-11-28 03:01:43,009][87424] Updated weights for policy 0, policy_version 107526 (0.0011) -[2023-11-28 03:01:43,240][87426] Updated weights for policy 1, policy_version 107340 (0.0009) -[2023-11-28 03:01:43,395][87424] Updated weights for policy 0, policy_version 107536 (0.0011) -[2023-11-28 03:01:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55001088. Throughput: 0: 2607.2, 1: 2774.3. Samples: 55022632. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:43,445][86177] Avg episode reward: [(0, '-527.830'), (1, '-499.390')] -[2023-11-28 03:01:43,626][87426] Updated weights for policy 1, policy_version 107350 (0.0011) -[2023-11-28 03:01:43,771][87424] Updated weights for policy 0, policy_version 107546 (0.0009) -[2023-11-28 03:01:44,011][87426] Updated weights for policy 1, policy_version 107360 (0.0007) -[2023-11-28 03:01:45,793][87424] Updated weights for policy 0, policy_version 107556 (0.0008) -[2023-11-28 03:01:46,172][87424] Updated weights for policy 0, policy_version 107566 (0.0008) -[2023-11-28 03:01:46,424][87426] Updated weights for policy 1, policy_version 107370 (0.0008) -[2023-11-28 03:01:46,552][87424] Updated weights for policy 0, policy_version 107576 (0.0008) -[2023-11-28 03:01:46,795][87426] Updated weights for policy 1, policy_version 107380 (0.0007) -[2023-11-28 03:01:47,177][87426] Updated weights for policy 1, policy_version 107390 (0.0008) -[2023-11-28 03:01:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 55033856. Throughput: 0: 2593.1, 1: 2741.9. Samples: 55045776. Policy #0 lag: (min: 30.0, avg: 39.5, max: 62.0) -[2023-11-28 03:01:48,445][86177] Avg episode reward: [(0, '-532.460'), (1, '-497.370')] -[2023-11-28 03:01:48,942][87424] Updated weights for policy 0, policy_version 107586 (0.0008) -[2023-11-28 03:01:48,943][87426] Updated weights for policy 1, policy_version 107400 (0.0011) -[2023-11-28 03:01:49,315][87426] Updated weights for policy 1, policy_version 107410 (0.0012) -[2023-11-28 03:01:49,335][87424] Updated weights for policy 0, policy_version 107596 (0.0009) -[2023-11-28 03:01:49,692][87426] Updated weights for policy 1, policy_version 107420 (0.0011) -[2023-11-28 03:01:49,714][87424] Updated weights for policy 0, policy_version 107606 (0.0012) -[2023-11-28 03:01:50,088][87424] Updated weights for policy 0, policy_version 107616 (0.0012) -[2023-11-28 03:01:52,139][87426] Updated weights for policy 1, policy_version 107430 (0.0010) -[2023-11-28 03:01:52,445][87424] Updated weights for policy 0, policy_version 107626 (0.0010) -[2023-11-28 03:01:52,513][87426] Updated weights for policy 1, policy_version 107440 (0.0010) -[2023-11-28 03:01:52,825][87424] Updated weights for policy 0, policy_version 107636 (0.0011) -[2023-11-28 03:01:52,899][87426] Updated weights for policy 1, policy_version 107450 (0.0010) -[2023-11-28 03:01:53,203][87424] Updated weights for policy 0, policy_version 107646 (0.0009) -[2023-11-28 03:01:53,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 55066624. Throughput: 0: 2631.7, 1: 2713.6. Samples: 55079336. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:01:53,445][86177] Avg episode reward: [(0, '-529.770'), (1, '-500.970')] -[2023-11-28 03:01:54,947][87426] Updated weights for policy 1, policy_version 107460 (0.0008) -[2023-11-28 03:01:55,320][87424] Updated weights for policy 0, policy_version 107656 (0.0008) -[2023-11-28 03:01:55,327][87426] Updated weights for policy 1, policy_version 107470 (0.0008) -[2023-11-28 03:01:55,692][87424] Updated weights for policy 0, policy_version 107666 (0.0008) -[2023-11-28 03:01:55,713][87426] Updated weights for policy 1, policy_version 107480 (0.0009) -[2023-11-28 03:01:56,080][87424] Updated weights for policy 0, policy_version 107676 (0.0008) -[2023-11-28 03:01:57,575][87426] Updated weights for policy 1, policy_version 107490 (0.0011) -[2023-11-28 03:01:57,949][87426] Updated weights for policy 1, policy_version 107500 (0.0012) -[2023-11-28 03:01:58,329][87426] Updated weights for policy 1, policy_version 107510 (0.0011) -[2023-11-28 03:01:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55083008. Throughput: 0: 2631.9, 1: 2730.8. Samples: 55103068. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:01:58,445][86177] Avg episode reward: [(0, '-525.300'), (1, '-500.930')] -[2023-11-28 03:01:58,558][87424] Updated weights for policy 0, policy_version 107686 (0.0009) -[2023-11-28 03:01:58,699][87426] Updated weights for policy 1, policy_version 107520 (0.0011) -[2023-11-28 03:01:58,937][87424] Updated weights for policy 0, policy_version 107696 (0.0010) -[2023-11-28 03:01:59,322][87424] Updated weights for policy 0, policy_version 107706 (0.0011) -[2023-11-28 03:02:01,167][87426] Updated weights for policy 1, policy_version 107530 (0.0008) -[2023-11-28 03:02:01,422][87424] Updated weights for policy 0, policy_version 107716 (0.0011) -[2023-11-28 03:02:01,550][87426] Updated weights for policy 1, policy_version 107540 (0.0009) -[2023-11-28 03:02:01,802][87424] Updated weights for policy 0, policy_version 107726 (0.0010) -[2023-11-28 03:02:01,930][87426] Updated weights for policy 1, policy_version 107550 (0.0011) -[2023-11-28 03:02:02,185][87424] Updated weights for policy 0, policy_version 107736 (0.0012) -[2023-11-28 03:02:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55115776. Throughput: 0: 2626.2, 1: 2721.8. Samples: 55127680. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:03,445][86177] Avg episode reward: [(0, '-525.770'), (1, '-510.110')] -[2023-11-28 03:02:04,390][87426] Updated weights for policy 1, policy_version 107560 (0.0010) -[2023-11-28 03:02:04,451][87424] Updated weights for policy 0, policy_version 107746 (0.0010) -[2023-11-28 03:02:04,772][87426] Updated weights for policy 1, policy_version 107570 (0.0010) -[2023-11-28 03:02:04,828][87424] Updated weights for policy 0, policy_version 107756 (0.0008) -[2023-11-28 03:02:05,154][87426] Updated weights for policy 1, policy_version 107580 (0.0012) -[2023-11-28 03:02:05,204][87424] Updated weights for policy 0, policy_version 107766 (0.0008) -[2023-11-28 03:02:05,591][87424] Updated weights for policy 0, policy_version 107776 (0.0007) -[2023-11-28 03:02:07,323][87426] Updated weights for policy 1, policy_version 107590 (0.0012) -[2023-11-28 03:02:07,412][87424] Updated weights for policy 0, policy_version 107786 (0.0011) -[2023-11-28 03:02:07,720][87426] Updated weights for policy 1, policy_version 107600 (0.0012) -[2023-11-28 03:02:07,804][87424] Updated weights for policy 0, policy_version 107796 (0.0012) -[2023-11-28 03:02:08,099][87426] Updated weights for policy 1, policy_version 107610 (0.0012) -[2023-11-28 03:02:08,186][87424] Updated weights for policy 0, policy_version 107806 (0.0011) -[2023-11-28 03:02:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 55148544. Throughput: 0: 2633.9, 1: 2701.7. Samples: 55159288. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:08,445][86177] Avg episode reward: [(0, '-515.920'), (1, '-511.260')] -[2023-11-28 03:02:09,838][87426] Updated weights for policy 1, policy_version 107620 (0.0010) -[2023-11-28 03:02:10,053][87424] Updated weights for policy 0, policy_version 107816 (0.0012) -[2023-11-28 03:02:10,226][87426] Updated weights for policy 1, policy_version 107630 (0.0011) -[2023-11-28 03:02:10,438][87424] Updated weights for policy 0, policy_version 107826 (0.0012) -[2023-11-28 03:02:10,596][87426] Updated weights for policy 1, policy_version 107640 (0.0010) -[2023-11-28 03:02:10,828][87424] Updated weights for policy 0, policy_version 107836 (0.0011) -[2023-11-28 03:02:12,780][87426] Updated weights for policy 1, policy_version 107650 (0.0011) -[2023-11-28 03:02:13,138][87424] Updated weights for policy 0, policy_version 107846 (0.0012) -[2023-11-28 03:02:13,170][87426] Updated weights for policy 1, policy_version 107660 (0.0011) -[2023-11-28 03:02:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55164928. Throughput: 0: 2633.4, 1: 2677.0. Samples: 55181928. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:13,445][86177] Avg episode reward: [(0, '-514.000'), (1, '-511.550')] -[2023-11-28 03:02:13,519][87424] Updated weights for policy 0, policy_version 107856 (0.0009) -[2023-11-28 03:02:13,547][87426] Updated weights for policy 1, policy_version 107670 (0.0011) -[2023-11-28 03:02:13,911][87424] Updated weights for policy 0, policy_version 107866 (0.0010) -[2023-11-28 03:02:13,926][87426] Updated weights for policy 1, policy_version 107680 (0.0009) -[2023-11-28 03:02:15,998][87424] Updated weights for policy 0, policy_version 107876 (0.0012) -[2023-11-28 03:02:16,129][87426] Updated weights for policy 1, policy_version 107690 (0.0011) -[2023-11-28 03:02:16,379][87424] Updated weights for policy 0, policy_version 107886 (0.0008) -[2023-11-28 03:02:16,499][87426] Updated weights for policy 1, policy_version 107700 (0.0008) -[2023-11-28 03:02:16,766][87424] Updated weights for policy 0, policy_version 107896 (0.0009) -[2023-11-28 03:02:16,877][87426] Updated weights for policy 1, policy_version 107710 (0.0007) -[2023-11-28 03:02:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 55197696. Throughput: 0: 2651.5, 1: 2685.5. Samples: 55206816. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:18,446][86177] Avg episode reward: [(0, '-566.490'), (1, '-522.850')] -[2023-11-28 03:02:18,460][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000107904_27623424.pth... -[2023-11-28 03:02:18,460][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000107712_27574272.pth... -[2023-11-28 03:02:18,506][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000105152_26918912.pth -[2023-11-28 03:02:18,506][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000105376_26976256.pth -[2023-11-28 03:02:19,303][87424] Updated weights for policy 0, policy_version 107906 (0.0008) -[2023-11-28 03:02:19,316][87426] Updated weights for policy 1, policy_version 107720 (0.0011) -[2023-11-28 03:02:19,690][87424] Updated weights for policy 0, policy_version 107916 (0.0008) -[2023-11-28 03:02:19,695][87426] Updated weights for policy 1, policy_version 107730 (0.0008) -[2023-11-28 03:02:20,068][87424] Updated weights for policy 0, policy_version 107926 (0.0011) -[2023-11-28 03:02:20,077][87426] Updated weights for policy 1, policy_version 107740 (0.0011) -[2023-11-28 03:02:20,448][87424] Updated weights for policy 0, policy_version 107936 (0.0011) -[2023-11-28 03:02:22,710][87426] Updated weights for policy 1, policy_version 107750 (0.0011) -[2023-11-28 03:02:22,972][87424] Updated weights for policy 0, policy_version 107946 (0.0011) -[2023-11-28 03:02:23,084][87426] Updated weights for policy 1, policy_version 107760 (0.0012) -[2023-11-28 03:02:23,356][87424] Updated weights for policy 0, policy_version 107956 (0.0011) -[2023-11-28 03:02:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 55214080. Throughput: 0: 2683.3, 1: 2662.2. Samples: 55239240. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:23,445][86177] Avg episode reward: [(0, '-560.850'), (1, '-528.620')] -[2023-11-28 03:02:23,465][87426] Updated weights for policy 1, policy_version 107770 (0.0011) -[2023-11-28 03:02:23,741][87424] Updated weights for policy 0, policy_version 107966 (0.0012) -[2023-11-28 03:02:25,268][87426] Updated weights for policy 1, policy_version 107780 (0.0008) -[2023-11-28 03:02:25,654][87426] Updated weights for policy 1, policy_version 107790 (0.0007) -[2023-11-28 03:02:25,775][87424] Updated weights for policy 0, policy_version 107976 (0.0012) -[2023-11-28 03:02:26,038][87426] Updated weights for policy 1, policy_version 107800 (0.0008) -[2023-11-28 03:02:26,160][87424] Updated weights for policy 0, policy_version 107986 (0.0011) -[2023-11-28 03:02:26,546][87424] Updated weights for policy 0, policy_version 107996 (0.0012) -[2023-11-28 03:02:28,125][87426] Updated weights for policy 1, policy_version 107810 (0.0008) -[2023-11-28 03:02:28,415][87424] Updated weights for policy 0, policy_version 108006 (0.0012) -[2023-11-28 03:02:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55246848. Throughput: 0: 2693.3, 1: 2670.6. Samples: 55264008. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:28,446][86177] Avg episode reward: [(0, '-604.370'), (1, '-528.790')] -[2023-11-28 03:02:28,507][87426] Updated weights for policy 1, policy_version 107820 (0.0007) -[2023-11-28 03:02:28,793][87424] Updated weights for policy 0, policy_version 108016 (0.0011) -[2023-11-28 03:02:28,893][87426] Updated weights for policy 1, policy_version 107830 (0.0009) -[2023-11-28 03:02:29,183][87424] Updated weights for policy 0, policy_version 108026 (0.0009) -[2023-11-28 03:02:29,268][87426] Updated weights for policy 1, policy_version 107840 (0.0009) -[2023-11-28 03:02:31,192][87424] Updated weights for policy 0, policy_version 108036 (0.0007) -[2023-11-28 03:02:31,571][87424] Updated weights for policy 0, policy_version 108046 (0.0008) -[2023-11-28 03:02:31,737][87426] Updated weights for policy 1, policy_version 107850 (0.0012) -[2023-11-28 03:02:31,954][87424] Updated weights for policy 0, policy_version 108056 (0.0010) -[2023-11-28 03:02:32,117][87426] Updated weights for policy 1, policy_version 107860 (0.0012) -[2023-11-28 03:02:32,490][87426] Updated weights for policy 1, policy_version 107870 (0.0012) -[2023-11-28 03:02:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 55279616. Throughput: 0: 2721.6, 1: 2678.1. Samples: 55288764. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:33,445][86177] Avg episode reward: [(0, '-599.640'), (1, '-526.690')] -[2023-11-28 03:02:34,339][87424] Updated weights for policy 0, policy_version 108066 (0.0010) -[2023-11-28 03:02:34,726][87424] Updated weights for policy 0, policy_version 108076 (0.0012) -[2023-11-28 03:02:35,013][87426] Updated weights for policy 1, policy_version 107880 (0.0010) -[2023-11-28 03:02:35,097][87424] Updated weights for policy 0, policy_version 108086 (0.0011) -[2023-11-28 03:02:35,395][87426] Updated weights for policy 1, policy_version 107890 (0.0011) -[2023-11-28 03:02:35,487][87424] Updated weights for policy 0, policy_version 108096 (0.0011) -[2023-11-28 03:02:35,775][87426] Updated weights for policy 1, policy_version 107900 (0.0011) -[2023-11-28 03:02:37,619][87424] Updated weights for policy 0, policy_version 108106 (0.0008) -[2023-11-28 03:02:37,778][87426] Updated weights for policy 1, policy_version 107910 (0.0011) -[2023-11-28 03:02:38,011][87424] Updated weights for policy 0, policy_version 108116 (0.0009) -[2023-11-28 03:02:38,157][87426] Updated weights for policy 1, policy_version 107920 (0.0012) -[2023-11-28 03:02:38,385][87424] Updated weights for policy 0, policy_version 108126 (0.0009) -[2023-11-28 03:02:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 55296000. Throughput: 0: 2692.5, 1: 2686.8. Samples: 55321404. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:38,445][86177] Avg episode reward: [(0, '-544.940'), (1, '-511.240')] -[2023-11-28 03:02:38,538][87426] Updated weights for policy 1, policy_version 107930 (0.0011) -[2023-11-28 03:02:40,606][87424] Updated weights for policy 0, policy_version 108136 (0.0011) -[2023-11-28 03:02:40,997][87424] Updated weights for policy 0, policy_version 108146 (0.0011) -[2023-11-28 03:02:41,105][87426] Updated weights for policy 1, policy_version 107940 (0.0009) -[2023-11-28 03:02:41,372][87424] Updated weights for policy 0, policy_version 108156 (0.0011) -[2023-11-28 03:02:41,476][87426] Updated weights for policy 1, policy_version 107950 (0.0012) -[2023-11-28 03:02:41,856][87426] Updated weights for policy 1, policy_version 107960 (0.0009) -[2023-11-28 03:02:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 55328768. Throughput: 0: 2699.6, 1: 2664.5. Samples: 55344456. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:43,445][86177] Avg episode reward: [(0, '-545.240'), (1, '-510.510')] -[2023-11-28 03:02:43,695][87424] Updated weights for policy 0, policy_version 108166 (0.0009) -[2023-11-28 03:02:44,071][87424] Updated weights for policy 0, policy_version 108176 (0.0008) -[2023-11-28 03:02:44,152][87426] Updated weights for policy 1, policy_version 107970 (0.0010) -[2023-11-28 03:02:44,454][87424] Updated weights for policy 0, policy_version 108186 (0.0007) -[2023-11-28 03:02:44,532][87426] Updated weights for policy 1, policy_version 107980 (0.0012) -[2023-11-28 03:02:44,911][87426] Updated weights for policy 1, policy_version 107990 (0.0012) -[2023-11-28 03:02:45,297][87426] Updated weights for policy 1, policy_version 108000 (0.0011) -[2023-11-28 03:02:46,240][87424] Updated weights for policy 0, policy_version 108196 (0.0010) -[2023-11-28 03:02:46,620][87424] Updated weights for policy 0, policy_version 108206 (0.0012) -[2023-11-28 03:02:46,996][87424] Updated weights for policy 0, policy_version 108216 (0.0012) -[2023-11-28 03:02:47,023][87426] Updated weights for policy 1, policy_version 108010 (0.0011) -[2023-11-28 03:02:47,399][87426] Updated weights for policy 1, policy_version 108020 (0.0012) -[2023-11-28 03:02:47,775][87426] Updated weights for policy 1, policy_version 108030 (0.0011) -[2023-11-28 03:02:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 55361536. Throughput: 0: 2715.5, 1: 2654.4. Samples: 55369324. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:48,445][86177] Avg episode reward: [(0, '-501.450'), (1, '-511.300')] -[2023-11-28 03:02:48,625][87424] Updated weights for policy 0, policy_version 108226 (0.0009) -[2023-11-28 03:02:49,017][87424] Updated weights for policy 0, policy_version 108236 (0.0008) -[2023-11-28 03:02:49,404][87424] Updated weights for policy 0, policy_version 108246 (0.0008) -[2023-11-28 03:02:49,788][87424] Updated weights for policy 0, policy_version 108256 (0.0008) -[2023-11-28 03:02:50,384][87426] Updated weights for policy 1, policy_version 108040 (0.0009) -[2023-11-28 03:02:50,771][87426] Updated weights for policy 1, policy_version 108050 (0.0008) -[2023-11-28 03:02:51,153][87426] Updated weights for policy 1, policy_version 108060 (0.0010) -[2023-11-28 03:02:51,889][87424] Updated weights for policy 0, policy_version 108266 (0.0012) -[2023-11-28 03:02:52,276][87424] Updated weights for policy 0, policy_version 108276 (0.0011) -[2023-11-28 03:02:52,656][87424] Updated weights for policy 0, policy_version 108286 (0.0011) -[2023-11-28 03:02:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55386112. Throughput: 0: 2745.4, 1: 2645.3. Samples: 55401872. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 03:02:53,445][86177] Avg episode reward: [(0, '-499.210'), (1, '-511.080')] -[2023-11-28 03:02:53,611][87426] Updated weights for policy 1, policy_version 108070 (0.0009) -[2023-11-28 03:02:53,988][87426] Updated weights for policy 1, policy_version 108080 (0.0009) -[2023-11-28 03:02:54,373][87426] Updated weights for policy 1, policy_version 108090 (0.0007) -[2023-11-28 03:02:55,243][87424] Updated weights for policy 0, policy_version 108296 (0.0011) -[2023-11-28 03:02:55,637][87424] Updated weights for policy 0, policy_version 108306 (0.0012) -[2023-11-28 03:02:56,020][87424] Updated weights for policy 0, policy_version 108316 (0.0011) -[2023-11-28 03:02:56,866][87426] Updated weights for policy 1, policy_version 108100 (0.0008) -[2023-11-28 03:02:57,235][87426] Updated weights for policy 1, policy_version 108110 (0.0010) -[2023-11-28 03:02:57,612][87426] Updated weights for policy 1, policy_version 108120 (0.0011) -[2023-11-28 03:02:58,323][87424] Updated weights for policy 0, policy_version 108326 (0.0009) -[2023-11-28 03:02:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 55410688. Throughput: 0: 2754.5, 1: 2648.6. Samples: 55425068. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:02:58,445][86177] Avg episode reward: [(0, '-542.960'), (1, '-507.420')] -[2023-11-28 03:02:58,697][87424] Updated weights for policy 0, policy_version 108336 (0.0007) -[2023-11-28 03:02:59,080][87424] Updated weights for policy 0, policy_version 108346 (0.0008) -[2023-11-28 03:02:59,750][87426] Updated weights for policy 1, policy_version 108130 (0.0011) -[2023-11-28 03:03:00,126][87426] Updated weights for policy 1, policy_version 108140 (0.0009) -[2023-11-28 03:03:00,496][87426] Updated weights for policy 1, policy_version 108150 (0.0009) -[2023-11-28 03:03:00,880][87426] Updated weights for policy 1, policy_version 108160 (0.0011) -[2023-11-28 03:03:01,205][87424] Updated weights for policy 0, policy_version 108356 (0.0008) -[2023-11-28 03:03:01,585][87424] Updated weights for policy 0, policy_version 108366 (0.0008) -[2023-11-28 03:03:01,973][87424] Updated weights for policy 0, policy_version 108376 (0.0009) -[2023-11-28 03:03:03,405][87426] Updated weights for policy 1, policy_version 108170 (0.0009) -[2023-11-28 03:03:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55435264. Throughput: 0: 2761.6, 1: 2635.1. Samples: 55449668. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:03,445][86177] Avg episode reward: [(0, '-538.180'), (1, '-500.190')] -[2023-11-28 03:03:03,785][87426] Updated weights for policy 1, policy_version 108180 (0.0008) -[2023-11-28 03:03:04,165][87426] Updated weights for policy 1, policy_version 108190 (0.0007) -[2023-11-28 03:03:04,180][87424] Updated weights for policy 0, policy_version 108386 (0.0009) -[2023-11-28 03:03:04,569][87424] Updated weights for policy 0, policy_version 108396 (0.0008) -[2023-11-28 03:03:04,954][87424] Updated weights for policy 0, policy_version 108406 (0.0008) -[2023-11-28 03:03:05,344][87424] Updated weights for policy 0, policy_version 108416 (0.0008) -[2023-11-28 03:03:06,241][87426] Updated weights for policy 1, policy_version 108200 (0.0008) -[2023-11-28 03:03:06,635][87426] Updated weights for policy 1, policy_version 108210 (0.0009) -[2023-11-28 03:03:06,995][87424] Updated weights for policy 0, policy_version 108426 (0.0011) -[2023-11-28 03:03:07,004][87426] Updated weights for policy 1, policy_version 108220 (0.0011) -[2023-11-28 03:03:07,379][87424] Updated weights for policy 0, policy_version 108436 (0.0009) -[2023-11-28 03:03:07,760][87424] Updated weights for policy 0, policy_version 108446 (0.0008) -[2023-11-28 03:03:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 55468032. Throughput: 0: 2743.4, 1: 2632.6. Samples: 55481160. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:08,445][86177] Avg episode reward: [(0, '-539.870'), (1, '-498.450')] -[2023-11-28 03:03:09,052][87426] Updated weights for policy 1, policy_version 108230 (0.0011) -[2023-11-28 03:03:09,430][87426] Updated weights for policy 1, policy_version 108240 (0.0011) -[2023-11-28 03:03:09,815][87426] Updated weights for policy 1, policy_version 108250 (0.0008) -[2023-11-28 03:03:10,280][87424] Updated weights for policy 0, policy_version 108456 (0.0009) -[2023-11-28 03:03:10,663][87424] Updated weights for policy 0, policy_version 108466 (0.0010) -[2023-11-28 03:03:11,052][87424] Updated weights for policy 0, policy_version 108476 (0.0009) -[2023-11-28 03:03:12,313][87426] Updated weights for policy 1, policy_version 108260 (0.0011) -[2023-11-28 03:03:12,691][87426] Updated weights for policy 1, policy_version 108270 (0.0011) -[2023-11-28 03:03:13,072][87426] Updated weights for policy 1, policy_version 108280 (0.0010) -[2023-11-28 03:03:13,227][87424] Updated weights for policy 0, policy_version 108486 (0.0010) -[2023-11-28 03:03:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 55492608. Throughput: 0: 2730.2, 1: 2639.7. Samples: 55505656. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:13,445][86177] Avg episode reward: [(0, '-542.040'), (1, '-495.560')] -[2023-11-28 03:03:13,598][87424] Updated weights for policy 0, policy_version 108496 (0.0012) -[2023-11-28 03:03:13,985][87424] Updated weights for policy 0, policy_version 108506 (0.0012) -[2023-11-28 03:03:15,073][87426] Updated weights for policy 1, policy_version 108290 (0.0009) -[2023-11-28 03:03:15,454][87426] Updated weights for policy 1, policy_version 108300 (0.0012) -[2023-11-28 03:03:15,830][87426] Updated weights for policy 1, policy_version 108310 (0.0012) -[2023-11-28 03:03:16,208][87426] Updated weights for policy 1, policy_version 108320 (0.0012) -[2023-11-28 03:03:16,432][87424] Updated weights for policy 0, policy_version 108516 (0.0010) -[2023-11-28 03:03:16,814][87424] Updated weights for policy 0, policy_version 108526 (0.0008) -[2023-11-28 03:03:17,199][87424] Updated weights for policy 0, policy_version 108536 (0.0008) -[2023-11-28 03:03:18,182][87426] Updated weights for policy 1, policy_version 108330 (0.0012) -[2023-11-28 03:03:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55517184. Throughput: 0: 2727.4, 1: 2647.5. Samples: 55530632. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:18,445][86177] Avg episode reward: [(0, '-504.490'), (1, '-497.560')] -[2023-11-28 03:03:18,551][87426] Updated weights for policy 1, policy_version 108340 (0.0012) -[2023-11-28 03:03:18,936][87426] Updated weights for policy 1, policy_version 108350 (0.0011) -[2023-11-28 03:03:18,975][87424] Updated weights for policy 0, policy_version 108546 (0.0011) -[2023-11-28 03:03:19,361][87424] Updated weights for policy 0, policy_version 108556 (0.0010) -[2023-11-28 03:03:19,745][87424] Updated weights for policy 0, policy_version 108566 (0.0011) -[2023-11-28 03:03:20,132][87424] Updated weights for policy 0, policy_version 108576 (0.0012) -[2023-11-28 03:03:20,774][87426] Updated weights for policy 1, policy_version 108360 (0.0011) -[2023-11-28 03:03:21,157][87426] Updated weights for policy 1, policy_version 108370 (0.0012) -[2023-11-28 03:03:21,539][87426] Updated weights for policy 1, policy_version 108380 (0.0012) -[2023-11-28 03:03:22,173][87424] Updated weights for policy 0, policy_version 108586 (0.0011) -[2023-11-28 03:03:22,554][87424] Updated weights for policy 0, policy_version 108596 (0.0010) -[2023-11-28 03:03:22,944][87424] Updated weights for policy 0, policy_version 108606 (0.0009) -[2023-11-28 03:03:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 55549952. Throughput: 0: 2731.7, 1: 2654.6. Samples: 55563788. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:23,445][86177] Avg episode reward: [(0, '-503.510'), (1, '-496.740')] -[2023-11-28 03:03:23,785][87426] Updated weights for policy 1, policy_version 108390 (0.0012) -[2023-11-28 03:03:24,161][87426] Updated weights for policy 1, policy_version 108400 (0.0012) -[2023-11-28 03:03:24,545][87426] Updated weights for policy 1, policy_version 108410 (0.0012) -[2023-11-28 03:03:25,497][87424] Updated weights for policy 0, policy_version 108616 (0.0012) -[2023-11-28 03:03:25,883][87424] Updated weights for policy 0, policy_version 108626 (0.0011) -[2023-11-28 03:03:26,264][87424] Updated weights for policy 0, policy_version 108636 (0.0009) -[2023-11-28 03:03:26,888][87426] Updated weights for policy 1, policy_version 108420 (0.0010) -[2023-11-28 03:03:27,257][87426] Updated weights for policy 1, policy_version 108430 (0.0010) -[2023-11-28 03:03:27,633][87426] Updated weights for policy 1, policy_version 108440 (0.0008) -[2023-11-28 03:03:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 55574528. Throughput: 0: 2744.0, 1: 2683.3. Samples: 55588684. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:28,445][86177] Avg episode reward: [(0, '-500.150'), (1, '-508.690')] -[2023-11-28 03:03:28,568][87424] Updated weights for policy 0, policy_version 108646 (0.0010) -[2023-11-28 03:03:28,952][87424] Updated weights for policy 0, policy_version 108656 (0.0012) -[2023-11-28 03:03:29,340][87424] Updated weights for policy 0, policy_version 108666 (0.0011) -[2023-11-28 03:03:29,411][87426] Updated weights for policy 1, policy_version 108450 (0.0011) -[2023-11-28 03:03:29,800][87426] Updated weights for policy 1, policy_version 108460 (0.0012) -[2023-11-28 03:03:30,185][87426] Updated weights for policy 1, policy_version 108470 (0.0012) -[2023-11-28 03:03:30,562][87426] Updated weights for policy 1, policy_version 108480 (0.0012) -[2023-11-28 03:03:31,164][87424] Updated weights for policy 0, policy_version 108676 (0.0012) -[2023-11-28 03:03:31,544][87424] Updated weights for policy 0, policy_version 108686 (0.0012) -[2023-11-28 03:03:31,921][87424] Updated weights for policy 0, policy_version 108696 (0.0012) -[2023-11-28 03:03:33,139][87426] Updated weights for policy 1, policy_version 108490 (0.0009) -[2023-11-28 03:03:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 55599104. Throughput: 0: 2734.7, 1: 2678.7. Samples: 55612924. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:33,445][86177] Avg episode reward: [(0, '-495.680'), (1, '-509.970')] -[2023-11-28 03:03:33,521][87426] Updated weights for policy 1, policy_version 108500 (0.0007) -[2023-11-28 03:03:33,924][87426] Updated weights for policy 1, policy_version 108510 (0.0007) -[2023-11-28 03:03:33,984][87424] Updated weights for policy 0, policy_version 108706 (0.0012) -[2023-11-28 03:03:34,359][87424] Updated weights for policy 0, policy_version 108716 (0.0010) -[2023-11-28 03:03:34,741][87424] Updated weights for policy 0, policy_version 108726 (0.0008) -[2023-11-28 03:03:35,124][87424] Updated weights for policy 0, policy_version 108736 (0.0009) -[2023-11-28 03:03:35,959][87426] Updated weights for policy 1, policy_version 108520 (0.0008) -[2023-11-28 03:03:36,339][87426] Updated weights for policy 1, policy_version 108530 (0.0008) -[2023-11-28 03:03:36,715][87426] Updated weights for policy 1, policy_version 108540 (0.0009) -[2023-11-28 03:03:37,595][87424] Updated weights for policy 0, policy_version 108746 (0.0009) -[2023-11-28 03:03:37,974][87424] Updated weights for policy 0, policy_version 108756 (0.0009) -[2023-11-28 03:03:38,355][87424] Updated weights for policy 0, policy_version 108766 (0.0010) -[2023-11-28 03:03:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 55631872. Throughput: 0: 2705.9, 1: 2706.2. Samples: 55645416. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:38,445][86177] Avg episode reward: [(0, '-510.210'), (1, '-510.110')] -[2023-11-28 03:03:38,696][87426] Updated weights for policy 1, policy_version 108550 (0.0010) -[2023-11-28 03:03:39,080][87426] Updated weights for policy 1, policy_version 108560 (0.0009) -[2023-11-28 03:03:39,464][87426] Updated weights for policy 1, policy_version 108570 (0.0007) -[2023-11-28 03:03:40,954][87424] Updated weights for policy 0, policy_version 108776 (0.0010) -[2023-11-28 03:03:41,338][87424] Updated weights for policy 0, policy_version 108786 (0.0009) -[2023-11-28 03:03:41,473][87426] Updated weights for policy 1, policy_version 108580 (0.0009) -[2023-11-28 03:03:41,719][87424] Updated weights for policy 0, policy_version 108796 (0.0010) -[2023-11-28 03:03:41,855][87426] Updated weights for policy 1, policy_version 108590 (0.0011) -[2023-11-28 03:03:42,234][87426] Updated weights for policy 1, policy_version 108600 (0.0011) -[2023-11-28 03:03:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 55656448. Throughput: 0: 2695.3, 1: 2719.5. Samples: 55668732. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:43,445][86177] Avg episode reward: [(0, '-515.480'), (1, '-510.600')] -[2023-11-28 03:03:44,221][87424] Updated weights for policy 0, policy_version 108806 (0.0009) -[2023-11-28 03:03:44,603][87424] Updated weights for policy 0, policy_version 108816 (0.0007) -[2023-11-28 03:03:44,688][87426] Updated weights for policy 1, policy_version 108610 (0.0009) -[2023-11-28 03:03:44,980][87424] Updated weights for policy 0, policy_version 108826 (0.0007) -[2023-11-28 03:03:45,065][87426] Updated weights for policy 1, policy_version 108620 (0.0012) -[2023-11-28 03:03:45,453][87426] Updated weights for policy 1, policy_version 108630 (0.0012) -[2023-11-28 03:03:45,823][87426] Updated weights for policy 1, policy_version 108640 (0.0012) -[2023-11-28 03:03:47,364][87424] Updated weights for policy 0, policy_version 108836 (0.0007) -[2023-11-28 03:03:47,745][87424] Updated weights for policy 0, policy_version 108846 (0.0008) -[2023-11-28 03:03:48,127][87424] Updated weights for policy 0, policy_version 108856 (0.0009) -[2023-11-28 03:03:48,180][87426] Updated weights for policy 1, policy_version 108650 (0.0011) -[2023-11-28 03:03:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 55681024. Throughput: 0: 2683.3, 1: 2711.6. Samples: 55692440. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:48,445][86177] Avg episode reward: [(0, '-517.150'), (1, '-505.940')] -[2023-11-28 03:03:48,560][87426] Updated weights for policy 1, policy_version 108660 (0.0012) -[2023-11-28 03:03:48,940][87426] Updated weights for policy 1, policy_version 108670 (0.0012) -[2023-11-28 03:03:49,881][87424] Updated weights for policy 0, policy_version 108866 (0.0008) -[2023-11-28 03:03:50,272][87424] Updated weights for policy 0, policy_version 108876 (0.0012) -[2023-11-28 03:03:50,660][87424] Updated weights for policy 0, policy_version 108886 (0.0012) -[2023-11-28 03:03:51,044][87424] Updated weights for policy 0, policy_version 108896 (0.0011) -[2023-11-28 03:03:51,142][87426] Updated weights for policy 1, policy_version 108680 (0.0012) -[2023-11-28 03:03:51,522][87426] Updated weights for policy 1, policy_version 108690 (0.0012) -[2023-11-28 03:03:51,898][87426] Updated weights for policy 1, policy_version 108700 (0.0012) -[2023-11-28 03:03:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55705600. Throughput: 0: 2698.8, 1: 2712.0. Samples: 55724648. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:53,445][86177] Avg episode reward: [(0, '-568.380'), (1, '-515.750')] -[2023-11-28 03:03:53,469][87424] Updated weights for policy 0, policy_version 108906 (0.0010) -[2023-11-28 03:03:53,849][87424] Updated weights for policy 0, policy_version 108916 (0.0010) -[2023-11-28 03:03:54,234][87424] Updated weights for policy 0, policy_version 108926 (0.0011) -[2023-11-28 03:03:54,415][87426] Updated weights for policy 1, policy_version 108710 (0.0012) -[2023-11-28 03:03:54,785][87426] Updated weights for policy 1, policy_version 108720 (0.0012) -[2023-11-28 03:03:55,155][87426] Updated weights for policy 1, policy_version 108730 (0.0011) -[2023-11-28 03:03:56,485][87424] Updated weights for policy 0, policy_version 108936 (0.0012) -[2023-11-28 03:03:56,870][87424] Updated weights for policy 0, policy_version 108946 (0.0010) -[2023-11-28 03:03:56,881][87426] Updated weights for policy 1, policy_version 108740 (0.0008) -[2023-11-28 03:03:57,242][87424] Updated weights for policy 0, policy_version 108956 (0.0008) -[2023-11-28 03:03:57,257][87426] Updated weights for policy 1, policy_version 108750 (0.0008) -[2023-11-28 03:03:57,634][87426] Updated weights for policy 1, policy_version 108760 (0.0009) -[2023-11-28 03:03:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 55738368. Throughput: 0: 2692.2, 1: 2724.9. Samples: 55749424. Policy #0 lag: (min: 21.0, avg: 35.1, max: 53.0) -[2023-11-28 03:03:58,445][86177] Avg episode reward: [(0, '-553.510'), (1, '-528.300')] -[2023-11-28 03:03:59,616][87424] Updated weights for policy 0, policy_version 108966 (0.0010) -[2023-11-28 03:03:59,716][87426] Updated weights for policy 1, policy_version 108770 (0.0008) -[2023-11-28 03:03:59,995][87424] Updated weights for policy 0, policy_version 108976 (0.0009) -[2023-11-28 03:04:00,086][87426] Updated weights for policy 1, policy_version 108780 (0.0011) -[2023-11-28 03:04:00,385][87424] Updated weights for policy 0, policy_version 108986 (0.0009) -[2023-11-28 03:04:00,463][87426] Updated weights for policy 1, policy_version 108790 (0.0011) -[2023-11-28 03:04:00,845][87426] Updated weights for policy 1, policy_version 108800 (0.0008) -[2023-11-28 03:04:02,901][87424] Updated weights for policy 0, policy_version 108996 (0.0010) -[2023-11-28 03:04:03,279][87424] Updated weights for policy 0, policy_version 109006 (0.0008) -[2023-11-28 03:04:03,327][87426] Updated weights for policy 1, policy_version 108810 (0.0012) -[2023-11-28 03:04:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 55754752. Throughput: 0: 2674.6, 1: 2717.7. Samples: 55773284. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:03,445][86177] Avg episode reward: [(0, '-545.740'), (1, '-527.850')] -[2023-11-28 03:04:03,657][87424] Updated weights for policy 0, policy_version 109016 (0.0008) -[2023-11-28 03:04:03,704][87426] Updated weights for policy 1, policy_version 108820 (0.0012) -[2023-11-28 03:04:04,081][87426] Updated weights for policy 1, policy_version 108830 (0.0010) -[2023-11-28 03:04:05,565][87424] Updated weights for policy 0, policy_version 109026 (0.0011) -[2023-11-28 03:04:05,955][87424] Updated weights for policy 0, policy_version 109036 (0.0011) -[2023-11-28 03:04:06,139][87426] Updated weights for policy 1, policy_version 108840 (0.0010) -[2023-11-28 03:04:06,339][87424] Updated weights for policy 0, policy_version 109046 (0.0011) -[2023-11-28 03:04:06,522][87426] Updated weights for policy 1, policy_version 108850 (0.0010) -[2023-11-28 03:04:06,716][87424] Updated weights for policy 0, policy_version 109056 (0.0013) -[2023-11-28 03:04:06,903][87426] Updated weights for policy 1, policy_version 108860 (0.0009) -[2023-11-28 03:04:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 55787520. Throughput: 0: 2665.8, 1: 2698.8. Samples: 55805192. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:08,445][86177] Avg episode reward: [(0, '-542.420'), (1, '-535.890')] -[2023-11-28 03:04:08,929][87424] Updated weights for policy 0, policy_version 109066 (0.0010) -[2023-11-28 03:04:08,944][87426] Updated weights for policy 1, policy_version 108870 (0.0011) -[2023-11-28 03:04:09,318][87424] Updated weights for policy 0, policy_version 109076 (0.0009) -[2023-11-28 03:04:09,323][87426] Updated weights for policy 1, policy_version 108880 (0.0011) -[2023-11-28 03:04:09,699][87424] Updated weights for policy 0, policy_version 109086 (0.0009) -[2023-11-28 03:04:09,704][87426] Updated weights for policy 1, policy_version 108890 (0.0008) -[2023-11-28 03:04:11,554][87426] Updated weights for policy 1, policy_version 108900 (0.0009) -[2023-11-28 03:04:11,769][87424] Updated weights for policy 0, policy_version 109096 (0.0009) -[2023-11-28 03:04:11,945][87426] Updated weights for policy 1, policy_version 108910 (0.0010) -[2023-11-28 03:04:12,161][87424] Updated weights for policy 0, policy_version 109106 (0.0009) -[2023-11-28 03:04:12,322][87426] Updated weights for policy 1, policy_version 108920 (0.0011) -[2023-11-28 03:04:12,536][87424] Updated weights for policy 0, policy_version 109116 (0.0010) -[2023-11-28 03:04:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 55820288. Throughput: 0: 2647.6, 1: 2707.4. Samples: 55829656. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:13,445][86177] Avg episode reward: [(0, '-503.940'), (1, '-537.380')] -[2023-11-28 03:04:14,506][87424] Updated weights for policy 0, policy_version 109126 (0.0008) -[2023-11-28 03:04:14,730][87426] Updated weights for policy 1, policy_version 108930 (0.0010) -[2023-11-28 03:04:14,876][87424] Updated weights for policy 0, policy_version 109136 (0.0009) -[2023-11-28 03:04:15,116][87426] Updated weights for policy 1, policy_version 108940 (0.0007) -[2023-11-28 03:04:15,254][87424] Updated weights for policy 0, policy_version 109146 (0.0010) -[2023-11-28 03:04:15,489][87426] Updated weights for policy 1, policy_version 108950 (0.0009) -[2023-11-28 03:04:15,868][87426] Updated weights for policy 1, policy_version 108960 (0.0008) -[2023-11-28 03:04:17,634][87426] Updated weights for policy 1, policy_version 108970 (0.0012) -[2023-11-28 03:04:17,689][87424] Updated weights for policy 0, policy_version 109156 (0.0011) -[2023-11-28 03:04:18,011][87426] Updated weights for policy 1, policy_version 108980 (0.0012) -[2023-11-28 03:04:18,067][87424] Updated weights for policy 0, policy_version 109166 (0.0012) -[2023-11-28 03:04:18,385][87426] Updated weights for policy 1, policy_version 108990 (0.0012) -[2023-11-28 03:04:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 55836672. Throughput: 0: 2633.8, 1: 2722.8. Samples: 55853972. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:18,445][86177] Avg episode reward: [(0, '-528.340'), (1, '-528.310')] -[2023-11-28 03:04:18,450][87424] Updated weights for policy 0, policy_version 109176 (0.0007) -[2023-11-28 03:04:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000108992_27901952.pth... -[2023-11-28 03:04:18,488][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000106464_27254784.pth -[2023-11-28 03:04:18,768][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000109184_27951104.pth... -[2023-11-28 03:04:18,816][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000106656_27303936.pth -[2023-11-28 03:04:20,769][87426] Updated weights for policy 1, policy_version 109000 (0.0012) -[2023-11-28 03:04:20,825][87424] Updated weights for policy 0, policy_version 109186 (0.0010) -[2023-11-28 03:04:21,149][87426] Updated weights for policy 1, policy_version 109010 (0.0012) -[2023-11-28 03:04:21,204][87424] Updated weights for policy 0, policy_version 109196 (0.0012) -[2023-11-28 03:04:21,525][87426] Updated weights for policy 1, policy_version 109020 (0.0011) -[2023-11-28 03:04:21,584][87424] Updated weights for policy 0, policy_version 109206 (0.0011) -[2023-11-28 03:04:21,964][87424] Updated weights for policy 0, policy_version 109216 (0.0012) -[2023-11-28 03:04:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 55869440. Throughput: 0: 2633.8, 1: 2725.7. Samples: 55886592. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:23,445][86177] Avg episode reward: [(0, '-582.710'), (1, '-573.420')] -[2023-11-28 03:04:23,772][87426] Updated weights for policy 1, policy_version 109030 (0.0012) -[2023-11-28 03:04:23,917][87424] Updated weights for policy 0, policy_version 109226 (0.0012) -[2023-11-28 03:04:24,149][87426] Updated weights for policy 1, policy_version 109040 (0.0012) -[2023-11-28 03:04:24,295][87424] Updated weights for policy 0, policy_version 109236 (0.0011) -[2023-11-28 03:04:24,521][87426] Updated weights for policy 1, policy_version 109050 (0.0012) -[2023-11-28 03:04:24,678][87424] Updated weights for policy 0, policy_version 109246 (0.0010) -[2023-11-28 03:04:26,247][87426] Updated weights for policy 1, policy_version 109060 (0.0011) -[2023-11-28 03:04:26,632][87426] Updated weights for policy 1, policy_version 109070 (0.0011) -[2023-11-28 03:04:27,008][87426] Updated weights for policy 1, policy_version 109080 (0.0011) -[2023-11-28 03:04:27,108][87424] Updated weights for policy 0, policy_version 109256 (0.0010) -[2023-11-28 03:04:27,480][87424] Updated weights for policy 0, policy_version 109266 (0.0009) -[2023-11-28 03:04:27,863][87424] Updated weights for policy 0, policy_version 109276 (0.0007) -[2023-11-28 03:04:28,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 55902208. Throughput: 0: 2646.5, 1: 2750.9. Samples: 55911616. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:28,445][86177] Avg episode reward: [(0, '-583.150'), (1, '-582.910')] -[2023-11-28 03:04:29,050][87426] Updated weights for policy 1, policy_version 109090 (0.0008) -[2023-11-28 03:04:29,430][87426] Updated weights for policy 1, policy_version 109100 (0.0007) -[2023-11-28 03:04:29,816][87426] Updated weights for policy 1, policy_version 109110 (0.0010) -[2023-11-28 03:04:30,196][87426] Updated weights for policy 1, policy_version 109120 (0.0011) -[2023-11-28 03:04:30,276][87424] Updated weights for policy 0, policy_version 109286 (0.0009) -[2023-11-28 03:04:30,661][87424] Updated weights for policy 0, policy_version 109296 (0.0012) -[2023-11-28 03:04:31,043][87424] Updated weights for policy 0, policy_version 109306 (0.0009) -[2023-11-28 03:04:32,576][87426] Updated weights for policy 1, policy_version 109130 (0.0012) -[2023-11-28 03:04:32,954][87426] Updated weights for policy 1, policy_version 109140 (0.0012) -[2023-11-28 03:04:33,104][87424] Updated weights for policy 0, policy_version 109316 (0.0009) -[2023-11-28 03:04:33,325][87426] Updated weights for policy 1, policy_version 109150 (0.0012) -[2023-11-28 03:04:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 55926784. Throughput: 0: 2643.4, 1: 2764.7. Samples: 55935804. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:33,445][86177] Avg episode reward: [(0, '-582.990'), (1, '-587.210')] -[2023-11-28 03:04:33,489][87424] Updated weights for policy 0, policy_version 109326 (0.0012) -[2023-11-28 03:04:33,882][87424] Updated weights for policy 0, policy_version 109336 (0.0011) -[2023-11-28 03:04:34,970][87426] Updated weights for policy 1, policy_version 109160 (0.0009) -[2023-11-28 03:04:35,358][87426] Updated weights for policy 1, policy_version 109170 (0.0009) -[2023-11-28 03:04:35,729][87426] Updated weights for policy 1, policy_version 109180 (0.0007) -[2023-11-28 03:04:35,887][87424] Updated weights for policy 0, policy_version 109346 (0.0012) -[2023-11-28 03:04:36,261][87424] Updated weights for policy 0, policy_version 109356 (0.0007) -[2023-11-28 03:04:36,647][87424] Updated weights for policy 0, policy_version 109366 (0.0008) -[2023-11-28 03:04:37,028][87424] Updated weights for policy 0, policy_version 109376 (0.0012) -[2023-11-28 03:04:37,765][87426] Updated weights for policy 1, policy_version 109190 (0.0010) -[2023-11-28 03:04:38,130][87426] Updated weights for policy 1, policy_version 109200 (0.0010) -[2023-11-28 03:04:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 55951360. Throughput: 0: 2652.5, 1: 2805.9. Samples: 55970276. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:38,445][86177] Avg episode reward: [(0, '-589.570'), (1, '-597.530')] -[2023-11-28 03:04:38,516][87426] Updated weights for policy 1, policy_version 109210 (0.0009) -[2023-11-28 03:04:38,957][87424] Updated weights for policy 0, policy_version 109386 (0.0012) -[2023-11-28 03:04:39,331][87424] Updated weights for policy 0, policy_version 109396 (0.0012) -[2023-11-28 03:04:39,718][87424] Updated weights for policy 0, policy_version 109406 (0.0011) -[2023-11-28 03:04:41,040][87426] Updated weights for policy 1, policy_version 109220 (0.0011) -[2023-11-28 03:04:41,407][87426] Updated weights for policy 1, policy_version 109230 (0.0012) -[2023-11-28 03:04:41,784][87426] Updated weights for policy 1, policy_version 109240 (0.0012) -[2023-11-28 03:04:42,237][87424] Updated weights for policy 0, policy_version 109416 (0.0009) -[2023-11-28 03:04:42,620][87424] Updated weights for policy 0, policy_version 109426 (0.0008) -[2023-11-28 03:04:43,007][87424] Updated weights for policy 0, policy_version 109436 (0.0009) -[2023-11-28 03:04:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 55984128. Throughput: 0: 2667.9, 1: 2765.0. Samples: 55993904. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:43,445][86177] Avg episode reward: [(0, '-634.350'), (1, '-595.760')] -[2023-11-28 03:04:44,397][87426] Updated weights for policy 1, policy_version 109250 (0.0010) -[2023-11-28 03:04:44,785][87426] Updated weights for policy 1, policy_version 109260 (0.0007) -[2023-11-28 03:04:45,150][87424] Updated weights for policy 0, policy_version 109446 (0.0009) -[2023-11-28 03:04:45,159][87426] Updated weights for policy 1, policy_version 109270 (0.0009) -[2023-11-28 03:04:45,528][87424] Updated weights for policy 0, policy_version 109456 (0.0012) -[2023-11-28 03:04:45,536][87426] Updated weights for policy 1, policy_version 109280 (0.0012) -[2023-11-28 03:04:45,910][87424] Updated weights for policy 0, policy_version 109466 (0.0011) -[2023-11-28 03:04:47,261][87426] Updated weights for policy 1, policy_version 109290 (0.0012) -[2023-11-28 03:04:47,637][87426] Updated weights for policy 1, policy_version 109300 (0.0012) -[2023-11-28 03:04:47,843][87424] Updated weights for policy 0, policy_version 109476 (0.0011) -[2023-11-28 03:04:48,009][87426] Updated weights for policy 1, policy_version 109310 (0.0011) -[2023-11-28 03:04:48,233][87424] Updated weights for policy 0, policy_version 109486 (0.0012) -[2023-11-28 03:04:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56008704. Throughput: 0: 2652.9, 1: 2783.5. Samples: 56017920. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:48,445][86177] Avg episode reward: [(0, '-580.560'), (1, '-578.420')] -[2023-11-28 03:04:48,613][87424] Updated weights for policy 0, policy_version 109496 (0.0010) -[2023-11-28 03:04:50,015][87426] Updated weights for policy 1, policy_version 109320 (0.0010) -[2023-11-28 03:04:50,395][87426] Updated weights for policy 1, policy_version 109330 (0.0008) -[2023-11-28 03:04:50,782][87426] Updated weights for policy 1, policy_version 109340 (0.0012) -[2023-11-28 03:04:50,994][87424] Updated weights for policy 0, policy_version 109506 (0.0008) -[2023-11-28 03:04:51,384][87424] Updated weights for policy 0, policy_version 109516 (0.0011) -[2023-11-28 03:04:51,756][87424] Updated weights for policy 0, policy_version 109526 (0.0010) -[2023-11-28 03:04:52,129][87424] Updated weights for policy 0, policy_version 109536 (0.0009) -[2023-11-28 03:04:53,322][87426] Updated weights for policy 1, policy_version 109350 (0.0011) -[2023-11-28 03:04:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56033280. Throughput: 0: 2680.4, 1: 2793.8. Samples: 56051532. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:53,445][86177] Avg episode reward: [(0, '-581.710'), (1, '-573.740')] -[2023-11-28 03:04:53,700][87426] Updated weights for policy 1, policy_version 109360 (0.0011) -[2023-11-28 03:04:54,082][87424] Updated weights for policy 0, policy_version 109546 (0.0009) -[2023-11-28 03:04:54,083][87426] Updated weights for policy 1, policy_version 109370 (0.0011) -[2023-11-28 03:04:54,465][87424] Updated weights for policy 0, policy_version 109556 (0.0008) -[2023-11-28 03:04:54,848][87424] Updated weights for policy 0, policy_version 109566 (0.0008) -[2023-11-28 03:04:56,417][87426] Updated weights for policy 1, policy_version 109380 (0.0009) -[2023-11-28 03:04:56,645][87424] Updated weights for policy 0, policy_version 109576 (0.0009) -[2023-11-28 03:04:56,796][87426] Updated weights for policy 1, policy_version 109390 (0.0011) -[2023-11-28 03:04:57,024][87424] Updated weights for policy 0, policy_version 109586 (0.0012) -[2023-11-28 03:04:57,171][87426] Updated weights for policy 1, policy_version 109400 (0.0011) -[2023-11-28 03:04:57,410][87424] Updated weights for policy 0, policy_version 109596 (0.0012) -[2023-11-28 03:04:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56066048. Throughput: 0: 2702.3, 1: 2760.3. Samples: 56075472. Policy #0 lag: (min: 34.0, avg: 54.6, max: 68.0) -[2023-11-28 03:04:58,445][86177] Avg episode reward: [(0, '-582.330'), (1, '-571.680')] -[2023-11-28 03:04:59,401][87426] Updated weights for policy 1, policy_version 109410 (0.0012) -[2023-11-28 03:04:59,789][87426] Updated weights for policy 1, policy_version 109420 (0.0011) -[2023-11-28 03:04:59,818][87424] Updated weights for policy 0, policy_version 109606 (0.0011) -[2023-11-28 03:05:00,171][87426] Updated weights for policy 1, policy_version 109430 (0.0008) -[2023-11-28 03:05:00,195][87424] Updated weights for policy 0, policy_version 109616 (0.0012) -[2023-11-28 03:05:00,541][87426] Updated weights for policy 1, policy_version 109440 (0.0010) -[2023-11-28 03:05:00,569][87424] Updated weights for policy 0, policy_version 109626 (0.0011) -[2023-11-28 03:05:02,363][87424] Updated weights for policy 0, policy_version 109636 (0.0011) -[2023-11-28 03:05:02,744][87424] Updated weights for policy 0, policy_version 109646 (0.0010) -[2023-11-28 03:05:02,912][87426] Updated weights for policy 1, policy_version 109450 (0.0012) -[2023-11-28 03:05:03,124][87424] Updated weights for policy 0, policy_version 109656 (0.0008) -[2023-11-28 03:05:03,289][87426] Updated weights for policy 1, policy_version 109460 (0.0008) -[2023-11-28 03:05:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 56090624. Throughput: 0: 2765.2, 1: 2750.4. Samples: 56102172. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:03,445][86177] Avg episode reward: [(0, '-541.960'), (1, '-554.370')] -[2023-11-28 03:05:03,673][87426] Updated weights for policy 1, policy_version 109470 (0.0008) -[2023-11-28 03:05:04,957][87424] Updated weights for policy 0, policy_version 109666 (0.0008) -[2023-11-28 03:05:05,342][87424] Updated weights for policy 0, policy_version 109676 (0.0011) -[2023-11-28 03:05:05,724][87424] Updated weights for policy 0, policy_version 109686 (0.0008) -[2023-11-28 03:05:06,105][87424] Updated weights for policy 0, policy_version 109696 (0.0008) -[2023-11-28 03:05:06,256][87426] Updated weights for policy 1, policy_version 109480 (0.0011) -[2023-11-28 03:05:06,639][87426] Updated weights for policy 1, policy_version 109490 (0.0012) -[2023-11-28 03:05:07,018][87426] Updated weights for policy 1, policy_version 109500 (0.0012) -[2023-11-28 03:05:07,965][87424] Updated weights for policy 0, policy_version 109706 (0.0010) -[2023-11-28 03:05:08,344][87424] Updated weights for policy 0, policy_version 109716 (0.0009) -[2023-11-28 03:05:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56115200. Throughput: 0: 2792.5, 1: 2733.3. Samples: 56135256. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:08,445][86177] Avg episode reward: [(0, '-546.400'), (1, '-573.040')] -[2023-11-28 03:05:08,736][87424] Updated weights for policy 0, policy_version 109726 (0.0009) -[2023-11-28 03:05:08,832][87426] Updated weights for policy 1, policy_version 109510 (0.0011) -[2023-11-28 03:05:09,210][87426] Updated weights for policy 1, policy_version 109520 (0.0008) -[2023-11-28 03:05:09,575][87426] Updated weights for policy 1, policy_version 109530 (0.0008) -[2023-11-28 03:05:10,951][87424] Updated weights for policy 0, policy_version 109736 (0.0012) -[2023-11-28 03:05:11,333][87424] Updated weights for policy 0, policy_version 109746 (0.0012) -[2023-11-28 03:05:11,713][87424] Updated weights for policy 0, policy_version 109756 (0.0012) -[2023-11-28 03:05:12,003][87426] Updated weights for policy 1, policy_version 109540 (0.0009) -[2023-11-28 03:05:12,377][87426] Updated weights for policy 1, policy_version 109550 (0.0012) -[2023-11-28 03:05:12,756][87426] Updated weights for policy 1, policy_version 109560 (0.0012) -[2023-11-28 03:05:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 56147968. Throughput: 0: 2793.9, 1: 2706.4. Samples: 56159128. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:13,446][86177] Avg episode reward: [(0, '-546.070'), (1, '-592.640')] -[2023-11-28 03:05:13,839][87424] Updated weights for policy 0, policy_version 109766 (0.0012) -[2023-11-28 03:05:14,217][87424] Updated weights for policy 0, policy_version 109776 (0.0011) -[2023-11-28 03:05:14,607][87424] Updated weights for policy 0, policy_version 109786 (0.0012) -[2023-11-28 03:05:14,724][87426] Updated weights for policy 1, policy_version 109570 (0.0012) -[2023-11-28 03:05:15,112][87426] Updated weights for policy 1, policy_version 109580 (0.0011) -[2023-11-28 03:05:15,485][87426] Updated weights for policy 1, policy_version 109590 (0.0011) -[2023-11-28 03:05:15,868][87426] Updated weights for policy 1, policy_version 109600 (0.0011) -[2023-11-28 03:05:16,776][87424] Updated weights for policy 0, policy_version 109796 (0.0010) -[2023-11-28 03:05:17,158][87424] Updated weights for policy 0, policy_version 109806 (0.0012) -[2023-11-28 03:05:17,538][87424] Updated weights for policy 0, policy_version 109816 (0.0011) -[2023-11-28 03:05:17,776][87426] Updated weights for policy 1, policy_version 109610 (0.0012) -[2023-11-28 03:05:18,162][87426] Updated weights for policy 1, policy_version 109620 (0.0011) -[2023-11-28 03:05:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 56172544. Throughput: 0: 2826.8, 1: 2710.2. Samples: 56184972. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:18,445][86177] Avg episode reward: [(0, '-531.280'), (1, '-583.490')] -[2023-11-28 03:05:18,538][87426] Updated weights for policy 1, policy_version 109630 (0.0011) -[2023-11-28 03:05:19,503][87424] Updated weights for policy 0, policy_version 109826 (0.0011) -[2023-11-28 03:05:19,881][87424] Updated weights for policy 0, policy_version 109836 (0.0011) -[2023-11-28 03:05:20,265][87424] Updated weights for policy 0, policy_version 109846 (0.0011) -[2023-11-28 03:05:20,644][87424] Updated weights for policy 0, policy_version 109856 (0.0009) -[2023-11-28 03:05:20,697][87426] Updated weights for policy 1, policy_version 109640 (0.0011) -[2023-11-28 03:05:21,070][87426] Updated weights for policy 1, policy_version 109650 (0.0012) -[2023-11-28 03:05:21,456][87426] Updated weights for policy 1, policy_version 109660 (0.0012) -[2023-11-28 03:05:22,483][87424] Updated weights for policy 0, policy_version 109866 (0.0012) -[2023-11-28 03:05:22,870][87424] Updated weights for policy 0, policy_version 109876 (0.0012) -[2023-11-28 03:05:23,246][87424] Updated weights for policy 0, policy_version 109886 (0.0012) -[2023-11-28 03:05:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 56205312. Throughput: 0: 2821.0, 1: 2686.3. Samples: 56218104. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:23,445][86177] Avg episode reward: [(0, '-528.630'), (1, '-570.230')] -[2023-11-28 03:05:23,717][87426] Updated weights for policy 1, policy_version 109670 (0.0012) -[2023-11-28 03:05:24,100][87426] Updated weights for policy 1, policy_version 109680 (0.0012) -[2023-11-28 03:05:24,477][87426] Updated weights for policy 1, policy_version 109690 (0.0009) -[2023-11-28 03:05:25,435][87424] Updated weights for policy 0, policy_version 109896 (0.0009) -[2023-11-28 03:05:25,821][87424] Updated weights for policy 0, policy_version 109906 (0.0008) -[2023-11-28 03:05:26,203][87424] Updated weights for policy 0, policy_version 109916 (0.0012) -[2023-11-28 03:05:26,708][87426] Updated weights for policy 1, policy_version 109700 (0.0009) -[2023-11-28 03:05:27,085][87426] Updated weights for policy 1, policy_version 109710 (0.0009) -[2023-11-28 03:05:27,471][87426] Updated weights for policy 1, policy_version 109720 (0.0010) -[2023-11-28 03:05:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56229888. Throughput: 0: 2810.7, 1: 2717.1. Samples: 56242652. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:28,445][86177] Avg episode reward: [(0, '-526.900'), (1, '-562.800')] -[2023-11-28 03:05:28,760][87424] Updated weights for policy 0, policy_version 109926 (0.0009) -[2023-11-28 03:05:29,143][87424] Updated weights for policy 0, policy_version 109936 (0.0008) -[2023-11-28 03:05:29,525][87424] Updated weights for policy 0, policy_version 109946 (0.0008) -[2023-11-28 03:05:29,634][87426] Updated weights for policy 1, policy_version 109730 (0.0011) -[2023-11-28 03:05:30,022][87426] Updated weights for policy 1, policy_version 109740 (0.0008) -[2023-11-28 03:05:30,397][87426] Updated weights for policy 1, policy_version 109750 (0.0010) -[2023-11-28 03:05:30,783][87426] Updated weights for policy 1, policy_version 109760 (0.0010) -[2023-11-28 03:05:31,799][87424] Updated weights for policy 0, policy_version 109956 (0.0010) -[2023-11-28 03:05:32,186][87424] Updated weights for policy 0, policy_version 109966 (0.0012) -[2023-11-28 03:05:32,565][87424] Updated weights for policy 0, policy_version 109976 (0.0010) -[2023-11-28 03:05:32,666][87426] Updated weights for policy 1, policy_version 109770 (0.0012) -[2023-11-28 03:05:33,037][87426] Updated weights for policy 1, policy_version 109780 (0.0012) -[2023-11-28 03:05:33,419][87426] Updated weights for policy 1, policy_version 109790 (0.0012) -[2023-11-28 03:05:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56254464. Throughput: 0: 2820.7, 1: 2713.7. Samples: 56266968. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:33,446][86177] Avg episode reward: [(0, '-573.760'), (1, '-547.360')] -[2023-11-28 03:05:34,563][87424] Updated weights for policy 0, policy_version 109986 (0.0008) -[2023-11-28 03:05:34,939][87424] Updated weights for policy 0, policy_version 109996 (0.0012) -[2023-11-28 03:05:35,326][87424] Updated weights for policy 0, policy_version 110006 (0.0012) -[2023-11-28 03:05:35,628][87426] Updated weights for policy 1, policy_version 109800 (0.0012) -[2023-11-28 03:05:35,719][87424] Updated weights for policy 0, policy_version 110016 (0.0011) -[2023-11-28 03:05:36,006][87426] Updated weights for policy 1, policy_version 109810 (0.0012) -[2023-11-28 03:05:36,379][87426] Updated weights for policy 1, policy_version 109820 (0.0011) -[2023-11-28 03:05:37,958][87424] Updated weights for policy 0, policy_version 110026 (0.0012) -[2023-11-28 03:05:38,302][87426] Updated weights for policy 1, policy_version 109830 (0.0012) -[2023-11-28 03:05:38,344][87424] Updated weights for policy 0, policy_version 110036 (0.0011) -[2023-11-28 03:05:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56279040. Throughput: 0: 2814.3, 1: 2720.4. Samples: 56300596. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:38,446][86177] Avg episode reward: [(0, '-604.190'), (1, '-543.290')] -[2023-11-28 03:05:38,688][87426] Updated weights for policy 1, policy_version 109840 (0.0012) -[2023-11-28 03:05:38,741][87424] Updated weights for policy 0, policy_version 110046 (0.0008) -[2023-11-28 03:05:39,070][87426] Updated weights for policy 1, policy_version 109850 (0.0012) -[2023-11-28 03:05:41,135][87424] Updated weights for policy 0, policy_version 110056 (0.0011) -[2023-11-28 03:05:41,521][87426] Updated weights for policy 1, policy_version 109860 (0.0011) -[2023-11-28 03:05:41,524][87424] Updated weights for policy 0, policy_version 110066 (0.0012) -[2023-11-28 03:05:41,901][87426] Updated weights for policy 1, policy_version 109870 (0.0011) -[2023-11-28 03:05:41,907][87424] Updated weights for policy 0, policy_version 110076 (0.0011) -[2023-11-28 03:05:42,280][87426] Updated weights for policy 1, policy_version 109880 (0.0012) -[2023-11-28 03:05:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 56311808. Throughput: 0: 2785.2, 1: 2747.4. Samples: 56324440. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:43,446][86177] Avg episode reward: [(0, '-665.340'), (1, '-553.240')] -[2023-11-28 03:05:44,014][87424] Updated weights for policy 0, policy_version 110086 (0.0008) -[2023-11-28 03:05:44,215][87426] Updated weights for policy 1, policy_version 109890 (0.0011) -[2023-11-28 03:05:44,393][87424] Updated weights for policy 0, policy_version 110096 (0.0010) -[2023-11-28 03:05:44,595][87426] Updated weights for policy 1, policy_version 109900 (0.0009) -[2023-11-28 03:05:44,778][87424] Updated weights for policy 0, policy_version 110106 (0.0011) -[2023-11-28 03:05:44,968][87426] Updated weights for policy 1, policy_version 109910 (0.0007) -[2023-11-28 03:05:45,341][87426] Updated weights for policy 1, policy_version 109920 (0.0008) -[2023-11-28 03:05:46,961][87424] Updated weights for policy 0, policy_version 110116 (0.0009) -[2023-11-28 03:05:47,339][87424] Updated weights for policy 0, policy_version 110126 (0.0008) -[2023-11-28 03:05:47,404][87426] Updated weights for policy 1, policy_version 109930 (0.0012) -[2023-11-28 03:05:47,709][87424] Updated weights for policy 0, policy_version 110136 (0.0010) -[2023-11-28 03:05:47,784][87426] Updated weights for policy 1, policy_version 109940 (0.0010) -[2023-11-28 03:05:48,173][87426] Updated weights for policy 1, policy_version 109950 (0.0011) -[2023-11-28 03:05:48,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 56344576. Throughput: 0: 2743.6, 1: 2750.1. Samples: 56349388. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:48,445][86177] Avg episode reward: [(0, '-714.300'), (1, '-547.050')] -[2023-11-28 03:05:49,868][87424] Updated weights for policy 0, policy_version 110146 (0.0012) -[2023-11-28 03:05:50,249][87424] Updated weights for policy 0, policy_version 110156 (0.0009) -[2023-11-28 03:05:50,629][87424] Updated weights for policy 0, policy_version 110166 (0.0008) -[2023-11-28 03:05:50,693][87426] Updated weights for policy 1, policy_version 109960 (0.0011) -[2023-11-28 03:05:51,017][87424] Updated weights for policy 0, policy_version 110176 (0.0008) -[2023-11-28 03:05:51,073][87426] Updated weights for policy 1, policy_version 109970 (0.0010) -[2023-11-28 03:05:51,454][87426] Updated weights for policy 1, policy_version 109980 (0.0009) -[2023-11-28 03:05:53,398][87424] Updated weights for policy 0, policy_version 110186 (0.0012) -[2023-11-28 03:05:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56360960. Throughput: 0: 2720.9, 1: 2742.8. Samples: 56381120. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:53,445][86177] Avg episode reward: [(0, '-801.930'), (1, '-587.830')] -[2023-11-28 03:05:53,474][87426] Updated weights for policy 1, policy_version 109990 (0.0011) -[2023-11-28 03:05:53,772][87424] Updated weights for policy 0, policy_version 110196 (0.0012) -[2023-11-28 03:05:53,849][87426] Updated weights for policy 1, policy_version 110000 (0.0012) -[2023-11-28 03:05:54,156][87424] Updated weights for policy 0, policy_version 110206 (0.0012) -[2023-11-28 03:05:54,227][87426] Updated weights for policy 1, policy_version 110010 (0.0010) -[2023-11-28 03:05:56,101][87424] Updated weights for policy 0, policy_version 110216 (0.0008) -[2023-11-28 03:05:56,293][87426] Updated weights for policy 1, policy_version 110020 (0.0012) -[2023-11-28 03:05:56,483][87424] Updated weights for policy 0, policy_version 110226 (0.0007) -[2023-11-28 03:05:56,672][87426] Updated weights for policy 1, policy_version 110030 (0.0011) -[2023-11-28 03:05:56,867][87424] Updated weights for policy 0, policy_version 110236 (0.0007) -[2023-11-28 03:05:57,061][87426] Updated weights for policy 1, policy_version 110040 (0.0011) -[2023-11-28 03:05:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 56393728. Throughput: 0: 2723.2, 1: 2774.9. Samples: 56406544. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:05:58,445][86177] Avg episode reward: [(0, '-816.810'), (1, '-616.100')] -[2023-11-28 03:05:58,905][87426] Updated weights for policy 1, policy_version 110050 (0.0011) -[2023-11-28 03:05:59,129][87424] Updated weights for policy 0, policy_version 110246 (0.0008) -[2023-11-28 03:05:59,276][87426] Updated weights for policy 1, policy_version 110060 (0.0008) -[2023-11-28 03:05:59,500][87424] Updated weights for policy 0, policy_version 110256 (0.0010) -[2023-11-28 03:05:59,657][87426] Updated weights for policy 1, policy_version 110070 (0.0007) -[2023-11-28 03:05:59,881][87424] Updated weights for policy 0, policy_version 110266 (0.0011) -[2023-11-28 03:06:00,034][87426] Updated weights for policy 1, policy_version 110080 (0.0014) -[2023-11-28 03:06:01,815][87426] Updated weights for policy 1, policy_version 110090 (0.0012) -[2023-11-28 03:06:02,167][87424] Updated weights for policy 0, policy_version 110276 (0.0012) -[2023-11-28 03:06:02,195][87426] Updated weights for policy 1, policy_version 110100 (0.0011) -[2023-11-28 03:06:02,546][87424] Updated weights for policy 0, policy_version 110286 (0.0012) -[2023-11-28 03:06:02,569][87426] Updated weights for policy 1, policy_version 110110 (0.0011) -[2023-11-28 03:06:02,919][87424] Updated weights for policy 0, policy_version 110296 (0.0012) -[2023-11-28 03:06:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 56426496. Throughput: 0: 2709.1, 1: 2785.3. Samples: 56432220. Policy #0 lag: (min: 25.0, avg: 46.7, max: 50.0) -[2023-11-28 03:06:03,445][86177] Avg episode reward: [(0, '-753.760'), (1, '-597.010')] -[2023-11-28 03:06:04,730][87424] Updated weights for policy 0, policy_version 110306 (0.0012) -[2023-11-28 03:06:04,975][87426] Updated weights for policy 1, policy_version 110120 (0.0010) -[2023-11-28 03:06:05,125][87424] Updated weights for policy 0, policy_version 110316 (0.0010) -[2023-11-28 03:06:05,360][87426] Updated weights for policy 1, policy_version 110130 (0.0011) -[2023-11-28 03:06:05,500][87424] Updated weights for policy 0, policy_version 110326 (0.0010) -[2023-11-28 03:06:05,732][87426] Updated weights for policy 1, policy_version 110140 (0.0008) -[2023-11-28 03:06:05,877][87424] Updated weights for policy 0, policy_version 110336 (0.0011) -[2023-11-28 03:06:07,655][87426] Updated weights for policy 1, policy_version 110150 (0.0008) -[2023-11-28 03:06:08,043][87426] Updated weights for policy 1, policy_version 110160 (0.0008) -[2023-11-28 03:06:08,212][87424] Updated weights for policy 0, policy_version 110346 (0.0011) -[2023-11-28 03:06:08,429][87426] Updated weights for policy 1, policy_version 110170 (0.0007) -[2023-11-28 03:06:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56442880. Throughput: 0: 2712.8, 1: 2802.5. Samples: 56466292. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:08,445][86177] Avg episode reward: [(0, '-702.440'), (1, '-586.160')] -[2023-11-28 03:06:08,594][87424] Updated weights for policy 0, policy_version 110356 (0.0012) -[2023-11-28 03:06:08,987][87424] Updated weights for policy 0, policy_version 110366 (0.0012) -[2023-11-28 03:06:10,764][87426] Updated weights for policy 1, policy_version 110180 (0.0010) -[2023-11-28 03:06:11,113][87424] Updated weights for policy 0, policy_version 110376 (0.0011) -[2023-11-28 03:06:11,143][87426] Updated weights for policy 1, policy_version 110190 (0.0011) -[2023-11-28 03:06:11,489][87424] Updated weights for policy 0, policy_version 110386 (0.0010) -[2023-11-28 03:06:11,528][87426] Updated weights for policy 1, policy_version 110200 (0.0012) -[2023-11-28 03:06:11,873][87424] Updated weights for policy 0, policy_version 110396 (0.0011) -[2023-11-28 03:06:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 56475648. Throughput: 0: 2717.1, 1: 2793.1. Samples: 56490608. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:13,445][86177] Avg episode reward: [(0, '-572.300'), (1, '-541.530')] -[2023-11-28 03:06:13,986][87426] Updated weights for policy 1, policy_version 110210 (0.0011) -[2023-11-28 03:06:14,025][87424] Updated weights for policy 0, policy_version 110406 (0.0008) -[2023-11-28 03:06:14,360][87426] Updated weights for policy 1, policy_version 110220 (0.0009) -[2023-11-28 03:06:14,409][87424] Updated weights for policy 0, policy_version 110416 (0.0010) -[2023-11-28 03:06:14,736][87426] Updated weights for policy 1, policy_version 110230 (0.0009) -[2023-11-28 03:06:14,787][87424] Updated weights for policy 0, policy_version 110426 (0.0010) -[2023-11-28 03:06:15,115][87426] Updated weights for policy 1, policy_version 110240 (0.0011) -[2023-11-28 03:06:16,836][87426] Updated weights for policy 1, policy_version 110250 (0.0012) -[2023-11-28 03:06:17,220][87426] Updated weights for policy 1, policy_version 110260 (0.0011) -[2023-11-28 03:06:17,302][87424] Updated weights for policy 0, policy_version 110436 (0.0012) -[2023-11-28 03:06:17,606][87426] Updated weights for policy 1, policy_version 110270 (0.0011) -[2023-11-28 03:06:17,683][87424] Updated weights for policy 0, policy_version 110446 (0.0012) -[2023-11-28 03:06:18,064][87424] Updated weights for policy 0, policy_version 110456 (0.0012) -[2023-11-28 03:06:18,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 56508416. Throughput: 0: 2730.4, 1: 2804.2. Samples: 56516024. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:18,446][86177] Avg episode reward: [(0, '-536.690'), (1, '-513.000')] -[2023-11-28 03:06:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000110272_28229632.pth... -[2023-11-28 03:06:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000110464_28278784.pth... -[2023-11-28 03:06:18,487][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000107712_27574272.pth -[2023-11-28 03:06:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000107904_27623424.pth -[2023-11-28 03:06:19,467][87426] Updated weights for policy 1, policy_version 110280 (0.0008) -[2023-11-28 03:06:19,856][87426] Updated weights for policy 1, policy_version 110290 (0.0008) -[2023-11-28 03:06:20,238][87426] Updated weights for policy 1, policy_version 110300 (0.0011) -[2023-11-28 03:06:20,376][87424] Updated weights for policy 0, policy_version 110466 (0.0011) -[2023-11-28 03:06:20,759][87424] Updated weights for policy 0, policy_version 110476 (0.0010) -[2023-11-28 03:06:21,141][87424] Updated weights for policy 0, policy_version 110486 (0.0009) -[2023-11-28 03:06:21,524][87424] Updated weights for policy 0, policy_version 110496 (0.0009) -[2023-11-28 03:06:22,256][87426] Updated weights for policy 1, policy_version 110310 (0.0010) -[2023-11-28 03:06:22,639][87426] Updated weights for policy 1, policy_version 110320 (0.0008) -[2023-11-28 03:06:23,012][87426] Updated weights for policy 1, policy_version 110330 (0.0009) -[2023-11-28 03:06:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 56532992. Throughput: 0: 2705.7, 1: 2797.3. Samples: 56548232. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:23,445][86177] Avg episode reward: [(0, '-529.700'), (1, '-523.030')] -[2023-11-28 03:06:23,893][87424] Updated weights for policy 0, policy_version 110506 (0.0011) -[2023-11-28 03:06:24,276][87424] Updated weights for policy 0, policy_version 110516 (0.0008) -[2023-11-28 03:06:24,654][87424] Updated weights for policy 0, policy_version 110526 (0.0008) -[2023-11-28 03:06:25,036][87426] Updated weights for policy 1, policy_version 110340 (0.0007) -[2023-11-28 03:06:25,422][87426] Updated weights for policy 1, policy_version 110350 (0.0008) -[2023-11-28 03:06:25,804][87426] Updated weights for policy 1, policy_version 110360 (0.0009) -[2023-11-28 03:06:27,200][87424] Updated weights for policy 0, policy_version 110536 (0.0009) -[2023-11-28 03:06:27,588][87424] Updated weights for policy 0, policy_version 110546 (0.0007) -[2023-11-28 03:06:27,989][87424] Updated weights for policy 0, policy_version 110556 (0.0008) -[2023-11-28 03:06:28,153][87426] Updated weights for policy 1, policy_version 110370 (0.0008) -[2023-11-28 03:06:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 56557568. Throughput: 0: 2712.0, 1: 2797.5. Samples: 56572368. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:28,445][86177] Avg episode reward: [(0, '-534.900'), (1, '-547.390')] -[2023-11-28 03:06:28,540][87426] Updated weights for policy 1, policy_version 110380 (0.0008) -[2023-11-28 03:06:28,915][87426] Updated weights for policy 1, policy_version 110390 (0.0009) -[2023-11-28 03:06:29,294][87426] Updated weights for policy 1, policy_version 110400 (0.0009) -[2023-11-28 03:06:29,819][87424] Updated weights for policy 0, policy_version 110566 (0.0008) -[2023-11-28 03:06:30,198][87424] Updated weights for policy 0, policy_version 110576 (0.0011) -[2023-11-28 03:06:30,577][87424] Updated weights for policy 0, policy_version 110586 (0.0011) -[2023-11-28 03:06:31,782][87426] Updated weights for policy 1, policy_version 110410 (0.0009) -[2023-11-28 03:06:32,170][87426] Updated weights for policy 1, policy_version 110420 (0.0010) -[2023-11-28 03:06:32,544][87426] Updated weights for policy 1, policy_version 110430 (0.0007) -[2023-11-28 03:06:32,993][87424] Updated weights for policy 0, policy_version 110596 (0.0011) -[2023-11-28 03:06:33,380][87424] Updated weights for policy 0, policy_version 110606 (0.0012) -[2023-11-28 03:06:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 56582144. Throughput: 0: 2694.5, 1: 2807.5. Samples: 56596976. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:33,446][86177] Avg episode reward: [(0, '-565.420'), (1, '-558.710')] -[2023-11-28 03:06:33,764][87424] Updated weights for policy 0, policy_version 110616 (0.0012) -[2023-11-28 03:06:34,744][87426] Updated weights for policy 1, policy_version 110440 (0.0007) -[2023-11-28 03:06:35,128][87426] Updated weights for policy 1, policy_version 110450 (0.0012) -[2023-11-28 03:06:35,501][87426] Updated weights for policy 1, policy_version 110460 (0.0007) -[2023-11-28 03:06:35,855][87424] Updated weights for policy 0, policy_version 110626 (0.0011) -[2023-11-28 03:06:36,232][87424] Updated weights for policy 0, policy_version 110636 (0.0007) -[2023-11-28 03:06:36,609][87424] Updated weights for policy 0, policy_version 110646 (0.0007) -[2023-11-28 03:06:36,997][87424] Updated weights for policy 0, policy_version 110656 (0.0010) -[2023-11-28 03:06:37,186][87426] Updated weights for policy 1, policy_version 110470 (0.0010) -[2023-11-28 03:06:37,569][87426] Updated weights for policy 1, policy_version 110480 (0.0011) -[2023-11-28 03:06:37,948][87426] Updated weights for policy 1, policy_version 110490 (0.0008) -[2023-11-28 03:06:38,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 56614912. Throughput: 0: 2687.2, 1: 2804.1. Samples: 56628228. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:38,446][86177] Avg episode reward: [(0, '-551.790'), (1, '-559.070')] -[2023-11-28 03:06:39,153][87424] Updated weights for policy 0, policy_version 110666 (0.0011) -[2023-11-28 03:06:39,524][87424] Updated weights for policy 0, policy_version 110676 (0.0012) -[2023-11-28 03:06:39,913][87424] Updated weights for policy 0, policy_version 110686 (0.0011) -[2023-11-28 03:06:40,243][87426] Updated weights for policy 1, policy_version 110500 (0.0008) -[2023-11-28 03:06:40,625][87426] Updated weights for policy 1, policy_version 110510 (0.0011) -[2023-11-28 03:06:40,998][87426] Updated weights for policy 1, policy_version 110520 (0.0012) -[2023-11-28 03:06:42,335][87424] Updated weights for policy 0, policy_version 110696 (0.0011) -[2023-11-28 03:06:42,716][87424] Updated weights for policy 0, policy_version 110706 (0.0011) -[2023-11-28 03:06:43,092][87424] Updated weights for policy 0, policy_version 110716 (0.0011) -[2023-11-28 03:06:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 56639488. Throughput: 0: 2676.3, 1: 2767.1. Samples: 56651496. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:43,445][86177] Avg episode reward: [(0, '-551.080'), (1, '-553.080')] -[2023-11-28 03:06:43,484][87426] Updated weights for policy 1, policy_version 110530 (0.0011) -[2023-11-28 03:06:43,862][87426] Updated weights for policy 1, policy_version 110540 (0.0012) -[2023-11-28 03:06:44,245][87426] Updated weights for policy 1, policy_version 110550 (0.0012) -[2023-11-28 03:06:44,628][87426] Updated weights for policy 1, policy_version 110560 (0.0011) -[2023-11-28 03:06:45,330][87424] Updated weights for policy 0, policy_version 110726 (0.0012) -[2023-11-28 03:06:45,702][87424] Updated weights for policy 0, policy_version 110736 (0.0012) -[2023-11-28 03:06:46,088][87424] Updated weights for policy 0, policy_version 110746 (0.0012) -[2023-11-28 03:06:47,192][87426] Updated weights for policy 1, policy_version 110570 (0.0011) -[2023-11-28 03:06:47,574][87426] Updated weights for policy 1, policy_version 110580 (0.0011) -[2023-11-28 03:06:47,947][87426] Updated weights for policy 1, policy_version 110590 (0.0011) -[2023-11-28 03:06:48,248][87424] Updated weights for policy 0, policy_version 110756 (0.0011) -[2023-11-28 03:06:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 56664064. Throughput: 0: 2663.7, 1: 2752.4. Samples: 56675944. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:48,445][86177] Avg episode reward: [(0, '-554.400'), (1, '-534.040')] -[2023-11-28 03:06:48,619][87424] Updated weights for policy 0, policy_version 110766 (0.0011) -[2023-11-28 03:06:49,007][87424] Updated weights for policy 0, policy_version 110776 (0.0011) -[2023-11-28 03:06:49,723][87426] Updated weights for policy 1, policy_version 110600 (0.0011) -[2023-11-28 03:06:50,110][87426] Updated weights for policy 1, policy_version 110610 (0.0011) -[2023-11-28 03:06:50,482][87426] Updated weights for policy 1, policy_version 110620 (0.0014) -[2023-11-28 03:06:50,983][87424] Updated weights for policy 0, policy_version 110786 (0.0012) -[2023-11-28 03:06:51,361][87424] Updated weights for policy 0, policy_version 110796 (0.0016) -[2023-11-28 03:06:51,752][87424] Updated weights for policy 0, policy_version 110806 (0.0010) -[2023-11-28 03:06:52,122][87424] Updated weights for policy 0, policy_version 110816 (0.0011) -[2023-11-28 03:06:52,293][87426] Updated weights for policy 1, policy_version 110630 (0.0009) -[2023-11-28 03:06:52,674][87426] Updated weights for policy 1, policy_version 110640 (0.0011) -[2023-11-28 03:06:53,055][87426] Updated weights for policy 1, policy_version 110650 (0.0010) -[2023-11-28 03:06:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 56696832. Throughput: 0: 2677.4, 1: 2738.1. Samples: 56709992. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:53,445][86177] Avg episode reward: [(0, '-516.190'), (1, '-522.750')] -[2023-11-28 03:06:54,253][87424] Updated weights for policy 0, policy_version 110826 (0.0012) -[2023-11-28 03:06:54,625][87424] Updated weights for policy 0, policy_version 110836 (0.0012) -[2023-11-28 03:06:55,008][87424] Updated weights for policy 0, policy_version 110846 (0.0012) -[2023-11-28 03:06:55,311][87426] Updated weights for policy 1, policy_version 110660 (0.0010) -[2023-11-28 03:06:55,703][87426] Updated weights for policy 1, policy_version 110670 (0.0007) -[2023-11-28 03:06:56,089][87426] Updated weights for policy 1, policy_version 110680 (0.0007) -[2023-11-28 03:06:57,439][87424] Updated weights for policy 0, policy_version 110856 (0.0011) -[2023-11-28 03:06:57,822][87424] Updated weights for policy 0, policy_version 110866 (0.0010) -[2023-11-28 03:06:58,192][87426] Updated weights for policy 1, policy_version 110690 (0.0009) -[2023-11-28 03:06:58,211][87424] Updated weights for policy 0, policy_version 110876 (0.0008) -[2023-11-28 03:06:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 56721408. Throughput: 0: 2676.4, 1: 2768.3. Samples: 56735620. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:06:58,445][86177] Avg episode reward: [(0, '-548.300'), (1, '-514.910')] -[2023-11-28 03:06:58,563][87426] Updated weights for policy 1, policy_version 110700 (0.0011) -[2023-11-28 03:06:58,946][87426] Updated weights for policy 1, policy_version 110710 (0.0012) -[2023-11-28 03:06:59,318][87426] Updated weights for policy 1, policy_version 110720 (0.0012) -[2023-11-28 03:06:59,981][87424] Updated weights for policy 0, policy_version 110886 (0.0010) -[2023-11-28 03:07:00,355][87424] Updated weights for policy 0, policy_version 110896 (0.0012) -[2023-11-28 03:07:00,740][87424] Updated weights for policy 0, policy_version 110906 (0.0011) -[2023-11-28 03:07:01,801][87426] Updated weights for policy 1, policy_version 110730 (0.0012) -[2023-11-28 03:07:02,175][87426] Updated weights for policy 1, policy_version 110740 (0.0012) -[2023-11-28 03:07:02,553][87426] Updated weights for policy 1, policy_version 110750 (0.0011) -[2023-11-28 03:07:03,028][87424] Updated weights for policy 0, policy_version 110916 (0.0009) -[2023-11-28 03:07:03,414][87424] Updated weights for policy 0, policy_version 110926 (0.0007) -[2023-11-28 03:07:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 56745984. Throughput: 0: 2693.0, 1: 2748.4. Samples: 56760884. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:07:03,445][86177] Avg episode reward: [(0, '-545.210'), (1, '-520.470')] -[2023-11-28 03:07:03,796][87424] Updated weights for policy 0, policy_version 110936 (0.0008) -[2023-11-28 03:07:04,636][87426] Updated weights for policy 1, policy_version 110760 (0.0012) -[2023-11-28 03:07:05,014][87426] Updated weights for policy 1, policy_version 110770 (0.0012) -[2023-11-28 03:07:05,390][87426] Updated weights for policy 1, policy_version 110780 (0.0011) -[2023-11-28 03:07:05,475][87424] Updated weights for policy 0, policy_version 110946 (0.0007) -[2023-11-28 03:07:05,861][87424] Updated weights for policy 0, policy_version 110956 (0.0011) -[2023-11-28 03:07:06,241][87424] Updated weights for policy 0, policy_version 110966 (0.0012) -[2023-11-28 03:07:06,634][87424] Updated weights for policy 0, policy_version 110976 (0.0008) -[2023-11-28 03:07:07,761][87426] Updated weights for policy 1, policy_version 110790 (0.0011) -[2023-11-28 03:07:08,143][87426] Updated weights for policy 1, policy_version 110800 (0.0012) -[2023-11-28 03:07:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 56770560. Throughput: 0: 2720.5, 1: 2756.3. Samples: 56794688. Policy #0 lag: (min: 4.0, avg: 33.8, max: 64.0) -[2023-11-28 03:07:08,445][86177] Avg episode reward: [(0, '-538.420'), (1, '-519.210')] -[2023-11-28 03:07:08,514][87426] Updated weights for policy 1, policy_version 110810 (0.0011) -[2023-11-28 03:07:08,690][87424] Updated weights for policy 0, policy_version 110986 (0.0011) -[2023-11-28 03:07:09,088][87424] Updated weights for policy 0, policy_version 110996 (0.0011) -[2023-11-28 03:07:09,462][87424] Updated weights for policy 0, policy_version 111006 (0.0011) -[2023-11-28 03:07:10,327][87426] Updated weights for policy 1, policy_version 110820 (0.0010) -[2023-11-28 03:07:10,703][87426] Updated weights for policy 1, policy_version 110830 (0.0008) -[2023-11-28 03:07:11,080][87426] Updated weights for policy 1, policy_version 110840 (0.0008) -[2023-11-28 03:07:12,060][87424] Updated weights for policy 0, policy_version 111016 (0.0011) -[2023-11-28 03:07:12,443][87424] Updated weights for policy 0, policy_version 111026 (0.0009) -[2023-11-28 03:07:12,829][87424] Updated weights for policy 0, policy_version 111036 (0.0009) -[2023-11-28 03:07:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 56803328. Throughput: 0: 2717.1, 1: 2751.2. Samples: 56818440. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:13,445][86177] Avg episode reward: [(0, '-544.570'), (1, '-554.830')] -[2023-11-28 03:07:13,471][87426] Updated weights for policy 1, policy_version 110850 (0.0009) -[2023-11-28 03:07:13,847][87426] Updated weights for policy 1, policy_version 110860 (0.0009) -[2023-11-28 03:07:14,227][87426] Updated weights for policy 1, policy_version 110870 (0.0011) -[2023-11-28 03:07:14,607][87426] Updated weights for policy 1, policy_version 110880 (0.0007) -[2023-11-28 03:07:15,207][87424] Updated weights for policy 0, policy_version 111046 (0.0010) -[2023-11-28 03:07:15,577][87424] Updated weights for policy 0, policy_version 111056 (0.0012) -[2023-11-28 03:07:15,958][87424] Updated weights for policy 0, policy_version 111066 (0.0011) -[2023-11-28 03:07:16,523][87426] Updated weights for policy 1, policy_version 110890 (0.0007) -[2023-11-28 03:07:16,903][87426] Updated weights for policy 1, policy_version 110900 (0.0007) -[2023-11-28 03:07:17,286][87426] Updated weights for policy 1, policy_version 110910 (0.0008) -[2023-11-28 03:07:17,897][87424] Updated weights for policy 0, policy_version 111076 (0.0010) -[2023-11-28 03:07:18,283][87424] Updated weights for policy 0, policy_version 111086 (0.0011) -[2023-11-28 03:07:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 56827904. Throughput: 0: 2726.9, 1: 2733.9. Samples: 56842712. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:18,445][86177] Avg episode reward: [(0, '-518.230'), (1, '-571.620')] -[2023-11-28 03:07:18,661][87424] Updated weights for policy 0, policy_version 111096 (0.0012) -[2023-11-28 03:07:19,504][87426] Updated weights for policy 1, policy_version 110920 (0.0012) -[2023-11-28 03:07:19,884][87426] Updated weights for policy 1, policy_version 110930 (0.0012) -[2023-11-28 03:07:20,267][87426] Updated weights for policy 1, policy_version 110940 (0.0012) -[2023-11-28 03:07:20,408][87424] Updated weights for policy 0, policy_version 111106 (0.0011) -[2023-11-28 03:07:20,782][87424] Updated weights for policy 0, policy_version 111116 (0.0008) -[2023-11-28 03:07:21,162][87424] Updated weights for policy 0, policy_version 111126 (0.0008) -[2023-11-28 03:07:21,543][87424] Updated weights for policy 0, policy_version 111136 (0.0010) -[2023-11-28 03:07:22,655][87426] Updated weights for policy 1, policy_version 110950 (0.0010) -[2023-11-28 03:07:23,044][87426] Updated weights for policy 1, policy_version 110960 (0.0010) -[2023-11-28 03:07:23,414][87426] Updated weights for policy 1, policy_version 110970 (0.0011) -[2023-11-28 03:07:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 56852480. Throughput: 0: 2750.9, 1: 2749.3. Samples: 56875736. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:23,445][86177] Avg episode reward: [(0, '-519.520'), (1, '-556.280')] -[2023-11-28 03:07:24,042][87424] Updated weights for policy 0, policy_version 111146 (0.0009) -[2023-11-28 03:07:24,419][87424] Updated weights for policy 0, policy_version 111156 (0.0011) -[2023-11-28 03:07:24,801][87424] Updated weights for policy 0, policy_version 111166 (0.0008) -[2023-11-28 03:07:25,687][87426] Updated weights for policy 1, policy_version 110980 (0.0009) -[2023-11-28 03:07:26,065][87426] Updated weights for policy 1, policy_version 110990 (0.0007) -[2023-11-28 03:07:26,445][87426] Updated weights for policy 1, policy_version 111000 (0.0008) -[2023-11-28 03:07:27,244][87424] Updated weights for policy 0, policy_version 111176 (0.0011) -[2023-11-28 03:07:27,626][87424] Updated weights for policy 0, policy_version 111186 (0.0012) -[2023-11-28 03:07:28,018][87424] Updated weights for policy 0, policy_version 111196 (0.0011) -[2023-11-28 03:07:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 56885248. Throughput: 0: 2756.3, 1: 2741.0. Samples: 56898872. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:28,446][86177] Avg episode reward: [(0, '-515.350'), (1, '-558.190')] -[2023-11-28 03:07:28,879][87426] Updated weights for policy 1, policy_version 111010 (0.0008) -[2023-11-28 03:07:29,262][87426] Updated weights for policy 1, policy_version 111020 (0.0008) -[2023-11-28 03:07:29,640][87426] Updated weights for policy 1, policy_version 111030 (0.0008) -[2023-11-28 03:07:29,867][87424] Updated weights for policy 0, policy_version 111206 (0.0010) -[2023-11-28 03:07:30,020][87426] Updated weights for policy 1, policy_version 111040 (0.0009) -[2023-11-28 03:07:30,248][87424] Updated weights for policy 0, policy_version 111216 (0.0008) -[2023-11-28 03:07:30,629][87424] Updated weights for policy 0, policy_version 111226 (0.0009) -[2023-11-28 03:07:31,902][87426] Updated weights for policy 1, policy_version 111050 (0.0012) -[2023-11-28 03:07:32,279][87426] Updated weights for policy 1, policy_version 111060 (0.0012) -[2023-11-28 03:07:32,655][87426] Updated weights for policy 1, policy_version 111070 (0.0012) -[2023-11-28 03:07:32,972][87424] Updated weights for policy 0, policy_version 111236 (0.0010) -[2023-11-28 03:07:33,359][87424] Updated weights for policy 0, policy_version 111246 (0.0011) -[2023-11-28 03:07:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 56909824. Throughput: 0: 2766.2, 1: 2739.0. Samples: 56923680. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:33,445][86177] Avg episode reward: [(0, '-509.280'), (1, '-516.940')] -[2023-11-28 03:07:33,748][87424] Updated weights for policy 0, policy_version 111256 (0.0008) -[2023-11-28 03:07:34,809][87426] Updated weights for policy 1, policy_version 111080 (0.0010) -[2023-11-28 03:07:35,188][87426] Updated weights for policy 1, policy_version 111090 (0.0009) -[2023-11-28 03:07:35,566][87426] Updated weights for policy 1, policy_version 111100 (0.0008) -[2023-11-28 03:07:35,933][87424] Updated weights for policy 0, policy_version 111266 (0.0008) -[2023-11-28 03:07:36,315][87424] Updated weights for policy 0, policy_version 111276 (0.0011) -[2023-11-28 03:07:36,699][87424] Updated weights for policy 0, policy_version 111286 (0.0012) -[2023-11-28 03:07:37,082][87424] Updated weights for policy 0, policy_version 111296 (0.0012) -[2023-11-28 03:07:37,297][87426] Updated weights for policy 1, policy_version 111110 (0.0007) -[2023-11-28 03:07:37,672][87426] Updated weights for policy 1, policy_version 111120 (0.0008) -[2023-11-28 03:07:38,057][87426] Updated weights for policy 1, policy_version 111130 (0.0007) -[2023-11-28 03:07:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 56942592. Throughput: 0: 2728.1, 1: 2757.0. Samples: 56956820. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:38,445][86177] Avg episode reward: [(0, '-509.890'), (1, '-522.750')] -[2023-11-28 03:07:39,112][87424] Updated weights for policy 0, policy_version 111306 (0.0008) -[2023-11-28 03:07:39,495][87424] Updated weights for policy 0, policy_version 111316 (0.0008) -[2023-11-28 03:07:39,887][87424] Updated weights for policy 0, policy_version 111326 (0.0008) -[2023-11-28 03:07:40,576][87426] Updated weights for policy 1, policy_version 111140 (0.0009) -[2023-11-28 03:07:40,959][87426] Updated weights for policy 1, policy_version 111150 (0.0011) -[2023-11-28 03:07:41,345][87426] Updated weights for policy 1, policy_version 111160 (0.0012) -[2023-11-28 03:07:41,832][87424] Updated weights for policy 0, policy_version 111336 (0.0010) -[2023-11-28 03:07:42,212][87424] Updated weights for policy 0, policy_version 111346 (0.0009) -[2023-11-28 03:07:42,595][87424] Updated weights for policy 0, policy_version 111356 (0.0010) -[2023-11-28 03:07:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 56967168. Throughput: 0: 2749.9, 1: 2695.9. Samples: 56980684. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:43,446][86177] Avg episode reward: [(0, '-507.470'), (1, '-527.750')] -[2023-11-28 03:07:43,866][87426] Updated weights for policy 1, policy_version 111170 (0.0010) -[2023-11-28 03:07:44,245][87426] Updated weights for policy 1, policy_version 111180 (0.0008) -[2023-11-28 03:07:44,625][87426] Updated weights for policy 1, policy_version 111190 (0.0010) -[2023-11-28 03:07:44,669][87424] Updated weights for policy 0, policy_version 111366 (0.0012) -[2023-11-28 03:07:45,011][87426] Updated weights for policy 1, policy_version 111200 (0.0009) -[2023-11-28 03:07:45,049][87424] Updated weights for policy 0, policy_version 111376 (0.0012) -[2023-11-28 03:07:45,425][87424] Updated weights for policy 0, policy_version 111386 (0.0012) -[2023-11-28 03:07:46,868][87426] Updated weights for policy 1, policy_version 111210 (0.0008) -[2023-11-28 03:07:47,258][87426] Updated weights for policy 1, policy_version 111220 (0.0007) -[2023-11-28 03:07:47,635][87426] Updated weights for policy 1, policy_version 111230 (0.0007) -[2023-11-28 03:07:47,710][87424] Updated weights for policy 0, policy_version 111396 (0.0012) -[2023-11-28 03:07:48,093][87424] Updated weights for policy 0, policy_version 111406 (0.0012) -[2023-11-28 03:07:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 56991744. Throughput: 0: 2738.4, 1: 2701.7. Samples: 57005688. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:48,445][86177] Avg episode reward: [(0, '-506.220'), (1, '-529.880')] -[2023-11-28 03:07:48,473][87424] Updated weights for policy 0, policy_version 111416 (0.0012) -[2023-11-28 03:07:49,949][87426] Updated weights for policy 1, policy_version 111240 (0.0009) -[2023-11-28 03:07:50,322][87426] Updated weights for policy 1, policy_version 111250 (0.0007) -[2023-11-28 03:07:50,709][87426] Updated weights for policy 1, policy_version 111260 (0.0009) -[2023-11-28 03:07:50,827][87424] Updated weights for policy 0, policy_version 111426 (0.0012) -[2023-11-28 03:07:51,205][87424] Updated weights for policy 0, policy_version 111436 (0.0011) -[2023-11-28 03:07:51,598][87424] Updated weights for policy 0, policy_version 111446 (0.0012) -[2023-11-28 03:07:51,969][87424] Updated weights for policy 0, policy_version 111456 (0.0011) -[2023-11-28 03:07:52,938][87426] Updated weights for policy 1, policy_version 111270 (0.0010) -[2023-11-28 03:07:53,318][87426] Updated weights for policy 1, policy_version 111280 (0.0009) -[2023-11-28 03:07:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 57016320. Throughput: 0: 2704.3, 1: 2695.0. Samples: 57037656. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:53,445][86177] Avg episode reward: [(0, '-500.800'), (1, '-533.230')] -[2023-11-28 03:07:53,704][87426] Updated weights for policy 1, policy_version 111290 (0.0011) -[2023-11-28 03:07:54,475][87424] Updated weights for policy 0, policy_version 111466 (0.0008) -[2023-11-28 03:07:54,870][87424] Updated weights for policy 0, policy_version 111476 (0.0007) -[2023-11-28 03:07:55,243][87424] Updated weights for policy 0, policy_version 111486 (0.0009) -[2023-11-28 03:07:55,407][87426] Updated weights for policy 1, policy_version 111300 (0.0010) -[2023-11-28 03:07:55,799][87426] Updated weights for policy 1, policy_version 111310 (0.0012) -[2023-11-28 03:07:56,183][87426] Updated weights for policy 1, policy_version 111320 (0.0012) -[2023-11-28 03:07:57,378][87424] Updated weights for policy 0, policy_version 111496 (0.0008) -[2023-11-28 03:07:57,762][87424] Updated weights for policy 0, policy_version 111506 (0.0007) -[2023-11-28 03:07:58,144][87424] Updated weights for policy 0, policy_version 111516 (0.0007) -[2023-11-28 03:07:58,211][87426] Updated weights for policy 1, policy_version 111330 (0.0012) -[2023-11-28 03:07:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57049088. Throughput: 0: 2705.3, 1: 2717.1. Samples: 57062444. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:07:58,445][86177] Avg episode reward: [(0, '-500.740'), (1, '-508.570')] -[2023-11-28 03:07:58,609][87426] Updated weights for policy 1, policy_version 111340 (0.0012) -[2023-11-28 03:07:58,991][87426] Updated weights for policy 1, policy_version 111350 (0.0008) -[2023-11-28 03:07:59,367][87426] Updated weights for policy 1, policy_version 111360 (0.0007) -[2023-11-28 03:08:00,120][87424] Updated weights for policy 0, policy_version 111526 (0.0010) -[2023-11-28 03:08:00,499][87424] Updated weights for policy 0, policy_version 111536 (0.0011) -[2023-11-28 03:08:00,880][87424] Updated weights for policy 0, policy_version 111546 (0.0007) -[2023-11-28 03:08:01,755][87426] Updated weights for policy 1, policy_version 111370 (0.0011) -[2023-11-28 03:08:02,139][87426] Updated weights for policy 1, policy_version 111380 (0.0010) -[2023-11-28 03:08:02,516][87426] Updated weights for policy 1, policy_version 111390 (0.0008) -[2023-11-28 03:08:02,569][87424] Updated weights for policy 0, policy_version 111556 (0.0009) -[2023-11-28 03:08:02,948][87424] Updated weights for policy 0, policy_version 111566 (0.0012) -[2023-11-28 03:08:03,336][87424] Updated weights for policy 0, policy_version 111576 (0.0012) -[2023-11-28 03:08:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57073664. Throughput: 0: 2725.7, 1: 2722.0. Samples: 57087860. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:08:03,445][86177] Avg episode reward: [(0, '-501.900'), (1, '-503.870')] -[2023-11-28 03:08:04,358][87426] Updated weights for policy 1, policy_version 111400 (0.0008) -[2023-11-28 03:08:04,735][87426] Updated weights for policy 1, policy_version 111410 (0.0011) -[2023-11-28 03:08:05,114][87426] Updated weights for policy 1, policy_version 111420 (0.0011) -[2023-11-28 03:08:05,709][87424] Updated weights for policy 0, policy_version 111586 (0.0011) -[2023-11-28 03:08:06,098][87424] Updated weights for policy 0, policy_version 111596 (0.0012) -[2023-11-28 03:08:06,481][87424] Updated weights for policy 0, policy_version 111606 (0.0012) -[2023-11-28 03:08:06,865][87424] Updated weights for policy 0, policy_version 111616 (0.0012) -[2023-11-28 03:08:07,182][87426] Updated weights for policy 1, policy_version 111430 (0.0011) -[2023-11-28 03:08:07,559][87426] Updated weights for policy 1, policy_version 111440 (0.0008) -[2023-11-28 03:08:07,939][87426] Updated weights for policy 1, policy_version 111450 (0.0007) -[2023-11-28 03:08:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 57106432. Throughput: 0: 2729.1, 1: 2707.4. Samples: 57120376. Policy #0 lag: (min: 33.0, avg: 45.9, max: 72.0) -[2023-11-28 03:08:08,445][86177] Avg episode reward: [(0, '-502.730'), (1, '-505.060')] -[2023-11-28 03:08:08,911][87424] Updated weights for policy 0, policy_version 111626 (0.0012) -[2023-11-28 03:08:09,299][87424] Updated weights for policy 0, policy_version 111636 (0.0011) -[2023-11-28 03:08:09,682][87424] Updated weights for policy 0, policy_version 111646 (0.0007) -[2023-11-28 03:08:10,498][87426] Updated weights for policy 1, policy_version 111460 (0.0009) -[2023-11-28 03:08:10,877][87426] Updated weights for policy 1, policy_version 111470 (0.0011) -[2023-11-28 03:08:11,252][87426] Updated weights for policy 1, policy_version 111480 (0.0012) -[2023-11-28 03:08:11,857][87424] Updated weights for policy 0, policy_version 111656 (0.0012) -[2023-11-28 03:08:12,228][87424] Updated weights for policy 0, policy_version 111666 (0.0012) -[2023-11-28 03:08:12,614][87424] Updated weights for policy 0, policy_version 111676 (0.0012) -[2023-11-28 03:08:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57131008. Throughput: 0: 2735.9, 1: 2718.3. Samples: 57144312. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:13,445][86177] Avg episode reward: [(0, '-505.550'), (1, '-499.640')] -[2023-11-28 03:08:13,664][87426] Updated weights for policy 1, policy_version 111490 (0.0012) -[2023-11-28 03:08:14,034][87426] Updated weights for policy 1, policy_version 111500 (0.0011) -[2023-11-28 03:08:14,413][87426] Updated weights for policy 1, policy_version 111510 (0.0012) -[2023-11-28 03:08:14,785][87426] Updated weights for policy 1, policy_version 111520 (0.0012) -[2023-11-28 03:08:15,154][87424] Updated weights for policy 0, policy_version 111686 (0.0012) -[2023-11-28 03:08:15,524][87424] Updated weights for policy 0, policy_version 111696 (0.0008) -[2023-11-28 03:08:15,907][87424] Updated weights for policy 0, policy_version 111706 (0.0009) -[2023-11-28 03:08:17,188][87426] Updated weights for policy 1, policy_version 111530 (0.0007) -[2023-11-28 03:08:17,569][87426] Updated weights for policy 1, policy_version 111540 (0.0007) -[2023-11-28 03:08:17,947][87426] Updated weights for policy 1, policy_version 111550 (0.0010) -[2023-11-28 03:08:18,049][87424] Updated weights for policy 0, policy_version 111716 (0.0011) -[2023-11-28 03:08:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57155584. Throughput: 0: 2715.6, 1: 2705.6. Samples: 57167636. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:18,445][86177] Avg episode reward: [(0, '-501.740'), (1, '-500.350')] -[2023-11-28 03:08:18,446][87424] Updated weights for policy 0, policy_version 111726 (0.0012) -[2023-11-28 03:08:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000111552_28557312.pth... -[2023-11-28 03:08:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000108992_27901952.pth -[2023-11-28 03:08:18,824][87424] Updated weights for policy 0, policy_version 111736 (0.0009) -[2023-11-28 03:08:19,120][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000111744_28606464.pth... -[2023-11-28 03:08:19,151][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000109184_27951104.pth -[2023-11-28 03:08:20,141][87426] Updated weights for policy 1, policy_version 111560 (0.0011) -[2023-11-28 03:08:20,522][87426] Updated weights for policy 1, policy_version 111570 (0.0012) -[2023-11-28 03:08:20,897][87426] Updated weights for policy 1, policy_version 111580 (0.0013) -[2023-11-28 03:08:21,048][87424] Updated weights for policy 0, policy_version 111746 (0.0011) -[2023-11-28 03:08:21,426][87424] Updated weights for policy 0, policy_version 111756 (0.0013) -[2023-11-28 03:08:21,811][87424] Updated weights for policy 0, policy_version 111766 (0.0010) -[2023-11-28 03:08:22,190][87424] Updated weights for policy 0, policy_version 111776 (0.0011) -[2023-11-28 03:08:23,256][87426] Updated weights for policy 1, policy_version 111590 (0.0012) -[2023-11-28 03:08:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57180160. Throughput: 0: 2720.8, 1: 2671.4. Samples: 57199468. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:23,445][86177] Avg episode reward: [(0, '-501.770'), (1, '-500.730')] -[2023-11-28 03:08:23,631][87426] Updated weights for policy 1, policy_version 111600 (0.0012) -[2023-11-28 03:08:24,022][87426] Updated weights for policy 1, policy_version 111610 (0.0012) -[2023-11-28 03:08:24,335][87424] Updated weights for policy 0, policy_version 111786 (0.0009) -[2023-11-28 03:08:24,719][87424] Updated weights for policy 0, policy_version 111796 (0.0012) -[2023-11-28 03:08:25,105][87424] Updated weights for policy 0, policy_version 111806 (0.0010) -[2023-11-28 03:08:25,967][87426] Updated weights for policy 1, policy_version 111620 (0.0012) -[2023-11-28 03:08:26,339][87426] Updated weights for policy 1, policy_version 111630 (0.0009) -[2023-11-28 03:08:26,717][87426] Updated weights for policy 1, policy_version 111640 (0.0007) -[2023-11-28 03:08:27,087][87424] Updated weights for policy 0, policy_version 111816 (0.0011) -[2023-11-28 03:08:27,474][87424] Updated weights for policy 0, policy_version 111826 (0.0010) -[2023-11-28 03:08:27,858][87424] Updated weights for policy 0, policy_version 111836 (0.0007) -[2023-11-28 03:08:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 57212928. Throughput: 0: 2706.0, 1: 2721.7. Samples: 57224928. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:28,445][86177] Avg episode reward: [(0, '-500.720'), (1, '-499.970')] -[2023-11-28 03:08:28,535][87426] Updated weights for policy 1, policy_version 111650 (0.0008) -[2023-11-28 03:08:28,912][87426] Updated weights for policy 1, policy_version 111660 (0.0012) -[2023-11-28 03:08:29,295][87426] Updated weights for policy 1, policy_version 111670 (0.0012) -[2023-11-28 03:08:29,675][87426] Updated weights for policy 1, policy_version 111680 (0.0012) -[2023-11-28 03:08:29,756][87424] Updated weights for policy 0, policy_version 111846 (0.0011) -[2023-11-28 03:08:30,132][87424] Updated weights for policy 0, policy_version 111856 (0.0012) -[2023-11-28 03:08:30,507][87424] Updated weights for policy 0, policy_version 111866 (0.0012) -[2023-11-28 03:08:32,006][87426] Updated weights for policy 1, policy_version 111690 (0.0012) -[2023-11-28 03:08:32,383][87426] Updated weights for policy 1, policy_version 111700 (0.0012) -[2023-11-28 03:08:32,763][87426] Updated weights for policy 1, policy_version 111710 (0.0011) -[2023-11-28 03:08:33,013][87424] Updated weights for policy 0, policy_version 111876 (0.0010) -[2023-11-28 03:08:33,404][87424] Updated weights for policy 0, policy_version 111886 (0.0008) -[2023-11-28 03:08:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57237504. Throughput: 0: 2715.9, 1: 2728.3. Samples: 57250676. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:33,445][86177] Avg episode reward: [(0, '-555.980'), (1, '-508.060')] -[2023-11-28 03:08:33,784][87424] Updated weights for policy 0, policy_version 111896 (0.0011) -[2023-11-28 03:08:34,783][87426] Updated weights for policy 1, policy_version 111720 (0.0008) -[2023-11-28 03:08:35,158][87426] Updated weights for policy 1, policy_version 111730 (0.0009) -[2023-11-28 03:08:35,544][87426] Updated weights for policy 1, policy_version 111740 (0.0011) -[2023-11-28 03:08:36,085][87424] Updated weights for policy 0, policy_version 111906 (0.0011) -[2023-11-28 03:08:36,466][87424] Updated weights for policy 0, policy_version 111916 (0.0012) -[2023-11-28 03:08:36,847][87424] Updated weights for policy 0, policy_version 111926 (0.0012) -[2023-11-28 03:08:37,229][87424] Updated weights for policy 0, policy_version 111936 (0.0011) -[2023-11-28 03:08:37,891][87426] Updated weights for policy 1, policy_version 111750 (0.0010) -[2023-11-28 03:08:38,273][87426] Updated weights for policy 1, policy_version 111760 (0.0011) -[2023-11-28 03:08:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 57262080. Throughput: 0: 2740.9, 1: 2747.6. Samples: 57284640. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:38,446][86177] Avg episode reward: [(0, '-555.590'), (1, '-509.300')] -[2023-11-28 03:08:38,655][87426] Updated weights for policy 1, policy_version 111770 (0.0012) -[2023-11-28 03:08:39,205][87424] Updated weights for policy 0, policy_version 111946 (0.0008) -[2023-11-28 03:08:39,596][87424] Updated weights for policy 0, policy_version 111956 (0.0008) -[2023-11-28 03:08:39,971][87424] Updated weights for policy 0, policy_version 111966 (0.0009) -[2023-11-28 03:08:40,872][87426] Updated weights for policy 1, policy_version 111780 (0.0010) -[2023-11-28 03:08:41,250][87426] Updated weights for policy 1, policy_version 111790 (0.0008) -[2023-11-28 03:08:41,624][87426] Updated weights for policy 1, policy_version 111800 (0.0011) -[2023-11-28 03:08:41,709][87424] Updated weights for policy 0, policy_version 111976 (0.0010) -[2023-11-28 03:08:42,089][87424] Updated weights for policy 0, policy_version 111986 (0.0009) -[2023-11-28 03:08:42,479][87424] Updated weights for policy 0, policy_version 111996 (0.0009) -[2023-11-28 03:08:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57294848. Throughput: 0: 2759.6, 1: 2717.3. Samples: 57308908. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:43,445][86177] Avg episode reward: [(0, '-555.730'), (1, '-510.310')] -[2023-11-28 03:08:43,477][87426] Updated weights for policy 1, policy_version 111810 (0.0010) -[2023-11-28 03:08:43,853][87426] Updated weights for policy 1, policy_version 111820 (0.0008) -[2023-11-28 03:08:44,231][87426] Updated weights for policy 1, policy_version 111830 (0.0008) -[2023-11-28 03:08:44,613][87426] Updated weights for policy 1, policy_version 111840 (0.0008) -[2023-11-28 03:08:44,788][87424] Updated weights for policy 0, policy_version 112006 (0.0010) -[2023-11-28 03:08:45,181][87424] Updated weights for policy 0, policy_version 112016 (0.0011) -[2023-11-28 03:08:45,553][87424] Updated weights for policy 0, policy_version 112026 (0.0009) -[2023-11-28 03:08:46,999][87426] Updated weights for policy 1, policy_version 111850 (0.0011) -[2023-11-28 03:08:47,377][87426] Updated weights for policy 1, policy_version 111860 (0.0008) -[2023-11-28 03:08:47,756][87426] Updated weights for policy 1, policy_version 111870 (0.0007) -[2023-11-28 03:08:48,104][87424] Updated weights for policy 0, policy_version 112036 (0.0007) -[2023-11-28 03:08:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57319424. Throughput: 0: 2732.7, 1: 2713.5. Samples: 57332940. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:48,446][86177] Avg episode reward: [(0, '-610.870'), (1, '-507.630')] -[2023-11-28 03:08:48,482][87424] Updated weights for policy 0, policy_version 112046 (0.0009) -[2023-11-28 03:08:48,871][87424] Updated weights for policy 0, policy_version 112056 (0.0008) -[2023-11-28 03:08:50,002][87426] Updated weights for policy 1, policy_version 111880 (0.0009) -[2023-11-28 03:08:50,379][87426] Updated weights for policy 1, policy_version 111890 (0.0012) -[2023-11-28 03:08:50,757][87426] Updated weights for policy 1, policy_version 111900 (0.0012) -[2023-11-28 03:08:51,177][87424] Updated weights for policy 0, policy_version 112066 (0.0008) -[2023-11-28 03:08:51,556][87424] Updated weights for policy 0, policy_version 112076 (0.0012) -[2023-11-28 03:08:51,934][87424] Updated weights for policy 0, policy_version 112086 (0.0010) -[2023-11-28 03:08:52,311][87424] Updated weights for policy 0, policy_version 112096 (0.0012) -[2023-11-28 03:08:52,985][87426] Updated weights for policy 1, policy_version 111910 (0.0011) -[2023-11-28 03:08:53,380][87426] Updated weights for policy 1, policy_version 111920 (0.0013) -[2023-11-28 03:08:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57344000. Throughput: 0: 2705.8, 1: 2731.9. Samples: 57365072. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:53,445][86177] Avg episode reward: [(0, '-553.400'), (1, '-512.050')] -[2023-11-28 03:08:53,749][87426] Updated weights for policy 1, policy_version 111930 (0.0012) -[2023-11-28 03:08:54,482][87424] Updated weights for policy 0, policy_version 112106 (0.0007) -[2023-11-28 03:08:54,866][87424] Updated weights for policy 0, policy_version 112116 (0.0008) -[2023-11-28 03:08:55,261][87424] Updated weights for policy 0, policy_version 112126 (0.0007) -[2023-11-28 03:08:55,717][87426] Updated weights for policy 1, policy_version 111940 (0.0010) -[2023-11-28 03:08:56,101][87426] Updated weights for policy 1, policy_version 111950 (0.0008) -[2023-11-28 03:08:56,478][87426] Updated weights for policy 1, policy_version 111960 (0.0007) -[2023-11-28 03:08:57,317][87424] Updated weights for policy 0, policy_version 112136 (0.0008) -[2023-11-28 03:08:57,700][87424] Updated weights for policy 0, policy_version 112146 (0.0008) -[2023-11-28 03:08:58,085][87424] Updated weights for policy 0, policy_version 112156 (0.0008) -[2023-11-28 03:08:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 57376768. Throughput: 0: 2691.3, 1: 2741.1. Samples: 57388768. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:08:58,445][86177] Avg episode reward: [(0, '-554.820'), (1, '-513.390')] -[2023-11-28 03:08:58,788][87426] Updated weights for policy 1, policy_version 111970 (0.0008) -[2023-11-28 03:08:59,169][87426] Updated weights for policy 1, policy_version 111980 (0.0012) -[2023-11-28 03:08:59,548][87426] Updated weights for policy 1, policy_version 111990 (0.0011) -[2023-11-28 03:08:59,926][87426] Updated weights for policy 1, policy_version 112000 (0.0010) -[2023-11-28 03:08:59,967][87424] Updated weights for policy 0, policy_version 112166 (0.0010) -[2023-11-28 03:09:00,355][87424] Updated weights for policy 0, policy_version 112176 (0.0012) -[2023-11-28 03:09:00,735][87424] Updated weights for policy 0, policy_version 112186 (0.0011) -[2023-11-28 03:09:02,228][87426] Updated weights for policy 1, policy_version 112010 (0.0012) -[2023-11-28 03:09:02,603][87426] Updated weights for policy 1, policy_version 112020 (0.0012) -[2023-11-28 03:09:02,711][87424] Updated weights for policy 0, policy_version 112196 (0.0010) -[2023-11-28 03:09:02,975][87426] Updated weights for policy 1, policy_version 112030 (0.0011) -[2023-11-28 03:09:03,090][87424] Updated weights for policy 0, policy_version 112206 (0.0008) -[2023-11-28 03:09:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57401344. Throughput: 0: 2714.8, 1: 2737.0. Samples: 57412968. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:09:03,445][86177] Avg episode reward: [(0, '-557.870'), (1, '-510.800')] -[2023-11-28 03:09:03,476][87424] Updated weights for policy 0, policy_version 112216 (0.0007) -[2023-11-28 03:09:05,110][87426] Updated weights for policy 1, policy_version 112040 (0.0012) -[2023-11-28 03:09:05,486][87426] Updated weights for policy 1, policy_version 112050 (0.0012) -[2023-11-28 03:09:05,698][87424] Updated weights for policy 0, policy_version 112226 (0.0008) -[2023-11-28 03:09:05,858][87426] Updated weights for policy 1, policy_version 112060 (0.0011) -[2023-11-28 03:09:06,079][87424] Updated weights for policy 0, policy_version 112236 (0.0012) -[2023-11-28 03:09:06,455][87424] Updated weights for policy 0, policy_version 112246 (0.0008) -[2023-11-28 03:09:06,837][87424] Updated weights for policy 0, policy_version 112256 (0.0008) -[2023-11-28 03:09:07,962][87426] Updated weights for policy 1, policy_version 112070 (0.0012) -[2023-11-28 03:09:08,338][87426] Updated weights for policy 1, policy_version 112080 (0.0012) -[2023-11-28 03:09:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 57425920. Throughput: 0: 2727.7, 1: 2744.4. Samples: 57445712. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:09:08,445][86177] Avg episode reward: [(0, '-543.660'), (1, '-521.060')] -[2023-11-28 03:09:08,704][87426] Updated weights for policy 1, policy_version 112090 (0.0011) -[2023-11-28 03:09:09,103][87424] Updated weights for policy 0, policy_version 112266 (0.0010) -[2023-11-28 03:09:09,483][87424] Updated weights for policy 0, policy_version 112276 (0.0012) -[2023-11-28 03:09:09,868][87424] Updated weights for policy 0, policy_version 112286 (0.0012) -[2023-11-28 03:09:10,578][87426] Updated weights for policy 1, policy_version 112100 (0.0011) -[2023-11-28 03:09:10,950][87426] Updated weights for policy 1, policy_version 112110 (0.0012) -[2023-11-28 03:09:11,330][87426] Updated weights for policy 1, policy_version 112120 (0.0012) -[2023-11-28 03:09:11,889][87424] Updated weights for policy 0, policy_version 112296 (0.0010) -[2023-11-28 03:09:12,270][87424] Updated weights for policy 0, policy_version 112306 (0.0009) -[2023-11-28 03:09:12,656][87424] Updated weights for policy 0, policy_version 112316 (0.0012) -[2023-11-28 03:09:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 57458688. Throughput: 0: 2729.8, 1: 2719.6. Samples: 57470152. Policy #0 lag: (min: 20.0, avg: 38.9, max: 57.0) -[2023-11-28 03:09:13,445][86177] Avg episode reward: [(0, '-545.330'), (1, '-509.500')] -[2023-11-28 03:09:13,624][87426] Updated weights for policy 1, policy_version 112130 (0.0011) -[2023-11-28 03:09:13,998][87426] Updated weights for policy 1, policy_version 112140 (0.0011) -[2023-11-28 03:09:14,376][87426] Updated weights for policy 1, policy_version 112150 (0.0008) -[2023-11-28 03:09:14,676][87424] Updated weights for policy 0, policy_version 112326 (0.0009) -[2023-11-28 03:09:14,755][87426] Updated weights for policy 1, policy_version 112160 (0.0008) -[2023-11-28 03:09:15,045][87424] Updated weights for policy 0, policy_version 112336 (0.0008) -[2023-11-28 03:09:15,425][87424] Updated weights for policy 0, policy_version 112346 (0.0008) -[2023-11-28 03:09:17,180][87426] Updated weights for policy 1, policy_version 112170 (0.0007) -[2023-11-28 03:09:17,566][87426] Updated weights for policy 1, policy_version 112180 (0.0007) -[2023-11-28 03:09:17,931][87424] Updated weights for policy 0, policy_version 112356 (0.0009) -[2023-11-28 03:09:17,953][87426] Updated weights for policy 1, policy_version 112190 (0.0007) -[2023-11-28 03:09:18,313][87424] Updated weights for policy 0, policy_version 112366 (0.0012) -[2023-11-28 03:09:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57483264. Throughput: 0: 2715.5, 1: 2700.5. Samples: 57494396. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:09:18,446][86177] Avg episode reward: [(0, '-577.550'), (1, '-507.380')] -[2023-11-28 03:09:18,703][87424] Updated weights for policy 0, policy_version 112376 (0.0012) -[2023-11-28 03:09:20,469][87426] Updated weights for policy 1, policy_version 112200 (0.0012) -[2023-11-28 03:09:20,853][87426] Updated weights for policy 1, policy_version 112210 (0.0008) -[2023-11-28 03:09:21,121][87424] Updated weights for policy 0, policy_version 112386 (0.0012) -[2023-11-28 03:09:21,230][87426] Updated weights for policy 1, policy_version 112220 (0.0011) -[2023-11-28 03:09:21,510][87424] Updated weights for policy 0, policy_version 112396 (0.0011) -[2023-11-28 03:09:21,886][87424] Updated weights for policy 0, policy_version 112406 (0.0012) -[2023-11-28 03:09:22,271][87424] Updated weights for policy 0, policy_version 112416 (0.0016) -[2023-11-28 03:09:23,280][87426] Updated weights for policy 1, policy_version 112230 (0.0012) -[2023-11-28 03:09:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57507840. Throughput: 0: 2680.2, 1: 2666.8. Samples: 57525256. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:09:23,446][86177] Avg episode reward: [(0, '-543.250'), (1, '-529.230')] -[2023-11-28 03:09:23,667][87426] Updated weights for policy 1, policy_version 112240 (0.0011) -[2023-11-28 03:09:24,040][87426] Updated weights for policy 1, policy_version 112250 (0.0012) -[2023-11-28 03:09:24,861][87424] Updated weights for policy 0, policy_version 112426 (0.0012) -[2023-11-28 03:09:25,243][87424] Updated weights for policy 0, policy_version 112436 (0.0012) -[2023-11-28 03:09:25,629][87424] Updated weights for policy 0, policy_version 112446 (0.0012) -[2023-11-28 03:09:25,800][87426] Updated weights for policy 1, policy_version 112260 (0.0012) -[2023-11-28 03:09:26,182][87426] Updated weights for policy 1, policy_version 112270 (0.0011) -[2023-11-28 03:09:26,563][87426] Updated weights for policy 1, policy_version 112280 (0.0012) -[2023-11-28 03:09:27,402][87424] Updated weights for policy 0, policy_version 112456 (0.0012) -[2023-11-28 03:09:27,778][87424] Updated weights for policy 0, policy_version 112466 (0.0012) -[2023-11-28 03:09:28,165][87424] Updated weights for policy 0, policy_version 112476 (0.0010) -[2023-11-28 03:09:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57540608. Throughput: 0: 2666.6, 1: 2695.2. Samples: 57550188. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:09:28,445][86177] Avg episode reward: [(0, '-541.870'), (1, '-524.870')] -[2023-11-28 03:09:28,836][87426] Updated weights for policy 1, policy_version 112290 (0.0010) -[2023-11-28 03:09:29,216][87426] Updated weights for policy 1, policy_version 112300 (0.0007) -[2023-11-28 03:09:29,603][87426] Updated weights for policy 1, policy_version 112310 (0.0007) -[2023-11-28 03:09:29,978][87426] Updated weights for policy 1, policy_version 112320 (0.0009) -[2023-11-28 03:09:30,658][87424] Updated weights for policy 0, policy_version 112486 (0.0007) -[2023-11-28 03:09:31,047][87424] Updated weights for policy 0, policy_version 112496 (0.0007) -[2023-11-28 03:09:31,423][87424] Updated weights for policy 0, policy_version 112506 (0.0007) -[2023-11-28 03:09:32,449][87426] Updated weights for policy 1, policy_version 112330 (0.0013) -[2023-11-28 03:09:32,826][87426] Updated weights for policy 1, policy_version 112340 (0.0012) -[2023-11-28 03:09:33,206][87426] Updated weights for policy 1, policy_version 112350 (0.0012) -[2023-11-28 03:09:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57565184. Throughput: 0: 2672.2, 1: 2689.5. Samples: 57574216. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:09:33,445][86177] Avg episode reward: [(0, '-526.470'), (1, '-525.400')] -[2023-11-28 03:09:33,554][87424] Updated weights for policy 0, policy_version 112516 (0.0011) -[2023-11-28 03:09:33,939][87424] Updated weights for policy 0, policy_version 112526 (0.0012) -[2023-11-28 03:09:34,325][87424] Updated weights for policy 0, policy_version 112536 (0.0012) -[2023-11-28 03:09:34,864][87426] Updated weights for policy 1, policy_version 112360 (0.0012) -[2023-11-28 03:09:35,227][87426] Updated weights for policy 1, policy_version 112370 (0.0012) -[2023-11-28 03:09:35,608][87426] Updated weights for policy 1, policy_version 112380 (0.0012) -[2023-11-28 03:09:36,463][87424] Updated weights for policy 0, policy_version 112546 (0.0012) -[2023-11-28 03:09:36,840][87424] Updated weights for policy 0, policy_version 112556 (0.0012) -[2023-11-28 03:09:37,224][87424] Updated weights for policy 0, policy_version 112566 (0.0012) -[2023-11-28 03:09:37,603][87424] Updated weights for policy 0, policy_version 112576 (0.0012) -[2023-11-28 03:09:37,995][87426] Updated weights for policy 1, policy_version 112390 (0.0009) -[2023-11-28 03:09:38,368][87426] Updated weights for policy 1, policy_version 112400 (0.0007) -[2023-11-28 03:09:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57589760. Throughput: 0: 2689.8, 1: 2703.3. Samples: 57607760. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:09:38,445][86177] Avg episode reward: [(0, '-511.310'), (1, '-525.000')] -[2023-11-28 03:09:38,749][87426] Updated weights for policy 1, policy_version 112410 (0.0008) -[2023-11-28 03:09:39,663][87424] Updated weights for policy 0, policy_version 112586 (0.0008) -[2023-11-28 03:09:40,046][87424] Updated weights for policy 0, policy_version 112596 (0.0010) -[2023-11-28 03:09:40,429][87424] Updated weights for policy 0, policy_version 112606 (0.0008) -[2023-11-28 03:09:41,028][87426] Updated weights for policy 1, policy_version 112420 (0.0012) -[2023-11-28 03:09:41,406][87426] Updated weights for policy 1, policy_version 112430 (0.0012) -[2023-11-28 03:09:41,775][87426] Updated weights for policy 1, policy_version 112440 (0.0012) -[2023-11-28 03:09:42,556][87424] Updated weights for policy 0, policy_version 112616 (0.0011) -[2023-11-28 03:09:42,927][87424] Updated weights for policy 0, policy_version 112626 (0.0012) -[2023-11-28 03:09:43,314][87424] Updated weights for policy 0, policy_version 112636 (0.0011) -[2023-11-28 03:09:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 57614336. Throughput: 0: 2717.4, 1: 2704.5. Samples: 57632756. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:09:43,445][86177] Avg episode reward: [(0, '-504.990'), (1, '-503.050')] -[2023-11-28 03:09:43,873][87426] Updated weights for policy 1, policy_version 112450 (0.0012) -[2023-11-28 03:09:44,247][87426] Updated weights for policy 1, policy_version 112460 (0.0012) -[2023-11-28 03:09:44,625][87426] Updated weights for policy 1, policy_version 112470 (0.0012) -[2023-11-28 03:09:45,005][87426] Updated weights for policy 1, policy_version 112480 (0.0011) -[2023-11-28 03:09:45,193][87424] Updated weights for policy 0, policy_version 112646 (0.0011) -[2023-11-28 03:09:45,566][87424] Updated weights for policy 0, policy_version 112656 (0.0011) -[2023-11-28 03:09:45,951][87424] Updated weights for policy 0, policy_version 112666 (0.0008) -[2023-11-28 03:09:47,279][87426] Updated weights for policy 1, policy_version 112490 (0.0010) -[2023-11-28 03:09:47,659][87426] Updated weights for policy 1, policy_version 112500 (0.0009) -[2023-11-28 03:09:47,852][87424] Updated weights for policy 0, policy_version 112676 (0.0010) -[2023-11-28 03:09:48,037][87426] Updated weights for policy 1, policy_version 112510 (0.0012) -[2023-11-28 03:09:48,231][87424] Updated weights for policy 0, policy_version 112686 (0.0008) -[2023-11-28 03:09:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 57647104. Throughput: 0: 2714.3, 1: 2722.9. Samples: 57657644. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:09:48,445][86177] Avg episode reward: [(0, '-502.670'), (1, '-516.090')] -[2023-11-28 03:09:48,607][87424] Updated weights for policy 0, policy_version 112696 (0.0007) -[2023-11-28 03:09:50,331][87426] Updated weights for policy 1, policy_version 112520 (0.0010) -[2023-11-28 03:09:50,708][87426] Updated weights for policy 1, policy_version 112530 (0.0010) -[2023-11-28 03:09:50,749][87424] Updated weights for policy 0, policy_version 112706 (0.0009) -[2023-11-28 03:09:51,100][87426] Updated weights for policy 1, policy_version 112540 (0.0009) -[2023-11-28 03:09:51,131][87424] Updated weights for policy 0, policy_version 112716 (0.0009) -[2023-11-28 03:09:51,524][87424] Updated weights for policy 0, policy_version 112726 (0.0012) -[2023-11-28 03:09:51,894][87424] Updated weights for policy 0, policy_version 112736 (0.0010) -[2023-11-28 03:09:53,179][87426] Updated weights for policy 1, policy_version 112550 (0.0011) -[2023-11-28 03:09:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57671680. Throughput: 0: 2718.2, 1: 2737.3. Samples: 57691212. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:09:53,445][86177] Avg episode reward: [(0, '-506.960'), (1, '-518.320')] -[2023-11-28 03:09:53,557][87426] Updated weights for policy 1, policy_version 112560 (0.0012) -[2023-11-28 03:09:53,932][87426] Updated weights for policy 1, policy_version 112570 (0.0012) -[2023-11-28 03:09:54,288][87424] Updated weights for policy 0, policy_version 112746 (0.0012) -[2023-11-28 03:09:54,665][87424] Updated weights for policy 0, policy_version 112756 (0.0012) -[2023-11-28 03:09:55,047][87424] Updated weights for policy 0, policy_version 112766 (0.0012) -[2023-11-28 03:09:56,313][87426] Updated weights for policy 1, policy_version 112580 (0.0010) -[2023-11-28 03:09:56,684][87426] Updated weights for policy 1, policy_version 112590 (0.0012) -[2023-11-28 03:09:57,051][87426] Updated weights for policy 1, policy_version 112600 (0.0011) -[2023-11-28 03:09:57,186][87424] Updated weights for policy 0, policy_version 112776 (0.0012) -[2023-11-28 03:09:57,566][87424] Updated weights for policy 0, policy_version 112786 (0.0012) -[2023-11-28 03:09:57,951][87424] Updated weights for policy 0, policy_version 112796 (0.0012) -[2023-11-28 03:09:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57704448. Throughput: 0: 2711.5, 1: 2756.1. Samples: 57716192. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:09:58,445][86177] Avg episode reward: [(0, '-514.380'), (1, '-518.600')] -[2023-11-28 03:09:58,708][87426] Updated weights for policy 1, policy_version 112610 (0.0009) -[2023-11-28 03:09:59,070][87426] Updated weights for policy 1, policy_version 112620 (0.0012) -[2023-11-28 03:09:59,449][87426] Updated weights for policy 1, policy_version 112630 (0.0011) -[2023-11-28 03:09:59,819][87426] Updated weights for policy 1, policy_version 112640 (0.0012) -[2023-11-28 03:10:00,551][87424] Updated weights for policy 0, policy_version 112806 (0.0011) -[2023-11-28 03:10:00,930][87424] Updated weights for policy 0, policy_version 112816 (0.0012) -[2023-11-28 03:10:01,309][87424] Updated weights for policy 0, policy_version 112826 (0.0008) -[2023-11-28 03:10:01,823][87426] Updated weights for policy 1, policy_version 112650 (0.0010) -[2023-11-28 03:10:02,194][87426] Updated weights for policy 1, policy_version 112660 (0.0009) -[2023-11-28 03:10:02,577][87426] Updated weights for policy 1, policy_version 112670 (0.0010) -[2023-11-28 03:10:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57729024. Throughput: 0: 2712.6, 1: 2762.3. Samples: 57740764. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:10:03,445][86177] Avg episode reward: [(0, '-523.690'), (1, '-524.330')] -[2023-11-28 03:10:03,661][87424] Updated weights for policy 0, policy_version 112836 (0.0009) -[2023-11-28 03:10:04,044][87424] Updated weights for policy 0, policy_version 112846 (0.0012) -[2023-11-28 03:10:04,438][87424] Updated weights for policy 0, policy_version 112856 (0.0012) -[2023-11-28 03:10:04,711][87426] Updated weights for policy 1, policy_version 112680 (0.0011) -[2023-11-28 03:10:05,097][87426] Updated weights for policy 1, policy_version 112690 (0.0012) -[2023-11-28 03:10:05,469][87426] Updated weights for policy 1, policy_version 112700 (0.0012) -[2023-11-28 03:10:06,487][87424] Updated weights for policy 0, policy_version 112866 (0.0011) -[2023-11-28 03:10:06,883][87424] Updated weights for policy 0, policy_version 112876 (0.0010) -[2023-11-28 03:10:07,257][87424] Updated weights for policy 0, policy_version 112886 (0.0012) -[2023-11-28 03:10:07,533][87426] Updated weights for policy 1, policy_version 112710 (0.0011) -[2023-11-28 03:10:07,640][87424] Updated weights for policy 0, policy_version 112896 (0.0012) -[2023-11-28 03:10:07,913][87426] Updated weights for policy 1, policy_version 112720 (0.0008) -[2023-11-28 03:10:08,298][87426] Updated weights for policy 1, policy_version 112730 (0.0008) -[2023-11-28 03:10:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57753600. Throughput: 0: 2733.2, 1: 2793.0. Samples: 57773932. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:10:08,445][86177] Avg episode reward: [(0, '-525.940'), (1, '-510.070')] -[2023-11-28 03:10:09,564][87424] Updated weights for policy 0, policy_version 112906 (0.0009) -[2023-11-28 03:10:09,945][87424] Updated weights for policy 0, policy_version 112916 (0.0009) -[2023-11-28 03:10:10,221][87426] Updated weights for policy 1, policy_version 112740 (0.0009) -[2023-11-28 03:10:10,329][87424] Updated weights for policy 0, policy_version 112926 (0.0007) -[2023-11-28 03:10:10,601][87426] Updated weights for policy 1, policy_version 112750 (0.0010) -[2023-11-28 03:10:10,979][87426] Updated weights for policy 1, policy_version 112760 (0.0012) -[2023-11-28 03:10:12,487][87424] Updated weights for policy 0, policy_version 112936 (0.0012) -[2023-11-28 03:10:12,862][87424] Updated weights for policy 0, policy_version 112946 (0.0010) -[2023-11-28 03:10:12,868][87426] Updated weights for policy 1, policy_version 112770 (0.0011) -[2023-11-28 03:10:13,242][87424] Updated weights for policy 0, policy_version 112956 (0.0008) -[2023-11-28 03:10:13,246][87426] Updated weights for policy 1, policy_version 112780 (0.0011) -[2023-11-28 03:10:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57786368. Throughput: 0: 2745.2, 1: 2765.4. Samples: 57798164. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:10:13,445][86177] Avg episode reward: [(0, '-525.680'), (1, '-507.780')] -[2023-11-28 03:10:13,629][87426] Updated weights for policy 1, policy_version 112790 (0.0012) -[2023-11-28 03:10:13,999][87426] Updated weights for policy 1, policy_version 112800 (0.0007) -[2023-11-28 03:10:15,110][87424] Updated weights for policy 0, policy_version 112966 (0.0011) -[2023-11-28 03:10:15,485][87424] Updated weights for policy 0, policy_version 112976 (0.0012) -[2023-11-28 03:10:15,870][87424] Updated weights for policy 0, policy_version 112986 (0.0012) -[2023-11-28 03:10:16,473][87426] Updated weights for policy 1, policy_version 112810 (0.0009) -[2023-11-28 03:10:16,851][87426] Updated weights for policy 1, policy_version 112820 (0.0008) -[2023-11-28 03:10:17,223][87426] Updated weights for policy 1, policy_version 112830 (0.0011) -[2023-11-28 03:10:17,923][87424] Updated weights for policy 0, policy_version 112996 (0.0011) -[2023-11-28 03:10:18,311][87424] Updated weights for policy 0, policy_version 113006 (0.0012) -[2023-11-28 03:10:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 57810944. Throughput: 0: 2745.6, 1: 2766.9. Samples: 57822280. Policy #0 lag: (min: 13.0, avg: 34.4, max: 69.0) -[2023-11-28 03:10:18,445][86177] Avg episode reward: [(0, '-524.320'), (1, '-509.300')] -[2023-11-28 03:10:18,452][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000112832_28884992.pth... -[2023-11-28 03:10:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000110272_28229632.pth -[2023-11-28 03:10:18,697][87424] Updated weights for policy 0, policy_version 113016 (0.0012) -[2023-11-28 03:10:18,989][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000113024_28934144.pth... -[2023-11-28 03:10:19,020][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000110464_28278784.pth -[2023-11-28 03:10:19,672][87426] Updated weights for policy 1, policy_version 112840 (0.0012) -[2023-11-28 03:10:20,040][87426] Updated weights for policy 1, policy_version 112850 (0.0012) -[2023-11-28 03:10:20,418][87426] Updated weights for policy 1, policy_version 112860 (0.0012) -[2023-11-28 03:10:20,797][87424] Updated weights for policy 0, policy_version 113026 (0.0011) -[2023-11-28 03:10:21,181][87424] Updated weights for policy 0, policy_version 113036 (0.0011) -[2023-11-28 03:10:21,559][87424] Updated weights for policy 0, policy_version 113046 (0.0012) -[2023-11-28 03:10:21,942][87424] Updated weights for policy 0, policy_version 113056 (0.0011) -[2023-11-28 03:10:22,929][87426] Updated weights for policy 1, policy_version 112870 (0.0010) -[2023-11-28 03:10:23,308][87426] Updated weights for policy 1, policy_version 112880 (0.0012) -[2023-11-28 03:10:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 57835520. Throughput: 0: 2747.4, 1: 2746.6. Samples: 57854988. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:10:23,445][86177] Avg episode reward: [(0, '-517.690'), (1, '-503.500')] -[2023-11-28 03:10:23,689][87426] Updated weights for policy 1, policy_version 112890 (0.0012) -[2023-11-28 03:10:24,100][87424] Updated weights for policy 0, policy_version 113066 (0.0013) -[2023-11-28 03:10:24,485][87424] Updated weights for policy 0, policy_version 113076 (0.0012) -[2023-11-28 03:10:24,881][87424] Updated weights for policy 0, policy_version 113086 (0.0012) -[2023-11-28 03:10:26,125][87426] Updated weights for policy 1, policy_version 112900 (0.0009) -[2023-11-28 03:10:26,505][87426] Updated weights for policy 1, policy_version 112910 (0.0010) -[2023-11-28 03:10:26,887][87426] Updated weights for policy 1, policy_version 112920 (0.0009) -[2023-11-28 03:10:27,021][87424] Updated weights for policy 0, policy_version 113096 (0.0012) -[2023-11-28 03:10:27,391][87424] Updated weights for policy 0, policy_version 113106 (0.0011) -[2023-11-28 03:10:27,775][87424] Updated weights for policy 0, policy_version 113116 (0.0012) -[2023-11-28 03:10:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57868288. Throughput: 0: 2735.7, 1: 2762.0. Samples: 57880156. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:10:28,445][86177] Avg episode reward: [(0, '-521.420'), (1, '-505.680')] -[2023-11-28 03:10:29,025][87426] Updated weights for policy 1, policy_version 112930 (0.0007) -[2023-11-28 03:10:29,399][87426] Updated weights for policy 1, policy_version 112940 (0.0007) -[2023-11-28 03:10:29,542][87424] Updated weights for policy 0, policy_version 113126 (0.0009) -[2023-11-28 03:10:29,776][87426] Updated weights for policy 1, policy_version 112950 (0.0008) -[2023-11-28 03:10:29,930][87424] Updated weights for policy 0, policy_version 113136 (0.0011) -[2023-11-28 03:10:30,157][87426] Updated weights for policy 1, policy_version 112960 (0.0007) -[2023-11-28 03:10:30,306][87424] Updated weights for policy 0, policy_version 113146 (0.0009) -[2023-11-28 03:10:32,190][87426] Updated weights for policy 1, policy_version 112970 (0.0012) -[2023-11-28 03:10:32,570][87426] Updated weights for policy 1, policy_version 112980 (0.0012) -[2023-11-28 03:10:32,898][87424] Updated weights for policy 0, policy_version 113156 (0.0010) -[2023-11-28 03:10:32,951][87426] Updated weights for policy 1, policy_version 112990 (0.0008) -[2023-11-28 03:10:33,281][87424] Updated weights for policy 0, policy_version 113166 (0.0012) -[2023-11-28 03:10:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57892864. Throughput: 0: 2738.8, 1: 2756.6. Samples: 57904936. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:10:33,445][86177] Avg episode reward: [(0, '-523.020'), (1, '-510.380')] -[2023-11-28 03:10:33,662][87424] Updated weights for policy 0, policy_version 113176 (0.0011) -[2023-11-28 03:10:34,704][87426] Updated weights for policy 1, policy_version 113000 (0.0010) -[2023-11-28 03:10:35,089][87426] Updated weights for policy 1, policy_version 113010 (0.0010) -[2023-11-28 03:10:35,466][87426] Updated weights for policy 1, policy_version 113020 (0.0011) -[2023-11-28 03:10:35,952][87424] Updated weights for policy 0, policy_version 113186 (0.0008) -[2023-11-28 03:10:36,328][87424] Updated weights for policy 0, policy_version 113196 (0.0007) -[2023-11-28 03:10:36,717][87424] Updated weights for policy 0, policy_version 113206 (0.0009) -[2023-11-28 03:10:37,092][87424] Updated weights for policy 0, policy_version 113216 (0.0011) -[2023-11-28 03:10:37,445][87426] Updated weights for policy 1, policy_version 113030 (0.0011) -[2023-11-28 03:10:37,827][87426] Updated weights for policy 1, policy_version 113040 (0.0011) -[2023-11-28 03:10:38,200][87426] Updated weights for policy 1, policy_version 113050 (0.0012) -[2023-11-28 03:10:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 57925632. Throughput: 0: 2730.7, 1: 2737.6. Samples: 57937284. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:10:38,445][86177] Avg episode reward: [(0, '-513.230'), (1, '-507.980')] -[2023-11-28 03:10:39,190][87424] Updated weights for policy 0, policy_version 113226 (0.0012) -[2023-11-28 03:10:39,573][87424] Updated weights for policy 0, policy_version 113236 (0.0012) -[2023-11-28 03:10:39,955][87424] Updated weights for policy 0, policy_version 113246 (0.0012) -[2023-11-28 03:10:40,423][87426] Updated weights for policy 1, policy_version 113060 (0.0011) -[2023-11-28 03:10:40,795][87426] Updated weights for policy 1, policy_version 113070 (0.0011) -[2023-11-28 03:10:41,168][87426] Updated weights for policy 1, policy_version 113080 (0.0010) -[2023-11-28 03:10:41,928][87424] Updated weights for policy 0, policy_version 113256 (0.0011) -[2023-11-28 03:10:42,301][87424] Updated weights for policy 0, policy_version 113266 (0.0012) -[2023-11-28 03:10:42,685][87424] Updated weights for policy 0, policy_version 113276 (0.0012) -[2023-11-28 03:10:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 57950208. Throughput: 0: 2746.7, 1: 2719.3. Samples: 57962160. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:10:43,445][86177] Avg episode reward: [(0, '-517.180'), (1, '-508.580')] -[2023-11-28 03:10:43,585][87426] Updated weights for policy 1, policy_version 113090 (0.0008) -[2023-11-28 03:10:43,967][87426] Updated weights for policy 1, policy_version 113100 (0.0012) -[2023-11-28 03:10:44,350][87426] Updated weights for policy 1, policy_version 113110 (0.0012) -[2023-11-28 03:10:44,733][87426] Updated weights for policy 1, policy_version 113120 (0.0011) -[2023-11-28 03:10:45,070][87424] Updated weights for policy 0, policy_version 113286 (0.0012) -[2023-11-28 03:10:45,453][87424] Updated weights for policy 0, policy_version 113296 (0.0012) -[2023-11-28 03:10:45,838][87424] Updated weights for policy 0, policy_version 113306 (0.0012) -[2023-11-28 03:10:47,288][87426] Updated weights for policy 1, policy_version 113130 (0.0012) -[2023-11-28 03:10:47,667][87426] Updated weights for policy 1, policy_version 113140 (0.0011) -[2023-11-28 03:10:48,037][87426] Updated weights for policy 1, policy_version 113150 (0.0012) -[2023-11-28 03:10:48,079][87424] Updated weights for policy 0, policy_version 113316 (0.0011) -[2023-11-28 03:10:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 57974784. Throughput: 0: 2750.1, 1: 2715.9. Samples: 57986736. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:10:48,445][86177] Avg episode reward: [(0, '-514.750'), (1, '-516.240')] -[2023-11-28 03:10:48,466][87424] Updated weights for policy 0, policy_version 113326 (0.0011) -[2023-11-28 03:10:48,845][87424] Updated weights for policy 0, policy_version 113336 (0.0008) -[2023-11-28 03:10:50,407][87426] Updated weights for policy 1, policy_version 113160 (0.0011) -[2023-11-28 03:10:50,787][87426] Updated weights for policy 1, policy_version 113170 (0.0012) -[2023-11-28 03:10:50,903][87424] Updated weights for policy 0, policy_version 113346 (0.0010) -[2023-11-28 03:10:51,169][87426] Updated weights for policy 1, policy_version 113180 (0.0011) -[2023-11-28 03:10:51,282][87424] Updated weights for policy 0, policy_version 113356 (0.0008) -[2023-11-28 03:10:51,675][87424] Updated weights for policy 0, policy_version 113366 (0.0009) -[2023-11-28 03:10:52,053][87424] Updated weights for policy 0, policy_version 113376 (0.0009) -[2023-11-28 03:10:53,421][87426] Updated weights for policy 1, policy_version 113190 (0.0010) -[2023-11-28 03:10:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 57999360. Throughput: 0: 2754.8, 1: 2682.1. Samples: 58018596. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:10:53,445][86177] Avg episode reward: [(0, '-530.480'), (1, '-512.780')] -[2023-11-28 03:10:53,799][87426] Updated weights for policy 1, policy_version 113200 (0.0011) -[2023-11-28 03:10:54,179][87426] Updated weights for policy 1, policy_version 113210 (0.0009) -[2023-11-28 03:10:54,377][87424] Updated weights for policy 0, policy_version 113386 (0.0012) -[2023-11-28 03:10:54,762][87424] Updated weights for policy 0, policy_version 113396 (0.0012) -[2023-11-28 03:10:55,144][87424] Updated weights for policy 0, policy_version 113406 (0.0012) -[2023-11-28 03:10:56,393][87426] Updated weights for policy 1, policy_version 113220 (0.0009) -[2023-11-28 03:10:56,780][87426] Updated weights for policy 1, policy_version 113230 (0.0009) -[2023-11-28 03:10:56,919][87424] Updated weights for policy 0, policy_version 113416 (0.0012) -[2023-11-28 03:10:57,160][87426] Updated weights for policy 1, policy_version 113240 (0.0008) -[2023-11-28 03:10:57,300][87424] Updated weights for policy 0, policy_version 113426 (0.0012) -[2023-11-28 03:10:57,692][87424] Updated weights for policy 0, policy_version 113436 (0.0012) -[2023-11-28 03:10:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58032128. Throughput: 0: 2758.5, 1: 2683.2. Samples: 58043040. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:10:58,445][86177] Avg episode reward: [(0, '-525.210'), (1, '-515.410')] -[2023-11-28 03:10:59,490][87424] Updated weights for policy 0, policy_version 113446 (0.0012) -[2023-11-28 03:10:59,615][87426] Updated weights for policy 1, policy_version 113250 (0.0008) -[2023-11-28 03:10:59,869][87424] Updated weights for policy 0, policy_version 113456 (0.0011) -[2023-11-28 03:10:59,992][87426] Updated weights for policy 1, policy_version 113260 (0.0010) -[2023-11-28 03:11:00,256][87424] Updated weights for policy 0, policy_version 113466 (0.0008) -[2023-11-28 03:11:00,380][87426] Updated weights for policy 1, policy_version 113270 (0.0008) -[2023-11-28 03:11:00,754][87426] Updated weights for policy 1, policy_version 113280 (0.0011) -[2023-11-28 03:11:02,275][87424] Updated weights for policy 0, policy_version 113476 (0.0010) -[2023-11-28 03:11:02,573][87426] Updated weights for policy 1, policy_version 113290 (0.0008) -[2023-11-28 03:11:02,657][87424] Updated weights for policy 0, policy_version 113486 (0.0011) -[2023-11-28 03:11:02,951][87426] Updated weights for policy 1, policy_version 113300 (0.0008) -[2023-11-28 03:11:03,041][87424] Updated weights for policy 0, policy_version 113496 (0.0012) -[2023-11-28 03:11:03,316][87426] Updated weights for policy 1, policy_version 113310 (0.0008) -[2023-11-28 03:11:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 58064896. Throughput: 0: 2804.7, 1: 2688.5. Samples: 58069476. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:11:03,445][86177] Avg episode reward: [(0, '-521.890'), (1, '-526.140')] -[2023-11-28 03:11:05,104][87424] Updated weights for policy 0, policy_version 113506 (0.0011) -[2023-11-28 03:11:05,472][87424] Updated weights for policy 0, policy_version 113516 (0.0010) -[2023-11-28 03:11:05,855][87426] Updated weights for policy 1, policy_version 113320 (0.0011) -[2023-11-28 03:11:05,857][87424] Updated weights for policy 0, policy_version 113526 (0.0008) -[2023-11-28 03:11:06,239][87426] Updated weights for policy 1, policy_version 113330 (0.0011) -[2023-11-28 03:11:06,242][87424] Updated weights for policy 0, policy_version 113536 (0.0009) -[2023-11-28 03:11:06,613][87426] Updated weights for policy 1, policy_version 113340 (0.0009) -[2023-11-28 03:11:08,082][87424] Updated weights for policy 0, policy_version 113546 (0.0008) -[2023-11-28 03:11:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58081280. Throughput: 0: 2823.9, 1: 2679.3. Samples: 58102632. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:11:08,445][86177] Avg episode reward: [(0, '-520.590'), (1, '-515.610')] -[2023-11-28 03:11:08,471][87424] Updated weights for policy 0, policy_version 113556 (0.0010) -[2023-11-28 03:11:08,789][87426] Updated weights for policy 1, policy_version 113350 (0.0010) -[2023-11-28 03:11:08,857][87424] Updated weights for policy 0, policy_version 113566 (0.0016) -[2023-11-28 03:11:09,171][87426] Updated weights for policy 1, policy_version 113360 (0.0011) -[2023-11-28 03:11:09,545][87426] Updated weights for policy 1, policy_version 113370 (0.0011) -[2023-11-28 03:11:11,317][87424] Updated weights for policy 0, policy_version 113576 (0.0012) -[2023-11-28 03:11:11,700][87424] Updated weights for policy 0, policy_version 113586 (0.0012) -[2023-11-28 03:11:11,957][87426] Updated weights for policy 1, policy_version 113380 (0.0011) -[2023-11-28 03:11:12,075][87424] Updated weights for policy 0, policy_version 113596 (0.0010) -[2023-11-28 03:11:12,333][87426] Updated weights for policy 1, policy_version 113390 (0.0011) -[2023-11-28 03:11:12,714][87426] Updated weights for policy 1, policy_version 113400 (0.0012) -[2023-11-28 03:11:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58114048. Throughput: 0: 2813.6, 1: 2657.8. Samples: 58126368. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:11:13,445][86177] Avg episode reward: [(0, '-516.770'), (1, '-532.360')] -[2023-11-28 03:11:14,564][87424] Updated weights for policy 0, policy_version 113606 (0.0009) -[2023-11-28 03:11:14,967][87424] Updated weights for policy 0, policy_version 113616 (0.0008) -[2023-11-28 03:11:15,071][87426] Updated weights for policy 1, policy_version 113410 (0.0011) -[2023-11-28 03:11:15,343][87424] Updated weights for policy 0, policy_version 113626 (0.0008) -[2023-11-28 03:11:15,448][87426] Updated weights for policy 1, policy_version 113420 (0.0011) -[2023-11-28 03:11:15,826][87426] Updated weights for policy 1, policy_version 113430 (0.0011) -[2023-11-28 03:11:16,205][87426] Updated weights for policy 1, policy_version 113440 (0.0010) -[2023-11-28 03:11:17,391][87424] Updated weights for policy 0, policy_version 113636 (0.0011) -[2023-11-28 03:11:17,776][87424] Updated weights for policy 0, policy_version 113646 (0.0011) -[2023-11-28 03:11:18,154][87424] Updated weights for policy 0, policy_version 113656 (0.0012) -[2023-11-28 03:11:18,264][87426] Updated weights for policy 1, policy_version 113450 (0.0009) -[2023-11-28 03:11:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 58130432. Throughput: 0: 2786.8, 1: 2657.2. Samples: 58149916. Policy #0 lag: (min: 31.0, avg: 33.6, max: 53.0) -[2023-11-28 03:11:18,445][86177] Avg episode reward: [(0, '-513.730'), (1, '-533.380')] -[2023-11-28 03:11:18,654][87426] Updated weights for policy 1, policy_version 113460 (0.0007) -[2023-11-28 03:11:19,021][87426] Updated weights for policy 1, policy_version 113470 (0.0009) -[2023-11-28 03:11:20,045][87424] Updated weights for policy 0, policy_version 113666 (0.0027) -[2023-11-28 03:11:20,403][87424] Updated weights for policy 0, policy_version 113676 (0.0009) -[2023-11-28 03:11:20,806][87424] Updated weights for policy 0, policy_version 113686 (0.0012) -[2023-11-28 03:11:21,191][87424] Updated weights for policy 0, policy_version 113696 (0.0012) -[2023-11-28 03:11:21,283][87426] Updated weights for policy 1, policy_version 113480 (0.0011) -[2023-11-28 03:11:21,661][87426] Updated weights for policy 1, policy_version 113490 (0.0012) -[2023-11-28 03:11:22,035][87426] Updated weights for policy 1, policy_version 113500 (0.0012) -[2023-11-28 03:11:23,099][87424] Updated weights for policy 0, policy_version 113706 (0.0012) -[2023-11-28 03:11:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58163200. Throughput: 0: 2800.1, 1: 2650.3. Samples: 58182552. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:11:23,445][86177] Avg episode reward: [(0, '-510.910'), (1, '-539.790')] -[2023-11-28 03:11:23,478][87424] Updated weights for policy 0, policy_version 113716 (0.0012) -[2023-11-28 03:11:23,862][87424] Updated weights for policy 0, policy_version 113726 (0.0012) -[2023-11-28 03:11:24,473][87426] Updated weights for policy 1, policy_version 113510 (0.0010) -[2023-11-28 03:11:24,859][87426] Updated weights for policy 1, policy_version 113520 (0.0010) -[2023-11-28 03:11:25,236][87426] Updated weights for policy 1, policy_version 113530 (0.0012) -[2023-11-28 03:11:26,091][87424] Updated weights for policy 0, policy_version 113736 (0.0010) -[2023-11-28 03:11:26,481][87424] Updated weights for policy 0, policy_version 113746 (0.0007) -[2023-11-28 03:11:26,857][87424] Updated weights for policy 0, policy_version 113756 (0.0007) -[2023-11-28 03:11:27,219][87426] Updated weights for policy 1, policy_version 113540 (0.0011) -[2023-11-28 03:11:27,603][87426] Updated weights for policy 1, policy_version 113550 (0.0008) -[2023-11-28 03:11:27,997][87426] Updated weights for policy 1, policy_version 113560 (0.0007) -[2023-11-28 03:11:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 58195968. Throughput: 0: 2799.2, 1: 2654.1. Samples: 58207560. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:11:28,445][86177] Avg episode reward: [(0, '-501.710'), (1, '-534.180')] -[2023-11-28 03:11:28,449][87424] Updated weights for policy 0, policy_version 113766 (0.0008) -[2023-11-28 03:11:28,835][87424] Updated weights for policy 0, policy_version 113776 (0.0007) -[2023-11-28 03:11:29,217][87424] Updated weights for policy 0, policy_version 113786 (0.0009) -[2023-11-28 03:11:30,242][87426] Updated weights for policy 1, policy_version 113570 (0.0008) -[2023-11-28 03:11:30,615][87426] Updated weights for policy 1, policy_version 113580 (0.0012) -[2023-11-28 03:11:30,993][87426] Updated weights for policy 1, policy_version 113590 (0.0010) -[2023-11-28 03:11:31,369][87426] Updated weights for policy 1, policy_version 113600 (0.0008) -[2023-11-28 03:11:31,415][87424] Updated weights for policy 0, policy_version 113796 (0.0012) -[2023-11-28 03:11:31,788][87424] Updated weights for policy 0, policy_version 113806 (0.0009) -[2023-11-28 03:11:32,176][87424] Updated weights for policy 0, policy_version 113816 (0.0009) -[2023-11-28 03:11:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58220544. Throughput: 0: 2800.6, 1: 2653.9. Samples: 58232192. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:11:33,446][86177] Avg episode reward: [(0, '-497.440'), (1, '-522.290')] -[2023-11-28 03:11:33,680][87426] Updated weights for policy 1, policy_version 113610 (0.0010) -[2023-11-28 03:11:34,059][87426] Updated weights for policy 1, policy_version 113620 (0.0009) -[2023-11-28 03:11:34,072][87424] Updated weights for policy 0, policy_version 113826 (0.0009) -[2023-11-28 03:11:34,444][87426] Updated weights for policy 1, policy_version 113630 (0.0010) -[2023-11-28 03:11:34,450][87424] Updated weights for policy 0, policy_version 113836 (0.0012) -[2023-11-28 03:11:34,833][87424] Updated weights for policy 0, policy_version 113846 (0.0010) -[2023-11-28 03:11:35,214][87424] Updated weights for policy 0, policy_version 113856 (0.0010) -[2023-11-28 03:11:36,858][87426] Updated weights for policy 1, policy_version 113640 (0.0012) -[2023-11-28 03:11:37,198][87424] Updated weights for policy 0, policy_version 113866 (0.0012) -[2023-11-28 03:11:37,231][87426] Updated weights for policy 1, policy_version 113650 (0.0012) -[2023-11-28 03:11:37,573][87424] Updated weights for policy 0, policy_version 113876 (0.0012) -[2023-11-28 03:11:37,607][87426] Updated weights for policy 1, policy_version 113660 (0.0011) -[2023-11-28 03:11:37,949][87424] Updated weights for policy 0, policy_version 113886 (0.0012) -[2023-11-28 03:11:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 58253312. Throughput: 0: 2817.8, 1: 2658.9. Samples: 58265048. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:11:38,445][86177] Avg episode reward: [(0, '-495.460'), (1, '-557.500')] -[2023-11-28 03:11:39,578][87426] Updated weights for policy 1, policy_version 113670 (0.0009) -[2023-11-28 03:11:39,952][87426] Updated weights for policy 1, policy_version 113680 (0.0009) -[2023-11-28 03:11:40,333][87426] Updated weights for policy 1, policy_version 113690 (0.0012) -[2023-11-28 03:11:40,427][87424] Updated weights for policy 0, policy_version 113896 (0.0012) -[2023-11-28 03:11:40,811][87424] Updated weights for policy 0, policy_version 113906 (0.0011) -[2023-11-28 03:11:41,203][87424] Updated weights for policy 0, policy_version 113916 (0.0012) -[2023-11-28 03:11:42,046][87426] Updated weights for policy 1, policy_version 113700 (0.0010) -[2023-11-28 03:11:42,425][87426] Updated weights for policy 1, policy_version 113710 (0.0011) -[2023-11-28 03:11:42,804][87426] Updated weights for policy 1, policy_version 113720 (0.0010) -[2023-11-28 03:11:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 58277888. Throughput: 0: 2822.6, 1: 2675.5. Samples: 58290452. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:11:43,445][86177] Avg episode reward: [(0, '-500.160'), (1, '-564.410')] -[2023-11-28 03:11:43,607][87424] Updated weights for policy 0, policy_version 113926 (0.0009) -[2023-11-28 03:11:43,993][87424] Updated weights for policy 0, policy_version 113936 (0.0007) -[2023-11-28 03:11:44,384][87424] Updated weights for policy 0, policy_version 113946 (0.0010) -[2023-11-28 03:11:44,994][87426] Updated weights for policy 1, policy_version 113730 (0.0010) -[2023-11-28 03:11:45,369][87426] Updated weights for policy 1, policy_version 113740 (0.0011) -[2023-11-28 03:11:45,752][87426] Updated weights for policy 1, policy_version 113750 (0.0011) -[2023-11-28 03:11:46,123][87426] Updated weights for policy 1, policy_version 113760 (0.0008) -[2023-11-28 03:11:46,834][87424] Updated weights for policy 0, policy_version 113956 (0.0007) -[2023-11-28 03:11:47,216][87424] Updated weights for policy 0, policy_version 113966 (0.0007) -[2023-11-28 03:11:47,601][87424] Updated weights for policy 0, policy_version 113976 (0.0008) -[2023-11-28 03:11:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58302464. Throughput: 0: 2763.0, 1: 2670.9. Samples: 58314004. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:11:48,445][86177] Avg episode reward: [(0, '-508.580'), (1, '-566.360')] -[2023-11-28 03:11:48,620][87426] Updated weights for policy 1, policy_version 113770 (0.0007) -[2023-11-28 03:11:49,000][87426] Updated weights for policy 1, policy_version 113780 (0.0010) -[2023-11-28 03:11:49,370][87426] Updated weights for policy 1, policy_version 113790 (0.0011) -[2023-11-28 03:11:50,133][87424] Updated weights for policy 0, policy_version 113986 (0.0011) -[2023-11-28 03:11:50,524][87424] Updated weights for policy 0, policy_version 113996 (0.0012) -[2023-11-28 03:11:50,905][87424] Updated weights for policy 0, policy_version 114006 (0.0012) -[2023-11-28 03:11:51,287][87424] Updated weights for policy 0, policy_version 114016 (0.0011) -[2023-11-28 03:11:51,755][87426] Updated weights for policy 1, policy_version 113800 (0.0009) -[2023-11-28 03:11:52,127][87426] Updated weights for policy 1, policy_version 113810 (0.0011) -[2023-11-28 03:11:52,500][87426] Updated weights for policy 1, policy_version 113820 (0.0008) -[2023-11-28 03:11:53,208][87424] Updated weights for policy 0, policy_version 114026 (0.0012) -[2023-11-28 03:11:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58327040. Throughput: 0: 2720.8, 1: 2658.0. Samples: 58344676. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:11:53,445][86177] Avg episode reward: [(0, '-510.490'), (1, '-565.090')] -[2023-11-28 03:11:53,598][87424] Updated weights for policy 0, policy_version 114036 (0.0012) -[2023-11-28 03:11:53,979][87424] Updated weights for policy 0, policy_version 114046 (0.0011) -[2023-11-28 03:11:54,938][87426] Updated weights for policy 1, policy_version 113830 (0.0010) -[2023-11-28 03:11:55,322][87426] Updated weights for policy 1, policy_version 113840 (0.0011) -[2023-11-28 03:11:55,697][87426] Updated weights for policy 1, policy_version 113850 (0.0010) -[2023-11-28 03:11:56,503][87424] Updated weights for policy 0, policy_version 114056 (0.0008) -[2023-11-28 03:11:56,887][87424] Updated weights for policy 0, policy_version 114066 (0.0007) -[2023-11-28 03:11:57,268][87424] Updated weights for policy 0, policy_version 114076 (0.0008) -[2023-11-28 03:11:58,179][87426] Updated weights for policy 1, policy_version 113860 (0.0007) -[2023-11-28 03:11:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 58351616. Throughput: 0: 2716.5, 1: 2661.0. Samples: 58368352. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:11:58,445][86177] Avg episode reward: [(0, '-509.250'), (1, '-538.050')] -[2023-11-28 03:11:58,558][87426] Updated weights for policy 1, policy_version 113870 (0.0007) -[2023-11-28 03:11:58,940][87426] Updated weights for policy 1, policy_version 113880 (0.0008) -[2023-11-28 03:11:59,462][87424] Updated weights for policy 0, policy_version 114086 (0.0008) -[2023-11-28 03:11:59,863][87424] Updated weights for policy 0, policy_version 114096 (0.0008) -[2023-11-28 03:12:00,239][87424] Updated weights for policy 0, policy_version 114106 (0.0008) -[2023-11-28 03:12:01,325][87426] Updated weights for policy 1, policy_version 113890 (0.0010) -[2023-11-28 03:12:01,710][87426] Updated weights for policy 1, policy_version 113900 (0.0009) -[2023-11-28 03:12:02,097][87426] Updated weights for policy 1, policy_version 113910 (0.0011) -[2023-11-28 03:12:02,473][87426] Updated weights for policy 1, policy_version 113920 (0.0010) -[2023-11-28 03:12:02,563][87424] Updated weights for policy 0, policy_version 114116 (0.0010) -[2023-11-28 03:12:02,949][87424] Updated weights for policy 0, policy_version 114126 (0.0011) -[2023-11-28 03:12:03,324][87424] Updated weights for policy 0, policy_version 114136 (0.0012) -[2023-11-28 03:12:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5442.8). Total num frames: 58376192. Throughput: 0: 2749.3, 1: 2655.4. Samples: 58393128. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:12:03,445][86177] Avg episode reward: [(0, '-500.210'), (1, '-525.700')] -[2023-11-28 03:12:04,356][87426] Updated weights for policy 1, policy_version 113930 (0.0009) -[2023-11-28 03:12:04,723][87426] Updated weights for policy 1, policy_version 113940 (0.0013) -[2023-11-28 03:12:05,108][87426] Updated weights for policy 1, policy_version 113950 (0.0011) -[2023-11-28 03:12:05,754][87424] Updated weights for policy 0, policy_version 114146 (0.0012) -[2023-11-28 03:12:06,138][87424] Updated weights for policy 0, policy_version 114156 (0.0012) -[2023-11-28 03:12:06,521][87424] Updated weights for policy 0, policy_version 114166 (0.0012) -[2023-11-28 03:12:06,793][87426] Updated weights for policy 1, policy_version 113960 (0.0012) -[2023-11-28 03:12:06,906][87424] Updated weights for policy 0, policy_version 114176 (0.0010) -[2023-11-28 03:12:07,174][87426] Updated weights for policy 1, policy_version 113970 (0.0012) -[2023-11-28 03:12:07,549][87426] Updated weights for policy 1, policy_version 113980 (0.0011) -[2023-11-28 03:12:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58408960. Throughput: 0: 2729.0, 1: 2672.3. Samples: 58425608. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:12:08,445][86177] Avg episode reward: [(0, '-501.670'), (1, '-528.640')] -[2023-11-28 03:12:08,749][87424] Updated weights for policy 0, policy_version 114186 (0.0012) -[2023-11-28 03:12:09,125][87424] Updated weights for policy 0, policy_version 114196 (0.0012) -[2023-11-28 03:12:09,500][87424] Updated weights for policy 0, policy_version 114206 (0.0012) -[2023-11-28 03:12:09,906][87426] Updated weights for policy 1, policy_version 113990 (0.0011) -[2023-11-28 03:12:10,288][87426] Updated weights for policy 1, policy_version 114000 (0.0012) -[2023-11-28 03:12:10,665][87426] Updated weights for policy 1, policy_version 114010 (0.0012) -[2023-11-28 03:12:11,745][87424] Updated weights for policy 0, policy_version 114216 (0.0011) -[2023-11-28 03:12:12,127][87424] Updated weights for policy 0, policy_version 114226 (0.0009) -[2023-11-28 03:12:12,510][87424] Updated weights for policy 0, policy_version 114236 (0.0011) -[2023-11-28 03:12:13,114][87426] Updated weights for policy 1, policy_version 114020 (0.0011) -[2023-11-28 03:12:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 58433536. Throughput: 0: 2714.0, 1: 2677.0. Samples: 58450156. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:12:13,445][86177] Avg episode reward: [(0, '-501.680'), (1, '-531.140')] -[2023-11-28 03:12:13,496][87426] Updated weights for policy 1, policy_version 114030 (0.0009) -[2023-11-28 03:12:13,868][87426] Updated weights for policy 1, policy_version 114040 (0.0007) -[2023-11-28 03:12:14,824][87424] Updated weights for policy 0, policy_version 114246 (0.0012) -[2023-11-28 03:12:15,217][87424] Updated weights for policy 0, policy_version 114256 (0.0012) -[2023-11-28 03:12:15,603][87424] Updated weights for policy 0, policy_version 114266 (0.0012) -[2023-11-28 03:12:15,738][87426] Updated weights for policy 1, policy_version 114050 (0.0009) -[2023-11-28 03:12:16,111][87426] Updated weights for policy 1, policy_version 114060 (0.0012) -[2023-11-28 03:12:16,494][87426] Updated weights for policy 1, policy_version 114070 (0.0012) -[2023-11-28 03:12:16,874][87426] Updated weights for policy 1, policy_version 114080 (0.0012) -[2023-11-28 03:12:17,398][87424] Updated weights for policy 0, policy_version 114276 (0.0012) -[2023-11-28 03:12:17,784][87424] Updated weights for policy 0, policy_version 114286 (0.0012) -[2023-11-28 03:12:18,182][87424] Updated weights for policy 0, policy_version 114296 (0.0011) -[2023-11-28 03:12:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58458112. Throughput: 0: 2704.6, 1: 2685.1. Samples: 58474728. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:12:18,445][86177] Avg episode reward: [(0, '-502.580'), (1, '-521.750')] -[2023-11-28 03:12:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000114080_29204480.pth... -[2023-11-28 03:12:18,478][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000114304_29261824.pth... -[2023-11-28 03:12:18,499][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000111552_28557312.pth -[2023-11-28 03:12:18,506][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000114080_29204480.pth -[2023-11-28 03:12:18,509][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000111744_28606464.pth -[2023-11-28 03:12:18,514][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000114304_29261824.pth -[2023-11-28 03:12:19,056][87426] Updated weights for policy 1, policy_version 114090 (0.0011) -[2023-11-28 03:12:19,434][87426] Updated weights for policy 1, policy_version 114100 (0.0008) -[2023-11-28 03:12:19,810][87426] Updated weights for policy 1, policy_version 114110 (0.0008) -[2023-11-28 03:12:20,388][87424] Updated weights for policy 0, policy_version 114306 (0.0008) -[2023-11-28 03:12:20,770][87424] Updated weights for policy 0, policy_version 114316 (0.0011) -[2023-11-28 03:12:21,156][87424] Updated weights for policy 0, policy_version 114326 (0.0011) -[2023-11-28 03:12:21,540][87424] Updated weights for policy 0, policy_version 114336 (0.0012) -[2023-11-28 03:12:22,135][87426] Updated weights for policy 1, policy_version 114120 (0.0012) -[2023-11-28 03:12:22,517][87426] Updated weights for policy 1, policy_version 114130 (0.0012) -[2023-11-28 03:12:22,900][87426] Updated weights for policy 1, policy_version 114140 (0.0012) -[2023-11-28 03:12:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58490880. Throughput: 0: 2689.3, 1: 2703.6. Samples: 58507728. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:12:23,445][86177] Avg episode reward: [(0, '-502.230'), (1, '-520.050')] -[2023-11-28 03:12:24,047][87424] Updated weights for policy 0, policy_version 114346 (0.0009) -[2023-11-28 03:12:24,430][87424] Updated weights for policy 0, policy_version 114356 (0.0007) -[2023-11-28 03:12:24,770][87426] Updated weights for policy 1, policy_version 114150 (0.0011) -[2023-11-28 03:12:24,813][87424] Updated weights for policy 0, policy_version 114366 (0.0009) -[2023-11-28 03:12:25,149][87426] Updated weights for policy 1, policy_version 114160 (0.0012) -[2023-11-28 03:12:25,528][87426] Updated weights for policy 1, policy_version 114170 (0.0011) -[2023-11-28 03:12:26,499][87424] Updated weights for policy 0, policy_version 114376 (0.0008) -[2023-11-28 03:12:26,878][87424] Updated weights for policy 0, policy_version 114386 (0.0008) -[2023-11-28 03:12:27,268][87424] Updated weights for policy 0, policy_version 114396 (0.0008) -[2023-11-28 03:12:27,531][87426] Updated weights for policy 1, policy_version 114180 (0.0012) -[2023-11-28 03:12:27,912][87426] Updated weights for policy 1, policy_version 114190 (0.0011) -[2023-11-28 03:12:28,286][87426] Updated weights for policy 1, policy_version 114200 (0.0011) -[2023-11-28 03:12:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 58515456. Throughput: 0: 2681.2, 1: 2709.6. Samples: 58533040. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:12:28,445][86177] Avg episode reward: [(0, '-497.440'), (1, '-512.370')] -[2023-11-28 03:12:29,268][87424] Updated weights for policy 0, policy_version 114406 (0.0010) -[2023-11-28 03:12:29,651][87424] Updated weights for policy 0, policy_version 114416 (0.0011) -[2023-11-28 03:12:30,043][87424] Updated weights for policy 0, policy_version 114426 (0.0011) -[2023-11-28 03:12:30,593][87426] Updated weights for policy 1, policy_version 114210 (0.0011) -[2023-11-28 03:12:30,978][87426] Updated weights for policy 1, policy_version 114220 (0.0007) -[2023-11-28 03:12:31,364][87426] Updated weights for policy 1, policy_version 114230 (0.0008) -[2023-11-28 03:12:31,744][87426] Updated weights for policy 1, policy_version 114240 (0.0008) -[2023-11-28 03:12:32,054][87424] Updated weights for policy 0, policy_version 114436 (0.0012) -[2023-11-28 03:12:32,428][87424] Updated weights for policy 0, policy_version 114446 (0.0011) -[2023-11-28 03:12:32,817][87424] Updated weights for policy 0, policy_version 114456 (0.0008) -[2023-11-28 03:12:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58548224. Throughput: 0: 2712.2, 1: 2714.3. Samples: 58558196. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:12:33,445][86177] Avg episode reward: [(0, '-500.100'), (1, '-518.650')] -[2023-11-28 03:12:33,677][87426] Updated weights for policy 1, policy_version 114250 (0.0012) -[2023-11-28 03:12:34,059][87426] Updated weights for policy 1, policy_version 114260 (0.0009) -[2023-11-28 03:12:34,440][87426] Updated weights for policy 1, policy_version 114270 (0.0009) -[2023-11-28 03:12:34,716][87424] Updated weights for policy 0, policy_version 114466 (0.0009) -[2023-11-28 03:12:35,096][87424] Updated weights for policy 0, policy_version 114476 (0.0008) -[2023-11-28 03:12:35,478][87424] Updated weights for policy 0, policy_version 114486 (0.0009) -[2023-11-28 03:12:35,857][87424] Updated weights for policy 0, policy_version 114496 (0.0007) -[2023-11-28 03:12:36,830][87426] Updated weights for policy 1, policy_version 114280 (0.0009) -[2023-11-28 03:12:37,210][87426] Updated weights for policy 1, policy_version 114290 (0.0008) -[2023-11-28 03:12:37,591][87426] Updated weights for policy 1, policy_version 114300 (0.0008) -[2023-11-28 03:12:37,867][87424] Updated weights for policy 0, policy_version 114506 (0.0008) -[2023-11-28 03:12:38,252][87424] Updated weights for policy 0, policy_version 114516 (0.0010) -[2023-11-28 03:12:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 58572800. Throughput: 0: 2732.8, 1: 2736.9. Samples: 58590812. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:12:38,445][86177] Avg episode reward: [(0, '-504.810'), (1, '-523.550')] -[2023-11-28 03:12:38,635][87424] Updated weights for policy 0, policy_version 114526 (0.0008) -[2023-11-28 03:12:39,535][87426] Updated weights for policy 1, policy_version 114310 (0.0010) -[2023-11-28 03:12:39,909][87426] Updated weights for policy 1, policy_version 114320 (0.0012) -[2023-11-28 03:12:40,288][87426] Updated weights for policy 1, policy_version 114330 (0.0011) -[2023-11-28 03:12:40,970][87424] Updated weights for policy 0, policy_version 114536 (0.0011) -[2023-11-28 03:12:41,360][87424] Updated weights for policy 0, policy_version 114546 (0.0012) -[2023-11-28 03:12:41,729][87424] Updated weights for policy 0, policy_version 114556 (0.0012) -[2023-11-28 03:12:42,830][87426] Updated weights for policy 1, policy_version 114340 (0.0011) -[2023-11-28 03:12:43,202][87426] Updated weights for policy 1, policy_version 114350 (0.0008) -[2023-11-28 03:12:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 58597376. Throughput: 0: 2740.5, 1: 2738.8. Samples: 58614924. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:12:43,445][86177] Avg episode reward: [(0, '-507.120'), (1, '-519.570')] -[2023-11-28 03:12:43,580][87426] Updated weights for policy 1, policy_version 114360 (0.0007) -[2023-11-28 03:12:44,132][87424] Updated weights for policy 0, policy_version 114566 (0.0009) -[2023-11-28 03:12:44,516][87424] Updated weights for policy 0, policy_version 114576 (0.0007) -[2023-11-28 03:12:44,898][87424] Updated weights for policy 0, policy_version 114586 (0.0007) -[2023-11-28 03:12:45,655][87426] Updated weights for policy 1, policy_version 114370 (0.0008) -[2023-11-28 03:12:46,035][87426] Updated weights for policy 1, policy_version 114380 (0.0012) -[2023-11-28 03:12:46,416][87426] Updated weights for policy 1, policy_version 114390 (0.0007) -[2023-11-28 03:12:46,794][87426] Updated weights for policy 1, policy_version 114400 (0.0007) -[2023-11-28 03:12:47,457][87424] Updated weights for policy 0, policy_version 114596 (0.0009) -[2023-11-28 03:12:47,833][87424] Updated weights for policy 0, policy_version 114606 (0.0012) -[2023-11-28 03:12:48,206][87424] Updated weights for policy 0, policy_version 114616 (0.0009) -[2023-11-28 03:12:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 58621952. Throughput: 0: 2705.1, 1: 2737.1. Samples: 58638024. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:12:48,446][86177] Avg episode reward: [(0, '-510.330'), (1, '-518.600')] -[2023-11-28 03:12:49,288][87426] Updated weights for policy 1, policy_version 114410 (0.0012) -[2023-11-28 03:12:49,665][87426] Updated weights for policy 1, policy_version 114420 (0.0012) -[2023-11-28 03:12:49,961][87424] Updated weights for policy 0, policy_version 114626 (0.0008) -[2023-11-28 03:12:50,044][87426] Updated weights for policy 1, policy_version 114430 (0.0011) -[2023-11-28 03:12:50,348][87424] Updated weights for policy 0, policy_version 114636 (0.0012) -[2023-11-28 03:12:50,721][87424] Updated weights for policy 0, policy_version 114646 (0.0012) -[2023-11-28 03:12:51,108][87424] Updated weights for policy 0, policy_version 114656 (0.0012) -[2023-11-28 03:12:52,455][87426] Updated weights for policy 1, policy_version 114440 (0.0011) -[2023-11-28 03:12:52,837][87426] Updated weights for policy 1, policy_version 114450 (0.0012) -[2023-11-28 03:12:53,215][87426] Updated weights for policy 1, policy_version 114460 (0.0012) -[2023-11-28 03:12:53,332][87424] Updated weights for policy 0, policy_version 114666 (0.0011) -[2023-11-28 03:12:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58654720. Throughput: 0: 2722.4, 1: 2726.0. Samples: 58670784. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:12:53,445][86177] Avg episode reward: [(0, '-510.450'), (1, '-519.700')] -[2023-11-28 03:12:53,721][87424] Updated weights for policy 0, policy_version 114676 (0.0011) -[2023-11-28 03:12:54,118][87424] Updated weights for policy 0, policy_version 114686 (0.0009) -[2023-11-28 03:12:55,268][87426] Updated weights for policy 1, policy_version 114470 (0.0011) -[2023-11-28 03:12:55,651][87426] Updated weights for policy 1, policy_version 114480 (0.0012) -[2023-11-28 03:12:56,034][87426] Updated weights for policy 1, policy_version 114490 (0.0010) -[2023-11-28 03:12:56,144][87424] Updated weights for policy 0, policy_version 114696 (0.0008) -[2023-11-28 03:12:56,529][87424] Updated weights for policy 0, policy_version 114706 (0.0008) -[2023-11-28 03:12:56,911][87424] Updated weights for policy 0, policy_version 114716 (0.0007) -[2023-11-28 03:12:57,859][87426] Updated weights for policy 1, policy_version 114500 (0.0007) -[2023-11-28 03:12:58,233][87426] Updated weights for policy 1, policy_version 114510 (0.0007) -[2023-11-28 03:12:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58679296. Throughput: 0: 2731.1, 1: 2753.4. Samples: 58696960. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:12:58,446][86177] Avg episode reward: [(0, '-505.320'), (1, '-511.910')] -[2023-11-28 03:12:58,612][87426] Updated weights for policy 1, policy_version 114520 (0.0007) -[2023-11-28 03:12:59,353][87424] Updated weights for policy 0, policy_version 114726 (0.0010) -[2023-11-28 03:12:59,740][87424] Updated weights for policy 0, policy_version 114736 (0.0012) -[2023-11-28 03:13:00,128][87424] Updated weights for policy 0, policy_version 114746 (0.0011) -[2023-11-28 03:13:00,148][87426] Updated weights for policy 1, policy_version 114530 (0.0010) -[2023-11-28 03:13:00,525][87426] Updated weights for policy 1, policy_version 114540 (0.0012) -[2023-11-28 03:13:00,905][87426] Updated weights for policy 1, policy_version 114550 (0.0010) -[2023-11-28 03:13:01,281][87426] Updated weights for policy 1, policy_version 114560 (0.0007) -[2023-11-28 03:13:02,351][87424] Updated weights for policy 0, policy_version 114756 (0.0010) -[2023-11-28 03:13:02,718][87424] Updated weights for policy 0, policy_version 114766 (0.0009) -[2023-11-28 03:13:03,097][87424] Updated weights for policy 0, policy_version 114776 (0.0009) -[2023-11-28 03:13:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 58712064. Throughput: 0: 2720.7, 1: 2750.9. Samples: 58720952. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:13:03,445][86177] Avg episode reward: [(0, '-500.760'), (1, '-558.460')] -[2023-11-28 03:13:03,802][87426] Updated weights for policy 1, policy_version 114570 (0.0007) -[2023-11-28 03:13:04,182][87426] Updated weights for policy 1, policy_version 114580 (0.0007) -[2023-11-28 03:13:04,561][87426] Updated weights for policy 1, policy_version 114590 (0.0009) -[2023-11-28 03:13:05,281][87424] Updated weights for policy 0, policy_version 114786 (0.0008) -[2023-11-28 03:13:05,662][87424] Updated weights for policy 0, policy_version 114796 (0.0012) -[2023-11-28 03:13:06,050][87424] Updated weights for policy 0, policy_version 114806 (0.0012) -[2023-11-28 03:13:06,429][87424] Updated weights for policy 0, policy_version 114816 (0.0011) -[2023-11-28 03:13:07,065][87426] Updated weights for policy 1, policy_version 114600 (0.0012) -[2023-11-28 03:13:07,457][87426] Updated weights for policy 1, policy_version 114610 (0.0012) -[2023-11-28 03:13:07,831][87426] Updated weights for policy 1, policy_version 114620 (0.0011) -[2023-11-28 03:13:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58736640. Throughput: 0: 2728.9, 1: 2731.0. Samples: 58753424. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:13:08,446][86177] Avg episode reward: [(0, '-499.480'), (1, '-570.940')] -[2023-11-28 03:13:08,486][87424] Updated weights for policy 0, policy_version 114826 (0.0009) -[2023-11-28 03:13:08,869][87424] Updated weights for policy 0, policy_version 114836 (0.0008) -[2023-11-28 03:13:09,250][87424] Updated weights for policy 0, policy_version 114846 (0.0011) -[2023-11-28 03:13:09,769][87426] Updated weights for policy 1, policy_version 114630 (0.0009) -[2023-11-28 03:13:10,140][87426] Updated weights for policy 1, policy_version 114640 (0.0009) -[2023-11-28 03:13:10,513][87426] Updated weights for policy 1, policy_version 114650 (0.0012) -[2023-11-28 03:13:11,671][87424] Updated weights for policy 0, policy_version 114856 (0.0012) -[2023-11-28 03:13:12,061][87424] Updated weights for policy 0, policy_version 114866 (0.0011) -[2023-11-28 03:13:12,450][87424] Updated weights for policy 0, policy_version 114876 (0.0010) -[2023-11-28 03:13:12,714][87426] Updated weights for policy 1, policy_version 114660 (0.0012) -[2023-11-28 03:13:13,095][87426] Updated weights for policy 1, policy_version 114670 (0.0010) -[2023-11-28 03:13:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58761216. Throughput: 0: 2714.4, 1: 2704.6. Samples: 58776896. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:13:13,445][86177] Avg episode reward: [(0, '-511.940'), (1, '-572.420')] -[2023-11-28 03:13:13,474][87426] Updated weights for policy 1, policy_version 114680 (0.0008) -[2023-11-28 03:13:14,688][87424] Updated weights for policy 0, policy_version 114886 (0.0009) -[2023-11-28 03:13:15,072][87424] Updated weights for policy 0, policy_version 114896 (0.0008) -[2023-11-28 03:13:15,456][87424] Updated weights for policy 0, policy_version 114906 (0.0011) -[2023-11-28 03:13:15,782][87426] Updated weights for policy 1, policy_version 114690 (0.0008) -[2023-11-28 03:13:16,159][87426] Updated weights for policy 1, policy_version 114700 (0.0012) -[2023-11-28 03:13:16,540][87426] Updated weights for policy 1, policy_version 114710 (0.0012) -[2023-11-28 03:13:16,912][87426] Updated weights for policy 1, policy_version 114720 (0.0012) -[2023-11-28 03:13:17,610][87424] Updated weights for policy 0, policy_version 114916 (0.0010) -[2023-11-28 03:13:17,985][87424] Updated weights for policy 0, policy_version 114926 (0.0012) -[2023-11-28 03:13:18,371][87424] Updated weights for policy 0, policy_version 114936 (0.0011) -[2023-11-28 03:13:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58785792. Throughput: 0: 2678.1, 1: 2688.9. Samples: 58799712. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:13:18,445][86177] Avg episode reward: [(0, '-513.750'), (1, '-584.080')] -[2023-11-28 03:13:19,458][87426] Updated weights for policy 1, policy_version 114730 (0.0012) -[2023-11-28 03:13:19,839][87426] Updated weights for policy 1, policy_version 114740 (0.0011) -[2023-11-28 03:13:20,219][87426] Updated weights for policy 1, policy_version 114750 (0.0011) -[2023-11-28 03:13:20,942][87424] Updated weights for policy 0, policy_version 114946 (0.0012) -[2023-11-28 03:13:21,319][87424] Updated weights for policy 0, policy_version 114956 (0.0012) -[2023-11-28 03:13:21,699][87424] Updated weights for policy 0, policy_version 114966 (0.0012) -[2023-11-28 03:13:22,078][87424] Updated weights for policy 0, policy_version 114976 (0.0012) -[2023-11-28 03:13:22,422][87426] Updated weights for policy 1, policy_version 114760 (0.0010) -[2023-11-28 03:13:22,805][87426] Updated weights for policy 1, policy_version 114770 (0.0010) -[2023-11-28 03:13:23,186][87426] Updated weights for policy 1, policy_version 114780 (0.0011) -[2023-11-28 03:13:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58818560. Throughput: 0: 2657.7, 1: 2718.8. Samples: 58832756. Policy #0 lag: (min: 31.0, avg: 35.7, max: 63.0) -[2023-11-28 03:13:23,445][86177] Avg episode reward: [(0, '-512.400'), (1, '-540.520')] -[2023-11-28 03:13:24,271][87424] Updated weights for policy 0, policy_version 114986 (0.0012) -[2023-11-28 03:13:24,657][87424] Updated weights for policy 0, policy_version 114996 (0.0011) -[2023-11-28 03:13:25,045][87424] Updated weights for policy 0, policy_version 115006 (0.0011) -[2023-11-28 03:13:25,403][87426] Updated weights for policy 1, policy_version 114790 (0.0012) -[2023-11-28 03:13:25,803][87426] Updated weights for policy 1, policy_version 114800 (0.0012) -[2023-11-28 03:13:26,176][87426] Updated weights for policy 1, policy_version 114810 (0.0011) -[2023-11-28 03:13:27,339][87424] Updated weights for policy 0, policy_version 115016 (0.0008) -[2023-11-28 03:13:27,725][87424] Updated weights for policy 0, policy_version 115026 (0.0008) -[2023-11-28 03:13:28,113][87424] Updated weights for policy 0, policy_version 115036 (0.0009) -[2023-11-28 03:13:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58843136. Throughput: 0: 2658.7, 1: 2719.2. Samples: 58856932. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:13:28,446][86177] Avg episode reward: [(0, '-515.490'), (1, '-528.790')] -[2023-11-28 03:13:28,649][87426] Updated weights for policy 1, policy_version 114820 (0.0012) -[2023-11-28 03:13:29,029][87426] Updated weights for policy 1, policy_version 114830 (0.0010) -[2023-11-28 03:13:29,404][87426] Updated weights for policy 1, policy_version 114840 (0.0007) -[2023-11-28 03:13:30,496][87424] Updated weights for policy 0, policy_version 115046 (0.0011) -[2023-11-28 03:13:30,882][87424] Updated weights for policy 0, policy_version 115056 (0.0012) -[2023-11-28 03:13:31,262][87424] Updated weights for policy 0, policy_version 115066 (0.0012) -[2023-11-28 03:13:31,623][87426] Updated weights for policy 1, policy_version 114850 (0.0008) -[2023-11-28 03:13:32,004][87426] Updated weights for policy 1, policy_version 114860 (0.0011) -[2023-11-28 03:13:32,380][87426] Updated weights for policy 1, policy_version 114870 (0.0012) -[2023-11-28 03:13:32,762][87426] Updated weights for policy 1, policy_version 114880 (0.0009) -[2023-11-28 03:13:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 58867712. Throughput: 0: 2670.8, 1: 2725.5. Samples: 58880856. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:13:33,445][86177] Avg episode reward: [(0, '-504.170'), (1, '-520.980')] -[2023-11-28 03:13:33,712][87424] Updated weights for policy 0, policy_version 115076 (0.0011) -[2023-11-28 03:13:34,093][87424] Updated weights for policy 0, policy_version 115086 (0.0012) -[2023-11-28 03:13:34,485][87424] Updated weights for policy 0, policy_version 115096 (0.0012) -[2023-11-28 03:13:34,577][87426] Updated weights for policy 1, policy_version 114890 (0.0011) -[2023-11-28 03:13:34,952][87426] Updated weights for policy 1, policy_version 114900 (0.0010) -[2023-11-28 03:13:35,331][87426] Updated weights for policy 1, policy_version 114910 (0.0008) -[2023-11-28 03:13:36,554][87424] Updated weights for policy 0, policy_version 115106 (0.0012) -[2023-11-28 03:13:36,935][87424] Updated weights for policy 0, policy_version 115116 (0.0012) -[2023-11-28 03:13:37,314][87424] Updated weights for policy 0, policy_version 115126 (0.0012) -[2023-11-28 03:13:37,664][87426] Updated weights for policy 1, policy_version 114920 (0.0010) -[2023-11-28 03:13:37,696][87424] Updated weights for policy 0, policy_version 115136 (0.0012) -[2023-11-28 03:13:38,042][87426] Updated weights for policy 1, policy_version 114930 (0.0008) -[2023-11-28 03:13:38,424][87426] Updated weights for policy 1, policy_version 114940 (0.0012) -[2023-11-28 03:13:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 58892288. Throughput: 0: 2652.4, 1: 2721.2. Samples: 58912596. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:13:38,445][86177] Avg episode reward: [(0, '-506.360'), (1, '-511.400')] -[2023-11-28 03:13:39,771][87424] Updated weights for policy 0, policy_version 115146 (0.0009) -[2023-11-28 03:13:40,154][87424] Updated weights for policy 0, policy_version 115156 (0.0011) -[2023-11-28 03:13:40,541][87424] Updated weights for policy 0, policy_version 115166 (0.0011) -[2023-11-28 03:13:40,973][87426] Updated weights for policy 1, policy_version 114950 (0.0012) -[2023-11-28 03:13:41,358][87426] Updated weights for policy 1, policy_version 114960 (0.0012) -[2023-11-28 03:13:41,731][87426] Updated weights for policy 1, policy_version 114970 (0.0012) -[2023-11-28 03:13:42,410][87424] Updated weights for policy 0, policy_version 115176 (0.0011) -[2023-11-28 03:13:42,792][87424] Updated weights for policy 0, policy_version 115186 (0.0010) -[2023-11-28 03:13:43,178][87424] Updated weights for policy 0, policy_version 115196 (0.0012) -[2023-11-28 03:13:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58925056. Throughput: 0: 2661.4, 1: 2652.2. Samples: 58936072. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:13:43,445][86177] Avg episode reward: [(0, '-503.770'), (1, '-529.690')] -[2023-11-28 03:13:44,256][87426] Updated weights for policy 1, policy_version 114980 (0.0011) -[2023-11-28 03:13:44,635][87426] Updated weights for policy 1, policy_version 114990 (0.0011) -[2023-11-28 03:13:45,016][87426] Updated weights for policy 1, policy_version 115000 (0.0011) -[2023-11-28 03:13:45,548][87424] Updated weights for policy 0, policy_version 115206 (0.0011) -[2023-11-28 03:13:45,937][87424] Updated weights for policy 0, policy_version 115216 (0.0010) -[2023-11-28 03:13:46,313][87424] Updated weights for policy 0, policy_version 115226 (0.0008) -[2023-11-28 03:13:46,953][87426] Updated weights for policy 1, policy_version 115010 (0.0011) -[2023-11-28 03:13:47,322][87426] Updated weights for policy 1, policy_version 115020 (0.0009) -[2023-11-28 03:13:47,703][87426] Updated weights for policy 1, policy_version 115030 (0.0009) -[2023-11-28 03:13:48,083][87426] Updated weights for policy 1, policy_version 115040 (0.0008) -[2023-11-28 03:13:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 58949632. Throughput: 0: 2671.9, 1: 2646.0. Samples: 58960260. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:13:48,445][86177] Avg episode reward: [(0, '-507.580'), (1, '-528.910')] -[2023-11-28 03:13:48,604][87424] Updated weights for policy 0, policy_version 115236 (0.0008) -[2023-11-28 03:13:48,981][87424] Updated weights for policy 0, policy_version 115246 (0.0008) -[2023-11-28 03:13:49,368][87424] Updated weights for policy 0, policy_version 115256 (0.0009) -[2023-11-28 03:13:50,528][87426] Updated weights for policy 1, policy_version 115050 (0.0011) -[2023-11-28 03:13:50,911][87426] Updated weights for policy 1, policy_version 115060 (0.0007) -[2023-11-28 03:13:51,284][87426] Updated weights for policy 1, policy_version 115070 (0.0008) -[2023-11-28 03:13:51,843][87424] Updated weights for policy 0, policy_version 115266 (0.0008) -[2023-11-28 03:13:52,229][87424] Updated weights for policy 0, policy_version 115276 (0.0012) -[2023-11-28 03:13:52,605][87424] Updated weights for policy 0, policy_version 115286 (0.0012) -[2023-11-28 03:13:52,983][87424] Updated weights for policy 0, policy_version 115296 (0.0012) -[2023-11-28 03:13:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 58974208. Throughput: 0: 2645.5, 1: 2649.5. Samples: 58991700. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:13:53,445][86177] Avg episode reward: [(0, '-506.480'), (1, '-527.020')] -[2023-11-28 03:13:53,509][87426] Updated weights for policy 1, policy_version 115080 (0.0012) -[2023-11-28 03:13:53,889][87426] Updated weights for policy 1, policy_version 115090 (0.0012) -[2023-11-28 03:13:54,270][87426] Updated weights for policy 1, policy_version 115100 (0.0012) -[2023-11-28 03:13:55,104][87424] Updated weights for policy 0, policy_version 115306 (0.0008) -[2023-11-28 03:13:55,491][87424] Updated weights for policy 0, policy_version 115316 (0.0007) -[2023-11-28 03:13:55,875][87424] Updated weights for policy 0, policy_version 115326 (0.0007) -[2023-11-28 03:13:56,876][87426] Updated weights for policy 1, policy_version 115110 (0.0009) -[2023-11-28 03:13:57,252][87426] Updated weights for policy 1, policy_version 115120 (0.0007) -[2023-11-28 03:13:57,636][87426] Updated weights for policy 1, policy_version 115130 (0.0007) -[2023-11-28 03:13:57,879][87424] Updated weights for policy 0, policy_version 115336 (0.0011) -[2023-11-28 03:13:58,253][87424] Updated weights for policy 0, policy_version 115346 (0.0011) -[2023-11-28 03:13:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 58998784. Throughput: 0: 2665.4, 1: 2642.9. Samples: 59015768. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:13:58,445][86177] Avg episode reward: [(0, '-509.360'), (1, '-523.230')] -[2023-11-28 03:13:58,644][87424] Updated weights for policy 0, policy_version 115356 (0.0010) -[2023-11-28 03:13:59,413][87426] Updated weights for policy 1, policy_version 115140 (0.0007) -[2023-11-28 03:13:59,798][87426] Updated weights for policy 1, policy_version 115150 (0.0008) -[2023-11-28 03:14:00,178][87426] Updated weights for policy 1, policy_version 115160 (0.0008) -[2023-11-28 03:14:00,864][87424] Updated weights for policy 0, policy_version 115366 (0.0009) -[2023-11-28 03:14:01,243][87424] Updated weights for policy 0, policy_version 115376 (0.0011) -[2023-11-28 03:14:01,632][87424] Updated weights for policy 0, policy_version 115386 (0.0008) -[2023-11-28 03:14:02,520][87426] Updated weights for policy 1, policy_version 115170 (0.0010) -[2023-11-28 03:14:02,894][87426] Updated weights for policy 1, policy_version 115180 (0.0010) -[2023-11-28 03:14:03,273][87426] Updated weights for policy 1, policy_version 115190 (0.0009) -[2023-11-28 03:14:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 59023360. Throughput: 0: 2684.3, 1: 2660.4. Samples: 59040224. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:14:03,445][86177] Avg episode reward: [(0, '-511.590'), (1, '-519.600')] -[2023-11-28 03:14:03,485][87424] Updated weights for policy 0, policy_version 115396 (0.0010) -[2023-11-28 03:14:03,648][87426] Updated weights for policy 1, policy_version 115200 (0.0009) -[2023-11-28 03:14:03,870][87424] Updated weights for policy 0, policy_version 115406 (0.0011) -[2023-11-28 03:14:04,247][87424] Updated weights for policy 0, policy_version 115416 (0.0012) -[2023-11-28 03:14:06,074][87426] Updated weights for policy 1, policy_version 115210 (0.0012) -[2023-11-28 03:14:06,277][87424] Updated weights for policy 0, policy_version 115426 (0.0012) -[2023-11-28 03:14:06,454][87426] Updated weights for policy 1, policy_version 115220 (0.0012) -[2023-11-28 03:14:06,664][87424] Updated weights for policy 0, policy_version 115436 (0.0011) -[2023-11-28 03:14:06,825][87426] Updated weights for policy 1, policy_version 115230 (0.0010) -[2023-11-28 03:14:07,040][87424] Updated weights for policy 0, policy_version 115446 (0.0012) -[2023-11-28 03:14:07,423][87424] Updated weights for policy 0, policy_version 115456 (0.0012) -[2023-11-28 03:14:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 59056128. Throughput: 0: 2716.9, 1: 2629.4. Samples: 59073340. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:14:08,445][86177] Avg episode reward: [(0, '-504.220'), (1, '-548.470')] -[2023-11-28 03:14:08,932][87426] Updated weights for policy 1, policy_version 115240 (0.0011) -[2023-11-28 03:14:09,311][87426] Updated weights for policy 1, policy_version 115250 (0.0011) -[2023-11-28 03:14:09,586][87424] Updated weights for policy 0, policy_version 115466 (0.0011) -[2023-11-28 03:14:09,688][87426] Updated weights for policy 1, policy_version 115260 (0.0011) -[2023-11-28 03:14:09,958][87424] Updated weights for policy 0, policy_version 115476 (0.0011) -[2023-11-28 03:14:10,342][87424] Updated weights for policy 0, policy_version 115486 (0.0012) -[2023-11-28 03:14:11,797][87426] Updated weights for policy 1, policy_version 115270 (0.0010) -[2023-11-28 03:14:12,169][87426] Updated weights for policy 1, policy_version 115280 (0.0012) -[2023-11-28 03:14:12,522][87424] Updated weights for policy 0, policy_version 115496 (0.0012) -[2023-11-28 03:14:12,551][87426] Updated weights for policy 1, policy_version 115290 (0.0011) -[2023-11-28 03:14:12,905][87424] Updated weights for policy 0, policy_version 115506 (0.0012) -[2023-11-28 03:14:13,288][87424] Updated weights for policy 0, policy_version 115516 (0.0012) -[2023-11-28 03:14:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 59088896. Throughput: 0: 2716.9, 1: 2633.4. Samples: 59097696. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:14:13,445][86177] Avg episode reward: [(0, '-513.910'), (1, '-550.480')] -[2023-11-28 03:14:14,877][87426] Updated weights for policy 1, policy_version 115300 (0.0010) -[2023-11-28 03:14:15,258][87426] Updated weights for policy 1, policy_version 115310 (0.0008) -[2023-11-28 03:14:15,265][87424] Updated weights for policy 0, policy_version 115526 (0.0012) -[2023-11-28 03:14:15,632][87426] Updated weights for policy 1, policy_version 115320 (0.0010) -[2023-11-28 03:14:15,649][87424] Updated weights for policy 0, policy_version 115536 (0.0011) -[2023-11-28 03:14:16,028][87424] Updated weights for policy 0, policy_version 115546 (0.0012) -[2023-11-28 03:14:17,604][87426] Updated weights for policy 1, policy_version 115330 (0.0011) -[2023-11-28 03:14:17,986][87426] Updated weights for policy 1, policy_version 115340 (0.0009) -[2023-11-28 03:14:18,114][87424] Updated weights for policy 0, policy_version 115556 (0.0011) -[2023-11-28 03:14:18,375][87426] Updated weights for policy 1, policy_version 115350 (0.0011) -[2023-11-28 03:14:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 59105280. Throughput: 0: 2732.2, 1: 2642.6. Samples: 59122728. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:14:18,446][86177] Avg episode reward: [(0, '-512.550'), (1, '-570.930')] -[2023-11-28 03:14:18,500][87424] Updated weights for policy 0, policy_version 115566 (0.0011) -[2023-11-28 03:14:18,743][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000115360_29532160.pth... -[2023-11-28 03:14:18,745][87426] Updated weights for policy 1, policy_version 115360 (0.0012) -[2023-11-28 03:14:18,788][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000112832_28884992.pth -[2023-11-28 03:14:18,889][87424] Updated weights for policy 0, policy_version 115576 (0.0008) -[2023-11-28 03:14:19,189][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000115584_29589504.pth... -[2023-11-28 03:14:19,235][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000113024_28934144.pth -[2023-11-28 03:14:20,802][87426] Updated weights for policy 1, policy_version 115370 (0.0012) -[2023-11-28 03:14:21,174][87426] Updated weights for policy 1, policy_version 115380 (0.0012) -[2023-11-28 03:14:21,432][87424] Updated weights for policy 0, policy_version 115586 (0.0009) -[2023-11-28 03:14:21,547][87426] Updated weights for policy 1, policy_version 115390 (0.0010) -[2023-11-28 03:14:21,812][87424] Updated weights for policy 0, policy_version 115596 (0.0011) -[2023-11-28 03:14:22,200][87424] Updated weights for policy 0, policy_version 115606 (0.0010) -[2023-11-28 03:14:22,575][87424] Updated weights for policy 0, policy_version 115616 (0.0010) -[2023-11-28 03:14:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 59138048. Throughput: 0: 2747.9, 1: 2667.0. Samples: 59156268. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:14:23,445][86177] Avg episode reward: [(0, '-522.970'), (1, '-569.710')] -[2023-11-28 03:14:23,700][87426] Updated weights for policy 1, policy_version 115400 (0.0011) -[2023-11-28 03:14:24,070][87426] Updated weights for policy 1, policy_version 115410 (0.0012) -[2023-11-28 03:14:24,455][87426] Updated weights for policy 1, policy_version 115420 (0.0011) -[2023-11-28 03:14:25,034][87424] Updated weights for policy 0, policy_version 115626 (0.0012) -[2023-11-28 03:14:25,416][87424] Updated weights for policy 0, policy_version 115636 (0.0011) -[2023-11-28 03:14:25,797][87424] Updated weights for policy 0, policy_version 115646 (0.0012) -[2023-11-28 03:14:26,331][87426] Updated weights for policy 1, policy_version 115430 (0.0010) -[2023-11-28 03:14:26,707][87426] Updated weights for policy 1, policy_version 115440 (0.0012) -[2023-11-28 03:14:27,087][87426] Updated weights for policy 1, policy_version 115450 (0.0011) -[2023-11-28 03:14:27,776][87424] Updated weights for policy 0, policy_version 115656 (0.0012) -[2023-11-28 03:14:28,162][87424] Updated weights for policy 0, policy_version 115666 (0.0012) -[2023-11-28 03:14:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 59162624. Throughput: 0: 2727.1, 1: 2739.6. Samples: 59182072. Policy #0 lag: (min: 38.0, avg: 58.9, max: 79.0) -[2023-11-28 03:14:28,445][86177] Avg episode reward: [(0, '-520.760'), (1, '-568.430')] -[2023-11-28 03:14:28,548][87424] Updated weights for policy 0, policy_version 115676 (0.0011) -[2023-11-28 03:14:28,950][87426] Updated weights for policy 1, policy_version 115460 (0.0011) -[2023-11-28 03:14:29,328][87426] Updated weights for policy 1, policy_version 115470 (0.0011) -[2023-11-28 03:14:29,708][87426] Updated weights for policy 1, policy_version 115480 (0.0009) -[2023-11-28 03:14:30,528][87424] Updated weights for policy 0, policy_version 115686 (0.0009) -[2023-11-28 03:14:30,911][87424] Updated weights for policy 0, policy_version 115696 (0.0011) -[2023-11-28 03:14:31,295][87424] Updated weights for policy 0, policy_version 115706 (0.0007) -[2023-11-28 03:14:31,695][87426] Updated weights for policy 1, policy_version 115490 (0.0009) -[2023-11-28 03:14:32,073][87426] Updated weights for policy 1, policy_version 115500 (0.0010) -[2023-11-28 03:14:32,461][87426] Updated weights for policy 1, policy_version 115510 (0.0011) -[2023-11-28 03:14:32,833][87426] Updated weights for policy 1, policy_version 115520 (0.0012) -[2023-11-28 03:14:33,342][87424] Updated weights for policy 0, policy_version 115716 (0.0008) -[2023-11-28 03:14:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 59195392. Throughput: 0: 2717.8, 1: 2756.8. Samples: 59206616. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:14:33,445][86177] Avg episode reward: [(0, '-506.930'), (1, '-563.380')] -[2023-11-28 03:14:33,727][87424] Updated weights for policy 0, policy_version 115726 (0.0008) -[2023-11-28 03:14:34,117][87424] Updated weights for policy 0, policy_version 115736 (0.0008) -[2023-11-28 03:14:34,554][87426] Updated weights for policy 1, policy_version 115530 (0.0009) -[2023-11-28 03:14:34,928][87426] Updated weights for policy 1, policy_version 115540 (0.0012) -[2023-11-28 03:14:35,306][87426] Updated weights for policy 1, policy_version 115550 (0.0010) -[2023-11-28 03:14:36,393][87424] Updated weights for policy 0, policy_version 115746 (0.0008) -[2023-11-28 03:14:36,773][87424] Updated weights for policy 0, policy_version 115756 (0.0012) -[2023-11-28 03:14:37,146][87424] Updated weights for policy 0, policy_version 115766 (0.0012) -[2023-11-28 03:14:37,535][87424] Updated weights for policy 0, policy_version 115776 (0.0012) -[2023-11-28 03:14:37,767][87426] Updated weights for policy 1, policy_version 115560 (0.0011) -[2023-11-28 03:14:38,143][87426] Updated weights for policy 1, policy_version 115570 (0.0012) -[2023-11-28 03:14:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 59219968. Throughput: 0: 2741.5, 1: 2770.0. Samples: 59239716. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:14:38,445][86177] Avg episode reward: [(0, '-509.680'), (1, '-563.430')] -[2023-11-28 03:14:38,518][87426] Updated weights for policy 1, policy_version 115580 (0.0011) -[2023-11-28 03:14:39,642][87424] Updated weights for policy 0, policy_version 115786 (0.0011) -[2023-11-28 03:14:40,022][87424] Updated weights for policy 0, policy_version 115796 (0.0011) -[2023-11-28 03:14:40,405][87424] Updated weights for policy 0, policy_version 115806 (0.0011) -[2023-11-28 03:14:40,953][87426] Updated weights for policy 1, policy_version 115590 (0.0011) -[2023-11-28 03:14:41,328][87426] Updated weights for policy 1, policy_version 115600 (0.0012) -[2023-11-28 03:14:41,712][87426] Updated weights for policy 1, policy_version 115610 (0.0009) -[2023-11-28 03:14:42,794][87424] Updated weights for policy 0, policy_version 115816 (0.0011) -[2023-11-28 03:14:43,176][87424] Updated weights for policy 0, policy_version 115826 (0.0009) -[2023-11-28 03:14:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 59244544. Throughput: 0: 2728.4, 1: 2750.0. Samples: 59262300. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:14:43,445][86177] Avg episode reward: [(0, '-499.710'), (1, '-559.550')] -[2023-11-28 03:14:43,555][87424] Updated weights for policy 0, policy_version 115836 (0.0008) -[2023-11-28 03:14:44,268][87426] Updated weights for policy 1, policy_version 115620 (0.0012) -[2023-11-28 03:14:44,652][87426] Updated weights for policy 1, policy_version 115630 (0.0012) -[2023-11-28 03:14:45,031][87426] Updated weights for policy 1, policy_version 115640 (0.0012) -[2023-11-28 03:14:45,957][87424] Updated weights for policy 0, policy_version 115846 (0.0010) -[2023-11-28 03:14:46,340][87424] Updated weights for policy 0, policy_version 115856 (0.0012) -[2023-11-28 03:14:46,724][87424] Updated weights for policy 0, policy_version 115866 (0.0012) -[2023-11-28 03:14:47,401][87426] Updated weights for policy 1, policy_version 115650 (0.0011) -[2023-11-28 03:14:47,782][87426] Updated weights for policy 1, policy_version 115660 (0.0007) -[2023-11-28 03:14:48,164][87426] Updated weights for policy 1, policy_version 115670 (0.0007) -[2023-11-28 03:14:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 59269120. Throughput: 0: 2723.4, 1: 2738.4. Samples: 59286004. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:14:48,445][86177] Avg episode reward: [(0, '-500.630'), (1, '-562.240')] -[2023-11-28 03:14:48,538][87426] Updated weights for policy 1, policy_version 115680 (0.0008) -[2023-11-28 03:14:48,942][87424] Updated weights for policy 0, policy_version 115876 (0.0012) -[2023-11-28 03:14:49,332][87424] Updated weights for policy 0, policy_version 115886 (0.0009) -[2023-11-28 03:14:49,706][87424] Updated weights for policy 0, policy_version 115896 (0.0008) -[2023-11-28 03:14:50,261][87426] Updated weights for policy 1, policy_version 115690 (0.0008) -[2023-11-28 03:14:50,644][87426] Updated weights for policy 1, policy_version 115700 (0.0008) -[2023-11-28 03:14:51,015][87426] Updated weights for policy 1, policy_version 115710 (0.0008) -[2023-11-28 03:14:52,074][87424] Updated weights for policy 0, policy_version 115906 (0.0010) -[2023-11-28 03:14:52,446][87424] Updated weights for policy 0, policy_version 115916 (0.0012) -[2023-11-28 03:14:52,824][87424] Updated weights for policy 0, policy_version 115926 (0.0011) -[2023-11-28 03:14:53,217][87424] Updated weights for policy 0, policy_version 115936 (0.0009) -[2023-11-28 03:14:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 59301888. Throughput: 0: 2708.1, 1: 2742.9. Samples: 59318636. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:14:53,445][86177] Avg episode reward: [(0, '-499.230'), (1, '-509.360')] -[2023-11-28 03:14:53,505][87426] Updated weights for policy 1, policy_version 115720 (0.0011) -[2023-11-28 03:14:53,893][87426] Updated weights for policy 1, policy_version 115730 (0.0011) -[2023-11-28 03:14:54,267][87426] Updated weights for policy 1, policy_version 115740 (0.0011) -[2023-11-28 03:14:55,262][87424] Updated weights for policy 0, policy_version 115946 (0.0008) -[2023-11-28 03:14:55,644][87424] Updated weights for policy 0, policy_version 115956 (0.0009) -[2023-11-28 03:14:56,018][87426] Updated weights for policy 1, policy_version 115750 (0.0010) -[2023-11-28 03:14:56,027][87424] Updated weights for policy 0, policy_version 115966 (0.0007) -[2023-11-28 03:14:56,397][87426] Updated weights for policy 1, policy_version 115760 (0.0011) -[2023-11-28 03:14:56,779][87426] Updated weights for policy 1, policy_version 115770 (0.0007) -[2023-11-28 03:14:57,722][87424] Updated weights for policy 0, policy_version 115976 (0.0010) -[2023-11-28 03:14:58,098][87424] Updated weights for policy 0, policy_version 115986 (0.0011) -[2023-11-28 03:14:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 59326464. Throughput: 0: 2702.7, 1: 2763.3. Samples: 59343664. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:14:58,445][86177] Avg episode reward: [(0, '-503.610'), (1, '-507.350')] -[2023-11-28 03:14:58,478][87424] Updated weights for policy 0, policy_version 115996 (0.0011) -[2023-11-28 03:14:59,027][87426] Updated weights for policy 1, policy_version 115780 (0.0007) -[2023-11-28 03:14:59,406][87426] Updated weights for policy 1, policy_version 115790 (0.0008) -[2023-11-28 03:14:59,787][87426] Updated weights for policy 1, policy_version 115800 (0.0008) -[2023-11-28 03:15:00,636][87424] Updated weights for policy 0, policy_version 116006 (0.0011) -[2023-11-28 03:15:01,015][87424] Updated weights for policy 0, policy_version 116016 (0.0012) -[2023-11-28 03:15:01,397][87424] Updated weights for policy 0, policy_version 116026 (0.0011) -[2023-11-28 03:15:01,806][87426] Updated weights for policy 1, policy_version 115810 (0.0008) -[2023-11-28 03:15:02,187][87426] Updated weights for policy 1, policy_version 115820 (0.0010) -[2023-11-28 03:15:02,566][87426] Updated weights for policy 1, policy_version 115830 (0.0012) -[2023-11-28 03:15:02,944][87426] Updated weights for policy 1, policy_version 115840 (0.0011) -[2023-11-28 03:15:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 59359232. Throughput: 0: 2686.9, 1: 2763.8. Samples: 59368008. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:15:03,445][86177] Avg episode reward: [(0, '-503.350'), (1, '-514.190')] -[2023-11-28 03:15:03,753][87424] Updated weights for policy 0, policy_version 116036 (0.0011) -[2023-11-28 03:15:04,134][87424] Updated weights for policy 0, policy_version 116046 (0.0012) -[2023-11-28 03:15:04,518][87424] Updated weights for policy 0, policy_version 116056 (0.0012) -[2023-11-28 03:15:05,202][87426] Updated weights for policy 1, policy_version 115850 (0.0012) -[2023-11-28 03:15:05,583][87426] Updated weights for policy 1, policy_version 115860 (0.0012) -[2023-11-28 03:15:05,954][87426] Updated weights for policy 1, policy_version 115870 (0.0012) -[2023-11-28 03:15:06,835][87424] Updated weights for policy 0, policy_version 116066 (0.0011) -[2023-11-28 03:15:07,227][87424] Updated weights for policy 0, policy_version 116076 (0.0011) -[2023-11-28 03:15:07,603][87424] Updated weights for policy 0, policy_version 116086 (0.0011) -[2023-11-28 03:15:07,890][87426] Updated weights for policy 1, policy_version 115880 (0.0012) -[2023-11-28 03:15:07,989][87424] Updated weights for policy 0, policy_version 116096 (0.0010) -[2023-11-28 03:15:08,274][87426] Updated weights for policy 1, policy_version 115890 (0.0011) -[2023-11-28 03:15:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 59383808. Throughput: 0: 2687.4, 1: 2752.4. Samples: 59401060. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:15:08,445][86177] Avg episode reward: [(0, '-501.900'), (1, '-512.000')] -[2023-11-28 03:15:08,653][87426] Updated weights for policy 1, policy_version 115900 (0.0012) -[2023-11-28 03:15:09,906][87424] Updated weights for policy 0, policy_version 116106 (0.0012) -[2023-11-28 03:15:10,279][87424] Updated weights for policy 0, policy_version 116116 (0.0012) -[2023-11-28 03:15:10,665][87424] Updated weights for policy 0, policy_version 116126 (0.0012) -[2023-11-28 03:15:10,667][87426] Updated weights for policy 1, policy_version 115910 (0.0012) -[2023-11-28 03:15:11,042][87426] Updated weights for policy 1, policy_version 115920 (0.0012) -[2023-11-28 03:15:11,428][87426] Updated weights for policy 1, policy_version 115930 (0.0012) -[2023-11-28 03:15:13,344][87424] Updated weights for policy 0, policy_version 116136 (0.0012) -[2023-11-28 03:15:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 59408384. Throughput: 0: 2683.8, 1: 2719.3. Samples: 59425212. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:15:13,445][86177] Avg episode reward: [(0, '-501.930'), (1, '-565.900')] -[2023-11-28 03:15:13,609][87426] Updated weights for policy 1, policy_version 115940 (0.0012) -[2023-11-28 03:15:13,719][87424] Updated weights for policy 0, policy_version 116146 (0.0010) -[2023-11-28 03:15:13,982][87426] Updated weights for policy 1, policy_version 115950 (0.0012) -[2023-11-28 03:15:14,097][87424] Updated weights for policy 0, policy_version 116156 (0.0011) -[2023-11-28 03:15:14,355][87426] Updated weights for policy 1, policy_version 115960 (0.0008) -[2023-11-28 03:15:16,563][87424] Updated weights for policy 0, policy_version 116166 (0.0011) -[2023-11-28 03:15:16,942][87424] Updated weights for policy 0, policy_version 116176 (0.0008) -[2023-11-28 03:15:16,945][87426] Updated weights for policy 1, policy_version 115970 (0.0008) -[2023-11-28 03:15:17,317][87426] Updated weights for policy 1, policy_version 115980 (0.0009) -[2023-11-28 03:15:17,323][87424] Updated weights for policy 0, policy_version 116186 (0.0007) -[2023-11-28 03:15:17,698][87426] Updated weights for policy 1, policy_version 115990 (0.0007) -[2023-11-28 03:15:18,085][87426] Updated weights for policy 1, policy_version 116000 (0.0011) -[2023-11-28 03:15:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 59441152. Throughput: 0: 2687.7, 1: 2690.7. Samples: 59448644. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:15:18,445][86177] Avg episode reward: [(0, '-495.180'), (1, '-564.680')] -[2023-11-28 03:15:19,373][87424] Updated weights for policy 0, policy_version 116196 (0.0009) -[2023-11-28 03:15:19,757][87424] Updated weights for policy 0, policy_version 116206 (0.0012) -[2023-11-28 03:15:20,133][87424] Updated weights for policy 0, policy_version 116216 (0.0012) -[2023-11-28 03:15:20,326][87426] Updated weights for policy 1, policy_version 116010 (0.0011) -[2023-11-28 03:15:20,713][87426] Updated weights for policy 1, policy_version 116020 (0.0011) -[2023-11-28 03:15:21,092][87426] Updated weights for policy 1, policy_version 116030 (0.0012) -[2023-11-28 03:15:22,242][87424] Updated weights for policy 0, policy_version 116226 (0.0012) -[2023-11-28 03:15:22,624][87424] Updated weights for policy 0, policy_version 116236 (0.0012) -[2023-11-28 03:15:22,995][87424] Updated weights for policy 0, policy_version 116246 (0.0012) -[2023-11-28 03:15:23,371][87424] Updated weights for policy 0, policy_version 116256 (0.0009) -[2023-11-28 03:15:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 59465728. Throughput: 0: 2683.2, 1: 2651.1. Samples: 59479760. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:15:23,445][86177] Avg episode reward: [(0, '-498.590'), (1, '-569.920')] -[2023-11-28 03:15:23,525][87426] Updated weights for policy 1, policy_version 116040 (0.0012) -[2023-11-28 03:15:23,907][87426] Updated weights for policy 1, policy_version 116050 (0.0011) -[2023-11-28 03:15:24,287][87426] Updated weights for policy 1, policy_version 116060 (0.0008) -[2023-11-28 03:15:25,797][87424] Updated weights for policy 0, policy_version 116266 (0.0012) -[2023-11-28 03:15:26,164][87424] Updated weights for policy 0, policy_version 116276 (0.0011) -[2023-11-28 03:15:26,546][87424] Updated weights for policy 0, policy_version 116286 (0.0011) -[2023-11-28 03:15:26,754][87426] Updated weights for policy 1, policy_version 116070 (0.0008) -[2023-11-28 03:15:27,135][87426] Updated weights for policy 1, policy_version 116080 (0.0012) -[2023-11-28 03:15:27,518][87426] Updated weights for policy 1, policy_version 116090 (0.0012) -[2023-11-28 03:15:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 59490304. Throughput: 0: 2696.3, 1: 2688.3. Samples: 59504608. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:15:28,445][86177] Avg episode reward: [(0, '-504.030'), (1, '-570.550')] -[2023-11-28 03:15:28,924][87424] Updated weights for policy 0, policy_version 116296 (0.0012) -[2023-11-28 03:15:29,302][87424] Updated weights for policy 0, policy_version 116306 (0.0012) -[2023-11-28 03:15:29,407][87426] Updated weights for policy 1, policy_version 116100 (0.0012) -[2023-11-28 03:15:29,686][87424] Updated weights for policy 0, policy_version 116316 (0.0011) -[2023-11-28 03:15:29,791][87426] Updated weights for policy 1, policy_version 116110 (0.0010) -[2023-11-28 03:15:30,167][87426] Updated weights for policy 1, policy_version 116120 (0.0008) -[2023-11-28 03:15:31,798][87424] Updated weights for policy 0, policy_version 116326 (0.0010) -[2023-11-28 03:15:32,176][87424] Updated weights for policy 0, policy_version 116336 (0.0009) -[2023-11-28 03:15:32,494][87426] Updated weights for policy 1, policy_version 116130 (0.0010) -[2023-11-28 03:15:32,551][87424] Updated weights for policy 0, policy_version 116346 (0.0008) -[2023-11-28 03:15:32,873][87426] Updated weights for policy 1, policy_version 116140 (0.0008) -[2023-11-28 03:15:33,260][87426] Updated weights for policy 1, policy_version 116150 (0.0008) -[2023-11-28 03:15:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 59514880. Throughput: 0: 2702.1, 1: 2716.1. Samples: 59529820. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 03:15:33,445][86177] Avg episode reward: [(0, '-511.300'), (1, '-554.220')] -[2023-11-28 03:15:33,640][87426] Updated weights for policy 1, policy_version 116160 (0.0007) -[2023-11-28 03:15:34,737][87424] Updated weights for policy 0, policy_version 116356 (0.0008) -[2023-11-28 03:15:35,123][87424] Updated weights for policy 0, policy_version 116366 (0.0008) -[2023-11-28 03:15:35,513][87424] Updated weights for policy 0, policy_version 116376 (0.0010) -[2023-11-28 03:15:35,781][87426] Updated weights for policy 1, policy_version 116170 (0.0009) -[2023-11-28 03:15:36,157][87426] Updated weights for policy 1, policy_version 116180 (0.0007) -[2023-11-28 03:15:36,546][87426] Updated weights for policy 1, policy_version 116190 (0.0007) -[2023-11-28 03:15:37,331][87424] Updated weights for policy 0, policy_version 116386 (0.0010) -[2023-11-28 03:15:37,717][87424] Updated weights for policy 0, policy_version 116396 (0.0011) -[2023-11-28 03:15:38,103][87424] Updated weights for policy 0, policy_version 116406 (0.0011) -[2023-11-28 03:15:38,290][87426] Updated weights for policy 1, policy_version 116200 (0.0011) -[2023-11-28 03:15:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 59539456. Throughput: 0: 2716.5, 1: 2722.0. Samples: 59563368. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:15:38,445][86177] Avg episode reward: [(0, '-510.360'), (1, '-542.350')] -[2023-11-28 03:15:38,489][87424] Updated weights for policy 0, policy_version 116416 (0.0008) -[2023-11-28 03:15:38,667][87426] Updated weights for policy 1, policy_version 116210 (0.0011) -[2023-11-28 03:15:39,049][87426] Updated weights for policy 1, policy_version 116220 (0.0012) -[2023-11-28 03:15:40,933][87424] Updated weights for policy 0, policy_version 116426 (0.0008) -[2023-11-28 03:15:41,211][87426] Updated weights for policy 1, policy_version 116230 (0.0011) -[2023-11-28 03:15:41,313][87424] Updated weights for policy 0, policy_version 116436 (0.0008) -[2023-11-28 03:15:41,597][87426] Updated weights for policy 1, policy_version 116240 (0.0009) -[2023-11-28 03:15:41,713][87424] Updated weights for policy 0, policy_version 116446 (0.0008) -[2023-11-28 03:15:41,978][87426] Updated weights for policy 1, policy_version 116250 (0.0011) -[2023-11-28 03:15:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 59572224. Throughput: 0: 2720.4, 1: 2698.3. Samples: 59587508. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:15:43,445][86177] Avg episode reward: [(0, '-508.560'), (1, '-530.840')] -[2023-11-28 03:15:43,723][87424] Updated weights for policy 0, policy_version 116456 (0.0012) -[2023-11-28 03:15:44,103][87424] Updated weights for policy 0, policy_version 116466 (0.0012) -[2023-11-28 03:15:44,368][87426] Updated weights for policy 1, policy_version 116260 (0.0009) -[2023-11-28 03:15:44,496][87424] Updated weights for policy 0, policy_version 116476 (0.0012) -[2023-11-28 03:15:44,740][87426] Updated weights for policy 1, policy_version 116270 (0.0011) -[2023-11-28 03:15:45,121][87426] Updated weights for policy 1, policy_version 116280 (0.0009) -[2023-11-28 03:15:46,215][87424] Updated weights for policy 0, policy_version 116486 (0.0009) -[2023-11-28 03:15:46,594][87424] Updated weights for policy 0, policy_version 116496 (0.0008) -[2023-11-28 03:15:46,967][87424] Updated weights for policy 0, policy_version 116506 (0.0007) -[2023-11-28 03:15:47,057][87426] Updated weights for policy 1, policy_version 116290 (0.0010) -[2023-11-28 03:15:47,446][87426] Updated weights for policy 1, policy_version 116300 (0.0008) -[2023-11-28 03:15:47,819][87426] Updated weights for policy 1, policy_version 116310 (0.0007) -[2023-11-28 03:15:48,199][87426] Updated weights for policy 1, policy_version 116320 (0.0007) -[2023-11-28 03:15:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 59604992. Throughput: 0: 2733.5, 1: 2686.6. Samples: 59611912. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:15:48,445][86177] Avg episode reward: [(0, '-502.360'), (1, '-555.820')] -[2023-11-28 03:15:49,258][87424] Updated weights for policy 0, policy_version 116516 (0.0008) -[2023-11-28 03:15:49,646][87424] Updated weights for policy 0, policy_version 116526 (0.0008) -[2023-11-28 03:15:50,023][87424] Updated weights for policy 0, policy_version 116536 (0.0011) -[2023-11-28 03:15:50,491][87426] Updated weights for policy 1, policy_version 116330 (0.0011) -[2023-11-28 03:15:50,872][87426] Updated weights for policy 1, policy_version 116340 (0.0008) -[2023-11-28 03:15:51,263][87426] Updated weights for policy 1, policy_version 116350 (0.0008) -[2023-11-28 03:15:52,637][87424] Updated weights for policy 0, policy_version 116546 (0.0012) -[2023-11-28 03:15:53,021][87424] Updated weights for policy 0, policy_version 116556 (0.0012) -[2023-11-28 03:15:53,382][87426] Updated weights for policy 1, policy_version 116360 (0.0010) -[2023-11-28 03:15:53,401][87424] Updated weights for policy 0, policy_version 116566 (0.0011) -[2023-11-28 03:15:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 59621376. Throughput: 0: 2708.8, 1: 2686.6. Samples: 59643852. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:15:53,445][86177] Avg episode reward: [(0, '-499.250'), (1, '-569.640')] -[2023-11-28 03:15:53,752][87426] Updated weights for policy 1, policy_version 116370 (0.0011) -[2023-11-28 03:15:53,780][87424] Updated weights for policy 0, policy_version 116576 (0.0011) -[2023-11-28 03:15:54,134][87426] Updated weights for policy 1, policy_version 116380 (0.0012) -[2023-11-28 03:15:55,601][87424] Updated weights for policy 0, policy_version 116586 (0.0011) -[2023-11-28 03:15:55,984][87424] Updated weights for policy 0, policy_version 116596 (0.0008) -[2023-11-28 03:15:56,359][87424] Updated weights for policy 0, policy_version 116606 (0.0008) -[2023-11-28 03:15:56,598][87426] Updated weights for policy 1, policy_version 116390 (0.0010) -[2023-11-28 03:15:56,972][87426] Updated weights for policy 1, policy_version 116400 (0.0007) -[2023-11-28 03:15:57,352][87426] Updated weights for policy 1, policy_version 116410 (0.0007) -[2023-11-28 03:15:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 59654144. Throughput: 0: 2723.2, 1: 2672.4. Samples: 59668012. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:15:58,445][86177] Avg episode reward: [(0, '-501.750'), (1, '-603.330')] -[2023-11-28 03:15:58,678][87424] Updated weights for policy 0, policy_version 116616 (0.0011) -[2023-11-28 03:15:59,070][87424] Updated weights for policy 0, policy_version 116626 (0.0010) -[2023-11-28 03:15:59,215][87426] Updated weights for policy 1, policy_version 116420 (0.0008) -[2023-11-28 03:15:59,454][87424] Updated weights for policy 0, policy_version 116636 (0.0007) -[2023-11-28 03:15:59,588][87426] Updated weights for policy 1, policy_version 116430 (0.0010) -[2023-11-28 03:15:59,974][87426] Updated weights for policy 1, policy_version 116440 (0.0012) -[2023-11-28 03:16:01,723][87424] Updated weights for policy 0, policy_version 116646 (0.0008) -[2023-11-28 03:16:02,109][87424] Updated weights for policy 0, policy_version 116656 (0.0013) -[2023-11-28 03:16:02,267][87426] Updated weights for policy 1, policy_version 116450 (0.0012) -[2023-11-28 03:16:02,482][87424] Updated weights for policy 0, policy_version 116666 (0.0010) -[2023-11-28 03:16:02,636][87426] Updated weights for policy 1, policy_version 116460 (0.0012) -[2023-11-28 03:16:03,015][87426] Updated weights for policy 1, policy_version 116470 (0.0011) -[2023-11-28 03:16:03,394][87426] Updated weights for policy 1, policy_version 116480 (0.0012) -[2023-11-28 03:16:03,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 59686912. Throughput: 0: 2718.1, 1: 2683.4. Samples: 59691712. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:16:03,445][86177] Avg episode reward: [(0, '-499.550'), (1, '-603.600')] -[2023-11-28 03:16:04,349][87424] Updated weights for policy 0, policy_version 116676 (0.0009) -[2023-11-28 03:16:04,725][87424] Updated weights for policy 0, policy_version 116686 (0.0011) -[2023-11-28 03:16:05,107][87424] Updated weights for policy 0, policy_version 116696 (0.0009) -[2023-11-28 03:16:05,563][87426] Updated weights for policy 1, policy_version 116490 (0.0009) -[2023-11-28 03:16:05,947][87426] Updated weights for policy 1, policy_version 116500 (0.0011) -[2023-11-28 03:16:06,333][87426] Updated weights for policy 1, policy_version 116510 (0.0012) -[2023-11-28 03:16:07,476][87424] Updated weights for policy 0, policy_version 116706 (0.0010) -[2023-11-28 03:16:07,856][87424] Updated weights for policy 0, policy_version 116716 (0.0007) -[2023-11-28 03:16:08,248][87424] Updated weights for policy 0, policy_version 116726 (0.0007) -[2023-11-28 03:16:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 59703296. Throughput: 0: 2738.8, 1: 2715.7. Samples: 59725216. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:16:08,445][86177] Avg episode reward: [(0, '-499.360'), (1, '-576.980')] -[2023-11-28 03:16:08,638][87424] Updated weights for policy 0, policy_version 116736 (0.0008) -[2023-11-28 03:16:08,672][87426] Updated weights for policy 1, policy_version 116520 (0.0011) -[2023-11-28 03:16:09,047][87426] Updated weights for policy 1, policy_version 116530 (0.0012) -[2023-11-28 03:16:09,422][87426] Updated weights for policy 1, policy_version 116540 (0.0012) -[2023-11-28 03:16:10,866][87424] Updated weights for policy 0, policy_version 116746 (0.0012) -[2023-11-28 03:16:11,242][87424] Updated weights for policy 0, policy_version 116756 (0.0012) -[2023-11-28 03:16:11,527][87426] Updated weights for policy 1, policy_version 116550 (0.0011) -[2023-11-28 03:16:11,625][87424] Updated weights for policy 0, policy_version 116766 (0.0011) -[2023-11-28 03:16:11,904][87426] Updated weights for policy 1, policy_version 116560 (0.0012) -[2023-11-28 03:16:12,292][87426] Updated weights for policy 1, policy_version 116570 (0.0011) -[2023-11-28 03:16:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 59736064. Throughput: 0: 2722.8, 1: 2724.1. Samples: 59749716. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:16:13,445][86177] Avg episode reward: [(0, '-503.920'), (1, '-542.560')] -[2023-11-28 03:16:14,059][87424] Updated weights for policy 0, policy_version 116776 (0.0012) -[2023-11-28 03:16:14,351][87426] Updated weights for policy 1, policy_version 116580 (0.0011) -[2023-11-28 03:16:14,439][87424] Updated weights for policy 0, policy_version 116786 (0.0012) -[2023-11-28 03:16:14,728][87426] Updated weights for policy 1, policy_version 116590 (0.0010) -[2023-11-28 03:16:14,821][87424] Updated weights for policy 0, policy_version 116796 (0.0008) -[2023-11-28 03:16:15,113][87426] Updated weights for policy 1, policy_version 116600 (0.0009) -[2023-11-28 03:16:17,233][87424] Updated weights for policy 0, policy_version 116806 (0.0007) -[2023-11-28 03:16:17,533][87426] Updated weights for policy 1, policy_version 116610 (0.0009) -[2023-11-28 03:16:17,614][87424] Updated weights for policy 0, policy_version 116816 (0.0008) -[2023-11-28 03:16:17,906][87426] Updated weights for policy 1, policy_version 116620 (0.0007) -[2023-11-28 03:16:17,994][87424] Updated weights for policy 0, policy_version 116826 (0.0010) -[2023-11-28 03:16:18,288][87426] Updated weights for policy 1, policy_version 116630 (0.0007) -[2023-11-28 03:16:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 59760640. Throughput: 0: 2704.5, 1: 2715.9. Samples: 59773740. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:16:18,445][86177] Avg episode reward: [(0, '-507.970'), (1, '-507.030')] -[2023-11-28 03:16:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000116832_29908992.pth... -[2023-11-28 03:16:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000114304_29261824.pth -[2023-11-28 03:16:18,670][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000116640_29859840.pth... -[2023-11-28 03:16:18,672][87426] Updated weights for policy 1, policy_version 116640 (0.0009) -[2023-11-28 03:16:18,710][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000114080_29204480.pth -[2023-11-28 03:16:20,468][87424] Updated weights for policy 0, policy_version 116836 (0.0009) -[2023-11-28 03:16:20,711][87426] Updated weights for policy 1, policy_version 116650 (0.0011) -[2023-11-28 03:16:20,858][87424] Updated weights for policy 0, policy_version 116846 (0.0012) -[2023-11-28 03:16:21,084][87426] Updated weights for policy 1, policy_version 116660 (0.0008) -[2023-11-28 03:16:21,235][87424] Updated weights for policy 0, policy_version 116856 (0.0009) -[2023-11-28 03:16:21,462][87426] Updated weights for policy 1, policy_version 116670 (0.0012) -[2023-11-28 03:16:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 59785216. Throughput: 0: 2667.5, 1: 2713.2. Samples: 59805496. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:16:23,445][86177] Avg episode reward: [(0, '-513.560'), (1, '-550.270')] -[2023-11-28 03:16:23,556][87424] Updated weights for policy 0, policy_version 116866 (0.0008) -[2023-11-28 03:16:23,946][87424] Updated weights for policy 0, policy_version 116876 (0.0007) -[2023-11-28 03:16:24,065][87426] Updated weights for policy 1, policy_version 116680 (0.0011) -[2023-11-28 03:16:24,318][87424] Updated weights for policy 0, policy_version 116886 (0.0012) -[2023-11-28 03:16:24,435][87426] Updated weights for policy 1, policy_version 116690 (0.0011) -[2023-11-28 03:16:24,701][87424] Updated weights for policy 0, policy_version 116896 (0.0012) -[2023-11-28 03:16:24,813][87426] Updated weights for policy 1, policy_version 116700 (0.0011) -[2023-11-28 03:16:26,406][87424] Updated weights for policy 0, policy_version 116906 (0.0011) -[2023-11-28 03:16:26,695][87426] Updated weights for policy 1, policy_version 116710 (0.0012) -[2023-11-28 03:16:26,789][87424] Updated weights for policy 0, policy_version 116916 (0.0011) -[2023-11-28 03:16:27,084][87426] Updated weights for policy 1, policy_version 116720 (0.0011) -[2023-11-28 03:16:27,168][87424] Updated weights for policy 0, policy_version 116926 (0.0011) -[2023-11-28 03:16:27,451][87426] Updated weights for policy 1, policy_version 116730 (0.0012) -[2023-11-28 03:16:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 59817984. Throughput: 0: 2669.2, 1: 2732.1. Samples: 59830568. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:16:28,445][86177] Avg episode reward: [(0, '-521.460'), (1, '-552.430')] -[2023-11-28 03:16:29,242][87426] Updated weights for policy 1, policy_version 116740 (0.0012) -[2023-11-28 03:16:29,611][87426] Updated weights for policy 1, policy_version 116750 (0.0011) -[2023-11-28 03:16:29,679][87424] Updated weights for policy 0, policy_version 116936 (0.0011) -[2023-11-28 03:16:30,002][87426] Updated weights for policy 1, policy_version 116760 (0.0012) -[2023-11-28 03:16:30,071][87424] Updated weights for policy 0, policy_version 116946 (0.0011) -[2023-11-28 03:16:30,446][87424] Updated weights for policy 0, policy_version 116956 (0.0012) -[2023-11-28 03:16:31,904][87426] Updated weights for policy 1, policy_version 116770 (0.0011) -[2023-11-28 03:16:32,279][87426] Updated weights for policy 1, policy_version 116780 (0.0011) -[2023-11-28 03:16:32,370][87424] Updated weights for policy 0, policy_version 116966 (0.0011) -[2023-11-28 03:16:32,661][87426] Updated weights for policy 1, policy_version 116790 (0.0012) -[2023-11-28 03:16:32,752][87424] Updated weights for policy 0, policy_version 116976 (0.0008) -[2023-11-28 03:16:33,038][87426] Updated weights for policy 1, policy_version 116800 (0.0011) -[2023-11-28 03:16:33,132][87424] Updated weights for policy 0, policy_version 116986 (0.0011) -[2023-11-28 03:16:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 59850752. Throughput: 0: 2685.2, 1: 2745.2. Samples: 59856284. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:16:33,445][86177] Avg episode reward: [(0, '-555.530'), (1, '-555.620')] -[2023-11-28 03:16:34,941][87424] Updated weights for policy 0, policy_version 116996 (0.0012) -[2023-11-28 03:16:35,159][87426] Updated weights for policy 1, policy_version 116810 (0.0011) -[2023-11-28 03:16:35,325][87424] Updated weights for policy 0, policy_version 117006 (0.0012) -[2023-11-28 03:16:35,538][87426] Updated weights for policy 1, policy_version 116820 (0.0011) -[2023-11-28 03:16:35,704][87424] Updated weights for policy 0, policy_version 117016 (0.0009) -[2023-11-28 03:16:35,917][87426] Updated weights for policy 1, policy_version 116830 (0.0011) -[2023-11-28 03:16:37,522][87424] Updated weights for policy 0, policy_version 117026 (0.0008) -[2023-11-28 03:16:37,907][87424] Updated weights for policy 0, policy_version 117036 (0.0011) -[2023-11-28 03:16:38,286][87424] Updated weights for policy 0, policy_version 117046 (0.0012) -[2023-11-28 03:16:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 59867136. Throughput: 0: 2734.6, 1: 2727.9. Samples: 59889664. Policy #0 lag: (min: 15.0, avg: 37.3, max: 79.0) -[2023-11-28 03:16:38,445][86177] Avg episode reward: [(0, '-552.900'), (1, '-573.450')] -[2023-11-28 03:16:38,490][87426] Updated weights for policy 1, policy_version 116840 (0.0010) -[2023-11-28 03:16:38,670][87424] Updated weights for policy 0, policy_version 117056 (0.0011) -[2023-11-28 03:16:38,874][87426] Updated weights for policy 1, policy_version 116850 (0.0008) -[2023-11-28 03:16:39,246][87426] Updated weights for policy 1, policy_version 116860 (0.0009) -[2023-11-28 03:16:40,831][87424] Updated weights for policy 0, policy_version 117066 (0.0010) -[2023-11-28 03:16:41,225][87424] Updated weights for policy 0, policy_version 117076 (0.0011) -[2023-11-28 03:16:41,607][87424] Updated weights for policy 0, policy_version 117086 (0.0012) -[2023-11-28 03:16:41,887][87426] Updated weights for policy 1, policy_version 116870 (0.0009) -[2023-11-28 03:16:42,280][87426] Updated weights for policy 1, policy_version 116880 (0.0011) -[2023-11-28 03:16:42,658][87426] Updated weights for policy 1, policy_version 116890 (0.0012) -[2023-11-28 03:16:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 59899904. Throughput: 0: 2723.6, 1: 2714.0. Samples: 59912708. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:16:43,445][86177] Avg episode reward: [(0, '-547.080'), (1, '-527.000')] -[2023-11-28 03:16:43,966][87424] Updated weights for policy 0, policy_version 117096 (0.0011) -[2023-11-28 03:16:44,346][87424] Updated weights for policy 0, policy_version 117106 (0.0011) -[2023-11-28 03:16:44,537][87426] Updated weights for policy 1, policy_version 116900 (0.0011) -[2023-11-28 03:16:44,727][87424] Updated weights for policy 0, policy_version 117116 (0.0008) -[2023-11-28 03:16:44,910][87426] Updated weights for policy 1, policy_version 116910 (0.0012) -[2023-11-28 03:16:45,285][87426] Updated weights for policy 1, policy_version 116920 (0.0010) -[2023-11-28 03:16:47,269][87424] Updated weights for policy 0, policy_version 117126 (0.0008) -[2023-11-28 03:16:47,657][87424] Updated weights for policy 0, policy_version 117136 (0.0007) -[2023-11-28 03:16:47,869][87426] Updated weights for policy 1, policy_version 116930 (0.0009) -[2023-11-28 03:16:48,036][87424] Updated weights for policy 0, policy_version 117146 (0.0007) -[2023-11-28 03:16:48,249][87426] Updated weights for policy 1, policy_version 116940 (0.0010) -[2023-11-28 03:16:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 59924480. Throughput: 0: 2708.6, 1: 2726.0. Samples: 59936272. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:16:48,445][86177] Avg episode reward: [(0, '-542.250'), (1, '-528.280')] -[2023-11-28 03:16:48,625][87426] Updated weights for policy 1, policy_version 116950 (0.0009) -[2023-11-28 03:16:49,004][87426] Updated weights for policy 1, policy_version 116960 (0.0009) -[2023-11-28 03:16:50,331][87424] Updated weights for policy 0, policy_version 117156 (0.0009) -[2023-11-28 03:16:50,730][87424] Updated weights for policy 0, policy_version 117166 (0.0012) -[2023-11-28 03:16:51,123][87424] Updated weights for policy 0, policy_version 117176 (0.0011) -[2023-11-28 03:16:51,216][87426] Updated weights for policy 1, policy_version 116970 (0.0010) -[2023-11-28 03:16:51,586][87426] Updated weights for policy 1, policy_version 116980 (0.0011) -[2023-11-28 03:16:51,960][87426] Updated weights for policy 1, policy_version 116990 (0.0012) -[2023-11-28 03:16:53,198][87424] Updated weights for policy 0, policy_version 117186 (0.0010) -[2023-11-28 03:16:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 59949056. Throughput: 0: 2688.4, 1: 2702.7. Samples: 59967816. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:16:53,445][86177] Avg episode reward: [(0, '-516.480'), (1, '-526.680')] -[2023-11-28 03:16:53,574][87424] Updated weights for policy 0, policy_version 117196 (0.0011) -[2023-11-28 03:16:53,960][87424] Updated weights for policy 0, policy_version 117206 (0.0010) -[2023-11-28 03:16:54,334][87424] Updated weights for policy 0, policy_version 117216 (0.0008) -[2023-11-28 03:16:54,503][87426] Updated weights for policy 1, policy_version 117000 (0.0010) -[2023-11-28 03:16:54,885][87426] Updated weights for policy 1, policy_version 117010 (0.0012) -[2023-11-28 03:16:55,272][87426] Updated weights for policy 1, policy_version 117020 (0.0012) -[2023-11-28 03:16:56,211][87424] Updated weights for policy 0, policy_version 117226 (0.0012) -[2023-11-28 03:16:56,598][87424] Updated weights for policy 0, policy_version 117236 (0.0012) -[2023-11-28 03:16:56,971][87424] Updated weights for policy 0, policy_version 117246 (0.0012) -[2023-11-28 03:16:57,844][87426] Updated weights for policy 1, policy_version 117030 (0.0009) -[2023-11-28 03:16:58,235][87426] Updated weights for policy 1, policy_version 117040 (0.0007) -[2023-11-28 03:16:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 59973632. Throughput: 0: 2700.0, 1: 2668.1. Samples: 59991280. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:16:58,445][86177] Avg episode reward: [(0, '-511.740'), (1, '-540.180')] -[2023-11-28 03:16:58,615][87426] Updated weights for policy 1, policy_version 117050 (0.0010) -[2023-11-28 03:16:58,918][87424] Updated weights for policy 0, policy_version 117256 (0.0010) -[2023-11-28 03:16:59,307][87424] Updated weights for policy 0, policy_version 117266 (0.0007) -[2023-11-28 03:16:59,694][87424] Updated weights for policy 0, policy_version 117276 (0.0007) -[2023-11-28 03:17:01,077][87426] Updated weights for policy 1, policy_version 117060 (0.0011) -[2023-11-28 03:17:01,447][87426] Updated weights for policy 1, policy_version 117070 (0.0012) -[2023-11-28 03:17:01,824][87426] Updated weights for policy 1, policy_version 117080 (0.0011) -[2023-11-28 03:17:02,041][87424] Updated weights for policy 0, policy_version 117286 (0.0012) -[2023-11-28 03:17:02,426][87424] Updated weights for policy 0, policy_version 117296 (0.0009) -[2023-11-28 03:17:02,819][87424] Updated weights for policy 0, policy_version 117306 (0.0008) -[2023-11-28 03:17:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 60006400. Throughput: 0: 2716.2, 1: 2663.8. Samples: 60015840. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:17:03,445][86177] Avg episode reward: [(0, '-514.410'), (1, '-542.000')] -[2023-11-28 03:17:04,279][87426] Updated weights for policy 1, policy_version 117090 (0.0011) -[2023-11-28 03:17:04,654][87426] Updated weights for policy 1, policy_version 117100 (0.0012) -[2023-11-28 03:17:04,786][87424] Updated weights for policy 0, policy_version 117316 (0.0009) -[2023-11-28 03:17:05,031][87426] Updated weights for policy 1, policy_version 117110 (0.0011) -[2023-11-28 03:17:05,155][87424] Updated weights for policy 0, policy_version 117326 (0.0011) -[2023-11-28 03:17:05,414][87426] Updated weights for policy 1, policy_version 117120 (0.0011) -[2023-11-28 03:17:05,540][87424] Updated weights for policy 0, policy_version 117336 (0.0009) -[2023-11-28 03:17:07,349][87426] Updated weights for policy 1, policy_version 117130 (0.0012) -[2023-11-28 03:17:07,510][87424] Updated weights for policy 0, policy_version 117346 (0.0008) -[2023-11-28 03:17:07,725][87426] Updated weights for policy 1, policy_version 117140 (0.0012) -[2023-11-28 03:17:07,887][87424] Updated weights for policy 0, policy_version 117356 (0.0007) -[2023-11-28 03:17:08,105][87426] Updated weights for policy 1, policy_version 117150 (0.0012) -[2023-11-28 03:17:08,283][87424] Updated weights for policy 0, policy_version 117366 (0.0007) -[2023-11-28 03:17:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 60030976. Throughput: 0: 2743.5, 1: 2656.7. Samples: 60048504. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:17:08,445][86177] Avg episode reward: [(0, '-494.510'), (1, '-542.000')] -[2023-11-28 03:17:08,658][87424] Updated weights for policy 0, policy_version 117376 (0.0007) -[2023-11-28 03:17:10,089][87426] Updated weights for policy 1, policy_version 117160 (0.0010) -[2023-11-28 03:17:10,466][87426] Updated weights for policy 1, policy_version 117170 (0.0011) -[2023-11-28 03:17:10,715][87424] Updated weights for policy 0, policy_version 117386 (0.0010) -[2023-11-28 03:17:10,844][87426] Updated weights for policy 1, policy_version 117180 (0.0011) -[2023-11-28 03:17:11,102][87424] Updated weights for policy 0, policy_version 117396 (0.0010) -[2023-11-28 03:17:11,483][87424] Updated weights for policy 0, policy_version 117406 (0.0012) -[2023-11-28 03:17:13,198][87426] Updated weights for policy 1, policy_version 117190 (0.0009) -[2023-11-28 03:17:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 60055552. Throughput: 0: 2742.6, 1: 2649.2. Samples: 60073196. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:17:13,445][86177] Avg episode reward: [(0, '-499.090'), (1, '-536.530')] -[2023-11-28 03:17:13,587][87426] Updated weights for policy 1, policy_version 117200 (0.0007) -[2023-11-28 03:17:13,661][87424] Updated weights for policy 0, policy_version 117416 (0.0011) -[2023-11-28 03:17:13,952][87426] Updated weights for policy 1, policy_version 117210 (0.0011) -[2023-11-28 03:17:14,048][87424] Updated weights for policy 0, policy_version 117426 (0.0007) -[2023-11-28 03:17:14,430][87424] Updated weights for policy 0, policy_version 117436 (0.0011) -[2023-11-28 03:17:16,084][87426] Updated weights for policy 1, policy_version 117220 (0.0011) -[2023-11-28 03:17:16,479][87426] Updated weights for policy 1, policy_version 117230 (0.0012) -[2023-11-28 03:17:16,854][87426] Updated weights for policy 1, policy_version 117240 (0.0011) -[2023-11-28 03:17:16,854][87424] Updated weights for policy 0, policy_version 117446 (0.0011) -[2023-11-28 03:17:17,237][87424] Updated weights for policy 0, policy_version 117456 (0.0012) -[2023-11-28 03:17:17,603][87424] Updated weights for policy 0, policy_version 117466 (0.0010) -[2023-11-28 03:17:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 60088320. Throughput: 0: 2745.0, 1: 2631.0. Samples: 60098204. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:17:18,446][86177] Avg episode reward: [(0, '-499.700'), (1, '-537.630')] -[2023-11-28 03:17:18,832][87426] Updated weights for policy 1, policy_version 117250 (0.0011) -[2023-11-28 03:17:19,216][87426] Updated weights for policy 1, policy_version 117260 (0.0011) -[2023-11-28 03:17:19,511][87424] Updated weights for policy 0, policy_version 117476 (0.0011) -[2023-11-28 03:17:19,586][87426] Updated weights for policy 1, policy_version 117270 (0.0012) -[2023-11-28 03:17:19,891][87424] Updated weights for policy 0, policy_version 117486 (0.0011) -[2023-11-28 03:17:19,972][87426] Updated weights for policy 1, policy_version 117280 (0.0011) -[2023-11-28 03:17:20,271][87424] Updated weights for policy 0, policy_version 117496 (0.0011) -[2023-11-28 03:17:22,237][87424] Updated weights for policy 0, policy_version 117506 (0.0012) -[2023-11-28 03:17:22,533][87426] Updated weights for policy 1, policy_version 117290 (0.0009) -[2023-11-28 03:17:22,618][87424] Updated weights for policy 0, policy_version 117516 (0.0012) -[2023-11-28 03:17:22,912][87426] Updated weights for policy 1, policy_version 117300 (0.0011) -[2023-11-28 03:17:23,025][87424] Updated weights for policy 0, policy_version 117526 (0.0012) -[2023-11-28 03:17:23,281][87426] Updated weights for policy 1, policy_version 117310 (0.0011) -[2023-11-28 03:17:23,395][87424] Updated weights for policy 0, policy_version 117536 (0.0012) -[2023-11-28 03:17:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 60121088. Throughput: 0: 2717.9, 1: 2639.3. Samples: 60130736. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:17:23,445][86177] Avg episode reward: [(0, '-496.220'), (1, '-514.110')] -[2023-11-28 03:17:25,337][87426] Updated weights for policy 1, policy_version 117320 (0.0011) -[2023-11-28 03:17:25,449][87424] Updated weights for policy 0, policy_version 117546 (0.0009) -[2023-11-28 03:17:25,714][87426] Updated weights for policy 1, policy_version 117330 (0.0011) -[2023-11-28 03:17:25,826][87424] Updated weights for policy 0, policy_version 117556 (0.0007) -[2023-11-28 03:17:26,100][87426] Updated weights for policy 1, policy_version 117340 (0.0011) -[2023-11-28 03:17:26,207][87424] Updated weights for policy 0, policy_version 117566 (0.0007) -[2023-11-28 03:17:28,359][87426] Updated weights for policy 1, policy_version 117350 (0.0011) -[2023-11-28 03:17:28,419][87424] Updated weights for policy 0, policy_version 117576 (0.0010) -[2023-11-28 03:17:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 60137472. Throughput: 0: 2734.4, 1: 2681.6. Samples: 60156428. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:17:28,445][86177] Avg episode reward: [(0, '-499.200'), (1, '-514.100')] -[2023-11-28 03:17:28,733][87426] Updated weights for policy 1, policy_version 117360 (0.0008) -[2023-11-28 03:17:28,802][87424] Updated weights for policy 0, policy_version 117586 (0.0007) -[2023-11-28 03:17:29,117][87426] Updated weights for policy 1, policy_version 117370 (0.0007) -[2023-11-28 03:17:29,185][87424] Updated weights for policy 0, policy_version 117596 (0.0011) -[2023-11-28 03:17:30,924][87426] Updated weights for policy 1, policy_version 117380 (0.0009) -[2023-11-28 03:17:31,175][87424] Updated weights for policy 0, policy_version 117606 (0.0009) -[2023-11-28 03:17:31,304][87426] Updated weights for policy 1, policy_version 117390 (0.0012) -[2023-11-28 03:17:31,569][87424] Updated weights for policy 0, policy_version 117616 (0.0008) -[2023-11-28 03:17:31,682][87426] Updated weights for policy 1, policy_version 117400 (0.0011) -[2023-11-28 03:17:31,945][87424] Updated weights for policy 0, policy_version 117626 (0.0008) -[2023-11-28 03:17:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 60170240. Throughput: 0: 2754.8, 1: 2673.0. Samples: 60180524. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:17:33,445][86177] Avg episode reward: [(0, '-498.490'), (1, '-532.160')] -[2023-11-28 03:17:34,073][87426] Updated weights for policy 1, policy_version 117410 (0.0010) -[2023-11-28 03:17:34,262][87424] Updated weights for policy 0, policy_version 117636 (0.0008) -[2023-11-28 03:17:34,455][87426] Updated weights for policy 1, policy_version 117420 (0.0007) -[2023-11-28 03:17:34,661][87424] Updated weights for policy 0, policy_version 117646 (0.0008) -[2023-11-28 03:17:34,840][87426] Updated weights for policy 1, policy_version 117430 (0.0009) -[2023-11-28 03:17:35,029][87424] Updated weights for policy 0, policy_version 117656 (0.0009) -[2023-11-28 03:17:35,220][87426] Updated weights for policy 1, policy_version 117440 (0.0009) -[2023-11-28 03:17:37,285][87424] Updated weights for policy 0, policy_version 117666 (0.0011) -[2023-11-28 03:17:37,661][87426] Updated weights for policy 1, policy_version 117450 (0.0012) -[2023-11-28 03:17:37,669][87424] Updated weights for policy 0, policy_version 117676 (0.0010) -[2023-11-28 03:17:38,032][87426] Updated weights for policy 1, policy_version 117460 (0.0011) -[2023-11-28 03:17:38,050][87424] Updated weights for policy 0, policy_version 117686 (0.0008) -[2023-11-28 03:17:38,411][87426] Updated weights for policy 1, policy_version 117470 (0.0008) -[2023-11-28 03:17:38,432][87424] Updated weights for policy 0, policy_version 117696 (0.0007) -[2023-11-28 03:17:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 60194816. Throughput: 0: 2758.1, 1: 2677.4. Samples: 60212416. Policy #0 lag: (min: 31.0, avg: 45.5, max: 63.0) -[2023-11-28 03:17:38,445][86177] Avg episode reward: [(0, '-536.280'), (1, '-572.830')] -[2023-11-28 03:17:40,678][87426] Updated weights for policy 1, policy_version 117480 (0.0010) -[2023-11-28 03:17:41,043][87424] Updated weights for policy 0, policy_version 117706 (0.0010) -[2023-11-28 03:17:41,055][87426] Updated weights for policy 1, policy_version 117490 (0.0011) -[2023-11-28 03:17:41,420][87424] Updated weights for policy 0, policy_version 117716 (0.0012) -[2023-11-28 03:17:41,436][87426] Updated weights for policy 1, policy_version 117500 (0.0011) -[2023-11-28 03:17:41,807][87424] Updated weights for policy 0, policy_version 117726 (0.0012) -[2023-11-28 03:17:43,395][87426] Updated weights for policy 1, policy_version 117510 (0.0012) -[2023-11-28 03:17:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 60219392. Throughput: 0: 2737.3, 1: 2693.9. Samples: 60235684. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:17:43,445][86177] Avg episode reward: [(0, '-538.010'), (1, '-582.680')] -[2023-11-28 03:17:43,773][87426] Updated weights for policy 1, policy_version 117520 (0.0012) -[2023-11-28 03:17:44,134][87424] Updated weights for policy 0, policy_version 117736 (0.0012) -[2023-11-28 03:17:44,161][87426] Updated weights for policy 1, policy_version 117530 (0.0012) -[2023-11-28 03:17:44,515][87424] Updated weights for policy 0, policy_version 117746 (0.0011) -[2023-11-28 03:17:44,900][87424] Updated weights for policy 0, policy_version 117756 (0.0012) -[2023-11-28 03:17:46,630][87426] Updated weights for policy 1, policy_version 117540 (0.0009) -[2023-11-28 03:17:46,634][87424] Updated weights for policy 0, policy_version 117766 (0.0012) -[2023-11-28 03:17:47,013][87426] Updated weights for policy 1, policy_version 117550 (0.0011) -[2023-11-28 03:17:47,020][87424] Updated weights for policy 0, policy_version 117776 (0.0011) -[2023-11-28 03:17:47,394][87426] Updated weights for policy 1, policy_version 117560 (0.0011) -[2023-11-28 03:17:47,400][87424] Updated weights for policy 0, policy_version 117786 (0.0008) -[2023-11-28 03:17:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 60252160. Throughput: 0: 2754.8, 1: 2678.4. Samples: 60260332. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:17:48,445][86177] Avg episode reward: [(0, '-539.710'), (1, '-581.760')] -[2023-11-28 03:17:49,185][87424] Updated weights for policy 0, policy_version 117796 (0.0009) -[2023-11-28 03:17:49,571][87424] Updated weights for policy 0, policy_version 117806 (0.0009) -[2023-11-28 03:17:49,827][87426] Updated weights for policy 1, policy_version 117570 (0.0011) -[2023-11-28 03:17:49,956][87424] Updated weights for policy 0, policy_version 117816 (0.0011) -[2023-11-28 03:17:50,210][87426] Updated weights for policy 1, policy_version 117580 (0.0012) -[2023-11-28 03:17:50,582][87426] Updated weights for policy 1, policy_version 117590 (0.0011) -[2023-11-28 03:17:50,956][87426] Updated weights for policy 1, policy_version 117600 (0.0011) -[2023-11-28 03:17:52,380][87424] Updated weights for policy 0, policy_version 117826 (0.0011) -[2023-11-28 03:17:52,763][87424] Updated weights for policy 0, policy_version 117836 (0.0010) -[2023-11-28 03:17:53,012][87426] Updated weights for policy 1, policy_version 117610 (0.0011) -[2023-11-28 03:17:53,149][87424] Updated weights for policy 0, policy_version 117846 (0.0012) -[2023-11-28 03:17:53,392][87426] Updated weights for policy 1, policy_version 117620 (0.0010) -[2023-11-28 03:17:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 60268544. Throughput: 0: 2755.2, 1: 2682.1. Samples: 60293180. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:17:53,445][86177] Avg episode reward: [(0, '-501.360'), (1, '-594.590')] -[2023-11-28 03:17:53,532][87424] Updated weights for policy 0, policy_version 117856 (0.0011) -[2023-11-28 03:17:53,775][87426] Updated weights for policy 1, policy_version 117630 (0.0009) -[2023-11-28 03:17:55,549][87424] Updated weights for policy 0, policy_version 117866 (0.0011) -[2023-11-28 03:17:55,944][87424] Updated weights for policy 0, policy_version 117876 (0.0012) -[2023-11-28 03:17:56,218][87426] Updated weights for policy 1, policy_version 117640 (0.0010) -[2023-11-28 03:17:56,338][87424] Updated weights for policy 0, policy_version 117886 (0.0011) -[2023-11-28 03:17:56,604][87426] Updated weights for policy 1, policy_version 117650 (0.0007) -[2023-11-28 03:17:56,990][87426] Updated weights for policy 1, policy_version 117660 (0.0007) -[2023-11-28 03:17:58,303][87424] Updated weights for policy 0, policy_version 117896 (0.0011) -[2023-11-28 03:17:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 60301312. Throughput: 0: 2760.4, 1: 2694.9. Samples: 60318688. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:17:58,445][86177] Avg episode reward: [(0, '-502.000'), (1, '-618.850')] -[2023-11-28 03:17:58,626][87426] Updated weights for policy 1, policy_version 117670 (0.0010) -[2023-11-28 03:17:58,685][87424] Updated weights for policy 0, policy_version 117906 (0.0012) -[2023-11-28 03:17:59,007][87426] Updated weights for policy 1, policy_version 117680 (0.0011) -[2023-11-28 03:17:59,072][87424] Updated weights for policy 0, policy_version 117916 (0.0012) -[2023-11-28 03:17:59,395][87426] Updated weights for policy 1, policy_version 117690 (0.0007) -[2023-11-28 03:18:01,142][87424] Updated weights for policy 0, policy_version 117926 (0.0012) -[2023-11-28 03:18:01,526][87424] Updated weights for policy 0, policy_version 117936 (0.0011) -[2023-11-28 03:18:01,550][87426] Updated weights for policy 1, policy_version 117700 (0.0010) -[2023-11-28 03:18:01,914][87424] Updated weights for policy 0, policy_version 117946 (0.0011) -[2023-11-28 03:18:01,931][87426] Updated weights for policy 1, policy_version 117710 (0.0011) -[2023-11-28 03:18:02,311][87426] Updated weights for policy 1, policy_version 117720 (0.0012) -[2023-11-28 03:18:03,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 60334080. Throughput: 0: 2757.3, 1: 2706.0. Samples: 60344052. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:18:03,445][86177] Avg episode reward: [(0, '-498.000'), (1, '-617.630')] -[2023-11-28 03:18:03,662][87424] Updated weights for policy 0, policy_version 117956 (0.0012) -[2023-11-28 03:18:03,985][87426] Updated weights for policy 1, policy_version 117730 (0.0012) -[2023-11-28 03:18:04,036][87424] Updated weights for policy 0, policy_version 117966 (0.0009) -[2023-11-28 03:18:04,363][87426] Updated weights for policy 1, policy_version 117740 (0.0011) -[2023-11-28 03:18:04,426][87424] Updated weights for policy 0, policy_version 117976 (0.0009) -[2023-11-28 03:18:04,744][87426] Updated weights for policy 1, policy_version 117750 (0.0012) -[2023-11-28 03:18:05,121][87426] Updated weights for policy 1, policy_version 117760 (0.0011) -[2023-11-28 03:18:06,873][87424] Updated weights for policy 0, policy_version 117986 (0.0010) -[2023-11-28 03:18:07,243][87424] Updated weights for policy 0, policy_version 117996 (0.0012) -[2023-11-28 03:18:07,626][87424] Updated weights for policy 0, policy_version 118006 (0.0012) -[2023-11-28 03:18:07,679][87426] Updated weights for policy 1, policy_version 117770 (0.0012) -[2023-11-28 03:18:08,006][87424] Updated weights for policy 0, policy_version 118016 (0.0009) -[2023-11-28 03:18:08,058][87426] Updated weights for policy 1, policy_version 117780 (0.0011) -[2023-11-28 03:18:08,437][87426] Updated weights for policy 1, policy_version 117790 (0.0011) -[2023-11-28 03:18:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 60358656. Throughput: 0: 2762.5, 1: 2743.9. Samples: 60378524. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:18:08,445][86177] Avg episode reward: [(0, '-499.810'), (1, '-631.110')] -[2023-11-28 03:18:10,144][87424] Updated weights for policy 0, policy_version 118026 (0.0010) -[2023-11-28 03:18:10,448][87426] Updated weights for policy 1, policy_version 117800 (0.0011) -[2023-11-28 03:18:10,517][87424] Updated weights for policy 0, policy_version 118036 (0.0011) -[2023-11-28 03:18:10,823][87426] Updated weights for policy 1, policy_version 117810 (0.0011) -[2023-11-28 03:18:10,897][87424] Updated weights for policy 0, policy_version 118046 (0.0010) -[2023-11-28 03:18:11,209][87426] Updated weights for policy 1, policy_version 117820 (0.0011) -[2023-11-28 03:18:13,240][87424] Updated weights for policy 0, policy_version 118056 (0.0008) -[2023-11-28 03:18:13,353][87426] Updated weights for policy 1, policy_version 117830 (0.0010) -[2023-11-28 03:18:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 60383232. Throughput: 0: 2742.4, 1: 2743.6. Samples: 60403300. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:18:13,445][86177] Avg episode reward: [(0, '-501.090'), (1, '-662.080')] -[2023-11-28 03:18:13,628][87424] Updated weights for policy 0, policy_version 118066 (0.0008) -[2023-11-28 03:18:13,729][87426] Updated weights for policy 1, policy_version 117840 (0.0007) -[2023-11-28 03:18:14,008][87424] Updated weights for policy 0, policy_version 118076 (0.0007) -[2023-11-28 03:18:14,107][87426] Updated weights for policy 1, policy_version 117850 (0.0007) -[2023-11-28 03:18:16,011][87426] Updated weights for policy 1, policy_version 117860 (0.0009) -[2023-11-28 03:18:16,290][87424] Updated weights for policy 0, policy_version 118086 (0.0011) -[2023-11-28 03:18:16,389][87426] Updated weights for policy 1, policy_version 117870 (0.0011) -[2023-11-28 03:18:16,673][87424] Updated weights for policy 0, policy_version 118096 (0.0011) -[2023-11-28 03:18:16,762][87426] Updated weights for policy 1, policy_version 117880 (0.0011) -[2023-11-28 03:18:17,062][87424] Updated weights for policy 0, policy_version 118106 (0.0008) -[2023-11-28 03:18:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 60416000. Throughput: 0: 2729.0, 1: 2743.7. Samples: 60426796. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:18:18,445][86177] Avg episode reward: [(0, '-501.310'), (1, '-640.520')] -[2023-11-28 03:18:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000118112_30236672.pth... -[2023-11-28 03:18:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000117888_30179328.pth... -[2023-11-28 03:18:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000115360_29532160.pth -[2023-11-28 03:18:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000115584_29589504.pth -[2023-11-28 03:18:19,105][87426] Updated weights for policy 1, policy_version 117890 (0.0011) -[2023-11-28 03:18:19,238][87424] Updated weights for policy 0, policy_version 118116 (0.0009) -[2023-11-28 03:18:19,487][87426] Updated weights for policy 1, policy_version 117900 (0.0012) -[2023-11-28 03:18:19,614][87424] Updated weights for policy 0, policy_version 118126 (0.0010) -[2023-11-28 03:18:19,861][87426] Updated weights for policy 1, policy_version 117910 (0.0012) -[2023-11-28 03:18:19,995][87424] Updated weights for policy 0, policy_version 118136 (0.0009) -[2023-11-28 03:18:20,239][87426] Updated weights for policy 1, policy_version 117920 (0.0011) -[2023-11-28 03:18:22,369][87424] Updated weights for policy 0, policy_version 118146 (0.0008) -[2023-11-28 03:18:22,537][87426] Updated weights for policy 1, policy_version 117930 (0.0011) -[2023-11-28 03:18:22,751][87424] Updated weights for policy 0, policy_version 118156 (0.0007) -[2023-11-28 03:18:22,913][87426] Updated weights for policy 1, policy_version 117940 (0.0011) -[2023-11-28 03:18:23,121][87424] Updated weights for policy 0, policy_version 118166 (0.0009) -[2023-11-28 03:18:23,300][87426] Updated weights for policy 1, policy_version 117950 (0.0012) -[2023-11-28 03:18:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 60440576. Throughput: 0: 2730.2, 1: 2741.1. Samples: 60458624. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:18:23,445][86177] Avg episode reward: [(0, '-511.400'), (1, '-606.180')] -[2023-11-28 03:18:23,505][87424] Updated weights for policy 0, policy_version 118176 (0.0008) -[2023-11-28 03:18:25,529][87424] Updated weights for policy 0, policy_version 118186 (0.0012) -[2023-11-28 03:18:25,866][87426] Updated weights for policy 1, policy_version 117960 (0.0011) -[2023-11-28 03:18:25,908][87424] Updated weights for policy 0, policy_version 118196 (0.0010) -[2023-11-28 03:18:26,252][87426] Updated weights for policy 1, policy_version 117970 (0.0011) -[2023-11-28 03:18:26,291][87424] Updated weights for policy 0, policy_version 118206 (0.0007) -[2023-11-28 03:18:26,627][87426] Updated weights for policy 1, policy_version 117980 (0.0012) -[2023-11-28 03:18:28,170][87424] Updated weights for policy 0, policy_version 118216 (0.0010) -[2023-11-28 03:18:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 60465152. Throughput: 0: 2755.2, 1: 2756.5. Samples: 60483712. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:18:28,445][86177] Avg episode reward: [(0, '-518.900'), (1, '-622.940')] -[2023-11-28 03:18:28,545][87424] Updated weights for policy 0, policy_version 118226 (0.0009) -[2023-11-28 03:18:28,633][87426] Updated weights for policy 1, policy_version 117990 (0.0010) -[2023-11-28 03:18:28,931][87424] Updated weights for policy 0, policy_version 118236 (0.0008) -[2023-11-28 03:18:29,022][87426] Updated weights for policy 1, policy_version 118000 (0.0008) -[2023-11-28 03:18:29,398][87426] Updated weights for policy 1, policy_version 118010 (0.0007) -[2023-11-28 03:18:31,233][87426] Updated weights for policy 1, policy_version 118020 (0.0011) -[2023-11-28 03:18:31,425][87424] Updated weights for policy 0, policy_version 118246 (0.0011) -[2023-11-28 03:18:31,612][87426] Updated weights for policy 1, policy_version 118030 (0.0011) -[2023-11-28 03:18:31,805][87424] Updated weights for policy 0, policy_version 118256 (0.0011) -[2023-11-28 03:18:31,995][87426] Updated weights for policy 1, policy_version 118040 (0.0011) -[2023-11-28 03:18:32,187][87424] Updated weights for policy 0, policy_version 118266 (0.0012) -[2023-11-28 03:18:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 60497920. Throughput: 0: 2739.2, 1: 2776.0. Samples: 60508516. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:18:33,445][86177] Avg episode reward: [(0, '-520.560'), (1, '-625.750')] -[2023-11-28 03:18:34,115][87424] Updated weights for policy 0, policy_version 118276 (0.0012) -[2023-11-28 03:18:34,488][87424] Updated weights for policy 0, policy_version 118286 (0.0012) -[2023-11-28 03:18:34,561][87426] Updated weights for policy 1, policy_version 118050 (0.0009) -[2023-11-28 03:18:34,869][87424] Updated weights for policy 0, policy_version 118296 (0.0010) -[2023-11-28 03:18:34,934][87426] Updated weights for policy 1, policy_version 118060 (0.0009) -[2023-11-28 03:18:35,314][87426] Updated weights for policy 1, policy_version 118070 (0.0011) -[2023-11-28 03:18:35,694][87426] Updated weights for policy 1, policy_version 118080 (0.0009) -[2023-11-28 03:18:36,936][87424] Updated weights for policy 0, policy_version 118306 (0.0011) -[2023-11-28 03:18:37,320][87424] Updated weights for policy 0, policy_version 118316 (0.0009) -[2023-11-28 03:18:37,701][87424] Updated weights for policy 0, policy_version 118326 (0.0008) -[2023-11-28 03:18:37,934][87426] Updated weights for policy 1, policy_version 118090 (0.0012) -[2023-11-28 03:18:38,081][87424] Updated weights for policy 0, policy_version 118336 (0.0011) -[2023-11-28 03:18:38,318][87426] Updated weights for policy 1, policy_version 118100 (0.0012) -[2023-11-28 03:18:38,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 60522496. Throughput: 0: 2743.3, 1: 2776.5. Samples: 60541572. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:18:38,446][86177] Avg episode reward: [(0, '-526.770'), (1, '-619.330')] -[2023-11-28 03:18:38,696][87426] Updated weights for policy 1, policy_version 118110 (0.0012) -[2023-11-28 03:18:40,161][87424] Updated weights for policy 0, policy_version 118346 (0.0011) -[2023-11-28 03:18:40,541][87424] Updated weights for policy 0, policy_version 118356 (0.0011) -[2023-11-28 03:18:40,573][87426] Updated weights for policy 1, policy_version 118120 (0.0012) -[2023-11-28 03:18:40,924][87424] Updated weights for policy 0, policy_version 118366 (0.0011) -[2023-11-28 03:18:40,950][87426] Updated weights for policy 1, policy_version 118130 (0.0011) -[2023-11-28 03:18:41,334][87426] Updated weights for policy 1, policy_version 118140 (0.0012) -[2023-11-28 03:18:43,241][87424] Updated weights for policy 0, policy_version 118376 (0.0011) -[2023-11-28 03:18:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 60547072. Throughput: 0: 2738.4, 1: 2760.2. Samples: 60566124. Policy #0 lag: (min: 29.0, avg: 43.6, max: 61.0) -[2023-11-28 03:18:43,445][86177] Avg episode reward: [(0, '-523.870'), (1, '-590.650')] -[2023-11-28 03:18:43,623][87424] Updated weights for policy 0, policy_version 118386 (0.0011) -[2023-11-28 03:18:43,640][87426] Updated weights for policy 1, policy_version 118150 (0.0010) -[2023-11-28 03:18:44,009][87424] Updated weights for policy 0, policy_version 118396 (0.0011) -[2023-11-28 03:18:44,019][87426] Updated weights for policy 1, policy_version 118160 (0.0009) -[2023-11-28 03:18:44,399][87426] Updated weights for policy 1, policy_version 118170 (0.0011) -[2023-11-28 03:18:46,424][87426] Updated weights for policy 1, policy_version 118180 (0.0012) -[2023-11-28 03:18:46,627][87424] Updated weights for policy 0, policy_version 118406 (0.0012) -[2023-11-28 03:18:46,803][87426] Updated weights for policy 1, policy_version 118190 (0.0011) -[2023-11-28 03:18:47,008][87424] Updated weights for policy 0, policy_version 118416 (0.0009) -[2023-11-28 03:18:47,178][87426] Updated weights for policy 1, policy_version 118200 (0.0009) -[2023-11-28 03:18:47,390][87424] Updated weights for policy 0, policy_version 118426 (0.0009) -[2023-11-28 03:18:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 60579840. Throughput: 0: 2718.1, 1: 2757.9. Samples: 60590472. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:18:48,446][86177] Avg episode reward: [(0, '-515.260'), (1, '-576.970')] -[2023-11-28 03:18:48,860][87426] Updated weights for policy 1, policy_version 118210 (0.0012) -[2023-11-28 03:18:49,240][87426] Updated weights for policy 1, policy_version 118220 (0.0012) -[2023-11-28 03:18:49,569][87424] Updated weights for policy 0, policy_version 118436 (0.0009) -[2023-11-28 03:18:49,622][87426] Updated weights for policy 1, policy_version 118230 (0.0011) -[2023-11-28 03:18:49,950][87424] Updated weights for policy 0, policy_version 118446 (0.0011) -[2023-11-28 03:18:49,987][87426] Updated weights for policy 1, policy_version 118240 (0.0011) -[2023-11-28 03:18:50,329][87424] Updated weights for policy 0, policy_version 118456 (0.0012) -[2023-11-28 03:18:52,548][87426] Updated weights for policy 1, policy_version 118250 (0.0011) -[2023-11-28 03:18:52,649][87424] Updated weights for policy 0, policy_version 118466 (0.0011) -[2023-11-28 03:18:52,926][87426] Updated weights for policy 1, policy_version 118260 (0.0012) -[2023-11-28 03:18:53,033][87424] Updated weights for policy 0, policy_version 118476 (0.0011) -[2023-11-28 03:18:53,308][87426] Updated weights for policy 1, policy_version 118270 (0.0012) -[2023-11-28 03:18:53,416][87424] Updated weights for policy 0, policy_version 118486 (0.0011) -[2023-11-28 03:18:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 60604416. Throughput: 0: 2713.3, 1: 2720.9. Samples: 60623064. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:18:53,445][86177] Avg episode reward: [(0, '-515.460'), (1, '-577.980')] -[2023-11-28 03:18:53,799][87424] Updated weights for policy 0, policy_version 118496 (0.0012) -[2023-11-28 03:18:55,241][87426] Updated weights for policy 1, policy_version 118280 (0.0012) -[2023-11-28 03:18:55,619][87426] Updated weights for policy 1, policy_version 118290 (0.0012) -[2023-11-28 03:18:56,002][87426] Updated weights for policy 1, policy_version 118300 (0.0011) -[2023-11-28 03:18:56,453][87424] Updated weights for policy 0, policy_version 118506 (0.0007) -[2023-11-28 03:18:56,842][87424] Updated weights for policy 0, policy_version 118516 (0.0007) -[2023-11-28 03:18:57,223][87424] Updated weights for policy 0, policy_version 118526 (0.0007) -[2023-11-28 03:18:57,666][87426] Updated weights for policy 1, policy_version 118310 (0.0011) -[2023-11-28 03:18:58,043][87426] Updated weights for policy 1, policy_version 118320 (0.0012) -[2023-11-28 03:18:58,425][87426] Updated weights for policy 1, policy_version 118330 (0.0011) -[2023-11-28 03:18:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 60628992. Throughput: 0: 2697.2, 1: 2705.1. Samples: 60646400. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:18:58,445][86177] Avg episode reward: [(0, '-520.270'), (1, '-604.380')] -[2023-11-28 03:18:59,690][87424] Updated weights for policy 0, policy_version 118536 (0.0008) -[2023-11-28 03:19:00,068][87424] Updated weights for policy 0, policy_version 118546 (0.0009) -[2023-11-28 03:19:00,460][87424] Updated weights for policy 0, policy_version 118556 (0.0012) -[2023-11-28 03:19:00,888][87426] Updated weights for policy 1, policy_version 118340 (0.0010) -[2023-11-28 03:19:01,265][87426] Updated weights for policy 1, policy_version 118350 (0.0008) -[2023-11-28 03:19:01,649][87426] Updated weights for policy 1, policy_version 118360 (0.0008) -[2023-11-28 03:19:02,706][87424] Updated weights for policy 0, policy_version 118566 (0.0011) -[2023-11-28 03:19:03,088][87424] Updated weights for policy 0, policy_version 118576 (0.0011) -[2023-11-28 03:19:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 60653568. Throughput: 0: 2698.8, 1: 2701.1. Samples: 60669788. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:03,445][86177] Avg episode reward: [(0, '-514.320'), (1, '-620.840')] -[2023-11-28 03:19:03,468][87424] Updated weights for policy 0, policy_version 118586 (0.0012) -[2023-11-28 03:19:04,122][87426] Updated weights for policy 1, policy_version 118370 (0.0010) -[2023-11-28 03:19:04,502][87426] Updated weights for policy 1, policy_version 118380 (0.0007) -[2023-11-28 03:19:04,887][87426] Updated weights for policy 1, policy_version 118390 (0.0008) -[2023-11-28 03:19:05,268][87426] Updated weights for policy 1, policy_version 118400 (0.0007) -[2023-11-28 03:19:05,683][87424] Updated weights for policy 0, policy_version 118596 (0.0012) -[2023-11-28 03:19:06,068][87424] Updated weights for policy 0, policy_version 118606 (0.0012) -[2023-11-28 03:19:06,448][87424] Updated weights for policy 0, policy_version 118616 (0.0012) -[2023-11-28 03:19:07,741][87426] Updated weights for policy 1, policy_version 118410 (0.0007) -[2023-11-28 03:19:08,120][87426] Updated weights for policy 1, policy_version 118420 (0.0008) -[2023-11-28 03:19:08,272][87424] Updated weights for policy 0, policy_version 118626 (0.0012) -[2023-11-28 03:19:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 60678144. Throughput: 0: 2692.7, 1: 2717.9. Samples: 60702100. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:08,445][86177] Avg episode reward: [(0, '-510.050'), (1, '-644.630')] -[2023-11-28 03:19:08,502][87426] Updated weights for policy 1, policy_version 118430 (0.0007) -[2023-11-28 03:19:08,647][87424] Updated weights for policy 0, policy_version 118636 (0.0011) -[2023-11-28 03:19:09,035][87424] Updated weights for policy 0, policy_version 118646 (0.0012) -[2023-11-28 03:19:09,419][87424] Updated weights for policy 0, policy_version 118656 (0.0011) -[2023-11-28 03:19:10,397][87426] Updated weights for policy 1, policy_version 118440 (0.0010) -[2023-11-28 03:19:10,771][87426] Updated weights for policy 1, policy_version 118450 (0.0010) -[2023-11-28 03:19:11,153][87426] Updated weights for policy 1, policy_version 118460 (0.0011) -[2023-11-28 03:19:11,363][87424] Updated weights for policy 0, policy_version 118666 (0.0012) -[2023-11-28 03:19:11,748][87424] Updated weights for policy 0, policy_version 118676 (0.0012) -[2023-11-28 03:19:12,133][87424] Updated weights for policy 0, policy_version 118686 (0.0012) -[2023-11-28 03:19:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 60710912. Throughput: 0: 2682.5, 1: 2713.9. Samples: 60726548. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:13,445][86177] Avg episode reward: [(0, '-506.640'), (1, '-600.140')] -[2023-11-28 03:19:13,591][87426] Updated weights for policy 1, policy_version 118470 (0.0009) -[2023-11-28 03:19:13,976][87426] Updated weights for policy 1, policy_version 118480 (0.0007) -[2023-11-28 03:19:14,359][87426] Updated weights for policy 1, policy_version 118490 (0.0008) -[2023-11-28 03:19:14,359][87424] Updated weights for policy 0, policy_version 118696 (0.0012) -[2023-11-28 03:19:14,756][87424] Updated weights for policy 0, policy_version 118706 (0.0010) -[2023-11-28 03:19:15,130][87424] Updated weights for policy 0, policy_version 118716 (0.0008) -[2023-11-28 03:19:16,886][87426] Updated weights for policy 1, policy_version 118500 (0.0009) -[2023-11-28 03:19:17,268][87426] Updated weights for policy 1, policy_version 118510 (0.0012) -[2023-11-28 03:19:17,432][87424] Updated weights for policy 0, policy_version 118726 (0.0010) -[2023-11-28 03:19:17,639][87426] Updated weights for policy 1, policy_version 118520 (0.0012) -[2023-11-28 03:19:17,816][87424] Updated weights for policy 0, policy_version 118736 (0.0012) -[2023-11-28 03:19:18,206][87424] Updated weights for policy 0, policy_version 118746 (0.0012) -[2023-11-28 03:19:18,445][86177] Fps is (10 sec: 6553.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 60743680. Throughput: 0: 2686.3, 1: 2697.0. Samples: 60750764. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:18,446][86177] Avg episode reward: [(0, '-493.990'), (1, '-569.820')] -[2023-11-28 03:19:20,095][87424] Updated weights for policy 0, policy_version 118756 (0.0012) -[2023-11-28 03:19:20,244][87426] Updated weights for policy 1, policy_version 118530 (0.0012) -[2023-11-28 03:19:20,476][87424] Updated weights for policy 0, policy_version 118766 (0.0011) -[2023-11-28 03:19:20,624][87426] Updated weights for policy 1, policy_version 118540 (0.0011) -[2023-11-28 03:19:20,856][87424] Updated weights for policy 0, policy_version 118776 (0.0008) -[2023-11-28 03:19:20,997][87426] Updated weights for policy 1, policy_version 118550 (0.0012) -[2023-11-28 03:19:21,373][87426] Updated weights for policy 1, policy_version 118560 (0.0011) -[2023-11-28 03:19:23,011][87424] Updated weights for policy 0, policy_version 118786 (0.0009) -[2023-11-28 03:19:23,405][87424] Updated weights for policy 0, policy_version 118796 (0.0009) -[2023-11-28 03:19:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 60760064. Throughput: 0: 2662.9, 1: 2674.9. Samples: 60781776. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:23,445][86177] Avg episode reward: [(0, '-498.160'), (1, '-559.470')] -[2023-11-28 03:19:23,676][87426] Updated weights for policy 1, policy_version 118570 (0.0012) -[2023-11-28 03:19:23,788][87424] Updated weights for policy 0, policy_version 118806 (0.0012) -[2023-11-28 03:19:24,053][87426] Updated weights for policy 1, policy_version 118580 (0.0011) -[2023-11-28 03:19:24,167][87424] Updated weights for policy 0, policy_version 118816 (0.0012) -[2023-11-28 03:19:24,428][87426] Updated weights for policy 1, policy_version 118590 (0.0011) -[2023-11-28 03:19:26,145][87426] Updated weights for policy 1, policy_version 118600 (0.0012) -[2023-11-28 03:19:26,524][87426] Updated weights for policy 1, policy_version 118610 (0.0011) -[2023-11-28 03:19:26,550][87424] Updated weights for policy 0, policy_version 118826 (0.0011) -[2023-11-28 03:19:26,907][87426] Updated weights for policy 1, policy_version 118620 (0.0011) -[2023-11-28 03:19:26,935][87424] Updated weights for policy 0, policy_version 118836 (0.0011) -[2023-11-28 03:19:27,325][87424] Updated weights for policy 0, policy_version 118846 (0.0012) -[2023-11-28 03:19:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 60792832. Throughput: 0: 2661.2, 1: 2702.0. Samples: 60807468. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:28,445][86177] Avg episode reward: [(0, '-496.830'), (1, '-524.190')] -[2023-11-28 03:19:28,487][87426] Updated weights for policy 1, policy_version 118630 (0.0011) -[2023-11-28 03:19:28,861][87426] Updated weights for policy 1, policy_version 118640 (0.0011) -[2023-11-28 03:19:29,244][87426] Updated weights for policy 1, policy_version 118650 (0.0012) -[2023-11-28 03:19:29,817][87424] Updated weights for policy 0, policy_version 118856 (0.0009) -[2023-11-28 03:19:30,193][87424] Updated weights for policy 0, policy_version 118866 (0.0011) -[2023-11-28 03:19:30,574][87424] Updated weights for policy 0, policy_version 118876 (0.0010) -[2023-11-28 03:19:31,604][87426] Updated weights for policy 1, policy_version 118660 (0.0012) -[2023-11-28 03:19:31,981][87426] Updated weights for policy 1, policy_version 118670 (0.0011) -[2023-11-28 03:19:32,359][87426] Updated weights for policy 1, policy_version 118680 (0.0008) -[2023-11-28 03:19:32,803][87424] Updated weights for policy 0, policy_version 118886 (0.0008) -[2023-11-28 03:19:33,192][87424] Updated weights for policy 0, policy_version 118896 (0.0008) -[2023-11-28 03:19:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 60817408. Throughput: 0: 2649.4, 1: 2713.1. Samples: 60831784. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:33,445][86177] Avg episode reward: [(0, '-498.370'), (1, '-544.190')] -[2023-11-28 03:19:33,573][87424] Updated weights for policy 0, policy_version 118906 (0.0008) -[2023-11-28 03:19:34,811][87426] Updated weights for policy 1, policy_version 118690 (0.0008) -[2023-11-28 03:19:35,186][87426] Updated weights for policy 1, policy_version 118700 (0.0008) -[2023-11-28 03:19:35,569][87426] Updated weights for policy 1, policy_version 118710 (0.0007) -[2023-11-28 03:19:35,893][87424] Updated weights for policy 0, policy_version 118916 (0.0008) -[2023-11-28 03:19:35,950][87426] Updated weights for policy 1, policy_version 118720 (0.0008) -[2023-11-28 03:19:36,270][87424] Updated weights for policy 0, policy_version 118926 (0.0010) -[2023-11-28 03:19:36,664][87424] Updated weights for policy 0, policy_version 118936 (0.0011) -[2023-11-28 03:19:38,342][87426] Updated weights for policy 1, policy_version 118730 (0.0012) -[2023-11-28 03:19:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 60841984. Throughput: 0: 2626.5, 1: 2698.6. Samples: 60862692. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:38,445][86177] Avg episode reward: [(0, '-500.300'), (1, '-567.660')] -[2023-11-28 03:19:38,719][87426] Updated weights for policy 1, policy_version 118740 (0.0012) -[2023-11-28 03:19:39,099][87424] Updated weights for policy 0, policy_version 118946 (0.0009) -[2023-11-28 03:19:39,110][87426] Updated weights for policy 1, policy_version 118750 (0.0011) -[2023-11-28 03:19:39,481][87424] Updated weights for policy 0, policy_version 118956 (0.0011) -[2023-11-28 03:19:39,863][87424] Updated weights for policy 0, policy_version 118966 (0.0012) -[2023-11-28 03:19:40,243][87424] Updated weights for policy 0, policy_version 118976 (0.0012) -[2023-11-28 03:19:41,549][87426] Updated weights for policy 1, policy_version 118760 (0.0008) -[2023-11-28 03:19:41,927][87426] Updated weights for policy 1, policy_version 118770 (0.0011) -[2023-11-28 03:19:42,310][87426] Updated weights for policy 1, policy_version 118780 (0.0012) -[2023-11-28 03:19:42,731][87424] Updated weights for policy 0, policy_version 118986 (0.0011) -[2023-11-28 03:19:43,120][87424] Updated weights for policy 0, policy_version 118996 (0.0012) -[2023-11-28 03:19:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 60866560. Throughput: 0: 2653.9, 1: 2681.2. Samples: 60886484. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:43,445][86177] Avg episode reward: [(0, '-495.830'), (1, '-596.540')] -[2023-11-28 03:19:43,499][87424] Updated weights for policy 0, policy_version 119006 (0.0008) -[2023-11-28 03:19:44,489][87426] Updated weights for policy 1, policy_version 118790 (0.0011) -[2023-11-28 03:19:44,868][87426] Updated weights for policy 1, policy_version 118800 (0.0011) -[2023-11-28 03:19:45,209][87424] Updated weights for policy 0, policy_version 119016 (0.0009) -[2023-11-28 03:19:45,253][87426] Updated weights for policy 1, policy_version 118810 (0.0012) -[2023-11-28 03:19:45,601][87424] Updated weights for policy 0, policy_version 119026 (0.0011) -[2023-11-28 03:19:45,981][87424] Updated weights for policy 0, policy_version 119036 (0.0010) -[2023-11-28 03:19:47,172][87426] Updated weights for policy 1, policy_version 118820 (0.0010) -[2023-11-28 03:19:47,550][87426] Updated weights for policy 1, policy_version 118830 (0.0007) -[2023-11-28 03:19:47,930][87426] Updated weights for policy 1, policy_version 118840 (0.0007) -[2023-11-28 03:19:48,153][87424] Updated weights for policy 0, policy_version 119046 (0.0010) -[2023-11-28 03:19:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 60899328. Throughput: 0: 2660.2, 1: 2683.0. Samples: 60910232. Policy #0 lag: (min: 2.0, avg: 19.4, max: 34.0) -[2023-11-28 03:19:48,446][86177] Avg episode reward: [(0, '-494.990'), (1, '-599.150')] -[2023-11-28 03:19:48,530][87424] Updated weights for policy 0, policy_version 119056 (0.0011) -[2023-11-28 03:19:48,913][87424] Updated weights for policy 0, policy_version 119066 (0.0012) -[2023-11-28 03:19:49,642][87426] Updated weights for policy 1, policy_version 118850 (0.0008) -[2023-11-28 03:19:50,016][87426] Updated weights for policy 1, policy_version 118860 (0.0009) -[2023-11-28 03:19:50,391][87426] Updated weights for policy 1, policy_version 118870 (0.0008) -[2023-11-28 03:19:50,770][87426] Updated weights for policy 1, policy_version 118880 (0.0011) -[2023-11-28 03:19:51,319][87424] Updated weights for policy 0, policy_version 119076 (0.0012) -[2023-11-28 03:19:51,714][87424] Updated weights for policy 0, policy_version 119086 (0.0008) -[2023-11-28 03:19:52,086][87424] Updated weights for policy 0, policy_version 119096 (0.0008) -[2023-11-28 03:19:53,308][87426] Updated weights for policy 1, policy_version 118890 (0.0011) -[2023-11-28 03:19:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 60923904. Throughput: 0: 2640.6, 1: 2692.9. Samples: 60942108. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:19:53,445][86177] Avg episode reward: [(0, '-496.120'), (1, '-598.820')] -[2023-11-28 03:19:53,694][87426] Updated weights for policy 1, policy_version 118900 (0.0010) -[2023-11-28 03:19:54,074][87426] Updated weights for policy 1, policy_version 118910 (0.0011) -[2023-11-28 03:19:54,544][87424] Updated weights for policy 0, policy_version 119106 (0.0009) -[2023-11-28 03:19:54,931][87424] Updated weights for policy 0, policy_version 119116 (0.0008) -[2023-11-28 03:19:55,311][87424] Updated weights for policy 0, policy_version 119126 (0.0008) -[2023-11-28 03:19:55,695][87424] Updated weights for policy 0, policy_version 119136 (0.0007) -[2023-11-28 03:19:56,101][87426] Updated weights for policy 1, policy_version 118920 (0.0012) -[2023-11-28 03:19:56,480][87426] Updated weights for policy 1, policy_version 118930 (0.0011) -[2023-11-28 03:19:56,862][87426] Updated weights for policy 1, policy_version 118940 (0.0012) -[2023-11-28 03:19:57,994][87424] Updated weights for policy 0, policy_version 119146 (0.0012) -[2023-11-28 03:19:58,378][87424] Updated weights for policy 0, policy_version 119156 (0.0010) -[2023-11-28 03:19:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 60948480. Throughput: 0: 2638.6, 1: 2728.2. Samples: 60968052. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:19:58,446][86177] Avg episode reward: [(0, '-496.890'), (1, '-570.460')] -[2023-11-28 03:19:58,763][87424] Updated weights for policy 0, policy_version 119166 (0.0012) -[2023-11-28 03:19:58,948][87426] Updated weights for policy 1, policy_version 118950 (0.0012) -[2023-11-28 03:19:59,317][87426] Updated weights for policy 1, policy_version 118960 (0.0012) -[2023-11-28 03:19:59,698][87426] Updated weights for policy 1, policy_version 118970 (0.0011) -[2023-11-28 03:20:01,287][87424] Updated weights for policy 0, policy_version 119176 (0.0012) -[2023-11-28 03:20:01,672][87424] Updated weights for policy 0, policy_version 119186 (0.0011) -[2023-11-28 03:20:02,043][87424] Updated weights for policy 0, policy_version 119196 (0.0011) -[2023-11-28 03:20:02,054][87426] Updated weights for policy 1, policy_version 118980 (0.0010) -[2023-11-28 03:20:02,432][87426] Updated weights for policy 1, policy_version 118990 (0.0010) -[2023-11-28 03:20:02,809][87426] Updated weights for policy 1, policy_version 119000 (0.0007) -[2023-11-28 03:20:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 60981248. Throughput: 0: 2625.1, 1: 2743.0. Samples: 60992324. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:03,445][86177] Avg episode reward: [(0, '-504.730'), (1, '-563.520')] -[2023-11-28 03:20:03,808][87424] Updated weights for policy 0, policy_version 119206 (0.0011) -[2023-11-28 03:20:04,190][87424] Updated weights for policy 0, policy_version 119216 (0.0012) -[2023-11-28 03:20:04,542][87426] Updated weights for policy 1, policy_version 119010 (0.0008) -[2023-11-28 03:20:04,568][87424] Updated weights for policy 0, policy_version 119226 (0.0010) -[2023-11-28 03:20:04,924][87426] Updated weights for policy 1, policy_version 119020 (0.0011) -[2023-11-28 03:20:05,307][87426] Updated weights for policy 1, policy_version 119030 (0.0008) -[2023-11-28 03:20:05,683][87426] Updated weights for policy 1, policy_version 119040 (0.0007) -[2023-11-28 03:20:06,947][87424] Updated weights for policy 0, policy_version 119236 (0.0009) -[2023-11-28 03:20:07,326][87424] Updated weights for policy 0, policy_version 119246 (0.0009) -[2023-11-28 03:20:07,453][87426] Updated weights for policy 1, policy_version 119050 (0.0011) -[2023-11-28 03:20:07,709][87424] Updated weights for policy 0, policy_version 119256 (0.0008) -[2023-11-28 03:20:07,824][87426] Updated weights for policy 1, policy_version 119060 (0.0010) -[2023-11-28 03:20:08,202][87426] Updated weights for policy 1, policy_version 119070 (0.0010) -[2023-11-28 03:20:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 61014016. Throughput: 0: 2645.9, 1: 2793.4. Samples: 61026548. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:08,446][86177] Avg episode reward: [(0, '-507.960'), (1, '-577.080')] -[2023-11-28 03:20:10,239][87424] Updated weights for policy 0, policy_version 119266 (0.0008) -[2023-11-28 03:20:10,341][87426] Updated weights for policy 1, policy_version 119080 (0.0009) -[2023-11-28 03:20:10,648][87424] Updated weights for policy 0, policy_version 119276 (0.0010) -[2023-11-28 03:20:10,725][87426] Updated weights for policy 1, policy_version 119090 (0.0013) -[2023-11-28 03:20:11,016][87424] Updated weights for policy 0, policy_version 119286 (0.0011) -[2023-11-28 03:20:11,105][87426] Updated weights for policy 1, policy_version 119100 (0.0012) -[2023-11-28 03:20:11,411][87424] Updated weights for policy 0, policy_version 119296 (0.0008) -[2023-11-28 03:20:13,306][87426] Updated weights for policy 1, policy_version 119110 (0.0011) -[2023-11-28 03:20:13,372][87424] Updated weights for policy 0, policy_version 119306 (0.0008) -[2023-11-28 03:20:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 61030400. Throughput: 0: 2641.0, 1: 2769.1. Samples: 61050924. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:13,445][86177] Avg episode reward: [(0, '-508.280'), (1, '-552.080')] -[2023-11-28 03:20:13,684][87426] Updated weights for policy 1, policy_version 119120 (0.0012) -[2023-11-28 03:20:13,760][87424] Updated weights for policy 0, policy_version 119316 (0.0008) -[2023-11-28 03:20:14,061][87426] Updated weights for policy 1, policy_version 119130 (0.0012) -[2023-11-28 03:20:14,147][87424] Updated weights for policy 0, policy_version 119326 (0.0010) -[2023-11-28 03:20:16,069][87426] Updated weights for policy 1, policy_version 119140 (0.0011) -[2023-11-28 03:20:16,075][87424] Updated weights for policy 0, policy_version 119336 (0.0011) -[2023-11-28 03:20:16,447][87426] Updated weights for policy 1, policy_version 119150 (0.0011) -[2023-11-28 03:20:16,458][87424] Updated weights for policy 0, policy_version 119346 (0.0011) -[2023-11-28 03:20:16,840][87426] Updated weights for policy 1, policy_version 119160 (0.0010) -[2023-11-28 03:20:16,846][87424] Updated weights for policy 0, policy_version 119356 (0.0010) -[2023-11-28 03:20:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 61063168. Throughput: 0: 2642.7, 1: 2755.9. Samples: 61074720. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:18,445][86177] Avg episode reward: [(0, '-507.220'), (1, '-574.210')] -[2023-11-28 03:20:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000119360_30556160.pth... -[2023-11-28 03:20:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000119168_30507008.pth... -[2023-11-28 03:20:18,499][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000116640_29859840.pth -[2023-11-28 03:20:18,506][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000116832_29908992.pth -[2023-11-28 03:20:18,867][87426] Updated weights for policy 1, policy_version 119170 (0.0008) -[2023-11-28 03:20:19,025][87424] Updated weights for policy 0, policy_version 119366 (0.0012) -[2023-11-28 03:20:19,237][87426] Updated weights for policy 1, policy_version 119180 (0.0010) -[2023-11-28 03:20:19,403][87424] Updated weights for policy 0, policy_version 119376 (0.0012) -[2023-11-28 03:20:19,611][87426] Updated weights for policy 1, policy_version 119190 (0.0011) -[2023-11-28 03:20:19,777][87424] Updated weights for policy 0, policy_version 119386 (0.0012) -[2023-11-28 03:20:19,986][87426] Updated weights for policy 1, policy_version 119200 (0.0011) -[2023-11-28 03:20:21,895][87424] Updated weights for policy 0, policy_version 119396 (0.0012) -[2023-11-28 03:20:22,161][87426] Updated weights for policy 1, policy_version 119210 (0.0010) -[2023-11-28 03:20:22,276][87424] Updated weights for policy 0, policy_version 119406 (0.0010) -[2023-11-28 03:20:22,538][87426] Updated weights for policy 1, policy_version 119220 (0.0012) -[2023-11-28 03:20:22,658][87424] Updated weights for policy 0, policy_version 119416 (0.0010) -[2023-11-28 03:20:22,922][87426] Updated weights for policy 1, policy_version 119230 (0.0011) -[2023-11-28 03:20:23,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 61095936. Throughput: 0: 2651.3, 1: 2780.1. Samples: 61107104. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:23,445][86177] Avg episode reward: [(0, '-505.930'), (1, '-565.820')] -[2023-11-28 03:20:25,003][87424] Updated weights for policy 0, policy_version 119426 (0.0010) -[2023-11-28 03:20:25,321][87426] Updated weights for policy 1, policy_version 119240 (0.0008) -[2023-11-28 03:20:25,387][87424] Updated weights for policy 0, policy_version 119436 (0.0009) -[2023-11-28 03:20:25,701][87426] Updated weights for policy 1, policy_version 119250 (0.0007) -[2023-11-28 03:20:25,765][87424] Updated weights for policy 0, policy_version 119446 (0.0007) -[2023-11-28 03:20:26,086][87426] Updated weights for policy 1, policy_version 119260 (0.0007) -[2023-11-28 03:20:26,143][87424] Updated weights for policy 0, policy_version 119456 (0.0008) -[2023-11-28 03:20:27,992][87424] Updated weights for policy 0, policy_version 119466 (0.0012) -[2023-11-28 03:20:28,375][87424] Updated weights for policy 0, policy_version 119476 (0.0009) -[2023-11-28 03:20:28,416][87426] Updated weights for policy 1, policy_version 119270 (0.0007) -[2023-11-28 03:20:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 61112320. Throughput: 0: 2670.0, 1: 2802.1. Samples: 61132728. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:28,445][86177] Avg episode reward: [(0, '-556.610'), (1, '-545.990')] -[2023-11-28 03:20:28,753][87424] Updated weights for policy 0, policy_version 119486 (0.0010) -[2023-11-28 03:20:28,790][87426] Updated weights for policy 1, policy_version 119280 (0.0011) -[2023-11-28 03:20:29,170][87426] Updated weights for policy 1, policy_version 119290 (0.0012) -[2023-11-28 03:20:30,993][87426] Updated weights for policy 1, policy_version 119300 (0.0008) -[2023-11-28 03:20:31,136][87424] Updated weights for policy 0, policy_version 119496 (0.0010) -[2023-11-28 03:20:31,366][87426] Updated weights for policy 1, policy_version 119310 (0.0007) -[2023-11-28 03:20:31,520][87424] Updated weights for policy 0, policy_version 119506 (0.0011) -[2023-11-28 03:20:31,754][87426] Updated weights for policy 1, policy_version 119320 (0.0009) -[2023-11-28 03:20:31,910][87424] Updated weights for policy 0, policy_version 119516 (0.0011) -[2023-11-28 03:20:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61145088. Throughput: 0: 2682.6, 1: 2806.0. Samples: 61157216. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:33,445][86177] Avg episode reward: [(0, '-558.110'), (1, '-545.270')] -[2023-11-28 03:20:33,885][87426] Updated weights for policy 1, policy_version 119330 (0.0009) -[2023-11-28 03:20:34,193][87424] Updated weights for policy 0, policy_version 119526 (0.0011) -[2023-11-28 03:20:34,266][87426] Updated weights for policy 1, policy_version 119340 (0.0009) -[2023-11-28 03:20:34,571][87424] Updated weights for policy 0, policy_version 119536 (0.0007) -[2023-11-28 03:20:34,641][87426] Updated weights for policy 1, policy_version 119350 (0.0009) -[2023-11-28 03:20:34,953][87424] Updated weights for policy 0, policy_version 119546 (0.0009) -[2023-11-28 03:20:35,016][87426] Updated weights for policy 1, policy_version 119360 (0.0008) -[2023-11-28 03:20:36,978][87426] Updated weights for policy 1, policy_version 119370 (0.0010) -[2023-11-28 03:20:37,021][87424] Updated weights for policy 0, policy_version 119556 (0.0009) -[2023-11-28 03:20:37,349][87426] Updated weights for policy 1, policy_version 119380 (0.0008) -[2023-11-28 03:20:37,396][87424] Updated weights for policy 0, policy_version 119566 (0.0012) -[2023-11-28 03:20:37,727][87426] Updated weights for policy 1, policy_version 119390 (0.0011) -[2023-11-28 03:20:37,776][87424] Updated weights for policy 0, policy_version 119576 (0.0009) -[2023-11-28 03:20:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 61177856. Throughput: 0: 2703.0, 1: 2800.2. Samples: 61189752. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:38,445][86177] Avg episode reward: [(0, '-554.320'), (1, '-513.180')] -[2023-11-28 03:20:39,882][87426] Updated weights for policy 1, policy_version 119400 (0.0011) -[2023-11-28 03:20:40,140][87424] Updated weights for policy 0, policy_version 119586 (0.0011) -[2023-11-28 03:20:40,269][87426] Updated weights for policy 1, policy_version 119410 (0.0011) -[2023-11-28 03:20:40,514][87424] Updated weights for policy 0, policy_version 119596 (0.0011) -[2023-11-28 03:20:40,642][87426] Updated weights for policy 1, policy_version 119420 (0.0011) -[2023-11-28 03:20:40,901][87424] Updated weights for policy 0, policy_version 119606 (0.0012) -[2023-11-28 03:20:41,273][87424] Updated weights for policy 0, policy_version 119616 (0.0012) -[2023-11-28 03:20:42,779][87426] Updated weights for policy 1, policy_version 119430 (0.0009) -[2023-11-28 03:20:43,161][87426] Updated weights for policy 1, policy_version 119440 (0.0011) -[2023-11-28 03:20:43,437][87424] Updated weights for policy 0, policy_version 119626 (0.0012) -[2023-11-28 03:20:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 61194240. Throughput: 0: 2698.2, 1: 2769.3. Samples: 61214088. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:43,445][86177] Avg episode reward: [(0, '-550.550'), (1, '-516.490')] -[2023-11-28 03:20:43,536][87426] Updated weights for policy 1, policy_version 119450 (0.0011) -[2023-11-28 03:20:43,816][87424] Updated weights for policy 0, policy_version 119636 (0.0011) -[2023-11-28 03:20:44,196][87424] Updated weights for policy 0, policy_version 119646 (0.0012) -[2023-11-28 03:20:45,304][87426] Updated weights for policy 1, policy_version 119460 (0.0011) -[2023-11-28 03:20:45,677][87426] Updated weights for policy 1, policy_version 119470 (0.0012) -[2023-11-28 03:20:46,058][87426] Updated weights for policy 1, policy_version 119480 (0.0012) -[2023-11-28 03:20:46,433][87424] Updated weights for policy 0, policy_version 119656 (0.0012) -[2023-11-28 03:20:46,829][87424] Updated weights for policy 0, policy_version 119666 (0.0012) -[2023-11-28 03:20:47,216][87424] Updated weights for policy 0, policy_version 119676 (0.0012) -[2023-11-28 03:20:47,972][87426] Updated weights for policy 1, policy_version 119490 (0.0012) -[2023-11-28 03:20:48,343][87426] Updated weights for policy 1, policy_version 119500 (0.0012) -[2023-11-28 03:20:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61227008. Throughput: 0: 2709.1, 1: 2777.3. Samples: 61239212. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:48,445][86177] Avg episode reward: [(0, '-505.830'), (1, '-533.180')] -[2023-11-28 03:20:48,714][87426] Updated weights for policy 1, policy_version 119510 (0.0012) -[2023-11-28 03:20:49,085][87426] Updated weights for policy 1, policy_version 119520 (0.0012) -[2023-11-28 03:20:49,669][87424] Updated weights for policy 0, policy_version 119686 (0.0012) -[2023-11-28 03:20:50,051][87424] Updated weights for policy 0, policy_version 119696 (0.0011) -[2023-11-28 03:20:50,432][87424] Updated weights for policy 0, policy_version 119706 (0.0011) -[2023-11-28 03:20:51,033][87426] Updated weights for policy 1, policy_version 119530 (0.0010) -[2023-11-28 03:20:51,411][87426] Updated weights for policy 1, policy_version 119540 (0.0010) -[2023-11-28 03:20:51,792][87426] Updated weights for policy 1, policy_version 119550 (0.0011) -[2023-11-28 03:20:52,483][87424] Updated weights for policy 0, policy_version 119716 (0.0010) -[2023-11-28 03:20:52,866][87424] Updated weights for policy 0, policy_version 119726 (0.0008) -[2023-11-28 03:20:53,252][87424] Updated weights for policy 0, policy_version 119736 (0.0009) -[2023-11-28 03:20:53,448][86177] Fps is (10 sec: 5732.0, 60 sec: 5460.9, 300 sec: 5415.0). Total num frames: 61251584. Throughput: 0: 2691.5, 1: 2769.6. Samples: 61272320. Policy #0 lag: (min: 31.0, avg: 40.3, max: 63.0) -[2023-11-28 03:20:53,449][86177] Avg episode reward: [(0, '-507.590'), (1, '-544.400')] -[2023-11-28 03:20:54,265][87426] Updated weights for policy 1, policy_version 119560 (0.0008) -[2023-11-28 03:20:54,652][87426] Updated weights for policy 1, policy_version 119570 (0.0008) -[2023-11-28 03:20:55,025][87426] Updated weights for policy 1, policy_version 119580 (0.0009) -[2023-11-28 03:20:55,417][87424] Updated weights for policy 0, policy_version 119746 (0.0012) -[2023-11-28 03:20:55,796][87424] Updated weights for policy 0, policy_version 119756 (0.0012) -[2023-11-28 03:20:56,176][87424] Updated weights for policy 0, policy_version 119766 (0.0007) -[2023-11-28 03:20:56,556][87424] Updated weights for policy 0, policy_version 119776 (0.0008) -[2023-11-28 03:20:57,165][87426] Updated weights for policy 1, policy_version 119590 (0.0011) -[2023-11-28 03:20:57,542][87426] Updated weights for policy 1, policy_version 119600 (0.0012) -[2023-11-28 03:20:57,918][87426] Updated weights for policy 1, policy_version 119610 (0.0011) -[2023-11-28 03:20:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 61284352. Throughput: 0: 2698.9, 1: 2772.2. Samples: 61297124. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:20:58,446][86177] Avg episode reward: [(0, '-507.070'), (1, '-543.850')] -[2023-11-28 03:20:58,903][87424] Updated weights for policy 0, policy_version 119786 (0.0007) -[2023-11-28 03:20:59,281][87424] Updated weights for policy 0, policy_version 119796 (0.0011) -[2023-11-28 03:20:59,648][87424] Updated weights for policy 0, policy_version 119806 (0.0008) -[2023-11-28 03:20:59,816][87426] Updated weights for policy 1, policy_version 119620 (0.0011) -[2023-11-28 03:21:00,196][87426] Updated weights for policy 1, policy_version 119630 (0.0012) -[2023-11-28 03:21:00,571][87426] Updated weights for policy 1, policy_version 119640 (0.0012) -[2023-11-28 03:21:01,530][87424] Updated weights for policy 0, policy_version 119816 (0.0011) -[2023-11-28 03:21:01,911][87424] Updated weights for policy 0, policy_version 119826 (0.0011) -[2023-11-28 03:21:02,293][87424] Updated weights for policy 0, policy_version 119836 (0.0011) -[2023-11-28 03:21:03,176][87426] Updated weights for policy 1, policy_version 119650 (0.0011) -[2023-11-28 03:21:03,444][86177] Fps is (10 sec: 5736.9, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61308928. Throughput: 0: 2716.9, 1: 2776.0. Samples: 61321900. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:03,445][86177] Avg episode reward: [(0, '-510.440'), (1, '-537.140')] -[2023-11-28 03:21:03,555][87426] Updated weights for policy 1, policy_version 119660 (0.0008) -[2023-11-28 03:21:03,934][87426] Updated weights for policy 1, policy_version 119670 (0.0008) -[2023-11-28 03:21:04,305][87426] Updated weights for policy 1, policy_version 119680 (0.0007) -[2023-11-28 03:21:04,653][87424] Updated weights for policy 0, policy_version 119846 (0.0011) -[2023-11-28 03:21:05,019][87424] Updated weights for policy 0, policy_version 119856 (0.0011) -[2023-11-28 03:21:05,398][87424] Updated weights for policy 0, policy_version 119866 (0.0009) -[2023-11-28 03:21:06,834][87426] Updated weights for policy 1, policy_version 119690 (0.0010) -[2023-11-28 03:21:07,202][87426] Updated weights for policy 1, policy_version 119700 (0.0012) -[2023-11-28 03:21:07,447][87424] Updated weights for policy 0, policy_version 119876 (0.0009) -[2023-11-28 03:21:07,583][87426] Updated weights for policy 1, policy_version 119710 (0.0011) -[2023-11-28 03:21:07,831][87424] Updated weights for policy 0, policy_version 119886 (0.0008) -[2023-11-28 03:21:08,219][87424] Updated weights for policy 0, policy_version 119896 (0.0007) -[2023-11-28 03:21:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 61333504. Throughput: 0: 2727.7, 1: 2751.2. Samples: 61353656. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:08,445][86177] Avg episode reward: [(0, '-505.140'), (1, '-529.740')] -[2023-11-28 03:21:09,550][87426] Updated weights for policy 1, policy_version 119720 (0.0012) -[2023-11-28 03:21:09,931][87426] Updated weights for policy 1, policy_version 119730 (0.0011) -[2023-11-28 03:21:10,197][87424] Updated weights for policy 0, policy_version 119906 (0.0008) -[2023-11-28 03:21:10,306][87426] Updated weights for policy 1, policy_version 119740 (0.0011) -[2023-11-28 03:21:10,575][87424] Updated weights for policy 0, policy_version 119916 (0.0009) -[2023-11-28 03:21:10,965][87424] Updated weights for policy 0, policy_version 119926 (0.0008) -[2023-11-28 03:21:11,350][87424] Updated weights for policy 0, policy_version 119936 (0.0008) -[2023-11-28 03:21:12,528][87426] Updated weights for policy 1, policy_version 119750 (0.0009) -[2023-11-28 03:21:12,924][87426] Updated weights for policy 1, policy_version 119760 (0.0009) -[2023-11-28 03:21:13,301][87426] Updated weights for policy 1, policy_version 119770 (0.0012) -[2023-11-28 03:21:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 61358080. Throughput: 0: 2700.6, 1: 2733.9. Samples: 61377284. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:13,445][86177] Avg episode reward: [(0, '-503.590'), (1, '-516.580')] -[2023-11-28 03:21:13,826][87424] Updated weights for policy 0, policy_version 119946 (0.0011) -[2023-11-28 03:21:14,222][87424] Updated weights for policy 0, policy_version 119956 (0.0012) -[2023-11-28 03:21:14,599][87424] Updated weights for policy 0, policy_version 119966 (0.0011) -[2023-11-28 03:21:15,610][87426] Updated weights for policy 1, policy_version 119780 (0.0010) -[2023-11-28 03:21:15,999][87426] Updated weights for policy 1, policy_version 119790 (0.0008) -[2023-11-28 03:21:16,368][87426] Updated weights for policy 1, policy_version 119800 (0.0007) -[2023-11-28 03:21:16,716][87424] Updated weights for policy 0, policy_version 119976 (0.0011) -[2023-11-28 03:21:17,108][87424] Updated weights for policy 0, policy_version 119986 (0.0011) -[2023-11-28 03:21:17,478][87424] Updated weights for policy 0, policy_version 119996 (0.0012) -[2023-11-28 03:21:18,082][87426] Updated weights for policy 1, policy_version 119810 (0.0008) -[2023-11-28 03:21:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61390848. Throughput: 0: 2697.8, 1: 2745.1. Samples: 61402144. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:18,445][86177] Avg episode reward: [(0, '-502.510'), (1, '-544.650')] -[2023-11-28 03:21:18,472][87426] Updated weights for policy 1, policy_version 119820 (0.0012) -[2023-11-28 03:21:18,847][87426] Updated weights for policy 1, policy_version 119830 (0.0012) -[2023-11-28 03:21:19,220][87426] Updated weights for policy 1, policy_version 119840 (0.0009) -[2023-11-28 03:21:19,432][87424] Updated weights for policy 0, policy_version 120006 (0.0011) -[2023-11-28 03:21:19,812][87424] Updated weights for policy 0, policy_version 120016 (0.0010) -[2023-11-28 03:21:20,192][87424] Updated weights for policy 0, policy_version 120026 (0.0009) -[2023-11-28 03:21:21,578][87426] Updated weights for policy 1, policy_version 119850 (0.0011) -[2023-11-28 03:21:21,947][87426] Updated weights for policy 1, policy_version 119860 (0.0010) -[2023-11-28 03:21:22,328][87426] Updated weights for policy 1, policy_version 119870 (0.0011) -[2023-11-28 03:21:22,688][87424] Updated weights for policy 0, policy_version 120036 (0.0010) -[2023-11-28 03:21:23,078][87424] Updated weights for policy 0, policy_version 120046 (0.0010) -[2023-11-28 03:21:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 61415424. Throughput: 0: 2702.0, 1: 2742.5. Samples: 61434756. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:23,445][86177] Avg episode reward: [(0, '-504.330'), (1, '-545.600')] -[2023-11-28 03:21:23,451][87424] Updated weights for policy 0, policy_version 120056 (0.0009) -[2023-11-28 03:21:24,985][87426] Updated weights for policy 1, policy_version 119880 (0.0011) -[2023-11-28 03:21:25,365][87426] Updated weights for policy 1, policy_version 119890 (0.0007) -[2023-11-28 03:21:25,522][87424] Updated weights for policy 0, policy_version 120066 (0.0008) -[2023-11-28 03:21:25,746][87426] Updated weights for policy 1, policy_version 119900 (0.0009) -[2023-11-28 03:21:25,911][87424] Updated weights for policy 0, policy_version 120076 (0.0012) -[2023-11-28 03:21:26,294][87424] Updated weights for policy 0, policy_version 120086 (0.0012) -[2023-11-28 03:21:26,677][87424] Updated weights for policy 0, policy_version 120096 (0.0012) -[2023-11-28 03:21:27,655][87426] Updated weights for policy 1, policy_version 119910 (0.0010) -[2023-11-28 03:21:28,035][87426] Updated weights for policy 1, policy_version 119920 (0.0012) -[2023-11-28 03:21:28,413][87426] Updated weights for policy 1, policy_version 119930 (0.0011) -[2023-11-28 03:21:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 61440000. Throughput: 0: 2724.1, 1: 2749.5. Samples: 61460400. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:28,445][86177] Avg episode reward: [(0, '-502.990'), (1, '-538.090')] -[2023-11-28 03:21:28,552][87424] Updated weights for policy 0, policy_version 120106 (0.0012) -[2023-11-28 03:21:28,928][87424] Updated weights for policy 0, policy_version 120116 (0.0012) -[2023-11-28 03:21:29,308][87424] Updated weights for policy 0, policy_version 120126 (0.0011) -[2023-11-28 03:21:30,867][87426] Updated weights for policy 1, policy_version 119940 (0.0012) -[2023-11-28 03:21:31,245][87426] Updated weights for policy 1, policy_version 119950 (0.0011) -[2023-11-28 03:21:31,629][87426] Updated weights for policy 1, policy_version 119960 (0.0010) -[2023-11-28 03:21:31,634][87424] Updated weights for policy 0, policy_version 120136 (0.0012) -[2023-11-28 03:21:32,017][87424] Updated weights for policy 0, policy_version 120146 (0.0012) -[2023-11-28 03:21:32,400][87424] Updated weights for policy 0, policy_version 120156 (0.0012) -[2023-11-28 03:21:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61472768. Throughput: 0: 2743.3, 1: 2723.0. Samples: 61485196. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:33,446][86177] Avg episode reward: [(0, '-513.310'), (1, '-548.020')] -[2023-11-28 03:21:33,670][87426] Updated weights for policy 1, policy_version 119970 (0.0011) -[2023-11-28 03:21:34,048][87426] Updated weights for policy 1, policy_version 119980 (0.0012) -[2023-11-28 03:21:34,425][87426] Updated weights for policy 1, policy_version 119990 (0.0009) -[2023-11-28 03:21:34,691][87424] Updated weights for policy 0, policy_version 120166 (0.0009) -[2023-11-28 03:21:34,812][87426] Updated weights for policy 1, policy_version 120000 (0.0009) -[2023-11-28 03:21:35,076][87424] Updated weights for policy 0, policy_version 120176 (0.0012) -[2023-11-28 03:21:35,450][87424] Updated weights for policy 0, policy_version 120186 (0.0012) -[2023-11-28 03:21:36,634][87426] Updated weights for policy 1, policy_version 120010 (0.0011) -[2023-11-28 03:21:37,007][87426] Updated weights for policy 1, policy_version 120020 (0.0012) -[2023-11-28 03:21:37,372][87424] Updated weights for policy 0, policy_version 120196 (0.0011) -[2023-11-28 03:21:37,387][87426] Updated weights for policy 1, policy_version 120030 (0.0011) -[2023-11-28 03:21:37,753][87424] Updated weights for policy 0, policy_version 120206 (0.0009) -[2023-11-28 03:21:38,139][87424] Updated weights for policy 0, policy_version 120216 (0.0008) -[2023-11-28 03:21:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61505536. Throughput: 0: 2742.0, 1: 2714.7. Samples: 61517848. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:38,445][86177] Avg episode reward: [(0, '-515.870'), (1, '-553.700')] -[2023-11-28 03:21:39,363][87426] Updated weights for policy 1, policy_version 120040 (0.0012) -[2023-11-28 03:21:39,741][87426] Updated weights for policy 1, policy_version 120050 (0.0011) -[2023-11-28 03:21:40,126][87426] Updated weights for policy 1, policy_version 120060 (0.0011) -[2023-11-28 03:21:40,595][87424] Updated weights for policy 0, policy_version 120226 (0.0010) -[2023-11-28 03:21:40,968][87424] Updated weights for policy 0, policy_version 120236 (0.0008) -[2023-11-28 03:21:41,344][87424] Updated weights for policy 0, policy_version 120246 (0.0008) -[2023-11-28 03:21:41,728][87424] Updated weights for policy 0, policy_version 120256 (0.0010) -[2023-11-28 03:21:42,651][87426] Updated weights for policy 1, policy_version 120070 (0.0009) -[2023-11-28 03:21:43,028][87426] Updated weights for policy 1, policy_version 120080 (0.0010) -[2023-11-28 03:21:43,400][87426] Updated weights for policy 1, policy_version 120090 (0.0012) -[2023-11-28 03:21:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 61521920. Throughput: 0: 2733.7, 1: 2706.7. Samples: 61541940. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:43,445][86177] Avg episode reward: [(0, '-514.440'), (1, '-567.060')] -[2023-11-28 03:21:44,261][87424] Updated weights for policy 0, policy_version 120266 (0.0010) -[2023-11-28 03:21:44,642][87424] Updated weights for policy 0, policy_version 120276 (0.0011) -[2023-11-28 03:21:45,033][87424] Updated weights for policy 0, policy_version 120286 (0.0012) -[2023-11-28 03:21:45,168][87426] Updated weights for policy 1, policy_version 120100 (0.0010) -[2023-11-28 03:21:45,550][87426] Updated weights for policy 1, policy_version 120110 (0.0011) -[2023-11-28 03:21:45,923][87426] Updated weights for policy 1, policy_version 120120 (0.0012) -[2023-11-28 03:21:46,726][87424] Updated weights for policy 0, policy_version 120296 (0.0011) -[2023-11-28 03:21:47,104][87424] Updated weights for policy 0, policy_version 120306 (0.0010) -[2023-11-28 03:21:47,496][87424] Updated weights for policy 0, policy_version 120316 (0.0008) -[2023-11-28 03:21:48,303][87426] Updated weights for policy 1, policy_version 120130 (0.0012) -[2023-11-28 03:21:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61554688. Throughput: 0: 2728.8, 1: 2702.9. Samples: 61566328. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:48,445][86177] Avg episode reward: [(0, '-525.120'), (1, '-569.770')] -[2023-11-28 03:21:48,676][87426] Updated weights for policy 1, policy_version 120140 (0.0012) -[2023-11-28 03:21:49,050][87426] Updated weights for policy 1, policy_version 120150 (0.0010) -[2023-11-28 03:21:49,257][87424] Updated weights for policy 0, policy_version 120326 (0.0009) -[2023-11-28 03:21:49,434][87426] Updated weights for policy 1, policy_version 120160 (0.0008) -[2023-11-28 03:21:49,636][87424] Updated weights for policy 0, policy_version 120336 (0.0012) -[2023-11-28 03:21:50,026][87424] Updated weights for policy 0, policy_version 120346 (0.0012) -[2023-11-28 03:21:51,416][87426] Updated weights for policy 1, policy_version 120170 (0.0012) -[2023-11-28 03:21:51,800][87426] Updated weights for policy 1, policy_version 120180 (0.0011) -[2023-11-28 03:21:52,181][87426] Updated weights for policy 1, policy_version 120190 (0.0008) -[2023-11-28 03:21:52,452][87424] Updated weights for policy 0, policy_version 120356 (0.0012) -[2023-11-28 03:21:52,838][87424] Updated weights for policy 0, policy_version 120366 (0.0010) -[2023-11-28 03:21:53,226][87424] Updated weights for policy 0, policy_version 120376 (0.0009) -[2023-11-28 03:21:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.7, 300 sec: 5442.8). Total num frames: 61579264. Throughput: 0: 2735.5, 1: 2727.7. Samples: 61599500. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:21:53,445][86177] Avg episode reward: [(0, '-515.780'), (1, '-560.920')] -[2023-11-28 03:21:54,734][87426] Updated weights for policy 1, policy_version 120200 (0.0009) -[2023-11-28 03:21:55,116][87426] Updated weights for policy 1, policy_version 120210 (0.0008) -[2023-11-28 03:21:55,407][87424] Updated weights for policy 0, policy_version 120386 (0.0010) -[2023-11-28 03:21:55,500][87426] Updated weights for policy 1, policy_version 120220 (0.0010) -[2023-11-28 03:21:55,794][87424] Updated weights for policy 0, policy_version 120396 (0.0009) -[2023-11-28 03:21:56,176][87424] Updated weights for policy 0, policy_version 120406 (0.0007) -[2023-11-28 03:21:56,578][87424] Updated weights for policy 0, policy_version 120416 (0.0008) -[2023-11-28 03:21:57,847][87426] Updated weights for policy 1, policy_version 120230 (0.0008) -[2023-11-28 03:21:58,221][87426] Updated weights for policy 1, policy_version 120240 (0.0008) -[2023-11-28 03:21:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 61603840. Throughput: 0: 2740.9, 1: 2740.2. Samples: 61623932. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:21:58,445][86177] Avg episode reward: [(0, '-523.570'), (1, '-539.850')] -[2023-11-28 03:21:58,604][87426] Updated weights for policy 1, policy_version 120250 (0.0007) -[2023-11-28 03:21:58,757][87424] Updated weights for policy 0, policy_version 120426 (0.0008) -[2023-11-28 03:21:59,135][87424] Updated weights for policy 0, policy_version 120436 (0.0008) -[2023-11-28 03:21:59,522][87424] Updated weights for policy 0, policy_version 120446 (0.0007) -[2023-11-28 03:22:00,663][87426] Updated weights for policy 1, policy_version 120260 (0.0007) -[2023-11-28 03:22:01,045][87426] Updated weights for policy 1, policy_version 120270 (0.0009) -[2023-11-28 03:22:01,297][87424] Updated weights for policy 0, policy_version 120456 (0.0011) -[2023-11-28 03:22:01,421][87426] Updated weights for policy 1, policy_version 120280 (0.0007) -[2023-11-28 03:22:01,684][87424] Updated weights for policy 0, policy_version 120466 (0.0011) -[2023-11-28 03:22:02,069][87424] Updated weights for policy 0, policy_version 120476 (0.0011) -[2023-11-28 03:22:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61636608. Throughput: 0: 2743.1, 1: 2716.2. Samples: 61647812. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:03,445][86177] Avg episode reward: [(0, '-531.250'), (1, '-540.740')] -[2023-11-28 03:22:03,838][87426] Updated weights for policy 1, policy_version 120290 (0.0009) -[2023-11-28 03:22:04,216][87426] Updated weights for policy 1, policy_version 120300 (0.0010) -[2023-11-28 03:22:04,467][87424] Updated weights for policy 0, policy_version 120486 (0.0010) -[2023-11-28 03:22:04,602][87426] Updated weights for policy 1, policy_version 120310 (0.0008) -[2023-11-28 03:22:04,843][87424] Updated weights for policy 0, policy_version 120496 (0.0008) -[2023-11-28 03:22:04,988][87426] Updated weights for policy 1, policy_version 120320 (0.0010) -[2023-11-28 03:22:05,237][87424] Updated weights for policy 0, policy_version 120506 (0.0008) -[2023-11-28 03:22:07,337][87426] Updated weights for policy 1, policy_version 120330 (0.0012) -[2023-11-28 03:22:07,728][87426] Updated weights for policy 1, policy_version 120340 (0.0012) -[2023-11-28 03:22:07,733][87424] Updated weights for policy 0, policy_version 120516 (0.0008) -[2023-11-28 03:22:08,107][87426] Updated weights for policy 1, policy_version 120350 (0.0011) -[2023-11-28 03:22:08,121][87424] Updated weights for policy 0, policy_version 120526 (0.0008) -[2023-11-28 03:22:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61661184. Throughput: 0: 2740.5, 1: 2714.6. Samples: 61680236. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:08,445][86177] Avg episode reward: [(0, '-523.820'), (1, '-526.690')] -[2023-11-28 03:22:08,502][87424] Updated weights for policy 0, policy_version 120536 (0.0007) -[2023-11-28 03:22:09,961][87426] Updated weights for policy 1, policy_version 120360 (0.0012) -[2023-11-28 03:22:10,342][87426] Updated weights for policy 1, policy_version 120370 (0.0009) -[2023-11-28 03:22:10,561][87424] Updated weights for policy 0, policy_version 120546 (0.0008) -[2023-11-28 03:22:10,720][87426] Updated weights for policy 1, policy_version 120380 (0.0011) -[2023-11-28 03:22:10,948][87424] Updated weights for policy 0, policy_version 120556 (0.0011) -[2023-11-28 03:22:11,326][87424] Updated weights for policy 0, policy_version 120566 (0.0009) -[2023-11-28 03:22:11,711][87424] Updated weights for policy 0, policy_version 120576 (0.0009) -[2023-11-28 03:22:12,834][87426] Updated weights for policy 1, policy_version 120390 (0.0011) -[2023-11-28 03:22:13,215][87426] Updated weights for policy 1, policy_version 120400 (0.0011) -[2023-11-28 03:22:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 61685760. Throughput: 0: 2722.0, 1: 2704.5. Samples: 61704592. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:13,445][86177] Avg episode reward: [(0, '-530.500'), (1, '-542.840')] -[2023-11-28 03:22:13,605][87426] Updated weights for policy 1, policy_version 120410 (0.0011) -[2023-11-28 03:22:13,909][87424] Updated weights for policy 0, policy_version 120586 (0.0012) -[2023-11-28 03:22:14,291][87424] Updated weights for policy 0, policy_version 120596 (0.0011) -[2023-11-28 03:22:14,694][87424] Updated weights for policy 0, policy_version 120606 (0.0012) -[2023-11-28 03:22:15,760][87426] Updated weights for policy 1, policy_version 120420 (0.0011) -[2023-11-28 03:22:16,134][87426] Updated weights for policy 1, policy_version 120430 (0.0011) -[2023-11-28 03:22:16,509][87426] Updated weights for policy 1, policy_version 120440 (0.0011) -[2023-11-28 03:22:16,791][87424] Updated weights for policy 0, policy_version 120616 (0.0012) -[2023-11-28 03:22:17,183][87424] Updated weights for policy 0, policy_version 120626 (0.0011) -[2023-11-28 03:22:17,569][87424] Updated weights for policy 0, policy_version 120636 (0.0012) -[2023-11-28 03:22:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 61718528. Throughput: 0: 2710.4, 1: 2727.0. Samples: 61729880. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:18,445][86177] Avg episode reward: [(0, '-517.310'), (1, '-563.980')] -[2023-11-28 03:22:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000120640_30883840.pth... -[2023-11-28 03:22:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000120448_30834688.pth... -[2023-11-28 03:22:18,493][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000117888_30179328.pth -[2023-11-28 03:22:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000118112_30236672.pth -[2023-11-28 03:22:18,836][87426] Updated weights for policy 1, policy_version 120450 (0.0012) -[2023-11-28 03:22:19,220][87426] Updated weights for policy 1, policy_version 120460 (0.0010) -[2023-11-28 03:22:19,371][87424] Updated weights for policy 0, policy_version 120646 (0.0012) -[2023-11-28 03:22:19,602][87426] Updated weights for policy 1, policy_version 120470 (0.0011) -[2023-11-28 03:22:19,764][87424] Updated weights for policy 0, policy_version 120656 (0.0009) -[2023-11-28 03:22:19,986][87426] Updated weights for policy 1, policy_version 120480 (0.0011) -[2023-11-28 03:22:20,139][87424] Updated weights for policy 0, policy_version 120666 (0.0009) -[2023-11-28 03:22:22,395][87426] Updated weights for policy 1, policy_version 120490 (0.0010) -[2023-11-28 03:22:22,517][87424] Updated weights for policy 0, policy_version 120676 (0.0008) -[2023-11-28 03:22:22,771][87426] Updated weights for policy 1, policy_version 120500 (0.0008) -[2023-11-28 03:22:22,906][87424] Updated weights for policy 0, policy_version 120686 (0.0009) -[2023-11-28 03:22:23,148][87426] Updated weights for policy 1, policy_version 120510 (0.0010) -[2023-11-28 03:22:23,285][87424] Updated weights for policy 0, policy_version 120696 (0.0012) -[2023-11-28 03:22:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61743104. Throughput: 0: 2735.2, 1: 2692.0. Samples: 61762072. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:23,445][86177] Avg episode reward: [(0, '-543.820'), (1, '-556.310')] -[2023-11-28 03:22:24,869][87426] Updated weights for policy 1, policy_version 120520 (0.0007) -[2023-11-28 03:22:25,233][87426] Updated weights for policy 1, policy_version 120530 (0.0008) -[2023-11-28 03:22:25,482][87424] Updated weights for policy 0, policy_version 120706 (0.0012) -[2023-11-28 03:22:25,611][87426] Updated weights for policy 1, policy_version 120540 (0.0008) -[2023-11-28 03:22:25,859][87424] Updated weights for policy 0, policy_version 120716 (0.0012) -[2023-11-28 03:22:26,236][87424] Updated weights for policy 0, policy_version 120726 (0.0009) -[2023-11-28 03:22:26,627][87424] Updated weights for policy 0, policy_version 120736 (0.0008) -[2023-11-28 03:22:27,553][87426] Updated weights for policy 1, policy_version 120550 (0.0007) -[2023-11-28 03:22:27,934][87426] Updated weights for policy 1, policy_version 120560 (0.0010) -[2023-11-28 03:22:28,313][87426] Updated weights for policy 1, policy_version 120570 (0.0012) -[2023-11-28 03:22:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 61767680. Throughput: 0: 2739.7, 1: 2708.9. Samples: 61787128. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:28,445][86177] Avg episode reward: [(0, '-529.700'), (1, '-559.090')] -[2023-11-28 03:22:28,708][87424] Updated weights for policy 0, policy_version 120746 (0.0011) -[2023-11-28 03:22:29,097][87424] Updated weights for policy 0, policy_version 120756 (0.0010) -[2023-11-28 03:22:29,484][87424] Updated weights for policy 0, policy_version 120766 (0.0012) -[2023-11-28 03:22:30,359][87426] Updated weights for policy 1, policy_version 120580 (0.0010) -[2023-11-28 03:22:30,734][87426] Updated weights for policy 1, policy_version 120590 (0.0011) -[2023-11-28 03:22:31,118][87426] Updated weights for policy 1, policy_version 120600 (0.0011) -[2023-11-28 03:22:31,665][87424] Updated weights for policy 0, policy_version 120776 (0.0011) -[2023-11-28 03:22:32,053][87424] Updated weights for policy 0, policy_version 120786 (0.0011) -[2023-11-28 03:22:32,437][87424] Updated weights for policy 0, policy_version 120796 (0.0011) -[2023-11-28 03:22:33,374][87426] Updated weights for policy 1, policy_version 120610 (0.0012) -[2023-11-28 03:22:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 61800448. Throughput: 0: 2738.1, 1: 2724.2. Samples: 61812132. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:33,445][86177] Avg episode reward: [(0, '-531.990'), (1, '-536.050')] -[2023-11-28 03:22:33,758][87426] Updated weights for policy 1, policy_version 120620 (0.0011) -[2023-11-28 03:22:34,134][87426] Updated weights for policy 1, policy_version 120630 (0.0011) -[2023-11-28 03:22:34,193][87424] Updated weights for policy 0, policy_version 120806 (0.0009) -[2023-11-28 03:22:34,514][87426] Updated weights for policy 1, policy_version 120640 (0.0007) -[2023-11-28 03:22:34,576][87424] Updated weights for policy 0, policy_version 120816 (0.0007) -[2023-11-28 03:22:34,969][87424] Updated weights for policy 0, policy_version 120826 (0.0011) -[2023-11-28 03:22:36,698][87426] Updated weights for policy 1, policy_version 120650 (0.0011) -[2023-11-28 03:22:37,083][87426] Updated weights for policy 1, policy_version 120660 (0.0011) -[2023-11-28 03:22:37,321][87424] Updated weights for policy 0, policy_version 120836 (0.0011) -[2023-11-28 03:22:37,444][87426] Updated weights for policy 1, policy_version 120670 (0.0011) -[2023-11-28 03:22:37,717][87424] Updated weights for policy 0, policy_version 120846 (0.0012) -[2023-11-28 03:22:38,096][87424] Updated weights for policy 0, policy_version 120856 (0.0012) -[2023-11-28 03:22:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 61833216. Throughput: 0: 2725.5, 1: 2720.9. Samples: 61844588. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:38,445][86177] Avg episode reward: [(0, '-527.060'), (1, '-550.980')] -[2023-11-28 03:22:39,416][87426] Updated weights for policy 1, policy_version 120680 (0.0010) -[2023-11-28 03:22:39,787][87426] Updated weights for policy 1, policy_version 120690 (0.0008) -[2023-11-28 03:22:40,169][87426] Updated weights for policy 1, policy_version 120700 (0.0009) -[2023-11-28 03:22:40,689][87424] Updated weights for policy 0, policy_version 120866 (0.0011) -[2023-11-28 03:22:41,085][87424] Updated weights for policy 0, policy_version 120876 (0.0008) -[2023-11-28 03:22:41,457][87424] Updated weights for policy 0, policy_version 120886 (0.0008) -[2023-11-28 03:22:41,842][87424] Updated weights for policy 0, policy_version 120896 (0.0010) -[2023-11-28 03:22:42,548][87426] Updated weights for policy 1, policy_version 120710 (0.0008) -[2023-11-28 03:22:42,919][87426] Updated weights for policy 1, policy_version 120720 (0.0011) -[2023-11-28 03:22:43,298][87426] Updated weights for policy 1, policy_version 120730 (0.0008) -[2023-11-28 03:22:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 61849600. Throughput: 0: 2731.1, 1: 2717.3. Samples: 61869112. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:43,445][86177] Avg episode reward: [(0, '-501.550'), (1, '-545.980')] -[2023-11-28 03:22:44,160][87424] Updated weights for policy 0, policy_version 120906 (0.0007) -[2023-11-28 03:22:44,553][87424] Updated weights for policy 0, policy_version 120916 (0.0008) -[2023-11-28 03:22:44,936][87424] Updated weights for policy 0, policy_version 120926 (0.0008) -[2023-11-28 03:22:45,877][87426] Updated weights for policy 1, policy_version 120740 (0.0009) -[2023-11-28 03:22:46,257][87426] Updated weights for policy 1, policy_version 120750 (0.0011) -[2023-11-28 03:22:46,633][87426] Updated weights for policy 1, policy_version 120760 (0.0012) -[2023-11-28 03:22:46,768][87424] Updated weights for policy 0, policy_version 120936 (0.0010) -[2023-11-28 03:22:47,153][87424] Updated weights for policy 0, policy_version 120946 (0.0010) -[2023-11-28 03:22:47,535][87424] Updated weights for policy 0, policy_version 120956 (0.0011) -[2023-11-28 03:22:48,348][87426] Updated weights for policy 1, policy_version 120770 (0.0012) -[2023-11-28 03:22:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 61882368. Throughput: 0: 2728.3, 1: 2713.9. Samples: 61892708. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:48,445][86177] Avg episode reward: [(0, '-497.950'), (1, '-636.350')] -[2023-11-28 03:22:48,725][87426] Updated weights for policy 1, policy_version 120780 (0.0012) -[2023-11-28 03:22:49,109][87426] Updated weights for policy 1, policy_version 120790 (0.0010) -[2023-11-28 03:22:49,164][87424] Updated weights for policy 0, policy_version 120966 (0.0010) -[2023-11-28 03:22:49,486][87426] Updated weights for policy 1, policy_version 120800 (0.0012) -[2023-11-28 03:22:49,548][87424] Updated weights for policy 0, policy_version 120976 (0.0007) -[2023-11-28 03:22:49,935][87424] Updated weights for policy 0, policy_version 120986 (0.0009) -[2023-11-28 03:22:51,493][87426] Updated weights for policy 1, policy_version 120810 (0.0012) -[2023-11-28 03:22:51,867][87426] Updated weights for policy 1, policy_version 120820 (0.0012) -[2023-11-28 03:22:52,240][87426] Updated weights for policy 1, policy_version 120830 (0.0011) -[2023-11-28 03:22:52,298][87424] Updated weights for policy 0, policy_version 120996 (0.0012) -[2023-11-28 03:22:52,685][87424] Updated weights for policy 0, policy_version 121006 (0.0012) -[2023-11-28 03:22:53,074][87424] Updated weights for policy 0, policy_version 121016 (0.0012) -[2023-11-28 03:22:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 61915136. Throughput: 0: 2736.1, 1: 2732.7. Samples: 61926332. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:53,445][86177] Avg episode reward: [(0, '-497.130'), (1, '-634.950')] -[2023-11-28 03:22:54,571][87426] Updated weights for policy 1, policy_version 120840 (0.0008) -[2023-11-28 03:22:54,945][87426] Updated weights for policy 1, policy_version 120850 (0.0011) -[2023-11-28 03:22:55,127][87424] Updated weights for policy 0, policy_version 121026 (0.0012) -[2023-11-28 03:22:55,325][87426] Updated weights for policy 1, policy_version 120860 (0.0008) -[2023-11-28 03:22:55,508][87424] Updated weights for policy 0, policy_version 121036 (0.0011) -[2023-11-28 03:22:55,893][87424] Updated weights for policy 0, policy_version 121046 (0.0012) -[2023-11-28 03:22:56,278][87424] Updated weights for policy 0, policy_version 121056 (0.0012) -[2023-11-28 03:22:56,922][87426] Updated weights for policy 1, policy_version 120870 (0.0010) -[2023-11-28 03:22:57,302][87426] Updated weights for policy 1, policy_version 120880 (0.0012) -[2023-11-28 03:22:57,682][87426] Updated weights for policy 1, policy_version 120890 (0.0012) -[2023-11-28 03:22:57,934][87424] Updated weights for policy 0, policy_version 121066 (0.0012) -[2023-11-28 03:22:58,317][87424] Updated weights for policy 0, policy_version 121076 (0.0012) -[2023-11-28 03:22:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 61939712. Throughput: 0: 2749.5, 1: 2751.1. Samples: 61952120. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 03:22:58,446][86177] Avg episode reward: [(0, '-501.580'), (1, '-605.880')] -[2023-11-28 03:22:58,706][87424] Updated weights for policy 0, policy_version 121086 (0.0009) -[2023-11-28 03:23:00,059][87426] Updated weights for policy 1, policy_version 120900 (0.0012) -[2023-11-28 03:23:00,429][87426] Updated weights for policy 1, policy_version 120910 (0.0012) -[2023-11-28 03:23:00,801][87426] Updated weights for policy 1, policy_version 120920 (0.0012) -[2023-11-28 03:23:00,941][87424] Updated weights for policy 0, policy_version 121096 (0.0007) -[2023-11-28 03:23:01,336][87424] Updated weights for policy 0, policy_version 121106 (0.0007) -[2023-11-28 03:23:01,704][87424] Updated weights for policy 0, policy_version 121116 (0.0009) -[2023-11-28 03:23:03,118][87426] Updated weights for policy 1, policy_version 120930 (0.0011) -[2023-11-28 03:23:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 61964288. Throughput: 0: 2769.8, 1: 2749.1. Samples: 61978228. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:03,445][86177] Avg episode reward: [(0, '-510.040'), (1, '-554.620')] -[2023-11-28 03:23:03,505][87426] Updated weights for policy 1, policy_version 120940 (0.0009) -[2023-11-28 03:23:03,760][87424] Updated weights for policy 0, policy_version 121126 (0.0011) -[2023-11-28 03:23:03,872][87426] Updated weights for policy 1, policy_version 120950 (0.0008) -[2023-11-28 03:23:04,147][87424] Updated weights for policy 0, policy_version 121136 (0.0011) -[2023-11-28 03:23:04,249][87426] Updated weights for policy 1, policy_version 120960 (0.0009) -[2023-11-28 03:23:04,531][87424] Updated weights for policy 0, policy_version 121146 (0.0009) -[2023-11-28 03:23:06,831][87426] Updated weights for policy 1, policy_version 120970 (0.0011) -[2023-11-28 03:23:06,908][87424] Updated weights for policy 0, policy_version 121156 (0.0010) -[2023-11-28 03:23:07,218][87426] Updated weights for policy 1, policy_version 120980 (0.0010) -[2023-11-28 03:23:07,290][87424] Updated weights for policy 0, policy_version 121166 (0.0008) -[2023-11-28 03:23:07,592][87426] Updated weights for policy 1, policy_version 120990 (0.0010) -[2023-11-28 03:23:07,674][87424] Updated weights for policy 0, policy_version 121176 (0.0009) -[2023-11-28 03:23:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 61997056. Throughput: 0: 2769.2, 1: 2768.4. Samples: 62011260. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:08,445][86177] Avg episode reward: [(0, '-512.760'), (1, '-500.660')] -[2023-11-28 03:23:09,658][87424] Updated weights for policy 0, policy_version 121186 (0.0008) -[2023-11-28 03:23:09,689][87426] Updated weights for policy 1, policy_version 121000 (0.0011) -[2023-11-28 03:23:10,040][87424] Updated weights for policy 0, policy_version 121196 (0.0010) -[2023-11-28 03:23:10,060][87426] Updated weights for policy 1, policy_version 121010 (0.0011) -[2023-11-28 03:23:10,421][87424] Updated weights for policy 0, policy_version 121206 (0.0011) -[2023-11-28 03:23:10,436][87426] Updated weights for policy 1, policy_version 121020 (0.0009) -[2023-11-28 03:23:10,804][87424] Updated weights for policy 0, policy_version 121216 (0.0011) -[2023-11-28 03:23:12,225][87426] Updated weights for policy 1, policy_version 121030 (0.0010) -[2023-11-28 03:23:12,593][87426] Updated weights for policy 1, policy_version 121040 (0.0011) -[2023-11-28 03:23:12,764][87424] Updated weights for policy 0, policy_version 121226 (0.0011) -[2023-11-28 03:23:12,973][87426] Updated weights for policy 1, policy_version 121050 (0.0011) -[2023-11-28 03:23:13,148][87424] Updated weights for policy 0, policy_version 121236 (0.0012) -[2023-11-28 03:23:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 62021632. Throughput: 0: 2780.8, 1: 2761.1. Samples: 62036512. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:13,445][86177] Avg episode reward: [(0, '-518.080'), (1, '-513.620')] -[2023-11-28 03:23:13,536][87424] Updated weights for policy 0, policy_version 121246 (0.0011) -[2023-11-28 03:23:15,046][87426] Updated weights for policy 1, policy_version 121060 (0.0011) -[2023-11-28 03:23:15,314][87424] Updated weights for policy 0, policy_version 121256 (0.0010) -[2023-11-28 03:23:15,421][87426] Updated weights for policy 1, policy_version 121070 (0.0011) -[2023-11-28 03:23:15,697][87424] Updated weights for policy 0, policy_version 121266 (0.0009) -[2023-11-28 03:23:15,807][87426] Updated weights for policy 1, policy_version 121080 (0.0011) -[2023-11-28 03:23:16,087][87424] Updated weights for policy 0, policy_version 121276 (0.0012) -[2023-11-28 03:23:17,666][87426] Updated weights for policy 1, policy_version 121090 (0.0012) -[2023-11-28 03:23:17,749][87424] Updated weights for policy 0, policy_version 121286 (0.0011) -[2023-11-28 03:23:18,045][87426] Updated weights for policy 1, policy_version 121100 (0.0012) -[2023-11-28 03:23:18,126][87424] Updated weights for policy 0, policy_version 121296 (0.0007) -[2023-11-28 03:23:18,425][87426] Updated weights for policy 1, policy_version 121110 (0.0011) -[2023-11-28 03:23:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 62046208. Throughput: 0: 2811.5, 1: 2747.4. Samples: 62062284. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:18,446][86177] Avg episode reward: [(0, '-514.150'), (1, '-514.840')] -[2023-11-28 03:23:18,510][87424] Updated weights for policy 0, policy_version 121306 (0.0008) -[2023-11-28 03:23:18,796][87426] Updated weights for policy 1, policy_version 121120 (0.0011) -[2023-11-28 03:23:21,012][87424] Updated weights for policy 0, policy_version 121316 (0.0009) -[2023-11-28 03:23:21,242][87426] Updated weights for policy 1, policy_version 121130 (0.0009) -[2023-11-28 03:23:21,396][87424] Updated weights for policy 0, policy_version 121326 (0.0011) -[2023-11-28 03:23:21,625][87426] Updated weights for policy 1, policy_version 121140 (0.0009) -[2023-11-28 03:23:21,780][87424] Updated weights for policy 0, policy_version 121336 (0.0012) -[2023-11-28 03:23:22,014][87426] Updated weights for policy 1, policy_version 121150 (0.0011) -[2023-11-28 03:23:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 62078976. Throughput: 0: 2806.4, 1: 2763.1. Samples: 62095216. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:23,445][86177] Avg episode reward: [(0, '-515.330'), (1, '-521.740')] -[2023-11-28 03:23:23,975][87424] Updated weights for policy 0, policy_version 121346 (0.0009) -[2023-11-28 03:23:24,357][87424] Updated weights for policy 0, policy_version 121356 (0.0011) -[2023-11-28 03:23:24,496][87426] Updated weights for policy 1, policy_version 121160 (0.0011) -[2023-11-28 03:23:24,737][87424] Updated weights for policy 0, policy_version 121366 (0.0007) -[2023-11-28 03:23:24,869][87426] Updated weights for policy 1, policy_version 121170 (0.0012) -[2023-11-28 03:23:25,128][87424] Updated weights for policy 0, policy_version 121376 (0.0007) -[2023-11-28 03:23:25,251][87426] Updated weights for policy 1, policy_version 121180 (0.0010) -[2023-11-28 03:23:27,013][87424] Updated weights for policy 0, policy_version 121386 (0.0012) -[2023-11-28 03:23:27,392][87424] Updated weights for policy 0, policy_version 121396 (0.0009) -[2023-11-28 03:23:27,629][87426] Updated weights for policy 1, policy_version 121190 (0.0010) -[2023-11-28 03:23:27,777][87424] Updated weights for policy 0, policy_version 121406 (0.0011) -[2023-11-28 03:23:28,000][87426] Updated weights for policy 1, policy_version 121200 (0.0012) -[2023-11-28 03:23:28,375][87426] Updated weights for policy 1, policy_version 121210 (0.0011) -[2023-11-28 03:23:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 62103552. Throughput: 0: 2802.0, 1: 2743.4. Samples: 62118652. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:28,445][86177] Avg episode reward: [(0, '-526.650'), (1, '-524.410')] -[2023-11-28 03:23:29,901][87424] Updated weights for policy 0, policy_version 121416 (0.0013) -[2023-11-28 03:23:30,269][87424] Updated weights for policy 0, policy_version 121426 (0.0012) -[2023-11-28 03:23:30,435][87426] Updated weights for policy 1, policy_version 121220 (0.0011) -[2023-11-28 03:23:30,657][87424] Updated weights for policy 0, policy_version 121436 (0.0011) -[2023-11-28 03:23:30,819][87426] Updated weights for policy 1, policy_version 121230 (0.0010) -[2023-11-28 03:23:31,193][87426] Updated weights for policy 1, policy_version 121240 (0.0010) -[2023-11-28 03:23:32,779][87424] Updated weights for policy 0, policy_version 121446 (0.0009) -[2023-11-28 03:23:33,169][87424] Updated weights for policy 0, policy_version 121456 (0.0009) -[2023-11-28 03:23:33,408][87426] Updated weights for policy 1, policy_version 121250 (0.0008) -[2023-11-28 03:23:33,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 62128128. Throughput: 0: 2826.2, 1: 2763.8. Samples: 62144260. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:33,446][86177] Avg episode reward: [(0, '-521.130'), (1, '-529.410')] -[2023-11-28 03:23:33,540][87424] Updated weights for policy 0, policy_version 121466 (0.0007) -[2023-11-28 03:23:33,791][87426] Updated weights for policy 1, policy_version 121260 (0.0012) -[2023-11-28 03:23:34,162][87426] Updated weights for policy 1, policy_version 121270 (0.0012) -[2023-11-28 03:23:34,539][87426] Updated weights for policy 1, policy_version 121280 (0.0011) -[2023-11-28 03:23:35,673][87424] Updated weights for policy 0, policy_version 121476 (0.0007) -[2023-11-28 03:23:36,068][87424] Updated weights for policy 0, policy_version 121486 (0.0012) -[2023-11-28 03:23:36,454][87424] Updated weights for policy 0, policy_version 121496 (0.0010) -[2023-11-28 03:23:36,687][87426] Updated weights for policy 1, policy_version 121290 (0.0010) -[2023-11-28 03:23:37,068][87426] Updated weights for policy 1, policy_version 121300 (0.0012) -[2023-11-28 03:23:37,440][87426] Updated weights for policy 1, policy_version 121310 (0.0012) -[2023-11-28 03:23:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62160896. Throughput: 0: 2826.0, 1: 2748.6. Samples: 62177188. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:38,445][86177] Avg episode reward: [(0, '-531.530'), (1, '-550.560')] -[2023-11-28 03:23:38,928][87424] Updated weights for policy 0, policy_version 121506 (0.0010) -[2023-11-28 03:23:39,309][87424] Updated weights for policy 0, policy_version 121516 (0.0012) -[2023-11-28 03:23:39,353][87426] Updated weights for policy 1, policy_version 121320 (0.0012) -[2023-11-28 03:23:39,682][87424] Updated weights for policy 0, policy_version 121526 (0.0011) -[2023-11-28 03:23:39,737][87426] Updated weights for policy 1, policy_version 121330 (0.0011) -[2023-11-28 03:23:40,064][87424] Updated weights for policy 0, policy_version 121536 (0.0012) -[2023-11-28 03:23:40,119][87426] Updated weights for policy 1, policy_version 121340 (0.0015) -[2023-11-28 03:23:41,941][87426] Updated weights for policy 1, policy_version 121350 (0.0012) -[2023-11-28 03:23:42,032][87424] Updated weights for policy 0, policy_version 121546 (0.0010) -[2023-11-28 03:23:42,327][87426] Updated weights for policy 1, policy_version 121360 (0.0010) -[2023-11-28 03:23:42,413][87424] Updated weights for policy 0, policy_version 121556 (0.0010) -[2023-11-28 03:23:42,701][87426] Updated weights for policy 1, policy_version 121370 (0.0007) -[2023-11-28 03:23:42,790][87424] Updated weights for policy 0, policy_version 121566 (0.0009) -[2023-11-28 03:23:43,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5734.4, 300 sec: 5470.6). Total num frames: 62193664. Throughput: 0: 2809.1, 1: 2739.9. Samples: 62201824. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:43,445][86177] Avg episode reward: [(0, '-536.960'), (1, '-545.790')] -[2023-11-28 03:23:44,870][87426] Updated weights for policy 1, policy_version 121380 (0.0011) -[2023-11-28 03:23:44,976][87424] Updated weights for policy 0, policy_version 121576 (0.0011) -[2023-11-28 03:23:45,250][87426] Updated weights for policy 1, policy_version 121390 (0.0011) -[2023-11-28 03:23:45,348][87424] Updated weights for policy 0, policy_version 121586 (0.0009) -[2023-11-28 03:23:45,615][87426] Updated weights for policy 1, policy_version 121400 (0.0012) -[2023-11-28 03:23:45,728][87424] Updated weights for policy 0, policy_version 121596 (0.0010) -[2023-11-28 03:23:47,487][87426] Updated weights for policy 1, policy_version 121410 (0.0011) -[2023-11-28 03:23:47,699][87424] Updated weights for policy 0, policy_version 121606 (0.0011) -[2023-11-28 03:23:47,876][87426] Updated weights for policy 1, policy_version 121420 (0.0010) -[2023-11-28 03:23:48,076][87424] Updated weights for policy 0, policy_version 121616 (0.0012) -[2023-11-28 03:23:48,248][87426] Updated weights for policy 1, policy_version 121430 (0.0010) -[2023-11-28 03:23:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 62210048. Throughput: 0: 2788.2, 1: 2739.6. Samples: 62226976. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:48,445][86177] Avg episode reward: [(0, '-536.560'), (1, '-590.130')] -[2023-11-28 03:23:48,461][87424] Updated weights for policy 0, policy_version 121626 (0.0011) -[2023-11-28 03:23:48,627][87426] Updated weights for policy 1, policy_version 121440 (0.0009) -[2023-11-28 03:23:50,751][87424] Updated weights for policy 0, policy_version 121636 (0.0012) -[2023-11-28 03:23:51,051][87426] Updated weights for policy 1, policy_version 121450 (0.0011) -[2023-11-28 03:23:51,133][87424] Updated weights for policy 0, policy_version 121646 (0.0012) -[2023-11-28 03:23:51,433][87426] Updated weights for policy 1, policy_version 121460 (0.0011) -[2023-11-28 03:23:51,510][87424] Updated weights for policy 0, policy_version 121656 (0.0012) -[2023-11-28 03:23:51,817][87426] Updated weights for policy 1, policy_version 121470 (0.0011) -[2023-11-28 03:23:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62242816. Throughput: 0: 2762.2, 1: 2753.8. Samples: 62259480. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:53,445][86177] Avg episode reward: [(0, '-532.060'), (1, '-600.920')] -[2023-11-28 03:23:53,879][87424] Updated weights for policy 0, policy_version 121666 (0.0011) -[2023-11-28 03:23:53,969][87426] Updated weights for policy 1, policy_version 121480 (0.0011) -[2023-11-28 03:23:54,257][87424] Updated weights for policy 0, policy_version 121676 (0.0012) -[2023-11-28 03:23:54,354][87426] Updated weights for policy 1, policy_version 121490 (0.0011) -[2023-11-28 03:23:54,645][87424] Updated weights for policy 0, policy_version 121686 (0.0008) -[2023-11-28 03:23:54,725][87426] Updated weights for policy 1, policy_version 121500 (0.0010) -[2023-11-28 03:23:55,020][87424] Updated weights for policy 0, policy_version 121696 (0.0008) -[2023-11-28 03:23:56,568][87426] Updated weights for policy 1, policy_version 121510 (0.0010) -[2023-11-28 03:23:56,946][87426] Updated weights for policy 1, policy_version 121520 (0.0011) -[2023-11-28 03:23:57,327][87426] Updated weights for policy 1, policy_version 121530 (0.0011) -[2023-11-28 03:23:57,409][87424] Updated weights for policy 0, policy_version 121706 (0.0007) -[2023-11-28 03:23:57,793][87424] Updated weights for policy 0, policy_version 121716 (0.0007) -[2023-11-28 03:23:58,181][87424] Updated weights for policy 0, policy_version 121726 (0.0007) -[2023-11-28 03:23:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 62275584. Throughput: 0: 2752.4, 1: 2751.0. Samples: 62284168. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:23:58,445][86177] Avg episode reward: [(0, '-521.200'), (1, '-629.600')] -[2023-11-28 03:23:59,677][87426] Updated weights for policy 1, policy_version 121540 (0.0011) -[2023-11-28 03:24:00,054][87426] Updated weights for policy 1, policy_version 121550 (0.0008) -[2023-11-28 03:24:00,316][87424] Updated weights for policy 0, policy_version 121736 (0.0008) -[2023-11-28 03:24:00,432][87426] Updated weights for policy 1, policy_version 121560 (0.0008) -[2023-11-28 03:24:00,705][87424] Updated weights for policy 0, policy_version 121746 (0.0009) -[2023-11-28 03:24:01,086][87424] Updated weights for policy 0, policy_version 121756 (0.0008) -[2023-11-28 03:24:02,567][87426] Updated weights for policy 1, policy_version 121570 (0.0009) -[2023-11-28 03:24:02,941][87426] Updated weights for policy 1, policy_version 121580 (0.0010) -[2023-11-28 03:24:03,323][87426] Updated weights for policy 1, policy_version 121590 (0.0008) -[2023-11-28 03:24:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62291968. Throughput: 0: 2714.7, 1: 2751.2. Samples: 62308248. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 03:24:03,446][86177] Avg episode reward: [(0, '-511.570'), (1, '-627.890')] -[2023-11-28 03:24:03,542][87424] Updated weights for policy 0, policy_version 121766 (0.0008) -[2023-11-28 03:24:03,708][87426] Updated weights for policy 1, policy_version 121600 (0.0008) -[2023-11-28 03:24:03,921][87424] Updated weights for policy 0, policy_version 121776 (0.0008) -[2023-11-28 03:24:04,302][87424] Updated weights for policy 0, policy_version 121786 (0.0007) -[2023-11-28 03:24:06,076][87426] Updated weights for policy 1, policy_version 121610 (0.0007) -[2023-11-28 03:24:06,465][87426] Updated weights for policy 1, policy_version 121620 (0.0010) -[2023-11-28 03:24:06,725][87424] Updated weights for policy 0, policy_version 121796 (0.0009) -[2023-11-28 03:24:06,831][87426] Updated weights for policy 1, policy_version 121630 (0.0009) -[2023-11-28 03:24:07,110][87424] Updated weights for policy 0, policy_version 121806 (0.0012) -[2023-11-28 03:24:07,494][87424] Updated weights for policy 0, policy_version 121816 (0.0012) -[2023-11-28 03:24:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62324736. Throughput: 0: 2700.4, 1: 2741.6. Samples: 62340104. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:08,445][86177] Avg episode reward: [(0, '-497.510'), (1, '-622.380')] -[2023-11-28 03:24:09,086][87426] Updated weights for policy 1, policy_version 121640 (0.0011) -[2023-11-28 03:24:09,464][87424] Updated weights for policy 0, policy_version 121826 (0.0012) -[2023-11-28 03:24:09,469][87426] Updated weights for policy 1, policy_version 121650 (0.0010) -[2023-11-28 03:24:09,844][87426] Updated weights for policy 1, policy_version 121660 (0.0012) -[2023-11-28 03:24:09,846][87424] Updated weights for policy 0, policy_version 121836 (0.0009) -[2023-11-28 03:24:10,228][87424] Updated weights for policy 0, policy_version 121846 (0.0011) -[2023-11-28 03:24:10,609][87424] Updated weights for policy 0, policy_version 121856 (0.0010) -[2023-11-28 03:24:12,514][87426] Updated weights for policy 1, policy_version 121670 (0.0011) -[2023-11-28 03:24:12,850][87424] Updated weights for policy 0, policy_version 121866 (0.0010) -[2023-11-28 03:24:12,890][87426] Updated weights for policy 1, policy_version 121680 (0.0008) -[2023-11-28 03:24:13,222][87424] Updated weights for policy 0, policy_version 121876 (0.0011) -[2023-11-28 03:24:13,276][87426] Updated weights for policy 1, policy_version 121690 (0.0010) -[2023-11-28 03:24:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 62341120. Throughput: 0: 2704.4, 1: 2749.0. Samples: 62364052. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:13,445][86177] Avg episode reward: [(0, '-495.850'), (1, '-596.600')] -[2023-11-28 03:24:13,605][87424] Updated weights for policy 0, policy_version 121886 (0.0011) -[2023-11-28 03:24:15,590][87424] Updated weights for policy 0, policy_version 121896 (0.0011) -[2023-11-28 03:24:15,608][87426] Updated weights for policy 1, policy_version 121700 (0.0010) -[2023-11-28 03:24:15,965][87424] Updated weights for policy 0, policy_version 121906 (0.0012) -[2023-11-28 03:24:15,989][87426] Updated weights for policy 1, policy_version 121710 (0.0010) -[2023-11-28 03:24:16,341][87424] Updated weights for policy 0, policy_version 121916 (0.0010) -[2023-11-28 03:24:16,380][87426] Updated weights for policy 1, policy_version 121720 (0.0012) -[2023-11-28 03:24:18,115][87426] Updated weights for policy 1, policy_version 121730 (0.0011) -[2023-11-28 03:24:18,310][87424] Updated weights for policy 0, policy_version 121926 (0.0010) -[2023-11-28 03:24:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62373888. Throughput: 0: 2699.3, 1: 2745.5. Samples: 62389276. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:18,445][86177] Avg episode reward: [(0, '-510.240'), (1, '-546.560')] -[2023-11-28 03:24:18,494][87426] Updated weights for policy 1, policy_version 121740 (0.0011) -[2023-11-28 03:24:18,685][87424] Updated weights for policy 0, policy_version 121936 (0.0008) -[2023-11-28 03:24:18,876][87426] Updated weights for policy 1, policy_version 121750 (0.0012) -[2023-11-28 03:24:19,067][87424] Updated weights for policy 0, policy_version 121946 (0.0008) -[2023-11-28 03:24:19,255][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000121760_31170560.pth... -[2023-11-28 03:24:19,256][87426] Updated weights for policy 1, policy_version 121760 (0.0008) -[2023-11-28 03:24:19,285][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000119168_30507008.pth -[2023-11-28 03:24:19,300][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000121952_31219712.pth... -[2023-11-28 03:24:19,347][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000119360_30556160.pth -[2023-11-28 03:24:21,183][87424] Updated weights for policy 0, policy_version 121956 (0.0008) -[2023-11-28 03:24:21,566][87424] Updated weights for policy 0, policy_version 121966 (0.0008) -[2023-11-28 03:24:21,580][87426] Updated weights for policy 1, policy_version 121770 (0.0012) -[2023-11-28 03:24:21,962][87424] Updated weights for policy 0, policy_version 121976 (0.0011) -[2023-11-28 03:24:21,965][87426] Updated weights for policy 1, policy_version 121780 (0.0009) -[2023-11-28 03:24:22,346][87426] Updated weights for policy 1, policy_version 121790 (0.0010) -[2023-11-28 03:24:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62406656. Throughput: 0: 2707.6, 1: 2752.0. Samples: 62422872. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:23,445][86177] Avg episode reward: [(0, '-518.630'), (1, '-558.060')] -[2023-11-28 03:24:24,030][87424] Updated weights for policy 0, policy_version 121986 (0.0011) -[2023-11-28 03:24:24,416][87424] Updated weights for policy 0, policy_version 121996 (0.0012) -[2023-11-28 03:24:24,469][87426] Updated weights for policy 1, policy_version 121800 (0.0011) -[2023-11-28 03:24:24,788][87424] Updated weights for policy 0, policy_version 122006 (0.0011) -[2023-11-28 03:24:24,844][87426] Updated weights for policy 1, policy_version 121810 (0.0012) -[2023-11-28 03:24:25,164][87424] Updated weights for policy 0, policy_version 122016 (0.0012) -[2023-11-28 03:24:25,221][87426] Updated weights for policy 1, policy_version 121820 (0.0012) -[2023-11-28 03:24:27,243][87426] Updated weights for policy 1, policy_version 121830 (0.0012) -[2023-11-28 03:24:27,391][87424] Updated weights for policy 0, policy_version 122026 (0.0012) -[2023-11-28 03:24:27,618][87426] Updated weights for policy 1, policy_version 121840 (0.0009) -[2023-11-28 03:24:27,771][87424] Updated weights for policy 0, policy_version 122036 (0.0011) -[2023-11-28 03:24:27,998][87426] Updated weights for policy 1, policy_version 121850 (0.0008) -[2023-11-28 03:24:28,153][87424] Updated weights for policy 0, policy_version 122046 (0.0009) -[2023-11-28 03:24:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 62439424. Throughput: 0: 2712.3, 1: 2742.5. Samples: 62447288. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:28,445][86177] Avg episode reward: [(0, '-520.150'), (1, '-526.950')] -[2023-11-28 03:24:29,889][87426] Updated weights for policy 1, policy_version 121860 (0.0010) -[2023-11-28 03:24:30,121][87424] Updated weights for policy 0, policy_version 122056 (0.0010) -[2023-11-28 03:24:30,267][87426] Updated weights for policy 1, policy_version 121870 (0.0011) -[2023-11-28 03:24:30,508][87424] Updated weights for policy 0, policy_version 122066 (0.0011) -[2023-11-28 03:24:30,640][87426] Updated weights for policy 1, policy_version 121880 (0.0011) -[2023-11-28 03:24:30,896][87424] Updated weights for policy 0, policy_version 122076 (0.0011) -[2023-11-28 03:24:32,896][87424] Updated weights for policy 0, policy_version 122086 (0.0009) -[2023-11-28 03:24:33,187][87426] Updated weights for policy 1, policy_version 121890 (0.0010) -[2023-11-28 03:24:33,273][87424] Updated weights for policy 0, policy_version 122096 (0.0009) -[2023-11-28 03:24:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 62455808. Throughput: 0: 2723.4, 1: 2741.8. Samples: 62472908. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:33,445][86177] Avg episode reward: [(0, '-511.470'), (1, '-524.170')] -[2023-11-28 03:24:33,566][87426] Updated weights for policy 1, policy_version 121900 (0.0008) -[2023-11-28 03:24:33,648][87424] Updated weights for policy 0, policy_version 122106 (0.0012) -[2023-11-28 03:24:33,947][87426] Updated weights for policy 1, policy_version 121910 (0.0012) -[2023-11-28 03:24:34,324][87426] Updated weights for policy 1, policy_version 121920 (0.0012) -[2023-11-28 03:24:35,730][87424] Updated weights for policy 0, policy_version 122116 (0.0012) -[2023-11-28 03:24:36,100][87424] Updated weights for policy 0, policy_version 122126 (0.0011) -[2023-11-28 03:24:36,457][87426] Updated weights for policy 1, policy_version 121930 (0.0007) -[2023-11-28 03:24:36,485][87424] Updated weights for policy 0, policy_version 122136 (0.0012) -[2023-11-28 03:24:36,844][87426] Updated weights for policy 1, policy_version 121940 (0.0009) -[2023-11-28 03:24:37,217][87426] Updated weights for policy 1, policy_version 121950 (0.0008) -[2023-11-28 03:24:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 62488576. Throughput: 0: 2745.8, 1: 2738.9. Samples: 62506292. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:38,445][86177] Avg episode reward: [(0, '-515.660'), (1, '-539.940')] -[2023-11-28 03:24:38,708][87424] Updated weights for policy 0, policy_version 122146 (0.0011) -[2023-11-28 03:24:39,082][87424] Updated weights for policy 0, policy_version 122156 (0.0008) -[2023-11-28 03:24:39,463][87424] Updated weights for policy 0, policy_version 122166 (0.0009) -[2023-11-28 03:24:39,605][87426] Updated weights for policy 1, policy_version 121960 (0.0011) -[2023-11-28 03:24:39,844][87424] Updated weights for policy 0, policy_version 122176 (0.0009) -[2023-11-28 03:24:39,973][87426] Updated weights for policy 1, policy_version 121970 (0.0011) -[2023-11-28 03:24:40,355][87426] Updated weights for policy 1, policy_version 121980 (0.0012) -[2023-11-28 03:24:42,004][87424] Updated weights for policy 0, policy_version 122186 (0.0012) -[2023-11-28 03:24:42,385][87424] Updated weights for policy 0, policy_version 122196 (0.0011) -[2023-11-28 03:24:42,660][87426] Updated weights for policy 1, policy_version 121990 (0.0012) -[2023-11-28 03:24:42,774][87424] Updated weights for policy 0, policy_version 122206 (0.0011) -[2023-11-28 03:24:43,037][87426] Updated weights for policy 1, policy_version 122000 (0.0012) -[2023-11-28 03:24:43,430][87426] Updated weights for policy 1, policy_version 122010 (0.0012) -[2023-11-28 03:24:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 62513152. Throughput: 0: 2756.3, 1: 2710.9. Samples: 62530192. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:43,445][86177] Avg episode reward: [(0, '-516.490'), (1, '-576.950')] -[2023-11-28 03:24:44,936][87424] Updated weights for policy 0, policy_version 122216 (0.0010) -[2023-11-28 03:24:45,322][87424] Updated weights for policy 0, policy_version 122226 (0.0008) -[2023-11-28 03:24:45,705][87424] Updated weights for policy 0, policy_version 122236 (0.0008) -[2023-11-28 03:24:45,890][87426] Updated weights for policy 1, policy_version 122020 (0.0012) -[2023-11-28 03:24:46,258][87426] Updated weights for policy 1, policy_version 122030 (0.0007) -[2023-11-28 03:24:46,627][87426] Updated weights for policy 1, policy_version 122040 (0.0008) -[2023-11-28 03:24:47,872][87424] Updated weights for policy 0, policy_version 122246 (0.0010) -[2023-11-28 03:24:48,256][87424] Updated weights for policy 0, policy_version 122256 (0.0012) -[2023-11-28 03:24:48,284][87426] Updated weights for policy 1, policy_version 122050 (0.0007) -[2023-11-28 03:24:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62537728. Throughput: 0: 2772.4, 1: 2706.2. Samples: 62554784. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:48,445][86177] Avg episode reward: [(0, '-515.560'), (1, '-577.040')] -[2023-11-28 03:24:48,638][87424] Updated weights for policy 0, policy_version 122266 (0.0012) -[2023-11-28 03:24:48,662][87426] Updated weights for policy 1, policy_version 122060 (0.0010) -[2023-11-28 03:24:49,041][87426] Updated weights for policy 1, policy_version 122070 (0.0009) -[2023-11-28 03:24:49,419][87426] Updated weights for policy 1, policy_version 122080 (0.0010) -[2023-11-28 03:24:50,527][87424] Updated weights for policy 0, policy_version 122276 (0.0010) -[2023-11-28 03:24:50,907][87424] Updated weights for policy 0, policy_version 122286 (0.0007) -[2023-11-28 03:24:51,288][87424] Updated weights for policy 0, policy_version 122296 (0.0008) -[2023-11-28 03:24:51,904][87426] Updated weights for policy 1, policy_version 122090 (0.0012) -[2023-11-28 03:24:52,272][87426] Updated weights for policy 1, policy_version 122100 (0.0012) -[2023-11-28 03:24:52,653][87426] Updated weights for policy 1, policy_version 122110 (0.0012) -[2023-11-28 03:24:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 62570496. Throughput: 0: 2786.2, 1: 2681.3. Samples: 62586144. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:53,445][86177] Avg episode reward: [(0, '-508.390'), (1, '-603.270')] -[2023-11-28 03:24:53,640][87424] Updated weights for policy 0, policy_version 122306 (0.0009) -[2023-11-28 03:24:54,020][87424] Updated weights for policy 0, policy_version 122316 (0.0010) -[2023-11-28 03:24:54,406][87424] Updated weights for policy 0, policy_version 122326 (0.0008) -[2023-11-28 03:24:54,762][87426] Updated weights for policy 1, policy_version 122120 (0.0012) -[2023-11-28 03:24:54,785][87424] Updated weights for policy 0, policy_version 122336 (0.0008) -[2023-11-28 03:24:55,137][87426] Updated weights for policy 1, policy_version 122130 (0.0012) -[2023-11-28 03:24:55,519][87426] Updated weights for policy 1, policy_version 122140 (0.0012) -[2023-11-28 03:24:57,063][87424] Updated weights for policy 0, policy_version 122346 (0.0007) -[2023-11-28 03:24:57,444][87424] Updated weights for policy 0, policy_version 122356 (0.0010) -[2023-11-28 03:24:57,823][87424] Updated weights for policy 0, policy_version 122366 (0.0011) -[2023-11-28 03:24:57,891][87426] Updated weights for policy 1, policy_version 122150 (0.0011) -[2023-11-28 03:24:58,277][87426] Updated weights for policy 1, policy_version 122160 (0.0011) -[2023-11-28 03:24:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 62595072. Throughput: 0: 2776.9, 1: 2706.5. Samples: 62610804. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:24:58,445][86177] Avg episode reward: [(0, '-509.580'), (1, '-615.280')] -[2023-11-28 03:24:58,647][87426] Updated weights for policy 1, policy_version 122170 (0.0009) -[2023-11-28 03:24:59,937][87424] Updated weights for policy 0, policy_version 122376 (0.0011) -[2023-11-28 03:25:00,307][87424] Updated weights for policy 0, policy_version 122386 (0.0011) -[2023-11-28 03:25:00,558][87426] Updated weights for policy 1, policy_version 122180 (0.0012) -[2023-11-28 03:25:00,691][87424] Updated weights for policy 0, policy_version 122396 (0.0011) -[2023-11-28 03:25:00,940][87426] Updated weights for policy 1, policy_version 122190 (0.0010) -[2023-11-28 03:25:01,307][87426] Updated weights for policy 1, policy_version 122200 (0.0012) -[2023-11-28 03:25:02,699][87424] Updated weights for policy 0, policy_version 122406 (0.0010) -[2023-11-28 03:25:03,083][87424] Updated weights for policy 0, policy_version 122416 (0.0008) -[2023-11-28 03:25:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 62619648. Throughput: 0: 2787.9, 1: 2705.3. Samples: 62636468. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:25:03,445][86177] Avg episode reward: [(0, '-506.290'), (1, '-567.190')] -[2023-11-28 03:25:03,461][87424] Updated weights for policy 0, policy_version 122426 (0.0008) -[2023-11-28 03:25:03,660][87426] Updated weights for policy 1, policy_version 122210 (0.0012) -[2023-11-28 03:25:04,044][87426] Updated weights for policy 1, policy_version 122220 (0.0012) -[2023-11-28 03:25:04,418][87426] Updated weights for policy 1, policy_version 122230 (0.0009) -[2023-11-28 03:25:04,798][87426] Updated weights for policy 1, policy_version 122240 (0.0008) -[2023-11-28 03:25:05,872][87424] Updated weights for policy 0, policy_version 122436 (0.0008) -[2023-11-28 03:25:06,256][87424] Updated weights for policy 0, policy_version 122446 (0.0008) -[2023-11-28 03:25:06,637][87424] Updated weights for policy 0, policy_version 122456 (0.0008) -[2023-11-28 03:25:07,309][87426] Updated weights for policy 1, policy_version 122250 (0.0012) -[2023-11-28 03:25:07,691][87426] Updated weights for policy 1, policy_version 122260 (0.0012) -[2023-11-28 03:25:08,066][87426] Updated weights for policy 1, policy_version 122270 (0.0012) -[2023-11-28 03:25:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 62652416. Throughput: 0: 2799.2, 1: 2682.1. Samples: 62669532. Policy #0 lag: (min: 31.0, avg: 54.8, max: 95.0) -[2023-11-28 03:25:08,445][86177] Avg episode reward: [(0, '-504.550'), (1, '-569.220')] -[2023-11-28 03:25:08,525][87424] Updated weights for policy 0, policy_version 122466 (0.0011) -[2023-11-28 03:25:08,910][87424] Updated weights for policy 0, policy_version 122476 (0.0011) -[2023-11-28 03:25:09,299][87424] Updated weights for policy 0, policy_version 122486 (0.0007) -[2023-11-28 03:25:09,676][87424] Updated weights for policy 0, policy_version 122496 (0.0009) -[2023-11-28 03:25:09,849][87426] Updated weights for policy 1, policy_version 122280 (0.0011) -[2023-11-28 03:25:10,229][87426] Updated weights for policy 1, policy_version 122290 (0.0012) -[2023-11-28 03:25:10,600][87426] Updated weights for policy 1, policy_version 122300 (0.0011) -[2023-11-28 03:25:11,414][87424] Updated weights for policy 0, policy_version 122506 (0.0010) -[2023-11-28 03:25:11,796][87424] Updated weights for policy 0, policy_version 122516 (0.0010) -[2023-11-28 03:25:12,187][87424] Updated weights for policy 0, policy_version 122526 (0.0012) -[2023-11-28 03:25:12,992][87426] Updated weights for policy 1, policy_version 122310 (0.0011) -[2023-11-28 03:25:13,368][87426] Updated weights for policy 1, policy_version 122320 (0.0012) -[2023-11-28 03:25:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 62676992. Throughput: 0: 2817.6, 1: 2677.0. Samples: 62694544. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:13,445][86177] Avg episode reward: [(0, '-507.850'), (1, '-539.700')] -[2023-11-28 03:25:13,748][87426] Updated weights for policy 1, policy_version 122330 (0.0012) -[2023-11-28 03:25:14,390][87424] Updated weights for policy 0, policy_version 122536 (0.0011) -[2023-11-28 03:25:14,790][87424] Updated weights for policy 0, policy_version 122546 (0.0012) -[2023-11-28 03:25:15,169][87424] Updated weights for policy 0, policy_version 122556 (0.0012) -[2023-11-28 03:25:15,540][87426] Updated weights for policy 1, policy_version 122340 (0.0012) -[2023-11-28 03:25:15,916][87426] Updated weights for policy 1, policy_version 122350 (0.0012) -[2023-11-28 03:25:16,296][87426] Updated weights for policy 1, policy_version 122360 (0.0012) -[2023-11-28 03:25:16,901][87424] Updated weights for policy 0, policy_version 122566 (0.0012) -[2023-11-28 03:25:17,286][87424] Updated weights for policy 0, policy_version 122576 (0.0012) -[2023-11-28 03:25:17,663][87424] Updated weights for policy 0, policy_version 122586 (0.0009) -[2023-11-28 03:25:18,124][87426] Updated weights for policy 1, policy_version 122370 (0.0012) -[2023-11-28 03:25:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 62709760. Throughput: 0: 2826.5, 1: 2677.7. Samples: 62720596. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:18,445][86177] Avg episode reward: [(0, '-503.240'), (1, '-517.890')] -[2023-11-28 03:25:18,498][87426] Updated weights for policy 1, policy_version 122380 (0.0011) -[2023-11-28 03:25:18,895][87426] Updated weights for policy 1, policy_version 122390 (0.0009) -[2023-11-28 03:25:19,267][87426] Updated weights for policy 1, policy_version 122400 (0.0011) -[2023-11-28 03:25:19,314][87424] Updated weights for policy 0, policy_version 122596 (0.0012) -[2023-11-28 03:25:19,695][87424] Updated weights for policy 0, policy_version 122606 (0.0012) -[2023-11-28 03:25:20,081][87424] Updated weights for policy 0, policy_version 122616 (0.0012) -[2023-11-28 03:25:21,319][87426] Updated weights for policy 1, policy_version 122410 (0.0011) -[2023-11-28 03:25:21,691][87426] Updated weights for policy 1, policy_version 122420 (0.0011) -[2023-11-28 03:25:22,078][87426] Updated weights for policy 1, policy_version 122430 (0.0012) -[2023-11-28 03:25:22,345][87424] Updated weights for policy 0, policy_version 122626 (0.0012) -[2023-11-28 03:25:22,732][87424] Updated weights for policy 0, policy_version 122636 (0.0011) -[2023-11-28 03:25:23,112][87424] Updated weights for policy 0, policy_version 122646 (0.0009) -[2023-11-28 03:25:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 62734336. Throughput: 0: 2810.6, 1: 2680.4. Samples: 62753384. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:23,445][86177] Avg episode reward: [(0, '-503.580'), (1, '-517.130')] -[2023-11-28 03:25:23,500][87424] Updated weights for policy 0, policy_version 122656 (0.0008) -[2023-11-28 03:25:24,485][87426] Updated weights for policy 1, policy_version 122440 (0.0008) -[2023-11-28 03:25:24,871][87426] Updated weights for policy 1, policy_version 122450 (0.0009) -[2023-11-28 03:25:25,253][87426] Updated weights for policy 1, policy_version 122460 (0.0009) -[2023-11-28 03:25:25,844][87424] Updated weights for policy 0, policy_version 122666 (0.0008) -[2023-11-28 03:25:26,225][87424] Updated weights for policy 0, policy_version 122676 (0.0009) -[2023-11-28 03:25:26,609][87424] Updated weights for policy 0, policy_version 122686 (0.0007) -[2023-11-28 03:25:27,484][87426] Updated weights for policy 1, policy_version 122470 (0.0010) -[2023-11-28 03:25:27,865][87426] Updated weights for policy 1, policy_version 122480 (0.0011) -[2023-11-28 03:25:28,248][87426] Updated weights for policy 1, policy_version 122490 (0.0011) -[2023-11-28 03:25:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 62758912. Throughput: 0: 2800.2, 1: 2715.7. Samples: 62778408. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:28,445][86177] Avg episode reward: [(0, '-502.740'), (1, '-516.260')] -[2023-11-28 03:25:28,931][87424] Updated weights for policy 0, policy_version 122696 (0.0009) -[2023-11-28 03:25:29,314][87424] Updated weights for policy 0, policy_version 122706 (0.0011) -[2023-11-28 03:25:29,702][87424] Updated weights for policy 0, policy_version 122716 (0.0012) -[2023-11-28 03:25:30,620][87426] Updated weights for policy 1, policy_version 122500 (0.0012) -[2023-11-28 03:25:30,987][87426] Updated weights for policy 1, policy_version 122510 (0.0012) -[2023-11-28 03:25:31,366][87426] Updated weights for policy 1, policy_version 122520 (0.0012) -[2023-11-28 03:25:32,043][87424] Updated weights for policy 0, policy_version 122726 (0.0012) -[2023-11-28 03:25:32,414][87424] Updated weights for policy 0, policy_version 122736 (0.0011) -[2023-11-28 03:25:32,794][87424] Updated weights for policy 0, policy_version 122746 (0.0012) -[2023-11-28 03:25:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 62791680. Throughput: 0: 2788.1, 1: 2727.7. Samples: 62802996. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:33,445][86177] Avg episode reward: [(0, '-499.840'), (1, '-516.760')] -[2023-11-28 03:25:33,788][87426] Updated weights for policy 1, policy_version 122530 (0.0012) -[2023-11-28 03:25:34,161][87426] Updated weights for policy 1, policy_version 122540 (0.0012) -[2023-11-28 03:25:34,532][87426] Updated weights for policy 1, policy_version 122550 (0.0012) -[2023-11-28 03:25:34,779][87424] Updated weights for policy 0, policy_version 122756 (0.0012) -[2023-11-28 03:25:34,914][87426] Updated weights for policy 1, policy_version 122560 (0.0011) -[2023-11-28 03:25:35,162][87424] Updated weights for policy 0, policy_version 122766 (0.0012) -[2023-11-28 03:25:35,538][87424] Updated weights for policy 0, policy_version 122776 (0.0012) -[2023-11-28 03:25:36,680][87426] Updated weights for policy 1, policy_version 122570 (0.0012) -[2023-11-28 03:25:37,051][87426] Updated weights for policy 1, policy_version 122580 (0.0011) -[2023-11-28 03:25:37,172][87424] Updated weights for policy 0, policy_version 122786 (0.0012) -[2023-11-28 03:25:37,427][87426] Updated weights for policy 1, policy_version 122590 (0.0012) -[2023-11-28 03:25:37,550][87424] Updated weights for policy 0, policy_version 122796 (0.0012) -[2023-11-28 03:25:37,921][87424] Updated weights for policy 0, policy_version 122806 (0.0012) -[2023-11-28 03:25:38,294][87424] Updated weights for policy 0, policy_version 122816 (0.0012) -[2023-11-28 03:25:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 62824448. Throughput: 0: 2818.8, 1: 2735.0. Samples: 62836068. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:38,445][86177] Avg episode reward: [(0, '-506.490'), (1, '-518.350')] -[2023-11-28 03:25:39,929][87426] Updated weights for policy 1, policy_version 122600 (0.0012) -[2023-11-28 03:25:40,309][87426] Updated weights for policy 1, policy_version 122610 (0.0012) -[2023-11-28 03:25:40,693][87426] Updated weights for policy 1, policy_version 122620 (0.0009) -[2023-11-28 03:25:40,916][87424] Updated weights for policy 0, policy_version 122826 (0.0011) -[2023-11-28 03:25:41,295][87424] Updated weights for policy 0, policy_version 122836 (0.0008) -[2023-11-28 03:25:41,678][87424] Updated weights for policy 0, policy_version 122846 (0.0009) -[2023-11-28 03:25:42,937][87426] Updated weights for policy 1, policy_version 122630 (0.0009) -[2023-11-28 03:25:43,314][87426] Updated weights for policy 1, policy_version 122640 (0.0007) -[2023-11-28 03:25:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62840832. Throughput: 0: 2845.3, 1: 2707.6. Samples: 62860684. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:43,445][86177] Avg episode reward: [(0, '-506.830'), (1, '-525.050')] -[2023-11-28 03:25:43,695][87426] Updated weights for policy 1, policy_version 122650 (0.0010) -[2023-11-28 03:25:43,705][87424] Updated weights for policy 0, policy_version 122856 (0.0010) -[2023-11-28 03:25:44,100][87424] Updated weights for policy 0, policy_version 122866 (0.0012) -[2023-11-28 03:25:44,481][87424] Updated weights for policy 0, policy_version 122876 (0.0012) -[2023-11-28 03:25:45,671][87426] Updated weights for policy 1, policy_version 122660 (0.0009) -[2023-11-28 03:25:46,054][87426] Updated weights for policy 1, policy_version 122670 (0.0012) -[2023-11-28 03:25:46,431][87426] Updated weights for policy 1, policy_version 122680 (0.0011) -[2023-11-28 03:25:46,921][87424] Updated weights for policy 0, policy_version 122886 (0.0012) -[2023-11-28 03:25:47,306][87424] Updated weights for policy 0, policy_version 122896 (0.0012) -[2023-11-28 03:25:47,703][87424] Updated weights for policy 0, policy_version 122906 (0.0012) -[2023-11-28 03:25:48,176][87426] Updated weights for policy 1, policy_version 122690 (0.0010) -[2023-11-28 03:25:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 62873600. Throughput: 0: 2796.4, 1: 2712.6. Samples: 62884372. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:48,445][86177] Avg episode reward: [(0, '-511.830'), (1, '-524.590')] -[2023-11-28 03:25:48,554][87426] Updated weights for policy 1, policy_version 122700 (0.0012) -[2023-11-28 03:25:48,930][87426] Updated weights for policy 1, policy_version 122710 (0.0008) -[2023-11-28 03:25:49,316][87426] Updated weights for policy 1, policy_version 122720 (0.0007) -[2023-11-28 03:25:49,807][87424] Updated weights for policy 0, policy_version 122916 (0.0012) -[2023-11-28 03:25:50,191][87424] Updated weights for policy 0, policy_version 122926 (0.0012) -[2023-11-28 03:25:50,571][87424] Updated weights for policy 0, policy_version 122936 (0.0011) -[2023-11-28 03:25:51,729][87426] Updated weights for policy 1, policy_version 122730 (0.0010) -[2023-11-28 03:25:52,105][87426] Updated weights for policy 1, policy_version 122740 (0.0012) -[2023-11-28 03:25:52,486][87426] Updated weights for policy 1, policy_version 122750 (0.0009) -[2023-11-28 03:25:52,945][87424] Updated weights for policy 0, policy_version 122946 (0.0011) -[2023-11-28 03:25:53,334][87424] Updated weights for policy 0, policy_version 122956 (0.0012) -[2023-11-28 03:25:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62898176. Throughput: 0: 2736.2, 1: 2745.8. Samples: 62916220. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:53,445][86177] Avg episode reward: [(0, '-504.690'), (1, '-521.540')] -[2023-11-28 03:25:53,723][87424] Updated weights for policy 0, policy_version 122966 (0.0009) -[2023-11-28 03:25:54,103][87424] Updated weights for policy 0, policy_version 122976 (0.0010) -[2023-11-28 03:25:55,024][87426] Updated weights for policy 1, policy_version 122760 (0.0011) -[2023-11-28 03:25:55,404][87426] Updated weights for policy 1, policy_version 122770 (0.0011) -[2023-11-28 03:25:55,784][87426] Updated weights for policy 1, policy_version 122780 (0.0011) -[2023-11-28 03:25:56,561][87424] Updated weights for policy 0, policy_version 122986 (0.0012) -[2023-11-28 03:25:56,937][87424] Updated weights for policy 0, policy_version 122996 (0.0012) -[2023-11-28 03:25:57,324][87424] Updated weights for policy 0, policy_version 123006 (0.0012) -[2023-11-28 03:25:57,998][87426] Updated weights for policy 1, policy_version 122790 (0.0009) -[2023-11-28 03:25:58,384][87426] Updated weights for policy 1, policy_version 122800 (0.0010) -[2023-11-28 03:25:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 62922752. Throughput: 0: 2719.3, 1: 2773.1. Samples: 62941700. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:25:58,445][86177] Avg episode reward: [(0, '-506.330'), (1, '-531.750')] -[2023-11-28 03:25:58,766][87426] Updated weights for policy 1, policy_version 122810 (0.0011) -[2023-11-28 03:25:59,309][87424] Updated weights for policy 0, policy_version 123016 (0.0012) -[2023-11-28 03:25:59,684][87424] Updated weights for policy 0, policy_version 123026 (0.0011) -[2023-11-28 03:26:00,065][87424] Updated weights for policy 0, policy_version 123036 (0.0009) -[2023-11-28 03:26:00,709][87426] Updated weights for policy 1, policy_version 122820 (0.0010) -[2023-11-28 03:26:01,092][87426] Updated weights for policy 1, policy_version 122830 (0.0007) -[2023-11-28 03:26:01,476][87426] Updated weights for policy 1, policy_version 122840 (0.0008) -[2023-11-28 03:26:02,342][87424] Updated weights for policy 0, policy_version 123046 (0.0010) -[2023-11-28 03:26:02,716][87424] Updated weights for policy 0, policy_version 123056 (0.0008) -[2023-11-28 03:26:03,102][87424] Updated weights for policy 0, policy_version 123066 (0.0008) -[2023-11-28 03:26:03,133][87426] Updated weights for policy 1, policy_version 122850 (0.0009) -[2023-11-28 03:26:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 62955520. Throughput: 0: 2709.3, 1: 2765.8. Samples: 62966976. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:26:03,445][86177] Avg episode reward: [(0, '-509.410'), (1, '-569.210')] -[2023-11-28 03:26:03,508][87426] Updated weights for policy 1, policy_version 122860 (0.0011) -[2023-11-28 03:26:03,876][87426] Updated weights for policy 1, policy_version 122870 (0.0011) -[2023-11-28 03:26:04,253][87426] Updated weights for policy 1, policy_version 122880 (0.0012) -[2023-11-28 03:26:05,216][87424] Updated weights for policy 0, policy_version 123076 (0.0009) -[2023-11-28 03:26:05,596][87424] Updated weights for policy 0, policy_version 123086 (0.0012) -[2023-11-28 03:26:05,981][87424] Updated weights for policy 0, policy_version 123096 (0.0012) -[2023-11-28 03:26:06,465][87426] Updated weights for policy 1, policy_version 122890 (0.0010) -[2023-11-28 03:26:06,833][87426] Updated weights for policy 1, policy_version 122900 (0.0012) -[2023-11-28 03:26:07,215][87426] Updated weights for policy 1, policy_version 122910 (0.0012) -[2023-11-28 03:26:07,715][87424] Updated weights for policy 0, policy_version 123106 (0.0011) -[2023-11-28 03:26:08,105][87424] Updated weights for policy 0, policy_version 123116 (0.0009) -[2023-11-28 03:26:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 62980096. Throughput: 0: 2705.2, 1: 2753.9. Samples: 62999044. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:26:08,445][86177] Avg episode reward: [(0, '-512.850'), (1, '-576.180')] -[2023-11-28 03:26:08,482][87424] Updated weights for policy 0, policy_version 123126 (0.0009) -[2023-11-28 03:26:08,863][87424] Updated weights for policy 0, policy_version 123136 (0.0008) -[2023-11-28 03:26:09,679][87426] Updated weights for policy 1, policy_version 122920 (0.0010) -[2023-11-28 03:26:10,058][87426] Updated weights for policy 1, policy_version 122930 (0.0011) -[2023-11-28 03:26:10,433][87426] Updated weights for policy 1, policy_version 122940 (0.0011) -[2023-11-28 03:26:10,745][87424] Updated weights for policy 0, policy_version 123146 (0.0012) -[2023-11-28 03:26:11,130][87424] Updated weights for policy 0, policy_version 123156 (0.0012) -[2023-11-28 03:26:11,509][87424] Updated weights for policy 0, policy_version 123166 (0.0012) -[2023-11-28 03:26:12,961][87426] Updated weights for policy 1, policy_version 122950 (0.0012) -[2023-11-28 03:26:13,335][87426] Updated weights for policy 1, policy_version 122960 (0.0016) -[2023-11-28 03:26:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63004672. Throughput: 0: 2703.6, 1: 2715.5. Samples: 63022264. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 03:26:13,445][86177] Avg episode reward: [(0, '-508.820'), (1, '-591.380')] -[2023-11-28 03:26:13,697][87424] Updated weights for policy 0, policy_version 123176 (0.0012) -[2023-11-28 03:26:13,723][87426] Updated weights for policy 1, policy_version 122970 (0.0011) -[2023-11-28 03:26:14,083][87424] Updated weights for policy 0, policy_version 123186 (0.0011) -[2023-11-28 03:26:14,461][87424] Updated weights for policy 0, policy_version 123196 (0.0009) -[2023-11-28 03:26:16,234][87426] Updated weights for policy 1, policy_version 122980 (0.0009) -[2023-11-28 03:26:16,421][87424] Updated weights for policy 0, policy_version 123206 (0.0010) -[2023-11-28 03:26:16,616][87426] Updated weights for policy 1, policy_version 122990 (0.0011) -[2023-11-28 03:26:16,800][87424] Updated weights for policy 0, policy_version 123216 (0.0012) -[2023-11-28 03:26:17,002][87426] Updated weights for policy 1, policy_version 123000 (0.0011) -[2023-11-28 03:26:17,182][87424] Updated weights for policy 0, policy_version 123226 (0.0012) -[2023-11-28 03:26:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 63037440. Throughput: 0: 2721.7, 1: 2693.1. Samples: 63046660. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:26:18,445][86177] Avg episode reward: [(0, '-509.620'), (1, '-625.490')] -[2023-11-28 03:26:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000123232_31547392.pth... -[2023-11-28 03:26:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000123008_31490048.pth... -[2023-11-28 03:26:18,505][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000120448_30834688.pth -[2023-11-28 03:26:18,506][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000120640_30883840.pth -[2023-11-28 03:26:18,986][87426] Updated weights for policy 1, policy_version 123010 (0.0011) -[2023-11-28 03:26:19,245][87424] Updated weights for policy 0, policy_version 123236 (0.0012) -[2023-11-28 03:26:19,368][87426] Updated weights for policy 1, policy_version 123020 (0.0010) -[2023-11-28 03:26:19,616][87424] Updated weights for policy 0, policy_version 123246 (0.0012) -[2023-11-28 03:26:19,735][87426] Updated weights for policy 1, policy_version 123030 (0.0007) -[2023-11-28 03:26:20,003][87424] Updated weights for policy 0, policy_version 123256 (0.0011) -[2023-11-28 03:26:20,119][87426] Updated weights for policy 1, policy_version 123040 (0.0011) -[2023-11-28 03:26:21,966][87424] Updated weights for policy 0, policy_version 123266 (0.0011) -[2023-11-28 03:26:22,052][87426] Updated weights for policy 1, policy_version 123050 (0.0011) -[2023-11-28 03:26:22,342][87424] Updated weights for policy 0, policy_version 123276 (0.0012) -[2023-11-28 03:26:22,429][87426] Updated weights for policy 1, policy_version 123060 (0.0010) -[2023-11-28 03:26:22,727][87424] Updated weights for policy 0, policy_version 123286 (0.0012) -[2023-11-28 03:26:22,807][87426] Updated weights for policy 1, policy_version 123070 (0.0008) -[2023-11-28 03:26:23,106][87424] Updated weights for policy 0, policy_version 123296 (0.0011) -[2023-11-28 03:26:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5526.1). Total num frames: 63070208. Throughput: 0: 2725.9, 1: 2698.7. Samples: 63080172. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:26:23,445][86177] Avg episode reward: [(0, '-514.750'), (1, '-609.880')] -[2023-11-28 03:26:24,980][87424] Updated weights for policy 0, policy_version 123306 (0.0012) -[2023-11-28 03:26:25,091][87426] Updated weights for policy 1, policy_version 123080 (0.0009) -[2023-11-28 03:26:25,356][87424] Updated weights for policy 0, policy_version 123316 (0.0011) -[2023-11-28 03:26:25,466][87426] Updated weights for policy 1, policy_version 123090 (0.0011) -[2023-11-28 03:26:25,744][87424] Updated weights for policy 0, policy_version 123326 (0.0011) -[2023-11-28 03:26:25,846][87426] Updated weights for policy 1, policy_version 123100 (0.0011) -[2023-11-28 03:26:27,397][87424] Updated weights for policy 0, policy_version 123336 (0.0012) -[2023-11-28 03:26:27,782][87424] Updated weights for policy 0, policy_version 123346 (0.0012) -[2023-11-28 03:26:28,160][87424] Updated weights for policy 0, policy_version 123356 (0.0012) -[2023-11-28 03:26:28,276][87426] Updated weights for policy 1, policy_version 123110 (0.0009) -[2023-11-28 03:26:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5498.4). Total num frames: 63094784. Throughput: 0: 2709.2, 1: 2730.7. Samples: 63105484. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:26:28,446][86177] Avg episode reward: [(0, '-505.510'), (1, '-614.220')] -[2023-11-28 03:26:28,665][87426] Updated weights for policy 1, policy_version 123120 (0.0007) -[2023-11-28 03:26:29,045][87426] Updated weights for policy 1, policy_version 123130 (0.0007) -[2023-11-28 03:26:30,645][87424] Updated weights for policy 0, policy_version 123366 (0.0012) -[2023-11-28 03:26:30,766][87426] Updated weights for policy 1, policy_version 123140 (0.0009) -[2023-11-28 03:26:31,027][87424] Updated weights for policy 0, policy_version 123376 (0.0011) -[2023-11-28 03:26:31,143][87426] Updated weights for policy 1, policy_version 123150 (0.0012) -[2023-11-28 03:26:31,417][87424] Updated weights for policy 0, policy_version 123386 (0.0009) -[2023-11-28 03:26:31,521][87426] Updated weights for policy 1, policy_version 123160 (0.0011) -[2023-11-28 03:26:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63119360. Throughput: 0: 2731.4, 1: 2726.5. Samples: 63129976. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:26:33,445][86177] Avg episode reward: [(0, '-506.990'), (1, '-604.270')] -[2023-11-28 03:26:33,480][87424] Updated weights for policy 0, policy_version 123396 (0.0011) -[2023-11-28 03:26:33,864][87424] Updated weights for policy 0, policy_version 123406 (0.0012) -[2023-11-28 03:26:33,946][87426] Updated weights for policy 1, policy_version 123170 (0.0010) -[2023-11-28 03:26:34,238][87424] Updated weights for policy 0, policy_version 123416 (0.0010) -[2023-11-28 03:26:34,323][87426] Updated weights for policy 1, policy_version 123180 (0.0007) -[2023-11-28 03:26:34,697][87426] Updated weights for policy 1, policy_version 123190 (0.0009) -[2023-11-28 03:26:35,074][87426] Updated weights for policy 1, policy_version 123200 (0.0010) -[2023-11-28 03:26:36,751][87424] Updated weights for policy 0, policy_version 123426 (0.0008) -[2023-11-28 03:26:37,135][87424] Updated weights for policy 0, policy_version 123436 (0.0010) -[2023-11-28 03:26:37,325][87426] Updated weights for policy 1, policy_version 123210 (0.0008) -[2023-11-28 03:26:37,517][87424] Updated weights for policy 0, policy_version 123446 (0.0010) -[2023-11-28 03:26:37,700][87426] Updated weights for policy 1, policy_version 123220 (0.0008) -[2023-11-28 03:26:37,898][87424] Updated weights for policy 0, policy_version 123456 (0.0007) -[2023-11-28 03:26:38,091][87426] Updated weights for policy 1, policy_version 123230 (0.0007) -[2023-11-28 03:26:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5526.1). Total num frames: 63152128. Throughput: 0: 2787.2, 1: 2696.8. Samples: 63163000. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:26:38,445][86177] Avg episode reward: [(0, '-517.950'), (1, '-581.630')] -[2023-11-28 03:26:39,778][87424] Updated weights for policy 0, policy_version 123466 (0.0011) -[2023-11-28 03:26:40,152][87424] Updated weights for policy 0, policy_version 123476 (0.0012) -[2023-11-28 03:26:40,530][87424] Updated weights for policy 0, policy_version 123486 (0.0011) -[2023-11-28 03:26:40,623][87426] Updated weights for policy 1, policy_version 123240 (0.0009) -[2023-11-28 03:26:41,001][87426] Updated weights for policy 1, policy_version 123250 (0.0008) -[2023-11-28 03:26:41,392][87426] Updated weights for policy 1, policy_version 123260 (0.0010) -[2023-11-28 03:26:42,952][87424] Updated weights for policy 0, policy_version 123496 (0.0011) -[2023-11-28 03:26:43,319][87424] Updated weights for policy 0, policy_version 123506 (0.0007) -[2023-11-28 03:26:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63168512. Throughput: 0: 2787.7, 1: 2637.3. Samples: 63185828. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:26:43,446][86177] Avg episode reward: [(0, '-509.070'), (1, '-582.540')] -[2023-11-28 03:26:43,698][87424] Updated weights for policy 0, policy_version 123516 (0.0007) -[2023-11-28 03:26:43,928][87426] Updated weights for policy 1, policy_version 123270 (0.0010) -[2023-11-28 03:26:44,313][87426] Updated weights for policy 1, policy_version 123280 (0.0009) -[2023-11-28 03:26:44,695][87426] Updated weights for policy 1, policy_version 123290 (0.0008) -[2023-11-28 03:26:46,254][87424] Updated weights for policy 0, policy_version 123526 (0.0010) -[2023-11-28 03:26:46,634][87424] Updated weights for policy 0, policy_version 123536 (0.0012) -[2023-11-28 03:26:46,713][87426] Updated weights for policy 1, policy_version 123300 (0.0009) -[2023-11-28 03:26:47,007][87424] Updated weights for policy 0, policy_version 123546 (0.0012) -[2023-11-28 03:26:47,092][87426] Updated weights for policy 1, policy_version 123310 (0.0010) -[2023-11-28 03:26:47,473][87426] Updated weights for policy 1, policy_version 123320 (0.0008) -[2023-11-28 03:26:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 63201280. Throughput: 0: 2741.2, 1: 2639.4. Samples: 63209100. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:26:48,445][86177] Avg episode reward: [(0, '-518.030'), (1, '-554.740')] -[2023-11-28 03:26:49,122][87424] Updated weights for policy 0, policy_version 123556 (0.0011) -[2023-11-28 03:26:49,502][87424] Updated weights for policy 0, policy_version 123566 (0.0012) -[2023-11-28 03:26:49,882][87426] Updated weights for policy 1, policy_version 123330 (0.0008) -[2023-11-28 03:26:49,883][87424] Updated weights for policy 0, policy_version 123576 (0.0011) -[2023-11-28 03:26:50,266][87426] Updated weights for policy 1, policy_version 123340 (0.0011) -[2023-11-28 03:26:50,645][87426] Updated weights for policy 1, policy_version 123350 (0.0011) -[2023-11-28 03:26:51,034][87426] Updated weights for policy 1, policy_version 123360 (0.0011) -[2023-11-28 03:26:52,265][87424] Updated weights for policy 0, policy_version 123586 (0.0011) -[2023-11-28 03:26:52,655][87424] Updated weights for policy 0, policy_version 123596 (0.0009) -[2023-11-28 03:26:53,048][87424] Updated weights for policy 0, policy_version 123606 (0.0009) -[2023-11-28 03:26:53,402][87426] Updated weights for policy 1, policy_version 123370 (0.0011) -[2023-11-28 03:26:53,424][87424] Updated weights for policy 0, policy_version 123616 (0.0011) -[2023-11-28 03:26:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 63225856. Throughput: 0: 2751.7, 1: 2632.9. Samples: 63241352. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:26:53,445][86177] Avg episode reward: [(0, '-517.800'), (1, '-559.060')] -[2023-11-28 03:26:53,784][87426] Updated weights for policy 1, policy_version 123380 (0.0011) -[2023-11-28 03:26:54,165][87426] Updated weights for policy 1, policy_version 123390 (0.0012) -[2023-11-28 03:26:55,280][87424] Updated weights for policy 0, policy_version 123626 (0.0011) -[2023-11-28 03:26:55,656][87424] Updated weights for policy 0, policy_version 123636 (0.0010) -[2023-11-28 03:26:56,031][87424] Updated weights for policy 0, policy_version 123646 (0.0010) -[2023-11-28 03:26:56,709][87426] Updated weights for policy 1, policy_version 123400 (0.0012) -[2023-11-28 03:26:57,072][87426] Updated weights for policy 1, policy_version 123410 (0.0009) -[2023-11-28 03:26:57,455][87426] Updated weights for policy 1, policy_version 123420 (0.0007) -[2023-11-28 03:26:58,291][87424] Updated weights for policy 0, policy_version 123656 (0.0011) -[2023-11-28 03:26:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63250432. Throughput: 0: 2770.0, 1: 2644.9. Samples: 63265936. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:26:58,445][86177] Avg episode reward: [(0, '-516.400'), (1, '-546.020')] -[2023-11-28 03:26:58,684][87424] Updated weights for policy 0, policy_version 123666 (0.0012) -[2023-11-28 03:26:59,058][87424] Updated weights for policy 0, policy_version 123676 (0.0011) -[2023-11-28 03:26:59,576][87426] Updated weights for policy 1, policy_version 123430 (0.0010) -[2023-11-28 03:26:59,946][87426] Updated weights for policy 1, policy_version 123440 (0.0012) -[2023-11-28 03:27:00,329][87426] Updated weights for policy 1, policy_version 123450 (0.0012) -[2023-11-28 03:27:01,130][87424] Updated weights for policy 0, policy_version 123686 (0.0010) -[2023-11-28 03:27:01,497][87424] Updated weights for policy 0, policy_version 123696 (0.0011) -[2023-11-28 03:27:01,882][87424] Updated weights for policy 0, policy_version 123706 (0.0012) -[2023-11-28 03:27:02,041][87426] Updated weights for policy 1, policy_version 123460 (0.0011) -[2023-11-28 03:27:02,418][87426] Updated weights for policy 1, policy_version 123470 (0.0011) -[2023-11-28 03:27:02,805][87426] Updated weights for policy 1, policy_version 123480 (0.0011) -[2023-11-28 03:27:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 63283200. Throughput: 0: 2753.2, 1: 2673.2. Samples: 63290848. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:27:03,445][86177] Avg episode reward: [(0, '-514.980'), (1, '-541.680')] -[2023-11-28 03:27:04,506][87424] Updated weights for policy 0, policy_version 123716 (0.0011) -[2023-11-28 03:27:04,586][87426] Updated weights for policy 1, policy_version 123490 (0.0011) -[2023-11-28 03:27:04,886][87424] Updated weights for policy 0, policy_version 123726 (0.0010) -[2023-11-28 03:27:04,956][87426] Updated weights for policy 1, policy_version 123500 (0.0011) -[2023-11-28 03:27:05,268][87424] Updated weights for policy 0, policy_version 123736 (0.0011) -[2023-11-28 03:27:05,344][87426] Updated weights for policy 1, policy_version 123510 (0.0010) -[2023-11-28 03:27:05,721][87426] Updated weights for policy 1, policy_version 123520 (0.0011) -[2023-11-28 03:27:07,532][87424] Updated weights for policy 0, policy_version 123746 (0.0011) -[2023-11-28 03:27:07,774][87426] Updated weights for policy 1, policy_version 123530 (0.0011) -[2023-11-28 03:27:07,914][87424] Updated weights for policy 0, policy_version 123756 (0.0011) -[2023-11-28 03:27:08,149][87426] Updated weights for policy 1, policy_version 123540 (0.0010) -[2023-11-28 03:27:08,293][87424] Updated weights for policy 0, policy_version 123766 (0.0012) -[2023-11-28 03:27:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 63299584. Throughput: 0: 2730.7, 1: 2699.7. Samples: 63324544. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:27:08,446][86177] Avg episode reward: [(0, '-503.660'), (1, '-538.180')] -[2023-11-28 03:27:08,537][87426] Updated weights for policy 1, policy_version 123550 (0.0007) -[2023-11-28 03:27:08,667][87424] Updated weights for policy 0, policy_version 123776 (0.0010) -[2023-11-28 03:27:11,083][87426] Updated weights for policy 1, policy_version 123560 (0.0011) -[2023-11-28 03:27:11,166][87424] Updated weights for policy 0, policy_version 123786 (0.0009) -[2023-11-28 03:27:11,462][87426] Updated weights for policy 1, policy_version 123570 (0.0012) -[2023-11-28 03:27:11,548][87424] Updated weights for policy 0, policy_version 123796 (0.0008) -[2023-11-28 03:27:11,833][87426] Updated weights for policy 1, policy_version 123580 (0.0011) -[2023-11-28 03:27:11,932][87424] Updated weights for policy 0, policy_version 123806 (0.0010) -[2023-11-28 03:27:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63332352. Throughput: 0: 2718.1, 1: 2665.3. Samples: 63347736. Policy #0 lag: (min: 23.0, avg: 34.1, max: 55.0) -[2023-11-28 03:27:13,445][86177] Avg episode reward: [(0, '-504.220'), (1, '-537.260')] -[2023-11-28 03:27:13,771][87424] Updated weights for policy 0, policy_version 123816 (0.0012) -[2023-11-28 03:27:13,874][87426] Updated weights for policy 1, policy_version 123590 (0.0010) -[2023-11-28 03:27:14,155][87424] Updated weights for policy 0, policy_version 123826 (0.0011) -[2023-11-28 03:27:14,255][87426] Updated weights for policy 1, policy_version 123600 (0.0012) -[2023-11-28 03:27:14,540][87424] Updated weights for policy 0, policy_version 123836 (0.0011) -[2023-11-28 03:27:14,629][87426] Updated weights for policy 1, policy_version 123610 (0.0009) -[2023-11-28 03:27:16,635][87424] Updated weights for policy 0, policy_version 123846 (0.0011) -[2023-11-28 03:27:16,956][87426] Updated weights for policy 1, policy_version 123620 (0.0008) -[2023-11-28 03:27:17,018][87424] Updated weights for policy 0, policy_version 123856 (0.0011) -[2023-11-28 03:27:17,330][87426] Updated weights for policy 1, policy_version 123630 (0.0007) -[2023-11-28 03:27:17,398][87424] Updated weights for policy 0, policy_version 123866 (0.0011) -[2023-11-28 03:27:17,710][87426] Updated weights for policy 1, policy_version 123640 (0.0010) -[2023-11-28 03:27:18,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 63365120. Throughput: 0: 2715.2, 1: 2662.8. Samples: 63371988. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:27:18,445][86177] Avg episode reward: [(0, '-497.690'), (1, '-538.190')] -[2023-11-28 03:27:19,798][87424] Updated weights for policy 0, policy_version 123876 (0.0009) -[2023-11-28 03:27:20,189][87424] Updated weights for policy 0, policy_version 123886 (0.0012) -[2023-11-28 03:27:20,244][87426] Updated weights for policy 1, policy_version 123650 (0.0012) -[2023-11-28 03:27:20,562][87424] Updated weights for policy 0, policy_version 123896 (0.0011) -[2023-11-28 03:27:20,624][87426] Updated weights for policy 1, policy_version 123660 (0.0009) -[2023-11-28 03:27:21,002][87426] Updated weights for policy 1, policy_version 123670 (0.0008) -[2023-11-28 03:27:21,379][87426] Updated weights for policy 1, policy_version 123680 (0.0010) -[2023-11-28 03:27:22,771][87424] Updated weights for policy 0, policy_version 123906 (0.0011) -[2023-11-28 03:27:23,155][87424] Updated weights for policy 0, policy_version 123916 (0.0008) -[2023-11-28 03:27:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5470.6). Total num frames: 63381504. Throughput: 0: 2674.8, 1: 2663.6. Samples: 63403228. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:27:23,445][86177] Avg episode reward: [(0, '-499.690'), (1, '-524.570')] -[2023-11-28 03:27:23,546][87424] Updated weights for policy 0, policy_version 123926 (0.0009) -[2023-11-28 03:27:23,705][87426] Updated weights for policy 1, policy_version 123690 (0.0011) -[2023-11-28 03:27:23,927][87424] Updated weights for policy 0, policy_version 123936 (0.0011) -[2023-11-28 03:27:24,080][87426] Updated weights for policy 1, policy_version 123700 (0.0012) -[2023-11-28 03:27:24,456][87426] Updated weights for policy 1, policy_version 123710 (0.0012) -[2023-11-28 03:27:25,950][87424] Updated weights for policy 0, policy_version 123946 (0.0010) -[2023-11-28 03:27:26,341][87424] Updated weights for policy 0, policy_version 123956 (0.0008) -[2023-11-28 03:27:26,728][87424] Updated weights for policy 0, policy_version 123966 (0.0009) -[2023-11-28 03:27:26,930][87426] Updated weights for policy 1, policy_version 123720 (0.0011) -[2023-11-28 03:27:27,304][87426] Updated weights for policy 1, policy_version 123730 (0.0008) -[2023-11-28 03:27:27,692][87426] Updated weights for policy 1, policy_version 123740 (0.0007) -[2023-11-28 03:27:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 63414272. Throughput: 0: 2683.7, 1: 2691.2. Samples: 63427696. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:27:28,445][86177] Avg episode reward: [(0, '-501.690'), (1, '-518.960')] -[2023-11-28 03:27:28,819][87424] Updated weights for policy 0, policy_version 123976 (0.0011) -[2023-11-28 03:27:29,190][87424] Updated weights for policy 0, policy_version 123986 (0.0012) -[2023-11-28 03:27:29,573][87424] Updated weights for policy 0, policy_version 123996 (0.0012) -[2023-11-28 03:27:30,252][87426] Updated weights for policy 1, policy_version 123750 (0.0010) -[2023-11-28 03:27:30,625][87426] Updated weights for policy 1, policy_version 123760 (0.0011) -[2023-11-28 03:27:31,003][87426] Updated weights for policy 1, policy_version 123770 (0.0011) -[2023-11-28 03:27:31,637][87424] Updated weights for policy 0, policy_version 124006 (0.0010) -[2023-11-28 03:27:32,014][87424] Updated weights for policy 0, policy_version 124016 (0.0011) -[2023-11-28 03:27:32,396][87424] Updated weights for policy 0, policy_version 124026 (0.0011) -[2023-11-28 03:27:33,177][87426] Updated weights for policy 1, policy_version 123780 (0.0011) -[2023-11-28 03:27:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 63438848. Throughput: 0: 2720.2, 1: 2678.2. Samples: 63452028. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:27:33,445][86177] Avg episode reward: [(0, '-501.190'), (1, '-572.880')] -[2023-11-28 03:27:33,555][87426] Updated weights for policy 1, policy_version 123790 (0.0011) -[2023-11-28 03:27:33,943][87426] Updated weights for policy 1, policy_version 123800 (0.0011) -[2023-11-28 03:27:34,564][87424] Updated weights for policy 0, policy_version 124036 (0.0009) -[2023-11-28 03:27:34,949][87424] Updated weights for policy 0, policy_version 124046 (0.0008) -[2023-11-28 03:27:35,334][87424] Updated weights for policy 0, policy_version 124056 (0.0009) -[2023-11-28 03:27:36,059][87426] Updated weights for policy 1, policy_version 123810 (0.0011) -[2023-11-28 03:27:36,431][87426] Updated weights for policy 1, policy_version 123820 (0.0011) -[2023-11-28 03:27:36,820][87426] Updated weights for policy 1, policy_version 123830 (0.0011) -[2023-11-28 03:27:36,972][87424] Updated weights for policy 0, policy_version 124066 (0.0011) -[2023-11-28 03:27:37,204][87426] Updated weights for policy 1, policy_version 123840 (0.0010) -[2023-11-28 03:27:37,340][87424] Updated weights for policy 0, policy_version 124076 (0.0012) -[2023-11-28 03:27:37,719][87424] Updated weights for policy 0, policy_version 124086 (0.0011) -[2023-11-28 03:27:38,106][87424] Updated weights for policy 0, policy_version 124096 (0.0011) -[2023-11-28 03:27:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 63471616. Throughput: 0: 2734.3, 1: 2680.3. Samples: 63485008. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:27:38,445][86177] Avg episode reward: [(0, '-499.500'), (1, '-586.890')] -[2023-11-28 03:27:39,282][87426] Updated weights for policy 1, policy_version 123850 (0.0012) -[2023-11-28 03:27:39,656][87426] Updated weights for policy 1, policy_version 123860 (0.0012) -[2023-11-28 03:27:40,035][87426] Updated weights for policy 1, policy_version 123870 (0.0011) -[2023-11-28 03:27:40,335][87424] Updated weights for policy 0, policy_version 124106 (0.0012) -[2023-11-28 03:27:40,723][87424] Updated weights for policy 0, policy_version 124116 (0.0010) -[2023-11-28 03:27:41,095][87424] Updated weights for policy 0, policy_version 124126 (0.0011) -[2023-11-28 03:27:42,225][87426] Updated weights for policy 1, policy_version 123880 (0.0012) -[2023-11-28 03:27:42,604][87426] Updated weights for policy 1, policy_version 123890 (0.0012) -[2023-11-28 03:27:42,983][87426] Updated weights for policy 1, policy_version 123900 (0.0011) -[2023-11-28 03:27:43,124][87424] Updated weights for policy 0, policy_version 124136 (0.0011) -[2023-11-28 03:27:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63496192. Throughput: 0: 2738.6, 1: 2681.3. Samples: 63509832. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:27:43,445][86177] Avg episode reward: [(0, '-497.810'), (1, '-603.670')] -[2023-11-28 03:27:43,518][87424] Updated weights for policy 0, policy_version 124146 (0.0011) -[2023-11-28 03:27:43,899][87424] Updated weights for policy 0, policy_version 124156 (0.0008) -[2023-11-28 03:27:45,249][87426] Updated weights for policy 1, policy_version 123910 (0.0011) -[2023-11-28 03:27:45,615][87426] Updated weights for policy 1, policy_version 123920 (0.0012) -[2023-11-28 03:27:45,995][87426] Updated weights for policy 1, policy_version 123930 (0.0012) -[2023-11-28 03:27:46,182][87424] Updated weights for policy 0, policy_version 124166 (0.0010) -[2023-11-28 03:27:46,558][87424] Updated weights for policy 0, policy_version 124176 (0.0012) -[2023-11-28 03:27:46,936][87424] Updated weights for policy 0, policy_version 124186 (0.0012) -[2023-11-28 03:27:47,755][87426] Updated weights for policy 1, policy_version 123940 (0.0011) -[2023-11-28 03:27:48,134][87426] Updated weights for policy 1, policy_version 123950 (0.0012) -[2023-11-28 03:27:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 63520768. Throughput: 0: 2735.2, 1: 2680.4. Samples: 63534552. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:27:48,445][86177] Avg episode reward: [(0, '-496.220'), (1, '-597.690')] -[2023-11-28 03:27:48,519][87426] Updated weights for policy 1, policy_version 123960 (0.0012) -[2023-11-28 03:27:48,871][87424] Updated weights for policy 0, policy_version 124196 (0.0010) -[2023-11-28 03:27:49,251][87424] Updated weights for policy 0, policy_version 124206 (0.0011) -[2023-11-28 03:27:49,623][87424] Updated weights for policy 0, policy_version 124216 (0.0012) -[2023-11-28 03:27:50,749][87426] Updated weights for policy 1, policy_version 123970 (0.0012) -[2023-11-28 03:27:51,129][87426] Updated weights for policy 1, policy_version 123980 (0.0012) -[2023-11-28 03:27:51,507][87426] Updated weights for policy 1, policy_version 123990 (0.0011) -[2023-11-28 03:27:51,805][87424] Updated weights for policy 0, policy_version 124226 (0.0011) -[2023-11-28 03:27:51,892][87426] Updated weights for policy 1, policy_version 124000 (0.0012) -[2023-11-28 03:27:52,195][87424] Updated weights for policy 0, policy_version 124236 (0.0009) -[2023-11-28 03:27:52,576][87424] Updated weights for policy 0, policy_version 124246 (0.0008) -[2023-11-28 03:27:52,956][87424] Updated weights for policy 0, policy_version 124256 (0.0010) -[2023-11-28 03:27:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63553536. Throughput: 0: 2737.8, 1: 2647.9. Samples: 63566900. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:27:53,445][86177] Avg episode reward: [(0, '-495.820'), (1, '-542.780')] -[2023-11-28 03:27:54,216][87426] Updated weights for policy 1, policy_version 124010 (0.0012) -[2023-11-28 03:27:54,594][87426] Updated weights for policy 1, policy_version 124020 (0.0012) -[2023-11-28 03:27:54,956][87424] Updated weights for policy 0, policy_version 124266 (0.0008) -[2023-11-28 03:27:54,973][87426] Updated weights for policy 1, policy_version 124030 (0.0011) -[2023-11-28 03:27:55,335][87424] Updated weights for policy 0, policy_version 124276 (0.0011) -[2023-11-28 03:27:55,720][87424] Updated weights for policy 0, policy_version 124286 (0.0007) -[2023-11-28 03:27:57,137][87426] Updated weights for policy 1, policy_version 124040 (0.0008) -[2023-11-28 03:27:57,525][87426] Updated weights for policy 1, policy_version 124050 (0.0007) -[2023-11-28 03:27:57,903][87426] Updated weights for policy 1, policy_version 124060 (0.0008) -[2023-11-28 03:27:57,908][87424] Updated weights for policy 0, policy_version 124296 (0.0008) -[2023-11-28 03:27:58,295][87424] Updated weights for policy 0, policy_version 124306 (0.0007) -[2023-11-28 03:27:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63578112. Throughput: 0: 2750.4, 1: 2671.4. Samples: 63591716. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:27:58,445][86177] Avg episode reward: [(0, '-499.720'), (1, '-547.690')] -[2023-11-28 03:27:58,684][87424] Updated weights for policy 0, policy_version 124316 (0.0008) -[2023-11-28 03:27:59,907][87426] Updated weights for policy 1, policy_version 124070 (0.0008) -[2023-11-28 03:28:00,287][87426] Updated weights for policy 1, policy_version 124080 (0.0007) -[2023-11-28 03:28:00,667][87426] Updated weights for policy 1, policy_version 124090 (0.0008) -[2023-11-28 03:28:00,991][87424] Updated weights for policy 0, policy_version 124326 (0.0007) -[2023-11-28 03:28:01,373][87424] Updated weights for policy 0, policy_version 124336 (0.0010) -[2023-11-28 03:28:01,767][87424] Updated weights for policy 0, policy_version 124346 (0.0010) -[2023-11-28 03:28:02,722][87426] Updated weights for policy 1, policy_version 124100 (0.0009) -[2023-11-28 03:28:03,095][87426] Updated weights for policy 1, policy_version 124110 (0.0011) -[2023-11-28 03:28:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 63602688. Throughput: 0: 2758.0, 1: 2681.8. Samples: 63616780. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:28:03,446][86177] Avg episode reward: [(0, '-503.470'), (1, '-529.480')] -[2023-11-28 03:28:03,473][87426] Updated weights for policy 1, policy_version 124120 (0.0012) -[2023-11-28 03:28:04,046][87424] Updated weights for policy 0, policy_version 124356 (0.0009) -[2023-11-28 03:28:04,438][87424] Updated weights for policy 0, policy_version 124366 (0.0008) -[2023-11-28 03:28:04,812][87424] Updated weights for policy 0, policy_version 124376 (0.0012) -[2023-11-28 03:28:05,793][87426] Updated weights for policy 1, policy_version 124130 (0.0011) -[2023-11-28 03:28:06,165][87426] Updated weights for policy 1, policy_version 124140 (0.0008) -[2023-11-28 03:28:06,548][87426] Updated weights for policy 1, policy_version 124150 (0.0009) -[2023-11-28 03:28:06,559][87424] Updated weights for policy 0, policy_version 124386 (0.0012) -[2023-11-28 03:28:06,930][87426] Updated weights for policy 1, policy_version 124160 (0.0010) -[2023-11-28 03:28:06,942][87424] Updated weights for policy 0, policy_version 124396 (0.0011) -[2023-11-28 03:28:07,332][87424] Updated weights for policy 0, policy_version 124406 (0.0011) -[2023-11-28 03:28:07,704][87424] Updated weights for policy 0, policy_version 124416 (0.0012) -[2023-11-28 03:28:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 63635456. Throughput: 0: 2767.5, 1: 2731.2. Samples: 63650668. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:28:08,445][86177] Avg episode reward: [(0, '-506.240'), (1, '-531.630')] -[2023-11-28 03:28:08,726][87426] Updated weights for policy 1, policy_version 124170 (0.0012) -[2023-11-28 03:28:09,096][87426] Updated weights for policy 1, policy_version 124180 (0.0012) -[2023-11-28 03:28:09,478][87426] Updated weights for policy 1, policy_version 124190 (0.0012) -[2023-11-28 03:28:09,640][87424] Updated weights for policy 0, policy_version 124426 (0.0012) -[2023-11-28 03:28:10,011][87424] Updated weights for policy 0, policy_version 124436 (0.0012) -[2023-11-28 03:28:10,396][87424] Updated weights for policy 0, policy_version 124446 (0.0011) -[2023-11-28 03:28:11,276][87426] Updated weights for policy 1, policy_version 124200 (0.0009) -[2023-11-28 03:28:11,663][87426] Updated weights for policy 1, policy_version 124210 (0.0008) -[2023-11-28 03:28:12,043][87426] Updated weights for policy 1, policy_version 124220 (0.0011) -[2023-11-28 03:28:12,919][87424] Updated weights for policy 0, policy_version 124456 (0.0009) -[2023-11-28 03:28:13,307][87424] Updated weights for policy 0, policy_version 124466 (0.0011) -[2023-11-28 03:28:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63660032. Throughput: 0: 2768.6, 1: 2734.2. Samples: 63675324. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:28:13,445][86177] Avg episode reward: [(0, '-505.740'), (1, '-512.010')] -[2023-11-28 03:28:13,700][87424] Updated weights for policy 0, policy_version 124476 (0.0010) -[2023-11-28 03:28:14,120][87426] Updated weights for policy 1, policy_version 124230 (0.0011) -[2023-11-28 03:28:14,501][87426] Updated weights for policy 1, policy_version 124240 (0.0012) -[2023-11-28 03:28:14,876][87426] Updated weights for policy 1, policy_version 124250 (0.0010) -[2023-11-28 03:28:16,086][87424] Updated weights for policy 0, policy_version 124486 (0.0011) -[2023-11-28 03:28:16,460][87424] Updated weights for policy 0, policy_version 124496 (0.0012) -[2023-11-28 03:28:16,705][87426] Updated weights for policy 1, policy_version 124260 (0.0011) -[2023-11-28 03:28:16,839][87424] Updated weights for policy 0, policy_version 124506 (0.0011) -[2023-11-28 03:28:17,098][87426] Updated weights for policy 1, policy_version 124270 (0.0011) -[2023-11-28 03:28:17,473][87426] Updated weights for policy 1, policy_version 124280 (0.0012) -[2023-11-28 03:28:18,445][86177] Fps is (10 sec: 5734.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63692800. Throughput: 0: 2748.8, 1: 2758.6. Samples: 63699864. Policy #0 lag: (min: 31.0, avg: 38.5, max: 63.0) -[2023-11-28 03:28:18,446][86177] Avg episode reward: [(0, '-503.890'), (1, '-511.890')] -[2023-11-28 03:28:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000124288_31817728.pth... -[2023-11-28 03:28:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000124512_31875072.pth... -[2023-11-28 03:28:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000121760_31170560.pth -[2023-11-28 03:28:18,506][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000121952_31219712.pth -[2023-11-28 03:28:19,289][87424] Updated weights for policy 0, policy_version 124516 (0.0010) -[2023-11-28 03:28:19,670][87424] Updated weights for policy 0, policy_version 124526 (0.0008) -[2023-11-28 03:28:19,716][87426] Updated weights for policy 1, policy_version 124290 (0.0012) -[2023-11-28 03:28:20,051][87424] Updated weights for policy 0, policy_version 124536 (0.0009) -[2023-11-28 03:28:20,096][87426] Updated weights for policy 1, policy_version 124300 (0.0010) -[2023-11-28 03:28:20,466][87426] Updated weights for policy 1, policy_version 124310 (0.0010) -[2023-11-28 03:28:20,842][87426] Updated weights for policy 1, policy_version 124320 (0.0007) -[2023-11-28 03:28:22,088][87424] Updated weights for policy 0, policy_version 124546 (0.0009) -[2023-11-28 03:28:22,482][87424] Updated weights for policy 0, policy_version 124556 (0.0009) -[2023-11-28 03:28:22,785][87426] Updated weights for policy 1, policy_version 124330 (0.0011) -[2023-11-28 03:28:22,849][87424] Updated weights for policy 0, policy_version 124566 (0.0009) -[2023-11-28 03:28:23,161][87426] Updated weights for policy 1, policy_version 124340 (0.0010) -[2023-11-28 03:28:23,226][87424] Updated weights for policy 0, policy_version 124576 (0.0010) -[2023-11-28 03:28:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 63717376. Throughput: 0: 2729.2, 1: 2784.7. Samples: 63733132. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:28:23,445][86177] Avg episode reward: [(0, '-501.410'), (1, '-501.780')] -[2023-11-28 03:28:23,540][87426] Updated weights for policy 1, policy_version 124350 (0.0011) -[2023-11-28 03:28:25,255][87424] Updated weights for policy 0, policy_version 124586 (0.0012) -[2023-11-28 03:28:25,630][87424] Updated weights for policy 0, policy_version 124596 (0.0012) -[2023-11-28 03:28:26,012][87424] Updated weights for policy 0, policy_version 124606 (0.0012) -[2023-11-28 03:28:26,014][87426] Updated weights for policy 1, policy_version 124360 (0.0009) -[2023-11-28 03:28:26,399][87426] Updated weights for policy 1, policy_version 124370 (0.0012) -[2023-11-28 03:28:26,774][87426] Updated weights for policy 1, policy_version 124380 (0.0012) -[2023-11-28 03:28:27,899][87424] Updated weights for policy 0, policy_version 124616 (0.0012) -[2023-11-28 03:28:28,279][87424] Updated weights for policy 0, policy_version 124626 (0.0011) -[2023-11-28 03:28:28,444][86177] Fps is (10 sec: 4915.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63741952. Throughput: 0: 2721.1, 1: 2795.6. Samples: 63758084. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:28:28,445][86177] Avg episode reward: [(0, '-501.840'), (1, '-504.200')] -[2023-11-28 03:28:28,667][87424] Updated weights for policy 0, policy_version 124636 (0.0008) -[2023-11-28 03:28:29,187][87426] Updated weights for policy 1, policy_version 124390 (0.0009) -[2023-11-28 03:28:29,573][87426] Updated weights for policy 1, policy_version 124400 (0.0007) -[2023-11-28 03:28:29,943][87426] Updated weights for policy 1, policy_version 124410 (0.0009) -[2023-11-28 03:28:30,982][87424] Updated weights for policy 0, policy_version 124646 (0.0009) -[2023-11-28 03:28:31,353][87424] Updated weights for policy 0, policy_version 124656 (0.0008) -[2023-11-28 03:28:31,735][87424] Updated weights for policy 0, policy_version 124666 (0.0011) -[2023-11-28 03:28:32,194][87426] Updated weights for policy 1, policy_version 124420 (0.0010) -[2023-11-28 03:28:32,573][87426] Updated weights for policy 1, policy_version 124430 (0.0012) -[2023-11-28 03:28:32,948][87426] Updated weights for policy 1, policy_version 124440 (0.0012) -[2023-11-28 03:28:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 63774720. Throughput: 0: 2718.1, 1: 2790.7. Samples: 63782448. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:28:33,445][86177] Avg episode reward: [(0, '-498.890'), (1, '-505.970')] -[2023-11-28 03:28:34,110][87424] Updated weights for policy 0, policy_version 124676 (0.0012) -[2023-11-28 03:28:34,497][87424] Updated weights for policy 0, policy_version 124686 (0.0011) -[2023-11-28 03:28:34,645][87426] Updated weights for policy 1, policy_version 124450 (0.0011) -[2023-11-28 03:28:34,879][87424] Updated weights for policy 0, policy_version 124696 (0.0011) -[2023-11-28 03:28:35,022][87426] Updated weights for policy 1, policy_version 124460 (0.0010) -[2023-11-28 03:28:35,414][87426] Updated weights for policy 1, policy_version 124470 (0.0009) -[2023-11-28 03:28:35,781][87426] Updated weights for policy 1, policy_version 124480 (0.0007) -[2023-11-28 03:28:37,410][87424] Updated weights for policy 0, policy_version 124706 (0.0011) -[2023-11-28 03:28:37,462][87426] Updated weights for policy 1, policy_version 124490 (0.0012) -[2023-11-28 03:28:37,795][87424] Updated weights for policy 0, policy_version 124716 (0.0007) -[2023-11-28 03:28:37,830][87426] Updated weights for policy 1, policy_version 124500 (0.0011) -[2023-11-28 03:28:38,184][87424] Updated weights for policy 0, policy_version 124726 (0.0007) -[2023-11-28 03:28:38,209][87426] Updated weights for policy 1, policy_version 124510 (0.0008) -[2023-11-28 03:28:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 63799296. Throughput: 0: 2741.0, 1: 2803.1. Samples: 63816384. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:28:38,446][86177] Avg episode reward: [(0, '-502.580'), (1, '-525.380')] -[2023-11-28 03:28:38,568][87424] Updated weights for policy 0, policy_version 124736 (0.0008) -[2023-11-28 03:28:40,601][87426] Updated weights for policy 1, policy_version 124520 (0.0009) -[2023-11-28 03:28:40,981][87426] Updated weights for policy 1, policy_version 124530 (0.0008) -[2023-11-28 03:28:40,989][87424] Updated weights for policy 0, policy_version 124746 (0.0010) -[2023-11-28 03:28:41,357][87426] Updated weights for policy 1, policy_version 124540 (0.0009) -[2023-11-28 03:28:41,375][87424] Updated weights for policy 0, policy_version 124756 (0.0008) -[2023-11-28 03:28:41,760][87424] Updated weights for policy 0, policy_version 124766 (0.0009) -[2023-11-28 03:28:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63823872. Throughput: 0: 2718.3, 1: 2794.6. Samples: 63839796. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:28:43,445][86177] Avg episode reward: [(0, '-498.780'), (1, '-532.830')] -[2023-11-28 03:28:43,877][87424] Updated weights for policy 0, policy_version 124776 (0.0011) -[2023-11-28 03:28:43,995][87426] Updated weights for policy 1, policy_version 124550 (0.0009) -[2023-11-28 03:28:44,260][87424] Updated weights for policy 0, policy_version 124786 (0.0008) -[2023-11-28 03:28:44,378][87426] Updated weights for policy 1, policy_version 124560 (0.0011) -[2023-11-28 03:28:44,651][87424] Updated weights for policy 0, policy_version 124796 (0.0007) -[2023-11-28 03:28:44,754][87426] Updated weights for policy 1, policy_version 124570 (0.0011) -[2023-11-28 03:28:46,305][87424] Updated weights for policy 0, policy_version 124806 (0.0011) -[2023-11-28 03:28:46,693][87424] Updated weights for policy 0, policy_version 124816 (0.0012) -[2023-11-28 03:28:46,704][87426] Updated weights for policy 1, policy_version 124580 (0.0012) -[2023-11-28 03:28:47,073][87424] Updated weights for policy 0, policy_version 124826 (0.0010) -[2023-11-28 03:28:47,074][87426] Updated weights for policy 1, policy_version 124590 (0.0010) -[2023-11-28 03:28:47,460][87426] Updated weights for policy 1, policy_version 124600 (0.0010) -[2023-11-28 03:28:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 63856640. Throughput: 0: 2695.8, 1: 2796.1. Samples: 63863916. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:28:48,445][86177] Avg episode reward: [(0, '-503.570'), (1, '-519.310')] -[2023-11-28 03:28:49,557][87424] Updated weights for policy 0, policy_version 124836 (0.0011) -[2023-11-28 03:28:49,559][87426] Updated weights for policy 1, policy_version 124610 (0.0010) -[2023-11-28 03:28:49,938][87424] Updated weights for policy 0, policy_version 124846 (0.0011) -[2023-11-28 03:28:49,943][87426] Updated weights for policy 1, policy_version 124620 (0.0010) -[2023-11-28 03:28:50,318][87424] Updated weights for policy 0, policy_version 124856 (0.0010) -[2023-11-28 03:28:50,320][87426] Updated weights for policy 1, policy_version 124630 (0.0007) -[2023-11-28 03:28:50,701][87426] Updated weights for policy 1, policy_version 124640 (0.0009) -[2023-11-28 03:28:52,278][87424] Updated weights for policy 0, policy_version 124866 (0.0010) -[2023-11-28 03:28:52,661][87424] Updated weights for policy 0, policy_version 124876 (0.0010) -[2023-11-28 03:28:53,044][87424] Updated weights for policy 0, policy_version 124886 (0.0009) -[2023-11-28 03:28:53,172][87426] Updated weights for policy 1, policy_version 124650 (0.0011) -[2023-11-28 03:28:53,431][87424] Updated weights for policy 0, policy_version 124896 (0.0010) -[2023-11-28 03:28:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 63881216. Throughput: 0: 2704.0, 1: 2753.6. Samples: 63896260. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:28:53,445][86177] Avg episode reward: [(0, '-506.150'), (1, '-517.400')] -[2023-11-28 03:28:53,559][87426] Updated weights for policy 1, policy_version 124660 (0.0011) -[2023-11-28 03:28:53,929][87426] Updated weights for policy 1, policy_version 124670 (0.0011) -[2023-11-28 03:28:55,545][87424] Updated weights for policy 0, policy_version 124906 (0.0011) -[2023-11-28 03:28:55,788][87426] Updated weights for policy 1, policy_version 124680 (0.0011) -[2023-11-28 03:28:55,930][87424] Updated weights for policy 0, policy_version 124916 (0.0008) -[2023-11-28 03:28:56,168][87426] Updated weights for policy 1, policy_version 124690 (0.0012) -[2023-11-28 03:28:56,312][87424] Updated weights for policy 0, policy_version 124926 (0.0007) -[2023-11-28 03:28:56,545][87426] Updated weights for policy 1, policy_version 124700 (0.0011) -[2023-11-28 03:28:58,431][87424] Updated weights for policy 0, policy_version 124936 (0.0011) -[2023-11-28 03:28:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63905792. Throughput: 0: 2704.2, 1: 2767.6. Samples: 63921552. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:28:58,445][86177] Avg episode reward: [(0, '-505.560'), (1, '-523.310')] -[2023-11-28 03:28:58,813][87424] Updated weights for policy 0, policy_version 124946 (0.0011) -[2023-11-28 03:28:59,014][87426] Updated weights for policy 1, policy_version 124710 (0.0017) -[2023-11-28 03:28:59,198][87424] Updated weights for policy 0, policy_version 124956 (0.0012) -[2023-11-28 03:28:59,389][87426] Updated weights for policy 1, policy_version 124720 (0.0007) -[2023-11-28 03:28:59,791][87426] Updated weights for policy 1, policy_version 124730 (0.0009) -[2023-11-28 03:29:01,525][87424] Updated weights for policy 0, policy_version 124966 (0.0010) -[2023-11-28 03:29:01,633][87426] Updated weights for policy 1, policy_version 124740 (0.0011) -[2023-11-28 03:29:01,919][87424] Updated weights for policy 0, policy_version 124976 (0.0012) -[2023-11-28 03:29:02,007][87426] Updated weights for policy 1, policy_version 124750 (0.0011) -[2023-11-28 03:29:02,290][87424] Updated weights for policy 0, policy_version 124986 (0.0011) -[2023-11-28 03:29:02,385][87426] Updated weights for policy 1, policy_version 124760 (0.0009) -[2023-11-28 03:29:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 63938560. Throughput: 0: 2721.0, 1: 2760.4. Samples: 63946524. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:29:03,445][86177] Avg episode reward: [(0, '-498.990'), (1, '-568.600')] -[2023-11-28 03:29:04,131][87424] Updated weights for policy 0, policy_version 124996 (0.0009) -[2023-11-28 03:29:04,508][87424] Updated weights for policy 0, policy_version 125006 (0.0012) -[2023-11-28 03:29:04,891][87424] Updated weights for policy 0, policy_version 125016 (0.0010) -[2023-11-28 03:29:04,895][87426] Updated weights for policy 1, policy_version 124770 (0.0009) -[2023-11-28 03:29:05,280][87426] Updated weights for policy 1, policy_version 124780 (0.0008) -[2023-11-28 03:29:05,662][87426] Updated weights for policy 1, policy_version 124790 (0.0007) -[2023-11-28 03:29:06,044][87426] Updated weights for policy 1, policy_version 124800 (0.0007) -[2023-11-28 03:29:06,815][87424] Updated weights for policy 0, policy_version 125026 (0.0012) -[2023-11-28 03:29:07,200][87424] Updated weights for policy 0, policy_version 125036 (0.0011) -[2023-11-28 03:29:07,594][87424] Updated weights for policy 0, policy_version 125046 (0.0012) -[2023-11-28 03:29:07,969][87424] Updated weights for policy 0, policy_version 125056 (0.0010) -[2023-11-28 03:29:08,063][87426] Updated weights for policy 1, policy_version 124810 (0.0011) -[2023-11-28 03:29:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 63963136. Throughput: 0: 2751.6, 1: 2748.8. Samples: 63980648. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:29:08,445][86177] Avg episode reward: [(0, '-499.690'), (1, '-583.720')] -[2023-11-28 03:29:08,446][87426] Updated weights for policy 1, policy_version 124820 (0.0012) -[2023-11-28 03:29:08,827][87426] Updated weights for policy 1, policy_version 124830 (0.0012) -[2023-11-28 03:29:10,481][87424] Updated weights for policy 0, policy_version 125066 (0.0010) -[2023-11-28 03:29:10,861][87424] Updated weights for policy 0, policy_version 125076 (0.0009) -[2023-11-28 03:29:11,017][87426] Updated weights for policy 1, policy_version 124840 (0.0012) -[2023-11-28 03:29:11,245][87424] Updated weights for policy 0, policy_version 125086 (0.0012) -[2023-11-28 03:29:11,395][87426] Updated weights for policy 1, policy_version 124850 (0.0010) -[2023-11-28 03:29:11,779][87426] Updated weights for policy 1, policy_version 124860 (0.0009) -[2023-11-28 03:29:13,326][87424] Updated weights for policy 0, policy_version 125096 (0.0011) -[2023-11-28 03:29:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 63987712. Throughput: 0: 2752.4, 1: 2740.7. Samples: 64005272. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:29:13,445][86177] Avg episode reward: [(0, '-498.960'), (1, '-594.780')] -[2023-11-28 03:29:13,705][87424] Updated weights for policy 0, policy_version 125106 (0.0008) -[2023-11-28 03:29:14,072][87426] Updated weights for policy 1, policy_version 124870 (0.0009) -[2023-11-28 03:29:14,097][87424] Updated weights for policy 0, policy_version 125116 (0.0011) -[2023-11-28 03:29:14,452][87426] Updated weights for policy 1, policy_version 124880 (0.0011) -[2023-11-28 03:29:14,827][87426] Updated weights for policy 1, policy_version 124890 (0.0012) -[2023-11-28 03:29:16,377][87424] Updated weights for policy 0, policy_version 125126 (0.0010) -[2023-11-28 03:29:16,777][87424] Updated weights for policy 0, policy_version 125136 (0.0008) -[2023-11-28 03:29:17,071][87426] Updated weights for policy 1, policy_version 124900 (0.0011) -[2023-11-28 03:29:17,153][87424] Updated weights for policy 0, policy_version 125146 (0.0008) -[2023-11-28 03:29:17,444][87426] Updated weights for policy 1, policy_version 124910 (0.0010) -[2023-11-28 03:29:17,821][87426] Updated weights for policy 1, policy_version 124920 (0.0008) -[2023-11-28 03:29:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 64020480. Throughput: 0: 2743.8, 1: 2735.0. Samples: 64028996. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:29:18,445][86177] Avg episode reward: [(0, '-497.360'), (1, '-586.510')] -[2023-11-28 03:29:19,022][87424] Updated weights for policy 0, policy_version 125156 (0.0009) -[2023-11-28 03:29:19,402][87424] Updated weights for policy 0, policy_version 125166 (0.0007) -[2023-11-28 03:29:19,790][87424] Updated weights for policy 0, policy_version 125176 (0.0008) -[2023-11-28 03:29:20,194][87426] Updated weights for policy 1, policy_version 124930 (0.0008) -[2023-11-28 03:29:20,573][87426] Updated weights for policy 1, policy_version 124940 (0.0010) -[2023-11-28 03:29:20,954][87426] Updated weights for policy 1, policy_version 124950 (0.0011) -[2023-11-28 03:29:21,333][87426] Updated weights for policy 1, policy_version 124960 (0.0009) -[2023-11-28 03:29:21,743][87424] Updated weights for policy 0, policy_version 125186 (0.0010) -[2023-11-28 03:29:22,125][87424] Updated weights for policy 0, policy_version 125196 (0.0009) -[2023-11-28 03:29:22,508][87424] Updated weights for policy 0, policy_version 125206 (0.0010) -[2023-11-28 03:29:22,891][87424] Updated weights for policy 0, policy_version 125216 (0.0011) -[2023-11-28 03:29:23,389][87426] Updated weights for policy 1, policy_version 124970 (0.0008) -[2023-11-28 03:29:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 64045056. Throughput: 0: 2719.0, 1: 2730.3. Samples: 64061604. Policy #0 lag: (min: 10.0, avg: 32.6, max: 42.0) -[2023-11-28 03:29:23,445][86177] Avg episode reward: [(0, '-497.690'), (1, '-555.230')] -[2023-11-28 03:29:23,774][87426] Updated weights for policy 1, policy_version 124980 (0.0008) -[2023-11-28 03:29:24,154][87426] Updated weights for policy 1, policy_version 124990 (0.0008) -[2023-11-28 03:29:25,465][87424] Updated weights for policy 0, policy_version 125226 (0.0008) -[2023-11-28 03:29:25,849][87424] Updated weights for policy 0, policy_version 125236 (0.0010) -[2023-11-28 03:29:26,236][87424] Updated weights for policy 0, policy_version 125246 (0.0008) -[2023-11-28 03:29:26,408][87426] Updated weights for policy 1, policy_version 125000 (0.0008) -[2023-11-28 03:29:26,785][87426] Updated weights for policy 1, policy_version 125010 (0.0007) -[2023-11-28 03:29:27,164][87426] Updated weights for policy 1, policy_version 125020 (0.0009) -[2023-11-28 03:29:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64069632. Throughput: 0: 2729.2, 1: 2728.7. Samples: 64085400. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:29:28,445][86177] Avg episode reward: [(0, '-500.480'), (1, '-556.040')] -[2023-11-28 03:29:28,488][87424] Updated weights for policy 0, policy_version 125256 (0.0007) -[2023-11-28 03:29:28,881][87424] Updated weights for policy 0, policy_version 125266 (0.0008) -[2023-11-28 03:29:29,260][87424] Updated weights for policy 0, policy_version 125276 (0.0010) -[2023-11-28 03:29:29,586][87426] Updated weights for policy 1, policy_version 125030 (0.0007) -[2023-11-28 03:29:29,965][87426] Updated weights for policy 1, policy_version 125040 (0.0009) -[2023-11-28 03:29:30,346][87426] Updated weights for policy 1, policy_version 125050 (0.0011) -[2023-11-28 03:29:31,342][87424] Updated weights for policy 0, policy_version 125286 (0.0009) -[2023-11-28 03:29:31,733][87424] Updated weights for policy 0, policy_version 125296 (0.0010) -[2023-11-28 03:29:32,114][87424] Updated weights for policy 0, policy_version 125306 (0.0008) -[2023-11-28 03:29:32,326][87426] Updated weights for policy 1, policy_version 125060 (0.0010) -[2023-11-28 03:29:32,697][87426] Updated weights for policy 1, policy_version 125070 (0.0011) -[2023-11-28 03:29:33,086][87426] Updated weights for policy 1, policy_version 125080 (0.0008) -[2023-11-28 03:29:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64102400. Throughput: 0: 2750.8, 1: 2721.7. Samples: 64110180. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:29:33,446][86177] Avg episode reward: [(0, '-501.890'), (1, '-564.100')] -[2023-11-28 03:29:34,226][87424] Updated weights for policy 0, policy_version 125316 (0.0010) -[2023-11-28 03:29:34,609][87424] Updated weights for policy 0, policy_version 125326 (0.0012) -[2023-11-28 03:29:35,001][87424] Updated weights for policy 0, policy_version 125336 (0.0012) -[2023-11-28 03:29:35,442][87426] Updated weights for policy 1, policy_version 125090 (0.0008) -[2023-11-28 03:29:35,825][87426] Updated weights for policy 1, policy_version 125100 (0.0009) -[2023-11-28 03:29:36,203][87426] Updated weights for policy 1, policy_version 125110 (0.0011) -[2023-11-28 03:29:36,576][87426] Updated weights for policy 1, policy_version 125120 (0.0007) -[2023-11-28 03:29:37,020][87424] Updated weights for policy 0, policy_version 125346 (0.0011) -[2023-11-28 03:29:37,409][87424] Updated weights for policy 0, policy_version 125356 (0.0011) -[2023-11-28 03:29:37,787][87424] Updated weights for policy 0, policy_version 125366 (0.0008) -[2023-11-28 03:29:38,167][87424] Updated weights for policy 0, policy_version 125376 (0.0010) -[2023-11-28 03:29:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64126976. Throughput: 0: 2773.8, 1: 2736.8. Samples: 64144236. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:29:38,445][86177] Avg episode reward: [(0, '-500.330'), (1, '-546.530')] -[2023-11-28 03:29:38,553][87426] Updated weights for policy 1, policy_version 125130 (0.0007) -[2023-11-28 03:29:38,925][87426] Updated weights for policy 1, policy_version 125140 (0.0008) -[2023-11-28 03:29:39,321][87426] Updated weights for policy 1, policy_version 125150 (0.0012) -[2023-11-28 03:29:39,905][87424] Updated weights for policy 0, policy_version 125386 (0.0010) -[2023-11-28 03:29:40,277][87424] Updated weights for policy 0, policy_version 125396 (0.0009) -[2023-11-28 03:29:40,657][87424] Updated weights for policy 0, policy_version 125406 (0.0011) -[2023-11-28 03:29:41,747][87426] Updated weights for policy 1, policy_version 125160 (0.0009) -[2023-11-28 03:29:42,128][87426] Updated weights for policy 1, policy_version 125170 (0.0011) -[2023-11-28 03:29:42,511][87426] Updated weights for policy 1, policy_version 125180 (0.0011) -[2023-11-28 03:29:43,079][87424] Updated weights for policy 0, policy_version 125416 (0.0011) -[2023-11-28 03:29:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64151552. Throughput: 0: 2768.6, 1: 2707.7. Samples: 64167988. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:29:43,445][86177] Avg episode reward: [(0, '-499.780'), (1, '-531.000')] -[2023-11-28 03:29:43,465][87424] Updated weights for policy 0, policy_version 125426 (0.0011) -[2023-11-28 03:29:43,848][87424] Updated weights for policy 0, policy_version 125436 (0.0010) -[2023-11-28 03:29:44,542][87426] Updated weights for policy 1, policy_version 125190 (0.0011) -[2023-11-28 03:29:44,927][87426] Updated weights for policy 1, policy_version 125200 (0.0011) -[2023-11-28 03:29:45,300][87426] Updated weights for policy 1, policy_version 125210 (0.0011) -[2023-11-28 03:29:46,347][87424] Updated weights for policy 0, policy_version 125446 (0.0010) -[2023-11-28 03:29:46,721][87424] Updated weights for policy 0, policy_version 125456 (0.0012) -[2023-11-28 03:29:47,102][87424] Updated weights for policy 0, policy_version 125466 (0.0010) -[2023-11-28 03:29:47,141][87426] Updated weights for policy 1, policy_version 125220 (0.0009) -[2023-11-28 03:29:47,524][87426] Updated weights for policy 1, policy_version 125230 (0.0012) -[2023-11-28 03:29:47,895][87426] Updated weights for policy 1, policy_version 125240 (0.0012) -[2023-11-28 03:29:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64184320. Throughput: 0: 2747.8, 1: 2715.8. Samples: 64192388. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:29:48,446][86177] Avg episode reward: [(0, '-496.950'), (1, '-529.460')] -[2023-11-28 03:29:49,252][87424] Updated weights for policy 0, policy_version 125476 (0.0007) -[2023-11-28 03:29:49,640][87424] Updated weights for policy 0, policy_version 125486 (0.0007) -[2023-11-28 03:29:50,032][87424] Updated weights for policy 0, policy_version 125496 (0.0009) -[2023-11-28 03:29:50,328][87426] Updated weights for policy 1, policy_version 125250 (0.0012) -[2023-11-28 03:29:50,705][87426] Updated weights for policy 1, policy_version 125260 (0.0009) -[2023-11-28 03:29:51,087][87426] Updated weights for policy 1, policy_version 125270 (0.0008) -[2023-11-28 03:29:51,466][87426] Updated weights for policy 1, policy_version 125280 (0.0008) -[2023-11-28 03:29:52,452][87424] Updated weights for policy 0, policy_version 125506 (0.0008) -[2023-11-28 03:29:52,835][87424] Updated weights for policy 0, policy_version 125516 (0.0008) -[2023-11-28 03:29:53,219][87424] Updated weights for policy 0, policy_version 125526 (0.0009) -[2023-11-28 03:29:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 64200704. Throughput: 0: 2720.3, 1: 2679.6. Samples: 64223640. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:29:53,445][86177] Avg episode reward: [(0, '-497.980'), (1, '-503.460')] -[2023-11-28 03:29:53,601][87424] Updated weights for policy 0, policy_version 125536 (0.0010) -[2023-11-28 03:29:54,002][87426] Updated weights for policy 1, policy_version 125290 (0.0012) -[2023-11-28 03:29:54,388][87426] Updated weights for policy 1, policy_version 125300 (0.0012) -[2023-11-28 03:29:54,768][87426] Updated weights for policy 1, policy_version 125310 (0.0012) -[2023-11-28 03:29:55,340][87424] Updated weights for policy 0, policy_version 125546 (0.0012) -[2023-11-28 03:29:55,727][87424] Updated weights for policy 0, policy_version 125556 (0.0012) -[2023-11-28 03:29:56,100][87424] Updated weights for policy 0, policy_version 125566 (0.0012) -[2023-11-28 03:29:57,018][87426] Updated weights for policy 1, policy_version 125320 (0.0012) -[2023-11-28 03:29:57,398][87426] Updated weights for policy 1, policy_version 125330 (0.0012) -[2023-11-28 03:29:57,774][87426] Updated weights for policy 1, policy_version 125340 (0.0011) -[2023-11-28 03:29:58,092][87424] Updated weights for policy 0, policy_version 125576 (0.0011) -[2023-11-28 03:29:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64233472. Throughput: 0: 2705.6, 1: 2663.3. Samples: 64246872. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:29:58,445][86177] Avg episode reward: [(0, '-496.040'), (1, '-499.120')] -[2023-11-28 03:29:58,480][87424] Updated weights for policy 0, policy_version 125586 (0.0010) -[2023-11-28 03:29:58,855][87424] Updated weights for policy 0, policy_version 125596 (0.0008) -[2023-11-28 03:30:00,034][87426] Updated weights for policy 1, policy_version 125350 (0.0010) -[2023-11-28 03:30:00,413][87426] Updated weights for policy 1, policy_version 125360 (0.0010) -[2023-11-28 03:30:00,789][87426] Updated weights for policy 1, policy_version 125370 (0.0016) -[2023-11-28 03:30:01,261][87424] Updated weights for policy 0, policy_version 125606 (0.0010) -[2023-11-28 03:30:01,644][87424] Updated weights for policy 0, policy_version 125616 (0.0011) -[2023-11-28 03:30:02,023][87424] Updated weights for policy 0, policy_version 125626 (0.0010) -[2023-11-28 03:30:03,174][87426] Updated weights for policy 1, policy_version 125380 (0.0011) -[2023-11-28 03:30:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 64258048. Throughput: 0: 2743.3, 1: 2659.6. Samples: 64272128. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:30:03,445][86177] Avg episode reward: [(0, '-503.000'), (1, '-489.370')] -[2023-11-28 03:30:03,559][87426] Updated weights for policy 1, policy_version 125390 (0.0010) -[2023-11-28 03:30:03,790][87424] Updated weights for policy 0, policy_version 125636 (0.0012) -[2023-11-28 03:30:03,924][87426] Updated weights for policy 1, policy_version 125400 (0.0010) -[2023-11-28 03:30:04,173][87424] Updated weights for policy 0, policy_version 125646 (0.0012) -[2023-11-28 03:30:04,230][87320] Saving new best policy, reward=-489.370! -[2023-11-28 03:30:04,559][87424] Updated weights for policy 0, policy_version 125656 (0.0012) -[2023-11-28 03:30:06,161][87426] Updated weights for policy 1, policy_version 125410 (0.0011) -[2023-11-28 03:30:06,542][87426] Updated weights for policy 1, policy_version 125420 (0.0012) -[2023-11-28 03:30:06,755][87424] Updated weights for policy 0, policy_version 125666 (0.0012) -[2023-11-28 03:30:06,914][87426] Updated weights for policy 1, policy_version 125430 (0.0011) -[2023-11-28 03:30:07,138][87424] Updated weights for policy 0, policy_version 125676 (0.0012) -[2023-11-28 03:30:07,294][87426] Updated weights for policy 1, policy_version 125440 (0.0011) -[2023-11-28 03:30:07,513][87424] Updated weights for policy 0, policy_version 125686 (0.0011) -[2023-11-28 03:30:07,893][87424] Updated weights for policy 0, policy_version 125696 (0.0008) -[2023-11-28 03:30:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64290816. Throughput: 0: 2735.7, 1: 2645.5. Samples: 64303760. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:30:08,445][86177] Avg episode reward: [(0, '-505.800'), (1, '-489.350')] -[2023-11-28 03:30:08,445][87320] Saving new best policy, reward=-489.350! -[2023-11-28 03:30:09,616][87426] Updated weights for policy 1, policy_version 125450 (0.0009) -[2023-11-28 03:30:09,643][87424] Updated weights for policy 0, policy_version 125706 (0.0010) -[2023-11-28 03:30:09,990][87426] Updated weights for policy 1, policy_version 125460 (0.0009) -[2023-11-28 03:30:10,032][87424] Updated weights for policy 0, policy_version 125716 (0.0009) -[2023-11-28 03:30:10,365][87426] Updated weights for policy 1, policy_version 125470 (0.0010) -[2023-11-28 03:30:10,411][87424] Updated weights for policy 0, policy_version 125726 (0.0011) -[2023-11-28 03:30:12,306][87426] Updated weights for policy 1, policy_version 125480 (0.0011) -[2023-11-28 03:30:12,657][87424] Updated weights for policy 0, policy_version 125736 (0.0012) -[2023-11-28 03:30:12,682][87426] Updated weights for policy 1, policy_version 125490 (0.0010) -[2023-11-28 03:30:13,031][87424] Updated weights for policy 0, policy_version 125746 (0.0011) -[2023-11-28 03:30:13,064][87426] Updated weights for policy 1, policy_version 125500 (0.0011) -[2023-11-28 03:30:13,415][87424] Updated weights for policy 0, policy_version 125756 (0.0012) -[2023-11-28 03:30:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 64315392. Throughput: 0: 2763.3, 1: 2654.6. Samples: 64329204. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:30:13,445][86177] Avg episode reward: [(0, '-510.490'), (1, '-496.460')] -[2023-11-28 03:30:14,897][87426] Updated weights for policy 1, policy_version 125510 (0.0012) -[2023-11-28 03:30:15,286][87426] Updated weights for policy 1, policy_version 125520 (0.0011) -[2023-11-28 03:30:15,572][87424] Updated weights for policy 0, policy_version 125766 (0.0012) -[2023-11-28 03:30:15,662][87426] Updated weights for policy 1, policy_version 125530 (0.0010) -[2023-11-28 03:30:15,956][87424] Updated weights for policy 0, policy_version 125776 (0.0011) -[2023-11-28 03:30:16,334][87424] Updated weights for policy 0, policy_version 125786 (0.0009) -[2023-11-28 03:30:17,830][87426] Updated weights for policy 1, policy_version 125540 (0.0011) -[2023-11-28 03:30:18,203][87426] Updated weights for policy 1, policy_version 125550 (0.0011) -[2023-11-28 03:30:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 64339968. Throughput: 0: 2767.8, 1: 2657.8. Samples: 64354332. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:30:18,446][86177] Avg episode reward: [(0, '-510.370'), (1, '-499.570')] -[2023-11-28 03:30:18,523][87424] Updated weights for policy 0, policy_version 125796 (0.0010) -[2023-11-28 03:30:18,587][87426] Updated weights for policy 1, policy_version 125560 (0.0012) -[2023-11-28 03:30:18,893][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000125568_32145408.pth... -[2023-11-28 03:30:18,922][87424] Updated weights for policy 0, policy_version 125806 (0.0008) -[2023-11-28 03:30:18,930][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000123008_31490048.pth -[2023-11-28 03:30:19,306][87424] Updated weights for policy 0, policy_version 125816 (0.0012) -[2023-11-28 03:30:19,608][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000125824_32210944.pth... -[2023-11-28 03:30:19,639][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000123232_31547392.pth -[2023-11-28 03:30:20,678][87426] Updated weights for policy 1, policy_version 125570 (0.0011) -[2023-11-28 03:30:21,061][87426] Updated weights for policy 1, policy_version 125580 (0.0011) -[2023-11-28 03:30:21,433][87426] Updated weights for policy 1, policy_version 125590 (0.0010) -[2023-11-28 03:30:21,630][87424] Updated weights for policy 0, policy_version 125826 (0.0009) -[2023-11-28 03:30:21,813][87426] Updated weights for policy 1, policy_version 125600 (0.0011) -[2023-11-28 03:30:22,022][87424] Updated weights for policy 0, policy_version 125836 (0.0010) -[2023-11-28 03:30:22,399][87424] Updated weights for policy 0, policy_version 125846 (0.0012) -[2023-11-28 03:30:22,777][87424] Updated weights for policy 0, policy_version 125856 (0.0012) -[2023-11-28 03:30:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64372736. Throughput: 0: 2753.8, 1: 2653.2. Samples: 64387548. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:30:23,445][86177] Avg episode reward: [(0, '-503.990'), (1, '-503.690')] -[2023-11-28 03:30:24,289][87426] Updated weights for policy 1, policy_version 125610 (0.0010) -[2023-11-28 03:30:24,663][87426] Updated weights for policy 1, policy_version 125620 (0.0007) -[2023-11-28 03:30:24,749][87424] Updated weights for policy 0, policy_version 125866 (0.0010) -[2023-11-28 03:30:25,043][87426] Updated weights for policy 1, policy_version 125630 (0.0010) -[2023-11-28 03:30:25,135][87424] Updated weights for policy 0, policy_version 125876 (0.0011) -[2023-11-28 03:30:25,524][87424] Updated weights for policy 0, policy_version 125886 (0.0007) -[2023-11-28 03:30:26,791][87426] Updated weights for policy 1, policy_version 125640 (0.0011) -[2023-11-28 03:30:27,166][87426] Updated weights for policy 1, policy_version 125650 (0.0008) -[2023-11-28 03:30:27,334][87424] Updated weights for policy 0, policy_version 125896 (0.0007) -[2023-11-28 03:30:27,536][87426] Updated weights for policy 1, policy_version 125660 (0.0008) -[2023-11-28 03:30:27,712][87424] Updated weights for policy 0, policy_version 125906 (0.0009) -[2023-11-28 03:30:28,098][87424] Updated weights for policy 0, policy_version 125916 (0.0007) -[2023-11-28 03:30:28,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 64405504. Throughput: 0: 2754.8, 1: 2679.2. Samples: 64412520. Policy #0 lag: (min: 20.0, avg: 30.8, max: 52.0) -[2023-11-28 03:30:28,445][86177] Avg episode reward: [(0, '-504.130'), (1, '-510.400')] -[2023-11-28 03:30:29,850][87426] Updated weights for policy 1, policy_version 125670 (0.0012) -[2023-11-28 03:30:30,222][87426] Updated weights for policy 1, policy_version 125680 (0.0011) -[2023-11-28 03:30:30,277][87424] Updated weights for policy 0, policy_version 125926 (0.0009) -[2023-11-28 03:30:30,599][87426] Updated weights for policy 1, policy_version 125690 (0.0012) -[2023-11-28 03:30:30,658][87424] Updated weights for policy 0, policy_version 125936 (0.0011) -[2023-11-28 03:30:31,036][87424] Updated weights for policy 0, policy_version 125946 (0.0011) -[2023-11-28 03:30:32,955][87426] Updated weights for policy 1, policy_version 125700 (0.0010) -[2023-11-28 03:30:33,337][87426] Updated weights for policy 1, policy_version 125710 (0.0008) -[2023-11-28 03:30:33,352][87424] Updated weights for policy 0, policy_version 125956 (0.0011) -[2023-11-28 03:30:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 64421888. Throughput: 0: 2768.3, 1: 2663.5. Samples: 64436816. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:30:33,445][86177] Avg episode reward: [(0, '-505.950'), (1, '-503.300')] -[2023-11-28 03:30:33,722][87426] Updated weights for policy 1, policy_version 125720 (0.0011) -[2023-11-28 03:30:33,724][87424] Updated weights for policy 0, policy_version 125966 (0.0011) -[2023-11-28 03:30:34,113][87424] Updated weights for policy 0, policy_version 125976 (0.0011) -[2023-11-28 03:30:35,812][87426] Updated weights for policy 1, policy_version 125730 (0.0010) -[2023-11-28 03:30:36,193][87426] Updated weights for policy 1, policy_version 125740 (0.0007) -[2023-11-28 03:30:36,572][87426] Updated weights for policy 1, policy_version 125750 (0.0008) -[2023-11-28 03:30:36,679][87424] Updated weights for policy 0, policy_version 125986 (0.0012) -[2023-11-28 03:30:36,942][87426] Updated weights for policy 1, policy_version 125760 (0.0010) -[2023-11-28 03:30:37,057][87424] Updated weights for policy 0, policy_version 125996 (0.0011) -[2023-11-28 03:30:37,436][87424] Updated weights for policy 0, policy_version 126006 (0.0007) -[2023-11-28 03:30:37,820][87424] Updated weights for policy 0, policy_version 126016 (0.0007) -[2023-11-28 03:30:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64454656. Throughput: 0: 2758.1, 1: 2705.7. Samples: 64469512. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:30:38,446][86177] Avg episode reward: [(0, '-505.820'), (1, '-509.410')] -[2023-11-28 03:30:39,205][87426] Updated weights for policy 1, policy_version 125770 (0.0009) -[2023-11-28 03:30:39,587][87426] Updated weights for policy 1, policy_version 125780 (0.0008) -[2023-11-28 03:30:39,846][87424] Updated weights for policy 0, policy_version 126026 (0.0009) -[2023-11-28 03:30:39,982][87426] Updated weights for policy 1, policy_version 125790 (0.0010) -[2023-11-28 03:30:40,218][87424] Updated weights for policy 0, policy_version 126036 (0.0010) -[2023-11-28 03:30:40,601][87424] Updated weights for policy 0, policy_version 126046 (0.0010) -[2023-11-28 03:30:42,443][87424] Updated weights for policy 0, policy_version 126056 (0.0011) -[2023-11-28 03:30:42,574][87426] Updated weights for policy 1, policy_version 125800 (0.0010) -[2023-11-28 03:30:42,820][87424] Updated weights for policy 0, policy_version 126066 (0.0012) -[2023-11-28 03:30:42,942][87426] Updated weights for policy 1, policy_version 125810 (0.0011) -[2023-11-28 03:30:43,203][87424] Updated weights for policy 0, policy_version 126076 (0.0012) -[2023-11-28 03:30:43,322][87426] Updated weights for policy 1, policy_version 125820 (0.0010) -[2023-11-28 03:30:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 64479232. Throughput: 0: 2765.3, 1: 2722.1. Samples: 64493808. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:30:43,445][86177] Avg episode reward: [(0, '-503.610'), (1, '-506.290')] -[2023-11-28 03:30:45,117][87426] Updated weights for policy 1, policy_version 125830 (0.0011) -[2023-11-28 03:30:45,495][87426] Updated weights for policy 1, policy_version 125840 (0.0012) -[2023-11-28 03:30:45,777][87424] Updated weights for policy 0, policy_version 126086 (0.0011) -[2023-11-28 03:30:45,871][87426] Updated weights for policy 1, policy_version 125850 (0.0011) -[2023-11-28 03:30:46,163][87424] Updated weights for policy 0, policy_version 126096 (0.0011) -[2023-11-28 03:30:46,544][87424] Updated weights for policy 0, policy_version 126106 (0.0012) -[2023-11-28 03:30:48,377][87426] Updated weights for policy 1, policy_version 125860 (0.0012) -[2023-11-28 03:30:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 64503808. Throughput: 0: 2750.0, 1: 2736.4. Samples: 64519016. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:30:48,445][86177] Avg episode reward: [(0, '-505.430'), (1, '-509.840')] -[2023-11-28 03:30:48,621][87424] Updated weights for policy 0, policy_version 126116 (0.0011) -[2023-11-28 03:30:48,745][87426] Updated weights for policy 1, policy_version 125870 (0.0010) -[2023-11-28 03:30:49,003][87424] Updated weights for policy 0, policy_version 126126 (0.0011) -[2023-11-28 03:30:49,123][87426] Updated weights for policy 1, policy_version 125880 (0.0010) -[2023-11-28 03:30:49,393][87424] Updated weights for policy 0, policy_version 126136 (0.0011) -[2023-11-28 03:30:51,262][87426] Updated weights for policy 1, policy_version 125890 (0.0010) -[2023-11-28 03:30:51,304][87424] Updated weights for policy 0, policy_version 126146 (0.0012) -[2023-11-28 03:30:51,639][87426] Updated weights for policy 1, policy_version 125900 (0.0011) -[2023-11-28 03:30:51,686][87424] Updated weights for policy 0, policy_version 126156 (0.0011) -[2023-11-28 03:30:52,019][87426] Updated weights for policy 1, policy_version 125910 (0.0008) -[2023-11-28 03:30:52,076][87424] Updated weights for policy 0, policy_version 126166 (0.0010) -[2023-11-28 03:30:52,399][87426] Updated weights for policy 1, policy_version 125920 (0.0010) -[2023-11-28 03:30:52,448][87424] Updated weights for policy 0, policy_version 126176 (0.0010) -[2023-11-28 03:30:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 64536576. Throughput: 0: 2763.5, 1: 2759.6. Samples: 64552300. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:30:53,445][86177] Avg episode reward: [(0, '-504.320'), (1, '-504.890')] -[2023-11-28 03:30:54,392][87426] Updated weights for policy 1, policy_version 125930 (0.0009) -[2023-11-28 03:30:54,772][87426] Updated weights for policy 1, policy_version 125940 (0.0010) -[2023-11-28 03:30:54,928][87424] Updated weights for policy 0, policy_version 126186 (0.0011) -[2023-11-28 03:30:55,154][87426] Updated weights for policy 1, policy_version 125950 (0.0011) -[2023-11-28 03:30:55,310][87424] Updated weights for policy 0, policy_version 126196 (0.0011) -[2023-11-28 03:30:55,680][87424] Updated weights for policy 0, policy_version 126206 (0.0008) -[2023-11-28 03:30:57,431][87426] Updated weights for policy 1, policy_version 125960 (0.0012) -[2023-11-28 03:30:57,806][87426] Updated weights for policy 1, policy_version 125970 (0.0011) -[2023-11-28 03:30:58,002][87424] Updated weights for policy 0, policy_version 126216 (0.0008) -[2023-11-28 03:30:58,181][87426] Updated weights for policy 1, policy_version 125980 (0.0008) -[2023-11-28 03:30:58,380][87424] Updated weights for policy 0, policy_version 126226 (0.0010) -[2023-11-28 03:30:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 64561152. Throughput: 0: 2744.7, 1: 2772.4. Samples: 64577476. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:30:58,445][86177] Avg episode reward: [(0, '-504.070'), (1, '-497.760')] -[2023-11-28 03:30:58,768][87424] Updated weights for policy 0, policy_version 126236 (0.0008) -[2023-11-28 03:31:00,087][87426] Updated weights for policy 1, policy_version 125990 (0.0010) -[2023-11-28 03:31:00,460][87426] Updated weights for policy 1, policy_version 126000 (0.0010) -[2023-11-28 03:31:00,518][87424] Updated weights for policy 0, policy_version 126246 (0.0011) -[2023-11-28 03:31:00,845][87426] Updated weights for policy 1, policy_version 126010 (0.0010) -[2023-11-28 03:31:00,891][87424] Updated weights for policy 0, policy_version 126256 (0.0009) -[2023-11-28 03:31:01,280][87424] Updated weights for policy 0, policy_version 126266 (0.0012) -[2023-11-28 03:31:02,890][87426] Updated weights for policy 1, policy_version 126020 (0.0010) -[2023-11-28 03:31:03,265][87426] Updated weights for policy 1, policy_version 126030 (0.0008) -[2023-11-28 03:31:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 64585728. Throughput: 0: 2749.4, 1: 2760.4. Samples: 64602272. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:31:03,445][86177] Avg episode reward: [(0, '-509.780'), (1, '-501.510')] -[2023-11-28 03:31:03,643][87426] Updated weights for policy 1, policy_version 126040 (0.0008) -[2023-11-28 03:31:03,779][87424] Updated weights for policy 0, policy_version 126276 (0.0010) -[2023-11-28 03:31:04,152][87424] Updated weights for policy 0, policy_version 126286 (0.0007) -[2023-11-28 03:31:04,532][87424] Updated weights for policy 0, policy_version 126296 (0.0009) -[2023-11-28 03:31:05,888][87426] Updated weights for policy 1, policy_version 126050 (0.0008) -[2023-11-28 03:31:06,272][87426] Updated weights for policy 1, policy_version 126060 (0.0011) -[2023-11-28 03:31:06,674][87426] Updated weights for policy 1, policy_version 126070 (0.0010) -[2023-11-28 03:31:06,996][87424] Updated weights for policy 0, policy_version 126306 (0.0011) -[2023-11-28 03:31:07,055][87426] Updated weights for policy 1, policy_version 126080 (0.0011) -[2023-11-28 03:31:07,384][87424] Updated weights for policy 0, policy_version 126316 (0.0012) -[2023-11-28 03:31:07,764][87424] Updated weights for policy 0, policy_version 126326 (0.0012) -[2023-11-28 03:31:08,145][87424] Updated weights for policy 0, policy_version 126336 (0.0011) -[2023-11-28 03:31:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64618496. Throughput: 0: 2727.9, 1: 2744.2. Samples: 64633792. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:31:08,445][86177] Avg episode reward: [(0, '-515.630'), (1, '-492.110')] -[2023-11-28 03:31:09,554][87426] Updated weights for policy 1, policy_version 126090 (0.0011) -[2023-11-28 03:31:09,830][87424] Updated weights for policy 0, policy_version 126346 (0.0008) -[2023-11-28 03:31:09,938][87426] Updated weights for policy 1, policy_version 126100 (0.0010) -[2023-11-28 03:31:10,210][87424] Updated weights for policy 0, policy_version 126356 (0.0011) -[2023-11-28 03:31:10,315][87426] Updated weights for policy 1, policy_version 126110 (0.0011) -[2023-11-28 03:31:10,592][87424] Updated weights for policy 0, policy_version 126366 (0.0012) -[2023-11-28 03:31:12,220][87426] Updated weights for policy 1, policy_version 126120 (0.0011) -[2023-11-28 03:31:12,604][87426] Updated weights for policy 1, policy_version 126130 (0.0008) -[2023-11-28 03:31:12,980][87426] Updated weights for policy 1, policy_version 126140 (0.0009) -[2023-11-28 03:31:13,175][87424] Updated weights for policy 0, policy_version 126376 (0.0012) -[2023-11-28 03:31:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 64643072. Throughput: 0: 2709.9, 1: 2719.3. Samples: 64656832. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:31:13,445][86177] Avg episode reward: [(0, '-516.190'), (1, '-494.090')] -[2023-11-28 03:31:13,550][87424] Updated weights for policy 0, policy_version 126386 (0.0012) -[2023-11-28 03:31:13,938][87424] Updated weights for policy 0, policy_version 126396 (0.0012) -[2023-11-28 03:31:15,531][87426] Updated weights for policy 1, policy_version 126150 (0.0011) -[2023-11-28 03:31:15,903][87426] Updated weights for policy 1, policy_version 126160 (0.0011) -[2023-11-28 03:31:16,276][87426] Updated weights for policy 1, policy_version 126170 (0.0012) -[2023-11-28 03:31:16,535][87424] Updated weights for policy 0, policy_version 126406 (0.0012) -[2023-11-28 03:31:16,921][87424] Updated weights for policy 0, policy_version 126416 (0.0012) -[2023-11-28 03:31:17,296][87424] Updated weights for policy 0, policy_version 126426 (0.0012) -[2023-11-28 03:31:18,082][87426] Updated weights for policy 1, policy_version 126180 (0.0011) -[2023-11-28 03:31:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 64667648. Throughput: 0: 2707.6, 1: 2729.1. Samples: 64681468. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:31:18,445][86177] Avg episode reward: [(0, '-515.850'), (1, '-498.490')] -[2023-11-28 03:31:18,464][87426] Updated weights for policy 1, policy_version 126190 (0.0011) -[2023-11-28 03:31:18,844][87426] Updated weights for policy 1, policy_version 126200 (0.0008) -[2023-11-28 03:31:19,161][87424] Updated weights for policy 0, policy_version 126436 (0.0012) -[2023-11-28 03:31:19,537][87424] Updated weights for policy 0, policy_version 126446 (0.0008) -[2023-11-28 03:31:19,918][87424] Updated weights for policy 0, policy_version 126456 (0.0009) -[2023-11-28 03:31:21,210][87426] Updated weights for policy 1, policy_version 126210 (0.0011) -[2023-11-28 03:31:21,589][87426] Updated weights for policy 1, policy_version 126220 (0.0011) -[2023-11-28 03:31:21,966][87426] Updated weights for policy 1, policy_version 126230 (0.0011) -[2023-11-28 03:31:22,107][87424] Updated weights for policy 0, policy_version 126466 (0.0010) -[2023-11-28 03:31:22,341][87426] Updated weights for policy 1, policy_version 126240 (0.0010) -[2023-11-28 03:31:22,486][87424] Updated weights for policy 0, policy_version 126476 (0.0011) -[2023-11-28 03:31:22,878][87424] Updated weights for policy 0, policy_version 126486 (0.0009) -[2023-11-28 03:31:23,260][87424] Updated weights for policy 0, policy_version 126496 (0.0008) -[2023-11-28 03:31:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 64700416. Throughput: 0: 2713.7, 1: 2729.9. Samples: 64714472. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:31:23,445][86177] Avg episode reward: [(0, '-515.040'), (1, '-493.830')] -[2023-11-28 03:31:24,355][87426] Updated weights for policy 1, policy_version 126250 (0.0007) -[2023-11-28 03:31:24,734][87426] Updated weights for policy 1, policy_version 126260 (0.0007) -[2023-11-28 03:31:25,114][87426] Updated weights for policy 1, policy_version 126270 (0.0010) -[2023-11-28 03:31:25,208][87424] Updated weights for policy 0, policy_version 126506 (0.0010) -[2023-11-28 03:31:25,586][87424] Updated weights for policy 0, policy_version 126516 (0.0010) -[2023-11-28 03:31:25,975][87424] Updated weights for policy 0, policy_version 126526 (0.0007) -[2023-11-28 03:31:26,867][87426] Updated weights for policy 1, policy_version 126280 (0.0010) -[2023-11-28 03:31:27,240][87426] Updated weights for policy 1, policy_version 126290 (0.0009) -[2023-11-28 03:31:27,621][87426] Updated weights for policy 1, policy_version 126300 (0.0007) -[2023-11-28 03:31:28,394][87424] Updated weights for policy 0, policy_version 126536 (0.0009) -[2023-11-28 03:31:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 64724992. Throughput: 0: 2704.0, 1: 2740.3. Samples: 64738800. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:31:28,445][86177] Avg episode reward: [(0, '-518.730'), (1, '-493.960')] -[2023-11-28 03:31:28,776][87424] Updated weights for policy 0, policy_version 126546 (0.0009) -[2023-11-28 03:31:29,156][87424] Updated weights for policy 0, policy_version 126556 (0.0010) -[2023-11-28 03:31:30,003][87426] Updated weights for policy 1, policy_version 126310 (0.0008) -[2023-11-28 03:31:30,383][87426] Updated weights for policy 1, policy_version 126320 (0.0007) -[2023-11-28 03:31:30,750][87426] Updated weights for policy 1, policy_version 126330 (0.0009) -[2023-11-28 03:31:31,403][87424] Updated weights for policy 0, policy_version 126566 (0.0011) -[2023-11-28 03:31:31,778][87424] Updated weights for policy 0, policy_version 126576 (0.0016) -[2023-11-28 03:31:32,157][87424] Updated weights for policy 0, policy_version 126586 (0.0010) -[2023-11-28 03:31:33,265][87426] Updated weights for policy 1, policy_version 126340 (0.0009) -[2023-11-28 03:31:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 64749568. Throughput: 0: 2674.5, 1: 2717.2. Samples: 64761640. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 03:31:33,445][86177] Avg episode reward: [(0, '-518.160'), (1, '-492.350')] -[2023-11-28 03:31:33,639][87426] Updated weights for policy 1, policy_version 126350 (0.0012) -[2023-11-28 03:31:34,028][87426] Updated weights for policy 1, policy_version 126360 (0.0010) -[2023-11-28 03:31:34,656][87424] Updated weights for policy 0, policy_version 126596 (0.0010) -[2023-11-28 03:31:35,040][87424] Updated weights for policy 0, policy_version 126606 (0.0008) -[2023-11-28 03:31:35,421][87424] Updated weights for policy 0, policy_version 126616 (0.0010) -[2023-11-28 03:31:36,193][87426] Updated weights for policy 1, policy_version 126370 (0.0010) -[2023-11-28 03:31:36,576][87426] Updated weights for policy 1, policy_version 126380 (0.0007) -[2023-11-28 03:31:36,949][87426] Updated weights for policy 1, policy_version 126390 (0.0011) -[2023-11-28 03:31:37,330][87426] Updated weights for policy 1, policy_version 126400 (0.0008) -[2023-11-28 03:31:37,917][87424] Updated weights for policy 0, policy_version 126626 (0.0010) -[2023-11-28 03:31:38,309][87424] Updated weights for policy 0, policy_version 126636 (0.0009) -[2023-11-28 03:31:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 64774144. Throughput: 0: 2641.5, 1: 2687.2. Samples: 64792092. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:31:38,445][86177] Avg episode reward: [(0, '-525.060'), (1, '-491.340')] -[2023-11-28 03:31:38,685][87424] Updated weights for policy 0, policy_version 126646 (0.0008) -[2023-11-28 03:31:39,063][87424] Updated weights for policy 0, policy_version 126656 (0.0009) -[2023-11-28 03:31:39,232][87426] Updated weights for policy 1, policy_version 126410 (0.0010) -[2023-11-28 03:31:39,613][87426] Updated weights for policy 1, policy_version 126420 (0.0012) -[2023-11-28 03:31:39,977][87426] Updated weights for policy 1, policy_version 126430 (0.0011) -[2023-11-28 03:31:41,446][87424] Updated weights for policy 0, policy_version 126666 (0.0009) -[2023-11-28 03:31:41,830][87424] Updated weights for policy 0, policy_version 126676 (0.0009) -[2023-11-28 03:31:41,958][87426] Updated weights for policy 1, policy_version 126440 (0.0011) -[2023-11-28 03:31:42,211][87424] Updated weights for policy 0, policy_version 126686 (0.0012) -[2023-11-28 03:31:42,325][87426] Updated weights for policy 1, policy_version 126450 (0.0010) -[2023-11-28 03:31:42,703][87426] Updated weights for policy 1, policy_version 126460 (0.0010) -[2023-11-28 03:31:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 64806912. Throughput: 0: 2632.5, 1: 2683.6. Samples: 64816700. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:31:43,445][86177] Avg episode reward: [(0, '-555.970'), (1, '-493.950')] -[2023-11-28 03:31:44,220][87424] Updated weights for policy 0, policy_version 126696 (0.0011) -[2023-11-28 03:31:44,607][87424] Updated weights for policy 0, policy_version 126706 (0.0011) -[2023-11-28 03:31:45,002][87424] Updated weights for policy 0, policy_version 126716 (0.0012) -[2023-11-28 03:31:45,102][87426] Updated weights for policy 1, policy_version 126470 (0.0011) -[2023-11-28 03:31:45,482][87426] Updated weights for policy 1, policy_version 126480 (0.0012) -[2023-11-28 03:31:45,854][87426] Updated weights for policy 1, policy_version 126490 (0.0012) -[2023-11-28 03:31:47,339][87424] Updated weights for policy 0, policy_version 126726 (0.0011) -[2023-11-28 03:31:47,717][87424] Updated weights for policy 0, policy_version 126736 (0.0012) -[2023-11-28 03:31:48,096][87424] Updated weights for policy 0, policy_version 126746 (0.0009) -[2023-11-28 03:31:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 64831488. Throughput: 0: 2608.8, 1: 2681.8. Samples: 64840348. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:31:48,445][86177] Avg episode reward: [(0, '-554.820'), (1, '-493.570')] -[2023-11-28 03:31:48,489][87426] Updated weights for policy 1, policy_version 126500 (0.0011) -[2023-11-28 03:31:48,861][87426] Updated weights for policy 1, policy_version 126510 (0.0011) -[2023-11-28 03:31:49,245][87426] Updated weights for policy 1, policy_version 126520 (0.0012) -[2023-11-28 03:31:50,571][87424] Updated weights for policy 0, policy_version 126756 (0.0010) -[2023-11-28 03:31:50,963][87424] Updated weights for policy 0, policy_version 126766 (0.0012) -[2023-11-28 03:31:51,348][87424] Updated weights for policy 0, policy_version 126776 (0.0011) -[2023-11-28 03:31:51,410][87426] Updated weights for policy 1, policy_version 126530 (0.0012) -[2023-11-28 03:31:51,790][87426] Updated weights for policy 1, policy_version 126540 (0.0011) -[2023-11-28 03:31:52,174][87426] Updated weights for policy 1, policy_version 126550 (0.0010) -[2023-11-28 03:31:52,554][87426] Updated weights for policy 1, policy_version 126560 (0.0008) -[2023-11-28 03:31:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 64856064. Throughput: 0: 2599.0, 1: 2686.5. Samples: 64871640. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:31:53,445][86177] Avg episode reward: [(0, '-547.490'), (1, '-495.930')] -[2023-11-28 03:31:53,748][87424] Updated weights for policy 0, policy_version 126786 (0.0008) -[2023-11-28 03:31:54,145][87424] Updated weights for policy 0, policy_version 126796 (0.0007) -[2023-11-28 03:31:54,518][87424] Updated weights for policy 0, policy_version 126806 (0.0007) -[2023-11-28 03:31:54,897][87424] Updated weights for policy 0, policy_version 126816 (0.0007) -[2023-11-28 03:31:55,129][87426] Updated weights for policy 1, policy_version 126570 (0.0012) -[2023-11-28 03:31:55,504][87426] Updated weights for policy 1, policy_version 126580 (0.0007) -[2023-11-28 03:31:55,889][87426] Updated weights for policy 1, policy_version 126590 (0.0008) -[2023-11-28 03:31:56,841][87424] Updated weights for policy 0, policy_version 126826 (0.0008) -[2023-11-28 03:31:57,228][87424] Updated weights for policy 0, policy_version 126836 (0.0007) -[2023-11-28 03:31:57,610][87424] Updated weights for policy 0, policy_version 126846 (0.0007) -[2023-11-28 03:31:58,320][87426] Updated weights for policy 1, policy_version 126600 (0.0011) -[2023-11-28 03:31:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 64880640. Throughput: 0: 2602.0, 1: 2677.5. Samples: 64894412. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:31:58,445][86177] Avg episode reward: [(0, '-541.020'), (1, '-499.950')] -[2023-11-28 03:31:58,694][87426] Updated weights for policy 1, policy_version 126610 (0.0012) -[2023-11-28 03:31:59,076][87426] Updated weights for policy 1, policy_version 126620 (0.0008) -[2023-11-28 03:31:59,702][87424] Updated weights for policy 0, policy_version 126856 (0.0007) -[2023-11-28 03:32:00,084][87424] Updated weights for policy 0, policy_version 126866 (0.0009) -[2023-11-28 03:32:00,465][87424] Updated weights for policy 0, policy_version 126876 (0.0008) -[2023-11-28 03:32:01,592][87426] Updated weights for policy 1, policy_version 126630 (0.0010) -[2023-11-28 03:32:01,969][87426] Updated weights for policy 1, policy_version 126640 (0.0012) -[2023-11-28 03:32:02,344][87426] Updated weights for policy 1, policy_version 126650 (0.0011) -[2023-11-28 03:32:02,497][87424] Updated weights for policy 0, policy_version 126886 (0.0010) -[2023-11-28 03:32:02,871][87424] Updated weights for policy 0, policy_version 126896 (0.0012) -[2023-11-28 03:32:03,263][87424] Updated weights for policy 0, policy_version 126906 (0.0012) -[2023-11-28 03:32:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 64905216. Throughput: 0: 2623.8, 1: 2672.5. Samples: 64919804. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:32:03,446][86177] Avg episode reward: [(0, '-500.410'), (1, '-501.940')] -[2023-11-28 03:32:04,563][87426] Updated weights for policy 1, policy_version 126660 (0.0012) -[2023-11-28 03:32:04,932][87426] Updated weights for policy 1, policy_version 126670 (0.0011) -[2023-11-28 03:32:05,306][87426] Updated weights for policy 1, policy_version 126680 (0.0010) -[2023-11-28 03:32:05,340][87424] Updated weights for policy 0, policy_version 126916 (0.0012) -[2023-11-28 03:32:05,718][87424] Updated weights for policy 0, policy_version 126926 (0.0010) -[2023-11-28 03:32:06,105][87424] Updated weights for policy 0, policy_version 126936 (0.0007) -[2023-11-28 03:32:07,552][87426] Updated weights for policy 1, policy_version 126690 (0.0009) -[2023-11-28 03:32:07,918][87426] Updated weights for policy 1, policy_version 126700 (0.0011) -[2023-11-28 03:32:08,310][87426] Updated weights for policy 1, policy_version 126710 (0.0012) -[2023-11-28 03:32:08,321][87424] Updated weights for policy 0, policy_version 126946 (0.0010) -[2023-11-28 03:32:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 64929792. Throughput: 0: 2623.7, 1: 2651.8. Samples: 64951872. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:32:08,445][86177] Avg episode reward: [(0, '-495.340'), (1, '-507.440')] -[2023-11-28 03:32:08,685][87426] Updated weights for policy 1, policy_version 126720 (0.0012) -[2023-11-28 03:32:08,705][87424] Updated weights for policy 0, policy_version 126956 (0.0007) -[2023-11-28 03:32:09,092][87424] Updated weights for policy 0, policy_version 126966 (0.0009) -[2023-11-28 03:32:09,468][87424] Updated weights for policy 0, policy_version 126976 (0.0007) -[2023-11-28 03:32:11,102][87426] Updated weights for policy 1, policy_version 126730 (0.0012) -[2023-11-28 03:32:11,482][87426] Updated weights for policy 1, policy_version 126740 (0.0012) -[2023-11-28 03:32:11,576][87424] Updated weights for policy 0, policy_version 126986 (0.0012) -[2023-11-28 03:32:11,855][87426] Updated weights for policy 1, policy_version 126750 (0.0012) -[2023-11-28 03:32:11,960][87424] Updated weights for policy 0, policy_version 126996 (0.0011) -[2023-11-28 03:32:12,349][87424] Updated weights for policy 0, policy_version 127006 (0.0010) -[2023-11-28 03:32:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 64962560. Throughput: 0: 2628.7, 1: 2626.8. Samples: 64975296. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:32:13,445][86177] Avg episode reward: [(0, '-504.590'), (1, '-509.950')] -[2023-11-28 03:32:14,382][87426] Updated weights for policy 1, policy_version 126760 (0.0012) -[2023-11-28 03:32:14,604][87424] Updated weights for policy 0, policy_version 127016 (0.0011) -[2023-11-28 03:32:14,765][87426] Updated weights for policy 1, policy_version 126770 (0.0011) -[2023-11-28 03:32:14,986][87424] Updated weights for policy 0, policy_version 127026 (0.0012) -[2023-11-28 03:32:15,138][87426] Updated weights for policy 1, policy_version 126780 (0.0010) -[2023-11-28 03:32:15,373][87424] Updated weights for policy 0, policy_version 127036 (0.0008) -[2023-11-28 03:32:17,037][87424] Updated weights for policy 0, policy_version 127046 (0.0009) -[2023-11-28 03:32:17,065][87426] Updated weights for policy 1, policy_version 126790 (0.0008) -[2023-11-28 03:32:17,424][87424] Updated weights for policy 0, policy_version 127056 (0.0007) -[2023-11-28 03:32:17,455][87426] Updated weights for policy 1, policy_version 126800 (0.0008) -[2023-11-28 03:32:17,822][87424] Updated weights for policy 0, policy_version 127066 (0.0008) -[2023-11-28 03:32:17,831][87426] Updated weights for policy 1, policy_version 126810 (0.0008) -[2023-11-28 03:32:18,445][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 64995328. Throughput: 0: 2671.8, 1: 2638.9. Samples: 65000624. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:32:18,446][86177] Avg episode reward: [(0, '-508.630'), (1, '-507.310')] -[2023-11-28 03:32:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000127072_32530432.pth... -[2023-11-28 03:32:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000126816_32464896.pth... -[2023-11-28 03:32:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000124288_31817728.pth -[2023-11-28 03:32:18,497][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000126816_32464896.pth -[2023-11-28 03:32:18,506][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000124512_31875072.pth -[2023-11-28 03:32:18,513][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000127072_32530432.pth -[2023-11-28 03:32:19,936][87424] Updated weights for policy 0, policy_version 127076 (0.0012) -[2023-11-28 03:32:20,266][87426] Updated weights for policy 1, policy_version 126820 (0.0011) -[2023-11-28 03:32:20,314][87424] Updated weights for policy 0, policy_version 127086 (0.0012) -[2023-11-28 03:32:20,650][87426] Updated weights for policy 1, policy_version 126830 (0.0011) -[2023-11-28 03:32:20,692][87424] Updated weights for policy 0, policy_version 127096 (0.0011) -[2023-11-28 03:32:21,025][87426] Updated weights for policy 1, policy_version 126840 (0.0011) -[2023-11-28 03:32:22,983][87424] Updated weights for policy 0, policy_version 127106 (0.0011) -[2023-11-28 03:32:23,264][87426] Updated weights for policy 1, policy_version 126850 (0.0011) -[2023-11-28 03:32:23,369][87424] Updated weights for policy 0, policy_version 127116 (0.0012) -[2023-11-28 03:32:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 65011712. Throughput: 0: 2710.5, 1: 2644.0. Samples: 65033044. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:32:23,445][86177] Avg episode reward: [(0, '-509.110'), (1, '-510.650')] -[2023-11-28 03:32:23,641][87426] Updated weights for policy 1, policy_version 126860 (0.0009) -[2023-11-28 03:32:23,748][87424] Updated weights for policy 0, policy_version 127126 (0.0012) -[2023-11-28 03:32:24,023][87426] Updated weights for policy 1, policy_version 126870 (0.0010) -[2023-11-28 03:32:24,133][87424] Updated weights for policy 0, policy_version 127136 (0.0008) -[2023-11-28 03:32:24,401][87426] Updated weights for policy 1, policy_version 126880 (0.0008) -[2023-11-28 03:32:26,280][87424] Updated weights for policy 0, policy_version 127146 (0.0012) -[2023-11-28 03:32:26,320][87426] Updated weights for policy 1, policy_version 126890 (0.0012) -[2023-11-28 03:32:26,653][87424] Updated weights for policy 0, policy_version 127156 (0.0010) -[2023-11-28 03:32:26,700][87426] Updated weights for policy 1, policy_version 126900 (0.0011) -[2023-11-28 03:32:27,036][87424] Updated weights for policy 0, policy_version 127166 (0.0007) -[2023-11-28 03:32:27,093][87426] Updated weights for policy 1, policy_version 126910 (0.0012) -[2023-11-28 03:32:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 65044480. Throughput: 0: 2733.1, 1: 2630.6. Samples: 65058064. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:32:28,445][86177] Avg episode reward: [(0, '-504.980'), (1, '-504.150')] -[2023-11-28 03:32:28,790][87426] Updated weights for policy 1, policy_version 126920 (0.0012) -[2023-11-28 03:32:29,175][87426] Updated weights for policy 1, policy_version 126930 (0.0011) -[2023-11-28 03:32:29,239][87424] Updated weights for policy 0, policy_version 127176 (0.0008) -[2023-11-28 03:32:29,547][87426] Updated weights for policy 1, policy_version 126940 (0.0008) -[2023-11-28 03:32:29,622][87424] Updated weights for policy 0, policy_version 127186 (0.0008) -[2023-11-28 03:32:30,009][87424] Updated weights for policy 0, policy_version 127196 (0.0009) -[2023-11-28 03:32:31,674][87426] Updated weights for policy 1, policy_version 126950 (0.0008) -[2023-11-28 03:32:32,046][87426] Updated weights for policy 1, policy_version 126960 (0.0011) -[2023-11-28 03:32:32,054][87424] Updated weights for policy 0, policy_version 127206 (0.0009) -[2023-11-28 03:32:32,427][87426] Updated weights for policy 1, policy_version 126970 (0.0011) -[2023-11-28 03:32:32,439][87424] Updated weights for policy 0, policy_version 127216 (0.0011) -[2023-11-28 03:32:32,829][87424] Updated weights for policy 0, policy_version 127226 (0.0012) -[2023-11-28 03:32:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65077248. Throughput: 0: 2749.8, 1: 2637.4. Samples: 65082772. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:32:33,445][86177] Avg episode reward: [(0, '-508.490'), (1, '-505.820')] -[2023-11-28 03:32:34,250][87426] Updated weights for policy 1, policy_version 126980 (0.0012) -[2023-11-28 03:32:34,635][87426] Updated weights for policy 1, policy_version 126990 (0.0011) -[2023-11-28 03:32:35,007][87426] Updated weights for policy 1, policy_version 127000 (0.0012) -[2023-11-28 03:32:35,223][87424] Updated weights for policy 0, policy_version 127236 (0.0008) -[2023-11-28 03:32:35,607][87424] Updated weights for policy 0, policy_version 127246 (0.0008) -[2023-11-28 03:32:36,000][87424] Updated weights for policy 0, policy_version 127256 (0.0008) -[2023-11-28 03:32:37,351][87426] Updated weights for policy 1, policy_version 127010 (0.0012) -[2023-11-28 03:32:37,727][87426] Updated weights for policy 1, policy_version 127020 (0.0012) -[2023-11-28 03:32:38,105][87426] Updated weights for policy 1, policy_version 127030 (0.0011) -[2023-11-28 03:32:38,436][87424] Updated weights for policy 0, policy_version 127266 (0.0008) -[2023-11-28 03:32:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 65093632. Throughput: 0: 2753.6, 1: 2654.1. Samples: 65114988. Policy #0 lag: (min: 30.0, avg: 46.6, max: 62.0) -[2023-11-28 03:32:38,445][86177] Avg episode reward: [(0, '-515.510'), (1, '-505.940')] -[2023-11-28 03:32:38,474][87426] Updated weights for policy 1, policy_version 127040 (0.0012) -[2023-11-28 03:32:38,817][87424] Updated weights for policy 0, policy_version 127276 (0.0012) -[2023-11-28 03:32:39,200][87424] Updated weights for policy 0, policy_version 127286 (0.0016) -[2023-11-28 03:32:39,585][87424] Updated weights for policy 0, policy_version 127296 (0.0011) -[2023-11-28 03:32:40,816][87426] Updated weights for policy 1, policy_version 127050 (0.0012) -[2023-11-28 03:32:41,195][87426] Updated weights for policy 1, policy_version 127060 (0.0011) -[2023-11-28 03:32:41,573][87426] Updated weights for policy 1, policy_version 127070 (0.0012) -[2023-11-28 03:32:41,681][87424] Updated weights for policy 0, policy_version 127306 (0.0012) -[2023-11-28 03:32:42,055][87424] Updated weights for policy 0, policy_version 127316 (0.0012) -[2023-11-28 03:32:42,460][87424] Updated weights for policy 0, policy_version 127326 (0.0012) -[2023-11-28 03:32:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 65126400. Throughput: 0: 2763.3, 1: 2682.6. Samples: 65139476. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:32:43,445][86177] Avg episode reward: [(0, '-520.160'), (1, '-498.750')] -[2023-11-28 03:32:43,953][87426] Updated weights for policy 1, policy_version 127080 (0.0012) -[2023-11-28 03:32:44,328][87426] Updated weights for policy 1, policy_version 127090 (0.0012) -[2023-11-28 03:32:44,427][87424] Updated weights for policy 0, policy_version 127336 (0.0009) -[2023-11-28 03:32:44,705][87426] Updated weights for policy 1, policy_version 127100 (0.0012) -[2023-11-28 03:32:44,809][87424] Updated weights for policy 0, policy_version 127346 (0.0009) -[2023-11-28 03:32:45,194][87424] Updated weights for policy 0, policy_version 127356 (0.0007) -[2023-11-28 03:32:47,040][87426] Updated weights for policy 1, policy_version 127110 (0.0012) -[2023-11-28 03:32:47,054][87424] Updated weights for policy 0, policy_version 127366 (0.0011) -[2023-11-28 03:32:47,413][87426] Updated weights for policy 1, policy_version 127120 (0.0011) -[2023-11-28 03:32:47,439][87424] Updated weights for policy 0, policy_version 127376 (0.0010) -[2023-11-28 03:32:47,805][87426] Updated weights for policy 1, policy_version 127130 (0.0012) -[2023-11-28 03:32:47,828][87424] Updated weights for policy 0, policy_version 127386 (0.0012) -[2023-11-28 03:32:48,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65159168. Throughput: 0: 2767.6, 1: 2691.6. Samples: 65165472. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:32:48,446][86177] Avg episode reward: [(0, '-525.950'), (1, '-501.020')] -[2023-11-28 03:32:49,816][87426] Updated weights for policy 1, policy_version 127140 (0.0012) -[2023-11-28 03:32:49,983][87424] Updated weights for policy 0, policy_version 127396 (0.0011) -[2023-11-28 03:32:50,187][87426] Updated weights for policy 1, policy_version 127150 (0.0009) -[2023-11-28 03:32:50,365][87424] Updated weights for policy 0, policy_version 127406 (0.0011) -[2023-11-28 03:32:50,567][87426] Updated weights for policy 1, policy_version 127160 (0.0011) -[2023-11-28 03:32:50,749][87424] Updated weights for policy 0, policy_version 127416 (0.0011) -[2023-11-28 03:32:52,621][87426] Updated weights for policy 1, policy_version 127170 (0.0012) -[2023-11-28 03:32:53,017][87426] Updated weights for policy 1, policy_version 127180 (0.0011) -[2023-11-28 03:32:53,327][87424] Updated weights for policy 0, policy_version 127426 (0.0012) -[2023-11-28 03:32:53,397][87426] Updated weights for policy 1, policy_version 127190 (0.0010) -[2023-11-28 03:32:53,448][86177] Fps is (10 sec: 4913.4, 60 sec: 5324.5, 300 sec: 5415.0). Total num frames: 65175552. Throughput: 0: 2783.1, 1: 2708.3. Samples: 65199004. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:32:53,449][86177] Avg episode reward: [(0, '-534.470'), (1, '-496.080')] -[2023-11-28 03:32:53,707][87424] Updated weights for policy 0, policy_version 127436 (0.0011) -[2023-11-28 03:32:53,775][87426] Updated weights for policy 1, policy_version 127200 (0.0010) -[2023-11-28 03:32:54,091][87424] Updated weights for policy 0, policy_version 127446 (0.0012) -[2023-11-28 03:32:54,468][87424] Updated weights for policy 0, policy_version 127456 (0.0012) -[2023-11-28 03:32:55,846][87426] Updated weights for policy 1, policy_version 127210 (0.0009) -[2023-11-28 03:32:56,218][87426] Updated weights for policy 1, policy_version 127220 (0.0008) -[2023-11-28 03:32:56,401][87424] Updated weights for policy 0, policy_version 127466 (0.0012) -[2023-11-28 03:32:56,597][87426] Updated weights for policy 1, policy_version 127230 (0.0010) -[2023-11-28 03:32:56,776][87424] Updated weights for policy 0, policy_version 127476 (0.0011) -[2023-11-28 03:32:57,156][87424] Updated weights for policy 0, policy_version 127486 (0.0011) -[2023-11-28 03:32:58,438][87426] Updated weights for policy 1, policy_version 127240 (0.0007) -[2023-11-28 03:32:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65208320. Throughput: 0: 2788.8, 1: 2749.4. Samples: 65224516. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:32:58,446][86177] Avg episode reward: [(0, '-524.980'), (1, '-495.320')] -[2023-11-28 03:32:58,812][87426] Updated weights for policy 1, policy_version 127250 (0.0007) -[2023-11-28 03:32:59,191][87426] Updated weights for policy 1, policy_version 127260 (0.0008) -[2023-11-28 03:32:59,414][87424] Updated weights for policy 0, policy_version 127496 (0.0012) -[2023-11-28 03:32:59,798][87424] Updated weights for policy 0, policy_version 127506 (0.0011) -[2023-11-28 03:33:00,184][87424] Updated weights for policy 0, policy_version 127516 (0.0008) -[2023-11-28 03:33:01,162][87426] Updated weights for policy 1, policy_version 127270 (0.0010) -[2023-11-28 03:33:01,540][87426] Updated weights for policy 1, policy_version 127280 (0.0008) -[2023-11-28 03:33:01,923][87426] Updated weights for policy 1, policy_version 127290 (0.0009) -[2023-11-28 03:33:02,372][87424] Updated weights for policy 0, policy_version 127526 (0.0010) -[2023-11-28 03:33:02,753][87424] Updated weights for policy 0, policy_version 127536 (0.0009) -[2023-11-28 03:33:03,136][87424] Updated weights for policy 0, policy_version 127546 (0.0008) -[2023-11-28 03:33:03,444][86177] Fps is (10 sec: 6556.1, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 65241088. Throughput: 0: 2772.0, 1: 2752.6. Samples: 65249232. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:33:03,445][86177] Avg episode reward: [(0, '-518.680'), (1, '-496.510')] -[2023-11-28 03:33:03,984][87426] Updated weights for policy 1, policy_version 127300 (0.0009) -[2023-11-28 03:33:04,363][87426] Updated weights for policy 1, policy_version 127310 (0.0009) -[2023-11-28 03:33:04,745][87426] Updated weights for policy 1, policy_version 127320 (0.0008) -[2023-11-28 03:33:05,096][87424] Updated weights for policy 0, policy_version 127556 (0.0009) -[2023-11-28 03:33:05,484][87424] Updated weights for policy 0, policy_version 127566 (0.0012) -[2023-11-28 03:33:05,880][87424] Updated weights for policy 0, policy_version 127576 (0.0012) -[2023-11-28 03:33:07,181][87426] Updated weights for policy 1, policy_version 127330 (0.0010) -[2023-11-28 03:33:07,474][87424] Updated weights for policy 0, policy_version 127586 (0.0011) -[2023-11-28 03:33:07,563][87426] Updated weights for policy 1, policy_version 127340 (0.0011) -[2023-11-28 03:33:07,845][87424] Updated weights for policy 0, policy_version 127596 (0.0011) -[2023-11-28 03:33:07,938][87426] Updated weights for policy 1, policy_version 127350 (0.0011) -[2023-11-28 03:33:08,231][87424] Updated weights for policy 0, policy_version 127606 (0.0011) -[2023-11-28 03:33:08,316][87426] Updated weights for policy 1, policy_version 127360 (0.0012) -[2023-11-28 03:33:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 65265664. Throughput: 0: 2766.4, 1: 2760.3. Samples: 65281744. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:33:08,445][86177] Avg episode reward: [(0, '-507.310'), (1, '-495.390')] -[2023-11-28 03:33:08,616][87424] Updated weights for policy 0, policy_version 127616 (0.0011) -[2023-11-28 03:33:10,828][87424] Updated weights for policy 0, policy_version 127626 (0.0012) -[2023-11-28 03:33:10,853][87426] Updated weights for policy 1, policy_version 127370 (0.0011) -[2023-11-28 03:33:11,210][87424] Updated weights for policy 0, policy_version 127636 (0.0012) -[2023-11-28 03:33:11,239][87426] Updated weights for policy 1, policy_version 127380 (0.0008) -[2023-11-28 03:33:11,593][87424] Updated weights for policy 0, policy_version 127646 (0.0009) -[2023-11-28 03:33:11,620][87426] Updated weights for policy 1, policy_version 127390 (0.0008) -[2023-11-28 03:33:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 65290240. Throughput: 0: 2757.6, 1: 2756.9. Samples: 65306216. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:33:13,445][86177] Avg episode reward: [(0, '-497.070'), (1, '-502.990')] -[2023-11-28 03:33:13,602][87424] Updated weights for policy 0, policy_version 127656 (0.0011) -[2023-11-28 03:33:13,653][87426] Updated weights for policy 1, policy_version 127400 (0.0011) -[2023-11-28 03:33:13,973][87424] Updated weights for policy 0, policy_version 127666 (0.0010) -[2023-11-28 03:33:14,029][87426] Updated weights for policy 1, policy_version 127410 (0.0008) -[2023-11-28 03:33:14,358][87424] Updated weights for policy 0, policy_version 127676 (0.0009) -[2023-11-28 03:33:14,413][87426] Updated weights for policy 1, policy_version 127420 (0.0010) -[2023-11-28 03:33:16,627][87426] Updated weights for policy 1, policy_version 127430 (0.0011) -[2023-11-28 03:33:16,831][87424] Updated weights for policy 0, policy_version 127686 (0.0011) -[2023-11-28 03:33:17,005][87426] Updated weights for policy 1, policy_version 127440 (0.0012) -[2023-11-28 03:33:17,202][87424] Updated weights for policy 0, policy_version 127696 (0.0008) -[2023-11-28 03:33:17,380][87426] Updated weights for policy 1, policy_version 127450 (0.0011) -[2023-11-28 03:33:17,582][87424] Updated weights for policy 0, policy_version 127706 (0.0007) -[2023-11-28 03:33:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65323008. Throughput: 0: 2755.6, 1: 2774.6. Samples: 65331632. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:33:18,446][86177] Avg episode reward: [(0, '-510.630'), (1, '-514.660')] -[2023-11-28 03:33:19,549][87424] Updated weights for policy 0, policy_version 127716 (0.0008) -[2023-11-28 03:33:19,932][87424] Updated weights for policy 0, policy_version 127726 (0.0010) -[2023-11-28 03:33:19,934][87426] Updated weights for policy 1, policy_version 127460 (0.0011) -[2023-11-28 03:33:20,315][87424] Updated weights for policy 0, policy_version 127736 (0.0011) -[2023-11-28 03:33:20,317][87426] Updated weights for policy 1, policy_version 127470 (0.0011) -[2023-11-28 03:33:20,692][87426] Updated weights for policy 1, policy_version 127480 (0.0011) -[2023-11-28 03:33:22,758][87424] Updated weights for policy 0, policy_version 127746 (0.0011) -[2023-11-28 03:33:23,035][87426] Updated weights for policy 1, policy_version 127490 (0.0009) -[2023-11-28 03:33:23,137][87424] Updated weights for policy 0, policy_version 127756 (0.0012) -[2023-11-28 03:33:23,418][87426] Updated weights for policy 1, policy_version 127500 (0.0010) -[2023-11-28 03:33:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 65339392. Throughput: 0: 2765.1, 1: 2751.4. Samples: 65363228. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:33:23,445][86177] Avg episode reward: [(0, '-509.150'), (1, '-517.640')] -[2023-11-28 03:33:23,519][87424] Updated weights for policy 0, policy_version 127766 (0.0008) -[2023-11-28 03:33:23,798][87426] Updated weights for policy 1, policy_version 127510 (0.0011) -[2023-11-28 03:33:23,897][87424] Updated weights for policy 0, policy_version 127776 (0.0011) -[2023-11-28 03:33:24,184][87426] Updated weights for policy 1, policy_version 127520 (0.0012) -[2023-11-28 03:33:25,858][87424] Updated weights for policy 0, policy_version 127786 (0.0007) -[2023-11-28 03:33:26,123][87426] Updated weights for policy 1, policy_version 127530 (0.0007) -[2023-11-28 03:33:26,238][87424] Updated weights for policy 0, policy_version 127796 (0.0007) -[2023-11-28 03:33:26,501][87426] Updated weights for policy 1, policy_version 127540 (0.0007) -[2023-11-28 03:33:26,610][87424] Updated weights for policy 0, policy_version 127806 (0.0008) -[2023-11-28 03:33:26,882][87426] Updated weights for policy 1, policy_version 127550 (0.0011) -[2023-11-28 03:33:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 65372160. Throughput: 0: 2757.6, 1: 2774.5. Samples: 65388420. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:33:28,445][86177] Avg episode reward: [(0, '-510.320'), (1, '-519.250')] -[2023-11-28 03:33:28,477][87424] Updated weights for policy 0, policy_version 127816 (0.0011) -[2023-11-28 03:33:28,704][87426] Updated weights for policy 1, policy_version 127560 (0.0011) -[2023-11-28 03:33:28,852][87424] Updated weights for policy 0, policy_version 127826 (0.0012) -[2023-11-28 03:33:29,082][87426] Updated weights for policy 1, policy_version 127570 (0.0010) -[2023-11-28 03:33:29,233][87424] Updated weights for policy 0, policy_version 127836 (0.0011) -[2023-11-28 03:33:29,461][87426] Updated weights for policy 1, policy_version 127580 (0.0011) -[2023-11-28 03:33:31,597][87424] Updated weights for policy 0, policy_version 127846 (0.0009) -[2023-11-28 03:33:31,976][87424] Updated weights for policy 0, policy_version 127856 (0.0010) -[2023-11-28 03:33:32,049][87426] Updated weights for policy 1, policy_version 127590 (0.0011) -[2023-11-28 03:33:32,357][87424] Updated weights for policy 0, policy_version 127866 (0.0011) -[2023-11-28 03:33:32,425][87426] Updated weights for policy 1, policy_version 127600 (0.0011) -[2023-11-28 03:33:32,806][87426] Updated weights for policy 1, policy_version 127610 (0.0012) -[2023-11-28 03:33:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65404928. Throughput: 0: 2765.4, 1: 2756.5. Samples: 65413960. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:33:33,446][86177] Avg episode reward: [(0, '-495.570'), (1, '-514.740')] -[2023-11-28 03:33:34,584][87426] Updated weights for policy 1, policy_version 127620 (0.0012) -[2023-11-28 03:33:34,644][87424] Updated weights for policy 0, policy_version 127876 (0.0009) -[2023-11-28 03:33:34,959][87426] Updated weights for policy 1, policy_version 127630 (0.0009) -[2023-11-28 03:33:35,031][87424] Updated weights for policy 0, policy_version 127886 (0.0010) -[2023-11-28 03:33:35,333][87426] Updated weights for policy 1, policy_version 127640 (0.0009) -[2023-11-28 03:33:35,407][87424] Updated weights for policy 0, policy_version 127896 (0.0010) -[2023-11-28 03:33:37,081][87424] Updated weights for policy 0, policy_version 127906 (0.0011) -[2023-11-28 03:33:37,455][87424] Updated weights for policy 0, policy_version 127916 (0.0011) -[2023-11-28 03:33:37,834][87424] Updated weights for policy 0, policy_version 127926 (0.0011) -[2023-11-28 03:33:37,838][87426] Updated weights for policy 1, policy_version 127650 (0.0008) -[2023-11-28 03:33:38,211][87424] Updated weights for policy 0, policy_version 127936 (0.0012) -[2023-11-28 03:33:38,217][87426] Updated weights for policy 1, policy_version 127660 (0.0008) -[2023-11-28 03:33:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 65429504. Throughput: 0: 2772.1, 1: 2736.6. Samples: 65446872. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:33:38,445][86177] Avg episode reward: [(0, '-505.800'), (1, '-498.320')] -[2023-11-28 03:33:38,593][87426] Updated weights for policy 1, policy_version 127670 (0.0011) -[2023-11-28 03:33:38,972][87426] Updated weights for policy 1, policy_version 127680 (0.0012) -[2023-11-28 03:33:40,643][87424] Updated weights for policy 0, policy_version 127946 (0.0012) -[2023-11-28 03:33:40,900][87426] Updated weights for policy 1, policy_version 127690 (0.0012) -[2023-11-28 03:33:41,033][87424] Updated weights for policy 0, policy_version 127956 (0.0012) -[2023-11-28 03:33:41,272][87426] Updated weights for policy 1, policy_version 127700 (0.0010) -[2023-11-28 03:33:41,420][87424] Updated weights for policy 0, policy_version 127966 (0.0012) -[2023-11-28 03:33:41,647][87426] Updated weights for policy 1, policy_version 127710 (0.0011) -[2023-11-28 03:33:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 65454080. Throughput: 0: 2768.3, 1: 2708.5. Samples: 65470968. Policy #0 lag: (min: 23.0, avg: 41.2, max: 63.0) -[2023-11-28 03:33:43,445][86177] Avg episode reward: [(0, '-505.790'), (1, '-494.160')] -[2023-11-28 03:33:43,654][87424] Updated weights for policy 0, policy_version 127976 (0.0011) -[2023-11-28 03:33:43,916][87426] Updated weights for policy 1, policy_version 127720 (0.0011) -[2023-11-28 03:33:44,032][87424] Updated weights for policy 0, policy_version 127986 (0.0012) -[2023-11-28 03:33:44,292][87426] Updated weights for policy 1, policy_version 127730 (0.0010) -[2023-11-28 03:33:44,414][87424] Updated weights for policy 0, policy_version 127996 (0.0012) -[2023-11-28 03:33:44,672][87426] Updated weights for policy 1, policy_version 127740 (0.0011) -[2023-11-28 03:33:46,360][87424] Updated weights for policy 0, policy_version 128006 (0.0012) -[2023-11-28 03:33:46,744][87424] Updated weights for policy 0, policy_version 128016 (0.0012) -[2023-11-28 03:33:47,054][87426] Updated weights for policy 1, policy_version 127750 (0.0010) -[2023-11-28 03:33:47,125][87424] Updated weights for policy 0, policy_version 128026 (0.0012) -[2023-11-28 03:33:47,428][87426] Updated weights for policy 1, policy_version 127760 (0.0010) -[2023-11-28 03:33:47,805][87426] Updated weights for policy 1, policy_version 127770 (0.0012) -[2023-11-28 03:33:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 65486848. Throughput: 0: 2781.9, 1: 2688.9. Samples: 65495420. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:33:48,445][86177] Avg episode reward: [(0, '-507.690'), (1, '-493.990')] -[2023-11-28 03:33:49,485][87424] Updated weights for policy 0, policy_version 128036 (0.0012) -[2023-11-28 03:33:49,823][87426] Updated weights for policy 1, policy_version 127780 (0.0012) -[2023-11-28 03:33:49,859][87424] Updated weights for policy 0, policy_version 128046 (0.0011) -[2023-11-28 03:33:50,204][87426] Updated weights for policy 1, policy_version 127790 (0.0015) -[2023-11-28 03:33:50,245][87424] Updated weights for policy 0, policy_version 128056 (0.0009) -[2023-11-28 03:33:50,578][87426] Updated weights for policy 1, policy_version 127800 (0.0010) -[2023-11-28 03:33:52,460][87424] Updated weights for policy 0, policy_version 128066 (0.0010) -[2023-11-28 03:33:52,842][87424] Updated weights for policy 0, policy_version 128076 (0.0011) -[2023-11-28 03:33:53,006][87426] Updated weights for policy 1, policy_version 127810 (0.0012) -[2023-11-28 03:33:53,228][87424] Updated weights for policy 0, policy_version 128086 (0.0011) -[2023-11-28 03:33:53,383][87426] Updated weights for policy 1, policy_version 127820 (0.0011) -[2023-11-28 03:33:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.7, 300 sec: 5415.1). Total num frames: 65503232. Throughput: 0: 2766.2, 1: 2694.0. Samples: 65527456. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:33:53,445][86177] Avg episode reward: [(0, '-504.300'), (1, '-493.990')] -[2023-11-28 03:33:53,610][87424] Updated weights for policy 0, policy_version 128096 (0.0010) -[2023-11-28 03:33:53,762][87426] Updated weights for policy 1, policy_version 127830 (0.0011) -[2023-11-28 03:33:54,142][87426] Updated weights for policy 1, policy_version 127840 (0.0012) -[2023-11-28 03:33:56,136][87424] Updated weights for policy 0, policy_version 128106 (0.0010) -[2023-11-28 03:33:56,167][87426] Updated weights for policy 1, policy_version 127850 (0.0010) -[2023-11-28 03:33:56,523][87424] Updated weights for policy 0, policy_version 128116 (0.0007) -[2023-11-28 03:33:56,532][87426] Updated weights for policy 1, policy_version 127860 (0.0007) -[2023-11-28 03:33:56,904][87426] Updated weights for policy 1, policy_version 127870 (0.0007) -[2023-11-28 03:33:56,910][87424] Updated weights for policy 0, policy_version 128126 (0.0007) -[2023-11-28 03:33:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 65536000. Throughput: 0: 2754.2, 1: 2697.3. Samples: 65551536. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:33:58,445][86177] Avg episode reward: [(0, '-499.910'), (1, '-500.110')] -[2023-11-28 03:33:59,161][87424] Updated weights for policy 0, policy_version 128136 (0.0011) -[2023-11-28 03:33:59,370][87426] Updated weights for policy 1, policy_version 127880 (0.0010) -[2023-11-28 03:33:59,539][87424] Updated weights for policy 0, policy_version 128146 (0.0011) -[2023-11-28 03:33:59,742][87426] Updated weights for policy 1, policy_version 127890 (0.0009) -[2023-11-28 03:33:59,924][87424] Updated weights for policy 0, policy_version 128156 (0.0009) -[2023-11-28 03:34:00,130][87426] Updated weights for policy 1, policy_version 127900 (0.0009) -[2023-11-28 03:34:01,815][87424] Updated weights for policy 0, policy_version 128166 (0.0012) -[2023-11-28 03:34:02,196][87424] Updated weights for policy 0, policy_version 128176 (0.0011) -[2023-11-28 03:34:02,341][87426] Updated weights for policy 1, policy_version 127910 (0.0010) -[2023-11-28 03:34:02,579][87424] Updated weights for policy 0, policy_version 128186 (0.0009) -[2023-11-28 03:34:02,719][87426] Updated weights for policy 1, policy_version 127920 (0.0012) -[2023-11-28 03:34:03,099][87426] Updated weights for policy 1, policy_version 127930 (0.0012) -[2023-11-28 03:34:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65568768. Throughput: 0: 2742.9, 1: 2675.6. Samples: 65575460. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:34:03,445][86177] Avg episode reward: [(0, '-503.770'), (1, '-501.420')] -[2023-11-28 03:34:04,281][87424] Updated weights for policy 0, policy_version 128196 (0.0009) -[2023-11-28 03:34:04,674][87424] Updated weights for policy 0, policy_version 128206 (0.0011) -[2023-11-28 03:34:05,045][87424] Updated weights for policy 0, policy_version 128216 (0.0011) -[2023-11-28 03:34:05,133][87426] Updated weights for policy 1, policy_version 127940 (0.0012) -[2023-11-28 03:34:05,517][87426] Updated weights for policy 1, policy_version 127950 (0.0008) -[2023-11-28 03:34:05,887][87426] Updated weights for policy 1, policy_version 127960 (0.0011) -[2023-11-28 03:34:07,114][87424] Updated weights for policy 0, policy_version 128226 (0.0008) -[2023-11-28 03:34:07,492][87424] Updated weights for policy 0, policy_version 128236 (0.0012) -[2023-11-28 03:34:07,883][87424] Updated weights for policy 0, policy_version 128246 (0.0012) -[2023-11-28 03:34:08,260][87424] Updated weights for policy 0, policy_version 128256 (0.0012) -[2023-11-28 03:34:08,344][87426] Updated weights for policy 1, policy_version 127970 (0.0011) -[2023-11-28 03:34:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65593344. Throughput: 0: 2762.5, 1: 2692.1. Samples: 65608684. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:34:08,445][86177] Avg episode reward: [(0, '-502.580'), (1, '-502.260')] -[2023-11-28 03:34:08,725][87426] Updated weights for policy 1, policy_version 127980 (0.0012) -[2023-11-28 03:34:09,106][87426] Updated weights for policy 1, policy_version 127990 (0.0012) -[2023-11-28 03:34:09,484][87426] Updated weights for policy 1, policy_version 128000 (0.0012) -[2023-11-28 03:34:10,861][87424] Updated weights for policy 0, policy_version 128266 (0.0008) -[2023-11-28 03:34:11,249][87424] Updated weights for policy 0, policy_version 128276 (0.0010) -[2023-11-28 03:34:11,626][87424] Updated weights for policy 0, policy_version 128286 (0.0011) -[2023-11-28 03:34:11,763][87426] Updated weights for policy 1, policy_version 128010 (0.0011) -[2023-11-28 03:34:12,139][87426] Updated weights for policy 1, policy_version 128020 (0.0012) -[2023-11-28 03:34:12,522][87426] Updated weights for policy 1, policy_version 128030 (0.0009) -[2023-11-28 03:34:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 65617920. Throughput: 0: 2761.5, 1: 2647.5. Samples: 65631824. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:34:13,445][86177] Avg episode reward: [(0, '-503.040'), (1, '-503.460')] -[2023-11-28 03:34:13,798][87424] Updated weights for policy 0, policy_version 128296 (0.0008) -[2023-11-28 03:34:14,180][87424] Updated weights for policy 0, policy_version 128306 (0.0007) -[2023-11-28 03:34:14,565][87424] Updated weights for policy 0, policy_version 128316 (0.0008) -[2023-11-28 03:34:14,769][87426] Updated weights for policy 1, policy_version 128040 (0.0008) -[2023-11-28 03:34:15,144][87426] Updated weights for policy 1, policy_version 128050 (0.0009) -[2023-11-28 03:34:15,526][87426] Updated weights for policy 1, policy_version 128060 (0.0009) -[2023-11-28 03:34:16,627][87424] Updated weights for policy 0, policy_version 128326 (0.0010) -[2023-11-28 03:34:17,005][87424] Updated weights for policy 0, policy_version 128336 (0.0007) -[2023-11-28 03:34:17,376][87424] Updated weights for policy 0, policy_version 128346 (0.0009) -[2023-11-28 03:34:17,377][87426] Updated weights for policy 1, policy_version 128070 (0.0009) -[2023-11-28 03:34:17,761][87426] Updated weights for policy 1, policy_version 128080 (0.0007) -[2023-11-28 03:34:18,142][87426] Updated weights for policy 1, policy_version 128090 (0.0008) -[2023-11-28 03:34:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 65650688. Throughput: 0: 2723.2, 1: 2658.2. Samples: 65656124. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:34:18,445][86177] Avg episode reward: [(0, '-500.680'), (1, '-496.960')] -[2023-11-28 03:34:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000128096_32792576.pth... -[2023-11-28 03:34:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000128352_32858112.pth... -[2023-11-28 03:34:18,507][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000125568_32145408.pth -[2023-11-28 03:34:18,507][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000125824_32210944.pth -[2023-11-28 03:34:19,766][87424] Updated weights for policy 0, policy_version 128356 (0.0009) -[2023-11-28 03:34:20,142][87424] Updated weights for policy 0, policy_version 128366 (0.0012) -[2023-11-28 03:34:20,400][87426] Updated weights for policy 1, policy_version 128100 (0.0010) -[2023-11-28 03:34:20,524][87424] Updated weights for policy 0, policy_version 128376 (0.0011) -[2023-11-28 03:34:20,779][87426] Updated weights for policy 1, policy_version 128110 (0.0012) -[2023-11-28 03:34:21,162][87426] Updated weights for policy 1, policy_version 128120 (0.0012) -[2023-11-28 03:34:23,009][87424] Updated weights for policy 0, policy_version 128386 (0.0009) -[2023-11-28 03:34:23,391][87424] Updated weights for policy 0, policy_version 128396 (0.0009) -[2023-11-28 03:34:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 65667072. Throughput: 0: 2705.2, 1: 2649.6. Samples: 65687840. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:34:23,445][86177] Avg episode reward: [(0, '-498.560'), (1, '-497.150')] -[2023-11-28 03:34:23,519][87426] Updated weights for policy 1, policy_version 128130 (0.0011) -[2023-11-28 03:34:23,773][87424] Updated weights for policy 0, policy_version 128406 (0.0008) -[2023-11-28 03:34:23,895][87426] Updated weights for policy 1, policy_version 128140 (0.0009) -[2023-11-28 03:34:24,155][87424] Updated weights for policy 0, policy_version 128416 (0.0008) -[2023-11-28 03:34:24,273][87426] Updated weights for policy 1, policy_version 128150 (0.0012) -[2023-11-28 03:34:24,650][87426] Updated weights for policy 1, policy_version 128160 (0.0012) -[2023-11-28 03:34:26,130][87424] Updated weights for policy 0, policy_version 128426 (0.0011) -[2023-11-28 03:34:26,518][87424] Updated weights for policy 0, policy_version 128436 (0.0012) -[2023-11-28 03:34:26,896][87424] Updated weights for policy 0, policy_version 128446 (0.0012) -[2023-11-28 03:34:27,125][87426] Updated weights for policy 1, policy_version 128170 (0.0012) -[2023-11-28 03:34:27,508][87426] Updated weights for policy 1, policy_version 128180 (0.0011) -[2023-11-28 03:34:27,890][87426] Updated weights for policy 1, policy_version 128190 (0.0012) -[2023-11-28 03:34:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 65699840. Throughput: 0: 2727.0, 1: 2650.3. Samples: 65712948. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:34:28,445][86177] Avg episode reward: [(0, '-495.740'), (1, '-493.930')] -[2023-11-28 03:34:28,646][87424] Updated weights for policy 0, policy_version 128456 (0.0011) -[2023-11-28 03:34:29,024][87424] Updated weights for policy 0, policy_version 128466 (0.0012) -[2023-11-28 03:34:29,401][87424] Updated weights for policy 0, policy_version 128476 (0.0012) -[2023-11-28 03:34:29,953][87426] Updated weights for policy 1, policy_version 128200 (0.0012) -[2023-11-28 03:34:30,331][87426] Updated weights for policy 1, policy_version 128210 (0.0009) -[2023-11-28 03:34:30,710][87426] Updated weights for policy 1, policy_version 128220 (0.0009) -[2023-11-28 03:34:31,140][87424] Updated weights for policy 0, policy_version 128486 (0.0010) -[2023-11-28 03:34:31,537][87424] Updated weights for policy 0, policy_version 128496 (0.0009) -[2023-11-28 03:34:31,907][87424] Updated weights for policy 0, policy_version 128506 (0.0012) -[2023-11-28 03:34:33,260][87426] Updated weights for policy 1, policy_version 128230 (0.0010) -[2023-11-28 03:34:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 65724416. Throughput: 0: 2722.1, 1: 2670.9. Samples: 65738100. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:34:33,445][86177] Avg episode reward: [(0, '-495.860'), (1, '-492.960')] -[2023-11-28 03:34:33,646][87426] Updated weights for policy 1, policy_version 128240 (0.0010) -[2023-11-28 03:34:34,036][87426] Updated weights for policy 1, policy_version 128250 (0.0008) -[2023-11-28 03:34:34,040][87424] Updated weights for policy 0, policy_version 128516 (0.0011) -[2023-11-28 03:34:34,416][87424] Updated weights for policy 0, policy_version 128526 (0.0007) -[2023-11-28 03:34:34,798][87424] Updated weights for policy 0, policy_version 128536 (0.0008) -[2023-11-28 03:34:36,372][87426] Updated weights for policy 1, policy_version 128260 (0.0010) -[2023-11-28 03:34:36,752][87426] Updated weights for policy 1, policy_version 128270 (0.0010) -[2023-11-28 03:34:37,136][87426] Updated weights for policy 1, policy_version 128280 (0.0011) -[2023-11-28 03:34:37,287][87424] Updated weights for policy 0, policy_version 128546 (0.0011) -[2023-11-28 03:34:37,666][87424] Updated weights for policy 0, policy_version 128556 (0.0011) -[2023-11-28 03:34:38,059][87424] Updated weights for policy 0, policy_version 128566 (0.0012) -[2023-11-28 03:34:38,429][87424] Updated weights for policy 0, policy_version 128576 (0.0012) -[2023-11-28 03:34:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65757184. Throughput: 0: 2733.6, 1: 2646.6. Samples: 65769564. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:34:38,445][86177] Avg episode reward: [(0, '-494.090'), (1, '-490.970')] -[2023-11-28 03:34:39,128][87426] Updated weights for policy 1, policy_version 128290 (0.0011) -[2023-11-28 03:34:39,507][87426] Updated weights for policy 1, policy_version 128300 (0.0011) -[2023-11-28 03:34:39,888][87426] Updated weights for policy 1, policy_version 128310 (0.0011) -[2023-11-28 03:34:40,267][87426] Updated weights for policy 1, policy_version 128320 (0.0011) -[2023-11-28 03:34:40,290][87424] Updated weights for policy 0, policy_version 128586 (0.0011) -[2023-11-28 03:34:40,683][87424] Updated weights for policy 0, policy_version 128596 (0.0012) -[2023-11-28 03:34:41,075][87424] Updated weights for policy 0, policy_version 128606 (0.0012) -[2023-11-28 03:34:42,659][87426] Updated weights for policy 1, policy_version 128330 (0.0009) -[2023-11-28 03:34:43,036][87426] Updated weights for policy 1, policy_version 128340 (0.0010) -[2023-11-28 03:34:43,366][87424] Updated weights for policy 0, policy_version 128616 (0.0009) -[2023-11-28 03:34:43,412][87426] Updated weights for policy 1, policy_version 128350 (0.0008) -[2023-11-28 03:34:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 65773568. Throughput: 0: 2736.0, 1: 2646.5. Samples: 65793748. Policy #0 lag: (min: 18.0, avg: 46.6, max: 58.0) -[2023-11-28 03:34:43,445][86177] Avg episode reward: [(0, '-497.200'), (1, '-489.330')] -[2023-11-28 03:34:43,487][87320] Saving new best policy, reward=-489.330! -[2023-11-28 03:34:43,742][87424] Updated weights for policy 0, policy_version 128626 (0.0012) -[2023-11-28 03:34:44,133][87424] Updated weights for policy 0, policy_version 128636 (0.0012) -[2023-11-28 03:34:45,231][87426] Updated weights for policy 1, policy_version 128360 (0.0008) -[2023-11-28 03:34:45,613][87426] Updated weights for policy 1, policy_version 128370 (0.0009) -[2023-11-28 03:34:45,987][87426] Updated weights for policy 1, policy_version 128380 (0.0007) -[2023-11-28 03:34:46,347][87424] Updated weights for policy 0, policy_version 128646 (0.0012) -[2023-11-28 03:34:46,741][87424] Updated weights for policy 0, policy_version 128656 (0.0012) -[2023-11-28 03:34:47,121][87424] Updated weights for policy 0, policy_version 128666 (0.0012) -[2023-11-28 03:34:48,415][87426] Updated weights for policy 1, policy_version 128390 (0.0010) -[2023-11-28 03:34:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 65806336. Throughput: 0: 2734.4, 1: 2661.0. Samples: 65818252. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:34:48,445][86177] Avg episode reward: [(0, '-496.450'), (1, '-492.710')] -[2023-11-28 03:34:48,794][87426] Updated weights for policy 1, policy_version 128400 (0.0012) -[2023-11-28 03:34:48,954][87424] Updated weights for policy 0, policy_version 128676 (0.0012) -[2023-11-28 03:34:49,173][87426] Updated weights for policy 1, policy_version 128410 (0.0011) -[2023-11-28 03:34:49,338][87424] Updated weights for policy 0, policy_version 128686 (0.0011) -[2023-11-28 03:34:49,720][87424] Updated weights for policy 0, policy_version 128696 (0.0010) -[2023-11-28 03:34:51,432][87426] Updated weights for policy 1, policy_version 128420 (0.0012) -[2023-11-28 03:34:51,814][87426] Updated weights for policy 1, policy_version 128430 (0.0011) -[2023-11-28 03:34:52,020][87424] Updated weights for policy 0, policy_version 128706 (0.0012) -[2023-11-28 03:34:52,195][87426] Updated weights for policy 1, policy_version 128440 (0.0012) -[2023-11-28 03:34:52,407][87424] Updated weights for policy 0, policy_version 128716 (0.0010) -[2023-11-28 03:34:52,798][87424] Updated weights for policy 0, policy_version 128726 (0.0008) -[2023-11-28 03:34:53,174][87424] Updated weights for policy 0, policy_version 128736 (0.0009) -[2023-11-28 03:34:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 65839104. Throughput: 0: 2765.0, 1: 2655.3. Samples: 65852596. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:34:53,445][86177] Avg episode reward: [(0, '-497.380'), (1, '-494.920')] -[2023-11-28 03:34:54,478][87426] Updated weights for policy 1, policy_version 128450 (0.0008) -[2023-11-28 03:34:54,860][87426] Updated weights for policy 1, policy_version 128460 (0.0008) -[2023-11-28 03:34:55,238][87426] Updated weights for policy 1, policy_version 128470 (0.0008) -[2023-11-28 03:34:55,452][87424] Updated weights for policy 0, policy_version 128746 (0.0012) -[2023-11-28 03:34:55,619][87426] Updated weights for policy 1, policy_version 128480 (0.0011) -[2023-11-28 03:34:55,845][87424] Updated weights for policy 0, policy_version 128756 (0.0012) -[2023-11-28 03:34:56,242][87424] Updated weights for policy 0, policy_version 128766 (0.0012) -[2023-11-28 03:34:57,476][87426] Updated weights for policy 1, policy_version 128490 (0.0011) -[2023-11-28 03:34:57,856][87426] Updated weights for policy 1, policy_version 128500 (0.0007) -[2023-11-28 03:34:57,962][87424] Updated weights for policy 0, policy_version 128776 (0.0012) -[2023-11-28 03:34:58,235][87426] Updated weights for policy 1, policy_version 128510 (0.0007) -[2023-11-28 03:34:58,341][87424] Updated weights for policy 0, policy_version 128786 (0.0012) -[2023-11-28 03:34:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65863680. Throughput: 0: 2763.5, 1: 2687.5. Samples: 65877120. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:34:58,445][86177] Avg episode reward: [(0, '-497.920'), (1, '-501.490')] -[2023-11-28 03:34:58,726][87424] Updated weights for policy 0, policy_version 128796 (0.0012) -[2023-11-28 03:35:00,288][87426] Updated weights for policy 1, policy_version 128520 (0.0011) -[2023-11-28 03:35:00,673][87426] Updated weights for policy 1, policy_version 128530 (0.0012) -[2023-11-28 03:35:01,044][87426] Updated weights for policy 1, policy_version 128540 (0.0009) -[2023-11-28 03:35:01,184][87424] Updated weights for policy 0, policy_version 128806 (0.0011) -[2023-11-28 03:35:01,585][87424] Updated weights for policy 0, policy_version 128816 (0.0012) -[2023-11-28 03:35:01,971][87424] Updated weights for policy 0, policy_version 128826 (0.0011) -[2023-11-28 03:35:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 65888256. Throughput: 0: 2775.3, 1: 2678.4. Samples: 65901540. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:03,446][86177] Avg episode reward: [(0, '-494.500'), (1, '-506.880')] -[2023-11-28 03:35:03,641][87426] Updated weights for policy 1, policy_version 128550 (0.0007) -[2023-11-28 03:35:04,024][87426] Updated weights for policy 1, policy_version 128560 (0.0007) -[2023-11-28 03:35:04,404][87426] Updated weights for policy 1, policy_version 128570 (0.0008) -[2023-11-28 03:35:04,406][87424] Updated weights for policy 0, policy_version 128836 (0.0010) -[2023-11-28 03:35:04,781][87424] Updated weights for policy 0, policy_version 128846 (0.0011) -[2023-11-28 03:35:05,162][87424] Updated weights for policy 0, policy_version 128856 (0.0012) -[2023-11-28 03:35:06,909][87426] Updated weights for policy 1, policy_version 128580 (0.0008) -[2023-11-28 03:35:06,974][87424] Updated weights for policy 0, policy_version 128866 (0.0012) -[2023-11-28 03:35:07,275][87426] Updated weights for policy 1, policy_version 128590 (0.0007) -[2023-11-28 03:35:07,360][87424] Updated weights for policy 0, policy_version 128876 (0.0012) -[2023-11-28 03:35:07,656][87426] Updated weights for policy 1, policy_version 128600 (0.0010) -[2023-11-28 03:35:07,741][87424] Updated weights for policy 0, policy_version 128886 (0.0012) -[2023-11-28 03:35:08,123][87424] Updated weights for policy 0, policy_version 128896 (0.0008) -[2023-11-28 03:35:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 65921024. Throughput: 0: 2783.4, 1: 2668.0. Samples: 65933152. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:08,445][86177] Avg episode reward: [(0, '-503.340'), (1, '-521.100')] -[2023-11-28 03:35:10,082][87426] Updated weights for policy 1, policy_version 128610 (0.0010) -[2023-11-28 03:35:10,463][87426] Updated weights for policy 1, policy_version 128620 (0.0012) -[2023-11-28 03:35:10,625][87424] Updated weights for policy 0, policy_version 128906 (0.0011) -[2023-11-28 03:35:10,845][87426] Updated weights for policy 1, policy_version 128630 (0.0011) -[2023-11-28 03:35:11,009][87424] Updated weights for policy 0, policy_version 128916 (0.0009) -[2023-11-28 03:35:11,223][87426] Updated weights for policy 1, policy_version 128640 (0.0011) -[2023-11-28 03:35:11,387][87424] Updated weights for policy 0, policy_version 128926 (0.0009) -[2023-11-28 03:35:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 65937408. Throughput: 0: 2764.3, 1: 2681.6. Samples: 65958012. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:13,445][86177] Avg episode reward: [(0, '-509.680'), (1, '-556.290')] -[2023-11-28 03:35:13,706][87426] Updated weights for policy 1, policy_version 128650 (0.0012) -[2023-11-28 03:35:13,722][87424] Updated weights for policy 0, policy_version 128936 (0.0011) -[2023-11-28 03:35:14,081][87426] Updated weights for policy 1, policy_version 128660 (0.0012) -[2023-11-28 03:35:14,103][87424] Updated weights for policy 0, policy_version 128946 (0.0012) -[2023-11-28 03:35:14,463][87426] Updated weights for policy 1, policy_version 128670 (0.0010) -[2023-11-28 03:35:14,483][87424] Updated weights for policy 0, policy_version 128956 (0.0012) -[2023-11-28 03:35:16,251][87424] Updated weights for policy 0, policy_version 128966 (0.0009) -[2023-11-28 03:35:16,634][87424] Updated weights for policy 0, policy_version 128976 (0.0008) -[2023-11-28 03:35:16,964][87426] Updated weights for policy 1, policy_version 128680 (0.0011) -[2023-11-28 03:35:17,018][87424] Updated weights for policy 0, policy_version 128986 (0.0009) -[2023-11-28 03:35:17,337][87426] Updated weights for policy 1, policy_version 128690 (0.0007) -[2023-11-28 03:35:17,713][87426] Updated weights for policy 1, policy_version 128700 (0.0007) -[2023-11-28 03:35:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 65970176. Throughput: 0: 2744.8, 1: 2669.9. Samples: 65981760. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:18,445][86177] Avg episode reward: [(0, '-510.780'), (1, '-556.800')] -[2023-11-28 03:35:18,858][87424] Updated weights for policy 0, policy_version 128996 (0.0009) -[2023-11-28 03:35:19,242][87424] Updated weights for policy 0, policy_version 129006 (0.0008) -[2023-11-28 03:35:19,524][87426] Updated weights for policy 1, policy_version 128710 (0.0007) -[2023-11-28 03:35:19,624][87424] Updated weights for policy 0, policy_version 129016 (0.0007) -[2023-11-28 03:35:19,902][87426] Updated weights for policy 1, policy_version 128720 (0.0009) -[2023-11-28 03:35:20,284][87426] Updated weights for policy 1, policy_version 128730 (0.0012) -[2023-11-28 03:35:21,482][87424] Updated weights for policy 0, policy_version 129026 (0.0010) -[2023-11-28 03:35:21,858][87424] Updated weights for policy 0, policy_version 129036 (0.0012) -[2023-11-28 03:35:22,241][87424] Updated weights for policy 0, policy_version 129046 (0.0011) -[2023-11-28 03:35:22,611][87426] Updated weights for policy 1, policy_version 128740 (0.0011) -[2023-11-28 03:35:22,615][87424] Updated weights for policy 0, policy_version 129056 (0.0011) -[2023-11-28 03:35:22,986][87426] Updated weights for policy 1, policy_version 128750 (0.0011) -[2023-11-28 03:35:23,362][87426] Updated weights for policy 1, policy_version 128760 (0.0009) -[2023-11-28 03:35:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 65994752. Throughput: 0: 2738.0, 1: 2692.8. Samples: 66013952. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:23,445][86177] Avg episode reward: [(0, '-501.260'), (1, '-579.430')] -[2023-11-28 03:35:25,008][87424] Updated weights for policy 0, policy_version 129066 (0.0012) -[2023-11-28 03:35:25,345][87426] Updated weights for policy 1, policy_version 128770 (0.0010) -[2023-11-28 03:35:25,387][87424] Updated weights for policy 0, policy_version 129076 (0.0012) -[2023-11-28 03:35:25,731][87426] Updated weights for policy 1, policy_version 128780 (0.0008) -[2023-11-28 03:35:25,764][87424] Updated weights for policy 0, policy_version 129086 (0.0012) -[2023-11-28 03:35:26,104][87426] Updated weights for policy 1, policy_version 128790 (0.0008) -[2023-11-28 03:35:26,476][87426] Updated weights for policy 1, policy_version 128800 (0.0007) -[2023-11-28 03:35:27,885][87424] Updated weights for policy 0, policy_version 129096 (0.0011) -[2023-11-28 03:35:28,269][87424] Updated weights for policy 0, policy_version 129106 (0.0008) -[2023-11-28 03:35:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 66019328. Throughput: 0: 2748.5, 1: 2683.3. Samples: 66038180. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:28,445][86177] Avg episode reward: [(0, '-500.030'), (1, '-588.510')] -[2023-11-28 03:35:28,650][87424] Updated weights for policy 0, policy_version 129116 (0.0007) -[2023-11-28 03:35:28,883][87426] Updated weights for policy 1, policy_version 128810 (0.0009) -[2023-11-28 03:35:29,259][87426] Updated weights for policy 1, policy_version 128820 (0.0012) -[2023-11-28 03:35:29,630][87426] Updated weights for policy 1, policy_version 128830 (0.0012) -[2023-11-28 03:35:30,573][87424] Updated weights for policy 0, policy_version 129126 (0.0010) -[2023-11-28 03:35:30,957][87424] Updated weights for policy 0, policy_version 129136 (0.0012) -[2023-11-28 03:35:31,351][87424] Updated weights for policy 0, policy_version 129146 (0.0012) -[2023-11-28 03:35:31,853][87426] Updated weights for policy 1, policy_version 128840 (0.0010) -[2023-11-28 03:35:32,241][87426] Updated weights for policy 1, policy_version 128850 (0.0009) -[2023-11-28 03:35:32,608][87426] Updated weights for policy 1, policy_version 128860 (0.0008) -[2023-11-28 03:35:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66052096. Throughput: 0: 2785.1, 1: 2680.1. Samples: 66064184. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:33,445][86177] Avg episode reward: [(0, '-494.820'), (1, '-552.610')] -[2023-11-28 03:35:33,743][87424] Updated weights for policy 0, policy_version 129156 (0.0012) -[2023-11-28 03:35:34,133][87424] Updated weights for policy 0, policy_version 129166 (0.0012) -[2023-11-28 03:35:34,280][87426] Updated weights for policy 1, policy_version 128870 (0.0009) -[2023-11-28 03:35:34,505][87424] Updated weights for policy 0, policy_version 129176 (0.0011) -[2023-11-28 03:35:34,652][87426] Updated weights for policy 1, policy_version 128880 (0.0009) -[2023-11-28 03:35:35,035][87426] Updated weights for policy 1, policy_version 128890 (0.0008) -[2023-11-28 03:35:36,570][87424] Updated weights for policy 0, policy_version 129186 (0.0011) -[2023-11-28 03:35:36,956][87424] Updated weights for policy 0, policy_version 129196 (0.0008) -[2023-11-28 03:35:37,247][87426] Updated weights for policy 1, policy_version 128900 (0.0008) -[2023-11-28 03:35:37,338][87424] Updated weights for policy 0, policy_version 129206 (0.0011) -[2023-11-28 03:35:37,626][87426] Updated weights for policy 1, policy_version 128910 (0.0008) -[2023-11-28 03:35:37,715][87424] Updated weights for policy 0, policy_version 129216 (0.0012) -[2023-11-28 03:35:38,005][87426] Updated weights for policy 1, policy_version 128920 (0.0011) -[2023-11-28 03:35:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 66084864. Throughput: 0: 2731.2, 1: 2697.0. Samples: 66096864. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:38,445][86177] Avg episode reward: [(0, '-494.080'), (1, '-531.440')] -[2023-11-28 03:35:40,084][87424] Updated weights for policy 0, policy_version 129226 (0.0012) -[2023-11-28 03:35:40,457][87424] Updated weights for policy 0, policy_version 129236 (0.0011) -[2023-11-28 03:35:40,462][87426] Updated weights for policy 1, policy_version 128930 (0.0008) -[2023-11-28 03:35:40,831][87424] Updated weights for policy 0, policy_version 129246 (0.0010) -[2023-11-28 03:35:40,845][87426] Updated weights for policy 1, policy_version 128940 (0.0008) -[2023-11-28 03:35:41,217][87426] Updated weights for policy 1, policy_version 128950 (0.0008) -[2023-11-28 03:35:41,593][87426] Updated weights for policy 1, policy_version 128960 (0.0008) -[2023-11-28 03:35:43,102][87424] Updated weights for policy 0, policy_version 129256 (0.0010) -[2023-11-28 03:35:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66101248. Throughput: 0: 2738.4, 1: 2686.7. Samples: 66121248. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:43,445][86177] Avg episode reward: [(0, '-494.990'), (1, '-524.110')] -[2023-11-28 03:35:43,490][87424] Updated weights for policy 0, policy_version 129266 (0.0011) -[2023-11-28 03:35:43,863][87424] Updated weights for policy 0, policy_version 129276 (0.0010) -[2023-11-28 03:35:43,958][87426] Updated weights for policy 1, policy_version 128970 (0.0011) -[2023-11-28 03:35:44,336][87426] Updated weights for policy 1, policy_version 128980 (0.0007) -[2023-11-28 03:35:44,716][87426] Updated weights for policy 1, policy_version 128990 (0.0011) -[2023-11-28 03:35:45,728][87424] Updated weights for policy 0, policy_version 129286 (0.0010) -[2023-11-28 03:35:46,102][87424] Updated weights for policy 0, policy_version 129296 (0.0010) -[2023-11-28 03:35:46,491][87424] Updated weights for policy 0, policy_version 129306 (0.0008) -[2023-11-28 03:35:47,252][87426] Updated weights for policy 1, policy_version 129000 (0.0011) -[2023-11-28 03:35:47,633][87426] Updated weights for policy 1, policy_version 129010 (0.0008) -[2023-11-28 03:35:48,011][87426] Updated weights for policy 1, policy_version 129020 (0.0008) -[2023-11-28 03:35:48,203][87424] Updated weights for policy 0, policy_version 129316 (0.0009) -[2023-11-28 03:35:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 66134016. Throughput: 0: 2729.0, 1: 2674.4. Samples: 66144692. Policy #0 lag: (min: 13.0, avg: 28.1, max: 45.0) -[2023-11-28 03:35:48,445][86177] Avg episode reward: [(0, '-498.480'), (1, '-523.990')] -[2023-11-28 03:35:48,585][87424] Updated weights for policy 0, policy_version 129326 (0.0011) -[2023-11-28 03:35:48,979][87424] Updated weights for policy 0, policy_version 129336 (0.0008) -[2023-11-28 03:35:49,712][87426] Updated weights for policy 1, policy_version 129030 (0.0009) -[2023-11-28 03:35:50,087][87426] Updated weights for policy 1, policy_version 129040 (0.0009) -[2023-11-28 03:35:50,473][87426] Updated weights for policy 1, policy_version 129050 (0.0008) -[2023-11-28 03:35:51,496][87424] Updated weights for policy 0, policy_version 129346 (0.0009) -[2023-11-28 03:35:51,903][87424] Updated weights for policy 0, policy_version 129356 (0.0012) -[2023-11-28 03:35:52,280][87424] Updated weights for policy 0, policy_version 129366 (0.0010) -[2023-11-28 03:35:52,301][87426] Updated weights for policy 1, policy_version 129060 (0.0009) -[2023-11-28 03:35:52,659][87424] Updated weights for policy 0, policy_version 129376 (0.0012) -[2023-11-28 03:35:52,671][87426] Updated weights for policy 1, policy_version 129070 (0.0008) -[2023-11-28 03:35:53,060][87426] Updated weights for policy 1, policy_version 129080 (0.0010) -[2023-11-28 03:35:53,445][86177] Fps is (10 sec: 6553.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 66166784. Throughput: 0: 2721.7, 1: 2707.6. Samples: 66177472. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:35:53,445][86177] Avg episode reward: [(0, '-497.160'), (1, '-523.270')] -[2023-11-28 03:35:54,761][87424] Updated weights for policy 0, policy_version 129386 (0.0012) -[2023-11-28 03:35:55,142][87424] Updated weights for policy 0, policy_version 129396 (0.0012) -[2023-11-28 03:35:55,225][87426] Updated weights for policy 1, policy_version 129090 (0.0010) -[2023-11-28 03:35:55,525][87424] Updated weights for policy 0, policy_version 129406 (0.0010) -[2023-11-28 03:35:55,609][87426] Updated weights for policy 1, policy_version 129100 (0.0007) -[2023-11-28 03:35:55,984][87426] Updated weights for policy 1, policy_version 129110 (0.0007) -[2023-11-28 03:35:56,367][87426] Updated weights for policy 1, policy_version 129120 (0.0007) -[2023-11-28 03:35:57,566][87424] Updated weights for policy 0, policy_version 129416 (0.0011) -[2023-11-28 03:35:57,954][87424] Updated weights for policy 0, policy_version 129426 (0.0011) -[2023-11-28 03:35:58,337][87424] Updated weights for policy 0, policy_version 129436 (0.0007) -[2023-11-28 03:35:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 66183168. Throughput: 0: 2722.0, 1: 2711.0. Samples: 66202500. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:35:58,445][86177] Avg episode reward: [(0, '-496.470'), (1, '-523.090')] -[2023-11-28 03:35:58,810][87426] Updated weights for policy 1, policy_version 129130 (0.0009) -[2023-11-28 03:35:59,191][87426] Updated weights for policy 1, policy_version 129140 (0.0011) -[2023-11-28 03:35:59,592][87426] Updated weights for policy 1, policy_version 129150 (0.0011) -[2023-11-28 03:36:00,278][87424] Updated weights for policy 0, policy_version 129446 (0.0008) -[2023-11-28 03:36:00,659][87424] Updated weights for policy 0, policy_version 129456 (0.0009) -[2023-11-28 03:36:01,042][87424] Updated weights for policy 0, policy_version 129466 (0.0008) -[2023-11-28 03:36:01,642][87426] Updated weights for policy 1, policy_version 129160 (0.0009) -[2023-11-28 03:36:02,017][87426] Updated weights for policy 1, policy_version 129170 (0.0011) -[2023-11-28 03:36:02,398][87426] Updated weights for policy 1, policy_version 129180 (0.0010) -[2023-11-28 03:36:03,444][86177] Fps is (10 sec: 4915.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 66215936. Throughput: 0: 2747.3, 1: 2718.8. Samples: 66227732. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:03,445][86177] Avg episode reward: [(0, '-494.680'), (1, '-495.640')] -[2023-11-28 03:36:03,611][87424] Updated weights for policy 0, policy_version 129476 (0.0008) -[2023-11-28 03:36:03,988][87424] Updated weights for policy 0, policy_version 129486 (0.0007) -[2023-11-28 03:36:04,086][87426] Updated weights for policy 1, policy_version 129190 (0.0009) -[2023-11-28 03:36:04,363][87424] Updated weights for policy 0, policy_version 129496 (0.0007) -[2023-11-28 03:36:04,464][87426] Updated weights for policy 1, policy_version 129200 (0.0008) -[2023-11-28 03:36:04,842][87426] Updated weights for policy 1, policy_version 129210 (0.0011) -[2023-11-28 03:36:06,931][87424] Updated weights for policy 0, policy_version 129506 (0.0008) -[2023-11-28 03:36:07,307][87424] Updated weights for policy 0, policy_version 129516 (0.0008) -[2023-11-28 03:36:07,326][87426] Updated weights for policy 1, policy_version 129220 (0.0010) -[2023-11-28 03:36:07,693][87424] Updated weights for policy 0, policy_version 129526 (0.0008) -[2023-11-28 03:36:07,706][87426] Updated weights for policy 1, policy_version 129230 (0.0007) -[2023-11-28 03:36:08,076][87424] Updated weights for policy 0, policy_version 129536 (0.0008) -[2023-11-28 03:36:08,089][87426] Updated weights for policy 1, policy_version 129240 (0.0008) -[2023-11-28 03:36:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 66248704. Throughput: 0: 2719.8, 1: 2744.9. Samples: 66259864. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:08,445][86177] Avg episode reward: [(0, '-492.640'), (1, '-500.800')] -[2023-11-28 03:36:10,012][87426] Updated weights for policy 1, policy_version 129250 (0.0008) -[2023-11-28 03:36:10,390][87426] Updated weights for policy 1, policy_version 129260 (0.0010) -[2023-11-28 03:36:10,391][87424] Updated weights for policy 0, policy_version 129546 (0.0011) -[2023-11-28 03:36:10,762][87426] Updated weights for policy 1, policy_version 129270 (0.0010) -[2023-11-28 03:36:10,779][87424] Updated weights for policy 0, policy_version 129556 (0.0011) -[2023-11-28 03:36:11,134][87426] Updated weights for policy 1, policy_version 129280 (0.0011) -[2023-11-28 03:36:11,158][87424] Updated weights for policy 0, policy_version 129566 (0.0010) -[2023-11-28 03:36:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66265088. Throughput: 0: 2708.3, 1: 2762.7. Samples: 66284372. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:13,445][86177] Avg episode reward: [(0, '-492.630'), (1, '-498.590')] -[2023-11-28 03:36:13,567][87426] Updated weights for policy 1, policy_version 129290 (0.0011) -[2023-11-28 03:36:13,659][87424] Updated weights for policy 0, policy_version 129576 (0.0010) -[2023-11-28 03:36:13,932][87426] Updated weights for policy 1, policy_version 129300 (0.0011) -[2023-11-28 03:36:14,031][87424] Updated weights for policy 0, policy_version 129586 (0.0012) -[2023-11-28 03:36:14,303][87426] Updated weights for policy 1, policy_version 129310 (0.0010) -[2023-11-28 03:36:14,414][87424] Updated weights for policy 0, policy_version 129596 (0.0011) -[2023-11-28 03:36:16,461][87424] Updated weights for policy 0, policy_version 129606 (0.0010) -[2023-11-28 03:36:16,790][87426] Updated weights for policy 1, policy_version 129320 (0.0010) -[2023-11-28 03:36:16,848][87424] Updated weights for policy 0, policy_version 129616 (0.0010) -[2023-11-28 03:36:17,171][87426] Updated weights for policy 1, policy_version 129330 (0.0010) -[2023-11-28 03:36:17,227][87424] Updated weights for policy 0, policy_version 129626 (0.0011) -[2023-11-28 03:36:17,553][87426] Updated weights for policy 1, policy_version 129340 (0.0007) -[2023-11-28 03:36:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66297856. Throughput: 0: 2657.5, 1: 2762.5. Samples: 66308084. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:18,445][86177] Avg episode reward: [(0, '-492.510'), (1, '-535.330')] -[2023-11-28 03:36:18,452][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000129344_33112064.pth... -[2023-11-28 03:36:18,452][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000129632_33185792.pth... -[2023-11-28 03:36:18,483][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000126816_32464896.pth -[2023-11-28 03:36:18,490][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000127072_32530432.pth -[2023-11-28 03:36:19,314][87424] Updated weights for policy 0, policy_version 129636 (0.0011) -[2023-11-28 03:36:19,573][87426] Updated weights for policy 1, policy_version 129350 (0.0010) -[2023-11-28 03:36:19,706][87424] Updated weights for policy 0, policy_version 129646 (0.0009) -[2023-11-28 03:36:19,959][87426] Updated weights for policy 1, policy_version 129360 (0.0010) -[2023-11-28 03:36:20,080][87424] Updated weights for policy 0, policy_version 129656 (0.0011) -[2023-11-28 03:36:20,337][87426] Updated weights for policy 1, policy_version 129370 (0.0011) -[2023-11-28 03:36:22,596][87424] Updated weights for policy 0, policy_version 129666 (0.0011) -[2023-11-28 03:36:22,803][87426] Updated weights for policy 1, policy_version 129380 (0.0012) -[2023-11-28 03:36:22,974][87424] Updated weights for policy 0, policy_version 129676 (0.0011) -[2023-11-28 03:36:23,166][87426] Updated weights for policy 1, policy_version 129390 (0.0011) -[2023-11-28 03:36:23,355][87424] Updated weights for policy 0, policy_version 129686 (0.0012) -[2023-11-28 03:36:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 66314240. Throughput: 0: 2673.2, 1: 2717.4. Samples: 66339444. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:23,445][86177] Avg episode reward: [(0, '-493.800'), (1, '-534.280')] -[2023-11-28 03:36:23,545][87426] Updated weights for policy 1, policy_version 129400 (0.0009) -[2023-11-28 03:36:23,736][87424] Updated weights for policy 0, policy_version 129696 (0.0012) -[2023-11-28 03:36:25,291][87426] Updated weights for policy 1, policy_version 129410 (0.0008) -[2023-11-28 03:36:25,658][87426] Updated weights for policy 1, policy_version 129420 (0.0011) -[2023-11-28 03:36:25,912][87424] Updated weights for policy 0, policy_version 129706 (0.0012) -[2023-11-28 03:36:26,043][87426] Updated weights for policy 1, policy_version 129430 (0.0012) -[2023-11-28 03:36:26,282][87424] Updated weights for policy 0, policy_version 129716 (0.0012) -[2023-11-28 03:36:26,434][87426] Updated weights for policy 1, policy_version 129440 (0.0012) -[2023-11-28 03:36:26,661][87424] Updated weights for policy 0, policy_version 129726 (0.0008) -[2023-11-28 03:36:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66347008. Throughput: 0: 2683.1, 1: 2724.5. Samples: 66364592. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:28,445][86177] Avg episode reward: [(0, '-496.270'), (1, '-541.380')] -[2023-11-28 03:36:28,846][87426] Updated weights for policy 1, policy_version 129450 (0.0008) -[2023-11-28 03:36:29,203][87424] Updated weights for policy 0, policy_version 129736 (0.0011) -[2023-11-28 03:36:29,228][87426] Updated weights for policy 1, policy_version 129460 (0.0010) -[2023-11-28 03:36:29,590][87424] Updated weights for policy 0, policy_version 129746 (0.0012) -[2023-11-28 03:36:29,603][87426] Updated weights for policy 1, policy_version 129470 (0.0007) -[2023-11-28 03:36:29,969][87424] Updated weights for policy 0, policy_version 129756 (0.0012) -[2023-11-28 03:36:31,660][87426] Updated weights for policy 1, policy_version 129480 (0.0011) -[2023-11-28 03:36:31,815][87424] Updated weights for policy 0, policy_version 129766 (0.0011) -[2023-11-28 03:36:32,035][87426] Updated weights for policy 1, policy_version 129490 (0.0012) -[2023-11-28 03:36:32,197][87424] Updated weights for policy 0, policy_version 129776 (0.0009) -[2023-11-28 03:36:32,412][87426] Updated weights for policy 1, policy_version 129500 (0.0011) -[2023-11-28 03:36:32,580][87424] Updated weights for policy 0, policy_version 129786 (0.0011) -[2023-11-28 03:36:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 66379776. Throughput: 0: 2686.3, 1: 2741.8. Samples: 66388956. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:33,445][86177] Avg episode reward: [(0, '-496.480'), (1, '-503.490')] -[2023-11-28 03:36:34,367][87426] Updated weights for policy 1, policy_version 129510 (0.0011) -[2023-11-28 03:36:34,748][87426] Updated weights for policy 1, policy_version 129520 (0.0011) -[2023-11-28 03:36:34,984][87424] Updated weights for policy 0, policy_version 129796 (0.0011) -[2023-11-28 03:36:35,118][87426] Updated weights for policy 1, policy_version 129530 (0.0011) -[2023-11-28 03:36:35,375][87424] Updated weights for policy 0, policy_version 129806 (0.0010) -[2023-11-28 03:36:35,755][87424] Updated weights for policy 0, policy_version 129816 (0.0012) -[2023-11-28 03:36:36,887][87426] Updated weights for policy 1, policy_version 129540 (0.0011) -[2023-11-28 03:36:37,263][87426] Updated weights for policy 1, policy_version 129550 (0.0010) -[2023-11-28 03:36:37,520][87424] Updated weights for policy 0, policy_version 129826 (0.0011) -[2023-11-28 03:36:37,646][87426] Updated weights for policy 1, policy_version 129560 (0.0007) -[2023-11-28 03:36:37,899][87424] Updated weights for policy 0, policy_version 129836 (0.0012) -[2023-11-28 03:36:38,286][87424] Updated weights for policy 0, policy_version 129846 (0.0012) -[2023-11-28 03:36:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 66404352. Throughput: 0: 2691.3, 1: 2738.9. Samples: 66421832. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:38,446][86177] Avg episode reward: [(0, '-495.020'), (1, '-502.940')] -[2023-11-28 03:36:38,660][87424] Updated weights for policy 0, policy_version 129856 (0.0012) -[2023-11-28 03:36:39,644][87426] Updated weights for policy 1, policy_version 129570 (0.0009) -[2023-11-28 03:36:40,014][87426] Updated weights for policy 1, policy_version 129580 (0.0011) -[2023-11-28 03:36:40,386][87426] Updated weights for policy 1, policy_version 129590 (0.0011) -[2023-11-28 03:36:40,769][87426] Updated weights for policy 1, policy_version 129600 (0.0011) -[2023-11-28 03:36:40,951][87424] Updated weights for policy 0, policy_version 129866 (0.0012) -[2023-11-28 03:36:41,333][87424] Updated weights for policy 0, policy_version 129876 (0.0011) -[2023-11-28 03:36:41,712][87424] Updated weights for policy 0, policy_version 129886 (0.0012) -[2023-11-28 03:36:43,323][87426] Updated weights for policy 1, policy_version 129610 (0.0012) -[2023-11-28 03:36:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66428928. Throughput: 0: 2680.4, 1: 2727.8. Samples: 66445868. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:43,445][86177] Avg episode reward: [(0, '-492.080'), (1, '-502.920')] -[2023-11-28 03:36:43,703][87426] Updated weights for policy 1, policy_version 129620 (0.0011) -[2023-11-28 03:36:44,089][87426] Updated weights for policy 1, policy_version 129630 (0.0012) -[2023-11-28 03:36:44,303][87424] Updated weights for policy 0, policy_version 129896 (0.0012) -[2023-11-28 03:36:44,691][87424] Updated weights for policy 0, policy_version 129906 (0.0012) -[2023-11-28 03:36:45,066][87424] Updated weights for policy 0, policy_version 129916 (0.0011) -[2023-11-28 03:36:46,036][87426] Updated weights for policy 1, policy_version 129640 (0.0011) -[2023-11-28 03:36:46,411][87426] Updated weights for policy 1, policy_version 129650 (0.0012) -[2023-11-28 03:36:46,798][87426] Updated weights for policy 1, policy_version 129660 (0.0012) -[2023-11-28 03:36:47,162][87424] Updated weights for policy 0, policy_version 129926 (0.0012) -[2023-11-28 03:36:47,544][87424] Updated weights for policy 0, policy_version 129936 (0.0009) -[2023-11-28 03:36:47,943][87424] Updated weights for policy 0, policy_version 129946 (0.0007) -[2023-11-28 03:36:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 66461696. Throughput: 0: 2658.4, 1: 2725.9. Samples: 66470028. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:48,445][86177] Avg episode reward: [(0, '-488.020'), (1, '-492.300')] -[2023-11-28 03:36:48,456][87281] Saving new best policy, reward=-488.020! -[2023-11-28 03:36:49,207][87426] Updated weights for policy 1, policy_version 129670 (0.0009) -[2023-11-28 03:36:49,583][87426] Updated weights for policy 1, policy_version 129680 (0.0007) -[2023-11-28 03:36:49,963][87426] Updated weights for policy 1, policy_version 129690 (0.0009) -[2023-11-28 03:36:50,426][87424] Updated weights for policy 0, policy_version 129956 (0.0009) -[2023-11-28 03:36:50,802][87424] Updated weights for policy 0, policy_version 129966 (0.0008) -[2023-11-28 03:36:51,183][87424] Updated weights for policy 0, policy_version 129976 (0.0008) -[2023-11-28 03:36:52,234][87426] Updated weights for policy 1, policy_version 129700 (0.0010) -[2023-11-28 03:36:52,615][87426] Updated weights for policy 1, policy_version 129710 (0.0012) -[2023-11-28 03:36:52,989][87426] Updated weights for policy 1, policy_version 129720 (0.0012) -[2023-11-28 03:36:53,415][87424] Updated weights for policy 0, policy_version 129986 (0.0012) -[2023-11-28 03:36:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 66486272. Throughput: 0: 2676.4, 1: 2711.1. Samples: 66502304. Policy #0 lag: (min: 4.0, avg: 13.3, max: 36.0) -[2023-11-28 03:36:53,445][86177] Avg episode reward: [(0, '-489.040'), (1, '-492.030')] -[2023-11-28 03:36:53,803][87424] Updated weights for policy 0, policy_version 129996 (0.0012) -[2023-11-28 03:36:54,185][87424] Updated weights for policy 0, policy_version 130006 (0.0010) -[2023-11-28 03:36:54,576][87424] Updated weights for policy 0, policy_version 130016 (0.0010) -[2023-11-28 03:36:54,934][87426] Updated weights for policy 1, policy_version 129730 (0.0009) -[2023-11-28 03:36:55,320][87426] Updated weights for policy 1, policy_version 129740 (0.0012) -[2023-11-28 03:36:55,684][87426] Updated weights for policy 1, policy_version 129750 (0.0012) -[2023-11-28 03:36:56,073][87426] Updated weights for policy 1, policy_version 129760 (0.0012) -[2023-11-28 03:36:56,428][87424] Updated weights for policy 0, policy_version 130026 (0.0011) -[2023-11-28 03:36:56,809][87424] Updated weights for policy 0, policy_version 130036 (0.0011) -[2023-11-28 03:36:57,191][87424] Updated weights for policy 0, policy_version 130046 (0.0012) -[2023-11-28 03:36:57,921][87426] Updated weights for policy 1, policy_version 129770 (0.0007) -[2023-11-28 03:36:58,301][87426] Updated weights for policy 1, policy_version 129780 (0.0010) -[2023-11-28 03:36:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 66510848. Throughput: 0: 2688.7, 1: 2716.1. Samples: 66527588. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:36:58,445][86177] Avg episode reward: [(0, '-491.260'), (1, '-522.310')] -[2023-11-28 03:36:58,683][87426] Updated weights for policy 1, policy_version 129790 (0.0012) -[2023-11-28 03:36:58,776][87424] Updated weights for policy 0, policy_version 130056 (0.0011) -[2023-11-28 03:36:59,160][87424] Updated weights for policy 0, policy_version 130066 (0.0009) -[2023-11-28 03:36:59,543][87424] Updated weights for policy 0, policy_version 130076 (0.0008) -[2023-11-28 03:37:00,967][87426] Updated weights for policy 1, policy_version 129800 (0.0011) -[2023-11-28 03:37:01,351][87426] Updated weights for policy 1, policy_version 129810 (0.0012) -[2023-11-28 03:37:01,708][87424] Updated weights for policy 0, policy_version 130086 (0.0010) -[2023-11-28 03:37:01,754][87426] Updated weights for policy 1, policy_version 129820 (0.0012) -[2023-11-28 03:37:02,085][87424] Updated weights for policy 0, policy_version 130096 (0.0012) -[2023-11-28 03:37:02,472][87424] Updated weights for policy 0, policy_version 130106 (0.0012) -[2023-11-28 03:37:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 66543616. Throughput: 0: 2742.1, 1: 2706.0. Samples: 66553252. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:03,445][86177] Avg episode reward: [(0, '-502.940'), (1, '-520.230')] -[2023-11-28 03:37:03,791][87426] Updated weights for policy 1, policy_version 129830 (0.0011) -[2023-11-28 03:37:04,176][87426] Updated weights for policy 1, policy_version 129840 (0.0008) -[2023-11-28 03:37:04,504][87424] Updated weights for policy 0, policy_version 130116 (0.0012) -[2023-11-28 03:37:04,553][87426] Updated weights for policy 1, policy_version 129850 (0.0009) -[2023-11-28 03:37:04,885][87424] Updated weights for policy 0, policy_version 130126 (0.0011) -[2023-11-28 03:37:05,259][87424] Updated weights for policy 0, policy_version 130136 (0.0009) -[2023-11-28 03:37:06,567][87426] Updated weights for policy 1, policy_version 129860 (0.0011) -[2023-11-28 03:37:06,949][87426] Updated weights for policy 1, policy_version 129870 (0.0012) -[2023-11-28 03:37:07,335][87426] Updated weights for policy 1, policy_version 129880 (0.0012) -[2023-11-28 03:37:07,823][87424] Updated weights for policy 0, policy_version 130146 (0.0008) -[2023-11-28 03:37:08,214][87424] Updated weights for policy 0, policy_version 130156 (0.0011) -[2023-11-28 03:37:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 66568192. Throughput: 0: 2727.4, 1: 2754.7. Samples: 66586136. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:08,445][86177] Avg episode reward: [(0, '-515.950'), (1, '-526.150')] -[2023-11-28 03:37:08,584][87424] Updated weights for policy 0, policy_version 130166 (0.0010) -[2023-11-28 03:37:08,968][87424] Updated weights for policy 0, policy_version 130176 (0.0008) -[2023-11-28 03:37:09,710][87426] Updated weights for policy 1, policy_version 129890 (0.0009) -[2023-11-28 03:37:10,091][87426] Updated weights for policy 1, policy_version 129900 (0.0012) -[2023-11-28 03:37:10,466][87426] Updated weights for policy 1, policy_version 129910 (0.0012) -[2023-11-28 03:37:10,834][87426] Updated weights for policy 1, policy_version 129920 (0.0012) -[2023-11-28 03:37:11,080][87424] Updated weights for policy 0, policy_version 130186 (0.0012) -[2023-11-28 03:37:11,464][87424] Updated weights for policy 0, policy_version 130196 (0.0012) -[2023-11-28 03:37:11,862][87424] Updated weights for policy 0, policy_version 130206 (0.0009) -[2023-11-28 03:37:13,439][87426] Updated weights for policy 1, policy_version 129930 (0.0011) -[2023-11-28 03:37:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66592768. Throughput: 0: 2718.8, 1: 2725.3. Samples: 66609576. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:13,445][86177] Avg episode reward: [(0, '-516.740'), (1, '-551.980')] -[2023-11-28 03:37:13,814][87426] Updated weights for policy 1, policy_version 129940 (0.0012) -[2023-11-28 03:37:13,943][87424] Updated weights for policy 0, policy_version 130216 (0.0011) -[2023-11-28 03:37:14,197][87426] Updated weights for policy 1, policy_version 129950 (0.0011) -[2023-11-28 03:37:14,324][87424] Updated weights for policy 0, policy_version 130226 (0.0012) -[2023-11-28 03:37:14,707][87424] Updated weights for policy 0, policy_version 130236 (0.0011) -[2023-11-28 03:37:16,431][87426] Updated weights for policy 1, policy_version 129960 (0.0011) -[2023-11-28 03:37:16,823][87426] Updated weights for policy 1, policy_version 129970 (0.0012) -[2023-11-28 03:37:17,028][87424] Updated weights for policy 0, policy_version 130246 (0.0010) -[2023-11-28 03:37:17,194][87426] Updated weights for policy 1, policy_version 129980 (0.0010) -[2023-11-28 03:37:17,401][87424] Updated weights for policy 0, policy_version 130256 (0.0012) -[2023-11-28 03:37:17,781][87424] Updated weights for policy 0, policy_version 130266 (0.0012) -[2023-11-28 03:37:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 66625536. Throughput: 0: 2711.4, 1: 2721.6. Samples: 66633440. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:18,445][86177] Avg episode reward: [(0, '-516.750'), (1, '-523.200')] -[2023-11-28 03:37:19,543][87426] Updated weights for policy 1, policy_version 129990 (0.0008) -[2023-11-28 03:37:19,926][87426] Updated weights for policy 1, policy_version 130000 (0.0011) -[2023-11-28 03:37:19,944][87424] Updated weights for policy 0, policy_version 130276 (0.0011) -[2023-11-28 03:37:20,308][87426] Updated weights for policy 1, policy_version 130010 (0.0009) -[2023-11-28 03:37:20,330][87424] Updated weights for policy 0, policy_version 130286 (0.0011) -[2023-11-28 03:37:20,710][87424] Updated weights for policy 0, policy_version 130296 (0.0008) -[2023-11-28 03:37:22,185][87426] Updated weights for policy 1, policy_version 130020 (0.0011) -[2023-11-28 03:37:22,566][87426] Updated weights for policy 1, policy_version 130030 (0.0012) -[2023-11-28 03:37:22,691][87424] Updated weights for policy 0, policy_version 130306 (0.0008) -[2023-11-28 03:37:22,941][87426] Updated weights for policy 1, policy_version 130040 (0.0009) -[2023-11-28 03:37:23,070][87424] Updated weights for policy 0, policy_version 130316 (0.0009) -[2023-11-28 03:37:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 66650112. Throughput: 0: 2712.2, 1: 2728.5. Samples: 66666660. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:23,445][86177] Avg episode reward: [(0, '-509.020'), (1, '-528.070')] -[2023-11-28 03:37:23,457][87424] Updated weights for policy 0, policy_version 130326 (0.0010) -[2023-11-28 03:37:23,829][87424] Updated weights for policy 0, policy_version 130336 (0.0010) -[2023-11-28 03:37:24,995][87426] Updated weights for policy 1, policy_version 130050 (0.0010) -[2023-11-28 03:37:25,371][87426] Updated weights for policy 1, policy_version 130060 (0.0008) -[2023-11-28 03:37:25,759][87426] Updated weights for policy 1, policy_version 130070 (0.0008) -[2023-11-28 03:37:26,140][87426] Updated weights for policy 1, policy_version 130080 (0.0008) -[2023-11-28 03:37:26,332][87424] Updated weights for policy 0, policy_version 130346 (0.0010) -[2023-11-28 03:37:26,699][87424] Updated weights for policy 0, policy_version 130356 (0.0011) -[2023-11-28 03:37:27,095][87424] Updated weights for policy 0, policy_version 130366 (0.0011) -[2023-11-28 03:37:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66674688. Throughput: 0: 2703.4, 1: 2744.4. Samples: 66691020. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:28,445][86177] Avg episode reward: [(0, '-497.890'), (1, '-514.130')] -[2023-11-28 03:37:28,497][87426] Updated weights for policy 1, policy_version 130090 (0.0007) -[2023-11-28 03:37:28,878][87426] Updated weights for policy 1, policy_version 130100 (0.0008) -[2023-11-28 03:37:29,264][87426] Updated weights for policy 1, policy_version 130110 (0.0010) -[2023-11-28 03:37:29,567][87424] Updated weights for policy 0, policy_version 130376 (0.0011) -[2023-11-28 03:37:29,945][87424] Updated weights for policy 0, policy_version 130386 (0.0012) -[2023-11-28 03:37:30,321][87424] Updated weights for policy 0, policy_version 130396 (0.0012) -[2023-11-28 03:37:31,502][87426] Updated weights for policy 1, policy_version 130120 (0.0010) -[2023-11-28 03:37:31,885][87426] Updated weights for policy 1, policy_version 130130 (0.0008) -[2023-11-28 03:37:32,271][87426] Updated weights for policy 1, policy_version 130140 (0.0012) -[2023-11-28 03:37:32,506][87424] Updated weights for policy 0, policy_version 130406 (0.0012) -[2023-11-28 03:37:32,879][87424] Updated weights for policy 0, policy_version 130416 (0.0012) -[2023-11-28 03:37:33,262][87424] Updated weights for policy 0, policy_version 130426 (0.0012) -[2023-11-28 03:37:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 66699264. Throughput: 0: 2687.6, 1: 2744.2. Samples: 66714460. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:33,445][86177] Avg episode reward: [(0, '-499.090'), (1, '-501.220')] -[2023-11-28 03:37:34,260][87426] Updated weights for policy 1, policy_version 130150 (0.0010) -[2023-11-28 03:37:34,638][87426] Updated weights for policy 1, policy_version 130160 (0.0010) -[2023-11-28 03:37:35,030][87426] Updated weights for policy 1, policy_version 130170 (0.0012) -[2023-11-28 03:37:35,685][87424] Updated weights for policy 0, policy_version 130436 (0.0010) -[2023-11-28 03:37:36,071][87424] Updated weights for policy 0, policy_version 130446 (0.0007) -[2023-11-28 03:37:36,454][87424] Updated weights for policy 0, policy_version 130456 (0.0008) -[2023-11-28 03:37:37,168][87426] Updated weights for policy 1, policy_version 130180 (0.0010) -[2023-11-28 03:37:37,559][87426] Updated weights for policy 1, policy_version 130190 (0.0007) -[2023-11-28 03:37:37,930][87426] Updated weights for policy 1, policy_version 130200 (0.0007) -[2023-11-28 03:37:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 66732032. Throughput: 0: 2692.4, 1: 2751.8. Samples: 66747296. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:38,446][86177] Avg episode reward: [(0, '-497.530'), (1, '-518.050')] -[2023-11-28 03:37:38,830][87424] Updated weights for policy 0, policy_version 130466 (0.0010) -[2023-11-28 03:37:39,210][87424] Updated weights for policy 0, policy_version 130476 (0.0012) -[2023-11-28 03:37:39,587][87424] Updated weights for policy 0, policy_version 130486 (0.0012) -[2023-11-28 03:37:39,956][87424] Updated weights for policy 0, policy_version 130496 (0.0012) -[2023-11-28 03:37:40,141][87426] Updated weights for policy 1, policy_version 130210 (0.0008) -[2023-11-28 03:37:40,524][87426] Updated weights for policy 1, policy_version 130220 (0.0012) -[2023-11-28 03:37:40,898][87426] Updated weights for policy 1, policy_version 130230 (0.0011) -[2023-11-28 03:37:41,271][87426] Updated weights for policy 1, policy_version 130240 (0.0011) -[2023-11-28 03:37:42,259][87424] Updated weights for policy 0, policy_version 130506 (0.0012) -[2023-11-28 03:37:42,643][87424] Updated weights for policy 0, policy_version 130516 (0.0012) -[2023-11-28 03:37:43,018][87424] Updated weights for policy 0, policy_version 130526 (0.0013) -[2023-11-28 03:37:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66756608. Throughput: 0: 2668.5, 1: 2734.5. Samples: 66770724. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:43,445][86177] Avg episode reward: [(0, '-494.290'), (1, '-505.090')] -[2023-11-28 03:37:43,591][87426] Updated weights for policy 1, policy_version 130250 (0.0012) -[2023-11-28 03:37:43,980][87426] Updated weights for policy 1, policy_version 130260 (0.0012) -[2023-11-28 03:37:44,362][87426] Updated weights for policy 1, policy_version 130270 (0.0012) -[2023-11-28 03:37:45,045][87424] Updated weights for policy 0, policy_version 130536 (0.0012) -[2023-11-28 03:37:45,440][87424] Updated weights for policy 0, policy_version 130546 (0.0010) -[2023-11-28 03:37:45,830][87424] Updated weights for policy 0, policy_version 130556 (0.0009) -[2023-11-28 03:37:46,887][87426] Updated weights for policy 1, policy_version 130280 (0.0010) -[2023-11-28 03:37:47,259][87426] Updated weights for policy 1, policy_version 130290 (0.0009) -[2023-11-28 03:37:47,636][87426] Updated weights for policy 1, policy_version 130300 (0.0007) -[2023-11-28 03:37:48,156][87424] Updated weights for policy 0, policy_version 130566 (0.0009) -[2023-11-28 03:37:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.9). Total num frames: 66781184. Throughput: 0: 2640.5, 1: 2729.8. Samples: 66794916. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:48,445][86177] Avg episode reward: [(0, '-491.670'), (1, '-504.940')] -[2023-11-28 03:37:48,537][87424] Updated weights for policy 0, policy_version 130576 (0.0008) -[2023-11-28 03:37:48,931][87424] Updated weights for policy 0, policy_version 130586 (0.0012) -[2023-11-28 03:37:49,605][87426] Updated weights for policy 1, policy_version 130310 (0.0007) -[2023-11-28 03:37:49,983][87426] Updated weights for policy 1, policy_version 130320 (0.0009) -[2023-11-28 03:37:50,363][87426] Updated weights for policy 1, policy_version 130330 (0.0009) -[2023-11-28 03:37:50,700][87424] Updated weights for policy 0, policy_version 130596 (0.0010) -[2023-11-28 03:37:51,079][87424] Updated weights for policy 0, policy_version 130606 (0.0008) -[2023-11-28 03:37:51,466][87424] Updated weights for policy 0, policy_version 130616 (0.0009) -[2023-11-28 03:37:52,268][87426] Updated weights for policy 1, policy_version 130340 (0.0011) -[2023-11-28 03:37:52,642][87426] Updated weights for policy 1, policy_version 130350 (0.0010) -[2023-11-28 03:37:53,020][87426] Updated weights for policy 1, policy_version 130360 (0.0011) -[2023-11-28 03:37:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 66813952. Throughput: 0: 2657.9, 1: 2702.1. Samples: 66827336. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:53,445][86177] Avg episode reward: [(0, '-492.350'), (1, '-511.320')] -[2023-11-28 03:37:53,868][87424] Updated weights for policy 0, policy_version 130626 (0.0011) -[2023-11-28 03:37:54,253][87424] Updated weights for policy 0, policy_version 130636 (0.0007) -[2023-11-28 03:37:54,644][87424] Updated weights for policy 0, policy_version 130646 (0.0008) -[2023-11-28 03:37:55,016][87424] Updated weights for policy 0, policy_version 130656 (0.0007) -[2023-11-28 03:37:55,566][87426] Updated weights for policy 1, policy_version 130370 (0.0011) -[2023-11-28 03:37:55,954][87426] Updated weights for policy 1, policy_version 130380 (0.0007) -[2023-11-28 03:37:56,335][87426] Updated weights for policy 1, policy_version 130390 (0.0007) -[2023-11-28 03:37:56,710][87426] Updated weights for policy 1, policy_version 130400 (0.0008) -[2023-11-28 03:37:57,351][87424] Updated weights for policy 0, policy_version 130666 (0.0008) -[2023-11-28 03:37:57,731][87424] Updated weights for policy 0, policy_version 130676 (0.0008) -[2023-11-28 03:37:58,117][87424] Updated weights for policy 0, policy_version 130686 (0.0007) -[2023-11-28 03:37:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 66838528. Throughput: 0: 2665.5, 1: 2705.6. Samples: 66851276. Policy #0 lag: (min: 31.0, avg: 36.3, max: 63.0) -[2023-11-28 03:37:58,445][86177] Avg episode reward: [(0, '-496.390'), (1, '-494.890')] -[2023-11-28 03:37:59,220][87426] Updated weights for policy 1, policy_version 130410 (0.0009) -[2023-11-28 03:37:59,595][87426] Updated weights for policy 1, policy_version 130420 (0.0011) -[2023-11-28 03:37:59,769][87424] Updated weights for policy 0, policy_version 130696 (0.0010) -[2023-11-28 03:37:59,962][87426] Updated weights for policy 1, policy_version 130430 (0.0011) -[2023-11-28 03:38:00,149][87424] Updated weights for policy 0, policy_version 130706 (0.0009) -[2023-11-28 03:38:00,531][87424] Updated weights for policy 0, policy_version 130716 (0.0009) -[2023-11-28 03:38:02,096][87426] Updated weights for policy 1, policy_version 130440 (0.0012) -[2023-11-28 03:38:02,475][87426] Updated weights for policy 1, policy_version 130450 (0.0012) -[2023-11-28 03:38:02,857][87426] Updated weights for policy 1, policy_version 130460 (0.0012) -[2023-11-28 03:38:02,901][87424] Updated weights for policy 0, policy_version 130726 (0.0011) -[2023-11-28 03:38:03,287][87424] Updated weights for policy 0, policy_version 130736 (0.0012) -[2023-11-28 03:38:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 66863104. Throughput: 0: 2692.7, 1: 2699.8. Samples: 66876104. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:03,445][86177] Avg episode reward: [(0, '-498.220'), (1, '-502.370')] -[2023-11-28 03:38:03,673][87424] Updated weights for policy 0, policy_version 130746 (0.0011) -[2023-11-28 03:38:05,254][87426] Updated weights for policy 1, policy_version 130470 (0.0011) -[2023-11-28 03:38:05,595][87424] Updated weights for policy 0, policy_version 130756 (0.0011) -[2023-11-28 03:38:05,621][87426] Updated weights for policy 1, policy_version 130480 (0.0011) -[2023-11-28 03:38:05,984][87424] Updated weights for policy 0, policy_version 130766 (0.0011) -[2023-11-28 03:38:06,006][87426] Updated weights for policy 1, policy_version 130490 (0.0012) -[2023-11-28 03:38:06,357][87424] Updated weights for policy 0, policy_version 130776 (0.0012) -[2023-11-28 03:38:08,337][87424] Updated weights for policy 0, policy_version 130786 (0.0012) -[2023-11-28 03:38:08,436][87426] Updated weights for policy 1, policy_version 130500 (0.0011) -[2023-11-28 03:38:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 66887680. Throughput: 0: 2703.3, 1: 2685.0. Samples: 66909132. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:08,445][86177] Avg episode reward: [(0, '-502.140'), (1, '-509.470')] -[2023-11-28 03:38:08,722][87424] Updated weights for policy 0, policy_version 130796 (0.0011) -[2023-11-28 03:38:08,816][87426] Updated weights for policy 1, policy_version 130510 (0.0011) -[2023-11-28 03:38:09,101][87424] Updated weights for policy 0, policy_version 130806 (0.0012) -[2023-11-28 03:38:09,188][87426] Updated weights for policy 1, policy_version 130520 (0.0012) -[2023-11-28 03:38:09,480][87424] Updated weights for policy 0, policy_version 130816 (0.0012) -[2023-11-28 03:38:11,530][87424] Updated weights for policy 0, policy_version 130826 (0.0009) -[2023-11-28 03:38:11,629][87426] Updated weights for policy 1, policy_version 130530 (0.0008) -[2023-11-28 03:38:11,922][87424] Updated weights for policy 0, policy_version 130836 (0.0011) -[2023-11-28 03:38:12,009][87426] Updated weights for policy 1, policy_version 130540 (0.0011) -[2023-11-28 03:38:12,301][87424] Updated weights for policy 0, policy_version 130846 (0.0011) -[2023-11-28 03:38:12,389][87426] Updated weights for policy 1, policy_version 130550 (0.0009) -[2023-11-28 03:38:12,762][87426] Updated weights for policy 1, policy_version 130560 (0.0010) -[2023-11-28 03:38:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 66920448. Throughput: 0: 2729.1, 1: 2655.9. Samples: 66933344. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:13,445][86177] Avg episode reward: [(0, '-503.250'), (1, '-504.130')] -[2023-11-28 03:38:14,804][87424] Updated weights for policy 0, policy_version 130856 (0.0008) -[2023-11-28 03:38:14,860][87426] Updated weights for policy 1, policy_version 130570 (0.0012) -[2023-11-28 03:38:15,180][87424] Updated weights for policy 0, policy_version 130866 (0.0008) -[2023-11-28 03:38:15,240][87426] Updated weights for policy 1, policy_version 130580 (0.0012) -[2023-11-28 03:38:15,563][87424] Updated weights for policy 0, policy_version 130876 (0.0011) -[2023-11-28 03:38:15,618][87426] Updated weights for policy 1, policy_version 130590 (0.0012) -[2023-11-28 03:38:17,314][87426] Updated weights for policy 1, policy_version 130600 (0.0008) -[2023-11-28 03:38:17,694][87426] Updated weights for policy 1, policy_version 130610 (0.0008) -[2023-11-28 03:38:17,766][87424] Updated weights for policy 0, policy_version 130886 (0.0011) -[2023-11-28 03:38:18,071][87426] Updated weights for policy 1, policy_version 130620 (0.0011) -[2023-11-28 03:38:18,151][87424] Updated weights for policy 0, policy_version 130896 (0.0012) -[2023-11-28 03:38:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 66945024. Throughput: 0: 2728.5, 1: 2666.6. Samples: 66957240. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:18,445][86177] Avg episode reward: [(0, '-503.930'), (1, '-515.140')] -[2023-11-28 03:38:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000130624_33439744.pth... -[2023-11-28 03:38:18,484][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000128096_32792576.pth -[2023-11-28 03:38:18,534][87424] Updated weights for policy 0, policy_version 130906 (0.0012) -[2023-11-28 03:38:18,758][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000130912_33513472.pth... -[2023-11-28 03:38:18,790][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000128352_32858112.pth -[2023-11-28 03:38:20,479][87426] Updated weights for policy 1, policy_version 130630 (0.0011) -[2023-11-28 03:38:20,851][87426] Updated weights for policy 1, policy_version 130640 (0.0011) -[2023-11-28 03:38:20,964][87424] Updated weights for policy 0, policy_version 130916 (0.0009) -[2023-11-28 03:38:21,231][87426] Updated weights for policy 1, policy_version 130650 (0.0010) -[2023-11-28 03:38:21,344][87424] Updated weights for policy 0, policy_version 130926 (0.0010) -[2023-11-28 03:38:21,728][87424] Updated weights for policy 0, policy_version 130936 (0.0009) -[2023-11-28 03:38:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 66969600. Throughput: 0: 2726.9, 1: 2652.9. Samples: 66989384. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:23,445][86177] Avg episode reward: [(0, '-505.110'), (1, '-506.720')] -[2023-11-28 03:38:23,465][87426] Updated weights for policy 1, policy_version 130660 (0.0012) -[2023-11-28 03:38:23,829][87426] Updated weights for policy 1, policy_version 130670 (0.0012) -[2023-11-28 03:38:23,910][87424] Updated weights for policy 0, policy_version 130946 (0.0009) -[2023-11-28 03:38:24,215][87426] Updated weights for policy 1, policy_version 130680 (0.0011) -[2023-11-28 03:38:24,291][87424] Updated weights for policy 0, policy_version 130956 (0.0010) -[2023-11-28 03:38:24,681][87424] Updated weights for policy 0, policy_version 130966 (0.0008) -[2023-11-28 03:38:25,058][87424] Updated weights for policy 0, policy_version 130976 (0.0012) -[2023-11-28 03:38:26,102][87426] Updated weights for policy 1, policy_version 130690 (0.0011) -[2023-11-28 03:38:26,471][87426] Updated weights for policy 1, policy_version 130700 (0.0008) -[2023-11-28 03:38:26,811][87424] Updated weights for policy 0, policy_version 130986 (0.0011) -[2023-11-28 03:38:26,852][87426] Updated weights for policy 1, policy_version 130710 (0.0007) -[2023-11-28 03:38:27,192][87424] Updated weights for policy 0, policy_version 130996 (0.0009) -[2023-11-28 03:38:27,235][87426] Updated weights for policy 1, policy_version 130720 (0.0007) -[2023-11-28 03:38:27,573][87424] Updated weights for policy 0, policy_version 131006 (0.0009) -[2023-11-28 03:38:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 67002368. Throughput: 0: 2752.9, 1: 2667.3. Samples: 67014632. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:28,445][86177] Avg episode reward: [(0, '-500.150'), (1, '-498.880')] -[2023-11-28 03:38:29,321][87424] Updated weights for policy 0, policy_version 131016 (0.0011) -[2023-11-28 03:38:29,621][87426] Updated weights for policy 1, policy_version 130730 (0.0011) -[2023-11-28 03:38:29,702][87424] Updated weights for policy 0, policy_version 131026 (0.0011) -[2023-11-28 03:38:30,001][87426] Updated weights for policy 1, policy_version 130740 (0.0011) -[2023-11-28 03:38:30,093][87424] Updated weights for policy 0, policy_version 131036 (0.0008) -[2023-11-28 03:38:30,383][87426] Updated weights for policy 1, policy_version 130750 (0.0011) -[2023-11-28 03:38:32,176][87426] Updated weights for policy 1, policy_version 130760 (0.0010) -[2023-11-28 03:38:32,348][87424] Updated weights for policy 0, policy_version 131046 (0.0009) -[2023-11-28 03:38:32,541][87426] Updated weights for policy 1, policy_version 130770 (0.0008) -[2023-11-28 03:38:32,734][87424] Updated weights for policy 0, policy_version 131056 (0.0010) -[2023-11-28 03:38:32,932][87426] Updated weights for policy 1, policy_version 130780 (0.0008) -[2023-11-28 03:38:33,118][87424] Updated weights for policy 0, policy_version 131066 (0.0012) -[2023-11-28 03:38:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 67035136. Throughput: 0: 2768.4, 1: 2692.0. Samples: 67040632. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:33,445][86177] Avg episode reward: [(0, '-499.040'), (1, '-528.300')] -[2023-11-28 03:38:35,277][87426] Updated weights for policy 1, policy_version 130790 (0.0009) -[2023-11-28 03:38:35,650][87426] Updated weights for policy 1, policy_version 130800 (0.0011) -[2023-11-28 03:38:35,650][87424] Updated weights for policy 0, policy_version 131076 (0.0012) -[2023-11-28 03:38:36,020][87426] Updated weights for policy 1, policy_version 130810 (0.0008) -[2023-11-28 03:38:36,025][87424] Updated weights for policy 0, policy_version 131086 (0.0010) -[2023-11-28 03:38:36,408][87424] Updated weights for policy 0, policy_version 131096 (0.0008) -[2023-11-28 03:38:38,183][87426] Updated weights for policy 1, policy_version 130820 (0.0007) -[2023-11-28 03:38:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 67051520. Throughput: 0: 2756.0, 1: 2705.0. Samples: 67073080. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:38,445][86177] Avg episode reward: [(0, '-538.390'), (1, '-534.180')] -[2023-11-28 03:38:38,561][87426] Updated weights for policy 1, policy_version 130830 (0.0008) -[2023-11-28 03:38:38,731][87424] Updated weights for policy 0, policy_version 131106 (0.0009) -[2023-11-28 03:38:38,937][87426] Updated weights for policy 1, policy_version 130840 (0.0009) -[2023-11-28 03:38:39,119][87424] Updated weights for policy 0, policy_version 131116 (0.0010) -[2023-11-28 03:38:39,498][87424] Updated weights for policy 0, policy_version 131126 (0.0009) -[2023-11-28 03:38:39,880][87424] Updated weights for policy 0, policy_version 131136 (0.0008) -[2023-11-28 03:38:40,965][87426] Updated weights for policy 1, policy_version 130850 (0.0011) -[2023-11-28 03:38:41,340][87426] Updated weights for policy 1, policy_version 130860 (0.0008) -[2023-11-28 03:38:41,722][87426] Updated weights for policy 1, policy_version 130870 (0.0009) -[2023-11-28 03:38:42,103][87426] Updated weights for policy 1, policy_version 130880 (0.0012) -[2023-11-28 03:38:42,187][87424] Updated weights for policy 0, policy_version 131146 (0.0012) -[2023-11-28 03:38:42,563][87424] Updated weights for policy 0, policy_version 131156 (0.0012) -[2023-11-28 03:38:42,946][87424] Updated weights for policy 0, policy_version 131166 (0.0012) -[2023-11-28 03:38:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 67084288. Throughput: 0: 2749.6, 1: 2712.6. Samples: 67097076. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:43,446][86177] Avg episode reward: [(0, '-538.440'), (1, '-542.910')] -[2023-11-28 03:38:44,530][87426] Updated weights for policy 1, policy_version 130890 (0.0012) -[2023-11-28 03:38:44,836][87424] Updated weights for policy 0, policy_version 131176 (0.0012) -[2023-11-28 03:38:44,908][87426] Updated weights for policy 1, policy_version 130900 (0.0011) -[2023-11-28 03:38:45,221][87424] Updated weights for policy 0, policy_version 131186 (0.0011) -[2023-11-28 03:38:45,301][87426] Updated weights for policy 1, policy_version 130910 (0.0011) -[2023-11-28 03:38:45,597][87424] Updated weights for policy 0, policy_version 131196 (0.0012) -[2023-11-28 03:38:47,314][87426] Updated weights for policy 1, policy_version 130920 (0.0008) -[2023-11-28 03:38:47,690][87426] Updated weights for policy 1, policy_version 130930 (0.0010) -[2023-11-28 03:38:47,997][87424] Updated weights for policy 0, policy_version 131206 (0.0012) -[2023-11-28 03:38:48,068][87426] Updated weights for policy 1, policy_version 130940 (0.0011) -[2023-11-28 03:38:48,373][87424] Updated weights for policy 0, policy_version 131216 (0.0012) -[2023-11-28 03:38:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67108864. Throughput: 0: 2736.3, 1: 2728.9. Samples: 67122036. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:48,445][86177] Avg episode reward: [(0, '-535.520'), (1, '-556.200')] -[2023-11-28 03:38:48,756][87424] Updated weights for policy 0, policy_version 131226 (0.0009) -[2023-11-28 03:38:50,396][87426] Updated weights for policy 1, policy_version 130950 (0.0012) -[2023-11-28 03:38:50,776][87426] Updated weights for policy 1, policy_version 130960 (0.0012) -[2023-11-28 03:38:51,050][87424] Updated weights for policy 0, policy_version 131236 (0.0008) -[2023-11-28 03:38:51,165][87426] Updated weights for policy 1, policy_version 130970 (0.0009) -[2023-11-28 03:38:51,427][87424] Updated weights for policy 0, policy_version 131246 (0.0011) -[2023-11-28 03:38:51,813][87424] Updated weights for policy 0, policy_version 131256 (0.0012) -[2023-11-28 03:38:53,327][87426] Updated weights for policy 1, policy_version 130980 (0.0011) -[2023-11-28 03:38:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 67133440. Throughput: 0: 2711.0, 1: 2728.1. Samples: 67153892. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:53,445][86177] Avg episode reward: [(0, '-495.620'), (1, '-531.830')] -[2023-11-28 03:38:53,708][87426] Updated weights for policy 1, policy_version 130990 (0.0009) -[2023-11-28 03:38:53,940][87424] Updated weights for policy 0, policy_version 131266 (0.0011) -[2023-11-28 03:38:54,099][87426] Updated weights for policy 1, policy_version 131000 (0.0010) -[2023-11-28 03:38:54,335][87424] Updated weights for policy 0, policy_version 131276 (0.0012) -[2023-11-28 03:38:54,714][87424] Updated weights for policy 0, policy_version 131286 (0.0012) -[2023-11-28 03:38:55,106][87424] Updated weights for policy 0, policy_version 131296 (0.0012) -[2023-11-28 03:38:56,291][87426] Updated weights for policy 1, policy_version 131010 (0.0011) -[2023-11-28 03:38:56,673][87426] Updated weights for policy 1, policy_version 131020 (0.0012) -[2023-11-28 03:38:57,046][87426] Updated weights for policy 1, policy_version 131030 (0.0011) -[2023-11-28 03:38:57,394][87424] Updated weights for policy 0, policy_version 131306 (0.0010) -[2023-11-28 03:38:57,422][87426] Updated weights for policy 1, policy_version 131040 (0.0012) -[2023-11-28 03:38:57,768][87424] Updated weights for policy 0, policy_version 131316 (0.0012) -[2023-11-28 03:38:58,141][87424] Updated weights for policy 0, policy_version 131326 (0.0012) -[2023-11-28 03:38:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 67166208. Throughput: 0: 2700.5, 1: 2745.3. Samples: 67178408. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:38:58,445][86177] Avg episode reward: [(0, '-495.270'), (1, '-516.480')] -[2023-11-28 03:38:59,581][87426] Updated weights for policy 1, policy_version 131050 (0.0010) -[2023-11-28 03:38:59,894][87424] Updated weights for policy 0, policy_version 131336 (0.0011) -[2023-11-28 03:38:59,952][87426] Updated weights for policy 1, policy_version 131060 (0.0010) -[2023-11-28 03:39:00,269][87424] Updated weights for policy 0, policy_version 131346 (0.0009) -[2023-11-28 03:39:00,330][87426] Updated weights for policy 1, policy_version 131070 (0.0007) -[2023-11-28 03:39:00,646][87424] Updated weights for policy 0, policy_version 131356 (0.0011) -[2023-11-28 03:39:02,406][87426] Updated weights for policy 1, policy_version 131080 (0.0010) -[2023-11-28 03:39:02,780][87426] Updated weights for policy 1, policy_version 131090 (0.0012) -[2023-11-28 03:39:02,994][87424] Updated weights for policy 0, policy_version 131366 (0.0012) -[2023-11-28 03:39:03,152][87426] Updated weights for policy 1, policy_version 131100 (0.0012) -[2023-11-28 03:39:03,368][87424] Updated weights for policy 0, policy_version 131376 (0.0011) -[2023-11-28 03:39:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 67190784. Throughput: 0: 2741.1, 1: 2743.6. Samples: 67204052. Policy #0 lag: (min: 31.0, avg: 50.9, max: 63.0) -[2023-11-28 03:39:03,446][86177] Avg episode reward: [(0, '-496.350'), (1, '-518.980')] -[2023-11-28 03:39:03,756][87424] Updated weights for policy 0, policy_version 131386 (0.0010) -[2023-11-28 03:39:05,018][87426] Updated weights for policy 1, policy_version 131110 (0.0012) -[2023-11-28 03:39:05,399][87426] Updated weights for policy 1, policy_version 131120 (0.0012) -[2023-11-28 03:39:05,783][87426] Updated weights for policy 1, policy_version 131130 (0.0012) -[2023-11-28 03:39:06,235][87424] Updated weights for policy 0, policy_version 131396 (0.0007) -[2023-11-28 03:39:06,612][87424] Updated weights for policy 0, policy_version 131406 (0.0009) -[2023-11-28 03:39:06,993][87424] Updated weights for policy 0, policy_version 131416 (0.0010) -[2023-11-28 03:39:07,623][87426] Updated weights for policy 1, policy_version 131140 (0.0012) -[2023-11-28 03:39:08,007][87426] Updated weights for policy 1, policy_version 131150 (0.0011) -[2023-11-28 03:39:08,384][87426] Updated weights for policy 1, policy_version 131160 (0.0008) -[2023-11-28 03:39:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 67215360. Throughput: 0: 2742.8, 1: 2761.8. Samples: 67237088. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:08,445][86177] Avg episode reward: [(0, '-498.040'), (1, '-511.300')] -[2023-11-28 03:39:08,936][87424] Updated weights for policy 0, policy_version 131426 (0.0011) -[2023-11-28 03:39:09,324][87424] Updated weights for policy 0, policy_version 131436 (0.0012) -[2023-11-28 03:39:09,694][87424] Updated weights for policy 0, policy_version 131446 (0.0012) -[2023-11-28 03:39:10,076][87424] Updated weights for policy 0, policy_version 131456 (0.0012) -[2023-11-28 03:39:10,587][87426] Updated weights for policy 1, policy_version 131170 (0.0008) -[2023-11-28 03:39:10,965][87426] Updated weights for policy 1, policy_version 131180 (0.0012) -[2023-11-28 03:39:11,334][87426] Updated weights for policy 1, policy_version 131190 (0.0009) -[2023-11-28 03:39:11,713][87426] Updated weights for policy 1, policy_version 131200 (0.0009) -[2023-11-28 03:39:11,791][87424] Updated weights for policy 0, policy_version 131466 (0.0011) -[2023-11-28 03:39:12,182][87424] Updated weights for policy 0, policy_version 131476 (0.0012) -[2023-11-28 03:39:12,558][87424] Updated weights for policy 0, policy_version 131486 (0.0012) -[2023-11-28 03:39:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 67248128. Throughput: 0: 2740.1, 1: 2740.0. Samples: 67261236. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:13,445][86177] Avg episode reward: [(0, '-499.260'), (1, '-512.080')] -[2023-11-28 03:39:13,841][87426] Updated weights for policy 1, policy_version 131210 (0.0008) -[2023-11-28 03:39:14,221][87426] Updated weights for policy 1, policy_version 131220 (0.0007) -[2023-11-28 03:39:14,604][87426] Updated weights for policy 1, policy_version 131230 (0.0007) -[2023-11-28 03:39:14,686][87424] Updated weights for policy 0, policy_version 131496 (0.0009) -[2023-11-28 03:39:15,072][87424] Updated weights for policy 0, policy_version 131506 (0.0007) -[2023-11-28 03:39:15,461][87424] Updated weights for policy 0, policy_version 131516 (0.0009) -[2023-11-28 03:39:17,006][87426] Updated weights for policy 1, policy_version 131240 (0.0011) -[2023-11-28 03:39:17,375][87426] Updated weights for policy 1, policy_version 131250 (0.0011) -[2023-11-28 03:39:17,514][87424] Updated weights for policy 0, policy_version 131526 (0.0008) -[2023-11-28 03:39:17,751][87426] Updated weights for policy 1, policy_version 131260 (0.0010) -[2023-11-28 03:39:17,904][87424] Updated weights for policy 0, policy_version 131536 (0.0007) -[2023-11-28 03:39:18,284][87424] Updated weights for policy 0, policy_version 131546 (0.0008) -[2023-11-28 03:39:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67272704. Throughput: 0: 2721.8, 1: 2740.4. Samples: 67286428. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:18,445][86177] Avg episode reward: [(0, '-497.330'), (1, '-512.700')] -[2023-11-28 03:39:20,029][87426] Updated weights for policy 1, policy_version 131270 (0.0010) -[2023-11-28 03:39:20,405][87426] Updated weights for policy 1, policy_version 131280 (0.0011) -[2023-11-28 03:39:20,421][87424] Updated weights for policy 0, policy_version 131556 (0.0012) -[2023-11-28 03:39:20,781][87426] Updated weights for policy 1, policy_version 131290 (0.0011) -[2023-11-28 03:39:20,798][87424] Updated weights for policy 0, policy_version 131566 (0.0012) -[2023-11-28 03:39:21,186][87424] Updated weights for policy 0, policy_version 131576 (0.0011) -[2023-11-28 03:39:23,126][87424] Updated weights for policy 0, policy_version 131586 (0.0009) -[2023-11-28 03:39:23,178][87426] Updated weights for policy 1, policy_version 131300 (0.0011) -[2023-11-28 03:39:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 67297280. Throughput: 0: 2736.4, 1: 2727.4. Samples: 67318948. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:23,445][86177] Avg episode reward: [(0, '-498.130'), (1, '-507.790')] -[2023-11-28 03:39:23,497][87424] Updated weights for policy 0, policy_version 131596 (0.0007) -[2023-11-28 03:39:23,559][87426] Updated weights for policy 1, policy_version 131310 (0.0012) -[2023-11-28 03:39:23,885][87424] Updated weights for policy 0, policy_version 131606 (0.0008) -[2023-11-28 03:39:23,933][87426] Updated weights for policy 1, policy_version 131320 (0.0012) -[2023-11-28 03:39:24,269][87424] Updated weights for policy 0, policy_version 131616 (0.0009) -[2023-11-28 03:39:25,730][87426] Updated weights for policy 1, policy_version 131330 (0.0010) -[2023-11-28 03:39:26,102][87426] Updated weights for policy 1, policy_version 131340 (0.0012) -[2023-11-28 03:39:26,481][87426] Updated weights for policy 1, policy_version 131350 (0.0011) -[2023-11-28 03:39:26,686][87424] Updated weights for policy 0, policy_version 131626 (0.0010) -[2023-11-28 03:39:26,853][87426] Updated weights for policy 1, policy_version 131360 (0.0011) -[2023-11-28 03:39:27,070][87424] Updated weights for policy 0, policy_version 131636 (0.0007) -[2023-11-28 03:39:27,450][87424] Updated weights for policy 0, policy_version 131646 (0.0010) -[2023-11-28 03:39:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67330048. Throughput: 0: 2730.8, 1: 2772.8. Samples: 67344736. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:28,445][86177] Avg episode reward: [(0, '-495.890'), (1, '-502.400')] -[2023-11-28 03:39:28,862][87426] Updated weights for policy 1, policy_version 131370 (0.0008) -[2023-11-28 03:39:29,233][87426] Updated weights for policy 1, policy_version 131380 (0.0010) -[2023-11-28 03:39:29,612][87426] Updated weights for policy 1, policy_version 131390 (0.0007) -[2023-11-28 03:39:29,709][87424] Updated weights for policy 0, policy_version 131656 (0.0011) -[2023-11-28 03:39:30,086][87424] Updated weights for policy 0, policy_version 131666 (0.0011) -[2023-11-28 03:39:30,465][87424] Updated weights for policy 0, policy_version 131676 (0.0011) -[2023-11-28 03:39:31,695][87426] Updated weights for policy 1, policy_version 131400 (0.0009) -[2023-11-28 03:39:32,077][87426] Updated weights for policy 1, policy_version 131410 (0.0010) -[2023-11-28 03:39:32,458][87426] Updated weights for policy 1, policy_version 131420 (0.0008) -[2023-11-28 03:39:32,870][87424] Updated weights for policy 0, policy_version 131686 (0.0009) -[2023-11-28 03:39:33,255][87424] Updated weights for policy 0, policy_version 131696 (0.0008) -[2023-11-28 03:39:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 67354624. Throughput: 0: 2739.3, 1: 2760.9. Samples: 67369544. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:33,445][86177] Avg episode reward: [(0, '-506.650'), (1, '-500.000')] -[2023-11-28 03:39:33,633][87424] Updated weights for policy 0, policy_version 131706 (0.0007) -[2023-11-28 03:39:34,707][87426] Updated weights for policy 1, policy_version 131430 (0.0009) -[2023-11-28 03:39:35,087][87426] Updated weights for policy 1, policy_version 131440 (0.0007) -[2023-11-28 03:39:35,466][87426] Updated weights for policy 1, policy_version 131450 (0.0007) -[2023-11-28 03:39:35,990][87424] Updated weights for policy 0, policy_version 131716 (0.0009) -[2023-11-28 03:39:36,367][87424] Updated weights for policy 0, policy_version 131726 (0.0012) -[2023-11-28 03:39:36,749][87424] Updated weights for policy 0, policy_version 131736 (0.0012) -[2023-11-28 03:39:37,320][87426] Updated weights for policy 1, policy_version 131460 (0.0007) -[2023-11-28 03:39:37,693][87426] Updated weights for policy 1, policy_version 131470 (0.0010) -[2023-11-28 03:39:38,082][87426] Updated weights for policy 1, policy_version 131480 (0.0011) -[2023-11-28 03:39:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 67387392. Throughput: 0: 2740.4, 1: 2757.2. Samples: 67401280. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:38,445][86177] Avg episode reward: [(0, '-503.580'), (1, '-514.450')] -[2023-11-28 03:39:38,644][87424] Updated weights for policy 0, policy_version 131746 (0.0012) -[2023-11-28 03:39:39,022][87424] Updated weights for policy 0, policy_version 131756 (0.0012) -[2023-11-28 03:39:39,404][87424] Updated weights for policy 0, policy_version 131766 (0.0012) -[2023-11-28 03:39:39,784][87424] Updated weights for policy 0, policy_version 131776 (0.0012) -[2023-11-28 03:39:40,343][87426] Updated weights for policy 1, policy_version 131490 (0.0012) -[2023-11-28 03:39:40,722][87426] Updated weights for policy 1, policy_version 131500 (0.0012) -[2023-11-28 03:39:41,096][87426] Updated weights for policy 1, policy_version 131510 (0.0012) -[2023-11-28 03:39:41,472][87426] Updated weights for policy 1, policy_version 131520 (0.0012) -[2023-11-28 03:39:41,991][87424] Updated weights for policy 0, policy_version 131786 (0.0010) -[2023-11-28 03:39:42,372][87424] Updated weights for policy 0, policy_version 131796 (0.0011) -[2023-11-28 03:39:42,759][87424] Updated weights for policy 0, policy_version 131806 (0.0011) -[2023-11-28 03:39:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 67411968. Throughput: 0: 2762.1, 1: 2742.0. Samples: 67426092. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:43,445][86177] Avg episode reward: [(0, '-505.950'), (1, '-508.830')] -[2023-11-28 03:39:43,948][87426] Updated weights for policy 1, policy_version 131530 (0.0007) -[2023-11-28 03:39:44,328][87426] Updated weights for policy 1, policy_version 131540 (0.0007) -[2023-11-28 03:39:44,701][87426] Updated weights for policy 1, policy_version 131550 (0.0007) -[2023-11-28 03:39:45,153][87424] Updated weights for policy 0, policy_version 131816 (0.0010) -[2023-11-28 03:39:45,539][87424] Updated weights for policy 0, policy_version 131826 (0.0009) -[2023-11-28 03:39:45,917][87424] Updated weights for policy 0, policy_version 131836 (0.0008) -[2023-11-28 03:39:47,003][87426] Updated weights for policy 1, policy_version 131560 (0.0011) -[2023-11-28 03:39:47,381][87426] Updated weights for policy 1, policy_version 131570 (0.0011) -[2023-11-28 03:39:47,545][87424] Updated weights for policy 0, policy_version 131846 (0.0009) -[2023-11-28 03:39:47,769][87426] Updated weights for policy 1, policy_version 131580 (0.0011) -[2023-11-28 03:39:47,916][87424] Updated weights for policy 0, policy_version 131856 (0.0011) -[2023-11-28 03:39:48,300][87424] Updated weights for policy 0, policy_version 131866 (0.0009) -[2023-11-28 03:39:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 67436544. Throughput: 0: 2743.6, 1: 2744.4. Samples: 67451008. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:48,445][86177] Avg episode reward: [(0, '-508.520'), (1, '-523.530')] -[2023-11-28 03:39:49,806][87426] Updated weights for policy 1, policy_version 131590 (0.0011) -[2023-11-28 03:39:50,180][87426] Updated weights for policy 1, policy_version 131600 (0.0012) -[2023-11-28 03:39:50,430][87424] Updated weights for policy 0, policy_version 131876 (0.0012) -[2023-11-28 03:39:50,565][87426] Updated weights for policy 1, policy_version 131610 (0.0012) -[2023-11-28 03:39:50,803][87424] Updated weights for policy 0, policy_version 131886 (0.0011) -[2023-11-28 03:39:51,184][87424] Updated weights for policy 0, policy_version 131896 (0.0010) -[2023-11-28 03:39:52,836][87426] Updated weights for policy 1, policy_version 131620 (0.0010) -[2023-11-28 03:39:53,217][87426] Updated weights for policy 1, policy_version 131630 (0.0011) -[2023-11-28 03:39:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 67461120. Throughput: 0: 2761.4, 1: 2735.2. Samples: 67484436. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:53,445][86177] Avg episode reward: [(0, '-502.810'), (1, '-530.320')] -[2023-11-28 03:39:53,502][87424] Updated weights for policy 0, policy_version 131906 (0.0010) -[2023-11-28 03:39:53,595][87426] Updated weights for policy 1, policy_version 131640 (0.0013) -[2023-11-28 03:39:53,871][87424] Updated weights for policy 0, policy_version 131916 (0.0011) -[2023-11-28 03:39:54,259][87424] Updated weights for policy 0, policy_version 131926 (0.0009) -[2023-11-28 03:39:54,645][87424] Updated weights for policy 0, policy_version 131936 (0.0007) -[2023-11-28 03:39:55,500][87426] Updated weights for policy 1, policy_version 131650 (0.0009) -[2023-11-28 03:39:55,878][87426] Updated weights for policy 1, policy_version 131660 (0.0012) -[2023-11-28 03:39:56,255][87426] Updated weights for policy 1, policy_version 131670 (0.0011) -[2023-11-28 03:39:56,634][87426] Updated weights for policy 1, policy_version 131680 (0.0011) -[2023-11-28 03:39:56,964][87424] Updated weights for policy 0, policy_version 131946 (0.0007) -[2023-11-28 03:39:57,356][87424] Updated weights for policy 0, policy_version 131956 (0.0008) -[2023-11-28 03:39:57,737][87424] Updated weights for policy 0, policy_version 131966 (0.0011) -[2023-11-28 03:39:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67493888. Throughput: 0: 2752.0, 1: 2765.4. Samples: 67509520. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:39:58,445][86177] Avg episode reward: [(0, '-501.690'), (1, '-521.790')] -[2023-11-28 03:39:58,498][87426] Updated weights for policy 1, policy_version 131690 (0.0012) -[2023-11-28 03:39:58,868][87426] Updated weights for policy 1, policy_version 131700 (0.0011) -[2023-11-28 03:39:59,251][87426] Updated weights for policy 1, policy_version 131710 (0.0012) -[2023-11-28 03:39:59,927][87424] Updated weights for policy 0, policy_version 131976 (0.0011) -[2023-11-28 03:40:00,311][87424] Updated weights for policy 0, policy_version 131986 (0.0011) -[2023-11-28 03:40:00,693][87424] Updated weights for policy 0, policy_version 131996 (0.0011) -[2023-11-28 03:40:00,914][87426] Updated weights for policy 1, policy_version 131720 (0.0011) -[2023-11-28 03:40:01,299][87426] Updated weights for policy 1, policy_version 131730 (0.0011) -[2023-11-28 03:40:01,680][87426] Updated weights for policy 1, policy_version 131740 (0.0012) -[2023-11-28 03:40:02,643][87424] Updated weights for policy 0, policy_version 132006 (0.0011) -[2023-11-28 03:40:03,034][87424] Updated weights for policy 0, policy_version 132016 (0.0012) -[2023-11-28 03:40:03,424][87424] Updated weights for policy 0, policy_version 132026 (0.0011) -[2023-11-28 03:40:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 67518464. Throughput: 0: 2742.5, 1: 2762.0. Samples: 67534128. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:40:03,445][86177] Avg episode reward: [(0, '-498.620'), (1, '-514.300')] -[2023-11-28 03:40:04,203][87426] Updated weights for policy 1, policy_version 131750 (0.0012) -[2023-11-28 03:40:04,579][87426] Updated weights for policy 1, policy_version 131760 (0.0012) -[2023-11-28 03:40:04,963][87426] Updated weights for policy 1, policy_version 131770 (0.0012) -[2023-11-28 03:40:05,540][87424] Updated weights for policy 0, policy_version 132036 (0.0012) -[2023-11-28 03:40:05,921][87424] Updated weights for policy 0, policy_version 132046 (0.0011) -[2023-11-28 03:40:06,312][87424] Updated weights for policy 0, policy_version 132056 (0.0012) -[2023-11-28 03:40:07,271][87426] Updated weights for policy 1, policy_version 131780 (0.0011) -[2023-11-28 03:40:07,654][87426] Updated weights for policy 1, policy_version 131790 (0.0011) -[2023-11-28 03:40:08,032][87426] Updated weights for policy 1, policy_version 131800 (0.0008) -[2023-11-28 03:40:08,305][87424] Updated weights for policy 0, policy_version 132066 (0.0011) -[2023-11-28 03:40:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 67551232. Throughput: 0: 2744.1, 1: 2761.5. Samples: 67566700. Policy #0 lag: (min: 22.0, avg: 40.3, max: 54.0) -[2023-11-28 03:40:08,445][86177] Avg episode reward: [(0, '-504.750'), (1, '-506.650')] -[2023-11-28 03:40:08,686][87424] Updated weights for policy 0, policy_version 132076 (0.0007) -[2023-11-28 03:40:09,068][87424] Updated weights for policy 0, policy_version 132086 (0.0010) -[2023-11-28 03:40:09,452][87424] Updated weights for policy 0, policy_version 132096 (0.0011) -[2023-11-28 03:40:10,415][87426] Updated weights for policy 1, policy_version 131810 (0.0009) -[2023-11-28 03:40:10,792][87426] Updated weights for policy 1, policy_version 131820 (0.0008) -[2023-11-28 03:40:11,176][87426] Updated weights for policy 1, policy_version 131830 (0.0008) -[2023-11-28 03:40:11,560][87426] Updated weights for policy 1, policy_version 131840 (0.0009) -[2023-11-28 03:40:11,571][87424] Updated weights for policy 0, policy_version 132106 (0.0010) -[2023-11-28 03:40:11,950][87424] Updated weights for policy 0, policy_version 132116 (0.0012) -[2023-11-28 03:40:12,329][87424] Updated weights for policy 0, policy_version 132126 (0.0010) -[2023-11-28 03:40:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67575808. Throughput: 0: 2756.5, 1: 2704.8. Samples: 67590496. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:13,446][86177] Avg episode reward: [(0, '-498.830'), (1, '-495.520')] -[2023-11-28 03:40:14,096][87426] Updated weights for policy 1, policy_version 131850 (0.0008) -[2023-11-28 03:40:14,474][87426] Updated weights for policy 1, policy_version 131860 (0.0009) -[2023-11-28 03:40:14,852][87426] Updated weights for policy 1, policy_version 131870 (0.0007) -[2023-11-28 03:40:14,951][87424] Updated weights for policy 0, policy_version 132136 (0.0009) -[2023-11-28 03:40:15,340][87424] Updated weights for policy 0, policy_version 132146 (0.0012) -[2023-11-28 03:40:15,723][87424] Updated weights for policy 0, policy_version 132156 (0.0012) -[2023-11-28 03:40:16,968][87426] Updated weights for policy 1, policy_version 131880 (0.0007) -[2023-11-28 03:40:17,349][87426] Updated weights for policy 1, policy_version 131890 (0.0008) -[2023-11-28 03:40:17,728][87426] Updated weights for policy 1, policy_version 131900 (0.0007) -[2023-11-28 03:40:18,044][87424] Updated weights for policy 0, policy_version 132166 (0.0012) -[2023-11-28 03:40:18,418][87424] Updated weights for policy 0, policy_version 132176 (0.0012) -[2023-11-28 03:40:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67600384. Throughput: 0: 2717.9, 1: 2707.6. Samples: 67613692. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:18,445][86177] Avg episode reward: [(0, '-506.670'), (1, '-492.590')] -[2023-11-28 03:40:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000131904_33767424.pth... -[2023-11-28 03:40:18,486][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000129344_33112064.pth -[2023-11-28 03:40:18,800][87424] Updated weights for policy 0, policy_version 132186 (0.0012) -[2023-11-28 03:40:19,028][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000132192_33841152.pth... -[2023-11-28 03:40:19,075][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000129632_33185792.pth -[2023-11-28 03:40:19,480][87426] Updated weights for policy 1, policy_version 131910 (0.0008) -[2023-11-28 03:40:19,848][87426] Updated weights for policy 1, policy_version 131920 (0.0008) -[2023-11-28 03:40:20,240][87426] Updated weights for policy 1, policy_version 131930 (0.0009) -[2023-11-28 03:40:20,961][87424] Updated weights for policy 0, policy_version 132196 (0.0011) -[2023-11-28 03:40:21,349][87424] Updated weights for policy 0, policy_version 132206 (0.0012) -[2023-11-28 03:40:21,740][87424] Updated weights for policy 0, policy_version 132216 (0.0012) -[2023-11-28 03:40:22,714][87426] Updated weights for policy 1, policy_version 131940 (0.0011) -[2023-11-28 03:40:23,090][87426] Updated weights for policy 1, policy_version 131950 (0.0009) -[2023-11-28 03:40:23,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67624960. Throughput: 0: 2722.4, 1: 2720.7. Samples: 67646220. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:23,446][86177] Avg episode reward: [(0, '-511.500'), (1, '-501.640')] -[2023-11-28 03:40:23,467][87426] Updated weights for policy 1, policy_version 131960 (0.0009) -[2023-11-28 03:40:23,949][87424] Updated weights for policy 0, policy_version 132226 (0.0011) -[2023-11-28 03:40:24,323][87424] Updated weights for policy 0, policy_version 132236 (0.0007) -[2023-11-28 03:40:24,702][87424] Updated weights for policy 0, policy_version 132246 (0.0008) -[2023-11-28 03:40:25,080][87424] Updated weights for policy 0, policy_version 132256 (0.0010) -[2023-11-28 03:40:25,776][87426] Updated weights for policy 1, policy_version 131970 (0.0009) -[2023-11-28 03:40:26,150][87426] Updated weights for policy 1, policy_version 131980 (0.0012) -[2023-11-28 03:40:26,523][87426] Updated weights for policy 1, policy_version 131990 (0.0011) -[2023-11-28 03:40:26,902][87426] Updated weights for policy 1, policy_version 132000 (0.0011) -[2023-11-28 03:40:27,024][87424] Updated weights for policy 0, policy_version 132266 (0.0012) -[2023-11-28 03:40:27,412][87424] Updated weights for policy 0, policy_version 132276 (0.0012) -[2023-11-28 03:40:27,791][87424] Updated weights for policy 0, policy_version 132286 (0.0012) -[2023-11-28 03:40:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67657728. Throughput: 0: 2699.6, 1: 2752.1. Samples: 67671420. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:28,446][86177] Avg episode reward: [(0, '-513.470'), (1, '-502.680')] -[2023-11-28 03:40:28,520][87426] Updated weights for policy 1, policy_version 132010 (0.0012) -[2023-11-28 03:40:28,899][87426] Updated weights for policy 1, policy_version 132020 (0.0011) -[2023-11-28 03:40:29,278][87426] Updated weights for policy 1, policy_version 132030 (0.0012) -[2023-11-28 03:40:29,856][87424] Updated weights for policy 0, policy_version 132296 (0.0011) -[2023-11-28 03:40:30,238][87424] Updated weights for policy 0, policy_version 132306 (0.0012) -[2023-11-28 03:40:30,620][87424] Updated weights for policy 0, policy_version 132316 (0.0010) -[2023-11-28 03:40:31,241][87426] Updated weights for policy 1, policy_version 132040 (0.0012) -[2023-11-28 03:40:31,621][87426] Updated weights for policy 1, policy_version 132050 (0.0009) -[2023-11-28 03:40:32,003][87426] Updated weights for policy 1, policy_version 132060 (0.0010) -[2023-11-28 03:40:33,004][87424] Updated weights for policy 0, policy_version 132326 (0.0008) -[2023-11-28 03:40:33,383][87424] Updated weights for policy 0, policy_version 132336 (0.0007) -[2023-11-28 03:40:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 67682304. Throughput: 0: 2713.9, 1: 2757.9. Samples: 67697236. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:33,445][86177] Avg episode reward: [(0, '-519.710'), (1, '-504.290')] -[2023-11-28 03:40:33,772][87424] Updated weights for policy 0, policy_version 132346 (0.0010) -[2023-11-28 03:40:34,407][87426] Updated weights for policy 1, policy_version 132070 (0.0010) -[2023-11-28 03:40:34,779][87426] Updated weights for policy 1, policy_version 132080 (0.0010) -[2023-11-28 03:40:35,161][87426] Updated weights for policy 1, policy_version 132090 (0.0009) -[2023-11-28 03:40:35,673][87424] Updated weights for policy 0, policy_version 132356 (0.0012) -[2023-11-28 03:40:36,065][87424] Updated weights for policy 0, policy_version 132366 (0.0012) -[2023-11-28 03:40:36,448][87424] Updated weights for policy 0, policy_version 132376 (0.0012) -[2023-11-28 03:40:37,109][87426] Updated weights for policy 1, policy_version 132100 (0.0008) -[2023-11-28 03:40:37,482][87426] Updated weights for policy 1, policy_version 132110 (0.0007) -[2023-11-28 03:40:37,860][87426] Updated weights for policy 1, policy_version 132120 (0.0007) -[2023-11-28 03:40:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 67715072. Throughput: 0: 2694.1, 1: 2777.4. Samples: 67730656. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:38,445][86177] Avg episode reward: [(0, '-509.930'), (1, '-503.420')] -[2023-11-28 03:40:38,778][87424] Updated weights for policy 0, policy_version 132386 (0.0012) -[2023-11-28 03:40:39,163][87424] Updated weights for policy 0, policy_version 132396 (0.0012) -[2023-11-28 03:40:39,539][87424] Updated weights for policy 0, policy_version 132406 (0.0012) -[2023-11-28 03:40:39,933][87424] Updated weights for policy 0, policy_version 132416 (0.0012) -[2023-11-28 03:40:39,992][87426] Updated weights for policy 1, policy_version 132130 (0.0008) -[2023-11-28 03:40:40,368][87426] Updated weights for policy 1, policy_version 132140 (0.0009) -[2023-11-28 03:40:40,746][87426] Updated weights for policy 1, policy_version 132150 (0.0012) -[2023-11-28 03:40:41,120][87426] Updated weights for policy 1, policy_version 132160 (0.0012) -[2023-11-28 03:40:42,031][87424] Updated weights for policy 0, policy_version 132426 (0.0011) -[2023-11-28 03:40:42,427][87424] Updated weights for policy 0, policy_version 132436 (0.0010) -[2023-11-28 03:40:42,806][87424] Updated weights for policy 0, policy_version 132446 (0.0008) -[2023-11-28 03:40:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67739648. Throughput: 0: 2696.3, 1: 2752.6. Samples: 67754724. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:43,446][86177] Avg episode reward: [(0, '-505.210'), (1, '-494.000')] -[2023-11-28 03:40:43,554][87426] Updated weights for policy 1, policy_version 132170 (0.0012) -[2023-11-28 03:40:43,930][87426] Updated weights for policy 1, policy_version 132180 (0.0012) -[2023-11-28 03:40:44,307][87426] Updated weights for policy 1, policy_version 132190 (0.0012) -[2023-11-28 03:40:45,127][87424] Updated weights for policy 0, policy_version 132456 (0.0011) -[2023-11-28 03:40:45,502][87424] Updated weights for policy 0, policy_version 132466 (0.0012) -[2023-11-28 03:40:45,886][87424] Updated weights for policy 0, policy_version 132476 (0.0012) -[2023-11-28 03:40:46,235][87426] Updated weights for policy 1, policy_version 132200 (0.0009) -[2023-11-28 03:40:46,614][87426] Updated weights for policy 1, policy_version 132210 (0.0008) -[2023-11-28 03:40:46,994][87426] Updated weights for policy 1, policy_version 132220 (0.0007) -[2023-11-28 03:40:47,920][87424] Updated weights for policy 0, policy_version 132486 (0.0012) -[2023-11-28 03:40:48,300][87424] Updated weights for policy 0, policy_version 132496 (0.0012) -[2023-11-28 03:40:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 67764224. Throughput: 0: 2705.9, 1: 2736.2. Samples: 67779020. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:48,445][86177] Avg episode reward: [(0, '-506.910'), (1, '-490.820')] -[2023-11-28 03:40:48,683][87424] Updated weights for policy 0, policy_version 132506 (0.0012) -[2023-11-28 03:40:49,469][87426] Updated weights for policy 1, policy_version 132230 (0.0007) -[2023-11-28 03:40:49,852][87426] Updated weights for policy 1, policy_version 132240 (0.0010) -[2023-11-28 03:40:50,230][87426] Updated weights for policy 1, policy_version 132250 (0.0010) -[2023-11-28 03:40:50,655][87424] Updated weights for policy 0, policy_version 132516 (0.0010) -[2023-11-28 03:40:51,034][87424] Updated weights for policy 0, policy_version 132526 (0.0007) -[2023-11-28 03:40:51,419][87424] Updated weights for policy 0, policy_version 132536 (0.0011) -[2023-11-28 03:40:52,529][87426] Updated weights for policy 1, policy_version 132260 (0.0008) -[2023-11-28 03:40:52,916][87426] Updated weights for policy 1, policy_version 132270 (0.0008) -[2023-11-28 03:40:53,302][87426] Updated weights for policy 1, policy_version 132280 (0.0011) -[2023-11-28 03:40:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67788800. Throughput: 0: 2707.5, 1: 2734.9. Samples: 67811608. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:53,445][86177] Avg episode reward: [(0, '-499.410'), (1, '-504.260')] -[2023-11-28 03:40:53,660][87424] Updated weights for policy 0, policy_version 132546 (0.0010) -[2023-11-28 03:40:54,043][87424] Updated weights for policy 0, policy_version 132556 (0.0010) -[2023-11-28 03:40:54,430][87424] Updated weights for policy 0, policy_version 132566 (0.0008) -[2023-11-28 03:40:54,811][87424] Updated weights for policy 0, policy_version 132576 (0.0007) -[2023-11-28 03:40:55,591][87426] Updated weights for policy 1, policy_version 132290 (0.0011) -[2023-11-28 03:40:55,967][87426] Updated weights for policy 1, policy_version 132300 (0.0008) -[2023-11-28 03:40:56,342][87426] Updated weights for policy 1, policy_version 132310 (0.0010) -[2023-11-28 03:40:56,725][87426] Updated weights for policy 1, policy_version 132320 (0.0011) -[2023-11-28 03:40:57,077][87424] Updated weights for policy 0, policy_version 132586 (0.0008) -[2023-11-28 03:40:57,461][87424] Updated weights for policy 0, policy_version 132596 (0.0007) -[2023-11-28 03:40:57,854][87424] Updated weights for policy 0, policy_version 132606 (0.0007) -[2023-11-28 03:40:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67821568. Throughput: 0: 2695.5, 1: 2733.6. Samples: 67834804. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:40:58,445][86177] Avg episode reward: [(0, '-499.610'), (1, '-508.700')] -[2023-11-28 03:40:59,011][87426] Updated weights for policy 1, policy_version 132330 (0.0010) -[2023-11-28 03:40:59,405][87426] Updated weights for policy 1, policy_version 132340 (0.0011) -[2023-11-28 03:40:59,780][87426] Updated weights for policy 1, policy_version 132350 (0.0011) -[2023-11-28 03:41:00,089][87424] Updated weights for policy 0, policy_version 132616 (0.0012) -[2023-11-28 03:41:00,469][87424] Updated weights for policy 0, policy_version 132626 (0.0010) -[2023-11-28 03:41:00,855][87424] Updated weights for policy 0, policy_version 132636 (0.0007) -[2023-11-28 03:41:02,012][87426] Updated weights for policy 1, policy_version 132360 (0.0012) -[2023-11-28 03:41:02,388][87426] Updated weights for policy 1, policy_version 132370 (0.0011) -[2023-11-28 03:41:02,764][87426] Updated weights for policy 1, policy_version 132380 (0.0009) -[2023-11-28 03:41:03,056][87424] Updated weights for policy 0, policy_version 132646 (0.0009) -[2023-11-28 03:41:03,439][87424] Updated weights for policy 0, policy_version 132656 (0.0008) -[2023-11-28 03:41:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 67846144. Throughput: 0: 2705.9, 1: 2743.9. Samples: 67858932. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:41:03,445][86177] Avg episode reward: [(0, '-503.870'), (1, '-526.930')] -[2023-11-28 03:41:03,818][87424] Updated weights for policy 0, policy_version 132666 (0.0011) -[2023-11-28 03:41:04,535][87426] Updated weights for policy 1, policy_version 132390 (0.0008) -[2023-11-28 03:41:04,909][87426] Updated weights for policy 1, policy_version 132400 (0.0009) -[2023-11-28 03:41:05,289][87426] Updated weights for policy 1, policy_version 132410 (0.0008) -[2023-11-28 03:41:05,988][87424] Updated weights for policy 0, policy_version 132676 (0.0011) -[2023-11-28 03:41:06,365][87424] Updated weights for policy 0, policy_version 132686 (0.0011) -[2023-11-28 03:41:06,747][87424] Updated weights for policy 0, policy_version 132696 (0.0011) -[2023-11-28 03:41:06,980][87426] Updated weights for policy 1, policy_version 132420 (0.0008) -[2023-11-28 03:41:07,358][87426] Updated weights for policy 1, policy_version 132430 (0.0007) -[2023-11-28 03:41:07,738][87426] Updated weights for policy 1, policy_version 132440 (0.0007) -[2023-11-28 03:41:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 67878912. Throughput: 0: 2722.0, 1: 2734.4. Samples: 67891756. Policy #0 lag: (min: 55.0, avg: 61.6, max: 88.0) -[2023-11-28 03:41:08,445][86177] Avg episode reward: [(0, '-503.890'), (1, '-527.140')] -[2023-11-28 03:41:08,674][87424] Updated weights for policy 0, policy_version 132706 (0.0012) -[2023-11-28 03:41:09,058][87424] Updated weights for policy 0, policy_version 132716 (0.0012) -[2023-11-28 03:41:09,435][87424] Updated weights for policy 0, policy_version 132726 (0.0012) -[2023-11-28 03:41:09,822][87424] Updated weights for policy 0, policy_version 132736 (0.0012) -[2023-11-28 03:41:09,859][87426] Updated weights for policy 1, policy_version 132450 (0.0008) -[2023-11-28 03:41:10,238][87426] Updated weights for policy 1, policy_version 132460 (0.0012) -[2023-11-28 03:41:10,606][87426] Updated weights for policy 1, policy_version 132470 (0.0012) -[2023-11-28 03:41:10,990][87426] Updated weights for policy 1, policy_version 132480 (0.0012) -[2023-11-28 03:41:11,948][87424] Updated weights for policy 0, policy_version 132746 (0.0010) -[2023-11-28 03:41:12,324][87424] Updated weights for policy 0, policy_version 132756 (0.0009) -[2023-11-28 03:41:12,721][87424] Updated weights for policy 0, policy_version 132766 (0.0010) -[2023-11-28 03:41:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 67903488. Throughput: 0: 2735.9, 1: 2738.2. Samples: 67917756. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:13,445][86177] Avg episode reward: [(0, '-502.590'), (1, '-514.940')] -[2023-11-28 03:41:13,593][87426] Updated weights for policy 1, policy_version 132490 (0.0012) -[2023-11-28 03:41:13,967][87426] Updated weights for policy 1, policy_version 132500 (0.0010) -[2023-11-28 03:41:14,348][87426] Updated weights for policy 1, policy_version 132510 (0.0007) -[2023-11-28 03:41:15,254][87424] Updated weights for policy 0, policy_version 132776 (0.0009) -[2023-11-28 03:41:15,656][87424] Updated weights for policy 0, policy_version 132786 (0.0012) -[2023-11-28 03:41:16,036][87424] Updated weights for policy 0, policy_version 132796 (0.0012) -[2023-11-28 03:41:16,788][87426] Updated weights for policy 1, policy_version 132520 (0.0009) -[2023-11-28 03:41:17,168][87426] Updated weights for policy 1, policy_version 132530 (0.0008) -[2023-11-28 03:41:17,535][87426] Updated weights for policy 1, policy_version 132540 (0.0007) -[2023-11-28 03:41:18,157][87424] Updated weights for policy 0, policy_version 132806 (0.0012) -[2023-11-28 03:41:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 67928064. Throughput: 0: 2714.9, 1: 2711.6. Samples: 67941432. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:18,445][86177] Avg episode reward: [(0, '-502.730'), (1, '-515.260')] -[2023-11-28 03:41:18,542][87424] Updated weights for policy 0, policy_version 132816 (0.0012) -[2023-11-28 03:41:18,921][87424] Updated weights for policy 0, policy_version 132826 (0.0012) -[2023-11-28 03:41:19,962][87426] Updated weights for policy 1, policy_version 132550 (0.0009) -[2023-11-28 03:41:20,335][87426] Updated weights for policy 1, policy_version 132560 (0.0012) -[2023-11-28 03:41:20,716][87426] Updated weights for policy 1, policy_version 132570 (0.0012) -[2023-11-28 03:41:21,008][87424] Updated weights for policy 0, policy_version 132836 (0.0010) -[2023-11-28 03:41:21,396][87424] Updated weights for policy 0, policy_version 132846 (0.0011) -[2023-11-28 03:41:21,779][87424] Updated weights for policy 0, policy_version 132856 (0.0012) -[2023-11-28 03:41:22,554][87426] Updated weights for policy 1, policy_version 132580 (0.0010) -[2023-11-28 03:41:22,927][87426] Updated weights for policy 1, policy_version 132590 (0.0010) -[2023-11-28 03:41:23,300][87426] Updated weights for policy 1, policy_version 132600 (0.0009) -[2023-11-28 03:41:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 67952640. Throughput: 0: 2727.9, 1: 2667.5. Samples: 67973448. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:23,445][86177] Avg episode reward: [(0, '-501.110'), (1, '-511.000')] -[2023-11-28 03:41:24,077][87424] Updated weights for policy 0, policy_version 132866 (0.0010) -[2023-11-28 03:41:24,460][87424] Updated weights for policy 0, policy_version 132876 (0.0008) -[2023-11-28 03:41:24,843][87424] Updated weights for policy 0, policy_version 132886 (0.0008) -[2023-11-28 03:41:25,224][87426] Updated weights for policy 1, policy_version 132610 (0.0008) -[2023-11-28 03:41:25,238][87424] Updated weights for policy 0, policy_version 132896 (0.0008) -[2023-11-28 03:41:25,601][87426] Updated weights for policy 1, policy_version 132620 (0.0012) -[2023-11-28 03:41:25,976][87426] Updated weights for policy 1, policy_version 132630 (0.0011) -[2023-11-28 03:41:26,355][87426] Updated weights for policy 1, policy_version 132640 (0.0009) -[2023-11-28 03:41:27,305][87424] Updated weights for policy 0, policy_version 132906 (0.0012) -[2023-11-28 03:41:27,679][87424] Updated weights for policy 0, policy_version 132916 (0.0011) -[2023-11-28 03:41:28,058][87424] Updated weights for policy 0, policy_version 132926 (0.0009) -[2023-11-28 03:41:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 67985408. Throughput: 0: 2725.3, 1: 2702.5. Samples: 67998976. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:28,445][86177] Avg episode reward: [(0, '-500.710'), (1, '-511.230')] -[2023-11-28 03:41:28,817][87426] Updated weights for policy 1, policy_version 132650 (0.0009) -[2023-11-28 03:41:29,198][87426] Updated weights for policy 1, policy_version 132660 (0.0008) -[2023-11-28 03:41:29,577][87426] Updated weights for policy 1, policy_version 132670 (0.0008) -[2023-11-28 03:41:30,521][87424] Updated weights for policy 0, policy_version 132936 (0.0011) -[2023-11-28 03:41:30,894][87424] Updated weights for policy 0, policy_version 132946 (0.0012) -[2023-11-28 03:41:31,271][87424] Updated weights for policy 0, policy_version 132956 (0.0012) -[2023-11-28 03:41:31,539][87426] Updated weights for policy 1, policy_version 132680 (0.0010) -[2023-11-28 03:41:31,920][87426] Updated weights for policy 1, policy_version 132690 (0.0012) -[2023-11-28 03:41:32,291][87426] Updated weights for policy 1, policy_version 132700 (0.0012) -[2023-11-28 03:41:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68009984. Throughput: 0: 2696.5, 1: 2719.1. Samples: 68022724. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:33,445][86177] Avg episode reward: [(0, '-501.980'), (1, '-510.670')] -[2023-11-28 03:41:33,732][87424] Updated weights for policy 0, policy_version 132966 (0.0010) -[2023-11-28 03:41:34,115][87424] Updated weights for policy 0, policy_version 132976 (0.0010) -[2023-11-28 03:41:34,496][87424] Updated weights for policy 0, policy_version 132986 (0.0009) -[2023-11-28 03:41:34,662][87426] Updated weights for policy 1, policy_version 132710 (0.0011) -[2023-11-28 03:41:35,052][87426] Updated weights for policy 1, policy_version 132720 (0.0011) -[2023-11-28 03:41:35,430][87426] Updated weights for policy 1, policy_version 132730 (0.0007) -[2023-11-28 03:41:36,663][87424] Updated weights for policy 0, policy_version 132996 (0.0008) -[2023-11-28 03:41:37,042][87424] Updated weights for policy 0, policy_version 133006 (0.0012) -[2023-11-28 03:41:37,424][87424] Updated weights for policy 0, policy_version 133016 (0.0012) -[2023-11-28 03:41:37,947][87426] Updated weights for policy 1, policy_version 132740 (0.0009) -[2023-11-28 03:41:38,330][87426] Updated weights for policy 1, policy_version 132750 (0.0011) -[2023-11-28 03:41:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 68034560. Throughput: 0: 2697.6, 1: 2705.4. Samples: 68054744. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:38,446][86177] Avg episode reward: [(0, '-515.350'), (1, '-506.840')] -[2023-11-28 03:41:38,708][87426] Updated weights for policy 1, policy_version 132760 (0.0010) -[2023-11-28 03:41:39,107][87424] Updated weights for policy 0, policy_version 133026 (0.0011) -[2023-11-28 03:41:39,482][87424] Updated weights for policy 0, policy_version 133036 (0.0010) -[2023-11-28 03:41:39,867][87424] Updated weights for policy 0, policy_version 133046 (0.0009) -[2023-11-28 03:41:40,244][87424] Updated weights for policy 0, policy_version 133056 (0.0011) -[2023-11-28 03:41:40,704][87426] Updated weights for policy 1, policy_version 132770 (0.0011) -[2023-11-28 03:41:41,090][87426] Updated weights for policy 1, policy_version 132780 (0.0012) -[2023-11-28 03:41:41,475][87426] Updated weights for policy 1, policy_version 132790 (0.0009) -[2023-11-28 03:41:41,847][87426] Updated weights for policy 1, policy_version 132800 (0.0010) -[2023-11-28 03:41:42,765][87424] Updated weights for policy 0, policy_version 133066 (0.0012) -[2023-11-28 03:41:43,142][87424] Updated weights for policy 0, policy_version 133076 (0.0009) -[2023-11-28 03:41:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 68059136. Throughput: 0: 2699.3, 1: 2727.4. Samples: 68079004. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:43,445][86177] Avg episode reward: [(0, '-515.160'), (1, '-496.220')] -[2023-11-28 03:41:43,523][87424] Updated weights for policy 0, policy_version 133086 (0.0008) -[2023-11-28 03:41:43,931][87426] Updated weights for policy 1, policy_version 132810 (0.0007) -[2023-11-28 03:41:44,315][87426] Updated weights for policy 1, policy_version 132820 (0.0007) -[2023-11-28 03:41:44,694][87426] Updated weights for policy 1, policy_version 132830 (0.0007) -[2023-11-28 03:41:45,733][87424] Updated weights for policy 0, policy_version 133096 (0.0010) -[2023-11-28 03:41:46,117][87424] Updated weights for policy 0, policy_version 133106 (0.0011) -[2023-11-28 03:41:46,511][87424] Updated weights for policy 0, policy_version 133116 (0.0012) -[2023-11-28 03:41:47,075][87426] Updated weights for policy 1, policy_version 132840 (0.0010) -[2023-11-28 03:41:47,449][87426] Updated weights for policy 1, policy_version 132850 (0.0012) -[2023-11-28 03:41:47,832][87426] Updated weights for policy 1, policy_version 132860 (0.0011) -[2023-11-28 03:41:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68091904. Throughput: 0: 2694.5, 1: 2721.4. Samples: 68102648. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:48,445][86177] Avg episode reward: [(0, '-512.690'), (1, '-506.560')] -[2023-11-28 03:41:49,081][87424] Updated weights for policy 0, policy_version 133126 (0.0010) -[2023-11-28 03:41:49,459][87424] Updated weights for policy 0, policy_version 133136 (0.0008) -[2023-11-28 03:41:49,842][87424] Updated weights for policy 0, policy_version 133146 (0.0009) -[2023-11-28 03:41:50,251][87426] Updated weights for policy 1, policy_version 132870 (0.0011) -[2023-11-28 03:41:50,628][87426] Updated weights for policy 1, policy_version 132880 (0.0009) -[2023-11-28 03:41:51,014][87426] Updated weights for policy 1, policy_version 132890 (0.0008) -[2023-11-28 03:41:52,209][87424] Updated weights for policy 0, policy_version 133156 (0.0009) -[2023-11-28 03:41:52,590][87424] Updated weights for policy 0, policy_version 133166 (0.0012) -[2023-11-28 03:41:52,981][87424] Updated weights for policy 0, policy_version 133176 (0.0012) -[2023-11-28 03:41:53,058][87426] Updated weights for policy 1, policy_version 132900 (0.0010) -[2023-11-28 03:41:53,449][86177] Fps is (10 sec: 5731.6, 60 sec: 5460.9, 300 sec: 5442.7). Total num frames: 68116480. Throughput: 0: 2671.3, 1: 2708.2. Samples: 68133860. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:53,450][86177] Avg episode reward: [(0, '-493.840'), (1, '-511.090')] -[2023-11-28 03:41:53,452][87426] Updated weights for policy 1, policy_version 132910 (0.0011) -[2023-11-28 03:41:53,820][87426] Updated weights for policy 1, policy_version 132920 (0.0011) -[2023-11-28 03:41:55,353][87424] Updated weights for policy 0, policy_version 133186 (0.0010) -[2023-11-28 03:41:55,732][87424] Updated weights for policy 0, policy_version 133196 (0.0008) -[2023-11-28 03:41:55,850][87426] Updated weights for policy 1, policy_version 132930 (0.0010) -[2023-11-28 03:41:56,117][87424] Updated weights for policy 0, policy_version 133206 (0.0008) -[2023-11-28 03:41:56,225][87426] Updated weights for policy 1, policy_version 132940 (0.0011) -[2023-11-28 03:41:56,495][87424] Updated weights for policy 0, policy_version 133216 (0.0009) -[2023-11-28 03:41:56,614][87426] Updated weights for policy 1, policy_version 132950 (0.0012) -[2023-11-28 03:41:56,993][87426] Updated weights for policy 1, policy_version 132960 (0.0011) -[2023-11-28 03:41:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 68141056. Throughput: 0: 2648.4, 1: 2702.5. Samples: 68158548. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:41:58,445][86177] Avg episode reward: [(0, '-496.200'), (1, '-523.260')] -[2023-11-28 03:41:58,554][87424] Updated weights for policy 0, policy_version 133226 (0.0010) -[2023-11-28 03:41:58,939][87424] Updated weights for policy 0, policy_version 133236 (0.0011) -[2023-11-28 03:41:58,955][87426] Updated weights for policy 1, policy_version 132970 (0.0008) -[2023-11-28 03:41:59,319][87424] Updated weights for policy 0, policy_version 133246 (0.0011) -[2023-11-28 03:41:59,337][87426] Updated weights for policy 1, policy_version 132980 (0.0007) -[2023-11-28 03:41:59,725][87426] Updated weights for policy 1, policy_version 132990 (0.0007) -[2023-11-28 03:42:01,698][87424] Updated weights for policy 0, policy_version 133256 (0.0010) -[2023-11-28 03:42:01,908][87426] Updated weights for policy 1, policy_version 133000 (0.0011) -[2023-11-28 03:42:02,085][87424] Updated weights for policy 0, policy_version 133266 (0.0010) -[2023-11-28 03:42:02,290][87426] Updated weights for policy 1, policy_version 133010 (0.0009) -[2023-11-28 03:42:02,473][87424] Updated weights for policy 0, policy_version 133276 (0.0011) -[2023-11-28 03:42:02,674][87426] Updated weights for policy 1, policy_version 133020 (0.0011) -[2023-11-28 03:42:03,444][86177] Fps is (10 sec: 5737.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68173824. Throughput: 0: 2651.8, 1: 2727.9. Samples: 68183520. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:42:03,445][86177] Avg episode reward: [(0, '-492.980'), (1, '-525.210')] -[2023-11-28 03:42:04,187][87424] Updated weights for policy 0, policy_version 133286 (0.0011) -[2023-11-28 03:42:04,566][87424] Updated weights for policy 0, policy_version 133296 (0.0012) -[2023-11-28 03:42:04,949][87424] Updated weights for policy 0, policy_version 133306 (0.0010) -[2023-11-28 03:42:05,212][87426] Updated weights for policy 1, policy_version 133030 (0.0010) -[2023-11-28 03:42:05,590][87426] Updated weights for policy 1, policy_version 133040 (0.0010) -[2023-11-28 03:42:05,978][87426] Updated weights for policy 1, policy_version 133050 (0.0011) -[2023-11-28 03:42:06,812][87424] Updated weights for policy 0, policy_version 133316 (0.0011) -[2023-11-28 03:42:07,193][87424] Updated weights for policy 0, policy_version 133326 (0.0012) -[2023-11-28 03:42:07,574][87424] Updated weights for policy 0, policy_version 133336 (0.0012) -[2023-11-28 03:42:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 68198400. Throughput: 0: 2638.2, 1: 2728.9. Samples: 68214968. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:42:08,445][86177] Avg episode reward: [(0, '-493.730'), (1, '-550.690')] -[2023-11-28 03:42:08,506][87426] Updated weights for policy 1, policy_version 133060 (0.0012) -[2023-11-28 03:42:08,883][87426] Updated weights for policy 1, policy_version 133070 (0.0012) -[2023-11-28 03:42:09,259][87426] Updated weights for policy 1, policy_version 133080 (0.0012) -[2023-11-28 03:42:09,726][87424] Updated weights for policy 0, policy_version 133346 (0.0012) -[2023-11-28 03:42:10,110][87424] Updated weights for policy 0, policy_version 133356 (0.0012) -[2023-11-28 03:42:10,481][87424] Updated weights for policy 0, policy_version 133366 (0.0012) -[2023-11-28 03:42:10,858][87424] Updated weights for policy 0, policy_version 133376 (0.0012) -[2023-11-28 03:42:11,308][87426] Updated weights for policy 1, policy_version 133090 (0.0012) -[2023-11-28 03:42:11,681][87426] Updated weights for policy 1, policy_version 133100 (0.0012) -[2023-11-28 03:42:12,060][87426] Updated weights for policy 1, policy_version 133110 (0.0010) -[2023-11-28 03:42:12,439][87426] Updated weights for policy 1, policy_version 133120 (0.0011) -[2023-11-28 03:42:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 68222976. Throughput: 0: 2662.5, 1: 2706.5. Samples: 68240580. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:42:13,445][86177] Avg episode reward: [(0, '-495.170'), (1, '-547.600')] -[2023-11-28 03:42:13,480][87424] Updated weights for policy 0, policy_version 133386 (0.0011) -[2023-11-28 03:42:13,882][87424] Updated weights for policy 0, policy_version 133396 (0.0008) -[2023-11-28 03:42:14,259][87424] Updated weights for policy 0, policy_version 133406 (0.0010) -[2023-11-28 03:42:14,264][87426] Updated weights for policy 1, policy_version 133130 (0.0007) -[2023-11-28 03:42:14,645][87426] Updated weights for policy 1, policy_version 133140 (0.0008) -[2023-11-28 03:42:15,020][87426] Updated weights for policy 1, policy_version 133150 (0.0008) -[2023-11-28 03:42:16,343][87424] Updated weights for policy 0, policy_version 133416 (0.0012) -[2023-11-28 03:42:16,729][87424] Updated weights for policy 0, policy_version 133426 (0.0012) -[2023-11-28 03:42:17,120][87424] Updated weights for policy 0, policy_version 133436 (0.0012) -[2023-11-28 03:42:17,377][87426] Updated weights for policy 1, policy_version 133160 (0.0012) -[2023-11-28 03:42:17,756][87426] Updated weights for policy 1, policy_version 133170 (0.0012) -[2023-11-28 03:42:18,127][87426] Updated weights for policy 1, policy_version 133180 (0.0011) -[2023-11-28 03:42:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68255744. Throughput: 0: 2681.9, 1: 2699.0. Samples: 68264864. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:42:18,446][86177] Avg episode reward: [(0, '-492.960'), (1, '-534.170')] -[2023-11-28 03:42:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000133440_34160640.pth... -[2023-11-28 03:42:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000133184_34095104.pth... -[2023-11-28 03:42:18,510][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000130624_33439744.pth -[2023-11-28 03:42:18,511][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000130912_33513472.pth -[2023-11-28 03:42:19,355][87424] Updated weights for policy 0, policy_version 133446 (0.0010) -[2023-11-28 03:42:19,744][87424] Updated weights for policy 0, policy_version 133456 (0.0011) -[2023-11-28 03:42:20,130][87424] Updated weights for policy 0, policy_version 133466 (0.0010) -[2023-11-28 03:42:20,562][87426] Updated weights for policy 1, policy_version 133190 (0.0011) -[2023-11-28 03:42:20,949][87426] Updated weights for policy 1, policy_version 133200 (0.0010) -[2023-11-28 03:42:21,324][87426] Updated weights for policy 1, policy_version 133210 (0.0010) -[2023-11-28 03:42:22,349][87424] Updated weights for policy 0, policy_version 133476 (0.0010) -[2023-11-28 03:42:22,728][87424] Updated weights for policy 0, policy_version 133486 (0.0012) -[2023-11-28 03:42:23,108][87424] Updated weights for policy 0, policy_version 133496 (0.0012) -[2023-11-28 03:42:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68280320. Throughput: 0: 2674.6, 1: 2716.1. Samples: 68297324. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:42:23,445][86177] Avg episode reward: [(0, '-493.190'), (1, '-579.500')] -[2023-11-28 03:42:23,565][87426] Updated weights for policy 1, policy_version 133220 (0.0012) -[2023-11-28 03:42:23,938][87426] Updated weights for policy 1, policy_version 133230 (0.0011) -[2023-11-28 03:42:24,318][87426] Updated weights for policy 1, policy_version 133240 (0.0008) -[2023-11-28 03:42:25,366][87424] Updated weights for policy 0, policy_version 133506 (0.0012) -[2023-11-28 03:42:25,756][87424] Updated weights for policy 0, policy_version 133516 (0.0012) -[2023-11-28 03:42:26,136][87424] Updated weights for policy 0, policy_version 133526 (0.0012) -[2023-11-28 03:42:26,514][87426] Updated weights for policy 1, policy_version 133250 (0.0008) -[2023-11-28 03:42:26,520][87424] Updated weights for policy 0, policy_version 133536 (0.0012) -[2023-11-28 03:42:26,883][87426] Updated weights for policy 1, policy_version 133260 (0.0010) -[2023-11-28 03:42:27,262][87426] Updated weights for policy 1, policy_version 133270 (0.0009) -[2023-11-28 03:42:27,634][87426] Updated weights for policy 1, policy_version 133280 (0.0008) -[2023-11-28 03:42:28,297][87424] Updated weights for policy 0, policy_version 133546 (0.0008) -[2023-11-28 03:42:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 68304896. Throughput: 0: 2681.9, 1: 2709.7. Samples: 68321624. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:42:28,445][86177] Avg episode reward: [(0, '-494.610'), (1, '-567.660')] -[2023-11-28 03:42:28,690][87424] Updated weights for policy 0, policy_version 133556 (0.0007) -[2023-11-28 03:42:29,074][87424] Updated weights for policy 0, policy_version 133566 (0.0008) -[2023-11-28 03:42:29,608][87426] Updated weights for policy 1, policy_version 133290 (0.0012) -[2023-11-28 03:42:29,979][87426] Updated weights for policy 1, policy_version 133300 (0.0012) -[2023-11-28 03:42:30,367][87426] Updated weights for policy 1, policy_version 133310 (0.0012) -[2023-11-28 03:42:31,115][87424] Updated weights for policy 0, policy_version 133576 (0.0011) -[2023-11-28 03:42:31,482][87424] Updated weights for policy 0, policy_version 133586 (0.0012) -[2023-11-28 03:42:31,872][87424] Updated weights for policy 0, policy_version 133596 (0.0012) -[2023-11-28 03:42:32,355][87426] Updated weights for policy 1, policy_version 133320 (0.0009) -[2023-11-28 03:42:32,746][87426] Updated weights for policy 1, policy_version 133330 (0.0011) -[2023-11-28 03:42:33,125][87426] Updated weights for policy 1, policy_version 133340 (0.0008) -[2023-11-28 03:42:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68337664. Throughput: 0: 2716.9, 1: 2705.3. Samples: 68346648. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:42:33,445][86177] Avg episode reward: [(0, '-498.320'), (1, '-570.240')] -[2023-11-28 03:42:33,901][87424] Updated weights for policy 0, policy_version 133606 (0.0012) -[2023-11-28 03:42:34,287][87424] Updated weights for policy 0, policy_version 133616 (0.0012) -[2023-11-28 03:42:34,674][87424] Updated weights for policy 0, policy_version 133626 (0.0011) -[2023-11-28 03:42:34,757][87426] Updated weights for policy 1, policy_version 133350 (0.0009) -[2023-11-28 03:42:35,144][87426] Updated weights for policy 1, policy_version 133360 (0.0009) -[2023-11-28 03:42:35,520][87426] Updated weights for policy 1, policy_version 133370 (0.0008) -[2023-11-28 03:42:36,401][87424] Updated weights for policy 0, policy_version 133636 (0.0009) -[2023-11-28 03:42:36,779][87424] Updated weights for policy 0, policy_version 133646 (0.0008) -[2023-11-28 03:42:37,159][87424] Updated weights for policy 0, policy_version 133656 (0.0008) -[2023-11-28 03:42:38,055][87426] Updated weights for policy 1, policy_version 133380 (0.0007) -[2023-11-28 03:42:38,435][87426] Updated weights for policy 1, policy_version 133390 (0.0007) -[2023-11-28 03:42:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68362240. Throughput: 0: 2754.2, 1: 2721.4. Samples: 68380232. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:42:38,445][86177] Avg episode reward: [(0, '-497.350'), (1, '-567.790')] -[2023-11-28 03:42:38,813][87426] Updated weights for policy 1, policy_version 133400 (0.0007) -[2023-11-28 03:42:39,352][87424] Updated weights for policy 0, policy_version 133666 (0.0009) -[2023-11-28 03:42:39,730][87424] Updated weights for policy 0, policy_version 133676 (0.0012) -[2023-11-28 03:42:40,112][87424] Updated weights for policy 0, policy_version 133686 (0.0012) -[2023-11-28 03:42:40,483][87424] Updated weights for policy 0, policy_version 133696 (0.0011) -[2023-11-28 03:42:41,234][87426] Updated weights for policy 1, policy_version 133410 (0.0011) -[2023-11-28 03:42:41,616][87426] Updated weights for policy 1, policy_version 133420 (0.0009) -[2023-11-28 03:42:41,989][87426] Updated weights for policy 1, policy_version 133430 (0.0009) -[2023-11-28 03:42:42,367][87426] Updated weights for policy 1, policy_version 133440 (0.0012) -[2023-11-28 03:42:43,021][87424] Updated weights for policy 0, policy_version 133706 (0.0010) -[2023-11-28 03:42:43,397][87424] Updated weights for policy 0, policy_version 133716 (0.0011) -[2023-11-28 03:42:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68386816. Throughput: 0: 2770.8, 1: 2678.9. Samples: 68403784. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:42:43,445][86177] Avg episode reward: [(0, '-497.580'), (1, '-499.910')] -[2023-11-28 03:42:43,781][87424] Updated weights for policy 0, policy_version 133726 (0.0007) -[2023-11-28 03:42:44,955][87426] Updated weights for policy 1, policy_version 133450 (0.0011) -[2023-11-28 03:42:45,340][87426] Updated weights for policy 1, policy_version 133460 (0.0012) -[2023-11-28 03:42:45,564][87424] Updated weights for policy 0, policy_version 133736 (0.0008) -[2023-11-28 03:42:45,717][87426] Updated weights for policy 1, policy_version 133470 (0.0011) -[2023-11-28 03:42:45,944][87424] Updated weights for policy 0, policy_version 133746 (0.0007) -[2023-11-28 03:42:46,325][87424] Updated weights for policy 0, policy_version 133756 (0.0008) -[2023-11-28 03:42:47,520][87426] Updated weights for policy 1, policy_version 133480 (0.0012) -[2023-11-28 03:42:47,903][87426] Updated weights for policy 1, policy_version 133490 (0.0008) -[2023-11-28 03:42:48,280][87426] Updated weights for policy 1, policy_version 133500 (0.0007) -[2023-11-28 03:42:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68419584. Throughput: 0: 2779.9, 1: 2657.4. Samples: 68428200. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:42:48,445][86177] Avg episode reward: [(0, '-496.040'), (1, '-502.420')] -[2023-11-28 03:42:48,493][87424] Updated weights for policy 0, policy_version 133766 (0.0010) -[2023-11-28 03:42:48,872][87424] Updated weights for policy 0, policy_version 133776 (0.0011) -[2023-11-28 03:42:49,250][87424] Updated weights for policy 0, policy_version 133786 (0.0011) -[2023-11-28 03:42:50,591][87426] Updated weights for policy 1, policy_version 133510 (0.0010) -[2023-11-28 03:42:50,970][87426] Updated weights for policy 1, policy_version 133520 (0.0012) -[2023-11-28 03:42:51,339][87424] Updated weights for policy 0, policy_version 133796 (0.0010) -[2023-11-28 03:42:51,350][87426] Updated weights for policy 1, policy_version 133530 (0.0012) -[2023-11-28 03:42:51,716][87424] Updated weights for policy 0, policy_version 133806 (0.0008) -[2023-11-28 03:42:52,098][87424] Updated weights for policy 0, policy_version 133816 (0.0008) -[2023-11-28 03:42:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.8, 300 sec: 5442.8). Total num frames: 68444160. Throughput: 0: 2806.8, 1: 2665.5. Samples: 68461224. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:42:53,445][86177] Avg episode reward: [(0, '-500.190'), (1, '-512.030')] -[2023-11-28 03:42:53,905][87426] Updated weights for policy 1, policy_version 133540 (0.0011) -[2023-11-28 03:42:54,201][87424] Updated weights for policy 0, policy_version 133826 (0.0011) -[2023-11-28 03:42:54,285][87426] Updated weights for policy 1, policy_version 133550 (0.0012) -[2023-11-28 03:42:54,579][87424] Updated weights for policy 0, policy_version 133836 (0.0008) -[2023-11-28 03:42:54,668][87426] Updated weights for policy 1, policy_version 133560 (0.0009) -[2023-11-28 03:42:54,966][87424] Updated weights for policy 0, policy_version 133846 (0.0008) -[2023-11-28 03:42:55,344][87424] Updated weights for policy 0, policy_version 133856 (0.0007) -[2023-11-28 03:42:56,375][87426] Updated weights for policy 1, policy_version 133570 (0.0008) -[2023-11-28 03:42:56,752][87426] Updated weights for policy 1, policy_version 133580 (0.0010) -[2023-11-28 03:42:57,136][87426] Updated weights for policy 1, policy_version 133590 (0.0008) -[2023-11-28 03:42:57,411][87424] Updated weights for policy 0, policy_version 133866 (0.0009) -[2023-11-28 03:42:57,513][87426] Updated weights for policy 1, policy_version 133600 (0.0007) -[2023-11-28 03:42:57,792][87424] Updated weights for policy 0, policy_version 133876 (0.0007) -[2023-11-28 03:42:58,173][87424] Updated weights for policy 0, policy_version 133886 (0.0007) -[2023-11-28 03:42:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 68476928. Throughput: 0: 2786.0, 1: 2674.2. Samples: 68486288. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:42:58,445][86177] Avg episode reward: [(0, '-498.280'), (1, '-531.260')] -[2023-11-28 03:42:59,926][87426] Updated weights for policy 1, policy_version 133610 (0.0012) -[2023-11-28 03:43:00,299][87426] Updated weights for policy 1, policy_version 133620 (0.0008) -[2023-11-28 03:43:00,440][87424] Updated weights for policy 0, policy_version 133896 (0.0009) -[2023-11-28 03:43:00,681][87426] Updated weights for policy 1, policy_version 133630 (0.0012) -[2023-11-28 03:43:00,819][87424] Updated weights for policy 0, policy_version 133906 (0.0012) -[2023-11-28 03:43:01,205][87424] Updated weights for policy 0, policy_version 133916 (0.0011) -[2023-11-28 03:43:03,101][87426] Updated weights for policy 1, policy_version 133640 (0.0011) -[2023-11-28 03:43:03,231][87424] Updated weights for policy 0, policy_version 133926 (0.0009) -[2023-11-28 03:43:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 68493312. Throughput: 0: 2800.2, 1: 2677.8. Samples: 68511372. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:43:03,446][86177] Avg episode reward: [(0, '-496.150'), (1, '-529.160')] -[2023-11-28 03:43:03,484][87426] Updated weights for policy 1, policy_version 133650 (0.0008) -[2023-11-28 03:43:03,616][87424] Updated weights for policy 0, policy_version 133936 (0.0011) -[2023-11-28 03:43:03,860][87426] Updated weights for policy 1, policy_version 133660 (0.0008) -[2023-11-28 03:43:03,997][87424] Updated weights for policy 0, policy_version 133946 (0.0011) -[2023-11-28 03:43:05,782][87426] Updated weights for policy 1, policy_version 133670 (0.0012) -[2023-11-28 03:43:05,992][87424] Updated weights for policy 0, policy_version 133956 (0.0012) -[2023-11-28 03:43:06,162][87426] Updated weights for policy 1, policy_version 133680 (0.0010) -[2023-11-28 03:43:06,374][87424] Updated weights for policy 0, policy_version 133966 (0.0012) -[2023-11-28 03:43:06,549][87426] Updated weights for policy 1, policy_version 133690 (0.0009) -[2023-11-28 03:43:06,746][87424] Updated weights for policy 0, policy_version 133976 (0.0010) -[2023-11-28 03:43:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68526080. Throughput: 0: 2820.7, 1: 2673.2. Samples: 68544552. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:43:08,445][86177] Avg episode reward: [(0, '-496.120'), (1, '-527.700')] -[2023-11-28 03:43:08,572][87424] Updated weights for policy 0, policy_version 133986 (0.0012) -[2023-11-28 03:43:08,776][87426] Updated weights for policy 1, policy_version 133700 (0.0011) -[2023-11-28 03:43:08,958][87424] Updated weights for policy 0, policy_version 133996 (0.0010) -[2023-11-28 03:43:09,153][87426] Updated weights for policy 1, policy_version 133710 (0.0012) -[2023-11-28 03:43:09,341][87424] Updated weights for policy 0, policy_version 134006 (0.0011) -[2023-11-28 03:43:09,528][87426] Updated weights for policy 1, policy_version 133720 (0.0011) -[2023-11-28 03:43:09,721][87424] Updated weights for policy 0, policy_version 134016 (0.0011) -[2023-11-28 03:43:11,570][87426] Updated weights for policy 1, policy_version 133730 (0.0012) -[2023-11-28 03:43:11,950][87426] Updated weights for policy 1, policy_version 133740 (0.0011) -[2023-11-28 03:43:12,217][87424] Updated weights for policy 0, policy_version 134026 (0.0011) -[2023-11-28 03:43:12,329][87426] Updated weights for policy 1, policy_version 133750 (0.0011) -[2023-11-28 03:43:12,598][87424] Updated weights for policy 0, policy_version 134036 (0.0011) -[2023-11-28 03:43:12,699][87426] Updated weights for policy 1, policy_version 133760 (0.0009) -[2023-11-28 03:43:12,987][87424] Updated weights for policy 0, policy_version 134046 (0.0012) -[2023-11-28 03:43:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 68558848. Throughput: 0: 2813.9, 1: 2687.7. Samples: 68569196. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:43:13,445][86177] Avg episode reward: [(0, '-493.150'), (1, '-539.050')] -[2023-11-28 03:43:14,684][87426] Updated weights for policy 1, policy_version 133770 (0.0008) -[2023-11-28 03:43:14,949][87424] Updated weights for policy 0, policy_version 134056 (0.0010) -[2023-11-28 03:43:15,069][87426] Updated weights for policy 1, policy_version 133780 (0.0011) -[2023-11-28 03:43:15,326][87424] Updated weights for policy 0, policy_version 134066 (0.0011) -[2023-11-28 03:43:15,437][87426] Updated weights for policy 1, policy_version 133790 (0.0011) -[2023-11-28 03:43:15,707][87424] Updated weights for policy 0, policy_version 134076 (0.0009) -[2023-11-28 03:43:17,520][87426] Updated weights for policy 1, policy_version 133800 (0.0012) -[2023-11-28 03:43:17,903][87426] Updated weights for policy 1, policy_version 133810 (0.0007) -[2023-11-28 03:43:18,123][87424] Updated weights for policy 0, policy_version 134086 (0.0007) -[2023-11-28 03:43:18,286][87426] Updated weights for policy 1, policy_version 133820 (0.0007) -[2023-11-28 03:43:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 68583424. Throughput: 0: 2809.9, 1: 2702.1. Samples: 68594688. Policy #0 lag: (min: 28.0, avg: 53.8, max: 62.0) -[2023-11-28 03:43:18,445][86177] Avg episode reward: [(0, '-497.540'), (1, '-528.140')] -[2023-11-28 03:43:18,502][87424] Updated weights for policy 0, policy_version 134096 (0.0007) -[2023-11-28 03:43:18,886][87424] Updated weights for policy 0, policy_version 134106 (0.0008) -[2023-11-28 03:43:20,052][87426] Updated weights for policy 1, policy_version 133830 (0.0009) -[2023-11-28 03:43:20,422][87426] Updated weights for policy 1, policy_version 133840 (0.0011) -[2023-11-28 03:43:20,561][87424] Updated weights for policy 0, policy_version 134116 (0.0010) -[2023-11-28 03:43:20,803][87426] Updated weights for policy 1, policy_version 133850 (0.0010) -[2023-11-28 03:43:20,926][87424] Updated weights for policy 0, policy_version 134126 (0.0010) -[2023-11-28 03:43:21,312][87424] Updated weights for policy 0, policy_version 134136 (0.0012) -[2023-11-28 03:43:23,282][87426] Updated weights for policy 1, policy_version 133860 (0.0011) -[2023-11-28 03:43:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68608000. Throughput: 0: 2777.8, 1: 2719.0. Samples: 68627588. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:43:23,445][86177] Avg episode reward: [(0, '-499.120'), (1, '-539.210')] -[2023-11-28 03:43:23,658][87426] Updated weights for policy 1, policy_version 133870 (0.0012) -[2023-11-28 03:43:23,796][87424] Updated weights for policy 0, policy_version 134146 (0.0011) -[2023-11-28 03:43:24,034][87426] Updated weights for policy 1, policy_version 133880 (0.0011) -[2023-11-28 03:43:24,178][87424] Updated weights for policy 0, policy_version 134156 (0.0011) -[2023-11-28 03:43:24,554][87424] Updated weights for policy 0, policy_version 134166 (0.0012) -[2023-11-28 03:43:24,930][87424] Updated weights for policy 0, policy_version 134176 (0.0012) -[2023-11-28 03:43:25,871][87426] Updated weights for policy 1, policy_version 133890 (0.0010) -[2023-11-28 03:43:26,246][87426] Updated weights for policy 1, policy_version 133900 (0.0012) -[2023-11-28 03:43:26,625][87426] Updated weights for policy 1, policy_version 133910 (0.0012) -[2023-11-28 03:43:26,996][87426] Updated weights for policy 1, policy_version 133920 (0.0012) -[2023-11-28 03:43:27,400][87424] Updated weights for policy 0, policy_version 134186 (0.0012) -[2023-11-28 03:43:27,780][87424] Updated weights for policy 0, policy_version 134196 (0.0012) -[2023-11-28 03:43:28,152][87424] Updated weights for policy 0, policy_version 134206 (0.0012) -[2023-11-28 03:43:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 68640768. Throughput: 0: 2760.7, 1: 2748.2. Samples: 68651684. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:43:28,445][86177] Avg episode reward: [(0, '-498.040'), (1, '-539.940')] -[2023-11-28 03:43:29,225][87426] Updated weights for policy 1, policy_version 133930 (0.0012) -[2023-11-28 03:43:29,599][87426] Updated weights for policy 1, policy_version 133940 (0.0012) -[2023-11-28 03:43:29,956][87424] Updated weights for policy 0, policy_version 134216 (0.0012) -[2023-11-28 03:43:29,981][87426] Updated weights for policy 1, policy_version 133950 (0.0011) -[2023-11-28 03:43:30,340][87424] Updated weights for policy 0, policy_version 134226 (0.0012) -[2023-11-28 03:43:30,726][87424] Updated weights for policy 0, policy_version 134236 (0.0012) -[2023-11-28 03:43:32,461][87424] Updated weights for policy 0, policy_version 134246 (0.0011) -[2023-11-28 03:43:32,542][87426] Updated weights for policy 1, policy_version 133960 (0.0011) -[2023-11-28 03:43:32,839][87424] Updated weights for policy 0, policy_version 134256 (0.0012) -[2023-11-28 03:43:32,927][87426] Updated weights for policy 1, policy_version 133970 (0.0011) -[2023-11-28 03:43:33,220][87424] Updated weights for policy 0, policy_version 134266 (0.0012) -[2023-11-28 03:43:33,298][87426] Updated weights for policy 1, policy_version 133980 (0.0012) -[2023-11-28 03:43:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 68657152. Throughput: 0: 2760.6, 1: 2742.3. Samples: 68675832. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:43:33,445][86177] Avg episode reward: [(0, '-502.530'), (1, '-526.660')] -[2023-11-28 03:43:35,549][87426] Updated weights for policy 1, policy_version 133990 (0.0010) -[2023-11-28 03:43:35,851][87424] Updated weights for policy 0, policy_version 134276 (0.0011) -[2023-11-28 03:43:35,923][87426] Updated weights for policy 1, policy_version 134000 (0.0010) -[2023-11-28 03:43:36,228][87424] Updated weights for policy 0, policy_version 134286 (0.0010) -[2023-11-28 03:43:36,306][87426] Updated weights for policy 1, policy_version 134010 (0.0011) -[2023-11-28 03:43:36,609][87424] Updated weights for policy 0, policy_version 134296 (0.0010) -[2023-11-28 03:43:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68689920. Throughput: 0: 2739.7, 1: 2749.8. Samples: 68708252. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:43:38,445][86177] Avg episode reward: [(0, '-503.550'), (1, '-533.870')] -[2023-11-28 03:43:38,531][87426] Updated weights for policy 1, policy_version 134020 (0.0010) -[2023-11-28 03:43:38,604][87424] Updated weights for policy 0, policy_version 134306 (0.0011) -[2023-11-28 03:43:38,916][87426] Updated weights for policy 1, policy_version 134030 (0.0010) -[2023-11-28 03:43:38,989][87424] Updated weights for policy 0, policy_version 134316 (0.0011) -[2023-11-28 03:43:39,294][87426] Updated weights for policy 1, policy_version 134040 (0.0011) -[2023-11-28 03:43:39,360][87424] Updated weights for policy 0, policy_version 134326 (0.0010) -[2023-11-28 03:43:39,742][87424] Updated weights for policy 0, policy_version 134336 (0.0011) -[2023-11-28 03:43:41,369][87426] Updated weights for policy 1, policy_version 134050 (0.0012) -[2023-11-28 03:43:41,741][87426] Updated weights for policy 1, policy_version 134060 (0.0012) -[2023-11-28 03:43:41,941][87424] Updated weights for policy 0, policy_version 134346 (0.0012) -[2023-11-28 03:43:42,119][87426] Updated weights for policy 1, policy_version 134070 (0.0011) -[2023-11-28 03:43:42,323][87424] Updated weights for policy 0, policy_version 134356 (0.0012) -[2023-11-28 03:43:42,496][87426] Updated weights for policy 1, policy_version 134080 (0.0011) -[2023-11-28 03:43:42,707][87424] Updated weights for policy 0, policy_version 134366 (0.0012) -[2023-11-28 03:43:43,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 68722688. Throughput: 0: 2746.0, 1: 2752.9. Samples: 68733736. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:43:43,445][86177] Avg episode reward: [(0, '-499.830'), (1, '-524.990')] -[2023-11-28 03:43:44,653][87426] Updated weights for policy 1, policy_version 134090 (0.0012) -[2023-11-28 03:43:44,909][87424] Updated weights for policy 0, policy_version 134376 (0.0011) -[2023-11-28 03:43:45,029][87426] Updated weights for policy 1, policy_version 134100 (0.0012) -[2023-11-28 03:43:45,282][87424] Updated weights for policy 0, policy_version 134386 (0.0011) -[2023-11-28 03:43:45,402][87426] Updated weights for policy 1, policy_version 134110 (0.0011) -[2023-11-28 03:43:45,667][87424] Updated weights for policy 0, policy_version 134396 (0.0012) -[2023-11-28 03:43:47,461][87426] Updated weights for policy 1, policy_version 134120 (0.0011) -[2023-11-28 03:43:47,832][87426] Updated weights for policy 1, policy_version 134130 (0.0010) -[2023-11-28 03:43:48,009][87424] Updated weights for policy 0, policy_version 134406 (0.0009) -[2023-11-28 03:43:48,209][87426] Updated weights for policy 1, policy_version 134140 (0.0011) -[2023-11-28 03:43:48,391][87424] Updated weights for policy 0, policy_version 134416 (0.0008) -[2023-11-28 03:43:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 68747264. Throughput: 0: 2729.4, 1: 2743.4. Samples: 68757648. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:43:48,446][86177] Avg episode reward: [(0, '-502.170'), (1, '-526.980')] -[2023-11-28 03:43:48,778][87424] Updated weights for policy 0, policy_version 134426 (0.0007) -[2023-11-28 03:43:50,178][87426] Updated weights for policy 1, policy_version 134150 (0.0011) -[2023-11-28 03:43:50,555][87426] Updated weights for policy 1, policy_version 134160 (0.0010) -[2023-11-28 03:43:50,939][87426] Updated weights for policy 1, policy_version 134170 (0.0011) -[2023-11-28 03:43:51,074][87424] Updated weights for policy 0, policy_version 134436 (0.0011) -[2023-11-28 03:43:51,458][87424] Updated weights for policy 0, policy_version 134446 (0.0010) -[2023-11-28 03:43:51,838][87424] Updated weights for policy 0, policy_version 134456 (0.0011) -[2023-11-28 03:43:53,362][87426] Updated weights for policy 1, policy_version 134180 (0.0011) -[2023-11-28 03:43:53,448][86177] Fps is (10 sec: 4913.3, 60 sec: 5461.0, 300 sec: 5442.8). Total num frames: 68771840. Throughput: 0: 2708.6, 1: 2756.1. Samples: 68790484. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:43:53,449][86177] Avg episode reward: [(0, '-496.430'), (1, '-523.090')] -[2023-11-28 03:43:53,746][87426] Updated weights for policy 1, policy_version 134190 (0.0010) -[2023-11-28 03:43:54,116][87426] Updated weights for policy 1, policy_version 134200 (0.0007) -[2023-11-28 03:43:54,181][87424] Updated weights for policy 0, policy_version 134466 (0.0010) -[2023-11-28 03:43:54,566][87424] Updated weights for policy 0, policy_version 134476 (0.0009) -[2023-11-28 03:43:54,948][87424] Updated weights for policy 0, policy_version 134486 (0.0008) -[2023-11-28 03:43:55,327][87424] Updated weights for policy 0, policy_version 134496 (0.0007) -[2023-11-28 03:43:56,501][87426] Updated weights for policy 1, policy_version 134210 (0.0008) -[2023-11-28 03:43:56,878][87426] Updated weights for policy 1, policy_version 134220 (0.0012) -[2023-11-28 03:43:56,979][87424] Updated weights for policy 0, policy_version 134506 (0.0010) -[2023-11-28 03:43:57,254][87426] Updated weights for policy 1, policy_version 134230 (0.0012) -[2023-11-28 03:43:57,360][87424] Updated weights for policy 0, policy_version 134516 (0.0010) -[2023-11-28 03:43:57,632][87426] Updated weights for policy 1, policy_version 134240 (0.0011) -[2023-11-28 03:43:57,748][87424] Updated weights for policy 0, policy_version 134526 (0.0011) -[2023-11-28 03:43:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 68804608. Throughput: 0: 2704.6, 1: 2752.7. Samples: 68814776. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:43:58,445][86177] Avg episode reward: [(0, '-494.860'), (1, '-519.390')] -[2023-11-28 03:43:59,553][87426] Updated weights for policy 1, policy_version 134250 (0.0011) -[2023-11-28 03:43:59,799][87424] Updated weights for policy 0, policy_version 134536 (0.0012) -[2023-11-28 03:43:59,925][87426] Updated weights for policy 1, policy_version 134260 (0.0009) -[2023-11-28 03:44:00,184][87424] Updated weights for policy 0, policy_version 134546 (0.0012) -[2023-11-28 03:44:00,311][87426] Updated weights for policy 1, policy_version 134270 (0.0011) -[2023-11-28 03:44:00,567][87424] Updated weights for policy 0, policy_version 134556 (0.0010) -[2023-11-28 03:44:02,341][87426] Updated weights for policy 1, policy_version 134280 (0.0012) -[2023-11-28 03:44:02,715][87426] Updated weights for policy 1, policy_version 134290 (0.0010) -[2023-11-28 03:44:02,895][87424] Updated weights for policy 0, policy_version 134566 (0.0011) -[2023-11-28 03:44:03,094][87426] Updated weights for policy 1, policy_version 134300 (0.0008) -[2023-11-28 03:44:03,275][87424] Updated weights for policy 0, policy_version 134576 (0.0012) -[2023-11-28 03:44:03,444][86177] Fps is (10 sec: 5736.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 68829184. Throughput: 0: 2708.0, 1: 2757.9. Samples: 68840652. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:44:03,445][86177] Avg episode reward: [(0, '-493.750'), (1, '-558.090')] -[2023-11-28 03:44:03,645][87424] Updated weights for policy 0, policy_version 134586 (0.0011) -[2023-11-28 03:44:05,235][87426] Updated weights for policy 1, policy_version 134310 (0.0010) -[2023-11-28 03:44:05,626][87426] Updated weights for policy 1, policy_version 134320 (0.0011) -[2023-11-28 03:44:05,885][87424] Updated weights for policy 0, policy_version 134596 (0.0009) -[2023-11-28 03:44:05,997][87426] Updated weights for policy 1, policy_version 134330 (0.0011) -[2023-11-28 03:44:06,262][87424] Updated weights for policy 0, policy_version 134606 (0.0011) -[2023-11-28 03:44:06,650][87424] Updated weights for policy 0, policy_version 134616 (0.0012) -[2023-11-28 03:44:08,232][87426] Updated weights for policy 1, policy_version 134340 (0.0010) -[2023-11-28 03:44:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68853760. Throughput: 0: 2711.6, 1: 2737.1. Samples: 68872780. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:44:08,445][86177] Avg episode reward: [(0, '-490.460'), (1, '-556.690')] -[2023-11-28 03:44:08,612][87426] Updated weights for policy 1, policy_version 134350 (0.0008) -[2023-11-28 03:44:08,927][87424] Updated weights for policy 0, policy_version 134626 (0.0011) -[2023-11-28 03:44:08,992][87426] Updated weights for policy 1, policy_version 134360 (0.0008) -[2023-11-28 03:44:09,316][87424] Updated weights for policy 0, policy_version 134636 (0.0010) -[2023-11-28 03:44:09,704][87424] Updated weights for policy 0, policy_version 134646 (0.0012) -[2023-11-28 03:44:10,074][87424] Updated weights for policy 0, policy_version 134656 (0.0011) -[2023-11-28 03:44:11,048][87426] Updated weights for policy 1, policy_version 134370 (0.0009) -[2023-11-28 03:44:11,424][87426] Updated weights for policy 1, policy_version 134380 (0.0007) -[2023-11-28 03:44:11,821][87426] Updated weights for policy 1, policy_version 134390 (0.0010) -[2023-11-28 03:44:12,228][87426] Updated weights for policy 1, policy_version 134400 (0.0011) -[2023-11-28 03:44:12,659][87424] Updated weights for policy 0, policy_version 134666 (0.0012) -[2023-11-28 03:44:13,042][87424] Updated weights for policy 0, policy_version 134676 (0.0012) -[2023-11-28 03:44:13,438][87424] Updated weights for policy 0, policy_version 134686 (0.0010) -[2023-11-28 03:44:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 68878336. Throughput: 0: 2718.2, 1: 2715.0. Samples: 68896180. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:44:13,445][86177] Avg episode reward: [(0, '-491.630'), (1, '-609.070')] -[2023-11-28 03:44:14,684][87426] Updated weights for policy 1, policy_version 134410 (0.0008) -[2023-11-28 03:44:15,061][87426] Updated weights for policy 1, policy_version 134420 (0.0011) -[2023-11-28 03:44:15,446][87426] Updated weights for policy 1, policy_version 134430 (0.0011) -[2023-11-28 03:44:15,709][87424] Updated weights for policy 0, policy_version 134696 (0.0011) -[2023-11-28 03:44:16,086][87424] Updated weights for policy 0, policy_version 134706 (0.0011) -[2023-11-28 03:44:16,470][87424] Updated weights for policy 0, policy_version 134716 (0.0012) -[2023-11-28 03:44:17,519][87426] Updated weights for policy 1, policy_version 134440 (0.0011) -[2023-11-28 03:44:17,898][87426] Updated weights for policy 1, policy_version 134450 (0.0010) -[2023-11-28 03:44:18,186][87424] Updated weights for policy 0, policy_version 134726 (0.0011) -[2023-11-28 03:44:18,279][87426] Updated weights for policy 1, policy_version 134460 (0.0008) -[2023-11-28 03:44:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 68911104. Throughput: 0: 2721.6, 1: 2731.2. Samples: 68921208. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:44:18,445][86177] Avg episode reward: [(0, '-493.190'), (1, '-627.280')] -[2023-11-28 03:44:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000134464_34422784.pth... -[2023-11-28 03:44:18,499][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000131904_33767424.pth -[2023-11-28 03:44:18,564][87424] Updated weights for policy 0, policy_version 134736 (0.0012) -[2023-11-28 03:44:18,944][87424] Updated weights for policy 0, policy_version 134746 (0.0011) -[2023-11-28 03:44:19,175][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000134752_34496512.pth... -[2023-11-28 03:44:19,222][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000132192_33841152.pth -[2023-11-28 03:44:20,518][87426] Updated weights for policy 1, policy_version 134470 (0.0008) -[2023-11-28 03:44:20,887][87426] Updated weights for policy 1, policy_version 134480 (0.0007) -[2023-11-28 03:44:21,265][87426] Updated weights for policy 1, policy_version 134490 (0.0010) -[2023-11-28 03:44:21,298][87424] Updated weights for policy 0, policy_version 134756 (0.0008) -[2023-11-28 03:44:21,674][87424] Updated weights for policy 0, policy_version 134766 (0.0011) -[2023-11-28 03:44:22,057][87424] Updated weights for policy 0, policy_version 134776 (0.0012) -[2023-11-28 03:44:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 68935680. Throughput: 0: 2714.1, 1: 2732.4. Samples: 68953340. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 03:44:23,445][86177] Avg episode reward: [(0, '-501.680'), (1, '-629.830')] -[2023-11-28 03:44:23,535][87426] Updated weights for policy 1, policy_version 134500 (0.0012) -[2023-11-28 03:44:23,910][87426] Updated weights for policy 1, policy_version 134510 (0.0012) -[2023-11-28 03:44:24,143][87424] Updated weights for policy 0, policy_version 134786 (0.0011) -[2023-11-28 03:44:24,284][87426] Updated weights for policy 1, policy_version 134520 (0.0012) -[2023-11-28 03:44:24,527][87424] Updated weights for policy 0, policy_version 134796 (0.0007) -[2023-11-28 03:44:24,910][87424] Updated weights for policy 0, policy_version 134806 (0.0007) -[2023-11-28 03:44:25,297][87424] Updated weights for policy 0, policy_version 134816 (0.0009) -[2023-11-28 03:44:26,068][87426] Updated weights for policy 1, policy_version 134530 (0.0010) -[2023-11-28 03:44:26,446][87426] Updated weights for policy 1, policy_version 134540 (0.0007) -[2023-11-28 03:44:26,825][87426] Updated weights for policy 1, policy_version 134550 (0.0007) -[2023-11-28 03:44:27,195][87426] Updated weights for policy 1, policy_version 134560 (0.0007) -[2023-11-28 03:44:27,590][87424] Updated weights for policy 0, policy_version 134826 (0.0012) -[2023-11-28 03:44:27,966][87424] Updated weights for policy 0, policy_version 134836 (0.0012) -[2023-11-28 03:44:28,351][87424] Updated weights for policy 0, policy_version 134846 (0.0008) -[2023-11-28 03:44:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 68968448. Throughput: 0: 2711.8, 1: 2746.6. Samples: 68979364. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:44:28,445][86177] Avg episode reward: [(0, '-501.220'), (1, '-588.290')] -[2023-11-28 03:44:29,412][87426] Updated weights for policy 1, policy_version 134570 (0.0011) -[2023-11-28 03:44:29,791][87426] Updated weights for policy 1, policy_version 134580 (0.0007) -[2023-11-28 03:44:30,178][87426] Updated weights for policy 1, policy_version 134590 (0.0008) -[2023-11-28 03:44:30,896][87424] Updated weights for policy 0, policy_version 134856 (0.0009) -[2023-11-28 03:44:31,275][87424] Updated weights for policy 0, policy_version 134866 (0.0010) -[2023-11-28 03:44:31,661][87424] Updated weights for policy 0, policy_version 134876 (0.0009) -[2023-11-28 03:44:32,328][87426] Updated weights for policy 1, policy_version 134600 (0.0011) -[2023-11-28 03:44:32,707][87426] Updated weights for policy 1, policy_version 134610 (0.0012) -[2023-11-28 03:44:33,085][87426] Updated weights for policy 1, policy_version 134620 (0.0011) -[2023-11-28 03:44:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 68993024. Throughput: 0: 2703.0, 1: 2751.6. Samples: 69003104. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:44:33,445][86177] Avg episode reward: [(0, '-501.940'), (1, '-567.680')] -[2023-11-28 03:44:34,014][87424] Updated weights for policy 0, policy_version 134886 (0.0008) -[2023-11-28 03:44:34,407][87424] Updated weights for policy 0, policy_version 134896 (0.0007) -[2023-11-28 03:44:34,787][87424] Updated weights for policy 0, policy_version 134906 (0.0008) -[2023-11-28 03:44:35,098][87426] Updated weights for policy 1, policy_version 134630 (0.0010) -[2023-11-28 03:44:35,478][87426] Updated weights for policy 1, policy_version 134640 (0.0008) -[2023-11-28 03:44:35,860][87426] Updated weights for policy 1, policy_version 134650 (0.0008) -[2023-11-28 03:44:36,835][87424] Updated weights for policy 0, policy_version 134916 (0.0011) -[2023-11-28 03:44:37,209][87424] Updated weights for policy 0, policy_version 134926 (0.0011) -[2023-11-28 03:44:37,596][87424] Updated weights for policy 0, policy_version 134936 (0.0007) -[2023-11-28 03:44:37,705][87426] Updated weights for policy 1, policy_version 134660 (0.0009) -[2023-11-28 03:44:38,081][87426] Updated weights for policy 1, policy_version 134670 (0.0012) -[2023-11-28 03:44:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 69017600. Throughput: 0: 2696.1, 1: 2750.2. Samples: 69035548. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:44:38,445][86177] Avg episode reward: [(0, '-503.870'), (1, '-556.960')] -[2023-11-28 03:44:38,456][87426] Updated weights for policy 1, policy_version 134680 (0.0012) -[2023-11-28 03:44:39,669][87424] Updated weights for policy 0, policy_version 134946 (0.0009) -[2023-11-28 03:44:40,051][87424] Updated weights for policy 0, policy_version 134956 (0.0011) -[2023-11-28 03:44:40,437][87424] Updated weights for policy 0, policy_version 134966 (0.0011) -[2023-11-28 03:44:40,823][87424] Updated weights for policy 0, policy_version 134976 (0.0008) -[2023-11-28 03:44:40,943][87426] Updated weights for policy 1, policy_version 134690 (0.0011) -[2023-11-28 03:44:41,313][87426] Updated weights for policy 1, policy_version 134700 (0.0007) -[2023-11-28 03:44:41,699][87426] Updated weights for policy 1, policy_version 134710 (0.0008) -[2023-11-28 03:44:42,072][87426] Updated weights for policy 1, policy_version 134720 (0.0009) -[2023-11-28 03:44:43,145][87424] Updated weights for policy 0, policy_version 134986 (0.0008) -[2023-11-28 03:44:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 69042176. Throughput: 0: 2701.9, 1: 2737.6. Samples: 69059552. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:44:43,445][86177] Avg episode reward: [(0, '-500.830'), (1, '-593.110')] -[2023-11-28 03:44:43,538][87424] Updated weights for policy 0, policy_version 134996 (0.0009) -[2023-11-28 03:44:43,916][87424] Updated weights for policy 0, policy_version 135006 (0.0008) -[2023-11-28 03:44:43,919][87426] Updated weights for policy 1, policy_version 134730 (0.0010) -[2023-11-28 03:44:44,299][87426] Updated weights for policy 1, policy_version 134740 (0.0010) -[2023-11-28 03:44:44,681][87426] Updated weights for policy 1, policy_version 134750 (0.0008) -[2023-11-28 03:44:46,431][87424] Updated weights for policy 0, policy_version 135016 (0.0010) -[2023-11-28 03:44:46,799][87424] Updated weights for policy 0, policy_version 135026 (0.0012) -[2023-11-28 03:44:47,109][87426] Updated weights for policy 1, policy_version 134760 (0.0010) -[2023-11-28 03:44:47,183][87424] Updated weights for policy 0, policy_version 135036 (0.0008) -[2023-11-28 03:44:47,483][87426] Updated weights for policy 1, policy_version 134770 (0.0007) -[2023-11-28 03:44:47,859][87426] Updated weights for policy 1, policy_version 134780 (0.0007) -[2023-11-28 03:44:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69074944. Throughput: 0: 2671.7, 1: 2727.7. Samples: 69083628. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:44:48,446][86177] Avg episode reward: [(0, '-504.670'), (1, '-602.660')] -[2023-11-28 03:44:49,704][87424] Updated weights for policy 0, policy_version 135046 (0.0011) -[2023-11-28 03:44:50,078][87424] Updated weights for policy 0, policy_version 135056 (0.0013) -[2023-11-28 03:44:50,393][87426] Updated weights for policy 1, policy_version 134790 (0.0009) -[2023-11-28 03:44:50,455][87424] Updated weights for policy 0, policy_version 135066 (0.0012) -[2023-11-28 03:44:50,771][87426] Updated weights for policy 1, policy_version 134800 (0.0011) -[2023-11-28 03:44:51,146][87426] Updated weights for policy 1, policy_version 134810 (0.0011) -[2023-11-28 03:44:52,501][87424] Updated weights for policy 0, policy_version 135076 (0.0012) -[2023-11-28 03:44:52,878][87424] Updated weights for policy 0, policy_version 135086 (0.0012) -[2023-11-28 03:44:53,252][87424] Updated weights for policy 0, policy_version 135096 (0.0012) -[2023-11-28 03:44:53,355][87426] Updated weights for policy 1, policy_version 134820 (0.0012) -[2023-11-28 03:44:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5325.1, 300 sec: 5415.0). Total num frames: 69091328. Throughput: 0: 2663.4, 1: 2760.0. Samples: 69116832. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:44:53,445][86177] Avg episode reward: [(0, '-503.320'), (1, '-614.770')] -[2023-11-28 03:44:53,721][87426] Updated weights for policy 1, policy_version 134830 (0.0010) -[2023-11-28 03:44:54,104][87426] Updated weights for policy 1, policy_version 134840 (0.0008) -[2023-11-28 03:44:55,345][87424] Updated weights for policy 0, policy_version 135106 (0.0011) -[2023-11-28 03:44:55,729][87424] Updated weights for policy 0, policy_version 135116 (0.0012) -[2023-11-28 03:44:56,027][87426] Updated weights for policy 1, policy_version 134850 (0.0008) -[2023-11-28 03:44:56,105][87424] Updated weights for policy 0, policy_version 135126 (0.0012) -[2023-11-28 03:44:56,415][87426] Updated weights for policy 1, policy_version 134860 (0.0011) -[2023-11-28 03:44:56,488][87424] Updated weights for policy 0, policy_version 135136 (0.0012) -[2023-11-28 03:44:56,787][87426] Updated weights for policy 1, policy_version 134870 (0.0011) -[2023-11-28 03:44:57,166][87426] Updated weights for policy 1, policy_version 134880 (0.0012) -[2023-11-28 03:44:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 69124096. Throughput: 0: 2664.1, 1: 2795.7. Samples: 69141872. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:44:58,445][86177] Avg episode reward: [(0, '-496.590'), (1, '-574.590')] -[2023-11-28 03:44:58,559][87424] Updated weights for policy 0, policy_version 135146 (0.0008) -[2023-11-28 03:44:58,935][87424] Updated weights for policy 0, policy_version 135156 (0.0008) -[2023-11-28 03:44:59,075][87426] Updated weights for policy 1, policy_version 134890 (0.0009) -[2023-11-28 03:44:59,319][87424] Updated weights for policy 0, policy_version 135166 (0.0007) -[2023-11-28 03:44:59,456][87426] Updated weights for policy 1, policy_version 134900 (0.0007) -[2023-11-28 03:44:59,828][87426] Updated weights for policy 1, policy_version 134910 (0.0008) -[2023-11-28 03:45:01,565][87426] Updated weights for policy 1, policy_version 134920 (0.0011) -[2023-11-28 03:45:01,718][87424] Updated weights for policy 0, policy_version 135176 (0.0011) -[2023-11-28 03:45:01,954][87426] Updated weights for policy 1, policy_version 134930 (0.0010) -[2023-11-28 03:45:02,103][87424] Updated weights for policy 0, policy_version 135186 (0.0010) -[2023-11-28 03:45:02,324][87426] Updated weights for policy 1, policy_version 134940 (0.0010) -[2023-11-28 03:45:02,478][87424] Updated weights for policy 0, policy_version 135196 (0.0011) -[2023-11-28 03:45:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 69156864. Throughput: 0: 2674.7, 1: 2791.2. Samples: 69167172. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:45:03,445][86177] Avg episode reward: [(0, '-495.900'), (1, '-552.880')] -[2023-11-28 03:45:04,281][87424] Updated weights for policy 0, policy_version 135206 (0.0009) -[2023-11-28 03:45:04,659][87424] Updated weights for policy 0, policy_version 135216 (0.0010) -[2023-11-28 03:45:04,752][87426] Updated weights for policy 1, policy_version 134950 (0.0010) -[2023-11-28 03:45:05,036][87424] Updated weights for policy 0, policy_version 135226 (0.0012) -[2023-11-28 03:45:05,138][87426] Updated weights for policy 1, policy_version 134960 (0.0009) -[2023-11-28 03:45:05,521][87426] Updated weights for policy 1, policy_version 134970 (0.0007) -[2023-11-28 03:45:06,653][87424] Updated weights for policy 0, policy_version 135236 (0.0012) -[2023-11-28 03:45:07,042][87424] Updated weights for policy 0, policy_version 135246 (0.0012) -[2023-11-28 03:45:07,420][87424] Updated weights for policy 0, policy_version 135256 (0.0012) -[2023-11-28 03:45:07,986][87426] Updated weights for policy 1, policy_version 134980 (0.0009) -[2023-11-28 03:45:08,368][87426] Updated weights for policy 1, policy_version 134990 (0.0011) -[2023-11-28 03:45:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 69181440. Throughput: 0: 2706.6, 1: 2769.9. Samples: 69199780. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:45:08,445][86177] Avg episode reward: [(0, '-491.300'), (1, '-553.570')] -[2023-11-28 03:45:08,754][87426] Updated weights for policy 1, policy_version 135000 (0.0012) -[2023-11-28 03:45:09,708][87424] Updated weights for policy 0, policy_version 135266 (0.0012) -[2023-11-28 03:45:10,081][87424] Updated weights for policy 0, policy_version 135276 (0.0012) -[2023-11-28 03:45:10,469][87424] Updated weights for policy 0, policy_version 135286 (0.0012) -[2023-11-28 03:45:10,568][87426] Updated weights for policy 1, policy_version 135010 (0.0011) -[2023-11-28 03:45:10,852][87424] Updated weights for policy 0, policy_version 135296 (0.0008) -[2023-11-28 03:45:10,957][87426] Updated weights for policy 1, policy_version 135020 (0.0008) -[2023-11-28 03:45:11,338][87426] Updated weights for policy 1, policy_version 135030 (0.0010) -[2023-11-28 03:45:11,717][87426] Updated weights for policy 1, policy_version 135040 (0.0011) -[2023-11-28 03:45:13,062][87424] Updated weights for policy 0, policy_version 135306 (0.0009) -[2023-11-28 03:45:13,440][87424] Updated weights for policy 0, policy_version 135316 (0.0010) -[2023-11-28 03:45:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 69206016. Throughput: 0: 2698.1, 1: 2749.6. Samples: 69224512. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:45:13,445][86177] Avg episode reward: [(0, '-525.200'), (1, '-526.560')] -[2023-11-28 03:45:13,556][87426] Updated weights for policy 1, policy_version 135050 (0.0011) -[2023-11-28 03:45:13,816][87424] Updated weights for policy 0, policy_version 135326 (0.0011) -[2023-11-28 03:45:13,939][87426] Updated weights for policy 1, policy_version 135060 (0.0011) -[2023-11-28 03:45:14,309][87426] Updated weights for policy 1, policy_version 135070 (0.0012) -[2023-11-28 03:45:16,231][87424] Updated weights for policy 0, policy_version 135336 (0.0012) -[2023-11-28 03:45:16,609][87424] Updated weights for policy 0, policy_version 135346 (0.0011) -[2023-11-28 03:45:16,789][87426] Updated weights for policy 1, policy_version 135080 (0.0008) -[2023-11-28 03:45:16,982][87424] Updated weights for policy 0, policy_version 135356 (0.0009) -[2023-11-28 03:45:17,167][87426] Updated weights for policy 1, policy_version 135090 (0.0010) -[2023-11-28 03:45:17,546][87426] Updated weights for policy 1, policy_version 135100 (0.0012) -[2023-11-28 03:45:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69238784. Throughput: 0: 2719.4, 1: 2757.7. Samples: 69249572. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:45:18,445][86177] Avg episode reward: [(0, '-527.180'), (1, '-521.810')] -[2023-11-28 03:45:18,682][87424] Updated weights for policy 0, policy_version 135366 (0.0008) -[2023-11-28 03:45:19,063][87424] Updated weights for policy 0, policy_version 135376 (0.0009) -[2023-11-28 03:45:19,447][87424] Updated weights for policy 0, policy_version 135386 (0.0008) -[2023-11-28 03:45:19,525][87426] Updated weights for policy 1, policy_version 135110 (0.0011) -[2023-11-28 03:45:19,906][87426] Updated weights for policy 1, policy_version 135120 (0.0012) -[2023-11-28 03:45:20,282][87426] Updated weights for policy 1, policy_version 135130 (0.0012) -[2023-11-28 03:45:21,259][87424] Updated weights for policy 0, policy_version 135396 (0.0010) -[2023-11-28 03:45:21,643][87424] Updated weights for policy 0, policy_version 135406 (0.0012) -[2023-11-28 03:45:22,038][87424] Updated weights for policy 0, policy_version 135416 (0.0011) -[2023-11-28 03:45:22,196][87426] Updated weights for policy 1, policy_version 135140 (0.0012) -[2023-11-28 03:45:22,567][87426] Updated weights for policy 1, policy_version 135150 (0.0012) -[2023-11-28 03:45:22,939][87426] Updated weights for policy 1, policy_version 135160 (0.0012) -[2023-11-28 03:45:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 69271552. Throughput: 0: 2730.4, 1: 2763.4. Samples: 69282768. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:45:23,445][86177] Avg episode reward: [(0, '-527.800'), (1, '-519.230')] -[2023-11-28 03:45:23,958][87424] Updated weights for policy 0, policy_version 135426 (0.0010) -[2023-11-28 03:45:24,338][87424] Updated weights for policy 0, policy_version 135436 (0.0007) -[2023-11-28 03:45:24,724][87424] Updated weights for policy 0, policy_version 135446 (0.0008) -[2023-11-28 03:45:24,984][87426] Updated weights for policy 1, policy_version 135170 (0.0012) -[2023-11-28 03:45:25,088][87424] Updated weights for policy 0, policy_version 135456 (0.0008) -[2023-11-28 03:45:25,363][87426] Updated weights for policy 1, policy_version 135180 (0.0007) -[2023-11-28 03:45:25,748][87426] Updated weights for policy 1, policy_version 135190 (0.0007) -[2023-11-28 03:45:26,135][87426] Updated weights for policy 1, policy_version 135200 (0.0007) -[2023-11-28 03:45:27,366][87424] Updated weights for policy 0, policy_version 135466 (0.0008) -[2023-11-28 03:45:27,746][87424] Updated weights for policy 0, policy_version 135476 (0.0007) -[2023-11-28 03:45:28,132][87424] Updated weights for policy 0, policy_version 135486 (0.0009) -[2023-11-28 03:45:28,367][87426] Updated weights for policy 1, policy_version 135210 (0.0009) -[2023-11-28 03:45:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69296128. Throughput: 0: 2733.8, 1: 2781.0. Samples: 69307716. Policy #0 lag: (min: 31.0, avg: 52.4, max: 90.0) -[2023-11-28 03:45:28,445][86177] Avg episode reward: [(0, '-540.590'), (1, '-540.680')] -[2023-11-28 03:45:28,745][87426] Updated weights for policy 1, policy_version 135220 (0.0012) -[2023-11-28 03:45:29,119][87426] Updated weights for policy 1, policy_version 135230 (0.0011) -[2023-11-28 03:45:30,550][87424] Updated weights for policy 0, policy_version 135496 (0.0009) -[2023-11-28 03:45:30,932][87424] Updated weights for policy 0, policy_version 135506 (0.0008) -[2023-11-28 03:45:31,319][87424] Updated weights for policy 0, policy_version 135516 (0.0008) -[2023-11-28 03:45:31,364][87426] Updated weights for policy 1, policy_version 135240 (0.0011) -[2023-11-28 03:45:31,742][87426] Updated weights for policy 1, policy_version 135250 (0.0010) -[2023-11-28 03:45:32,121][87426] Updated weights for policy 1, policy_version 135260 (0.0010) -[2023-11-28 03:45:33,172][87424] Updated weights for policy 0, policy_version 135526 (0.0008) -[2023-11-28 03:45:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 69320704. Throughput: 0: 2780.6, 1: 2780.4. Samples: 69333872. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:45:33,445][86177] Avg episode reward: [(0, '-508.420'), (1, '-533.780')] -[2023-11-28 03:45:33,556][87424] Updated weights for policy 0, policy_version 135536 (0.0008) -[2023-11-28 03:45:33,936][87424] Updated weights for policy 0, policy_version 135546 (0.0007) -[2023-11-28 03:45:34,386][87426] Updated weights for policy 1, policy_version 135270 (0.0009) -[2023-11-28 03:45:34,772][87426] Updated weights for policy 1, policy_version 135280 (0.0008) -[2023-11-28 03:45:35,145][87426] Updated weights for policy 1, policy_version 135290 (0.0010) -[2023-11-28 03:45:36,262][87424] Updated weights for policy 0, policy_version 135556 (0.0008) -[2023-11-28 03:45:36,638][87424] Updated weights for policy 0, policy_version 135566 (0.0008) -[2023-11-28 03:45:37,018][87424] Updated weights for policy 0, policy_version 135576 (0.0009) -[2023-11-28 03:45:37,113][87426] Updated weights for policy 1, policy_version 135300 (0.0010) -[2023-11-28 03:45:37,493][87426] Updated weights for policy 1, policy_version 135310 (0.0011) -[2023-11-28 03:45:37,871][87426] Updated weights for policy 1, policy_version 135320 (0.0012) -[2023-11-28 03:45:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 69353472. Throughput: 0: 2785.1, 1: 2768.0. Samples: 69366720. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:45:38,445][86177] Avg episode reward: [(0, '-509.030'), (1, '-557.310')] -[2023-11-28 03:45:39,007][87424] Updated weights for policy 0, policy_version 135586 (0.0009) -[2023-11-28 03:45:39,399][87424] Updated weights for policy 0, policy_version 135596 (0.0012) -[2023-11-28 03:45:39,777][87424] Updated weights for policy 0, policy_version 135606 (0.0012) -[2023-11-28 03:45:40,152][87424] Updated weights for policy 0, policy_version 135616 (0.0010) -[2023-11-28 03:45:40,163][87426] Updated weights for policy 1, policy_version 135330 (0.0011) -[2023-11-28 03:45:40,553][87426] Updated weights for policy 1, policy_version 135340 (0.0009) -[2023-11-28 03:45:40,927][87426] Updated weights for policy 1, policy_version 135350 (0.0011) -[2023-11-28 03:45:41,307][87426] Updated weights for policy 1, policy_version 135360 (0.0011) -[2023-11-28 03:45:42,073][87424] Updated weights for policy 0, policy_version 135626 (0.0012) -[2023-11-28 03:45:42,456][87424] Updated weights for policy 0, policy_version 135636 (0.0012) -[2023-11-28 03:45:42,830][87424] Updated weights for policy 0, policy_version 135646 (0.0012) -[2023-11-28 03:45:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 69378048. Throughput: 0: 2810.9, 1: 2752.7. Samples: 69392232. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:45:43,445][86177] Avg episode reward: [(0, '-512.550'), (1, '-577.810')] -[2023-11-28 03:45:43,481][87426] Updated weights for policy 1, policy_version 135370 (0.0012) -[2023-11-28 03:45:43,870][87426] Updated weights for policy 1, policy_version 135380 (0.0012) -[2023-11-28 03:45:44,258][87426] Updated weights for policy 1, policy_version 135390 (0.0012) -[2023-11-28 03:45:45,338][87424] Updated weights for policy 0, policy_version 135656 (0.0012) -[2023-11-28 03:45:45,718][87424] Updated weights for policy 0, policy_version 135666 (0.0012) -[2023-11-28 03:45:46,105][87424] Updated weights for policy 0, policy_version 135676 (0.0010) -[2023-11-28 03:45:46,161][87426] Updated weights for policy 1, policy_version 135400 (0.0011) -[2023-11-28 03:45:46,540][87426] Updated weights for policy 1, policy_version 135410 (0.0009) -[2023-11-28 03:45:46,926][87426] Updated weights for policy 1, policy_version 135420 (0.0007) -[2023-11-28 03:45:48,064][87424] Updated weights for policy 0, policy_version 135686 (0.0008) -[2023-11-28 03:45:48,443][87424] Updated weights for policy 0, policy_version 135696 (0.0007) -[2023-11-28 03:45:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69402624. Throughput: 0: 2774.0, 1: 2770.5. Samples: 69416676. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:45:48,445][86177] Avg episode reward: [(0, '-510.060'), (1, '-560.220')] -[2023-11-28 03:45:48,834][87424] Updated weights for policy 0, policy_version 135706 (0.0008) -[2023-11-28 03:45:49,144][87426] Updated weights for policy 1, policy_version 135430 (0.0010) -[2023-11-28 03:45:49,525][87426] Updated weights for policy 1, policy_version 135440 (0.0011) -[2023-11-28 03:45:49,904][87426] Updated weights for policy 1, policy_version 135450 (0.0012) -[2023-11-28 03:45:50,892][87424] Updated weights for policy 0, policy_version 135716 (0.0010) -[2023-11-28 03:45:51,279][87424] Updated weights for policy 0, policy_version 135726 (0.0012) -[2023-11-28 03:45:51,654][87424] Updated weights for policy 0, policy_version 135736 (0.0012) -[2023-11-28 03:45:52,400][87426] Updated weights for policy 1, policy_version 135460 (0.0010) -[2023-11-28 03:45:52,777][87426] Updated weights for policy 1, policy_version 135470 (0.0012) -[2023-11-28 03:45:53,160][87426] Updated weights for policy 1, policy_version 135480 (0.0012) -[2023-11-28 03:45:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 69427200. Throughput: 0: 2766.2, 1: 2779.1. Samples: 69449320. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:45:53,445][86177] Avg episode reward: [(0, '-512.500'), (1, '-533.300')] -[2023-11-28 03:45:53,744][87424] Updated weights for policy 0, policy_version 135746 (0.0012) -[2023-11-28 03:45:54,130][87424] Updated weights for policy 0, policy_version 135756 (0.0012) -[2023-11-28 03:45:54,511][87424] Updated weights for policy 0, policy_version 135766 (0.0012) -[2023-11-28 03:45:54,895][87424] Updated weights for policy 0, policy_version 135776 (0.0012) -[2023-11-28 03:45:55,594][87426] Updated weights for policy 1, policy_version 135490 (0.0011) -[2023-11-28 03:45:55,971][87426] Updated weights for policy 1, policy_version 135500 (0.0008) -[2023-11-28 03:45:56,351][87426] Updated weights for policy 1, policy_version 135510 (0.0007) -[2023-11-28 03:45:56,728][87426] Updated weights for policy 1, policy_version 135520 (0.0007) -[2023-11-28 03:45:57,315][87424] Updated weights for policy 0, policy_version 135786 (0.0007) -[2023-11-28 03:45:57,704][87424] Updated weights for policy 0, policy_version 135796 (0.0007) -[2023-11-28 03:45:58,079][87424] Updated weights for policy 0, policy_version 135806 (0.0007) -[2023-11-28 03:45:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 69459968. Throughput: 0: 2770.0, 1: 2761.3. Samples: 69473424. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:45:58,446][86177] Avg episode reward: [(0, '-512.580'), (1, '-530.460')] -[2023-11-28 03:45:58,927][87426] Updated weights for policy 1, policy_version 135530 (0.0008) -[2023-11-28 03:45:59,303][87426] Updated weights for policy 1, policy_version 135540 (0.0008) -[2023-11-28 03:45:59,678][87426] Updated weights for policy 1, policy_version 135550 (0.0011) -[2023-11-28 03:46:00,382][87424] Updated weights for policy 0, policy_version 135816 (0.0011) -[2023-11-28 03:46:00,768][87424] Updated weights for policy 0, policy_version 135826 (0.0011) -[2023-11-28 03:46:01,142][87424] Updated weights for policy 0, policy_version 135836 (0.0012) -[2023-11-28 03:46:01,492][87426] Updated weights for policy 1, policy_version 135560 (0.0011) -[2023-11-28 03:46:01,870][87426] Updated weights for policy 1, policy_version 135570 (0.0012) -[2023-11-28 03:46:02,247][87426] Updated weights for policy 1, policy_version 135580 (0.0012) -[2023-11-28 03:46:03,422][87424] Updated weights for policy 0, policy_version 135846 (0.0010) -[2023-11-28 03:46:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 69484544. Throughput: 0: 2758.5, 1: 2750.8. Samples: 69497488. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:46:03,445][86177] Avg episode reward: [(0, '-513.160'), (1, '-517.210')] -[2023-11-28 03:46:03,799][87424] Updated weights for policy 0, policy_version 135856 (0.0012) -[2023-11-28 03:46:04,160][87426] Updated weights for policy 1, policy_version 135590 (0.0012) -[2023-11-28 03:46:04,191][87424] Updated weights for policy 0, policy_version 135866 (0.0011) -[2023-11-28 03:46:04,547][87426] Updated weights for policy 1, policy_version 135600 (0.0011) -[2023-11-28 03:46:04,914][87426] Updated weights for policy 1, policy_version 135610 (0.0012) -[2023-11-28 03:46:06,298][87424] Updated weights for policy 0, policy_version 135876 (0.0011) -[2023-11-28 03:46:06,684][87424] Updated weights for policy 0, policy_version 135886 (0.0009) -[2023-11-28 03:46:07,060][87424] Updated weights for policy 0, policy_version 135896 (0.0010) -[2023-11-28 03:46:07,420][87426] Updated weights for policy 1, policy_version 135620 (0.0011) -[2023-11-28 03:46:07,788][87426] Updated weights for policy 1, policy_version 135630 (0.0016) -[2023-11-28 03:46:08,170][87426] Updated weights for policy 1, policy_version 135640 (0.0011) -[2023-11-28 03:46:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 69509120. Throughput: 0: 2752.9, 1: 2763.6. Samples: 69531008. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:46:08,445][86177] Avg episode reward: [(0, '-515.140'), (1, '-503.260')] -[2023-11-28 03:46:08,962][87424] Updated weights for policy 0, policy_version 135906 (0.0012) -[2023-11-28 03:46:09,344][87424] Updated weights for policy 0, policy_version 135916 (0.0011) -[2023-11-28 03:46:09,728][87424] Updated weights for policy 0, policy_version 135926 (0.0012) -[2023-11-28 03:46:10,095][87426] Updated weights for policy 1, policy_version 135650 (0.0011) -[2023-11-28 03:46:10,105][87424] Updated weights for policy 0, policy_version 135936 (0.0011) -[2023-11-28 03:46:10,472][87426] Updated weights for policy 1, policy_version 135660 (0.0012) -[2023-11-28 03:46:10,850][87426] Updated weights for policy 1, policy_version 135670 (0.0012) -[2023-11-28 03:46:11,230][87426] Updated weights for policy 1, policy_version 135680 (0.0011) -[2023-11-28 03:46:12,575][87424] Updated weights for policy 0, policy_version 135946 (0.0010) -[2023-11-28 03:46:12,952][87424] Updated weights for policy 0, policy_version 135956 (0.0010) -[2023-11-28 03:46:13,341][87424] Updated weights for policy 0, policy_version 135966 (0.0011) -[2023-11-28 03:46:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 69541888. Throughput: 0: 2759.9, 1: 2748.2. Samples: 69555580. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:46:13,445][86177] Avg episode reward: [(0, '-511.150'), (1, '-524.770')] -[2023-11-28 03:46:13,612][87426] Updated weights for policy 1, policy_version 135690 (0.0007) -[2023-11-28 03:46:14,000][87426] Updated weights for policy 1, policy_version 135700 (0.0007) -[2023-11-28 03:46:14,386][87426] Updated weights for policy 1, policy_version 135710 (0.0008) -[2023-11-28 03:46:15,590][87424] Updated weights for policy 0, policy_version 135976 (0.0012) -[2023-11-28 03:46:15,970][87424] Updated weights for policy 0, policy_version 135986 (0.0012) -[2023-11-28 03:46:16,356][87424] Updated weights for policy 0, policy_version 135996 (0.0012) -[2023-11-28 03:46:16,794][87426] Updated weights for policy 1, policy_version 135720 (0.0008) -[2023-11-28 03:46:17,176][87426] Updated weights for policy 1, policy_version 135730 (0.0011) -[2023-11-28 03:46:17,554][87426] Updated weights for policy 1, policy_version 135740 (0.0012) -[2023-11-28 03:46:18,035][87424] Updated weights for policy 0, policy_version 136006 (0.0009) -[2023-11-28 03:46:18,420][87424] Updated weights for policy 0, policy_version 136016 (0.0008) -[2023-11-28 03:46:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69566464. Throughput: 0: 2730.1, 1: 2724.4. Samples: 69579324. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:46:18,445][86177] Avg episode reward: [(0, '-503.890'), (1, '-526.410')] -[2023-11-28 03:46:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000135744_34750464.pth... -[2023-11-28 03:46:18,500][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000133184_34095104.pth -[2023-11-28 03:46:18,804][87424] Updated weights for policy 0, policy_version 136026 (0.0008) -[2023-11-28 03:46:19,031][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000136032_34824192.pth... -[2023-11-28 03:46:19,080][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000133440_34160640.pth -[2023-11-28 03:46:19,377][87426] Updated weights for policy 1, policy_version 135750 (0.0012) -[2023-11-28 03:46:19,761][87426] Updated weights for policy 1, policy_version 135760 (0.0012) -[2023-11-28 03:46:20,137][87426] Updated weights for policy 1, policy_version 135770 (0.0012) -[2023-11-28 03:46:21,191][87424] Updated weights for policy 0, policy_version 136036 (0.0012) -[2023-11-28 03:46:21,570][87424] Updated weights for policy 0, policy_version 136046 (0.0012) -[2023-11-28 03:46:21,953][87424] Updated weights for policy 0, policy_version 136056 (0.0012) -[2023-11-28 03:46:22,658][87426] Updated weights for policy 1, policy_version 135780 (0.0012) -[2023-11-28 03:46:23,037][87426] Updated weights for policy 1, policy_version 135790 (0.0010) -[2023-11-28 03:46:23,413][87426] Updated weights for policy 1, policy_version 135800 (0.0012) -[2023-11-28 03:46:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 69591040. Throughput: 0: 2736.1, 1: 2713.7. Samples: 69611960. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:46:23,445][86177] Avg episode reward: [(0, '-502.730'), (1, '-524.760')] -[2023-11-28 03:46:24,487][87424] Updated weights for policy 0, policy_version 136066 (0.0012) -[2023-11-28 03:46:24,872][87424] Updated weights for policy 0, policy_version 136076 (0.0012) -[2023-11-28 03:46:25,251][87424] Updated weights for policy 0, policy_version 136086 (0.0011) -[2023-11-28 03:46:25,630][87424] Updated weights for policy 0, policy_version 136096 (0.0012) -[2023-11-28 03:46:25,635][87426] Updated weights for policy 1, policy_version 135810 (0.0012) -[2023-11-28 03:46:26,016][87426] Updated weights for policy 1, policy_version 135820 (0.0012) -[2023-11-28 03:46:26,383][87426] Updated weights for policy 1, policy_version 135830 (0.0012) -[2023-11-28 03:46:26,765][87426] Updated weights for policy 1, policy_version 135840 (0.0012) -[2023-11-28 03:46:27,403][87424] Updated weights for policy 0, policy_version 136106 (0.0012) -[2023-11-28 03:46:27,794][87424] Updated weights for policy 0, policy_version 136116 (0.0008) -[2023-11-28 03:46:28,179][87424] Updated weights for policy 0, policy_version 136126 (0.0008) -[2023-11-28 03:46:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69623808. Throughput: 0: 2713.5, 1: 2702.9. Samples: 69635972. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:46:28,446][86177] Avg episode reward: [(0, '-502.330'), (1, '-525.070')] -[2023-11-28 03:46:29,106][87426] Updated weights for policy 1, policy_version 135850 (0.0012) -[2023-11-28 03:46:29,492][87426] Updated weights for policy 1, policy_version 135860 (0.0011) -[2023-11-28 03:46:29,863][87424] Updated weights for policy 0, policy_version 136136 (0.0008) -[2023-11-28 03:46:29,866][87426] Updated weights for policy 1, policy_version 135870 (0.0012) -[2023-11-28 03:46:30,251][87424] Updated weights for policy 0, policy_version 136146 (0.0008) -[2023-11-28 03:46:30,626][87424] Updated weights for policy 0, policy_version 136156 (0.0011) -[2023-11-28 03:46:32,329][87426] Updated weights for policy 1, policy_version 135880 (0.0009) -[2023-11-28 03:46:32,701][87426] Updated weights for policy 1, policy_version 135890 (0.0011) -[2023-11-28 03:46:32,784][87424] Updated weights for policy 0, policy_version 136166 (0.0011) -[2023-11-28 03:46:33,084][87426] Updated weights for policy 1, policy_version 135900 (0.0011) -[2023-11-28 03:46:33,165][87424] Updated weights for policy 0, policy_version 136176 (0.0010) -[2023-11-28 03:46:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69648384. Throughput: 0: 2740.9, 1: 2676.6. Samples: 69660464. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 03:46:33,445][86177] Avg episode reward: [(0, '-504.990'), (1, '-506.170')] -[2023-11-28 03:46:33,546][87424] Updated weights for policy 0, policy_version 136186 (0.0012) -[2023-11-28 03:46:35,192][87426] Updated weights for policy 1, policy_version 135910 (0.0011) -[2023-11-28 03:46:35,569][87426] Updated weights for policy 1, policy_version 135920 (0.0010) -[2023-11-28 03:46:35,961][87426] Updated weights for policy 1, policy_version 135930 (0.0007) -[2023-11-28 03:46:36,125][87424] Updated weights for policy 0, policy_version 136196 (0.0012) -[2023-11-28 03:46:36,507][87424] Updated weights for policy 0, policy_version 136206 (0.0011) -[2023-11-28 03:46:36,883][87424] Updated weights for policy 0, policy_version 136216 (0.0011) -[2023-11-28 03:46:37,661][87426] Updated weights for policy 1, policy_version 135940 (0.0009) -[2023-11-28 03:46:38,045][87426] Updated weights for policy 1, policy_version 135950 (0.0011) -[2023-11-28 03:46:38,419][87426] Updated weights for policy 1, policy_version 135960 (0.0009) -[2023-11-28 03:46:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 69672960. Throughput: 0: 2722.7, 1: 2694.0. Samples: 69693076. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:46:38,445][86177] Avg episode reward: [(0, '-504.590'), (1, '-528.810')] -[2023-11-28 03:46:39,418][87424] Updated weights for policy 0, policy_version 136226 (0.0011) -[2023-11-28 03:46:39,804][87424] Updated weights for policy 0, policy_version 136236 (0.0008) -[2023-11-28 03:46:40,200][87424] Updated weights for policy 0, policy_version 136246 (0.0011) -[2023-11-28 03:46:40,444][87426] Updated weights for policy 1, policy_version 135970 (0.0008) -[2023-11-28 03:46:40,580][87424] Updated weights for policy 0, policy_version 136256 (0.0010) -[2023-11-28 03:46:40,827][87426] Updated weights for policy 1, policy_version 135980 (0.0012) -[2023-11-28 03:46:41,196][87426] Updated weights for policy 1, policy_version 135990 (0.0012) -[2023-11-28 03:46:41,575][87426] Updated weights for policy 1, policy_version 136000 (0.0011) -[2023-11-28 03:46:42,571][87424] Updated weights for policy 0, policy_version 136266 (0.0012) -[2023-11-28 03:46:42,953][87424] Updated weights for policy 0, policy_version 136276 (0.0012) -[2023-11-28 03:46:43,330][87424] Updated weights for policy 0, policy_version 136286 (0.0012) -[2023-11-28 03:46:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69705728. Throughput: 0: 2733.1, 1: 2699.5. Samples: 69717888. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:46:43,445][86177] Avg episode reward: [(0, '-504.060'), (1, '-545.030')] -[2023-11-28 03:46:43,786][87426] Updated weights for policy 1, policy_version 136010 (0.0012) -[2023-11-28 03:46:44,166][87426] Updated weights for policy 1, policy_version 136020 (0.0012) -[2023-11-28 03:46:44,538][87426] Updated weights for policy 1, policy_version 136030 (0.0010) -[2023-11-28 03:46:45,033][87424] Updated weights for policy 0, policy_version 136296 (0.0008) -[2023-11-28 03:46:45,410][87424] Updated weights for policy 0, policy_version 136306 (0.0008) -[2023-11-28 03:46:45,792][87424] Updated weights for policy 0, policy_version 136316 (0.0012) -[2023-11-28 03:46:46,937][87426] Updated weights for policy 1, policy_version 136040 (0.0011) -[2023-11-28 03:46:47,328][87426] Updated weights for policy 1, policy_version 136050 (0.0012) -[2023-11-28 03:46:47,707][87426] Updated weights for policy 1, policy_version 136060 (0.0011) -[2023-11-28 03:46:47,770][87424] Updated weights for policy 0, policy_version 136326 (0.0011) -[2023-11-28 03:46:48,155][87424] Updated weights for policy 0, policy_version 136336 (0.0007) -[2023-11-28 03:46:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.7). Total num frames: 69730304. Throughput: 0: 2757.7, 1: 2702.1. Samples: 69743180. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:46:48,445][86177] Avg episode reward: [(0, '-513.550'), (1, '-546.200')] -[2023-11-28 03:46:48,538][87424] Updated weights for policy 0, policy_version 136346 (0.0007) -[2023-11-28 03:46:50,037][87424] Updated weights for policy 0, policy_version 136356 (0.0009) -[2023-11-28 03:46:50,264][87426] Updated weights for policy 1, policy_version 136070 (0.0011) -[2023-11-28 03:46:50,420][87424] Updated weights for policy 0, policy_version 136366 (0.0008) -[2023-11-28 03:46:50,640][87426] Updated weights for policy 1, policy_version 136080 (0.0011) -[2023-11-28 03:46:50,811][87424] Updated weights for policy 0, policy_version 136376 (0.0012) -[2023-11-28 03:46:51,016][87426] Updated weights for policy 1, policy_version 136090 (0.0011) -[2023-11-28 03:46:53,117][87424] Updated weights for policy 0, policy_version 136386 (0.0012) -[2023-11-28 03:46:53,184][87426] Updated weights for policy 1, policy_version 136100 (0.0012) -[2023-11-28 03:46:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69754880. Throughput: 0: 2756.4, 1: 2665.8. Samples: 69775008. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:46:53,445][86177] Avg episode reward: [(0, '-512.630'), (1, '-542.340')] -[2023-11-28 03:46:53,489][87424] Updated weights for policy 0, policy_version 136396 (0.0011) -[2023-11-28 03:46:53,563][87426] Updated weights for policy 1, policy_version 136110 (0.0011) -[2023-11-28 03:46:53,875][87424] Updated weights for policy 0, policy_version 136406 (0.0011) -[2023-11-28 03:46:53,941][87426] Updated weights for policy 1, policy_version 136120 (0.0009) -[2023-11-28 03:46:54,254][87424] Updated weights for policy 0, policy_version 136416 (0.0007) -[2023-11-28 03:46:56,243][87426] Updated weights for policy 1, policy_version 136130 (0.0007) -[2023-11-28 03:46:56,622][87426] Updated weights for policy 1, policy_version 136140 (0.0008) -[2023-11-28 03:46:56,847][87424] Updated weights for policy 0, policy_version 136426 (0.0009) -[2023-11-28 03:46:57,005][87426] Updated weights for policy 1, policy_version 136150 (0.0007) -[2023-11-28 03:46:57,222][87424] Updated weights for policy 0, policy_version 136436 (0.0007) -[2023-11-28 03:46:57,385][87426] Updated weights for policy 1, policy_version 136160 (0.0007) -[2023-11-28 03:46:57,606][87424] Updated weights for policy 0, policy_version 136446 (0.0008) -[2023-11-28 03:46:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69787648. Throughput: 0: 2725.6, 1: 2653.5. Samples: 69797640. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:46:58,446][86177] Avg episode reward: [(0, '-514.080'), (1, '-520.660')] -[2023-11-28 03:46:59,828][87426] Updated weights for policy 1, policy_version 136170 (0.0007) -[2023-11-28 03:47:00,118][87424] Updated weights for policy 0, policy_version 136456 (0.0011) -[2023-11-28 03:47:00,217][87426] Updated weights for policy 1, policy_version 136180 (0.0008) -[2023-11-28 03:47:00,498][87424] Updated weights for policy 0, policy_version 136466 (0.0011) -[2023-11-28 03:47:00,593][87426] Updated weights for policy 1, policy_version 136190 (0.0009) -[2023-11-28 03:47:00,884][87424] Updated weights for policy 0, policy_version 136476 (0.0009) -[2023-11-28 03:47:03,090][87426] Updated weights for policy 1, policy_version 136200 (0.0009) -[2023-11-28 03:47:03,367][87424] Updated weights for policy 0, policy_version 136486 (0.0011) -[2023-11-28 03:47:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 69804032. Throughput: 0: 2701.2, 1: 2664.8. Samples: 69820792. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:47:03,445][86177] Avg episode reward: [(0, '-526.270'), (1, '-516.960')] -[2023-11-28 03:47:03,458][87426] Updated weights for policy 1, policy_version 136210 (0.0009) -[2023-11-28 03:47:03,752][87424] Updated weights for policy 0, policy_version 136496 (0.0012) -[2023-11-28 03:47:03,837][87426] Updated weights for policy 1, policy_version 136220 (0.0007) -[2023-11-28 03:47:04,130][87424] Updated weights for policy 0, policy_version 136506 (0.0012) -[2023-11-28 03:47:06,314][87424] Updated weights for policy 0, policy_version 136516 (0.0010) -[2023-11-28 03:47:06,370][87426] Updated weights for policy 1, policy_version 136230 (0.0011) -[2023-11-28 03:47:06,702][87424] Updated weights for policy 0, policy_version 136526 (0.0008) -[2023-11-28 03:47:06,738][87426] Updated weights for policy 1, policy_version 136240 (0.0009) -[2023-11-28 03:47:07,076][87424] Updated weights for policy 0, policy_version 136536 (0.0011) -[2023-11-28 03:47:07,118][87426] Updated weights for policy 1, policy_version 136250 (0.0009) -[2023-11-28 03:47:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69836800. Throughput: 0: 2725.4, 1: 2646.6. Samples: 69853700. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:47:08,445][86177] Avg episode reward: [(0, '-515.100'), (1, '-527.350')] -[2023-11-28 03:47:08,936][87424] Updated weights for policy 0, policy_version 136546 (0.0010) -[2023-11-28 03:47:09,292][87426] Updated weights for policy 1, policy_version 136260 (0.0011) -[2023-11-28 03:47:09,322][87424] Updated weights for policy 0, policy_version 136556 (0.0012) -[2023-11-28 03:47:09,660][87426] Updated weights for policy 1, policy_version 136270 (0.0010) -[2023-11-28 03:47:09,700][87424] Updated weights for policy 0, policy_version 136566 (0.0012) -[2023-11-28 03:47:10,038][87426] Updated weights for policy 1, policy_version 136280 (0.0011) -[2023-11-28 03:47:10,082][87424] Updated weights for policy 0, policy_version 136576 (0.0011) -[2023-11-28 03:47:12,212][87424] Updated weights for policy 0, policy_version 136586 (0.0011) -[2023-11-28 03:47:12,405][87426] Updated weights for policy 1, policy_version 136290 (0.0008) -[2023-11-28 03:47:12,590][87424] Updated weights for policy 0, policy_version 136596 (0.0011) -[2023-11-28 03:47:12,775][87426] Updated weights for policy 1, policy_version 136300 (0.0011) -[2023-11-28 03:47:12,967][87424] Updated weights for policy 0, policy_version 136606 (0.0010) -[2023-11-28 03:47:13,154][87426] Updated weights for policy 1, policy_version 136310 (0.0010) -[2023-11-28 03:47:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 69861376. Throughput: 0: 2735.4, 1: 2647.9. Samples: 69878220. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:47:13,445][86177] Avg episode reward: [(0, '-513.240'), (1, '-528.510')] -[2023-11-28 03:47:13,536][87426] Updated weights for policy 1, policy_version 136320 (0.0009) -[2023-11-28 03:47:15,282][87424] Updated weights for policy 0, policy_version 136616 (0.0012) -[2023-11-28 03:47:15,653][87424] Updated weights for policy 0, policy_version 136626 (0.0011) -[2023-11-28 03:47:15,834][87426] Updated weights for policy 1, policy_version 136330 (0.0007) -[2023-11-28 03:47:16,041][87424] Updated weights for policy 0, policy_version 136636 (0.0012) -[2023-11-28 03:47:16,223][87426] Updated weights for policy 1, policy_version 136340 (0.0007) -[2023-11-28 03:47:16,594][87426] Updated weights for policy 1, policy_version 136350 (0.0011) -[2023-11-28 03:47:17,797][87424] Updated weights for policy 0, policy_version 136646 (0.0010) -[2023-11-28 03:47:18,169][87424] Updated weights for policy 0, policy_version 136656 (0.0012) -[2023-11-28 03:47:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 69885952. Throughput: 0: 2731.7, 1: 2650.0. Samples: 69902640. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:47:18,445][86177] Avg episode reward: [(0, '-497.710'), (1, '-550.890')] -[2023-11-28 03:47:18,533][87426] Updated weights for policy 1, policy_version 136360 (0.0008) -[2023-11-28 03:47:18,555][87424] Updated weights for policy 0, policy_version 136666 (0.0010) -[2023-11-28 03:47:18,906][87426] Updated weights for policy 1, policy_version 136370 (0.0009) -[2023-11-28 03:47:19,288][87426] Updated weights for policy 1, policy_version 136380 (0.0011) -[2023-11-28 03:47:21,020][87424] Updated weights for policy 0, policy_version 136676 (0.0011) -[2023-11-28 03:47:21,220][87426] Updated weights for policy 1, policy_version 136390 (0.0010) -[2023-11-28 03:47:21,399][87424] Updated weights for policy 0, policy_version 136686 (0.0009) -[2023-11-28 03:47:21,594][87426] Updated weights for policy 1, policy_version 136400 (0.0011) -[2023-11-28 03:47:21,786][87424] Updated weights for policy 0, policy_version 136696 (0.0010) -[2023-11-28 03:47:21,975][87426] Updated weights for policy 1, policy_version 136410 (0.0011) -[2023-11-28 03:47:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69918720. Throughput: 0: 2733.0, 1: 2627.1. Samples: 69934280. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:47:23,445][86177] Avg episode reward: [(0, '-496.580'), (1, '-555.780')] -[2023-11-28 03:47:23,842][87424] Updated weights for policy 0, policy_version 136706 (0.0010) -[2023-11-28 03:47:23,854][87426] Updated weights for policy 1, policy_version 136420 (0.0012) -[2023-11-28 03:47:24,224][87424] Updated weights for policy 0, policy_version 136716 (0.0012) -[2023-11-28 03:47:24,224][87426] Updated weights for policy 1, policy_version 136430 (0.0011) -[2023-11-28 03:47:24,603][87426] Updated weights for policy 1, policy_version 136440 (0.0007) -[2023-11-28 03:47:24,603][87424] Updated weights for policy 0, policy_version 136726 (0.0012) -[2023-11-28 03:47:24,977][87424] Updated weights for policy 0, policy_version 136736 (0.0011) -[2023-11-28 03:47:27,092][87426] Updated weights for policy 1, policy_version 136450 (0.0008) -[2023-11-28 03:47:27,242][87424] Updated weights for policy 0, policy_version 136746 (0.0012) -[2023-11-28 03:47:27,475][87426] Updated weights for policy 1, policy_version 136460 (0.0011) -[2023-11-28 03:47:27,623][87424] Updated weights for policy 0, policy_version 136756 (0.0012) -[2023-11-28 03:47:27,862][87426] Updated weights for policy 1, policy_version 136470 (0.0011) -[2023-11-28 03:47:28,011][87424] Updated weights for policy 0, policy_version 136766 (0.0011) -[2023-11-28 03:47:28,240][87426] Updated weights for policy 1, policy_version 136480 (0.0011) -[2023-11-28 03:47:28,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 69951488. Throughput: 0: 2719.9, 1: 2624.9. Samples: 69958404. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:47:28,445][86177] Avg episode reward: [(0, '-498.470'), (1, '-548.810')] -[2023-11-28 03:47:30,124][87424] Updated weights for policy 0, policy_version 136776 (0.0012) -[2023-11-28 03:47:30,150][87426] Updated weights for policy 1, policy_version 136490 (0.0011) -[2023-11-28 03:47:30,511][87424] Updated weights for policy 0, policy_version 136786 (0.0012) -[2023-11-28 03:47:30,528][87426] Updated weights for policy 1, policy_version 136500 (0.0009) -[2023-11-28 03:47:30,893][87424] Updated weights for policy 0, policy_version 136796 (0.0012) -[2023-11-28 03:47:30,909][87426] Updated weights for policy 1, policy_version 136510 (0.0008) -[2023-11-28 03:47:33,381][87426] Updated weights for policy 1, policy_version 136520 (0.0008) -[2023-11-28 03:47:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 69967872. Throughput: 0: 2710.3, 1: 2633.4. Samples: 69983648. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:47:33,446][86177] Avg episode reward: [(0, '-503.390'), (1, '-520.580')] -[2023-11-28 03:47:33,492][87424] Updated weights for policy 0, policy_version 136806 (0.0012) -[2023-11-28 03:47:33,761][87426] Updated weights for policy 1, policy_version 136530 (0.0007) -[2023-11-28 03:47:33,868][87424] Updated weights for policy 0, policy_version 136816 (0.0012) -[2023-11-28 03:47:34,146][87426] Updated weights for policy 1, policy_version 136540 (0.0008) -[2023-11-28 03:47:34,251][87424] Updated weights for policy 0, policy_version 136826 (0.0012) -[2023-11-28 03:47:35,828][87426] Updated weights for policy 1, policy_version 136550 (0.0010) -[2023-11-28 03:47:36,206][87426] Updated weights for policy 1, policy_version 136560 (0.0011) -[2023-11-28 03:47:36,213][87424] Updated weights for policy 0, policy_version 136836 (0.0012) -[2023-11-28 03:47:36,582][87426] Updated weights for policy 1, policy_version 136570 (0.0011) -[2023-11-28 03:47:36,605][87424] Updated weights for policy 0, policy_version 136846 (0.0009) -[2023-11-28 03:47:36,979][87424] Updated weights for policy 0, policy_version 136856 (0.0009) -[2023-11-28 03:47:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 70000640. Throughput: 0: 2709.3, 1: 2664.5. Samples: 70016828. Policy #0 lag: (min: 0.0, avg: 26.4, max: 42.0) -[2023-11-28 03:47:38,445][86177] Avg episode reward: [(0, '-503.460'), (1, '-520.260')] -[2023-11-28 03:47:38,542][87426] Updated weights for policy 1, policy_version 136580 (0.0011) -[2023-11-28 03:47:38,644][87424] Updated weights for policy 0, policy_version 136866 (0.0011) -[2023-11-28 03:47:38,912][87426] Updated weights for policy 1, policy_version 136590 (0.0011) -[2023-11-28 03:47:39,033][87424] Updated weights for policy 0, policy_version 136876 (0.0010) -[2023-11-28 03:47:39,293][87426] Updated weights for policy 1, policy_version 136600 (0.0011) -[2023-11-28 03:47:39,417][87424] Updated weights for policy 0, policy_version 136886 (0.0011) -[2023-11-28 03:47:39,794][87424] Updated weights for policy 0, policy_version 136896 (0.0012) -[2023-11-28 03:47:41,488][87426] Updated weights for policy 1, policy_version 136610 (0.0009) -[2023-11-28 03:47:41,875][87426] Updated weights for policy 1, policy_version 136620 (0.0011) -[2023-11-28 03:47:42,258][87426] Updated weights for policy 1, policy_version 136630 (0.0011) -[2023-11-28 03:47:42,366][87424] Updated weights for policy 0, policy_version 136906 (0.0011) -[2023-11-28 03:47:42,628][87426] Updated weights for policy 1, policy_version 136640 (0.0010) -[2023-11-28 03:47:42,749][87424] Updated weights for policy 0, policy_version 136916 (0.0011) -[2023-11-28 03:47:43,134][87424] Updated weights for policy 0, policy_version 136926 (0.0012) -[2023-11-28 03:47:43,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 70033408. Throughput: 0: 2721.6, 1: 2705.1. Samples: 70041840. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:47:43,445][86177] Avg episode reward: [(0, '-504.940'), (1, '-509.540')] -[2023-11-28 03:47:45,044][87424] Updated weights for policy 0, policy_version 136936 (0.0011) -[2023-11-28 03:47:45,225][87426] Updated weights for policy 1, policy_version 136650 (0.0012) -[2023-11-28 03:47:45,420][87424] Updated weights for policy 0, policy_version 136946 (0.0011) -[2023-11-28 03:47:45,604][87426] Updated weights for policy 1, policy_version 136660 (0.0011) -[2023-11-28 03:47:45,803][87424] Updated weights for policy 0, policy_version 136956 (0.0012) -[2023-11-28 03:47:45,979][87426] Updated weights for policy 1, policy_version 136670 (0.0011) -[2023-11-28 03:47:47,706][87424] Updated weights for policy 0, policy_version 136966 (0.0012) -[2023-11-28 03:47:47,920][87426] Updated weights for policy 1, policy_version 136680 (0.0012) -[2023-11-28 03:47:48,090][87424] Updated weights for policy 0, policy_version 136976 (0.0011) -[2023-11-28 03:47:48,304][87426] Updated weights for policy 1, policy_version 136690 (0.0009) -[2023-11-28 03:47:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 70049792. Throughput: 0: 2737.6, 1: 2718.9. Samples: 70066336. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:47:48,445][86177] Avg episode reward: [(0, '-504.570'), (1, '-515.400')] -[2023-11-28 03:47:48,473][87424] Updated weights for policy 0, policy_version 136986 (0.0012) -[2023-11-28 03:47:48,688][87426] Updated weights for policy 1, policy_version 136700 (0.0008) -[2023-11-28 03:47:50,575][87424] Updated weights for policy 0, policy_version 136996 (0.0012) -[2023-11-28 03:47:50,755][87426] Updated weights for policy 1, policy_version 136710 (0.0010) -[2023-11-28 03:47:50,960][87424] Updated weights for policy 0, policy_version 137006 (0.0012) -[2023-11-28 03:47:51,137][87426] Updated weights for policy 1, policy_version 136720 (0.0009) -[2023-11-28 03:47:51,340][87424] Updated weights for policy 0, policy_version 137016 (0.0012) -[2023-11-28 03:47:51,510][87426] Updated weights for policy 1, policy_version 136730 (0.0009) -[2023-11-28 03:47:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70082560. Throughput: 0: 2731.4, 1: 2747.6. Samples: 70100256. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:47:53,445][86177] Avg episode reward: [(0, '-514.670'), (1, '-525.510')] -[2023-11-28 03:47:53,807][87426] Updated weights for policy 1, policy_version 136740 (0.0010) -[2023-11-28 03:47:53,823][87424] Updated weights for policy 0, policy_version 137026 (0.0012) -[2023-11-28 03:47:54,189][87426] Updated weights for policy 1, policy_version 136750 (0.0010) -[2023-11-28 03:47:54,215][87424] Updated weights for policy 0, policy_version 137036 (0.0012) -[2023-11-28 03:47:54,568][87426] Updated weights for policy 1, policy_version 136760 (0.0007) -[2023-11-28 03:47:54,607][87424] Updated weights for policy 0, policy_version 137046 (0.0012) -[2023-11-28 03:47:54,979][87424] Updated weights for policy 0, policy_version 137056 (0.0012) -[2023-11-28 03:47:57,035][87426] Updated weights for policy 1, policy_version 136770 (0.0008) -[2023-11-28 03:47:57,202][87424] Updated weights for policy 0, policy_version 137066 (0.0011) -[2023-11-28 03:47:57,426][87426] Updated weights for policy 1, policy_version 136780 (0.0012) -[2023-11-28 03:47:57,597][87424] Updated weights for policy 0, policy_version 137076 (0.0012) -[2023-11-28 03:47:57,815][87426] Updated weights for policy 1, policy_version 136790 (0.0011) -[2023-11-28 03:47:57,987][87424] Updated weights for policy 0, policy_version 137086 (0.0012) -[2023-11-28 03:47:58,193][87426] Updated weights for policy 1, policy_version 136800 (0.0010) -[2023-11-28 03:47:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 70115328. Throughput: 0: 2715.9, 1: 2742.2. Samples: 70123836. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:47:58,445][86177] Avg episode reward: [(0, '-518.030'), (1, '-524.490')] -[2023-11-28 03:47:59,751][87424] Updated weights for policy 0, policy_version 137096 (0.0011) -[2023-11-28 03:48:00,002][87426] Updated weights for policy 1, policy_version 136810 (0.0012) -[2023-11-28 03:48:00,133][87424] Updated weights for policy 0, policy_version 137106 (0.0009) -[2023-11-28 03:48:00,392][87426] Updated weights for policy 1, policy_version 136820 (0.0012) -[2023-11-28 03:48:00,522][87424] Updated weights for policy 0, policy_version 137116 (0.0009) -[2023-11-28 03:48:00,768][87426] Updated weights for policy 1, policy_version 136830 (0.0011) -[2023-11-28 03:48:02,551][87424] Updated weights for policy 0, policy_version 137126 (0.0010) -[2023-11-28 03:48:02,892][87426] Updated weights for policy 1, policy_version 136840 (0.0011) -[2023-11-28 03:48:02,918][87424] Updated weights for policy 0, policy_version 137136 (0.0011) -[2023-11-28 03:48:03,286][87426] Updated weights for policy 1, policy_version 136850 (0.0009) -[2023-11-28 03:48:03,303][87424] Updated weights for policy 0, policy_version 137146 (0.0009) -[2023-11-28 03:48:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70131712. Throughput: 0: 2730.8, 1: 2760.6. Samples: 70149756. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:48:03,445][86177] Avg episode reward: [(0, '-528.760'), (1, '-528.170')] -[2023-11-28 03:48:03,657][87426] Updated weights for policy 1, policy_version 136860 (0.0007) -[2023-11-28 03:48:05,588][87424] Updated weights for policy 0, policy_version 137156 (0.0007) -[2023-11-28 03:48:05,969][87424] Updated weights for policy 0, policy_version 137166 (0.0008) -[2023-11-28 03:48:06,044][87426] Updated weights for policy 1, policy_version 136870 (0.0009) -[2023-11-28 03:48:06,359][87424] Updated weights for policy 0, policy_version 137176 (0.0010) -[2023-11-28 03:48:06,413][87426] Updated weights for policy 1, policy_version 136880 (0.0009) -[2023-11-28 03:48:06,793][87426] Updated weights for policy 1, policy_version 136890 (0.0008) -[2023-11-28 03:48:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70164480. Throughput: 0: 2742.2, 1: 2779.7. Samples: 70182768. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:48:08,445][86177] Avg episode reward: [(0, '-536.400'), (1, '-542.630')] -[2023-11-28 03:48:08,629][87424] Updated weights for policy 0, policy_version 137186 (0.0011) -[2023-11-28 03:48:09,011][87424] Updated weights for policy 0, policy_version 137196 (0.0008) -[2023-11-28 03:48:09,202][87426] Updated weights for policy 1, policy_version 136900 (0.0009) -[2023-11-28 03:48:09,386][87424] Updated weights for policy 0, policy_version 137206 (0.0010) -[2023-11-28 03:48:09,574][87426] Updated weights for policy 1, policy_version 136910 (0.0010) -[2023-11-28 03:48:09,770][87424] Updated weights for policy 0, policy_version 137216 (0.0011) -[2023-11-28 03:48:09,955][87426] Updated weights for policy 1, policy_version 136920 (0.0011) -[2023-11-28 03:48:11,991][87424] Updated weights for policy 0, policy_version 137226 (0.0012) -[2023-11-28 03:48:12,162][87426] Updated weights for policy 1, policy_version 136930 (0.0008) -[2023-11-28 03:48:12,379][87424] Updated weights for policy 0, policy_version 137236 (0.0011) -[2023-11-28 03:48:12,552][87426] Updated weights for policy 1, policy_version 136940 (0.0008) -[2023-11-28 03:48:12,754][87424] Updated weights for policy 0, policy_version 137246 (0.0012) -[2023-11-28 03:48:12,929][87426] Updated weights for policy 1, policy_version 136950 (0.0008) -[2023-11-28 03:48:13,293][87426] Updated weights for policy 1, policy_version 136960 (0.0008) -[2023-11-28 03:48:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 70197248. Throughput: 0: 2750.1, 1: 2768.7. Samples: 70206752. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:48:13,445][86177] Avg episode reward: [(0, '-522.810'), (1, '-533.850')] -[2023-11-28 03:48:15,224][87426] Updated weights for policy 1, policy_version 136970 (0.0009) -[2023-11-28 03:48:15,320][87424] Updated weights for policy 0, policy_version 137256 (0.0009) -[2023-11-28 03:48:15,601][87426] Updated weights for policy 1, policy_version 136980 (0.0008) -[2023-11-28 03:48:15,700][87424] Updated weights for policy 0, policy_version 137266 (0.0011) -[2023-11-28 03:48:15,988][87426] Updated weights for policy 1, policy_version 136990 (0.0011) -[2023-11-28 03:48:16,073][87424] Updated weights for policy 0, policy_version 137276 (0.0010) -[2023-11-28 03:48:17,736][87426] Updated weights for policy 1, policy_version 137000 (0.0009) -[2023-11-28 03:48:17,983][87424] Updated weights for policy 0, policy_version 137286 (0.0010) -[2023-11-28 03:48:18,117][87426] Updated weights for policy 1, policy_version 137010 (0.0009) -[2023-11-28 03:48:18,370][87424] Updated weights for policy 0, policy_version 137296 (0.0011) -[2023-11-28 03:48:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70213632. Throughput: 0: 2728.9, 1: 2776.8. Samples: 70231404. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:48:18,445][86177] Avg episode reward: [(0, '-525.390'), (1, '-537.470')] -[2023-11-28 03:48:18,506][87426] Updated weights for policy 1, policy_version 137020 (0.0011) -[2023-11-28 03:48:18,649][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000137024_35078144.pth... -[2023-11-28 03:48:18,680][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000134464_34422784.pth -[2023-11-28 03:48:18,757][87424] Updated weights for policy 0, policy_version 137306 (0.0012) -[2023-11-28 03:48:18,989][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000137312_35151872.pth... -[2023-11-28 03:48:19,036][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000134752_34496512.pth -[2023-11-28 03:48:20,740][87424] Updated weights for policy 0, policy_version 137316 (0.0010) -[2023-11-28 03:48:20,753][87426] Updated weights for policy 1, policy_version 137030 (0.0011) -[2023-11-28 03:48:21,117][87424] Updated weights for policy 0, policy_version 137326 (0.0011) -[2023-11-28 03:48:21,125][87426] Updated weights for policy 1, policy_version 137040 (0.0010) -[2023-11-28 03:48:21,506][87426] Updated weights for policy 1, policy_version 137050 (0.0011) -[2023-11-28 03:48:21,507][87424] Updated weights for policy 0, policy_version 137336 (0.0012) -[2023-11-28 03:48:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70246400. Throughput: 0: 2740.4, 1: 2753.3. Samples: 70264044. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:48:23,445][86177] Avg episode reward: [(0, '-512.230'), (1, '-542.100')] -[2023-11-28 03:48:23,674][87424] Updated weights for policy 0, policy_version 137346 (0.0011) -[2023-11-28 03:48:24,043][87426] Updated weights for policy 1, policy_version 137060 (0.0010) -[2023-11-28 03:48:24,055][87424] Updated weights for policy 0, policy_version 137356 (0.0010) -[2023-11-28 03:48:24,417][87426] Updated weights for policy 1, policy_version 137070 (0.0008) -[2023-11-28 03:48:24,440][87424] Updated weights for policy 0, policy_version 137366 (0.0011) -[2023-11-28 03:48:24,795][87426] Updated weights for policy 1, policy_version 137080 (0.0008) -[2023-11-28 03:48:24,824][87424] Updated weights for policy 0, policy_version 137376 (0.0008) -[2023-11-28 03:48:27,058][87424] Updated weights for policy 0, policy_version 137386 (0.0012) -[2023-11-28 03:48:27,314][87426] Updated weights for policy 1, policy_version 137090 (0.0011) -[2023-11-28 03:48:27,444][87424] Updated weights for policy 0, policy_version 137396 (0.0012) -[2023-11-28 03:48:27,690][87426] Updated weights for policy 1, policy_version 137100 (0.0012) -[2023-11-28 03:48:27,825][87424] Updated weights for policy 0, policy_version 137406 (0.0012) -[2023-11-28 03:48:28,070][87426] Updated weights for policy 1, policy_version 137110 (0.0012) -[2023-11-28 03:48:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 70270976. Throughput: 0: 2744.1, 1: 2726.9. Samples: 70288036. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:48:28,445][86177] Avg episode reward: [(0, '-508.590'), (1, '-525.110')] -[2023-11-28 03:48:28,454][87426] Updated weights for policy 1, policy_version 137120 (0.0011) -[2023-11-28 03:48:30,222][87424] Updated weights for policy 0, policy_version 137416 (0.0012) -[2023-11-28 03:48:30,601][87426] Updated weights for policy 1, policy_version 137130 (0.0011) -[2023-11-28 03:48:30,604][87424] Updated weights for policy 0, policy_version 137426 (0.0010) -[2023-11-28 03:48:30,987][87426] Updated weights for policy 1, policy_version 137140 (0.0012) -[2023-11-28 03:48:30,988][87424] Updated weights for policy 0, policy_version 137436 (0.0009) -[2023-11-28 03:48:31,370][87426] Updated weights for policy 1, policy_version 137150 (0.0010) -[2023-11-28 03:48:33,047][87424] Updated weights for policy 0, policy_version 137446 (0.0010) -[2023-11-28 03:48:33,424][87426] Updated weights for policy 1, policy_version 137160 (0.0010) -[2023-11-28 03:48:33,428][87424] Updated weights for policy 0, policy_version 137456 (0.0009) -[2023-11-28 03:48:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70295552. Throughput: 0: 2743.4, 1: 2724.3. Samples: 70312384. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:48:33,446][86177] Avg episode reward: [(0, '-518.920'), (1, '-521.050')] -[2023-11-28 03:48:33,808][87424] Updated weights for policy 0, policy_version 137466 (0.0011) -[2023-11-28 03:48:33,809][87426] Updated weights for policy 1, policy_version 137170 (0.0007) -[2023-11-28 03:48:34,196][87426] Updated weights for policy 1, policy_version 137180 (0.0007) -[2023-11-28 03:48:36,138][87424] Updated weights for policy 0, policy_version 137476 (0.0011) -[2023-11-28 03:48:36,519][87424] Updated weights for policy 0, policy_version 137486 (0.0012) -[2023-11-28 03:48:36,652][87426] Updated weights for policy 1, policy_version 137190 (0.0009) -[2023-11-28 03:48:36,907][87424] Updated weights for policy 0, policy_version 137496 (0.0011) -[2023-11-28 03:48:37,033][87426] Updated weights for policy 1, policy_version 137200 (0.0011) -[2023-11-28 03:48:37,397][87426] Updated weights for policy 1, policy_version 137210 (0.0011) -[2023-11-28 03:48:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70328320. Throughput: 0: 2723.5, 1: 2684.6. Samples: 70343624. Policy #0 lag: (min: 13.0, avg: 40.2, max: 64.0) -[2023-11-28 03:48:38,445][86177] Avg episode reward: [(0, '-505.370'), (1, '-528.950')] -[2023-11-28 03:48:38,829][87424] Updated weights for policy 0, policy_version 137506 (0.0011) -[2023-11-28 03:48:39,192][87426] Updated weights for policy 1, policy_version 137220 (0.0007) -[2023-11-28 03:48:39,203][87424] Updated weights for policy 0, policy_version 137516 (0.0008) -[2023-11-28 03:48:39,567][87426] Updated weights for policy 1, policy_version 137230 (0.0010) -[2023-11-28 03:48:39,588][87424] Updated weights for policy 0, policy_version 137526 (0.0008) -[2023-11-28 03:48:39,946][87426] Updated weights for policy 1, policy_version 137240 (0.0011) -[2023-11-28 03:48:39,971][87424] Updated weights for policy 0, policy_version 137536 (0.0011) -[2023-11-28 03:48:41,831][87426] Updated weights for policy 1, policy_version 137250 (0.0011) -[2023-11-28 03:48:42,211][87426] Updated weights for policy 1, policy_version 137260 (0.0010) -[2023-11-28 03:48:42,422][87424] Updated weights for policy 0, policy_version 137546 (0.0009) -[2023-11-28 03:48:42,586][87426] Updated weights for policy 1, policy_version 137270 (0.0009) -[2023-11-28 03:48:42,805][87424] Updated weights for policy 0, policy_version 137556 (0.0009) -[2023-11-28 03:48:42,964][87426] Updated weights for policy 1, policy_version 137280 (0.0011) -[2023-11-28 03:48:43,196][87424] Updated weights for policy 0, policy_version 137566 (0.0008) -[2023-11-28 03:48:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 70361088. Throughput: 0: 2729.6, 1: 2697.3. Samples: 70368048. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:48:43,446][86177] Avg episode reward: [(0, '-506.930'), (1, '-535.020')] -[2023-11-28 03:48:45,002][87426] Updated weights for policy 1, policy_version 137290 (0.0012) -[2023-11-28 03:48:45,374][87426] Updated weights for policy 1, policy_version 137300 (0.0011) -[2023-11-28 03:48:45,748][87426] Updated weights for policy 1, policy_version 137310 (0.0008) -[2023-11-28 03:48:45,829][87424] Updated weights for policy 0, policy_version 137576 (0.0011) -[2023-11-28 03:48:46,215][87424] Updated weights for policy 0, policy_version 137586 (0.0012) -[2023-11-28 03:48:46,590][87424] Updated weights for policy 0, policy_version 137596 (0.0012) -[2023-11-28 03:48:47,625][87426] Updated weights for policy 1, policy_version 137320 (0.0009) -[2023-11-28 03:48:48,004][87426] Updated weights for policy 1, policy_version 137330 (0.0007) -[2023-11-28 03:48:48,382][87426] Updated weights for policy 1, policy_version 137340 (0.0007) -[2023-11-28 03:48:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.9). Total num frames: 70377472. Throughput: 0: 2692.8, 1: 2702.6. Samples: 70392548. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:48:48,446][86177] Avg episode reward: [(0, '-504.890'), (1, '-531.050')] -[2023-11-28 03:48:49,220][87424] Updated weights for policy 0, policy_version 137606 (0.0009) -[2023-11-28 03:48:49,610][87424] Updated weights for policy 0, policy_version 137616 (0.0007) -[2023-11-28 03:48:49,986][87424] Updated weights for policy 0, policy_version 137626 (0.0009) -[2023-11-28 03:48:50,460][87426] Updated weights for policy 1, policy_version 137350 (0.0009) -[2023-11-28 03:48:50,837][87426] Updated weights for policy 1, policy_version 137360 (0.0008) -[2023-11-28 03:48:51,216][87426] Updated weights for policy 1, policy_version 137370 (0.0008) -[2023-11-28 03:48:51,727][87424] Updated weights for policy 0, policy_version 137636 (0.0008) -[2023-11-28 03:48:52,102][87424] Updated weights for policy 0, policy_version 137646 (0.0009) -[2023-11-28 03:48:52,484][87424] Updated weights for policy 0, policy_version 137656 (0.0009) -[2023-11-28 03:48:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70410240. Throughput: 0: 2663.3, 1: 2714.1. Samples: 70424752. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:48:53,445][86177] Avg episode reward: [(0, '-537.570'), (1, '-530.970')] -[2023-11-28 03:48:53,843][87426] Updated weights for policy 1, policy_version 137380 (0.0009) -[2023-11-28 03:48:54,219][87426] Updated weights for policy 1, policy_version 137390 (0.0012) -[2023-11-28 03:48:54,598][87426] Updated weights for policy 1, policy_version 137400 (0.0008) -[2023-11-28 03:48:54,786][87424] Updated weights for policy 0, policy_version 137666 (0.0009) -[2023-11-28 03:48:55,167][87424] Updated weights for policy 0, policy_version 137676 (0.0008) -[2023-11-28 03:48:55,553][87424] Updated weights for policy 0, policy_version 137686 (0.0007) -[2023-11-28 03:48:55,940][87424] Updated weights for policy 0, policy_version 137696 (0.0008) -[2023-11-28 03:48:56,419][87426] Updated weights for policy 1, policy_version 137410 (0.0011) -[2023-11-28 03:48:56,796][87426] Updated weights for policy 1, policy_version 137420 (0.0012) -[2023-11-28 03:48:57,183][87426] Updated weights for policy 1, policy_version 137430 (0.0012) -[2023-11-28 03:48:57,557][87426] Updated weights for policy 1, policy_version 137440 (0.0012) -[2023-11-28 03:48:58,400][87424] Updated weights for policy 0, policy_version 137706 (0.0012) -[2023-11-28 03:48:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 70434816. Throughput: 0: 2648.6, 1: 2737.7. Samples: 70449136. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:48:58,445][86177] Avg episode reward: [(0, '-540.400'), (1, '-523.430')] -[2023-11-28 03:48:58,786][87424] Updated weights for policy 0, policy_version 137716 (0.0012) -[2023-11-28 03:48:59,160][87424] Updated weights for policy 0, policy_version 137726 (0.0008) -[2023-11-28 03:48:59,764][87426] Updated weights for policy 1, policy_version 137450 (0.0009) -[2023-11-28 03:49:00,128][87426] Updated weights for policy 1, policy_version 137460 (0.0023) -[2023-11-28 03:49:00,506][87426] Updated weights for policy 1, policy_version 137470 (0.0011) -[2023-11-28 03:49:01,758][87424] Updated weights for policy 0, policy_version 137736 (0.0012) -[2023-11-28 03:49:02,139][87424] Updated weights for policy 0, policy_version 137746 (0.0012) -[2023-11-28 03:49:02,444][87426] Updated weights for policy 1, policy_version 137480 (0.0009) -[2023-11-28 03:49:02,517][87424] Updated weights for policy 0, policy_version 137756 (0.0011) -[2023-11-28 03:49:02,822][87426] Updated weights for policy 1, policy_version 137490 (0.0008) -[2023-11-28 03:49:03,192][87426] Updated weights for policy 1, policy_version 137500 (0.0011) -[2023-11-28 03:49:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 70467584. Throughput: 0: 2657.2, 1: 2726.5. Samples: 70473668. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:49:03,445][86177] Avg episode reward: [(0, '-544.730'), (1, '-507.570')] -[2023-11-28 03:49:05,037][87424] Updated weights for policy 0, policy_version 137766 (0.0012) -[2023-11-28 03:49:05,156][87426] Updated weights for policy 1, policy_version 137510 (0.0011) -[2023-11-28 03:49:05,420][87424] Updated weights for policy 0, policy_version 137776 (0.0011) -[2023-11-28 03:49:05,534][87426] Updated weights for policy 1, policy_version 137520 (0.0011) -[2023-11-28 03:49:05,804][87424] Updated weights for policy 0, policy_version 137786 (0.0010) -[2023-11-28 03:49:05,911][87426] Updated weights for policy 1, policy_version 137530 (0.0012) -[2023-11-28 03:49:07,764][87424] Updated weights for policy 0, policy_version 137796 (0.0012) -[2023-11-28 03:49:08,126][87426] Updated weights for policy 1, policy_version 137540 (0.0012) -[2023-11-28 03:49:08,147][87424] Updated weights for policy 0, policy_version 137806 (0.0012) -[2023-11-28 03:49:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 70483968. Throughput: 0: 2647.5, 1: 2762.8. Samples: 70507504. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:49:08,445][86177] Avg episode reward: [(0, '-546.880'), (1, '-509.960')] -[2023-11-28 03:49:08,511][87426] Updated weights for policy 1, policy_version 137550 (0.0010) -[2023-11-28 03:49:08,545][87424] Updated weights for policy 0, policy_version 137816 (0.0008) -[2023-11-28 03:49:08,878][87426] Updated weights for policy 1, policy_version 137560 (0.0011) -[2023-11-28 03:49:10,726][87424] Updated weights for policy 0, policy_version 137826 (0.0009) -[2023-11-28 03:49:11,109][87424] Updated weights for policy 0, policy_version 137836 (0.0012) -[2023-11-28 03:49:11,179][87426] Updated weights for policy 1, policy_version 137570 (0.0010) -[2023-11-28 03:49:11,488][87424] Updated weights for policy 0, policy_version 137846 (0.0012) -[2023-11-28 03:49:11,564][87426] Updated weights for policy 1, policy_version 137580 (0.0011) -[2023-11-28 03:49:11,875][87424] Updated weights for policy 0, policy_version 137856 (0.0012) -[2023-11-28 03:49:11,947][87426] Updated weights for policy 1, policy_version 137590 (0.0011) -[2023-11-28 03:49:12,318][87426] Updated weights for policy 1, policy_version 137600 (0.0012) -[2023-11-28 03:49:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 70516736. Throughput: 0: 2649.1, 1: 2753.2. Samples: 70531140. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:49:13,445][86177] Avg episode reward: [(0, '-507.130'), (1, '-509.150')] -[2023-11-28 03:49:14,210][87424] Updated weights for policy 0, policy_version 137866 (0.0008) -[2023-11-28 03:49:14,587][87424] Updated weights for policy 0, policy_version 137876 (0.0007) -[2023-11-28 03:49:14,706][87426] Updated weights for policy 1, policy_version 137610 (0.0007) -[2023-11-28 03:49:14,969][87424] Updated weights for policy 0, policy_version 137886 (0.0007) -[2023-11-28 03:49:15,082][87426] Updated weights for policy 1, policy_version 137620 (0.0007) -[2023-11-28 03:49:15,473][87426] Updated weights for policy 1, policy_version 137630 (0.0009) -[2023-11-28 03:49:16,872][87424] Updated weights for policy 0, policy_version 137896 (0.0008) -[2023-11-28 03:49:17,257][87424] Updated weights for policy 0, policy_version 137906 (0.0007) -[2023-11-28 03:49:17,654][87424] Updated weights for policy 0, policy_version 137916 (0.0007) -[2023-11-28 03:49:18,000][87426] Updated weights for policy 1, policy_version 137640 (0.0011) -[2023-11-28 03:49:18,387][87426] Updated weights for policy 1, policy_version 137650 (0.0011) -[2023-11-28 03:49:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70541312. Throughput: 0: 2664.7, 1: 2739.2. Samples: 70555560. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:49:18,445][86177] Avg episode reward: [(0, '-497.980'), (1, '-504.130')] -[2023-11-28 03:49:18,765][87426] Updated weights for policy 1, policy_version 137660 (0.0011) -[2023-11-28 03:49:19,936][87424] Updated weights for policy 0, policy_version 137926 (0.0010) -[2023-11-28 03:49:20,322][87424] Updated weights for policy 0, policy_version 137936 (0.0008) -[2023-11-28 03:49:20,707][87424] Updated weights for policy 0, policy_version 137946 (0.0010) -[2023-11-28 03:49:20,839][87426] Updated weights for policy 1, policy_version 137670 (0.0011) -[2023-11-28 03:49:21,221][87426] Updated weights for policy 1, policy_version 137680 (0.0011) -[2023-11-28 03:49:21,593][87426] Updated weights for policy 1, policy_version 137690 (0.0012) -[2023-11-28 03:49:23,009][87424] Updated weights for policy 0, policy_version 137956 (0.0011) -[2023-11-28 03:49:23,388][87424] Updated weights for policy 0, policy_version 137966 (0.0012) -[2023-11-28 03:49:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 70565888. Throughput: 0: 2664.6, 1: 2753.0. Samples: 70587416. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:49:23,445][86177] Avg episode reward: [(0, '-496.740'), (1, '-506.470')] -[2023-11-28 03:49:23,768][87424] Updated weights for policy 0, policy_version 137976 (0.0012) -[2023-11-28 03:49:23,857][87426] Updated weights for policy 1, policy_version 137700 (0.0011) -[2023-11-28 03:49:24,244][87426] Updated weights for policy 1, policy_version 137710 (0.0009) -[2023-11-28 03:49:24,625][87426] Updated weights for policy 1, policy_version 137720 (0.0010) -[2023-11-28 03:49:25,796][87424] Updated weights for policy 0, policy_version 137986 (0.0011) -[2023-11-28 03:49:26,179][87424] Updated weights for policy 0, policy_version 137996 (0.0008) -[2023-11-28 03:49:26,559][87424] Updated weights for policy 0, policy_version 138006 (0.0007) -[2023-11-28 03:49:26,592][87426] Updated weights for policy 1, policy_version 137730 (0.0008) -[2023-11-28 03:49:26,944][87424] Updated weights for policy 0, policy_version 138016 (0.0007) -[2023-11-28 03:49:26,980][87426] Updated weights for policy 1, policy_version 137740 (0.0011) -[2023-11-28 03:49:27,360][87426] Updated weights for policy 1, policy_version 137750 (0.0012) -[2023-11-28 03:49:27,746][87426] Updated weights for policy 1, policy_version 137760 (0.0012) -[2023-11-28 03:49:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70598656. Throughput: 0: 2663.8, 1: 2770.1. Samples: 70612572. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:49:28,445][86177] Avg episode reward: [(0, '-497.990'), (1, '-512.350')] -[2023-11-28 03:49:29,299][87424] Updated weights for policy 0, policy_version 138026 (0.0012) -[2023-11-28 03:49:29,565][87426] Updated weights for policy 1, policy_version 137770 (0.0007) -[2023-11-28 03:49:29,678][87424] Updated weights for policy 0, policy_version 138036 (0.0012) -[2023-11-28 03:49:29,943][87426] Updated weights for policy 1, policy_version 137780 (0.0011) -[2023-11-28 03:49:30,060][87424] Updated weights for policy 0, policy_version 138046 (0.0012) -[2023-11-28 03:49:30,326][87426] Updated weights for policy 1, policy_version 137790 (0.0011) -[2023-11-28 03:49:32,180][87424] Updated weights for policy 0, policy_version 138056 (0.0011) -[2023-11-28 03:49:32,363][87426] Updated weights for policy 1, policy_version 137800 (0.0011) -[2023-11-28 03:49:32,563][87424] Updated weights for policy 0, policy_version 138066 (0.0011) -[2023-11-28 03:49:32,742][87426] Updated weights for policy 1, policy_version 137810 (0.0010) -[2023-11-28 03:49:32,958][87424] Updated weights for policy 0, policy_version 138076 (0.0012) -[2023-11-28 03:49:33,123][87426] Updated weights for policy 1, policy_version 137820 (0.0010) -[2023-11-28 03:49:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 70631424. Throughput: 0: 2687.7, 1: 2752.4. Samples: 70637352. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:49:33,445][86177] Avg episode reward: [(0, '-505.640'), (1, '-510.390')] -[2023-11-28 03:49:34,718][87424] Updated weights for policy 0, policy_version 138086 (0.0011) -[2023-11-28 03:49:35,096][87424] Updated weights for policy 0, policy_version 138096 (0.0012) -[2023-11-28 03:49:35,163][87426] Updated weights for policy 1, policy_version 137830 (0.0012) -[2023-11-28 03:49:35,486][87424] Updated weights for policy 0, policy_version 138106 (0.0011) -[2023-11-28 03:49:35,532][87426] Updated weights for policy 1, policy_version 137840 (0.0011) -[2023-11-28 03:49:35,922][87426] Updated weights for policy 1, policy_version 137850 (0.0011) -[2023-11-28 03:49:37,430][87424] Updated weights for policy 0, policy_version 138116 (0.0010) -[2023-11-28 03:49:37,817][87424] Updated weights for policy 0, policy_version 138126 (0.0011) -[2023-11-28 03:49:38,188][87424] Updated weights for policy 0, policy_version 138136 (0.0012) -[2023-11-28 03:49:38,441][87426] Updated weights for policy 1, policy_version 137860 (0.0009) -[2023-11-28 03:49:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 70647808. Throughput: 0: 2730.8, 1: 2739.6. Samples: 70670920. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:49:38,445][86177] Avg episode reward: [(0, '-510.970'), (1, '-550.970')] -[2023-11-28 03:49:38,813][87426] Updated weights for policy 1, policy_version 137870 (0.0008) -[2023-11-28 03:49:39,193][87426] Updated weights for policy 1, policy_version 137880 (0.0008) -[2023-11-28 03:49:39,938][87424] Updated weights for policy 0, policy_version 138146 (0.0011) -[2023-11-28 03:49:40,315][87424] Updated weights for policy 0, policy_version 138156 (0.0012) -[2023-11-28 03:49:40,698][87424] Updated weights for policy 0, policy_version 138166 (0.0012) -[2023-11-28 03:49:41,087][87424] Updated weights for policy 0, policy_version 138176 (0.0012) -[2023-11-28 03:49:41,530][87426] Updated weights for policy 1, policy_version 137890 (0.0008) -[2023-11-28 03:49:41,903][87426] Updated weights for policy 1, policy_version 137900 (0.0012) -[2023-11-28 03:49:42,287][87426] Updated weights for policy 1, policy_version 137910 (0.0010) -[2023-11-28 03:49:42,669][87426] Updated weights for policy 1, policy_version 137920 (0.0010) -[2023-11-28 03:49:43,114][87424] Updated weights for policy 0, policy_version 138186 (0.0010) -[2023-11-28 03:49:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 70680576. Throughput: 0: 2735.5, 1: 2712.4. Samples: 70694288. Policy #0 lag: (min: 31.0, avg: 40.7, max: 63.0) -[2023-11-28 03:49:43,445][86177] Avg episode reward: [(0, '-518.630'), (1, '-560.870')] -[2023-11-28 03:49:43,501][87424] Updated weights for policy 0, policy_version 138196 (0.0012) -[2023-11-28 03:49:43,887][87424] Updated weights for policy 0, policy_version 138206 (0.0008) -[2023-11-28 03:49:44,835][87426] Updated weights for policy 1, policy_version 137930 (0.0011) -[2023-11-28 03:49:45,218][87426] Updated weights for policy 1, policy_version 137940 (0.0011) -[2023-11-28 03:49:45,610][87426] Updated weights for policy 1, policy_version 137950 (0.0011) -[2023-11-28 03:49:46,236][87424] Updated weights for policy 0, policy_version 138216 (0.0007) -[2023-11-28 03:49:46,628][87424] Updated weights for policy 0, policy_version 138226 (0.0012) -[2023-11-28 03:49:47,002][87424] Updated weights for policy 0, policy_version 138236 (0.0010) -[2023-11-28 03:49:47,951][87426] Updated weights for policy 1, policy_version 137960 (0.0011) -[2023-11-28 03:49:48,336][87426] Updated weights for policy 1, policy_version 137970 (0.0011) -[2023-11-28 03:49:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 70705152. Throughput: 0: 2739.4, 1: 2712.3. Samples: 70718992. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:49:48,445][86177] Avg episode reward: [(0, '-529.920'), (1, '-555.570')] -[2023-11-28 03:49:48,713][87426] Updated weights for policy 1, policy_version 137980 (0.0011) -[2023-11-28 03:49:49,147][87424] Updated weights for policy 0, policy_version 138246 (0.0010) -[2023-11-28 03:49:49,525][87424] Updated weights for policy 0, policy_version 138256 (0.0011) -[2023-11-28 03:49:49,906][87424] Updated weights for policy 0, policy_version 138266 (0.0012) -[2023-11-28 03:49:51,198][87426] Updated weights for policy 1, policy_version 137990 (0.0011) -[2023-11-28 03:49:51,583][87426] Updated weights for policy 1, policy_version 138000 (0.0012) -[2023-11-28 03:49:51,955][87426] Updated weights for policy 1, policy_version 138010 (0.0011) -[2023-11-28 03:49:52,223][87424] Updated weights for policy 0, policy_version 138276 (0.0008) -[2023-11-28 03:49:52,610][87424] Updated weights for policy 0, policy_version 138286 (0.0010) -[2023-11-28 03:49:52,992][87424] Updated weights for policy 0, policy_version 138296 (0.0010) -[2023-11-28 03:49:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 70737920. Throughput: 0: 2738.8, 1: 2675.6. Samples: 70751156. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:49:53,445][86177] Avg episode reward: [(0, '-525.740'), (1, '-555.650')] -[2023-11-28 03:49:54,114][87426] Updated weights for policy 1, policy_version 138020 (0.0010) -[2023-11-28 03:49:54,510][87426] Updated weights for policy 1, policy_version 138030 (0.0009) -[2023-11-28 03:49:54,888][87426] Updated weights for policy 1, policy_version 138040 (0.0011) -[2023-11-28 03:49:54,985][87424] Updated weights for policy 0, policy_version 138306 (0.0010) -[2023-11-28 03:49:55,370][87424] Updated weights for policy 0, policy_version 138316 (0.0011) -[2023-11-28 03:49:55,753][87424] Updated weights for policy 0, policy_version 138326 (0.0010) -[2023-11-28 03:49:56,140][87424] Updated weights for policy 0, policy_version 138336 (0.0007) -[2023-11-28 03:49:56,957][87426] Updated weights for policy 1, policy_version 138050 (0.0010) -[2023-11-28 03:49:57,342][87426] Updated weights for policy 1, policy_version 138060 (0.0009) -[2023-11-28 03:49:57,725][87426] Updated weights for policy 1, policy_version 138070 (0.0007) -[2023-11-28 03:49:58,106][87426] Updated weights for policy 1, policy_version 138080 (0.0007) -[2023-11-28 03:49:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70762496. Throughput: 0: 2744.8, 1: 2695.0. Samples: 70775932. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:49:58,445][86177] Avg episode reward: [(0, '-535.630'), (1, '-514.680')] -[2023-11-28 03:49:58,513][87424] Updated weights for policy 0, policy_version 138346 (0.0007) -[2023-11-28 03:49:58,898][87424] Updated weights for policy 0, policy_version 138356 (0.0008) -[2023-11-28 03:49:59,296][87424] Updated weights for policy 0, policy_version 138366 (0.0009) -[2023-11-28 03:50:00,526][87426] Updated weights for policy 1, policy_version 138090 (0.0008) -[2023-11-28 03:50:00,905][87426] Updated weights for policy 1, policy_version 138100 (0.0007) -[2023-11-28 03:50:01,286][87426] Updated weights for policy 1, policy_version 138110 (0.0007) -[2023-11-28 03:50:01,630][87424] Updated weights for policy 0, policy_version 138376 (0.0008) -[2023-11-28 03:50:02,019][87424] Updated weights for policy 0, policy_version 138386 (0.0009) -[2023-11-28 03:50:02,392][87424] Updated weights for policy 0, policy_version 138396 (0.0008) -[2023-11-28 03:50:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 70787072. Throughput: 0: 2739.5, 1: 2703.9. Samples: 70800512. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:03,445][86177] Avg episode reward: [(0, '-535.740'), (1, '-512.080')] -[2023-11-28 03:50:03,630][87426] Updated weights for policy 1, policy_version 138120 (0.0011) -[2023-11-28 03:50:04,006][87426] Updated weights for policy 1, policy_version 138130 (0.0012) -[2023-11-28 03:50:04,399][87426] Updated weights for policy 1, policy_version 138140 (0.0012) -[2023-11-28 03:50:04,552][87424] Updated weights for policy 0, policy_version 138406 (0.0007) -[2023-11-28 03:50:04,943][87424] Updated weights for policy 0, policy_version 138416 (0.0010) -[2023-11-28 03:50:05,312][87424] Updated weights for policy 0, policy_version 138426 (0.0010) -[2023-11-28 03:50:06,850][87426] Updated weights for policy 1, policy_version 138150 (0.0010) -[2023-11-28 03:50:07,231][87426] Updated weights for policy 1, policy_version 138160 (0.0012) -[2023-11-28 03:50:07,601][87426] Updated weights for policy 1, policy_version 138170 (0.0012) -[2023-11-28 03:50:07,778][87424] Updated weights for policy 0, policy_version 138436 (0.0009) -[2023-11-28 03:50:08,161][87424] Updated weights for policy 0, policy_version 138446 (0.0008) -[2023-11-28 03:50:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 70811648. Throughput: 0: 2737.1, 1: 2684.3. Samples: 70831376. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:08,445][86177] Avg episode reward: [(0, '-510.870'), (1, '-503.310')] -[2023-11-28 03:50:08,541][87424] Updated weights for policy 0, policy_version 138456 (0.0007) -[2023-11-28 03:50:10,002][87426] Updated weights for policy 1, policy_version 138180 (0.0009) -[2023-11-28 03:50:10,376][87426] Updated weights for policy 1, policy_version 138190 (0.0008) -[2023-11-28 03:50:10,764][87426] Updated weights for policy 1, policy_version 138200 (0.0010) -[2023-11-28 03:50:10,936][87424] Updated weights for policy 0, policy_version 138466 (0.0024) -[2023-11-28 03:50:11,325][87424] Updated weights for policy 0, policy_version 138476 (0.0011) -[2023-11-28 03:50:11,710][87424] Updated weights for policy 0, policy_version 138486 (0.0008) -[2023-11-28 03:50:12,091][87424] Updated weights for policy 0, policy_version 138496 (0.0009) -[2023-11-28 03:50:13,291][87426] Updated weights for policy 1, policy_version 138210 (0.0011) -[2023-11-28 03:50:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 70836224. Throughput: 0: 2728.6, 1: 2658.5. Samples: 70854992. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:13,445][86177] Avg episode reward: [(0, '-509.340'), (1, '-526.580')] -[2023-11-28 03:50:13,670][87426] Updated weights for policy 1, policy_version 138220 (0.0011) -[2023-11-28 03:50:14,062][87426] Updated weights for policy 1, policy_version 138230 (0.0011) -[2023-11-28 03:50:14,172][87424] Updated weights for policy 0, policy_version 138506 (0.0009) -[2023-11-28 03:50:14,431][87426] Updated weights for policy 1, policy_version 138240 (0.0011) -[2023-11-28 03:50:14,550][87424] Updated weights for policy 0, policy_version 138516 (0.0009) -[2023-11-28 03:50:14,938][87424] Updated weights for policy 0, policy_version 138526 (0.0010) -[2023-11-28 03:50:16,099][87426] Updated weights for policy 1, policy_version 138250 (0.0012) -[2023-11-28 03:50:16,477][87426] Updated weights for policy 1, policy_version 138260 (0.0011) -[2023-11-28 03:50:16,857][87426] Updated weights for policy 1, policy_version 138270 (0.0009) -[2023-11-28 03:50:17,006][87424] Updated weights for policy 0, policy_version 138536 (0.0012) -[2023-11-28 03:50:17,393][87424] Updated weights for policy 0, policy_version 138546 (0.0011) -[2023-11-28 03:50:17,788][87424] Updated weights for policy 0, policy_version 138556 (0.0012) -[2023-11-28 03:50:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 70868992. Throughput: 0: 2727.9, 1: 2657.2. Samples: 70879684. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:18,445][86177] Avg episode reward: [(0, '-498.250'), (1, '-546.350')] -[2023-11-28 03:50:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000138272_35397632.pth... -[2023-11-28 03:50:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000138560_35471360.pth... -[2023-11-28 03:50:18,499][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000135744_34750464.pth -[2023-11-28 03:50:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000136032_34824192.pth -[2023-11-28 03:50:19,432][87426] Updated weights for policy 1, policy_version 138280 (0.0011) -[2023-11-28 03:50:19,608][87424] Updated weights for policy 0, policy_version 138566 (0.0009) -[2023-11-28 03:50:19,809][87426] Updated weights for policy 1, policy_version 138290 (0.0011) -[2023-11-28 03:50:19,990][87424] Updated weights for policy 0, policy_version 138576 (0.0009) -[2023-11-28 03:50:20,196][87426] Updated weights for policy 1, policy_version 138300 (0.0010) -[2023-11-28 03:50:20,375][87424] Updated weights for policy 0, policy_version 138586 (0.0010) -[2023-11-28 03:50:22,743][87426] Updated weights for policy 1, policy_version 138310 (0.0011) -[2023-11-28 03:50:22,871][87424] Updated weights for policy 0, policy_version 138596 (0.0011) -[2023-11-28 03:50:23,117][87426] Updated weights for policy 1, policy_version 138320 (0.0012) -[2023-11-28 03:50:23,254][87424] Updated weights for policy 0, policy_version 138606 (0.0012) -[2023-11-28 03:50:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 70885376. Throughput: 0: 2702.0, 1: 2626.5. Samples: 70910704. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:23,446][86177] Avg episode reward: [(0, '-497.060'), (1, '-547.980')] -[2023-11-28 03:50:23,494][87426] Updated weights for policy 1, policy_version 138330 (0.0009) -[2023-11-28 03:50:23,641][87424] Updated weights for policy 0, policy_version 138616 (0.0012) -[2023-11-28 03:50:25,737][87424] Updated weights for policy 0, policy_version 138626 (0.0011) -[2023-11-28 03:50:25,749][87426] Updated weights for policy 1, policy_version 138340 (0.0009) -[2023-11-28 03:50:26,125][87424] Updated weights for policy 0, policy_version 138636 (0.0012) -[2023-11-28 03:50:26,136][87426] Updated weights for policy 1, policy_version 138350 (0.0012) -[2023-11-28 03:50:26,507][87424] Updated weights for policy 0, policy_version 138646 (0.0011) -[2023-11-28 03:50:26,516][87426] Updated weights for policy 1, policy_version 138360 (0.0012) -[2023-11-28 03:50:26,890][87424] Updated weights for policy 0, policy_version 138656 (0.0011) -[2023-11-28 03:50:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 70918144. Throughput: 0: 2703.0, 1: 2656.0. Samples: 70935444. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:28,445][86177] Avg episode reward: [(0, '-539.790'), (1, '-575.750')] -[2023-11-28 03:50:28,703][87426] Updated weights for policy 1, policy_version 138370 (0.0011) -[2023-11-28 03:50:29,046][87424] Updated weights for policy 0, policy_version 138666 (0.0009) -[2023-11-28 03:50:29,074][87426] Updated weights for policy 1, policy_version 138380 (0.0012) -[2023-11-28 03:50:29,426][87424] Updated weights for policy 0, policy_version 138676 (0.0007) -[2023-11-28 03:50:29,447][87426] Updated weights for policy 1, policy_version 138390 (0.0011) -[2023-11-28 03:50:29,820][87424] Updated weights for policy 0, policy_version 138686 (0.0011) -[2023-11-28 03:50:29,827][87426] Updated weights for policy 1, policy_version 138400 (0.0008) -[2023-11-28 03:50:31,569][87426] Updated weights for policy 1, policy_version 138410 (0.0012) -[2023-11-28 03:50:31,947][87426] Updated weights for policy 1, policy_version 138420 (0.0009) -[2023-11-28 03:50:32,337][87426] Updated weights for policy 1, policy_version 138430 (0.0012) -[2023-11-28 03:50:32,360][87424] Updated weights for policy 0, policy_version 138696 (0.0010) -[2023-11-28 03:50:32,736][87424] Updated weights for policy 0, policy_version 138706 (0.0012) -[2023-11-28 03:50:33,123][87424] Updated weights for policy 0, policy_version 138716 (0.0012) -[2023-11-28 03:50:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 70950912. Throughput: 0: 2688.2, 1: 2648.0. Samples: 70959120. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:33,445][86177] Avg episode reward: [(0, '-541.440'), (1, '-563.170')] -[2023-11-28 03:50:34,353][87426] Updated weights for policy 1, policy_version 138440 (0.0008) -[2023-11-28 03:50:34,744][87426] Updated weights for policy 1, policy_version 138450 (0.0008) -[2023-11-28 03:50:35,033][87424] Updated weights for policy 0, policy_version 138726 (0.0012) -[2023-11-28 03:50:35,126][87426] Updated weights for policy 1, policy_version 138460 (0.0011) -[2023-11-28 03:50:35,411][87424] Updated weights for policy 0, policy_version 138736 (0.0010) -[2023-11-28 03:50:35,795][87424] Updated weights for policy 0, policy_version 138746 (0.0007) -[2023-11-28 03:50:37,537][87426] Updated weights for policy 1, policy_version 138470 (0.0010) -[2023-11-28 03:50:37,915][87426] Updated weights for policy 1, policy_version 138480 (0.0009) -[2023-11-28 03:50:38,202][87424] Updated weights for policy 0, policy_version 138756 (0.0010) -[2023-11-28 03:50:38,296][87426] Updated weights for policy 1, policy_version 138490 (0.0010) -[2023-11-28 03:50:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 70967296. Throughput: 0: 2687.8, 1: 2670.8. Samples: 70992292. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:38,445][86177] Avg episode reward: [(0, '-546.460'), (1, '-551.810')] -[2023-11-28 03:50:38,584][87424] Updated weights for policy 0, policy_version 138766 (0.0009) -[2023-11-28 03:50:38,975][87424] Updated weights for policy 0, policy_version 138776 (0.0012) -[2023-11-28 03:50:40,805][87426] Updated weights for policy 1, policy_version 138500 (0.0011) -[2023-11-28 03:50:41,178][87426] Updated weights for policy 1, policy_version 138510 (0.0011) -[2023-11-28 03:50:41,207][87424] Updated weights for policy 0, policy_version 138786 (0.0011) -[2023-11-28 03:50:41,562][87426] Updated weights for policy 1, policy_version 138520 (0.0008) -[2023-11-28 03:50:41,587][87424] Updated weights for policy 0, policy_version 138796 (0.0012) -[2023-11-28 03:50:41,968][87424] Updated weights for policy 0, policy_version 138806 (0.0012) -[2023-11-28 03:50:42,341][87424] Updated weights for policy 0, policy_version 138816 (0.0012) -[2023-11-28 03:50:43,339][87426] Updated weights for policy 1, policy_version 138530 (0.0011) -[2023-11-28 03:50:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 71000064. Throughput: 0: 2683.5, 1: 2669.0. Samples: 71016796. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:43,445][86177] Avg episode reward: [(0, '-509.880'), (1, '-538.400')] -[2023-11-28 03:50:43,727][87426] Updated weights for policy 1, policy_version 138540 (0.0012) -[2023-11-28 03:50:44,107][87426] Updated weights for policy 1, policy_version 138550 (0.0012) -[2023-11-28 03:50:44,426][87424] Updated weights for policy 0, policy_version 138826 (0.0012) -[2023-11-28 03:50:44,489][87426] Updated weights for policy 1, policy_version 138560 (0.0012) -[2023-11-28 03:50:44,808][87424] Updated weights for policy 0, policy_version 138836 (0.0012) -[2023-11-28 03:50:45,200][87424] Updated weights for policy 0, policy_version 138846 (0.0012) -[2023-11-28 03:50:46,373][87426] Updated weights for policy 1, policy_version 138570 (0.0011) -[2023-11-28 03:50:46,747][87426] Updated weights for policy 1, policy_version 138580 (0.0011) -[2023-11-28 03:50:47,125][87426] Updated weights for policy 1, policy_version 138590 (0.0010) -[2023-11-28 03:50:47,487][87424] Updated weights for policy 0, policy_version 138856 (0.0011) -[2023-11-28 03:50:47,876][87424] Updated weights for policy 0, policy_version 138866 (0.0012) -[2023-11-28 03:50:48,261][87424] Updated weights for policy 0, policy_version 138876 (0.0012) -[2023-11-28 03:50:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71032832. Throughput: 0: 2682.9, 1: 2663.2. Samples: 71041088. Policy #0 lag: (min: 31.0, avg: 45.6, max: 63.0) -[2023-11-28 03:50:48,446][86177] Avg episode reward: [(0, '-510.490'), (1, '-571.980')] -[2023-11-28 03:50:49,661][87426] Updated weights for policy 1, policy_version 138600 (0.0011) -[2023-11-28 03:50:50,047][87426] Updated weights for policy 1, policy_version 138610 (0.0011) -[2023-11-28 03:50:50,097][87424] Updated weights for policy 0, policy_version 138886 (0.0011) -[2023-11-28 03:50:50,442][87426] Updated weights for policy 1, policy_version 138620 (0.0011) -[2023-11-28 03:50:50,473][87424] Updated weights for policy 0, policy_version 138896 (0.0011) -[2023-11-28 03:50:50,870][87424] Updated weights for policy 0, policy_version 138906 (0.0008) -[2023-11-28 03:50:52,292][87426] Updated weights for policy 1, policy_version 138630 (0.0012) -[2023-11-28 03:50:52,669][87426] Updated weights for policy 1, policy_version 138640 (0.0012) -[2023-11-28 03:50:53,045][87426] Updated weights for policy 1, policy_version 138650 (0.0011) -[2023-11-28 03:50:53,410][87424] Updated weights for policy 0, policy_version 138916 (0.0011) -[2023-11-28 03:50:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 71057408. Throughput: 0: 2683.4, 1: 2693.2. Samples: 71073320. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:50:53,445][86177] Avg episode reward: [(0, '-511.380'), (1, '-542.270')] -[2023-11-28 03:50:53,787][87424] Updated weights for policy 0, policy_version 138926 (0.0012) -[2023-11-28 03:50:54,174][87424] Updated weights for policy 0, policy_version 138936 (0.0012) -[2023-11-28 03:50:55,383][87426] Updated weights for policy 1, policy_version 138660 (0.0010) -[2023-11-28 03:50:55,762][87426] Updated weights for policy 1, policy_version 138670 (0.0010) -[2023-11-28 03:50:56,142][87426] Updated weights for policy 1, policy_version 138680 (0.0007) -[2023-11-28 03:50:56,638][87424] Updated weights for policy 0, policy_version 138946 (0.0011) -[2023-11-28 03:50:57,027][87424] Updated weights for policy 0, policy_version 138956 (0.0007) -[2023-11-28 03:50:57,419][87424] Updated weights for policy 0, policy_version 138966 (0.0007) -[2023-11-28 03:50:57,799][87424] Updated weights for policy 0, policy_version 138976 (0.0007) -[2023-11-28 03:50:58,439][87426] Updated weights for policy 1, policy_version 138690 (0.0008) -[2023-11-28 03:50:58,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 71081984. Throughput: 0: 2681.7, 1: 2693.5. Samples: 71096876. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:50:58,446][86177] Avg episode reward: [(0, '-509.860'), (1, '-571.220')] -[2023-11-28 03:50:58,828][87426] Updated weights for policy 1, policy_version 138700 (0.0011) -[2023-11-28 03:50:59,199][87426] Updated weights for policy 1, policy_version 138710 (0.0010) -[2023-11-28 03:50:59,579][87426] Updated weights for policy 1, policy_version 138720 (0.0011) -[2023-11-28 03:50:59,809][87424] Updated weights for policy 0, policy_version 138986 (0.0012) -[2023-11-28 03:51:00,187][87424] Updated weights for policy 0, policy_version 138996 (0.0012) -[2023-11-28 03:51:00,565][87424] Updated weights for policy 0, policy_version 139006 (0.0010) -[2023-11-28 03:51:01,742][87426] Updated weights for policy 1, policy_version 138730 (0.0010) -[2023-11-28 03:51:02,121][87426] Updated weights for policy 1, policy_version 138740 (0.0011) -[2023-11-28 03:51:02,496][87426] Updated weights for policy 1, policy_version 138750 (0.0009) -[2023-11-28 03:51:02,855][87424] Updated weights for policy 0, policy_version 139016 (0.0010) -[2023-11-28 03:51:03,245][87424] Updated weights for policy 0, policy_version 139026 (0.0011) -[2023-11-28 03:51:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 71106560. Throughput: 0: 2677.9, 1: 2695.1. Samples: 71121468. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:03,445][86177] Avg episode reward: [(0, '-505.460'), (1, '-585.650')] -[2023-11-28 03:51:03,626][87424] Updated weights for policy 0, policy_version 139036 (0.0008) -[2023-11-28 03:51:04,473][87426] Updated weights for policy 1, policy_version 138760 (0.0010) -[2023-11-28 03:51:04,860][87426] Updated weights for policy 1, policy_version 138770 (0.0012) -[2023-11-28 03:51:05,238][87426] Updated weights for policy 1, policy_version 138780 (0.0011) -[2023-11-28 03:51:05,655][87424] Updated weights for policy 0, policy_version 139046 (0.0010) -[2023-11-28 03:51:06,027][87424] Updated weights for policy 0, policy_version 139056 (0.0012) -[2023-11-28 03:51:06,417][87424] Updated weights for policy 0, policy_version 139066 (0.0012) -[2023-11-28 03:51:07,757][87426] Updated weights for policy 1, policy_version 138790 (0.0012) -[2023-11-28 03:51:08,133][87426] Updated weights for policy 1, policy_version 138800 (0.0012) -[2023-11-28 03:51:08,216][87424] Updated weights for policy 0, policy_version 139076 (0.0012) -[2023-11-28 03:51:08,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 71131136. Throughput: 0: 2695.2, 1: 2728.5. Samples: 71154768. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:08,445][86177] Avg episode reward: [(0, '-510.950'), (1, '-543.550')] -[2023-11-28 03:51:08,499][87426] Updated weights for policy 1, policy_version 138810 (0.0011) -[2023-11-28 03:51:08,600][87424] Updated weights for policy 0, policy_version 139086 (0.0009) -[2023-11-28 03:51:08,968][87424] Updated weights for policy 0, policy_version 139096 (0.0011) -[2023-11-28 03:51:10,939][87426] Updated weights for policy 1, policy_version 138820 (0.0010) -[2023-11-28 03:51:11,185][87424] Updated weights for policy 0, policy_version 139106 (0.0010) -[2023-11-28 03:51:11,323][87426] Updated weights for policy 1, policy_version 138830 (0.0009) -[2023-11-28 03:51:11,568][87424] Updated weights for policy 0, policy_version 139116 (0.0008) -[2023-11-28 03:51:11,697][87426] Updated weights for policy 1, policy_version 138840 (0.0011) -[2023-11-28 03:51:11,957][87424] Updated weights for policy 0, policy_version 139126 (0.0011) -[2023-11-28 03:51:12,334][87424] Updated weights for policy 0, policy_version 139136 (0.0010) -[2023-11-28 03:51:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 71163904. Throughput: 0: 2705.8, 1: 2700.6. Samples: 71178732. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:13,445][86177] Avg episode reward: [(0, '-524.680'), (1, '-542.560')] -[2023-11-28 03:51:13,943][87426] Updated weights for policy 1, policy_version 138850 (0.0010) -[2023-11-28 03:51:14,319][87426] Updated weights for policy 1, policy_version 138860 (0.0008) -[2023-11-28 03:51:14,407][87424] Updated weights for policy 0, policy_version 139146 (0.0012) -[2023-11-28 03:51:14,695][87426] Updated weights for policy 1, policy_version 138870 (0.0007) -[2023-11-28 03:51:14,795][87424] Updated weights for policy 0, policy_version 139156 (0.0012) -[2023-11-28 03:51:15,076][87426] Updated weights for policy 1, policy_version 138880 (0.0010) -[2023-11-28 03:51:15,176][87424] Updated weights for policy 0, policy_version 139166 (0.0012) -[2023-11-28 03:51:17,028][87424] Updated weights for policy 0, policy_version 139176 (0.0011) -[2023-11-28 03:51:17,219][87426] Updated weights for policy 1, policy_version 138890 (0.0012) -[2023-11-28 03:51:17,411][87424] Updated weights for policy 0, policy_version 139186 (0.0012) -[2023-11-28 03:51:17,601][87426] Updated weights for policy 1, policy_version 138900 (0.0011) -[2023-11-28 03:51:17,791][87424] Updated weights for policy 0, policy_version 139196 (0.0008) -[2023-11-28 03:51:17,981][87426] Updated weights for policy 1, policy_version 138910 (0.0011) -[2023-11-28 03:51:18,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71196672. Throughput: 0: 2729.3, 1: 2710.4. Samples: 71203904. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:18,445][86177] Avg episode reward: [(0, '-526.300'), (1, '-511.630')] -[2023-11-28 03:51:19,857][87424] Updated weights for policy 0, policy_version 139206 (0.0008) -[2023-11-28 03:51:20,045][87426] Updated weights for policy 1, policy_version 138920 (0.0011) -[2023-11-28 03:51:20,233][87424] Updated weights for policy 0, policy_version 139216 (0.0011) -[2023-11-28 03:51:20,415][87426] Updated weights for policy 1, policy_version 138930 (0.0010) -[2023-11-28 03:51:20,618][87424] Updated weights for policy 0, policy_version 139226 (0.0012) -[2023-11-28 03:51:20,795][87426] Updated weights for policy 1, policy_version 138940 (0.0012) -[2023-11-28 03:51:23,067][87424] Updated weights for policy 0, policy_version 139236 (0.0010) -[2023-11-28 03:51:23,352][87426] Updated weights for policy 1, policy_version 138950 (0.0010) -[2023-11-28 03:51:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 71213056. Throughput: 0: 2729.2, 1: 2687.9. Samples: 71236060. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:23,445][87424] Updated weights for policy 0, policy_version 139246 (0.0008) -[2023-11-28 03:51:23,445][86177] Avg episode reward: [(0, '-521.350'), (1, '-507.850')] -[2023-11-28 03:51:23,727][87426] Updated weights for policy 1, policy_version 138960 (0.0009) -[2023-11-28 03:51:23,834][87424] Updated weights for policy 0, policy_version 139256 (0.0011) -[2023-11-28 03:51:24,117][87426] Updated weights for policy 1, policy_version 138970 (0.0010) -[2023-11-28 03:51:25,816][87424] Updated weights for policy 0, policy_version 139266 (0.0012) -[2023-11-28 03:51:26,179][87426] Updated weights for policy 1, policy_version 138980 (0.0010) -[2023-11-28 03:51:26,199][87424] Updated weights for policy 0, policy_version 139276 (0.0012) -[2023-11-28 03:51:26,549][87426] Updated weights for policy 1, policy_version 138990 (0.0008) -[2023-11-28 03:51:26,579][87424] Updated weights for policy 0, policy_version 139286 (0.0012) -[2023-11-28 03:51:26,928][87426] Updated weights for policy 1, policy_version 139000 (0.0007) -[2023-11-28 03:51:26,960][87424] Updated weights for policy 0, policy_version 139296 (0.0012) -[2023-11-28 03:51:28,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 71245824. Throughput: 0: 2742.9, 1: 2688.5. Samples: 71261212. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:28,446][86177] Avg episode reward: [(0, '-512.180'), (1, '-516.280')] -[2023-11-28 03:51:28,878][87426] Updated weights for policy 1, policy_version 139010 (0.0008) -[2023-11-28 03:51:29,158][87424] Updated weights for policy 0, policy_version 139306 (0.0012) -[2023-11-28 03:51:29,256][87426] Updated weights for policy 1, policy_version 139020 (0.0010) -[2023-11-28 03:51:29,542][87424] Updated weights for policy 0, policy_version 139316 (0.0012) -[2023-11-28 03:51:29,639][87426] Updated weights for policy 1, policy_version 139030 (0.0010) -[2023-11-28 03:51:29,927][87424] Updated weights for policy 0, policy_version 139326 (0.0012) -[2023-11-28 03:51:30,020][87426] Updated weights for policy 1, policy_version 139040 (0.0009) -[2023-11-28 03:51:31,669][87424] Updated weights for policy 0, policy_version 139336 (0.0011) -[2023-11-28 03:51:31,946][87426] Updated weights for policy 1, policy_version 139050 (0.0012) -[2023-11-28 03:51:32,054][87424] Updated weights for policy 0, policy_version 139346 (0.0010) -[2023-11-28 03:51:32,329][87426] Updated weights for policy 1, policy_version 139060 (0.0010) -[2023-11-28 03:51:32,437][87424] Updated weights for policy 0, policy_version 139356 (0.0011) -[2023-11-28 03:51:32,714][87426] Updated weights for policy 1, policy_version 139070 (0.0012) -[2023-11-28 03:51:33,445][86177] Fps is (10 sec: 6553.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71278592. Throughput: 0: 2753.6, 1: 2713.9. Samples: 71287124. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:33,446][86177] Avg episode reward: [(0, '-522.180'), (1, '-519.240')] -[2023-11-28 03:51:34,600][87424] Updated weights for policy 0, policy_version 139366 (0.0011) -[2023-11-28 03:51:34,856][87426] Updated weights for policy 1, policy_version 139080 (0.0012) -[2023-11-28 03:51:34,979][87424] Updated weights for policy 0, policy_version 139376 (0.0011) -[2023-11-28 03:51:35,234][87426] Updated weights for policy 1, policy_version 139090 (0.0011) -[2023-11-28 03:51:35,354][87424] Updated weights for policy 0, policy_version 139386 (0.0012) -[2023-11-28 03:51:35,611][87426] Updated weights for policy 1, policy_version 139100 (0.0012) -[2023-11-28 03:51:37,513][87424] Updated weights for policy 0, policy_version 139396 (0.0011) -[2023-11-28 03:51:37,767][87426] Updated weights for policy 1, policy_version 139110 (0.0008) -[2023-11-28 03:51:37,895][87424] Updated weights for policy 0, policy_version 139406 (0.0009) -[2023-11-28 03:51:38,144][87426] Updated weights for policy 1, policy_version 139120 (0.0007) -[2023-11-28 03:51:38,279][87424] Updated weights for policy 0, policy_version 139416 (0.0008) -[2023-11-28 03:51:38,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 71294976. Throughput: 0: 2774.9, 1: 2712.5. Samples: 71320252. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:38,445][86177] Avg episode reward: [(0, '-515.460'), (1, '-533.000')] -[2023-11-28 03:51:38,525][87426] Updated weights for policy 1, policy_version 139130 (0.0008) -[2023-11-28 03:51:40,447][87424] Updated weights for policy 0, policy_version 139426 (0.0008) -[2023-11-28 03:51:40,455][87426] Updated weights for policy 1, policy_version 139140 (0.0009) -[2023-11-28 03:51:40,826][87424] Updated weights for policy 0, policy_version 139436 (0.0011) -[2023-11-28 03:51:40,836][87426] Updated weights for policy 1, policy_version 139150 (0.0008) -[2023-11-28 03:51:41,210][87424] Updated weights for policy 0, policy_version 139446 (0.0011) -[2023-11-28 03:51:41,216][87426] Updated weights for policy 1, policy_version 139160 (0.0011) -[2023-11-28 03:51:41,597][87424] Updated weights for policy 0, policy_version 139456 (0.0010) -[2023-11-28 03:51:43,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 71327744. Throughput: 0: 2778.5, 1: 2700.0. Samples: 71343408. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:43,445][86177] Avg episode reward: [(0, '-511.580'), (1, '-520.530')] -[2023-11-28 03:51:43,608][87426] Updated weights for policy 1, policy_version 139170 (0.0012) -[2023-11-28 03:51:43,804][87424] Updated weights for policy 0, policy_version 139466 (0.0009) -[2023-11-28 03:51:43,990][87426] Updated weights for policy 1, policy_version 139180 (0.0011) -[2023-11-28 03:51:44,184][87424] Updated weights for policy 0, policy_version 139476 (0.0012) -[2023-11-28 03:51:44,366][87426] Updated weights for policy 1, policy_version 139190 (0.0012) -[2023-11-28 03:51:44,565][87424] Updated weights for policy 0, policy_version 139486 (0.0011) -[2023-11-28 03:51:44,746][87426] Updated weights for policy 1, policy_version 139200 (0.0011) -[2023-11-28 03:51:46,694][87424] Updated weights for policy 0, policy_version 139496 (0.0011) -[2023-11-28 03:51:46,814][87426] Updated weights for policy 1, policy_version 139210 (0.0012) -[2023-11-28 03:51:47,073][87424] Updated weights for policy 0, policy_version 139506 (0.0010) -[2023-11-28 03:51:47,201][87426] Updated weights for policy 1, policy_version 139220 (0.0011) -[2023-11-28 03:51:47,460][87424] Updated weights for policy 0, policy_version 139516 (0.0007) -[2023-11-28 03:51:47,576][87426] Updated weights for policy 1, policy_version 139230 (0.0011) -[2023-11-28 03:51:48,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71360512. Throughput: 0: 2786.8, 1: 2699.7. Samples: 71368364. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:48,446][86177] Avg episode reward: [(0, '-500.260'), (1, '-513.280')] -[2023-11-28 03:51:49,535][87424] Updated weights for policy 0, policy_version 139526 (0.0010) -[2023-11-28 03:51:49,915][87424] Updated weights for policy 0, policy_version 139536 (0.0011) -[2023-11-28 03:51:50,032][87426] Updated weights for policy 1, policy_version 139240 (0.0010) -[2023-11-28 03:51:50,296][87424] Updated weights for policy 0, policy_version 139546 (0.0011) -[2023-11-28 03:51:50,406][87426] Updated weights for policy 1, policy_version 139250 (0.0008) -[2023-11-28 03:51:50,783][87426] Updated weights for policy 1, policy_version 139260 (0.0012) -[2023-11-28 03:51:52,122][87424] Updated weights for policy 0, policy_version 139556 (0.0012) -[2023-11-28 03:51:52,506][87424] Updated weights for policy 0, policy_version 139566 (0.0010) -[2023-11-28 03:51:52,888][87424] Updated weights for policy 0, policy_version 139576 (0.0011) -[2023-11-28 03:51:53,118][87426] Updated weights for policy 1, policy_version 139270 (0.0010) -[2023-11-28 03:51:53,445][86177] Fps is (10 sec: 5734.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 71385088. Throughput: 0: 2780.4, 1: 2699.7. Samples: 71401376. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 03:51:53,446][86177] Avg episode reward: [(0, '-497.920'), (1, '-517.960')] -[2023-11-28 03:51:53,500][87426] Updated weights for policy 1, policy_version 139280 (0.0010) -[2023-11-28 03:51:53,884][87426] Updated weights for policy 1, policy_version 139290 (0.0009) -[2023-11-28 03:51:55,438][87424] Updated weights for policy 0, policy_version 139586 (0.0011) -[2023-11-28 03:51:55,809][87424] Updated weights for policy 0, policy_version 139596 (0.0011) -[2023-11-28 03:51:56,205][87424] Updated weights for policy 0, policy_version 139606 (0.0011) -[2023-11-28 03:51:56,312][87426] Updated weights for policy 1, policy_version 139300 (0.0011) -[2023-11-28 03:51:56,590][87424] Updated weights for policy 0, policy_version 139616 (0.0009) -[2023-11-28 03:51:56,681][87426] Updated weights for policy 1, policy_version 139310 (0.0009) -[2023-11-28 03:51:57,052][87426] Updated weights for policy 1, policy_version 139320 (0.0007) -[2023-11-28 03:51:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 71409664. Throughput: 0: 2766.2, 1: 2734.9. Samples: 71426284. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:51:58,445][86177] Avg episode reward: [(0, '-509.690'), (1, '-499.900')] -[2023-11-28 03:51:58,562][87424] Updated weights for policy 0, policy_version 139626 (0.0008) -[2023-11-28 03:51:58,760][87426] Updated weights for policy 1, policy_version 139330 (0.0008) -[2023-11-28 03:51:58,948][87424] Updated weights for policy 0, policy_version 139636 (0.0009) -[2023-11-28 03:51:59,128][87426] Updated weights for policy 1, policy_version 139340 (0.0011) -[2023-11-28 03:51:59,324][87424] Updated weights for policy 0, policy_version 139646 (0.0011) -[2023-11-28 03:51:59,518][87426] Updated weights for policy 1, policy_version 139350 (0.0012) -[2023-11-28 03:51:59,893][87426] Updated weights for policy 1, policy_version 139360 (0.0011) -[2023-11-28 03:52:01,425][87424] Updated weights for policy 0, policy_version 139656 (0.0011) -[2023-11-28 03:52:01,818][87424] Updated weights for policy 0, policy_version 139666 (0.0011) -[2023-11-28 03:52:02,015][87426] Updated weights for policy 1, policy_version 139370 (0.0011) -[2023-11-28 03:52:02,199][87424] Updated weights for policy 0, policy_version 139676 (0.0011) -[2023-11-28 03:52:02,397][87426] Updated weights for policy 1, policy_version 139380 (0.0009) -[2023-11-28 03:52:02,773][87426] Updated weights for policy 1, policy_version 139390 (0.0007) -[2023-11-28 03:52:03,444][86177] Fps is (10 sec: 5734.8, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 71442432. Throughput: 0: 2758.5, 1: 2747.5. Samples: 71451672. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:03,445][86177] Avg episode reward: [(0, '-514.060'), (1, '-510.980')] -[2023-11-28 03:52:04,449][87424] Updated weights for policy 0, policy_version 139686 (0.0009) -[2023-11-28 03:52:04,821][87424] Updated weights for policy 0, policy_version 139696 (0.0007) -[2023-11-28 03:52:05,201][87424] Updated weights for policy 0, policy_version 139706 (0.0007) -[2023-11-28 03:52:05,303][87426] Updated weights for policy 1, policy_version 139400 (0.0008) -[2023-11-28 03:52:05,682][87426] Updated weights for policy 1, policy_version 139410 (0.0007) -[2023-11-28 03:52:06,062][87426] Updated weights for policy 1, policy_version 139420 (0.0008) -[2023-11-28 03:52:07,613][87424] Updated weights for policy 0, policy_version 139716 (0.0009) -[2023-11-28 03:52:08,004][87424] Updated weights for policy 0, policy_version 139726 (0.0010) -[2023-11-28 03:52:08,377][87424] Updated weights for policy 0, policy_version 139736 (0.0011) -[2023-11-28 03:52:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 71458816. Throughput: 0: 2747.5, 1: 2735.6. Samples: 71482796. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:08,445][86177] Avg episode reward: [(0, '-513.950'), (1, '-513.510')] -[2023-11-28 03:52:08,462][87426] Updated weights for policy 1, policy_version 139430 (0.0010) -[2023-11-28 03:52:08,830][87426] Updated weights for policy 1, policy_version 139440 (0.0011) -[2023-11-28 03:52:09,210][87426] Updated weights for policy 1, policy_version 139450 (0.0012) -[2023-11-28 03:52:10,759][87424] Updated weights for policy 0, policy_version 139746 (0.0008) -[2023-11-28 03:52:11,029][87426] Updated weights for policy 1, policy_version 139460 (0.0012) -[2023-11-28 03:52:11,137][87424] Updated weights for policy 0, policy_version 139756 (0.0011) -[2023-11-28 03:52:11,409][87426] Updated weights for policy 1, policy_version 139470 (0.0011) -[2023-11-28 03:52:11,517][87424] Updated weights for policy 0, policy_version 139766 (0.0011) -[2023-11-28 03:52:11,789][87426] Updated weights for policy 1, policy_version 139480 (0.0010) -[2023-11-28 03:52:11,898][87424] Updated weights for policy 0, policy_version 139776 (0.0011) -[2023-11-28 03:52:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71491584. Throughput: 0: 2720.6, 1: 2719.1. Samples: 71506000. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:13,445][86177] Avg episode reward: [(0, '-516.940'), (1, '-542.290')] -[2023-11-28 03:52:13,756][87426] Updated weights for policy 1, policy_version 139490 (0.0010) -[2023-11-28 03:52:13,830][87424] Updated weights for policy 0, policy_version 139786 (0.0012) -[2023-11-28 03:52:14,130][87426] Updated weights for policy 1, policy_version 139500 (0.0010) -[2023-11-28 03:52:14,205][87424] Updated weights for policy 0, policy_version 139796 (0.0011) -[2023-11-28 03:52:14,507][87426] Updated weights for policy 1, policy_version 139510 (0.0008) -[2023-11-28 03:52:14,596][87424] Updated weights for policy 0, policy_version 139806 (0.0010) -[2023-11-28 03:52:14,885][87426] Updated weights for policy 1, policy_version 139520 (0.0007) -[2023-11-28 03:52:16,449][87424] Updated weights for policy 0, policy_version 139816 (0.0010) -[2023-11-28 03:52:16,738][87426] Updated weights for policy 1, policy_version 139530 (0.0011) -[2023-11-28 03:52:16,820][87424] Updated weights for policy 0, policy_version 139826 (0.0011) -[2023-11-28 03:52:17,112][87426] Updated weights for policy 1, policy_version 139540 (0.0010) -[2023-11-28 03:52:17,205][87424] Updated weights for policy 0, policy_version 139836 (0.0012) -[2023-11-28 03:52:17,488][87426] Updated weights for policy 1, policy_version 139550 (0.0011) -[2023-11-28 03:52:18,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71524352. Throughput: 0: 2731.0, 1: 2705.5. Samples: 71531768. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:18,445][86177] Avg episode reward: [(0, '-510.070'), (1, '-550.970')] -[2023-11-28 03:52:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000139552_35725312.pth... -[2023-11-28 03:52:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000139840_35799040.pth... -[2023-11-28 03:52:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000137024_35078144.pth -[2023-11-28 03:52:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000137312_35151872.pth -[2023-11-28 03:52:18,511][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000139552_35725312.pth -[2023-11-28 03:52:18,512][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000139840_35799040.pth -[2023-11-28 03:52:19,092][87424] Updated weights for policy 0, policy_version 139846 (0.0011) -[2023-11-28 03:52:19,479][87424] Updated weights for policy 0, policy_version 139856 (0.0011) -[2023-11-28 03:52:19,687][87426] Updated weights for policy 1, policy_version 139560 (0.0012) -[2023-11-28 03:52:19,869][87424] Updated weights for policy 0, policy_version 139866 (0.0012) -[2023-11-28 03:52:20,071][87426] Updated weights for policy 1, policy_version 139570 (0.0011) -[2023-11-28 03:52:20,448][87426] Updated weights for policy 1, policy_version 139580 (0.0011) -[2023-11-28 03:52:22,011][87424] Updated weights for policy 0, policy_version 139877 (0.0010) -[2023-11-28 03:52:22,397][87424] Updated weights for policy 0, policy_version 139887 (0.0010) -[2023-11-28 03:52:22,679][87426] Updated weights for policy 1, policy_version 139590 (0.0012) -[2023-11-28 03:52:22,773][87424] Updated weights for policy 0, policy_version 139897 (0.0012) -[2023-11-28 03:52:23,061][87426] Updated weights for policy 1, policy_version 139600 (0.0012) -[2023-11-28 03:52:23,435][87426] Updated weights for policy 1, policy_version 139610 (0.0012) -[2023-11-28 03:52:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 71548928. Throughput: 0: 2740.1, 1: 2725.0. Samples: 71566180. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:23,445][86177] Avg episode reward: [(0, '-513.620'), (1, '-556.350')] -[2023-11-28 03:52:25,169][87424] Updated weights for policy 0, policy_version 139907 (0.0011) -[2023-11-28 03:52:25,544][87424] Updated weights for policy 0, policy_version 139917 (0.0007) -[2023-11-28 03:52:25,727][87426] Updated weights for policy 1, policy_version 139620 (0.0012) -[2023-11-28 03:52:25,930][87424] Updated weights for policy 0, policy_version 139927 (0.0009) -[2023-11-28 03:52:26,097][87426] Updated weights for policy 1, policy_version 139630 (0.0011) -[2023-11-28 03:52:26,483][87426] Updated weights for policy 1, policy_version 139640 (0.0011) -[2023-11-28 03:52:27,990][87424] Updated weights for policy 0, policy_version 139937 (0.0010) -[2023-11-28 03:52:28,371][87424] Updated weights for policy 0, policy_version 139947 (0.0011) -[2023-11-28 03:52:28,422][87426] Updated weights for policy 1, policy_version 139650 (0.0011) -[2023-11-28 03:52:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 71573504. Throughput: 0: 2742.0, 1: 2746.6. Samples: 71590392. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:28,445][86177] Avg episode reward: [(0, '-518.680'), (1, '-566.250')] -[2023-11-28 03:52:28,754][87424] Updated weights for policy 0, policy_version 139957 (0.0009) -[2023-11-28 03:52:28,804][87426] Updated weights for policy 1, policy_version 139660 (0.0008) -[2023-11-28 03:52:29,132][87424] Updated weights for policy 0, policy_version 139967 (0.0011) -[2023-11-28 03:52:29,186][87426] Updated weights for policy 1, policy_version 139670 (0.0007) -[2023-11-28 03:52:29,565][87426] Updated weights for policy 1, policy_version 139680 (0.0008) -[2023-11-28 03:52:30,906][87424] Updated weights for policy 0, policy_version 139977 (0.0011) -[2023-11-28 03:52:31,285][87424] Updated weights for policy 0, policy_version 139987 (0.0011) -[2023-11-28 03:52:31,514][87426] Updated weights for policy 1, policy_version 139690 (0.0007) -[2023-11-28 03:52:31,670][87424] Updated weights for policy 0, policy_version 139997 (0.0011) -[2023-11-28 03:52:31,892][87426] Updated weights for policy 1, policy_version 139700 (0.0010) -[2023-11-28 03:52:32,269][87426] Updated weights for policy 1, policy_version 139710 (0.0010) -[2023-11-28 03:52:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 71606272. Throughput: 0: 2745.3, 1: 2758.0. Samples: 71616008. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:33,445][86177] Avg episode reward: [(0, '-516.940'), (1, '-548.150')] -[2023-11-28 03:52:33,602][87424] Updated weights for policy 0, policy_version 140007 (0.0009) -[2023-11-28 03:52:33,991][87424] Updated weights for policy 0, policy_version 140017 (0.0007) -[2023-11-28 03:52:34,367][87424] Updated weights for policy 0, policy_version 140027 (0.0007) -[2023-11-28 03:52:34,657][87426] Updated weights for policy 1, policy_version 139720 (0.0008) -[2023-11-28 03:52:35,052][87426] Updated weights for policy 1, policy_version 139730 (0.0011) -[2023-11-28 03:52:35,425][87426] Updated weights for policy 1, policy_version 139740 (0.0012) -[2023-11-28 03:52:36,932][87424] Updated weights for policy 0, policy_version 140037 (0.0009) -[2023-11-28 03:52:37,310][87424] Updated weights for policy 0, policy_version 140047 (0.0012) -[2023-11-28 03:52:37,693][87424] Updated weights for policy 0, policy_version 140057 (0.0012) -[2023-11-28 03:52:37,865][87426] Updated weights for policy 1, policy_version 139750 (0.0009) -[2023-11-28 03:52:38,244][87426] Updated weights for policy 1, policy_version 139760 (0.0007) -[2023-11-28 03:52:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 71630848. Throughput: 0: 2727.1, 1: 2722.2. Samples: 71646588. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:38,445][86177] Avg episode reward: [(0, '-523.900'), (1, '-540.310')] -[2023-11-28 03:52:38,632][87426] Updated weights for policy 1, policy_version 139770 (0.0008) -[2023-11-28 03:52:40,258][87424] Updated weights for policy 0, policy_version 140067 (0.0010) -[2023-11-28 03:52:40,658][87424] Updated weights for policy 0, policy_version 140077 (0.0009) -[2023-11-28 03:52:40,981][87426] Updated weights for policy 1, policy_version 139780 (0.0012) -[2023-11-28 03:52:41,042][87424] Updated weights for policy 0, policy_version 140087 (0.0011) -[2023-11-28 03:52:41,353][87426] Updated weights for policy 1, policy_version 139790 (0.0009) -[2023-11-28 03:52:41,731][87426] Updated weights for policy 1, policy_version 139800 (0.0012) -[2023-11-28 03:52:42,988][87424] Updated weights for policy 0, policy_version 140097 (0.0012) -[2023-11-28 03:52:43,375][87424] Updated weights for policy 0, policy_version 140107 (0.0010) -[2023-11-28 03:52:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71655424. Throughput: 0: 2729.5, 1: 2694.0. Samples: 71670344. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:43,445][86177] Avg episode reward: [(0, '-520.830'), (1, '-523.810')] -[2023-11-28 03:52:43,683][87426] Updated weights for policy 1, policy_version 139810 (0.0009) -[2023-11-28 03:52:43,767][87424] Updated weights for policy 0, policy_version 140117 (0.0011) -[2023-11-28 03:52:44,062][87426] Updated weights for policy 1, policy_version 139820 (0.0007) -[2023-11-28 03:52:44,147][87424] Updated weights for policy 0, policy_version 140127 (0.0008) -[2023-11-28 03:52:44,442][87426] Updated weights for policy 1, policy_version 139830 (0.0007) -[2023-11-28 03:52:44,823][87426] Updated weights for policy 1, policy_version 139840 (0.0007) -[2023-11-28 03:52:46,484][87424] Updated weights for policy 0, policy_version 140137 (0.0008) -[2023-11-28 03:52:46,866][87424] Updated weights for policy 0, policy_version 140147 (0.0008) -[2023-11-28 03:52:47,248][87424] Updated weights for policy 0, policy_version 140157 (0.0008) -[2023-11-28 03:52:47,334][87426] Updated weights for policy 1, policy_version 139850 (0.0011) -[2023-11-28 03:52:47,711][87426] Updated weights for policy 1, policy_version 139860 (0.0011) -[2023-11-28 03:52:48,088][87426] Updated weights for policy 1, policy_version 139870 (0.0011) -[2023-11-28 03:52:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71688192. Throughput: 0: 2741.3, 1: 2673.7. Samples: 71695348. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:48,445][86177] Avg episode reward: [(0, '-518.420'), (1, '-515.320')] -[2023-11-28 03:52:49,409][87424] Updated weights for policy 0, policy_version 140167 (0.0009) -[2023-11-28 03:52:49,788][87424] Updated weights for policy 0, policy_version 140177 (0.0010) -[2023-11-28 03:52:50,171][87424] Updated weights for policy 0, policy_version 140187 (0.0009) -[2023-11-28 03:52:50,610][87426] Updated weights for policy 1, policy_version 139880 (0.0011) -[2023-11-28 03:52:50,992][87426] Updated weights for policy 1, policy_version 139890 (0.0009) -[2023-11-28 03:52:51,374][87426] Updated weights for policy 1, policy_version 139900 (0.0008) -[2023-11-28 03:52:52,660][87424] Updated weights for policy 0, policy_version 140197 (0.0011) -[2023-11-28 03:52:53,039][87424] Updated weights for policy 0, policy_version 140207 (0.0012) -[2023-11-28 03:52:53,424][87424] Updated weights for policy 0, policy_version 140217 (0.0012) -[2023-11-28 03:52:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.9, 300 sec: 5387.3). Total num frames: 71704576. Throughput: 0: 2740.3, 1: 2686.5. Samples: 71727000. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:53,445][86177] Avg episode reward: [(0, '-524.360'), (1, '-499.830')] -[2023-11-28 03:52:53,820][87426] Updated weights for policy 1, policy_version 139910 (0.0010) -[2023-11-28 03:52:54,190][87426] Updated weights for policy 1, policy_version 139920 (0.0009) -[2023-11-28 03:52:54,572][87426] Updated weights for policy 1, policy_version 139930 (0.0008) -[2023-11-28 03:52:55,778][87424] Updated weights for policy 0, policy_version 140227 (0.0010) -[2023-11-28 03:52:56,177][87424] Updated weights for policy 0, policy_version 140237 (0.0008) -[2023-11-28 03:52:56,557][87424] Updated weights for policy 0, policy_version 140247 (0.0009) -[2023-11-28 03:52:56,986][87426] Updated weights for policy 1, policy_version 139940 (0.0011) -[2023-11-28 03:52:57,373][87426] Updated weights for policy 1, policy_version 139950 (0.0012) -[2023-11-28 03:52:57,748][87426] Updated weights for policy 1, policy_version 139960 (0.0012) -[2023-11-28 03:52:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71737344. Throughput: 0: 2764.3, 1: 2689.2. Samples: 71751408. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 03:52:58,445][86177] Avg episode reward: [(0, '-523.960'), (1, '-540.490')] -[2023-11-28 03:52:58,681][87424] Updated weights for policy 0, policy_version 140257 (0.0008) -[2023-11-28 03:52:59,069][87424] Updated weights for policy 0, policy_version 140267 (0.0008) -[2023-11-28 03:52:59,455][87424] Updated weights for policy 0, policy_version 140277 (0.0007) -[2023-11-28 03:52:59,698][87426] Updated weights for policy 1, policy_version 139970 (0.0010) -[2023-11-28 03:52:59,848][87424] Updated weights for policy 0, policy_version 140287 (0.0008) -[2023-11-28 03:53:00,076][87426] Updated weights for policy 1, policy_version 139980 (0.0010) -[2023-11-28 03:53:00,453][87426] Updated weights for policy 1, policy_version 139990 (0.0011) -[2023-11-28 03:53:00,828][87426] Updated weights for policy 1, policy_version 140000 (0.0009) -[2023-11-28 03:53:02,227][87424] Updated weights for policy 0, policy_version 140297 (0.0010) -[2023-11-28 03:53:02,609][87424] Updated weights for policy 0, policy_version 140307 (0.0011) -[2023-11-28 03:53:02,910][87426] Updated weights for policy 1, policy_version 140010 (0.0009) -[2023-11-28 03:53:03,003][87424] Updated weights for policy 0, policy_version 140317 (0.0012) -[2023-11-28 03:53:03,287][87426] Updated weights for policy 1, policy_version 140020 (0.0011) -[2023-11-28 03:53:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 71761920. Throughput: 0: 2738.0, 1: 2675.3. Samples: 71775368. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:03,445][86177] Avg episode reward: [(0, '-523.060'), (1, '-550.370')] -[2023-11-28 03:53:03,668][87426] Updated weights for policy 1, policy_version 140030 (0.0008) -[2023-11-28 03:53:04,720][87424] Updated weights for policy 0, policy_version 140327 (0.0011) -[2023-11-28 03:53:05,104][87424] Updated weights for policy 0, policy_version 140337 (0.0012) -[2023-11-28 03:53:05,480][87424] Updated weights for policy 0, policy_version 140347 (0.0012) -[2023-11-28 03:53:06,127][87426] Updated weights for policy 1, policy_version 140040 (0.0011) -[2023-11-28 03:53:06,510][87426] Updated weights for policy 1, policy_version 140050 (0.0012) -[2023-11-28 03:53:06,882][87426] Updated weights for policy 1, policy_version 140060 (0.0012) -[2023-11-28 03:53:07,790][87424] Updated weights for policy 0, policy_version 140357 (0.0010) -[2023-11-28 03:53:08,175][87424] Updated weights for policy 0, policy_version 140367 (0.0009) -[2023-11-28 03:53:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 71786496. Throughput: 0: 2719.9, 1: 2673.8. Samples: 71808896. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:08,445][86177] Avg episode reward: [(0, '-520.420'), (1, '-545.330')] -[2023-11-28 03:53:08,557][87424] Updated weights for policy 0, policy_version 140377 (0.0010) -[2023-11-28 03:53:09,025][87426] Updated weights for policy 1, policy_version 140070 (0.0012) -[2023-11-28 03:53:09,407][87426] Updated weights for policy 1, policy_version 140080 (0.0012) -[2023-11-28 03:53:09,779][87426] Updated weights for policy 1, policy_version 140090 (0.0011) -[2023-11-28 03:53:10,549][87424] Updated weights for policy 0, policy_version 140387 (0.0010) -[2023-11-28 03:53:10,932][87424] Updated weights for policy 0, policy_version 140397 (0.0007) -[2023-11-28 03:53:11,318][87424] Updated weights for policy 0, policy_version 140407 (0.0008) -[2023-11-28 03:53:12,127][87426] Updated weights for policy 1, policy_version 140100 (0.0010) -[2023-11-28 03:53:12,508][87426] Updated weights for policy 1, policy_version 140110 (0.0010) -[2023-11-28 03:53:12,892][87426] Updated weights for policy 1, policy_version 140120 (0.0009) -[2023-11-28 03:53:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71819264. Throughput: 0: 2729.2, 1: 2658.2. Samples: 71832828. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:13,446][86177] Avg episode reward: [(0, '-535.400'), (1, '-542.610')] -[2023-11-28 03:53:13,632][87424] Updated weights for policy 0, policy_version 140417 (0.0012) -[2023-11-28 03:53:14,015][87424] Updated weights for policy 0, policy_version 140427 (0.0011) -[2023-11-28 03:53:14,394][87424] Updated weights for policy 0, policy_version 140437 (0.0008) -[2023-11-28 03:53:14,782][87424] Updated weights for policy 0, policy_version 140447 (0.0007) -[2023-11-28 03:53:14,881][87426] Updated weights for policy 1, policy_version 140130 (0.0009) -[2023-11-28 03:53:15,257][87426] Updated weights for policy 1, policy_version 140140 (0.0009) -[2023-11-28 03:53:15,636][87426] Updated weights for policy 1, policy_version 140150 (0.0008) -[2023-11-28 03:53:16,015][87426] Updated weights for policy 1, policy_version 140160 (0.0007) -[2023-11-28 03:53:17,080][87424] Updated weights for policy 0, policy_version 140457 (0.0012) -[2023-11-28 03:53:17,465][87424] Updated weights for policy 0, policy_version 140467 (0.0012) -[2023-11-28 03:53:17,849][87424] Updated weights for policy 0, policy_version 140477 (0.0012) -[2023-11-28 03:53:18,288][87426] Updated weights for policy 1, policy_version 140170 (0.0007) -[2023-11-28 03:53:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 71843840. Throughput: 0: 2710.8, 1: 2647.2. Samples: 71857120. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:18,445][86177] Avg episode reward: [(0, '-604.110'), (1, '-516.960')] -[2023-11-28 03:53:18,664][87426] Updated weights for policy 1, policy_version 140180 (0.0008) -[2023-11-28 03:53:19,045][87426] Updated weights for policy 1, policy_version 140190 (0.0009) -[2023-11-28 03:53:19,664][87424] Updated weights for policy 0, policy_version 140487 (0.0012) -[2023-11-28 03:53:20,045][87424] Updated weights for policy 0, policy_version 140497 (0.0011) -[2023-11-28 03:53:20,425][87424] Updated weights for policy 0, policy_version 140507 (0.0012) -[2023-11-28 03:53:21,219][87426] Updated weights for policy 1, policy_version 140200 (0.0011) -[2023-11-28 03:53:21,601][87426] Updated weights for policy 1, policy_version 140210 (0.0012) -[2023-11-28 03:53:21,983][87426] Updated weights for policy 1, policy_version 140220 (0.0012) -[2023-11-28 03:53:22,521][87424] Updated weights for policy 0, policy_version 140517 (0.0011) -[2023-11-28 03:53:22,901][87424] Updated weights for policy 0, policy_version 140527 (0.0009) -[2023-11-28 03:53:23,279][87424] Updated weights for policy 0, policy_version 140537 (0.0012) -[2023-11-28 03:53:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 71868416. Throughput: 0: 2730.2, 1: 2663.1. Samples: 71889288. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:23,445][86177] Avg episode reward: [(0, '-604.060'), (1, '-511.580')] -[2023-11-28 03:53:24,255][87426] Updated weights for policy 1, policy_version 140230 (0.0010) -[2023-11-28 03:53:24,633][87426] Updated weights for policy 1, policy_version 140240 (0.0008) -[2023-11-28 03:53:25,013][87426] Updated weights for policy 1, policy_version 140250 (0.0009) -[2023-11-28 03:53:25,194][87424] Updated weights for policy 0, policy_version 140547 (0.0012) -[2023-11-28 03:53:25,579][87424] Updated weights for policy 0, policy_version 140557 (0.0011) -[2023-11-28 03:53:25,949][87424] Updated weights for policy 0, policy_version 140567 (0.0011) -[2023-11-28 03:53:26,823][87426] Updated weights for policy 1, policy_version 140260 (0.0009) -[2023-11-28 03:53:27,197][87426] Updated weights for policy 1, policy_version 140270 (0.0007) -[2023-11-28 03:53:27,573][87426] Updated weights for policy 1, policy_version 140280 (0.0007) -[2023-11-28 03:53:28,050][87424] Updated weights for policy 0, policy_version 140577 (0.0012) -[2023-11-28 03:53:28,438][87424] Updated weights for policy 0, policy_version 140587 (0.0012) -[2023-11-28 03:53:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71901184. Throughput: 0: 2748.4, 1: 2687.6. Samples: 71914968. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:28,445][86177] Avg episode reward: [(0, '-600.820'), (1, '-514.990')] -[2023-11-28 03:53:28,813][87424] Updated weights for policy 0, policy_version 140597 (0.0012) -[2023-11-28 03:53:29,200][87424] Updated weights for policy 0, policy_version 140607 (0.0008) -[2023-11-28 03:53:30,118][87426] Updated weights for policy 1, policy_version 140290 (0.0008) -[2023-11-28 03:53:30,488][87426] Updated weights for policy 1, policy_version 140300 (0.0011) -[2023-11-28 03:53:30,873][87426] Updated weights for policy 1, policy_version 140310 (0.0010) -[2023-11-28 03:53:31,255][87426] Updated weights for policy 1, policy_version 140320 (0.0011) -[2023-11-28 03:53:31,703][87424] Updated weights for policy 0, policy_version 140617 (0.0008) -[2023-11-28 03:53:32,086][87424] Updated weights for policy 0, policy_version 140627 (0.0008) -[2023-11-28 03:53:32,465][87424] Updated weights for policy 0, policy_version 140637 (0.0009) -[2023-11-28 03:53:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 71925760. Throughput: 0: 2732.8, 1: 2693.5. Samples: 71939532. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:33,445][86177] Avg episode reward: [(0, '-582.780'), (1, '-521.590')] -[2023-11-28 03:53:33,485][87426] Updated weights for policy 1, policy_version 140330 (0.0011) -[2023-11-28 03:53:33,866][87426] Updated weights for policy 1, policy_version 140340 (0.0012) -[2023-11-28 03:53:34,241][87426] Updated weights for policy 1, policy_version 140350 (0.0011) -[2023-11-28 03:53:34,262][87424] Updated weights for policy 0, policy_version 140647 (0.0010) -[2023-11-28 03:53:34,646][87424] Updated weights for policy 0, policy_version 140657 (0.0011) -[2023-11-28 03:53:35,027][87424] Updated weights for policy 0, policy_version 140667 (0.0012) -[2023-11-28 03:53:36,130][87426] Updated weights for policy 1, policy_version 140360 (0.0008) -[2023-11-28 03:53:36,509][87426] Updated weights for policy 1, policy_version 140370 (0.0007) -[2023-11-28 03:53:36,835][87424] Updated weights for policy 0, policy_version 140677 (0.0012) -[2023-11-28 03:53:36,899][87426] Updated weights for policy 1, policy_version 140380 (0.0008) -[2023-11-28 03:53:37,220][87424] Updated weights for policy 0, policy_version 140687 (0.0012) -[2023-11-28 03:53:37,597][87424] Updated weights for policy 0, policy_version 140697 (0.0011) -[2023-11-28 03:53:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 71958528. Throughput: 0: 2763.6, 1: 2713.2. Samples: 71973460. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:38,445][86177] Avg episode reward: [(0, '-499.840'), (1, '-509.480')] -[2023-11-28 03:53:38,651][87426] Updated weights for policy 1, policy_version 140390 (0.0012) -[2023-11-28 03:53:39,033][87426] Updated weights for policy 1, policy_version 140400 (0.0011) -[2023-11-28 03:53:39,416][87426] Updated weights for policy 1, policy_version 140410 (0.0011) -[2023-11-28 03:53:39,945][87424] Updated weights for policy 0, policy_version 140707 (0.0012) -[2023-11-28 03:53:40,323][87424] Updated weights for policy 0, policy_version 140717 (0.0009) -[2023-11-28 03:53:40,707][87424] Updated weights for policy 0, policy_version 140727 (0.0011) -[2023-11-28 03:53:41,749][87426] Updated weights for policy 1, policy_version 140420 (0.0011) -[2023-11-28 03:53:42,133][87426] Updated weights for policy 1, policy_version 140430 (0.0012) -[2023-11-28 03:53:42,509][87426] Updated weights for policy 1, policy_version 140440 (0.0012) -[2023-11-28 03:53:43,134][87424] Updated weights for policy 0, policy_version 140737 (0.0010) -[2023-11-28 03:53:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 71983104. Throughput: 0: 2740.7, 1: 2720.3. Samples: 71997152. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:43,445][86177] Avg episode reward: [(0, '-528.510'), (1, '-508.200')] -[2023-11-28 03:53:43,520][87424] Updated weights for policy 0, policy_version 140747 (0.0012) -[2023-11-28 03:53:43,900][87424] Updated weights for policy 0, policy_version 140757 (0.0012) -[2023-11-28 03:53:44,273][87424] Updated weights for policy 0, policy_version 140767 (0.0011) -[2023-11-28 03:53:44,962][87426] Updated weights for policy 1, policy_version 140450 (0.0011) -[2023-11-28 03:53:45,343][87426] Updated weights for policy 1, policy_version 140460 (0.0008) -[2023-11-28 03:53:45,721][87426] Updated weights for policy 1, policy_version 140470 (0.0011) -[2023-11-28 03:53:46,106][87426] Updated weights for policy 1, policy_version 140480 (0.0011) -[2023-11-28 03:53:46,828][87424] Updated weights for policy 0, policy_version 140777 (0.0012) -[2023-11-28 03:53:47,208][87424] Updated weights for policy 0, policy_version 140787 (0.0012) -[2023-11-28 03:53:47,602][87424] Updated weights for policy 0, policy_version 140797 (0.0012) -[2023-11-28 03:53:48,176][87426] Updated weights for policy 1, policy_version 140490 (0.0007) -[2023-11-28 03:53:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 72007680. Throughput: 0: 2749.6, 1: 2723.3. Samples: 72021648. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:48,445][86177] Avg episode reward: [(0, '-535.520'), (1, '-511.280')] -[2023-11-28 03:53:48,551][87426] Updated weights for policy 1, policy_version 140500 (0.0007) -[2023-11-28 03:53:48,926][87426] Updated weights for policy 1, policy_version 140510 (0.0008) -[2023-11-28 03:53:50,145][87424] Updated weights for policy 0, policy_version 140807 (0.0012) -[2023-11-28 03:53:50,524][87424] Updated weights for policy 0, policy_version 140817 (0.0010) -[2023-11-28 03:53:50,910][87424] Updated weights for policy 0, policy_version 140827 (0.0009) -[2023-11-28 03:53:51,218][87426] Updated weights for policy 1, policy_version 140520 (0.0008) -[2023-11-28 03:53:51,604][87426] Updated weights for policy 1, policy_version 140530 (0.0011) -[2023-11-28 03:53:51,981][87426] Updated weights for policy 1, policy_version 140540 (0.0010) -[2023-11-28 03:53:53,117][87424] Updated weights for policy 0, policy_version 140837 (0.0009) -[2023-11-28 03:53:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 72032256. Throughput: 0: 2728.6, 1: 2696.7. Samples: 72053036. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:53,445][86177] Avg episode reward: [(0, '-570.350'), (1, '-509.850')] -[2023-11-28 03:53:53,497][87424] Updated weights for policy 0, policy_version 140847 (0.0010) -[2023-11-28 03:53:53,895][87424] Updated weights for policy 0, policy_version 140857 (0.0011) -[2023-11-28 03:53:54,127][87426] Updated weights for policy 1, policy_version 140550 (0.0011) -[2023-11-28 03:53:54,502][87426] Updated weights for policy 1, policy_version 140560 (0.0012) -[2023-11-28 03:53:54,876][87426] Updated weights for policy 1, policy_version 140570 (0.0012) -[2023-11-28 03:53:55,760][87424] Updated weights for policy 0, policy_version 140867 (0.0009) -[2023-11-28 03:53:56,149][87424] Updated weights for policy 0, policy_version 140877 (0.0012) -[2023-11-28 03:53:56,534][87424] Updated weights for policy 0, policy_version 140887 (0.0012) -[2023-11-28 03:53:57,479][87426] Updated weights for policy 1, policy_version 140580 (0.0011) -[2023-11-28 03:53:57,860][87426] Updated weights for policy 1, policy_version 140590 (0.0008) -[2023-11-28 03:53:58,240][87426] Updated weights for policy 1, policy_version 140600 (0.0012) -[2023-11-28 03:53:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 72056832. Throughput: 0: 2735.7, 1: 2705.1. Samples: 72077664. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:53:58,445][86177] Avg episode reward: [(0, '-621.790'), (1, '-513.300')] -[2023-11-28 03:53:58,580][87424] Updated weights for policy 0, policy_version 140897 (0.0012) -[2023-11-28 03:53:58,956][87424] Updated weights for policy 0, policy_version 140907 (0.0011) -[2023-11-28 03:53:59,347][87424] Updated weights for policy 0, policy_version 140917 (0.0008) -[2023-11-28 03:53:59,725][87424] Updated weights for policy 0, policy_version 140927 (0.0011) -[2023-11-28 03:54:00,372][87426] Updated weights for policy 1, policy_version 140610 (0.0011) -[2023-11-28 03:54:00,742][87426] Updated weights for policy 1, policy_version 140620 (0.0009) -[2023-11-28 03:54:01,127][87426] Updated weights for policy 1, policy_version 140630 (0.0011) -[2023-11-28 03:54:01,385][87424] Updated weights for policy 0, policy_version 140937 (0.0008) -[2023-11-28 03:54:01,507][87426] Updated weights for policy 1, policy_version 140640 (0.0007) -[2023-11-28 03:54:01,763][87424] Updated weights for policy 0, policy_version 140947 (0.0010) -[2023-11-28 03:54:02,146][87424] Updated weights for policy 0, policy_version 140957 (0.0010) -[2023-11-28 03:54:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72089600. Throughput: 0: 2750.3, 1: 2706.8. Samples: 72102688. Policy #0 lag: (min: 14.0, avg: 27.6, max: 46.0) -[2023-11-28 03:54:03,445][86177] Avg episode reward: [(0, '-589.670'), (1, '-515.420')] -[2023-11-28 03:54:04,037][87426] Updated weights for policy 1, policy_version 140650 (0.0008) -[2023-11-28 03:54:04,069][87424] Updated weights for policy 0, policy_version 140967 (0.0009) -[2023-11-28 03:54:04,422][87426] Updated weights for policy 1, policy_version 140660 (0.0008) -[2023-11-28 03:54:04,452][87424] Updated weights for policy 0, policy_version 140977 (0.0008) -[2023-11-28 03:54:04,792][87426] Updated weights for policy 1, policy_version 140670 (0.0009) -[2023-11-28 03:54:04,835][87424] Updated weights for policy 0, policy_version 140987 (0.0008) -[2023-11-28 03:54:06,719][87424] Updated weights for policy 0, policy_version 140997 (0.0008) -[2023-11-28 03:54:07,002][87426] Updated weights for policy 1, policy_version 140680 (0.0011) -[2023-11-28 03:54:07,106][87424] Updated weights for policy 0, policy_version 141007 (0.0011) -[2023-11-28 03:54:07,383][87426] Updated weights for policy 1, policy_version 140690 (0.0011) -[2023-11-28 03:54:07,484][87424] Updated weights for policy 0, policy_version 141017 (0.0012) -[2023-11-28 03:54:07,753][87426] Updated weights for policy 1, policy_version 140700 (0.0011) -[2023-11-28 03:54:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 72122368. Throughput: 0: 2754.4, 1: 2703.4. Samples: 72134888. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:08,445][86177] Avg episode reward: [(0, '-549.100'), (1, '-539.820')] -[2023-11-28 03:54:09,408][87424] Updated weights for policy 0, policy_version 141027 (0.0010) -[2023-11-28 03:54:09,786][87426] Updated weights for policy 1, policy_version 140710 (0.0011) -[2023-11-28 03:54:09,799][87424] Updated weights for policy 0, policy_version 141037 (0.0009) -[2023-11-28 03:54:10,177][87426] Updated weights for policy 1, policy_version 140720 (0.0010) -[2023-11-28 03:54:10,187][87424] Updated weights for policy 0, policy_version 141047 (0.0009) -[2023-11-28 03:54:10,545][87426] Updated weights for policy 1, policy_version 140730 (0.0010) -[2023-11-28 03:54:12,694][87424] Updated weights for policy 0, policy_version 141057 (0.0011) -[2023-11-28 03:54:13,010][87426] Updated weights for policy 1, policy_version 140740 (0.0011) -[2023-11-28 03:54:13,068][87424] Updated weights for policy 0, policy_version 141067 (0.0011) -[2023-11-28 03:54:13,389][87426] Updated weights for policy 1, policy_version 140750 (0.0008) -[2023-11-28 03:54:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 72138752. Throughput: 0: 2757.2, 1: 2678.2. Samples: 72159564. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:13,446][86177] Avg episode reward: [(0, '-553.050'), (1, '-584.850')] -[2023-11-28 03:54:13,451][87424] Updated weights for policy 0, policy_version 141077 (0.0009) -[2023-11-28 03:54:13,767][87426] Updated weights for policy 1, policy_version 140760 (0.0008) -[2023-11-28 03:54:13,831][87424] Updated weights for policy 0, policy_version 141087 (0.0009) -[2023-11-28 03:54:16,288][87426] Updated weights for policy 1, policy_version 140770 (0.0009) -[2023-11-28 03:54:16,383][87424] Updated weights for policy 0, policy_version 141097 (0.0008) -[2023-11-28 03:54:16,660][87426] Updated weights for policy 1, policy_version 140780 (0.0008) -[2023-11-28 03:54:16,767][87424] Updated weights for policy 0, policy_version 141107 (0.0008) -[2023-11-28 03:54:17,040][87426] Updated weights for policy 1, policy_version 140790 (0.0007) -[2023-11-28 03:54:17,144][87424] Updated weights for policy 0, policy_version 141117 (0.0008) -[2023-11-28 03:54:17,424][87426] Updated weights for policy 1, policy_version 140800 (0.0009) -[2023-11-28 03:54:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72171520. Throughput: 0: 2741.6, 1: 2687.9. Samples: 72183860. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:18,445][86177] Avg episode reward: [(0, '-497.580'), (1, '-593.960')] -[2023-11-28 03:54:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000140800_36044800.pth... -[2023-11-28 03:54:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000141120_36126720.pth... -[2023-11-28 03:54:18,494][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000138560_35471360.pth -[2023-11-28 03:54:18,504][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000138272_35397632.pth -[2023-11-28 03:54:19,067][87424] Updated weights for policy 0, policy_version 141127 (0.0008) -[2023-11-28 03:54:19,452][87424] Updated weights for policy 0, policy_version 141137 (0.0008) -[2023-11-28 03:54:19,845][87424] Updated weights for policy 0, policy_version 141147 (0.0011) -[2023-11-28 03:54:19,952][87426] Updated weights for policy 1, policy_version 140810 (0.0009) -[2023-11-28 03:54:20,330][87426] Updated weights for policy 1, policy_version 140820 (0.0008) -[2023-11-28 03:54:20,712][87426] Updated weights for policy 1, policy_version 140830 (0.0011) -[2023-11-28 03:54:21,703][87424] Updated weights for policy 0, policy_version 141157 (0.0011) -[2023-11-28 03:54:22,079][87424] Updated weights for policy 0, policy_version 141167 (0.0012) -[2023-11-28 03:54:22,467][87424] Updated weights for policy 0, policy_version 141177 (0.0011) -[2023-11-28 03:54:23,273][87426] Updated weights for policy 1, policy_version 140840 (0.0009) -[2023-11-28 03:54:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 72196096. Throughput: 0: 2721.7, 1: 2640.4. Samples: 72214752. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:23,445][86177] Avg episode reward: [(0, '-497.770'), (1, '-573.670')] -[2023-11-28 03:54:23,640][87426] Updated weights for policy 1, policy_version 140850 (0.0008) -[2023-11-28 03:54:24,024][87426] Updated weights for policy 1, policy_version 140860 (0.0007) -[2023-11-28 03:54:24,965][87424] Updated weights for policy 0, policy_version 141187 (0.0009) -[2023-11-28 03:54:25,348][87424] Updated weights for policy 0, policy_version 141197 (0.0011) -[2023-11-28 03:54:25,731][87424] Updated weights for policy 0, policy_version 141207 (0.0011) -[2023-11-28 03:54:26,440][87426] Updated weights for policy 1, policy_version 140870 (0.0009) -[2023-11-28 03:54:26,822][87426] Updated weights for policy 1, policy_version 140880 (0.0007) -[2023-11-28 03:54:27,217][87426] Updated weights for policy 1, policy_version 140890 (0.0008) -[2023-11-28 03:54:28,228][87424] Updated weights for policy 0, policy_version 141217 (0.0011) -[2023-11-28 03:54:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 72220672. Throughput: 0: 2721.7, 1: 2637.2. Samples: 72238300. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:28,445][86177] Avg episode reward: [(0, '-505.110'), (1, '-574.290')] -[2023-11-28 03:54:28,621][87424] Updated weights for policy 0, policy_version 141227 (0.0012) -[2023-11-28 03:54:28,892][87426] Updated weights for policy 1, policy_version 140900 (0.0008) -[2023-11-28 03:54:29,004][87424] Updated weights for policy 0, policy_version 141237 (0.0011) -[2023-11-28 03:54:29,273][87426] Updated weights for policy 1, policy_version 140910 (0.0008) -[2023-11-28 03:54:29,393][87424] Updated weights for policy 0, policy_version 141247 (0.0011) -[2023-11-28 03:54:29,651][87426] Updated weights for policy 1, policy_version 140920 (0.0007) -[2023-11-28 03:54:31,135][87426] Updated weights for policy 1, policy_version 140930 (0.0009) -[2023-11-28 03:54:31,513][87426] Updated weights for policy 1, policy_version 140940 (0.0012) -[2023-11-28 03:54:31,735][87424] Updated weights for policy 0, policy_version 141257 (0.0009) -[2023-11-28 03:54:31,884][87426] Updated weights for policy 1, policy_version 140950 (0.0008) -[2023-11-28 03:54:32,124][87424] Updated weights for policy 0, policy_version 141267 (0.0011) -[2023-11-28 03:54:32,263][87426] Updated weights for policy 1, policy_version 140960 (0.0009) -[2023-11-28 03:54:32,507][87424] Updated weights for policy 0, policy_version 141277 (0.0009) -[2023-11-28 03:54:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72253440. Throughput: 0: 2702.8, 1: 2655.6. Samples: 72262772. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:33,445][86177] Avg episode reward: [(0, '-509.320'), (1, '-521.930')] -[2023-11-28 03:54:34,330][87426] Updated weights for policy 1, policy_version 140970 (0.0007) -[2023-11-28 03:54:34,398][87424] Updated weights for policy 0, policy_version 141287 (0.0011) -[2023-11-28 03:54:34,713][87426] Updated weights for policy 1, policy_version 140980 (0.0008) -[2023-11-28 03:54:34,773][87424] Updated weights for policy 0, policy_version 141297 (0.0011) -[2023-11-28 03:54:35,081][87426] Updated weights for policy 1, policy_version 140990 (0.0010) -[2023-11-28 03:54:35,156][87424] Updated weights for policy 0, policy_version 141307 (0.0012) -[2023-11-28 03:54:36,803][87426] Updated weights for policy 1, policy_version 141000 (0.0012) -[2023-11-28 03:54:37,188][87426] Updated weights for policy 1, policy_version 141010 (0.0010) -[2023-11-28 03:54:37,413][87424] Updated weights for policy 0, policy_version 141317 (0.0012) -[2023-11-28 03:54:37,560][87426] Updated weights for policy 1, policy_version 141020 (0.0010) -[2023-11-28 03:54:37,792][87424] Updated weights for policy 0, policy_version 141327 (0.0012) -[2023-11-28 03:54:38,185][87424] Updated weights for policy 0, policy_version 141337 (0.0012) -[2023-11-28 03:54:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 72278016. Throughput: 0: 2727.2, 1: 2696.1. Samples: 72297084. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:38,445][86177] Avg episode reward: [(0, '-516.270'), (1, '-518.790')] -[2023-11-28 03:54:39,597][87426] Updated weights for policy 1, policy_version 141030 (0.0009) -[2023-11-28 03:54:39,974][87426] Updated weights for policy 1, policy_version 141040 (0.0010) -[2023-11-28 03:54:40,349][87426] Updated weights for policy 1, policy_version 141050 (0.0010) -[2023-11-28 03:54:40,751][87424] Updated weights for policy 0, policy_version 141347 (0.0011) -[2023-11-28 03:54:41,126][87424] Updated weights for policy 0, policy_version 141357 (0.0010) -[2023-11-28 03:54:41,509][87424] Updated weights for policy 0, policy_version 141367 (0.0011) -[2023-11-28 03:54:42,709][87426] Updated weights for policy 1, policy_version 141060 (0.0011) -[2023-11-28 03:54:43,079][87426] Updated weights for policy 1, policy_version 141070 (0.0011) -[2023-11-28 03:54:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 72302592. Throughput: 0: 2709.2, 1: 2693.7. Samples: 72320796. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:43,445][86177] Avg episode reward: [(0, '-519.250'), (1, '-515.420')] -[2023-11-28 03:54:43,457][87426] Updated weights for policy 1, policy_version 141080 (0.0008) -[2023-11-28 03:54:43,886][87424] Updated weights for policy 0, policy_version 141377 (0.0010) -[2023-11-28 03:54:44,267][87424] Updated weights for policy 0, policy_version 141387 (0.0012) -[2023-11-28 03:54:44,646][87424] Updated weights for policy 0, policy_version 141397 (0.0012) -[2023-11-28 03:54:45,022][87424] Updated weights for policy 0, policy_version 141407 (0.0012) -[2023-11-28 03:54:45,764][87426] Updated weights for policy 1, policy_version 141090 (0.0010) -[2023-11-28 03:54:46,140][87426] Updated weights for policy 1, policy_version 141100 (0.0012) -[2023-11-28 03:54:46,529][87426] Updated weights for policy 1, policy_version 141110 (0.0012) -[2023-11-28 03:54:46,905][87426] Updated weights for policy 1, policy_version 141120 (0.0007) -[2023-11-28 03:54:46,931][87424] Updated weights for policy 0, policy_version 141417 (0.0008) -[2023-11-28 03:54:47,313][87424] Updated weights for policy 0, policy_version 141427 (0.0007) -[2023-11-28 03:54:47,699][87424] Updated weights for policy 0, policy_version 141437 (0.0009) -[2023-11-28 03:54:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 72335360. Throughput: 0: 2706.8, 1: 2712.7. Samples: 72346568. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:48,445][86177] Avg episode reward: [(0, '-519.400'), (1, '-527.910')] -[2023-11-28 03:54:48,579][87426] Updated weights for policy 1, policy_version 141130 (0.0007) -[2023-11-28 03:54:48,951][87426] Updated weights for policy 1, policy_version 141140 (0.0008) -[2023-11-28 03:54:49,332][87426] Updated weights for policy 1, policy_version 141150 (0.0008) -[2023-11-28 03:54:49,572][87424] Updated weights for policy 0, policy_version 141447 (0.0011) -[2023-11-28 03:54:49,957][87424] Updated weights for policy 0, policy_version 141457 (0.0011) -[2023-11-28 03:54:50,352][87424] Updated weights for policy 0, policy_version 141467 (0.0008) -[2023-11-28 03:54:51,208][87426] Updated weights for policy 1, policy_version 141160 (0.0009) -[2023-11-28 03:54:51,589][87426] Updated weights for policy 1, policy_version 141170 (0.0009) -[2023-11-28 03:54:51,968][87426] Updated weights for policy 1, policy_version 141180 (0.0012) -[2023-11-28 03:54:52,615][87424] Updated weights for policy 0, policy_version 141477 (0.0012) -[2023-11-28 03:54:52,988][87424] Updated weights for policy 0, policy_version 141487 (0.0011) -[2023-11-28 03:54:53,370][87424] Updated weights for policy 0, policy_version 141497 (0.0011) -[2023-11-28 03:54:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 72359936. Throughput: 0: 2697.1, 1: 2748.9. Samples: 72379956. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:53,445][86177] Avg episode reward: [(0, '-524.000'), (1, '-534.140')] -[2023-11-28 03:54:54,470][87426] Updated weights for policy 1, policy_version 141190 (0.0012) -[2023-11-28 03:54:54,840][87426] Updated weights for policy 1, policy_version 141200 (0.0012) -[2023-11-28 03:54:55,219][87426] Updated weights for policy 1, policy_version 141210 (0.0009) -[2023-11-28 03:54:55,656][87424] Updated weights for policy 0, policy_version 141507 (0.0011) -[2023-11-28 03:54:56,044][87424] Updated weights for policy 0, policy_version 141517 (0.0012) -[2023-11-28 03:54:56,437][87424] Updated weights for policy 0, policy_version 141527 (0.0012) -[2023-11-28 03:54:57,649][87426] Updated weights for policy 1, policy_version 141220 (0.0007) -[2023-11-28 03:54:58,018][87426] Updated weights for policy 1, policy_version 141230 (0.0009) -[2023-11-28 03:54:58,341][87424] Updated weights for policy 0, policy_version 141537 (0.0011) -[2023-11-28 03:54:58,395][87426] Updated weights for policy 1, policy_version 141240 (0.0010) -[2023-11-28 03:54:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 72384512. Throughput: 0: 2688.2, 1: 2761.2. Samples: 72404784. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:54:58,445][86177] Avg episode reward: [(0, '-521.550'), (1, '-543.320')] -[2023-11-28 03:54:58,723][87424] Updated weights for policy 0, policy_version 141547 (0.0007) -[2023-11-28 03:54:59,104][87424] Updated weights for policy 0, policy_version 141557 (0.0008) -[2023-11-28 03:54:59,483][87424] Updated weights for policy 0, policy_version 141567 (0.0007) -[2023-11-28 03:55:00,883][87426] Updated weights for policy 1, policy_version 141250 (0.0008) -[2023-11-28 03:55:01,001][87424] Updated weights for policy 0, policy_version 141577 (0.0010) -[2023-11-28 03:55:01,270][87426] Updated weights for policy 1, policy_version 141260 (0.0009) -[2023-11-28 03:55:01,384][87424] Updated weights for policy 0, policy_version 141587 (0.0008) -[2023-11-28 03:55:01,638][87426] Updated weights for policy 1, policy_version 141270 (0.0011) -[2023-11-28 03:55:01,770][87424] Updated weights for policy 0, policy_version 141597 (0.0010) -[2023-11-28 03:55:02,014][87426] Updated weights for policy 1, policy_version 141280 (0.0011) -[2023-11-28 03:55:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72417280. Throughput: 0: 2702.6, 1: 2733.5. Samples: 72428484. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:55:03,445][86177] Avg episode reward: [(0, '-518.720'), (1, '-558.960')] -[2023-11-28 03:55:03,791][87424] Updated weights for policy 0, policy_version 141607 (0.0011) -[2023-11-28 03:55:03,862][87426] Updated weights for policy 1, policy_version 141290 (0.0011) -[2023-11-28 03:55:04,177][87424] Updated weights for policy 0, policy_version 141617 (0.0011) -[2023-11-28 03:55:04,243][87426] Updated weights for policy 1, policy_version 141300 (0.0011) -[2023-11-28 03:55:04,577][87424] Updated weights for policy 0, policy_version 141627 (0.0010) -[2023-11-28 03:55:04,626][87426] Updated weights for policy 1, policy_version 141310 (0.0011) -[2023-11-28 03:55:06,321][87426] Updated weights for policy 1, policy_version 141320 (0.0011) -[2023-11-28 03:55:06,704][87426] Updated weights for policy 1, policy_version 141330 (0.0011) -[2023-11-28 03:55:07,052][87424] Updated weights for policy 0, policy_version 141637 (0.0010) -[2023-11-28 03:55:07,080][87426] Updated weights for policy 1, policy_version 141340 (0.0011) -[2023-11-28 03:55:07,420][87424] Updated weights for policy 0, policy_version 141647 (0.0012) -[2023-11-28 03:55:07,802][87424] Updated weights for policy 0, policy_version 141657 (0.0010) -[2023-11-28 03:55:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 72450048. Throughput: 0: 2693.2, 1: 2781.1. Samples: 72461096. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:55:08,445][86177] Avg episode reward: [(0, '-524.100'), (1, '-551.970')] -[2023-11-28 03:55:09,458][87426] Updated weights for policy 1, policy_version 141350 (0.0012) -[2023-11-28 03:55:09,847][87426] Updated weights for policy 1, policy_version 141360 (0.0011) -[2023-11-28 03:55:10,218][87426] Updated weights for policy 1, policy_version 141370 (0.0012) -[2023-11-28 03:55:10,351][87424] Updated weights for policy 0, policy_version 141667 (0.0012) -[2023-11-28 03:55:10,735][87424] Updated weights for policy 0, policy_version 141677 (0.0012) -[2023-11-28 03:55:11,122][87424] Updated weights for policy 0, policy_version 141687 (0.0012) -[2023-11-28 03:55:12,317][87426] Updated weights for policy 1, policy_version 141380 (0.0015) -[2023-11-28 03:55:12,694][87426] Updated weights for policy 1, policy_version 141390 (0.0011) -[2023-11-28 03:55:13,068][87426] Updated weights for policy 1, policy_version 141400 (0.0011) -[2023-11-28 03:55:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 72474624. Throughput: 0: 2691.1, 1: 2815.9. Samples: 72486116. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 03:55:13,445][86177] Avg episode reward: [(0, '-510.050'), (1, '-565.820')] -[2023-11-28 03:55:13,530][87424] Updated weights for policy 0, policy_version 141697 (0.0012) -[2023-11-28 03:55:13,916][87424] Updated weights for policy 0, policy_version 141707 (0.0011) -[2023-11-28 03:55:14,309][87424] Updated weights for policy 0, policy_version 141717 (0.0011) -[2023-11-28 03:55:14,677][87424] Updated weights for policy 0, policy_version 141727 (0.0011) -[2023-11-28 03:55:14,872][87426] Updated weights for policy 1, policy_version 141410 (0.0010) -[2023-11-28 03:55:15,254][87426] Updated weights for policy 1, policy_version 141420 (0.0012) -[2023-11-28 03:55:15,628][87426] Updated weights for policy 1, policy_version 141430 (0.0011) -[2023-11-28 03:55:16,008][87426] Updated weights for policy 1, policy_version 141440 (0.0012) -[2023-11-28 03:55:17,236][87424] Updated weights for policy 0, policy_version 141737 (0.0008) -[2023-11-28 03:55:17,623][87424] Updated weights for policy 0, policy_version 141747 (0.0007) -[2023-11-28 03:55:17,648][87426] Updated weights for policy 1, policy_version 141450 (0.0012) -[2023-11-28 03:55:17,996][87424] Updated weights for policy 0, policy_version 141757 (0.0007) -[2023-11-28 03:55:18,027][87426] Updated weights for policy 1, policy_version 141460 (0.0011) -[2023-11-28 03:55:18,408][87426] Updated weights for policy 1, policy_version 141470 (0.0012) -[2023-11-28 03:55:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 72499200. Throughput: 0: 2692.8, 1: 2807.8. Samples: 72510300. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:55:18,445][86177] Avg episode reward: [(0, '-517.230'), (1, '-576.290')] -[2023-11-28 03:55:20,516][87424] Updated weights for policy 0, policy_version 141767 (0.0010) -[2023-11-28 03:55:20,634][87426] Updated weights for policy 1, policy_version 141480 (0.0012) -[2023-11-28 03:55:20,903][87424] Updated weights for policy 0, policy_version 141777 (0.0008) -[2023-11-28 03:55:21,012][87426] Updated weights for policy 1, policy_version 141490 (0.0010) -[2023-11-28 03:55:21,288][87424] Updated weights for policy 0, policy_version 141787 (0.0009) -[2023-11-28 03:55:21,397][87426] Updated weights for policy 1, policy_version 141500 (0.0008) -[2023-11-28 03:55:23,358][87426] Updated weights for policy 1, policy_version 141510 (0.0010) -[2023-11-28 03:55:23,419][87424] Updated weights for policy 0, policy_version 141797 (0.0010) -[2023-11-28 03:55:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72523776. Throughput: 0: 2670.8, 1: 2784.0. Samples: 72542552. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:55:23,445][86177] Avg episode reward: [(0, '-529.250'), (1, '-594.460')] -[2023-11-28 03:55:23,749][87426] Updated weights for policy 1, policy_version 141520 (0.0009) -[2023-11-28 03:55:23,803][87424] Updated weights for policy 0, policy_version 141807 (0.0008) -[2023-11-28 03:55:24,139][87426] Updated weights for policy 1, policy_version 141530 (0.0008) -[2023-11-28 03:55:24,183][87424] Updated weights for policy 0, policy_version 141817 (0.0007) -[2023-11-28 03:55:26,343][87426] Updated weights for policy 1, policy_version 141540 (0.0009) -[2023-11-28 03:55:26,389][87424] Updated weights for policy 0, policy_version 141827 (0.0007) -[2023-11-28 03:55:26,721][87426] Updated weights for policy 1, policy_version 141550 (0.0007) -[2023-11-28 03:55:26,774][87424] Updated weights for policy 0, policy_version 141837 (0.0007) -[2023-11-28 03:55:27,106][87426] Updated weights for policy 1, policy_version 141560 (0.0007) -[2023-11-28 03:55:27,169][87424] Updated weights for policy 0, policy_version 141847 (0.0007) -[2023-11-28 03:55:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 72556544. Throughput: 0: 2688.0, 1: 2789.9. Samples: 72567304. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:55:28,445][86177] Avg episode reward: [(0, '-514.270'), (1, '-585.040')] -[2023-11-28 03:55:29,380][87426] Updated weights for policy 1, policy_version 141570 (0.0007) -[2023-11-28 03:55:29,552][87424] Updated weights for policy 0, policy_version 141857 (0.0010) -[2023-11-28 03:55:29,767][87426] Updated weights for policy 1, policy_version 141580 (0.0008) -[2023-11-28 03:55:29,926][87424] Updated weights for policy 0, policy_version 141867 (0.0012) -[2023-11-28 03:55:30,145][87426] Updated weights for policy 1, policy_version 141590 (0.0008) -[2023-11-28 03:55:30,307][87424] Updated weights for policy 0, policy_version 141877 (0.0012) -[2023-11-28 03:55:30,521][87426] Updated weights for policy 1, policy_version 141600 (0.0009) -[2023-11-28 03:55:30,694][87424] Updated weights for policy 0, policy_version 141887 (0.0011) -[2023-11-28 03:55:32,645][87424] Updated weights for policy 0, policy_version 141897 (0.0008) -[2023-11-28 03:55:32,837][87426] Updated weights for policy 1, policy_version 141610 (0.0011) -[2023-11-28 03:55:33,022][87424] Updated weights for policy 0, policy_version 141907 (0.0010) -[2023-11-28 03:55:33,217][87426] Updated weights for policy 1, policy_version 141620 (0.0011) -[2023-11-28 03:55:33,403][87424] Updated weights for policy 0, policy_version 141917 (0.0009) -[2023-11-28 03:55:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 72572928. Throughput: 0: 2668.7, 1: 2776.7. Samples: 72591612. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:55:33,445][86177] Avg episode reward: [(0, '-522.840'), (1, '-612.940')] -[2023-11-28 03:55:33,605][87426] Updated weights for policy 1, policy_version 141630 (0.0011) -[2023-11-28 03:55:35,527][87426] Updated weights for policy 1, policy_version 141640 (0.0009) -[2023-11-28 03:55:35,741][87424] Updated weights for policy 0, policy_version 141927 (0.0007) -[2023-11-28 03:55:35,915][87426] Updated weights for policy 1, policy_version 141650 (0.0011) -[2023-11-28 03:55:36,132][87424] Updated weights for policy 0, policy_version 141937 (0.0007) -[2023-11-28 03:55:36,284][87426] Updated weights for policy 1, policy_version 141660 (0.0009) -[2023-11-28 03:55:36,520][87424] Updated weights for policy 0, policy_version 141947 (0.0008) -[2023-11-28 03:55:38,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72605696. Throughput: 0: 2674.0, 1: 2783.8. Samples: 72625560. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:55:38,446][86177] Avg episode reward: [(0, '-538.500'), (1, '-617.220')] -[2023-11-28 03:55:38,447][87426] Updated weights for policy 1, policy_version 141670 (0.0010) -[2023-11-28 03:55:38,548][87424] Updated weights for policy 0, policy_version 141957 (0.0012) -[2023-11-28 03:55:38,823][87426] Updated weights for policy 1, policy_version 141680 (0.0011) -[2023-11-28 03:55:38,939][87424] Updated weights for policy 0, policy_version 141967 (0.0012) -[2023-11-28 03:55:39,203][87426] Updated weights for policy 1, policy_version 141690 (0.0011) -[2023-11-28 03:55:39,312][87424] Updated weights for policy 0, policy_version 141977 (0.0010) -[2023-11-28 03:55:41,473][87426] Updated weights for policy 1, policy_version 141700 (0.0009) -[2023-11-28 03:55:41,761][87424] Updated weights for policy 0, policy_version 141987 (0.0009) -[2023-11-28 03:55:41,856][87426] Updated weights for policy 1, policy_version 141710 (0.0009) -[2023-11-28 03:55:42,145][87424] Updated weights for policy 0, policy_version 141997 (0.0011) -[2023-11-28 03:55:42,234][87426] Updated weights for policy 1, policy_version 141720 (0.0011) -[2023-11-28 03:55:42,529][87424] Updated weights for policy 0, policy_version 142007 (0.0012) -[2023-11-28 03:55:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 72638464. Throughput: 0: 2671.5, 1: 2778.2. Samples: 72650020. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:55:43,445][86177] Avg episode reward: [(0, '-540.730'), (1, '-572.210')] -[2023-11-28 03:55:44,647][87426] Updated weights for policy 1, policy_version 141730 (0.0011) -[2023-11-28 03:55:44,803][87424] Updated weights for policy 0, policy_version 142017 (0.0012) -[2023-11-28 03:55:45,022][87426] Updated weights for policy 1, policy_version 141740 (0.0009) -[2023-11-28 03:55:45,185][87424] Updated weights for policy 0, policy_version 142027 (0.0007) -[2023-11-28 03:55:45,396][87426] Updated weights for policy 1, policy_version 141750 (0.0010) -[2023-11-28 03:55:45,571][87424] Updated weights for policy 0, policy_version 142037 (0.0010) -[2023-11-28 03:55:45,774][87426] Updated weights for policy 1, policy_version 141760 (0.0008) -[2023-11-28 03:55:45,950][87424] Updated weights for policy 0, policy_version 142047 (0.0009) -[2023-11-28 03:55:47,693][87426] Updated weights for policy 1, policy_version 141770 (0.0007) -[2023-11-28 03:55:48,066][87426] Updated weights for policy 1, policy_version 141780 (0.0009) -[2023-11-28 03:55:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 72654848. Throughput: 0: 2657.2, 1: 2800.8. Samples: 72674092. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:55:48,445][86177] Avg episode reward: [(0, '-550.710'), (1, '-580.990')] -[2023-11-28 03:55:48,450][87426] Updated weights for policy 1, policy_version 141790 (0.0007) -[2023-11-28 03:55:48,457][87424] Updated weights for policy 0, policy_version 142057 (0.0008) -[2023-11-28 03:55:48,845][87424] Updated weights for policy 0, policy_version 142067 (0.0011) -[2023-11-28 03:55:49,230][87424] Updated weights for policy 0, policy_version 142077 (0.0012) -[2023-11-28 03:55:50,823][87426] Updated weights for policy 1, policy_version 141800 (0.0007) -[2023-11-28 03:55:51,211][87426] Updated weights for policy 1, policy_version 141810 (0.0008) -[2023-11-28 03:55:51,482][87424] Updated weights for policy 0, policy_version 142087 (0.0011) -[2023-11-28 03:55:51,600][87426] Updated weights for policy 1, policy_version 141820 (0.0009) -[2023-11-28 03:55:51,854][87424] Updated weights for policy 0, policy_version 142097 (0.0010) -[2023-11-28 03:55:52,241][87424] Updated weights for policy 0, policy_version 142107 (0.0009) -[2023-11-28 03:55:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72687616. Throughput: 0: 2647.1, 1: 2801.1. Samples: 72706264. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:55:53,445][86177] Avg episode reward: [(0, '-549.190'), (1, '-552.800')] -[2023-11-28 03:55:53,558][87426] Updated weights for policy 1, policy_version 141830 (0.0011) -[2023-11-28 03:55:53,931][87426] Updated weights for policy 1, policy_version 141840 (0.0010) -[2023-11-28 03:55:54,324][87426] Updated weights for policy 1, policy_version 141850 (0.0007) -[2023-11-28 03:55:54,748][87424] Updated weights for policy 0, policy_version 142117 (0.0011) -[2023-11-28 03:55:55,136][87424] Updated weights for policy 0, policy_version 142127 (0.0012) -[2023-11-28 03:55:55,514][87424] Updated weights for policy 0, policy_version 142137 (0.0012) -[2023-11-28 03:55:56,317][87426] Updated weights for policy 1, policy_version 141860 (0.0007) -[2023-11-28 03:55:56,703][87426] Updated weights for policy 1, policy_version 141870 (0.0007) -[2023-11-28 03:55:57,092][87426] Updated weights for policy 1, policy_version 141880 (0.0008) -[2023-11-28 03:55:57,400][87424] Updated weights for policy 0, policy_version 142147 (0.0012) -[2023-11-28 03:55:57,786][87424] Updated weights for policy 0, policy_version 142157 (0.0012) -[2023-11-28 03:55:58,158][87424] Updated weights for policy 0, policy_version 142167 (0.0012) -[2023-11-28 03:55:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72712192. Throughput: 0: 2652.2, 1: 2784.3. Samples: 72730756. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:55:58,445][86177] Avg episode reward: [(0, '-518.230'), (1, '-566.510')] -[2023-11-28 03:55:59,090][87426] Updated weights for policy 1, policy_version 141890 (0.0011) -[2023-11-28 03:55:59,467][87426] Updated weights for policy 1, policy_version 141900 (0.0007) -[2023-11-28 03:55:59,850][87426] Updated weights for policy 1, policy_version 141910 (0.0009) -[2023-11-28 03:56:00,224][87426] Updated weights for policy 1, policy_version 141920 (0.0012) -[2023-11-28 03:56:00,490][87424] Updated weights for policy 0, policy_version 142177 (0.0012) -[2023-11-28 03:56:00,872][87424] Updated weights for policy 0, policy_version 142187 (0.0011) -[2023-11-28 03:56:01,259][87424] Updated weights for policy 0, policy_version 142197 (0.0010) -[2023-11-28 03:56:01,655][87424] Updated weights for policy 0, policy_version 142207 (0.0009) -[2023-11-28 03:56:02,341][87426] Updated weights for policy 1, policy_version 141930 (0.0009) -[2023-11-28 03:56:02,720][87426] Updated weights for policy 1, policy_version 141940 (0.0010) -[2023-11-28 03:56:03,109][87426] Updated weights for policy 1, policy_version 141950 (0.0009) -[2023-11-28 03:56:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 72744960. Throughput: 0: 2647.4, 1: 2785.7. Samples: 72754788. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:56:03,446][86177] Avg episode reward: [(0, '-511.690'), (1, '-581.250')] -[2023-11-28 03:56:03,587][87424] Updated weights for policy 0, policy_version 142217 (0.0008) -[2023-11-28 03:56:03,966][87424] Updated weights for policy 0, policy_version 142227 (0.0008) -[2023-11-28 03:56:04,348][87424] Updated weights for policy 0, policy_version 142237 (0.0008) -[2023-11-28 03:56:05,495][87426] Updated weights for policy 1, policy_version 141960 (0.0011) -[2023-11-28 03:56:05,881][87426] Updated weights for policy 1, policy_version 141970 (0.0012) -[2023-11-28 03:56:06,265][87426] Updated weights for policy 1, policy_version 141980 (0.0012) -[2023-11-28 03:56:06,346][87424] Updated weights for policy 0, policy_version 142247 (0.0009) -[2023-11-28 03:56:06,734][87424] Updated weights for policy 0, policy_version 142257 (0.0012) -[2023-11-28 03:56:07,112][87424] Updated weights for policy 0, policy_version 142267 (0.0012) -[2023-11-28 03:56:07,963][87426] Updated weights for policy 1, policy_version 141990 (0.0011) -[2023-11-28 03:56:08,344][87426] Updated weights for policy 1, policy_version 142000 (0.0012) -[2023-11-28 03:56:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 72769536. Throughput: 0: 2680.0, 1: 2782.6. Samples: 72788368. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:56:08,445][86177] Avg episode reward: [(0, '-511.210'), (1, '-589.570')] -[2023-11-28 03:56:08,715][87426] Updated weights for policy 1, policy_version 142010 (0.0012) -[2023-11-28 03:56:08,985][87424] Updated weights for policy 0, policy_version 142277 (0.0012) -[2023-11-28 03:56:09,367][87424] Updated weights for policy 0, policy_version 142287 (0.0012) -[2023-11-28 03:56:09,756][87424] Updated weights for policy 0, policy_version 142297 (0.0012) -[2023-11-28 03:56:11,039][87426] Updated weights for policy 1, policy_version 142020 (0.0011) -[2023-11-28 03:56:11,417][87426] Updated weights for policy 1, policy_version 142030 (0.0008) -[2023-11-28 03:56:11,801][87426] Updated weights for policy 1, policy_version 142040 (0.0011) -[2023-11-28 03:56:12,242][87424] Updated weights for policy 0, policy_version 142307 (0.0010) -[2023-11-28 03:56:12,627][87424] Updated weights for policy 0, policy_version 142317 (0.0012) -[2023-11-28 03:56:13,009][87424] Updated weights for policy 0, policy_version 142327 (0.0010) -[2023-11-28 03:56:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72802304. Throughput: 0: 2674.8, 1: 2775.2. Samples: 72812552. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:56:13,445][86177] Avg episode reward: [(0, '-511.390'), (1, '-593.410')] -[2023-11-28 03:56:14,286][87426] Updated weights for policy 1, policy_version 142050 (0.0010) -[2023-11-28 03:56:14,673][87426] Updated weights for policy 1, policy_version 142060 (0.0010) -[2023-11-28 03:56:15,042][87426] Updated weights for policy 1, policy_version 142070 (0.0010) -[2023-11-28 03:56:15,397][87424] Updated weights for policy 0, policy_version 142337 (0.0009) -[2023-11-28 03:56:15,415][87426] Updated weights for policy 1, policy_version 142080 (0.0009) -[2023-11-28 03:56:15,786][87424] Updated weights for policy 0, policy_version 142347 (0.0011) -[2023-11-28 03:56:16,173][87424] Updated weights for policy 0, policy_version 142357 (0.0012) -[2023-11-28 03:56:16,558][87424] Updated weights for policy 0, policy_version 142367 (0.0012) -[2023-11-28 03:56:17,668][87426] Updated weights for policy 1, policy_version 142090 (0.0007) -[2023-11-28 03:56:18,048][87426] Updated weights for policy 1, policy_version 142100 (0.0009) -[2023-11-28 03:56:18,425][87426] Updated weights for policy 1, policy_version 142110 (0.0011) -[2023-11-28 03:56:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 72818688. Throughput: 0: 2668.7, 1: 2764.4. Samples: 72836104. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 03:56:18,446][86177] Avg episode reward: [(0, '-512.510'), (1, '-599.280')] -[2023-11-28 03:56:18,497][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000142112_36380672.pth... -[2023-11-28 03:56:18,529][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000139552_35725312.pth -[2023-11-28 03:56:18,750][87424] Updated weights for policy 0, policy_version 142377 (0.0012) -[2023-11-28 03:56:19,140][87424] Updated weights for policy 0, policy_version 142387 (0.0011) -[2023-11-28 03:56:19,522][87424] Updated weights for policy 0, policy_version 142397 (0.0007) -[2023-11-28 03:56:19,639][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000142400_36454400.pth... -[2023-11-28 03:56:19,686][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000139840_35799040.pth -[2023-11-28 03:56:20,629][87426] Updated weights for policy 1, policy_version 142120 (0.0010) -[2023-11-28 03:56:21,016][87426] Updated weights for policy 1, policy_version 142130 (0.0008) -[2023-11-28 03:56:21,388][87426] Updated weights for policy 1, policy_version 142140 (0.0011) -[2023-11-28 03:56:21,875][87424] Updated weights for policy 0, policy_version 142407 (0.0011) -[2023-11-28 03:56:22,252][87424] Updated weights for policy 0, policy_version 142417 (0.0012) -[2023-11-28 03:56:22,631][87424] Updated weights for policy 0, policy_version 142427 (0.0012) -[2023-11-28 03:56:23,359][87426] Updated weights for policy 1, policy_version 142150 (0.0012) -[2023-11-28 03:56:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72851456. Throughput: 0: 2661.8, 1: 2731.5. Samples: 72868256. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:56:23,445][86177] Avg episode reward: [(0, '-495.260'), (1, '-580.990')] -[2023-11-28 03:56:23,733][87426] Updated weights for policy 1, policy_version 142160 (0.0011) -[2023-11-28 03:56:24,105][87426] Updated weights for policy 1, policy_version 142170 (0.0012) -[2023-11-28 03:56:24,588][87424] Updated weights for policy 0, policy_version 142437 (0.0012) -[2023-11-28 03:56:24,962][87424] Updated weights for policy 0, policy_version 142447 (0.0012) -[2023-11-28 03:56:25,340][87424] Updated weights for policy 0, policy_version 142457 (0.0011) -[2023-11-28 03:56:26,656][87426] Updated weights for policy 1, policy_version 142180 (0.0012) -[2023-11-28 03:56:27,044][87426] Updated weights for policy 1, policy_version 142190 (0.0012) -[2023-11-28 03:56:27,429][87426] Updated weights for policy 1, policy_version 142200 (0.0011) -[2023-11-28 03:56:27,699][87424] Updated weights for policy 0, policy_version 142467 (0.0010) -[2023-11-28 03:56:28,083][87424] Updated weights for policy 0, policy_version 142477 (0.0007) -[2023-11-28 03:56:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 72876032. Throughput: 0: 2663.4, 1: 2728.7. Samples: 72892664. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:56:28,445][86177] Avg episode reward: [(0, '-495.730'), (1, '-557.690')] -[2023-11-28 03:56:28,475][87424] Updated weights for policy 0, policy_version 142487 (0.0008) -[2023-11-28 03:56:29,339][87426] Updated weights for policy 1, policy_version 142210 (0.0012) -[2023-11-28 03:56:29,712][87426] Updated weights for policy 1, policy_version 142220 (0.0011) -[2023-11-28 03:56:30,094][87426] Updated weights for policy 1, policy_version 142230 (0.0011) -[2023-11-28 03:56:30,266][87424] Updated weights for policy 0, policy_version 142497 (0.0008) -[2023-11-28 03:56:30,468][87426] Updated weights for policy 1, policy_version 142240 (0.0011) -[2023-11-28 03:56:30,644][87424] Updated weights for policy 0, policy_version 142507 (0.0010) -[2023-11-28 03:56:31,032][87424] Updated weights for policy 0, policy_version 142517 (0.0008) -[2023-11-28 03:56:31,420][87424] Updated weights for policy 0, policy_version 142527 (0.0008) -[2023-11-28 03:56:32,747][87426] Updated weights for policy 1, policy_version 142250 (0.0012) -[2023-11-28 03:56:33,121][87426] Updated weights for policy 1, policy_version 142260 (0.0012) -[2023-11-28 03:56:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72900608. Throughput: 0: 2690.6, 1: 2720.7. Samples: 72917600. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:56:33,445][86177] Avg episode reward: [(0, '-492.650'), (1, '-550.070')] -[2023-11-28 03:56:33,504][87426] Updated weights for policy 1, policy_version 142270 (0.0012) -[2023-11-28 03:56:33,924][87424] Updated weights for policy 0, policy_version 142537 (0.0007) -[2023-11-28 03:56:34,308][87424] Updated weights for policy 0, policy_version 142547 (0.0007) -[2023-11-28 03:56:34,698][87424] Updated weights for policy 0, policy_version 142557 (0.0008) -[2023-11-28 03:56:35,395][87426] Updated weights for policy 1, policy_version 142280 (0.0012) -[2023-11-28 03:56:35,773][87426] Updated weights for policy 1, policy_version 142290 (0.0012) -[2023-11-28 03:56:36,148][87426] Updated weights for policy 1, policy_version 142300 (0.0012) -[2023-11-28 03:56:36,704][87424] Updated weights for policy 0, policy_version 142567 (0.0009) -[2023-11-28 03:56:37,075][87424] Updated weights for policy 0, policy_version 142577 (0.0012) -[2023-11-28 03:56:37,455][87424] Updated weights for policy 0, policy_version 142587 (0.0008) -[2023-11-28 03:56:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 72933376. Throughput: 0: 2719.9, 1: 2710.8. Samples: 72950648. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:56:38,445][86177] Avg episode reward: [(0, '-491.910'), (1, '-555.930')] -[2023-11-28 03:56:38,718][87426] Updated weights for policy 1, policy_version 142310 (0.0011) -[2023-11-28 03:56:39,092][87426] Updated weights for policy 1, policy_version 142320 (0.0012) -[2023-11-28 03:56:39,102][87424] Updated weights for policy 0, policy_version 142597 (0.0010) -[2023-11-28 03:56:39,474][87424] Updated weights for policy 0, policy_version 142607 (0.0011) -[2023-11-28 03:56:39,478][87426] Updated weights for policy 1, policy_version 142330 (0.0012) -[2023-11-28 03:56:39,857][87424] Updated weights for policy 0, policy_version 142617 (0.0009) -[2023-11-28 03:56:41,655][87426] Updated weights for policy 1, policy_version 142340 (0.0011) -[2023-11-28 03:56:42,030][87426] Updated weights for policy 1, policy_version 142350 (0.0019) -[2023-11-28 03:56:42,297][87424] Updated weights for policy 0, policy_version 142627 (0.0011) -[2023-11-28 03:56:42,408][87426] Updated weights for policy 1, policy_version 142360 (0.0011) -[2023-11-28 03:56:42,683][87424] Updated weights for policy 0, policy_version 142637 (0.0011) -[2023-11-28 03:56:43,055][87424] Updated weights for policy 0, policy_version 142647 (0.0011) -[2023-11-28 03:56:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 72966144. Throughput: 0: 2732.7, 1: 2698.3. Samples: 72975152. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:56:43,445][86177] Avg episode reward: [(0, '-537.460'), (1, '-552.350')] -[2023-11-28 03:56:44,496][87426] Updated weights for policy 1, policy_version 142370 (0.0011) -[2023-11-28 03:56:44,877][87426] Updated weights for policy 1, policy_version 142380 (0.0008) -[2023-11-28 03:56:45,258][87426] Updated weights for policy 1, policy_version 142390 (0.0010) -[2023-11-28 03:56:45,336][87424] Updated weights for policy 0, policy_version 142657 (0.0010) -[2023-11-28 03:56:45,638][87426] Updated weights for policy 1, policy_version 142400 (0.0012) -[2023-11-28 03:56:45,715][87424] Updated weights for policy 0, policy_version 142667 (0.0010) -[2023-11-28 03:56:46,094][87424] Updated weights for policy 0, policy_version 142677 (0.0007) -[2023-11-28 03:56:46,474][87424] Updated weights for policy 0, policy_version 142687 (0.0007) -[2023-11-28 03:56:47,910][87426] Updated weights for policy 1, policy_version 142410 (0.0007) -[2023-11-28 03:56:48,295][87426] Updated weights for policy 1, policy_version 142420 (0.0007) -[2023-11-28 03:56:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 72982528. Throughput: 0: 2732.3, 1: 2686.5. Samples: 72998632. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:56:48,445][86177] Avg episode reward: [(0, '-535.910'), (1, '-533.900')] -[2023-11-28 03:56:48,670][87426] Updated weights for policy 1, policy_version 142430 (0.0007) -[2023-11-28 03:56:48,813][87424] Updated weights for policy 0, policy_version 142697 (0.0008) -[2023-11-28 03:56:49,203][87424] Updated weights for policy 0, policy_version 142707 (0.0012) -[2023-11-28 03:56:49,580][87424] Updated weights for policy 0, policy_version 142717 (0.0012) -[2023-11-28 03:56:50,813][87426] Updated weights for policy 1, policy_version 142440 (0.0011) -[2023-11-28 03:56:51,194][87426] Updated weights for policy 1, policy_version 142450 (0.0012) -[2023-11-28 03:56:51,573][87426] Updated weights for policy 1, policy_version 142460 (0.0012) -[2023-11-28 03:56:51,663][87424] Updated weights for policy 0, policy_version 142727 (0.0012) -[2023-11-28 03:56:52,044][87424] Updated weights for policy 0, policy_version 142737 (0.0010) -[2023-11-28 03:56:52,433][87424] Updated weights for policy 0, policy_version 142747 (0.0010) -[2023-11-28 03:56:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73015296. Throughput: 0: 2724.9, 1: 2677.8. Samples: 73031488. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:56:53,445][86177] Avg episode reward: [(0, '-600.010'), (1, '-529.270')] -[2023-11-28 03:56:53,919][87426] Updated weights for policy 1, policy_version 142470 (0.0010) -[2023-11-28 03:56:54,289][87426] Updated weights for policy 1, policy_version 142480 (0.0009) -[2023-11-28 03:56:54,621][87424] Updated weights for policy 0, policy_version 142757 (0.0009) -[2023-11-28 03:56:54,673][87426] Updated weights for policy 1, policy_version 142490 (0.0007) -[2023-11-28 03:56:55,009][87424] Updated weights for policy 0, policy_version 142767 (0.0011) -[2023-11-28 03:56:55,382][87424] Updated weights for policy 0, policy_version 142777 (0.0012) -[2023-11-28 03:56:56,451][87426] Updated weights for policy 1, policy_version 142500 (0.0009) -[2023-11-28 03:56:56,825][87426] Updated weights for policy 1, policy_version 142510 (0.0009) -[2023-11-28 03:56:57,162][87424] Updated weights for policy 0, policy_version 142787 (0.0012) -[2023-11-28 03:56:57,197][87426] Updated weights for policy 1, policy_version 142520 (0.0007) -[2023-11-28 03:56:57,545][87424] Updated weights for policy 0, policy_version 142797 (0.0008) -[2023-11-28 03:56:57,934][87424] Updated weights for policy 0, policy_version 142807 (0.0007) -[2023-11-28 03:56:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 73048064. Throughput: 0: 2717.3, 1: 2709.4. Samples: 73056756. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:56:58,445][86177] Avg episode reward: [(0, '-602.290'), (1, '-531.510')] -[2023-11-28 03:56:59,674][87426] Updated weights for policy 1, policy_version 142530 (0.0007) -[2023-11-28 03:57:00,060][87426] Updated weights for policy 1, policy_version 142540 (0.0008) -[2023-11-28 03:57:00,401][87424] Updated weights for policy 0, policy_version 142817 (0.0008) -[2023-11-28 03:57:00,437][87426] Updated weights for policy 1, policy_version 142550 (0.0008) -[2023-11-28 03:57:00,773][87424] Updated weights for policy 0, policy_version 142827 (0.0008) -[2023-11-28 03:57:00,815][87426] Updated weights for policy 1, policy_version 142560 (0.0009) -[2023-11-28 03:57:01,168][87424] Updated weights for policy 0, policy_version 142837 (0.0011) -[2023-11-28 03:57:01,544][87424] Updated weights for policy 0, policy_version 142847 (0.0011) -[2023-11-28 03:57:02,859][87426] Updated weights for policy 1, policy_version 142570 (0.0012) -[2023-11-28 03:57:03,233][87426] Updated weights for policy 1, policy_version 142580 (0.0011) -[2023-11-28 03:57:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 73064448. Throughput: 0: 2729.1, 1: 2719.1. Samples: 73081272. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:57:03,445][86177] Avg episode reward: [(0, '-598.190'), (1, '-549.520')] -[2023-11-28 03:57:03,612][87426] Updated weights for policy 1, policy_version 142590 (0.0011) -[2023-11-28 03:57:03,645][87424] Updated weights for policy 0, policy_version 142857 (0.0010) -[2023-11-28 03:57:04,030][87424] Updated weights for policy 0, policy_version 142867 (0.0007) -[2023-11-28 03:57:04,417][87424] Updated weights for policy 0, policy_version 142877 (0.0008) -[2023-11-28 03:57:05,975][87426] Updated weights for policy 1, policy_version 142600 (0.0008) -[2023-11-28 03:57:06,363][87426] Updated weights for policy 1, policy_version 142610 (0.0007) -[2023-11-28 03:57:06,728][87426] Updated weights for policy 1, policy_version 142620 (0.0011) -[2023-11-28 03:57:06,760][87424] Updated weights for policy 0, policy_version 142887 (0.0010) -[2023-11-28 03:57:07,145][87424] Updated weights for policy 0, policy_version 142897 (0.0011) -[2023-11-28 03:57:07,528][87424] Updated weights for policy 0, policy_version 142907 (0.0012) -[2023-11-28 03:57:08,416][87426] Updated weights for policy 1, policy_version 142630 (0.0012) -[2023-11-28 03:57:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73097216. Throughput: 0: 2734.7, 1: 2741.1. Samples: 73114664. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:57:08,445][86177] Avg episode reward: [(0, '-574.520'), (1, '-542.870')] -[2023-11-28 03:57:08,803][87426] Updated weights for policy 1, policy_version 142640 (0.0012) -[2023-11-28 03:57:09,178][87426] Updated weights for policy 1, policy_version 142650 (0.0012) -[2023-11-28 03:57:09,478][87424] Updated weights for policy 0, policy_version 142917 (0.0012) -[2023-11-28 03:57:09,869][87424] Updated weights for policy 0, policy_version 142927 (0.0016) -[2023-11-28 03:57:10,252][87424] Updated weights for policy 0, policy_version 142937 (0.0012) -[2023-11-28 03:57:11,420][87426] Updated weights for policy 1, policy_version 142660 (0.0010) -[2023-11-28 03:57:11,803][87426] Updated weights for policy 1, policy_version 142670 (0.0010) -[2023-11-28 03:57:12,179][87426] Updated weights for policy 1, policy_version 142680 (0.0011) -[2023-11-28 03:57:12,564][87424] Updated weights for policy 0, policy_version 142947 (0.0011) -[2023-11-28 03:57:12,953][87424] Updated weights for policy 0, policy_version 142957 (0.0009) -[2023-11-28 03:57:13,324][87424] Updated weights for policy 0, policy_version 142967 (0.0008) -[2023-11-28 03:57:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 73121792. Throughput: 0: 2730.5, 1: 2750.3. Samples: 73139300. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:57:13,445][86177] Avg episode reward: [(0, '-532.980'), (1, '-544.030')] -[2023-11-28 03:57:14,489][87426] Updated weights for policy 1, policy_version 142690 (0.0011) -[2023-11-28 03:57:14,870][87426] Updated weights for policy 1, policy_version 142700 (0.0011) -[2023-11-28 03:57:15,254][87426] Updated weights for policy 1, policy_version 142710 (0.0010) -[2023-11-28 03:57:15,633][87424] Updated weights for policy 0, policy_version 142977 (0.0008) -[2023-11-28 03:57:15,640][87426] Updated weights for policy 1, policy_version 142720 (0.0011) -[2023-11-28 03:57:16,010][87424] Updated weights for policy 0, policy_version 142987 (0.0012) -[2023-11-28 03:57:16,387][87424] Updated weights for policy 0, policy_version 142997 (0.0012) -[2023-11-28 03:57:16,762][87424] Updated weights for policy 0, policy_version 143007 (0.0012) -[2023-11-28 03:57:17,985][87426] Updated weights for policy 1, policy_version 142730 (0.0010) -[2023-11-28 03:57:18,359][87426] Updated weights for policy 1, policy_version 142740 (0.0010) -[2023-11-28 03:57:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 73146368. Throughput: 0: 2717.6, 1: 2739.9. Samples: 73163188. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:57:18,445][86177] Avg episode reward: [(0, '-492.920'), (1, '-521.260')] -[2023-11-28 03:57:18,743][87426] Updated weights for policy 1, policy_version 142750 (0.0007) -[2023-11-28 03:57:18,827][87424] Updated weights for policy 0, policy_version 143017 (0.0010) -[2023-11-28 03:57:19,209][87424] Updated weights for policy 0, policy_version 143027 (0.0008) -[2023-11-28 03:57:19,603][87424] Updated weights for policy 0, policy_version 143037 (0.0008) -[2023-11-28 03:57:20,405][87426] Updated weights for policy 1, policy_version 142760 (0.0011) -[2023-11-28 03:57:20,786][87426] Updated weights for policy 1, policy_version 142770 (0.0012) -[2023-11-28 03:57:21,171][87426] Updated weights for policy 1, policy_version 142780 (0.0012) -[2023-11-28 03:57:21,593][87424] Updated weights for policy 0, policy_version 143047 (0.0011) -[2023-11-28 03:57:21,980][87424] Updated weights for policy 0, policy_version 143057 (0.0012) -[2023-11-28 03:57:22,357][87424] Updated weights for policy 0, policy_version 143067 (0.0012) -[2023-11-28 03:57:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73179136. Throughput: 0: 2718.3, 1: 2742.7. Samples: 73196392. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 03:57:23,445][86177] Avg episode reward: [(0, '-494.960'), (1, '-515.200')] -[2023-11-28 03:57:23,754][87426] Updated weights for policy 1, policy_version 142790 (0.0012) -[2023-11-28 03:57:24,131][87426] Updated weights for policy 1, policy_version 142800 (0.0012) -[2023-11-28 03:57:24,516][87426] Updated weights for policy 1, policy_version 142810 (0.0012) -[2023-11-28 03:57:24,569][87424] Updated weights for policy 0, policy_version 143077 (0.0013) -[2023-11-28 03:57:24,957][87424] Updated weights for policy 0, policy_version 143087 (0.0007) -[2023-11-28 03:57:25,341][87424] Updated weights for policy 0, policy_version 143097 (0.0008) -[2023-11-28 03:57:27,059][87426] Updated weights for policy 1, policy_version 142820 (0.0012) -[2023-11-28 03:57:27,373][87424] Updated weights for policy 0, policy_version 143107 (0.0009) -[2023-11-28 03:57:27,438][87426] Updated weights for policy 1, policy_version 142830 (0.0012) -[2023-11-28 03:57:27,754][87424] Updated weights for policy 0, policy_version 143117 (0.0012) -[2023-11-28 03:57:27,803][87426] Updated weights for policy 1, policy_version 142840 (0.0009) -[2023-11-28 03:57:28,140][87424] Updated weights for policy 0, policy_version 143127 (0.0011) -[2023-11-28 03:57:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 73203712. Throughput: 0: 2722.0, 1: 2730.6. Samples: 73220516. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:57:28,445][86177] Avg episode reward: [(0, '-504.280'), (1, '-526.620')] -[2023-11-28 03:57:30,337][87426] Updated weights for policy 1, policy_version 142850 (0.0009) -[2023-11-28 03:57:30,637][87424] Updated weights for policy 0, policy_version 143137 (0.0011) -[2023-11-28 03:57:30,724][87426] Updated weights for policy 1, policy_version 142860 (0.0011) -[2023-11-28 03:57:31,019][87424] Updated weights for policy 0, policy_version 143147 (0.0010) -[2023-11-28 03:57:31,099][87426] Updated weights for policy 1, policy_version 142870 (0.0009) -[2023-11-28 03:57:31,418][87424] Updated weights for policy 0, policy_version 143157 (0.0011) -[2023-11-28 03:57:31,486][87426] Updated weights for policy 1, policy_version 142880 (0.0008) -[2023-11-28 03:57:31,791][87424] Updated weights for policy 0, policy_version 143167 (0.0010) -[2023-11-28 03:57:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 73228288. Throughput: 0: 2738.5, 1: 2735.5. Samples: 73244960. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:57:33,445][86177] Avg episode reward: [(0, '-514.080'), (1, '-528.800')] -[2023-11-28 03:57:33,477][87426] Updated weights for policy 1, policy_version 142890 (0.0007) -[2023-11-28 03:57:33,722][87424] Updated weights for policy 0, policy_version 143177 (0.0009) -[2023-11-28 03:57:33,851][87426] Updated weights for policy 1, policy_version 142900 (0.0010) -[2023-11-28 03:57:34,095][87424] Updated weights for policy 0, policy_version 143187 (0.0007) -[2023-11-28 03:57:34,251][87426] Updated weights for policy 1, policy_version 142910 (0.0012) -[2023-11-28 03:57:34,475][87424] Updated weights for policy 0, policy_version 143197 (0.0007) -[2023-11-28 03:57:36,159][87426] Updated weights for policy 1, policy_version 142920 (0.0010) -[2023-11-28 03:57:36,553][87426] Updated weights for policy 1, policy_version 142930 (0.0009) -[2023-11-28 03:57:36,927][87426] Updated weights for policy 1, policy_version 142940 (0.0011) -[2023-11-28 03:57:36,964][87424] Updated weights for policy 0, policy_version 143207 (0.0008) -[2023-11-28 03:57:37,345][87424] Updated weights for policy 0, policy_version 143217 (0.0011) -[2023-11-28 03:57:37,727][87424] Updated weights for policy 0, policy_version 143227 (0.0010) -[2023-11-28 03:57:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73261056. Throughput: 0: 2720.0, 1: 2726.0. Samples: 73276556. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:57:38,445][86177] Avg episode reward: [(0, '-546.720'), (1, '-557.650')] -[2023-11-28 03:57:38,618][87426] Updated weights for policy 1, policy_version 142950 (0.0012) -[2023-11-28 03:57:39,010][87426] Updated weights for policy 1, policy_version 142960 (0.0009) -[2023-11-28 03:57:39,393][87426] Updated weights for policy 1, policy_version 142970 (0.0008) -[2023-11-28 03:57:40,271][87424] Updated weights for policy 0, policy_version 143237 (0.0009) -[2023-11-28 03:57:40,642][87424] Updated weights for policy 0, policy_version 143247 (0.0011) -[2023-11-28 03:57:41,023][87424] Updated weights for policy 0, policy_version 143257 (0.0011) -[2023-11-28 03:57:41,405][87426] Updated weights for policy 1, policy_version 142980 (0.0008) -[2023-11-28 03:57:41,788][87426] Updated weights for policy 1, policy_version 142990 (0.0011) -[2023-11-28 03:57:42,162][87426] Updated weights for policy 1, policy_version 143000 (0.0011) -[2023-11-28 03:57:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 73285632. Throughput: 0: 2704.4, 1: 2700.4. Samples: 73299972. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:57:43,445][86177] Avg episode reward: [(0, '-552.540'), (1, '-568.620')] -[2023-11-28 03:57:43,631][87424] Updated weights for policy 0, policy_version 143267 (0.0011) -[2023-11-28 03:57:44,007][87424] Updated weights for policy 0, policy_version 143277 (0.0010) -[2023-11-28 03:57:44,391][87424] Updated weights for policy 0, policy_version 143287 (0.0010) -[2023-11-28 03:57:44,467][87426] Updated weights for policy 1, policy_version 143010 (0.0011) -[2023-11-28 03:57:44,845][87426] Updated weights for policy 1, policy_version 143020 (0.0011) -[2023-11-28 03:57:45,224][87426] Updated weights for policy 1, policy_version 143030 (0.0010) -[2023-11-28 03:57:45,601][87426] Updated weights for policy 1, policy_version 143040 (0.0008) -[2023-11-28 03:57:46,528][87424] Updated weights for policy 0, policy_version 143297 (0.0009) -[2023-11-28 03:57:46,906][87424] Updated weights for policy 0, policy_version 143307 (0.0011) -[2023-11-28 03:57:47,296][87424] Updated weights for policy 0, policy_version 143317 (0.0012) -[2023-11-28 03:57:47,671][87424] Updated weights for policy 0, policy_version 143327 (0.0011) -[2023-11-28 03:57:47,854][87426] Updated weights for policy 1, policy_version 143050 (0.0012) -[2023-11-28 03:57:48,233][87426] Updated weights for policy 1, policy_version 143060 (0.0012) -[2023-11-28 03:57:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73310208. Throughput: 0: 2696.4, 1: 2692.4. Samples: 73323764. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:57:48,445][86177] Avg episode reward: [(0, '-546.490'), (1, '-574.090')] -[2023-11-28 03:57:48,615][87426] Updated weights for policy 1, policy_version 143070 (0.0012) -[2023-11-28 03:57:49,794][87424] Updated weights for policy 0, policy_version 143337 (0.0011) -[2023-11-28 03:57:50,176][87424] Updated weights for policy 0, policy_version 143347 (0.0008) -[2023-11-28 03:57:50,567][87424] Updated weights for policy 0, policy_version 143357 (0.0010) -[2023-11-28 03:57:50,792][87426] Updated weights for policy 1, policy_version 143080 (0.0012) -[2023-11-28 03:57:51,177][87426] Updated weights for policy 1, policy_version 143090 (0.0011) -[2023-11-28 03:57:51,554][87426] Updated weights for policy 1, policy_version 143100 (0.0012) -[2023-11-28 03:57:52,530][87424] Updated weights for policy 0, policy_version 143367 (0.0010) -[2023-11-28 03:57:52,913][87424] Updated weights for policy 0, policy_version 143377 (0.0009) -[2023-11-28 03:57:53,294][87424] Updated weights for policy 0, policy_version 143387 (0.0012) -[2023-11-28 03:57:53,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 73334784. Throughput: 0: 2712.2, 1: 2668.5. Samples: 73356800. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:57:53,445][86177] Avg episode reward: [(0, '-541.580'), (1, '-572.700')] -[2023-11-28 03:57:53,982][87426] Updated weights for policy 1, policy_version 143110 (0.0011) -[2023-11-28 03:57:54,361][87426] Updated weights for policy 1, policy_version 143120 (0.0012) -[2023-11-28 03:57:54,742][87426] Updated weights for policy 1, policy_version 143130 (0.0012) -[2023-11-28 03:57:55,492][87424] Updated weights for policy 0, policy_version 143397 (0.0011) -[2023-11-28 03:57:55,880][87424] Updated weights for policy 0, policy_version 143407 (0.0007) -[2023-11-28 03:57:56,269][87424] Updated weights for policy 0, policy_version 143417 (0.0007) -[2023-11-28 03:57:57,024][87426] Updated weights for policy 1, policy_version 143140 (0.0011) -[2023-11-28 03:57:57,408][87426] Updated weights for policy 1, policy_version 143150 (0.0012) -[2023-11-28 03:57:57,694][87424] Updated weights for policy 0, policy_version 143427 (0.0008) -[2023-11-28 03:57:57,785][87426] Updated weights for policy 1, policy_version 143160 (0.0011) -[2023-11-28 03:57:58,075][87424] Updated weights for policy 0, policy_version 143437 (0.0010) -[2023-11-28 03:57:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 73367552. Throughput: 0: 2706.7, 1: 2659.3. Samples: 73380772. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:57:58,445][86177] Avg episode reward: [(0, '-513.900'), (1, '-549.740')] -[2023-11-28 03:57:58,461][87424] Updated weights for policy 0, policy_version 143447 (0.0012) -[2023-11-28 03:58:00,251][87426] Updated weights for policy 1, policy_version 143170 (0.0011) -[2023-11-28 03:58:00,633][87426] Updated weights for policy 1, policy_version 143180 (0.0012) -[2023-11-28 03:58:00,926][87424] Updated weights for policy 0, policy_version 143457 (0.0011) -[2023-11-28 03:58:01,011][87426] Updated weights for policy 1, policy_version 143190 (0.0011) -[2023-11-28 03:58:01,303][87424] Updated weights for policy 0, policy_version 143467 (0.0012) -[2023-11-28 03:58:01,396][87426] Updated weights for policy 1, policy_version 143200 (0.0009) -[2023-11-28 03:58:01,695][87424] Updated weights for policy 0, policy_version 143477 (0.0011) -[2023-11-28 03:58:02,076][87424] Updated weights for policy 0, policy_version 143487 (0.0010) -[2023-11-28 03:58:03,205][87426] Updated weights for policy 1, policy_version 143210 (0.0010) -[2023-11-28 03:58:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73392128. Throughput: 0: 2717.9, 1: 2676.5. Samples: 73405936. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:58:03,445][86177] Avg episode reward: [(0, '-514.570'), (1, '-528.020')] -[2023-11-28 03:58:03,588][87426] Updated weights for policy 1, policy_version 143220 (0.0008) -[2023-11-28 03:58:03,972][87426] Updated weights for policy 1, policy_version 143230 (0.0011) -[2023-11-28 03:58:04,593][87424] Updated weights for policy 0, policy_version 143497 (0.0008) -[2023-11-28 03:58:04,975][87424] Updated weights for policy 0, policy_version 143507 (0.0011) -[2023-11-28 03:58:05,365][87424] Updated weights for policy 0, policy_version 143517 (0.0011) -[2023-11-28 03:58:06,005][87426] Updated weights for policy 1, policy_version 143240 (0.0012) -[2023-11-28 03:58:06,382][87426] Updated weights for policy 1, policy_version 143250 (0.0012) -[2023-11-28 03:58:06,758][87426] Updated weights for policy 1, policy_version 143260 (0.0008) -[2023-11-28 03:58:07,916][87424] Updated weights for policy 0, policy_version 143527 (0.0008) -[2023-11-28 03:58:08,291][87424] Updated weights for policy 0, policy_version 143537 (0.0008) -[2023-11-28 03:58:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 73416704. Throughput: 0: 2681.1, 1: 2695.2. Samples: 73438324. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:58:08,445][86177] Avg episode reward: [(0, '-518.740'), (1, '-505.380')] -[2023-11-28 03:58:08,682][87424] Updated weights for policy 0, policy_version 143547 (0.0007) -[2023-11-28 03:58:09,152][87426] Updated weights for policy 1, policy_version 143270 (0.0009) -[2023-11-28 03:58:09,532][87426] Updated weights for policy 1, policy_version 143280 (0.0008) -[2023-11-28 03:58:09,921][87426] Updated weights for policy 1, policy_version 143290 (0.0009) -[2023-11-28 03:58:10,950][87424] Updated weights for policy 0, policy_version 143557 (0.0009) -[2023-11-28 03:58:11,327][87424] Updated weights for policy 0, policy_version 143567 (0.0008) -[2023-11-28 03:58:11,714][87424] Updated weights for policy 0, policy_version 143577 (0.0010) -[2023-11-28 03:58:11,783][87426] Updated weights for policy 1, policy_version 143300 (0.0009) -[2023-11-28 03:58:12,161][87426] Updated weights for policy 1, policy_version 143310 (0.0011) -[2023-11-28 03:58:12,542][87426] Updated weights for policy 1, policy_version 143320 (0.0011) -[2023-11-28 03:58:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73449472. Throughput: 0: 2671.2, 1: 2698.5. Samples: 73462152. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:58:13,445][86177] Avg episode reward: [(0, '-519.610'), (1, '-506.460')] -[2023-11-28 03:58:13,830][87424] Updated weights for policy 0, policy_version 143587 (0.0012) -[2023-11-28 03:58:14,210][87424] Updated weights for policy 0, policy_version 143597 (0.0012) -[2023-11-28 03:58:14,598][87424] Updated weights for policy 0, policy_version 143607 (0.0011) -[2023-11-28 03:58:15,088][87426] Updated weights for policy 1, policy_version 143330 (0.0011) -[2023-11-28 03:58:15,476][87426] Updated weights for policy 1, policy_version 143340 (0.0009) -[2023-11-28 03:58:15,855][87426] Updated weights for policy 1, policy_version 143350 (0.0011) -[2023-11-28 03:58:16,231][87426] Updated weights for policy 1, policy_version 143360 (0.0011) -[2023-11-28 03:58:17,058][87424] Updated weights for policy 0, policy_version 143617 (0.0009) -[2023-11-28 03:58:17,442][87424] Updated weights for policy 0, policy_version 143627 (0.0012) -[2023-11-28 03:58:17,823][87424] Updated weights for policy 0, policy_version 143637 (0.0012) -[2023-11-28 03:58:18,199][87424] Updated weights for policy 0, policy_version 143647 (0.0012) -[2023-11-28 03:58:18,231][87426] Updated weights for policy 1, policy_version 143370 (0.0008) -[2023-11-28 03:58:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73474048. Throughput: 0: 2664.4, 1: 2684.4. Samples: 73485656. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:58:18,445][86177] Avg episode reward: [(0, '-525.600'), (1, '-520.080')] -[2023-11-28 03:58:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000143648_36773888.pth... -[2023-11-28 03:58:18,507][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000141120_36126720.pth -[2023-11-28 03:58:18,614][87426] Updated weights for policy 1, policy_version 143380 (0.0008) -[2023-11-28 03:58:18,997][87426] Updated weights for policy 1, policy_version 143390 (0.0009) -[2023-11-28 03:58:19,073][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000143392_36708352.pth... -[2023-11-28 03:58:19,120][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000140800_36044800.pth -[2023-11-28 03:58:19,816][87424] Updated weights for policy 0, policy_version 143657 (0.0011) -[2023-11-28 03:58:20,198][87424] Updated weights for policy 0, policy_version 143667 (0.0009) -[2023-11-28 03:58:20,585][87424] Updated weights for policy 0, policy_version 143677 (0.0008) -[2023-11-28 03:58:21,139][87426] Updated weights for policy 1, policy_version 143400 (0.0010) -[2023-11-28 03:58:21,514][87426] Updated weights for policy 1, policy_version 143410 (0.0011) -[2023-11-28 03:58:21,906][87426] Updated weights for policy 1, policy_version 143420 (0.0009) -[2023-11-28 03:58:22,934][87424] Updated weights for policy 0, policy_version 143687 (0.0010) -[2023-11-28 03:58:23,318][87424] Updated weights for policy 0, policy_version 143697 (0.0012) -[2023-11-28 03:58:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 73498624. Throughput: 0: 2668.9, 1: 2684.2. Samples: 73517444. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:58:23,445][86177] Avg episode reward: [(0, '-532.800'), (1, '-526.630')] -[2023-11-28 03:58:23,702][87424] Updated weights for policy 0, policy_version 143707 (0.0011) -[2023-11-28 03:58:24,428][87426] Updated weights for policy 1, policy_version 143430 (0.0010) -[2023-11-28 03:58:24,812][87426] Updated weights for policy 1, policy_version 143440 (0.0011) -[2023-11-28 03:58:25,198][87426] Updated weights for policy 1, policy_version 143450 (0.0011) -[2023-11-28 03:58:25,508][87424] Updated weights for policy 0, policy_version 143717 (0.0011) -[2023-11-28 03:58:25,872][87424] Updated weights for policy 0, policy_version 143727 (0.0012) -[2023-11-28 03:58:26,257][87424] Updated weights for policy 0, policy_version 143737 (0.0012) -[2023-11-28 03:58:27,725][87426] Updated weights for policy 1, policy_version 143460 (0.0011) -[2023-11-28 03:58:28,116][87426] Updated weights for policy 1, policy_version 143470 (0.0012) -[2023-11-28 03:58:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 73523200. Throughput: 0: 2685.2, 1: 2684.6. Samples: 73541612. Policy #0 lag: (min: 31.0, avg: 48.1, max: 71.0) -[2023-11-28 03:58:28,445][86177] Avg episode reward: [(0, '-529.820'), (1, '-528.420')] -[2023-11-28 03:58:28,494][87426] Updated weights for policy 1, policy_version 143480 (0.0011) -[2023-11-28 03:58:28,590][87424] Updated weights for policy 0, policy_version 143747 (0.0012) -[2023-11-28 03:58:28,966][87424] Updated weights for policy 0, policy_version 143757 (0.0011) -[2023-11-28 03:58:29,354][87424] Updated weights for policy 0, policy_version 143767 (0.0010) -[2023-11-28 03:58:30,985][87426] Updated weights for policy 1, policy_version 143490 (0.0010) -[2023-11-28 03:58:31,362][87426] Updated weights for policy 1, policy_version 143500 (0.0008) -[2023-11-28 03:58:31,743][87426] Updated weights for policy 1, policy_version 143510 (0.0008) -[2023-11-28 03:58:31,871][87424] Updated weights for policy 0, policy_version 143777 (0.0008) -[2023-11-28 03:58:32,121][87426] Updated weights for policy 1, policy_version 143520 (0.0009) -[2023-11-28 03:58:32,253][87424] Updated weights for policy 0, policy_version 143787 (0.0011) -[2023-11-28 03:58:32,649][87424] Updated weights for policy 0, policy_version 143797 (0.0012) -[2023-11-28 03:58:33,038][87424] Updated weights for policy 0, policy_version 143807 (0.0012) -[2023-11-28 03:58:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 73555968. Throughput: 0: 2693.2, 1: 2691.1. Samples: 73566060. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:58:33,445][86177] Avg episode reward: [(0, '-532.400'), (1, '-514.330')] -[2023-11-28 03:58:34,212][87426] Updated weights for policy 1, policy_version 143530 (0.0008) -[2023-11-28 03:58:34,601][87426] Updated weights for policy 1, policy_version 143540 (0.0009) -[2023-11-28 03:58:34,636][87424] Updated weights for policy 0, policy_version 143817 (0.0008) -[2023-11-28 03:58:34,974][87426] Updated weights for policy 1, policy_version 143550 (0.0011) -[2023-11-28 03:58:35,014][87424] Updated weights for policy 0, policy_version 143827 (0.0009) -[2023-11-28 03:58:35,388][87424] Updated weights for policy 0, policy_version 143837 (0.0008) -[2023-11-28 03:58:37,068][87426] Updated weights for policy 1, policy_version 143560 (0.0010) -[2023-11-28 03:58:37,172][87424] Updated weights for policy 0, policy_version 143847 (0.0009) -[2023-11-28 03:58:37,447][87426] Updated weights for policy 1, policy_version 143570 (0.0008) -[2023-11-28 03:58:37,554][87424] Updated weights for policy 0, policy_version 143857 (0.0009) -[2023-11-28 03:58:37,825][87426] Updated weights for policy 1, policy_version 143580 (0.0007) -[2023-11-28 03:58:37,943][87424] Updated weights for policy 0, policy_version 143867 (0.0008) -[2023-11-28 03:58:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73588736. Throughput: 0: 2678.4, 1: 2709.1. Samples: 73599236. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:58:38,445][86177] Avg episode reward: [(0, '-527.520'), (1, '-507.620')] -[2023-11-28 03:58:39,474][87426] Updated weights for policy 1, policy_version 143590 (0.0009) -[2023-11-28 03:58:39,844][87426] Updated weights for policy 1, policy_version 143600 (0.0010) -[2023-11-28 03:58:40,220][87426] Updated weights for policy 1, policy_version 143610 (0.0011) -[2023-11-28 03:58:40,285][87424] Updated weights for policy 0, policy_version 143877 (0.0008) -[2023-11-28 03:58:40,665][87424] Updated weights for policy 0, policy_version 143887 (0.0011) -[2023-11-28 03:58:41,047][87424] Updated weights for policy 0, policy_version 143897 (0.0012) -[2023-11-28 03:58:42,680][87426] Updated weights for policy 1, policy_version 143620 (0.0011) -[2023-11-28 03:58:43,063][87426] Updated weights for policy 1, policy_version 143630 (0.0012) -[2023-11-28 03:58:43,307][87424] Updated weights for policy 0, policy_version 143907 (0.0010) -[2023-11-28 03:58:43,433][87426] Updated weights for policy 1, policy_version 143640 (0.0012) -[2023-11-28 03:58:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 73605120. Throughput: 0: 2676.4, 1: 2708.9. Samples: 73623108. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:58:43,445][86177] Avg episode reward: [(0, '-531.410'), (1, '-511.040')] -[2023-11-28 03:58:43,691][87424] Updated weights for policy 0, policy_version 143917 (0.0012) -[2023-11-28 03:58:44,068][87424] Updated weights for policy 0, policy_version 143927 (0.0012) -[2023-11-28 03:58:45,798][87426] Updated weights for policy 1, policy_version 143650 (0.0011) -[2023-11-28 03:58:46,180][87426] Updated weights for policy 1, policy_version 143660 (0.0008) -[2023-11-28 03:58:46,367][87424] Updated weights for policy 0, policy_version 143937 (0.0009) -[2023-11-28 03:58:46,562][87426] Updated weights for policy 1, policy_version 143670 (0.0009) -[2023-11-28 03:58:46,751][87424] Updated weights for policy 0, policy_version 143947 (0.0009) -[2023-11-28 03:58:46,943][87426] Updated weights for policy 1, policy_version 143680 (0.0008) -[2023-11-28 03:58:47,134][87424] Updated weights for policy 0, policy_version 143957 (0.0011) -[2023-11-28 03:58:47,519][87424] Updated weights for policy 0, policy_version 143967 (0.0012) -[2023-11-28 03:58:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73637888. Throughput: 0: 2688.0, 1: 2704.5. Samples: 73648600. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:58:48,445][86177] Avg episode reward: [(0, '-532.890'), (1, '-542.170')] -[2023-11-28 03:58:48,815][87426] Updated weights for policy 1, policy_version 143690 (0.0012) -[2023-11-28 03:58:49,190][87426] Updated weights for policy 1, policy_version 143700 (0.0012) -[2023-11-28 03:58:49,571][87426] Updated weights for policy 1, policy_version 143710 (0.0011) -[2023-11-28 03:58:49,816][87424] Updated weights for policy 0, policy_version 143977 (0.0011) -[2023-11-28 03:58:50,201][87424] Updated weights for policy 0, policy_version 143987 (0.0012) -[2023-11-28 03:58:50,581][87424] Updated weights for policy 0, policy_version 143997 (0.0012) -[2023-11-28 03:58:51,693][87426] Updated weights for policy 1, policy_version 143720 (0.0009) -[2023-11-28 03:58:52,064][87426] Updated weights for policy 1, policy_version 143730 (0.0010) -[2023-11-28 03:58:52,445][87426] Updated weights for policy 1, policy_version 143740 (0.0009) -[2023-11-28 03:58:52,822][87424] Updated weights for policy 0, policy_version 144007 (0.0011) -[2023-11-28 03:58:53,199][87424] Updated weights for policy 0, policy_version 144017 (0.0009) -[2023-11-28 03:58:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 73662464. Throughput: 0: 2709.7, 1: 2694.1. Samples: 73681492. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:58:53,445][86177] Avg episode reward: [(0, '-570.520'), (1, '-564.050')] -[2023-11-28 03:58:53,596][87424] Updated weights for policy 0, policy_version 144027 (0.0012) -[2023-11-28 03:58:54,823][87426] Updated weights for policy 1, policy_version 143750 (0.0011) -[2023-11-28 03:58:55,205][87426] Updated weights for policy 1, policy_version 143760 (0.0008) -[2023-11-28 03:58:55,594][87426] Updated weights for policy 1, policy_version 143770 (0.0007) -[2023-11-28 03:58:55,860][87424] Updated weights for policy 0, policy_version 144037 (0.0011) -[2023-11-28 03:58:56,236][87424] Updated weights for policy 0, policy_version 144047 (0.0012) -[2023-11-28 03:58:56,611][87424] Updated weights for policy 0, policy_version 144057 (0.0012) -[2023-11-28 03:58:57,238][87426] Updated weights for policy 1, policy_version 143780 (0.0009) -[2023-11-28 03:58:57,624][87426] Updated weights for policy 1, policy_version 143790 (0.0012) -[2023-11-28 03:58:58,008][87426] Updated weights for policy 1, policy_version 143800 (0.0012) -[2023-11-28 03:58:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73695232. Throughput: 0: 2716.9, 1: 2698.1. Samples: 73705828. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:58:58,445][86177] Avg episode reward: [(0, '-573.180'), (1, '-594.630')] -[2023-11-28 03:58:58,955][87424] Updated weights for policy 0, policy_version 144067 (0.0011) -[2023-11-28 03:58:59,331][87424] Updated weights for policy 0, policy_version 144077 (0.0007) -[2023-11-28 03:58:59,712][87424] Updated weights for policy 0, policy_version 144087 (0.0008) -[2023-11-28 03:59:00,278][87426] Updated weights for policy 1, policy_version 143810 (0.0012) -[2023-11-28 03:59:00,665][87426] Updated weights for policy 1, policy_version 143820 (0.0011) -[2023-11-28 03:59:01,035][87426] Updated weights for policy 1, policy_version 143830 (0.0009) -[2023-11-28 03:59:01,415][87426] Updated weights for policy 1, policy_version 143840 (0.0008) -[2023-11-28 03:59:01,638][87424] Updated weights for policy 0, policy_version 144097 (0.0010) -[2023-11-28 03:59:02,013][87424] Updated weights for policy 0, policy_version 144107 (0.0010) -[2023-11-28 03:59:02,406][87424] Updated weights for policy 0, policy_version 144117 (0.0009) -[2023-11-28 03:59:02,789][87424] Updated weights for policy 0, policy_version 144127 (0.0008) -[2023-11-28 03:59:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 73719808. Throughput: 0: 2708.4, 1: 2718.0. Samples: 73729840. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:59:03,445][86177] Avg episode reward: [(0, '-553.030'), (1, '-597.420')] -[2023-11-28 03:59:03,650][87426] Updated weights for policy 1, policy_version 143850 (0.0011) -[2023-11-28 03:59:04,035][87426] Updated weights for policy 1, policy_version 143860 (0.0011) -[2023-11-28 03:59:04,416][87426] Updated weights for policy 1, policy_version 143870 (0.0012) -[2023-11-28 03:59:04,898][87424] Updated weights for policy 0, policy_version 144137 (0.0011) -[2023-11-28 03:59:05,279][87424] Updated weights for policy 0, policy_version 144147 (0.0010) -[2023-11-28 03:59:05,655][87424] Updated weights for policy 0, policy_version 144157 (0.0008) -[2023-11-28 03:59:06,612][87426] Updated weights for policy 1, policy_version 143880 (0.0008) -[2023-11-28 03:59:06,991][87426] Updated weights for policy 1, policy_version 143890 (0.0012) -[2023-11-28 03:59:07,361][87426] Updated weights for policy 1, policy_version 143900 (0.0010) -[2023-11-28 03:59:08,084][87424] Updated weights for policy 0, policy_version 144167 (0.0007) -[2023-11-28 03:59:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73744384. Throughput: 0: 2709.2, 1: 2715.4. Samples: 73761552. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:59:08,445][86177] Avg episode reward: [(0, '-591.530'), (1, '-564.390')] -[2023-11-28 03:59:08,468][87424] Updated weights for policy 0, policy_version 144177 (0.0007) -[2023-11-28 03:59:08,847][87424] Updated weights for policy 0, policy_version 144187 (0.0008) -[2023-11-28 03:59:09,480][87426] Updated weights for policy 1, policy_version 143910 (0.0011) -[2023-11-28 03:59:09,862][87426] Updated weights for policy 1, policy_version 143920 (0.0011) -[2023-11-28 03:59:10,246][87426] Updated weights for policy 1, policy_version 143930 (0.0011) -[2023-11-28 03:59:11,383][87424] Updated weights for policy 0, policy_version 144197 (0.0008) -[2023-11-28 03:59:11,762][87424] Updated weights for policy 0, policy_version 144207 (0.0009) -[2023-11-28 03:59:12,139][87424] Updated weights for policy 0, policy_version 144217 (0.0011) -[2023-11-28 03:59:12,388][87426] Updated weights for policy 1, policy_version 143940 (0.0010) -[2023-11-28 03:59:12,766][87426] Updated weights for policy 1, policy_version 143950 (0.0008) -[2023-11-28 03:59:13,148][87426] Updated weights for policy 1, policy_version 143960 (0.0011) -[2023-11-28 03:59:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 73768960. Throughput: 0: 2693.2, 1: 2731.0. Samples: 73785700. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:59:13,445][86177] Avg episode reward: [(0, '-544.430'), (1, '-601.060')] -[2023-11-28 03:59:14,751][87424] Updated weights for policy 0, policy_version 144227 (0.0011) -[2023-11-28 03:59:15,139][87424] Updated weights for policy 0, policy_version 144237 (0.0011) -[2023-11-28 03:59:15,309][87426] Updated weights for policy 1, policy_version 143970 (0.0011) -[2023-11-28 03:59:15,521][87424] Updated weights for policy 0, policy_version 144247 (0.0012) -[2023-11-28 03:59:15,678][87426] Updated weights for policy 1, policy_version 143980 (0.0012) -[2023-11-28 03:59:16,048][87426] Updated weights for policy 1, policy_version 143990 (0.0012) -[2023-11-28 03:59:16,424][87426] Updated weights for policy 1, policy_version 144000 (0.0011) -[2023-11-28 03:59:17,294][87424] Updated weights for policy 0, policy_version 144257 (0.0012) -[2023-11-28 03:59:17,682][87424] Updated weights for policy 0, policy_version 144267 (0.0012) -[2023-11-28 03:59:18,059][87424] Updated weights for policy 0, policy_version 144277 (0.0011) -[2023-11-28 03:59:18,438][87424] Updated weights for policy 0, policy_version 144287 (0.0012) -[2023-11-28 03:59:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 73793536. Throughput: 0: 2680.1, 1: 2732.6. Samples: 73809632. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:59:18,445][86177] Avg episode reward: [(0, '-592.030'), (1, '-572.950')] -[2023-11-28 03:59:18,745][87426] Updated weights for policy 1, policy_version 144010 (0.0011) -[2023-11-28 03:59:19,131][87426] Updated weights for policy 1, policy_version 144020 (0.0012) -[2023-11-28 03:59:19,519][87426] Updated weights for policy 1, policy_version 144030 (0.0012) -[2023-11-28 03:59:20,200][87424] Updated weights for policy 0, policy_version 144297 (0.0012) -[2023-11-28 03:59:20,582][87424] Updated weights for policy 0, policy_version 144307 (0.0011) -[2023-11-28 03:59:20,960][87424] Updated weights for policy 0, policy_version 144317 (0.0012) -[2023-11-28 03:59:21,755][87426] Updated weights for policy 1, policy_version 144040 (0.0010) -[2023-11-28 03:59:22,128][87426] Updated weights for policy 1, policy_version 144050 (0.0009) -[2023-11-28 03:59:22,507][87426] Updated weights for policy 1, policy_version 144060 (0.0011) -[2023-11-28 03:59:23,348][87424] Updated weights for policy 0, policy_version 144327 (0.0011) -[2023-11-28 03:59:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73826304. Throughput: 0: 2686.0, 1: 2726.9. Samples: 73842820. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:59:23,445][86177] Avg episode reward: [(0, '-601.480'), (1, '-559.100')] -[2023-11-28 03:59:23,728][87424] Updated weights for policy 0, policy_version 144337 (0.0012) -[2023-11-28 03:59:24,117][87424] Updated weights for policy 0, policy_version 144347 (0.0012) -[2023-11-28 03:59:24,475][87426] Updated weights for policy 1, policy_version 144070 (0.0010) -[2023-11-28 03:59:24,847][87426] Updated weights for policy 1, policy_version 144080 (0.0007) -[2023-11-28 03:59:25,226][87426] Updated weights for policy 1, policy_version 144090 (0.0008) -[2023-11-28 03:59:26,663][87424] Updated weights for policy 0, policy_version 144357 (0.0009) -[2023-11-28 03:59:27,052][87424] Updated weights for policy 0, policy_version 144367 (0.0011) -[2023-11-28 03:59:27,432][87424] Updated weights for policy 0, policy_version 144377 (0.0011) -[2023-11-28 03:59:27,717][87426] Updated weights for policy 1, policy_version 144100 (0.0009) -[2023-11-28 03:59:28,087][87426] Updated weights for policy 1, policy_version 144110 (0.0011) -[2023-11-28 03:59:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 73850880. Throughput: 0: 2684.6, 1: 2724.2. Samples: 73866504. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:59:28,445][86177] Avg episode reward: [(0, '-570.780'), (1, '-584.490')] -[2023-11-28 03:59:28,465][87426] Updated weights for policy 1, policy_version 144120 (0.0011) -[2023-11-28 03:59:29,724][87424] Updated weights for policy 0, policy_version 144387 (0.0012) -[2023-11-28 03:59:30,115][87424] Updated weights for policy 0, policy_version 144397 (0.0012) -[2023-11-28 03:59:30,496][87424] Updated weights for policy 0, policy_version 144407 (0.0012) -[2023-11-28 03:59:30,789][87426] Updated weights for policy 1, policy_version 144130 (0.0012) -[2023-11-28 03:59:31,173][87426] Updated weights for policy 1, policy_version 144140 (0.0009) -[2023-11-28 03:59:31,546][87426] Updated weights for policy 1, policy_version 144150 (0.0011) -[2023-11-28 03:59:31,923][87426] Updated weights for policy 1, policy_version 144160 (0.0012) -[2023-11-28 03:59:32,316][87424] Updated weights for policy 0, policy_version 144417 (0.0010) -[2023-11-28 03:59:32,695][87424] Updated weights for policy 0, policy_version 144427 (0.0011) -[2023-11-28 03:59:33,077][87424] Updated weights for policy 0, policy_version 144437 (0.0011) -[2023-11-28 03:59:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 73875456. Throughput: 0: 2674.7, 1: 2715.5. Samples: 73891156. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:59:33,445][86177] Avg episode reward: [(0, '-580.460'), (1, '-532.470')] -[2023-11-28 03:59:33,449][87424] Updated weights for policy 0, policy_version 144447 (0.0011) -[2023-11-28 03:59:33,959][87426] Updated weights for policy 1, policy_version 144170 (0.0008) -[2023-11-28 03:59:34,340][87426] Updated weights for policy 1, policy_version 144180 (0.0007) -[2023-11-28 03:59:34,724][87426] Updated weights for policy 1, policy_version 144190 (0.0008) -[2023-11-28 03:59:35,325][87424] Updated weights for policy 0, policy_version 144457 (0.0011) -[2023-11-28 03:59:35,710][87424] Updated weights for policy 0, policy_version 144467 (0.0009) -[2023-11-28 03:59:36,097][87424] Updated weights for policy 0, policy_version 144477 (0.0007) -[2023-11-28 03:59:36,787][87426] Updated weights for policy 1, policy_version 144200 (0.0010) -[2023-11-28 03:59:37,168][87426] Updated weights for policy 1, policy_version 144210 (0.0007) -[2023-11-28 03:59:37,546][87426] Updated weights for policy 1, policy_version 144220 (0.0008) -[2023-11-28 03:59:37,875][87424] Updated weights for policy 0, policy_version 144487 (0.0011) -[2023-11-28 03:59:38,254][87424] Updated weights for policy 0, policy_version 144497 (0.0012) -[2023-11-28 03:59:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 73908224. Throughput: 0: 2704.7, 1: 2699.1. Samples: 73924664. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 03:59:38,445][86177] Avg episode reward: [(0, '-576.250'), (1, '-527.170')] -[2023-11-28 03:59:38,639][87424] Updated weights for policy 0, policy_version 144507 (0.0010) -[2023-11-28 03:59:39,736][87426] Updated weights for policy 1, policy_version 144230 (0.0011) -[2023-11-28 03:59:40,110][87426] Updated weights for policy 1, policy_version 144240 (0.0012) -[2023-11-28 03:59:40,486][87426] Updated weights for policy 1, policy_version 144250 (0.0012) -[2023-11-28 03:59:40,877][87424] Updated weights for policy 0, policy_version 144517 (0.0008) -[2023-11-28 03:59:41,263][87424] Updated weights for policy 0, policy_version 144527 (0.0008) -[2023-11-28 03:59:41,646][87424] Updated weights for policy 0, policy_version 144537 (0.0008) -[2023-11-28 03:59:43,111][87426] Updated weights for policy 1, policy_version 144260 (0.0010) -[2023-11-28 03:59:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 73932800. Throughput: 0: 2704.5, 1: 2707.4. Samples: 73949364. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:59:43,445][86177] Avg episode reward: [(0, '-609.780'), (1, '-568.190')] -[2023-11-28 03:59:43,494][87426] Updated weights for policy 1, policy_version 144270 (0.0008) -[2023-11-28 03:59:43,880][87426] Updated weights for policy 1, policy_version 144280 (0.0007) -[2023-11-28 03:59:44,034][87424] Updated weights for policy 0, policy_version 144547 (0.0009) -[2023-11-28 03:59:44,402][87424] Updated weights for policy 0, policy_version 144557 (0.0011) -[2023-11-28 03:59:44,780][87424] Updated weights for policy 0, policy_version 144567 (0.0012) -[2023-11-28 03:59:45,891][87426] Updated weights for policy 1, policy_version 144290 (0.0008) -[2023-11-28 03:59:46,272][87426] Updated weights for policy 1, policy_version 144300 (0.0012) -[2023-11-28 03:59:46,643][87426] Updated weights for policy 1, policy_version 144310 (0.0011) -[2023-11-28 03:59:46,722][87424] Updated weights for policy 0, policy_version 144577 (0.0012) -[2023-11-28 03:59:47,032][87426] Updated weights for policy 1, policy_version 144320 (0.0011) -[2023-11-28 03:59:47,107][87424] Updated weights for policy 0, policy_version 144587 (0.0008) -[2023-11-28 03:59:47,491][87424] Updated weights for policy 0, policy_version 144597 (0.0007) -[2023-11-28 03:59:47,876][87424] Updated weights for policy 0, policy_version 144607 (0.0008) -[2023-11-28 03:59:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73965568. Throughput: 0: 2714.6, 1: 2702.6. Samples: 73973612. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:59:48,445][86177] Avg episode reward: [(0, '-631.500'), (1, '-563.500')] -[2023-11-28 03:59:49,117][87426] Updated weights for policy 1, policy_version 144330 (0.0011) -[2023-11-28 03:59:49,504][87426] Updated weights for policy 1, policy_version 144340 (0.0011) -[2023-11-28 03:59:49,855][87424] Updated weights for policy 0, policy_version 144617 (0.0009) -[2023-11-28 03:59:49,885][87426] Updated weights for policy 1, policy_version 144350 (0.0012) -[2023-11-28 03:59:50,238][87424] Updated weights for policy 0, policy_version 144627 (0.0012) -[2023-11-28 03:59:50,615][87424] Updated weights for policy 0, policy_version 144637 (0.0011) -[2023-11-28 03:59:52,341][87426] Updated weights for policy 1, policy_version 144360 (0.0011) -[2023-11-28 03:59:52,727][87426] Updated weights for policy 1, policy_version 144370 (0.0008) -[2023-11-28 03:59:52,948][87424] Updated weights for policy 0, policy_version 144647 (0.0011) -[2023-11-28 03:59:53,112][87426] Updated weights for policy 1, policy_version 144380 (0.0011) -[2023-11-28 03:59:53,348][87424] Updated weights for policy 0, policy_version 144657 (0.0012) -[2023-11-28 03:59:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 73990144. Throughput: 0: 2722.7, 1: 2714.0. Samples: 74006200. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:59:53,445][86177] Avg episode reward: [(0, '-627.440'), (1, '-585.750')] -[2023-11-28 03:59:53,737][87424] Updated weights for policy 0, policy_version 144667 (0.0012) -[2023-11-28 03:59:55,382][87426] Updated weights for policy 1, policy_version 144390 (0.0011) -[2023-11-28 03:59:55,769][87426] Updated weights for policy 1, policy_version 144400 (0.0012) -[2023-11-28 03:59:56,081][87424] Updated weights for policy 0, policy_version 144677 (0.0010) -[2023-11-28 03:59:56,148][87426] Updated weights for policy 1, policy_version 144410 (0.0011) -[2023-11-28 03:59:56,455][87424] Updated weights for policy 0, policy_version 144687 (0.0011) -[2023-11-28 03:59:56,846][87424] Updated weights for policy 0, policy_version 144697 (0.0012) -[2023-11-28 03:59:57,772][87426] Updated weights for policy 1, policy_version 144420 (0.0009) -[2023-11-28 03:59:58,146][87426] Updated weights for policy 1, policy_version 144430 (0.0009) -[2023-11-28 03:59:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 74014720. Throughput: 0: 2728.5, 1: 2720.4. Samples: 74030904. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 03:59:58,445][86177] Avg episode reward: [(0, '-586.370'), (1, '-595.890')] -[2023-11-28 03:59:58,525][87426] Updated weights for policy 1, policy_version 144440 (0.0009) -[2023-11-28 03:59:58,907][87424] Updated weights for policy 0, policy_version 144707 (0.0011) -[2023-11-28 03:59:59,281][87424] Updated weights for policy 0, policy_version 144717 (0.0008) -[2023-11-28 03:59:59,669][87424] Updated weights for policy 0, policy_version 144727 (0.0007) -[2023-11-28 04:00:00,854][87426] Updated weights for policy 1, policy_version 144450 (0.0009) -[2023-11-28 04:00:01,238][87426] Updated weights for policy 1, policy_version 144460 (0.0008) -[2023-11-28 04:00:01,621][87426] Updated weights for policy 1, policy_version 144470 (0.0007) -[2023-11-28 04:00:01,996][87426] Updated weights for policy 1, policy_version 144480 (0.0009) -[2023-11-28 04:00:02,000][87424] Updated weights for policy 0, policy_version 144737 (0.0010) -[2023-11-28 04:00:02,374][87424] Updated weights for policy 0, policy_version 144747 (0.0012) -[2023-11-28 04:00:02,754][87424] Updated weights for policy 0, policy_version 144757 (0.0012) -[2023-11-28 04:00:03,136][87424] Updated weights for policy 0, policy_version 144767 (0.0012) -[2023-11-28 04:00:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74047488. Throughput: 0: 2750.3, 1: 2725.5. Samples: 74056044. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 04:00:03,445][86177] Avg episode reward: [(0, '-559.330'), (1, '-559.060')] -[2023-11-28 04:00:03,847][87426] Updated weights for policy 1, policy_version 144490 (0.0009) -[2023-11-28 04:00:04,238][87426] Updated weights for policy 1, policy_version 144500 (0.0007) -[2023-11-28 04:00:04,616][87426] Updated weights for policy 1, policy_version 144510 (0.0008) -[2023-11-28 04:00:05,479][87424] Updated weights for policy 0, policy_version 144777 (0.0008) -[2023-11-28 04:00:05,861][87424] Updated weights for policy 0, policy_version 144787 (0.0007) -[2023-11-28 04:00:06,257][87424] Updated weights for policy 0, policy_version 144797 (0.0007) -[2023-11-28 04:00:06,790][87426] Updated weights for policy 1, policy_version 144520 (0.0010) -[2023-11-28 04:00:07,177][87426] Updated weights for policy 1, policy_version 144530 (0.0010) -[2023-11-28 04:00:07,564][87426] Updated weights for policy 1, policy_version 144540 (0.0007) -[2023-11-28 04:00:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74072064. Throughput: 0: 2721.8, 1: 2719.7. Samples: 74087684. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 04:00:08,445][86177] Avg episode reward: [(0, '-520.810'), (1, '-543.510')] -[2023-11-28 04:00:08,704][87424] Updated weights for policy 0, policy_version 144807 (0.0011) -[2023-11-28 04:00:09,089][87424] Updated weights for policy 0, policy_version 144817 (0.0011) -[2023-11-28 04:00:09,464][87424] Updated weights for policy 0, policy_version 144827 (0.0011) -[2023-11-28 04:00:09,937][87426] Updated weights for policy 1, policy_version 144550 (0.0008) -[2023-11-28 04:00:10,315][87426] Updated weights for policy 1, policy_version 144560 (0.0007) -[2023-11-28 04:00:10,698][87426] Updated weights for policy 1, policy_version 144570 (0.0008) -[2023-11-28 04:00:11,899][87424] Updated weights for policy 0, policy_version 144837 (0.0009) -[2023-11-28 04:00:12,282][87424] Updated weights for policy 0, policy_version 144847 (0.0011) -[2023-11-28 04:00:12,666][87424] Updated weights for policy 0, policy_version 144857 (0.0011) -[2023-11-28 04:00:12,925][87426] Updated weights for policy 1, policy_version 144580 (0.0010) -[2023-11-28 04:00:13,304][87426] Updated weights for policy 1, policy_version 144590 (0.0010) -[2023-11-28 04:00:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74096640. Throughput: 0: 2717.1, 1: 2722.8. Samples: 74111296. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 04:00:13,445][86177] Avg episode reward: [(0, '-525.030'), (1, '-513.600')] -[2023-11-28 04:00:13,692][87426] Updated weights for policy 1, policy_version 144600 (0.0010) -[2023-11-28 04:00:14,744][87424] Updated weights for policy 0, policy_version 144867 (0.0011) -[2023-11-28 04:00:15,121][87424] Updated weights for policy 0, policy_version 144877 (0.0012) -[2023-11-28 04:00:15,490][87424] Updated weights for policy 0, policy_version 144887 (0.0012) -[2023-11-28 04:00:16,102][87426] Updated weights for policy 1, policy_version 144610 (0.0008) -[2023-11-28 04:00:16,481][87426] Updated weights for policy 1, policy_version 144620 (0.0012) -[2023-11-28 04:00:16,853][87426] Updated weights for policy 1, policy_version 144630 (0.0007) -[2023-11-28 04:00:17,233][87426] Updated weights for policy 1, policy_version 144640 (0.0008) -[2023-11-28 04:00:17,533][87424] Updated weights for policy 0, policy_version 144897 (0.0010) -[2023-11-28 04:00:17,904][87424] Updated weights for policy 0, policy_version 144907 (0.0010) -[2023-11-28 04:00:18,291][87424] Updated weights for policy 0, policy_version 144917 (0.0008) -[2023-11-28 04:00:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 74121216. Throughput: 0: 2707.6, 1: 2714.6. Samples: 74135152. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 04:00:18,445][86177] Avg episode reward: [(0, '-538.700'), (1, '-521.950')] -[2023-11-28 04:00:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000144640_37027840.pth... -[2023-11-28 04:00:18,495][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000142112_36380672.pth -[2023-11-28 04:00:18,672][87424] Updated weights for policy 0, policy_version 144927 (0.0008) -[2023-11-28 04:00:18,709][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000144928_37101568.pth... -[2023-11-28 04:00:18,739][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000142400_36454400.pth -[2023-11-28 04:00:19,702][87426] Updated weights for policy 1, policy_version 144650 (0.0012) -[2023-11-28 04:00:20,088][87426] Updated weights for policy 1, policy_version 144660 (0.0012) -[2023-11-28 04:00:20,457][87426] Updated weights for policy 1, policy_version 144670 (0.0011) -[2023-11-28 04:00:21,103][87424] Updated weights for policy 0, policy_version 144937 (0.0011) -[2023-11-28 04:00:21,491][87424] Updated weights for policy 0, policy_version 144947 (0.0012) -[2023-11-28 04:00:21,871][87424] Updated weights for policy 0, policy_version 144957 (0.0012) -[2023-11-28 04:00:22,565][87426] Updated weights for policy 1, policy_version 144680 (0.0011) -[2023-11-28 04:00:22,936][87426] Updated weights for policy 1, policy_version 144690 (0.0012) -[2023-11-28 04:00:23,316][87426] Updated weights for policy 1, policy_version 144700 (0.0008) -[2023-11-28 04:00:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 74145792. Throughput: 0: 2657.8, 1: 2714.6. Samples: 74166420. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 04:00:23,445][86177] Avg episode reward: [(0, '-544.050'), (1, '-516.570')] -[2023-11-28 04:00:24,255][87424] Updated weights for policy 0, policy_version 144967 (0.0012) -[2023-11-28 04:00:24,635][87424] Updated weights for policy 0, policy_version 144977 (0.0012) -[2023-11-28 04:00:25,023][87424] Updated weights for policy 0, policy_version 144987 (0.0012) -[2023-11-28 04:00:25,423][87426] Updated weights for policy 1, policy_version 144710 (0.0010) -[2023-11-28 04:00:25,812][87426] Updated weights for policy 1, policy_version 144720 (0.0012) -[2023-11-28 04:00:26,190][87426] Updated weights for policy 1, policy_version 144730 (0.0009) -[2023-11-28 04:00:27,090][87424] Updated weights for policy 0, policy_version 144997 (0.0012) -[2023-11-28 04:00:27,467][87424] Updated weights for policy 0, policy_version 145007 (0.0012) -[2023-11-28 04:00:27,856][87424] Updated weights for policy 0, policy_version 145017 (0.0012) -[2023-11-28 04:00:28,189][87426] Updated weights for policy 1, policy_version 144740 (0.0010) -[2023-11-28 04:00:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 74178560. Throughput: 0: 2655.2, 1: 2739.7. Samples: 74192136. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 04:00:28,445][86177] Avg episode reward: [(0, '-552.740'), (1, '-511.840')] -[2023-11-28 04:00:28,562][87426] Updated weights for policy 1, policy_version 144750 (0.0008) -[2023-11-28 04:00:28,941][87426] Updated weights for policy 1, policy_version 144760 (0.0012) -[2023-11-28 04:00:30,244][87424] Updated weights for policy 0, policy_version 145027 (0.0011) -[2023-11-28 04:00:30,629][87424] Updated weights for policy 0, policy_version 145037 (0.0012) -[2023-11-28 04:00:30,740][87426] Updated weights for policy 1, policy_version 144770 (0.0011) -[2023-11-28 04:00:31,017][87424] Updated weights for policy 0, policy_version 145047 (0.0011) -[2023-11-28 04:00:31,112][87426] Updated weights for policy 1, policy_version 144780 (0.0008) -[2023-11-28 04:00:31,495][87426] Updated weights for policy 1, policy_version 144790 (0.0009) -[2023-11-28 04:00:31,872][87426] Updated weights for policy 1, policy_version 144800 (0.0010) -[2023-11-28 04:00:33,190][87424] Updated weights for policy 0, policy_version 145057 (0.0011) -[2023-11-28 04:00:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74203136. Throughput: 0: 2660.7, 1: 2747.8. Samples: 74216996. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 04:00:33,445][86177] Avg episode reward: [(0, '-565.380'), (1, '-511.020')] -[2023-11-28 04:00:33,571][87424] Updated weights for policy 0, policy_version 145067 (0.0011) -[2023-11-28 04:00:33,898][87426] Updated weights for policy 1, policy_version 144810 (0.0011) -[2023-11-28 04:00:33,952][87424] Updated weights for policy 0, policy_version 145077 (0.0008) -[2023-11-28 04:00:34,292][87426] Updated weights for policy 1, policy_version 144820 (0.0011) -[2023-11-28 04:00:34,339][87424] Updated weights for policy 0, policy_version 145087 (0.0010) -[2023-11-28 04:00:34,669][87426] Updated weights for policy 1, policy_version 144830 (0.0012) -[2023-11-28 04:00:36,593][87424] Updated weights for policy 0, policy_version 145097 (0.0010) -[2023-11-28 04:00:36,971][87424] Updated weights for policy 0, policy_version 145107 (0.0010) -[2023-11-28 04:00:37,102][87426] Updated weights for policy 1, policy_version 144840 (0.0011) -[2023-11-28 04:00:37,349][87424] Updated weights for policy 0, policy_version 145117 (0.0011) -[2023-11-28 04:00:37,483][87426] Updated weights for policy 1, policy_version 144850 (0.0009) -[2023-11-28 04:00:37,866][87426] Updated weights for policy 1, policy_version 144860 (0.0007) -[2023-11-28 04:00:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 74235904. Throughput: 0: 2659.3, 1: 2743.6. Samples: 74249332. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 04:00:38,445][86177] Avg episode reward: [(0, '-559.730'), (1, '-513.380')] -[2023-11-28 04:00:39,389][87424] Updated weights for policy 0, policy_version 145127 (0.0011) -[2023-11-28 04:00:39,771][87424] Updated weights for policy 0, policy_version 145137 (0.0010) -[2023-11-28 04:00:39,799][87426] Updated weights for policy 1, policy_version 144870 (0.0008) -[2023-11-28 04:00:40,153][87424] Updated weights for policy 0, policy_version 145147 (0.0010) -[2023-11-28 04:00:40,181][87426] Updated weights for policy 1, policy_version 144880 (0.0010) -[2023-11-28 04:00:40,559][87426] Updated weights for policy 1, policy_version 144890 (0.0010) -[2023-11-28 04:00:42,271][87424] Updated weights for policy 0, policy_version 145157 (0.0010) -[2023-11-28 04:00:42,519][87426] Updated weights for policy 1, policy_version 144900 (0.0012) -[2023-11-28 04:00:42,646][87424] Updated weights for policy 0, policy_version 145167 (0.0008) -[2023-11-28 04:00:42,890][87426] Updated weights for policy 1, policy_version 144910 (0.0012) -[2023-11-28 04:00:43,020][87424] Updated weights for policy 0, policy_version 145177 (0.0010) -[2023-11-28 04:00:43,269][87426] Updated weights for policy 1, policy_version 144920 (0.0012) -[2023-11-28 04:00:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 74260480. Throughput: 0: 2678.7, 1: 2742.8. Samples: 74274868. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:00:43,445][86177] Avg episode reward: [(0, '-541.470'), (1, '-514.450')] -[2023-11-28 04:00:44,954][87424] Updated weights for policy 0, policy_version 145187 (0.0009) -[2023-11-28 04:00:45,338][87424] Updated weights for policy 0, policy_version 145197 (0.0010) -[2023-11-28 04:00:45,720][87424] Updated weights for policy 0, policy_version 145207 (0.0008) -[2023-11-28 04:00:45,918][87426] Updated weights for policy 1, policy_version 144930 (0.0011) -[2023-11-28 04:00:46,305][87426] Updated weights for policy 1, policy_version 144940 (0.0008) -[2023-11-28 04:00:46,676][87426] Updated weights for policy 1, policy_version 144950 (0.0007) -[2023-11-28 04:00:47,058][87426] Updated weights for policy 1, policy_version 144960 (0.0007) -[2023-11-28 04:00:48,231][87424] Updated weights for policy 0, policy_version 145217 (0.0008) -[2023-11-28 04:00:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 74285056. Throughput: 0: 2680.4, 1: 2718.8. Samples: 74299008. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:00:48,445][86177] Avg episode reward: [(0, '-537.570'), (1, '-512.450')] -[2023-11-28 04:00:48,602][87424] Updated weights for policy 0, policy_version 145227 (0.0008) -[2023-11-28 04:00:48,982][87424] Updated weights for policy 0, policy_version 145237 (0.0009) -[2023-11-28 04:00:49,366][87424] Updated weights for policy 0, policy_version 145247 (0.0010) -[2023-11-28 04:00:49,632][87426] Updated weights for policy 1, policy_version 144970 (0.0011) -[2023-11-28 04:00:50,011][87426] Updated weights for policy 1, policy_version 144980 (0.0012) -[2023-11-28 04:00:50,382][87426] Updated weights for policy 1, policy_version 144990 (0.0012) -[2023-11-28 04:00:51,573][87424] Updated weights for policy 0, policy_version 145257 (0.0009) -[2023-11-28 04:00:51,956][87424] Updated weights for policy 0, policy_version 145267 (0.0012) -[2023-11-28 04:00:52,333][87424] Updated weights for policy 0, policy_version 145277 (0.0014) -[2023-11-28 04:00:52,818][87426] Updated weights for policy 1, policy_version 145000 (0.0010) -[2023-11-28 04:00:53,200][87426] Updated weights for policy 1, policy_version 145010 (0.0009) -[2023-11-28 04:00:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 74309632. Throughput: 0: 2705.2, 1: 2705.1. Samples: 74331152. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:00:53,445][86177] Avg episode reward: [(0, '-517.140'), (1, '-509.270')] -[2023-11-28 04:00:53,575][87426] Updated weights for policy 1, policy_version 145020 (0.0010) -[2023-11-28 04:00:54,814][87424] Updated weights for policy 0, policy_version 145287 (0.0009) -[2023-11-28 04:00:55,197][87424] Updated weights for policy 0, policy_version 145297 (0.0009) -[2023-11-28 04:00:55,518][87426] Updated weights for policy 1, policy_version 145030 (0.0011) -[2023-11-28 04:00:55,580][87424] Updated weights for policy 0, policy_version 145307 (0.0010) -[2023-11-28 04:00:55,905][87426] Updated weights for policy 1, policy_version 145040 (0.0007) -[2023-11-28 04:00:56,287][87426] Updated weights for policy 1, policy_version 145050 (0.0007) -[2023-11-28 04:00:57,132][87424] Updated weights for policy 0, policy_version 145317 (0.0012) -[2023-11-28 04:00:57,505][87424] Updated weights for policy 0, policy_version 145327 (0.0012) -[2023-11-28 04:00:57,885][87424] Updated weights for policy 0, policy_version 145337 (0.0012) -[2023-11-28 04:00:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74342400. Throughput: 0: 2715.3, 1: 2722.4. Samples: 74355992. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:00:58,445][86177] Avg episode reward: [(0, '-519.080'), (1, '-493.120')] -[2023-11-28 04:00:58,586][87426] Updated weights for policy 1, policy_version 145060 (0.0007) -[2023-11-28 04:00:58,955][87426] Updated weights for policy 1, policy_version 145070 (0.0008) -[2023-11-28 04:00:59,339][87426] Updated weights for policy 1, policy_version 145080 (0.0009) -[2023-11-28 04:00:59,870][87424] Updated weights for policy 0, policy_version 145347 (0.0011) -[2023-11-28 04:01:00,258][87424] Updated weights for policy 0, policy_version 145357 (0.0011) -[2023-11-28 04:01:00,639][87424] Updated weights for policy 0, policy_version 145367 (0.0009) -[2023-11-28 04:01:01,174][87426] Updated weights for policy 1, policy_version 145090 (0.0008) -[2023-11-28 04:01:01,547][87426] Updated weights for policy 1, policy_version 145100 (0.0008) -[2023-11-28 04:01:01,929][87426] Updated weights for policy 1, policy_version 145110 (0.0009) -[2023-11-28 04:01:02,311][87426] Updated weights for policy 1, policy_version 145120 (0.0008) -[2023-11-28 04:01:03,065][87424] Updated weights for policy 0, policy_version 145377 (0.0010) -[2023-11-28 04:01:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 74366976. Throughput: 0: 2719.8, 1: 2742.1. Samples: 74380936. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:03,445][86177] Avg episode reward: [(0, '-526.960'), (1, '-494.160')] -[2023-11-28 04:01:03,445][87424] Updated weights for policy 0, policy_version 145387 (0.0009) -[2023-11-28 04:01:03,839][87424] Updated weights for policy 0, policy_version 145397 (0.0011) -[2023-11-28 04:01:04,222][87424] Updated weights for policy 0, policy_version 145407 (0.0011) -[2023-11-28 04:01:04,703][87426] Updated weights for policy 1, policy_version 145130 (0.0009) -[2023-11-28 04:01:05,081][87426] Updated weights for policy 1, policy_version 145140 (0.0008) -[2023-11-28 04:01:05,464][87426] Updated weights for policy 1, policy_version 145150 (0.0007) -[2023-11-28 04:01:06,621][87424] Updated weights for policy 0, policy_version 145417 (0.0008) -[2023-11-28 04:01:07,004][87424] Updated weights for policy 0, policy_version 145427 (0.0011) -[2023-11-28 04:01:07,130][87426] Updated weights for policy 1, policy_version 145160 (0.0011) -[2023-11-28 04:01:07,392][87424] Updated weights for policy 0, policy_version 145437 (0.0011) -[2023-11-28 04:01:07,514][87426] Updated weights for policy 1, policy_version 145170 (0.0010) -[2023-11-28 04:01:07,894][87426] Updated weights for policy 1, policy_version 145180 (0.0009) -[2023-11-28 04:01:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74399744. Throughput: 0: 2709.0, 1: 2736.4. Samples: 74411460. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:08,445][86177] Avg episode reward: [(0, '-540.180'), (1, '-496.340')] -[2023-11-28 04:01:09,597][87424] Updated weights for policy 0, policy_version 145447 (0.0012) -[2023-11-28 04:01:09,985][87424] Updated weights for policy 0, policy_version 145457 (0.0011) -[2023-11-28 04:01:10,142][87426] Updated weights for policy 1, policy_version 145190 (0.0009) -[2023-11-28 04:01:10,371][87424] Updated weights for policy 0, policy_version 145467 (0.0010) -[2023-11-28 04:01:10,529][87426] Updated weights for policy 1, policy_version 145200 (0.0010) -[2023-11-28 04:01:10,898][87426] Updated weights for policy 1, policy_version 145210 (0.0012) -[2023-11-28 04:01:12,622][87424] Updated weights for policy 0, policy_version 145477 (0.0012) -[2023-11-28 04:01:13,010][87424] Updated weights for policy 0, policy_version 145487 (0.0015) -[2023-11-28 04:01:13,229][87426] Updated weights for policy 1, policy_version 145220 (0.0011) -[2023-11-28 04:01:13,396][87424] Updated weights for policy 0, policy_version 145497 (0.0011) -[2023-11-28 04:01:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 74416128. Throughput: 0: 2702.6, 1: 2703.1. Samples: 74435392. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:13,445][86177] Avg episode reward: [(0, '-533.950'), (1, '-500.040')] -[2023-11-28 04:01:13,606][87426] Updated weights for policy 1, policy_version 145230 (0.0010) -[2023-11-28 04:01:13,995][87426] Updated weights for policy 1, policy_version 145240 (0.0007) -[2023-11-28 04:01:15,445][87424] Updated weights for policy 0, policy_version 145507 (0.0012) -[2023-11-28 04:01:15,818][87424] Updated weights for policy 0, policy_version 145517 (0.0011) -[2023-11-28 04:01:16,210][87424] Updated weights for policy 0, policy_version 145527 (0.0008) -[2023-11-28 04:01:16,484][87426] Updated weights for policy 1, policy_version 145250 (0.0012) -[2023-11-28 04:01:16,860][87426] Updated weights for policy 1, policy_version 145260 (0.0012) -[2023-11-28 04:01:17,228][87426] Updated weights for policy 1, policy_version 145270 (0.0012) -[2023-11-28 04:01:17,607][87426] Updated weights for policy 1, policy_version 145280 (0.0010) -[2023-11-28 04:01:17,924][87424] Updated weights for policy 0, policy_version 145537 (0.0012) -[2023-11-28 04:01:18,309][87424] Updated weights for policy 0, policy_version 145547 (0.0012) -[2023-11-28 04:01:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 74448896. Throughput: 0: 2722.0, 1: 2689.6. Samples: 74460520. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:18,445][86177] Avg episode reward: [(0, '-547.400'), (1, '-503.910')] -[2023-11-28 04:01:18,681][87424] Updated weights for policy 0, policy_version 145557 (0.0012) -[2023-11-28 04:01:19,054][87424] Updated weights for policy 0, policy_version 145567 (0.0008) -[2023-11-28 04:01:20,019][87426] Updated weights for policy 1, policy_version 145290 (0.0011) -[2023-11-28 04:01:20,389][87426] Updated weights for policy 1, policy_version 145300 (0.0012) -[2023-11-28 04:01:20,758][87426] Updated weights for policy 1, policy_version 145310 (0.0008) -[2023-11-28 04:01:21,410][87424] Updated weights for policy 0, policy_version 145577 (0.0010) -[2023-11-28 04:01:21,803][87424] Updated weights for policy 0, policy_version 145587 (0.0011) -[2023-11-28 04:01:22,190][87424] Updated weights for policy 0, policy_version 145597 (0.0012) -[2023-11-28 04:01:23,132][87426] Updated weights for policy 1, policy_version 145320 (0.0010) -[2023-11-28 04:01:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 74473472. Throughput: 0: 2720.2, 1: 2690.6. Samples: 74492816. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:23,445][86177] Avg episode reward: [(0, '-558.710'), (1, '-512.470')] -[2023-11-28 04:01:23,519][87426] Updated weights for policy 1, policy_version 145330 (0.0010) -[2023-11-28 04:01:23,889][87426] Updated weights for policy 1, policy_version 145340 (0.0008) -[2023-11-28 04:01:24,264][87424] Updated weights for policy 0, policy_version 145607 (0.0010) -[2023-11-28 04:01:24,647][87424] Updated weights for policy 0, policy_version 145617 (0.0011) -[2023-11-28 04:01:25,029][87424] Updated weights for policy 0, policy_version 145627 (0.0010) -[2023-11-28 04:01:26,298][87426] Updated weights for policy 1, policy_version 145350 (0.0011) -[2023-11-28 04:01:26,682][87426] Updated weights for policy 1, policy_version 145360 (0.0008) -[2023-11-28 04:01:27,061][87426] Updated weights for policy 1, policy_version 145370 (0.0007) -[2023-11-28 04:01:27,095][87424] Updated weights for policy 0, policy_version 145637 (0.0011) -[2023-11-28 04:01:27,474][87424] Updated weights for policy 0, policy_version 145647 (0.0012) -[2023-11-28 04:01:27,866][87424] Updated weights for policy 0, policy_version 145657 (0.0012) -[2023-11-28 04:01:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 74506240. Throughput: 0: 2721.7, 1: 2701.4. Samples: 74518908. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:28,445][86177] Avg episode reward: [(0, '-560.670'), (1, '-523.920')] -[2023-11-28 04:01:28,756][87426] Updated weights for policy 1, policy_version 145380 (0.0010) -[2023-11-28 04:01:29,138][87426] Updated weights for policy 1, policy_version 145390 (0.0011) -[2023-11-28 04:01:29,517][87426] Updated weights for policy 1, policy_version 145400 (0.0012) -[2023-11-28 04:01:30,281][87424] Updated weights for policy 0, policy_version 145667 (0.0010) -[2023-11-28 04:01:30,670][87424] Updated weights for policy 0, policy_version 145677 (0.0012) -[2023-11-28 04:01:31,050][87424] Updated weights for policy 0, policy_version 145687 (0.0012) -[2023-11-28 04:01:31,284][87426] Updated weights for policy 1, policy_version 145410 (0.0011) -[2023-11-28 04:01:31,661][87426] Updated weights for policy 1, policy_version 145420 (0.0009) -[2023-11-28 04:01:32,046][87426] Updated weights for policy 1, policy_version 145430 (0.0011) -[2023-11-28 04:01:32,416][87426] Updated weights for policy 1, policy_version 145440 (0.0011) -[2023-11-28 04:01:33,009][87424] Updated weights for policy 0, policy_version 145697 (0.0011) -[2023-11-28 04:01:33,388][87424] Updated weights for policy 0, policy_version 145707 (0.0007) -[2023-11-28 04:01:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74530816. Throughput: 0: 2703.9, 1: 2716.6. Samples: 74542932. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:33,445][86177] Avg episode reward: [(0, '-556.560'), (1, '-521.940')] -[2023-11-28 04:01:33,773][87424] Updated weights for policy 0, policy_version 145717 (0.0008) -[2023-11-28 04:01:34,154][87424] Updated weights for policy 0, policy_version 145727 (0.0009) -[2023-11-28 04:01:34,269][87426] Updated weights for policy 1, policy_version 145450 (0.0011) -[2023-11-28 04:01:34,643][87426] Updated weights for policy 1, policy_version 145460 (0.0012) -[2023-11-28 04:01:35,024][87426] Updated weights for policy 1, policy_version 145470 (0.0012) -[2023-11-28 04:01:36,193][87424] Updated weights for policy 0, policy_version 145737 (0.0012) -[2023-11-28 04:01:36,580][87424] Updated weights for policy 0, policy_version 145747 (0.0012) -[2023-11-28 04:01:36,966][87424] Updated weights for policy 0, policy_version 145757 (0.0011) -[2023-11-28 04:01:37,018][87426] Updated weights for policy 1, policy_version 145480 (0.0011) -[2023-11-28 04:01:37,393][87426] Updated weights for policy 1, policy_version 145490 (0.0011) -[2023-11-28 04:01:37,763][87426] Updated weights for policy 1, policy_version 145500 (0.0010) -[2023-11-28 04:01:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74563584. Throughput: 0: 2706.0, 1: 2755.0. Samples: 74576900. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:38,445][86177] Avg episode reward: [(0, '-530.580'), (1, '-536.590')] -[2023-11-28 04:01:39,283][87424] Updated weights for policy 0, policy_version 145767 (0.0011) -[2023-11-28 04:01:39,666][87424] Updated weights for policy 0, policy_version 145777 (0.0007) -[2023-11-28 04:01:40,053][87424] Updated weights for policy 0, policy_version 145787 (0.0010) -[2023-11-28 04:01:40,333][87426] Updated weights for policy 1, policy_version 145510 (0.0008) -[2023-11-28 04:01:40,710][87426] Updated weights for policy 1, policy_version 145520 (0.0009) -[2023-11-28 04:01:41,090][87426] Updated weights for policy 1, policy_version 145530 (0.0008) -[2023-11-28 04:01:41,857][87424] Updated weights for policy 0, policy_version 145797 (0.0009) -[2023-11-28 04:01:42,250][87424] Updated weights for policy 0, policy_version 145807 (0.0011) -[2023-11-28 04:01:42,622][87424] Updated weights for policy 0, policy_version 145817 (0.0012) -[2023-11-28 04:01:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 74588160. Throughput: 0: 2721.7, 1: 2748.6. Samples: 74602156. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:43,445][86177] Avg episode reward: [(0, '-514.510'), (1, '-526.600')] -[2023-11-28 04:01:43,607][87426] Updated weights for policy 1, policy_version 145540 (0.0009) -[2023-11-28 04:01:43,986][87426] Updated weights for policy 1, policy_version 145550 (0.0011) -[2023-11-28 04:01:44,372][87426] Updated weights for policy 1, policy_version 145560 (0.0011) -[2023-11-28 04:01:45,235][87424] Updated weights for policy 0, policy_version 145827 (0.0011) -[2023-11-28 04:01:45,617][87424] Updated weights for policy 0, policy_version 145837 (0.0008) -[2023-11-28 04:01:45,994][87424] Updated weights for policy 0, policy_version 145847 (0.0010) -[2023-11-28 04:01:46,117][87426] Updated weights for policy 1, policy_version 145570 (0.0012) -[2023-11-28 04:01:46,495][87426] Updated weights for policy 1, policy_version 145580 (0.0010) -[2023-11-28 04:01:46,875][87426] Updated weights for policy 1, policy_version 145590 (0.0008) -[2023-11-28 04:01:47,248][87426] Updated weights for policy 1, policy_version 145600 (0.0007) -[2023-11-28 04:01:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74612736. Throughput: 0: 2700.9, 1: 2732.0. Samples: 74625416. Policy #0 lag: (min: 5.0, avg: 17.8, max: 37.0) -[2023-11-28 04:01:48,445][86177] Avg episode reward: [(0, '-519.060'), (1, '-518.900')] -[2023-11-28 04:01:48,536][87424] Updated weights for policy 0, policy_version 145857 (0.0010) -[2023-11-28 04:01:48,922][87424] Updated weights for policy 0, policy_version 145867 (0.0012) -[2023-11-28 04:01:49,307][87424] Updated weights for policy 0, policy_version 145877 (0.0012) -[2023-11-28 04:01:49,689][87424] Updated weights for policy 0, policy_version 145887 (0.0011) -[2023-11-28 04:01:49,709][87426] Updated weights for policy 1, policy_version 145610 (0.0011) -[2023-11-28 04:01:50,090][87426] Updated weights for policy 1, policy_version 145620 (0.0010) -[2023-11-28 04:01:50,475][87426] Updated weights for policy 1, policy_version 145630 (0.0013) -[2023-11-28 04:01:51,659][87424] Updated weights for policy 0, policy_version 145897 (0.0011) -[2023-11-28 04:01:52,039][87424] Updated weights for policy 0, policy_version 145907 (0.0011) -[2023-11-28 04:01:52,357][87426] Updated weights for policy 1, policy_version 145640 (0.0010) -[2023-11-28 04:01:52,418][87424] Updated weights for policy 0, policy_version 145917 (0.0011) -[2023-11-28 04:01:52,746][87426] Updated weights for policy 1, policy_version 145650 (0.0008) -[2023-11-28 04:01:53,118][87426] Updated weights for policy 1, policy_version 145660 (0.0008) -[2023-11-28 04:01:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 74645504. Throughput: 0: 2729.5, 1: 2738.4. Samples: 74657516. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:01:53,445][86177] Avg episode reward: [(0, '-519.200'), (1, '-519.250')] -[2023-11-28 04:01:54,818][87424] Updated weights for policy 0, policy_version 145927 (0.0012) -[2023-11-28 04:01:55,205][87424] Updated weights for policy 0, policy_version 145937 (0.0010) -[2023-11-28 04:01:55,241][87426] Updated weights for policy 1, policy_version 145670 (0.0009) -[2023-11-28 04:01:55,585][87424] Updated weights for policy 0, policy_version 145947 (0.0008) -[2023-11-28 04:01:55,627][87426] Updated weights for policy 1, policy_version 145680 (0.0008) -[2023-11-28 04:01:56,007][87426] Updated weights for policy 1, policy_version 145690 (0.0007) -[2023-11-28 04:01:57,895][87424] Updated weights for policy 0, policy_version 145957 (0.0008) -[2023-11-28 04:01:58,278][87424] Updated weights for policy 0, policy_version 145967 (0.0007) -[2023-11-28 04:01:58,355][87426] Updated weights for policy 1, policy_version 145700 (0.0007) -[2023-11-28 04:01:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 74661888. Throughput: 0: 2732.4, 1: 2761.2. Samples: 74682608. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:01:58,445][86177] Avg episode reward: [(0, '-529.340'), (1, '-519.470')] -[2023-11-28 04:01:58,660][87424] Updated weights for policy 0, policy_version 145977 (0.0008) -[2023-11-28 04:01:58,737][87426] Updated weights for policy 1, policy_version 145710 (0.0008) -[2023-11-28 04:01:59,120][87426] Updated weights for policy 1, policy_version 145720 (0.0008) -[2023-11-28 04:02:01,044][87424] Updated weights for policy 0, policy_version 145987 (0.0009) -[2023-11-28 04:02:01,086][87426] Updated weights for policy 1, policy_version 145730 (0.0008) -[2023-11-28 04:02:01,435][87424] Updated weights for policy 0, policy_version 145997 (0.0008) -[2023-11-28 04:02:01,466][87426] Updated weights for policy 1, policy_version 145740 (0.0008) -[2023-11-28 04:02:01,810][87424] Updated weights for policy 0, policy_version 146007 (0.0010) -[2023-11-28 04:02:01,840][87426] Updated weights for policy 1, policy_version 145750 (0.0010) -[2023-11-28 04:02:02,219][87426] Updated weights for policy 1, policy_version 145760 (0.0010) -[2023-11-28 04:02:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74694656. Throughput: 0: 2724.0, 1: 2764.4. Samples: 74707496. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:03,445][86177] Avg episode reward: [(0, '-540.610'), (1, '-526.640')] -[2023-11-28 04:02:03,649][87424] Updated weights for policy 0, policy_version 146017 (0.0011) -[2023-11-28 04:02:04,034][87424] Updated weights for policy 0, policy_version 146027 (0.0008) -[2023-11-28 04:02:04,384][87426] Updated weights for policy 1, policy_version 145770 (0.0016) -[2023-11-28 04:02:04,410][87424] Updated weights for policy 0, policy_version 146037 (0.0008) -[2023-11-28 04:02:04,757][87426] Updated weights for policy 1, policy_version 145780 (0.0009) -[2023-11-28 04:02:04,799][87424] Updated weights for policy 0, policy_version 146047 (0.0011) -[2023-11-28 04:02:05,133][87426] Updated weights for policy 1, policy_version 145790 (0.0010) -[2023-11-28 04:02:07,088][87424] Updated weights for policy 0, policy_version 146057 (0.0010) -[2023-11-28 04:02:07,241][87426] Updated weights for policy 1, policy_version 145800 (0.0010) -[2023-11-28 04:02:07,472][87424] Updated weights for policy 0, policy_version 146067 (0.0010) -[2023-11-28 04:02:07,622][87426] Updated weights for policy 1, policy_version 145810 (0.0007) -[2023-11-28 04:02:07,856][87424] Updated weights for policy 0, policy_version 146077 (0.0009) -[2023-11-28 04:02:08,006][87426] Updated weights for policy 1, policy_version 145820 (0.0007) -[2023-11-28 04:02:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 74727424. Throughput: 0: 2722.1, 1: 2782.6. Samples: 74740528. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:08,445][86177] Avg episode reward: [(0, '-525.040'), (1, '-523.270')] -[2023-11-28 04:02:09,879][87424] Updated weights for policy 0, policy_version 146087 (0.0009) -[2023-11-28 04:02:10,260][87424] Updated weights for policy 0, policy_version 146097 (0.0010) -[2023-11-28 04:02:10,424][87426] Updated weights for policy 1, policy_version 145830 (0.0009) -[2023-11-28 04:02:10,641][87424] Updated weights for policy 0, policy_version 146107 (0.0010) -[2023-11-28 04:02:10,815][87426] Updated weights for policy 1, policy_version 145840 (0.0008) -[2023-11-28 04:02:11,181][87426] Updated weights for policy 1, policy_version 145850 (0.0007) -[2023-11-28 04:02:13,088][87424] Updated weights for policy 0, policy_version 146117 (0.0010) -[2023-11-28 04:02:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74743808. Throughput: 0: 2711.6, 1: 2741.0. Samples: 74764272. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:13,445][86177] Avg episode reward: [(0, '-533.360'), (1, '-530.280')] -[2023-11-28 04:02:13,470][87424] Updated weights for policy 0, policy_version 146127 (0.0012) -[2023-11-28 04:02:13,478][87426] Updated weights for policy 1, policy_version 145860 (0.0010) -[2023-11-28 04:02:13,853][87424] Updated weights for policy 0, policy_version 146137 (0.0011) -[2023-11-28 04:02:13,857][87426] Updated weights for policy 1, policy_version 145870 (0.0011) -[2023-11-28 04:02:14,248][87426] Updated weights for policy 1, policy_version 145880 (0.0011) -[2023-11-28 04:02:15,550][87424] Updated weights for policy 0, policy_version 146147 (0.0011) -[2023-11-28 04:02:15,936][87424] Updated weights for policy 0, policy_version 146157 (0.0011) -[2023-11-28 04:02:16,329][87424] Updated weights for policy 0, policy_version 146167 (0.0009) -[2023-11-28 04:02:16,734][87426] Updated weights for policy 1, policy_version 145890 (0.0007) -[2023-11-28 04:02:17,111][87426] Updated weights for policy 1, policy_version 145900 (0.0009) -[2023-11-28 04:02:17,491][87426] Updated weights for policy 1, policy_version 145910 (0.0008) -[2023-11-28 04:02:17,874][87426] Updated weights for policy 1, policy_version 145920 (0.0008) -[2023-11-28 04:02:17,950][87424] Updated weights for policy 0, policy_version 146177 (0.0008) -[2023-11-28 04:02:18,356][87424] Updated weights for policy 0, policy_version 146187 (0.0012) -[2023-11-28 04:02:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 74776576. Throughput: 0: 2743.4, 1: 2723.5. Samples: 74788944. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:18,445][86177] Avg episode reward: [(0, '-527.100'), (1, '-529.890')] -[2023-11-28 04:02:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000145920_37355520.pth... -[2023-11-28 04:02:18,499][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000143392_36708352.pth -[2023-11-28 04:02:18,726][87424] Updated weights for policy 0, policy_version 146197 (0.0011) -[2023-11-28 04:02:19,117][87424] Updated weights for policy 0, policy_version 146207 (0.0012) -[2023-11-28 04:02:19,153][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000146208_37429248.pth... -[2023-11-28 04:02:19,200][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000143648_36773888.pth -[2023-11-28 04:02:20,416][87426] Updated weights for policy 1, policy_version 145930 (0.0011) -[2023-11-28 04:02:20,794][87426] Updated weights for policy 1, policy_version 145940 (0.0011) -[2023-11-28 04:02:21,003][87424] Updated weights for policy 0, policy_version 146217 (0.0011) -[2023-11-28 04:02:21,160][87426] Updated weights for policy 1, policy_version 145950 (0.0010) -[2023-11-28 04:02:21,378][87424] Updated weights for policy 0, policy_version 146227 (0.0012) -[2023-11-28 04:02:21,767][87424] Updated weights for policy 0, policy_version 146237 (0.0011) -[2023-11-28 04:02:23,409][87426] Updated weights for policy 1, policy_version 145960 (0.0011) -[2023-11-28 04:02:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 74801152. Throughput: 0: 2709.5, 1: 2693.9. Samples: 74820052. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:23,445][86177] Avg episode reward: [(0, '-517.690'), (1, '-541.680')] -[2023-11-28 04:02:23,793][87426] Updated weights for policy 1, policy_version 145970 (0.0011) -[2023-11-28 04:02:24,168][87426] Updated weights for policy 1, policy_version 145980 (0.0010) -[2023-11-28 04:02:24,274][87424] Updated weights for policy 0, policy_version 146247 (0.0012) -[2023-11-28 04:02:24,651][87424] Updated weights for policy 0, policy_version 146257 (0.0012) -[2023-11-28 04:02:25,028][87424] Updated weights for policy 0, policy_version 146267 (0.0012) -[2023-11-28 04:02:25,937][87426] Updated weights for policy 1, policy_version 145990 (0.0011) -[2023-11-28 04:02:26,312][87426] Updated weights for policy 1, policy_version 146000 (0.0012) -[2023-11-28 04:02:26,694][87426] Updated weights for policy 1, policy_version 146010 (0.0012) -[2023-11-28 04:02:27,584][87424] Updated weights for policy 0, policy_version 146277 (0.0012) -[2023-11-28 04:02:27,953][87424] Updated weights for policy 0, policy_version 146287 (0.0012) -[2023-11-28 04:02:28,336][87424] Updated weights for policy 0, policy_version 146297 (0.0012) -[2023-11-28 04:02:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 74825728. Throughput: 0: 2694.4, 1: 2712.7. Samples: 74845476. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:28,445][86177] Avg episode reward: [(0, '-514.160'), (1, '-571.240')] -[2023-11-28 04:02:28,575][87426] Updated weights for policy 1, policy_version 146020 (0.0012) -[2023-11-28 04:02:28,948][87426] Updated weights for policy 1, policy_version 146030 (0.0011) -[2023-11-28 04:02:29,326][87426] Updated weights for policy 1, policy_version 146040 (0.0008) -[2023-11-28 04:02:30,344][87424] Updated weights for policy 0, policy_version 146307 (0.0012) -[2023-11-28 04:02:30,728][87424] Updated weights for policy 0, policy_version 146317 (0.0012) -[2023-11-28 04:02:31,114][87424] Updated weights for policy 0, policy_version 146327 (0.0012) -[2023-11-28 04:02:31,545][87426] Updated weights for policy 1, policy_version 146050 (0.0009) -[2023-11-28 04:02:31,930][87426] Updated weights for policy 1, policy_version 146060 (0.0009) -[2023-11-28 04:02:32,308][87426] Updated weights for policy 1, policy_version 146070 (0.0009) -[2023-11-28 04:02:32,676][87426] Updated weights for policy 1, policy_version 146080 (0.0009) -[2023-11-28 04:02:33,238][87424] Updated weights for policy 0, policy_version 146337 (0.0012) -[2023-11-28 04:02:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 74858496. Throughput: 0: 2748.0, 1: 2713.0. Samples: 74871160. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:33,445][86177] Avg episode reward: [(0, '-503.080'), (1, '-564.390')] -[2023-11-28 04:02:33,626][87424] Updated weights for policy 0, policy_version 146347 (0.0012) -[2023-11-28 04:02:34,012][87424] Updated weights for policy 0, policy_version 146357 (0.0012) -[2023-11-28 04:02:34,395][87424] Updated weights for policy 0, policy_version 146367 (0.0011) -[2023-11-28 04:02:34,548][87426] Updated weights for policy 1, policy_version 146090 (0.0011) -[2023-11-28 04:02:34,929][87426] Updated weights for policy 1, policy_version 146100 (0.0012) -[2023-11-28 04:02:35,308][87426] Updated weights for policy 1, policy_version 146110 (0.0012) -[2023-11-28 04:02:36,461][87424] Updated weights for policy 0, policy_version 146377 (0.0012) -[2023-11-28 04:02:36,833][87424] Updated weights for policy 0, policy_version 146387 (0.0012) -[2023-11-28 04:02:37,213][87424] Updated weights for policy 0, policy_version 146397 (0.0012) -[2023-11-28 04:02:37,346][87426] Updated weights for policy 1, policy_version 146120 (0.0012) -[2023-11-28 04:02:37,720][87426] Updated weights for policy 1, policy_version 146130 (0.0012) -[2023-11-28 04:02:38,103][87426] Updated weights for policy 1, policy_version 146140 (0.0012) -[2023-11-28 04:02:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 74891264. Throughput: 0: 2749.5, 1: 2716.3. Samples: 74903476. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:38,445][86177] Avg episode reward: [(0, '-509.720'), (1, '-531.710')] -[2023-11-28 04:02:39,316][87424] Updated weights for policy 0, policy_version 146407 (0.0012) -[2023-11-28 04:02:39,702][87424] Updated weights for policy 0, policy_version 146417 (0.0011) -[2023-11-28 04:02:39,994][87426] Updated weights for policy 1, policy_version 146150 (0.0011) -[2023-11-28 04:02:40,084][87424] Updated weights for policy 0, policy_version 146427 (0.0011) -[2023-11-28 04:02:40,389][87426] Updated weights for policy 1, policy_version 146160 (0.0010) -[2023-11-28 04:02:40,764][87426] Updated weights for policy 1, policy_version 146170 (0.0008) -[2023-11-28 04:02:42,562][87424] Updated weights for policy 0, policy_version 146437 (0.0010) -[2023-11-28 04:02:42,944][87424] Updated weights for policy 0, policy_version 146447 (0.0012) -[2023-11-28 04:02:43,098][87426] Updated weights for policy 1, policy_version 146180 (0.0008) -[2023-11-28 04:02:43,322][87424] Updated weights for policy 0, policy_version 146457 (0.0012) -[2023-11-28 04:02:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 74907648. Throughput: 0: 2750.4, 1: 2706.5. Samples: 74928168. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:43,445][86177] Avg episode reward: [(0, '-504.130'), (1, '-532.000')] -[2023-11-28 04:02:43,485][87426] Updated weights for policy 1, policy_version 146190 (0.0008) -[2023-11-28 04:02:43,853][87426] Updated weights for policy 1, policy_version 146200 (0.0011) -[2023-11-28 04:02:45,118][87424] Updated weights for policy 0, policy_version 146467 (0.0011) -[2023-11-28 04:02:45,500][87424] Updated weights for policy 0, policy_version 146477 (0.0011) -[2023-11-28 04:02:45,883][87424] Updated weights for policy 0, policy_version 146487 (0.0011) -[2023-11-28 04:02:46,033][87426] Updated weights for policy 1, policy_version 146210 (0.0010) -[2023-11-28 04:02:46,408][87426] Updated weights for policy 1, policy_version 146220 (0.0011) -[2023-11-28 04:02:46,793][87426] Updated weights for policy 1, policy_version 146230 (0.0012) -[2023-11-28 04:02:47,175][87426] Updated weights for policy 1, policy_version 146240 (0.0011) -[2023-11-28 04:02:47,725][87424] Updated weights for policy 0, policy_version 146497 (0.0010) -[2023-11-28 04:02:48,106][87424] Updated weights for policy 0, policy_version 146507 (0.0012) -[2023-11-28 04:02:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 74940416. Throughput: 0: 2734.8, 1: 2696.4. Samples: 74951904. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:48,445][86177] Avg episode reward: [(0, '-507.630'), (1, '-505.450')] -[2023-11-28 04:02:48,499][87424] Updated weights for policy 0, policy_version 146517 (0.0012) -[2023-11-28 04:02:48,873][87424] Updated weights for policy 0, policy_version 146527 (0.0011) -[2023-11-28 04:02:49,256][87426] Updated weights for policy 1, policy_version 146250 (0.0011) -[2023-11-28 04:02:49,635][87426] Updated weights for policy 1, policy_version 146260 (0.0011) -[2023-11-28 04:02:50,014][87426] Updated weights for policy 1, policy_version 146270 (0.0011) -[2023-11-28 04:02:51,126][87424] Updated weights for policy 0, policy_version 146537 (0.0008) -[2023-11-28 04:02:51,511][87424] Updated weights for policy 0, policy_version 146547 (0.0009) -[2023-11-28 04:02:51,902][87424] Updated weights for policy 0, policy_version 146557 (0.0011) -[2023-11-28 04:02:51,943][87426] Updated weights for policy 1, policy_version 146280 (0.0011) -[2023-11-28 04:02:52,323][87426] Updated weights for policy 1, policy_version 146290 (0.0012) -[2023-11-28 04:02:52,707][87426] Updated weights for policy 1, policy_version 146300 (0.0012) -[2023-11-28 04:02:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 74973184. Throughput: 0: 2733.5, 1: 2709.9. Samples: 74985480. Policy #0 lag: (min: 6.0, avg: 16.5, max: 38.0) -[2023-11-28 04:02:53,445][86177] Avg episode reward: [(0, '-515.440'), (1, '-509.670')] -[2023-11-28 04:02:54,393][87424] Updated weights for policy 0, policy_version 146567 (0.0011) -[2023-11-28 04:02:54,768][87424] Updated weights for policy 0, policy_version 146577 (0.0012) -[2023-11-28 04:02:55,150][87424] Updated weights for policy 0, policy_version 146587 (0.0010) -[2023-11-28 04:02:55,234][87426] Updated weights for policy 1, policy_version 146310 (0.0011) -[2023-11-28 04:02:55,616][87426] Updated weights for policy 1, policy_version 146320 (0.0009) -[2023-11-28 04:02:56,002][87426] Updated weights for policy 1, policy_version 146330 (0.0010) -[2023-11-28 04:02:56,918][87424] Updated weights for policy 0, policy_version 146597 (0.0011) -[2023-11-28 04:02:57,300][87424] Updated weights for policy 0, policy_version 146607 (0.0012) -[2023-11-28 04:02:57,694][87424] Updated weights for policy 0, policy_version 146617 (0.0011) -[2023-11-28 04:02:58,102][87426] Updated weights for policy 1, policy_version 146340 (0.0011) -[2023-11-28 04:02:58,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 74997760. Throughput: 0: 2744.8, 1: 2710.5. Samples: 75009760. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:02:58,446][86177] Avg episode reward: [(0, '-542.450'), (1, '-519.750')] -[2023-11-28 04:02:58,475][87426] Updated weights for policy 1, policy_version 146350 (0.0012) -[2023-11-28 04:02:58,866][87426] Updated weights for policy 1, policy_version 146360 (0.0012) -[2023-11-28 04:02:59,984][87424] Updated weights for policy 0, policy_version 146627 (0.0009) -[2023-11-28 04:03:00,367][87424] Updated weights for policy 0, policy_version 146637 (0.0010) -[2023-11-28 04:03:00,748][87424] Updated weights for policy 0, policy_version 146647 (0.0009) -[2023-11-28 04:03:01,421][87426] Updated weights for policy 1, policy_version 146370 (0.0011) -[2023-11-28 04:03:01,806][87426] Updated weights for policy 1, policy_version 146380 (0.0009) -[2023-11-28 04:03:02,185][87426] Updated weights for policy 1, policy_version 146390 (0.0010) -[2023-11-28 04:03:02,550][87424] Updated weights for policy 0, policy_version 146657 (0.0008) -[2023-11-28 04:03:02,565][87426] Updated weights for policy 1, policy_version 146400 (0.0008) -[2023-11-28 04:03:02,928][87424] Updated weights for policy 0, policy_version 146667 (0.0012) -[2023-11-28 04:03:03,311][87424] Updated weights for policy 0, policy_version 146677 (0.0012) -[2023-11-28 04:03:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75022336. Throughput: 0: 2752.0, 1: 2723.9. Samples: 75035360. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:03,445][86177] Avg episode reward: [(0, '-555.730'), (1, '-513.700')] -[2023-11-28 04:03:03,692][87424] Updated weights for policy 0, policy_version 146687 (0.0012) -[2023-11-28 04:03:04,896][87426] Updated weights for policy 1, policy_version 146410 (0.0012) -[2023-11-28 04:03:05,277][87426] Updated weights for policy 1, policy_version 146420 (0.0012) -[2023-11-28 04:03:05,656][87426] Updated weights for policy 1, policy_version 146430 (0.0012) -[2023-11-28 04:03:06,085][87424] Updated weights for policy 0, policy_version 146697 (0.0009) -[2023-11-28 04:03:06,463][87424] Updated weights for policy 0, policy_version 146707 (0.0008) -[2023-11-28 04:03:06,853][87424] Updated weights for policy 0, policy_version 146717 (0.0010) -[2023-11-28 04:03:07,600][87426] Updated weights for policy 1, policy_version 146440 (0.0012) -[2023-11-28 04:03:07,988][87426] Updated weights for policy 1, policy_version 146450 (0.0012) -[2023-11-28 04:03:08,365][87426] Updated weights for policy 1, policy_version 146460 (0.0012) -[2023-11-28 04:03:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 75046912. Throughput: 0: 2768.5, 1: 2744.8. Samples: 75068152. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:08,446][86177] Avg episode reward: [(0, '-554.490'), (1, '-525.700')] -[2023-11-28 04:03:09,113][87424] Updated weights for policy 0, policy_version 146727 (0.0011) -[2023-11-28 04:03:09,483][87424] Updated weights for policy 0, policy_version 146737 (0.0011) -[2023-11-28 04:03:09,861][87424] Updated weights for policy 0, policy_version 146747 (0.0010) -[2023-11-28 04:03:10,264][87426] Updated weights for policy 1, policy_version 146470 (0.0012) -[2023-11-28 04:03:10,640][87426] Updated weights for policy 1, policy_version 146480 (0.0012) -[2023-11-28 04:03:11,012][87426] Updated weights for policy 1, policy_version 146490 (0.0012) -[2023-11-28 04:03:12,083][87424] Updated weights for policy 0, policy_version 146757 (0.0011) -[2023-11-28 04:03:12,464][87424] Updated weights for policy 0, policy_version 146767 (0.0012) -[2023-11-28 04:03:12,855][87424] Updated weights for policy 0, policy_version 146777 (0.0012) -[2023-11-28 04:03:13,319][87426] Updated weights for policy 1, policy_version 146500 (0.0011) -[2023-11-28 04:03:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 75079680. Throughput: 0: 2773.2, 1: 2729.2. Samples: 75093084. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:13,445][86177] Avg episode reward: [(0, '-544.810'), (1, '-533.920')] -[2023-11-28 04:03:13,699][87426] Updated weights for policy 1, policy_version 146510 (0.0008) -[2023-11-28 04:03:14,082][87426] Updated weights for policy 1, policy_version 146520 (0.0010) -[2023-11-28 04:03:15,228][87424] Updated weights for policy 0, policy_version 146787 (0.0012) -[2023-11-28 04:03:15,612][87424] Updated weights for policy 0, policy_version 146797 (0.0011) -[2023-11-28 04:03:16,003][87424] Updated weights for policy 0, policy_version 146807 (0.0011) -[2023-11-28 04:03:16,213][87426] Updated weights for policy 1, policy_version 146530 (0.0011) -[2023-11-28 04:03:16,596][87426] Updated weights for policy 1, policy_version 146540 (0.0011) -[2023-11-28 04:03:16,971][87426] Updated weights for policy 1, policy_version 146550 (0.0011) -[2023-11-28 04:03:17,352][87426] Updated weights for policy 1, policy_version 146560 (0.0011) -[2023-11-28 04:03:17,975][87424] Updated weights for policy 0, policy_version 146817 (0.0012) -[2023-11-28 04:03:18,360][87424] Updated weights for policy 0, policy_version 146827 (0.0012) -[2023-11-28 04:03:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75104256. Throughput: 0: 2723.3, 1: 2739.2. Samples: 75116972. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:18,446][86177] Avg episode reward: [(0, '-505.760'), (1, '-525.470')] -[2023-11-28 04:03:18,755][87424] Updated weights for policy 0, policy_version 146837 (0.0012) -[2023-11-28 04:03:19,125][87424] Updated weights for policy 0, policy_version 146847 (0.0012) -[2023-11-28 04:03:19,592][87426] Updated weights for policy 1, policy_version 146570 (0.0012) -[2023-11-28 04:03:19,973][87426] Updated weights for policy 1, policy_version 146580 (0.0011) -[2023-11-28 04:03:20,353][87426] Updated weights for policy 1, policy_version 146590 (0.0009) -[2023-11-28 04:03:21,608][87424] Updated weights for policy 0, policy_version 146857 (0.0012) -[2023-11-28 04:03:21,992][87424] Updated weights for policy 0, policy_version 146867 (0.0012) -[2023-11-28 04:03:22,370][87424] Updated weights for policy 0, policy_version 146877 (0.0012) -[2023-11-28 04:03:22,443][87426] Updated weights for policy 1, policy_version 146600 (0.0012) -[2023-11-28 04:03:22,819][87426] Updated weights for policy 1, policy_version 146610 (0.0011) -[2023-11-28 04:03:23,203][87426] Updated weights for policy 1, policy_version 146620 (0.0011) -[2023-11-28 04:03:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 75137024. Throughput: 0: 2714.8, 1: 2740.8. Samples: 75148980. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:23,445][86177] Avg episode reward: [(0, '-506.500'), (1, '-520.250')] -[2023-11-28 04:03:24,960][87424] Updated weights for policy 0, policy_version 146887 (0.0011) -[2023-11-28 04:03:24,971][87426] Updated weights for policy 1, policy_version 146630 (0.0011) -[2023-11-28 04:03:25,341][87424] Updated weights for policy 0, policy_version 146897 (0.0011) -[2023-11-28 04:03:25,362][87426] Updated weights for policy 1, policy_version 146640 (0.0011) -[2023-11-28 04:03:25,729][87424] Updated weights for policy 0, policy_version 146907 (0.0011) -[2023-11-28 04:03:25,733][87426] Updated weights for policy 1, policy_version 146650 (0.0012) -[2023-11-28 04:03:27,494][87426] Updated weights for policy 1, policy_version 146660 (0.0011) -[2023-11-28 04:03:27,871][87426] Updated weights for policy 1, policy_version 146670 (0.0012) -[2023-11-28 04:03:28,092][87424] Updated weights for policy 0, policy_version 146917 (0.0009) -[2023-11-28 04:03:28,265][87426] Updated weights for policy 1, policy_version 146680 (0.0011) -[2023-11-28 04:03:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 75153408. Throughput: 0: 2715.5, 1: 2785.6. Samples: 75175716. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:28,445][86177] Avg episode reward: [(0, '-500.380'), (1, '-524.350')] -[2023-11-28 04:03:28,472][87424] Updated weights for policy 0, policy_version 146927 (0.0008) -[2023-11-28 04:03:28,851][87424] Updated weights for policy 0, policy_version 146937 (0.0008) -[2023-11-28 04:03:30,392][87426] Updated weights for policy 1, policy_version 146690 (0.0012) -[2023-11-28 04:03:30,771][87426] Updated weights for policy 1, policy_version 146700 (0.0012) -[2023-11-28 04:03:30,811][87424] Updated weights for policy 0, policy_version 146947 (0.0008) -[2023-11-28 04:03:31,147][87426] Updated weights for policy 1, policy_version 146710 (0.0011) -[2023-11-28 04:03:31,196][87424] Updated weights for policy 0, policy_version 146957 (0.0007) -[2023-11-28 04:03:31,527][87426] Updated weights for policy 1, policy_version 146720 (0.0011) -[2023-11-28 04:03:31,586][87424] Updated weights for policy 0, policy_version 146967 (0.0007) -[2023-11-28 04:03:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 75186176. Throughput: 0: 2724.7, 1: 2802.8. Samples: 75200644. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:33,445][86177] Avg episode reward: [(0, '-500.680'), (1, '-512.250')] -[2023-11-28 04:03:33,484][87426] Updated weights for policy 1, policy_version 146730 (0.0011) -[2023-11-28 04:03:33,569][87424] Updated weights for policy 0, policy_version 146977 (0.0011) -[2023-11-28 04:03:33,869][87426] Updated weights for policy 1, policy_version 146740 (0.0009) -[2023-11-28 04:03:33,951][87424] Updated weights for policy 0, policy_version 146987 (0.0010) -[2023-11-28 04:03:34,238][87426] Updated weights for policy 1, policy_version 146750 (0.0008) -[2023-11-28 04:03:34,330][87424] Updated weights for policy 0, policy_version 146997 (0.0012) -[2023-11-28 04:03:34,718][87424] Updated weights for policy 0, policy_version 147007 (0.0012) -[2023-11-28 04:03:36,327][87426] Updated weights for policy 1, policy_version 146760 (0.0010) -[2023-11-28 04:03:36,700][87426] Updated weights for policy 1, policy_version 146770 (0.0008) -[2023-11-28 04:03:37,082][87426] Updated weights for policy 1, policy_version 146780 (0.0008) -[2023-11-28 04:03:37,213][87424] Updated weights for policy 0, policy_version 147017 (0.0012) -[2023-11-28 04:03:37,598][87424] Updated weights for policy 0, policy_version 147027 (0.0012) -[2023-11-28 04:03:37,978][87424] Updated weights for policy 0, policy_version 147037 (0.0012) -[2023-11-28 04:03:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 75218944. Throughput: 0: 2711.6, 1: 2789.8. Samples: 75233044. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:38,445][86177] Avg episode reward: [(0, '-516.510'), (1, '-516.360')] -[2023-11-28 04:03:39,179][87426] Updated weights for policy 1, policy_version 146790 (0.0010) -[2023-11-28 04:03:39,561][87426] Updated weights for policy 1, policy_version 146800 (0.0011) -[2023-11-28 04:03:39,942][87426] Updated weights for policy 1, policy_version 146810 (0.0010) -[2023-11-28 04:03:40,372][87424] Updated weights for policy 0, policy_version 147047 (0.0010) -[2023-11-28 04:03:40,756][87424] Updated weights for policy 0, policy_version 147057 (0.0012) -[2023-11-28 04:03:41,139][87424] Updated weights for policy 0, policy_version 147067 (0.0009) -[2023-11-28 04:03:42,351][87426] Updated weights for policy 1, policy_version 146820 (0.0011) -[2023-11-28 04:03:42,717][87426] Updated weights for policy 1, policy_version 146830 (0.0011) -[2023-11-28 04:03:43,100][87426] Updated weights for policy 1, policy_version 146840 (0.0012) -[2023-11-28 04:03:43,391][87424] Updated weights for policy 0, policy_version 147077 (0.0008) -[2023-11-28 04:03:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 75243520. Throughput: 0: 2706.2, 1: 2795.0. Samples: 75257316. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:43,445][86177] Avg episode reward: [(0, '-519.660'), (1, '-511.380')] -[2023-11-28 04:03:43,779][87424] Updated weights for policy 0, policy_version 147087 (0.0009) -[2023-11-28 04:03:44,158][87424] Updated weights for policy 0, policy_version 147097 (0.0012) -[2023-11-28 04:03:44,874][87426] Updated weights for policy 1, policy_version 146850 (0.0011) -[2023-11-28 04:03:45,267][87426] Updated weights for policy 1, policy_version 146860 (0.0012) -[2023-11-28 04:03:45,644][87426] Updated weights for policy 1, policy_version 146870 (0.0012) -[2023-11-28 04:03:45,875][87424] Updated weights for policy 0, policy_version 147107 (0.0011) -[2023-11-28 04:03:46,023][87426] Updated weights for policy 1, policy_version 146880 (0.0010) -[2023-11-28 04:03:46,262][87424] Updated weights for policy 0, policy_version 147117 (0.0008) -[2023-11-28 04:03:46,646][87424] Updated weights for policy 0, policy_version 147127 (0.0007) -[2023-11-28 04:03:48,240][87426] Updated weights for policy 1, policy_version 146890 (0.0009) -[2023-11-28 04:03:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75268096. Throughput: 0: 2687.0, 1: 2807.3. Samples: 75282604. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:48,445][86177] Avg episode reward: [(0, '-526.190'), (1, '-500.440')] -[2023-11-28 04:03:48,619][87426] Updated weights for policy 1, policy_version 146900 (0.0009) -[2023-11-28 04:03:48,808][87424] Updated weights for policy 0, policy_version 147137 (0.0008) -[2023-11-28 04:03:49,003][87426] Updated weights for policy 1, policy_version 146910 (0.0009) -[2023-11-28 04:03:49,196][87424] Updated weights for policy 0, policy_version 147147 (0.0011) -[2023-11-28 04:03:49,572][87424] Updated weights for policy 0, policy_version 147157 (0.0012) -[2023-11-28 04:03:49,952][87424] Updated weights for policy 0, policy_version 147167 (0.0012) -[2023-11-28 04:03:51,218][87426] Updated weights for policy 1, policy_version 146920 (0.0011) -[2023-11-28 04:03:51,596][87426] Updated weights for policy 1, policy_version 146930 (0.0011) -[2023-11-28 04:03:51,974][87426] Updated weights for policy 1, policy_version 146940 (0.0010) -[2023-11-28 04:03:52,468][87424] Updated weights for policy 0, policy_version 147177 (0.0012) -[2023-11-28 04:03:52,850][87424] Updated weights for policy 0, policy_version 147187 (0.0012) -[2023-11-28 04:03:53,228][87424] Updated weights for policy 0, policy_version 147197 (0.0012) -[2023-11-28 04:03:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75300864. Throughput: 0: 2675.9, 1: 2794.7. Samples: 75314328. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:53,445][86177] Avg episode reward: [(0, '-528.470'), (1, '-500.970')] -[2023-11-28 04:03:54,086][87426] Updated weights for policy 1, policy_version 146950 (0.0010) -[2023-11-28 04:03:54,457][87426] Updated weights for policy 1, policy_version 146960 (0.0011) -[2023-11-28 04:03:54,834][87426] Updated weights for policy 1, policy_version 146970 (0.0012) -[2023-11-28 04:03:55,752][87424] Updated weights for policy 0, policy_version 147207 (0.0012) -[2023-11-28 04:03:56,135][87424] Updated weights for policy 0, policy_version 147217 (0.0012) -[2023-11-28 04:03:56,515][87424] Updated weights for policy 0, policy_version 147227 (0.0012) -[2023-11-28 04:03:57,338][87426] Updated weights for policy 1, policy_version 146980 (0.0008) -[2023-11-28 04:03:57,715][87426] Updated weights for policy 1, policy_version 146990 (0.0007) -[2023-11-28 04:03:58,082][87424] Updated weights for policy 0, policy_version 147237 (0.0012) -[2023-11-28 04:03:58,093][87426] Updated weights for policy 1, policy_version 147000 (0.0007) -[2023-11-28 04:03:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75325440. Throughput: 0: 2676.8, 1: 2770.4. Samples: 75338208. Policy #0 lag: (min: 11.0, avg: 28.8, max: 43.0) -[2023-11-28 04:03:58,445][86177] Avg episode reward: [(0, '-516.580'), (1, '-514.930')] -[2023-11-28 04:03:58,465][87424] Updated weights for policy 0, policy_version 147247 (0.0011) -[2023-11-28 04:03:58,852][87424] Updated weights for policy 0, policy_version 147257 (0.0011) -[2023-11-28 04:04:00,097][87426] Updated weights for policy 1, policy_version 147010 (0.0008) -[2023-11-28 04:04:00,475][87426] Updated weights for policy 1, policy_version 147020 (0.0011) -[2023-11-28 04:04:00,810][87424] Updated weights for policy 0, policy_version 147267 (0.0010) -[2023-11-28 04:04:00,854][87426] Updated weights for policy 1, policy_version 147030 (0.0011) -[2023-11-28 04:04:01,191][87424] Updated weights for policy 0, policy_version 147277 (0.0011) -[2023-11-28 04:04:01,232][87426] Updated weights for policy 1, policy_version 147040 (0.0009) -[2023-11-28 04:04:01,567][87424] Updated weights for policy 0, policy_version 147287 (0.0011) -[2023-11-28 04:04:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75350016. Throughput: 0: 2709.9, 1: 2767.9. Samples: 75363472. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:03,446][86177] Avg episode reward: [(0, '-511.330'), (1, '-523.440')] -[2023-11-28 04:04:03,693][87426] Updated weights for policy 1, policy_version 147050 (0.0007) -[2023-11-28 04:04:04,001][87424] Updated weights for policy 0, policy_version 147297 (0.0012) -[2023-11-28 04:04:04,067][87426] Updated weights for policy 1, policy_version 147060 (0.0009) -[2023-11-28 04:04:04,382][87424] Updated weights for policy 0, policy_version 147307 (0.0011) -[2023-11-28 04:04:04,450][87426] Updated weights for policy 1, policy_version 147070 (0.0008) -[2023-11-28 04:04:04,778][87424] Updated weights for policy 0, policy_version 147317 (0.0012) -[2023-11-28 04:04:05,156][87424] Updated weights for policy 0, policy_version 147327 (0.0012) -[2023-11-28 04:04:06,450][87426] Updated weights for policy 1, policy_version 147080 (0.0011) -[2023-11-28 04:04:06,830][87426] Updated weights for policy 1, policy_version 147090 (0.0012) -[2023-11-28 04:04:06,912][87424] Updated weights for policy 0, policy_version 147337 (0.0011) -[2023-11-28 04:04:07,211][87426] Updated weights for policy 1, policy_version 147100 (0.0012) -[2023-11-28 04:04:07,299][87424] Updated weights for policy 0, policy_version 147347 (0.0011) -[2023-11-28 04:04:07,670][87424] Updated weights for policy 0, policy_version 147357 (0.0012) -[2023-11-28 04:04:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 75382784. Throughput: 0: 2726.9, 1: 2773.5. Samples: 75396500. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:08,445][86177] Avg episode reward: [(0, '-509.630'), (1, '-520.850')] -[2023-11-28 04:04:09,400][87426] Updated weights for policy 1, policy_version 147110 (0.0012) -[2023-11-28 04:04:09,780][87426] Updated weights for policy 1, policy_version 147120 (0.0012) -[2023-11-28 04:04:10,115][87424] Updated weights for policy 0, policy_version 147367 (0.0010) -[2023-11-28 04:04:10,164][87426] Updated weights for policy 1, policy_version 147130 (0.0011) -[2023-11-28 04:04:10,490][87424] Updated weights for policy 0, policy_version 147377 (0.0009) -[2023-11-28 04:04:10,894][87424] Updated weights for policy 0, policy_version 147387 (0.0008) -[2023-11-28 04:04:12,778][87426] Updated weights for policy 1, policy_version 147140 (0.0011) -[2023-11-28 04:04:12,805][87424] Updated weights for policy 0, policy_version 147397 (0.0009) -[2023-11-28 04:04:13,160][87426] Updated weights for policy 1, policy_version 147150 (0.0012) -[2023-11-28 04:04:13,194][87424] Updated weights for policy 0, policy_version 147407 (0.0011) -[2023-11-28 04:04:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 75399168. Throughput: 0: 2709.0, 1: 2713.5. Samples: 75419728. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:13,445][86177] Avg episode reward: [(0, '-545.470'), (1, '-523.290')] -[2023-11-28 04:04:13,534][87426] Updated weights for policy 1, policy_version 147160 (0.0009) -[2023-11-28 04:04:13,583][87424] Updated weights for policy 0, policy_version 147417 (0.0012) -[2023-11-28 04:04:15,253][87424] Updated weights for policy 0, policy_version 147427 (0.0012) -[2023-11-28 04:04:15,632][87424] Updated weights for policy 0, policy_version 147437 (0.0012) -[2023-11-28 04:04:16,013][87424] Updated weights for policy 0, policy_version 147447 (0.0011) -[2023-11-28 04:04:16,026][87426] Updated weights for policy 1, policy_version 147170 (0.0008) -[2023-11-28 04:04:16,410][87426] Updated weights for policy 1, policy_version 147180 (0.0009) -[2023-11-28 04:04:16,777][87426] Updated weights for policy 1, policy_version 147190 (0.0012) -[2023-11-28 04:04:17,164][87426] Updated weights for policy 1, policy_version 147200 (0.0011) -[2023-11-28 04:04:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 75431936. Throughput: 0: 2724.5, 1: 2694.8. Samples: 75444512. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:18,445][86177] Avg episode reward: [(0, '-542.410'), (1, '-503.930')] -[2023-11-28 04:04:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000147200_37683200.pth... -[2023-11-28 04:04:18,484][87424] Updated weights for policy 0, policy_version 147457 (0.0008) -[2023-11-28 04:04:18,497][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000144640_37027840.pth -[2023-11-28 04:04:18,883][87424] Updated weights for policy 0, policy_version 147467 (0.0013) -[2023-11-28 04:04:19,272][87426] Updated weights for policy 1, policy_version 147210 (0.0012) -[2023-11-28 04:04:19,275][87424] Updated weights for policy 0, policy_version 147477 (0.0011) -[2023-11-28 04:04:19,649][87424] Updated weights for policy 0, policy_version 147487 (0.0011) -[2023-11-28 04:04:19,653][87426] Updated weights for policy 1, policy_version 147220 (0.0011) -[2023-11-28 04:04:19,684][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000147488_37756928.pth... -[2023-11-28 04:04:19,730][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000144928_37101568.pth -[2023-11-28 04:04:20,024][87426] Updated weights for policy 1, policy_version 147230 (0.0009) -[2023-11-28 04:04:21,930][87424] Updated weights for policy 0, policy_version 147497 (0.0010) -[2023-11-28 04:04:21,943][87426] Updated weights for policy 1, policy_version 147240 (0.0011) -[2023-11-28 04:04:22,298][87424] Updated weights for policy 0, policy_version 147507 (0.0009) -[2023-11-28 04:04:22,324][87426] Updated weights for policy 1, policy_version 147250 (0.0010) -[2023-11-28 04:04:22,678][87424] Updated weights for policy 0, policy_version 147517 (0.0010) -[2023-11-28 04:04:22,707][87426] Updated weights for policy 1, policy_version 147260 (0.0011) -[2023-11-28 04:04:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 75464704. Throughput: 0: 2736.9, 1: 2690.9. Samples: 75477296. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:23,445][86177] Avg episode reward: [(0, '-559.510'), (1, '-534.540')] -[2023-11-28 04:04:24,613][87424] Updated weights for policy 0, policy_version 147527 (0.0012) -[2023-11-28 04:04:24,688][87426] Updated weights for policy 1, policy_version 147270 (0.0011) -[2023-11-28 04:04:24,990][87424] Updated weights for policy 0, policy_version 147537 (0.0012) -[2023-11-28 04:04:25,068][87426] Updated weights for policy 1, policy_version 147280 (0.0008) -[2023-11-28 04:04:25,368][87424] Updated weights for policy 0, policy_version 147547 (0.0011) -[2023-11-28 04:04:25,444][87426] Updated weights for policy 1, policy_version 147290 (0.0011) -[2023-11-28 04:04:27,370][87426] Updated weights for policy 1, policy_version 147300 (0.0009) -[2023-11-28 04:04:27,586][87424] Updated weights for policy 0, policy_version 147557 (0.0009) -[2023-11-28 04:04:27,751][87426] Updated weights for policy 1, policy_version 147310 (0.0007) -[2023-11-28 04:04:27,975][87424] Updated weights for policy 0, policy_version 147567 (0.0009) -[2023-11-28 04:04:28,116][87426] Updated weights for policy 1, policy_version 147320 (0.0008) -[2023-11-28 04:04:28,367][87424] Updated weights for policy 0, policy_version 147577 (0.0009) -[2023-11-28 04:04:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 75489280. Throughput: 0: 2736.1, 1: 2710.8. Samples: 75502428. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:28,445][86177] Avg episode reward: [(0, '-550.580'), (1, '-585.600')] -[2023-11-28 04:04:30,546][87424] Updated weights for policy 0, policy_version 147587 (0.0010) -[2023-11-28 04:04:30,549][87426] Updated weights for policy 1, policy_version 147330 (0.0008) -[2023-11-28 04:04:30,924][87424] Updated weights for policy 0, policy_version 147597 (0.0011) -[2023-11-28 04:04:30,932][87426] Updated weights for policy 1, policy_version 147340 (0.0012) -[2023-11-28 04:04:31,311][87426] Updated weights for policy 1, policy_version 147350 (0.0011) -[2023-11-28 04:04:31,315][87424] Updated weights for policy 0, policy_version 147607 (0.0011) -[2023-11-28 04:04:31,686][87426] Updated weights for policy 1, policy_version 147360 (0.0011) -[2023-11-28 04:04:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75513856. Throughput: 0: 2730.9, 1: 2696.5. Samples: 75526840. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:33,445][86177] Avg episode reward: [(0, '-549.990'), (1, '-583.380')] -[2023-11-28 04:04:33,553][87426] Updated weights for policy 1, policy_version 147370 (0.0008) -[2023-11-28 04:04:33,667][87424] Updated weights for policy 0, policy_version 147617 (0.0010) -[2023-11-28 04:04:33,935][87426] Updated weights for policy 1, policy_version 147380 (0.0007) -[2023-11-28 04:04:34,055][87424] Updated weights for policy 0, policy_version 147627 (0.0007) -[2023-11-28 04:04:34,316][87426] Updated weights for policy 1, policy_version 147390 (0.0007) -[2023-11-28 04:04:34,435][87424] Updated weights for policy 0, policy_version 147637 (0.0007) -[2023-11-28 04:04:34,824][87424] Updated weights for policy 0, policy_version 147647 (0.0009) -[2023-11-28 04:04:36,456][87426] Updated weights for policy 1, policy_version 147400 (0.0007) -[2023-11-28 04:04:36,836][87426] Updated weights for policy 1, policy_version 147410 (0.0008) -[2023-11-28 04:04:36,939][87424] Updated weights for policy 0, policy_version 147657 (0.0011) -[2023-11-28 04:04:37,208][87426] Updated weights for policy 1, policy_version 147420 (0.0008) -[2023-11-28 04:04:37,320][87424] Updated weights for policy 0, policy_version 147667 (0.0010) -[2023-11-28 04:04:37,702][87424] Updated weights for policy 0, policy_version 147677 (0.0007) -[2023-11-28 04:04:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 75546624. Throughput: 0: 2744.7, 1: 2718.8. Samples: 75560188. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:38,445][86177] Avg episode reward: [(0, '-545.140'), (1, '-586.020')] -[2023-11-28 04:04:39,204][87426] Updated weights for policy 1, policy_version 147430 (0.0008) -[2023-11-28 04:04:39,587][87426] Updated weights for policy 1, policy_version 147440 (0.0008) -[2023-11-28 04:04:39,968][87426] Updated weights for policy 1, policy_version 147450 (0.0009) -[2023-11-28 04:04:40,173][87424] Updated weights for policy 0, policy_version 147687 (0.0010) -[2023-11-28 04:04:40,558][87424] Updated weights for policy 0, policy_version 147697 (0.0011) -[2023-11-28 04:04:40,940][87424] Updated weights for policy 0, policy_version 147707 (0.0011) -[2023-11-28 04:04:42,492][87426] Updated weights for policy 1, policy_version 147460 (0.0010) -[2023-11-28 04:04:42,868][87426] Updated weights for policy 1, policy_version 147470 (0.0009) -[2023-11-28 04:04:43,242][87426] Updated weights for policy 1, policy_version 147480 (0.0012) -[2023-11-28 04:04:43,332][87424] Updated weights for policy 0, policy_version 147717 (0.0011) -[2023-11-28 04:04:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 75563008. Throughput: 0: 2723.5, 1: 2733.9. Samples: 75583788. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:43,445][86177] Avg episode reward: [(0, '-553.830'), (1, '-588.590')] -[2023-11-28 04:04:43,716][87424] Updated weights for policy 0, policy_version 147727 (0.0011) -[2023-11-28 04:04:44,104][87424] Updated weights for policy 0, policy_version 147737 (0.0011) -[2023-11-28 04:04:45,309][87426] Updated weights for policy 1, policy_version 147490 (0.0011) -[2023-11-28 04:04:45,690][87426] Updated weights for policy 1, policy_version 147500 (0.0011) -[2023-11-28 04:04:46,073][87426] Updated weights for policy 1, policy_version 147510 (0.0012) -[2023-11-28 04:04:46,337][87424] Updated weights for policy 0, policy_version 147747 (0.0012) -[2023-11-28 04:04:46,451][87426] Updated weights for policy 1, policy_version 147520 (0.0010) -[2023-11-28 04:04:46,713][87424] Updated weights for policy 0, policy_version 147757 (0.0008) -[2023-11-28 04:04:47,098][87424] Updated weights for policy 0, policy_version 147767 (0.0008) -[2023-11-28 04:04:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75595776. Throughput: 0: 2699.0, 1: 2722.2. Samples: 75607428. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:48,445][86177] Avg episode reward: [(0, '-611.260'), (1, '-555.060')] -[2023-11-28 04:04:48,994][87426] Updated weights for policy 1, policy_version 147530 (0.0011) -[2023-11-28 04:04:49,377][87426] Updated weights for policy 1, policy_version 147540 (0.0010) -[2023-11-28 04:04:49,546][87424] Updated weights for policy 0, policy_version 147777 (0.0007) -[2023-11-28 04:04:49,757][87426] Updated weights for policy 1, policy_version 147550 (0.0009) -[2023-11-28 04:04:49,923][87424] Updated weights for policy 0, policy_version 147787 (0.0009) -[2023-11-28 04:04:50,306][87424] Updated weights for policy 0, policy_version 147797 (0.0010) -[2023-11-28 04:04:50,697][87424] Updated weights for policy 0, policy_version 147807 (0.0011) -[2023-11-28 04:04:52,111][87426] Updated weights for policy 1, policy_version 147560 (0.0009) -[2023-11-28 04:04:52,488][87426] Updated weights for policy 1, policy_version 147570 (0.0011) -[2023-11-28 04:04:52,863][87426] Updated weights for policy 1, policy_version 147580 (0.0012) -[2023-11-28 04:04:53,143][87424] Updated weights for policy 0, policy_version 147817 (0.0009) -[2023-11-28 04:04:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 75620352. Throughput: 0: 2667.3, 1: 2705.1. Samples: 75638256. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:53,445][86177] Avg episode reward: [(0, '-611.960'), (1, '-562.220')] -[2023-11-28 04:04:53,536][87424] Updated weights for policy 0, policy_version 147827 (0.0010) -[2023-11-28 04:04:53,926][87424] Updated weights for policy 0, policy_version 147837 (0.0012) -[2023-11-28 04:04:54,885][87426] Updated weights for policy 1, policy_version 147590 (0.0011) -[2023-11-28 04:04:55,279][87426] Updated weights for policy 1, policy_version 147600 (0.0012) -[2023-11-28 04:04:55,664][87426] Updated weights for policy 1, policy_version 147610 (0.0012) -[2023-11-28 04:04:56,006][87424] Updated weights for policy 0, policy_version 147847 (0.0012) -[2023-11-28 04:04:56,390][87424] Updated weights for policy 0, policy_version 147857 (0.0012) -[2023-11-28 04:04:56,774][87424] Updated weights for policy 0, policy_version 147867 (0.0012) -[2023-11-28 04:04:57,798][87426] Updated weights for policy 1, policy_version 147620 (0.0010) -[2023-11-28 04:04:58,184][87426] Updated weights for policy 1, policy_version 147630 (0.0011) -[2023-11-28 04:04:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 75644928. Throughput: 0: 2688.9, 1: 2723.7. Samples: 75663296. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:04:58,445][86177] Avg episode reward: [(0, '-580.890'), (1, '-558.850')] -[2023-11-28 04:04:58,566][87426] Updated weights for policy 1, policy_version 147640 (0.0011) -[2023-11-28 04:04:58,677][87424] Updated weights for policy 0, policy_version 147877 (0.0012) -[2023-11-28 04:04:59,055][87424] Updated weights for policy 0, policy_version 147887 (0.0016) -[2023-11-28 04:04:59,442][87424] Updated weights for policy 0, policy_version 147897 (0.0012) -[2023-11-28 04:05:00,457][87426] Updated weights for policy 1, policy_version 147650 (0.0011) -[2023-11-28 04:05:00,841][87426] Updated weights for policy 1, policy_version 147660 (0.0012) -[2023-11-28 04:05:01,219][87426] Updated weights for policy 1, policy_version 147670 (0.0012) -[2023-11-28 04:05:01,471][87424] Updated weights for policy 0, policy_version 147907 (0.0011) -[2023-11-28 04:05:01,590][87426] Updated weights for policy 1, policy_version 147680 (0.0009) -[2023-11-28 04:05:01,864][87424] Updated weights for policy 0, policy_version 147917 (0.0011) -[2023-11-28 04:05:02,230][87424] Updated weights for policy 0, policy_version 147927 (0.0014) -[2023-11-28 04:05:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 75677696. Throughput: 0: 2665.4, 1: 2740.8. Samples: 75687792. Policy #0 lag: (min: 31.0, avg: 43.2, max: 63.0) -[2023-11-28 04:05:03,445][86177] Avg episode reward: [(0, '-598.540'), (1, '-555.220')] -[2023-11-28 04:05:03,707][87426] Updated weights for policy 1, policy_version 147690 (0.0008) -[2023-11-28 04:05:04,084][87426] Updated weights for policy 1, policy_version 147700 (0.0007) -[2023-11-28 04:05:04,468][87426] Updated weights for policy 1, policy_version 147710 (0.0008) -[2023-11-28 04:05:04,566][87424] Updated weights for policy 0, policy_version 147937 (0.0013) -[2023-11-28 04:05:04,956][87424] Updated weights for policy 0, policy_version 147947 (0.0012) -[2023-11-28 04:05:05,328][87424] Updated weights for policy 0, policy_version 147957 (0.0012) -[2023-11-28 04:05:05,710][87424] Updated weights for policy 0, policy_version 147967 (0.0012) -[2023-11-28 04:05:06,846][87426] Updated weights for policy 1, policy_version 147720 (0.0011) -[2023-11-28 04:05:07,225][87426] Updated weights for policy 1, policy_version 147730 (0.0012) -[2023-11-28 04:05:07,604][87426] Updated weights for policy 1, policy_version 147740 (0.0012) -[2023-11-28 04:05:07,879][87424] Updated weights for policy 0, policy_version 147977 (0.0011) -[2023-11-28 04:05:08,256][87424] Updated weights for policy 0, policy_version 147987 (0.0012) -[2023-11-28 04:05:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 75702272. Throughput: 0: 2676.0, 1: 2741.3. Samples: 75721076. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:08,445][86177] Avg episode reward: [(0, '-543.130'), (1, '-569.530')] -[2023-11-28 04:05:08,642][87424] Updated weights for policy 0, policy_version 147997 (0.0012) -[2023-11-28 04:05:09,312][87426] Updated weights for policy 1, policy_version 147750 (0.0012) -[2023-11-28 04:05:09,700][87426] Updated weights for policy 1, policy_version 147760 (0.0012) -[2023-11-28 04:05:10,082][87426] Updated weights for policy 1, policy_version 147770 (0.0012) -[2023-11-28 04:05:10,556][87424] Updated weights for policy 0, policy_version 148007 (0.0012) -[2023-11-28 04:05:10,934][87424] Updated weights for policy 0, policy_version 148017 (0.0012) -[2023-11-28 04:05:11,317][87424] Updated weights for policy 0, policy_version 148027 (0.0012) -[2023-11-28 04:05:12,593][87426] Updated weights for policy 1, policy_version 147780 (0.0012) -[2023-11-28 04:05:12,961][87426] Updated weights for policy 1, policy_version 147790 (0.0012) -[2023-11-28 04:05:13,352][87426] Updated weights for policy 1, policy_version 147800 (0.0012) -[2023-11-28 04:05:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75726848. Throughput: 0: 2677.4, 1: 2741.1. Samples: 75746264. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:13,446][86177] Avg episode reward: [(0, '-586.220'), (1, '-562.790')] -[2023-11-28 04:05:13,699][87424] Updated weights for policy 0, policy_version 148037 (0.0012) -[2023-11-28 04:05:14,080][87424] Updated weights for policy 0, policy_version 148047 (0.0011) -[2023-11-28 04:05:14,467][87424] Updated weights for policy 0, policy_version 148057 (0.0009) -[2023-11-28 04:05:15,020][87426] Updated weights for policy 1, policy_version 147810 (0.0011) -[2023-11-28 04:05:15,402][87426] Updated weights for policy 1, policy_version 147820 (0.0012) -[2023-11-28 04:05:15,782][87426] Updated weights for policy 1, policy_version 147830 (0.0012) -[2023-11-28 04:05:16,163][87426] Updated weights for policy 1, policy_version 147840 (0.0010) -[2023-11-28 04:05:16,883][87424] Updated weights for policy 0, policy_version 148067 (0.0008) -[2023-11-28 04:05:17,263][87424] Updated weights for policy 0, policy_version 148077 (0.0010) -[2023-11-28 04:05:17,637][87424] Updated weights for policy 0, policy_version 148087 (0.0012) -[2023-11-28 04:05:18,070][87426] Updated weights for policy 1, policy_version 147850 (0.0007) -[2023-11-28 04:05:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 75759616. Throughput: 0: 2658.7, 1: 2765.4. Samples: 75770924. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:18,445][86177] Avg episode reward: [(0, '-536.930'), (1, '-562.550')] -[2023-11-28 04:05:18,448][87426] Updated weights for policy 1, policy_version 147860 (0.0007) -[2023-11-28 04:05:18,822][87426] Updated weights for policy 1, policy_version 147870 (0.0010) -[2023-11-28 04:05:20,003][87424] Updated weights for policy 0, policy_version 148097 (0.0012) -[2023-11-28 04:05:20,389][87424] Updated weights for policy 0, policy_version 148107 (0.0012) -[2023-11-28 04:05:20,765][87424] Updated weights for policy 0, policy_version 148117 (0.0012) -[2023-11-28 04:05:21,141][87424] Updated weights for policy 0, policy_version 148127 (0.0012) -[2023-11-28 04:05:21,353][87426] Updated weights for policy 1, policy_version 147880 (0.0010) -[2023-11-28 04:05:21,745][87426] Updated weights for policy 1, policy_version 147890 (0.0010) -[2023-11-28 04:05:22,132][87426] Updated weights for policy 1, policy_version 147900 (0.0011) -[2023-11-28 04:05:23,121][87424] Updated weights for policy 0, policy_version 148137 (0.0012) -[2023-11-28 04:05:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 75784192. Throughput: 0: 2659.7, 1: 2739.3. Samples: 75803140. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:23,445][86177] Avg episode reward: [(0, '-533.010'), (1, '-526.610')] -[2023-11-28 04:05:23,505][87424] Updated weights for policy 0, policy_version 148147 (0.0009) -[2023-11-28 04:05:23,893][87424] Updated weights for policy 0, policy_version 148157 (0.0010) -[2023-11-28 04:05:24,681][87426] Updated weights for policy 1, policy_version 147910 (0.0009) -[2023-11-28 04:05:25,068][87426] Updated weights for policy 1, policy_version 147920 (0.0007) -[2023-11-28 04:05:25,458][87426] Updated weights for policy 1, policy_version 147930 (0.0008) -[2023-11-28 04:05:26,155][87424] Updated weights for policy 0, policy_version 148167 (0.0011) -[2023-11-28 04:05:26,534][87424] Updated weights for policy 0, policy_version 148177 (0.0012) -[2023-11-28 04:05:26,922][87424] Updated weights for policy 0, policy_version 148187 (0.0012) -[2023-11-28 04:05:27,810][87426] Updated weights for policy 1, policy_version 147940 (0.0008) -[2023-11-28 04:05:28,192][87426] Updated weights for policy 1, policy_version 147950 (0.0011) -[2023-11-28 04:05:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 75808768. Throughput: 0: 2677.2, 1: 2737.0. Samples: 75827428. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:28,445][86177] Avg episode reward: [(0, '-535.570'), (1, '-494.670')] -[2023-11-28 04:05:28,570][87426] Updated weights for policy 1, policy_version 147960 (0.0009) -[2023-11-28 04:05:28,742][87424] Updated weights for policy 0, policy_version 148197 (0.0012) -[2023-11-28 04:05:29,126][87424] Updated weights for policy 0, policy_version 148207 (0.0011) -[2023-11-28 04:05:29,509][87424] Updated weights for policy 0, policy_version 148217 (0.0012) -[2023-11-28 04:05:30,577][87426] Updated weights for policy 1, policy_version 147970 (0.0010) -[2023-11-28 04:05:30,962][87426] Updated weights for policy 1, policy_version 147980 (0.0011) -[2023-11-28 04:05:31,347][87426] Updated weights for policy 1, policy_version 147990 (0.0012) -[2023-11-28 04:05:31,747][87426] Updated weights for policy 1, policy_version 148000 (0.0010) -[2023-11-28 04:05:32,013][87424] Updated weights for policy 0, policy_version 148227 (0.0012) -[2023-11-28 04:05:32,408][87424] Updated weights for policy 0, policy_version 148237 (0.0011) -[2023-11-28 04:05:32,785][87424] Updated weights for policy 0, policy_version 148247 (0.0012) -[2023-11-28 04:05:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75841536. Throughput: 0: 2682.6, 1: 2752.3. Samples: 75851996. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:33,445][86177] Avg episode reward: [(0, '-493.210'), (1, '-535.110')] -[2023-11-28 04:05:34,068][87426] Updated weights for policy 1, policy_version 148010 (0.0011) -[2023-11-28 04:05:34,440][87426] Updated weights for policy 1, policy_version 148020 (0.0012) -[2023-11-28 04:05:34,596][87424] Updated weights for policy 0, policy_version 148257 (0.0012) -[2023-11-28 04:05:34,819][87426] Updated weights for policy 1, policy_version 148030 (0.0011) -[2023-11-28 04:05:34,985][87424] Updated weights for policy 0, policy_version 148267 (0.0012) -[2023-11-28 04:05:35,368][87424] Updated weights for policy 0, policy_version 148277 (0.0012) -[2023-11-28 04:05:35,750][87424] Updated weights for policy 0, policy_version 148287 (0.0011) -[2023-11-28 04:05:36,593][87426] Updated weights for policy 1, policy_version 148040 (0.0011) -[2023-11-28 04:05:36,987][87426] Updated weights for policy 1, policy_version 148050 (0.0012) -[2023-11-28 04:05:37,370][87426] Updated weights for policy 1, policy_version 148060 (0.0012) -[2023-11-28 04:05:37,729][87424] Updated weights for policy 0, policy_version 148297 (0.0011) -[2023-11-28 04:05:38,108][87424] Updated weights for policy 0, policy_version 148307 (0.0007) -[2023-11-28 04:05:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 75866112. Throughput: 0: 2712.2, 1: 2761.1. Samples: 75884552. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:38,445][86177] Avg episode reward: [(0, '-492.460'), (1, '-545.890')] -[2023-11-28 04:05:38,496][87424] Updated weights for policy 0, policy_version 148317 (0.0007) -[2023-11-28 04:05:39,369][87426] Updated weights for policy 1, policy_version 148070 (0.0009) -[2023-11-28 04:05:39,751][87426] Updated weights for policy 1, policy_version 148080 (0.0008) -[2023-11-28 04:05:40,125][87426] Updated weights for policy 1, policy_version 148090 (0.0011) -[2023-11-28 04:05:40,968][87424] Updated weights for policy 0, policy_version 148327 (0.0010) -[2023-11-28 04:05:41,344][87424] Updated weights for policy 0, policy_version 148337 (0.0012) -[2023-11-28 04:05:41,733][87424] Updated weights for policy 0, policy_version 148347 (0.0012) -[2023-11-28 04:05:42,630][87426] Updated weights for policy 1, policy_version 148100 (0.0009) -[2023-11-28 04:05:43,007][87426] Updated weights for policy 1, policy_version 148110 (0.0010) -[2023-11-28 04:05:43,390][87426] Updated weights for policy 1, policy_version 148120 (0.0012) -[2023-11-28 04:05:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75890688. Throughput: 0: 2709.1, 1: 2751.6. Samples: 75909024. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:43,445][86177] Avg episode reward: [(0, '-490.020'), (1, '-568.590')] -[2023-11-28 04:05:44,110][87424] Updated weights for policy 0, policy_version 148357 (0.0012) -[2023-11-28 04:05:44,500][87424] Updated weights for policy 0, policy_version 148367 (0.0012) -[2023-11-28 04:05:44,877][87424] Updated weights for policy 0, policy_version 148377 (0.0012) -[2023-11-28 04:05:45,062][87426] Updated weights for policy 1, policy_version 148130 (0.0008) -[2023-11-28 04:05:45,442][87426] Updated weights for policy 1, policy_version 148140 (0.0011) -[2023-11-28 04:05:45,817][87426] Updated weights for policy 1, policy_version 148150 (0.0012) -[2023-11-28 04:05:46,191][87426] Updated weights for policy 1, policy_version 148160 (0.0012) -[2023-11-28 04:05:46,836][87424] Updated weights for policy 0, policy_version 148387 (0.0012) -[2023-11-28 04:05:47,219][87424] Updated weights for policy 0, policy_version 148397 (0.0011) -[2023-11-28 04:05:47,601][87424] Updated weights for policy 0, policy_version 148407 (0.0007) -[2023-11-28 04:05:48,167][87426] Updated weights for policy 1, policy_version 148170 (0.0008) -[2023-11-28 04:05:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 75923456. Throughput: 0: 2727.4, 1: 2753.6. Samples: 75934436. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:48,445][86177] Avg episode reward: [(0, '-493.250'), (1, '-569.210')] -[2023-11-28 04:05:48,548][87426] Updated weights for policy 1, policy_version 148180 (0.0007) -[2023-11-28 04:05:48,936][87426] Updated weights for policy 1, policy_version 148190 (0.0009) -[2023-11-28 04:05:49,966][87424] Updated weights for policy 0, policy_version 148417 (0.0008) -[2023-11-28 04:05:50,350][87424] Updated weights for policy 0, policy_version 148427 (0.0009) -[2023-11-28 04:05:50,723][87424] Updated weights for policy 0, policy_version 148437 (0.0009) -[2023-11-28 04:05:51,107][87424] Updated weights for policy 0, policy_version 148447 (0.0010) -[2023-11-28 04:05:51,197][87426] Updated weights for policy 1, policy_version 148200 (0.0011) -[2023-11-28 04:05:51,570][87426] Updated weights for policy 1, policy_version 148210 (0.0009) -[2023-11-28 04:05:51,956][87426] Updated weights for policy 1, policy_version 148220 (0.0012) -[2023-11-28 04:05:53,437][87424] Updated weights for policy 0, policy_version 148457 (0.0011) -[2023-11-28 04:05:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75948032. Throughput: 0: 2722.9, 1: 2753.1. Samples: 75967496. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:53,445][86177] Avg episode reward: [(0, '-493.040'), (1, '-541.370')] -[2023-11-28 04:05:53,819][87424] Updated weights for policy 0, policy_version 148467 (0.0010) -[2023-11-28 04:05:54,202][87424] Updated weights for policy 0, policy_version 148477 (0.0011) -[2023-11-28 04:05:54,465][87426] Updated weights for policy 1, policy_version 148230 (0.0011) -[2023-11-28 04:05:54,839][87426] Updated weights for policy 1, policy_version 148240 (0.0010) -[2023-11-28 04:05:55,217][87426] Updated weights for policy 1, policy_version 148250 (0.0011) -[2023-11-28 04:05:56,113][87424] Updated weights for policy 0, policy_version 148487 (0.0009) -[2023-11-28 04:05:56,504][87424] Updated weights for policy 0, policy_version 148497 (0.0007) -[2023-11-28 04:05:56,894][87424] Updated weights for policy 0, policy_version 148507 (0.0008) -[2023-11-28 04:05:57,552][87426] Updated weights for policy 1, policy_version 148260 (0.0011) -[2023-11-28 04:05:57,932][87426] Updated weights for policy 1, policy_version 148270 (0.0011) -[2023-11-28 04:05:58,325][87426] Updated weights for policy 1, policy_version 148280 (0.0011) -[2023-11-28 04:05:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 75972608. Throughput: 0: 2711.5, 1: 2729.4. Samples: 75991104. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:05:58,445][86177] Avg episode reward: [(0, '-499.350'), (1, '-525.900')] -[2023-11-28 04:05:59,353][87424] Updated weights for policy 0, policy_version 148517 (0.0008) -[2023-11-28 04:05:59,719][87424] Updated weights for policy 0, policy_version 148527 (0.0007) -[2023-11-28 04:06:00,107][87424] Updated weights for policy 0, policy_version 148537 (0.0009) -[2023-11-28 04:06:00,829][87426] Updated weights for policy 1, policy_version 148290 (0.0012) -[2023-11-28 04:06:01,206][87426] Updated weights for policy 1, policy_version 148300 (0.0008) -[2023-11-28 04:06:01,585][87426] Updated weights for policy 1, policy_version 148310 (0.0008) -[2023-11-28 04:06:01,957][87426] Updated weights for policy 1, policy_version 148320 (0.0009) -[2023-11-28 04:06:02,549][87424] Updated weights for policy 0, policy_version 148547 (0.0009) -[2023-11-28 04:06:02,927][87424] Updated weights for policy 0, policy_version 148557 (0.0012) -[2023-11-28 04:06:03,298][87424] Updated weights for policy 0, policy_version 148567 (0.0012) -[2023-11-28 04:06:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 75997184. Throughput: 0: 2705.8, 1: 2708.2. Samples: 76014552. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:06:03,445][86177] Avg episode reward: [(0, '-497.100'), (1, '-514.830')] -[2023-11-28 04:06:04,003][87426] Updated weights for policy 1, policy_version 148330 (0.0012) -[2023-11-28 04:06:04,381][87426] Updated weights for policy 1, policy_version 148340 (0.0011) -[2023-11-28 04:06:04,752][87426] Updated weights for policy 1, policy_version 148350 (0.0011) -[2023-11-28 04:06:05,837][87424] Updated weights for policy 0, policy_version 148577 (0.0011) -[2023-11-28 04:06:06,211][87424] Updated weights for policy 0, policy_version 148587 (0.0012) -[2023-11-28 04:06:06,585][87424] Updated weights for policy 0, policy_version 148597 (0.0012) -[2023-11-28 04:06:06,753][87426] Updated weights for policy 1, policy_version 148360 (0.0012) -[2023-11-28 04:06:06,981][87424] Updated weights for policy 0, policy_version 148607 (0.0012) -[2023-11-28 04:06:07,147][87426] Updated weights for policy 1, policy_version 148370 (0.0012) -[2023-11-28 04:06:07,516][87426] Updated weights for policy 1, policy_version 148380 (0.0012) -[2023-11-28 04:06:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 76029952. Throughput: 0: 2672.5, 1: 2715.3. Samples: 76045592. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:06:08,445][86177] Avg episode reward: [(0, '-496.730'), (1, '-528.080')] -[2023-11-28 04:06:09,323][87424] Updated weights for policy 0, policy_version 148617 (0.0012) -[2023-11-28 04:06:09,653][87426] Updated weights for policy 1, policy_version 148390 (0.0009) -[2023-11-28 04:06:09,708][87424] Updated weights for policy 0, policy_version 148627 (0.0012) -[2023-11-28 04:06:10,039][87426] Updated weights for policy 1, policy_version 148400 (0.0010) -[2023-11-28 04:06:10,097][87424] Updated weights for policy 0, policy_version 148637 (0.0011) -[2023-11-28 04:06:10,414][87426] Updated weights for policy 1, policy_version 148410 (0.0011) -[2023-11-28 04:06:12,003][87424] Updated weights for policy 0, policy_version 148647 (0.0011) -[2023-11-28 04:06:12,386][87424] Updated weights for policy 0, policy_version 148657 (0.0011) -[2023-11-28 04:06:12,706][87426] Updated weights for policy 1, policy_version 148420 (0.0012) -[2023-11-28 04:06:12,766][87424] Updated weights for policy 0, policy_version 148667 (0.0010) -[2023-11-28 04:06:13,086][87426] Updated weights for policy 1, policy_version 148430 (0.0011) -[2023-11-28 04:06:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 76054528. Throughput: 0: 2662.7, 1: 2711.6. Samples: 76069268. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:13,445][86177] Avg episode reward: [(0, '-491.510'), (1, '-513.140')] -[2023-11-28 04:06:13,472][87426] Updated weights for policy 1, policy_version 148440 (0.0009) -[2023-11-28 04:06:14,889][87424] Updated weights for policy 0, policy_version 148677 (0.0010) -[2023-11-28 04:06:15,274][87424] Updated weights for policy 0, policy_version 148687 (0.0007) -[2023-11-28 04:06:15,352][87426] Updated weights for policy 1, policy_version 148450 (0.0011) -[2023-11-28 04:06:15,644][87424] Updated weights for policy 0, policy_version 148697 (0.0009) -[2023-11-28 04:06:15,725][87426] Updated weights for policy 1, policy_version 148460 (0.0009) -[2023-11-28 04:06:16,098][87426] Updated weights for policy 1, policy_version 148470 (0.0008) -[2023-11-28 04:06:16,476][87426] Updated weights for policy 1, policy_version 148480 (0.0007) -[2023-11-28 04:06:18,018][87424] Updated weights for policy 0, policy_version 148707 (0.0010) -[2023-11-28 04:06:18,397][87424] Updated weights for policy 0, policy_version 148717 (0.0008) -[2023-11-28 04:06:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 76079104. Throughput: 0: 2679.4, 1: 2717.8. Samples: 76094868. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:18,445][86177] Avg episode reward: [(0, '-492.280'), (1, '-522.760')] -[2023-11-28 04:06:18,778][87424] Updated weights for policy 0, policy_version 148727 (0.0008) -[2023-11-28 04:06:18,887][87426] Updated weights for policy 1, policy_version 148490 (0.0011) -[2023-11-28 04:06:19,117][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000148736_38076416.pth... -[2023-11-28 04:06:19,164][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000146208_37429248.pth -[2023-11-28 04:06:19,269][87426] Updated weights for policy 1, policy_version 148500 (0.0012) -[2023-11-28 04:06:19,655][87426] Updated weights for policy 1, policy_version 148510 (0.0007) -[2023-11-28 04:06:19,729][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000148512_38019072.pth... -[2023-11-28 04:06:19,764][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000145920_37355520.pth -[2023-11-28 04:06:21,088][87424] Updated weights for policy 0, policy_version 148737 (0.0008) -[2023-11-28 04:06:21,467][87424] Updated weights for policy 0, policy_version 148747 (0.0012) -[2023-11-28 04:06:21,742][87426] Updated weights for policy 1, policy_version 148520 (0.0010) -[2023-11-28 04:06:21,852][87424] Updated weights for policy 0, policy_version 148757 (0.0010) -[2023-11-28 04:06:22,125][87426] Updated weights for policy 1, policy_version 148530 (0.0013) -[2023-11-28 04:06:22,242][87424] Updated weights for policy 0, policy_version 148767 (0.0011) -[2023-11-28 04:06:22,506][87426] Updated weights for policy 1, policy_version 148540 (0.0011) -[2023-11-28 04:06:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 76111872. Throughput: 0: 2669.2, 1: 2708.7. Samples: 76126556. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:23,445][86177] Avg episode reward: [(0, '-499.680'), (1, '-526.490')] -[2023-11-28 04:06:24,273][87424] Updated weights for policy 0, policy_version 148777 (0.0012) -[2023-11-28 04:06:24,649][87424] Updated weights for policy 0, policy_version 148787 (0.0012) -[2023-11-28 04:06:24,869][87426] Updated weights for policy 1, policy_version 148550 (0.0008) -[2023-11-28 04:06:25,029][87424] Updated weights for policy 0, policy_version 148797 (0.0010) -[2023-11-28 04:06:25,251][87426] Updated weights for policy 1, policy_version 148560 (0.0008) -[2023-11-28 04:06:25,625][87426] Updated weights for policy 1, policy_version 148570 (0.0008) -[2023-11-28 04:06:26,969][87424] Updated weights for policy 0, policy_version 148807 (0.0011) -[2023-11-28 04:06:27,356][87424] Updated weights for policy 0, policy_version 148817 (0.0012) -[2023-11-28 04:06:27,425][87426] Updated weights for policy 1, policy_version 148580 (0.0007) -[2023-11-28 04:06:27,729][87424] Updated weights for policy 0, policy_version 148827 (0.0010) -[2023-11-28 04:06:27,804][87426] Updated weights for policy 1, policy_version 148590 (0.0007) -[2023-11-28 04:06:28,186][87426] Updated weights for policy 1, policy_version 148600 (0.0007) -[2023-11-28 04:06:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 76136448. Throughput: 0: 2674.0, 1: 2723.5. Samples: 76151908. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:28,445][86177] Avg episode reward: [(0, '-504.660'), (1, '-522.670')] -[2023-11-28 04:06:29,958][87424] Updated weights for policy 0, policy_version 148837 (0.0011) -[2023-11-28 04:06:30,351][87424] Updated weights for policy 0, policy_version 148847 (0.0012) -[2023-11-28 04:06:30,550][87426] Updated weights for policy 1, policy_version 148610 (0.0008) -[2023-11-28 04:06:30,725][87424] Updated weights for policy 0, policy_version 148857 (0.0009) -[2023-11-28 04:06:30,923][87426] Updated weights for policy 1, policy_version 148620 (0.0008) -[2023-11-28 04:06:31,300][87426] Updated weights for policy 1, policy_version 148630 (0.0007) -[2023-11-28 04:06:31,678][87426] Updated weights for policy 1, policy_version 148640 (0.0008) -[2023-11-28 04:06:32,842][87424] Updated weights for policy 0, policy_version 148867 (0.0008) -[2023-11-28 04:06:33,214][87424] Updated weights for policy 0, policy_version 148877 (0.0009) -[2023-11-28 04:06:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 76161024. Throughput: 0: 2662.7, 1: 2708.6. Samples: 76176144. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:33,445][86177] Avg episode reward: [(0, '-507.690'), (1, '-532.310')] -[2023-11-28 04:06:33,597][87424] Updated weights for policy 0, policy_version 148887 (0.0008) -[2023-11-28 04:06:34,214][87426] Updated weights for policy 1, policy_version 148650 (0.0007) -[2023-11-28 04:06:34,599][87426] Updated weights for policy 1, policy_version 148660 (0.0009) -[2023-11-28 04:06:34,981][87426] Updated weights for policy 1, policy_version 148670 (0.0011) -[2023-11-28 04:06:36,015][87424] Updated weights for policy 0, policy_version 148897 (0.0008) -[2023-11-28 04:06:36,399][87424] Updated weights for policy 0, policy_version 148907 (0.0007) -[2023-11-28 04:06:36,794][87424] Updated weights for policy 0, policy_version 148917 (0.0009) -[2023-11-28 04:06:37,181][87424] Updated weights for policy 0, policy_version 148927 (0.0010) -[2023-11-28 04:06:37,379][87426] Updated weights for policy 1, policy_version 148680 (0.0011) -[2023-11-28 04:06:37,755][87426] Updated weights for policy 1, policy_version 148690 (0.0011) -[2023-11-28 04:06:38,133][87426] Updated weights for policy 1, policy_version 148700 (0.0011) -[2023-11-28 04:06:38,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 76193792. Throughput: 0: 2638.6, 1: 2691.9. Samples: 76207368. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:38,445][86177] Avg episode reward: [(0, '-503.720'), (1, '-519.940')] -[2023-11-28 04:06:39,740][87424] Updated weights for policy 0, policy_version 148937 (0.0011) -[2023-11-28 04:06:40,120][87424] Updated weights for policy 0, policy_version 148947 (0.0010) -[2023-11-28 04:06:40,480][87426] Updated weights for policy 1, policy_version 148710 (0.0010) -[2023-11-28 04:06:40,506][87424] Updated weights for policy 0, policy_version 148957 (0.0011) -[2023-11-28 04:06:40,858][87426] Updated weights for policy 1, policy_version 148720 (0.0008) -[2023-11-28 04:06:41,241][87426] Updated weights for policy 1, policy_version 148730 (0.0007) -[2023-11-28 04:06:42,843][87424] Updated weights for policy 0, policy_version 148967 (0.0011) -[2023-11-28 04:06:43,221][87424] Updated weights for policy 0, policy_version 148977 (0.0009) -[2023-11-28 04:06:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 76210176. Throughput: 0: 2645.1, 1: 2696.5. Samples: 76231476. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:43,445][86177] Avg episode reward: [(0, '-493.090'), (1, '-523.370')] -[2023-11-28 04:06:43,605][87424] Updated weights for policy 0, policy_version 148987 (0.0007) -[2023-11-28 04:06:43,746][87426] Updated weights for policy 1, policy_version 148740 (0.0011) -[2023-11-28 04:06:44,131][87426] Updated weights for policy 1, policy_version 148750 (0.0007) -[2023-11-28 04:06:44,524][87426] Updated weights for policy 1, policy_version 148760 (0.0007) -[2023-11-28 04:06:45,618][87424] Updated weights for policy 0, policy_version 148997 (0.0007) -[2023-11-28 04:06:46,000][87424] Updated weights for policy 0, policy_version 149007 (0.0008) -[2023-11-28 04:06:46,391][87424] Updated weights for policy 0, policy_version 149017 (0.0008) -[2023-11-28 04:06:47,060][87426] Updated weights for policy 1, policy_version 148770 (0.0008) -[2023-11-28 04:06:47,436][87426] Updated weights for policy 1, policy_version 148780 (0.0009) -[2023-11-28 04:06:47,820][87426] Updated weights for policy 1, policy_version 148790 (0.0008) -[2023-11-28 04:06:48,202][87426] Updated weights for policy 1, policy_version 148800 (0.0012) -[2023-11-28 04:06:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 76242944. Throughput: 0: 2652.7, 1: 2679.6. Samples: 76254504. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:48,445][86177] Avg episode reward: [(0, '-496.020'), (1, '-524.030')] -[2023-11-28 04:06:48,685][87424] Updated weights for policy 0, policy_version 149027 (0.0007) -[2023-11-28 04:06:49,078][87424] Updated weights for policy 0, policy_version 149037 (0.0008) -[2023-11-28 04:06:49,450][87424] Updated weights for policy 0, policy_version 149047 (0.0008) -[2023-11-28 04:06:50,577][87426] Updated weights for policy 1, policy_version 148810 (0.0010) -[2023-11-28 04:06:50,953][87426] Updated weights for policy 1, policy_version 148820 (0.0007) -[2023-11-28 04:06:51,332][87426] Updated weights for policy 1, policy_version 148830 (0.0008) -[2023-11-28 04:06:51,752][87424] Updated weights for policy 0, policy_version 149057 (0.0008) -[2023-11-28 04:06:52,141][87424] Updated weights for policy 0, policy_version 149067 (0.0009) -[2023-11-28 04:06:52,517][87424] Updated weights for policy 0, policy_version 149077 (0.0012) -[2023-11-28 04:06:52,898][87424] Updated weights for policy 0, policy_version 149087 (0.0012) -[2023-11-28 04:06:53,316][87426] Updated weights for policy 1, policy_version 148840 (0.0009) -[2023-11-28 04:06:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 76267520. Throughput: 0: 2669.2, 1: 2659.7. Samples: 76285388. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:53,445][86177] Avg episode reward: [(0, '-494.530'), (1, '-553.870')] -[2023-11-28 04:06:53,700][87426] Updated weights for policy 1, policy_version 148850 (0.0010) -[2023-11-28 04:06:54,080][87426] Updated weights for policy 1, policy_version 148860 (0.0007) -[2023-11-28 04:06:55,421][87424] Updated weights for policy 0, policy_version 149097 (0.0010) -[2023-11-28 04:06:55,807][87424] Updated weights for policy 0, policy_version 149107 (0.0008) -[2023-11-28 04:06:55,883][87426] Updated weights for policy 1, policy_version 148870 (0.0010) -[2023-11-28 04:06:56,182][87424] Updated weights for policy 0, policy_version 149117 (0.0011) -[2023-11-28 04:06:56,253][87426] Updated weights for policy 1, policy_version 148880 (0.0011) -[2023-11-28 04:06:56,632][87426] Updated weights for policy 1, policy_version 148890 (0.0011) -[2023-11-28 04:06:58,114][87424] Updated weights for policy 0, policy_version 149127 (0.0011) -[2023-11-28 04:06:58,413][87426] Updated weights for policy 1, policy_version 148900 (0.0011) -[2023-11-28 04:06:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 76292096. Throughput: 0: 2670.0, 1: 2679.9. Samples: 76310016. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:06:58,446][86177] Avg episode reward: [(0, '-495.240'), (1, '-552.190')] -[2023-11-28 04:06:58,490][87424] Updated weights for policy 0, policy_version 149137 (0.0011) -[2023-11-28 04:06:58,801][87426] Updated weights for policy 1, policy_version 148910 (0.0008) -[2023-11-28 04:06:58,873][87424] Updated weights for policy 0, policy_version 149147 (0.0012) -[2023-11-28 04:06:59,172][87426] Updated weights for policy 1, policy_version 148920 (0.0011) -[2023-11-28 04:07:00,900][87424] Updated weights for policy 0, policy_version 149157 (0.0012) -[2023-11-28 04:07:01,283][87424] Updated weights for policy 0, policy_version 149167 (0.0012) -[2023-11-28 04:07:01,341][87426] Updated weights for policy 1, policy_version 148930 (0.0011) -[2023-11-28 04:07:01,673][87424] Updated weights for policy 0, policy_version 149177 (0.0010) -[2023-11-28 04:07:01,713][87426] Updated weights for policy 1, policy_version 148940 (0.0010) -[2023-11-28 04:07:02,094][87426] Updated weights for policy 1, policy_version 148950 (0.0012) -[2023-11-28 04:07:02,480][87426] Updated weights for policy 1, policy_version 148960 (0.0012) -[2023-11-28 04:07:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 76324864. Throughput: 0: 2655.5, 1: 2679.6. Samples: 76334944. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:07:03,445][86177] Avg episode reward: [(0, '-492.850'), (1, '-544.020')] -[2023-11-28 04:07:04,060][87424] Updated weights for policy 0, policy_version 149187 (0.0010) -[2023-11-28 04:07:04,437][87424] Updated weights for policy 0, policy_version 149197 (0.0012) -[2023-11-28 04:07:04,567][87426] Updated weights for policy 1, policy_version 148970 (0.0011) -[2023-11-28 04:07:04,825][87424] Updated weights for policy 0, policy_version 149207 (0.0010) -[2023-11-28 04:07:04,967][87426] Updated weights for policy 1, policy_version 148980 (0.0011) -[2023-11-28 04:07:05,341][87426] Updated weights for policy 1, policy_version 148990 (0.0012) -[2023-11-28 04:07:07,188][87424] Updated weights for policy 0, policy_version 149217 (0.0010) -[2023-11-28 04:07:07,574][87424] Updated weights for policy 0, policy_version 149227 (0.0007) -[2023-11-28 04:07:07,763][87426] Updated weights for policy 1, policy_version 149000 (0.0010) -[2023-11-28 04:07:07,962][87424] Updated weights for policy 0, policy_version 149237 (0.0009) -[2023-11-28 04:07:08,144][87426] Updated weights for policy 1, policy_version 149010 (0.0010) -[2023-11-28 04:07:08,348][87424] Updated weights for policy 0, policy_version 149247 (0.0012) -[2023-11-28 04:07:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 76349440. Throughput: 0: 2691.1, 1: 2700.6. Samples: 76369184. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:07:08,445][86177] Avg episode reward: [(0, '-494.270'), (1, '-505.650')] -[2023-11-28 04:07:08,529][87426] Updated weights for policy 1, policy_version 149020 (0.0007) -[2023-11-28 04:07:10,127][87424] Updated weights for policy 0, policy_version 149257 (0.0011) -[2023-11-28 04:07:10,507][87424] Updated weights for policy 0, policy_version 149267 (0.0012) -[2023-11-28 04:07:10,889][87424] Updated weights for policy 0, policy_version 149277 (0.0012) -[2023-11-28 04:07:11,053][87426] Updated weights for policy 1, policy_version 149030 (0.0007) -[2023-11-28 04:07:11,421][87426] Updated weights for policy 1, policy_version 149040 (0.0007) -[2023-11-28 04:07:11,801][87426] Updated weights for policy 1, policy_version 149050 (0.0008) -[2023-11-28 04:07:12,739][87424] Updated weights for policy 0, policy_version 149287 (0.0009) -[2023-11-28 04:07:13,124][87424] Updated weights for policy 0, policy_version 149297 (0.0008) -[2023-11-28 04:07:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 76374016. Throughput: 0: 2686.0, 1: 2669.9. Samples: 76392924. Policy #0 lag: (min: 11.0, avg: 30.2, max: 43.0) -[2023-11-28 04:07:13,445][86177] Avg episode reward: [(0, '-493.900'), (1, '-512.170')] -[2023-11-28 04:07:13,504][87424] Updated weights for policy 0, policy_version 149307 (0.0012) -[2023-11-28 04:07:13,905][87426] Updated weights for policy 1, policy_version 149060 (0.0011) -[2023-11-28 04:07:14,286][87426] Updated weights for policy 1, policy_version 149070 (0.0011) -[2023-11-28 04:07:14,661][87426] Updated weights for policy 1, policy_version 149080 (0.0012) -[2023-11-28 04:07:15,517][87424] Updated weights for policy 0, policy_version 149317 (0.0012) -[2023-11-28 04:07:15,897][87424] Updated weights for policy 0, policy_version 149327 (0.0012) -[2023-11-28 04:07:16,287][87424] Updated weights for policy 0, policy_version 149337 (0.0012) -[2023-11-28 04:07:16,567][87426] Updated weights for policy 1, policy_version 149090 (0.0011) -[2023-11-28 04:07:16,948][87426] Updated weights for policy 1, policy_version 149100 (0.0011) -[2023-11-28 04:07:17,319][87426] Updated weights for policy 1, policy_version 149110 (0.0008) -[2023-11-28 04:07:17,701][87426] Updated weights for policy 1, policy_version 149120 (0.0007) -[2023-11-28 04:07:18,393][87424] Updated weights for policy 0, policy_version 149347 (0.0012) -[2023-11-28 04:07:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 76406784. Throughput: 0: 2707.5, 1: 2694.4. Samples: 76419232. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:07:18,446][86177] Avg episode reward: [(0, '-495.630'), (1, '-510.370')] -[2023-11-28 04:07:18,768][87424] Updated weights for policy 0, policy_version 149357 (0.0008) -[2023-11-28 04:07:19,149][87424] Updated weights for policy 0, policy_version 149367 (0.0008) -[2023-11-28 04:07:20,164][87426] Updated weights for policy 1, policy_version 149130 (0.0012) -[2023-11-28 04:07:20,530][87426] Updated weights for policy 1, policy_version 149140 (0.0012) -[2023-11-28 04:07:20,916][87426] Updated weights for policy 1, policy_version 149150 (0.0012) -[2023-11-28 04:07:21,518][87424] Updated weights for policy 0, policy_version 149377 (0.0012) -[2023-11-28 04:07:21,897][87424] Updated weights for policy 0, policy_version 149387 (0.0012) -[2023-11-28 04:07:22,278][87424] Updated weights for policy 0, policy_version 149397 (0.0012) -[2023-11-28 04:07:22,662][87424] Updated weights for policy 0, policy_version 149407 (0.0012) -[2023-11-28 04:07:23,234][87426] Updated weights for policy 1, policy_version 149160 (0.0008) -[2023-11-28 04:07:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 76431360. Throughput: 0: 2730.9, 1: 2678.3. Samples: 76450780. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:07:23,445][86177] Avg episode reward: [(0, '-497.280'), (1, '-517.220')] -[2023-11-28 04:07:23,604][87426] Updated weights for policy 1, policy_version 149170 (0.0007) -[2023-11-28 04:07:23,986][87426] Updated weights for policy 1, policy_version 149180 (0.0007) -[2023-11-28 04:07:25,229][87424] Updated weights for policy 0, policy_version 149417 (0.0010) -[2023-11-28 04:07:25,615][87424] Updated weights for policy 0, policy_version 149427 (0.0011) -[2023-11-28 04:07:25,983][87424] Updated weights for policy 0, policy_version 149437 (0.0012) -[2023-11-28 04:07:26,492][87426] Updated weights for policy 1, policy_version 149190 (0.0008) -[2023-11-28 04:07:26,873][87426] Updated weights for policy 1, policy_version 149200 (0.0007) -[2023-11-28 04:07:27,258][87426] Updated weights for policy 1, policy_version 149210 (0.0007) -[2023-11-28 04:07:27,963][87424] Updated weights for policy 0, policy_version 149447 (0.0008) -[2023-11-28 04:07:28,337][87424] Updated weights for policy 0, policy_version 149457 (0.0007) -[2023-11-28 04:07:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 76455936. Throughput: 0: 2714.3, 1: 2656.7. Samples: 76473172. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:07:28,445][86177] Avg episode reward: [(0, '-498.150'), (1, '-511.150')] -[2023-11-28 04:07:28,740][87424] Updated weights for policy 0, policy_version 149467 (0.0007) -[2023-11-28 04:07:29,715][87426] Updated weights for policy 1, policy_version 149220 (0.0010) -[2023-11-28 04:07:30,092][87426] Updated weights for policy 1, policy_version 149230 (0.0012) -[2023-11-28 04:07:30,472][87426] Updated weights for policy 1, policy_version 149240 (0.0011) -[2023-11-28 04:07:31,197][87424] Updated weights for policy 0, policy_version 149477 (0.0008) -[2023-11-28 04:07:31,592][87424] Updated weights for policy 0, policy_version 149487 (0.0008) -[2023-11-28 04:07:31,962][87424] Updated weights for policy 0, policy_version 149497 (0.0009) -[2023-11-28 04:07:32,533][87426] Updated weights for policy 1, policy_version 149250 (0.0012) -[2023-11-28 04:07:32,907][87426] Updated weights for policy 1, policy_version 149260 (0.0012) -[2023-11-28 04:07:33,287][87426] Updated weights for policy 1, policy_version 149270 (0.0010) -[2023-11-28 04:07:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 76480512. Throughput: 0: 2709.9, 1: 2661.0. Samples: 76496192. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:07:33,445][86177] Avg episode reward: [(0, '-498.810'), (1, '-499.910')] -[2023-11-28 04:07:33,667][87426] Updated weights for policy 1, policy_version 149280 (0.0007) -[2023-11-28 04:07:33,951][87424] Updated weights for policy 0, policy_version 149507 (0.0010) -[2023-11-28 04:07:34,336][87424] Updated weights for policy 0, policy_version 149517 (0.0007) -[2023-11-28 04:07:34,718][87424] Updated weights for policy 0, policy_version 149527 (0.0008) -[2023-11-28 04:07:35,864][87426] Updated weights for policy 1, policy_version 149290 (0.0011) -[2023-11-28 04:07:36,242][87426] Updated weights for policy 1, policy_version 149300 (0.0008) -[2023-11-28 04:07:36,375][87424] Updated weights for policy 0, policy_version 149537 (0.0012) -[2023-11-28 04:07:36,619][87426] Updated weights for policy 1, policy_version 149310 (0.0008) -[2023-11-28 04:07:36,754][87424] Updated weights for policy 0, policy_version 149547 (0.0011) -[2023-11-28 04:07:37,150][87424] Updated weights for policy 0, policy_version 149557 (0.0011) -[2023-11-28 04:07:37,530][87424] Updated weights for policy 0, policy_version 149567 (0.0011) -[2023-11-28 04:07:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 76513280. Throughput: 0: 2750.6, 1: 2666.0. Samples: 76529132. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:07:38,445][86177] Avg episode reward: [(0, '-499.400'), (1, '-510.070')] -[2023-11-28 04:07:38,689][87426] Updated weights for policy 1, policy_version 149320 (0.0008) -[2023-11-28 04:07:39,065][87426] Updated weights for policy 1, policy_version 149330 (0.0010) -[2023-11-28 04:07:39,449][87426] Updated weights for policy 1, policy_version 149340 (0.0011) -[2023-11-28 04:07:39,789][87424] Updated weights for policy 0, policy_version 149577 (0.0011) -[2023-11-28 04:07:40,164][87424] Updated weights for policy 0, policy_version 149587 (0.0011) -[2023-11-28 04:07:40,550][87424] Updated weights for policy 0, policy_version 149597 (0.0010) -[2023-11-28 04:07:41,769][87426] Updated weights for policy 1, policy_version 149350 (0.0011) -[2023-11-28 04:07:42,150][87426] Updated weights for policy 1, policy_version 149360 (0.0009) -[2023-11-28 04:07:42,531][87426] Updated weights for policy 1, policy_version 149370 (0.0009) -[2023-11-28 04:07:43,007][87424] Updated weights for policy 0, policy_version 149607 (0.0009) -[2023-11-28 04:07:43,372][87424] Updated weights for policy 0, policy_version 149617 (0.0011) -[2023-11-28 04:07:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 76537856. Throughput: 0: 2750.8, 1: 2662.9. Samples: 76553632. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:07:43,445][86177] Avg episode reward: [(0, '-501.560'), (1, '-526.690')] -[2023-11-28 04:07:43,757][87424] Updated weights for policy 0, policy_version 149627 (0.0008) -[2023-11-28 04:07:44,345][87426] Updated weights for policy 1, policy_version 149380 (0.0009) -[2023-11-28 04:07:44,735][87426] Updated weights for policy 1, policy_version 149390 (0.0007) -[2023-11-28 04:07:45,112][87426] Updated weights for policy 1, policy_version 149400 (0.0011) -[2023-11-28 04:07:45,790][87424] Updated weights for policy 0, policy_version 149637 (0.0008) -[2023-11-28 04:07:46,175][87424] Updated weights for policy 0, policy_version 149647 (0.0008) -[2023-11-28 04:07:46,542][87424] Updated weights for policy 0, policy_version 149657 (0.0008) -[2023-11-28 04:07:47,398][87426] Updated weights for policy 1, policy_version 149410 (0.0011) -[2023-11-28 04:07:47,767][87426] Updated weights for policy 1, policy_version 149420 (0.0011) -[2023-11-28 04:07:48,156][87426] Updated weights for policy 1, policy_version 149430 (0.0007) -[2023-11-28 04:07:48,255][87424] Updated weights for policy 0, policy_version 149667 (0.0008) -[2023-11-28 04:07:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 76562432. Throughput: 0: 2750.8, 1: 2666.8. Samples: 76578732. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:07:48,445][86177] Avg episode reward: [(0, '-512.410'), (1, '-529.410')] -[2023-11-28 04:07:48,532][87426] Updated weights for policy 1, policy_version 149440 (0.0007) -[2023-11-28 04:07:48,638][87424] Updated weights for policy 0, policy_version 149677 (0.0008) -[2023-11-28 04:07:49,021][87424] Updated weights for policy 0, policy_version 149687 (0.0008) -[2023-11-28 04:07:50,961][87426] Updated weights for policy 1, policy_version 149450 (0.0010) -[2023-11-28 04:07:51,329][87424] Updated weights for policy 0, policy_version 149697 (0.0008) -[2023-11-28 04:07:51,351][87426] Updated weights for policy 1, policy_version 149460 (0.0009) -[2023-11-28 04:07:51,702][87424] Updated weights for policy 0, policy_version 149707 (0.0011) -[2023-11-28 04:07:51,729][87426] Updated weights for policy 1, policy_version 149470 (0.0009) -[2023-11-28 04:07:52,089][87424] Updated weights for policy 0, policy_version 149717 (0.0012) -[2023-11-28 04:07:52,459][87424] Updated weights for policy 0, policy_version 149727 (0.0012) -[2023-11-28 04:07:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 76595200. Throughput: 0: 2700.0, 1: 2637.7. Samples: 76609380. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:07:53,445][86177] Avg episode reward: [(0, '-510.380'), (1, '-547.390')] -[2023-11-28 04:07:53,833][87426] Updated weights for policy 1, policy_version 149480 (0.0012) -[2023-11-28 04:07:54,217][87426] Updated weights for policy 1, policy_version 149490 (0.0012) -[2023-11-28 04:07:54,604][87426] Updated weights for policy 1, policy_version 149500 (0.0012) -[2023-11-28 04:07:54,906][87424] Updated weights for policy 0, policy_version 149737 (0.0012) -[2023-11-28 04:07:55,284][87424] Updated weights for policy 0, policy_version 149747 (0.0012) -[2023-11-28 04:07:55,683][87424] Updated weights for policy 0, policy_version 149757 (0.0012) -[2023-11-28 04:07:57,095][87426] Updated weights for policy 1, policy_version 149510 (0.0011) -[2023-11-28 04:07:57,466][87426] Updated weights for policy 1, policy_version 149520 (0.0012) -[2023-11-28 04:07:57,844][87426] Updated weights for policy 1, policy_version 149530 (0.0012) -[2023-11-28 04:07:57,865][87424] Updated weights for policy 0, policy_version 149767 (0.0012) -[2023-11-28 04:07:58,239][87424] Updated weights for policy 0, policy_version 149777 (0.0011) -[2023-11-28 04:07:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 76619776. Throughput: 0: 2703.8, 1: 2646.8. Samples: 76633704. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:07:58,445][86177] Avg episode reward: [(0, '-514.820'), (1, '-515.640')] -[2023-11-28 04:07:58,625][87424] Updated weights for policy 0, policy_version 149787 (0.0012) -[2023-11-28 04:08:00,305][87426] Updated weights for policy 1, policy_version 149540 (0.0011) -[2023-11-28 04:08:00,684][87426] Updated weights for policy 1, policy_version 149550 (0.0012) -[2023-11-28 04:08:00,832][87424] Updated weights for policy 0, policy_version 149797 (0.0011) -[2023-11-28 04:08:01,068][87426] Updated weights for policy 1, policy_version 149560 (0.0012) -[2023-11-28 04:08:01,216][87424] Updated weights for policy 0, policy_version 149807 (0.0008) -[2023-11-28 04:08:01,595][87424] Updated weights for policy 0, policy_version 149817 (0.0009) -[2023-11-28 04:08:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 76644352. Throughput: 0: 2676.6, 1: 2639.8. Samples: 76658472. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:08:03,445][86177] Avg episode reward: [(0, '-512.160'), (1, '-513.060')] -[2023-11-28 04:08:03,475][87426] Updated weights for policy 1, policy_version 149570 (0.0009) -[2023-11-28 04:08:03,558][87424] Updated weights for policy 0, policy_version 149827 (0.0010) -[2023-11-28 04:08:03,854][87426] Updated weights for policy 1, policy_version 149580 (0.0011) -[2023-11-28 04:08:03,941][87424] Updated weights for policy 0, policy_version 149837 (0.0007) -[2023-11-28 04:08:04,231][87426] Updated weights for policy 1, policy_version 149590 (0.0011) -[2023-11-28 04:08:04,324][87424] Updated weights for policy 0, policy_version 149847 (0.0007) -[2023-11-28 04:08:04,615][87426] Updated weights for policy 1, policy_version 149600 (0.0010) -[2023-11-28 04:08:06,482][87426] Updated weights for policy 1, policy_version 149610 (0.0012) -[2023-11-28 04:08:06,735][87424] Updated weights for policy 0, policy_version 149857 (0.0011) -[2023-11-28 04:08:06,855][87426] Updated weights for policy 1, policy_version 149620 (0.0009) -[2023-11-28 04:08:07,112][87424] Updated weights for policy 0, policy_version 149867 (0.0012) -[2023-11-28 04:08:07,225][87426] Updated weights for policy 1, policy_version 149630 (0.0011) -[2023-11-28 04:08:07,485][87424] Updated weights for policy 0, policy_version 149877 (0.0012) -[2023-11-28 04:08:07,869][87424] Updated weights for policy 0, policy_version 149887 (0.0012) -[2023-11-28 04:08:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 76677120. Throughput: 0: 2689.9, 1: 2653.1. Samples: 76691216. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:08:08,445][86177] Avg episode reward: [(0, '-502.010'), (1, '-539.320')] -[2023-11-28 04:08:09,398][87426] Updated weights for policy 1, policy_version 149640 (0.0011) -[2023-11-28 04:08:09,771][87426] Updated weights for policy 1, policy_version 149650 (0.0012) -[2023-11-28 04:08:09,834][87424] Updated weights for policy 0, policy_version 149897 (0.0010) -[2023-11-28 04:08:10,154][87426] Updated weights for policy 1, policy_version 149660 (0.0011) -[2023-11-28 04:08:10,215][87424] Updated weights for policy 0, policy_version 149907 (0.0011) -[2023-11-28 04:08:10,595][87424] Updated weights for policy 0, policy_version 149917 (0.0011) -[2023-11-28 04:08:11,914][87426] Updated weights for policy 1, policy_version 149670 (0.0012) -[2023-11-28 04:08:12,295][87426] Updated weights for policy 1, policy_version 149680 (0.0011) -[2023-11-28 04:08:12,675][87426] Updated weights for policy 1, policy_version 149690 (0.0010) -[2023-11-28 04:08:12,886][87424] Updated weights for policy 0, policy_version 149927 (0.0008) -[2023-11-28 04:08:13,267][87424] Updated weights for policy 0, policy_version 149937 (0.0008) -[2023-11-28 04:08:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 76701696. Throughput: 0: 2716.5, 1: 2677.2. Samples: 76715884. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:08:13,445][86177] Avg episode reward: [(0, '-499.990'), (1, '-523.300')] -[2023-11-28 04:08:13,646][87424] Updated weights for policy 0, policy_version 149947 (0.0008) -[2023-11-28 04:08:14,882][87426] Updated weights for policy 1, policy_version 149700 (0.0011) -[2023-11-28 04:08:15,275][87426] Updated weights for policy 1, policy_version 149710 (0.0011) -[2023-11-28 04:08:15,649][87426] Updated weights for policy 1, policy_version 149720 (0.0012) -[2023-11-28 04:08:16,145][87424] Updated weights for policy 0, policy_version 149957 (0.0009) -[2023-11-28 04:08:16,528][87424] Updated weights for policy 0, policy_version 149967 (0.0011) -[2023-11-28 04:08:16,897][87424] Updated weights for policy 0, policy_version 149977 (0.0010) -[2023-11-28 04:08:17,782][87426] Updated weights for policy 1, policy_version 149730 (0.0011) -[2023-11-28 04:08:18,176][87426] Updated weights for policy 1, policy_version 149740 (0.0012) -[2023-11-28 04:08:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 76726272. Throughput: 0: 2726.6, 1: 2700.5. Samples: 76740412. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 04:08:18,445][86177] Avg episode reward: [(0, '-493.210'), (1, '-524.930')] -[2023-11-28 04:08:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000149984_38395904.pth... -[2023-11-28 04:08:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000147488_37756928.pth -[2023-11-28 04:08:18,555][87426] Updated weights for policy 1, policy_version 149750 (0.0012) -[2023-11-28 04:08:18,745][87424] Updated weights for policy 0, policy_version 149987 (0.0008) -[2023-11-28 04:08:18,928][87426] Updated weights for policy 1, policy_version 149760 (0.0010) -[2023-11-28 04:08:18,928][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000149760_38338560.pth... -[2023-11-28 04:08:18,975][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000147200_37683200.pth -[2023-11-28 04:08:19,130][87424] Updated weights for policy 0, policy_version 149997 (0.0011) -[2023-11-28 04:08:19,511][87424] Updated weights for policy 0, policy_version 150007 (0.0011) -[2023-11-28 04:08:21,038][87426] Updated weights for policy 1, policy_version 149770 (0.0008) -[2023-11-28 04:08:21,414][87426] Updated weights for policy 1, policy_version 149780 (0.0009) -[2023-11-28 04:08:21,789][87426] Updated weights for policy 1, policy_version 149790 (0.0010) -[2023-11-28 04:08:21,942][87424] Updated weights for policy 0, policy_version 150017 (0.0009) -[2023-11-28 04:08:22,318][87424] Updated weights for policy 0, policy_version 150027 (0.0012) -[2023-11-28 04:08:22,693][87424] Updated weights for policy 0, policy_version 150037 (0.0012) -[2023-11-28 04:08:23,074][87424] Updated weights for policy 0, policy_version 150047 (0.0011) -[2023-11-28 04:08:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 76759040. Throughput: 0: 2697.5, 1: 2725.4. Samples: 76773164. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:08:23,445][86177] Avg episode reward: [(0, '-492.130'), (1, '-516.970')] -[2023-11-28 04:08:24,035][87426] Updated weights for policy 1, policy_version 149800 (0.0011) -[2023-11-28 04:08:24,423][87426] Updated weights for policy 1, policy_version 149810 (0.0012) -[2023-11-28 04:08:24,796][87426] Updated weights for policy 1, policy_version 149820 (0.0012) -[2023-11-28 04:08:25,132][87424] Updated weights for policy 0, policy_version 150057 (0.0008) -[2023-11-28 04:08:25,513][87424] Updated weights for policy 0, policy_version 150067 (0.0008) -[2023-11-28 04:08:25,895][87424] Updated weights for policy 0, policy_version 150077 (0.0007) -[2023-11-28 04:08:27,180][87426] Updated weights for policy 1, policy_version 149830 (0.0012) -[2023-11-28 04:08:27,563][87426] Updated weights for policy 1, policy_version 149840 (0.0010) -[2023-11-28 04:08:27,800][87424] Updated weights for policy 0, policy_version 150087 (0.0010) -[2023-11-28 04:08:27,939][87426] Updated weights for policy 1, policy_version 149850 (0.0009) -[2023-11-28 04:08:28,180][87424] Updated weights for policy 0, policy_version 150097 (0.0007) -[2023-11-28 04:08:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 76783616. Throughput: 0: 2703.6, 1: 2708.0. Samples: 76797156. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:08:28,445][86177] Avg episode reward: [(0, '-490.720'), (1, '-521.390')] -[2023-11-28 04:08:28,564][87424] Updated weights for policy 0, policy_version 150107 (0.0009) -[2023-11-28 04:08:30,218][87426] Updated weights for policy 1, policy_version 149860 (0.0011) -[2023-11-28 04:08:30,495][87424] Updated weights for policy 0, policy_version 150117 (0.0009) -[2023-11-28 04:08:30,596][87426] Updated weights for policy 1, policy_version 149870 (0.0011) -[2023-11-28 04:08:30,876][87424] Updated weights for policy 0, policy_version 150127 (0.0008) -[2023-11-28 04:08:30,980][87426] Updated weights for policy 1, policy_version 149880 (0.0011) -[2023-11-28 04:08:31,261][87424] Updated weights for policy 0, policy_version 150137 (0.0008) -[2023-11-28 04:08:33,005][87426] Updated weights for policy 1, policy_version 149890 (0.0012) -[2023-11-28 04:08:33,315][87424] Updated weights for policy 0, policy_version 150147 (0.0009) -[2023-11-28 04:08:33,383][87426] Updated weights for policy 1, policy_version 149900 (0.0008) -[2023-11-28 04:08:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 76808192. Throughput: 0: 2735.0, 1: 2689.5. Samples: 76822836. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:08:33,445][86177] Avg episode reward: [(0, '-494.400'), (1, '-519.180')] -[2023-11-28 04:08:33,696][87424] Updated weights for policy 0, policy_version 150157 (0.0009) -[2023-11-28 04:08:33,764][87426] Updated weights for policy 1, policy_version 149910 (0.0010) -[2023-11-28 04:08:34,076][87424] Updated weights for policy 0, policy_version 150167 (0.0011) -[2023-11-28 04:08:34,143][87426] Updated weights for policy 1, policy_version 149920 (0.0012) -[2023-11-28 04:08:36,151][87424] Updated weights for policy 0, policy_version 150177 (0.0011) -[2023-11-28 04:08:36,339][87426] Updated weights for policy 1, policy_version 149930 (0.0010) -[2023-11-28 04:08:36,542][87424] Updated weights for policy 0, policy_version 150187 (0.0010) -[2023-11-28 04:08:36,714][87426] Updated weights for policy 1, policy_version 149940 (0.0012) -[2023-11-28 04:08:36,925][87424] Updated weights for policy 0, policy_version 150197 (0.0012) -[2023-11-28 04:08:37,086][87426] Updated weights for policy 1, policy_version 149950 (0.0011) -[2023-11-28 04:08:37,312][87424] Updated weights for policy 0, policy_version 150207 (0.0011) -[2023-11-28 04:08:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 76840960. Throughput: 0: 2761.0, 1: 2706.1. Samples: 76855400. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:08:38,445][86177] Avg episode reward: [(0, '-496.380'), (1, '-526.220')] -[2023-11-28 04:08:39,052][87424] Updated weights for policy 0, policy_version 150217 (0.0011) -[2023-11-28 04:08:39,438][87424] Updated weights for policy 0, policy_version 150227 (0.0008) -[2023-11-28 04:08:39,638][87426] Updated weights for policy 1, policy_version 149960 (0.0011) -[2023-11-28 04:08:39,821][87424] Updated weights for policy 0, policy_version 150237 (0.0011) -[2023-11-28 04:08:40,020][87426] Updated weights for policy 1, policy_version 149970 (0.0010) -[2023-11-28 04:08:40,403][87426] Updated weights for policy 1, policy_version 149980 (0.0010) -[2023-11-28 04:08:42,282][87424] Updated weights for policy 0, policy_version 150247 (0.0012) -[2023-11-28 04:08:42,327][87426] Updated weights for policy 1, policy_version 149990 (0.0010) -[2023-11-28 04:08:42,669][87424] Updated weights for policy 0, policy_version 150257 (0.0011) -[2023-11-28 04:08:42,703][87426] Updated weights for policy 1, policy_version 150000 (0.0011) -[2023-11-28 04:08:43,050][87424] Updated weights for policy 0, policy_version 150267 (0.0011) -[2023-11-28 04:08:43,083][87426] Updated weights for policy 1, policy_version 150010 (0.0011) -[2023-11-28 04:08:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 76873728. Throughput: 0: 2770.4, 1: 2715.4. Samples: 76880564. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:08:43,445][86177] Avg episode reward: [(0, '-499.810'), (1, '-504.690')] -[2023-11-28 04:08:45,483][87426] Updated weights for policy 1, policy_version 150020 (0.0011) -[2023-11-28 04:08:45,639][87424] Updated weights for policy 0, policy_version 150277 (0.0012) -[2023-11-28 04:08:45,867][87426] Updated weights for policy 1, policy_version 150030 (0.0009) -[2023-11-28 04:08:46,024][87424] Updated weights for policy 0, policy_version 150287 (0.0011) -[2023-11-28 04:08:46,243][87426] Updated weights for policy 1, policy_version 150040 (0.0009) -[2023-11-28 04:08:46,416][87424] Updated weights for policy 0, policy_version 150297 (0.0012) -[2023-11-28 04:08:47,912][87426] Updated weights for policy 1, policy_version 150050 (0.0009) -[2023-11-28 04:08:48,177][87424] Updated weights for policy 0, policy_version 150307 (0.0011) -[2023-11-28 04:08:48,288][87426] Updated weights for policy 1, policy_version 150060 (0.0012) -[2023-11-28 04:08:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 76890112. Throughput: 0: 2769.7, 1: 2714.6. Samples: 76905264. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:08:48,445][86177] Avg episode reward: [(0, '-495.060'), (1, '-514.010')] -[2023-11-28 04:08:48,554][87424] Updated weights for policy 0, policy_version 150317 (0.0008) -[2023-11-28 04:08:48,669][87426] Updated weights for policy 1, policy_version 150070 (0.0010) -[2023-11-28 04:08:48,935][87424] Updated weights for policy 0, policy_version 150327 (0.0010) -[2023-11-28 04:08:49,047][87426] Updated weights for policy 1, policy_version 150080 (0.0009) -[2023-11-28 04:08:51,370][87424] Updated weights for policy 0, policy_version 150337 (0.0008) -[2023-11-28 04:08:51,528][87426] Updated weights for policy 1, policy_version 150090 (0.0013) -[2023-11-28 04:08:51,769][87424] Updated weights for policy 0, policy_version 150347 (0.0012) -[2023-11-28 04:08:51,907][87426] Updated weights for policy 1, policy_version 150100 (0.0010) -[2023-11-28 04:08:52,142][87424] Updated weights for policy 0, policy_version 150357 (0.0011) -[2023-11-28 04:08:52,281][87426] Updated weights for policy 1, policy_version 150110 (0.0012) -[2023-11-28 04:08:52,531][87424] Updated weights for policy 0, policy_version 150367 (0.0008) -[2023-11-28 04:08:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 76922880. Throughput: 0: 2763.0, 1: 2731.1. Samples: 76938452. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:08:53,445][86177] Avg episode reward: [(0, '-497.940'), (1, '-510.660')] -[2023-11-28 04:08:54,487][87426] Updated weights for policy 1, policy_version 150120 (0.0012) -[2023-11-28 04:08:54,858][87424] Updated weights for policy 0, policy_version 150377 (0.0007) -[2023-11-28 04:08:54,869][87426] Updated weights for policy 1, policy_version 150130 (0.0011) -[2023-11-28 04:08:55,242][87424] Updated weights for policy 0, policy_version 150387 (0.0011) -[2023-11-28 04:08:55,252][87426] Updated weights for policy 1, policy_version 150140 (0.0012) -[2023-11-28 04:08:55,626][87424] Updated weights for policy 0, policy_version 150397 (0.0012) -[2023-11-28 04:08:57,230][87426] Updated weights for policy 1, policy_version 150150 (0.0012) -[2023-11-28 04:08:57,585][87424] Updated weights for policy 0, policy_version 150407 (0.0011) -[2023-11-28 04:08:57,607][87426] Updated weights for policy 1, policy_version 150160 (0.0012) -[2023-11-28 04:08:57,968][87424] Updated weights for policy 0, policy_version 150417 (0.0012) -[2023-11-28 04:08:57,996][87426] Updated weights for policy 1, policy_version 150170 (0.0011) -[2023-11-28 04:08:58,348][87424] Updated weights for policy 0, policy_version 150427 (0.0012) -[2023-11-28 04:08:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 76947456. Throughput: 0: 2756.3, 1: 2738.5. Samples: 76963152. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:08:58,445][86177] Avg episode reward: [(0, '-490.790'), (1, '-507.920')] -[2023-11-28 04:09:00,120][87426] Updated weights for policy 1, policy_version 150180 (0.0009) -[2023-11-28 04:09:00,375][87424] Updated weights for policy 0, policy_version 150437 (0.0010) -[2023-11-28 04:09:00,502][87426] Updated weights for policy 1, policy_version 150190 (0.0010) -[2023-11-28 04:09:00,756][87424] Updated weights for policy 0, policy_version 150447 (0.0011) -[2023-11-28 04:09:00,879][87426] Updated weights for policy 1, policy_version 150200 (0.0008) -[2023-11-28 04:09:01,135][87424] Updated weights for policy 0, policy_version 150457 (0.0009) -[2023-11-28 04:09:03,128][87424] Updated weights for policy 0, policy_version 150467 (0.0009) -[2023-11-28 04:09:03,363][87426] Updated weights for policy 1, policy_version 150210 (0.0008) -[2023-11-28 04:09:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 76972032. Throughput: 0: 2779.4, 1: 2724.8. Samples: 76988100. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:09:03,445][86177] Avg episode reward: [(0, '-490.820'), (1, '-505.240')] -[2023-11-28 04:09:03,512][87424] Updated weights for policy 0, policy_version 150477 (0.0012) -[2023-11-28 04:09:03,732][87426] Updated weights for policy 1, policy_version 150220 (0.0007) -[2023-11-28 04:09:03,892][87424] Updated weights for policy 0, policy_version 150487 (0.0011) -[2023-11-28 04:09:04,115][87426] Updated weights for policy 1, policy_version 150230 (0.0008) -[2023-11-28 04:09:04,497][87426] Updated weights for policy 1, policy_version 150240 (0.0009) -[2023-11-28 04:09:05,964][87424] Updated weights for policy 0, policy_version 150497 (0.0008) -[2023-11-28 04:09:06,311][87426] Updated weights for policy 1, policy_version 150250 (0.0011) -[2023-11-28 04:09:06,343][87424] Updated weights for policy 0, policy_version 150507 (0.0010) -[2023-11-28 04:09:06,685][87426] Updated weights for policy 1, policy_version 150260 (0.0011) -[2023-11-28 04:09:06,730][87424] Updated weights for policy 0, policy_version 150517 (0.0008) -[2023-11-28 04:09:07,067][87426] Updated weights for policy 1, policy_version 150270 (0.0008) -[2023-11-28 04:09:07,102][87424] Updated weights for policy 0, policy_version 150527 (0.0008) -[2023-11-28 04:09:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 77004800. Throughput: 0: 2793.6, 1: 2713.4. Samples: 77020980. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:09:08,445][86177] Avg episode reward: [(0, '-491.290'), (1, '-493.420')] -[2023-11-28 04:09:08,806][87426] Updated weights for policy 1, policy_version 150280 (0.0008) -[2023-11-28 04:09:09,134][87424] Updated weights for policy 0, policy_version 150537 (0.0008) -[2023-11-28 04:09:09,186][87426] Updated weights for policy 1, policy_version 150290 (0.0010) -[2023-11-28 04:09:09,516][87424] Updated weights for policy 0, policy_version 150547 (0.0011) -[2023-11-28 04:09:09,564][87426] Updated weights for policy 1, policy_version 150300 (0.0011) -[2023-11-28 04:09:09,897][87424] Updated weights for policy 0, policy_version 150557 (0.0012) -[2023-11-28 04:09:11,894][87426] Updated weights for policy 1, policy_version 150310 (0.0011) -[2023-11-28 04:09:12,275][87426] Updated weights for policy 1, policy_version 150320 (0.0014) -[2023-11-28 04:09:12,479][87424] Updated weights for policy 0, policy_version 150567 (0.0011) -[2023-11-28 04:09:12,651][87426] Updated weights for policy 1, policy_version 150330 (0.0011) -[2023-11-28 04:09:12,858][87424] Updated weights for policy 0, policy_version 150577 (0.0011) -[2023-11-28 04:09:13,246][87424] Updated weights for policy 0, policy_version 150587 (0.0012) -[2023-11-28 04:09:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 77037568. Throughput: 0: 2794.2, 1: 2708.8. Samples: 77044792. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:09:13,445][86177] Avg episode reward: [(0, '-489.070'), (1, '-494.680')] -[2023-11-28 04:09:15,201][87426] Updated weights for policy 1, policy_version 150340 (0.0011) -[2023-11-28 04:09:15,273][87424] Updated weights for policy 0, policy_version 150597 (0.0012) -[2023-11-28 04:09:15,580][87426] Updated weights for policy 1, policy_version 150350 (0.0011) -[2023-11-28 04:09:15,653][87424] Updated weights for policy 0, policy_version 150607 (0.0008) -[2023-11-28 04:09:15,961][87426] Updated weights for policy 1, policy_version 150360 (0.0010) -[2023-11-28 04:09:16,041][87424] Updated weights for policy 0, policy_version 150617 (0.0009) -[2023-11-28 04:09:17,838][87424] Updated weights for policy 0, policy_version 150627 (0.0008) -[2023-11-28 04:09:18,223][87424] Updated weights for policy 0, policy_version 150637 (0.0007) -[2023-11-28 04:09:18,347][87426] Updated weights for policy 1, policy_version 150370 (0.0011) -[2023-11-28 04:09:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 77053952. Throughput: 0: 2761.6, 1: 2701.7. Samples: 77068684. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:09:18,445][86177] Avg episode reward: [(0, '-490.580'), (1, '-505.610')] -[2023-11-28 04:09:18,609][87424] Updated weights for policy 0, policy_version 150647 (0.0010) -[2023-11-28 04:09:18,720][87426] Updated weights for policy 1, policy_version 150380 (0.0010) -[2023-11-28 04:09:19,099][87426] Updated weights for policy 1, policy_version 150390 (0.0008) -[2023-11-28 04:09:19,479][87426] Updated weights for policy 1, policy_version 150400 (0.0008) -[2023-11-28 04:09:20,774][87424] Updated weights for policy 0, policy_version 150657 (0.0011) -[2023-11-28 04:09:21,169][87424] Updated weights for policy 0, policy_version 150667 (0.0012) -[2023-11-28 04:09:21,542][87424] Updated weights for policy 0, policy_version 150677 (0.0011) -[2023-11-28 04:09:21,851][87426] Updated weights for policy 1, policy_version 150410 (0.0009) -[2023-11-28 04:09:21,929][87424] Updated weights for policy 0, policy_version 150687 (0.0011) -[2023-11-28 04:09:22,229][87426] Updated weights for policy 1, policy_version 150420 (0.0011) -[2023-11-28 04:09:22,612][87426] Updated weights for policy 1, policy_version 150430 (0.0011) -[2023-11-28 04:09:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 77086720. Throughput: 0: 2750.0, 1: 2694.7. Samples: 77100408. Policy #0 lag: (min: 36.0, avg: 52.1, max: 77.0) -[2023-11-28 04:09:23,445][86177] Avg episode reward: [(0, '-491.810'), (1, '-508.300')] -[2023-11-28 04:09:24,374][87424] Updated weights for policy 0, policy_version 150697 (0.0012) -[2023-11-28 04:09:24,527][87426] Updated weights for policy 1, policy_version 150440 (0.0011) -[2023-11-28 04:09:24,747][87424] Updated weights for policy 0, policy_version 150707 (0.0012) -[2023-11-28 04:09:24,910][87426] Updated weights for policy 1, policy_version 150450 (0.0009) -[2023-11-28 04:09:25,129][87424] Updated weights for policy 0, policy_version 150717 (0.0012) -[2023-11-28 04:09:25,289][87426] Updated weights for policy 1, policy_version 150460 (0.0008) -[2023-11-28 04:09:26,849][87424] Updated weights for policy 0, policy_version 150727 (0.0012) -[2023-11-28 04:09:27,228][87424] Updated weights for policy 0, policy_version 150737 (0.0012) -[2023-11-28 04:09:27,473][87426] Updated weights for policy 1, policy_version 150470 (0.0008) -[2023-11-28 04:09:27,611][87424] Updated weights for policy 0, policy_version 150747 (0.0012) -[2023-11-28 04:09:27,855][87426] Updated weights for policy 1, policy_version 150480 (0.0008) -[2023-11-28 04:09:28,240][87426] Updated weights for policy 1, policy_version 150490 (0.0007) -[2023-11-28 04:09:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 77111296. Throughput: 0: 2743.6, 1: 2706.8. Samples: 77125832. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:09:28,445][86177] Avg episode reward: [(0, '-492.320'), (1, '-509.300')] -[2023-11-28 04:09:29,716][87424] Updated weights for policy 0, policy_version 150757 (0.0012) -[2023-11-28 04:09:30,093][87424] Updated weights for policy 0, policy_version 150767 (0.0008) -[2023-11-28 04:09:30,475][87424] Updated weights for policy 0, policy_version 150777 (0.0009) -[2023-11-28 04:09:30,627][87426] Updated weights for policy 1, policy_version 150500 (0.0009) -[2023-11-28 04:09:31,005][87426] Updated weights for policy 1, policy_version 150510 (0.0012) -[2023-11-28 04:09:31,386][87426] Updated weights for policy 1, policy_version 150520 (0.0011) -[2023-11-28 04:09:32,826][87424] Updated weights for policy 0, policy_version 150787 (0.0009) -[2023-11-28 04:09:33,210][87424] Updated weights for policy 0, policy_version 150797 (0.0012) -[2023-11-28 04:09:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 77135872. Throughput: 0: 2753.2, 1: 2695.0. Samples: 77150436. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:09:33,445][86177] Avg episode reward: [(0, '-491.170'), (1, '-510.500')] -[2023-11-28 04:09:33,591][87424] Updated weights for policy 0, policy_version 150807 (0.0012) -[2023-11-28 04:09:33,763][87426] Updated weights for policy 1, policy_version 150530 (0.0011) -[2023-11-28 04:09:34,148][87426] Updated weights for policy 1, policy_version 150540 (0.0012) -[2023-11-28 04:09:34,526][87426] Updated weights for policy 1, policy_version 150550 (0.0012) -[2023-11-28 04:09:34,904][87426] Updated weights for policy 1, policy_version 150560 (0.0012) -[2023-11-28 04:09:35,777][87424] Updated weights for policy 0, policy_version 150817 (0.0009) -[2023-11-28 04:09:36,172][87424] Updated weights for policy 0, policy_version 150827 (0.0008) -[2023-11-28 04:09:36,560][87424] Updated weights for policy 0, policy_version 150837 (0.0008) -[2023-11-28 04:09:36,940][87424] Updated weights for policy 0, policy_version 150847 (0.0009) -[2023-11-28 04:09:36,975][87426] Updated weights for policy 1, policy_version 150570 (0.0010) -[2023-11-28 04:09:37,353][87426] Updated weights for policy 1, policy_version 150580 (0.0008) -[2023-11-28 04:09:37,735][87426] Updated weights for policy 1, policy_version 150590 (0.0008) -[2023-11-28 04:09:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 77168640. Throughput: 0: 2747.5, 1: 2696.6. Samples: 77183436. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:09:38,445][86177] Avg episode reward: [(0, '-492.010'), (1, '-501.580')] -[2023-11-28 04:09:39,204][87424] Updated weights for policy 0, policy_version 150857 (0.0011) -[2023-11-28 04:09:39,584][87424] Updated weights for policy 0, policy_version 150867 (0.0012) -[2023-11-28 04:09:39,880][87426] Updated weights for policy 1, policy_version 150600 (0.0009) -[2023-11-28 04:09:39,967][87424] Updated weights for policy 0, policy_version 150877 (0.0010) -[2023-11-28 04:09:40,264][87426] Updated weights for policy 1, policy_version 150610 (0.0012) -[2023-11-28 04:09:40,637][87426] Updated weights for policy 1, policy_version 150620 (0.0011) -[2023-11-28 04:09:42,340][87424] Updated weights for policy 0, policy_version 150887 (0.0010) -[2023-11-28 04:09:42,726][87424] Updated weights for policy 0, policy_version 150897 (0.0011) -[2023-11-28 04:09:43,050][87426] Updated weights for policy 1, policy_version 150630 (0.0010) -[2023-11-28 04:09:43,104][87424] Updated weights for policy 0, policy_version 150907 (0.0011) -[2023-11-28 04:09:43,435][87426] Updated weights for policy 1, policy_version 150640 (0.0012) -[2023-11-28 04:09:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77193216. Throughput: 0: 2744.5, 1: 2689.3. Samples: 77207672. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:09:43,445][86177] Avg episode reward: [(0, '-489.160'), (1, '-500.750')] -[2023-11-28 04:09:43,812][87426] Updated weights for policy 1, policy_version 150650 (0.0012) -[2023-11-28 04:09:45,270][87424] Updated weights for policy 0, policy_version 150917 (0.0010) -[2023-11-28 04:09:45,655][87424] Updated weights for policy 0, policy_version 150927 (0.0011) -[2023-11-28 04:09:45,951][87426] Updated weights for policy 1, policy_version 150660 (0.0012) -[2023-11-28 04:09:46,046][87424] Updated weights for policy 0, policy_version 150937 (0.0011) -[2023-11-28 04:09:46,334][87426] Updated weights for policy 1, policy_version 150670 (0.0009) -[2023-11-28 04:09:46,702][87426] Updated weights for policy 1, policy_version 150680 (0.0012) -[2023-11-28 04:09:47,854][87424] Updated weights for policy 0, policy_version 150947 (0.0010) -[2023-11-28 04:09:48,246][87424] Updated weights for policy 0, policy_version 150957 (0.0011) -[2023-11-28 04:09:48,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 77217792. Throughput: 0: 2739.0, 1: 2689.3. Samples: 77232376. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:09:48,446][86177] Avg episode reward: [(0, '-490.290'), (1, '-501.020')] -[2023-11-28 04:09:48,632][87424] Updated weights for policy 0, policy_version 150967 (0.0009) -[2023-11-28 04:09:49,246][87426] Updated weights for policy 1, policy_version 150690 (0.0011) -[2023-11-28 04:09:49,619][87426] Updated weights for policy 1, policy_version 150700 (0.0007) -[2023-11-28 04:09:50,010][87426] Updated weights for policy 1, policy_version 150710 (0.0010) -[2023-11-28 04:09:50,388][87426] Updated weights for policy 1, policy_version 150720 (0.0009) -[2023-11-28 04:09:50,727][87424] Updated weights for policy 0, policy_version 150977 (0.0010) -[2023-11-28 04:09:51,108][87424] Updated weights for policy 0, policy_version 150987 (0.0009) -[2023-11-28 04:09:51,491][87424] Updated weights for policy 0, policy_version 150997 (0.0011) -[2023-11-28 04:09:51,873][87424] Updated weights for policy 0, policy_version 151007 (0.0009) -[2023-11-28 04:09:52,867][87426] Updated weights for policy 1, policy_version 150730 (0.0011) -[2023-11-28 04:09:53,248][87426] Updated weights for policy 1, policy_version 150740 (0.0011) -[2023-11-28 04:09:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77242368. Throughput: 0: 2746.0, 1: 2654.7. Samples: 77264012. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:09:53,445][86177] Avg episode reward: [(0, '-494.910'), (1, '-507.970')] -[2023-11-28 04:09:53,647][87426] Updated weights for policy 1, policy_version 150750 (0.0010) -[2023-11-28 04:09:53,958][87424] Updated weights for policy 0, policy_version 151017 (0.0011) -[2023-11-28 04:09:54,343][87424] Updated weights for policy 0, policy_version 151027 (0.0012) -[2023-11-28 04:09:54,730][87424] Updated weights for policy 0, policy_version 151037 (0.0012) -[2023-11-28 04:09:55,482][87426] Updated weights for policy 1, policy_version 150760 (0.0010) -[2023-11-28 04:09:55,861][87426] Updated weights for policy 1, policy_version 150770 (0.0011) -[2023-11-28 04:09:56,251][87426] Updated weights for policy 1, policy_version 150780 (0.0008) -[2023-11-28 04:09:56,624][87424] Updated weights for policy 0, policy_version 151047 (0.0012) -[2023-11-28 04:09:57,004][87424] Updated weights for policy 0, policy_version 151057 (0.0012) -[2023-11-28 04:09:57,392][87424] Updated weights for policy 0, policy_version 151067 (0.0012) -[2023-11-28 04:09:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 77275136. Throughput: 0: 2752.1, 1: 2657.2. Samples: 77288208. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:09:58,445][86177] Avg episode reward: [(0, '-495.190'), (1, '-516.840')] -[2023-11-28 04:09:58,623][87426] Updated weights for policy 1, policy_version 150790 (0.0008) -[2023-11-28 04:09:58,995][87426] Updated weights for policy 1, policy_version 150800 (0.0010) -[2023-11-28 04:09:59,385][87426] Updated weights for policy 1, policy_version 150810 (0.0011) -[2023-11-28 04:09:59,422][87424] Updated weights for policy 0, policy_version 151077 (0.0012) -[2023-11-28 04:09:59,803][87424] Updated weights for policy 0, policy_version 151087 (0.0011) -[2023-11-28 04:10:00,186][87424] Updated weights for policy 0, policy_version 151097 (0.0011) -[2023-11-28 04:10:01,951][87426] Updated weights for policy 1, policy_version 150820 (0.0011) -[2023-11-28 04:10:02,333][87426] Updated weights for policy 1, policy_version 150830 (0.0009) -[2023-11-28 04:10:02,586][87424] Updated weights for policy 0, policy_version 151107 (0.0010) -[2023-11-28 04:10:02,708][87426] Updated weights for policy 1, policy_version 150840 (0.0011) -[2023-11-28 04:10:02,961][87424] Updated weights for policy 0, policy_version 151117 (0.0008) -[2023-11-28 04:10:03,347][87424] Updated weights for policy 0, policy_version 151127 (0.0008) -[2023-11-28 04:10:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 77299712. Throughput: 0: 2771.9, 1: 2651.0. Samples: 77312716. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:10:03,445][86177] Avg episode reward: [(0, '-495.200'), (1, '-521.570')] -[2023-11-28 04:10:05,186][87426] Updated weights for policy 1, policy_version 150850 (0.0013) -[2023-11-28 04:10:05,565][87426] Updated weights for policy 1, policy_version 150860 (0.0011) -[2023-11-28 04:10:05,806][87424] Updated weights for policy 0, policy_version 151137 (0.0008) -[2023-11-28 04:10:05,934][87426] Updated weights for policy 1, policy_version 150870 (0.0011) -[2023-11-28 04:10:06,187][87424] Updated weights for policy 0, policy_version 151147 (0.0012) -[2023-11-28 04:10:06,312][87426] Updated weights for policy 1, policy_version 150880 (0.0012) -[2023-11-28 04:10:06,563][87424] Updated weights for policy 0, policy_version 151157 (0.0012) -[2023-11-28 04:10:06,950][87424] Updated weights for policy 0, policy_version 151167 (0.0011) -[2023-11-28 04:10:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77324288. Throughput: 0: 2781.8, 1: 2620.9. Samples: 77343528. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:10:08,445][86177] Avg episode reward: [(0, '-495.020'), (1, '-527.150')] -[2023-11-28 04:10:08,757][87426] Updated weights for policy 1, policy_version 150890 (0.0009) -[2023-11-28 04:10:08,776][87424] Updated weights for policy 0, policy_version 151177 (0.0010) -[2023-11-28 04:10:09,135][87426] Updated weights for policy 1, policy_version 150900 (0.0011) -[2023-11-28 04:10:09,149][87424] Updated weights for policy 0, policy_version 151187 (0.0011) -[2023-11-28 04:10:09,516][87426] Updated weights for policy 1, policy_version 150910 (0.0011) -[2023-11-28 04:10:09,530][87424] Updated weights for policy 0, policy_version 151197 (0.0012) -[2023-11-28 04:10:11,416][87424] Updated weights for policy 0, policy_version 151207 (0.0009) -[2023-11-28 04:10:11,802][87424] Updated weights for policy 0, policy_version 151217 (0.0010) -[2023-11-28 04:10:11,824][87426] Updated weights for policy 1, policy_version 150920 (0.0010) -[2023-11-28 04:10:12,197][87424] Updated weights for policy 0, policy_version 151227 (0.0010) -[2023-11-28 04:10:12,200][87426] Updated weights for policy 1, policy_version 150930 (0.0014) -[2023-11-28 04:10:12,584][87426] Updated weights for policy 1, policy_version 150940 (0.0012) -[2023-11-28 04:10:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77357056. Throughput: 0: 2785.5, 1: 2583.6. Samples: 77367444. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:10:13,445][86177] Avg episode reward: [(0, '-494.410'), (1, '-516.860')] -[2023-11-28 04:10:14,056][87424] Updated weights for policy 0, policy_version 151237 (0.0011) -[2023-11-28 04:10:14,436][87424] Updated weights for policy 0, policy_version 151247 (0.0012) -[2023-11-28 04:10:14,822][87424] Updated weights for policy 0, policy_version 151257 (0.0012) -[2023-11-28 04:10:15,157][87426] Updated weights for policy 1, policy_version 150950 (0.0012) -[2023-11-28 04:10:15,538][87426] Updated weights for policy 1, policy_version 150960 (0.0008) -[2023-11-28 04:10:15,914][87426] Updated weights for policy 1, policy_version 150970 (0.0008) -[2023-11-28 04:10:16,996][87424] Updated weights for policy 0, policy_version 151267 (0.0010) -[2023-11-28 04:10:17,367][87424] Updated weights for policy 0, policy_version 151277 (0.0008) -[2023-11-28 04:10:17,751][87424] Updated weights for policy 0, policy_version 151287 (0.0011) -[2023-11-28 04:10:18,371][87426] Updated weights for policy 1, policy_version 150980 (0.0011) -[2023-11-28 04:10:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 77381632. Throughput: 0: 2787.5, 1: 2585.5. Samples: 77392220. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:10:18,445][86177] Avg episode reward: [(0, '-495.380'), (1, '-507.170')] -[2023-11-28 04:10:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000151296_38731776.pth... -[2023-11-28 04:10:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000148736_38076416.pth -[2023-11-28 04:10:18,753][87426] Updated weights for policy 1, policy_version 150990 (0.0010) -[2023-11-28 04:10:19,154][87426] Updated weights for policy 1, policy_version 151000 (0.0010) -[2023-11-28 04:10:19,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000151008_38658048.pth... -[2023-11-28 04:10:19,499][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000148512_38019072.pth -[2023-11-28 04:10:20,079][87424] Updated weights for policy 0, policy_version 151297 (0.0011) -[2023-11-28 04:10:20,463][87424] Updated weights for policy 0, policy_version 151307 (0.0012) -[2023-11-28 04:10:20,844][87424] Updated weights for policy 0, policy_version 151317 (0.0012) -[2023-11-28 04:10:21,224][87424] Updated weights for policy 0, policy_version 151327 (0.0012) -[2023-11-28 04:10:21,300][87426] Updated weights for policy 1, policy_version 151010 (0.0011) -[2023-11-28 04:10:21,680][87426] Updated weights for policy 1, policy_version 151020 (0.0012) -[2023-11-28 04:10:22,063][87426] Updated weights for policy 1, policy_version 151030 (0.0009) -[2023-11-28 04:10:22,449][87426] Updated weights for policy 1, policy_version 151040 (0.0011) -[2023-11-28 04:10:23,176][87424] Updated weights for policy 0, policy_version 151337 (0.0008) -[2023-11-28 04:10:23,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 77406208. Throughput: 0: 2800.7, 1: 2579.5. Samples: 77425544. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:10:23,446][86177] Avg episode reward: [(0, '-496.340'), (1, '-511.260')] -[2023-11-28 04:10:23,558][87424] Updated weights for policy 0, policy_version 151347 (0.0007) -[2023-11-28 04:10:23,962][87424] Updated weights for policy 0, policy_version 151357 (0.0009) -[2023-11-28 04:10:24,507][87426] Updated weights for policy 1, policy_version 151050 (0.0008) -[2023-11-28 04:10:24,888][87426] Updated weights for policy 1, policy_version 151060 (0.0008) -[2023-11-28 04:10:25,274][87426] Updated weights for policy 1, policy_version 151070 (0.0008) -[2023-11-28 04:10:26,143][87424] Updated weights for policy 0, policy_version 151367 (0.0011) -[2023-11-28 04:10:26,520][87424] Updated weights for policy 0, policy_version 151377 (0.0010) -[2023-11-28 04:10:26,816][87426] Updated weights for policy 1, policy_version 151080 (0.0007) -[2023-11-28 04:10:26,904][87424] Updated weights for policy 0, policy_version 151387 (0.0007) -[2023-11-28 04:10:27,195][87426] Updated weights for policy 1, policy_version 151090 (0.0008) -[2023-11-28 04:10:27,573][87426] Updated weights for policy 1, policy_version 151100 (0.0007) -[2023-11-28 04:10:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 77438976. Throughput: 0: 2809.4, 1: 2579.3. Samples: 77450164. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:10:28,446][86177] Avg episode reward: [(0, '-494.250'), (1, '-517.930')] -[2023-11-28 04:10:28,786][87424] Updated weights for policy 0, policy_version 151397 (0.0009) -[2023-11-28 04:10:29,165][87424] Updated weights for policy 0, policy_version 151407 (0.0012) -[2023-11-28 04:10:29,559][87424] Updated weights for policy 0, policy_version 151417 (0.0012) -[2023-11-28 04:10:29,964][87426] Updated weights for policy 1, policy_version 151110 (0.0010) -[2023-11-28 04:10:30,337][87426] Updated weights for policy 1, policy_version 151120 (0.0012) -[2023-11-28 04:10:30,718][87426] Updated weights for policy 1, policy_version 151130 (0.0012) -[2023-11-28 04:10:31,499][87424] Updated weights for policy 0, policy_version 151427 (0.0011) -[2023-11-28 04:10:31,880][87424] Updated weights for policy 0, policy_version 151437 (0.0011) -[2023-11-28 04:10:32,270][87424] Updated weights for policy 0, policy_version 151447 (0.0015) -[2023-11-28 04:10:32,849][87426] Updated weights for policy 1, policy_version 151140 (0.0012) -[2023-11-28 04:10:33,223][87426] Updated weights for policy 1, policy_version 151150 (0.0011) -[2023-11-28 04:10:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 77463552. Throughput: 0: 2816.5, 1: 2580.5. Samples: 77475240. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:10:33,445][86177] Avg episode reward: [(0, '-499.570'), (1, '-521.830')] -[2023-11-28 04:10:33,605][87426] Updated weights for policy 1, policy_version 151160 (0.0011) -[2023-11-28 04:10:34,419][87424] Updated weights for policy 0, policy_version 151457 (0.0013) -[2023-11-28 04:10:34,800][87424] Updated weights for policy 0, policy_version 151467 (0.0012) -[2023-11-28 04:10:35,180][87424] Updated weights for policy 0, policy_version 151477 (0.0009) -[2023-11-28 04:10:35,566][87424] Updated weights for policy 0, policy_version 151487 (0.0012) -[2023-11-28 04:10:35,903][87426] Updated weights for policy 1, policy_version 151170 (0.0010) -[2023-11-28 04:10:36,282][87426] Updated weights for policy 1, policy_version 151180 (0.0007) -[2023-11-28 04:10:36,668][87426] Updated weights for policy 1, policy_version 151190 (0.0008) -[2023-11-28 04:10:37,040][87426] Updated weights for policy 1, policy_version 151200 (0.0010) -[2023-11-28 04:10:37,880][87424] Updated weights for policy 0, policy_version 151497 (0.0011) -[2023-11-28 04:10:38,251][87424] Updated weights for policy 0, policy_version 151507 (0.0012) -[2023-11-28 04:10:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77488128. Throughput: 0: 2804.4, 1: 2631.2. Samples: 77508616. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:10:38,445][86177] Avg episode reward: [(0, '-504.840'), (1, '-524.070')] -[2023-11-28 04:10:38,631][87424] Updated weights for policy 0, policy_version 151517 (0.0012) -[2023-11-28 04:10:39,392][87426] Updated weights for policy 1, policy_version 151210 (0.0012) -[2023-11-28 04:10:39,764][87426] Updated weights for policy 1, policy_version 151220 (0.0012) -[2023-11-28 04:10:40,138][87426] Updated weights for policy 1, policy_version 151230 (0.0012) -[2023-11-28 04:10:41,054][87424] Updated weights for policy 0, policy_version 151527 (0.0012) -[2023-11-28 04:10:41,433][87424] Updated weights for policy 0, policy_version 151537 (0.0012) -[2023-11-28 04:10:41,818][87424] Updated weights for policy 0, policy_version 151547 (0.0012) -[2023-11-28 04:10:42,374][87426] Updated weights for policy 1, policy_version 151240 (0.0010) -[2023-11-28 04:10:42,753][87426] Updated weights for policy 1, policy_version 151250 (0.0007) -[2023-11-28 04:10:43,133][87426] Updated weights for policy 1, policy_version 151260 (0.0009) -[2023-11-28 04:10:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 77520896. Throughput: 0: 2808.6, 1: 2628.4. Samples: 77532872. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:10:43,445][86177] Avg episode reward: [(0, '-505.730'), (1, '-519.800')] -[2023-11-28 04:10:43,927][87424] Updated weights for policy 0, policy_version 151557 (0.0012) -[2023-11-28 04:10:44,303][87424] Updated weights for policy 0, policy_version 151567 (0.0012) -[2023-11-28 04:10:44,684][87424] Updated weights for policy 0, policy_version 151577 (0.0012) -[2023-11-28 04:10:45,012][87426] Updated weights for policy 1, policy_version 151270 (0.0011) -[2023-11-28 04:10:45,391][87426] Updated weights for policy 1, policy_version 151280 (0.0007) -[2023-11-28 04:10:45,780][87426] Updated weights for policy 1, policy_version 151290 (0.0008) -[2023-11-28 04:10:46,857][87424] Updated weights for policy 0, policy_version 151587 (0.0010) -[2023-11-28 04:10:47,246][87424] Updated weights for policy 0, policy_version 151597 (0.0007) -[2023-11-28 04:10:47,631][87424] Updated weights for policy 0, policy_version 151607 (0.0007) -[2023-11-28 04:10:48,025][87426] Updated weights for policy 1, policy_version 151300 (0.0008) -[2023-11-28 04:10:48,397][87426] Updated weights for policy 1, policy_version 151310 (0.0007) -[2023-11-28 04:10:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 77545472. Throughput: 0: 2798.7, 1: 2648.8. Samples: 77557856. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:10:48,445][86177] Avg episode reward: [(0, '-507.790'), (1, '-509.170')] -[2023-11-28 04:10:48,779][87426] Updated weights for policy 1, policy_version 151320 (0.0010) -[2023-11-28 04:10:49,556][87424] Updated weights for policy 0, policy_version 151617 (0.0008) -[2023-11-28 04:10:49,944][87424] Updated weights for policy 0, policy_version 151627 (0.0010) -[2023-11-28 04:10:50,323][87424] Updated weights for policy 0, policy_version 151637 (0.0012) -[2023-11-28 04:10:50,694][87424] Updated weights for policy 0, policy_version 151647 (0.0011) -[2023-11-28 04:10:50,777][87426] Updated weights for policy 1, policy_version 151330 (0.0011) -[2023-11-28 04:10:51,152][87426] Updated weights for policy 1, policy_version 151340 (0.0009) -[2023-11-28 04:10:51,534][87426] Updated weights for policy 1, policy_version 151350 (0.0007) -[2023-11-28 04:10:51,916][87426] Updated weights for policy 1, policy_version 151360 (0.0010) -[2023-11-28 04:10:53,034][87424] Updated weights for policy 0, policy_version 151657 (0.0009) -[2023-11-28 04:10:53,426][87424] Updated weights for policy 0, policy_version 151667 (0.0010) -[2023-11-28 04:10:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 77570048. Throughput: 0: 2802.5, 1: 2666.4. Samples: 77589628. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:10:53,445][86177] Avg episode reward: [(0, '-499.430'), (1, '-511.950')] -[2023-11-28 04:10:53,814][87424] Updated weights for policy 0, policy_version 151677 (0.0010) -[2023-11-28 04:10:54,294][87426] Updated weights for policy 1, policy_version 151370 (0.0007) -[2023-11-28 04:10:54,667][87426] Updated weights for policy 1, policy_version 151380 (0.0007) -[2023-11-28 04:10:55,053][87426] Updated weights for policy 1, policy_version 151390 (0.0008) -[2023-11-28 04:10:55,923][87424] Updated weights for policy 0, policy_version 151687 (0.0011) -[2023-11-28 04:10:56,325][87424] Updated weights for policy 0, policy_version 151697 (0.0012) -[2023-11-28 04:10:56,703][87424] Updated weights for policy 0, policy_version 151707 (0.0011) -[2023-11-28 04:10:57,416][87426] Updated weights for policy 1, policy_version 151400 (0.0009) -[2023-11-28 04:10:57,790][87426] Updated weights for policy 1, policy_version 151410 (0.0007) -[2023-11-28 04:10:58,170][87426] Updated weights for policy 1, policy_version 151420 (0.0008) -[2023-11-28 04:10:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 77602816. Throughput: 0: 2788.5, 1: 2689.5. Samples: 77613956. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:10:58,445][86177] Avg episode reward: [(0, '-495.430'), (1, '-510.660')] -[2023-11-28 04:10:58,794][87424] Updated weights for policy 0, policy_version 151717 (0.0011) -[2023-11-28 04:10:59,193][87424] Updated weights for policy 0, policy_version 151727 (0.0007) -[2023-11-28 04:10:59,579][87424] Updated weights for policy 0, policy_version 151737 (0.0007) -[2023-11-28 04:11:00,667][87426] Updated weights for policy 1, policy_version 151430 (0.0010) -[2023-11-28 04:11:01,036][87426] Updated weights for policy 1, policy_version 151440 (0.0011) -[2023-11-28 04:11:01,416][87426] Updated weights for policy 1, policy_version 151450 (0.0012) -[2023-11-28 04:11:01,972][87424] Updated weights for policy 0, policy_version 151747 (0.0009) -[2023-11-28 04:11:02,358][87424] Updated weights for policy 0, policy_version 151757 (0.0011) -[2023-11-28 04:11:02,737][87424] Updated weights for policy 0, policy_version 151767 (0.0012) -[2023-11-28 04:11:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 77627392. Throughput: 0: 2772.4, 1: 2672.3. Samples: 77637228. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:11:03,445][86177] Avg episode reward: [(0, '-494.910'), (1, '-505.770')] -[2023-11-28 04:11:04,001][87426] Updated weights for policy 1, policy_version 151460 (0.0012) -[2023-11-28 04:11:04,373][87426] Updated weights for policy 1, policy_version 151470 (0.0012) -[2023-11-28 04:11:04,752][87426] Updated weights for policy 1, policy_version 151480 (0.0010) -[2023-11-28 04:11:05,338][87424] Updated weights for policy 0, policy_version 151777 (0.0011) -[2023-11-28 04:11:05,717][87424] Updated weights for policy 0, policy_version 151787 (0.0008) -[2023-11-28 04:11:06,095][87424] Updated weights for policy 0, policy_version 151797 (0.0008) -[2023-11-28 04:11:06,479][87424] Updated weights for policy 0, policy_version 151807 (0.0008) -[2023-11-28 04:11:06,725][87426] Updated weights for policy 1, policy_version 151490 (0.0009) -[2023-11-28 04:11:07,108][87426] Updated weights for policy 1, policy_version 151500 (0.0011) -[2023-11-28 04:11:07,483][87426] Updated weights for policy 1, policy_version 151510 (0.0010) -[2023-11-28 04:11:07,864][87426] Updated weights for policy 1, policy_version 151520 (0.0007) -[2023-11-28 04:11:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 77651968. Throughput: 0: 2715.8, 1: 2676.0. Samples: 77668176. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:11:08,445][86177] Avg episode reward: [(0, '-497.690'), (1, '-523.360')] -[2023-11-28 04:11:09,016][87424] Updated weights for policy 0, policy_version 151817 (0.0010) -[2023-11-28 04:11:09,394][87424] Updated weights for policy 0, policy_version 151827 (0.0011) -[2023-11-28 04:11:09,773][87424] Updated weights for policy 0, policy_version 151837 (0.0010) -[2023-11-28 04:11:10,329][87426] Updated weights for policy 1, policy_version 151530 (0.0012) -[2023-11-28 04:11:10,711][87426] Updated weights for policy 1, policy_version 151540 (0.0011) -[2023-11-28 04:11:11,091][87426] Updated weights for policy 1, policy_version 151550 (0.0011) -[2023-11-28 04:11:11,764][87424] Updated weights for policy 0, policy_version 151847 (0.0009) -[2023-11-28 04:11:12,141][87424] Updated weights for policy 0, policy_version 151857 (0.0009) -[2023-11-28 04:11:12,525][87424] Updated weights for policy 0, policy_version 151867 (0.0009) -[2023-11-28 04:11:13,163][87426] Updated weights for policy 1, policy_version 151560 (0.0012) -[2023-11-28 04:11:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77676544. Throughput: 0: 2702.3, 1: 2661.0. Samples: 77691512. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:11:13,445][86177] Avg episode reward: [(0, '-498.980'), (1, '-519.290')] -[2023-11-28 04:11:13,546][87426] Updated weights for policy 1, policy_version 151570 (0.0011) -[2023-11-28 04:11:13,918][87426] Updated weights for policy 1, policy_version 151580 (0.0007) -[2023-11-28 04:11:14,568][87424] Updated weights for policy 0, policy_version 151877 (0.0008) -[2023-11-28 04:11:14,949][87424] Updated weights for policy 0, policy_version 151887 (0.0009) -[2023-11-28 04:11:15,329][87424] Updated weights for policy 0, policy_version 151897 (0.0011) -[2023-11-28 04:11:16,363][87426] Updated weights for policy 1, policy_version 151590 (0.0010) -[2023-11-28 04:11:16,742][87426] Updated weights for policy 1, policy_version 151600 (0.0012) -[2023-11-28 04:11:17,125][87426] Updated weights for policy 1, policy_version 151610 (0.0012) -[2023-11-28 04:11:17,379][87424] Updated weights for policy 0, policy_version 151907 (0.0011) -[2023-11-28 04:11:17,770][87424] Updated weights for policy 0, policy_version 151917 (0.0010) -[2023-11-28 04:11:18,161][87424] Updated weights for policy 0, policy_version 151927 (0.0010) -[2023-11-28 04:11:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 77701120. Throughput: 0: 2674.9, 1: 2663.7. Samples: 77715480. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:11:18,445][86177] Avg episode reward: [(0, '-499.590'), (1, '-520.440')] -[2023-11-28 04:11:18,929][87426] Updated weights for policy 1, policy_version 151620 (0.0011) -[2023-11-28 04:11:19,313][87426] Updated weights for policy 1, policy_version 151630 (0.0012) -[2023-11-28 04:11:19,688][87426] Updated weights for policy 1, policy_version 151640 (0.0010) -[2023-11-28 04:11:20,675][87424] Updated weights for policy 0, policy_version 151937 (0.0011) -[2023-11-28 04:11:21,058][87424] Updated weights for policy 0, policy_version 151947 (0.0010) -[2023-11-28 04:11:21,443][87424] Updated weights for policy 0, policy_version 151957 (0.0008) -[2023-11-28 04:11:21,833][87424] Updated weights for policy 0, policy_version 151967 (0.0008) -[2023-11-28 04:11:22,078][87426] Updated weights for policy 1, policy_version 151650 (0.0011) -[2023-11-28 04:11:22,457][87426] Updated weights for policy 1, policy_version 151660 (0.0018) -[2023-11-28 04:11:22,835][87426] Updated weights for policy 1, policy_version 151670 (0.0010) -[2023-11-28 04:11:23,214][87426] Updated weights for policy 1, policy_version 151680 (0.0010) -[2023-11-28 04:11:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 77733888. Throughput: 0: 2667.1, 1: 2645.9. Samples: 77747700. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:11:23,445][86177] Avg episode reward: [(0, '-498.790'), (1, '-521.420')] -[2023-11-28 04:11:23,939][87424] Updated weights for policy 0, policy_version 151977 (0.0011) -[2023-11-28 04:11:24,326][87424] Updated weights for policy 0, policy_version 151987 (0.0011) -[2023-11-28 04:11:24,716][87424] Updated weights for policy 0, policy_version 151997 (0.0012) -[2023-11-28 04:11:25,801][87426] Updated weights for policy 1, policy_version 151690 (0.0012) -[2023-11-28 04:11:26,173][87426] Updated weights for policy 1, policy_version 151700 (0.0010) -[2023-11-28 04:11:26,553][87426] Updated weights for policy 1, policy_version 151710 (0.0009) -[2023-11-28 04:11:26,736][87424] Updated weights for policy 0, policy_version 152007 (0.0012) -[2023-11-28 04:11:27,115][87424] Updated weights for policy 0, policy_version 152017 (0.0011) -[2023-11-28 04:11:27,492][87424] Updated weights for policy 0, policy_version 152027 (0.0012) -[2023-11-28 04:11:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77758464. Throughput: 0: 2660.9, 1: 2656.4. Samples: 77772148. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:11:28,445][86177] Avg episode reward: [(0, '-495.310'), (1, '-498.070')] -[2023-11-28 04:11:28,848][87426] Updated weights for policy 1, policy_version 151720 (0.0008) -[2023-11-28 04:11:29,224][87426] Updated weights for policy 1, policy_version 151730 (0.0009) -[2023-11-28 04:11:29,602][87426] Updated weights for policy 1, policy_version 151740 (0.0007) -[2023-11-28 04:11:29,653][87424] Updated weights for policy 0, policy_version 152037 (0.0012) -[2023-11-28 04:11:30,045][87424] Updated weights for policy 0, policy_version 152047 (0.0010) -[2023-11-28 04:11:30,425][87424] Updated weights for policy 0, policy_version 152057 (0.0007) -[2023-11-28 04:11:31,909][87426] Updated weights for policy 1, policy_version 151750 (0.0010) -[2023-11-28 04:11:32,283][87426] Updated weights for policy 1, policy_version 151760 (0.0012) -[2023-11-28 04:11:32,667][87426] Updated weights for policy 1, policy_version 151770 (0.0012) -[2023-11-28 04:11:32,893][87424] Updated weights for policy 0, policy_version 152067 (0.0009) -[2023-11-28 04:11:33,266][87424] Updated weights for policy 0, policy_version 152077 (0.0012) -[2023-11-28 04:11:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 77783040. Throughput: 0: 2662.7, 1: 2640.0. Samples: 77796476. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 04:11:33,445][86177] Avg episode reward: [(0, '-498.600'), (1, '-507.850')] -[2023-11-28 04:11:33,650][87424] Updated weights for policy 0, policy_version 152087 (0.0012) -[2023-11-28 04:11:34,556][87426] Updated weights for policy 1, policy_version 151780 (0.0010) -[2023-11-28 04:11:34,941][87426] Updated weights for policy 1, policy_version 151790 (0.0011) -[2023-11-28 04:11:35,315][87426] Updated weights for policy 1, policy_version 151800 (0.0010) -[2023-11-28 04:11:36,141][87424] Updated weights for policy 0, policy_version 152097 (0.0007) -[2023-11-28 04:11:36,524][87424] Updated weights for policy 0, policy_version 152107 (0.0007) -[2023-11-28 04:11:36,915][87424] Updated weights for policy 0, policy_version 152117 (0.0010) -[2023-11-28 04:11:37,289][87424] Updated weights for policy 0, policy_version 152127 (0.0008) -[2023-11-28 04:11:37,604][87426] Updated weights for policy 1, policy_version 151810 (0.0009) -[2023-11-28 04:11:37,979][87426] Updated weights for policy 1, policy_version 151820 (0.0011) -[2023-11-28 04:11:38,363][87426] Updated weights for policy 1, policy_version 151830 (0.0010) -[2023-11-28 04:11:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 77807616. Throughput: 0: 2642.4, 1: 2674.4. Samples: 77828884. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:11:38,445][86177] Avg episode reward: [(0, '-498.860'), (1, '-504.840')] -[2023-11-28 04:11:38,742][87426] Updated weights for policy 1, policy_version 151840 (0.0012) -[2023-11-28 04:11:39,177][87424] Updated weights for policy 0, policy_version 152137 (0.0008) -[2023-11-28 04:11:39,562][87424] Updated weights for policy 0, policy_version 152147 (0.0010) -[2023-11-28 04:11:39,939][87424] Updated weights for policy 0, policy_version 152157 (0.0011) -[2023-11-28 04:11:40,852][87426] Updated weights for policy 1, policy_version 151850 (0.0010) -[2023-11-28 04:11:41,229][87426] Updated weights for policy 1, policy_version 151860 (0.0010) -[2023-11-28 04:11:41,618][87426] Updated weights for policy 1, policy_version 151870 (0.0008) -[2023-11-28 04:11:42,274][87424] Updated weights for policy 0, policy_version 152167 (0.0010) -[2023-11-28 04:11:42,653][87424] Updated weights for policy 0, policy_version 152177 (0.0010) -[2023-11-28 04:11:43,032][87424] Updated weights for policy 0, policy_version 152187 (0.0012) -[2023-11-28 04:11:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77840384. Throughput: 0: 2650.1, 1: 2670.8. Samples: 77853400. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:11:43,445][86177] Avg episode reward: [(0, '-498.480'), (1, '-504.700')] -[2023-11-28 04:11:43,829][87426] Updated weights for policy 1, policy_version 151880 (0.0008) -[2023-11-28 04:11:44,209][87426] Updated weights for policy 1, policy_version 151890 (0.0008) -[2023-11-28 04:11:44,593][87426] Updated weights for policy 1, policy_version 151900 (0.0008) -[2023-11-28 04:11:44,820][87424] Updated weights for policy 0, policy_version 152197 (0.0012) -[2023-11-28 04:11:45,203][87424] Updated weights for policy 0, policy_version 152207 (0.0010) -[2023-11-28 04:11:45,578][87424] Updated weights for policy 0, policy_version 152217 (0.0009) -[2023-11-28 04:11:47,057][87426] Updated weights for policy 1, policy_version 151910 (0.0011) -[2023-11-28 04:11:47,429][87426] Updated weights for policy 1, policy_version 151920 (0.0011) -[2023-11-28 04:11:47,505][87424] Updated weights for policy 0, policy_version 152227 (0.0012) -[2023-11-28 04:11:47,808][87426] Updated weights for policy 1, policy_version 151930 (0.0009) -[2023-11-28 04:11:47,875][87424] Updated weights for policy 0, policy_version 152237 (0.0011) -[2023-11-28 04:11:48,261][87424] Updated weights for policy 0, policy_version 152247 (0.0016) -[2023-11-28 04:11:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 77864960. Throughput: 0: 2651.6, 1: 2677.2. Samples: 77877020. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:11:48,445][86177] Avg episode reward: [(0, '-506.510'), (1, '-510.760')] -[2023-11-28 04:11:49,745][87426] Updated weights for policy 1, policy_version 151940 (0.0010) -[2023-11-28 04:11:50,119][87426] Updated weights for policy 1, policy_version 151950 (0.0009) -[2023-11-28 04:11:50,502][87426] Updated weights for policy 1, policy_version 151960 (0.0009) -[2023-11-28 04:11:50,523][87424] Updated weights for policy 0, policy_version 152257 (0.0012) -[2023-11-28 04:11:50,902][87424] Updated weights for policy 0, policy_version 152267 (0.0012) -[2023-11-28 04:11:51,293][87424] Updated weights for policy 0, policy_version 152277 (0.0010) -[2023-11-28 04:11:51,683][87424] Updated weights for policy 0, policy_version 152287 (0.0009) -[2023-11-28 04:11:52,389][87426] Updated weights for policy 1, policy_version 151970 (0.0008) -[2023-11-28 04:11:52,767][87426] Updated weights for policy 1, policy_version 151980 (0.0007) -[2023-11-28 04:11:53,160][87426] Updated weights for policy 1, policy_version 151990 (0.0008) -[2023-11-28 04:11:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77889536. Throughput: 0: 2688.4, 1: 2691.3. Samples: 77910264. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:11:53,445][86177] Avg episode reward: [(0, '-504.200'), (1, '-508.940')] -[2023-11-28 04:11:53,531][87426] Updated weights for policy 1, policy_version 152000 (0.0011) -[2023-11-28 04:11:54,191][87424] Updated weights for policy 0, policy_version 152297 (0.0011) -[2023-11-28 04:11:54,572][87424] Updated weights for policy 0, policy_version 152307 (0.0010) -[2023-11-28 04:11:54,951][87424] Updated weights for policy 0, policy_version 152317 (0.0008) -[2023-11-28 04:11:55,344][87426] Updated weights for policy 1, policy_version 152010 (0.0009) -[2023-11-28 04:11:55,722][87426] Updated weights for policy 1, policy_version 152020 (0.0007) -[2023-11-28 04:11:56,104][87426] Updated weights for policy 1, policy_version 152030 (0.0010) -[2023-11-28 04:11:56,678][87424] Updated weights for policy 0, policy_version 152327 (0.0007) -[2023-11-28 04:11:57,056][87424] Updated weights for policy 0, policy_version 152337 (0.0008) -[2023-11-28 04:11:57,445][87424] Updated weights for policy 0, policy_version 152347 (0.0007) -[2023-11-28 04:11:58,249][87426] Updated weights for policy 1, policy_version 152040 (0.0009) -[2023-11-28 04:11:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 77922304. Throughput: 0: 2692.5, 1: 2739.5. Samples: 77935952. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:11:58,445][86177] Avg episode reward: [(0, '-497.680'), (1, '-509.360')] -[2023-11-28 04:11:58,640][87426] Updated weights for policy 1, policy_version 152050 (0.0009) -[2023-11-28 04:11:59,023][87426] Updated weights for policy 1, policy_version 152060 (0.0008) -[2023-11-28 04:11:59,958][87424] Updated weights for policy 0, policy_version 152357 (0.0010) -[2023-11-28 04:12:00,329][87424] Updated weights for policy 0, policy_version 152367 (0.0010) -[2023-11-28 04:12:00,720][87424] Updated weights for policy 0, policy_version 152377 (0.0008) -[2023-11-28 04:12:01,072][87426] Updated weights for policy 1, policy_version 152070 (0.0009) -[2023-11-28 04:12:01,442][87426] Updated weights for policy 1, policy_version 152080 (0.0012) -[2023-11-28 04:12:01,829][87426] Updated weights for policy 1, policy_version 152090 (0.0010) -[2023-11-28 04:12:02,974][87424] Updated weights for policy 0, policy_version 152387 (0.0010) -[2023-11-28 04:12:03,357][87424] Updated weights for policy 0, policy_version 152397 (0.0008) -[2023-11-28 04:12:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 77946880. Throughput: 0: 2676.9, 1: 2749.9. Samples: 77959688. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:12:03,445][86177] Avg episode reward: [(0, '-499.210'), (1, '-508.580')] -[2023-11-28 04:12:03,736][87424] Updated weights for policy 0, policy_version 152407 (0.0008) -[2023-11-28 04:12:03,989][87426] Updated weights for policy 1, policy_version 152100 (0.0009) -[2023-11-28 04:12:04,368][87426] Updated weights for policy 1, policy_version 152110 (0.0012) -[2023-11-28 04:12:04,752][87426] Updated weights for policy 1, policy_version 152120 (0.0012) -[2023-11-28 04:12:06,104][87424] Updated weights for policy 0, policy_version 152417 (0.0008) -[2023-11-28 04:12:06,480][87424] Updated weights for policy 0, policy_version 152427 (0.0012) -[2023-11-28 04:12:06,736][87426] Updated weights for policy 1, policy_version 152130 (0.0012) -[2023-11-28 04:12:06,861][87424] Updated weights for policy 0, policy_version 152437 (0.0012) -[2023-11-28 04:12:07,113][87426] Updated weights for policy 1, policy_version 152140 (0.0011) -[2023-11-28 04:12:07,241][87424] Updated weights for policy 0, policy_version 152447 (0.0011) -[2023-11-28 04:12:07,491][87426] Updated weights for policy 1, policy_version 152150 (0.0011) -[2023-11-28 04:12:07,866][87426] Updated weights for policy 1, policy_version 152160 (0.0010) -[2023-11-28 04:12:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 77979648. Throughput: 0: 2677.2, 1: 2762.1. Samples: 77992472. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:12:08,445][86177] Avg episode reward: [(0, '-489.340'), (1, '-520.490')] -[2023-11-28 04:12:09,540][87424] Updated weights for policy 0, policy_version 152457 (0.0010) -[2023-11-28 04:12:09,926][87424] Updated weights for policy 0, policy_version 152467 (0.0012) -[2023-11-28 04:12:10,127][87426] Updated weights for policy 1, policy_version 152170 (0.0011) -[2023-11-28 04:12:10,310][87424] Updated weights for policy 0, policy_version 152477 (0.0012) -[2023-11-28 04:12:10,504][87426] Updated weights for policy 1, policy_version 152180 (0.0011) -[2023-11-28 04:12:10,882][87426] Updated weights for policy 1, policy_version 152190 (0.0009) -[2023-11-28 04:12:12,492][87424] Updated weights for policy 0, policy_version 152487 (0.0012) -[2023-11-28 04:12:12,869][87424] Updated weights for policy 0, policy_version 152497 (0.0009) -[2023-11-28 04:12:12,914][87426] Updated weights for policy 1, policy_version 152200 (0.0011) -[2023-11-28 04:12:13,254][87424] Updated weights for policy 0, policy_version 152507 (0.0010) -[2023-11-28 04:12:13,292][87426] Updated weights for policy 1, policy_version 152210 (0.0011) -[2023-11-28 04:12:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 78004224. Throughput: 0: 2674.9, 1: 2758.5. Samples: 78016652. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:12:13,445][86177] Avg episode reward: [(0, '-491.940'), (1, '-515.740')] -[2023-11-28 04:12:13,678][87426] Updated weights for policy 1, policy_version 152220 (0.0012) -[2023-11-28 04:12:15,545][87424] Updated weights for policy 0, policy_version 152517 (0.0012) -[2023-11-28 04:12:15,927][87424] Updated weights for policy 0, policy_version 152527 (0.0012) -[2023-11-28 04:12:16,249][87426] Updated weights for policy 1, policy_version 152230 (0.0012) -[2023-11-28 04:12:16,304][87424] Updated weights for policy 0, policy_version 152537 (0.0012) -[2023-11-28 04:12:16,622][87426] Updated weights for policy 1, policy_version 152240 (0.0009) -[2023-11-28 04:12:17,001][87426] Updated weights for policy 1, policy_version 152250 (0.0010) -[2023-11-28 04:12:18,291][87424] Updated weights for policy 0, policy_version 152547 (0.0008) -[2023-11-28 04:12:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 78028800. Throughput: 0: 2682.2, 1: 2777.6. Samples: 78042168. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:12:18,445][86177] Avg episode reward: [(0, '-491.360'), (1, '-523.640')] -[2023-11-28 04:12:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000152256_38977536.pth... -[2023-11-28 04:12:18,504][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000149760_38338560.pth -[2023-11-28 04:12:18,511][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000152256_38977536.pth -[2023-11-28 04:12:18,682][87424] Updated weights for policy 0, policy_version 152557 (0.0009) -[2023-11-28 04:12:19,058][87424] Updated weights for policy 0, policy_version 152567 (0.0008) -[2023-11-28 04:12:19,191][87426] Updated weights for policy 1, policy_version 152260 (0.0009) -[2023-11-28 04:12:19,402][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000152576_39059456.pth... -[2023-11-28 04:12:19,442][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000149984_38395904.pth -[2023-11-28 04:12:19,446][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000152576_39059456.pth -[2023-11-28 04:12:19,569][87426] Updated weights for policy 1, policy_version 152270 (0.0012) -[2023-11-28 04:12:19,958][87426] Updated weights for policy 1, policy_version 152280 (0.0012) -[2023-11-28 04:12:21,471][87424] Updated weights for policy 0, policy_version 152577 (0.0008) -[2023-11-28 04:12:21,850][87424] Updated weights for policy 0, policy_version 152587 (0.0010) -[2023-11-28 04:12:21,999][87426] Updated weights for policy 1, policy_version 152290 (0.0011) -[2023-11-28 04:12:22,240][87424] Updated weights for policy 0, policy_version 152597 (0.0011) -[2023-11-28 04:12:22,380][87426] Updated weights for policy 1, policy_version 152300 (0.0009) -[2023-11-28 04:12:22,616][87424] Updated weights for policy 0, policy_version 152607 (0.0010) -[2023-11-28 04:12:22,761][87426] Updated weights for policy 1, policy_version 152310 (0.0011) -[2023-11-28 04:12:23,139][87426] Updated weights for policy 1, policy_version 152320 (0.0012) -[2023-11-28 04:12:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78061568. Throughput: 0: 2685.2, 1: 2755.6. Samples: 78073724. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:12:23,445][86177] Avg episode reward: [(0, '-492.570'), (1, '-520.770')] -[2023-11-28 04:12:24,720][87424] Updated weights for policy 0, policy_version 152617 (0.0012) -[2023-11-28 04:12:25,098][87424] Updated weights for policy 0, policy_version 152627 (0.0011) -[2023-11-28 04:12:25,195][87426] Updated weights for policy 1, policy_version 152330 (0.0010) -[2023-11-28 04:12:25,472][87424] Updated weights for policy 0, policy_version 152637 (0.0011) -[2023-11-28 04:12:25,576][87426] Updated weights for policy 1, policy_version 152340 (0.0010) -[2023-11-28 04:12:25,964][87426] Updated weights for policy 1, policy_version 152350 (0.0012) -[2023-11-28 04:12:27,273][87424] Updated weights for policy 0, policy_version 152647 (0.0012) -[2023-11-28 04:12:27,661][87424] Updated weights for policy 0, policy_version 152657 (0.0012) -[2023-11-28 04:12:28,039][87424] Updated weights for policy 0, policy_version 152667 (0.0010) -[2023-11-28 04:12:28,180][87426] Updated weights for policy 1, policy_version 152360 (0.0011) -[2023-11-28 04:12:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78086144. Throughput: 0: 2706.2, 1: 2782.0. Samples: 78100372. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:12:28,445][86177] Avg episode reward: [(0, '-494.120'), (1, '-507.580')] -[2023-11-28 04:12:28,549][87426] Updated weights for policy 1, policy_version 152370 (0.0007) -[2023-11-28 04:12:28,942][87426] Updated weights for policy 1, policy_version 152380 (0.0008) -[2023-11-28 04:12:30,307][87424] Updated weights for policy 0, policy_version 152677 (0.0010) -[2023-11-28 04:12:30,688][87424] Updated weights for policy 0, policy_version 152687 (0.0012) -[2023-11-28 04:12:31,001][87426] Updated weights for policy 1, policy_version 152390 (0.0008) -[2023-11-28 04:12:31,067][87424] Updated weights for policy 0, policy_version 152697 (0.0011) -[2023-11-28 04:12:31,374][87426] Updated weights for policy 1, policy_version 152400 (0.0008) -[2023-11-28 04:12:31,754][87426] Updated weights for policy 1, policy_version 152410 (0.0010) -[2023-11-28 04:12:32,965][87424] Updated weights for policy 0, policy_version 152707 (0.0011) -[2023-11-28 04:12:33,342][87424] Updated weights for policy 0, policy_version 152717 (0.0010) -[2023-11-28 04:12:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 78110720. Throughput: 0: 2724.5, 1: 2793.2. Samples: 78125320. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:12:33,445][86177] Avg episode reward: [(0, '-496.950'), (1, '-511.460')] -[2023-11-28 04:12:33,719][87424] Updated weights for policy 0, policy_version 152727 (0.0011) -[2023-11-28 04:12:33,845][87426] Updated weights for policy 1, policy_version 152420 (0.0010) -[2023-11-28 04:12:34,234][87426] Updated weights for policy 1, policy_version 152430 (0.0007) -[2023-11-28 04:12:34,610][87426] Updated weights for policy 1, policy_version 152440 (0.0009) -[2023-11-28 04:12:35,880][87424] Updated weights for policy 0, policy_version 152737 (0.0008) -[2023-11-28 04:12:36,257][87424] Updated weights for policy 0, policy_version 152747 (0.0011) -[2023-11-28 04:12:36,647][87424] Updated weights for policy 0, policy_version 152757 (0.0011) -[2023-11-28 04:12:36,729][87426] Updated weights for policy 1, policy_version 152450 (0.0012) -[2023-11-28 04:12:37,017][87424] Updated weights for policy 0, policy_version 152767 (0.0011) -[2023-11-28 04:12:37,097][87426] Updated weights for policy 1, policy_version 152460 (0.0011) -[2023-11-28 04:12:37,485][87426] Updated weights for policy 1, policy_version 152470 (0.0012) -[2023-11-28 04:12:37,863][87426] Updated weights for policy 1, policy_version 152480 (0.0012) -[2023-11-28 04:12:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 78143488. Throughput: 0: 2728.7, 1: 2770.1. Samples: 78157712. Policy #0 lag: (min: 14.0, avg: 27.9, max: 46.0) -[2023-11-28 04:12:38,445][86177] Avg episode reward: [(0, '-496.870'), (1, '-507.900')] -[2023-11-28 04:12:39,041][87424] Updated weights for policy 0, policy_version 152777 (0.0012) -[2023-11-28 04:12:39,429][87424] Updated weights for policy 0, policy_version 152787 (0.0012) -[2023-11-28 04:12:39,759][87426] Updated weights for policy 1, policy_version 152490 (0.0009) -[2023-11-28 04:12:39,821][87424] Updated weights for policy 0, policy_version 152797 (0.0012) -[2023-11-28 04:12:40,145][87426] Updated weights for policy 1, policy_version 152500 (0.0009) -[2023-11-28 04:12:40,521][87426] Updated weights for policy 1, policy_version 152510 (0.0011) -[2023-11-28 04:12:42,044][87424] Updated weights for policy 0, policy_version 152807 (0.0010) -[2023-11-28 04:12:42,425][87424] Updated weights for policy 0, policy_version 152817 (0.0011) -[2023-11-28 04:12:42,807][87424] Updated weights for policy 0, policy_version 152827 (0.0009) -[2023-11-28 04:12:43,025][87426] Updated weights for policy 1, policy_version 152520 (0.0012) -[2023-11-28 04:12:43,403][87426] Updated weights for policy 1, policy_version 152530 (0.0012) -[2023-11-28 04:12:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78168064. Throughput: 0: 2732.3, 1: 2735.0. Samples: 78181984. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:12:43,445][86177] Avg episode reward: [(0, '-511.520'), (1, '-515.040')] -[2023-11-28 04:12:43,782][87426] Updated weights for policy 1, policy_version 152540 (0.0012) -[2023-11-28 04:12:45,087][87424] Updated weights for policy 0, policy_version 152837 (0.0010) -[2023-11-28 04:12:45,482][87424] Updated weights for policy 0, policy_version 152847 (0.0008) -[2023-11-28 04:12:45,864][87424] Updated weights for policy 0, policy_version 152857 (0.0008) -[2023-11-28 04:12:46,301][87426] Updated weights for policy 1, policy_version 152550 (0.0009) -[2023-11-28 04:12:46,681][87426] Updated weights for policy 1, policy_version 152560 (0.0007) -[2023-11-28 04:12:47,059][87426] Updated weights for policy 1, policy_version 152570 (0.0011) -[2023-11-28 04:12:47,530][87424] Updated weights for policy 0, policy_version 152867 (0.0010) -[2023-11-28 04:12:47,924][87424] Updated weights for policy 0, policy_version 152877 (0.0012) -[2023-11-28 04:12:48,303][87424] Updated weights for policy 0, policy_version 152887 (0.0010) -[2023-11-28 04:12:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 78192640. Throughput: 0: 2753.5, 1: 2733.4. Samples: 78206600. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:12:48,445][86177] Avg episode reward: [(0, '-513.140'), (1, '-515.860')] -[2023-11-28 04:12:49,355][87426] Updated weights for policy 1, policy_version 152580 (0.0012) -[2023-11-28 04:12:49,741][87426] Updated weights for policy 1, policy_version 152590 (0.0010) -[2023-11-28 04:12:50,108][87426] Updated weights for policy 1, policy_version 152600 (0.0009) -[2023-11-28 04:12:50,659][87424] Updated weights for policy 0, policy_version 152897 (0.0007) -[2023-11-28 04:12:51,051][87424] Updated weights for policy 0, policy_version 152907 (0.0007) -[2023-11-28 04:12:51,424][87424] Updated weights for policy 0, policy_version 152917 (0.0008) -[2023-11-28 04:12:51,805][87424] Updated weights for policy 0, policy_version 152927 (0.0009) -[2023-11-28 04:12:52,281][87426] Updated weights for policy 1, policy_version 152610 (0.0009) -[2023-11-28 04:12:52,666][87426] Updated weights for policy 1, policy_version 152620 (0.0008) -[2023-11-28 04:12:53,039][87426] Updated weights for policy 1, policy_version 152630 (0.0010) -[2023-11-28 04:12:53,416][87426] Updated weights for policy 1, policy_version 152640 (0.0011) -[2023-11-28 04:12:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 78225408. Throughput: 0: 2759.9, 1: 2728.9. Samples: 78239468. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:12:53,445][86177] Avg episode reward: [(0, '-510.360'), (1, '-509.810')] -[2023-11-28 04:12:54,377][87424] Updated weights for policy 0, policy_version 152937 (0.0011) -[2023-11-28 04:12:54,753][87424] Updated weights for policy 0, policy_version 152947 (0.0012) -[2023-11-28 04:12:55,139][87424] Updated weights for policy 0, policy_version 152957 (0.0011) -[2023-11-28 04:12:55,604][87426] Updated weights for policy 1, policy_version 152650 (0.0011) -[2023-11-28 04:12:55,994][87426] Updated weights for policy 1, policy_version 152660 (0.0008) -[2023-11-28 04:12:56,371][87426] Updated weights for policy 1, policy_version 152670 (0.0007) -[2023-11-28 04:12:57,412][87424] Updated weights for policy 0, policy_version 152967 (0.0007) -[2023-11-28 04:12:57,802][87424] Updated weights for policy 0, policy_version 152977 (0.0007) -[2023-11-28 04:12:58,187][87424] Updated weights for policy 0, policy_version 152987 (0.0008) -[2023-11-28 04:12:58,349][87426] Updated weights for policy 1, policy_version 152680 (0.0007) -[2023-11-28 04:12:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78249984. Throughput: 0: 2747.2, 1: 2723.6. Samples: 78262836. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:12:58,445][86177] Avg episode reward: [(0, '-515.800'), (1, '-500.860')] -[2023-11-28 04:12:58,726][87426] Updated weights for policy 1, policy_version 152690 (0.0007) -[2023-11-28 04:12:59,112][87426] Updated weights for policy 1, policy_version 152700 (0.0011) -[2023-11-28 04:13:00,650][87424] Updated weights for policy 0, policy_version 152997 (0.0007) -[2023-11-28 04:13:01,030][87424] Updated weights for policy 0, policy_version 153007 (0.0008) -[2023-11-28 04:13:01,318][87426] Updated weights for policy 1, policy_version 152710 (0.0010) -[2023-11-28 04:13:01,413][87424] Updated weights for policy 0, policy_version 153017 (0.0007) -[2023-11-28 04:13:01,708][87426] Updated weights for policy 1, policy_version 152720 (0.0009) -[2023-11-28 04:13:02,089][87426] Updated weights for policy 1, policy_version 152730 (0.0012) -[2023-11-28 04:13:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 78274560. Throughput: 0: 2727.0, 1: 2710.0. Samples: 78286832. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:03,445][86177] Avg episode reward: [(0, '-497.450'), (1, '-493.810')] -[2023-11-28 04:13:03,504][87424] Updated weights for policy 0, policy_version 153027 (0.0010) -[2023-11-28 04:13:03,843][87426] Updated weights for policy 1, policy_version 152740 (0.0009) -[2023-11-28 04:13:03,886][87424] Updated weights for policy 0, policy_version 153037 (0.0012) -[2023-11-28 04:13:04,227][87426] Updated weights for policy 1, policy_version 152750 (0.0007) -[2023-11-28 04:13:04,266][87424] Updated weights for policy 0, policy_version 153047 (0.0012) -[2023-11-28 04:13:04,603][87426] Updated weights for policy 1, policy_version 152760 (0.0008) -[2023-11-28 04:13:06,083][87424] Updated weights for policy 0, policy_version 153057 (0.0009) -[2023-11-28 04:13:06,472][87424] Updated weights for policy 0, policy_version 153067 (0.0012) -[2023-11-28 04:13:06,854][87424] Updated weights for policy 0, policy_version 153077 (0.0010) -[2023-11-28 04:13:07,039][87426] Updated weights for policy 1, policy_version 152770 (0.0011) -[2023-11-28 04:13:07,239][87424] Updated weights for policy 0, policy_version 153087 (0.0009) -[2023-11-28 04:13:07,421][87426] Updated weights for policy 1, policy_version 152780 (0.0010) -[2023-11-28 04:13:07,795][87426] Updated weights for policy 1, policy_version 152790 (0.0012) -[2023-11-28 04:13:08,169][87426] Updated weights for policy 1, policy_version 152800 (0.0012) -[2023-11-28 04:13:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78307328. Throughput: 0: 2761.7, 1: 2738.5. Samples: 78321232. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:08,445][86177] Avg episode reward: [(0, '-495.670'), (1, '-502.610')] -[2023-11-28 04:13:09,246][87424] Updated weights for policy 0, policy_version 153097 (0.0011) -[2023-11-28 04:13:09,632][87424] Updated weights for policy 0, policy_version 153107 (0.0012) -[2023-11-28 04:13:10,015][87424] Updated weights for policy 0, policy_version 153117 (0.0012) -[2023-11-28 04:13:10,444][87426] Updated weights for policy 1, policy_version 152810 (0.0009) -[2023-11-28 04:13:10,822][87426] Updated weights for policy 1, policy_version 152820 (0.0012) -[2023-11-28 04:13:11,206][87426] Updated weights for policy 1, policy_version 152830 (0.0012) -[2023-11-28 04:13:12,091][87424] Updated weights for policy 0, policy_version 153127 (0.0010) -[2023-11-28 04:13:12,474][87424] Updated weights for policy 0, policy_version 153137 (0.0009) -[2023-11-28 04:13:12,853][87424] Updated weights for policy 0, policy_version 153147 (0.0011) -[2023-11-28 04:13:13,417][87426] Updated weights for policy 1, policy_version 152840 (0.0011) -[2023-11-28 04:13:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78331904. Throughput: 0: 2733.5, 1: 2707.9. Samples: 78345236. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:13,445][86177] Avg episode reward: [(0, '-514.050'), (1, '-513.850')] -[2023-11-28 04:13:13,795][87426] Updated weights for policy 1, policy_version 152850 (0.0007) -[2023-11-28 04:13:14,173][87426] Updated weights for policy 1, policy_version 152860 (0.0007) -[2023-11-28 04:13:15,226][87424] Updated weights for policy 0, policy_version 153157 (0.0011) -[2023-11-28 04:13:15,609][87424] Updated weights for policy 0, policy_version 153167 (0.0011) -[2023-11-28 04:13:15,983][87424] Updated weights for policy 0, policy_version 153177 (0.0010) -[2023-11-28 04:13:16,640][87426] Updated weights for policy 1, policy_version 152870 (0.0007) -[2023-11-28 04:13:17,016][87426] Updated weights for policy 1, policy_version 152880 (0.0008) -[2023-11-28 04:13:17,394][87426] Updated weights for policy 1, policy_version 152890 (0.0010) -[2023-11-28 04:13:17,755][87424] Updated weights for policy 0, policy_version 153187 (0.0011) -[2023-11-28 04:13:18,129][87424] Updated weights for policy 0, policy_version 153197 (0.0011) -[2023-11-28 04:13:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 78356480. Throughput: 0: 2722.3, 1: 2693.8. Samples: 78369044. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:18,445][86177] Avg episode reward: [(0, '-509.080'), (1, '-516.980')] -[2023-11-28 04:13:18,526][87424] Updated weights for policy 0, policy_version 153207 (0.0011) -[2023-11-28 04:13:19,939][87426] Updated weights for policy 1, policy_version 152900 (0.0009) -[2023-11-28 04:13:20,329][87426] Updated weights for policy 1, policy_version 152910 (0.0012) -[2023-11-28 04:13:20,697][87426] Updated weights for policy 1, policy_version 152920 (0.0012) -[2023-11-28 04:13:20,734][87424] Updated weights for policy 0, policy_version 153217 (0.0012) -[2023-11-28 04:13:21,108][87424] Updated weights for policy 0, policy_version 153227 (0.0012) -[2023-11-28 04:13:21,497][87424] Updated weights for policy 0, policy_version 153237 (0.0012) -[2023-11-28 04:13:21,884][87424] Updated weights for policy 0, policy_version 153247 (0.0010) -[2023-11-28 04:13:23,228][87426] Updated weights for policy 1, policy_version 152930 (0.0011) -[2023-11-28 04:13:23,445][86177] Fps is (10 sec: 4914.9, 60 sec: 5324.7, 300 sec: 5415.0). Total num frames: 78381056. Throughput: 0: 2730.7, 1: 2683.0. Samples: 78401332. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:23,446][86177] Avg episode reward: [(0, '-518.680'), (1, '-517.440')] -[2023-11-28 04:13:23,599][87426] Updated weights for policy 1, policy_version 152940 (0.0009) -[2023-11-28 04:13:23,981][87426] Updated weights for policy 1, policy_version 152950 (0.0011) -[2023-11-28 04:13:24,040][87424] Updated weights for policy 0, policy_version 153257 (0.0008) -[2023-11-28 04:13:24,357][87426] Updated weights for policy 1, policy_version 152960 (0.0009) -[2023-11-28 04:13:24,422][87424] Updated weights for policy 0, policy_version 153267 (0.0007) -[2023-11-28 04:13:24,804][87424] Updated weights for policy 0, policy_version 153277 (0.0008) -[2023-11-28 04:13:26,116][87426] Updated weights for policy 1, policy_version 152970 (0.0008) -[2023-11-28 04:13:26,495][87426] Updated weights for policy 1, policy_version 152980 (0.0007) -[2023-11-28 04:13:26,876][87426] Updated weights for policy 1, policy_version 152990 (0.0008) -[2023-11-28 04:13:26,944][87424] Updated weights for policy 0, policy_version 153287 (0.0010) -[2023-11-28 04:13:27,318][87424] Updated weights for policy 0, policy_version 153297 (0.0009) -[2023-11-28 04:13:27,708][87424] Updated weights for policy 0, policy_version 153307 (0.0008) -[2023-11-28 04:13:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78413824. Throughput: 0: 2729.7, 1: 2695.8. Samples: 78426132. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:28,445][86177] Avg episode reward: [(0, '-516.720'), (1, '-502.760')] -[2023-11-28 04:13:28,856][87426] Updated weights for policy 1, policy_version 153000 (0.0010) -[2023-11-28 04:13:29,238][87426] Updated weights for policy 1, policy_version 153010 (0.0012) -[2023-11-28 04:13:29,612][87426] Updated weights for policy 1, policy_version 153020 (0.0009) -[2023-11-28 04:13:29,809][87424] Updated weights for policy 0, policy_version 153317 (0.0008) -[2023-11-28 04:13:30,196][87424] Updated weights for policy 0, policy_version 153327 (0.0008) -[2023-11-28 04:13:30,588][87424] Updated weights for policy 0, policy_version 153337 (0.0009) -[2023-11-28 04:13:32,148][87426] Updated weights for policy 1, policy_version 153030 (0.0010) -[2023-11-28 04:13:32,522][87426] Updated weights for policy 1, policy_version 153040 (0.0008) -[2023-11-28 04:13:32,766][87424] Updated weights for policy 0, policy_version 153347 (0.0008) -[2023-11-28 04:13:32,904][87426] Updated weights for policy 1, policy_version 153050 (0.0008) -[2023-11-28 04:13:33,151][87424] Updated weights for policy 0, policy_version 153357 (0.0010) -[2023-11-28 04:13:33,444][86177] Fps is (10 sec: 5734.8, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 78438400. Throughput: 0: 2735.2, 1: 2682.9. Samples: 78450416. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:33,445][86177] Avg episode reward: [(0, '-510.740'), (1, '-500.440')] -[2023-11-28 04:13:33,533][87424] Updated weights for policy 0, policy_version 153367 (0.0011) -[2023-11-28 04:13:35,071][87426] Updated weights for policy 1, policy_version 153060 (0.0008) -[2023-11-28 04:13:35,314][87424] Updated weights for policy 0, policy_version 153377 (0.0008) -[2023-11-28 04:13:35,452][87426] Updated weights for policy 1, policy_version 153070 (0.0010) -[2023-11-28 04:13:35,682][87424] Updated weights for policy 0, policy_version 153387 (0.0012) -[2023-11-28 04:13:35,835][87426] Updated weights for policy 1, policy_version 153080 (0.0011) -[2023-11-28 04:13:36,068][87424] Updated weights for policy 0, policy_version 153397 (0.0012) -[2023-11-28 04:13:36,457][87424] Updated weights for policy 0, policy_version 153407 (0.0012) -[2023-11-28 04:13:38,163][87426] Updated weights for policy 1, policy_version 153090 (0.0012) -[2023-11-28 04:13:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 78462976. Throughput: 0: 2754.0, 1: 2676.6. Samples: 78483844. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:38,445][86177] Avg episode reward: [(0, '-518.150'), (1, '-500.400')] -[2023-11-28 04:13:38,538][87426] Updated weights for policy 1, policy_version 153100 (0.0012) -[2023-11-28 04:13:38,625][87424] Updated weights for policy 0, policy_version 153417 (0.0010) -[2023-11-28 04:13:38,917][87426] Updated weights for policy 1, policy_version 153110 (0.0012) -[2023-11-28 04:13:39,006][87424] Updated weights for policy 0, policy_version 153427 (0.0011) -[2023-11-28 04:13:39,295][87426] Updated weights for policy 1, policy_version 153120 (0.0012) -[2023-11-28 04:13:39,392][87424] Updated weights for policy 0, policy_version 153437 (0.0011) -[2023-11-28 04:13:41,293][87426] Updated weights for policy 1, policy_version 153130 (0.0011) -[2023-11-28 04:13:41,680][87426] Updated weights for policy 1, policy_version 153140 (0.0011) -[2023-11-28 04:13:41,896][87424] Updated weights for policy 0, policy_version 153447 (0.0012) -[2023-11-28 04:13:42,056][87426] Updated weights for policy 1, policy_version 153150 (0.0009) -[2023-11-28 04:13:42,276][87424] Updated weights for policy 0, policy_version 153457 (0.0010) -[2023-11-28 04:13:42,657][87424] Updated weights for policy 0, policy_version 153467 (0.0011) -[2023-11-28 04:13:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78495744. Throughput: 0: 2761.2, 1: 2673.0. Samples: 78507372. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:43,445][86177] Avg episode reward: [(0, '-525.390'), (1, '-501.250')] -[2023-11-28 04:13:44,655][87426] Updated weights for policy 1, policy_version 153160 (0.0010) -[2023-11-28 04:13:44,662][87424] Updated weights for policy 0, policy_version 153477 (0.0011) -[2023-11-28 04:13:45,045][87424] Updated weights for policy 0, policy_version 153487 (0.0012) -[2023-11-28 04:13:45,050][87426] Updated weights for policy 1, policy_version 153170 (0.0009) -[2023-11-28 04:13:45,423][87426] Updated weights for policy 1, policy_version 153180 (0.0009) -[2023-11-28 04:13:45,439][87424] Updated weights for policy 0, policy_version 153497 (0.0010) -[2023-11-28 04:13:47,142][87426] Updated weights for policy 1, policy_version 153190 (0.0009) -[2023-11-28 04:13:47,487][87424] Updated weights for policy 0, policy_version 153507 (0.0012) -[2023-11-28 04:13:47,530][87426] Updated weights for policy 1, policy_version 153200 (0.0007) -[2023-11-28 04:13:47,870][87424] Updated weights for policy 0, policy_version 153517 (0.0008) -[2023-11-28 04:13:47,898][87426] Updated weights for policy 1, policy_version 153210 (0.0008) -[2023-11-28 04:13:48,261][87424] Updated weights for policy 0, policy_version 153527 (0.0007) -[2023-11-28 04:13:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 78520320. Throughput: 0: 2758.8, 1: 2682.1. Samples: 78531672. Policy #0 lag: (min: 31.0, avg: 48.7, max: 75.0) -[2023-11-28 04:13:48,445][86177] Avg episode reward: [(0, '-520.650'), (1, '-501.560')] -[2023-11-28 04:13:50,184][87426] Updated weights for policy 1, policy_version 153220 (0.0011) -[2023-11-28 04:13:50,565][87426] Updated weights for policy 1, policy_version 153230 (0.0009) -[2023-11-28 04:13:50,648][87424] Updated weights for policy 0, policy_version 153537 (0.0007) -[2023-11-28 04:13:50,942][87426] Updated weights for policy 1, policy_version 153240 (0.0011) -[2023-11-28 04:13:51,025][87424] Updated weights for policy 0, policy_version 153547 (0.0007) -[2023-11-28 04:13:51,407][87424] Updated weights for policy 0, policy_version 153557 (0.0010) -[2023-11-28 04:13:51,792][87424] Updated weights for policy 0, policy_version 153567 (0.0012) -[2023-11-28 04:13:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 78544896. Throughput: 0: 2724.1, 1: 2668.2. Samples: 78563884. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:13:53,445][86177] Avg episode reward: [(0, '-519.300'), (1, '-500.690')] -[2023-11-28 04:13:53,537][87426] Updated weights for policy 1, policy_version 153250 (0.0011) -[2023-11-28 04:13:53,919][87426] Updated weights for policy 1, policy_version 153260 (0.0011) -[2023-11-28 04:13:54,238][87424] Updated weights for policy 0, policy_version 153577 (0.0012) -[2023-11-28 04:13:54,296][87426] Updated weights for policy 1, policy_version 153270 (0.0010) -[2023-11-28 04:13:54,613][87424] Updated weights for policy 0, policy_version 153587 (0.0012) -[2023-11-28 04:13:54,675][87426] Updated weights for policy 1, policy_version 153280 (0.0008) -[2023-11-28 04:13:54,990][87424] Updated weights for policy 0, policy_version 153597 (0.0012) -[2023-11-28 04:13:57,117][87424] Updated weights for policy 0, policy_version 153607 (0.0011) -[2023-11-28 04:13:57,220][87426] Updated weights for policy 1, policy_version 153290 (0.0012) -[2023-11-28 04:13:57,506][87424] Updated weights for policy 0, policy_version 153617 (0.0011) -[2023-11-28 04:13:57,612][87426] Updated weights for policy 1, policy_version 153300 (0.0008) -[2023-11-28 04:13:57,900][87424] Updated weights for policy 0, policy_version 153627 (0.0011) -[2023-11-28 04:13:57,995][87426] Updated weights for policy 1, policy_version 153310 (0.0008) -[2023-11-28 04:13:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78577664. Throughput: 0: 2715.8, 1: 2655.2. Samples: 78586932. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:13:58,445][86177] Avg episode reward: [(0, '-512.850'), (1, '-500.130')] -[2023-11-28 04:13:59,751][87426] Updated weights for policy 1, policy_version 153320 (0.0010) -[2023-11-28 04:14:00,128][87426] Updated weights for policy 1, policy_version 153330 (0.0011) -[2023-11-28 04:14:00,271][87424] Updated weights for policy 0, policy_version 153637 (0.0012) -[2023-11-28 04:14:00,515][87426] Updated weights for policy 1, policy_version 153340 (0.0010) -[2023-11-28 04:14:00,654][87424] Updated weights for policy 0, policy_version 153647 (0.0009) -[2023-11-28 04:14:01,041][87424] Updated weights for policy 0, policy_version 153657 (0.0007) -[2023-11-28 04:14:02,989][87426] Updated weights for policy 1, policy_version 153350 (0.0010) -[2023-11-28 04:14:03,100][87424] Updated weights for policy 0, policy_version 153667 (0.0009) -[2023-11-28 04:14:03,374][87426] Updated weights for policy 1, policy_version 153360 (0.0009) -[2023-11-28 04:14:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 78594048. Throughput: 0: 2716.8, 1: 2671.3. Samples: 78611508. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:03,445][86177] Avg episode reward: [(0, '-521.550'), (1, '-500.760')] -[2023-11-28 04:14:03,478][87424] Updated weights for policy 0, policy_version 153677 (0.0008) -[2023-11-28 04:14:03,751][87426] Updated weights for policy 1, policy_version 153370 (0.0011) -[2023-11-28 04:14:03,859][87424] Updated weights for policy 0, policy_version 153687 (0.0008) -[2023-11-28 04:14:05,709][87426] Updated weights for policy 1, policy_version 153380 (0.0010) -[2023-11-28 04:14:06,093][87426] Updated weights for policy 1, policy_version 153390 (0.0008) -[2023-11-28 04:14:06,180][87424] Updated weights for policy 0, policy_version 153697 (0.0008) -[2023-11-28 04:14:06,476][87426] Updated weights for policy 1, policy_version 153400 (0.0009) -[2023-11-28 04:14:06,557][87424] Updated weights for policy 0, policy_version 153707 (0.0010) -[2023-11-28 04:14:06,942][87424] Updated weights for policy 0, policy_version 153717 (0.0008) -[2023-11-28 04:14:07,328][87424] Updated weights for policy 0, policy_version 153727 (0.0008) -[2023-11-28 04:14:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 78626816. Throughput: 0: 2687.3, 1: 2689.9. Samples: 78643304. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:08,445][86177] Avg episode reward: [(0, '-517.730'), (1, '-507.160')] -[2023-11-28 04:14:08,522][87426] Updated weights for policy 1, policy_version 153410 (0.0010) -[2023-11-28 04:14:08,901][87426] Updated weights for policy 1, policy_version 153420 (0.0008) -[2023-11-28 04:14:09,279][87426] Updated weights for policy 1, policy_version 153430 (0.0008) -[2023-11-28 04:14:09,660][87426] Updated weights for policy 1, policy_version 153440 (0.0007) -[2023-11-28 04:14:09,786][87424] Updated weights for policy 0, policy_version 153737 (0.0009) -[2023-11-28 04:14:10,170][87424] Updated weights for policy 0, policy_version 153747 (0.0012) -[2023-11-28 04:14:10,552][87424] Updated weights for policy 0, policy_version 153757 (0.0012) -[2023-11-28 04:14:11,887][87426] Updated weights for policy 1, policy_version 153450 (0.0011) -[2023-11-28 04:14:12,267][87426] Updated weights for policy 1, policy_version 153460 (0.0012) -[2023-11-28 04:14:12,588][87424] Updated weights for policy 0, policy_version 153767 (0.0012) -[2023-11-28 04:14:12,649][87426] Updated weights for policy 1, policy_version 153470 (0.0009) -[2023-11-28 04:14:12,960][87424] Updated weights for policy 0, policy_version 153777 (0.0012) -[2023-11-28 04:14:13,342][87424] Updated weights for policy 0, policy_version 153787 (0.0012) -[2023-11-28 04:14:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 78651392. Throughput: 0: 2676.3, 1: 2700.0. Samples: 78668064. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:13,445][86177] Avg episode reward: [(0, '-542.060'), (1, '-501.590')] -[2023-11-28 04:14:14,693][87426] Updated weights for policy 1, policy_version 153480 (0.0009) -[2023-11-28 04:14:15,066][87426] Updated weights for policy 1, policy_version 153490 (0.0009) -[2023-11-28 04:14:15,451][87426] Updated weights for policy 1, policy_version 153500 (0.0008) -[2023-11-28 04:14:15,814][87424] Updated weights for policy 0, policy_version 153797 (0.0009) -[2023-11-28 04:14:16,199][87424] Updated weights for policy 0, policy_version 153807 (0.0008) -[2023-11-28 04:14:16,577][87424] Updated weights for policy 0, policy_version 153817 (0.0008) -[2023-11-28 04:14:17,674][87426] Updated weights for policy 1, policy_version 153510 (0.0010) -[2023-11-28 04:14:18,048][87426] Updated weights for policy 1, policy_version 153520 (0.0008) -[2023-11-28 04:14:18,331][87424] Updated weights for policy 0, policy_version 153827 (0.0008) -[2023-11-28 04:14:18,425][87426] Updated weights for policy 1, policy_version 153530 (0.0010) -[2023-11-28 04:14:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 78675968. Throughput: 0: 2683.0, 1: 2707.7. Samples: 78693000. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:18,445][86177] Avg episode reward: [(0, '-549.170'), (1, '-501.720')] -[2023-11-28 04:14:18,653][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000153536_39305216.pth... -[2023-11-28 04:14:18,684][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000151008_38658048.pth -[2023-11-28 04:14:18,705][87424] Updated weights for policy 0, policy_version 153837 (0.0010) -[2023-11-28 04:14:19,083][87424] Updated weights for policy 0, policy_version 153847 (0.0008) -[2023-11-28 04:14:19,428][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000153856_39387136.pth... -[2023-11-28 04:14:19,458][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000151296_38731776.pth -[2023-11-28 04:14:20,859][87426] Updated weights for policy 1, policy_version 153540 (0.0009) -[2023-11-28 04:14:21,243][87426] Updated weights for policy 1, policy_version 153550 (0.0009) -[2023-11-28 04:14:21,478][87424] Updated weights for policy 0, policy_version 153857 (0.0009) -[2023-11-28 04:14:21,620][87426] Updated weights for policy 1, policy_version 153560 (0.0010) -[2023-11-28 04:14:21,867][87424] Updated weights for policy 0, policy_version 153867 (0.0011) -[2023-11-28 04:14:22,250][87424] Updated weights for policy 0, policy_version 153877 (0.0012) -[2023-11-28 04:14:22,629][87424] Updated weights for policy 0, policy_version 153887 (0.0009) -[2023-11-28 04:14:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 78708736. Throughput: 0: 2644.8, 1: 2683.6. Samples: 78723620. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:23,445][86177] Avg episode reward: [(0, '-523.370'), (1, '-518.790')] -[2023-11-28 04:14:23,531][87426] Updated weights for policy 1, policy_version 153570 (0.0011) -[2023-11-28 04:14:23,904][87426] Updated weights for policy 1, policy_version 153580 (0.0012) -[2023-11-28 04:14:24,295][87426] Updated weights for policy 1, policy_version 153590 (0.0012) -[2023-11-28 04:14:24,673][87426] Updated weights for policy 1, policy_version 153600 (0.0011) -[2023-11-28 04:14:24,999][87424] Updated weights for policy 0, policy_version 153897 (0.0008) -[2023-11-28 04:14:25,373][87424] Updated weights for policy 0, policy_version 153907 (0.0009) -[2023-11-28 04:14:25,761][87424] Updated weights for policy 0, policy_version 153917 (0.0008) -[2023-11-28 04:14:26,441][87426] Updated weights for policy 1, policy_version 153610 (0.0012) -[2023-11-28 04:14:26,819][87426] Updated weights for policy 1, policy_version 153620 (0.0011) -[2023-11-28 04:14:27,186][87426] Updated weights for policy 1, policy_version 153630 (0.0011) -[2023-11-28 04:14:28,270][87424] Updated weights for policy 0, policy_version 153927 (0.0012) -[2023-11-28 04:14:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 78733312. Throughput: 0: 2660.9, 1: 2727.7. Samples: 78749860. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:28,445][86177] Avg episode reward: [(0, '-529.960'), (1, '-512.160')] -[2023-11-28 04:14:28,656][87424] Updated weights for policy 0, policy_version 153937 (0.0012) -[2023-11-28 04:14:29,041][87424] Updated weights for policy 0, policy_version 153947 (0.0012) -[2023-11-28 04:14:29,488][87426] Updated weights for policy 1, policy_version 153640 (0.0011) -[2023-11-28 04:14:29,865][87426] Updated weights for policy 1, policy_version 153650 (0.0011) -[2023-11-28 04:14:30,238][87426] Updated weights for policy 1, policy_version 153660 (0.0011) -[2023-11-28 04:14:31,415][87424] Updated weights for policy 0, policy_version 153957 (0.0010) -[2023-11-28 04:14:31,799][87424] Updated weights for policy 0, policy_version 153967 (0.0011) -[2023-11-28 04:14:32,154][87426] Updated weights for policy 1, policy_version 153670 (0.0009) -[2023-11-28 04:14:32,181][87424] Updated weights for policy 0, policy_version 153977 (0.0009) -[2023-11-28 04:14:32,535][87426] Updated weights for policy 1, policy_version 153680 (0.0008) -[2023-11-28 04:14:32,911][87426] Updated weights for policy 1, policy_version 153690 (0.0009) -[2023-11-28 04:14:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 78766080. Throughput: 0: 2659.8, 1: 2739.5. Samples: 78774640. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:33,445][86177] Avg episode reward: [(0, '-510.800'), (1, '-516.560')] -[2023-11-28 04:14:34,528][87424] Updated weights for policy 0, policy_version 153987 (0.0009) -[2023-11-28 04:14:34,921][87424] Updated weights for policy 0, policy_version 153997 (0.0010) -[2023-11-28 04:14:35,115][87426] Updated weights for policy 1, policy_version 153700 (0.0009) -[2023-11-28 04:14:35,299][87424] Updated weights for policy 0, policy_version 154007 (0.0009) -[2023-11-28 04:14:35,487][87426] Updated weights for policy 1, policy_version 153710 (0.0011) -[2023-11-28 04:14:35,868][87426] Updated weights for policy 1, policy_version 153720 (0.0012) -[2023-11-28 04:14:37,629][87424] Updated weights for policy 0, policy_version 154017 (0.0009) -[2023-11-28 04:14:37,816][87426] Updated weights for policy 1, policy_version 153730 (0.0012) -[2023-11-28 04:14:38,010][87424] Updated weights for policy 0, policy_version 154027 (0.0011) -[2023-11-28 04:14:38,194][87426] Updated weights for policy 1, policy_version 153740 (0.0009) -[2023-11-28 04:14:38,389][87424] Updated weights for policy 0, policy_version 154037 (0.0011) -[2023-11-28 04:14:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 78782464. Throughput: 0: 2667.5, 1: 2747.1. Samples: 78807544. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:38,446][86177] Avg episode reward: [(0, '-503.270'), (1, '-512.170')] -[2023-11-28 04:14:38,573][87426] Updated weights for policy 1, policy_version 153750 (0.0011) -[2023-11-28 04:14:38,772][87424] Updated weights for policy 0, policy_version 154047 (0.0010) -[2023-11-28 04:14:38,971][87426] Updated weights for policy 1, policy_version 153760 (0.0011) -[2023-11-28 04:14:40,684][87424] Updated weights for policy 0, policy_version 154057 (0.0011) -[2023-11-28 04:14:40,876][87426] Updated weights for policy 1, policy_version 153770 (0.0008) -[2023-11-28 04:14:41,060][87424] Updated weights for policy 0, policy_version 154067 (0.0010) -[2023-11-28 04:14:41,253][87426] Updated weights for policy 1, policy_version 153780 (0.0009) -[2023-11-28 04:14:41,445][87424] Updated weights for policy 0, policy_version 154077 (0.0009) -[2023-11-28 04:14:41,636][87426] Updated weights for policy 1, policy_version 153790 (0.0008) -[2023-11-28 04:14:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 78815232. Throughput: 0: 2676.9, 1: 2776.7. Samples: 78832344. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:43,445][86177] Avg episode reward: [(0, '-501.900'), (1, '-507.610')] -[2023-11-28 04:14:43,686][87424] Updated weights for policy 0, policy_version 154087 (0.0011) -[2023-11-28 04:14:43,908][87426] Updated weights for policy 1, policy_version 153800 (0.0015) -[2023-11-28 04:14:44,073][87424] Updated weights for policy 0, policy_version 154097 (0.0010) -[2023-11-28 04:14:44,297][87426] Updated weights for policy 1, policy_version 153810 (0.0009) -[2023-11-28 04:14:44,446][87424] Updated weights for policy 0, policy_version 154107 (0.0008) -[2023-11-28 04:14:44,671][87426] Updated weights for policy 1, policy_version 153820 (0.0008) -[2023-11-28 04:14:46,664][87424] Updated weights for policy 0, policy_version 154117 (0.0011) -[2023-11-28 04:14:46,823][87426] Updated weights for policy 1, policy_version 153830 (0.0009) -[2023-11-28 04:14:47,039][87424] Updated weights for policy 0, policy_version 154127 (0.0009) -[2023-11-28 04:14:47,189][87426] Updated weights for policy 1, policy_version 153840 (0.0011) -[2023-11-28 04:14:47,424][87424] Updated weights for policy 0, policy_version 154137 (0.0007) -[2023-11-28 04:14:47,572][87426] Updated weights for policy 1, policy_version 153850 (0.0007) -[2023-11-28 04:14:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 78848000. Throughput: 0: 2669.7, 1: 2782.4. Samples: 78856852. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:48,445][86177] Avg episode reward: [(0, '-531.840'), (1, '-510.960')] -[2023-11-28 04:14:49,720][87426] Updated weights for policy 1, policy_version 153860 (0.0010) -[2023-11-28 04:14:49,890][87424] Updated weights for policy 0, policy_version 154147 (0.0008) -[2023-11-28 04:14:50,100][87426] Updated weights for policy 1, policy_version 153870 (0.0011) -[2023-11-28 04:14:50,276][87424] Updated weights for policy 0, policy_version 154157 (0.0011) -[2023-11-28 04:14:50,472][87426] Updated weights for policy 1, policy_version 153880 (0.0011) -[2023-11-28 04:14:50,652][87424] Updated weights for policy 0, policy_version 154167 (0.0011) -[2023-11-28 04:14:52,896][87426] Updated weights for policy 1, policy_version 153890 (0.0010) -[2023-11-28 04:14:52,945][87424] Updated weights for policy 0, policy_version 154177 (0.0011) -[2023-11-28 04:14:53,279][87426] Updated weights for policy 1, policy_version 153900 (0.0008) -[2023-11-28 04:14:53,324][87424] Updated weights for policy 0, policy_version 154187 (0.0011) -[2023-11-28 04:14:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 78864384. Throughput: 0: 2667.6, 1: 2782.8. Samples: 78888576. Policy #0 lag: (min: 4.0, avg: 20.2, max: 36.0) -[2023-11-28 04:14:53,445][86177] Avg episode reward: [(0, '-539.810'), (1, '-510.650')] -[2023-11-28 04:14:53,659][87426] Updated weights for policy 1, policy_version 153910 (0.0011) -[2023-11-28 04:14:53,705][87424] Updated weights for policy 0, policy_version 154197 (0.0011) -[2023-11-28 04:14:54,030][87426] Updated weights for policy 1, policy_version 153920 (0.0010) -[2023-11-28 04:14:54,091][87424] Updated weights for policy 0, policy_version 154207 (0.0009) -[2023-11-28 04:14:55,920][87426] Updated weights for policy 1, policy_version 153930 (0.0008) -[2023-11-28 04:14:56,298][87426] Updated weights for policy 1, policy_version 153940 (0.0007) -[2023-11-28 04:14:56,669][87426] Updated weights for policy 1, policy_version 153950 (0.0007) -[2023-11-28 04:14:56,729][87424] Updated weights for policy 0, policy_version 154217 (0.0009) -[2023-11-28 04:14:57,107][87424] Updated weights for policy 0, policy_version 154227 (0.0008) -[2023-11-28 04:14:57,488][87424] Updated weights for policy 0, policy_version 154237 (0.0008) -[2023-11-28 04:14:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 78897152. Throughput: 0: 2656.7, 1: 2764.4. Samples: 78912012. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:14:58,445][86177] Avg episode reward: [(0, '-538.390'), (1, '-504.140')] -[2023-11-28 04:14:58,930][87426] Updated weights for policy 1, policy_version 153960 (0.0008) -[2023-11-28 04:14:59,315][87426] Updated weights for policy 1, policy_version 153970 (0.0010) -[2023-11-28 04:14:59,451][87424] Updated weights for policy 0, policy_version 154247 (0.0010) -[2023-11-28 04:14:59,686][87426] Updated weights for policy 1, policy_version 153980 (0.0008) -[2023-11-28 04:14:59,824][87424] Updated weights for policy 0, policy_version 154257 (0.0011) -[2023-11-28 04:15:00,215][87424] Updated weights for policy 0, policy_version 154267 (0.0012) -[2023-11-28 04:15:01,801][87426] Updated weights for policy 1, policy_version 153990 (0.0011) -[2023-11-28 04:15:02,171][87426] Updated weights for policy 1, policy_version 154000 (0.0008) -[2023-11-28 04:15:02,549][87426] Updated weights for policy 1, policy_version 154010 (0.0010) -[2023-11-28 04:15:02,750][87424] Updated weights for policy 0, policy_version 154277 (0.0012) -[2023-11-28 04:15:03,135][87424] Updated weights for policy 0, policy_version 154287 (0.0012) -[2023-11-28 04:15:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 78921728. Throughput: 0: 2635.6, 1: 2766.4. Samples: 78936092. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:03,446][86177] Avg episode reward: [(0, '-542.180'), (1, '-504.700')] -[2023-11-28 04:15:03,528][87424] Updated weights for policy 0, policy_version 154297 (0.0012) -[2023-11-28 04:15:04,666][87426] Updated weights for policy 1, policy_version 154020 (0.0012) -[2023-11-28 04:15:05,045][87426] Updated weights for policy 1, policy_version 154030 (0.0011) -[2023-11-28 04:15:05,433][87426] Updated weights for policy 1, policy_version 154040 (0.0012) -[2023-11-28 04:15:05,805][87424] Updated weights for policy 0, policy_version 154307 (0.0011) -[2023-11-28 04:15:06,195][87424] Updated weights for policy 0, policy_version 154317 (0.0009) -[2023-11-28 04:15:06,582][87424] Updated weights for policy 0, policy_version 154327 (0.0008) -[2023-11-28 04:15:07,562][87426] Updated weights for policy 1, policy_version 154050 (0.0011) -[2023-11-28 04:15:07,942][87426] Updated weights for policy 1, policy_version 154060 (0.0007) -[2023-11-28 04:15:08,331][87426] Updated weights for policy 1, policy_version 154070 (0.0007) -[2023-11-28 04:15:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 78946304. Throughput: 0: 2652.3, 1: 2794.4. Samples: 78968720. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:08,446][86177] Avg episode reward: [(0, '-502.050'), (1, '-517.570')] -[2023-11-28 04:15:08,593][87424] Updated weights for policy 0, policy_version 154337 (0.0008) -[2023-11-28 04:15:08,702][87426] Updated weights for policy 1, policy_version 154080 (0.0008) -[2023-11-28 04:15:08,975][87424] Updated weights for policy 0, policy_version 154347 (0.0009) -[2023-11-28 04:15:09,358][87424] Updated weights for policy 0, policy_version 154357 (0.0012) -[2023-11-28 04:15:09,752][87424] Updated weights for policy 0, policy_version 154367 (0.0011) -[2023-11-28 04:15:10,996][87426] Updated weights for policy 1, policy_version 154090 (0.0012) -[2023-11-28 04:15:11,372][87426] Updated weights for policy 1, policy_version 154100 (0.0009) -[2023-11-28 04:15:11,756][87426] Updated weights for policy 1, policy_version 154110 (0.0010) -[2023-11-28 04:15:12,036][87424] Updated weights for policy 0, policy_version 154377 (0.0012) -[2023-11-28 04:15:12,413][87424] Updated weights for policy 0, policy_version 154387 (0.0013) -[2023-11-28 04:15:12,793][87424] Updated weights for policy 0, policy_version 154397 (0.0012) -[2023-11-28 04:15:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 78979072. Throughput: 0: 2627.2, 1: 2778.1. Samples: 78993096. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:13,445][86177] Avg episode reward: [(0, '-495.950'), (1, '-516.380')] -[2023-11-28 04:15:13,944][87426] Updated weights for policy 1, policy_version 154120 (0.0008) -[2023-11-28 04:15:14,329][87426] Updated weights for policy 1, policy_version 154130 (0.0007) -[2023-11-28 04:15:14,719][87426] Updated weights for policy 1, policy_version 154140 (0.0007) -[2023-11-28 04:15:15,285][87424] Updated weights for policy 0, policy_version 154407 (0.0011) -[2023-11-28 04:15:15,666][87424] Updated weights for policy 0, policy_version 154417 (0.0008) -[2023-11-28 04:15:16,049][87424] Updated weights for policy 0, policy_version 154427 (0.0010) -[2023-11-28 04:15:16,814][87426] Updated weights for policy 1, policy_version 154150 (0.0008) -[2023-11-28 04:15:17,192][87426] Updated weights for policy 1, policy_version 154160 (0.0011) -[2023-11-28 04:15:17,565][87426] Updated weights for policy 1, policy_version 154170 (0.0012) -[2023-11-28 04:15:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 79003648. Throughput: 0: 2600.9, 1: 2772.2. Samples: 79016428. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:18,446][86177] Avg episode reward: [(0, '-496.950'), (1, '-517.660')] -[2023-11-28 04:15:18,502][87424] Updated weights for policy 0, policy_version 154437 (0.0011) -[2023-11-28 04:15:18,891][87424] Updated weights for policy 0, policy_version 154447 (0.0012) -[2023-11-28 04:15:19,267][87424] Updated weights for policy 0, policy_version 154457 (0.0011) -[2023-11-28 04:15:19,527][87426] Updated weights for policy 1, policy_version 154180 (0.0011) -[2023-11-28 04:15:19,906][87426] Updated weights for policy 1, policy_version 154190 (0.0009) -[2023-11-28 04:15:20,279][87426] Updated weights for policy 1, policy_version 154200 (0.0011) -[2023-11-28 04:15:21,492][87424] Updated weights for policy 0, policy_version 154467 (0.0011) -[2023-11-28 04:15:21,867][87424] Updated weights for policy 0, policy_version 154477 (0.0010) -[2023-11-28 04:15:22,261][87424] Updated weights for policy 0, policy_version 154487 (0.0011) -[2023-11-28 04:15:22,406][87426] Updated weights for policy 1, policy_version 154210 (0.0011) -[2023-11-28 04:15:22,785][87426] Updated weights for policy 1, policy_version 154220 (0.0011) -[2023-11-28 04:15:23,171][87426] Updated weights for policy 1, policy_version 154230 (0.0012) -[2023-11-28 04:15:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 79028224. Throughput: 0: 2592.5, 1: 2755.1. Samples: 79048184. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:23,445][86177] Avg episode reward: [(0, '-504.300'), (1, '-499.130')] -[2023-11-28 04:15:23,539][87426] Updated weights for policy 1, policy_version 154240 (0.0012) -[2023-11-28 04:15:24,420][87424] Updated weights for policy 0, policy_version 154497 (0.0011) -[2023-11-28 04:15:24,806][87424] Updated weights for policy 0, policy_version 154507 (0.0012) -[2023-11-28 04:15:25,189][87424] Updated weights for policy 0, policy_version 154517 (0.0012) -[2023-11-28 04:15:25,512][87426] Updated weights for policy 1, policy_version 154250 (0.0011) -[2023-11-28 04:15:25,583][87424] Updated weights for policy 0, policy_version 154527 (0.0011) -[2023-11-28 04:15:25,902][87426] Updated weights for policy 1, policy_version 154260 (0.0012) -[2023-11-28 04:15:26,283][87426] Updated weights for policy 1, policy_version 154270 (0.0012) -[2023-11-28 04:15:27,607][87424] Updated weights for policy 0, policy_version 154537 (0.0011) -[2023-11-28 04:15:27,994][87424] Updated weights for policy 0, policy_version 154547 (0.0011) -[2023-11-28 04:15:28,266][87426] Updated weights for policy 1, policy_version 154280 (0.0011) -[2023-11-28 04:15:28,378][87424] Updated weights for policy 0, policy_version 154557 (0.0010) -[2023-11-28 04:15:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 79052800. Throughput: 0: 2597.4, 1: 2758.0. Samples: 79073336. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:28,445][86177] Avg episode reward: [(0, '-501.860'), (1, '-498.130')] -[2023-11-28 04:15:28,648][87426] Updated weights for policy 1, policy_version 154290 (0.0012) -[2023-11-28 04:15:29,029][87426] Updated weights for policy 1, policy_version 154300 (0.0012) -[2023-11-28 04:15:30,367][87424] Updated weights for policy 0, policy_version 154567 (0.0011) -[2023-11-28 04:15:30,762][87424] Updated weights for policy 0, policy_version 154577 (0.0012) -[2023-11-28 04:15:31,133][87424] Updated weights for policy 0, policy_version 154587 (0.0012) -[2023-11-28 04:15:31,332][87426] Updated weights for policy 1, policy_version 154310 (0.0010) -[2023-11-28 04:15:31,709][87426] Updated weights for policy 1, policy_version 154320 (0.0009) -[2023-11-28 04:15:32,080][87426] Updated weights for policy 1, policy_version 154330 (0.0011) -[2023-11-28 04:15:33,410][87424] Updated weights for policy 0, policy_version 154597 (0.0012) -[2023-11-28 04:15:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 79085568. Throughput: 0: 2620.8, 1: 2743.4. Samples: 79098240. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:33,445][86177] Avg episode reward: [(0, '-502.370'), (1, '-503.220')] -[2023-11-28 04:15:33,785][87424] Updated weights for policy 0, policy_version 154607 (0.0012) -[2023-11-28 04:15:34,177][87426] Updated weights for policy 1, policy_version 154340 (0.0009) -[2023-11-28 04:15:34,178][87424] Updated weights for policy 0, policy_version 154617 (0.0012) -[2023-11-28 04:15:34,566][87426] Updated weights for policy 1, policy_version 154350 (0.0011) -[2023-11-28 04:15:34,936][87426] Updated weights for policy 1, policy_version 154360 (0.0012) -[2023-11-28 04:15:36,061][87424] Updated weights for policy 0, policy_version 154627 (0.0012) -[2023-11-28 04:15:36,448][87424] Updated weights for policy 0, policy_version 154637 (0.0012) -[2023-11-28 04:15:36,833][87424] Updated weights for policy 0, policy_version 154647 (0.0012) -[2023-11-28 04:15:36,918][87426] Updated weights for policy 1, policy_version 154370 (0.0011) -[2023-11-28 04:15:37,301][87426] Updated weights for policy 1, policy_version 154380 (0.0008) -[2023-11-28 04:15:37,675][87426] Updated weights for policy 1, policy_version 154390 (0.0011) -[2023-11-28 04:15:38,057][87426] Updated weights for policy 1, policy_version 154400 (0.0008) -[2023-11-28 04:15:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 79118336. Throughput: 0: 2639.3, 1: 2762.2. Samples: 79131644. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:38,445][86177] Avg episode reward: [(0, '-500.480'), (1, '-509.400')] -[2023-11-28 04:15:39,291][87424] Updated weights for policy 0, policy_version 154657 (0.0012) -[2023-11-28 04:15:39,669][87424] Updated weights for policy 0, policy_version 154667 (0.0012) -[2023-11-28 04:15:40,068][87424] Updated weights for policy 0, policy_version 154677 (0.0011) -[2023-11-28 04:15:40,447][87424] Updated weights for policy 0, policy_version 154687 (0.0010) -[2023-11-28 04:15:40,496][87426] Updated weights for policy 1, policy_version 154410 (0.0016) -[2023-11-28 04:15:40,875][87426] Updated weights for policy 1, policy_version 154420 (0.0011) -[2023-11-28 04:15:41,259][87426] Updated weights for policy 1, policy_version 154430 (0.0008) -[2023-11-28 04:15:42,492][87424] Updated weights for policy 0, policy_version 154697 (0.0012) -[2023-11-28 04:15:42,859][87424] Updated weights for policy 0, policy_version 154707 (0.0011) -[2023-11-28 04:15:43,241][87424] Updated weights for policy 0, policy_version 154717 (0.0011) -[2023-11-28 04:15:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 79142912. Throughput: 0: 2648.4, 1: 2750.1. Samples: 79154944. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:43,445][86177] Avg episode reward: [(0, '-491.590'), (1, '-509.290')] -[2023-11-28 04:15:43,452][87426] Updated weights for policy 1, policy_version 154440 (0.0011) -[2023-11-28 04:15:43,832][87426] Updated weights for policy 1, policy_version 154450 (0.0012) -[2023-11-28 04:15:44,213][87426] Updated weights for policy 1, policy_version 154460 (0.0012) -[2023-11-28 04:15:45,016][87424] Updated weights for policy 0, policy_version 154727 (0.0009) -[2023-11-28 04:15:45,394][87424] Updated weights for policy 0, policy_version 154737 (0.0008) -[2023-11-28 04:15:45,777][87424] Updated weights for policy 0, policy_version 154747 (0.0008) -[2023-11-28 04:15:46,219][87426] Updated weights for policy 1, policy_version 154470 (0.0012) -[2023-11-28 04:15:46,604][87426] Updated weights for policy 1, policy_version 154480 (0.0012) -[2023-11-28 04:15:46,980][87426] Updated weights for policy 1, policy_version 154490 (0.0011) -[2023-11-28 04:15:48,174][87424] Updated weights for policy 0, policy_version 154757 (0.0010) -[2023-11-28 04:15:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 79167488. Throughput: 0: 2671.4, 1: 2752.5. Samples: 79180168. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:48,445][86177] Avg episode reward: [(0, '-489.040'), (1, '-520.690')] -[2023-11-28 04:15:48,556][87424] Updated weights for policy 0, policy_version 154767 (0.0009) -[2023-11-28 04:15:48,939][87424] Updated weights for policy 0, policy_version 154777 (0.0010) -[2023-11-28 04:15:49,047][87426] Updated weights for policy 1, policy_version 154500 (0.0012) -[2023-11-28 04:15:49,429][87426] Updated weights for policy 1, policy_version 154510 (0.0012) -[2023-11-28 04:15:49,804][87426] Updated weights for policy 1, policy_version 154520 (0.0011) -[2023-11-28 04:15:50,958][87424] Updated weights for policy 0, policy_version 154787 (0.0009) -[2023-11-28 04:15:51,348][87424] Updated weights for policy 0, policy_version 154797 (0.0008) -[2023-11-28 04:15:51,728][87424] Updated weights for policy 0, policy_version 154807 (0.0009) -[2023-11-28 04:15:52,143][87426] Updated weights for policy 1, policy_version 154530 (0.0011) -[2023-11-28 04:15:52,526][87426] Updated weights for policy 1, policy_version 154540 (0.0012) -[2023-11-28 04:15:52,908][87426] Updated weights for policy 1, policy_version 154550 (0.0012) -[2023-11-28 04:15:53,285][87426] Updated weights for policy 1, policy_version 154560 (0.0012) -[2023-11-28 04:15:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 79200256. Throughput: 0: 2687.8, 1: 2755.3. Samples: 79213660. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:53,445][86177] Avg episode reward: [(0, '-491.330'), (1, '-525.180')] -[2023-11-28 04:15:54,239][87424] Updated weights for policy 0, policy_version 154817 (0.0008) -[2023-11-28 04:15:54,611][87424] Updated weights for policy 0, policy_version 154827 (0.0012) -[2023-11-28 04:15:54,989][87424] Updated weights for policy 0, policy_version 154837 (0.0012) -[2023-11-28 04:15:55,378][87424] Updated weights for policy 0, policy_version 154847 (0.0012) -[2023-11-28 04:15:55,488][87426] Updated weights for policy 1, policy_version 154570 (0.0007) -[2023-11-28 04:15:55,861][87426] Updated weights for policy 1, policy_version 154580 (0.0008) -[2023-11-28 04:15:56,250][87426] Updated weights for policy 1, policy_version 154590 (0.0007) -[2023-11-28 04:15:57,989][87424] Updated weights for policy 0, policy_version 154857 (0.0008) -[2023-11-28 04:15:58,359][87424] Updated weights for policy 0, policy_version 154867 (0.0007) -[2023-11-28 04:15:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 79216640. Throughput: 0: 2682.4, 1: 2750.9. Samples: 79237596. Policy #0 lag: (min: 31.0, avg: 55.1, max: 95.0) -[2023-11-28 04:15:58,445][86177] Avg episode reward: [(0, '-491.740'), (1, '-529.720')] -[2023-11-28 04:15:58,612][87426] Updated weights for policy 1, policy_version 154600 (0.0008) -[2023-11-28 04:15:58,745][87424] Updated weights for policy 0, policy_version 154877 (0.0007) -[2023-11-28 04:15:58,993][87426] Updated weights for policy 1, policy_version 154610 (0.0008) -[2023-11-28 04:15:59,371][87426] Updated weights for policy 1, policy_version 154620 (0.0007) -[2023-11-28 04:16:00,877][87424] Updated weights for policy 0, policy_version 154887 (0.0008) -[2023-11-28 04:16:01,251][87424] Updated weights for policy 0, policy_version 154897 (0.0008) -[2023-11-28 04:16:01,638][87424] Updated weights for policy 0, policy_version 154907 (0.0008) -[2023-11-28 04:16:01,864][87426] Updated weights for policy 1, policy_version 154630 (0.0010) -[2023-11-28 04:16:02,250][87426] Updated weights for policy 1, policy_version 154640 (0.0012) -[2023-11-28 04:16:02,628][87426] Updated weights for policy 1, policy_version 154650 (0.0012) -[2023-11-28 04:16:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 79249408. Throughput: 0: 2718.4, 1: 2728.9. Samples: 79261556. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:03,445][86177] Avg episode reward: [(0, '-493.370'), (1, '-534.310')] -[2023-11-28 04:16:03,667][87424] Updated weights for policy 0, policy_version 154917 (0.0011) -[2023-11-28 04:16:04,036][87424] Updated weights for policy 0, policy_version 154927 (0.0012) -[2023-11-28 04:16:04,426][87424] Updated weights for policy 0, policy_version 154937 (0.0012) -[2023-11-28 04:16:04,966][87426] Updated weights for policy 1, policy_version 154660 (0.0011) -[2023-11-28 04:16:05,348][87426] Updated weights for policy 1, policy_version 154670 (0.0009) -[2023-11-28 04:16:05,720][87426] Updated weights for policy 1, policy_version 154680 (0.0007) -[2023-11-28 04:16:06,519][87424] Updated weights for policy 0, policy_version 154947 (0.0011) -[2023-11-28 04:16:06,900][87424] Updated weights for policy 0, policy_version 154957 (0.0008) -[2023-11-28 04:16:07,278][87424] Updated weights for policy 0, policy_version 154967 (0.0010) -[2023-11-28 04:16:07,533][87426] Updated weights for policy 1, policy_version 154690 (0.0007) -[2023-11-28 04:16:07,917][87426] Updated weights for policy 1, policy_version 154700 (0.0009) -[2023-11-28 04:16:08,290][87426] Updated weights for policy 1, policy_version 154710 (0.0011) -[2023-11-28 04:16:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 79273984. Throughput: 0: 2732.5, 1: 2730.1. Samples: 79294004. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:08,445][86177] Avg episode reward: [(0, '-494.970'), (1, '-514.710')] -[2023-11-28 04:16:08,676][87426] Updated weights for policy 1, policy_version 154720 (0.0010) -[2023-11-28 04:16:09,681][87424] Updated weights for policy 0, policy_version 154977 (0.0009) -[2023-11-28 04:16:10,069][87424] Updated weights for policy 0, policy_version 154987 (0.0010) -[2023-11-28 04:16:10,445][87424] Updated weights for policy 0, policy_version 154997 (0.0009) -[2023-11-28 04:16:10,829][87424] Updated weights for policy 0, policy_version 155007 (0.0008) -[2023-11-28 04:16:11,072][87426] Updated weights for policy 1, policy_version 154730 (0.0008) -[2023-11-28 04:16:11,453][87426] Updated weights for policy 1, policy_version 154740 (0.0009) -[2023-11-28 04:16:11,831][87426] Updated weights for policy 1, policy_version 154750 (0.0010) -[2023-11-28 04:16:12,776][87424] Updated weights for policy 0, policy_version 155017 (0.0011) -[2023-11-28 04:16:13,161][87424] Updated weights for policy 0, policy_version 155027 (0.0009) -[2023-11-28 04:16:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 79298560. Throughput: 0: 2730.3, 1: 2686.7. Samples: 79317100. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:13,445][86177] Avg episode reward: [(0, '-492.280'), (1, '-517.920')] -[2023-11-28 04:16:13,548][87424] Updated weights for policy 0, policy_version 155037 (0.0008) -[2023-11-28 04:16:14,253][87426] Updated weights for policy 1, policy_version 154760 (0.0011) -[2023-11-28 04:16:14,628][87426] Updated weights for policy 1, policy_version 154770 (0.0011) -[2023-11-28 04:16:15,005][87426] Updated weights for policy 1, policy_version 154780 (0.0012) -[2023-11-28 04:16:15,816][87424] Updated weights for policy 0, policy_version 155047 (0.0011) -[2023-11-28 04:16:16,196][87424] Updated weights for policy 0, policy_version 155057 (0.0012) -[2023-11-28 04:16:16,568][87424] Updated weights for policy 0, policy_version 155067 (0.0012) -[2023-11-28 04:16:17,040][87426] Updated weights for policy 1, policy_version 154790 (0.0011) -[2023-11-28 04:16:17,409][87426] Updated weights for policy 1, policy_version 154800 (0.0012) -[2023-11-28 04:16:17,791][87426] Updated weights for policy 1, policy_version 154810 (0.0012) -[2023-11-28 04:16:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 79331328. Throughput: 0: 2712.8, 1: 2689.4. Samples: 79341340. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:18,445][86177] Avg episode reward: [(0, '-497.140'), (1, '-504.050')] -[2023-11-28 04:16:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000154816_39632896.pth... -[2023-11-28 04:16:18,491][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000152256_38977536.pth -[2023-11-28 04:16:18,618][87424] Updated weights for policy 0, policy_version 155077 (0.0012) -[2023-11-28 04:16:18,996][87424] Updated weights for policy 0, policy_version 155087 (0.0012) -[2023-11-28 04:16:19,372][87424] Updated weights for policy 0, policy_version 155097 (0.0012) -[2023-11-28 04:16:19,641][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000155104_39706624.pth... -[2023-11-28 04:16:19,687][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000152576_39059456.pth -[2023-11-28 04:16:20,238][87426] Updated weights for policy 1, policy_version 154820 (0.0010) -[2023-11-28 04:16:20,626][87426] Updated weights for policy 1, policy_version 154830 (0.0010) -[2023-11-28 04:16:20,992][87426] Updated weights for policy 1, policy_version 154840 (0.0011) -[2023-11-28 04:16:21,459][87424] Updated weights for policy 0, policy_version 155107 (0.0012) -[2023-11-28 04:16:21,836][87424] Updated weights for policy 0, policy_version 155117 (0.0012) -[2023-11-28 04:16:22,212][87424] Updated weights for policy 0, policy_version 155127 (0.0012) -[2023-11-28 04:16:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 79355904. Throughput: 0: 2712.0, 1: 2651.8. Samples: 79373016. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:23,445][86177] Avg episode reward: [(0, '-505.540'), (1, '-500.860')] -[2023-11-28 04:16:23,554][87426] Updated weights for policy 1, policy_version 154850 (0.0010) -[2023-11-28 04:16:23,928][87426] Updated weights for policy 1, policy_version 154860 (0.0008) -[2023-11-28 04:16:24,307][87426] Updated weights for policy 1, policy_version 154870 (0.0007) -[2023-11-28 04:16:24,536][87424] Updated weights for policy 0, policy_version 155137 (0.0012) -[2023-11-28 04:16:24,690][87426] Updated weights for policy 1, policy_version 154880 (0.0008) -[2023-11-28 04:16:24,924][87424] Updated weights for policy 0, policy_version 155147 (0.0012) -[2023-11-28 04:16:25,303][87424] Updated weights for policy 0, policy_version 155157 (0.0011) -[2023-11-28 04:16:25,670][87424] Updated weights for policy 0, policy_version 155167 (0.0012) -[2023-11-28 04:16:27,207][87426] Updated weights for policy 1, policy_version 154890 (0.0008) -[2023-11-28 04:16:27,580][87424] Updated weights for policy 0, policy_version 155177 (0.0008) -[2023-11-28 04:16:27,587][87426] Updated weights for policy 1, policy_version 154900 (0.0011) -[2023-11-28 04:16:27,958][87424] Updated weights for policy 0, policy_version 155187 (0.0008) -[2023-11-28 04:16:27,967][87426] Updated weights for policy 1, policy_version 154910 (0.0011) -[2023-11-28 04:16:28,340][87424] Updated weights for policy 0, policy_version 155197 (0.0008) -[2023-11-28 04:16:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 79380480. Throughput: 0: 2728.0, 1: 2637.9. Samples: 79396408. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:28,445][86177] Avg episode reward: [(0, '-503.830'), (1, '-508.400')] -[2023-11-28 04:16:30,304][87426] Updated weights for policy 1, policy_version 154920 (0.0011) -[2023-11-28 04:16:30,689][87426] Updated weights for policy 1, policy_version 154930 (0.0010) -[2023-11-28 04:16:30,756][87424] Updated weights for policy 0, policy_version 155207 (0.0008) -[2023-11-28 04:16:31,054][87426] Updated weights for policy 1, policy_version 154940 (0.0010) -[2023-11-28 04:16:31,141][87424] Updated weights for policy 0, policy_version 155217 (0.0012) -[2023-11-28 04:16:31,519][87424] Updated weights for policy 0, policy_version 155227 (0.0012) -[2023-11-28 04:16:32,980][87426] Updated weights for policy 1, policy_version 154950 (0.0012) -[2023-11-28 04:16:33,368][87426] Updated weights for policy 1, policy_version 154960 (0.0012) -[2023-11-28 04:16:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 79405056. Throughput: 0: 2712.3, 1: 2634.6. Samples: 79420776. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:33,445][86177] Avg episode reward: [(0, '-500.270'), (1, '-507.150')] -[2023-11-28 04:16:33,743][87426] Updated weights for policy 1, policy_version 154970 (0.0012) -[2023-11-28 04:16:33,785][87424] Updated weights for policy 0, policy_version 155237 (0.0009) -[2023-11-28 04:16:34,176][87424] Updated weights for policy 0, policy_version 155247 (0.0008) -[2023-11-28 04:16:34,564][87424] Updated weights for policy 0, policy_version 155257 (0.0008) -[2023-11-28 04:16:35,864][87426] Updated weights for policy 1, policy_version 154980 (0.0011) -[2023-11-28 04:16:36,243][87426] Updated weights for policy 1, policy_version 154990 (0.0007) -[2023-11-28 04:16:36,511][87424] Updated weights for policy 0, policy_version 155267 (0.0010) -[2023-11-28 04:16:36,626][87426] Updated weights for policy 1, policy_version 155000 (0.0008) -[2023-11-28 04:16:36,890][87424] Updated weights for policy 0, policy_version 155277 (0.0011) -[2023-11-28 04:16:37,270][87424] Updated weights for policy 0, policy_version 155287 (0.0011) -[2023-11-28 04:16:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 79437824. Throughput: 0: 2690.7, 1: 2620.0. Samples: 79452644. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:38,445][86177] Avg episode reward: [(0, '-495.160'), (1, '-510.690')] -[2023-11-28 04:16:38,910][87426] Updated weights for policy 1, policy_version 155010 (0.0008) -[2023-11-28 04:16:39,223][87424] Updated weights for policy 0, policy_version 155297 (0.0012) -[2023-11-28 04:16:39,284][87426] Updated weights for policy 1, policy_version 155020 (0.0007) -[2023-11-28 04:16:39,604][87424] Updated weights for policy 0, policy_version 155307 (0.0012) -[2023-11-28 04:16:39,662][87426] Updated weights for policy 1, policy_version 155030 (0.0008) -[2023-11-28 04:16:39,983][87424] Updated weights for policy 0, policy_version 155317 (0.0010) -[2023-11-28 04:16:40,042][87426] Updated weights for policy 1, policy_version 155040 (0.0010) -[2023-11-28 04:16:40,365][87424] Updated weights for policy 0, policy_version 155327 (0.0012) -[2023-11-28 04:16:42,246][87426] Updated weights for policy 1, policy_version 155050 (0.0010) -[2023-11-28 04:16:42,386][87424] Updated weights for policy 0, policy_version 155337 (0.0010) -[2023-11-28 04:16:42,620][87426] Updated weights for policy 1, policy_version 155060 (0.0011) -[2023-11-28 04:16:42,763][87424] Updated weights for policy 0, policy_version 155347 (0.0012) -[2023-11-28 04:16:42,998][87426] Updated weights for policy 1, policy_version 155070 (0.0011) -[2023-11-28 04:16:43,139][87424] Updated weights for policy 0, policy_version 155357 (0.0012) -[2023-11-28 04:16:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 79470592. Throughput: 0: 2700.0, 1: 2609.7. Samples: 79476532. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:43,445][86177] Avg episode reward: [(0, '-511.670'), (1, '-506.580')] -[2023-11-28 04:16:45,314][87426] Updated weights for policy 1, policy_version 155080 (0.0011) -[2023-11-28 04:16:45,697][87426] Updated weights for policy 1, policy_version 155090 (0.0010) -[2023-11-28 04:16:45,724][87424] Updated weights for policy 0, policy_version 155367 (0.0012) -[2023-11-28 04:16:46,078][87426] Updated weights for policy 1, policy_version 155100 (0.0008) -[2023-11-28 04:16:46,105][87424] Updated weights for policy 0, policy_version 155377 (0.0012) -[2023-11-28 04:16:46,493][87424] Updated weights for policy 0, policy_version 155387 (0.0010) -[2023-11-28 04:16:47,844][87426] Updated weights for policy 1, policy_version 155110 (0.0012) -[2023-11-28 04:16:48,222][87426] Updated weights for policy 1, policy_version 155120 (0.0012) -[2023-11-28 04:16:48,374][87424] Updated weights for policy 0, policy_version 155397 (0.0010) -[2023-11-28 04:16:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 79486976. Throughput: 0: 2705.2, 1: 2636.1. Samples: 79501916. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:48,445][86177] Avg episode reward: [(0, '-513.020'), (1, '-502.980')] -[2023-11-28 04:16:48,609][87426] Updated weights for policy 1, policy_version 155130 (0.0007) -[2023-11-28 04:16:48,756][87424] Updated weights for policy 0, policy_version 155407 (0.0011) -[2023-11-28 04:16:49,138][87424] Updated weights for policy 0, policy_version 155417 (0.0012) -[2023-11-28 04:16:50,718][87426] Updated weights for policy 1, policy_version 155140 (0.0011) -[2023-11-28 04:16:51,120][87426] Updated weights for policy 1, policy_version 155150 (0.0012) -[2023-11-28 04:16:51,495][87426] Updated weights for policy 1, policy_version 155160 (0.0011) -[2023-11-28 04:16:51,622][87424] Updated weights for policy 0, policy_version 155427 (0.0011) -[2023-11-28 04:16:51,998][87424] Updated weights for policy 0, policy_version 155437 (0.0010) -[2023-11-28 04:16:52,386][87424] Updated weights for policy 0, policy_version 155447 (0.0010) -[2023-11-28 04:16:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 79519744. Throughput: 0: 2709.0, 1: 2661.0. Samples: 79535652. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:53,445][86177] Avg episode reward: [(0, '-510.290'), (1, '-500.370')] -[2023-11-28 04:16:53,482][87426] Updated weights for policy 1, policy_version 155170 (0.0011) -[2023-11-28 04:16:53,873][87426] Updated weights for policy 1, policy_version 155180 (0.0012) -[2023-11-28 04:16:54,255][87426] Updated weights for policy 1, policy_version 155190 (0.0012) -[2023-11-28 04:16:54,626][87426] Updated weights for policy 1, policy_version 155200 (0.0011) -[2023-11-28 04:16:54,662][87424] Updated weights for policy 0, policy_version 155457 (0.0011) -[2023-11-28 04:16:55,043][87424] Updated weights for policy 0, policy_version 155467 (0.0012) -[2023-11-28 04:16:55,418][87424] Updated weights for policy 0, policy_version 155477 (0.0012) -[2023-11-28 04:16:55,801][87424] Updated weights for policy 0, policy_version 155487 (0.0012) -[2023-11-28 04:16:57,123][87426] Updated weights for policy 1, policy_version 155210 (0.0009) -[2023-11-28 04:16:57,499][87426] Updated weights for policy 1, policy_version 155220 (0.0012) -[2023-11-28 04:16:57,881][87426] Updated weights for policy 1, policy_version 155230 (0.0011) -[2023-11-28 04:16:58,225][87424] Updated weights for policy 0, policy_version 155497 (0.0008) -[2023-11-28 04:16:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 79544320. Throughput: 0: 2703.0, 1: 2683.0. Samples: 79559472. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:16:58,445][86177] Avg episode reward: [(0, '-508.160'), (1, '-496.640')] -[2023-11-28 04:16:58,609][87424] Updated weights for policy 0, policy_version 155507 (0.0007) -[2023-11-28 04:16:58,991][87424] Updated weights for policy 0, policy_version 155517 (0.0008) -[2023-11-28 04:16:59,644][87426] Updated weights for policy 1, policy_version 155240 (0.0010) -[2023-11-28 04:17:00,015][87426] Updated weights for policy 1, policy_version 155250 (0.0012) -[2023-11-28 04:17:00,398][87426] Updated weights for policy 1, policy_version 155260 (0.0011) -[2023-11-28 04:17:01,229][87424] Updated weights for policy 0, policy_version 155527 (0.0011) -[2023-11-28 04:17:01,612][87424] Updated weights for policy 0, policy_version 155537 (0.0012) -[2023-11-28 04:17:02,008][87424] Updated weights for policy 0, policy_version 155547 (0.0011) -[2023-11-28 04:17:02,315][87426] Updated weights for policy 1, policy_version 155270 (0.0010) -[2023-11-28 04:17:02,706][87426] Updated weights for policy 1, policy_version 155280 (0.0010) -[2023-11-28 04:17:03,076][87426] Updated weights for policy 1, policy_version 155290 (0.0010) -[2023-11-28 04:17:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 79577088. Throughput: 0: 2687.5, 1: 2705.6. Samples: 79584028. Policy #0 lag: (min: 31.0, avg: 35.6, max: 61.0) -[2023-11-28 04:17:03,445][86177] Avg episode reward: [(0, '-493.900'), (1, '-497.750')] -[2023-11-28 04:17:04,055][87424] Updated weights for policy 0, policy_version 155557 (0.0009) -[2023-11-28 04:17:04,452][87424] Updated weights for policy 0, policy_version 155567 (0.0008) -[2023-11-28 04:17:04,825][87424] Updated weights for policy 0, policy_version 155577 (0.0012) -[2023-11-28 04:17:04,955][87426] Updated weights for policy 1, policy_version 155300 (0.0009) -[2023-11-28 04:17:05,333][87426] Updated weights for policy 1, policy_version 155310 (0.0012) -[2023-11-28 04:17:05,712][87426] Updated weights for policy 1, policy_version 155320 (0.0012) -[2023-11-28 04:17:07,026][87424] Updated weights for policy 0, policy_version 155587 (0.0012) -[2023-11-28 04:17:07,406][87424] Updated weights for policy 0, policy_version 155597 (0.0012) -[2023-11-28 04:17:07,787][87424] Updated weights for policy 0, policy_version 155607 (0.0012) -[2023-11-28 04:17:07,892][87426] Updated weights for policy 1, policy_version 155330 (0.0011) -[2023-11-28 04:17:08,275][87426] Updated weights for policy 1, policy_version 155340 (0.0011) -[2023-11-28 04:17:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 79601664. Throughput: 0: 2705.3, 1: 2755.7. Samples: 79618764. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:08,445][86177] Avg episode reward: [(0, '-496.580'), (1, '-496.440')] -[2023-11-28 04:17:08,647][87426] Updated weights for policy 1, policy_version 155350 (0.0007) -[2023-11-28 04:17:09,026][87426] Updated weights for policy 1, policy_version 155360 (0.0009) -[2023-11-28 04:17:09,950][87424] Updated weights for policy 0, policy_version 155617 (0.0012) -[2023-11-28 04:17:10,337][87424] Updated weights for policy 0, policy_version 155627 (0.0012) -[2023-11-28 04:17:10,721][87424] Updated weights for policy 0, policy_version 155637 (0.0012) -[2023-11-28 04:17:11,115][87424] Updated weights for policy 0, policy_version 155647 (0.0011) -[2023-11-28 04:17:11,290][87426] Updated weights for policy 1, policy_version 155370 (0.0011) -[2023-11-28 04:17:11,661][87426] Updated weights for policy 1, policy_version 155380 (0.0012) -[2023-11-28 04:17:12,040][87426] Updated weights for policy 1, policy_version 155390 (0.0011) -[2023-11-28 04:17:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 79626240. Throughput: 0: 2703.8, 1: 2782.9. Samples: 79643312. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:13,445][86177] Avg episode reward: [(0, '-500.820'), (1, '-494.720')] -[2023-11-28 04:17:13,521][87424] Updated weights for policy 0, policy_version 155657 (0.0012) -[2023-11-28 04:17:13,911][87424] Updated weights for policy 0, policy_version 155667 (0.0012) -[2023-11-28 04:17:14,124][87426] Updated weights for policy 1, policy_version 155400 (0.0012) -[2023-11-28 04:17:14,284][87424] Updated weights for policy 0, policy_version 155677 (0.0012) -[2023-11-28 04:17:14,504][87426] Updated weights for policy 1, policy_version 155410 (0.0012) -[2023-11-28 04:17:14,886][87426] Updated weights for policy 1, policy_version 155420 (0.0012) -[2023-11-28 04:17:16,874][87424] Updated weights for policy 0, policy_version 155687 (0.0012) -[2023-11-28 04:17:17,062][87426] Updated weights for policy 1, policy_version 155430 (0.0011) -[2023-11-28 04:17:17,254][87424] Updated weights for policy 0, policy_version 155697 (0.0011) -[2023-11-28 04:17:17,439][87426] Updated weights for policy 1, policy_version 155440 (0.0008) -[2023-11-28 04:17:17,626][87424] Updated weights for policy 0, policy_version 155707 (0.0009) -[2023-11-28 04:17:17,818][87426] Updated weights for policy 1, policy_version 155450 (0.0009) -[2023-11-28 04:17:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 79659008. Throughput: 0: 2694.3, 1: 2796.5. Samples: 79667864. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:18,445][86177] Avg episode reward: [(0, '-544.010'), (1, '-503.150')] -[2023-11-28 04:17:19,380][87424] Updated weights for policy 0, policy_version 155717 (0.0010) -[2023-11-28 04:17:19,599][87426] Updated weights for policy 1, policy_version 155460 (0.0009) -[2023-11-28 04:17:19,768][87424] Updated weights for policy 0, policy_version 155727 (0.0016) -[2023-11-28 04:17:19,967][87426] Updated weights for policy 1, policy_version 155470 (0.0009) -[2023-11-28 04:17:20,149][87424] Updated weights for policy 0, policy_version 155737 (0.0012) -[2023-11-28 04:17:20,350][87426] Updated weights for policy 1, policy_version 155480 (0.0009) -[2023-11-28 04:17:22,628][87424] Updated weights for policy 0, policy_version 155747 (0.0012) -[2023-11-28 04:17:22,707][87426] Updated weights for policy 1, policy_version 155490 (0.0008) -[2023-11-28 04:17:23,002][87424] Updated weights for policy 0, policy_version 155757 (0.0010) -[2023-11-28 04:17:23,089][87426] Updated weights for policy 1, policy_version 155500 (0.0008) -[2023-11-28 04:17:23,394][87424] Updated weights for policy 0, policy_version 155767 (0.0008) -[2023-11-28 04:17:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 79675392. Throughput: 0: 2690.1, 1: 2829.3. Samples: 79701016. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:23,445][86177] Avg episode reward: [(0, '-541.420'), (1, '-510.260')] -[2023-11-28 04:17:23,464][87426] Updated weights for policy 1, policy_version 155510 (0.0009) -[2023-11-28 04:17:23,845][87426] Updated weights for policy 1, policy_version 155520 (0.0008) -[2023-11-28 04:17:25,219][87424] Updated weights for policy 0, policy_version 155777 (0.0008) -[2023-11-28 04:17:25,598][87424] Updated weights for policy 0, policy_version 155787 (0.0007) -[2023-11-28 04:17:25,682][87426] Updated weights for policy 1, policy_version 155530 (0.0011) -[2023-11-28 04:17:25,986][87424] Updated weights for policy 0, policy_version 155797 (0.0011) -[2023-11-28 04:17:26,056][87426] Updated weights for policy 1, policy_version 155540 (0.0009) -[2023-11-28 04:17:26,358][87424] Updated weights for policy 0, policy_version 155807 (0.0008) -[2023-11-28 04:17:26,440][87426] Updated weights for policy 1, policy_version 155550 (0.0008) -[2023-11-28 04:17:28,082][87426] Updated weights for policy 1, policy_version 155560 (0.0009) -[2023-11-28 04:17:28,247][87424] Updated weights for policy 0, policy_version 155817 (0.0010) -[2023-11-28 04:17:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 79708160. Throughput: 0: 2725.3, 1: 2825.2. Samples: 79726308. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:28,446][86177] Avg episode reward: [(0, '-540.940'), (1, '-513.830')] -[2023-11-28 04:17:28,468][87426] Updated weights for policy 1, policy_version 155570 (0.0011) -[2023-11-28 04:17:28,626][87424] Updated weights for policy 0, policy_version 155827 (0.0011) -[2023-11-28 04:17:28,850][87426] Updated weights for policy 1, policy_version 155580 (0.0011) -[2023-11-28 04:17:29,005][87424] Updated weights for policy 0, policy_version 155837 (0.0011) -[2023-11-28 04:17:31,195][87426] Updated weights for policy 1, policy_version 155590 (0.0010) -[2023-11-28 04:17:31,531][87424] Updated weights for policy 0, policy_version 155847 (0.0009) -[2023-11-28 04:17:31,579][87426] Updated weights for policy 1, policy_version 155600 (0.0009) -[2023-11-28 04:17:31,923][87424] Updated weights for policy 0, policy_version 155857 (0.0011) -[2023-11-28 04:17:31,953][87426] Updated weights for policy 1, policy_version 155610 (0.0010) -[2023-11-28 04:17:32,300][87424] Updated weights for policy 0, policy_version 155867 (0.0011) -[2023-11-28 04:17:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 79740928. Throughput: 0: 2729.5, 1: 2813.9. Samples: 79751368. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:33,445][86177] Avg episode reward: [(0, '-540.060'), (1, '-516.830')] -[2023-11-28 04:17:34,230][87424] Updated weights for policy 0, policy_version 155877 (0.0012) -[2023-11-28 04:17:34,239][87426] Updated weights for policy 1, policy_version 155620 (0.0011) -[2023-11-28 04:17:34,604][87424] Updated weights for policy 0, policy_version 155887 (0.0011) -[2023-11-28 04:17:34,621][87426] Updated weights for policy 1, policy_version 155630 (0.0012) -[2023-11-28 04:17:34,974][87424] Updated weights for policy 0, policy_version 155897 (0.0010) -[2023-11-28 04:17:35,001][87426] Updated weights for policy 1, policy_version 155640 (0.0010) -[2023-11-28 04:17:36,815][87424] Updated weights for policy 0, policy_version 155907 (0.0010) -[2023-11-28 04:17:36,866][87426] Updated weights for policy 1, policy_version 155650 (0.0011) -[2023-11-28 04:17:37,197][87424] Updated weights for policy 0, policy_version 155917 (0.0011) -[2023-11-28 04:17:37,244][87426] Updated weights for policy 1, policy_version 155660 (0.0008) -[2023-11-28 04:17:37,588][87424] Updated weights for policy 0, policy_version 155927 (0.0011) -[2023-11-28 04:17:37,628][87426] Updated weights for policy 1, policy_version 155670 (0.0007) -[2023-11-28 04:17:38,000][87426] Updated weights for policy 1, policy_version 155680 (0.0008) -[2023-11-28 04:17:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 79773696. Throughput: 0: 2738.2, 1: 2799.5. Samples: 79784848. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:38,445][86177] Avg episode reward: [(0, '-498.570'), (1, '-515.370')] -[2023-11-28 04:17:39,810][87424] Updated weights for policy 0, policy_version 155937 (0.0010) -[2023-11-28 04:17:39,922][87426] Updated weights for policy 1, policy_version 155690 (0.0011) -[2023-11-28 04:17:40,190][87424] Updated weights for policy 0, policy_version 155947 (0.0012) -[2023-11-28 04:17:40,306][87426] Updated weights for policy 1, policy_version 155700 (0.0011) -[2023-11-28 04:17:40,571][87424] Updated weights for policy 0, policy_version 155957 (0.0010) -[2023-11-28 04:17:40,689][87426] Updated weights for policy 1, policy_version 155710 (0.0011) -[2023-11-28 04:17:40,952][87424] Updated weights for policy 0, policy_version 155967 (0.0008) -[2023-11-28 04:17:43,090][87426] Updated weights for policy 1, policy_version 155720 (0.0012) -[2023-11-28 04:17:43,283][87424] Updated weights for policy 0, policy_version 155977 (0.0011) -[2023-11-28 04:17:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 79790080. Throughput: 0: 2764.3, 1: 2807.4. Samples: 79810200. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:43,445][86177] Avg episode reward: [(0, '-502.070'), (1, '-500.090')] -[2023-11-28 04:17:43,471][87426] Updated weights for policy 1, policy_version 155730 (0.0011) -[2023-11-28 04:17:43,663][87424] Updated weights for policy 0, policy_version 155987 (0.0011) -[2023-11-28 04:17:43,846][87426] Updated weights for policy 1, policy_version 155740 (0.0010) -[2023-11-28 04:17:44,046][87424] Updated weights for policy 0, policy_version 155997 (0.0012) -[2023-11-28 04:17:46,059][87426] Updated weights for policy 1, policy_version 155750 (0.0010) -[2023-11-28 04:17:46,446][87426] Updated weights for policy 1, policy_version 155760 (0.0008) -[2023-11-28 04:17:46,636][87424] Updated weights for policy 0, policy_version 156007 (0.0009) -[2023-11-28 04:17:46,828][87426] Updated weights for policy 1, policy_version 155770 (0.0010) -[2023-11-28 04:17:47,020][87424] Updated weights for policy 0, policy_version 156017 (0.0008) -[2023-11-28 04:17:47,409][87424] Updated weights for policy 0, policy_version 156027 (0.0008) -[2023-11-28 04:17:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 79822848. Throughput: 0: 2753.0, 1: 2815.2. Samples: 79834596. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:48,445][86177] Avg episode reward: [(0, '-513.330'), (1, '-517.490')] -[2023-11-28 04:17:49,371][87426] Updated weights for policy 1, policy_version 155780 (0.0010) -[2023-11-28 04:17:49,741][87426] Updated weights for policy 1, policy_version 155790 (0.0008) -[2023-11-28 04:17:49,929][87424] Updated weights for policy 0, policy_version 156037 (0.0009) -[2023-11-28 04:17:50,122][87426] Updated weights for policy 1, policy_version 155800 (0.0009) -[2023-11-28 04:17:50,313][87424] Updated weights for policy 0, policy_version 156047 (0.0012) -[2023-11-28 04:17:50,699][87424] Updated weights for policy 0, policy_version 156057 (0.0011) -[2023-11-28 04:17:52,475][87426] Updated weights for policy 1, policy_version 155810 (0.0009) -[2023-11-28 04:17:52,861][87426] Updated weights for policy 1, policy_version 155820 (0.0008) -[2023-11-28 04:17:53,115][87424] Updated weights for policy 0, policy_version 156067 (0.0010) -[2023-11-28 04:17:53,238][87426] Updated weights for policy 1, policy_version 155830 (0.0010) -[2023-11-28 04:17:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 79839232. Throughput: 0: 2717.6, 1: 2788.1. Samples: 79866520. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:53,445][86177] Avg episode reward: [(0, '-513.990'), (1, '-533.180')] -[2023-11-28 04:17:53,504][87424] Updated weights for policy 0, policy_version 156077 (0.0010) -[2023-11-28 04:17:53,627][87426] Updated weights for policy 1, policy_version 155840 (0.0010) -[2023-11-28 04:17:53,888][87424] Updated weights for policy 0, policy_version 156087 (0.0009) -[2023-11-28 04:17:55,982][87424] Updated weights for policy 0, policy_version 156097 (0.0008) -[2023-11-28 04:17:56,135][87426] Updated weights for policy 1, policy_version 155850 (0.0012) -[2023-11-28 04:17:56,356][87424] Updated weights for policy 0, policy_version 156107 (0.0013) -[2023-11-28 04:17:56,500][87426] Updated weights for policy 1, policy_version 155860 (0.0011) -[2023-11-28 04:17:56,745][87424] Updated weights for policy 0, policy_version 156117 (0.0009) -[2023-11-28 04:17:56,877][87426] Updated weights for policy 1, policy_version 155870 (0.0012) -[2023-11-28 04:17:57,116][87424] Updated weights for policy 0, policy_version 156127 (0.0011) -[2023-11-28 04:17:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 79872000. Throughput: 0: 2708.6, 1: 2789.3. Samples: 79890720. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:17:58,445][86177] Avg episode reward: [(0, '-520.810'), (1, '-573.420')] -[2023-11-28 04:17:58,607][87426] Updated weights for policy 1, policy_version 155880 (0.0009) -[2023-11-28 04:17:58,824][87424] Updated weights for policy 0, policy_version 156137 (0.0012) -[2023-11-28 04:17:59,004][87426] Updated weights for policy 1, policy_version 155890 (0.0009) -[2023-11-28 04:17:59,216][87424] Updated weights for policy 0, policy_version 156147 (0.0009) -[2023-11-28 04:17:59,382][87426] Updated weights for policy 1, policy_version 155900 (0.0007) -[2023-11-28 04:17:59,594][87424] Updated weights for policy 0, policy_version 156157 (0.0008) -[2023-11-28 04:18:01,554][87424] Updated weights for policy 0, policy_version 156167 (0.0010) -[2023-11-28 04:18:01,629][87426] Updated weights for policy 1, policy_version 155910 (0.0009) -[2023-11-28 04:18:01,934][87424] Updated weights for policy 0, policy_version 156177 (0.0010) -[2023-11-28 04:18:02,014][87426] Updated weights for policy 1, policy_version 155920 (0.0011) -[2023-11-28 04:18:02,319][87424] Updated weights for policy 0, policy_version 156187 (0.0009) -[2023-11-28 04:18:02,385][87426] Updated weights for policy 1, policy_version 155930 (0.0011) -[2023-11-28 04:18:03,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 79904768. Throughput: 0: 2754.9, 1: 2757.9. Samples: 79915936. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:18:03,445][86177] Avg episode reward: [(0, '-515.620'), (1, '-576.230')] -[2023-11-28 04:18:04,171][87424] Updated weights for policy 0, policy_version 156197 (0.0009) -[2023-11-28 04:18:04,510][87426] Updated weights for policy 1, policy_version 155940 (0.0011) -[2023-11-28 04:18:04,555][87424] Updated weights for policy 0, policy_version 156207 (0.0008) -[2023-11-28 04:18:04,906][87426] Updated weights for policy 1, policy_version 155950 (0.0009) -[2023-11-28 04:18:04,939][87424] Updated weights for policy 0, policy_version 156217 (0.0009) -[2023-11-28 04:18:05,274][87426] Updated weights for policy 1, policy_version 155960 (0.0009) -[2023-11-28 04:18:07,199][87426] Updated weights for policy 1, policy_version 155970 (0.0008) -[2023-11-28 04:18:07,213][87424] Updated weights for policy 0, policy_version 156227 (0.0010) -[2023-11-28 04:18:07,567][87426] Updated weights for policy 1, policy_version 155980 (0.0012) -[2023-11-28 04:18:07,590][87424] Updated weights for policy 0, policy_version 156237 (0.0012) -[2023-11-28 04:18:07,944][87426] Updated weights for policy 1, policy_version 155990 (0.0011) -[2023-11-28 04:18:07,972][87424] Updated weights for policy 0, policy_version 156247 (0.0012) -[2023-11-28 04:18:08,316][87426] Updated weights for policy 1, policy_version 156000 (0.0011) -[2023-11-28 04:18:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 79937536. Throughput: 0: 2778.0, 1: 2731.7. Samples: 79948956. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:18:08,445][86177] Avg episode reward: [(0, '-503.010'), (1, '-557.420')] -[2023-11-28 04:18:09,751][87424] Updated weights for policy 0, policy_version 156257 (0.0010) -[2023-11-28 04:18:10,127][87424] Updated weights for policy 0, policy_version 156267 (0.0010) -[2023-11-28 04:18:10,174][87426] Updated weights for policy 1, policy_version 156010 (0.0011) -[2023-11-28 04:18:10,507][87424] Updated weights for policy 0, policy_version 156277 (0.0011) -[2023-11-28 04:18:10,555][87426] Updated weights for policy 1, policy_version 156020 (0.0010) -[2023-11-28 04:18:10,890][87424] Updated weights for policy 0, policy_version 156287 (0.0009) -[2023-11-28 04:18:10,943][87426] Updated weights for policy 1, policy_version 156030 (0.0008) -[2023-11-28 04:18:12,941][87426] Updated weights for policy 1, policy_version 156040 (0.0010) -[2023-11-28 04:18:13,300][87424] Updated weights for policy 0, policy_version 156297 (0.0008) -[2023-11-28 04:18:13,315][87426] Updated weights for policy 1, policy_version 156050 (0.0009) -[2023-11-28 04:18:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 79953920. Throughput: 0: 2756.9, 1: 2733.8. Samples: 79973388. Policy #0 lag: (min: 31.0, avg: 35.5, max: 61.0) -[2023-11-28 04:18:13,445][86177] Avg episode reward: [(0, '-506.310'), (1, '-585.080')] -[2023-11-28 04:18:13,684][87424] Updated weights for policy 0, policy_version 156307 (0.0008) -[2023-11-28 04:18:13,694][87426] Updated weights for policy 1, policy_version 156060 (0.0009) -[2023-11-28 04:18:14,064][87424] Updated weights for policy 0, policy_version 156317 (0.0007) -[2023-11-28 04:18:15,783][87424] Updated weights for policy 0, policy_version 156327 (0.0010) -[2023-11-28 04:18:16,164][87424] Updated weights for policy 0, policy_version 156337 (0.0009) -[2023-11-28 04:18:16,230][87426] Updated weights for policy 1, policy_version 156070 (0.0011) -[2023-11-28 04:18:16,547][87424] Updated weights for policy 0, policy_version 156347 (0.0007) -[2023-11-28 04:18:16,618][87426] Updated weights for policy 1, policy_version 156080 (0.0011) -[2023-11-28 04:18:16,996][87426] Updated weights for policy 1, policy_version 156090 (0.0007) -[2023-11-28 04:18:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 79986688. Throughput: 0: 2735.6, 1: 2744.3. Samples: 79997968. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:18:18,446][86177] Avg episode reward: [(0, '-508.990'), (1, '-594.470')] -[2023-11-28 04:18:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000156096_39960576.pth... -[2023-11-28 04:18:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000153536_39305216.pth -[2023-11-28 04:18:18,632][87424] Updated weights for policy 0, policy_version 156357 (0.0011) -[2023-11-28 04:18:18,807][87426] Updated weights for policy 1, policy_version 156100 (0.0008) -[2023-11-28 04:18:19,012][87424] Updated weights for policy 0, policy_version 156367 (0.0011) -[2023-11-28 04:18:19,176][87426] Updated weights for policy 1, policy_version 156110 (0.0009) -[2023-11-28 04:18:19,392][87424] Updated weights for policy 0, policy_version 156377 (0.0007) -[2023-11-28 04:18:19,562][87426] Updated weights for policy 1, policy_version 156120 (0.0010) -[2023-11-28 04:18:19,657][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000156384_40034304.pth... -[2023-11-28 04:18:19,688][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000153856_39387136.pth -[2023-11-28 04:18:21,233][87424] Updated weights for policy 0, policy_version 156387 (0.0008) -[2023-11-28 04:18:21,616][87424] Updated weights for policy 0, policy_version 156397 (0.0008) -[2023-11-28 04:18:21,996][87424] Updated weights for policy 0, policy_version 156407 (0.0011) -[2023-11-28 04:18:22,111][87426] Updated weights for policy 1, policy_version 156130 (0.0012) -[2023-11-28 04:18:22,494][87426] Updated weights for policy 1, policy_version 156140 (0.0018) -[2023-11-28 04:18:22,869][87426] Updated weights for policy 1, policy_version 156150 (0.0011) -[2023-11-28 04:18:23,246][87426] Updated weights for policy 1, policy_version 156160 (0.0010) -[2023-11-28 04:18:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5442.8). Total num frames: 80019456. Throughput: 0: 2744.1, 1: 2717.4. Samples: 80030616. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:18:23,445][86177] Avg episode reward: [(0, '-515.060'), (1, '-592.880')] -[2023-11-28 04:18:24,065][87424] Updated weights for policy 0, policy_version 156417 (0.0011) -[2023-11-28 04:18:24,447][87424] Updated weights for policy 0, policy_version 156427 (0.0012) -[2023-11-28 04:18:24,824][87424] Updated weights for policy 0, policy_version 156437 (0.0009) -[2023-11-28 04:18:25,219][87424] Updated weights for policy 0, policy_version 156447 (0.0009) -[2023-11-28 04:18:25,905][87426] Updated weights for policy 1, policy_version 156170 (0.0009) -[2023-11-28 04:18:26,279][87426] Updated weights for policy 1, policy_version 156180 (0.0007) -[2023-11-28 04:18:26,669][87426] Updated weights for policy 1, policy_version 156190 (0.0008) -[2023-11-28 04:18:27,585][87424] Updated weights for policy 0, policy_version 156457 (0.0012) -[2023-11-28 04:18:27,962][87424] Updated weights for policy 0, policy_version 156467 (0.0007) -[2023-11-28 04:18:28,354][87424] Updated weights for policy 0, policy_version 156477 (0.0008) -[2023-11-28 04:18:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 80035840. Throughput: 0: 2733.0, 1: 2708.8. Samples: 80055080. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:18:28,446][86177] Avg episode reward: [(0, '-515.860'), (1, '-649.870')] -[2023-11-28 04:18:28,942][87426] Updated weights for policy 1, policy_version 156200 (0.0011) -[2023-11-28 04:18:29,325][87426] Updated weights for policy 1, policy_version 156210 (0.0008) -[2023-11-28 04:18:29,709][87426] Updated weights for policy 1, policy_version 156220 (0.0008) -[2023-11-28 04:18:30,817][87424] Updated weights for policy 0, policy_version 156487 (0.0010) -[2023-11-28 04:18:31,197][87424] Updated weights for policy 0, policy_version 156497 (0.0012) -[2023-11-28 04:18:31,590][87424] Updated weights for policy 0, policy_version 156507 (0.0012) -[2023-11-28 04:18:31,813][87426] Updated weights for policy 1, policy_version 156230 (0.0011) -[2023-11-28 04:18:32,188][87426] Updated weights for policy 1, policy_version 156240 (0.0010) -[2023-11-28 04:18:32,571][87426] Updated weights for policy 1, policy_version 156250 (0.0011) -[2023-11-28 04:18:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80068608. Throughput: 0: 2748.4, 1: 2696.5. Samples: 80079620. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:18:33,445][86177] Avg episode reward: [(0, '-507.370'), (1, '-617.980')] -[2023-11-28 04:18:33,785][87424] Updated weights for policy 0, policy_version 156517 (0.0009) -[2023-11-28 04:18:34,158][87424] Updated weights for policy 0, policy_version 156527 (0.0007) -[2023-11-28 04:18:34,538][87424] Updated weights for policy 0, policy_version 156537 (0.0007) -[2023-11-28 04:18:34,679][87426] Updated weights for policy 1, policy_version 156260 (0.0010) -[2023-11-28 04:18:35,057][87426] Updated weights for policy 1, policy_version 156270 (0.0009) -[2023-11-28 04:18:35,435][87426] Updated weights for policy 1, policy_version 156280 (0.0011) -[2023-11-28 04:18:36,823][87424] Updated weights for policy 0, policy_version 156547 (0.0010) -[2023-11-28 04:18:37,212][87424] Updated weights for policy 0, policy_version 156557 (0.0011) -[2023-11-28 04:18:37,593][87424] Updated weights for policy 0, policy_version 156567 (0.0007) -[2023-11-28 04:18:37,705][87426] Updated weights for policy 1, policy_version 156290 (0.0011) -[2023-11-28 04:18:38,076][87426] Updated weights for policy 1, policy_version 156300 (0.0007) -[2023-11-28 04:18:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 80093184. Throughput: 0: 2763.9, 1: 2705.8. Samples: 80112656. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:18:38,445][86177] Avg episode reward: [(0, '-500.060'), (1, '-565.240')] -[2023-11-28 04:18:38,455][87426] Updated weights for policy 1, policy_version 156310 (0.0008) -[2023-11-28 04:18:38,838][87426] Updated weights for policy 1, policy_version 156320 (0.0007) -[2023-11-28 04:18:40,015][87424] Updated weights for policy 0, policy_version 156577 (0.0007) -[2023-11-28 04:18:40,393][87424] Updated weights for policy 0, policy_version 156587 (0.0008) -[2023-11-28 04:18:40,779][87424] Updated weights for policy 0, policy_version 156597 (0.0009) -[2023-11-28 04:18:41,091][87426] Updated weights for policy 1, policy_version 156330 (0.0011) -[2023-11-28 04:18:41,164][87424] Updated weights for policy 0, policy_version 156607 (0.0011) -[2023-11-28 04:18:41,463][87426] Updated weights for policy 1, policy_version 156340 (0.0012) -[2023-11-28 04:18:41,857][87426] Updated weights for policy 1, policy_version 156350 (0.0011) -[2023-11-28 04:18:43,299][87424] Updated weights for policy 0, policy_version 156617 (0.0012) -[2023-11-28 04:18:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 80117760. Throughput: 0: 2779.8, 1: 2687.6. Samples: 80136756. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:18:43,445][86177] Avg episode reward: [(0, '-519.780'), (1, '-575.960')] -[2023-11-28 04:18:43,675][87424] Updated weights for policy 0, policy_version 156627 (0.0012) -[2023-11-28 04:18:43,930][87426] Updated weights for policy 1, policy_version 156360 (0.0009) -[2023-11-28 04:18:44,062][87424] Updated weights for policy 0, policy_version 156637 (0.0011) -[2023-11-28 04:18:44,299][87426] Updated weights for policy 1, policy_version 156370 (0.0012) -[2023-11-28 04:18:44,680][87426] Updated weights for policy 1, policy_version 156380 (0.0011) -[2023-11-28 04:18:46,123][87424] Updated weights for policy 0, policy_version 156647 (0.0011) -[2023-11-28 04:18:46,504][87424] Updated weights for policy 0, policy_version 156657 (0.0012) -[2023-11-28 04:18:46,814][87426] Updated weights for policy 1, policy_version 156390 (0.0012) -[2023-11-28 04:18:46,883][87424] Updated weights for policy 0, policy_version 156667 (0.0011) -[2023-11-28 04:18:47,198][87426] Updated weights for policy 1, policy_version 156400 (0.0012) -[2023-11-28 04:18:47,585][87426] Updated weights for policy 1, policy_version 156410 (0.0012) -[2023-11-28 04:18:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80150528. Throughput: 0: 2742.4, 1: 2708.1. Samples: 80161208. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:18:48,445][86177] Avg episode reward: [(0, '-520.860'), (1, '-504.010')] -[2023-11-28 04:18:48,918][87424] Updated weights for policy 0, policy_version 156677 (0.0011) -[2023-11-28 04:18:49,305][87424] Updated weights for policy 0, policy_version 156687 (0.0009) -[2023-11-28 04:18:49,680][87424] Updated weights for policy 0, policy_version 156697 (0.0008) -[2023-11-28 04:18:49,967][87426] Updated weights for policy 1, policy_version 156420 (0.0011) -[2023-11-28 04:18:50,343][87426] Updated weights for policy 1, policy_version 156430 (0.0011) -[2023-11-28 04:18:50,732][87426] Updated weights for policy 1, policy_version 156440 (0.0012) -[2023-11-28 04:18:51,636][87424] Updated weights for policy 0, policy_version 156707 (0.0010) -[2023-11-28 04:18:52,022][87424] Updated weights for policy 0, policy_version 156717 (0.0012) -[2023-11-28 04:18:52,393][87424] Updated weights for policy 0, policy_version 156727 (0.0012) -[2023-11-28 04:18:52,770][87426] Updated weights for policy 1, policy_version 156450 (0.0012) -[2023-11-28 04:18:53,151][87426] Updated weights for policy 1, policy_version 156460 (0.0012) -[2023-11-28 04:18:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 80175104. Throughput: 0: 2732.7, 1: 2713.3. Samples: 80194028. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:18:53,445][86177] Avg episode reward: [(0, '-523.370'), (1, '-512.900')] -[2023-11-28 04:18:53,532][87426] Updated weights for policy 1, policy_version 156470 (0.0012) -[2023-11-28 04:18:53,909][87426] Updated weights for policy 1, policy_version 156480 (0.0012) -[2023-11-28 04:18:54,511][87424] Updated weights for policy 0, policy_version 156737 (0.0012) -[2023-11-28 04:18:54,892][87424] Updated weights for policy 0, policy_version 156747 (0.0012) -[2023-11-28 04:18:55,278][87424] Updated weights for policy 0, policy_version 156757 (0.0011) -[2023-11-28 04:18:55,668][87424] Updated weights for policy 0, policy_version 156767 (0.0012) -[2023-11-28 04:18:56,321][87426] Updated weights for policy 1, policy_version 156490 (0.0012) -[2023-11-28 04:18:56,686][87426] Updated weights for policy 1, policy_version 156500 (0.0011) -[2023-11-28 04:18:57,073][87426] Updated weights for policy 1, policy_version 156510 (0.0012) -[2023-11-28 04:18:57,476][87424] Updated weights for policy 0, policy_version 156777 (0.0012) -[2023-11-28 04:18:57,850][87424] Updated weights for policy 0, policy_version 156787 (0.0012) -[2023-11-28 04:18:58,240][87424] Updated weights for policy 0, policy_version 156797 (0.0012) -[2023-11-28 04:18:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 80207872. Throughput: 0: 2728.7, 1: 2705.7. Samples: 80217936. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:18:58,445][86177] Avg episode reward: [(0, '-499.130'), (1, '-513.130')] -[2023-11-28 04:18:58,975][87426] Updated weights for policy 1, policy_version 156520 (0.0009) -[2023-11-28 04:18:59,356][87426] Updated weights for policy 1, policy_version 156530 (0.0012) -[2023-11-28 04:18:59,731][87426] Updated weights for policy 1, policy_version 156540 (0.0012) -[2023-11-28 04:19:00,101][87424] Updated weights for policy 0, policy_version 156807 (0.0010) -[2023-11-28 04:19:00,478][87424] Updated weights for policy 0, policy_version 156817 (0.0008) -[2023-11-28 04:19:00,878][87424] Updated weights for policy 0, policy_version 156827 (0.0012) -[2023-11-28 04:19:02,106][87426] Updated weights for policy 1, policy_version 156550 (0.0011) -[2023-11-28 04:19:02,479][87426] Updated weights for policy 1, policy_version 156560 (0.0012) -[2023-11-28 04:19:02,869][87426] Updated weights for policy 1, policy_version 156570 (0.0012) -[2023-11-28 04:19:03,436][87424] Updated weights for policy 0, policy_version 156837 (0.0010) -[2023-11-28 04:19:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80232448. Throughput: 0: 2771.0, 1: 2692.0. Samples: 80243800. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:19:03,445][86177] Avg episode reward: [(0, '-511.330'), (1, '-517.570')] -[2023-11-28 04:19:03,822][87424] Updated weights for policy 0, policy_version 156847 (0.0010) -[2023-11-28 04:19:04,206][87424] Updated weights for policy 0, policy_version 156857 (0.0012) -[2023-11-28 04:19:04,705][87426] Updated weights for policy 1, policy_version 156580 (0.0011) -[2023-11-28 04:19:05,081][87426] Updated weights for policy 1, policy_version 156590 (0.0011) -[2023-11-28 04:19:05,461][87426] Updated weights for policy 1, policy_version 156600 (0.0008) -[2023-11-28 04:19:06,232][87424] Updated weights for policy 0, policy_version 156867 (0.0012) -[2023-11-28 04:19:06,610][87424] Updated weights for policy 0, policy_version 156877 (0.0011) -[2023-11-28 04:19:06,986][87424] Updated weights for policy 0, policy_version 156887 (0.0012) -[2023-11-28 04:19:07,422][87426] Updated weights for policy 1, policy_version 156610 (0.0007) -[2023-11-28 04:19:07,803][87426] Updated weights for policy 1, policy_version 156620 (0.0007) -[2023-11-28 04:19:08,174][87426] Updated weights for policy 1, policy_version 156630 (0.0007) -[2023-11-28 04:19:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80257024. Throughput: 0: 2748.0, 1: 2728.3. Samples: 80277048. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:19:08,445][86177] Avg episode reward: [(0, '-511.260'), (1, '-517.780')] -[2023-11-28 04:19:08,551][87426] Updated weights for policy 1, policy_version 156640 (0.0007) -[2023-11-28 04:19:09,252][87424] Updated weights for policy 0, policy_version 156897 (0.0011) -[2023-11-28 04:19:09,626][87424] Updated weights for policy 0, policy_version 156907 (0.0012) -[2023-11-28 04:19:10,011][87424] Updated weights for policy 0, policy_version 156917 (0.0012) -[2023-11-28 04:19:10,401][87424] Updated weights for policy 0, policy_version 156927 (0.0012) -[2023-11-28 04:19:10,867][87426] Updated weights for policy 1, policy_version 156650 (0.0009) -[2023-11-28 04:19:11,256][87426] Updated weights for policy 1, policy_version 156660 (0.0012) -[2023-11-28 04:19:11,627][87426] Updated weights for policy 1, policy_version 156670 (0.0011) -[2023-11-28 04:19:12,755][87424] Updated weights for policy 0, policy_version 156937 (0.0009) -[2023-11-28 04:19:13,130][87424] Updated weights for policy 0, policy_version 156947 (0.0011) -[2023-11-28 04:19:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80281600. Throughput: 0: 2735.6, 1: 2726.4. Samples: 80300868. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:19:13,446][86177] Avg episode reward: [(0, '-525.740'), (1, '-571.400')] -[2023-11-28 04:19:13,509][87424] Updated weights for policy 0, policy_version 156957 (0.0008) -[2023-11-28 04:19:14,007][87426] Updated weights for policy 1, policy_version 156680 (0.0008) -[2023-11-28 04:19:14,393][87426] Updated weights for policy 1, policy_version 156690 (0.0007) -[2023-11-28 04:19:14,775][87426] Updated weights for policy 1, policy_version 156700 (0.0007) -[2023-11-28 04:19:15,869][87424] Updated weights for policy 0, policy_version 156967 (0.0009) -[2023-11-28 04:19:16,250][87424] Updated weights for policy 0, policy_version 156977 (0.0007) -[2023-11-28 04:19:16,650][87424] Updated weights for policy 0, policy_version 156987 (0.0007) -[2023-11-28 04:19:17,280][87426] Updated weights for policy 1, policy_version 156710 (0.0010) -[2023-11-28 04:19:17,657][87426] Updated weights for policy 1, policy_version 156720 (0.0011) -[2023-11-28 04:19:18,038][87426] Updated weights for policy 1, policy_version 156730 (0.0011) -[2023-11-28 04:19:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 80314368. Throughput: 0: 2724.1, 1: 2702.6. Samples: 80323820. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 04:19:18,445][86177] Avg episode reward: [(0, '-516.890'), (1, '-578.980')] -[2023-11-28 04:19:18,677][87424] Updated weights for policy 0, policy_version 156997 (0.0008) -[2023-11-28 04:19:19,062][87424] Updated weights for policy 0, policy_version 157007 (0.0010) -[2023-11-28 04:19:19,437][87424] Updated weights for policy 0, policy_version 157017 (0.0011) -[2023-11-28 04:19:20,106][87426] Updated weights for policy 1, policy_version 156740 (0.0012) -[2023-11-28 04:19:20,505][87426] Updated weights for policy 1, policy_version 156750 (0.0012) -[2023-11-28 04:19:20,883][87426] Updated weights for policy 1, policy_version 156760 (0.0011) -[2023-11-28 04:19:21,782][87424] Updated weights for policy 0, policy_version 157027 (0.0011) -[2023-11-28 04:19:22,157][87424] Updated weights for policy 0, policy_version 157037 (0.0011) -[2023-11-28 04:19:22,541][87424] Updated weights for policy 0, policy_version 157047 (0.0010) -[2023-11-28 04:19:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80338944. Throughput: 0: 2737.2, 1: 2679.7. Samples: 80356416. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:19:23,445][86177] Avg episode reward: [(0, '-515.760'), (1, '-562.280')] -[2023-11-28 04:19:23,446][87426] Updated weights for policy 1, policy_version 156770 (0.0012) -[2023-11-28 04:19:23,832][87426] Updated weights for policy 1, policy_version 156780 (0.0011) -[2023-11-28 04:19:24,217][87426] Updated weights for policy 1, policy_version 156790 (0.0008) -[2023-11-28 04:19:24,405][87424] Updated weights for policy 0, policy_version 157057 (0.0009) -[2023-11-28 04:19:24,597][87426] Updated weights for policy 1, policy_version 156800 (0.0007) -[2023-11-28 04:19:24,794][87424] Updated weights for policy 0, policy_version 157067 (0.0012) -[2023-11-28 04:19:25,172][87424] Updated weights for policy 0, policy_version 157077 (0.0011) -[2023-11-28 04:19:25,549][87424] Updated weights for policy 0, policy_version 157087 (0.0008) -[2023-11-28 04:19:26,557][87426] Updated weights for policy 1, policy_version 156810 (0.0011) -[2023-11-28 04:19:26,937][87426] Updated weights for policy 1, policy_version 156820 (0.0007) -[2023-11-28 04:19:27,267][87424] Updated weights for policy 0, policy_version 157097 (0.0008) -[2023-11-28 04:19:27,324][87426] Updated weights for policy 1, policy_version 156830 (0.0009) -[2023-11-28 04:19:27,656][87424] Updated weights for policy 0, policy_version 157107 (0.0011) -[2023-11-28 04:19:28,031][87424] Updated weights for policy 0, policy_version 157117 (0.0010) -[2023-11-28 04:19:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 80371712. Throughput: 0: 2728.7, 1: 2691.5. Samples: 80380664. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:19:28,445][86177] Avg episode reward: [(0, '-515.870'), (1, '-546.190')] -[2023-11-28 04:19:29,666][87426] Updated weights for policy 1, policy_version 156840 (0.0009) -[2023-11-28 04:19:30,046][87426] Updated weights for policy 1, policy_version 156850 (0.0009) -[2023-11-28 04:19:30,418][87426] Updated weights for policy 1, policy_version 156860 (0.0009) -[2023-11-28 04:19:30,465][87424] Updated weights for policy 0, policy_version 157127 (0.0011) -[2023-11-28 04:19:30,858][87424] Updated weights for policy 0, policy_version 157137 (0.0012) -[2023-11-28 04:19:31,239][87424] Updated weights for policy 0, policy_version 157147 (0.0008) -[2023-11-28 04:19:32,568][87426] Updated weights for policy 1, policy_version 156870 (0.0008) -[2023-11-28 04:19:32,947][87426] Updated weights for policy 1, policy_version 156880 (0.0008) -[2023-11-28 04:19:33,329][87426] Updated weights for policy 1, policy_version 156890 (0.0007) -[2023-11-28 04:19:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80388096. Throughput: 0: 2723.6, 1: 2694.0. Samples: 80405004. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:19:33,445][86177] Avg episode reward: [(0, '-497.210'), (1, '-508.990')] -[2023-11-28 04:19:33,743][87424] Updated weights for policy 0, policy_version 157157 (0.0009) -[2023-11-28 04:19:34,135][87424] Updated weights for policy 0, policy_version 157167 (0.0011) -[2023-11-28 04:19:34,515][87424] Updated weights for policy 0, policy_version 157177 (0.0008) -[2023-11-28 04:19:35,123][87426] Updated weights for policy 1, policy_version 156900 (0.0008) -[2023-11-28 04:19:35,501][87426] Updated weights for policy 1, policy_version 156910 (0.0008) -[2023-11-28 04:19:35,879][87426] Updated weights for policy 1, policy_version 156920 (0.0007) -[2023-11-28 04:19:36,611][87424] Updated weights for policy 0, policy_version 157187 (0.0009) -[2023-11-28 04:19:37,001][87424] Updated weights for policy 0, policy_version 157197 (0.0008) -[2023-11-28 04:19:37,387][87424] Updated weights for policy 0, policy_version 157207 (0.0008) -[2023-11-28 04:19:38,386][87426] Updated weights for policy 1, policy_version 156930 (0.0009) -[2023-11-28 04:19:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80420864. Throughput: 0: 2706.2, 1: 2687.9. Samples: 80436764. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:19:38,445][86177] Avg episode reward: [(0, '-495.510'), (1, '-503.790')] -[2023-11-28 04:19:38,762][87426] Updated weights for policy 1, policy_version 156940 (0.0007) -[2023-11-28 04:19:39,139][87426] Updated weights for policy 1, policy_version 156950 (0.0008) -[2023-11-28 04:19:39,518][87426] Updated weights for policy 1, policy_version 156960 (0.0007) -[2023-11-28 04:19:39,735][87424] Updated weights for policy 0, policy_version 157217 (0.0008) -[2023-11-28 04:19:40,118][87424] Updated weights for policy 0, policy_version 157227 (0.0011) -[2023-11-28 04:19:40,502][87424] Updated weights for policy 0, policy_version 157237 (0.0010) -[2023-11-28 04:19:40,880][87424] Updated weights for policy 0, policy_version 157247 (0.0009) -[2023-11-28 04:19:41,697][87426] Updated weights for policy 1, policy_version 156970 (0.0012) -[2023-11-28 04:19:42,080][87426] Updated weights for policy 1, policy_version 156980 (0.0011) -[2023-11-28 04:19:42,460][87426] Updated weights for policy 1, policy_version 156990 (0.0012) -[2023-11-28 04:19:43,236][87424] Updated weights for policy 0, policy_version 157257 (0.0011) -[2023-11-28 04:19:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 80445440. Throughput: 0: 2698.8, 1: 2705.7. Samples: 80461140. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:19:43,445][86177] Avg episode reward: [(0, '-497.000'), (1, '-512.070')] -[2023-11-28 04:19:43,613][87424] Updated weights for policy 0, policy_version 157267 (0.0012) -[2023-11-28 04:19:43,998][87424] Updated weights for policy 0, policy_version 157277 (0.0011) -[2023-11-28 04:19:44,389][87426] Updated weights for policy 1, policy_version 157000 (0.0011) -[2023-11-28 04:19:44,756][87426] Updated weights for policy 1, policy_version 157010 (0.0011) -[2023-11-28 04:19:45,146][87426] Updated weights for policy 1, policy_version 157020 (0.0010) -[2023-11-28 04:19:46,238][87424] Updated weights for policy 0, policy_version 157287 (0.0009) -[2023-11-28 04:19:46,637][87424] Updated weights for policy 0, policy_version 157297 (0.0008) -[2023-11-28 04:19:47,015][87424] Updated weights for policy 0, policy_version 157307 (0.0008) -[2023-11-28 04:19:47,588][87426] Updated weights for policy 1, policy_version 157030 (0.0009) -[2023-11-28 04:19:47,968][87426] Updated weights for policy 1, policy_version 157040 (0.0008) -[2023-11-28 04:19:48,349][87426] Updated weights for policy 1, policy_version 157050 (0.0009) -[2023-11-28 04:19:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80470016. Throughput: 0: 2693.3, 1: 2701.0. Samples: 80486544. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:19:48,445][86177] Avg episode reward: [(0, '-499.000'), (1, '-504.850')] -[2023-11-28 04:19:49,286][87424] Updated weights for policy 0, policy_version 157317 (0.0008) -[2023-11-28 04:19:49,665][87424] Updated weights for policy 0, policy_version 157327 (0.0010) -[2023-11-28 04:19:50,049][87424] Updated weights for policy 0, policy_version 157337 (0.0010) -[2023-11-28 04:19:50,398][87426] Updated weights for policy 1, policy_version 157060 (0.0009) -[2023-11-28 04:19:50,775][87426] Updated weights for policy 1, policy_version 157070 (0.0008) -[2023-11-28 04:19:51,163][87426] Updated weights for policy 1, policy_version 157080 (0.0008) -[2023-11-28 04:19:52,060][87424] Updated weights for policy 0, policy_version 157347 (0.0010) -[2023-11-28 04:19:52,441][87424] Updated weights for policy 0, policy_version 157357 (0.0012) -[2023-11-28 04:19:52,823][87424] Updated weights for policy 0, policy_version 157367 (0.0012) -[2023-11-28 04:19:53,303][87426] Updated weights for policy 1, policy_version 157090 (0.0010) -[2023-11-28 04:19:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80502784. Throughput: 0: 2685.7, 1: 2673.9. Samples: 80518228. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:19:53,445][86177] Avg episode reward: [(0, '-500.560'), (1, '-520.510')] -[2023-11-28 04:19:53,682][87426] Updated weights for policy 1, policy_version 157100 (0.0011) -[2023-11-28 04:19:54,058][87426] Updated weights for policy 1, policy_version 157110 (0.0009) -[2023-11-28 04:19:54,444][87426] Updated weights for policy 1, policy_version 157120 (0.0008) -[2023-11-28 04:19:54,893][87424] Updated weights for policy 0, policy_version 157377 (0.0011) -[2023-11-28 04:19:55,272][87424] Updated weights for policy 0, policy_version 157387 (0.0012) -[2023-11-28 04:19:55,651][87424] Updated weights for policy 0, policy_version 157397 (0.0011) -[2023-11-28 04:19:56,037][87424] Updated weights for policy 0, policy_version 157407 (0.0008) -[2023-11-28 04:19:56,975][87426] Updated weights for policy 1, policy_version 157130 (0.0008) -[2023-11-28 04:19:57,360][87426] Updated weights for policy 1, policy_version 157140 (0.0007) -[2023-11-28 04:19:57,733][87426] Updated weights for policy 1, policy_version 157150 (0.0008) -[2023-11-28 04:19:57,977][87424] Updated weights for policy 0, policy_version 157417 (0.0008) -[2023-11-28 04:19:58,356][87424] Updated weights for policy 0, policy_version 157427 (0.0008) -[2023-11-28 04:19:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80527360. Throughput: 0: 2690.8, 1: 2686.0. Samples: 80542824. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:19:58,446][86177] Avg episode reward: [(0, '-505.670'), (1, '-512.200')] -[2023-11-28 04:19:58,739][87424] Updated weights for policy 0, policy_version 157437 (0.0011) -[2023-11-28 04:19:59,616][87426] Updated weights for policy 1, policy_version 157160 (0.0011) -[2023-11-28 04:19:59,994][87426] Updated weights for policy 1, policy_version 157170 (0.0011) -[2023-11-28 04:20:00,381][87426] Updated weights for policy 1, policy_version 157180 (0.0010) -[2023-11-28 04:20:00,878][87424] Updated weights for policy 0, policy_version 157447 (0.0011) -[2023-11-28 04:20:01,274][87424] Updated weights for policy 0, policy_version 157457 (0.0010) -[2023-11-28 04:20:01,650][87424] Updated weights for policy 0, policy_version 157467 (0.0009) -[2023-11-28 04:20:02,404][87426] Updated weights for policy 1, policy_version 157190 (0.0016) -[2023-11-28 04:20:02,789][87426] Updated weights for policy 1, policy_version 157200 (0.0012) -[2023-11-28 04:20:03,167][87426] Updated weights for policy 1, policy_version 157210 (0.0012) -[2023-11-28 04:20:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 80560128. Throughput: 0: 2704.7, 1: 2702.4. Samples: 80567140. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:20:03,445][86177] Avg episode reward: [(0, '-505.440'), (1, '-512.570')] -[2023-11-28 04:20:03,763][87424] Updated weights for policy 0, policy_version 157477 (0.0008) -[2023-11-28 04:20:04,151][87424] Updated weights for policy 0, policy_version 157487 (0.0007) -[2023-11-28 04:20:04,540][87424] Updated weights for policy 0, policy_version 157497 (0.0008) -[2023-11-28 04:20:05,653][87426] Updated weights for policy 1, policy_version 157220 (0.0010) -[2023-11-28 04:20:06,042][87426] Updated weights for policy 1, policy_version 157230 (0.0011) -[2023-11-28 04:20:06,425][87426] Updated weights for policy 1, policy_version 157240 (0.0011) -[2023-11-28 04:20:07,085][87424] Updated weights for policy 0, policy_version 157507 (0.0009) -[2023-11-28 04:20:07,471][87424] Updated weights for policy 0, policy_version 157517 (0.0012) -[2023-11-28 04:20:07,846][87424] Updated weights for policy 0, policy_version 157527 (0.0012) -[2023-11-28 04:20:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80584704. Throughput: 0: 2681.0, 1: 2710.8. Samples: 80599044. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:20:08,445][86177] Avg episode reward: [(0, '-519.200'), (1, '-536.590')] -[2023-11-28 04:20:08,459][87426] Updated weights for policy 1, policy_version 157250 (0.0011) -[2023-11-28 04:20:08,831][87426] Updated weights for policy 1, policy_version 157260 (0.0011) -[2023-11-28 04:20:09,209][87426] Updated weights for policy 1, policy_version 157270 (0.0012) -[2023-11-28 04:20:09,583][87426] Updated weights for policy 1, policy_version 157280 (0.0011) -[2023-11-28 04:20:10,276][87424] Updated weights for policy 0, policy_version 157537 (0.0011) -[2023-11-28 04:20:10,657][87424] Updated weights for policy 0, policy_version 157547 (0.0010) -[2023-11-28 04:20:11,038][87424] Updated weights for policy 0, policy_version 157557 (0.0007) -[2023-11-28 04:20:11,430][87424] Updated weights for policy 0, policy_version 157567 (0.0008) -[2023-11-28 04:20:12,110][87426] Updated weights for policy 1, policy_version 157290 (0.0009) -[2023-11-28 04:20:12,476][87426] Updated weights for policy 1, policy_version 157300 (0.0011) -[2023-11-28 04:20:12,851][87426] Updated weights for policy 1, policy_version 157310 (0.0012) -[2023-11-28 04:20:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 80609280. Throughput: 0: 2672.4, 1: 2705.3. Samples: 80622660. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:20:13,445][86177] Avg episode reward: [(0, '-527.280'), (1, '-525.540')] -[2023-11-28 04:20:13,655][87424] Updated weights for policy 0, policy_version 157577 (0.0008) -[2023-11-28 04:20:14,031][87424] Updated weights for policy 0, policy_version 157587 (0.0008) -[2023-11-28 04:20:14,412][87424] Updated weights for policy 0, policy_version 157597 (0.0007) -[2023-11-28 04:20:15,196][87426] Updated weights for policy 1, policy_version 157320 (0.0012) -[2023-11-28 04:20:15,558][87426] Updated weights for policy 1, policy_version 157330 (0.0011) -[2023-11-28 04:20:15,936][87426] Updated weights for policy 1, policy_version 157340 (0.0012) -[2023-11-28 04:20:16,788][87424] Updated weights for policy 0, policy_version 157607 (0.0009) -[2023-11-28 04:20:17,173][87424] Updated weights for policy 0, policy_version 157617 (0.0010) -[2023-11-28 04:20:17,563][87424] Updated weights for policy 0, policy_version 157627 (0.0011) -[2023-11-28 04:20:17,879][87426] Updated weights for policy 1, policy_version 157350 (0.0012) -[2023-11-28 04:20:18,260][87426] Updated weights for policy 1, policy_version 157360 (0.0012) -[2023-11-28 04:20:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80633856. Throughput: 0: 2684.6, 1: 2692.3. Samples: 80646968. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:20:18,445][86177] Avg episode reward: [(0, '-533.240'), (1, '-525.180')] -[2023-11-28 04:20:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000157632_40353792.pth... -[2023-11-28 04:20:18,485][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000155104_39706624.pth -[2023-11-28 04:20:18,636][87426] Updated weights for policy 1, policy_version 157370 (0.0012) -[2023-11-28 04:20:18,858][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000157376_40288256.pth... -[2023-11-28 04:20:18,893][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000154816_39632896.pth -[2023-11-28 04:20:19,716][87424] Updated weights for policy 0, policy_version 157637 (0.0009) -[2023-11-28 04:20:20,099][87424] Updated weights for policy 0, policy_version 157647 (0.0012) -[2023-11-28 04:20:20,482][87424] Updated weights for policy 0, policy_version 157657 (0.0012) -[2023-11-28 04:20:20,938][87426] Updated weights for policy 1, policy_version 157380 (0.0012) -[2023-11-28 04:20:21,324][87426] Updated weights for policy 1, policy_version 157390 (0.0012) -[2023-11-28 04:20:21,694][87426] Updated weights for policy 1, policy_version 157400 (0.0012) -[2023-11-28 04:20:22,796][87424] Updated weights for policy 0, policy_version 157667 (0.0012) -[2023-11-28 04:20:23,176][87424] Updated weights for policy 0, policy_version 157677 (0.0011) -[2023-11-28 04:20:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80658432. Throughput: 0: 2698.4, 1: 2688.4. Samples: 80679168. Policy #0 lag: (min: 31.0, avg: 45.7, max: 63.0) -[2023-11-28 04:20:23,445][86177] Avg episode reward: [(0, '-549.030'), (1, '-517.200')] -[2023-11-28 04:20:23,557][87424] Updated weights for policy 0, policy_version 157687 (0.0012) -[2023-11-28 04:20:24,042][87426] Updated weights for policy 1, policy_version 157410 (0.0011) -[2023-11-28 04:20:24,422][87426] Updated weights for policy 1, policy_version 157420 (0.0007) -[2023-11-28 04:20:24,797][87426] Updated weights for policy 1, policy_version 157430 (0.0007) -[2023-11-28 04:20:25,175][87426] Updated weights for policy 1, policy_version 157440 (0.0008) -[2023-11-28 04:20:25,580][87424] Updated weights for policy 0, policy_version 157697 (0.0012) -[2023-11-28 04:20:25,952][87424] Updated weights for policy 0, policy_version 157707 (0.0012) -[2023-11-28 04:20:26,351][87424] Updated weights for policy 0, policy_version 157717 (0.0012) -[2023-11-28 04:20:26,741][87424] Updated weights for policy 0, policy_version 157727 (0.0012) -[2023-11-28 04:20:27,282][87426] Updated weights for policy 1, policy_version 157450 (0.0010) -[2023-11-28 04:20:27,666][87426] Updated weights for policy 1, policy_version 157460 (0.0007) -[2023-11-28 04:20:28,052][87426] Updated weights for policy 1, policy_version 157470 (0.0010) -[2023-11-28 04:20:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80691200. Throughput: 0: 2714.0, 1: 2679.3. Samples: 80703840. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:20:28,445][86177] Avg episode reward: [(0, '-532.320'), (1, '-516.500')] -[2023-11-28 04:20:29,203][87424] Updated weights for policy 0, policy_version 157737 (0.0012) -[2023-11-28 04:20:29,593][87424] Updated weights for policy 0, policy_version 157747 (0.0012) -[2023-11-28 04:20:29,969][87424] Updated weights for policy 0, policy_version 157757 (0.0011) -[2023-11-28 04:20:30,482][87426] Updated weights for policy 1, policy_version 157480 (0.0012) -[2023-11-28 04:20:30,860][87426] Updated weights for policy 1, policy_version 157490 (0.0012) -[2023-11-28 04:20:31,240][87426] Updated weights for policy 1, policy_version 157500 (0.0012) -[2023-11-28 04:20:31,934][87424] Updated weights for policy 0, policy_version 157767 (0.0012) -[2023-11-28 04:20:32,309][87424] Updated weights for policy 0, policy_version 157777 (0.0012) -[2023-11-28 04:20:32,693][87424] Updated weights for policy 0, policy_version 157787 (0.0012) -[2023-11-28 04:20:33,398][87426] Updated weights for policy 1, policy_version 157510 (0.0012) -[2023-11-28 04:20:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 80715776. Throughput: 0: 2705.1, 1: 2679.1. Samples: 80728832. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:20:33,445][86177] Avg episode reward: [(0, '-530.740'), (1, '-516.340')] -[2023-11-28 04:20:33,778][87426] Updated weights for policy 1, policy_version 157520 (0.0012) -[2023-11-28 04:20:34,160][87426] Updated weights for policy 1, policy_version 157530 (0.0008) -[2023-11-28 04:20:34,953][87424] Updated weights for policy 0, policy_version 157797 (0.0012) -[2023-11-28 04:20:35,346][87424] Updated weights for policy 0, policy_version 157807 (0.0011) -[2023-11-28 04:20:35,733][87424] Updated weights for policy 0, policy_version 157817 (0.0011) -[2023-11-28 04:20:36,038][87426] Updated weights for policy 1, policy_version 157540 (0.0009) -[2023-11-28 04:20:36,433][87426] Updated weights for policy 1, policy_version 157550 (0.0012) -[2023-11-28 04:20:36,803][87426] Updated weights for policy 1, policy_version 157560 (0.0012) -[2023-11-28 04:20:37,473][87424] Updated weights for policy 0, policy_version 157827 (0.0012) -[2023-11-28 04:20:37,858][87424] Updated weights for policy 0, policy_version 157837 (0.0012) -[2023-11-28 04:20:38,238][87424] Updated weights for policy 0, policy_version 157847 (0.0012) -[2023-11-28 04:20:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 80740352. Throughput: 0: 2720.9, 1: 2694.8. Samples: 80761932. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:20:38,445][86177] Avg episode reward: [(0, '-518.740'), (1, '-521.060')] -[2023-11-28 04:20:39,389][87426] Updated weights for policy 1, policy_version 157570 (0.0011) -[2023-11-28 04:20:39,763][87426] Updated weights for policy 1, policy_version 157580 (0.0012) -[2023-11-28 04:20:40,139][87426] Updated weights for policy 1, policy_version 157590 (0.0012) -[2023-11-28 04:20:40,513][87426] Updated weights for policy 1, policy_version 157600 (0.0011) -[2023-11-28 04:20:40,526][87424] Updated weights for policy 0, policy_version 157857 (0.0011) -[2023-11-28 04:20:40,910][87424] Updated weights for policy 0, policy_version 157867 (0.0008) -[2023-11-28 04:20:41,290][87424] Updated weights for policy 0, policy_version 157877 (0.0008) -[2023-11-28 04:20:41,673][87424] Updated weights for policy 0, policy_version 157887 (0.0008) -[2023-11-28 04:20:42,561][87426] Updated weights for policy 1, policy_version 157610 (0.0009) -[2023-11-28 04:20:42,941][87426] Updated weights for policy 1, policy_version 157620 (0.0011) -[2023-11-28 04:20:43,320][87426] Updated weights for policy 1, policy_version 157630 (0.0011) -[2023-11-28 04:20:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80773120. Throughput: 0: 2716.8, 1: 2698.7. Samples: 80786520. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:20:43,445][86177] Avg episode reward: [(0, '-581.470'), (1, '-526.640')] -[2023-11-28 04:20:43,973][87424] Updated weights for policy 0, policy_version 157897 (0.0010) -[2023-11-28 04:20:44,343][87424] Updated weights for policy 0, policy_version 157907 (0.0008) -[2023-11-28 04:20:44,722][87424] Updated weights for policy 0, policy_version 157917 (0.0008) -[2023-11-28 04:20:45,094][87426] Updated weights for policy 1, policy_version 157640 (0.0011) -[2023-11-28 04:20:45,499][87426] Updated weights for policy 1, policy_version 157650 (0.0011) -[2023-11-28 04:20:45,884][87426] Updated weights for policy 1, policy_version 157660 (0.0012) -[2023-11-28 04:20:47,063][87424] Updated weights for policy 0, policy_version 157927 (0.0009) -[2023-11-28 04:20:47,446][87424] Updated weights for policy 0, policy_version 157937 (0.0008) -[2023-11-28 04:20:47,485][87426] Updated weights for policy 1, policy_version 157670 (0.0010) -[2023-11-28 04:20:47,830][87424] Updated weights for policy 0, policy_version 157947 (0.0011) -[2023-11-28 04:20:47,860][87426] Updated weights for policy 1, policy_version 157680 (0.0007) -[2023-11-28 04:20:48,246][87426] Updated weights for policy 1, policy_version 157690 (0.0007) -[2023-11-28 04:20:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 80797696. Throughput: 0: 2699.4, 1: 2700.0. Samples: 80810112. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:20:48,445][86177] Avg episode reward: [(0, '-579.770'), (1, '-524.470')] -[2023-11-28 04:20:49,997][87424] Updated weights for policy 0, policy_version 157957 (0.0010) -[2023-11-28 04:20:50,380][87424] Updated weights for policy 0, policy_version 157967 (0.0009) -[2023-11-28 04:20:50,664][87426] Updated weights for policy 1, policy_version 157700 (0.0009) -[2023-11-28 04:20:50,758][87424] Updated weights for policy 0, policy_version 157977 (0.0011) -[2023-11-28 04:20:51,035][87426] Updated weights for policy 1, policy_version 157710 (0.0012) -[2023-11-28 04:20:51,418][87426] Updated weights for policy 1, policy_version 157720 (0.0011) -[2023-11-28 04:20:52,788][87424] Updated weights for policy 0, policy_version 157987 (0.0009) -[2023-11-28 04:20:53,170][87424] Updated weights for policy 0, policy_version 157997 (0.0011) -[2023-11-28 04:20:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80822272. Throughput: 0: 2729.3, 1: 2710.8. Samples: 80843848. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:20:53,445][86177] Avg episode reward: [(0, '-586.200'), (1, '-517.340')] -[2023-11-28 04:20:53,555][87424] Updated weights for policy 0, policy_version 158007 (0.0011) -[2023-11-28 04:20:54,003][87426] Updated weights for policy 1, policy_version 157730 (0.0011) -[2023-11-28 04:20:54,386][87426] Updated weights for policy 1, policy_version 157740 (0.0008) -[2023-11-28 04:20:54,766][87426] Updated weights for policy 1, policy_version 157750 (0.0007) -[2023-11-28 04:20:55,148][87426] Updated weights for policy 1, policy_version 157760 (0.0008) -[2023-11-28 04:20:55,209][87424] Updated weights for policy 0, policy_version 158017 (0.0012) -[2023-11-28 04:20:55,593][87424] Updated weights for policy 0, policy_version 158027 (0.0012) -[2023-11-28 04:20:55,974][87424] Updated weights for policy 0, policy_version 158037 (0.0012) -[2023-11-28 04:20:56,356][87424] Updated weights for policy 0, policy_version 158047 (0.0011) -[2023-11-28 04:20:57,530][87426] Updated weights for policy 1, policy_version 157770 (0.0012) -[2023-11-28 04:20:57,901][87426] Updated weights for policy 1, policy_version 157780 (0.0012) -[2023-11-28 04:20:58,237][87424] Updated weights for policy 0, policy_version 158057 (0.0010) -[2023-11-28 04:20:58,275][87426] Updated weights for policy 1, policy_version 157790 (0.0011) -[2023-11-28 04:20:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80855040. Throughput: 0: 2741.2, 1: 2713.2. Samples: 80868108. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:20:58,445][86177] Avg episode reward: [(0, '-582.940'), (1, '-510.460')] -[2023-11-28 04:20:58,624][87424] Updated weights for policy 0, policy_version 158067 (0.0011) -[2023-11-28 04:20:59,004][87424] Updated weights for policy 0, policy_version 158077 (0.0012) -[2023-11-28 04:20:59,947][87426] Updated weights for policy 1, policy_version 157800 (0.0012) -[2023-11-28 04:21:00,321][87426] Updated weights for policy 1, policy_version 157810 (0.0012) -[2023-11-28 04:21:00,699][87426] Updated weights for policy 1, policy_version 157820 (0.0012) -[2023-11-28 04:21:01,058][87424] Updated weights for policy 0, policy_version 158087 (0.0012) -[2023-11-28 04:21:01,448][87424] Updated weights for policy 0, policy_version 158097 (0.0012) -[2023-11-28 04:21:01,827][87424] Updated weights for policy 0, policy_version 158107 (0.0012) -[2023-11-28 04:21:02,646][87426] Updated weights for policy 1, policy_version 157830 (0.0012) -[2023-11-28 04:21:03,018][87426] Updated weights for policy 1, policy_version 157840 (0.0010) -[2023-11-28 04:21:03,399][87426] Updated weights for policy 1, policy_version 157850 (0.0008) -[2023-11-28 04:21:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 80879616. Throughput: 0: 2743.5, 1: 2740.5. Samples: 80893748. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:21:03,445][86177] Avg episode reward: [(0, '-516.520'), (1, '-521.290')] -[2023-11-28 04:21:04,030][87424] Updated weights for policy 0, policy_version 158117 (0.0012) -[2023-11-28 04:21:04,416][87424] Updated weights for policy 0, policy_version 158127 (0.0012) -[2023-11-28 04:21:04,795][87424] Updated weights for policy 0, policy_version 158137 (0.0008) -[2023-11-28 04:21:05,824][87426] Updated weights for policy 1, policy_version 157860 (0.0009) -[2023-11-28 04:21:06,205][87426] Updated weights for policy 1, policy_version 157870 (0.0012) -[2023-11-28 04:21:06,574][87426] Updated weights for policy 1, policy_version 157880 (0.0010) -[2023-11-28 04:21:07,064][87424] Updated weights for policy 0, policy_version 158147 (0.0009) -[2023-11-28 04:21:07,450][87424] Updated weights for policy 0, policy_version 158157 (0.0012) -[2023-11-28 04:21:07,833][87424] Updated weights for policy 0, policy_version 158167 (0.0012) -[2023-11-28 04:21:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 80912384. Throughput: 0: 2755.6, 1: 2735.7. Samples: 80926276. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:21:08,445][86177] Avg episode reward: [(0, '-505.560'), (1, '-515.070')] -[2023-11-28 04:21:08,743][87426] Updated weights for policy 1, policy_version 157890 (0.0011) -[2023-11-28 04:21:09,123][87426] Updated weights for policy 1, policy_version 157900 (0.0011) -[2023-11-28 04:21:09,499][87426] Updated weights for policy 1, policy_version 157910 (0.0012) -[2023-11-28 04:21:09,868][87424] Updated weights for policy 0, policy_version 158177 (0.0011) -[2023-11-28 04:21:09,880][87426] Updated weights for policy 1, policy_version 157920 (0.0012) -[2023-11-28 04:21:10,250][87424] Updated weights for policy 0, policy_version 158187 (0.0011) -[2023-11-28 04:21:10,644][87424] Updated weights for policy 0, policy_version 158197 (0.0012) -[2023-11-28 04:21:11,035][87424] Updated weights for policy 0, policy_version 158207 (0.0012) -[2023-11-28 04:21:12,118][87426] Updated weights for policy 1, policy_version 157930 (0.0010) -[2023-11-28 04:21:12,502][87426] Updated weights for policy 1, policy_version 157940 (0.0009) -[2023-11-28 04:21:12,881][87426] Updated weights for policy 1, policy_version 157950 (0.0008) -[2023-11-28 04:21:13,356][87424] Updated weights for policy 0, policy_version 158217 (0.0010) -[2023-11-28 04:21:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80936960. Throughput: 0: 2748.1, 1: 2759.0. Samples: 80951660. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:21:13,445][86177] Avg episode reward: [(0, '-505.240'), (1, '-541.400')] -[2023-11-28 04:21:13,734][87424] Updated weights for policy 0, policy_version 158227 (0.0009) -[2023-11-28 04:21:14,129][87424] Updated weights for policy 0, policy_version 158237 (0.0008) -[2023-11-28 04:21:14,911][87426] Updated weights for policy 1, policy_version 157960 (0.0011) -[2023-11-28 04:21:15,311][87426] Updated weights for policy 1, policy_version 157970 (0.0011) -[2023-11-28 04:21:15,682][87426] Updated weights for policy 1, policy_version 157980 (0.0011) -[2023-11-28 04:21:16,364][87424] Updated weights for policy 0, policy_version 158247 (0.0012) -[2023-11-28 04:21:16,739][87424] Updated weights for policy 0, policy_version 158257 (0.0012) -[2023-11-28 04:21:17,121][87424] Updated weights for policy 0, policy_version 158267 (0.0011) -[2023-11-28 04:21:17,621][87426] Updated weights for policy 1, policy_version 157990 (0.0009) -[2023-11-28 04:21:18,002][87426] Updated weights for policy 1, policy_version 158000 (0.0008) -[2023-11-28 04:21:18,383][87426] Updated weights for policy 1, policy_version 158010 (0.0007) -[2023-11-28 04:21:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80961536. Throughput: 0: 2736.8, 1: 2772.4. Samples: 80976748. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:21:18,445][86177] Avg episode reward: [(0, '-501.520'), (1, '-540.380')] -[2023-11-28 04:21:19,124][87424] Updated weights for policy 0, policy_version 158277 (0.0012) -[2023-11-28 04:21:19,503][87424] Updated weights for policy 0, policy_version 158287 (0.0010) -[2023-11-28 04:21:19,880][87424] Updated weights for policy 0, policy_version 158297 (0.0011) -[2023-11-28 04:21:20,246][87426] Updated weights for policy 1, policy_version 158020 (0.0009) -[2023-11-28 04:21:20,628][87426] Updated weights for policy 1, policy_version 158030 (0.0012) -[2023-11-28 04:21:21,001][87426] Updated weights for policy 1, policy_version 158040 (0.0012) -[2023-11-28 04:21:22,430][87424] Updated weights for policy 0, policy_version 158307 (0.0012) -[2023-11-28 04:21:22,824][87424] Updated weights for policy 0, policy_version 158317 (0.0012) -[2023-11-28 04:21:23,207][87424] Updated weights for policy 0, policy_version 158327 (0.0016) -[2023-11-28 04:21:23,404][87426] Updated weights for policy 1, policy_version 158050 (0.0011) -[2023-11-28 04:21:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 80986112. Throughput: 0: 2711.6, 1: 2762.6. Samples: 81008272. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:21:23,445][86177] Avg episode reward: [(0, '-497.520'), (1, '-532.520')] -[2023-11-28 04:21:23,790][87426] Updated weights for policy 1, policy_version 158060 (0.0011) -[2023-11-28 04:21:24,161][87426] Updated weights for policy 1, policy_version 158070 (0.0009) -[2023-11-28 04:21:24,544][87426] Updated weights for policy 1, policy_version 158080 (0.0008) -[2023-11-28 04:21:25,463][87424] Updated weights for policy 0, policy_version 158337 (0.0012) -[2023-11-28 04:21:25,846][87424] Updated weights for policy 0, policy_version 158347 (0.0008) -[2023-11-28 04:21:26,160][87426] Updated weights for policy 1, policy_version 158090 (0.0007) -[2023-11-28 04:21:26,224][87424] Updated weights for policy 0, policy_version 158357 (0.0007) -[2023-11-28 04:21:26,539][87426] Updated weights for policy 1, policy_version 158100 (0.0007) -[2023-11-28 04:21:26,601][87424] Updated weights for policy 0, policy_version 158367 (0.0008) -[2023-11-28 04:21:26,922][87426] Updated weights for policy 1, policy_version 158110 (0.0007) -[2023-11-28 04:21:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 81018880. Throughput: 0: 2730.5, 1: 2762.1. Samples: 81033688. Policy #0 lag: (min: 40.0, avg: 52.2, max: 76.0) -[2023-11-28 04:21:28,445][86177] Avg episode reward: [(0, '-508.280'), (1, '-583.290')] -[2023-11-28 04:21:28,559][87424] Updated weights for policy 0, policy_version 158377 (0.0011) -[2023-11-28 04:21:28,950][87424] Updated weights for policy 0, policy_version 158387 (0.0012) -[2023-11-28 04:21:29,140][87426] Updated weights for policy 1, policy_version 158120 (0.0010) -[2023-11-28 04:21:29,334][87424] Updated weights for policy 0, policy_version 158397 (0.0012) -[2023-11-28 04:21:29,521][87426] Updated weights for policy 1, policy_version 158130 (0.0011) -[2023-11-28 04:21:29,889][87426] Updated weights for policy 1, policy_version 158140 (0.0011) -[2023-11-28 04:21:31,328][87424] Updated weights for policy 0, policy_version 158407 (0.0012) -[2023-11-28 04:21:31,711][87424] Updated weights for policy 0, policy_version 158417 (0.0011) -[2023-11-28 04:21:32,081][87424] Updated weights for policy 0, policy_version 158427 (0.0011) -[2023-11-28 04:21:32,369][87426] Updated weights for policy 1, policy_version 158150 (0.0010) -[2023-11-28 04:21:32,741][87426] Updated weights for policy 1, policy_version 158160 (0.0011) -[2023-11-28 04:21:33,131][87426] Updated weights for policy 1, policy_version 158170 (0.0011) -[2023-11-28 04:21:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 81051648. Throughput: 0: 2756.0, 1: 2749.4. Samples: 81057856. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:21:33,445][86177] Avg episode reward: [(0, '-532.800'), (1, '-554.020')] -[2023-11-28 04:21:34,044][87424] Updated weights for policy 0, policy_version 158437 (0.0011) -[2023-11-28 04:21:34,427][87424] Updated weights for policy 0, policy_version 158447 (0.0011) -[2023-11-28 04:21:34,810][87424] Updated weights for policy 0, policy_version 158457 (0.0009) -[2023-11-28 04:21:35,213][87426] Updated weights for policy 1, policy_version 158180 (0.0012) -[2023-11-28 04:21:35,593][87426] Updated weights for policy 1, policy_version 158190 (0.0012) -[2023-11-28 04:21:35,969][87426] Updated weights for policy 1, policy_version 158200 (0.0011) -[2023-11-28 04:21:36,974][87424] Updated weights for policy 0, policy_version 158467 (0.0011) -[2023-11-28 04:21:37,356][87424] Updated weights for policy 0, policy_version 158477 (0.0012) -[2023-11-28 04:21:37,739][87424] Updated weights for policy 0, policy_version 158487 (0.0012) -[2023-11-28 04:21:38,241][87426] Updated weights for policy 1, policy_version 158210 (0.0012) -[2023-11-28 04:21:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 81076224. Throughput: 0: 2745.4, 1: 2770.0. Samples: 81092044. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:21:38,445][86177] Avg episode reward: [(0, '-578.400'), (1, '-553.620')] -[2023-11-28 04:21:38,628][87426] Updated weights for policy 1, policy_version 158220 (0.0012) -[2023-11-28 04:21:39,006][87426] Updated weights for policy 1, policy_version 158230 (0.0012) -[2023-11-28 04:21:39,377][87426] Updated weights for policy 1, policy_version 158240 (0.0012) -[2023-11-28 04:21:39,599][87424] Updated weights for policy 0, policy_version 158497 (0.0009) -[2023-11-28 04:21:39,994][87424] Updated weights for policy 0, policy_version 158507 (0.0012) -[2023-11-28 04:21:40,367][87424] Updated weights for policy 0, policy_version 158517 (0.0010) -[2023-11-28 04:21:40,746][87424] Updated weights for policy 0, policy_version 158527 (0.0011) -[2023-11-28 04:21:41,355][87426] Updated weights for policy 1, policy_version 158250 (0.0012) -[2023-11-28 04:21:41,730][87426] Updated weights for policy 1, policy_version 158260 (0.0009) -[2023-11-28 04:21:42,110][87426] Updated weights for policy 1, policy_version 158270 (0.0009) -[2023-11-28 04:21:42,618][87424] Updated weights for policy 0, policy_version 158537 (0.0011) -[2023-11-28 04:21:43,004][87424] Updated weights for policy 0, policy_version 158547 (0.0011) -[2023-11-28 04:21:43,386][87424] Updated weights for policy 0, policy_version 158557 (0.0011) -[2023-11-28 04:21:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 81100800. Throughput: 0: 2742.1, 1: 2761.5. Samples: 81115772. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:21:43,445][86177] Avg episode reward: [(0, '-578.530'), (1, '-538.870')] -[2023-11-28 04:21:44,467][87426] Updated weights for policy 1, policy_version 158280 (0.0010) -[2023-11-28 04:21:44,845][87426] Updated weights for policy 1, policy_version 158290 (0.0007) -[2023-11-28 04:21:45,220][87426] Updated weights for policy 1, policy_version 158300 (0.0007) -[2023-11-28 04:21:45,688][87424] Updated weights for policy 0, policy_version 158567 (0.0011) -[2023-11-28 04:21:46,063][87424] Updated weights for policy 0, policy_version 158577 (0.0011) -[2023-11-28 04:21:46,442][87424] Updated weights for policy 0, policy_version 158587 (0.0008) -[2023-11-28 04:21:47,736][87426] Updated weights for policy 1, policy_version 158310 (0.0009) -[2023-11-28 04:21:48,122][87426] Updated weights for policy 1, policy_version 158320 (0.0007) -[2023-11-28 04:21:48,289][87424] Updated weights for policy 0, policy_version 158597 (0.0008) -[2023-11-28 04:21:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 81125376. Throughput: 0: 2754.1, 1: 2731.9. Samples: 81140620. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:21:48,445][86177] Avg episode reward: [(0, '-551.680'), (1, '-493.550')] -[2023-11-28 04:21:48,501][87426] Updated weights for policy 1, policy_version 158330 (0.0010) -[2023-11-28 04:21:48,667][87424] Updated weights for policy 0, policy_version 158607 (0.0007) -[2023-11-28 04:21:49,051][87424] Updated weights for policy 0, policy_version 158617 (0.0011) -[2023-11-28 04:21:50,269][87426] Updated weights for policy 1, policy_version 158340 (0.0011) -[2023-11-28 04:21:50,647][87426] Updated weights for policy 1, policy_version 158350 (0.0009) -[2023-11-28 04:21:51,028][87426] Updated weights for policy 1, policy_version 158360 (0.0011) -[2023-11-28 04:21:51,556][87424] Updated weights for policy 0, policy_version 158627 (0.0011) -[2023-11-28 04:21:51,942][87424] Updated weights for policy 0, policy_version 158637 (0.0010) -[2023-11-28 04:21:52,313][87424] Updated weights for policy 0, policy_version 158647 (0.0012) -[2023-11-28 04:21:53,416][87426] Updated weights for policy 1, policy_version 158370 (0.0011) -[2023-11-28 04:21:53,446][86177] Fps is (10 sec: 5733.2, 60 sec: 5597.7, 300 sec: 5470.5). Total num frames: 81158144. Throughput: 0: 2737.0, 1: 2739.2. Samples: 81172716. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:21:53,447][86177] Avg episode reward: [(0, '-550.190'), (1, '-509.490')] -[2023-11-28 04:21:53,795][87426] Updated weights for policy 1, policy_version 158380 (0.0010) -[2023-11-28 04:21:54,175][87426] Updated weights for policy 1, policy_version 158390 (0.0009) -[2023-11-28 04:21:54,565][87426] Updated weights for policy 1, policy_version 158400 (0.0009) -[2023-11-28 04:21:54,671][87424] Updated weights for policy 0, policy_version 158657 (0.0011) -[2023-11-28 04:21:55,064][87424] Updated weights for policy 0, policy_version 158667 (0.0010) -[2023-11-28 04:21:55,457][87424] Updated weights for policy 0, policy_version 158677 (0.0008) -[2023-11-28 04:21:55,841][87424] Updated weights for policy 0, policy_version 158687 (0.0008) -[2023-11-28 04:21:57,053][87426] Updated weights for policy 1, policy_version 158410 (0.0012) -[2023-11-28 04:21:57,424][87426] Updated weights for policy 1, policy_version 158420 (0.0012) -[2023-11-28 04:21:57,523][87424] Updated weights for policy 0, policy_version 158697 (0.0007) -[2023-11-28 04:21:57,811][87426] Updated weights for policy 1, policy_version 158430 (0.0012) -[2023-11-28 04:21:57,915][87424] Updated weights for policy 0, policy_version 158707 (0.0008) -[2023-11-28 04:21:58,294][87424] Updated weights for policy 0, policy_version 158717 (0.0009) -[2023-11-28 04:21:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 81190912. Throughput: 0: 2734.5, 1: 2692.1. Samples: 81195856. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:21:58,445][86177] Avg episode reward: [(0, '-507.950'), (1, '-509.960')] -[2023-11-28 04:22:00,335][87426] Updated weights for policy 1, policy_version 158440 (0.0010) -[2023-11-28 04:22:00,509][87424] Updated weights for policy 0, policy_version 158727 (0.0010) -[2023-11-28 04:22:00,714][87426] Updated weights for policy 1, policy_version 158450 (0.0008) -[2023-11-28 04:22:00,901][87424] Updated weights for policy 0, policy_version 158737 (0.0010) -[2023-11-28 04:22:01,095][87426] Updated weights for policy 1, policy_version 158460 (0.0008) -[2023-11-28 04:22:01,274][87424] Updated weights for policy 0, policy_version 158747 (0.0009) -[2023-11-28 04:22:03,444][86177] Fps is (10 sec: 4916.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 81207296. Throughput: 0: 2750.5, 1: 2692.8. Samples: 81221696. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:22:03,445][86177] Avg episode reward: [(0, '-520.530'), (1, '-510.300')] -[2023-11-28 04:22:03,568][87424] Updated weights for policy 0, policy_version 158757 (0.0008) -[2023-11-28 04:22:03,640][87426] Updated weights for policy 1, policy_version 158470 (0.0009) -[2023-11-28 04:22:03,954][87424] Updated weights for policy 0, policy_version 158767 (0.0007) -[2023-11-28 04:22:04,009][87426] Updated weights for policy 1, policy_version 158480 (0.0007) -[2023-11-28 04:22:04,327][87424] Updated weights for policy 0, policy_version 158777 (0.0007) -[2023-11-28 04:22:04,392][87426] Updated weights for policy 1, policy_version 158490 (0.0008) -[2023-11-28 04:22:06,429][87424] Updated weights for policy 0, policy_version 158787 (0.0008) -[2023-11-28 04:22:06,614][87426] Updated weights for policy 1, policy_version 158500 (0.0010) -[2023-11-28 04:22:06,836][87424] Updated weights for policy 0, policy_version 158797 (0.0011) -[2023-11-28 04:22:06,983][87426] Updated weights for policy 1, policy_version 158510 (0.0011) -[2023-11-28 04:22:07,213][87424] Updated weights for policy 0, policy_version 158807 (0.0009) -[2023-11-28 04:22:07,363][87426] Updated weights for policy 1, policy_version 158520 (0.0009) -[2023-11-28 04:22:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 81240064. Throughput: 0: 2779.3, 1: 2691.5. Samples: 81254456. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:22:08,445][86177] Avg episode reward: [(0, '-521.180'), (1, '-511.880')] -[2023-11-28 04:22:09,115][87424] Updated weights for policy 0, policy_version 158817 (0.0010) -[2023-11-28 04:22:09,183][87426] Updated weights for policy 1, policy_version 158530 (0.0010) -[2023-11-28 04:22:09,500][87424] Updated weights for policy 0, policy_version 158827 (0.0011) -[2023-11-28 04:22:09,564][87426] Updated weights for policy 1, policy_version 158540 (0.0012) -[2023-11-28 04:22:09,883][87424] Updated weights for policy 0, policy_version 158837 (0.0009) -[2023-11-28 04:22:09,949][87426] Updated weights for policy 1, policy_version 158550 (0.0010) -[2023-11-28 04:22:10,263][87424] Updated weights for policy 0, policy_version 158847 (0.0011) -[2023-11-28 04:22:10,324][87426] Updated weights for policy 1, policy_version 158560 (0.0009) -[2023-11-28 04:22:12,685][87426] Updated weights for policy 1, policy_version 158570 (0.0010) -[2023-11-28 04:22:12,695][87424] Updated weights for policy 0, policy_version 158857 (0.0011) -[2023-11-28 04:22:13,061][87426] Updated weights for policy 1, policy_version 158580 (0.0011) -[2023-11-28 04:22:13,075][87424] Updated weights for policy 0, policy_version 158867 (0.0012) -[2023-11-28 04:22:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 81256448. Throughput: 0: 2780.8, 1: 2686.9. Samples: 81279736. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:22:13,445][86177] Avg episode reward: [(0, '-539.290'), (1, '-499.820')] -[2023-11-28 04:22:13,446][87426] Updated weights for policy 1, policy_version 158590 (0.0009) -[2023-11-28 04:22:13,458][87424] Updated weights for policy 0, policy_version 158877 (0.0008) -[2023-11-28 04:22:15,199][87424] Updated weights for policy 0, policy_version 158887 (0.0012) -[2023-11-28 04:22:15,584][87424] Updated weights for policy 0, policy_version 158897 (0.0012) -[2023-11-28 04:22:15,717][87426] Updated weights for policy 1, policy_version 158600 (0.0008) -[2023-11-28 04:22:15,954][87424] Updated weights for policy 0, policy_version 158907 (0.0012) -[2023-11-28 04:22:16,100][87426] Updated weights for policy 1, policy_version 158610 (0.0010) -[2023-11-28 04:22:16,478][87426] Updated weights for policy 1, policy_version 158620 (0.0012) -[2023-11-28 04:22:17,648][87424] Updated weights for policy 0, policy_version 158917 (0.0011) -[2023-11-28 04:22:18,025][87424] Updated weights for policy 0, policy_version 158927 (0.0011) -[2023-11-28 04:22:18,197][87426] Updated weights for policy 1, policy_version 158630 (0.0010) -[2023-11-28 04:22:18,419][87424] Updated weights for policy 0, policy_version 158937 (0.0009) -[2023-11-28 04:22:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 81289216. Throughput: 0: 2777.5, 1: 2705.1. Samples: 81304572. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:22:18,445][86177] Avg episode reward: [(0, '-537.440'), (1, '-501.470')] -[2023-11-28 04:22:18,581][87426] Updated weights for policy 1, policy_version 158640 (0.0010) -[2023-11-28 04:22:18,677][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000158944_40689664.pth... -[2023-11-28 04:22:18,723][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000156384_40034304.pth -[2023-11-28 04:22:18,968][87426] Updated weights for policy 1, policy_version 158650 (0.0008) -[2023-11-28 04:22:19,194][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000158656_40615936.pth... -[2023-11-28 04:22:19,238][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000156096_39960576.pth -[2023-11-28 04:22:20,713][87424] Updated weights for policy 0, policy_version 158947 (0.0009) -[2023-11-28 04:22:21,119][87424] Updated weights for policy 0, policy_version 158957 (0.0012) -[2023-11-28 04:22:21,221][87426] Updated weights for policy 1, policy_version 158660 (0.0011) -[2023-11-28 04:22:21,494][87424] Updated weights for policy 0, policy_version 158967 (0.0012) -[2023-11-28 04:22:21,602][87426] Updated weights for policy 1, policy_version 158670 (0.0008) -[2023-11-28 04:22:21,984][87426] Updated weights for policy 1, policy_version 158680 (0.0009) -[2023-11-28 04:22:23,428][87424] Updated weights for policy 0, policy_version 158977 (0.0012) -[2023-11-28 04:22:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5470.6). Total num frames: 81321984. Throughput: 0: 2798.9, 1: 2665.5. Samples: 81337944. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:22:23,445][86177] Avg episode reward: [(0, '-535.650'), (1, '-498.820')] -[2023-11-28 04:22:23,817][87424] Updated weights for policy 0, policy_version 158987 (0.0008) -[2023-11-28 04:22:24,212][87424] Updated weights for policy 0, policy_version 158997 (0.0007) -[2023-11-28 04:22:24,541][87426] Updated weights for policy 1, policy_version 158690 (0.0011) -[2023-11-28 04:22:24,594][87424] Updated weights for policy 0, policy_version 159007 (0.0007) -[2023-11-28 04:22:24,915][87426] Updated weights for policy 1, policy_version 158700 (0.0010) -[2023-11-28 04:22:25,290][87426] Updated weights for policy 1, policy_version 158710 (0.0011) -[2023-11-28 04:22:25,661][87426] Updated weights for policy 1, policy_version 158720 (0.0011) -[2023-11-28 04:22:26,586][87424] Updated weights for policy 0, policy_version 159017 (0.0007) -[2023-11-28 04:22:26,970][87424] Updated weights for policy 0, policy_version 159027 (0.0007) -[2023-11-28 04:22:27,345][87424] Updated weights for policy 0, policy_version 159037 (0.0007) -[2023-11-28 04:22:28,291][87426] Updated weights for policy 1, policy_version 158730 (0.0008) -[2023-11-28 04:22:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 81346560. Throughput: 0: 2798.0, 1: 2675.1. Samples: 81362064. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:22:28,445][86177] Avg episode reward: [(0, '-526.110'), (1, '-491.600')] -[2023-11-28 04:22:28,676][87426] Updated weights for policy 1, policy_version 158740 (0.0007) -[2023-11-28 04:22:29,062][87426] Updated weights for policy 1, policy_version 158750 (0.0010) -[2023-11-28 04:22:29,842][87424] Updated weights for policy 0, policy_version 159047 (0.0007) -[2023-11-28 04:22:30,231][87424] Updated weights for policy 0, policy_version 159057 (0.0009) -[2023-11-28 04:22:30,614][87424] Updated weights for policy 0, policy_version 159067 (0.0010) -[2023-11-28 04:22:31,507][87426] Updated weights for policy 1, policy_version 158760 (0.0012) -[2023-11-28 04:22:31,882][87426] Updated weights for policy 1, policy_version 158770 (0.0012) -[2023-11-28 04:22:32,261][87426] Updated weights for policy 1, policy_version 158780 (0.0011) -[2023-11-28 04:22:32,879][87424] Updated weights for policy 0, policy_version 159077 (0.0008) -[2023-11-28 04:22:33,258][87424] Updated weights for policy 0, policy_version 159087 (0.0012) -[2023-11-28 04:22:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 81371136. Throughput: 0: 2795.6, 1: 2672.9. Samples: 81386704. Policy #0 lag: (min: 13.0, avg: 35.2, max: 74.0) -[2023-11-28 04:22:33,445][86177] Avg episode reward: [(0, '-517.570'), (1, '-491.900')] -[2023-11-28 04:22:33,648][87424] Updated weights for policy 0, policy_version 159097 (0.0012) -[2023-11-28 04:22:34,538][87426] Updated weights for policy 1, policy_version 158790 (0.0010) -[2023-11-28 04:22:34,923][87426] Updated weights for policy 1, policy_version 158800 (0.0011) -[2023-11-28 04:22:35,303][87426] Updated weights for policy 1, policy_version 158810 (0.0011) -[2023-11-28 04:22:35,682][87424] Updated weights for policy 0, policy_version 159107 (0.0012) -[2023-11-28 04:22:36,069][87424] Updated weights for policy 0, policy_version 159117 (0.0012) -[2023-11-28 04:22:36,442][87424] Updated weights for policy 0, policy_version 159127 (0.0009) -[2023-11-28 04:22:37,087][87426] Updated weights for policy 1, policy_version 158820 (0.0010) -[2023-11-28 04:22:37,461][87426] Updated weights for policy 1, policy_version 158830 (0.0011) -[2023-11-28 04:22:37,842][87426] Updated weights for policy 1, policy_version 158840 (0.0009) -[2023-11-28 04:22:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 81403904. Throughput: 0: 2818.4, 1: 2671.1. Samples: 81419728. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:22:38,445][86177] Avg episode reward: [(0, '-501.970'), (1, '-490.430')] -[2023-11-28 04:22:38,534][87424] Updated weights for policy 0, policy_version 159137 (0.0008) -[2023-11-28 04:22:38,918][87424] Updated weights for policy 0, policy_version 159147 (0.0008) -[2023-11-28 04:22:39,308][87424] Updated weights for policy 0, policy_version 159157 (0.0009) -[2023-11-28 04:22:39,684][87424] Updated weights for policy 0, policy_version 159167 (0.0011) -[2023-11-28 04:22:39,821][87426] Updated weights for policy 1, policy_version 158850 (0.0008) -[2023-11-28 04:22:40,197][87426] Updated weights for policy 1, policy_version 158860 (0.0010) -[2023-11-28 04:22:40,571][87426] Updated weights for policy 1, policy_version 158870 (0.0010) -[2023-11-28 04:22:40,951][87426] Updated weights for policy 1, policy_version 158880 (0.0009) -[2023-11-28 04:22:41,954][87424] Updated weights for policy 0, policy_version 159177 (0.0011) -[2023-11-28 04:22:42,351][87424] Updated weights for policy 0, policy_version 159187 (0.0010) -[2023-11-28 04:22:42,730][87424] Updated weights for policy 0, policy_version 159197 (0.0008) -[2023-11-28 04:22:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 81428480. Throughput: 0: 2821.9, 1: 2675.1. Samples: 81443220. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:22:43,445][86177] Avg episode reward: [(0, '-513.330'), (1, '-530.720')] -[2023-11-28 04:22:43,500][87426] Updated weights for policy 1, policy_version 158890 (0.0012) -[2023-11-28 04:22:43,890][87426] Updated weights for policy 1, policy_version 158900 (0.0011) -[2023-11-28 04:22:44,262][87426] Updated weights for policy 1, policy_version 158910 (0.0010) -[2023-11-28 04:22:44,919][87424] Updated weights for policy 0, policy_version 159207 (0.0010) -[2023-11-28 04:22:45,309][87424] Updated weights for policy 0, policy_version 159217 (0.0010) -[2023-11-28 04:22:45,691][87424] Updated weights for policy 0, policy_version 159227 (0.0012) -[2023-11-28 04:22:46,049][87426] Updated weights for policy 1, policy_version 158920 (0.0012) -[2023-11-28 04:22:46,431][87426] Updated weights for policy 1, policy_version 158930 (0.0012) -[2023-11-28 04:22:46,812][87426] Updated weights for policy 1, policy_version 158940 (0.0012) -[2023-11-28 04:22:47,670][87424] Updated weights for policy 0, policy_version 159237 (0.0012) -[2023-11-28 04:22:48,061][87424] Updated weights for policy 0, policy_version 159247 (0.0012) -[2023-11-28 04:22:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 81453056. Throughput: 0: 2787.5, 1: 2673.8. Samples: 81467456. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:22:48,445][86177] Avg episode reward: [(0, '-553.290'), (1, '-548.350')] -[2023-11-28 04:22:48,456][87424] Updated weights for policy 0, policy_version 159257 (0.0011) -[2023-11-28 04:22:48,959][87426] Updated weights for policy 1, policy_version 158950 (0.0012) -[2023-11-28 04:22:49,341][87426] Updated weights for policy 1, policy_version 158960 (0.0010) -[2023-11-28 04:22:49,713][87426] Updated weights for policy 1, policy_version 158970 (0.0007) -[2023-11-28 04:22:50,922][87424] Updated weights for policy 0, policy_version 159267 (0.0009) -[2023-11-28 04:22:51,297][87424] Updated weights for policy 0, policy_version 159277 (0.0012) -[2023-11-28 04:22:51,679][87424] Updated weights for policy 0, policy_version 159287 (0.0010) -[2023-11-28 04:22:52,314][87426] Updated weights for policy 1, policy_version 158980 (0.0009) -[2023-11-28 04:22:52,696][87426] Updated weights for policy 1, policy_version 158990 (0.0007) -[2023-11-28 04:22:53,071][87426] Updated weights for policy 1, policy_version 159000 (0.0011) -[2023-11-28 04:22:53,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.5, 300 sec: 5470.6). Total num frames: 81485824. Throughput: 0: 2758.3, 1: 2659.8. Samples: 81498272. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:22:53,445][86177] Avg episode reward: [(0, '-546.260'), (1, '-550.290')] -[2023-11-28 04:22:54,206][87424] Updated weights for policy 0, policy_version 159297 (0.0010) -[2023-11-28 04:22:54,595][87424] Updated weights for policy 0, policy_version 159307 (0.0012) -[2023-11-28 04:22:54,977][87424] Updated weights for policy 0, policy_version 159317 (0.0012) -[2023-11-28 04:22:55,347][87424] Updated weights for policy 0, policy_version 159327 (0.0012) -[2023-11-28 04:22:55,586][87426] Updated weights for policy 1, policy_version 159010 (0.0012) -[2023-11-28 04:22:55,964][87426] Updated weights for policy 1, policy_version 159020 (0.0011) -[2023-11-28 04:22:56,351][87426] Updated weights for policy 1, policy_version 159030 (0.0012) -[2023-11-28 04:22:56,731][87426] Updated weights for policy 1, policy_version 159040 (0.0011) -[2023-11-28 04:22:57,759][87424] Updated weights for policy 0, policy_version 159337 (0.0012) -[2023-11-28 04:22:58,140][87424] Updated weights for policy 0, policy_version 159347 (0.0010) -[2023-11-28 04:22:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 81502208. Throughput: 0: 2722.8, 1: 2681.0. Samples: 81522908. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:22:58,445][86177] Avg episode reward: [(0, '-544.000'), (1, '-511.600')] -[2023-11-28 04:22:58,526][87424] Updated weights for policy 0, policy_version 159357 (0.0008) -[2023-11-28 04:22:58,884][87426] Updated weights for policy 1, policy_version 159050 (0.0012) -[2023-11-28 04:22:59,255][87426] Updated weights for policy 1, policy_version 159060 (0.0007) -[2023-11-28 04:22:59,632][87426] Updated weights for policy 1, policy_version 159070 (0.0011) -[2023-11-28 04:23:00,804][87424] Updated weights for policy 0, policy_version 159367 (0.0009) -[2023-11-28 04:23:01,194][87424] Updated weights for policy 0, policy_version 159377 (0.0007) -[2023-11-28 04:23:01,591][87424] Updated weights for policy 0, policy_version 159387 (0.0008) -[2023-11-28 04:23:02,130][87426] Updated weights for policy 1, policy_version 159080 (0.0009) -[2023-11-28 04:23:02,513][87426] Updated weights for policy 1, policy_version 159090 (0.0011) -[2023-11-28 04:23:02,885][87426] Updated weights for policy 1, policy_version 159100 (0.0009) -[2023-11-28 04:23:03,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 81534976. Throughput: 0: 2712.7, 1: 2660.2. Samples: 81546352. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:23:03,445][86177] Avg episode reward: [(0, '-546.980'), (1, '-522.070')] -[2023-11-28 04:23:03,761][87424] Updated weights for policy 0, policy_version 159397 (0.0009) -[2023-11-28 04:23:04,158][87424] Updated weights for policy 0, policy_version 159407 (0.0007) -[2023-11-28 04:23:04,544][87424] Updated weights for policy 0, policy_version 159417 (0.0007) -[2023-11-28 04:23:04,929][87426] Updated weights for policy 1, policy_version 159110 (0.0010) -[2023-11-28 04:23:05,308][87426] Updated weights for policy 1, policy_version 159120 (0.0009) -[2023-11-28 04:23:05,691][87426] Updated weights for policy 1, policy_version 159130 (0.0008) -[2023-11-28 04:23:06,611][87424] Updated weights for policy 0, policy_version 159427 (0.0010) -[2023-11-28 04:23:06,984][87424] Updated weights for policy 0, policy_version 159437 (0.0012) -[2023-11-28 04:23:07,354][87424] Updated weights for policy 0, policy_version 159447 (0.0010) -[2023-11-28 04:23:07,823][87426] Updated weights for policy 1, policy_version 159140 (0.0008) -[2023-11-28 04:23:08,202][87426] Updated weights for policy 1, policy_version 159150 (0.0007) -[2023-11-28 04:23:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 81559552. Throughput: 0: 2692.4, 1: 2649.3. Samples: 81578320. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:23:08,445][86177] Avg episode reward: [(0, '-509.310'), (1, '-506.130')] -[2023-11-28 04:23:08,578][87426] Updated weights for policy 1, policy_version 159160 (0.0007) -[2023-11-28 04:23:09,552][87424] Updated weights for policy 0, policy_version 159457 (0.0008) -[2023-11-28 04:23:09,938][87424] Updated weights for policy 0, policy_version 159467 (0.0011) -[2023-11-28 04:23:10,318][87424] Updated weights for policy 0, policy_version 159477 (0.0011) -[2023-11-28 04:23:10,621][87426] Updated weights for policy 1, policy_version 159170 (0.0009) -[2023-11-28 04:23:10,703][87424] Updated weights for policy 0, policy_version 159487 (0.0011) -[2023-11-28 04:23:10,997][87426] Updated weights for policy 1, policy_version 159180 (0.0011) -[2023-11-28 04:23:11,378][87426] Updated weights for policy 1, policy_version 159190 (0.0012) -[2023-11-28 04:23:11,753][87426] Updated weights for policy 1, policy_version 159200 (0.0012) -[2023-11-28 04:23:13,102][87424] Updated weights for policy 0, policy_version 159497 (0.0011) -[2023-11-28 04:23:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 81584128. Throughput: 0: 2682.0, 1: 2654.8. Samples: 81602224. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:23:13,445][86177] Avg episode reward: [(0, '-508.380'), (1, '-521.670')] -[2023-11-28 04:23:13,481][87424] Updated weights for policy 0, policy_version 159507 (0.0012) -[2023-11-28 04:23:13,860][87424] Updated weights for policy 0, policy_version 159517 (0.0012) -[2023-11-28 04:23:13,937][87426] Updated weights for policy 1, policy_version 159210 (0.0012) -[2023-11-28 04:23:14,327][87426] Updated weights for policy 1, policy_version 159220 (0.0012) -[2023-11-28 04:23:14,709][87426] Updated weights for policy 1, policy_version 159230 (0.0009) -[2023-11-28 04:23:15,896][87424] Updated weights for policy 0, policy_version 159527 (0.0011) -[2023-11-28 04:23:16,283][87424] Updated weights for policy 0, policy_version 159537 (0.0008) -[2023-11-28 04:23:16,669][87424] Updated weights for policy 0, policy_version 159547 (0.0008) -[2023-11-28 04:23:16,879][87426] Updated weights for policy 1, policy_version 159240 (0.0008) -[2023-11-28 04:23:17,279][87426] Updated weights for policy 1, policy_version 159250 (0.0011) -[2023-11-28 04:23:17,653][87426] Updated weights for policy 1, policy_version 159260 (0.0011) -[2023-11-28 04:23:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 81616896. Throughput: 0: 2675.6, 1: 2677.9. Samples: 81627612. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:23:18,445][86177] Avg episode reward: [(0, '-524.610'), (1, '-519.540')] -[2023-11-28 04:23:18,485][87424] Updated weights for policy 0, policy_version 159557 (0.0012) -[2023-11-28 04:23:18,864][87424] Updated weights for policy 0, policy_version 159567 (0.0012) -[2023-11-28 04:23:19,237][87424] Updated weights for policy 0, policy_version 159577 (0.0011) -[2023-11-28 04:23:19,287][87426] Updated weights for policy 1, policy_version 159270 (0.0011) -[2023-11-28 04:23:19,669][87426] Updated weights for policy 1, policy_version 159280 (0.0012) -[2023-11-28 04:23:20,044][87426] Updated weights for policy 1, policy_version 159290 (0.0011) -[2023-11-28 04:23:21,357][87424] Updated weights for policy 0, policy_version 159587 (0.0011) -[2023-11-28 04:23:21,738][87424] Updated weights for policy 0, policy_version 159597 (0.0009) -[2023-11-28 04:23:22,129][87424] Updated weights for policy 0, policy_version 159607 (0.0010) -[2023-11-28 04:23:22,276][87426] Updated weights for policy 1, policy_version 159300 (0.0009) -[2023-11-28 04:23:22,664][87426] Updated weights for policy 1, policy_version 159310 (0.0011) -[2023-11-28 04:23:23,039][87426] Updated weights for policy 1, policy_version 159320 (0.0010) -[2023-11-28 04:23:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 81649664. Throughput: 0: 2667.0, 1: 2691.5. Samples: 81660864. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:23:23,445][86177] Avg episode reward: [(0, '-519.510'), (1, '-506.660')] -[2023-11-28 04:23:24,618][87424] Updated weights for policy 0, policy_version 159617 (0.0011) -[2023-11-28 04:23:25,011][87424] Updated weights for policy 0, policy_version 159627 (0.0012) -[2023-11-28 04:23:25,274][87426] Updated weights for policy 1, policy_version 159330 (0.0011) -[2023-11-28 04:23:25,392][87424] Updated weights for policy 0, policy_version 159637 (0.0012) -[2023-11-28 04:23:25,657][87426] Updated weights for policy 1, policy_version 159340 (0.0007) -[2023-11-28 04:23:25,775][87424] Updated weights for policy 0, policy_version 159647 (0.0012) -[2023-11-28 04:23:26,031][87426] Updated weights for policy 1, policy_version 159350 (0.0009) -[2023-11-28 04:23:26,413][87426] Updated weights for policy 1, policy_version 159360 (0.0011) -[2023-11-28 04:23:27,681][87424] Updated weights for policy 0, policy_version 159657 (0.0012) -[2023-11-28 04:23:28,071][87424] Updated weights for policy 0, policy_version 159667 (0.0010) -[2023-11-28 04:23:28,104][87426] Updated weights for policy 1, policy_version 159370 (0.0012) -[2023-11-28 04:23:28,440][87424] Updated weights for policy 0, policy_version 159677 (0.0011) -[2023-11-28 04:23:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 81666048. Throughput: 0: 2673.2, 1: 2746.9. Samples: 81687124. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:23:28,445][86177] Avg episode reward: [(0, '-527.150'), (1, '-507.590')] -[2023-11-28 04:23:28,485][87426] Updated weights for policy 1, policy_version 159380 (0.0011) -[2023-11-28 04:23:28,876][87426] Updated weights for policy 1, policy_version 159390 (0.0011) -[2023-11-28 04:23:30,698][87424] Updated weights for policy 0, policy_version 159687 (0.0010) -[2023-11-28 04:23:30,839][87426] Updated weights for policy 1, policy_version 159400 (0.0011) -[2023-11-28 04:23:31,081][87424] Updated weights for policy 0, policy_version 159697 (0.0009) -[2023-11-28 04:23:31,216][87426] Updated weights for policy 1, policy_version 159410 (0.0011) -[2023-11-28 04:23:31,462][87424] Updated weights for policy 0, policy_version 159707 (0.0011) -[2023-11-28 04:23:31,598][87426] Updated weights for policy 1, policy_version 159420 (0.0010) -[2023-11-28 04:23:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 81698816. Throughput: 0: 2697.8, 1: 2758.9. Samples: 81713008. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:23:33,446][86177] Avg episode reward: [(0, '-529.400'), (1, '-501.730')] -[2023-11-28 04:23:33,493][87424] Updated weights for policy 0, policy_version 159717 (0.0011) -[2023-11-28 04:23:33,504][87426] Updated weights for policy 1, policy_version 159430 (0.0011) -[2023-11-28 04:23:33,879][87424] Updated weights for policy 0, policy_version 159727 (0.0010) -[2023-11-28 04:23:33,895][87426] Updated weights for policy 1, policy_version 159440 (0.0010) -[2023-11-28 04:23:34,272][87424] Updated weights for policy 0, policy_version 159737 (0.0011) -[2023-11-28 04:23:34,280][87426] Updated weights for policy 1, policy_version 159450 (0.0007) -[2023-11-28 04:23:36,562][87424] Updated weights for policy 0, policy_version 159747 (0.0011) -[2023-11-28 04:23:36,746][87426] Updated weights for policy 1, policy_version 159460 (0.0009) -[2023-11-28 04:23:36,938][87424] Updated weights for policy 0, policy_version 159757 (0.0010) -[2023-11-28 04:23:37,125][87426] Updated weights for policy 1, policy_version 159470 (0.0011) -[2023-11-28 04:23:37,320][87424] Updated weights for policy 0, policy_version 159767 (0.0011) -[2023-11-28 04:23:37,504][87426] Updated weights for policy 1, policy_version 159480 (0.0011) -[2023-11-28 04:23:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 81731584. Throughput: 0: 2717.6, 1: 2780.5. Samples: 81745684. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 04:23:38,445][86177] Avg episode reward: [(0, '-523.660'), (1, '-503.910')] -[2023-11-28 04:23:39,101][87424] Updated weights for policy 0, policy_version 159777 (0.0011) -[2023-11-28 04:23:39,398][87426] Updated weights for policy 1, policy_version 159490 (0.0011) -[2023-11-28 04:23:39,481][87424] Updated weights for policy 0, policy_version 159787 (0.0011) -[2023-11-28 04:23:39,779][87426] Updated weights for policy 1, policy_version 159500 (0.0011) -[2023-11-28 04:23:39,868][87424] Updated weights for policy 0, policy_version 159797 (0.0011) -[2023-11-28 04:23:40,153][87426] Updated weights for policy 1, policy_version 159510 (0.0011) -[2023-11-28 04:23:40,247][87424] Updated weights for policy 0, policy_version 159807 (0.0012) -[2023-11-28 04:23:40,536][87426] Updated weights for policy 1, policy_version 159520 (0.0014) -[2023-11-28 04:23:42,525][87424] Updated weights for policy 0, policy_version 159817 (0.0012) -[2023-11-28 04:23:42,901][87424] Updated weights for policy 0, policy_version 159827 (0.0012) -[2023-11-28 04:23:42,903][87426] Updated weights for policy 1, policy_version 159530 (0.0008) -[2023-11-28 04:23:43,289][87424] Updated weights for policy 0, policy_version 159837 (0.0008) -[2023-11-28 04:23:43,290][87426] Updated weights for policy 1, policy_version 159540 (0.0011) -[2023-11-28 04:23:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 81756160. Throughput: 0: 2742.6, 1: 2770.7. Samples: 81771004. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:23:43,445][86177] Avg episode reward: [(0, '-549.470'), (1, '-519.050')] -[2023-11-28 04:23:43,661][87426] Updated weights for policy 1, policy_version 159550 (0.0011) -[2023-11-28 04:23:45,434][87426] Updated weights for policy 1, policy_version 159560 (0.0012) -[2023-11-28 04:23:45,623][87424] Updated weights for policy 0, policy_version 159847 (0.0009) -[2023-11-28 04:23:45,808][87426] Updated weights for policy 1, policy_version 159570 (0.0011) -[2023-11-28 04:23:46,005][87424] Updated weights for policy 0, policy_version 159857 (0.0008) -[2023-11-28 04:23:46,193][87426] Updated weights for policy 1, policy_version 159580 (0.0008) -[2023-11-28 04:23:46,383][87424] Updated weights for policy 0, policy_version 159867 (0.0007) -[2023-11-28 04:23:48,292][87426] Updated weights for policy 1, policy_version 159590 (0.0010) -[2023-11-28 04:23:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 81780736. Throughput: 0: 2752.1, 1: 2788.1. Samples: 81795660. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:23:48,445][86177] Avg episode reward: [(0, '-548.510'), (1, '-529.000')] -[2023-11-28 04:23:48,486][87424] Updated weights for policy 0, policy_version 159877 (0.0010) -[2023-11-28 04:23:48,672][87426] Updated weights for policy 1, policy_version 159600 (0.0012) -[2023-11-28 04:23:48,865][87424] Updated weights for policy 0, policy_version 159887 (0.0011) -[2023-11-28 04:23:49,052][87426] Updated weights for policy 1, policy_version 159610 (0.0012) -[2023-11-28 04:23:49,252][87424] Updated weights for policy 0, policy_version 159897 (0.0009) -[2023-11-28 04:23:51,351][87426] Updated weights for policy 1, policy_version 159620 (0.0011) -[2023-11-28 04:23:51,453][87424] Updated weights for policy 0, policy_version 159907 (0.0009) -[2023-11-28 04:23:51,725][87426] Updated weights for policy 1, policy_version 159630 (0.0011) -[2023-11-28 04:23:51,832][87424] Updated weights for policy 0, policy_version 159917 (0.0011) -[2023-11-28 04:23:52,103][87426] Updated weights for policy 1, policy_version 159640 (0.0009) -[2023-11-28 04:23:52,209][87424] Updated weights for policy 0, policy_version 159927 (0.0010) -[2023-11-28 04:23:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 81813504. Throughput: 0: 2755.4, 1: 2810.3. Samples: 81828776. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:23:53,445][86177] Avg episode reward: [(0, '-552.450'), (1, '-542.850')] -[2023-11-28 04:23:54,174][87424] Updated weights for policy 0, policy_version 159937 (0.0009) -[2023-11-28 04:23:54,557][87424] Updated weights for policy 0, policy_version 159947 (0.0008) -[2023-11-28 04:23:54,752][87426] Updated weights for policy 1, policy_version 159650 (0.0010) -[2023-11-28 04:23:54,937][87424] Updated weights for policy 0, policy_version 159957 (0.0012) -[2023-11-28 04:23:55,132][87426] Updated weights for policy 1, policy_version 159660 (0.0007) -[2023-11-28 04:23:55,318][87424] Updated weights for policy 0, policy_version 159967 (0.0012) -[2023-11-28 04:23:55,517][87426] Updated weights for policy 1, policy_version 159670 (0.0008) -[2023-11-28 04:23:55,897][87426] Updated weights for policy 1, policy_version 159680 (0.0007) -[2023-11-28 04:23:57,207][87424] Updated weights for policy 0, policy_version 159977 (0.0010) -[2023-11-28 04:23:57,592][87424] Updated weights for policy 0, policy_version 159987 (0.0007) -[2023-11-28 04:23:57,714][87426] Updated weights for policy 1, policy_version 159690 (0.0008) -[2023-11-28 04:23:57,977][87424] Updated weights for policy 0, policy_version 159997 (0.0012) -[2023-11-28 04:23:58,092][87426] Updated weights for policy 1, policy_version 159700 (0.0010) -[2023-11-28 04:23:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 81838080. Throughput: 0: 2768.2, 1: 2814.3. Samples: 81853436. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:23:58,445][86177] Avg episode reward: [(0, '-564.810'), (1, '-542.900')] -[2023-11-28 04:23:58,474][87426] Updated weights for policy 1, policy_version 159710 (0.0008) -[2023-11-28 04:23:59,757][87424] Updated weights for policy 0, policy_version 160007 (0.0012) -[2023-11-28 04:24:00,137][87424] Updated weights for policy 0, policy_version 160017 (0.0012) -[2023-11-28 04:24:00,527][87424] Updated weights for policy 0, policy_version 160027 (0.0012) -[2023-11-28 04:24:00,748][87426] Updated weights for policy 1, policy_version 159720 (0.0010) -[2023-11-28 04:24:01,121][87426] Updated weights for policy 1, policy_version 159730 (0.0011) -[2023-11-28 04:24:01,507][87426] Updated weights for policy 1, policy_version 159740 (0.0011) -[2023-11-28 04:24:02,616][87424] Updated weights for policy 0, policy_version 160037 (0.0011) -[2023-11-28 04:24:02,991][87424] Updated weights for policy 0, policy_version 160047 (0.0010) -[2023-11-28 04:24:03,282][87426] Updated weights for policy 1, policy_version 159750 (0.0011) -[2023-11-28 04:24:03,373][87424] Updated weights for policy 0, policy_version 160057 (0.0011) -[2023-11-28 04:24:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 81862656. Throughput: 0: 2791.1, 1: 2792.6. Samples: 81878880. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:03,445][86177] Avg episode reward: [(0, '-538.460'), (1, '-528.640')] -[2023-11-28 04:24:03,651][87426] Updated weights for policy 1, policy_version 159760 (0.0010) -[2023-11-28 04:24:04,038][87426] Updated weights for policy 1, policy_version 159770 (0.0007) -[2023-11-28 04:24:05,540][87424] Updated weights for policy 0, policy_version 160067 (0.0010) -[2023-11-28 04:24:05,921][87424] Updated weights for policy 0, policy_version 160077 (0.0008) -[2023-11-28 04:24:06,304][87424] Updated weights for policy 0, policy_version 160087 (0.0007) -[2023-11-28 04:24:06,453][87426] Updated weights for policy 1, policy_version 159780 (0.0008) -[2023-11-28 04:24:06,837][87426] Updated weights for policy 1, policy_version 159790 (0.0009) -[2023-11-28 04:24:07,206][87426] Updated weights for policy 1, policy_version 159800 (0.0008) -[2023-11-28 04:24:08,336][87424] Updated weights for policy 0, policy_version 160097 (0.0008) -[2023-11-28 04:24:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 81895424. Throughput: 0: 2803.6, 1: 2797.8. Samples: 81912924. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:08,445][86177] Avg episode reward: [(0, '-551.490'), (1, '-503.150')] -[2023-11-28 04:24:08,715][87424] Updated weights for policy 0, policy_version 160107 (0.0011) -[2023-11-28 04:24:09,101][87424] Updated weights for policy 0, policy_version 160117 (0.0009) -[2023-11-28 04:24:09,424][87426] Updated weights for policy 1, policy_version 159810 (0.0010) -[2023-11-28 04:24:09,494][87424] Updated weights for policy 0, policy_version 160127 (0.0011) -[2023-11-28 04:24:09,802][87426] Updated weights for policy 1, policy_version 159820 (0.0012) -[2023-11-28 04:24:10,175][87426] Updated weights for policy 1, policy_version 159830 (0.0009) -[2023-11-28 04:24:10,557][87426] Updated weights for policy 1, policy_version 159840 (0.0010) -[2023-11-28 04:24:11,294][87424] Updated weights for policy 0, policy_version 160137 (0.0012) -[2023-11-28 04:24:11,669][87424] Updated weights for policy 0, policy_version 160147 (0.0012) -[2023-11-28 04:24:12,049][87424] Updated weights for policy 0, policy_version 160157 (0.0012) -[2023-11-28 04:24:12,565][87426] Updated weights for policy 1, policy_version 159850 (0.0010) -[2023-11-28 04:24:12,943][87426] Updated weights for policy 1, policy_version 159860 (0.0009) -[2023-11-28 04:24:13,328][87426] Updated weights for policy 1, policy_version 159870 (0.0008) -[2023-11-28 04:24:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5470.6). Total num frames: 81928192. Throughput: 0: 2805.4, 1: 2766.4. Samples: 81937856. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:13,445][86177] Avg episode reward: [(0, '-543.230'), (1, '-495.520')] -[2023-11-28 04:24:14,511][87424] Updated weights for policy 0, policy_version 160167 (0.0009) -[2023-11-28 04:24:14,886][87424] Updated weights for policy 0, policy_version 160177 (0.0008) -[2023-11-28 04:24:15,300][87424] Updated weights for policy 0, policy_version 160187 (0.0008) -[2023-11-28 04:24:15,977][87426] Updated weights for policy 1, policy_version 159880 (0.0009) -[2023-11-28 04:24:16,374][87426] Updated weights for policy 1, policy_version 159890 (0.0009) -[2023-11-28 04:24:16,747][87426] Updated weights for policy 1, policy_version 159900 (0.0012) -[2023-11-28 04:24:17,212][87424] Updated weights for policy 0, policy_version 160197 (0.0011) -[2023-11-28 04:24:17,598][87424] Updated weights for policy 0, policy_version 160207 (0.0012) -[2023-11-28 04:24:17,974][87424] Updated weights for policy 0, policy_version 160217 (0.0012) -[2023-11-28 04:24:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 81952768. Throughput: 0: 2786.1, 1: 2734.7. Samples: 81961440. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:18,445][86177] Avg episode reward: [(0, '-538.430'), (1, '-502.990')] -[2023-11-28 04:24:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000160224_41017344.pth... -[2023-11-28 04:24:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000157632_40353792.pth -[2023-11-28 04:24:18,640][87426] Updated weights for policy 1, policy_version 159910 (0.0012) -[2023-11-28 04:24:19,019][87426] Updated weights for policy 1, policy_version 159920 (0.0012) -[2023-11-28 04:24:19,394][87426] Updated weights for policy 1, policy_version 159930 (0.0011) -[2023-11-28 04:24:19,620][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000159936_40943616.pth... -[2023-11-28 04:24:19,650][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000157376_40288256.pth -[2023-11-28 04:24:20,375][87424] Updated weights for policy 0, policy_version 160227 (0.0012) -[2023-11-28 04:24:20,756][87424] Updated weights for policy 0, policy_version 160237 (0.0011) -[2023-11-28 04:24:21,135][87424] Updated weights for policy 0, policy_version 160247 (0.0009) -[2023-11-28 04:24:21,908][87426] Updated weights for policy 1, policy_version 159940 (0.0009) -[2023-11-28 04:24:22,285][87426] Updated weights for policy 1, policy_version 159950 (0.0011) -[2023-11-28 04:24:22,668][87426] Updated weights for policy 1, policy_version 159960 (0.0011) -[2023-11-28 04:24:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 81977344. Throughput: 0: 2777.2, 1: 2707.7. Samples: 81992508. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:23,445][86177] Avg episode reward: [(0, '-531.820'), (1, '-503.380')] -[2023-11-28 04:24:23,508][87424] Updated weights for policy 0, policy_version 160257 (0.0011) -[2023-11-28 04:24:23,890][87424] Updated weights for policy 0, policy_version 160267 (0.0012) -[2023-11-28 04:24:24,271][87424] Updated weights for policy 0, policy_version 160277 (0.0012) -[2023-11-28 04:24:24,652][87424] Updated weights for policy 0, policy_version 160287 (0.0012) -[2023-11-28 04:24:24,778][87426] Updated weights for policy 1, policy_version 159970 (0.0010) -[2023-11-28 04:24:25,157][87426] Updated weights for policy 1, policy_version 159980 (0.0012) -[2023-11-28 04:24:25,538][87426] Updated weights for policy 1, policy_version 159990 (0.0012) -[2023-11-28 04:24:25,916][87426] Updated weights for policy 1, policy_version 160000 (0.0012) -[2023-11-28 04:24:26,576][87424] Updated weights for policy 0, policy_version 160297 (0.0012) -[2023-11-28 04:24:26,962][87424] Updated weights for policy 0, policy_version 160307 (0.0012) -[2023-11-28 04:24:27,337][87424] Updated weights for policy 0, policy_version 160317 (0.0012) -[2023-11-28 04:24:27,886][87426] Updated weights for policy 1, policy_version 160010 (0.0012) -[2023-11-28 04:24:28,267][87426] Updated weights for policy 1, policy_version 160020 (0.0012) -[2023-11-28 04:24:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 82001920. Throughput: 0: 2778.8, 1: 2709.7. Samples: 82017988. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:28,445][86177] Avg episode reward: [(0, '-519.350'), (1, '-502.800')] -[2023-11-28 04:24:28,640][87426] Updated weights for policy 1, policy_version 160030 (0.0012) -[2023-11-28 04:24:29,145][87424] Updated weights for policy 0, policy_version 160327 (0.0009) -[2023-11-28 04:24:29,519][87424] Updated weights for policy 0, policy_version 160337 (0.0007) -[2023-11-28 04:24:29,896][87424] Updated weights for policy 0, policy_version 160347 (0.0011) -[2023-11-28 04:24:31,013][87426] Updated weights for policy 1, policy_version 160040 (0.0011) -[2023-11-28 04:24:31,394][87426] Updated weights for policy 1, policy_version 160050 (0.0011) -[2023-11-28 04:24:31,770][87426] Updated weights for policy 1, policy_version 160060 (0.0010) -[2023-11-28 04:24:32,164][87424] Updated weights for policy 0, policy_version 160357 (0.0012) -[2023-11-28 04:24:32,550][87424] Updated weights for policy 0, policy_version 160367 (0.0011) -[2023-11-28 04:24:32,915][87424] Updated weights for policy 0, policy_version 160377 (0.0008) -[2023-11-28 04:24:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 82034688. Throughput: 0: 2812.6, 1: 2693.0. Samples: 82043412. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:33,446][86177] Avg episode reward: [(0, '-547.790'), (1, '-508.600')] -[2023-11-28 04:24:34,136][87426] Updated weights for policy 1, policy_version 160070 (0.0009) -[2023-11-28 04:24:34,508][87426] Updated weights for policy 1, policy_version 160080 (0.0007) -[2023-11-28 04:24:34,888][87426] Updated weights for policy 1, policy_version 160090 (0.0011) -[2023-11-28 04:24:35,167][87424] Updated weights for policy 0, policy_version 160387 (0.0010) -[2023-11-28 04:24:35,549][87424] Updated weights for policy 0, policy_version 160397 (0.0007) -[2023-11-28 04:24:35,945][87424] Updated weights for policy 0, policy_version 160407 (0.0007) -[2023-11-28 04:24:37,119][87426] Updated weights for policy 1, policy_version 160100 (0.0012) -[2023-11-28 04:24:37,496][87426] Updated weights for policy 1, policy_version 160110 (0.0011) -[2023-11-28 04:24:37,877][87426] Updated weights for policy 1, policy_version 160120 (0.0008) -[2023-11-28 04:24:37,945][87424] Updated weights for policy 0, policy_version 160417 (0.0007) -[2023-11-28 04:24:38,324][87424] Updated weights for policy 0, policy_version 160427 (0.0011) -[2023-11-28 04:24:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 82059264. Throughput: 0: 2803.8, 1: 2702.0. Samples: 82076536. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:38,445][86177] Avg episode reward: [(0, '-540.830'), (1, '-543.670')] -[2023-11-28 04:24:38,710][87424] Updated weights for policy 0, policy_version 160437 (0.0009) -[2023-11-28 04:24:39,097][87424] Updated weights for policy 0, policy_version 160447 (0.0008) -[2023-11-28 04:24:40,136][87426] Updated weights for policy 1, policy_version 160130 (0.0010) -[2023-11-28 04:24:40,514][87426] Updated weights for policy 1, policy_version 160140 (0.0012) -[2023-11-28 04:24:40,887][87424] Updated weights for policy 0, policy_version 160457 (0.0011) -[2023-11-28 04:24:40,890][87426] Updated weights for policy 1, policy_version 160150 (0.0011) -[2023-11-28 04:24:41,269][87426] Updated weights for policy 1, policy_version 160160 (0.0011) -[2023-11-28 04:24:41,277][87424] Updated weights for policy 0, policy_version 160467 (0.0009) -[2023-11-28 04:24:41,658][87424] Updated weights for policy 0, policy_version 160477 (0.0009) -[2023-11-28 04:24:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 82083840. Throughput: 0: 2806.4, 1: 2692.5. Samples: 82100884. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:43,445][86177] Avg episode reward: [(0, '-537.220'), (1, '-546.560')] -[2023-11-28 04:24:43,508][87426] Updated weights for policy 1, policy_version 160170 (0.0011) -[2023-11-28 04:24:43,889][87426] Updated weights for policy 1, policy_version 160180 (0.0010) -[2023-11-28 04:24:44,018][87424] Updated weights for policy 0, policy_version 160487 (0.0012) -[2023-11-28 04:24:44,274][87426] Updated weights for policy 1, policy_version 160190 (0.0007) -[2023-11-28 04:24:44,401][87424] Updated weights for policy 0, policy_version 160497 (0.0011) -[2023-11-28 04:24:44,781][87424] Updated weights for policy 0, policy_version 160507 (0.0012) -[2023-11-28 04:24:46,328][87426] Updated weights for policy 1, policy_version 160200 (0.0011) -[2023-11-28 04:24:46,524][87424] Updated weights for policy 0, policy_version 160517 (0.0010) -[2023-11-28 04:24:46,713][87426] Updated weights for policy 1, policy_version 160210 (0.0011) -[2023-11-28 04:24:46,916][87424] Updated weights for policy 0, policy_version 160527 (0.0009) -[2023-11-28 04:24:47,093][87426] Updated weights for policy 1, policy_version 160220 (0.0011) -[2023-11-28 04:24:47,288][87424] Updated weights for policy 0, policy_version 160537 (0.0007) -[2023-11-28 04:24:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 82116608. Throughput: 0: 2779.6, 1: 2691.8. Samples: 82125096. Policy #0 lag: (min: 22.0, avg: 42.2, max: 74.0) -[2023-11-28 04:24:48,445][86177] Avg episode reward: [(0, '-541.120'), (1, '-546.390')] -[2023-11-28 04:24:49,342][87426] Updated weights for policy 1, policy_version 160230 (0.0010) -[2023-11-28 04:24:49,713][87426] Updated weights for policy 1, policy_version 160240 (0.0010) -[2023-11-28 04:24:49,833][87424] Updated weights for policy 0, policy_version 160547 (0.0008) -[2023-11-28 04:24:50,088][87426] Updated weights for policy 1, policy_version 160250 (0.0008) -[2023-11-28 04:24:50,213][87424] Updated weights for policy 0, policy_version 160557 (0.0008) -[2023-11-28 04:24:50,594][87424] Updated weights for policy 0, policy_version 160567 (0.0009) -[2023-11-28 04:24:52,260][87426] Updated weights for policy 1, policy_version 160260 (0.0009) -[2023-11-28 04:24:52,636][87426] Updated weights for policy 1, policy_version 160270 (0.0012) -[2023-11-28 04:24:52,781][87424] Updated weights for policy 0, policy_version 160577 (0.0011) -[2023-11-28 04:24:53,010][87426] Updated weights for policy 1, policy_version 160280 (0.0011) -[2023-11-28 04:24:53,156][87424] Updated weights for policy 0, policy_version 160587 (0.0011) -[2023-11-28 04:24:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 82141184. Throughput: 0: 2747.6, 1: 2671.2. Samples: 82156768. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:24:53,445][86177] Avg episode reward: [(0, '-514.050'), (1, '-502.240')] -[2023-11-28 04:24:53,542][87424] Updated weights for policy 0, policy_version 160597 (0.0011) -[2023-11-28 04:24:53,925][87424] Updated weights for policy 0, policy_version 160607 (0.0011) -[2023-11-28 04:24:55,458][87426] Updated weights for policy 1, policy_version 160290 (0.0011) -[2023-11-28 04:24:55,833][87426] Updated weights for policy 1, policy_version 160300 (0.0011) -[2023-11-28 04:24:56,208][87426] Updated weights for policy 1, policy_version 160310 (0.0011) -[2023-11-28 04:24:56,388][87424] Updated weights for policy 0, policy_version 160617 (0.0008) -[2023-11-28 04:24:56,588][87426] Updated weights for policy 1, policy_version 160320 (0.0010) -[2023-11-28 04:24:56,777][87424] Updated weights for policy 0, policy_version 160627 (0.0012) -[2023-11-28 04:24:57,170][87424] Updated weights for policy 0, policy_version 160637 (0.0012) -[2023-11-28 04:24:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 82165760. Throughput: 0: 2746.0, 1: 2667.3. Samples: 82181452. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:24:58,445][86177] Avg episode reward: [(0, '-510.380'), (1, '-493.980')] -[2023-11-28 04:24:58,613][87426] Updated weights for policy 1, policy_version 160330 (0.0008) -[2023-11-28 04:24:58,924][87424] Updated weights for policy 0, policy_version 160647 (0.0012) -[2023-11-28 04:24:58,998][87426] Updated weights for policy 1, policy_version 160340 (0.0009) -[2023-11-28 04:24:59,298][87424] Updated weights for policy 0, policy_version 160657 (0.0009) -[2023-11-28 04:24:59,378][87426] Updated weights for policy 1, policy_version 160350 (0.0012) -[2023-11-28 04:24:59,691][87424] Updated weights for policy 0, policy_version 160667 (0.0012) -[2023-11-28 04:25:01,662][87426] Updated weights for policy 1, policy_version 160360 (0.0012) -[2023-11-28 04:25:01,717][87424] Updated weights for policy 0, policy_version 160677 (0.0012) -[2023-11-28 04:25:02,040][87426] Updated weights for policy 1, policy_version 160370 (0.0011) -[2023-11-28 04:25:02,099][87424] Updated weights for policy 0, policy_version 160687 (0.0012) -[2023-11-28 04:25:02,418][87426] Updated weights for policy 1, policy_version 160380 (0.0011) -[2023-11-28 04:25:02,484][87424] Updated weights for policy 0, policy_version 160697 (0.0011) -[2023-11-28 04:25:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 82198528. Throughput: 0: 2759.6, 1: 2678.1. Samples: 82206140. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:03,446][86177] Avg episode reward: [(0, '-511.250'), (1, '-489.560')] -[2023-11-28 04:25:04,619][87424] Updated weights for policy 0, policy_version 160707 (0.0010) -[2023-11-28 04:25:04,793][87426] Updated weights for policy 1, policy_version 160390 (0.0010) -[2023-11-28 04:25:05,002][87424] Updated weights for policy 0, policy_version 160717 (0.0011) -[2023-11-28 04:25:05,170][87426] Updated weights for policy 1, policy_version 160400 (0.0009) -[2023-11-28 04:25:05,386][87424] Updated weights for policy 0, policy_version 160727 (0.0007) -[2023-11-28 04:25:05,551][87426] Updated weights for policy 1, policy_version 160410 (0.0008) -[2023-11-28 04:25:07,576][87424] Updated weights for policy 0, policy_version 160737 (0.0008) -[2023-11-28 04:25:07,606][87426] Updated weights for policy 1, policy_version 160420 (0.0008) -[2023-11-28 04:25:07,962][87424] Updated weights for policy 0, policy_version 160747 (0.0012) -[2023-11-28 04:25:07,988][87426] Updated weights for policy 1, policy_version 160430 (0.0007) -[2023-11-28 04:25:08,343][87424] Updated weights for policy 0, policy_version 160757 (0.0012) -[2023-11-28 04:25:08,350][87426] Updated weights for policy 1, policy_version 160440 (0.0008) -[2023-11-28 04:25:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 82214912. Throughput: 0: 2779.8, 1: 2713.0. Samples: 82239684. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:08,445][86177] Avg episode reward: [(0, '-507.550'), (1, '-517.630')] -[2023-11-28 04:25:08,718][87424] Updated weights for policy 0, policy_version 160767 (0.0010) -[2023-11-28 04:25:10,937][87426] Updated weights for policy 1, policy_version 160450 (0.0011) -[2023-11-28 04:25:11,140][87424] Updated weights for policy 0, policy_version 160777 (0.0010) -[2023-11-28 04:25:11,306][87426] Updated weights for policy 1, policy_version 160460 (0.0011) -[2023-11-28 04:25:11,521][87424] Updated weights for policy 0, policy_version 160787 (0.0011) -[2023-11-28 04:25:11,694][87426] Updated weights for policy 1, policy_version 160470 (0.0010) -[2023-11-28 04:25:11,907][87424] Updated weights for policy 0, policy_version 160797 (0.0012) -[2023-11-28 04:25:12,064][87426] Updated weights for policy 1, policy_version 160480 (0.0011) -[2023-11-28 04:25:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 82247680. Throughput: 0: 2767.8, 1: 2680.4. Samples: 82263160. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:13,445][86177] Avg episode reward: [(0, '-563.600'), (1, '-524.920')] -[2023-11-28 04:25:14,202][87426] Updated weights for policy 1, policy_version 160490 (0.0011) -[2023-11-28 04:25:14,298][87424] Updated weights for policy 0, policy_version 160807 (0.0009) -[2023-11-28 04:25:14,581][87426] Updated weights for policy 1, policy_version 160500 (0.0012) -[2023-11-28 04:25:14,681][87424] Updated weights for policy 0, policy_version 160817 (0.0010) -[2023-11-28 04:25:14,962][87426] Updated weights for policy 1, policy_version 160510 (0.0012) -[2023-11-28 04:25:15,057][87424] Updated weights for policy 0, policy_version 160827 (0.0009) -[2023-11-28 04:25:16,906][87424] Updated weights for policy 0, policy_version 160837 (0.0009) -[2023-11-28 04:25:17,235][87426] Updated weights for policy 1, policy_version 160520 (0.0011) -[2023-11-28 04:25:17,294][87424] Updated weights for policy 0, policy_version 160847 (0.0010) -[2023-11-28 04:25:17,617][87426] Updated weights for policy 1, policy_version 160530 (0.0008) -[2023-11-28 04:25:17,678][87424] Updated weights for policy 0, policy_version 160857 (0.0010) -[2023-11-28 04:25:17,984][87426] Updated weights for policy 1, policy_version 160540 (0.0010) -[2023-11-28 04:25:18,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 82280448. Throughput: 0: 2744.6, 1: 2677.5. Samples: 82287408. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:18,445][86177] Avg episode reward: [(0, '-565.640'), (1, '-525.850')] -[2023-11-28 04:25:20,174][87424] Updated weights for policy 0, policy_version 160867 (0.0009) -[2023-11-28 04:25:20,473][87426] Updated weights for policy 1, policy_version 160550 (0.0010) -[2023-11-28 04:25:20,553][87424] Updated weights for policy 0, policy_version 160877 (0.0011) -[2023-11-28 04:25:20,853][87426] Updated weights for policy 1, policy_version 160560 (0.0011) -[2023-11-28 04:25:20,936][87424] Updated weights for policy 0, policy_version 160887 (0.0008) -[2023-11-28 04:25:21,233][87426] Updated weights for policy 1, policy_version 160570 (0.0011) -[2023-11-28 04:25:22,946][87424] Updated weights for policy 0, policy_version 160897 (0.0010) -[2023-11-28 04:25:23,332][87424] Updated weights for policy 0, policy_version 160907 (0.0011) -[2023-11-28 04:25:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 82296832. Throughput: 0: 2727.2, 1: 2656.5. Samples: 82318804. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:23,445][86177] Avg episode reward: [(0, '-560.690'), (1, '-535.770')] -[2023-11-28 04:25:23,464][87426] Updated weights for policy 1, policy_version 160580 (0.0011) -[2023-11-28 04:25:23,708][87424] Updated weights for policy 0, policy_version 160917 (0.0010) -[2023-11-28 04:25:23,848][87426] Updated weights for policy 1, policy_version 160590 (0.0012) -[2023-11-28 04:25:24,088][87424] Updated weights for policy 0, policy_version 160927 (0.0008) -[2023-11-28 04:25:24,218][87426] Updated weights for policy 1, policy_version 160600 (0.0011) -[2023-11-28 04:25:26,161][87424] Updated weights for policy 0, policy_version 160937 (0.0011) -[2023-11-28 04:25:26,493][87426] Updated weights for policy 1, policy_version 160610 (0.0010) -[2023-11-28 04:25:26,539][87424] Updated weights for policy 0, policy_version 160947 (0.0011) -[2023-11-28 04:25:26,871][87426] Updated weights for policy 1, policy_version 160620 (0.0009) -[2023-11-28 04:25:26,918][87424] Updated weights for policy 0, policy_version 160957 (0.0010) -[2023-11-28 04:25:27,252][87426] Updated weights for policy 1, policy_version 160630 (0.0012) -[2023-11-28 04:25:27,629][87426] Updated weights for policy 1, policy_version 160640 (0.0011) -[2023-11-28 04:25:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 82329600. Throughput: 0: 2719.5, 1: 2661.4. Samples: 82343028. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:28,446][86177] Avg episode reward: [(0, '-523.050'), (1, '-509.040')] -[2023-11-28 04:25:29,046][87424] Updated weights for policy 0, policy_version 160967 (0.0008) -[2023-11-28 04:25:29,431][87424] Updated weights for policy 0, policy_version 160977 (0.0009) -[2023-11-28 04:25:29,435][87426] Updated weights for policy 1, policy_version 160650 (0.0011) -[2023-11-28 04:25:29,810][87426] Updated weights for policy 1, policy_version 160660 (0.0008) -[2023-11-28 04:25:29,825][87424] Updated weights for policy 0, policy_version 160987 (0.0009) -[2023-11-28 04:25:30,191][87426] Updated weights for policy 1, policy_version 160670 (0.0011) -[2023-11-28 04:25:32,015][87426] Updated weights for policy 1, policy_version 160680 (0.0010) -[2023-11-28 04:25:32,261][87424] Updated weights for policy 0, policy_version 160997 (0.0012) -[2023-11-28 04:25:32,390][87426] Updated weights for policy 1, policy_version 160690 (0.0010) -[2023-11-28 04:25:32,641][87424] Updated weights for policy 0, policy_version 161007 (0.0011) -[2023-11-28 04:25:32,779][87426] Updated weights for policy 1, policy_version 160700 (0.0011) -[2023-11-28 04:25:33,027][87424] Updated weights for policy 0, policy_version 161017 (0.0009) -[2023-11-28 04:25:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5498.4). Total num frames: 82362368. Throughput: 0: 2718.2, 1: 2683.4. Samples: 82368168. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:33,445][86177] Avg episode reward: [(0, '-505.850'), (1, '-509.670')] -[2023-11-28 04:25:34,789][87426] Updated weights for policy 1, policy_version 160710 (0.0010) -[2023-11-28 04:25:35,158][87426] Updated weights for policy 1, policy_version 160720 (0.0011) -[2023-11-28 04:25:35,337][87424] Updated weights for policy 0, policy_version 161027 (0.0009) -[2023-11-28 04:25:35,542][87426] Updated weights for policy 1, policy_version 160730 (0.0007) -[2023-11-28 04:25:35,720][87424] Updated weights for policy 0, policy_version 161037 (0.0012) -[2023-11-28 04:25:36,115][87424] Updated weights for policy 0, policy_version 161047 (0.0009) -[2023-11-28 04:25:37,922][87426] Updated weights for policy 1, policy_version 160740 (0.0008) -[2023-11-28 04:25:38,304][87426] Updated weights for policy 1, policy_version 160750 (0.0010) -[2023-11-28 04:25:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 82378752. Throughput: 0: 2719.8, 1: 2704.5. Samples: 82400860. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:38,445][86177] Avg episode reward: [(0, '-503.180'), (1, '-509.560')] -[2023-11-28 04:25:38,445][87424] Updated weights for policy 0, policy_version 161057 (0.0008) -[2023-11-28 04:25:38,692][87426] Updated weights for policy 1, policy_version 160760 (0.0010) -[2023-11-28 04:25:38,821][87424] Updated weights for policy 0, policy_version 161067 (0.0011) -[2023-11-28 04:25:39,209][87424] Updated weights for policy 0, policy_version 161077 (0.0012) -[2023-11-28 04:25:39,585][87424] Updated weights for policy 0, policy_version 161087 (0.0012) -[2023-11-28 04:25:40,541][87426] Updated weights for policy 1, policy_version 160770 (0.0011) -[2023-11-28 04:25:40,917][87426] Updated weights for policy 1, policy_version 160780 (0.0012) -[2023-11-28 04:25:41,298][87426] Updated weights for policy 1, policy_version 160790 (0.0012) -[2023-11-28 04:25:41,615][87424] Updated weights for policy 0, policy_version 161097 (0.0009) -[2023-11-28 04:25:41,669][87426] Updated weights for policy 1, policy_version 160800 (0.0009) -[2023-11-28 04:25:41,994][87424] Updated weights for policy 0, policy_version 161107 (0.0011) -[2023-11-28 04:25:42,376][87424] Updated weights for policy 0, policy_version 161117 (0.0011) -[2023-11-28 04:25:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 82411520. Throughput: 0: 2713.3, 1: 2683.4. Samples: 82424304. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:43,445][86177] Avg episode reward: [(0, '-504.460'), (1, '-513.200')] -[2023-11-28 04:25:44,129][87426] Updated weights for policy 1, policy_version 160810 (0.0012) -[2023-11-28 04:25:44,508][87426] Updated weights for policy 1, policy_version 160820 (0.0011) -[2023-11-28 04:25:44,783][87424] Updated weights for policy 0, policy_version 161127 (0.0012) -[2023-11-28 04:25:44,886][87426] Updated weights for policy 1, policy_version 160830 (0.0010) -[2023-11-28 04:25:45,169][87424] Updated weights for policy 0, policy_version 161137 (0.0012) -[2023-11-28 04:25:45,544][87424] Updated weights for policy 0, policy_version 161147 (0.0012) -[2023-11-28 04:25:47,331][87424] Updated weights for policy 0, policy_version 161157 (0.0012) -[2023-11-28 04:25:47,474][87426] Updated weights for policy 1, policy_version 160840 (0.0010) -[2023-11-28 04:25:47,714][87424] Updated weights for policy 0, policy_version 161167 (0.0011) -[2023-11-28 04:25:47,857][87426] Updated weights for policy 1, policy_version 160850 (0.0010) -[2023-11-28 04:25:48,096][87424] Updated weights for policy 0, policy_version 161177 (0.0012) -[2023-11-28 04:25:48,237][87426] Updated weights for policy 1, policy_version 160860 (0.0008) -[2023-11-28 04:25:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 82444288. Throughput: 0: 2724.3, 1: 2677.1. Samples: 82449200. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:48,445][86177] Avg episode reward: [(0, '-497.590'), (1, '-533.700')] -[2023-11-28 04:25:49,872][87424] Updated weights for policy 0, policy_version 161187 (0.0010) -[2023-11-28 04:25:50,255][87424] Updated weights for policy 0, policy_version 161197 (0.0011) -[2023-11-28 04:25:50,404][87426] Updated weights for policy 1, policy_version 160870 (0.0010) -[2023-11-28 04:25:50,631][87424] Updated weights for policy 0, policy_version 161207 (0.0012) -[2023-11-28 04:25:50,782][87426] Updated weights for policy 1, policy_version 160880 (0.0009) -[2023-11-28 04:25:51,164][87426] Updated weights for policy 1, policy_version 160890 (0.0009) -[2023-11-28 04:25:52,814][87424] Updated weights for policy 0, policy_version 161217 (0.0012) -[2023-11-28 04:25:53,206][87424] Updated weights for policy 0, policy_version 161227 (0.0010) -[2023-11-28 04:25:53,289][87426] Updated weights for policy 1, policy_version 160900 (0.0011) -[2023-11-28 04:25:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 82460672. Throughput: 0: 2739.6, 1: 2653.1. Samples: 82482352. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:25:53,445][86177] Avg episode reward: [(0, '-501.720'), (1, '-553.770')] -[2023-11-28 04:25:53,581][87424] Updated weights for policy 0, policy_version 161237 (0.0011) -[2023-11-28 04:25:53,666][87426] Updated weights for policy 1, policy_version 160910 (0.0010) -[2023-11-28 04:25:53,966][87424] Updated weights for policy 0, policy_version 161247 (0.0009) -[2023-11-28 04:25:54,049][87426] Updated weights for policy 1, policy_version 160920 (0.0010) -[2023-11-28 04:25:55,738][87424] Updated weights for policy 0, policy_version 161257 (0.0008) -[2023-11-28 04:25:56,125][87424] Updated weights for policy 0, policy_version 161267 (0.0012) -[2023-11-28 04:25:56,519][87424] Updated weights for policy 0, policy_version 161277 (0.0012) -[2023-11-28 04:25:56,609][87426] Updated weights for policy 1, policy_version 160930 (0.0011) -[2023-11-28 04:25:56,996][87426] Updated weights for policy 1, policy_version 160940 (0.0007) -[2023-11-28 04:25:57,361][87426] Updated weights for policy 1, policy_version 160950 (0.0007) -[2023-11-28 04:25:57,742][87426] Updated weights for policy 1, policy_version 160960 (0.0008) -[2023-11-28 04:25:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 82493440. Throughput: 0: 2745.4, 1: 2650.6. Samples: 82505980. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:25:58,445][86177] Avg episode reward: [(0, '-498.000'), (1, '-570.550')] -[2023-11-28 04:25:58,921][87424] Updated weights for policy 0, policy_version 161287 (0.0012) -[2023-11-28 04:25:59,305][87424] Updated weights for policy 0, policy_version 161297 (0.0011) -[2023-11-28 04:25:59,697][87424] Updated weights for policy 0, policy_version 161307 (0.0012) -[2023-11-28 04:26:00,085][87426] Updated weights for policy 1, policy_version 160970 (0.0009) -[2023-11-28 04:26:00,467][87426] Updated weights for policy 1, policy_version 160980 (0.0009) -[2023-11-28 04:26:00,847][87426] Updated weights for policy 1, policy_version 160990 (0.0008) -[2023-11-28 04:26:01,655][87424] Updated weights for policy 0, policy_version 161317 (0.0012) -[2023-11-28 04:26:02,036][87424] Updated weights for policy 0, policy_version 161327 (0.0012) -[2023-11-28 04:26:02,413][87424] Updated weights for policy 0, policy_version 161337 (0.0012) -[2023-11-28 04:26:02,850][87426] Updated weights for policy 1, policy_version 161000 (0.0011) -[2023-11-28 04:26:03,219][87426] Updated weights for policy 1, policy_version 161010 (0.0012) -[2023-11-28 04:26:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 82518016. Throughput: 0: 2744.0, 1: 2661.4. Samples: 82530652. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:03,445][86177] Avg episode reward: [(0, '-537.700'), (1, '-571.460')] -[2023-11-28 04:26:03,598][87426] Updated weights for policy 1, policy_version 161020 (0.0012) -[2023-11-28 04:26:04,489][87424] Updated weights for policy 0, policy_version 161347 (0.0012) -[2023-11-28 04:26:04,869][87424] Updated weights for policy 0, policy_version 161357 (0.0012) -[2023-11-28 04:26:05,241][87424] Updated weights for policy 0, policy_version 161367 (0.0012) -[2023-11-28 04:26:05,851][87426] Updated weights for policy 1, policy_version 161030 (0.0011) -[2023-11-28 04:26:06,223][87426] Updated weights for policy 1, policy_version 161040 (0.0011) -[2023-11-28 04:26:06,601][87426] Updated weights for policy 1, policy_version 161050 (0.0007) -[2023-11-28 04:26:07,284][87424] Updated weights for policy 0, policy_version 161377 (0.0012) -[2023-11-28 04:26:07,665][87424] Updated weights for policy 0, policy_version 161387 (0.0012) -[2023-11-28 04:26:08,055][87424] Updated weights for policy 0, policy_version 161397 (0.0012) -[2023-11-28 04:26:08,440][87424] Updated weights for policy 0, policy_version 161407 (0.0012) -[2023-11-28 04:26:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 82542592. Throughput: 0: 2792.6, 1: 2676.3. Samples: 82564904. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:08,445][86177] Avg episode reward: [(0, '-533.680'), (1, '-590.780')] -[2023-11-28 04:26:08,623][87426] Updated weights for policy 1, policy_version 161060 (0.0012) -[2023-11-28 04:26:09,002][87426] Updated weights for policy 1, policy_version 161070 (0.0012) -[2023-11-28 04:26:09,382][87426] Updated weights for policy 1, policy_version 161080 (0.0008) -[2023-11-28 04:26:10,377][87424] Updated weights for policy 0, policy_version 161417 (0.0011) -[2023-11-28 04:26:10,754][87424] Updated weights for policy 0, policy_version 161427 (0.0010) -[2023-11-28 04:26:11,141][87424] Updated weights for policy 0, policy_version 161437 (0.0012) -[2023-11-28 04:26:11,472][87426] Updated weights for policy 1, policy_version 161090 (0.0009) -[2023-11-28 04:26:11,862][87426] Updated weights for policy 1, policy_version 161100 (0.0009) -[2023-11-28 04:26:12,237][87426] Updated weights for policy 1, policy_version 161110 (0.0010) -[2023-11-28 04:26:12,617][87426] Updated weights for policy 1, policy_version 161120 (0.0010) -[2023-11-28 04:26:13,301][87424] Updated weights for policy 0, policy_version 161447 (0.0011) -[2023-11-28 04:26:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 82575360. Throughput: 0: 2802.5, 1: 2685.6. Samples: 82589992. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:13,445][86177] Avg episode reward: [(0, '-532.590'), (1, '-600.450')] -[2023-11-28 04:26:13,675][87424] Updated weights for policy 0, policy_version 161457 (0.0012) -[2023-11-28 04:26:14,059][87424] Updated weights for policy 0, policy_version 161467 (0.0012) -[2023-11-28 04:26:14,887][87426] Updated weights for policy 1, policy_version 161130 (0.0009) -[2023-11-28 04:26:15,265][87426] Updated weights for policy 1, policy_version 161140 (0.0007) -[2023-11-28 04:26:15,642][87426] Updated weights for policy 1, policy_version 161150 (0.0011) -[2023-11-28 04:26:16,253][87424] Updated weights for policy 0, policy_version 161477 (0.0012) -[2023-11-28 04:26:16,632][87424] Updated weights for policy 0, policy_version 161487 (0.0011) -[2023-11-28 04:26:17,016][87424] Updated weights for policy 0, policy_version 161497 (0.0009) -[2023-11-28 04:26:18,028][87426] Updated weights for policy 1, policy_version 161160 (0.0010) -[2023-11-28 04:26:18,398][87426] Updated weights for policy 1, policy_version 161170 (0.0008) -[2023-11-28 04:26:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 82599936. Throughput: 0: 2801.8, 1: 2670.7. Samples: 82614436. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:18,446][86177] Avg episode reward: [(0, '-534.240'), (1, '-598.260')] -[2023-11-28 04:26:18,461][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000161504_41345024.pth... -[2023-11-28 04:26:18,493][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000158944_40689664.pth -[2023-11-28 04:26:18,777][87426] Updated weights for policy 1, policy_version 161180 (0.0008) -[2023-11-28 04:26:18,926][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000161184_41263104.pth... -[2023-11-28 04:26:18,971][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000158656_40615936.pth -[2023-11-28 04:26:19,487][87424] Updated weights for policy 0, policy_version 161507 (0.0010) -[2023-11-28 04:26:19,868][87424] Updated weights for policy 0, policy_version 161517 (0.0009) -[2023-11-28 04:26:20,252][87424] Updated weights for policy 0, policy_version 161527 (0.0011) -[2023-11-28 04:26:21,221][87426] Updated weights for policy 1, policy_version 161190 (0.0009) -[2023-11-28 04:26:21,592][87426] Updated weights for policy 1, policy_version 161200 (0.0009) -[2023-11-28 04:26:21,974][87426] Updated weights for policy 1, policy_version 161210 (0.0011) -[2023-11-28 04:26:22,354][87424] Updated weights for policy 0, policy_version 161537 (0.0011) -[2023-11-28 04:26:22,739][87424] Updated weights for policy 0, policy_version 161547 (0.0011) -[2023-11-28 04:26:23,122][87424] Updated weights for policy 0, policy_version 161557 (0.0011) -[2023-11-28 04:26:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 82624512. Throughput: 0: 2804.6, 1: 2635.8. Samples: 82645680. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:23,445][86177] Avg episode reward: [(0, '-494.290'), (1, '-604.210')] -[2023-11-28 04:26:23,507][87424] Updated weights for policy 0, policy_version 161567 (0.0007) -[2023-11-28 04:26:24,230][87426] Updated weights for policy 1, policy_version 161220 (0.0011) -[2023-11-28 04:26:24,610][87426] Updated weights for policy 1, policy_version 161230 (0.0011) -[2023-11-28 04:26:25,000][87426] Updated weights for policy 1, policy_version 161240 (0.0009) -[2023-11-28 04:26:25,649][87424] Updated weights for policy 0, policy_version 161577 (0.0011) -[2023-11-28 04:26:26,035][87424] Updated weights for policy 0, policy_version 161587 (0.0012) -[2023-11-28 04:26:26,427][87424] Updated weights for policy 0, policy_version 161597 (0.0008) -[2023-11-28 04:26:27,468][87426] Updated weights for policy 1, policy_version 161250 (0.0009) -[2023-11-28 04:26:27,840][87426] Updated weights for policy 1, policy_version 161260 (0.0012) -[2023-11-28 04:26:28,214][87426] Updated weights for policy 1, policy_version 161270 (0.0012) -[2023-11-28 04:26:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 82649088. Throughput: 0: 2813.5, 1: 2655.1. Samples: 82670392. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:28,445][86177] Avg episode reward: [(0, '-495.250'), (1, '-634.530')] -[2023-11-28 04:26:28,583][87426] Updated weights for policy 1, policy_version 161280 (0.0011) -[2023-11-28 04:26:28,657][87424] Updated weights for policy 0, policy_version 161607 (0.0009) -[2023-11-28 04:26:29,043][87424] Updated weights for policy 0, policy_version 161617 (0.0008) -[2023-11-28 04:26:29,428][87424] Updated weights for policy 0, policy_version 161627 (0.0008) -[2023-11-28 04:26:30,929][87426] Updated weights for policy 1, policy_version 161290 (0.0010) -[2023-11-28 04:26:31,295][87426] Updated weights for policy 1, policy_version 161300 (0.0012) -[2023-11-28 04:26:31,311][87424] Updated weights for policy 0, policy_version 161637 (0.0010) -[2023-11-28 04:26:31,673][87426] Updated weights for policy 1, policy_version 161310 (0.0012) -[2023-11-28 04:26:31,681][87424] Updated weights for policy 0, policy_version 161647 (0.0012) -[2023-11-28 04:26:32,063][87424] Updated weights for policy 0, policy_version 161657 (0.0011) -[2023-11-28 04:26:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 82681856. Throughput: 0: 2790.8, 1: 2664.7. Samples: 82694696. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:33,445][86177] Avg episode reward: [(0, '-499.400'), (1, '-619.400')] -[2023-11-28 04:26:33,620][87426] Updated weights for policy 1, policy_version 161320 (0.0012) -[2023-11-28 04:26:34,006][87426] Updated weights for policy 1, policy_version 161330 (0.0012) -[2023-11-28 04:26:34,382][87426] Updated weights for policy 1, policy_version 161340 (0.0012) -[2023-11-28 04:26:34,627][87424] Updated weights for policy 0, policy_version 161667 (0.0012) -[2023-11-28 04:26:35,017][87424] Updated weights for policy 0, policy_version 161677 (0.0011) -[2023-11-28 04:26:35,399][87424] Updated weights for policy 0, policy_version 161687 (0.0012) -[2023-11-28 04:26:36,508][87426] Updated weights for policy 1, policy_version 161350 (0.0010) -[2023-11-28 04:26:36,889][87426] Updated weights for policy 1, policy_version 161360 (0.0009) -[2023-11-28 04:26:37,272][87426] Updated weights for policy 1, policy_version 161370 (0.0011) -[2023-11-28 04:26:37,648][87424] Updated weights for policy 0, policy_version 161697 (0.0012) -[2023-11-28 04:26:38,029][87424] Updated weights for policy 0, policy_version 161707 (0.0012) -[2023-11-28 04:26:38,405][87424] Updated weights for policy 0, policy_version 161717 (0.0012) -[2023-11-28 04:26:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 82706432. Throughput: 0: 2750.7, 1: 2690.1. Samples: 82727188. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:38,445][86177] Avg episode reward: [(0, '-498.820'), (1, '-617.400')] -[2023-11-28 04:26:38,790][87424] Updated weights for policy 0, policy_version 161727 (0.0012) -[2023-11-28 04:26:39,642][87426] Updated weights for policy 1, policy_version 161380 (0.0010) -[2023-11-28 04:26:40,021][87426] Updated weights for policy 1, policy_version 161390 (0.0011) -[2023-11-28 04:26:40,401][87426] Updated weights for policy 1, policy_version 161400 (0.0009) -[2023-11-28 04:26:40,650][87424] Updated weights for policy 0, policy_version 161737 (0.0012) -[2023-11-28 04:26:41,023][87424] Updated weights for policy 0, policy_version 161747 (0.0011) -[2023-11-28 04:26:41,415][87424] Updated weights for policy 0, policy_version 161757 (0.0010) -[2023-11-28 04:26:42,919][87426] Updated weights for policy 1, policy_version 161410 (0.0011) -[2023-11-28 04:26:43,310][87426] Updated weights for policy 1, policy_version 161420 (0.0010) -[2023-11-28 04:26:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 82731008. Throughput: 0: 2739.4, 1: 2689.1. Samples: 82750264. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:43,445][86177] Avg episode reward: [(0, '-502.980'), (1, '-602.960')] -[2023-11-28 04:26:43,681][87426] Updated weights for policy 1, policy_version 161430 (0.0009) -[2023-11-28 04:26:43,776][87424] Updated weights for policy 0, policy_version 161767 (0.0011) -[2023-11-28 04:26:44,063][87426] Updated weights for policy 1, policy_version 161440 (0.0007) -[2023-11-28 04:26:44,158][87424] Updated weights for policy 0, policy_version 161777 (0.0008) -[2023-11-28 04:26:44,544][87424] Updated weights for policy 0, policy_version 161787 (0.0007) -[2023-11-28 04:26:46,457][87424] Updated weights for policy 0, policy_version 161797 (0.0009) -[2023-11-28 04:26:46,527][87426] Updated weights for policy 1, policy_version 161450 (0.0011) -[2023-11-28 04:26:46,849][87424] Updated weights for policy 0, policy_version 161807 (0.0011) -[2023-11-28 04:26:46,906][87426] Updated weights for policy 1, policy_version 161460 (0.0011) -[2023-11-28 04:26:47,232][87424] Updated weights for policy 0, policy_version 161817 (0.0011) -[2023-11-28 04:26:47,284][87426] Updated weights for policy 1, policy_version 161470 (0.0011) -[2023-11-28 04:26:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.9). Total num frames: 82763776. Throughput: 0: 2750.6, 1: 2672.4. Samples: 82774684. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:48,445][86177] Avg episode reward: [(0, '-506.680'), (1, '-560.330')] -[2023-11-28 04:26:48,842][87424] Updated weights for policy 0, policy_version 161827 (0.0012) -[2023-11-28 04:26:49,239][87424] Updated weights for policy 0, policy_version 161837 (0.0011) -[2023-11-28 04:26:49,271][87426] Updated weights for policy 1, policy_version 161480 (0.0010) -[2023-11-28 04:26:49,629][87424] Updated weights for policy 0, policy_version 161847 (0.0011) -[2023-11-28 04:26:49,653][87426] Updated weights for policy 1, policy_version 161490 (0.0011) -[2023-11-28 04:26:50,028][87426] Updated weights for policy 1, policy_version 161500 (0.0010) -[2023-11-28 04:26:51,686][87424] Updated weights for policy 0, policy_version 161857 (0.0009) -[2023-11-28 04:26:52,076][87424] Updated weights for policy 0, policy_version 161867 (0.0009) -[2023-11-28 04:26:52,452][87424] Updated weights for policy 0, policy_version 161877 (0.0009) -[2023-11-28 04:26:52,495][87426] Updated weights for policy 1, policy_version 161510 (0.0009) -[2023-11-28 04:26:52,829][87424] Updated weights for policy 0, policy_version 161887 (0.0009) -[2023-11-28 04:26:52,875][87426] Updated weights for policy 1, policy_version 161520 (0.0012) -[2023-11-28 04:26:53,252][87426] Updated weights for policy 1, policy_version 161530 (0.0011) -[2023-11-28 04:26:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 82788352. Throughput: 0: 2720.4, 1: 2655.5. Samples: 82806816. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:53,445][86177] Avg episode reward: [(0, '-507.770'), (1, '-583.770')] -[2023-11-28 04:26:55,092][87424] Updated weights for policy 0, policy_version 161897 (0.0008) -[2023-11-28 04:26:55,210][87426] Updated weights for policy 1, policy_version 161540 (0.0010) -[2023-11-28 04:26:55,462][87424] Updated weights for policy 0, policy_version 161907 (0.0008) -[2023-11-28 04:26:55,592][87426] Updated weights for policy 1, policy_version 161550 (0.0011) -[2023-11-28 04:26:55,838][87424] Updated weights for policy 0, policy_version 161917 (0.0009) -[2023-11-28 04:26:55,973][87426] Updated weights for policy 1, policy_version 161560 (0.0007) -[2023-11-28 04:26:58,088][87426] Updated weights for policy 1, policy_version 161570 (0.0008) -[2023-11-28 04:26:58,174][87424] Updated weights for policy 0, policy_version 161927 (0.0010) -[2023-11-28 04:26:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 82812928. Throughput: 0: 2706.8, 1: 2657.4. Samples: 82831384. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:26:58,445][86177] Avg episode reward: [(0, '-507.560'), (1, '-540.650')] -[2023-11-28 04:26:58,467][87426] Updated weights for policy 1, policy_version 161580 (0.0011) -[2023-11-28 04:26:58,559][87424] Updated weights for policy 0, policy_version 161937 (0.0011) -[2023-11-28 04:26:58,847][87426] Updated weights for policy 1, policy_version 161590 (0.0008) -[2023-11-28 04:26:58,945][87424] Updated weights for policy 0, policy_version 161947 (0.0011) -[2023-11-28 04:26:59,227][87426] Updated weights for policy 1, policy_version 161600 (0.0008) -[2023-11-28 04:27:00,805][87424] Updated weights for policy 0, policy_version 161957 (0.0012) -[2023-11-28 04:27:01,186][87424] Updated weights for policy 0, policy_version 161967 (0.0012) -[2023-11-28 04:27:01,466][87426] Updated weights for policy 1, policy_version 161610 (0.0010) -[2023-11-28 04:27:01,568][87424] Updated weights for policy 0, policy_version 161977 (0.0010) -[2023-11-28 04:27:01,838][87426] Updated weights for policy 1, policy_version 161620 (0.0011) -[2023-11-28 04:27:02,217][87426] Updated weights for policy 1, policy_version 161630 (0.0008) -[2023-11-28 04:27:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 82845696. Throughput: 0: 2737.4, 1: 2660.9. Samples: 82857360. Policy #0 lag: (min: 31.0, avg: 46.3, max: 63.0) -[2023-11-28 04:27:03,445][86177] Avg episode reward: [(0, '-506.750'), (1, '-542.260')] -[2023-11-28 04:27:03,753][87424] Updated weights for policy 0, policy_version 161987 (0.0009) -[2023-11-28 04:27:04,138][87424] Updated weights for policy 0, policy_version 161997 (0.0011) -[2023-11-28 04:27:04,404][87426] Updated weights for policy 1, policy_version 161640 (0.0011) -[2023-11-28 04:27:04,532][87424] Updated weights for policy 0, policy_version 162007 (0.0008) -[2023-11-28 04:27:04,785][87426] Updated weights for policy 1, policy_version 161650 (0.0008) -[2023-11-28 04:27:05,162][87426] Updated weights for policy 1, policy_version 161660 (0.0007) -[2023-11-28 04:27:06,695][87424] Updated weights for policy 0, policy_version 162017 (0.0009) -[2023-11-28 04:27:07,074][87424] Updated weights for policy 0, policy_version 162027 (0.0009) -[2023-11-28 04:27:07,465][87424] Updated weights for policy 0, policy_version 162037 (0.0009) -[2023-11-28 04:27:07,653][87426] Updated weights for policy 1, policy_version 161670 (0.0007) -[2023-11-28 04:27:07,849][87424] Updated weights for policy 0, policy_version 162047 (0.0007) -[2023-11-28 04:27:08,033][87426] Updated weights for policy 1, policy_version 161680 (0.0008) -[2023-11-28 04:27:08,420][87426] Updated weights for policy 1, policy_version 161690 (0.0007) -[2023-11-28 04:27:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 82870272. Throughput: 0: 2752.1, 1: 2667.6. Samples: 82889568. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:08,446][86177] Avg episode reward: [(0, '-512.030'), (1, '-540.360')] -[2023-11-28 04:27:09,992][87424] Updated weights for policy 0, policy_version 162057 (0.0009) -[2023-11-28 04:27:10,376][87424] Updated weights for policy 0, policy_version 162067 (0.0011) -[2023-11-28 04:27:10,752][87424] Updated weights for policy 0, policy_version 162077 (0.0010) -[2023-11-28 04:27:10,853][87426] Updated weights for policy 1, policy_version 161700 (0.0009) -[2023-11-28 04:27:11,228][87426] Updated weights for policy 1, policy_version 161710 (0.0012) -[2023-11-28 04:27:11,597][87426] Updated weights for policy 1, policy_version 161720 (0.0012) -[2023-11-28 04:27:12,866][87424] Updated weights for policy 0, policy_version 162087 (0.0008) -[2023-11-28 04:27:13,248][87424] Updated weights for policy 0, policy_version 162097 (0.0008) -[2023-11-28 04:27:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 82894848. Throughput: 0: 2730.8, 1: 2644.1. Samples: 82912264. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:13,445][86177] Avg episode reward: [(0, '-508.010'), (1, '-545.610')] -[2023-11-28 04:27:13,629][87424] Updated weights for policy 0, policy_version 162107 (0.0007) -[2023-11-28 04:27:13,928][87426] Updated weights for policy 1, policy_version 161730 (0.0010) -[2023-11-28 04:27:14,306][87426] Updated weights for policy 1, policy_version 161740 (0.0007) -[2023-11-28 04:27:14,686][87426] Updated weights for policy 1, policy_version 161750 (0.0007) -[2023-11-28 04:27:15,071][87426] Updated weights for policy 1, policy_version 161760 (0.0007) -[2023-11-28 04:27:15,990][87424] Updated weights for policy 0, policy_version 162117 (0.0009) -[2023-11-28 04:27:16,376][87424] Updated weights for policy 0, policy_version 162127 (0.0007) -[2023-11-28 04:27:16,764][87424] Updated weights for policy 0, policy_version 162137 (0.0008) -[2023-11-28 04:27:17,204][87426] Updated weights for policy 1, policy_version 161770 (0.0010) -[2023-11-28 04:27:17,573][87426] Updated weights for policy 1, policy_version 161780 (0.0009) -[2023-11-28 04:27:17,956][87426] Updated weights for policy 1, policy_version 161790 (0.0010) -[2023-11-28 04:27:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 82927616. Throughput: 0: 2752.2, 1: 2642.3. Samples: 82937448. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:18,445][86177] Avg episode reward: [(0, '-506.130'), (1, '-554.420')] -[2023-11-28 04:27:18,591][87424] Updated weights for policy 0, policy_version 162147 (0.0010) -[2023-11-28 04:27:18,981][87424] Updated weights for policy 0, policy_version 162157 (0.0009) -[2023-11-28 04:27:19,360][87424] Updated weights for policy 0, policy_version 162167 (0.0012) -[2023-11-28 04:27:20,502][87426] Updated weights for policy 1, policy_version 161800 (0.0009) -[2023-11-28 04:27:20,875][87426] Updated weights for policy 1, policy_version 161810 (0.0011) -[2023-11-28 04:27:21,253][87426] Updated weights for policy 1, policy_version 161820 (0.0011) -[2023-11-28 04:27:21,491][87424] Updated weights for policy 0, policy_version 162177 (0.0012) -[2023-11-28 04:27:21,882][87424] Updated weights for policy 0, policy_version 162187 (0.0012) -[2023-11-28 04:27:22,261][87424] Updated weights for policy 0, policy_version 162197 (0.0012) -[2023-11-28 04:27:22,646][87424] Updated weights for policy 0, policy_version 162207 (0.0012) -[2023-11-28 04:27:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 82952192. Throughput: 0: 2760.0, 1: 2604.4. Samples: 82968588. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:23,445][86177] Avg episode reward: [(0, '-502.210'), (1, '-545.490')] -[2023-11-28 04:27:23,629][87426] Updated weights for policy 1, policy_version 161830 (0.0010) -[2023-11-28 04:27:24,005][87426] Updated weights for policy 1, policy_version 161840 (0.0012) -[2023-11-28 04:27:24,382][87426] Updated weights for policy 1, policy_version 161850 (0.0011) -[2023-11-28 04:27:24,714][87424] Updated weights for policy 0, policy_version 162217 (0.0012) -[2023-11-28 04:27:25,111][87424] Updated weights for policy 0, policy_version 162227 (0.0010) -[2023-11-28 04:27:25,498][87424] Updated weights for policy 0, policy_version 162237 (0.0007) -[2023-11-28 04:27:26,617][87426] Updated weights for policy 1, policy_version 161860 (0.0009) -[2023-11-28 04:27:26,995][87426] Updated weights for policy 1, policy_version 161870 (0.0007) -[2023-11-28 04:27:27,387][87426] Updated weights for policy 1, policy_version 161880 (0.0012) -[2023-11-28 04:27:27,540][87424] Updated weights for policy 0, policy_version 162247 (0.0010) -[2023-11-28 04:27:27,925][87424] Updated weights for policy 0, policy_version 162257 (0.0012) -[2023-11-28 04:27:28,299][87424] Updated weights for policy 0, policy_version 162267 (0.0011) -[2023-11-28 04:27:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 82976768. Throughput: 0: 2790.5, 1: 2640.5. Samples: 82994660. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:28,445][86177] Avg episode reward: [(0, '-499.820'), (1, '-548.450')] -[2023-11-28 04:27:29,368][87426] Updated weights for policy 1, policy_version 161890 (0.0012) -[2023-11-28 04:27:29,742][87426] Updated weights for policy 1, policy_version 161900 (0.0012) -[2023-11-28 04:27:30,123][87426] Updated weights for policy 1, policy_version 161910 (0.0012) -[2023-11-28 04:27:30,498][87426] Updated weights for policy 1, policy_version 161920 (0.0011) -[2023-11-28 04:27:30,604][87424] Updated weights for policy 0, policy_version 162277 (0.0012) -[2023-11-28 04:27:30,998][87424] Updated weights for policy 0, policy_version 162287 (0.0012) -[2023-11-28 04:27:31,372][87424] Updated weights for policy 0, policy_version 162297 (0.0012) -[2023-11-28 04:27:32,843][87426] Updated weights for policy 1, policy_version 161930 (0.0012) -[2023-11-28 04:27:33,213][87426] Updated weights for policy 1, policy_version 161940 (0.0011) -[2023-11-28 04:27:33,292][87424] Updated weights for policy 0, policy_version 162307 (0.0012) -[2023-11-28 04:27:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 83001344. Throughput: 0: 2790.6, 1: 2656.6. Samples: 83019808. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:33,445][86177] Avg episode reward: [(0, '-509.450'), (1, '-508.430')] -[2023-11-28 04:27:33,594][87426] Updated weights for policy 1, policy_version 161950 (0.0012) -[2023-11-28 04:27:33,672][87424] Updated weights for policy 0, policy_version 162317 (0.0012) -[2023-11-28 04:27:34,060][87424] Updated weights for policy 0, policy_version 162327 (0.0012) -[2023-11-28 04:27:35,762][87426] Updated weights for policy 1, policy_version 161960 (0.0011) -[2023-11-28 04:27:35,947][87424] Updated weights for policy 0, policy_version 162337 (0.0012) -[2023-11-28 04:27:36,147][87426] Updated weights for policy 1, policy_version 161970 (0.0012) -[2023-11-28 04:27:36,331][87424] Updated weights for policy 0, policy_version 162347 (0.0011) -[2023-11-28 04:27:36,524][87426] Updated weights for policy 1, policy_version 161980 (0.0011) -[2023-11-28 04:27:36,721][87424] Updated weights for policy 0, policy_version 162357 (0.0010) -[2023-11-28 04:27:37,098][87424] Updated weights for policy 0, policy_version 162367 (0.0007) -[2023-11-28 04:27:38,425][87426] Updated weights for policy 1, policy_version 161990 (0.0012) -[2023-11-28 04:27:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83034112. Throughput: 0: 2813.6, 1: 2659.5. Samples: 83053104. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:38,445][86177] Avg episode reward: [(0, '-515.330'), (1, '-521.780')] -[2023-11-28 04:27:38,804][87426] Updated weights for policy 1, policy_version 162000 (0.0011) -[2023-11-28 04:27:38,858][87424] Updated weights for policy 0, policy_version 162377 (0.0010) -[2023-11-28 04:27:39,179][87426] Updated weights for policy 1, policy_version 162010 (0.0008) -[2023-11-28 04:27:39,253][87424] Updated weights for policy 0, policy_version 162387 (0.0011) -[2023-11-28 04:27:39,633][87424] Updated weights for policy 0, policy_version 162397 (0.0012) -[2023-11-28 04:27:41,700][87426] Updated weights for policy 1, policy_version 162020 (0.0009) -[2023-11-28 04:27:41,844][87424] Updated weights for policy 0, policy_version 162407 (0.0011) -[2023-11-28 04:27:42,087][87426] Updated weights for policy 1, policy_version 162030 (0.0009) -[2023-11-28 04:27:42,216][87424] Updated weights for policy 0, policy_version 162417 (0.0012) -[2023-11-28 04:27:42,459][87426] Updated weights for policy 1, policy_version 162040 (0.0009) -[2023-11-28 04:27:42,599][87424] Updated weights for policy 0, policy_version 162427 (0.0009) -[2023-11-28 04:27:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 83066880. Throughput: 0: 2826.8, 1: 2632.4. Samples: 83077048. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:43,445][86177] Avg episode reward: [(0, '-511.020'), (1, '-528.750')] -[2023-11-28 04:27:44,488][87426] Updated weights for policy 1, policy_version 162050 (0.0012) -[2023-11-28 04:27:44,570][87424] Updated weights for policy 0, policy_version 162437 (0.0009) -[2023-11-28 04:27:44,864][87426] Updated weights for policy 1, policy_version 162060 (0.0010) -[2023-11-28 04:27:44,970][87424] Updated weights for policy 0, policy_version 162447 (0.0010) -[2023-11-28 04:27:45,244][87426] Updated weights for policy 1, policy_version 162070 (0.0011) -[2023-11-28 04:27:45,354][87424] Updated weights for policy 0, policy_version 162457 (0.0010) -[2023-11-28 04:27:45,624][87426] Updated weights for policy 1, policy_version 162080 (0.0010) -[2023-11-28 04:27:47,325][87424] Updated weights for policy 0, policy_version 162467 (0.0012) -[2023-11-28 04:27:47,703][87424] Updated weights for policy 0, policy_version 162477 (0.0012) -[2023-11-28 04:27:48,090][87424] Updated weights for policy 0, policy_version 162487 (0.0008) -[2023-11-28 04:27:48,096][87426] Updated weights for policy 1, policy_version 162090 (0.0011) -[2023-11-28 04:27:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83091456. Throughput: 0: 2794.5, 1: 2627.3. Samples: 83101340. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:48,445][86177] Avg episode reward: [(0, '-501.510'), (1, '-528.200')] -[2023-11-28 04:27:48,481][87426] Updated weights for policy 1, policy_version 162100 (0.0008) -[2023-11-28 04:27:48,855][87426] Updated weights for policy 1, policy_version 162110 (0.0008) -[2023-11-28 04:27:50,523][87424] Updated weights for policy 0, policy_version 162497 (0.0008) -[2023-11-28 04:27:50,903][87426] Updated weights for policy 1, policy_version 162120 (0.0011) -[2023-11-28 04:27:50,909][87424] Updated weights for policy 0, policy_version 162507 (0.0010) -[2023-11-28 04:27:51,282][87426] Updated weights for policy 1, policy_version 162130 (0.0011) -[2023-11-28 04:27:51,291][87424] Updated weights for policy 0, policy_version 162517 (0.0009) -[2023-11-28 04:27:51,668][87426] Updated weights for policy 1, policy_version 162140 (0.0011) -[2023-11-28 04:27:51,681][87424] Updated weights for policy 0, policy_version 162527 (0.0011) -[2023-11-28 04:27:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 83116032. Throughput: 0: 2780.8, 1: 2644.2. Samples: 83133692. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:53,445][86177] Avg episode reward: [(0, '-502.810'), (1, '-526.090')] -[2023-11-28 04:27:53,692][87426] Updated weights for policy 1, policy_version 162150 (0.0010) -[2023-11-28 04:27:54,073][87426] Updated weights for policy 1, policy_version 162160 (0.0010) -[2023-11-28 04:27:54,264][87424] Updated weights for policy 0, policy_version 162537 (0.0011) -[2023-11-28 04:27:54,448][87426] Updated weights for policy 1, policy_version 162170 (0.0011) -[2023-11-28 04:27:54,650][87424] Updated weights for policy 0, policy_version 162547 (0.0011) -[2023-11-28 04:27:55,025][87424] Updated weights for policy 0, policy_version 162557 (0.0012) -[2023-11-28 04:27:56,624][87426] Updated weights for policy 1, policy_version 162180 (0.0011) -[2023-11-28 04:27:57,005][87424] Updated weights for policy 0, policy_version 162567 (0.0012) -[2023-11-28 04:27:57,006][87426] Updated weights for policy 1, policy_version 162190 (0.0012) -[2023-11-28 04:27:57,381][87426] Updated weights for policy 1, policy_version 162200 (0.0012) -[2023-11-28 04:27:57,389][87424] Updated weights for policy 0, policy_version 162577 (0.0012) -[2023-11-28 04:27:57,778][87424] Updated weights for policy 0, policy_version 162587 (0.0007) -[2023-11-28 04:27:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 83148800. Throughput: 0: 2782.7, 1: 2690.5. Samples: 83158556. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:27:58,445][86177] Avg episode reward: [(0, '-502.150'), (1, '-535.140')] -[2023-11-28 04:27:59,230][87426] Updated weights for policy 1, policy_version 162210 (0.0011) -[2023-11-28 04:27:59,608][87426] Updated weights for policy 1, policy_version 162220 (0.0012) -[2023-11-28 04:27:59,990][87426] Updated weights for policy 1, policy_version 162230 (0.0010) -[2023-11-28 04:28:00,161][87424] Updated weights for policy 0, policy_version 162597 (0.0007) -[2023-11-28 04:28:00,366][87426] Updated weights for policy 1, policy_version 162240 (0.0012) -[2023-11-28 04:28:00,554][87424] Updated weights for policy 0, policy_version 162607 (0.0008) -[2023-11-28 04:28:00,930][87424] Updated weights for policy 0, policy_version 162617 (0.0008) -[2023-11-28 04:28:02,636][87426] Updated weights for policy 1, policy_version 162250 (0.0012) -[2023-11-28 04:28:03,010][87426] Updated weights for policy 1, policy_version 162260 (0.0012) -[2023-11-28 04:28:03,300][87424] Updated weights for policy 0, policy_version 162627 (0.0011) -[2023-11-28 04:28:03,380][87426] Updated weights for policy 1, policy_version 162270 (0.0011) -[2023-11-28 04:28:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 83165184. Throughput: 0: 2757.2, 1: 2696.7. Samples: 83182872. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:28:03,445][86177] Avg episode reward: [(0, '-506.040'), (1, '-556.430')] -[2023-11-28 04:28:03,685][87424] Updated weights for policy 0, policy_version 162637 (0.0009) -[2023-11-28 04:28:04,073][87424] Updated weights for policy 0, policy_version 162647 (0.0008) -[2023-11-28 04:28:05,650][87426] Updated weights for policy 1, policy_version 162280 (0.0012) -[2023-11-28 04:28:05,778][87424] Updated weights for policy 0, policy_version 162657 (0.0010) -[2023-11-28 04:28:06,027][87426] Updated weights for policy 1, policy_version 162290 (0.0011) -[2023-11-28 04:28:06,155][87424] Updated weights for policy 0, policy_version 162667 (0.0011) -[2023-11-28 04:28:06,410][87426] Updated weights for policy 1, policy_version 162300 (0.0012) -[2023-11-28 04:28:06,545][87424] Updated weights for policy 0, policy_version 162677 (0.0011) -[2023-11-28 04:28:06,936][87424] Updated weights for policy 0, policy_version 162687 (0.0009) -[2023-11-28 04:28:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 83197952. Throughput: 0: 2757.4, 1: 2721.6. Samples: 83215144. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:28:08,445][86177] Avg episode reward: [(0, '-505.830'), (1, '-555.480')] -[2023-11-28 04:28:08,718][87426] Updated weights for policy 1, policy_version 162310 (0.0009) -[2023-11-28 04:28:09,103][87426] Updated weights for policy 1, policy_version 162320 (0.0010) -[2023-11-28 04:28:09,253][87424] Updated weights for policy 0, policy_version 162697 (0.0011) -[2023-11-28 04:28:09,494][87426] Updated weights for policy 1, policy_version 162330 (0.0012) -[2023-11-28 04:28:09,636][87424] Updated weights for policy 0, policy_version 162707 (0.0012) -[2023-11-28 04:28:10,032][87424] Updated weights for policy 0, policy_version 162717 (0.0012) -[2023-11-28 04:28:11,596][87426] Updated weights for policy 1, policy_version 162340 (0.0010) -[2023-11-28 04:28:11,977][87426] Updated weights for policy 1, policy_version 162350 (0.0011) -[2023-11-28 04:28:12,361][87426] Updated weights for policy 1, policy_version 162360 (0.0011) -[2023-11-28 04:28:12,551][87424] Updated weights for policy 0, policy_version 162727 (0.0012) -[2023-11-28 04:28:12,920][87424] Updated weights for policy 0, policy_version 162737 (0.0012) -[2023-11-28 04:28:13,309][87424] Updated weights for policy 0, policy_version 162747 (0.0011) -[2023-11-28 04:28:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83222528. Throughput: 0: 2730.3, 1: 2709.7. Samples: 83239460. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 04:28:13,445][86177] Avg episode reward: [(0, '-502.520'), (1, '-563.790')] -[2023-11-28 04:28:14,438][87426] Updated weights for policy 1, policy_version 162370 (0.0011) -[2023-11-28 04:28:14,822][87426] Updated weights for policy 1, policy_version 162380 (0.0009) -[2023-11-28 04:28:15,048][87424] Updated weights for policy 0, policy_version 162757 (0.0012) -[2023-11-28 04:28:15,211][87426] Updated weights for policy 1, policy_version 162390 (0.0008) -[2023-11-28 04:28:15,435][87424] Updated weights for policy 0, policy_version 162767 (0.0012) -[2023-11-28 04:28:15,577][87426] Updated weights for policy 1, policy_version 162400 (0.0010) -[2023-11-28 04:28:15,819][87424] Updated weights for policy 0, policy_version 162777 (0.0012) -[2023-11-28 04:28:17,608][87424] Updated weights for policy 0, policy_version 162787 (0.0012) -[2023-11-28 04:28:17,998][87424] Updated weights for policy 0, policy_version 162797 (0.0011) -[2023-11-28 04:28:18,047][87426] Updated weights for policy 1, policy_version 162410 (0.0009) -[2023-11-28 04:28:18,382][87424] Updated weights for policy 0, policy_version 162807 (0.0010) -[2023-11-28 04:28:18,436][87426] Updated weights for policy 1, policy_version 162420 (0.0011) -[2023-11-28 04:28:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 83247104. Throughput: 0: 2710.9, 1: 2710.2. Samples: 83263760. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:28:18,446][86177] Avg episode reward: [(0, '-501.370'), (1, '-536.960')] -[2023-11-28 04:28:18,723][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000162816_41680896.pth... -[2023-11-28 04:28:18,753][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000160224_41017344.pth -[2023-11-28 04:28:18,826][87426] Updated weights for policy 1, policy_version 162430 (0.0011) -[2023-11-28 04:28:18,901][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000162432_41582592.pth... -[2023-11-28 04:28:18,946][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000159936_40943616.pth -[2023-11-28 04:28:20,930][87424] Updated weights for policy 0, policy_version 162817 (0.0008) -[2023-11-28 04:28:21,284][87426] Updated weights for policy 1, policy_version 162440 (0.0011) -[2023-11-28 04:28:21,311][87424] Updated weights for policy 0, policy_version 162827 (0.0011) -[2023-11-28 04:28:21,668][87426] Updated weights for policy 1, policy_version 162450 (0.0011) -[2023-11-28 04:28:21,707][87424] Updated weights for policy 0, policy_version 162837 (0.0011) -[2023-11-28 04:28:22,049][87426] Updated weights for policy 1, policy_version 162460 (0.0012) -[2023-11-28 04:28:22,089][87424] Updated weights for policy 0, policy_version 162847 (0.0011) -[2023-11-28 04:28:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 83279872. Throughput: 0: 2684.3, 1: 2698.7. Samples: 83295336. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:28:23,445][86177] Avg episode reward: [(0, '-498.050'), (1, '-510.810')] -[2023-11-28 04:28:24,360][87424] Updated weights for policy 0, policy_version 162857 (0.0008) -[2023-11-28 04:28:24,360][87426] Updated weights for policy 1, policy_version 162470 (0.0012) -[2023-11-28 04:28:24,733][87426] Updated weights for policy 1, policy_version 162480 (0.0011) -[2023-11-28 04:28:24,753][87424] Updated weights for policy 0, policy_version 162867 (0.0010) -[2023-11-28 04:28:25,110][87426] Updated weights for policy 1, policy_version 162490 (0.0008) -[2023-11-28 04:28:25,132][87424] Updated weights for policy 0, policy_version 162877 (0.0010) -[2023-11-28 04:28:26,776][87426] Updated weights for policy 1, policy_version 162500 (0.0007) -[2023-11-28 04:28:27,155][87426] Updated weights for policy 1, policy_version 162510 (0.0008) -[2023-11-28 04:28:27,530][87426] Updated weights for policy 1, policy_version 162520 (0.0007) -[2023-11-28 04:28:27,676][87424] Updated weights for policy 0, policy_version 162887 (0.0007) -[2023-11-28 04:28:28,055][87424] Updated weights for policy 0, policy_version 162897 (0.0008) -[2023-11-28 04:28:28,442][87424] Updated weights for policy 0, policy_version 162907 (0.0007) -[2023-11-28 04:28:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83304448. Throughput: 0: 2672.4, 1: 2711.9. Samples: 83319340. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:28:28,445][86177] Avg episode reward: [(0, '-498.210'), (1, '-509.910')] -[2023-11-28 04:28:29,640][87426] Updated weights for policy 1, policy_version 162530 (0.0009) -[2023-11-28 04:28:30,018][87426] Updated weights for policy 1, policy_version 162540 (0.0011) -[2023-11-28 04:28:30,409][87426] Updated weights for policy 1, policy_version 162550 (0.0008) -[2023-11-28 04:28:30,779][87426] Updated weights for policy 1, policy_version 162560 (0.0008) -[2023-11-28 04:28:30,928][87424] Updated weights for policy 0, policy_version 162917 (0.0010) -[2023-11-28 04:28:31,307][87424] Updated weights for policy 0, policy_version 162927 (0.0012) -[2023-11-28 04:28:31,684][87424] Updated weights for policy 0, policy_version 162937 (0.0012) -[2023-11-28 04:28:33,188][87426] Updated weights for policy 1, policy_version 162570 (0.0008) -[2023-11-28 04:28:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 83329024. Throughput: 0: 2645.8, 1: 2718.8. Samples: 83342752. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:28:33,446][86177] Avg episode reward: [(0, '-500.340'), (1, '-552.260')] -[2023-11-28 04:28:33,574][87426] Updated weights for policy 1, policy_version 162580 (0.0008) -[2023-11-28 04:28:33,947][87426] Updated weights for policy 1, policy_version 162590 (0.0010) -[2023-11-28 04:28:34,217][87424] Updated weights for policy 0, policy_version 162947 (0.0011) -[2023-11-28 04:28:34,601][87424] Updated weights for policy 0, policy_version 162957 (0.0007) -[2023-11-28 04:28:34,981][87424] Updated weights for policy 0, policy_version 162967 (0.0009) -[2023-11-28 04:28:36,019][87426] Updated weights for policy 1, policy_version 162600 (0.0012) -[2023-11-28 04:28:36,404][87426] Updated weights for policy 1, policy_version 162610 (0.0011) -[2023-11-28 04:28:36,791][87426] Updated weights for policy 1, policy_version 162620 (0.0011) -[2023-11-28 04:28:37,070][87424] Updated weights for policy 0, policy_version 162977 (0.0011) -[2023-11-28 04:28:37,453][87424] Updated weights for policy 0, policy_version 162987 (0.0012) -[2023-11-28 04:28:37,833][87424] Updated weights for policy 0, policy_version 162997 (0.0010) -[2023-11-28 04:28:38,219][87424] Updated weights for policy 0, policy_version 163007 (0.0008) -[2023-11-28 04:28:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83361792. Throughput: 0: 2643.8, 1: 2712.6. Samples: 83374732. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:28:38,445][86177] Avg episode reward: [(0, '-500.640'), (1, '-569.120')] -[2023-11-28 04:28:38,863][87426] Updated weights for policy 1, policy_version 162630 (0.0011) -[2023-11-28 04:28:39,233][87426] Updated weights for policy 1, policy_version 162640 (0.0011) -[2023-11-28 04:28:39,613][87426] Updated weights for policy 1, policy_version 162650 (0.0011) -[2023-11-28 04:28:40,199][87424] Updated weights for policy 0, policy_version 163017 (0.0008) -[2023-11-28 04:28:40,586][87424] Updated weights for policy 0, policy_version 163027 (0.0011) -[2023-11-28 04:28:40,963][87424] Updated weights for policy 0, policy_version 163037 (0.0012) -[2023-11-28 04:28:41,840][87426] Updated weights for policy 1, policy_version 162660 (0.0011) -[2023-11-28 04:28:42,225][87426] Updated weights for policy 1, policy_version 162670 (0.0011) -[2023-11-28 04:28:42,606][87426] Updated weights for policy 1, policy_version 162680 (0.0010) -[2023-11-28 04:28:43,383][87424] Updated weights for policy 0, policy_version 163047 (0.0010) -[2023-11-28 04:28:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 83386368. Throughput: 0: 2653.9, 1: 2696.6. Samples: 83399328. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:28:43,446][86177] Avg episode reward: [(0, '-504.600'), (1, '-576.200')] -[2023-11-28 04:28:43,766][87424] Updated weights for policy 0, policy_version 163057 (0.0007) -[2023-11-28 04:28:44,148][87424] Updated weights for policy 0, policy_version 163067 (0.0007) -[2023-11-28 04:28:44,701][87426] Updated weights for policy 1, policy_version 162690 (0.0012) -[2023-11-28 04:28:45,077][87426] Updated weights for policy 1, policy_version 162700 (0.0012) -[2023-11-28 04:28:45,462][87426] Updated weights for policy 1, policy_version 162710 (0.0011) -[2023-11-28 04:28:45,826][87426] Updated weights for policy 1, policy_version 162720 (0.0012) -[2023-11-28 04:28:45,873][87424] Updated weights for policy 0, policy_version 163077 (0.0008) -[2023-11-28 04:28:46,264][87424] Updated weights for policy 0, policy_version 163087 (0.0007) -[2023-11-28 04:28:46,643][87424] Updated weights for policy 0, policy_version 163097 (0.0007) -[2023-11-28 04:28:47,835][87426] Updated weights for policy 1, policy_version 162730 (0.0012) -[2023-11-28 04:28:48,222][87426] Updated weights for policy 1, policy_version 162740 (0.0010) -[2023-11-28 04:28:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 83410944. Throughput: 0: 2667.2, 1: 2700.0. Samples: 83424396. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:28:48,445][86177] Avg episode reward: [(0, '-501.100'), (1, '-578.440')] -[2023-11-28 04:28:48,598][87426] Updated weights for policy 1, policy_version 162750 (0.0008) -[2023-11-28 04:28:48,906][87424] Updated weights for policy 0, policy_version 163107 (0.0009) -[2023-11-28 04:28:49,292][87424] Updated weights for policy 0, policy_version 163117 (0.0012) -[2023-11-28 04:28:49,674][87424] Updated weights for policy 0, policy_version 163127 (0.0009) -[2023-11-28 04:28:51,180][87426] Updated weights for policy 1, policy_version 162760 (0.0011) -[2023-11-28 04:28:51,566][87426] Updated weights for policy 1, policy_version 162770 (0.0012) -[2023-11-28 04:28:51,939][87426] Updated weights for policy 1, policy_version 162780 (0.0012) -[2023-11-28 04:28:52,164][87424] Updated weights for policy 0, policy_version 163137 (0.0011) -[2023-11-28 04:28:52,551][87424] Updated weights for policy 0, policy_version 163147 (0.0012) -[2023-11-28 04:28:52,928][87424] Updated weights for policy 0, policy_version 163157 (0.0012) -[2023-11-28 04:28:53,306][87424] Updated weights for policy 0, policy_version 163167 (0.0012) -[2023-11-28 04:28:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83443712. Throughput: 0: 2689.4, 1: 2712.1. Samples: 83458212. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:28:53,445][86177] Avg episode reward: [(0, '-496.770'), (1, '-529.020')] -[2023-11-28 04:28:54,183][87426] Updated weights for policy 1, policy_version 162790 (0.0010) -[2023-11-28 04:28:54,569][87426] Updated weights for policy 1, policy_version 162800 (0.0011) -[2023-11-28 04:28:54,940][87426] Updated weights for policy 1, policy_version 162810 (0.0011) -[2023-11-28 04:28:55,407][87424] Updated weights for policy 0, policy_version 163177 (0.0008) -[2023-11-28 04:28:55,790][87424] Updated weights for policy 0, policy_version 163187 (0.0007) -[2023-11-28 04:28:56,178][87424] Updated weights for policy 0, policy_version 163197 (0.0008) -[2023-11-28 04:28:56,892][87426] Updated weights for policy 1, policy_version 162820 (0.0010) -[2023-11-28 04:28:57,268][87426] Updated weights for policy 1, policy_version 162830 (0.0007) -[2023-11-28 04:28:57,647][87426] Updated weights for policy 1, policy_version 162840 (0.0007) -[2023-11-28 04:28:57,944][87424] Updated weights for policy 0, policy_version 163207 (0.0009) -[2023-11-28 04:28:58,329][87424] Updated weights for policy 0, policy_version 163217 (0.0011) -[2023-11-28 04:28:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 83468288. Throughput: 0: 2688.6, 1: 2721.6. Samples: 83482920. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:28:58,445][86177] Avg episode reward: [(0, '-496.500'), (1, '-513.340')] -[2023-11-28 04:28:58,698][87424] Updated weights for policy 0, policy_version 163227 (0.0010) -[2023-11-28 04:28:59,708][87426] Updated weights for policy 1, policy_version 162850 (0.0010) -[2023-11-28 04:29:00,087][87426] Updated weights for policy 1, policy_version 162860 (0.0012) -[2023-11-28 04:29:00,454][87426] Updated weights for policy 1, policy_version 162870 (0.0011) -[2023-11-28 04:29:00,834][87426] Updated weights for policy 1, policy_version 162880 (0.0012) -[2023-11-28 04:29:01,247][87424] Updated weights for policy 0, policy_version 163237 (0.0009) -[2023-11-28 04:29:01,626][87424] Updated weights for policy 0, policy_version 163247 (0.0008) -[2023-11-28 04:29:02,008][87424] Updated weights for policy 0, policy_version 163257 (0.0008) -[2023-11-28 04:29:03,278][87426] Updated weights for policy 1, policy_version 162890 (0.0012) -[2023-11-28 04:29:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 83492864. Throughput: 0: 2688.0, 1: 2723.5. Samples: 83507276. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:29:03,445][86177] Avg episode reward: [(0, '-491.070'), (1, '-501.700')] -[2023-11-28 04:29:03,660][87426] Updated weights for policy 1, policy_version 162900 (0.0012) -[2023-11-28 04:29:04,045][87426] Updated weights for policy 1, policy_version 162910 (0.0012) -[2023-11-28 04:29:04,325][87424] Updated weights for policy 0, policy_version 163267 (0.0008) -[2023-11-28 04:29:04,715][87424] Updated weights for policy 0, policy_version 163277 (0.0011) -[2023-11-28 04:29:05,094][87424] Updated weights for policy 0, policy_version 163287 (0.0011) -[2023-11-28 04:29:06,474][87426] Updated weights for policy 1, policy_version 162920 (0.0012) -[2023-11-28 04:29:06,849][87426] Updated weights for policy 1, policy_version 162930 (0.0011) -[2023-11-28 04:29:07,237][87426] Updated weights for policy 1, policy_version 162940 (0.0007) -[2023-11-28 04:29:07,415][87424] Updated weights for policy 0, policy_version 163297 (0.0011) -[2023-11-28 04:29:07,798][87424] Updated weights for policy 0, policy_version 163307 (0.0010) -[2023-11-28 04:29:08,186][87424] Updated weights for policy 0, policy_version 163317 (0.0008) -[2023-11-28 04:29:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 83517440. Throughput: 0: 2702.2, 1: 2729.3. Samples: 83539756. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:29:08,445][86177] Avg episode reward: [(0, '-495.000'), (1, '-500.990')] -[2023-11-28 04:29:08,566][87424] Updated weights for policy 0, policy_version 163327 (0.0012) -[2023-11-28 04:29:08,955][87426] Updated weights for policy 1, policy_version 162950 (0.0010) -[2023-11-28 04:29:09,327][87426] Updated weights for policy 1, policy_version 162960 (0.0009) -[2023-11-28 04:29:09,710][87426] Updated weights for policy 1, policy_version 162970 (0.0008) -[2023-11-28 04:29:10,603][87424] Updated weights for policy 0, policy_version 163337 (0.0012) -[2023-11-28 04:29:10,986][87424] Updated weights for policy 0, policy_version 163347 (0.0012) -[2023-11-28 04:29:11,371][87424] Updated weights for policy 0, policy_version 163357 (0.0012) -[2023-11-28 04:29:12,120][87426] Updated weights for policy 1, policy_version 162980 (0.0012) -[2023-11-28 04:29:12,504][87426] Updated weights for policy 1, policy_version 162990 (0.0012) -[2023-11-28 04:29:12,875][87426] Updated weights for policy 1, policy_version 163000 (0.0011) -[2023-11-28 04:29:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 83550208. Throughput: 0: 2719.9, 1: 2740.9. Samples: 83565076. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:29:13,445][86177] Avg episode reward: [(0, '-497.030'), (1, '-547.930')] -[2023-11-28 04:29:13,836][87424] Updated weights for policy 0, policy_version 163367 (0.0009) -[2023-11-28 04:29:14,222][87424] Updated weights for policy 0, policy_version 163377 (0.0007) -[2023-11-28 04:29:14,603][87424] Updated weights for policy 0, policy_version 163387 (0.0008) -[2023-11-28 04:29:14,803][87426] Updated weights for policy 1, policy_version 163010 (0.0009) -[2023-11-28 04:29:15,184][87426] Updated weights for policy 1, policy_version 163020 (0.0012) -[2023-11-28 04:29:15,562][87426] Updated weights for policy 1, policy_version 163030 (0.0009) -[2023-11-28 04:29:15,940][87426] Updated weights for policy 1, policy_version 163040 (0.0010) -[2023-11-28 04:29:16,460][87424] Updated weights for policy 0, policy_version 163397 (0.0010) -[2023-11-28 04:29:16,850][87424] Updated weights for policy 0, policy_version 163407 (0.0011) -[2023-11-28 04:29:17,234][87424] Updated weights for policy 0, policy_version 163417 (0.0007) -[2023-11-28 04:29:18,159][87426] Updated weights for policy 1, policy_version 163050 (0.0010) -[2023-11-28 04:29:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 83574784. Throughput: 0: 2750.8, 1: 2735.6. Samples: 83589636. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 04:29:18,445][86177] Avg episode reward: [(0, '-502.010'), (1, '-577.120')] -[2023-11-28 04:29:18,533][87426] Updated weights for policy 1, policy_version 163060 (0.0011) -[2023-11-28 04:29:18,906][87426] Updated weights for policy 1, policy_version 163070 (0.0009) -[2023-11-28 04:29:19,586][87424] Updated weights for policy 0, policy_version 163427 (0.0008) -[2023-11-28 04:29:19,959][87424] Updated weights for policy 0, policy_version 163437 (0.0009) -[2023-11-28 04:29:20,345][87424] Updated weights for policy 0, policy_version 163447 (0.0010) -[2023-11-28 04:29:20,906][87426] Updated weights for policy 1, policy_version 163080 (0.0009) -[2023-11-28 04:29:21,286][87426] Updated weights for policy 1, policy_version 163090 (0.0009) -[2023-11-28 04:29:21,669][87426] Updated weights for policy 1, policy_version 163100 (0.0010) -[2023-11-28 04:29:22,210][87424] Updated weights for policy 0, policy_version 163457 (0.0010) -[2023-11-28 04:29:22,592][87424] Updated weights for policy 0, policy_version 163467 (0.0008) -[2023-11-28 04:29:22,984][87424] Updated weights for policy 0, policy_version 163477 (0.0010) -[2023-11-28 04:29:23,361][87424] Updated weights for policy 0, policy_version 163487 (0.0009) -[2023-11-28 04:29:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83607552. Throughput: 0: 2758.4, 1: 2739.5. Samples: 83622136. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:29:23,445][86177] Avg episode reward: [(0, '-501.100'), (1, '-595.310')] -[2023-11-28 04:29:24,278][87426] Updated weights for policy 1, policy_version 163110 (0.0010) -[2023-11-28 04:29:24,656][87426] Updated weights for policy 1, policy_version 163120 (0.0009) -[2023-11-28 04:29:25,040][87426] Updated weights for policy 1, policy_version 163130 (0.0008) -[2023-11-28 04:29:25,609][87424] Updated weights for policy 0, policy_version 163497 (0.0011) -[2023-11-28 04:29:25,996][87424] Updated weights for policy 0, policy_version 163507 (0.0012) -[2023-11-28 04:29:26,379][87424] Updated weights for policy 0, policy_version 163517 (0.0012) -[2023-11-28 04:29:27,208][87426] Updated weights for policy 1, policy_version 163140 (0.0009) -[2023-11-28 04:29:27,581][87426] Updated weights for policy 1, policy_version 163150 (0.0008) -[2023-11-28 04:29:27,963][87426] Updated weights for policy 1, policy_version 163160 (0.0007) -[2023-11-28 04:29:28,111][87424] Updated weights for policy 0, policy_version 163527 (0.0012) -[2023-11-28 04:29:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 83632128. Throughput: 0: 2757.5, 1: 2737.2. Samples: 83646588. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:29:28,445][86177] Avg episode reward: [(0, '-500.720'), (1, '-601.620')] -[2023-11-28 04:29:28,499][87424] Updated weights for policy 0, policy_version 163537 (0.0012) -[2023-11-28 04:29:28,873][87424] Updated weights for policy 0, policy_version 163547 (0.0011) -[2023-11-28 04:29:29,876][87426] Updated weights for policy 1, policy_version 163170 (0.0009) -[2023-11-28 04:29:30,253][87426] Updated weights for policy 1, policy_version 163180 (0.0012) -[2023-11-28 04:29:30,629][87424] Updated weights for policy 0, policy_version 163557 (0.0011) -[2023-11-28 04:29:30,632][87426] Updated weights for policy 1, policy_version 163190 (0.0012) -[2023-11-28 04:29:31,006][87426] Updated weights for policy 1, policy_version 163200 (0.0008) -[2023-11-28 04:29:31,014][87424] Updated weights for policy 0, policy_version 163567 (0.0011) -[2023-11-28 04:29:31,397][87424] Updated weights for policy 0, policy_version 163577 (0.0012) -[2023-11-28 04:29:32,834][87426] Updated weights for policy 1, policy_version 163210 (0.0010) -[2023-11-28 04:29:33,215][87426] Updated weights for policy 1, policy_version 163220 (0.0010) -[2023-11-28 04:29:33,359][87424] Updated weights for policy 0, policy_version 163587 (0.0011) -[2023-11-28 04:29:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 83656704. Throughput: 0: 2742.8, 1: 2742.2. Samples: 83671220. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:29:33,445][86177] Avg episode reward: [(0, '-497.040'), (1, '-616.150')] -[2023-11-28 04:29:33,599][87426] Updated weights for policy 1, policy_version 163230 (0.0011) -[2023-11-28 04:29:33,740][87424] Updated weights for policy 0, policy_version 163597 (0.0011) -[2023-11-28 04:29:34,125][87424] Updated weights for policy 0, policy_version 163607 (0.0010) -[2023-11-28 04:29:35,966][87424] Updated weights for policy 0, policy_version 163617 (0.0007) -[2023-11-28 04:29:36,047][87426] Updated weights for policy 1, policy_version 163240 (0.0009) -[2023-11-28 04:29:36,353][87424] Updated weights for policy 0, policy_version 163627 (0.0010) -[2023-11-28 04:29:36,425][87426] Updated weights for policy 1, policy_version 163250 (0.0010) -[2023-11-28 04:29:36,731][87424] Updated weights for policy 0, policy_version 163637 (0.0009) -[2023-11-28 04:29:36,809][87426] Updated weights for policy 1, policy_version 163260 (0.0012) -[2023-11-28 04:29:37,126][87424] Updated weights for policy 0, policy_version 163647 (0.0012) -[2023-11-28 04:29:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83689472. Throughput: 0: 2758.3, 1: 2712.2. Samples: 83704384. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:29:38,445][86177] Avg episode reward: [(0, '-507.960'), (1, '-563.370')] -[2023-11-28 04:29:38,680][87426] Updated weights for policy 1, policy_version 163270 (0.0010) -[2023-11-28 04:29:38,756][87424] Updated weights for policy 0, policy_version 163657 (0.0012) -[2023-11-28 04:29:39,056][87426] Updated weights for policy 1, policy_version 163280 (0.0011) -[2023-11-28 04:29:39,144][87424] Updated weights for policy 0, policy_version 163667 (0.0012) -[2023-11-28 04:29:39,443][87426] Updated weights for policy 1, policy_version 163290 (0.0010) -[2023-11-28 04:29:39,522][87424] Updated weights for policy 0, policy_version 163677 (0.0011) -[2023-11-28 04:29:42,009][87426] Updated weights for policy 1, policy_version 163300 (0.0009) -[2023-11-28 04:29:42,015][87424] Updated weights for policy 0, policy_version 163687 (0.0010) -[2023-11-28 04:29:42,381][87426] Updated weights for policy 1, policy_version 163310 (0.0011) -[2023-11-28 04:29:42,387][87424] Updated weights for policy 0, policy_version 163697 (0.0011) -[2023-11-28 04:29:42,759][87426] Updated weights for policy 1, policy_version 163320 (0.0011) -[2023-11-28 04:29:42,771][87424] Updated weights for policy 0, policy_version 163707 (0.0008) -[2023-11-28 04:29:43,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 83722240. Throughput: 0: 2773.8, 1: 2687.9. Samples: 83728696. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:29:43,445][86177] Avg episode reward: [(0, '-507.330'), (1, '-548.940')] -[2023-11-28 04:29:45,161][87424] Updated weights for policy 0, policy_version 163717 (0.0012) -[2023-11-28 04:29:45,316][87426] Updated weights for policy 1, policy_version 163330 (0.0009) -[2023-11-28 04:29:45,533][87424] Updated weights for policy 0, policy_version 163727 (0.0011) -[2023-11-28 04:29:45,692][87426] Updated weights for policy 1, policy_version 163340 (0.0010) -[2023-11-28 04:29:45,917][87424] Updated weights for policy 0, policy_version 163737 (0.0011) -[2023-11-28 04:29:46,075][87426] Updated weights for policy 1, policy_version 163350 (0.0011) -[2023-11-28 04:29:46,444][87426] Updated weights for policy 1, policy_version 163360 (0.0011) -[2023-11-28 04:29:48,388][87424] Updated weights for policy 0, policy_version 163747 (0.0011) -[2023-11-28 04:29:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 83738624. Throughput: 0: 2765.7, 1: 2666.9. Samples: 83751744. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:29:48,445][87426] Updated weights for policy 1, policy_version 163370 (0.0011) -[2023-11-28 04:29:48,445][86177] Avg episode reward: [(0, '-509.340'), (1, '-552.370')] -[2023-11-28 04:29:48,761][87424] Updated weights for policy 0, policy_version 163757 (0.0010) -[2023-11-28 04:29:48,823][87426] Updated weights for policy 1, policy_version 163380 (0.0010) -[2023-11-28 04:29:49,142][87424] Updated weights for policy 0, policy_version 163767 (0.0011) -[2023-11-28 04:29:49,198][87426] Updated weights for policy 1, policy_version 163390 (0.0011) -[2023-11-28 04:29:51,098][87426] Updated weights for policy 1, policy_version 163400 (0.0012) -[2023-11-28 04:29:51,476][87426] Updated weights for policy 1, policy_version 163410 (0.0012) -[2023-11-28 04:29:51,599][87424] Updated weights for policy 0, policy_version 163777 (0.0012) -[2023-11-28 04:29:51,854][87426] Updated weights for policy 1, policy_version 163420 (0.0011) -[2023-11-28 04:29:51,986][87424] Updated weights for policy 0, policy_version 163787 (0.0012) -[2023-11-28 04:29:52,370][87424] Updated weights for policy 0, policy_version 163797 (0.0012) -[2023-11-28 04:29:52,756][87424] Updated weights for policy 0, policy_version 163807 (0.0012) -[2023-11-28 04:29:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83771392. Throughput: 0: 2748.2, 1: 2706.0. Samples: 83785196. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:29:53,445][86177] Avg episode reward: [(0, '-508.820'), (1, '-529.390')] -[2023-11-28 04:29:54,309][87426] Updated weights for policy 1, policy_version 163430 (0.0011) -[2023-11-28 04:29:54,686][87426] Updated weights for policy 1, policy_version 163440 (0.0012) -[2023-11-28 04:29:54,899][87424] Updated weights for policy 0, policy_version 163817 (0.0010) -[2023-11-28 04:29:55,056][87426] Updated weights for policy 1, policy_version 163450 (0.0011) -[2023-11-28 04:29:55,280][87424] Updated weights for policy 0, policy_version 163827 (0.0011) -[2023-11-28 04:29:55,662][87424] Updated weights for policy 0, policy_version 163837 (0.0012) -[2023-11-28 04:29:56,942][87426] Updated weights for policy 1, policy_version 163460 (0.0012) -[2023-11-28 04:29:57,326][87426] Updated weights for policy 1, policy_version 163470 (0.0011) -[2023-11-28 04:29:57,705][87426] Updated weights for policy 1, policy_version 163480 (0.0011) -[2023-11-28 04:29:57,749][87424] Updated weights for policy 0, policy_version 163847 (0.0011) -[2023-11-28 04:29:58,127][87424] Updated weights for policy 0, policy_version 163857 (0.0007) -[2023-11-28 04:29:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 83795968. Throughput: 0: 2734.2, 1: 2729.7. Samples: 83810952. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:29:58,445][86177] Avg episode reward: [(0, '-499.420'), (1, '-528.870')] -[2023-11-28 04:29:58,513][87424] Updated weights for policy 0, policy_version 163867 (0.0007) -[2023-11-28 04:29:59,748][87426] Updated weights for policy 1, policy_version 163490 (0.0011) -[2023-11-28 04:30:00,129][87426] Updated weights for policy 1, policy_version 163500 (0.0008) -[2023-11-28 04:30:00,522][87426] Updated weights for policy 1, policy_version 163510 (0.0008) -[2023-11-28 04:30:00,895][87426] Updated weights for policy 1, policy_version 163520 (0.0010) -[2023-11-28 04:30:00,989][87424] Updated weights for policy 0, policy_version 163877 (0.0010) -[2023-11-28 04:30:01,365][87424] Updated weights for policy 0, policy_version 163887 (0.0011) -[2023-11-28 04:30:01,749][87424] Updated weights for policy 0, policy_version 163897 (0.0009) -[2023-11-28 04:30:03,143][87426] Updated weights for policy 1, policy_version 163530 (0.0008) -[2023-11-28 04:30:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83820544. Throughput: 0: 2731.8, 1: 2734.0. Samples: 83835596. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:30:03,445][86177] Avg episode reward: [(0, '-511.350'), (1, '-509.960')] -[2023-11-28 04:30:03,529][87426] Updated weights for policy 1, policy_version 163540 (0.0011) -[2023-11-28 04:30:03,792][87424] Updated weights for policy 0, policy_version 163907 (0.0010) -[2023-11-28 04:30:03,912][87426] Updated weights for policy 1, policy_version 163550 (0.0009) -[2023-11-28 04:30:04,168][87424] Updated weights for policy 0, policy_version 163917 (0.0011) -[2023-11-28 04:30:04,566][87424] Updated weights for policy 0, policy_version 163927 (0.0011) -[2023-11-28 04:30:06,239][87426] Updated weights for policy 1, policy_version 163560 (0.0010) -[2023-11-28 04:30:06,608][87426] Updated weights for policy 1, policy_version 163570 (0.0011) -[2023-11-28 04:30:06,625][87424] Updated weights for policy 0, policy_version 163937 (0.0010) -[2023-11-28 04:30:06,983][87426] Updated weights for policy 1, policy_version 163580 (0.0010) -[2023-11-28 04:30:06,999][87424] Updated weights for policy 0, policy_version 163947 (0.0011) -[2023-11-28 04:30:07,379][87424] Updated weights for policy 0, policy_version 163957 (0.0012) -[2023-11-28 04:30:07,761][87424] Updated weights for policy 0, policy_version 163967 (0.0008) -[2023-11-28 04:30:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 83853312. Throughput: 0: 2730.1, 1: 2718.0. Samples: 83867300. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:30:08,445][86177] Avg episode reward: [(0, '-514.420'), (1, '-497.070')] -[2023-11-28 04:30:08,937][87426] Updated weights for policy 1, policy_version 163590 (0.0010) -[2023-11-28 04:30:09,309][87426] Updated weights for policy 1, policy_version 163600 (0.0011) -[2023-11-28 04:30:09,652][87424] Updated weights for policy 0, policy_version 163977 (0.0011) -[2023-11-28 04:30:09,687][87426] Updated weights for policy 1, policy_version 163610 (0.0011) -[2023-11-28 04:30:10,034][87424] Updated weights for policy 0, policy_version 163987 (0.0012) -[2023-11-28 04:30:10,414][87424] Updated weights for policy 0, policy_version 163997 (0.0012) -[2023-11-28 04:30:11,913][87426] Updated weights for policy 1, policy_version 163620 (0.0012) -[2023-11-28 04:30:12,297][87426] Updated weights for policy 1, policy_version 163630 (0.0012) -[2023-11-28 04:30:12,514][87424] Updated weights for policy 0, policy_version 164007 (0.0011) -[2023-11-28 04:30:12,677][87426] Updated weights for policy 1, policy_version 163640 (0.0012) -[2023-11-28 04:30:12,896][87424] Updated weights for policy 0, policy_version 164017 (0.0010) -[2023-11-28 04:30:13,282][87424] Updated weights for policy 0, policy_version 164027 (0.0011) -[2023-11-28 04:30:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 83877888. Throughput: 0: 2725.4, 1: 2725.6. Samples: 83891884. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:30:13,446][86177] Avg episode reward: [(0, '-524.010'), (1, '-498.460')] -[2023-11-28 04:30:14,636][87426] Updated weights for policy 1, policy_version 163650 (0.0011) -[2023-11-28 04:30:15,020][87426] Updated weights for policy 1, policy_version 163660 (0.0010) -[2023-11-28 04:30:15,176][87424] Updated weights for policy 0, policy_version 164037 (0.0011) -[2023-11-28 04:30:15,407][87426] Updated weights for policy 1, policy_version 163670 (0.0009) -[2023-11-28 04:30:15,545][87424] Updated weights for policy 0, policy_version 164047 (0.0011) -[2023-11-28 04:30:15,775][87426] Updated weights for policy 1, policy_version 163680 (0.0011) -[2023-11-28 04:30:15,934][87424] Updated weights for policy 0, policy_version 164057 (0.0011) -[2023-11-28 04:30:18,074][87426] Updated weights for policy 1, policy_version 163690 (0.0012) -[2023-11-28 04:30:18,281][87424] Updated weights for policy 0, policy_version 164067 (0.0011) -[2023-11-28 04:30:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83902464. Throughput: 0: 2764.0, 1: 2730.9. Samples: 83918492. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:30:18,445][86177] Avg episode reward: [(0, '-541.150'), (1, '-498.880')] -[2023-11-28 04:30:18,461][87426] Updated weights for policy 1, policy_version 163700 (0.0011) -[2023-11-28 04:30:18,662][87424] Updated weights for policy 0, policy_version 164077 (0.0012) -[2023-11-28 04:30:18,835][87426] Updated weights for policy 1, policy_version 163710 (0.0010) -[2023-11-28 04:30:18,910][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000163712_41910272.pth... -[2023-11-28 04:30:18,959][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000161184_41263104.pth -[2023-11-28 04:30:19,042][87424] Updated weights for policy 0, policy_version 164087 (0.0020) -[2023-11-28 04:30:19,387][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000164096_42008576.pth... -[2023-11-28 04:30:19,434][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000161504_41345024.pth -[2023-11-28 04:30:20,985][87426] Updated weights for policy 1, policy_version 163720 (0.0009) -[2023-11-28 04:30:21,195][87424] Updated weights for policy 0, policy_version 164097 (0.0012) -[2023-11-28 04:30:21,362][87426] Updated weights for policy 1, policy_version 163730 (0.0010) -[2023-11-28 04:30:21,595][87424] Updated weights for policy 0, policy_version 164107 (0.0012) -[2023-11-28 04:30:21,736][87426] Updated weights for policy 1, policy_version 163740 (0.0010) -[2023-11-28 04:30:21,971][87424] Updated weights for policy 0, policy_version 164117 (0.0011) -[2023-11-28 04:30:22,364][87424] Updated weights for policy 0, policy_version 164127 (0.0012) -[2023-11-28 04:30:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83935232. Throughput: 0: 2740.4, 1: 2748.4. Samples: 83951384. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:30:23,445][86177] Avg episode reward: [(0, '-529.180'), (1, '-599.850')] -[2023-11-28 04:30:23,981][87426] Updated weights for policy 1, policy_version 163750 (0.0010) -[2023-11-28 04:30:24,362][87426] Updated weights for policy 1, policy_version 163760 (0.0010) -[2023-11-28 04:30:24,742][87426] Updated weights for policy 1, policy_version 163770 (0.0007) -[2023-11-28 04:30:24,879][87424] Updated weights for policy 0, policy_version 164137 (0.0008) -[2023-11-28 04:30:25,270][87424] Updated weights for policy 0, policy_version 164147 (0.0008) -[2023-11-28 04:30:25,648][87424] Updated weights for policy 0, policy_version 164157 (0.0008) -[2023-11-28 04:30:26,829][87426] Updated weights for policy 1, policy_version 163780 (0.0009) -[2023-11-28 04:30:27,204][87426] Updated weights for policy 1, policy_version 163790 (0.0010) -[2023-11-28 04:30:27,585][87426] Updated weights for policy 1, policy_version 163800 (0.0011) -[2023-11-28 04:30:27,691][87424] Updated weights for policy 0, policy_version 164167 (0.0010) -[2023-11-28 04:30:28,067][87424] Updated weights for policy 0, policy_version 164177 (0.0011) -[2023-11-28 04:30:28,444][87424] Updated weights for policy 0, policy_version 164187 (0.0012) -[2023-11-28 04:30:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 83959808. Throughput: 0: 2725.2, 1: 2761.2. Samples: 83975588. Policy #0 lag: (min: 45.0, avg: 62.6, max: 89.0) -[2023-11-28 04:30:28,445][86177] Avg episode reward: [(0, '-523.000'), (1, '-612.300')] -[2023-11-28 04:30:30,082][87426] Updated weights for policy 1, policy_version 163810 (0.0008) -[2023-11-28 04:30:30,356][87424] Updated weights for policy 0, policy_version 164197 (0.0010) -[2023-11-28 04:30:30,461][87426] Updated weights for policy 1, policy_version 163820 (0.0010) -[2023-11-28 04:30:30,737][87424] Updated weights for policy 0, policy_version 164207 (0.0008) -[2023-11-28 04:30:30,842][87426] Updated weights for policy 1, policy_version 163830 (0.0007) -[2023-11-28 04:30:31,121][87424] Updated weights for policy 0, policy_version 164217 (0.0008) -[2023-11-28 04:30:31,220][87426] Updated weights for policy 1, policy_version 163840 (0.0008) -[2023-11-28 04:30:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 83984384. Throughput: 0: 2751.9, 1: 2773.9. Samples: 84000404. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:30:33,445][86177] Avg episode reward: [(0, '-500.970'), (1, '-611.400')] -[2023-11-28 04:30:33,471][87424] Updated weights for policy 0, policy_version 164227 (0.0008) -[2023-11-28 04:30:33,846][87426] Updated weights for policy 1, policy_version 163850 (0.0012) -[2023-11-28 04:30:33,850][87424] Updated weights for policy 0, policy_version 164237 (0.0008) -[2023-11-28 04:30:34,226][87426] Updated weights for policy 1, policy_version 163860 (0.0009) -[2023-11-28 04:30:34,252][87424] Updated weights for policy 0, policy_version 164247 (0.0010) -[2023-11-28 04:30:34,602][87426] Updated weights for policy 1, policy_version 163870 (0.0009) -[2023-11-28 04:30:36,340][87424] Updated weights for policy 0, policy_version 164257 (0.0011) -[2023-11-28 04:30:36,484][87426] Updated weights for policy 1, policy_version 163880 (0.0008) -[2023-11-28 04:30:36,729][87424] Updated weights for policy 0, policy_version 164267 (0.0010) -[2023-11-28 04:30:36,862][87426] Updated weights for policy 1, policy_version 163890 (0.0010) -[2023-11-28 04:30:37,107][87424] Updated weights for policy 0, policy_version 164277 (0.0009) -[2023-11-28 04:30:37,247][87426] Updated weights for policy 1, policy_version 163900 (0.0011) -[2023-11-28 04:30:37,486][87424] Updated weights for policy 0, policy_version 164287 (0.0008) -[2023-11-28 04:30:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84017152. Throughput: 0: 2746.8, 1: 2736.7. Samples: 84031956. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:30:38,445][86177] Avg episode reward: [(0, '-496.250'), (1, '-608.390')] -[2023-11-28 04:30:39,488][87426] Updated weights for policy 1, policy_version 163910 (0.0010) -[2023-11-28 04:30:39,748][87424] Updated weights for policy 0, policy_version 164297 (0.0010) -[2023-11-28 04:30:39,872][87426] Updated weights for policy 1, policy_version 163920 (0.0010) -[2023-11-28 04:30:40,130][87424] Updated weights for policy 0, policy_version 164307 (0.0011) -[2023-11-28 04:30:40,251][87426] Updated weights for policy 1, policy_version 163930 (0.0009) -[2023-11-28 04:30:40,510][87424] Updated weights for policy 0, policy_version 164317 (0.0010) -[2023-11-28 04:30:42,667][87426] Updated weights for policy 1, policy_version 163940 (0.0010) -[2023-11-28 04:30:42,699][87424] Updated weights for policy 0, policy_version 164327 (0.0010) -[2023-11-28 04:30:43,040][87426] Updated weights for policy 1, policy_version 163950 (0.0011) -[2023-11-28 04:30:43,087][87424] Updated weights for policy 0, policy_version 164337 (0.0011) -[2023-11-28 04:30:43,420][87426] Updated weights for policy 1, policy_version 163960 (0.0011) -[2023-11-28 04:30:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 84033536. Throughput: 0: 2738.0, 1: 2686.0. Samples: 84055032. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:30:43,445][86177] Avg episode reward: [(0, '-498.890'), (1, '-518.210')] -[2023-11-28 04:30:43,468][87424] Updated weights for policy 0, policy_version 164347 (0.0011) -[2023-11-28 04:30:45,402][87424] Updated weights for policy 0, policy_version 164357 (0.0011) -[2023-11-28 04:30:45,781][87424] Updated weights for policy 0, policy_version 164367 (0.0012) -[2023-11-28 04:30:45,801][87426] Updated weights for policy 1, policy_version 163970 (0.0009) -[2023-11-28 04:30:46,167][87424] Updated weights for policy 0, policy_version 164377 (0.0007) -[2023-11-28 04:30:46,174][87426] Updated weights for policy 1, policy_version 163980 (0.0011) -[2023-11-28 04:30:46,559][87426] Updated weights for policy 1, policy_version 163990 (0.0011) -[2023-11-28 04:30:46,940][87426] Updated weights for policy 1, policy_version 164000 (0.0010) -[2023-11-28 04:30:48,171][87424] Updated weights for policy 0, policy_version 164387 (0.0007) -[2023-11-28 04:30:48,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84066304. Throughput: 0: 2752.2, 1: 2678.1. Samples: 84079960. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:30:48,446][86177] Avg episode reward: [(0, '-493.060'), (1, '-510.860')] -[2023-11-28 04:30:48,562][87424] Updated weights for policy 0, policy_version 164397 (0.0008) -[2023-11-28 04:30:48,938][87424] Updated weights for policy 0, policy_version 164407 (0.0008) -[2023-11-28 04:30:49,127][87426] Updated weights for policy 1, policy_version 164010 (0.0009) -[2023-11-28 04:30:49,510][87426] Updated weights for policy 1, policy_version 164020 (0.0009) -[2023-11-28 04:30:49,900][87426] Updated weights for policy 1, policy_version 164030 (0.0011) -[2023-11-28 04:30:51,071][87424] Updated weights for policy 0, policy_version 164417 (0.0011) -[2023-11-28 04:30:51,451][87424] Updated weights for policy 0, policy_version 164427 (0.0009) -[2023-11-28 04:30:51,843][87424] Updated weights for policy 0, policy_version 164437 (0.0009) -[2023-11-28 04:30:52,145][87426] Updated weights for policy 1, policy_version 164040 (0.0008) -[2023-11-28 04:30:52,222][87424] Updated weights for policy 0, policy_version 164447 (0.0008) -[2023-11-28 04:30:52,517][87426] Updated weights for policy 1, policy_version 164050 (0.0009) -[2023-11-28 04:30:52,899][87426] Updated weights for policy 1, policy_version 164060 (0.0011) -[2023-11-28 04:30:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84099072. Throughput: 0: 2774.7, 1: 2682.1. Samples: 84112856. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:30:53,445][86177] Avg episode reward: [(0, '-495.530'), (1, '-514.300')] -[2023-11-28 04:30:54,404][87424] Updated weights for policy 0, policy_version 164457 (0.0012) -[2023-11-28 04:30:54,780][87424] Updated weights for policy 0, policy_version 164467 (0.0011) -[2023-11-28 04:30:54,863][87426] Updated weights for policy 1, policy_version 164070 (0.0010) -[2023-11-28 04:30:55,156][87424] Updated weights for policy 0, policy_version 164477 (0.0012) -[2023-11-28 04:30:55,245][87426] Updated weights for policy 1, policy_version 164080 (0.0007) -[2023-11-28 04:30:55,637][87426] Updated weights for policy 1, policy_version 164090 (0.0007) -[2023-11-28 04:30:57,335][87424] Updated weights for policy 0, policy_version 164487 (0.0012) -[2023-11-28 04:30:57,572][87426] Updated weights for policy 1, policy_version 164100 (0.0009) -[2023-11-28 04:30:57,708][87424] Updated weights for policy 0, policy_version 164497 (0.0010) -[2023-11-28 04:30:57,962][87426] Updated weights for policy 1, policy_version 164110 (0.0010) -[2023-11-28 04:30:58,081][87424] Updated weights for policy 0, policy_version 164507 (0.0009) -[2023-11-28 04:30:58,344][87426] Updated weights for policy 1, policy_version 164120 (0.0007) -[2023-11-28 04:30:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84123648. Throughput: 0: 2770.4, 1: 2699.5. Samples: 84138028. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:30:58,445][86177] Avg episode reward: [(0, '-494.620'), (1, '-531.870')] -[2023-11-28 04:31:00,236][87424] Updated weights for policy 0, policy_version 164517 (0.0009) -[2023-11-28 04:31:00,619][87424] Updated weights for policy 0, policy_version 164527 (0.0009) -[2023-11-28 04:31:00,836][87426] Updated weights for policy 1, policy_version 164130 (0.0008) -[2023-11-28 04:31:01,001][87424] Updated weights for policy 0, policy_version 164537 (0.0008) -[2023-11-28 04:31:01,212][87426] Updated weights for policy 1, policy_version 164140 (0.0011) -[2023-11-28 04:31:01,602][87426] Updated weights for policy 1, policy_version 164150 (0.0012) -[2023-11-28 04:31:01,985][87426] Updated weights for policy 1, policy_version 164160 (0.0009) -[2023-11-28 04:31:03,326][87424] Updated weights for policy 0, policy_version 164547 (0.0009) -[2023-11-28 04:31:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84148224. Throughput: 0: 2735.6, 1: 2664.1. Samples: 84161476. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:31:03,445][86177] Avg episode reward: [(0, '-494.300'), (1, '-525.430')] -[2023-11-28 04:31:03,704][87424] Updated weights for policy 0, policy_version 164557 (0.0012) -[2023-11-28 04:31:04,015][87426] Updated weights for policy 1, policy_version 164170 (0.0011) -[2023-11-28 04:31:04,092][87424] Updated weights for policy 0, policy_version 164567 (0.0011) -[2023-11-28 04:31:04,382][87426] Updated weights for policy 1, policy_version 164180 (0.0011) -[2023-11-28 04:31:04,761][87426] Updated weights for policy 1, policy_version 164190 (0.0012) -[2023-11-28 04:31:06,045][87424] Updated weights for policy 0, policy_version 164577 (0.0011) -[2023-11-28 04:31:06,426][87424] Updated weights for policy 0, policy_version 164587 (0.0012) -[2023-11-28 04:31:06,816][87424] Updated weights for policy 0, policy_version 164597 (0.0011) -[2023-11-28 04:31:06,838][87426] Updated weights for policy 1, policy_version 164200 (0.0012) -[2023-11-28 04:31:07,193][87424] Updated weights for policy 0, policy_version 164607 (0.0012) -[2023-11-28 04:31:07,216][87426] Updated weights for policy 1, policy_version 164210 (0.0011) -[2023-11-28 04:31:07,599][87426] Updated weights for policy 1, policy_version 164220 (0.0012) -[2023-11-28 04:31:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84180992. Throughput: 0: 2734.0, 1: 2689.4. Samples: 84195440. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:31:08,445][86177] Avg episode reward: [(0, '-493.050'), (1, '-527.980')] -[2023-11-28 04:31:09,309][87424] Updated weights for policy 0, policy_version 164617 (0.0009) -[2023-11-28 04:31:09,564][87426] Updated weights for policy 1, policy_version 164230 (0.0011) -[2023-11-28 04:31:09,689][87424] Updated weights for policy 0, policy_version 164627 (0.0010) -[2023-11-28 04:31:09,941][87426] Updated weights for policy 1, policy_version 164240 (0.0012) -[2023-11-28 04:31:10,078][87424] Updated weights for policy 0, policy_version 164637 (0.0011) -[2023-11-28 04:31:10,326][87426] Updated weights for policy 1, policy_version 164250 (0.0012) -[2023-11-28 04:31:11,848][87424] Updated weights for policy 0, policy_version 164647 (0.0012) -[2023-11-28 04:31:12,217][87424] Updated weights for policy 0, policy_version 164657 (0.0012) -[2023-11-28 04:31:12,575][87426] Updated weights for policy 1, policy_version 164260 (0.0012) -[2023-11-28 04:31:12,599][87424] Updated weights for policy 0, policy_version 164667 (0.0011) -[2023-11-28 04:31:12,955][87426] Updated weights for policy 1, policy_version 164270 (0.0011) -[2023-11-28 04:31:13,338][87426] Updated weights for policy 1, policy_version 164280 (0.0010) -[2023-11-28 04:31:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84205568. Throughput: 0: 2748.4, 1: 2682.4. Samples: 84219976. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:31:13,445][86177] Avg episode reward: [(0, '-495.830'), (1, '-526.470')] -[2023-11-28 04:31:15,095][87424] Updated weights for policy 0, policy_version 164677 (0.0008) -[2023-11-28 04:31:15,484][87424] Updated weights for policy 0, policy_version 164687 (0.0009) -[2023-11-28 04:31:15,792][87426] Updated weights for policy 1, policy_version 164290 (0.0011) -[2023-11-28 04:31:15,856][87424] Updated weights for policy 0, policy_version 164697 (0.0011) -[2023-11-28 04:31:16,166][87426] Updated weights for policy 1, policy_version 164300 (0.0012) -[2023-11-28 04:31:16,547][87426] Updated weights for policy 1, policy_version 164310 (0.0008) -[2023-11-28 04:31:16,927][87426] Updated weights for policy 1, policy_version 164320 (0.0008) -[2023-11-28 04:31:18,129][87424] Updated weights for policy 0, policy_version 164707 (0.0012) -[2023-11-28 04:31:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84230144. Throughput: 0: 2729.5, 1: 2681.9. Samples: 84243916. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:31:18,445][86177] Avg episode reward: [(0, '-497.630'), (1, '-506.530')] -[2023-11-28 04:31:18,520][87424] Updated weights for policy 0, policy_version 164717 (0.0012) -[2023-11-28 04:31:18,768][87426] Updated weights for policy 1, policy_version 164330 (0.0011) -[2023-11-28 04:31:18,906][87424] Updated weights for policy 0, policy_version 164727 (0.0011) -[2023-11-28 04:31:19,161][87426] Updated weights for policy 1, policy_version 164340 (0.0011) -[2023-11-28 04:31:19,552][87426] Updated weights for policy 1, policy_version 164350 (0.0010) -[2023-11-28 04:31:20,884][87424] Updated weights for policy 0, policy_version 164737 (0.0008) -[2023-11-28 04:31:21,262][87424] Updated weights for policy 0, policy_version 164747 (0.0012) -[2023-11-28 04:31:21,638][87424] Updated weights for policy 0, policy_version 164757 (0.0011) -[2023-11-28 04:31:21,860][87426] Updated weights for policy 1, policy_version 164360 (0.0011) -[2023-11-28 04:31:22,029][87424] Updated weights for policy 0, policy_version 164767 (0.0011) -[2023-11-28 04:31:22,237][87426] Updated weights for policy 1, policy_version 164370 (0.0012) -[2023-11-28 04:31:22,622][87426] Updated weights for policy 1, policy_version 164380 (0.0012) -[2023-11-28 04:31:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 84262912. Throughput: 0: 2739.8, 1: 2697.2. Samples: 84276624. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:31:23,445][86177] Avg episode reward: [(0, '-500.530'), (1, '-505.490')] -[2023-11-28 04:31:24,492][87424] Updated weights for policy 0, policy_version 164777 (0.0010) -[2023-11-28 04:31:24,644][87426] Updated weights for policy 1, policy_version 164390 (0.0011) -[2023-11-28 04:31:24,875][87424] Updated weights for policy 0, policy_version 164787 (0.0012) -[2023-11-28 04:31:25,018][87426] Updated weights for policy 1, policy_version 164400 (0.0010) -[2023-11-28 04:31:25,259][87424] Updated weights for policy 0, policy_version 164797 (0.0012) -[2023-11-28 04:31:25,394][87426] Updated weights for policy 1, policy_version 164410 (0.0011) -[2023-11-28 04:31:27,345][87424] Updated weights for policy 0, policy_version 164807 (0.0010) -[2023-11-28 04:31:27,422][87426] Updated weights for policy 1, policy_version 164420 (0.0012) -[2023-11-28 04:31:27,729][87424] Updated weights for policy 0, policy_version 164817 (0.0007) -[2023-11-28 04:31:27,806][87426] Updated weights for policy 1, policy_version 164430 (0.0010) -[2023-11-28 04:31:28,118][87424] Updated weights for policy 0, policy_version 164827 (0.0008) -[2023-11-28 04:31:28,174][87426] Updated weights for policy 1, policy_version 164440 (0.0007) -[2023-11-28 04:31:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84287488. Throughput: 0: 2762.0, 1: 2739.6. Samples: 84302608. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:31:28,445][86177] Avg episode reward: [(0, '-500.140'), (1, '-500.130')] -[2023-11-28 04:31:30,067][87424] Updated weights for policy 0, policy_version 164837 (0.0010) -[2023-11-28 04:31:30,451][87424] Updated weights for policy 0, policy_version 164847 (0.0012) -[2023-11-28 04:31:30,723][87426] Updated weights for policy 1, policy_version 164450 (0.0008) -[2023-11-28 04:31:30,830][87424] Updated weights for policy 0, policy_version 164857 (0.0011) -[2023-11-28 04:31:31,107][87426] Updated weights for policy 1, policy_version 164460 (0.0011) -[2023-11-28 04:31:31,489][87426] Updated weights for policy 1, policy_version 164470 (0.0012) -[2023-11-28 04:31:31,861][87426] Updated weights for policy 1, policy_version 164480 (0.0011) -[2023-11-28 04:31:32,898][87424] Updated weights for policy 0, policy_version 164867 (0.0010) -[2023-11-28 04:31:33,272][87424] Updated weights for policy 0, policy_version 164877 (0.0012) -[2023-11-28 04:31:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84312064. Throughput: 0: 2745.7, 1: 2733.9. Samples: 84326540. Policy #0 lag: (min: 2.0, avg: 27.2, max: 39.0) -[2023-11-28 04:31:33,445][86177] Avg episode reward: [(0, '-497.710'), (1, '-498.610')] -[2023-11-28 04:31:33,655][87424] Updated weights for policy 0, policy_version 164887 (0.0011) -[2023-11-28 04:31:33,702][87426] Updated weights for policy 1, policy_version 164490 (0.0009) -[2023-11-28 04:31:34,080][87426] Updated weights for policy 1, policy_version 164500 (0.0010) -[2023-11-28 04:31:34,452][87426] Updated weights for policy 1, policy_version 164510 (0.0012) -[2023-11-28 04:31:36,285][87424] Updated weights for policy 0, policy_version 164897 (0.0011) -[2023-11-28 04:31:36,596][87426] Updated weights for policy 1, policy_version 164520 (0.0011) -[2023-11-28 04:31:36,665][87424] Updated weights for policy 0, policy_version 164907 (0.0012) -[2023-11-28 04:31:36,981][87426] Updated weights for policy 1, policy_version 164530 (0.0011) -[2023-11-28 04:31:37,045][87424] Updated weights for policy 0, policy_version 164917 (0.0011) -[2023-11-28 04:31:37,368][87426] Updated weights for policy 1, policy_version 164540 (0.0012) -[2023-11-28 04:31:37,441][87424] Updated weights for policy 0, policy_version 164927 (0.0011) -[2023-11-28 04:31:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 84344832. Throughput: 0: 2712.3, 1: 2750.5. Samples: 84358680. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:31:38,445][86177] Avg episode reward: [(0, '-497.310'), (1, '-521.310')] -[2023-11-28 04:31:39,458][87426] Updated weights for policy 1, policy_version 164550 (0.0009) -[2023-11-28 04:31:39,837][87426] Updated weights for policy 1, policy_version 164560 (0.0010) -[2023-11-28 04:31:39,874][87424] Updated weights for policy 0, policy_version 164937 (0.0012) -[2023-11-28 04:31:40,217][87426] Updated weights for policy 1, policy_version 164570 (0.0012) -[2023-11-28 04:31:40,257][87424] Updated weights for policy 0, policy_version 164947 (0.0011) -[2023-11-28 04:31:40,637][87424] Updated weights for policy 0, policy_version 164957 (0.0012) -[2023-11-28 04:31:42,665][87426] Updated weights for policy 1, policy_version 164580 (0.0010) -[2023-11-28 04:31:43,051][87426] Updated weights for policy 1, policy_version 164590 (0.0010) -[2023-11-28 04:31:43,148][87424] Updated weights for policy 0, policy_version 164967 (0.0009) -[2023-11-28 04:31:43,423][87426] Updated weights for policy 1, policy_version 164600 (0.0011) -[2023-11-28 04:31:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 84361216. Throughput: 0: 2718.0, 1: 2719.2. Samples: 84382700. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:31:43,445][86177] Avg episode reward: [(0, '-494.870'), (1, '-521.460')] -[2023-11-28 04:31:43,536][87424] Updated weights for policy 0, policy_version 164977 (0.0011) -[2023-11-28 04:31:43,918][87424] Updated weights for policy 0, policy_version 164987 (0.0012) -[2023-11-28 04:31:45,726][87424] Updated weights for policy 0, policy_version 164997 (0.0012) -[2023-11-28 04:31:45,747][87426] Updated weights for policy 1, policy_version 164610 (0.0008) -[2023-11-28 04:31:46,101][87424] Updated weights for policy 0, policy_version 165007 (0.0012) -[2023-11-28 04:31:46,119][87426] Updated weights for policy 1, policy_version 164620 (0.0008) -[2023-11-28 04:31:46,484][87424] Updated weights for policy 0, policy_version 165017 (0.0012) -[2023-11-28 04:31:46,507][87426] Updated weights for policy 1, policy_version 164630 (0.0007) -[2023-11-28 04:31:46,878][87426] Updated weights for policy 1, policy_version 164640 (0.0008) -[2023-11-28 04:31:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84393984. Throughput: 0: 2706.0, 1: 2728.3. Samples: 84406020. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:31:48,445][86177] Avg episode reward: [(0, '-492.240'), (1, '-521.760')] -[2023-11-28 04:31:48,754][87426] Updated weights for policy 1, policy_version 164650 (0.0008) -[2023-11-28 04:31:48,857][87424] Updated weights for policy 0, policy_version 165027 (0.0012) -[2023-11-28 04:31:49,136][87426] Updated weights for policy 1, policy_version 164660 (0.0010) -[2023-11-28 04:31:49,240][87424] Updated weights for policy 0, policy_version 165037 (0.0011) -[2023-11-28 04:31:49,513][87426] Updated weights for policy 1, policy_version 164670 (0.0012) -[2023-11-28 04:31:49,613][87424] Updated weights for policy 0, policy_version 165047 (0.0012) -[2023-11-28 04:31:51,592][87426] Updated weights for policy 1, policy_version 164680 (0.0010) -[2023-11-28 04:31:51,908][87424] Updated weights for policy 0, policy_version 165057 (0.0010) -[2023-11-28 04:31:51,976][87426] Updated weights for policy 1, policy_version 164690 (0.0012) -[2023-11-28 04:31:52,291][87424] Updated weights for policy 0, policy_version 165067 (0.0010) -[2023-11-28 04:31:52,347][87426] Updated weights for policy 1, policy_version 164700 (0.0011) -[2023-11-28 04:31:52,679][87424] Updated weights for policy 0, policy_version 165077 (0.0010) -[2023-11-28 04:31:53,057][87424] Updated weights for policy 0, policy_version 165087 (0.0012) -[2023-11-28 04:31:53,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 84426752. Throughput: 0: 2670.2, 1: 2720.4. Samples: 84438020. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:31:53,445][86177] Avg episode reward: [(0, '-491.950'), (1, '-527.860')] -[2023-11-28 04:31:54,333][87426] Updated weights for policy 1, policy_version 164710 (0.0007) -[2023-11-28 04:31:54,716][87426] Updated weights for policy 1, policy_version 164720 (0.0008) -[2023-11-28 04:31:55,106][87426] Updated weights for policy 1, policy_version 164730 (0.0009) -[2023-11-28 04:31:55,266][87424] Updated weights for policy 0, policy_version 165097 (0.0012) -[2023-11-28 04:31:55,649][87424] Updated weights for policy 0, policy_version 165107 (0.0008) -[2023-11-28 04:31:56,035][87424] Updated weights for policy 0, policy_version 165117 (0.0008) -[2023-11-28 04:31:57,646][87426] Updated weights for policy 1, policy_version 164740 (0.0011) -[2023-11-28 04:31:58,027][87426] Updated weights for policy 1, policy_version 164750 (0.0012) -[2023-11-28 04:31:58,318][87424] Updated weights for policy 0, policy_version 165127 (0.0008) -[2023-11-28 04:31:58,405][87426] Updated weights for policy 1, policy_version 164760 (0.0010) -[2023-11-28 04:31:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 84443136. Throughput: 0: 2662.8, 1: 2737.9. Samples: 84463012. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:31:58,446][86177] Avg episode reward: [(0, '-498.240'), (1, '-503.560')] -[2023-11-28 04:31:58,692][87424] Updated weights for policy 0, policy_version 165137 (0.0009) -[2023-11-28 04:31:59,078][87424] Updated weights for policy 0, policy_version 165147 (0.0010) -[2023-11-28 04:32:00,678][87426] Updated weights for policy 1, policy_version 164770 (0.0011) -[2023-11-28 04:32:01,053][87426] Updated weights for policy 1, policy_version 164780 (0.0012) -[2023-11-28 04:32:01,426][87426] Updated weights for policy 1, policy_version 164790 (0.0012) -[2023-11-28 04:32:01,434][87424] Updated weights for policy 0, policy_version 165157 (0.0012) -[2023-11-28 04:32:01,806][87426] Updated weights for policy 1, policy_version 164800 (0.0010) -[2023-11-28 04:32:01,825][87424] Updated weights for policy 0, policy_version 165167 (0.0011) -[2023-11-28 04:32:02,204][87424] Updated weights for policy 0, policy_version 165177 (0.0009) -[2023-11-28 04:32:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84475904. Throughput: 0: 2671.8, 1: 2743.6. Samples: 84487612. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:32:03,445][86177] Avg episode reward: [(0, '-502.290'), (1, '-515.190')] -[2023-11-28 04:32:03,992][87424] Updated weights for policy 0, policy_version 165187 (0.0009) -[2023-11-28 04:32:04,250][87426] Updated weights for policy 1, policy_version 164810 (0.0010) -[2023-11-28 04:32:04,385][87424] Updated weights for policy 0, policy_version 165197 (0.0011) -[2023-11-28 04:32:04,635][87426] Updated weights for policy 1, policy_version 164820 (0.0012) -[2023-11-28 04:32:04,761][87424] Updated weights for policy 0, policy_version 165207 (0.0011) -[2023-11-28 04:32:05,022][87426] Updated weights for policy 1, policy_version 164830 (0.0012) -[2023-11-28 04:32:06,735][87426] Updated weights for policy 1, policy_version 164840 (0.0011) -[2023-11-28 04:32:06,925][87424] Updated weights for policy 0, policy_version 165217 (0.0011) -[2023-11-28 04:32:07,120][87426] Updated weights for policy 1, policy_version 164850 (0.0011) -[2023-11-28 04:32:07,304][87424] Updated weights for policy 0, policy_version 165227 (0.0012) -[2023-11-28 04:32:07,498][87426] Updated weights for policy 1, policy_version 164860 (0.0008) -[2023-11-28 04:32:07,686][87424] Updated weights for policy 0, policy_version 165237 (0.0011) -[2023-11-28 04:32:08,063][87424] Updated weights for policy 0, policy_version 165247 (0.0012) -[2023-11-28 04:32:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 84508672. Throughput: 0: 2688.5, 1: 2741.8. Samples: 84520984. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:32:08,445][86177] Avg episode reward: [(0, '-504.790'), (1, '-518.490')] -[2023-11-28 04:32:09,427][87426] Updated weights for policy 1, policy_version 164870 (0.0009) -[2023-11-28 04:32:09,811][87426] Updated weights for policy 1, policy_version 164880 (0.0010) -[2023-11-28 04:32:10,188][87426] Updated weights for policy 1, policy_version 164890 (0.0010) -[2023-11-28 04:32:10,492][87424] Updated weights for policy 0, policy_version 165257 (0.0012) -[2023-11-28 04:32:10,878][87424] Updated weights for policy 0, policy_version 165267 (0.0012) -[2023-11-28 04:32:11,261][87424] Updated weights for policy 0, policy_version 165277 (0.0012) -[2023-11-28 04:32:12,576][87426] Updated weights for policy 1, policy_version 164900 (0.0011) -[2023-11-28 04:32:12,951][87426] Updated weights for policy 1, policy_version 164910 (0.0011) -[2023-11-28 04:32:13,331][87426] Updated weights for policy 1, policy_version 164920 (0.0011) -[2023-11-28 04:32:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 84525056. Throughput: 0: 2665.7, 1: 2718.8. Samples: 84544908. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:32:13,445][86177] Avg episode reward: [(0, '-519.630'), (1, '-526.120')] -[2023-11-28 04:32:13,629][87424] Updated weights for policy 0, policy_version 165287 (0.0010) -[2023-11-28 04:32:14,003][87424] Updated weights for policy 0, policy_version 165297 (0.0012) -[2023-11-28 04:32:14,391][87424] Updated weights for policy 0, policy_version 165307 (0.0012) -[2023-11-28 04:32:15,136][87426] Updated weights for policy 1, policy_version 164930 (0.0011) -[2023-11-28 04:32:15,510][87426] Updated weights for policy 1, policy_version 164940 (0.0011) -[2023-11-28 04:32:15,886][87426] Updated weights for policy 1, policy_version 164950 (0.0012) -[2023-11-28 04:32:16,256][87426] Updated weights for policy 1, policy_version 164960 (0.0008) -[2023-11-28 04:32:16,933][87424] Updated weights for policy 0, policy_version 165317 (0.0012) -[2023-11-28 04:32:17,307][87424] Updated weights for policy 0, policy_version 165327 (0.0012) -[2023-11-28 04:32:17,684][87424] Updated weights for policy 0, policy_version 165337 (0.0012) -[2023-11-28 04:32:18,390][87426] Updated weights for policy 1, policy_version 164970 (0.0012) -[2023-11-28 04:32:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84557824. Throughput: 0: 2640.6, 1: 2739.1. Samples: 84568628. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:32:18,445][86177] Avg episode reward: [(0, '-511.740'), (1, '-535.100')] -[2023-11-28 04:32:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000165344_42328064.pth... -[2023-11-28 04:32:18,500][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000162816_41680896.pth -[2023-11-28 04:32:18,507][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000165344_42328064.pth -[2023-11-28 04:32:18,760][87426] Updated weights for policy 1, policy_version 164980 (0.0012) -[2023-11-28 04:32:19,136][87426] Updated weights for policy 1, policy_version 164990 (0.0012) -[2023-11-28 04:32:19,211][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000164992_42237952.pth... -[2023-11-28 04:32:19,259][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000162432_41582592.pth -[2023-11-28 04:32:19,266][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000164992_42237952.pth -[2023-11-28 04:32:19,763][87424] Updated weights for policy 0, policy_version 165347 (0.0011) -[2023-11-28 04:32:20,145][87424] Updated weights for policy 0, policy_version 165357 (0.0011) -[2023-11-28 04:32:20,526][87424] Updated weights for policy 0, policy_version 165367 (0.0009) -[2023-11-28 04:32:21,671][87426] Updated weights for policy 1, policy_version 165000 (0.0011) -[2023-11-28 04:32:22,051][87426] Updated weights for policy 1, policy_version 165010 (0.0012) -[2023-11-28 04:32:22,430][87426] Updated weights for policy 1, policy_version 165020 (0.0011) -[2023-11-28 04:32:22,494][87424] Updated weights for policy 0, policy_version 165377 (0.0012) -[2023-11-28 04:32:22,866][87424] Updated weights for policy 0, policy_version 165387 (0.0012) -[2023-11-28 04:32:23,242][87424] Updated weights for policy 0, policy_version 165397 (0.0012) -[2023-11-28 04:32:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 84582400. Throughput: 0: 2651.4, 1: 2734.3. Samples: 84601036. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:32:23,445][86177] Avg episode reward: [(0, '-511.400'), (1, '-530.370')] -[2023-11-28 04:32:23,625][87424] Updated weights for policy 0, policy_version 165407 (0.0010) -[2023-11-28 04:32:24,434][87426] Updated weights for policy 1, policy_version 165030 (0.0009) -[2023-11-28 04:32:24,821][87426] Updated weights for policy 1, policy_version 165040 (0.0010) -[2023-11-28 04:32:25,198][87426] Updated weights for policy 1, policy_version 165050 (0.0011) -[2023-11-28 04:32:25,714][87424] Updated weights for policy 0, policy_version 165417 (0.0010) -[2023-11-28 04:32:26,089][87424] Updated weights for policy 0, policy_version 165427 (0.0011) -[2023-11-28 04:32:26,474][87424] Updated weights for policy 0, policy_version 165437 (0.0007) -[2023-11-28 04:32:27,468][87426] Updated weights for policy 1, policy_version 165060 (0.0007) -[2023-11-28 04:32:27,842][87426] Updated weights for policy 1, policy_version 165070 (0.0008) -[2023-11-28 04:32:28,225][87426] Updated weights for policy 1, policy_version 165080 (0.0009) -[2023-11-28 04:32:28,403][87424] Updated weights for policy 0, policy_version 165447 (0.0007) -[2023-11-28 04:32:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 84606976. Throughput: 0: 2664.0, 1: 2751.7. Samples: 84626404. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:32:28,445][86177] Avg episode reward: [(0, '-508.470'), (1, '-530.740')] -[2023-11-28 04:32:28,790][87424] Updated weights for policy 0, policy_version 165457 (0.0007) -[2023-11-28 04:32:29,174][87424] Updated weights for policy 0, policy_version 165467 (0.0009) -[2023-11-28 04:32:30,737][87426] Updated weights for policy 1, policy_version 165090 (0.0008) -[2023-11-28 04:32:31,103][87426] Updated weights for policy 1, policy_version 165100 (0.0011) -[2023-11-28 04:32:31,487][87426] Updated weights for policy 1, policy_version 165110 (0.0007) -[2023-11-28 04:32:31,644][87424] Updated weights for policy 0, policy_version 165477 (0.0009) -[2023-11-28 04:32:31,863][87426] Updated weights for policy 1, policy_version 165120 (0.0009) -[2023-11-28 04:32:32,023][87424] Updated weights for policy 0, policy_version 165487 (0.0010) -[2023-11-28 04:32:32,406][87424] Updated weights for policy 0, policy_version 165497 (0.0011) -[2023-11-28 04:32:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84639744. Throughput: 0: 2701.4, 1: 2744.7. Samples: 84651096. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:32:33,445][86177] Avg episode reward: [(0, '-499.930'), (1, '-535.660')] -[2023-11-28 04:32:34,325][87424] Updated weights for policy 0, policy_version 165507 (0.0011) -[2023-11-28 04:32:34,339][87426] Updated weights for policy 1, policy_version 165130 (0.0011) -[2023-11-28 04:32:34,714][87424] Updated weights for policy 0, policy_version 165517 (0.0011) -[2023-11-28 04:32:34,723][87426] Updated weights for policy 1, policy_version 165140 (0.0009) -[2023-11-28 04:32:35,100][87424] Updated weights for policy 0, policy_version 165527 (0.0010) -[2023-11-28 04:32:35,104][87426] Updated weights for policy 1, policy_version 165150 (0.0008) -[2023-11-28 04:32:36,717][87424] Updated weights for policy 0, policy_version 165537 (0.0012) -[2023-11-28 04:32:37,081][87426] Updated weights for policy 1, policy_version 165160 (0.0010) -[2023-11-28 04:32:37,099][87424] Updated weights for policy 0, policy_version 165547 (0.0012) -[2023-11-28 04:32:37,466][87426] Updated weights for policy 1, policy_version 165170 (0.0010) -[2023-11-28 04:32:37,485][87424] Updated weights for policy 0, policy_version 165557 (0.0012) -[2023-11-28 04:32:37,836][87426] Updated weights for policy 1, policy_version 165180 (0.0011) -[2023-11-28 04:32:37,866][87424] Updated weights for policy 0, policy_version 165567 (0.0011) -[2023-11-28 04:32:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84672512. Throughput: 0: 2738.4, 1: 2707.7. Samples: 84683096. Policy #0 lag: (min: 27.0, avg: 46.3, max: 59.0) -[2023-11-28 04:32:38,445][86177] Avg episode reward: [(0, '-498.700'), (1, '-533.110')] -[2023-11-28 04:32:39,984][87424] Updated weights for policy 0, policy_version 165577 (0.0013) -[2023-11-28 04:32:40,358][87424] Updated weights for policy 0, policy_version 165587 (0.0010) -[2023-11-28 04:32:40,382][87426] Updated weights for policy 1, policy_version 165190 (0.0011) -[2023-11-28 04:32:40,743][87424] Updated weights for policy 0, policy_version 165597 (0.0012) -[2023-11-28 04:32:40,758][87426] Updated weights for policy 1, policy_version 165200 (0.0009) -[2023-11-28 04:32:41,140][87426] Updated weights for policy 1, policy_version 165210 (0.0011) -[2023-11-28 04:32:42,889][87424] Updated weights for policy 0, policy_version 165607 (0.0012) -[2023-11-28 04:32:43,110][87426] Updated weights for policy 1, policy_version 165220 (0.0010) -[2023-11-28 04:32:43,269][87424] Updated weights for policy 0, policy_version 165617 (0.0009) -[2023-11-28 04:32:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 84688896. Throughput: 0: 2748.2, 1: 2700.2. Samples: 84708188. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:32:43,445][86177] Avg episode reward: [(0, '-502.580'), (1, '-525.050')] -[2023-11-28 04:32:43,489][87426] Updated weights for policy 1, policy_version 165230 (0.0007) -[2023-11-28 04:32:43,662][87424] Updated weights for policy 0, policy_version 165627 (0.0011) -[2023-11-28 04:32:43,874][87426] Updated weights for policy 1, policy_version 165240 (0.0011) -[2023-11-28 04:32:45,687][87424] Updated weights for policy 0, policy_version 165637 (0.0011) -[2023-11-28 04:32:46,073][87424] Updated weights for policy 0, policy_version 165647 (0.0012) -[2023-11-28 04:32:46,260][87426] Updated weights for policy 1, policy_version 165250 (0.0009) -[2023-11-28 04:32:46,448][87424] Updated weights for policy 0, policy_version 165657 (0.0011) -[2023-11-28 04:32:46,639][87426] Updated weights for policy 1, policy_version 165260 (0.0010) -[2023-11-28 04:32:47,023][87426] Updated weights for policy 1, policy_version 165270 (0.0007) -[2023-11-28 04:32:47,404][87426] Updated weights for policy 1, policy_version 165280 (0.0007) -[2023-11-28 04:32:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84721664. Throughput: 0: 2753.5, 1: 2688.3. Samples: 84732492. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:32:48,445][86177] Avg episode reward: [(0, '-501.130'), (1, '-533.390')] -[2023-11-28 04:32:48,721][87424] Updated weights for policy 0, policy_version 165667 (0.0012) -[2023-11-28 04:32:49,091][87424] Updated weights for policy 0, policy_version 165677 (0.0011) -[2023-11-28 04:32:49,476][87424] Updated weights for policy 0, policy_version 165687 (0.0011) -[2023-11-28 04:32:49,556][87426] Updated weights for policy 1, policy_version 165290 (0.0011) -[2023-11-28 04:32:49,936][87426] Updated weights for policy 1, policy_version 165300 (0.0011) -[2023-11-28 04:32:50,310][87426] Updated weights for policy 1, policy_version 165310 (0.0012) -[2023-11-28 04:32:51,962][87424] Updated weights for policy 0, policy_version 165697 (0.0010) -[2023-11-28 04:32:52,341][87424] Updated weights for policy 0, policy_version 165707 (0.0010) -[2023-11-28 04:32:52,691][87426] Updated weights for policy 1, policy_version 165320 (0.0009) -[2023-11-28 04:32:52,733][87424] Updated weights for policy 0, policy_version 165717 (0.0007) -[2023-11-28 04:32:53,077][87426] Updated weights for policy 1, policy_version 165330 (0.0008) -[2023-11-28 04:32:53,110][87424] Updated weights for policy 0, policy_version 165727 (0.0011) -[2023-11-28 04:32:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 84746240. Throughput: 0: 2742.8, 1: 2681.4. Samples: 84765076. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:32:53,445][86177] Avg episode reward: [(0, '-498.000'), (1, '-516.820')] -[2023-11-28 04:32:53,454][87426] Updated weights for policy 1, policy_version 165340 (0.0009) -[2023-11-28 04:32:55,287][87424] Updated weights for policy 0, policy_version 165737 (0.0011) -[2023-11-28 04:32:55,639][87426] Updated weights for policy 1, policy_version 165350 (0.0009) -[2023-11-28 04:32:55,672][87424] Updated weights for policy 0, policy_version 165747 (0.0011) -[2023-11-28 04:32:56,014][87426] Updated weights for policy 1, policy_version 165360 (0.0007) -[2023-11-28 04:32:56,057][87424] Updated weights for policy 0, policy_version 165757 (0.0007) -[2023-11-28 04:32:56,400][87426] Updated weights for policy 1, policy_version 165370 (0.0007) -[2023-11-28 04:32:57,840][87424] Updated weights for policy 0, policy_version 165767 (0.0010) -[2023-11-28 04:32:58,225][87424] Updated weights for policy 0, policy_version 165777 (0.0011) -[2023-11-28 04:32:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84770816. Throughput: 0: 2753.5, 1: 2661.0. Samples: 84788560. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:32:58,445][86177] Avg episode reward: [(0, '-496.240'), (1, '-512.080')] -[2023-11-28 04:32:58,607][87424] Updated weights for policy 0, policy_version 165787 (0.0008) -[2023-11-28 04:32:58,904][87426] Updated weights for policy 1, policy_version 165380 (0.0008) -[2023-11-28 04:32:59,285][87426] Updated weights for policy 1, policy_version 165390 (0.0007) -[2023-11-28 04:32:59,668][87426] Updated weights for policy 1, policy_version 165400 (0.0008) -[2023-11-28 04:33:00,812][87424] Updated weights for policy 0, policy_version 165797 (0.0008) -[2023-11-28 04:33:01,194][87424] Updated weights for policy 0, policy_version 165807 (0.0008) -[2023-11-28 04:33:01,569][87424] Updated weights for policy 0, policy_version 165817 (0.0008) -[2023-11-28 04:33:01,591][87426] Updated weights for policy 1, policy_version 165410 (0.0011) -[2023-11-28 04:33:01,970][87426] Updated weights for policy 1, policy_version 165420 (0.0009) -[2023-11-28 04:33:02,352][87426] Updated weights for policy 1, policy_version 165430 (0.0010) -[2023-11-28 04:33:02,730][87426] Updated weights for policy 1, policy_version 165440 (0.0009) -[2023-11-28 04:33:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84803584. Throughput: 0: 2797.6, 1: 2649.2. Samples: 84813736. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:33:03,446][86177] Avg episode reward: [(0, '-489.750'), (1, '-526.890')] -[2023-11-28 04:33:04,030][87424] Updated weights for policy 0, policy_version 165827 (0.0008) -[2023-11-28 04:33:04,411][87424] Updated weights for policy 0, policy_version 165837 (0.0008) -[2023-11-28 04:33:04,791][87424] Updated weights for policy 0, policy_version 165847 (0.0010) -[2023-11-28 04:33:04,980][87426] Updated weights for policy 1, policy_version 165450 (0.0010) -[2023-11-28 04:33:05,365][87426] Updated weights for policy 1, policy_version 165460 (0.0007) -[2023-11-28 04:33:05,738][87426] Updated weights for policy 1, policy_version 165470 (0.0008) -[2023-11-28 04:33:06,491][87424] Updated weights for policy 0, policy_version 165857 (0.0011) -[2023-11-28 04:33:06,884][87424] Updated weights for policy 0, policy_version 165867 (0.0012) -[2023-11-28 04:33:07,255][87424] Updated weights for policy 0, policy_version 165877 (0.0012) -[2023-11-28 04:33:07,641][87424] Updated weights for policy 0, policy_version 165887 (0.0012) -[2023-11-28 04:33:08,283][87426] Updated weights for policy 1, policy_version 165480 (0.0011) -[2023-11-28 04:33:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 84828160. Throughput: 0: 2829.2, 1: 2625.5. Samples: 84846496. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:33:08,445][86177] Avg episode reward: [(0, '-496.780'), (1, '-530.960')] -[2023-11-28 04:33:08,651][87426] Updated weights for policy 1, policy_version 165490 (0.0012) -[2023-11-28 04:33:09,026][87426] Updated weights for policy 1, policy_version 165500 (0.0012) -[2023-11-28 04:33:09,521][87424] Updated weights for policy 0, policy_version 165897 (0.0012) -[2023-11-28 04:33:09,899][87424] Updated weights for policy 0, policy_version 165907 (0.0011) -[2023-11-28 04:33:10,280][87424] Updated weights for policy 0, policy_version 165917 (0.0012) -[2023-11-28 04:33:11,578][87426] Updated weights for policy 1, policy_version 165510 (0.0010) -[2023-11-28 04:33:11,977][87426] Updated weights for policy 1, policy_version 165520 (0.0010) -[2023-11-28 04:33:12,354][87426] Updated weights for policy 1, policy_version 165530 (0.0012) -[2023-11-28 04:33:12,660][87424] Updated weights for policy 0, policy_version 165927 (0.0008) -[2023-11-28 04:33:13,043][87424] Updated weights for policy 0, policy_version 165937 (0.0008) -[2023-11-28 04:33:13,434][87424] Updated weights for policy 0, policy_version 165947 (0.0007) -[2023-11-28 04:33:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84852736. Throughput: 0: 2817.5, 1: 2585.2. Samples: 84869528. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:33:13,445][86177] Avg episode reward: [(0, '-500.340'), (1, '-556.100')] -[2023-11-28 04:33:14,494][87426] Updated weights for policy 1, policy_version 165540 (0.0012) -[2023-11-28 04:33:14,886][87426] Updated weights for policy 1, policy_version 165550 (0.0009) -[2023-11-28 04:33:15,270][87426] Updated weights for policy 1, policy_version 165560 (0.0009) -[2023-11-28 04:33:15,946][87424] Updated weights for policy 0, policy_version 165957 (0.0008) -[2023-11-28 04:33:16,330][87424] Updated weights for policy 0, policy_version 165967 (0.0008) -[2023-11-28 04:33:16,712][87424] Updated weights for policy 0, policy_version 165977 (0.0007) -[2023-11-28 04:33:17,773][87426] Updated weights for policy 1, policy_version 165570 (0.0010) -[2023-11-28 04:33:18,142][87426] Updated weights for policy 1, policy_version 165580 (0.0012) -[2023-11-28 04:33:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 84877312. Throughput: 0: 2795.8, 1: 2596.3. Samples: 84893740. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:33:18,445][86177] Avg episode reward: [(0, '-508.660'), (1, '-564.720')] -[2023-11-28 04:33:18,532][87426] Updated weights for policy 1, policy_version 165590 (0.0012) -[2023-11-28 04:33:18,778][87424] Updated weights for policy 0, policy_version 165987 (0.0009) -[2023-11-28 04:33:18,907][87426] Updated weights for policy 1, policy_version 165600 (0.0010) -[2023-11-28 04:33:19,157][87424] Updated weights for policy 0, policy_version 165997 (0.0008) -[2023-11-28 04:33:19,537][87424] Updated weights for policy 0, policy_version 166007 (0.0007) -[2023-11-28 04:33:21,130][87426] Updated weights for policy 1, policy_version 165610 (0.0012) -[2023-11-28 04:33:21,514][87426] Updated weights for policy 1, policy_version 165620 (0.0011) -[2023-11-28 04:33:21,901][87426] Updated weights for policy 1, policy_version 165630 (0.0010) -[2023-11-28 04:33:21,910][87424] Updated weights for policy 0, policy_version 166017 (0.0009) -[2023-11-28 04:33:22,292][87424] Updated weights for policy 0, policy_version 166027 (0.0010) -[2023-11-28 04:33:22,680][87424] Updated weights for policy 0, policy_version 166037 (0.0012) -[2023-11-28 04:33:23,061][87424] Updated weights for policy 0, policy_version 166047 (0.0011) -[2023-11-28 04:33:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84910080. Throughput: 0: 2782.3, 1: 2615.2. Samples: 84925984. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:33:23,445][86177] Avg episode reward: [(0, '-505.900'), (1, '-587.540')] -[2023-11-28 04:33:24,405][87426] Updated weights for policy 1, policy_version 165640 (0.0010) -[2023-11-28 04:33:24,789][87426] Updated weights for policy 1, policy_version 165650 (0.0009) -[2023-11-28 04:33:24,843][87424] Updated weights for policy 0, policy_version 166057 (0.0012) -[2023-11-28 04:33:25,159][87426] Updated weights for policy 1, policy_version 165660 (0.0007) -[2023-11-28 04:33:25,226][87424] Updated weights for policy 0, policy_version 166067 (0.0010) -[2023-11-28 04:33:25,612][87424] Updated weights for policy 0, policy_version 166077 (0.0008) -[2023-11-28 04:33:27,336][87426] Updated weights for policy 1, policy_version 165670 (0.0010) -[2023-11-28 04:33:27,705][87426] Updated weights for policy 1, policy_version 165680 (0.0011) -[2023-11-28 04:33:27,761][87424] Updated weights for policy 0, policy_version 166087 (0.0008) -[2023-11-28 04:33:28,087][87426] Updated weights for policy 1, policy_version 165690 (0.0012) -[2023-11-28 04:33:28,141][87424] Updated weights for policy 0, policy_version 166097 (0.0011) -[2023-11-28 04:33:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 84934656. Throughput: 0: 2769.0, 1: 2607.0. Samples: 84950108. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:33:28,446][86177] Avg episode reward: [(0, '-503.890'), (1, '-568.980')] -[2023-11-28 04:33:28,531][87424] Updated weights for policy 0, policy_version 166107 (0.0007) -[2023-11-28 04:33:30,385][87424] Updated weights for policy 0, policy_version 166117 (0.0008) -[2023-11-28 04:33:30,444][87426] Updated weights for policy 1, policy_version 165700 (0.0012) -[2023-11-28 04:33:30,762][87424] Updated weights for policy 0, policy_version 166127 (0.0010) -[2023-11-28 04:33:30,823][87426] Updated weights for policy 1, policy_version 165710 (0.0011) -[2023-11-28 04:33:31,146][87424] Updated weights for policy 0, policy_version 166137 (0.0012) -[2023-11-28 04:33:31,206][87426] Updated weights for policy 1, policy_version 165720 (0.0010) -[2023-11-28 04:33:33,341][87424] Updated weights for policy 0, policy_version 166147 (0.0011) -[2023-11-28 04:33:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 84959232. Throughput: 0: 2758.4, 1: 2620.4. Samples: 84974536. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:33:33,445][86177] Avg episode reward: [(0, '-501.620'), (1, '-582.140')] -[2023-11-28 04:33:33,639][87426] Updated weights for policy 1, policy_version 165730 (0.0007) -[2023-11-28 04:33:33,718][87424] Updated weights for policy 0, policy_version 166157 (0.0007) -[2023-11-28 04:33:34,008][87426] Updated weights for policy 1, policy_version 165740 (0.0008) -[2023-11-28 04:33:34,124][87424] Updated weights for policy 0, policy_version 166167 (0.0008) -[2023-11-28 04:33:34,392][87426] Updated weights for policy 1, policy_version 165750 (0.0007) -[2023-11-28 04:33:34,786][87426] Updated weights for policy 1, policy_version 165760 (0.0009) -[2023-11-28 04:33:36,568][87424] Updated weights for policy 0, policy_version 166177 (0.0008) -[2023-11-28 04:33:36,582][87426] Updated weights for policy 1, policy_version 165770 (0.0012) -[2023-11-28 04:33:36,945][87424] Updated weights for policy 0, policy_version 166187 (0.0011) -[2023-11-28 04:33:36,960][87426] Updated weights for policy 1, policy_version 165780 (0.0011) -[2023-11-28 04:33:37,330][87424] Updated weights for policy 0, policy_version 166197 (0.0012) -[2023-11-28 04:33:37,341][87426] Updated weights for policy 1, policy_version 165790 (0.0011) -[2023-11-28 04:33:37,720][87424] Updated weights for policy 0, policy_version 166207 (0.0012) -[2023-11-28 04:33:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 84992000. Throughput: 0: 2748.0, 1: 2614.5. Samples: 85006388. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:33:38,445][86177] Avg episode reward: [(0, '-497.110'), (1, '-573.110')] -[2023-11-28 04:33:39,376][87426] Updated weights for policy 1, policy_version 165800 (0.0010) -[2023-11-28 04:33:39,741][87426] Updated weights for policy 1, policy_version 165810 (0.0008) -[2023-11-28 04:33:39,778][87424] Updated weights for policy 0, policy_version 166217 (0.0012) -[2023-11-28 04:33:40,118][87426] Updated weights for policy 1, policy_version 165820 (0.0009) -[2023-11-28 04:33:40,159][87424] Updated weights for policy 0, policy_version 166227 (0.0009) -[2023-11-28 04:33:40,544][87424] Updated weights for policy 0, policy_version 166237 (0.0009) -[2023-11-28 04:33:42,589][87426] Updated weights for policy 1, policy_version 165830 (0.0010) -[2023-11-28 04:33:42,959][87426] Updated weights for policy 1, policy_version 165840 (0.0011) -[2023-11-28 04:33:43,037][87424] Updated weights for policy 0, policy_version 166247 (0.0010) -[2023-11-28 04:33:43,346][87426] Updated weights for policy 1, policy_version 165850 (0.0010) -[2023-11-28 04:33:43,414][87424] Updated weights for policy 0, policy_version 166257 (0.0010) -[2023-11-28 04:33:43,445][86177] Fps is (10 sec: 4914.6, 60 sec: 5324.7, 300 sec: 5415.0). Total num frames: 85008384. Throughput: 0: 2748.7, 1: 2628.7. Samples: 85030552. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 04:33:43,446][86177] Avg episode reward: [(0, '-497.550'), (1, '-552.660')] -[2023-11-28 04:33:43,802][87424] Updated weights for policy 0, policy_version 166267 (0.0008) -[2023-11-28 04:33:45,593][87426] Updated weights for policy 1, policy_version 165860 (0.0010) -[2023-11-28 04:33:45,976][87426] Updated weights for policy 1, policy_version 165870 (0.0007) -[2023-11-28 04:33:46,325][87424] Updated weights for policy 0, policy_version 166277 (0.0008) -[2023-11-28 04:33:46,356][87426] Updated weights for policy 1, policy_version 165880 (0.0007) -[2023-11-28 04:33:46,699][87424] Updated weights for policy 0, policy_version 166287 (0.0008) -[2023-11-28 04:33:47,082][87424] Updated weights for policy 0, policy_version 166297 (0.0012) -[2023-11-28 04:33:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 85041152. Throughput: 0: 2708.4, 1: 2634.7. Samples: 85054172. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:33:48,445][86177] Avg episode reward: [(0, '-515.480'), (1, '-566.450')] -[2023-11-28 04:33:48,506][87426] Updated weights for policy 1, policy_version 165890 (0.0008) -[2023-11-28 04:33:48,821][87424] Updated weights for policy 0, policy_version 166307 (0.0010) -[2023-11-28 04:33:48,874][87426] Updated weights for policy 1, policy_version 165900 (0.0012) -[2023-11-28 04:33:49,200][87424] Updated weights for policy 0, policy_version 166317 (0.0011) -[2023-11-28 04:33:49,259][87426] Updated weights for policy 1, policy_version 165910 (0.0011) -[2023-11-28 04:33:49,591][87424] Updated weights for policy 0, policy_version 166327 (0.0012) -[2023-11-28 04:33:49,630][87426] Updated weights for policy 1, policy_version 165920 (0.0011) -[2023-11-28 04:33:51,432][87426] Updated weights for policy 1, policy_version 165930 (0.0011) -[2023-11-28 04:33:51,771][87424] Updated weights for policy 0, policy_version 166337 (0.0010) -[2023-11-28 04:33:51,814][87426] Updated weights for policy 1, policy_version 165940 (0.0009) -[2023-11-28 04:33:52,153][87424] Updated weights for policy 0, policy_version 166347 (0.0011) -[2023-11-28 04:33:52,194][87426] Updated weights for policy 1, policy_version 165950 (0.0009) -[2023-11-28 04:33:52,525][87424] Updated weights for policy 0, policy_version 166357 (0.0008) -[2023-11-28 04:33:52,909][87424] Updated weights for policy 0, policy_version 166367 (0.0008) -[2023-11-28 04:33:53,444][86177] Fps is (10 sec: 6554.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85073920. Throughput: 0: 2675.6, 1: 2647.8. Samples: 85086048. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:33:53,445][86177] Avg episode reward: [(0, '-513.300'), (1, '-532.670')] -[2023-11-28 04:33:54,692][87426] Updated weights for policy 1, policy_version 165960 (0.0009) -[2023-11-28 04:33:54,980][87424] Updated weights for policy 0, policy_version 166377 (0.0015) -[2023-11-28 04:33:55,064][87426] Updated weights for policy 1, policy_version 165970 (0.0008) -[2023-11-28 04:33:55,366][87424] Updated weights for policy 0, policy_version 166387 (0.0012) -[2023-11-28 04:33:55,454][87426] Updated weights for policy 1, policy_version 165980 (0.0011) -[2023-11-28 04:33:55,760][87424] Updated weights for policy 0, policy_version 166397 (0.0011) -[2023-11-28 04:33:57,582][87426] Updated weights for policy 1, policy_version 165990 (0.0008) -[2023-11-28 04:33:57,963][87426] Updated weights for policy 1, policy_version 166000 (0.0007) -[2023-11-28 04:33:58,242][87424] Updated weights for policy 0, policy_version 166407 (0.0011) -[2023-11-28 04:33:58,351][87426] Updated weights for policy 1, policy_version 166010 (0.0007) -[2023-11-28 04:33:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 85090304. Throughput: 0: 2674.0, 1: 2701.3. Samples: 85111420. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:33:58,445][86177] Avg episode reward: [(0, '-515.500'), (1, '-508.470')] -[2023-11-28 04:33:58,630][87424] Updated weights for policy 0, policy_version 166417 (0.0007) -[2023-11-28 04:33:59,006][87424] Updated weights for policy 0, policy_version 166427 (0.0009) -[2023-11-28 04:34:00,766][87426] Updated weights for policy 1, policy_version 166020 (0.0008) -[2023-11-28 04:34:00,784][87424] Updated weights for policy 0, policy_version 166437 (0.0011) -[2023-11-28 04:34:01,150][87426] Updated weights for policy 1, policy_version 166030 (0.0009) -[2023-11-28 04:34:01,169][87424] Updated weights for policy 0, policy_version 166447 (0.0012) -[2023-11-28 04:34:01,523][87426] Updated weights for policy 1, policy_version 166040 (0.0009) -[2023-11-28 04:34:01,548][87424] Updated weights for policy 0, policy_version 166457 (0.0012) -[2023-11-28 04:34:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 85123072. Throughput: 0: 2672.9, 1: 2695.3. Samples: 85135308. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:03,445][86177] Avg episode reward: [(0, '-514.020'), (1, '-522.710')] -[2023-11-28 04:34:03,641][87424] Updated weights for policy 0, policy_version 166467 (0.0012) -[2023-11-28 04:34:03,681][87426] Updated weights for policy 1, policy_version 166050 (0.0010) -[2023-11-28 04:34:04,035][87424] Updated weights for policy 0, policy_version 166477 (0.0009) -[2023-11-28 04:34:04,064][87426] Updated weights for policy 1, policy_version 166060 (0.0011) -[2023-11-28 04:34:04,421][87424] Updated weights for policy 0, policy_version 166487 (0.0010) -[2023-11-28 04:34:04,439][87426] Updated weights for policy 1, policy_version 166070 (0.0011) -[2023-11-28 04:34:04,815][87426] Updated weights for policy 1, policy_version 166080 (0.0011) -[2023-11-28 04:34:06,501][87424] Updated weights for policy 0, policy_version 166497 (0.0012) -[2023-11-28 04:34:06,809][87426] Updated weights for policy 1, policy_version 166090 (0.0012) -[2023-11-28 04:34:06,887][87424] Updated weights for policy 0, policy_version 166507 (0.0010) -[2023-11-28 04:34:07,190][87426] Updated weights for policy 1, policy_version 166100 (0.0012) -[2023-11-28 04:34:07,260][87424] Updated weights for policy 0, policy_version 166517 (0.0010) -[2023-11-28 04:34:07,567][87426] Updated weights for policy 1, policy_version 166110 (0.0012) -[2023-11-28 04:34:07,645][87424] Updated weights for policy 0, policy_version 166527 (0.0012) -[2023-11-28 04:34:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85155840. Throughput: 0: 2702.3, 1: 2700.9. Samples: 85169128. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:08,445][86177] Avg episode reward: [(0, '-515.090'), (1, '-522.250')] -[2023-11-28 04:34:09,350][87426] Updated weights for policy 1, policy_version 166120 (0.0010) -[2023-11-28 04:34:09,730][87426] Updated weights for policy 1, policy_version 166130 (0.0008) -[2023-11-28 04:34:09,991][87424] Updated weights for policy 0, policy_version 166537 (0.0012) -[2023-11-28 04:34:10,109][87426] Updated weights for policy 1, policy_version 166140 (0.0011) -[2023-11-28 04:34:10,382][87424] Updated weights for policy 0, policy_version 166547 (0.0010) -[2023-11-28 04:34:10,752][87424] Updated weights for policy 0, policy_version 166557 (0.0009) -[2023-11-28 04:34:12,612][87426] Updated weights for policy 1, policy_version 166150 (0.0011) -[2023-11-28 04:34:12,985][87426] Updated weights for policy 1, policy_version 166160 (0.0011) -[2023-11-28 04:34:12,993][87424] Updated weights for policy 0, policy_version 166567 (0.0011) -[2023-11-28 04:34:13,366][87426] Updated weights for policy 1, policy_version 166170 (0.0012) -[2023-11-28 04:34:13,377][87424] Updated weights for policy 0, policy_version 166577 (0.0010) -[2023-11-28 04:34:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 85172224. Throughput: 0: 2716.7, 1: 2704.9. Samples: 85194080. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:13,445][86177] Avg episode reward: [(0, '-512.950'), (1, '-520.360')] -[2023-11-28 04:34:13,765][87424] Updated weights for policy 0, policy_version 166587 (0.0009) -[2023-11-28 04:34:15,336][87426] Updated weights for policy 1, policy_version 166180 (0.0011) -[2023-11-28 04:34:15,715][87426] Updated weights for policy 1, policy_version 166190 (0.0012) -[2023-11-28 04:34:15,849][87424] Updated weights for policy 0, policy_version 166597 (0.0008) -[2023-11-28 04:34:16,095][87426] Updated weights for policy 1, policy_version 166200 (0.0009) -[2023-11-28 04:34:16,227][87424] Updated weights for policy 0, policy_version 166607 (0.0010) -[2023-11-28 04:34:16,618][87424] Updated weights for policy 0, policy_version 166617 (0.0008) -[2023-11-28 04:34:17,779][87426] Updated weights for policy 1, policy_version 166210 (0.0007) -[2023-11-28 04:34:18,158][87426] Updated weights for policy 1, policy_version 166220 (0.0007) -[2023-11-28 04:34:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 85204992. Throughput: 0: 2703.7, 1: 2709.6. Samples: 85218136. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:18,445][86177] Avg episode reward: [(0, '-511.930'), (1, '-530.620')] -[2023-11-28 04:34:18,480][87424] Updated weights for policy 0, policy_version 166627 (0.0009) -[2023-11-28 04:34:18,540][87426] Updated weights for policy 1, policy_version 166230 (0.0007) -[2023-11-28 04:34:18,862][87424] Updated weights for policy 0, policy_version 166637 (0.0012) -[2023-11-28 04:34:18,914][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000166240_42557440.pth... -[2023-11-28 04:34:18,917][87426] Updated weights for policy 1, policy_version 166240 (0.0011) -[2023-11-28 04:34:18,960][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000163712_41910272.pth -[2023-11-28 04:34:19,247][87424] Updated weights for policy 0, policy_version 166647 (0.0011) -[2023-11-28 04:34:19,589][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000166656_42663936.pth... -[2023-11-28 04:34:19,636][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000164096_42008576.pth -[2023-11-28 04:34:21,289][87426] Updated weights for policy 1, policy_version 166250 (0.0011) -[2023-11-28 04:34:21,331][87424] Updated weights for policy 0, policy_version 166657 (0.0011) -[2023-11-28 04:34:21,669][87426] Updated weights for policy 1, policy_version 166260 (0.0011) -[2023-11-28 04:34:21,710][87424] Updated weights for policy 0, policy_version 166667 (0.0009) -[2023-11-28 04:34:22,048][87426] Updated weights for policy 1, policy_version 166270 (0.0012) -[2023-11-28 04:34:22,104][87424] Updated weights for policy 0, policy_version 166677 (0.0011) -[2023-11-28 04:34:22,477][87424] Updated weights for policy 0, policy_version 166687 (0.0011) -[2023-11-28 04:34:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85237760. Throughput: 0: 2704.2, 1: 2731.6. Samples: 85250996. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:23,445][86177] Avg episode reward: [(0, '-498.790'), (1, '-569.530')] -[2023-11-28 04:34:24,307][87426] Updated weights for policy 1, policy_version 166280 (0.0012) -[2023-11-28 04:34:24,681][87426] Updated weights for policy 1, policy_version 166290 (0.0011) -[2023-11-28 04:34:24,905][87424] Updated weights for policy 0, policy_version 166697 (0.0011) -[2023-11-28 04:34:25,062][87426] Updated weights for policy 1, policy_version 166300 (0.0010) -[2023-11-28 04:34:25,294][87424] Updated weights for policy 0, policy_version 166707 (0.0010) -[2023-11-28 04:34:25,666][87424] Updated weights for policy 0, policy_version 166717 (0.0007) -[2023-11-28 04:34:27,425][87426] Updated weights for policy 1, policy_version 166310 (0.0008) -[2023-11-28 04:34:27,537][87424] Updated weights for policy 0, policy_version 166727 (0.0009) -[2023-11-28 04:34:27,803][87426] Updated weights for policy 1, policy_version 166320 (0.0007) -[2023-11-28 04:34:27,924][87424] Updated weights for policy 0, policy_version 166737 (0.0007) -[2023-11-28 04:34:28,189][87426] Updated weights for policy 1, policy_version 166330 (0.0007) -[2023-11-28 04:34:28,305][87424] Updated weights for policy 0, policy_version 166747 (0.0008) -[2023-11-28 04:34:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 85262336. Throughput: 0: 2727.9, 1: 2730.8. Samples: 85276188. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:28,445][86177] Avg episode reward: [(0, '-497.540'), (1, '-578.070')] -[2023-11-28 04:34:30,522][87426] Updated weights for policy 1, policy_version 166340 (0.0007) -[2023-11-28 04:34:30,682][87424] Updated weights for policy 0, policy_version 166757 (0.0010) -[2023-11-28 04:34:30,900][87426] Updated weights for policy 1, policy_version 166350 (0.0010) -[2023-11-28 04:34:31,064][87424] Updated weights for policy 0, policy_version 166767 (0.0010) -[2023-11-28 04:34:31,269][87426] Updated weights for policy 1, policy_version 166360 (0.0012) -[2023-11-28 04:34:31,446][87424] Updated weights for policy 0, policy_version 166777 (0.0011) -[2023-11-28 04:34:33,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 85286912. Throughput: 0: 2747.2, 1: 2732.4. Samples: 85300756. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:33,446][86177] Avg episode reward: [(0, '-499.760'), (1, '-595.920')] -[2023-11-28 04:34:33,774][87426] Updated weights for policy 1, policy_version 166370 (0.0011) -[2023-11-28 04:34:34,056][87424] Updated weights for policy 0, policy_version 166787 (0.0012) -[2023-11-28 04:34:34,158][87426] Updated weights for policy 1, policy_version 166380 (0.0012) -[2023-11-28 04:34:34,440][87424] Updated weights for policy 0, policy_version 166797 (0.0009) -[2023-11-28 04:34:34,537][87426] Updated weights for policy 1, policy_version 166390 (0.0010) -[2023-11-28 04:34:34,819][87424] Updated weights for policy 0, policy_version 166807 (0.0008) -[2023-11-28 04:34:34,917][87426] Updated weights for policy 1, policy_version 166400 (0.0011) -[2023-11-28 04:34:36,670][87424] Updated weights for policy 0, policy_version 166817 (0.0008) -[2023-11-28 04:34:37,050][87424] Updated weights for policy 0, policy_version 166827 (0.0012) -[2023-11-28 04:34:37,357][87426] Updated weights for policy 1, policy_version 166410 (0.0008) -[2023-11-28 04:34:37,433][87424] Updated weights for policy 0, policy_version 166837 (0.0011) -[2023-11-28 04:34:37,737][87426] Updated weights for policy 1, policy_version 166420 (0.0007) -[2023-11-28 04:34:37,817][87424] Updated weights for policy 0, policy_version 166847 (0.0011) -[2023-11-28 04:34:38,125][87426] Updated weights for policy 1, policy_version 166430 (0.0008) -[2023-11-28 04:34:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 85319680. Throughput: 0: 2744.8, 1: 2742.1. Samples: 85332960. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:38,445][86177] Avg episode reward: [(0, '-500.380'), (1, '-611.630')] -[2023-11-28 04:34:39,698][87424] Updated weights for policy 0, policy_version 166857 (0.0011) -[2023-11-28 04:34:39,896][87426] Updated weights for policy 1, policy_version 166440 (0.0011) -[2023-11-28 04:34:40,078][87424] Updated weights for policy 0, policy_version 166867 (0.0011) -[2023-11-28 04:34:40,274][87426] Updated weights for policy 1, policy_version 166450 (0.0011) -[2023-11-28 04:34:40,461][87424] Updated weights for policy 0, policy_version 166877 (0.0010) -[2023-11-28 04:34:40,645][87426] Updated weights for policy 1, policy_version 166460 (0.0010) -[2023-11-28 04:34:42,477][87424] Updated weights for policy 0, policy_version 166887 (0.0012) -[2023-11-28 04:34:42,612][87426] Updated weights for policy 1, policy_version 166470 (0.0011) -[2023-11-28 04:34:42,858][87424] Updated weights for policy 0, policy_version 166897 (0.0012) -[2023-11-28 04:34:42,991][87426] Updated weights for policy 1, policy_version 166480 (0.0012) -[2023-11-28 04:34:43,243][87424] Updated weights for policy 0, policy_version 166907 (0.0012) -[2023-11-28 04:34:43,369][87426] Updated weights for policy 1, policy_version 166490 (0.0011) -[2023-11-28 04:34:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5598.0, 300 sec: 5442.8). Total num frames: 85344256. Throughput: 0: 2749.3, 1: 2706.9. Samples: 85356952. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:43,445][86177] Avg episode reward: [(0, '-494.880'), (1, '-575.620')] -[2023-11-28 04:34:45,564][87426] Updated weights for policy 1, policy_version 166500 (0.0011) -[2023-11-28 04:34:45,671][87424] Updated weights for policy 0, policy_version 166917 (0.0011) -[2023-11-28 04:34:45,947][87426] Updated weights for policy 1, policy_version 166510 (0.0011) -[2023-11-28 04:34:46,055][87424] Updated weights for policy 0, policy_version 166927 (0.0011) -[2023-11-28 04:34:46,319][87426] Updated weights for policy 1, policy_version 166520 (0.0010) -[2023-11-28 04:34:46,427][87424] Updated weights for policy 0, policy_version 166937 (0.0008) -[2023-11-28 04:34:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 85368832. Throughput: 0: 2739.1, 1: 2726.3. Samples: 85381252. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:48,445][86177] Avg episode reward: [(0, '-513.790'), (1, '-585.590')] -[2023-11-28 04:34:48,452][87426] Updated weights for policy 1, policy_version 166530 (0.0010) -[2023-11-28 04:34:48,764][87424] Updated weights for policy 0, policy_version 166947 (0.0009) -[2023-11-28 04:34:48,840][87426] Updated weights for policy 1, policy_version 166540 (0.0008) -[2023-11-28 04:34:49,146][87424] Updated weights for policy 0, policy_version 166957 (0.0010) -[2023-11-28 04:34:49,221][87426] Updated weights for policy 1, policy_version 166550 (0.0011) -[2023-11-28 04:34:49,525][87424] Updated weights for policy 0, policy_version 166967 (0.0011) -[2023-11-28 04:34:49,593][87426] Updated weights for policy 1, policy_version 166560 (0.0011) -[2023-11-28 04:34:51,633][87424] Updated weights for policy 0, policy_version 166977 (0.0010) -[2023-11-28 04:34:51,786][87426] Updated weights for policy 1, policy_version 166570 (0.0012) -[2023-11-28 04:34:52,023][87424] Updated weights for policy 0, policy_version 166987 (0.0012) -[2023-11-28 04:34:52,157][87426] Updated weights for policy 1, policy_version 166580 (0.0011) -[2023-11-28 04:34:52,393][87424] Updated weights for policy 0, policy_version 166997 (0.0011) -[2023-11-28 04:34:52,537][87426] Updated weights for policy 1, policy_version 166590 (0.0011) -[2023-11-28 04:34:52,780][87424] Updated weights for policy 0, policy_version 167007 (0.0012) -[2023-11-28 04:34:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85401600. Throughput: 0: 2721.7, 1: 2721.3. Samples: 85414064. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 04:34:53,445][86177] Avg episode reward: [(0, '-509.600'), (1, '-567.750')] -[2023-11-28 04:34:54,945][87424] Updated weights for policy 0, policy_version 167017 (0.0011) -[2023-11-28 04:34:55,004][87426] Updated weights for policy 1, policy_version 166600 (0.0010) -[2023-11-28 04:34:55,326][87424] Updated weights for policy 0, policy_version 167027 (0.0012) -[2023-11-28 04:34:55,389][87426] Updated weights for policy 1, policy_version 166610 (0.0007) -[2023-11-28 04:34:55,715][87424] Updated weights for policy 0, policy_version 167037 (0.0010) -[2023-11-28 04:34:55,773][87426] Updated weights for policy 1, policy_version 166620 (0.0007) -[2023-11-28 04:34:57,506][87424] Updated weights for policy 0, policy_version 167047 (0.0012) -[2023-11-28 04:34:57,884][87424] Updated weights for policy 0, policy_version 167057 (0.0011) -[2023-11-28 04:34:58,134][87426] Updated weights for policy 1, policy_version 166630 (0.0009) -[2023-11-28 04:34:58,260][87424] Updated weights for policy 0, policy_version 167067 (0.0007) -[2023-11-28 04:34:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 85417984. Throughput: 0: 2718.9, 1: 2710.9. Samples: 85438424. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:34:58,445][86177] Avg episode reward: [(0, '-511.130'), (1, '-555.120')] -[2023-11-28 04:34:58,511][87426] Updated weights for policy 1, policy_version 166640 (0.0007) -[2023-11-28 04:34:58,888][87426] Updated weights for policy 1, policy_version 166650 (0.0007) -[2023-11-28 04:35:00,404][87424] Updated weights for policy 0, policy_version 167077 (0.0009) -[2023-11-28 04:35:00,785][87424] Updated weights for policy 0, policy_version 167087 (0.0011) -[2023-11-28 04:35:01,167][87424] Updated weights for policy 0, policy_version 167097 (0.0009) -[2023-11-28 04:35:01,333][87426] Updated weights for policy 1, policy_version 166660 (0.0009) -[2023-11-28 04:35:01,713][87426] Updated weights for policy 1, policy_version 166670 (0.0008) -[2023-11-28 04:35:02,098][87426] Updated weights for policy 1, policy_version 166680 (0.0012) -[2023-11-28 04:35:03,199][87424] Updated weights for policy 0, policy_version 167107 (0.0010) -[2023-11-28 04:35:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 85450752. Throughput: 0: 2745.9, 1: 2691.3. Samples: 85462812. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:03,446][86177] Avg episode reward: [(0, '-515.900'), (1, '-559.440')] -[2023-11-28 04:35:03,581][87424] Updated weights for policy 0, policy_version 167117 (0.0011) -[2023-11-28 04:35:03,963][87424] Updated weights for policy 0, policy_version 167127 (0.0009) -[2023-11-28 04:35:04,544][87426] Updated weights for policy 1, policy_version 166690 (0.0011) -[2023-11-28 04:35:04,908][87426] Updated weights for policy 1, policy_version 166700 (0.0008) -[2023-11-28 04:35:05,288][87426] Updated weights for policy 1, policy_version 166710 (0.0011) -[2023-11-28 04:35:05,666][87426] Updated weights for policy 1, policy_version 166720 (0.0012) -[2023-11-28 04:35:06,078][87424] Updated weights for policy 0, policy_version 167137 (0.0011) -[2023-11-28 04:35:06,466][87424] Updated weights for policy 0, policy_version 167147 (0.0012) -[2023-11-28 04:35:06,859][87424] Updated weights for policy 0, policy_version 167157 (0.0011) -[2023-11-28 04:35:07,243][87424] Updated weights for policy 0, policy_version 167167 (0.0012) -[2023-11-28 04:35:07,470][87426] Updated weights for policy 1, policy_version 166730 (0.0011) -[2023-11-28 04:35:07,852][87426] Updated weights for policy 1, policy_version 166740 (0.0012) -[2023-11-28 04:35:08,240][87426] Updated weights for policy 1, policy_version 166750 (0.0012) -[2023-11-28 04:35:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85483520. Throughput: 0: 2764.4, 1: 2690.7. Samples: 85496472. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:08,445][86177] Avg episode reward: [(0, '-498.290'), (1, '-620.840')] -[2023-11-28 04:35:09,515][87424] Updated weights for policy 0, policy_version 167177 (0.0012) -[2023-11-28 04:35:09,895][87424] Updated weights for policy 0, policy_version 167187 (0.0011) -[2023-11-28 04:35:10,123][87426] Updated weights for policy 1, policy_version 166760 (0.0014) -[2023-11-28 04:35:10,279][87424] Updated weights for policy 0, policy_version 167197 (0.0008) -[2023-11-28 04:35:10,498][87426] Updated weights for policy 1, policy_version 166770 (0.0011) -[2023-11-28 04:35:10,876][87426] Updated weights for policy 1, policy_version 166780 (0.0008) -[2023-11-28 04:35:12,722][87424] Updated weights for policy 0, policy_version 167207 (0.0012) -[2023-11-28 04:35:13,094][87424] Updated weights for policy 0, policy_version 167217 (0.0010) -[2023-11-28 04:35:13,210][87426] Updated weights for policy 1, policy_version 166790 (0.0011) -[2023-11-28 04:35:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 85499904. Throughput: 0: 2752.0, 1: 2695.5. Samples: 85521324. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:13,445][86177] Avg episode reward: [(0, '-498.350'), (1, '-623.630')] -[2023-11-28 04:35:13,483][87424] Updated weights for policy 0, policy_version 167227 (0.0010) -[2023-11-28 04:35:13,588][87426] Updated weights for policy 1, policy_version 166800 (0.0012) -[2023-11-28 04:35:13,985][87426] Updated weights for policy 1, policy_version 166810 (0.0008) -[2023-11-28 04:35:15,256][87424] Updated weights for policy 0, policy_version 167237 (0.0011) -[2023-11-28 04:35:15,646][87424] Updated weights for policy 0, policy_version 167247 (0.0012) -[2023-11-28 04:35:16,027][87424] Updated weights for policy 0, policy_version 167257 (0.0012) -[2023-11-28 04:35:16,249][87426] Updated weights for policy 1, policy_version 166820 (0.0009) -[2023-11-28 04:35:16,638][87426] Updated weights for policy 1, policy_version 166830 (0.0012) -[2023-11-28 04:35:17,011][87426] Updated weights for policy 1, policy_version 166840 (0.0012) -[2023-11-28 04:35:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 85532672. Throughput: 0: 2748.7, 1: 2681.4. Samples: 85545112. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:18,445][86177] Avg episode reward: [(0, '-497.220'), (1, '-660.210')] -[2023-11-28 04:35:18,501][87424] Updated weights for policy 0, policy_version 167267 (0.0011) -[2023-11-28 04:35:18,885][87424] Updated weights for policy 0, policy_version 167277 (0.0011) -[2023-11-28 04:35:19,036][87426] Updated weights for policy 1, policy_version 166850 (0.0009) -[2023-11-28 04:35:19,269][87424] Updated weights for policy 0, policy_version 167287 (0.0008) -[2023-11-28 04:35:19,419][87426] Updated weights for policy 1, policy_version 166860 (0.0012) -[2023-11-28 04:35:19,801][87426] Updated weights for policy 1, policy_version 166870 (0.0010) -[2023-11-28 04:35:20,178][87426] Updated weights for policy 1, policy_version 166880 (0.0011) -[2023-11-28 04:35:21,362][87424] Updated weights for policy 0, policy_version 167297 (0.0008) -[2023-11-28 04:35:21,748][87424] Updated weights for policy 0, policy_version 167307 (0.0012) -[2023-11-28 04:35:22,129][87424] Updated weights for policy 0, policy_version 167317 (0.0011) -[2023-11-28 04:35:22,438][87426] Updated weights for policy 1, policy_version 166890 (0.0010) -[2023-11-28 04:35:22,508][87424] Updated weights for policy 0, policy_version 167327 (0.0011) -[2023-11-28 04:35:22,831][87426] Updated weights for policy 1, policy_version 166900 (0.0008) -[2023-11-28 04:35:23,206][87426] Updated weights for policy 1, policy_version 166910 (0.0009) -[2023-11-28 04:35:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85565440. Throughput: 0: 2763.6, 1: 2686.0. Samples: 85578192. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:23,445][86177] Avg episode reward: [(0, '-494.850'), (1, '-632.670')] -[2023-11-28 04:35:24,377][87424] Updated weights for policy 0, policy_version 167337 (0.0010) -[2023-11-28 04:35:24,761][87424] Updated weights for policy 0, policy_version 167347 (0.0008) -[2023-11-28 04:35:25,146][87424] Updated weights for policy 0, policy_version 167357 (0.0008) -[2023-11-28 04:35:25,735][87426] Updated weights for policy 1, policy_version 166920 (0.0012) -[2023-11-28 04:35:26,118][87426] Updated weights for policy 1, policy_version 166930 (0.0012) -[2023-11-28 04:35:26,505][87426] Updated weights for policy 1, policy_version 166940 (0.0011) -[2023-11-28 04:35:27,037][87424] Updated weights for policy 0, policy_version 167367 (0.0009) -[2023-11-28 04:35:27,429][87424] Updated weights for policy 0, policy_version 167377 (0.0007) -[2023-11-28 04:35:27,805][87424] Updated weights for policy 0, policy_version 167387 (0.0007) -[2023-11-28 04:35:28,242][87426] Updated weights for policy 1, policy_version 166950 (0.0010) -[2023-11-28 04:35:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85590016. Throughput: 0: 2785.7, 1: 2702.8. Samples: 85603932. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:28,445][86177] Avg episode reward: [(0, '-496.720'), (1, '-563.720')] -[2023-11-28 04:35:28,627][87426] Updated weights for policy 1, policy_version 166960 (0.0007) -[2023-11-28 04:35:29,016][87426] Updated weights for policy 1, policy_version 166970 (0.0008) -[2023-11-28 04:35:29,575][87424] Updated weights for policy 0, policy_version 167397 (0.0012) -[2023-11-28 04:35:29,970][87424] Updated weights for policy 0, policy_version 167407 (0.0011) -[2023-11-28 04:35:30,355][87424] Updated weights for policy 0, policy_version 167417 (0.0011) -[2023-11-28 04:35:31,270][87426] Updated weights for policy 1, policy_version 166980 (0.0008) -[2023-11-28 04:35:31,653][87426] Updated weights for policy 1, policy_version 166990 (0.0008) -[2023-11-28 04:35:32,028][87426] Updated weights for policy 1, policy_version 167000 (0.0008) -[2023-11-28 04:35:32,657][87424] Updated weights for policy 0, policy_version 167427 (0.0012) -[2023-11-28 04:35:33,040][87424] Updated weights for policy 0, policy_version 167437 (0.0012) -[2023-11-28 04:35:33,420][87424] Updated weights for policy 0, policy_version 167447 (0.0012) -[2023-11-28 04:35:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 85614592. Throughput: 0: 2834.4, 1: 2679.7. Samples: 85629388. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:33,446][86177] Avg episode reward: [(0, '-502.960'), (1, '-570.660')] -[2023-11-28 04:35:34,065][87426] Updated weights for policy 1, policy_version 167010 (0.0008) -[2023-11-28 04:35:34,448][87426] Updated weights for policy 1, policy_version 167020 (0.0008) -[2023-11-28 04:35:34,825][87426] Updated weights for policy 1, policy_version 167030 (0.0010) -[2023-11-28 04:35:35,171][87424] Updated weights for policy 0, policy_version 167457 (0.0012) -[2023-11-28 04:35:35,199][87426] Updated weights for policy 1, policy_version 167040 (0.0010) -[2023-11-28 04:35:35,551][87424] Updated weights for policy 0, policy_version 167467 (0.0010) -[2023-11-28 04:35:35,931][87424] Updated weights for policy 0, policy_version 167477 (0.0012) -[2023-11-28 04:35:36,321][87424] Updated weights for policy 0, policy_version 167487 (0.0012) -[2023-11-28 04:35:37,546][87426] Updated weights for policy 1, policy_version 167050 (0.0012) -[2023-11-28 04:35:37,927][87426] Updated weights for policy 1, policy_version 167060 (0.0012) -[2023-11-28 04:35:38,088][87424] Updated weights for policy 0, policy_version 167497 (0.0011) -[2023-11-28 04:35:38,309][87426] Updated weights for policy 1, policy_version 167070 (0.0011) -[2023-11-28 04:35:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 85647360. Throughput: 0: 2854.9, 1: 2681.5. Samples: 85663204. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:38,445][86177] Avg episode reward: [(0, '-502.670'), (1, '-561.730')] -[2023-11-28 04:35:38,475][87424] Updated weights for policy 0, policy_version 167507 (0.0009) -[2023-11-28 04:35:38,854][87424] Updated weights for policy 0, policy_version 167517 (0.0008) -[2023-11-28 04:35:40,651][87426] Updated weights for policy 1, policy_version 167080 (0.0010) -[2023-11-28 04:35:40,971][87424] Updated weights for policy 0, policy_version 167527 (0.0010) -[2023-11-28 04:35:41,031][87426] Updated weights for policy 1, policy_version 167090 (0.0009) -[2023-11-28 04:35:41,352][87424] Updated weights for policy 0, policy_version 167537 (0.0010) -[2023-11-28 04:35:41,408][87426] Updated weights for policy 1, policy_version 167100 (0.0007) -[2023-11-28 04:35:41,763][87424] Updated weights for policy 0, policy_version 167547 (0.0008) -[2023-11-28 04:35:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85671936. Throughput: 0: 2844.2, 1: 2667.8. Samples: 85686464. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:43,445][86177] Avg episode reward: [(0, '-500.560'), (1, '-521.050')] -[2023-11-28 04:35:43,641][87424] Updated weights for policy 0, policy_version 167557 (0.0012) -[2023-11-28 04:35:43,745][87426] Updated weights for policy 1, policy_version 167110 (0.0010) -[2023-11-28 04:35:44,027][87424] Updated weights for policy 0, policy_version 167567 (0.0012) -[2023-11-28 04:35:44,119][87426] Updated weights for policy 1, policy_version 167120 (0.0010) -[2023-11-28 04:35:44,407][87424] Updated weights for policy 0, policy_version 167577 (0.0012) -[2023-11-28 04:35:44,495][87426] Updated weights for policy 1, policy_version 167130 (0.0008) -[2023-11-28 04:35:46,736][87426] Updated weights for policy 1, policy_version 167140 (0.0011) -[2023-11-28 04:35:46,738][87424] Updated weights for policy 0, policy_version 167587 (0.0012) -[2023-11-28 04:35:47,115][87426] Updated weights for policy 1, policy_version 167150 (0.0009) -[2023-11-28 04:35:47,116][87424] Updated weights for policy 0, policy_version 167597 (0.0012) -[2023-11-28 04:35:47,502][87424] Updated weights for policy 0, policy_version 167607 (0.0012) -[2023-11-28 04:35:47,508][87426] Updated weights for policy 1, policy_version 167160 (0.0011) -[2023-11-28 04:35:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 85704704. Throughput: 0: 2839.4, 1: 2688.2. Samples: 85711552. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:48,445][86177] Avg episode reward: [(0, '-503.370'), (1, '-518.910')] -[2023-11-28 04:35:49,349][87424] Updated weights for policy 0, policy_version 167617 (0.0011) -[2023-11-28 04:35:49,400][87426] Updated weights for policy 1, policy_version 167170 (0.0011) -[2023-11-28 04:35:49,735][87424] Updated weights for policy 0, policy_version 167627 (0.0011) -[2023-11-28 04:35:49,772][87426] Updated weights for policy 1, policy_version 167180 (0.0011) -[2023-11-28 04:35:50,114][87424] Updated weights for policy 0, policy_version 167637 (0.0012) -[2023-11-28 04:35:50,158][87426] Updated weights for policy 1, policy_version 167190 (0.0009) -[2023-11-28 04:35:50,495][87424] Updated weights for policy 0, policy_version 167647 (0.0011) -[2023-11-28 04:35:50,539][87426] Updated weights for policy 1, policy_version 167200 (0.0008) -[2023-11-28 04:35:52,348][87424] Updated weights for policy 0, policy_version 167657 (0.0009) -[2023-11-28 04:35:52,726][87424] Updated weights for policy 0, policy_version 167667 (0.0008) -[2023-11-28 04:35:52,997][87426] Updated weights for policy 1, policy_version 167210 (0.0011) -[2023-11-28 04:35:53,115][87424] Updated weights for policy 0, policy_version 167677 (0.0009) -[2023-11-28 04:35:53,380][87426] Updated weights for policy 1, policy_version 167220 (0.0008) -[2023-11-28 04:35:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85729280. Throughput: 0: 2830.3, 1: 2670.6. Samples: 85744012. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:53,445][86177] Avg episode reward: [(0, '-497.220'), (1, '-490.930')] -[2023-11-28 04:35:53,762][87426] Updated weights for policy 1, policy_version 167230 (0.0010) -[2023-11-28 04:35:55,682][87424] Updated weights for policy 0, policy_version 167687 (0.0008) -[2023-11-28 04:35:56,065][87424] Updated weights for policy 0, policy_version 167697 (0.0008) -[2023-11-28 04:35:56,272][87426] Updated weights for policy 1, policy_version 167240 (0.0011) -[2023-11-28 04:35:56,447][87424] Updated weights for policy 0, policy_version 167707 (0.0008) -[2023-11-28 04:35:56,646][87426] Updated weights for policy 1, policy_version 167250 (0.0011) -[2023-11-28 04:35:57,028][87426] Updated weights for policy 1, policy_version 167260 (0.0011) -[2023-11-28 04:35:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 85753856. Throughput: 0: 2814.9, 1: 2665.9. Samples: 85767960. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 04:35:58,445][86177] Avg episode reward: [(0, '-502.620'), (1, '-515.960')] -[2023-11-28 04:35:58,738][87424] Updated weights for policy 0, policy_version 167717 (0.0007) -[2023-11-28 04:35:59,119][87424] Updated weights for policy 0, policy_version 167727 (0.0009) -[2023-11-28 04:35:59,209][87426] Updated weights for policy 1, policy_version 167270 (0.0012) -[2023-11-28 04:35:59,503][87424] Updated weights for policy 0, policy_version 167737 (0.0008) -[2023-11-28 04:35:59,594][87426] Updated weights for policy 1, policy_version 167280 (0.0012) -[2023-11-28 04:35:59,972][87426] Updated weights for policy 1, policy_version 167290 (0.0011) -[2023-11-28 04:36:01,946][87426] Updated weights for policy 1, policy_version 167300 (0.0011) -[2023-11-28 04:36:02,018][87424] Updated weights for policy 0, policy_version 167747 (0.0009) -[2023-11-28 04:36:02,329][87426] Updated weights for policy 1, policy_version 167310 (0.0011) -[2023-11-28 04:36:02,388][87424] Updated weights for policy 0, policy_version 167757 (0.0008) -[2023-11-28 04:36:02,700][87426] Updated weights for policy 1, policy_version 167320 (0.0011) -[2023-11-28 04:36:02,775][87424] Updated weights for policy 0, policy_version 167767 (0.0010) -[2023-11-28 04:36:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 85786624. Throughput: 0: 2814.8, 1: 2671.4. Samples: 85791988. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:03,445][86177] Avg episode reward: [(0, '-501.230'), (1, '-537.130')] -[2023-11-28 04:36:04,742][87424] Updated weights for policy 0, policy_version 167777 (0.0008) -[2023-11-28 04:36:05,131][87424] Updated weights for policy 0, policy_version 167787 (0.0012) -[2023-11-28 04:36:05,253][87426] Updated weights for policy 1, policy_version 167330 (0.0010) -[2023-11-28 04:36:05,508][87424] Updated weights for policy 0, policy_version 167797 (0.0010) -[2023-11-28 04:36:05,642][87426] Updated weights for policy 1, policy_version 167340 (0.0011) -[2023-11-28 04:36:05,895][87424] Updated weights for policy 0, policy_version 167807 (0.0011) -[2023-11-28 04:36:06,017][87426] Updated weights for policy 1, policy_version 167350 (0.0008) -[2023-11-28 04:36:06,396][87426] Updated weights for policy 1, policy_version 167360 (0.0008) -[2023-11-28 04:36:08,302][87424] Updated weights for policy 0, policy_version 167817 (0.0012) -[2023-11-28 04:36:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 85803008. Throughput: 0: 2822.6, 1: 2661.9. Samples: 85824992. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:08,445][86177] Avg episode reward: [(0, '-496.190'), (1, '-563.310')] -[2023-11-28 04:36:08,667][87426] Updated weights for policy 1, policy_version 167370 (0.0007) -[2023-11-28 04:36:08,683][87424] Updated weights for policy 0, policy_version 167827 (0.0012) -[2023-11-28 04:36:09,051][87426] Updated weights for policy 1, policy_version 167380 (0.0008) -[2023-11-28 04:36:09,061][87424] Updated weights for policy 0, policy_version 167837 (0.0012) -[2023-11-28 04:36:09,432][87426] Updated weights for policy 1, policy_version 167390 (0.0009) -[2023-11-28 04:36:10,833][87424] Updated weights for policy 0, policy_version 167847 (0.0012) -[2023-11-28 04:36:11,227][87424] Updated weights for policy 0, policy_version 167857 (0.0012) -[2023-11-28 04:36:11,439][87426] Updated weights for policy 1, policy_version 167400 (0.0011) -[2023-11-28 04:36:11,601][87424] Updated weights for policy 0, policy_version 167867 (0.0011) -[2023-11-28 04:36:11,815][87426] Updated weights for policy 1, policy_version 167410 (0.0011) -[2023-11-28 04:36:12,200][87426] Updated weights for policy 1, policy_version 167420 (0.0009) -[2023-11-28 04:36:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 85835776. Throughput: 0: 2796.4, 1: 2636.2. Samples: 85848400. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:13,445][86177] Avg episode reward: [(0, '-507.720'), (1, '-613.520')] -[2023-11-28 04:36:13,931][87424] Updated weights for policy 0, policy_version 167877 (0.0011) -[2023-11-28 04:36:14,315][87424] Updated weights for policy 0, policy_version 167887 (0.0012) -[2023-11-28 04:36:14,695][87424] Updated weights for policy 0, policy_version 167897 (0.0011) -[2023-11-28 04:36:14,779][87426] Updated weights for policy 1, policy_version 167430 (0.0011) -[2023-11-28 04:36:15,155][87426] Updated weights for policy 1, policy_version 167440 (0.0012) -[2023-11-28 04:36:15,535][87426] Updated weights for policy 1, policy_version 167450 (0.0012) -[2023-11-28 04:36:16,534][87424] Updated weights for policy 0, policy_version 167907 (0.0007) -[2023-11-28 04:36:16,915][87424] Updated weights for policy 0, policy_version 167917 (0.0008) -[2023-11-28 04:36:17,242][87426] Updated weights for policy 1, policy_version 167460 (0.0011) -[2023-11-28 04:36:17,298][87424] Updated weights for policy 0, policy_version 167927 (0.0009) -[2023-11-28 04:36:17,607][87426] Updated weights for policy 1, policy_version 167470 (0.0012) -[2023-11-28 04:36:17,984][87426] Updated weights for policy 1, policy_version 167480 (0.0012) -[2023-11-28 04:36:18,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 85868544. Throughput: 0: 2771.6, 1: 2655.2. Samples: 85873592. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:18,445][86177] Avg episode reward: [(0, '-507.670'), (1, '-607.180')] -[2023-11-28 04:36:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000167488_42876928.pth... -[2023-11-28 04:36:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000167936_42991616.pth... -[2023-11-28 04:36:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000165344_42328064.pth -[2023-11-28 04:36:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000164992_42237952.pth -[2023-11-28 04:36:19,508][87424] Updated weights for policy 0, policy_version 167937 (0.0009) -[2023-11-28 04:36:19,886][87424] Updated weights for policy 0, policy_version 167947 (0.0009) -[2023-11-28 04:36:20,267][87424] Updated weights for policy 0, policy_version 167957 (0.0009) -[2023-11-28 04:36:20,450][87426] Updated weights for policy 1, policy_version 167490 (0.0012) -[2023-11-28 04:36:20,646][87424] Updated weights for policy 0, policy_version 167967 (0.0010) -[2023-11-28 04:36:20,829][87426] Updated weights for policy 1, policy_version 167500 (0.0011) -[2023-11-28 04:36:21,210][87426] Updated weights for policy 1, policy_version 167510 (0.0010) -[2023-11-28 04:36:21,577][87426] Updated weights for policy 1, policy_version 167520 (0.0012) -[2023-11-28 04:36:23,024][87424] Updated weights for policy 0, policy_version 167977 (0.0012) -[2023-11-28 04:36:23,402][87424] Updated weights for policy 0, policy_version 167987 (0.0011) -[2023-11-28 04:36:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 85884928. Throughput: 0: 2730.9, 1: 2662.0. Samples: 85905888. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:23,445][86177] Avg episode reward: [(0, '-508.880'), (1, '-606.250')] -[2023-11-28 04:36:23,785][87424] Updated weights for policy 0, policy_version 167997 (0.0012) -[2023-11-28 04:36:23,979][87426] Updated weights for policy 1, policy_version 167530 (0.0007) -[2023-11-28 04:36:24,361][87426] Updated weights for policy 1, policy_version 167540 (0.0008) -[2023-11-28 04:36:24,741][87426] Updated weights for policy 1, policy_version 167550 (0.0008) -[2023-11-28 04:36:25,670][87424] Updated weights for policy 0, policy_version 168007 (0.0011) -[2023-11-28 04:36:26,052][87424] Updated weights for policy 0, policy_version 168017 (0.0012) -[2023-11-28 04:36:26,439][87424] Updated weights for policy 0, policy_version 168027 (0.0012) -[2023-11-28 04:36:26,491][87426] Updated weights for policy 1, policy_version 167560 (0.0010) -[2023-11-28 04:36:26,874][87426] Updated weights for policy 1, policy_version 167570 (0.0011) -[2023-11-28 04:36:27,250][87426] Updated weights for policy 1, policy_version 167580 (0.0011) -[2023-11-28 04:36:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85917696. Throughput: 0: 2729.8, 1: 2679.5. Samples: 85929880. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:28,445][86177] Avg episode reward: [(0, '-510.210'), (1, '-562.820')] -[2023-11-28 04:36:28,747][87424] Updated weights for policy 0, policy_version 168037 (0.0012) -[2023-11-28 04:36:29,133][87424] Updated weights for policy 0, policy_version 168047 (0.0012) -[2023-11-28 04:36:29,516][87424] Updated weights for policy 0, policy_version 168057 (0.0012) -[2023-11-28 04:36:29,775][87426] Updated weights for policy 1, policy_version 167590 (0.0008) -[2023-11-28 04:36:30,157][87426] Updated weights for policy 1, policy_version 167600 (0.0008) -[2023-11-28 04:36:30,526][87426] Updated weights for policy 1, policy_version 167610 (0.0009) -[2023-11-28 04:36:31,620][87424] Updated weights for policy 0, policy_version 168067 (0.0011) -[2023-11-28 04:36:32,000][87424] Updated weights for policy 0, policy_version 168077 (0.0008) -[2023-11-28 04:36:32,389][87424] Updated weights for policy 0, policy_version 168087 (0.0009) -[2023-11-28 04:36:32,809][87426] Updated weights for policy 1, policy_version 167620 (0.0009) -[2023-11-28 04:36:33,186][87426] Updated weights for policy 1, policy_version 167630 (0.0007) -[2023-11-28 04:36:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 85942272. Throughput: 0: 2756.5, 1: 2668.1. Samples: 85955660. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:33,445][86177] Avg episode reward: [(0, '-495.300'), (1, '-534.630')] -[2023-11-28 04:36:33,569][87426] Updated weights for policy 1, policy_version 167640 (0.0007) -[2023-11-28 04:36:34,871][87424] Updated weights for policy 0, policy_version 168097 (0.0011) -[2023-11-28 04:36:35,255][87424] Updated weights for policy 0, policy_version 168107 (0.0012) -[2023-11-28 04:36:35,643][87424] Updated weights for policy 0, policy_version 168117 (0.0012) -[2023-11-28 04:36:35,898][87426] Updated weights for policy 1, policy_version 167650 (0.0007) -[2023-11-28 04:36:36,021][87424] Updated weights for policy 0, policy_version 168127 (0.0011) -[2023-11-28 04:36:36,267][87426] Updated weights for policy 1, policy_version 167660 (0.0009) -[2023-11-28 04:36:36,648][87426] Updated weights for policy 1, policy_version 167670 (0.0008) -[2023-11-28 04:36:37,031][87426] Updated weights for policy 1, policy_version 167680 (0.0008) -[2023-11-28 04:36:37,902][87424] Updated weights for policy 0, policy_version 168137 (0.0012) -[2023-11-28 04:36:38,277][87424] Updated weights for policy 0, policy_version 168147 (0.0011) -[2023-11-28 04:36:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 85966848. Throughput: 0: 2754.2, 1: 2668.9. Samples: 85988052. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:38,445][86177] Avg episode reward: [(0, '-512.530'), (1, '-522.960')] -[2023-11-28 04:36:38,660][87424] Updated weights for policy 0, policy_version 168157 (0.0008) -[2023-11-28 04:36:39,162][87426] Updated weights for policy 1, policy_version 167690 (0.0011) -[2023-11-28 04:36:39,523][87426] Updated weights for policy 1, policy_version 167700 (0.0007) -[2023-11-28 04:36:39,896][87426] Updated weights for policy 1, policy_version 167710 (0.0008) -[2023-11-28 04:36:41,130][87424] Updated weights for policy 0, policy_version 168167 (0.0011) -[2023-11-28 04:36:41,525][87424] Updated weights for policy 0, policy_version 168177 (0.0012) -[2023-11-28 04:36:41,904][87424] Updated weights for policy 0, policy_version 168187 (0.0012) -[2023-11-28 04:36:42,113][87426] Updated weights for policy 1, policy_version 167720 (0.0011) -[2023-11-28 04:36:42,495][87426] Updated weights for policy 1, policy_version 167730 (0.0008) -[2023-11-28 04:36:42,879][87426] Updated weights for policy 1, policy_version 167740 (0.0008) -[2023-11-28 04:36:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 85999616. Throughput: 0: 2745.4, 1: 2670.3. Samples: 86011668. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:43,445][86177] Avg episode reward: [(0, '-509.730'), (1, '-507.150')] -[2023-11-28 04:36:44,048][87424] Updated weights for policy 0, policy_version 168197 (0.0010) -[2023-11-28 04:36:44,428][87424] Updated weights for policy 0, policy_version 168207 (0.0011) -[2023-11-28 04:36:44,810][87424] Updated weights for policy 0, policy_version 168217 (0.0007) -[2023-11-28 04:36:45,406][87426] Updated weights for policy 1, policy_version 167750 (0.0010) -[2023-11-28 04:36:45,791][87426] Updated weights for policy 1, policy_version 167760 (0.0012) -[2023-11-28 04:36:46,178][87426] Updated weights for policy 1, policy_version 167770 (0.0012) -[2023-11-28 04:36:46,679][87424] Updated weights for policy 0, policy_version 168227 (0.0009) -[2023-11-28 04:36:47,050][87424] Updated weights for policy 0, policy_version 168237 (0.0007) -[2023-11-28 04:36:47,434][87424] Updated weights for policy 0, policy_version 168247 (0.0007) -[2023-11-28 04:36:48,031][87426] Updated weights for policy 1, policy_version 167780 (0.0010) -[2023-11-28 04:36:48,415][87426] Updated weights for policy 1, policy_version 167790 (0.0007) -[2023-11-28 04:36:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 86024192. Throughput: 0: 2730.2, 1: 2677.2. Samples: 86035320. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:48,445][86177] Avg episode reward: [(0, '-509.230'), (1, '-505.230')] -[2023-11-28 04:36:48,788][87426] Updated weights for policy 1, policy_version 167800 (0.0007) -[2023-11-28 04:36:49,498][87424] Updated weights for policy 0, policy_version 168257 (0.0008) -[2023-11-28 04:36:49,889][87424] Updated weights for policy 0, policy_version 168267 (0.0010) -[2023-11-28 04:36:50,266][87424] Updated weights for policy 0, policy_version 168277 (0.0012) -[2023-11-28 04:36:50,534][87426] Updated weights for policy 1, policy_version 167810 (0.0011) -[2023-11-28 04:36:50,648][87424] Updated weights for policy 0, policy_version 168287 (0.0010) -[2023-11-28 04:36:50,912][87426] Updated weights for policy 1, policy_version 167820 (0.0010) -[2023-11-28 04:36:51,293][87426] Updated weights for policy 1, policy_version 167830 (0.0012) -[2023-11-28 04:36:51,671][87426] Updated weights for policy 1, policy_version 167840 (0.0011) -[2023-11-28 04:36:52,835][87424] Updated weights for policy 0, policy_version 168297 (0.0011) -[2023-11-28 04:36:53,223][87424] Updated weights for policy 0, policy_version 168307 (0.0010) -[2023-11-28 04:36:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 86048768. Throughput: 0: 2703.3, 1: 2692.2. Samples: 86067788. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:53,445][86177] Avg episode reward: [(0, '-492.720'), (1, '-543.030')] -[2023-11-28 04:36:53,609][87424] Updated weights for policy 0, policy_version 168317 (0.0011) -[2023-11-28 04:36:53,705][87426] Updated weights for policy 1, policy_version 167850 (0.0011) -[2023-11-28 04:36:54,091][87426] Updated weights for policy 1, policy_version 167860 (0.0008) -[2023-11-28 04:36:54,461][87426] Updated weights for policy 1, policy_version 167870 (0.0009) -[2023-11-28 04:36:56,192][87424] Updated weights for policy 0, policy_version 168327 (0.0011) -[2023-11-28 04:36:56,306][87426] Updated weights for policy 1, policy_version 167880 (0.0010) -[2023-11-28 04:36:56,582][87424] Updated weights for policy 0, policy_version 168337 (0.0012) -[2023-11-28 04:36:56,675][87426] Updated weights for policy 1, policy_version 167890 (0.0007) -[2023-11-28 04:36:56,962][87424] Updated weights for policy 0, policy_version 168347 (0.0012) -[2023-11-28 04:36:57,058][87426] Updated weights for policy 1, policy_version 167900 (0.0007) -[2023-11-28 04:36:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86081536. Throughput: 0: 2705.4, 1: 2742.8. Samples: 86093568. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:36:58,445][86177] Avg episode reward: [(0, '-492.830'), (1, '-537.790')] -[2023-11-28 04:36:59,150][87424] Updated weights for policy 0, policy_version 168357 (0.0011) -[2023-11-28 04:36:59,339][87426] Updated weights for policy 1, policy_version 167910 (0.0009) -[2023-11-28 04:36:59,532][87424] Updated weights for policy 0, policy_version 168367 (0.0010) -[2023-11-28 04:36:59,708][87426] Updated weights for policy 1, policy_version 167920 (0.0010) -[2023-11-28 04:36:59,909][87424] Updated weights for policy 0, policy_version 168377 (0.0012) -[2023-11-28 04:37:00,090][87426] Updated weights for policy 1, policy_version 167930 (0.0012) -[2023-11-28 04:37:01,647][87424] Updated weights for policy 0, policy_version 168387 (0.0010) -[2023-11-28 04:37:02,025][87424] Updated weights for policy 0, policy_version 168397 (0.0012) -[2023-11-28 04:37:02,407][87424] Updated weights for policy 0, policy_version 168407 (0.0010) -[2023-11-28 04:37:02,580][87426] Updated weights for policy 1, policy_version 167940 (0.0011) -[2023-11-28 04:37:02,955][87426] Updated weights for policy 1, policy_version 167950 (0.0011) -[2023-11-28 04:37:03,334][87426] Updated weights for policy 1, policy_version 167960 (0.0012) -[2023-11-28 04:37:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 86106112. Throughput: 0: 2727.6, 1: 2756.9. Samples: 86120392. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:37:03,445][86177] Avg episode reward: [(0, '-495.410'), (1, '-565.020')] -[2023-11-28 04:37:04,490][87424] Updated weights for policy 0, policy_version 168417 (0.0010) -[2023-11-28 04:37:04,875][87424] Updated weights for policy 0, policy_version 168427 (0.0012) -[2023-11-28 04:37:05,070][87426] Updated weights for policy 1, policy_version 167970 (0.0011) -[2023-11-28 04:37:05,265][87424] Updated weights for policy 0, policy_version 168437 (0.0011) -[2023-11-28 04:37:05,446][87426] Updated weights for policy 1, policy_version 167980 (0.0011) -[2023-11-28 04:37:05,656][87424] Updated weights for policy 0, policy_version 168447 (0.0011) -[2023-11-28 04:37:05,825][87426] Updated weights for policy 1, policy_version 167990 (0.0011) -[2023-11-28 04:37:06,213][87426] Updated weights for policy 1, policy_version 168000 (0.0011) -[2023-11-28 04:37:07,740][87424] Updated weights for policy 0, policy_version 168457 (0.0012) -[2023-11-28 04:37:07,898][87426] Updated weights for policy 1, policy_version 168010 (0.0009) -[2023-11-28 04:37:08,120][87424] Updated weights for policy 0, policy_version 168467 (0.0011) -[2023-11-28 04:37:08,276][87426] Updated weights for policy 1, policy_version 168020 (0.0010) -[2023-11-28 04:37:08,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86130688. Throughput: 0: 2760.3, 1: 2755.0. Samples: 86154080. Policy #0 lag: (min: 31.0, avg: 49.8, max: 67.0) -[2023-11-28 04:37:08,446][86177] Avg episode reward: [(0, '-493.470'), (1, '-546.350')] -[2023-11-28 04:37:08,512][87424] Updated weights for policy 0, policy_version 168477 (0.0012) -[2023-11-28 04:37:08,652][87426] Updated weights for policy 1, policy_version 168030 (0.0011) -[2023-11-28 04:37:10,552][87424] Updated weights for policy 0, policy_version 168487 (0.0012) -[2023-11-28 04:37:10,944][87424] Updated weights for policy 0, policy_version 168497 (0.0011) -[2023-11-28 04:37:11,149][87426] Updated weights for policy 1, policy_version 168040 (0.0011) -[2023-11-28 04:37:11,320][87424] Updated weights for policy 0, policy_version 168507 (0.0012) -[2023-11-28 04:37:11,523][87426] Updated weights for policy 1, policy_version 168050 (0.0012) -[2023-11-28 04:37:11,904][87426] Updated weights for policy 1, policy_version 168060 (0.0012) -[2023-11-28 04:37:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86163456. Throughput: 0: 2756.2, 1: 2740.9. Samples: 86177248. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:13,445][86177] Avg episode reward: [(0, '-502.390'), (1, '-524.580')] -[2023-11-28 04:37:13,584][87424] Updated weights for policy 0, policy_version 168517 (0.0010) -[2023-11-28 04:37:13,965][87424] Updated weights for policy 0, policy_version 168527 (0.0008) -[2023-11-28 04:37:14,047][87426] Updated weights for policy 1, policy_version 168070 (0.0010) -[2023-11-28 04:37:14,350][87424] Updated weights for policy 0, policy_version 168537 (0.0007) -[2023-11-28 04:37:14,425][87426] Updated weights for policy 1, policy_version 168080 (0.0009) -[2023-11-28 04:37:14,808][87426] Updated weights for policy 1, policy_version 168090 (0.0007) -[2023-11-28 04:37:16,718][87424] Updated weights for policy 0, policy_version 168547 (0.0008) -[2023-11-28 04:37:16,942][87426] Updated weights for policy 1, policy_version 168100 (0.0009) -[2023-11-28 04:37:17,098][87424] Updated weights for policy 0, policy_version 168557 (0.0007) -[2023-11-28 04:37:17,320][87426] Updated weights for policy 1, policy_version 168110 (0.0008) -[2023-11-28 04:37:17,474][87424] Updated weights for policy 0, policy_version 168567 (0.0007) -[2023-11-28 04:37:17,705][87426] Updated weights for policy 1, policy_version 168120 (0.0007) -[2023-11-28 04:37:18,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 86196224. Throughput: 0: 2703.4, 1: 2741.1. Samples: 86200660. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:18,446][86177] Avg episode reward: [(0, '-503.200'), (1, '-577.380')] -[2023-11-28 04:37:19,712][87424] Updated weights for policy 0, policy_version 168577 (0.0009) -[2023-11-28 04:37:20,101][87424] Updated weights for policy 0, policy_version 168587 (0.0011) -[2023-11-28 04:37:20,235][87426] Updated weights for policy 1, policy_version 168130 (0.0010) -[2023-11-28 04:37:20,487][87424] Updated weights for policy 0, policy_version 168597 (0.0012) -[2023-11-28 04:37:20,620][87426] Updated weights for policy 1, policy_version 168140 (0.0012) -[2023-11-28 04:37:20,864][87424] Updated weights for policy 0, policy_version 168607 (0.0012) -[2023-11-28 04:37:20,990][87426] Updated weights for policy 1, policy_version 168150 (0.0011) -[2023-11-28 04:37:21,373][87426] Updated weights for policy 1, policy_version 168160 (0.0012) -[2023-11-28 04:37:23,253][87424] Updated weights for policy 0, policy_version 168617 (0.0012) -[2023-11-28 04:37:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86212608. Throughput: 0: 2704.7, 1: 2747.6. Samples: 86233408. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:23,445][86177] Avg episode reward: [(0, '-502.650'), (1, '-556.490')] -[2023-11-28 04:37:23,523][87426] Updated weights for policy 1, policy_version 168170 (0.0011) -[2023-11-28 04:37:23,633][87424] Updated weights for policy 0, policy_version 168627 (0.0011) -[2023-11-28 04:37:23,889][87426] Updated weights for policy 1, policy_version 168180 (0.0011) -[2023-11-28 04:37:24,019][87424] Updated weights for policy 0, policy_version 168637 (0.0011) -[2023-11-28 04:37:24,271][87426] Updated weights for policy 1, policy_version 168190 (0.0012) -[2023-11-28 04:37:25,832][87424] Updated weights for policy 0, policy_version 168647 (0.0012) -[2023-11-28 04:37:26,209][87424] Updated weights for policy 0, policy_version 168657 (0.0011) -[2023-11-28 04:37:26,601][87424] Updated weights for policy 0, policy_version 168667 (0.0012) -[2023-11-28 04:37:26,836][87426] Updated weights for policy 1, policy_version 168200 (0.0009) -[2023-11-28 04:37:27,209][87426] Updated weights for policy 1, policy_version 168210 (0.0007) -[2023-11-28 04:37:27,591][87426] Updated weights for policy 1, policy_version 168220 (0.0007) -[2023-11-28 04:37:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86245376. Throughput: 0: 2735.1, 1: 2751.5. Samples: 86258564. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:28,446][86177] Avg episode reward: [(0, '-504.590'), (1, '-579.220')] -[2023-11-28 04:37:29,004][87424] Updated weights for policy 0, policy_version 168677 (0.0012) -[2023-11-28 04:37:29,386][87424] Updated weights for policy 0, policy_version 168687 (0.0011) -[2023-11-28 04:37:29,431][87426] Updated weights for policy 1, policy_version 168230 (0.0009) -[2023-11-28 04:37:29,762][87424] Updated weights for policy 0, policy_version 168697 (0.0012) -[2023-11-28 04:37:29,813][87426] Updated weights for policy 1, policy_version 168240 (0.0008) -[2023-11-28 04:37:30,185][87426] Updated weights for policy 1, policy_version 168250 (0.0010) -[2023-11-28 04:37:32,280][87424] Updated weights for policy 0, policy_version 168707 (0.0011) -[2023-11-28 04:37:32,379][87426] Updated weights for policy 1, policy_version 168260 (0.0010) -[2023-11-28 04:37:32,665][87424] Updated weights for policy 0, policy_version 168717 (0.0011) -[2023-11-28 04:37:32,760][87426] Updated weights for policy 1, policy_version 168270 (0.0009) -[2023-11-28 04:37:33,050][87424] Updated weights for policy 0, policy_version 168727 (0.0009) -[2023-11-28 04:37:33,140][87426] Updated weights for policy 1, policy_version 168280 (0.0012) -[2023-11-28 04:37:33,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 86278144. Throughput: 0: 2752.9, 1: 2769.0. Samples: 86283804. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:33,445][86177] Avg episode reward: [(0, '-493.610'), (1, '-579.010')] -[2023-11-28 04:37:34,954][87424] Updated weights for policy 0, policy_version 168737 (0.0008) -[2023-11-28 04:37:35,322][87426] Updated weights for policy 1, policy_version 168290 (0.0011) -[2023-11-28 04:37:35,339][87424] Updated weights for policy 0, policy_version 168747 (0.0012) -[2023-11-28 04:37:35,703][87426] Updated weights for policy 1, policy_version 168300 (0.0011) -[2023-11-28 04:37:35,720][87424] Updated weights for policy 0, policy_version 168757 (0.0011) -[2023-11-28 04:37:36,078][87426] Updated weights for policy 1, policy_version 168310 (0.0012) -[2023-11-28 04:37:36,103][87424] Updated weights for policy 0, policy_version 168767 (0.0011) -[2023-11-28 04:37:36,447][87426] Updated weights for policy 1, policy_version 168320 (0.0011) -[2023-11-28 04:37:38,030][87424] Updated weights for policy 0, policy_version 168777 (0.0011) -[2023-11-28 04:37:38,423][87424] Updated weights for policy 0, policy_version 168787 (0.0009) -[2023-11-28 04:37:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86294528. Throughput: 0: 2793.4, 1: 2788.4. Samples: 86318972. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:38,445][86177] Avg episode reward: [(0, '-493.290'), (1, '-516.200')] -[2023-11-28 04:37:38,533][87426] Updated weights for policy 1, policy_version 168330 (0.0009) -[2023-11-28 04:37:38,797][87424] Updated weights for policy 0, policy_version 168797 (0.0010) -[2023-11-28 04:37:38,912][87426] Updated weights for policy 1, policy_version 168340 (0.0008) -[2023-11-28 04:37:39,278][87426] Updated weights for policy 1, policy_version 168350 (0.0007) -[2023-11-28 04:37:41,314][87424] Updated weights for policy 0, policy_version 168807 (0.0008) -[2023-11-28 04:37:41,550][87426] Updated weights for policy 1, policy_version 168360 (0.0008) -[2023-11-28 04:37:41,694][87424] Updated weights for policy 0, policy_version 168817 (0.0009) -[2023-11-28 04:37:41,924][87426] Updated weights for policy 1, policy_version 168370 (0.0010) -[2023-11-28 04:37:42,083][87424] Updated weights for policy 0, policy_version 168827 (0.0009) -[2023-11-28 04:37:42,311][87426] Updated weights for policy 1, policy_version 168380 (0.0011) -[2023-11-28 04:37:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86327296. Throughput: 0: 2781.1, 1: 2749.0. Samples: 86342420. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:43,445][86177] Avg episode reward: [(0, '-490.540'), (1, '-521.170')] -[2023-11-28 04:37:43,885][87424] Updated weights for policy 0, policy_version 168837 (0.0009) -[2023-11-28 04:37:44,270][87424] Updated weights for policy 0, policy_version 168847 (0.0007) -[2023-11-28 04:37:44,649][87424] Updated weights for policy 0, policy_version 168857 (0.0007) -[2023-11-28 04:37:44,773][87426] Updated weights for policy 1, policy_version 168390 (0.0008) -[2023-11-28 04:37:45,153][87426] Updated weights for policy 1, policy_version 168400 (0.0008) -[2023-11-28 04:37:45,546][87426] Updated weights for policy 1, policy_version 168410 (0.0010) -[2023-11-28 04:37:47,067][87424] Updated weights for policy 0, policy_version 168867 (0.0007) -[2023-11-28 04:37:47,447][87424] Updated weights for policy 0, policy_version 168877 (0.0011) -[2023-11-28 04:37:47,700][87426] Updated weights for policy 1, policy_version 168420 (0.0010) -[2023-11-28 04:37:47,838][87424] Updated weights for policy 0, policy_version 168887 (0.0012) -[2023-11-28 04:37:48,080][87426] Updated weights for policy 1, policy_version 168430 (0.0012) -[2023-11-28 04:37:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86351872. Throughput: 0: 2736.3, 1: 2720.6. Samples: 86365952. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:48,445][86177] Avg episode reward: [(0, '-491.900'), (1, '-500.490')] -[2023-11-28 04:37:48,458][87426] Updated weights for policy 1, policy_version 168440 (0.0012) -[2023-11-28 04:37:50,184][87424] Updated weights for policy 0, policy_version 168897 (0.0011) -[2023-11-28 04:37:50,569][87424] Updated weights for policy 0, policy_version 168907 (0.0011) -[2023-11-28 04:37:50,948][87424] Updated weights for policy 0, policy_version 168917 (0.0010) -[2023-11-28 04:37:51,009][87426] Updated weights for policy 1, policy_version 168450 (0.0010) -[2023-11-28 04:37:51,325][87424] Updated weights for policy 0, policy_version 168927 (0.0012) -[2023-11-28 04:37:51,396][87426] Updated weights for policy 1, policy_version 168460 (0.0008) -[2023-11-28 04:37:51,777][87426] Updated weights for policy 1, policy_version 168470 (0.0010) -[2023-11-28 04:37:52,155][87426] Updated weights for policy 1, policy_version 168480 (0.0009) -[2023-11-28 04:37:53,445][86177] Fps is (10 sec: 4914.7, 60 sec: 5461.2, 300 sec: 5442.8). Total num frames: 86376448. Throughput: 0: 2715.4, 1: 2703.2. Samples: 86397924. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:53,446][86177] Avg episode reward: [(0, '-492.600'), (1, '-497.480')] -[2023-11-28 04:37:53,495][87424] Updated weights for policy 0, policy_version 168937 (0.0016) -[2023-11-28 04:37:53,886][87424] Updated weights for policy 0, policy_version 168947 (0.0012) -[2023-11-28 04:37:54,265][87424] Updated weights for policy 0, policy_version 168957 (0.0012) -[2023-11-28 04:37:54,496][87426] Updated weights for policy 1, policy_version 168490 (0.0007) -[2023-11-28 04:37:54,876][87426] Updated weights for policy 1, policy_version 168500 (0.0007) -[2023-11-28 04:37:55,254][87426] Updated weights for policy 1, policy_version 168510 (0.0008) -[2023-11-28 04:37:56,210][87424] Updated weights for policy 0, policy_version 168967 (0.0012) -[2023-11-28 04:37:56,584][87424] Updated weights for policy 0, policy_version 168977 (0.0012) -[2023-11-28 04:37:56,971][87424] Updated weights for policy 0, policy_version 168987 (0.0012) -[2023-11-28 04:37:57,696][87426] Updated weights for policy 1, policy_version 168520 (0.0008) -[2023-11-28 04:37:58,069][87426] Updated weights for policy 1, policy_version 168530 (0.0007) -[2023-11-28 04:37:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 86401024. Throughput: 0: 2714.2, 1: 2702.8. Samples: 86421016. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:37:58,445][86177] Avg episode reward: [(0, '-491.630'), (1, '-497.890')] -[2023-11-28 04:37:58,451][87426] Updated weights for policy 1, policy_version 168540 (0.0008) -[2023-11-28 04:37:58,515][87424] Updated weights for policy 0, policy_version 168997 (0.0012) -[2023-11-28 04:37:58,891][87424] Updated weights for policy 0, policy_version 169007 (0.0012) -[2023-11-28 04:37:59,273][87424] Updated weights for policy 0, policy_version 169017 (0.0012) -[2023-11-28 04:38:00,454][87426] Updated weights for policy 1, policy_version 168550 (0.0007) -[2023-11-28 04:38:00,840][87426] Updated weights for policy 1, policy_version 168560 (0.0010) -[2023-11-28 04:38:01,215][87426] Updated weights for policy 1, policy_version 168570 (0.0007) -[2023-11-28 04:38:01,506][87424] Updated weights for policy 0, policy_version 169027 (0.0012) -[2023-11-28 04:38:01,885][87424] Updated weights for policy 0, policy_version 169037 (0.0012) -[2023-11-28 04:38:02,270][87424] Updated weights for policy 0, policy_version 169047 (0.0013) -[2023-11-28 04:38:03,352][87426] Updated weights for policy 1, policy_version 168580 (0.0009) -[2023-11-28 04:38:03,444][86177] Fps is (10 sec: 5735.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86433792. Throughput: 0: 2727.4, 1: 2709.1. Samples: 86445300. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:38:03,445][86177] Avg episode reward: [(0, '-493.770'), (1, '-500.250')] -[2023-11-28 04:38:03,730][87426] Updated weights for policy 1, policy_version 168590 (0.0011) -[2023-11-28 04:38:04,115][87426] Updated weights for policy 1, policy_version 168600 (0.0011) -[2023-11-28 04:38:04,625][87424] Updated weights for policy 0, policy_version 169057 (0.0012) -[2023-11-28 04:38:05,006][87424] Updated weights for policy 0, policy_version 169067 (0.0008) -[2023-11-28 04:38:05,390][87424] Updated weights for policy 0, policy_version 169077 (0.0008) -[2023-11-28 04:38:05,782][87424] Updated weights for policy 0, policy_version 169087 (0.0007) -[2023-11-28 04:38:06,039][87426] Updated weights for policy 1, policy_version 168610 (0.0011) -[2023-11-28 04:38:06,419][87426] Updated weights for policy 1, policy_version 168620 (0.0010) -[2023-11-28 04:38:06,800][87426] Updated weights for policy 1, policy_version 168630 (0.0012) -[2023-11-28 04:38:07,179][87426] Updated weights for policy 1, policy_version 168640 (0.0011) -[2023-11-28 04:38:07,722][87424] Updated weights for policy 0, policy_version 169097 (0.0010) -[2023-11-28 04:38:08,105][87424] Updated weights for policy 0, policy_version 169107 (0.0011) -[2023-11-28 04:38:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 86458368. Throughput: 0: 2759.1, 1: 2701.2. Samples: 86479124. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:38:08,445][86177] Avg episode reward: [(0, '-493.430'), (1, '-504.760')] -[2023-11-28 04:38:08,501][87424] Updated weights for policy 0, policy_version 169117 (0.0010) -[2023-11-28 04:38:09,670][87426] Updated weights for policy 1, policy_version 168650 (0.0011) -[2023-11-28 04:38:10,047][87426] Updated weights for policy 1, policy_version 168660 (0.0011) -[2023-11-28 04:38:10,425][87426] Updated weights for policy 1, policy_version 168670 (0.0011) -[2023-11-28 04:38:10,889][87424] Updated weights for policy 0, policy_version 169127 (0.0011) -[2023-11-28 04:38:11,268][87424] Updated weights for policy 0, policy_version 169137 (0.0012) -[2023-11-28 04:38:11,651][87424] Updated weights for policy 0, policy_version 169147 (0.0012) -[2023-11-28 04:38:12,599][87426] Updated weights for policy 1, policy_version 168680 (0.0012) -[2023-11-28 04:38:12,980][87426] Updated weights for policy 1, policy_version 168690 (0.0012) -[2023-11-28 04:38:13,358][87426] Updated weights for policy 1, policy_version 168700 (0.0012) -[2023-11-28 04:38:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 86482944. Throughput: 0: 2731.1, 1: 2686.8. Samples: 86502368. Policy #0 lag: (min: 31.0, avg: 46.0, max: 63.0) -[2023-11-28 04:38:13,445][86177] Avg episode reward: [(0, '-493.230'), (1, '-546.510')] -[2023-11-28 04:38:13,810][87424] Updated weights for policy 0, policy_version 169157 (0.0011) -[2023-11-28 04:38:14,200][87424] Updated weights for policy 0, policy_version 169167 (0.0009) -[2023-11-28 04:38:14,577][87424] Updated weights for policy 0, policy_version 169177 (0.0009) -[2023-11-28 04:38:15,584][87426] Updated weights for policy 1, policy_version 168710 (0.0011) -[2023-11-28 04:38:15,965][87426] Updated weights for policy 1, policy_version 168720 (0.0009) -[2023-11-28 04:38:16,348][87426] Updated weights for policy 1, policy_version 168730 (0.0011) -[2023-11-28 04:38:16,567][87424] Updated weights for policy 0, policy_version 169187 (0.0009) -[2023-11-28 04:38:16,949][87424] Updated weights for policy 0, policy_version 169197 (0.0012) -[2023-11-28 04:38:17,333][87424] Updated weights for policy 0, policy_version 169207 (0.0011) -[2023-11-28 04:38:18,374][87426] Updated weights for policy 1, policy_version 168740 (0.0012) -[2023-11-28 04:38:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 86515712. Throughput: 0: 2735.5, 1: 2683.3. Samples: 86527652. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:38:18,445][86177] Avg episode reward: [(0, '-490.370'), (1, '-560.110')] -[2023-11-28 04:38:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000169216_43319296.pth... -[2023-11-28 04:38:18,488][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000166656_42663936.pth -[2023-11-28 04:38:18,746][87426] Updated weights for policy 1, policy_version 168750 (0.0012) -[2023-11-28 04:38:19,133][87426] Updated weights for policy 1, policy_version 168760 (0.0012) -[2023-11-28 04:38:19,300][87424] Updated weights for policy 0, policy_version 169217 (0.0012) -[2023-11-28 04:38:19,425][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000168768_43204608.pth... -[2023-11-28 04:38:19,473][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000166240_42557440.pth -[2023-11-28 04:38:19,681][87424] Updated weights for policy 0, policy_version 169227 (0.0012) -[2023-11-28 04:38:20,070][87424] Updated weights for policy 0, policy_version 169237 (0.0012) -[2023-11-28 04:38:20,453][87424] Updated weights for policy 0, policy_version 169247 (0.0011) -[2023-11-28 04:38:21,193][87426] Updated weights for policy 1, policy_version 168770 (0.0011) -[2023-11-28 04:38:21,571][87426] Updated weights for policy 1, policy_version 168780 (0.0010) -[2023-11-28 04:38:21,953][87426] Updated weights for policy 1, policy_version 168790 (0.0009) -[2023-11-28 04:38:22,326][87426] Updated weights for policy 1, policy_version 168800 (0.0009) -[2023-11-28 04:38:22,510][87424] Updated weights for policy 0, policy_version 169257 (0.0009) -[2023-11-28 04:38:22,894][87424] Updated weights for policy 0, policy_version 169267 (0.0009) -[2023-11-28 04:38:23,274][87424] Updated weights for policy 0, policy_version 169277 (0.0008) -[2023-11-28 04:38:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 86548480. Throughput: 0: 2699.5, 1: 2665.1. Samples: 86560384. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:38:23,446][86177] Avg episode reward: [(0, '-494.800'), (1, '-558.500')] -[2023-11-28 04:38:24,385][87426] Updated weights for policy 1, policy_version 168810 (0.0011) -[2023-11-28 04:38:24,769][87426] Updated weights for policy 1, policy_version 168820 (0.0009) -[2023-11-28 04:38:25,150][87426] Updated weights for policy 1, policy_version 168830 (0.0011) -[2023-11-28 04:38:25,641][87424] Updated weights for policy 0, policy_version 169287 (0.0011) -[2023-11-28 04:38:26,027][87424] Updated weights for policy 0, policy_version 169297 (0.0011) -[2023-11-28 04:38:26,415][87424] Updated weights for policy 0, policy_version 169307 (0.0011) -[2023-11-28 04:38:27,591][87426] Updated weights for policy 1, policy_version 168840 (0.0010) -[2023-11-28 04:38:27,968][87426] Updated weights for policy 1, policy_version 168850 (0.0012) -[2023-11-28 04:38:28,354][87426] Updated weights for policy 1, policy_version 168860 (0.0011) -[2023-11-28 04:38:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 86564864. Throughput: 0: 2729.5, 1: 2666.7. Samples: 86585248. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:38:28,445][86177] Avg episode reward: [(0, '-493.770'), (1, '-519.580')] -[2023-11-28 04:38:28,468][87424] Updated weights for policy 0, policy_version 169317 (0.0010) -[2023-11-28 04:38:28,853][87424] Updated weights for policy 0, policy_version 169327 (0.0008) -[2023-11-28 04:38:29,243][87424] Updated weights for policy 0, policy_version 169337 (0.0008) -[2023-11-28 04:38:30,805][87426] Updated weights for policy 1, policy_version 168870 (0.0008) -[2023-11-28 04:38:31,194][87426] Updated weights for policy 1, policy_version 168880 (0.0008) -[2023-11-28 04:38:31,568][87426] Updated weights for policy 1, policy_version 168890 (0.0008) -[2023-11-28 04:38:31,800][87424] Updated weights for policy 0, policy_version 169347 (0.0008) -[2023-11-28 04:38:32,180][87424] Updated weights for policy 0, policy_version 169357 (0.0009) -[2023-11-28 04:38:32,564][87424] Updated weights for policy 0, policy_version 169367 (0.0011) -[2023-11-28 04:38:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 86597632. Throughput: 0: 2737.9, 1: 2677.6. Samples: 86609652. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:38:33,445][86177] Avg episode reward: [(0, '-494.000'), (1, '-506.990')] -[2023-11-28 04:38:33,937][87426] Updated weights for policy 1, policy_version 168900 (0.0010) -[2023-11-28 04:38:34,294][87424] Updated weights for policy 0, policy_version 169377 (0.0011) -[2023-11-28 04:38:34,322][87426] Updated weights for policy 1, policy_version 168910 (0.0009) -[2023-11-28 04:38:34,678][87424] Updated weights for policy 0, policy_version 169387 (0.0011) -[2023-11-28 04:38:34,711][87426] Updated weights for policy 1, policy_version 168920 (0.0008) -[2023-11-28 04:38:35,061][87424] Updated weights for policy 0, policy_version 169397 (0.0011) -[2023-11-28 04:38:35,443][87424] Updated weights for policy 0, policy_version 169407 (0.0008) -[2023-11-28 04:38:36,516][87426] Updated weights for policy 1, policy_version 168930 (0.0010) -[2023-11-28 04:38:36,901][87426] Updated weights for policy 1, policy_version 168940 (0.0012) -[2023-11-28 04:38:37,215][87424] Updated weights for policy 0, policy_version 169417 (0.0008) -[2023-11-28 04:38:37,271][87426] Updated weights for policy 1, policy_version 168950 (0.0012) -[2023-11-28 04:38:37,598][87424] Updated weights for policy 0, policy_version 169427 (0.0008) -[2023-11-28 04:38:37,656][87426] Updated weights for policy 1, policy_version 168960 (0.0012) -[2023-11-28 04:38:37,980][87424] Updated weights for policy 0, policy_version 169437 (0.0010) -[2023-11-28 04:38:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 86630400. Throughput: 0: 2752.1, 1: 2696.0. Samples: 86643080. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:38:38,446][86177] Avg episode reward: [(0, '-491.610'), (1, '-509.630')] -[2023-11-28 04:38:39,725][87424] Updated weights for policy 0, policy_version 169447 (0.0011) -[2023-11-28 04:38:39,756][87426] Updated weights for policy 1, policy_version 168970 (0.0011) -[2023-11-28 04:38:40,105][87424] Updated weights for policy 0, policy_version 169457 (0.0011) -[2023-11-28 04:38:40,134][87426] Updated weights for policy 1, policy_version 168980 (0.0011) -[2023-11-28 04:38:40,491][87424] Updated weights for policy 0, policy_version 169467 (0.0011) -[2023-11-28 04:38:40,507][87426] Updated weights for policy 1, policy_version 168990 (0.0011) -[2023-11-28 04:38:42,622][87426] Updated weights for policy 1, policy_version 169000 (0.0012) -[2023-11-28 04:38:42,818][87424] Updated weights for policy 0, policy_version 169477 (0.0012) -[2023-11-28 04:38:43,001][87426] Updated weights for policy 1, policy_version 169010 (0.0012) -[2023-11-28 04:38:43,201][87424] Updated weights for policy 0, policy_version 169487 (0.0011) -[2023-11-28 04:38:43,382][87426] Updated weights for policy 1, policy_version 169020 (0.0010) -[2023-11-28 04:38:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 86646784. Throughput: 0: 2758.6, 1: 2712.6. Samples: 86667220. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:38:43,445][86177] Avg episode reward: [(0, '-490.280'), (1, '-501.950')] -[2023-11-28 04:38:43,574][87424] Updated weights for policy 0, policy_version 169497 (0.0011) -[2023-11-28 04:38:45,333][87426] Updated weights for policy 1, policy_version 169030 (0.0012) -[2023-11-28 04:38:45,713][87426] Updated weights for policy 1, policy_version 169040 (0.0012) -[2023-11-28 04:38:46,084][87426] Updated weights for policy 1, policy_version 169050 (0.0012) -[2023-11-28 04:38:46,147][87424] Updated weights for policy 0, policy_version 169507 (0.0010) -[2023-11-28 04:38:46,524][87424] Updated weights for policy 0, policy_version 169517 (0.0012) -[2023-11-28 04:38:46,898][87424] Updated weights for policy 0, policy_version 169527 (0.0009) -[2023-11-28 04:38:48,246][87426] Updated weights for policy 1, policy_version 169060 (0.0011) -[2023-11-28 04:38:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86679552. Throughput: 0: 2771.2, 1: 2730.7. Samples: 86692884. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:38:48,445][86177] Avg episode reward: [(0, '-490.670'), (1, '-499.620')] -[2023-11-28 04:38:48,625][87426] Updated weights for policy 1, policy_version 169070 (0.0012) -[2023-11-28 04:38:48,810][87424] Updated weights for policy 0, policy_version 169537 (0.0012) -[2023-11-28 04:38:49,001][87426] Updated weights for policy 1, policy_version 169080 (0.0011) -[2023-11-28 04:38:49,186][87424] Updated weights for policy 0, policy_version 169547 (0.0010) -[2023-11-28 04:38:49,570][87424] Updated weights for policy 0, policy_version 169557 (0.0008) -[2023-11-28 04:38:49,945][87424] Updated weights for policy 0, policy_version 169567 (0.0010) -[2023-11-28 04:38:51,155][87426] Updated weights for policy 1, policy_version 169090 (0.0010) -[2023-11-28 04:38:51,529][87426] Updated weights for policy 1, policy_version 169100 (0.0009) -[2023-11-28 04:38:51,909][87426] Updated weights for policy 1, policy_version 169110 (0.0012) -[2023-11-28 04:38:52,085][87424] Updated weights for policy 0, policy_version 169577 (0.0011) -[2023-11-28 04:38:52,287][87426] Updated weights for policy 1, policy_version 169120 (0.0012) -[2023-11-28 04:38:52,468][87424] Updated weights for policy 0, policy_version 169587 (0.0012) -[2023-11-28 04:38:52,839][87424] Updated weights for policy 0, policy_version 169597 (0.0012) -[2023-11-28 04:38:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5598.0, 300 sec: 5498.4). Total num frames: 86712320. Throughput: 0: 2755.5, 1: 2738.4. Samples: 86726348. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:38:53,445][86177] Avg episode reward: [(0, '-489.770'), (1, '-528.480')] -[2023-11-28 04:38:54,907][87426] Updated weights for policy 1, policy_version 169130 (0.0012) -[2023-11-28 04:38:55,193][87424] Updated weights for policy 0, policy_version 169607 (0.0012) -[2023-11-28 04:38:55,275][87426] Updated weights for policy 1, policy_version 169140 (0.0012) -[2023-11-28 04:38:55,591][87424] Updated weights for policy 0, policy_version 169617 (0.0007) -[2023-11-28 04:38:55,657][87426] Updated weights for policy 1, policy_version 169150 (0.0012) -[2023-11-28 04:38:55,966][87424] Updated weights for policy 0, policy_version 169627 (0.0007) -[2023-11-28 04:38:57,538][87426] Updated weights for policy 1, policy_version 169160 (0.0010) -[2023-11-28 04:38:57,912][87426] Updated weights for policy 1, policy_version 169170 (0.0007) -[2023-11-28 04:38:58,140][87424] Updated weights for policy 0, policy_version 169637 (0.0008) -[2023-11-28 04:38:58,286][87426] Updated weights for policy 1, policy_version 169180 (0.0007) -[2023-11-28 04:38:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 86736896. Throughput: 0: 2762.3, 1: 2740.0. Samples: 86749972. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:38:58,445][86177] Avg episode reward: [(0, '-491.260'), (1, '-531.010')] -[2023-11-28 04:38:58,520][87424] Updated weights for policy 0, policy_version 169647 (0.0007) -[2023-11-28 04:38:58,900][87424] Updated weights for policy 0, policy_version 169657 (0.0008) -[2023-11-28 04:39:00,597][87426] Updated weights for policy 1, policy_version 169190 (0.0010) -[2023-11-28 04:39:00,976][87426] Updated weights for policy 1, policy_version 169200 (0.0012) -[2023-11-28 04:39:01,073][87424] Updated weights for policy 0, policy_version 169667 (0.0009) -[2023-11-28 04:39:01,356][87426] Updated weights for policy 1, policy_version 169210 (0.0012) -[2023-11-28 04:39:01,463][87424] Updated weights for policy 0, policy_version 169677 (0.0012) -[2023-11-28 04:39:01,844][87424] Updated weights for policy 0, policy_version 169687 (0.0012) -[2023-11-28 04:39:03,352][87426] Updated weights for policy 1, policy_version 169220 (0.0011) -[2023-11-28 04:39:03,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86761472. Throughput: 0: 2754.3, 1: 2708.3. Samples: 86773472. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:39:03,445][86177] Avg episode reward: [(0, '-492.470'), (1, '-555.570')] -[2023-11-28 04:39:03,746][87426] Updated weights for policy 1, policy_version 169230 (0.0009) -[2023-11-28 04:39:04,121][87426] Updated weights for policy 1, policy_version 169240 (0.0008) -[2023-11-28 04:39:04,235][87424] Updated weights for policy 0, policy_version 169697 (0.0012) -[2023-11-28 04:39:04,619][87424] Updated weights for policy 0, policy_version 169707 (0.0011) -[2023-11-28 04:39:04,996][87424] Updated weights for policy 0, policy_version 169717 (0.0012) -[2023-11-28 04:39:05,387][87424] Updated weights for policy 0, policy_version 169727 (0.0012) -[2023-11-28 04:39:06,390][87426] Updated weights for policy 1, policy_version 169250 (0.0010) -[2023-11-28 04:39:06,771][87426] Updated weights for policy 1, policy_version 169260 (0.0008) -[2023-11-28 04:39:07,155][87426] Updated weights for policy 1, policy_version 169270 (0.0012) -[2023-11-28 04:39:07,343][87424] Updated weights for policy 0, policy_version 169737 (0.0011) -[2023-11-28 04:39:07,527][87426] Updated weights for policy 1, policy_version 169280 (0.0009) -[2023-11-28 04:39:07,731][87424] Updated weights for policy 0, policy_version 169747 (0.0008) -[2023-11-28 04:39:08,113][87424] Updated weights for policy 0, policy_version 169757 (0.0007) -[2023-11-28 04:39:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 86794240. Throughput: 0: 2769.7, 1: 2687.4. Samples: 86805952. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:39:08,445][86177] Avg episode reward: [(0, '-495.620'), (1, '-556.870')] -[2023-11-28 04:39:09,865][87424] Updated weights for policy 0, policy_version 169767 (0.0009) -[2023-11-28 04:39:10,108][87426] Updated weights for policy 1, policy_version 169290 (0.0011) -[2023-11-28 04:39:10,236][87424] Updated weights for policy 0, policy_version 169777 (0.0011) -[2023-11-28 04:39:10,477][87426] Updated weights for policy 1, policy_version 169300 (0.0012) -[2023-11-28 04:39:10,618][87424] Updated weights for policy 0, policy_version 169787 (0.0010) -[2023-11-28 04:39:10,858][87426] Updated weights for policy 1, policy_version 169310 (0.0011) -[2023-11-28 04:39:13,081][87424] Updated weights for policy 0, policy_version 169797 (0.0009) -[2023-11-28 04:39:13,209][87426] Updated weights for policy 1, policy_version 169320 (0.0008) -[2023-11-28 04:39:13,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86810624. Throughput: 0: 2755.6, 1: 2679.6. Samples: 86829832. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:39:13,445][86177] Avg episode reward: [(0, '-508.540'), (1, '-536.250')] -[2023-11-28 04:39:13,475][87424] Updated weights for policy 0, policy_version 169807 (0.0011) -[2023-11-28 04:39:13,593][87426] Updated weights for policy 1, policy_version 169330 (0.0007) -[2023-11-28 04:39:13,856][87424] Updated weights for policy 0, policy_version 169817 (0.0009) -[2023-11-28 04:39:13,973][87426] Updated weights for policy 1, policy_version 169340 (0.0009) -[2023-11-28 04:39:16,084][87426] Updated weights for policy 1, policy_version 169350 (0.0011) -[2023-11-28 04:39:16,369][87424] Updated weights for policy 0, policy_version 169827 (0.0009) -[2023-11-28 04:39:16,459][87426] Updated weights for policy 1, policy_version 169360 (0.0011) -[2023-11-28 04:39:16,750][87424] Updated weights for policy 0, policy_version 169837 (0.0007) -[2023-11-28 04:39:16,840][87426] Updated weights for policy 1, policy_version 169370 (0.0009) -[2023-11-28 04:39:17,135][87424] Updated weights for policy 0, policy_version 169847 (0.0008) -[2023-11-28 04:39:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86843392. Throughput: 0: 2760.5, 1: 2685.7. Samples: 86854732. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:39:18,445][86177] Avg episode reward: [(0, '-504.580'), (1, '-531.560')] -[2023-11-28 04:39:18,963][87426] Updated weights for policy 1, policy_version 169380 (0.0011) -[2023-11-28 04:39:19,257][87424] Updated weights for policy 0, policy_version 169857 (0.0007) -[2023-11-28 04:39:19,342][87426] Updated weights for policy 1, policy_version 169390 (0.0011) -[2023-11-28 04:39:19,641][87424] Updated weights for policy 0, policy_version 169867 (0.0007) -[2023-11-28 04:39:19,717][87426] Updated weights for policy 1, policy_version 169400 (0.0011) -[2023-11-28 04:39:20,021][87424] Updated weights for policy 0, policy_version 169877 (0.0010) -[2023-11-28 04:39:20,404][87424] Updated weights for policy 0, policy_version 169887 (0.0008) -[2023-11-28 04:39:21,850][87426] Updated weights for policy 1, policy_version 169410 (0.0011) -[2023-11-28 04:39:22,232][87426] Updated weights for policy 1, policy_version 169420 (0.0010) -[2023-11-28 04:39:22,450][87424] Updated weights for policy 0, policy_version 169897 (0.0009) -[2023-11-28 04:39:22,609][87426] Updated weights for policy 1, policy_version 169430 (0.0011) -[2023-11-28 04:39:22,830][87424] Updated weights for policy 0, policy_version 169907 (0.0011) -[2023-11-28 04:39:22,988][87426] Updated weights for policy 1, policy_version 169440 (0.0010) -[2023-11-28 04:39:23,221][87424] Updated weights for policy 0, policy_version 169917 (0.0011) -[2023-11-28 04:39:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 86876160. Throughput: 0: 2742.2, 1: 2680.0. Samples: 86887080. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 04:39:23,445][86177] Avg episode reward: [(0, '-500.990'), (1, '-508.960')] -[2023-11-28 04:39:24,862][87426] Updated weights for policy 1, policy_version 169450 (0.0009) -[2023-11-28 04:39:25,238][87426] Updated weights for policy 1, policy_version 169460 (0.0008) -[2023-11-28 04:39:25,273][87424] Updated weights for policy 0, policy_version 169927 (0.0011) -[2023-11-28 04:39:25,615][87426] Updated weights for policy 1, policy_version 169470 (0.0007) -[2023-11-28 04:39:25,656][87424] Updated weights for policy 0, policy_version 169937 (0.0012) -[2023-11-28 04:39:26,040][87424] Updated weights for policy 0, policy_version 169947 (0.0012) -[2023-11-28 04:39:28,146][87426] Updated weights for policy 1, policy_version 169480 (0.0011) -[2023-11-28 04:39:28,244][87424] Updated weights for policy 0, policy_version 169957 (0.0012) -[2023-11-28 04:39:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86892544. Throughput: 0: 2755.6, 1: 2711.6. Samples: 86913248. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:39:28,446][86177] Avg episode reward: [(0, '-500.150'), (1, '-508.080')] -[2023-11-28 04:39:28,530][87426] Updated weights for policy 1, policy_version 169490 (0.0012) -[2023-11-28 04:39:28,628][87424] Updated weights for policy 0, policy_version 169967 (0.0012) -[2023-11-28 04:39:28,895][87426] Updated weights for policy 1, policy_version 169500 (0.0011) -[2023-11-28 04:39:29,018][87424] Updated weights for policy 0, policy_version 169977 (0.0012) -[2023-11-28 04:39:30,891][87426] Updated weights for policy 1, policy_version 169510 (0.0008) -[2023-11-28 04:39:31,204][87424] Updated weights for policy 0, policy_version 169987 (0.0011) -[2023-11-28 04:39:31,276][87426] Updated weights for policy 1, policy_version 169520 (0.0008) -[2023-11-28 04:39:31,584][87424] Updated weights for policy 0, policy_version 169997 (0.0010) -[2023-11-28 04:39:31,651][87426] Updated weights for policy 1, policy_version 169530 (0.0011) -[2023-11-28 04:39:31,973][87424] Updated weights for policy 0, policy_version 170007 (0.0009) -[2023-11-28 04:39:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86925312. Throughput: 0: 2754.4, 1: 2683.6. Samples: 86937596. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:39:33,446][86177] Avg episode reward: [(0, '-493.270'), (1, '-505.500')] -[2023-11-28 04:39:33,927][87424] Updated weights for policy 0, policy_version 170017 (0.0009) -[2023-11-28 04:39:34,072][87426] Updated weights for policy 1, policy_version 169540 (0.0011) -[2023-11-28 04:39:34,310][87424] Updated weights for policy 0, policy_version 170027 (0.0012) -[2023-11-28 04:39:34,459][87426] Updated weights for policy 1, policy_version 169550 (0.0007) -[2023-11-28 04:39:34,686][87424] Updated weights for policy 0, policy_version 170037 (0.0011) -[2023-11-28 04:39:34,836][87426] Updated weights for policy 1, policy_version 169560 (0.0009) -[2023-11-28 04:39:35,069][87424] Updated weights for policy 0, policy_version 170047 (0.0012) -[2023-11-28 04:39:36,728][87426] Updated weights for policy 1, policy_version 169570 (0.0011) -[2023-11-28 04:39:37,098][87426] Updated weights for policy 1, policy_version 169580 (0.0011) -[2023-11-28 04:39:37,369][87424] Updated weights for policy 0, policy_version 170057 (0.0011) -[2023-11-28 04:39:37,481][87426] Updated weights for policy 1, policy_version 169590 (0.0011) -[2023-11-28 04:39:37,748][87424] Updated weights for policy 0, policy_version 170067 (0.0010) -[2023-11-28 04:39:37,851][87426] Updated weights for policy 1, policy_version 169600 (0.0010) -[2023-11-28 04:39:38,131][87424] Updated weights for policy 0, policy_version 170077 (0.0011) -[2023-11-28 04:39:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 86958080. Throughput: 0: 2733.1, 1: 2677.3. Samples: 86969816. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:39:38,446][86177] Avg episode reward: [(0, '-498.270'), (1, '-512.990')] -[2023-11-28 04:39:39,793][87426] Updated weights for policy 1, policy_version 169610 (0.0012) -[2023-11-28 04:39:40,168][87426] Updated weights for policy 1, policy_version 169620 (0.0009) -[2023-11-28 04:39:40,544][87426] Updated weights for policy 1, policy_version 169630 (0.0009) -[2023-11-28 04:39:40,733][87424] Updated weights for policy 0, policy_version 170087 (0.0012) -[2023-11-28 04:39:41,111][87424] Updated weights for policy 0, policy_version 170097 (0.0012) -[2023-11-28 04:39:41,508][87424] Updated weights for policy 0, policy_version 170107 (0.0012) -[2023-11-28 04:39:42,594][87426] Updated weights for policy 1, policy_version 169640 (0.0012) -[2023-11-28 04:39:42,968][87426] Updated weights for policy 1, policy_version 169650 (0.0011) -[2023-11-28 04:39:43,349][87426] Updated weights for policy 1, policy_version 169660 (0.0012) -[2023-11-28 04:39:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 86974464. Throughput: 0: 2730.5, 1: 2710.9. Samples: 86994836. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:39:43,445][86177] Avg episode reward: [(0, '-496.280'), (1, '-509.400')] -[2023-11-28 04:39:44,053][87424] Updated weights for policy 0, policy_version 170117 (0.0012) -[2023-11-28 04:39:44,426][87424] Updated weights for policy 0, policy_version 170127 (0.0012) -[2023-11-28 04:39:44,809][87424] Updated weights for policy 0, policy_version 170137 (0.0012) -[2023-11-28 04:39:45,138][87426] Updated weights for policy 1, policy_version 169670 (0.0011) -[2023-11-28 04:39:45,517][87426] Updated weights for policy 1, policy_version 169680 (0.0011) -[2023-11-28 04:39:45,898][87426] Updated weights for policy 1, policy_version 169690 (0.0009) -[2023-11-28 04:39:47,240][87424] Updated weights for policy 0, policy_version 170147 (0.0011) -[2023-11-28 04:39:47,618][87424] Updated weights for policy 0, policy_version 170157 (0.0007) -[2023-11-28 04:39:47,700][87426] Updated weights for policy 1, policy_version 169700 (0.0009) -[2023-11-28 04:39:48,003][87424] Updated weights for policy 0, policy_version 170167 (0.0011) -[2023-11-28 04:39:48,078][87426] Updated weights for policy 1, policy_version 169710 (0.0008) -[2023-11-28 04:39:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 87007232. Throughput: 0: 2715.8, 1: 2747.6. Samples: 87019324. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:39:48,445][86177] Avg episode reward: [(0, '-493.910'), (1, '-510.500')] -[2023-11-28 04:39:48,451][87426] Updated weights for policy 1, policy_version 169720 (0.0007) -[2023-11-28 04:39:50,363][87424] Updated weights for policy 0, policy_version 170177 (0.0008) -[2023-11-28 04:39:50,741][87424] Updated weights for policy 0, policy_version 170187 (0.0009) -[2023-11-28 04:39:50,876][87426] Updated weights for policy 1, policy_version 169730 (0.0007) -[2023-11-28 04:39:51,119][87424] Updated weights for policy 0, policy_version 170197 (0.0008) -[2023-11-28 04:39:51,255][87426] Updated weights for policy 1, policy_version 169740 (0.0008) -[2023-11-28 04:39:51,498][87424] Updated weights for policy 0, policy_version 170207 (0.0011) -[2023-11-28 04:39:51,643][87426] Updated weights for policy 1, policy_version 169750 (0.0009) -[2023-11-28 04:39:52,033][87426] Updated weights for policy 1, policy_version 169760 (0.0010) -[2023-11-28 04:39:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 87031808. Throughput: 0: 2683.5, 1: 2766.1. Samples: 87051184. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:39:53,445][86177] Avg episode reward: [(0, '-495.010'), (1, '-515.820')] -[2023-11-28 04:39:53,907][87424] Updated weights for policy 0, policy_version 170217 (0.0009) -[2023-11-28 04:39:54,294][87424] Updated weights for policy 0, policy_version 170227 (0.0009) -[2023-11-28 04:39:54,428][87426] Updated weights for policy 1, policy_version 169770 (0.0010) -[2023-11-28 04:39:54,682][87424] Updated weights for policy 0, policy_version 170237 (0.0008) -[2023-11-28 04:39:54,802][87426] Updated weights for policy 1, policy_version 169780 (0.0012) -[2023-11-28 04:39:55,183][87426] Updated weights for policy 1, policy_version 169790 (0.0012) -[2023-11-28 04:39:56,484][87424] Updated weights for policy 0, policy_version 170247 (0.0010) -[2023-11-28 04:39:56,867][87424] Updated weights for policy 0, policy_version 170257 (0.0012) -[2023-11-28 04:39:57,241][87424] Updated weights for policy 0, policy_version 170267 (0.0010) -[2023-11-28 04:39:57,261][87426] Updated weights for policy 1, policy_version 169800 (0.0012) -[2023-11-28 04:39:57,641][87426] Updated weights for policy 1, policy_version 169810 (0.0009) -[2023-11-28 04:39:58,020][87426] Updated weights for policy 1, policy_version 169820 (0.0007) -[2023-11-28 04:39:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 87064576. Throughput: 0: 2682.1, 1: 2772.9. Samples: 87075308. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:39:58,445][86177] Avg episode reward: [(0, '-490.000'), (1, '-513.600')] -[2023-11-28 04:39:59,237][87424] Updated weights for policy 0, policy_version 170277 (0.0009) -[2023-11-28 04:39:59,607][87424] Updated weights for policy 0, policy_version 170287 (0.0008) -[2023-11-28 04:39:59,991][87424] Updated weights for policy 0, policy_version 170297 (0.0011) -[2023-11-28 04:40:00,533][87426] Updated weights for policy 1, policy_version 169830 (0.0010) -[2023-11-28 04:40:00,918][87426] Updated weights for policy 1, policy_version 169840 (0.0012) -[2023-11-28 04:40:01,301][87426] Updated weights for policy 1, policy_version 169850 (0.0012) -[2023-11-28 04:40:02,493][87424] Updated weights for policy 0, policy_version 170307 (0.0011) -[2023-11-28 04:40:02,871][87424] Updated weights for policy 0, policy_version 170317 (0.0012) -[2023-11-28 04:40:03,262][87424] Updated weights for policy 0, policy_version 170327 (0.0009) -[2023-11-28 04:40:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 87080960. Throughput: 0: 2684.2, 1: 2747.6. Samples: 87099164. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:40:03,445][86177] Avg episode reward: [(0, '-492.760'), (1, '-515.480')] -[2023-11-28 04:40:03,738][87426] Updated weights for policy 1, policy_version 169860 (0.0009) -[2023-11-28 04:40:04,122][87426] Updated weights for policy 1, policy_version 169870 (0.0009) -[2023-11-28 04:40:04,504][87426] Updated weights for policy 1, policy_version 169880 (0.0010) -[2023-11-28 04:40:05,406][87424] Updated weights for policy 0, policy_version 170337 (0.0010) -[2023-11-28 04:40:05,792][87424] Updated weights for policy 0, policy_version 170347 (0.0008) -[2023-11-28 04:40:06,177][87424] Updated weights for policy 0, policy_version 170357 (0.0007) -[2023-11-28 04:40:06,573][87424] Updated weights for policy 0, policy_version 170367 (0.0007) -[2023-11-28 04:40:06,944][87426] Updated weights for policy 1, policy_version 169890 (0.0008) -[2023-11-28 04:40:07,322][87426] Updated weights for policy 1, policy_version 169900 (0.0009) -[2023-11-28 04:40:07,705][87426] Updated weights for policy 1, policy_version 169910 (0.0007) -[2023-11-28 04:40:08,083][87426] Updated weights for policy 1, policy_version 169920 (0.0007) -[2023-11-28 04:40:08,270][87424] Updated weights for policy 0, policy_version 170377 (0.0008) -[2023-11-28 04:40:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 87113728. Throughput: 0: 2684.6, 1: 2737.2. Samples: 87131064. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:40:08,445][86177] Avg episode reward: [(0, '-492.880'), (1, '-517.580')] -[2023-11-28 04:40:08,656][87424] Updated weights for policy 0, policy_version 170387 (0.0009) -[2023-11-28 04:40:09,045][87424] Updated weights for policy 0, policy_version 170397 (0.0010) -[2023-11-28 04:40:09,977][87426] Updated weights for policy 1, policy_version 169930 (0.0010) -[2023-11-28 04:40:10,356][87426] Updated weights for policy 1, policy_version 169940 (0.0010) -[2023-11-28 04:40:10,732][87426] Updated weights for policy 1, policy_version 169950 (0.0012) -[2023-11-28 04:40:11,027][87424] Updated weights for policy 0, policy_version 170407 (0.0009) -[2023-11-28 04:40:11,411][87424] Updated weights for policy 0, policy_version 170417 (0.0007) -[2023-11-28 04:40:11,809][87424] Updated weights for policy 0, policy_version 170427 (0.0008) -[2023-11-28 04:40:12,960][87426] Updated weights for policy 1, policy_version 169960 (0.0010) -[2023-11-28 04:40:13,354][87426] Updated weights for policy 1, policy_version 169970 (0.0008) -[2023-11-28 04:40:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 87138304. Throughput: 0: 2669.3, 1: 2718.9. Samples: 87155720. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:40:13,445][86177] Avg episode reward: [(0, '-493.390'), (1, '-516.550')] -[2023-11-28 04:40:13,731][87426] Updated weights for policy 1, policy_version 169980 (0.0008) -[2023-11-28 04:40:14,235][87424] Updated weights for policy 0, policy_version 170437 (0.0011) -[2023-11-28 04:40:14,613][87424] Updated weights for policy 0, policy_version 170447 (0.0012) -[2023-11-28 04:40:15,001][87424] Updated weights for policy 0, policy_version 170457 (0.0009) -[2023-11-28 04:40:16,161][87426] Updated weights for policy 1, policy_version 169990 (0.0010) -[2023-11-28 04:40:16,540][87426] Updated weights for policy 1, policy_version 170000 (0.0010) -[2023-11-28 04:40:16,926][87426] Updated weights for policy 1, policy_version 170010 (0.0007) -[2023-11-28 04:40:17,423][87424] Updated weights for policy 0, policy_version 170467 (0.0008) -[2023-11-28 04:40:17,809][87424] Updated weights for policy 0, policy_version 170477 (0.0007) -[2023-11-28 04:40:18,191][87424] Updated weights for policy 0, policy_version 170487 (0.0008) -[2023-11-28 04:40:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 87162880. Throughput: 0: 2650.5, 1: 2724.7. Samples: 87179480. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:40:18,445][86177] Avg episode reward: [(0, '-493.540'), (1, '-509.890')] -[2023-11-28 04:40:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000170016_43524096.pth... -[2023-11-28 04:40:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000167488_42876928.pth -[2023-11-28 04:40:18,529][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000170496_43646976.pth... -[2023-11-28 04:40:18,568][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000167936_42991616.pth -[2023-11-28 04:40:18,792][87426] Updated weights for policy 1, policy_version 170020 (0.0009) -[2023-11-28 04:40:19,158][87426] Updated weights for policy 1, policy_version 170030 (0.0011) -[2023-11-28 04:40:19,538][87426] Updated weights for policy 1, policy_version 170040 (0.0011) -[2023-11-28 04:40:20,357][87424] Updated weights for policy 0, policy_version 170497 (0.0009) -[2023-11-28 04:40:20,746][87424] Updated weights for policy 0, policy_version 170507 (0.0010) -[2023-11-28 04:40:21,131][87424] Updated weights for policy 0, policy_version 170517 (0.0010) -[2023-11-28 04:40:21,513][87424] Updated weights for policy 0, policy_version 170527 (0.0009) -[2023-11-28 04:40:21,953][87426] Updated weights for policy 1, policy_version 170050 (0.0011) -[2023-11-28 04:40:22,339][87426] Updated weights for policy 1, policy_version 170060 (0.0010) -[2023-11-28 04:40:22,712][87426] Updated weights for policy 1, policy_version 170070 (0.0011) -[2023-11-28 04:40:23,093][87426] Updated weights for policy 1, policy_version 170080 (0.0010) -[2023-11-28 04:40:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 87195648. Throughput: 0: 2645.3, 1: 2742.7. Samples: 87212272. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:40:23,445][86177] Avg episode reward: [(0, '-492.000'), (1, '-512.820')] -[2023-11-28 04:40:23,855][87424] Updated weights for policy 0, policy_version 170537 (0.0011) -[2023-11-28 04:40:24,231][87424] Updated weights for policy 0, policy_version 170547 (0.0012) -[2023-11-28 04:40:24,611][87424] Updated weights for policy 0, policy_version 170557 (0.0011) -[2023-11-28 04:40:25,041][87426] Updated weights for policy 1, policy_version 170090 (0.0011) -[2023-11-28 04:40:25,422][87426] Updated weights for policy 1, policy_version 170100 (0.0009) -[2023-11-28 04:40:25,818][87426] Updated weights for policy 1, policy_version 170110 (0.0007) -[2023-11-28 04:40:27,107][87424] Updated weights for policy 0, policy_version 170567 (0.0009) -[2023-11-28 04:40:27,492][87424] Updated weights for policy 0, policy_version 170577 (0.0007) -[2023-11-28 04:40:27,874][87424] Updated weights for policy 0, policy_version 170587 (0.0007) -[2023-11-28 04:40:28,165][87426] Updated weights for policy 1, policy_version 170120 (0.0010) -[2023-11-28 04:40:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 87220224. Throughput: 0: 2645.6, 1: 2724.4. Samples: 87236488. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:40:28,445][86177] Avg episode reward: [(0, '-496.490'), (1, '-506.500')] -[2023-11-28 04:40:28,550][87426] Updated weights for policy 1, policy_version 170130 (0.0008) -[2023-11-28 04:40:28,945][87426] Updated weights for policy 1, policy_version 170140 (0.0008) -[2023-11-28 04:40:29,595][87424] Updated weights for policy 0, policy_version 170597 (0.0009) -[2023-11-28 04:40:29,973][87424] Updated weights for policy 0, policy_version 170607 (0.0011) -[2023-11-28 04:40:30,359][87424] Updated weights for policy 0, policy_version 170617 (0.0009) -[2023-11-28 04:40:31,145][87426] Updated weights for policy 1, policy_version 170150 (0.0010) -[2023-11-28 04:40:31,522][87426] Updated weights for policy 1, policy_version 170160 (0.0011) -[2023-11-28 04:40:31,900][87426] Updated weights for policy 1, policy_version 170170 (0.0011) -[2023-11-28 04:40:32,734][87424] Updated weights for policy 0, policy_version 170627 (0.0008) -[2023-11-28 04:40:33,117][87424] Updated weights for policy 0, policy_version 170637 (0.0010) -[2023-11-28 04:40:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 87244800. Throughput: 0: 2657.2, 1: 2691.5. Samples: 87260020. Policy #0 lag: (min: 15.0, avg: 30.3, max: 47.0) -[2023-11-28 04:40:33,445][86177] Avg episode reward: [(0, '-496.920'), (1, '-497.020')] -[2023-11-28 04:40:33,497][87424] Updated weights for policy 0, policy_version 170647 (0.0009) -[2023-11-28 04:40:34,469][87426] Updated weights for policy 1, policy_version 170180 (0.0009) -[2023-11-28 04:40:34,845][87426] Updated weights for policy 1, policy_version 170190 (0.0008) -[2023-11-28 04:40:35,232][87426] Updated weights for policy 1, policy_version 170200 (0.0008) -[2023-11-28 04:40:36,024][87424] Updated weights for policy 0, policy_version 170657 (0.0008) -[2023-11-28 04:40:36,408][87424] Updated weights for policy 0, policy_version 170667 (0.0008) -[2023-11-28 04:40:36,789][87424] Updated weights for policy 0, policy_version 170677 (0.0008) -[2023-11-28 04:40:37,169][87424] Updated weights for policy 0, policy_version 170687 (0.0011) -[2023-11-28 04:40:37,364][87426] Updated weights for policy 1, policy_version 170210 (0.0008) -[2023-11-28 04:40:37,744][87426] Updated weights for policy 1, policy_version 170220 (0.0007) -[2023-11-28 04:40:38,122][87426] Updated weights for policy 1, policy_version 170230 (0.0007) -[2023-11-28 04:40:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 87269376. Throughput: 0: 2665.8, 1: 2663.6. Samples: 87291004. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:40:38,445][86177] Avg episode reward: [(0, '-499.070'), (1, '-502.980')] -[2023-11-28 04:40:38,503][87426] Updated weights for policy 1, policy_version 170240 (0.0008) -[2023-11-28 04:40:39,623][87424] Updated weights for policy 0, policy_version 170697 (0.0011) -[2023-11-28 04:40:40,012][87424] Updated weights for policy 0, policy_version 170707 (0.0010) -[2023-11-28 04:40:40,392][87424] Updated weights for policy 0, policy_version 170717 (0.0011) -[2023-11-28 04:40:41,012][87426] Updated weights for policy 1, policy_version 170250 (0.0007) -[2023-11-28 04:40:41,391][87426] Updated weights for policy 1, policy_version 170260 (0.0007) -[2023-11-28 04:40:41,785][87426] Updated weights for policy 1, policy_version 170270 (0.0010) -[2023-11-28 04:40:42,497][87424] Updated weights for policy 0, policy_version 170727 (0.0011) -[2023-11-28 04:40:42,873][87424] Updated weights for policy 0, policy_version 170737 (0.0012) -[2023-11-28 04:40:43,266][87424] Updated weights for policy 0, policy_version 170747 (0.0012) -[2023-11-28 04:40:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 87293952. Throughput: 0: 2645.4, 1: 2670.9. Samples: 87314540. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:40:43,445][86177] Avg episode reward: [(0, '-494.120'), (1, '-501.490')] -[2023-11-28 04:40:43,866][87426] Updated weights for policy 1, policy_version 170280 (0.0012) -[2023-11-28 04:40:44,245][87426] Updated weights for policy 1, policy_version 170290 (0.0009) -[2023-11-28 04:40:44,626][87426] Updated weights for policy 1, policy_version 170300 (0.0007) -[2023-11-28 04:40:45,864][87424] Updated weights for policy 0, policy_version 170757 (0.0011) -[2023-11-28 04:40:46,245][87424] Updated weights for policy 0, policy_version 170767 (0.0009) -[2023-11-28 04:40:46,628][87424] Updated weights for policy 0, policy_version 170777 (0.0008) -[2023-11-28 04:40:46,887][87426] Updated weights for policy 1, policy_version 170310 (0.0010) -[2023-11-28 04:40:47,273][87426] Updated weights for policy 1, policy_version 170320 (0.0012) -[2023-11-28 04:40:47,657][87426] Updated weights for policy 1, policy_version 170330 (0.0012) -[2023-11-28 04:40:48,291][87424] Updated weights for policy 0, policy_version 170787 (0.0008) -[2023-11-28 04:40:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 87326720. Throughput: 0: 2644.2, 1: 2683.2. Samples: 87338896. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:40:48,445][86177] Avg episode reward: [(0, '-495.340'), (1, '-507.100')] -[2023-11-28 04:40:48,679][87424] Updated weights for policy 0, policy_version 170797 (0.0012) -[2023-11-28 04:40:49,065][87424] Updated weights for policy 0, policy_version 170807 (0.0012) -[2023-11-28 04:40:49,880][87426] Updated weights for policy 1, policy_version 170340 (0.0009) -[2023-11-28 04:40:50,258][87426] Updated weights for policy 1, policy_version 170350 (0.0008) -[2023-11-28 04:40:50,639][87426] Updated weights for policy 1, policy_version 170360 (0.0008) -[2023-11-28 04:40:51,277][87424] Updated weights for policy 0, policy_version 170817 (0.0012) -[2023-11-28 04:40:51,656][87424] Updated weights for policy 0, policy_version 170827 (0.0011) -[2023-11-28 04:40:52,041][87424] Updated weights for policy 0, policy_version 170837 (0.0011) -[2023-11-28 04:40:52,425][87424] Updated weights for policy 0, policy_version 170847 (0.0011) -[2023-11-28 04:40:53,077][87426] Updated weights for policy 1, policy_version 170370 (0.0007) -[2023-11-28 04:40:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 87351296. Throughput: 0: 2631.0, 1: 2682.9. Samples: 87370192. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:40:53,445][86177] Avg episode reward: [(0, '-496.350'), (1, '-508.700')] -[2023-11-28 04:40:53,454][87426] Updated weights for policy 1, policy_version 170380 (0.0010) -[2023-11-28 04:40:53,830][87426] Updated weights for policy 1, policy_version 170390 (0.0012) -[2023-11-28 04:40:54,208][87426] Updated weights for policy 1, policy_version 170400 (0.0010) -[2023-11-28 04:40:54,898][87424] Updated weights for policy 0, policy_version 170857 (0.0011) -[2023-11-28 04:40:55,281][87424] Updated weights for policy 0, policy_version 170867 (0.0009) -[2023-11-28 04:40:55,664][87424] Updated weights for policy 0, policy_version 170877 (0.0011) -[2023-11-28 04:40:56,373][87426] Updated weights for policy 1, policy_version 170410 (0.0007) -[2023-11-28 04:40:56,756][87426] Updated weights for policy 1, policy_version 170420 (0.0008) -[2023-11-28 04:40:57,131][87426] Updated weights for policy 1, policy_version 170430 (0.0008) -[2023-11-28 04:40:57,770][87424] Updated weights for policy 0, policy_version 170887 (0.0011) -[2023-11-28 04:40:58,153][87424] Updated weights for policy 0, policy_version 170897 (0.0012) -[2023-11-28 04:40:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 87375872. Throughput: 0: 2630.6, 1: 2675.1. Samples: 87394476. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:40:58,446][86177] Avg episode reward: [(0, '-495.600'), (1, '-512.420')] -[2023-11-28 04:40:58,532][87424] Updated weights for policy 0, policy_version 170907 (0.0012) -[2023-11-28 04:40:58,883][87426] Updated weights for policy 1, policy_version 170440 (0.0010) -[2023-11-28 04:40:59,258][87426] Updated weights for policy 1, policy_version 170450 (0.0007) -[2023-11-28 04:40:59,634][87426] Updated weights for policy 1, policy_version 170460 (0.0007) -[2023-11-28 04:41:00,498][87424] Updated weights for policy 0, policy_version 170917 (0.0010) -[2023-11-28 04:41:00,887][87424] Updated weights for policy 0, policy_version 170927 (0.0008) -[2023-11-28 04:41:01,270][87424] Updated weights for policy 0, policy_version 170937 (0.0007) -[2023-11-28 04:41:01,647][87426] Updated weights for policy 1, policy_version 170470 (0.0014) -[2023-11-28 04:41:02,014][87426] Updated weights for policy 1, policy_version 170480 (0.0012) -[2023-11-28 04:41:02,391][87426] Updated weights for policy 1, policy_version 170490 (0.0011) -[2023-11-28 04:41:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 87408640. Throughput: 0: 2639.5, 1: 2680.4. Samples: 87418872. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:41:03,445][86177] Avg episode reward: [(0, '-497.910'), (1, '-539.660')] -[2023-11-28 04:41:03,621][87424] Updated weights for policy 0, policy_version 170947 (0.0009) -[2023-11-28 04:41:04,007][87424] Updated weights for policy 0, policy_version 170957 (0.0012) -[2023-11-28 04:41:04,337][87426] Updated weights for policy 1, policy_version 170500 (0.0011) -[2023-11-28 04:41:04,386][87424] Updated weights for policy 0, policy_version 170967 (0.0011) -[2023-11-28 04:41:04,712][87426] Updated weights for policy 1, policy_version 170510 (0.0012) -[2023-11-28 04:41:05,094][87426] Updated weights for policy 1, policy_version 170520 (0.0012) -[2023-11-28 04:41:06,593][87424] Updated weights for policy 0, policy_version 170977 (0.0011) -[2023-11-28 04:41:06,979][87424] Updated weights for policy 0, policy_version 170987 (0.0012) -[2023-11-28 04:41:07,357][87424] Updated weights for policy 0, policy_version 170997 (0.0012) -[2023-11-28 04:41:07,435][87426] Updated weights for policy 1, policy_version 170530 (0.0012) -[2023-11-28 04:41:07,745][87424] Updated weights for policy 0, policy_version 171007 (0.0011) -[2023-11-28 04:41:07,823][87426] Updated weights for policy 1, policy_version 170540 (0.0012) -[2023-11-28 04:41:08,191][87426] Updated weights for policy 1, policy_version 170550 (0.0011) -[2023-11-28 04:41:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 87433216. Throughput: 0: 2651.9, 1: 2675.9. Samples: 87452024. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:41:08,445][86177] Avg episode reward: [(0, '-498.730'), (1, '-551.180')] -[2023-11-28 04:41:08,573][87426] Updated weights for policy 1, policy_version 170560 (0.0011) -[2023-11-28 04:41:09,805][87424] Updated weights for policy 0, policy_version 171017 (0.0008) -[2023-11-28 04:41:10,175][87424] Updated weights for policy 0, policy_version 171027 (0.0011) -[2023-11-28 04:41:10,563][87424] Updated weights for policy 0, policy_version 171037 (0.0011) -[2023-11-28 04:41:10,738][87426] Updated weights for policy 1, policy_version 170570 (0.0011) -[2023-11-28 04:41:11,117][87426] Updated weights for policy 1, policy_version 170580 (0.0011) -[2023-11-28 04:41:11,493][87426] Updated weights for policy 1, policy_version 170590 (0.0012) -[2023-11-28 04:41:12,506][87424] Updated weights for policy 0, policy_version 171047 (0.0010) -[2023-11-28 04:41:12,887][87424] Updated weights for policy 0, policy_version 171057 (0.0011) -[2023-11-28 04:41:13,282][87424] Updated weights for policy 0, policy_version 171067 (0.0009) -[2023-11-28 04:41:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 87457792. Throughput: 0: 2649.2, 1: 2659.5. Samples: 87475376. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:41:13,445][86177] Avg episode reward: [(0, '-493.920'), (1, '-559.140')] -[2023-11-28 04:41:13,869][87426] Updated weights for policy 1, policy_version 170600 (0.0008) -[2023-11-28 04:41:14,245][87426] Updated weights for policy 1, policy_version 170610 (0.0007) -[2023-11-28 04:41:14,629][87426] Updated weights for policy 1, policy_version 170620 (0.0007) -[2023-11-28 04:41:15,808][87424] Updated weights for policy 0, policy_version 171077 (0.0009) -[2023-11-28 04:41:16,184][87424] Updated weights for policy 0, policy_version 171087 (0.0007) -[2023-11-28 04:41:16,574][87424] Updated weights for policy 0, policy_version 171097 (0.0007) -[2023-11-28 04:41:17,076][87426] Updated weights for policy 1, policy_version 170630 (0.0009) -[2023-11-28 04:41:17,449][87426] Updated weights for policy 1, policy_version 170640 (0.0008) -[2023-11-28 04:41:17,822][87426] Updated weights for policy 1, policy_version 170650 (0.0009) -[2023-11-28 04:41:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 87490560. Throughput: 0: 2651.2, 1: 2654.8. Samples: 87498788. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:41:18,445][86177] Avg episode reward: [(0, '-492.530'), (1, '-565.930')] -[2023-11-28 04:41:18,990][87424] Updated weights for policy 0, policy_version 171107 (0.0009) -[2023-11-28 04:41:19,372][87424] Updated weights for policy 0, policy_version 171117 (0.0012) -[2023-11-28 04:41:19,751][87424] Updated weights for policy 0, policy_version 171127 (0.0012) -[2023-11-28 04:41:19,791][87426] Updated weights for policy 1, policy_version 170660 (0.0012) -[2023-11-28 04:41:20,167][87426] Updated weights for policy 1, policy_version 170670 (0.0011) -[2023-11-28 04:41:20,546][87426] Updated weights for policy 1, policy_version 170680 (0.0011) -[2023-11-28 04:41:21,966][87424] Updated weights for policy 0, policy_version 171137 (0.0011) -[2023-11-28 04:41:22,348][87424] Updated weights for policy 0, policy_version 171147 (0.0011) -[2023-11-28 04:41:22,734][87424] Updated weights for policy 0, policy_version 171157 (0.0011) -[2023-11-28 04:41:23,085][87426] Updated weights for policy 1, policy_version 170690 (0.0008) -[2023-11-28 04:41:23,117][87424] Updated weights for policy 0, policy_version 171167 (0.0009) -[2023-11-28 04:41:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 87515136. Throughput: 0: 2657.5, 1: 2663.4. Samples: 87530444. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:41:23,445][86177] Avg episode reward: [(0, '-493.010'), (1, '-544.650')] -[2023-11-28 04:41:23,465][87426] Updated weights for policy 1, policy_version 170700 (0.0008) -[2023-11-28 04:41:23,842][87426] Updated weights for policy 1, policy_version 170710 (0.0007) -[2023-11-28 04:41:24,223][87426] Updated weights for policy 1, policy_version 170720 (0.0009) -[2023-11-28 04:41:25,696][87424] Updated weights for policy 0, policy_version 171177 (0.0011) -[2023-11-28 04:41:26,086][87424] Updated weights for policy 0, policy_version 171187 (0.0012) -[2023-11-28 04:41:26,249][87426] Updated weights for policy 1, policy_version 170730 (0.0011) -[2023-11-28 04:41:26,462][87424] Updated weights for policy 0, policy_version 171197 (0.0011) -[2023-11-28 04:41:26,627][87426] Updated weights for policy 1, policy_version 170740 (0.0011) -[2023-11-28 04:41:27,008][87426] Updated weights for policy 1, policy_version 170750 (0.0011) -[2023-11-28 04:41:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 87539712. Throughput: 0: 2679.8, 1: 2698.6. Samples: 87556568. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:41:28,445][86177] Avg episode reward: [(0, '-492.620'), (1, '-526.110')] -[2023-11-28 04:41:28,744][87424] Updated weights for policy 0, policy_version 171207 (0.0010) -[2023-11-28 04:41:29,125][87424] Updated weights for policy 0, policy_version 171217 (0.0011) -[2023-11-28 04:41:29,506][87424] Updated weights for policy 0, policy_version 171227 (0.0012) -[2023-11-28 04:41:29,597][87426] Updated weights for policy 1, policy_version 170760 (0.0009) -[2023-11-28 04:41:29,962][87426] Updated weights for policy 1, policy_version 170770 (0.0010) -[2023-11-28 04:41:30,342][87426] Updated weights for policy 1, policy_version 170780 (0.0011) -[2023-11-28 04:41:31,341][87424] Updated weights for policy 0, policy_version 171237 (0.0012) -[2023-11-28 04:41:31,731][87424] Updated weights for policy 0, policy_version 171247 (0.0012) -[2023-11-28 04:41:32,114][87424] Updated weights for policy 0, policy_version 171257 (0.0012) -[2023-11-28 04:41:32,576][87426] Updated weights for policy 1, policy_version 170790 (0.0009) -[2023-11-28 04:41:32,965][87426] Updated weights for policy 1, policy_version 170800 (0.0009) -[2023-11-28 04:41:33,339][87426] Updated weights for policy 1, policy_version 170810 (0.0012) -[2023-11-28 04:41:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 87564288. Throughput: 0: 2703.5, 1: 2711.9. Samples: 87582588. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:41:33,445][86177] Avg episode reward: [(0, '-494.300'), (1, '-518.490')] -[2023-11-28 04:41:34,007][87424] Updated weights for policy 0, policy_version 171267 (0.0011) -[2023-11-28 04:41:34,385][87424] Updated weights for policy 0, policy_version 171277 (0.0008) -[2023-11-28 04:41:34,767][87424] Updated weights for policy 0, policy_version 171287 (0.0009) -[2023-11-28 04:41:35,133][87426] Updated weights for policy 1, policy_version 170820 (0.0011) -[2023-11-28 04:41:35,506][87426] Updated weights for policy 1, policy_version 170830 (0.0012) -[2023-11-28 04:41:35,868][87426] Updated weights for policy 1, policy_version 170840 (0.0012) -[2023-11-28 04:41:37,158][87424] Updated weights for policy 0, policy_version 171297 (0.0011) -[2023-11-28 04:41:37,542][87424] Updated weights for policy 0, policy_version 171307 (0.0012) -[2023-11-28 04:41:37,919][87424] Updated weights for policy 0, policy_version 171317 (0.0012) -[2023-11-28 04:41:38,060][87426] Updated weights for policy 1, policy_version 170850 (0.0011) -[2023-11-28 04:41:38,303][87424] Updated weights for policy 0, policy_version 171327 (0.0011) -[2023-11-28 04:41:38,444][87426] Updated weights for policy 1, policy_version 170860 (0.0008) -[2023-11-28 04:41:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 87597056. Throughput: 0: 2717.7, 1: 2718.3. Samples: 87614812. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 04:41:38,445][86177] Avg episode reward: [(0, '-495.460'), (1, '-512.870')] -[2023-11-28 04:41:38,815][87426] Updated weights for policy 1, policy_version 170870 (0.0007) -[2023-11-28 04:41:39,194][87426] Updated weights for policy 1, policy_version 170880 (0.0008) -[2023-11-28 04:41:40,281][87424] Updated weights for policy 0, policy_version 171337 (0.0011) -[2023-11-28 04:41:40,657][87424] Updated weights for policy 0, policy_version 171347 (0.0012) -[2023-11-28 04:41:41,034][87424] Updated weights for policy 0, policy_version 171357 (0.0010) -[2023-11-28 04:41:41,725][87426] Updated weights for policy 1, policy_version 170890 (0.0012) -[2023-11-28 04:41:42,111][87426] Updated weights for policy 1, policy_version 170900 (0.0012) -[2023-11-28 04:41:42,489][87426] Updated weights for policy 1, policy_version 170910 (0.0012) -[2023-11-28 04:41:42,975][87424] Updated weights for policy 0, policy_version 171367 (0.0009) -[2023-11-28 04:41:43,352][87424] Updated weights for policy 0, policy_version 171377 (0.0010) -[2023-11-28 04:41:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 87621632. Throughput: 0: 2719.8, 1: 2694.1. Samples: 87638104. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:41:43,445][86177] Avg episode reward: [(0, '-493.480'), (1, '-514.820')] -[2023-11-28 04:41:43,733][87424] Updated weights for policy 0, policy_version 171387 (0.0007) -[2023-11-28 04:41:44,493][87426] Updated weights for policy 1, policy_version 170920 (0.0012) -[2023-11-28 04:41:44,873][87426] Updated weights for policy 1, policy_version 170930 (0.0007) -[2023-11-28 04:41:45,264][87426] Updated weights for policy 1, policy_version 170940 (0.0008) -[2023-11-28 04:41:46,232][87424] Updated weights for policy 0, policy_version 171397 (0.0007) -[2023-11-28 04:41:46,617][87424] Updated weights for policy 0, policy_version 171407 (0.0007) -[2023-11-28 04:41:47,001][87424] Updated weights for policy 0, policy_version 171417 (0.0007) -[2023-11-28 04:41:47,638][87426] Updated weights for policy 1, policy_version 170950 (0.0010) -[2023-11-28 04:41:48,009][87426] Updated weights for policy 1, policy_version 170960 (0.0012) -[2023-11-28 04:41:48,388][87426] Updated weights for policy 1, policy_version 170970 (0.0012) -[2023-11-28 04:41:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 87646208. Throughput: 0: 2702.6, 1: 2696.2. Samples: 87661816. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:41:48,445][86177] Avg episode reward: [(0, '-497.520'), (1, '-519.430')] -[2023-11-28 04:41:49,184][87424] Updated weights for policy 0, policy_version 171427 (0.0008) -[2023-11-28 04:41:49,570][87424] Updated weights for policy 0, policy_version 171437 (0.0008) -[2023-11-28 04:41:49,953][87424] Updated weights for policy 0, policy_version 171447 (0.0009) -[2023-11-28 04:41:50,393][87426] Updated weights for policy 1, policy_version 170980 (0.0011) -[2023-11-28 04:41:50,773][87426] Updated weights for policy 1, policy_version 170990 (0.0012) -[2023-11-28 04:41:51,146][87426] Updated weights for policy 1, policy_version 171000 (0.0011) -[2023-11-28 04:41:52,434][87424] Updated weights for policy 0, policy_version 171457 (0.0011) -[2023-11-28 04:41:52,826][87424] Updated weights for policy 0, policy_version 171467 (0.0012) -[2023-11-28 04:41:53,206][87424] Updated weights for policy 0, policy_version 171477 (0.0012) -[2023-11-28 04:41:53,425][87426] Updated weights for policy 1, policy_version 171010 (0.0011) -[2023-11-28 04:41:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 87670784. Throughput: 0: 2698.8, 1: 2672.8. Samples: 87693744. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:41:53,445][86177] Avg episode reward: [(0, '-494.300'), (1, '-512.010')] -[2023-11-28 04:41:53,586][87424] Updated weights for policy 0, policy_version 171487 (0.0012) -[2023-11-28 04:41:53,805][87426] Updated weights for policy 1, policy_version 171020 (0.0011) -[2023-11-28 04:41:54,183][87426] Updated weights for policy 1, policy_version 171030 (0.0012) -[2023-11-28 04:41:54,560][87426] Updated weights for policy 1, policy_version 171040 (0.0012) -[2023-11-28 04:41:55,508][87424] Updated weights for policy 0, policy_version 171497 (0.0012) -[2023-11-28 04:41:55,904][87424] Updated weights for policy 0, policy_version 171507 (0.0011) -[2023-11-28 04:41:56,280][87424] Updated weights for policy 0, policy_version 171517 (0.0012) -[2023-11-28 04:41:56,860][87426] Updated weights for policy 1, policy_version 171050 (0.0011) -[2023-11-28 04:41:57,255][87426] Updated weights for policy 1, policy_version 171060 (0.0007) -[2023-11-28 04:41:57,644][87426] Updated weights for policy 1, policy_version 171070 (0.0007) -[2023-11-28 04:41:58,442][87424] Updated weights for policy 0, policy_version 171527 (0.0012) -[2023-11-28 04:41:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 87703552. Throughput: 0: 2717.7, 1: 2666.1. Samples: 87717648. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:41:58,445][86177] Avg episode reward: [(0, '-491.500'), (1, '-515.170')] -[2023-11-28 04:41:58,816][87424] Updated weights for policy 0, policy_version 171537 (0.0011) -[2023-11-28 04:41:59,201][87424] Updated weights for policy 0, policy_version 171547 (0.0012) -[2023-11-28 04:41:59,747][87426] Updated weights for policy 1, policy_version 171080 (0.0008) -[2023-11-28 04:42:00,123][87426] Updated weights for policy 1, policy_version 171090 (0.0011) -[2023-11-28 04:42:00,506][87426] Updated weights for policy 1, policy_version 171100 (0.0010) -[2023-11-28 04:42:01,273][87424] Updated weights for policy 0, policy_version 171557 (0.0009) -[2023-11-28 04:42:01,656][87424] Updated weights for policy 0, policy_version 171567 (0.0009) -[2023-11-28 04:42:02,040][87424] Updated weights for policy 0, policy_version 171577 (0.0012) -[2023-11-28 04:42:02,479][87426] Updated weights for policy 1, policy_version 171110 (0.0011) -[2023-11-28 04:42:02,861][87426] Updated weights for policy 1, policy_version 171120 (0.0012) -[2023-11-28 04:42:03,233][87426] Updated weights for policy 1, policy_version 171130 (0.0012) -[2023-11-28 04:42:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 87728128. Throughput: 0: 2715.5, 1: 2687.4. Samples: 87741916. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:42:03,445][86177] Avg episode reward: [(0, '-492.510'), (1, '-516.850')] -[2023-11-28 04:42:04,470][87424] Updated weights for policy 0, policy_version 171587 (0.0010) -[2023-11-28 04:42:04,851][87424] Updated weights for policy 0, policy_version 171597 (0.0012) -[2023-11-28 04:42:05,234][87424] Updated weights for policy 0, policy_version 171607 (0.0012) -[2023-11-28 04:42:05,358][87426] Updated weights for policy 1, policy_version 171140 (0.0010) -[2023-11-28 04:42:05,735][87426] Updated weights for policy 1, policy_version 171150 (0.0008) -[2023-11-28 04:42:06,109][87426] Updated weights for policy 1, policy_version 171160 (0.0012) -[2023-11-28 04:42:06,978][87424] Updated weights for policy 0, policy_version 171617 (0.0011) -[2023-11-28 04:42:07,359][87424] Updated weights for policy 0, policy_version 171627 (0.0009) -[2023-11-28 04:42:07,742][87424] Updated weights for policy 0, policy_version 171637 (0.0011) -[2023-11-28 04:42:08,037][87426] Updated weights for policy 1, policy_version 171170 (0.0011) -[2023-11-28 04:42:08,128][87424] Updated weights for policy 0, policy_version 171647 (0.0012) -[2023-11-28 04:42:08,424][87426] Updated weights for policy 1, policy_version 171180 (0.0007) -[2023-11-28 04:42:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 87760896. Throughput: 0: 2730.8, 1: 2715.1. Samples: 87775512. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:42:08,445][86177] Avg episode reward: [(0, '-492.140'), (1, '-512.870')] -[2023-11-28 04:42:08,802][87426] Updated weights for policy 1, policy_version 171190 (0.0007) -[2023-11-28 04:42:09,181][87426] Updated weights for policy 1, policy_version 171200 (0.0008) -[2023-11-28 04:42:10,058][87424] Updated weights for policy 0, policy_version 171657 (0.0010) -[2023-11-28 04:42:10,436][87424] Updated weights for policy 0, policy_version 171667 (0.0013) -[2023-11-28 04:42:10,831][87424] Updated weights for policy 0, policy_version 171677 (0.0009) -[2023-11-28 04:42:11,565][87426] Updated weights for policy 1, policy_version 171210 (0.0012) -[2023-11-28 04:42:11,943][87426] Updated weights for policy 1, policy_version 171220 (0.0011) -[2023-11-28 04:42:12,329][87426] Updated weights for policy 1, policy_version 171230 (0.0012) -[2023-11-28 04:42:13,342][87424] Updated weights for policy 0, policy_version 171687 (0.0010) -[2023-11-28 04:42:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 87785472. Throughput: 0: 2726.9, 1: 2677.8. Samples: 87799780. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:42:13,446][86177] Avg episode reward: [(0, '-492.140'), (1, '-514.620')] -[2023-11-28 04:42:13,721][87424] Updated weights for policy 0, policy_version 171697 (0.0012) -[2023-11-28 04:42:14,108][87424] Updated weights for policy 0, policy_version 171707 (0.0012) -[2023-11-28 04:42:14,667][87426] Updated weights for policy 1, policy_version 171240 (0.0012) -[2023-11-28 04:42:15,036][87426] Updated weights for policy 1, policy_version 171250 (0.0009) -[2023-11-28 04:42:15,410][87426] Updated weights for policy 1, policy_version 171260 (0.0008) -[2023-11-28 04:42:16,352][87424] Updated weights for policy 0, policy_version 171717 (0.0011) -[2023-11-28 04:42:16,730][87424] Updated weights for policy 0, policy_version 171727 (0.0011) -[2023-11-28 04:42:17,118][87424] Updated weights for policy 0, policy_version 171737 (0.0011) -[2023-11-28 04:42:17,811][87426] Updated weights for policy 1, policy_version 171270 (0.0007) -[2023-11-28 04:42:18,194][87426] Updated weights for policy 1, policy_version 171280 (0.0007) -[2023-11-28 04:42:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 87810048. Throughput: 0: 2700.1, 1: 2668.8. Samples: 87824188. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:42:18,445][86177] Avg episode reward: [(0, '-489.040'), (1, '-509.340')] -[2023-11-28 04:42:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000171744_43966464.pth... -[2023-11-28 04:42:18,493][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000169216_43319296.pth -[2023-11-28 04:42:18,573][87426] Updated weights for policy 1, policy_version 171290 (0.0007) -[2023-11-28 04:42:18,797][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000171296_43851776.pth... -[2023-11-28 04:42:18,844][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000168768_43204608.pth -[2023-11-28 04:42:19,033][87424] Updated weights for policy 0, policy_version 171747 (0.0012) -[2023-11-28 04:42:19,423][87424] Updated weights for policy 0, policy_version 171757 (0.0012) -[2023-11-28 04:42:19,798][87424] Updated weights for policy 0, policy_version 171767 (0.0012) -[2023-11-28 04:42:20,342][87426] Updated weights for policy 1, policy_version 171300 (0.0009) -[2023-11-28 04:42:20,721][87426] Updated weights for policy 1, policy_version 171310 (0.0010) -[2023-11-28 04:42:21,104][87426] Updated weights for policy 1, policy_version 171320 (0.0011) -[2023-11-28 04:42:21,913][87424] Updated weights for policy 0, policy_version 171777 (0.0012) -[2023-11-28 04:42:22,283][87424] Updated weights for policy 0, policy_version 171787 (0.0012) -[2023-11-28 04:42:22,664][87424] Updated weights for policy 0, policy_version 171797 (0.0012) -[2023-11-28 04:42:23,052][87424] Updated weights for policy 0, policy_version 171807 (0.0012) -[2023-11-28 04:42:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 87842816. Throughput: 0: 2703.8, 1: 2660.9. Samples: 87856224. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:42:23,445][86177] Avg episode reward: [(0, '-491.210'), (1, '-510.930')] -[2023-11-28 04:42:23,634][87426] Updated weights for policy 1, policy_version 171330 (0.0009) -[2023-11-28 04:42:24,026][87426] Updated weights for policy 1, policy_version 171340 (0.0007) -[2023-11-28 04:42:24,403][87426] Updated weights for policy 1, policy_version 171350 (0.0007) -[2023-11-28 04:42:24,789][87426] Updated weights for policy 1, policy_version 171360 (0.0007) -[2023-11-28 04:42:25,695][87424] Updated weights for policy 0, policy_version 171817 (0.0008) -[2023-11-28 04:42:26,088][87424] Updated weights for policy 0, policy_version 171827 (0.0009) -[2023-11-28 04:42:26,475][87424] Updated weights for policy 0, policy_version 171837 (0.0011) -[2023-11-28 04:42:27,091][87426] Updated weights for policy 1, policy_version 171370 (0.0009) -[2023-11-28 04:42:27,468][87426] Updated weights for policy 1, policy_version 171380 (0.0012) -[2023-11-28 04:42:27,846][87426] Updated weights for policy 1, policy_version 171390 (0.0010) -[2023-11-28 04:42:28,413][87424] Updated weights for policy 0, policy_version 171847 (0.0011) -[2023-11-28 04:42:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 87867392. Throughput: 0: 2689.8, 1: 2702.1. Samples: 87880740. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:42:28,445][86177] Avg episode reward: [(0, '-490.680'), (1, '-513.930')] -[2023-11-28 04:42:28,798][87424] Updated weights for policy 0, policy_version 171857 (0.0007) -[2023-11-28 04:42:29,185][87424] Updated weights for policy 0, policy_version 171867 (0.0010) -[2023-11-28 04:42:29,663][87426] Updated weights for policy 1, policy_version 171400 (0.0011) -[2023-11-28 04:42:30,037][87426] Updated weights for policy 1, policy_version 171410 (0.0011) -[2023-11-28 04:42:30,423][87426] Updated weights for policy 1, policy_version 171420 (0.0012) -[2023-11-28 04:42:31,135][87424] Updated weights for policy 0, policy_version 171877 (0.0011) -[2023-11-28 04:42:31,526][87424] Updated weights for policy 0, policy_version 171887 (0.0012) -[2023-11-28 04:42:31,908][87424] Updated weights for policy 0, policy_version 171897 (0.0011) -[2023-11-28 04:42:32,308][87426] Updated weights for policy 1, policy_version 171430 (0.0011) -[2023-11-28 04:42:32,672][87426] Updated weights for policy 1, policy_version 171440 (0.0011) -[2023-11-28 04:42:33,046][87426] Updated weights for policy 1, policy_version 171450 (0.0010) -[2023-11-28 04:42:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 87900160. Throughput: 0: 2718.2, 1: 2706.3. Samples: 87905920. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:42:33,445][86177] Avg episode reward: [(0, '-491.590'), (1, '-516.030')] -[2023-11-28 04:42:34,076][87424] Updated weights for policy 0, policy_version 171907 (0.0011) -[2023-11-28 04:42:34,449][87424] Updated weights for policy 0, policy_version 171917 (0.0009) -[2023-11-28 04:42:34,855][87424] Updated weights for policy 0, policy_version 171927 (0.0011) -[2023-11-28 04:42:35,046][87426] Updated weights for policy 1, policy_version 171460 (0.0010) -[2023-11-28 04:42:35,417][87426] Updated weights for policy 1, policy_version 171470 (0.0008) -[2023-11-28 04:42:35,792][87426] Updated weights for policy 1, policy_version 171480 (0.0008) -[2023-11-28 04:42:36,937][87424] Updated weights for policy 0, policy_version 171937 (0.0012) -[2023-11-28 04:42:37,314][87424] Updated weights for policy 0, policy_version 171947 (0.0012) -[2023-11-28 04:42:37,689][87424] Updated weights for policy 0, policy_version 171957 (0.0010) -[2023-11-28 04:42:38,072][87424] Updated weights for policy 0, policy_version 171967 (0.0010) -[2023-11-28 04:42:38,286][87426] Updated weights for policy 1, policy_version 171490 (0.0007) -[2023-11-28 04:42:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 87924736. Throughput: 0: 2715.0, 1: 2738.5. Samples: 87939152. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:42:38,445][86177] Avg episode reward: [(0, '-489.960'), (1, '-519.130')] -[2023-11-28 04:42:38,671][87426] Updated weights for policy 1, policy_version 171500 (0.0007) -[2023-11-28 04:42:39,056][87426] Updated weights for policy 1, policy_version 171510 (0.0008) -[2023-11-28 04:42:39,438][87426] Updated weights for policy 1, policy_version 171520 (0.0008) -[2023-11-28 04:42:40,698][87424] Updated weights for policy 0, policy_version 171977 (0.0011) -[2023-11-28 04:42:41,064][87424] Updated weights for policy 0, policy_version 171987 (0.0009) -[2023-11-28 04:42:41,441][87424] Updated weights for policy 0, policy_version 171997 (0.0008) -[2023-11-28 04:42:41,930][87426] Updated weights for policy 1, policy_version 171530 (0.0012) -[2023-11-28 04:42:42,311][87426] Updated weights for policy 1, policy_version 171540 (0.0009) -[2023-11-28 04:42:42,683][87426] Updated weights for policy 1, policy_version 171550 (0.0012) -[2023-11-28 04:42:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 87949312. Throughput: 0: 2710.6, 1: 2726.5. Samples: 87962316. Policy #0 lag: (min: 12.0, avg: 37.6, max: 47.0) -[2023-11-28 04:42:43,445][86177] Avg episode reward: [(0, '-489.940'), (1, '-509.250')] -[2023-11-28 04:42:43,526][87424] Updated weights for policy 0, policy_version 172007 (0.0009) -[2023-11-28 04:42:43,909][87424] Updated weights for policy 0, policy_version 172017 (0.0009) -[2023-11-28 04:42:44,298][87424] Updated weights for policy 0, policy_version 172027 (0.0009) -[2023-11-28 04:42:45,152][87426] Updated weights for policy 1, policy_version 171560 (0.0012) -[2023-11-28 04:42:45,529][87426] Updated weights for policy 1, policy_version 171570 (0.0012) -[2023-11-28 04:42:45,901][87426] Updated weights for policy 1, policy_version 171580 (0.0011) -[2023-11-28 04:42:45,937][87424] Updated weights for policy 0, policy_version 172037 (0.0011) -[2023-11-28 04:42:46,323][87424] Updated weights for policy 0, policy_version 172047 (0.0012) -[2023-11-28 04:42:46,711][87424] Updated weights for policy 0, policy_version 172057 (0.0012) -[2023-11-28 04:42:48,095][87426] Updated weights for policy 1, policy_version 171590 (0.0011) -[2023-11-28 04:42:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 87973888. Throughput: 0: 2709.3, 1: 2713.2. Samples: 87985928. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:42:48,445][86177] Avg episode reward: [(0, '-498.330'), (1, '-506.630')] -[2023-11-28 04:42:48,468][87426] Updated weights for policy 1, policy_version 171600 (0.0012) -[2023-11-28 04:42:48,849][87426] Updated weights for policy 1, policy_version 171610 (0.0011) -[2023-11-28 04:42:49,183][87424] Updated weights for policy 0, policy_version 172067 (0.0011) -[2023-11-28 04:42:49,577][87424] Updated weights for policy 0, policy_version 172077 (0.0012) -[2023-11-28 04:42:49,948][87424] Updated weights for policy 0, policy_version 172087 (0.0012) -[2023-11-28 04:42:51,227][87426] Updated weights for policy 1, policy_version 171620 (0.0011) -[2023-11-28 04:42:51,601][87426] Updated weights for policy 1, policy_version 171630 (0.0012) -[2023-11-28 04:42:51,980][87426] Updated weights for policy 1, policy_version 171640 (0.0011) -[2023-11-28 04:42:52,024][87424] Updated weights for policy 0, policy_version 172097 (0.0011) -[2023-11-28 04:42:52,406][87424] Updated weights for policy 0, policy_version 172107 (0.0012) -[2023-11-28 04:42:52,798][87424] Updated weights for policy 0, policy_version 172117 (0.0012) -[2023-11-28 04:42:53,171][87424] Updated weights for policy 0, policy_version 172127 (0.0012) -[2023-11-28 04:42:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 88006656. Throughput: 0: 2712.1, 1: 2692.7. Samples: 88018728. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:42:53,445][86177] Avg episode reward: [(0, '-500.250'), (1, '-519.520')] -[2023-11-28 04:42:54,588][87426] Updated weights for policy 1, policy_version 171650 (0.0010) -[2023-11-28 04:42:54,970][87426] Updated weights for policy 1, policy_version 171660 (0.0008) -[2023-11-28 04:42:55,223][87424] Updated weights for policy 0, policy_version 172137 (0.0009) -[2023-11-28 04:42:55,353][87426] Updated weights for policy 1, policy_version 171670 (0.0010) -[2023-11-28 04:42:55,612][87424] Updated weights for policy 0, policy_version 172147 (0.0008) -[2023-11-28 04:42:55,740][87426] Updated weights for policy 1, policy_version 171680 (0.0009) -[2023-11-28 04:42:55,992][87424] Updated weights for policy 0, policy_version 172157 (0.0007) -[2023-11-28 04:42:58,116][87426] Updated weights for policy 1, policy_version 171690 (0.0008) -[2023-11-28 04:42:58,118][87424] Updated weights for policy 0, policy_version 172167 (0.0010) -[2023-11-28 04:42:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 88023040. Throughput: 0: 2718.6, 1: 2691.6. Samples: 88043240. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:42:58,446][86177] Avg episode reward: [(0, '-497.460'), (1, '-511.550')] -[2023-11-28 04:42:58,503][87426] Updated weights for policy 1, policy_version 171700 (0.0007) -[2023-11-28 04:42:58,506][87424] Updated weights for policy 0, policy_version 172177 (0.0011) -[2023-11-28 04:42:58,879][87426] Updated weights for policy 1, policy_version 171710 (0.0007) -[2023-11-28 04:42:58,886][87424] Updated weights for policy 0, policy_version 172187 (0.0010) -[2023-11-28 04:43:00,669][87424] Updated weights for policy 0, policy_version 172197 (0.0010) -[2023-11-28 04:43:01,045][87424] Updated weights for policy 0, policy_version 172207 (0.0010) -[2023-11-28 04:43:01,157][87426] Updated weights for policy 1, policy_version 171720 (0.0010) -[2023-11-28 04:43:01,443][87424] Updated weights for policy 0, policy_version 172217 (0.0008) -[2023-11-28 04:43:01,549][87426] Updated weights for policy 1, policy_version 171730 (0.0011) -[2023-11-28 04:43:01,920][87426] Updated weights for policy 1, policy_version 171740 (0.0012) -[2023-11-28 04:43:03,251][87424] Updated weights for policy 0, policy_version 172227 (0.0012) -[2023-11-28 04:43:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 88055808. Throughput: 0: 2734.2, 1: 2691.2. Samples: 88068332. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:03,445][86177] Avg episode reward: [(0, '-509.400'), (1, '-522.430')] -[2023-11-28 04:43:03,622][87424] Updated weights for policy 0, policy_version 172237 (0.0012) -[2023-11-28 04:43:03,762][87426] Updated weights for policy 1, policy_version 171750 (0.0011) -[2023-11-28 04:43:03,998][87424] Updated weights for policy 0, policy_version 172247 (0.0011) -[2023-11-28 04:43:04,138][87426] Updated weights for policy 1, policy_version 171760 (0.0011) -[2023-11-28 04:43:04,527][87426] Updated weights for policy 1, policy_version 171770 (0.0012) -[2023-11-28 04:43:06,432][87424] Updated weights for policy 0, policy_version 172257 (0.0012) -[2023-11-28 04:43:06,816][87424] Updated weights for policy 0, policy_version 172267 (0.0011) -[2023-11-28 04:43:06,819][87426] Updated weights for policy 1, policy_version 171780 (0.0010) -[2023-11-28 04:43:07,198][87424] Updated weights for policy 0, policy_version 172277 (0.0010) -[2023-11-28 04:43:07,209][87426] Updated weights for policy 1, policy_version 171790 (0.0010) -[2023-11-28 04:43:07,576][87424] Updated weights for policy 0, policy_version 172287 (0.0010) -[2023-11-28 04:43:07,584][87426] Updated weights for policy 1, policy_version 171800 (0.0010) -[2023-11-28 04:43:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 88088576. Throughput: 0: 2722.8, 1: 2706.5. Samples: 88100544. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:08,445][86177] Avg episode reward: [(0, '-508.650'), (1, '-527.590')] -[2023-11-28 04:43:09,329][87426] Updated weights for policy 1, policy_version 171810 (0.0007) -[2023-11-28 04:43:09,704][87426] Updated weights for policy 1, policy_version 171820 (0.0007) -[2023-11-28 04:43:10,086][87426] Updated weights for policy 1, policy_version 171830 (0.0010) -[2023-11-28 04:43:10,163][87424] Updated weights for policy 0, policy_version 172297 (0.0011) -[2023-11-28 04:43:10,465][87426] Updated weights for policy 1, policy_version 171840 (0.0010) -[2023-11-28 04:43:10,559][87424] Updated weights for policy 0, policy_version 172307 (0.0010) -[2023-11-28 04:43:10,943][87424] Updated weights for policy 0, policy_version 172317 (0.0007) -[2023-11-28 04:43:12,942][87426] Updated weights for policy 1, policy_version 171850 (0.0010) -[2023-11-28 04:43:13,310][87426] Updated weights for policy 1, policy_version 171860 (0.0011) -[2023-11-28 04:43:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 88104960. Throughput: 0: 2745.9, 1: 2697.7. Samples: 88125700. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:13,446][86177] Avg episode reward: [(0, '-508.300'), (1, '-515.500')] -[2023-11-28 04:43:13,559][87424] Updated weights for policy 0, policy_version 172327 (0.0011) -[2023-11-28 04:43:13,684][87426] Updated weights for policy 1, policy_version 171870 (0.0010) -[2023-11-28 04:43:13,944][87424] Updated weights for policy 0, policy_version 172337 (0.0012) -[2023-11-28 04:43:14,326][87424] Updated weights for policy 0, policy_version 172347 (0.0012) -[2023-11-28 04:43:15,856][87426] Updated weights for policy 1, policy_version 171880 (0.0009) -[2023-11-28 04:43:16,236][87426] Updated weights for policy 1, policy_version 171890 (0.0012) -[2023-11-28 04:43:16,616][87426] Updated weights for policy 1, policy_version 171900 (0.0012) -[2023-11-28 04:43:16,826][87424] Updated weights for policy 0, policy_version 172357 (0.0012) -[2023-11-28 04:43:17,214][87424] Updated weights for policy 0, policy_version 172367 (0.0008) -[2023-11-28 04:43:17,590][87424] Updated weights for policy 0, policy_version 172377 (0.0007) -[2023-11-28 04:43:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 88137728. Throughput: 0: 2725.6, 1: 2702.5. Samples: 88150184. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:18,445][86177] Avg episode reward: [(0, '-506.940'), (1, '-538.500')] -[2023-11-28 04:43:19,002][87426] Updated weights for policy 1, policy_version 171910 (0.0012) -[2023-11-28 04:43:19,380][87426] Updated weights for policy 1, policy_version 171920 (0.0011) -[2023-11-28 04:43:19,433][87424] Updated weights for policy 0, policy_version 172387 (0.0008) -[2023-11-28 04:43:19,754][87426] Updated weights for policy 1, policy_version 171930 (0.0012) -[2023-11-28 04:43:19,820][87424] Updated weights for policy 0, policy_version 172397 (0.0009) -[2023-11-28 04:43:20,223][87424] Updated weights for policy 0, policy_version 172407 (0.0012) -[2023-11-28 04:43:21,709][87426] Updated weights for policy 1, policy_version 171940 (0.0011) -[2023-11-28 04:43:22,087][87426] Updated weights for policy 1, policy_version 171950 (0.0012) -[2023-11-28 04:43:22,467][87426] Updated weights for policy 1, policy_version 171960 (0.0009) -[2023-11-28 04:43:22,613][87424] Updated weights for policy 0, policy_version 172417 (0.0010) -[2023-11-28 04:43:23,003][87424] Updated weights for policy 0, policy_version 172427 (0.0011) -[2023-11-28 04:43:23,386][87424] Updated weights for policy 0, policy_version 172437 (0.0012) -[2023-11-28 04:43:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 88162304. Throughput: 0: 2733.3, 1: 2671.6. Samples: 88182372. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:23,445][86177] Avg episode reward: [(0, '-494.990'), (1, '-534.440')] -[2023-11-28 04:43:23,767][87424] Updated weights for policy 0, policy_version 172447 (0.0011) -[2023-11-28 04:43:24,667][87426] Updated weights for policy 1, policy_version 171970 (0.0009) -[2023-11-28 04:43:25,051][87426] Updated weights for policy 1, policy_version 171980 (0.0007) -[2023-11-28 04:43:25,422][87426] Updated weights for policy 1, policy_version 171990 (0.0008) -[2023-11-28 04:43:25,765][87424] Updated weights for policy 0, policy_version 172457 (0.0011) -[2023-11-28 04:43:25,799][87426] Updated weights for policy 1, policy_version 172000 (0.0009) -[2023-11-28 04:43:26,133][87424] Updated weights for policy 0, policy_version 172467 (0.0012) -[2023-11-28 04:43:26,515][87424] Updated weights for policy 0, policy_version 172477 (0.0012) -[2023-11-28 04:43:28,293][87426] Updated weights for policy 1, policy_version 172010 (0.0012) -[2023-11-28 04:43:28,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 88186880. Throughput: 0: 2728.4, 1: 2725.2. Samples: 88207732. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:28,446][86177] Avg episode reward: [(0, '-493.940'), (1, '-538.040')] -[2023-11-28 04:43:28,666][87424] Updated weights for policy 0, policy_version 172487 (0.0012) -[2023-11-28 04:43:28,680][87426] Updated weights for policy 1, policy_version 172020 (0.0012) -[2023-11-28 04:43:29,053][87424] Updated weights for policy 0, policy_version 172497 (0.0012) -[2023-11-28 04:43:29,053][87426] Updated weights for policy 1, policy_version 172030 (0.0012) -[2023-11-28 04:43:29,428][87424] Updated weights for policy 0, policy_version 172507 (0.0012) -[2023-11-28 04:43:30,747][87426] Updated weights for policy 1, policy_version 172040 (0.0008) -[2023-11-28 04:43:31,139][87426] Updated weights for policy 1, policy_version 172050 (0.0010) -[2023-11-28 04:43:31,485][87424] Updated weights for policy 0, policy_version 172517 (0.0012) -[2023-11-28 04:43:31,512][87426] Updated weights for policy 1, policy_version 172060 (0.0009) -[2023-11-28 04:43:31,862][87424] Updated weights for policy 0, policy_version 172527 (0.0011) -[2023-11-28 04:43:32,246][87424] Updated weights for policy 0, policy_version 172537 (0.0012) -[2023-11-28 04:43:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 88219648. Throughput: 0: 2736.5, 1: 2731.1. Samples: 88231972. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:33,445][86177] Avg episode reward: [(0, '-495.500'), (1, '-537.890')] -[2023-11-28 04:43:33,969][87426] Updated weights for policy 1, policy_version 172070 (0.0012) -[2023-11-28 04:43:33,997][87424] Updated weights for policy 0, policy_version 172547 (0.0011) -[2023-11-28 04:43:34,335][87426] Updated weights for policy 1, policy_version 172080 (0.0010) -[2023-11-28 04:43:34,386][87424] Updated weights for policy 0, policy_version 172557 (0.0008) -[2023-11-28 04:43:34,708][87426] Updated weights for policy 1, policy_version 172090 (0.0008) -[2023-11-28 04:43:34,762][87424] Updated weights for policy 0, policy_version 172567 (0.0008) -[2023-11-28 04:43:36,475][87424] Updated weights for policy 0, policy_version 172577 (0.0008) -[2023-11-28 04:43:36,595][87426] Updated weights for policy 1, policy_version 172100 (0.0011) -[2023-11-28 04:43:36,860][87424] Updated weights for policy 0, policy_version 172587 (0.0011) -[2023-11-28 04:43:36,962][87426] Updated weights for policy 1, policy_version 172110 (0.0010) -[2023-11-28 04:43:37,234][87424] Updated weights for policy 0, policy_version 172597 (0.0011) -[2023-11-28 04:43:37,336][87426] Updated weights for policy 1, policy_version 172120 (0.0008) -[2023-11-28 04:43:37,625][87424] Updated weights for policy 0, policy_version 172607 (0.0012) -[2023-11-28 04:43:38,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 88252416. Throughput: 0: 2722.0, 1: 2749.3. Samples: 88264936. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:38,445][86177] Avg episode reward: [(0, '-495.720'), (1, '-527.830')] -[2023-11-28 04:43:39,110][87426] Updated weights for policy 1, policy_version 172130 (0.0012) -[2023-11-28 04:43:39,484][87426] Updated weights for policy 1, policy_version 172140 (0.0012) -[2023-11-28 04:43:39,861][87426] Updated weights for policy 1, policy_version 172150 (0.0012) -[2023-11-28 04:43:39,952][87424] Updated weights for policy 0, policy_version 172617 (0.0011) -[2023-11-28 04:43:40,241][87426] Updated weights for policy 1, policy_version 172160 (0.0010) -[2023-11-28 04:43:40,342][87424] Updated weights for policy 0, policy_version 172627 (0.0011) -[2023-11-28 04:43:40,720][87424] Updated weights for policy 0, policy_version 172637 (0.0012) -[2023-11-28 04:43:42,760][87426] Updated weights for policy 1, policy_version 172170 (0.0012) -[2023-11-28 04:43:43,144][87426] Updated weights for policy 1, policy_version 172180 (0.0011) -[2023-11-28 04:43:43,367][87424] Updated weights for policy 0, policy_version 172647 (0.0012) -[2023-11-28 04:43:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 88268800. Throughput: 0: 2713.3, 1: 2756.5. Samples: 88289384. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:43,445][86177] Avg episode reward: [(0, '-495.840'), (1, '-515.660')] -[2023-11-28 04:43:43,516][87426] Updated weights for policy 1, policy_version 172190 (0.0009) -[2023-11-28 04:43:43,742][87424] Updated weights for policy 0, policy_version 172657 (0.0008) -[2023-11-28 04:43:44,125][87424] Updated weights for policy 0, policy_version 172667 (0.0008) -[2023-11-28 04:43:45,330][87426] Updated weights for policy 1, policy_version 172200 (0.0012) -[2023-11-28 04:43:45,708][87426] Updated weights for policy 1, policy_version 172210 (0.0012) -[2023-11-28 04:43:46,091][87426] Updated weights for policy 1, policy_version 172220 (0.0012) -[2023-11-28 04:43:46,576][87424] Updated weights for policy 0, policy_version 172677 (0.0007) -[2023-11-28 04:43:46,955][87424] Updated weights for policy 0, policy_version 172687 (0.0008) -[2023-11-28 04:43:47,340][87424] Updated weights for policy 0, policy_version 172697 (0.0008) -[2023-11-28 04:43:48,041][87426] Updated weights for policy 1, policy_version 172230 (0.0012) -[2023-11-28 04:43:48,417][87426] Updated weights for policy 1, policy_version 172240 (0.0012) -[2023-11-28 04:43:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 88301568. Throughput: 0: 2706.4, 1: 2763.5. Samples: 88314476. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:48,445][86177] Avg episode reward: [(0, '-489.530'), (1, '-514.260')] -[2023-11-28 04:43:48,793][87426] Updated weights for policy 1, policy_version 172250 (0.0012) -[2023-11-28 04:43:49,480][87424] Updated weights for policy 0, policy_version 172707 (0.0009) -[2023-11-28 04:43:49,867][87424] Updated weights for policy 0, policy_version 172717 (0.0012) -[2023-11-28 04:43:50,256][87424] Updated weights for policy 0, policy_version 172727 (0.0012) -[2023-11-28 04:43:50,693][87426] Updated weights for policy 1, policy_version 172260 (0.0010) -[2023-11-28 04:43:51,064][87426] Updated weights for policy 1, policy_version 172270 (0.0007) -[2023-11-28 04:43:51,442][87426] Updated weights for policy 1, policy_version 172280 (0.0008) -[2023-11-28 04:43:52,691][87424] Updated weights for policy 0, policy_version 172737 (0.0012) -[2023-11-28 04:43:53,070][87424] Updated weights for policy 0, policy_version 172747 (0.0012) -[2023-11-28 04:43:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 88326144. Throughput: 0: 2722.6, 1: 2758.1. Samples: 88347176. Policy #0 lag: (min: 12.0, avg: 30.4, max: 44.0) -[2023-11-28 04:43:53,445][86177] Avg episode reward: [(0, '-492.010'), (1, '-523.480')] -[2023-11-28 04:43:53,454][87424] Updated weights for policy 0, policy_version 172757 (0.0012) -[2023-11-28 04:43:53,841][87424] Updated weights for policy 0, policy_version 172767 (0.0010) -[2023-11-28 04:43:53,986][87426] Updated weights for policy 1, policy_version 172290 (0.0011) -[2023-11-28 04:43:54,363][87426] Updated weights for policy 1, policy_version 172300 (0.0008) -[2023-11-28 04:43:54,750][87426] Updated weights for policy 1, policy_version 172310 (0.0007) -[2023-11-28 04:43:55,122][87426] Updated weights for policy 1, policy_version 172320 (0.0007) -[2023-11-28 04:43:56,404][87424] Updated weights for policy 0, policy_version 172777 (0.0011) -[2023-11-28 04:43:56,775][87424] Updated weights for policy 0, policy_version 172787 (0.0008) -[2023-11-28 04:43:57,162][87424] Updated weights for policy 0, policy_version 172797 (0.0008) -[2023-11-28 04:43:57,548][87426] Updated weights for policy 1, policy_version 172330 (0.0011) -[2023-11-28 04:43:57,923][87426] Updated weights for policy 1, policy_version 172340 (0.0012) -[2023-11-28 04:43:58,295][87426] Updated weights for policy 1, policy_version 172350 (0.0009) -[2023-11-28 04:43:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 88358912. Throughput: 0: 2711.6, 1: 2725.3. Samples: 88370356. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:43:58,445][86177] Avg episode reward: [(0, '-491.330'), (1, '-514.940')] -[2023-11-28 04:43:59,221][87424] Updated weights for policy 0, policy_version 172807 (0.0010) -[2023-11-28 04:43:59,596][87424] Updated weights for policy 0, policy_version 172817 (0.0012) -[2023-11-28 04:43:59,994][87424] Updated weights for policy 0, policy_version 172827 (0.0012) -[2023-11-28 04:44:00,602][87426] Updated weights for policy 1, policy_version 172360 (0.0009) -[2023-11-28 04:44:00,969][87426] Updated weights for policy 1, policy_version 172370 (0.0008) -[2023-11-28 04:44:01,351][87426] Updated weights for policy 1, policy_version 172380 (0.0007) -[2023-11-28 04:44:02,008][87424] Updated weights for policy 0, policy_version 172837 (0.0010) -[2023-11-28 04:44:02,398][87424] Updated weights for policy 0, policy_version 172847 (0.0011) -[2023-11-28 04:44:02,774][87424] Updated weights for policy 0, policy_version 172857 (0.0010) -[2023-11-28 04:44:03,352][87426] Updated weights for policy 1, policy_version 172390 (0.0010) -[2023-11-28 04:44:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 88383488. Throughput: 0: 2727.4, 1: 2708.1. Samples: 88394780. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:03,445][86177] Avg episode reward: [(0, '-492.430'), (1, '-544.070')] -[2023-11-28 04:44:03,726][87426] Updated weights for policy 1, policy_version 172400 (0.0012) -[2023-11-28 04:44:04,115][87426] Updated weights for policy 1, policy_version 172410 (0.0012) -[2023-11-28 04:44:04,624][87424] Updated weights for policy 0, policy_version 172867 (0.0010) -[2023-11-28 04:44:05,001][87424] Updated weights for policy 0, policy_version 172877 (0.0009) -[2023-11-28 04:44:05,383][87424] Updated weights for policy 0, policy_version 172887 (0.0007) -[2023-11-28 04:44:06,487][87426] Updated weights for policy 1, policy_version 172420 (0.0011) -[2023-11-28 04:44:06,872][87426] Updated weights for policy 1, policy_version 172430 (0.0011) -[2023-11-28 04:44:07,254][87426] Updated weights for policy 1, policy_version 172440 (0.0011) -[2023-11-28 04:44:07,279][87424] Updated weights for policy 0, policy_version 172897 (0.0008) -[2023-11-28 04:44:07,662][87424] Updated weights for policy 0, policy_version 172907 (0.0011) -[2023-11-28 04:44:08,049][87424] Updated weights for policy 0, policy_version 172917 (0.0011) -[2023-11-28 04:44:08,433][87424] Updated weights for policy 0, policy_version 172927 (0.0008) -[2023-11-28 04:44:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 88408064. Throughput: 0: 2752.9, 1: 2731.9. Samples: 88429188. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:08,445][86177] Avg episode reward: [(0, '-498.280'), (1, '-560.760')] -[2023-11-28 04:44:09,087][87426] Updated weights for policy 1, policy_version 172450 (0.0011) -[2023-11-28 04:44:09,467][87426] Updated weights for policy 1, policy_version 172460 (0.0011) -[2023-11-28 04:44:09,851][87426] Updated weights for policy 1, policy_version 172470 (0.0008) -[2023-11-28 04:44:10,224][87426] Updated weights for policy 1, policy_version 172480 (0.0011) -[2023-11-28 04:44:10,678][87424] Updated weights for policy 0, policy_version 172937 (0.0010) -[2023-11-28 04:44:11,064][87424] Updated weights for policy 0, policy_version 172947 (0.0012) -[2023-11-28 04:44:11,450][87424] Updated weights for policy 0, policy_version 172957 (0.0012) -[2023-11-28 04:44:12,632][87426] Updated weights for policy 1, policy_version 172490 (0.0012) -[2023-11-28 04:44:13,009][87426] Updated weights for policy 1, policy_version 172500 (0.0009) -[2023-11-28 04:44:13,389][87426] Updated weights for policy 1, policy_version 172510 (0.0012) -[2023-11-28 04:44:13,404][87424] Updated weights for policy 0, policy_version 172967 (0.0009) -[2023-11-28 04:44:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 88432640. Throughput: 0: 2739.9, 1: 2698.3. Samples: 88452452. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:13,445][86177] Avg episode reward: [(0, '-497.550'), (1, '-551.280')] -[2023-11-28 04:44:13,793][87424] Updated weights for policy 0, policy_version 172977 (0.0008) -[2023-11-28 04:44:14,176][87424] Updated weights for policy 0, policy_version 172987 (0.0008) -[2023-11-28 04:44:15,167][87426] Updated weights for policy 1, policy_version 172520 (0.0011) -[2023-11-28 04:44:15,548][87426] Updated weights for policy 1, policy_version 172530 (0.0012) -[2023-11-28 04:44:15,926][87426] Updated weights for policy 1, policy_version 172540 (0.0011) -[2023-11-28 04:44:16,522][87424] Updated weights for policy 0, policy_version 172997 (0.0007) -[2023-11-28 04:44:16,903][87424] Updated weights for policy 0, policy_version 173007 (0.0007) -[2023-11-28 04:44:17,284][87424] Updated weights for policy 0, policy_version 173017 (0.0009) -[2023-11-28 04:44:18,382][87426] Updated weights for policy 1, policy_version 172550 (0.0009) -[2023-11-28 04:44:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 88465408. Throughput: 0: 2718.3, 1: 2699.2. Samples: 88475760. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:18,446][86177] Avg episode reward: [(0, '-497.650'), (1, '-544.390')] -[2023-11-28 04:44:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000173024_44294144.pth... -[2023-11-28 04:44:18,496][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000170496_43646976.pth -[2023-11-28 04:44:18,758][87426] Updated weights for policy 1, policy_version 172560 (0.0007) -[2023-11-28 04:44:19,144][87426] Updated weights for policy 1, policy_version 172570 (0.0008) -[2023-11-28 04:44:19,367][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000172576_44179456.pth... -[2023-11-28 04:44:19,410][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000170016_43524096.pth -[2023-11-28 04:44:19,699][87424] Updated weights for policy 0, policy_version 173027 (0.0009) -[2023-11-28 04:44:20,078][87424] Updated weights for policy 0, policy_version 173037 (0.0012) -[2023-11-28 04:44:20,457][87424] Updated weights for policy 0, policy_version 173047 (0.0012) -[2023-11-28 04:44:21,538][87426] Updated weights for policy 1, policy_version 172580 (0.0009) -[2023-11-28 04:44:21,913][87426] Updated weights for policy 1, policy_version 172590 (0.0012) -[2023-11-28 04:44:22,300][87426] Updated weights for policy 1, policy_version 172600 (0.0012) -[2023-11-28 04:44:22,758][87424] Updated weights for policy 0, policy_version 173057 (0.0012) -[2023-11-28 04:44:23,138][87424] Updated weights for policy 0, policy_version 173067 (0.0012) -[2023-11-28 04:44:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 88489984. Throughput: 0: 2698.5, 1: 2668.0. Samples: 88506428. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:23,445][86177] Avg episode reward: [(0, '-497.540'), (1, '-507.900')] -[2023-11-28 04:44:23,521][87424] Updated weights for policy 0, policy_version 173077 (0.0011) -[2023-11-28 04:44:23,905][87424] Updated weights for policy 0, policy_version 173087 (0.0009) -[2023-11-28 04:44:24,136][87426] Updated weights for policy 1, policy_version 172610 (0.0012) -[2023-11-28 04:44:24,511][87426] Updated weights for policy 1, policy_version 172620 (0.0012) -[2023-11-28 04:44:24,889][87426] Updated weights for policy 1, policy_version 172630 (0.0008) -[2023-11-28 04:44:25,267][87426] Updated weights for policy 1, policy_version 172640 (0.0008) -[2023-11-28 04:44:26,349][87424] Updated weights for policy 0, policy_version 173097 (0.0012) -[2023-11-28 04:44:26,736][87424] Updated weights for policy 0, policy_version 173107 (0.0012) -[2023-11-28 04:44:27,117][87424] Updated weights for policy 0, policy_version 173117 (0.0012) -[2023-11-28 04:44:27,765][87426] Updated weights for policy 1, policy_version 172650 (0.0008) -[2023-11-28 04:44:28,143][87426] Updated weights for policy 1, policy_version 172660 (0.0007) -[2023-11-28 04:44:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 88514560. Throughput: 0: 2694.1, 1: 2681.3. Samples: 88531280. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:28,446][86177] Avg episode reward: [(0, '-494.070'), (1, '-498.610')] -[2023-11-28 04:44:28,529][87426] Updated weights for policy 1, policy_version 172670 (0.0007) -[2023-11-28 04:44:28,834][87424] Updated weights for policy 0, policy_version 173127 (0.0012) -[2023-11-28 04:44:29,209][87424] Updated weights for policy 0, policy_version 173137 (0.0008) -[2023-11-28 04:44:29,596][87424] Updated weights for policy 0, policy_version 173147 (0.0007) -[2023-11-28 04:44:30,447][87426] Updated weights for policy 1, policy_version 172680 (0.0010) -[2023-11-28 04:44:30,827][87426] Updated weights for policy 1, policy_version 172690 (0.0011) -[2023-11-28 04:44:31,221][87426] Updated weights for policy 1, policy_version 172700 (0.0011) -[2023-11-28 04:44:32,018][87424] Updated weights for policy 0, policy_version 173157 (0.0010) -[2023-11-28 04:44:32,401][87424] Updated weights for policy 0, policy_version 173167 (0.0008) -[2023-11-28 04:44:32,784][87424] Updated weights for policy 0, policy_version 173177 (0.0008) -[2023-11-28 04:44:33,394][87426] Updated weights for policy 1, policy_version 172710 (0.0011) -[2023-11-28 04:44:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 88547328. Throughput: 0: 2658.1, 1: 2680.5. Samples: 88554716. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:33,446][86177] Avg episode reward: [(0, '-493.840'), (1, '-504.440')] -[2023-11-28 04:44:33,768][87426] Updated weights for policy 1, policy_version 172720 (0.0012) -[2023-11-28 04:44:34,147][87426] Updated weights for policy 1, policy_version 172730 (0.0012) -[2023-11-28 04:44:34,944][87424] Updated weights for policy 0, policy_version 173187 (0.0011) -[2023-11-28 04:44:35,318][87424] Updated weights for policy 0, policy_version 173197 (0.0010) -[2023-11-28 04:44:35,709][87424] Updated weights for policy 0, policy_version 173207 (0.0007) -[2023-11-28 04:44:36,174][87426] Updated weights for policy 1, policy_version 172740 (0.0011) -[2023-11-28 04:44:36,562][87426] Updated weights for policy 1, policy_version 172750 (0.0011) -[2023-11-28 04:44:36,941][87426] Updated weights for policy 1, policy_version 172760 (0.0011) -[2023-11-28 04:44:38,035][87424] Updated weights for policy 0, policy_version 173217 (0.0008) -[2023-11-28 04:44:38,417][87424] Updated weights for policy 0, policy_version 173227 (0.0012) -[2023-11-28 04:44:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 88571904. Throughput: 0: 2669.2, 1: 2695.8. Samples: 88588600. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:38,445][86177] Avg episode reward: [(0, '-495.060'), (1, '-505.500')] -[2023-11-28 04:44:38,768][87426] Updated weights for policy 1, policy_version 172770 (0.0012) -[2023-11-28 04:44:38,798][87424] Updated weights for policy 0, policy_version 173237 (0.0011) -[2023-11-28 04:44:39,156][87426] Updated weights for policy 1, policy_version 172780 (0.0011) -[2023-11-28 04:44:39,190][87424] Updated weights for policy 0, policy_version 173247 (0.0012) -[2023-11-28 04:44:39,531][87426] Updated weights for policy 1, policy_version 172790 (0.0011) -[2023-11-28 04:44:39,914][87426] Updated weights for policy 1, policy_version 172800 (0.0008) -[2023-11-28 04:44:41,127][87424] Updated weights for policy 0, policy_version 173257 (0.0011) -[2023-11-28 04:44:41,508][87424] Updated weights for policy 0, policy_version 173267 (0.0009) -[2023-11-28 04:44:41,890][87424] Updated weights for policy 0, policy_version 173277 (0.0011) -[2023-11-28 04:44:42,372][87426] Updated weights for policy 1, policy_version 172810 (0.0012) -[2023-11-28 04:44:42,744][87426] Updated weights for policy 1, policy_version 172820 (0.0011) -[2023-11-28 04:44:43,120][87426] Updated weights for policy 1, policy_version 172830 (0.0008) -[2023-11-28 04:44:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 88604672. Throughput: 0: 2675.8, 1: 2722.3. Samples: 88613272. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:43,446][86177] Avg episode reward: [(0, '-503.560'), (1, '-506.750')] -[2023-11-28 04:44:44,234][87424] Updated weights for policy 0, policy_version 173287 (0.0011) -[2023-11-28 04:44:44,614][87424] Updated weights for policy 0, policy_version 173297 (0.0007) -[2023-11-28 04:44:44,996][87424] Updated weights for policy 0, policy_version 173307 (0.0007) -[2023-11-28 04:44:45,624][87426] Updated weights for policy 1, policy_version 172840 (0.0008) -[2023-11-28 04:44:46,003][87426] Updated weights for policy 1, policy_version 172850 (0.0007) -[2023-11-28 04:44:46,385][87426] Updated weights for policy 1, policy_version 172860 (0.0008) -[2023-11-28 04:44:47,590][87424] Updated weights for policy 0, policy_version 173317 (0.0009) -[2023-11-28 04:44:47,964][87424] Updated weights for policy 0, policy_version 173327 (0.0012) -[2023-11-28 04:44:48,346][87424] Updated weights for policy 0, policy_version 173337 (0.0011) -[2023-11-28 04:44:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 88621056. Throughput: 0: 2658.0, 1: 2723.8. Samples: 88636964. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:48,446][86177] Avg episode reward: [(0, '-500.740'), (1, '-507.460')] -[2023-11-28 04:44:48,907][87426] Updated weights for policy 1, policy_version 172870 (0.0010) -[2023-11-28 04:44:49,290][87426] Updated weights for policy 1, policy_version 172880 (0.0010) -[2023-11-28 04:44:49,684][87426] Updated weights for policy 1, policy_version 172890 (0.0008) -[2023-11-28 04:44:50,395][87424] Updated weights for policy 0, policy_version 173347 (0.0009) -[2023-11-28 04:44:50,780][87424] Updated weights for policy 0, policy_version 173357 (0.0009) -[2023-11-28 04:44:51,172][87424] Updated weights for policy 0, policy_version 173367 (0.0009) -[2023-11-28 04:44:52,062][87426] Updated weights for policy 1, policy_version 172900 (0.0009) -[2023-11-28 04:44:52,434][87426] Updated weights for policy 1, policy_version 172910 (0.0010) -[2023-11-28 04:44:52,815][87426] Updated weights for policy 1, policy_version 172920 (0.0008) -[2023-11-28 04:44:53,432][87424] Updated weights for policy 0, policy_version 173377 (0.0012) -[2023-11-28 04:44:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 88653824. Throughput: 0: 2606.6, 1: 2718.6. Samples: 88668820. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:53,445][86177] Avg episode reward: [(0, '-501.870'), (1, '-501.900')] -[2023-11-28 04:44:53,809][87424] Updated weights for policy 0, policy_version 173387 (0.0010) -[2023-11-28 04:44:54,188][87424] Updated weights for policy 0, policy_version 173397 (0.0008) -[2023-11-28 04:44:54,572][87424] Updated weights for policy 0, policy_version 173407 (0.0007) -[2023-11-28 04:44:55,162][87426] Updated weights for policy 1, policy_version 172930 (0.0009) -[2023-11-28 04:44:55,541][87426] Updated weights for policy 1, policy_version 172940 (0.0008) -[2023-11-28 04:44:55,929][87426] Updated weights for policy 1, policy_version 172950 (0.0008) -[2023-11-28 04:44:56,298][87426] Updated weights for policy 1, policy_version 172960 (0.0011) -[2023-11-28 04:44:56,918][87424] Updated weights for policy 0, policy_version 173417 (0.0011) -[2023-11-28 04:44:57,309][87424] Updated weights for policy 0, policy_version 173427 (0.0012) -[2023-11-28 04:44:57,690][87424] Updated weights for policy 0, policy_version 173437 (0.0012) -[2023-11-28 04:44:58,239][87426] Updated weights for policy 1, policy_version 172970 (0.0012) -[2023-11-28 04:44:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 88678400. Throughput: 0: 2612.8, 1: 2726.9. Samples: 88692740. Policy #0 lag: (min: 26.0, avg: 48.5, max: 58.0) -[2023-11-28 04:44:58,445][86177] Avg episode reward: [(0, '-502.550'), (1, '-501.400')] -[2023-11-28 04:44:58,616][87426] Updated weights for policy 1, policy_version 172980 (0.0012) -[2023-11-28 04:44:58,987][87426] Updated weights for policy 1, policy_version 172990 (0.0012) -[2023-11-28 04:45:00,163][87424] Updated weights for policy 0, policy_version 173447 (0.0012) -[2023-11-28 04:45:00,546][87424] Updated weights for policy 0, policy_version 173457 (0.0012) -[2023-11-28 04:45:00,928][87424] Updated weights for policy 0, policy_version 173467 (0.0011) -[2023-11-28 04:45:00,932][87426] Updated weights for policy 1, policy_version 173000 (0.0012) -[2023-11-28 04:45:01,319][87426] Updated weights for policy 1, policy_version 173010 (0.0011) -[2023-11-28 04:45:01,704][87426] Updated weights for policy 1, policy_version 173020 (0.0009) -[2023-11-28 04:45:03,061][87424] Updated weights for policy 0, policy_version 173477 (0.0009) -[2023-11-28 04:45:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 88702976. Throughput: 0: 2654.5, 1: 2722.9. Samples: 88717744. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:03,445][86177] Avg episode reward: [(0, '-498.100'), (1, '-497.250')] -[2023-11-28 04:45:03,450][87424] Updated weights for policy 0, policy_version 173487 (0.0009) -[2023-11-28 04:45:03,831][87424] Updated weights for policy 0, policy_version 173497 (0.0008) -[2023-11-28 04:45:04,246][87426] Updated weights for policy 1, policy_version 173030 (0.0009) -[2023-11-28 04:45:04,624][87426] Updated weights for policy 1, policy_version 173040 (0.0011) -[2023-11-28 04:45:05,007][87426] Updated weights for policy 1, policy_version 173050 (0.0012) -[2023-11-28 04:45:05,878][87424] Updated weights for policy 0, policy_version 173507 (0.0009) -[2023-11-28 04:45:06,265][87424] Updated weights for policy 0, policy_version 173517 (0.0012) -[2023-11-28 04:45:06,640][87424] Updated weights for policy 0, policy_version 173527 (0.0012) -[2023-11-28 04:45:06,960][87426] Updated weights for policy 1, policy_version 173060 (0.0011) -[2023-11-28 04:45:07,334][87426] Updated weights for policy 1, policy_version 173070 (0.0012) -[2023-11-28 04:45:07,711][87426] Updated weights for policy 1, policy_version 173080 (0.0012) -[2023-11-28 04:45:08,438][87424] Updated weights for policy 0, policy_version 173537 (0.0011) -[2023-11-28 04:45:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 88735744. Throughput: 0: 2688.2, 1: 2744.0. Samples: 88750876. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:08,445][86177] Avg episode reward: [(0, '-498.380'), (1, '-494.340')] -[2023-11-28 04:45:08,820][87424] Updated weights for policy 0, policy_version 173547 (0.0012) -[2023-11-28 04:45:09,210][87424] Updated weights for policy 0, policy_version 173557 (0.0012) -[2023-11-28 04:45:09,587][87424] Updated weights for policy 0, policy_version 173567 (0.0012) -[2023-11-28 04:45:09,895][87426] Updated weights for policy 1, policy_version 173090 (0.0012) -[2023-11-28 04:45:10,275][87426] Updated weights for policy 1, policy_version 173100 (0.0008) -[2023-11-28 04:45:10,661][87426] Updated weights for policy 1, policy_version 173110 (0.0010) -[2023-11-28 04:45:11,032][87426] Updated weights for policy 1, policy_version 173120 (0.0008) -[2023-11-28 04:45:11,985][87424] Updated weights for policy 0, policy_version 173577 (0.0011) -[2023-11-28 04:45:12,366][87424] Updated weights for policy 0, policy_version 173587 (0.0012) -[2023-11-28 04:45:12,748][87424] Updated weights for policy 0, policy_version 173597 (0.0012) -[2023-11-28 04:45:13,086][87426] Updated weights for policy 1, policy_version 173130 (0.0011) -[2023-11-28 04:45:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 88760320. Throughput: 0: 2694.5, 1: 2733.4. Samples: 88775536. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:13,445][86177] Avg episode reward: [(0, '-497.980'), (1, '-494.670')] -[2023-11-28 04:45:13,472][87426] Updated weights for policy 1, policy_version 173140 (0.0012) -[2023-11-28 04:45:13,849][87426] Updated weights for policy 1, policy_version 173150 (0.0012) -[2023-11-28 04:45:15,057][87424] Updated weights for policy 0, policy_version 173607 (0.0011) -[2023-11-28 04:45:15,439][87424] Updated weights for policy 0, policy_version 173617 (0.0012) -[2023-11-28 04:45:15,808][87424] Updated weights for policy 0, policy_version 173627 (0.0010) -[2023-11-28 04:45:16,013][87426] Updated weights for policy 1, policy_version 173160 (0.0010) -[2023-11-28 04:45:16,389][87426] Updated weights for policy 1, policy_version 173170 (0.0012) -[2023-11-28 04:45:16,765][87426] Updated weights for policy 1, policy_version 173180 (0.0011) -[2023-11-28 04:45:17,816][87424] Updated weights for policy 0, policy_version 173637 (0.0012) -[2023-11-28 04:45:18,196][87424] Updated weights for policy 0, policy_version 173647 (0.0012) -[2023-11-28 04:45:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 88784896. Throughput: 0: 2731.2, 1: 2740.9. Samples: 88800960. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:18,445][86177] Avg episode reward: [(0, '-495.170'), (1, '-507.860')] -[2023-11-28 04:45:18,579][87424] Updated weights for policy 0, policy_version 173657 (0.0012) -[2023-11-28 04:45:18,763][87426] Updated weights for policy 1, policy_version 173190 (0.0008) -[2023-11-28 04:45:19,141][87426] Updated weights for policy 1, policy_version 173200 (0.0010) -[2023-11-28 04:45:19,517][87426] Updated weights for policy 1, policy_version 173210 (0.0011) -[2023-11-28 04:45:20,357][87424] Updated weights for policy 0, policy_version 173667 (0.0012) -[2023-11-28 04:45:20,745][87424] Updated weights for policy 0, policy_version 173677 (0.0012) -[2023-11-28 04:45:21,128][87424] Updated weights for policy 0, policy_version 173687 (0.0012) -[2023-11-28 04:45:21,946][87426] Updated weights for policy 1, policy_version 173220 (0.0012) -[2023-11-28 04:45:22,323][87426] Updated weights for policy 1, policy_version 173230 (0.0015) -[2023-11-28 04:45:22,704][87426] Updated weights for policy 1, policy_version 173240 (0.0012) -[2023-11-28 04:45:23,377][87424] Updated weights for policy 0, policy_version 173697 (0.0012) -[2023-11-28 04:45:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 88817664. Throughput: 0: 2721.1, 1: 2716.4. Samples: 88833284. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:23,445][86177] Avg episode reward: [(0, '-492.500'), (1, '-518.760')] -[2023-11-28 04:45:23,756][87424] Updated weights for policy 0, policy_version 173707 (0.0007) -[2023-11-28 04:45:24,136][87424] Updated weights for policy 0, policy_version 173717 (0.0007) -[2023-11-28 04:45:24,522][87424] Updated weights for policy 0, policy_version 173727 (0.0008) -[2023-11-28 04:45:25,057][87426] Updated weights for policy 1, policy_version 173250 (0.0011) -[2023-11-28 04:45:25,445][87426] Updated weights for policy 1, policy_version 173260 (0.0010) -[2023-11-28 04:45:25,827][87426] Updated weights for policy 1, policy_version 173270 (0.0007) -[2023-11-28 04:45:26,198][87426] Updated weights for policy 1, policy_version 173280 (0.0007) -[2023-11-28 04:45:26,689][87424] Updated weights for policy 0, policy_version 173737 (0.0012) -[2023-11-28 04:45:27,058][87424] Updated weights for policy 0, policy_version 173747 (0.0011) -[2023-11-28 04:45:27,443][87424] Updated weights for policy 0, policy_version 173757 (0.0012) -[2023-11-28 04:45:28,383][87426] Updated weights for policy 1, policy_version 173290 (0.0011) -[2023-11-28 04:45:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 88842240. Throughput: 0: 2743.9, 1: 2713.3. Samples: 88858844. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:28,445][86177] Avg episode reward: [(0, '-493.580'), (1, '-528.980')] -[2023-11-28 04:45:28,758][87426] Updated weights for policy 1, policy_version 173300 (0.0012) -[2023-11-28 04:45:29,133][87426] Updated weights for policy 1, policy_version 173310 (0.0011) -[2023-11-28 04:45:29,242][87424] Updated weights for policy 0, policy_version 173767 (0.0011) -[2023-11-28 04:45:29,636][87424] Updated weights for policy 0, policy_version 173777 (0.0011) -[2023-11-28 04:45:30,010][87424] Updated weights for policy 0, policy_version 173787 (0.0012) -[2023-11-28 04:45:31,355][87426] Updated weights for policy 1, policy_version 173320 (0.0012) -[2023-11-28 04:45:31,729][87426] Updated weights for policy 1, policy_version 173330 (0.0012) -[2023-11-28 04:45:32,001][87424] Updated weights for policy 0, policy_version 173797 (0.0012) -[2023-11-28 04:45:32,107][87426] Updated weights for policy 1, policy_version 173340 (0.0011) -[2023-11-28 04:45:32,383][87424] Updated weights for policy 0, policy_version 173807 (0.0011) -[2023-11-28 04:45:32,753][87424] Updated weights for policy 0, policy_version 173817 (0.0007) -[2023-11-28 04:45:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 88875008. Throughput: 0: 2769.4, 1: 2730.6. Samples: 88884464. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:33,445][86177] Avg episode reward: [(0, '-495.200'), (1, '-523.390')] -[2023-11-28 04:45:34,625][87426] Updated weights for policy 1, policy_version 173350 (0.0011) -[2023-11-28 04:45:34,629][87424] Updated weights for policy 0, policy_version 173827 (0.0010) -[2023-11-28 04:45:35,005][87426] Updated weights for policy 1, policy_version 173360 (0.0009) -[2023-11-28 04:45:35,011][87424] Updated weights for policy 0, policy_version 173837 (0.0009) -[2023-11-28 04:45:35,384][87426] Updated weights for policy 1, policy_version 173370 (0.0008) -[2023-11-28 04:45:35,398][87424] Updated weights for policy 0, policy_version 173847 (0.0008) -[2023-11-28 04:45:37,457][87426] Updated weights for policy 1, policy_version 173380 (0.0008) -[2023-11-28 04:45:37,675][87424] Updated weights for policy 0, policy_version 173857 (0.0008) -[2023-11-28 04:45:37,841][87426] Updated weights for policy 1, policy_version 173390 (0.0009) -[2023-11-28 04:45:38,055][87424] Updated weights for policy 0, policy_version 173867 (0.0010) -[2023-11-28 04:45:38,216][87426] Updated weights for policy 1, policy_version 173400 (0.0010) -[2023-11-28 04:45:38,434][87424] Updated weights for policy 0, policy_version 173877 (0.0011) -[2023-11-28 04:45:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 88891392. Throughput: 0: 2803.6, 1: 2699.6. Samples: 88916464. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:38,445][86177] Avg episode reward: [(0, '-496.770'), (1, '-517.140')] -[2023-11-28 04:45:38,817][87424] Updated weights for policy 0, policy_version 173887 (0.0009) -[2023-11-28 04:45:40,601][87426] Updated weights for policy 1, policy_version 173410 (0.0008) -[2023-11-28 04:45:40,974][87426] Updated weights for policy 1, policy_version 173420 (0.0008) -[2023-11-28 04:45:41,359][87426] Updated weights for policy 1, policy_version 173430 (0.0010) -[2023-11-28 04:45:41,417][87424] Updated weights for policy 0, policy_version 173897 (0.0012) -[2023-11-28 04:45:41,736][87426] Updated weights for policy 1, policy_version 173440 (0.0011) -[2023-11-28 04:45:41,800][87424] Updated weights for policy 0, policy_version 173907 (0.0011) -[2023-11-28 04:45:42,191][87424] Updated weights for policy 0, policy_version 173917 (0.0011) -[2023-11-28 04:45:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 88924160. Throughput: 0: 2796.3, 1: 2690.3. Samples: 88939636. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:43,445][86177] Avg episode reward: [(0, '-500.980'), (1, '-508.230')] -[2023-11-28 04:45:44,277][87424] Updated weights for policy 0, policy_version 173927 (0.0012) -[2023-11-28 04:45:44,289][87426] Updated weights for policy 1, policy_version 173450 (0.0010) -[2023-11-28 04:45:44,665][87426] Updated weights for policy 1, policy_version 173460 (0.0011) -[2023-11-28 04:45:44,667][87424] Updated weights for policy 0, policy_version 173937 (0.0010) -[2023-11-28 04:45:45,041][87426] Updated weights for policy 1, policy_version 173470 (0.0011) -[2023-11-28 04:45:45,046][87424] Updated weights for policy 0, policy_version 173947 (0.0011) -[2023-11-28 04:45:46,975][87426] Updated weights for policy 1, policy_version 173480 (0.0010) -[2023-11-28 04:45:47,045][87424] Updated weights for policy 0, policy_version 173957 (0.0009) -[2023-11-28 04:45:47,356][87426] Updated weights for policy 1, policy_version 173490 (0.0007) -[2023-11-28 04:45:47,425][87424] Updated weights for policy 0, policy_version 173967 (0.0009) -[2023-11-28 04:45:47,742][87426] Updated weights for policy 1, policy_version 173500 (0.0007) -[2023-11-28 04:45:47,813][87424] Updated weights for policy 0, policy_version 173977 (0.0008) -[2023-11-28 04:45:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 88956928. Throughput: 0: 2775.7, 1: 2696.5. Samples: 88963992. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:48,445][86177] Avg episode reward: [(0, '-504.380'), (1, '-500.690')] -[2023-11-28 04:45:49,924][87424] Updated weights for policy 0, policy_version 173987 (0.0009) -[2023-11-28 04:45:50,055][87426] Updated weights for policy 1, policy_version 173510 (0.0008) -[2023-11-28 04:45:50,318][87424] Updated weights for policy 0, policy_version 173997 (0.0011) -[2023-11-28 04:45:50,433][87426] Updated weights for policy 1, policy_version 173520 (0.0009) -[2023-11-28 04:45:50,691][87424] Updated weights for policy 0, policy_version 174007 (0.0012) -[2023-11-28 04:45:50,814][87426] Updated weights for policy 1, policy_version 173530 (0.0009) -[2023-11-28 04:45:52,827][87426] Updated weights for policy 1, policy_version 173540 (0.0009) -[2023-11-28 04:45:53,206][87426] Updated weights for policy 1, policy_version 173550 (0.0009) -[2023-11-28 04:45:53,317][87424] Updated weights for policy 0, policy_version 174017 (0.0011) -[2023-11-28 04:45:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 88973312. Throughput: 0: 2761.0, 1: 2695.6. Samples: 88996424. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:53,445][86177] Avg episode reward: [(0, '-504.250'), (1, '-500.630')] -[2023-11-28 04:45:53,590][87426] Updated weights for policy 1, policy_version 173560 (0.0011) -[2023-11-28 04:45:53,697][87424] Updated weights for policy 0, policy_version 174027 (0.0011) -[2023-11-28 04:45:54,084][87424] Updated weights for policy 0, policy_version 174037 (0.0009) -[2023-11-28 04:45:54,467][87424] Updated weights for policy 0, policy_version 174047 (0.0007) -[2023-11-28 04:45:55,332][87426] Updated weights for policy 1, policy_version 173570 (0.0010) -[2023-11-28 04:45:55,700][87426] Updated weights for policy 1, policy_version 173580 (0.0012) -[2023-11-28 04:45:56,074][87426] Updated weights for policy 1, policy_version 173590 (0.0011) -[2023-11-28 04:45:56,357][87424] Updated weights for policy 0, policy_version 174057 (0.0008) -[2023-11-28 04:45:56,458][87426] Updated weights for policy 1, policy_version 173600 (0.0009) -[2023-11-28 04:45:56,752][87424] Updated weights for policy 0, policy_version 174067 (0.0008) -[2023-11-28 04:45:57,133][87424] Updated weights for policy 0, policy_version 174077 (0.0010) -[2023-11-28 04:45:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89006080. Throughput: 0: 2751.8, 1: 2701.8. Samples: 89020948. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:45:58,445][86177] Avg episode reward: [(0, '-502.050'), (1, '-500.100')] -[2023-11-28 04:45:58,671][87426] Updated weights for policy 1, policy_version 173610 (0.0008) -[2023-11-28 04:45:59,052][87426] Updated weights for policy 1, policy_version 173620 (0.0008) -[2023-11-28 04:45:59,429][87426] Updated weights for policy 1, policy_version 173630 (0.0009) -[2023-11-28 04:45:59,678][87424] Updated weights for policy 0, policy_version 174087 (0.0008) -[2023-11-28 04:46:00,062][87424] Updated weights for policy 0, policy_version 174097 (0.0010) -[2023-11-28 04:46:00,446][87424] Updated weights for policy 0, policy_version 174107 (0.0011) -[2023-11-28 04:46:01,424][87426] Updated weights for policy 1, policy_version 173640 (0.0012) -[2023-11-28 04:46:01,805][87426] Updated weights for policy 1, policy_version 173650 (0.0012) -[2023-11-28 04:46:02,183][87426] Updated weights for policy 1, policy_version 173660 (0.0009) -[2023-11-28 04:46:02,480][87424] Updated weights for policy 0, policy_version 174117 (0.0012) -[2023-11-28 04:46:02,875][87424] Updated weights for policy 0, policy_version 174127 (0.0012) -[2023-11-28 04:46:03,252][87424] Updated weights for policy 0, policy_version 174137 (0.0012) -[2023-11-28 04:46:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89030656. Throughput: 0: 2736.8, 1: 2696.9. Samples: 89045476. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:46:03,445][86177] Avg episode reward: [(0, '-496.930'), (1, '-540.890')] -[2023-11-28 04:46:04,501][87426] Updated weights for policy 1, policy_version 173670 (0.0012) -[2023-11-28 04:46:04,874][87426] Updated weights for policy 1, policy_version 173680 (0.0012) -[2023-11-28 04:46:05,252][87426] Updated weights for policy 1, policy_version 173690 (0.0012) -[2023-11-28 04:46:05,705][87424] Updated weights for policy 0, policy_version 174147 (0.0011) -[2023-11-28 04:46:06,098][87424] Updated weights for policy 0, policy_version 174157 (0.0007) -[2023-11-28 04:46:06,485][87424] Updated weights for policy 0, policy_version 174167 (0.0007) -[2023-11-28 04:46:07,693][87426] Updated weights for policy 1, policy_version 173700 (0.0012) -[2023-11-28 04:46:08,072][87426] Updated weights for policy 1, policy_version 173710 (0.0012) -[2023-11-28 04:46:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 89055232. Throughput: 0: 2722.8, 1: 2688.7. Samples: 89076800. Policy #0 lag: (min: 27.0, avg: 51.7, max: 59.0) -[2023-11-28 04:46:08,445][86177] Avg episode reward: [(0, '-489.220'), (1, '-540.090')] -[2023-11-28 04:46:08,450][87426] Updated weights for policy 1, policy_version 173720 (0.0012) -[2023-11-28 04:46:08,747][87424] Updated weights for policy 0, policy_version 174177 (0.0008) -[2023-11-28 04:46:09,131][87424] Updated weights for policy 0, policy_version 174187 (0.0011) -[2023-11-28 04:46:09,515][87424] Updated weights for policy 0, policy_version 174197 (0.0011) -[2023-11-28 04:46:09,901][87424] Updated weights for policy 0, policy_version 174207 (0.0011) -[2023-11-28 04:46:11,080][87426] Updated weights for policy 1, policy_version 173730 (0.0011) -[2023-11-28 04:46:11,458][87426] Updated weights for policy 1, policy_version 173740 (0.0007) -[2023-11-28 04:46:11,837][87426] Updated weights for policy 1, policy_version 173750 (0.0011) -[2023-11-28 04:46:12,032][87424] Updated weights for policy 0, policy_version 174217 (0.0013) -[2023-11-28 04:46:12,217][87426] Updated weights for policy 1, policy_version 173760 (0.0012) -[2023-11-28 04:46:12,412][87424] Updated weights for policy 0, policy_version 174227 (0.0011) -[2023-11-28 04:46:12,802][87424] Updated weights for policy 0, policy_version 174237 (0.0011) -[2023-11-28 04:46:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 89088000. Throughput: 0: 2687.1, 1: 2645.2. Samples: 89098800. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:13,445][86177] Avg episode reward: [(0, '-488.080'), (1, '-539.010')] -[2023-11-28 04:46:14,804][87426] Updated weights for policy 1, policy_version 173770 (0.0008) -[2023-11-28 04:46:14,851][87424] Updated weights for policy 0, policy_version 174247 (0.0008) -[2023-11-28 04:46:15,175][87426] Updated weights for policy 1, policy_version 173780 (0.0010) -[2023-11-28 04:46:15,236][87424] Updated weights for policy 0, policy_version 174257 (0.0009) -[2023-11-28 04:46:15,555][87426] Updated weights for policy 1, policy_version 173790 (0.0010) -[2023-11-28 04:46:15,605][87424] Updated weights for policy 0, policy_version 174267 (0.0011) -[2023-11-28 04:46:17,728][87426] Updated weights for policy 1, policy_version 173800 (0.0010) -[2023-11-28 04:46:17,869][87424] Updated weights for policy 0, policy_version 174277 (0.0010) -[2023-11-28 04:46:18,114][87426] Updated weights for policy 1, policy_version 173810 (0.0007) -[2023-11-28 04:46:18,253][87424] Updated weights for policy 0, policy_version 174287 (0.0008) -[2023-11-28 04:46:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 89104384. Throughput: 0: 2689.2, 1: 2617.1. Samples: 89123244. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:18,445][86177] Avg episode reward: [(0, '-531.460'), (1, '-542.600')] -[2023-11-28 04:46:18,497][87426] Updated weights for policy 1, policy_version 173820 (0.0007) -[2023-11-28 04:46:18,643][87424] Updated weights for policy 0, policy_version 174297 (0.0007) -[2023-11-28 04:46:18,652][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000173824_44498944.pth... -[2023-11-28 04:46:18,698][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000171296_43851776.pth -[2023-11-28 04:46:18,903][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000174304_44621824.pth... -[2023-11-28 04:46:18,951][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000171744_43966464.pth -[2023-11-28 04:46:20,454][87426] Updated weights for policy 1, policy_version 173830 (0.0009) -[2023-11-28 04:46:20,557][87424] Updated weights for policy 0, policy_version 174307 (0.0012) -[2023-11-28 04:46:20,827][87426] Updated weights for policy 1, policy_version 173840 (0.0011) -[2023-11-28 04:46:20,949][87424] Updated weights for policy 0, policy_version 174317 (0.0012) -[2023-11-28 04:46:21,222][87426] Updated weights for policy 1, policy_version 173850 (0.0012) -[2023-11-28 04:46:21,326][87424] Updated weights for policy 0, policy_version 174327 (0.0010) -[2023-11-28 04:46:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 89137152. Throughput: 0: 2674.5, 1: 2651.9. Samples: 89156152. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:23,445][86177] Avg episode reward: [(0, '-535.520'), (1, '-545.230')] -[2023-11-28 04:46:23,471][87426] Updated weights for policy 1, policy_version 173860 (0.0011) -[2023-11-28 04:46:23,545][87424] Updated weights for policy 0, policy_version 174337 (0.0009) -[2023-11-28 04:46:23,858][87426] Updated weights for policy 1, policy_version 173870 (0.0012) -[2023-11-28 04:46:23,932][87424] Updated weights for policy 0, policy_version 174347 (0.0008) -[2023-11-28 04:46:24,231][87426] Updated weights for policy 1, policy_version 173880 (0.0009) -[2023-11-28 04:46:24,326][87424] Updated weights for policy 0, policy_version 174357 (0.0010) -[2023-11-28 04:46:24,706][87424] Updated weights for policy 0, policy_version 174367 (0.0007) -[2023-11-28 04:46:26,776][87426] Updated weights for policy 1, policy_version 173890 (0.0007) -[2023-11-28 04:46:26,999][87424] Updated weights for policy 0, policy_version 174377 (0.0011) -[2023-11-28 04:46:27,157][87426] Updated weights for policy 1, policy_version 173900 (0.0011) -[2023-11-28 04:46:27,387][87424] Updated weights for policy 0, policy_version 174387 (0.0009) -[2023-11-28 04:46:27,538][87426] Updated weights for policy 1, policy_version 173910 (0.0011) -[2023-11-28 04:46:27,771][87424] Updated weights for policy 0, policy_version 174397 (0.0007) -[2023-11-28 04:46:27,917][87426] Updated weights for policy 1, policy_version 173920 (0.0012) -[2023-11-28 04:46:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 89169920. Throughput: 0: 2688.4, 1: 2656.0. Samples: 89180136. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:28,445][86177] Avg episode reward: [(0, '-554.030'), (1, '-508.250')] -[2023-11-28 04:46:29,593][87424] Updated weights for policy 0, policy_version 174407 (0.0010) -[2023-11-28 04:46:29,654][87426] Updated weights for policy 1, policy_version 173930 (0.0012) -[2023-11-28 04:46:29,972][87424] Updated weights for policy 0, policy_version 174417 (0.0009) -[2023-11-28 04:46:30,026][87426] Updated weights for policy 1, policy_version 173940 (0.0014) -[2023-11-28 04:46:30,355][87424] Updated weights for policy 0, policy_version 174427 (0.0008) -[2023-11-28 04:46:30,404][87426] Updated weights for policy 1, policy_version 173950 (0.0008) -[2023-11-28 04:46:32,138][87424] Updated weights for policy 0, policy_version 174437 (0.0009) -[2023-11-28 04:46:32,522][87424] Updated weights for policy 0, policy_version 174447 (0.0012) -[2023-11-28 04:46:32,869][87426] Updated weights for policy 1, policy_version 173960 (0.0011) -[2023-11-28 04:46:32,907][87424] Updated weights for policy 0, policy_version 174457 (0.0011) -[2023-11-28 04:46:33,248][87426] Updated weights for policy 1, policy_version 173970 (0.0012) -[2023-11-28 04:46:33,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 89194496. Throughput: 0: 2725.3, 1: 2660.9. Samples: 89206372. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:33,446][86177] Avg episode reward: [(0, '-551.640'), (1, '-514.120')] -[2023-11-28 04:46:33,631][87426] Updated weights for policy 1, policy_version 173980 (0.0012) -[2023-11-28 04:46:35,227][87424] Updated weights for policy 0, policy_version 174467 (0.0010) -[2023-11-28 04:46:35,602][87424] Updated weights for policy 0, policy_version 174477 (0.0009) -[2023-11-28 04:46:35,906][87426] Updated weights for policy 1, policy_version 173990 (0.0011) -[2023-11-28 04:46:35,996][87424] Updated weights for policy 0, policy_version 174487 (0.0007) -[2023-11-28 04:46:36,290][87426] Updated weights for policy 1, policy_version 174000 (0.0008) -[2023-11-28 04:46:36,667][87426] Updated weights for policy 1, policy_version 174010 (0.0008) -[2023-11-28 04:46:38,388][87426] Updated weights for policy 1, policy_version 174020 (0.0009) -[2023-11-28 04:46:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 89219072. Throughput: 0: 2709.1, 1: 2665.9. Samples: 89238300. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:38,445][86177] Avg episode reward: [(0, '-541.650'), (1, '-515.300')] -[2023-11-28 04:46:38,489][87424] Updated weights for policy 0, policy_version 174497 (0.0007) -[2023-11-28 04:46:38,763][87426] Updated weights for policy 1, policy_version 174030 (0.0012) -[2023-11-28 04:46:38,872][87424] Updated weights for policy 0, policy_version 174507 (0.0008) -[2023-11-28 04:46:39,140][87426] Updated weights for policy 1, policy_version 174040 (0.0011) -[2023-11-28 04:46:39,260][87424] Updated weights for policy 0, policy_version 174517 (0.0011) -[2023-11-28 04:46:39,637][87424] Updated weights for policy 0, policy_version 174527 (0.0012) -[2023-11-28 04:46:41,580][87424] Updated weights for policy 0, policy_version 174537 (0.0010) -[2023-11-28 04:46:41,689][87426] Updated weights for policy 1, policy_version 174050 (0.0012) -[2023-11-28 04:46:41,958][87424] Updated weights for policy 0, policy_version 174547 (0.0010) -[2023-11-28 04:46:42,066][87426] Updated weights for policy 1, policy_version 174060 (0.0012) -[2023-11-28 04:46:42,342][87424] Updated weights for policy 0, policy_version 174557 (0.0010) -[2023-11-28 04:46:42,440][87426] Updated weights for policy 1, policy_version 174070 (0.0011) -[2023-11-28 04:46:42,822][87426] Updated weights for policy 1, policy_version 174080 (0.0012) -[2023-11-28 04:46:43,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 89251840. Throughput: 0: 2714.7, 1: 2647.0. Samples: 89262224. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:43,445][86177] Avg episode reward: [(0, '-523.070'), (1, '-513.250')] -[2023-11-28 04:46:44,517][87424] Updated weights for policy 0, policy_version 174567 (0.0012) -[2023-11-28 04:46:44,896][87424] Updated weights for policy 0, policy_version 174577 (0.0012) -[2023-11-28 04:46:44,951][87426] Updated weights for policy 1, policy_version 174090 (0.0010) -[2023-11-28 04:46:45,278][87424] Updated weights for policy 0, policy_version 174587 (0.0011) -[2023-11-28 04:46:45,325][87426] Updated weights for policy 1, policy_version 174100 (0.0011) -[2023-11-28 04:46:45,704][87426] Updated weights for policy 1, policy_version 174110 (0.0009) -[2023-11-28 04:46:47,519][87424] Updated weights for policy 0, policy_version 174597 (0.0008) -[2023-11-28 04:46:47,676][87426] Updated weights for policy 1, policy_version 174120 (0.0008) -[2023-11-28 04:46:47,906][87424] Updated weights for policy 0, policy_version 174607 (0.0007) -[2023-11-28 04:46:48,048][87426] Updated weights for policy 1, policy_version 174130 (0.0010) -[2023-11-28 04:46:48,285][87424] Updated weights for policy 0, policy_version 174617 (0.0007) -[2023-11-28 04:46:48,429][87426] Updated weights for policy 1, policy_version 174140 (0.0007) -[2023-11-28 04:46:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 89268224. Throughput: 0: 2738.8, 1: 2654.6. Samples: 89288180. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:48,445][86177] Avg episode reward: [(0, '-521.980'), (1, '-507.490')] -[2023-11-28 04:46:50,194][87424] Updated weights for policy 0, policy_version 174627 (0.0007) -[2023-11-28 04:46:50,509][87426] Updated weights for policy 1, policy_version 174150 (0.0010) -[2023-11-28 04:46:50,569][87424] Updated weights for policy 0, policy_version 174637 (0.0008) -[2023-11-28 04:46:50,888][87426] Updated weights for policy 1, policy_version 174160 (0.0011) -[2023-11-28 04:46:50,956][87424] Updated weights for policy 0, policy_version 174647 (0.0008) -[2023-11-28 04:46:51,268][87426] Updated weights for policy 1, policy_version 174170 (0.0010) -[2023-11-28 04:46:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89300992. Throughput: 0: 2749.4, 1: 2675.7. Samples: 89320932. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:53,445][86177] Avg episode reward: [(0, '-495.410'), (1, '-514.230')] -[2023-11-28 04:46:53,471][87424] Updated weights for policy 0, policy_version 174657 (0.0008) -[2023-11-28 04:46:53,541][87426] Updated weights for policy 1, policy_version 174180 (0.0009) -[2023-11-28 04:46:53,844][87424] Updated weights for policy 0, policy_version 174667 (0.0009) -[2023-11-28 04:46:53,917][87426] Updated weights for policy 1, policy_version 174190 (0.0010) -[2023-11-28 04:46:54,227][87424] Updated weights for policy 0, policy_version 174677 (0.0008) -[2023-11-28 04:46:54,293][87426] Updated weights for policy 1, policy_version 174200 (0.0009) -[2023-11-28 04:46:54,619][87424] Updated weights for policy 0, policy_version 174687 (0.0008) -[2023-11-28 04:46:56,188][87426] Updated weights for policy 1, policy_version 174210 (0.0007) -[2023-11-28 04:46:56,563][87426] Updated weights for policy 1, policy_version 174220 (0.0007) -[2023-11-28 04:46:56,913][87424] Updated weights for policy 0, policy_version 174697 (0.0012) -[2023-11-28 04:46:56,942][87426] Updated weights for policy 1, policy_version 174230 (0.0007) -[2023-11-28 04:46:57,303][87424] Updated weights for policy 0, policy_version 174707 (0.0012) -[2023-11-28 04:46:57,329][87426] Updated weights for policy 1, policy_version 174240 (0.0007) -[2023-11-28 04:46:57,684][87424] Updated weights for policy 0, policy_version 174717 (0.0012) -[2023-11-28 04:46:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 89333760. Throughput: 0: 2754.6, 1: 2740.3. Samples: 89346068. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:46:58,445][86177] Avg episode reward: [(0, '-492.530'), (1, '-509.870')] -[2023-11-28 04:46:59,149][87426] Updated weights for policy 1, policy_version 174250 (0.0009) -[2023-11-28 04:46:59,454][87424] Updated weights for policy 0, policy_version 174727 (0.0010) -[2023-11-28 04:46:59,525][87426] Updated weights for policy 1, policy_version 174260 (0.0007) -[2023-11-28 04:46:59,834][87424] Updated weights for policy 0, policy_version 174737 (0.0008) -[2023-11-28 04:46:59,917][87426] Updated weights for policy 1, policy_version 174270 (0.0009) -[2023-11-28 04:47:00,219][87424] Updated weights for policy 0, policy_version 174747 (0.0012) -[2023-11-28 04:47:02,341][87426] Updated weights for policy 1, policy_version 174280 (0.0011) -[2023-11-28 04:47:02,446][87424] Updated weights for policy 0, policy_version 174757 (0.0012) -[2023-11-28 04:47:02,709][87426] Updated weights for policy 1, policy_version 174290 (0.0011) -[2023-11-28 04:47:02,829][87424] Updated weights for policy 0, policy_version 174767 (0.0012) -[2023-11-28 04:47:03,088][87426] Updated weights for policy 1, policy_version 174300 (0.0011) -[2023-11-28 04:47:03,217][87424] Updated weights for policy 0, policy_version 174777 (0.0011) -[2023-11-28 04:47:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89358336. Throughput: 0: 2746.7, 1: 2747.8. Samples: 89370496. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:47:03,445][86177] Avg episode reward: [(0, '-493.750'), (1, '-511.720')] -[2023-11-28 04:47:05,298][87424] Updated weights for policy 0, policy_version 174787 (0.0010) -[2023-11-28 04:47:05,674][87426] Updated weights for policy 1, policy_version 174310 (0.0009) -[2023-11-28 04:47:05,679][87424] Updated weights for policy 0, policy_version 174797 (0.0008) -[2023-11-28 04:47:06,043][87426] Updated weights for policy 1, policy_version 174320 (0.0007) -[2023-11-28 04:47:06,060][87424] Updated weights for policy 0, policy_version 174807 (0.0007) -[2023-11-28 04:47:06,422][87426] Updated weights for policy 1, policy_version 174330 (0.0007) -[2023-11-28 04:47:08,041][87424] Updated weights for policy 0, policy_version 174817 (0.0008) -[2023-11-28 04:47:08,431][87424] Updated weights for policy 0, policy_version 174827 (0.0007) -[2023-11-28 04:47:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89382912. Throughput: 0: 2750.5, 1: 2707.2. Samples: 89401748. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:47:08,445][86177] Avg episode reward: [(0, '-501.120'), (1, '-510.690')] -[2023-11-28 04:47:08,806][87424] Updated weights for policy 0, policy_version 174837 (0.0008) -[2023-11-28 04:47:08,998][87426] Updated weights for policy 1, policy_version 174340 (0.0009) -[2023-11-28 04:47:09,195][87424] Updated weights for policy 0, policy_version 174847 (0.0011) -[2023-11-28 04:47:09,375][87426] Updated weights for policy 1, policy_version 174350 (0.0010) -[2023-11-28 04:47:09,755][87426] Updated weights for policy 1, policy_version 174360 (0.0008) -[2023-11-28 04:47:11,744][87424] Updated weights for policy 0, policy_version 174857 (0.0012) -[2023-11-28 04:47:11,853][87426] Updated weights for policy 1, policy_version 174370 (0.0010) -[2023-11-28 04:47:12,123][87424] Updated weights for policy 0, policy_version 174867 (0.0011) -[2023-11-28 04:47:12,227][87426] Updated weights for policy 1, policy_version 174380 (0.0011) -[2023-11-28 04:47:12,496][87424] Updated weights for policy 0, policy_version 174877 (0.0012) -[2023-11-28 04:47:12,613][87426] Updated weights for policy 1, policy_version 174390 (0.0010) -[2023-11-28 04:47:12,982][87426] Updated weights for policy 1, policy_version 174400 (0.0009) -[2023-11-28 04:47:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 89415680. Throughput: 0: 2749.0, 1: 2698.8. Samples: 89425288. Policy #0 lag: (min: 19.0, avg: 49.1, max: 74.0) -[2023-11-28 04:47:13,445][86177] Avg episode reward: [(0, '-500.360'), (1, '-506.180')] -[2023-11-28 04:47:14,380][87424] Updated weights for policy 0, policy_version 174887 (0.0011) -[2023-11-28 04:47:14,771][87424] Updated weights for policy 0, policy_version 174897 (0.0012) -[2023-11-28 04:47:15,147][87424] Updated weights for policy 0, policy_version 174907 (0.0012) -[2023-11-28 04:47:15,561][87426] Updated weights for policy 1, policy_version 174410 (0.0011) -[2023-11-28 04:47:15,938][87426] Updated weights for policy 1, policy_version 174420 (0.0012) -[2023-11-28 04:47:16,321][87426] Updated weights for policy 1, policy_version 174430 (0.0012) -[2023-11-28 04:47:17,269][87424] Updated weights for policy 0, policy_version 174917 (0.0011) -[2023-11-28 04:47:17,655][87424] Updated weights for policy 0, policy_version 174927 (0.0012) -[2023-11-28 04:47:18,033][87424] Updated weights for policy 0, policy_version 174937 (0.0012) -[2023-11-28 04:47:18,393][87426] Updated weights for policy 1, policy_version 174440 (0.0011) -[2023-11-28 04:47:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 89440256. Throughput: 0: 2732.0, 1: 2677.2. Samples: 89449784. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:47:18,446][86177] Avg episode reward: [(0, '-501.470'), (1, '-506.890')] -[2023-11-28 04:47:18,763][87426] Updated weights for policy 1, policy_version 174450 (0.0011) -[2023-11-28 04:47:19,141][87426] Updated weights for policy 1, policy_version 174460 (0.0009) -[2023-11-28 04:47:19,892][87424] Updated weights for policy 0, policy_version 174947 (0.0010) -[2023-11-28 04:47:20,274][87424] Updated weights for policy 0, policy_version 174957 (0.0010) -[2023-11-28 04:47:20,658][87424] Updated weights for policy 0, policy_version 174967 (0.0009) -[2023-11-28 04:47:21,705][87426] Updated weights for policy 1, policy_version 174470 (0.0010) -[2023-11-28 04:47:22,087][87426] Updated weights for policy 1, policy_version 174480 (0.0009) -[2023-11-28 04:47:22,475][87426] Updated weights for policy 1, policy_version 174490 (0.0009) -[2023-11-28 04:47:22,782][87424] Updated weights for policy 0, policy_version 174977 (0.0008) -[2023-11-28 04:47:23,165][87424] Updated weights for policy 0, policy_version 174987 (0.0012) -[2023-11-28 04:47:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89464832. Throughput: 0: 2763.8, 1: 2647.0. Samples: 89481788. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:47:23,445][86177] Avg episode reward: [(0, '-503.760'), (1, '-513.990')] -[2023-11-28 04:47:23,550][87424] Updated weights for policy 0, policy_version 174997 (0.0012) -[2023-11-28 04:47:23,921][87424] Updated weights for policy 0, policy_version 175007 (0.0012) -[2023-11-28 04:47:24,981][87426] Updated weights for policy 1, policy_version 174500 (0.0010) -[2023-11-28 04:47:25,365][87426] Updated weights for policy 1, policy_version 174510 (0.0011) -[2023-11-28 04:47:25,741][87426] Updated weights for policy 1, policy_version 174520 (0.0011) -[2023-11-28 04:47:26,499][87424] Updated weights for policy 0, policy_version 175017 (0.0012) -[2023-11-28 04:47:26,883][87424] Updated weights for policy 0, policy_version 175027 (0.0012) -[2023-11-28 04:47:27,258][87424] Updated weights for policy 0, policy_version 175037 (0.0012) -[2023-11-28 04:47:27,938][87426] Updated weights for policy 1, policy_version 174530 (0.0012) -[2023-11-28 04:47:28,320][87426] Updated weights for policy 1, policy_version 174540 (0.0012) -[2023-11-28 04:47:28,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 89489408. Throughput: 0: 2772.1, 1: 2650.0. Samples: 89506220. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:47:28,446][86177] Avg episode reward: [(0, '-497.900'), (1, '-513.750')] -[2023-11-28 04:47:28,706][87426] Updated weights for policy 1, policy_version 174550 (0.0011) -[2023-11-28 04:47:29,065][87424] Updated weights for policy 0, policy_version 175047 (0.0012) -[2023-11-28 04:47:29,082][87426] Updated weights for policy 1, policy_version 174560 (0.0011) -[2023-11-28 04:47:29,440][87424] Updated weights for policy 0, policy_version 175057 (0.0012) -[2023-11-28 04:47:29,819][87424] Updated weights for policy 0, policy_version 175067 (0.0011) -[2023-11-28 04:47:31,337][87426] Updated weights for policy 1, policy_version 174570 (0.0011) -[2023-11-28 04:47:31,719][87426] Updated weights for policy 1, policy_version 174580 (0.0012) -[2023-11-28 04:47:32,095][87426] Updated weights for policy 1, policy_version 174590 (0.0012) -[2023-11-28 04:47:32,111][87424] Updated weights for policy 0, policy_version 175077 (0.0009) -[2023-11-28 04:47:32,489][87424] Updated weights for policy 0, policy_version 175087 (0.0011) -[2023-11-28 04:47:32,874][87424] Updated weights for policy 0, policy_version 175097 (0.0010) -[2023-11-28 04:47:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 89522176. Throughput: 0: 2746.5, 1: 2646.9. Samples: 89530884. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:47:33,445][86177] Avg episode reward: [(0, '-505.150'), (1, '-521.590')] -[2023-11-28 04:47:34,061][87426] Updated weights for policy 1, policy_version 174600 (0.0008) -[2023-11-28 04:47:34,452][87426] Updated weights for policy 1, policy_version 174610 (0.0007) -[2023-11-28 04:47:34,778][87424] Updated weights for policy 0, policy_version 175107 (0.0009) -[2023-11-28 04:47:34,828][87426] Updated weights for policy 1, policy_version 174620 (0.0008) -[2023-11-28 04:47:35,172][87424] Updated weights for policy 0, policy_version 175117 (0.0011) -[2023-11-28 04:47:35,551][87424] Updated weights for policy 0, policy_version 175127 (0.0009) -[2023-11-28 04:47:36,997][87426] Updated weights for policy 1, policy_version 174630 (0.0009) -[2023-11-28 04:47:37,371][87426] Updated weights for policy 1, policy_version 174640 (0.0009) -[2023-11-28 04:47:37,757][87426] Updated weights for policy 1, policy_version 174650 (0.0007) -[2023-11-28 04:47:38,013][87424] Updated weights for policy 0, policy_version 175137 (0.0007) -[2023-11-28 04:47:38,399][87424] Updated weights for policy 0, policy_version 175147 (0.0009) -[2023-11-28 04:47:38,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89546752. Throughput: 0: 2724.8, 1: 2642.7. Samples: 89562468. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:47:38,445][86177] Avg episode reward: [(0, '-504.780'), (1, '-521.080')] -[2023-11-28 04:47:38,780][87424] Updated weights for policy 0, policy_version 175157 (0.0007) -[2023-11-28 04:47:39,163][87424] Updated weights for policy 0, policy_version 175167 (0.0009) -[2023-11-28 04:47:39,773][87426] Updated weights for policy 1, policy_version 174660 (0.0008) -[2023-11-28 04:47:40,151][87426] Updated weights for policy 1, policy_version 174670 (0.0010) -[2023-11-28 04:47:40,531][87426] Updated weights for policy 1, policy_version 174680 (0.0009) -[2023-11-28 04:47:41,770][87424] Updated weights for policy 0, policy_version 175177 (0.0012) -[2023-11-28 04:47:42,153][87424] Updated weights for policy 0, policy_version 175187 (0.0010) -[2023-11-28 04:47:42,538][87424] Updated weights for policy 0, policy_version 175197 (0.0012) -[2023-11-28 04:47:42,709][87426] Updated weights for policy 1, policy_version 174690 (0.0012) -[2023-11-28 04:47:43,090][87426] Updated weights for policy 1, policy_version 174700 (0.0012) -[2023-11-28 04:47:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 89571328. Throughput: 0: 2709.0, 1: 2624.4. Samples: 89586072. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:47:43,445][86177] Avg episode reward: [(0, '-504.800'), (1, '-517.030')] -[2023-11-28 04:47:43,473][87426] Updated weights for policy 1, policy_version 174710 (0.0012) -[2023-11-28 04:47:43,841][87426] Updated weights for policy 1, policy_version 174720 (0.0012) -[2023-11-28 04:47:45,259][87424] Updated weights for policy 0, policy_version 175207 (0.0009) -[2023-11-28 04:47:45,641][87424] Updated weights for policy 0, policy_version 175217 (0.0008) -[2023-11-28 04:47:46,020][87424] Updated weights for policy 0, policy_version 175227 (0.0009) -[2023-11-28 04:47:46,336][87426] Updated weights for policy 1, policy_version 174730 (0.0010) -[2023-11-28 04:47:46,717][87426] Updated weights for policy 1, policy_version 174740 (0.0008) -[2023-11-28 04:47:47,105][87426] Updated weights for policy 1, policy_version 174750 (0.0007) -[2023-11-28 04:47:47,886][87424] Updated weights for policy 0, policy_version 175237 (0.0011) -[2023-11-28 04:47:48,269][87424] Updated weights for policy 0, policy_version 175247 (0.0012) -[2023-11-28 04:47:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 89595904. Throughput: 0: 2698.6, 1: 2626.0. Samples: 89610104. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:47:48,445][86177] Avg episode reward: [(0, '-506.560'), (1, '-523.510')] -[2023-11-28 04:47:48,649][87424] Updated weights for policy 0, policy_version 175257 (0.0010) -[2023-11-28 04:47:48,864][87426] Updated weights for policy 1, policy_version 174760 (0.0010) -[2023-11-28 04:47:49,245][87426] Updated weights for policy 1, policy_version 174770 (0.0009) -[2023-11-28 04:47:49,625][87426] Updated weights for policy 1, policy_version 174780 (0.0007) -[2023-11-28 04:47:50,749][87424] Updated weights for policy 0, policy_version 175267 (0.0009) -[2023-11-28 04:47:51,132][87424] Updated weights for policy 0, policy_version 175277 (0.0011) -[2023-11-28 04:47:51,517][87424] Updated weights for policy 0, policy_version 175287 (0.0012) -[2023-11-28 04:47:51,955][87426] Updated weights for policy 1, policy_version 174790 (0.0010) -[2023-11-28 04:47:52,337][87426] Updated weights for policy 1, policy_version 174800 (0.0010) -[2023-11-28 04:47:52,715][87426] Updated weights for policy 1, policy_version 174810 (0.0009) -[2023-11-28 04:47:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 89628672. Throughput: 0: 2698.2, 1: 2675.6. Samples: 89643568. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:47:53,445][86177] Avg episode reward: [(0, '-499.060'), (1, '-518.700')] -[2023-11-28 04:47:53,901][87424] Updated weights for policy 0, policy_version 175297 (0.0012) -[2023-11-28 04:47:54,290][87424] Updated weights for policy 0, policy_version 175307 (0.0010) -[2023-11-28 04:47:54,671][87424] Updated weights for policy 0, policy_version 175317 (0.0012) -[2023-11-28 04:47:54,983][87426] Updated weights for policy 1, policy_version 174820 (0.0010) -[2023-11-28 04:47:55,052][87424] Updated weights for policy 0, policy_version 175327 (0.0010) -[2023-11-28 04:47:55,372][87426] Updated weights for policy 1, policy_version 174830 (0.0008) -[2023-11-28 04:47:55,746][87426] Updated weights for policy 1, policy_version 174840 (0.0007) -[2023-11-28 04:47:57,247][87424] Updated weights for policy 0, policy_version 175337 (0.0007) -[2023-11-28 04:47:57,624][87424] Updated weights for policy 0, policy_version 175347 (0.0008) -[2023-11-28 04:47:57,959][87426] Updated weights for policy 1, policy_version 174850 (0.0008) -[2023-11-28 04:47:58,012][87424] Updated weights for policy 0, policy_version 175357 (0.0007) -[2023-11-28 04:47:58,339][87426] Updated weights for policy 1, policy_version 174860 (0.0008) -[2023-11-28 04:47:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 89653248. Throughput: 0: 2694.6, 1: 2689.2. Samples: 89667560. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:47:58,445][86177] Avg episode reward: [(0, '-497.780'), (1, '-516.400')] -[2023-11-28 04:47:58,719][87426] Updated weights for policy 1, policy_version 174870 (0.0009) -[2023-11-28 04:47:59,096][87426] Updated weights for policy 1, policy_version 174880 (0.0010) -[2023-11-28 04:48:00,228][87424] Updated weights for policy 0, policy_version 175367 (0.0010) -[2023-11-28 04:48:00,607][87424] Updated weights for policy 0, policy_version 175377 (0.0011) -[2023-11-28 04:48:00,984][87424] Updated weights for policy 0, policy_version 175387 (0.0010) -[2023-11-28 04:48:01,108][87426] Updated weights for policy 1, policy_version 174890 (0.0012) -[2023-11-28 04:48:01,490][87426] Updated weights for policy 1, policy_version 174900 (0.0012) -[2023-11-28 04:48:01,876][87426] Updated weights for policy 1, policy_version 174910 (0.0011) -[2023-11-28 04:48:03,141][87424] Updated weights for policy 0, policy_version 175397 (0.0009) -[2023-11-28 04:48:03,445][86177] Fps is (10 sec: 4914.7, 60 sec: 5324.7, 300 sec: 5387.3). Total num frames: 89677824. Throughput: 0: 2692.0, 1: 2701.5. Samples: 89692496. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:48:03,446][86177] Avg episode reward: [(0, '-490.830'), (1, '-520.690')] -[2023-11-28 04:48:03,516][87424] Updated weights for policy 0, policy_version 175407 (0.0008) -[2023-11-28 04:48:03,897][87424] Updated weights for policy 0, policy_version 175417 (0.0007) -[2023-11-28 04:48:03,948][87426] Updated weights for policy 1, policy_version 174920 (0.0009) -[2023-11-28 04:48:04,326][87426] Updated weights for policy 1, policy_version 174930 (0.0008) -[2023-11-28 04:48:04,707][87426] Updated weights for policy 1, policy_version 174940 (0.0011) -[2023-11-28 04:48:06,017][87424] Updated weights for policy 0, policy_version 175427 (0.0008) -[2023-11-28 04:48:06,404][87424] Updated weights for policy 0, policy_version 175437 (0.0008) -[2023-11-28 04:48:06,780][87424] Updated weights for policy 0, policy_version 175447 (0.0008) -[2023-11-28 04:48:06,911][87426] Updated weights for policy 1, policy_version 174950 (0.0011) -[2023-11-28 04:48:07,290][87426] Updated weights for policy 1, policy_version 174960 (0.0012) -[2023-11-28 04:48:07,668][87426] Updated weights for policy 1, policy_version 174970 (0.0012) -[2023-11-28 04:48:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 89710592. Throughput: 0: 2678.8, 1: 2749.5. Samples: 89726064. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:48:08,445][86177] Avg episode reward: [(0, '-492.150'), (1, '-515.470')] -[2023-11-28 04:48:08,536][87424] Updated weights for policy 0, policy_version 175457 (0.0008) -[2023-11-28 04:48:08,914][87424] Updated weights for policy 0, policy_version 175467 (0.0008) -[2023-11-28 04:48:09,296][87424] Updated weights for policy 0, policy_version 175477 (0.0008) -[2023-11-28 04:48:09,595][87426] Updated weights for policy 1, policy_version 174980 (0.0012) -[2023-11-28 04:48:09,680][87424] Updated weights for policy 0, policy_version 175487 (0.0008) -[2023-11-28 04:48:09,975][87426] Updated weights for policy 1, policy_version 174990 (0.0012) -[2023-11-28 04:48:10,359][87426] Updated weights for policy 1, policy_version 175000 (0.0012) -[2023-11-28 04:48:11,723][87424] Updated weights for policy 0, policy_version 175497 (0.0012) -[2023-11-28 04:48:12,105][87424] Updated weights for policy 0, policy_version 175507 (0.0012) -[2023-11-28 04:48:12,485][87424] Updated weights for policy 0, policy_version 175517 (0.0012) -[2023-11-28 04:48:12,767][87426] Updated weights for policy 1, policy_version 175010 (0.0010) -[2023-11-28 04:48:13,156][87426] Updated weights for policy 1, policy_version 175020 (0.0010) -[2023-11-28 04:48:13,444][86177] Fps is (10 sec: 5735.0, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 89735168. Throughput: 0: 2686.0, 1: 2739.9. Samples: 89750384. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:48:13,445][86177] Avg episode reward: [(0, '-488.700'), (1, '-520.680')] -[2023-11-28 04:48:13,542][87426] Updated weights for policy 1, policy_version 175030 (0.0011) -[2023-11-28 04:48:13,914][87426] Updated weights for policy 1, policy_version 175040 (0.0010) -[2023-11-28 04:48:14,811][87424] Updated weights for policy 0, policy_version 175527 (0.0011) -[2023-11-28 04:48:15,203][87424] Updated weights for policy 0, policy_version 175537 (0.0012) -[2023-11-28 04:48:15,579][87424] Updated weights for policy 0, policy_version 175547 (0.0012) -[2023-11-28 04:48:16,447][87426] Updated weights for policy 1, policy_version 175050 (0.0008) -[2023-11-28 04:48:16,836][87426] Updated weights for policy 1, policy_version 175060 (0.0009) -[2023-11-28 04:48:17,212][87426] Updated weights for policy 1, policy_version 175070 (0.0011) -[2023-11-28 04:48:17,953][87424] Updated weights for policy 0, policy_version 175557 (0.0012) -[2023-11-28 04:48:18,331][87424] Updated weights for policy 0, policy_version 175567 (0.0012) -[2023-11-28 04:48:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 89759744. Throughput: 0: 2686.2, 1: 2732.3. Samples: 89774716. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:48:18,445][86177] Avg episode reward: [(0, '-490.250'), (1, '-523.030')] -[2023-11-28 04:48:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000175072_44818432.pth... -[2023-11-28 04:48:18,498][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000172576_44179456.pth -[2023-11-28 04:48:18,715][87424] Updated weights for policy 0, policy_version 175577 (0.0012) -[2023-11-28 04:48:18,971][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000175584_44949504.pth... -[2023-11-28 04:48:19,018][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000173024_44294144.pth -[2023-11-28 04:48:19,264][87426] Updated weights for policy 1, policy_version 175080 (0.0011) -[2023-11-28 04:48:19,638][87426] Updated weights for policy 1, policy_version 175090 (0.0011) -[2023-11-28 04:48:20,025][87426] Updated weights for policy 1, policy_version 175100 (0.0011) -[2023-11-28 04:48:20,904][87424] Updated weights for policy 0, policy_version 175587 (0.0011) -[2023-11-28 04:48:21,290][87424] Updated weights for policy 0, policy_version 175597 (0.0012) -[2023-11-28 04:48:21,669][87424] Updated weights for policy 0, policy_version 175607 (0.0012) -[2023-11-28 04:48:22,262][87426] Updated weights for policy 1, policy_version 175110 (0.0011) -[2023-11-28 04:48:22,635][87426] Updated weights for policy 1, policy_version 175120 (0.0011) -[2023-11-28 04:48:23,013][87426] Updated weights for policy 1, policy_version 175130 (0.0011) -[2023-11-28 04:48:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 89792512. Throughput: 0: 2703.4, 1: 2738.1. Samples: 89807336. Policy #0 lag: (min: 26.0, avg: 44.8, max: 58.0) -[2023-11-28 04:48:23,445][86177] Avg episode reward: [(0, '-490.000'), (1, '-516.130')] -[2023-11-28 04:48:23,661][87424] Updated weights for policy 0, policy_version 175617 (0.0012) -[2023-11-28 04:48:24,029][87424] Updated weights for policy 0, policy_version 175627 (0.0012) -[2023-11-28 04:48:24,424][87424] Updated weights for policy 0, policy_version 175637 (0.0012) -[2023-11-28 04:48:24,814][87424] Updated weights for policy 0, policy_version 175647 (0.0011) -[2023-11-28 04:48:25,270][87426] Updated weights for policy 1, policy_version 175140 (0.0010) -[2023-11-28 04:48:25,650][87426] Updated weights for policy 1, policy_version 175150 (0.0012) -[2023-11-28 04:48:26,039][87426] Updated weights for policy 1, policy_version 175160 (0.0012) -[2023-11-28 04:48:27,110][87424] Updated weights for policy 0, policy_version 175657 (0.0007) -[2023-11-28 04:48:27,492][87424] Updated weights for policy 0, policy_version 175667 (0.0007) -[2023-11-28 04:48:27,867][87424] Updated weights for policy 0, policy_version 175677 (0.0007) -[2023-11-28 04:48:28,002][87426] Updated weights for policy 1, policy_version 175170 (0.0011) -[2023-11-28 04:48:28,379][87426] Updated weights for policy 1, policy_version 175180 (0.0010) -[2023-11-28 04:48:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 89817088. Throughput: 0: 2720.8, 1: 2724.8. Samples: 89831124. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:48:28,445][86177] Avg episode reward: [(0, '-490.590'), (1, '-524.560')] -[2023-11-28 04:48:28,762][87426] Updated weights for policy 1, policy_version 175190 (0.0011) -[2023-11-28 04:48:29,141][87426] Updated weights for policy 1, policy_version 175200 (0.0008) -[2023-11-28 04:48:30,033][87424] Updated weights for policy 0, policy_version 175687 (0.0010) -[2023-11-28 04:48:30,417][87424] Updated weights for policy 0, policy_version 175697 (0.0012) -[2023-11-28 04:48:30,806][87424] Updated weights for policy 0, policy_version 175707 (0.0011) -[2023-11-28 04:48:31,661][87426] Updated weights for policy 1, policy_version 175210 (0.0008) -[2023-11-28 04:48:32,036][87426] Updated weights for policy 1, policy_version 175220 (0.0011) -[2023-11-28 04:48:32,412][87426] Updated weights for policy 1, policy_version 175230 (0.0011) -[2023-11-28 04:48:32,913][87424] Updated weights for policy 0, policy_version 175717 (0.0011) -[2023-11-28 04:48:33,297][87424] Updated weights for policy 0, policy_version 175727 (0.0011) -[2023-11-28 04:48:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 89841664. Throughput: 0: 2736.9, 1: 2726.7. Samples: 89855964. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:48:33,445][86177] Avg episode reward: [(0, '-493.100'), (1, '-522.060')] -[2023-11-28 04:48:33,674][87424] Updated weights for policy 0, policy_version 175737 (0.0011) -[2023-11-28 04:48:34,424][87426] Updated weights for policy 1, policy_version 175240 (0.0008) -[2023-11-28 04:48:34,805][87426] Updated weights for policy 1, policy_version 175250 (0.0008) -[2023-11-28 04:48:35,186][87426] Updated weights for policy 1, policy_version 175260 (0.0009) -[2023-11-28 04:48:35,642][87424] Updated weights for policy 0, policy_version 175747 (0.0011) -[2023-11-28 04:48:36,018][87424] Updated weights for policy 0, policy_version 175757 (0.0012) -[2023-11-28 04:48:36,412][87424] Updated weights for policy 0, policy_version 175767 (0.0012) -[2023-11-28 04:48:37,128][87426] Updated weights for policy 1, policy_version 175270 (0.0008) -[2023-11-28 04:48:37,508][87426] Updated weights for policy 1, policy_version 175280 (0.0008) -[2023-11-28 04:48:37,887][87426] Updated weights for policy 1, policy_version 175290 (0.0008) -[2023-11-28 04:48:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 89874432. Throughput: 0: 2731.6, 1: 2720.3. Samples: 89888904. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:48:38,445][86177] Avg episode reward: [(0, '-500.730'), (1, '-518.410')] -[2023-11-28 04:48:38,786][87424] Updated weights for policy 0, policy_version 175777 (0.0012) -[2023-11-28 04:48:39,172][87424] Updated weights for policy 0, policy_version 175787 (0.0012) -[2023-11-28 04:48:39,552][87424] Updated weights for policy 0, policy_version 175797 (0.0012) -[2023-11-28 04:48:39,937][87424] Updated weights for policy 0, policy_version 175807 (0.0012) -[2023-11-28 04:48:40,416][87426] Updated weights for policy 1, policy_version 175300 (0.0009) -[2023-11-28 04:48:40,787][87426] Updated weights for policy 1, policy_version 175310 (0.0012) -[2023-11-28 04:48:41,167][87426] Updated weights for policy 1, policy_version 175320 (0.0011) -[2023-11-28 04:48:42,496][87424] Updated weights for policy 0, policy_version 175817 (0.0012) -[2023-11-28 04:48:42,881][87424] Updated weights for policy 0, policy_version 175827 (0.0012) -[2023-11-28 04:48:43,219][87426] Updated weights for policy 1, policy_version 175330 (0.0011) -[2023-11-28 04:48:43,259][87424] Updated weights for policy 0, policy_version 175837 (0.0011) -[2023-11-28 04:48:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89899008. Throughput: 0: 2728.3, 1: 2728.9. Samples: 89913132. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:48:43,445][86177] Avg episode reward: [(0, '-545.180'), (1, '-529.880')] -[2023-11-28 04:48:43,597][87426] Updated weights for policy 1, policy_version 175340 (0.0012) -[2023-11-28 04:48:43,966][87426] Updated weights for policy 1, policy_version 175350 (0.0012) -[2023-11-28 04:48:44,339][87426] Updated weights for policy 1, policy_version 175360 (0.0012) -[2023-11-28 04:48:45,221][87424] Updated weights for policy 0, policy_version 175847 (0.0011) -[2023-11-28 04:48:45,617][87424] Updated weights for policy 0, policy_version 175857 (0.0011) -[2023-11-28 04:48:45,995][87424] Updated weights for policy 0, policy_version 175867 (0.0009) -[2023-11-28 04:48:46,391][87426] Updated weights for policy 1, policy_version 175370 (0.0010) -[2023-11-28 04:48:46,768][87426] Updated weights for policy 1, policy_version 175380 (0.0012) -[2023-11-28 04:48:47,146][87426] Updated weights for policy 1, policy_version 175390 (0.0011) -[2023-11-28 04:48:48,159][87424] Updated weights for policy 0, policy_version 175877 (0.0009) -[2023-11-28 04:48:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89923584. Throughput: 0: 2713.9, 1: 2746.2. Samples: 89938196. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:48:48,445][86177] Avg episode reward: [(0, '-551.340'), (1, '-516.770')] -[2023-11-28 04:48:48,546][87424] Updated weights for policy 0, policy_version 175887 (0.0012) -[2023-11-28 04:48:48,916][87424] Updated weights for policy 0, policy_version 175897 (0.0012) -[2023-11-28 04:48:49,110][87426] Updated weights for policy 1, policy_version 175400 (0.0011) -[2023-11-28 04:48:49,495][87426] Updated weights for policy 1, policy_version 175410 (0.0011) -[2023-11-28 04:48:49,874][87426] Updated weights for policy 1, policy_version 175420 (0.0012) -[2023-11-28 04:48:50,980][87424] Updated weights for policy 0, policy_version 175907 (0.0012) -[2023-11-28 04:48:51,358][87424] Updated weights for policy 0, policy_version 175917 (0.0012) -[2023-11-28 04:48:51,742][87424] Updated weights for policy 0, policy_version 175927 (0.0012) -[2023-11-28 04:48:52,112][87426] Updated weights for policy 1, policy_version 175430 (0.0010) -[2023-11-28 04:48:52,486][87426] Updated weights for policy 1, policy_version 175440 (0.0011) -[2023-11-28 04:48:52,861][87426] Updated weights for policy 1, policy_version 175450 (0.0011) -[2023-11-28 04:48:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89956352. Throughput: 0: 2711.9, 1: 2717.5. Samples: 89970388. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:48:53,445][86177] Avg episode reward: [(0, '-549.790'), (1, '-523.430')] -[2023-11-28 04:48:54,220][87424] Updated weights for policy 0, policy_version 175937 (0.0011) -[2023-11-28 04:48:54,607][87424] Updated weights for policy 0, policy_version 175947 (0.0011) -[2023-11-28 04:48:54,990][87424] Updated weights for policy 0, policy_version 175957 (0.0008) -[2023-11-28 04:48:55,154][87426] Updated weights for policy 1, policy_version 175460 (0.0012) -[2023-11-28 04:48:55,375][87424] Updated weights for policy 0, policy_version 175967 (0.0008) -[2023-11-28 04:48:55,530][87426] Updated weights for policy 1, policy_version 175470 (0.0012) -[2023-11-28 04:48:55,909][87426] Updated weights for policy 1, policy_version 175480 (0.0011) -[2023-11-28 04:48:57,432][87424] Updated weights for policy 0, policy_version 175977 (0.0007) -[2023-11-28 04:48:57,813][87424] Updated weights for policy 0, policy_version 175987 (0.0007) -[2023-11-28 04:48:57,916][87426] Updated weights for policy 1, policy_version 175490 (0.0011) -[2023-11-28 04:48:58,199][87424] Updated weights for policy 0, policy_version 175997 (0.0007) -[2023-11-28 04:48:58,296][87426] Updated weights for policy 1, policy_version 175500 (0.0010) -[2023-11-28 04:48:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 89980928. Throughput: 0: 2690.8, 1: 2725.7. Samples: 89994128. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:48:58,445][86177] Avg episode reward: [(0, '-539.770'), (1, '-523.960')] -[2023-11-28 04:48:58,693][87426] Updated weights for policy 1, policy_version 175510 (0.0007) -[2023-11-28 04:48:59,077][87426] Updated weights for policy 1, policy_version 175520 (0.0008) -[2023-11-28 04:48:59,857][87424] Updated weights for policy 0, policy_version 176007 (0.0011) -[2023-11-28 04:49:00,241][87424] Updated weights for policy 0, policy_version 176017 (0.0015) -[2023-11-28 04:49:00,620][87424] Updated weights for policy 0, policy_version 176027 (0.0011) -[2023-11-28 04:49:01,631][87426] Updated weights for policy 1, policy_version 175530 (0.0008) -[2023-11-28 04:49:02,013][87426] Updated weights for policy 1, policy_version 175540 (0.0009) -[2023-11-28 04:49:02,395][87426] Updated weights for policy 1, policy_version 175550 (0.0012) -[2023-11-28 04:49:02,734][87424] Updated weights for policy 0, policy_version 176037 (0.0012) -[2023-11-28 04:49:03,120][87424] Updated weights for policy 0, policy_version 176047 (0.0008) -[2023-11-28 04:49:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 90005504. Throughput: 0: 2720.9, 1: 2710.9. Samples: 90019144. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:49:03,445][86177] Avg episode reward: [(0, '-501.840'), (1, '-523.680')] -[2023-11-28 04:49:03,499][87424] Updated weights for policy 0, policy_version 176057 (0.0007) -[2023-11-28 04:49:04,146][87426] Updated weights for policy 1, policy_version 175560 (0.0012) -[2023-11-28 04:49:04,525][87426] Updated weights for policy 1, policy_version 175570 (0.0012) -[2023-11-28 04:49:04,892][87426] Updated weights for policy 1, policy_version 175580 (0.0012) -[2023-11-28 04:49:05,779][87424] Updated weights for policy 0, policy_version 176067 (0.0009) -[2023-11-28 04:49:06,160][87424] Updated weights for policy 0, policy_version 176077 (0.0012) -[2023-11-28 04:49:06,546][87424] Updated weights for policy 0, policy_version 176087 (0.0012) -[2023-11-28 04:49:07,336][87426] Updated weights for policy 1, policy_version 175590 (0.0012) -[2023-11-28 04:49:07,709][87426] Updated weights for policy 1, policy_version 175600 (0.0012) -[2023-11-28 04:49:08,094][87426] Updated weights for policy 1, policy_version 175610 (0.0012) -[2023-11-28 04:49:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90038272. Throughput: 0: 2716.3, 1: 2718.9. Samples: 90051924. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:49:08,445][86177] Avg episode reward: [(0, '-496.500'), (1, '-523.660')] -[2023-11-28 04:49:08,866][87424] Updated weights for policy 0, policy_version 176097 (0.0012) -[2023-11-28 04:49:09,245][87424] Updated weights for policy 0, policy_version 176107 (0.0007) -[2023-11-28 04:49:09,629][87424] Updated weights for policy 0, policy_version 176117 (0.0007) -[2023-11-28 04:49:09,955][87426] Updated weights for policy 1, policy_version 175620 (0.0011) -[2023-11-28 04:49:10,008][87424] Updated weights for policy 0, policy_version 176127 (0.0010) -[2023-11-28 04:49:10,332][87426] Updated weights for policy 1, policy_version 175630 (0.0011) -[2023-11-28 04:49:10,712][87426] Updated weights for policy 1, policy_version 175640 (0.0009) -[2023-11-28 04:49:12,319][87424] Updated weights for policy 0, policy_version 176137 (0.0010) -[2023-11-28 04:49:12,699][87424] Updated weights for policy 0, policy_version 176147 (0.0010) -[2023-11-28 04:49:13,093][87424] Updated weights for policy 0, policy_version 176157 (0.0011) -[2023-11-28 04:49:13,300][87426] Updated weights for policy 1, policy_version 175650 (0.0009) -[2023-11-28 04:49:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90062848. Throughput: 0: 2730.8, 1: 2715.5. Samples: 90076204. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:49:13,445][86177] Avg episode reward: [(0, '-501.160'), (1, '-503.940')] -[2023-11-28 04:49:13,673][87426] Updated weights for policy 1, policy_version 175660 (0.0012) -[2023-11-28 04:49:14,053][87426] Updated weights for policy 1, policy_version 175670 (0.0012) -[2023-11-28 04:49:14,435][87426] Updated weights for policy 1, policy_version 175680 (0.0012) -[2023-11-28 04:49:15,536][87424] Updated weights for policy 0, policy_version 176167 (0.0012) -[2023-11-28 04:49:15,920][87424] Updated weights for policy 0, policy_version 176177 (0.0011) -[2023-11-28 04:49:16,298][87424] Updated weights for policy 0, policy_version 176187 (0.0011) -[2023-11-28 04:49:16,546][87426] Updated weights for policy 1, policy_version 175690 (0.0009) -[2023-11-28 04:49:16,927][87426] Updated weights for policy 1, policy_version 175700 (0.0009) -[2023-11-28 04:49:17,306][87426] Updated weights for policy 1, policy_version 175710 (0.0008) -[2023-11-28 04:49:17,968][87424] Updated weights for policy 0, policy_version 176197 (0.0012) -[2023-11-28 04:49:18,360][87424] Updated weights for policy 0, policy_version 176207 (0.0012) -[2023-11-28 04:49:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90087424. Throughput: 0: 2699.8, 1: 2720.4. Samples: 90099872. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:49:18,445][86177] Avg episode reward: [(0, '-515.650'), (1, '-499.350')] -[2023-11-28 04:49:18,744][87424] Updated weights for policy 0, policy_version 176217 (0.0012) -[2023-11-28 04:49:19,352][87426] Updated weights for policy 1, policy_version 175720 (0.0008) -[2023-11-28 04:49:19,733][87426] Updated weights for policy 1, policy_version 175730 (0.0008) -[2023-11-28 04:49:20,114][87426] Updated weights for policy 1, policy_version 175740 (0.0010) -[2023-11-28 04:49:20,916][87424] Updated weights for policy 0, policy_version 176227 (0.0010) -[2023-11-28 04:49:21,301][87424] Updated weights for policy 0, policy_version 176237 (0.0010) -[2023-11-28 04:49:21,682][87424] Updated weights for policy 0, policy_version 176247 (0.0011) -[2023-11-28 04:49:22,643][87426] Updated weights for policy 1, policy_version 175750 (0.0012) -[2023-11-28 04:49:23,011][87426] Updated weights for policy 1, policy_version 175760 (0.0011) -[2023-11-28 04:49:23,388][87426] Updated weights for policy 1, policy_version 175770 (0.0011) -[2023-11-28 04:49:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 90112000. Throughput: 0: 2716.1, 1: 2716.3. Samples: 90133360. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:49:23,445][86177] Avg episode reward: [(0, '-511.590'), (1, '-498.050')] -[2023-11-28 04:49:23,736][87424] Updated weights for policy 0, policy_version 176257 (0.0011) -[2023-11-28 04:49:24,114][87424] Updated weights for policy 0, policy_version 176267 (0.0012) -[2023-11-28 04:49:24,497][87424] Updated weights for policy 0, policy_version 176277 (0.0012) -[2023-11-28 04:49:24,875][87424] Updated weights for policy 0, policy_version 176287 (0.0012) -[2023-11-28 04:49:25,619][87426] Updated weights for policy 1, policy_version 175780 (0.0010) -[2023-11-28 04:49:26,004][87426] Updated weights for policy 1, policy_version 175790 (0.0012) -[2023-11-28 04:49:26,378][87426] Updated weights for policy 1, policy_version 175800 (0.0011) -[2023-11-28 04:49:26,603][87424] Updated weights for policy 0, policy_version 176297 (0.0011) -[2023-11-28 04:49:26,987][87424] Updated weights for policy 0, policy_version 176307 (0.0011) -[2023-11-28 04:49:27,367][87424] Updated weights for policy 0, policy_version 176317 (0.0011) -[2023-11-28 04:49:28,303][87426] Updated weights for policy 1, policy_version 175810 (0.0012) -[2023-11-28 04:49:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90144768. Throughput: 0: 2744.9, 1: 2696.2. Samples: 90157980. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:49:28,446][86177] Avg episode reward: [(0, '-506.430'), (1, '-499.830')] -[2023-11-28 04:49:28,684][87426] Updated weights for policy 1, policy_version 175820 (0.0012) -[2023-11-28 04:49:29,068][87426] Updated weights for policy 1, policy_version 175830 (0.0009) -[2023-11-28 04:49:29,451][87426] Updated weights for policy 1, policy_version 175840 (0.0007) -[2023-11-28 04:49:29,745][87424] Updated weights for policy 0, policy_version 176327 (0.0008) -[2023-11-28 04:49:30,127][87424] Updated weights for policy 0, policy_version 176337 (0.0012) -[2023-11-28 04:49:30,515][87424] Updated weights for policy 0, policy_version 176347 (0.0012) -[2023-11-28 04:49:31,781][87426] Updated weights for policy 1, policy_version 175850 (0.0011) -[2023-11-28 04:49:32,160][87426] Updated weights for policy 1, policy_version 175860 (0.0010) -[2023-11-28 04:49:32,543][87426] Updated weights for policy 1, policy_version 175870 (0.0010) -[2023-11-28 04:49:32,598][87424] Updated weights for policy 0, policy_version 176357 (0.0011) -[2023-11-28 04:49:32,979][87424] Updated weights for policy 0, policy_version 176367 (0.0009) -[2023-11-28 04:49:33,364][87424] Updated weights for policy 0, policy_version 176377 (0.0009) -[2023-11-28 04:49:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 90169344. Throughput: 0: 2747.5, 1: 2693.5. Samples: 90183044. Policy #0 lag: (min: 31.0, avg: 44.3, max: 63.0) -[2023-11-28 04:49:33,446][86177] Avg episode reward: [(0, '-524.310'), (1, '-500.040')] -[2023-11-28 04:49:34,548][87426] Updated weights for policy 1, policy_version 175880 (0.0008) -[2023-11-28 04:49:34,924][87426] Updated weights for policy 1, policy_version 175890 (0.0009) -[2023-11-28 04:49:35,316][87426] Updated weights for policy 1, policy_version 175900 (0.0010) -[2023-11-28 04:49:35,484][87424] Updated weights for policy 0, policy_version 176387 (0.0011) -[2023-11-28 04:49:35,879][87424] Updated weights for policy 0, policy_version 176397 (0.0012) -[2023-11-28 04:49:36,248][87424] Updated weights for policy 0, policy_version 176407 (0.0012) -[2023-11-28 04:49:37,463][87426] Updated weights for policy 1, policy_version 175910 (0.0012) -[2023-11-28 04:49:37,839][87426] Updated weights for policy 1, policy_version 175920 (0.0012) -[2023-11-28 04:49:38,223][87426] Updated weights for policy 1, policy_version 175930 (0.0012) -[2023-11-28 04:49:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90202112. Throughput: 0: 2749.1, 1: 2703.3. Samples: 90215744. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:49:38,445][86177] Avg episode reward: [(0, '-514.020'), (1, '-500.950')] -[2023-11-28 04:49:38,707][87424] Updated weights for policy 0, policy_version 176417 (0.0012) -[2023-11-28 04:49:39,086][87424] Updated weights for policy 0, policy_version 176427 (0.0011) -[2023-11-28 04:49:39,462][87424] Updated weights for policy 0, policy_version 176437 (0.0012) -[2023-11-28 04:49:39,836][87424] Updated weights for policy 0, policy_version 176447 (0.0011) -[2023-11-28 04:49:40,844][87426] Updated weights for policy 1, policy_version 175940 (0.0010) -[2023-11-28 04:49:41,228][87426] Updated weights for policy 1, policy_version 175950 (0.0009) -[2023-11-28 04:49:41,605][87426] Updated weights for policy 1, policy_version 175960 (0.0009) -[2023-11-28 04:49:41,813][87424] Updated weights for policy 0, policy_version 176457 (0.0009) -[2023-11-28 04:49:42,199][87424] Updated weights for policy 0, policy_version 176467 (0.0011) -[2023-11-28 04:49:42,578][87424] Updated weights for policy 0, policy_version 176477 (0.0010) -[2023-11-28 04:49:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90226688. Throughput: 0: 2755.5, 1: 2680.7. Samples: 90238756. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:49:43,445][86177] Avg episode reward: [(0, '-516.160'), (1, '-501.520')] -[2023-11-28 04:49:43,870][87426] Updated weights for policy 1, policy_version 175970 (0.0009) -[2023-11-28 04:49:44,250][87426] Updated weights for policy 1, policy_version 175980 (0.0008) -[2023-11-28 04:49:44,640][87426] Updated weights for policy 1, policy_version 175990 (0.0007) -[2023-11-28 04:49:44,831][87424] Updated weights for policy 0, policy_version 176487 (0.0012) -[2023-11-28 04:49:45,018][87426] Updated weights for policy 1, policy_version 176000 (0.0007) -[2023-11-28 04:49:45,206][87424] Updated weights for policy 0, policy_version 176497 (0.0012) -[2023-11-28 04:49:45,584][87424] Updated weights for policy 0, policy_version 176507 (0.0012) -[2023-11-28 04:49:47,449][87426] Updated weights for policy 1, policy_version 176010 (0.0011) -[2023-11-28 04:49:47,632][87424] Updated weights for policy 0, policy_version 176517 (0.0012) -[2023-11-28 04:49:47,838][87426] Updated weights for policy 1, policy_version 176020 (0.0008) -[2023-11-28 04:49:48,015][87424] Updated weights for policy 0, policy_version 176527 (0.0012) -[2023-11-28 04:49:48,214][87426] Updated weights for policy 1, policy_version 176030 (0.0007) -[2023-11-28 04:49:48,393][87424] Updated weights for policy 0, policy_version 176537 (0.0012) -[2023-11-28 04:49:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90251264. Throughput: 0: 2738.5, 1: 2687.6. Samples: 90263316. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:49:48,445][86177] Avg episode reward: [(0, '-525.490'), (1, '-524.100')] -[2023-11-28 04:49:50,537][87426] Updated weights for policy 1, policy_version 176040 (0.0009) -[2023-11-28 04:49:50,897][87424] Updated weights for policy 0, policy_version 176547 (0.0011) -[2023-11-28 04:49:50,913][87426] Updated weights for policy 1, policy_version 176050 (0.0009) -[2023-11-28 04:49:51,289][87424] Updated weights for policy 0, policy_version 176557 (0.0010) -[2023-11-28 04:49:51,292][87426] Updated weights for policy 1, policy_version 176060 (0.0010) -[2023-11-28 04:49:51,669][87424] Updated weights for policy 0, policy_version 176567 (0.0008) -[2023-11-28 04:49:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 90275840. Throughput: 0: 2743.6, 1: 2651.8. Samples: 90294716. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:49:53,446][86177] Avg episode reward: [(0, '-511.910'), (1, '-525.980')] -[2023-11-28 04:49:53,643][87426] Updated weights for policy 1, policy_version 176070 (0.0012) -[2023-11-28 04:49:54,026][87426] Updated weights for policy 1, policy_version 176080 (0.0012) -[2023-11-28 04:49:54,080][87424] Updated weights for policy 0, policy_version 176577 (0.0008) -[2023-11-28 04:49:54,403][87426] Updated weights for policy 1, policy_version 176090 (0.0012) -[2023-11-28 04:49:54,469][87424] Updated weights for policy 0, policy_version 176587 (0.0008) -[2023-11-28 04:49:54,855][87424] Updated weights for policy 0, policy_version 176597 (0.0007) -[2023-11-28 04:49:55,247][87424] Updated weights for policy 0, policy_version 176607 (0.0008) -[2023-11-28 04:49:56,620][87426] Updated weights for policy 1, policy_version 176100 (0.0009) -[2023-11-28 04:49:57,005][87426] Updated weights for policy 1, policy_version 176110 (0.0012) -[2023-11-28 04:49:57,375][87426] Updated weights for policy 1, policy_version 176120 (0.0011) -[2023-11-28 04:49:57,481][87424] Updated weights for policy 0, policy_version 176617 (0.0010) -[2023-11-28 04:49:57,865][87424] Updated weights for policy 0, policy_version 176627 (0.0007) -[2023-11-28 04:49:58,243][87424] Updated weights for policy 0, policy_version 176637 (0.0008) -[2023-11-28 04:49:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90308608. Throughput: 0: 2731.2, 1: 2667.0. Samples: 90319124. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:49:58,445][86177] Avg episode reward: [(0, '-547.040'), (1, '-529.210')] -[2023-11-28 04:49:59,351][87426] Updated weights for policy 1, policy_version 176130 (0.0011) -[2023-11-28 04:49:59,730][87426] Updated weights for policy 1, policy_version 176140 (0.0012) -[2023-11-28 04:50:00,114][87426] Updated weights for policy 1, policy_version 176150 (0.0012) -[2023-11-28 04:50:00,392][87424] Updated weights for policy 0, policy_version 176647 (0.0009) -[2023-11-28 04:50:00,486][87426] Updated weights for policy 1, policy_version 176160 (0.0011) -[2023-11-28 04:50:00,772][87424] Updated weights for policy 0, policy_version 176657 (0.0008) -[2023-11-28 04:50:01,157][87424] Updated weights for policy 0, policy_version 176667 (0.0009) -[2023-11-28 04:50:02,345][87426] Updated weights for policy 1, policy_version 176170 (0.0012) -[2023-11-28 04:50:02,720][87426] Updated weights for policy 1, policy_version 176180 (0.0010) -[2023-11-28 04:50:03,091][87426] Updated weights for policy 1, policy_version 176190 (0.0010) -[2023-11-28 04:50:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90333184. Throughput: 0: 2750.7, 1: 2685.1. Samples: 90344480. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:50:03,445][86177] Avg episode reward: [(0, '-546.810'), (1, '-529.430')] -[2023-11-28 04:50:03,490][87424] Updated weights for policy 0, policy_version 176677 (0.0009) -[2023-11-28 04:50:03,864][87424] Updated weights for policy 0, policy_version 176687 (0.0008) -[2023-11-28 04:50:04,246][87424] Updated weights for policy 0, policy_version 176697 (0.0009) -[2023-11-28 04:50:05,564][87426] Updated weights for policy 1, policy_version 176200 (0.0008) -[2023-11-28 04:50:05,943][87426] Updated weights for policy 1, policy_version 176210 (0.0007) -[2023-11-28 04:50:06,315][87426] Updated weights for policy 1, policy_version 176220 (0.0009) -[2023-11-28 04:50:06,480][87424] Updated weights for policy 0, policy_version 176707 (0.0009) -[2023-11-28 04:50:06,861][87424] Updated weights for policy 0, policy_version 176717 (0.0008) -[2023-11-28 04:50:07,244][87424] Updated weights for policy 0, policy_version 176727 (0.0009) -[2023-11-28 04:50:08,054][87426] Updated weights for policy 1, policy_version 176230 (0.0009) -[2023-11-28 04:50:08,439][87426] Updated weights for policy 1, policy_version 176240 (0.0010) -[2023-11-28 04:50:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 90357760. Throughput: 0: 2727.1, 1: 2694.7. Samples: 90377340. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:50:08,445][86177] Avg episode reward: [(0, '-584.060'), (1, '-506.010')] -[2023-11-28 04:50:08,815][87426] Updated weights for policy 1, policy_version 176250 (0.0010) -[2023-11-28 04:50:09,376][87424] Updated weights for policy 0, policy_version 176737 (0.0010) -[2023-11-28 04:50:09,751][87424] Updated weights for policy 0, policy_version 176747 (0.0011) -[2023-11-28 04:50:10,131][87424] Updated weights for policy 0, policy_version 176757 (0.0015) -[2023-11-28 04:50:10,515][87424] Updated weights for policy 0, policy_version 176767 (0.0011) -[2023-11-28 04:50:10,776][87426] Updated weights for policy 1, policy_version 176260 (0.0011) -[2023-11-28 04:50:11,162][87426] Updated weights for policy 1, policy_version 176270 (0.0012) -[2023-11-28 04:50:11,540][87426] Updated weights for policy 1, policy_version 176280 (0.0011) -[2023-11-28 04:50:12,935][87424] Updated weights for policy 0, policy_version 176777 (0.0010) -[2023-11-28 04:50:13,318][87424] Updated weights for policy 0, policy_version 176787 (0.0008) -[2023-11-28 04:50:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 90382336. Throughput: 0: 2704.3, 1: 2714.9. Samples: 90401844. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:50:13,445][86177] Avg episode reward: [(0, '-579.550'), (1, '-539.560')] -[2023-11-28 04:50:13,702][87424] Updated weights for policy 0, policy_version 176797 (0.0007) -[2023-11-28 04:50:13,892][87426] Updated weights for policy 1, policy_version 176290 (0.0011) -[2023-11-28 04:50:14,265][87426] Updated weights for policy 1, policy_version 176300 (0.0007) -[2023-11-28 04:50:14,652][87426] Updated weights for policy 1, policy_version 176310 (0.0008) -[2023-11-28 04:50:15,040][87426] Updated weights for policy 1, policy_version 176320 (0.0008) -[2023-11-28 04:50:15,962][87424] Updated weights for policy 0, policy_version 176807 (0.0010) -[2023-11-28 04:50:16,344][87424] Updated weights for policy 0, policy_version 176817 (0.0011) -[2023-11-28 04:50:16,724][87424] Updated weights for policy 0, policy_version 176827 (0.0011) -[2023-11-28 04:50:16,944][87426] Updated weights for policy 1, policy_version 176330 (0.0007) -[2023-11-28 04:50:17,325][87426] Updated weights for policy 1, policy_version 176340 (0.0008) -[2023-11-28 04:50:17,705][87426] Updated weights for policy 1, policy_version 176350 (0.0007) -[2023-11-28 04:50:18,388][87424] Updated weights for policy 0, policy_version 176837 (0.0010) -[2023-11-28 04:50:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90415104. Throughput: 0: 2689.5, 1: 2709.3. Samples: 90425992. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:50:18,445][86177] Avg episode reward: [(0, '-540.540'), (1, '-538.710')] -[2023-11-28 04:50:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000176352_45146112.pth... -[2023-11-28 04:50:18,493][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000173824_44498944.pth -[2023-11-28 04:50:18,773][87424] Updated weights for policy 0, policy_version 176847 (0.0008) -[2023-11-28 04:50:19,158][87424] Updated weights for policy 0, policy_version 176857 (0.0010) -[2023-11-28 04:50:19,419][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000176864_45277184.pth... -[2023-11-28 04:50:19,467][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000174304_44621824.pth -[2023-11-28 04:50:19,535][87426] Updated weights for policy 1, policy_version 176360 (0.0011) -[2023-11-28 04:50:19,909][87426] Updated weights for policy 1, policy_version 176370 (0.0012) -[2023-11-28 04:50:20,292][87426] Updated weights for policy 1, policy_version 176380 (0.0011) -[2023-11-28 04:50:20,934][87424] Updated weights for policy 0, policy_version 176867 (0.0010) -[2023-11-28 04:50:21,314][87424] Updated weights for policy 0, policy_version 176877 (0.0010) -[2023-11-28 04:50:21,691][87424] Updated weights for policy 0, policy_version 176887 (0.0011) -[2023-11-28 04:50:22,354][87426] Updated weights for policy 1, policy_version 176390 (0.0012) -[2023-11-28 04:50:22,729][87426] Updated weights for policy 1, policy_version 176400 (0.0011) -[2023-11-28 04:50:23,114][87426] Updated weights for policy 1, policy_version 176410 (0.0011) -[2023-11-28 04:50:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 90447872. Throughput: 0: 2699.2, 1: 2694.2. Samples: 90458448. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:50:23,445][86177] Avg episode reward: [(0, '-537.540'), (1, '-539.570')] -[2023-11-28 04:50:24,036][87424] Updated weights for policy 0, policy_version 176897 (0.0012) -[2023-11-28 04:50:24,422][87424] Updated weights for policy 0, policy_version 176907 (0.0008) -[2023-11-28 04:50:24,809][87424] Updated weights for policy 0, policy_version 176917 (0.0011) -[2023-11-28 04:50:25,071][87426] Updated weights for policy 1, policy_version 176420 (0.0010) -[2023-11-28 04:50:25,188][87424] Updated weights for policy 0, policy_version 176927 (0.0012) -[2023-11-28 04:50:25,447][87426] Updated weights for policy 1, policy_version 176430 (0.0008) -[2023-11-28 04:50:25,830][87426] Updated weights for policy 1, policy_version 176440 (0.0007) -[2023-11-28 04:50:27,253][87424] Updated weights for policy 0, policy_version 176937 (0.0009) -[2023-11-28 04:50:27,633][87424] Updated weights for policy 0, policy_version 176947 (0.0010) -[2023-11-28 04:50:28,022][87424] Updated weights for policy 0, policy_version 176957 (0.0011) -[2023-11-28 04:50:28,058][87426] Updated weights for policy 1, policy_version 176450 (0.0008) -[2023-11-28 04:50:28,425][87426] Updated weights for policy 1, policy_version 176460 (0.0012) -[2023-11-28 04:50:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90472448. Throughput: 0: 2697.3, 1: 2729.2. Samples: 90482948. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:50:28,445][86177] Avg episode reward: [(0, '-490.020'), (1, '-541.540')] -[2023-11-28 04:50:28,802][87426] Updated weights for policy 1, policy_version 176470 (0.0012) -[2023-11-28 04:50:29,175][87426] Updated weights for policy 1, policy_version 176480 (0.0008) -[2023-11-28 04:50:29,799][87424] Updated weights for policy 0, policy_version 176967 (0.0010) -[2023-11-28 04:50:30,178][87424] Updated weights for policy 0, policy_version 176977 (0.0012) -[2023-11-28 04:50:30,561][87424] Updated weights for policy 0, policy_version 176987 (0.0011) -[2023-11-28 04:50:31,777][87426] Updated weights for policy 1, policy_version 176490 (0.0011) -[2023-11-28 04:50:32,155][87426] Updated weights for policy 1, policy_version 176500 (0.0010) -[2023-11-28 04:50:32,539][87426] Updated weights for policy 1, policy_version 176510 (0.0008) -[2023-11-28 04:50:33,175][87424] Updated weights for policy 0, policy_version 176997 (0.0011) -[2023-11-28 04:50:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90497024. Throughput: 0: 2712.5, 1: 2744.4. Samples: 90508876. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:50:33,445][86177] Avg episode reward: [(0, '-530.090'), (1, '-504.560')] -[2023-11-28 04:50:33,562][87424] Updated weights for policy 0, policy_version 177007 (0.0011) -[2023-11-28 04:50:33,940][87424] Updated weights for policy 0, policy_version 177017 (0.0011) -[2023-11-28 04:50:34,947][87426] Updated weights for policy 1, policy_version 176520 (0.0011) -[2023-11-28 04:50:35,325][87426] Updated weights for policy 1, policy_version 176530 (0.0012) -[2023-11-28 04:50:35,698][87426] Updated weights for policy 1, policy_version 176540 (0.0011) -[2023-11-28 04:50:36,481][87424] Updated weights for policy 0, policy_version 177027 (0.0012) -[2023-11-28 04:50:36,854][87424] Updated weights for policy 0, policy_version 177037 (0.0011) -[2023-11-28 04:50:37,230][87424] Updated weights for policy 0, policy_version 177047 (0.0011) -[2023-11-28 04:50:37,727][87426] Updated weights for policy 1, policy_version 176550 (0.0010) -[2023-11-28 04:50:38,105][87426] Updated weights for policy 1, policy_version 176560 (0.0007) -[2023-11-28 04:50:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 90521600. Throughput: 0: 2713.1, 1: 2762.0. Samples: 90541092. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 04:50:38,445][86177] Avg episode reward: [(0, '-529.110'), (1, '-507.840')] -[2023-11-28 04:50:38,484][87426] Updated weights for policy 1, policy_version 176570 (0.0008) -[2023-11-28 04:50:38,977][87424] Updated weights for policy 0, policy_version 177057 (0.0012) -[2023-11-28 04:50:39,361][87424] Updated weights for policy 0, policy_version 177067 (0.0012) -[2023-11-28 04:50:39,742][87424] Updated weights for policy 0, policy_version 177077 (0.0012) -[2023-11-28 04:50:40,122][87424] Updated weights for policy 0, policy_version 177087 (0.0011) -[2023-11-28 04:50:40,670][87426] Updated weights for policy 1, policy_version 176580 (0.0008) -[2023-11-28 04:50:41,033][87426] Updated weights for policy 1, policy_version 176590 (0.0008) -[2023-11-28 04:50:41,413][87426] Updated weights for policy 1, policy_version 176600 (0.0009) -[2023-11-28 04:50:42,500][87424] Updated weights for policy 0, policy_version 177097 (0.0011) -[2023-11-28 04:50:42,882][87424] Updated weights for policy 0, policy_version 177107 (0.0011) -[2023-11-28 04:50:43,265][87424] Updated weights for policy 0, policy_version 177117 (0.0008) -[2023-11-28 04:50:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90554368. Throughput: 0: 2723.4, 1: 2754.5. Samples: 90565628. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:50:43,445][86177] Avg episode reward: [(0, '-533.720'), (1, '-507.960')] -[2023-11-28 04:50:43,998][87426] Updated weights for policy 1, policy_version 176610 (0.0011) -[2023-11-28 04:50:44,377][87426] Updated weights for policy 1, policy_version 176620 (0.0007) -[2023-11-28 04:50:44,757][87426] Updated weights for policy 1, policy_version 176630 (0.0007) -[2023-11-28 04:50:45,143][87426] Updated weights for policy 1, policy_version 176640 (0.0010) -[2023-11-28 04:50:45,207][87424] Updated weights for policy 0, policy_version 177127 (0.0011) -[2023-11-28 04:50:45,593][87424] Updated weights for policy 0, policy_version 177137 (0.0012) -[2023-11-28 04:50:45,971][87424] Updated weights for policy 0, policy_version 177147 (0.0012) -[2023-11-28 04:50:47,004][87426] Updated weights for policy 1, policy_version 176650 (0.0012) -[2023-11-28 04:50:47,378][87426] Updated weights for policy 1, policy_version 176660 (0.0010) -[2023-11-28 04:50:47,755][87426] Updated weights for policy 1, policy_version 176670 (0.0009) -[2023-11-28 04:50:47,837][87424] Updated weights for policy 0, policy_version 177157 (0.0012) -[2023-11-28 04:50:48,220][87424] Updated weights for policy 0, policy_version 177167 (0.0012) -[2023-11-28 04:50:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90578944. Throughput: 0: 2731.9, 1: 2737.7. Samples: 90590612. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:50:48,446][86177] Avg episode reward: [(0, '-565.070'), (1, '-512.010')] -[2023-11-28 04:50:48,605][87424] Updated weights for policy 0, policy_version 177177 (0.0012) -[2023-11-28 04:50:49,978][87426] Updated weights for policy 1, policy_version 176680 (0.0011) -[2023-11-28 04:50:50,364][87426] Updated weights for policy 1, policy_version 176690 (0.0012) -[2023-11-28 04:50:50,763][87426] Updated weights for policy 1, policy_version 176700 (0.0012) -[2023-11-28 04:50:51,037][87424] Updated weights for policy 0, policy_version 177187 (0.0012) -[2023-11-28 04:50:51,419][87424] Updated weights for policy 0, policy_version 177197 (0.0012) -[2023-11-28 04:50:51,801][87424] Updated weights for policy 0, policy_version 177207 (0.0011) -[2023-11-28 04:50:52,805][87426] Updated weights for policy 1, policy_version 176710 (0.0011) -[2023-11-28 04:50:53,171][87426] Updated weights for policy 1, policy_version 176720 (0.0012) -[2023-11-28 04:50:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90603520. Throughput: 0: 2745.0, 1: 2726.1. Samples: 90623540. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:50:53,445][86177] Avg episode reward: [(0, '-563.060'), (1, '-529.200')] -[2023-11-28 04:50:53,552][87426] Updated weights for policy 1, policy_version 176730 (0.0011) -[2023-11-28 04:50:54,003][87424] Updated weights for policy 0, policy_version 177217 (0.0010) -[2023-11-28 04:50:54,393][87424] Updated weights for policy 0, policy_version 177227 (0.0011) -[2023-11-28 04:50:54,765][87424] Updated weights for policy 0, policy_version 177237 (0.0010) -[2023-11-28 04:50:55,152][87424] Updated weights for policy 0, policy_version 177247 (0.0008) -[2023-11-28 04:50:55,954][87426] Updated weights for policy 1, policy_version 176740 (0.0012) -[2023-11-28 04:50:56,340][87426] Updated weights for policy 1, policy_version 176750 (0.0012) -[2023-11-28 04:50:56,713][87426] Updated weights for policy 1, policy_version 176760 (0.0012) -[2023-11-28 04:50:57,177][87424] Updated weights for policy 0, policy_version 177257 (0.0008) -[2023-11-28 04:50:57,576][87424] Updated weights for policy 0, policy_version 177267 (0.0007) -[2023-11-28 04:50:57,955][87424] Updated weights for policy 0, policy_version 177277 (0.0007) -[2023-11-28 04:50:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90636288. Throughput: 0: 2747.1, 1: 2730.7. Samples: 90648344. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:50:58,445][86177] Avg episode reward: [(0, '-564.080'), (1, '-530.110')] -[2023-11-28 04:50:58,935][87426] Updated weights for policy 1, policy_version 176770 (0.0012) -[2023-11-28 04:50:59,317][87426] Updated weights for policy 1, policy_version 176780 (0.0012) -[2023-11-28 04:50:59,690][87426] Updated weights for policy 1, policy_version 176790 (0.0012) -[2023-11-28 04:51:00,000][87424] Updated weights for policy 0, policy_version 177287 (0.0010) -[2023-11-28 04:51:00,065][87426] Updated weights for policy 1, policy_version 176800 (0.0012) -[2023-11-28 04:51:00,384][87424] Updated weights for policy 0, policy_version 177297 (0.0011) -[2023-11-28 04:51:00,768][87424] Updated weights for policy 0, policy_version 177307 (0.0011) -[2023-11-28 04:51:02,144][87426] Updated weights for policy 1, policy_version 176810 (0.0012) -[2023-11-28 04:51:02,522][87426] Updated weights for policy 1, policy_version 176820 (0.0011) -[2023-11-28 04:51:02,885][87424] Updated weights for policy 0, policy_version 177317 (0.0012) -[2023-11-28 04:51:02,890][87426] Updated weights for policy 1, policy_version 176830 (0.0011) -[2023-11-28 04:51:03,259][87424] Updated weights for policy 0, policy_version 177327 (0.0012) -[2023-11-28 04:51:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90660864. Throughput: 0: 2744.3, 1: 2739.1. Samples: 90672744. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:51:03,445][86177] Avg episode reward: [(0, '-562.280'), (1, '-535.180')] -[2023-11-28 04:51:03,640][87424] Updated weights for policy 0, policy_version 177337 (0.0008) -[2023-11-28 04:51:05,102][87426] Updated weights for policy 1, policy_version 176840 (0.0010) -[2023-11-28 04:51:05,479][87426] Updated weights for policy 1, policy_version 176850 (0.0007) -[2023-11-28 04:51:05,857][87426] Updated weights for policy 1, policy_version 176860 (0.0007) -[2023-11-28 04:51:06,163][87424] Updated weights for policy 0, policy_version 177347 (0.0007) -[2023-11-28 04:51:06,547][87424] Updated weights for policy 0, policy_version 177357 (0.0008) -[2023-11-28 04:51:06,930][87424] Updated weights for policy 0, policy_version 177367 (0.0008) -[2023-11-28 04:51:07,765][87426] Updated weights for policy 1, policy_version 176870 (0.0010) -[2023-11-28 04:51:08,147][87426] Updated weights for policy 1, policy_version 176880 (0.0012) -[2023-11-28 04:51:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 90685440. Throughput: 0: 2707.6, 1: 2757.9. Samples: 90704400. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:51:08,446][86177] Avg episode reward: [(0, '-539.030'), (1, '-542.420')] -[2023-11-28 04:51:08,530][87426] Updated weights for policy 1, policy_version 176890 (0.0012) -[2023-11-28 04:51:09,337][87424] Updated weights for policy 0, policy_version 177377 (0.0011) -[2023-11-28 04:51:09,712][87424] Updated weights for policy 0, policy_version 177387 (0.0012) -[2023-11-28 04:51:10,095][87424] Updated weights for policy 0, policy_version 177397 (0.0012) -[2023-11-28 04:51:10,478][87424] Updated weights for policy 0, policy_version 177407 (0.0012) -[2023-11-28 04:51:10,876][87426] Updated weights for policy 1, policy_version 176900 (0.0012) -[2023-11-28 04:51:11,266][87426] Updated weights for policy 1, policy_version 176910 (0.0012) -[2023-11-28 04:51:11,637][87426] Updated weights for policy 1, policy_version 176920 (0.0011) -[2023-11-28 04:51:12,682][87424] Updated weights for policy 0, policy_version 177417 (0.0012) -[2023-11-28 04:51:13,062][87424] Updated weights for policy 0, policy_version 177427 (0.0012) -[2023-11-28 04:51:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90710016. Throughput: 0: 2713.2, 1: 2755.5. Samples: 90729044. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:51:13,446][86177] Avg episode reward: [(0, '-532.810'), (1, '-527.110')] -[2023-11-28 04:51:13,448][87424] Updated weights for policy 0, policy_version 177437 (0.0012) -[2023-11-28 04:51:13,703][87426] Updated weights for policy 1, policy_version 176930 (0.0012) -[2023-11-28 04:51:14,080][87426] Updated weights for policy 1, policy_version 176940 (0.0011) -[2023-11-28 04:51:14,464][87426] Updated weights for policy 1, policy_version 176950 (0.0012) -[2023-11-28 04:51:14,843][87426] Updated weights for policy 1, policy_version 176960 (0.0011) -[2023-11-28 04:51:15,512][87424] Updated weights for policy 0, policy_version 177447 (0.0012) -[2023-11-28 04:51:15,889][87424] Updated weights for policy 0, policy_version 177457 (0.0012) -[2023-11-28 04:51:16,263][87424] Updated weights for policy 0, policy_version 177467 (0.0012) -[2023-11-28 04:51:16,663][87426] Updated weights for policy 1, policy_version 176970 (0.0012) -[2023-11-28 04:51:17,040][87426] Updated weights for policy 1, policy_version 176980 (0.0012) -[2023-11-28 04:51:17,423][87426] Updated weights for policy 1, policy_version 176990 (0.0012) -[2023-11-28 04:51:18,437][87424] Updated weights for policy 0, policy_version 177477 (0.0009) -[2023-11-28 04:51:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90742784. Throughput: 0: 2688.4, 1: 2756.4. Samples: 90753888. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:51:18,445][86177] Avg episode reward: [(0, '-555.100'), (1, '-522.380')] -[2023-11-28 04:51:18,817][87424] Updated weights for policy 0, policy_version 177487 (0.0007) -[2023-11-28 04:51:19,090][87426] Updated weights for policy 1, policy_version 177000 (0.0009) -[2023-11-28 04:51:19,199][87424] Updated weights for policy 0, policy_version 177497 (0.0008) -[2023-11-28 04:51:19,478][87426] Updated weights for policy 1, policy_version 177010 (0.0010) -[2023-11-28 04:51:19,849][87426] Updated weights for policy 1, policy_version 177020 (0.0012) -[2023-11-28 04:51:21,321][87424] Updated weights for policy 0, policy_version 177507 (0.0011) -[2023-11-28 04:51:21,701][87424] Updated weights for policy 0, policy_version 177517 (0.0012) -[2023-11-28 04:51:22,080][87424] Updated weights for policy 0, policy_version 177527 (0.0011) -[2023-11-28 04:51:22,249][87426] Updated weights for policy 1, policy_version 177030 (0.0011) -[2023-11-28 04:51:22,626][87426] Updated weights for policy 1, policy_version 177040 (0.0009) -[2023-11-28 04:51:23,001][87426] Updated weights for policy 1, policy_version 177050 (0.0009) -[2023-11-28 04:51:23,445][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90775552. Throughput: 0: 2690.7, 1: 2771.1. Samples: 90786876. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:51:23,446][86177] Avg episode reward: [(0, '-570.080'), (1, '-523.870')] -[2023-11-28 04:51:24,526][87424] Updated weights for policy 0, policy_version 177537 (0.0009) -[2023-11-28 04:51:24,909][87424] Updated weights for policy 0, policy_version 177547 (0.0007) -[2023-11-28 04:51:25,285][87424] Updated weights for policy 0, policy_version 177557 (0.0008) -[2023-11-28 04:51:25,425][87426] Updated weights for policy 1, policy_version 177060 (0.0010) -[2023-11-28 04:51:25,666][87424] Updated weights for policy 0, policy_version 177567 (0.0008) -[2023-11-28 04:51:25,795][87426] Updated weights for policy 1, policy_version 177070 (0.0011) -[2023-11-28 04:51:26,173][87426] Updated weights for policy 1, policy_version 177080 (0.0007) -[2023-11-28 04:51:27,362][87424] Updated weights for policy 0, policy_version 177577 (0.0011) -[2023-11-28 04:51:27,741][87424] Updated weights for policy 0, policy_version 177587 (0.0012) -[2023-11-28 04:51:28,127][87424] Updated weights for policy 0, policy_version 177597 (0.0012) -[2023-11-28 04:51:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90800128. Throughput: 0: 2686.1, 1: 2766.6. Samples: 90811000. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:51:28,445][86177] Avg episode reward: [(0, '-588.920'), (1, '-517.340')] -[2023-11-28 04:51:28,573][87426] Updated weights for policy 1, policy_version 177090 (0.0008) -[2023-11-28 04:51:28,951][87426] Updated weights for policy 1, policy_version 177100 (0.0007) -[2023-11-28 04:51:29,334][87426] Updated weights for policy 1, policy_version 177110 (0.0007) -[2023-11-28 04:51:29,705][87426] Updated weights for policy 1, policy_version 177120 (0.0008) -[2023-11-28 04:51:30,662][87424] Updated weights for policy 0, policy_version 177607 (0.0012) -[2023-11-28 04:51:31,042][87424] Updated weights for policy 0, policy_version 177617 (0.0010) -[2023-11-28 04:51:31,425][87424] Updated weights for policy 0, policy_version 177627 (0.0011) -[2023-11-28 04:51:31,569][87426] Updated weights for policy 1, policy_version 177130 (0.0010) -[2023-11-28 04:51:31,955][87426] Updated weights for policy 1, policy_version 177140 (0.0012) -[2023-11-28 04:51:32,323][87426] Updated weights for policy 1, policy_version 177150 (0.0012) -[2023-11-28 04:51:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90824704. Throughput: 0: 2681.5, 1: 2767.6. Samples: 90835820. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:51:33,446][86177] Avg episode reward: [(0, '-594.430'), (1, '-513.580')] -[2023-11-28 04:51:33,857][87424] Updated weights for policy 0, policy_version 177637 (0.0010) -[2023-11-28 04:51:34,247][87424] Updated weights for policy 0, policy_version 177647 (0.0007) -[2023-11-28 04:51:34,628][87424] Updated weights for policy 0, policy_version 177657 (0.0007) -[2023-11-28 04:51:34,808][87426] Updated weights for policy 1, policy_version 177160 (0.0011) -[2023-11-28 04:51:35,185][87426] Updated weights for policy 1, policy_version 177170 (0.0007) -[2023-11-28 04:51:35,566][87426] Updated weights for policy 1, policy_version 177180 (0.0008) -[2023-11-28 04:51:36,894][87424] Updated weights for policy 0, policy_version 177667 (0.0009) -[2023-11-28 04:51:37,280][87424] Updated weights for policy 0, policy_version 177677 (0.0012) -[2023-11-28 04:51:37,398][87426] Updated weights for policy 1, policy_version 177190 (0.0010) -[2023-11-28 04:51:37,660][87424] Updated weights for policy 0, policy_version 177687 (0.0010) -[2023-11-28 04:51:37,778][87426] Updated weights for policy 1, policy_version 177200 (0.0010) -[2023-11-28 04:51:38,148][87426] Updated weights for policy 1, policy_version 177210 (0.0011) -[2023-11-28 04:51:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 90857472. Throughput: 0: 2676.8, 1: 2762.3. Samples: 90868300. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:51:38,445][86177] Avg episode reward: [(0, '-587.150'), (1, '-518.430')] -[2023-11-28 04:51:39,655][87424] Updated weights for policy 0, policy_version 177697 (0.0012) -[2023-11-28 04:51:40,037][87424] Updated weights for policy 0, policy_version 177707 (0.0011) -[2023-11-28 04:51:40,274][87426] Updated weights for policy 1, policy_version 177220 (0.0009) -[2023-11-28 04:51:40,422][87424] Updated weights for policy 0, policy_version 177717 (0.0011) -[2023-11-28 04:51:40,646][87426] Updated weights for policy 1, policy_version 177230 (0.0011) -[2023-11-28 04:51:40,809][87424] Updated weights for policy 0, policy_version 177727 (0.0012) -[2023-11-28 04:51:41,028][87426] Updated weights for policy 1, policy_version 177240 (0.0010) -[2023-11-28 04:51:43,319][87424] Updated weights for policy 0, policy_version 177737 (0.0010) -[2023-11-28 04:51:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 90873856. Throughput: 0: 2685.1, 1: 2761.8. Samples: 90893452. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 04:51:43,445][86177] Avg episode reward: [(0, '-577.690'), (1, '-512.440')] -[2023-11-28 04:51:43,525][87426] Updated weights for policy 1, policy_version 177250 (0.0011) -[2023-11-28 04:51:43,690][87424] Updated weights for policy 0, policy_version 177747 (0.0011) -[2023-11-28 04:51:43,904][87426] Updated weights for policy 1, policy_version 177260 (0.0012) -[2023-11-28 04:51:44,080][87424] Updated weights for policy 0, policy_version 177757 (0.0011) -[2023-11-28 04:51:44,279][87426] Updated weights for policy 1, policy_version 177270 (0.0011) -[2023-11-28 04:51:44,661][87426] Updated weights for policy 1, policy_version 177280 (0.0012) -[2023-11-28 04:51:46,441][87424] Updated weights for policy 0, policy_version 177767 (0.0011) -[2023-11-28 04:51:46,605][87426] Updated weights for policy 1, policy_version 177290 (0.0011) -[2023-11-28 04:51:46,827][87424] Updated weights for policy 0, policy_version 177777 (0.0007) -[2023-11-28 04:51:46,988][87426] Updated weights for policy 1, policy_version 177300 (0.0011) -[2023-11-28 04:51:47,211][87424] Updated weights for policy 0, policy_version 177787 (0.0008) -[2023-11-28 04:51:47,367][87426] Updated weights for policy 1, policy_version 177310 (0.0011) -[2023-11-28 04:51:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 90906624. Throughput: 0: 2694.2, 1: 2749.4. Samples: 90917708. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:51:48,445][86177] Avg episode reward: [(0, '-554.390'), (1, '-519.060')] -[2023-11-28 04:51:48,874][87424] Updated weights for policy 0, policy_version 177797 (0.0010) -[2023-11-28 04:51:49,236][87426] Updated weights for policy 1, policy_version 177320 (0.0012) -[2023-11-28 04:51:49,255][87424] Updated weights for policy 0, policy_version 177807 (0.0012) -[2023-11-28 04:51:49,610][87426] Updated weights for policy 1, policy_version 177330 (0.0011) -[2023-11-28 04:51:49,637][87424] Updated weights for policy 0, policy_version 177817 (0.0012) -[2023-11-28 04:51:49,990][87426] Updated weights for policy 1, policy_version 177340 (0.0011) -[2023-11-28 04:51:51,686][87424] Updated weights for policy 0, policy_version 177827 (0.0011) -[2023-11-28 04:51:52,067][87424] Updated weights for policy 0, policy_version 177837 (0.0012) -[2023-11-28 04:51:52,157][87426] Updated weights for policy 1, policy_version 177350 (0.0009) -[2023-11-28 04:51:52,440][87424] Updated weights for policy 0, policy_version 177847 (0.0009) -[2023-11-28 04:51:52,532][87426] Updated weights for policy 1, policy_version 177360 (0.0011) -[2023-11-28 04:51:52,908][87426] Updated weights for policy 1, policy_version 177370 (0.0010) -[2023-11-28 04:51:53,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 90939392. Throughput: 0: 2733.6, 1: 2746.0. Samples: 90950980. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:51:53,445][86177] Avg episode reward: [(0, '-537.140'), (1, '-519.450')] -[2023-11-28 04:51:54,544][87424] Updated weights for policy 0, policy_version 177857 (0.0008) -[2023-11-28 04:51:54,928][87424] Updated weights for policy 0, policy_version 177867 (0.0008) -[2023-11-28 04:51:55,325][87424] Updated weights for policy 0, policy_version 177877 (0.0008) -[2023-11-28 04:51:55,388][87426] Updated weights for policy 1, policy_version 177380 (0.0009) -[2023-11-28 04:51:55,699][87424] Updated weights for policy 0, policy_version 177887 (0.0008) -[2023-11-28 04:51:55,772][87426] Updated weights for policy 1, policy_version 177390 (0.0008) -[2023-11-28 04:51:56,143][87426] Updated weights for policy 1, policy_version 177400 (0.0007) -[2023-11-28 04:51:57,755][87424] Updated weights for policy 0, policy_version 177897 (0.0007) -[2023-11-28 04:51:58,132][87424] Updated weights for policy 0, policy_version 177907 (0.0007) -[2023-11-28 04:51:58,362][87426] Updated weights for policy 1, policy_version 177410 (0.0007) -[2023-11-28 04:51:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 90955776. Throughput: 0: 2727.8, 1: 2734.9. Samples: 90974864. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:51:58,445][86177] Avg episode reward: [(0, '-529.390'), (1, '-521.720')] -[2023-11-28 04:51:58,518][87424] Updated weights for policy 0, policy_version 177917 (0.0008) -[2023-11-28 04:51:58,743][87426] Updated weights for policy 1, policy_version 177420 (0.0012) -[2023-11-28 04:51:59,130][87426] Updated weights for policy 1, policy_version 177430 (0.0012) -[2023-11-28 04:51:59,503][87426] Updated weights for policy 1, policy_version 177440 (0.0008) -[2023-11-28 04:52:00,724][87424] Updated weights for policy 0, policy_version 177927 (0.0011) -[2023-11-28 04:52:01,106][87424] Updated weights for policy 0, policy_version 177937 (0.0010) -[2023-11-28 04:52:01,447][87426] Updated weights for policy 1, policy_version 177450 (0.0012) -[2023-11-28 04:52:01,497][87424] Updated weights for policy 0, policy_version 177947 (0.0012) -[2023-11-28 04:52:01,826][87426] Updated weights for policy 1, policy_version 177460 (0.0011) -[2023-11-28 04:52:02,205][87426] Updated weights for policy 1, policy_version 177470 (0.0009) -[2023-11-28 04:52:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 90988544. Throughput: 0: 2732.6, 1: 2729.6. Samples: 90999688. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:03,445][86177] Avg episode reward: [(0, '-531.650'), (1, '-521.750')] -[2023-11-28 04:52:03,708][87424] Updated weights for policy 0, policy_version 177957 (0.0012) -[2023-11-28 04:52:04,096][87424] Updated weights for policy 0, policy_version 177967 (0.0012) -[2023-11-28 04:52:04,449][87426] Updated weights for policy 1, policy_version 177480 (0.0008) -[2023-11-28 04:52:04,487][87424] Updated weights for policy 0, policy_version 177977 (0.0012) -[2023-11-28 04:52:04,828][87426] Updated weights for policy 1, policy_version 177490 (0.0011) -[2023-11-28 04:52:05,208][87426] Updated weights for policy 1, policy_version 177500 (0.0012) -[2023-11-28 04:52:06,878][87424] Updated weights for policy 0, policy_version 177987 (0.0012) -[2023-11-28 04:52:07,260][87424] Updated weights for policy 0, policy_version 177997 (0.0011) -[2023-11-28 04:52:07,299][87426] Updated weights for policy 1, policy_version 177510 (0.0011) -[2023-11-28 04:52:07,639][87424] Updated weights for policy 0, policy_version 178007 (0.0011) -[2023-11-28 04:52:07,672][87426] Updated weights for policy 1, policy_version 177520 (0.0012) -[2023-11-28 04:52:08,059][87426] Updated weights for policy 1, policy_version 177530 (0.0011) -[2023-11-28 04:52:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 91021312. Throughput: 0: 2731.1, 1: 2746.5. Samples: 91033368. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:08,446][86177] Avg episode reward: [(0, '-529.490'), (1, '-516.350')] -[2023-11-28 04:52:09,568][87424] Updated weights for policy 0, policy_version 178017 (0.0011) -[2023-11-28 04:52:09,959][87424] Updated weights for policy 0, policy_version 178027 (0.0012) -[2023-11-28 04:52:10,016][87426] Updated weights for policy 1, policy_version 177540 (0.0011) -[2023-11-28 04:52:10,342][87424] Updated weights for policy 0, policy_version 178037 (0.0010) -[2023-11-28 04:52:10,395][87426] Updated weights for policy 1, policy_version 177550 (0.0011) -[2023-11-28 04:52:10,717][87424] Updated weights for policy 0, policy_version 178047 (0.0012) -[2023-11-28 04:52:10,777][87426] Updated weights for policy 1, policy_version 177560 (0.0012) -[2023-11-28 04:52:12,976][87426] Updated weights for policy 1, policy_version 177570 (0.0009) -[2023-11-28 04:52:13,161][87424] Updated weights for policy 0, policy_version 178057 (0.0010) -[2023-11-28 04:52:13,352][87426] Updated weights for policy 1, policy_version 177580 (0.0010) -[2023-11-28 04:52:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 91037696. Throughput: 0: 2729.0, 1: 2735.6. Samples: 91056908. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:13,445][86177] Avg episode reward: [(0, '-496.890'), (1, '-531.000')] -[2023-11-28 04:52:13,544][87424] Updated weights for policy 0, policy_version 178067 (0.0012) -[2023-11-28 04:52:13,725][87426] Updated weights for policy 1, policy_version 177590 (0.0011) -[2023-11-28 04:52:13,924][87424] Updated weights for policy 0, policy_version 178077 (0.0010) -[2023-11-28 04:52:14,103][87426] Updated weights for policy 1, policy_version 177600 (0.0011) -[2023-11-28 04:52:15,958][87424] Updated weights for policy 0, policy_version 178087 (0.0010) -[2023-11-28 04:52:16,333][87426] Updated weights for policy 1, policy_version 177610 (0.0011) -[2023-11-28 04:52:16,343][87424] Updated weights for policy 0, policy_version 178097 (0.0009) -[2023-11-28 04:52:16,700][87426] Updated weights for policy 1, policy_version 177620 (0.0011) -[2023-11-28 04:52:16,724][87424] Updated weights for policy 0, policy_version 178107 (0.0007) -[2023-11-28 04:52:17,077][87426] Updated weights for policy 1, policy_version 177630 (0.0012) -[2023-11-28 04:52:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91070464. Throughput: 0: 2733.3, 1: 2735.3. Samples: 91081904. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:18,445][86177] Avg episode reward: [(0, '-499.430'), (1, '-524.350')] -[2023-11-28 04:52:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000178112_45596672.pth... -[2023-11-28 04:52:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000177632_45473792.pth... -[2023-11-28 04:52:18,494][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000175072_44818432.pth -[2023-11-28 04:52:18,498][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000177632_45473792.pth -[2023-11-28 04:52:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000175584_44949504.pth -[2023-11-28 04:52:18,512][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000178112_45596672.pth -[2023-11-28 04:52:18,975][87426] Updated weights for policy 1, policy_version 177640 (0.0011) -[2023-11-28 04:52:19,075][87424] Updated weights for policy 0, policy_version 178117 (0.0009) -[2023-11-28 04:52:19,351][87426] Updated weights for policy 1, policy_version 177650 (0.0011) -[2023-11-28 04:52:19,452][87424] Updated weights for policy 0, policy_version 178127 (0.0008) -[2023-11-28 04:52:19,726][87426] Updated weights for policy 1, policy_version 177660 (0.0011) -[2023-11-28 04:52:19,836][87424] Updated weights for policy 0, policy_version 178137 (0.0008) -[2023-11-28 04:52:21,554][87424] Updated weights for policy 0, policy_version 178147 (0.0011) -[2023-11-28 04:52:21,797][87426] Updated weights for policy 1, policy_version 177670 (0.0010) -[2023-11-28 04:52:21,930][87424] Updated weights for policy 0, policy_version 178157 (0.0012) -[2023-11-28 04:52:22,175][87426] Updated weights for policy 1, policy_version 177680 (0.0011) -[2023-11-28 04:52:22,312][87424] Updated weights for policy 0, policy_version 178167 (0.0009) -[2023-11-28 04:52:22,560][87426] Updated weights for policy 1, policy_version 177690 (0.0012) -[2023-11-28 04:52:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 91103232. Throughput: 0: 2719.2, 1: 2744.9. Samples: 91114184. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:23,445][86177] Avg episode reward: [(0, '-508.280'), (1, '-521.220')] -[2023-11-28 04:52:24,805][87426] Updated weights for policy 1, policy_version 177700 (0.0010) -[2023-11-28 04:52:24,837][87424] Updated weights for policy 0, policy_version 178177 (0.0010) -[2023-11-28 04:52:25,187][87426] Updated weights for policy 1, policy_version 177710 (0.0007) -[2023-11-28 04:52:25,215][87424] Updated weights for policy 0, policy_version 178187 (0.0010) -[2023-11-28 04:52:25,570][87426] Updated weights for policy 1, policy_version 177720 (0.0007) -[2023-11-28 04:52:25,603][87424] Updated weights for policy 0, policy_version 178197 (0.0007) -[2023-11-28 04:52:25,980][87424] Updated weights for policy 0, policy_version 178207 (0.0007) -[2023-11-28 04:52:27,996][87426] Updated weights for policy 1, policy_version 177730 (0.0008) -[2023-11-28 04:52:28,376][87426] Updated weights for policy 1, policy_version 177740 (0.0008) -[2023-11-28 04:52:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 91119616. Throughput: 0: 2701.6, 1: 2766.3. Samples: 91139508. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:28,445][86177] Avg episode reward: [(0, '-520.620'), (1, '-526.680')] -[2023-11-28 04:52:28,537][87424] Updated weights for policy 0, policy_version 178217 (0.0010) -[2023-11-28 04:52:28,760][87426] Updated weights for policy 1, policy_version 177750 (0.0009) -[2023-11-28 04:52:28,922][87424] Updated weights for policy 0, policy_version 178227 (0.0008) -[2023-11-28 04:52:29,140][87426] Updated weights for policy 1, policy_version 177760 (0.0009) -[2023-11-28 04:52:29,308][87424] Updated weights for policy 0, policy_version 178237 (0.0011) -[2023-11-28 04:52:31,234][87426] Updated weights for policy 1, policy_version 177770 (0.0011) -[2023-11-28 04:52:31,340][87424] Updated weights for policy 0, policy_version 178247 (0.0008) -[2023-11-28 04:52:31,617][87426] Updated weights for policy 1, policy_version 177780 (0.0009) -[2023-11-28 04:52:31,729][87424] Updated weights for policy 0, policy_version 178257 (0.0010) -[2023-11-28 04:52:32,012][87426] Updated weights for policy 1, policy_version 177790 (0.0010) -[2023-11-28 04:52:32,111][87424] Updated weights for policy 0, policy_version 178267 (0.0012) -[2023-11-28 04:52:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91152384. Throughput: 0: 2709.8, 1: 2767.0. Samples: 91164164. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:33,446][86177] Avg episode reward: [(0, '-520.630'), (1, '-521.010')] -[2023-11-28 04:52:33,889][87426] Updated weights for policy 1, policy_version 177800 (0.0012) -[2023-11-28 04:52:34,265][87426] Updated weights for policy 1, policy_version 177810 (0.0012) -[2023-11-28 04:52:34,370][87424] Updated weights for policy 0, policy_version 178277 (0.0010) -[2023-11-28 04:52:34,643][87426] Updated weights for policy 1, policy_version 177820 (0.0010) -[2023-11-28 04:52:34,750][87424] Updated weights for policy 0, policy_version 178287 (0.0009) -[2023-11-28 04:52:35,137][87424] Updated weights for policy 0, policy_version 178297 (0.0008) -[2023-11-28 04:52:36,534][87426] Updated weights for policy 1, policy_version 177830 (0.0010) -[2023-11-28 04:52:36,906][87426] Updated weights for policy 1, policy_version 177840 (0.0010) -[2023-11-28 04:52:37,296][87426] Updated weights for policy 1, policy_version 177850 (0.0011) -[2023-11-28 04:52:37,638][87424] Updated weights for policy 0, policy_version 178307 (0.0009) -[2023-11-28 04:52:38,020][87424] Updated weights for policy 0, policy_version 178317 (0.0009) -[2023-11-28 04:52:38,403][87424] Updated weights for policy 0, policy_version 178327 (0.0007) -[2023-11-28 04:52:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 91176960. Throughput: 0: 2676.2, 1: 2749.4. Samples: 91195132. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:38,445][86177] Avg episode reward: [(0, '-517.990'), (1, '-518.850')] -[2023-11-28 04:52:39,809][87426] Updated weights for policy 1, policy_version 177860 (0.0009) -[2023-11-28 04:52:40,191][87426] Updated weights for policy 1, policy_version 177870 (0.0011) -[2023-11-28 04:52:40,580][87426] Updated weights for policy 1, policy_version 177880 (0.0010) -[2023-11-28 04:52:40,585][87424] Updated weights for policy 0, policy_version 178337 (0.0010) -[2023-11-28 04:52:40,968][87424] Updated weights for policy 0, policy_version 178347 (0.0009) -[2023-11-28 04:52:41,354][87424] Updated weights for policy 0, policy_version 178357 (0.0009) -[2023-11-28 04:52:41,735][87424] Updated weights for policy 0, policy_version 178367 (0.0009) -[2023-11-28 04:52:43,005][87426] Updated weights for policy 1, policy_version 177890 (0.0010) -[2023-11-28 04:52:43,390][87426] Updated weights for policy 1, policy_version 177900 (0.0011) -[2023-11-28 04:52:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91201536. Throughput: 0: 2674.3, 1: 2761.3. Samples: 91219468. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:43,446][86177] Avg episode reward: [(0, '-509.910'), (1, '-521.820')] -[2023-11-28 04:52:43,763][87426] Updated weights for policy 1, policy_version 177910 (0.0009) -[2023-11-28 04:52:44,140][87426] Updated weights for policy 1, policy_version 177920 (0.0010) -[2023-11-28 04:52:44,350][87424] Updated weights for policy 0, policy_version 178377 (0.0008) -[2023-11-28 04:52:44,729][87424] Updated weights for policy 0, policy_version 178387 (0.0009) -[2023-11-28 04:52:45,120][87424] Updated weights for policy 0, policy_version 178397 (0.0008) -[2023-11-28 04:52:46,135][87426] Updated weights for policy 1, policy_version 177930 (0.0009) -[2023-11-28 04:52:46,512][87426] Updated weights for policy 1, policy_version 177940 (0.0008) -[2023-11-28 04:52:46,887][87426] Updated weights for policy 1, policy_version 177950 (0.0007) -[2023-11-28 04:52:47,546][87424] Updated weights for policy 0, policy_version 178407 (0.0011) -[2023-11-28 04:52:47,930][87424] Updated weights for policy 0, policy_version 178417 (0.0011) -[2023-11-28 04:52:48,317][87424] Updated weights for policy 0, policy_version 178427 (0.0010) -[2023-11-28 04:52:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 91226112. Throughput: 0: 2650.4, 1: 2761.5. Samples: 91243224. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:48,446][86177] Avg episode reward: [(0, '-523.370'), (1, '-503.850')] -[2023-11-28 04:52:49,070][87426] Updated weights for policy 1, policy_version 177960 (0.0007) -[2023-11-28 04:52:49,460][87426] Updated weights for policy 1, policy_version 177970 (0.0012) -[2023-11-28 04:52:49,831][87426] Updated weights for policy 1, policy_version 177980 (0.0011) -[2023-11-28 04:52:50,330][87424] Updated weights for policy 0, policy_version 178437 (0.0009) -[2023-11-28 04:52:50,704][87424] Updated weights for policy 0, policy_version 178447 (0.0011) -[2023-11-28 04:52:51,100][87424] Updated weights for policy 0, policy_version 178457 (0.0012) -[2023-11-28 04:52:52,038][87426] Updated weights for policy 1, policy_version 177990 (0.0010) -[2023-11-28 04:52:52,414][87426] Updated weights for policy 1, policy_version 178000 (0.0010) -[2023-11-28 04:52:52,792][87426] Updated weights for policy 1, policy_version 178010 (0.0011) -[2023-11-28 04:52:53,297][87424] Updated weights for policy 0, policy_version 178467 (0.0012) -[2023-11-28 04:52:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 91258880. Throughput: 0: 2643.0, 1: 2724.7. Samples: 91274916. Policy #0 lag: (min: 15.0, avg: 21.5, max: 47.0) -[2023-11-28 04:52:53,445][86177] Avg episode reward: [(0, '-526.290'), (1, '-506.290')] -[2023-11-28 04:52:53,681][87424] Updated weights for policy 0, policy_version 178477 (0.0016) -[2023-11-28 04:52:54,057][87424] Updated weights for policy 0, policy_version 178487 (0.0012) -[2023-11-28 04:52:55,060][87426] Updated weights for policy 1, policy_version 178020 (0.0010) -[2023-11-28 04:52:55,444][87426] Updated weights for policy 1, policy_version 178030 (0.0012) -[2023-11-28 04:52:55,814][87426] Updated weights for policy 1, policy_version 178040 (0.0009) -[2023-11-28 04:52:56,444][87424] Updated weights for policy 0, policy_version 178497 (0.0011) -[2023-11-28 04:52:56,826][87424] Updated weights for policy 0, policy_version 178507 (0.0012) -[2023-11-28 04:52:57,208][87424] Updated weights for policy 0, policy_version 178517 (0.0012) -[2023-11-28 04:52:57,601][87424] Updated weights for policy 0, policy_version 178527 (0.0011) -[2023-11-28 04:52:58,234][87426] Updated weights for policy 1, policy_version 178050 (0.0009) -[2023-11-28 04:52:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91283456. Throughput: 0: 2646.8, 1: 2747.3. Samples: 91299644. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:52:58,445][86177] Avg episode reward: [(0, '-527.530'), (1, '-509.410')] -[2023-11-28 04:52:58,611][87426] Updated weights for policy 1, policy_version 178060 (0.0012) -[2023-11-28 04:52:59,003][87426] Updated weights for policy 1, policy_version 178070 (0.0012) -[2023-11-28 04:52:59,379][87426] Updated weights for policy 1, policy_version 178080 (0.0011) -[2023-11-28 04:52:59,554][87424] Updated weights for policy 0, policy_version 178537 (0.0008) -[2023-11-28 04:52:59,945][87424] Updated weights for policy 0, policy_version 178547 (0.0010) -[2023-11-28 04:53:00,322][87424] Updated weights for policy 0, policy_version 178557 (0.0008) -[2023-11-28 04:53:01,316][87426] Updated weights for policy 1, policy_version 178090 (0.0012) -[2023-11-28 04:53:01,692][87426] Updated weights for policy 1, policy_version 178100 (0.0012) -[2023-11-28 04:53:02,069][87426] Updated weights for policy 1, policy_version 178110 (0.0011) -[2023-11-28 04:53:02,140][87424] Updated weights for policy 0, policy_version 178567 (0.0009) -[2023-11-28 04:53:02,524][87424] Updated weights for policy 0, policy_version 178577 (0.0010) -[2023-11-28 04:53:02,911][87424] Updated weights for policy 0, policy_version 178587 (0.0009) -[2023-11-28 04:53:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91316224. Throughput: 0: 2659.9, 1: 2749.2. Samples: 91325316. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:03,445][86177] Avg episode reward: [(0, '-526.120'), (1, '-526.820')] -[2023-11-28 04:53:04,127][87426] Updated weights for policy 1, policy_version 178120 (0.0009) -[2023-11-28 04:53:04,503][87426] Updated weights for policy 1, policy_version 178130 (0.0012) -[2023-11-28 04:53:04,885][87426] Updated weights for policy 1, policy_version 178140 (0.0009) -[2023-11-28 04:53:04,928][87424] Updated weights for policy 0, policy_version 178597 (0.0010) -[2023-11-28 04:53:05,310][87424] Updated weights for policy 0, policy_version 178607 (0.0012) -[2023-11-28 04:53:05,707][87424] Updated weights for policy 0, policy_version 178617 (0.0012) -[2023-11-28 04:53:06,970][87426] Updated weights for policy 1, policy_version 178150 (0.0012) -[2023-11-28 04:53:07,354][87426] Updated weights for policy 1, policy_version 178160 (0.0010) -[2023-11-28 04:53:07,641][87424] Updated weights for policy 0, policy_version 178627 (0.0012) -[2023-11-28 04:53:07,735][87426] Updated weights for policy 1, policy_version 178170 (0.0011) -[2023-11-28 04:53:08,013][87424] Updated weights for policy 0, policy_version 178637 (0.0012) -[2023-11-28 04:53:08,395][87424] Updated weights for policy 0, policy_version 178647 (0.0008) -[2023-11-28 04:53:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 91340800. Throughput: 0: 2686.9, 1: 2762.1. Samples: 91359392. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:08,445][86177] Avg episode reward: [(0, '-502.000'), (1, '-525.890')] -[2023-11-28 04:53:09,511][87426] Updated weights for policy 1, policy_version 178180 (0.0009) -[2023-11-28 04:53:09,886][87426] Updated weights for policy 1, policy_version 178190 (0.0012) -[2023-11-28 04:53:10,256][87426] Updated weights for policy 1, policy_version 178200 (0.0010) -[2023-11-28 04:53:10,363][87424] Updated weights for policy 0, policy_version 178657 (0.0008) -[2023-11-28 04:53:10,744][87424] Updated weights for policy 0, policy_version 178667 (0.0012) -[2023-11-28 04:53:11,122][87424] Updated weights for policy 0, policy_version 178677 (0.0012) -[2023-11-28 04:53:11,519][87424] Updated weights for policy 0, policy_version 178687 (0.0012) -[2023-11-28 04:53:12,562][87426] Updated weights for policy 1, policy_version 178210 (0.0008) -[2023-11-28 04:53:12,953][87426] Updated weights for policy 1, policy_version 178220 (0.0011) -[2023-11-28 04:53:13,330][87426] Updated weights for policy 1, policy_version 178230 (0.0008) -[2023-11-28 04:53:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91365376. Throughput: 0: 2692.6, 1: 2739.6. Samples: 91383956. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:13,445][86177] Avg episode reward: [(0, '-504.690'), (1, '-536.350')] -[2023-11-28 04:53:13,710][87426] Updated weights for policy 1, policy_version 178240 (0.0008) -[2023-11-28 04:53:13,778][87424] Updated weights for policy 0, policy_version 178697 (0.0008) -[2023-11-28 04:53:14,168][87424] Updated weights for policy 0, policy_version 178707 (0.0008) -[2023-11-28 04:53:14,542][87424] Updated weights for policy 0, policy_version 178717 (0.0007) -[2023-11-28 04:53:15,544][87426] Updated weights for policy 1, policy_version 178250 (0.0008) -[2023-11-28 04:53:15,913][87426] Updated weights for policy 1, policy_version 178260 (0.0007) -[2023-11-28 04:53:16,296][87426] Updated weights for policy 1, policy_version 178270 (0.0009) -[2023-11-28 04:53:17,039][87424] Updated weights for policy 0, policy_version 178727 (0.0007) -[2023-11-28 04:53:17,435][87424] Updated weights for policy 0, policy_version 178737 (0.0007) -[2023-11-28 04:53:17,812][87424] Updated weights for policy 0, policy_version 178747 (0.0008) -[2023-11-28 04:53:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91398144. Throughput: 0: 2697.7, 1: 2730.9. Samples: 91408448. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:18,445][86177] Avg episode reward: [(0, '-509.080'), (1, '-559.000')] -[2023-11-28 04:53:18,832][87426] Updated weights for policy 1, policy_version 178280 (0.0011) -[2023-11-28 04:53:19,211][87426] Updated weights for policy 1, policy_version 178290 (0.0011) -[2023-11-28 04:53:19,591][87426] Updated weights for policy 1, policy_version 178300 (0.0011) -[2023-11-28 04:53:20,157][87424] Updated weights for policy 0, policy_version 178757 (0.0012) -[2023-11-28 04:53:20,531][87424] Updated weights for policy 0, policy_version 178767 (0.0012) -[2023-11-28 04:53:20,899][87424] Updated weights for policy 0, policy_version 178777 (0.0012) -[2023-11-28 04:53:21,594][87426] Updated weights for policy 1, policy_version 178310 (0.0011) -[2023-11-28 04:53:21,970][87426] Updated weights for policy 1, policy_version 178320 (0.0009) -[2023-11-28 04:53:22,355][87426] Updated weights for policy 1, policy_version 178330 (0.0009) -[2023-11-28 04:53:23,223][87424] Updated weights for policy 0, policy_version 178787 (0.0012) -[2023-11-28 04:53:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 91422720. Throughput: 0: 2729.2, 1: 2751.2. Samples: 91441752. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:23,445][86177] Avg episode reward: [(0, '-505.520'), (1, '-544.210')] -[2023-11-28 04:53:23,597][87424] Updated weights for policy 0, policy_version 178797 (0.0008) -[2023-11-28 04:53:23,977][87424] Updated weights for policy 0, policy_version 178807 (0.0007) -[2023-11-28 04:53:24,533][87426] Updated weights for policy 1, policy_version 178340 (0.0008) -[2023-11-28 04:53:24,911][87426] Updated weights for policy 1, policy_version 178350 (0.0011) -[2023-11-28 04:53:25,292][87426] Updated weights for policy 1, policy_version 178360 (0.0009) -[2023-11-28 04:53:26,024][87424] Updated weights for policy 0, policy_version 178817 (0.0008) -[2023-11-28 04:53:26,407][87424] Updated weights for policy 0, policy_version 178827 (0.0012) -[2023-11-28 04:53:26,791][87424] Updated weights for policy 0, policy_version 178837 (0.0012) -[2023-11-28 04:53:27,182][87424] Updated weights for policy 0, policy_version 178847 (0.0012) -[2023-11-28 04:53:27,252][87426] Updated weights for policy 1, policy_version 178370 (0.0008) -[2023-11-28 04:53:27,634][87426] Updated weights for policy 1, policy_version 178380 (0.0010) -[2023-11-28 04:53:28,017][87426] Updated weights for policy 1, policy_version 178390 (0.0011) -[2023-11-28 04:53:28,404][87426] Updated weights for policy 1, policy_version 178400 (0.0011) -[2023-11-28 04:53:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5470.6). Total num frames: 91455488. Throughput: 0: 2746.0, 1: 2758.4. Samples: 91467164. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:28,445][86177] Avg episode reward: [(0, '-507.390'), (1, '-543.430')] -[2023-11-28 04:53:28,952][87424] Updated weights for policy 0, policy_version 178857 (0.0011) -[2023-11-28 04:53:29,334][87424] Updated weights for policy 0, policy_version 178867 (0.0012) -[2023-11-28 04:53:29,723][87424] Updated weights for policy 0, policy_version 178877 (0.0012) -[2023-11-28 04:53:30,545][87426] Updated weights for policy 1, policy_version 178410 (0.0011) -[2023-11-28 04:53:30,919][87426] Updated weights for policy 1, policy_version 178420 (0.0008) -[2023-11-28 04:53:31,304][87426] Updated weights for policy 1, policy_version 178430 (0.0007) -[2023-11-28 04:53:31,706][87424] Updated weights for policy 0, policy_version 178887 (0.0011) -[2023-11-28 04:53:32,088][87424] Updated weights for policy 0, policy_version 178897 (0.0011) -[2023-11-28 04:53:32,474][87424] Updated weights for policy 0, policy_version 178907 (0.0009) -[2023-11-28 04:53:33,437][87426] Updated weights for policy 1, policy_version 178440 (0.0009) -[2023-11-28 04:53:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 91480064. Throughput: 0: 2766.4, 1: 2754.6. Samples: 91491668. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:33,445][86177] Avg episode reward: [(0, '-500.530'), (1, '-573.420')] -[2023-11-28 04:53:33,816][87426] Updated weights for policy 1, policy_version 178450 (0.0008) -[2023-11-28 04:53:34,201][87426] Updated weights for policy 1, policy_version 178460 (0.0007) -[2023-11-28 04:53:34,929][87424] Updated weights for policy 0, policy_version 178917 (0.0009) -[2023-11-28 04:53:35,313][87424] Updated weights for policy 0, policy_version 178927 (0.0011) -[2023-11-28 04:53:35,691][87424] Updated weights for policy 0, policy_version 178937 (0.0007) -[2023-11-28 04:53:36,517][87426] Updated weights for policy 1, policy_version 178470 (0.0008) -[2023-11-28 04:53:36,921][87426] Updated weights for policy 1, policy_version 178480 (0.0010) -[2023-11-28 04:53:37,301][87426] Updated weights for policy 1, policy_version 178490 (0.0011) -[2023-11-28 04:53:37,861][87424] Updated weights for policy 0, policy_version 178947 (0.0008) -[2023-11-28 04:53:38,245][87424] Updated weights for policy 0, policy_version 178957 (0.0008) -[2023-11-28 04:53:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91504640. Throughput: 0: 2782.7, 1: 2768.5. Samples: 91524720. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:38,445][86177] Avg episode reward: [(0, '-497.270'), (1, '-578.070')] -[2023-11-28 04:53:38,623][87424] Updated weights for policy 0, policy_version 178967 (0.0008) -[2023-11-28 04:53:39,509][87426] Updated weights for policy 1, policy_version 178500 (0.0011) -[2023-11-28 04:53:39,877][87426] Updated weights for policy 1, policy_version 178510 (0.0012) -[2023-11-28 04:53:40,263][87426] Updated weights for policy 1, policy_version 178520 (0.0012) -[2023-11-28 04:53:40,648][87424] Updated weights for policy 0, policy_version 178977 (0.0011) -[2023-11-28 04:53:41,040][87424] Updated weights for policy 0, policy_version 178987 (0.0008) -[2023-11-28 04:53:41,421][87424] Updated weights for policy 0, policy_version 178997 (0.0008) -[2023-11-28 04:53:41,810][87424] Updated weights for policy 0, policy_version 179007 (0.0011) -[2023-11-28 04:53:42,562][87426] Updated weights for policy 1, policy_version 178530 (0.0010) -[2023-11-28 04:53:42,947][87426] Updated weights for policy 1, policy_version 178540 (0.0012) -[2023-11-28 04:53:43,329][87426] Updated weights for policy 1, policy_version 178550 (0.0011) -[2023-11-28 04:53:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 91529216. Throughput: 0: 2769.2, 1: 2754.0. Samples: 91548188. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:43,445][86177] Avg episode reward: [(0, '-494.690'), (1, '-641.230')] -[2023-11-28 04:53:43,696][87426] Updated weights for policy 1, policy_version 178560 (0.0012) -[2023-11-28 04:53:43,780][87424] Updated weights for policy 0, policy_version 179017 (0.0012) -[2023-11-28 04:53:44,154][87424] Updated weights for policy 0, policy_version 179027 (0.0012) -[2023-11-28 04:53:44,540][87424] Updated weights for policy 0, policy_version 179037 (0.0012) -[2023-11-28 04:53:46,049][87426] Updated weights for policy 1, policy_version 178570 (0.0012) -[2023-11-28 04:53:46,424][87426] Updated weights for policy 1, policy_version 178580 (0.0012) -[2023-11-28 04:53:46,803][87426] Updated weights for policy 1, policy_version 178590 (0.0012) -[2023-11-28 04:53:47,046][87424] Updated weights for policy 0, policy_version 179047 (0.0012) -[2023-11-28 04:53:47,432][87424] Updated weights for policy 0, policy_version 179057 (0.0009) -[2023-11-28 04:53:47,814][87424] Updated weights for policy 0, policy_version 179067 (0.0007) -[2023-11-28 04:53:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 91561984. Throughput: 0: 2749.2, 1: 2741.2. Samples: 91572384. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:48,445][86177] Avg episode reward: [(0, '-492.120'), (1, '-637.280')] -[2023-11-28 04:53:48,644][87426] Updated weights for policy 1, policy_version 178600 (0.0011) -[2023-11-28 04:53:49,034][87426] Updated weights for policy 1, policy_version 178610 (0.0012) -[2023-11-28 04:53:49,404][87426] Updated weights for policy 1, policy_version 178620 (0.0012) -[2023-11-28 04:53:49,839][87424] Updated weights for policy 0, policy_version 179077 (0.0011) -[2023-11-28 04:53:50,214][87424] Updated weights for policy 0, policy_version 179087 (0.0026) -[2023-11-28 04:53:50,595][87424] Updated weights for policy 0, policy_version 179097 (0.0011) -[2023-11-28 04:53:51,879][87426] Updated weights for policy 1, policy_version 178630 (0.0011) -[2023-11-28 04:53:52,265][87426] Updated weights for policy 1, policy_version 178640 (0.0011) -[2023-11-28 04:53:52,637][87426] Updated weights for policy 1, policy_version 178650 (0.0011) -[2023-11-28 04:53:52,763][87424] Updated weights for policy 0, policy_version 179107 (0.0011) -[2023-11-28 04:53:53,135][87424] Updated weights for policy 0, policy_version 179117 (0.0009) -[2023-11-28 04:53:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91586560. Throughput: 0: 2723.4, 1: 2715.1. Samples: 91604124. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:53,445][86177] Avg episode reward: [(0, '-492.850'), (1, '-653.470')] -[2023-11-28 04:53:53,515][87424] Updated weights for policy 0, policy_version 179127 (0.0010) -[2023-11-28 04:53:54,723][87426] Updated weights for policy 1, policy_version 178660 (0.0012) -[2023-11-28 04:53:55,104][87426] Updated weights for policy 1, policy_version 178670 (0.0010) -[2023-11-28 04:53:55,388][87424] Updated weights for policy 0, policy_version 179137 (0.0010) -[2023-11-28 04:53:55,476][87426] Updated weights for policy 1, policy_version 178680 (0.0009) -[2023-11-28 04:53:55,770][87424] Updated weights for policy 0, policy_version 179147 (0.0011) -[2023-11-28 04:53:56,155][87424] Updated weights for policy 0, policy_version 179157 (0.0012) -[2023-11-28 04:53:56,535][87424] Updated weights for policy 0, policy_version 179167 (0.0011) -[2023-11-28 04:53:57,614][87426] Updated weights for policy 1, policy_version 178690 (0.0007) -[2023-11-28 04:53:57,989][87426] Updated weights for policy 1, policy_version 178700 (0.0007) -[2023-11-28 04:53:58,367][87426] Updated weights for policy 1, policy_version 178710 (0.0007) -[2023-11-28 04:53:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91611136. Throughput: 0: 2734.3, 1: 2714.5. Samples: 91629152. Policy #0 lag: (min: 12.0, avg: 27.2, max: 44.0) -[2023-11-28 04:53:58,446][86177] Avg episode reward: [(0, '-501.100'), (1, '-605.470')] -[2023-11-28 04:53:58,752][87426] Updated weights for policy 1, policy_version 178720 (0.0008) -[2023-11-28 04:53:59,049][87424] Updated weights for policy 0, policy_version 179177 (0.0008) -[2023-11-28 04:53:59,435][87424] Updated weights for policy 0, policy_version 179187 (0.0008) -[2023-11-28 04:53:59,816][87424] Updated weights for policy 0, policy_version 179197 (0.0008) -[2023-11-28 04:54:01,121][87426] Updated weights for policy 1, policy_version 178730 (0.0007) -[2023-11-28 04:54:01,495][87426] Updated weights for policy 1, policy_version 178740 (0.0007) -[2023-11-28 04:54:01,872][87426] Updated weights for policy 1, policy_version 178750 (0.0010) -[2023-11-28 04:54:01,900][87424] Updated weights for policy 0, policy_version 179207 (0.0010) -[2023-11-28 04:54:02,289][87424] Updated weights for policy 0, policy_version 179217 (0.0009) -[2023-11-28 04:54:02,662][87424] Updated weights for policy 0, policy_version 179227 (0.0007) -[2023-11-28 04:54:03,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91643904. Throughput: 0: 2736.3, 1: 2706.7. Samples: 91653380. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:03,446][86177] Avg episode reward: [(0, '-502.520'), (1, '-559.960')] -[2023-11-28 04:54:03,926][87426] Updated weights for policy 1, policy_version 178760 (0.0010) -[2023-11-28 04:54:04,310][87426] Updated weights for policy 1, policy_version 178770 (0.0007) -[2023-11-28 04:54:04,693][87426] Updated weights for policy 1, policy_version 178780 (0.0011) -[2023-11-28 04:54:05,150][87424] Updated weights for policy 0, policy_version 179237 (0.0009) -[2023-11-28 04:54:05,544][87424] Updated weights for policy 0, policy_version 179247 (0.0012) -[2023-11-28 04:54:05,921][87424] Updated weights for policy 0, policy_version 179257 (0.0012) -[2023-11-28 04:54:06,716][87426] Updated weights for policy 1, policy_version 178790 (0.0011) -[2023-11-28 04:54:07,094][87426] Updated weights for policy 1, policy_version 178800 (0.0012) -[2023-11-28 04:54:07,473][87426] Updated weights for policy 1, policy_version 178810 (0.0012) -[2023-11-28 04:54:07,653][87424] Updated weights for policy 0, policy_version 179267 (0.0012) -[2023-11-28 04:54:08,036][87424] Updated weights for policy 0, policy_version 179277 (0.0010) -[2023-11-28 04:54:08,417][87424] Updated weights for policy 0, policy_version 179287 (0.0011) -[2023-11-28 04:54:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91668480. Throughput: 0: 2756.2, 1: 2695.3. Samples: 91687068. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:08,445][86177] Avg episode reward: [(0, '-502.420'), (1, '-566.710')] -[2023-11-28 04:54:09,897][87426] Updated weights for policy 1, policy_version 178820 (0.0012) -[2023-11-28 04:54:10,281][87426] Updated weights for policy 1, policy_version 178830 (0.0010) -[2023-11-28 04:54:10,534][87424] Updated weights for policy 0, policy_version 179297 (0.0012) -[2023-11-28 04:54:10,662][87426] Updated weights for policy 1, policy_version 178840 (0.0011) -[2023-11-28 04:54:10,915][87424] Updated weights for policy 0, policy_version 179307 (0.0012) -[2023-11-28 04:54:11,297][87424] Updated weights for policy 0, policy_version 179317 (0.0012) -[2023-11-28 04:54:11,677][87424] Updated weights for policy 0, policy_version 179327 (0.0012) -[2023-11-28 04:54:13,034][87426] Updated weights for policy 1, policy_version 178850 (0.0010) -[2023-11-28 04:54:13,416][87426] Updated weights for policy 1, policy_version 178860 (0.0012) -[2023-11-28 04:54:13,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91693056. Throughput: 0: 2742.1, 1: 2678.9. Samples: 91711112. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:13,445][86177] Avg episode reward: [(0, '-499.110'), (1, '-584.800')] -[2023-11-28 04:54:13,757][87424] Updated weights for policy 0, policy_version 179337 (0.0011) -[2023-11-28 04:54:13,806][87426] Updated weights for policy 1, policy_version 178870 (0.0010) -[2023-11-28 04:54:14,134][87424] Updated weights for policy 0, policy_version 179347 (0.0009) -[2023-11-28 04:54:14,178][87426] Updated weights for policy 1, policy_version 178880 (0.0007) -[2023-11-28 04:54:14,510][87424] Updated weights for policy 0, policy_version 179357 (0.0009) -[2023-11-28 04:54:16,264][87426] Updated weights for policy 1, policy_version 178890 (0.0012) -[2023-11-28 04:54:16,580][87424] Updated weights for policy 0, policy_version 179367 (0.0008) -[2023-11-28 04:54:16,636][87426] Updated weights for policy 1, policy_version 178900 (0.0011) -[2023-11-28 04:54:16,954][87424] Updated weights for policy 0, policy_version 179377 (0.0007) -[2023-11-28 04:54:17,021][87426] Updated weights for policy 1, policy_version 178910 (0.0011) -[2023-11-28 04:54:17,327][87424] Updated weights for policy 0, policy_version 179387 (0.0011) -[2023-11-28 04:54:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 91725824. Throughput: 0: 2734.7, 1: 2669.9. Samples: 91734872. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:18,445][86177] Avg episode reward: [(0, '-500.140'), (1, '-566.100')] -[2023-11-28 04:54:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000179392_45924352.pth... -[2023-11-28 04:54:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000178912_45801472.pth... -[2023-11-28 04:54:18,489][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000176864_45277184.pth -[2023-11-28 04:54:18,504][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000176352_45146112.pth -[2023-11-28 04:54:19,157][87426] Updated weights for policy 1, policy_version 178920 (0.0012) -[2023-11-28 04:54:19,537][87426] Updated weights for policy 1, policy_version 178930 (0.0012) -[2023-11-28 04:54:19,763][87424] Updated weights for policy 0, policy_version 179397 (0.0010) -[2023-11-28 04:54:19,918][87426] Updated weights for policy 1, policy_version 178940 (0.0011) -[2023-11-28 04:54:20,146][87424] Updated weights for policy 0, policy_version 179407 (0.0011) -[2023-11-28 04:54:20,532][87424] Updated weights for policy 0, policy_version 179417 (0.0012) -[2023-11-28 04:54:22,056][87426] Updated weights for policy 1, policy_version 178950 (0.0011) -[2023-11-28 04:54:22,438][87426] Updated weights for policy 1, policy_version 178960 (0.0009) -[2023-11-28 04:54:22,820][87426] Updated weights for policy 1, policy_version 178970 (0.0008) -[2023-11-28 04:54:22,866][87424] Updated weights for policy 0, policy_version 179427 (0.0011) -[2023-11-28 04:54:23,246][87424] Updated weights for policy 0, policy_version 179437 (0.0012) -[2023-11-28 04:54:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91750400. Throughput: 0: 2708.7, 1: 2671.8. Samples: 91766844. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:23,445][86177] Avg episode reward: [(0, '-499.910'), (1, '-547.850')] -[2023-11-28 04:54:23,631][87424] Updated weights for policy 0, policy_version 179447 (0.0011) -[2023-11-28 04:54:24,934][87426] Updated weights for policy 1, policy_version 178980 (0.0011) -[2023-11-28 04:54:25,318][87426] Updated weights for policy 1, policy_version 178990 (0.0012) -[2023-11-28 04:54:25,701][87426] Updated weights for policy 1, policy_version 179000 (0.0012) -[2023-11-28 04:54:25,809][87424] Updated weights for policy 0, policy_version 179457 (0.0011) -[2023-11-28 04:54:26,197][87424] Updated weights for policy 0, policy_version 179467 (0.0007) -[2023-11-28 04:54:26,584][87424] Updated weights for policy 0, policy_version 179477 (0.0008) -[2023-11-28 04:54:26,970][87424] Updated weights for policy 0, policy_version 179487 (0.0007) -[2023-11-28 04:54:28,077][87426] Updated weights for policy 1, policy_version 179010 (0.0008) -[2023-11-28 04:54:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 91774976. Throughput: 0: 2716.4, 1: 2717.6. Samples: 91792720. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:28,446][86177] Avg episode reward: [(0, '-496.120'), (1, '-561.850')] -[2023-11-28 04:54:28,464][87426] Updated weights for policy 1, policy_version 179020 (0.0007) -[2023-11-28 04:54:28,856][87426] Updated weights for policy 1, policy_version 179030 (0.0008) -[2023-11-28 04:54:29,230][87426] Updated weights for policy 1, policy_version 179040 (0.0008) -[2023-11-28 04:54:29,304][87424] Updated weights for policy 0, policy_version 179497 (0.0012) -[2023-11-28 04:54:29,688][87424] Updated weights for policy 0, policy_version 179507 (0.0009) -[2023-11-28 04:54:30,064][87424] Updated weights for policy 0, policy_version 179517 (0.0009) -[2023-11-28 04:54:31,180][87426] Updated weights for policy 1, policy_version 179050 (0.0012) -[2023-11-28 04:54:31,561][87426] Updated weights for policy 1, policy_version 179060 (0.0011) -[2023-11-28 04:54:31,940][87426] Updated weights for policy 1, policy_version 179070 (0.0012) -[2023-11-28 04:54:32,386][87424] Updated weights for policy 0, policy_version 179527 (0.0010) -[2023-11-28 04:54:32,767][87424] Updated weights for policy 0, policy_version 179537 (0.0009) -[2023-11-28 04:54:33,158][87424] Updated weights for policy 0, policy_version 179547 (0.0008) -[2023-11-28 04:54:33,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91807744. Throughput: 0: 2701.9, 1: 2725.9. Samples: 91816636. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:33,446][86177] Avg episode reward: [(0, '-493.960'), (1, '-528.890')] -[2023-11-28 04:54:34,432][87426] Updated weights for policy 1, policy_version 179080 (0.0010) -[2023-11-28 04:54:34,814][87426] Updated weights for policy 1, policy_version 179090 (0.0010) -[2023-11-28 04:54:34,995][87424] Updated weights for policy 0, policy_version 179557 (0.0010) -[2023-11-28 04:54:35,189][87426] Updated weights for policy 1, policy_version 179100 (0.0010) -[2023-11-28 04:54:35,380][87424] Updated weights for policy 0, policy_version 179567 (0.0012) -[2023-11-28 04:54:35,758][87424] Updated weights for policy 0, policy_version 179577 (0.0012) -[2023-11-28 04:54:37,460][87426] Updated weights for policy 1, policy_version 179110 (0.0011) -[2023-11-28 04:54:37,832][87426] Updated weights for policy 1, policy_version 179120 (0.0012) -[2023-11-28 04:54:38,165][87424] Updated weights for policy 0, policy_version 179587 (0.0012) -[2023-11-28 04:54:38,209][87426] Updated weights for policy 1, policy_version 179130 (0.0011) -[2023-11-28 04:54:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 91832320. Throughput: 0: 2718.3, 1: 2726.6. Samples: 91849144. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:38,445][86177] Avg episode reward: [(0, '-495.140'), (1, '-527.540')] -[2023-11-28 04:54:38,545][87424] Updated weights for policy 0, policy_version 179597 (0.0011) -[2023-11-28 04:54:38,925][87424] Updated weights for policy 0, policy_version 179607 (0.0012) -[2023-11-28 04:54:40,335][87426] Updated weights for policy 1, policy_version 179140 (0.0008) -[2023-11-28 04:54:40,722][87426] Updated weights for policy 1, policy_version 179150 (0.0010) -[2023-11-28 04:54:41,051][87424] Updated weights for policy 0, policy_version 179617 (0.0011) -[2023-11-28 04:54:41,095][87426] Updated weights for policy 1, policy_version 179160 (0.0007) -[2023-11-28 04:54:41,421][87424] Updated weights for policy 0, policy_version 179627 (0.0012) -[2023-11-28 04:54:41,801][87424] Updated weights for policy 0, policy_version 179637 (0.0012) -[2023-11-28 04:54:42,192][87424] Updated weights for policy 0, policy_version 179647 (0.0011) -[2023-11-28 04:54:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91856896. Throughput: 0: 2699.9, 1: 2707.3. Samples: 91872476. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:43,445][86177] Avg episode reward: [(0, '-494.560'), (1, '-529.790')] -[2023-11-28 04:54:43,462][87426] Updated weights for policy 1, policy_version 179170 (0.0008) -[2023-11-28 04:54:43,840][87426] Updated weights for policy 1, policy_version 179180 (0.0012) -[2023-11-28 04:54:44,219][87426] Updated weights for policy 1, policy_version 179190 (0.0012) -[2023-11-28 04:54:44,598][87426] Updated weights for policy 1, policy_version 179200 (0.0011) -[2023-11-28 04:54:44,858][87424] Updated weights for policy 0, policy_version 179657 (0.0011) -[2023-11-28 04:54:45,254][87424] Updated weights for policy 0, policy_version 179667 (0.0011) -[2023-11-28 04:54:45,629][87424] Updated weights for policy 0, policy_version 179677 (0.0009) -[2023-11-28 04:54:47,072][87426] Updated weights for policy 1, policy_version 179210 (0.0012) -[2023-11-28 04:54:47,341][87424] Updated weights for policy 0, policy_version 179687 (0.0011) -[2023-11-28 04:54:47,458][87426] Updated weights for policy 1, policy_version 179220 (0.0012) -[2023-11-28 04:54:47,718][87424] Updated weights for policy 0, policy_version 179697 (0.0011) -[2023-11-28 04:54:47,842][87426] Updated weights for policy 1, policy_version 179230 (0.0012) -[2023-11-28 04:54:48,101][87424] Updated weights for policy 0, policy_version 179707 (0.0012) -[2023-11-28 04:54:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 91889664. Throughput: 0: 2692.5, 1: 2699.7. Samples: 91896032. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:48,445][86177] Avg episode reward: [(0, '-493.880'), (1, '-572.290')] -[2023-11-28 04:54:49,776][87426] Updated weights for policy 1, policy_version 179240 (0.0010) -[2023-11-28 04:54:50,150][87426] Updated weights for policy 1, policy_version 179250 (0.0010) -[2023-11-28 04:54:50,524][87426] Updated weights for policy 1, policy_version 179260 (0.0008) -[2023-11-28 04:54:50,643][87424] Updated weights for policy 0, policy_version 179717 (0.0011) -[2023-11-28 04:54:51,014][87424] Updated weights for policy 0, policy_version 179727 (0.0008) -[2023-11-28 04:54:51,411][87424] Updated weights for policy 0, policy_version 179737 (0.0008) -[2023-11-28 04:54:52,788][87426] Updated weights for policy 1, policy_version 179270 (0.0011) -[2023-11-28 04:54:53,164][87426] Updated weights for policy 1, policy_version 179280 (0.0012) -[2023-11-28 04:54:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 91906048. Throughput: 0: 2659.9, 1: 2705.8. Samples: 91928524. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:53,446][86177] Avg episode reward: [(0, '-501.250'), (1, '-567.840')] -[2023-11-28 04:54:53,545][87426] Updated weights for policy 1, policy_version 179290 (0.0010) -[2023-11-28 04:54:53,788][87424] Updated weights for policy 0, policy_version 179747 (0.0010) -[2023-11-28 04:54:54,180][87424] Updated weights for policy 0, policy_version 179757 (0.0009) -[2023-11-28 04:54:54,562][87424] Updated weights for policy 0, policy_version 179767 (0.0007) -[2023-11-28 04:54:56,010][87426] Updated weights for policy 1, policy_version 179300 (0.0011) -[2023-11-28 04:54:56,380][87426] Updated weights for policy 1, policy_version 179310 (0.0012) -[2023-11-28 04:54:56,595][87424] Updated weights for policy 0, policy_version 179777 (0.0008) -[2023-11-28 04:54:56,757][87426] Updated weights for policy 1, policy_version 179320 (0.0012) -[2023-11-28 04:54:56,974][87424] Updated weights for policy 0, policy_version 179787 (0.0011) -[2023-11-28 04:54:57,358][87424] Updated weights for policy 0, policy_version 179797 (0.0011) -[2023-11-28 04:54:57,740][87424] Updated weights for policy 0, policy_version 179807 (0.0012) -[2023-11-28 04:54:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 91938816. Throughput: 0: 2665.7, 1: 2701.2. Samples: 91952624. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:54:58,445][86177] Avg episode reward: [(0, '-499.400'), (1, '-617.890')] -[2023-11-28 04:54:58,649][87426] Updated weights for policy 1, policy_version 179330 (0.0011) -[2023-11-28 04:54:59,042][87426] Updated weights for policy 1, policy_version 179340 (0.0008) -[2023-11-28 04:54:59,415][87426] Updated weights for policy 1, policy_version 179350 (0.0008) -[2023-11-28 04:54:59,797][87426] Updated weights for policy 1, policy_version 179360 (0.0008) -[2023-11-28 04:55:00,115][87424] Updated weights for policy 0, policy_version 179817 (0.0012) -[2023-11-28 04:55:00,504][87424] Updated weights for policy 0, policy_version 179827 (0.0012) -[2023-11-28 04:55:00,883][87424] Updated weights for policy 0, policy_version 179837 (0.0012) -[2023-11-28 04:55:02,084][87426] Updated weights for policy 1, policy_version 179370 (0.0011) -[2023-11-28 04:55:02,460][87426] Updated weights for policy 1, policy_version 179380 (0.0010) -[2023-11-28 04:55:02,840][87426] Updated weights for policy 1, policy_version 179390 (0.0010) -[2023-11-28 04:55:03,189][87424] Updated weights for policy 0, policy_version 179847 (0.0010) -[2023-11-28 04:55:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 91963392. Throughput: 0: 2663.8, 1: 2699.6. Samples: 91976224. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:55:03,445][86177] Avg episode reward: [(0, '-502.010'), (1, '-629.620')] -[2023-11-28 04:55:03,573][87424] Updated weights for policy 0, policy_version 179857 (0.0008) -[2023-11-28 04:55:03,960][87424] Updated weights for policy 0, policy_version 179867 (0.0009) -[2023-11-28 04:55:05,373][87426] Updated weights for policy 1, policy_version 179400 (0.0012) -[2023-11-28 04:55:05,754][87426] Updated weights for policy 1, policy_version 179410 (0.0011) -[2023-11-28 04:55:06,017][87424] Updated weights for policy 0, policy_version 179877 (0.0010) -[2023-11-28 04:55:06,132][87426] Updated weights for policy 1, policy_version 179420 (0.0011) -[2023-11-28 04:55:06,399][87424] Updated weights for policy 0, policy_version 179887 (0.0008) -[2023-11-28 04:55:06,783][87424] Updated weights for policy 0, policy_version 179897 (0.0010) -[2023-11-28 04:55:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 91987968. Throughput: 0: 2664.2, 1: 2678.9. Samples: 92007284. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 04:55:08,445][86177] Avg episode reward: [(0, '-502.980'), (1, '-582.820')] -[2023-11-28 04:55:08,475][87426] Updated weights for policy 1, policy_version 179430 (0.0011) -[2023-11-28 04:55:08,843][87426] Updated weights for policy 1, policy_version 179440 (0.0010) -[2023-11-28 04:55:08,848][87424] Updated weights for policy 0, policy_version 179907 (0.0011) -[2023-11-28 04:55:09,225][87424] Updated weights for policy 0, policy_version 179917 (0.0011) -[2023-11-28 04:55:09,226][87426] Updated weights for policy 1, policy_version 179450 (0.0010) -[2023-11-28 04:55:09,605][87424] Updated weights for policy 0, policy_version 179927 (0.0012) -[2023-11-28 04:55:11,231][87426] Updated weights for policy 1, policy_version 179460 (0.0011) -[2023-11-28 04:55:11,603][87426] Updated weights for policy 1, policy_version 179470 (0.0012) -[2023-11-28 04:55:11,981][87426] Updated weights for policy 1, policy_version 179480 (0.0012) -[2023-11-28 04:55:12,067][87424] Updated weights for policy 0, policy_version 179937 (0.0012) -[2023-11-28 04:55:12,441][87424] Updated weights for policy 0, policy_version 179947 (0.0012) -[2023-11-28 04:55:12,825][87424] Updated weights for policy 0, policy_version 179957 (0.0012) -[2023-11-28 04:55:13,208][87424] Updated weights for policy 0, policy_version 179967 (0.0012) -[2023-11-28 04:55:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 92020736. Throughput: 0: 2658.1, 1: 2645.4. Samples: 92031380. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:13,445][86177] Avg episode reward: [(0, '-502.500'), (1, '-580.640')] -[2023-11-28 04:55:14,214][87426] Updated weights for policy 1, policy_version 179490 (0.0011) -[2023-11-28 04:55:14,598][87426] Updated weights for policy 1, policy_version 179500 (0.0012) -[2023-11-28 04:55:14,968][87426] Updated weights for policy 1, policy_version 179510 (0.0012) -[2023-11-28 04:55:15,345][87426] Updated weights for policy 1, policy_version 179520 (0.0011) -[2023-11-28 04:55:15,496][87424] Updated weights for policy 0, policy_version 179977 (0.0011) -[2023-11-28 04:55:15,870][87424] Updated weights for policy 0, policy_version 179987 (0.0011) -[2023-11-28 04:55:16,257][87424] Updated weights for policy 0, policy_version 179997 (0.0009) -[2023-11-28 04:55:17,399][87426] Updated weights for policy 1, policy_version 179530 (0.0012) -[2023-11-28 04:55:17,773][87426] Updated weights for policy 1, policy_version 179540 (0.0012) -[2023-11-28 04:55:18,161][87426] Updated weights for policy 1, policy_version 179550 (0.0011) -[2023-11-28 04:55:18,228][87424] Updated weights for policy 0, policy_version 180007 (0.0010) -[2023-11-28 04:55:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92045312. Throughput: 0: 2651.9, 1: 2643.1. Samples: 92054912. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:18,445][86177] Avg episode reward: [(0, '-506.130'), (1, '-527.350')] -[2023-11-28 04:55:18,624][87424] Updated weights for policy 0, policy_version 180017 (0.0012) -[2023-11-28 04:55:19,000][87424] Updated weights for policy 0, policy_version 180027 (0.0012) -[2023-11-28 04:55:20,331][87426] Updated weights for policy 1, policy_version 179560 (0.0011) -[2023-11-28 04:55:20,708][87426] Updated weights for policy 1, policy_version 179570 (0.0012) -[2023-11-28 04:55:21,089][87426] Updated weights for policy 1, policy_version 179580 (0.0012) -[2023-11-28 04:55:21,124][87424] Updated weights for policy 0, policy_version 180037 (0.0011) -[2023-11-28 04:55:21,505][87424] Updated weights for policy 0, policy_version 180047 (0.0012) -[2023-11-28 04:55:21,896][87424] Updated weights for policy 0, policy_version 180057 (0.0012) -[2023-11-28 04:55:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 92069888. Throughput: 0: 2654.0, 1: 2628.3. Samples: 92086852. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:23,446][86177] Avg episode reward: [(0, '-506.010'), (1, '-555.020')] -[2023-11-28 04:55:23,709][87426] Updated weights for policy 1, policy_version 179590 (0.0011) -[2023-11-28 04:55:24,079][87426] Updated weights for policy 1, policy_version 179600 (0.0012) -[2023-11-28 04:55:24,086][87424] Updated weights for policy 0, policy_version 180067 (0.0011) -[2023-11-28 04:55:24,464][87424] Updated weights for policy 0, policy_version 180077 (0.0007) -[2023-11-28 04:55:24,470][87426] Updated weights for policy 1, policy_version 179610 (0.0007) -[2023-11-28 04:55:24,851][87424] Updated weights for policy 0, policy_version 180087 (0.0007) -[2023-11-28 04:55:26,263][87426] Updated weights for policy 1, policy_version 179620 (0.0009) -[2023-11-28 04:55:26,641][87426] Updated weights for policy 1, policy_version 179630 (0.0011) -[2023-11-28 04:55:27,012][87424] Updated weights for policy 0, policy_version 180097 (0.0008) -[2023-11-28 04:55:27,023][87426] Updated weights for policy 1, policy_version 179640 (0.0012) -[2023-11-28 04:55:27,390][87424] Updated weights for policy 0, policy_version 180107 (0.0011) -[2023-11-28 04:55:27,781][87424] Updated weights for policy 0, policy_version 180117 (0.0012) -[2023-11-28 04:55:28,166][87424] Updated weights for policy 0, policy_version 180127 (0.0012) -[2023-11-28 04:55:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 92102656. Throughput: 0: 2661.2, 1: 2648.3. Samples: 92111404. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:28,446][86177] Avg episode reward: [(0, '-504.180'), (1, '-557.030')] -[2023-11-28 04:55:29,113][87426] Updated weights for policy 1, policy_version 179650 (0.0008) -[2023-11-28 04:55:29,488][87426] Updated weights for policy 1, policy_version 179660 (0.0008) -[2023-11-28 04:55:29,862][87426] Updated weights for policy 1, policy_version 179670 (0.0008) -[2023-11-28 04:55:30,060][87424] Updated weights for policy 0, policy_version 180137 (0.0012) -[2023-11-28 04:55:30,248][87426] Updated weights for policy 1, policy_version 179680 (0.0008) -[2023-11-28 04:55:30,448][87424] Updated weights for policy 0, policy_version 180147 (0.0011) -[2023-11-28 04:55:30,829][87424] Updated weights for policy 0, policy_version 180157 (0.0007) -[2023-11-28 04:55:32,599][87426] Updated weights for policy 1, policy_version 179690 (0.0010) -[2023-11-28 04:55:32,710][87424] Updated weights for policy 0, policy_version 180167 (0.0010) -[2023-11-28 04:55:32,975][87426] Updated weights for policy 1, policy_version 179700 (0.0007) -[2023-11-28 04:55:33,092][87424] Updated weights for policy 0, policy_version 180177 (0.0010) -[2023-11-28 04:55:33,352][87426] Updated weights for policy 1, policy_version 179710 (0.0008) -[2023-11-28 04:55:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 92127232. Throughput: 0: 2690.6, 1: 2669.1. Samples: 92137216. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:33,445][86177] Avg episode reward: [(0, '-508.210'), (1, '-556.440')] -[2023-11-28 04:55:33,476][87424] Updated weights for policy 0, policy_version 180187 (0.0011) -[2023-11-28 04:55:35,566][87424] Updated weights for policy 0, policy_version 180197 (0.0012) -[2023-11-28 04:55:35,860][87426] Updated weights for policy 1, policy_version 179720 (0.0011) -[2023-11-28 04:55:35,941][87424] Updated weights for policy 0, policy_version 180207 (0.0011) -[2023-11-28 04:55:36,236][87426] Updated weights for policy 1, policy_version 179730 (0.0011) -[2023-11-28 04:55:36,323][87424] Updated weights for policy 0, policy_version 180217 (0.0010) -[2023-11-28 04:55:36,623][87426] Updated weights for policy 1, policy_version 179740 (0.0011) -[2023-11-28 04:55:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92151808. Throughput: 0: 2702.9, 1: 2664.0. Samples: 92170036. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:38,445][86177] Avg episode reward: [(0, '-509.530'), (1, '-559.620')] -[2023-11-28 04:55:38,515][87426] Updated weights for policy 1, policy_version 179750 (0.0010) -[2023-11-28 04:55:38,871][87424] Updated weights for policy 0, policy_version 180227 (0.0009) -[2023-11-28 04:55:38,904][87426] Updated weights for policy 1, policy_version 179760 (0.0013) -[2023-11-28 04:55:39,255][87424] Updated weights for policy 0, policy_version 180237 (0.0011) -[2023-11-28 04:55:39,281][87426] Updated weights for policy 1, policy_version 179770 (0.0011) -[2023-11-28 04:55:39,637][87424] Updated weights for policy 0, policy_version 180247 (0.0011) -[2023-11-28 04:55:41,170][87426] Updated weights for policy 1, policy_version 179780 (0.0010) -[2023-11-28 04:55:41,563][87426] Updated weights for policy 1, policy_version 179790 (0.0010) -[2023-11-28 04:55:41,928][87426] Updated weights for policy 1, policy_version 179800 (0.0011) -[2023-11-28 04:55:42,105][87424] Updated weights for policy 0, policy_version 180257 (0.0011) -[2023-11-28 04:55:42,486][87424] Updated weights for policy 0, policy_version 180267 (0.0009) -[2023-11-28 04:55:42,874][87424] Updated weights for policy 0, policy_version 180277 (0.0009) -[2023-11-28 04:55:43,251][87424] Updated weights for policy 0, policy_version 180287 (0.0008) -[2023-11-28 04:55:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 92184576. Throughput: 0: 2689.9, 1: 2679.7. Samples: 92194256. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:43,446][86177] Avg episode reward: [(0, '-505.710'), (1, '-540.260')] -[2023-11-28 04:55:44,490][87426] Updated weights for policy 1, policy_version 179810 (0.0008) -[2023-11-28 04:55:44,874][87426] Updated weights for policy 1, policy_version 179820 (0.0007) -[2023-11-28 04:55:45,256][87426] Updated weights for policy 1, policy_version 179830 (0.0008) -[2023-11-28 04:55:45,637][87426] Updated weights for policy 1, policy_version 179840 (0.0010) -[2023-11-28 04:55:45,745][87424] Updated weights for policy 0, policy_version 180297 (0.0011) -[2023-11-28 04:55:46,132][87424] Updated weights for policy 0, policy_version 180307 (0.0012) -[2023-11-28 04:55:46,512][87424] Updated weights for policy 0, policy_version 180317 (0.0012) -[2023-11-28 04:55:47,655][87426] Updated weights for policy 1, policy_version 179850 (0.0010) -[2023-11-28 04:55:48,043][87426] Updated weights for policy 1, policy_version 179860 (0.0009) -[2023-11-28 04:55:48,418][87426] Updated weights for policy 1, policy_version 179870 (0.0011) -[2023-11-28 04:55:48,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.2, 300 sec: 5415.0). Total num frames: 92200960. Throughput: 0: 2691.8, 1: 2691.0. Samples: 92218452. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:48,446][86177] Avg episode reward: [(0, '-502.710'), (1, '-562.320')] -[2023-11-28 04:55:48,831][87424] Updated weights for policy 0, policy_version 180327 (0.0012) -[2023-11-28 04:55:49,222][87424] Updated weights for policy 0, policy_version 180337 (0.0012) -[2023-11-28 04:55:49,597][87424] Updated weights for policy 0, policy_version 180347 (0.0012) -[2023-11-28 04:55:50,401][87426] Updated weights for policy 1, policy_version 179880 (0.0011) -[2023-11-28 04:55:50,782][87426] Updated weights for policy 1, policy_version 179890 (0.0010) -[2023-11-28 04:55:51,163][87426] Updated weights for policy 1, policy_version 179900 (0.0009) -[2023-11-28 04:55:51,480][87424] Updated weights for policy 0, policy_version 180357 (0.0011) -[2023-11-28 04:55:51,851][87424] Updated weights for policy 0, policy_version 180367 (0.0012) -[2023-11-28 04:55:52,230][87424] Updated weights for policy 0, policy_version 180377 (0.0012) -[2023-11-28 04:55:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 92233728. Throughput: 0: 2700.5, 1: 2720.0. Samples: 92251208. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:53,445][86177] Avg episode reward: [(0, '-496.360'), (1, '-578.000')] -[2023-11-28 04:55:53,480][87426] Updated weights for policy 1, policy_version 179910 (0.0010) -[2023-11-28 04:55:53,855][87426] Updated weights for policy 1, policy_version 179920 (0.0009) -[2023-11-28 04:55:54,236][87426] Updated weights for policy 1, policy_version 179930 (0.0007) -[2023-11-28 04:55:54,603][87424] Updated weights for policy 0, policy_version 180387 (0.0009) -[2023-11-28 04:55:54,992][87424] Updated weights for policy 0, policy_version 180397 (0.0009) -[2023-11-28 04:55:55,371][87424] Updated weights for policy 0, policy_version 180407 (0.0007) -[2023-11-28 04:55:56,427][87426] Updated weights for policy 1, policy_version 179940 (0.0009) -[2023-11-28 04:55:56,805][87426] Updated weights for policy 1, policy_version 179950 (0.0011) -[2023-11-28 04:55:57,190][87426] Updated weights for policy 1, policy_version 179960 (0.0010) -[2023-11-28 04:55:57,621][87424] Updated weights for policy 0, policy_version 180417 (0.0008) -[2023-11-28 04:55:58,019][87424] Updated weights for policy 0, policy_version 180427 (0.0010) -[2023-11-28 04:55:58,415][87424] Updated weights for policy 0, policy_version 180437 (0.0011) -[2023-11-28 04:55:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 92258304. Throughput: 0: 2714.4, 1: 2706.4. Samples: 92275316. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:55:58,445][86177] Avg episode reward: [(0, '-499.180'), (1, '-575.300')] -[2023-11-28 04:55:58,788][87424] Updated weights for policy 0, policy_version 180447 (0.0009) -[2023-11-28 04:55:59,368][87426] Updated weights for policy 1, policy_version 179970 (0.0011) -[2023-11-28 04:55:59,755][87426] Updated weights for policy 1, policy_version 179980 (0.0012) -[2023-11-28 04:56:00,134][87426] Updated weights for policy 1, policy_version 179990 (0.0009) -[2023-11-28 04:56:00,517][87426] Updated weights for policy 1, policy_version 180000 (0.0009) -[2023-11-28 04:56:00,682][87424] Updated weights for policy 0, policy_version 180457 (0.0011) -[2023-11-28 04:56:01,058][87424] Updated weights for policy 0, policy_version 180467 (0.0012) -[2023-11-28 04:56:01,444][87424] Updated weights for policy 0, policy_version 180477 (0.0012) -[2023-11-28 04:56:02,711][87426] Updated weights for policy 1, policy_version 180010 (0.0011) -[2023-11-28 04:56:03,087][87426] Updated weights for policy 1, policy_version 180020 (0.0009) -[2023-11-28 04:56:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92282880. Throughput: 0: 2734.2, 1: 2706.1. Samples: 92299728. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:56:03,445][86177] Avg episode reward: [(0, '-497.490'), (1, '-555.900')] -[2023-11-28 04:56:03,459][87426] Updated weights for policy 1, policy_version 180030 (0.0009) -[2023-11-28 04:56:03,708][87424] Updated weights for policy 0, policy_version 180487 (0.0012) -[2023-11-28 04:56:04,086][87424] Updated weights for policy 0, policy_version 180497 (0.0011) -[2023-11-28 04:56:04,468][87424] Updated weights for policy 0, policy_version 180507 (0.0012) -[2023-11-28 04:56:05,778][87426] Updated weights for policy 1, policy_version 180040 (0.0010) -[2023-11-28 04:56:06,161][87426] Updated weights for policy 1, policy_version 180050 (0.0012) -[2023-11-28 04:56:06,540][87426] Updated weights for policy 1, policy_version 180060 (0.0012) -[2023-11-28 04:56:06,884][87424] Updated weights for policy 0, policy_version 180517 (0.0011) -[2023-11-28 04:56:07,275][87424] Updated weights for policy 0, policy_version 180527 (0.0010) -[2023-11-28 04:56:07,649][87424] Updated weights for policy 0, policy_version 180537 (0.0007) -[2023-11-28 04:56:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 92315648. Throughput: 0: 2714.7, 1: 2721.9. Samples: 92331496. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:56:08,445][86177] Avg episode reward: [(0, '-497.350'), (1, '-517.710')] -[2023-11-28 04:56:08,522][87426] Updated weights for policy 1, policy_version 180070 (0.0011) -[2023-11-28 04:56:08,894][87426] Updated weights for policy 1, policy_version 180080 (0.0007) -[2023-11-28 04:56:09,273][87426] Updated weights for policy 1, policy_version 180090 (0.0008) -[2023-11-28 04:56:10,104][87424] Updated weights for policy 0, policy_version 180547 (0.0008) -[2023-11-28 04:56:10,485][87424] Updated weights for policy 0, policy_version 180557 (0.0011) -[2023-11-28 04:56:10,875][87424] Updated weights for policy 0, policy_version 180567 (0.0008) -[2023-11-28 04:56:11,635][87426] Updated weights for policy 1, policy_version 180100 (0.0009) -[2023-11-28 04:56:12,020][87426] Updated weights for policy 1, policy_version 180110 (0.0009) -[2023-11-28 04:56:12,408][87426] Updated weights for policy 1, policy_version 180120 (0.0009) -[2023-11-28 04:56:13,320][87424] Updated weights for policy 0, policy_version 180577 (0.0009) -[2023-11-28 04:56:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92340224. Throughput: 0: 2699.9, 1: 2717.3. Samples: 92355180. Policy #0 lag: (min: 1.0, avg: 28.2, max: 47.0) -[2023-11-28 04:56:13,445][86177] Avg episode reward: [(0, '-496.780'), (1, '-506.500')] -[2023-11-28 04:56:13,706][87424] Updated weights for policy 0, policy_version 180587 (0.0012) -[2023-11-28 04:56:14,081][87424] Updated weights for policy 0, policy_version 180597 (0.0012) -[2023-11-28 04:56:14,397][87426] Updated weights for policy 1, policy_version 180130 (0.0008) -[2023-11-28 04:56:14,465][87424] Updated weights for policy 0, policy_version 180607 (0.0012) -[2023-11-28 04:56:14,770][87426] Updated weights for policy 1, policy_version 180140 (0.0007) -[2023-11-28 04:56:15,152][87426] Updated weights for policy 1, policy_version 180150 (0.0009) -[2023-11-28 04:56:15,533][87426] Updated weights for policy 1, policy_version 180160 (0.0008) -[2023-11-28 04:56:16,250][87424] Updated weights for policy 0, policy_version 180617 (0.0012) -[2023-11-28 04:56:16,624][87424] Updated weights for policy 0, policy_version 180627 (0.0012) -[2023-11-28 04:56:17,016][87424] Updated weights for policy 0, policy_version 180637 (0.0012) -[2023-11-28 04:56:17,621][87426] Updated weights for policy 1, policy_version 180170 (0.0008) -[2023-11-28 04:56:17,998][87426] Updated weights for policy 1, policy_version 180180 (0.0007) -[2023-11-28 04:56:18,386][87426] Updated weights for policy 1, policy_version 180190 (0.0007) -[2023-11-28 04:56:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 92364800. Throughput: 0: 2670.2, 1: 2720.1. Samples: 92379780. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:56:18,445][86177] Avg episode reward: [(0, '-493.810'), (1, '-519.540')] -[2023-11-28 04:56:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000180192_46129152.pth... -[2023-11-28 04:56:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000180640_46243840.pth... -[2023-11-28 04:56:18,484][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000177632_45473792.pth -[2023-11-28 04:56:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000178112_45596672.pth -[2023-11-28 04:56:19,088][87424] Updated weights for policy 0, policy_version 180647 (0.0012) -[2023-11-28 04:56:19,478][87424] Updated weights for policy 0, policy_version 180657 (0.0012) -[2023-11-28 04:56:19,856][87424] Updated weights for policy 0, policy_version 180667 (0.0012) -[2023-11-28 04:56:20,807][87426] Updated weights for policy 1, policy_version 180200 (0.0009) -[2023-11-28 04:56:21,181][87426] Updated weights for policy 1, policy_version 180210 (0.0008) -[2023-11-28 04:56:21,564][87426] Updated weights for policy 1, policy_version 180220 (0.0009) -[2023-11-28 04:56:22,254][87424] Updated weights for policy 0, policy_version 180677 (0.0012) -[2023-11-28 04:56:22,636][87424] Updated weights for policy 0, policy_version 180687 (0.0010) -[2023-11-28 04:56:23,020][87424] Updated weights for policy 0, policy_version 180697 (0.0011) -[2023-11-28 04:56:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 92397568. Throughput: 0: 2662.6, 1: 2714.8. Samples: 92412020. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:56:23,445][86177] Avg episode reward: [(0, '-494.660'), (1, '-516.760')] -[2023-11-28 04:56:23,938][87426] Updated weights for policy 1, policy_version 180230 (0.0010) -[2023-11-28 04:56:24,319][87426] Updated weights for policy 1, policy_version 180240 (0.0012) -[2023-11-28 04:56:24,694][87426] Updated weights for policy 1, policy_version 180250 (0.0012) -[2023-11-28 04:56:25,592][87424] Updated weights for policy 0, policy_version 180707 (0.0011) -[2023-11-28 04:56:25,968][87424] Updated weights for policy 0, policy_version 180717 (0.0010) -[2023-11-28 04:56:26,348][87424] Updated weights for policy 0, policy_version 180727 (0.0012) -[2023-11-28 04:56:27,110][87426] Updated weights for policy 1, policy_version 180260 (0.0012) -[2023-11-28 04:56:27,490][87426] Updated weights for policy 1, policy_version 180270 (0.0012) -[2023-11-28 04:56:27,866][87426] Updated weights for policy 1, policy_version 180280 (0.0012) -[2023-11-28 04:56:28,338][87424] Updated weights for policy 0, policy_version 180737 (0.0011) -[2023-11-28 04:56:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92422144. Throughput: 0: 2668.9, 1: 2694.0. Samples: 92435588. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:56:28,446][86177] Avg episode reward: [(0, '-494.060'), (1, '-522.830')] -[2023-11-28 04:56:28,732][87424] Updated weights for policy 0, policy_version 180747 (0.0007) -[2023-11-28 04:56:29,121][87424] Updated weights for policy 0, policy_version 180757 (0.0007) -[2023-11-28 04:56:29,507][87424] Updated weights for policy 0, policy_version 180767 (0.0007) -[2023-11-28 04:56:30,324][87426] Updated weights for policy 1, policy_version 180290 (0.0010) -[2023-11-28 04:56:30,701][87426] Updated weights for policy 1, policy_version 180300 (0.0012) -[2023-11-28 04:56:31,078][87426] Updated weights for policy 1, policy_version 180310 (0.0011) -[2023-11-28 04:56:31,448][87426] Updated weights for policy 1, policy_version 180320 (0.0011) -[2023-11-28 04:56:31,782][87424] Updated weights for policy 0, policy_version 180777 (0.0011) -[2023-11-28 04:56:32,162][87424] Updated weights for policy 0, policy_version 180787 (0.0012) -[2023-11-28 04:56:32,555][87424] Updated weights for policy 0, policy_version 180797 (0.0012) -[2023-11-28 04:56:33,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 92446720. Throughput: 0: 2673.3, 1: 2674.6. Samples: 92459108. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:56:33,446][86177] Avg episode reward: [(0, '-495.860'), (1, '-529.980')] -[2023-11-28 04:56:33,802][87426] Updated weights for policy 1, policy_version 180330 (0.0012) -[2023-11-28 04:56:34,185][87426] Updated weights for policy 1, policy_version 180340 (0.0012) -[2023-11-28 04:56:34,425][87424] Updated weights for policy 0, policy_version 180807 (0.0012) -[2023-11-28 04:56:34,565][87426] Updated weights for policy 1, policy_version 180350 (0.0012) -[2023-11-28 04:56:34,812][87424] Updated weights for policy 0, policy_version 180817 (0.0011) -[2023-11-28 04:56:35,198][87424] Updated weights for policy 0, policy_version 180827 (0.0011) -[2023-11-28 04:56:36,371][87426] Updated weights for policy 1, policy_version 180360 (0.0012) -[2023-11-28 04:56:36,748][87426] Updated weights for policy 1, policy_version 180370 (0.0012) -[2023-11-28 04:56:37,126][87426] Updated weights for policy 1, policy_version 180380 (0.0012) -[2023-11-28 04:56:37,398][87424] Updated weights for policy 0, policy_version 180837 (0.0011) -[2023-11-28 04:56:37,779][87424] Updated weights for policy 0, policy_version 180847 (0.0010) -[2023-11-28 04:56:38,163][87424] Updated weights for policy 0, policy_version 180857 (0.0007) -[2023-11-28 04:56:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 92479488. Throughput: 0: 2685.8, 1: 2665.6. Samples: 92492020. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:56:38,445][86177] Avg episode reward: [(0, '-502.300'), (1, '-515.860')] -[2023-11-28 04:56:39,164][87426] Updated weights for policy 1, policy_version 180390 (0.0009) -[2023-11-28 04:56:39,555][87426] Updated weights for policy 1, policy_version 180400 (0.0011) -[2023-11-28 04:56:39,937][87426] Updated weights for policy 1, policy_version 180410 (0.0012) -[2023-11-28 04:56:40,111][87424] Updated weights for policy 0, policy_version 180867 (0.0009) -[2023-11-28 04:56:40,499][87424] Updated weights for policy 0, policy_version 180877 (0.0011) -[2023-11-28 04:56:40,877][87424] Updated weights for policy 0, policy_version 180887 (0.0011) -[2023-11-28 04:56:41,763][87426] Updated weights for policy 1, policy_version 180420 (0.0012) -[2023-11-28 04:56:42,141][87426] Updated weights for policy 1, policy_version 180430 (0.0012) -[2023-11-28 04:56:42,517][87426] Updated weights for policy 1, policy_version 180440 (0.0012) -[2023-11-28 04:56:43,035][87424] Updated weights for policy 0, policy_version 180897 (0.0010) -[2023-11-28 04:56:43,420][87424] Updated weights for policy 0, policy_version 180907 (0.0010) -[2023-11-28 04:56:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92504064. Throughput: 0: 2673.1, 1: 2674.2. Samples: 92515944. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:56:43,445][86177] Avg episode reward: [(0, '-582.660'), (1, '-512.870')] -[2023-11-28 04:56:43,797][87424] Updated weights for policy 0, policy_version 180917 (0.0012) -[2023-11-28 04:56:44,178][87424] Updated weights for policy 0, policy_version 180927 (0.0011) -[2023-11-28 04:56:45,093][87426] Updated weights for policy 1, policy_version 180450 (0.0011) -[2023-11-28 04:56:45,471][87426] Updated weights for policy 1, policy_version 180460 (0.0009) -[2023-11-28 04:56:45,845][87426] Updated weights for policy 1, policy_version 180470 (0.0011) -[2023-11-28 04:56:46,232][87426] Updated weights for policy 1, policy_version 180480 (0.0010) -[2023-11-28 04:56:46,630][87424] Updated weights for policy 0, policy_version 180937 (0.0008) -[2023-11-28 04:56:47,012][87424] Updated weights for policy 0, policy_version 180947 (0.0007) -[2023-11-28 04:56:47,393][87424] Updated weights for policy 0, policy_version 180957 (0.0008) -[2023-11-28 04:56:48,318][87426] Updated weights for policy 1, policy_version 180490 (0.0012) -[2023-11-28 04:56:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 92528640. Throughput: 0: 2659.4, 1: 2692.7. Samples: 92540572. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:56:48,445][86177] Avg episode reward: [(0, '-588.900'), (1, '-548.200')] -[2023-11-28 04:56:48,694][87426] Updated weights for policy 1, policy_version 180500 (0.0011) -[2023-11-28 04:56:49,075][87426] Updated weights for policy 1, policy_version 180510 (0.0010) -[2023-11-28 04:56:49,882][87424] Updated weights for policy 0, policy_version 180967 (0.0009) -[2023-11-28 04:56:50,270][87424] Updated weights for policy 0, policy_version 180977 (0.0008) -[2023-11-28 04:56:50,655][87424] Updated weights for policy 0, policy_version 180987 (0.0012) -[2023-11-28 04:56:51,321][87426] Updated weights for policy 1, policy_version 180520 (0.0008) -[2023-11-28 04:56:51,694][87426] Updated weights for policy 1, policy_version 180530 (0.0009) -[2023-11-28 04:56:52,070][87426] Updated weights for policy 1, policy_version 180540 (0.0012) -[2023-11-28 04:56:53,134][87424] Updated weights for policy 0, policy_version 180997 (0.0012) -[2023-11-28 04:56:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92553216. Throughput: 0: 2656.5, 1: 2684.8. Samples: 92571852. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:56:53,445][86177] Avg episode reward: [(0, '-610.730'), (1, '-531.730')] -[2023-11-28 04:56:53,513][87424] Updated weights for policy 0, policy_version 181007 (0.0010) -[2023-11-28 04:56:53,903][87424] Updated weights for policy 0, policy_version 181017 (0.0010) -[2023-11-28 04:56:54,419][87426] Updated weights for policy 1, policy_version 180550 (0.0009) -[2023-11-28 04:56:54,796][87426] Updated weights for policy 1, policy_version 180560 (0.0008) -[2023-11-28 04:56:55,173][87426] Updated weights for policy 1, policy_version 180570 (0.0007) -[2023-11-28 04:56:56,479][87424] Updated weights for policy 0, policy_version 181027 (0.0011) -[2023-11-28 04:56:56,851][87424] Updated weights for policy 0, policy_version 181037 (0.0010) -[2023-11-28 04:56:57,218][87426] Updated weights for policy 1, policy_version 180580 (0.0009) -[2023-11-28 04:56:57,235][87424] Updated weights for policy 0, policy_version 181047 (0.0012) -[2023-11-28 04:56:57,596][87426] Updated weights for policy 1, policy_version 180590 (0.0011) -[2023-11-28 04:56:57,976][87426] Updated weights for policy 1, policy_version 180600 (0.0012) -[2023-11-28 04:56:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 92585984. Throughput: 0: 2662.0, 1: 2702.8. Samples: 92596600. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:56:58,446][86177] Avg episode reward: [(0, '-603.580'), (1, '-531.970')] -[2023-11-28 04:56:59,113][87424] Updated weights for policy 0, policy_version 181057 (0.0009) -[2023-11-28 04:56:59,500][87424] Updated weights for policy 0, policy_version 181067 (0.0009) -[2023-11-28 04:56:59,723][87426] Updated weights for policy 1, policy_version 180610 (0.0012) -[2023-11-28 04:56:59,885][87424] Updated weights for policy 0, policy_version 181077 (0.0011) -[2023-11-28 04:57:00,096][87426] Updated weights for policy 1, policy_version 180620 (0.0012) -[2023-11-28 04:57:00,267][87424] Updated weights for policy 0, policy_version 181087 (0.0011) -[2023-11-28 04:57:00,480][87426] Updated weights for policy 1, policy_version 180630 (0.0012) -[2023-11-28 04:57:00,863][87426] Updated weights for policy 1, policy_version 180640 (0.0012) -[2023-11-28 04:57:02,438][87424] Updated weights for policy 0, policy_version 181097 (0.0009) -[2023-11-28 04:57:02,828][87424] Updated weights for policy 0, policy_version 181107 (0.0008) -[2023-11-28 04:57:03,200][87424] Updated weights for policy 0, policy_version 181117 (0.0008) -[2023-11-28 04:57:03,330][87426] Updated weights for policy 1, policy_version 180650 (0.0011) -[2023-11-28 04:57:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 92610560. Throughput: 0: 2667.6, 1: 2710.1. Samples: 92621780. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:57:03,445][86177] Avg episode reward: [(0, '-521.550'), (1, '-546.670')] -[2023-11-28 04:57:03,703][87426] Updated weights for policy 1, policy_version 180660 (0.0011) -[2023-11-28 04:57:04,078][87426] Updated weights for policy 1, policy_version 180670 (0.0011) -[2023-11-28 04:57:05,303][87424] Updated weights for policy 0, policy_version 181127 (0.0009) -[2023-11-28 04:57:05,689][87424] Updated weights for policy 0, policy_version 181137 (0.0007) -[2023-11-28 04:57:06,080][87424] Updated weights for policy 0, policy_version 181147 (0.0008) -[2023-11-28 04:57:06,682][87426] Updated weights for policy 1, policy_version 180680 (0.0008) -[2023-11-28 04:57:07,060][87426] Updated weights for policy 1, policy_version 180690 (0.0011) -[2023-11-28 04:57:07,440][87426] Updated weights for policy 1, policy_version 180700 (0.0011) -[2023-11-28 04:57:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92635136. Throughput: 0: 2646.9, 1: 2714.4. Samples: 92653280. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:57:08,445][86177] Avg episode reward: [(0, '-519.910'), (1, '-539.470')] -[2023-11-28 04:57:08,449][87424] Updated weights for policy 0, policy_version 181157 (0.0009) -[2023-11-28 04:57:08,825][87424] Updated weights for policy 0, policy_version 181167 (0.0007) -[2023-11-28 04:57:09,214][87424] Updated weights for policy 0, policy_version 181177 (0.0008) -[2023-11-28 04:57:09,991][87426] Updated weights for policy 1, policy_version 180710 (0.0009) -[2023-11-28 04:57:10,374][87426] Updated weights for policy 1, policy_version 180720 (0.0010) -[2023-11-28 04:57:10,759][87426] Updated weights for policy 1, policy_version 180730 (0.0008) -[2023-11-28 04:57:11,172][87424] Updated weights for policy 0, policy_version 181187 (0.0009) -[2023-11-28 04:57:11,556][87424] Updated weights for policy 0, policy_version 181197 (0.0007) -[2023-11-28 04:57:11,948][87424] Updated weights for policy 0, policy_version 181207 (0.0009) -[2023-11-28 04:57:13,160][87426] Updated weights for policy 1, policy_version 180740 (0.0009) -[2023-11-28 04:57:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 92659712. Throughput: 0: 2652.9, 1: 2702.3. Samples: 92676572. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:57:13,445][86177] Avg episode reward: [(0, '-496.080'), (1, '-541.300')] -[2023-11-28 04:57:13,541][87426] Updated weights for policy 1, policy_version 180750 (0.0011) -[2023-11-28 04:57:13,906][87426] Updated weights for policy 1, policy_version 180760 (0.0010) -[2023-11-28 04:57:14,354][87424] Updated weights for policy 0, policy_version 181217 (0.0009) -[2023-11-28 04:57:14,739][87424] Updated weights for policy 0, policy_version 181227 (0.0008) -[2023-11-28 04:57:15,125][87424] Updated weights for policy 0, policy_version 181237 (0.0007) -[2023-11-28 04:57:15,518][87424] Updated weights for policy 0, policy_version 181247 (0.0010) -[2023-11-28 04:57:15,692][87426] Updated weights for policy 1, policy_version 180770 (0.0007) -[2023-11-28 04:57:16,074][87426] Updated weights for policy 1, policy_version 180780 (0.0008) -[2023-11-28 04:57:16,459][87426] Updated weights for policy 1, policy_version 180790 (0.0011) -[2023-11-28 04:57:16,842][87426] Updated weights for policy 1, policy_version 180800 (0.0012) -[2023-11-28 04:57:17,967][87424] Updated weights for policy 0, policy_version 181257 (0.0011) -[2023-11-28 04:57:18,350][87424] Updated weights for policy 0, policy_version 181267 (0.0007) -[2023-11-28 04:57:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 92684288. Throughput: 0: 2641.6, 1: 2711.1. Samples: 92699980. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:57:18,445][86177] Avg episode reward: [(0, '-497.420'), (1, '-531.120')] -[2023-11-28 04:57:18,718][87426] Updated weights for policy 1, policy_version 180810 (0.0012) -[2023-11-28 04:57:18,723][87424] Updated weights for policy 0, policy_version 181277 (0.0009) -[2023-11-28 04:57:19,094][87426] Updated weights for policy 1, policy_version 180820 (0.0012) -[2023-11-28 04:57:19,472][87426] Updated weights for policy 1, policy_version 180830 (0.0012) -[2023-11-28 04:57:21,166][87426] Updated weights for policy 1, policy_version 180840 (0.0009) -[2023-11-28 04:57:21,275][87424] Updated weights for policy 0, policy_version 181287 (0.0010) -[2023-11-28 04:57:21,554][87426] Updated weights for policy 1, policy_version 180850 (0.0009) -[2023-11-28 04:57:21,656][87424] Updated weights for policy 0, policy_version 181297 (0.0011) -[2023-11-28 04:57:21,925][87426] Updated weights for policy 1, policy_version 180860 (0.0011) -[2023-11-28 04:57:22,040][87424] Updated weights for policy 0, policy_version 181307 (0.0012) -[2023-11-28 04:57:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 92717056. Throughput: 0: 2618.8, 1: 2703.6. Samples: 92731528. Policy #0 lag: (min: 19.0, avg: 40.4, max: 50.0) -[2023-11-28 04:57:23,445][86177] Avg episode reward: [(0, '-495.790'), (1, '-534.950')] -[2023-11-28 04:57:24,131][87424] Updated weights for policy 0, policy_version 181317 (0.0009) -[2023-11-28 04:57:24,242][87426] Updated weights for policy 1, policy_version 180870 (0.0010) -[2023-11-28 04:57:24,508][87424] Updated weights for policy 0, policy_version 181327 (0.0007) -[2023-11-28 04:57:24,629][87426] Updated weights for policy 1, policy_version 180880 (0.0008) -[2023-11-28 04:57:24,898][87424] Updated weights for policy 0, policy_version 181337 (0.0008) -[2023-11-28 04:57:25,010][87426] Updated weights for policy 1, policy_version 180890 (0.0007) -[2023-11-28 04:57:27,286][87424] Updated weights for policy 0, policy_version 181347 (0.0011) -[2023-11-28 04:57:27,526][87426] Updated weights for policy 1, policy_version 180900 (0.0008) -[2023-11-28 04:57:27,669][87424] Updated weights for policy 0, policy_version 181357 (0.0011) -[2023-11-28 04:57:27,905][87426] Updated weights for policy 1, policy_version 180910 (0.0008) -[2023-11-28 04:57:28,049][87424] Updated weights for policy 0, policy_version 181367 (0.0009) -[2023-11-28 04:57:28,290][87426] Updated weights for policy 1, policy_version 180920 (0.0008) -[2023-11-28 04:57:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 92741632. Throughput: 0: 2612.3, 1: 2706.4. Samples: 92755284. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:57:28,445][86177] Avg episode reward: [(0, '-494.690'), (1, '-508.900')] -[2023-11-28 04:57:30,320][87424] Updated weights for policy 0, policy_version 181377 (0.0008) -[2023-11-28 04:57:30,703][87424] Updated weights for policy 0, policy_version 181387 (0.0008) -[2023-11-28 04:57:30,857][87426] Updated weights for policy 1, policy_version 180930 (0.0009) -[2023-11-28 04:57:31,084][87424] Updated weights for policy 0, policy_version 181397 (0.0010) -[2023-11-28 04:57:31,236][87426] Updated weights for policy 1, policy_version 180940 (0.0012) -[2023-11-28 04:57:31,460][87424] Updated weights for policy 0, policy_version 181407 (0.0008) -[2023-11-28 04:57:31,606][87426] Updated weights for policy 1, policy_version 180950 (0.0011) -[2023-11-28 04:57:31,988][87426] Updated weights for policy 1, policy_version 180960 (0.0012) -[2023-11-28 04:57:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 92766208. Throughput: 0: 2609.5, 1: 2674.3. Samples: 92778344. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:57:33,445][86177] Avg episode reward: [(0, '-497.800'), (1, '-514.980')] -[2023-11-28 04:57:33,611][87424] Updated weights for policy 0, policy_version 181417 (0.0011) -[2023-11-28 04:57:33,989][87424] Updated weights for policy 0, policy_version 181427 (0.0012) -[2023-11-28 04:57:34,220][87426] Updated weights for policy 1, policy_version 180970 (0.0007) -[2023-11-28 04:57:34,375][87424] Updated weights for policy 0, policy_version 181437 (0.0011) -[2023-11-28 04:57:34,600][87426] Updated weights for policy 1, policy_version 180980 (0.0009) -[2023-11-28 04:57:34,980][87426] Updated weights for policy 1, policy_version 180990 (0.0008) -[2023-11-28 04:57:36,300][87424] Updated weights for policy 0, policy_version 181447 (0.0009) -[2023-11-28 04:57:36,686][87424] Updated weights for policy 0, policy_version 181457 (0.0008) -[2023-11-28 04:57:36,945][87426] Updated weights for policy 1, policy_version 181000 (0.0010) -[2023-11-28 04:57:37,076][87424] Updated weights for policy 0, policy_version 181467 (0.0008) -[2023-11-28 04:57:37,324][87426] Updated weights for policy 1, policy_version 181010 (0.0012) -[2023-11-28 04:57:37,707][87426] Updated weights for policy 1, policy_version 181020 (0.0012) -[2023-11-28 04:57:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92798976. Throughput: 0: 2627.2, 1: 2678.3. Samples: 92810600. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:57:38,446][86177] Avg episode reward: [(0, '-500.720'), (1, '-518.280')] -[2023-11-28 04:57:39,094][87424] Updated weights for policy 0, policy_version 181477 (0.0012) -[2023-11-28 04:57:39,481][87424] Updated weights for policy 0, policy_version 181487 (0.0011) -[2023-11-28 04:57:39,866][87424] Updated weights for policy 0, policy_version 181497 (0.0008) -[2023-11-28 04:57:40,160][87426] Updated weights for policy 1, policy_version 181030 (0.0009) -[2023-11-28 04:57:40,544][87426] Updated weights for policy 1, policy_version 181040 (0.0008) -[2023-11-28 04:57:40,921][87426] Updated weights for policy 1, policy_version 181050 (0.0009) -[2023-11-28 04:57:42,247][87424] Updated weights for policy 0, policy_version 181507 (0.0012) -[2023-11-28 04:57:42,622][87424] Updated weights for policy 0, policy_version 181517 (0.0008) -[2023-11-28 04:57:43,007][87424] Updated weights for policy 0, policy_version 181527 (0.0009) -[2023-11-28 04:57:43,018][87426] Updated weights for policy 1, policy_version 181060 (0.0009) -[2023-11-28 04:57:43,385][87426] Updated weights for policy 1, policy_version 181070 (0.0011) -[2023-11-28 04:57:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 92823552. Throughput: 0: 2650.9, 1: 2662.5. Samples: 92835704. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:57:43,445][86177] Avg episode reward: [(0, '-501.910'), (1, '-523.190')] -[2023-11-28 04:57:43,764][87426] Updated weights for policy 1, policy_version 181080 (0.0011) -[2023-11-28 04:57:45,006][87424] Updated weights for policy 0, policy_version 181537 (0.0010) -[2023-11-28 04:57:45,397][87424] Updated weights for policy 0, policy_version 181547 (0.0011) -[2023-11-28 04:57:45,760][87426] Updated weights for policy 1, policy_version 181090 (0.0011) -[2023-11-28 04:57:45,773][87424] Updated weights for policy 0, policy_version 181557 (0.0008) -[2023-11-28 04:57:46,136][87426] Updated weights for policy 1, policy_version 181100 (0.0011) -[2023-11-28 04:57:46,154][87424] Updated weights for policy 0, policy_version 181567 (0.0010) -[2023-11-28 04:57:46,519][87426] Updated weights for policy 1, policy_version 181110 (0.0011) -[2023-11-28 04:57:46,891][87426] Updated weights for policy 1, policy_version 181120 (0.0011) -[2023-11-28 04:57:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 92848128. Throughput: 0: 2649.2, 1: 2654.8. Samples: 92860460. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:57:48,445][86177] Avg episode reward: [(0, '-502.360'), (1, '-563.430')] -[2023-11-28 04:57:48,458][87424] Updated weights for policy 0, policy_version 181577 (0.0012) -[2023-11-28 04:57:48,839][87424] Updated weights for policy 0, policy_version 181587 (0.0011) -[2023-11-28 04:57:49,066][87426] Updated weights for policy 1, policy_version 181130 (0.0012) -[2023-11-28 04:57:49,223][87424] Updated weights for policy 0, policy_version 181597 (0.0011) -[2023-11-28 04:57:49,444][87426] Updated weights for policy 1, policy_version 181140 (0.0012) -[2023-11-28 04:57:49,818][87426] Updated weights for policy 1, policy_version 181150 (0.0012) -[2023-11-28 04:57:51,788][87424] Updated weights for policy 0, policy_version 181607 (0.0011) -[2023-11-28 04:57:52,169][87424] Updated weights for policy 0, policy_version 181617 (0.0009) -[2023-11-28 04:57:52,210][87426] Updated weights for policy 1, policy_version 181160 (0.0010) -[2023-11-28 04:57:52,552][87424] Updated weights for policy 0, policy_version 181627 (0.0008) -[2023-11-28 04:57:52,589][87426] Updated weights for policy 1, policy_version 181170 (0.0008) -[2023-11-28 04:57:52,970][87426] Updated weights for policy 1, policy_version 181180 (0.0011) -[2023-11-28 04:57:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 92880896. Throughput: 0: 2664.6, 1: 2653.5. Samples: 92892596. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:57:53,445][86177] Avg episode reward: [(0, '-500.950'), (1, '-566.190')] -[2023-11-28 04:57:54,564][87424] Updated weights for policy 0, policy_version 181637 (0.0010) -[2023-11-28 04:57:54,945][87424] Updated weights for policy 0, policy_version 181647 (0.0012) -[2023-11-28 04:57:55,039][87426] Updated weights for policy 1, policy_version 181190 (0.0009) -[2023-11-28 04:57:55,334][87424] Updated weights for policy 0, policy_version 181657 (0.0011) -[2023-11-28 04:57:55,424][87426] Updated weights for policy 1, policy_version 181200 (0.0013) -[2023-11-28 04:57:55,805][87426] Updated weights for policy 1, policy_version 181210 (0.0011) -[2023-11-28 04:57:57,297][87424] Updated weights for policy 0, policy_version 181667 (0.0010) -[2023-11-28 04:57:57,673][87424] Updated weights for policy 0, policy_version 181677 (0.0012) -[2023-11-28 04:57:58,069][87424] Updated weights for policy 0, policy_version 181687 (0.0011) -[2023-11-28 04:57:58,195][87426] Updated weights for policy 1, policy_version 181220 (0.0011) -[2023-11-28 04:57:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 92905472. Throughput: 0: 2661.1, 1: 2708.7. Samples: 92918216. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:57:58,445][86177] Avg episode reward: [(0, '-543.590'), (1, '-567.300')] -[2023-11-28 04:57:58,573][87426] Updated weights for policy 1, policy_version 181230 (0.0008) -[2023-11-28 04:57:58,967][87426] Updated weights for policy 1, policy_version 181240 (0.0008) -[2023-11-28 04:58:00,217][87424] Updated weights for policy 0, policy_version 181697 (0.0011) -[2023-11-28 04:58:00,605][87424] Updated weights for policy 0, policy_version 181707 (0.0010) -[2023-11-28 04:58:00,836][87426] Updated weights for policy 1, policy_version 181250 (0.0011) -[2023-11-28 04:58:00,988][87424] Updated weights for policy 0, policy_version 181717 (0.0012) -[2023-11-28 04:58:01,211][87426] Updated weights for policy 1, policy_version 181260 (0.0011) -[2023-11-28 04:58:01,376][87424] Updated weights for policy 0, policy_version 181727 (0.0011) -[2023-11-28 04:58:01,582][87426] Updated weights for policy 1, policy_version 181270 (0.0011) -[2023-11-28 04:58:01,959][87426] Updated weights for policy 1, policy_version 181280 (0.0012) -[2023-11-28 04:58:03,200][87424] Updated weights for policy 0, policy_version 181737 (0.0008) -[2023-11-28 04:58:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 92930048. Throughput: 0: 2694.8, 1: 2731.3. Samples: 92944156. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:58:03,446][86177] Avg episode reward: [(0, '-542.340'), (1, '-581.940')] -[2023-11-28 04:58:03,584][87424] Updated weights for policy 0, policy_version 181747 (0.0007) -[2023-11-28 04:58:03,964][87424] Updated weights for policy 0, policy_version 181757 (0.0007) -[2023-11-28 04:58:04,151][87426] Updated weights for policy 1, policy_version 181290 (0.0011) -[2023-11-28 04:58:04,527][87426] Updated weights for policy 1, policy_version 181300 (0.0009) -[2023-11-28 04:58:04,895][87426] Updated weights for policy 1, policy_version 181310 (0.0010) -[2023-11-28 04:58:06,268][87424] Updated weights for policy 0, policy_version 181767 (0.0011) -[2023-11-28 04:58:06,650][87424] Updated weights for policy 0, policy_version 181777 (0.0010) -[2023-11-28 04:58:07,034][87424] Updated weights for policy 0, policy_version 181787 (0.0009) -[2023-11-28 04:58:07,405][87426] Updated weights for policy 1, policy_version 181320 (0.0008) -[2023-11-28 04:58:07,779][87426] Updated weights for policy 1, policy_version 181330 (0.0011) -[2023-11-28 04:58:08,158][87426] Updated weights for policy 1, policy_version 181340 (0.0011) -[2023-11-28 04:58:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 92962816. Throughput: 0: 2735.8, 1: 2733.9. Samples: 92977664. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:58:08,445][86177] Avg episode reward: [(0, '-542.910'), (1, '-542.540')] -[2023-11-28 04:58:09,547][87424] Updated weights for policy 0, policy_version 181797 (0.0010) -[2023-11-28 04:58:09,937][87424] Updated weights for policy 0, policy_version 181807 (0.0011) -[2023-11-28 04:58:10,319][87424] Updated weights for policy 0, policy_version 181817 (0.0011) -[2023-11-28 04:58:10,332][87426] Updated weights for policy 1, policy_version 181350 (0.0012) -[2023-11-28 04:58:10,710][87426] Updated weights for policy 1, policy_version 181360 (0.0009) -[2023-11-28 04:58:11,090][87426] Updated weights for policy 1, policy_version 181370 (0.0010) -[2023-11-28 04:58:12,505][87424] Updated weights for policy 0, policy_version 181827 (0.0011) -[2023-11-28 04:58:12,889][87424] Updated weights for policy 0, policy_version 181837 (0.0010) -[2023-11-28 04:58:13,269][87424] Updated weights for policy 0, policy_version 181847 (0.0012) -[2023-11-28 04:58:13,405][87426] Updated weights for policy 1, policy_version 181380 (0.0011) -[2023-11-28 04:58:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 92979200. Throughput: 0: 2748.1, 1: 2750.7. Samples: 93002728. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:58:13,445][86177] Avg episode reward: [(0, '-501.940'), (1, '-534.590')] -[2023-11-28 04:58:13,784][87426] Updated weights for policy 1, policy_version 181390 (0.0010) -[2023-11-28 04:58:14,176][87426] Updated weights for policy 1, policy_version 181400 (0.0012) -[2023-11-28 04:58:15,061][87424] Updated weights for policy 0, policy_version 181857 (0.0011) -[2023-11-28 04:58:15,443][87424] Updated weights for policy 0, policy_version 181867 (0.0008) -[2023-11-28 04:58:15,826][87424] Updated weights for policy 0, policy_version 181877 (0.0008) -[2023-11-28 04:58:16,211][87424] Updated weights for policy 0, policy_version 181887 (0.0007) -[2023-11-28 04:58:16,756][87426] Updated weights for policy 1, policy_version 181410 (0.0011) -[2023-11-28 04:58:17,131][87426] Updated weights for policy 1, policy_version 181420 (0.0007) -[2023-11-28 04:58:17,511][87426] Updated weights for policy 1, policy_version 181430 (0.0008) -[2023-11-28 04:58:17,890][87426] Updated weights for policy 1, policy_version 181440 (0.0008) -[2023-11-28 04:58:18,020][87424] Updated weights for policy 0, policy_version 181897 (0.0008) -[2023-11-28 04:58:18,405][87424] Updated weights for policy 0, policy_version 181907 (0.0007) -[2023-11-28 04:58:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93011968. Throughput: 0: 2766.2, 1: 2748.9. Samples: 93026524. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:58:18,445][86177] Avg episode reward: [(0, '-499.380'), (1, '-544.620')] -[2023-11-28 04:58:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000181440_46448640.pth... -[2023-11-28 04:58:18,487][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000178912_45801472.pth -[2023-11-28 04:58:18,777][87424] Updated weights for policy 0, policy_version 181917 (0.0008) -[2023-11-28 04:58:18,891][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000181920_46571520.pth... -[2023-11-28 04:58:18,923][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000179392_45924352.pth -[2023-11-28 04:58:20,416][87426] Updated weights for policy 1, policy_version 181450 (0.0012) -[2023-11-28 04:58:20,788][87426] Updated weights for policy 1, policy_version 181460 (0.0011) -[2023-11-28 04:58:21,163][87426] Updated weights for policy 1, policy_version 181470 (0.0010) -[2023-11-28 04:58:21,256][87424] Updated weights for policy 0, policy_version 181927 (0.0011) -[2023-11-28 04:58:21,634][87424] Updated weights for policy 0, policy_version 181937 (0.0011) -[2023-11-28 04:58:22,020][87424] Updated weights for policy 0, policy_version 181947 (0.0010) -[2023-11-28 04:58:23,202][87426] Updated weights for policy 1, policy_version 181480 (0.0011) -[2023-11-28 04:58:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 93036544. Throughput: 0: 2769.2, 1: 2732.0. Samples: 93058152. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:58:23,445][86177] Avg episode reward: [(0, '-496.980'), (1, '-544.130')] -[2023-11-28 04:58:23,586][87426] Updated weights for policy 1, policy_version 181490 (0.0012) -[2023-11-28 04:58:23,970][87426] Updated weights for policy 1, policy_version 181500 (0.0009) -[2023-11-28 04:58:24,048][87424] Updated weights for policy 0, policy_version 181957 (0.0012) -[2023-11-28 04:58:24,420][87424] Updated weights for policy 0, policy_version 181967 (0.0009) -[2023-11-28 04:58:24,807][87424] Updated weights for policy 0, policy_version 181977 (0.0008) -[2023-11-28 04:58:25,913][87426] Updated weights for policy 1, policy_version 181510 (0.0009) -[2023-11-28 04:58:26,288][87426] Updated weights for policy 1, policy_version 181520 (0.0007) -[2023-11-28 04:58:26,672][87426] Updated weights for policy 1, policy_version 181530 (0.0007) -[2023-11-28 04:58:27,253][87424] Updated weights for policy 0, policy_version 181987 (0.0008) -[2023-11-28 04:58:27,640][87424] Updated weights for policy 0, policy_version 181997 (0.0008) -[2023-11-28 04:58:28,025][87424] Updated weights for policy 0, policy_version 182007 (0.0009) -[2023-11-28 04:58:28,214][87426] Updated weights for policy 1, policy_version 181540 (0.0007) -[2023-11-28 04:58:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93069312. Throughput: 0: 2746.1, 1: 2736.6. Samples: 93082428. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:58:28,446][86177] Avg episode reward: [(0, '-498.000'), (1, '-533.720')] -[2023-11-28 04:58:28,595][87426] Updated weights for policy 1, policy_version 181550 (0.0012) -[2023-11-28 04:58:28,978][87426] Updated weights for policy 1, policy_version 181560 (0.0012) -[2023-11-28 04:58:30,561][87424] Updated weights for policy 0, policy_version 182017 (0.0008) -[2023-11-28 04:58:30,931][87424] Updated weights for policy 0, policy_version 182027 (0.0009) -[2023-11-28 04:58:31,040][87426] Updated weights for policy 1, policy_version 181570 (0.0012) -[2023-11-28 04:58:31,312][87424] Updated weights for policy 0, policy_version 182037 (0.0010) -[2023-11-28 04:58:31,421][87426] Updated weights for policy 1, policy_version 181580 (0.0011) -[2023-11-28 04:58:31,702][87424] Updated weights for policy 0, policy_version 182047 (0.0010) -[2023-11-28 04:58:31,813][87426] Updated weights for policy 1, policy_version 181590 (0.0011) -[2023-11-28 04:58:32,183][87426] Updated weights for policy 1, policy_version 181600 (0.0010) -[2023-11-28 04:58:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93093888. Throughput: 0: 2730.5, 1: 2720.0. Samples: 93105732. Policy #0 lag: (min: 31.0, avg: 34.3, max: 59.0) -[2023-11-28 04:58:33,446][86177] Avg episode reward: [(0, '-497.390'), (1, '-550.230')] -[2023-11-28 04:58:33,653][87424] Updated weights for policy 0, policy_version 182057 (0.0012) -[2023-11-28 04:58:34,022][87424] Updated weights for policy 0, policy_version 182067 (0.0012) -[2023-11-28 04:58:34,137][87426] Updated weights for policy 1, policy_version 181610 (0.0011) -[2023-11-28 04:58:34,407][87424] Updated weights for policy 0, policy_version 182077 (0.0012) -[2023-11-28 04:58:34,515][87426] Updated weights for policy 1, policy_version 181620 (0.0011) -[2023-11-28 04:58:34,900][87426] Updated weights for policy 1, policy_version 181630 (0.0009) -[2023-11-28 04:58:36,447][87424] Updated weights for policy 0, policy_version 182087 (0.0009) -[2023-11-28 04:58:36,827][87424] Updated weights for policy 0, policy_version 182097 (0.0010) -[2023-11-28 04:58:37,141][87426] Updated weights for policy 1, policy_version 181640 (0.0009) -[2023-11-28 04:58:37,210][87424] Updated weights for policy 0, policy_version 182107 (0.0010) -[2023-11-28 04:58:37,521][87426] Updated weights for policy 1, policy_version 181650 (0.0011) -[2023-11-28 04:58:37,890][87426] Updated weights for policy 1, policy_version 181660 (0.0011) -[2023-11-28 04:58:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 93126656. Throughput: 0: 2755.1, 1: 2727.6. Samples: 93139316. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:58:38,445][86177] Avg episode reward: [(0, '-498.340'), (1, '-570.060')] -[2023-11-28 04:58:39,504][87424] Updated weights for policy 0, policy_version 182117 (0.0009) -[2023-11-28 04:58:39,839][87426] Updated weights for policy 1, policy_version 181670 (0.0011) -[2023-11-28 04:58:39,892][87424] Updated weights for policy 0, policy_version 182127 (0.0012) -[2023-11-28 04:58:40,225][87426] Updated weights for policy 1, policy_version 181680 (0.0011) -[2023-11-28 04:58:40,269][87424] Updated weights for policy 0, policy_version 182137 (0.0012) -[2023-11-28 04:58:40,607][87426] Updated weights for policy 1, policy_version 181690 (0.0011) -[2023-11-28 04:58:42,337][87424] Updated weights for policy 0, policy_version 182147 (0.0011) -[2023-11-28 04:58:42,728][87424] Updated weights for policy 0, policy_version 182157 (0.0011) -[2023-11-28 04:58:42,814][87426] Updated weights for policy 1, policy_version 181700 (0.0011) -[2023-11-28 04:58:43,116][87424] Updated weights for policy 0, policy_version 182167 (0.0011) -[2023-11-28 04:58:43,196][87426] Updated weights for policy 1, policy_version 181710 (0.0011) -[2023-11-28 04:58:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 93143040. Throughput: 0: 2742.9, 1: 2712.5. Samples: 93163708. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:58:43,445][86177] Avg episode reward: [(0, '-498.510'), (1, '-587.570')] -[2023-11-28 04:58:43,575][87426] Updated weights for policy 1, policy_version 181720 (0.0009) -[2023-11-28 04:58:44,944][87424] Updated weights for policy 0, policy_version 182177 (0.0012) -[2023-11-28 04:58:45,329][87424] Updated weights for policy 0, policy_version 182187 (0.0012) -[2023-11-28 04:58:45,715][87424] Updated weights for policy 0, policy_version 182197 (0.0009) -[2023-11-28 04:58:45,795][87426] Updated weights for policy 1, policy_version 181730 (0.0008) -[2023-11-28 04:58:46,096][87424] Updated weights for policy 0, policy_version 182207 (0.0008) -[2023-11-28 04:58:46,169][87426] Updated weights for policy 1, policy_version 181740 (0.0011) -[2023-11-28 04:58:46,542][87426] Updated weights for policy 1, policy_version 181750 (0.0009) -[2023-11-28 04:58:46,929][87426] Updated weights for policy 1, policy_version 181760 (0.0008) -[2023-11-28 04:58:47,934][87424] Updated weights for policy 0, policy_version 182217 (0.0008) -[2023-11-28 04:58:48,321][87424] Updated weights for policy 0, policy_version 182227 (0.0007) -[2023-11-28 04:58:48,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93175808. Throughput: 0: 2747.3, 1: 2689.9. Samples: 93188832. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:58:48,446][86177] Avg episode reward: [(0, '-517.770'), (1, '-574.760')] -[2023-11-28 04:58:48,700][87424] Updated weights for policy 0, policy_version 182237 (0.0008) -[2023-11-28 04:58:49,307][87426] Updated weights for policy 1, policy_version 181770 (0.0007) -[2023-11-28 04:58:49,689][87426] Updated weights for policy 1, policy_version 181780 (0.0008) -[2023-11-28 04:58:50,073][87426] Updated weights for policy 1, policy_version 181790 (0.0011) -[2023-11-28 04:58:51,134][87424] Updated weights for policy 0, policy_version 182247 (0.0009) -[2023-11-28 04:58:51,533][87424] Updated weights for policy 0, policy_version 182257 (0.0012) -[2023-11-28 04:58:51,913][87424] Updated weights for policy 0, policy_version 182267 (0.0012) -[2023-11-28 04:58:52,364][87426] Updated weights for policy 1, policy_version 181800 (0.0012) -[2023-11-28 04:58:52,741][87426] Updated weights for policy 1, policy_version 181810 (0.0012) -[2023-11-28 04:58:53,119][87426] Updated weights for policy 1, policy_version 181820 (0.0012) -[2023-11-28 04:58:53,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 93208576. Throughput: 0: 2724.0, 1: 2682.1. Samples: 93220940. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:58:53,445][86177] Avg episode reward: [(0, '-527.940'), (1, '-561.250')] -[2023-11-28 04:58:54,050][87424] Updated weights for policy 0, policy_version 182277 (0.0011) -[2023-11-28 04:58:54,440][87424] Updated weights for policy 0, policy_version 182287 (0.0012) -[2023-11-28 04:58:54,825][87424] Updated weights for policy 0, policy_version 182297 (0.0012) -[2023-11-28 04:58:55,151][87426] Updated weights for policy 1, policy_version 181830 (0.0011) -[2023-11-28 04:58:55,522][87426] Updated weights for policy 1, policy_version 181840 (0.0011) -[2023-11-28 04:58:55,898][87426] Updated weights for policy 1, policy_version 181850 (0.0010) -[2023-11-28 04:58:56,710][87424] Updated weights for policy 0, policy_version 182307 (0.0012) -[2023-11-28 04:58:57,093][87424] Updated weights for policy 0, policy_version 182317 (0.0011) -[2023-11-28 04:58:57,473][87424] Updated weights for policy 0, policy_version 182327 (0.0011) -[2023-11-28 04:58:58,243][87426] Updated weights for policy 1, policy_version 181860 (0.0009) -[2023-11-28 04:58:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93233152. Throughput: 0: 2718.0, 1: 2698.7. Samples: 93246476. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:58:58,445][86177] Avg episode reward: [(0, '-530.410'), (1, '-537.760')] -[2023-11-28 04:58:58,623][87426] Updated weights for policy 1, policy_version 181870 (0.0008) -[2023-11-28 04:58:58,991][87426] Updated weights for policy 1, policy_version 181880 (0.0008) -[2023-11-28 04:58:59,918][87424] Updated weights for policy 0, policy_version 182337 (0.0008) -[2023-11-28 04:59:00,299][87424] Updated weights for policy 0, policy_version 182347 (0.0007) -[2023-11-28 04:59:00,682][87424] Updated weights for policy 0, policy_version 182357 (0.0008) -[2023-11-28 04:59:01,067][87424] Updated weights for policy 0, policy_version 182367 (0.0007) -[2023-11-28 04:59:01,245][87426] Updated weights for policy 1, policy_version 181890 (0.0010) -[2023-11-28 04:59:01,627][87426] Updated weights for policy 1, policy_version 181900 (0.0008) -[2023-11-28 04:59:02,003][87426] Updated weights for policy 1, policy_version 181910 (0.0008) -[2023-11-28 04:59:02,381][87426] Updated weights for policy 1, policy_version 181920 (0.0008) -[2023-11-28 04:59:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93257728. Throughput: 0: 2725.5, 1: 2703.6. Samples: 93270832. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:59:03,445][86177] Avg episode reward: [(0, '-528.160'), (1, '-533.260')] -[2023-11-28 04:59:03,565][87424] Updated weights for policy 0, policy_version 182377 (0.0010) -[2023-11-28 04:59:03,947][87424] Updated weights for policy 0, policy_version 182387 (0.0008) -[2023-11-28 04:59:04,329][87424] Updated weights for policy 0, policy_version 182397 (0.0007) -[2023-11-28 04:59:04,525][87426] Updated weights for policy 1, policy_version 181930 (0.0010) -[2023-11-28 04:59:04,899][87426] Updated weights for policy 1, policy_version 181940 (0.0009) -[2023-11-28 04:59:05,284][87426] Updated weights for policy 1, policy_version 181950 (0.0011) -[2023-11-28 04:59:06,517][87424] Updated weights for policy 0, policy_version 182407 (0.0008) -[2023-11-28 04:59:06,903][87424] Updated weights for policy 0, policy_version 182417 (0.0010) -[2023-11-28 04:59:07,289][87424] Updated weights for policy 0, policy_version 182427 (0.0011) -[2023-11-28 04:59:07,382][87426] Updated weights for policy 1, policy_version 181960 (0.0010) -[2023-11-28 04:59:07,752][87426] Updated weights for policy 1, policy_version 181970 (0.0007) -[2023-11-28 04:59:08,136][87426] Updated weights for policy 1, policy_version 181980 (0.0008) -[2023-11-28 04:59:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 93290496. Throughput: 0: 2713.3, 1: 2732.2. Samples: 93303200. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:59:08,445][86177] Avg episode reward: [(0, '-518.530'), (1, '-541.440')] -[2023-11-28 04:59:09,085][87424] Updated weights for policy 0, policy_version 182437 (0.0011) -[2023-11-28 04:59:09,470][87424] Updated weights for policy 0, policy_version 182447 (0.0012) -[2023-11-28 04:59:09,858][87424] Updated weights for policy 0, policy_version 182457 (0.0012) -[2023-11-28 04:59:09,984][87426] Updated weights for policy 1, policy_version 181990 (0.0010) -[2023-11-28 04:59:10,355][87426] Updated weights for policy 1, policy_version 182000 (0.0008) -[2023-11-28 04:59:10,734][87426] Updated weights for policy 1, policy_version 182010 (0.0008) -[2023-11-28 04:59:12,195][87424] Updated weights for policy 0, policy_version 182467 (0.0012) -[2023-11-28 04:59:12,575][87424] Updated weights for policy 0, policy_version 182477 (0.0011) -[2023-11-28 04:59:12,954][87424] Updated weights for policy 0, policy_version 182487 (0.0009) -[2023-11-28 04:59:13,219][87426] Updated weights for policy 1, policy_version 182020 (0.0009) -[2023-11-28 04:59:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 93315072. Throughput: 0: 2733.4, 1: 2709.5. Samples: 93327360. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:59:13,445][86177] Avg episode reward: [(0, '-511.300'), (1, '-535.570')] -[2023-11-28 04:59:13,597][87426] Updated weights for policy 1, policy_version 182030 (0.0008) -[2023-11-28 04:59:13,974][87426] Updated weights for policy 1, policy_version 182040 (0.0008) -[2023-11-28 04:59:14,955][87424] Updated weights for policy 0, policy_version 182497 (0.0009) -[2023-11-28 04:59:15,328][87424] Updated weights for policy 0, policy_version 182507 (0.0010) -[2023-11-28 04:59:15,708][87424] Updated weights for policy 0, policy_version 182517 (0.0011) -[2023-11-28 04:59:16,085][87424] Updated weights for policy 0, policy_version 182527 (0.0012) -[2023-11-28 04:59:16,407][87426] Updated weights for policy 1, policy_version 182050 (0.0009) -[2023-11-28 04:59:16,776][87426] Updated weights for policy 1, policy_version 182060 (0.0011) -[2023-11-28 04:59:17,162][87426] Updated weights for policy 1, policy_version 182070 (0.0011) -[2023-11-28 04:59:17,544][87426] Updated weights for policy 1, policy_version 182080 (0.0010) -[2023-11-28 04:59:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93339648. Throughput: 0: 2737.3, 1: 2720.9. Samples: 93351348. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:59:18,445][86177] Avg episode reward: [(0, '-525.740'), (1, '-552.510')] -[2023-11-28 04:59:18,613][87424] Updated weights for policy 0, policy_version 182537 (0.0008) -[2023-11-28 04:59:18,991][87424] Updated weights for policy 0, policy_version 182547 (0.0009) -[2023-11-28 04:59:19,369][87424] Updated weights for policy 0, policy_version 182557 (0.0011) -[2023-11-28 04:59:19,961][87426] Updated weights for policy 1, policy_version 182090 (0.0009) -[2023-11-28 04:59:20,341][87426] Updated weights for policy 1, policy_version 182100 (0.0011) -[2023-11-28 04:59:20,721][87426] Updated weights for policy 1, policy_version 182110 (0.0010) -[2023-11-28 04:59:21,730][87424] Updated weights for policy 0, policy_version 182567 (0.0011) -[2023-11-28 04:59:22,111][87424] Updated weights for policy 0, policy_version 182577 (0.0011) -[2023-11-28 04:59:22,491][87424] Updated weights for policy 0, policy_version 182587 (0.0012) -[2023-11-28 04:59:23,046][87426] Updated weights for policy 1, policy_version 182120 (0.0009) -[2023-11-28 04:59:23,423][87426] Updated weights for policy 1, policy_version 182130 (0.0007) -[2023-11-28 04:59:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93364224. Throughput: 0: 2711.3, 1: 2693.2. Samples: 93382516. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:59:23,445][86177] Avg episode reward: [(0, '-524.780'), (1, '-531.840')] -[2023-11-28 04:59:23,804][87426] Updated weights for policy 1, policy_version 182140 (0.0010) -[2023-11-28 04:59:24,775][87424] Updated weights for policy 0, policy_version 182597 (0.0010) -[2023-11-28 04:59:25,158][87424] Updated weights for policy 0, policy_version 182607 (0.0008) -[2023-11-28 04:59:25,548][87424] Updated weights for policy 0, policy_version 182617 (0.0008) -[2023-11-28 04:59:25,730][87426] Updated weights for policy 1, policy_version 182150 (0.0009) -[2023-11-28 04:59:26,121][87426] Updated weights for policy 1, policy_version 182160 (0.0007) -[2023-11-28 04:59:26,510][87426] Updated weights for policy 1, policy_version 182170 (0.0007) -[2023-11-28 04:59:27,480][87424] Updated weights for policy 0, policy_version 182627 (0.0008) -[2023-11-28 04:59:27,867][87424] Updated weights for policy 0, policy_version 182637 (0.0008) -[2023-11-28 04:59:28,235][87424] Updated weights for policy 0, policy_version 182647 (0.0007) -[2023-11-28 04:59:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 93388800. Throughput: 0: 2723.6, 1: 2681.2. Samples: 93406928. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:59:28,445][86177] Avg episode reward: [(0, '-522.940'), (1, '-520.660')] -[2023-11-28 04:59:28,941][87426] Updated weights for policy 1, policy_version 182180 (0.0008) -[2023-11-28 04:59:29,320][87426] Updated weights for policy 1, policy_version 182190 (0.0010) -[2023-11-28 04:59:29,707][87426] Updated weights for policy 1, policy_version 182200 (0.0011) -[2023-11-28 04:59:30,724][87424] Updated weights for policy 0, policy_version 182657 (0.0008) -[2023-11-28 04:59:31,111][87424] Updated weights for policy 0, policy_version 182667 (0.0009) -[2023-11-28 04:59:31,494][87424] Updated weights for policy 0, policy_version 182677 (0.0008) -[2023-11-28 04:59:31,859][87426] Updated weights for policy 1, policy_version 182210 (0.0011) -[2023-11-28 04:59:31,888][87424] Updated weights for policy 0, policy_version 182687 (0.0010) -[2023-11-28 04:59:32,247][87426] Updated weights for policy 1, policy_version 182220 (0.0011) -[2023-11-28 04:59:32,630][87426] Updated weights for policy 1, policy_version 182230 (0.0007) -[2023-11-28 04:59:33,012][87426] Updated weights for policy 1, policy_version 182240 (0.0008) -[2023-11-28 04:59:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93421568. Throughput: 0: 2695.1, 1: 2689.6. Samples: 93431144. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:59:33,445][86177] Avg episode reward: [(0, '-518.590'), (1, '-526.500')] -[2023-11-28 04:59:34,008][87424] Updated weights for policy 0, policy_version 182697 (0.0009) -[2023-11-28 04:59:34,397][87424] Updated weights for policy 0, policy_version 182707 (0.0007) -[2023-11-28 04:59:34,772][87424] Updated weights for policy 0, policy_version 182717 (0.0009) -[2023-11-28 04:59:35,319][87426] Updated weights for policy 1, policy_version 182250 (0.0010) -[2023-11-28 04:59:35,698][87426] Updated weights for policy 1, policy_version 182260 (0.0011) -[2023-11-28 04:59:36,077][87426] Updated weights for policy 1, policy_version 182270 (0.0009) -[2023-11-28 04:59:37,287][87424] Updated weights for policy 0, policy_version 182727 (0.0010) -[2023-11-28 04:59:37,672][87424] Updated weights for policy 0, policy_version 182737 (0.0010) -[2023-11-28 04:59:38,056][87424] Updated weights for policy 0, policy_version 182747 (0.0011) -[2023-11-28 04:59:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93446144. Throughput: 0: 2683.6, 1: 2686.1. Samples: 93462580. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:59:38,445][86177] Avg episode reward: [(0, '-503.930'), (1, '-505.140')] -[2023-11-28 04:59:38,529][87426] Updated weights for policy 1, policy_version 182280 (0.0011) -[2023-11-28 04:59:38,912][87426] Updated weights for policy 1, policy_version 182290 (0.0011) -[2023-11-28 04:59:39,284][87426] Updated weights for policy 1, policy_version 182300 (0.0007) -[2023-11-28 04:59:40,214][87424] Updated weights for policy 0, policy_version 182757 (0.0010) -[2023-11-28 04:59:40,585][87424] Updated weights for policy 0, policy_version 182767 (0.0012) -[2023-11-28 04:59:40,970][87424] Updated weights for policy 0, policy_version 182777 (0.0010) -[2023-11-28 04:59:41,779][87426] Updated weights for policy 1, policy_version 182310 (0.0010) -[2023-11-28 04:59:42,147][87426] Updated weights for policy 1, policy_version 182320 (0.0011) -[2023-11-28 04:59:42,532][87426] Updated weights for policy 1, policy_version 182330 (0.0018) -[2023-11-28 04:59:43,316][87424] Updated weights for policy 0, policy_version 182787 (0.0009) -[2023-11-28 04:59:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 93470720. Throughput: 0: 2692.2, 1: 2649.9. Samples: 93486868. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 04:59:43,445][86177] Avg episode reward: [(0, '-507.450'), (1, '-504.550')] -[2023-11-28 04:59:43,699][87424] Updated weights for policy 0, policy_version 182797 (0.0012) -[2023-11-28 04:59:44,073][87424] Updated weights for policy 0, policy_version 182807 (0.0012) -[2023-11-28 04:59:44,777][87426] Updated weights for policy 1, policy_version 182340 (0.0011) -[2023-11-28 04:59:45,157][87426] Updated weights for policy 1, policy_version 182350 (0.0009) -[2023-11-28 04:59:45,536][87426] Updated weights for policy 1, policy_version 182360 (0.0011) -[2023-11-28 04:59:46,271][87424] Updated weights for policy 0, policy_version 182817 (0.0012) -[2023-11-28 04:59:46,656][87424] Updated weights for policy 0, policy_version 182827 (0.0012) -[2023-11-28 04:59:47,037][87424] Updated weights for policy 0, policy_version 182837 (0.0012) -[2023-11-28 04:59:47,408][87424] Updated weights for policy 0, policy_version 182847 (0.0012) -[2023-11-28 04:59:47,767][87426] Updated weights for policy 1, policy_version 182370 (0.0012) -[2023-11-28 04:59:48,142][87426] Updated weights for policy 1, policy_version 182380 (0.0012) -[2023-11-28 04:59:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93495296. Throughput: 0: 2687.4, 1: 2664.6. Samples: 93511672. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 04:59:48,445][86177] Avg episode reward: [(0, '-507.370'), (1, '-558.350')] -[2023-11-28 04:59:48,518][87426] Updated weights for policy 1, policy_version 182390 (0.0008) -[2023-11-28 04:59:48,893][87426] Updated weights for policy 1, policy_version 182400 (0.0008) -[2023-11-28 04:59:49,103][87424] Updated weights for policy 0, policy_version 182857 (0.0008) -[2023-11-28 04:59:49,492][87424] Updated weights for policy 0, policy_version 182867 (0.0007) -[2023-11-28 04:59:49,860][87424] Updated weights for policy 0, policy_version 182877 (0.0009) -[2023-11-28 04:59:51,229][87426] Updated weights for policy 1, policy_version 182410 (0.0012) -[2023-11-28 04:59:51,614][87426] Updated weights for policy 1, policy_version 182420 (0.0011) -[2023-11-28 04:59:51,985][87426] Updated weights for policy 1, policy_version 182430 (0.0011) -[2023-11-28 04:59:52,016][87424] Updated weights for policy 0, policy_version 182887 (0.0011) -[2023-11-28 04:59:52,392][87424] Updated weights for policy 0, policy_version 182897 (0.0008) -[2023-11-28 04:59:52,778][87424] Updated weights for policy 0, policy_version 182907 (0.0009) -[2023-11-28 04:59:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93528064. Throughput: 0: 2692.0, 1: 2637.7. Samples: 93543036. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 04:59:53,445][86177] Avg episode reward: [(0, '-513.910'), (1, '-554.390')] -[2023-11-28 04:59:54,356][87426] Updated weights for policy 1, policy_version 182440 (0.0012) -[2023-11-28 04:59:54,744][87426] Updated weights for policy 1, policy_version 182450 (0.0011) -[2023-11-28 04:59:54,930][87424] Updated weights for policy 0, policy_version 182917 (0.0009) -[2023-11-28 04:59:55,129][87426] Updated weights for policy 1, policy_version 182460 (0.0011) -[2023-11-28 04:59:55,315][87424] Updated weights for policy 0, policy_version 182927 (0.0008) -[2023-11-28 04:59:55,704][87424] Updated weights for policy 0, policy_version 182937 (0.0007) -[2023-11-28 04:59:56,960][87426] Updated weights for policy 1, policy_version 182470 (0.0008) -[2023-11-28 04:59:57,337][87426] Updated weights for policy 1, policy_version 182480 (0.0010) -[2023-11-28 04:59:57,722][87426] Updated weights for policy 1, policy_version 182490 (0.0010) -[2023-11-28 04:59:58,206][87424] Updated weights for policy 0, policy_version 182947 (0.0007) -[2023-11-28 04:59:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93552640. Throughput: 0: 2684.4, 1: 2666.9. Samples: 93568172. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 04:59:58,446][86177] Avg episode reward: [(0, '-510.810'), (1, '-593.210')] -[2023-11-28 04:59:58,591][87424] Updated weights for policy 0, policy_version 182957 (0.0007) -[2023-11-28 04:59:58,988][87424] Updated weights for policy 0, policy_version 182967 (0.0009) -[2023-11-28 05:00:00,184][87426] Updated weights for policy 1, policy_version 182500 (0.0011) -[2023-11-28 05:00:00,561][87426] Updated weights for policy 1, policy_version 182510 (0.0012) -[2023-11-28 05:00:00,954][87426] Updated weights for policy 1, policy_version 182520 (0.0012) -[2023-11-28 05:00:01,291][87424] Updated weights for policy 0, policy_version 182977 (0.0009) -[2023-11-28 05:00:01,673][87424] Updated weights for policy 0, policy_version 182987 (0.0008) -[2023-11-28 05:00:02,054][87424] Updated weights for policy 0, policy_version 182997 (0.0009) -[2023-11-28 05:00:02,438][87424] Updated weights for policy 0, policy_version 183007 (0.0008) -[2023-11-28 05:00:03,279][87426] Updated weights for policy 1, policy_version 182530 (0.0008) -[2023-11-28 05:00:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93577216. Throughput: 0: 2688.4, 1: 2662.5. Samples: 93592140. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:03,446][86177] Avg episode reward: [(0, '-505.320'), (1, '-595.220')] -[2023-11-28 05:00:03,657][87426] Updated weights for policy 1, policy_version 182540 (0.0007) -[2023-11-28 05:00:04,043][87426] Updated weights for policy 1, policy_version 182550 (0.0007) -[2023-11-28 05:00:04,424][87426] Updated weights for policy 1, policy_version 182560 (0.0008) -[2023-11-28 05:00:04,884][87424] Updated weights for policy 0, policy_version 183017 (0.0011) -[2023-11-28 05:00:05,277][87424] Updated weights for policy 0, policy_version 183027 (0.0011) -[2023-11-28 05:00:05,649][87424] Updated weights for policy 0, policy_version 183037 (0.0007) -[2023-11-28 05:00:06,312][87426] Updated weights for policy 1, policy_version 182570 (0.0008) -[2023-11-28 05:00:06,701][87426] Updated weights for policy 1, policy_version 182580 (0.0011) -[2023-11-28 05:00:07,089][87426] Updated weights for policy 1, policy_version 182590 (0.0010) -[2023-11-28 05:00:07,364][87424] Updated weights for policy 0, policy_version 183047 (0.0010) -[2023-11-28 05:00:07,748][87424] Updated weights for policy 0, policy_version 183057 (0.0009) -[2023-11-28 05:00:08,138][87424] Updated weights for policy 0, policy_version 183067 (0.0011) -[2023-11-28 05:00:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93609984. Throughput: 0: 2688.6, 1: 2667.8. Samples: 93623556. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:08,445][86177] Avg episode reward: [(0, '-515.130'), (1, '-545.600')] -[2023-11-28 05:00:09,352][87426] Updated weights for policy 1, policy_version 182600 (0.0011) -[2023-11-28 05:00:09,716][87426] Updated weights for policy 1, policy_version 182610 (0.0012) -[2023-11-28 05:00:09,977][87424] Updated weights for policy 0, policy_version 183077 (0.0010) -[2023-11-28 05:00:10,094][87426] Updated weights for policy 1, policy_version 182620 (0.0012) -[2023-11-28 05:00:10,363][87424] Updated weights for policy 0, policy_version 183087 (0.0009) -[2023-11-28 05:00:10,742][87424] Updated weights for policy 0, policy_version 183097 (0.0011) -[2023-11-28 05:00:12,054][87426] Updated weights for policy 1, policy_version 182630 (0.0012) -[2023-11-28 05:00:12,438][87426] Updated weights for policy 1, policy_version 182640 (0.0011) -[2023-11-28 05:00:12,813][87426] Updated weights for policy 1, policy_version 182650 (0.0011) -[2023-11-28 05:00:12,919][87424] Updated weights for policy 0, policy_version 183107 (0.0012) -[2023-11-28 05:00:13,307][87424] Updated weights for policy 0, policy_version 183117 (0.0008) -[2023-11-28 05:00:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93634560. Throughput: 0: 2697.9, 1: 2666.3. Samples: 93648316. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:13,445][86177] Avg episode reward: [(0, '-522.700'), (1, '-505.140')] -[2023-11-28 05:00:13,691][87424] Updated weights for policy 0, policy_version 183127 (0.0007) -[2023-11-28 05:00:15,234][87426] Updated weights for policy 1, policy_version 182660 (0.0011) -[2023-11-28 05:00:15,611][87426] Updated weights for policy 1, policy_version 182670 (0.0010) -[2023-11-28 05:00:15,682][87424] Updated weights for policy 0, policy_version 183137 (0.0011) -[2023-11-28 05:00:16,002][87426] Updated weights for policy 1, policy_version 182680 (0.0008) -[2023-11-28 05:00:16,064][87424] Updated weights for policy 0, policy_version 183147 (0.0010) -[2023-11-28 05:00:16,444][87424] Updated weights for policy 0, policy_version 183157 (0.0009) -[2023-11-28 05:00:16,826][87424] Updated weights for policy 0, policy_version 183167 (0.0007) -[2023-11-28 05:00:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93659136. Throughput: 0: 2693.5, 1: 2656.2. Samples: 93671880. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:18,445][86177] Avg episode reward: [(0, '-533.100'), (1, '-500.560')] -[2023-11-28 05:00:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000183168_46891008.pth... -[2023-11-28 05:00:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000180640_46243840.pth -[2023-11-28 05:00:18,513][87426] Updated weights for policy 1, policy_version 182690 (0.0009) -[2023-11-28 05:00:18,901][87426] Updated weights for policy 1, policy_version 182700 (0.0012) -[2023-11-28 05:00:19,242][87424] Updated weights for policy 0, policy_version 183177 (0.0007) -[2023-11-28 05:00:19,270][87426] Updated weights for policy 1, policy_version 182710 (0.0012) -[2023-11-28 05:00:19,622][87424] Updated weights for policy 0, policy_version 183187 (0.0011) -[2023-11-28 05:00:19,651][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000182720_46776320.pth... -[2023-11-28 05:00:19,652][87426] Updated weights for policy 1, policy_version 182720 (0.0012) -[2023-11-28 05:00:19,695][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000180192_46129152.pth -[2023-11-28 05:00:20,002][87424] Updated weights for policy 0, policy_version 183197 (0.0009) -[2023-11-28 05:00:21,804][87426] Updated weights for policy 1, policy_version 182730 (0.0010) -[2023-11-28 05:00:22,188][87426] Updated weights for policy 1, policy_version 182740 (0.0009) -[2023-11-28 05:00:22,485][87424] Updated weights for policy 0, policy_version 183207 (0.0011) -[2023-11-28 05:00:22,563][87426] Updated weights for policy 1, policy_version 182750 (0.0012) -[2023-11-28 05:00:22,859][87424] Updated weights for policy 0, policy_version 183217 (0.0011) -[2023-11-28 05:00:23,247][87424] Updated weights for policy 0, policy_version 183227 (0.0012) -[2023-11-28 05:00:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93691904. Throughput: 0: 2689.2, 1: 2657.6. Samples: 93703188. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:23,445][86177] Avg episode reward: [(0, '-553.390'), (1, '-508.610')] -[2023-11-28 05:00:24,362][87426] Updated weights for policy 1, policy_version 182760 (0.0011) -[2023-11-28 05:00:24,747][87426] Updated weights for policy 1, policy_version 182770 (0.0008) -[2023-11-28 05:00:25,120][87426] Updated weights for policy 1, policy_version 182780 (0.0009) -[2023-11-28 05:00:25,553][87424] Updated weights for policy 0, policy_version 183237 (0.0010) -[2023-11-28 05:00:25,946][87424] Updated weights for policy 0, policy_version 183247 (0.0011) -[2023-11-28 05:00:26,335][87424] Updated weights for policy 0, policy_version 183257 (0.0011) -[2023-11-28 05:00:27,571][87426] Updated weights for policy 1, policy_version 182790 (0.0009) -[2023-11-28 05:00:27,945][87426] Updated weights for policy 1, policy_version 182800 (0.0007) -[2023-11-28 05:00:28,332][87426] Updated weights for policy 1, policy_version 182810 (0.0007) -[2023-11-28 05:00:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 93708288. Throughput: 0: 2682.7, 1: 2685.5. Samples: 93728436. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:28,445][86177] Avg episode reward: [(0, '-550.810'), (1, '-503.610')] -[2023-11-28 05:00:28,481][87424] Updated weights for policy 0, policy_version 183267 (0.0007) -[2023-11-28 05:00:28,864][87424] Updated weights for policy 0, policy_version 183277 (0.0008) -[2023-11-28 05:00:29,251][87424] Updated weights for policy 0, policy_version 183287 (0.0007) -[2023-11-28 05:00:30,621][87426] Updated weights for policy 1, policy_version 182820 (0.0009) -[2023-11-28 05:00:31,009][87426] Updated weights for policy 1, policy_version 182830 (0.0011) -[2023-11-28 05:00:31,385][87426] Updated weights for policy 1, policy_version 182840 (0.0012) -[2023-11-28 05:00:31,500][87424] Updated weights for policy 0, policy_version 183297 (0.0008) -[2023-11-28 05:00:31,886][87424] Updated weights for policy 0, policy_version 183307 (0.0010) -[2023-11-28 05:00:32,270][87424] Updated weights for policy 0, policy_version 183317 (0.0012) -[2023-11-28 05:00:32,664][87424] Updated weights for policy 0, policy_version 183327 (0.0012) -[2023-11-28 05:00:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93741056. Throughput: 0: 2662.0, 1: 2676.4. Samples: 93751900. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:33,445][86177] Avg episode reward: [(0, '-539.230'), (1, '-506.210')] -[2023-11-28 05:00:33,776][87426] Updated weights for policy 1, policy_version 182850 (0.0012) -[2023-11-28 05:00:34,153][87426] Updated weights for policy 1, policy_version 182860 (0.0011) -[2023-11-28 05:00:34,530][87426] Updated weights for policy 1, policy_version 182870 (0.0010) -[2023-11-28 05:00:34,730][87424] Updated weights for policy 0, policy_version 183337 (0.0009) -[2023-11-28 05:00:34,909][87426] Updated weights for policy 1, policy_version 182880 (0.0011) -[2023-11-28 05:00:35,115][87424] Updated weights for policy 0, policy_version 183347 (0.0007) -[2023-11-28 05:00:35,501][87424] Updated weights for policy 0, policy_version 183357 (0.0007) -[2023-11-28 05:00:37,422][87426] Updated weights for policy 1, policy_version 182890 (0.0010) -[2023-11-28 05:00:37,805][87426] Updated weights for policy 1, policy_version 182900 (0.0008) -[2023-11-28 05:00:37,809][87424] Updated weights for policy 0, policy_version 183367 (0.0010) -[2023-11-28 05:00:38,179][87426] Updated weights for policy 1, policy_version 182910 (0.0009) -[2023-11-28 05:00:38,194][87424] Updated weights for policy 0, policy_version 183377 (0.0008) -[2023-11-28 05:00:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 93765632. Throughput: 0: 2681.2, 1: 2677.8. Samples: 93784192. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:38,445][86177] Avg episode reward: [(0, '-532.980'), (1, '-519.040')] -[2023-11-28 05:00:38,569][87424] Updated weights for policy 0, policy_version 183387 (0.0008) -[2023-11-28 05:00:40,485][87426] Updated weights for policy 1, policy_version 182920 (0.0009) -[2023-11-28 05:00:40,837][87424] Updated weights for policy 0, policy_version 183397 (0.0009) -[2023-11-28 05:00:40,865][87426] Updated weights for policy 1, policy_version 182930 (0.0010) -[2023-11-28 05:00:41,209][87424] Updated weights for policy 0, policy_version 183407 (0.0011) -[2023-11-28 05:00:41,250][87426] Updated weights for policy 1, policy_version 182940 (0.0009) -[2023-11-28 05:00:41,591][87424] Updated weights for policy 0, policy_version 183417 (0.0009) -[2023-11-28 05:00:43,360][87426] Updated weights for policy 1, policy_version 182950 (0.0015) -[2023-11-28 05:00:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93790208. Throughput: 0: 2671.0, 1: 2669.3. Samples: 93808484. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:43,445][86177] Avg episode reward: [(0, '-522.230'), (1, '-515.990')] -[2023-11-28 05:00:43,730][87426] Updated weights for policy 1, policy_version 182960 (0.0012) -[2023-11-28 05:00:43,820][87424] Updated weights for policy 0, policy_version 183427 (0.0011) -[2023-11-28 05:00:44,115][87426] Updated weights for policy 1, policy_version 182970 (0.0013) -[2023-11-28 05:00:44,202][87424] Updated weights for policy 0, policy_version 183437 (0.0012) -[2023-11-28 05:00:44,583][87424] Updated weights for policy 0, policy_version 183447 (0.0012) -[2023-11-28 05:00:45,995][87426] Updated weights for policy 1, policy_version 182980 (0.0011) -[2023-11-28 05:00:46,377][87426] Updated weights for policy 1, policy_version 182990 (0.0012) -[2023-11-28 05:00:46,539][87424] Updated weights for policy 0, policy_version 183457 (0.0011) -[2023-11-28 05:00:46,753][87426] Updated weights for policy 1, policy_version 183000 (0.0012) -[2023-11-28 05:00:46,937][87424] Updated weights for policy 0, policy_version 183467 (0.0010) -[2023-11-28 05:00:47,318][87424] Updated weights for policy 0, policy_version 183477 (0.0012) -[2023-11-28 05:00:47,698][87424] Updated weights for policy 0, policy_version 183487 (0.0012) -[2023-11-28 05:00:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93822976. Throughput: 0: 2667.0, 1: 2696.7. Samples: 93833508. Policy #0 lag: (min: 21.0, avg: 39.8, max: 53.0) -[2023-11-28 05:00:48,445][86177] Avg episode reward: [(0, '-513.110'), (1, '-555.430')] -[2023-11-28 05:00:48,528][87426] Updated weights for policy 1, policy_version 183010 (0.0012) -[2023-11-28 05:00:48,898][87426] Updated weights for policy 1, policy_version 183020 (0.0011) -[2023-11-28 05:00:49,276][87426] Updated weights for policy 1, policy_version 183030 (0.0008) -[2023-11-28 05:00:49,655][87426] Updated weights for policy 1, policy_version 183040 (0.0011) -[2023-11-28 05:00:50,100][87424] Updated weights for policy 0, policy_version 183497 (0.0012) -[2023-11-28 05:00:50,475][87424] Updated weights for policy 0, policy_version 183507 (0.0011) -[2023-11-28 05:00:50,859][87424] Updated weights for policy 0, policy_version 183517 (0.0008) -[2023-11-28 05:00:52,182][87426] Updated weights for policy 1, policy_version 183050 (0.0011) -[2023-11-28 05:00:52,565][87426] Updated weights for policy 1, policy_version 183060 (0.0009) -[2023-11-28 05:00:52,940][87426] Updated weights for policy 1, policy_version 183070 (0.0009) -[2023-11-28 05:00:53,062][87424] Updated weights for policy 0, policy_version 183527 (0.0011) -[2023-11-28 05:00:53,438][87424] Updated weights for policy 0, policy_version 183537 (0.0012) -[2023-11-28 05:00:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93847552. Throughput: 0: 2683.0, 1: 2705.6. Samples: 93866044. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:00:53,445][86177] Avg episode reward: [(0, '-511.340'), (1, '-559.170')] -[2023-11-28 05:00:53,820][87424] Updated weights for policy 0, policy_version 183547 (0.0012) -[2023-11-28 05:00:55,354][87426] Updated weights for policy 1, policy_version 183080 (0.0009) -[2023-11-28 05:00:55,740][87426] Updated weights for policy 1, policy_version 183090 (0.0011) -[2023-11-28 05:00:55,941][87424] Updated weights for policy 0, policy_version 183557 (0.0011) -[2023-11-28 05:00:56,115][87426] Updated weights for policy 1, policy_version 183100 (0.0008) -[2023-11-28 05:00:56,327][87424] Updated weights for policy 0, policy_version 183567 (0.0012) -[2023-11-28 05:00:56,718][87424] Updated weights for policy 0, policy_version 183577 (0.0009) -[2023-11-28 05:00:58,129][87426] Updated weights for policy 1, policy_version 183110 (0.0007) -[2023-11-28 05:00:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93872128. Throughput: 0: 2666.8, 1: 2708.0. Samples: 93890184. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:00:58,445][86177] Avg episode reward: [(0, '-521.100'), (1, '-550.740')] -[2023-11-28 05:00:58,508][87426] Updated weights for policy 1, policy_version 183120 (0.0007) -[2023-11-28 05:00:58,886][87426] Updated weights for policy 1, policy_version 183130 (0.0009) -[2023-11-28 05:00:59,147][87424] Updated weights for policy 0, policy_version 183587 (0.0008) -[2023-11-28 05:00:59,531][87424] Updated weights for policy 0, policy_version 183597 (0.0007) -[2023-11-28 05:00:59,914][87424] Updated weights for policy 0, policy_version 183607 (0.0009) -[2023-11-28 05:01:00,818][87426] Updated weights for policy 1, policy_version 183140 (0.0011) -[2023-11-28 05:01:01,202][87426] Updated weights for policy 1, policy_version 183150 (0.0011) -[2023-11-28 05:01:01,572][87426] Updated weights for policy 1, policy_version 183160 (0.0011) -[2023-11-28 05:01:02,180][87424] Updated weights for policy 0, policy_version 183617 (0.0009) -[2023-11-28 05:01:02,566][87424] Updated weights for policy 0, policy_version 183627 (0.0008) -[2023-11-28 05:01:02,946][87424] Updated weights for policy 0, policy_version 183637 (0.0008) -[2023-11-28 05:01:03,324][87424] Updated weights for policy 0, policy_version 183647 (0.0008) -[2023-11-28 05:01:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93904896. Throughput: 0: 2675.2, 1: 2723.7. Samples: 93914832. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:03,445][86177] Avg episode reward: [(0, '-513.420'), (1, '-545.020')] -[2023-11-28 05:01:03,640][87426] Updated weights for policy 1, policy_version 183170 (0.0011) -[2023-11-28 05:01:04,017][87426] Updated weights for policy 1, policy_version 183180 (0.0008) -[2023-11-28 05:01:04,395][87426] Updated weights for policy 1, policy_version 183190 (0.0008) -[2023-11-28 05:01:04,773][87426] Updated weights for policy 1, policy_version 183200 (0.0011) -[2023-11-28 05:01:05,793][87424] Updated weights for policy 0, policy_version 183657 (0.0007) -[2023-11-28 05:01:06,180][87424] Updated weights for policy 0, policy_version 183667 (0.0007) -[2023-11-28 05:01:06,568][87424] Updated weights for policy 0, policy_version 183677 (0.0009) -[2023-11-28 05:01:06,774][87426] Updated weights for policy 1, policy_version 183210 (0.0011) -[2023-11-28 05:01:07,154][87426] Updated weights for policy 1, policy_version 183220 (0.0012) -[2023-11-28 05:01:07,535][87426] Updated weights for policy 1, policy_version 183230 (0.0014) -[2023-11-28 05:01:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93929472. Throughput: 0: 2677.4, 1: 2737.2. Samples: 93946844. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:08,445][86177] Avg episode reward: [(0, '-514.620'), (1, '-510.940')] -[2023-11-28 05:01:08,970][87424] Updated weights for policy 0, policy_version 183687 (0.0010) -[2023-11-28 05:01:09,362][87424] Updated weights for policy 0, policy_version 183697 (0.0012) -[2023-11-28 05:01:09,532][87426] Updated weights for policy 1, policy_version 183240 (0.0011) -[2023-11-28 05:01:09,736][87424] Updated weights for policy 0, policy_version 183707 (0.0012) -[2023-11-28 05:01:09,917][87426] Updated weights for policy 1, policy_version 183250 (0.0011) -[2023-11-28 05:01:10,285][87426] Updated weights for policy 1, policy_version 183260 (0.0012) -[2023-11-28 05:01:11,809][87424] Updated weights for policy 0, policy_version 183717 (0.0015) -[2023-11-28 05:01:12,190][87424] Updated weights for policy 0, policy_version 183727 (0.0011) -[2023-11-28 05:01:12,569][87424] Updated weights for policy 0, policy_version 183737 (0.0011) -[2023-11-28 05:01:12,760][87426] Updated weights for policy 1, policy_version 183270 (0.0012) -[2023-11-28 05:01:13,133][87426] Updated weights for policy 1, policy_version 183280 (0.0009) -[2023-11-28 05:01:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 93954048. Throughput: 0: 2678.5, 1: 2702.8. Samples: 93970592. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:13,445][86177] Avg episode reward: [(0, '-519.870'), (1, '-512.280')] -[2023-11-28 05:01:13,518][87426] Updated weights for policy 1, policy_version 183290 (0.0008) -[2023-11-28 05:01:14,493][87424] Updated weights for policy 0, policy_version 183747 (0.0010) -[2023-11-28 05:01:14,870][87424] Updated weights for policy 0, policy_version 183757 (0.0008) -[2023-11-28 05:01:15,261][87424] Updated weights for policy 0, policy_version 183767 (0.0007) -[2023-11-28 05:01:15,992][87426] Updated weights for policy 1, policy_version 183300 (0.0008) -[2023-11-28 05:01:16,379][87426] Updated weights for policy 1, policy_version 183310 (0.0012) -[2023-11-28 05:01:16,752][87426] Updated weights for policy 1, policy_version 183320 (0.0011) -[2023-11-28 05:01:16,916][87424] Updated weights for policy 0, policy_version 183777 (0.0010) -[2023-11-28 05:01:17,307][87424] Updated weights for policy 0, policy_version 183787 (0.0008) -[2023-11-28 05:01:17,685][87424] Updated weights for policy 0, policy_version 183797 (0.0008) -[2023-11-28 05:01:18,069][87424] Updated weights for policy 0, policy_version 183807 (0.0007) -[2023-11-28 05:01:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 93986816. Throughput: 0: 2704.4, 1: 2706.9. Samples: 93995408. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:18,445][86177] Avg episode reward: [(0, '-506.050'), (1, '-513.640')] -[2023-11-28 05:01:18,901][87426] Updated weights for policy 1, policy_version 183330 (0.0011) -[2023-11-28 05:01:19,279][87426] Updated weights for policy 1, policy_version 183340 (0.0012) -[2023-11-28 05:01:19,661][87426] Updated weights for policy 1, policy_version 183350 (0.0011) -[2023-11-28 05:01:20,041][87426] Updated weights for policy 1, policy_version 183360 (0.0010) -[2023-11-28 05:01:20,373][87424] Updated weights for policy 0, policy_version 183817 (0.0011) -[2023-11-28 05:01:20,757][87424] Updated weights for policy 0, policy_version 183827 (0.0012) -[2023-11-28 05:01:21,148][87424] Updated weights for policy 0, policy_version 183837 (0.0009) -[2023-11-28 05:01:22,090][87426] Updated weights for policy 1, policy_version 183370 (0.0009) -[2023-11-28 05:01:22,464][87426] Updated weights for policy 1, policy_version 183380 (0.0010) -[2023-11-28 05:01:22,843][87426] Updated weights for policy 1, policy_version 183390 (0.0009) -[2023-11-28 05:01:23,401][87424] Updated weights for policy 0, policy_version 183847 (0.0011) -[2023-11-28 05:01:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 94011392. Throughput: 0: 2682.2, 1: 2738.1. Samples: 94028104. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:23,445][86177] Avg episode reward: [(0, '-505.880'), (1, '-505.410')] -[2023-11-28 05:01:23,778][87424] Updated weights for policy 0, policy_version 183857 (0.0009) -[2023-11-28 05:01:24,171][87424] Updated weights for policy 0, policy_version 183867 (0.0010) -[2023-11-28 05:01:25,026][87426] Updated weights for policy 1, policy_version 183400 (0.0008) -[2023-11-28 05:01:25,402][87426] Updated weights for policy 1, policy_version 183410 (0.0008) -[2023-11-28 05:01:25,777][87426] Updated weights for policy 1, policy_version 183420 (0.0007) -[2023-11-28 05:01:26,479][87424] Updated weights for policy 0, policy_version 183877 (0.0010) -[2023-11-28 05:01:26,861][87424] Updated weights for policy 0, policy_version 183887 (0.0008) -[2023-11-28 05:01:27,240][87424] Updated weights for policy 0, policy_version 183897 (0.0008) -[2023-11-28 05:01:27,871][87426] Updated weights for policy 1, policy_version 183430 (0.0008) -[2023-11-28 05:01:28,256][87426] Updated weights for policy 1, policy_version 183440 (0.0007) -[2023-11-28 05:01:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 94035968. Throughput: 0: 2705.1, 1: 2731.0. Samples: 94053112. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:28,445][86177] Avg episode reward: [(0, '-505.730'), (1, '-507.260')] -[2023-11-28 05:01:28,644][87426] Updated weights for policy 1, policy_version 183450 (0.0008) -[2023-11-28 05:01:29,775][87424] Updated weights for policy 0, policy_version 183907 (0.0009) -[2023-11-28 05:01:30,153][87424] Updated weights for policy 0, policy_version 183917 (0.0011) -[2023-11-28 05:01:30,526][87424] Updated weights for policy 0, policy_version 183927 (0.0012) -[2023-11-28 05:01:31,093][87426] Updated weights for policy 1, policy_version 183460 (0.0007) -[2023-11-28 05:01:31,477][87426] Updated weights for policy 1, policy_version 183470 (0.0010) -[2023-11-28 05:01:31,846][87426] Updated weights for policy 1, policy_version 183480 (0.0014) -[2023-11-28 05:01:32,261][87424] Updated weights for policy 0, policy_version 183937 (0.0012) -[2023-11-28 05:01:32,640][87424] Updated weights for policy 0, policy_version 183947 (0.0008) -[2023-11-28 05:01:33,021][87424] Updated weights for policy 0, policy_version 183957 (0.0010) -[2023-11-28 05:01:33,403][87424] Updated weights for policy 0, policy_version 183967 (0.0008) -[2023-11-28 05:01:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 94068736. Throughput: 0: 2716.2, 1: 2700.9. Samples: 94077276. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:33,445][86177] Avg episode reward: [(0, '-524.560'), (1, '-513.050')] -[2023-11-28 05:01:34,270][87426] Updated weights for policy 1, policy_version 183490 (0.0011) -[2023-11-28 05:01:34,657][87426] Updated weights for policy 1, policy_version 183500 (0.0008) -[2023-11-28 05:01:35,031][87426] Updated weights for policy 1, policy_version 183510 (0.0011) -[2023-11-28 05:01:35,246][87424] Updated weights for policy 0, policy_version 183977 (0.0011) -[2023-11-28 05:01:35,407][87426] Updated weights for policy 1, policy_version 183520 (0.0011) -[2023-11-28 05:01:35,625][87424] Updated weights for policy 0, policy_version 183987 (0.0011) -[2023-11-28 05:01:36,005][87424] Updated weights for policy 0, policy_version 183997 (0.0012) -[2023-11-28 05:01:37,036][87426] Updated weights for policy 1, policy_version 183530 (0.0009) -[2023-11-28 05:01:37,414][87426] Updated weights for policy 1, policy_version 183540 (0.0010) -[2023-11-28 05:01:37,792][87426] Updated weights for policy 1, policy_version 183550 (0.0011) -[2023-11-28 05:01:38,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 94093312. Throughput: 0: 2703.9, 1: 2717.3. Samples: 94110000. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:38,446][86177] Avg episode reward: [(0, '-526.640'), (1, '-511.900')] -[2023-11-28 05:01:38,552][87424] Updated weights for policy 0, policy_version 184007 (0.0010) -[2023-11-28 05:01:38,936][87424] Updated weights for policy 0, policy_version 184017 (0.0009) -[2023-11-28 05:01:39,317][87424] Updated weights for policy 0, policy_version 184027 (0.0010) -[2023-11-28 05:01:39,811][87426] Updated weights for policy 1, policy_version 183560 (0.0011) -[2023-11-28 05:01:40,189][87426] Updated weights for policy 1, policy_version 183570 (0.0012) -[2023-11-28 05:01:40,570][87426] Updated weights for policy 1, policy_version 183580 (0.0016) -[2023-11-28 05:01:41,391][87424] Updated weights for policy 0, policy_version 184037 (0.0011) -[2023-11-28 05:01:41,774][87424] Updated weights for policy 0, policy_version 184047 (0.0011) -[2023-11-28 05:01:42,162][87424] Updated weights for policy 0, policy_version 184057 (0.0009) -[2023-11-28 05:01:43,051][87426] Updated weights for policy 1, policy_version 183590 (0.0012) -[2023-11-28 05:01:43,424][87426] Updated weights for policy 1, policy_version 183600 (0.0012) -[2023-11-28 05:01:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 94117888. Throughput: 0: 2717.4, 1: 2695.5. Samples: 94133764. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:43,445][86177] Avg episode reward: [(0, '-527.750'), (1, '-510.450')] -[2023-11-28 05:01:43,806][87426] Updated weights for policy 1, policy_version 183610 (0.0012) -[2023-11-28 05:01:44,136][87424] Updated weights for policy 0, policy_version 184067 (0.0009) -[2023-11-28 05:01:44,532][87424] Updated weights for policy 0, policy_version 184077 (0.0012) -[2023-11-28 05:01:44,919][87424] Updated weights for policy 0, policy_version 184087 (0.0012) -[2023-11-28 05:01:46,066][87426] Updated weights for policy 1, policy_version 183620 (0.0010) -[2023-11-28 05:01:46,446][87426] Updated weights for policy 1, policy_version 183630 (0.0007) -[2023-11-28 05:01:46,827][87426] Updated weights for policy 1, policy_version 183640 (0.0008) -[2023-11-28 05:01:47,423][87424] Updated weights for policy 0, policy_version 184097 (0.0012) -[2023-11-28 05:01:47,802][87424] Updated weights for policy 0, policy_version 184107 (0.0012) -[2023-11-28 05:01:48,186][87424] Updated weights for policy 0, policy_version 184117 (0.0012) -[2023-11-28 05:01:48,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 94142464. Throughput: 0: 2729.6, 1: 2687.4. Samples: 94158596. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:48,445][86177] Avg episode reward: [(0, '-528.920'), (1, '-508.030')] -[2023-11-28 05:01:48,573][87424] Updated weights for policy 0, policy_version 184127 (0.0012) -[2023-11-28 05:01:49,015][87426] Updated weights for policy 1, policy_version 183650 (0.0008) -[2023-11-28 05:01:49,396][87426] Updated weights for policy 1, policy_version 183660 (0.0008) -[2023-11-28 05:01:49,775][87426] Updated weights for policy 1, policy_version 183670 (0.0008) -[2023-11-28 05:01:50,155][87426] Updated weights for policy 1, policy_version 183680 (0.0009) -[2023-11-28 05:01:50,962][87424] Updated weights for policy 0, policy_version 184137 (0.0009) -[2023-11-28 05:01:51,352][87424] Updated weights for policy 0, policy_version 184147 (0.0010) -[2023-11-28 05:01:51,722][87424] Updated weights for policy 0, policy_version 184157 (0.0010) -[2023-11-28 05:01:52,265][87426] Updated weights for policy 1, policy_version 183690 (0.0011) -[2023-11-28 05:01:52,641][87426] Updated weights for policy 1, policy_version 183700 (0.0009) -[2023-11-28 05:01:53,021][87426] Updated weights for policy 1, policy_version 183710 (0.0008) -[2023-11-28 05:01:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 94175232. Throughput: 0: 2755.6, 1: 2691.6. Samples: 94191964. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:53,445][86177] Avg episode reward: [(0, '-517.180'), (1, '-506.460')] -[2023-11-28 05:01:53,486][87424] Updated weights for policy 0, policy_version 184167 (0.0010) -[2023-11-28 05:01:53,871][87424] Updated weights for policy 0, policy_version 184177 (0.0008) -[2023-11-28 05:01:54,253][87424] Updated weights for policy 0, policy_version 184187 (0.0011) -[2023-11-28 05:01:55,347][87426] Updated weights for policy 1, policy_version 183720 (0.0008) -[2023-11-28 05:01:55,716][87426] Updated weights for policy 1, policy_version 183730 (0.0007) -[2023-11-28 05:01:55,980][87424] Updated weights for policy 0, policy_version 184197 (0.0011) -[2023-11-28 05:01:56,101][87426] Updated weights for policy 1, policy_version 183740 (0.0008) -[2023-11-28 05:01:56,352][87424] Updated weights for policy 0, policy_version 184207 (0.0012) -[2023-11-28 05:01:56,731][87424] Updated weights for policy 0, policy_version 184217 (0.0012) -[2023-11-28 05:01:58,051][87426] Updated weights for policy 1, policy_version 183750 (0.0008) -[2023-11-28 05:01:58,434][87426] Updated weights for policy 1, policy_version 183760 (0.0007) -[2023-11-28 05:01:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 94199808. Throughput: 0: 2762.9, 1: 2713.2. Samples: 94217016. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 05:01:58,445][86177] Avg episode reward: [(0, '-516.880'), (1, '-510.720')] -[2023-11-28 05:01:58,809][87426] Updated weights for policy 1, policy_version 183770 (0.0007) -[2023-11-28 05:01:58,989][87424] Updated weights for policy 0, policy_version 184227 (0.0011) -[2023-11-28 05:01:59,368][87424] Updated weights for policy 0, policy_version 184237 (0.0011) -[2023-11-28 05:01:59,753][87424] Updated weights for policy 0, policy_version 184247 (0.0009) -[2023-11-28 05:02:00,613][87426] Updated weights for policy 1, policy_version 183780 (0.0010) -[2023-11-28 05:02:00,989][87426] Updated weights for policy 1, policy_version 183790 (0.0010) -[2023-11-28 05:02:01,376][87426] Updated weights for policy 1, policy_version 183800 (0.0010) -[2023-11-28 05:02:02,183][87424] Updated weights for policy 0, policy_version 184257 (0.0012) -[2023-11-28 05:02:02,563][87424] Updated weights for policy 0, policy_version 184267 (0.0012) -[2023-11-28 05:02:02,944][87424] Updated weights for policy 0, policy_version 184277 (0.0012) -[2023-11-28 05:02:03,326][87424] Updated weights for policy 0, policy_version 184287 (0.0010) -[2023-11-28 05:02:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 94232576. Throughput: 0: 2758.7, 1: 2723.7. Samples: 94242116. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:03,445][86177] Avg episode reward: [(0, '-517.530'), (1, '-511.220')] -[2023-11-28 05:02:03,447][87426] Updated weights for policy 1, policy_version 183810 (0.0011) -[2023-11-28 05:02:03,825][87426] Updated weights for policy 1, policy_version 183820 (0.0011) -[2023-11-28 05:02:04,196][87426] Updated weights for policy 1, policy_version 183830 (0.0009) -[2023-11-28 05:02:04,575][87426] Updated weights for policy 1, policy_version 183840 (0.0011) -[2023-11-28 05:02:05,601][87424] Updated weights for policy 0, policy_version 184297 (0.0009) -[2023-11-28 05:02:05,987][87424] Updated weights for policy 0, policy_version 184307 (0.0009) -[2023-11-28 05:02:06,370][87424] Updated weights for policy 0, policy_version 184317 (0.0011) -[2023-11-28 05:02:06,577][87426] Updated weights for policy 1, policy_version 183850 (0.0011) -[2023-11-28 05:02:06,964][87426] Updated weights for policy 1, policy_version 183860 (0.0011) -[2023-11-28 05:02:07,354][87426] Updated weights for policy 1, policy_version 183870 (0.0011) -[2023-11-28 05:02:08,206][87424] Updated weights for policy 0, policy_version 184327 (0.0010) -[2023-11-28 05:02:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 94257152. Throughput: 0: 2762.8, 1: 2730.8. Samples: 94275320. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:08,445][86177] Avg episode reward: [(0, '-522.370'), (1, '-516.780')] -[2023-11-28 05:02:08,592][87424] Updated weights for policy 0, policy_version 184337 (0.0011) -[2023-11-28 05:02:08,973][87424] Updated weights for policy 0, policy_version 184347 (0.0011) -[2023-11-28 05:02:09,928][87426] Updated weights for policy 1, policy_version 183880 (0.0009) -[2023-11-28 05:02:10,311][87426] Updated weights for policy 1, policy_version 183890 (0.0008) -[2023-11-28 05:02:10,688][87426] Updated weights for policy 1, policy_version 183900 (0.0011) -[2023-11-28 05:02:11,254][87424] Updated weights for policy 0, policy_version 184357 (0.0011) -[2023-11-28 05:02:11,634][87424] Updated weights for policy 0, policy_version 184367 (0.0012) -[2023-11-28 05:02:12,010][87424] Updated weights for policy 0, policy_version 184377 (0.0011) -[2023-11-28 05:02:12,775][87426] Updated weights for policy 1, policy_version 183910 (0.0011) -[2023-11-28 05:02:13,147][87426] Updated weights for policy 1, policy_version 183920 (0.0010) -[2023-11-28 05:02:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 94281728. Throughput: 0: 2751.1, 1: 2735.1. Samples: 94299992. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:13,445][86177] Avg episode reward: [(0, '-513.900'), (1, '-514.430')] -[2023-11-28 05:02:13,524][87426] Updated weights for policy 1, policy_version 183930 (0.0009) -[2023-11-28 05:02:14,508][87424] Updated weights for policy 0, policy_version 184387 (0.0009) -[2023-11-28 05:02:14,886][87424] Updated weights for policy 0, policy_version 184397 (0.0009) -[2023-11-28 05:02:15,273][87424] Updated weights for policy 0, policy_version 184407 (0.0012) -[2023-11-28 05:02:15,371][87426] Updated weights for policy 1, policy_version 183940 (0.0009) -[2023-11-28 05:02:15,750][87426] Updated weights for policy 1, policy_version 183950 (0.0012) -[2023-11-28 05:02:16,130][87426] Updated weights for policy 1, policy_version 183960 (0.0012) -[2023-11-28 05:02:17,106][87424] Updated weights for policy 0, policy_version 184417 (0.0011) -[2023-11-28 05:02:17,485][87424] Updated weights for policy 0, policy_version 184427 (0.0008) -[2023-11-28 05:02:17,865][87424] Updated weights for policy 0, policy_version 184437 (0.0007) -[2023-11-28 05:02:18,254][87424] Updated weights for policy 0, policy_version 184447 (0.0007) -[2023-11-28 05:02:18,323][87426] Updated weights for policy 1, policy_version 183970 (0.0011) -[2023-11-28 05:02:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 94314496. Throughput: 0: 2737.2, 1: 2745.4. Samples: 94323992. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:18,445][86177] Avg episode reward: [(0, '-518.340'), (1, '-524.200')] -[2023-11-28 05:02:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000184448_47218688.pth... -[2023-11-28 05:02:18,497][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000181920_46571520.pth -[2023-11-28 05:02:18,708][87426] Updated weights for policy 1, policy_version 183980 (0.0007) -[2023-11-28 05:02:19,088][87426] Updated weights for policy 1, policy_version 183990 (0.0009) -[2023-11-28 05:02:19,466][87426] Updated weights for policy 1, policy_version 184000 (0.0010) -[2023-11-28 05:02:19,466][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000184000_47104000.pth... -[2023-11-28 05:02:19,513][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000181440_46448640.pth -[2023-11-28 05:02:20,307][87424] Updated weights for policy 0, policy_version 184457 (0.0011) -[2023-11-28 05:02:20,694][87424] Updated weights for policy 0, policy_version 184467 (0.0012) -[2023-11-28 05:02:21,069][87424] Updated weights for policy 0, policy_version 184477 (0.0011) -[2023-11-28 05:02:21,591][87426] Updated weights for policy 1, policy_version 184010 (0.0008) -[2023-11-28 05:02:21,958][87426] Updated weights for policy 1, policy_version 184020 (0.0010) -[2023-11-28 05:02:22,336][87426] Updated weights for policy 1, policy_version 184030 (0.0011) -[2023-11-28 05:02:23,423][87424] Updated weights for policy 0, policy_version 184487 (0.0009) -[2023-11-28 05:02:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 94339072. Throughput: 0: 2731.8, 1: 2749.9. Samples: 94356676. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:23,445][86177] Avg episode reward: [(0, '-521.120'), (1, '-528.580')] -[2023-11-28 05:02:23,809][87424] Updated weights for policy 0, policy_version 184497 (0.0012) -[2023-11-28 05:02:24,183][87424] Updated weights for policy 0, policy_version 184507 (0.0012) -[2023-11-28 05:02:24,877][87426] Updated weights for policy 1, policy_version 184040 (0.0012) -[2023-11-28 05:02:25,259][87426] Updated weights for policy 1, policy_version 184050 (0.0008) -[2023-11-28 05:02:25,642][87426] Updated weights for policy 1, policy_version 184060 (0.0007) -[2023-11-28 05:02:26,001][87424] Updated weights for policy 0, policy_version 184517 (0.0012) -[2023-11-28 05:02:26,377][87424] Updated weights for policy 0, policy_version 184527 (0.0011) -[2023-11-28 05:02:26,754][87424] Updated weights for policy 0, policy_version 184537 (0.0011) -[2023-11-28 05:02:27,952][87426] Updated weights for policy 1, policy_version 184070 (0.0010) -[2023-11-28 05:02:28,350][87426] Updated weights for policy 1, policy_version 184080 (0.0012) -[2023-11-28 05:02:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 94363648. Throughput: 0: 2738.0, 1: 2753.7. Samples: 94380888. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:28,445][86177] Avg episode reward: [(0, '-513.640'), (1, '-531.160')] -[2023-11-28 05:02:28,726][87426] Updated weights for policy 1, policy_version 184090 (0.0012) -[2023-11-28 05:02:28,975][87424] Updated weights for policy 0, policy_version 184547 (0.0009) -[2023-11-28 05:02:29,372][87424] Updated weights for policy 0, policy_version 184557 (0.0008) -[2023-11-28 05:02:29,759][87424] Updated weights for policy 0, policy_version 184567 (0.0008) -[2023-11-28 05:02:31,218][87426] Updated weights for policy 1, policy_version 184100 (0.0009) -[2023-11-28 05:02:31,600][87426] Updated weights for policy 1, policy_version 184110 (0.0007) -[2023-11-28 05:02:31,976][87426] Updated weights for policy 1, policy_version 184120 (0.0010) -[2023-11-28 05:02:32,185][87424] Updated weights for policy 0, policy_version 184577 (0.0010) -[2023-11-28 05:02:32,567][87424] Updated weights for policy 0, policy_version 184587 (0.0009) -[2023-11-28 05:02:32,948][87424] Updated weights for policy 0, policy_version 184597 (0.0007) -[2023-11-28 05:02:33,330][87424] Updated weights for policy 0, policy_version 184607 (0.0007) -[2023-11-28 05:02:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 94396416. Throughput: 0: 2730.6, 1: 2746.7. Samples: 94405080. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:33,445][86177] Avg episode reward: [(0, '-527.400'), (1, '-552.110')] -[2023-11-28 05:02:34,509][87426] Updated weights for policy 1, policy_version 184130 (0.0009) -[2023-11-28 05:02:34,897][87426] Updated weights for policy 1, policy_version 184140 (0.0010) -[2023-11-28 05:02:35,276][87426] Updated weights for policy 1, policy_version 184150 (0.0008) -[2023-11-28 05:02:35,305][87424] Updated weights for policy 0, policy_version 184617 (0.0010) -[2023-11-28 05:02:35,660][87426] Updated weights for policy 1, policy_version 184160 (0.0008) -[2023-11-28 05:02:35,681][87424] Updated weights for policy 0, policy_version 184627 (0.0012) -[2023-11-28 05:02:36,077][87424] Updated weights for policy 0, policy_version 184637 (0.0012) -[2023-11-28 05:02:37,583][87426] Updated weights for policy 1, policy_version 184170 (0.0008) -[2023-11-28 05:02:37,965][87426] Updated weights for policy 1, policy_version 184180 (0.0008) -[2023-11-28 05:02:38,356][87426] Updated weights for policy 1, policy_version 184190 (0.0008) -[2023-11-28 05:02:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 94420992. Throughput: 0: 2709.6, 1: 2730.5. Samples: 94436768. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:38,445][86177] Avg episode reward: [(0, '-521.590'), (1, '-550.630')] -[2023-11-28 05:02:38,636][87424] Updated weights for policy 0, policy_version 184647 (0.0010) -[2023-11-28 05:02:39,015][87424] Updated weights for policy 0, policy_version 184657 (0.0012) -[2023-11-28 05:02:39,402][87424] Updated weights for policy 0, policy_version 184667 (0.0011) -[2023-11-28 05:02:40,636][87426] Updated weights for policy 1, policy_version 184200 (0.0011) -[2023-11-28 05:02:41,016][87426] Updated weights for policy 1, policy_version 184210 (0.0012) -[2023-11-28 05:02:41,363][87424] Updated weights for policy 0, policy_version 184677 (0.0009) -[2023-11-28 05:02:41,404][87426] Updated weights for policy 1, policy_version 184220 (0.0010) -[2023-11-28 05:02:41,749][87424] Updated weights for policy 0, policy_version 184687 (0.0009) -[2023-11-28 05:02:42,132][87424] Updated weights for policy 0, policy_version 184697 (0.0011) -[2023-11-28 05:02:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 94445568. Throughput: 0: 2704.8, 1: 2705.2. Samples: 94460468. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:43,445][86177] Avg episode reward: [(0, '-519.640'), (1, '-569.210')] -[2023-11-28 05:02:43,591][87426] Updated weights for policy 1, policy_version 184230 (0.0011) -[2023-11-28 05:02:43,974][87426] Updated weights for policy 1, policy_version 184240 (0.0011) -[2023-11-28 05:02:44,355][87426] Updated weights for policy 1, policy_version 184250 (0.0007) -[2023-11-28 05:02:44,455][87424] Updated weights for policy 0, policy_version 184707 (0.0011) -[2023-11-28 05:02:44,841][87424] Updated weights for policy 0, policy_version 184717 (0.0010) -[2023-11-28 05:02:45,220][87424] Updated weights for policy 0, policy_version 184727 (0.0009) -[2023-11-28 05:02:46,646][87426] Updated weights for policy 1, policy_version 184260 (0.0009) -[2023-11-28 05:02:47,019][87424] Updated weights for policy 0, policy_version 184737 (0.0008) -[2023-11-28 05:02:47,022][87426] Updated weights for policy 1, policy_version 184270 (0.0011) -[2023-11-28 05:02:47,397][87424] Updated weights for policy 0, policy_version 184747 (0.0008) -[2023-11-28 05:02:47,403][87426] Updated weights for policy 1, policy_version 184280 (0.0012) -[2023-11-28 05:02:47,788][87424] Updated weights for policy 0, policy_version 184757 (0.0007) -[2023-11-28 05:02:48,165][87424] Updated weights for policy 0, policy_version 184767 (0.0007) -[2023-11-28 05:02:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 94478336. Throughput: 0: 2713.4, 1: 2693.4. Samples: 94485424. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:48,446][86177] Avg episode reward: [(0, '-517.160'), (1, '-571.570')] -[2023-11-28 05:02:49,346][87426] Updated weights for policy 1, policy_version 184290 (0.0011) -[2023-11-28 05:02:49,727][87426] Updated weights for policy 1, policy_version 184300 (0.0007) -[2023-11-28 05:02:50,105][87426] Updated weights for policy 1, policy_version 184310 (0.0011) -[2023-11-28 05:02:50,478][87424] Updated weights for policy 0, policy_version 184777 (0.0011) -[2023-11-28 05:02:50,484][87426] Updated weights for policy 1, policy_version 184320 (0.0012) -[2023-11-28 05:02:50,853][87424] Updated weights for policy 0, policy_version 184787 (0.0012) -[2023-11-28 05:02:51,235][87424] Updated weights for policy 0, policy_version 184797 (0.0012) -[2023-11-28 05:02:52,432][87426] Updated weights for policy 1, policy_version 184330 (0.0011) -[2023-11-28 05:02:52,809][87426] Updated weights for policy 1, policy_version 184340 (0.0009) -[2023-11-28 05:02:53,190][87426] Updated weights for policy 1, policy_version 184350 (0.0012) -[2023-11-28 05:02:53,446][86177] Fps is (10 sec: 5733.1, 60 sec: 5461.1, 300 sec: 5415.0). Total num frames: 94502912. Throughput: 0: 2702.2, 1: 2702.6. Samples: 94518548. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:53,447][86177] Avg episode reward: [(0, '-504.210'), (1, '-567.350')] -[2023-11-28 05:02:53,654][87424] Updated weights for policy 0, policy_version 184807 (0.0011) -[2023-11-28 05:02:54,042][87424] Updated weights for policy 0, policy_version 184817 (0.0010) -[2023-11-28 05:02:54,427][87424] Updated weights for policy 0, policy_version 184827 (0.0012) -[2023-11-28 05:02:55,365][87426] Updated weights for policy 1, policy_version 184360 (0.0012) -[2023-11-28 05:02:55,742][87426] Updated weights for policy 1, policy_version 184370 (0.0012) -[2023-11-28 05:02:56,119][87426] Updated weights for policy 1, policy_version 184380 (0.0011) -[2023-11-28 05:02:56,388][87424] Updated weights for policy 0, policy_version 184837 (0.0011) -[2023-11-28 05:02:56,763][87424] Updated weights for policy 0, policy_version 184847 (0.0007) -[2023-11-28 05:02:57,140][87424] Updated weights for policy 0, policy_version 184857 (0.0007) -[2023-11-28 05:02:58,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 94527488. Throughput: 0: 2707.7, 1: 2707.7. Samples: 94543688. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:02:58,446][86177] Avg episode reward: [(0, '-500.420'), (1, '-573.060')] -[2023-11-28 05:02:58,472][87426] Updated weights for policy 1, policy_version 184390 (0.0007) -[2023-11-28 05:02:58,847][87426] Updated weights for policy 1, policy_version 184400 (0.0007) -[2023-11-28 05:02:59,029][87424] Updated weights for policy 0, policy_version 184867 (0.0010) -[2023-11-28 05:02:59,226][87426] Updated weights for policy 1, policy_version 184410 (0.0008) -[2023-11-28 05:02:59,413][87424] Updated weights for policy 0, policy_version 184877 (0.0011) -[2023-11-28 05:02:59,795][87424] Updated weights for policy 0, policy_version 184887 (0.0010) -[2023-11-28 05:03:01,605][87426] Updated weights for policy 1, policy_version 184420 (0.0008) -[2023-11-28 05:03:01,984][87426] Updated weights for policy 1, policy_version 184430 (0.0012) -[2023-11-28 05:03:02,280][87424] Updated weights for policy 0, policy_version 184897 (0.0011) -[2023-11-28 05:03:02,358][87426] Updated weights for policy 1, policy_version 184440 (0.0012) -[2023-11-28 05:03:02,654][87424] Updated weights for policy 0, policy_version 184907 (0.0011) -[2023-11-28 05:03:03,041][87424] Updated weights for policy 0, policy_version 184917 (0.0012) -[2023-11-28 05:03:03,415][87424] Updated weights for policy 0, policy_version 184927 (0.0012) -[2023-11-28 05:03:03,444][86177] Fps is (10 sec: 4916.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 94552064. Throughput: 0: 2729.3, 1: 2716.7. Samples: 94569064. Policy #0 lag: (min: 3.0, avg: 25.2, max: 39.0) -[2023-11-28 05:03:03,445][86177] Avg episode reward: [(0, '-503.150'), (1, '-576.510')] -[2023-11-28 05:03:04,267][87426] Updated weights for policy 1, policy_version 184450 (0.0010) -[2023-11-28 05:03:04,647][87426] Updated weights for policy 1, policy_version 184460 (0.0008) -[2023-11-28 05:03:05,025][87426] Updated weights for policy 1, policy_version 184470 (0.0008) -[2023-11-28 05:03:05,406][87426] Updated weights for policy 1, policy_version 184480 (0.0008) -[2023-11-28 05:03:05,576][87424] Updated weights for policy 0, policy_version 184937 (0.0009) -[2023-11-28 05:03:05,959][87424] Updated weights for policy 0, policy_version 184947 (0.0007) -[2023-11-28 05:03:06,342][87424] Updated weights for policy 0, policy_version 184957 (0.0008) -[2023-11-28 05:03:06,963][87426] Updated weights for policy 1, policy_version 184490 (0.0010) -[2023-11-28 05:03:07,343][87426] Updated weights for policy 1, policy_version 184500 (0.0011) -[2023-11-28 05:03:07,722][87426] Updated weights for policy 1, policy_version 184510 (0.0007) -[2023-11-28 05:03:08,406][87424] Updated weights for policy 0, policy_version 184967 (0.0010) -[2023-11-28 05:03:08,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 94584832. Throughput: 0: 2737.2, 1: 2711.6. Samples: 94601868. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:08,445][86177] Avg episode reward: [(0, '-501.950'), (1, '-572.650')] -[2023-11-28 05:03:08,789][87424] Updated weights for policy 0, policy_version 184977 (0.0008) -[2023-11-28 05:03:09,173][87424] Updated weights for policy 0, policy_version 184987 (0.0011) -[2023-11-28 05:03:09,728][87426] Updated weights for policy 1, policy_version 184520 (0.0007) -[2023-11-28 05:03:10,110][87426] Updated weights for policy 1, policy_version 184530 (0.0011) -[2023-11-28 05:03:10,492][87426] Updated weights for policy 1, policy_version 184540 (0.0010) -[2023-11-28 05:03:11,136][87424] Updated weights for policy 0, policy_version 184997 (0.0010) -[2023-11-28 05:03:11,513][87424] Updated weights for policy 0, policy_version 185007 (0.0012) -[2023-11-28 05:03:11,918][87424] Updated weights for policy 0, policy_version 185017 (0.0012) -[2023-11-28 05:03:12,513][87426] Updated weights for policy 1, policy_version 184550 (0.0012) -[2023-11-28 05:03:12,891][87426] Updated weights for policy 1, policy_version 184560 (0.0011) -[2023-11-28 05:03:13,281][87426] Updated weights for policy 1, policy_version 184570 (0.0011) -[2023-11-28 05:03:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 94609408. Throughput: 0: 2722.2, 1: 2720.8. Samples: 94625824. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:13,445][86177] Avg episode reward: [(0, '-502.100'), (1, '-581.920')] -[2023-11-28 05:03:14,515][87424] Updated weights for policy 0, policy_version 185027 (0.0012) -[2023-11-28 05:03:14,904][87424] Updated weights for policy 0, policy_version 185037 (0.0008) -[2023-11-28 05:03:15,275][87424] Updated weights for policy 0, policy_version 185047 (0.0008) -[2023-11-28 05:03:15,490][87426] Updated weights for policy 1, policy_version 184580 (0.0010) -[2023-11-28 05:03:15,872][87426] Updated weights for policy 1, policy_version 184590 (0.0012) -[2023-11-28 05:03:16,245][87426] Updated weights for policy 1, policy_version 184600 (0.0011) -[2023-11-28 05:03:17,560][87424] Updated weights for policy 0, policy_version 185057 (0.0010) -[2023-11-28 05:03:17,945][87424] Updated weights for policy 0, policy_version 185067 (0.0012) -[2023-11-28 05:03:18,334][87424] Updated weights for policy 0, policy_version 185077 (0.0012) -[2023-11-28 05:03:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 94633984. Throughput: 0: 2713.5, 1: 2736.2. Samples: 94650316. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:18,445][86177] Avg episode reward: [(0, '-504.280'), (1, '-540.190')] -[2023-11-28 05:03:18,549][87426] Updated weights for policy 1, policy_version 184610 (0.0012) -[2023-11-28 05:03:18,724][87424] Updated weights for policy 0, policy_version 185087 (0.0011) -[2023-11-28 05:03:18,930][87426] Updated weights for policy 1, policy_version 184620 (0.0008) -[2023-11-28 05:03:19,307][87426] Updated weights for policy 1, policy_version 184630 (0.0010) -[2023-11-28 05:03:19,681][87426] Updated weights for policy 1, policy_version 184640 (0.0008) -[2023-11-28 05:03:20,769][87424] Updated weights for policy 0, policy_version 185097 (0.0012) -[2023-11-28 05:03:21,148][87424] Updated weights for policy 0, policy_version 185107 (0.0009) -[2023-11-28 05:03:21,530][87424] Updated weights for policy 0, policy_version 185117 (0.0010) -[2023-11-28 05:03:21,767][87426] Updated weights for policy 1, policy_version 184650 (0.0011) -[2023-11-28 05:03:22,151][87426] Updated weights for policy 1, policy_version 184660 (0.0011) -[2023-11-28 05:03:22,531][87426] Updated weights for policy 1, policy_version 184670 (0.0011) -[2023-11-28 05:03:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 94666752. Throughput: 0: 2736.1, 1: 2751.9. Samples: 94683728. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:23,445][86177] Avg episode reward: [(0, '-514.310'), (1, '-523.920')] -[2023-11-28 05:03:23,552][87424] Updated weights for policy 0, policy_version 185127 (0.0011) -[2023-11-28 05:03:23,933][87424] Updated weights for policy 0, policy_version 185137 (0.0012) -[2023-11-28 05:03:24,308][87424] Updated weights for policy 0, policy_version 185147 (0.0008) -[2023-11-28 05:03:24,766][87426] Updated weights for policy 1, policy_version 184680 (0.0011) -[2023-11-28 05:03:25,147][87426] Updated weights for policy 1, policy_version 184690 (0.0012) -[2023-11-28 05:03:25,523][87426] Updated weights for policy 1, policy_version 184700 (0.0012) -[2023-11-28 05:03:26,329][87424] Updated weights for policy 0, policy_version 185157 (0.0009) -[2023-11-28 05:03:26,716][87424] Updated weights for policy 0, policy_version 185167 (0.0007) -[2023-11-28 05:03:27,113][87424] Updated weights for policy 0, policy_version 185177 (0.0010) -[2023-11-28 05:03:27,226][87426] Updated weights for policy 1, policy_version 184710 (0.0011) -[2023-11-28 05:03:27,608][87426] Updated weights for policy 1, policy_version 184720 (0.0012) -[2023-11-28 05:03:27,987][87426] Updated weights for policy 1, policy_version 184730 (0.0010) -[2023-11-28 05:03:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 94699520. Throughput: 0: 2739.1, 1: 2774.6. Samples: 94708584. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:28,445][86177] Avg episode reward: [(0, '-516.200'), (1, '-567.320')] -[2023-11-28 05:03:29,508][87424] Updated weights for policy 0, policy_version 185187 (0.0011) -[2023-11-28 05:03:29,887][87424] Updated weights for policy 0, policy_version 185197 (0.0007) -[2023-11-28 05:03:30,280][87424] Updated weights for policy 0, policy_version 185207 (0.0008) -[2023-11-28 05:03:30,371][87426] Updated weights for policy 1, policy_version 184740 (0.0008) -[2023-11-28 05:03:30,747][87426] Updated weights for policy 1, policy_version 184750 (0.0008) -[2023-11-28 05:03:31,125][87426] Updated weights for policy 1, policy_version 184760 (0.0008) -[2023-11-28 05:03:32,247][87424] Updated weights for policy 0, policy_version 185217 (0.0008) -[2023-11-28 05:03:32,633][87424] Updated weights for policy 0, policy_version 185227 (0.0008) -[2023-11-28 05:03:33,017][87424] Updated weights for policy 0, policy_version 185237 (0.0009) -[2023-11-28 05:03:33,319][87426] Updated weights for policy 1, policy_version 184770 (0.0007) -[2023-11-28 05:03:33,403][87424] Updated weights for policy 0, policy_version 185247 (0.0009) -[2023-11-28 05:03:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 94724096. Throughput: 0: 2737.5, 1: 2774.8. Samples: 94733476. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:33,445][86177] Avg episode reward: [(0, '-510.930'), (1, '-566.690')] -[2023-11-28 05:03:33,700][87426] Updated weights for policy 1, policy_version 184780 (0.0007) -[2023-11-28 05:03:34,081][87426] Updated weights for policy 1, policy_version 184790 (0.0007) -[2023-11-28 05:03:34,465][87426] Updated weights for policy 1, policy_version 184800 (0.0007) -[2023-11-28 05:03:35,443][87424] Updated weights for policy 0, policy_version 185257 (0.0011) -[2023-11-28 05:03:35,832][87424] Updated weights for policy 0, policy_version 185267 (0.0012) -[2023-11-28 05:03:36,204][87424] Updated weights for policy 0, policy_version 185277 (0.0012) -[2023-11-28 05:03:36,797][87426] Updated weights for policy 1, policy_version 184810 (0.0012) -[2023-11-28 05:03:37,177][87426] Updated weights for policy 1, policy_version 184820 (0.0012) -[2023-11-28 05:03:37,559][87426] Updated weights for policy 1, policy_version 184830 (0.0012) -[2023-11-28 05:03:38,015][87424] Updated weights for policy 0, policy_version 185287 (0.0012) -[2023-11-28 05:03:38,404][87424] Updated weights for policy 0, policy_version 185297 (0.0012) -[2023-11-28 05:03:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 94748672. Throughput: 0: 2763.3, 1: 2757.8. Samples: 94766988. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:38,445][86177] Avg episode reward: [(0, '-513.540'), (1, '-554.850')] -[2023-11-28 05:03:38,794][87424] Updated weights for policy 0, policy_version 185307 (0.0012) -[2023-11-28 05:03:40,178][87426] Updated weights for policy 1, policy_version 184840 (0.0011) -[2023-11-28 05:03:40,551][87426] Updated weights for policy 1, policy_version 184850 (0.0009) -[2023-11-28 05:03:40,934][87426] Updated weights for policy 1, policy_version 184860 (0.0008) -[2023-11-28 05:03:41,385][87424] Updated weights for policy 0, policy_version 185317 (0.0012) -[2023-11-28 05:03:41,782][87424] Updated weights for policy 0, policy_version 185327 (0.0012) -[2023-11-28 05:03:42,164][87424] Updated weights for policy 0, policy_version 185337 (0.0012) -[2023-11-28 05:03:43,216][87426] Updated weights for policy 1, policy_version 184870 (0.0010) -[2023-11-28 05:03:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 94773248. Throughput: 0: 2749.0, 1: 2755.9. Samples: 94791408. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:43,445][86177] Avg episode reward: [(0, '-505.410'), (1, '-547.990')] -[2023-11-28 05:03:43,606][87426] Updated weights for policy 1, policy_version 184880 (0.0011) -[2023-11-28 05:03:43,988][87426] Updated weights for policy 1, policy_version 184890 (0.0008) -[2023-11-28 05:03:44,399][87424] Updated weights for policy 0, policy_version 185347 (0.0011) -[2023-11-28 05:03:44,776][87424] Updated weights for policy 0, policy_version 185357 (0.0007) -[2023-11-28 05:03:45,159][87424] Updated weights for policy 0, policy_version 185367 (0.0007) -[2023-11-28 05:03:45,650][87426] Updated weights for policy 1, policy_version 184900 (0.0010) -[2023-11-28 05:03:46,029][87426] Updated weights for policy 1, policy_version 184910 (0.0012) -[2023-11-28 05:03:46,409][87426] Updated weights for policy 1, policy_version 184920 (0.0010) -[2023-11-28 05:03:46,905][87424] Updated weights for policy 0, policy_version 185377 (0.0008) -[2023-11-28 05:03:47,287][87424] Updated weights for policy 0, policy_version 185387 (0.0012) -[2023-11-28 05:03:47,665][87424] Updated weights for policy 0, policy_version 185397 (0.0012) -[2023-11-28 05:03:48,031][87424] Updated weights for policy 0, policy_version 185407 (0.0012) -[2023-11-28 05:03:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 94806016. Throughput: 0: 2744.9, 1: 2747.5. Samples: 94816220. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:48,445][86177] Avg episode reward: [(0, '-505.290'), (1, '-503.620')] -[2023-11-28 05:03:48,794][87426] Updated weights for policy 1, policy_version 184930 (0.0009) -[2023-11-28 05:03:49,161][87426] Updated weights for policy 1, policy_version 184940 (0.0012) -[2023-11-28 05:03:49,536][87426] Updated weights for policy 1, policy_version 184950 (0.0012) -[2023-11-28 05:03:49,919][87426] Updated weights for policy 1, policy_version 184960 (0.0012) -[2023-11-28 05:03:50,478][87424] Updated weights for policy 0, policy_version 185417 (0.0010) -[2023-11-28 05:03:50,849][87424] Updated weights for policy 0, policy_version 185427 (0.0011) -[2023-11-28 05:03:51,230][87424] Updated weights for policy 0, policy_version 185437 (0.0012) -[2023-11-28 05:03:51,893][87426] Updated weights for policy 1, policy_version 184970 (0.0010) -[2023-11-28 05:03:52,269][87426] Updated weights for policy 1, policy_version 184980 (0.0011) -[2023-11-28 05:03:52,657][87426] Updated weights for policy 1, policy_version 184990 (0.0010) -[2023-11-28 05:03:53,286][87424] Updated weights for policy 0, policy_version 185447 (0.0011) -[2023-11-28 05:03:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.5, 300 sec: 5415.1). Total num frames: 94830592. Throughput: 0: 2734.8, 1: 2720.4. Samples: 94847352. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:53,445][86177] Avg episode reward: [(0, '-506.880'), (1, '-500.740')] -[2023-11-28 05:03:53,666][87424] Updated weights for policy 0, policy_version 185457 (0.0012) -[2023-11-28 05:03:54,054][87424] Updated weights for policy 0, policy_version 185467 (0.0012) -[2023-11-28 05:03:54,576][87426] Updated weights for policy 1, policy_version 185000 (0.0012) -[2023-11-28 05:03:54,959][87426] Updated weights for policy 1, policy_version 185010 (0.0012) -[2023-11-28 05:03:55,328][87426] Updated weights for policy 1, policy_version 185020 (0.0012) -[2023-11-28 05:03:56,188][87424] Updated weights for policy 0, policy_version 185477 (0.0012) -[2023-11-28 05:03:56,567][87424] Updated weights for policy 0, policy_version 185487 (0.0007) -[2023-11-28 05:03:56,949][87424] Updated weights for policy 0, policy_version 185497 (0.0009) -[2023-11-28 05:03:57,929][87426] Updated weights for policy 1, policy_version 185030 (0.0009) -[2023-11-28 05:03:58,316][87426] Updated weights for policy 1, policy_version 185040 (0.0008) -[2023-11-28 05:03:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 94855168. Throughput: 0: 2743.5, 1: 2738.2. Samples: 94872504. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:03:58,446][86177] Avg episode reward: [(0, '-507.630'), (1, '-584.900')] -[2023-11-28 05:03:58,694][87426] Updated weights for policy 1, policy_version 185050 (0.0009) -[2023-11-28 05:03:59,295][87424] Updated weights for policy 0, policy_version 185507 (0.0010) -[2023-11-28 05:03:59,673][87424] Updated weights for policy 0, policy_version 185517 (0.0008) -[2023-11-28 05:04:00,042][87424] Updated weights for policy 0, policy_version 185527 (0.0008) -[2023-11-28 05:04:01,066][87426] Updated weights for policy 1, policy_version 185060 (0.0008) -[2023-11-28 05:04:01,447][87426] Updated weights for policy 1, policy_version 185070 (0.0007) -[2023-11-28 05:04:01,826][87426] Updated weights for policy 1, policy_version 185080 (0.0008) -[2023-11-28 05:04:02,408][87424] Updated weights for policy 0, policy_version 185537 (0.0008) -[2023-11-28 05:04:02,797][87424] Updated weights for policy 0, policy_version 185547 (0.0008) -[2023-11-28 05:04:03,171][87424] Updated weights for policy 0, policy_version 185557 (0.0008) -[2023-11-28 05:04:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 94879744. Throughput: 0: 2732.4, 1: 2718.7. Samples: 94895612. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:04:03,445][86177] Avg episode reward: [(0, '-518.900'), (1, '-623.410')] -[2023-11-28 05:04:03,559][87424] Updated weights for policy 0, policy_version 185567 (0.0007) -[2023-11-28 05:04:04,176][87426] Updated weights for policy 1, policy_version 185090 (0.0010) -[2023-11-28 05:04:04,566][87426] Updated weights for policy 1, policy_version 185100 (0.0008) -[2023-11-28 05:04:04,936][87426] Updated weights for policy 1, policy_version 185110 (0.0009) -[2023-11-28 05:04:05,313][87426] Updated weights for policy 1, policy_version 185120 (0.0008) -[2023-11-28 05:04:05,973][87424] Updated weights for policy 0, policy_version 185577 (0.0007) -[2023-11-28 05:04:06,350][87424] Updated weights for policy 0, policy_version 185587 (0.0007) -[2023-11-28 05:04:06,730][87424] Updated weights for policy 0, policy_version 185597 (0.0008) -[2023-11-28 05:04:07,763][87426] Updated weights for policy 1, policy_version 185130 (0.0009) -[2023-11-28 05:04:08,157][87426] Updated weights for policy 1, policy_version 185140 (0.0010) -[2023-11-28 05:04:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 94904320. Throughput: 0: 2708.3, 1: 2704.5. Samples: 94927304. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:04:08,445][86177] Avg episode reward: [(0, '-543.260'), (1, '-646.010')] -[2023-11-28 05:04:08,531][87426] Updated weights for policy 1, policy_version 185150 (0.0008) -[2023-11-28 05:04:08,969][87424] Updated weights for policy 0, policy_version 185607 (0.0009) -[2023-11-28 05:04:09,352][87424] Updated weights for policy 0, policy_version 185617 (0.0009) -[2023-11-28 05:04:09,733][87424] Updated weights for policy 0, policy_version 185627 (0.0008) -[2023-11-28 05:04:10,888][87426] Updated weights for policy 1, policy_version 185160 (0.0011) -[2023-11-28 05:04:11,269][87426] Updated weights for policy 1, policy_version 185170 (0.0012) -[2023-11-28 05:04:11,655][87426] Updated weights for policy 1, policy_version 185180 (0.0012) -[2023-11-28 05:04:12,130][87424] Updated weights for policy 0, policy_version 185637 (0.0010) -[2023-11-28 05:04:12,507][87424] Updated weights for policy 0, policy_version 185647 (0.0012) -[2023-11-28 05:04:12,891][87424] Updated weights for policy 0, policy_version 185657 (0.0012) -[2023-11-28 05:04:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 94937088. Throughput: 0: 2698.7, 1: 2684.3. Samples: 94950816. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 05:04:13,445][86177] Avg episode reward: [(0, '-544.180'), (1, '-680.070')] -[2023-11-28 05:04:13,727][87426] Updated weights for policy 1, policy_version 185190 (0.0013) -[2023-11-28 05:04:14,107][87426] Updated weights for policy 1, policy_version 185200 (0.0011) -[2023-11-28 05:04:14,487][87426] Updated weights for policy 1, policy_version 185210 (0.0012) -[2023-11-28 05:04:14,780][87424] Updated weights for policy 0, policy_version 185667 (0.0011) -[2023-11-28 05:04:15,167][87424] Updated weights for policy 0, policy_version 185677 (0.0009) -[2023-11-28 05:04:15,548][87424] Updated weights for policy 0, policy_version 185687 (0.0011) -[2023-11-28 05:04:16,481][87426] Updated weights for policy 1, policy_version 185220 (0.0011) -[2023-11-28 05:04:16,857][87426] Updated weights for policy 1, policy_version 185230 (0.0009) -[2023-11-28 05:04:17,236][87426] Updated weights for policy 1, policy_version 185240 (0.0011) -[2023-11-28 05:04:17,709][87424] Updated weights for policy 0, policy_version 185697 (0.0012) -[2023-11-28 05:04:18,093][87424] Updated weights for policy 0, policy_version 185707 (0.0012) -[2023-11-28 05:04:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 94961664. Throughput: 0: 2690.5, 1: 2702.1. Samples: 94976144. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:04:18,446][86177] Avg episode reward: [(0, '-550.130'), (1, '-634.130')] -[2023-11-28 05:04:18,460][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000185248_47423488.pth... -[2023-11-28 05:04:18,473][87424] Updated weights for policy 0, policy_version 185717 (0.0011) -[2023-11-28 05:04:18,494][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000182720_46776320.pth -[2023-11-28 05:04:18,863][87424] Updated weights for policy 0, policy_version 185727 (0.0011) -[2023-11-28 05:04:18,899][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000185728_47546368.pth... -[2023-11-28 05:04:18,947][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000183168_46891008.pth -[2023-11-28 05:04:19,349][87426] Updated weights for policy 1, policy_version 185250 (0.0012) -[2023-11-28 05:04:19,720][87426] Updated weights for policy 1, policy_version 185260 (0.0012) -[2023-11-28 05:04:20,104][87426] Updated weights for policy 1, policy_version 185270 (0.0012) -[2023-11-28 05:04:20,484][87426] Updated weights for policy 1, policy_version 185280 (0.0012) -[2023-11-28 05:04:20,931][87424] Updated weights for policy 0, policy_version 185737 (0.0012) -[2023-11-28 05:04:21,322][87424] Updated weights for policy 0, policy_version 185747 (0.0011) -[2023-11-28 05:04:21,700][87424] Updated weights for policy 0, policy_version 185757 (0.0011) -[2023-11-28 05:04:22,299][87426] Updated weights for policy 1, policy_version 185290 (0.0012) -[2023-11-28 05:04:22,669][87426] Updated weights for policy 1, policy_version 185300 (0.0008) -[2023-11-28 05:04:23,049][87426] Updated weights for policy 1, policy_version 185310 (0.0010) -[2023-11-28 05:04:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 94994432. Throughput: 0: 2674.6, 1: 2691.3. Samples: 95008452. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:04:23,445][86177] Avg episode reward: [(0, '-534.960'), (1, '-592.840')] -[2023-11-28 05:04:24,131][87424] Updated weights for policy 0, policy_version 185767 (0.0012) -[2023-11-28 05:04:24,516][87424] Updated weights for policy 0, policy_version 185777 (0.0012) -[2023-11-28 05:04:24,897][87424] Updated weights for policy 0, policy_version 185787 (0.0012) -[2023-11-28 05:04:25,416][87426] Updated weights for policy 1, policy_version 185320 (0.0008) -[2023-11-28 05:04:25,794][87426] Updated weights for policy 1, policy_version 185330 (0.0007) -[2023-11-28 05:04:26,169][87426] Updated weights for policy 1, policy_version 185340 (0.0007) -[2023-11-28 05:04:26,947][87424] Updated weights for policy 0, policy_version 185797 (0.0012) -[2023-11-28 05:04:27,333][87424] Updated weights for policy 0, policy_version 185807 (0.0012) -[2023-11-28 05:04:27,717][87424] Updated weights for policy 0, policy_version 185817 (0.0011) -[2023-11-28 05:04:28,101][87426] Updated weights for policy 1, policy_version 185350 (0.0009) -[2023-11-28 05:04:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 95019008. Throughput: 0: 2672.5, 1: 2711.0. Samples: 95033668. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:04:28,445][86177] Avg episode reward: [(0, '-522.530'), (1, '-569.400')] -[2023-11-28 05:04:28,483][87426] Updated weights for policy 1, policy_version 185360 (0.0008) -[2023-11-28 05:04:28,872][87426] Updated weights for policy 1, policy_version 185370 (0.0008) -[2023-11-28 05:04:29,846][87424] Updated weights for policy 0, policy_version 185827 (0.0012) -[2023-11-28 05:04:30,238][87424] Updated weights for policy 0, policy_version 185837 (0.0011) -[2023-11-28 05:04:30,611][87424] Updated weights for policy 0, policy_version 185847 (0.0009) -[2023-11-28 05:04:31,105][87426] Updated weights for policy 1, policy_version 185380 (0.0011) -[2023-11-28 05:04:31,482][87426] Updated weights for policy 1, policy_version 185390 (0.0007) -[2023-11-28 05:04:31,862][87426] Updated weights for policy 1, policy_version 185400 (0.0013) -[2023-11-28 05:04:32,734][87424] Updated weights for policy 0, policy_version 185857 (0.0009) -[2023-11-28 05:04:33,119][87424] Updated weights for policy 0, policy_version 185867 (0.0011) -[2023-11-28 05:04:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 95043584. Throughput: 0: 2686.0, 1: 2717.2. Samples: 95059368. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:04:33,446][86177] Avg episode reward: [(0, '-530.980'), (1, '-565.460')] -[2023-11-28 05:04:33,504][87424] Updated weights for policy 0, policy_version 185877 (0.0007) -[2023-11-28 05:04:33,730][87426] Updated weights for policy 1, policy_version 185410 (0.0010) -[2023-11-28 05:04:33,890][87424] Updated weights for policy 0, policy_version 185887 (0.0008) -[2023-11-28 05:04:34,110][87426] Updated weights for policy 1, policy_version 185420 (0.0011) -[2023-11-28 05:04:34,491][87426] Updated weights for policy 1, policy_version 185430 (0.0011) -[2023-11-28 05:04:34,873][87426] Updated weights for policy 1, policy_version 185440 (0.0013) -[2023-11-28 05:04:36,054][87424] Updated weights for policy 0, policy_version 185897 (0.0009) -[2023-11-28 05:04:36,443][87424] Updated weights for policy 0, policy_version 185907 (0.0007) -[2023-11-28 05:04:36,723][87426] Updated weights for policy 1, policy_version 185450 (0.0011) -[2023-11-28 05:04:36,831][87424] Updated weights for policy 0, policy_version 185917 (0.0008) -[2023-11-28 05:04:37,105][87426] Updated weights for policy 1, policy_version 185460 (0.0012) -[2023-11-28 05:04:37,480][87426] Updated weights for policy 1, policy_version 185470 (0.0012) -[2023-11-28 05:04:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95076352. Throughput: 0: 2705.4, 1: 2734.5. Samples: 95092148. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:04:38,445][86177] Avg episode reward: [(0, '-528.520'), (1, '-569.510')] -[2023-11-28 05:04:38,744][87424] Updated weights for policy 0, policy_version 185927 (0.0008) -[2023-11-28 05:04:39,126][87424] Updated weights for policy 0, policy_version 185937 (0.0008) -[2023-11-28 05:04:39,517][87424] Updated weights for policy 0, policy_version 185947 (0.0008) -[2023-11-28 05:04:40,049][87426] Updated weights for policy 1, policy_version 185480 (0.0012) -[2023-11-28 05:04:40,428][87426] Updated weights for policy 1, policy_version 185490 (0.0012) -[2023-11-28 05:04:40,806][87426] Updated weights for policy 1, policy_version 185500 (0.0009) -[2023-11-28 05:04:41,320][87424] Updated weights for policy 0, policy_version 185957 (0.0010) -[2023-11-28 05:04:41,696][87424] Updated weights for policy 0, policy_version 185967 (0.0012) -[2023-11-28 05:04:42,070][87424] Updated weights for policy 0, policy_version 185977 (0.0012) -[2023-11-28 05:04:43,013][87426] Updated weights for policy 1, policy_version 185510 (0.0010) -[2023-11-28 05:04:43,390][87426] Updated weights for policy 1, policy_version 185520 (0.0011) -[2023-11-28 05:04:43,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95100928. Throughput: 0: 2708.2, 1: 2705.3. Samples: 95116108. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:04:43,445][86177] Avg episode reward: [(0, '-525.210'), (1, '-573.070')] -[2023-11-28 05:04:43,768][87426] Updated weights for policy 1, policy_version 185530 (0.0008) -[2023-11-28 05:04:44,304][87424] Updated weights for policy 0, policy_version 185987 (0.0010) -[2023-11-28 05:04:44,687][87424] Updated weights for policy 0, policy_version 185997 (0.0008) -[2023-11-28 05:04:45,071][87424] Updated weights for policy 0, policy_version 186007 (0.0010) -[2023-11-28 05:04:45,965][87426] Updated weights for policy 1, policy_version 185540 (0.0008) -[2023-11-28 05:04:46,341][87426] Updated weights for policy 1, policy_version 185550 (0.0007) -[2023-11-28 05:04:46,729][87426] Updated weights for policy 1, policy_version 185560 (0.0007) -[2023-11-28 05:04:47,398][87424] Updated weights for policy 0, policy_version 186017 (0.0010) -[2023-11-28 05:04:47,780][87424] Updated weights for policy 0, policy_version 186027 (0.0011) -[2023-11-28 05:04:48,169][87424] Updated weights for policy 0, policy_version 186037 (0.0012) -[2023-11-28 05:04:48,306][87426] Updated weights for policy 1, policy_version 185570 (0.0008) -[2023-11-28 05:04:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 95125504. Throughput: 0: 2728.4, 1: 2725.1. Samples: 95141020. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:04:48,446][86177] Avg episode reward: [(0, '-510.010'), (1, '-596.060')] -[2023-11-28 05:04:48,543][87424] Updated weights for policy 0, policy_version 186047 (0.0010) -[2023-11-28 05:04:48,685][87426] Updated weights for policy 1, policy_version 185580 (0.0012) -[2023-11-28 05:04:49,056][87426] Updated weights for policy 1, policy_version 185590 (0.0011) -[2023-11-28 05:04:49,439][87426] Updated weights for policy 1, policy_version 185600 (0.0011) -[2023-11-28 05:04:51,163][87424] Updated weights for policy 0, policy_version 186057 (0.0012) -[2023-11-28 05:04:51,538][87424] Updated weights for policy 0, policy_version 186067 (0.0012) -[2023-11-28 05:04:51,878][87426] Updated weights for policy 1, policy_version 185610 (0.0011) -[2023-11-28 05:04:51,921][87424] Updated weights for policy 0, policy_version 186077 (0.0011) -[2023-11-28 05:04:52,255][87426] Updated weights for policy 1, policy_version 185620 (0.0012) -[2023-11-28 05:04:52,633][87426] Updated weights for policy 1, policy_version 185630 (0.0012) -[2023-11-28 05:04:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95158272. Throughput: 0: 2717.4, 1: 2756.9. Samples: 95173648. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:04:53,445][86177] Avg episode reward: [(0, '-497.880'), (1, '-600.310')] -[2023-11-28 05:04:54,164][87424] Updated weights for policy 0, policy_version 186087 (0.0012) -[2023-11-28 05:04:54,546][87424] Updated weights for policy 0, policy_version 186097 (0.0011) -[2023-11-28 05:04:54,928][87424] Updated weights for policy 0, policy_version 186107 (0.0012) -[2023-11-28 05:04:54,982][87426] Updated weights for policy 1, policy_version 185640 (0.0011) -[2023-11-28 05:04:55,359][87426] Updated weights for policy 1, policy_version 185650 (0.0012) -[2023-11-28 05:04:55,753][87426] Updated weights for policy 1, policy_version 185660 (0.0010) -[2023-11-28 05:04:57,031][87424] Updated weights for policy 0, policy_version 186117 (0.0010) -[2023-11-28 05:04:57,409][87424] Updated weights for policy 0, policy_version 186127 (0.0007) -[2023-11-28 05:04:57,559][87426] Updated weights for policy 1, policy_version 185670 (0.0010) -[2023-11-28 05:04:57,790][87424] Updated weights for policy 0, policy_version 186137 (0.0007) -[2023-11-28 05:04:57,939][87426] Updated weights for policy 1, policy_version 185680 (0.0011) -[2023-11-28 05:04:58,325][87426] Updated weights for policy 1, policy_version 185690 (0.0012) -[2023-11-28 05:04:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95182848. Throughput: 0: 2719.5, 1: 2781.1. Samples: 95198348. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:04:58,445][86177] Avg episode reward: [(0, '-497.580'), (1, '-558.120')] -[2023-11-28 05:04:59,702][87424] Updated weights for policy 0, policy_version 186147 (0.0011) -[2023-11-28 05:05:00,083][87424] Updated weights for policy 0, policy_version 186157 (0.0012) -[2023-11-28 05:05:00,473][87424] Updated weights for policy 0, policy_version 186167 (0.0011) -[2023-11-28 05:05:00,534][87426] Updated weights for policy 1, policy_version 185700 (0.0011) -[2023-11-28 05:05:00,918][87426] Updated weights for policy 1, policy_version 185710 (0.0009) -[2023-11-28 05:05:01,309][87426] Updated weights for policy 1, policy_version 185720 (0.0008) -[2023-11-28 05:05:02,967][87424] Updated weights for policy 0, policy_version 186177 (0.0009) -[2023-11-28 05:05:03,348][87424] Updated weights for policy 0, policy_version 186187 (0.0012) -[2023-11-28 05:05:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 95207424. Throughput: 0: 2720.2, 1: 2772.9. Samples: 95223332. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:05:03,445][86177] Avg episode reward: [(0, '-501.430'), (1, '-557.600')] -[2023-11-28 05:05:03,734][87426] Updated weights for policy 1, policy_version 185730 (0.0008) -[2023-11-28 05:05:03,738][87424] Updated weights for policy 0, policy_version 186197 (0.0008) -[2023-11-28 05:05:04,118][87424] Updated weights for policy 0, policy_version 186207 (0.0007) -[2023-11-28 05:05:04,119][87426] Updated weights for policy 1, policy_version 185740 (0.0011) -[2023-11-28 05:05:04,502][87426] Updated weights for policy 1, policy_version 185750 (0.0011) -[2023-11-28 05:05:04,879][87426] Updated weights for policy 1, policy_version 185760 (0.0009) -[2023-11-28 05:05:06,644][87424] Updated weights for policy 0, policy_version 186217 (0.0008) -[2023-11-28 05:05:06,795][87426] Updated weights for policy 1, policy_version 185770 (0.0010) -[2023-11-28 05:05:07,026][87424] Updated weights for policy 0, policy_version 186227 (0.0008) -[2023-11-28 05:05:07,169][87426] Updated weights for policy 1, policy_version 185780 (0.0012) -[2023-11-28 05:05:07,414][87424] Updated weights for policy 0, policy_version 186237 (0.0009) -[2023-11-28 05:05:07,548][87426] Updated weights for policy 1, policy_version 185790 (0.0012) -[2023-11-28 05:05:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 95240192. Throughput: 0: 2702.4, 1: 2778.7. Samples: 95255100. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:05:08,445][86177] Avg episode reward: [(0, '-504.270'), (1, '-545.370')] -[2023-11-28 05:05:09,732][87426] Updated weights for policy 1, policy_version 185800 (0.0011) -[2023-11-28 05:05:09,789][87424] Updated weights for policy 0, policy_version 186247 (0.0012) -[2023-11-28 05:05:10,119][87426] Updated weights for policy 1, policy_version 185810 (0.0010) -[2023-11-28 05:05:10,159][87424] Updated weights for policy 0, policy_version 186257 (0.0012) -[2023-11-28 05:05:10,488][87426] Updated weights for policy 1, policy_version 185820 (0.0010) -[2023-11-28 05:05:10,542][87424] Updated weights for policy 0, policy_version 186267 (0.0010) -[2023-11-28 05:05:12,637][87424] Updated weights for policy 0, policy_version 186277 (0.0008) -[2023-11-28 05:05:12,725][87426] Updated weights for policy 1, policy_version 185830 (0.0011) -[2023-11-28 05:05:13,020][87424] Updated weights for policy 0, policy_version 186287 (0.0011) -[2023-11-28 05:05:13,102][87426] Updated weights for policy 1, policy_version 185840 (0.0011) -[2023-11-28 05:05:13,398][87424] Updated weights for policy 0, policy_version 186297 (0.0011) -[2023-11-28 05:05:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 95256576. Throughput: 0: 2715.6, 1: 2756.3. Samples: 95279900. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:05:13,445][86177] Avg episode reward: [(0, '-501.060'), (1, '-567.220')] -[2023-11-28 05:05:13,476][87426] Updated weights for policy 1, policy_version 185850 (0.0011) -[2023-11-28 05:05:15,481][87424] Updated weights for policy 0, policy_version 186307 (0.0011) -[2023-11-28 05:05:15,741][87426] Updated weights for policy 1, policy_version 185860 (0.0011) -[2023-11-28 05:05:15,866][87424] Updated weights for policy 0, policy_version 186317 (0.0011) -[2023-11-28 05:05:16,119][87426] Updated weights for policy 1, policy_version 185870 (0.0010) -[2023-11-28 05:05:16,245][87424] Updated weights for policy 0, policy_version 186327 (0.0011) -[2023-11-28 05:05:16,500][87426] Updated weights for policy 1, policy_version 185880 (0.0008) -[2023-11-28 05:05:17,901][87424] Updated weights for policy 0, policy_version 186337 (0.0009) -[2023-11-28 05:05:18,279][87424] Updated weights for policy 0, policy_version 186347 (0.0011) -[2023-11-28 05:05:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 95289344. Throughput: 0: 2712.4, 1: 2746.1. Samples: 95305004. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:05:18,446][86177] Avg episode reward: [(0, '-497.820'), (1, '-566.220')] -[2023-11-28 05:05:18,663][87424] Updated weights for policy 0, policy_version 186357 (0.0012) -[2023-11-28 05:05:18,739][87426] Updated weights for policy 1, policy_version 185890 (0.0011) -[2023-11-28 05:05:19,038][87424] Updated weights for policy 0, policy_version 186367 (0.0009) -[2023-11-28 05:05:19,120][87426] Updated weights for policy 1, policy_version 185900 (0.0009) -[2023-11-28 05:05:19,500][87426] Updated weights for policy 1, policy_version 185910 (0.0007) -[2023-11-28 05:05:19,880][87426] Updated weights for policy 1, policy_version 185920 (0.0008) -[2023-11-28 05:05:21,567][87424] Updated weights for policy 0, policy_version 186377 (0.0012) -[2023-11-28 05:05:21,963][87424] Updated weights for policy 0, policy_version 186387 (0.0011) -[2023-11-28 05:05:22,161][87426] Updated weights for policy 1, policy_version 185930 (0.0010) -[2023-11-28 05:05:22,348][87424] Updated weights for policy 0, policy_version 186397 (0.0008) -[2023-11-28 05:05:22,541][87426] Updated weights for policy 1, policy_version 185940 (0.0010) -[2023-11-28 05:05:22,921][87426] Updated weights for policy 1, policy_version 185950 (0.0011) -[2023-11-28 05:05:23,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 95322112. Throughput: 0: 2703.0, 1: 2749.8. Samples: 95337524. Policy #0 lag: (min: 31.0, avg: 55.3, max: 60.0) -[2023-11-28 05:05:23,445][86177] Avg episode reward: [(0, '-499.140'), (1, '-564.210')] -[2023-11-28 05:05:24,711][87424] Updated weights for policy 0, policy_version 186407 (0.0011) -[2023-11-28 05:05:25,085][87424] Updated weights for policy 0, policy_version 186417 (0.0012) -[2023-11-28 05:05:25,441][87426] Updated weights for policy 1, policy_version 185960 (0.0011) -[2023-11-28 05:05:25,473][87424] Updated weights for policy 0, policy_version 186427 (0.0011) -[2023-11-28 05:05:25,822][87426] Updated weights for policy 1, policy_version 185970 (0.0012) -[2023-11-28 05:05:26,201][87426] Updated weights for policy 1, policy_version 185980 (0.0012) -[2023-11-28 05:05:27,165][87424] Updated weights for policy 0, policy_version 186437 (0.0012) -[2023-11-28 05:05:27,541][87424] Updated weights for policy 0, policy_version 186447 (0.0012) -[2023-11-28 05:05:27,928][87424] Updated weights for policy 0, policy_version 186457 (0.0012) -[2023-11-28 05:05:27,960][87426] Updated weights for policy 1, policy_version 185990 (0.0011) -[2023-11-28 05:05:28,332][87426] Updated weights for policy 1, policy_version 186000 (0.0011) -[2023-11-28 05:05:28,444][86177] Fps is (10 sec: 5734.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95346688. Throughput: 0: 2697.4, 1: 2782.0. Samples: 95362684. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:05:28,445][86177] Avg episode reward: [(0, '-497.620'), (1, '-519.120')] -[2023-11-28 05:05:28,709][87426] Updated weights for policy 1, policy_version 186010 (0.0012) -[2023-11-28 05:05:30,048][87424] Updated weights for policy 0, policy_version 186467 (0.0012) -[2023-11-28 05:05:30,434][87424] Updated weights for policy 0, policy_version 186477 (0.0012) -[2023-11-28 05:05:30,821][87424] Updated weights for policy 0, policy_version 186487 (0.0011) -[2023-11-28 05:05:30,932][87426] Updated weights for policy 1, policy_version 186020 (0.0012) -[2023-11-28 05:05:31,300][87426] Updated weights for policy 1, policy_version 186030 (0.0008) -[2023-11-28 05:05:31,681][87426] Updated weights for policy 1, policy_version 186040 (0.0008) -[2023-11-28 05:05:32,862][87424] Updated weights for policy 0, policy_version 186497 (0.0011) -[2023-11-28 05:05:33,245][87424] Updated weights for policy 0, policy_version 186507 (0.0008) -[2023-11-28 05:05:33,425][87426] Updated weights for policy 1, policy_version 186050 (0.0009) -[2023-11-28 05:05:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 95371264. Throughput: 0: 2713.3, 1: 2770.6. Samples: 95387792. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:05:33,445][86177] Avg episode reward: [(0, '-499.810'), (1, '-537.450')] -[2023-11-28 05:05:33,628][87424] Updated weights for policy 0, policy_version 186517 (0.0009) -[2023-11-28 05:05:33,804][87426] Updated weights for policy 1, policy_version 186060 (0.0012) -[2023-11-28 05:05:34,014][87424] Updated weights for policy 0, policy_version 186527 (0.0012) -[2023-11-28 05:05:34,173][87426] Updated weights for policy 1, policy_version 186070 (0.0010) -[2023-11-28 05:05:34,559][87426] Updated weights for policy 1, policy_version 186080 (0.0008) -[2023-11-28 05:05:35,920][87424] Updated weights for policy 0, policy_version 186537 (0.0012) -[2023-11-28 05:05:36,313][87424] Updated weights for policy 0, policy_version 186547 (0.0012) -[2023-11-28 05:05:36,643][87426] Updated weights for policy 1, policy_version 186090 (0.0012) -[2023-11-28 05:05:36,698][87424] Updated weights for policy 0, policy_version 186557 (0.0011) -[2023-11-28 05:05:37,014][87426] Updated weights for policy 1, policy_version 186100 (0.0011) -[2023-11-28 05:05:37,391][87426] Updated weights for policy 1, policy_version 186110 (0.0010) -[2023-11-28 05:05:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 95404032. Throughput: 0: 2739.8, 1: 2729.9. Samples: 95419784. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:05:38,445][86177] Avg episode reward: [(0, '-500.360'), (1, '-542.290')] -[2023-11-28 05:05:39,204][87424] Updated weights for policy 0, policy_version 186567 (0.0012) -[2023-11-28 05:05:39,589][87424] Updated weights for policy 0, policy_version 186577 (0.0010) -[2023-11-28 05:05:39,602][87426] Updated weights for policy 1, policy_version 186120 (0.0011) -[2023-11-28 05:05:39,968][87424] Updated weights for policy 0, policy_version 186587 (0.0011) -[2023-11-28 05:05:39,977][87426] Updated weights for policy 1, policy_version 186130 (0.0012) -[2023-11-28 05:05:40,357][87426] Updated weights for policy 1, policy_version 186140 (0.0011) -[2023-11-28 05:05:42,319][87424] Updated weights for policy 0, policy_version 186597 (0.0009) -[2023-11-28 05:05:42,702][87424] Updated weights for policy 0, policy_version 186607 (0.0010) -[2023-11-28 05:05:42,866][87426] Updated weights for policy 1, policy_version 186150 (0.0012) -[2023-11-28 05:05:43,084][87424] Updated weights for policy 0, policy_version 186617 (0.0009) -[2023-11-28 05:05:43,239][87426] Updated weights for policy 1, policy_version 186160 (0.0008) -[2023-11-28 05:05:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95428608. Throughput: 0: 2741.1, 1: 2719.5. Samples: 95444072. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:05:43,445][86177] Avg episode reward: [(0, '-501.290'), (1, '-546.780')] -[2023-11-28 05:05:43,617][87426] Updated weights for policy 1, policy_version 186170 (0.0008) -[2023-11-28 05:05:45,322][87424] Updated weights for policy 0, policy_version 186627 (0.0009) -[2023-11-28 05:05:45,352][87426] Updated weights for policy 1, policy_version 186180 (0.0008) -[2023-11-28 05:05:45,704][87424] Updated weights for policy 0, policy_version 186637 (0.0012) -[2023-11-28 05:05:45,730][87426] Updated weights for policy 1, policy_version 186190 (0.0009) -[2023-11-28 05:05:46,094][87424] Updated weights for policy 0, policy_version 186647 (0.0009) -[2023-11-28 05:05:46,119][87426] Updated weights for policy 1, policy_version 186200 (0.0008) -[2023-11-28 05:05:48,013][87424] Updated weights for policy 0, policy_version 186657 (0.0008) -[2023-11-28 05:05:48,405][87424] Updated weights for policy 0, policy_version 186667 (0.0012) -[2023-11-28 05:05:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95453184. Throughput: 0: 2715.8, 1: 2733.3. Samples: 95468544. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:05:48,446][86177] Avg episode reward: [(0, '-500.420'), (1, '-551.880')] -[2023-11-28 05:05:48,525][87426] Updated weights for policy 1, policy_version 186210 (0.0011) -[2023-11-28 05:05:48,799][87424] Updated weights for policy 0, policy_version 186677 (0.0008) -[2023-11-28 05:05:48,913][87426] Updated weights for policy 1, policy_version 186220 (0.0008) -[2023-11-28 05:05:49,178][87424] Updated weights for policy 0, policy_version 186687 (0.0012) -[2023-11-28 05:05:49,282][87426] Updated weights for policy 1, policy_version 186230 (0.0007) -[2023-11-28 05:05:49,662][87426] Updated weights for policy 1, policy_version 186240 (0.0007) -[2023-11-28 05:05:51,478][87424] Updated weights for policy 0, policy_version 186697 (0.0010) -[2023-11-28 05:05:51,867][87424] Updated weights for policy 0, policy_version 186707 (0.0010) -[2023-11-28 05:05:52,008][87426] Updated weights for policy 1, policy_version 186250 (0.0010) -[2023-11-28 05:05:52,248][87424] Updated weights for policy 0, policy_version 186717 (0.0010) -[2023-11-28 05:05:52,395][87426] Updated weights for policy 1, policy_version 186260 (0.0011) -[2023-11-28 05:05:52,770][87426] Updated weights for policy 1, policy_version 186270 (0.0012) -[2023-11-28 05:05:53,447][86177] Fps is (10 sec: 5732.8, 60 sec: 5461.1, 300 sec: 5470.5). Total num frames: 95485952. Throughput: 0: 2731.8, 1: 2734.8. Samples: 95501112. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:05:53,448][86177] Avg episode reward: [(0, '-499.990'), (1, '-512.780')] -[2023-11-28 05:05:54,740][87426] Updated weights for policy 1, policy_version 186280 (0.0012) -[2023-11-28 05:05:54,780][87424] Updated weights for policy 0, policy_version 186727 (0.0012) -[2023-11-28 05:05:55,116][87426] Updated weights for policy 1, policy_version 186290 (0.0010) -[2023-11-28 05:05:55,150][87424] Updated weights for policy 0, policy_version 186737 (0.0012) -[2023-11-28 05:05:55,490][87426] Updated weights for policy 1, policy_version 186300 (0.0010) -[2023-11-28 05:05:55,529][87424] Updated weights for policy 0, policy_version 186747 (0.0011) -[2023-11-28 05:05:57,546][87424] Updated weights for policy 0, policy_version 186757 (0.0011) -[2023-11-28 05:05:57,598][87426] Updated weights for policy 1, policy_version 186310 (0.0011) -[2023-11-28 05:05:57,933][87424] Updated weights for policy 0, policy_version 186767 (0.0012) -[2023-11-28 05:05:57,973][87426] Updated weights for policy 1, policy_version 186320 (0.0011) -[2023-11-28 05:05:58,315][87424] Updated weights for policy 0, policy_version 186777 (0.0012) -[2023-11-28 05:05:58,361][87426] Updated weights for policy 1, policy_version 186330 (0.0010) -[2023-11-28 05:05:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 95502336. Throughput: 0: 2725.2, 1: 2726.7. Samples: 95525240. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:05:58,445][86177] Avg episode reward: [(0, '-504.400'), (1, '-547.090')] -[2023-11-28 05:06:00,345][87424] Updated weights for policy 0, policy_version 186787 (0.0012) -[2023-11-28 05:06:00,497][87426] Updated weights for policy 1, policy_version 186340 (0.0009) -[2023-11-28 05:06:00,730][87424] Updated weights for policy 0, policy_version 186797 (0.0008) -[2023-11-28 05:06:00,875][87426] Updated weights for policy 1, policy_version 186350 (0.0012) -[2023-11-28 05:06:01,113][87424] Updated weights for policy 0, policy_version 186807 (0.0008) -[2023-11-28 05:06:01,254][87426] Updated weights for policy 1, policy_version 186360 (0.0011) -[2023-11-28 05:06:02,885][87424] Updated weights for policy 0, policy_version 186817 (0.0008) -[2023-11-28 05:06:03,265][87424] Updated weights for policy 0, policy_version 186827 (0.0012) -[2023-11-28 05:06:03,399][87426] Updated weights for policy 1, policy_version 186370 (0.0011) -[2023-11-28 05:06:03,444][86177] Fps is (10 sec: 4916.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95535104. Throughput: 0: 2733.6, 1: 2725.2. Samples: 95550648. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:06:03,445][86177] Avg episode reward: [(0, '-502.610'), (1, '-545.360')] -[2023-11-28 05:06:03,646][87424] Updated weights for policy 0, policy_version 186837 (0.0012) -[2023-11-28 05:06:03,770][87426] Updated weights for policy 1, policy_version 186380 (0.0008) -[2023-11-28 05:06:04,030][87424] Updated weights for policy 0, policy_version 186847 (0.0012) -[2023-11-28 05:06:04,153][87426] Updated weights for policy 1, policy_version 186390 (0.0008) -[2023-11-28 05:06:04,531][87426] Updated weights for policy 1, policy_version 186400 (0.0010) -[2023-11-28 05:06:06,368][87424] Updated weights for policy 0, policy_version 186857 (0.0008) -[2023-11-28 05:06:06,746][87424] Updated weights for policy 0, policy_version 186867 (0.0008) -[2023-11-28 05:06:06,791][87426] Updated weights for policy 1, policy_version 186410 (0.0009) -[2023-11-28 05:06:07,131][87424] Updated weights for policy 0, policy_version 186877 (0.0008) -[2023-11-28 05:06:07,164][87426] Updated weights for policy 1, policy_version 186420 (0.0008) -[2023-11-28 05:06:07,543][87426] Updated weights for policy 1, policy_version 186430 (0.0008) -[2023-11-28 05:06:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 95567872. Throughput: 0: 2740.6, 1: 2728.4. Samples: 95583632. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:06:08,445][86177] Avg episode reward: [(0, '-506.880'), (1, '-615.600')] -[2023-11-28 05:06:08,967][87424] Updated weights for policy 0, policy_version 186887 (0.0011) -[2023-11-28 05:06:09,351][87424] Updated weights for policy 0, policy_version 186897 (0.0012) -[2023-11-28 05:06:09,590][87426] Updated weights for policy 1, policy_version 186440 (0.0011) -[2023-11-28 05:06:09,736][87424] Updated weights for policy 0, policy_version 186907 (0.0011) -[2023-11-28 05:06:09,969][87426] Updated weights for policy 1, policy_version 186450 (0.0011) -[2023-11-28 05:06:10,338][87426] Updated weights for policy 1, policy_version 186460 (0.0012) -[2023-11-28 05:06:11,581][87424] Updated weights for policy 0, policy_version 186917 (0.0012) -[2023-11-28 05:06:11,965][87424] Updated weights for policy 0, policy_version 186927 (0.0012) -[2023-11-28 05:06:12,337][87424] Updated weights for policy 0, policy_version 186937 (0.0011) -[2023-11-28 05:06:12,412][87426] Updated weights for policy 1, policy_version 186470 (0.0010) -[2023-11-28 05:06:12,787][87426] Updated weights for policy 1, policy_version 186480 (0.0011) -[2023-11-28 05:06:13,170][87426] Updated weights for policy 1, policy_version 186490 (0.0012) -[2023-11-28 05:06:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5734.4, 300 sec: 5470.6). Total num frames: 95600640. Throughput: 0: 2729.0, 1: 2724.1. Samples: 95608072. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:06:13,446][86177] Avg episode reward: [(0, '-509.240'), (1, '-663.510')] -[2023-11-28 05:06:14,366][87424] Updated weights for policy 0, policy_version 186947 (0.0010) -[2023-11-28 05:06:14,746][87424] Updated weights for policy 0, policy_version 186957 (0.0010) -[2023-11-28 05:06:15,134][87424] Updated weights for policy 0, policy_version 186967 (0.0010) -[2023-11-28 05:06:15,391][87426] Updated weights for policy 1, policy_version 186500 (0.0011) -[2023-11-28 05:06:15,773][87426] Updated weights for policy 1, policy_version 186510 (0.0011) -[2023-11-28 05:06:16,159][87426] Updated weights for policy 1, policy_version 186520 (0.0009) -[2023-11-28 05:06:17,391][87424] Updated weights for policy 0, policy_version 186977 (0.0010) -[2023-11-28 05:06:17,769][87424] Updated weights for policy 0, policy_version 186987 (0.0007) -[2023-11-28 05:06:18,150][87424] Updated weights for policy 0, policy_version 186997 (0.0007) -[2023-11-28 05:06:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 95617024. Throughput: 0: 2731.8, 1: 2724.7. Samples: 95633336. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:06:18,445][86177] Avg episode reward: [(0, '-508.770'), (1, '-648.860')] -[2023-11-28 05:06:18,527][87424] Updated weights for policy 0, policy_version 187007 (0.0008) -[2023-11-28 05:06:18,564][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000187008_47874048.pth... -[2023-11-28 05:06:18,567][87426] Updated weights for policy 1, policy_version 186530 (0.0008) -[2023-11-28 05:06:18,593][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000184448_47218688.pth -[2023-11-28 05:06:18,951][87426] Updated weights for policy 1, policy_version 186540 (0.0012) -[2023-11-28 05:06:19,329][87426] Updated weights for policy 1, policy_version 186550 (0.0012) -[2023-11-28 05:06:19,698][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000186560_47759360.pth... -[2023-11-28 05:06:19,700][87426] Updated weights for policy 1, policy_version 186560 (0.0012) -[2023-11-28 05:06:19,729][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000184000_47104000.pth -[2023-11-28 05:06:20,901][87424] Updated weights for policy 0, policy_version 187017 (0.0011) -[2023-11-28 05:06:21,282][87424] Updated weights for policy 0, policy_version 187027 (0.0012) -[2023-11-28 05:06:21,664][87424] Updated weights for policy 0, policy_version 187037 (0.0010) -[2023-11-28 05:06:21,718][87426] Updated weights for policy 1, policy_version 186570 (0.0012) -[2023-11-28 05:06:22,095][87426] Updated weights for policy 1, policy_version 186580 (0.0011) -[2023-11-28 05:06:22,477][87426] Updated weights for policy 1, policy_version 186590 (0.0009) -[2023-11-28 05:06:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 95649792. Throughput: 0: 2722.5, 1: 2724.9. Samples: 95664916. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:06:23,445][86177] Avg episode reward: [(0, '-518.520'), (1, '-620.590')] -[2023-11-28 05:06:23,699][87424] Updated weights for policy 0, policy_version 187047 (0.0011) -[2023-11-28 05:06:24,081][87424] Updated weights for policy 0, policy_version 187057 (0.0011) -[2023-11-28 05:06:24,456][87426] Updated weights for policy 1, policy_version 186600 (0.0007) -[2023-11-28 05:06:24,464][87424] Updated weights for policy 0, policy_version 187067 (0.0011) -[2023-11-28 05:06:24,832][87426] Updated weights for policy 1, policy_version 186610 (0.0009) -[2023-11-28 05:06:25,212][87426] Updated weights for policy 1, policy_version 186620 (0.0008) -[2023-11-28 05:06:26,442][87424] Updated weights for policy 0, policy_version 187077 (0.0012) -[2023-11-28 05:06:26,815][87424] Updated weights for policy 0, policy_version 187087 (0.0012) -[2023-11-28 05:06:27,192][87424] Updated weights for policy 0, policy_version 187097 (0.0012) -[2023-11-28 05:06:27,532][87426] Updated weights for policy 1, policy_version 186630 (0.0010) -[2023-11-28 05:06:27,911][87426] Updated weights for policy 1, policy_version 186640 (0.0011) -[2023-11-28 05:06:28,282][87426] Updated weights for policy 1, policy_version 186650 (0.0012) -[2023-11-28 05:06:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95674368. Throughput: 0: 2721.1, 1: 2734.9. Samples: 95689592. Policy #0 lag: (min: 31.0, avg: 49.1, max: 63.0) -[2023-11-28 05:06:28,445][86177] Avg episode reward: [(0, '-543.960'), (1, '-558.340')] -[2023-11-28 05:06:29,118][87424] Updated weights for policy 0, policy_version 187107 (0.0011) -[2023-11-28 05:06:29,496][87424] Updated weights for policy 0, policy_version 187117 (0.0012) -[2023-11-28 05:06:29,875][87424] Updated weights for policy 0, policy_version 187127 (0.0011) -[2023-11-28 05:06:30,574][87426] Updated weights for policy 1, policy_version 186660 (0.0012) -[2023-11-28 05:06:30,949][87426] Updated weights for policy 1, policy_version 186670 (0.0012) -[2023-11-28 05:06:31,326][87426] Updated weights for policy 1, policy_version 186680 (0.0012) -[2023-11-28 05:06:32,110][87424] Updated weights for policy 0, policy_version 187137 (0.0012) -[2023-11-28 05:06:32,491][87424] Updated weights for policy 0, policy_version 187147 (0.0012) -[2023-11-28 05:06:32,873][87424] Updated weights for policy 0, policy_version 187157 (0.0012) -[2023-11-28 05:06:33,258][87424] Updated weights for policy 0, policy_version 187167 (0.0012) -[2023-11-28 05:06:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 95707136. Throughput: 0: 2764.4, 1: 2712.7. Samples: 95715012. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:06:33,445][86177] Avg episode reward: [(0, '-546.090'), (1, '-508.010')] -[2023-11-28 05:06:33,560][87426] Updated weights for policy 1, policy_version 186690 (0.0011) -[2023-11-28 05:06:33,949][87426] Updated weights for policy 1, policy_version 186700 (0.0008) -[2023-11-28 05:06:34,319][87426] Updated weights for policy 1, policy_version 186710 (0.0007) -[2023-11-28 05:06:34,699][87426] Updated weights for policy 1, policy_version 186720 (0.0008) -[2023-11-28 05:06:35,482][87424] Updated weights for policy 0, policy_version 187177 (0.0012) -[2023-11-28 05:06:35,864][87424] Updated weights for policy 0, policy_version 187187 (0.0012) -[2023-11-28 05:06:36,247][87424] Updated weights for policy 0, policy_version 187197 (0.0012) -[2023-11-28 05:06:36,593][87426] Updated weights for policy 1, policy_version 186730 (0.0012) -[2023-11-28 05:06:36,969][87426] Updated weights for policy 1, policy_version 186740 (0.0010) -[2023-11-28 05:06:37,345][87426] Updated weights for policy 1, policy_version 186750 (0.0012) -[2023-11-28 05:06:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 95731712. Throughput: 0: 2768.1, 1: 2719.7. Samples: 95748048. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:06:38,445][86177] Avg episode reward: [(0, '-535.030'), (1, '-506.780')] -[2023-11-28 05:06:38,585][87424] Updated weights for policy 0, policy_version 187207 (0.0012) -[2023-11-28 05:06:38,963][87424] Updated weights for policy 0, policy_version 187217 (0.0012) -[2023-11-28 05:06:39,099][87426] Updated weights for policy 1, policy_version 186760 (0.0012) -[2023-11-28 05:06:39,341][87424] Updated weights for policy 0, policy_version 187227 (0.0011) -[2023-11-28 05:06:39,472][87426] Updated weights for policy 1, policy_version 186770 (0.0009) -[2023-11-28 05:06:39,852][87426] Updated weights for policy 1, policy_version 186780 (0.0008) -[2023-11-28 05:06:41,728][87424] Updated weights for policy 0, policy_version 187237 (0.0009) -[2023-11-28 05:06:42,117][87424] Updated weights for policy 0, policy_version 187247 (0.0010) -[2023-11-28 05:06:42,175][87426] Updated weights for policy 1, policy_version 186790 (0.0011) -[2023-11-28 05:06:42,505][87424] Updated weights for policy 0, policy_version 187257 (0.0011) -[2023-11-28 05:06:42,548][87426] Updated weights for policy 1, policy_version 186800 (0.0012) -[2023-11-28 05:06:42,931][87426] Updated weights for policy 1, policy_version 186810 (0.0012) -[2023-11-28 05:06:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 95764480. Throughput: 0: 2763.2, 1: 2744.5. Samples: 95773088. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:06:43,445][86177] Avg episode reward: [(0, '-537.460'), (1, '-530.290')] -[2023-11-28 05:06:44,343][87424] Updated weights for policy 0, policy_version 187267 (0.0010) -[2023-11-28 05:06:44,731][87424] Updated weights for policy 0, policy_version 187277 (0.0011) -[2023-11-28 05:06:45,103][87424] Updated weights for policy 0, policy_version 187287 (0.0011) -[2023-11-28 05:06:45,387][87426] Updated weights for policy 1, policy_version 186820 (0.0010) -[2023-11-28 05:06:45,768][87426] Updated weights for policy 1, policy_version 186830 (0.0008) -[2023-11-28 05:06:46,153][87426] Updated weights for policy 1, policy_version 186840 (0.0008) -[2023-11-28 05:06:47,542][87424] Updated weights for policy 0, policy_version 187297 (0.0012) -[2023-11-28 05:06:47,921][87424] Updated weights for policy 0, policy_version 187307 (0.0012) -[2023-11-28 05:06:48,292][87426] Updated weights for policy 1, policy_version 186850 (0.0011) -[2023-11-28 05:06:48,298][87424] Updated weights for policy 0, policy_version 187317 (0.0011) -[2023-11-28 05:06:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 95780864. Throughput: 0: 2737.3, 1: 2770.6. Samples: 95798504. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:06:48,445][86177] Avg episode reward: [(0, '-508.900'), (1, '-533.360')] -[2023-11-28 05:06:48,664][87426] Updated weights for policy 1, policy_version 186860 (0.0007) -[2023-11-28 05:06:48,685][87424] Updated weights for policy 0, policy_version 187327 (0.0012) -[2023-11-28 05:06:49,044][87426] Updated weights for policy 1, policy_version 186870 (0.0008) -[2023-11-28 05:06:49,422][87426] Updated weights for policy 1, policy_version 186880 (0.0010) -[2023-11-28 05:06:51,235][87424] Updated weights for policy 0, policy_version 187337 (0.0011) -[2023-11-28 05:06:51,623][87424] Updated weights for policy 0, policy_version 187347 (0.0009) -[2023-11-28 05:06:51,646][87426] Updated weights for policy 1, policy_version 186890 (0.0011) -[2023-11-28 05:06:51,990][87424] Updated weights for policy 0, policy_version 187357 (0.0009) -[2023-11-28 05:06:52,026][87426] Updated weights for policy 1, policy_version 186900 (0.0011) -[2023-11-28 05:06:52,406][87426] Updated weights for policy 1, policy_version 186910 (0.0012) -[2023-11-28 05:06:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.6, 300 sec: 5470.6). Total num frames: 95813632. Throughput: 0: 2722.0, 1: 2762.7. Samples: 95830444. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:06:53,445][86177] Avg episode reward: [(0, '-510.510'), (1, '-531.040')] -[2023-11-28 05:06:54,608][87424] Updated weights for policy 0, policy_version 187367 (0.0008) -[2023-11-28 05:06:54,727][87426] Updated weights for policy 1, policy_version 186920 (0.0011) -[2023-11-28 05:06:54,993][87424] Updated weights for policy 0, policy_version 187377 (0.0009) -[2023-11-28 05:06:55,108][87426] Updated weights for policy 1, policy_version 186930 (0.0009) -[2023-11-28 05:06:55,377][87424] Updated weights for policy 0, policy_version 187387 (0.0009) -[2023-11-28 05:06:55,487][87426] Updated weights for policy 1, policy_version 186940 (0.0010) -[2023-11-28 05:06:57,184][87424] Updated weights for policy 0, policy_version 187397 (0.0007) -[2023-11-28 05:06:57,570][87424] Updated weights for policy 0, policy_version 187407 (0.0010) -[2023-11-28 05:06:57,950][87424] Updated weights for policy 0, policy_version 187417 (0.0007) -[2023-11-28 05:06:58,020][87426] Updated weights for policy 1, policy_version 186950 (0.0010) -[2023-11-28 05:06:58,396][87426] Updated weights for policy 1, policy_version 186960 (0.0007) -[2023-11-28 05:06:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 95838208. Throughput: 0: 2729.4, 1: 2740.3. Samples: 95854208. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:06:58,445][86177] Avg episode reward: [(0, '-510.820'), (1, '-508.360')] -[2023-11-28 05:06:58,775][87426] Updated weights for policy 1, policy_version 186970 (0.0010) -[2023-11-28 05:06:59,610][87424] Updated weights for policy 0, policy_version 187427 (0.0010) -[2023-11-28 05:06:59,998][87424] Updated weights for policy 0, policy_version 187437 (0.0009) -[2023-11-28 05:07:00,365][87424] Updated weights for policy 0, policy_version 187447 (0.0008) -[2023-11-28 05:07:00,729][87426] Updated weights for policy 1, policy_version 186980 (0.0011) -[2023-11-28 05:07:01,103][87426] Updated weights for policy 1, policy_version 186990 (0.0010) -[2023-11-28 05:07:01,493][87426] Updated weights for policy 1, policy_version 187000 (0.0007) -[2023-11-28 05:07:02,731][87424] Updated weights for policy 0, policy_version 187457 (0.0008) -[2023-11-28 05:07:03,111][87424] Updated weights for policy 0, policy_version 187467 (0.0012) -[2023-11-28 05:07:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95862784. Throughput: 0: 2739.6, 1: 2730.8. Samples: 95879504. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:07:03,445][86177] Avg episode reward: [(0, '-502.420'), (1, '-518.110')] -[2023-11-28 05:07:03,500][87424] Updated weights for policy 0, policy_version 187477 (0.0012) -[2023-11-28 05:07:03,691][87426] Updated weights for policy 1, policy_version 187010 (0.0010) -[2023-11-28 05:07:03,876][87424] Updated weights for policy 0, policy_version 187487 (0.0012) -[2023-11-28 05:07:04,065][87426] Updated weights for policy 1, policy_version 187020 (0.0011) -[2023-11-28 05:07:04,448][87426] Updated weights for policy 1, policy_version 187030 (0.0012) -[2023-11-28 05:07:04,829][87426] Updated weights for policy 1, policy_version 187040 (0.0012) -[2023-11-28 05:07:06,288][87424] Updated weights for policy 0, policy_version 187497 (0.0011) -[2023-11-28 05:07:06,624][87426] Updated weights for policy 1, policy_version 187050 (0.0010) -[2023-11-28 05:07:06,681][87424] Updated weights for policy 0, policy_version 187507 (0.0011) -[2023-11-28 05:07:07,006][87426] Updated weights for policy 1, policy_version 187060 (0.0011) -[2023-11-28 05:07:07,066][87424] Updated weights for policy 0, policy_version 187517 (0.0011) -[2023-11-28 05:07:07,383][87426] Updated weights for policy 1, policy_version 187070 (0.0012) -[2023-11-28 05:07:08,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 95895552. Throughput: 0: 2731.4, 1: 2748.8. Samples: 95911524. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:07:08,446][86177] Avg episode reward: [(0, '-554.960'), (1, '-514.150')] -[2023-11-28 05:07:09,003][87424] Updated weights for policy 0, policy_version 187527 (0.0011) -[2023-11-28 05:07:09,384][87424] Updated weights for policy 0, policy_version 187537 (0.0011) -[2023-11-28 05:07:09,409][87426] Updated weights for policy 1, policy_version 187080 (0.0011) -[2023-11-28 05:07:09,764][87424] Updated weights for policy 0, policy_version 187547 (0.0011) -[2023-11-28 05:07:09,788][87426] Updated weights for policy 1, policy_version 187090 (0.0011) -[2023-11-28 05:07:10,167][87426] Updated weights for policy 1, policy_version 187100 (0.0011) -[2023-11-28 05:07:12,154][87424] Updated weights for policy 0, policy_version 187557 (0.0009) -[2023-11-28 05:07:12,517][87426] Updated weights for policy 1, policy_version 187110 (0.0009) -[2023-11-28 05:07:12,539][87424] Updated weights for policy 0, policy_version 187567 (0.0012) -[2023-11-28 05:07:12,898][87426] Updated weights for policy 1, policy_version 187120 (0.0009) -[2023-11-28 05:07:12,917][87424] Updated weights for policy 0, policy_version 187577 (0.0011) -[2023-11-28 05:07:13,271][87426] Updated weights for policy 1, policy_version 187130 (0.0012) -[2023-11-28 05:07:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 95920128. Throughput: 0: 2733.2, 1: 2756.5. Samples: 95936632. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:07:13,445][86177] Avg episode reward: [(0, '-550.470'), (1, '-516.870')] -[2023-11-28 05:07:15,185][87424] Updated weights for policy 0, policy_version 187587 (0.0011) -[2023-11-28 05:07:15,307][87426] Updated weights for policy 1, policy_version 187140 (0.0012) -[2023-11-28 05:07:15,574][87424] Updated weights for policy 0, policy_version 187597 (0.0009) -[2023-11-28 05:07:15,681][87426] Updated weights for policy 1, policy_version 187150 (0.0009) -[2023-11-28 05:07:15,956][87424] Updated weights for policy 0, policy_version 187607 (0.0009) -[2023-11-28 05:07:16,059][87426] Updated weights for policy 1, policy_version 187160 (0.0011) -[2023-11-28 05:07:17,953][87424] Updated weights for policy 0, policy_version 187617 (0.0008) -[2023-11-28 05:07:18,333][87424] Updated weights for policy 0, policy_version 187627 (0.0012) -[2023-11-28 05:07:18,441][87426] Updated weights for policy 1, policy_version 187170 (0.0012) -[2023-11-28 05:07:18,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 95944704. Throughput: 0: 2693.2, 1: 2759.8. Samples: 95960400. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:07:18,445][86177] Avg episode reward: [(0, '-553.650'), (1, '-518.240')] -[2023-11-28 05:07:18,718][87424] Updated weights for policy 0, policy_version 187637 (0.0012) -[2023-11-28 05:07:18,827][87426] Updated weights for policy 1, policy_version 187180 (0.0009) -[2023-11-28 05:07:19,101][87424] Updated weights for policy 0, policy_version 187647 (0.0012) -[2023-11-28 05:07:19,213][87426] Updated weights for policy 1, policy_version 187190 (0.0010) -[2023-11-28 05:07:19,585][87426] Updated weights for policy 1, policy_version 187200 (0.0010) -[2023-11-28 05:07:21,337][87424] Updated weights for policy 0, policy_version 187657 (0.0010) -[2023-11-28 05:07:21,572][87426] Updated weights for policy 1, policy_version 187210 (0.0011) -[2023-11-28 05:07:21,716][87424] Updated weights for policy 0, policy_version 187667 (0.0010) -[2023-11-28 05:07:21,945][87426] Updated weights for policy 1, policy_version 187220 (0.0011) -[2023-11-28 05:07:22,090][87424] Updated weights for policy 0, policy_version 187677 (0.0011) -[2023-11-28 05:07:22,318][87426] Updated weights for policy 1, policy_version 187230 (0.0011) -[2023-11-28 05:07:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 95977472. Throughput: 0: 2686.2, 1: 2764.7. Samples: 95993340. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:07:23,445][86177] Avg episode reward: [(0, '-551.270'), (1, '-543.450')] -[2023-11-28 05:07:24,241][87426] Updated weights for policy 1, policy_version 187240 (0.0011) -[2023-11-28 05:07:24,483][87424] Updated weights for policy 0, policy_version 187687 (0.0011) -[2023-11-28 05:07:24,618][87426] Updated weights for policy 1, policy_version 187250 (0.0012) -[2023-11-28 05:07:24,863][87424] Updated weights for policy 0, policy_version 187697 (0.0009) -[2023-11-28 05:07:24,993][87426] Updated weights for policy 1, policy_version 187260 (0.0011) -[2023-11-28 05:07:25,245][87424] Updated weights for policy 0, policy_version 187707 (0.0009) -[2023-11-28 05:07:27,054][87426] Updated weights for policy 1, policy_version 187270 (0.0012) -[2023-11-28 05:07:27,428][87424] Updated weights for policy 0, policy_version 187717 (0.0012) -[2023-11-28 05:07:27,430][87426] Updated weights for policy 1, policy_version 187280 (0.0011) -[2023-11-28 05:07:27,806][87424] Updated weights for policy 0, policy_version 187727 (0.0012) -[2023-11-28 05:07:27,820][87426] Updated weights for policy 1, policy_version 187290 (0.0012) -[2023-11-28 05:07:28,189][87424] Updated weights for policy 0, policy_version 187737 (0.0011) -[2023-11-28 05:07:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 96002048. Throughput: 0: 2701.0, 1: 2746.8. Samples: 96018240. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:07:28,445][86177] Avg episode reward: [(0, '-500.960'), (1, '-549.090')] -[2023-11-28 05:07:30,025][87426] Updated weights for policy 1, policy_version 187300 (0.0010) -[2023-11-28 05:07:30,169][87424] Updated weights for policy 0, policy_version 187747 (0.0011) -[2023-11-28 05:07:30,403][87426] Updated weights for policy 1, policy_version 187310 (0.0011) -[2023-11-28 05:07:30,549][87424] Updated weights for policy 0, policy_version 187757 (0.0010) -[2023-11-28 05:07:30,781][87426] Updated weights for policy 1, policy_version 187320 (0.0010) -[2023-11-28 05:07:30,941][87424] Updated weights for policy 0, policy_version 187767 (0.0008) -[2023-11-28 05:07:32,916][87426] Updated weights for policy 1, policy_version 187330 (0.0010) -[2023-11-28 05:07:33,101][87424] Updated weights for policy 0, policy_version 187777 (0.0008) -[2023-11-28 05:07:33,289][87426] Updated weights for policy 1, policy_version 187340 (0.0008) -[2023-11-28 05:07:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 96026624. Throughput: 0: 2712.4, 1: 2738.4. Samples: 96043788. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:07:33,445][86177] Avg episode reward: [(0, '-505.000'), (1, '-547.560')] -[2023-11-28 05:07:33,477][87424] Updated weights for policy 0, policy_version 187787 (0.0011) -[2023-11-28 05:07:33,671][87426] Updated weights for policy 1, policy_version 187350 (0.0007) -[2023-11-28 05:07:33,865][87424] Updated weights for policy 0, policy_version 187797 (0.0011) -[2023-11-28 05:07:34,049][87426] Updated weights for policy 1, policy_version 187360 (0.0010) -[2023-11-28 05:07:34,256][87424] Updated weights for policy 0, policy_version 187807 (0.0008) -[2023-11-28 05:07:36,325][87426] Updated weights for policy 1, policy_version 187370 (0.0007) -[2023-11-28 05:07:36,705][87426] Updated weights for policy 1, policy_version 187380 (0.0010) -[2023-11-28 05:07:36,721][87424] Updated weights for policy 0, policy_version 187817 (0.0008) -[2023-11-28 05:07:37,093][87424] Updated weights for policy 0, policy_version 187827 (0.0008) -[2023-11-28 05:07:37,098][87426] Updated weights for policy 1, policy_version 187390 (0.0010) -[2023-11-28 05:07:37,476][87424] Updated weights for policy 0, policy_version 187837 (0.0012) -[2023-11-28 05:07:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96059392. Throughput: 0: 2698.0, 1: 2750.3. Samples: 96075620. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:07:38,445][86177] Avg episode reward: [(0, '-497.390'), (1, '-543.000')] -[2023-11-28 05:07:38,889][87426] Updated weights for policy 1, policy_version 187400 (0.0012) -[2023-11-28 05:07:39,272][87426] Updated weights for policy 1, policy_version 187410 (0.0011) -[2023-11-28 05:07:39,278][87424] Updated weights for policy 0, policy_version 187847 (0.0010) -[2023-11-28 05:07:39,644][87426] Updated weights for policy 1, policy_version 187420 (0.0011) -[2023-11-28 05:07:39,663][87424] Updated weights for policy 0, policy_version 187857 (0.0010) -[2023-11-28 05:07:40,049][87424] Updated weights for policy 0, policy_version 187867 (0.0011) -[2023-11-28 05:07:42,001][87426] Updated weights for policy 1, policy_version 187430 (0.0010) -[2023-11-28 05:07:42,374][87426] Updated weights for policy 1, policy_version 187440 (0.0011) -[2023-11-28 05:07:42,490][87424] Updated weights for policy 0, policy_version 187877 (0.0010) -[2023-11-28 05:07:42,745][87426] Updated weights for policy 1, policy_version 187450 (0.0011) -[2023-11-28 05:07:42,867][87424] Updated weights for policy 0, policy_version 187887 (0.0011) -[2023-11-28 05:07:43,252][87424] Updated weights for policy 0, policy_version 187897 (0.0008) -[2023-11-28 05:07:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 96083968. Throughput: 0: 2703.8, 1: 2767.6. Samples: 96100424. Policy #0 lag: (min: 31.0, avg: 42.1, max: 63.0) -[2023-11-28 05:07:43,445][86177] Avg episode reward: [(0, '-505.000'), (1, '-513.030')] -[2023-11-28 05:07:44,661][87426] Updated weights for policy 1, policy_version 187460 (0.0010) -[2023-11-28 05:07:45,043][87426] Updated weights for policy 1, policy_version 187470 (0.0011) -[2023-11-28 05:07:45,420][87426] Updated weights for policy 1, policy_version 187480 (0.0009) -[2023-11-28 05:07:45,739][87424] Updated weights for policy 0, policy_version 187907 (0.0008) -[2023-11-28 05:07:46,129][87424] Updated weights for policy 0, policy_version 187917 (0.0008) -[2023-11-28 05:07:46,500][87424] Updated weights for policy 0, policy_version 187927 (0.0008) -[2023-11-28 05:07:47,349][87426] Updated weights for policy 1, policy_version 187490 (0.0011) -[2023-11-28 05:07:47,737][87426] Updated weights for policy 1, policy_version 187500 (0.0011) -[2023-11-28 05:07:48,114][87426] Updated weights for policy 1, policy_version 187510 (0.0011) -[2023-11-28 05:07:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.9). Total num frames: 96108544. Throughput: 0: 2665.7, 1: 2800.4. Samples: 96125476. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:07:48,445][86177] Avg episode reward: [(0, '-508.990'), (1, '-516.480')] -[2023-11-28 05:07:48,490][87426] Updated weights for policy 1, policy_version 187520 (0.0010) -[2023-11-28 05:07:48,631][87424] Updated weights for policy 0, policy_version 187937 (0.0011) -[2023-11-28 05:07:49,013][87424] Updated weights for policy 0, policy_version 187947 (0.0012) -[2023-11-28 05:07:49,393][87424] Updated weights for policy 0, policy_version 187957 (0.0012) -[2023-11-28 05:07:49,775][87424] Updated weights for policy 0, policy_version 187967 (0.0008) -[2023-11-28 05:07:51,076][87426] Updated weights for policy 1, policy_version 187530 (0.0011) -[2023-11-28 05:07:51,451][87426] Updated weights for policy 1, policy_version 187540 (0.0008) -[2023-11-28 05:07:51,830][87426] Updated weights for policy 1, policy_version 187550 (0.0009) -[2023-11-28 05:07:52,162][87424] Updated weights for policy 0, policy_version 187977 (0.0008) -[2023-11-28 05:07:52,551][87424] Updated weights for policy 0, policy_version 187987 (0.0012) -[2023-11-28 05:07:52,925][87424] Updated weights for policy 0, policy_version 187997 (0.0012) -[2023-11-28 05:07:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96141312. Throughput: 0: 2682.8, 1: 2786.1. Samples: 96157620. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:07:53,445][86177] Avg episode reward: [(0, '-504.020'), (1, '-524.500')] -[2023-11-28 05:07:53,884][87426] Updated weights for policy 1, policy_version 187560 (0.0011) -[2023-11-28 05:07:54,279][87426] Updated weights for policy 1, policy_version 187570 (0.0012) -[2023-11-28 05:07:54,659][87426] Updated weights for policy 1, policy_version 187580 (0.0012) -[2023-11-28 05:07:55,086][87424] Updated weights for policy 0, policy_version 188007 (0.0012) -[2023-11-28 05:07:55,469][87424] Updated weights for policy 0, policy_version 188017 (0.0012) -[2023-11-28 05:07:55,843][87424] Updated weights for policy 0, policy_version 188027 (0.0012) -[2023-11-28 05:07:56,929][87426] Updated weights for policy 1, policy_version 187590 (0.0012) -[2023-11-28 05:07:57,312][87426] Updated weights for policy 1, policy_version 187600 (0.0010) -[2023-11-28 05:07:57,647][87424] Updated weights for policy 0, policy_version 188037 (0.0009) -[2023-11-28 05:07:57,692][87426] Updated weights for policy 1, policy_version 187610 (0.0009) -[2023-11-28 05:07:58,020][87424] Updated weights for policy 0, policy_version 188047 (0.0008) -[2023-11-28 05:07:58,406][87424] Updated weights for policy 0, policy_version 188057 (0.0008) -[2023-11-28 05:07:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96165888. Throughput: 0: 2690.8, 1: 2772.7. Samples: 96182492. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:07:58,445][86177] Avg episode reward: [(0, '-513.760'), (1, '-530.150')] -[2023-11-28 05:07:59,689][87426] Updated weights for policy 1, policy_version 187620 (0.0010) -[2023-11-28 05:08:00,064][87426] Updated weights for policy 1, policy_version 187630 (0.0010) -[2023-11-28 05:08:00,431][87426] Updated weights for policy 1, policy_version 187640 (0.0011) -[2023-11-28 05:08:00,450][87424] Updated weights for policy 0, policy_version 188067 (0.0008) -[2023-11-28 05:08:00,843][87424] Updated weights for policy 0, policy_version 188077 (0.0009) -[2023-11-28 05:08:01,211][87424] Updated weights for policy 0, policy_version 188087 (0.0008) -[2023-11-28 05:08:02,729][87426] Updated weights for policy 1, policy_version 187650 (0.0007) -[2023-11-28 05:08:03,113][87426] Updated weights for policy 1, policy_version 187660 (0.0008) -[2023-11-28 05:08:03,418][87424] Updated weights for policy 0, policy_version 188097 (0.0010) -[2023-11-28 05:08:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 96190464. Throughput: 0: 2723.5, 1: 2773.0. Samples: 96207740. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:03,445][86177] Avg episode reward: [(0, '-508.530'), (1, '-527.800')] -[2023-11-28 05:08:03,496][87426] Updated weights for policy 1, policy_version 187670 (0.0011) -[2023-11-28 05:08:03,803][87424] Updated weights for policy 0, policy_version 188107 (0.0010) -[2023-11-28 05:08:03,871][87426] Updated weights for policy 1, policy_version 187680 (0.0011) -[2023-11-28 05:08:04,182][87424] Updated weights for policy 0, policy_version 188117 (0.0012) -[2023-11-28 05:08:04,559][87424] Updated weights for policy 0, policy_version 188127 (0.0012) -[2023-11-28 05:08:05,862][87426] Updated weights for policy 1, policy_version 187690 (0.0011) -[2023-11-28 05:08:06,252][87426] Updated weights for policy 1, policy_version 187700 (0.0012) -[2023-11-28 05:08:06,621][87426] Updated weights for policy 1, policy_version 187710 (0.0012) -[2023-11-28 05:08:06,973][87424] Updated weights for policy 0, policy_version 188137 (0.0011) -[2023-11-28 05:08:07,361][87424] Updated weights for policy 0, policy_version 188147 (0.0008) -[2023-11-28 05:08:07,733][87424] Updated weights for policy 0, policy_version 188157 (0.0008) -[2023-11-28 05:08:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 96223232. Throughput: 0: 2703.8, 1: 2760.5. Samples: 96239236. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:08,445][86177] Avg episode reward: [(0, '-507.040'), (1, '-518.020')] -[2023-11-28 05:08:08,670][87426] Updated weights for policy 1, policy_version 187720 (0.0011) -[2023-11-28 05:08:09,044][87426] Updated weights for policy 1, policy_version 187730 (0.0008) -[2023-11-28 05:08:09,429][87426] Updated weights for policy 1, policy_version 187740 (0.0007) -[2023-11-28 05:08:10,107][87424] Updated weights for policy 0, policy_version 188167 (0.0008) -[2023-11-28 05:08:10,502][87424] Updated weights for policy 0, policy_version 188177 (0.0008) -[2023-11-28 05:08:10,884][87424] Updated weights for policy 0, policy_version 188187 (0.0008) -[2023-11-28 05:08:11,417][87426] Updated weights for policy 1, policy_version 187750 (0.0010) -[2023-11-28 05:08:11,793][87426] Updated weights for policy 1, policy_version 187760 (0.0011) -[2023-11-28 05:08:12,174][87426] Updated weights for policy 1, policy_version 187770 (0.0012) -[2023-11-28 05:08:13,151][87424] Updated weights for policy 0, policy_version 188197 (0.0010) -[2023-11-28 05:08:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96247808. Throughput: 0: 2692.0, 1: 2775.3. Samples: 96264268. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:13,445][86177] Avg episode reward: [(0, '-511.570'), (1, '-553.380')] -[2023-11-28 05:08:13,548][87424] Updated weights for policy 0, policy_version 188207 (0.0012) -[2023-11-28 05:08:13,926][87424] Updated weights for policy 0, policy_version 188217 (0.0009) -[2023-11-28 05:08:14,405][87426] Updated weights for policy 1, policy_version 187780 (0.0012) -[2023-11-28 05:08:14,789][87426] Updated weights for policy 1, policy_version 187790 (0.0011) -[2023-11-28 05:08:15,171][87426] Updated weights for policy 1, policy_version 187800 (0.0012) -[2023-11-28 05:08:16,291][87424] Updated weights for policy 0, policy_version 188227 (0.0010) -[2023-11-28 05:08:16,676][87424] Updated weights for policy 0, policy_version 188237 (0.0012) -[2023-11-28 05:08:16,839][87426] Updated weights for policy 1, policy_version 187810 (0.0012) -[2023-11-28 05:08:17,054][87424] Updated weights for policy 0, policy_version 188247 (0.0012) -[2023-11-28 05:08:17,213][87426] Updated weights for policy 1, policy_version 187820 (0.0008) -[2023-11-28 05:08:17,594][87426] Updated weights for policy 1, policy_version 187830 (0.0009) -[2023-11-28 05:08:17,982][87426] Updated weights for policy 1, policy_version 187840 (0.0008) -[2023-11-28 05:08:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 96280576. Throughput: 0: 2673.7, 1: 2789.9. Samples: 96289648. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:18,445][86177] Avg episode reward: [(0, '-508.720'), (1, '-559.710')] -[2023-11-28 05:08:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000188256_48193536.pth... -[2023-11-28 05:08:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000187840_48087040.pth... -[2023-11-28 05:08:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000185248_47423488.pth -[2023-11-28 05:08:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000185728_47546368.pth -[2023-11-28 05:08:18,823][87424] Updated weights for policy 0, policy_version 188257 (0.0010) -[2023-11-28 05:08:19,207][87424] Updated weights for policy 0, policy_version 188267 (0.0012) -[2023-11-28 05:08:19,589][87424] Updated weights for policy 0, policy_version 188277 (0.0011) -[2023-11-28 05:08:19,657][87426] Updated weights for policy 1, policy_version 187850 (0.0011) -[2023-11-28 05:08:19,962][87424] Updated weights for policy 0, policy_version 188287 (0.0009) -[2023-11-28 05:08:20,038][87426] Updated weights for policy 1, policy_version 187860 (0.0010) -[2023-11-28 05:08:20,415][87426] Updated weights for policy 1, policy_version 187870 (0.0012) -[2023-11-28 05:08:21,903][87424] Updated weights for policy 0, policy_version 188297 (0.0011) -[2023-11-28 05:08:22,286][87424] Updated weights for policy 0, policy_version 188307 (0.0012) -[2023-11-28 05:08:22,360][87426] Updated weights for policy 1, policy_version 187880 (0.0010) -[2023-11-28 05:08:22,664][87424] Updated weights for policy 0, policy_version 188317 (0.0011) -[2023-11-28 05:08:22,744][87426] Updated weights for policy 1, policy_version 187890 (0.0010) -[2023-11-28 05:08:23,122][87426] Updated weights for policy 1, policy_version 187900 (0.0009) -[2023-11-28 05:08:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 96313344. Throughput: 0: 2710.1, 1: 2797.7. Samples: 96323468. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:23,445][86177] Avg episode reward: [(0, '-515.940'), (1, '-602.690')] -[2023-11-28 05:08:25,181][87424] Updated weights for policy 0, policy_version 188327 (0.0011) -[2023-11-28 05:08:25,315][87426] Updated weights for policy 1, policy_version 187910 (0.0010) -[2023-11-28 05:08:25,579][87424] Updated weights for policy 0, policy_version 188337 (0.0009) -[2023-11-28 05:08:25,703][87426] Updated weights for policy 1, policy_version 187920 (0.0012) -[2023-11-28 05:08:25,954][87424] Updated weights for policy 0, policy_version 188347 (0.0008) -[2023-11-28 05:08:26,080][87426] Updated weights for policy 1, policy_version 187930 (0.0011) -[2023-11-28 05:08:27,938][87424] Updated weights for policy 0, policy_version 188357 (0.0008) -[2023-11-28 05:08:28,319][87424] Updated weights for policy 0, policy_version 188367 (0.0007) -[2023-11-28 05:08:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 96329728. Throughput: 0: 2705.0, 1: 2805.1. Samples: 96348376. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:28,445][86177] Avg episode reward: [(0, '-518.960'), (1, '-574.840')] -[2023-11-28 05:08:28,581][87426] Updated weights for policy 1, policy_version 187940 (0.0012) -[2023-11-28 05:08:28,707][87424] Updated weights for policy 0, policy_version 188377 (0.0011) -[2023-11-28 05:08:28,962][87426] Updated weights for policy 1, policy_version 187950 (0.0012) -[2023-11-28 05:08:29,350][87426] Updated weights for policy 1, policy_version 187960 (0.0012) -[2023-11-28 05:08:30,814][87424] Updated weights for policy 0, policy_version 188387 (0.0010) -[2023-11-28 05:08:31,189][87424] Updated weights for policy 0, policy_version 188397 (0.0012) -[2023-11-28 05:08:31,577][87424] Updated weights for policy 0, policy_version 188407 (0.0010) -[2023-11-28 05:08:31,766][87426] Updated weights for policy 1, policy_version 187970 (0.0011) -[2023-11-28 05:08:32,148][87426] Updated weights for policy 1, policy_version 187980 (0.0010) -[2023-11-28 05:08:32,528][87426] Updated weights for policy 1, policy_version 187990 (0.0008) -[2023-11-28 05:08:32,908][87426] Updated weights for policy 1, policy_version 188000 (0.0012) -[2023-11-28 05:08:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 96362496. Throughput: 0: 2703.8, 1: 2782.0. Samples: 96372340. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:33,445][86177] Avg episode reward: [(0, '-555.390'), (1, '-561.990')] -[2023-11-28 05:08:33,904][87424] Updated weights for policy 0, policy_version 188417 (0.0008) -[2023-11-28 05:08:34,288][87424] Updated weights for policy 0, policy_version 188427 (0.0008) -[2023-11-28 05:08:34,659][87424] Updated weights for policy 0, policy_version 188437 (0.0007) -[2023-11-28 05:08:34,710][87426] Updated weights for policy 1, policy_version 188010 (0.0010) -[2023-11-28 05:08:35,058][87424] Updated weights for policy 0, policy_version 188447 (0.0011) -[2023-11-28 05:08:35,096][87426] Updated weights for policy 1, policy_version 188020 (0.0011) -[2023-11-28 05:08:35,475][87426] Updated weights for policy 1, policy_version 188030 (0.0012) -[2023-11-28 05:08:37,270][87424] Updated weights for policy 0, policy_version 188457 (0.0011) -[2023-11-28 05:08:37,662][87424] Updated weights for policy 0, policy_version 188467 (0.0012) -[2023-11-28 05:08:37,828][87426] Updated weights for policy 1, policy_version 188040 (0.0008) -[2023-11-28 05:08:38,038][87424] Updated weights for policy 0, policy_version 188477 (0.0012) -[2023-11-28 05:08:38,212][87426] Updated weights for policy 1, policy_version 188050 (0.0011) -[2023-11-28 05:08:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96387072. Throughput: 0: 2699.0, 1: 2788.7. Samples: 96404568. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:38,446][86177] Avg episode reward: [(0, '-547.680'), (1, '-565.700')] -[2023-11-28 05:08:38,595][87426] Updated weights for policy 1, policy_version 188060 (0.0012) -[2023-11-28 05:08:40,011][87424] Updated weights for policy 0, policy_version 188487 (0.0012) -[2023-11-28 05:08:40,393][87424] Updated weights for policy 0, policy_version 188497 (0.0010) -[2023-11-28 05:08:40,772][87424] Updated weights for policy 0, policy_version 188507 (0.0010) -[2023-11-28 05:08:40,989][87426] Updated weights for policy 1, policy_version 188070 (0.0011) -[2023-11-28 05:08:41,360][87426] Updated weights for policy 1, policy_version 188080 (0.0011) -[2023-11-28 05:08:41,743][87426] Updated weights for policy 1, policy_version 188090 (0.0012) -[2023-11-28 05:08:43,140][87424] Updated weights for policy 0, policy_version 188517 (0.0009) -[2023-11-28 05:08:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 96411648. Throughput: 0: 2709.9, 1: 2757.1. Samples: 96428508. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:43,445][86177] Avg episode reward: [(0, '-539.330'), (1, '-533.250')] -[2023-11-28 05:08:43,522][87424] Updated weights for policy 0, policy_version 188527 (0.0009) -[2023-11-28 05:08:43,904][87424] Updated weights for policy 0, policy_version 188537 (0.0011) -[2023-11-28 05:08:44,277][87426] Updated weights for policy 1, policy_version 188100 (0.0010) -[2023-11-28 05:08:44,654][87426] Updated weights for policy 1, policy_version 188110 (0.0007) -[2023-11-28 05:08:45,036][87426] Updated weights for policy 1, policy_version 188120 (0.0007) -[2023-11-28 05:08:45,845][87424] Updated weights for policy 0, policy_version 188547 (0.0011) -[2023-11-28 05:08:46,229][87424] Updated weights for policy 0, policy_version 188557 (0.0009) -[2023-11-28 05:08:46,615][87424] Updated weights for policy 0, policy_version 188567 (0.0007) -[2023-11-28 05:08:47,446][87426] Updated weights for policy 1, policy_version 188130 (0.0009) -[2023-11-28 05:08:47,829][87426] Updated weights for policy 1, policy_version 188140 (0.0012) -[2023-11-28 05:08:48,202][87426] Updated weights for policy 1, policy_version 188150 (0.0012) -[2023-11-28 05:08:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 96436224. Throughput: 0: 2679.0, 1: 2756.3. Samples: 96452328. Policy #0 lag: (min: 9.0, avg: 34.1, max: 61.0) -[2023-11-28 05:08:48,445][86177] Avg episode reward: [(0, '-537.150'), (1, '-562.580')] -[2023-11-28 05:08:48,581][87426] Updated weights for policy 1, policy_version 188160 (0.0010) -[2023-11-28 05:08:49,073][87424] Updated weights for policy 0, policy_version 188577 (0.0008) -[2023-11-28 05:08:49,449][87424] Updated weights for policy 0, policy_version 188587 (0.0012) -[2023-11-28 05:08:49,841][87424] Updated weights for policy 0, policy_version 188597 (0.0012) -[2023-11-28 05:08:50,217][87424] Updated weights for policy 0, policy_version 188607 (0.0012) -[2023-11-28 05:08:50,720][87426] Updated weights for policy 1, policy_version 188170 (0.0011) -[2023-11-28 05:08:51,089][87426] Updated weights for policy 1, policy_version 188180 (0.0011) -[2023-11-28 05:08:51,468][87426] Updated weights for policy 1, policy_version 188190 (0.0012) -[2023-11-28 05:08:52,332][87424] Updated weights for policy 0, policy_version 188617 (0.0012) -[2023-11-28 05:08:52,717][87424] Updated weights for policy 0, policy_version 188627 (0.0012) -[2023-11-28 05:08:53,092][87424] Updated weights for policy 0, policy_version 188637 (0.0012) -[2023-11-28 05:08:53,445][86177] Fps is (10 sec: 5733.9, 60 sec: 5461.2, 300 sec: 5470.6). Total num frames: 96468992. Throughput: 0: 2730.2, 1: 2740.6. Samples: 96485424. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:08:53,446][86177] Avg episode reward: [(0, '-496.150'), (1, '-567.560')] -[2023-11-28 05:08:53,804][87426] Updated weights for policy 1, policy_version 188200 (0.0011) -[2023-11-28 05:08:54,184][87426] Updated weights for policy 1, policy_version 188210 (0.0012) -[2023-11-28 05:08:54,565][87426] Updated weights for policy 1, policy_version 188220 (0.0012) -[2023-11-28 05:08:55,184][87424] Updated weights for policy 0, policy_version 188647 (0.0010) -[2023-11-28 05:08:55,567][87424] Updated weights for policy 0, policy_version 188657 (0.0007) -[2023-11-28 05:08:55,949][87424] Updated weights for policy 0, policy_version 188667 (0.0008) -[2023-11-28 05:08:56,495][87426] Updated weights for policy 1, policy_version 188230 (0.0012) -[2023-11-28 05:08:56,876][87426] Updated weights for policy 1, policy_version 188240 (0.0012) -[2023-11-28 05:08:57,243][87426] Updated weights for policy 1, policy_version 188250 (0.0010) -[2023-11-28 05:08:58,036][87424] Updated weights for policy 0, policy_version 188677 (0.0009) -[2023-11-28 05:08:58,418][87424] Updated weights for policy 0, policy_version 188687 (0.0012) -[2023-11-28 05:08:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96493568. Throughput: 0: 2737.4, 1: 2734.7. Samples: 96510516. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:08:58,446][86177] Avg episode reward: [(0, '-495.760'), (1, '-561.690')] -[2023-11-28 05:08:58,805][87424] Updated weights for policy 0, policy_version 188697 (0.0012) -[2023-11-28 05:08:59,438][87426] Updated weights for policy 1, policy_version 188260 (0.0011) -[2023-11-28 05:08:59,823][87426] Updated weights for policy 1, policy_version 188270 (0.0009) -[2023-11-28 05:09:00,194][87426] Updated weights for policy 1, policy_version 188280 (0.0011) -[2023-11-28 05:09:00,876][87424] Updated weights for policy 0, policy_version 188707 (0.0012) -[2023-11-28 05:09:01,267][87424] Updated weights for policy 0, policy_version 188717 (0.0012) -[2023-11-28 05:09:01,660][87424] Updated weights for policy 0, policy_version 188727 (0.0009) -[2023-11-28 05:09:02,795][87426] Updated weights for policy 1, policy_version 188290 (0.0011) -[2023-11-28 05:09:03,170][87426] Updated weights for policy 1, policy_version 188300 (0.0012) -[2023-11-28 05:09:03,431][87424] Updated weights for policy 0, policy_version 188737 (0.0011) -[2023-11-28 05:09:03,444][86177] Fps is (10 sec: 4915.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96518144. Throughput: 0: 2741.9, 1: 2698.5. Samples: 96534464. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:03,445][86177] Avg episode reward: [(0, '-494.120'), (1, '-553.980')] -[2023-11-28 05:09:03,546][87426] Updated weights for policy 1, policy_version 188310 (0.0011) -[2023-11-28 05:09:03,810][87424] Updated weights for policy 0, policy_version 188747 (0.0011) -[2023-11-28 05:09:03,930][87426] Updated weights for policy 1, policy_version 188320 (0.0012) -[2023-11-28 05:09:04,199][87424] Updated weights for policy 0, policy_version 188757 (0.0012) -[2023-11-28 05:09:04,580][87424] Updated weights for policy 0, policy_version 188767 (0.0012) -[2023-11-28 05:09:05,848][87426] Updated weights for policy 1, policy_version 188330 (0.0008) -[2023-11-28 05:09:06,226][87426] Updated weights for policy 1, policy_version 188340 (0.0008) -[2023-11-28 05:09:06,463][87424] Updated weights for policy 0, policy_version 188777 (0.0009) -[2023-11-28 05:09:06,604][87426] Updated weights for policy 1, policy_version 188350 (0.0007) -[2023-11-28 05:09:06,849][87424] Updated weights for policy 0, policy_version 188787 (0.0012) -[2023-11-28 05:09:07,233][87424] Updated weights for policy 0, policy_version 188797 (0.0011) -[2023-11-28 05:09:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96550912. Throughput: 0: 2754.2, 1: 2669.8. Samples: 96567548. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:08,445][86177] Avg episode reward: [(0, '-501.640'), (1, '-519.380')] -[2023-11-28 05:09:09,060][87426] Updated weights for policy 1, policy_version 188360 (0.0007) -[2023-11-28 05:09:09,441][87426] Updated weights for policy 1, policy_version 188370 (0.0007) -[2023-11-28 05:09:09,685][87424] Updated weights for policy 0, policy_version 188807 (0.0012) -[2023-11-28 05:09:09,826][87426] Updated weights for policy 1, policy_version 188380 (0.0008) -[2023-11-28 05:09:10,065][87424] Updated weights for policy 0, policy_version 188817 (0.0011) -[2023-11-28 05:09:10,447][87424] Updated weights for policy 0, policy_version 188827 (0.0012) -[2023-11-28 05:09:12,237][87426] Updated weights for policy 1, policy_version 188390 (0.0011) -[2023-11-28 05:09:12,613][87426] Updated weights for policy 1, policy_version 188400 (0.0012) -[2023-11-28 05:09:12,987][87426] Updated weights for policy 1, policy_version 188410 (0.0012) -[2023-11-28 05:09:13,013][87424] Updated weights for policy 0, policy_version 188837 (0.0010) -[2023-11-28 05:09:13,394][87424] Updated weights for policy 0, policy_version 188847 (0.0008) -[2023-11-28 05:09:13,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96575488. Throughput: 0: 2755.4, 1: 2634.7. Samples: 96590936. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:13,446][86177] Avg episode reward: [(0, '-504.180'), (1, '-513.140')] -[2023-11-28 05:09:13,780][87424] Updated weights for policy 0, policy_version 188857 (0.0007) -[2023-11-28 05:09:15,579][87426] Updated weights for policy 1, policy_version 188420 (0.0011) -[2023-11-28 05:09:15,749][87424] Updated weights for policy 0, policy_version 188867 (0.0009) -[2023-11-28 05:09:15,948][87426] Updated weights for policy 1, policy_version 188430 (0.0011) -[2023-11-28 05:09:16,129][87424] Updated weights for policy 0, policy_version 188877 (0.0012) -[2023-11-28 05:09:16,331][87426] Updated weights for policy 1, policy_version 188440 (0.0012) -[2023-11-28 05:09:16,511][87424] Updated weights for policy 0, policy_version 188887 (0.0011) -[2023-11-28 05:09:18,259][87424] Updated weights for policy 0, policy_version 188897 (0.0009) -[2023-11-28 05:09:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 96600064. Throughput: 0: 2761.2, 1: 2618.2. Samples: 96614412. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:18,445][86177] Avg episode reward: [(0, '-510.600'), (1, '-537.880')] -[2023-11-28 05:09:18,645][87424] Updated weights for policy 0, policy_version 188907 (0.0012) -[2023-11-28 05:09:18,923][87426] Updated weights for policy 1, policy_version 188450 (0.0011) -[2023-11-28 05:09:19,032][87424] Updated weights for policy 0, policy_version 188917 (0.0009) -[2023-11-28 05:09:19,297][87426] Updated weights for policy 1, policy_version 188460 (0.0011) -[2023-11-28 05:09:19,416][87424] Updated weights for policy 0, policy_version 188927 (0.0010) -[2023-11-28 05:09:19,680][87426] Updated weights for policy 1, policy_version 188470 (0.0012) -[2023-11-28 05:09:20,062][87426] Updated weights for policy 1, policy_version 188480 (0.0012) -[2023-11-28 05:09:21,787][87424] Updated weights for policy 0, policy_version 188937 (0.0012) -[2023-11-28 05:09:22,103][87426] Updated weights for policy 1, policy_version 188490 (0.0010) -[2023-11-28 05:09:22,177][87424] Updated weights for policy 0, policy_version 188947 (0.0008) -[2023-11-28 05:09:22,480][87426] Updated weights for policy 1, policy_version 188500 (0.0012) -[2023-11-28 05:09:22,549][87424] Updated weights for policy 0, policy_version 188957 (0.0010) -[2023-11-28 05:09:22,855][87426] Updated weights for policy 1, policy_version 188510 (0.0012) -[2023-11-28 05:09:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 96632832. Throughput: 0: 2752.3, 1: 2609.9. Samples: 96645864. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:23,446][86177] Avg episode reward: [(0, '-515.140'), (1, '-540.010')] -[2023-11-28 05:09:25,139][87424] Updated weights for policy 0, policy_version 188967 (0.0012) -[2023-11-28 05:09:25,358][87426] Updated weights for policy 1, policy_version 188520 (0.0010) -[2023-11-28 05:09:25,521][87424] Updated weights for policy 0, policy_version 188977 (0.0012) -[2023-11-28 05:09:25,745][87426] Updated weights for policy 1, policy_version 188530 (0.0007) -[2023-11-28 05:09:25,896][87424] Updated weights for policy 0, policy_version 188987 (0.0008) -[2023-11-28 05:09:26,128][87426] Updated weights for policy 1, policy_version 188540 (0.0007) -[2023-11-28 05:09:27,914][87424] Updated weights for policy 0, policy_version 188997 (0.0010) -[2023-11-28 05:09:28,028][87426] Updated weights for policy 1, policy_version 188550 (0.0007) -[2023-11-28 05:09:28,296][87424] Updated weights for policy 0, policy_version 189007 (0.0007) -[2023-11-28 05:09:28,409][87426] Updated weights for policy 1, policy_version 188560 (0.0007) -[2023-11-28 05:09:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 96649216. Throughput: 0: 2752.8, 1: 2656.1. Samples: 96671908. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:28,445][86177] Avg episode reward: [(0, '-509.980'), (1, '-542.180')] -[2023-11-28 05:09:28,687][87424] Updated weights for policy 0, policy_version 189017 (0.0007) -[2023-11-28 05:09:28,794][87426] Updated weights for policy 1, policy_version 188570 (0.0011) -[2023-11-28 05:09:30,401][87426] Updated weights for policy 1, policy_version 188580 (0.0008) -[2023-11-28 05:09:30,778][87426] Updated weights for policy 1, policy_version 188590 (0.0011) -[2023-11-28 05:09:31,101][87424] Updated weights for policy 0, policy_version 189027 (0.0009) -[2023-11-28 05:09:31,166][87426] Updated weights for policy 1, policy_version 188600 (0.0011) -[2023-11-28 05:09:31,483][87424] Updated weights for policy 0, policy_version 189037 (0.0007) -[2023-11-28 05:09:31,866][87424] Updated weights for policy 0, policy_version 189047 (0.0010) -[2023-11-28 05:09:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 96681984. Throughput: 0: 2748.8, 1: 2642.8. Samples: 96694952. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:33,445][86177] Avg episode reward: [(0, '-519.850'), (1, '-550.020')] -[2023-11-28 05:09:33,515][87424] Updated weights for policy 0, policy_version 189057 (0.0010) -[2023-11-28 05:09:33,684][87426] Updated weights for policy 1, policy_version 188610 (0.0011) -[2023-11-28 05:09:33,898][87424] Updated weights for policy 0, policy_version 189067 (0.0009) -[2023-11-28 05:09:34,069][87426] Updated weights for policy 1, policy_version 188620 (0.0012) -[2023-11-28 05:09:34,282][87424] Updated weights for policy 0, policy_version 189077 (0.0008) -[2023-11-28 05:09:34,445][87426] Updated weights for policy 1, policy_version 188630 (0.0011) -[2023-11-28 05:09:34,679][87424] Updated weights for policy 0, policy_version 189087 (0.0008) -[2023-11-28 05:09:34,833][87426] Updated weights for policy 1, policy_version 188640 (0.0012) -[2023-11-28 05:09:37,005][87424] Updated weights for policy 0, policy_version 189097 (0.0011) -[2023-11-28 05:09:37,059][87426] Updated weights for policy 1, policy_version 188650 (0.0011) -[2023-11-28 05:09:37,388][87424] Updated weights for policy 0, policy_version 189107 (0.0012) -[2023-11-28 05:09:37,436][87426] Updated weights for policy 1, policy_version 188660 (0.0011) -[2023-11-28 05:09:37,765][87424] Updated weights for policy 0, policy_version 189117 (0.0011) -[2023-11-28 05:09:37,815][87426] Updated weights for policy 1, policy_version 188670 (0.0011) -[2023-11-28 05:09:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96714752. Throughput: 0: 2736.3, 1: 2640.1. Samples: 96727360. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:38,445][86177] Avg episode reward: [(0, '-522.030'), (1, '-547.150')] -[2023-11-28 05:09:39,557][87424] Updated weights for policy 0, policy_version 189127 (0.0012) -[2023-11-28 05:09:39,897][87426] Updated weights for policy 1, policy_version 188680 (0.0011) -[2023-11-28 05:09:39,939][87424] Updated weights for policy 0, policy_version 189137 (0.0012) -[2023-11-28 05:09:40,265][87426] Updated weights for policy 1, policy_version 188690 (0.0011) -[2023-11-28 05:09:40,330][87424] Updated weights for policy 0, policy_version 189147 (0.0010) -[2023-11-28 05:09:40,649][87426] Updated weights for policy 1, policy_version 188700 (0.0012) -[2023-11-28 05:09:42,391][87424] Updated weights for policy 0, policy_version 189157 (0.0008) -[2023-11-28 05:09:42,766][87424] Updated weights for policy 0, policy_version 189167 (0.0009) -[2023-11-28 05:09:43,165][87424] Updated weights for policy 0, policy_version 189177 (0.0009) -[2023-11-28 05:09:43,310][87426] Updated weights for policy 1, policy_version 188710 (0.0010) -[2023-11-28 05:09:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 96739328. Throughput: 0: 2742.3, 1: 2598.0. Samples: 96750828. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:43,445][86177] Avg episode reward: [(0, '-520.280'), (1, '-554.660')] -[2023-11-28 05:09:43,687][87426] Updated weights for policy 1, policy_version 188720 (0.0011) -[2023-11-28 05:09:44,064][87426] Updated weights for policy 1, policy_version 188730 (0.0011) -[2023-11-28 05:09:45,522][87424] Updated weights for policy 0, policy_version 189187 (0.0010) -[2023-11-28 05:09:45,899][87424] Updated weights for policy 0, policy_version 189197 (0.0012) -[2023-11-28 05:09:46,278][87424] Updated weights for policy 0, policy_version 189207 (0.0012) -[2023-11-28 05:09:46,476][87426] Updated weights for policy 1, policy_version 188740 (0.0010) -[2023-11-28 05:09:46,852][87426] Updated weights for policy 1, policy_version 188750 (0.0008) -[2023-11-28 05:09:47,230][87426] Updated weights for policy 1, policy_version 188760 (0.0007) -[2023-11-28 05:09:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 96763904. Throughput: 0: 2765.3, 1: 2612.3. Samples: 96776456. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:48,445][86177] Avg episode reward: [(0, '-512.620'), (1, '-556.250')] -[2023-11-28 05:09:48,659][87424] Updated weights for policy 0, policy_version 189217 (0.0012) -[2023-11-28 05:09:48,901][87426] Updated weights for policy 1, policy_version 188770 (0.0008) -[2023-11-28 05:09:49,043][87424] Updated weights for policy 0, policy_version 189227 (0.0009) -[2023-11-28 05:09:49,271][87426] Updated weights for policy 1, policy_version 188780 (0.0011) -[2023-11-28 05:09:49,430][87424] Updated weights for policy 0, policy_version 189237 (0.0010) -[2023-11-28 05:09:49,654][87426] Updated weights for policy 1, policy_version 188790 (0.0012) -[2023-11-28 05:09:49,813][87424] Updated weights for policy 0, policy_version 189247 (0.0011) -[2023-11-28 05:09:50,033][87426] Updated weights for policy 1, policy_version 188800 (0.0011) -[2023-11-28 05:09:51,718][87424] Updated weights for policy 0, policy_version 189257 (0.0012) -[2023-11-28 05:09:51,967][87426] Updated weights for policy 1, policy_version 188810 (0.0010) -[2023-11-28 05:09:52,092][87424] Updated weights for policy 0, policy_version 189267 (0.0011) -[2023-11-28 05:09:52,356][87426] Updated weights for policy 1, policy_version 188820 (0.0009) -[2023-11-28 05:09:52,482][87424] Updated weights for policy 0, policy_version 189277 (0.0012) -[2023-11-28 05:09:52,730][87426] Updated weights for policy 1, policy_version 188830 (0.0010) -[2023-11-28 05:09:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 96796672. Throughput: 0: 2744.5, 1: 2639.8. Samples: 96809844. Policy #0 lag: (min: 31.0, avg: 35.3, max: 63.0) -[2023-11-28 05:09:53,445][86177] Avg episode reward: [(0, '-512.120'), (1, '-554.770')] -[2023-11-28 05:09:54,749][87424] Updated weights for policy 0, policy_version 189287 (0.0010) -[2023-11-28 05:09:55,116][87424] Updated weights for policy 0, policy_version 189297 (0.0010) -[2023-11-28 05:09:55,234][87426] Updated weights for policy 1, policy_version 188840 (0.0008) -[2023-11-28 05:09:55,499][87424] Updated weights for policy 0, policy_version 189307 (0.0011) -[2023-11-28 05:09:55,603][87426] Updated weights for policy 1, policy_version 188850 (0.0011) -[2023-11-28 05:09:55,985][87426] Updated weights for policy 1, policy_version 188860 (0.0007) -[2023-11-28 05:09:57,307][87424] Updated weights for policy 0, policy_version 189317 (0.0010) -[2023-11-28 05:09:57,692][87424] Updated weights for policy 0, policy_version 189327 (0.0008) -[2023-11-28 05:09:58,076][87424] Updated weights for policy 0, policy_version 189337 (0.0010) -[2023-11-28 05:09:58,233][87426] Updated weights for policy 1, policy_version 188870 (0.0010) -[2023-11-28 05:09:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96821248. Throughput: 0: 2754.0, 1: 2650.3. Samples: 96834128. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:09:58,445][86177] Avg episode reward: [(0, '-550.710'), (1, '-539.640')] -[2023-11-28 05:09:58,613][87426] Updated weights for policy 1, policy_version 188880 (0.0012) -[2023-11-28 05:09:59,004][87426] Updated weights for policy 1, policy_version 188890 (0.0011) -[2023-11-28 05:09:59,746][87424] Updated weights for policy 0, policy_version 189347 (0.0009) -[2023-11-28 05:10:00,130][87424] Updated weights for policy 0, policy_version 189357 (0.0012) -[2023-11-28 05:10:00,516][87424] Updated weights for policy 0, policy_version 189367 (0.0011) -[2023-11-28 05:10:00,885][87426] Updated weights for policy 1, policy_version 188900 (0.0011) -[2023-11-28 05:10:01,262][87426] Updated weights for policy 1, policy_version 188910 (0.0012) -[2023-11-28 05:10:01,657][87426] Updated weights for policy 1, policy_version 188920 (0.0012) -[2023-11-28 05:10:02,902][87424] Updated weights for policy 0, policy_version 189377 (0.0011) -[2023-11-28 05:10:03,284][87424] Updated weights for policy 0, policy_version 189387 (0.0012) -[2023-11-28 05:10:03,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 96845824. Throughput: 0: 2774.1, 1: 2677.3. Samples: 96859728. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:03,446][86177] Avg episode reward: [(0, '-550.270'), (1, '-535.260')] -[2023-11-28 05:10:03,660][87424] Updated weights for policy 0, policy_version 189397 (0.0012) -[2023-11-28 05:10:04,049][87424] Updated weights for policy 0, policy_version 189407 (0.0012) -[2023-11-28 05:10:04,106][87426] Updated weights for policy 1, policy_version 188930 (0.0011) -[2023-11-28 05:10:04,488][87426] Updated weights for policy 1, policy_version 188940 (0.0009) -[2023-11-28 05:10:04,869][87426] Updated weights for policy 1, policy_version 188950 (0.0011) -[2023-11-28 05:10:05,242][87426] Updated weights for policy 1, policy_version 188960 (0.0012) -[2023-11-28 05:10:05,980][87424] Updated weights for policy 0, policy_version 189417 (0.0009) -[2023-11-28 05:10:06,371][87424] Updated weights for policy 0, policy_version 189427 (0.0008) -[2023-11-28 05:10:06,756][87424] Updated weights for policy 0, policy_version 189437 (0.0008) -[2023-11-28 05:10:07,643][87426] Updated weights for policy 1, policy_version 188970 (0.0007) -[2023-11-28 05:10:08,020][87426] Updated weights for policy 1, policy_version 188980 (0.0007) -[2023-11-28 05:10:08,401][87426] Updated weights for policy 1, policy_version 188990 (0.0007) -[2023-11-28 05:10:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 96870400. Throughput: 0: 2781.2, 1: 2701.9. Samples: 96892600. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:08,445][86177] Avg episode reward: [(0, '-567.270'), (1, '-541.990')] -[2023-11-28 05:10:09,161][87424] Updated weights for policy 0, policy_version 189447 (0.0011) -[2023-11-28 05:10:09,549][87424] Updated weights for policy 0, policy_version 189457 (0.0011) -[2023-11-28 05:10:09,935][87424] Updated weights for policy 0, policy_version 189467 (0.0013) -[2023-11-28 05:10:10,206][87426] Updated weights for policy 1, policy_version 189000 (0.0012) -[2023-11-28 05:10:10,587][87426] Updated weights for policy 1, policy_version 189010 (0.0012) -[2023-11-28 05:10:10,962][87426] Updated weights for policy 1, policy_version 189020 (0.0012) -[2023-11-28 05:10:12,410][87424] Updated weights for policy 0, policy_version 189477 (0.0008) -[2023-11-28 05:10:12,791][87424] Updated weights for policy 0, policy_version 189487 (0.0011) -[2023-11-28 05:10:13,176][87424] Updated weights for policy 0, policy_version 189497 (0.0011) -[2023-11-28 05:10:13,362][87426] Updated weights for policy 1, policy_version 189030 (0.0011) -[2023-11-28 05:10:13,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 96903168. Throughput: 0: 2762.4, 1: 2689.0. Samples: 96917220. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:13,445][86177] Avg episode reward: [(0, '-560.770'), (1, '-543.080')] -[2023-11-28 05:10:13,737][87426] Updated weights for policy 1, policy_version 189040 (0.0011) -[2023-11-28 05:10:14,113][87426] Updated weights for policy 1, policy_version 189050 (0.0007) -[2023-11-28 05:10:14,981][87424] Updated weights for policy 0, policy_version 189507 (0.0011) -[2023-11-28 05:10:15,362][87424] Updated weights for policy 0, policy_version 189517 (0.0008) -[2023-11-28 05:10:15,735][87424] Updated weights for policy 0, policy_version 189527 (0.0007) -[2023-11-28 05:10:15,866][87426] Updated weights for policy 1, policy_version 189060 (0.0009) -[2023-11-28 05:10:16,246][87426] Updated weights for policy 1, policy_version 189070 (0.0012) -[2023-11-28 05:10:16,618][87426] Updated weights for policy 1, policy_version 189080 (0.0012) -[2023-11-28 05:10:17,867][87424] Updated weights for policy 0, policy_version 189537 (0.0008) -[2023-11-28 05:10:18,246][87424] Updated weights for policy 0, policy_version 189547 (0.0010) -[2023-11-28 05:10:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 96927744. Throughput: 0: 2793.5, 1: 2691.4. Samples: 96941772. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:18,446][86177] Avg episode reward: [(0, '-525.380'), (1, '-550.600')] -[2023-11-28 05:10:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000189088_48406528.pth... -[2023-11-28 05:10:18,498][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000186560_47759360.pth -[2023-11-28 05:10:18,632][87424] Updated weights for policy 0, policy_version 189557 (0.0008) -[2023-11-28 05:10:18,985][87426] Updated weights for policy 1, policy_version 189090 (0.0012) -[2023-11-28 05:10:19,014][87424] Updated weights for policy 0, policy_version 189567 (0.0009) -[2023-11-28 05:10:19,051][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000189568_48529408.pth... -[2023-11-28 05:10:19,082][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000187008_47874048.pth -[2023-11-28 05:10:19,356][87426] Updated weights for policy 1, policy_version 189100 (0.0011) -[2023-11-28 05:10:19,723][87426] Updated weights for policy 1, policy_version 189110 (0.0011) -[2023-11-28 05:10:20,102][87426] Updated weights for policy 1, policy_version 189120 (0.0011) -[2023-11-28 05:10:21,285][87424] Updated weights for policy 0, policy_version 189577 (0.0011) -[2023-11-28 05:10:21,657][87424] Updated weights for policy 0, policy_version 189587 (0.0012) -[2023-11-28 05:10:22,039][87424] Updated weights for policy 0, policy_version 189597 (0.0012) -[2023-11-28 05:10:22,327][87426] Updated weights for policy 1, policy_version 189130 (0.0010) -[2023-11-28 05:10:22,704][87426] Updated weights for policy 1, policy_version 189140 (0.0012) -[2023-11-28 05:10:23,074][87426] Updated weights for policy 1, policy_version 189150 (0.0011) -[2023-11-28 05:10:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 96960512. Throughput: 0: 2778.2, 1: 2713.9. Samples: 96974508. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:23,446][86177] Avg episode reward: [(0, '-532.420'), (1, '-531.710')] -[2023-11-28 05:10:23,865][87424] Updated weights for policy 0, policy_version 189607 (0.0012) -[2023-11-28 05:10:24,240][87424] Updated weights for policy 0, policy_version 189617 (0.0010) -[2023-11-28 05:10:24,622][87424] Updated weights for policy 0, policy_version 189627 (0.0007) -[2023-11-28 05:10:24,876][87426] Updated weights for policy 1, policy_version 189160 (0.0012) -[2023-11-28 05:10:25,256][87426] Updated weights for policy 1, policy_version 189170 (0.0012) -[2023-11-28 05:10:25,630][87426] Updated weights for policy 1, policy_version 189180 (0.0012) -[2023-11-28 05:10:27,025][87424] Updated weights for policy 0, policy_version 189637 (0.0010) -[2023-11-28 05:10:27,406][87424] Updated weights for policy 0, policy_version 189647 (0.0012) -[2023-11-28 05:10:27,786][87424] Updated weights for policy 0, policy_version 189657 (0.0012) -[2023-11-28 05:10:27,824][87426] Updated weights for policy 1, policy_version 189190 (0.0011) -[2023-11-28 05:10:28,203][87426] Updated weights for policy 1, policy_version 189200 (0.0011) -[2023-11-28 05:10:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 96985088. Throughput: 0: 2762.5, 1: 2770.7. Samples: 96999824. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:28,445][86177] Avg episode reward: [(0, '-555.980'), (1, '-517.150')] -[2023-11-28 05:10:28,592][87426] Updated weights for policy 1, policy_version 189210 (0.0012) -[2023-11-28 05:10:30,003][87424] Updated weights for policy 0, policy_version 189667 (0.0011) -[2023-11-28 05:10:30,383][87424] Updated weights for policy 0, policy_version 189677 (0.0009) -[2023-11-28 05:10:30,588][87426] Updated weights for policy 1, policy_version 189220 (0.0010) -[2023-11-28 05:10:30,757][87424] Updated weights for policy 0, policy_version 189687 (0.0008) -[2023-11-28 05:10:30,970][87426] Updated weights for policy 1, policy_version 189230 (0.0008) -[2023-11-28 05:10:31,349][87426] Updated weights for policy 1, policy_version 189240 (0.0007) -[2023-11-28 05:10:32,932][87424] Updated weights for policy 0, policy_version 189697 (0.0008) -[2023-11-28 05:10:33,321][87424] Updated weights for policy 0, policy_version 189707 (0.0012) -[2023-11-28 05:10:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97009664. Throughput: 0: 2750.2, 1: 2774.0. Samples: 97025044. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:33,445][86177] Avg episode reward: [(0, '-585.130'), (1, '-513.900')] -[2023-11-28 05:10:33,588][87426] Updated weights for policy 1, policy_version 189250 (0.0008) -[2023-11-28 05:10:33,699][87424] Updated weights for policy 0, policy_version 189717 (0.0009) -[2023-11-28 05:10:33,975][87426] Updated weights for policy 1, policy_version 189260 (0.0008) -[2023-11-28 05:10:34,084][87424] Updated weights for policy 0, policy_version 189727 (0.0008) -[2023-11-28 05:10:34,346][87426] Updated weights for policy 1, policy_version 189270 (0.0007) -[2023-11-28 05:10:34,728][87426] Updated weights for policy 1, policy_version 189280 (0.0008) -[2023-11-28 05:10:36,452][87424] Updated weights for policy 0, policy_version 189737 (0.0010) -[2023-11-28 05:10:36,744][87426] Updated weights for policy 1, policy_version 189290 (0.0010) -[2023-11-28 05:10:36,836][87424] Updated weights for policy 0, policy_version 189747 (0.0010) -[2023-11-28 05:10:37,124][87426] Updated weights for policy 1, policy_version 189300 (0.0009) -[2023-11-28 05:10:37,230][87424] Updated weights for policy 0, policy_version 189757 (0.0010) -[2023-11-28 05:10:37,507][87426] Updated weights for policy 1, policy_version 189310 (0.0011) -[2023-11-28 05:10:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 97042432. Throughput: 0: 2736.6, 1: 2738.9. Samples: 97056244. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:38,446][86177] Avg episode reward: [(0, '-610.960'), (1, '-508.300')] -[2023-11-28 05:10:39,347][87424] Updated weights for policy 0, policy_version 189767 (0.0009) -[2023-11-28 05:10:39,733][87424] Updated weights for policy 0, policy_version 189777 (0.0008) -[2023-11-28 05:10:40,057][87426] Updated weights for policy 1, policy_version 189320 (0.0010) -[2023-11-28 05:10:40,111][87424] Updated weights for policy 0, policy_version 189787 (0.0009) -[2023-11-28 05:10:40,436][87426] Updated weights for policy 1, policy_version 189330 (0.0011) -[2023-11-28 05:10:40,807][87426] Updated weights for policy 1, policy_version 189340 (0.0012) -[2023-11-28 05:10:42,174][87424] Updated weights for policy 0, policy_version 189797 (0.0009) -[2023-11-28 05:10:42,556][87424] Updated weights for policy 0, policy_version 189807 (0.0011) -[2023-11-28 05:10:42,927][87426] Updated weights for policy 1, policy_version 189350 (0.0012) -[2023-11-28 05:10:42,944][87424] Updated weights for policy 0, policy_version 189817 (0.0011) -[2023-11-28 05:10:43,309][87426] Updated weights for policy 1, policy_version 189360 (0.0010) -[2023-11-28 05:10:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 97067008. Throughput: 0: 2737.5, 1: 2754.6. Samples: 97081272. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:43,445][86177] Avg episode reward: [(0, '-616.630'), (1, '-510.160')] -[2023-11-28 05:10:43,691][87426] Updated weights for policy 1, policy_version 189370 (0.0007) -[2023-11-28 05:10:45,280][87424] Updated weights for policy 0, policy_version 189827 (0.0012) -[2023-11-28 05:10:45,664][87424] Updated weights for policy 0, policy_version 189837 (0.0011) -[2023-11-28 05:10:46,046][87424] Updated weights for policy 0, policy_version 189847 (0.0012) -[2023-11-28 05:10:46,114][87426] Updated weights for policy 1, policy_version 189380 (0.0010) -[2023-11-28 05:10:46,491][87426] Updated weights for policy 1, policy_version 189390 (0.0007) -[2023-11-28 05:10:46,866][87426] Updated weights for policy 1, policy_version 189400 (0.0008) -[2023-11-28 05:10:48,341][87424] Updated weights for policy 0, policy_version 189857 (0.0012) -[2023-11-28 05:10:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.9). Total num frames: 97091584. Throughput: 0: 2728.5, 1: 2765.7. Samples: 97106964. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:48,445][86177] Avg episode reward: [(0, '-594.180'), (1, '-507.370')] -[2023-11-28 05:10:48,727][87424] Updated weights for policy 0, policy_version 189867 (0.0011) -[2023-11-28 05:10:48,742][87426] Updated weights for policy 1, policy_version 189410 (0.0008) -[2023-11-28 05:10:49,107][87424] Updated weights for policy 0, policy_version 189877 (0.0012) -[2023-11-28 05:10:49,124][87426] Updated weights for policy 1, policy_version 189420 (0.0009) -[2023-11-28 05:10:49,488][87424] Updated weights for policy 0, policy_version 189887 (0.0011) -[2023-11-28 05:10:49,505][87426] Updated weights for policy 1, policy_version 189430 (0.0009) -[2023-11-28 05:10:49,874][87426] Updated weights for policy 1, policy_version 189440 (0.0012) -[2023-11-28 05:10:51,286][87424] Updated weights for policy 0, policy_version 189897 (0.0009) -[2023-11-28 05:10:51,666][87424] Updated weights for policy 0, policy_version 189907 (0.0009) -[2023-11-28 05:10:51,892][87426] Updated weights for policy 1, policy_version 189450 (0.0011) -[2023-11-28 05:10:52,047][87424] Updated weights for policy 0, policy_version 189917 (0.0010) -[2023-11-28 05:10:52,273][87426] Updated weights for policy 1, policy_version 189460 (0.0011) -[2023-11-28 05:10:52,647][87426] Updated weights for policy 1, policy_version 189470 (0.0012) -[2023-11-28 05:10:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 97124352. Throughput: 0: 2735.5, 1: 2765.0. Samples: 97140120. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:53,445][86177] Avg episode reward: [(0, '-562.600'), (1, '-535.000')] -[2023-11-28 05:10:53,938][87424] Updated weights for policy 0, policy_version 189927 (0.0010) -[2023-11-28 05:10:54,317][87424] Updated weights for policy 0, policy_version 189937 (0.0007) -[2023-11-28 05:10:54,683][87426] Updated weights for policy 1, policy_version 189480 (0.0011) -[2023-11-28 05:10:54,697][87424] Updated weights for policy 0, policy_version 189947 (0.0010) -[2023-11-28 05:10:55,067][87426] Updated weights for policy 1, policy_version 189490 (0.0012) -[2023-11-28 05:10:55,446][87426] Updated weights for policy 1, policy_version 189500 (0.0011) -[2023-11-28 05:10:56,924][87424] Updated weights for policy 0, policy_version 189957 (0.0010) -[2023-11-28 05:10:57,322][87424] Updated weights for policy 0, policy_version 189967 (0.0012) -[2023-11-28 05:10:57,699][87424] Updated weights for policy 0, policy_version 189977 (0.0010) -[2023-11-28 05:10:57,781][87426] Updated weights for policy 1, policy_version 189510 (0.0007) -[2023-11-28 05:10:58,169][87426] Updated weights for policy 1, policy_version 189520 (0.0011) -[2023-11-28 05:10:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 97148928. Throughput: 0: 2739.9, 1: 2742.3. Samples: 97163920. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:10:58,445][86177] Avg episode reward: [(0, '-529.960'), (1, '-538.230')] -[2023-11-28 05:10:58,539][87426] Updated weights for policy 1, policy_version 189530 (0.0012) -[2023-11-28 05:10:59,658][87424] Updated weights for policy 0, policy_version 189987 (0.0008) -[2023-11-28 05:11:00,043][87424] Updated weights for policy 0, policy_version 189997 (0.0010) -[2023-11-28 05:11:00,345][87426] Updated weights for policy 1, policy_version 189540 (0.0012) -[2023-11-28 05:11:00,410][87424] Updated weights for policy 0, policy_version 190007 (0.0009) -[2023-11-28 05:11:00,718][87426] Updated weights for policy 1, policy_version 189550 (0.0007) -[2023-11-28 05:11:01,098][87426] Updated weights for policy 1, policy_version 189560 (0.0008) -[2023-11-28 05:11:02,506][87424] Updated weights for policy 0, policy_version 190017 (0.0011) -[2023-11-28 05:11:02,898][87424] Updated weights for policy 0, policy_version 190027 (0.0009) -[2023-11-28 05:11:03,268][87424] Updated weights for policy 0, policy_version 190037 (0.0011) -[2023-11-28 05:11:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 97173504. Throughput: 0: 2738.3, 1: 2756.5. Samples: 97189036. Policy #0 lag: (min: 31.0, avg: 46.7, max: 63.0) -[2023-11-28 05:11:03,445][86177] Avg episode reward: [(0, '-539.300'), (1, '-532.640')] -[2023-11-28 05:11:03,545][87426] Updated weights for policy 1, policy_version 189570 (0.0007) -[2023-11-28 05:11:03,649][87424] Updated weights for policy 0, policy_version 190047 (0.0008) -[2023-11-28 05:11:03,927][87426] Updated weights for policy 1, policy_version 189580 (0.0007) -[2023-11-28 05:11:04,317][87426] Updated weights for policy 1, policy_version 189590 (0.0007) -[2023-11-28 05:11:04,697][87426] Updated weights for policy 1, policy_version 189600 (0.0008) -[2023-11-28 05:11:06,161][87424] Updated weights for policy 0, policy_version 190057 (0.0011) -[2023-11-28 05:11:06,544][87424] Updated weights for policy 0, policy_version 190067 (0.0012) -[2023-11-28 05:11:06,921][87424] Updated weights for policy 0, policy_version 190077 (0.0012) -[2023-11-28 05:11:07,175][87426] Updated weights for policy 1, policy_version 189610 (0.0011) -[2023-11-28 05:11:07,544][87426] Updated weights for policy 1, policy_version 189620 (0.0011) -[2023-11-28 05:11:07,922][87426] Updated weights for policy 1, policy_version 189630 (0.0011) -[2023-11-28 05:11:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 97206272. Throughput: 0: 2739.1, 1: 2755.0. Samples: 97221744. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:08,445][86177] Avg episode reward: [(0, '-541.080'), (1, '-535.740')] -[2023-11-28 05:11:08,956][87424] Updated weights for policy 0, policy_version 190087 (0.0011) -[2023-11-28 05:11:09,334][87424] Updated weights for policy 0, policy_version 190097 (0.0012) -[2023-11-28 05:11:09,717][87424] Updated weights for policy 0, policy_version 190107 (0.0012) -[2023-11-28 05:11:10,266][87426] Updated weights for policy 1, policy_version 189640 (0.0012) -[2023-11-28 05:11:10,648][87426] Updated weights for policy 1, policy_version 189650 (0.0012) -[2023-11-28 05:11:11,029][87426] Updated weights for policy 1, policy_version 189660 (0.0012) -[2023-11-28 05:11:11,987][87424] Updated weights for policy 0, policy_version 190117 (0.0011) -[2023-11-28 05:11:12,384][87424] Updated weights for policy 0, policy_version 190127 (0.0011) -[2023-11-28 05:11:12,766][87424] Updated weights for policy 0, policy_version 190137 (0.0012) -[2023-11-28 05:11:13,073][87426] Updated weights for policy 1, policy_version 189670 (0.0010) -[2023-11-28 05:11:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 97230848. Throughput: 0: 2749.9, 1: 2712.5. Samples: 97245628. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:13,445][86177] Avg episode reward: [(0, '-534.250'), (1, '-508.660')] -[2023-11-28 05:11:13,457][87426] Updated weights for policy 1, policy_version 189680 (0.0008) -[2023-11-28 05:11:13,834][87426] Updated weights for policy 1, policy_version 189690 (0.0011) -[2023-11-28 05:11:14,929][87424] Updated weights for policy 0, policy_version 190147 (0.0012) -[2023-11-28 05:11:15,298][87424] Updated weights for policy 0, policy_version 190157 (0.0012) -[2023-11-28 05:11:15,690][87424] Updated weights for policy 0, policy_version 190167 (0.0010) -[2023-11-28 05:11:15,721][87426] Updated weights for policy 1, policy_version 189700 (0.0010) -[2023-11-28 05:11:16,102][87426] Updated weights for policy 1, policy_version 189710 (0.0011) -[2023-11-28 05:11:16,482][87426] Updated weights for policy 1, policy_version 189720 (0.0011) -[2023-11-28 05:11:17,289][87424] Updated weights for policy 0, policy_version 190177 (0.0008) -[2023-11-28 05:11:17,683][87424] Updated weights for policy 0, policy_version 190187 (0.0011) -[2023-11-28 05:11:18,058][87424] Updated weights for policy 0, policy_version 190197 (0.0011) -[2023-11-28 05:11:18,443][87424] Updated weights for policy 0, policy_version 190207 (0.0012) -[2023-11-28 05:11:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 97255424. Throughput: 0: 2749.0, 1: 2705.4. Samples: 97270492. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:18,445][86177] Avg episode reward: [(0, '-534.510'), (1, '-504.980')] -[2023-11-28 05:11:19,098][87426] Updated weights for policy 1, policy_version 189730 (0.0011) -[2023-11-28 05:11:19,480][87426] Updated weights for policy 1, policy_version 189740 (0.0011) -[2023-11-28 05:11:19,858][87426] Updated weights for policy 1, policy_version 189750 (0.0011) -[2023-11-28 05:11:20,240][87426] Updated weights for policy 1, policy_version 189760 (0.0011) -[2023-11-28 05:11:20,871][87424] Updated weights for policy 0, policy_version 190217 (0.0011) -[2023-11-28 05:11:21,256][87424] Updated weights for policy 0, policy_version 190227 (0.0010) -[2023-11-28 05:11:21,636][87424] Updated weights for policy 0, policy_version 190237 (0.0010) -[2023-11-28 05:11:22,602][87426] Updated weights for policy 1, policy_version 189770 (0.0011) -[2023-11-28 05:11:22,985][87426] Updated weights for policy 1, policy_version 189780 (0.0009) -[2023-11-28 05:11:23,369][87426] Updated weights for policy 1, policy_version 189790 (0.0009) -[2023-11-28 05:11:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 97288192. Throughput: 0: 2745.9, 1: 2709.2. Samples: 97301720. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:23,445][86177] Avg episode reward: [(0, '-530.370'), (1, '-500.480')] -[2023-11-28 05:11:23,864][87424] Updated weights for policy 0, policy_version 190247 (0.0010) -[2023-11-28 05:11:24,237][87424] Updated weights for policy 0, policy_version 190257 (0.0008) -[2023-11-28 05:11:24,624][87424] Updated weights for policy 0, policy_version 190267 (0.0007) -[2023-11-28 05:11:25,808][87426] Updated weights for policy 1, policy_version 189800 (0.0012) -[2023-11-28 05:11:26,183][87426] Updated weights for policy 1, policy_version 189810 (0.0012) -[2023-11-28 05:11:26,562][87426] Updated weights for policy 1, policy_version 189820 (0.0012) -[2023-11-28 05:11:26,938][87424] Updated weights for policy 0, policy_version 190277 (0.0008) -[2023-11-28 05:11:27,315][87424] Updated weights for policy 0, policy_version 190287 (0.0008) -[2023-11-28 05:11:27,696][87424] Updated weights for policy 0, policy_version 190297 (0.0012) -[2023-11-28 05:11:28,288][87426] Updated weights for policy 1, policy_version 189830 (0.0012) -[2023-11-28 05:11:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97312768. Throughput: 0: 2734.8, 1: 2709.2. Samples: 97326252. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:28,445][86177] Avg episode reward: [(0, '-535.440'), (1, '-509.840')] -[2023-11-28 05:11:28,668][87426] Updated weights for policy 1, policy_version 189840 (0.0011) -[2023-11-28 05:11:29,046][87426] Updated weights for policy 1, policy_version 189850 (0.0011) -[2023-11-28 05:11:29,986][87424] Updated weights for policy 0, policy_version 190307 (0.0012) -[2023-11-28 05:11:30,368][87424] Updated weights for policy 0, policy_version 190317 (0.0011) -[2023-11-28 05:11:30,746][87424] Updated weights for policy 0, policy_version 190327 (0.0008) -[2023-11-28 05:11:30,908][87426] Updated weights for policy 1, policy_version 189860 (0.0010) -[2023-11-28 05:11:31,282][87426] Updated weights for policy 1, policy_version 189870 (0.0011) -[2023-11-28 05:11:31,657][87426] Updated weights for policy 1, policy_version 189880 (0.0010) -[2023-11-28 05:11:33,309][87424] Updated weights for policy 0, policy_version 190337 (0.0007) -[2023-11-28 05:11:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97337344. Throughput: 0: 2712.9, 1: 2695.7. Samples: 97350352. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:33,445][86177] Avg episode reward: [(0, '-532.590'), (1, '-512.050')] -[2023-11-28 05:11:33,680][87424] Updated weights for policy 0, policy_version 190347 (0.0007) -[2023-11-28 05:11:33,856][87426] Updated weights for policy 1, policy_version 189890 (0.0009) -[2023-11-28 05:11:34,064][87424] Updated weights for policy 0, policy_version 190357 (0.0009) -[2023-11-28 05:11:34,235][87426] Updated weights for policy 1, policy_version 189900 (0.0010) -[2023-11-28 05:11:34,446][87424] Updated weights for policy 0, policy_version 190367 (0.0007) -[2023-11-28 05:11:34,617][87426] Updated weights for policy 1, policy_version 189910 (0.0012) -[2023-11-28 05:11:34,992][87426] Updated weights for policy 1, policy_version 189920 (0.0010) -[2023-11-28 05:11:36,369][87424] Updated weights for policy 0, policy_version 190377 (0.0011) -[2023-11-28 05:11:36,749][87424] Updated weights for policy 0, policy_version 190387 (0.0010) -[2023-11-28 05:11:37,070][87426] Updated weights for policy 1, policy_version 189930 (0.0010) -[2023-11-28 05:11:37,136][87424] Updated weights for policy 0, policy_version 190397 (0.0008) -[2023-11-28 05:11:37,443][87426] Updated weights for policy 1, policy_version 189940 (0.0008) -[2023-11-28 05:11:37,823][87426] Updated weights for policy 1, policy_version 189950 (0.0011) -[2023-11-28 05:11:38,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97370112. Throughput: 0: 2693.7, 1: 2690.1. Samples: 97382392. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:38,446][86177] Avg episode reward: [(0, '-546.560'), (1, '-520.600')] -[2023-11-28 05:11:39,382][87424] Updated weights for policy 0, policy_version 190407 (0.0011) -[2023-11-28 05:11:39,762][87424] Updated weights for policy 0, policy_version 190417 (0.0012) -[2023-11-28 05:11:40,142][87424] Updated weights for policy 0, policy_version 190427 (0.0012) -[2023-11-28 05:11:40,410][87426] Updated weights for policy 1, policy_version 189960 (0.0011) -[2023-11-28 05:11:40,789][87426] Updated weights for policy 1, policy_version 189970 (0.0012) -[2023-11-28 05:11:41,175][87426] Updated weights for policy 1, policy_version 189980 (0.0011) -[2023-11-28 05:11:42,566][87424] Updated weights for policy 0, policy_version 190437 (0.0011) -[2023-11-28 05:11:42,947][87424] Updated weights for policy 0, policy_version 190447 (0.0010) -[2023-11-28 05:11:43,102][87426] Updated weights for policy 1, policy_version 189990 (0.0011) -[2023-11-28 05:11:43,327][87424] Updated weights for policy 0, policy_version 190457 (0.0012) -[2023-11-28 05:11:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 97386496. Throughput: 0: 2696.2, 1: 2705.4. Samples: 97406992. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:43,445][86177] Avg episode reward: [(0, '-538.760'), (1, '-548.470')] -[2023-11-28 05:11:43,480][87426] Updated weights for policy 1, policy_version 190000 (0.0010) -[2023-11-28 05:11:43,862][87426] Updated weights for policy 1, policy_version 190010 (0.0011) -[2023-11-28 05:11:45,439][87424] Updated weights for policy 0, policy_version 190467 (0.0012) -[2023-11-28 05:11:45,811][87424] Updated weights for policy 0, policy_version 190477 (0.0011) -[2023-11-28 05:11:46,192][87424] Updated weights for policy 0, policy_version 190487 (0.0012) -[2023-11-28 05:11:46,439][87426] Updated weights for policy 1, policy_version 190020 (0.0011) -[2023-11-28 05:11:46,828][87426] Updated weights for policy 1, policy_version 190030 (0.0009) -[2023-11-28 05:11:47,197][87426] Updated weights for policy 1, policy_version 190040 (0.0007) -[2023-11-28 05:11:47,793][87424] Updated weights for policy 0, policy_version 190497 (0.0012) -[2023-11-28 05:11:48,181][87424] Updated weights for policy 0, policy_version 190507 (0.0011) -[2023-11-28 05:11:48,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97419264. Throughput: 0: 2683.7, 1: 2708.8. Samples: 97431700. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:48,446][86177] Avg episode reward: [(0, '-537.920'), (1, '-537.300')] -[2023-11-28 05:11:48,557][87424] Updated weights for policy 0, policy_version 190517 (0.0007) -[2023-11-28 05:11:48,940][87424] Updated weights for policy 0, policy_version 190527 (0.0008) -[2023-11-28 05:11:49,310][87426] Updated weights for policy 1, policy_version 190050 (0.0008) -[2023-11-28 05:11:49,677][87426] Updated weights for policy 1, policy_version 190060 (0.0011) -[2023-11-28 05:11:50,064][87426] Updated weights for policy 1, policy_version 190070 (0.0012) -[2023-11-28 05:11:50,437][87426] Updated weights for policy 1, policy_version 190080 (0.0011) -[2023-11-28 05:11:51,200][87424] Updated weights for policy 0, policy_version 190537 (0.0012) -[2023-11-28 05:11:51,577][87424] Updated weights for policy 0, policy_version 190547 (0.0012) -[2023-11-28 05:11:51,946][87424] Updated weights for policy 0, policy_version 190557 (0.0012) -[2023-11-28 05:11:52,877][87426] Updated weights for policy 1, policy_version 190090 (0.0010) -[2023-11-28 05:11:53,257][87426] Updated weights for policy 1, policy_version 190100 (0.0009) -[2023-11-28 05:11:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 97443840. Throughput: 0: 2671.7, 1: 2701.1. Samples: 97463520. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:53,445][86177] Avg episode reward: [(0, '-512.780'), (1, '-534.390')] -[2023-11-28 05:11:53,625][87426] Updated weights for policy 1, policy_version 190110 (0.0010) -[2023-11-28 05:11:54,416][87424] Updated weights for policy 0, policy_version 190567 (0.0012) -[2023-11-28 05:11:54,797][87424] Updated weights for policy 0, policy_version 190577 (0.0012) -[2023-11-28 05:11:55,189][87424] Updated weights for policy 0, policy_version 190587 (0.0012) -[2023-11-28 05:11:55,927][87426] Updated weights for policy 1, policy_version 190120 (0.0011) -[2023-11-28 05:11:56,310][87426] Updated weights for policy 1, policy_version 190130 (0.0012) -[2023-11-28 05:11:56,692][87426] Updated weights for policy 1, policy_version 190140 (0.0011) -[2023-11-28 05:11:57,491][87424] Updated weights for policy 0, policy_version 190597 (0.0012) -[2023-11-28 05:11:57,869][87424] Updated weights for policy 0, policy_version 190607 (0.0012) -[2023-11-28 05:11:58,265][87424] Updated weights for policy 0, policy_version 190617 (0.0011) -[2023-11-28 05:11:58,378][87426] Updated weights for policy 1, policy_version 190150 (0.0012) -[2023-11-28 05:11:58,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 97468416. Throughput: 0: 2658.7, 1: 2705.3. Samples: 97487008. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:11:58,445][86177] Avg episode reward: [(0, '-508.860'), (1, '-527.100')] -[2023-11-28 05:11:58,757][87426] Updated weights for policy 1, policy_version 190160 (0.0011) -[2023-11-28 05:11:59,141][87426] Updated weights for policy 1, policy_version 190170 (0.0010) -[2023-11-28 05:12:00,792][87424] Updated weights for policy 0, policy_version 190627 (0.0012) -[2023-11-28 05:12:01,163][87424] Updated weights for policy 0, policy_version 190637 (0.0009) -[2023-11-28 05:12:01,489][87426] Updated weights for policy 1, policy_version 190180 (0.0007) -[2023-11-28 05:12:01,553][87424] Updated weights for policy 0, policy_version 190647 (0.0009) -[2023-11-28 05:12:01,871][87426] Updated weights for policy 1, policy_version 190190 (0.0010) -[2023-11-28 05:12:02,244][87426] Updated weights for policy 1, policy_version 190200 (0.0012) -[2023-11-28 05:12:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97501184. Throughput: 0: 2651.0, 1: 2709.7. Samples: 97511724. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:12:03,446][86177] Avg episode reward: [(0, '-510.110'), (1, '-534.860')] -[2023-11-28 05:12:03,877][87424] Updated weights for policy 0, policy_version 190657 (0.0010) -[2023-11-28 05:12:04,225][87426] Updated weights for policy 1, policy_version 190210 (0.0010) -[2023-11-28 05:12:04,270][87424] Updated weights for policy 0, policy_version 190667 (0.0010) -[2023-11-28 05:12:04,614][87426] Updated weights for policy 1, policy_version 190220 (0.0010) -[2023-11-28 05:12:04,653][87424] Updated weights for policy 0, policy_version 190677 (0.0009) -[2023-11-28 05:12:04,983][87426] Updated weights for policy 1, policy_version 190230 (0.0012) -[2023-11-28 05:12:05,033][87424] Updated weights for policy 0, policy_version 190687 (0.0010) -[2023-11-28 05:12:05,363][87426] Updated weights for policy 1, policy_version 190240 (0.0010) -[2023-11-28 05:12:07,187][87426] Updated weights for policy 1, policy_version 190250 (0.0011) -[2023-11-28 05:12:07,450][87424] Updated weights for policy 0, policy_version 190697 (0.0010) -[2023-11-28 05:12:07,567][87426] Updated weights for policy 1, policy_version 190260 (0.0009) -[2023-11-28 05:12:07,821][87424] Updated weights for policy 0, policy_version 190707 (0.0010) -[2023-11-28 05:12:07,950][87426] Updated weights for policy 1, policy_version 190270 (0.0008) -[2023-11-28 05:12:08,206][87424] Updated weights for policy 0, policy_version 190717 (0.0012) -[2023-11-28 05:12:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 97533952. Throughput: 0: 2667.9, 1: 2751.9. Samples: 97545612. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:12:08,445][86177] Avg episode reward: [(0, '-496.230'), (1, '-534.360')] -[2023-11-28 05:12:09,851][87426] Updated weights for policy 1, policy_version 190280 (0.0011) -[2023-11-28 05:12:10,237][87426] Updated weights for policy 1, policy_version 190290 (0.0008) -[2023-11-28 05:12:10,608][87426] Updated weights for policy 1, policy_version 190300 (0.0011) -[2023-11-28 05:12:10,745][87424] Updated weights for policy 0, policy_version 190727 (0.0010) -[2023-11-28 05:12:11,126][87424] Updated weights for policy 0, policy_version 190737 (0.0008) -[2023-11-28 05:12:11,507][87424] Updated weights for policy 0, policy_version 190747 (0.0008) -[2023-11-28 05:12:12,921][87426] Updated weights for policy 1, policy_version 190310 (0.0012) -[2023-11-28 05:12:13,301][87426] Updated weights for policy 1, policy_version 190320 (0.0012) -[2023-11-28 05:12:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 97550336. Throughput: 0: 2661.4, 1: 2752.1. Samples: 97569860. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 05:12:13,445][86177] Avg episode reward: [(0, '-511.040'), (1, '-553.500')] -[2023-11-28 05:12:13,683][87426] Updated weights for policy 1, policy_version 190330 (0.0011) -[2023-11-28 05:12:13,817][87424] Updated weights for policy 0, policy_version 190757 (0.0009) -[2023-11-28 05:12:14,200][87424] Updated weights for policy 0, policy_version 190767 (0.0011) -[2023-11-28 05:12:14,581][87424] Updated weights for policy 0, policy_version 190777 (0.0008) -[2023-11-28 05:12:15,472][87426] Updated weights for policy 1, policy_version 190340 (0.0010) -[2023-11-28 05:12:15,855][87426] Updated weights for policy 1, policy_version 190350 (0.0009) -[2023-11-28 05:12:16,233][87426] Updated weights for policy 1, policy_version 190360 (0.0007) -[2023-11-28 05:12:16,841][87424] Updated weights for policy 0, policy_version 190787 (0.0010) -[2023-11-28 05:12:17,212][87424] Updated weights for policy 0, policy_version 190797 (0.0012) -[2023-11-28 05:12:17,587][87424] Updated weights for policy 0, policy_version 190807 (0.0012) -[2023-11-28 05:12:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97583104. Throughput: 0: 2657.1, 1: 2753.0. Samples: 97593808. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:12:18,445][86177] Avg episode reward: [(0, '-512.520'), (1, '-576.710')] -[2023-11-28 05:12:18,451][87426] Updated weights for policy 1, policy_version 190370 (0.0008) -[2023-11-28 05:12:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000190816_48848896.pth... -[2023-11-28 05:12:18,488][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000188256_48193536.pth -[2023-11-28 05:12:18,493][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000190816_48848896.pth -[2023-11-28 05:12:18,823][87426] Updated weights for policy 1, policy_version 190380 (0.0008) -[2023-11-28 05:12:19,208][87426] Updated weights for policy 1, policy_version 190390 (0.0009) -[2023-11-28 05:12:19,462][87424] Updated weights for policy 0, policy_version 190817 (0.0012) -[2023-11-28 05:12:19,586][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000190400_48742400.pth... -[2023-11-28 05:12:19,587][87426] Updated weights for policy 1, policy_version 190400 (0.0012) -[2023-11-28 05:12:19,632][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000187840_48087040.pth -[2023-11-28 05:12:19,640][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000190400_48742400.pth -[2023-11-28 05:12:19,838][87424] Updated weights for policy 0, policy_version 190827 (0.0011) -[2023-11-28 05:12:20,230][87424] Updated weights for policy 0, policy_version 190837 (0.0012) -[2023-11-28 05:12:20,603][87424] Updated weights for policy 0, policy_version 190847 (0.0012) -[2023-11-28 05:12:21,716][87426] Updated weights for policy 1, policy_version 190410 (0.0011) -[2023-11-28 05:12:22,094][87426] Updated weights for policy 1, policy_version 190420 (0.0010) -[2023-11-28 05:12:22,473][87426] Updated weights for policy 1, policy_version 190430 (0.0012) -[2023-11-28 05:12:23,045][87424] Updated weights for policy 0, policy_version 190857 (0.0012) -[2023-11-28 05:12:23,421][87424] Updated weights for policy 0, policy_version 190867 (0.0012) -[2023-11-28 05:12:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 97607680. Throughput: 0: 2667.6, 1: 2767.9. Samples: 97626988. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:12:23,445][86177] Avg episode reward: [(0, '-511.440'), (1, '-552.190')] -[2023-11-28 05:12:23,806][87424] Updated weights for policy 0, policy_version 190877 (0.0012) -[2023-11-28 05:12:24,645][87426] Updated weights for policy 1, policy_version 190440 (0.0011) -[2023-11-28 05:12:25,024][87426] Updated weights for policy 1, policy_version 190450 (0.0011) -[2023-11-28 05:12:25,403][87426] Updated weights for policy 1, policy_version 190460 (0.0011) -[2023-11-28 05:12:25,748][87424] Updated weights for policy 0, policy_version 190887 (0.0011) -[2023-11-28 05:12:26,125][87424] Updated weights for policy 0, policy_version 190897 (0.0009) -[2023-11-28 05:12:26,503][87424] Updated weights for policy 0, policy_version 190907 (0.0008) -[2023-11-28 05:12:27,300][87426] Updated weights for policy 1, policy_version 190470 (0.0010) -[2023-11-28 05:12:27,679][87426] Updated weights for policy 1, policy_version 190480 (0.0009) -[2023-11-28 05:12:28,057][87426] Updated weights for policy 1, policy_version 190490 (0.0012) -[2023-11-28 05:12:28,301][87424] Updated weights for policy 0, policy_version 190917 (0.0007) -[2023-11-28 05:12:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 97640448. Throughput: 0: 2690.5, 1: 2764.9. Samples: 97652484. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:12:28,445][86177] Avg episode reward: [(0, '-511.810'), (1, '-551.780')] -[2023-11-28 05:12:28,687][87424] Updated weights for policy 0, policy_version 190927 (0.0007) -[2023-11-28 05:12:29,072][87424] Updated weights for policy 0, policy_version 190937 (0.0008) -[2023-11-28 05:12:29,932][87426] Updated weights for policy 1, policy_version 190500 (0.0011) -[2023-11-28 05:12:30,318][87426] Updated weights for policy 1, policy_version 190510 (0.0011) -[2023-11-28 05:12:30,702][87426] Updated weights for policy 1, policy_version 190520 (0.0012) -[2023-11-28 05:12:31,472][87424] Updated weights for policy 0, policy_version 190947 (0.0009) -[2023-11-28 05:12:31,852][87424] Updated weights for policy 0, policy_version 190957 (0.0012) -[2023-11-28 05:12:32,238][87424] Updated weights for policy 0, policy_version 190967 (0.0010) -[2023-11-28 05:12:33,083][87426] Updated weights for policy 1, policy_version 190530 (0.0011) -[2023-11-28 05:12:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97665024. Throughput: 0: 2691.4, 1: 2772.6. Samples: 97677580. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:12:33,445][86177] Avg episode reward: [(0, '-497.350'), (1, '-540.350')] -[2023-11-28 05:12:33,470][87426] Updated weights for policy 1, policy_version 190540 (0.0012) -[2023-11-28 05:12:33,842][87426] Updated weights for policy 1, policy_version 190550 (0.0010) -[2023-11-28 05:12:34,217][87426] Updated weights for policy 1, policy_version 190560 (0.0008) -[2023-11-28 05:12:34,581][87424] Updated weights for policy 0, policy_version 190977 (0.0008) -[2023-11-28 05:12:34,963][87424] Updated weights for policy 0, policy_version 190987 (0.0010) -[2023-11-28 05:12:35,345][87424] Updated weights for policy 0, policy_version 190997 (0.0008) -[2023-11-28 05:12:35,734][87424] Updated weights for policy 0, policy_version 191007 (0.0009) -[2023-11-28 05:12:36,382][87426] Updated weights for policy 1, policy_version 190570 (0.0012) -[2023-11-28 05:12:36,749][87426] Updated weights for policy 1, policy_version 190580 (0.0008) -[2023-11-28 05:12:37,132][87426] Updated weights for policy 1, policy_version 190590 (0.0011) -[2023-11-28 05:12:37,782][87424] Updated weights for policy 0, policy_version 191017 (0.0012) -[2023-11-28 05:12:38,157][87424] Updated weights for policy 0, policy_version 191027 (0.0012) -[2023-11-28 05:12:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 97689600. Throughput: 0: 2695.9, 1: 2763.9. Samples: 97709212. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:12:38,446][86177] Avg episode reward: [(0, '-504.160'), (1, '-520.840')] -[2023-11-28 05:12:38,542][87424] Updated weights for policy 0, policy_version 191037 (0.0012) -[2023-11-28 05:12:39,108][87426] Updated weights for policy 1, policy_version 190600 (0.0012) -[2023-11-28 05:12:39,491][87426] Updated weights for policy 1, policy_version 190610 (0.0012) -[2023-11-28 05:12:39,866][87426] Updated weights for policy 1, policy_version 190620 (0.0012) -[2023-11-28 05:12:40,920][87424] Updated weights for policy 0, policy_version 191047 (0.0011) -[2023-11-28 05:12:41,304][87424] Updated weights for policy 0, policy_version 191057 (0.0008) -[2023-11-28 05:12:41,686][87424] Updated weights for policy 0, policy_version 191067 (0.0008) -[2023-11-28 05:12:42,313][87426] Updated weights for policy 1, policy_version 190630 (0.0011) -[2023-11-28 05:12:42,682][87426] Updated weights for policy 1, policy_version 190640 (0.0012) -[2023-11-28 05:12:43,068][87426] Updated weights for policy 1, policy_version 190650 (0.0012) -[2023-11-28 05:12:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 97722368. Throughput: 0: 2709.3, 1: 2762.3. Samples: 97733232. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:12:43,445][86177] Avg episode reward: [(0, '-526.180'), (1, '-503.810')] -[2023-11-28 05:12:43,980][87424] Updated weights for policy 0, policy_version 191077 (0.0011) -[2023-11-28 05:12:44,372][87424] Updated weights for policy 0, policy_version 191087 (0.0012) -[2023-11-28 05:12:44,751][87424] Updated weights for policy 0, policy_version 191097 (0.0012) -[2023-11-28 05:12:45,105][87426] Updated weights for policy 1, policy_version 190660 (0.0011) -[2023-11-28 05:12:45,486][87426] Updated weights for policy 1, policy_version 190670 (0.0010) -[2023-11-28 05:12:45,865][87426] Updated weights for policy 1, policy_version 190680 (0.0012) -[2023-11-28 05:12:47,067][87424] Updated weights for policy 0, policy_version 191107 (0.0009) -[2023-11-28 05:12:47,455][87424] Updated weights for policy 0, policy_version 191117 (0.0007) -[2023-11-28 05:12:47,839][87424] Updated weights for policy 0, policy_version 191127 (0.0007) -[2023-11-28 05:12:47,987][87426] Updated weights for policy 1, policy_version 190690 (0.0011) -[2023-11-28 05:12:48,371][87426] Updated weights for policy 1, policy_version 190700 (0.0009) -[2023-11-28 05:12:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97746944. Throughput: 0: 2687.4, 1: 2767.4. Samples: 97757188. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:12:48,446][86177] Avg episode reward: [(0, '-528.670'), (1, '-514.770')] -[2023-11-28 05:12:48,750][87426] Updated weights for policy 1, policy_version 190710 (0.0011) -[2023-11-28 05:12:49,123][87426] Updated weights for policy 1, policy_version 190720 (0.0010) -[2023-11-28 05:12:49,539][87424] Updated weights for policy 0, policy_version 191137 (0.0012) -[2023-11-28 05:12:49,922][87424] Updated weights for policy 0, policy_version 191147 (0.0010) -[2023-11-28 05:12:50,303][87424] Updated weights for policy 0, policy_version 191157 (0.0008) -[2023-11-28 05:12:50,692][87424] Updated weights for policy 0, policy_version 191167 (0.0009) -[2023-11-28 05:12:51,298][87426] Updated weights for policy 1, policy_version 190730 (0.0012) -[2023-11-28 05:12:51,669][87426] Updated weights for policy 1, policy_version 190740 (0.0012) -[2023-11-28 05:12:52,049][87426] Updated weights for policy 1, policy_version 190750 (0.0012) -[2023-11-28 05:12:53,044][87424] Updated weights for policy 0, policy_version 191177 (0.0012) -[2023-11-28 05:12:53,426][87424] Updated weights for policy 0, policy_version 191187 (0.0012) -[2023-11-28 05:12:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97771520. Throughput: 0: 2687.5, 1: 2740.4. Samples: 97789868. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:12:53,445][86177] Avg episode reward: [(0, '-527.390'), (1, '-509.530')] -[2023-11-28 05:12:53,813][87424] Updated weights for policy 0, policy_version 191197 (0.0012) -[2023-11-28 05:12:54,675][87426] Updated weights for policy 1, policy_version 190760 (0.0012) -[2023-11-28 05:12:55,061][87426] Updated weights for policy 1, policy_version 190770 (0.0012) -[2023-11-28 05:12:55,434][87426] Updated weights for policy 1, policy_version 190780 (0.0012) -[2023-11-28 05:12:55,829][87424] Updated weights for policy 0, policy_version 191207 (0.0012) -[2023-11-28 05:12:56,211][87424] Updated weights for policy 0, policy_version 191217 (0.0012) -[2023-11-28 05:12:56,592][87424] Updated weights for policy 0, policy_version 191227 (0.0012) -[2023-11-28 05:12:57,945][87426] Updated weights for policy 1, policy_version 190790 (0.0010) -[2023-11-28 05:12:58,328][87426] Updated weights for policy 1, policy_version 190800 (0.0007) -[2023-11-28 05:12:58,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97796096. Throughput: 0: 2711.4, 1: 2744.2. Samples: 97815364. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:12:58,446][86177] Avg episode reward: [(0, '-513.570'), (1, '-517.360')] -[2023-11-28 05:12:58,716][87426] Updated weights for policy 1, policy_version 190810 (0.0010) -[2023-11-28 05:12:58,802][87424] Updated weights for policy 0, policy_version 191237 (0.0010) -[2023-11-28 05:12:59,184][87424] Updated weights for policy 0, policy_version 191247 (0.0009) -[2023-11-28 05:12:59,574][87424] Updated weights for policy 0, policy_version 191257 (0.0011) -[2023-11-28 05:13:00,508][87426] Updated weights for policy 1, policy_version 190820 (0.0012) -[2023-11-28 05:13:00,881][87426] Updated weights for policy 1, policy_version 190830 (0.0012) -[2023-11-28 05:13:01,261][87426] Updated weights for policy 1, policy_version 190840 (0.0011) -[2023-11-28 05:13:01,420][87424] Updated weights for policy 0, policy_version 191267 (0.0010) -[2023-11-28 05:13:01,799][87424] Updated weights for policy 0, policy_version 191277 (0.0008) -[2023-11-28 05:13:02,181][87424] Updated weights for policy 0, policy_version 191287 (0.0009) -[2023-11-28 05:13:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97828864. Throughput: 0: 2748.1, 1: 2741.8. Samples: 97840852. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:13:03,445][86177] Avg episode reward: [(0, '-501.400'), (1, '-518.010')] -[2023-11-28 05:13:03,633][87426] Updated weights for policy 1, policy_version 190850 (0.0011) -[2023-11-28 05:13:04,016][87426] Updated weights for policy 1, policy_version 190860 (0.0007) -[2023-11-28 05:13:04,397][87426] Updated weights for policy 1, policy_version 190870 (0.0008) -[2023-11-28 05:13:04,466][87424] Updated weights for policy 0, policy_version 191297 (0.0010) -[2023-11-28 05:13:04,774][87426] Updated weights for policy 1, policy_version 190880 (0.0010) -[2023-11-28 05:13:04,850][87424] Updated weights for policy 0, policy_version 191307 (0.0010) -[2023-11-28 05:13:05,237][87424] Updated weights for policy 0, policy_version 191317 (0.0011) -[2023-11-28 05:13:05,628][87424] Updated weights for policy 0, policy_version 191327 (0.0011) -[2023-11-28 05:13:07,160][87426] Updated weights for policy 1, policy_version 190890 (0.0007) -[2023-11-28 05:13:07,388][87424] Updated weights for policy 0, policy_version 191337 (0.0008) -[2023-11-28 05:13:07,545][87426] Updated weights for policy 1, policy_version 190900 (0.0008) -[2023-11-28 05:13:07,782][87424] Updated weights for policy 0, policy_version 191347 (0.0012) -[2023-11-28 05:13:07,931][87426] Updated weights for policy 1, policy_version 190910 (0.0007) -[2023-11-28 05:13:08,161][87424] Updated weights for policy 0, policy_version 191357 (0.0012) -[2023-11-28 05:13:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 97861632. Throughput: 0: 2739.5, 1: 2702.7. Samples: 97871884. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:13:08,446][86177] Avg episode reward: [(0, '-504.910'), (1, '-515.080')] -[2023-11-28 05:13:09,874][87426] Updated weights for policy 1, policy_version 190920 (0.0011) -[2023-11-28 05:13:10,254][87426] Updated weights for policy 1, policy_version 190930 (0.0012) -[2023-11-28 05:13:10,491][87424] Updated weights for policy 0, policy_version 191367 (0.0011) -[2023-11-28 05:13:10,622][87426] Updated weights for policy 1, policy_version 190940 (0.0011) -[2023-11-28 05:13:10,876][87424] Updated weights for policy 0, policy_version 191377 (0.0011) -[2023-11-28 05:13:11,272][87424] Updated weights for policy 0, policy_version 191387 (0.0010) -[2023-11-28 05:13:12,577][87426] Updated weights for policy 1, policy_version 190950 (0.0009) -[2023-11-28 05:13:12,960][87426] Updated weights for policy 1, policy_version 190960 (0.0008) -[2023-11-28 05:13:13,334][87426] Updated weights for policy 1, policy_version 190970 (0.0010) -[2023-11-28 05:13:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 97878016. Throughput: 0: 2716.7, 1: 2691.2. Samples: 97895840. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:13:13,445][86177] Avg episode reward: [(0, '-502.040'), (1, '-520.890')] -[2023-11-28 05:13:13,722][87424] Updated weights for policy 0, policy_version 191397 (0.0009) -[2023-11-28 05:13:14,104][87424] Updated weights for policy 0, policy_version 191407 (0.0012) -[2023-11-28 05:13:14,474][87424] Updated weights for policy 0, policy_version 191417 (0.0011) -[2023-11-28 05:13:15,883][87426] Updated weights for policy 1, policy_version 190980 (0.0009) -[2023-11-28 05:13:16,264][87426] Updated weights for policy 1, policy_version 190990 (0.0008) -[2023-11-28 05:13:16,643][87426] Updated weights for policy 1, policy_version 191000 (0.0011) -[2023-11-28 05:13:16,810][87424] Updated weights for policy 0, policy_version 191427 (0.0011) -[2023-11-28 05:13:17,197][87424] Updated weights for policy 0, policy_version 191437 (0.0010) -[2023-11-28 05:13:17,570][87424] Updated weights for policy 0, policy_version 191447 (0.0007) -[2023-11-28 05:13:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 97910784. Throughput: 0: 2706.5, 1: 2684.4. Samples: 97920172. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:13:18,446][86177] Avg episode reward: [(0, '-498.680'), (1, '-513.050')] -[2023-11-28 05:13:19,105][87426] Updated weights for policy 1, policy_version 191010 (0.0010) -[2023-11-28 05:13:19,481][87426] Updated weights for policy 1, policy_version 191020 (0.0012) -[2023-11-28 05:13:19,785][87424] Updated weights for policy 0, policy_version 191457 (0.0008) -[2023-11-28 05:13:19,858][87426] Updated weights for policy 1, policy_version 191030 (0.0010) -[2023-11-28 05:13:20,169][87424] Updated weights for policy 0, policy_version 191467 (0.0012) -[2023-11-28 05:13:20,238][87426] Updated weights for policy 1, policy_version 191040 (0.0011) -[2023-11-28 05:13:20,554][87424] Updated weights for policy 0, policy_version 191477 (0.0012) -[2023-11-28 05:13:20,942][87424] Updated weights for policy 0, policy_version 191487 (0.0012) -[2023-11-28 05:13:22,742][87426] Updated weights for policy 1, policy_version 191050 (0.0011) -[2023-11-28 05:13:23,116][87426] Updated weights for policy 1, policy_version 191060 (0.0011) -[2023-11-28 05:13:23,304][87424] Updated weights for policy 0, policy_version 191497 (0.0012) -[2023-11-28 05:13:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 97927168. Throughput: 0: 2713.6, 1: 2691.3. Samples: 97952432. Policy #0 lag: (min: 22.0, avg: 43.1, max: 73.0) -[2023-11-28 05:13:23,445][86177] Avg episode reward: [(0, '-497.130'), (1, '-513.350')] -[2023-11-28 05:13:23,504][87426] Updated weights for policy 1, policy_version 191070 (0.0008) -[2023-11-28 05:13:23,692][87424] Updated weights for policy 0, policy_version 191507 (0.0012) -[2023-11-28 05:13:24,071][87424] Updated weights for policy 0, policy_version 191517 (0.0011) -[2023-11-28 05:13:25,605][87426] Updated weights for policy 1, policy_version 191080 (0.0008) -[2023-11-28 05:13:25,715][87424] Updated weights for policy 0, policy_version 191527 (0.0011) -[2023-11-28 05:13:25,985][87426] Updated weights for policy 1, policy_version 191090 (0.0007) -[2023-11-28 05:13:26,106][87424] Updated weights for policy 0, policy_version 191537 (0.0011) -[2023-11-28 05:13:26,364][87426] Updated weights for policy 1, policy_version 191100 (0.0008) -[2023-11-28 05:13:26,480][87424] Updated weights for policy 0, policy_version 191547 (0.0008) -[2023-11-28 05:13:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 97959936. Throughput: 0: 2709.5, 1: 2702.5. Samples: 97976772. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:13:28,445][86177] Avg episode reward: [(0, '-497.570'), (1, '-517.760')] -[2023-11-28 05:13:28,502][87426] Updated weights for policy 1, policy_version 191110 (0.0007) -[2023-11-28 05:13:28,831][87424] Updated weights for policy 0, policy_version 191557 (0.0009) -[2023-11-28 05:13:28,882][87426] Updated weights for policy 1, policy_version 191120 (0.0010) -[2023-11-28 05:13:29,210][87424] Updated weights for policy 0, policy_version 191567 (0.0012) -[2023-11-28 05:13:29,265][87426] Updated weights for policy 1, policy_version 191130 (0.0008) -[2023-11-28 05:13:29,586][87424] Updated weights for policy 0, policy_version 191577 (0.0011) -[2023-11-28 05:13:31,443][87426] Updated weights for policy 1, policy_version 191140 (0.0008) -[2023-11-28 05:13:31,829][87426] Updated weights for policy 1, policy_version 191150 (0.0009) -[2023-11-28 05:13:31,882][87424] Updated weights for policy 0, policy_version 191587 (0.0011) -[2023-11-28 05:13:32,219][87426] Updated weights for policy 1, policy_version 191160 (0.0010) -[2023-11-28 05:13:32,262][87424] Updated weights for policy 0, policy_version 191597 (0.0011) -[2023-11-28 05:13:32,634][87424] Updated weights for policy 0, policy_version 191607 (0.0012) -[2023-11-28 05:13:33,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 97992704. Throughput: 0: 2717.6, 1: 2685.6. Samples: 98000332. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:13:33,445][86177] Avg episode reward: [(0, '-500.840'), (1, '-553.270')] -[2023-11-28 05:13:34,491][87426] Updated weights for policy 1, policy_version 191170 (0.0008) -[2023-11-28 05:13:34,492][87424] Updated weights for policy 0, policy_version 191617 (0.0012) -[2023-11-28 05:13:34,863][87424] Updated weights for policy 0, policy_version 191627 (0.0008) -[2023-11-28 05:13:34,874][87426] Updated weights for policy 1, policy_version 191180 (0.0010) -[2023-11-28 05:13:35,243][87424] Updated weights for policy 0, policy_version 191637 (0.0009) -[2023-11-28 05:13:35,252][87426] Updated weights for policy 1, policy_version 191190 (0.0009) -[2023-11-28 05:13:35,628][87426] Updated weights for policy 1, policy_version 191200 (0.0011) -[2023-11-28 05:13:35,630][87424] Updated weights for policy 0, policy_version 191647 (0.0011) -[2023-11-28 05:13:37,631][87426] Updated weights for policy 1, policy_version 191210 (0.0012) -[2023-11-28 05:13:38,010][87426] Updated weights for policy 1, policy_version 191220 (0.0012) -[2023-11-28 05:13:38,134][87424] Updated weights for policy 0, policy_version 191657 (0.0012) -[2023-11-28 05:13:38,388][87426] Updated weights for policy 1, policy_version 191230 (0.0012) -[2023-11-28 05:13:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 98009088. Throughput: 0: 2719.7, 1: 2676.5. Samples: 98032700. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:13:38,445][86177] Avg episode reward: [(0, '-499.030'), (1, '-550.190')] -[2023-11-28 05:13:38,518][87424] Updated weights for policy 0, policy_version 191667 (0.0012) -[2023-11-28 05:13:38,898][87424] Updated weights for policy 0, policy_version 191677 (0.0009) -[2023-11-28 05:13:40,584][87426] Updated weights for policy 1, policy_version 191240 (0.0012) -[2023-11-28 05:13:40,960][87426] Updated weights for policy 1, policy_version 191250 (0.0012) -[2023-11-28 05:13:41,302][87424] Updated weights for policy 0, policy_version 191687 (0.0011) -[2023-11-28 05:13:41,344][87426] Updated weights for policy 1, policy_version 191260 (0.0009) -[2023-11-28 05:13:41,689][87424] Updated weights for policy 0, policy_version 191697 (0.0012) -[2023-11-28 05:13:42,065][87424] Updated weights for policy 0, policy_version 191707 (0.0011) -[2023-11-28 05:13:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 98041856. Throughput: 0: 2697.5, 1: 2658.2. Samples: 98056368. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:13:43,445][86177] Avg episode reward: [(0, '-498.900'), (1, '-548.400')] -[2023-11-28 05:13:43,881][87426] Updated weights for policy 1, policy_version 191270 (0.0010) -[2023-11-28 05:13:44,252][87426] Updated weights for policy 1, policy_version 191280 (0.0012) -[2023-11-28 05:13:44,280][87424] Updated weights for policy 0, policy_version 191717 (0.0009) -[2023-11-28 05:13:44,627][87426] Updated weights for policy 1, policy_version 191290 (0.0012) -[2023-11-28 05:13:44,662][87424] Updated weights for policy 0, policy_version 191727 (0.0008) -[2023-11-28 05:13:45,043][87424] Updated weights for policy 0, policy_version 191737 (0.0008) -[2023-11-28 05:13:46,604][87426] Updated weights for policy 1, policy_version 191300 (0.0011) -[2023-11-28 05:13:46,985][87426] Updated weights for policy 1, policy_version 191310 (0.0007) -[2023-11-28 05:13:47,367][87426] Updated weights for policy 1, policy_version 191320 (0.0008) -[2023-11-28 05:13:47,471][87424] Updated weights for policy 0, policy_version 191747 (0.0009) -[2023-11-28 05:13:47,852][87424] Updated weights for policy 0, policy_version 191757 (0.0009) -[2023-11-28 05:13:48,232][87424] Updated weights for policy 0, policy_version 191767 (0.0007) -[2023-11-28 05:13:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 98066432. Throughput: 0: 2650.7, 1: 2657.7. Samples: 98079728. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:13:48,445][86177] Avg episode reward: [(0, '-501.880'), (1, '-536.430')] -[2023-11-28 05:13:49,343][87426] Updated weights for policy 1, policy_version 191330 (0.0008) -[2023-11-28 05:13:49,716][87426] Updated weights for policy 1, policy_version 191340 (0.0011) -[2023-11-28 05:13:50,089][87426] Updated weights for policy 1, policy_version 191350 (0.0011) -[2023-11-28 05:13:50,471][87426] Updated weights for policy 1, policy_version 191360 (0.0012) -[2023-11-28 05:13:50,661][87424] Updated weights for policy 0, policy_version 191777 (0.0010) -[2023-11-28 05:13:51,052][87424] Updated weights for policy 0, policy_version 191787 (0.0011) -[2023-11-28 05:13:51,438][87424] Updated weights for policy 0, policy_version 191797 (0.0012) -[2023-11-28 05:13:51,816][87424] Updated weights for policy 0, policy_version 191807 (0.0012) -[2023-11-28 05:13:52,883][87426] Updated weights for policy 1, policy_version 191370 (0.0009) -[2023-11-28 05:13:53,264][87426] Updated weights for policy 1, policy_version 191380 (0.0011) -[2023-11-28 05:13:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 98091008. Throughput: 0: 2651.5, 1: 2672.7. Samples: 98111472. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:13:53,445][86177] Avg episode reward: [(0, '-498.510'), (1, '-508.540')] -[2023-11-28 05:13:53,641][87426] Updated weights for policy 1, policy_version 191390 (0.0011) -[2023-11-28 05:13:53,927][87424] Updated weights for policy 0, policy_version 191817 (0.0012) -[2023-11-28 05:13:54,317][87424] Updated weights for policy 0, policy_version 191827 (0.0012) -[2023-11-28 05:13:54,698][87424] Updated weights for policy 0, policy_version 191837 (0.0012) -[2023-11-28 05:13:55,893][87426] Updated weights for policy 1, policy_version 191400 (0.0008) -[2023-11-28 05:13:56,274][87426] Updated weights for policy 1, policy_version 191410 (0.0011) -[2023-11-28 05:13:56,654][87426] Updated weights for policy 1, policy_version 191420 (0.0011) -[2023-11-28 05:13:56,779][87424] Updated weights for policy 0, policy_version 191847 (0.0010) -[2023-11-28 05:13:57,160][87424] Updated weights for policy 0, policy_version 191857 (0.0012) -[2023-11-28 05:13:57,542][87424] Updated weights for policy 0, policy_version 191867 (0.0011) -[2023-11-28 05:13:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 98123776. Throughput: 0: 2644.9, 1: 2735.6. Samples: 98137960. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:13:58,445][86177] Avg episode reward: [(0, '-494.550'), (1, '-513.860')] -[2023-11-28 05:13:58,693][87426] Updated weights for policy 1, policy_version 191430 (0.0012) -[2023-11-28 05:13:59,067][87426] Updated weights for policy 1, policy_version 191440 (0.0011) -[2023-11-28 05:13:59,445][87426] Updated weights for policy 1, policy_version 191450 (0.0010) -[2023-11-28 05:13:59,564][87424] Updated weights for policy 0, policy_version 191877 (0.0011) -[2023-11-28 05:13:59,950][87424] Updated weights for policy 0, policy_version 191887 (0.0010) -[2023-11-28 05:14:00,336][87424] Updated weights for policy 0, policy_version 191897 (0.0008) -[2023-11-28 05:14:01,350][87426] Updated weights for policy 1, policy_version 191460 (0.0010) -[2023-11-28 05:14:01,739][87426] Updated weights for policy 1, policy_version 191470 (0.0009) -[2023-11-28 05:14:02,106][87426] Updated weights for policy 1, policy_version 191480 (0.0009) -[2023-11-28 05:14:02,427][87424] Updated weights for policy 0, policy_version 191907 (0.0009) -[2023-11-28 05:14:02,817][87424] Updated weights for policy 0, policy_version 191917 (0.0008) -[2023-11-28 05:14:03,201][87424] Updated weights for policy 0, policy_version 191927 (0.0008) -[2023-11-28 05:14:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 98148352. Throughput: 0: 2674.1, 1: 2733.5. Samples: 98163512. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:14:03,446][86177] Avg episode reward: [(0, '-493.220'), (1, '-516.510')] -[2023-11-28 05:14:04,409][87426] Updated weights for policy 1, policy_version 191490 (0.0011) -[2023-11-28 05:14:04,789][87426] Updated weights for policy 1, policy_version 191500 (0.0012) -[2023-11-28 05:14:05,171][87426] Updated weights for policy 1, policy_version 191510 (0.0012) -[2023-11-28 05:14:05,552][87426] Updated weights for policy 1, policy_version 191520 (0.0012) -[2023-11-28 05:14:05,555][87424] Updated weights for policy 0, policy_version 191937 (0.0008) -[2023-11-28 05:14:05,941][87424] Updated weights for policy 0, policy_version 191947 (0.0008) -[2023-11-28 05:14:06,313][87424] Updated weights for policy 0, policy_version 191957 (0.0007) -[2023-11-28 05:14:06,703][87424] Updated weights for policy 0, policy_version 191967 (0.0008) -[2023-11-28 05:14:07,884][87426] Updated weights for policy 1, policy_version 191530 (0.0008) -[2023-11-28 05:14:08,274][87426] Updated weights for policy 1, policy_version 191540 (0.0007) -[2023-11-28 05:14:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 98172928. Throughput: 0: 2680.1, 1: 2721.2. Samples: 98195492. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:14:08,445][86177] Avg episode reward: [(0, '-490.730'), (1, '-530.610')] -[2023-11-28 05:14:08,652][87426] Updated weights for policy 1, policy_version 191550 (0.0008) -[2023-11-28 05:14:09,077][87424] Updated weights for policy 0, policy_version 191977 (0.0012) -[2023-11-28 05:14:09,452][87424] Updated weights for policy 0, policy_version 191987 (0.0011) -[2023-11-28 05:14:09,835][87424] Updated weights for policy 0, policy_version 191997 (0.0012) -[2023-11-28 05:14:10,677][87426] Updated weights for policy 1, policy_version 191560 (0.0011) -[2023-11-28 05:14:11,060][87426] Updated weights for policy 1, policy_version 191570 (0.0011) -[2023-11-28 05:14:11,440][87426] Updated weights for policy 1, policy_version 191580 (0.0012) -[2023-11-28 05:14:11,694][87424] Updated weights for policy 0, policy_version 192007 (0.0011) -[2023-11-28 05:14:12,074][87424] Updated weights for policy 0, policy_version 192017 (0.0010) -[2023-11-28 05:14:12,453][87424] Updated weights for policy 0, policy_version 192027 (0.0010) -[2023-11-28 05:14:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 98205696. Throughput: 0: 2666.0, 1: 2716.3. Samples: 98218972. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:14:13,445][86177] Avg episode reward: [(0, '-492.740'), (1, '-563.200')] -[2023-11-28 05:14:13,542][87426] Updated weights for policy 1, policy_version 191590 (0.0010) -[2023-11-28 05:14:13,919][87426] Updated weights for policy 1, policy_version 191600 (0.0011) -[2023-11-28 05:14:14,304][87426] Updated weights for policy 1, policy_version 191610 (0.0010) -[2023-11-28 05:14:14,497][87424] Updated weights for policy 0, policy_version 192037 (0.0009) -[2023-11-28 05:14:14,883][87424] Updated weights for policy 0, policy_version 192047 (0.0011) -[2023-11-28 05:14:15,267][87424] Updated weights for policy 0, policy_version 192057 (0.0007) -[2023-11-28 05:14:16,770][87426] Updated weights for policy 1, policy_version 191620 (0.0010) -[2023-11-28 05:14:17,156][87426] Updated weights for policy 1, policy_version 191630 (0.0007) -[2023-11-28 05:14:17,543][87426] Updated weights for policy 1, policy_version 191640 (0.0007) -[2023-11-28 05:14:17,697][87424] Updated weights for policy 0, policy_version 192067 (0.0009) -[2023-11-28 05:14:18,073][87424] Updated weights for policy 0, policy_version 192077 (0.0008) -[2023-11-28 05:14:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 98230272. Throughput: 0: 2675.1, 1: 2719.2. Samples: 98243076. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:14:18,445][86177] Avg episode reward: [(0, '-494.960'), (1, '-560.440')] -[2023-11-28 05:14:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000191648_49061888.pth... -[2023-11-28 05:14:18,459][87424] Updated weights for policy 0, policy_version 192087 (0.0008) -[2023-11-28 05:14:18,496][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000189088_48406528.pth -[2023-11-28 05:14:18,787][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000192096_49176576.pth... -[2023-11-28 05:14:18,819][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000189568_48529408.pth -[2023-11-28 05:14:20,021][87426] Updated weights for policy 1, policy_version 191650 (0.0008) -[2023-11-28 05:14:20,406][87426] Updated weights for policy 1, policy_version 191660 (0.0012) -[2023-11-28 05:14:20,671][87424] Updated weights for policy 0, policy_version 192097 (0.0010) -[2023-11-28 05:14:20,782][87426] Updated weights for policy 1, policy_version 191670 (0.0011) -[2023-11-28 05:14:21,043][87424] Updated weights for policy 0, policy_version 192107 (0.0008) -[2023-11-28 05:14:21,154][87426] Updated weights for policy 1, policy_version 191680 (0.0012) -[2023-11-28 05:14:21,435][87424] Updated weights for policy 0, policy_version 192117 (0.0012) -[2023-11-28 05:14:21,818][87424] Updated weights for policy 0, policy_version 192127 (0.0012) -[2023-11-28 05:14:23,122][87426] Updated weights for policy 1, policy_version 191690 (0.0012) -[2023-11-28 05:14:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 98254848. Throughput: 0: 2645.7, 1: 2711.6. Samples: 98273780. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:14:23,445][86177] Avg episode reward: [(0, '-493.330'), (1, '-562.850')] -[2023-11-28 05:14:23,491][87426] Updated weights for policy 1, policy_version 191700 (0.0012) -[2023-11-28 05:14:23,880][87426] Updated weights for policy 1, policy_version 191710 (0.0012) -[2023-11-28 05:14:24,374][87424] Updated weights for policy 0, policy_version 192137 (0.0009) -[2023-11-28 05:14:24,756][87424] Updated weights for policy 0, policy_version 192147 (0.0012) -[2023-11-28 05:14:25,142][87424] Updated weights for policy 0, policy_version 192157 (0.0012) -[2023-11-28 05:14:26,501][87426] Updated weights for policy 1, policy_version 191720 (0.0008) -[2023-11-28 05:14:26,891][87426] Updated weights for policy 1, policy_version 191730 (0.0008) -[2023-11-28 05:14:27,196][87424] Updated weights for policy 0, policy_version 192167 (0.0011) -[2023-11-28 05:14:27,260][87426] Updated weights for policy 1, policy_version 191740 (0.0011) -[2023-11-28 05:14:27,578][87424] Updated weights for policy 0, policy_version 192177 (0.0009) -[2023-11-28 05:14:27,961][87424] Updated weights for policy 0, policy_version 192187 (0.0007) -[2023-11-28 05:14:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 98287616. Throughput: 0: 2647.8, 1: 2740.2. Samples: 98298828. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:14:28,445][86177] Avg episode reward: [(0, '-492.730'), (1, '-545.030')] -[2023-11-28 05:14:29,022][87426] Updated weights for policy 1, policy_version 191750 (0.0012) -[2023-11-28 05:14:29,404][87426] Updated weights for policy 1, policy_version 191760 (0.0012) -[2023-11-28 05:14:29,792][87426] Updated weights for policy 1, policy_version 191770 (0.0011) -[2023-11-28 05:14:30,073][87424] Updated weights for policy 0, policy_version 192197 (0.0010) -[2023-11-28 05:14:30,460][87424] Updated weights for policy 0, policy_version 192207 (0.0012) -[2023-11-28 05:14:30,839][87424] Updated weights for policy 0, policy_version 192217 (0.0012) -[2023-11-28 05:14:31,734][87426] Updated weights for policy 1, policy_version 191780 (0.0012) -[2023-11-28 05:14:32,107][87426] Updated weights for policy 1, policy_version 191790 (0.0008) -[2023-11-28 05:14:32,483][87426] Updated weights for policy 1, policy_version 191800 (0.0008) -[2023-11-28 05:14:33,192][87424] Updated weights for policy 0, policy_version 192227 (0.0012) -[2023-11-28 05:14:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 98312192. Throughput: 0: 2691.7, 1: 2763.8. Samples: 98325228. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 05:14:33,445][86177] Avg episode reward: [(0, '-492.060'), (1, '-501.260')] -[2023-11-28 05:14:33,574][87424] Updated weights for policy 0, policy_version 192237 (0.0011) -[2023-11-28 05:14:33,960][87424] Updated weights for policy 0, policy_version 192247 (0.0009) -[2023-11-28 05:14:34,420][87426] Updated weights for policy 1, policy_version 191810 (0.0009) -[2023-11-28 05:14:34,809][87426] Updated weights for policy 1, policy_version 191820 (0.0008) -[2023-11-28 05:14:35,185][87426] Updated weights for policy 1, policy_version 191830 (0.0011) -[2023-11-28 05:14:35,568][87426] Updated weights for policy 1, policy_version 191840 (0.0012) -[2023-11-28 05:14:36,029][87424] Updated weights for policy 0, policy_version 192257 (0.0011) -[2023-11-28 05:14:36,413][87424] Updated weights for policy 0, policy_version 192267 (0.0012) -[2023-11-28 05:14:36,805][87424] Updated weights for policy 0, policy_version 192277 (0.0012) -[2023-11-28 05:14:37,175][87424] Updated weights for policy 0, policy_version 192287 (0.0012) -[2023-11-28 05:14:37,418][87426] Updated weights for policy 1, policy_version 191850 (0.0012) -[2023-11-28 05:14:37,798][87426] Updated weights for policy 1, policy_version 191860 (0.0011) -[2023-11-28 05:14:38,178][87426] Updated weights for policy 1, policy_version 191870 (0.0011) -[2023-11-28 05:14:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 98344960. Throughput: 0: 2697.3, 1: 2795.6. Samples: 98358656. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:14:38,446][86177] Avg episode reward: [(0, '-492.840'), (1, '-501.080')] -[2023-11-28 05:14:39,238][87424] Updated weights for policy 0, policy_version 192297 (0.0009) -[2023-11-28 05:14:39,621][87424] Updated weights for policy 0, policy_version 192307 (0.0007) -[2023-11-28 05:14:40,012][87424] Updated weights for policy 0, policy_version 192317 (0.0009) -[2023-11-28 05:14:40,701][87426] Updated weights for policy 1, policy_version 191880 (0.0008) -[2023-11-28 05:14:41,072][87426] Updated weights for policy 1, policy_version 191890 (0.0008) -[2023-11-28 05:14:41,461][87426] Updated weights for policy 1, policy_version 191900 (0.0007) -[2023-11-28 05:14:42,150][87424] Updated weights for policy 0, policy_version 192327 (0.0011) -[2023-11-28 05:14:42,525][87424] Updated weights for policy 0, policy_version 192337 (0.0012) -[2023-11-28 05:14:42,905][87424] Updated weights for policy 0, policy_version 192347 (0.0012) -[2023-11-28 05:14:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 98369536. Throughput: 0: 2697.9, 1: 2733.2. Samples: 98382364. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:14:43,445][86177] Avg episode reward: [(0, '-492.680'), (1, '-497.660')] -[2023-11-28 05:14:43,832][87426] Updated weights for policy 1, policy_version 191910 (0.0010) -[2023-11-28 05:14:44,213][87426] Updated weights for policy 1, policy_version 191920 (0.0011) -[2023-11-28 05:14:44,596][87426] Updated weights for policy 1, policy_version 191930 (0.0009) -[2023-11-28 05:14:45,474][87424] Updated weights for policy 0, policy_version 192357 (0.0010) -[2023-11-28 05:14:45,859][87424] Updated weights for policy 0, policy_version 192367 (0.0009) -[2023-11-28 05:14:46,246][87424] Updated weights for policy 0, policy_version 192377 (0.0009) -[2023-11-28 05:14:46,272][87426] Updated weights for policy 1, policy_version 191940 (0.0010) -[2023-11-28 05:14:46,654][87426] Updated weights for policy 1, policy_version 191950 (0.0012) -[2023-11-28 05:14:47,025][87426] Updated weights for policy 1, policy_version 191960 (0.0012) -[2023-11-28 05:14:48,280][87424] Updated weights for policy 0, policy_version 192387 (0.0009) -[2023-11-28 05:14:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 98394112. Throughput: 0: 2664.5, 1: 2725.0. Samples: 98406040. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:14:48,446][86177] Avg episode reward: [(0, '-495.500'), (1, '-510.920')] -[2023-11-28 05:14:48,658][87424] Updated weights for policy 0, policy_version 192397 (0.0012) -[2023-11-28 05:14:49,037][87424] Updated weights for policy 0, policy_version 192407 (0.0011) -[2023-11-28 05:14:49,175][87426] Updated weights for policy 1, policy_version 191970 (0.0011) -[2023-11-28 05:14:49,546][87426] Updated weights for policy 1, policy_version 191980 (0.0011) -[2023-11-28 05:14:49,929][87426] Updated weights for policy 1, policy_version 191990 (0.0012) -[2023-11-28 05:14:50,295][87426] Updated weights for policy 1, policy_version 192000 (0.0012) -[2023-11-28 05:14:51,202][87424] Updated weights for policy 0, policy_version 192417 (0.0011) -[2023-11-28 05:14:51,592][87424] Updated weights for policy 0, policy_version 192427 (0.0011) -[2023-11-28 05:14:51,981][87424] Updated weights for policy 0, policy_version 192437 (0.0012) -[2023-11-28 05:14:52,356][87424] Updated weights for policy 0, policy_version 192447 (0.0010) -[2023-11-28 05:14:52,429][87426] Updated weights for policy 1, policy_version 192010 (0.0011) -[2023-11-28 05:14:52,811][87426] Updated weights for policy 1, policy_version 192020 (0.0010) -[2023-11-28 05:14:53,184][87426] Updated weights for policy 1, policy_version 192030 (0.0010) -[2023-11-28 05:14:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 98426880. Throughput: 0: 2666.8, 1: 2742.1. Samples: 98438888. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:14:53,445][86177] Avg episode reward: [(0, '-494.320'), (1, '-515.690')] -[2023-11-28 05:14:54,532][87424] Updated weights for policy 0, policy_version 192457 (0.0008) -[2023-11-28 05:14:54,908][87424] Updated weights for policy 0, policy_version 192467 (0.0008) -[2023-11-28 05:14:55,290][87426] Updated weights for policy 1, policy_version 192040 (0.0008) -[2023-11-28 05:14:55,290][87424] Updated weights for policy 0, policy_version 192477 (0.0008) -[2023-11-28 05:14:55,668][87426] Updated weights for policy 1, policy_version 192050 (0.0007) -[2023-11-28 05:14:56,047][87426] Updated weights for policy 1, policy_version 192060 (0.0007) -[2023-11-28 05:14:56,964][87424] Updated weights for policy 0, policy_version 192487 (0.0007) -[2023-11-28 05:14:57,349][87424] Updated weights for policy 0, policy_version 192497 (0.0007) -[2023-11-28 05:14:57,730][87424] Updated weights for policy 0, policy_version 192507 (0.0011) -[2023-11-28 05:14:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 98451456. Throughput: 0: 2683.4, 1: 2750.6. Samples: 98463500. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:14:58,445][86177] Avg episode reward: [(0, '-496.490'), (1, '-551.550')] -[2023-11-28 05:14:58,484][87426] Updated weights for policy 1, policy_version 192070 (0.0008) -[2023-11-28 05:14:58,868][87426] Updated weights for policy 1, policy_version 192080 (0.0010) -[2023-11-28 05:14:59,255][87426] Updated weights for policy 1, policy_version 192090 (0.0008) -[2023-11-28 05:14:59,961][87424] Updated weights for policy 0, policy_version 192517 (0.0011) -[2023-11-28 05:15:00,344][87424] Updated weights for policy 0, policy_version 192527 (0.0012) -[2023-11-28 05:15:00,722][87424] Updated weights for policy 0, policy_version 192537 (0.0012) -[2023-11-28 05:15:01,565][87426] Updated weights for policy 1, policy_version 192100 (0.0009) -[2023-11-28 05:15:01,948][87426] Updated weights for policy 1, policy_version 192110 (0.0012) -[2023-11-28 05:15:02,321][87426] Updated weights for policy 1, policy_version 192120 (0.0012) -[2023-11-28 05:15:02,872][87424] Updated weights for policy 0, policy_version 192547 (0.0012) -[2023-11-28 05:15:03,263][87424] Updated weights for policy 0, policy_version 192557 (0.0012) -[2023-11-28 05:15:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 98476032. Throughput: 0: 2700.8, 1: 2757.8. Samples: 98488712. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:15:03,445][86177] Avg episode reward: [(0, '-495.690'), (1, '-551.880')] -[2023-11-28 05:15:03,653][87424] Updated weights for policy 0, policy_version 192567 (0.0012) -[2023-11-28 05:15:04,069][87426] Updated weights for policy 1, policy_version 192130 (0.0011) -[2023-11-28 05:15:04,432][87426] Updated weights for policy 1, policy_version 192140 (0.0011) -[2023-11-28 05:15:04,817][87426] Updated weights for policy 1, policy_version 192150 (0.0008) -[2023-11-28 05:15:05,196][87426] Updated weights for policy 1, policy_version 192160 (0.0007) -[2023-11-28 05:15:05,579][87424] Updated weights for policy 0, policy_version 192577 (0.0011) -[2023-11-28 05:15:05,953][87424] Updated weights for policy 0, policy_version 192587 (0.0007) -[2023-11-28 05:15:06,336][87424] Updated weights for policy 0, policy_version 192597 (0.0007) -[2023-11-28 05:15:06,724][87424] Updated weights for policy 0, policy_version 192607 (0.0008) -[2023-11-28 05:15:07,546][87426] Updated weights for policy 1, policy_version 192170 (0.0012) -[2023-11-28 05:15:07,917][87426] Updated weights for policy 1, policy_version 192180 (0.0009) -[2023-11-28 05:15:08,304][87426] Updated weights for policy 1, policy_version 192190 (0.0008) -[2023-11-28 05:15:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 98508800. Throughput: 0: 2757.0, 1: 2764.6. Samples: 98522252. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:15:08,445][86177] Avg episode reward: [(0, '-494.390'), (1, '-546.870')] -[2023-11-28 05:15:08,473][87424] Updated weights for policy 0, policy_version 192617 (0.0008) -[2023-11-28 05:15:08,855][87424] Updated weights for policy 0, policy_version 192627 (0.0008) -[2023-11-28 05:15:09,238][87424] Updated weights for policy 0, policy_version 192637 (0.0008) -[2023-11-28 05:15:10,773][87426] Updated weights for policy 1, policy_version 192200 (0.0007) -[2023-11-28 05:15:11,151][87426] Updated weights for policy 1, policy_version 192210 (0.0008) -[2023-11-28 05:15:11,280][87424] Updated weights for policy 0, policy_version 192647 (0.0011) -[2023-11-28 05:15:11,537][87426] Updated weights for policy 1, policy_version 192220 (0.0007) -[2023-11-28 05:15:11,669][87424] Updated weights for policy 0, policy_version 192657 (0.0011) -[2023-11-28 05:15:12,047][87424] Updated weights for policy 0, policy_version 192667 (0.0008) -[2023-11-28 05:15:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 98533376. Throughput: 0: 2762.2, 1: 2735.4. Samples: 98546220. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:15:13,445][86177] Avg episode reward: [(0, '-497.920'), (1, '-508.450')] -[2023-11-28 05:15:13,841][87426] Updated weights for policy 1, policy_version 192230 (0.0010) -[2023-11-28 05:15:14,217][87426] Updated weights for policy 1, policy_version 192240 (0.0009) -[2023-11-28 05:15:14,547][87424] Updated weights for policy 0, policy_version 192677 (0.0008) -[2023-11-28 05:15:14,594][87426] Updated weights for policy 1, policy_version 192250 (0.0012) -[2023-11-28 05:15:14,939][87424] Updated weights for policy 0, policy_version 192687 (0.0008) -[2023-11-28 05:15:15,331][87424] Updated weights for policy 0, policy_version 192697 (0.0010) -[2023-11-28 05:15:16,809][87426] Updated weights for policy 1, policy_version 192260 (0.0011) -[2023-11-28 05:15:17,186][87426] Updated weights for policy 1, policy_version 192270 (0.0012) -[2023-11-28 05:15:17,574][87426] Updated weights for policy 1, policy_version 192280 (0.0012) -[2023-11-28 05:15:17,739][87424] Updated weights for policy 0, policy_version 192707 (0.0009) -[2023-11-28 05:15:18,124][87424] Updated weights for policy 0, policy_version 192717 (0.0008) -[2023-11-28 05:15:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 98557952. Throughput: 0: 2729.2, 1: 2706.6. Samples: 98569840. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:15:18,446][86177] Avg episode reward: [(0, '-501.980'), (1, '-543.410')] -[2023-11-28 05:15:18,505][87424] Updated weights for policy 0, policy_version 192727 (0.0007) -[2023-11-28 05:15:19,666][87426] Updated weights for policy 1, policy_version 192290 (0.0012) -[2023-11-28 05:15:20,052][87426] Updated weights for policy 1, policy_version 192300 (0.0011) -[2023-11-28 05:15:20,427][87426] Updated weights for policy 1, policy_version 192310 (0.0011) -[2023-11-28 05:15:20,813][87426] Updated weights for policy 1, policy_version 192320 (0.0012) -[2023-11-28 05:15:20,937][87424] Updated weights for policy 0, policy_version 192737 (0.0008) -[2023-11-28 05:15:21,325][87424] Updated weights for policy 0, policy_version 192747 (0.0012) -[2023-11-28 05:15:21,709][87424] Updated weights for policy 0, policy_version 192757 (0.0012) -[2023-11-28 05:15:22,091][87424] Updated weights for policy 0, policy_version 192767 (0.0012) -[2023-11-28 05:15:22,861][87426] Updated weights for policy 1, policy_version 192330 (0.0012) -[2023-11-28 05:15:23,230][87426] Updated weights for policy 1, policy_version 192340 (0.0012) -[2023-11-28 05:15:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 98582528. Throughput: 0: 2707.1, 1: 2680.8. Samples: 98601112. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:15:23,445][86177] Avg episode reward: [(0, '-500.930'), (1, '-545.470')] -[2023-11-28 05:15:23,606][87426] Updated weights for policy 1, policy_version 192350 (0.0009) -[2023-11-28 05:15:24,769][87424] Updated weights for policy 0, policy_version 192777 (0.0010) -[2023-11-28 05:15:25,147][87424] Updated weights for policy 0, policy_version 192787 (0.0009) -[2023-11-28 05:15:25,526][87424] Updated weights for policy 0, policy_version 192797 (0.0010) -[2023-11-28 05:15:25,783][87426] Updated weights for policy 1, policy_version 192360 (0.0008) -[2023-11-28 05:15:26,167][87426] Updated weights for policy 1, policy_version 192370 (0.0010) -[2023-11-28 05:15:26,563][87426] Updated weights for policy 1, policy_version 192380 (0.0011) -[2023-11-28 05:15:28,034][87424] Updated weights for policy 0, policy_version 192807 (0.0008) -[2023-11-28 05:15:28,428][87424] Updated weights for policy 0, policy_version 192817 (0.0007) -[2023-11-28 05:15:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 98607104. Throughput: 0: 2696.8, 1: 2692.6. Samples: 98624888. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:15:28,445][86177] Avg episode reward: [(0, '-502.300'), (1, '-537.980')] -[2023-11-28 05:15:28,801][87424] Updated weights for policy 0, policy_version 192827 (0.0007) -[2023-11-28 05:15:29,076][87426] Updated weights for policy 1, policy_version 192390 (0.0011) -[2023-11-28 05:15:29,460][87426] Updated weights for policy 1, policy_version 192400 (0.0012) -[2023-11-28 05:15:29,836][87426] Updated weights for policy 1, policy_version 192410 (0.0012) -[2023-11-28 05:15:31,159][87424] Updated weights for policy 0, policy_version 192837 (0.0010) -[2023-11-28 05:15:31,539][87424] Updated weights for policy 0, policy_version 192847 (0.0012) -[2023-11-28 05:15:31,807][87426] Updated weights for policy 1, policy_version 192420 (0.0012) -[2023-11-28 05:15:31,927][87424] Updated weights for policy 0, policy_version 192857 (0.0011) -[2023-11-28 05:15:32,179][87426] Updated weights for policy 1, policy_version 192430 (0.0012) -[2023-11-28 05:15:32,559][87426] Updated weights for policy 1, policy_version 192440 (0.0009) -[2023-11-28 05:15:33,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 98639872. Throughput: 0: 2680.8, 1: 2703.5. Samples: 98648336. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:15:33,445][86177] Avg episode reward: [(0, '-502.400'), (1, '-499.930')] -[2023-11-28 05:15:34,554][87424] Updated weights for policy 0, policy_version 192867 (0.0010) -[2023-11-28 05:15:34,908][87426] Updated weights for policy 1, policy_version 192450 (0.0009) -[2023-11-28 05:15:34,934][87424] Updated weights for policy 0, policy_version 192877 (0.0009) -[2023-11-28 05:15:35,287][87426] Updated weights for policy 1, policy_version 192460 (0.0012) -[2023-11-28 05:15:35,318][87424] Updated weights for policy 0, policy_version 192887 (0.0010) -[2023-11-28 05:15:35,661][87426] Updated weights for policy 1, policy_version 192470 (0.0008) -[2023-11-28 05:15:36,045][87426] Updated weights for policy 1, policy_version 192480 (0.0007) -[2023-11-28 05:15:37,723][87424] Updated weights for policy 0, policy_version 192897 (0.0009) -[2023-11-28 05:15:38,098][87424] Updated weights for policy 0, policy_version 192907 (0.0008) -[2023-11-28 05:15:38,403][87426] Updated weights for policy 1, policy_version 192490 (0.0008) -[2023-11-28 05:15:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 98656256. Throughput: 0: 2641.2, 1: 2686.8. Samples: 98678644. Policy #0 lag: (min: 9.0, avg: 35.8, max: 65.0) -[2023-11-28 05:15:38,445][86177] Avg episode reward: [(0, '-495.850'), (1, '-501.860')] -[2023-11-28 05:15:38,493][87424] Updated weights for policy 0, policy_version 192917 (0.0008) -[2023-11-28 05:15:38,787][87426] Updated weights for policy 1, policy_version 192500 (0.0011) -[2023-11-28 05:15:38,872][87424] Updated weights for policy 0, policy_version 192927 (0.0011) -[2023-11-28 05:15:39,167][87426] Updated weights for policy 1, policy_version 192510 (0.0011) -[2023-11-28 05:15:41,155][87424] Updated weights for policy 0, policy_version 192937 (0.0012) -[2023-11-28 05:15:41,375][87426] Updated weights for policy 1, policy_version 192520 (0.0009) -[2023-11-28 05:15:41,540][87424] Updated weights for policy 0, policy_version 192947 (0.0011) -[2023-11-28 05:15:41,752][87426] Updated weights for policy 1, policy_version 192530 (0.0009) -[2023-11-28 05:15:41,919][87424] Updated weights for policy 0, policy_version 192957 (0.0011) -[2023-11-28 05:15:42,141][87426] Updated weights for policy 1, policy_version 192540 (0.0012) -[2023-11-28 05:15:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 98689024. Throughput: 0: 2646.2, 1: 2675.6. Samples: 98702984. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:15:43,445][86177] Avg episode reward: [(0, '-499.590'), (1, '-499.670')] -[2023-11-28 05:15:44,379][87424] Updated weights for policy 0, policy_version 192967 (0.0011) -[2023-11-28 05:15:44,644][87426] Updated weights for policy 1, policy_version 192550 (0.0011) -[2023-11-28 05:15:44,754][87424] Updated weights for policy 0, policy_version 192977 (0.0011) -[2023-11-28 05:15:45,019][87426] Updated weights for policy 1, policy_version 192560 (0.0011) -[2023-11-28 05:15:45,134][87424] Updated weights for policy 0, policy_version 192987 (0.0010) -[2023-11-28 05:15:45,401][87426] Updated weights for policy 1, policy_version 192570 (0.0008) -[2023-11-28 05:15:47,199][87424] Updated weights for policy 0, policy_version 192997 (0.0012) -[2023-11-28 05:15:47,354][87426] Updated weights for policy 1, policy_version 192580 (0.0009) -[2023-11-28 05:15:47,568][87424] Updated weights for policy 0, policy_version 193007 (0.0011) -[2023-11-28 05:15:47,731][87426] Updated weights for policy 1, policy_version 192590 (0.0011) -[2023-11-28 05:15:47,955][87424] Updated weights for policy 0, policy_version 193017 (0.0010) -[2023-11-28 05:15:48,119][87426] Updated weights for policy 1, policy_version 192600 (0.0008) -[2023-11-28 05:15:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 98721792. Throughput: 0: 2626.7, 1: 2667.3. Samples: 98726940. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:15:48,445][86177] Avg episode reward: [(0, '-499.390'), (1, '-500.540')] -[2023-11-28 05:15:49,819][87424] Updated weights for policy 0, policy_version 193027 (0.0012) -[2023-11-28 05:15:49,950][87426] Updated weights for policy 1, policy_version 192610 (0.0008) -[2023-11-28 05:15:50,220][87424] Updated weights for policy 0, policy_version 193037 (0.0011) -[2023-11-28 05:15:50,334][87426] Updated weights for policy 1, policy_version 192620 (0.0011) -[2023-11-28 05:15:50,586][87424] Updated weights for policy 0, policy_version 193047 (0.0011) -[2023-11-28 05:15:50,710][87426] Updated weights for policy 1, policy_version 192630 (0.0010) -[2023-11-28 05:15:51,092][87426] Updated weights for policy 1, policy_version 192640 (0.0012) -[2023-11-28 05:15:52,982][87424] Updated weights for policy 0, policy_version 193057 (0.0011) -[2023-11-28 05:15:53,377][87424] Updated weights for policy 0, policy_version 193067 (0.0011) -[2023-11-28 05:15:53,398][87426] Updated weights for policy 1, policy_version 192650 (0.0012) -[2023-11-28 05:15:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 98738176. Throughput: 0: 2605.8, 1: 2681.6. Samples: 98760184. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:15:53,445][86177] Avg episode reward: [(0, '-499.580'), (1, '-511.260')] -[2023-11-28 05:15:53,757][87424] Updated weights for policy 0, policy_version 193077 (0.0011) -[2023-11-28 05:15:53,773][87426] Updated weights for policy 1, policy_version 192660 (0.0012) -[2023-11-28 05:15:54,133][87424] Updated weights for policy 0, policy_version 193087 (0.0011) -[2023-11-28 05:15:54,156][87426] Updated weights for policy 1, policy_version 192670 (0.0012) -[2023-11-28 05:15:56,172][87424] Updated weights for policy 0, policy_version 193097 (0.0008) -[2023-11-28 05:15:56,559][87424] Updated weights for policy 0, policy_version 193107 (0.0008) -[2023-11-28 05:15:56,584][87426] Updated weights for policy 1, policy_version 192680 (0.0011) -[2023-11-28 05:15:56,935][87424] Updated weights for policy 0, policy_version 193117 (0.0010) -[2023-11-28 05:15:56,976][87426] Updated weights for policy 1, policy_version 192690 (0.0010) -[2023-11-28 05:15:57,354][87426] Updated weights for policy 1, policy_version 192700 (0.0007) -[2023-11-28 05:15:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 98770944. Throughput: 0: 2614.7, 1: 2709.1. Samples: 98785788. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:15:58,445][86177] Avg episode reward: [(0, '-504.430'), (1, '-512.980')] -[2023-11-28 05:15:58,638][87424] Updated weights for policy 0, policy_version 193127 (0.0011) -[2023-11-28 05:15:59,014][87424] Updated weights for policy 0, policy_version 193137 (0.0008) -[2023-11-28 05:15:59,038][87426] Updated weights for policy 1, policy_version 192710 (0.0009) -[2023-11-28 05:15:59,398][87424] Updated weights for policy 0, policy_version 193147 (0.0011) -[2023-11-28 05:15:59,427][87426] Updated weights for policy 1, policy_version 192720 (0.0011) -[2023-11-28 05:15:59,810][87426] Updated weights for policy 1, policy_version 192730 (0.0011) -[2023-11-28 05:16:01,554][87424] Updated weights for policy 0, policy_version 193157 (0.0011) -[2023-11-28 05:16:01,932][87424] Updated weights for policy 0, policy_version 193167 (0.0011) -[2023-11-28 05:16:01,956][87426] Updated weights for policy 1, policy_version 192740 (0.0009) -[2023-11-28 05:16:02,319][87424] Updated weights for policy 0, policy_version 193177 (0.0009) -[2023-11-28 05:16:02,332][87426] Updated weights for policy 1, policy_version 192750 (0.0012) -[2023-11-28 05:16:02,715][87426] Updated weights for policy 1, policy_version 192760 (0.0012) -[2023-11-28 05:16:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 98803712. Throughput: 0: 2646.2, 1: 2714.5. Samples: 98811072. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:03,445][86177] Avg episode reward: [(0, '-502.300'), (1, '-514.450')] -[2023-11-28 05:16:04,858][87426] Updated weights for policy 1, policy_version 192770 (0.0011) -[2023-11-28 05:16:04,923][87424] Updated weights for policy 0, policy_version 193187 (0.0010) -[2023-11-28 05:16:05,241][87426] Updated weights for policy 1, policy_version 192780 (0.0012) -[2023-11-28 05:16:05,308][87424] Updated weights for policy 0, policy_version 193197 (0.0011) -[2023-11-28 05:16:05,616][87426] Updated weights for policy 1, policy_version 192790 (0.0011) -[2023-11-28 05:16:05,682][87424] Updated weights for policy 0, policy_version 193207 (0.0009) -[2023-11-28 05:16:05,994][87426] Updated weights for policy 1, policy_version 192800 (0.0012) -[2023-11-28 05:16:07,791][87424] Updated weights for policy 0, policy_version 193217 (0.0008) -[2023-11-28 05:16:07,899][87426] Updated weights for policy 1, policy_version 192810 (0.0011) -[2023-11-28 05:16:08,180][87424] Updated weights for policy 0, policy_version 193227 (0.0008) -[2023-11-28 05:16:08,279][87426] Updated weights for policy 1, policy_version 192820 (0.0011) -[2023-11-28 05:16:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 98820096. Throughput: 0: 2652.4, 1: 2723.3. Samples: 98843020. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:08,445][86177] Avg episode reward: [(0, '-502.710'), (1, '-511.960')] -[2023-11-28 05:16:08,558][87424] Updated weights for policy 0, policy_version 193237 (0.0008) -[2023-11-28 05:16:08,652][87426] Updated weights for policy 1, policy_version 192830 (0.0008) -[2023-11-28 05:16:08,943][87424] Updated weights for policy 0, policy_version 193247 (0.0009) -[2023-11-28 05:16:10,577][87426] Updated weights for policy 1, policy_version 192840 (0.0010) -[2023-11-28 05:16:10,958][87426] Updated weights for policy 1, policy_version 192850 (0.0011) -[2023-11-28 05:16:11,338][87426] Updated weights for policy 1, policy_version 192860 (0.0010) -[2023-11-28 05:16:11,461][87424] Updated weights for policy 0, policy_version 193257 (0.0010) -[2023-11-28 05:16:11,853][87424] Updated weights for policy 0, policy_version 193267 (0.0011) -[2023-11-28 05:16:12,241][87424] Updated weights for policy 0, policy_version 193277 (0.0012) -[2023-11-28 05:16:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 98852864. Throughput: 0: 2647.9, 1: 2733.3. Samples: 98867044. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:13,446][86177] Avg episode reward: [(0, '-503.740'), (1, '-500.080')] -[2023-11-28 05:16:13,461][87426] Updated weights for policy 1, policy_version 192870 (0.0012) -[2023-11-28 05:16:13,837][87426] Updated weights for policy 1, policy_version 192880 (0.0012) -[2023-11-28 05:16:14,227][87426] Updated weights for policy 1, policy_version 192890 (0.0011) -[2023-11-28 05:16:14,693][87424] Updated weights for policy 0, policy_version 193287 (0.0010) -[2023-11-28 05:16:15,066][87424] Updated weights for policy 0, policy_version 193297 (0.0008) -[2023-11-28 05:16:15,447][87424] Updated weights for policy 0, policy_version 193307 (0.0009) -[2023-11-28 05:16:16,765][87426] Updated weights for policy 1, policy_version 192900 (0.0009) -[2023-11-28 05:16:17,150][87426] Updated weights for policy 1, policy_version 192910 (0.0011) -[2023-11-28 05:16:17,318][87424] Updated weights for policy 0, policy_version 193317 (0.0010) -[2023-11-28 05:16:17,539][87426] Updated weights for policy 1, policy_version 192920 (0.0012) -[2023-11-28 05:16:17,702][87424] Updated weights for policy 0, policy_version 193327 (0.0011) -[2023-11-28 05:16:18,081][87424] Updated weights for policy 0, policy_version 193337 (0.0009) -[2023-11-28 05:16:18,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 98885632. Throughput: 0: 2670.1, 1: 2725.1. Samples: 98891120. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:18,445][86177] Avg episode reward: [(0, '-510.960'), (1, '-499.920')] -[2023-11-28 05:16:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000192928_49389568.pth... -[2023-11-28 05:16:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000193344_49496064.pth... -[2023-11-28 05:16:18,494][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000190816_48848896.pth -[2023-11-28 05:16:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000190400_48742400.pth -[2023-11-28 05:16:19,319][87426] Updated weights for policy 1, policy_version 192930 (0.0012) -[2023-11-28 05:16:19,695][87426] Updated weights for policy 1, policy_version 192940 (0.0011) -[2023-11-28 05:16:20,070][87426] Updated weights for policy 1, policy_version 192950 (0.0011) -[2023-11-28 05:16:20,236][87424] Updated weights for policy 0, policy_version 193347 (0.0008) -[2023-11-28 05:16:20,448][87426] Updated weights for policy 1, policy_version 192960 (0.0012) -[2023-11-28 05:16:20,618][87424] Updated weights for policy 0, policy_version 193357 (0.0011) -[2023-11-28 05:16:21,002][87424] Updated weights for policy 0, policy_version 193367 (0.0010) -[2023-11-28 05:16:22,879][87426] Updated weights for policy 1, policy_version 192970 (0.0012) -[2023-11-28 05:16:23,254][87426] Updated weights for policy 1, policy_version 192980 (0.0016) -[2023-11-28 05:16:23,292][87424] Updated weights for policy 0, policy_version 193377 (0.0010) -[2023-11-28 05:16:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 98902016. Throughput: 0: 2711.7, 1: 2757.5. Samples: 98924760. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:23,445][86177] Avg episode reward: [(0, '-509.280'), (1, '-500.230')] -[2023-11-28 05:16:23,634][87426] Updated weights for policy 1, policy_version 192990 (0.0009) -[2023-11-28 05:16:23,682][87424] Updated weights for policy 0, policy_version 193387 (0.0012) -[2023-11-28 05:16:24,057][87424] Updated weights for policy 0, policy_version 193397 (0.0012) -[2023-11-28 05:16:24,441][87424] Updated weights for policy 0, policy_version 193407 (0.0012) -[2023-11-28 05:16:25,470][87426] Updated weights for policy 1, policy_version 193000 (0.0012) -[2023-11-28 05:16:25,852][87426] Updated weights for policy 1, policy_version 193010 (0.0012) -[2023-11-28 05:16:26,233][87426] Updated weights for policy 1, policy_version 193020 (0.0010) -[2023-11-28 05:16:26,413][87424] Updated weights for policy 0, policy_version 193417 (0.0011) -[2023-11-28 05:16:26,794][87424] Updated weights for policy 0, policy_version 193427 (0.0012) -[2023-11-28 05:16:27,183][87424] Updated weights for policy 0, policy_version 193437 (0.0009) -[2023-11-28 05:16:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 98934784. Throughput: 0: 2706.8, 1: 2781.3. Samples: 98949948. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:28,445][86177] Avg episode reward: [(0, '-508.590'), (1, '-501.420')] -[2023-11-28 05:16:28,635][87426] Updated weights for policy 1, policy_version 193030 (0.0007) -[2023-11-28 05:16:29,021][87426] Updated weights for policy 1, policy_version 193040 (0.0008) -[2023-11-28 05:16:29,406][87426] Updated weights for policy 1, policy_version 193050 (0.0007) -[2023-11-28 05:16:29,570][87424] Updated weights for policy 0, policy_version 193447 (0.0009) -[2023-11-28 05:16:29,950][87424] Updated weights for policy 0, policy_version 193457 (0.0011) -[2023-11-28 05:16:30,325][87424] Updated weights for policy 0, policy_version 193467 (0.0010) -[2023-11-28 05:16:31,697][87426] Updated weights for policy 1, policy_version 193060 (0.0009) -[2023-11-28 05:16:32,075][87424] Updated weights for policy 0, policy_version 193477 (0.0011) -[2023-11-28 05:16:32,079][87426] Updated weights for policy 1, policy_version 193070 (0.0013) -[2023-11-28 05:16:32,458][87426] Updated weights for policy 1, policy_version 193080 (0.0010) -[2023-11-28 05:16:32,462][87424] Updated weights for policy 0, policy_version 193487 (0.0011) -[2023-11-28 05:16:32,834][87424] Updated weights for policy 0, policy_version 193497 (0.0009) -[2023-11-28 05:16:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 98967552. Throughput: 0: 2717.6, 1: 2790.8. Samples: 98974820. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:33,446][86177] Avg episode reward: [(0, '-499.180'), (1, '-543.880')] -[2023-11-28 05:16:34,268][87426] Updated weights for policy 1, policy_version 193090 (0.0009) -[2023-11-28 05:16:34,649][87426] Updated weights for policy 1, policy_version 193100 (0.0012) -[2023-11-28 05:16:34,763][87424] Updated weights for policy 0, policy_version 193507 (0.0010) -[2023-11-28 05:16:35,034][87426] Updated weights for policy 1, policy_version 193110 (0.0011) -[2023-11-28 05:16:35,130][87424] Updated weights for policy 0, policy_version 193517 (0.0009) -[2023-11-28 05:16:35,404][87426] Updated weights for policy 1, policy_version 193120 (0.0010) -[2023-11-28 05:16:35,523][87424] Updated weights for policy 0, policy_version 193527 (0.0012) -[2023-11-28 05:16:37,534][87426] Updated weights for policy 1, policy_version 193130 (0.0009) -[2023-11-28 05:16:37,673][87424] Updated weights for policy 0, policy_version 193537 (0.0011) -[2023-11-28 05:16:37,924][87426] Updated weights for policy 1, policy_version 193140 (0.0011) -[2023-11-28 05:16:38,053][87424] Updated weights for policy 0, policy_version 193547 (0.0009) -[2023-11-28 05:16:38,292][87426] Updated weights for policy 1, policy_version 193150 (0.0012) -[2023-11-28 05:16:38,440][87424] Updated weights for policy 0, policy_version 193557 (0.0008) -[2023-11-28 05:16:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 98992128. Throughput: 0: 2716.4, 1: 2806.0. Samples: 99008688. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:38,445][86177] Avg episode reward: [(0, '-511.530'), (1, '-544.850')] -[2023-11-28 05:16:38,817][87424] Updated weights for policy 0, policy_version 193567 (0.0007) -[2023-11-28 05:16:40,221][87426] Updated weights for policy 1, policy_version 193160 (0.0012) -[2023-11-28 05:16:40,613][87426] Updated weights for policy 1, policy_version 193170 (0.0016) -[2023-11-28 05:16:40,985][87426] Updated weights for policy 1, policy_version 193180 (0.0011) -[2023-11-28 05:16:41,278][87424] Updated weights for policy 0, policy_version 193577 (0.0011) -[2023-11-28 05:16:41,656][87424] Updated weights for policy 0, policy_version 193587 (0.0011) -[2023-11-28 05:16:42,032][87424] Updated weights for policy 0, policy_version 193597 (0.0012) -[2023-11-28 05:16:43,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99016704. Throughput: 0: 2703.8, 1: 2779.2. Samples: 99032524. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:43,445][86177] Avg episode reward: [(0, '-509.050'), (1, '-569.070')] -[2023-11-28 05:16:43,595][87426] Updated weights for policy 1, policy_version 193190 (0.0008) -[2023-11-28 05:16:43,971][87426] Updated weights for policy 1, policy_version 193200 (0.0007) -[2023-11-28 05:16:44,328][87424] Updated weights for policy 0, policy_version 193607 (0.0009) -[2023-11-28 05:16:44,351][87426] Updated weights for policy 1, policy_version 193210 (0.0007) -[2023-11-28 05:16:44,709][87424] Updated weights for policy 0, policy_version 193617 (0.0007) -[2023-11-28 05:16:45,092][87424] Updated weights for policy 0, policy_version 193627 (0.0009) -[2023-11-28 05:16:46,790][87426] Updated weights for policy 1, policy_version 193220 (0.0010) -[2023-11-28 05:16:47,167][87426] Updated weights for policy 1, policy_version 193230 (0.0009) -[2023-11-28 05:16:47,332][87424] Updated weights for policy 0, policy_version 193637 (0.0009) -[2023-11-28 05:16:47,535][87426] Updated weights for policy 1, policy_version 193240 (0.0011) -[2023-11-28 05:16:47,717][87424] Updated weights for policy 0, policy_version 193647 (0.0007) -[2023-11-28 05:16:48,098][87424] Updated weights for policy 0, policy_version 193657 (0.0008) -[2023-11-28 05:16:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 99049472. Throughput: 0: 2670.6, 1: 2766.9. Samples: 99055760. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 05:16:48,445][86177] Avg episode reward: [(0, '-511.890'), (1, '-566.930')] -[2023-11-28 05:16:49,253][87426] Updated weights for policy 1, policy_version 193250 (0.0010) -[2023-11-28 05:16:49,636][87426] Updated weights for policy 1, policy_version 193260 (0.0011) -[2023-11-28 05:16:50,008][87426] Updated weights for policy 1, policy_version 193270 (0.0012) -[2023-11-28 05:16:50,383][87426] Updated weights for policy 1, policy_version 193280 (0.0012) -[2023-11-28 05:16:50,392][87424] Updated weights for policy 0, policy_version 193667 (0.0009) -[2023-11-28 05:16:50,773][87424] Updated weights for policy 0, policy_version 193677 (0.0012) -[2023-11-28 05:16:51,154][87424] Updated weights for policy 0, policy_version 193687 (0.0012) -[2023-11-28 05:16:52,554][87426] Updated weights for policy 1, policy_version 193290 (0.0012) -[2023-11-28 05:16:52,934][87426] Updated weights for policy 1, policy_version 193300 (0.0010) -[2023-11-28 05:16:53,314][87426] Updated weights for policy 1, policy_version 193310 (0.0011) -[2023-11-28 05:16:53,411][87424] Updated weights for policy 0, policy_version 193697 (0.0011) -[2023-11-28 05:16:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 99074048. Throughput: 0: 2693.9, 1: 2762.3. Samples: 99088548. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:16:53,445][86177] Avg episode reward: [(0, '-496.430'), (1, '-525.780')] -[2023-11-28 05:16:53,796][87424] Updated weights for policy 0, policy_version 193707 (0.0009) -[2023-11-28 05:16:54,176][87424] Updated weights for policy 0, policy_version 193717 (0.0008) -[2023-11-28 05:16:54,558][87424] Updated weights for policy 0, policy_version 193727 (0.0007) -[2023-11-28 05:16:55,596][87426] Updated weights for policy 1, policy_version 193320 (0.0011) -[2023-11-28 05:16:55,971][87426] Updated weights for policy 1, policy_version 193330 (0.0012) -[2023-11-28 05:16:56,202][87424] Updated weights for policy 0, policy_version 193737 (0.0011) -[2023-11-28 05:16:56,355][87426] Updated weights for policy 1, policy_version 193340 (0.0009) -[2023-11-28 05:16:56,587][87424] Updated weights for policy 0, policy_version 193747 (0.0011) -[2023-11-28 05:16:56,967][87424] Updated weights for policy 0, policy_version 193757 (0.0008) -[2023-11-28 05:16:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99098624. Throughput: 0: 2717.0, 1: 2740.5. Samples: 99112628. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:16:58,445][86177] Avg episode reward: [(0, '-495.630'), (1, '-530.870')] -[2023-11-28 05:16:58,465][87426] Updated weights for policy 1, policy_version 193350 (0.0010) -[2023-11-28 05:16:58,842][87426] Updated weights for policy 1, policy_version 193360 (0.0012) -[2023-11-28 05:16:59,224][87426] Updated weights for policy 1, policy_version 193370 (0.0012) -[2023-11-28 05:16:59,435][87424] Updated weights for policy 0, policy_version 193767 (0.0008) -[2023-11-28 05:16:59,818][87424] Updated weights for policy 0, policy_version 193777 (0.0008) -[2023-11-28 05:17:00,212][87424] Updated weights for policy 0, policy_version 193787 (0.0009) -[2023-11-28 05:17:01,542][87426] Updated weights for policy 1, policy_version 193380 (0.0007) -[2023-11-28 05:17:01,919][87426] Updated weights for policy 1, policy_version 193390 (0.0011) -[2023-11-28 05:17:02,295][87426] Updated weights for policy 1, policy_version 193400 (0.0009) -[2023-11-28 05:17:02,620][87424] Updated weights for policy 0, policy_version 193797 (0.0008) -[2023-11-28 05:17:03,003][87424] Updated weights for policy 0, policy_version 193807 (0.0009) -[2023-11-28 05:17:03,386][87424] Updated weights for policy 0, policy_version 193817 (0.0008) -[2023-11-28 05:17:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 99123200. Throughput: 0: 2725.2, 1: 2749.4. Samples: 99137480. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:03,445][86177] Avg episode reward: [(0, '-496.100'), (1, '-507.630')] -[2023-11-28 05:17:04,608][87426] Updated weights for policy 1, policy_version 193410 (0.0009) -[2023-11-28 05:17:04,981][87426] Updated weights for policy 1, policy_version 193420 (0.0007) -[2023-11-28 05:17:05,366][87426] Updated weights for policy 1, policy_version 193430 (0.0010) -[2023-11-28 05:17:05,687][87424] Updated weights for policy 0, policy_version 193827 (0.0009) -[2023-11-28 05:17:05,741][87426] Updated weights for policy 1, policy_version 193440 (0.0009) -[2023-11-28 05:17:06,062][87424] Updated weights for policy 0, policy_version 193837 (0.0011) -[2023-11-28 05:17:06,438][87424] Updated weights for policy 0, policy_version 193847 (0.0010) -[2023-11-28 05:17:07,939][87426] Updated weights for policy 1, policy_version 193450 (0.0012) -[2023-11-28 05:17:08,317][87426] Updated weights for policy 1, policy_version 193460 (0.0012) -[2023-11-28 05:17:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 99147776. Throughput: 0: 2709.3, 1: 2727.8. Samples: 99169428. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:08,445][86177] Avg episode reward: [(0, '-496.140'), (1, '-508.010')] -[2023-11-28 05:17:08,696][87426] Updated weights for policy 1, policy_version 193470 (0.0011) -[2023-11-28 05:17:08,766][87424] Updated weights for policy 0, policy_version 193857 (0.0009) -[2023-11-28 05:17:09,147][87424] Updated weights for policy 0, policy_version 193867 (0.0011) -[2023-11-28 05:17:09,547][87424] Updated weights for policy 0, policy_version 193877 (0.0011) -[2023-11-28 05:17:09,933][87424] Updated weights for policy 0, policy_version 193887 (0.0009) -[2023-11-28 05:17:10,915][87426] Updated weights for policy 1, policy_version 193480 (0.0011) -[2023-11-28 05:17:11,294][87426] Updated weights for policy 1, policy_version 193490 (0.0008) -[2023-11-28 05:17:11,693][87426] Updated weights for policy 1, policy_version 193500 (0.0008) -[2023-11-28 05:17:12,444][87424] Updated weights for policy 0, policy_version 193897 (0.0009) -[2023-11-28 05:17:12,832][87424] Updated weights for policy 0, policy_version 193907 (0.0012) -[2023-11-28 05:17:13,216][87424] Updated weights for policy 0, policy_version 193917 (0.0012) -[2023-11-28 05:17:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99180544. Throughput: 0: 2690.1, 1: 2693.7. Samples: 99192220. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:13,445][86177] Avg episode reward: [(0, '-496.140'), (1, '-503.840')] -[2023-11-28 05:17:13,948][87426] Updated weights for policy 1, policy_version 193510 (0.0012) -[2023-11-28 05:17:14,327][87426] Updated weights for policy 1, policy_version 193520 (0.0012) -[2023-11-28 05:17:14,703][87426] Updated weights for policy 1, policy_version 193530 (0.0011) -[2023-11-28 05:17:14,940][87424] Updated weights for policy 0, policy_version 193927 (0.0011) -[2023-11-28 05:17:15,317][87424] Updated weights for policy 0, policy_version 193937 (0.0012) -[2023-11-28 05:17:15,697][87424] Updated weights for policy 0, policy_version 193947 (0.0009) -[2023-11-28 05:17:17,046][87426] Updated weights for policy 1, policy_version 193540 (0.0012) -[2023-11-28 05:17:17,427][87426] Updated weights for policy 1, policy_version 193550 (0.0012) -[2023-11-28 05:17:17,806][87426] Updated weights for policy 1, policy_version 193560 (0.0011) -[2023-11-28 05:17:17,815][87424] Updated weights for policy 0, policy_version 193957 (0.0008) -[2023-11-28 05:17:18,207][87424] Updated weights for policy 0, policy_version 193967 (0.0007) -[2023-11-28 05:17:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 99205120. Throughput: 0: 2687.4, 1: 2691.0. Samples: 99216848. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:18,445][86177] Avg episode reward: [(0, '-504.300'), (1, '-500.790')] -[2023-11-28 05:17:18,580][87424] Updated weights for policy 0, policy_version 193977 (0.0010) -[2023-11-28 05:17:19,763][87426] Updated weights for policy 1, policy_version 193570 (0.0011) -[2023-11-28 05:17:20,142][87426] Updated weights for policy 1, policy_version 193580 (0.0010) -[2023-11-28 05:17:20,513][87426] Updated weights for policy 1, policy_version 193590 (0.0011) -[2023-11-28 05:17:20,893][87426] Updated weights for policy 1, policy_version 193600 (0.0010) -[2023-11-28 05:17:20,987][87424] Updated weights for policy 0, policy_version 193987 (0.0010) -[2023-11-28 05:17:21,365][87424] Updated weights for policy 0, policy_version 193997 (0.0011) -[2023-11-28 05:17:21,746][87424] Updated weights for policy 0, policy_version 194007 (0.0011) -[2023-11-28 05:17:23,058][87426] Updated weights for policy 1, policy_version 193610 (0.0012) -[2023-11-28 05:17:23,429][87426] Updated weights for policy 1, policy_version 193620 (0.0012) -[2023-11-28 05:17:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 99229696. Throughput: 0: 2661.7, 1: 2666.7. Samples: 99248464. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:23,445][86177] Avg episode reward: [(0, '-503.940'), (1, '-501.730')] -[2023-11-28 05:17:23,810][87426] Updated weights for policy 1, policy_version 193630 (0.0011) -[2023-11-28 05:17:24,363][87424] Updated weights for policy 0, policy_version 194017 (0.0010) -[2023-11-28 05:17:24,745][87424] Updated weights for policy 0, policy_version 194027 (0.0008) -[2023-11-28 05:17:25,136][87424] Updated weights for policy 0, policy_version 194037 (0.0008) -[2023-11-28 05:17:25,513][87424] Updated weights for policy 0, policy_version 194047 (0.0007) -[2023-11-28 05:17:25,667][87426] Updated weights for policy 1, policy_version 193640 (0.0009) -[2023-11-28 05:17:26,052][87426] Updated weights for policy 1, policy_version 193650 (0.0008) -[2023-11-28 05:17:26,429][87426] Updated weights for policy 1, policy_version 193660 (0.0007) -[2023-11-28 05:17:27,325][87424] Updated weights for policy 0, policy_version 194057 (0.0007) -[2023-11-28 05:17:27,706][87424] Updated weights for policy 0, policy_version 194067 (0.0009) -[2023-11-28 05:17:28,085][87424] Updated weights for policy 0, policy_version 194077 (0.0008) -[2023-11-28 05:17:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99262464. Throughput: 0: 2675.1, 1: 2690.0. Samples: 99273956. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:28,445][86177] Avg episode reward: [(0, '-500.450'), (1, '-500.080')] -[2023-11-28 05:17:28,555][87426] Updated weights for policy 1, policy_version 193670 (0.0010) -[2023-11-28 05:17:28,932][87426] Updated weights for policy 1, policy_version 193680 (0.0010) -[2023-11-28 05:17:29,316][87426] Updated weights for policy 1, policy_version 193690 (0.0007) -[2023-11-28 05:17:30,145][87424] Updated weights for policy 0, policy_version 194087 (0.0008) -[2023-11-28 05:17:30,526][87424] Updated weights for policy 0, policy_version 194097 (0.0008) -[2023-11-28 05:17:30,903][87424] Updated weights for policy 0, policy_version 194107 (0.0009) -[2023-11-28 05:17:31,874][87426] Updated weights for policy 1, policy_version 193700 (0.0008) -[2023-11-28 05:17:32,257][87426] Updated weights for policy 1, policy_version 193710 (0.0011) -[2023-11-28 05:17:32,636][87426] Updated weights for policy 1, policy_version 193720 (0.0010) -[2023-11-28 05:17:33,433][87424] Updated weights for policy 0, policy_version 194117 (0.0010) -[2023-11-28 05:17:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 99287040. Throughput: 0: 2698.3, 1: 2683.9. Samples: 99297960. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:33,445][86177] Avg episode reward: [(0, '-494.720'), (1, '-500.740')] -[2023-11-28 05:17:33,819][87424] Updated weights for policy 0, policy_version 194127 (0.0010) -[2023-11-28 05:17:34,198][87424] Updated weights for policy 0, policy_version 194137 (0.0010) -[2023-11-28 05:17:35,238][87426] Updated weights for policy 1, policy_version 193730 (0.0010) -[2023-11-28 05:17:35,622][87426] Updated weights for policy 1, policy_version 193740 (0.0010) -[2023-11-28 05:17:36,000][87426] Updated weights for policy 1, policy_version 193750 (0.0011) -[2023-11-28 05:17:36,383][87426] Updated weights for policy 1, policy_version 193760 (0.0008) -[2023-11-28 05:17:36,492][87424] Updated weights for policy 0, policy_version 194147 (0.0008) -[2023-11-28 05:17:36,873][87424] Updated weights for policy 0, policy_version 194157 (0.0008) -[2023-11-28 05:17:37,265][87424] Updated weights for policy 0, policy_version 194167 (0.0008) -[2023-11-28 05:17:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 99311616. Throughput: 0: 2690.4, 1: 2669.6. Samples: 99329748. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:38,445][86177] Avg episode reward: [(0, '-492.810'), (1, '-501.370')] -[2023-11-28 05:17:38,493][87426] Updated weights for policy 1, policy_version 193770 (0.0007) -[2023-11-28 05:17:38,876][87426] Updated weights for policy 1, policy_version 193780 (0.0008) -[2023-11-28 05:17:39,256][87426] Updated weights for policy 1, policy_version 193790 (0.0008) -[2023-11-28 05:17:39,793][87424] Updated weights for policy 0, policy_version 194177 (0.0008) -[2023-11-28 05:17:40,169][87424] Updated weights for policy 0, policy_version 194187 (0.0012) -[2023-11-28 05:17:40,556][87424] Updated weights for policy 0, policy_version 194197 (0.0011) -[2023-11-28 05:17:40,937][87424] Updated weights for policy 0, policy_version 194207 (0.0010) -[2023-11-28 05:17:41,686][87426] Updated weights for policy 1, policy_version 193800 (0.0010) -[2023-11-28 05:17:42,074][87426] Updated weights for policy 1, policy_version 193810 (0.0009) -[2023-11-28 05:17:42,452][87426] Updated weights for policy 1, policy_version 193820 (0.0009) -[2023-11-28 05:17:43,270][87424] Updated weights for policy 0, policy_version 194217 (0.0009) -[2023-11-28 05:17:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 99336192. Throughput: 0: 2668.6, 1: 2662.9. Samples: 99352548. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:43,445][86177] Avg episode reward: [(0, '-492.660'), (1, '-499.730')] -[2023-11-28 05:17:43,648][87424] Updated weights for policy 0, policy_version 194227 (0.0012) -[2023-11-28 05:17:44,028][87424] Updated weights for policy 0, policy_version 194237 (0.0012) -[2023-11-28 05:17:44,743][87426] Updated weights for policy 1, policy_version 193830 (0.0010) -[2023-11-28 05:17:45,117][87426] Updated weights for policy 1, policy_version 193840 (0.0012) -[2023-11-28 05:17:45,496][87426] Updated weights for policy 1, policy_version 193850 (0.0010) -[2023-11-28 05:17:45,965][87424] Updated weights for policy 0, policy_version 194247 (0.0009) -[2023-11-28 05:17:46,349][87424] Updated weights for policy 0, policy_version 194257 (0.0007) -[2023-11-28 05:17:46,729][87424] Updated weights for policy 0, policy_version 194267 (0.0007) -[2023-11-28 05:17:47,782][87426] Updated weights for policy 1, policy_version 193860 (0.0010) -[2023-11-28 05:17:48,149][87426] Updated weights for policy 1, policy_version 193870 (0.0008) -[2023-11-28 05:17:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 99360768. Throughput: 0: 2671.6, 1: 2648.9. Samples: 99376904. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:48,445][86177] Avg episode reward: [(0, '-493.050'), (1, '-500.570')] -[2023-11-28 05:17:48,530][87426] Updated weights for policy 1, policy_version 193880 (0.0007) -[2023-11-28 05:17:48,760][87424] Updated weights for policy 0, policy_version 194277 (0.0009) -[2023-11-28 05:17:49,150][87424] Updated weights for policy 0, policy_version 194287 (0.0009) -[2023-11-28 05:17:49,522][87424] Updated weights for policy 0, policy_version 194297 (0.0010) -[2023-11-28 05:17:51,004][87426] Updated weights for policy 1, policy_version 193890 (0.0008) -[2023-11-28 05:17:51,377][87426] Updated weights for policy 1, policy_version 193900 (0.0009) -[2023-11-28 05:17:51,758][87426] Updated weights for policy 1, policy_version 193910 (0.0008) -[2023-11-28 05:17:51,920][87424] Updated weights for policy 0, policy_version 194307 (0.0011) -[2023-11-28 05:17:52,131][87426] Updated weights for policy 1, policy_version 193920 (0.0011) -[2023-11-28 05:17:52,294][87424] Updated weights for policy 0, policy_version 194317 (0.0012) -[2023-11-28 05:17:52,682][87424] Updated weights for policy 0, policy_version 194327 (0.0012) -[2023-11-28 05:17:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 99393536. Throughput: 0: 2658.6, 1: 2627.2. Samples: 99407288. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:53,445][86177] Avg episode reward: [(0, '-491.150'), (1, '-497.590')] -[2023-11-28 05:17:54,496][87426] Updated weights for policy 1, policy_version 193930 (0.0009) -[2023-11-28 05:17:54,729][87424] Updated weights for policy 0, policy_version 194337 (0.0012) -[2023-11-28 05:17:54,870][87426] Updated weights for policy 1, policy_version 193940 (0.0007) -[2023-11-28 05:17:55,118][87424] Updated weights for policy 0, policy_version 194347 (0.0012) -[2023-11-28 05:17:55,259][87426] Updated weights for policy 1, policy_version 193950 (0.0007) -[2023-11-28 05:17:55,496][87424] Updated weights for policy 0, policy_version 194357 (0.0011) -[2023-11-28 05:17:55,882][87424] Updated weights for policy 0, policy_version 194367 (0.0007) -[2023-11-28 05:17:57,409][87426] Updated weights for policy 1, policy_version 193960 (0.0011) -[2023-11-28 05:17:57,786][87426] Updated weights for policy 1, policy_version 193970 (0.0012) -[2023-11-28 05:17:57,909][87424] Updated weights for policy 0, policy_version 194377 (0.0009) -[2023-11-28 05:17:58,161][87426] Updated weights for policy 1, policy_version 193980 (0.0011) -[2023-11-28 05:17:58,290][87424] Updated weights for policy 0, policy_version 194387 (0.0007) -[2023-11-28 05:17:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 99418112. Throughput: 0: 2674.8, 1: 2642.8. Samples: 99431508. Policy #0 lag: (min: 22.0, avg: 30.5, max: 54.0) -[2023-11-28 05:17:58,445][86177] Avg episode reward: [(0, '-493.280'), (1, '-503.370')] -[2023-11-28 05:17:58,669][87424] Updated weights for policy 0, policy_version 194397 (0.0007) -[2023-11-28 05:18:00,537][87426] Updated weights for policy 1, policy_version 193990 (0.0011) -[2023-11-28 05:18:00,920][87426] Updated weights for policy 1, policy_version 194000 (0.0011) -[2023-11-28 05:18:00,958][87424] Updated weights for policy 0, policy_version 194407 (0.0010) -[2023-11-28 05:18:01,305][87426] Updated weights for policy 1, policy_version 194010 (0.0011) -[2023-11-28 05:18:01,323][87424] Updated weights for policy 0, policy_version 194417 (0.0010) -[2023-11-28 05:18:01,710][87424] Updated weights for policy 0, policy_version 194427 (0.0009) -[2023-11-28 05:18:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 99442688. Throughput: 0: 2688.9, 1: 2641.7. Samples: 99456724. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:03,445][86177] Avg episode reward: [(0, '-498.860'), (1, '-507.070')] -[2023-11-28 05:18:03,629][87426] Updated weights for policy 1, policy_version 194020 (0.0009) -[2023-11-28 05:18:03,691][87424] Updated weights for policy 0, policy_version 194437 (0.0009) -[2023-11-28 05:18:04,006][87426] Updated weights for policy 1, policy_version 194030 (0.0009) -[2023-11-28 05:18:04,074][87424] Updated weights for policy 0, policy_version 194447 (0.0008) -[2023-11-28 05:18:04,393][87426] Updated weights for policy 1, policy_version 194040 (0.0008) -[2023-11-28 05:18:04,455][87424] Updated weights for policy 0, policy_version 194457 (0.0008) -[2023-11-28 05:18:06,355][87424] Updated weights for policy 0, policy_version 194467 (0.0011) -[2023-11-28 05:18:06,435][87426] Updated weights for policy 1, policy_version 194050 (0.0008) -[2023-11-28 05:18:06,746][87424] Updated weights for policy 0, policy_version 194477 (0.0011) -[2023-11-28 05:18:06,809][87426] Updated weights for policy 1, policy_version 194060 (0.0009) -[2023-11-28 05:18:07,139][87424] Updated weights for policy 0, policy_version 194487 (0.0008) -[2023-11-28 05:18:07,193][87426] Updated weights for policy 1, policy_version 194070 (0.0010) -[2023-11-28 05:18:07,567][87426] Updated weights for policy 1, policy_version 194080 (0.0012) -[2023-11-28 05:18:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 99475456. Throughput: 0: 2699.3, 1: 2669.1. Samples: 99490044. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:08,445][86177] Avg episode reward: [(0, '-499.170'), (1, '-507.610')] -[2023-11-28 05:18:09,351][87424] Updated weights for policy 0, policy_version 194497 (0.0010) -[2023-11-28 05:18:09,644][87426] Updated weights for policy 1, policy_version 194090 (0.0012) -[2023-11-28 05:18:09,736][87424] Updated weights for policy 0, policy_version 194507 (0.0008) -[2023-11-28 05:18:10,030][87426] Updated weights for policy 1, policy_version 194100 (0.0011) -[2023-11-28 05:18:10,117][87424] Updated weights for policy 0, policy_version 194517 (0.0010) -[2023-11-28 05:18:10,406][87426] Updated weights for policy 1, policy_version 194110 (0.0010) -[2023-11-28 05:18:10,503][87424] Updated weights for policy 0, policy_version 194527 (0.0011) -[2023-11-28 05:18:12,635][87426] Updated weights for policy 1, policy_version 194120 (0.0009) -[2023-11-28 05:18:12,978][87424] Updated weights for policy 0, policy_version 194537 (0.0011) -[2023-11-28 05:18:13,015][87426] Updated weights for policy 1, policy_version 194130 (0.0009) -[2023-11-28 05:18:13,364][87424] Updated weights for policy 0, policy_version 194547 (0.0010) -[2023-11-28 05:18:13,405][87426] Updated weights for policy 1, policy_version 194140 (0.0010) -[2023-11-28 05:18:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 99491840. Throughput: 0: 2708.5, 1: 2655.9. Samples: 99515356. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:13,445][86177] Avg episode reward: [(0, '-499.690'), (1, '-506.550')] -[2023-11-28 05:18:13,746][87424] Updated weights for policy 0, policy_version 194557 (0.0009) -[2023-11-28 05:18:15,517][87426] Updated weights for policy 1, policy_version 194150 (0.0010) -[2023-11-28 05:18:15,704][87424] Updated weights for policy 0, policy_version 194567 (0.0008) -[2023-11-28 05:18:15,890][87426] Updated weights for policy 1, policy_version 194160 (0.0011) -[2023-11-28 05:18:16,083][87424] Updated weights for policy 0, policy_version 194577 (0.0012) -[2023-11-28 05:18:16,269][87426] Updated weights for policy 1, policy_version 194170 (0.0010) -[2023-11-28 05:18:16,462][87424] Updated weights for policy 0, policy_version 194587 (0.0011) -[2023-11-28 05:18:18,085][87424] Updated weights for policy 0, policy_version 194597 (0.0011) -[2023-11-28 05:18:18,264][87426] Updated weights for policy 1, policy_version 194180 (0.0012) -[2023-11-28 05:18:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 99524608. Throughput: 0: 2703.4, 1: 2680.8. Samples: 99540248. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:18,445][86177] Avg episode reward: [(0, '-499.860'), (1, '-504.520')] -[2023-11-28 05:18:18,470][87424] Updated weights for policy 0, policy_version 194607 (0.0009) -[2023-11-28 05:18:18,641][87426] Updated weights for policy 1, policy_version 194190 (0.0011) -[2023-11-28 05:18:18,836][87424] Updated weights for policy 0, policy_version 194617 (0.0008) -[2023-11-28 05:18:19,018][87426] Updated weights for policy 1, policy_version 194200 (0.0012) -[2023-11-28 05:18:19,103][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000194624_49823744.pth... -[2023-11-28 05:18:19,134][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000192096_49176576.pth -[2023-11-28 05:18:19,322][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000194208_49717248.pth... -[2023-11-28 05:18:19,353][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000191648_49061888.pth -[2023-11-28 05:18:21,205][87424] Updated weights for policy 0, policy_version 194627 (0.0010) -[2023-11-28 05:18:21,478][87426] Updated weights for policy 1, policy_version 194210 (0.0011) -[2023-11-28 05:18:21,592][87424] Updated weights for policy 0, policy_version 194637 (0.0011) -[2023-11-28 05:18:21,858][87426] Updated weights for policy 1, policy_version 194220 (0.0011) -[2023-11-28 05:18:21,973][87424] Updated weights for policy 0, policy_version 194647 (0.0009) -[2023-11-28 05:18:22,234][87426] Updated weights for policy 1, policy_version 194230 (0.0012) -[2023-11-28 05:18:22,607][87426] Updated weights for policy 1, policy_version 194240 (0.0009) -[2023-11-28 05:18:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99557376. Throughput: 0: 2721.5, 1: 2683.7. Samples: 99572984. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:23,445][86177] Avg episode reward: [(0, '-495.880'), (1, '-501.750')] -[2023-11-28 05:18:24,022][87424] Updated weights for policy 0, policy_version 194657 (0.0009) -[2023-11-28 05:18:24,408][87424] Updated weights for policy 0, policy_version 194667 (0.0009) -[2023-11-28 05:18:24,747][87426] Updated weights for policy 1, policy_version 194250 (0.0008) -[2023-11-28 05:18:24,792][87424] Updated weights for policy 0, policy_version 194677 (0.0009) -[2023-11-28 05:18:25,126][87426] Updated weights for policy 1, policy_version 194260 (0.0009) -[2023-11-28 05:18:25,177][87424] Updated weights for policy 0, policy_version 194687 (0.0008) -[2023-11-28 05:18:25,503][87426] Updated weights for policy 1, policy_version 194270 (0.0007) -[2023-11-28 05:18:27,505][87424] Updated weights for policy 0, policy_version 194697 (0.0008) -[2023-11-28 05:18:27,686][87426] Updated weights for policy 1, policy_version 194280 (0.0011) -[2023-11-28 05:18:27,884][87424] Updated weights for policy 0, policy_version 194707 (0.0008) -[2023-11-28 05:18:28,058][87426] Updated weights for policy 1, policy_version 194290 (0.0012) -[2023-11-28 05:18:28,273][87424] Updated weights for policy 0, policy_version 194717 (0.0007) -[2023-11-28 05:18:28,435][87426] Updated weights for policy 1, policy_version 194300 (0.0012) -[2023-11-28 05:18:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 99581952. Throughput: 0: 2738.9, 1: 2699.3. Samples: 99597268. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:28,445][86177] Avg episode reward: [(0, '-498.070'), (1, '-500.660')] -[2023-11-28 05:18:29,841][87424] Updated weights for policy 0, policy_version 194727 (0.0008) -[2023-11-28 05:18:30,225][87424] Updated weights for policy 0, policy_version 194737 (0.0008) -[2023-11-28 05:18:30,491][87426] Updated weights for policy 1, policy_version 194310 (0.0011) -[2023-11-28 05:18:30,612][87424] Updated weights for policy 0, policy_version 194747 (0.0011) -[2023-11-28 05:18:30,871][87426] Updated weights for policy 1, policy_version 194320 (0.0008) -[2023-11-28 05:18:31,252][87426] Updated weights for policy 1, policy_version 194330 (0.0007) -[2023-11-28 05:18:32,859][87424] Updated weights for policy 0, policy_version 194757 (0.0011) -[2023-11-28 05:18:33,239][87424] Updated weights for policy 0, policy_version 194767 (0.0012) -[2023-11-28 05:18:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 99606528. Throughput: 0: 2755.5, 1: 2699.0. Samples: 99622356. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:33,445][86177] Avg episode reward: [(0, '-500.720'), (1, '-498.220')] -[2023-11-28 05:18:33,545][87426] Updated weights for policy 1, policy_version 194340 (0.0007) -[2023-11-28 05:18:33,611][87424] Updated weights for policy 0, policy_version 194777 (0.0010) -[2023-11-28 05:18:33,918][87426] Updated weights for policy 1, policy_version 194350 (0.0008) -[2023-11-28 05:18:34,299][87426] Updated weights for policy 1, policy_version 194360 (0.0007) -[2023-11-28 05:18:35,517][87424] Updated weights for policy 0, policy_version 194787 (0.0011) -[2023-11-28 05:18:35,901][87424] Updated weights for policy 0, policy_version 194797 (0.0009) -[2023-11-28 05:18:36,284][87424] Updated weights for policy 0, policy_version 194807 (0.0007) -[2023-11-28 05:18:36,482][87426] Updated weights for policy 1, policy_version 194370 (0.0008) -[2023-11-28 05:18:36,861][87426] Updated weights for policy 1, policy_version 194380 (0.0012) -[2023-11-28 05:18:37,243][87426] Updated weights for policy 1, policy_version 194390 (0.0012) -[2023-11-28 05:18:37,604][87426] Updated weights for policy 1, policy_version 194400 (0.0012) -[2023-11-28 05:18:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 99639296. Throughput: 0: 2774.8, 1: 2714.0. Samples: 99654284. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:38,445][86177] Avg episode reward: [(0, '-498.940'), (1, '-513.460')] -[2023-11-28 05:18:38,711][87424] Updated weights for policy 0, policy_version 194817 (0.0008) -[2023-11-28 05:18:39,098][87424] Updated weights for policy 0, policy_version 194827 (0.0011) -[2023-11-28 05:18:39,466][87424] Updated weights for policy 0, policy_version 194837 (0.0011) -[2023-11-28 05:18:39,830][87426] Updated weights for policy 1, policy_version 194410 (0.0011) -[2023-11-28 05:18:39,863][87424] Updated weights for policy 0, policy_version 194847 (0.0012) -[2023-11-28 05:18:40,205][87426] Updated weights for policy 1, policy_version 194420 (0.0012) -[2023-11-28 05:18:40,583][87426] Updated weights for policy 1, policy_version 194430 (0.0012) -[2023-11-28 05:18:42,477][87424] Updated weights for policy 0, policy_version 194857 (0.0012) -[2023-11-28 05:18:42,543][87426] Updated weights for policy 1, policy_version 194440 (0.0012) -[2023-11-28 05:18:42,853][87424] Updated weights for policy 0, policy_version 194867 (0.0012) -[2023-11-28 05:18:42,925][87426] Updated weights for policy 1, policy_version 194450 (0.0011) -[2023-11-28 05:18:43,241][87424] Updated weights for policy 0, policy_version 194877 (0.0008) -[2023-11-28 05:18:43,303][87426] Updated weights for policy 1, policy_version 194460 (0.0008) -[2023-11-28 05:18:43,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 99663872. Throughput: 0: 2771.9, 1: 2718.7. Samples: 99678584. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:43,446][86177] Avg episode reward: [(0, '-500.140'), (1, '-511.730')] -[2023-11-28 05:18:45,298][87424] Updated weights for policy 0, policy_version 194887 (0.0010) -[2023-11-28 05:18:45,684][87424] Updated weights for policy 0, policy_version 194897 (0.0012) -[2023-11-28 05:18:45,753][87426] Updated weights for policy 1, policy_version 194470 (0.0010) -[2023-11-28 05:18:46,060][87424] Updated weights for policy 0, policy_version 194907 (0.0012) -[2023-11-28 05:18:46,131][87426] Updated weights for policy 1, policy_version 194480 (0.0008) -[2023-11-28 05:18:46,519][87426] Updated weights for policy 1, policy_version 194490 (0.0007) -[2023-11-28 05:18:48,032][87424] Updated weights for policy 0, policy_version 194917 (0.0012) -[2023-11-28 05:18:48,414][87424] Updated weights for policy 0, policy_version 194927 (0.0010) -[2023-11-28 05:18:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99688448. Throughput: 0: 2759.8, 1: 2714.6. Samples: 99703072. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:48,445][86177] Avg episode reward: [(0, '-495.710'), (1, '-512.150')] -[2023-11-28 05:18:48,794][87424] Updated weights for policy 0, policy_version 194937 (0.0011) -[2023-11-28 05:18:48,877][87426] Updated weights for policy 1, policy_version 194500 (0.0009) -[2023-11-28 05:18:49,263][87426] Updated weights for policy 1, policy_version 194510 (0.0008) -[2023-11-28 05:18:49,634][87426] Updated weights for policy 1, policy_version 194520 (0.0008) -[2023-11-28 05:18:51,235][87424] Updated weights for policy 0, policy_version 194947 (0.0010) -[2023-11-28 05:18:51,626][87424] Updated weights for policy 0, policy_version 194957 (0.0009) -[2023-11-28 05:18:51,996][87424] Updated weights for policy 0, policy_version 194967 (0.0011) -[2023-11-28 05:18:52,177][87426] Updated weights for policy 1, policy_version 194530 (0.0008) -[2023-11-28 05:18:52,549][87426] Updated weights for policy 1, policy_version 194540 (0.0008) -[2023-11-28 05:18:52,928][87426] Updated weights for policy 1, policy_version 194550 (0.0008) -[2023-11-28 05:18:53,312][87426] Updated weights for policy 1, policy_version 194560 (0.0008) -[2023-11-28 05:18:53,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99721216. Throughput: 0: 2751.4, 1: 2700.5. Samples: 99735380. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:53,445][86177] Avg episode reward: [(0, '-494.430'), (1, '-503.760')] -[2023-11-28 05:18:54,229][87424] Updated weights for policy 0, policy_version 194977 (0.0009) -[2023-11-28 05:18:54,612][87424] Updated weights for policy 0, policy_version 194987 (0.0010) -[2023-11-28 05:18:54,999][87424] Updated weights for policy 0, policy_version 194997 (0.0011) -[2023-11-28 05:18:55,377][87424] Updated weights for policy 0, policy_version 195007 (0.0012) -[2023-11-28 05:18:55,543][87426] Updated weights for policy 1, policy_version 194570 (0.0011) -[2023-11-28 05:18:55,924][87426] Updated weights for policy 1, policy_version 194580 (0.0011) -[2023-11-28 05:18:56,305][87426] Updated weights for policy 1, policy_version 194590 (0.0011) -[2023-11-28 05:18:57,250][87424] Updated weights for policy 0, policy_version 195017 (0.0012) -[2023-11-28 05:18:57,627][87424] Updated weights for policy 0, policy_version 195027 (0.0012) -[2023-11-28 05:18:57,950][87426] Updated weights for policy 1, policy_version 194600 (0.0012) -[2023-11-28 05:18:58,008][87424] Updated weights for policy 0, policy_version 195037 (0.0011) -[2023-11-28 05:18:58,323][87426] Updated weights for policy 1, policy_version 194610 (0.0011) -[2023-11-28 05:18:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 99745792. Throughput: 0: 2728.0, 1: 2705.9. Samples: 99759884. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:18:58,445][86177] Avg episode reward: [(0, '-496.420'), (1, '-501.580')] -[2023-11-28 05:18:58,713][87426] Updated weights for policy 1, policy_version 194620 (0.0011) -[2023-11-28 05:19:00,158][87424] Updated weights for policy 0, policy_version 195047 (0.0009) -[2023-11-28 05:19:00,551][87424] Updated weights for policy 0, policy_version 195057 (0.0010) -[2023-11-28 05:19:00,941][87424] Updated weights for policy 0, policy_version 195067 (0.0011) -[2023-11-28 05:19:01,028][87426] Updated weights for policy 1, policy_version 194630 (0.0010) -[2023-11-28 05:19:01,407][87426] Updated weights for policy 1, policy_version 194640 (0.0007) -[2023-11-28 05:19:01,798][87426] Updated weights for policy 1, policy_version 194650 (0.0010) -[2023-11-28 05:19:02,895][87424] Updated weights for policy 0, policy_version 195077 (0.0010) -[2023-11-28 05:19:03,269][87424] Updated weights for policy 0, policy_version 195087 (0.0012) -[2023-11-28 05:19:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99770368. Throughput: 0: 2733.3, 1: 2691.2. Samples: 99784348. Policy #0 lag: (min: 22.0, avg: 37.6, max: 54.0) -[2023-11-28 05:19:03,445][86177] Avg episode reward: [(0, '-496.260'), (1, '-503.790')] -[2023-11-28 05:19:03,655][87424] Updated weights for policy 0, policy_version 195097 (0.0012) -[2023-11-28 05:19:03,775][87426] Updated weights for policy 1, policy_version 194660 (0.0011) -[2023-11-28 05:19:04,164][87426] Updated weights for policy 1, policy_version 194670 (0.0011) -[2023-11-28 05:19:04,532][87426] Updated weights for policy 1, policy_version 194680 (0.0009) -[2023-11-28 05:19:06,156][87424] Updated weights for policy 0, policy_version 195107 (0.0010) -[2023-11-28 05:19:06,551][87424] Updated weights for policy 0, policy_version 195117 (0.0007) -[2023-11-28 05:19:06,924][87424] Updated weights for policy 0, policy_version 195127 (0.0008) -[2023-11-28 05:19:06,962][87426] Updated weights for policy 1, policy_version 194690 (0.0009) -[2023-11-28 05:19:07,337][87426] Updated weights for policy 1, policy_version 194700 (0.0008) -[2023-11-28 05:19:07,712][87426] Updated weights for policy 1, policy_version 194710 (0.0008) -[2023-11-28 05:19:08,097][87426] Updated weights for policy 1, policy_version 194720 (0.0008) -[2023-11-28 05:19:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99803136. Throughput: 0: 2738.2, 1: 2702.8. Samples: 99817828. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:08,445][86177] Avg episode reward: [(0, '-496.070'), (1, '-507.220')] -[2023-11-28 05:19:08,791][87424] Updated weights for policy 0, policy_version 195137 (0.0007) -[2023-11-28 05:19:09,171][87424] Updated weights for policy 0, policy_version 195147 (0.0010) -[2023-11-28 05:19:09,550][87424] Updated weights for policy 0, policy_version 195157 (0.0011) -[2023-11-28 05:19:09,930][87424] Updated weights for policy 0, policy_version 195167 (0.0010) -[2023-11-28 05:19:10,193][87426] Updated weights for policy 1, policy_version 194730 (0.0011) -[2023-11-28 05:19:10,576][87426] Updated weights for policy 1, policy_version 194740 (0.0013) -[2023-11-28 05:19:10,959][87426] Updated weights for policy 1, policy_version 194750 (0.0012) -[2023-11-28 05:19:11,822][87424] Updated weights for policy 0, policy_version 195177 (0.0012) -[2023-11-28 05:19:12,212][87424] Updated weights for policy 0, policy_version 195187 (0.0010) -[2023-11-28 05:19:12,584][87424] Updated weights for policy 0, policy_version 195197 (0.0011) -[2023-11-28 05:19:13,021][87426] Updated weights for policy 1, policy_version 194760 (0.0011) -[2023-11-28 05:19:13,402][87426] Updated weights for policy 1, policy_version 194770 (0.0008) -[2023-11-28 05:19:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 99827712. Throughput: 0: 2738.2, 1: 2710.8. Samples: 99842476. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:13,445][86177] Avg episode reward: [(0, '-494.350'), (1, '-502.990')] -[2023-11-28 05:19:13,790][87426] Updated weights for policy 1, policy_version 194780 (0.0007) -[2023-11-28 05:19:14,947][87424] Updated weights for policy 0, policy_version 195207 (0.0010) -[2023-11-28 05:19:15,325][87424] Updated weights for policy 0, policy_version 195217 (0.0009) -[2023-11-28 05:19:15,699][87424] Updated weights for policy 0, policy_version 195227 (0.0010) -[2023-11-28 05:19:16,124][87426] Updated weights for policy 1, policy_version 194790 (0.0010) -[2023-11-28 05:19:16,503][87426] Updated weights for policy 1, policy_version 194800 (0.0011) -[2023-11-28 05:19:16,890][87426] Updated weights for policy 1, policy_version 194810 (0.0012) -[2023-11-28 05:19:17,610][87424] Updated weights for policy 0, policy_version 195237 (0.0010) -[2023-11-28 05:19:17,990][87424] Updated weights for policy 0, policy_version 195247 (0.0012) -[2023-11-28 05:19:18,381][87424] Updated weights for policy 0, policy_version 195257 (0.0012) -[2023-11-28 05:19:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 99852288. Throughput: 0: 2731.6, 1: 2711.6. Samples: 99867300. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:18,445][86177] Avg episode reward: [(0, '-494.550'), (1, '-504.260')] -[2023-11-28 05:19:18,775][87426] Updated weights for policy 1, policy_version 194820 (0.0012) -[2023-11-28 05:19:19,148][87426] Updated weights for policy 1, policy_version 194830 (0.0012) -[2023-11-28 05:19:19,523][87426] Updated weights for policy 1, policy_version 194840 (0.0012) -[2023-11-28 05:19:20,815][87424] Updated weights for policy 0, policy_version 195267 (0.0011) -[2023-11-28 05:19:21,196][87424] Updated weights for policy 0, policy_version 195277 (0.0011) -[2023-11-28 05:19:21,589][87424] Updated weights for policy 0, policy_version 195287 (0.0012) -[2023-11-28 05:19:21,690][87426] Updated weights for policy 1, policy_version 194850 (0.0011) -[2023-11-28 05:19:22,069][87426] Updated weights for policy 1, policy_version 194860 (0.0012) -[2023-11-28 05:19:22,445][87426] Updated weights for policy 1, policy_version 194870 (0.0011) -[2023-11-28 05:19:22,832][87426] Updated weights for policy 1, policy_version 194880 (0.0011) -[2023-11-28 05:19:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99885056. Throughput: 0: 2732.4, 1: 2721.3. Samples: 99899704. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:23,445][86177] Avg episode reward: [(0, '-498.120'), (1, '-503.400')] -[2023-11-28 05:19:24,011][87424] Updated weights for policy 0, policy_version 195297 (0.0011) -[2023-11-28 05:19:24,404][87424] Updated weights for policy 0, policy_version 195307 (0.0012) -[2023-11-28 05:19:24,781][87424] Updated weights for policy 0, policy_version 195317 (0.0012) -[2023-11-28 05:19:25,076][87426] Updated weights for policy 1, policy_version 194890 (0.0008) -[2023-11-28 05:19:25,154][87424] Updated weights for policy 0, policy_version 195327 (0.0011) -[2023-11-28 05:19:25,450][87426] Updated weights for policy 1, policy_version 194900 (0.0012) -[2023-11-28 05:19:25,830][87426] Updated weights for policy 1, policy_version 194910 (0.0012) -[2023-11-28 05:19:26,930][87424] Updated weights for policy 0, policy_version 195337 (0.0011) -[2023-11-28 05:19:27,313][87424] Updated weights for policy 0, policy_version 195347 (0.0012) -[2023-11-28 05:19:27,694][87424] Updated weights for policy 0, policy_version 195357 (0.0011) -[2023-11-28 05:19:28,007][87426] Updated weights for policy 1, policy_version 194920 (0.0009) -[2023-11-28 05:19:28,381][87426] Updated weights for policy 1, policy_version 194930 (0.0010) -[2023-11-28 05:19:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99909632. Throughput: 0: 2741.8, 1: 2725.5. Samples: 99924612. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:28,445][86177] Avg episode reward: [(0, '-498.490'), (1, '-504.350')] -[2023-11-28 05:19:28,769][87426] Updated weights for policy 1, policy_version 194940 (0.0007) -[2023-11-28 05:19:30,007][87424] Updated weights for policy 0, policy_version 195367 (0.0009) -[2023-11-28 05:19:30,385][87424] Updated weights for policy 0, policy_version 195377 (0.0010) -[2023-11-28 05:19:30,761][87424] Updated weights for policy 0, policy_version 195387 (0.0010) -[2023-11-28 05:19:30,815][87426] Updated weights for policy 1, policy_version 194950 (0.0009) -[2023-11-28 05:19:31,188][87426] Updated weights for policy 1, policy_version 194960 (0.0011) -[2023-11-28 05:19:31,568][87426] Updated weights for policy 1, policy_version 194970 (0.0009) -[2023-11-28 05:19:32,668][87424] Updated weights for policy 0, policy_version 195397 (0.0011) -[2023-11-28 05:19:33,047][87424] Updated weights for policy 0, policy_version 195407 (0.0012) -[2023-11-28 05:19:33,436][87424] Updated weights for policy 0, policy_version 195417 (0.0012) -[2023-11-28 05:19:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 99934208. Throughput: 0: 2746.0, 1: 2722.9. Samples: 99949176. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:33,445][86177] Avg episode reward: [(0, '-497.590'), (1, '-502.590')] -[2023-11-28 05:19:34,131][87426] Updated weights for policy 1, policy_version 194980 (0.0008) -[2023-11-28 05:19:34,506][87426] Updated weights for policy 1, policy_version 194990 (0.0007) -[2023-11-28 05:19:34,892][87426] Updated weights for policy 1, policy_version 195000 (0.0012) -[2023-11-28 05:19:35,944][87424] Updated weights for policy 0, policy_version 195427 (0.0012) -[2023-11-28 05:19:36,318][87424] Updated weights for policy 0, policy_version 195437 (0.0012) -[2023-11-28 05:19:36,697][87424] Updated weights for policy 0, policy_version 195447 (0.0012) -[2023-11-28 05:19:37,045][87426] Updated weights for policy 1, policy_version 195010 (0.0012) -[2023-11-28 05:19:37,413][87426] Updated weights for policy 1, policy_version 195020 (0.0012) -[2023-11-28 05:19:37,790][87426] Updated weights for policy 1, policy_version 195030 (0.0012) -[2023-11-28 05:19:38,177][87426] Updated weights for policy 1, policy_version 195040 (0.0012) -[2023-11-28 05:19:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 99966976. Throughput: 0: 2730.6, 1: 2723.6. Samples: 99980816. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:38,445][86177] Avg episode reward: [(0, '-498.110'), (1, '-505.020')] -[2023-11-28 05:19:39,248][87424] Updated weights for policy 0, policy_version 195457 (0.0012) -[2023-11-28 05:19:39,643][87424] Updated weights for policy 0, policy_version 195467 (0.0012) -[2023-11-28 05:19:40,030][87424] Updated weights for policy 0, policy_version 195477 (0.0010) -[2023-11-28 05:19:40,086][87426] Updated weights for policy 1, policy_version 195050 (0.0011) -[2023-11-28 05:19:40,405][87424] Updated weights for policy 0, policy_version 195487 (0.0008) -[2023-11-28 05:19:40,465][87426] Updated weights for policy 1, policy_version 195060 (0.0011) -[2023-11-28 05:19:40,843][87426] Updated weights for policy 1, policy_version 195070 (0.0011) -[2023-11-28 05:19:42,863][87424] Updated weights for policy 0, policy_version 195497 (0.0012) -[2023-11-28 05:19:43,235][87426] Updated weights for policy 1, policy_version 195080 (0.0011) -[2023-11-28 05:19:43,249][87424] Updated weights for policy 0, policy_version 195507 (0.0012) -[2023-11-28 05:19:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 99983360. Throughput: 0: 2729.3, 1: 2715.8. Samples: 100004916. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:43,445][86177] Avg episode reward: [(0, '-494.220'), (1, '-499.910')] -[2023-11-28 05:19:43,609][87426] Updated weights for policy 1, policy_version 195090 (0.0011) -[2023-11-28 05:19:43,634][87424] Updated weights for policy 0, policy_version 195517 (0.0011) -[2023-11-28 05:19:43,985][87426] Updated weights for policy 1, policy_version 195100 (0.0011) -[2023-11-28 05:19:46,099][87424] Updated weights for policy 0, policy_version 195527 (0.0011) -[2023-11-28 05:19:46,137][87426] Updated weights for policy 1, policy_version 195110 (0.0012) -[2023-11-28 05:19:46,478][87424] Updated weights for policy 0, policy_version 195537 (0.0012) -[2023-11-28 05:19:46,520][87426] Updated weights for policy 1, policy_version 195120 (0.0012) -[2023-11-28 05:19:46,860][87424] Updated weights for policy 0, policy_version 195547 (0.0012) -[2023-11-28 05:19:46,909][87426] Updated weights for policy 1, policy_version 195130 (0.0009) -[2023-11-28 05:19:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 100016128. Throughput: 0: 2713.5, 1: 2726.0. Samples: 100029124. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:48,445][86177] Avg episode reward: [(0, '-496.520'), (1, '-501.210')] -[2023-11-28 05:19:48,912][87426] Updated weights for policy 1, policy_version 195140 (0.0009) -[2023-11-28 05:19:49,004][87424] Updated weights for policy 0, policy_version 195557 (0.0011) -[2023-11-28 05:19:49,289][87426] Updated weights for policy 1, policy_version 195150 (0.0012) -[2023-11-28 05:19:49,376][87424] Updated weights for policy 0, policy_version 195567 (0.0008) -[2023-11-28 05:19:49,668][87426] Updated weights for policy 1, policy_version 195160 (0.0010) -[2023-11-28 05:19:49,766][87424] Updated weights for policy 0, policy_version 195577 (0.0012) -[2023-11-28 05:19:52,076][87424] Updated weights for policy 0, policy_version 195587 (0.0009) -[2023-11-28 05:19:52,236][87426] Updated weights for policy 1, policy_version 195170 (0.0011) -[2023-11-28 05:19:52,449][87424] Updated weights for policy 0, policy_version 195597 (0.0010) -[2023-11-28 05:19:52,615][87426] Updated weights for policy 1, policy_version 195180 (0.0012) -[2023-11-28 05:19:52,830][87424] Updated weights for policy 0, policy_version 195607 (0.0009) -[2023-11-28 05:19:52,991][87426] Updated weights for policy 1, policy_version 195190 (0.0011) -[2023-11-28 05:19:53,380][87426] Updated weights for policy 1, policy_version 195200 (0.0012) -[2023-11-28 05:19:53,445][86177] Fps is (10 sec: 6553.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 100048896. Throughput: 0: 2669.2, 1: 2724.8. Samples: 100060560. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:53,446][86177] Avg episode reward: [(0, '-498.330'), (1, '-501.890')] -[2023-11-28 05:19:55,327][87426] Updated weights for policy 1, policy_version 195210 (0.0011) -[2023-11-28 05:19:55,351][87424] Updated weights for policy 0, policy_version 195617 (0.0011) -[2023-11-28 05:19:55,703][87426] Updated weights for policy 1, policy_version 195220 (0.0010) -[2023-11-28 05:19:55,729][87424] Updated weights for policy 0, policy_version 195627 (0.0011) -[2023-11-28 05:19:56,085][87426] Updated weights for policy 1, policy_version 195230 (0.0012) -[2023-11-28 05:19:56,113][87424] Updated weights for policy 0, policy_version 195637 (0.0010) -[2023-11-28 05:19:56,491][87424] Updated weights for policy 0, policy_version 195647 (0.0012) -[2023-11-28 05:19:57,691][87426] Updated weights for policy 1, policy_version 195240 (0.0012) -[2023-11-28 05:19:58,068][87426] Updated weights for policy 1, policy_version 195250 (0.0010) -[2023-11-28 05:19:58,445][86177] Fps is (10 sec: 4914.9, 60 sec: 5324.7, 300 sec: 5387.3). Total num frames: 100065280. Throughput: 0: 2663.7, 1: 2730.2. Samples: 100085204. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:19:58,446][87426] Updated weights for policy 1, policy_version 195260 (0.0007) -[2023-11-28 05:19:58,446][86177] Avg episode reward: [(0, '-497.930'), (1, '-501.410')] -[2023-11-28 05:19:58,574][87424] Updated weights for policy 0, policy_version 195657 (0.0008) -[2023-11-28 05:19:58,958][87424] Updated weights for policy 0, policy_version 195667 (0.0008) -[2023-11-28 05:19:59,336][87424] Updated weights for policy 0, policy_version 195677 (0.0008) -[2023-11-28 05:20:00,904][87426] Updated weights for policy 1, policy_version 195270 (0.0009) -[2023-11-28 05:20:01,274][87426] Updated weights for policy 1, policy_version 195280 (0.0007) -[2023-11-28 05:20:01,645][87426] Updated weights for policy 1, policy_version 195290 (0.0008) -[2023-11-28 05:20:01,651][87424] Updated weights for policy 0, policy_version 195687 (0.0010) -[2023-11-28 05:20:02,032][87424] Updated weights for policy 0, policy_version 195697 (0.0012) -[2023-11-28 05:20:02,420][87424] Updated weights for policy 0, policy_version 195707 (0.0009) -[2023-11-28 05:20:03,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 100098048. Throughput: 0: 2653.1, 1: 2725.2. Samples: 100109324. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:20:03,445][86177] Avg episode reward: [(0, '-495.620'), (1, '-502.400')] -[2023-11-28 05:20:04,087][87426] Updated weights for policy 1, policy_version 195300 (0.0008) -[2023-11-28 05:20:04,464][87426] Updated weights for policy 1, policy_version 195310 (0.0008) -[2023-11-28 05:20:04,840][87426] Updated weights for policy 1, policy_version 195320 (0.0008) -[2023-11-28 05:20:04,968][87424] Updated weights for policy 0, policy_version 195717 (0.0010) -[2023-11-28 05:20:05,350][87424] Updated weights for policy 0, policy_version 195727 (0.0012) -[2023-11-28 05:20:05,731][87424] Updated weights for policy 0, policy_version 195737 (0.0011) -[2023-11-28 05:20:06,750][87426] Updated weights for policy 1, policy_version 195330 (0.0011) -[2023-11-28 05:20:07,134][87426] Updated weights for policy 1, policy_version 195340 (0.0012) -[2023-11-28 05:20:07,512][87426] Updated weights for policy 1, policy_version 195350 (0.0011) -[2023-11-28 05:20:07,897][87426] Updated weights for policy 1, policy_version 195360 (0.0012) -[2023-11-28 05:20:08,075][87424] Updated weights for policy 0, policy_version 195747 (0.0009) -[2023-11-28 05:20:08,444][86177] Fps is (10 sec: 5734.8, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 100122624. Throughput: 0: 2652.1, 1: 2723.9. Samples: 100141624. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:20:08,445][86177] Avg episode reward: [(0, '-498.050'), (1, '-507.770')] -[2023-11-28 05:20:08,457][87424] Updated weights for policy 0, policy_version 195757 (0.0011) -[2023-11-28 05:20:08,846][87424] Updated weights for policy 0, policy_version 195767 (0.0012) -[2023-11-28 05:20:09,928][87426] Updated weights for policy 1, policy_version 195370 (0.0009) -[2023-11-28 05:20:10,310][87426] Updated weights for policy 1, policy_version 195380 (0.0011) -[2023-11-28 05:20:10,694][87426] Updated weights for policy 1, policy_version 195390 (0.0012) -[2023-11-28 05:20:11,157][87424] Updated weights for policy 0, policy_version 195777 (0.0011) -[2023-11-28 05:20:11,537][87424] Updated weights for policy 0, policy_version 195787 (0.0009) -[2023-11-28 05:20:11,928][87424] Updated weights for policy 0, policy_version 195797 (0.0010) -[2023-11-28 05:20:12,306][87424] Updated weights for policy 0, policy_version 195807 (0.0011) -[2023-11-28 05:20:13,079][87426] Updated weights for policy 1, policy_version 195400 (0.0012) -[2023-11-28 05:20:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 100147200. Throughput: 0: 2645.0, 1: 2731.4. Samples: 100166548. Policy #0 lag: (min: 7.0, avg: 13.9, max: 39.0) -[2023-11-28 05:20:13,445][86177] Avg episode reward: [(0, '-495.140'), (1, '-509.070')] -[2023-11-28 05:20:13,463][87426] Updated weights for policy 1, policy_version 195410 (0.0008) -[2023-11-28 05:20:13,843][87426] Updated weights for policy 1, policy_version 195420 (0.0008) -[2023-11-28 05:20:14,228][87424] Updated weights for policy 0, policy_version 195817 (0.0008) -[2023-11-28 05:20:14,613][87424] Updated weights for policy 0, policy_version 195827 (0.0007) -[2023-11-28 05:20:14,995][87424] Updated weights for policy 0, policy_version 195837 (0.0007) -[2023-11-28 05:20:16,210][87426] Updated weights for policy 1, policy_version 195430 (0.0011) -[2023-11-28 05:20:16,580][87426] Updated weights for policy 1, policy_version 195440 (0.0012) -[2023-11-28 05:20:16,959][87426] Updated weights for policy 1, policy_version 195450 (0.0011) -[2023-11-28 05:20:17,008][87424] Updated weights for policy 0, policy_version 195847 (0.0008) -[2023-11-28 05:20:17,390][87424] Updated weights for policy 0, policy_version 195857 (0.0008) -[2023-11-28 05:20:17,772][87424] Updated weights for policy 0, policy_version 195867 (0.0007) -[2023-11-28 05:20:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 100179968. Throughput: 0: 2632.0, 1: 2733.5. Samples: 100190624. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:20:18,445][86177] Avg episode reward: [(0, '-498.760'), (1, '-509.000')] -[2023-11-28 05:20:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000195456_50036736.pth... -[2023-11-28 05:20:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000195872_50143232.pth... -[2023-11-28 05:20:18,494][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000192928_49389568.pth -[2023-11-28 05:20:18,494][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000193344_49496064.pth -[2023-11-28 05:20:19,160][87426] Updated weights for policy 1, policy_version 195460 (0.0008) -[2023-11-28 05:20:19,551][87426] Updated weights for policy 1, policy_version 195470 (0.0008) -[2023-11-28 05:20:19,932][87426] Updated weights for policy 1, policy_version 195480 (0.0009) -[2023-11-28 05:20:20,006][87424] Updated weights for policy 0, policy_version 195877 (0.0009) -[2023-11-28 05:20:20,377][87424] Updated weights for policy 0, policy_version 195887 (0.0011) -[2023-11-28 05:20:20,760][87424] Updated weights for policy 0, policy_version 195897 (0.0012) -[2023-11-28 05:20:22,225][87426] Updated weights for policy 1, policy_version 195490 (0.0010) -[2023-11-28 05:20:22,604][87426] Updated weights for policy 1, policy_version 195500 (0.0008) -[2023-11-28 05:20:22,983][87426] Updated weights for policy 1, policy_version 195510 (0.0008) -[2023-11-28 05:20:23,143][87424] Updated weights for policy 0, policy_version 195907 (0.0012) -[2023-11-28 05:20:23,361][87426] Updated weights for policy 1, policy_version 195520 (0.0008) -[2023-11-28 05:20:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 100204544. Throughput: 0: 2628.6, 1: 2713.0. Samples: 100221188. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:20:23,445][86177] Avg episode reward: [(0, '-504.440'), (1, '-505.380')] -[2023-11-28 05:20:23,531][87424] Updated weights for policy 0, policy_version 195917 (0.0012) -[2023-11-28 05:20:23,908][87424] Updated weights for policy 0, policy_version 195927 (0.0010) -[2023-11-28 05:20:25,578][87426] Updated weights for policy 1, policy_version 195530 (0.0012) -[2023-11-28 05:20:25,961][87426] Updated weights for policy 1, policy_version 195540 (0.0011) -[2023-11-28 05:20:26,333][87424] Updated weights for policy 0, policy_version 195937 (0.0011) -[2023-11-28 05:20:26,346][87426] Updated weights for policy 1, policy_version 195550 (0.0010) -[2023-11-28 05:20:26,712][87424] Updated weights for policy 0, policy_version 195947 (0.0012) -[2023-11-28 05:20:27,094][87424] Updated weights for policy 0, policy_version 195957 (0.0011) -[2023-11-28 05:20:27,477][87424] Updated weights for policy 0, policy_version 195967 (0.0012) -[2023-11-28 05:20:27,982][87426] Updated weights for policy 1, policy_version 195560 (0.0010) -[2023-11-28 05:20:28,363][87426] Updated weights for policy 1, policy_version 195570 (0.0008) -[2023-11-28 05:20:28,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 100229120. Throughput: 0: 2631.3, 1: 2730.9. Samples: 100246216. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:20:28,446][86177] Avg episode reward: [(0, '-500.070'), (1, '-517.600')] -[2023-11-28 05:20:28,748][87426] Updated weights for policy 1, policy_version 195580 (0.0008) -[2023-11-28 05:20:29,329][87424] Updated weights for policy 0, policy_version 195977 (0.0008) -[2023-11-28 05:20:29,712][87424] Updated weights for policy 0, policy_version 195987 (0.0007) -[2023-11-28 05:20:30,094][87424] Updated weights for policy 0, policy_version 195997 (0.0009) -[2023-11-28 05:20:31,076][87426] Updated weights for policy 1, policy_version 195590 (0.0010) -[2023-11-28 05:20:31,464][87426] Updated weights for policy 1, policy_version 195600 (0.0012) -[2023-11-28 05:20:31,832][87426] Updated weights for policy 1, policy_version 195610 (0.0011) -[2023-11-28 05:20:31,975][87424] Updated weights for policy 0, policy_version 196007 (0.0010) -[2023-11-28 05:20:32,352][87424] Updated weights for policy 0, policy_version 196017 (0.0012) -[2023-11-28 05:20:32,731][87424] Updated weights for policy 0, policy_version 196027 (0.0012) -[2023-11-28 05:20:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 100261888. Throughput: 0: 2670.4, 1: 2721.9. Samples: 100271776. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:20:33,445][86177] Avg episode reward: [(0, '-498.040'), (1, '-518.390')] -[2023-11-28 05:20:33,800][87426] Updated weights for policy 1, policy_version 195620 (0.0010) -[2023-11-28 05:20:34,176][87426] Updated weights for policy 1, policy_version 195630 (0.0009) -[2023-11-28 05:20:34,556][87426] Updated weights for policy 1, policy_version 195640 (0.0007) -[2023-11-28 05:20:35,004][87424] Updated weights for policy 0, policy_version 196037 (0.0012) -[2023-11-28 05:20:35,379][87424] Updated weights for policy 0, policy_version 196047 (0.0012) -[2023-11-28 05:20:35,767][87424] Updated weights for policy 0, policy_version 196057 (0.0012) -[2023-11-28 05:20:36,222][87426] Updated weights for policy 1, policy_version 195650 (0.0011) -[2023-11-28 05:20:36,604][87426] Updated weights for policy 1, policy_version 195660 (0.0012) -[2023-11-28 05:20:36,975][87426] Updated weights for policy 1, policy_version 195670 (0.0011) -[2023-11-28 05:20:37,354][87426] Updated weights for policy 1, policy_version 195680 (0.0012) -[2023-11-28 05:20:37,635][87424] Updated weights for policy 0, policy_version 196067 (0.0011) -[2023-11-28 05:20:38,020][87424] Updated weights for policy 0, policy_version 196077 (0.0007) -[2023-11-28 05:20:38,406][87424] Updated weights for policy 0, policy_version 196087 (0.0007) -[2023-11-28 05:20:38,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 100286464. Throughput: 0: 2714.0, 1: 2722.9. Samples: 100305216. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:20:38,445][86177] Avg episode reward: [(0, '-497.350'), (1, '-538.150')] -[2023-11-28 05:20:39,844][87426] Updated weights for policy 1, policy_version 195690 (0.0012) -[2023-11-28 05:20:40,220][87426] Updated weights for policy 1, policy_version 195700 (0.0011) -[2023-11-28 05:20:40,577][87424] Updated weights for policy 0, policy_version 196097 (0.0008) -[2023-11-28 05:20:40,602][87426] Updated weights for policy 1, policy_version 195710 (0.0010) -[2023-11-28 05:20:40,963][87424] Updated weights for policy 0, policy_version 196107 (0.0012) -[2023-11-28 05:20:41,346][87424] Updated weights for policy 0, policy_version 196117 (0.0012) -[2023-11-28 05:20:41,717][87424] Updated weights for policy 0, policy_version 196127 (0.0012) -[2023-11-28 05:20:42,427][87426] Updated weights for policy 1, policy_version 195720 (0.0012) -[2023-11-28 05:20:42,810][87426] Updated weights for policy 1, policy_version 195730 (0.0010) -[2023-11-28 05:20:43,177][87426] Updated weights for policy 1, policy_version 195740 (0.0011) -[2023-11-28 05:20:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 100319232. Throughput: 0: 2716.6, 1: 2726.0. Samples: 100330116. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:20:43,445][86177] Avg episode reward: [(0, '-495.680'), (1, '-539.550')] -[2023-11-28 05:20:44,315][87424] Updated weights for policy 0, policy_version 196137 (0.0008) -[2023-11-28 05:20:44,691][87424] Updated weights for policy 0, policy_version 196147 (0.0008) -[2023-11-28 05:20:45,070][87424] Updated weights for policy 0, policy_version 196157 (0.0007) -[2023-11-28 05:20:45,491][87426] Updated weights for policy 1, policy_version 195750 (0.0012) -[2023-11-28 05:20:45,879][87426] Updated weights for policy 1, policy_version 195760 (0.0012) -[2023-11-28 05:20:46,257][87426] Updated weights for policy 1, policy_version 195770 (0.0012) -[2023-11-28 05:20:46,822][87424] Updated weights for policy 0, policy_version 196167 (0.0010) -[2023-11-28 05:20:47,196][87424] Updated weights for policy 0, policy_version 196177 (0.0008) -[2023-11-28 05:20:47,575][87424] Updated weights for policy 0, policy_version 196187 (0.0009) -[2023-11-28 05:20:48,220][87426] Updated weights for policy 1, policy_version 195780 (0.0011) -[2023-11-28 05:20:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 100343808. Throughput: 0: 2690.0, 1: 2753.1. Samples: 100354260. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:20:48,446][86177] Avg episode reward: [(0, '-496.030'), (1, '-525.760')] -[2023-11-28 05:20:48,589][87426] Updated weights for policy 1, policy_version 195790 (0.0011) -[2023-11-28 05:20:48,966][87426] Updated weights for policy 1, policy_version 195800 (0.0009) -[2023-11-28 05:20:49,881][87424] Updated weights for policy 0, policy_version 196197 (0.0010) -[2023-11-28 05:20:50,256][87424] Updated weights for policy 0, policy_version 196207 (0.0012) -[2023-11-28 05:20:50,640][87424] Updated weights for policy 0, policy_version 196217 (0.0012) -[2023-11-28 05:20:50,828][87426] Updated weights for policy 1, policy_version 195810 (0.0009) -[2023-11-28 05:20:51,210][87426] Updated weights for policy 1, policy_version 195820 (0.0012) -[2023-11-28 05:20:51,588][87426] Updated weights for policy 1, policy_version 195830 (0.0012) -[2023-11-28 05:20:51,961][87426] Updated weights for policy 1, policy_version 195840 (0.0011) -[2023-11-28 05:20:53,059][87424] Updated weights for policy 0, policy_version 196227 (0.0011) -[2023-11-28 05:20:53,442][87424] Updated weights for policy 0, policy_version 196237 (0.0012) -[2023-11-28 05:20:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.9, 300 sec: 5415.1). Total num frames: 100368384. Throughput: 0: 2673.1, 1: 2773.8. Samples: 100386732. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:20:53,445][86177] Avg episode reward: [(0, '-497.820'), (1, '-525.470')] -[2023-11-28 05:20:53,823][87424] Updated weights for policy 0, policy_version 196247 (0.0011) -[2023-11-28 05:20:54,196][87426] Updated weights for policy 1, policy_version 195850 (0.0011) -[2023-11-28 05:20:54,577][87426] Updated weights for policy 1, policy_version 195860 (0.0011) -[2023-11-28 05:20:54,951][87426] Updated weights for policy 1, policy_version 195870 (0.0012) -[2023-11-28 05:20:56,441][87424] Updated weights for policy 0, policy_version 196257 (0.0010) -[2023-11-28 05:20:56,814][87424] Updated weights for policy 0, policy_version 196267 (0.0008) -[2023-11-28 05:20:57,204][87424] Updated weights for policy 0, policy_version 196277 (0.0007) -[2023-11-28 05:20:57,446][87426] Updated weights for policy 1, policy_version 195880 (0.0009) -[2023-11-28 05:20:57,590][87424] Updated weights for policy 0, policy_version 196287 (0.0008) -[2023-11-28 05:20:57,823][87426] Updated weights for policy 1, policy_version 195890 (0.0007) -[2023-11-28 05:20:58,210][87426] Updated weights for policy 1, policy_version 195900 (0.0007) -[2023-11-28 05:20:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 100401152. Throughput: 0: 2651.5, 1: 2766.2. Samples: 100410348. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:20:58,446][86177] Avg episode reward: [(0, '-501.370'), (1, '-505.980')] -[2023-11-28 05:20:59,779][87424] Updated weights for policy 0, policy_version 196297 (0.0011) -[2023-11-28 05:21:00,164][87424] Updated weights for policy 0, policy_version 196307 (0.0010) -[2023-11-28 05:21:00,284][87426] Updated weights for policy 1, policy_version 195910 (0.0007) -[2023-11-28 05:21:00,534][87424] Updated weights for policy 0, policy_version 196317 (0.0011) -[2023-11-28 05:21:00,664][87426] Updated weights for policy 1, policy_version 195920 (0.0010) -[2023-11-28 05:21:01,045][87426] Updated weights for policy 1, policy_version 195930 (0.0007) -[2023-11-28 05:21:02,781][87424] Updated weights for policy 0, policy_version 196327 (0.0012) -[2023-11-28 05:21:03,012][87426] Updated weights for policy 1, policy_version 195940 (0.0009) -[2023-11-28 05:21:03,156][87424] Updated weights for policy 0, policy_version 196337 (0.0008) -[2023-11-28 05:21:03,395][87426] Updated weights for policy 1, policy_version 195950 (0.0009) -[2023-11-28 05:21:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 100417536. Throughput: 0: 2643.7, 1: 2770.0. Samples: 100434244. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:21:03,445][86177] Avg episode reward: [(0, '-503.540'), (1, '-554.160')] -[2023-11-28 05:21:03,541][87424] Updated weights for policy 0, policy_version 196347 (0.0008) -[2023-11-28 05:21:03,767][87426] Updated weights for policy 1, policy_version 195960 (0.0008) -[2023-11-28 05:21:05,517][87426] Updated weights for policy 1, policy_version 195970 (0.0008) -[2023-11-28 05:21:05,831][87424] Updated weights for policy 0, policy_version 196357 (0.0007) -[2023-11-28 05:21:05,892][87426] Updated weights for policy 1, policy_version 195980 (0.0010) -[2023-11-28 05:21:06,211][87424] Updated weights for policy 0, policy_version 196367 (0.0007) -[2023-11-28 05:21:06,276][87426] Updated weights for policy 1, policy_version 195990 (0.0011) -[2023-11-28 05:21:06,604][87424] Updated weights for policy 0, policy_version 196377 (0.0007) -[2023-11-28 05:21:06,651][87426] Updated weights for policy 1, policy_version 196000 (0.0009) -[2023-11-28 05:21:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 100450304. Throughput: 0: 2683.5, 1: 2795.4. Samples: 100467744. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:21:08,446][86177] Avg episode reward: [(0, '-504.270'), (1, '-552.310')] -[2023-11-28 05:21:08,837][87424] Updated weights for policy 0, policy_version 196387 (0.0011) -[2023-11-28 05:21:08,958][87426] Updated weights for policy 1, policy_version 196010 (0.0008) -[2023-11-28 05:21:09,222][87424] Updated weights for policy 0, policy_version 196397 (0.0011) -[2023-11-28 05:21:09,330][87426] Updated weights for policy 1, policy_version 196020 (0.0011) -[2023-11-28 05:21:09,599][87424] Updated weights for policy 0, policy_version 196407 (0.0012) -[2023-11-28 05:21:09,712][87426] Updated weights for policy 1, policy_version 196030 (0.0012) -[2023-11-28 05:21:11,903][87424] Updated weights for policy 0, policy_version 196417 (0.0011) -[2023-11-28 05:21:12,202][87426] Updated weights for policy 1, policy_version 196040 (0.0011) -[2023-11-28 05:21:12,279][87424] Updated weights for policy 0, policy_version 196427 (0.0009) -[2023-11-28 05:21:12,574][87426] Updated weights for policy 1, policy_version 196050 (0.0011) -[2023-11-28 05:21:12,656][87424] Updated weights for policy 0, policy_version 196437 (0.0011) -[2023-11-28 05:21:12,960][87426] Updated weights for policy 1, policy_version 196060 (0.0011) -[2023-11-28 05:21:13,049][87424] Updated weights for policy 0, policy_version 196447 (0.0011) -[2023-11-28 05:21:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 100483072. Throughput: 0: 2683.3, 1: 2775.9. Samples: 100491880. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:21:13,445][86177] Avg episode reward: [(0, '-501.360'), (1, '-555.270')] -[2023-11-28 05:21:15,000][87424] Updated weights for policy 0, policy_version 196457 (0.0012) -[2023-11-28 05:21:15,277][87426] Updated weights for policy 1, policy_version 196070 (0.0011) -[2023-11-28 05:21:15,387][87424] Updated weights for policy 0, policy_version 196467 (0.0011) -[2023-11-28 05:21:15,655][87426] Updated weights for policy 1, policy_version 196080 (0.0011) -[2023-11-28 05:21:15,768][87424] Updated weights for policy 0, policy_version 196477 (0.0009) -[2023-11-28 05:21:16,035][87426] Updated weights for policy 1, policy_version 196090 (0.0011) -[2023-11-28 05:21:17,412][87424] Updated weights for policy 0, policy_version 196487 (0.0009) -[2023-11-28 05:21:17,789][87426] Updated weights for policy 1, policy_version 196100 (0.0010) -[2023-11-28 05:21:17,791][87424] Updated weights for policy 0, policy_version 196497 (0.0009) -[2023-11-28 05:21:18,162][87426] Updated weights for policy 1, policy_version 196110 (0.0008) -[2023-11-28 05:21:18,171][87424] Updated weights for policy 0, policy_version 196507 (0.0012) -[2023-11-28 05:21:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 100507648. Throughput: 0: 2669.3, 1: 2771.1. Samples: 100516596. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:21:18,446][86177] Avg episode reward: [(0, '-497.590'), (1, '-555.210')] -[2023-11-28 05:21:18,540][87426] Updated weights for policy 1, policy_version 196120 (0.0009) -[2023-11-28 05:21:20,096][87424] Updated weights for policy 0, policy_version 196517 (0.0012) -[2023-11-28 05:21:20,327][87426] Updated weights for policy 1, policy_version 196130 (0.0009) -[2023-11-28 05:21:20,479][87424] Updated weights for policy 0, policy_version 196527 (0.0011) -[2023-11-28 05:21:20,700][87426] Updated weights for policy 1, policy_version 196140 (0.0011) -[2023-11-28 05:21:20,855][87424] Updated weights for policy 0, policy_version 196537 (0.0008) -[2023-11-28 05:21:21,086][87426] Updated weights for policy 1, policy_version 196150 (0.0012) -[2023-11-28 05:21:21,473][87426] Updated weights for policy 1, policy_version 196160 (0.0009) -[2023-11-28 05:21:23,083][87424] Updated weights for policy 0, policy_version 196547 (0.0009) -[2023-11-28 05:21:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 100532224. Throughput: 0: 2662.1, 1: 2792.9. Samples: 100550692. Policy #0 lag: (min: 57.0, avg: 67.7, max: 94.0) -[2023-11-28 05:21:23,445][86177] Avg episode reward: [(0, '-494.570'), (1, '-503.630')] -[2023-11-28 05:21:23,457][87424] Updated weights for policy 0, policy_version 196557 (0.0012) -[2023-11-28 05:21:23,595][87426] Updated weights for policy 1, policy_version 196170 (0.0012) -[2023-11-28 05:21:23,836][87424] Updated weights for policy 0, policy_version 196567 (0.0011) -[2023-11-28 05:21:23,971][87426] Updated weights for policy 1, policy_version 196180 (0.0011) -[2023-11-28 05:21:24,355][87426] Updated weights for policy 1, policy_version 196190 (0.0009) -[2023-11-28 05:21:25,849][87424] Updated weights for policy 0, policy_version 196577 (0.0011) -[2023-11-28 05:21:26,224][87424] Updated weights for policy 0, policy_version 196587 (0.0010) -[2023-11-28 05:21:26,523][87426] Updated weights for policy 1, policy_version 196200 (0.0009) -[2023-11-28 05:21:26,606][87424] Updated weights for policy 0, policy_version 196597 (0.0009) -[2023-11-28 05:21:26,896][87426] Updated weights for policy 1, policy_version 196210 (0.0010) -[2023-11-28 05:21:26,996][87424] Updated weights for policy 0, policy_version 196607 (0.0008) -[2023-11-28 05:21:27,276][87426] Updated weights for policy 1, policy_version 196220 (0.0012) -[2023-11-28 05:21:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 100564992. Throughput: 0: 2658.3, 1: 2787.7. Samples: 100575188. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:21:28,445][86177] Avg episode reward: [(0, '-495.520'), (1, '-505.760')] -[2023-11-28 05:21:29,151][87424] Updated weights for policy 0, policy_version 196617 (0.0009) -[2023-11-28 05:21:29,353][87426] Updated weights for policy 1, policy_version 196230 (0.0011) -[2023-11-28 05:21:29,533][87424] Updated weights for policy 0, policy_version 196627 (0.0008) -[2023-11-28 05:21:29,722][87426] Updated weights for policy 1, policy_version 196240 (0.0011) -[2023-11-28 05:21:29,922][87424] Updated weights for policy 0, policy_version 196637 (0.0011) -[2023-11-28 05:21:30,103][87426] Updated weights for policy 1, policy_version 196250 (0.0012) -[2023-11-28 05:21:32,117][87424] Updated weights for policy 0, policy_version 196647 (0.0012) -[2023-11-28 05:21:32,212][87426] Updated weights for policy 1, policy_version 196260 (0.0012) -[2023-11-28 05:21:32,499][87424] Updated weights for policy 0, policy_version 196657 (0.0009) -[2023-11-28 05:21:32,594][87426] Updated weights for policy 1, policy_version 196270 (0.0011) -[2023-11-28 05:21:32,875][87424] Updated weights for policy 0, policy_version 196667 (0.0011) -[2023-11-28 05:21:32,966][87426] Updated weights for policy 1, policy_version 196280 (0.0012) -[2023-11-28 05:21:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 100597760. Throughput: 0: 2700.1, 1: 2782.8. Samples: 100600992. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:21:33,446][86177] Avg episode reward: [(0, '-497.130'), (1, '-514.180')] -[2023-11-28 05:21:35,186][87426] Updated weights for policy 1, policy_version 196290 (0.0010) -[2023-11-28 05:21:35,324][87424] Updated weights for policy 0, policy_version 196677 (0.0012) -[2023-11-28 05:21:35,573][87426] Updated weights for policy 1, policy_version 196300 (0.0007) -[2023-11-28 05:21:35,713][87424] Updated weights for policy 0, policy_version 196687 (0.0011) -[2023-11-28 05:21:35,948][87426] Updated weights for policy 1, policy_version 196310 (0.0007) -[2023-11-28 05:21:36,090][87424] Updated weights for policy 0, policy_version 196697 (0.0011) -[2023-11-28 05:21:36,327][87426] Updated weights for policy 1, policy_version 196320 (0.0008) -[2023-11-28 05:21:38,179][87424] Updated weights for policy 0, policy_version 196707 (0.0012) -[2023-11-28 05:21:38,427][87426] Updated weights for policy 1, policy_version 196330 (0.0011) -[2023-11-28 05:21:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 100614144. Throughput: 0: 2725.2, 1: 2775.0. Samples: 100634240. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:21:38,445][86177] Avg episode reward: [(0, '-525.470'), (1, '-513.010')] -[2023-11-28 05:21:38,555][87424] Updated weights for policy 0, policy_version 196717 (0.0009) -[2023-11-28 05:21:38,800][87426] Updated weights for policy 1, policy_version 196340 (0.0007) -[2023-11-28 05:21:38,933][87424] Updated weights for policy 0, policy_version 196727 (0.0008) -[2023-11-28 05:21:39,180][87426] Updated weights for policy 1, policy_version 196350 (0.0008) -[2023-11-28 05:21:41,306][87426] Updated weights for policy 1, policy_version 196360 (0.0010) -[2023-11-28 05:21:41,484][87424] Updated weights for policy 0, policy_version 196737 (0.0008) -[2023-11-28 05:21:41,686][87426] Updated weights for policy 1, policy_version 196370 (0.0012) -[2023-11-28 05:21:41,869][87424] Updated weights for policy 0, policy_version 196747 (0.0010) -[2023-11-28 05:21:42,060][87426] Updated weights for policy 1, policy_version 196380 (0.0011) -[2023-11-28 05:21:42,247][87424] Updated weights for policy 0, policy_version 196757 (0.0011) -[2023-11-28 05:21:42,633][87424] Updated weights for policy 0, policy_version 196767 (0.0012) -[2023-11-28 05:21:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 100646912. Throughput: 0: 2736.2, 1: 2798.9. Samples: 100659424. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:21:43,445][86177] Avg episode reward: [(0, '-527.640'), (1, '-515.970')] -[2023-11-28 05:21:44,078][87426] Updated weights for policy 1, policy_version 196390 (0.0011) -[2023-11-28 05:21:44,446][87426] Updated weights for policy 1, policy_version 196400 (0.0011) -[2023-11-28 05:21:44,820][87426] Updated weights for policy 1, policy_version 196410 (0.0010) -[2023-11-28 05:21:44,909][87424] Updated weights for policy 0, policy_version 196777 (0.0009) -[2023-11-28 05:21:45,284][87424] Updated weights for policy 0, policy_version 196787 (0.0008) -[2023-11-28 05:21:45,675][87424] Updated weights for policy 0, policy_version 196797 (0.0008) -[2023-11-28 05:21:47,178][87426] Updated weights for policy 1, policy_version 196420 (0.0007) -[2023-11-28 05:21:47,558][87426] Updated weights for policy 1, policy_version 196430 (0.0007) -[2023-11-28 05:21:47,897][87424] Updated weights for policy 0, policy_version 196807 (0.0011) -[2023-11-28 05:21:47,940][87426] Updated weights for policy 1, policy_version 196440 (0.0007) -[2023-11-28 05:21:48,286][87424] Updated weights for policy 0, policy_version 196817 (0.0012) -[2023-11-28 05:21:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 100671488. Throughput: 0: 2738.3, 1: 2800.5. Samples: 100683492. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:21:48,445][86177] Avg episode reward: [(0, '-528.340'), (1, '-512.710')] -[2023-11-28 05:21:48,662][87424] Updated weights for policy 0, policy_version 196827 (0.0012) -[2023-11-28 05:21:49,708][87426] Updated weights for policy 1, policy_version 196450 (0.0008) -[2023-11-28 05:21:50,084][87426] Updated weights for policy 1, policy_version 196460 (0.0011) -[2023-11-28 05:21:50,458][87426] Updated weights for policy 1, policy_version 196470 (0.0012) -[2023-11-28 05:21:50,673][87424] Updated weights for policy 0, policy_version 196837 (0.0011) -[2023-11-28 05:21:50,831][87426] Updated weights for policy 1, policy_version 196480 (0.0012) -[2023-11-28 05:21:51,050][87424] Updated weights for policy 0, policy_version 196847 (0.0011) -[2023-11-28 05:21:51,445][87424] Updated weights for policy 0, policy_version 196857 (0.0012) -[2023-11-28 05:21:53,090][87426] Updated weights for policy 1, policy_version 196490 (0.0011) -[2023-11-28 05:21:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 100696064. Throughput: 0: 2719.9, 1: 2785.9. Samples: 100715504. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:21:53,445][86177] Avg episode reward: [(0, '-501.590'), (1, '-502.000')] -[2023-11-28 05:21:53,468][87426] Updated weights for policy 1, policy_version 196500 (0.0012) -[2023-11-28 05:21:53,850][87426] Updated weights for policy 1, policy_version 196510 (0.0011) -[2023-11-28 05:21:53,882][87424] Updated weights for policy 0, policy_version 196867 (0.0011) -[2023-11-28 05:21:54,262][87424] Updated weights for policy 0, policy_version 196877 (0.0008) -[2023-11-28 05:21:54,642][87424] Updated weights for policy 0, policy_version 196887 (0.0008) -[2023-11-28 05:21:56,083][87426] Updated weights for policy 1, policy_version 196520 (0.0009) -[2023-11-28 05:21:56,452][87426] Updated weights for policy 1, policy_version 196530 (0.0007) -[2023-11-28 05:21:56,836][87426] Updated weights for policy 1, policy_version 196540 (0.0007) -[2023-11-28 05:21:56,902][87424] Updated weights for policy 0, policy_version 196897 (0.0008) -[2023-11-28 05:21:57,286][87424] Updated weights for policy 0, policy_version 196907 (0.0008) -[2023-11-28 05:21:57,671][87424] Updated weights for policy 0, policy_version 196917 (0.0008) -[2023-11-28 05:21:58,054][87424] Updated weights for policy 0, policy_version 196927 (0.0007) -[2023-11-28 05:21:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 100728832. Throughput: 0: 2716.7, 1: 2802.4. Samples: 100740240. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:21:58,445][86177] Avg episode reward: [(0, '-499.930'), (1, '-543.470')] -[2023-11-28 05:21:59,090][87426] Updated weights for policy 1, policy_version 196550 (0.0008) -[2023-11-28 05:21:59,468][87426] Updated weights for policy 1, policy_version 196560 (0.0008) -[2023-11-28 05:21:59,850][87426] Updated weights for policy 1, policy_version 196570 (0.0009) -[2023-11-28 05:21:59,880][87424] Updated weights for policy 0, policy_version 196937 (0.0009) -[2023-11-28 05:22:00,270][87424] Updated weights for policy 0, policy_version 196947 (0.0011) -[2023-11-28 05:22:00,645][87424] Updated weights for policy 0, policy_version 196957 (0.0012) -[2023-11-28 05:22:01,934][87426] Updated weights for policy 1, policy_version 196580 (0.0012) -[2023-11-28 05:22:02,308][87426] Updated weights for policy 1, policy_version 196590 (0.0010) -[2023-11-28 05:22:02,686][87426] Updated weights for policy 1, policy_version 196600 (0.0007) -[2023-11-28 05:22:03,107][87424] Updated weights for policy 0, policy_version 196967 (0.0011) -[2023-11-28 05:22:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 100753408. Throughput: 0: 2700.6, 1: 2828.8. Samples: 100765420. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:22:03,445][86177] Avg episode reward: [(0, '-500.760'), (1, '-568.870')] -[2023-11-28 05:22:03,483][87424] Updated weights for policy 0, policy_version 196977 (0.0008) -[2023-11-28 05:22:03,873][87424] Updated weights for policy 0, policy_version 196987 (0.0007) -[2023-11-28 05:22:04,415][87426] Updated weights for policy 1, policy_version 196610 (0.0009) -[2023-11-28 05:22:04,797][87426] Updated weights for policy 1, policy_version 196620 (0.0008) -[2023-11-28 05:22:05,180][87426] Updated weights for policy 1, policy_version 196630 (0.0010) -[2023-11-28 05:22:05,560][87426] Updated weights for policy 1, policy_version 196640 (0.0011) -[2023-11-28 05:22:05,968][87424] Updated weights for policy 0, policy_version 196997 (0.0009) -[2023-11-28 05:22:06,363][87424] Updated weights for policy 0, policy_version 197007 (0.0012) -[2023-11-28 05:22:06,758][87424] Updated weights for policy 0, policy_version 197017 (0.0012) -[2023-11-28 05:22:07,723][87426] Updated weights for policy 1, policy_version 196650 (0.0009) -[2023-11-28 05:22:08,102][87426] Updated weights for policy 1, policy_version 196660 (0.0011) -[2023-11-28 05:22:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 100777984. Throughput: 0: 2679.8, 1: 2799.7. Samples: 100797272. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:22:08,445][86177] Avg episode reward: [(0, '-502.700'), (1, '-574.060')] -[2023-11-28 05:22:08,473][87426] Updated weights for policy 1, policy_version 196670 (0.0012) -[2023-11-28 05:22:08,626][87424] Updated weights for policy 0, policy_version 197027 (0.0012) -[2023-11-28 05:22:09,010][87424] Updated weights for policy 0, policy_version 197037 (0.0011) -[2023-11-28 05:22:09,387][87424] Updated weights for policy 0, policy_version 197047 (0.0007) -[2023-11-28 05:22:10,576][87426] Updated weights for policy 1, policy_version 196680 (0.0009) -[2023-11-28 05:22:10,959][87426] Updated weights for policy 1, policy_version 196690 (0.0008) -[2023-11-28 05:22:11,339][87426] Updated weights for policy 1, policy_version 196700 (0.0008) -[2023-11-28 05:22:11,874][87424] Updated weights for policy 0, policy_version 197057 (0.0008) -[2023-11-28 05:22:12,254][87424] Updated weights for policy 0, policy_version 197067 (0.0012) -[2023-11-28 05:22:12,636][87424] Updated weights for policy 0, policy_version 197077 (0.0012) -[2023-11-28 05:22:13,015][87424] Updated weights for policy 0, policy_version 197087 (0.0012) -[2023-11-28 05:22:13,407][87426] Updated weights for policy 1, policy_version 196710 (0.0010) -[2023-11-28 05:22:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 100810752. Throughput: 0: 2686.6, 1: 2804.9. Samples: 100822304. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:22:13,445][86177] Avg episode reward: [(0, '-501.180'), (1, '-572.910')] -[2023-11-28 05:22:13,788][87426] Updated weights for policy 1, policy_version 196720 (0.0008) -[2023-11-28 05:22:14,170][87426] Updated weights for policy 1, policy_version 196730 (0.0012) -[2023-11-28 05:22:15,380][87424] Updated weights for policy 0, policy_version 197097 (0.0012) -[2023-11-28 05:22:15,756][87424] Updated weights for policy 0, policy_version 197107 (0.0012) -[2023-11-28 05:22:16,137][87424] Updated weights for policy 0, policy_version 197117 (0.0011) -[2023-11-28 05:22:16,288][87426] Updated weights for policy 1, policy_version 196740 (0.0012) -[2023-11-28 05:22:16,668][87426] Updated weights for policy 1, policy_version 196750 (0.0012) -[2023-11-28 05:22:17,044][87426] Updated weights for policy 1, policy_version 196760 (0.0012) -[2023-11-28 05:22:17,968][87424] Updated weights for policy 0, policy_version 197127 (0.0011) -[2023-11-28 05:22:18,349][87424] Updated weights for policy 0, policy_version 197137 (0.0010) -[2023-11-28 05:22:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 100835328. Throughput: 0: 2691.1, 1: 2798.2. Samples: 100848012. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:22:18,445][86177] Avg episode reward: [(0, '-499.370'), (1, '-532.120')] -[2023-11-28 05:22:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000196768_50372608.pth... -[2023-11-28 05:22:18,491][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000194208_49717248.pth -[2023-11-28 05:22:18,729][87424] Updated weights for policy 0, policy_version 197147 (0.0007) -[2023-11-28 05:22:18,918][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000197152_50470912.pth... -[2023-11-28 05:22:18,963][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000194624_49823744.pth -[2023-11-28 05:22:19,334][87426] Updated weights for policy 1, policy_version 196770 (0.0012) -[2023-11-28 05:22:19,716][87426] Updated weights for policy 1, policy_version 196780 (0.0012) -[2023-11-28 05:22:20,086][87426] Updated weights for policy 1, policy_version 196790 (0.0012) -[2023-11-28 05:22:20,462][87426] Updated weights for policy 1, policy_version 196800 (0.0012) -[2023-11-28 05:22:21,125][87424] Updated weights for policy 0, policy_version 197157 (0.0009) -[2023-11-28 05:22:21,497][87424] Updated weights for policy 0, policy_version 197167 (0.0009) -[2023-11-28 05:22:21,880][87424] Updated weights for policy 0, policy_version 197177 (0.0009) -[2023-11-28 05:22:22,773][87426] Updated weights for policy 1, policy_version 196810 (0.0008) -[2023-11-28 05:22:23,141][87426] Updated weights for policy 1, policy_version 196820 (0.0010) -[2023-11-28 05:22:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 100859904. Throughput: 0: 2681.9, 1: 2789.2. Samples: 100880440. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:22:23,445][86177] Avg episode reward: [(0, '-494.690'), (1, '-554.070')] -[2023-11-28 05:22:23,519][87426] Updated weights for policy 1, policy_version 196830 (0.0012) -[2023-11-28 05:22:24,383][87424] Updated weights for policy 0, policy_version 197187 (0.0009) -[2023-11-28 05:22:24,763][87424] Updated weights for policy 0, policy_version 197197 (0.0008) -[2023-11-28 05:22:25,144][87424] Updated weights for policy 0, policy_version 197207 (0.0009) -[2023-11-28 05:22:26,041][87426] Updated weights for policy 1, policy_version 196840 (0.0008) -[2023-11-28 05:22:26,418][87426] Updated weights for policy 1, policy_version 196850 (0.0007) -[2023-11-28 05:22:26,792][87426] Updated weights for policy 1, policy_version 196860 (0.0008) -[2023-11-28 05:22:27,392][87424] Updated weights for policy 0, policy_version 197217 (0.0011) -[2023-11-28 05:22:27,774][87424] Updated weights for policy 0, policy_version 197227 (0.0007) -[2023-11-28 05:22:28,157][87424] Updated weights for policy 0, policy_version 197237 (0.0008) -[2023-11-28 05:22:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 100884480. Throughput: 0: 2696.6, 1: 2743.4. Samples: 100904224. Policy #0 lag: (min: 15.0, avg: 25.1, max: 47.0) -[2023-11-28 05:22:28,445][86177] Avg episode reward: [(0, '-501.430'), (1, '-549.360')] -[2023-11-28 05:22:28,545][87424] Updated weights for policy 0, policy_version 197247 (0.0008) -[2023-11-28 05:22:29,270][87426] Updated weights for policy 1, policy_version 196870 (0.0008) -[2023-11-28 05:22:29,653][87426] Updated weights for policy 1, policy_version 196880 (0.0008) -[2023-11-28 05:22:30,035][87426] Updated weights for policy 1, policy_version 196890 (0.0008) -[2023-11-28 05:22:30,923][87424] Updated weights for policy 0, policy_version 197257 (0.0007) -[2023-11-28 05:22:31,306][87424] Updated weights for policy 0, policy_version 197267 (0.0007) -[2023-11-28 05:22:31,684][87424] Updated weights for policy 0, policy_version 197277 (0.0009) -[2023-11-28 05:22:31,934][87426] Updated weights for policy 1, policy_version 196900 (0.0008) -[2023-11-28 05:22:32,301][87426] Updated weights for policy 1, policy_version 196910 (0.0009) -[2023-11-28 05:22:32,681][87426] Updated weights for policy 1, policy_version 196920 (0.0011) -[2023-11-28 05:22:33,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 100917248. Throughput: 0: 2683.0, 1: 2737.4. Samples: 100927412. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:22:33,446][86177] Avg episode reward: [(0, '-512.480'), (1, '-550.830')] -[2023-11-28 05:22:34,068][87424] Updated weights for policy 0, policy_version 197287 (0.0011) -[2023-11-28 05:22:34,439][87424] Updated weights for policy 0, policy_version 197297 (0.0011) -[2023-11-28 05:22:34,485][87426] Updated weights for policy 1, policy_version 196930 (0.0010) -[2023-11-28 05:22:34,817][87424] Updated weights for policy 0, policy_version 197307 (0.0012) -[2023-11-28 05:22:34,870][87426] Updated weights for policy 1, policy_version 196940 (0.0008) -[2023-11-28 05:22:35,252][87426] Updated weights for policy 1, policy_version 196950 (0.0008) -[2023-11-28 05:22:35,621][87426] Updated weights for policy 1, policy_version 196960 (0.0009) -[2023-11-28 05:22:36,439][87424] Updated weights for policy 0, policy_version 197317 (0.0010) -[2023-11-28 05:22:36,817][87424] Updated weights for policy 0, policy_version 197327 (0.0009) -[2023-11-28 05:22:37,220][87424] Updated weights for policy 0, policy_version 197337 (0.0009) -[2023-11-28 05:22:38,159][87426] Updated weights for policy 1, policy_version 196970 (0.0011) -[2023-11-28 05:22:38,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 100941824. Throughput: 0: 2702.7, 1: 2722.9. Samples: 100959656. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:22:38,445][86177] Avg episode reward: [(0, '-514.750'), (1, '-550.920')] -[2023-11-28 05:22:38,549][87426] Updated weights for policy 1, policy_version 196980 (0.0012) -[2023-11-28 05:22:38,939][87426] Updated weights for policy 1, policy_version 196990 (0.0012) -[2023-11-28 05:22:39,153][87424] Updated weights for policy 0, policy_version 197347 (0.0009) -[2023-11-28 05:22:39,539][87424] Updated weights for policy 0, policy_version 197357 (0.0012) -[2023-11-28 05:22:39,922][87424] Updated weights for policy 0, policy_version 197367 (0.0012) -[2023-11-28 05:22:41,015][87426] Updated weights for policy 1, policy_version 197000 (0.0012) -[2023-11-28 05:22:41,382][87426] Updated weights for policy 1, policy_version 197010 (0.0010) -[2023-11-28 05:22:41,764][87426] Updated weights for policy 1, policy_version 197020 (0.0009) -[2023-11-28 05:22:42,317][87424] Updated weights for policy 0, policy_version 197377 (0.0012) -[2023-11-28 05:22:42,691][87424] Updated weights for policy 0, policy_version 197387 (0.0010) -[2023-11-28 05:22:43,076][87424] Updated weights for policy 0, policy_version 197397 (0.0009) -[2023-11-28 05:22:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 100966400. Throughput: 0: 2718.6, 1: 2701.2. Samples: 100984132. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:22:43,445][86177] Avg episode reward: [(0, '-518.680'), (1, '-514.230')] -[2023-11-28 05:22:43,464][87424] Updated weights for policy 0, policy_version 197407 (0.0008) -[2023-11-28 05:22:44,146][87426] Updated weights for policy 1, policy_version 197030 (0.0010) -[2023-11-28 05:22:44,525][87426] Updated weights for policy 1, policy_version 197040 (0.0007) -[2023-11-28 05:22:44,910][87426] Updated weights for policy 1, policy_version 197050 (0.0010) -[2023-11-28 05:22:45,504][87424] Updated weights for policy 0, policy_version 197417 (0.0010) -[2023-11-28 05:22:45,879][87424] Updated weights for policy 0, policy_version 197427 (0.0011) -[2023-11-28 05:22:46,265][87424] Updated weights for policy 0, policy_version 197437 (0.0012) -[2023-11-28 05:22:47,460][87426] Updated weights for policy 1, policy_version 197060 (0.0012) -[2023-11-28 05:22:47,843][87426] Updated weights for policy 1, policy_version 197070 (0.0011) -[2023-11-28 05:22:48,224][87426] Updated weights for policy 1, policy_version 197080 (0.0011) -[2023-11-28 05:22:48,352][87424] Updated weights for policy 0, policy_version 197447 (0.0010) -[2023-11-28 05:22:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 100990976. Throughput: 0: 2724.8, 1: 2681.4. Samples: 101008700. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:22:48,445][86177] Avg episode reward: [(0, '-509.690'), (1, '-554.360')] -[2023-11-28 05:22:48,737][87424] Updated weights for policy 0, policy_version 197457 (0.0008) -[2023-11-28 05:22:49,115][87424] Updated weights for policy 0, policy_version 197467 (0.0009) -[2023-11-28 05:22:50,241][87426] Updated weights for policy 1, policy_version 197090 (0.0011) -[2023-11-28 05:22:50,610][87426] Updated weights for policy 1, policy_version 197100 (0.0011) -[2023-11-28 05:22:50,989][87426] Updated weights for policy 1, policy_version 197110 (0.0008) -[2023-11-28 05:22:51,341][87424] Updated weights for policy 0, policy_version 197477 (0.0007) -[2023-11-28 05:22:51,375][87426] Updated weights for policy 1, policy_version 197120 (0.0010) -[2023-11-28 05:22:51,722][87424] Updated weights for policy 0, policy_version 197487 (0.0010) -[2023-11-28 05:22:52,116][87424] Updated weights for policy 0, policy_version 197497 (0.0011) -[2023-11-28 05:22:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101023744. Throughput: 0: 2739.7, 1: 2694.1. Samples: 101041796. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:22:53,445][86177] Avg episode reward: [(0, '-508.150'), (1, '-554.760')] -[2023-11-28 05:22:53,819][87426] Updated weights for policy 1, policy_version 197130 (0.0011) -[2023-11-28 05:22:54,199][87426] Updated weights for policy 1, policy_version 197140 (0.0012) -[2023-11-28 05:22:54,575][87424] Updated weights for policy 0, policy_version 197507 (0.0010) -[2023-11-28 05:22:54,582][87426] Updated weights for policy 1, policy_version 197150 (0.0011) -[2023-11-28 05:22:54,949][87424] Updated weights for policy 0, policy_version 197517 (0.0010) -[2023-11-28 05:22:55,335][87424] Updated weights for policy 0, policy_version 197527 (0.0010) -[2023-11-28 05:22:56,370][87426] Updated weights for policy 1, policy_version 197160 (0.0010) -[2023-11-28 05:22:56,743][87426] Updated weights for policy 1, policy_version 197170 (0.0012) -[2023-11-28 05:22:57,118][87426] Updated weights for policy 1, policy_version 197180 (0.0012) -[2023-11-28 05:22:57,534][87424] Updated weights for policy 0, policy_version 197537 (0.0011) -[2023-11-28 05:22:57,907][87424] Updated weights for policy 0, policy_version 197547 (0.0012) -[2023-11-28 05:22:58,289][87424] Updated weights for policy 0, policy_version 197557 (0.0007) -[2023-11-28 05:22:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 101048320. Throughput: 0: 2725.2, 1: 2695.1. Samples: 101066216. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:22:58,445][86177] Avg episode reward: [(0, '-508.040'), (1, '-558.340')] -[2023-11-28 05:22:58,679][87424] Updated weights for policy 0, policy_version 197567 (0.0007) -[2023-11-28 05:22:59,356][87426] Updated weights for policy 1, policy_version 197190 (0.0012) -[2023-11-28 05:22:59,739][87426] Updated weights for policy 1, policy_version 197200 (0.0008) -[2023-11-28 05:23:00,120][87426] Updated weights for policy 1, policy_version 197210 (0.0009) -[2023-11-28 05:23:00,971][87424] Updated weights for policy 0, policy_version 197577 (0.0012) -[2023-11-28 05:23:01,350][87424] Updated weights for policy 0, policy_version 197587 (0.0010) -[2023-11-28 05:23:01,728][87424] Updated weights for policy 0, policy_version 197597 (0.0009) -[2023-11-28 05:23:02,270][87426] Updated weights for policy 1, policy_version 197220 (0.0010) -[2023-11-28 05:23:02,655][87426] Updated weights for policy 1, policy_version 197230 (0.0012) -[2023-11-28 05:23:03,027][87426] Updated weights for policy 1, policy_version 197240 (0.0012) -[2023-11-28 05:23:03,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101081088. Throughput: 0: 2695.3, 1: 2697.5. Samples: 101090688. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:23:03,446][86177] Avg episode reward: [(0, '-507.820'), (1, '-547.610')] -[2023-11-28 05:23:03,580][87424] Updated weights for policy 0, policy_version 197607 (0.0010) -[2023-11-28 05:23:03,958][87424] Updated weights for policy 0, policy_version 197617 (0.0007) -[2023-11-28 05:23:04,344][87424] Updated weights for policy 0, policy_version 197627 (0.0008) -[2023-11-28 05:23:05,299][87426] Updated weights for policy 1, policy_version 197250 (0.0012) -[2023-11-28 05:23:05,693][87426] Updated weights for policy 1, policy_version 197260 (0.0009) -[2023-11-28 05:23:06,078][87426] Updated weights for policy 1, policy_version 197270 (0.0011) -[2023-11-28 05:23:06,454][87426] Updated weights for policy 1, policy_version 197280 (0.0011) -[2023-11-28 05:23:06,704][87424] Updated weights for policy 0, policy_version 197637 (0.0011) -[2023-11-28 05:23:07,085][87424] Updated weights for policy 0, policy_version 197647 (0.0012) -[2023-11-28 05:23:07,465][87424] Updated weights for policy 0, policy_version 197657 (0.0012) -[2023-11-28 05:23:08,324][87426] Updated weights for policy 1, policy_version 197290 (0.0009) -[2023-11-28 05:23:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 101105664. Throughput: 0: 2693.7, 1: 2713.3. Samples: 101123756. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:23:08,445][86177] Avg episode reward: [(0, '-507.300'), (1, '-510.130')] -[2023-11-28 05:23:08,700][87426] Updated weights for policy 1, policy_version 197300 (0.0008) -[2023-11-28 05:23:09,078][87426] Updated weights for policy 1, policy_version 197310 (0.0010) -[2023-11-28 05:23:09,860][87424] Updated weights for policy 0, policy_version 197667 (0.0011) -[2023-11-28 05:23:10,249][87424] Updated weights for policy 0, policy_version 197677 (0.0012) -[2023-11-28 05:23:10,630][87424] Updated weights for policy 0, policy_version 197687 (0.0012) -[2023-11-28 05:23:11,316][87426] Updated weights for policy 1, policy_version 197320 (0.0011) -[2023-11-28 05:23:11,694][87426] Updated weights for policy 1, policy_version 197330 (0.0012) -[2023-11-28 05:23:12,072][87426] Updated weights for policy 1, policy_version 197340 (0.0012) -[2023-11-28 05:23:12,741][87424] Updated weights for policy 0, policy_version 197697 (0.0012) -[2023-11-28 05:23:13,123][87424] Updated weights for policy 0, policy_version 197707 (0.0010) -[2023-11-28 05:23:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 101130240. Throughput: 0: 2685.9, 1: 2745.8. Samples: 101148648. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:23:13,445][86177] Avg episode reward: [(0, '-502.400'), (1, '-513.870')] -[2023-11-28 05:23:13,506][87424] Updated weights for policy 0, policy_version 197717 (0.0009) -[2023-11-28 05:23:13,895][87424] Updated weights for policy 0, policy_version 197727 (0.0011) -[2023-11-28 05:23:14,063][87426] Updated weights for policy 1, policy_version 197350 (0.0012) -[2023-11-28 05:23:14,442][87426] Updated weights for policy 1, policy_version 197360 (0.0012) -[2023-11-28 05:23:14,834][87426] Updated weights for policy 1, policy_version 197370 (0.0012) -[2023-11-28 05:23:16,162][87424] Updated weights for policy 0, policy_version 197737 (0.0011) -[2023-11-28 05:23:16,419][87426] Updated weights for policy 1, policy_version 197380 (0.0012) -[2023-11-28 05:23:16,543][87424] Updated weights for policy 0, policy_version 197747 (0.0011) -[2023-11-28 05:23:16,807][87426] Updated weights for policy 1, policy_version 197390 (0.0011) -[2023-11-28 05:23:16,932][87424] Updated weights for policy 0, policy_version 197757 (0.0011) -[2023-11-28 05:23:17,176][87426] Updated weights for policy 1, policy_version 197400 (0.0008) -[2023-11-28 05:23:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101163008. Throughput: 0: 2711.4, 1: 2764.1. Samples: 101173808. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:23:18,445][86177] Avg episode reward: [(0, '-500.710'), (1, '-508.990')] -[2023-11-28 05:23:19,224][87424] Updated weights for policy 0, policy_version 197767 (0.0007) -[2023-11-28 05:23:19,522][87426] Updated weights for policy 1, policy_version 197410 (0.0008) -[2023-11-28 05:23:19,599][87424] Updated weights for policy 0, policy_version 197777 (0.0007) -[2023-11-28 05:23:19,910][87426] Updated weights for policy 1, policy_version 197420 (0.0011) -[2023-11-28 05:23:19,981][87424] Updated weights for policy 0, policy_version 197787 (0.0010) -[2023-11-28 05:23:20,282][87426] Updated weights for policy 1, policy_version 197430 (0.0010) -[2023-11-28 05:23:20,657][87426] Updated weights for policy 1, policy_version 197440 (0.0009) -[2023-11-28 05:23:22,438][87424] Updated weights for policy 0, policy_version 197797 (0.0008) -[2023-11-28 05:23:22,682][87426] Updated weights for policy 1, policy_version 197450 (0.0010) -[2023-11-28 05:23:22,817][87424] Updated weights for policy 0, policy_version 197807 (0.0008) -[2023-11-28 05:23:23,064][87426] Updated weights for policy 1, policy_version 197460 (0.0011) -[2023-11-28 05:23:23,198][87424] Updated weights for policy 0, policy_version 197817 (0.0008) -[2023-11-28 05:23:23,442][87426] Updated weights for policy 1, policy_version 197470 (0.0011) -[2023-11-28 05:23:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 101179392. Throughput: 0: 2692.1, 1: 2769.5. Samples: 101205428. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:23:23,445][86177] Avg episode reward: [(0, '-503.150'), (1, '-508.580')] -[2023-11-28 05:23:25,208][87424] Updated weights for policy 0, policy_version 197827 (0.0010) -[2023-11-28 05:23:25,537][87426] Updated weights for policy 1, policy_version 197480 (0.0010) -[2023-11-28 05:23:25,592][87424] Updated weights for policy 0, policy_version 197837 (0.0011) -[2023-11-28 05:23:25,914][87426] Updated weights for policy 1, policy_version 197490 (0.0009) -[2023-11-28 05:23:25,960][87424] Updated weights for policy 0, policy_version 197847 (0.0011) -[2023-11-28 05:23:26,302][87426] Updated weights for policy 1, policy_version 197500 (0.0007) -[2023-11-28 05:23:28,366][87424] Updated weights for policy 0, policy_version 197857 (0.0011) -[2023-11-28 05:23:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101212160. Throughput: 0: 2681.1, 1: 2797.6. Samples: 101230672. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:23:28,445][86177] Avg episode reward: [(0, '-530.750'), (1, '-504.820')] -[2023-11-28 05:23:28,738][87426] Updated weights for policy 1, policy_version 197510 (0.0010) -[2023-11-28 05:23:28,756][87424] Updated weights for policy 0, policy_version 197867 (0.0007) -[2023-11-28 05:23:29,109][87426] Updated weights for policy 1, policy_version 197520 (0.0011) -[2023-11-28 05:23:29,135][87424] Updated weights for policy 0, policy_version 197877 (0.0008) -[2023-11-28 05:23:29,496][87426] Updated weights for policy 1, policy_version 197530 (0.0010) -[2023-11-28 05:23:29,520][87424] Updated weights for policy 0, policy_version 197887 (0.0008) -[2023-11-28 05:23:31,352][87426] Updated weights for policy 1, policy_version 197540 (0.0008) -[2023-11-28 05:23:31,680][87424] Updated weights for policy 0, policy_version 197897 (0.0008) -[2023-11-28 05:23:31,735][87426] Updated weights for policy 1, policy_version 197550 (0.0008) -[2023-11-28 05:23:32,058][87424] Updated weights for policy 0, policy_version 197907 (0.0010) -[2023-11-28 05:23:32,112][87426] Updated weights for policy 1, policy_version 197560 (0.0008) -[2023-11-28 05:23:32,437][87424] Updated weights for policy 0, policy_version 197917 (0.0008) -[2023-11-28 05:23:33,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 101244928. Throughput: 0: 2673.9, 1: 2792.2. Samples: 101254672. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:23:33,445][86177] Avg episode reward: [(0, '-530.150'), (1, '-505.490')] -[2023-11-28 05:23:34,366][87426] Updated weights for policy 1, policy_version 197570 (0.0010) -[2023-11-28 05:23:34,738][87426] Updated weights for policy 1, policy_version 197580 (0.0011) -[2023-11-28 05:23:34,929][87424] Updated weights for policy 0, policy_version 197927 (0.0010) -[2023-11-28 05:23:35,115][87426] Updated weights for policy 1, policy_version 197590 (0.0010) -[2023-11-28 05:23:35,304][87424] Updated weights for policy 0, policy_version 197937 (0.0010) -[2023-11-28 05:23:35,492][87426] Updated weights for policy 1, policy_version 197600 (0.0011) -[2023-11-28 05:23:35,690][87424] Updated weights for policy 0, policy_version 197947 (0.0012) -[2023-11-28 05:23:37,424][87426] Updated weights for policy 1, policy_version 197610 (0.0012) -[2023-11-28 05:23:37,813][87426] Updated weights for policy 1, policy_version 197620 (0.0012) -[2023-11-28 05:23:38,124][87424] Updated weights for policy 0, policy_version 197957 (0.0012) -[2023-11-28 05:23:38,190][87426] Updated weights for policy 1, policy_version 197630 (0.0008) -[2023-11-28 05:23:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 101269504. Throughput: 0: 2659.2, 1: 2806.2. Samples: 101287740. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 05:23:38,445][86177] Avg episode reward: [(0, '-529.560'), (1, '-516.480')] -[2023-11-28 05:23:38,504][87424] Updated weights for policy 0, policy_version 197967 (0.0008) -[2023-11-28 05:23:38,894][87424] Updated weights for policy 0, policy_version 197977 (0.0010) -[2023-11-28 05:23:40,504][87426] Updated weights for policy 1, policy_version 197640 (0.0011) -[2023-11-28 05:23:40,858][87424] Updated weights for policy 0, policy_version 197987 (0.0011) -[2023-11-28 05:23:40,894][87426] Updated weights for policy 1, policy_version 197650 (0.0008) -[2023-11-28 05:23:41,243][87424] Updated weights for policy 0, policy_version 197997 (0.0011) -[2023-11-28 05:23:41,261][87426] Updated weights for policy 1, policy_version 197660 (0.0011) -[2023-11-28 05:23:41,624][87424] Updated weights for policy 0, policy_version 198007 (0.0010) -[2023-11-28 05:23:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101294080. Throughput: 0: 2671.1, 1: 2791.0. Samples: 101312012. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:23:43,445][86177] Avg episode reward: [(0, '-524.950'), (1, '-520.490')] -[2023-11-28 05:23:43,738][87426] Updated weights for policy 1, policy_version 197670 (0.0010) -[2023-11-28 05:23:44,008][87424] Updated weights for policy 0, policy_version 198017 (0.0010) -[2023-11-28 05:23:44,117][87426] Updated weights for policy 1, policy_version 197680 (0.0012) -[2023-11-28 05:23:44,392][87424] Updated weights for policy 0, policy_version 198027 (0.0012) -[2023-11-28 05:23:44,504][87426] Updated weights for policy 1, policy_version 197690 (0.0012) -[2023-11-28 05:23:44,772][87424] Updated weights for policy 0, policy_version 198037 (0.0012) -[2023-11-28 05:23:45,154][87424] Updated weights for policy 0, policy_version 198047 (0.0009) -[2023-11-28 05:23:46,574][87426] Updated weights for policy 1, policy_version 197700 (0.0010) -[2023-11-28 05:23:46,962][87426] Updated weights for policy 1, policy_version 197710 (0.0012) -[2023-11-28 05:23:47,334][87426] Updated weights for policy 1, policy_version 197720 (0.0011) -[2023-11-28 05:23:47,386][87424] Updated weights for policy 0, policy_version 198057 (0.0011) -[2023-11-28 05:23:47,763][87424] Updated weights for policy 0, policy_version 198067 (0.0008) -[2023-11-28 05:23:48,143][87424] Updated weights for policy 0, policy_version 198077 (0.0009) -[2023-11-28 05:23:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 101326848. Throughput: 0: 2672.5, 1: 2789.6. Samples: 101336480. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:23:48,445][86177] Avg episode reward: [(0, '-496.590'), (1, '-524.150')] -[2023-11-28 05:23:49,258][87426] Updated weights for policy 1, policy_version 197730 (0.0009) -[2023-11-28 05:23:49,634][87426] Updated weights for policy 1, policy_version 197740 (0.0008) -[2023-11-28 05:23:49,977][87424] Updated weights for policy 0, policy_version 198087 (0.0008) -[2023-11-28 05:23:50,018][87426] Updated weights for policy 1, policy_version 197750 (0.0010) -[2023-11-28 05:23:50,358][87424] Updated weights for policy 0, policy_version 198097 (0.0010) -[2023-11-28 05:23:50,390][87426] Updated weights for policy 1, policy_version 197760 (0.0011) -[2023-11-28 05:23:50,744][87424] Updated weights for policy 0, policy_version 198107 (0.0012) -[2023-11-28 05:23:52,718][87426] Updated weights for policy 1, policy_version 197770 (0.0009) -[2023-11-28 05:23:53,046][87424] Updated weights for policy 0, policy_version 198117 (0.0010) -[2023-11-28 05:23:53,095][87426] Updated weights for policy 1, policy_version 197780 (0.0011) -[2023-11-28 05:23:53,437][87424] Updated weights for policy 0, policy_version 198127 (0.0010) -[2023-11-28 05:23:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 101343232. Throughput: 0: 2680.0, 1: 2757.1. Samples: 101368424. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:23:53,445][86177] Avg episode reward: [(0, '-540.080'), (1, '-520.190')] -[2023-11-28 05:23:53,473][87426] Updated weights for policy 1, policy_version 197790 (0.0010) -[2023-11-28 05:23:53,831][87424] Updated weights for policy 0, policy_version 198137 (0.0018) -[2023-11-28 05:23:55,760][87426] Updated weights for policy 1, policy_version 197800 (0.0011) -[2023-11-28 05:23:55,917][87424] Updated weights for policy 0, policy_version 198147 (0.0012) -[2023-11-28 05:23:56,136][87426] Updated weights for policy 1, policy_version 197810 (0.0011) -[2023-11-28 05:23:56,305][87424] Updated weights for policy 0, policy_version 198157 (0.0011) -[2023-11-28 05:23:56,512][87426] Updated weights for policy 1, policy_version 197820 (0.0012) -[2023-11-28 05:23:56,679][87424] Updated weights for policy 0, policy_version 198167 (0.0011) -[2023-11-28 05:23:58,286][87426] Updated weights for policy 1, policy_version 197830 (0.0011) -[2023-11-28 05:23:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101376000. Throughput: 0: 2685.7, 1: 2773.1. Samples: 101394292. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:23:58,445][86177] Avg episode reward: [(0, '-548.610'), (1, '-516.530')] -[2023-11-28 05:23:58,668][87426] Updated weights for policy 1, policy_version 197840 (0.0011) -[2023-11-28 05:23:59,040][87424] Updated weights for policy 0, policy_version 198177 (0.0012) -[2023-11-28 05:23:59,061][87426] Updated weights for policy 1, policy_version 197850 (0.0011) -[2023-11-28 05:23:59,424][87424] Updated weights for policy 0, policy_version 198187 (0.0008) -[2023-11-28 05:23:59,798][87424] Updated weights for policy 0, policy_version 198197 (0.0008) -[2023-11-28 05:24:00,181][87424] Updated weights for policy 0, policy_version 198207 (0.0009) -[2023-11-28 05:24:00,686][87426] Updated weights for policy 1, policy_version 197860 (0.0012) -[2023-11-28 05:24:01,062][87426] Updated weights for policy 1, policy_version 197870 (0.0012) -[2023-11-28 05:24:01,449][87426] Updated weights for policy 1, policy_version 197880 (0.0012) -[2023-11-28 05:24:02,221][87424] Updated weights for policy 0, policy_version 198217 (0.0014) -[2023-11-28 05:24:02,611][87424] Updated weights for policy 0, policy_version 198227 (0.0011) -[2023-11-28 05:24:02,983][87424] Updated weights for policy 0, policy_version 198237 (0.0010) -[2023-11-28 05:24:03,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 101408768. Throughput: 0: 2675.7, 1: 2757.5. Samples: 101418304. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:03,445][86177] Avg episode reward: [(0, '-549.900'), (1, '-514.680')] -[2023-11-28 05:24:03,889][87426] Updated weights for policy 1, policy_version 197890 (0.0012) -[2023-11-28 05:24:04,261][87426] Updated weights for policy 1, policy_version 197900 (0.0012) -[2023-11-28 05:24:04,648][87426] Updated weights for policy 1, policy_version 197910 (0.0011) -[2023-11-28 05:24:05,015][87426] Updated weights for policy 1, policy_version 197920 (0.0011) -[2023-11-28 05:24:05,047][87424] Updated weights for policy 0, policy_version 198247 (0.0011) -[2023-11-28 05:24:05,419][87424] Updated weights for policy 0, policy_version 198257 (0.0009) -[2023-11-28 05:24:05,804][87424] Updated weights for policy 0, policy_version 198267 (0.0011) -[2023-11-28 05:24:07,499][87426] Updated weights for policy 1, policy_version 197930 (0.0011) -[2023-11-28 05:24:07,845][87424] Updated weights for policy 0, policy_version 198277 (0.0010) -[2023-11-28 05:24:07,876][87426] Updated weights for policy 1, policy_version 197940 (0.0009) -[2023-11-28 05:24:08,217][87424] Updated weights for policy 0, policy_version 198287 (0.0008) -[2023-11-28 05:24:08,245][87426] Updated weights for policy 1, policy_version 197950 (0.0008) -[2023-11-28 05:24:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101433344. Throughput: 0: 2716.9, 1: 2754.0. Samples: 101451620. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:08,445][86177] Avg episode reward: [(0, '-548.290'), (1, '-512.290')] -[2023-11-28 05:24:08,602][87424] Updated weights for policy 0, policy_version 198297 (0.0012) -[2023-11-28 05:24:10,232][87426] Updated weights for policy 1, policy_version 197960 (0.0011) -[2023-11-28 05:24:10,611][87426] Updated weights for policy 1, policy_version 197970 (0.0010) -[2023-11-28 05:24:10,717][87424] Updated weights for policy 0, policy_version 198307 (0.0012) -[2023-11-28 05:24:10,984][87426] Updated weights for policy 1, policy_version 197980 (0.0008) -[2023-11-28 05:24:11,101][87424] Updated weights for policy 0, policy_version 198317 (0.0011) -[2023-11-28 05:24:11,485][87424] Updated weights for policy 0, policy_version 198327 (0.0009) -[2023-11-28 05:24:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101457920. Throughput: 0: 2712.9, 1: 2736.3. Samples: 101475888. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:13,445][86177] Avg episode reward: [(0, '-516.570'), (1, '-512.360')] -[2023-11-28 05:24:13,540][87426] Updated weights for policy 1, policy_version 197990 (0.0011) -[2023-11-28 05:24:13,634][87424] Updated weights for policy 0, policy_version 198337 (0.0009) -[2023-11-28 05:24:13,925][87426] Updated weights for policy 1, policy_version 198000 (0.0011) -[2023-11-28 05:24:14,017][87424] Updated weights for policy 0, policy_version 198347 (0.0009) -[2023-11-28 05:24:14,302][87426] Updated weights for policy 1, policy_version 198010 (0.0009) -[2023-11-28 05:24:14,401][87424] Updated weights for policy 0, policy_version 198357 (0.0007) -[2023-11-28 05:24:14,787][87424] Updated weights for policy 0, policy_version 198367 (0.0007) -[2023-11-28 05:24:16,823][87424] Updated weights for policy 0, policy_version 198377 (0.0011) -[2023-11-28 05:24:16,891][87426] Updated weights for policy 1, policy_version 198020 (0.0009) -[2023-11-28 05:24:17,207][87424] Updated weights for policy 0, policy_version 198387 (0.0008) -[2023-11-28 05:24:17,269][87426] Updated weights for policy 1, policy_version 198030 (0.0008) -[2023-11-28 05:24:17,592][87424] Updated weights for policy 0, policy_version 198397 (0.0007) -[2023-11-28 05:24:17,647][87426] Updated weights for policy 1, policy_version 198040 (0.0007) -[2023-11-28 05:24:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101490688. Throughput: 0: 2718.1, 1: 2730.7. Samples: 101499868. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:18,445][86177] Avg episode reward: [(0, '-516.680'), (1, '-514.990')] -[2023-11-28 05:24:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000198400_50790400.pth... -[2023-11-28 05:24:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000198048_50700288.pth... -[2023-11-28 05:24:18,504][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000195456_50036736.pth -[2023-11-28 05:24:18,505][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000195872_50143232.pth -[2023-11-28 05:24:19,329][87426] Updated weights for policy 1, policy_version 198050 (0.0008) -[2023-11-28 05:24:19,620][87424] Updated weights for policy 0, policy_version 198407 (0.0010) -[2023-11-28 05:24:19,695][87426] Updated weights for policy 1, policy_version 198060 (0.0011) -[2023-11-28 05:24:20,003][87424] Updated weights for policy 0, policy_version 198417 (0.0011) -[2023-11-28 05:24:20,071][87426] Updated weights for policy 1, policy_version 198070 (0.0009) -[2023-11-28 05:24:20,386][87424] Updated weights for policy 0, policy_version 198427 (0.0012) -[2023-11-28 05:24:20,446][87426] Updated weights for policy 1, policy_version 198080 (0.0011) -[2023-11-28 05:24:22,355][87424] Updated weights for policy 0, policy_version 198437 (0.0010) -[2023-11-28 05:24:22,688][87426] Updated weights for policy 1, policy_version 198090 (0.0011) -[2023-11-28 05:24:22,733][87424] Updated weights for policy 0, policy_version 198447 (0.0011) -[2023-11-28 05:24:23,069][87426] Updated weights for policy 1, policy_version 198100 (0.0012) -[2023-11-28 05:24:23,119][87424] Updated weights for policy 0, policy_version 198457 (0.0010) -[2023-11-28 05:24:23,444][87426] Updated weights for policy 1, policy_version 198110 (0.0012) -[2023-11-28 05:24:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 101515264. Throughput: 0: 2735.7, 1: 2704.8. Samples: 101532564. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:23,446][86177] Avg episode reward: [(0, '-516.880'), (1, '-524.550')] -[2023-11-28 05:24:25,325][87424] Updated weights for policy 0, policy_version 198467 (0.0010) -[2023-11-28 05:24:25,331][87426] Updated weights for policy 1, policy_version 198120 (0.0009) -[2023-11-28 05:24:25,704][87424] Updated weights for policy 0, policy_version 198477 (0.0008) -[2023-11-28 05:24:25,711][87426] Updated weights for policy 1, policy_version 198130 (0.0009) -[2023-11-28 05:24:26,085][87424] Updated weights for policy 0, policy_version 198487 (0.0007) -[2023-11-28 05:24:26,086][87426] Updated weights for policy 1, policy_version 198140 (0.0008) -[2023-11-28 05:24:27,823][87426] Updated weights for policy 1, policy_version 198150 (0.0010) -[2023-11-28 05:24:28,133][87424] Updated weights for policy 0, policy_version 198497 (0.0008) -[2023-11-28 05:24:28,210][87426] Updated weights for policy 1, policy_version 198160 (0.0011) -[2023-11-28 05:24:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101539840. Throughput: 0: 2741.5, 1: 2723.6. Samples: 101557944. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:28,445][86177] Avg episode reward: [(0, '-508.970'), (1, '-527.800')] -[2023-11-28 05:24:28,521][87424] Updated weights for policy 0, policy_version 198507 (0.0010) -[2023-11-28 05:24:28,577][87426] Updated weights for policy 1, policy_version 198170 (0.0012) -[2023-11-28 05:24:28,891][87424] Updated weights for policy 0, policy_version 198517 (0.0008) -[2023-11-28 05:24:29,278][87424] Updated weights for policy 0, policy_version 198527 (0.0008) -[2023-11-28 05:24:30,915][87426] Updated weights for policy 1, policy_version 198180 (0.0009) -[2023-11-28 05:24:31,312][87426] Updated weights for policy 1, policy_version 198190 (0.0008) -[2023-11-28 05:24:31,684][87426] Updated weights for policy 1, policy_version 198200 (0.0008) -[2023-11-28 05:24:31,711][87424] Updated weights for policy 0, policy_version 198537 (0.0009) -[2023-11-28 05:24:32,092][87424] Updated weights for policy 0, policy_version 198547 (0.0011) -[2023-11-28 05:24:32,479][87424] Updated weights for policy 0, policy_version 198557 (0.0012) -[2023-11-28 05:24:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101572608. Throughput: 0: 2737.0, 1: 2713.8. Samples: 101581764. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:33,445][86177] Avg episode reward: [(0, '-509.400'), (1, '-522.650')] -[2023-11-28 05:24:33,807][87426] Updated weights for policy 1, policy_version 198210 (0.0011) -[2023-11-28 05:24:34,183][87426] Updated weights for policy 1, policy_version 198220 (0.0011) -[2023-11-28 05:24:34,369][87424] Updated weights for policy 0, policy_version 198567 (0.0009) -[2023-11-28 05:24:34,575][87426] Updated weights for policy 1, policy_version 198230 (0.0012) -[2023-11-28 05:24:34,752][87424] Updated weights for policy 0, policy_version 198577 (0.0009) -[2023-11-28 05:24:34,944][87426] Updated weights for policy 1, policy_version 198240 (0.0008) -[2023-11-28 05:24:35,129][87424] Updated weights for policy 0, policy_version 198587 (0.0011) -[2023-11-28 05:24:37,095][87424] Updated weights for policy 0, policy_version 198597 (0.0008) -[2023-11-28 05:24:37,154][87426] Updated weights for policy 1, policy_version 198250 (0.0011) -[2023-11-28 05:24:37,478][87424] Updated weights for policy 0, policy_version 198607 (0.0009) -[2023-11-28 05:24:37,537][87426] Updated weights for policy 1, policy_version 198260 (0.0010) -[2023-11-28 05:24:37,857][87424] Updated weights for policy 0, policy_version 198617 (0.0008) -[2023-11-28 05:24:37,923][87426] Updated weights for policy 1, policy_version 198270 (0.0009) -[2023-11-28 05:24:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 101605376. Throughput: 0: 2755.3, 1: 2730.9. Samples: 101615304. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:38,445][86177] Avg episode reward: [(0, '-503.770'), (1, '-518.220')] -[2023-11-28 05:24:39,892][87426] Updated weights for policy 1, policy_version 198280 (0.0012) -[2023-11-28 05:24:39,914][87424] Updated weights for policy 0, policy_version 198627 (0.0008) -[2023-11-28 05:24:40,269][87426] Updated weights for policy 1, policy_version 198290 (0.0010) -[2023-11-28 05:24:40,307][87424] Updated weights for policy 0, policy_version 198637 (0.0010) -[2023-11-28 05:24:40,651][87426] Updated weights for policy 1, policy_version 198300 (0.0010) -[2023-11-28 05:24:40,686][87424] Updated weights for policy 0, policy_version 198647 (0.0011) -[2023-11-28 05:24:42,882][87426] Updated weights for policy 1, policy_version 198310 (0.0009) -[2023-11-28 05:24:43,188][87424] Updated weights for policy 0, policy_version 198657 (0.0009) -[2023-11-28 05:24:43,271][87426] Updated weights for policy 1, policy_version 198320 (0.0007) -[2023-11-28 05:24:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101621760. Throughput: 0: 2756.3, 1: 2695.1. Samples: 101639604. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:43,445][86177] Avg episode reward: [(0, '-505.190'), (1, '-504.390')] -[2023-11-28 05:24:43,575][87424] Updated weights for policy 0, policy_version 198667 (0.0012) -[2023-11-28 05:24:43,654][87426] Updated weights for policy 1, policy_version 198330 (0.0011) -[2023-11-28 05:24:43,952][87424] Updated weights for policy 0, policy_version 198677 (0.0012) -[2023-11-28 05:24:44,328][87424] Updated weights for policy 0, policy_version 198687 (0.0012) -[2023-11-28 05:24:46,148][87424] Updated weights for policy 0, policy_version 198697 (0.0012) -[2023-11-28 05:24:46,179][87426] Updated weights for policy 1, policy_version 198340 (0.0011) -[2023-11-28 05:24:46,533][87424] Updated weights for policy 0, policy_version 198707 (0.0012) -[2023-11-28 05:24:46,560][87426] Updated weights for policy 1, policy_version 198350 (0.0010) -[2023-11-28 05:24:46,922][87424] Updated weights for policy 0, policy_version 198717 (0.0008) -[2023-11-28 05:24:46,940][87426] Updated weights for policy 1, policy_version 198360 (0.0007) -[2023-11-28 05:24:48,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101654528. Throughput: 0: 2769.7, 1: 2698.4. Samples: 101664368. Policy #0 lag: (min: 26.0, avg: 48.8, max: 61.0) -[2023-11-28 05:24:48,446][86177] Avg episode reward: [(0, '-508.150'), (1, '-510.800')] -[2023-11-28 05:24:49,070][87424] Updated weights for policy 0, policy_version 198727 (0.0011) -[2023-11-28 05:24:49,329][87426] Updated weights for policy 1, policy_version 198370 (0.0008) -[2023-11-28 05:24:49,449][87424] Updated weights for policy 0, policy_version 198737 (0.0012) -[2023-11-28 05:24:49,707][87426] Updated weights for policy 1, policy_version 198380 (0.0011) -[2023-11-28 05:24:49,829][87424] Updated weights for policy 0, policy_version 198747 (0.0010) -[2023-11-28 05:24:50,087][87426] Updated weights for policy 1, policy_version 198390 (0.0011) -[2023-11-28 05:24:50,465][87426] Updated weights for policy 1, policy_version 198400 (0.0012) -[2023-11-28 05:24:52,144][87424] Updated weights for policy 0, policy_version 198757 (0.0011) -[2023-11-28 05:24:52,527][87424] Updated weights for policy 0, policy_version 198767 (0.0009) -[2023-11-28 05:24:52,859][87426] Updated weights for policy 1, policy_version 198410 (0.0011) -[2023-11-28 05:24:52,912][87424] Updated weights for policy 0, policy_version 198777 (0.0009) -[2023-11-28 05:24:53,238][87426] Updated weights for policy 1, policy_version 198420 (0.0010) -[2023-11-28 05:24:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 101679104. Throughput: 0: 2748.8, 1: 2700.5. Samples: 101696840. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:24:53,445][86177] Avg episode reward: [(0, '-503.640'), (1, '-521.210')] -[2023-11-28 05:24:53,628][87426] Updated weights for policy 1, policy_version 198430 (0.0010) -[2023-11-28 05:24:55,210][87424] Updated weights for policy 0, policy_version 198787 (0.0008) -[2023-11-28 05:24:55,593][87424] Updated weights for policy 0, policy_version 198797 (0.0008) -[2023-11-28 05:24:55,608][87426] Updated weights for policy 1, policy_version 198440 (0.0009) -[2023-11-28 05:24:55,983][87424] Updated weights for policy 0, policy_version 198807 (0.0007) -[2023-11-28 05:24:55,991][87426] Updated weights for policy 1, policy_version 198450 (0.0012) -[2023-11-28 05:24:56,375][87426] Updated weights for policy 1, policy_version 198460 (0.0012) -[2023-11-28 05:24:58,082][87424] Updated weights for policy 0, policy_version 198817 (0.0008) -[2023-11-28 05:24:58,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101703680. Throughput: 0: 2750.5, 1: 2685.0. Samples: 101720484. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:24:58,445][86177] Avg episode reward: [(0, '-505.870'), (1, '-530.340')] -[2023-11-28 05:24:58,462][87424] Updated weights for policy 0, policy_version 198827 (0.0008) -[2023-11-28 05:24:58,845][87424] Updated weights for policy 0, policy_version 198837 (0.0008) -[2023-11-28 05:24:58,923][87426] Updated weights for policy 1, policy_version 198470 (0.0011) -[2023-11-28 05:24:59,235][87424] Updated weights for policy 0, policy_version 198847 (0.0010) -[2023-11-28 05:24:59,293][87426] Updated weights for policy 1, policy_version 198480 (0.0009) -[2023-11-28 05:24:59,669][87426] Updated weights for policy 1, policy_version 198490 (0.0011) -[2023-11-28 05:25:01,173][87424] Updated weights for policy 0, policy_version 198857 (0.0007) -[2023-11-28 05:25:01,555][87424] Updated weights for policy 0, policy_version 198867 (0.0008) -[2023-11-28 05:25:01,815][87426] Updated weights for policy 1, policy_version 198500 (0.0011) -[2023-11-28 05:25:01,937][87424] Updated weights for policy 0, policy_version 198877 (0.0010) -[2023-11-28 05:25:02,200][87426] Updated weights for policy 1, policy_version 198510 (0.0011) -[2023-11-28 05:25:02,573][87426] Updated weights for policy 1, policy_version 198520 (0.0012) -[2023-11-28 05:25:03,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 101736448. Throughput: 0: 2762.7, 1: 2698.6. Samples: 101745628. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:03,446][86177] Avg episode reward: [(0, '-505.150'), (1, '-525.440')] -[2023-11-28 05:25:04,045][87424] Updated weights for policy 0, policy_version 198887 (0.0011) -[2023-11-28 05:25:04,418][87424] Updated weights for policy 0, policy_version 198897 (0.0009) -[2023-11-28 05:25:04,797][87424] Updated weights for policy 0, policy_version 198907 (0.0008) -[2023-11-28 05:25:04,882][87426] Updated weights for policy 1, policy_version 198530 (0.0012) -[2023-11-28 05:25:05,259][87426] Updated weights for policy 1, policy_version 198540 (0.0011) -[2023-11-28 05:25:05,633][87426] Updated weights for policy 1, policy_version 198550 (0.0012) -[2023-11-28 05:25:06,026][87426] Updated weights for policy 1, policy_version 198560 (0.0012) -[2023-11-28 05:25:06,863][87424] Updated weights for policy 0, policy_version 198917 (0.0009) -[2023-11-28 05:25:07,242][87424] Updated weights for policy 0, policy_version 198927 (0.0008) -[2023-11-28 05:25:07,632][87424] Updated weights for policy 0, policy_version 198937 (0.0007) -[2023-11-28 05:25:08,225][87426] Updated weights for policy 1, policy_version 198570 (0.0008) -[2023-11-28 05:25:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 101761024. Throughput: 0: 2770.5, 1: 2692.4. Samples: 101778396. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:08,446][86177] Avg episode reward: [(0, '-501.650'), (1, '-527.530')] -[2023-11-28 05:25:08,606][87426] Updated weights for policy 1, policy_version 198580 (0.0007) -[2023-11-28 05:25:08,989][87426] Updated weights for policy 1, policy_version 198590 (0.0010) -[2023-11-28 05:25:09,667][87424] Updated weights for policy 0, policy_version 198947 (0.0008) -[2023-11-28 05:25:10,049][87424] Updated weights for policy 0, policy_version 198957 (0.0011) -[2023-11-28 05:25:10,433][87424] Updated weights for policy 0, policy_version 198967 (0.0011) -[2023-11-28 05:25:11,316][87426] Updated weights for policy 1, policy_version 198600 (0.0012) -[2023-11-28 05:25:11,699][87426] Updated weights for policy 1, policy_version 198610 (0.0010) -[2023-11-28 05:25:12,081][87426] Updated weights for policy 1, policy_version 198620 (0.0011) -[2023-11-28 05:25:12,752][87424] Updated weights for policy 0, policy_version 198977 (0.0012) -[2023-11-28 05:25:13,142][87424] Updated weights for policy 0, policy_version 198987 (0.0012) -[2023-11-28 05:25:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101785600. Throughput: 0: 2763.1, 1: 2663.2. Samples: 101802128. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:13,445][86177] Avg episode reward: [(0, '-506.380'), (1, '-520.460')] -[2023-11-28 05:25:13,519][87424] Updated weights for policy 0, policy_version 198997 (0.0012) -[2023-11-28 05:25:13,903][87424] Updated weights for policy 0, policy_version 199007 (0.0012) -[2023-11-28 05:25:14,192][87426] Updated weights for policy 1, policy_version 198630 (0.0011) -[2023-11-28 05:25:14,572][87426] Updated weights for policy 1, policy_version 198640 (0.0011) -[2023-11-28 05:25:14,939][87426] Updated weights for policy 1, policy_version 198650 (0.0011) -[2023-11-28 05:25:15,725][87424] Updated weights for policy 0, policy_version 199017 (0.0012) -[2023-11-28 05:25:16,110][87424] Updated weights for policy 0, policy_version 199027 (0.0012) -[2023-11-28 05:25:16,492][87424] Updated weights for policy 0, policy_version 199037 (0.0012) -[2023-11-28 05:25:17,357][87426] Updated weights for policy 1, policy_version 198660 (0.0011) -[2023-11-28 05:25:17,736][87426] Updated weights for policy 1, policy_version 198670 (0.0011) -[2023-11-28 05:25:18,124][87426] Updated weights for policy 1, policy_version 198680 (0.0011) -[2023-11-28 05:25:18,195][87424] Updated weights for policy 0, policy_version 199047 (0.0012) -[2023-11-28 05:25:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 101818368. Throughput: 0: 2767.8, 1: 2661.7. Samples: 101826092. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:18,445][86177] Avg episode reward: [(0, '-539.310'), (1, '-554.750')] -[2023-11-28 05:25:18,582][87424] Updated weights for policy 0, policy_version 199057 (0.0012) -[2023-11-28 05:25:18,960][87424] Updated weights for policy 0, policy_version 199067 (0.0011) -[2023-11-28 05:25:20,440][87426] Updated weights for policy 1, policy_version 198690 (0.0007) -[2023-11-28 05:25:20,813][87426] Updated weights for policy 1, policy_version 198700 (0.0011) -[2023-11-28 05:25:21,196][87426] Updated weights for policy 1, policy_version 198710 (0.0012) -[2023-11-28 05:25:21,318][87424] Updated weights for policy 0, policy_version 199077 (0.0010) -[2023-11-28 05:25:21,574][87426] Updated weights for policy 1, policy_version 198720 (0.0012) -[2023-11-28 05:25:21,707][87424] Updated weights for policy 0, policy_version 199087 (0.0011) -[2023-11-28 05:25:22,090][87424] Updated weights for policy 0, policy_version 199097 (0.0012) -[2023-11-28 05:25:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 101842944. Throughput: 0: 2753.2, 1: 2648.4. Samples: 101858372. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:23,445][86177] Avg episode reward: [(0, '-536.740'), (1, '-552.840')] -[2023-11-28 05:25:23,652][87426] Updated weights for policy 1, policy_version 198730 (0.0011) -[2023-11-28 05:25:24,028][87426] Updated weights for policy 1, policy_version 198740 (0.0011) -[2023-11-28 05:25:24,410][87426] Updated weights for policy 1, policy_version 198750 (0.0011) -[2023-11-28 05:25:24,716][87424] Updated weights for policy 0, policy_version 199107 (0.0011) -[2023-11-28 05:25:25,098][87424] Updated weights for policy 0, policy_version 199117 (0.0010) -[2023-11-28 05:25:25,486][87424] Updated weights for policy 0, policy_version 199127 (0.0007) -[2023-11-28 05:25:26,683][87426] Updated weights for policy 1, policy_version 198760 (0.0012) -[2023-11-28 05:25:27,058][87426] Updated weights for policy 1, policy_version 198770 (0.0012) -[2023-11-28 05:25:27,450][87426] Updated weights for policy 1, policy_version 198780 (0.0012) -[2023-11-28 05:25:28,016][87424] Updated weights for policy 0, policy_version 199137 (0.0008) -[2023-11-28 05:25:28,391][87424] Updated weights for policy 0, policy_version 199147 (0.0009) -[2023-11-28 05:25:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101867520. Throughput: 0: 2736.8, 1: 2666.4. Samples: 101882748. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:28,445][86177] Avg episode reward: [(0, '-546.480'), (1, '-550.480')] -[2023-11-28 05:25:28,772][87424] Updated weights for policy 0, policy_version 199157 (0.0007) -[2023-11-28 05:25:29,156][87424] Updated weights for policy 0, policy_version 199167 (0.0008) -[2023-11-28 05:25:29,822][87426] Updated weights for policy 1, policy_version 198790 (0.0011) -[2023-11-28 05:25:30,193][87426] Updated weights for policy 1, policy_version 198800 (0.0011) -[2023-11-28 05:25:30,574][87426] Updated weights for policy 1, policy_version 198810 (0.0008) -[2023-11-28 05:25:31,170][87424] Updated weights for policy 0, policy_version 199177 (0.0011) -[2023-11-28 05:25:31,549][87424] Updated weights for policy 0, policy_version 199187 (0.0011) -[2023-11-28 05:25:31,929][87424] Updated weights for policy 0, policy_version 199197 (0.0016) -[2023-11-28 05:25:32,853][87426] Updated weights for policy 1, policy_version 198820 (0.0009) -[2023-11-28 05:25:33,231][87426] Updated weights for policy 1, policy_version 198830 (0.0010) -[2023-11-28 05:25:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 101892096. Throughput: 0: 2724.9, 1: 2654.8. Samples: 101906452. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:33,446][86177] Avg episode reward: [(0, '-543.880'), (1, '-546.660')] -[2023-11-28 05:25:33,612][87426] Updated weights for policy 1, policy_version 198840 (0.0010) -[2023-11-28 05:25:34,252][87424] Updated weights for policy 0, policy_version 199207 (0.0009) -[2023-11-28 05:25:34,648][87424] Updated weights for policy 0, policy_version 199217 (0.0009) -[2023-11-28 05:25:35,031][87424] Updated weights for policy 0, policy_version 199227 (0.0008) -[2023-11-28 05:25:35,928][87426] Updated weights for policy 1, policy_version 198850 (0.0008) -[2023-11-28 05:25:36,303][87426] Updated weights for policy 1, policy_version 198860 (0.0012) -[2023-11-28 05:25:36,679][87426] Updated weights for policy 1, policy_version 198870 (0.0012) -[2023-11-28 05:25:37,054][87426] Updated weights for policy 1, policy_version 198880 (0.0012) -[2023-11-28 05:25:37,231][87424] Updated weights for policy 0, policy_version 199237 (0.0010) -[2023-11-28 05:25:37,605][87424] Updated weights for policy 0, policy_version 199247 (0.0012) -[2023-11-28 05:25:37,993][87424] Updated weights for policy 0, policy_version 199257 (0.0012) -[2023-11-28 05:25:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 101924864. Throughput: 0: 2722.0, 1: 2658.5. Samples: 101938964. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:38,445][86177] Avg episode reward: [(0, '-506.980'), (1, '-507.840')] -[2023-11-28 05:25:39,047][87426] Updated weights for policy 1, policy_version 198890 (0.0009) -[2023-11-28 05:25:39,422][87426] Updated weights for policy 1, policy_version 198900 (0.0011) -[2023-11-28 05:25:39,797][87426] Updated weights for policy 1, policy_version 198910 (0.0010) -[2023-11-28 05:25:40,551][87424] Updated weights for policy 0, policy_version 199267 (0.0012) -[2023-11-28 05:25:40,930][87424] Updated weights for policy 0, policy_version 199277 (0.0012) -[2023-11-28 05:25:41,312][87424] Updated weights for policy 0, policy_version 199287 (0.0012) -[2023-11-28 05:25:41,959][87426] Updated weights for policy 1, policy_version 198920 (0.0012) -[2023-11-28 05:25:42,343][87426] Updated weights for policy 1, policy_version 198930 (0.0010) -[2023-11-28 05:25:42,723][87426] Updated weights for policy 1, policy_version 198940 (0.0008) -[2023-11-28 05:25:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 101949440. Throughput: 0: 2703.7, 1: 2681.7. Samples: 101962828. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:43,445][86177] Avg episode reward: [(0, '-515.350'), (1, '-507.520')] -[2023-11-28 05:25:43,905][87424] Updated weights for policy 0, policy_version 199297 (0.0012) -[2023-11-28 05:25:44,287][87424] Updated weights for policy 0, policy_version 199307 (0.0010) -[2023-11-28 05:25:44,668][87424] Updated weights for policy 0, policy_version 199317 (0.0012) -[2023-11-28 05:25:44,992][87426] Updated weights for policy 1, policy_version 198950 (0.0010) -[2023-11-28 05:25:45,049][87424] Updated weights for policy 0, policy_version 199327 (0.0012) -[2023-11-28 05:25:45,369][87426] Updated weights for policy 1, policy_version 198960 (0.0012) -[2023-11-28 05:25:45,754][87426] Updated weights for policy 1, policy_version 198970 (0.0012) -[2023-11-28 05:25:47,056][87424] Updated weights for policy 0, policy_version 199337 (0.0011) -[2023-11-28 05:25:47,435][87424] Updated weights for policy 0, policy_version 199347 (0.0007) -[2023-11-28 05:25:47,818][87424] Updated weights for policy 0, policy_version 199357 (0.0008) -[2023-11-28 05:25:47,851][87426] Updated weights for policy 1, policy_version 198980 (0.0010) -[2023-11-28 05:25:48,235][87426] Updated weights for policy 1, policy_version 198990 (0.0008) -[2023-11-28 05:25:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 101974016. Throughput: 0: 2699.3, 1: 2683.3. Samples: 101987844. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:48,445][86177] Avg episode reward: [(0, '-505.760'), (1, '-507.450')] -[2023-11-28 05:25:48,615][87426] Updated weights for policy 1, policy_version 199000 (0.0007) -[2023-11-28 05:25:49,909][87424] Updated weights for policy 0, policy_version 199367 (0.0011) -[2023-11-28 05:25:50,293][87424] Updated weights for policy 0, policy_version 199377 (0.0011) -[2023-11-28 05:25:50,669][87424] Updated weights for policy 0, policy_version 199387 (0.0008) -[2023-11-28 05:25:50,818][87426] Updated weights for policy 1, policy_version 199010 (0.0008) -[2023-11-28 05:25:51,190][87426] Updated weights for policy 1, policy_version 199020 (0.0011) -[2023-11-28 05:25:51,568][87426] Updated weights for policy 1, policy_version 199030 (0.0011) -[2023-11-28 05:25:51,947][87426] Updated weights for policy 1, policy_version 199040 (0.0011) -[2023-11-28 05:25:53,176][87424] Updated weights for policy 0, policy_version 199397 (0.0010) -[2023-11-28 05:25:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 101998592. Throughput: 0: 2676.5, 1: 2680.3. Samples: 102019452. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:53,445][86177] Avg episode reward: [(0, '-504.480'), (1, '-514.460')] -[2023-11-28 05:25:53,550][87424] Updated weights for policy 0, policy_version 199407 (0.0011) -[2023-11-28 05:25:53,938][87424] Updated weights for policy 0, policy_version 199417 (0.0011) -[2023-11-28 05:25:54,339][87426] Updated weights for policy 1, policy_version 199050 (0.0009) -[2023-11-28 05:25:54,716][87426] Updated weights for policy 1, policy_version 199060 (0.0010) -[2023-11-28 05:25:55,097][87426] Updated weights for policy 1, policy_version 199070 (0.0010) -[2023-11-28 05:25:55,902][87424] Updated weights for policy 0, policy_version 199427 (0.0012) -[2023-11-28 05:25:56,291][87424] Updated weights for policy 0, policy_version 199437 (0.0011) -[2023-11-28 05:25:56,671][87424] Updated weights for policy 0, policy_version 199447 (0.0007) -[2023-11-28 05:25:57,127][87426] Updated weights for policy 1, policy_version 199080 (0.0011) -[2023-11-28 05:25:57,504][87426] Updated weights for policy 1, policy_version 199090 (0.0011) -[2023-11-28 05:25:57,887][87426] Updated weights for policy 1, policy_version 199100 (0.0012) -[2023-11-28 05:25:58,409][87424] Updated weights for policy 0, policy_version 199457 (0.0008) -[2023-11-28 05:25:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 102031360. Throughput: 0: 2692.3, 1: 2703.3. Samples: 102044928. Policy #0 lag: (min: 31.0, avg: 53.0, max: 95.0) -[2023-11-28 05:25:58,445][86177] Avg episode reward: [(0, '-499.880'), (1, '-511.810')] -[2023-11-28 05:25:58,793][87424] Updated weights for policy 0, policy_version 199467 (0.0012) -[2023-11-28 05:25:59,175][87424] Updated weights for policy 0, policy_version 199477 (0.0012) -[2023-11-28 05:25:59,564][87424] Updated weights for policy 0, policy_version 199487 (0.0012) -[2023-11-28 05:26:00,114][87426] Updated weights for policy 1, policy_version 199110 (0.0011) -[2023-11-28 05:26:00,503][87426] Updated weights for policy 1, policy_version 199120 (0.0012) -[2023-11-28 05:26:00,885][87426] Updated weights for policy 1, policy_version 199130 (0.0012) -[2023-11-28 05:26:02,038][87424] Updated weights for policy 0, policy_version 199497 (0.0008) -[2023-11-28 05:26:02,420][87424] Updated weights for policy 0, policy_version 199507 (0.0009) -[2023-11-28 05:26:02,798][87424] Updated weights for policy 0, policy_version 199517 (0.0008) -[2023-11-28 05:26:03,292][87426] Updated weights for policy 1, policy_version 199140 (0.0010) -[2023-11-28 05:26:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 102055936. Throughput: 0: 2690.8, 1: 2703.8. Samples: 102068848. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:03,445][86177] Avg episode reward: [(0, '-503.510'), (1, '-513.800')] -[2023-11-28 05:26:03,665][87426] Updated weights for policy 1, policy_version 199150 (0.0012) -[2023-11-28 05:26:04,039][87426] Updated weights for policy 1, policy_version 199160 (0.0012) -[2023-11-28 05:26:04,942][87424] Updated weights for policy 0, policy_version 199527 (0.0011) -[2023-11-28 05:26:05,319][87424] Updated weights for policy 0, policy_version 199537 (0.0012) -[2023-11-28 05:26:05,696][87424] Updated weights for policy 0, policy_version 199547 (0.0012) -[2023-11-28 05:26:06,396][87426] Updated weights for policy 1, policy_version 199170 (0.0008) -[2023-11-28 05:26:06,784][87426] Updated weights for policy 1, policy_version 199180 (0.0009) -[2023-11-28 05:26:07,162][87426] Updated weights for policy 1, policy_version 199190 (0.0012) -[2023-11-28 05:26:07,540][87426] Updated weights for policy 1, policy_version 199200 (0.0012) -[2023-11-28 05:26:07,911][87424] Updated weights for policy 0, policy_version 199557 (0.0012) -[2023-11-28 05:26:08,298][87424] Updated weights for policy 0, policy_version 199567 (0.0011) -[2023-11-28 05:26:08,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 102080512. Throughput: 0: 2676.9, 1: 2712.5. Samples: 102100896. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:08,446][86177] Avg episode reward: [(0, '-502.490'), (1, '-507.260')] -[2023-11-28 05:26:08,677][87424] Updated weights for policy 0, policy_version 199577 (0.0012) -[2023-11-28 05:26:09,636][87426] Updated weights for policy 1, policy_version 199210 (0.0012) -[2023-11-28 05:26:10,009][87426] Updated weights for policy 1, policy_version 199220 (0.0011) -[2023-11-28 05:26:10,408][87426] Updated weights for policy 1, policy_version 199230 (0.0011) -[2023-11-28 05:26:10,930][87424] Updated weights for policy 0, policy_version 199587 (0.0011) -[2023-11-28 05:26:11,314][87424] Updated weights for policy 0, policy_version 199597 (0.0008) -[2023-11-28 05:26:11,707][87424] Updated weights for policy 0, policy_version 199607 (0.0009) -[2023-11-28 05:26:12,313][87426] Updated weights for policy 1, policy_version 199240 (0.0012) -[2023-11-28 05:26:12,694][87426] Updated weights for policy 1, policy_version 199250 (0.0009) -[2023-11-28 05:26:13,072][87426] Updated weights for policy 1, policy_version 199260 (0.0011) -[2023-11-28 05:26:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102113280. Throughput: 0: 2697.5, 1: 2708.9. Samples: 102126036. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:13,445][86177] Avg episode reward: [(0, '-508.240'), (1, '-509.950')] -[2023-11-28 05:26:14,143][87424] Updated weights for policy 0, policy_version 199617 (0.0011) -[2023-11-28 05:26:14,523][87424] Updated weights for policy 0, policy_version 199627 (0.0007) -[2023-11-28 05:26:14,915][87424] Updated weights for policy 0, policy_version 199637 (0.0010) -[2023-11-28 05:26:15,299][87424] Updated weights for policy 0, policy_version 199647 (0.0011) -[2023-11-28 05:26:15,478][87426] Updated weights for policy 1, policy_version 199270 (0.0010) -[2023-11-28 05:26:15,853][87426] Updated weights for policy 1, policy_version 199280 (0.0009) -[2023-11-28 05:26:16,231][87426] Updated weights for policy 1, policy_version 199290 (0.0008) -[2023-11-28 05:26:17,275][87424] Updated weights for policy 0, policy_version 199657 (0.0009) -[2023-11-28 05:26:17,655][87424] Updated weights for policy 0, policy_version 199667 (0.0008) -[2023-11-28 05:26:17,962][87426] Updated weights for policy 1, policy_version 199300 (0.0011) -[2023-11-28 05:26:18,035][87424] Updated weights for policy 0, policy_version 199677 (0.0008) -[2023-11-28 05:26:18,336][87426] Updated weights for policy 1, policy_version 199310 (0.0008) -[2023-11-28 05:26:18,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 102137856. Throughput: 0: 2708.3, 1: 2716.1. Samples: 102150548. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:18,446][86177] Avg episode reward: [(0, '-505.770'), (1, '-508.950')] -[2023-11-28 05:26:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000199680_51118080.pth... -[2023-11-28 05:26:18,491][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000197152_50470912.pth -[2023-11-28 05:26:18,720][87426] Updated weights for policy 1, policy_version 199320 (0.0007) -[2023-11-28 05:26:19,021][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000199328_51027968.pth... -[2023-11-28 05:26:19,052][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000196768_50372608.pth -[2023-11-28 05:26:20,440][87424] Updated weights for policy 0, policy_version 199687 (0.0009) -[2023-11-28 05:26:20,825][87424] Updated weights for policy 0, policy_version 199697 (0.0008) -[2023-11-28 05:26:21,207][87424] Updated weights for policy 0, policy_version 199707 (0.0008) -[2023-11-28 05:26:21,209][87426] Updated weights for policy 1, policy_version 199330 (0.0008) -[2023-11-28 05:26:21,588][87426] Updated weights for policy 1, policy_version 199340 (0.0009) -[2023-11-28 05:26:21,971][87426] Updated weights for policy 1, policy_version 199350 (0.0011) -[2023-11-28 05:26:22,351][87426] Updated weights for policy 1, policy_version 199360 (0.0011) -[2023-11-28 05:26:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 102162432. Throughput: 0: 2677.7, 1: 2719.4. Samples: 102181832. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:23,446][86177] Avg episode reward: [(0, '-501.460'), (1, '-510.290')] -[2023-11-28 05:26:23,713][87424] Updated weights for policy 0, policy_version 199717 (0.0012) -[2023-11-28 05:26:24,108][87424] Updated weights for policy 0, policy_version 199727 (0.0012) -[2023-11-28 05:26:24,482][87424] Updated weights for policy 0, policy_version 199737 (0.0008) -[2023-11-28 05:26:24,495][87426] Updated weights for policy 1, policy_version 199370 (0.0011) -[2023-11-28 05:26:24,867][87426] Updated weights for policy 1, policy_version 199380 (0.0012) -[2023-11-28 05:26:25,246][87426] Updated weights for policy 1, policy_version 199390 (0.0011) -[2023-11-28 05:26:27,008][87424] Updated weights for policy 0, policy_version 199747 (0.0009) -[2023-11-28 05:26:27,097][87426] Updated weights for policy 1, policy_version 199400 (0.0008) -[2023-11-28 05:26:27,399][87424] Updated weights for policy 0, policy_version 199757 (0.0008) -[2023-11-28 05:26:27,478][87426] Updated weights for policy 1, policy_version 199410 (0.0007) -[2023-11-28 05:26:27,797][87424] Updated weights for policy 0, policy_version 199767 (0.0008) -[2023-11-28 05:26:27,858][87426] Updated weights for policy 1, policy_version 199420 (0.0007) -[2023-11-28 05:26:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 102195200. Throughput: 0: 2686.0, 1: 2724.6. Samples: 102206308. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:28,445][86177] Avg episode reward: [(0, '-507.690'), (1, '-502.630')] -[2023-11-28 05:26:29,491][87424] Updated weights for policy 0, policy_version 199777 (0.0010) -[2023-11-28 05:26:29,888][87424] Updated weights for policy 0, policy_version 199787 (0.0008) -[2023-11-28 05:26:30,139][87426] Updated weights for policy 1, policy_version 199430 (0.0008) -[2023-11-28 05:26:30,264][87424] Updated weights for policy 0, policy_version 199797 (0.0008) -[2023-11-28 05:26:30,514][87426] Updated weights for policy 1, policy_version 199440 (0.0010) -[2023-11-28 05:26:30,644][87424] Updated weights for policy 0, policy_version 199807 (0.0012) -[2023-11-28 05:26:30,897][87426] Updated weights for policy 1, policy_version 199450 (0.0011) -[2023-11-28 05:26:32,816][87424] Updated weights for policy 0, policy_version 199817 (0.0011) -[2023-11-28 05:26:33,194][87424] Updated weights for policy 0, policy_version 199827 (0.0012) -[2023-11-28 05:26:33,199][87426] Updated weights for policy 1, policy_version 199460 (0.0012) -[2023-11-28 05:26:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 102211584. Throughput: 0: 2684.1, 1: 2713.6. Samples: 102230740. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:33,445][86177] Avg episode reward: [(0, '-505.720'), (1, '-542.360')] -[2023-11-28 05:26:33,570][87426] Updated weights for policy 1, policy_version 199470 (0.0010) -[2023-11-28 05:26:33,579][87424] Updated weights for policy 0, policy_version 199837 (0.0011) -[2023-11-28 05:26:33,952][87426] Updated weights for policy 1, policy_version 199480 (0.0007) -[2023-11-28 05:26:35,625][87424] Updated weights for policy 0, policy_version 199847 (0.0011) -[2023-11-28 05:26:35,668][87426] Updated weights for policy 1, policy_version 199490 (0.0008) -[2023-11-28 05:26:36,002][87424] Updated weights for policy 0, policy_version 199857 (0.0008) -[2023-11-28 05:26:36,043][87426] Updated weights for policy 1, policy_version 199500 (0.0011) -[2023-11-28 05:26:36,385][87424] Updated weights for policy 0, policy_version 199867 (0.0009) -[2023-11-28 05:26:36,428][87426] Updated weights for policy 1, policy_version 199510 (0.0011) -[2023-11-28 05:26:36,799][87426] Updated weights for policy 1, policy_version 199520 (0.0011) -[2023-11-28 05:26:38,095][87424] Updated weights for policy 0, policy_version 199877 (0.0011) -[2023-11-28 05:26:38,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 102244352. Throughput: 0: 2699.9, 1: 2739.3. Samples: 102264216. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:38,446][86177] Avg episode reward: [(0, '-506.580'), (1, '-545.400')] -[2023-11-28 05:26:38,474][87424] Updated weights for policy 0, policy_version 199887 (0.0012) -[2023-11-28 05:26:38,859][87424] Updated weights for policy 0, policy_version 199897 (0.0010) -[2023-11-28 05:26:38,873][87426] Updated weights for policy 1, policy_version 199530 (0.0008) -[2023-11-28 05:26:39,247][87426] Updated weights for policy 1, policy_version 199540 (0.0008) -[2023-11-28 05:26:39,626][87426] Updated weights for policy 1, policy_version 199550 (0.0010) -[2023-11-28 05:26:41,055][87424] Updated weights for policy 0, policy_version 199907 (0.0008) -[2023-11-28 05:26:41,441][87424] Updated weights for policy 0, policy_version 199917 (0.0008) -[2023-11-28 05:26:41,826][87424] Updated weights for policy 0, policy_version 199927 (0.0009) -[2023-11-28 05:26:42,023][87426] Updated weights for policy 1, policy_version 199560 (0.0009) -[2023-11-28 05:26:42,407][87426] Updated weights for policy 1, policy_version 199570 (0.0011) -[2023-11-28 05:26:42,788][87426] Updated weights for policy 1, policy_version 199580 (0.0012) -[2023-11-28 05:26:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102277120. Throughput: 0: 2672.3, 1: 2716.6. Samples: 102287428. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:43,445][86177] Avg episode reward: [(0, '-504.160'), (1, '-544.690')] -[2023-11-28 05:26:44,134][87424] Updated weights for policy 0, policy_version 199937 (0.0012) -[2023-11-28 05:26:44,517][87424] Updated weights for policy 0, policy_version 199947 (0.0008) -[2023-11-28 05:26:44,897][87424] Updated weights for policy 0, policy_version 199957 (0.0010) -[2023-11-28 05:26:45,035][87426] Updated weights for policy 1, policy_version 199590 (0.0009) -[2023-11-28 05:26:45,275][87424] Updated weights for policy 0, policy_version 199967 (0.0008) -[2023-11-28 05:26:45,411][87426] Updated weights for policy 1, policy_version 199600 (0.0009) -[2023-11-28 05:26:45,785][87426] Updated weights for policy 1, policy_version 199610 (0.0011) -[2023-11-28 05:26:47,442][87424] Updated weights for policy 0, policy_version 199977 (0.0012) -[2023-11-28 05:26:47,828][87424] Updated weights for policy 0, policy_version 199987 (0.0012) -[2023-11-28 05:26:48,100][87426] Updated weights for policy 1, policy_version 199620 (0.0011) -[2023-11-28 05:26:48,215][87424] Updated weights for policy 0, policy_version 199997 (0.0010) -[2023-11-28 05:26:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102301696. Throughput: 0: 2696.8, 1: 2730.1. Samples: 102313060. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:48,445][86177] Avg episode reward: [(0, '-506.160'), (1, '-503.720')] -[2023-11-28 05:26:48,478][87426] Updated weights for policy 1, policy_version 199630 (0.0012) -[2023-11-28 05:26:48,858][87426] Updated weights for policy 1, policy_version 199640 (0.0011) -[2023-11-28 05:26:50,411][87424] Updated weights for policy 0, policy_version 200007 (0.0011) -[2023-11-28 05:26:50,793][87424] Updated weights for policy 0, policy_version 200017 (0.0009) -[2023-11-28 05:26:51,180][87424] Updated weights for policy 0, policy_version 200027 (0.0011) -[2023-11-28 05:26:51,187][87426] Updated weights for policy 1, policy_version 199650 (0.0010) -[2023-11-28 05:26:51,560][87426] Updated weights for policy 1, policy_version 199660 (0.0011) -[2023-11-28 05:26:51,938][87426] Updated weights for policy 1, policy_version 199670 (0.0009) -[2023-11-28 05:26:52,317][87426] Updated weights for policy 1, policy_version 199680 (0.0008) -[2023-11-28 05:26:53,186][87424] Updated weights for policy 0, policy_version 200037 (0.0010) -[2023-11-28 05:26:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 102326272. Throughput: 0: 2717.2, 1: 2743.3. Samples: 102346616. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:53,445][86177] Avg episode reward: [(0, '-514.860'), (1, '-503.780')] -[2023-11-28 05:26:53,576][87424] Updated weights for policy 0, policy_version 200047 (0.0009) -[2023-11-28 05:26:53,954][87424] Updated weights for policy 0, policy_version 200057 (0.0011) -[2023-11-28 05:26:54,432][87426] Updated weights for policy 1, policy_version 199690 (0.0010) -[2023-11-28 05:26:54,819][87426] Updated weights for policy 1, policy_version 199700 (0.0012) -[2023-11-28 05:26:55,191][87426] Updated weights for policy 1, policy_version 199710 (0.0011) -[2023-11-28 05:26:55,905][87424] Updated weights for policy 0, policy_version 200067 (0.0012) -[2023-11-28 05:26:56,282][87424] Updated weights for policy 0, policy_version 200077 (0.0008) -[2023-11-28 05:26:56,658][87424] Updated weights for policy 0, policy_version 200087 (0.0008) -[2023-11-28 05:26:56,798][87426] Updated weights for policy 1, policy_version 199720 (0.0012) -[2023-11-28 05:26:57,173][87426] Updated weights for policy 1, policy_version 199730 (0.0012) -[2023-11-28 05:26:57,553][87426] Updated weights for policy 1, policy_version 199740 (0.0010) -[2023-11-28 05:26:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102359040. Throughput: 0: 2729.5, 1: 2747.6. Samples: 102372508. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:26:58,446][86177] Avg episode reward: [(0, '-518.530'), (1, '-508.630')] -[2023-11-28 05:26:58,520][87424] Updated weights for policy 0, policy_version 200097 (0.0008) -[2023-11-28 05:26:58,902][87424] Updated weights for policy 0, policy_version 200107 (0.0012) -[2023-11-28 05:26:59,286][87424] Updated weights for policy 0, policy_version 200117 (0.0012) -[2023-11-28 05:26:59,407][87426] Updated weights for policy 1, policy_version 199750 (0.0012) -[2023-11-28 05:26:59,662][87424] Updated weights for policy 0, policy_version 200127 (0.0011) -[2023-11-28 05:26:59,786][87426] Updated weights for policy 1, policy_version 199760 (0.0010) -[2023-11-28 05:27:00,168][87426] Updated weights for policy 1, policy_version 199770 (0.0009) -[2023-11-28 05:27:01,891][87424] Updated weights for policy 0, policy_version 200137 (0.0010) -[2023-11-28 05:27:02,126][87426] Updated weights for policy 1, policy_version 199780 (0.0010) -[2023-11-28 05:27:02,277][87424] Updated weights for policy 0, policy_version 200147 (0.0011) -[2023-11-28 05:27:02,505][87426] Updated weights for policy 1, policy_version 199790 (0.0009) -[2023-11-28 05:27:02,647][87424] Updated weights for policy 0, policy_version 200157 (0.0011) -[2023-11-28 05:27:02,879][87426] Updated weights for policy 1, policy_version 199800 (0.0009) -[2023-11-28 05:27:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 102391808. Throughput: 0: 2737.7, 1: 2758.7. Samples: 102397884. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:27:03,445][86177] Avg episode reward: [(0, '-517.850'), (1, '-508.630')] -[2023-11-28 05:27:04,813][87426] Updated weights for policy 1, policy_version 199810 (0.0010) -[2023-11-28 05:27:04,877][87424] Updated weights for policy 0, policy_version 200167 (0.0012) -[2023-11-28 05:27:05,204][87426] Updated weights for policy 1, policy_version 199820 (0.0010) -[2023-11-28 05:27:05,275][87424] Updated weights for policy 0, policy_version 200177 (0.0012) -[2023-11-28 05:27:05,578][87426] Updated weights for policy 1, policy_version 199830 (0.0007) -[2023-11-28 05:27:05,660][87424] Updated weights for policy 0, policy_version 200187 (0.0012) -[2023-11-28 05:27:05,958][87426] Updated weights for policy 1, policy_version 199840 (0.0007) -[2023-11-28 05:27:07,495][87424] Updated weights for policy 0, policy_version 200197 (0.0010) -[2023-11-28 05:27:07,885][87424] Updated weights for policy 0, policy_version 200207 (0.0007) -[2023-11-28 05:27:08,266][87424] Updated weights for policy 0, policy_version 200217 (0.0010) -[2023-11-28 05:27:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 102408192. Throughput: 0: 2783.8, 1: 2779.5. Samples: 102432180. Policy #0 lag: (min: 31.0, avg: 50.3, max: 80.0) -[2023-11-28 05:27:08,445][86177] Avg episode reward: [(0, '-512.630'), (1, '-510.980')] -[2023-11-28 05:27:08,452][87426] Updated weights for policy 1, policy_version 199850 (0.0010) -[2023-11-28 05:27:08,830][87426] Updated weights for policy 1, policy_version 199860 (0.0010) -[2023-11-28 05:27:09,210][87426] Updated weights for policy 1, policy_version 199870 (0.0011) -[2023-11-28 05:27:10,569][87424] Updated weights for policy 0, policy_version 200227 (0.0011) -[2023-11-28 05:27:10,953][87424] Updated weights for policy 0, policy_version 200237 (0.0012) -[2023-11-28 05:27:11,336][87424] Updated weights for policy 0, policy_version 200247 (0.0010) -[2023-11-28 05:27:11,515][87426] Updated weights for policy 1, policy_version 199880 (0.0011) -[2023-11-28 05:27:11,897][87426] Updated weights for policy 1, policy_version 199890 (0.0012) -[2023-11-28 05:27:12,267][87426] Updated weights for policy 1, policy_version 199900 (0.0012) -[2023-11-28 05:27:13,422][87424] Updated weights for policy 0, policy_version 200257 (0.0009) -[2023-11-28 05:27:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102440960. Throughput: 0: 2794.3, 1: 2756.3. Samples: 102456084. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:13,445][86177] Avg episode reward: [(0, '-502.430'), (1, '-522.320')] -[2023-11-28 05:27:13,808][87424] Updated weights for policy 0, policy_version 200267 (0.0008) -[2023-11-28 05:27:14,178][87424] Updated weights for policy 0, policy_version 200277 (0.0007) -[2023-11-28 05:27:14,562][87424] Updated weights for policy 0, policy_version 200287 (0.0008) -[2023-11-28 05:27:14,792][87426] Updated weights for policy 1, policy_version 199910 (0.0012) -[2023-11-28 05:27:15,169][87426] Updated weights for policy 1, policy_version 199920 (0.0011) -[2023-11-28 05:27:15,542][87426] Updated weights for policy 1, policy_version 199930 (0.0012) -[2023-11-28 05:27:16,288][87424] Updated weights for policy 0, policy_version 200297 (0.0012) -[2023-11-28 05:27:16,662][87424] Updated weights for policy 0, policy_version 200307 (0.0012) -[2023-11-28 05:27:17,047][87424] Updated weights for policy 0, policy_version 200317 (0.0012) -[2023-11-28 05:27:17,510][87426] Updated weights for policy 1, policy_version 199940 (0.0012) -[2023-11-28 05:27:17,883][87426] Updated weights for policy 1, policy_version 199950 (0.0012) -[2023-11-28 05:27:18,262][87426] Updated weights for policy 1, policy_version 199960 (0.0011) -[2023-11-28 05:27:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 102465536. Throughput: 0: 2782.8, 1: 2767.9. Samples: 102480524. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:18,445][86177] Avg episode reward: [(0, '-502.180'), (1, '-528.350')] -[2023-11-28 05:27:19,526][87424] Updated weights for policy 0, policy_version 200327 (0.0009) -[2023-11-28 05:27:19,888][87426] Updated weights for policy 1, policy_version 199970 (0.0009) -[2023-11-28 05:27:19,920][87424] Updated weights for policy 0, policy_version 200337 (0.0008) -[2023-11-28 05:27:20,268][87426] Updated weights for policy 1, policy_version 199980 (0.0011) -[2023-11-28 05:27:20,287][87424] Updated weights for policy 0, policy_version 200347 (0.0008) -[2023-11-28 05:27:20,641][87426] Updated weights for policy 1, policy_version 199990 (0.0010) -[2023-11-28 05:27:21,015][87426] Updated weights for policy 1, policy_version 200000 (0.0007) -[2023-11-28 05:27:22,736][87424] Updated weights for policy 0, policy_version 200357 (0.0012) -[2023-11-28 05:27:23,127][87424] Updated weights for policy 0, policy_version 200367 (0.0012) -[2023-11-28 05:27:23,414][87426] Updated weights for policy 1, policy_version 200010 (0.0012) -[2023-11-28 05:27:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 102490112. Throughput: 0: 2789.4, 1: 2765.8. Samples: 102514200. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:23,445][86177] Avg episode reward: [(0, '-509.570'), (1, '-532.900')] -[2023-11-28 05:27:23,510][87424] Updated weights for policy 0, policy_version 200377 (0.0011) -[2023-11-28 05:27:23,788][87426] Updated weights for policy 1, policy_version 200020 (0.0009) -[2023-11-28 05:27:24,166][87426] Updated weights for policy 1, policy_version 200030 (0.0007) -[2023-11-28 05:27:25,562][87424] Updated weights for policy 0, policy_version 200387 (0.0010) -[2023-11-28 05:27:25,950][87424] Updated weights for policy 0, policy_version 200397 (0.0007) -[2023-11-28 05:27:26,342][87424] Updated weights for policy 0, policy_version 200407 (0.0009) -[2023-11-28 05:27:26,843][87426] Updated weights for policy 1, policy_version 200040 (0.0011) -[2023-11-28 05:27:27,211][87426] Updated weights for policy 1, policy_version 200050 (0.0010) -[2023-11-28 05:27:27,593][87426] Updated weights for policy 1, policy_version 200060 (0.0012) -[2023-11-28 05:27:28,184][87424] Updated weights for policy 0, policy_version 200417 (0.0010) -[2023-11-28 05:27:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102522880. Throughput: 0: 2800.5, 1: 2762.5. Samples: 102537764. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:28,445][86177] Avg episode reward: [(0, '-514.520'), (1, '-535.760')] -[2023-11-28 05:27:28,562][87424] Updated weights for policy 0, policy_version 200427 (0.0012) -[2023-11-28 05:27:28,949][87424] Updated weights for policy 0, policy_version 200437 (0.0012) -[2023-11-28 05:27:29,320][87424] Updated weights for policy 0, policy_version 200447 (0.0012) -[2023-11-28 05:27:29,390][87426] Updated weights for policy 1, policy_version 200070 (0.0012) -[2023-11-28 05:27:29,756][87426] Updated weights for policy 1, policy_version 200080 (0.0012) -[2023-11-28 05:27:30,131][87426] Updated weights for policy 1, policy_version 200090 (0.0012) -[2023-11-28 05:27:31,635][87424] Updated weights for policy 0, policy_version 200457 (0.0010) -[2023-11-28 05:27:32,019][87424] Updated weights for policy 0, policy_version 200467 (0.0009) -[2023-11-28 05:27:32,260][87426] Updated weights for policy 1, policy_version 200100 (0.0011) -[2023-11-28 05:27:32,399][87424] Updated weights for policy 0, policy_version 200477 (0.0010) -[2023-11-28 05:27:32,643][87426] Updated weights for policy 1, policy_version 200110 (0.0011) -[2023-11-28 05:27:33,022][87426] Updated weights for policy 1, policy_version 200120 (0.0011) -[2023-11-28 05:27:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5734.4, 300 sec: 5470.6). Total num frames: 102555648. Throughput: 0: 2800.8, 1: 2754.6. Samples: 102563052. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:33,445][86177] Avg episode reward: [(0, '-515.170'), (1, '-527.810')] -[2023-11-28 05:27:34,547][87424] Updated weights for policy 0, policy_version 200487 (0.0008) -[2023-11-28 05:27:34,890][87426] Updated weights for policy 1, policy_version 200130 (0.0011) -[2023-11-28 05:27:34,928][87424] Updated weights for policy 0, policy_version 200497 (0.0010) -[2023-11-28 05:27:35,272][87426] Updated weights for policy 1, policy_version 200140 (0.0011) -[2023-11-28 05:27:35,309][87424] Updated weights for policy 0, policy_version 200507 (0.0007) -[2023-11-28 05:27:35,645][87426] Updated weights for policy 1, policy_version 200150 (0.0009) -[2023-11-28 05:27:36,022][87426] Updated weights for policy 1, policy_version 200160 (0.0007) -[2023-11-28 05:27:37,527][87424] Updated weights for policy 0, policy_version 200517 (0.0008) -[2023-11-28 05:27:37,913][87424] Updated weights for policy 0, policy_version 200527 (0.0009) -[2023-11-28 05:27:38,288][87424] Updated weights for policy 0, policy_version 200537 (0.0008) -[2023-11-28 05:27:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 102572032. Throughput: 0: 2789.5, 1: 2739.5. Samples: 102595420. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:38,445][86177] Avg episode reward: [(0, '-519.530'), (1, '-554.900')] -[2023-11-28 05:27:38,514][87426] Updated weights for policy 1, policy_version 200170 (0.0011) -[2023-11-28 05:27:38,892][87426] Updated weights for policy 1, policy_version 200180 (0.0009) -[2023-11-28 05:27:39,281][87426] Updated weights for policy 1, policy_version 200190 (0.0012) -[2023-11-28 05:27:40,503][87424] Updated weights for policy 0, policy_version 200547 (0.0010) -[2023-11-28 05:27:40,887][87424] Updated weights for policy 0, policy_version 200557 (0.0012) -[2023-11-28 05:27:41,266][87424] Updated weights for policy 0, policy_version 200567 (0.0009) -[2023-11-28 05:27:41,705][87426] Updated weights for policy 1, policy_version 200200 (0.0012) -[2023-11-28 05:27:42,083][87426] Updated weights for policy 1, policy_version 200210 (0.0012) -[2023-11-28 05:27:42,471][87426] Updated weights for policy 1, policy_version 200220 (0.0011) -[2023-11-28 05:27:43,392][87424] Updated weights for policy 0, policy_version 200577 (0.0009) -[2023-11-28 05:27:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 102604800. Throughput: 0: 2770.0, 1: 2724.5. Samples: 102619756. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:43,445][86177] Avg episode reward: [(0, '-504.390'), (1, '-544.430')] -[2023-11-28 05:27:43,769][87424] Updated weights for policy 0, policy_version 200587 (0.0010) -[2023-11-28 05:27:44,154][87424] Updated weights for policy 0, policy_version 200597 (0.0008) -[2023-11-28 05:27:44,540][87424] Updated weights for policy 0, policy_version 200607 (0.0009) -[2023-11-28 05:27:44,598][87426] Updated weights for policy 1, policy_version 200230 (0.0011) -[2023-11-28 05:27:44,980][87426] Updated weights for policy 1, policy_version 200240 (0.0012) -[2023-11-28 05:27:45,360][87426] Updated weights for policy 1, policy_version 200250 (0.0012) -[2023-11-28 05:27:46,742][87424] Updated weights for policy 0, policy_version 200617 (0.0011) -[2023-11-28 05:27:47,125][87424] Updated weights for policy 0, policy_version 200627 (0.0012) -[2023-11-28 05:27:47,504][87424] Updated weights for policy 0, policy_version 200637 (0.0012) -[2023-11-28 05:27:47,684][87426] Updated weights for policy 1, policy_version 200260 (0.0012) -[2023-11-28 05:27:48,057][87426] Updated weights for policy 1, policy_version 200270 (0.0012) -[2023-11-28 05:27:48,430][87426] Updated weights for policy 1, policy_version 200280 (0.0010) -[2023-11-28 05:27:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102629376. Throughput: 0: 2760.4, 1: 2722.8. Samples: 102644628. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:48,445][86177] Avg episode reward: [(0, '-501.790'), (1, '-572.590')] -[2023-11-28 05:27:49,311][87424] Updated weights for policy 0, policy_version 200647 (0.0009) -[2023-11-28 05:27:49,700][87424] Updated weights for policy 0, policy_version 200657 (0.0012) -[2023-11-28 05:27:50,078][87424] Updated weights for policy 0, policy_version 200667 (0.0012) -[2023-11-28 05:27:50,133][87426] Updated weights for policy 1, policy_version 200290 (0.0009) -[2023-11-28 05:27:50,517][87426] Updated weights for policy 1, policy_version 200300 (0.0011) -[2023-11-28 05:27:50,893][87426] Updated weights for policy 1, policy_version 200310 (0.0011) -[2023-11-28 05:27:51,271][87426] Updated weights for policy 1, policy_version 200320 (0.0012) -[2023-11-28 05:27:52,493][87424] Updated weights for policy 0, policy_version 200677 (0.0010) -[2023-11-28 05:27:52,872][87424] Updated weights for policy 0, policy_version 200687 (0.0009) -[2023-11-28 05:27:53,250][87424] Updated weights for policy 0, policy_version 200697 (0.0010) -[2023-11-28 05:27:53,456][86177] Fps is (10 sec: 4909.5, 60 sec: 5460.3, 300 sec: 5442.6). Total num frames: 102653952. Throughput: 0: 2749.7, 1: 2717.9. Samples: 102678284. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:53,457][86177] Avg episode reward: [(0, '-500.200'), (1, '-593.470')] -[2023-11-28 05:27:53,775][87426] Updated weights for policy 1, policy_version 200330 (0.0012) -[2023-11-28 05:27:54,151][87426] Updated weights for policy 1, policy_version 200340 (0.0012) -[2023-11-28 05:27:54,531][87426] Updated weights for policy 1, policy_version 200350 (0.0012) -[2023-11-28 05:27:55,133][87424] Updated weights for policy 0, policy_version 200707 (0.0015) -[2023-11-28 05:27:55,513][87424] Updated weights for policy 0, policy_version 200717 (0.0010) -[2023-11-28 05:27:55,893][87424] Updated weights for policy 0, policy_version 200727 (0.0009) -[2023-11-28 05:27:56,943][87426] Updated weights for policy 1, policy_version 200360 (0.0010) -[2023-11-28 05:27:57,318][87426] Updated weights for policy 1, policy_version 200370 (0.0011) -[2023-11-28 05:27:57,696][87426] Updated weights for policy 1, policy_version 200380 (0.0010) -[2023-11-28 05:27:58,135][87424] Updated weights for policy 0, policy_version 200737 (0.0009) -[2023-11-28 05:27:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102686720. Throughput: 0: 2754.9, 1: 2709.8. Samples: 102701996. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:27:58,445][86177] Avg episode reward: [(0, '-498.900'), (1, '-563.820')] -[2023-11-28 05:27:58,505][87424] Updated weights for policy 0, policy_version 200747 (0.0007) -[2023-11-28 05:27:58,886][87424] Updated weights for policy 0, policy_version 200757 (0.0009) -[2023-11-28 05:27:59,278][87424] Updated weights for policy 0, policy_version 200767 (0.0012) -[2023-11-28 05:27:59,488][87426] Updated weights for policy 1, policy_version 200390 (0.0009) -[2023-11-28 05:27:59,885][87426] Updated weights for policy 1, policy_version 200400 (0.0008) -[2023-11-28 05:28:00,257][87426] Updated weights for policy 1, policy_version 200410 (0.0010) -[2023-11-28 05:28:01,383][87424] Updated weights for policy 0, policy_version 200777 (0.0012) -[2023-11-28 05:28:01,761][87424] Updated weights for policy 0, policy_version 200787 (0.0011) -[2023-11-28 05:28:02,144][87424] Updated weights for policy 0, policy_version 200797 (0.0011) -[2023-11-28 05:28:02,746][87426] Updated weights for policy 1, policy_version 200420 (0.0010) -[2023-11-28 05:28:03,121][87426] Updated weights for policy 1, policy_version 200430 (0.0011) -[2023-11-28 05:28:03,444][86177] Fps is (10 sec: 5741.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 102711296. Throughput: 0: 2760.7, 1: 2708.2. Samples: 102726624. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:28:03,445][86177] Avg episode reward: [(0, '-497.480'), (1, '-561.230')] -[2023-11-28 05:28:03,492][87426] Updated weights for policy 1, policy_version 200440 (0.0012) -[2023-11-28 05:28:04,404][87424] Updated weights for policy 0, policy_version 200807 (0.0009) -[2023-11-28 05:28:04,798][87424] Updated weights for policy 0, policy_version 200817 (0.0008) -[2023-11-28 05:28:05,171][87424] Updated weights for policy 0, policy_version 200827 (0.0008) -[2023-11-28 05:28:05,743][87426] Updated weights for policy 1, policy_version 200450 (0.0010) -[2023-11-28 05:28:06,121][87426] Updated weights for policy 1, policy_version 200460 (0.0007) -[2023-11-28 05:28:06,498][87426] Updated weights for policy 1, policy_version 200470 (0.0007) -[2023-11-28 05:28:06,878][87426] Updated weights for policy 1, policy_version 200480 (0.0008) -[2023-11-28 05:28:07,388][87424] Updated weights for policy 0, policy_version 200837 (0.0010) -[2023-11-28 05:28:07,786][87424] Updated weights for policy 0, policy_version 200847 (0.0011) -[2023-11-28 05:28:08,165][87424] Updated weights for policy 0, policy_version 200857 (0.0010) -[2023-11-28 05:28:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 102744064. Throughput: 0: 2751.6, 1: 2688.5. Samples: 102759008. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:28:08,445][86177] Avg episode reward: [(0, '-499.060'), (1, '-548.220')] -[2023-11-28 05:28:08,996][87426] Updated weights for policy 1, policy_version 200490 (0.0009) -[2023-11-28 05:28:09,373][87426] Updated weights for policy 1, policy_version 200500 (0.0007) -[2023-11-28 05:28:09,751][87426] Updated weights for policy 1, policy_version 200510 (0.0007) -[2023-11-28 05:28:10,381][87424] Updated weights for policy 0, policy_version 200867 (0.0008) -[2023-11-28 05:28:10,761][87424] Updated weights for policy 0, policy_version 200877 (0.0012) -[2023-11-28 05:28:11,140][87424] Updated weights for policy 0, policy_version 200887 (0.0012) -[2023-11-28 05:28:12,251][87426] Updated weights for policy 1, policy_version 200520 (0.0012) -[2023-11-28 05:28:12,628][87426] Updated weights for policy 1, policy_version 200530 (0.0009) -[2023-11-28 05:28:13,005][87426] Updated weights for policy 1, policy_version 200540 (0.0012) -[2023-11-28 05:28:13,084][87424] Updated weights for policy 0, policy_version 200897 (0.0012) -[2023-11-28 05:28:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102768640. Throughput: 0: 2745.2, 1: 2682.3. Samples: 102782000. Policy #0 lag: (min: 44.0, avg: 57.8, max: 83.0) -[2023-11-28 05:28:13,445][86177] Avg episode reward: [(0, '-499.730'), (1, '-522.520')] -[2023-11-28 05:28:13,462][87424] Updated weights for policy 0, policy_version 200907 (0.0012) -[2023-11-28 05:28:13,849][87424] Updated weights for policy 0, policy_version 200917 (0.0012) -[2023-11-28 05:28:14,224][87424] Updated weights for policy 0, policy_version 200927 (0.0008) -[2023-11-28 05:28:14,933][87426] Updated weights for policy 1, policy_version 200550 (0.0009) -[2023-11-28 05:28:15,301][87426] Updated weights for policy 1, policy_version 200560 (0.0008) -[2023-11-28 05:28:15,681][87426] Updated weights for policy 1, policy_version 200570 (0.0009) -[2023-11-28 05:28:16,691][87424] Updated weights for policy 0, policy_version 200937 (0.0011) -[2023-11-28 05:28:17,067][87424] Updated weights for policy 0, policy_version 200947 (0.0011) -[2023-11-28 05:28:17,452][87424] Updated weights for policy 0, policy_version 200957 (0.0011) -[2023-11-28 05:28:17,604][87426] Updated weights for policy 1, policy_version 200580 (0.0008) -[2023-11-28 05:28:17,987][87426] Updated weights for policy 1, policy_version 200590 (0.0009) -[2023-11-28 05:28:18,365][87426] Updated weights for policy 1, policy_version 200600 (0.0007) -[2023-11-28 05:28:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 102793216. Throughput: 0: 2725.6, 1: 2699.1. Samples: 102807164. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:28:18,445][86177] Avg episode reward: [(0, '-504.370'), (1, '-523.220')] -[2023-11-28 05:28:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000200960_51445760.pth... -[2023-11-28 05:28:18,486][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000198400_50790400.pth -[2023-11-28 05:28:18,663][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000200608_51355648.pth... -[2023-11-28 05:28:18,693][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000198048_50700288.pth -[2023-11-28 05:28:19,194][87424] Updated weights for policy 0, policy_version 200967 (0.0011) -[2023-11-28 05:28:19,576][87424] Updated weights for policy 0, policy_version 200977 (0.0012) -[2023-11-28 05:28:19,969][87424] Updated weights for policy 0, policy_version 200987 (0.0012) -[2023-11-28 05:28:20,721][87426] Updated weights for policy 1, policy_version 200610 (0.0008) -[2023-11-28 05:28:21,099][87426] Updated weights for policy 1, policy_version 200620 (0.0012) -[2023-11-28 05:28:21,483][87426] Updated weights for policy 1, policy_version 200630 (0.0012) -[2023-11-28 05:28:21,858][87426] Updated weights for policy 1, policy_version 200640 (0.0012) -[2023-11-28 05:28:22,268][87424] Updated weights for policy 0, policy_version 200997 (0.0011) -[2023-11-28 05:28:22,648][87424] Updated weights for policy 0, policy_version 201007 (0.0011) -[2023-11-28 05:28:23,034][87424] Updated weights for policy 0, policy_version 201017 (0.0010) -[2023-11-28 05:28:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 102825984. Throughput: 0: 2708.5, 1: 2705.2. Samples: 102839040. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:28:23,445][86177] Avg episode reward: [(0, '-549.490'), (1, '-544.550')] -[2023-11-28 05:28:24,451][87426] Updated weights for policy 1, policy_version 200650 (0.0012) -[2023-11-28 05:28:24,819][87426] Updated weights for policy 1, policy_version 200660 (0.0011) -[2023-11-28 05:28:25,197][87426] Updated weights for policy 1, policy_version 200670 (0.0011) -[2023-11-28 05:28:25,269][87424] Updated weights for policy 0, policy_version 201027 (0.0009) -[2023-11-28 05:28:25,648][87424] Updated weights for policy 0, policy_version 201037 (0.0008) -[2023-11-28 05:28:26,026][87424] Updated weights for policy 0, policy_version 201047 (0.0008) -[2023-11-28 05:28:26,938][87426] Updated weights for policy 1, policy_version 200680 (0.0008) -[2023-11-28 05:28:27,323][87426] Updated weights for policy 1, policy_version 200690 (0.0012) -[2023-11-28 05:28:27,698][87426] Updated weights for policy 1, policy_version 200700 (0.0008) -[2023-11-28 05:28:28,311][87424] Updated weights for policy 0, policy_version 201057 (0.0007) -[2023-11-28 05:28:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102850560. Throughput: 0: 2707.7, 1: 2710.8. Samples: 102863588. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:28:28,445][86177] Avg episode reward: [(0, '-551.700'), (1, '-529.330')] -[2023-11-28 05:28:28,684][87424] Updated weights for policy 0, policy_version 201067 (0.0008) -[2023-11-28 05:28:29,068][87424] Updated weights for policy 0, policy_version 201077 (0.0011) -[2023-11-28 05:28:29,447][87424] Updated weights for policy 0, policy_version 201087 (0.0008) -[2023-11-28 05:28:30,012][87426] Updated weights for policy 1, policy_version 200710 (0.0009) -[2023-11-28 05:28:30,399][87426] Updated weights for policy 1, policy_version 200720 (0.0008) -[2023-11-28 05:28:30,769][87426] Updated weights for policy 1, policy_version 200730 (0.0008) -[2023-11-28 05:28:31,862][87424] Updated weights for policy 0, policy_version 201097 (0.0011) -[2023-11-28 05:28:32,241][87424] Updated weights for policy 0, policy_version 201107 (0.0009) -[2023-11-28 05:28:32,628][87424] Updated weights for policy 0, policy_version 201117 (0.0008) -[2023-11-28 05:28:32,791][87426] Updated weights for policy 1, policy_version 200740 (0.0010) -[2023-11-28 05:28:33,168][87426] Updated weights for policy 1, policy_version 200750 (0.0012) -[2023-11-28 05:28:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 102875136. Throughput: 0: 2696.7, 1: 2706.7. Samples: 102887780. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:28:33,445][86177] Avg episode reward: [(0, '-553.620'), (1, '-533.780')] -[2023-11-28 05:28:33,545][87426] Updated weights for policy 1, policy_version 200760 (0.0012) -[2023-11-28 05:28:34,545][87424] Updated weights for policy 0, policy_version 201127 (0.0010) -[2023-11-28 05:28:34,917][87424] Updated weights for policy 0, policy_version 201137 (0.0012) -[2023-11-28 05:28:35,301][87424] Updated weights for policy 0, policy_version 201147 (0.0012) -[2023-11-28 05:28:35,876][87426] Updated weights for policy 1, policy_version 200770 (0.0008) -[2023-11-28 05:28:36,243][87426] Updated weights for policy 1, policy_version 200780 (0.0008) -[2023-11-28 05:28:36,620][87426] Updated weights for policy 1, policy_version 200790 (0.0008) -[2023-11-28 05:28:37,003][87426] Updated weights for policy 1, policy_version 200800 (0.0008) -[2023-11-28 05:28:37,417][87424] Updated weights for policy 0, policy_version 201157 (0.0010) -[2023-11-28 05:28:37,800][87424] Updated weights for policy 0, policy_version 201167 (0.0007) -[2023-11-28 05:28:38,179][87424] Updated weights for policy 0, policy_version 201177 (0.0007) -[2023-11-28 05:28:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 102899712. Throughput: 0: 2703.1, 1: 2676.9. Samples: 102920320. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:28:38,445][86177] Avg episode reward: [(0, '-553.890'), (1, '-535.960')] -[2023-11-28 05:28:39,411][87426] Updated weights for policy 1, policy_version 200810 (0.0011) -[2023-11-28 05:28:39,787][87426] Updated weights for policy 1, policy_version 200820 (0.0010) -[2023-11-28 05:28:40,157][87426] Updated weights for policy 1, policy_version 200830 (0.0010) -[2023-11-28 05:28:40,205][87424] Updated weights for policy 0, policy_version 201187 (0.0007) -[2023-11-28 05:28:40,587][87424] Updated weights for policy 0, policy_version 201197 (0.0008) -[2023-11-28 05:28:40,964][87424] Updated weights for policy 0, policy_version 201207 (0.0009) -[2023-11-28 05:28:42,593][87426] Updated weights for policy 1, policy_version 200840 (0.0011) -[2023-11-28 05:28:42,961][87426] Updated weights for policy 1, policy_version 200850 (0.0012) -[2023-11-28 05:28:43,338][87426] Updated weights for policy 1, policy_version 200860 (0.0011) -[2023-11-28 05:28:43,358][87424] Updated weights for policy 0, policy_version 201217 (0.0010) -[2023-11-28 05:28:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 102924288. Throughput: 0: 2694.0, 1: 2681.5. Samples: 102943892. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:28:43,445][86177] Avg episode reward: [(0, '-510.900'), (1, '-514.260')] -[2023-11-28 05:28:43,736][87424] Updated weights for policy 0, policy_version 201227 (0.0009) -[2023-11-28 05:28:44,128][87424] Updated weights for policy 0, policy_version 201237 (0.0008) -[2023-11-28 05:28:44,517][87424] Updated weights for policy 0, policy_version 201247 (0.0007) -[2023-11-28 05:28:45,578][87426] Updated weights for policy 1, policy_version 200870 (0.0011) -[2023-11-28 05:28:45,959][87426] Updated weights for policy 1, policy_version 200880 (0.0012) -[2023-11-28 05:28:46,340][87426] Updated weights for policy 1, policy_version 200890 (0.0012) -[2023-11-28 05:28:46,511][87424] Updated weights for policy 0, policy_version 201257 (0.0011) -[2023-11-28 05:28:46,908][87424] Updated weights for policy 0, policy_version 201267 (0.0012) -[2023-11-28 05:28:47,282][87424] Updated weights for policy 0, policy_version 201277 (0.0011) -[2023-11-28 05:28:48,437][87426] Updated weights for policy 1, policy_version 200900 (0.0012) -[2023-11-28 05:28:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 102957056. Throughput: 0: 2684.4, 1: 2673.2. Samples: 102967720. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:28:48,445][86177] Avg episode reward: [(0, '-518.330'), (1, '-544.120')] -[2023-11-28 05:28:48,822][87426] Updated weights for policy 1, policy_version 200910 (0.0012) -[2023-11-28 05:28:49,194][87426] Updated weights for policy 1, policy_version 200920 (0.0012) -[2023-11-28 05:28:49,800][87424] Updated weights for policy 0, policy_version 201287 (0.0009) -[2023-11-28 05:28:50,177][87424] Updated weights for policy 0, policy_version 201297 (0.0011) -[2023-11-28 05:28:50,549][87424] Updated weights for policy 0, policy_version 201307 (0.0011) -[2023-11-28 05:28:51,768][87426] Updated weights for policy 1, policy_version 200930 (0.0012) -[2023-11-28 05:28:52,142][87426] Updated weights for policy 1, policy_version 200940 (0.0012) -[2023-11-28 05:28:52,535][87426] Updated weights for policy 1, policy_version 200950 (0.0012) -[2023-11-28 05:28:52,903][87426] Updated weights for policy 1, policy_version 200960 (0.0011) -[2023-11-28 05:28:52,965][87424] Updated weights for policy 0, policy_version 201317 (0.0011) -[2023-11-28 05:28:53,340][87424] Updated weights for policy 0, policy_version 201327 (0.0012) -[2023-11-28 05:28:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5462.4, 300 sec: 5442.8). Total num frames: 102981632. Throughput: 0: 2676.9, 1: 2669.6. Samples: 102999600. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:28:53,445][86177] Avg episode reward: [(0, '-520.230'), (1, '-543.550')] -[2023-11-28 05:28:53,729][87424] Updated weights for policy 0, policy_version 201337 (0.0011) -[2023-11-28 05:28:55,046][87426] Updated weights for policy 1, policy_version 200970 (0.0008) -[2023-11-28 05:28:55,431][87426] Updated weights for policy 1, policy_version 200980 (0.0007) -[2023-11-28 05:28:55,775][87424] Updated weights for policy 0, policy_version 201347 (0.0011) -[2023-11-28 05:28:55,806][87426] Updated weights for policy 1, policy_version 200990 (0.0007) -[2023-11-28 05:28:56,144][87424] Updated weights for policy 0, policy_version 201357 (0.0007) -[2023-11-28 05:28:56,527][87424] Updated weights for policy 0, policy_version 201367 (0.0008) -[2023-11-28 05:28:57,864][87426] Updated weights for policy 1, policy_version 201000 (0.0011) -[2023-11-28 05:28:58,248][87426] Updated weights for policy 1, policy_version 201010 (0.0012) -[2023-11-28 05:28:58,357][87424] Updated weights for policy 0, policy_version 201377 (0.0008) -[2023-11-28 05:28:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 103006208. Throughput: 0: 2691.0, 1: 2697.5. Samples: 103024484. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:28:58,445][86177] Avg episode reward: [(0, '-535.890'), (1, '-540.670')] -[2023-11-28 05:28:58,621][87426] Updated weights for policy 1, policy_version 201020 (0.0009) -[2023-11-28 05:28:58,741][87424] Updated weights for policy 0, policy_version 201387 (0.0007) -[2023-11-28 05:28:59,128][87424] Updated weights for policy 0, policy_version 201397 (0.0007) -[2023-11-28 05:28:59,508][87424] Updated weights for policy 0, policy_version 201407 (0.0008) -[2023-11-28 05:29:01,138][87426] Updated weights for policy 1, policy_version 201030 (0.0010) -[2023-11-28 05:29:01,202][87424] Updated weights for policy 0, policy_version 201417 (0.0010) -[2023-11-28 05:29:01,511][87426] Updated weights for policy 1, policy_version 201040 (0.0011) -[2023-11-28 05:29:01,586][87424] Updated weights for policy 0, policy_version 201427 (0.0008) -[2023-11-28 05:29:01,895][87426] Updated weights for policy 1, policy_version 201050 (0.0010) -[2023-11-28 05:29:01,976][87424] Updated weights for policy 0, policy_version 201437 (0.0009) -[2023-11-28 05:29:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103038976. Throughput: 0: 2730.0, 1: 2661.3. Samples: 103049768. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:29:03,445][86177] Avg episode reward: [(0, '-532.360'), (1, '-540.250')] -[2023-11-28 05:29:03,733][87426] Updated weights for policy 1, policy_version 201060 (0.0009) -[2023-11-28 05:29:03,979][87424] Updated weights for policy 0, policy_version 201447 (0.0007) -[2023-11-28 05:29:04,108][87426] Updated weights for policy 1, policy_version 201070 (0.0007) -[2023-11-28 05:29:04,380][87424] Updated weights for policy 0, policy_version 201457 (0.0008) -[2023-11-28 05:29:04,490][87426] Updated weights for policy 1, policy_version 201080 (0.0008) -[2023-11-28 05:29:04,756][87424] Updated weights for policy 0, policy_version 201467 (0.0009) -[2023-11-28 05:29:06,697][87426] Updated weights for policy 1, policy_version 201090 (0.0012) -[2023-11-28 05:29:07,026][87424] Updated weights for policy 0, policy_version 201477 (0.0012) -[2023-11-28 05:29:07,065][87426] Updated weights for policy 1, policy_version 201100 (0.0009) -[2023-11-28 05:29:07,419][87424] Updated weights for policy 0, policy_version 201487 (0.0012) -[2023-11-28 05:29:07,445][87426] Updated weights for policy 1, policy_version 201110 (0.0012) -[2023-11-28 05:29:07,793][87424] Updated weights for policy 0, policy_version 201497 (0.0010) -[2023-11-28 05:29:07,822][87426] Updated weights for policy 1, policy_version 201120 (0.0012) -[2023-11-28 05:29:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 103071744. Throughput: 0: 2742.0, 1: 2672.7. Samples: 103082704. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:29:08,445][86177] Avg episode reward: [(0, '-520.680'), (1, '-540.370')] -[2023-11-28 05:29:09,933][87426] Updated weights for policy 1, policy_version 201130 (0.0012) -[2023-11-28 05:29:10,309][87426] Updated weights for policy 1, policy_version 201140 (0.0011) -[2023-11-28 05:29:10,346][87424] Updated weights for policy 0, policy_version 201507 (0.0008) -[2023-11-28 05:29:10,686][87426] Updated weights for policy 1, policy_version 201150 (0.0012) -[2023-11-28 05:29:10,720][87424] Updated weights for policy 0, policy_version 201517 (0.0009) -[2023-11-28 05:29:11,104][87424] Updated weights for policy 0, policy_version 201527 (0.0007) -[2023-11-28 05:29:12,933][87426] Updated weights for policy 1, policy_version 201160 (0.0011) -[2023-11-28 05:29:13,312][87426] Updated weights for policy 1, policy_version 201170 (0.0010) -[2023-11-28 05:29:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 103088128. Throughput: 0: 2739.1, 1: 2690.0. Samples: 103107900. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:29:13,445][86177] Avg episode reward: [(0, '-526.300'), (1, '-512.780')] -[2023-11-28 05:29:13,495][87424] Updated weights for policy 0, policy_version 201537 (0.0008) -[2023-11-28 05:29:13,696][87426] Updated weights for policy 1, policy_version 201180 (0.0010) -[2023-11-28 05:29:13,871][87424] Updated weights for policy 0, policy_version 201547 (0.0011) -[2023-11-28 05:29:14,256][87424] Updated weights for policy 0, policy_version 201557 (0.0012) -[2023-11-28 05:29:14,631][87424] Updated weights for policy 0, policy_version 201567 (0.0009) -[2023-11-28 05:29:15,885][87426] Updated weights for policy 1, policy_version 201190 (0.0010) -[2023-11-28 05:29:16,265][87426] Updated weights for policy 1, policy_version 201200 (0.0011) -[2023-11-28 05:29:16,561][87424] Updated weights for policy 0, policy_version 201577 (0.0011) -[2023-11-28 05:29:16,645][87426] Updated weights for policy 1, policy_version 201210 (0.0011) -[2023-11-28 05:29:16,935][87424] Updated weights for policy 0, policy_version 201587 (0.0012) -[2023-11-28 05:29:17,316][87424] Updated weights for policy 0, policy_version 201597 (0.0011) -[2023-11-28 05:29:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103120896. Throughput: 0: 2749.2, 1: 2696.3. Samples: 103132828. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:29:18,445][86177] Avg episode reward: [(0, '-518.450'), (1, '-541.060')] -[2023-11-28 05:29:18,854][87426] Updated weights for policy 1, policy_version 201220 (0.0012) -[2023-11-28 05:29:19,238][87426] Updated weights for policy 1, policy_version 201230 (0.0011) -[2023-11-28 05:29:19,479][87424] Updated weights for policy 0, policy_version 201607 (0.0009) -[2023-11-28 05:29:19,611][87426] Updated weights for policy 1, policy_version 201240 (0.0009) -[2023-11-28 05:29:19,863][87424] Updated weights for policy 0, policy_version 201617 (0.0008) -[2023-11-28 05:29:20,250][87424] Updated weights for policy 0, policy_version 201627 (0.0011) -[2023-11-28 05:29:22,044][87426] Updated weights for policy 1, policy_version 201250 (0.0010) -[2023-11-28 05:29:22,277][87424] Updated weights for policy 0, policy_version 201637 (0.0010) -[2023-11-28 05:29:22,418][87426] Updated weights for policy 1, policy_version 201260 (0.0010) -[2023-11-28 05:29:22,658][87424] Updated weights for policy 0, policy_version 201647 (0.0009) -[2023-11-28 05:29:22,802][87426] Updated weights for policy 1, policy_version 201270 (0.0011) -[2023-11-28 05:29:23,030][87424] Updated weights for policy 0, policy_version 201657 (0.0009) -[2023-11-28 05:29:23,189][87426] Updated weights for policy 1, policy_version 201280 (0.0011) -[2023-11-28 05:29:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 103153664. Throughput: 0: 2747.2, 1: 2700.5. Samples: 103165468. Policy #0 lag: (min: 40.0, avg: 46.1, max: 72.0) -[2023-11-28 05:29:23,446][86177] Avg episode reward: [(0, '-517.710'), (1, '-554.240')] -[2023-11-28 05:29:25,115][87424] Updated weights for policy 0, policy_version 201667 (0.0009) -[2023-11-28 05:29:25,502][87424] Updated weights for policy 0, policy_version 201677 (0.0009) -[2023-11-28 05:29:25,728][87426] Updated weights for policy 1, policy_version 201290 (0.0010) -[2023-11-28 05:29:25,892][87424] Updated weights for policy 0, policy_version 201687 (0.0007) -[2023-11-28 05:29:26,116][87426] Updated weights for policy 1, policy_version 201300 (0.0008) -[2023-11-28 05:29:26,495][87426] Updated weights for policy 1, policy_version 201310 (0.0007) -[2023-11-28 05:29:27,617][87424] Updated weights for policy 0, policy_version 201697 (0.0007) -[2023-11-28 05:29:28,002][87424] Updated weights for policy 0, policy_version 201707 (0.0008) -[2023-11-28 05:29:28,218][87426] Updated weights for policy 1, policy_version 201320 (0.0007) -[2023-11-28 05:29:28,388][87424] Updated weights for policy 0, policy_version 201717 (0.0008) -[2023-11-28 05:29:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 103170048. Throughput: 0: 2767.9, 1: 2701.7. Samples: 103190024. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:29:28,445][86177] Avg episode reward: [(0, '-519.450'), (1, '-565.240')] -[2023-11-28 05:29:28,597][87426] Updated weights for policy 1, policy_version 201330 (0.0008) -[2023-11-28 05:29:28,771][87424] Updated weights for policy 0, policy_version 201727 (0.0008) -[2023-11-28 05:29:28,972][87426] Updated weights for policy 1, policy_version 201340 (0.0009) -[2023-11-28 05:29:30,885][87424] Updated weights for policy 0, policy_version 201737 (0.0007) -[2023-11-28 05:29:31,142][87426] Updated weights for policy 1, policy_version 201350 (0.0010) -[2023-11-28 05:29:31,270][87424] Updated weights for policy 0, policy_version 201747 (0.0008) -[2023-11-28 05:29:31,520][87426] Updated weights for policy 1, policy_version 201360 (0.0011) -[2023-11-28 05:29:31,673][87424] Updated weights for policy 0, policy_version 201757 (0.0009) -[2023-11-28 05:29:31,901][87426] Updated weights for policy 1, policy_version 201370 (0.0011) -[2023-11-28 05:29:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 103202816. Throughput: 0: 2778.0, 1: 2703.9. Samples: 103214408. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:29:33,446][86177] Avg episode reward: [(0, '-504.910'), (1, '-565.520')] -[2023-11-28 05:29:33,888][87424] Updated weights for policy 0, policy_version 201767 (0.0010) -[2023-11-28 05:29:34,272][87424] Updated weights for policy 0, policy_version 201777 (0.0008) -[2023-11-28 05:29:34,299][87426] Updated weights for policy 1, policy_version 201380 (0.0009) -[2023-11-28 05:29:34,653][87424] Updated weights for policy 0, policy_version 201787 (0.0011) -[2023-11-28 05:29:34,679][87426] Updated weights for policy 1, policy_version 201390 (0.0008) -[2023-11-28 05:29:35,055][87426] Updated weights for policy 1, policy_version 201400 (0.0009) -[2023-11-28 05:29:37,165][87424] Updated weights for policy 0, policy_version 201797 (0.0012) -[2023-11-28 05:29:37,441][87426] Updated weights for policy 1, policy_version 201410 (0.0011) -[2023-11-28 05:29:37,545][87424] Updated weights for policy 0, policy_version 201807 (0.0012) -[2023-11-28 05:29:37,825][87426] Updated weights for policy 1, policy_version 201420 (0.0009) -[2023-11-28 05:29:37,926][87424] Updated weights for policy 0, policy_version 201817 (0.0012) -[2023-11-28 05:29:38,202][87426] Updated weights for policy 1, policy_version 201430 (0.0009) -[2023-11-28 05:29:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103227392. Throughput: 0: 2780.5, 1: 2731.6. Samples: 103247648. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:29:38,445][86177] Avg episode reward: [(0, '-501.290'), (1, '-542.420')] -[2023-11-28 05:29:38,568][87426] Updated weights for policy 1, policy_version 201440 (0.0012) -[2023-11-28 05:29:40,335][87424] Updated weights for policy 0, policy_version 201827 (0.0011) -[2023-11-28 05:29:40,681][87426] Updated weights for policy 1, policy_version 201450 (0.0011) -[2023-11-28 05:29:40,725][87424] Updated weights for policy 0, policy_version 201837 (0.0010) -[2023-11-28 05:29:41,057][87426] Updated weights for policy 1, policy_version 201460 (0.0012) -[2023-11-28 05:29:41,098][87424] Updated weights for policy 0, policy_version 201847 (0.0009) -[2023-11-28 05:29:41,448][87426] Updated weights for policy 1, policy_version 201470 (0.0011) -[2023-11-28 05:29:43,203][87424] Updated weights for policy 0, policy_version 201857 (0.0008) -[2023-11-28 05:29:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 103251968. Throughput: 0: 2765.5, 1: 2714.7. Samples: 103271092. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:29:43,446][86177] Avg episode reward: [(0, '-506.170'), (1, '-532.440')] -[2023-11-28 05:29:43,589][87424] Updated weights for policy 0, policy_version 201867 (0.0010) -[2023-11-28 05:29:43,969][87424] Updated weights for policy 0, policy_version 201877 (0.0007) -[2023-11-28 05:29:44,024][87426] Updated weights for policy 1, policy_version 201480 (0.0008) -[2023-11-28 05:29:44,346][87424] Updated weights for policy 0, policy_version 201887 (0.0007) -[2023-11-28 05:29:44,397][87426] Updated weights for policy 1, policy_version 201490 (0.0010) -[2023-11-28 05:29:44,777][87426] Updated weights for policy 1, policy_version 201500 (0.0009) -[2023-11-28 05:29:46,459][87424] Updated weights for policy 0, policy_version 201897 (0.0011) -[2023-11-28 05:29:46,533][87426] Updated weights for policy 1, policy_version 201510 (0.0007) -[2023-11-28 05:29:46,834][87424] Updated weights for policy 0, policy_version 201907 (0.0012) -[2023-11-28 05:29:46,907][87426] Updated weights for policy 1, policy_version 201520 (0.0009) -[2023-11-28 05:29:47,215][87424] Updated weights for policy 0, policy_version 201917 (0.0011) -[2023-11-28 05:29:47,291][87426] Updated weights for policy 1, policy_version 201530 (0.0007) -[2023-11-28 05:29:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103284736. Throughput: 0: 2727.3, 1: 2732.4. Samples: 103295456. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:29:48,445][86177] Avg episode reward: [(0, '-502.930'), (1, '-543.730')] -[2023-11-28 05:29:48,990][87424] Updated weights for policy 0, policy_version 201927 (0.0012) -[2023-11-28 05:29:49,371][87424] Updated weights for policy 0, policy_version 201937 (0.0010) -[2023-11-28 05:29:49,429][87426] Updated weights for policy 1, policy_version 201540 (0.0009) -[2023-11-28 05:29:49,749][87424] Updated weights for policy 0, policy_version 201947 (0.0009) -[2023-11-28 05:29:49,806][87426] Updated weights for policy 1, policy_version 201550 (0.0012) -[2023-11-28 05:29:50,186][87426] Updated weights for policy 1, policy_version 201560 (0.0011) -[2023-11-28 05:29:52,086][87424] Updated weights for policy 0, policy_version 201957 (0.0012) -[2023-11-28 05:29:52,189][87426] Updated weights for policy 1, policy_version 201570 (0.0010) -[2023-11-28 05:29:52,483][87424] Updated weights for policy 0, policy_version 201967 (0.0010) -[2023-11-28 05:29:52,568][87426] Updated weights for policy 1, policy_version 201580 (0.0010) -[2023-11-28 05:29:52,861][87424] Updated weights for policy 0, policy_version 201977 (0.0010) -[2023-11-28 05:29:52,943][87426] Updated weights for policy 1, policy_version 201590 (0.0011) -[2023-11-28 05:29:53,324][87426] Updated weights for policy 1, policy_version 201600 (0.0012) -[2023-11-28 05:29:53,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 103317504. Throughput: 0: 2740.4, 1: 2702.1. Samples: 103327616. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:29:53,445][86177] Avg episode reward: [(0, '-524.760'), (1, '-553.690')] -[2023-11-28 05:29:54,995][87424] Updated weights for policy 0, policy_version 201987 (0.0009) -[2023-11-28 05:29:55,378][87424] Updated weights for policy 0, policy_version 201997 (0.0009) -[2023-11-28 05:29:55,602][87426] Updated weights for policy 1, policy_version 201610 (0.0007) -[2023-11-28 05:29:55,757][87424] Updated weights for policy 0, policy_version 202007 (0.0007) -[2023-11-28 05:29:55,968][87426] Updated weights for policy 1, policy_version 201620 (0.0007) -[2023-11-28 05:29:56,345][87426] Updated weights for policy 1, policy_version 201630 (0.0009) -[2023-11-28 05:29:57,884][87424] Updated weights for policy 0, policy_version 202017 (0.0008) -[2023-11-28 05:29:58,263][87424] Updated weights for policy 0, policy_version 202027 (0.0009) -[2023-11-28 05:29:58,370][87426] Updated weights for policy 1, policy_version 201640 (0.0007) -[2023-11-28 05:29:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 103333888. Throughput: 0: 2748.7, 1: 2680.2. Samples: 103352200. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:29:58,446][86177] Avg episode reward: [(0, '-543.160'), (1, '-556.200')] -[2023-11-28 05:29:58,649][87424] Updated weights for policy 0, policy_version 202037 (0.0007) -[2023-11-28 05:29:58,751][87426] Updated weights for policy 1, policy_version 201650 (0.0007) -[2023-11-28 05:29:59,029][87424] Updated weights for policy 0, policy_version 202047 (0.0009) -[2023-11-28 05:29:59,128][87426] Updated weights for policy 1, policy_version 201660 (0.0011) -[2023-11-28 05:30:01,255][87424] Updated weights for policy 0, policy_version 202057 (0.0011) -[2023-11-28 05:30:01,436][87426] Updated weights for policy 1, policy_version 201670 (0.0009) -[2023-11-28 05:30:01,648][87424] Updated weights for policy 0, policy_version 202067 (0.0012) -[2023-11-28 05:30:01,818][87426] Updated weights for policy 1, policy_version 201680 (0.0009) -[2023-11-28 05:30:02,027][87424] Updated weights for policy 0, policy_version 202077 (0.0011) -[2023-11-28 05:30:02,198][87426] Updated weights for policy 1, policy_version 201690 (0.0009) -[2023-11-28 05:30:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103366656. Throughput: 0: 2768.8, 1: 2665.0. Samples: 103377348. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:30:03,445][86177] Avg episode reward: [(0, '-581.610'), (1, '-591.330')] -[2023-11-28 05:30:04,064][87426] Updated weights for policy 1, policy_version 201700 (0.0011) -[2023-11-28 05:30:04,154][87424] Updated weights for policy 0, policy_version 202087 (0.0011) -[2023-11-28 05:30:04,431][87426] Updated weights for policy 1, policy_version 201710 (0.0012) -[2023-11-28 05:30:04,527][87424] Updated weights for policy 0, policy_version 202097 (0.0010) -[2023-11-28 05:30:04,806][87426] Updated weights for policy 1, policy_version 201720 (0.0012) -[2023-11-28 05:30:04,908][87424] Updated weights for policy 0, policy_version 202107 (0.0011) -[2023-11-28 05:30:07,001][87426] Updated weights for policy 1, policy_version 201730 (0.0011) -[2023-11-28 05:30:07,042][87424] Updated weights for policy 0, policy_version 202117 (0.0012) -[2023-11-28 05:30:07,378][87426] Updated weights for policy 1, policy_version 201740 (0.0011) -[2023-11-28 05:30:07,432][87424] Updated weights for policy 0, policy_version 202127 (0.0012) -[2023-11-28 05:30:07,748][87426] Updated weights for policy 1, policy_version 201750 (0.0009) -[2023-11-28 05:30:07,804][87424] Updated weights for policy 0, policy_version 202137 (0.0012) -[2023-11-28 05:30:08,136][87426] Updated weights for policy 1, policy_version 201760 (0.0009) -[2023-11-28 05:30:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 103399424. Throughput: 0: 2736.4, 1: 2695.7. Samples: 103409908. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:30:08,445][86177] Avg episode reward: [(0, '-570.440'), (1, '-572.250')] -[2023-11-28 05:30:09,845][87424] Updated weights for policy 0, policy_version 202147 (0.0010) -[2023-11-28 05:30:10,222][87424] Updated weights for policy 0, policy_version 202157 (0.0011) -[2023-11-28 05:30:10,556][87426] Updated weights for policy 1, policy_version 201770 (0.0011) -[2023-11-28 05:30:10,604][87424] Updated weights for policy 0, policy_version 202167 (0.0010) -[2023-11-28 05:30:10,934][87426] Updated weights for policy 1, policy_version 201780 (0.0011) -[2023-11-28 05:30:11,308][87426] Updated weights for policy 1, policy_version 201790 (0.0008) -[2023-11-28 05:30:12,958][87424] Updated weights for policy 0, policy_version 202177 (0.0011) -[2023-11-28 05:30:13,334][87424] Updated weights for policy 0, policy_version 202187 (0.0009) -[2023-11-28 05:30:13,432][87426] Updated weights for policy 1, policy_version 201800 (0.0011) -[2023-11-28 05:30:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 103415808. Throughput: 0: 2722.5, 1: 2703.6. Samples: 103434196. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:30:13,445][86177] Avg episode reward: [(0, '-558.280'), (1, '-567.570')] -[2023-11-28 05:30:13,722][87424] Updated weights for policy 0, policy_version 202197 (0.0007) -[2023-11-28 05:30:13,806][87426] Updated weights for policy 1, policy_version 201810 (0.0011) -[2023-11-28 05:30:14,099][87424] Updated weights for policy 0, policy_version 202207 (0.0007) -[2023-11-28 05:30:14,187][87426] Updated weights for policy 1, policy_version 201820 (0.0008) -[2023-11-28 05:30:16,085][87424] Updated weights for policy 0, policy_version 202217 (0.0009) -[2023-11-28 05:30:16,463][87424] Updated weights for policy 0, policy_version 202227 (0.0008) -[2023-11-28 05:30:16,687][87426] Updated weights for policy 1, policy_version 201830 (0.0007) -[2023-11-28 05:30:16,844][87424] Updated weights for policy 0, policy_version 202237 (0.0007) -[2023-11-28 05:30:17,073][87426] Updated weights for policy 1, policy_version 201840 (0.0007) -[2023-11-28 05:30:17,463][87426] Updated weights for policy 1, policy_version 201850 (0.0008) -[2023-11-28 05:30:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103448576. Throughput: 0: 2717.7, 1: 2692.2. Samples: 103457852. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:30:18,445][86177] Avg episode reward: [(0, '-515.010'), (1, '-573.360')] -[2023-11-28 05:30:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000201856_51675136.pth... -[2023-11-28 05:30:18,500][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000199328_51027968.pth -[2023-11-28 05:30:18,505][87424] Updated weights for policy 0, policy_version 202247 (0.0010) -[2023-11-28 05:30:18,891][87424] Updated weights for policy 0, policy_version 202257 (0.0012) -[2023-11-28 05:30:19,272][87424] Updated weights for policy 0, policy_version 202267 (0.0011) -[2023-11-28 05:30:19,460][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000202272_51781632.pth... -[2023-11-28 05:30:19,508][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000199680_51118080.pth -[2023-11-28 05:30:19,821][87426] Updated weights for policy 1, policy_version 201860 (0.0010) -[2023-11-28 05:30:20,193][87426] Updated weights for policy 1, policy_version 201870 (0.0012) -[2023-11-28 05:30:20,576][87426] Updated weights for policy 1, policy_version 201880 (0.0012) -[2023-11-28 05:30:21,391][87424] Updated weights for policy 0, policy_version 202277 (0.0011) -[2023-11-28 05:30:21,778][87424] Updated weights for policy 0, policy_version 202287 (0.0011) -[2023-11-28 05:30:22,161][87424] Updated weights for policy 0, policy_version 202297 (0.0010) -[2023-11-28 05:30:22,729][87426] Updated weights for policy 1, policy_version 201890 (0.0011) -[2023-11-28 05:30:23,114][87426] Updated weights for policy 1, policy_version 201900 (0.0009) -[2023-11-28 05:30:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 103473152. Throughput: 0: 2730.8, 1: 2664.5. Samples: 103490440. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:30:23,445][86177] Avg episode reward: [(0, '-517.340'), (1, '-551.130')] -[2023-11-28 05:30:23,483][87426] Updated weights for policy 1, policy_version 201910 (0.0008) -[2023-11-28 05:30:23,860][87426] Updated weights for policy 1, policy_version 201920 (0.0007) -[2023-11-28 05:30:24,514][87424] Updated weights for policy 0, policy_version 202307 (0.0009) -[2023-11-28 05:30:24,902][87424] Updated weights for policy 0, policy_version 202317 (0.0007) -[2023-11-28 05:30:25,282][87424] Updated weights for policy 0, policy_version 202327 (0.0010) -[2023-11-28 05:30:26,180][87426] Updated weights for policy 1, policy_version 201930 (0.0012) -[2023-11-28 05:30:26,562][87426] Updated weights for policy 1, policy_version 201940 (0.0011) -[2023-11-28 05:30:26,937][87426] Updated weights for policy 1, policy_version 201950 (0.0012) -[2023-11-28 05:30:27,545][87424] Updated weights for policy 0, policy_version 202337 (0.0011) -[2023-11-28 05:30:27,927][87424] Updated weights for policy 0, policy_version 202347 (0.0011) -[2023-11-28 05:30:28,314][87424] Updated weights for policy 0, policy_version 202357 (0.0012) -[2023-11-28 05:30:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103497728. Throughput: 0: 2739.5, 1: 2691.6. Samples: 103515488. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:30:28,445][86177] Avg episode reward: [(0, '-517.320'), (1, '-555.060')] -[2023-11-28 05:30:28,690][87424] Updated weights for policy 0, policy_version 202367 (0.0012) -[2023-11-28 05:30:28,881][87426] Updated weights for policy 1, policy_version 201960 (0.0009) -[2023-11-28 05:30:29,272][87426] Updated weights for policy 1, policy_version 201970 (0.0012) -[2023-11-28 05:30:29,645][87426] Updated weights for policy 1, policy_version 201980 (0.0011) -[2023-11-28 05:30:30,675][87424] Updated weights for policy 0, policy_version 202377 (0.0012) -[2023-11-28 05:30:31,061][87424] Updated weights for policy 0, policy_version 202387 (0.0012) -[2023-11-28 05:30:31,435][87424] Updated weights for policy 0, policy_version 202397 (0.0009) -[2023-11-28 05:30:31,623][87426] Updated weights for policy 1, policy_version 201990 (0.0011) -[2023-11-28 05:30:31,997][87426] Updated weights for policy 1, policy_version 202000 (0.0012) -[2023-11-28 05:30:32,385][87426] Updated weights for policy 1, policy_version 202010 (0.0012) -[2023-11-28 05:30:33,419][87424] Updated weights for policy 0, policy_version 202407 (0.0010) -[2023-11-28 05:30:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103530496. Throughput: 0: 2747.5, 1: 2707.4. Samples: 103540924. Policy #0 lag: (min: 30.0, avg: 50.7, max: 83.0) -[2023-11-28 05:30:33,445][86177] Avg episode reward: [(0, '-505.100'), (1, '-540.730')] -[2023-11-28 05:30:33,803][87424] Updated weights for policy 0, policy_version 202417 (0.0010) -[2023-11-28 05:30:34,184][87424] Updated weights for policy 0, policy_version 202427 (0.0012) -[2023-11-28 05:30:34,838][87426] Updated weights for policy 1, policy_version 202020 (0.0012) -[2023-11-28 05:30:35,223][87426] Updated weights for policy 1, policy_version 202030 (0.0012) -[2023-11-28 05:30:35,592][87426] Updated weights for policy 1, policy_version 202040 (0.0012) -[2023-11-28 05:30:36,649][87424] Updated weights for policy 0, policy_version 202437 (0.0012) -[2023-11-28 05:30:37,027][87424] Updated weights for policy 0, policy_version 202447 (0.0011) -[2023-11-28 05:30:37,403][87424] Updated weights for policy 0, policy_version 202457 (0.0012) -[2023-11-28 05:30:37,700][87426] Updated weights for policy 1, policy_version 202050 (0.0012) -[2023-11-28 05:30:38,078][87426] Updated weights for policy 1, policy_version 202060 (0.0010) -[2023-11-28 05:30:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103555072. Throughput: 0: 2742.8, 1: 2723.6. Samples: 103573608. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:30:38,445][86177] Avg episode reward: [(0, '-504.660'), (1, '-531.730')] -[2023-11-28 05:30:38,468][87426] Updated weights for policy 1, policy_version 202070 (0.0007) -[2023-11-28 05:30:38,846][87426] Updated weights for policy 1, policy_version 202080 (0.0008) -[2023-11-28 05:30:39,458][87424] Updated weights for policy 0, policy_version 202467 (0.0011) -[2023-11-28 05:30:39,835][87424] Updated weights for policy 0, policy_version 202477 (0.0008) -[2023-11-28 05:30:40,221][87424] Updated weights for policy 0, policy_version 202487 (0.0009) -[2023-11-28 05:30:41,186][87426] Updated weights for policy 1, policy_version 202090 (0.0007) -[2023-11-28 05:30:41,582][87426] Updated weights for policy 1, policy_version 202100 (0.0008) -[2023-11-28 05:30:41,965][87426] Updated weights for policy 1, policy_version 202110 (0.0011) -[2023-11-28 05:30:42,549][87424] Updated weights for policy 0, policy_version 202497 (0.0010) -[2023-11-28 05:30:42,932][87424] Updated weights for policy 0, policy_version 202507 (0.0010) -[2023-11-28 05:30:43,313][87424] Updated weights for policy 0, policy_version 202517 (0.0007) -[2023-11-28 05:30:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103579648. Throughput: 0: 2753.1, 1: 2724.6. Samples: 103598696. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:30:43,445][86177] Avg episode reward: [(0, '-501.820'), (1, '-523.130')] -[2023-11-28 05:30:43,704][87424] Updated weights for policy 0, policy_version 202527 (0.0008) -[2023-11-28 05:30:44,164][87426] Updated weights for policy 1, policy_version 202120 (0.0011) -[2023-11-28 05:30:44,547][87426] Updated weights for policy 1, policy_version 202130 (0.0012) -[2023-11-28 05:30:44,929][87426] Updated weights for policy 1, policy_version 202140 (0.0012) -[2023-11-28 05:30:46,236][87424] Updated weights for policy 0, policy_version 202537 (0.0008) -[2023-11-28 05:30:46,557][87426] Updated weights for policy 1, policy_version 202150 (0.0011) -[2023-11-28 05:30:46,615][87424] Updated weights for policy 0, policy_version 202547 (0.0011) -[2023-11-28 05:30:46,927][87426] Updated weights for policy 1, policy_version 202160 (0.0008) -[2023-11-28 05:30:47,003][87424] Updated weights for policy 0, policy_version 202557 (0.0012) -[2023-11-28 05:30:47,316][87426] Updated weights for policy 1, policy_version 202170 (0.0007) -[2023-11-28 05:30:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 103612416. Throughput: 0: 2703.4, 1: 2744.8. Samples: 103622516. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:30:48,445][86177] Avg episode reward: [(0, '-557.870'), (1, '-527.740')] -[2023-11-28 05:30:49,269][87424] Updated weights for policy 0, policy_version 202567 (0.0011) -[2023-11-28 05:30:49,410][87426] Updated weights for policy 1, policy_version 202180 (0.0009) -[2023-11-28 05:30:49,650][87424] Updated weights for policy 0, policy_version 202577 (0.0008) -[2023-11-28 05:30:49,789][87426] Updated weights for policy 1, policy_version 202190 (0.0009) -[2023-11-28 05:30:50,035][87424] Updated weights for policy 0, policy_version 202587 (0.0012) -[2023-11-28 05:30:50,170][87426] Updated weights for policy 1, policy_version 202200 (0.0008) -[2023-11-28 05:30:52,256][87424] Updated weights for policy 0, policy_version 202597 (0.0011) -[2023-11-28 05:30:52,544][87426] Updated weights for policy 1, policy_version 202210 (0.0009) -[2023-11-28 05:30:52,629][87424] Updated weights for policy 0, policy_version 202607 (0.0009) -[2023-11-28 05:30:52,922][87426] Updated weights for policy 1, policy_version 202220 (0.0011) -[2023-11-28 05:30:53,011][87424] Updated weights for policy 0, policy_version 202617 (0.0009) -[2023-11-28 05:30:53,304][87426] Updated weights for policy 1, policy_version 202230 (0.0010) -[2023-11-28 05:30:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 103636992. Throughput: 0: 2722.4, 1: 2732.9. Samples: 103655396. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:30:53,445][86177] Avg episode reward: [(0, '-561.500'), (1, '-539.180')] -[2023-11-28 05:30:53,685][87426] Updated weights for policy 1, policy_version 202240 (0.0011) -[2023-11-28 05:30:55,183][87424] Updated weights for policy 0, policy_version 202627 (0.0012) -[2023-11-28 05:30:55,545][87426] Updated weights for policy 1, policy_version 202250 (0.0010) -[2023-11-28 05:30:55,555][87424] Updated weights for policy 0, policy_version 202637 (0.0011) -[2023-11-28 05:30:55,918][87426] Updated weights for policy 1, policy_version 202260 (0.0011) -[2023-11-28 05:30:55,940][87424] Updated weights for policy 0, policy_version 202647 (0.0011) -[2023-11-28 05:30:56,302][87426] Updated weights for policy 1, policy_version 202270 (0.0012) -[2023-11-28 05:30:58,038][87426] Updated weights for policy 1, policy_version 202280 (0.0012) -[2023-11-28 05:30:58,279][87424] Updated weights for policy 0, policy_version 202657 (0.0009) -[2023-11-28 05:30:58,411][87426] Updated weights for policy 1, policy_version 202290 (0.0011) -[2023-11-28 05:30:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103661568. Throughput: 0: 2719.8, 1: 2753.9. Samples: 103680516. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:30:58,445][86177] Avg episode reward: [(0, '-571.720'), (1, '-540.870')] -[2023-11-28 05:30:58,658][87424] Updated weights for policy 0, policy_version 202667 (0.0010) -[2023-11-28 05:30:58,787][87426] Updated weights for policy 1, policy_version 202300 (0.0008) -[2023-11-28 05:30:59,042][87424] Updated weights for policy 0, policy_version 202677 (0.0011) -[2023-11-28 05:30:59,424][87424] Updated weights for policy 0, policy_version 202687 (0.0012) -[2023-11-28 05:31:01,069][87426] Updated weights for policy 1, policy_version 202310 (0.0025) -[2023-11-28 05:31:01,452][87426] Updated weights for policy 1, policy_version 202320 (0.0007) -[2023-11-28 05:31:01,542][87424] Updated weights for policy 0, policy_version 202697 (0.0010) -[2023-11-28 05:31:01,831][87426] Updated weights for policy 1, policy_version 202330 (0.0009) -[2023-11-28 05:31:01,937][87424] Updated weights for policy 0, policy_version 202707 (0.0011) -[2023-11-28 05:31:02,323][87424] Updated weights for policy 0, policy_version 202717 (0.0012) -[2023-11-28 05:31:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 103694336. Throughput: 0: 2713.9, 1: 2784.9. Samples: 103705296. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:31:03,445][86177] Avg episode reward: [(0, '-559.550'), (1, '-537.450')] -[2023-11-28 05:31:03,704][87426] Updated weights for policy 1, policy_version 202340 (0.0011) -[2023-11-28 05:31:04,073][87426] Updated weights for policy 1, policy_version 202350 (0.0010) -[2023-11-28 05:31:04,300][87424] Updated weights for policy 0, policy_version 202727 (0.0012) -[2023-11-28 05:31:04,458][87426] Updated weights for policy 1, policy_version 202360 (0.0008) -[2023-11-28 05:31:04,687][87424] Updated weights for policy 0, policy_version 202737 (0.0012) -[2023-11-28 05:31:05,075][87424] Updated weights for policy 0, policy_version 202747 (0.0012) -[2023-11-28 05:31:06,662][87426] Updated weights for policy 1, policy_version 202370 (0.0009) -[2023-11-28 05:31:07,040][87426] Updated weights for policy 1, policy_version 202380 (0.0012) -[2023-11-28 05:31:07,102][87424] Updated weights for policy 0, policy_version 202757 (0.0011) -[2023-11-28 05:31:07,422][87426] Updated weights for policy 1, policy_version 202390 (0.0012) -[2023-11-28 05:31:07,485][87424] Updated weights for policy 0, policy_version 202767 (0.0011) -[2023-11-28 05:31:07,799][87426] Updated weights for policy 1, policy_version 202400 (0.0011) -[2023-11-28 05:31:07,869][87424] Updated weights for policy 0, policy_version 202777 (0.0010) -[2023-11-28 05:31:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 103727104. Throughput: 0: 2715.5, 1: 2819.6. Samples: 103739516. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:31:08,445][86177] Avg episode reward: [(0, '-515.070'), (1, '-552.080')] -[2023-11-28 05:31:09,641][87426] Updated weights for policy 1, policy_version 202410 (0.0012) -[2023-11-28 05:31:09,944][87424] Updated weights for policy 0, policy_version 202787 (0.0012) -[2023-11-28 05:31:10,015][87426] Updated weights for policy 1, policy_version 202420 (0.0010) -[2023-11-28 05:31:10,319][87424] Updated weights for policy 0, policy_version 202797 (0.0012) -[2023-11-28 05:31:10,399][87426] Updated weights for policy 1, policy_version 202430 (0.0008) -[2023-11-28 05:31:10,703][87424] Updated weights for policy 0, policy_version 202807 (0.0011) -[2023-11-28 05:31:12,821][87426] Updated weights for policy 1, policy_version 202440 (0.0011) -[2023-11-28 05:31:12,988][87424] Updated weights for policy 0, policy_version 202817 (0.0009) -[2023-11-28 05:31:13,202][87426] Updated weights for policy 1, policy_version 202450 (0.0011) -[2023-11-28 05:31:13,369][87424] Updated weights for policy 0, policy_version 202827 (0.0010) -[2023-11-28 05:31:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103743488. Throughput: 0: 2715.5, 1: 2802.0. Samples: 103763772. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:31:13,445][86177] Avg episode reward: [(0, '-517.170'), (1, '-546.750')] -[2023-11-28 05:31:13,572][87426] Updated weights for policy 1, policy_version 202460 (0.0011) -[2023-11-28 05:31:13,745][87424] Updated weights for policy 0, policy_version 202837 (0.0009) -[2023-11-28 05:31:14,127][87424] Updated weights for policy 0, policy_version 202847 (0.0007) -[2023-11-28 05:31:15,828][87426] Updated weights for policy 1, policy_version 202470 (0.0011) -[2023-11-28 05:31:16,042][87424] Updated weights for policy 0, policy_version 202857 (0.0012) -[2023-11-28 05:31:16,204][87426] Updated weights for policy 1, policy_version 202480 (0.0011) -[2023-11-28 05:31:16,419][87424] Updated weights for policy 0, policy_version 202867 (0.0011) -[2023-11-28 05:31:16,589][87426] Updated weights for policy 1, policy_version 202490 (0.0009) -[2023-11-28 05:31:16,797][87424] Updated weights for policy 0, policy_version 202877 (0.0011) -[2023-11-28 05:31:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 103776256. Throughput: 0: 2706.7, 1: 2799.2. Samples: 103788688. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:31:18,445][86177] Avg episode reward: [(0, '-508.970'), (1, '-547.760')] -[2023-11-28 05:31:18,586][87426] Updated weights for policy 1, policy_version 202500 (0.0009) -[2023-11-28 05:31:18,946][87426] Updated weights for policy 1, policy_version 202510 (0.0011) -[2023-11-28 05:31:19,083][87424] Updated weights for policy 0, policy_version 202887 (0.0012) -[2023-11-28 05:31:19,330][87426] Updated weights for policy 1, policy_version 202520 (0.0008) -[2023-11-28 05:31:19,466][87424] Updated weights for policy 0, policy_version 202897 (0.0011) -[2023-11-28 05:31:19,846][87424] Updated weights for policy 0, policy_version 202907 (0.0012) -[2023-11-28 05:31:21,766][87426] Updated weights for policy 1, policy_version 202530 (0.0009) -[2023-11-28 05:31:21,927][87424] Updated weights for policy 0, policy_version 202917 (0.0011) -[2023-11-28 05:31:22,136][87426] Updated weights for policy 1, policy_version 202540 (0.0011) -[2023-11-28 05:31:22,312][87424] Updated weights for policy 0, policy_version 202927 (0.0012) -[2023-11-28 05:31:22,515][87426] Updated weights for policy 1, policy_version 202550 (0.0010) -[2023-11-28 05:31:22,695][87424] Updated weights for policy 0, policy_version 202937 (0.0010) -[2023-11-28 05:31:22,896][87426] Updated weights for policy 1, policy_version 202560 (0.0011) -[2023-11-28 05:31:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 103809024. Throughput: 0: 2704.5, 1: 2805.8. Samples: 103821572. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:31:23,445][86177] Avg episode reward: [(0, '-521.440'), (1, '-544.860')] -[2023-11-28 05:31:24,927][87426] Updated weights for policy 1, policy_version 202570 (0.0010) -[2023-11-28 05:31:24,928][87424] Updated weights for policy 0, policy_version 202947 (0.0010) -[2023-11-28 05:31:25,302][87424] Updated weights for policy 0, policy_version 202957 (0.0012) -[2023-11-28 05:31:25,307][87426] Updated weights for policy 1, policy_version 202580 (0.0007) -[2023-11-28 05:31:25,687][87426] Updated weights for policy 1, policy_version 202590 (0.0009) -[2023-11-28 05:31:25,694][87424] Updated weights for policy 0, policy_version 202967 (0.0011) -[2023-11-28 05:31:27,461][87426] Updated weights for policy 1, policy_version 202600 (0.0011) -[2023-11-28 05:31:27,847][87426] Updated weights for policy 1, policy_version 202610 (0.0011) -[2023-11-28 05:31:28,088][87424] Updated weights for policy 0, policy_version 202977 (0.0011) -[2023-11-28 05:31:28,217][87426] Updated weights for policy 1, policy_version 202620 (0.0007) -[2023-11-28 05:31:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 103833600. Throughput: 0: 2695.5, 1: 2812.0. Samples: 103846532. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:31:28,445][86177] Avg episode reward: [(0, '-517.700'), (1, '-531.750')] -[2023-11-28 05:31:28,475][87424] Updated weights for policy 0, policy_version 202987 (0.0007) -[2023-11-28 05:31:28,853][87424] Updated weights for policy 0, policy_version 202997 (0.0008) -[2023-11-28 05:31:29,233][87424] Updated weights for policy 0, policy_version 203007 (0.0008) -[2023-11-28 05:31:30,204][87426] Updated weights for policy 1, policy_version 202630 (0.0010) -[2023-11-28 05:31:30,580][87426] Updated weights for policy 1, policy_version 202640 (0.0011) -[2023-11-28 05:31:30,962][87426] Updated weights for policy 1, policy_version 202650 (0.0007) -[2023-11-28 05:31:31,258][87424] Updated weights for policy 0, policy_version 203017 (0.0010) -[2023-11-28 05:31:31,647][87424] Updated weights for policy 0, policy_version 203027 (0.0012) -[2023-11-28 05:31:32,018][87424] Updated weights for policy 0, policy_version 203037 (0.0011) -[2023-11-28 05:31:33,107][87426] Updated weights for policy 1, policy_version 202660 (0.0009) -[2023-11-28 05:31:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 103858176. Throughput: 0: 2710.6, 1: 2796.0. Samples: 103870312. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:31:33,445][86177] Avg episode reward: [(0, '-509.730'), (1, '-538.770')] -[2023-11-28 05:31:33,483][87426] Updated weights for policy 1, policy_version 202670 (0.0010) -[2023-11-28 05:31:33,860][87426] Updated weights for policy 1, policy_version 202680 (0.0007) -[2023-11-28 05:31:34,405][87424] Updated weights for policy 0, policy_version 203047 (0.0009) -[2023-11-28 05:31:34,795][87424] Updated weights for policy 0, policy_version 203057 (0.0008) -[2023-11-28 05:31:35,170][87424] Updated weights for policy 0, policy_version 203067 (0.0008) -[2023-11-28 05:31:36,081][87426] Updated weights for policy 1, policy_version 202690 (0.0007) -[2023-11-28 05:31:36,466][87426] Updated weights for policy 1, policy_version 202700 (0.0007) -[2023-11-28 05:31:36,847][87426] Updated weights for policy 1, policy_version 202710 (0.0008) -[2023-11-28 05:31:37,228][87426] Updated weights for policy 1, policy_version 202720 (0.0007) -[2023-11-28 05:31:37,654][87424] Updated weights for policy 0, policy_version 203077 (0.0009) -[2023-11-28 05:31:38,033][87424] Updated weights for policy 0, policy_version 203087 (0.0011) -[2023-11-28 05:31:38,427][87424] Updated weights for policy 0, policy_version 203097 (0.0008) -[2023-11-28 05:31:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103882752. Throughput: 0: 2690.4, 1: 2799.6. Samples: 103902448. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:31:38,445][86177] Avg episode reward: [(0, '-508.540'), (1, '-538.160')] -[2023-11-28 05:31:39,071][87426] Updated weights for policy 1, policy_version 202730 (0.0011) -[2023-11-28 05:31:39,454][87426] Updated weights for policy 1, policy_version 202740 (0.0012) -[2023-11-28 05:31:39,829][87426] Updated weights for policy 1, policy_version 202750 (0.0012) -[2023-11-28 05:31:40,925][87424] Updated weights for policy 0, policy_version 203107 (0.0010) -[2023-11-28 05:31:41,301][87424] Updated weights for policy 0, policy_version 203117 (0.0012) -[2023-11-28 05:31:41,696][87424] Updated weights for policy 0, policy_version 203127 (0.0011) -[2023-11-28 05:31:42,352][87426] Updated weights for policy 1, policy_version 202760 (0.0010) -[2023-11-28 05:31:42,734][87426] Updated weights for policy 1, policy_version 202770 (0.0011) -[2023-11-28 05:31:43,103][87426] Updated weights for policy 1, policy_version 202780 (0.0011) -[2023-11-28 05:31:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 103915520. Throughput: 0: 2686.4, 1: 2773.0. Samples: 103926188. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:31:43,445][86177] Avg episode reward: [(0, '-519.410'), (1, '-536.120')] -[2023-11-28 05:31:43,859][87424] Updated weights for policy 0, policy_version 203137 (0.0010) -[2023-11-28 05:31:44,246][87424] Updated weights for policy 0, policy_version 203147 (0.0012) -[2023-11-28 05:31:44,630][87424] Updated weights for policy 0, policy_version 203157 (0.0009) -[2023-11-28 05:31:45,013][87424] Updated weights for policy 0, policy_version 203167 (0.0009) -[2023-11-28 05:31:45,351][87426] Updated weights for policy 1, policy_version 202790 (0.0011) -[2023-11-28 05:31:45,735][87426] Updated weights for policy 1, policy_version 202800 (0.0011) -[2023-11-28 05:31:46,116][87426] Updated weights for policy 1, policy_version 202810 (0.0010) -[2023-11-28 05:31:47,220][87424] Updated weights for policy 0, policy_version 203177 (0.0008) -[2023-11-28 05:31:47,603][87424] Updated weights for policy 0, policy_version 203187 (0.0007) -[2023-11-28 05:31:47,993][87424] Updated weights for policy 0, policy_version 203197 (0.0007) -[2023-11-28 05:31:48,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 103940096. Throughput: 0: 2670.0, 1: 2766.3. Samples: 103949932. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:31:48,446][86177] Avg episode reward: [(0, '-551.700'), (1, '-530.320')] -[2023-11-28 05:31:48,550][87426] Updated weights for policy 1, policy_version 202820 (0.0009) -[2023-11-28 05:31:48,927][87426] Updated weights for policy 1, policy_version 202830 (0.0011) -[2023-11-28 05:31:49,306][87426] Updated weights for policy 1, policy_version 202840 (0.0011) -[2023-11-28 05:31:50,438][87424] Updated weights for policy 0, policy_version 203207 (0.0009) -[2023-11-28 05:31:50,821][87424] Updated weights for policy 0, policy_version 203217 (0.0008) -[2023-11-28 05:31:51,203][87424] Updated weights for policy 0, policy_version 203227 (0.0010) -[2023-11-28 05:31:51,461][87426] Updated weights for policy 1, policy_version 202850 (0.0011) -[2023-11-28 05:31:51,837][87426] Updated weights for policy 1, policy_version 202860 (0.0011) -[2023-11-28 05:31:52,215][87426] Updated weights for policy 1, policy_version 202870 (0.0011) -[2023-11-28 05:31:52,601][87426] Updated weights for policy 1, policy_version 202880 (0.0012) -[2023-11-28 05:31:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 103964672. Throughput: 0: 2629.3, 1: 2739.6. Samples: 103981112. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:31:53,445][86177] Avg episode reward: [(0, '-552.570'), (1, '-528.330')] -[2023-11-28 05:31:53,691][87424] Updated weights for policy 0, policy_version 203237 (0.0011) -[2023-11-28 05:31:54,070][87424] Updated weights for policy 0, policy_version 203247 (0.0010) -[2023-11-28 05:31:54,452][87424] Updated weights for policy 0, policy_version 203257 (0.0009) -[2023-11-28 05:31:54,756][87426] Updated weights for policy 1, policy_version 202890 (0.0008) -[2023-11-28 05:31:55,128][87426] Updated weights for policy 1, policy_version 202900 (0.0009) -[2023-11-28 05:31:55,510][87426] Updated weights for policy 1, policy_version 202910 (0.0011) -[2023-11-28 05:31:57,066][87424] Updated weights for policy 0, policy_version 203267 (0.0008) -[2023-11-28 05:31:57,382][87426] Updated weights for policy 1, policy_version 202920 (0.0011) -[2023-11-28 05:31:57,454][87424] Updated weights for policy 0, policy_version 203277 (0.0010) -[2023-11-28 05:31:57,756][87426] Updated weights for policy 1, policy_version 202930 (0.0011) -[2023-11-28 05:31:57,838][87424] Updated weights for policy 0, policy_version 203287 (0.0011) -[2023-11-28 05:31:58,139][87426] Updated weights for policy 1, policy_version 202940 (0.0011) -[2023-11-28 05:31:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 103997440. Throughput: 0: 2618.6, 1: 2750.5. Samples: 104005380. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:31:58,445][86177] Avg episode reward: [(0, '-550.960'), (1, '-529.350')] -[2023-11-28 05:31:59,803][87424] Updated weights for policy 0, policy_version 203297 (0.0010) -[2023-11-28 05:31:59,849][87426] Updated weights for policy 1, policy_version 202950 (0.0012) -[2023-11-28 05:32:00,177][87424] Updated weights for policy 0, policy_version 203307 (0.0011) -[2023-11-28 05:32:00,219][87426] Updated weights for policy 1, policy_version 202960 (0.0009) -[2023-11-28 05:32:00,563][87424] Updated weights for policy 0, policy_version 203317 (0.0010) -[2023-11-28 05:32:00,606][87426] Updated weights for policy 1, policy_version 202970 (0.0011) -[2023-11-28 05:32:00,938][87424] Updated weights for policy 0, policy_version 203327 (0.0011) -[2023-11-28 05:32:03,061][87426] Updated weights for policy 1, policy_version 202980 (0.0010) -[2023-11-28 05:32:03,121][87424] Updated weights for policy 0, policy_version 203337 (0.0011) -[2023-11-28 05:32:03,437][87426] Updated weights for policy 1, policy_version 202990 (0.0010) -[2023-11-28 05:32:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104013824. Throughput: 0: 2635.6, 1: 2741.5. Samples: 104030656. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:03,445][86177] Avg episode reward: [(0, '-541.380'), (1, '-530.730')] -[2023-11-28 05:32:03,507][87424] Updated weights for policy 0, policy_version 203347 (0.0012) -[2023-11-28 05:32:03,812][87426] Updated weights for policy 1, policy_version 203000 (0.0009) -[2023-11-28 05:32:03,877][87424] Updated weights for policy 0, policy_version 203357 (0.0008) -[2023-11-28 05:32:05,926][87424] Updated weights for policy 0, policy_version 203367 (0.0007) -[2023-11-28 05:32:06,177][87426] Updated weights for policy 1, policy_version 203010 (0.0008) -[2023-11-28 05:32:06,304][87424] Updated weights for policy 0, policy_version 203377 (0.0009) -[2023-11-28 05:32:06,552][87426] Updated weights for policy 1, policy_version 203020 (0.0007) -[2023-11-28 05:32:06,690][87424] Updated weights for policy 0, policy_version 203387 (0.0008) -[2023-11-28 05:32:06,932][87426] Updated weights for policy 1, policy_version 203030 (0.0008) -[2023-11-28 05:32:07,308][87426] Updated weights for policy 1, policy_version 203040 (0.0007) -[2023-11-28 05:32:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104046592. Throughput: 0: 2638.1, 1: 2738.7. Samples: 104063528. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:08,445][86177] Avg episode reward: [(0, '-501.100'), (1, '-531.690')] -[2023-11-28 05:32:09,088][87424] Updated weights for policy 0, policy_version 203397 (0.0010) -[2023-11-28 05:32:09,156][87426] Updated weights for policy 1, policy_version 203050 (0.0011) -[2023-11-28 05:32:09,461][87424] Updated weights for policy 0, policy_version 203407 (0.0010) -[2023-11-28 05:32:09,526][87426] Updated weights for policy 1, policy_version 203060 (0.0011) -[2023-11-28 05:32:09,845][87424] Updated weights for policy 0, policy_version 203417 (0.0009) -[2023-11-28 05:32:09,901][87426] Updated weights for policy 1, policy_version 203070 (0.0011) -[2023-11-28 05:32:11,694][87424] Updated weights for policy 0, policy_version 203427 (0.0010) -[2023-11-28 05:32:12,076][87424] Updated weights for policy 0, policy_version 203437 (0.0010) -[2023-11-28 05:32:12,255][87426] Updated weights for policy 1, policy_version 203080 (0.0010) -[2023-11-28 05:32:12,469][87424] Updated weights for policy 0, policy_version 203447 (0.0010) -[2023-11-28 05:32:12,632][87426] Updated weights for policy 1, policy_version 203090 (0.0007) -[2023-11-28 05:32:13,011][87426] Updated weights for policy 1, policy_version 203100 (0.0010) -[2023-11-28 05:32:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5470.6). Total num frames: 104079360. Throughput: 0: 2640.3, 1: 2723.9. Samples: 104087920. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:13,446][86177] Avg episode reward: [(0, '-499.230'), (1, '-553.090')] -[2023-11-28 05:32:14,967][87426] Updated weights for policy 1, policy_version 203110 (0.0008) -[2023-11-28 05:32:14,968][87424] Updated weights for policy 0, policy_version 203457 (0.0011) -[2023-11-28 05:32:15,350][87426] Updated weights for policy 1, policy_version 203120 (0.0010) -[2023-11-28 05:32:15,361][87424] Updated weights for policy 0, policy_version 203467 (0.0009) -[2023-11-28 05:32:15,732][87426] Updated weights for policy 1, policy_version 203130 (0.0011) -[2023-11-28 05:32:15,746][87424] Updated weights for policy 0, policy_version 203477 (0.0011) -[2023-11-28 05:32:16,128][87424] Updated weights for policy 0, policy_version 203487 (0.0012) -[2023-11-28 05:32:17,599][87426] Updated weights for policy 1, policy_version 203140 (0.0010) -[2023-11-28 05:32:17,977][87426] Updated weights for policy 1, policy_version 203150 (0.0011) -[2023-11-28 05:32:18,047][87424] Updated weights for policy 0, policy_version 203497 (0.0011) -[2023-11-28 05:32:18,353][87426] Updated weights for policy 1, policy_version 203160 (0.0010) -[2023-11-28 05:32:18,430][87424] Updated weights for policy 0, policy_version 203507 (0.0012) -[2023-11-28 05:32:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104095744. Throughput: 0: 2630.8, 1: 2741.5. Samples: 104112064. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:18,445][86177] Avg episode reward: [(0, '-496.710'), (1, '-552.490')] -[2023-11-28 05:32:18,657][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000203168_52011008.pth... -[2023-11-28 05:32:18,702][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000200608_51355648.pth -[2023-11-28 05:32:18,709][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000203168_52011008.pth -[2023-11-28 05:32:18,813][87424] Updated weights for policy 0, policy_version 203517 (0.0012) -[2023-11-28 05:32:18,924][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000203520_52101120.pth... -[2023-11-28 05:32:18,971][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000200960_51445760.pth -[2023-11-28 05:32:18,978][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000203520_52101120.pth -[2023-11-28 05:32:20,654][87424] Updated weights for policy 0, policy_version 203527 (0.0012) -[2023-11-28 05:32:20,944][87426] Updated weights for policy 1, policy_version 203170 (0.0008) -[2023-11-28 05:32:21,029][87424] Updated weights for policy 0, policy_version 203537 (0.0011) -[2023-11-28 05:32:21,318][87426] Updated weights for policy 1, policy_version 203180 (0.0009) -[2023-11-28 05:32:21,412][87424] Updated weights for policy 0, policy_version 203547 (0.0012) -[2023-11-28 05:32:21,697][87426] Updated weights for policy 1, policy_version 203190 (0.0009) -[2023-11-28 05:32:22,081][87426] Updated weights for policy 1, policy_version 203200 (0.0010) -[2023-11-28 05:32:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104128512. Throughput: 0: 2661.1, 1: 2717.7. Samples: 104144492. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:23,445][86177] Avg episode reward: [(0, '-496.540'), (1, '-549.800')] -[2023-11-28 05:32:23,923][87424] Updated weights for policy 0, policy_version 203557 (0.0011) -[2023-11-28 05:32:24,311][87424] Updated weights for policy 0, policy_version 203567 (0.0007) -[2023-11-28 05:32:24,332][87426] Updated weights for policy 1, policy_version 203210 (0.0008) -[2023-11-28 05:32:24,694][87424] Updated weights for policy 0, policy_version 203577 (0.0008) -[2023-11-28 05:32:24,713][87426] Updated weights for policy 1, policy_version 203220 (0.0008) -[2023-11-28 05:32:25,094][87426] Updated weights for policy 1, policy_version 203230 (0.0009) -[2023-11-28 05:32:26,982][87424] Updated weights for policy 0, policy_version 203587 (0.0011) -[2023-11-28 05:32:27,354][87426] Updated weights for policy 1, policy_version 203240 (0.0008) -[2023-11-28 05:32:27,361][87424] Updated weights for policy 0, policy_version 203597 (0.0009) -[2023-11-28 05:32:27,736][87426] Updated weights for policy 1, policy_version 203250 (0.0007) -[2023-11-28 05:32:27,742][87424] Updated weights for policy 0, policy_version 203607 (0.0007) -[2023-11-28 05:32:28,113][87426] Updated weights for policy 1, policy_version 203260 (0.0007) -[2023-11-28 05:32:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 104161280. Throughput: 0: 2668.7, 1: 2750.1. Samples: 104170036. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:28,445][86177] Avg episode reward: [(0, '-497.330'), (1, '-538.150')] -[2023-11-28 05:32:29,824][87424] Updated weights for policy 0, policy_version 203617 (0.0008) -[2023-11-28 05:32:30,203][87424] Updated weights for policy 0, policy_version 203627 (0.0011) -[2023-11-28 05:32:30,400][87426] Updated weights for policy 1, policy_version 203270 (0.0008) -[2023-11-28 05:32:30,585][87424] Updated weights for policy 0, policy_version 203637 (0.0010) -[2023-11-28 05:32:30,780][87426] Updated weights for policy 1, policy_version 203280 (0.0010) -[2023-11-28 05:32:30,962][87424] Updated weights for policy 0, policy_version 203647 (0.0010) -[2023-11-28 05:32:31,163][87426] Updated weights for policy 1, policy_version 203290 (0.0012) -[2023-11-28 05:32:33,139][87426] Updated weights for policy 1, policy_version 203300 (0.0011) -[2023-11-28 05:32:33,420][87424] Updated weights for policy 0, policy_version 203657 (0.0012) -[2023-11-28 05:32:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104177664. Throughput: 0: 2676.6, 1: 2744.6. Samples: 104193884. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:33,445][86177] Avg episode reward: [(0, '-495.410'), (1, '-515.390')] -[2023-11-28 05:32:33,515][87426] Updated weights for policy 1, policy_version 203310 (0.0009) -[2023-11-28 05:32:33,803][87424] Updated weights for policy 0, policy_version 203667 (0.0011) -[2023-11-28 05:32:33,897][87426] Updated weights for policy 1, policy_version 203320 (0.0008) -[2023-11-28 05:32:34,201][87424] Updated weights for policy 0, policy_version 203677 (0.0011) -[2023-11-28 05:32:36,087][87426] Updated weights for policy 1, policy_version 203330 (0.0008) -[2023-11-28 05:32:36,471][87426] Updated weights for policy 1, policy_version 203340 (0.0011) -[2023-11-28 05:32:36,741][87424] Updated weights for policy 0, policy_version 203687 (0.0009) -[2023-11-28 05:32:36,845][87426] Updated weights for policy 1, policy_version 203350 (0.0010) -[2023-11-28 05:32:37,122][87424] Updated weights for policy 0, policy_version 203697 (0.0008) -[2023-11-28 05:32:37,222][87426] Updated weights for policy 1, policy_version 203360 (0.0011) -[2023-11-28 05:32:37,508][87424] Updated weights for policy 0, policy_version 203707 (0.0012) -[2023-11-28 05:32:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 104210432. Throughput: 0: 2705.3, 1: 2747.3. Samples: 104226480. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:38,445][86177] Avg episode reward: [(0, '-504.100'), (1, '-512.510')] -[2023-11-28 05:32:39,615][87424] Updated weights for policy 0, policy_version 203717 (0.0012) -[2023-11-28 05:32:39,681][87426] Updated weights for policy 1, policy_version 203370 (0.0012) -[2023-11-28 05:32:39,996][87424] Updated weights for policy 0, policy_version 203727 (0.0010) -[2023-11-28 05:32:40,063][87426] Updated weights for policy 1, policy_version 203380 (0.0011) -[2023-11-28 05:32:40,384][87424] Updated weights for policy 0, policy_version 203737 (0.0008) -[2023-11-28 05:32:40,441][87426] Updated weights for policy 1, policy_version 203390 (0.0012) -[2023-11-28 05:32:42,747][87424] Updated weights for policy 0, policy_version 203747 (0.0010) -[2023-11-28 05:32:43,022][87426] Updated weights for policy 1, policy_version 203400 (0.0011) -[2023-11-28 05:32:43,129][87424] Updated weights for policy 0, policy_version 203757 (0.0011) -[2023-11-28 05:32:43,400][87426] Updated weights for policy 1, policy_version 203410 (0.0012) -[2023-11-28 05:32:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 104226816. Throughput: 0: 2721.1, 1: 2731.3. Samples: 104250736. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:43,445][86177] Avg episode reward: [(0, '-503.200'), (1, '-517.950')] -[2023-11-28 05:32:43,520][87424] Updated weights for policy 0, policy_version 203767 (0.0009) -[2023-11-28 05:32:43,784][87426] Updated weights for policy 1, policy_version 203420 (0.0011) -[2023-11-28 05:32:45,517][87424] Updated weights for policy 0, policy_version 203777 (0.0008) -[2023-11-28 05:32:45,631][87426] Updated weights for policy 1, policy_version 203430 (0.0009) -[2023-11-28 05:32:45,897][87424] Updated weights for policy 0, policy_version 203787 (0.0012) -[2023-11-28 05:32:46,018][87426] Updated weights for policy 1, policy_version 203440 (0.0011) -[2023-11-28 05:32:46,281][87424] Updated weights for policy 0, policy_version 203797 (0.0012) -[2023-11-28 05:32:46,394][87426] Updated weights for policy 1, policy_version 203450 (0.0011) -[2023-11-28 05:32:46,671][87424] Updated weights for policy 0, policy_version 203807 (0.0011) -[2023-11-28 05:32:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5443.0). Total num frames: 104259584. Throughput: 0: 2702.4, 1: 2735.0. Samples: 104275340. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:48,445][86177] Avg episode reward: [(0, '-501.800'), (1, '-526.680')] -[2023-11-28 05:32:48,489][87424] Updated weights for policy 0, policy_version 203817 (0.0012) -[2023-11-28 05:32:48,871][87424] Updated weights for policy 0, policy_version 203827 (0.0012) -[2023-11-28 05:32:48,890][87426] Updated weights for policy 1, policy_version 203460 (0.0009) -[2023-11-28 05:32:49,262][87424] Updated weights for policy 0, policy_version 203837 (0.0012) -[2023-11-28 05:32:49,264][87426] Updated weights for policy 1, policy_version 203470 (0.0011) -[2023-11-28 05:32:49,636][87426] Updated weights for policy 1, policy_version 203480 (0.0011) -[2023-11-28 05:32:51,023][87424] Updated weights for policy 0, policy_version 203847 (0.0010) -[2023-11-28 05:32:51,402][87424] Updated weights for policy 0, policy_version 203857 (0.0009) -[2023-11-28 05:32:51,794][87424] Updated weights for policy 0, policy_version 203867 (0.0012) -[2023-11-28 05:32:51,903][87426] Updated weights for policy 1, policy_version 203490 (0.0012) -[2023-11-28 05:32:52,280][87426] Updated weights for policy 1, policy_version 203500 (0.0010) -[2023-11-28 05:32:52,659][87426] Updated weights for policy 1, policy_version 203510 (0.0008) -[2023-11-28 05:32:53,039][87426] Updated weights for policy 1, policy_version 203520 (0.0009) -[2023-11-28 05:32:53,445][86177] Fps is (10 sec: 6553.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 104292352. Throughput: 0: 2728.1, 1: 2703.3. Samples: 104307948. Policy #0 lag: (min: 26.0, avg: 50.8, max: 63.0) -[2023-11-28 05:32:53,446][86177] Avg episode reward: [(0, '-504.970'), (1, '-537.540')] -[2023-11-28 05:32:53,840][87424] Updated weights for policy 0, policy_version 203877 (0.0012) -[2023-11-28 05:32:54,218][87424] Updated weights for policy 0, policy_version 203887 (0.0012) -[2023-11-28 05:32:54,600][87424] Updated weights for policy 0, policy_version 203897 (0.0012) -[2023-11-28 05:32:55,087][87426] Updated weights for policy 1, policy_version 203530 (0.0011) -[2023-11-28 05:32:55,458][87426] Updated weights for policy 1, policy_version 203540 (0.0012) -[2023-11-28 05:32:55,840][87426] Updated weights for policy 1, policy_version 203550 (0.0012) -[2023-11-28 05:32:57,118][87424] Updated weights for policy 0, policy_version 203907 (0.0011) -[2023-11-28 05:32:57,488][87424] Updated weights for policy 0, policy_version 203917 (0.0012) -[2023-11-28 05:32:57,876][87424] Updated weights for policy 0, policy_version 203927 (0.0012) -[2023-11-28 05:32:58,265][87426] Updated weights for policy 1, policy_version 203560 (0.0008) -[2023-11-28 05:32:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104316928. Throughput: 0: 2723.9, 1: 2723.7. Samples: 104333064. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:32:58,445][86177] Avg episode reward: [(0, '-501.280'), (1, '-573.400')] -[2023-11-28 05:32:58,647][87426] Updated weights for policy 1, policy_version 203570 (0.0007) -[2023-11-28 05:32:59,036][87426] Updated weights for policy 1, policy_version 203580 (0.0009) -[2023-11-28 05:33:00,205][87424] Updated weights for policy 0, policy_version 203937 (0.0011) -[2023-11-28 05:33:00,586][87424] Updated weights for policy 0, policy_version 203947 (0.0012) -[2023-11-28 05:33:00,966][87426] Updated weights for policy 1, policy_version 203590 (0.0011) -[2023-11-28 05:33:00,973][87424] Updated weights for policy 0, policy_version 203957 (0.0012) -[2023-11-28 05:33:01,349][87424] Updated weights for policy 0, policy_version 203967 (0.0011) -[2023-11-28 05:33:01,352][87426] Updated weights for policy 1, policy_version 203600 (0.0012) -[2023-11-28 05:33:01,722][87426] Updated weights for policy 1, policy_version 203610 (0.0012) -[2023-11-28 05:33:03,089][87424] Updated weights for policy 0, policy_version 203977 (0.0008) -[2023-11-28 05:33:03,444][86177] Fps is (10 sec: 4915.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 104341504. Throughput: 0: 2758.0, 1: 2713.2. Samples: 104358268. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:03,445][86177] Avg episode reward: [(0, '-500.630'), (1, '-564.920')] -[2023-11-28 05:33:03,474][87424] Updated weights for policy 0, policy_version 203987 (0.0008) -[2023-11-28 05:33:03,857][87424] Updated weights for policy 0, policy_version 203997 (0.0007) -[2023-11-28 05:33:03,958][87426] Updated weights for policy 1, policy_version 203620 (0.0011) -[2023-11-28 05:33:04,329][87426] Updated weights for policy 1, policy_version 203630 (0.0007) -[2023-11-28 05:33:04,724][87426] Updated weights for policy 1, policy_version 203640 (0.0008) -[2023-11-28 05:33:05,760][87424] Updated weights for policy 0, policy_version 204007 (0.0008) -[2023-11-28 05:33:06,146][87424] Updated weights for policy 0, policy_version 204017 (0.0007) -[2023-11-28 05:33:06,523][87424] Updated weights for policy 0, policy_version 204027 (0.0008) -[2023-11-28 05:33:06,589][87426] Updated weights for policy 1, policy_version 203650 (0.0008) -[2023-11-28 05:33:06,970][87426] Updated weights for policy 1, policy_version 203660 (0.0010) -[2023-11-28 05:33:07,350][87426] Updated weights for policy 1, policy_version 203670 (0.0011) -[2023-11-28 05:33:07,720][87426] Updated weights for policy 1, policy_version 203680 (0.0010) -[2023-11-28 05:33:08,415][87424] Updated weights for policy 0, policy_version 204037 (0.0008) -[2023-11-28 05:33:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 104374272. Throughput: 0: 2759.6, 1: 2714.8. Samples: 104390844. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:08,445][86177] Avg episode reward: [(0, '-501.010'), (1, '-567.440')] -[2023-11-28 05:33:08,806][87424] Updated weights for policy 0, policy_version 204047 (0.0008) -[2023-11-28 05:33:09,191][87424] Updated weights for policy 0, policy_version 204057 (0.0012) -[2023-11-28 05:33:09,560][87426] Updated weights for policy 1, policy_version 203690 (0.0009) -[2023-11-28 05:33:09,942][87426] Updated weights for policy 1, policy_version 203700 (0.0009) -[2023-11-28 05:33:10,331][87426] Updated weights for policy 1, policy_version 203710 (0.0009) -[2023-11-28 05:33:11,751][87424] Updated weights for policy 0, policy_version 204067 (0.0010) -[2023-11-28 05:33:12,116][87424] Updated weights for policy 0, policy_version 204077 (0.0012) -[2023-11-28 05:33:12,504][87424] Updated weights for policy 0, policy_version 204087 (0.0012) -[2023-11-28 05:33:12,700][87426] Updated weights for policy 1, policy_version 203720 (0.0010) -[2023-11-28 05:33:13,075][87426] Updated weights for policy 1, policy_version 203730 (0.0012) -[2023-11-28 05:33:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104398848. Throughput: 0: 2744.5, 1: 2676.0. Samples: 104413956. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:13,445][86177] Avg episode reward: [(0, '-495.440'), (1, '-570.200')] -[2023-11-28 05:33:13,458][87426] Updated weights for policy 1, policy_version 203740 (0.0012) -[2023-11-28 05:33:14,399][87424] Updated weights for policy 0, policy_version 204097 (0.0011) -[2023-11-28 05:33:14,793][87424] Updated weights for policy 0, policy_version 204107 (0.0007) -[2023-11-28 05:33:15,170][87424] Updated weights for policy 0, policy_version 204117 (0.0008) -[2023-11-28 05:33:15,558][87424] Updated weights for policy 0, policy_version 204127 (0.0011) -[2023-11-28 05:33:15,952][87426] Updated weights for policy 1, policy_version 203750 (0.0012) -[2023-11-28 05:33:16,337][87426] Updated weights for policy 1, policy_version 203760 (0.0012) -[2023-11-28 05:33:16,717][87426] Updated weights for policy 1, policy_version 203770 (0.0012) -[2023-11-28 05:33:17,797][87424] Updated weights for policy 0, policy_version 204137 (0.0009) -[2023-11-28 05:33:18,180][87424] Updated weights for policy 0, policy_version 204147 (0.0007) -[2023-11-28 05:33:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 104423424. Throughput: 0: 2769.2, 1: 2656.4. Samples: 104438032. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:18,445][86177] Avg episode reward: [(0, '-497.230'), (1, '-539.310')] -[2023-11-28 05:33:18,561][87424] Updated weights for policy 0, policy_version 204157 (0.0008) -[2023-11-28 05:33:18,706][87426] Updated weights for policy 1, policy_version 203780 (0.0011) -[2023-11-28 05:33:19,078][87426] Updated weights for policy 1, policy_version 203790 (0.0012) -[2023-11-28 05:33:19,447][87426] Updated weights for policy 1, policy_version 203800 (0.0012) -[2023-11-28 05:33:20,997][87424] Updated weights for policy 0, policy_version 204167 (0.0011) -[2023-11-28 05:33:21,378][87424] Updated weights for policy 0, policy_version 204177 (0.0012) -[2023-11-28 05:33:21,760][87424] Updated weights for policy 0, policy_version 204187 (0.0011) -[2023-11-28 05:33:21,863][87426] Updated weights for policy 1, policy_version 203810 (0.0012) -[2023-11-28 05:33:22,233][87426] Updated weights for policy 1, policy_version 203820 (0.0012) -[2023-11-28 05:33:22,611][87426] Updated weights for policy 1, policy_version 203830 (0.0012) -[2023-11-28 05:33:22,988][87426] Updated weights for policy 1, policy_version 203840 (0.0012) -[2023-11-28 05:33:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 104456192. Throughput: 0: 2756.1, 1: 2659.2. Samples: 104470168. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:23,445][86177] Avg episode reward: [(0, '-499.530'), (1, '-557.290')] -[2023-11-28 05:33:24,010][87424] Updated weights for policy 0, policy_version 204197 (0.0010) -[2023-11-28 05:33:24,408][87424] Updated weights for policy 0, policy_version 204207 (0.0010) -[2023-11-28 05:33:24,798][87424] Updated weights for policy 0, policy_version 204217 (0.0011) -[2023-11-28 05:33:25,024][87426] Updated weights for policy 1, policy_version 203850 (0.0011) -[2023-11-28 05:33:25,395][87426] Updated weights for policy 1, policy_version 203860 (0.0012) -[2023-11-28 05:33:25,766][87426] Updated weights for policy 1, policy_version 203870 (0.0012) -[2023-11-28 05:33:26,596][87424] Updated weights for policy 0, policy_version 204227 (0.0011) -[2023-11-28 05:33:26,976][87424] Updated weights for policy 0, policy_version 204237 (0.0008) -[2023-11-28 05:33:27,363][87424] Updated weights for policy 0, policy_version 204247 (0.0008) -[2023-11-28 05:33:28,282][87426] Updated weights for policy 1, policy_version 203880 (0.0012) -[2023-11-28 05:33:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104480768. Throughput: 0: 2742.6, 1: 2665.2. Samples: 104494084. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:28,445][86177] Avg episode reward: [(0, '-500.780'), (1, '-566.270')] -[2023-11-28 05:33:28,655][87426] Updated weights for policy 1, policy_version 203890 (0.0012) -[2023-11-28 05:33:29,033][87426] Updated weights for policy 1, policy_version 203900 (0.0010) -[2023-11-28 05:33:29,723][87424] Updated weights for policy 0, policy_version 204257 (0.0008) -[2023-11-28 05:33:30,099][87424] Updated weights for policy 0, policy_version 204267 (0.0012) -[2023-11-28 05:33:30,486][87424] Updated weights for policy 0, policy_version 204277 (0.0012) -[2023-11-28 05:33:30,859][87424] Updated weights for policy 0, policy_version 204287 (0.0012) -[2023-11-28 05:33:31,599][87426] Updated weights for policy 1, policy_version 203910 (0.0008) -[2023-11-28 05:33:31,970][87426] Updated weights for policy 1, policy_version 203920 (0.0010) -[2023-11-28 05:33:32,359][87426] Updated weights for policy 1, policy_version 203930 (0.0008) -[2023-11-28 05:33:33,283][87424] Updated weights for policy 0, policy_version 204297 (0.0009) -[2023-11-28 05:33:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 104505344. Throughput: 0: 2744.0, 1: 2652.5. Samples: 104518180. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:33,445][86177] Avg episode reward: [(0, '-524.990'), (1, '-565.300')] -[2023-11-28 05:33:33,668][87424] Updated weights for policy 0, policy_version 204307 (0.0007) -[2023-11-28 05:33:34,059][87424] Updated weights for policy 0, policy_version 204317 (0.0009) -[2023-11-28 05:33:34,757][87426] Updated weights for policy 1, policy_version 203940 (0.0008) -[2023-11-28 05:33:35,143][87426] Updated weights for policy 1, policy_version 203950 (0.0007) -[2023-11-28 05:33:35,509][87426] Updated weights for policy 1, policy_version 203960 (0.0007) -[2023-11-28 05:33:35,728][87424] Updated weights for policy 0, policy_version 204327 (0.0008) -[2023-11-28 05:33:36,112][87424] Updated weights for policy 0, policy_version 204337 (0.0007) -[2023-11-28 05:33:36,497][87424] Updated weights for policy 0, policy_version 204347 (0.0007) -[2023-11-28 05:33:37,324][87426] Updated weights for policy 1, policy_version 203970 (0.0009) -[2023-11-28 05:33:37,697][87426] Updated weights for policy 1, policy_version 203980 (0.0012) -[2023-11-28 05:33:38,079][87426] Updated weights for policy 1, policy_version 203990 (0.0009) -[2023-11-28 05:33:38,358][87424] Updated weights for policy 0, policy_version 204357 (0.0009) -[2023-11-28 05:33:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104529920. Throughput: 0: 2722.9, 1: 2671.3. Samples: 104550684. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:38,445][86177] Avg episode reward: [(0, '-525.280'), (1, '-533.100')] -[2023-11-28 05:33:38,466][87426] Updated weights for policy 1, policy_version 204000 (0.0008) -[2023-11-28 05:33:38,743][87424] Updated weights for policy 0, policy_version 204367 (0.0011) -[2023-11-28 05:33:39,133][87424] Updated weights for policy 0, policy_version 204377 (0.0011) -[2023-11-28 05:33:41,025][87426] Updated weights for policy 1, policy_version 204010 (0.0012) -[2023-11-28 05:33:41,399][87424] Updated weights for policy 0, policy_version 204387 (0.0011) -[2023-11-28 05:33:41,404][87426] Updated weights for policy 1, policy_version 204020 (0.0012) -[2023-11-28 05:33:41,785][87426] Updated weights for policy 1, policy_version 204030 (0.0011) -[2023-11-28 05:33:41,790][87424] Updated weights for policy 0, policy_version 204397 (0.0011) -[2023-11-28 05:33:42,179][87424] Updated weights for policy 0, policy_version 204407 (0.0012) -[2023-11-28 05:33:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 104562688. Throughput: 0: 2716.3, 1: 2653.9. Samples: 104574720. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:43,445][86177] Avg episode reward: [(0, '-544.600'), (1, '-524.180')] -[2023-11-28 05:33:43,959][87426] Updated weights for policy 1, policy_version 204040 (0.0011) -[2023-11-28 05:33:44,336][87426] Updated weights for policy 1, policy_version 204050 (0.0012) -[2023-11-28 05:33:44,538][87424] Updated weights for policy 0, policy_version 204417 (0.0011) -[2023-11-28 05:33:44,721][87426] Updated weights for policy 1, policy_version 204060 (0.0011) -[2023-11-28 05:33:44,915][87424] Updated weights for policy 0, policy_version 204427 (0.0012) -[2023-11-28 05:33:45,306][87424] Updated weights for policy 0, policy_version 204437 (0.0011) -[2023-11-28 05:33:45,681][87424] Updated weights for policy 0, policy_version 204447 (0.0010) -[2023-11-28 05:33:46,683][87426] Updated weights for policy 1, policy_version 204070 (0.0012) -[2023-11-28 05:33:47,062][87426] Updated weights for policy 1, policy_version 204080 (0.0012) -[2023-11-28 05:33:47,443][87426] Updated weights for policy 1, policy_version 204090 (0.0012) -[2023-11-28 05:33:48,218][87424] Updated weights for policy 0, policy_version 204457 (0.0008) -[2023-11-28 05:33:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 104587264. Throughput: 0: 2690.6, 1: 2656.7. Samples: 104598896. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:48,445][86177] Avg episode reward: [(0, '-550.240'), (1, '-530.130')] -[2023-11-28 05:33:48,617][87424] Updated weights for policy 0, policy_version 204467 (0.0008) -[2023-11-28 05:33:48,998][87424] Updated weights for policy 0, policy_version 204477 (0.0009) -[2023-11-28 05:33:49,463][87426] Updated weights for policy 1, policy_version 204100 (0.0011) -[2023-11-28 05:33:49,837][87426] Updated weights for policy 1, policy_version 204110 (0.0012) -[2023-11-28 05:33:50,216][87426] Updated weights for policy 1, policy_version 204120 (0.0012) -[2023-11-28 05:33:51,318][87424] Updated weights for policy 0, policy_version 204487 (0.0011) -[2023-11-28 05:33:51,701][87424] Updated weights for policy 0, policy_version 204497 (0.0012) -[2023-11-28 05:33:52,078][87424] Updated weights for policy 0, policy_version 204507 (0.0011) -[2023-11-28 05:33:52,482][87426] Updated weights for policy 1, policy_version 204130 (0.0012) -[2023-11-28 05:33:52,864][87426] Updated weights for policy 1, policy_version 204140 (0.0009) -[2023-11-28 05:33:53,251][87426] Updated weights for policy 1, policy_version 204150 (0.0011) -[2023-11-28 05:33:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.9, 300 sec: 5442.8). Total num frames: 104611840. Throughput: 0: 2646.3, 1: 2668.8. Samples: 104630024. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:53,445][86177] Avg episode reward: [(0, '-556.950'), (1, '-527.770')] -[2023-11-28 05:33:53,617][87426] Updated weights for policy 1, policy_version 204160 (0.0011) -[2023-11-28 05:33:54,576][87424] Updated weights for policy 0, policy_version 204517 (0.0011) -[2023-11-28 05:33:54,953][87424] Updated weights for policy 0, policy_version 204527 (0.0010) -[2023-11-28 05:33:55,335][87424] Updated weights for policy 0, policy_version 204537 (0.0010) -[2023-11-28 05:33:56,122][87426] Updated weights for policy 1, policy_version 204170 (0.0012) -[2023-11-28 05:33:56,501][87426] Updated weights for policy 1, policy_version 204180 (0.0012) -[2023-11-28 05:33:56,882][87426] Updated weights for policy 1, policy_version 204190 (0.0012) -[2023-11-28 05:33:57,295][87424] Updated weights for policy 0, policy_version 204547 (0.0009) -[2023-11-28 05:33:57,675][87424] Updated weights for policy 0, policy_version 204557 (0.0011) -[2023-11-28 05:33:58,058][87424] Updated weights for policy 0, policy_version 204567 (0.0012) -[2023-11-28 05:33:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 104644608. Throughput: 0: 2653.7, 1: 2693.6. Samples: 104654584. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:33:58,446][86177] Avg episode reward: [(0, '-556.490'), (1, '-537.970')] -[2023-11-28 05:33:59,223][87426] Updated weights for policy 1, policy_version 204200 (0.0008) -[2023-11-28 05:33:59,604][87426] Updated weights for policy 1, policy_version 204210 (0.0008) -[2023-11-28 05:33:59,977][87426] Updated weights for policy 1, policy_version 204220 (0.0008) -[2023-11-28 05:34:00,562][87424] Updated weights for policy 0, policy_version 204577 (0.0009) -[2023-11-28 05:34:00,952][87424] Updated weights for policy 0, policy_version 204587 (0.0008) -[2023-11-28 05:34:01,322][87424] Updated weights for policy 0, policy_version 204597 (0.0010) -[2023-11-28 05:34:01,706][87424] Updated weights for policy 0, policy_version 204607 (0.0012) -[2023-11-28 05:34:02,358][87426] Updated weights for policy 1, policy_version 204230 (0.0010) -[2023-11-28 05:34:02,735][87426] Updated weights for policy 1, policy_version 204240 (0.0012) -[2023-11-28 05:34:03,112][87426] Updated weights for policy 1, policy_version 204250 (0.0009) -[2023-11-28 05:34:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 104669184. Throughput: 0: 2639.0, 1: 2707.9. Samples: 104678644. Policy #0 lag: (min: 31.0, avg: 49.4, max: 73.0) -[2023-11-28 05:34:03,445][86177] Avg episode reward: [(0, '-533.810'), (1, '-534.290')] -[2023-11-28 05:34:04,078][87424] Updated weights for policy 0, policy_version 204617 (0.0008) -[2023-11-28 05:34:04,464][87424] Updated weights for policy 0, policy_version 204627 (0.0008) -[2023-11-28 05:34:04,844][87424] Updated weights for policy 0, policy_version 204637 (0.0011) -[2023-11-28 05:34:05,153][87426] Updated weights for policy 1, policy_version 204260 (0.0011) -[2023-11-28 05:34:05,520][87426] Updated weights for policy 1, policy_version 204270 (0.0011) -[2023-11-28 05:34:05,891][87426] Updated weights for policy 1, policy_version 204280 (0.0011) -[2023-11-28 05:34:07,380][87424] Updated weights for policy 0, policy_version 204647 (0.0012) -[2023-11-28 05:34:07,757][87424] Updated weights for policy 0, policy_version 204657 (0.0010) -[2023-11-28 05:34:08,088][87426] Updated weights for policy 1, policy_version 204290 (0.0011) -[2023-11-28 05:34:08,134][87424] Updated weights for policy 0, policy_version 204667 (0.0010) -[2023-11-28 05:34:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 104693760. Throughput: 0: 2652.9, 1: 2716.8. Samples: 104711804. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:08,445][86177] Avg episode reward: [(0, '-537.010'), (1, '-534.400')] -[2023-11-28 05:34:08,471][87426] Updated weights for policy 1, policy_version 204300 (0.0007) -[2023-11-28 05:34:08,858][87426] Updated weights for policy 1, policy_version 204310 (0.0008) -[2023-11-28 05:34:09,234][87426] Updated weights for policy 1, policy_version 204320 (0.0008) -[2023-11-28 05:34:10,670][87424] Updated weights for policy 0, policy_version 204677 (0.0009) -[2023-11-28 05:34:11,048][87424] Updated weights for policy 0, policy_version 204687 (0.0009) -[2023-11-28 05:34:11,172][87426] Updated weights for policy 1, policy_version 204330 (0.0011) -[2023-11-28 05:34:11,433][87424] Updated weights for policy 0, policy_version 204697 (0.0007) -[2023-11-28 05:34:11,549][87426] Updated weights for policy 1, policy_version 204340 (0.0012) -[2023-11-28 05:34:11,948][87426] Updated weights for policy 1, policy_version 204350 (0.0010) -[2023-11-28 05:34:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 104718336. Throughput: 0: 2645.0, 1: 2715.6. Samples: 104735308. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:13,445][86177] Avg episode reward: [(0, '-516.910'), (1, '-536.950')] -[2023-11-28 05:34:13,776][87424] Updated weights for policy 0, policy_version 204707 (0.0010) -[2023-11-28 05:34:14,157][87424] Updated weights for policy 0, policy_version 204717 (0.0011) -[2023-11-28 05:34:14,164][87426] Updated weights for policy 1, policy_version 204360 (0.0011) -[2023-11-28 05:34:14,540][87424] Updated weights for policy 0, policy_version 204727 (0.0012) -[2023-11-28 05:34:14,543][87426] Updated weights for policy 1, policy_version 204370 (0.0009) -[2023-11-28 05:34:14,921][87426] Updated weights for policy 1, policy_version 204380 (0.0012) -[2023-11-28 05:34:16,555][87424] Updated weights for policy 0, policy_version 204737 (0.0011) -[2023-11-28 05:34:16,620][87426] Updated weights for policy 1, policy_version 204390 (0.0012) -[2023-11-28 05:34:16,936][87424] Updated weights for policy 0, policy_version 204747 (0.0009) -[2023-11-28 05:34:16,999][87426] Updated weights for policy 1, policy_version 204400 (0.0012) -[2023-11-28 05:34:17,320][87424] Updated weights for policy 0, policy_version 204757 (0.0008) -[2023-11-28 05:34:17,388][87426] Updated weights for policy 1, policy_version 204410 (0.0008) -[2023-11-28 05:34:17,706][87424] Updated weights for policy 0, policy_version 204767 (0.0008) -[2023-11-28 05:34:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 104751104. Throughput: 0: 2633.1, 1: 2731.3. Samples: 104759580. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:18,446][86177] Avg episode reward: [(0, '-520.610'), (1, '-521.640')] -[2023-11-28 05:34:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000204416_52330496.pth... -[2023-11-28 05:34:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000204768_52420608.pth... -[2023-11-28 05:34:18,509][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000201856_51675136.pth -[2023-11-28 05:34:18,510][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000202272_51781632.pth -[2023-11-28 05:34:19,813][87426] Updated weights for policy 1, policy_version 204420 (0.0009) -[2023-11-28 05:34:19,929][87424] Updated weights for policy 0, policy_version 204777 (0.0009) -[2023-11-28 05:34:20,190][87426] Updated weights for policy 1, policy_version 204430 (0.0009) -[2023-11-28 05:34:20,320][87424] Updated weights for policy 0, policy_version 204787 (0.0010) -[2023-11-28 05:34:20,569][87426] Updated weights for policy 1, policy_version 204440 (0.0009) -[2023-11-28 05:34:20,689][87424] Updated weights for policy 0, policy_version 204797 (0.0009) -[2023-11-28 05:34:22,677][87426] Updated weights for policy 1, policy_version 204450 (0.0009) -[2023-11-28 05:34:23,062][87426] Updated weights for policy 1, policy_version 204460 (0.0010) -[2023-11-28 05:34:23,264][87424] Updated weights for policy 0, policy_version 204807 (0.0010) -[2023-11-28 05:34:23,441][87426] Updated weights for policy 1, policy_version 204470 (0.0009) -[2023-11-28 05:34:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 104767488. Throughput: 0: 2600.3, 1: 2729.2. Samples: 104790512. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:23,445][86177] Avg episode reward: [(0, '-521.450'), (1, '-523.120')] -[2023-11-28 05:34:23,647][87424] Updated weights for policy 0, policy_version 204817 (0.0012) -[2023-11-28 05:34:23,819][87426] Updated weights for policy 1, policy_version 204480 (0.0011) -[2023-11-28 05:34:24,036][87424] Updated weights for policy 0, policy_version 204827 (0.0012) -[2023-11-28 05:34:25,811][87424] Updated weights for policy 0, policy_version 204837 (0.0012) -[2023-11-28 05:34:26,066][87426] Updated weights for policy 1, policy_version 204490 (0.0007) -[2023-11-28 05:34:26,193][87424] Updated weights for policy 0, policy_version 204847 (0.0012) -[2023-11-28 05:34:26,446][87426] Updated weights for policy 1, policy_version 204500 (0.0008) -[2023-11-28 05:34:26,578][87424] Updated weights for policy 0, policy_version 204857 (0.0012) -[2023-11-28 05:34:26,829][87426] Updated weights for policy 1, policy_version 204510 (0.0007) -[2023-11-28 05:34:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 104800256. Throughput: 0: 2617.8, 1: 2751.8. Samples: 104816352. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:28,445][86177] Avg episode reward: [(0, '-520.140'), (1, '-525.200')] -[2023-11-28 05:34:28,515][87426] Updated weights for policy 1, policy_version 204520 (0.0011) -[2023-11-28 05:34:28,683][87424] Updated weights for policy 0, policy_version 204867 (0.0012) -[2023-11-28 05:34:28,893][87426] Updated weights for policy 1, policy_version 204530 (0.0008) -[2023-11-28 05:34:29,063][87424] Updated weights for policy 0, policy_version 204877 (0.0009) -[2023-11-28 05:34:29,278][87426] Updated weights for policy 1, policy_version 204540 (0.0011) -[2023-11-28 05:34:29,448][87424] Updated weights for policy 0, policy_version 204887 (0.0010) -[2023-11-28 05:34:31,284][87424] Updated weights for policy 0, policy_version 204897 (0.0010) -[2023-11-28 05:34:31,663][87424] Updated weights for policy 0, policy_version 204907 (0.0008) -[2023-11-28 05:34:31,734][87426] Updated weights for policy 1, policy_version 204550 (0.0011) -[2023-11-28 05:34:32,046][87424] Updated weights for policy 0, policy_version 204917 (0.0009) -[2023-11-28 05:34:32,107][87426] Updated weights for policy 1, policy_version 204560 (0.0012) -[2023-11-28 05:34:32,437][87424] Updated weights for policy 0, policy_version 204927 (0.0010) -[2023-11-28 05:34:32,479][87426] Updated weights for policy 1, policy_version 204570 (0.0011) -[2023-11-28 05:34:33,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 104833024. Throughput: 0: 2641.5, 1: 2750.5. Samples: 104841536. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:33,445][86177] Avg episode reward: [(0, '-506.580'), (1, '-535.410')] -[2023-11-28 05:34:34,277][87426] Updated weights for policy 1, policy_version 204580 (0.0008) -[2023-11-28 05:34:34,651][87426] Updated weights for policy 1, policy_version 204590 (0.0007) -[2023-11-28 05:34:34,934][87424] Updated weights for policy 0, policy_version 204937 (0.0010) -[2023-11-28 05:34:35,028][87426] Updated weights for policy 1, policy_version 204600 (0.0008) -[2023-11-28 05:34:35,321][87424] Updated weights for policy 0, policy_version 204947 (0.0008) -[2023-11-28 05:34:35,693][87424] Updated weights for policy 0, policy_version 204957 (0.0007) -[2023-11-28 05:34:37,480][87426] Updated weights for policy 1, policy_version 204610 (0.0009) -[2023-11-28 05:34:37,864][87426] Updated weights for policy 1, policy_version 204620 (0.0007) -[2023-11-28 05:34:37,915][87424] Updated weights for policy 0, policy_version 204967 (0.0010) -[2023-11-28 05:34:38,242][87426] Updated weights for policy 1, policy_version 204630 (0.0011) -[2023-11-28 05:34:38,295][87424] Updated weights for policy 0, policy_version 204977 (0.0012) -[2023-11-28 05:34:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 104849408. Throughput: 0: 2662.8, 1: 2739.4. Samples: 104873124. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:38,445][86177] Avg episode reward: [(0, '-516.980'), (1, '-536.780')] -[2023-11-28 05:34:38,613][87426] Updated weights for policy 1, policy_version 204640 (0.0010) -[2023-11-28 05:34:38,679][87424] Updated weights for policy 0, policy_version 204987 (0.0012) -[2023-11-28 05:34:40,894][87424] Updated weights for policy 0, policy_version 204997 (0.0011) -[2023-11-28 05:34:41,183][87426] Updated weights for policy 1, policy_version 204650 (0.0008) -[2023-11-28 05:34:41,283][87424] Updated weights for policy 0, policy_version 205007 (0.0010) -[2023-11-28 05:34:41,562][87426] Updated weights for policy 1, policy_version 204660 (0.0008) -[2023-11-28 05:34:41,657][87424] Updated weights for policy 0, policy_version 205017 (0.0009) -[2023-11-28 05:34:41,935][87426] Updated weights for policy 1, policy_version 204670 (0.0010) -[2023-11-28 05:34:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 104882176. Throughput: 0: 2667.6, 1: 2710.1. Samples: 104896576. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:43,445][86177] Avg episode reward: [(0, '-515.560'), (1, '-533.400')] -[2023-11-28 05:34:43,970][87426] Updated weights for policy 1, policy_version 204680 (0.0010) -[2023-11-28 05:34:44,038][87424] Updated weights for policy 0, policy_version 205027 (0.0010) -[2023-11-28 05:34:44,349][87426] Updated weights for policy 1, policy_version 204690 (0.0010) -[2023-11-28 05:34:44,422][87424] Updated weights for policy 0, policy_version 205037 (0.0011) -[2023-11-28 05:34:44,731][87426] Updated weights for policy 1, policy_version 204700 (0.0008) -[2023-11-28 05:34:44,806][87424] Updated weights for policy 0, policy_version 205047 (0.0011) -[2023-11-28 05:34:46,966][87426] Updated weights for policy 1, policy_version 204710 (0.0011) -[2023-11-28 05:34:47,157][87424] Updated weights for policy 0, policy_version 205057 (0.0010) -[2023-11-28 05:34:47,331][87426] Updated weights for policy 1, policy_version 204720 (0.0011) -[2023-11-28 05:34:47,543][87424] Updated weights for policy 0, policy_version 205067 (0.0007) -[2023-11-28 05:34:47,717][87426] Updated weights for policy 1, policy_version 204730 (0.0011) -[2023-11-28 05:34:47,920][87424] Updated weights for policy 0, policy_version 205077 (0.0007) -[2023-11-28 05:34:48,313][87424] Updated weights for policy 0, policy_version 205087 (0.0007) -[2023-11-28 05:34:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 104914944. Throughput: 0: 2659.0, 1: 2708.0. Samples: 104920160. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:48,445][86177] Avg episode reward: [(0, '-507.920'), (1, '-538.640')] -[2023-11-28 05:34:50,259][87426] Updated weights for policy 1, policy_version 204740 (0.0012) -[2023-11-28 05:34:50,638][87426] Updated weights for policy 1, policy_version 204750 (0.0011) -[2023-11-28 05:34:50,673][87424] Updated weights for policy 0, policy_version 205097 (0.0011) -[2023-11-28 05:34:51,024][87426] Updated weights for policy 1, policy_version 204760 (0.0010) -[2023-11-28 05:34:51,065][87424] Updated weights for policy 0, policy_version 205107 (0.0008) -[2023-11-28 05:34:51,442][87424] Updated weights for policy 0, policy_version 205117 (0.0011) -[2023-11-28 05:34:52,917][87426] Updated weights for policy 1, policy_version 204770 (0.0011) -[2023-11-28 05:34:53,295][87426] Updated weights for policy 1, policy_version 204780 (0.0009) -[2023-11-28 05:34:53,366][87424] Updated weights for policy 0, policy_version 205127 (0.0012) -[2023-11-28 05:34:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 104931328. Throughput: 0: 2648.9, 1: 2679.2. Samples: 104951568. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:53,445][86177] Avg episode reward: [(0, '-504.760'), (1, '-513.750')] -[2023-11-28 05:34:53,680][87426] Updated weights for policy 1, policy_version 204790 (0.0010) -[2023-11-28 05:34:53,747][87424] Updated weights for policy 0, policy_version 205137 (0.0011) -[2023-11-28 05:34:54,054][87426] Updated weights for policy 1, policy_version 204800 (0.0010) -[2023-11-28 05:34:54,142][87424] Updated weights for policy 0, policy_version 205147 (0.0011) -[2023-11-28 05:34:56,511][87426] Updated weights for policy 1, policy_version 204810 (0.0011) -[2023-11-28 05:34:56,569][87424] Updated weights for policy 0, policy_version 205157 (0.0010) -[2023-11-28 05:34:56,897][87426] Updated weights for policy 1, policy_version 204820 (0.0007) -[2023-11-28 05:34:56,947][87424] Updated weights for policy 0, policy_version 205167 (0.0008) -[2023-11-28 05:34:57,272][87426] Updated weights for policy 1, policy_version 204830 (0.0007) -[2023-11-28 05:34:57,330][87424] Updated weights for policy 0, policy_version 205177 (0.0007) -[2023-11-28 05:34:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 104964096. Throughput: 0: 2657.3, 1: 2686.0. Samples: 104975760. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:34:58,446][86177] Avg episode reward: [(0, '-492.720'), (1, '-536.830')] -[2023-11-28 05:34:59,438][87424] Updated weights for policy 0, policy_version 205187 (0.0008) -[2023-11-28 05:34:59,649][87426] Updated weights for policy 1, policy_version 204840 (0.0010) -[2023-11-28 05:34:59,820][87424] Updated weights for policy 0, policy_version 205197 (0.0010) -[2023-11-28 05:35:00,027][87426] Updated weights for policy 1, policy_version 204850 (0.0011) -[2023-11-28 05:35:00,199][87424] Updated weights for policy 0, policy_version 205207 (0.0008) -[2023-11-28 05:35:00,403][87426] Updated weights for policy 1, policy_version 204860 (0.0014) -[2023-11-28 05:35:02,160][87426] Updated weights for policy 1, policy_version 204870 (0.0012) -[2023-11-28 05:35:02,310][87424] Updated weights for policy 0, policy_version 205217 (0.0010) -[2023-11-28 05:35:02,540][87426] Updated weights for policy 1, policy_version 204880 (0.0012) -[2023-11-28 05:35:02,684][87424] Updated weights for policy 0, policy_version 205227 (0.0007) -[2023-11-28 05:35:02,924][87426] Updated weights for policy 1, policy_version 204890 (0.0012) -[2023-11-28 05:35:03,074][87424] Updated weights for policy 0, policy_version 205237 (0.0010) -[2023-11-28 05:35:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 104988672. Throughput: 0: 2680.2, 1: 2674.2. Samples: 105000524. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:35:03,445][86177] Avg episode reward: [(0, '-492.460'), (1, '-538.840')] -[2023-11-28 05:35:03,466][87424] Updated weights for policy 0, policy_version 205247 (0.0007) -[2023-11-28 05:35:04,923][87426] Updated weights for policy 1, policy_version 204900 (0.0011) -[2023-11-28 05:35:05,242][87424] Updated weights for policy 0, policy_version 205257 (0.0011) -[2023-11-28 05:35:05,296][87426] Updated weights for policy 1, policy_version 204910 (0.0011) -[2023-11-28 05:35:05,624][87424] Updated weights for policy 0, policy_version 205267 (0.0012) -[2023-11-28 05:35:05,666][87426] Updated weights for policy 1, policy_version 204920 (0.0008) -[2023-11-28 05:35:06,014][87424] Updated weights for policy 0, policy_version 205277 (0.0012) -[2023-11-28 05:35:08,129][87426] Updated weights for policy 1, policy_version 204930 (0.0007) -[2023-11-28 05:35:08,196][87424] Updated weights for policy 0, policy_version 205287 (0.0011) -[2023-11-28 05:35:08,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 105013248. Throughput: 0: 2733.6, 1: 2672.1. Samples: 105033768. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:35:08,446][86177] Avg episode reward: [(0, '-488.270'), (1, '-539.070')] -[2023-11-28 05:35:08,511][87426] Updated weights for policy 1, policy_version 204940 (0.0008) -[2023-11-28 05:35:08,587][87424] Updated weights for policy 0, policy_version 205297 (0.0010) -[2023-11-28 05:35:08,887][87426] Updated weights for policy 1, policy_version 204950 (0.0009) -[2023-11-28 05:35:08,970][87424] Updated weights for policy 0, policy_version 205307 (0.0009) -[2023-11-28 05:35:09,268][87426] Updated weights for policy 1, policy_version 204960 (0.0012) -[2023-11-28 05:35:11,096][87424] Updated weights for policy 0, policy_version 205317 (0.0012) -[2023-11-28 05:35:11,477][87424] Updated weights for policy 0, policy_version 205327 (0.0009) -[2023-11-28 05:35:11,641][87426] Updated weights for policy 1, policy_version 204970 (0.0011) -[2023-11-28 05:35:11,856][87424] Updated weights for policy 0, policy_version 205337 (0.0010) -[2023-11-28 05:35:12,024][87426] Updated weights for policy 1, policy_version 204980 (0.0011) -[2023-11-28 05:35:12,412][87426] Updated weights for policy 1, policy_version 204990 (0.0011) -[2023-11-28 05:35:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 105046016. Throughput: 0: 2717.6, 1: 2651.0. Samples: 105057940. Policy #0 lag: (min: 6.0, avg: 15.5, max: 38.0) -[2023-11-28 05:35:13,446][86177] Avg episode reward: [(0, '-528.530'), (1, '-552.000')] -[2023-11-28 05:35:13,683][87424] Updated weights for policy 0, policy_version 205347 (0.0011) -[2023-11-28 05:35:14,066][87424] Updated weights for policy 0, policy_version 205357 (0.0012) -[2023-11-28 05:35:14,452][87424] Updated weights for policy 0, policy_version 205367 (0.0012) -[2023-11-28 05:35:14,460][87426] Updated weights for policy 1, policy_version 205000 (0.0010) -[2023-11-28 05:35:14,835][87426] Updated weights for policy 1, policy_version 205010 (0.0009) -[2023-11-28 05:35:15,216][87426] Updated weights for policy 1, policy_version 205020 (0.0007) -[2023-11-28 05:35:16,586][87424] Updated weights for policy 0, policy_version 205377 (0.0009) -[2023-11-28 05:35:16,963][87424] Updated weights for policy 0, policy_version 205387 (0.0008) -[2023-11-28 05:35:17,340][87424] Updated weights for policy 0, policy_version 205397 (0.0007) -[2023-11-28 05:35:17,525][87426] Updated weights for policy 1, policy_version 205030 (0.0011) -[2023-11-28 05:35:17,722][87424] Updated weights for policy 0, policy_version 205407 (0.0010) -[2023-11-28 05:35:17,910][87426] Updated weights for policy 1, policy_version 205040 (0.0008) -[2023-11-28 05:35:18,277][87426] Updated weights for policy 1, policy_version 205050 (0.0008) -[2023-11-28 05:35:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 105070592. Throughput: 0: 2735.4, 1: 2648.4. Samples: 105083808. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:35:18,445][86177] Avg episode reward: [(0, '-532.490'), (1, '-526.830')] -[2023-11-28 05:35:19,524][87424] Updated weights for policy 0, policy_version 205417 (0.0008) -[2023-11-28 05:35:19,910][87424] Updated weights for policy 0, policy_version 205427 (0.0009) -[2023-11-28 05:35:20,296][87424] Updated weights for policy 0, policy_version 205437 (0.0008) -[2023-11-28 05:35:20,763][87426] Updated weights for policy 1, policy_version 205060 (0.0009) -[2023-11-28 05:35:21,149][87426] Updated weights for policy 1, policy_version 205070 (0.0011) -[2023-11-28 05:35:21,518][87426] Updated weights for policy 1, policy_version 205080 (0.0009) -[2023-11-28 05:35:22,592][87424] Updated weights for policy 0, policy_version 205447 (0.0011) -[2023-11-28 05:35:22,979][87424] Updated weights for policy 0, policy_version 205457 (0.0011) -[2023-11-28 05:35:23,356][87424] Updated weights for policy 0, policy_version 205467 (0.0010) -[2023-11-28 05:35:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 105095168. Throughput: 0: 2749.2, 1: 2641.3. Samples: 105115696. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:35:23,445][86177] Avg episode reward: [(0, '-532.510'), (1, '-532.900')] -[2023-11-28 05:35:23,699][87426] Updated weights for policy 1, policy_version 205090 (0.0012) -[2023-11-28 05:35:24,083][87426] Updated weights for policy 1, policy_version 205100 (0.0012) -[2023-11-28 05:35:24,452][87426] Updated weights for policy 1, policy_version 205110 (0.0012) -[2023-11-28 05:35:24,826][87426] Updated weights for policy 1, policy_version 205120 (0.0010) -[2023-11-28 05:35:25,381][87424] Updated weights for policy 0, policy_version 205477 (0.0011) -[2023-11-28 05:35:25,754][87424] Updated weights for policy 0, policy_version 205487 (0.0011) -[2023-11-28 05:35:26,143][87424] Updated weights for policy 0, policy_version 205497 (0.0011) -[2023-11-28 05:35:27,066][87426] Updated weights for policy 1, policy_version 205130 (0.0008) -[2023-11-28 05:35:27,443][87426] Updated weights for policy 1, policy_version 205140 (0.0011) -[2023-11-28 05:35:27,836][87426] Updated weights for policy 1, policy_version 205150 (0.0012) -[2023-11-28 05:35:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 105127936. Throughput: 0: 2772.6, 1: 2650.8. Samples: 105140628. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:35:28,445][86177] Avg episode reward: [(0, '-553.820'), (1, '-528.930')] -[2023-11-28 05:35:28,496][87424] Updated weights for policy 0, policy_version 205507 (0.0011) -[2023-11-28 05:35:28,868][87424] Updated weights for policy 0, policy_version 205517 (0.0012) -[2023-11-28 05:35:29,246][87424] Updated weights for policy 0, policy_version 205527 (0.0010) -[2023-11-28 05:35:30,027][87426] Updated weights for policy 1, policy_version 205160 (0.0009) -[2023-11-28 05:35:30,404][87426] Updated weights for policy 1, policy_version 205170 (0.0010) -[2023-11-28 05:35:30,782][87426] Updated weights for policy 1, policy_version 205180 (0.0012) -[2023-11-28 05:35:31,392][87424] Updated weights for policy 0, policy_version 205537 (0.0009) -[2023-11-28 05:35:31,786][87424] Updated weights for policy 0, policy_version 205547 (0.0011) -[2023-11-28 05:35:32,169][87424] Updated weights for policy 0, policy_version 205557 (0.0011) -[2023-11-28 05:35:32,549][87424] Updated weights for policy 0, policy_version 205567 (0.0012) -[2023-11-28 05:35:33,102][87426] Updated weights for policy 1, policy_version 205190 (0.0011) -[2023-11-28 05:35:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 105152512. Throughput: 0: 2797.0, 1: 2662.8. Samples: 105165848. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:35:33,445][86177] Avg episode reward: [(0, '-516.050'), (1, '-518.660')] -[2023-11-28 05:35:33,471][87426] Updated weights for policy 1, policy_version 205200 (0.0007) -[2023-11-28 05:35:33,850][87426] Updated weights for policy 1, policy_version 205210 (0.0007) -[2023-11-28 05:35:34,549][87424] Updated weights for policy 0, policy_version 205577 (0.0012) -[2023-11-28 05:35:34,932][87424] Updated weights for policy 0, policy_version 205587 (0.0012) -[2023-11-28 05:35:35,319][87424] Updated weights for policy 0, policy_version 205597 (0.0012) -[2023-11-28 05:35:36,283][87426] Updated weights for policy 1, policy_version 205220 (0.0011) -[2023-11-28 05:35:36,657][87426] Updated weights for policy 1, policy_version 205230 (0.0012) -[2023-11-28 05:35:37,043][87426] Updated weights for policy 1, policy_version 205240 (0.0012) -[2023-11-28 05:35:37,043][87424] Updated weights for policy 0, policy_version 205607 (0.0012) -[2023-11-28 05:35:37,418][87424] Updated weights for policy 0, policy_version 205617 (0.0012) -[2023-11-28 05:35:37,803][87424] Updated weights for policy 0, policy_version 205627 (0.0012) -[2023-11-28 05:35:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 105185280. Throughput: 0: 2821.2, 1: 2688.5. Samples: 105199508. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:35:38,445][86177] Avg episode reward: [(0, '-535.010'), (1, '-536.920')] -[2023-11-28 05:35:38,966][87426] Updated weights for policy 1, policy_version 205250 (0.0012) -[2023-11-28 05:35:39,344][87426] Updated weights for policy 1, policy_version 205260 (0.0012) -[2023-11-28 05:35:39,727][87426] Updated weights for policy 1, policy_version 205270 (0.0012) -[2023-11-28 05:35:40,095][87426] Updated weights for policy 1, policy_version 205280 (0.0011) -[2023-11-28 05:35:40,281][87424] Updated weights for policy 0, policy_version 205637 (0.0011) -[2023-11-28 05:35:40,659][87424] Updated weights for policy 0, policy_version 205647 (0.0010) -[2023-11-28 05:35:41,052][87424] Updated weights for policy 0, policy_version 205657 (0.0008) -[2023-11-28 05:35:42,583][87426] Updated weights for policy 1, policy_version 205290 (0.0008) -[2023-11-28 05:35:42,958][87426] Updated weights for policy 1, policy_version 205300 (0.0008) -[2023-11-28 05:35:42,968][87424] Updated weights for policy 0, policy_version 205667 (0.0008) -[2023-11-28 05:35:43,336][87426] Updated weights for policy 1, policy_version 205310 (0.0008) -[2023-11-28 05:35:43,349][87424] Updated weights for policy 0, policy_version 205677 (0.0012) -[2023-11-28 05:35:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 105209856. Throughput: 0: 2818.2, 1: 2658.5. Samples: 105222212. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:35:43,445][86177] Avg episode reward: [(0, '-538.050'), (1, '-534.810')] -[2023-11-28 05:35:43,725][87424] Updated weights for policy 0, policy_version 205687 (0.0008) -[2023-11-28 05:35:45,811][87426] Updated weights for policy 1, policy_version 205320 (0.0011) -[2023-11-28 05:35:45,982][87424] Updated weights for policy 0, policy_version 205697 (0.0007) -[2023-11-28 05:35:46,183][87426] Updated weights for policy 1, policy_version 205330 (0.0011) -[2023-11-28 05:35:46,364][87424] Updated weights for policy 0, policy_version 205707 (0.0009) -[2023-11-28 05:35:46,559][87426] Updated weights for policy 1, policy_version 205340 (0.0010) -[2023-11-28 05:35:46,751][87424] Updated weights for policy 0, policy_version 205717 (0.0010) -[2023-11-28 05:35:47,131][87424] Updated weights for policy 0, policy_version 205727 (0.0012) -[2023-11-28 05:35:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 105234432. Throughput: 0: 2820.6, 1: 2643.3. Samples: 105246400. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:35:48,445][86177] Avg episode reward: [(0, '-560.730'), (1, '-532.580')] -[2023-11-28 05:35:48,703][87426] Updated weights for policy 1, policy_version 205350 (0.0010) -[2023-11-28 05:35:49,078][87426] Updated weights for policy 1, policy_version 205360 (0.0012) -[2023-11-28 05:35:49,410][87424] Updated weights for policy 0, policy_version 205737 (0.0012) -[2023-11-28 05:35:49,456][87426] Updated weights for policy 1, policy_version 205370 (0.0010) -[2023-11-28 05:35:49,792][87424] Updated weights for policy 0, policy_version 205747 (0.0010) -[2023-11-28 05:35:50,174][87424] Updated weights for policy 0, policy_version 205757 (0.0010) -[2023-11-28 05:35:51,937][87426] Updated weights for policy 1, policy_version 205380 (0.0009) -[2023-11-28 05:35:52,127][87424] Updated weights for policy 0, policy_version 205767 (0.0012) -[2023-11-28 05:35:52,310][87426] Updated weights for policy 1, policy_version 205390 (0.0010) -[2023-11-28 05:35:52,508][87424] Updated weights for policy 0, policy_version 205777 (0.0010) -[2023-11-28 05:35:52,691][87426] Updated weights for policy 1, policy_version 205400 (0.0011) -[2023-11-28 05:35:52,889][87424] Updated weights for policy 0, policy_version 205787 (0.0008) -[2023-11-28 05:35:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 105267200. Throughput: 0: 2809.5, 1: 2665.0. Samples: 105280120. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:35:53,445][86177] Avg episode reward: [(0, '-562.540'), (1, '-564.230')] -[2023-11-28 05:35:54,898][87426] Updated weights for policy 1, policy_version 205410 (0.0011) -[2023-11-28 05:35:55,156][87424] Updated weights for policy 0, policy_version 205797 (0.0009) -[2023-11-28 05:35:55,270][87426] Updated weights for policy 1, policy_version 205420 (0.0009) -[2023-11-28 05:35:55,535][87424] Updated weights for policy 0, policy_version 205807 (0.0007) -[2023-11-28 05:35:55,649][87426] Updated weights for policy 1, policy_version 205430 (0.0010) -[2023-11-28 05:35:55,920][87424] Updated weights for policy 0, policy_version 205817 (0.0008) -[2023-11-28 05:35:56,026][87426] Updated weights for policy 1, policy_version 205440 (0.0012) -[2023-11-28 05:35:57,745][87424] Updated weights for policy 0, policy_version 205827 (0.0009) -[2023-11-28 05:35:57,854][87426] Updated weights for policy 1, policy_version 205450 (0.0012) -[2023-11-28 05:35:58,130][87424] Updated weights for policy 0, policy_version 205837 (0.0008) -[2023-11-28 05:35:58,232][87426] Updated weights for policy 1, policy_version 205460 (0.0012) -[2023-11-28 05:35:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 105283584. Throughput: 0: 2815.6, 1: 2677.4. Samples: 105305124. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:35:58,445][86177] Avg episode reward: [(0, '-590.860'), (1, '-557.600')] -[2023-11-28 05:35:58,517][87424] Updated weights for policy 0, policy_version 205847 (0.0009) -[2023-11-28 05:35:58,613][87426] Updated weights for policy 1, policy_version 205470 (0.0011) -[2023-11-28 05:36:00,600][87424] Updated weights for policy 0, policy_version 205857 (0.0011) -[2023-11-28 05:36:00,778][87426] Updated weights for policy 1, policy_version 205480 (0.0012) -[2023-11-28 05:36:00,984][87424] Updated weights for policy 0, policy_version 205867 (0.0008) -[2023-11-28 05:36:01,162][87426] Updated weights for policy 1, policy_version 205490 (0.0011) -[2023-11-28 05:36:01,372][87424] Updated weights for policy 0, policy_version 205877 (0.0010) -[2023-11-28 05:36:01,553][87426] Updated weights for policy 1, policy_version 205500 (0.0012) -[2023-11-28 05:36:01,761][87424] Updated weights for policy 0, policy_version 205887 (0.0011) -[2023-11-28 05:36:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 105316352. Throughput: 0: 2791.7, 1: 2677.2. Samples: 105329908. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:36:03,446][86177] Avg episode reward: [(0, '-586.240'), (1, '-568.170')] -[2023-11-28 05:36:03,554][87426] Updated weights for policy 1, policy_version 205510 (0.0012) -[2023-11-28 05:36:03,924][87426] Updated weights for policy 1, policy_version 205520 (0.0012) -[2023-11-28 05:36:04,067][87424] Updated weights for policy 0, policy_version 205897 (0.0009) -[2023-11-28 05:36:04,301][87426] Updated weights for policy 1, policy_version 205530 (0.0008) -[2023-11-28 05:36:04,441][87424] Updated weights for policy 0, policy_version 205907 (0.0011) -[2023-11-28 05:36:04,822][87424] Updated weights for policy 0, policy_version 205917 (0.0012) -[2023-11-28 05:36:06,540][87426] Updated weights for policy 1, policy_version 205540 (0.0009) -[2023-11-28 05:36:06,922][87426] Updated weights for policy 1, policy_version 205550 (0.0010) -[2023-11-28 05:36:07,123][87424] Updated weights for policy 0, policy_version 205927 (0.0010) -[2023-11-28 05:36:07,289][87426] Updated weights for policy 1, policy_version 205560 (0.0011) -[2023-11-28 05:36:07,505][87424] Updated weights for policy 0, policy_version 205937 (0.0010) -[2023-11-28 05:36:07,884][87424] Updated weights for policy 0, policy_version 205947 (0.0008) -[2023-11-28 05:36:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 105349120. Throughput: 0: 2785.0, 1: 2717.3. Samples: 105363300. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:36:08,445][86177] Avg episode reward: [(0, '-548.620'), (1, '-570.080')] -[2023-11-28 05:36:09,428][87426] Updated weights for policy 1, policy_version 205570 (0.0009) -[2023-11-28 05:36:09,801][87426] Updated weights for policy 1, policy_version 205580 (0.0012) -[2023-11-28 05:36:09,888][87424] Updated weights for policy 0, policy_version 205957 (0.0009) -[2023-11-28 05:36:10,178][87426] Updated weights for policy 1, policy_version 205590 (0.0012) -[2023-11-28 05:36:10,270][87424] Updated weights for policy 0, policy_version 205967 (0.0010) -[2023-11-28 05:36:10,557][87426] Updated weights for policy 1, policy_version 205600 (0.0011) -[2023-11-28 05:36:10,654][87424] Updated weights for policy 0, policy_version 205977 (0.0012) -[2023-11-28 05:36:12,721][87424] Updated weights for policy 0, policy_version 205987 (0.0011) -[2023-11-28 05:36:12,938][87426] Updated weights for policy 1, policy_version 205610 (0.0012) -[2023-11-28 05:36:13,091][87424] Updated weights for policy 0, policy_version 205997 (0.0010) -[2023-11-28 05:36:13,318][87426] Updated weights for policy 1, policy_version 205620 (0.0012) -[2023-11-28 05:36:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 105365504. Throughput: 0: 2749.1, 1: 2711.9. Samples: 105386376. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:36:13,445][86177] Avg episode reward: [(0, '-550.150'), (1, '-540.400')] -[2023-11-28 05:36:13,474][87424] Updated weights for policy 0, policy_version 206007 (0.0011) -[2023-11-28 05:36:13,702][87426] Updated weights for policy 1, policy_version 205630 (0.0011) -[2023-11-28 05:36:15,489][87426] Updated weights for policy 1, policy_version 205640 (0.0012) -[2023-11-28 05:36:15,503][87424] Updated weights for policy 0, policy_version 206017 (0.0011) -[2023-11-28 05:36:15,867][87426] Updated weights for policy 1, policy_version 205650 (0.0011) -[2023-11-28 05:36:15,890][87424] Updated weights for policy 0, policy_version 206027 (0.0012) -[2023-11-28 05:36:16,241][87426] Updated weights for policy 1, policy_version 205660 (0.0012) -[2023-11-28 05:36:16,266][87424] Updated weights for policy 0, policy_version 206037 (0.0010) -[2023-11-28 05:36:16,650][87424] Updated weights for policy 0, policy_version 206047 (0.0011) -[2023-11-28 05:36:18,125][87426] Updated weights for policy 1, policy_version 205670 (0.0009) -[2023-11-28 05:36:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 105398272. Throughput: 0: 2756.3, 1: 2712.4. Samples: 105411936. Policy #0 lag: (min: 45.0, avg: 62.7, max: 89.0) -[2023-11-28 05:36:18,445][86177] Avg episode reward: [(0, '-499.820'), (1, '-532.120')] -[2023-11-28 05:36:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000206048_52748288.pth... -[2023-11-28 05:36:18,491][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000203520_52101120.pth -[2023-11-28 05:36:18,499][87426] Updated weights for policy 1, policy_version 205680 (0.0007) -[2023-11-28 05:36:18,879][87426] Updated weights for policy 1, policy_version 205690 (0.0009) -[2023-11-28 05:36:19,034][87424] Updated weights for policy 0, policy_version 206057 (0.0011) -[2023-11-28 05:36:19,103][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000205696_52658176.pth... -[2023-11-28 05:36:19,133][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000203168_52011008.pth -[2023-11-28 05:36:19,411][87424] Updated weights for policy 0, policy_version 206067 (0.0011) -[2023-11-28 05:36:19,795][87424] Updated weights for policy 0, policy_version 206077 (0.0009) -[2023-11-28 05:36:21,313][87426] Updated weights for policy 1, policy_version 205700 (0.0010) -[2023-11-28 05:36:21,690][87426] Updated weights for policy 1, policy_version 205710 (0.0011) -[2023-11-28 05:36:22,074][87426] Updated weights for policy 1, policy_version 205720 (0.0009) -[2023-11-28 05:36:22,341][87424] Updated weights for policy 0, policy_version 206087 (0.0011) -[2023-11-28 05:36:22,721][87424] Updated weights for policy 0, policy_version 206097 (0.0007) -[2023-11-28 05:36:23,105][87424] Updated weights for policy 0, policy_version 206107 (0.0008) -[2023-11-28 05:36:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 105431040. Throughput: 0: 2705.0, 1: 2694.9. Samples: 105442504. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:36:23,445][86177] Avg episode reward: [(0, '-543.780'), (1, '-519.800')] -[2023-11-28 05:36:24,413][87426] Updated weights for policy 1, policy_version 205730 (0.0012) -[2023-11-28 05:36:24,788][87426] Updated weights for policy 1, policy_version 205740 (0.0012) -[2023-11-28 05:36:25,181][87426] Updated weights for policy 1, policy_version 205750 (0.0009) -[2023-11-28 05:36:25,253][87424] Updated weights for policy 0, policy_version 206117 (0.0009) -[2023-11-28 05:36:25,561][87426] Updated weights for policy 1, policy_version 205760 (0.0010) -[2023-11-28 05:36:25,637][87424] Updated weights for policy 0, policy_version 206127 (0.0012) -[2023-11-28 05:36:26,017][87424] Updated weights for policy 0, policy_version 206137 (0.0012) -[2023-11-28 05:36:27,679][87426] Updated weights for policy 1, policy_version 205770 (0.0009) -[2023-11-28 05:36:27,788][87424] Updated weights for policy 0, policy_version 206147 (0.0011) -[2023-11-28 05:36:28,063][87426] Updated weights for policy 1, policy_version 205780 (0.0007) -[2023-11-28 05:36:28,165][87424] Updated weights for policy 0, policy_version 206157 (0.0007) -[2023-11-28 05:36:28,432][87426] Updated weights for policy 1, policy_version 205790 (0.0011) -[2023-11-28 05:36:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 105447424. Throughput: 0: 2722.8, 1: 2718.2. Samples: 105467056. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:36:28,445][86177] Avg episode reward: [(0, '-544.770'), (1, '-544.670')] -[2023-11-28 05:36:28,554][87424] Updated weights for policy 0, policy_version 206167 (0.0007) -[2023-11-28 05:36:30,747][87424] Updated weights for policy 0, policy_version 206177 (0.0009) -[2023-11-28 05:36:30,821][87426] Updated weights for policy 1, policy_version 205800 (0.0012) -[2023-11-28 05:36:31,128][87424] Updated weights for policy 0, policy_version 206187 (0.0011) -[2023-11-28 05:36:31,195][87426] Updated weights for policy 1, policy_version 205810 (0.0011) -[2023-11-28 05:36:31,514][87424] Updated weights for policy 0, policy_version 206197 (0.0010) -[2023-11-28 05:36:31,567][87426] Updated weights for policy 1, policy_version 205820 (0.0012) -[2023-11-28 05:36:31,900][87424] Updated weights for policy 0, policy_version 206207 (0.0011) -[2023-11-28 05:36:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 105480192. Throughput: 0: 2715.8, 1: 2729.1. Samples: 105491420. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:36:33,445][86177] Avg episode reward: [(0, '-540.450'), (1, '-545.510')] -[2023-11-28 05:36:33,907][87424] Updated weights for policy 0, policy_version 206217 (0.0012) -[2023-11-28 05:36:33,956][87426] Updated weights for policy 1, policy_version 205830 (0.0009) -[2023-11-28 05:36:34,284][87424] Updated weights for policy 0, policy_version 206227 (0.0012) -[2023-11-28 05:36:34,337][87426] Updated weights for policy 1, policy_version 205840 (0.0008) -[2023-11-28 05:36:34,667][87424] Updated weights for policy 0, policy_version 206237 (0.0009) -[2023-11-28 05:36:34,715][87426] Updated weights for policy 1, policy_version 205850 (0.0010) -[2023-11-28 05:36:36,692][87424] Updated weights for policy 0, policy_version 206247 (0.0011) -[2023-11-28 05:36:36,714][87426] Updated weights for policy 1, policy_version 205860 (0.0010) -[2023-11-28 05:36:37,077][87424] Updated weights for policy 0, policy_version 206257 (0.0012) -[2023-11-28 05:36:37,096][87426] Updated weights for policy 1, policy_version 205870 (0.0011) -[2023-11-28 05:36:37,451][87424] Updated weights for policy 0, policy_version 206267 (0.0011) -[2023-11-28 05:36:37,475][87426] Updated weights for policy 1, policy_version 205880 (0.0012) -[2023-11-28 05:36:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 105512960. Throughput: 0: 2710.0, 1: 2729.9. Samples: 105524916. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:36:38,445][86177] Avg episode reward: [(0, '-543.670'), (1, '-558.580')] -[2023-11-28 05:36:39,543][87426] Updated weights for policy 1, policy_version 205890 (0.0012) -[2023-11-28 05:36:39,927][87426] Updated weights for policy 1, policy_version 205900 (0.0011) -[2023-11-28 05:36:39,939][87424] Updated weights for policy 0, policy_version 206277 (0.0014) -[2023-11-28 05:36:40,306][87426] Updated weights for policy 1, policy_version 205910 (0.0009) -[2023-11-28 05:36:40,319][87424] Updated weights for policy 0, policy_version 206287 (0.0012) -[2023-11-28 05:36:40,681][87426] Updated weights for policy 1, policy_version 205920 (0.0009) -[2023-11-28 05:36:40,703][87424] Updated weights for policy 0, policy_version 206297 (0.0012) -[2023-11-28 05:36:42,757][87426] Updated weights for policy 1, policy_version 205930 (0.0011) -[2023-11-28 05:36:43,134][87426] Updated weights for policy 1, policy_version 205940 (0.0011) -[2023-11-28 05:36:43,237][87424] Updated weights for policy 0, policy_version 206307 (0.0011) -[2023-11-28 05:36:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 105529344. Throughput: 0: 2699.9, 1: 2726.4. Samples: 105549308. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:36:43,445][86177] Avg episode reward: [(0, '-539.380'), (1, '-558.530')] -[2023-11-28 05:36:43,518][87426] Updated weights for policy 1, policy_version 205950 (0.0011) -[2023-11-28 05:36:43,618][87424] Updated weights for policy 0, policy_version 206317 (0.0011) -[2023-11-28 05:36:43,993][87424] Updated weights for policy 0, policy_version 206327 (0.0008) -[2023-11-28 05:36:45,920][87426] Updated weights for policy 1, policy_version 205960 (0.0011) -[2023-11-28 05:36:46,306][87426] Updated weights for policy 1, policy_version 205970 (0.0007) -[2023-11-28 05:36:46,409][87424] Updated weights for policy 0, policy_version 206337 (0.0008) -[2023-11-28 05:36:46,684][87426] Updated weights for policy 1, policy_version 205980 (0.0009) -[2023-11-28 05:36:46,787][87424] Updated weights for policy 0, policy_version 206347 (0.0007) -[2023-11-28 05:36:47,164][87424] Updated weights for policy 0, policy_version 206357 (0.0009) -[2023-11-28 05:36:47,553][87424] Updated weights for policy 0, policy_version 206367 (0.0012) -[2023-11-28 05:36:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 105562112. Throughput: 0: 2698.0, 1: 2717.8. Samples: 105573616. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:36:48,445][86177] Avg episode reward: [(0, '-548.210'), (1, '-535.720')] -[2023-11-28 05:36:48,547][87426] Updated weights for policy 1, policy_version 205990 (0.0010) -[2023-11-28 05:36:48,924][87426] Updated weights for policy 1, policy_version 206000 (0.0012) -[2023-11-28 05:36:49,308][87426] Updated weights for policy 1, policy_version 206010 (0.0009) -[2023-11-28 05:36:49,658][87424] Updated weights for policy 0, policy_version 206377 (0.0011) -[2023-11-28 05:36:50,035][87424] Updated weights for policy 0, policy_version 206387 (0.0012) -[2023-11-28 05:36:50,410][87424] Updated weights for policy 0, policy_version 206397 (0.0010) -[2023-11-28 05:36:51,136][87426] Updated weights for policy 1, policy_version 206020 (0.0008) -[2023-11-28 05:36:51,514][87426] Updated weights for policy 1, policy_version 206030 (0.0008) -[2023-11-28 05:36:51,897][87426] Updated weights for policy 1, policy_version 206040 (0.0012) -[2023-11-28 05:36:52,752][87424] Updated weights for policy 0, policy_version 206407 (0.0011) -[2023-11-28 05:36:53,134][87424] Updated weights for policy 0, policy_version 206417 (0.0012) -[2023-11-28 05:36:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 105586688. Throughput: 0: 2689.1, 1: 2703.7. Samples: 105605976. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:36:53,445][86177] Avg episode reward: [(0, '-548.080'), (1, '-535.690')] -[2023-11-28 05:36:53,527][87424] Updated weights for policy 0, policy_version 206427 (0.0012) -[2023-11-28 05:36:54,248][87426] Updated weights for policy 1, policy_version 206050 (0.0011) -[2023-11-28 05:36:54,630][87426] Updated weights for policy 1, policy_version 206060 (0.0008) -[2023-11-28 05:36:55,011][87426] Updated weights for policy 1, policy_version 206070 (0.0008) -[2023-11-28 05:36:55,389][87426] Updated weights for policy 1, policy_version 206080 (0.0011) -[2023-11-28 05:36:55,423][87424] Updated weights for policy 0, policy_version 206437 (0.0009) -[2023-11-28 05:36:55,800][87424] Updated weights for policy 0, policy_version 206447 (0.0007) -[2023-11-28 05:36:56,185][87424] Updated weights for policy 0, policy_version 206457 (0.0007) -[2023-11-28 05:36:57,656][87426] Updated weights for policy 1, policy_version 206090 (0.0008) -[2023-11-28 05:36:58,049][87426] Updated weights for policy 1, policy_version 206100 (0.0007) -[2023-11-28 05:36:58,420][87426] Updated weights for policy 1, policy_version 206110 (0.0007) -[2023-11-28 05:36:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 105611264. Throughput: 0: 2690.6, 1: 2739.4. Samples: 105630724. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:36:58,445][86177] Avg episode reward: [(0, '-546.010'), (1, '-536.340')] -[2023-11-28 05:36:58,626][87424] Updated weights for policy 0, policy_version 206467 (0.0009) -[2023-11-28 05:36:59,009][87424] Updated weights for policy 0, policy_version 206477 (0.0012) -[2023-11-28 05:36:59,399][87424] Updated weights for policy 0, policy_version 206487 (0.0012) -[2023-11-28 05:37:00,714][87426] Updated weights for policy 1, policy_version 206120 (0.0011) -[2023-11-28 05:37:01,097][87426] Updated weights for policy 1, policy_version 206130 (0.0012) -[2023-11-28 05:37:01,432][87424] Updated weights for policy 0, policy_version 206497 (0.0012) -[2023-11-28 05:37:01,475][87426] Updated weights for policy 1, policy_version 206140 (0.0012) -[2023-11-28 05:37:01,808][87424] Updated weights for policy 0, policy_version 206507 (0.0009) -[2023-11-28 05:37:02,192][87424] Updated weights for policy 0, policy_version 206517 (0.0009) -[2023-11-28 05:37:02,581][87424] Updated weights for policy 0, policy_version 206527 (0.0008) -[2023-11-28 05:37:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 105644032. Throughput: 0: 2680.5, 1: 2737.5. Samples: 105655748. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:37:03,445][86177] Avg episode reward: [(0, '-511.050'), (1, '-586.770')] -[2023-11-28 05:37:03,905][87426] Updated weights for policy 1, policy_version 206150 (0.0010) -[2023-11-28 05:37:04,280][87426] Updated weights for policy 1, policy_version 206160 (0.0011) -[2023-11-28 05:37:04,668][87426] Updated weights for policy 1, policy_version 206170 (0.0011) -[2023-11-28 05:37:04,781][87424] Updated weights for policy 0, policy_version 206537 (0.0011) -[2023-11-28 05:37:05,166][87424] Updated weights for policy 0, policy_version 206547 (0.0012) -[2023-11-28 05:37:05,541][87424] Updated weights for policy 0, policy_version 206557 (0.0012) -[2023-11-28 05:37:06,771][87426] Updated weights for policy 1, policy_version 206180 (0.0012) -[2023-11-28 05:37:07,157][87426] Updated weights for policy 1, policy_version 206190 (0.0012) -[2023-11-28 05:37:07,356][87424] Updated weights for policy 0, policy_version 206567 (0.0010) -[2023-11-28 05:37:07,539][87426] Updated weights for policy 1, policy_version 206200 (0.0012) -[2023-11-28 05:37:07,746][87424] Updated weights for policy 0, policy_version 206577 (0.0011) -[2023-11-28 05:37:08,123][87424] Updated weights for policy 0, policy_version 206587 (0.0012) -[2023-11-28 05:37:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 105676800. Throughput: 0: 2719.0, 1: 2746.1. Samples: 105688432. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:37:08,445][86177] Avg episode reward: [(0, '-517.540'), (1, '-582.930')] -[2023-11-28 05:37:09,251][87426] Updated weights for policy 1, policy_version 206210 (0.0012) -[2023-11-28 05:37:09,626][87426] Updated weights for policy 1, policy_version 206220 (0.0012) -[2023-11-28 05:37:10,004][87426] Updated weights for policy 1, policy_version 206230 (0.0011) -[2023-11-28 05:37:10,386][87426] Updated weights for policy 1, policy_version 206240 (0.0011) -[2023-11-28 05:37:10,624][87424] Updated weights for policy 0, policy_version 206597 (0.0011) -[2023-11-28 05:37:11,008][87424] Updated weights for policy 0, policy_version 206607 (0.0011) -[2023-11-28 05:37:11,392][87424] Updated weights for policy 0, policy_version 206617 (0.0012) -[2023-11-28 05:37:12,201][87426] Updated weights for policy 1, policy_version 206250 (0.0010) -[2023-11-28 05:37:12,580][87426] Updated weights for policy 1, policy_version 206260 (0.0009) -[2023-11-28 05:37:12,964][87426] Updated weights for policy 1, policy_version 206270 (0.0009) -[2023-11-28 05:37:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 105701376. Throughput: 0: 2722.3, 1: 2755.9. Samples: 105713576. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:37:13,445][86177] Avg episode reward: [(0, '-516.440'), (1, '-580.520')] -[2023-11-28 05:37:13,789][87424] Updated weights for policy 0, policy_version 206627 (0.0009) -[2023-11-28 05:37:14,180][87424] Updated weights for policy 0, policy_version 206637 (0.0009) -[2023-11-28 05:37:14,559][87424] Updated weights for policy 0, policy_version 206647 (0.0008) -[2023-11-28 05:37:15,424][87426] Updated weights for policy 1, policy_version 206280 (0.0008) -[2023-11-28 05:37:15,803][87426] Updated weights for policy 1, policy_version 206290 (0.0010) -[2023-11-28 05:37:16,178][87426] Updated weights for policy 1, policy_version 206300 (0.0011) -[2023-11-28 05:37:16,706][87424] Updated weights for policy 0, policy_version 206657 (0.0008) -[2023-11-28 05:37:17,089][87424] Updated weights for policy 0, policy_version 206667 (0.0008) -[2023-11-28 05:37:17,473][87424] Updated weights for policy 0, policy_version 206677 (0.0007) -[2023-11-28 05:37:17,857][87424] Updated weights for policy 0, policy_version 206687 (0.0010) -[2023-11-28 05:37:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 105725952. Throughput: 0: 2714.3, 1: 2753.1. Samples: 105737452. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:37:18,445][86177] Avg episode reward: [(0, '-526.300'), (1, '-572.640')] -[2023-11-28 05:37:18,497][87426] Updated weights for policy 1, policy_version 206310 (0.0012) -[2023-11-28 05:37:18,868][87426] Updated weights for policy 1, policy_version 206320 (0.0010) -[2023-11-28 05:37:19,258][87426] Updated weights for policy 1, policy_version 206330 (0.0009) -[2023-11-28 05:37:20,043][87424] Updated weights for policy 0, policy_version 206697 (0.0009) -[2023-11-28 05:37:20,430][87424] Updated weights for policy 0, policy_version 206707 (0.0009) -[2023-11-28 05:37:20,820][87424] Updated weights for policy 0, policy_version 206717 (0.0010) -[2023-11-28 05:37:21,044][87426] Updated weights for policy 1, policy_version 206340 (0.0010) -[2023-11-28 05:37:21,434][87426] Updated weights for policy 1, policy_version 206350 (0.0008) -[2023-11-28 05:37:21,813][87426] Updated weights for policy 1, policy_version 206360 (0.0009) -[2023-11-28 05:37:23,286][87424] Updated weights for policy 0, policy_version 206727 (0.0011) -[2023-11-28 05:37:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 105750528. Throughput: 0: 2689.2, 1: 2752.8. Samples: 105769808. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:37:23,445][86177] Avg episode reward: [(0, '-525.440'), (1, '-524.980')] -[2023-11-28 05:37:23,666][87424] Updated weights for policy 0, policy_version 206737 (0.0012) -[2023-11-28 05:37:24,048][87424] Updated weights for policy 0, policy_version 206747 (0.0011) -[2023-11-28 05:37:24,145][87426] Updated weights for policy 1, policy_version 206370 (0.0010) -[2023-11-28 05:37:24,521][87426] Updated weights for policy 1, policy_version 206380 (0.0012) -[2023-11-28 05:37:24,901][87426] Updated weights for policy 1, policy_version 206390 (0.0011) -[2023-11-28 05:37:25,278][87426] Updated weights for policy 1, policy_version 206400 (0.0009) -[2023-11-28 05:37:26,153][87424] Updated weights for policy 0, policy_version 206757 (0.0009) -[2023-11-28 05:37:26,534][87424] Updated weights for policy 0, policy_version 206767 (0.0007) -[2023-11-28 05:37:26,915][87424] Updated weights for policy 0, policy_version 206777 (0.0007) -[2023-11-28 05:37:27,601][87426] Updated weights for policy 1, policy_version 206410 (0.0012) -[2023-11-28 05:37:27,974][87426] Updated weights for policy 1, policy_version 206420 (0.0010) -[2023-11-28 05:37:28,360][87426] Updated weights for policy 1, policy_version 206430 (0.0011) -[2023-11-28 05:37:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 105783296. Throughput: 0: 2687.5, 1: 2743.4. Samples: 105793696. Policy #0 lag: (min: 18.0, avg: 38.5, max: 50.0) -[2023-11-28 05:37:28,445][86177] Avg episode reward: [(0, '-514.720'), (1, '-535.770')] -[2023-11-28 05:37:28,820][87424] Updated weights for policy 0, policy_version 206787 (0.0009) -[2023-11-28 05:37:29,210][87424] Updated weights for policy 0, policy_version 206797 (0.0008) -[2023-11-28 05:37:29,586][87424] Updated weights for policy 0, policy_version 206807 (0.0008) -[2023-11-28 05:37:30,933][87426] Updated weights for policy 1, policy_version 206440 (0.0010) -[2023-11-28 05:37:31,315][87426] Updated weights for policy 1, policy_version 206450 (0.0011) -[2023-11-28 05:37:31,685][87426] Updated weights for policy 1, policy_version 206460 (0.0010) -[2023-11-28 05:37:32,037][87424] Updated weights for policy 0, policy_version 206817 (0.0009) -[2023-11-28 05:37:32,417][87424] Updated weights for policy 0, policy_version 206827 (0.0009) -[2023-11-28 05:37:32,799][87424] Updated weights for policy 0, policy_version 206837 (0.0013) -[2023-11-28 05:37:33,198][87424] Updated weights for policy 0, policy_version 206847 (0.0012) -[2023-11-28 05:37:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 105807872. Throughput: 0: 2676.9, 1: 2729.0. Samples: 105816880. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:37:33,445][86177] Avg episode reward: [(0, '-519.900'), (1, '-538.670')] -[2023-11-28 05:37:34,206][87426] Updated weights for policy 1, policy_version 206470 (0.0010) -[2023-11-28 05:37:34,584][87426] Updated weights for policy 1, policy_version 206480 (0.0011) -[2023-11-28 05:37:34,986][87426] Updated weights for policy 1, policy_version 206490 (0.0012) -[2023-11-28 05:37:35,313][87424] Updated weights for policy 0, policy_version 206857 (0.0012) -[2023-11-28 05:37:35,693][87424] Updated weights for policy 0, policy_version 206867 (0.0012) -[2023-11-28 05:37:36,086][87424] Updated weights for policy 0, policy_version 206877 (0.0012) -[2023-11-28 05:37:36,966][87426] Updated weights for policy 1, policy_version 206500 (0.0012) -[2023-11-28 05:37:37,343][87426] Updated weights for policy 1, policy_version 206510 (0.0012) -[2023-11-28 05:37:37,717][87426] Updated weights for policy 1, policy_version 206520 (0.0012) -[2023-11-28 05:37:38,324][87424] Updated weights for policy 0, policy_version 206887 (0.0009) -[2023-11-28 05:37:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 105832448. Throughput: 0: 2698.2, 1: 2733.7. Samples: 105850412. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:37:38,445][86177] Avg episode reward: [(0, '-516.320'), (1, '-566.900')] -[2023-11-28 05:37:38,714][87424] Updated weights for policy 0, policy_version 206897 (0.0009) -[2023-11-28 05:37:39,091][87424] Updated weights for policy 0, policy_version 206907 (0.0012) -[2023-11-28 05:37:39,724][87426] Updated weights for policy 1, policy_version 206530 (0.0012) -[2023-11-28 05:37:40,105][87426] Updated weights for policy 1, policy_version 206540 (0.0012) -[2023-11-28 05:37:40,482][87426] Updated weights for policy 1, policy_version 206550 (0.0012) -[2023-11-28 05:37:40,850][87426] Updated weights for policy 1, policy_version 206560 (0.0010) -[2023-11-28 05:37:40,971][87424] Updated weights for policy 0, policy_version 206917 (0.0011) -[2023-11-28 05:37:41,365][87424] Updated weights for policy 0, policy_version 206927 (0.0008) -[2023-11-28 05:37:41,755][87424] Updated weights for policy 0, policy_version 206937 (0.0009) -[2023-11-28 05:37:43,252][87426] Updated weights for policy 1, policy_version 206570 (0.0011) -[2023-11-28 05:37:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 105857024. Throughput: 0: 2721.0, 1: 2717.0. Samples: 105875432. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:37:43,445][86177] Avg episode reward: [(0, '-515.650'), (1, '-562.170')] -[2023-11-28 05:37:43,628][87426] Updated weights for policy 1, policy_version 206580 (0.0010) -[2023-11-28 05:37:43,891][87424] Updated weights for policy 0, policy_version 206947 (0.0010) -[2023-11-28 05:37:44,000][87426] Updated weights for policy 1, policy_version 206590 (0.0007) -[2023-11-28 05:37:44,281][87424] Updated weights for policy 0, policy_version 206957 (0.0008) -[2023-11-28 05:37:44,657][87424] Updated weights for policy 0, policy_version 206967 (0.0008) -[2023-11-28 05:37:46,178][87426] Updated weights for policy 1, policy_version 206600 (0.0008) -[2023-11-28 05:37:46,562][87426] Updated weights for policy 1, policy_version 206610 (0.0011) -[2023-11-28 05:37:46,944][87426] Updated weights for policy 1, policy_version 206620 (0.0007) -[2023-11-28 05:37:47,165][87424] Updated weights for policy 0, policy_version 206977 (0.0008) -[2023-11-28 05:37:47,543][87424] Updated weights for policy 0, policy_version 206987 (0.0012) -[2023-11-28 05:37:47,926][87424] Updated weights for policy 0, policy_version 206997 (0.0012) -[2023-11-28 05:37:48,290][87424] Updated weights for policy 0, policy_version 207007 (0.0012) -[2023-11-28 05:37:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 105889792. Throughput: 0: 2700.7, 1: 2717.1. Samples: 105899548. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:37:48,446][86177] Avg episode reward: [(0, '-509.130'), (1, '-563.220')] -[2023-11-28 05:37:49,241][87426] Updated weights for policy 1, policy_version 206630 (0.0010) -[2023-11-28 05:37:49,624][87426] Updated weights for policy 1, policy_version 206640 (0.0012) -[2023-11-28 05:37:49,999][87426] Updated weights for policy 1, policy_version 206650 (0.0012) -[2023-11-28 05:37:50,652][87424] Updated weights for policy 0, policy_version 207017 (0.0010) -[2023-11-28 05:37:51,049][87424] Updated weights for policy 0, policy_version 207027 (0.0008) -[2023-11-28 05:37:51,424][87424] Updated weights for policy 0, policy_version 207037 (0.0008) -[2023-11-28 05:37:52,059][87426] Updated weights for policy 1, policy_version 206660 (0.0012) -[2023-11-28 05:37:52,438][87426] Updated weights for policy 1, policy_version 206670 (0.0009) -[2023-11-28 05:37:52,816][87426] Updated weights for policy 1, policy_version 206680 (0.0009) -[2023-11-28 05:37:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 105914368. Throughput: 0: 2680.0, 1: 2710.5. Samples: 105931004. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:37:53,445][86177] Avg episode reward: [(0, '-510.680'), (1, '-558.770')] -[2023-11-28 05:37:53,655][87424] Updated weights for policy 0, policy_version 207047 (0.0011) -[2023-11-28 05:37:54,036][87424] Updated weights for policy 0, policy_version 207057 (0.0012) -[2023-11-28 05:37:54,426][87424] Updated weights for policy 0, policy_version 207067 (0.0012) -[2023-11-28 05:37:55,307][87426] Updated weights for policy 1, policy_version 206690 (0.0009) -[2023-11-28 05:37:55,679][87426] Updated weights for policy 1, policy_version 206700 (0.0008) -[2023-11-28 05:37:56,058][87426] Updated weights for policy 1, policy_version 206710 (0.0007) -[2023-11-28 05:37:56,434][87426] Updated weights for policy 1, policy_version 206720 (0.0009) -[2023-11-28 05:37:57,102][87424] Updated weights for policy 0, policy_version 207077 (0.0012) -[2023-11-28 05:37:57,492][87424] Updated weights for policy 0, policy_version 207087 (0.0012) -[2023-11-28 05:37:57,876][87424] Updated weights for policy 0, policy_version 207097 (0.0011) -[2023-11-28 05:37:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 105938944. Throughput: 0: 2653.9, 1: 2718.4. Samples: 105955328. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:37:58,445][86177] Avg episode reward: [(0, '-522.680'), (1, '-566.210')] -[2023-11-28 05:37:58,447][87426] Updated weights for policy 1, policy_version 206730 (0.0012) -[2023-11-28 05:37:58,831][87426] Updated weights for policy 1, policy_version 206740 (0.0007) -[2023-11-28 05:37:59,211][87426] Updated weights for policy 1, policy_version 206750 (0.0011) -[2023-11-28 05:37:59,828][87424] Updated weights for policy 0, policy_version 207107 (0.0015) -[2023-11-28 05:38:00,206][87424] Updated weights for policy 0, policy_version 207117 (0.0011) -[2023-11-28 05:38:00,587][87424] Updated weights for policy 0, policy_version 207127 (0.0009) -[2023-11-28 05:38:01,584][87426] Updated weights for policy 1, policy_version 206760 (0.0011) -[2023-11-28 05:38:01,965][87426] Updated weights for policy 1, policy_version 206770 (0.0012) -[2023-11-28 05:38:02,341][87426] Updated weights for policy 1, policy_version 206780 (0.0012) -[2023-11-28 05:38:02,609][87424] Updated weights for policy 0, policy_version 207137 (0.0007) -[2023-11-28 05:38:02,993][87424] Updated weights for policy 0, policy_version 207147 (0.0008) -[2023-11-28 05:38:03,375][87424] Updated weights for policy 0, policy_version 207157 (0.0007) -[2023-11-28 05:38:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 105963520. Throughput: 0: 2665.6, 1: 2716.5. Samples: 105979648. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:38:03,445][86177] Avg episode reward: [(0, '-522.070'), (1, '-555.270')] -[2023-11-28 05:38:03,754][87424] Updated weights for policy 0, policy_version 207167 (0.0008) -[2023-11-28 05:38:04,355][87426] Updated weights for policy 1, policy_version 206790 (0.0010) -[2023-11-28 05:38:04,727][87426] Updated weights for policy 1, policy_version 206800 (0.0011) -[2023-11-28 05:38:05,112][87426] Updated weights for policy 1, policy_version 206810 (0.0012) -[2023-11-28 05:38:05,599][87424] Updated weights for policy 0, policy_version 207177 (0.0008) -[2023-11-28 05:38:05,977][87424] Updated weights for policy 0, policy_version 207187 (0.0007) -[2023-11-28 05:38:06,365][87424] Updated weights for policy 0, policy_version 207197 (0.0007) -[2023-11-28 05:38:07,427][87426] Updated weights for policy 1, policy_version 206820 (0.0012) -[2023-11-28 05:38:07,805][87426] Updated weights for policy 1, policy_version 206830 (0.0012) -[2023-11-28 05:38:08,172][87426] Updated weights for policy 1, policy_version 206840 (0.0012) -[2023-11-28 05:38:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 105988096. Throughput: 0: 2677.5, 1: 2701.6. Samples: 106011868. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:38:08,445][86177] Avg episode reward: [(0, '-521.680'), (1, '-542.860')] -[2023-11-28 05:38:08,668][87424] Updated weights for policy 0, policy_version 207207 (0.0008) -[2023-11-28 05:38:09,059][87424] Updated weights for policy 0, policy_version 207217 (0.0010) -[2023-11-28 05:38:09,431][87424] Updated weights for policy 0, policy_version 207227 (0.0012) -[2023-11-28 05:38:10,708][87426] Updated weights for policy 1, policy_version 206850 (0.0011) -[2023-11-28 05:38:11,083][87426] Updated weights for policy 1, policy_version 206860 (0.0011) -[2023-11-28 05:38:11,472][87426] Updated weights for policy 1, policy_version 206870 (0.0010) -[2023-11-28 05:38:11,689][87424] Updated weights for policy 0, policy_version 207237 (0.0011) -[2023-11-28 05:38:11,843][87426] Updated weights for policy 1, policy_version 206880 (0.0010) -[2023-11-28 05:38:12,071][87424] Updated weights for policy 0, policy_version 207247 (0.0010) -[2023-11-28 05:38:12,447][87424] Updated weights for policy 0, policy_version 207257 (0.0009) -[2023-11-28 05:38:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 106020864. Throughput: 0: 2675.2, 1: 2681.9. Samples: 106034764. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:38:13,445][86177] Avg episode reward: [(0, '-527.160'), (1, '-542.300')] -[2023-11-28 05:38:14,235][87426] Updated weights for policy 1, policy_version 206890 (0.0011) -[2023-11-28 05:38:14,613][87426] Updated weights for policy 1, policy_version 206900 (0.0009) -[2023-11-28 05:38:14,781][87424] Updated weights for policy 0, policy_version 207267 (0.0008) -[2023-11-28 05:38:14,986][87426] Updated weights for policy 1, policy_version 206910 (0.0010) -[2023-11-28 05:38:15,159][87424] Updated weights for policy 0, policy_version 207277 (0.0011) -[2023-11-28 05:38:15,540][87424] Updated weights for policy 0, policy_version 207287 (0.0011) -[2023-11-28 05:38:16,844][87426] Updated weights for policy 1, policy_version 206920 (0.0012) -[2023-11-28 05:38:17,228][87426] Updated weights for policy 1, policy_version 206930 (0.0012) -[2023-11-28 05:38:17,312][87424] Updated weights for policy 0, policy_version 207297 (0.0011) -[2023-11-28 05:38:17,604][87426] Updated weights for policy 1, policy_version 206940 (0.0009) -[2023-11-28 05:38:17,690][87424] Updated weights for policy 0, policy_version 207307 (0.0008) -[2023-11-28 05:38:18,072][87424] Updated weights for policy 0, policy_version 207317 (0.0007) -[2023-11-28 05:38:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 106045440. Throughput: 0: 2694.6, 1: 2703.0. Samples: 106059772. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:38:18,445][86177] Avg episode reward: [(0, '-510.870'), (1, '-542.150')] -[2023-11-28 05:38:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000206944_52977664.pth... -[2023-11-28 05:38:18,462][87424] Updated weights for policy 0, policy_version 207327 (0.0008) -[2023-11-28 05:38:18,485][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000204416_52330496.pth -[2023-11-28 05:38:18,495][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000207328_53075968.pth... -[2023-11-28 05:38:18,527][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000204768_52420608.pth -[2023-11-28 05:38:19,794][87426] Updated weights for policy 1, policy_version 206950 (0.0010) -[2023-11-28 05:38:20,177][87426] Updated weights for policy 1, policy_version 206960 (0.0010) -[2023-11-28 05:38:20,564][87426] Updated weights for policy 1, policy_version 206970 (0.0011) -[2023-11-28 05:38:20,848][87424] Updated weights for policy 0, policy_version 207337 (0.0010) -[2023-11-28 05:38:21,235][87424] Updated weights for policy 0, policy_version 207347 (0.0012) -[2023-11-28 05:38:21,621][87424] Updated weights for policy 0, policy_version 207357 (0.0010) -[2023-11-28 05:38:23,007][87426] Updated weights for policy 1, policy_version 206980 (0.0011) -[2023-11-28 05:38:23,388][87426] Updated weights for policy 1, policy_version 206990 (0.0012) -[2023-11-28 05:38:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 106070016. Throughput: 0: 2684.2, 1: 2688.3. Samples: 106092172. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:38:23,445][86177] Avg episode reward: [(0, '-509.460'), (1, '-547.360')] -[2023-11-28 05:38:23,764][87424] Updated weights for policy 0, policy_version 207367 (0.0010) -[2023-11-28 05:38:23,766][87426] Updated weights for policy 1, policy_version 207000 (0.0011) -[2023-11-28 05:38:24,151][87424] Updated weights for policy 0, policy_version 207377 (0.0011) -[2023-11-28 05:38:24,524][87424] Updated weights for policy 0, policy_version 207387 (0.0012) -[2023-11-28 05:38:25,651][87426] Updated weights for policy 1, policy_version 207010 (0.0010) -[2023-11-28 05:38:26,034][87426] Updated weights for policy 1, policy_version 207020 (0.0008) -[2023-11-28 05:38:26,421][87426] Updated weights for policy 1, policy_version 207030 (0.0010) -[2023-11-28 05:38:26,796][87426] Updated weights for policy 1, policy_version 207040 (0.0012) -[2023-11-28 05:38:26,916][87424] Updated weights for policy 0, policy_version 207397 (0.0012) -[2023-11-28 05:38:27,292][87424] Updated weights for policy 0, policy_version 207407 (0.0009) -[2023-11-28 05:38:27,678][87424] Updated weights for policy 0, policy_version 207417 (0.0008) -[2023-11-28 05:38:28,343][87426] Updated weights for policy 1, policy_version 207050 (0.0011) -[2023-11-28 05:38:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 106102784. Throughput: 0: 2675.4, 1: 2713.2. Samples: 106117916. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:38:28,445][86177] Avg episode reward: [(0, '-508.820'), (1, '-543.910')] -[2023-11-28 05:38:28,727][87426] Updated weights for policy 1, policy_version 207060 (0.0012) -[2023-11-28 05:38:29,103][87426] Updated weights for policy 1, policy_version 207070 (0.0012) -[2023-11-28 05:38:30,070][87424] Updated weights for policy 0, policy_version 207427 (0.0010) -[2023-11-28 05:38:30,467][87424] Updated weights for policy 0, policy_version 207437 (0.0011) -[2023-11-28 05:38:30,840][87424] Updated weights for policy 0, policy_version 207447 (0.0008) -[2023-11-28 05:38:30,900][87426] Updated weights for policy 1, policy_version 207080 (0.0011) -[2023-11-28 05:38:31,283][87426] Updated weights for policy 1, policy_version 207090 (0.0011) -[2023-11-28 05:38:31,681][87426] Updated weights for policy 1, policy_version 207100 (0.0011) -[2023-11-28 05:38:33,206][87424] Updated weights for policy 0, policy_version 207457 (0.0007) -[2023-11-28 05:38:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 106127360. Throughput: 0: 2679.4, 1: 2702.9. Samples: 106141752. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:38:33,445][86177] Avg episode reward: [(0, '-497.380'), (1, '-548.960')] -[2023-11-28 05:38:33,586][87424] Updated weights for policy 0, policy_version 207467 (0.0007) -[2023-11-28 05:38:33,777][87426] Updated weights for policy 1, policy_version 207110 (0.0012) -[2023-11-28 05:38:33,970][87424] Updated weights for policy 0, policy_version 207477 (0.0011) -[2023-11-28 05:38:34,150][87426] Updated weights for policy 1, policy_version 207120 (0.0012) -[2023-11-28 05:38:34,347][87424] Updated weights for policy 0, policy_version 207487 (0.0011) -[2023-11-28 05:38:34,526][87426] Updated weights for policy 1, policy_version 207130 (0.0011) -[2023-11-28 05:38:36,455][87424] Updated weights for policy 0, policy_version 207497 (0.0011) -[2023-11-28 05:38:36,836][87424] Updated weights for policy 0, policy_version 207507 (0.0011) -[2023-11-28 05:38:36,955][87426] Updated weights for policy 1, policy_version 207140 (0.0011) -[2023-11-28 05:38:37,220][87424] Updated weights for policy 0, policy_version 207517 (0.0012) -[2023-11-28 05:38:37,323][87426] Updated weights for policy 1, policy_version 207150 (0.0010) -[2023-11-28 05:38:37,703][87426] Updated weights for policy 1, policy_version 207160 (0.0012) -[2023-11-28 05:38:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 106160128. Throughput: 0: 2707.6, 1: 2711.2. Samples: 106174848. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 05:38:38,445][86177] Avg episode reward: [(0, '-497.450'), (1, '-574.540')] -[2023-11-28 05:38:39,001][87424] Updated weights for policy 0, policy_version 207527 (0.0012) -[2023-11-28 05:38:39,384][87424] Updated weights for policy 0, policy_version 207537 (0.0012) -[2023-11-28 05:38:39,673][87426] Updated weights for policy 1, policy_version 207170 (0.0012) -[2023-11-28 05:38:39,766][87424] Updated weights for policy 0, policy_version 207547 (0.0012) -[2023-11-28 05:38:40,047][87426] Updated weights for policy 1, policy_version 207180 (0.0009) -[2023-11-28 05:38:40,430][87426] Updated weights for policy 1, policy_version 207190 (0.0009) -[2023-11-28 05:38:40,800][87426] Updated weights for policy 1, policy_version 207200 (0.0008) -[2023-11-28 05:38:42,303][87424] Updated weights for policy 0, policy_version 207557 (0.0012) -[2023-11-28 05:38:42,690][87424] Updated weights for policy 0, policy_version 207567 (0.0011) -[2023-11-28 05:38:43,068][87424] Updated weights for policy 0, policy_version 207577 (0.0012) -[2023-11-28 05:38:43,289][87426] Updated weights for policy 1, policy_version 207210 (0.0009) -[2023-11-28 05:38:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 106184704. Throughput: 0: 2725.8, 1: 2708.7. Samples: 106199880. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:38:43,445][86177] Avg episode reward: [(0, '-542.210'), (1, '-591.350')] -[2023-11-28 05:38:43,658][87426] Updated weights for policy 1, policy_version 207220 (0.0010) -[2023-11-28 05:38:44,041][87426] Updated weights for policy 1, policy_version 207230 (0.0008) -[2023-11-28 05:38:45,607][87424] Updated weights for policy 0, policy_version 207587 (0.0010) -[2023-11-28 05:38:45,992][87424] Updated weights for policy 0, policy_version 207597 (0.0008) -[2023-11-28 05:38:46,374][87424] Updated weights for policy 0, policy_version 207607 (0.0007) -[2023-11-28 05:38:46,567][87426] Updated weights for policy 1, policy_version 207240 (0.0010) -[2023-11-28 05:38:46,953][87426] Updated weights for policy 1, policy_version 207250 (0.0011) -[2023-11-28 05:38:47,323][87426] Updated weights for policy 1, policy_version 207260 (0.0011) -[2023-11-28 05:38:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 106209280. Throughput: 0: 2682.6, 1: 2720.6. Samples: 106222792. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:38:48,445][86177] Avg episode reward: [(0, '-568.800'), (1, '-593.290')] -[2023-11-28 05:38:48,602][87424] Updated weights for policy 0, policy_version 207617 (0.0010) -[2023-11-28 05:38:49,003][87424] Updated weights for policy 0, policy_version 207627 (0.0009) -[2023-11-28 05:38:49,352][87426] Updated weights for policy 1, policy_version 207270 (0.0009) -[2023-11-28 05:38:49,369][87424] Updated weights for policy 0, policy_version 207637 (0.0011) -[2023-11-28 05:38:49,745][87426] Updated weights for policy 1, policy_version 207280 (0.0008) -[2023-11-28 05:38:49,754][87424] Updated weights for policy 0, policy_version 207647 (0.0012) -[2023-11-28 05:38:50,119][87426] Updated weights for policy 1, policy_version 207290 (0.0011) -[2023-11-28 05:38:51,655][87424] Updated weights for policy 0, policy_version 207657 (0.0012) -[2023-11-28 05:38:52,029][87424] Updated weights for policy 0, policy_version 207667 (0.0012) -[2023-11-28 05:38:52,416][87424] Updated weights for policy 0, policy_version 207677 (0.0012) -[2023-11-28 05:38:52,589][87426] Updated weights for policy 1, policy_version 207300 (0.0010) -[2023-11-28 05:38:52,955][87426] Updated weights for policy 1, policy_version 207310 (0.0011) -[2023-11-28 05:38:53,337][87426] Updated weights for policy 1, policy_version 207320 (0.0009) -[2023-11-28 05:38:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 106233856. Throughput: 0: 2681.1, 1: 2707.0. Samples: 106254332. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:38:53,445][86177] Avg episode reward: [(0, '-571.980'), (1, '-595.190')] -[2023-11-28 05:38:54,518][87424] Updated weights for policy 0, policy_version 207687 (0.0009) -[2023-11-28 05:38:54,906][87424] Updated weights for policy 0, policy_version 207697 (0.0008) -[2023-11-28 05:38:55,297][87424] Updated weights for policy 0, policy_version 207707 (0.0007) -[2023-11-28 05:38:55,797][87426] Updated weights for policy 1, policy_version 207330 (0.0010) -[2023-11-28 05:38:56,175][87426] Updated weights for policy 1, policy_version 207340 (0.0007) -[2023-11-28 05:38:56,557][87426] Updated weights for policy 1, policy_version 207350 (0.0008) -[2023-11-28 05:38:56,943][87426] Updated weights for policy 1, policy_version 207360 (0.0008) -[2023-11-28 05:38:57,734][87424] Updated weights for policy 0, policy_version 207717 (0.0010) -[2023-11-28 05:38:58,116][87424] Updated weights for policy 0, policy_version 207727 (0.0012) -[2023-11-28 05:38:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 106258432. Throughput: 0: 2693.2, 1: 2734.9. Samples: 106279028. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:38:58,445][86177] Avg episode reward: [(0, '-571.100'), (1, '-564.280')] -[2023-11-28 05:38:58,496][87424] Updated weights for policy 0, policy_version 207737 (0.0011) -[2023-11-28 05:38:58,587][87426] Updated weights for policy 1, policy_version 207370 (0.0008) -[2023-11-28 05:38:58,967][87426] Updated weights for policy 1, policy_version 207380 (0.0010) -[2023-11-28 05:38:59,347][87426] Updated weights for policy 1, policy_version 207390 (0.0008) -[2023-11-28 05:39:00,430][87424] Updated weights for policy 0, policy_version 207747 (0.0011) -[2023-11-28 05:39:00,817][87424] Updated weights for policy 0, policy_version 207757 (0.0009) -[2023-11-28 05:39:01,191][87424] Updated weights for policy 0, policy_version 207767 (0.0009) -[2023-11-28 05:39:01,325][87426] Updated weights for policy 1, policy_version 207400 (0.0011) -[2023-11-28 05:39:01,706][87426] Updated weights for policy 1, policy_version 207410 (0.0011) -[2023-11-28 05:39:02,089][87426] Updated weights for policy 1, policy_version 207420 (0.0011) -[2023-11-28 05:39:03,070][87424] Updated weights for policy 0, policy_version 207777 (0.0008) -[2023-11-28 05:39:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 106291200. Throughput: 0: 2691.6, 1: 2732.9. Samples: 106303876. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:03,445][86177] Avg episode reward: [(0, '-529.190'), (1, '-561.290')] -[2023-11-28 05:39:03,447][87424] Updated weights for policy 0, policy_version 207787 (0.0007) -[2023-11-28 05:39:03,837][87424] Updated weights for policy 0, policy_version 207797 (0.0007) -[2023-11-28 05:39:03,958][87426] Updated weights for policy 1, policy_version 207430 (0.0009) -[2023-11-28 05:39:04,207][87424] Updated weights for policy 0, policy_version 207807 (0.0007) -[2023-11-28 05:39:04,332][87426] Updated weights for policy 1, policy_version 207440 (0.0007) -[2023-11-28 05:39:04,717][87426] Updated weights for policy 1, policy_version 207450 (0.0010) -[2023-11-28 05:39:06,020][87424] Updated weights for policy 0, policy_version 207817 (0.0011) -[2023-11-28 05:39:06,411][87424] Updated weights for policy 0, policy_version 207827 (0.0008) -[2023-11-28 05:39:06,787][87424] Updated weights for policy 0, policy_version 207837 (0.0008) -[2023-11-28 05:39:07,125][87426] Updated weights for policy 1, policy_version 207460 (0.0010) -[2023-11-28 05:39:07,499][87426] Updated weights for policy 1, policy_version 207470 (0.0012) -[2023-11-28 05:39:07,871][87426] Updated weights for policy 1, policy_version 207480 (0.0012) -[2023-11-28 05:39:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 106323968. Throughput: 0: 2680.5, 1: 2738.0. Samples: 106336004. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:08,445][86177] Avg episode reward: [(0, '-514.740'), (1, '-560.760')] -[2023-11-28 05:39:09,178][87424] Updated weights for policy 0, policy_version 207847 (0.0010) -[2023-11-28 05:39:09,558][87424] Updated weights for policy 0, policy_version 207857 (0.0012) -[2023-11-28 05:39:09,944][87424] Updated weights for policy 0, policy_version 207867 (0.0012) -[2023-11-28 05:39:10,474][87426] Updated weights for policy 1, policy_version 207490 (0.0012) -[2023-11-28 05:39:10,850][87426] Updated weights for policy 1, policy_version 207500 (0.0009) -[2023-11-28 05:39:11,233][87426] Updated weights for policy 1, policy_version 207510 (0.0008) -[2023-11-28 05:39:11,608][87426] Updated weights for policy 1, policy_version 207520 (0.0012) -[2023-11-28 05:39:12,333][87424] Updated weights for policy 0, policy_version 207877 (0.0012) -[2023-11-28 05:39:12,709][87424] Updated weights for policy 0, policy_version 207887 (0.0015) -[2023-11-28 05:39:13,093][87424] Updated weights for policy 0, policy_version 207897 (0.0009) -[2023-11-28 05:39:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 106348544. Throughput: 0: 2681.4, 1: 2698.9. Samples: 106360032. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:13,445][86177] Avg episode reward: [(0, '-520.740'), (1, '-558.040')] -[2023-11-28 05:39:13,718][87426] Updated weights for policy 1, policy_version 207530 (0.0009) -[2023-11-28 05:39:14,097][87426] Updated weights for policy 1, policy_version 207540 (0.0007) -[2023-11-28 05:39:14,479][87426] Updated weights for policy 1, policy_version 207550 (0.0011) -[2023-11-28 05:39:15,174][87424] Updated weights for policy 0, policy_version 207907 (0.0009) -[2023-11-28 05:39:15,551][87424] Updated weights for policy 0, policy_version 207917 (0.0012) -[2023-11-28 05:39:15,935][87424] Updated weights for policy 0, policy_version 207927 (0.0012) -[2023-11-28 05:39:16,144][87426] Updated weights for policy 1, policy_version 207560 (0.0008) -[2023-11-28 05:39:16,526][87426] Updated weights for policy 1, policy_version 207570 (0.0012) -[2023-11-28 05:39:16,910][87426] Updated weights for policy 1, policy_version 207580 (0.0011) -[2023-11-28 05:39:17,646][87424] Updated weights for policy 0, policy_version 207937 (0.0012) -[2023-11-28 05:39:18,016][87424] Updated weights for policy 0, policy_version 207947 (0.0009) -[2023-11-28 05:39:18,401][87424] Updated weights for policy 0, policy_version 207957 (0.0009) -[2023-11-28 05:39:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106373120. Throughput: 0: 2700.5, 1: 2704.4. Samples: 106384972. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:18,445][86177] Avg episode reward: [(0, '-516.670'), (1, '-531.470')] -[2023-11-28 05:39:18,782][87424] Updated weights for policy 0, policy_version 207967 (0.0010) -[2023-11-28 05:39:19,466][87426] Updated weights for policy 1, policy_version 207590 (0.0012) -[2023-11-28 05:39:19,838][87426] Updated weights for policy 1, policy_version 207600 (0.0011) -[2023-11-28 05:39:20,231][87426] Updated weights for policy 1, policy_version 207610 (0.0011) -[2023-11-28 05:39:21,251][87424] Updated weights for policy 0, policy_version 207977 (0.0012) -[2023-11-28 05:39:21,632][87424] Updated weights for policy 0, policy_version 207987 (0.0012) -[2023-11-28 05:39:22,019][87424] Updated weights for policy 0, policy_version 207997 (0.0010) -[2023-11-28 05:39:22,775][87426] Updated weights for policy 1, policy_version 207620 (0.0012) -[2023-11-28 05:39:23,149][87426] Updated weights for policy 1, policy_version 207630 (0.0012) -[2023-11-28 05:39:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 106397696. Throughput: 0: 2687.6, 1: 2711.4. Samples: 106417800. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:23,445][86177] Avg episode reward: [(0, '-517.880'), (1, '-520.840')] -[2023-11-28 05:39:23,531][87426] Updated weights for policy 1, policy_version 207640 (0.0012) -[2023-11-28 05:39:24,184][87424] Updated weights for policy 0, policy_version 208007 (0.0008) -[2023-11-28 05:39:24,561][87424] Updated weights for policy 0, policy_version 208017 (0.0008) -[2023-11-28 05:39:24,943][87424] Updated weights for policy 0, policy_version 208027 (0.0007) -[2023-11-28 05:39:26,005][87426] Updated weights for policy 1, policy_version 207650 (0.0011) -[2023-11-28 05:39:26,383][87426] Updated weights for policy 1, policy_version 207660 (0.0007) -[2023-11-28 05:39:26,755][87426] Updated weights for policy 1, policy_version 207670 (0.0010) -[2023-11-28 05:39:27,130][87426] Updated weights for policy 1, policy_version 207680 (0.0011) -[2023-11-28 05:39:27,310][87424] Updated weights for policy 0, policy_version 208037 (0.0009) -[2023-11-28 05:39:27,688][87424] Updated weights for policy 0, policy_version 208047 (0.0010) -[2023-11-28 05:39:28,079][87424] Updated weights for policy 0, policy_version 208057 (0.0008) -[2023-11-28 05:39:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 106430464. Throughput: 0: 2680.3, 1: 2731.6. Samples: 106443420. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:28,445][86177] Avg episode reward: [(0, '-505.370'), (1, '-520.280')] -[2023-11-28 05:39:28,695][87426] Updated weights for policy 1, policy_version 207690 (0.0012) -[2023-11-28 05:39:29,081][87426] Updated weights for policy 1, policy_version 207700 (0.0012) -[2023-11-28 05:39:29,453][87426] Updated weights for policy 1, policy_version 207710 (0.0012) -[2023-11-28 05:39:30,065][87424] Updated weights for policy 0, policy_version 208067 (0.0010) -[2023-11-28 05:39:30,457][87424] Updated weights for policy 0, policy_version 208077 (0.0011) -[2023-11-28 05:39:30,826][87424] Updated weights for policy 0, policy_version 208087 (0.0012) -[2023-11-28 05:39:31,319][87426] Updated weights for policy 1, policy_version 207720 (0.0011) -[2023-11-28 05:39:31,690][87426] Updated weights for policy 1, policy_version 207730 (0.0012) -[2023-11-28 05:39:32,074][87426] Updated weights for policy 1, policy_version 207740 (0.0010) -[2023-11-28 05:39:33,231][87424] Updated weights for policy 0, policy_version 208097 (0.0011) -[2023-11-28 05:39:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106455040. Throughput: 0: 2731.0, 1: 2723.1. Samples: 106468228. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:33,445][86177] Avg episode reward: [(0, '-513.690'), (1, '-522.850')] -[2023-11-28 05:39:33,611][87424] Updated weights for policy 0, policy_version 208107 (0.0012) -[2023-11-28 05:39:33,998][87424] Updated weights for policy 0, policy_version 208117 (0.0012) -[2023-11-28 05:39:34,096][87426] Updated weights for policy 1, policy_version 207750 (0.0009) -[2023-11-28 05:39:34,392][87424] Updated weights for policy 0, policy_version 208127 (0.0012) -[2023-11-28 05:39:34,485][87426] Updated weights for policy 1, policy_version 207760 (0.0008) -[2023-11-28 05:39:34,870][87426] Updated weights for policy 1, policy_version 207770 (0.0010) -[2023-11-28 05:39:36,716][87424] Updated weights for policy 0, policy_version 208137 (0.0009) -[2023-11-28 05:39:36,832][87426] Updated weights for policy 1, policy_version 207780 (0.0011) -[2023-11-28 05:39:37,106][87424] Updated weights for policy 0, policy_version 208147 (0.0011) -[2023-11-28 05:39:37,213][87426] Updated weights for policy 1, policy_version 207790 (0.0011) -[2023-11-28 05:39:37,487][87424] Updated weights for policy 0, policy_version 208157 (0.0011) -[2023-11-28 05:39:37,583][87426] Updated weights for policy 1, policy_version 207800 (0.0012) -[2023-11-28 05:39:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106487808. Throughput: 0: 2735.0, 1: 2729.0. Samples: 106500212. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:38,445][86177] Avg episode reward: [(0, '-517.820'), (1, '-529.500')] -[2023-11-28 05:39:39,238][87424] Updated weights for policy 0, policy_version 208167 (0.0012) -[2023-11-28 05:39:39,623][87424] Updated weights for policy 0, policy_version 208177 (0.0012) -[2023-11-28 05:39:39,998][87424] Updated weights for policy 0, policy_version 208187 (0.0011) -[2023-11-28 05:39:40,127][87426] Updated weights for policy 1, policy_version 207810 (0.0011) -[2023-11-28 05:39:40,503][87426] Updated weights for policy 1, policy_version 207820 (0.0011) -[2023-11-28 05:39:40,881][87426] Updated weights for policy 1, policy_version 207830 (0.0011) -[2023-11-28 05:39:41,256][87426] Updated weights for policy 1, policy_version 207840 (0.0011) -[2023-11-28 05:39:42,350][87424] Updated weights for policy 0, policy_version 208197 (0.0011) -[2023-11-28 05:39:42,734][87424] Updated weights for policy 0, policy_version 208207 (0.0010) -[2023-11-28 05:39:43,115][87424] Updated weights for policy 0, policy_version 208217 (0.0010) -[2023-11-28 05:39:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 106512384. Throughput: 0: 2740.5, 1: 2709.8. Samples: 106524292. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:43,445][86177] Avg episode reward: [(0, '-516.390'), (1, '-528.600')] -[2023-11-28 05:39:43,813][87426] Updated weights for policy 1, policy_version 207850 (0.0012) -[2023-11-28 05:39:44,192][87426] Updated weights for policy 1, policy_version 207860 (0.0012) -[2023-11-28 05:39:44,570][87426] Updated weights for policy 1, policy_version 207870 (0.0012) -[2023-11-28 05:39:45,156][87424] Updated weights for policy 0, policy_version 208227 (0.0011) -[2023-11-28 05:39:45,533][87424] Updated weights for policy 0, policy_version 208237 (0.0012) -[2023-11-28 05:39:45,927][87424] Updated weights for policy 0, policy_version 208247 (0.0012) -[2023-11-28 05:39:47,166][87426] Updated weights for policy 1, policy_version 207880 (0.0011) -[2023-11-28 05:39:47,535][87426] Updated weights for policy 1, policy_version 207890 (0.0012) -[2023-11-28 05:39:47,933][87426] Updated weights for policy 1, policy_version 207900 (0.0012) -[2023-11-28 05:39:48,201][87424] Updated weights for policy 0, policy_version 208257 (0.0011) -[2023-11-28 05:39:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106536960. Throughput: 0: 2741.8, 1: 2688.6. Samples: 106548244. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 05:39:48,445][86177] Avg episode reward: [(0, '-519.420'), (1, '-529.430')] -[2023-11-28 05:39:48,583][87424] Updated weights for policy 0, policy_version 208267 (0.0008) -[2023-11-28 05:39:48,971][87424] Updated weights for policy 0, policy_version 208277 (0.0009) -[2023-11-28 05:39:49,356][87424] Updated weights for policy 0, policy_version 208287 (0.0011) -[2023-11-28 05:39:49,741][87426] Updated weights for policy 1, policy_version 207910 (0.0012) -[2023-11-28 05:39:50,120][87426] Updated weights for policy 1, policy_version 207920 (0.0008) -[2023-11-28 05:39:50,496][87426] Updated weights for policy 1, policy_version 207930 (0.0010) -[2023-11-28 05:39:51,285][87424] Updated weights for policy 0, policy_version 208297 (0.0012) -[2023-11-28 05:39:51,670][87424] Updated weights for policy 0, policy_version 208307 (0.0012) -[2023-11-28 05:39:52,044][87424] Updated weights for policy 0, policy_version 208317 (0.0012) -[2023-11-28 05:39:52,717][87426] Updated weights for policy 1, policy_version 207940 (0.0012) -[2023-11-28 05:39:53,086][87426] Updated weights for policy 1, policy_version 207950 (0.0011) -[2023-11-28 05:39:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 106561536. Throughput: 0: 2761.2, 1: 2679.9. Samples: 106580856. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:39:53,445][86177] Avg episode reward: [(0, '-506.740'), (1, '-528.190')] -[2023-11-28 05:39:53,465][87426] Updated weights for policy 1, policy_version 207960 (0.0012) -[2023-11-28 05:39:54,285][87424] Updated weights for policy 0, policy_version 208327 (0.0012) -[2023-11-28 05:39:54,659][87424] Updated weights for policy 0, policy_version 208337 (0.0011) -[2023-11-28 05:39:55,035][87424] Updated weights for policy 0, policy_version 208347 (0.0009) -[2023-11-28 05:39:56,031][87426] Updated weights for policy 1, policy_version 207970 (0.0011) -[2023-11-28 05:39:56,407][87426] Updated weights for policy 1, policy_version 207980 (0.0010) -[2023-11-28 05:39:56,787][87426] Updated weights for policy 1, policy_version 207990 (0.0007) -[2023-11-28 05:39:56,981][87424] Updated weights for policy 0, policy_version 208357 (0.0008) -[2023-11-28 05:39:57,167][87426] Updated weights for policy 1, policy_version 208000 (0.0007) -[2023-11-28 05:39:57,369][87424] Updated weights for policy 0, policy_version 208367 (0.0008) -[2023-11-28 05:39:57,755][87424] Updated weights for policy 0, policy_version 208377 (0.0008) -[2023-11-28 05:39:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 106594304. Throughput: 0: 2761.1, 1: 2691.8. Samples: 106605412. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:39:58,445][86177] Avg episode reward: [(0, '-507.560'), (1, '-512.350')] -[2023-11-28 05:39:58,705][87426] Updated weights for policy 1, policy_version 208010 (0.0007) -[2023-11-28 05:39:59,089][87426] Updated weights for policy 1, policy_version 208020 (0.0008) -[2023-11-28 05:39:59,454][87424] Updated weights for policy 0, policy_version 208387 (0.0008) -[2023-11-28 05:39:59,467][87426] Updated weights for policy 1, policy_version 208030 (0.0007) -[2023-11-28 05:39:59,846][87424] Updated weights for policy 0, policy_version 208397 (0.0008) -[2023-11-28 05:40:00,224][87424] Updated weights for policy 0, policy_version 208407 (0.0008) -[2023-11-28 05:40:01,937][87426] Updated weights for policy 1, policy_version 208040 (0.0009) -[2023-11-28 05:40:02,312][87426] Updated weights for policy 1, policy_version 208050 (0.0008) -[2023-11-28 05:40:02,609][87424] Updated weights for policy 0, policy_version 208417 (0.0008) -[2023-11-28 05:40:02,695][87426] Updated weights for policy 1, policy_version 208060 (0.0008) -[2023-11-28 05:40:02,992][87424] Updated weights for policy 0, policy_version 208427 (0.0012) -[2023-11-28 05:40:03,378][87424] Updated weights for policy 0, policy_version 208437 (0.0011) -[2023-11-28 05:40:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106618880. Throughput: 0: 2760.4, 1: 2674.9. Samples: 106629564. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:03,445][86177] Avg episode reward: [(0, '-506.600'), (1, '-515.220')] -[2023-11-28 05:40:03,754][87424] Updated weights for policy 0, policy_version 208447 (0.0010) -[2023-11-28 05:40:05,217][87426] Updated weights for policy 1, policy_version 208070 (0.0010) -[2023-11-28 05:40:05,602][87426] Updated weights for policy 1, policy_version 208080 (0.0012) -[2023-11-28 05:40:05,967][87426] Updated weights for policy 1, policy_version 208090 (0.0008) -[2023-11-28 05:40:06,058][87424] Updated weights for policy 0, policy_version 208457 (0.0008) -[2023-11-28 05:40:06,441][87424] Updated weights for policy 0, policy_version 208467 (0.0007) -[2023-11-28 05:40:06,834][87424] Updated weights for policy 0, policy_version 208477 (0.0009) -[2023-11-28 05:40:08,151][87426] Updated weights for policy 1, policy_version 208100 (0.0008) -[2023-11-28 05:40:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 106643456. Throughput: 0: 2768.8, 1: 2671.5. Samples: 106662612. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:08,445][86177] Avg episode reward: [(0, '-500.450'), (1, '-519.970')] -[2023-11-28 05:40:08,531][87426] Updated weights for policy 1, policy_version 208110 (0.0008) -[2023-11-28 05:40:08,912][87426] Updated weights for policy 1, policy_version 208120 (0.0012) -[2023-11-28 05:40:09,234][87424] Updated weights for policy 0, policy_version 208487 (0.0011) -[2023-11-28 05:40:09,620][87424] Updated weights for policy 0, policy_version 208497 (0.0012) -[2023-11-28 05:40:09,997][87424] Updated weights for policy 0, policy_version 208507 (0.0008) -[2023-11-28 05:40:11,081][87426] Updated weights for policy 1, policy_version 208130 (0.0011) -[2023-11-28 05:40:11,453][87426] Updated weights for policy 1, policy_version 208140 (0.0011) -[2023-11-28 05:40:11,823][87426] Updated weights for policy 1, policy_version 208150 (0.0011) -[2023-11-28 05:40:12,195][87424] Updated weights for policy 0, policy_version 208517 (0.0009) -[2023-11-28 05:40:12,202][87426] Updated weights for policy 1, policy_version 208160 (0.0012) -[2023-11-28 05:40:12,576][87424] Updated weights for policy 0, policy_version 208527 (0.0012) -[2023-11-28 05:40:12,958][87424] Updated weights for policy 0, policy_version 208537 (0.0012) -[2023-11-28 05:40:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106676224. Throughput: 0: 2777.3, 1: 2629.2. Samples: 106686712. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:13,445][86177] Avg episode reward: [(0, '-500.520'), (1, '-521.490')] -[2023-11-28 05:40:14,691][87426] Updated weights for policy 1, policy_version 208170 (0.0012) -[2023-11-28 05:40:15,075][87426] Updated weights for policy 1, policy_version 208180 (0.0010) -[2023-11-28 05:40:15,114][87424] Updated weights for policy 0, policy_version 208547 (0.0010) -[2023-11-28 05:40:15,450][87426] Updated weights for policy 1, policy_version 208190 (0.0009) -[2023-11-28 05:40:15,493][87424] Updated weights for policy 0, policy_version 208557 (0.0008) -[2023-11-28 05:40:15,880][87424] Updated weights for policy 0, policy_version 208567 (0.0008) -[2023-11-28 05:40:17,263][87426] Updated weights for policy 1, policy_version 208200 (0.0011) -[2023-11-28 05:40:17,652][87426] Updated weights for policy 1, policy_version 208210 (0.0012) -[2023-11-28 05:40:18,022][87426] Updated weights for policy 1, policy_version 208220 (0.0011) -[2023-11-28 05:40:18,279][87424] Updated weights for policy 0, policy_version 208577 (0.0010) -[2023-11-28 05:40:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106700800. Throughput: 0: 2768.8, 1: 2635.7. Samples: 106711432. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:18,446][86177] Avg episode reward: [(0, '-508.050'), (1, '-522.200')] -[2023-11-28 05:40:18,460][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000208224_53305344.pth... -[2023-11-28 05:40:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000205696_52658176.pth -[2023-11-28 05:40:18,656][87424] Updated weights for policy 0, policy_version 208587 (0.0007) -[2023-11-28 05:40:19,051][87424] Updated weights for policy 0, policy_version 208597 (0.0010) -[2023-11-28 05:40:19,430][87424] Updated weights for policy 0, policy_version 208607 (0.0012) -[2023-11-28 05:40:19,461][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000208608_53403648.pth... -[2023-11-28 05:40:19,490][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000206048_52748288.pth -[2023-11-28 05:40:20,531][87426] Updated weights for policy 1, policy_version 208230 (0.0012) -[2023-11-28 05:40:20,914][87426] Updated weights for policy 1, policy_version 208240 (0.0012) -[2023-11-28 05:40:21,293][87426] Updated weights for policy 1, policy_version 208250 (0.0010) -[2023-11-28 05:40:21,807][87424] Updated weights for policy 0, policy_version 208617 (0.0012) -[2023-11-28 05:40:22,188][87424] Updated weights for policy 0, policy_version 208627 (0.0012) -[2023-11-28 05:40:22,582][87424] Updated weights for policy 0, policy_version 208637 (0.0012) -[2023-11-28 05:40:23,336][87426] Updated weights for policy 1, policy_version 208260 (0.0012) -[2023-11-28 05:40:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 106725376. Throughput: 0: 2747.5, 1: 2638.8. Samples: 106742596. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:23,445][86177] Avg episode reward: [(0, '-509.570'), (1, '-526.270')] -[2023-11-28 05:40:23,716][87426] Updated weights for policy 1, policy_version 208270 (0.0012) -[2023-11-28 05:40:24,099][87426] Updated weights for policy 1, policy_version 208280 (0.0012) -[2023-11-28 05:40:24,749][87424] Updated weights for policy 0, policy_version 208647 (0.0012) -[2023-11-28 05:40:25,130][87424] Updated weights for policy 0, policy_version 208657 (0.0010) -[2023-11-28 05:40:25,516][87424] Updated weights for policy 0, policy_version 208667 (0.0012) -[2023-11-28 05:40:26,478][87426] Updated weights for policy 1, policy_version 208290 (0.0012) -[2023-11-28 05:40:26,850][87426] Updated weights for policy 1, policy_version 208300 (0.0012) -[2023-11-28 05:40:27,224][87426] Updated weights for policy 1, policy_version 208310 (0.0016) -[2023-11-28 05:40:27,236][87424] Updated weights for policy 0, policy_version 208677 (0.0010) -[2023-11-28 05:40:27,606][87426] Updated weights for policy 1, policy_version 208320 (0.0011) -[2023-11-28 05:40:27,613][87424] Updated weights for policy 0, policy_version 208687 (0.0012) -[2023-11-28 05:40:28,003][87424] Updated weights for policy 0, policy_version 208697 (0.0011) -[2023-11-28 05:40:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106758144. Throughput: 0: 2742.0, 1: 2667.6. Samples: 106767728. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:28,445][86177] Avg episode reward: [(0, '-527.090'), (1, '-541.510')] -[2023-11-28 05:40:29,210][87426] Updated weights for policy 1, policy_version 208330 (0.0012) -[2023-11-28 05:40:29,589][87426] Updated weights for policy 1, policy_version 208340 (0.0011) -[2023-11-28 05:40:29,976][87426] Updated weights for policy 1, policy_version 208350 (0.0011) -[2023-11-28 05:40:30,225][87424] Updated weights for policy 0, policy_version 208707 (0.0010) -[2023-11-28 05:40:30,607][87424] Updated weights for policy 0, policy_version 208717 (0.0009) -[2023-11-28 05:40:30,998][87424] Updated weights for policy 0, policy_version 208727 (0.0008) -[2023-11-28 05:40:32,516][87426] Updated weights for policy 1, policy_version 208360 (0.0012) -[2023-11-28 05:40:32,803][87424] Updated weights for policy 0, policy_version 208737 (0.0007) -[2023-11-28 05:40:32,884][87426] Updated weights for policy 1, policy_version 208370 (0.0012) -[2023-11-28 05:40:33,186][87424] Updated weights for policy 0, policy_version 208747 (0.0012) -[2023-11-28 05:40:33,260][87426] Updated weights for policy 1, policy_version 208380 (0.0011) -[2023-11-28 05:40:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 106782720. Throughput: 0: 2763.9, 1: 2691.9. Samples: 106793756. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:33,445][86177] Avg episode reward: [(0, '-522.710'), (1, '-538.240')] -[2023-11-28 05:40:33,553][87424] Updated weights for policy 0, policy_version 208757 (0.0010) -[2023-11-28 05:40:33,946][87424] Updated weights for policy 0, policy_version 208767 (0.0007) -[2023-11-28 05:40:35,540][87426] Updated weights for policy 1, policy_version 208390 (0.0010) -[2023-11-28 05:40:35,925][87426] Updated weights for policy 1, policy_version 208400 (0.0012) -[2023-11-28 05:40:36,036][87424] Updated weights for policy 0, policy_version 208777 (0.0011) -[2023-11-28 05:40:36,307][87426] Updated weights for policy 1, policy_version 208410 (0.0009) -[2023-11-28 05:40:36,413][87424] Updated weights for policy 0, policy_version 208787 (0.0011) -[2023-11-28 05:40:36,803][87424] Updated weights for policy 0, policy_version 208797 (0.0011) -[2023-11-28 05:40:38,094][87426] Updated weights for policy 1, policy_version 208420 (0.0011) -[2023-11-28 05:40:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 106807296. Throughput: 0: 2741.3, 1: 2720.3. Samples: 106826628. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:38,445][86177] Avg episode reward: [(0, '-515.740'), (1, '-540.040')] -[2023-11-28 05:40:38,462][87426] Updated weights for policy 1, policy_version 208430 (0.0011) -[2023-11-28 05:40:38,843][87426] Updated weights for policy 1, policy_version 208440 (0.0008) -[2023-11-28 05:40:39,177][87424] Updated weights for policy 0, policy_version 208807 (0.0010) -[2023-11-28 05:40:39,556][87424] Updated weights for policy 0, policy_version 208817 (0.0008) -[2023-11-28 05:40:39,950][87424] Updated weights for policy 0, policy_version 208827 (0.0009) -[2023-11-28 05:40:41,199][87426] Updated weights for policy 1, policy_version 208450 (0.0008) -[2023-11-28 05:40:41,576][87426] Updated weights for policy 1, policy_version 208460 (0.0012) -[2023-11-28 05:40:41,952][87426] Updated weights for policy 1, policy_version 208470 (0.0012) -[2023-11-28 05:40:42,335][87426] Updated weights for policy 1, policy_version 208480 (0.0010) -[2023-11-28 05:40:42,468][87424] Updated weights for policy 0, policy_version 208837 (0.0010) -[2023-11-28 05:40:42,840][87424] Updated weights for policy 0, policy_version 208847 (0.0012) -[2023-11-28 05:40:43,223][87424] Updated weights for policy 0, policy_version 208857 (0.0010) -[2023-11-28 05:40:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 106831872. Throughput: 0: 2729.2, 1: 2722.1. Samples: 106850720. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:43,445][86177] Avg episode reward: [(0, '-516.260'), (1, '-504.130')] -[2023-11-28 05:40:44,713][87426] Updated weights for policy 1, policy_version 208490 (0.0012) -[2023-11-28 05:40:45,002][87424] Updated weights for policy 0, policy_version 208867 (0.0009) -[2023-11-28 05:40:45,086][87426] Updated weights for policy 1, policy_version 208500 (0.0011) -[2023-11-28 05:40:45,386][87424] Updated weights for policy 0, policy_version 208877 (0.0008) -[2023-11-28 05:40:45,458][87426] Updated weights for policy 1, policy_version 208510 (0.0011) -[2023-11-28 05:40:45,765][87424] Updated weights for policy 0, policy_version 208887 (0.0011) -[2023-11-28 05:40:47,632][87424] Updated weights for policy 0, policy_version 208897 (0.0012) -[2023-11-28 05:40:47,927][87426] Updated weights for policy 1, policy_version 208520 (0.0011) -[2023-11-28 05:40:48,009][87424] Updated weights for policy 0, policy_version 208907 (0.0008) -[2023-11-28 05:40:48,302][87426] Updated weights for policy 1, policy_version 208530 (0.0011) -[2023-11-28 05:40:48,391][87424] Updated weights for policy 0, policy_version 208917 (0.0008) -[2023-11-28 05:40:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 106856448. Throughput: 0: 2721.2, 1: 2729.0. Samples: 106874820. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:48,445][86177] Avg episode reward: [(0, '-519.000'), (1, '-509.450')] -[2023-11-28 05:40:48,677][87426] Updated weights for policy 1, policy_version 208540 (0.0008) -[2023-11-28 05:40:48,785][87424] Updated weights for policy 0, policy_version 208927 (0.0008) -[2023-11-28 05:40:50,862][87426] Updated weights for policy 1, policy_version 208550 (0.0010) -[2023-11-28 05:40:51,227][87424] Updated weights for policy 0, policy_version 208937 (0.0010) -[2023-11-28 05:40:51,237][87426] Updated weights for policy 1, policy_version 208560 (0.0011) -[2023-11-28 05:40:51,607][87424] Updated weights for policy 0, policy_version 208947 (0.0012) -[2023-11-28 05:40:51,618][87426] Updated weights for policy 1, policy_version 208570 (0.0008) -[2023-11-28 05:40:51,992][87424] Updated weights for policy 0, policy_version 208957 (0.0011) -[2023-11-28 05:40:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106889216. Throughput: 0: 2709.9, 1: 2706.2. Samples: 106906336. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:53,445][86177] Avg episode reward: [(0, '-522.940'), (1, '-507.640')] -[2023-11-28 05:40:54,045][87426] Updated weights for policy 1, policy_version 208580 (0.0011) -[2023-11-28 05:40:54,234][87424] Updated weights for policy 0, policy_version 208967 (0.0009) -[2023-11-28 05:40:54,418][87426] Updated weights for policy 1, policy_version 208590 (0.0009) -[2023-11-28 05:40:54,613][87424] Updated weights for policy 0, policy_version 208977 (0.0011) -[2023-11-28 05:40:54,795][87426] Updated weights for policy 1, policy_version 208600 (0.0010) -[2023-11-28 05:40:54,999][87424] Updated weights for policy 0, policy_version 208987 (0.0012) -[2023-11-28 05:40:57,003][87426] Updated weights for policy 1, policy_version 208610 (0.0011) -[2023-11-28 05:40:57,370][87426] Updated weights for policy 1, policy_version 208620 (0.0012) -[2023-11-28 05:40:57,472][87424] Updated weights for policy 0, policy_version 208997 (0.0011) -[2023-11-28 05:40:57,749][87426] Updated weights for policy 1, policy_version 208630 (0.0012) -[2023-11-28 05:40:57,865][87424] Updated weights for policy 0, policy_version 209007 (0.0012) -[2023-11-28 05:40:58,122][87426] Updated weights for policy 1, policy_version 208640 (0.0011) -[2023-11-28 05:40:58,248][87424] Updated weights for policy 0, policy_version 209017 (0.0012) -[2023-11-28 05:40:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 106913792. Throughput: 0: 2695.0, 1: 2730.7. Samples: 106930868. Policy #0 lag: (min: 31.0, avg: 47.8, max: 63.0) -[2023-11-28 05:40:58,445][86177] Avg episode reward: [(0, '-518.490'), (1, '-512.130')] -[2023-11-28 05:41:00,079][87426] Updated weights for policy 1, policy_version 208650 (0.0011) -[2023-11-28 05:41:00,451][87426] Updated weights for policy 1, policy_version 208660 (0.0011) -[2023-11-28 05:41:00,559][87424] Updated weights for policy 0, policy_version 209027 (0.0012) -[2023-11-28 05:41:00,835][87426] Updated weights for policy 1, policy_version 208670 (0.0008) -[2023-11-28 05:41:00,946][87424] Updated weights for policy 0, policy_version 209037 (0.0010) -[2023-11-28 05:41:01,326][87424] Updated weights for policy 0, policy_version 209047 (0.0008) -[2023-11-28 05:41:02,821][87426] Updated weights for policy 1, policy_version 208680 (0.0010) -[2023-11-28 05:41:03,200][87426] Updated weights for policy 1, policy_version 208690 (0.0008) -[2023-11-28 05:41:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 106938368. Throughput: 0: 2688.4, 1: 2736.2. Samples: 106955536. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:03,445][86177] Avg episode reward: [(0, '-558.760'), (1, '-517.200')] -[2023-11-28 05:41:03,587][87426] Updated weights for policy 1, policy_version 208700 (0.0008) -[2023-11-28 05:41:03,647][87424] Updated weights for policy 0, policy_version 209057 (0.0011) -[2023-11-28 05:41:04,025][87424] Updated weights for policy 0, policy_version 209067 (0.0012) -[2023-11-28 05:41:04,407][87424] Updated weights for policy 0, policy_version 209077 (0.0011) -[2023-11-28 05:41:04,791][87424] Updated weights for policy 0, policy_version 209087 (0.0012) -[2023-11-28 05:41:06,090][87426] Updated weights for policy 1, policy_version 208710 (0.0008) -[2023-11-28 05:41:06,479][87426] Updated weights for policy 1, policy_version 208720 (0.0007) -[2023-11-28 05:41:06,618][87424] Updated weights for policy 0, policy_version 209097 (0.0012) -[2023-11-28 05:41:06,850][87426] Updated weights for policy 1, policy_version 208730 (0.0010) -[2023-11-28 05:41:07,001][87424] Updated weights for policy 0, policy_version 209107 (0.0011) -[2023-11-28 05:41:07,381][87424] Updated weights for policy 0, policy_version 209117 (0.0012) -[2023-11-28 05:41:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 106971136. Throughput: 0: 2713.3, 1: 2736.9. Samples: 106987856. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:08,445][86177] Avg episode reward: [(0, '-541.290'), (1, '-511.130')] -[2023-11-28 05:41:08,704][87426] Updated weights for policy 1, policy_version 208740 (0.0011) -[2023-11-28 05:41:09,078][87426] Updated weights for policy 1, policy_version 208750 (0.0010) -[2023-11-28 05:41:09,142][87424] Updated weights for policy 0, policy_version 209127 (0.0011) -[2023-11-28 05:41:09,466][87426] Updated weights for policy 1, policy_version 208760 (0.0008) -[2023-11-28 05:41:09,519][87424] Updated weights for policy 0, policy_version 209137 (0.0011) -[2023-11-28 05:41:09,894][87424] Updated weights for policy 0, policy_version 209147 (0.0012) -[2023-11-28 05:41:11,423][87426] Updated weights for policy 1, policy_version 208770 (0.0008) -[2023-11-28 05:41:11,815][87426] Updated weights for policy 1, policy_version 208780 (0.0008) -[2023-11-28 05:41:12,057][87424] Updated weights for policy 0, policy_version 209157 (0.0012) -[2023-11-28 05:41:12,201][87426] Updated weights for policy 1, policy_version 208790 (0.0011) -[2023-11-28 05:41:12,440][87424] Updated weights for policy 0, policy_version 209167 (0.0009) -[2023-11-28 05:41:12,563][87426] Updated weights for policy 1, policy_version 208800 (0.0011) -[2023-11-28 05:41:12,825][87424] Updated weights for policy 0, policy_version 209177 (0.0008) -[2023-11-28 05:41:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107003904. Throughput: 0: 2729.5, 1: 2739.3. Samples: 107013824. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:13,445][86177] Avg episode reward: [(0, '-538.390'), (1, '-510.870')] -[2023-11-28 05:41:14,729][87426] Updated weights for policy 1, policy_version 208810 (0.0008) -[2023-11-28 05:41:15,108][87426] Updated weights for policy 1, policy_version 208820 (0.0008) -[2023-11-28 05:41:15,410][87424] Updated weights for policy 0, policy_version 209187 (0.0011) -[2023-11-28 05:41:15,488][87426] Updated weights for policy 1, policy_version 208830 (0.0009) -[2023-11-28 05:41:15,790][87424] Updated weights for policy 0, policy_version 209197 (0.0010) -[2023-11-28 05:41:16,173][87424] Updated weights for policy 0, policy_version 209207 (0.0009) -[2023-11-28 05:41:17,911][87426] Updated weights for policy 1, policy_version 208840 (0.0011) -[2023-11-28 05:41:18,217][87424] Updated weights for policy 0, policy_version 209217 (0.0011) -[2023-11-28 05:41:18,300][87426] Updated weights for policy 1, policy_version 208850 (0.0012) -[2023-11-28 05:41:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 107020288. Throughput: 0: 2688.0, 1: 2735.4. Samples: 107037808. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:18,445][86177] Avg episode reward: [(0, '-499.690'), (1, '-512.680')] -[2023-11-28 05:41:18,607][87424] Updated weights for policy 0, policy_version 209227 (0.0011) -[2023-11-28 05:41:18,674][87426] Updated weights for policy 1, policy_version 208860 (0.0011) -[2023-11-28 05:41:18,988][87424] Updated weights for policy 0, policy_version 209237 (0.0012) -[2023-11-28 05:41:19,366][87424] Updated weights for policy 0, policy_version 209247 (0.0012) -[2023-11-28 05:41:20,981][87426] Updated weights for policy 1, policy_version 208870 (0.0011) -[2023-11-28 05:41:21,295][87424] Updated weights for policy 0, policy_version 209257 (0.0010) -[2023-11-28 05:41:21,364][87426] Updated weights for policy 1, policy_version 208880 (0.0012) -[2023-11-28 05:41:21,674][87424] Updated weights for policy 0, policy_version 209267 (0.0011) -[2023-11-28 05:41:21,742][87426] Updated weights for policy 1, policy_version 208890 (0.0010) -[2023-11-28 05:41:22,062][87424] Updated weights for policy 0, policy_version 209277 (0.0009) -[2023-11-28 05:41:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107053056. Throughput: 0: 2714.2, 1: 2702.7. Samples: 107070388. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:23,445][86177] Avg episode reward: [(0, '-496.580'), (1, '-521.210')] -[2023-11-28 05:41:23,927][87426] Updated weights for policy 1, policy_version 208900 (0.0011) -[2023-11-28 05:41:24,311][87426] Updated weights for policy 1, policy_version 208910 (0.0012) -[2023-11-28 05:41:24,639][87424] Updated weights for policy 0, policy_version 209287 (0.0008) -[2023-11-28 05:41:24,684][87426] Updated weights for policy 1, policy_version 208920 (0.0012) -[2023-11-28 05:41:25,026][87424] Updated weights for policy 0, policy_version 209297 (0.0008) -[2023-11-28 05:41:25,413][87424] Updated weights for policy 0, policy_version 209307 (0.0012) -[2023-11-28 05:41:26,437][87426] Updated weights for policy 1, policy_version 208930 (0.0011) -[2023-11-28 05:41:26,817][87426] Updated weights for policy 1, policy_version 208940 (0.0012) -[2023-11-28 05:41:27,212][87426] Updated weights for policy 1, policy_version 208950 (0.0012) -[2023-11-28 05:41:27,258][87424] Updated weights for policy 0, policy_version 209317 (0.0010) -[2023-11-28 05:41:27,584][87426] Updated weights for policy 1, policy_version 208960 (0.0012) -[2023-11-28 05:41:27,647][87424] Updated weights for policy 0, policy_version 209327 (0.0008) -[2023-11-28 05:41:28,024][87424] Updated weights for policy 0, policy_version 209337 (0.0007) -[2023-11-28 05:41:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107085824. Throughput: 0: 2730.7, 1: 2737.9. Samples: 107096804. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:28,445][86177] Avg episode reward: [(0, '-516.370'), (1, '-539.200')] -[2023-11-28 05:41:29,130][87426] Updated weights for policy 1, policy_version 208970 (0.0012) -[2023-11-28 05:41:29,503][87426] Updated weights for policy 1, policy_version 208980 (0.0012) -[2023-11-28 05:41:29,881][87426] Updated weights for policy 1, policy_version 208990 (0.0011) -[2023-11-28 05:41:30,566][87424] Updated weights for policy 0, policy_version 209347 (0.0008) -[2023-11-28 05:41:30,946][87424] Updated weights for policy 0, policy_version 209357 (0.0007) -[2023-11-28 05:41:31,327][87424] Updated weights for policy 0, policy_version 209367 (0.0007) -[2023-11-28 05:41:32,235][87426] Updated weights for policy 1, policy_version 209000 (0.0009) -[2023-11-28 05:41:32,615][87426] Updated weights for policy 1, policy_version 209010 (0.0008) -[2023-11-28 05:41:32,995][87426] Updated weights for policy 1, policy_version 209020 (0.0007) -[2023-11-28 05:41:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 107110400. Throughput: 0: 2711.0, 1: 2751.2. Samples: 107120620. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:33,445][86177] Avg episode reward: [(0, '-513.990'), (1, '-533.190')] -[2023-11-28 05:41:33,651][87424] Updated weights for policy 0, policy_version 209377 (0.0009) -[2023-11-28 05:41:34,029][87424] Updated weights for policy 0, policy_version 209387 (0.0012) -[2023-11-28 05:41:34,415][87424] Updated weights for policy 0, policy_version 209397 (0.0012) -[2023-11-28 05:41:34,799][87424] Updated weights for policy 0, policy_version 209407 (0.0012) -[2023-11-28 05:41:35,249][87426] Updated weights for policy 1, policy_version 209030 (0.0010) -[2023-11-28 05:41:35,629][87426] Updated weights for policy 1, policy_version 209040 (0.0009) -[2023-11-28 05:41:36,009][87426] Updated weights for policy 1, policy_version 209050 (0.0007) -[2023-11-28 05:41:36,992][87424] Updated weights for policy 0, policy_version 209417 (0.0012) -[2023-11-28 05:41:37,371][87424] Updated weights for policy 0, policy_version 209427 (0.0012) -[2023-11-28 05:41:37,746][87424] Updated weights for policy 0, policy_version 209437 (0.0009) -[2023-11-28 05:41:38,097][87426] Updated weights for policy 1, policy_version 209060 (0.0007) -[2023-11-28 05:41:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107134976. Throughput: 0: 2695.1, 1: 2767.1. Samples: 107152136. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:38,445][86177] Avg episode reward: [(0, '-513.380'), (1, '-599.870')] -[2023-11-28 05:41:38,476][87426] Updated weights for policy 1, policy_version 209070 (0.0007) -[2023-11-28 05:41:38,861][87426] Updated weights for policy 1, policy_version 209080 (0.0008) -[2023-11-28 05:41:40,304][87424] Updated weights for policy 0, policy_version 209447 (0.0008) -[2023-11-28 05:41:40,687][87424] Updated weights for policy 0, policy_version 209457 (0.0008) -[2023-11-28 05:41:41,067][87424] Updated weights for policy 0, policy_version 209467 (0.0009) -[2023-11-28 05:41:41,326][87426] Updated weights for policy 1, policy_version 209090 (0.0010) -[2023-11-28 05:41:41,710][87426] Updated weights for policy 1, policy_version 209100 (0.0008) -[2023-11-28 05:41:42,094][87426] Updated weights for policy 1, policy_version 209110 (0.0010) -[2023-11-28 05:41:42,466][87426] Updated weights for policy 1, policy_version 209120 (0.0009) -[2023-11-28 05:41:43,106][87424] Updated weights for policy 0, policy_version 209477 (0.0011) -[2023-11-28 05:41:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 107159552. Throughput: 0: 2702.0, 1: 2739.0. Samples: 107175716. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:43,445][86177] Avg episode reward: [(0, '-518.630'), (1, '-580.380')] -[2023-11-28 05:41:43,483][87424] Updated weights for policy 0, policy_version 209487 (0.0011) -[2023-11-28 05:41:43,869][87424] Updated weights for policy 0, policy_version 209497 (0.0012) -[2023-11-28 05:41:44,643][87426] Updated weights for policy 1, policy_version 209130 (0.0011) -[2023-11-28 05:41:45,022][87426] Updated weights for policy 1, policy_version 209140 (0.0011) -[2023-11-28 05:41:45,402][87426] Updated weights for policy 1, policy_version 209150 (0.0011) -[2023-11-28 05:41:46,134][87424] Updated weights for policy 0, policy_version 209507 (0.0011) -[2023-11-28 05:41:46,518][87424] Updated weights for policy 0, policy_version 209517 (0.0007) -[2023-11-28 05:41:46,901][87424] Updated weights for policy 0, policy_version 209527 (0.0009) -[2023-11-28 05:41:47,177][87426] Updated weights for policy 1, policy_version 209160 (0.0010) -[2023-11-28 05:41:47,552][87426] Updated weights for policy 1, policy_version 209170 (0.0008) -[2023-11-28 05:41:47,936][87426] Updated weights for policy 1, policy_version 209180 (0.0011) -[2023-11-28 05:41:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 107192320. Throughput: 0: 2714.5, 1: 2753.2. Samples: 107201584. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:48,445][86177] Avg episode reward: [(0, '-518.700'), (1, '-581.780')] -[2023-11-28 05:41:48,720][87424] Updated weights for policy 0, policy_version 209537 (0.0008) -[2023-11-28 05:41:49,105][87424] Updated weights for policy 0, policy_version 209547 (0.0008) -[2023-11-28 05:41:49,485][87424] Updated weights for policy 0, policy_version 209557 (0.0009) -[2023-11-28 05:41:49,868][87424] Updated weights for policy 0, policy_version 209567 (0.0008) -[2023-11-28 05:41:50,313][87426] Updated weights for policy 1, policy_version 209190 (0.0009) -[2023-11-28 05:41:50,683][87426] Updated weights for policy 1, policy_version 209200 (0.0010) -[2023-11-28 05:41:51,058][87426] Updated weights for policy 1, policy_version 209210 (0.0007) -[2023-11-28 05:41:52,307][87424] Updated weights for policy 0, policy_version 209577 (0.0012) -[2023-11-28 05:41:52,700][87424] Updated weights for policy 0, policy_version 209587 (0.0011) -[2023-11-28 05:41:53,073][87424] Updated weights for policy 0, policy_version 209597 (0.0010) -[2023-11-28 05:41:53,166][87426] Updated weights for policy 1, policy_version 209220 (0.0011) -[2023-11-28 05:41:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107216896. Throughput: 0: 2702.0, 1: 2746.9. Samples: 107233060. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:53,445][86177] Avg episode reward: [(0, '-509.890'), (1, '-580.780')] -[2023-11-28 05:41:53,551][87426] Updated weights for policy 1, policy_version 209230 (0.0012) -[2023-11-28 05:41:53,930][87426] Updated weights for policy 1, policy_version 209240 (0.0012) -[2023-11-28 05:41:55,376][87424] Updated weights for policy 0, policy_version 209607 (0.0010) -[2023-11-28 05:41:55,761][87424] Updated weights for policy 0, policy_version 209617 (0.0007) -[2023-11-28 05:41:56,148][87424] Updated weights for policy 0, policy_version 209627 (0.0007) -[2023-11-28 05:41:56,207][87426] Updated weights for policy 1, policy_version 209250 (0.0012) -[2023-11-28 05:41:56,585][87426] Updated weights for policy 1, policy_version 209260 (0.0008) -[2023-11-28 05:41:56,966][87426] Updated weights for policy 1, policy_version 209270 (0.0007) -[2023-11-28 05:41:57,346][87426] Updated weights for policy 1, policy_version 209280 (0.0007) -[2023-11-28 05:41:57,945][87424] Updated weights for policy 0, policy_version 209637 (0.0007) -[2023-11-28 05:41:58,327][87424] Updated weights for policy 0, policy_version 209647 (0.0008) -[2023-11-28 05:41:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 107241472. Throughput: 0: 2696.3, 1: 2722.6. Samples: 107257676. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:41:58,445][86177] Avg episode reward: [(0, '-508.090'), (1, '-513.920')] -[2023-11-28 05:41:58,713][87424] Updated weights for policy 0, policy_version 209657 (0.0007) -[2023-11-28 05:41:59,891][87426] Updated weights for policy 1, policy_version 209290 (0.0010) -[2023-11-28 05:42:00,259][87426] Updated weights for policy 1, policy_version 209300 (0.0012) -[2023-11-28 05:42:00,574][87424] Updated weights for policy 0, policy_version 209667 (0.0010) -[2023-11-28 05:42:00,643][87426] Updated weights for policy 1, policy_version 209310 (0.0011) -[2023-11-28 05:42:00,954][87424] Updated weights for policy 0, policy_version 209677 (0.0011) -[2023-11-28 05:42:01,337][87424] Updated weights for policy 0, policy_version 209687 (0.0009) -[2023-11-28 05:42:03,124][87426] Updated weights for policy 1, policy_version 209320 (0.0012) -[2023-11-28 05:42:03,319][87424] Updated weights for policy 0, policy_version 209697 (0.0009) -[2023-11-28 05:42:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 107266048. Throughput: 0: 2710.3, 1: 2719.7. Samples: 107282160. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:42:03,445][86177] Avg episode reward: [(0, '-506.180'), (1, '-510.740')] -[2023-11-28 05:42:03,503][87426] Updated weights for policy 1, policy_version 209330 (0.0012) -[2023-11-28 05:42:03,702][87424] Updated weights for policy 0, policy_version 209707 (0.0011) -[2023-11-28 05:42:03,877][87426] Updated weights for policy 1, policy_version 209340 (0.0011) -[2023-11-28 05:42:04,084][87424] Updated weights for policy 0, policy_version 209717 (0.0012) -[2023-11-28 05:42:04,468][87424] Updated weights for policy 0, policy_version 209727 (0.0009) -[2023-11-28 05:42:05,784][87426] Updated weights for policy 1, policy_version 209350 (0.0010) -[2023-11-28 05:42:06,160][87426] Updated weights for policy 1, policy_version 209360 (0.0011) -[2023-11-28 05:42:06,527][87426] Updated weights for policy 1, policy_version 209370 (0.0011) -[2023-11-28 05:42:06,529][87424] Updated weights for policy 0, policy_version 209737 (0.0011) -[2023-11-28 05:42:06,909][87424] Updated weights for policy 0, policy_version 209747 (0.0012) -[2023-11-28 05:42:07,296][87424] Updated weights for policy 0, policy_version 209757 (0.0012) -[2023-11-28 05:42:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 107298816. Throughput: 0: 2722.9, 1: 2731.5. Samples: 107315836. Policy #0 lag: (min: 15.0, avg: 32.0, max: 57.0) -[2023-11-28 05:42:08,445][86177] Avg episode reward: [(0, '-506.720'), (1, '-512.850')] -[2023-11-28 05:42:08,564][87426] Updated weights for policy 1, policy_version 209380 (0.0011) -[2023-11-28 05:42:08,938][87426] Updated weights for policy 1, policy_version 209390 (0.0011) -[2023-11-28 05:42:09,313][87426] Updated weights for policy 1, policy_version 209400 (0.0012) -[2023-11-28 05:42:09,631][87424] Updated weights for policy 0, policy_version 209767 (0.0011) -[2023-11-28 05:42:10,022][87424] Updated weights for policy 0, policy_version 209777 (0.0012) -[2023-11-28 05:42:10,399][87424] Updated weights for policy 0, policy_version 209787 (0.0012) -[2023-11-28 05:42:11,669][87426] Updated weights for policy 1, policy_version 209410 (0.0011) -[2023-11-28 05:42:12,044][87426] Updated weights for policy 1, policy_version 209420 (0.0012) -[2023-11-28 05:42:12,383][87424] Updated weights for policy 0, policy_version 209797 (0.0012) -[2023-11-28 05:42:12,423][87426] Updated weights for policy 1, policy_version 209430 (0.0012) -[2023-11-28 05:42:12,755][87424] Updated weights for policy 0, policy_version 209807 (0.0009) -[2023-11-28 05:42:12,798][87426] Updated weights for policy 1, policy_version 209440 (0.0011) -[2023-11-28 05:42:13,135][87424] Updated weights for policy 0, policy_version 209817 (0.0011) -[2023-11-28 05:42:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107331584. Throughput: 0: 2722.2, 1: 2691.0. Samples: 107340400. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:13,445][86177] Avg episode reward: [(0, '-494.600'), (1, '-516.610')] -[2023-11-28 05:42:14,861][87424] Updated weights for policy 0, policy_version 209827 (0.0012) -[2023-11-28 05:42:14,974][87426] Updated weights for policy 1, policy_version 209450 (0.0009) -[2023-11-28 05:42:15,235][87424] Updated weights for policy 0, policy_version 209837 (0.0009) -[2023-11-28 05:42:15,365][87426] Updated weights for policy 1, policy_version 209460 (0.0010) -[2023-11-28 05:42:15,622][87424] Updated weights for policy 0, policy_version 209847 (0.0010) -[2023-11-28 05:42:15,748][87426] Updated weights for policy 1, policy_version 209470 (0.0008) -[2023-11-28 05:42:17,721][87426] Updated weights for policy 1, policy_version 209480 (0.0012) -[2023-11-28 05:42:17,990][87424] Updated weights for policy 0, policy_version 209857 (0.0011) -[2023-11-28 05:42:18,094][87426] Updated weights for policy 1, policy_version 209490 (0.0012) -[2023-11-28 05:42:18,372][87424] Updated weights for policy 0, policy_version 209867 (0.0011) -[2023-11-28 05:42:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 107347968. Throughput: 0: 2763.1, 1: 2696.0. Samples: 107366280. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:18,445][86177] Avg episode reward: [(0, '-493.730'), (1, '-528.150')] -[2023-11-28 05:42:18,470][87426] Updated weights for policy 1, policy_version 209500 (0.0011) -[2023-11-28 05:42:18,620][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000209504_53633024.pth... -[2023-11-28 05:42:18,652][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000206944_52977664.pth -[2023-11-28 05:42:18,752][87424] Updated weights for policy 0, policy_version 209877 (0.0010) -[2023-11-28 05:42:19,138][87424] Updated weights for policy 0, policy_version 209887 (0.0010) -[2023-11-28 05:42:19,175][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000209888_53731328.pth... -[2023-11-28 05:42:19,222][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000207328_53075968.pth -[2023-11-28 05:42:20,652][87426] Updated weights for policy 1, policy_version 209510 (0.0010) -[2023-11-28 05:42:21,044][87426] Updated weights for policy 1, policy_version 209520 (0.0008) -[2023-11-28 05:42:21,421][87426] Updated weights for policy 1, policy_version 209530 (0.0008) -[2023-11-28 05:42:21,690][87424] Updated weights for policy 0, policy_version 209897 (0.0009) -[2023-11-28 05:42:22,072][87424] Updated weights for policy 0, policy_version 209907 (0.0009) -[2023-11-28 05:42:22,463][87424] Updated weights for policy 0, policy_version 209917 (0.0011) -[2023-11-28 05:42:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 107380736. Throughput: 0: 2763.9, 1: 2699.7. Samples: 107398000. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:23,445][86177] Avg episode reward: [(0, '-494.870'), (1, '-541.060')] -[2023-11-28 05:42:23,639][87426] Updated weights for policy 1, policy_version 209540 (0.0008) -[2023-11-28 05:42:24,013][87426] Updated weights for policy 1, policy_version 209550 (0.0008) -[2023-11-28 05:42:24,397][87426] Updated weights for policy 1, policy_version 209560 (0.0007) -[2023-11-28 05:42:24,523][87424] Updated weights for policy 0, policy_version 209927 (0.0009) -[2023-11-28 05:42:24,909][87424] Updated weights for policy 0, policy_version 209937 (0.0009) -[2023-11-28 05:42:25,299][87424] Updated weights for policy 0, policy_version 209947 (0.0012) -[2023-11-28 05:42:26,841][87426] Updated weights for policy 1, policy_version 209570 (0.0008) -[2023-11-28 05:42:27,209][87426] Updated weights for policy 1, policy_version 209580 (0.0011) -[2023-11-28 05:42:27,464][87424] Updated weights for policy 0, policy_version 209957 (0.0012) -[2023-11-28 05:42:27,586][87426] Updated weights for policy 1, policy_version 209590 (0.0011) -[2023-11-28 05:42:27,853][87424] Updated weights for policy 0, policy_version 209967 (0.0009) -[2023-11-28 05:42:27,967][87426] Updated weights for policy 1, policy_version 209600 (0.0012) -[2023-11-28 05:42:28,235][87424] Updated weights for policy 0, policy_version 209977 (0.0010) -[2023-11-28 05:42:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 107405312. Throughput: 0: 2760.2, 1: 2713.6. Samples: 107422036. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:28,445][86177] Avg episode reward: [(0, '-506.210'), (1, '-541.910')] -[2023-11-28 05:42:30,026][87426] Updated weights for policy 1, policy_version 209610 (0.0009) -[2023-11-28 05:42:30,408][87426] Updated weights for policy 1, policy_version 209620 (0.0008) -[2023-11-28 05:42:30,485][87424] Updated weights for policy 0, policy_version 209987 (0.0010) -[2023-11-28 05:42:30,798][87426] Updated weights for policy 1, policy_version 209630 (0.0009) -[2023-11-28 05:42:30,870][87424] Updated weights for policy 0, policy_version 209997 (0.0008) -[2023-11-28 05:42:31,254][87424] Updated weights for policy 0, policy_version 210007 (0.0007) -[2023-11-28 05:42:33,098][87426] Updated weights for policy 1, policy_version 209640 (0.0011) -[2023-11-28 05:42:33,432][87424] Updated weights for policy 0, policy_version 210017 (0.0008) -[2023-11-28 05:42:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 107429888. Throughput: 0: 2735.1, 1: 2689.6. Samples: 107445696. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:33,445][86177] Avg episode reward: [(0, '-513.620'), (1, '-545.180')] -[2023-11-28 05:42:33,483][87426] Updated weights for policy 1, policy_version 209650 (0.0010) -[2023-11-28 05:42:33,808][87424] Updated weights for policy 0, policy_version 210027 (0.0008) -[2023-11-28 05:42:33,853][87426] Updated weights for policy 1, policy_version 209660 (0.0007) -[2023-11-28 05:42:34,193][87424] Updated weights for policy 0, policy_version 210037 (0.0008) -[2023-11-28 05:42:34,580][87424] Updated weights for policy 0, policy_version 210047 (0.0007) -[2023-11-28 05:42:35,856][87426] Updated weights for policy 1, policy_version 209670 (0.0010) -[2023-11-28 05:42:36,241][87426] Updated weights for policy 1, policy_version 209680 (0.0011) -[2023-11-28 05:42:36,613][87426] Updated weights for policy 1, policy_version 209690 (0.0012) -[2023-11-28 05:42:36,762][87424] Updated weights for policy 0, policy_version 210057 (0.0008) -[2023-11-28 05:42:37,139][87424] Updated weights for policy 0, policy_version 210067 (0.0012) -[2023-11-28 05:42:37,521][87424] Updated weights for policy 0, policy_version 210077 (0.0012) -[2023-11-28 05:42:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107462656. Throughput: 0: 2733.8, 1: 2687.1. Samples: 107477000. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:38,445][86177] Avg episode reward: [(0, '-512.690'), (1, '-533.660')] -[2023-11-28 05:42:38,875][87426] Updated weights for policy 1, policy_version 209700 (0.0011) -[2023-11-28 05:42:39,260][87426] Updated weights for policy 1, policy_version 209710 (0.0007) -[2023-11-28 05:42:39,639][87426] Updated weights for policy 1, policy_version 209720 (0.0008) -[2023-11-28 05:42:40,108][87424] Updated weights for policy 0, policy_version 210087 (0.0010) -[2023-11-28 05:42:40,479][87424] Updated weights for policy 0, policy_version 210097 (0.0009) -[2023-11-28 05:42:40,864][87424] Updated weights for policy 0, policy_version 210107 (0.0011) -[2023-11-28 05:42:41,903][87426] Updated weights for policy 1, policy_version 209730 (0.0010) -[2023-11-28 05:42:42,279][87426] Updated weights for policy 1, policy_version 209740 (0.0011) -[2023-11-28 05:42:42,662][87426] Updated weights for policy 1, policy_version 209750 (0.0011) -[2023-11-28 05:42:43,046][87426] Updated weights for policy 1, policy_version 209760 (0.0008) -[2023-11-28 05:42:43,259][87424] Updated weights for policy 0, policy_version 210117 (0.0012) -[2023-11-28 05:42:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 107487232. Throughput: 0: 2713.0, 1: 2702.6. Samples: 107501376. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:43,445][86177] Avg episode reward: [(0, '-513.060'), (1, '-516.970')] -[2023-11-28 05:42:43,641][87424] Updated weights for policy 0, policy_version 210127 (0.0012) -[2023-11-28 05:42:44,026][87424] Updated weights for policy 0, policy_version 210137 (0.0012) -[2023-11-28 05:42:44,946][87426] Updated weights for policy 1, policy_version 209770 (0.0012) -[2023-11-28 05:42:45,321][87426] Updated weights for policy 1, policy_version 209780 (0.0011) -[2023-11-28 05:42:45,705][87426] Updated weights for policy 1, policy_version 209790 (0.0011) -[2023-11-28 05:42:45,990][87424] Updated weights for policy 0, policy_version 210147 (0.0011) -[2023-11-28 05:42:46,371][87424] Updated weights for policy 0, policy_version 210157 (0.0008) -[2023-11-28 05:42:46,752][87424] Updated weights for policy 0, policy_version 210167 (0.0008) -[2023-11-28 05:42:48,053][87426] Updated weights for policy 1, policy_version 209800 (0.0009) -[2023-11-28 05:42:48,439][87426] Updated weights for policy 1, policy_version 209810 (0.0011) -[2023-11-28 05:42:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 107511808. Throughput: 0: 2721.7, 1: 2709.5. Samples: 107526564. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:48,446][86177] Avg episode reward: [(0, '-500.630'), (1, '-523.650')] -[2023-11-28 05:42:48,773][87424] Updated weights for policy 0, policy_version 210177 (0.0010) -[2023-11-28 05:42:48,819][87426] Updated weights for policy 1, policy_version 209820 (0.0011) -[2023-11-28 05:42:49,152][87424] Updated weights for policy 0, policy_version 210187 (0.0008) -[2023-11-28 05:42:49,530][87424] Updated weights for policy 0, policy_version 210197 (0.0008) -[2023-11-28 05:42:49,914][87424] Updated weights for policy 0, policy_version 210207 (0.0009) -[2023-11-28 05:42:51,273][87426] Updated weights for policy 1, policy_version 209830 (0.0009) -[2023-11-28 05:42:51,651][87426] Updated weights for policy 1, policy_version 209840 (0.0009) -[2023-11-28 05:42:52,028][87426] Updated weights for policy 1, policy_version 209850 (0.0010) -[2023-11-28 05:42:52,507][87424] Updated weights for policy 0, policy_version 210217 (0.0011) -[2023-11-28 05:42:52,885][87424] Updated weights for policy 0, policy_version 210227 (0.0009) -[2023-11-28 05:42:53,270][87424] Updated weights for policy 0, policy_version 210237 (0.0008) -[2023-11-28 05:42:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107544576. Throughput: 0: 2704.7, 1: 2696.4. Samples: 107558884. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:53,445][86177] Avg episode reward: [(0, '-504.190'), (1, '-532.890')] -[2023-11-28 05:42:54,410][87426] Updated weights for policy 1, policy_version 209860 (0.0010) -[2023-11-28 05:42:54,791][87426] Updated weights for policy 1, policy_version 209870 (0.0012) -[2023-11-28 05:42:55,168][87426] Updated weights for policy 1, policy_version 209880 (0.0012) -[2023-11-28 05:42:55,522][87424] Updated weights for policy 0, policy_version 210247 (0.0012) -[2023-11-28 05:42:55,903][87424] Updated weights for policy 0, policy_version 210257 (0.0012) -[2023-11-28 05:42:56,281][87424] Updated weights for policy 0, policy_version 210267 (0.0012) -[2023-11-28 05:42:57,154][87426] Updated weights for policy 1, policy_version 209890 (0.0010) -[2023-11-28 05:42:57,526][87426] Updated weights for policy 1, policy_version 209900 (0.0012) -[2023-11-28 05:42:57,907][87426] Updated weights for policy 1, policy_version 209910 (0.0012) -[2023-11-28 05:42:58,194][87424] Updated weights for policy 0, policy_version 210277 (0.0012) -[2023-11-28 05:42:58,283][87426] Updated weights for policy 1, policy_version 209920 (0.0011) -[2023-11-28 05:42:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107569152. Throughput: 0: 2688.7, 1: 2689.2. Samples: 107582404. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:42:58,445][86177] Avg episode reward: [(0, '-509.760'), (1, '-542.620')] -[2023-11-28 05:42:58,578][87424] Updated weights for policy 0, policy_version 210287 (0.0008) -[2023-11-28 05:42:58,962][87424] Updated weights for policy 0, policy_version 210297 (0.0011) -[2023-11-28 05:43:00,859][87426] Updated weights for policy 1, policy_version 209930 (0.0012) -[2023-11-28 05:43:01,222][87424] Updated weights for policy 0, policy_version 210307 (0.0010) -[2023-11-28 05:43:01,238][87426] Updated weights for policy 1, policy_version 209940 (0.0009) -[2023-11-28 05:43:01,603][87424] Updated weights for policy 0, policy_version 210317 (0.0009) -[2023-11-28 05:43:01,617][87426] Updated weights for policy 1, policy_version 209950 (0.0007) -[2023-11-28 05:43:01,998][87424] Updated weights for policy 0, policy_version 210327 (0.0009) -[2023-11-28 05:43:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107593728. Throughput: 0: 2660.7, 1: 2700.7. Samples: 107607544. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:43:03,446][86177] Avg episode reward: [(0, '-540.010'), (1, '-546.590')] -[2023-11-28 05:43:03,689][87426] Updated weights for policy 1, policy_version 209960 (0.0008) -[2023-11-28 05:43:04,070][87426] Updated weights for policy 1, policy_version 209970 (0.0007) -[2023-11-28 05:43:04,260][87424] Updated weights for policy 0, policy_version 210337 (0.0009) -[2023-11-28 05:43:04,462][87426] Updated weights for policy 1, policy_version 209980 (0.0008) -[2023-11-28 05:43:04,639][87424] Updated weights for policy 0, policy_version 210347 (0.0011) -[2023-11-28 05:43:05,025][87424] Updated weights for policy 0, policy_version 210357 (0.0009) -[2023-11-28 05:43:05,403][87424] Updated weights for policy 0, policy_version 210367 (0.0011) -[2023-11-28 05:43:06,307][87426] Updated weights for policy 1, policy_version 209990 (0.0011) -[2023-11-28 05:43:06,690][87426] Updated weights for policy 1, policy_version 210000 (0.0008) -[2023-11-28 05:43:07,065][87426] Updated weights for policy 1, policy_version 210010 (0.0012) -[2023-11-28 05:43:07,172][87424] Updated weights for policy 0, policy_version 210377 (0.0010) -[2023-11-28 05:43:07,556][87424] Updated weights for policy 0, policy_version 210387 (0.0008) -[2023-11-28 05:43:07,936][87424] Updated weights for policy 0, policy_version 210397 (0.0007) -[2023-11-28 05:43:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107626496. Throughput: 0: 2696.3, 1: 2688.9. Samples: 107640332. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:43:08,445][86177] Avg episode reward: [(0, '-548.060'), (1, '-535.120')] -[2023-11-28 05:43:08,767][87426] Updated weights for policy 1, policy_version 210020 (0.0011) -[2023-11-28 05:43:09,142][87426] Updated weights for policy 1, policy_version 210030 (0.0009) -[2023-11-28 05:43:09,522][87426] Updated weights for policy 1, policy_version 210040 (0.0010) -[2023-11-28 05:43:09,851][87424] Updated weights for policy 0, policy_version 210407 (0.0010) -[2023-11-28 05:43:10,234][87424] Updated weights for policy 0, policy_version 210417 (0.0009) -[2023-11-28 05:43:10,625][87424] Updated weights for policy 0, policy_version 210427 (0.0010) -[2023-11-28 05:43:11,994][87426] Updated weights for policy 1, policy_version 210050 (0.0011) -[2023-11-28 05:43:12,366][87426] Updated weights for policy 1, policy_version 210060 (0.0012) -[2023-11-28 05:43:12,752][87426] Updated weights for policy 1, policy_version 210070 (0.0011) -[2023-11-28 05:43:12,960][87424] Updated weights for policy 0, policy_version 210437 (0.0011) -[2023-11-28 05:43:13,121][87426] Updated weights for policy 1, policy_version 210080 (0.0010) -[2023-11-28 05:43:13,343][87424] Updated weights for policy 0, policy_version 210447 (0.0012) -[2023-11-28 05:43:13,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 107651072. Throughput: 0: 2707.8, 1: 2678.8. Samples: 107664432. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:43:13,445][86177] Avg episode reward: [(0, '-528.660'), (1, '-528.270')] -[2023-11-28 05:43:13,732][87424] Updated weights for policy 0, policy_version 210457 (0.0012) -[2023-11-28 05:43:15,664][87424] Updated weights for policy 0, policy_version 210467 (0.0011) -[2023-11-28 05:43:15,717][87426] Updated weights for policy 1, policy_version 210090 (0.0012) -[2023-11-28 05:43:16,045][87424] Updated weights for policy 0, policy_version 210477 (0.0011) -[2023-11-28 05:43:16,096][87426] Updated weights for policy 1, policy_version 210100 (0.0010) -[2023-11-28 05:43:16,433][87424] Updated weights for policy 0, policy_version 210487 (0.0011) -[2023-11-28 05:43:16,473][87426] Updated weights for policy 1, policy_version 210110 (0.0011) -[2023-11-28 05:43:18,425][87426] Updated weights for policy 1, policy_version 210120 (0.0011) -[2023-11-28 05:43:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107675648. Throughput: 0: 2742.0, 1: 2696.2. Samples: 107690416. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 05:43:18,445][86177] Avg episode reward: [(0, '-534.440'), (1, '-531.920')] -[2023-11-28 05:43:18,560][87424] Updated weights for policy 0, policy_version 210497 (0.0011) -[2023-11-28 05:43:18,802][87426] Updated weights for policy 1, policy_version 210130 (0.0011) -[2023-11-28 05:43:18,940][87424] Updated weights for policy 0, policy_version 210507 (0.0011) -[2023-11-28 05:43:19,188][87426] Updated weights for policy 1, policy_version 210140 (0.0010) -[2023-11-28 05:43:19,321][87424] Updated weights for policy 0, policy_version 210517 (0.0009) -[2023-11-28 05:43:19,713][87424] Updated weights for policy 0, policy_version 210527 (0.0008) -[2023-11-28 05:43:21,140][87426] Updated weights for policy 1, policy_version 210150 (0.0010) -[2023-11-28 05:43:21,512][87426] Updated weights for policy 1, policy_version 210160 (0.0011) -[2023-11-28 05:43:21,887][87426] Updated weights for policy 1, policy_version 210170 (0.0011) -[2023-11-28 05:43:22,182][87424] Updated weights for policy 0, policy_version 210537 (0.0009) -[2023-11-28 05:43:22,561][87424] Updated weights for policy 0, policy_version 210547 (0.0011) -[2023-11-28 05:43:22,942][87424] Updated weights for policy 0, policy_version 210557 (0.0010) -[2023-11-28 05:43:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107708416. Throughput: 0: 2729.5, 1: 2732.7. Samples: 107722800. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:43:23,445][86177] Avg episode reward: [(0, '-536.330'), (1, '-531.560')] -[2023-11-28 05:43:24,499][87426] Updated weights for policy 1, policy_version 210180 (0.0010) -[2023-11-28 05:43:24,874][87426] Updated weights for policy 1, policy_version 210190 (0.0007) -[2023-11-28 05:43:25,141][87424] Updated weights for policy 0, policy_version 210567 (0.0011) -[2023-11-28 05:43:25,258][87426] Updated weights for policy 1, policy_version 210200 (0.0008) -[2023-11-28 05:43:25,528][87424] Updated weights for policy 0, policy_version 210577 (0.0008) -[2023-11-28 05:43:25,902][87424] Updated weights for policy 0, policy_version 210587 (0.0008) -[2023-11-28 05:43:27,129][87426] Updated weights for policy 1, policy_version 210210 (0.0007) -[2023-11-28 05:43:27,508][87426] Updated weights for policy 1, policy_version 210220 (0.0007) -[2023-11-28 05:43:27,897][87426] Updated weights for policy 1, policy_version 210230 (0.0008) -[2023-11-28 05:43:28,268][87426] Updated weights for policy 1, policy_version 210240 (0.0011) -[2023-11-28 05:43:28,297][87424] Updated weights for policy 0, policy_version 210597 (0.0008) -[2023-11-28 05:43:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107732992. Throughput: 0: 2727.8, 1: 2726.0. Samples: 107746800. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:43:28,445][86177] Avg episode reward: [(0, '-530.330'), (1, '-535.670')] -[2023-11-28 05:43:28,686][87424] Updated weights for policy 0, policy_version 210607 (0.0008) -[2023-11-28 05:43:29,066][87424] Updated weights for policy 0, policy_version 210617 (0.0011) -[2023-11-28 05:43:30,218][87426] Updated weights for policy 1, policy_version 210250 (0.0008) -[2023-11-28 05:43:30,597][87426] Updated weights for policy 1, policy_version 210260 (0.0011) -[2023-11-28 05:43:30,987][87426] Updated weights for policy 1, policy_version 210270 (0.0012) -[2023-11-28 05:43:31,396][87424] Updated weights for policy 0, policy_version 210627 (0.0008) -[2023-11-28 05:43:31,765][87424] Updated weights for policy 0, policy_version 210637 (0.0009) -[2023-11-28 05:43:32,145][87424] Updated weights for policy 0, policy_version 210647 (0.0011) -[2023-11-28 05:43:32,852][87426] Updated weights for policy 1, policy_version 210280 (0.0012) -[2023-11-28 05:43:33,223][87426] Updated weights for policy 1, policy_version 210290 (0.0010) -[2023-11-28 05:43:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 107757568. Throughput: 0: 2705.3, 1: 2734.3. Samples: 107771348. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:43:33,446][86177] Avg episode reward: [(0, '-537.690'), (1, '-534.540')] -[2023-11-28 05:43:33,602][87426] Updated weights for policy 1, policy_version 210300 (0.0007) -[2023-11-28 05:43:34,160][87424] Updated weights for policy 0, policy_version 210657 (0.0008) -[2023-11-28 05:43:34,536][87424] Updated weights for policy 0, policy_version 210667 (0.0007) -[2023-11-28 05:43:34,922][87424] Updated weights for policy 0, policy_version 210677 (0.0011) -[2023-11-28 05:43:35,301][87424] Updated weights for policy 0, policy_version 210687 (0.0012) -[2023-11-28 05:43:35,580][87426] Updated weights for policy 1, policy_version 210310 (0.0012) -[2023-11-28 05:43:35,957][87426] Updated weights for policy 1, policy_version 210320 (0.0009) -[2023-11-28 05:43:36,335][87426] Updated weights for policy 1, policy_version 210330 (0.0007) -[2023-11-28 05:43:37,410][87424] Updated weights for policy 0, policy_version 210697 (0.0012) -[2023-11-28 05:43:37,796][87424] Updated weights for policy 0, policy_version 210707 (0.0012) -[2023-11-28 05:43:38,185][87424] Updated weights for policy 0, policy_version 210717 (0.0011) -[2023-11-28 05:43:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107790336. Throughput: 0: 2703.3, 1: 2736.6. Samples: 107803680. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:43:38,445][86177] Avg episode reward: [(0, '-509.790'), (1, '-540.170')] -[2023-11-28 05:43:38,815][87426] Updated weights for policy 1, policy_version 210340 (0.0007) -[2023-11-28 05:43:39,198][87426] Updated weights for policy 1, policy_version 210350 (0.0010) -[2023-11-28 05:43:39,583][87426] Updated weights for policy 1, policy_version 210360 (0.0008) -[2023-11-28 05:43:40,760][87424] Updated weights for policy 0, policy_version 210727 (0.0009) -[2023-11-28 05:43:41,139][87424] Updated weights for policy 0, policy_version 210737 (0.0008) -[2023-11-28 05:43:41,510][87424] Updated weights for policy 0, policy_version 210747 (0.0010) -[2023-11-28 05:43:41,717][87426] Updated weights for policy 1, policy_version 210370 (0.0009) -[2023-11-28 05:43:42,099][87426] Updated weights for policy 1, policy_version 210380 (0.0008) -[2023-11-28 05:43:42,483][87426] Updated weights for policy 1, policy_version 210390 (0.0010) -[2023-11-28 05:43:42,862][87426] Updated weights for policy 1, policy_version 210400 (0.0010) -[2023-11-28 05:43:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107814912. Throughput: 0: 2697.0, 1: 2740.4. Samples: 107827088. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:43:43,445][86177] Avg episode reward: [(0, '-510.860'), (1, '-579.640')] -[2023-11-28 05:43:43,770][87424] Updated weights for policy 0, policy_version 210757 (0.0010) -[2023-11-28 05:43:44,150][87424] Updated weights for policy 0, policy_version 210767 (0.0008) -[2023-11-28 05:43:44,529][87424] Updated weights for policy 0, policy_version 210777 (0.0007) -[2023-11-28 05:43:45,354][87426] Updated weights for policy 1, policy_version 210410 (0.0011) -[2023-11-28 05:43:45,749][87426] Updated weights for policy 1, policy_version 210420 (0.0007) -[2023-11-28 05:43:46,118][87426] Updated weights for policy 1, policy_version 210430 (0.0007) -[2023-11-28 05:43:46,970][87424] Updated weights for policy 0, policy_version 210787 (0.0009) -[2023-11-28 05:43:47,359][87424] Updated weights for policy 0, policy_version 210797 (0.0007) -[2023-11-28 05:43:47,743][87424] Updated weights for policy 0, policy_version 210807 (0.0007) -[2023-11-28 05:43:47,846][87426] Updated weights for policy 1, policy_version 210440 (0.0011) -[2023-11-28 05:43:48,229][87426] Updated weights for policy 1, policy_version 210450 (0.0012) -[2023-11-28 05:43:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 107839488. Throughput: 0: 2686.6, 1: 2716.2. Samples: 107850668. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:43:48,445][86177] Avg episode reward: [(0, '-559.470'), (1, '-568.480')] -[2023-11-28 05:43:48,604][87426] Updated weights for policy 1, policy_version 210460 (0.0012) -[2023-11-28 05:43:49,776][87424] Updated weights for policy 0, policy_version 210817 (0.0011) -[2023-11-28 05:43:50,158][87424] Updated weights for policy 0, policy_version 210827 (0.0011) -[2023-11-28 05:43:50,543][87424] Updated weights for policy 0, policy_version 210837 (0.0010) -[2023-11-28 05:43:50,638][87426] Updated weights for policy 1, policy_version 210470 (0.0012) -[2023-11-28 05:43:50,930][87424] Updated weights for policy 0, policy_version 210847 (0.0010) -[2023-11-28 05:43:51,012][87426] Updated weights for policy 1, policy_version 210480 (0.0012) -[2023-11-28 05:43:51,384][87426] Updated weights for policy 1, policy_version 210490 (0.0012) -[2023-11-28 05:43:52,962][87424] Updated weights for policy 0, policy_version 210857 (0.0012) -[2023-11-28 05:43:53,345][87424] Updated weights for policy 0, policy_version 210867 (0.0012) -[2023-11-28 05:43:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 107864064. Throughput: 0: 2681.0, 1: 2723.6. Samples: 107883540. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:43:53,445][86177] Avg episode reward: [(0, '-555.680'), (1, '-587.030')] -[2023-11-28 05:43:53,736][87424] Updated weights for policy 0, policy_version 210877 (0.0012) -[2023-11-28 05:43:53,932][87426] Updated weights for policy 1, policy_version 210500 (0.0012) -[2023-11-28 05:43:54,321][87426] Updated weights for policy 1, policy_version 210510 (0.0009) -[2023-11-28 05:43:54,696][87426] Updated weights for policy 1, policy_version 210520 (0.0008) -[2023-11-28 05:43:55,505][87424] Updated weights for policy 0, policy_version 210887 (0.0012) -[2023-11-28 05:43:55,888][87424] Updated weights for policy 0, policy_version 210897 (0.0012) -[2023-11-28 05:43:56,276][87424] Updated weights for policy 0, policy_version 210907 (0.0012) -[2023-11-28 05:43:56,864][87426] Updated weights for policy 1, policy_version 210530 (0.0011) -[2023-11-28 05:43:57,246][87426] Updated weights for policy 1, policy_version 210540 (0.0012) -[2023-11-28 05:43:57,612][87426] Updated weights for policy 1, policy_version 210550 (0.0012) -[2023-11-28 05:43:57,982][87426] Updated weights for policy 1, policy_version 210560 (0.0008) -[2023-11-28 05:43:58,206][87424] Updated weights for policy 0, policy_version 210917 (0.0011) -[2023-11-28 05:43:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107896832. Throughput: 0: 2672.7, 1: 2748.8. Samples: 107908400. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:43:58,445][86177] Avg episode reward: [(0, '-547.980'), (1, '-564.420')] -[2023-11-28 05:43:58,591][87424] Updated weights for policy 0, policy_version 210927 (0.0012) -[2023-11-28 05:43:58,980][87424] Updated weights for policy 0, policy_version 210937 (0.0012) -[2023-11-28 05:44:00,493][87426] Updated weights for policy 1, policy_version 210570 (0.0009) -[2023-11-28 05:44:00,886][87426] Updated weights for policy 1, policy_version 210580 (0.0007) -[2023-11-28 05:44:01,259][87426] Updated weights for policy 1, policy_version 210590 (0.0007) -[2023-11-28 05:44:01,361][87424] Updated weights for policy 0, policy_version 210947 (0.0012) -[2023-11-28 05:44:01,746][87424] Updated weights for policy 0, policy_version 210957 (0.0011) -[2023-11-28 05:44:02,119][87424] Updated weights for policy 0, policy_version 210967 (0.0011) -[2023-11-28 05:44:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 107921408. Throughput: 0: 2651.9, 1: 2728.5. Samples: 107932536. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:44:03,446][86177] Avg episode reward: [(0, '-580.420'), (1, '-530.020')] -[2023-11-28 05:44:03,773][87426] Updated weights for policy 1, policy_version 210600 (0.0010) -[2023-11-28 05:44:04,091][87424] Updated weights for policy 0, policy_version 210977 (0.0011) -[2023-11-28 05:44:04,152][87426] Updated weights for policy 1, policy_version 210610 (0.0010) -[2023-11-28 05:44:04,483][87424] Updated weights for policy 0, policy_version 210987 (0.0008) -[2023-11-28 05:44:04,531][87426] Updated weights for policy 1, policy_version 210620 (0.0008) -[2023-11-28 05:44:04,857][87424] Updated weights for policy 0, policy_version 210997 (0.0010) -[2023-11-28 05:44:05,240][87424] Updated weights for policy 0, policy_version 211007 (0.0009) -[2023-11-28 05:44:06,978][87426] Updated weights for policy 1, policy_version 210630 (0.0010) -[2023-11-28 05:44:07,361][87426] Updated weights for policy 1, policy_version 210640 (0.0010) -[2023-11-28 05:44:07,487][87424] Updated weights for policy 0, policy_version 211017 (0.0008) -[2023-11-28 05:44:07,731][87426] Updated weights for policy 1, policy_version 210650 (0.0009) -[2023-11-28 05:44:07,869][87424] Updated weights for policy 0, policy_version 211027 (0.0008) -[2023-11-28 05:44:08,254][87424] Updated weights for policy 0, policy_version 211037 (0.0008) -[2023-11-28 05:44:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 107954176. Throughput: 0: 2673.3, 1: 2694.1. Samples: 107964328. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:44:08,445][86177] Avg episode reward: [(0, '-532.720'), (1, '-529.780')] -[2023-11-28 05:44:09,611][87426] Updated weights for policy 1, policy_version 210660 (0.0011) -[2023-11-28 05:44:09,991][87426] Updated weights for policy 1, policy_version 210670 (0.0011) -[2023-11-28 05:44:10,367][87426] Updated weights for policy 1, policy_version 210680 (0.0011) -[2023-11-28 05:44:10,573][87424] Updated weights for policy 0, policy_version 211047 (0.0012) -[2023-11-28 05:44:10,956][87424] Updated weights for policy 0, policy_version 211057 (0.0012) -[2023-11-28 05:44:11,333][87424] Updated weights for policy 0, policy_version 211067 (0.0012) -[2023-11-28 05:44:12,652][87426] Updated weights for policy 1, policy_version 210690 (0.0012) -[2023-11-28 05:44:13,022][87426] Updated weights for policy 1, policy_version 210700 (0.0018) -[2023-11-28 05:44:13,396][87426] Updated weights for policy 1, policy_version 210710 (0.0010) -[2023-11-28 05:44:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 107970560. Throughput: 0: 2678.7, 1: 2687.7. Samples: 107988284. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:44:13,445][86177] Avg episode reward: [(0, '-589.960'), (1, '-509.160')] -[2023-11-28 05:44:13,559][87424] Updated weights for policy 0, policy_version 211077 (0.0012) -[2023-11-28 05:44:13,778][87426] Updated weights for policy 1, policy_version 210720 (0.0007) -[2023-11-28 05:44:13,942][87424] Updated weights for policy 0, policy_version 211087 (0.0012) -[2023-11-28 05:44:14,315][87424] Updated weights for policy 0, policy_version 211097 (0.0011) -[2023-11-28 05:44:15,913][87426] Updated weights for policy 1, policy_version 210730 (0.0012) -[2023-11-28 05:44:16,291][87426] Updated weights for policy 1, policy_version 210740 (0.0011) -[2023-11-28 05:44:16,601][87424] Updated weights for policy 0, policy_version 211107 (0.0011) -[2023-11-28 05:44:16,660][87426] Updated weights for policy 1, policy_version 210750 (0.0011) -[2023-11-28 05:44:16,985][87424] Updated weights for policy 0, policy_version 211117 (0.0009) -[2023-11-28 05:44:17,380][87424] Updated weights for policy 0, policy_version 211127 (0.0007) -[2023-11-28 05:44:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 108003328. Throughput: 0: 2696.8, 1: 2687.4. Samples: 108013636. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:44:18,445][86177] Avg episode reward: [(0, '-588.060'), (1, '-514.110')] -[2023-11-28 05:44:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000211136_54050816.pth... -[2023-11-28 05:44:18,500][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000208608_53403648.pth -[2023-11-28 05:44:18,601][87426] Updated weights for policy 1, policy_version 210760 (0.0012) -[2023-11-28 05:44:18,976][87426] Updated weights for policy 1, policy_version 210770 (0.0011) -[2023-11-28 05:44:19,253][87424] Updated weights for policy 0, policy_version 211137 (0.0008) -[2023-11-28 05:44:19,362][87426] Updated weights for policy 1, policy_version 210780 (0.0011) -[2023-11-28 05:44:19,505][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000210784_53960704.pth... -[2023-11-28 05:44:19,553][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000208224_53305344.pth -[2023-11-28 05:44:19,629][87424] Updated weights for policy 0, policy_version 211147 (0.0012) -[2023-11-28 05:44:20,024][87424] Updated weights for policy 0, policy_version 211157 (0.0012) -[2023-11-28 05:44:20,399][87424] Updated weights for policy 0, policy_version 211167 (0.0012) -[2023-11-28 05:44:21,500][87426] Updated weights for policy 1, policy_version 210790 (0.0012) -[2023-11-28 05:44:21,875][87426] Updated weights for policy 1, policy_version 210800 (0.0011) -[2023-11-28 05:44:22,254][87426] Updated weights for policy 1, policy_version 210810 (0.0011) -[2023-11-28 05:44:22,876][87424] Updated weights for policy 0, policy_version 211177 (0.0010) -[2023-11-28 05:44:23,256][87424] Updated weights for policy 0, policy_version 211187 (0.0008) -[2023-11-28 05:44:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 108027904. Throughput: 0: 2706.3, 1: 2688.6. Samples: 108046452. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:44:23,445][86177] Avg episode reward: [(0, '-554.290'), (1, '-526.560')] -[2023-11-28 05:44:23,638][87424] Updated weights for policy 0, policy_version 211197 (0.0009) -[2023-11-28 05:44:24,794][87426] Updated weights for policy 1, policy_version 210820 (0.0010) -[2023-11-28 05:44:25,166][87426] Updated weights for policy 1, policy_version 210830 (0.0009) -[2023-11-28 05:44:25,553][87426] Updated weights for policy 1, policy_version 210840 (0.0007) -[2023-11-28 05:44:26,181][87424] Updated weights for policy 0, policy_version 211207 (0.0011) -[2023-11-28 05:44:26,558][87424] Updated weights for policy 0, policy_version 211217 (0.0012) -[2023-11-28 05:44:26,947][87424] Updated weights for policy 0, policy_version 211227 (0.0012) -[2023-11-28 05:44:27,800][87426] Updated weights for policy 1, policy_version 210850 (0.0007) -[2023-11-28 05:44:28,175][87426] Updated weights for policy 1, policy_version 210860 (0.0007) -[2023-11-28 05:44:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 108052480. Throughput: 0: 2727.9, 1: 2690.6. Samples: 108070920. Policy #0 lag: (min: 30.0, avg: 37.9, max: 62.0) -[2023-11-28 05:44:28,445][86177] Avg episode reward: [(0, '-552.050'), (1, '-538.210')] -[2023-11-28 05:44:28,549][87426] Updated weights for policy 1, policy_version 210870 (0.0008) -[2023-11-28 05:44:28,928][87426] Updated weights for policy 1, policy_version 210880 (0.0008) -[2023-11-28 05:44:28,959][87424] Updated weights for policy 0, policy_version 211237 (0.0010) -[2023-11-28 05:44:29,346][87424] Updated weights for policy 0, policy_version 211247 (0.0008) -[2023-11-28 05:44:29,720][87424] Updated weights for policy 0, policy_version 211257 (0.0010) -[2023-11-28 05:44:31,351][87424] Updated weights for policy 0, policy_version 211267 (0.0010) -[2023-11-28 05:44:31,441][87426] Updated weights for policy 1, policy_version 210890 (0.0011) -[2023-11-28 05:44:31,738][87424] Updated weights for policy 0, policy_version 211277 (0.0012) -[2023-11-28 05:44:31,820][87426] Updated weights for policy 1, policy_version 210900 (0.0010) -[2023-11-28 05:44:32,123][87424] Updated weights for policy 0, policy_version 211287 (0.0008) -[2023-11-28 05:44:32,202][87426] Updated weights for policy 1, policy_version 210910 (0.0011) -[2023-11-28 05:44:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 108085248. Throughput: 0: 2763.9, 1: 2675.3. Samples: 108095432. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:44:33,445][86177] Avg episode reward: [(0, '-519.800'), (1, '-541.780')] -[2023-11-28 05:44:33,820][87424] Updated weights for policy 0, policy_version 211297 (0.0008) -[2023-11-28 05:44:34,203][87424] Updated weights for policy 0, policy_version 211307 (0.0010) -[2023-11-28 05:44:34,584][87424] Updated weights for policy 0, policy_version 211317 (0.0008) -[2023-11-28 05:44:34,792][87426] Updated weights for policy 1, policy_version 210920 (0.0009) -[2023-11-28 05:44:34,963][87424] Updated weights for policy 0, policy_version 211327 (0.0009) -[2023-11-28 05:44:35,172][87426] Updated weights for policy 1, policy_version 210930 (0.0012) -[2023-11-28 05:44:35,552][87426] Updated weights for policy 1, policy_version 210940 (0.0012) -[2023-11-28 05:44:37,135][87424] Updated weights for policy 0, policy_version 211337 (0.0009) -[2023-11-28 05:44:37,519][87424] Updated weights for policy 0, policy_version 211347 (0.0012) -[2023-11-28 05:44:37,820][87426] Updated weights for policy 1, policy_version 210950 (0.0010) -[2023-11-28 05:44:37,906][87424] Updated weights for policy 0, policy_version 211357 (0.0012) -[2023-11-28 05:44:38,193][87426] Updated weights for policy 1, policy_version 210960 (0.0008) -[2023-11-28 05:44:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 108109824. Throughput: 0: 2759.9, 1: 2658.2. Samples: 108127356. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:44:38,445][86177] Avg episode reward: [(0, '-522.070'), (1, '-551.160')] -[2023-11-28 05:44:38,568][87426] Updated weights for policy 1, policy_version 210970 (0.0008) -[2023-11-28 05:44:40,096][87424] Updated weights for policy 0, policy_version 211367 (0.0012) -[2023-11-28 05:44:40,468][87424] Updated weights for policy 0, policy_version 211377 (0.0012) -[2023-11-28 05:44:40,596][87426] Updated weights for policy 1, policy_version 210980 (0.0009) -[2023-11-28 05:44:40,856][87424] Updated weights for policy 0, policy_version 211387 (0.0011) -[2023-11-28 05:44:40,981][87426] Updated weights for policy 1, policy_version 210990 (0.0011) -[2023-11-28 05:44:41,357][87426] Updated weights for policy 1, policy_version 211000 (0.0010) -[2023-11-28 05:44:43,188][87424] Updated weights for policy 0, policy_version 211397 (0.0012) -[2023-11-28 05:44:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 108134400. Throughput: 0: 2751.4, 1: 2648.9. Samples: 108151412. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:44:43,445][86177] Avg episode reward: [(0, '-531.750'), (1, '-533.600')] -[2023-11-28 05:44:43,572][87424] Updated weights for policy 0, policy_version 211407 (0.0012) -[2023-11-28 05:44:43,800][87426] Updated weights for policy 1, policy_version 211010 (0.0010) -[2023-11-28 05:44:43,952][87424] Updated weights for policy 0, policy_version 211417 (0.0012) -[2023-11-28 05:44:44,168][87426] Updated weights for policy 1, policy_version 211020 (0.0012) -[2023-11-28 05:44:44,554][87426] Updated weights for policy 1, policy_version 211030 (0.0011) -[2023-11-28 05:44:44,925][87426] Updated weights for policy 1, policy_version 211040 (0.0010) -[2023-11-28 05:44:45,686][87424] Updated weights for policy 0, policy_version 211427 (0.0012) -[2023-11-28 05:44:46,063][87424] Updated weights for policy 0, policy_version 211437 (0.0012) -[2023-11-28 05:44:46,446][87424] Updated weights for policy 0, policy_version 211447 (0.0012) -[2023-11-28 05:44:47,489][87426] Updated weights for policy 1, policy_version 211050 (0.0008) -[2023-11-28 05:44:47,876][87426] Updated weights for policy 1, policy_version 211060 (0.0007) -[2023-11-28 05:44:48,268][87426] Updated weights for policy 1, policy_version 211070 (0.0008) -[2023-11-28 05:44:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 108167168. Throughput: 0: 2778.9, 1: 2642.1. Samples: 108176484. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:44:48,445][86177] Avg episode reward: [(0, '-505.640'), (1, '-524.610')] -[2023-11-28 05:44:48,786][87424] Updated weights for policy 0, policy_version 211457 (0.0012) -[2023-11-28 05:44:49,163][87424] Updated weights for policy 0, policy_version 211467 (0.0010) -[2023-11-28 05:44:49,544][87424] Updated weights for policy 0, policy_version 211477 (0.0012) -[2023-11-28 05:44:49,923][87424] Updated weights for policy 0, policy_version 211487 (0.0012) -[2023-11-28 05:44:50,725][87426] Updated weights for policy 1, policy_version 211080 (0.0010) -[2023-11-28 05:44:51,106][87426] Updated weights for policy 1, policy_version 211090 (0.0011) -[2023-11-28 05:44:51,480][87426] Updated weights for policy 1, policy_version 211100 (0.0011) -[2023-11-28 05:44:52,080][87424] Updated weights for policy 0, policy_version 211497 (0.0009) -[2023-11-28 05:44:52,466][87424] Updated weights for policy 0, policy_version 211507 (0.0010) -[2023-11-28 05:44:52,849][87424] Updated weights for policy 0, policy_version 211517 (0.0012) -[2023-11-28 05:44:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 108191744. Throughput: 0: 2788.3, 1: 2629.9. Samples: 108208148. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:44:53,445][86177] Avg episode reward: [(0, '-506.500'), (1, '-541.060')] -[2023-11-28 05:44:53,956][87426] Updated weights for policy 1, policy_version 211110 (0.0011) -[2023-11-28 05:44:54,334][87426] Updated weights for policy 1, policy_version 211120 (0.0011) -[2023-11-28 05:44:54,718][87426] Updated weights for policy 1, policy_version 211130 (0.0010) -[2023-11-28 05:44:55,134][87424] Updated weights for policy 0, policy_version 211527 (0.0011) -[2023-11-28 05:44:55,512][87424] Updated weights for policy 0, policy_version 211537 (0.0008) -[2023-11-28 05:44:55,887][87424] Updated weights for policy 0, policy_version 211547 (0.0012) -[2023-11-28 05:44:56,568][87426] Updated weights for policy 1, policy_version 211140 (0.0007) -[2023-11-28 05:44:56,957][87426] Updated weights for policy 1, policy_version 211150 (0.0008) -[2023-11-28 05:44:57,330][87426] Updated weights for policy 1, policy_version 211160 (0.0008) -[2023-11-28 05:44:57,782][87424] Updated weights for policy 0, policy_version 211557 (0.0009) -[2023-11-28 05:44:58,165][87424] Updated weights for policy 0, policy_version 211567 (0.0012) -[2023-11-28 05:44:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 108216320. Throughput: 0: 2786.9, 1: 2645.6. Samples: 108232748. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:44:58,445][86177] Avg episode reward: [(0, '-506.380'), (1, '-528.010')] -[2023-11-28 05:44:58,554][87424] Updated weights for policy 0, policy_version 211577 (0.0011) -[2023-11-28 05:44:58,937][87426] Updated weights for policy 1, policy_version 211170 (0.0008) -[2023-11-28 05:44:59,319][87426] Updated weights for policy 1, policy_version 211180 (0.0011) -[2023-11-28 05:44:59,699][87426] Updated weights for policy 1, policy_version 211190 (0.0012) -[2023-11-28 05:45:00,075][87426] Updated weights for policy 1, policy_version 211200 (0.0012) -[2023-11-28 05:45:00,637][87424] Updated weights for policy 0, policy_version 211587 (0.0010) -[2023-11-28 05:45:01,021][87424] Updated weights for policy 0, policy_version 211597 (0.0007) -[2023-11-28 05:45:01,404][87424] Updated weights for policy 0, policy_version 211607 (0.0007) -[2023-11-28 05:45:02,478][87426] Updated weights for policy 1, policy_version 211210 (0.0008) -[2023-11-28 05:45:02,852][87426] Updated weights for policy 1, policy_version 211220 (0.0008) -[2023-11-28 05:45:03,238][87426] Updated weights for policy 1, policy_version 211230 (0.0007) -[2023-11-28 05:45:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 108249088. Throughput: 0: 2784.4, 1: 2632.4. Samples: 108257396. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:45:03,445][86177] Avg episode reward: [(0, '-496.790'), (1, '-528.800')] -[2023-11-28 05:45:03,867][87424] Updated weights for policy 0, policy_version 211617 (0.0010) -[2023-11-28 05:45:04,253][87424] Updated weights for policy 0, policy_version 211627 (0.0011) -[2023-11-28 05:45:04,633][87424] Updated weights for policy 0, policy_version 211637 (0.0010) -[2023-11-28 05:45:05,022][87424] Updated weights for policy 0, policy_version 211647 (0.0008) -[2023-11-28 05:45:05,719][87426] Updated weights for policy 1, policy_version 211240 (0.0008) -[2023-11-28 05:45:06,099][87426] Updated weights for policy 1, policy_version 211250 (0.0007) -[2023-11-28 05:45:06,479][87426] Updated weights for policy 1, policy_version 211260 (0.0007) -[2023-11-28 05:45:07,341][87424] Updated weights for policy 0, policy_version 211657 (0.0012) -[2023-11-28 05:45:07,728][87424] Updated weights for policy 0, policy_version 211667 (0.0012) -[2023-11-28 05:45:08,103][87424] Updated weights for policy 0, policy_version 211677 (0.0012) -[2023-11-28 05:45:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 108273664. Throughput: 0: 2759.2, 1: 2625.6. Samples: 108288768. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:45:08,446][86177] Avg episode reward: [(0, '-498.860'), (1, '-525.990')] -[2023-11-28 05:45:08,690][87426] Updated weights for policy 1, policy_version 211270 (0.0010) -[2023-11-28 05:45:09,066][87426] Updated weights for policy 1, policy_version 211280 (0.0012) -[2023-11-28 05:45:09,439][87426] Updated weights for policy 1, policy_version 211290 (0.0012) -[2023-11-28 05:45:10,424][87424] Updated weights for policy 0, policy_version 211687 (0.0009) -[2023-11-28 05:45:10,807][87424] Updated weights for policy 0, policy_version 211697 (0.0011) -[2023-11-28 05:45:11,186][87424] Updated weights for policy 0, policy_version 211707 (0.0012) -[2023-11-28 05:45:11,895][87426] Updated weights for policy 1, policy_version 211300 (0.0012) -[2023-11-28 05:45:12,277][87426] Updated weights for policy 1, policy_version 211310 (0.0012) -[2023-11-28 05:45:12,660][87426] Updated weights for policy 1, policy_version 211320 (0.0012) -[2023-11-28 05:45:13,194][87424] Updated weights for policy 0, policy_version 211717 (0.0012) -[2023-11-28 05:45:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 108298240. Throughput: 0: 2759.7, 1: 2617.2. Samples: 108312880. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:45:13,445][86177] Avg episode reward: [(0, '-512.760'), (1, '-506.300')] -[2023-11-28 05:45:13,575][87424] Updated weights for policy 0, policy_version 211727 (0.0011) -[2023-11-28 05:45:13,963][87424] Updated weights for policy 0, policy_version 211737 (0.0012) -[2023-11-28 05:45:14,504][87426] Updated weights for policy 1, policy_version 211330 (0.0012) -[2023-11-28 05:45:14,883][87426] Updated weights for policy 1, policy_version 211340 (0.0012) -[2023-11-28 05:45:15,258][87426] Updated weights for policy 1, policy_version 211350 (0.0012) -[2023-11-28 05:45:15,642][87426] Updated weights for policy 1, policy_version 211360 (0.0009) -[2023-11-28 05:45:16,042][87424] Updated weights for policy 0, policy_version 211747 (0.0012) -[2023-11-28 05:45:16,419][87424] Updated weights for policy 0, policy_version 211757 (0.0012) -[2023-11-28 05:45:16,793][87424] Updated weights for policy 0, policy_version 211767 (0.0012) -[2023-11-28 05:45:17,455][87426] Updated weights for policy 1, policy_version 211370 (0.0011) -[2023-11-28 05:45:17,835][87426] Updated weights for policy 1, policy_version 211380 (0.0011) -[2023-11-28 05:45:18,207][87426] Updated weights for policy 1, policy_version 211390 (0.0012) -[2023-11-28 05:45:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 108331008. Throughput: 0: 2738.7, 1: 2653.8. Samples: 108338092. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:45:18,445][86177] Avg episode reward: [(0, '-519.630'), (1, '-505.440')] -[2023-11-28 05:45:18,795][87424] Updated weights for policy 0, policy_version 211777 (0.0012) -[2023-11-28 05:45:19,159][87424] Updated weights for policy 0, policy_version 211787 (0.0010) -[2023-11-28 05:45:19,543][87424] Updated weights for policy 0, policy_version 211797 (0.0009) -[2023-11-28 05:45:19,939][87424] Updated weights for policy 0, policy_version 211807 (0.0009) -[2023-11-28 05:45:19,941][87426] Updated weights for policy 1, policy_version 211400 (0.0011) -[2023-11-28 05:45:20,317][87426] Updated weights for policy 1, policy_version 211410 (0.0010) -[2023-11-28 05:45:20,695][87426] Updated weights for policy 1, policy_version 211420 (0.0009) -[2023-11-28 05:45:22,052][87424] Updated weights for policy 0, policy_version 211817 (0.0009) -[2023-11-28 05:45:22,424][87424] Updated weights for policy 0, policy_version 211827 (0.0011) -[2023-11-28 05:45:22,809][87424] Updated weights for policy 0, policy_version 211837 (0.0010) -[2023-11-28 05:45:23,196][87426] Updated weights for policy 1, policy_version 211430 (0.0010) -[2023-11-28 05:45:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 108355584. Throughput: 0: 2740.3, 1: 2689.1. Samples: 108371676. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:45:23,445][86177] Avg episode reward: [(0, '-519.320'), (1, '-521.070')] -[2023-11-28 05:45:23,585][87426] Updated weights for policy 1, policy_version 211440 (0.0010) -[2023-11-28 05:45:23,963][87426] Updated weights for policy 1, policy_version 211450 (0.0008) -[2023-11-28 05:45:25,015][87424] Updated weights for policy 0, policy_version 211847 (0.0009) -[2023-11-28 05:45:25,397][87424] Updated weights for policy 0, policy_version 211857 (0.0007) -[2023-11-28 05:45:25,777][87424] Updated weights for policy 0, policy_version 211867 (0.0007) -[2023-11-28 05:45:26,525][87426] Updated weights for policy 1, policy_version 211460 (0.0010) -[2023-11-28 05:45:26,908][87426] Updated weights for policy 1, policy_version 211470 (0.0007) -[2023-11-28 05:45:27,292][87426] Updated weights for policy 1, policy_version 211480 (0.0007) -[2023-11-28 05:45:28,001][87424] Updated weights for policy 0, policy_version 211877 (0.0008) -[2023-11-28 05:45:28,387][87424] Updated weights for policy 0, policy_version 211887 (0.0008) -[2023-11-28 05:45:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 108380160. Throughput: 0: 2749.4, 1: 2666.1. Samples: 108395112. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:45:28,445][86177] Avg episode reward: [(0, '-554.470'), (1, '-532.840')] -[2023-11-28 05:45:28,771][87424] Updated weights for policy 0, policy_version 211897 (0.0008) -[2023-11-28 05:45:29,073][87426] Updated weights for policy 1, policy_version 211490 (0.0007) -[2023-11-28 05:45:29,460][87426] Updated weights for policy 1, policy_version 211500 (0.0008) -[2023-11-28 05:45:29,839][87426] Updated weights for policy 1, policy_version 211510 (0.0012) -[2023-11-28 05:45:30,207][87426] Updated weights for policy 1, policy_version 211520 (0.0012) -[2023-11-28 05:45:31,281][87424] Updated weights for policy 0, policy_version 211907 (0.0007) -[2023-11-28 05:45:31,662][87424] Updated weights for policy 0, policy_version 211917 (0.0008) -[2023-11-28 05:45:32,046][87424] Updated weights for policy 0, policy_version 211927 (0.0011) -[2023-11-28 05:45:32,706][87426] Updated weights for policy 1, policy_version 211530 (0.0010) -[2023-11-28 05:45:33,084][87426] Updated weights for policy 1, policy_version 211540 (0.0010) -[2023-11-28 05:45:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 108404736. Throughput: 0: 2728.7, 1: 2667.2. Samples: 108419300. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:45:33,445][86177] Avg episode reward: [(0, '-549.060'), (1, '-540.390')] -[2023-11-28 05:45:33,463][87426] Updated weights for policy 1, policy_version 211550 (0.0010) -[2023-11-28 05:45:33,881][87424] Updated weights for policy 0, policy_version 211937 (0.0011) -[2023-11-28 05:45:34,264][87424] Updated weights for policy 0, policy_version 211947 (0.0012) -[2023-11-28 05:45:34,645][87424] Updated weights for policy 0, policy_version 211957 (0.0011) -[2023-11-28 05:45:35,024][87424] Updated weights for policy 0, policy_version 211967 (0.0011) -[2023-11-28 05:45:35,887][87426] Updated weights for policy 1, policy_version 211560 (0.0011) -[2023-11-28 05:45:36,269][87426] Updated weights for policy 1, policy_version 211570 (0.0011) -[2023-11-28 05:45:36,649][87426] Updated weights for policy 1, policy_version 211580 (0.0011) -[2023-11-28 05:45:37,483][87424] Updated weights for policy 0, policy_version 211977 (0.0011) -[2023-11-28 05:45:37,868][87424] Updated weights for policy 0, policy_version 211987 (0.0012) -[2023-11-28 05:45:38,245][87424] Updated weights for policy 0, policy_version 211997 (0.0012) -[2023-11-28 05:45:38,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 108437504. Throughput: 0: 2710.4, 1: 2689.6. Samples: 108451148. Policy #0 lag: (min: 31.0, avg: 47.1, max: 63.0) -[2023-11-28 05:45:38,445][86177] Avg episode reward: [(0, '-544.830'), (1, '-548.740')] -[2023-11-28 05:45:38,869][87426] Updated weights for policy 1, policy_version 211590 (0.0012) -[2023-11-28 05:45:39,248][87426] Updated weights for policy 1, policy_version 211600 (0.0012) -[2023-11-28 05:45:39,638][87426] Updated weights for policy 1, policy_version 211610 (0.0011) -[2023-11-28 05:45:40,076][87424] Updated weights for policy 0, policy_version 212007 (0.0011) -[2023-11-28 05:45:40,457][87424] Updated weights for policy 0, policy_version 212017 (0.0009) -[2023-11-28 05:45:40,836][87424] Updated weights for policy 0, policy_version 212027 (0.0008) -[2023-11-28 05:45:42,092][87426] Updated weights for policy 1, policy_version 211620 (0.0011) -[2023-11-28 05:45:42,466][87426] Updated weights for policy 1, policy_version 211630 (0.0011) -[2023-11-28 05:45:42,835][87424] Updated weights for policy 0, policy_version 212037 (0.0009) -[2023-11-28 05:45:42,847][87426] Updated weights for policy 1, policy_version 211640 (0.0010) -[2023-11-28 05:45:43,218][87424] Updated weights for policy 0, policy_version 212047 (0.0008) -[2023-11-28 05:45:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 108462080. Throughput: 0: 2729.9, 1: 2663.4. Samples: 108475444. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:45:43,445][86177] Avg episode reward: [(0, '-545.830'), (1, '-535.050')] -[2023-11-28 05:45:43,600][87424] Updated weights for policy 0, policy_version 212057 (0.0008) -[2023-11-28 05:45:45,313][87426] Updated weights for policy 1, policy_version 211650 (0.0009) -[2023-11-28 05:45:45,467][87424] Updated weights for policy 0, policy_version 212067 (0.0009) -[2023-11-28 05:45:45,690][87426] Updated weights for policy 1, policy_version 211660 (0.0012) -[2023-11-28 05:45:45,847][87424] Updated weights for policy 0, policy_version 212077 (0.0008) -[2023-11-28 05:45:46,075][87426] Updated weights for policy 1, policy_version 211670 (0.0011) -[2023-11-28 05:45:46,229][87424] Updated weights for policy 0, policy_version 212087 (0.0009) -[2023-11-28 05:45:46,446][87426] Updated weights for policy 1, policy_version 211680 (0.0009) -[2023-11-28 05:45:48,286][87426] Updated weights for policy 1, policy_version 211690 (0.0008) -[2023-11-28 05:45:48,397][87424] Updated weights for policy 0, policy_version 212097 (0.0008) -[2023-11-28 05:45:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 108486656. Throughput: 0: 2716.9, 1: 2662.2. Samples: 108499456. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:45:48,445][86177] Avg episode reward: [(0, '-525.900'), (1, '-533.570')] -[2023-11-28 05:45:48,670][87426] Updated weights for policy 1, policy_version 211700 (0.0007) -[2023-11-28 05:45:48,772][87424] Updated weights for policy 0, policy_version 212107 (0.0012) -[2023-11-28 05:45:49,045][87426] Updated weights for policy 1, policy_version 211710 (0.0009) -[2023-11-28 05:45:49,152][87424] Updated weights for policy 0, policy_version 212117 (0.0012) -[2023-11-28 05:45:49,533][87424] Updated weights for policy 0, policy_version 212127 (0.0012) -[2023-11-28 05:45:51,024][87426] Updated weights for policy 1, policy_version 211720 (0.0008) -[2023-11-28 05:45:51,410][87426] Updated weights for policy 1, policy_version 211730 (0.0008) -[2023-11-28 05:45:51,792][87426] Updated weights for policy 1, policy_version 211740 (0.0010) -[2023-11-28 05:45:52,009][87424] Updated weights for policy 0, policy_version 212137 (0.0013) -[2023-11-28 05:45:52,389][87424] Updated weights for policy 0, policy_version 212147 (0.0010) -[2023-11-28 05:45:52,769][87424] Updated weights for policy 0, policy_version 212157 (0.0011) -[2023-11-28 05:45:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 108519424. Throughput: 0: 2713.3, 1: 2704.4. Samples: 108532564. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:45:53,445][86177] Avg episode reward: [(0, '-516.640'), (1, '-565.050')] -[2023-11-28 05:45:54,162][87426] Updated weights for policy 1, policy_version 211750 (0.0010) -[2023-11-28 05:45:54,551][87426] Updated weights for policy 1, policy_version 211760 (0.0007) -[2023-11-28 05:45:54,918][87426] Updated weights for policy 1, policy_version 211770 (0.0009) -[2023-11-28 05:45:55,395][87424] Updated weights for policy 0, policy_version 212167 (0.0008) -[2023-11-28 05:45:55,781][87424] Updated weights for policy 0, policy_version 212177 (0.0007) -[2023-11-28 05:45:56,170][87424] Updated weights for policy 0, policy_version 212187 (0.0009) -[2023-11-28 05:45:56,835][87426] Updated weights for policy 1, policy_version 211780 (0.0009) -[2023-11-28 05:45:57,200][87426] Updated weights for policy 1, policy_version 211790 (0.0010) -[2023-11-28 05:45:57,579][87426] Updated weights for policy 1, policy_version 211800 (0.0007) -[2023-11-28 05:45:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 108544000. Throughput: 0: 2697.5, 1: 2725.2. Samples: 108556900. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:45:58,445][86177] Avg episode reward: [(0, '-514.550'), (1, '-553.330')] -[2023-11-28 05:45:58,649][87424] Updated weights for policy 0, policy_version 212197 (0.0010) -[2023-11-28 05:45:59,045][87424] Updated weights for policy 0, policy_version 212207 (0.0012) -[2023-11-28 05:45:59,424][87424] Updated weights for policy 0, policy_version 212217 (0.0009) -[2023-11-28 05:45:59,800][87426] Updated weights for policy 1, policy_version 211810 (0.0008) -[2023-11-28 05:46:00,176][87426] Updated weights for policy 1, policy_version 211820 (0.0011) -[2023-11-28 05:46:00,552][87426] Updated weights for policy 1, policy_version 211830 (0.0010) -[2023-11-28 05:46:00,930][87426] Updated weights for policy 1, policy_version 211840 (0.0010) -[2023-11-28 05:46:01,506][87424] Updated weights for policy 0, policy_version 212227 (0.0011) -[2023-11-28 05:46:01,891][87424] Updated weights for policy 0, policy_version 212237 (0.0011) -[2023-11-28 05:46:02,273][87424] Updated weights for policy 0, policy_version 212247 (0.0010) -[2023-11-28 05:46:02,994][87426] Updated weights for policy 1, policy_version 211850 (0.0012) -[2023-11-28 05:46:03,367][87426] Updated weights for policy 1, policy_version 211860 (0.0012) -[2023-11-28 05:46:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 108568576. Throughput: 0: 2717.0, 1: 2721.2. Samples: 108582812. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:03,445][86177] Avg episode reward: [(0, '-505.240'), (1, '-546.890')] -[2023-11-28 05:46:03,742][87426] Updated weights for policy 1, policy_version 211870 (0.0012) -[2023-11-28 05:46:04,732][87424] Updated weights for policy 0, policy_version 212257 (0.0010) -[2023-11-28 05:46:05,109][87424] Updated weights for policy 0, policy_version 212267 (0.0011) -[2023-11-28 05:46:05,490][87424] Updated weights for policy 0, policy_version 212277 (0.0011) -[2023-11-28 05:46:05,883][87424] Updated weights for policy 0, policy_version 212287 (0.0009) -[2023-11-28 05:46:06,219][87426] Updated weights for policy 1, policy_version 211880 (0.0012) -[2023-11-28 05:46:06,595][87426] Updated weights for policy 1, policy_version 211890 (0.0012) -[2023-11-28 05:46:06,980][87426] Updated weights for policy 1, policy_version 211900 (0.0012) -[2023-11-28 05:46:08,015][87424] Updated weights for policy 0, policy_version 212297 (0.0007) -[2023-11-28 05:46:08,394][87424] Updated weights for policy 0, policy_version 212307 (0.0008) -[2023-11-28 05:46:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 108593152. Throughput: 0: 2719.4, 1: 2712.9. Samples: 108616128. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:08,445][86177] Avg episode reward: [(0, '-524.910'), (1, '-568.140')] -[2023-11-28 05:46:08,781][87424] Updated weights for policy 0, policy_version 212317 (0.0008) -[2023-11-28 05:46:09,528][87426] Updated weights for policy 1, policy_version 211910 (0.0012) -[2023-11-28 05:46:09,911][87426] Updated weights for policy 1, policy_version 211920 (0.0010) -[2023-11-28 05:46:10,289][87426] Updated weights for policy 1, policy_version 211930 (0.0009) -[2023-11-28 05:46:10,504][87424] Updated weights for policy 0, policy_version 212327 (0.0011) -[2023-11-28 05:46:10,880][87424] Updated weights for policy 0, policy_version 212337 (0.0011) -[2023-11-28 05:46:11,255][87424] Updated weights for policy 0, policy_version 212347 (0.0010) -[2023-11-28 05:46:12,192][87426] Updated weights for policy 1, policy_version 211940 (0.0010) -[2023-11-28 05:46:12,571][87426] Updated weights for policy 1, policy_version 211950 (0.0011) -[2023-11-28 05:46:12,953][87426] Updated weights for policy 1, policy_version 211960 (0.0011) -[2023-11-28 05:46:13,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 108625920. Throughput: 0: 2720.6, 1: 2711.3. Samples: 108639548. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:13,446][86177] Avg episode reward: [(0, '-529.030'), (1, '-553.540')] -[2023-11-28 05:46:13,628][87424] Updated weights for policy 0, policy_version 212357 (0.0011) -[2023-11-28 05:46:14,024][87424] Updated weights for policy 0, policy_version 212367 (0.0010) -[2023-11-28 05:46:14,406][87424] Updated weights for policy 0, policy_version 212377 (0.0009) -[2023-11-28 05:46:14,797][87426] Updated weights for policy 1, policy_version 211970 (0.0010) -[2023-11-28 05:46:15,191][87426] Updated weights for policy 1, policy_version 211980 (0.0011) -[2023-11-28 05:46:15,570][87426] Updated weights for policy 1, policy_version 211990 (0.0011) -[2023-11-28 05:46:15,949][87426] Updated weights for policy 1, policy_version 212000 (0.0011) -[2023-11-28 05:46:16,329][87424] Updated weights for policy 0, policy_version 212387 (0.0011) -[2023-11-28 05:46:16,699][87424] Updated weights for policy 0, policy_version 212397 (0.0009) -[2023-11-28 05:46:17,082][87424] Updated weights for policy 0, policy_version 212407 (0.0008) -[2023-11-28 05:46:17,605][87426] Updated weights for policy 1, policy_version 212010 (0.0008) -[2023-11-28 05:46:17,986][87426] Updated weights for policy 1, policy_version 212020 (0.0008) -[2023-11-28 05:46:18,372][87426] Updated weights for policy 1, policy_version 212030 (0.0007) -[2023-11-28 05:46:18,449][86177] Fps is (10 sec: 6550.4, 60 sec: 5460.9, 300 sec: 5442.7). Total num frames: 108658688. Throughput: 0: 2703.4, 1: 2722.5. Samples: 108663488. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:18,451][86177] Avg episode reward: [(0, '-527.900'), (1, '-558.350')] -[2023-11-28 05:46:18,463][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000212416_54378496.pth... -[2023-11-28 05:46:18,463][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000212032_54280192.pth... -[2023-11-28 05:46:18,495][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000209504_53633024.pth -[2023-11-28 05:46:18,500][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000209888_53731328.pth -[2023-11-28 05:46:19,237][87424] Updated weights for policy 0, policy_version 212417 (0.0008) -[2023-11-28 05:46:19,625][87424] Updated weights for policy 0, policy_version 212427 (0.0012) -[2023-11-28 05:46:20,022][87424] Updated weights for policy 0, policy_version 212437 (0.0011) -[2023-11-28 05:46:20,397][87424] Updated weights for policy 0, policy_version 212447 (0.0011) -[2023-11-28 05:46:20,717][87426] Updated weights for policy 1, policy_version 212040 (0.0010) -[2023-11-28 05:46:21,094][87426] Updated weights for policy 1, policy_version 212050 (0.0012) -[2023-11-28 05:46:21,472][87426] Updated weights for policy 1, policy_version 212060 (0.0012) -[2023-11-28 05:46:22,422][87424] Updated weights for policy 0, policy_version 212457 (0.0011) -[2023-11-28 05:46:22,806][87424] Updated weights for policy 0, policy_version 212467 (0.0011) -[2023-11-28 05:46:23,181][87424] Updated weights for policy 0, policy_version 212477 (0.0010) -[2023-11-28 05:46:23,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 108683264. Throughput: 0: 2704.2, 1: 2709.1. Samples: 108694744. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:23,445][86177] Avg episode reward: [(0, '-510.950'), (1, '-553.250')] -[2023-11-28 05:46:23,772][87426] Updated weights for policy 1, policy_version 212070 (0.0012) -[2023-11-28 05:46:24,156][87426] Updated weights for policy 1, policy_version 212080 (0.0011) -[2023-11-28 05:46:24,552][87426] Updated weights for policy 1, policy_version 212090 (0.0011) -[2023-11-28 05:46:25,748][87424] Updated weights for policy 0, policy_version 212487 (0.0008) -[2023-11-28 05:46:26,130][87424] Updated weights for policy 0, policy_version 212497 (0.0007) -[2023-11-28 05:46:26,527][87424] Updated weights for policy 0, policy_version 212507 (0.0007) -[2023-11-28 05:46:27,044][87426] Updated weights for policy 1, policy_version 212100 (0.0009) -[2023-11-28 05:46:27,434][87426] Updated weights for policy 1, policy_version 212110 (0.0012) -[2023-11-28 05:46:27,812][87426] Updated weights for policy 1, policy_version 212120 (0.0012) -[2023-11-28 05:46:28,428][87424] Updated weights for policy 0, policy_version 212517 (0.0011) -[2023-11-28 05:46:28,444][86177] Fps is (10 sec: 4917.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 108707840. Throughput: 0: 2706.7, 1: 2703.3. Samples: 108718896. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:28,445][86177] Avg episode reward: [(0, '-524.940'), (1, '-533.280')] -[2023-11-28 05:46:28,808][87424] Updated weights for policy 0, policy_version 212527 (0.0012) -[2023-11-28 05:46:29,180][87424] Updated weights for policy 0, policy_version 212537 (0.0010) -[2023-11-28 05:46:30,309][87426] Updated weights for policy 1, policy_version 212130 (0.0011) -[2023-11-28 05:46:30,690][87426] Updated weights for policy 1, policy_version 212140 (0.0011) -[2023-11-28 05:46:31,071][87426] Updated weights for policy 1, policy_version 212150 (0.0008) -[2023-11-28 05:46:31,378][87424] Updated weights for policy 0, policy_version 212547 (0.0010) -[2023-11-28 05:46:31,447][87426] Updated weights for policy 1, policy_version 212160 (0.0010) -[2023-11-28 05:46:31,764][87424] Updated weights for policy 0, policy_version 212557 (0.0009) -[2023-11-28 05:46:32,152][87424] Updated weights for policy 0, policy_version 212567 (0.0012) -[2023-11-28 05:46:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 108732416. Throughput: 0: 2728.2, 1: 2708.6. Samples: 108744112. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:33,445][86177] Avg episode reward: [(0, '-520.270'), (1, '-515.650')] -[2023-11-28 05:46:33,921][87426] Updated weights for policy 1, policy_version 212170 (0.0012) -[2023-11-28 05:46:34,310][87426] Updated weights for policy 1, policy_version 212180 (0.0008) -[2023-11-28 05:46:34,325][87424] Updated weights for policy 0, policy_version 212577 (0.0011) -[2023-11-28 05:46:34,689][87426] Updated weights for policy 1, policy_version 212190 (0.0008) -[2023-11-28 05:46:34,709][87424] Updated weights for policy 0, policy_version 212587 (0.0009) -[2023-11-28 05:46:35,087][87424] Updated weights for policy 0, policy_version 212597 (0.0011) -[2023-11-28 05:46:35,468][87424] Updated weights for policy 0, policy_version 212607 (0.0011) -[2023-11-28 05:46:36,835][87426] Updated weights for policy 1, policy_version 212200 (0.0012) -[2023-11-28 05:46:37,217][87426] Updated weights for policy 1, policy_version 212210 (0.0010) -[2023-11-28 05:46:37,294][87424] Updated weights for policy 0, policy_version 212617 (0.0012) -[2023-11-28 05:46:37,596][87426] Updated weights for policy 1, policy_version 212220 (0.0011) -[2023-11-28 05:46:37,677][87424] Updated weights for policy 0, policy_version 212627 (0.0012) -[2023-11-28 05:46:38,056][87424] Updated weights for policy 0, policy_version 212637 (0.0012) -[2023-11-28 05:46:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 108765184. Throughput: 0: 2764.7, 1: 2687.6. Samples: 108777920. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:38,445][86177] Avg episode reward: [(0, '-524.700'), (1, '-516.710')] -[2023-11-28 05:46:39,899][87426] Updated weights for policy 1, policy_version 212230 (0.0011) -[2023-11-28 05:46:40,279][87426] Updated weights for policy 1, policy_version 212240 (0.0009) -[2023-11-28 05:46:40,472][87424] Updated weights for policy 0, policy_version 212647 (0.0011) -[2023-11-28 05:46:40,658][87426] Updated weights for policy 1, policy_version 212250 (0.0011) -[2023-11-28 05:46:40,844][87424] Updated weights for policy 0, policy_version 212657 (0.0010) -[2023-11-28 05:46:41,225][87424] Updated weights for policy 0, policy_version 212667 (0.0008) -[2023-11-28 05:46:42,921][87426] Updated weights for policy 1, policy_version 212260 (0.0010) -[2023-11-28 05:46:43,297][87426] Updated weights for policy 1, policy_version 212270 (0.0011) -[2023-11-28 05:46:43,369][87424] Updated weights for policy 0, policy_version 212677 (0.0010) -[2023-11-28 05:46:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 108781568. Throughput: 0: 2764.6, 1: 2669.2. Samples: 108801424. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:43,445][86177] Avg episode reward: [(0, '-506.550'), (1, '-520.780')] -[2023-11-28 05:46:43,671][87426] Updated weights for policy 1, policy_version 212280 (0.0011) -[2023-11-28 05:46:43,750][87424] Updated weights for policy 0, policy_version 212687 (0.0011) -[2023-11-28 05:46:44,126][87424] Updated weights for policy 0, policy_version 212697 (0.0012) -[2023-11-28 05:46:45,917][87424] Updated weights for policy 0, policy_version 212707 (0.0012) -[2023-11-28 05:46:45,924][87426] Updated weights for policy 1, policy_version 212290 (0.0011) -[2023-11-28 05:46:46,296][87424] Updated weights for policy 0, policy_version 212717 (0.0012) -[2023-11-28 05:46:46,310][87426] Updated weights for policy 1, policy_version 212300 (0.0011) -[2023-11-28 05:46:46,684][87426] Updated weights for policy 1, policy_version 212310 (0.0011) -[2023-11-28 05:46:46,688][87424] Updated weights for policy 0, policy_version 212727 (0.0010) -[2023-11-28 05:46:47,059][87426] Updated weights for policy 1, policy_version 212320 (0.0010) -[2023-11-28 05:46:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 108814336. Throughput: 0: 2760.2, 1: 2661.8. Samples: 108826800. Policy #0 lag: (min: 2.0, avg: 22.4, max: 34.0) -[2023-11-28 05:46:48,445][86177] Avg episode reward: [(0, '-500.900'), (1, '-516.230')] -[2023-11-28 05:46:48,959][87424] Updated weights for policy 0, policy_version 212737 (0.0012) -[2023-11-28 05:46:49,131][87426] Updated weights for policy 1, policy_version 212330 (0.0010) -[2023-11-28 05:46:49,344][87424] Updated weights for policy 0, policy_version 212747 (0.0011) -[2023-11-28 05:46:49,511][87426] Updated weights for policy 1, policy_version 212340 (0.0011) -[2023-11-28 05:46:49,744][87424] Updated weights for policy 0, policy_version 212757 (0.0010) -[2023-11-28 05:46:49,880][87426] Updated weights for policy 1, policy_version 212350 (0.0012) -[2023-11-28 05:46:50,125][87424] Updated weights for policy 0, policy_version 212767 (0.0011) -[2023-11-28 05:46:51,851][87426] Updated weights for policy 1, policy_version 212360 (0.0011) -[2023-11-28 05:46:51,972][87424] Updated weights for policy 0, policy_version 212777 (0.0011) -[2023-11-28 05:46:52,230][87426] Updated weights for policy 1, policy_version 212370 (0.0010) -[2023-11-28 05:46:52,353][87424] Updated weights for policy 0, policy_version 212787 (0.0011) -[2023-11-28 05:46:52,607][87426] Updated weights for policy 1, policy_version 212380 (0.0011) -[2023-11-28 05:46:52,741][87424] Updated weights for policy 0, policy_version 212797 (0.0008) -[2023-11-28 05:46:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 108847104. Throughput: 0: 2752.0, 1: 2670.5. Samples: 108860140. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:46:53,445][86177] Avg episode reward: [(0, '-503.620'), (1, '-520.050')] -[2023-11-28 05:46:55,195][87426] Updated weights for policy 1, policy_version 212390 (0.0010) -[2023-11-28 05:46:55,206][87424] Updated weights for policy 0, policy_version 212807 (0.0010) -[2023-11-28 05:46:55,579][87426] Updated weights for policy 1, policy_version 212400 (0.0007) -[2023-11-28 05:46:55,599][87424] Updated weights for policy 0, policy_version 212817 (0.0011) -[2023-11-28 05:46:55,962][87426] Updated weights for policy 1, policy_version 212410 (0.0007) -[2023-11-28 05:46:55,971][87424] Updated weights for policy 0, policy_version 212827 (0.0012) -[2023-11-28 05:46:57,632][87424] Updated weights for policy 0, policy_version 212837 (0.0012) -[2023-11-28 05:46:57,833][87426] Updated weights for policy 1, policy_version 212420 (0.0009) -[2023-11-28 05:46:58,015][87424] Updated weights for policy 0, policy_version 212847 (0.0012) -[2023-11-28 05:46:58,216][87426] Updated weights for policy 1, policy_version 212430 (0.0008) -[2023-11-28 05:46:58,397][87424] Updated weights for policy 0, policy_version 212857 (0.0011) -[2023-11-28 05:46:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 108863488. Throughput: 0: 2751.4, 1: 2709.5. Samples: 108885288. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:46:58,445][86177] Avg episode reward: [(0, '-547.830'), (1, '-523.510')] -[2023-11-28 05:46:58,601][87426] Updated weights for policy 1, policy_version 212440 (0.0007) -[2023-11-28 05:47:00,213][87424] Updated weights for policy 0, policy_version 212867 (0.0010) -[2023-11-28 05:47:00,592][87424] Updated weights for policy 0, policy_version 212877 (0.0009) -[2023-11-28 05:47:00,645][87426] Updated weights for policy 1, policy_version 212450 (0.0009) -[2023-11-28 05:47:00,983][87424] Updated weights for policy 0, policy_version 212887 (0.0011) -[2023-11-28 05:47:01,024][87426] Updated weights for policy 1, policy_version 212460 (0.0009) -[2023-11-28 05:47:01,403][87426] Updated weights for policy 1, policy_version 212470 (0.0008) -[2023-11-28 05:47:01,783][87426] Updated weights for policy 1, policy_version 212480 (0.0009) -[2023-11-28 05:47:03,259][87424] Updated weights for policy 0, policy_version 212897 (0.0009) -[2023-11-28 05:47:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 108896256. Throughput: 0: 2783.0, 1: 2718.9. Samples: 108911044. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:03,445][86177] Avg episode reward: [(0, '-548.020'), (1, '-542.000')] -[2023-11-28 05:47:03,638][87424] Updated weights for policy 0, policy_version 212907 (0.0012) -[2023-11-28 05:47:03,802][87426] Updated weights for policy 1, policy_version 212490 (0.0011) -[2023-11-28 05:47:04,020][87424] Updated weights for policy 0, policy_version 212917 (0.0008) -[2023-11-28 05:47:04,180][87426] Updated weights for policy 1, policy_version 212500 (0.0011) -[2023-11-28 05:47:04,395][87424] Updated weights for policy 0, policy_version 212927 (0.0008) -[2023-11-28 05:47:04,562][87426] Updated weights for policy 1, policy_version 212510 (0.0012) -[2023-11-28 05:47:06,569][87424] Updated weights for policy 0, policy_version 212937 (0.0012) -[2023-11-28 05:47:06,590][87426] Updated weights for policy 1, policy_version 212520 (0.0012) -[2023-11-28 05:47:06,942][87424] Updated weights for policy 0, policy_version 212947 (0.0012) -[2023-11-28 05:47:06,961][87426] Updated weights for policy 1, policy_version 212530 (0.0012) -[2023-11-28 05:47:07,319][87424] Updated weights for policy 0, policy_version 212957 (0.0011) -[2023-11-28 05:47:07,335][87426] Updated weights for policy 1, policy_version 212540 (0.0012) -[2023-11-28 05:47:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 108929024. Throughput: 0: 2797.5, 1: 2735.5. Samples: 108943728. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:08,445][86177] Avg episode reward: [(0, '-547.680'), (1, '-543.720')] -[2023-11-28 05:47:09,058][87424] Updated weights for policy 0, policy_version 212967 (0.0012) -[2023-11-28 05:47:09,448][87424] Updated weights for policy 0, policy_version 212977 (0.0009) -[2023-11-28 05:47:09,677][87426] Updated weights for policy 1, policy_version 212550 (0.0009) -[2023-11-28 05:47:09,825][87424] Updated weights for policy 0, policy_version 212987 (0.0010) -[2023-11-28 05:47:10,055][87426] Updated weights for policy 1, policy_version 212560 (0.0009) -[2023-11-28 05:47:10,437][87426] Updated weights for policy 1, policy_version 212570 (0.0009) -[2023-11-28 05:47:12,137][87424] Updated weights for policy 0, policy_version 212997 (0.0008) -[2023-11-28 05:47:12,399][87426] Updated weights for policy 1, policy_version 212580 (0.0009) -[2023-11-28 05:47:12,521][87424] Updated weights for policy 0, policy_version 213007 (0.0010) -[2023-11-28 05:47:12,783][87426] Updated weights for policy 1, policy_version 212590 (0.0008) -[2023-11-28 05:47:12,901][87424] Updated weights for policy 0, policy_version 213017 (0.0011) -[2023-11-28 05:47:13,159][87426] Updated weights for policy 1, policy_version 212600 (0.0008) -[2023-11-28 05:47:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 108953600. Throughput: 0: 2802.4, 1: 2750.8. Samples: 108968788. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:13,445][86177] Avg episode reward: [(0, '-555.170'), (1, '-542.270')] -[2023-11-28 05:47:14,826][87424] Updated weights for policy 0, policy_version 213027 (0.0012) -[2023-11-28 05:47:15,215][87424] Updated weights for policy 0, policy_version 213037 (0.0008) -[2023-11-28 05:47:15,602][87424] Updated weights for policy 0, policy_version 213047 (0.0008) -[2023-11-28 05:47:15,630][87426] Updated weights for policy 1, policy_version 212610 (0.0009) -[2023-11-28 05:47:16,014][87426] Updated weights for policy 1, policy_version 212620 (0.0010) -[2023-11-28 05:47:16,394][87426] Updated weights for policy 1, policy_version 212630 (0.0010) -[2023-11-28 05:47:16,768][87426] Updated weights for policy 1, policy_version 212640 (0.0011) -[2023-11-28 05:47:17,568][87424] Updated weights for policy 0, policy_version 213057 (0.0009) -[2023-11-28 05:47:17,957][87424] Updated weights for policy 0, policy_version 213067 (0.0012) -[2023-11-28 05:47:18,344][87424] Updated weights for policy 0, policy_version 213077 (0.0012) -[2023-11-28 05:47:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5325.2, 300 sec: 5415.0). Total num frames: 108978176. Throughput: 0: 2805.0, 1: 2728.0. Samples: 108993096. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:18,446][86177] Avg episode reward: [(0, '-512.860'), (1, '-538.500')] -[2023-11-28 05:47:18,733][87424] Updated weights for policy 0, policy_version 213087 (0.0008) -[2023-11-28 05:47:19,221][87426] Updated weights for policy 1, policy_version 212650 (0.0008) -[2023-11-28 05:47:19,589][87426] Updated weights for policy 1, policy_version 212660 (0.0010) -[2023-11-28 05:47:19,974][87426] Updated weights for policy 1, policy_version 212670 (0.0008) -[2023-11-28 05:47:21,195][87424] Updated weights for policy 0, policy_version 213097 (0.0011) -[2023-11-28 05:47:21,579][87424] Updated weights for policy 0, policy_version 213107 (0.0011) -[2023-11-28 05:47:21,834][87426] Updated weights for policy 1, policy_version 212680 (0.0011) -[2023-11-28 05:47:21,963][87424] Updated weights for policy 0, policy_version 213117 (0.0011) -[2023-11-28 05:47:22,218][87426] Updated weights for policy 1, policy_version 212690 (0.0011) -[2023-11-28 05:47:22,598][87426] Updated weights for policy 1, policy_version 212700 (0.0011) -[2023-11-28 05:47:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109010944. Throughput: 0: 2778.4, 1: 2713.3. Samples: 109025048. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:23,445][86177] Avg episode reward: [(0, '-512.860'), (1, '-510.310')] -[2023-11-28 05:47:24,074][87424] Updated weights for policy 0, policy_version 213127 (0.0012) -[2023-11-28 05:47:24,452][87424] Updated weights for policy 0, policy_version 213137 (0.0011) -[2023-11-28 05:47:24,637][87426] Updated weights for policy 1, policy_version 212710 (0.0010) -[2023-11-28 05:47:24,841][87424] Updated weights for policy 0, policy_version 213147 (0.0011) -[2023-11-28 05:47:25,019][87426] Updated weights for policy 1, policy_version 212720 (0.0010) -[2023-11-28 05:47:25,401][87426] Updated weights for policy 1, policy_version 212730 (0.0008) -[2023-11-28 05:47:26,817][87424] Updated weights for policy 0, policy_version 213157 (0.0010) -[2023-11-28 05:47:27,191][87424] Updated weights for policy 0, policy_version 213167 (0.0008) -[2023-11-28 05:47:27,572][87424] Updated weights for policy 0, policy_version 213177 (0.0008) -[2023-11-28 05:47:27,713][87426] Updated weights for policy 1, policy_version 212740 (0.0008) -[2023-11-28 05:47:28,092][87426] Updated weights for policy 1, policy_version 212750 (0.0009) -[2023-11-28 05:47:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109035520. Throughput: 0: 2800.1, 1: 2761.7. Samples: 109051704. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:28,445][86177] Avg episode reward: [(0, '-519.530'), (1, '-512.650')] -[2023-11-28 05:47:28,475][87426] Updated weights for policy 1, policy_version 212760 (0.0007) -[2023-11-28 05:47:29,405][87424] Updated weights for policy 0, policy_version 213187 (0.0010) -[2023-11-28 05:47:29,785][87424] Updated weights for policy 0, policy_version 213197 (0.0011) -[2023-11-28 05:47:30,175][87424] Updated weights for policy 0, policy_version 213207 (0.0009) -[2023-11-28 05:47:30,561][87426] Updated weights for policy 1, policy_version 212770 (0.0009) -[2023-11-28 05:47:30,931][87426] Updated weights for policy 1, policy_version 212780 (0.0008) -[2023-11-28 05:47:31,312][87426] Updated weights for policy 1, policy_version 212790 (0.0007) -[2023-11-28 05:47:31,702][87426] Updated weights for policy 1, policy_version 212800 (0.0009) -[2023-11-28 05:47:32,626][87424] Updated weights for policy 0, policy_version 213217 (0.0009) -[2023-11-28 05:47:32,998][87424] Updated weights for policy 0, policy_version 213227 (0.0009) -[2023-11-28 05:47:33,390][87424] Updated weights for policy 0, policy_version 213237 (0.0009) -[2023-11-28 05:47:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 109060096. Throughput: 0: 2792.8, 1: 2747.6. Samples: 109076116. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:33,445][86177] Avg episode reward: [(0, '-513.190'), (1, '-516.890')] -[2023-11-28 05:47:33,771][87424] Updated weights for policy 0, policy_version 213247 (0.0011) -[2023-11-28 05:47:33,865][87426] Updated weights for policy 1, policy_version 212810 (0.0009) -[2023-11-28 05:47:34,243][87426] Updated weights for policy 1, policy_version 212820 (0.0007) -[2023-11-28 05:47:34,629][87426] Updated weights for policy 1, policy_version 212830 (0.0007) -[2023-11-28 05:47:35,706][87424] Updated weights for policy 0, policy_version 213257 (0.0012) -[2023-11-28 05:47:36,087][87424] Updated weights for policy 0, policy_version 213267 (0.0012) -[2023-11-28 05:47:36,465][87424] Updated weights for policy 0, policy_version 213277 (0.0010) -[2023-11-28 05:47:36,722][87426] Updated weights for policy 1, policy_version 212840 (0.0011) -[2023-11-28 05:47:37,100][87426] Updated weights for policy 1, policy_version 212850 (0.0010) -[2023-11-28 05:47:37,483][87426] Updated weights for policy 1, policy_version 212860 (0.0011) -[2023-11-28 05:47:38,383][87424] Updated weights for policy 0, policy_version 213287 (0.0010) -[2023-11-28 05:47:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109092864. Throughput: 0: 2807.7, 1: 2723.5. Samples: 109109044. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:38,445][86177] Avg episode reward: [(0, '-510.100'), (1, '-522.660')] -[2023-11-28 05:47:38,764][87424] Updated weights for policy 0, policy_version 213297 (0.0012) -[2023-11-28 05:47:39,147][87424] Updated weights for policy 0, policy_version 213307 (0.0010) -[2023-11-28 05:47:39,722][87426] Updated weights for policy 1, policy_version 212870 (0.0010) -[2023-11-28 05:47:40,099][87426] Updated weights for policy 1, policy_version 212880 (0.0008) -[2023-11-28 05:47:40,475][87426] Updated weights for policy 1, policy_version 212890 (0.0008) -[2023-11-28 05:47:41,401][87424] Updated weights for policy 0, policy_version 213317 (0.0011) -[2023-11-28 05:47:41,786][87424] Updated weights for policy 0, policy_version 213327 (0.0012) -[2023-11-28 05:47:42,182][87424] Updated weights for policy 0, policy_version 213337 (0.0009) -[2023-11-28 05:47:42,836][87426] Updated weights for policy 1, policy_version 212900 (0.0008) -[2023-11-28 05:47:43,216][87426] Updated weights for policy 1, policy_version 212910 (0.0012) -[2023-11-28 05:47:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 109117440. Throughput: 0: 2808.9, 1: 2717.6. Samples: 109133980. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:43,445][86177] Avg episode reward: [(0, '-512.690'), (1, '-522.290')] -[2023-11-28 05:47:43,599][87426] Updated weights for policy 1, policy_version 212920 (0.0011) -[2023-11-28 05:47:44,497][87424] Updated weights for policy 0, policy_version 213347 (0.0008) -[2023-11-28 05:47:44,887][87424] Updated weights for policy 0, policy_version 213357 (0.0008) -[2023-11-28 05:47:45,264][87424] Updated weights for policy 0, policy_version 213367 (0.0007) -[2023-11-28 05:47:45,458][87426] Updated weights for policy 1, policy_version 212930 (0.0011) -[2023-11-28 05:47:45,830][87426] Updated weights for policy 1, policy_version 212940 (0.0012) -[2023-11-28 05:47:46,205][87426] Updated weights for policy 1, policy_version 212950 (0.0012) -[2023-11-28 05:47:46,583][87426] Updated weights for policy 1, policy_version 212960 (0.0012) -[2023-11-28 05:47:47,647][87424] Updated weights for policy 0, policy_version 213377 (0.0011) -[2023-11-28 05:47:48,029][87424] Updated weights for policy 0, policy_version 213387 (0.0012) -[2023-11-28 05:47:48,398][87424] Updated weights for policy 0, policy_version 213397 (0.0009) -[2023-11-28 05:47:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 109142016. Throughput: 0: 2770.3, 1: 2719.9. Samples: 109158104. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:48,445][86177] Avg episode reward: [(0, '-512.050'), (1, '-520.050')] -[2023-11-28 05:47:48,782][87424] Updated weights for policy 0, policy_version 213407 (0.0007) -[2023-11-28 05:47:49,050][87426] Updated weights for policy 1, policy_version 212970 (0.0012) -[2023-11-28 05:47:49,418][87426] Updated weights for policy 1, policy_version 212980 (0.0012) -[2023-11-28 05:47:49,803][87426] Updated weights for policy 1, policy_version 212990 (0.0012) -[2023-11-28 05:47:50,779][87424] Updated weights for policy 0, policy_version 213417 (0.0011) -[2023-11-28 05:47:51,170][87424] Updated weights for policy 0, policy_version 213427 (0.0011) -[2023-11-28 05:47:51,548][87424] Updated weights for policy 0, policy_version 213437 (0.0012) -[2023-11-28 05:47:51,595][87426] Updated weights for policy 1, policy_version 213000 (0.0009) -[2023-11-28 05:47:51,975][87426] Updated weights for policy 1, policy_version 213010 (0.0011) -[2023-11-28 05:47:52,358][87426] Updated weights for policy 1, policy_version 213020 (0.0012) -[2023-11-28 05:47:53,445][86177] Fps is (10 sec: 5734.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109174784. Throughput: 0: 2781.4, 1: 2723.3. Samples: 109191440. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:53,446][86177] Avg episode reward: [(0, '-518.420'), (1, '-532.210')] -[2023-11-28 05:47:53,704][87424] Updated weights for policy 0, policy_version 213447 (0.0013) -[2023-11-28 05:47:54,078][87424] Updated weights for policy 0, policy_version 213457 (0.0008) -[2023-11-28 05:47:54,323][87426] Updated weights for policy 1, policy_version 213030 (0.0010) -[2023-11-28 05:47:54,460][87424] Updated weights for policy 0, policy_version 213467 (0.0009) -[2023-11-28 05:47:54,705][87426] Updated weights for policy 1, policy_version 213040 (0.0008) -[2023-11-28 05:47:55,087][87426] Updated weights for policy 1, policy_version 213050 (0.0008) -[2023-11-28 05:47:56,573][87424] Updated weights for policy 0, policy_version 213477 (0.0012) -[2023-11-28 05:47:56,961][87424] Updated weights for policy 0, policy_version 213487 (0.0012) -[2023-11-28 05:47:57,345][87424] Updated weights for policy 0, policy_version 213497 (0.0012) -[2023-11-28 05:47:57,637][87426] Updated weights for policy 1, policy_version 213060 (0.0008) -[2023-11-28 05:47:58,019][87426] Updated weights for policy 1, policy_version 213070 (0.0008) -[2023-11-28 05:47:58,403][87426] Updated weights for policy 1, policy_version 213080 (0.0007) -[2023-11-28 05:47:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 109199360. Throughput: 0: 2763.1, 1: 2737.2. Samples: 109216304. Policy #0 lag: (min: 19.0, avg: 45.8, max: 67.0) -[2023-11-28 05:47:58,445][86177] Avg episode reward: [(0, '-529.980'), (1, '-531.730')] -[2023-11-28 05:47:59,672][87424] Updated weights for policy 0, policy_version 213507 (0.0009) -[2023-11-28 05:48:00,060][87424] Updated weights for policy 0, policy_version 213517 (0.0010) -[2023-11-28 05:48:00,450][87424] Updated weights for policy 0, policy_version 213527 (0.0010) -[2023-11-28 05:48:00,916][87426] Updated weights for policy 1, policy_version 213090 (0.0008) -[2023-11-28 05:48:01,297][87426] Updated weights for policy 1, policy_version 213100 (0.0012) -[2023-11-28 05:48:01,693][87426] Updated weights for policy 1, policy_version 213110 (0.0011) -[2023-11-28 05:48:02,063][87426] Updated weights for policy 1, policy_version 213120 (0.0011) -[2023-11-28 05:48:02,793][87424] Updated weights for policy 0, policy_version 213537 (0.0011) -[2023-11-28 05:48:03,181][87424] Updated weights for policy 0, policy_version 213547 (0.0012) -[2023-11-28 05:48:03,444][86177] Fps is (10 sec: 4915.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 109223936. Throughput: 0: 2735.8, 1: 2745.7. Samples: 109239760. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:03,445][86177] Avg episode reward: [(0, '-523.240'), (1, '-529.980')] -[2023-11-28 05:48:03,554][87424] Updated weights for policy 0, policy_version 213557 (0.0012) -[2023-11-28 05:48:03,944][87424] Updated weights for policy 0, policy_version 213567 (0.0012) -[2023-11-28 05:48:04,408][87426] Updated weights for policy 1, policy_version 213130 (0.0008) -[2023-11-28 05:48:04,786][87426] Updated weights for policy 1, policy_version 213140 (0.0012) -[2023-11-28 05:48:05,163][87426] Updated weights for policy 1, policy_version 213150 (0.0012) -[2023-11-28 05:48:06,446][87424] Updated weights for policy 0, policy_version 213577 (0.0008) -[2023-11-28 05:48:06,826][87424] Updated weights for policy 0, policy_version 213587 (0.0009) -[2023-11-28 05:48:07,210][87424] Updated weights for policy 0, policy_version 213597 (0.0011) -[2023-11-28 05:48:07,305][87426] Updated weights for policy 1, policy_version 213160 (0.0011) -[2023-11-28 05:48:07,687][87426] Updated weights for policy 1, policy_version 213170 (0.0012) -[2023-11-28 05:48:08,066][87426] Updated weights for policy 1, policy_version 213180 (0.0012) -[2023-11-28 05:48:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109256704. Throughput: 0: 2721.2, 1: 2768.8. Samples: 109272096. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:08,445][86177] Avg episode reward: [(0, '-514.980'), (1, '-523.050')] -[2023-11-28 05:48:09,599][87424] Updated weights for policy 0, policy_version 213607 (0.0010) -[2023-11-28 05:48:09,853][87426] Updated weights for policy 1, policy_version 213190 (0.0011) -[2023-11-28 05:48:09,980][87424] Updated weights for policy 0, policy_version 213617 (0.0008) -[2023-11-28 05:48:10,230][87426] Updated weights for policy 1, policy_version 213200 (0.0012) -[2023-11-28 05:48:10,367][87424] Updated weights for policy 0, policy_version 213627 (0.0008) -[2023-11-28 05:48:10,615][87426] Updated weights for policy 1, policy_version 213210 (0.0011) -[2023-11-28 05:48:12,689][87424] Updated weights for policy 0, policy_version 213637 (0.0010) -[2023-11-28 05:48:13,075][87424] Updated weights for policy 0, policy_version 213647 (0.0012) -[2023-11-28 05:48:13,081][87426] Updated weights for policy 1, policy_version 213220 (0.0009) -[2023-11-28 05:48:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 109273088. Throughput: 0: 2703.7, 1: 2726.1. Samples: 109296048. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:13,445][86177] Avg episode reward: [(0, '-515.040'), (1, '-550.640')] -[2023-11-28 05:48:13,462][87424] Updated weights for policy 0, policy_version 213657 (0.0012) -[2023-11-28 05:48:13,469][87426] Updated weights for policy 1, policy_version 213230 (0.0011) -[2023-11-28 05:48:13,839][87426] Updated weights for policy 1, policy_version 213240 (0.0012) -[2023-11-28 05:48:15,234][87424] Updated weights for policy 0, policy_version 213667 (0.0012) -[2023-11-28 05:48:15,611][87424] Updated weights for policy 0, policy_version 213677 (0.0012) -[2023-11-28 05:48:15,652][87426] Updated weights for policy 1, policy_version 213250 (0.0012) -[2023-11-28 05:48:15,991][87424] Updated weights for policy 0, policy_version 213687 (0.0011) -[2023-11-28 05:48:16,021][87426] Updated weights for policy 1, policy_version 213260 (0.0012) -[2023-11-28 05:48:16,390][87426] Updated weights for policy 1, policy_version 213270 (0.0011) -[2023-11-28 05:48:16,779][87426] Updated weights for policy 1, policy_version 213280 (0.0008) -[2023-11-28 05:48:17,870][87424] Updated weights for policy 0, policy_version 213697 (0.0011) -[2023-11-28 05:48:18,256][87424] Updated weights for policy 0, policy_version 213707 (0.0008) -[2023-11-28 05:48:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 109305856. Throughput: 0: 2702.6, 1: 2733.9. Samples: 109320756. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:18,445][86177] Avg episode reward: [(0, '-503.220'), (1, '-548.930')] -[2023-11-28 05:48:18,643][87424] Updated weights for policy 0, policy_version 213717 (0.0010) -[2023-11-28 05:48:18,849][87426] Updated weights for policy 1, policy_version 213290 (0.0010) -[2023-11-28 05:48:19,023][87424] Updated weights for policy 0, policy_version 213727 (0.0011) -[2023-11-28 05:48:19,061][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000213728_54714368.pth... -[2023-11-28 05:48:19,095][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000211136_54050816.pth -[2023-11-28 05:48:19,220][87426] Updated weights for policy 1, policy_version 213300 (0.0008) -[2023-11-28 05:48:19,602][87426] Updated weights for policy 1, policy_version 213310 (0.0008) -[2023-11-28 05:48:19,676][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000213312_54607872.pth... -[2023-11-28 05:48:19,724][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000210784_53960704.pth -[2023-11-28 05:48:21,125][87424] Updated weights for policy 0, policy_version 213737 (0.0009) -[2023-11-28 05:48:21,507][87424] Updated weights for policy 0, policy_version 213747 (0.0011) -[2023-11-28 05:48:21,559][87426] Updated weights for policy 1, policy_version 213320 (0.0011) -[2023-11-28 05:48:21,889][87424] Updated weights for policy 0, policy_version 213757 (0.0011) -[2023-11-28 05:48:21,927][87426] Updated weights for policy 1, policy_version 213330 (0.0011) -[2023-11-28 05:48:22,309][87426] Updated weights for policy 1, policy_version 213340 (0.0012) -[2023-11-28 05:48:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109338624. Throughput: 0: 2702.0, 1: 2742.8. Samples: 109354060. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:23,445][86177] Avg episode reward: [(0, '-507.620'), (1, '-550.490')] -[2023-11-28 05:48:24,044][87424] Updated weights for policy 0, policy_version 213767 (0.0010) -[2023-11-28 05:48:24,085][87426] Updated weights for policy 1, policy_version 213350 (0.0012) -[2023-11-28 05:48:24,430][87424] Updated weights for policy 0, policy_version 213777 (0.0008) -[2023-11-28 05:48:24,466][87426] Updated weights for policy 1, policy_version 213360 (0.0009) -[2023-11-28 05:48:24,803][87424] Updated weights for policy 0, policy_version 213787 (0.0008) -[2023-11-28 05:48:24,848][87426] Updated weights for policy 1, policy_version 213370 (0.0008) -[2023-11-28 05:48:27,171][87424] Updated weights for policy 0, policy_version 213797 (0.0010) -[2023-11-28 05:48:27,314][87426] Updated weights for policy 1, policy_version 213380 (0.0010) -[2023-11-28 05:48:27,552][87424] Updated weights for policy 0, policy_version 213807 (0.0012) -[2023-11-28 05:48:27,700][87426] Updated weights for policy 1, policy_version 213390 (0.0008) -[2023-11-28 05:48:27,941][87424] Updated weights for policy 0, policy_version 213817 (0.0012) -[2023-11-28 05:48:28,086][87426] Updated weights for policy 1, policy_version 213400 (0.0007) -[2023-11-28 05:48:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 109371392. Throughput: 0: 2695.7, 1: 2730.5. Samples: 109378160. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:28,445][86177] Avg episode reward: [(0, '-506.750'), (1, '-551.110')] -[2023-11-28 05:48:30,349][87426] Updated weights for policy 1, policy_version 213410 (0.0008) -[2023-11-28 05:48:30,560][87424] Updated weights for policy 0, policy_version 213827 (0.0012) -[2023-11-28 05:48:30,731][87426] Updated weights for policy 1, policy_version 213420 (0.0010) -[2023-11-28 05:48:30,932][87424] Updated weights for policy 0, policy_version 213837 (0.0008) -[2023-11-28 05:48:31,111][87426] Updated weights for policy 1, policy_version 213430 (0.0011) -[2023-11-28 05:48:31,325][87424] Updated weights for policy 0, policy_version 213847 (0.0007) -[2023-11-28 05:48:31,477][87426] Updated weights for policy 1, policy_version 213440 (0.0012) -[2023-11-28 05:48:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 109387776. Throughput: 0: 2701.4, 1: 2724.0. Samples: 109402248. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:33,445][86177] Avg episode reward: [(0, '-503.030'), (1, '-510.130')] -[2023-11-28 05:48:33,554][87426] Updated weights for policy 1, policy_version 213450 (0.0012) -[2023-11-28 05:48:33,575][87424] Updated weights for policy 0, policy_version 213857 (0.0009) -[2023-11-28 05:48:33,930][87426] Updated weights for policy 1, policy_version 213460 (0.0009) -[2023-11-28 05:48:33,953][87424] Updated weights for policy 0, policy_version 213867 (0.0009) -[2023-11-28 05:48:34,309][87426] Updated weights for policy 1, policy_version 213470 (0.0012) -[2023-11-28 05:48:34,344][87424] Updated weights for policy 0, policy_version 213877 (0.0007) -[2023-11-28 05:48:34,733][87424] Updated weights for policy 0, policy_version 213887 (0.0008) -[2023-11-28 05:48:36,545][87426] Updated weights for policy 1, policy_version 213480 (0.0011) -[2023-11-28 05:48:36,914][87426] Updated weights for policy 1, policy_version 213490 (0.0011) -[2023-11-28 05:48:36,970][87424] Updated weights for policy 0, policy_version 213897 (0.0011) -[2023-11-28 05:48:37,294][87426] Updated weights for policy 1, policy_version 213500 (0.0011) -[2023-11-28 05:48:37,351][87424] Updated weights for policy 0, policy_version 213907 (0.0009) -[2023-11-28 05:48:37,731][87424] Updated weights for policy 0, policy_version 213917 (0.0008) -[2023-11-28 05:48:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109420544. Throughput: 0: 2664.3, 1: 2733.7. Samples: 109434348. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:38,445][86177] Avg episode reward: [(0, '-505.680'), (1, '-518.420')] -[2023-11-28 05:48:39,064][87426] Updated weights for policy 1, policy_version 213510 (0.0010) -[2023-11-28 05:48:39,438][87426] Updated weights for policy 1, policy_version 213520 (0.0011) -[2023-11-28 05:48:39,548][87424] Updated weights for policy 0, policy_version 213927 (0.0009) -[2023-11-28 05:48:39,834][87426] Updated weights for policy 1, policy_version 213530 (0.0012) -[2023-11-28 05:48:39,931][87424] Updated weights for policy 0, policy_version 213937 (0.0011) -[2023-11-28 05:48:40,312][87424] Updated weights for policy 0, policy_version 213947 (0.0010) -[2023-11-28 05:48:42,040][87426] Updated weights for policy 1, policy_version 213540 (0.0009) -[2023-11-28 05:48:42,414][87426] Updated weights for policy 1, policy_version 213550 (0.0011) -[2023-11-28 05:48:42,799][87426] Updated weights for policy 1, policy_version 213560 (0.0012) -[2023-11-28 05:48:42,839][87424] Updated weights for policy 0, policy_version 213957 (0.0009) -[2023-11-28 05:48:43,211][87424] Updated weights for policy 0, policy_version 213967 (0.0009) -[2023-11-28 05:48:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109445120. Throughput: 0: 2674.3, 1: 2725.9. Samples: 109459312. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:43,445][86177] Avg episode reward: [(0, '-505.400'), (1, '-523.390')] -[2023-11-28 05:48:43,597][87424] Updated weights for policy 0, policy_version 213977 (0.0009) -[2023-11-28 05:48:44,699][87426] Updated weights for policy 1, policy_version 213570 (0.0012) -[2023-11-28 05:48:45,079][87426] Updated weights for policy 1, policy_version 213580 (0.0009) -[2023-11-28 05:48:45,460][87426] Updated weights for policy 1, policy_version 213590 (0.0011) -[2023-11-28 05:48:45,851][87426] Updated weights for policy 1, policy_version 213600 (0.0010) -[2023-11-28 05:48:46,161][87424] Updated weights for policy 0, policy_version 213987 (0.0008) -[2023-11-28 05:48:46,540][87424] Updated weights for policy 0, policy_version 213997 (0.0007) -[2023-11-28 05:48:46,926][87424] Updated weights for policy 0, policy_version 214007 (0.0007) -[2023-11-28 05:48:48,013][87426] Updated weights for policy 1, policy_version 213610 (0.0011) -[2023-11-28 05:48:48,391][87426] Updated weights for policy 1, policy_version 213620 (0.0007) -[2023-11-28 05:48:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109469696. Throughput: 0: 2654.8, 1: 2745.7. Samples: 109482780. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:48,445][86177] Avg episode reward: [(0, '-504.780'), (1, '-524.490')] -[2023-11-28 05:48:48,772][87426] Updated weights for policy 1, policy_version 213630 (0.0007) -[2023-11-28 05:48:49,295][87424] Updated weights for policy 0, policy_version 214017 (0.0007) -[2023-11-28 05:48:49,687][87424] Updated weights for policy 0, policy_version 214027 (0.0011) -[2023-11-28 05:48:50,066][87424] Updated weights for policy 0, policy_version 214037 (0.0010) -[2023-11-28 05:48:50,449][87424] Updated weights for policy 0, policy_version 214047 (0.0008) -[2023-11-28 05:48:51,177][87426] Updated weights for policy 1, policy_version 213640 (0.0010) -[2023-11-28 05:48:51,552][87426] Updated weights for policy 1, policy_version 213650 (0.0008) -[2023-11-28 05:48:51,937][87426] Updated weights for policy 1, policy_version 213660 (0.0011) -[2023-11-28 05:48:52,847][87424] Updated weights for policy 0, policy_version 214057 (0.0011) -[2023-11-28 05:48:53,220][87424] Updated weights for policy 0, policy_version 214067 (0.0008) -[2023-11-28 05:48:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 109494272. Throughput: 0: 2664.5, 1: 2726.7. Samples: 109514704. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:53,445][86177] Avg episode reward: [(0, '-511.240'), (1, '-522.810')] -[2023-11-28 05:48:53,609][87424] Updated weights for policy 0, policy_version 214077 (0.0011) -[2023-11-28 05:48:53,977][87426] Updated weights for policy 1, policy_version 213670 (0.0012) -[2023-11-28 05:48:54,364][87426] Updated weights for policy 1, policy_version 213680 (0.0012) -[2023-11-28 05:48:54,746][87426] Updated weights for policy 1, policy_version 213690 (0.0011) -[2023-11-28 05:48:56,275][87424] Updated weights for policy 0, policy_version 214087 (0.0011) -[2023-11-28 05:48:56,651][87424] Updated weights for policy 0, policy_version 214097 (0.0011) -[2023-11-28 05:48:57,034][87424] Updated weights for policy 0, policy_version 214107 (0.0011) -[2023-11-28 05:48:57,071][87426] Updated weights for policy 1, policy_version 213700 (0.0011) -[2023-11-28 05:48:57,466][87426] Updated weights for policy 1, policy_version 213710 (0.0012) -[2023-11-28 05:48:57,845][87426] Updated weights for policy 1, policy_version 213720 (0.0012) -[2023-11-28 05:48:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109527040. Throughput: 0: 2677.4, 1: 2746.6. Samples: 109540128. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:48:58,445][86177] Avg episode reward: [(0, '-519.390'), (1, '-531.260')] -[2023-11-28 05:48:58,996][87424] Updated weights for policy 0, policy_version 214117 (0.0010) -[2023-11-28 05:48:59,382][87424] Updated weights for policy 0, policy_version 214127 (0.0012) -[2023-11-28 05:48:59,731][87426] Updated weights for policy 1, policy_version 213730 (0.0012) -[2023-11-28 05:48:59,758][87424] Updated weights for policy 0, policy_version 214137 (0.0012) -[2023-11-28 05:49:00,110][87426] Updated weights for policy 1, policy_version 213740 (0.0010) -[2023-11-28 05:49:00,497][87426] Updated weights for policy 1, policy_version 213750 (0.0009) -[2023-11-28 05:49:00,871][87426] Updated weights for policy 1, policy_version 213760 (0.0011) -[2023-11-28 05:49:01,717][87424] Updated weights for policy 0, policy_version 214147 (0.0011) -[2023-11-28 05:49:02,099][87424] Updated weights for policy 0, policy_version 214157 (0.0012) -[2023-11-28 05:49:02,479][87424] Updated weights for policy 0, policy_version 214167 (0.0012) -[2023-11-28 05:49:03,429][87426] Updated weights for policy 1, policy_version 213770 (0.0012) -[2023-11-28 05:49:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 109551616. Throughput: 0: 2672.3, 1: 2753.6. Samples: 109564924. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:49:03,446][86177] Avg episode reward: [(0, '-517.310'), (1, '-527.690')] -[2023-11-28 05:49:03,815][87426] Updated weights for policy 1, policy_version 213780 (0.0012) -[2023-11-28 05:49:04,190][87426] Updated weights for policy 1, policy_version 213790 (0.0012) -[2023-11-28 05:49:04,248][87424] Updated weights for policy 0, policy_version 214177 (0.0012) -[2023-11-28 05:49:04,630][87424] Updated weights for policy 0, policy_version 214187 (0.0012) -[2023-11-28 05:49:05,002][87424] Updated weights for policy 0, policy_version 214197 (0.0009) -[2023-11-28 05:49:05,392][87424] Updated weights for policy 0, policy_version 214207 (0.0012) -[2023-11-28 05:49:06,657][87426] Updated weights for policy 1, policy_version 213800 (0.0010) -[2023-11-28 05:49:07,038][87426] Updated weights for policy 1, policy_version 213810 (0.0008) -[2023-11-28 05:49:07,420][87426] Updated weights for policy 1, policy_version 213820 (0.0007) -[2023-11-28 05:49:07,686][87424] Updated weights for policy 0, policy_version 214217 (0.0012) -[2023-11-28 05:49:08,070][87424] Updated weights for policy 0, policy_version 214227 (0.0012) -[2023-11-28 05:49:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 109576192. Throughput: 0: 2670.6, 1: 2722.1. Samples: 109596732. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 05:49:08,445][86177] Avg episode reward: [(0, '-517.420'), (1, '-538.430')] -[2023-11-28 05:49:08,456][87424] Updated weights for policy 0, policy_version 214237 (0.0007) -[2023-11-28 05:49:09,237][87426] Updated weights for policy 1, policy_version 213830 (0.0008) -[2023-11-28 05:49:09,621][87426] Updated weights for policy 1, policy_version 213840 (0.0007) -[2023-11-28 05:49:09,999][87426] Updated weights for policy 1, policy_version 213850 (0.0011) -[2023-11-28 05:49:10,536][87424] Updated weights for policy 0, policy_version 214247 (0.0011) -[2023-11-28 05:49:10,921][87424] Updated weights for policy 0, policy_version 214257 (0.0012) -[2023-11-28 05:49:11,311][87424] Updated weights for policy 0, policy_version 214267 (0.0012) -[2023-11-28 05:49:11,837][87426] Updated weights for policy 1, policy_version 213860 (0.0011) -[2023-11-28 05:49:12,220][87426] Updated weights for policy 1, policy_version 213870 (0.0009) -[2023-11-28 05:49:12,600][87426] Updated weights for policy 1, policy_version 213880 (0.0012) -[2023-11-28 05:49:13,096][87424] Updated weights for policy 0, policy_version 214277 (0.0011) -[2023-11-28 05:49:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 109608960. Throughput: 0: 2671.6, 1: 2733.5. Samples: 109621392. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:13,445][86177] Avg episode reward: [(0, '-513.080'), (1, '-540.360')] -[2023-11-28 05:49:13,471][87424] Updated weights for policy 0, policy_version 214287 (0.0011) -[2023-11-28 05:49:13,852][87424] Updated weights for policy 0, policy_version 214297 (0.0011) -[2023-11-28 05:49:14,628][87426] Updated weights for policy 1, policy_version 213890 (0.0012) -[2023-11-28 05:49:15,006][87426] Updated weights for policy 1, policy_version 213900 (0.0012) -[2023-11-28 05:49:15,384][87426] Updated weights for policy 1, policy_version 213910 (0.0012) -[2023-11-28 05:49:15,765][87426] Updated weights for policy 1, policy_version 213920 (0.0012) -[2023-11-28 05:49:16,529][87424] Updated weights for policy 0, policy_version 214307 (0.0012) -[2023-11-28 05:49:16,922][87424] Updated weights for policy 0, policy_version 214317 (0.0011) -[2023-11-28 05:49:17,307][87424] Updated weights for policy 0, policy_version 214327 (0.0012) -[2023-11-28 05:49:18,079][87426] Updated weights for policy 1, policy_version 213930 (0.0011) -[2023-11-28 05:49:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109633536. Throughput: 0: 2681.9, 1: 2747.3. Samples: 109646560. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:18,445][86177] Avg episode reward: [(0, '-500.530'), (1, '-526.730')] -[2023-11-28 05:49:18,457][87426] Updated weights for policy 1, policy_version 213940 (0.0011) -[2023-11-28 05:49:18,841][87426] Updated weights for policy 1, policy_version 213950 (0.0007) -[2023-11-28 05:49:19,174][87424] Updated weights for policy 0, policy_version 214337 (0.0011) -[2023-11-28 05:49:19,565][87424] Updated weights for policy 0, policy_version 214347 (0.0008) -[2023-11-28 05:49:19,944][87424] Updated weights for policy 0, policy_version 214357 (0.0009) -[2023-11-28 05:49:20,330][87424] Updated weights for policy 0, policy_version 214367 (0.0009) -[2023-11-28 05:49:21,361][87426] Updated weights for policy 1, policy_version 213960 (0.0011) -[2023-11-28 05:49:21,762][87426] Updated weights for policy 1, policy_version 213970 (0.0010) -[2023-11-28 05:49:22,132][87426] Updated weights for policy 1, policy_version 213980 (0.0011) -[2023-11-28 05:49:22,186][87424] Updated weights for policy 0, policy_version 214377 (0.0010) -[2023-11-28 05:49:22,557][87424] Updated weights for policy 0, policy_version 214387 (0.0009) -[2023-11-28 05:49:22,940][87424] Updated weights for policy 0, policy_version 214397 (0.0008) -[2023-11-28 05:49:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 109666304. Throughput: 0: 2708.2, 1: 2715.5. Samples: 109678412. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:23,445][86177] Avg episode reward: [(0, '-500.000'), (1, '-524.180')] -[2023-11-28 05:49:24,439][87426] Updated weights for policy 1, policy_version 213990 (0.0011) -[2023-11-28 05:49:24,819][87426] Updated weights for policy 1, policy_version 214000 (0.0012) -[2023-11-28 05:49:25,179][87424] Updated weights for policy 0, policy_version 214407 (0.0009) -[2023-11-28 05:49:25,208][87426] Updated weights for policy 1, policy_version 214010 (0.0012) -[2023-11-28 05:49:25,559][87424] Updated weights for policy 0, policy_version 214417 (0.0008) -[2023-11-28 05:49:25,950][87424] Updated weights for policy 0, policy_version 214427 (0.0010) -[2023-11-28 05:49:27,458][87426] Updated weights for policy 1, policy_version 214020 (0.0012) -[2023-11-28 05:49:27,796][87424] Updated weights for policy 0, policy_version 214437 (0.0012) -[2023-11-28 05:49:27,836][87426] Updated weights for policy 1, policy_version 214030 (0.0012) -[2023-11-28 05:49:28,179][87424] Updated weights for policy 0, policy_version 214447 (0.0011) -[2023-11-28 05:49:28,211][87426] Updated weights for policy 1, policy_version 214040 (0.0012) -[2023-11-28 05:49:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 109682688. Throughput: 0: 2707.6, 1: 2739.4. Samples: 109704428. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:28,445][86177] Avg episode reward: [(0, '-500.540'), (1, '-518.360')] -[2023-11-28 05:49:28,564][87424] Updated weights for policy 0, policy_version 214457 (0.0008) -[2023-11-28 05:49:29,978][87426] Updated weights for policy 1, policy_version 214050 (0.0011) -[2023-11-28 05:49:30,364][87426] Updated weights for policy 1, policy_version 214060 (0.0011) -[2023-11-28 05:49:30,747][87426] Updated weights for policy 1, policy_version 214070 (0.0008) -[2023-11-28 05:49:30,919][87424] Updated weights for policy 0, policy_version 214467 (0.0009) -[2023-11-28 05:49:31,121][87426] Updated weights for policy 1, policy_version 214080 (0.0008) -[2023-11-28 05:49:31,294][87424] Updated weights for policy 0, policy_version 214477 (0.0012) -[2023-11-28 05:49:31,684][87424] Updated weights for policy 0, policy_version 214487 (0.0011) -[2023-11-28 05:49:33,249][87426] Updated weights for policy 1, policy_version 214090 (0.0011) -[2023-11-28 05:49:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109715456. Throughput: 0: 2735.4, 1: 2730.6. Samples: 109728748. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:33,446][86177] Avg episode reward: [(0, '-501.630'), (1, '-519.960')] -[2023-11-28 05:49:33,628][87426] Updated weights for policy 1, policy_version 214100 (0.0010) -[2023-11-28 05:49:33,895][87424] Updated weights for policy 0, policy_version 214497 (0.0009) -[2023-11-28 05:49:34,014][87426] Updated weights for policy 1, policy_version 214110 (0.0010) -[2023-11-28 05:49:34,276][87424] Updated weights for policy 0, policy_version 214507 (0.0008) -[2023-11-28 05:49:34,666][87424] Updated weights for policy 0, policy_version 214517 (0.0008) -[2023-11-28 05:49:35,037][87424] Updated weights for policy 0, policy_version 214527 (0.0011) -[2023-11-28 05:49:36,557][87426] Updated weights for policy 1, policy_version 214120 (0.0008) -[2023-11-28 05:49:36,933][87426] Updated weights for policy 1, policy_version 214130 (0.0011) -[2023-11-28 05:49:37,224][87424] Updated weights for policy 0, policy_version 214537 (0.0012) -[2023-11-28 05:49:37,311][87426] Updated weights for policy 1, policy_version 214140 (0.0011) -[2023-11-28 05:49:37,602][87424] Updated weights for policy 0, policy_version 214547 (0.0009) -[2023-11-28 05:49:37,989][87424] Updated weights for policy 0, policy_version 214557 (0.0008) -[2023-11-28 05:49:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 109748224. Throughput: 0: 2768.8, 1: 2703.0. Samples: 109760936. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:38,446][86177] Avg episode reward: [(0, '-495.660'), (1, '-529.300')] -[2023-11-28 05:49:39,875][87426] Updated weights for policy 1, policy_version 214150 (0.0011) -[2023-11-28 05:49:40,254][87426] Updated weights for policy 1, policy_version 214160 (0.0012) -[2023-11-28 05:49:40,257][87424] Updated weights for policy 0, policy_version 214567 (0.0010) -[2023-11-28 05:49:40,630][87426] Updated weights for policy 1, policy_version 214170 (0.0011) -[2023-11-28 05:49:40,639][87424] Updated weights for policy 0, policy_version 214577 (0.0009) -[2023-11-28 05:49:41,019][87424] Updated weights for policy 0, policy_version 214587 (0.0010) -[2023-11-28 05:49:42,790][87426] Updated weights for policy 1, policy_version 214180 (0.0009) -[2023-11-28 05:49:42,932][87424] Updated weights for policy 0, policy_version 214597 (0.0011) -[2023-11-28 05:49:43,166][87426] Updated weights for policy 1, policy_version 214190 (0.0012) -[2023-11-28 05:49:43,313][87424] Updated weights for policy 0, policy_version 214607 (0.0012) -[2023-11-28 05:49:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 109764608. Throughput: 0: 2758.8, 1: 2698.0. Samples: 109785680. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:43,445][86177] Avg episode reward: [(0, '-495.460'), (1, '-527.220')] -[2023-11-28 05:49:43,541][87426] Updated weights for policy 1, policy_version 214200 (0.0010) -[2023-11-28 05:49:43,701][87424] Updated weights for policy 0, policy_version 214617 (0.0012) -[2023-11-28 05:49:45,672][87424] Updated weights for policy 0, policy_version 214627 (0.0011) -[2023-11-28 05:49:45,989][87426] Updated weights for policy 1, policy_version 214210 (0.0007) -[2023-11-28 05:49:46,055][87424] Updated weights for policy 0, policy_version 214637 (0.0011) -[2023-11-28 05:49:46,368][87426] Updated weights for policy 1, policy_version 214220 (0.0009) -[2023-11-28 05:49:46,444][87424] Updated weights for policy 0, policy_version 214647 (0.0011) -[2023-11-28 05:49:46,756][87426] Updated weights for policy 1, policy_version 214230 (0.0008) -[2023-11-28 05:49:47,145][87426] Updated weights for policy 1, policy_version 214240 (0.0008) -[2023-11-28 05:49:48,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109797376. Throughput: 0: 2756.7, 1: 2673.8. Samples: 109809296. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:48,446][86177] Avg episode reward: [(0, '-516.850'), (1, '-533.330')] -[2023-11-28 05:49:48,598][87424] Updated weights for policy 0, policy_version 214657 (0.0011) -[2023-11-28 05:49:48,985][87424] Updated weights for policy 0, policy_version 214667 (0.0012) -[2023-11-28 05:49:49,367][87424] Updated weights for policy 0, policy_version 214677 (0.0011) -[2023-11-28 05:49:49,659][87426] Updated weights for policy 1, policy_version 214250 (0.0010) -[2023-11-28 05:49:49,758][87424] Updated weights for policy 0, policy_version 214687 (0.0012) -[2023-11-28 05:49:50,035][87426] Updated weights for policy 1, policy_version 214260 (0.0008) -[2023-11-28 05:49:50,422][87426] Updated weights for policy 1, policy_version 214270 (0.0008) -[2023-11-28 05:49:51,813][87424] Updated weights for policy 0, policy_version 214697 (0.0010) -[2023-11-28 05:49:52,195][87424] Updated weights for policy 0, policy_version 214707 (0.0011) -[2023-11-28 05:49:52,426][87426] Updated weights for policy 1, policy_version 214280 (0.0010) -[2023-11-28 05:49:52,584][87424] Updated weights for policy 0, policy_version 214717 (0.0012) -[2023-11-28 05:49:52,814][87426] Updated weights for policy 1, policy_version 214290 (0.0010) -[2023-11-28 05:49:53,198][87426] Updated weights for policy 1, policy_version 214300 (0.0019) -[2023-11-28 05:49:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 109830144. Throughput: 0: 2747.5, 1: 2676.2. Samples: 109840796. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:53,445][86177] Avg episode reward: [(0, '-521.890'), (1, '-531.950')] -[2023-11-28 05:49:54,924][87424] Updated weights for policy 0, policy_version 214727 (0.0012) -[2023-11-28 05:49:55,285][87426] Updated weights for policy 1, policy_version 214310 (0.0009) -[2023-11-28 05:49:55,306][87424] Updated weights for policy 0, policy_version 214737 (0.0012) -[2023-11-28 05:49:55,664][87426] Updated weights for policy 1, policy_version 214320 (0.0008) -[2023-11-28 05:49:55,694][87424] Updated weights for policy 0, policy_version 214747 (0.0011) -[2023-11-28 05:49:56,043][87426] Updated weights for policy 1, policy_version 214330 (0.0007) -[2023-11-28 05:49:57,314][87424] Updated weights for policy 0, policy_version 214757 (0.0011) -[2023-11-28 05:49:57,703][87424] Updated weights for policy 0, policy_version 214767 (0.0012) -[2023-11-28 05:49:58,090][87424] Updated weights for policy 0, policy_version 214777 (0.0009) -[2023-11-28 05:49:58,424][87426] Updated weights for policy 1, policy_version 214340 (0.0009) -[2023-11-28 05:49:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109854720. Throughput: 0: 2769.0, 1: 2661.4. Samples: 109865760. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:49:58,446][86177] Avg episode reward: [(0, '-529.430'), (1, '-527.150')] -[2023-11-28 05:49:58,804][87426] Updated weights for policy 1, policy_version 214350 (0.0012) -[2023-11-28 05:49:59,182][87426] Updated weights for policy 1, policy_version 214360 (0.0012) -[2023-11-28 05:50:00,173][87424] Updated weights for policy 0, policy_version 214787 (0.0007) -[2023-11-28 05:50:00,554][87424] Updated weights for policy 0, policy_version 214797 (0.0011) -[2023-11-28 05:50:00,931][87424] Updated weights for policy 0, policy_version 214807 (0.0012) -[2023-11-28 05:50:01,474][87426] Updated weights for policy 1, policy_version 214370 (0.0012) -[2023-11-28 05:50:01,850][87426] Updated weights for policy 1, policy_version 214380 (0.0012) -[2023-11-28 05:50:02,225][87426] Updated weights for policy 1, policy_version 214390 (0.0012) -[2023-11-28 05:50:02,605][87426] Updated weights for policy 1, policy_version 214400 (0.0011) -[2023-11-28 05:50:03,027][87424] Updated weights for policy 0, policy_version 214817 (0.0012) -[2023-11-28 05:50:03,406][87424] Updated weights for policy 0, policy_version 214827 (0.0011) -[2023-11-28 05:50:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 109879296. Throughput: 0: 2794.0, 1: 2650.6. Samples: 109891564. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:50:03,445][86177] Avg episode reward: [(0, '-531.400'), (1, '-534.050')] -[2023-11-28 05:50:03,786][87424] Updated weights for policy 0, policy_version 214837 (0.0009) -[2023-11-28 05:50:04,175][87424] Updated weights for policy 0, policy_version 214847 (0.0007) -[2023-11-28 05:50:05,194][87426] Updated weights for policy 1, policy_version 214410 (0.0011) -[2023-11-28 05:50:05,579][87426] Updated weights for policy 1, policy_version 214420 (0.0008) -[2023-11-28 05:50:05,952][87424] Updated weights for policy 0, policy_version 214857 (0.0008) -[2023-11-28 05:50:05,953][87426] Updated weights for policy 1, policy_version 214430 (0.0010) -[2023-11-28 05:50:06,335][87424] Updated weights for policy 0, policy_version 214867 (0.0008) -[2023-11-28 05:50:06,711][87424] Updated weights for policy 0, policy_version 214877 (0.0008) -[2023-11-28 05:50:08,034][87426] Updated weights for policy 1, policy_version 214440 (0.0008) -[2023-11-28 05:50:08,413][87426] Updated weights for policy 1, policy_version 214450 (0.0007) -[2023-11-28 05:50:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109903872. Throughput: 0: 2803.7, 1: 2670.1. Samples: 109924736. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:50:08,445][86177] Avg episode reward: [(0, '-508.950'), (1, '-538.030')] -[2023-11-28 05:50:08,677][87424] Updated weights for policy 0, policy_version 214887 (0.0011) -[2023-11-28 05:50:08,792][87426] Updated weights for policy 1, policy_version 214460 (0.0011) -[2023-11-28 05:50:09,052][87424] Updated weights for policy 0, policy_version 214897 (0.0011) -[2023-11-28 05:50:09,442][87424] Updated weights for policy 0, policy_version 214907 (0.0011) -[2023-11-28 05:50:11,228][87426] Updated weights for policy 1, policy_version 214470 (0.0011) -[2023-11-28 05:50:11,608][87426] Updated weights for policy 1, policy_version 214480 (0.0012) -[2023-11-28 05:50:11,913][87424] Updated weights for policy 0, policy_version 214917 (0.0010) -[2023-11-28 05:50:11,991][87426] Updated weights for policy 1, policy_version 214490 (0.0011) -[2023-11-28 05:50:12,298][87424] Updated weights for policy 0, policy_version 214927 (0.0011) -[2023-11-28 05:50:12,678][87424] Updated weights for policy 0, policy_version 214937 (0.0010) -[2023-11-28 05:50:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109936640. Throughput: 0: 2800.0, 1: 2625.1. Samples: 109948556. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:50:13,445][86177] Avg episode reward: [(0, '-535.910'), (1, '-554.540')] -[2023-11-28 05:50:14,478][87426] Updated weights for policy 1, policy_version 214500 (0.0012) -[2023-11-28 05:50:14,534][87424] Updated weights for policy 0, policy_version 214947 (0.0009) -[2023-11-28 05:50:14,852][87426] Updated weights for policy 1, policy_version 214510 (0.0011) -[2023-11-28 05:50:14,918][87424] Updated weights for policy 0, policy_version 214957 (0.0011) -[2023-11-28 05:50:15,235][87426] Updated weights for policy 1, policy_version 214520 (0.0011) -[2023-11-28 05:50:15,300][87424] Updated weights for policy 0, policy_version 214967 (0.0010) -[2023-11-28 05:50:17,051][87426] Updated weights for policy 1, policy_version 214530 (0.0011) -[2023-11-28 05:50:17,431][87426] Updated weights for policy 1, policy_version 214540 (0.0009) -[2023-11-28 05:50:17,600][87424] Updated weights for policy 0, policy_version 214977 (0.0008) -[2023-11-28 05:50:17,811][87426] Updated weights for policy 1, policy_version 214550 (0.0008) -[2023-11-28 05:50:17,990][87424] Updated weights for policy 0, policy_version 214987 (0.0012) -[2023-11-28 05:50:18,194][87426] Updated weights for policy 1, policy_version 214560 (0.0011) -[2023-11-28 05:50:18,365][87424] Updated weights for policy 0, policy_version 214997 (0.0011) -[2023-11-28 05:50:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 109961216. Throughput: 0: 2826.5, 1: 2622.0. Samples: 109973928. Policy #0 lag: (min: 15.0, avg: 29.0, max: 47.0) -[2023-11-28 05:50:18,445][86177] Avg episode reward: [(0, '-530.530'), (1, '-543.710')] -[2023-11-28 05:50:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000214560_54927360.pth... -[2023-11-28 05:50:18,500][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000212032_54280192.pth -[2023-11-28 05:50:18,749][87424] Updated weights for policy 0, policy_version 215007 (0.0008) -[2023-11-28 05:50:18,786][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000215008_55042048.pth... -[2023-11-28 05:50:18,834][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000212416_54378496.pth -[2023-11-28 05:50:20,045][87426] Updated weights for policy 1, policy_version 214570 (0.0012) -[2023-11-28 05:50:20,422][87426] Updated weights for policy 1, policy_version 214580 (0.0013) -[2023-11-28 05:50:20,561][87424] Updated weights for policy 0, policy_version 215017 (0.0009) -[2023-11-28 05:50:20,791][87426] Updated weights for policy 1, policy_version 214590 (0.0011) -[2023-11-28 05:50:20,955][87424] Updated weights for policy 0, policy_version 215027 (0.0009) -[2023-11-28 05:50:21,328][87424] Updated weights for policy 0, policy_version 215037 (0.0010) -[2023-11-28 05:50:23,094][87426] Updated weights for policy 1, policy_version 214600 (0.0012) -[2023-11-28 05:50:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 109985792. Throughput: 0: 2800.2, 1: 2668.9. Samples: 110007044. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:50:23,445][86177] Avg episode reward: [(0, '-528.900'), (1, '-533.540')] -[2023-11-28 05:50:23,481][87426] Updated weights for policy 1, policy_version 214610 (0.0011) -[2023-11-28 05:50:23,782][87424] Updated weights for policy 0, policy_version 215047 (0.0012) -[2023-11-28 05:50:23,857][87426] Updated weights for policy 1, policy_version 214620 (0.0008) -[2023-11-28 05:50:24,160][87424] Updated weights for policy 0, policy_version 215057 (0.0011) -[2023-11-28 05:50:24,543][87424] Updated weights for policy 0, policy_version 215067 (0.0008) -[2023-11-28 05:50:25,878][87426] Updated weights for policy 1, policy_version 214630 (0.0010) -[2023-11-28 05:50:26,255][87426] Updated weights for policy 1, policy_version 214640 (0.0009) -[2023-11-28 05:50:26,643][87426] Updated weights for policy 1, policy_version 214650 (0.0010) -[2023-11-28 05:50:26,941][87424] Updated weights for policy 0, policy_version 215077 (0.0008) -[2023-11-28 05:50:27,306][87424] Updated weights for policy 0, policy_version 215087 (0.0007) -[2023-11-28 05:50:27,691][87424] Updated weights for policy 0, policy_version 215097 (0.0007) -[2023-11-28 05:50:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 110018560. Throughput: 0: 2793.5, 1: 2674.1. Samples: 110031724. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:50:28,445][86177] Avg episode reward: [(0, '-528.880'), (1, '-524.020')] -[2023-11-28 05:50:28,504][87426] Updated weights for policy 1, policy_version 214660 (0.0011) -[2023-11-28 05:50:28,905][87426] Updated weights for policy 1, policy_version 214670 (0.0011) -[2023-11-28 05:50:29,271][87426] Updated weights for policy 1, policy_version 214680 (0.0011) -[2023-11-28 05:50:29,833][87424] Updated weights for policy 0, policy_version 215107 (0.0008) -[2023-11-28 05:50:30,218][87424] Updated weights for policy 0, policy_version 215117 (0.0008) -[2023-11-28 05:50:30,614][87424] Updated weights for policy 0, policy_version 215127 (0.0008) -[2023-11-28 05:50:31,497][87426] Updated weights for policy 1, policy_version 214690 (0.0009) -[2023-11-28 05:50:31,887][87426] Updated weights for policy 1, policy_version 214700 (0.0011) -[2023-11-28 05:50:32,267][87426] Updated weights for policy 1, policy_version 214710 (0.0011) -[2023-11-28 05:50:32,422][87424] Updated weights for policy 0, policy_version 215137 (0.0008) -[2023-11-28 05:50:32,635][87426] Updated weights for policy 1, policy_version 214720 (0.0011) -[2023-11-28 05:50:32,802][87424] Updated weights for policy 0, policy_version 215147 (0.0011) -[2023-11-28 05:50:33,188][87424] Updated weights for policy 0, policy_version 215157 (0.0011) -[2023-11-28 05:50:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 110043136. Throughput: 0: 2787.1, 1: 2694.8. Samples: 110055980. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:50:33,445][86177] Avg episode reward: [(0, '-499.450'), (1, '-514.530')] -[2023-11-28 05:50:33,580][87424] Updated weights for policy 0, policy_version 215167 (0.0007) -[2023-11-28 05:50:34,628][87426] Updated weights for policy 1, policy_version 214730 (0.0011) -[2023-11-28 05:50:35,007][87426] Updated weights for policy 1, policy_version 214740 (0.0012) -[2023-11-28 05:50:35,385][87426] Updated weights for policy 1, policy_version 214750 (0.0010) -[2023-11-28 05:50:35,921][87424] Updated weights for policy 0, policy_version 215177 (0.0011) -[2023-11-28 05:50:36,300][87424] Updated weights for policy 0, policy_version 215187 (0.0012) -[2023-11-28 05:50:36,670][87424] Updated weights for policy 0, policy_version 215197 (0.0012) -[2023-11-28 05:50:37,423][87426] Updated weights for policy 1, policy_version 214760 (0.0011) -[2023-11-28 05:50:37,804][87426] Updated weights for policy 1, policy_version 214770 (0.0012) -[2023-11-28 05:50:38,195][87426] Updated weights for policy 1, policy_version 214780 (0.0008) -[2023-11-28 05:50:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 110075904. Throughput: 0: 2779.8, 1: 2741.3. Samples: 110089248. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:50:38,445][86177] Avg episode reward: [(0, '-498.110'), (1, '-511.960')] -[2023-11-28 05:50:39,058][87424] Updated weights for policy 0, policy_version 215207 (0.0010) -[2023-11-28 05:50:39,438][87424] Updated weights for policy 0, policy_version 215217 (0.0008) -[2023-11-28 05:50:39,820][87424] Updated weights for policy 0, policy_version 215227 (0.0009) -[2023-11-28 05:50:40,002][87426] Updated weights for policy 1, policy_version 214790 (0.0011) -[2023-11-28 05:50:40,380][87426] Updated weights for policy 1, policy_version 214800 (0.0011) -[2023-11-28 05:50:40,754][87426] Updated weights for policy 1, policy_version 214810 (0.0011) -[2023-11-28 05:50:41,587][87424] Updated weights for policy 0, policy_version 215237 (0.0011) -[2023-11-28 05:50:41,968][87424] Updated weights for policy 0, policy_version 215247 (0.0012) -[2023-11-28 05:50:42,357][87424] Updated weights for policy 0, policy_version 215257 (0.0012) -[2023-11-28 05:50:43,086][87426] Updated weights for policy 1, policy_version 214820 (0.0009) -[2023-11-28 05:50:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 110100480. Throughput: 0: 2761.5, 1: 2758.5. Samples: 110114160. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:50:43,445][86177] Avg episode reward: [(0, '-500.860'), (1, '-505.020')] -[2023-11-28 05:50:43,470][87426] Updated weights for policy 1, policy_version 214830 (0.0010) -[2023-11-28 05:50:43,853][87426] Updated weights for policy 1, policy_version 214840 (0.0012) -[2023-11-28 05:50:44,928][87424] Updated weights for policy 0, policy_version 215267 (0.0012) -[2023-11-28 05:50:45,304][87424] Updated weights for policy 0, policy_version 215277 (0.0012) -[2023-11-28 05:50:45,688][87424] Updated weights for policy 0, policy_version 215287 (0.0008) -[2023-11-28 05:50:46,147][87426] Updated weights for policy 1, policy_version 214850 (0.0011) -[2023-11-28 05:50:46,526][87426] Updated weights for policy 1, policy_version 214860 (0.0011) -[2023-11-28 05:50:46,900][87426] Updated weights for policy 1, policy_version 214870 (0.0011) -[2023-11-28 05:50:47,277][87426] Updated weights for policy 1, policy_version 214880 (0.0011) -[2023-11-28 05:50:48,206][87424] Updated weights for policy 0, policy_version 215297 (0.0009) -[2023-11-28 05:50:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 110125056. Throughput: 0: 2711.3, 1: 2754.2. Samples: 110137512. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:50:48,445][86177] Avg episode reward: [(0, '-499.380'), (1, '-508.020')] -[2023-11-28 05:50:48,592][87424] Updated weights for policy 0, policy_version 215307 (0.0012) -[2023-11-28 05:50:48,959][87424] Updated weights for policy 0, policy_version 215317 (0.0012) -[2023-11-28 05:50:49,340][87424] Updated weights for policy 0, policy_version 215327 (0.0011) -[2023-11-28 05:50:49,456][87426] Updated weights for policy 1, policy_version 214890 (0.0010) -[2023-11-28 05:50:49,830][87426] Updated weights for policy 1, policy_version 214900 (0.0012) -[2023-11-28 05:50:50,204][87426] Updated weights for policy 1, policy_version 214910 (0.0012) -[2023-11-28 05:50:51,642][87424] Updated weights for policy 0, policy_version 215337 (0.0012) -[2023-11-28 05:50:52,018][87424] Updated weights for policy 0, policy_version 215347 (0.0012) -[2023-11-28 05:50:52,406][87424] Updated weights for policy 0, policy_version 215357 (0.0008) -[2023-11-28 05:50:52,539][87426] Updated weights for policy 1, policy_version 214920 (0.0009) -[2023-11-28 05:50:52,919][87426] Updated weights for policy 1, policy_version 214930 (0.0009) -[2023-11-28 05:50:53,303][87426] Updated weights for policy 1, policy_version 214940 (0.0012) -[2023-11-28 05:50:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 110149632. Throughput: 0: 2684.3, 1: 2753.7. Samples: 110169444. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:50:53,445][86177] Avg episode reward: [(0, '-500.000'), (1, '-505.000')] -[2023-11-28 05:50:54,929][87424] Updated weights for policy 0, policy_version 215367 (0.0007) -[2023-11-28 05:50:55,308][87424] Updated weights for policy 0, policy_version 215377 (0.0008) -[2023-11-28 05:50:55,679][87426] Updated weights for policy 1, policy_version 214950 (0.0008) -[2023-11-28 05:50:55,687][87424] Updated weights for policy 0, policy_version 215387 (0.0012) -[2023-11-28 05:50:56,052][87426] Updated weights for policy 1, policy_version 214960 (0.0008) -[2023-11-28 05:50:56,442][87426] Updated weights for policy 1, policy_version 214970 (0.0007) -[2023-11-28 05:50:57,851][87424] Updated weights for policy 0, policy_version 215397 (0.0011) -[2023-11-28 05:50:58,230][87424] Updated weights for policy 0, policy_version 215407 (0.0012) -[2023-11-28 05:50:58,299][87426] Updated weights for policy 1, policy_version 214980 (0.0007) -[2023-11-28 05:50:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 110174208. Throughput: 0: 2657.3, 1: 2762.1. Samples: 110192432. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:50:58,445][86177] Avg episode reward: [(0, '-499.340'), (1, '-507.620')] -[2023-11-28 05:50:58,622][87424] Updated weights for policy 0, policy_version 215417 (0.0010) -[2023-11-28 05:50:58,672][87426] Updated weights for policy 1, policy_version 214990 (0.0007) -[2023-11-28 05:50:59,053][87426] Updated weights for policy 1, policy_version 215000 (0.0010) -[2023-11-28 05:51:00,780][87424] Updated weights for policy 0, policy_version 215427 (0.0009) -[2023-11-28 05:51:01,118][87426] Updated weights for policy 1, policy_version 215010 (0.0010) -[2023-11-28 05:51:01,167][87424] Updated weights for policy 0, policy_version 215437 (0.0009) -[2023-11-28 05:51:01,494][87426] Updated weights for policy 1, policy_version 215020 (0.0008) -[2023-11-28 05:51:01,539][87424] Updated weights for policy 0, policy_version 215447 (0.0008) -[2023-11-28 05:51:01,873][87426] Updated weights for policy 1, policy_version 215030 (0.0012) -[2023-11-28 05:51:02,254][87426] Updated weights for policy 1, policy_version 215040 (0.0010) -[2023-11-28 05:51:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 110206976. Throughput: 0: 2609.9, 1: 2766.2. Samples: 110215852. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:51:03,445][86177] Avg episode reward: [(0, '-493.240'), (1, '-506.980')] -[2023-11-28 05:51:04,100][87426] Updated weights for policy 1, policy_version 215050 (0.0011) -[2023-11-28 05:51:04,101][87424] Updated weights for policy 0, policy_version 215457 (0.0015) -[2023-11-28 05:51:04,479][87426] Updated weights for policy 1, policy_version 215060 (0.0011) -[2023-11-28 05:51:04,484][87424] Updated weights for policy 0, policy_version 215467 (0.0009) -[2023-11-28 05:51:04,852][87426] Updated weights for policy 1, policy_version 215070 (0.0011) -[2023-11-28 05:51:04,859][87424] Updated weights for policy 0, policy_version 215477 (0.0012) -[2023-11-28 05:51:05,257][87424] Updated weights for policy 0, policy_version 215487 (0.0012) -[2023-11-28 05:51:07,171][87426] Updated weights for policy 1, policy_version 215080 (0.0011) -[2023-11-28 05:51:07,552][87426] Updated weights for policy 1, policy_version 215090 (0.0011) -[2023-11-28 05:51:07,651][87424] Updated weights for policy 0, policy_version 215497 (0.0009) -[2023-11-28 05:51:07,924][87426] Updated weights for policy 1, policy_version 215100 (0.0012) -[2023-11-28 05:51:08,046][87424] Updated weights for policy 0, policy_version 215507 (0.0008) -[2023-11-28 05:51:08,418][87424] Updated weights for policy 0, policy_version 215517 (0.0012) -[2023-11-28 05:51:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110231552. Throughput: 0: 2613.7, 1: 2773.3. Samples: 110249460. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:51:08,445][86177] Avg episode reward: [(0, '-491.610'), (1, '-509.690')] -[2023-11-28 05:51:10,009][87426] Updated weights for policy 1, policy_version 215110 (0.0010) -[2023-11-28 05:51:10,387][87426] Updated weights for policy 1, policy_version 215120 (0.0011) -[2023-11-28 05:51:10,538][87424] Updated weights for policy 0, policy_version 215527 (0.0012) -[2023-11-28 05:51:10,776][87426] Updated weights for policy 1, policy_version 215130 (0.0009) -[2023-11-28 05:51:10,923][87424] Updated weights for policy 0, policy_version 215537 (0.0012) -[2023-11-28 05:51:11,301][87424] Updated weights for policy 0, policy_version 215547 (0.0012) -[2023-11-28 05:51:13,007][87426] Updated weights for policy 1, policy_version 215140 (0.0011) -[2023-11-28 05:51:13,380][87426] Updated weights for policy 1, policy_version 215150 (0.0012) -[2023-11-28 05:51:13,407][87424] Updated weights for policy 0, policy_version 215557 (0.0010) -[2023-11-28 05:51:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 110256128. Throughput: 0: 2621.0, 1: 2751.5. Samples: 110273484. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:51:13,445][86177] Avg episode reward: [(0, '-491.250'), (1, '-508.690')] -[2023-11-28 05:51:13,764][87426] Updated weights for policy 1, policy_version 215160 (0.0012) -[2023-11-28 05:51:13,788][87424] Updated weights for policy 0, policy_version 215567 (0.0010) -[2023-11-28 05:51:14,162][87424] Updated weights for policy 0, policy_version 215577 (0.0012) -[2023-11-28 05:51:15,566][87426] Updated weights for policy 1, policy_version 215170 (0.0012) -[2023-11-28 05:51:15,945][87426] Updated weights for policy 1, policy_version 215180 (0.0008) -[2023-11-28 05:51:16,328][87426] Updated weights for policy 1, policy_version 215190 (0.0007) -[2023-11-28 05:51:16,657][87424] Updated weights for policy 0, policy_version 215587 (0.0008) -[2023-11-28 05:51:16,702][87426] Updated weights for policy 1, policy_version 215200 (0.0008) -[2023-11-28 05:51:17,036][87424] Updated weights for policy 0, policy_version 215597 (0.0007) -[2023-11-28 05:51:17,411][87424] Updated weights for policy 0, policy_version 215607 (0.0007) -[2023-11-28 05:51:18,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110288896. Throughput: 0: 2626.3, 1: 2750.3. Samples: 110297928. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:51:18,446][86177] Avg episode reward: [(0, '-494.230'), (1, '-511.920')] -[2023-11-28 05:51:19,083][87426] Updated weights for policy 1, policy_version 215210 (0.0009) -[2023-11-28 05:51:19,470][87426] Updated weights for policy 1, policy_version 215220 (0.0011) -[2023-11-28 05:51:19,729][87424] Updated weights for policy 0, policy_version 215617 (0.0008) -[2023-11-28 05:51:19,843][87426] Updated weights for policy 1, policy_version 215230 (0.0010) -[2023-11-28 05:51:20,118][87424] Updated weights for policy 0, policy_version 215627 (0.0011) -[2023-11-28 05:51:20,500][87424] Updated weights for policy 0, policy_version 215637 (0.0012) -[2023-11-28 05:51:20,870][87424] Updated weights for policy 0, policy_version 215647 (0.0012) -[2023-11-28 05:51:22,407][87426] Updated weights for policy 1, policy_version 215240 (0.0011) -[2023-11-28 05:51:22,778][87426] Updated weights for policy 1, policy_version 215250 (0.0012) -[2023-11-28 05:51:23,155][87426] Updated weights for policy 1, policy_version 215260 (0.0012) -[2023-11-28 05:51:23,428][87424] Updated weights for policy 0, policy_version 215657 (0.0012) -[2023-11-28 05:51:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110313472. Throughput: 0: 2605.3, 1: 2720.3. Samples: 110328900. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:51:23,445][86177] Avg episode reward: [(0, '-496.360'), (1, '-511.220')] -[2023-11-28 05:51:23,810][87424] Updated weights for policy 0, policy_version 215667 (0.0012) -[2023-11-28 05:51:24,198][87424] Updated weights for policy 0, policy_version 215677 (0.0011) -[2023-11-28 05:51:25,079][87426] Updated weights for policy 1, policy_version 215270 (0.0009) -[2023-11-28 05:51:25,456][87426] Updated weights for policy 1, policy_version 215280 (0.0008) -[2023-11-28 05:51:25,838][87426] Updated weights for policy 1, policy_version 215290 (0.0008) -[2023-11-28 05:51:26,092][87424] Updated weights for policy 0, policy_version 215687 (0.0010) -[2023-11-28 05:51:26,475][87424] Updated weights for policy 0, policy_version 215697 (0.0011) -[2023-11-28 05:51:26,865][87424] Updated weights for policy 0, policy_version 215707 (0.0009) -[2023-11-28 05:51:28,153][87426] Updated weights for policy 1, policy_version 215300 (0.0009) -[2023-11-28 05:51:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 110338048. Throughput: 0: 2622.1, 1: 2707.4. Samples: 110353988. Policy #0 lag: (min: 30.0, avg: 49.0, max: 62.0) -[2023-11-28 05:51:28,445][86177] Avg episode reward: [(0, '-494.940'), (1, '-510.410')] -[2023-11-28 05:51:28,463][87424] Updated weights for policy 0, policy_version 215717 (0.0012) -[2023-11-28 05:51:28,534][87426] Updated weights for policy 1, policy_version 215310 (0.0007) -[2023-11-28 05:51:28,839][87424] Updated weights for policy 0, policy_version 215727 (0.0012) -[2023-11-28 05:51:28,902][87426] Updated weights for policy 1, policy_version 215320 (0.0008) -[2023-11-28 05:51:29,228][87424] Updated weights for policy 0, policy_version 215737 (0.0011) -[2023-11-28 05:51:31,011][87426] Updated weights for policy 1, policy_version 215330 (0.0011) -[2023-11-28 05:51:31,202][87424] Updated weights for policy 0, policy_version 215747 (0.0012) -[2023-11-28 05:51:31,394][87426] Updated weights for policy 1, policy_version 215340 (0.0011) -[2023-11-28 05:51:31,573][87424] Updated weights for policy 0, policy_version 215757 (0.0011) -[2023-11-28 05:51:31,762][87426] Updated weights for policy 1, policy_version 215350 (0.0011) -[2023-11-28 05:51:31,951][87424] Updated weights for policy 0, policy_version 215767 (0.0009) -[2023-11-28 05:51:32,141][87426] Updated weights for policy 1, policy_version 215360 (0.0010) -[2023-11-28 05:51:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110370816. Throughput: 0: 2684.8, 1: 2712.8. Samples: 110380404. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:51:33,445][86177] Avg episode reward: [(0, '-496.610'), (1, '-505.740')] -[2023-11-28 05:51:34,121][87426] Updated weights for policy 1, policy_version 215370 (0.0011) -[2023-11-28 05:51:34,414][87424] Updated weights for policy 0, policy_version 215777 (0.0012) -[2023-11-28 05:51:34,504][87426] Updated weights for policy 1, policy_version 215380 (0.0012) -[2023-11-28 05:51:34,795][87424] Updated weights for policy 0, policy_version 215787 (0.0009) -[2023-11-28 05:51:34,875][87426] Updated weights for policy 1, policy_version 215390 (0.0011) -[2023-11-28 05:51:35,175][87424] Updated weights for policy 0, policy_version 215797 (0.0009) -[2023-11-28 05:51:35,556][87424] Updated weights for policy 0, policy_version 215807 (0.0012) -[2023-11-28 05:51:37,297][87424] Updated weights for policy 0, policy_version 215817 (0.0011) -[2023-11-28 05:51:37,358][87426] Updated weights for policy 1, policy_version 215400 (0.0012) -[2023-11-28 05:51:37,673][87424] Updated weights for policy 0, policy_version 215827 (0.0010) -[2023-11-28 05:51:37,735][87426] Updated weights for policy 1, policy_version 215410 (0.0011) -[2023-11-28 05:51:38,052][87424] Updated weights for policy 0, policy_version 215837 (0.0011) -[2023-11-28 05:51:38,122][87426] Updated weights for policy 1, policy_version 215420 (0.0011) -[2023-11-28 05:51:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 110403584. Throughput: 0: 2710.6, 1: 2705.4. Samples: 110413164. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:51:38,445][86177] Avg episode reward: [(0, '-501.940'), (1, '-499.870')] -[2023-11-28 05:51:40,074][87426] Updated weights for policy 1, policy_version 215430 (0.0011) -[2023-11-28 05:51:40,121][87424] Updated weights for policy 0, policy_version 215847 (0.0011) -[2023-11-28 05:51:40,457][87426] Updated weights for policy 1, policy_version 215440 (0.0011) -[2023-11-28 05:51:40,504][87424] Updated weights for policy 0, policy_version 215857 (0.0011) -[2023-11-28 05:51:40,841][87426] Updated weights for policy 1, policy_version 215450 (0.0011) -[2023-11-28 05:51:40,885][87424] Updated weights for policy 0, policy_version 215867 (0.0011) -[2023-11-28 05:51:42,836][87426] Updated weights for policy 1, policy_version 215460 (0.0011) -[2023-11-28 05:51:43,215][87426] Updated weights for policy 1, policy_version 215470 (0.0011) -[2023-11-28 05:51:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 110419968. Throughput: 0: 2712.6, 1: 2730.0. Samples: 110437352. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:51:43,445][86177] Avg episode reward: [(0, '-500.720'), (1, '-512.600')] -[2023-11-28 05:51:43,466][87424] Updated weights for policy 0, policy_version 215877 (0.0010) -[2023-11-28 05:51:43,599][87426] Updated weights for policy 1, policy_version 215480 (0.0011) -[2023-11-28 05:51:43,851][87424] Updated weights for policy 0, policy_version 215887 (0.0008) -[2023-11-28 05:51:44,235][87424] Updated weights for policy 0, policy_version 215897 (0.0009) -[2023-11-28 05:51:46,151][87426] Updated weights for policy 1, policy_version 215490 (0.0011) -[2023-11-28 05:51:46,517][87426] Updated weights for policy 1, policy_version 215500 (0.0010) -[2023-11-28 05:51:46,587][87424] Updated weights for policy 0, policy_version 215907 (0.0012) -[2023-11-28 05:51:46,899][87426] Updated weights for policy 1, policy_version 215510 (0.0007) -[2023-11-28 05:51:46,967][87424] Updated weights for policy 0, policy_version 215917 (0.0012) -[2023-11-28 05:51:47,280][87426] Updated weights for policy 1, policy_version 215520 (0.0008) -[2023-11-28 05:51:47,357][87424] Updated weights for policy 0, policy_version 215927 (0.0012) -[2023-11-28 05:51:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110452736. Throughput: 0: 2741.1, 1: 2739.9. Samples: 110462496. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:51:48,445][86177] Avg episode reward: [(0, '-499.920'), (1, '-513.470')] -[2023-11-28 05:51:49,022][87426] Updated weights for policy 1, policy_version 215530 (0.0009) -[2023-11-28 05:51:49,405][87426] Updated weights for policy 1, policy_version 215540 (0.0012) -[2023-11-28 05:51:49,612][87424] Updated weights for policy 0, policy_version 215937 (0.0011) -[2023-11-28 05:51:49,789][87426] Updated weights for policy 1, policy_version 215550 (0.0011) -[2023-11-28 05:51:49,988][87424] Updated weights for policy 0, policy_version 215947 (0.0010) -[2023-11-28 05:51:50,372][87424] Updated weights for policy 0, policy_version 215957 (0.0008) -[2023-11-28 05:51:50,752][87424] Updated weights for policy 0, policy_version 215967 (0.0008) -[2023-11-28 05:51:52,260][87426] Updated weights for policy 1, policy_version 215560 (0.0009) -[2023-11-28 05:51:52,647][87426] Updated weights for policy 1, policy_version 215570 (0.0008) -[2023-11-28 05:51:53,017][87426] Updated weights for policy 1, policy_version 215580 (0.0009) -[2023-11-28 05:51:53,280][87424] Updated weights for policy 0, policy_version 215977 (0.0009) -[2023-11-28 05:51:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 110477312. Throughput: 0: 2723.8, 1: 2721.7. Samples: 110494508. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:51:53,445][86177] Avg episode reward: [(0, '-498.990'), (1, '-516.240')] -[2023-11-28 05:51:53,649][87424] Updated weights for policy 0, policy_version 215987 (0.0010) -[2023-11-28 05:51:54,028][87424] Updated weights for policy 0, policy_version 215997 (0.0012) -[2023-11-28 05:51:55,029][87426] Updated weights for policy 1, policy_version 215590 (0.0011) -[2023-11-28 05:51:55,406][87426] Updated weights for policy 1, policy_version 215600 (0.0012) -[2023-11-28 05:51:55,794][87426] Updated weights for policy 1, policy_version 215610 (0.0012) -[2023-11-28 05:51:55,946][87424] Updated weights for policy 0, policy_version 216007 (0.0010) -[2023-11-28 05:51:56,331][87424] Updated weights for policy 0, policy_version 216017 (0.0012) -[2023-11-28 05:51:56,731][87424] Updated weights for policy 0, policy_version 216027 (0.0011) -[2023-11-28 05:51:57,651][87426] Updated weights for policy 1, policy_version 215620 (0.0010) -[2023-11-28 05:51:58,028][87426] Updated weights for policy 1, policy_version 215630 (0.0012) -[2023-11-28 05:51:58,407][87426] Updated weights for policy 1, policy_version 215640 (0.0012) -[2023-11-28 05:51:58,417][87424] Updated weights for policy 0, policy_version 216037 (0.0010) -[2023-11-28 05:51:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110501888. Throughput: 0: 2740.9, 1: 2733.1. Samples: 110519812. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:51:58,446][86177] Avg episode reward: [(0, '-493.990'), (1, '-521.090')] -[2023-11-28 05:51:58,805][87424] Updated weights for policy 0, policy_version 216047 (0.0007) -[2023-11-28 05:51:59,188][87424] Updated weights for policy 0, policy_version 216057 (0.0008) -[2023-11-28 05:52:00,842][87426] Updated weights for policy 1, policy_version 215650 (0.0011) -[2023-11-28 05:52:01,218][87426] Updated weights for policy 1, policy_version 215660 (0.0012) -[2023-11-28 05:52:01,592][87424] Updated weights for policy 0, policy_version 216067 (0.0008) -[2023-11-28 05:52:01,593][87426] Updated weights for policy 1, policy_version 215670 (0.0012) -[2023-11-28 05:52:01,974][87426] Updated weights for policy 1, policy_version 215680 (0.0011) -[2023-11-28 05:52:01,979][87424] Updated weights for policy 0, policy_version 216077 (0.0010) -[2023-11-28 05:52:02,363][87424] Updated weights for policy 0, policy_version 216087 (0.0009) -[2023-11-28 05:52:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110534656. Throughput: 0: 2751.1, 1: 2730.7. Samples: 110544608. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:52:03,445][86177] Avg episode reward: [(0, '-494.530'), (1, '-505.850')] -[2023-11-28 05:52:04,331][87426] Updated weights for policy 1, policy_version 215690 (0.0011) -[2023-11-28 05:52:04,408][87424] Updated weights for policy 0, policy_version 216097 (0.0008) -[2023-11-28 05:52:04,711][87426] Updated weights for policy 1, policy_version 215700 (0.0011) -[2023-11-28 05:52:04,787][87424] Updated weights for policy 0, policy_version 216107 (0.0010) -[2023-11-28 05:52:05,102][87426] Updated weights for policy 1, policy_version 215710 (0.0011) -[2023-11-28 05:52:05,177][87424] Updated weights for policy 0, policy_version 216117 (0.0012) -[2023-11-28 05:52:05,550][87424] Updated weights for policy 0, policy_version 216127 (0.0012) -[2023-11-28 05:52:07,217][87426] Updated weights for policy 1, policy_version 215720 (0.0010) -[2023-11-28 05:52:07,602][87426] Updated weights for policy 1, policy_version 215730 (0.0009) -[2023-11-28 05:52:07,656][87424] Updated weights for policy 0, policy_version 216137 (0.0011) -[2023-11-28 05:52:07,983][87426] Updated weights for policy 1, policy_version 215740 (0.0011) -[2023-11-28 05:52:08,028][87424] Updated weights for policy 0, policy_version 216147 (0.0011) -[2023-11-28 05:52:08,411][87424] Updated weights for policy 0, policy_version 216157 (0.0012) -[2023-11-28 05:52:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110559232. Throughput: 0: 2785.3, 1: 2742.0. Samples: 110577632. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:52:08,445][86177] Avg episode reward: [(0, '-498.320'), (1, '-513.130')] -[2023-11-28 05:52:10,183][87426] Updated weights for policy 1, policy_version 215750 (0.0010) -[2023-11-28 05:52:10,399][87424] Updated weights for policy 0, policy_version 216167 (0.0012) -[2023-11-28 05:52:10,555][87426] Updated weights for policy 1, policy_version 215760 (0.0010) -[2023-11-28 05:52:10,783][87424] Updated weights for policy 0, policy_version 216177 (0.0010) -[2023-11-28 05:52:10,940][87426] Updated weights for policy 1, policy_version 215770 (0.0012) -[2023-11-28 05:52:11,172][87424] Updated weights for policy 0, policy_version 216187 (0.0009) -[2023-11-28 05:52:13,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110583808. Throughput: 0: 2769.1, 1: 2723.3. Samples: 110601148. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:52:13,446][86177] Avg episode reward: [(0, '-498.720'), (1, '-506.120')] -[2023-11-28 05:52:13,518][87426] Updated weights for policy 1, policy_version 215780 (0.0011) -[2023-11-28 05:52:13,641][87424] Updated weights for policy 0, policy_version 216197 (0.0011) -[2023-11-28 05:52:13,893][87426] Updated weights for policy 1, policy_version 215790 (0.0011) -[2023-11-28 05:52:14,012][87424] Updated weights for policy 0, policy_version 216207 (0.0012) -[2023-11-28 05:52:14,278][87426] Updated weights for policy 1, policy_version 215800 (0.0010) -[2023-11-28 05:52:14,402][87424] Updated weights for policy 0, policy_version 216217 (0.0010) -[2023-11-28 05:52:16,315][87426] Updated weights for policy 1, policy_version 215810 (0.0011) -[2023-11-28 05:52:16,683][87424] Updated weights for policy 0, policy_version 216227 (0.0009) -[2023-11-28 05:52:16,691][87426] Updated weights for policy 1, policy_version 215820 (0.0012) -[2023-11-28 05:52:17,066][87426] Updated weights for policy 1, policy_version 215830 (0.0012) -[2023-11-28 05:52:17,072][87424] Updated weights for policy 0, policy_version 216237 (0.0012) -[2023-11-28 05:52:17,433][87426] Updated weights for policy 1, policy_version 215840 (0.0011) -[2023-11-28 05:52:17,445][87424] Updated weights for policy 0, policy_version 216247 (0.0011) -[2023-11-28 05:52:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110616576. Throughput: 0: 2739.4, 1: 2714.9. Samples: 110625848. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:52:18,446][86177] Avg episode reward: [(0, '-499.280'), (1, '-504.940')] -[2023-11-28 05:52:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000215840_55255040.pth... -[2023-11-28 05:52:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000216256_55361536.pth... -[2023-11-28 05:52:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000213312_54607872.pth -[2023-11-28 05:52:18,495][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000215840_55255040.pth -[2023-11-28 05:52:18,506][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000213728_54714368.pth -[2023-11-28 05:52:18,514][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000216256_55361536.pth -[2023-11-28 05:52:19,791][87426] Updated weights for policy 1, policy_version 215850 (0.0011) -[2023-11-28 05:52:19,993][87424] Updated weights for policy 0, policy_version 216257 (0.0007) -[2023-11-28 05:52:20,164][87426] Updated weights for policy 1, policy_version 215860 (0.0010) -[2023-11-28 05:52:20,375][87424] Updated weights for policy 0, policy_version 216267 (0.0010) -[2023-11-28 05:52:20,540][87426] Updated weights for policy 1, policy_version 215870 (0.0010) -[2023-11-28 05:52:20,756][87424] Updated weights for policy 0, policy_version 216277 (0.0012) -[2023-11-28 05:52:21,142][87424] Updated weights for policy 0, policy_version 216287 (0.0012) -[2023-11-28 05:52:23,138][87426] Updated weights for policy 1, policy_version 215880 (0.0011) -[2023-11-28 05:52:23,318][87424] Updated weights for policy 0, policy_version 216297 (0.0010) -[2023-11-28 05:52:23,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 110632960. Throughput: 0: 2711.4, 1: 2715.6. Samples: 110657380. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:52:23,445][86177] Avg episode reward: [(0, '-499.250'), (1, '-504.520')] -[2023-11-28 05:52:23,523][87426] Updated weights for policy 1, policy_version 215890 (0.0012) -[2023-11-28 05:52:23,705][87424] Updated weights for policy 0, policy_version 216307 (0.0008) -[2023-11-28 05:52:23,899][87426] Updated weights for policy 1, policy_version 215900 (0.0011) -[2023-11-28 05:52:24,088][87424] Updated weights for policy 0, policy_version 216317 (0.0008) -[2023-11-28 05:52:25,801][87424] Updated weights for policy 0, policy_version 216327 (0.0010) -[2023-11-28 05:52:26,185][87424] Updated weights for policy 0, policy_version 216337 (0.0011) -[2023-11-28 05:52:26,429][87426] Updated weights for policy 1, policy_version 215910 (0.0010) -[2023-11-28 05:52:26,566][87424] Updated weights for policy 0, policy_version 216347 (0.0007) -[2023-11-28 05:52:26,800][87426] Updated weights for policy 1, policy_version 215920 (0.0010) -[2023-11-28 05:52:27,180][87426] Updated weights for policy 1, policy_version 215930 (0.0010) -[2023-11-28 05:52:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110665728. Throughput: 0: 2739.6, 1: 2715.9. Samples: 110682848. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:52:28,445][86177] Avg episode reward: [(0, '-493.370'), (1, '-511.830')] -[2023-11-28 05:52:28,595][87424] Updated weights for policy 0, policy_version 216357 (0.0012) -[2023-11-28 05:52:28,981][87424] Updated weights for policy 0, policy_version 216367 (0.0012) -[2023-11-28 05:52:29,004][87426] Updated weights for policy 1, policy_version 215940 (0.0009) -[2023-11-28 05:52:29,370][87424] Updated weights for policy 0, policy_version 216377 (0.0011) -[2023-11-28 05:52:29,372][87426] Updated weights for policy 1, policy_version 215950 (0.0011) -[2023-11-28 05:52:29,753][87426] Updated weights for policy 1, policy_version 215960 (0.0008) -[2023-11-28 05:52:31,389][87424] Updated weights for policy 0, policy_version 216387 (0.0010) -[2023-11-28 05:52:31,521][87426] Updated weights for policy 1, policy_version 215970 (0.0009) -[2023-11-28 05:52:31,779][87424] Updated weights for policy 0, policy_version 216397 (0.0011) -[2023-11-28 05:52:31,898][87426] Updated weights for policy 1, policy_version 215980 (0.0009) -[2023-11-28 05:52:32,150][87424] Updated weights for policy 0, policy_version 216407 (0.0012) -[2023-11-28 05:52:32,281][87426] Updated weights for policy 1, policy_version 215990 (0.0008) -[2023-11-28 05:52:32,660][87426] Updated weights for policy 1, policy_version 216000 (0.0011) -[2023-11-28 05:52:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110698496. Throughput: 0: 2746.2, 1: 2705.5. Samples: 110707824. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:52:33,445][86177] Avg episode reward: [(0, '-495.330'), (1, '-517.940')] -[2023-11-28 05:52:34,650][87424] Updated weights for policy 0, policy_version 216417 (0.0009) -[2023-11-28 05:52:34,870][87426] Updated weights for policy 1, policy_version 216010 (0.0012) -[2023-11-28 05:52:35,030][87424] Updated weights for policy 0, policy_version 216427 (0.0011) -[2023-11-28 05:52:35,245][87426] Updated weights for policy 1, policy_version 216020 (0.0010) -[2023-11-28 05:52:35,406][87424] Updated weights for policy 0, policy_version 216437 (0.0011) -[2023-11-28 05:52:35,628][87426] Updated weights for policy 1, policy_version 216030 (0.0010) -[2023-11-28 05:52:35,788][87424] Updated weights for policy 0, policy_version 216447 (0.0011) -[2023-11-28 05:52:37,594][87424] Updated weights for policy 0, policy_version 216457 (0.0011) -[2023-11-28 05:52:37,654][87426] Updated weights for policy 1, policy_version 216040 (0.0008) -[2023-11-28 05:52:37,973][87424] Updated weights for policy 0, policy_version 216467 (0.0012) -[2023-11-28 05:52:38,036][87426] Updated weights for policy 1, policy_version 216050 (0.0009) -[2023-11-28 05:52:38,360][87424] Updated weights for policy 0, policy_version 216477 (0.0012) -[2023-11-28 05:52:38,419][87426] Updated weights for policy 1, policy_version 216060 (0.0010) -[2023-11-28 05:52:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 110714880. Throughput: 0: 2748.8, 1: 2733.0. Samples: 110741188. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 05:52:38,445][86177] Avg episode reward: [(0, '-500.360'), (1, '-531.010')] -[2023-11-28 05:52:40,205][87426] Updated weights for policy 1, policy_version 216070 (0.0012) -[2023-11-28 05:52:40,576][87426] Updated weights for policy 1, policy_version 216080 (0.0011) -[2023-11-28 05:52:40,772][87424] Updated weights for policy 0, policy_version 216487 (0.0011) -[2023-11-28 05:52:40,960][87426] Updated weights for policy 1, policy_version 216090 (0.0011) -[2023-11-28 05:52:41,158][87424] Updated weights for policy 0, policy_version 216497 (0.0011) -[2023-11-28 05:52:41,533][87424] Updated weights for policy 0, policy_version 216507 (0.0011) -[2023-11-28 05:52:43,038][87426] Updated weights for policy 1, policy_version 216100 (0.0011) -[2023-11-28 05:52:43,413][87426] Updated weights for policy 1, policy_version 216110 (0.0012) -[2023-11-28 05:52:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110747648. Throughput: 0: 2722.9, 1: 2725.3. Samples: 110764980. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:52:43,445][86177] Avg episode reward: [(0, '-499.030'), (1, '-517.280')] -[2023-11-28 05:52:43,806][87426] Updated weights for policy 1, policy_version 216120 (0.0012) -[2023-11-28 05:52:44,152][87424] Updated weights for policy 0, policy_version 216517 (0.0012) -[2023-11-28 05:52:44,531][87424] Updated weights for policy 0, policy_version 216527 (0.0011) -[2023-11-28 05:52:44,920][87424] Updated weights for policy 0, policy_version 216537 (0.0012) -[2023-11-28 05:52:46,295][87426] Updated weights for policy 1, policy_version 216130 (0.0012) -[2023-11-28 05:52:46,668][87426] Updated weights for policy 1, policy_version 216140 (0.0009) -[2023-11-28 05:52:46,718][87424] Updated weights for policy 0, policy_version 216547 (0.0010) -[2023-11-28 05:52:47,054][87426] Updated weights for policy 1, policy_version 216150 (0.0007) -[2023-11-28 05:52:47,086][87424] Updated weights for policy 0, policy_version 216557 (0.0007) -[2023-11-28 05:52:47,427][87426] Updated weights for policy 1, policy_version 216160 (0.0009) -[2023-11-28 05:52:47,466][87424] Updated weights for policy 0, policy_version 216567 (0.0007) -[2023-11-28 05:52:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110780416. Throughput: 0: 2711.6, 1: 2741.0. Samples: 110789976. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:52:48,446][86177] Avg episode reward: [(0, '-497.770'), (1, '-520.440')] -[2023-11-28 05:52:49,691][87424] Updated weights for policy 0, policy_version 216577 (0.0008) -[2023-11-28 05:52:49,957][87426] Updated weights for policy 1, policy_version 216170 (0.0010) -[2023-11-28 05:52:50,077][87424] Updated weights for policy 0, policy_version 216587 (0.0011) -[2023-11-28 05:52:50,334][87426] Updated weights for policy 1, policy_version 216180 (0.0012) -[2023-11-28 05:52:50,456][87424] Updated weights for policy 0, policy_version 216597 (0.0012) -[2023-11-28 05:52:50,709][87426] Updated weights for policy 1, policy_version 216190 (0.0012) -[2023-11-28 05:52:50,834][87424] Updated weights for policy 0, policy_version 216607 (0.0011) -[2023-11-28 05:52:52,829][87426] Updated weights for policy 1, policy_version 216200 (0.0010) -[2023-11-28 05:52:53,210][87426] Updated weights for policy 1, policy_version 216210 (0.0012) -[2023-11-28 05:52:53,351][87424] Updated weights for policy 0, policy_version 216617 (0.0011) -[2023-11-28 05:52:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 110796800. Throughput: 0: 2690.6, 1: 2728.8. Samples: 110821504. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:52:53,445][86177] Avg episode reward: [(0, '-497.020'), (1, '-511.550')] -[2023-11-28 05:52:53,589][87426] Updated weights for policy 1, policy_version 216220 (0.0012) -[2023-11-28 05:52:53,738][87424] Updated weights for policy 0, policy_version 216627 (0.0012) -[2023-11-28 05:52:54,122][87424] Updated weights for policy 0, policy_version 216637 (0.0012) -[2023-11-28 05:52:55,690][87426] Updated weights for policy 1, policy_version 216230 (0.0011) -[2023-11-28 05:52:55,964][87424] Updated weights for policy 0, policy_version 216647 (0.0012) -[2023-11-28 05:52:56,062][87426] Updated weights for policy 1, policy_version 216240 (0.0011) -[2023-11-28 05:52:56,353][87424] Updated weights for policy 0, policy_version 216657 (0.0011) -[2023-11-28 05:52:56,451][87426] Updated weights for policy 1, policy_version 216250 (0.0012) -[2023-11-28 05:52:56,741][87424] Updated weights for policy 0, policy_version 216667 (0.0011) -[2023-11-28 05:52:58,384][87424] Updated weights for policy 0, policy_version 216677 (0.0011) -[2023-11-28 05:52:58,406][87426] Updated weights for policy 1, policy_version 216260 (0.0012) -[2023-11-28 05:52:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110829568. Throughput: 0: 2690.1, 1: 2768.2. Samples: 110846768. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:52:58,445][86177] Avg episode reward: [(0, '-496.610'), (1, '-510.040')] -[2023-11-28 05:52:58,778][87424] Updated weights for policy 0, policy_version 216687 (0.0008) -[2023-11-28 05:52:58,784][87426] Updated weights for policy 1, policy_version 216270 (0.0012) -[2023-11-28 05:52:59,158][87424] Updated weights for policy 0, policy_version 216697 (0.0008) -[2023-11-28 05:52:59,162][87426] Updated weights for policy 1, policy_version 216280 (0.0012) -[2023-11-28 05:53:01,151][87426] Updated weights for policy 1, policy_version 216290 (0.0012) -[2023-11-28 05:53:01,505][87424] Updated weights for policy 0, policy_version 216707 (0.0008) -[2023-11-28 05:53:01,532][87426] Updated weights for policy 1, policy_version 216300 (0.0012) -[2023-11-28 05:53:01,882][87424] Updated weights for policy 0, policy_version 216717 (0.0011) -[2023-11-28 05:53:01,921][87426] Updated weights for policy 1, policy_version 216310 (0.0010) -[2023-11-28 05:53:02,264][87424] Updated weights for policy 0, policy_version 216727 (0.0011) -[2023-11-28 05:53:02,287][87426] Updated weights for policy 1, policy_version 216320 (0.0009) -[2023-11-28 05:53:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110862336. Throughput: 0: 2686.5, 1: 2769.7. Samples: 110871376. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:03,445][86177] Avg episode reward: [(0, '-500.460'), (1, '-509.470')] -[2023-11-28 05:53:04,477][87424] Updated weights for policy 0, policy_version 216737 (0.0012) -[2023-11-28 05:53:04,553][87426] Updated weights for policy 1, policy_version 216330 (0.0008) -[2023-11-28 05:53:04,856][87424] Updated weights for policy 0, policy_version 216747 (0.0009) -[2023-11-28 05:53:04,938][87426] Updated weights for policy 1, policy_version 216340 (0.0010) -[2023-11-28 05:53:05,240][87424] Updated weights for policy 0, policy_version 216757 (0.0011) -[2023-11-28 05:53:05,312][87426] Updated weights for policy 1, policy_version 216350 (0.0011) -[2023-11-28 05:53:05,621][87424] Updated weights for policy 0, policy_version 216767 (0.0009) -[2023-11-28 05:53:07,179][87426] Updated weights for policy 1, policy_version 216360 (0.0011) -[2023-11-28 05:53:07,553][87426] Updated weights for policy 1, policy_version 216370 (0.0008) -[2023-11-28 05:53:07,851][87424] Updated weights for policy 0, policy_version 216777 (0.0011) -[2023-11-28 05:53:07,946][87426] Updated weights for policy 1, policy_version 216380 (0.0007) -[2023-11-28 05:53:08,233][87424] Updated weights for policy 0, policy_version 216787 (0.0010) -[2023-11-28 05:53:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 110886912. Throughput: 0: 2702.1, 1: 2772.9. Samples: 110903756. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:08,445][86177] Avg episode reward: [(0, '-512.380'), (1, '-511.260')] -[2023-11-28 05:53:08,617][87424] Updated weights for policy 0, policy_version 216797 (0.0008) -[2023-11-28 05:53:10,196][87426] Updated weights for policy 1, policy_version 216390 (0.0009) -[2023-11-28 05:53:10,581][87426] Updated weights for policy 1, policy_version 216400 (0.0010) -[2023-11-28 05:53:10,959][87426] Updated weights for policy 1, policy_version 216410 (0.0010) -[2023-11-28 05:53:11,101][87424] Updated weights for policy 0, policy_version 216807 (0.0010) -[2023-11-28 05:53:11,484][87424] Updated weights for policy 0, policy_version 216817 (0.0011) -[2023-11-28 05:53:11,879][87424] Updated weights for policy 0, policy_version 216827 (0.0010) -[2023-11-28 05:53:13,188][87426] Updated weights for policy 1, policy_version 216420 (0.0010) -[2023-11-28 05:53:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 110911488. Throughput: 0: 2676.2, 1: 2749.0. Samples: 110926980. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:13,445][86177] Avg episode reward: [(0, '-512.710'), (1, '-513.960')] -[2023-11-28 05:53:13,563][87426] Updated weights for policy 1, policy_version 216430 (0.0009) -[2023-11-28 05:53:13,953][87426] Updated weights for policy 1, policy_version 216440 (0.0007) -[2023-11-28 05:53:13,964][87424] Updated weights for policy 0, policy_version 216837 (0.0009) -[2023-11-28 05:53:14,342][87424] Updated weights for policy 0, policy_version 216847 (0.0011) -[2023-11-28 05:53:14,722][87424] Updated weights for policy 0, policy_version 216857 (0.0012) -[2023-11-28 05:53:15,965][87426] Updated weights for policy 1, policy_version 216450 (0.0011) -[2023-11-28 05:53:16,352][87426] Updated weights for policy 1, policy_version 216460 (0.0012) -[2023-11-28 05:53:16,721][87426] Updated weights for policy 1, policy_version 216470 (0.0012) -[2023-11-28 05:53:16,840][87424] Updated weights for policy 0, policy_version 216867 (0.0012) -[2023-11-28 05:53:17,107][87426] Updated weights for policy 1, policy_version 216480 (0.0011) -[2023-11-28 05:53:17,216][87424] Updated weights for policy 0, policy_version 216877 (0.0011) -[2023-11-28 05:53:17,599][87424] Updated weights for policy 0, policy_version 216887 (0.0012) -[2023-11-28 05:53:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 110944256. Throughput: 0: 2675.4, 1: 2759.3. Samples: 110952384. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:18,445][86177] Avg episode reward: [(0, '-512.410'), (1, '-513.820')] -[2023-11-28 05:53:19,061][87426] Updated weights for policy 1, policy_version 216490 (0.0012) -[2023-11-28 05:53:19,439][87426] Updated weights for policy 1, policy_version 216500 (0.0012) -[2023-11-28 05:53:19,805][87424] Updated weights for policy 0, policy_version 216897 (0.0012) -[2023-11-28 05:53:19,818][87426] Updated weights for policy 1, policy_version 216510 (0.0012) -[2023-11-28 05:53:20,192][87424] Updated weights for policy 0, policy_version 216907 (0.0012) -[2023-11-28 05:53:20,578][87424] Updated weights for policy 0, policy_version 216917 (0.0012) -[2023-11-28 05:53:20,962][87424] Updated weights for policy 0, policy_version 216927 (0.0011) -[2023-11-28 05:53:22,318][87426] Updated weights for policy 1, policy_version 216520 (0.0011) -[2023-11-28 05:53:22,699][87426] Updated weights for policy 1, policy_version 216530 (0.0012) -[2023-11-28 05:53:23,083][87426] Updated weights for policy 1, policy_version 216540 (0.0010) -[2023-11-28 05:53:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 110968832. Throughput: 0: 2654.7, 1: 2725.7. Samples: 110983304. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:23,446][86177] Avg episode reward: [(0, '-510.320'), (1, '-512.570')] -[2023-11-28 05:53:23,554][87424] Updated weights for policy 0, policy_version 216937 (0.0012) -[2023-11-28 05:53:23,974][87424] Updated weights for policy 0, policy_version 216947 (0.0012) -[2023-11-28 05:53:24,347][87424] Updated weights for policy 0, policy_version 216957 (0.0012) -[2023-11-28 05:53:25,535][87426] Updated weights for policy 1, policy_version 216550 (0.0010) -[2023-11-28 05:53:25,919][87426] Updated weights for policy 1, policy_version 216560 (0.0009) -[2023-11-28 05:53:26,290][87426] Updated weights for policy 1, policy_version 216570 (0.0011) -[2023-11-28 05:53:26,531][87424] Updated weights for policy 0, policy_version 216967 (0.0012) -[2023-11-28 05:53:26,923][87424] Updated weights for policy 0, policy_version 216977 (0.0012) -[2023-11-28 05:53:27,299][87424] Updated weights for policy 0, policy_version 216987 (0.0012) -[2023-11-28 05:53:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 110993408. Throughput: 0: 2654.0, 1: 2740.5. Samples: 111007736. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:28,445][86177] Avg episode reward: [(0, '-497.560'), (1, '-513.020')] -[2023-11-28 05:53:28,578][87426] Updated weights for policy 1, policy_version 216580 (0.0012) -[2023-11-28 05:53:28,972][87426] Updated weights for policy 1, policy_version 216590 (0.0016) -[2023-11-28 05:53:29,340][87426] Updated weights for policy 1, policy_version 216600 (0.0012) -[2023-11-28 05:53:29,856][87424] Updated weights for policy 0, policy_version 216997 (0.0012) -[2023-11-28 05:53:30,238][87424] Updated weights for policy 0, policy_version 217007 (0.0012) -[2023-11-28 05:53:30,613][87424] Updated weights for policy 0, policy_version 217017 (0.0012) -[2023-11-28 05:53:31,205][87426] Updated weights for policy 1, policy_version 216610 (0.0012) -[2023-11-28 05:53:31,593][87426] Updated weights for policy 1, policy_version 216620 (0.0012) -[2023-11-28 05:53:31,967][87426] Updated weights for policy 1, policy_version 216630 (0.0011) -[2023-11-28 05:53:32,349][87426] Updated weights for policy 1, policy_version 216640 (0.0011) -[2023-11-28 05:53:32,486][87424] Updated weights for policy 0, policy_version 217027 (0.0012) -[2023-11-28 05:53:32,869][87424] Updated weights for policy 0, policy_version 217037 (0.0011) -[2023-11-28 05:53:33,246][87424] Updated weights for policy 0, policy_version 217047 (0.0011) -[2023-11-28 05:53:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 111017984. Throughput: 0: 2682.2, 1: 2724.6. Samples: 111033284. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:33,445][86177] Avg episode reward: [(0, '-503.270'), (1, '-508.090')] -[2023-11-28 05:53:34,850][87426] Updated weights for policy 1, policy_version 216650 (0.0012) -[2023-11-28 05:53:35,227][87426] Updated weights for policy 1, policy_version 216660 (0.0012) -[2023-11-28 05:53:35,259][87424] Updated weights for policy 0, policy_version 217057 (0.0012) -[2023-11-28 05:53:35,602][87426] Updated weights for policy 1, policy_version 216670 (0.0012) -[2023-11-28 05:53:35,636][87424] Updated weights for policy 0, policy_version 217067 (0.0009) -[2023-11-28 05:53:36,026][87424] Updated weights for policy 0, policy_version 217077 (0.0007) -[2023-11-28 05:53:36,396][87424] Updated weights for policy 0, policy_version 217087 (0.0007) -[2023-11-28 05:53:38,110][87426] Updated weights for policy 1, policy_version 216680 (0.0012) -[2023-11-28 05:53:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 111042560. Throughput: 0: 2687.0, 1: 2733.2. Samples: 111065412. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:38,445][86177] Avg episode reward: [(0, '-508.090'), (1, '-512.300')] -[2023-11-28 05:53:38,485][87426] Updated weights for policy 1, policy_version 216690 (0.0012) -[2023-11-28 05:53:38,862][87426] Updated weights for policy 1, policy_version 216700 (0.0008) -[2023-11-28 05:53:38,970][87424] Updated weights for policy 0, policy_version 217097 (0.0011) -[2023-11-28 05:53:39,353][87424] Updated weights for policy 0, policy_version 217107 (0.0012) -[2023-11-28 05:53:39,733][87424] Updated weights for policy 0, policy_version 217117 (0.0011) -[2023-11-28 05:53:41,357][87426] Updated weights for policy 1, policy_version 216710 (0.0011) -[2023-11-28 05:53:41,741][87426] Updated weights for policy 1, policy_version 216720 (0.0012) -[2023-11-28 05:53:42,117][87426] Updated weights for policy 1, policy_version 216730 (0.0011) -[2023-11-28 05:53:42,264][87424] Updated weights for policy 0, policy_version 217127 (0.0011) -[2023-11-28 05:53:42,644][87424] Updated weights for policy 0, policy_version 217137 (0.0008) -[2023-11-28 05:53:43,030][87424] Updated weights for policy 0, policy_version 217147 (0.0012) -[2023-11-28 05:53:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 111075328. Throughput: 0: 2680.4, 1: 2687.8. Samples: 111088336. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:43,445][86177] Avg episode reward: [(0, '-508.450'), (1, '-513.760')] -[2023-11-28 05:53:44,038][87426] Updated weights for policy 1, policy_version 216740 (0.0011) -[2023-11-28 05:53:44,406][87426] Updated weights for policy 1, policy_version 216750 (0.0008) -[2023-11-28 05:53:44,786][87426] Updated weights for policy 1, policy_version 216760 (0.0008) -[2023-11-28 05:53:45,363][87424] Updated weights for policy 0, policy_version 217157 (0.0010) -[2023-11-28 05:53:45,743][87424] Updated weights for policy 0, policy_version 217167 (0.0008) -[2023-11-28 05:53:46,118][87424] Updated weights for policy 0, policy_version 217177 (0.0008) -[2023-11-28 05:53:47,239][87426] Updated weights for policy 1, policy_version 216770 (0.0007) -[2023-11-28 05:53:47,619][87426] Updated weights for policy 1, policy_version 216780 (0.0007) -[2023-11-28 05:53:47,903][87424] Updated weights for policy 0, policy_version 217187 (0.0009) -[2023-11-28 05:53:48,000][87426] Updated weights for policy 1, policy_version 216790 (0.0007) -[2023-11-28 05:53:48,284][87424] Updated weights for policy 0, policy_version 217197 (0.0012) -[2023-11-28 05:53:48,380][87426] Updated weights for policy 1, policy_version 216800 (0.0008) -[2023-11-28 05:53:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 111099904. Throughput: 0: 2669.2, 1: 2676.8. Samples: 111111948. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 05:53:48,446][86177] Avg episode reward: [(0, '-511.410'), (1, '-516.930')] -[2023-11-28 05:53:48,672][87424] Updated weights for policy 0, policy_version 217207 (0.0012) -[2023-11-28 05:53:50,900][87426] Updated weights for policy 1, policy_version 216810 (0.0010) -[2023-11-28 05:53:50,932][87424] Updated weights for policy 0, policy_version 217217 (0.0012) -[2023-11-28 05:53:51,275][87426] Updated weights for policy 1, policy_version 216820 (0.0009) -[2023-11-28 05:53:51,315][87424] Updated weights for policy 0, policy_version 217227 (0.0014) -[2023-11-28 05:53:51,665][87426] Updated weights for policy 1, policy_version 216830 (0.0011) -[2023-11-28 05:53:51,693][87424] Updated weights for policy 0, policy_version 217237 (0.0011) -[2023-11-28 05:53:52,080][87424] Updated weights for policy 0, policy_version 217247 (0.0012) -[2023-11-28 05:53:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 111124480. Throughput: 0: 2664.7, 1: 2668.2. Samples: 111143736. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:53:53,445][86177] Avg episode reward: [(0, '-500.810'), (1, '-524.210')] -[2023-11-28 05:53:53,574][87426] Updated weights for policy 1, policy_version 216840 (0.0011) -[2023-11-28 05:53:53,951][87426] Updated weights for policy 1, policy_version 216850 (0.0010) -[2023-11-28 05:53:54,330][87426] Updated weights for policy 1, policy_version 216860 (0.0012) -[2023-11-28 05:53:54,544][87424] Updated weights for policy 0, policy_version 217257 (0.0012) -[2023-11-28 05:53:54,922][87424] Updated weights for policy 0, policy_version 217267 (0.0012) -[2023-11-28 05:53:55,298][87424] Updated weights for policy 0, policy_version 217277 (0.0012) -[2023-11-28 05:53:56,828][87426] Updated weights for policy 1, policy_version 216870 (0.0011) -[2023-11-28 05:53:57,218][87426] Updated weights for policy 1, policy_version 216880 (0.0010) -[2023-11-28 05:53:57,301][87424] Updated weights for policy 0, policy_version 217287 (0.0012) -[2023-11-28 05:53:57,602][87426] Updated weights for policy 1, policy_version 216890 (0.0010) -[2023-11-28 05:53:57,683][87424] Updated weights for policy 0, policy_version 217297 (0.0011) -[2023-11-28 05:53:58,070][87424] Updated weights for policy 0, policy_version 217307 (0.0012) -[2023-11-28 05:53:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 111157248. Throughput: 0: 2672.8, 1: 2674.9. Samples: 111167628. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:53:58,445][86177] Avg episode reward: [(0, '-494.290'), (1, '-521.790')] -[2023-11-28 05:53:59,377][87426] Updated weights for policy 1, policy_version 216900 (0.0012) -[2023-11-28 05:53:59,764][87426] Updated weights for policy 1, policy_version 216910 (0.0012) -[2023-11-28 05:54:00,098][87424] Updated weights for policy 0, policy_version 217317 (0.0011) -[2023-11-28 05:54:00,140][87426] Updated weights for policy 1, policy_version 216920 (0.0008) -[2023-11-28 05:54:00,479][87424] Updated weights for policy 0, policy_version 217327 (0.0010) -[2023-11-28 05:54:00,856][87424] Updated weights for policy 0, policy_version 217337 (0.0008) -[2023-11-28 05:54:02,235][87426] Updated weights for policy 1, policy_version 216930 (0.0008) -[2023-11-28 05:54:02,617][87426] Updated weights for policy 1, policy_version 216940 (0.0011) -[2023-11-28 05:54:02,999][87426] Updated weights for policy 1, policy_version 216950 (0.0012) -[2023-11-28 05:54:03,187][87424] Updated weights for policy 0, policy_version 217347 (0.0009) -[2023-11-28 05:54:03,368][87426] Updated weights for policy 1, policy_version 216960 (0.0011) -[2023-11-28 05:54:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 111181824. Throughput: 0: 2650.4, 1: 2672.4. Samples: 111191908. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:03,445][86177] Avg episode reward: [(0, '-492.740'), (1, '-521.460')] -[2023-11-28 05:54:03,566][87424] Updated weights for policy 0, policy_version 217357 (0.0012) -[2023-11-28 05:54:03,950][87424] Updated weights for policy 0, policy_version 217367 (0.0012) -[2023-11-28 05:54:05,549][87426] Updated weights for policy 1, policy_version 216970 (0.0008) -[2023-11-28 05:54:05,691][87424] Updated weights for policy 0, policy_version 217377 (0.0011) -[2023-11-28 05:54:05,931][87426] Updated weights for policy 1, policy_version 216980 (0.0008) -[2023-11-28 05:54:06,074][87424] Updated weights for policy 0, policy_version 217387 (0.0010) -[2023-11-28 05:54:06,312][87426] Updated weights for policy 1, policy_version 216990 (0.0008) -[2023-11-28 05:54:06,464][87424] Updated weights for policy 0, policy_version 217397 (0.0011) -[2023-11-28 05:54:06,838][87424] Updated weights for policy 0, policy_version 217407 (0.0010) -[2023-11-28 05:54:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 111206400. Throughput: 0: 2670.3, 1: 2663.0. Samples: 111223304. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:08,445][86177] Avg episode reward: [(0, '-489.350'), (1, '-516.410')] -[2023-11-28 05:54:08,609][87426] Updated weights for policy 1, policy_version 217000 (0.0012) -[2023-11-28 05:54:09,007][87426] Updated weights for policy 1, policy_version 217010 (0.0012) -[2023-11-28 05:54:09,382][87426] Updated weights for policy 1, policy_version 217020 (0.0011) -[2023-11-28 05:54:09,494][87424] Updated weights for policy 0, policy_version 217417 (0.0009) -[2023-11-28 05:54:09,885][87424] Updated weights for policy 0, policy_version 217427 (0.0012) -[2023-11-28 05:54:10,270][87424] Updated weights for policy 0, policy_version 217437 (0.0012) -[2023-11-28 05:54:11,643][87426] Updated weights for policy 1, policy_version 217030 (0.0010) -[2023-11-28 05:54:12,027][87426] Updated weights for policy 1, policy_version 217040 (0.0009) -[2023-11-28 05:54:12,413][87426] Updated weights for policy 1, policy_version 217050 (0.0010) -[2023-11-28 05:54:12,943][87424] Updated weights for policy 0, policy_version 217447 (0.0012) -[2023-11-28 05:54:13,332][87424] Updated weights for policy 0, policy_version 217457 (0.0008) -[2023-11-28 05:54:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 111230976. Throughput: 0: 2674.5, 1: 2638.3. Samples: 111246812. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:13,445][86177] Avg episode reward: [(0, '-491.070'), (1, '-510.160')] -[2023-11-28 05:54:13,727][87424] Updated weights for policy 0, policy_version 217467 (0.0008) -[2023-11-28 05:54:14,697][87426] Updated weights for policy 1, policy_version 217060 (0.0010) -[2023-11-28 05:54:15,073][87426] Updated weights for policy 1, policy_version 217070 (0.0008) -[2023-11-28 05:54:15,450][87426] Updated weights for policy 1, policy_version 217080 (0.0008) -[2023-11-28 05:54:15,862][87424] Updated weights for policy 0, policy_version 217477 (0.0009) -[2023-11-28 05:54:16,236][87424] Updated weights for policy 0, policy_version 217487 (0.0012) -[2023-11-28 05:54:16,616][87424] Updated weights for policy 0, policy_version 217497 (0.0012) -[2023-11-28 05:54:17,730][87426] Updated weights for policy 1, policy_version 217090 (0.0009) -[2023-11-28 05:54:18,097][87426] Updated weights for policy 1, policy_version 217100 (0.0007) -[2023-11-28 05:54:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 111255552. Throughput: 0: 2627.7, 1: 2643.3. Samples: 111270480. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:18,445][86177] Avg episode reward: [(0, '-491.460'), (1, '-514.260')] -[2023-11-28 05:54:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000217504_55681024.pth... -[2023-11-28 05:54:18,487][87426] Updated weights for policy 1, policy_version 217110 (0.0007) -[2023-11-28 05:54:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000215008_55042048.pth -[2023-11-28 05:54:18,755][87424] Updated weights for policy 0, policy_version 217507 (0.0009) -[2023-11-28 05:54:18,869][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000217120_55582720.pth... -[2023-11-28 05:54:18,870][87426] Updated weights for policy 1, policy_version 217120 (0.0011) -[2023-11-28 05:54:18,908][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000214560_54927360.pth -[2023-11-28 05:54:19,145][87424] Updated weights for policy 0, policy_version 217517 (0.0010) -[2023-11-28 05:54:19,523][87424] Updated weights for policy 0, policy_version 217527 (0.0011) -[2023-11-28 05:54:21,000][87426] Updated weights for policy 1, policy_version 217130 (0.0012) -[2023-11-28 05:54:21,381][87426] Updated weights for policy 1, policy_version 217140 (0.0011) -[2023-11-28 05:54:21,738][87424] Updated weights for policy 0, policy_version 217537 (0.0010) -[2023-11-28 05:54:21,763][87426] Updated weights for policy 1, policy_version 217150 (0.0010) -[2023-11-28 05:54:22,117][87424] Updated weights for policy 0, policy_version 217547 (0.0009) -[2023-11-28 05:54:22,515][87424] Updated weights for policy 0, policy_version 217557 (0.0008) -[2023-11-28 05:54:22,901][87424] Updated weights for policy 0, policy_version 217567 (0.0008) -[2023-11-28 05:54:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 111288320. Throughput: 0: 2637.0, 1: 2645.6. Samples: 111303128. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:23,445][86177] Avg episode reward: [(0, '-492.310'), (1, '-531.860')] -[2023-11-28 05:54:24,009][87426] Updated weights for policy 1, policy_version 217160 (0.0012) -[2023-11-28 05:54:24,387][87426] Updated weights for policy 1, policy_version 217170 (0.0011) -[2023-11-28 05:54:24,766][87426] Updated weights for policy 1, policy_version 217180 (0.0010) -[2023-11-28 05:54:24,973][87424] Updated weights for policy 0, policy_version 217577 (0.0012) -[2023-11-28 05:54:25,347][87424] Updated weights for policy 0, policy_version 217587 (0.0011) -[2023-11-28 05:54:25,734][87424] Updated weights for policy 0, policy_version 217597 (0.0011) -[2023-11-28 05:54:27,362][87426] Updated weights for policy 1, policy_version 217190 (0.0011) -[2023-11-28 05:54:27,618][87424] Updated weights for policy 0, policy_version 217607 (0.0009) -[2023-11-28 05:54:27,746][87426] Updated weights for policy 1, policy_version 217200 (0.0011) -[2023-11-28 05:54:27,998][87424] Updated weights for policy 0, policy_version 217617 (0.0007) -[2023-11-28 05:54:28,133][87426] Updated weights for policy 1, policy_version 217210 (0.0012) -[2023-11-28 05:54:28,379][87424] Updated weights for policy 0, policy_version 217627 (0.0008) -[2023-11-28 05:54:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 111312896. Throughput: 0: 2656.4, 1: 2664.4. Samples: 111327768. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:28,445][86177] Avg episode reward: [(0, '-492.250'), (1, '-534.120')] -[2023-11-28 05:54:30,400][87426] Updated weights for policy 1, policy_version 217220 (0.0011) -[2023-11-28 05:54:30,780][87426] Updated weights for policy 1, policy_version 217230 (0.0011) -[2023-11-28 05:54:30,806][87424] Updated weights for policy 0, policy_version 217637 (0.0009) -[2023-11-28 05:54:31,160][87426] Updated weights for policy 1, policy_version 217240 (0.0011) -[2023-11-28 05:54:31,183][87424] Updated weights for policy 0, policy_version 217647 (0.0008) -[2023-11-28 05:54:31,570][87424] Updated weights for policy 0, policy_version 217657 (0.0007) -[2023-11-28 05:54:32,935][87426] Updated weights for policy 1, policy_version 217250 (0.0012) -[2023-11-28 05:54:33,305][87426] Updated weights for policy 1, policy_version 217260 (0.0012) -[2023-11-28 05:54:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 111337472. Throughput: 0: 2653.0, 1: 2681.4. Samples: 111351996. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:33,445][86177] Avg episode reward: [(0, '-492.380'), (1, '-534.830')] -[2023-11-28 05:54:33,690][87426] Updated weights for policy 1, policy_version 217270 (0.0012) -[2023-11-28 05:54:33,729][87424] Updated weights for policy 0, policy_version 217667 (0.0011) -[2023-11-28 05:54:34,064][87426] Updated weights for policy 1, policy_version 217280 (0.0011) -[2023-11-28 05:54:34,109][87424] Updated weights for policy 0, policy_version 217677 (0.0012) -[2023-11-28 05:54:34,485][87424] Updated weights for policy 0, policy_version 217687 (0.0012) -[2023-11-28 05:54:36,048][87426] Updated weights for policy 1, policy_version 217290 (0.0008) -[2023-11-28 05:54:36,436][87426] Updated weights for policy 1, policy_version 217300 (0.0007) -[2023-11-28 05:54:36,678][87424] Updated weights for policy 0, policy_version 217697 (0.0012) -[2023-11-28 05:54:36,818][87426] Updated weights for policy 1, policy_version 217310 (0.0009) -[2023-11-28 05:54:37,053][87424] Updated weights for policy 0, policy_version 217707 (0.0009) -[2023-11-28 05:54:37,440][87424] Updated weights for policy 0, policy_version 217717 (0.0012) -[2023-11-28 05:54:37,815][87424] Updated weights for policy 0, policy_version 217727 (0.0012) -[2023-11-28 05:54:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 111370240. Throughput: 0: 2673.4, 1: 2713.2. Samples: 111386132. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:38,445][86177] Avg episode reward: [(0, '-495.830'), (1, '-526.390')] -[2023-11-28 05:54:38,494][87426] Updated weights for policy 1, policy_version 217320 (0.0011) -[2023-11-28 05:54:38,874][87426] Updated weights for policy 1, policy_version 217330 (0.0013) -[2023-11-28 05:54:39,254][87426] Updated weights for policy 1, policy_version 217340 (0.0007) -[2023-11-28 05:54:39,854][87424] Updated weights for policy 0, policy_version 217737 (0.0012) -[2023-11-28 05:54:40,240][87424] Updated weights for policy 0, policy_version 217747 (0.0011) -[2023-11-28 05:54:40,624][87424] Updated weights for policy 0, policy_version 217757 (0.0015) -[2023-11-28 05:54:41,801][87426] Updated weights for policy 1, policy_version 217350 (0.0011) -[2023-11-28 05:54:42,175][87426] Updated weights for policy 1, policy_version 217360 (0.0011) -[2023-11-28 05:54:42,555][87426] Updated weights for policy 1, policy_version 217370 (0.0008) -[2023-11-28 05:54:43,128][87424] Updated weights for policy 0, policy_version 217767 (0.0009) -[2023-11-28 05:54:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 111394816. Throughput: 0: 2676.4, 1: 2721.6. Samples: 111410540. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:43,445][86177] Avg episode reward: [(0, '-499.410'), (1, '-507.790')] -[2023-11-28 05:54:43,511][87424] Updated weights for policy 0, policy_version 217777 (0.0008) -[2023-11-28 05:54:43,900][87424] Updated weights for policy 0, policy_version 217787 (0.0011) -[2023-11-28 05:54:44,927][87426] Updated weights for policy 1, policy_version 217380 (0.0008) -[2023-11-28 05:54:45,307][87426] Updated weights for policy 1, policy_version 217390 (0.0009) -[2023-11-28 05:54:45,678][87426] Updated weights for policy 1, policy_version 217400 (0.0008) -[2023-11-28 05:54:46,330][87424] Updated weights for policy 0, policy_version 217797 (0.0008) -[2023-11-28 05:54:46,728][87424] Updated weights for policy 0, policy_version 217807 (0.0007) -[2023-11-28 05:54:47,096][87424] Updated weights for policy 0, policy_version 217817 (0.0007) -[2023-11-28 05:54:47,610][87426] Updated weights for policy 1, policy_version 217410 (0.0009) -[2023-11-28 05:54:47,992][87426] Updated weights for policy 1, policy_version 217420 (0.0010) -[2023-11-28 05:54:48,372][87426] Updated weights for policy 1, policy_version 217430 (0.0007) -[2023-11-28 05:54:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 111419392. Throughput: 0: 2698.1, 1: 2717.6. Samples: 111435616. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:48,445][86177] Avg episode reward: [(0, '-499.340'), (1, '-506.940')] -[2023-11-28 05:54:48,753][87426] Updated weights for policy 1, policy_version 217440 (0.0007) -[2023-11-28 05:54:49,316][87424] Updated weights for policy 0, policy_version 217827 (0.0008) -[2023-11-28 05:54:49,703][87424] Updated weights for policy 0, policy_version 217837 (0.0008) -[2023-11-28 05:54:50,085][87424] Updated weights for policy 0, policy_version 217847 (0.0008) -[2023-11-28 05:54:51,187][87426] Updated weights for policy 1, policy_version 217450 (0.0010) -[2023-11-28 05:54:51,567][87426] Updated weights for policy 1, policy_version 217460 (0.0008) -[2023-11-28 05:54:51,946][87426] Updated weights for policy 1, policy_version 217470 (0.0009) -[2023-11-28 05:54:52,567][87424] Updated weights for policy 0, policy_version 217857 (0.0008) -[2023-11-28 05:54:52,944][87424] Updated weights for policy 0, policy_version 217867 (0.0008) -[2023-11-28 05:54:53,332][87424] Updated weights for policy 0, policy_version 217877 (0.0009) -[2023-11-28 05:54:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 111443968. Throughput: 0: 2702.5, 1: 2716.3. Samples: 111467148. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:53,445][86177] Avg episode reward: [(0, '-501.470'), (1, '-504.380')] -[2023-11-28 05:54:53,717][87424] Updated weights for policy 0, policy_version 217887 (0.0011) -[2023-11-28 05:54:54,355][87426] Updated weights for policy 1, policy_version 217480 (0.0011) -[2023-11-28 05:54:54,733][87426] Updated weights for policy 1, policy_version 217490 (0.0012) -[2023-11-28 05:54:55,109][87426] Updated weights for policy 1, policy_version 217500 (0.0010) -[2023-11-28 05:54:55,517][87424] Updated weights for policy 0, policy_version 217897 (0.0010) -[2023-11-28 05:54:55,910][87424] Updated weights for policy 0, policy_version 217907 (0.0011) -[2023-11-28 05:54:56,297][87424] Updated weights for policy 0, policy_version 217917 (0.0011) -[2023-11-28 05:54:57,595][87426] Updated weights for policy 1, policy_version 217510 (0.0011) -[2023-11-28 05:54:57,973][87426] Updated weights for policy 1, policy_version 217520 (0.0011) -[2023-11-28 05:54:58,084][87424] Updated weights for policy 0, policy_version 217927 (0.0011) -[2023-11-28 05:54:58,349][87426] Updated weights for policy 1, policy_version 217530 (0.0008) -[2023-11-28 05:54:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.2, 300 sec: 5387.3). Total num frames: 111468544. Throughput: 0: 2712.3, 1: 2712.2. Samples: 111490916. Policy #0 lag: (min: 31.0, avg: 47.3, max: 76.0) -[2023-11-28 05:54:58,445][86177] Avg episode reward: [(0, '-498.770'), (1, '-512.250')] -[2023-11-28 05:54:58,463][87424] Updated weights for policy 0, policy_version 217937 (0.0010) -[2023-11-28 05:54:58,855][87424] Updated weights for policy 0, policy_version 217947 (0.0012) -[2023-11-28 05:55:00,660][87424] Updated weights for policy 0, policy_version 217957 (0.0012) -[2023-11-28 05:55:00,839][87426] Updated weights for policy 1, policy_version 217540 (0.0011) -[2023-11-28 05:55:01,040][87424] Updated weights for policy 0, policy_version 217967 (0.0010) -[2023-11-28 05:55:01,219][87426] Updated weights for policy 1, policy_version 217550 (0.0010) -[2023-11-28 05:55:01,425][87424] Updated weights for policy 0, policy_version 217977 (0.0010) -[2023-11-28 05:55:01,601][87426] Updated weights for policy 1, policy_version 217560 (0.0008) -[2023-11-28 05:55:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 111501312. Throughput: 0: 2748.4, 1: 2702.7. Samples: 111515776. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:03,445][86177] Avg episode reward: [(0, '-499.620'), (1, '-513.810')] -[2023-11-28 05:55:03,456][87424] Updated weights for policy 0, policy_version 217987 (0.0011) -[2023-11-28 05:55:03,840][87424] Updated weights for policy 0, policy_version 217997 (0.0010) -[2023-11-28 05:55:04,122][87426] Updated weights for policy 1, policy_version 217570 (0.0008) -[2023-11-28 05:55:04,218][87424] Updated weights for policy 0, policy_version 218007 (0.0007) -[2023-11-28 05:55:04,505][87426] Updated weights for policy 1, policy_version 217580 (0.0009) -[2023-11-28 05:55:04,885][87426] Updated weights for policy 1, policy_version 217590 (0.0009) -[2023-11-28 05:55:05,262][87426] Updated weights for policy 1, policy_version 217600 (0.0009) -[2023-11-28 05:55:06,459][87424] Updated weights for policy 0, policy_version 218017 (0.0009) -[2023-11-28 05:55:06,834][87424] Updated weights for policy 0, policy_version 218027 (0.0011) -[2023-11-28 05:55:07,016][87426] Updated weights for policy 1, policy_version 217610 (0.0012) -[2023-11-28 05:55:07,212][87424] Updated weights for policy 0, policy_version 218037 (0.0011) -[2023-11-28 05:55:07,403][87426] Updated weights for policy 1, policy_version 217620 (0.0012) -[2023-11-28 05:55:07,597][87424] Updated weights for policy 0, policy_version 218047 (0.0012) -[2023-11-28 05:55:07,779][87426] Updated weights for policy 1, policy_version 217630 (0.0011) -[2023-11-28 05:55:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 111534080. Throughput: 0: 2749.2, 1: 2681.6. Samples: 111547516. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:08,445][86177] Avg episode reward: [(0, '-497.010'), (1, '-551.920')] -[2023-11-28 05:55:09,457][87424] Updated weights for policy 0, policy_version 218057 (0.0011) -[2023-11-28 05:55:09,841][87424] Updated weights for policy 0, policy_version 218067 (0.0009) -[2023-11-28 05:55:10,215][87424] Updated weights for policy 0, policy_version 218077 (0.0010) -[2023-11-28 05:55:10,257][87426] Updated weights for policy 1, policy_version 217640 (0.0009) -[2023-11-28 05:55:10,635][87426] Updated weights for policy 1, policy_version 217650 (0.0011) -[2023-11-28 05:55:11,020][87426] Updated weights for policy 1, policy_version 217660 (0.0012) -[2023-11-28 05:55:12,649][87424] Updated weights for policy 0, policy_version 218087 (0.0011) -[2023-11-28 05:55:12,900][87426] Updated weights for policy 1, policy_version 217670 (0.0011) -[2023-11-28 05:55:13,029][87424] Updated weights for policy 0, policy_version 218097 (0.0010) -[2023-11-28 05:55:13,280][87426] Updated weights for policy 1, policy_version 217680 (0.0011) -[2023-11-28 05:55:13,414][87424] Updated weights for policy 0, policy_version 218107 (0.0011) -[2023-11-28 05:55:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 111550464. Throughput: 0: 2756.4, 1: 2688.0. Samples: 111572764. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:13,445][86177] Avg episode reward: [(0, '-498.790'), (1, '-556.850')] -[2023-11-28 05:55:13,659][87426] Updated weights for policy 1, policy_version 217690 (0.0011) -[2023-11-28 05:55:15,346][87424] Updated weights for policy 0, policy_version 218117 (0.0011) -[2023-11-28 05:55:15,721][87424] Updated weights for policy 0, policy_version 218127 (0.0012) -[2023-11-28 05:55:16,099][87424] Updated weights for policy 0, policy_version 218137 (0.0012) -[2023-11-28 05:55:16,144][87426] Updated weights for policy 1, policy_version 217700 (0.0011) -[2023-11-28 05:55:16,525][87426] Updated weights for policy 1, policy_version 217710 (0.0011) -[2023-11-28 05:55:16,895][87426] Updated weights for policy 1, policy_version 217720 (0.0010) -[2023-11-28 05:55:17,933][87424] Updated weights for policy 0, policy_version 218147 (0.0011) -[2023-11-28 05:55:18,310][87424] Updated weights for policy 0, policy_version 218157 (0.0010) -[2023-11-28 05:55:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 111583232. Throughput: 0: 2773.2, 1: 2660.8. Samples: 111596528. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:18,445][86177] Avg episode reward: [(0, '-497.800'), (1, '-553.490')] -[2023-11-28 05:55:18,691][87424] Updated weights for policy 0, policy_version 218167 (0.0008) -[2023-11-28 05:55:18,932][87426] Updated weights for policy 1, policy_version 217730 (0.0008) -[2023-11-28 05:55:19,317][87426] Updated weights for policy 1, policy_version 217740 (0.0012) -[2023-11-28 05:55:19,685][87426] Updated weights for policy 1, policy_version 217750 (0.0012) -[2023-11-28 05:55:20,062][87426] Updated weights for policy 1, policy_version 217760 (0.0012) -[2023-11-28 05:55:20,684][87424] Updated weights for policy 0, policy_version 218177 (0.0008) -[2023-11-28 05:55:21,075][87424] Updated weights for policy 0, policy_version 218187 (0.0012) -[2023-11-28 05:55:21,460][87424] Updated weights for policy 0, policy_version 218197 (0.0008) -[2023-11-28 05:55:21,839][87424] Updated weights for policy 0, policy_version 218207 (0.0009) -[2023-11-28 05:55:22,385][87426] Updated weights for policy 1, policy_version 217770 (0.0009) -[2023-11-28 05:55:22,768][87426] Updated weights for policy 1, policy_version 217780 (0.0010) -[2023-11-28 05:55:23,148][87426] Updated weights for policy 1, policy_version 217790 (0.0011) -[2023-11-28 05:55:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 111616000. Throughput: 0: 2763.4, 1: 2629.3. Samples: 111628804. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:23,445][86177] Avg episode reward: [(0, '-496.230'), (1, '-550.540')] -[2023-11-28 05:55:24,384][87424] Updated weights for policy 0, policy_version 218217 (0.0008) -[2023-11-28 05:55:24,763][87424] Updated weights for policy 0, policy_version 218227 (0.0009) -[2023-11-28 05:55:24,965][87426] Updated weights for policy 1, policy_version 217800 (0.0012) -[2023-11-28 05:55:25,150][87424] Updated weights for policy 0, policy_version 218237 (0.0011) -[2023-11-28 05:55:25,351][87426] Updated weights for policy 1, policy_version 217810 (0.0012) -[2023-11-28 05:55:25,731][87426] Updated weights for policy 1, policy_version 217820 (0.0011) -[2023-11-28 05:55:27,262][87424] Updated weights for policy 0, policy_version 218247 (0.0011) -[2023-11-28 05:55:27,488][87426] Updated weights for policy 1, policy_version 217830 (0.0012) -[2023-11-28 05:55:27,636][87424] Updated weights for policy 0, policy_version 218257 (0.0011) -[2023-11-28 05:55:27,868][87426] Updated weights for policy 1, policy_version 217840 (0.0012) -[2023-11-28 05:55:28,031][87424] Updated weights for policy 0, policy_version 218267 (0.0009) -[2023-11-28 05:55:28,247][87426] Updated weights for policy 1, policy_version 217850 (0.0012) -[2023-11-28 05:55:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 111640576. Throughput: 0: 2762.7, 1: 2651.7. Samples: 111654188. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:28,445][86177] Avg episode reward: [(0, '-493.330'), (1, '-512.180')] -[2023-11-28 05:55:30,514][87424] Updated weights for policy 0, policy_version 218277 (0.0008) -[2023-11-28 05:55:30,668][87426] Updated weights for policy 1, policy_version 217860 (0.0011) -[2023-11-28 05:55:30,897][87424] Updated weights for policy 0, policy_version 218287 (0.0008) -[2023-11-28 05:55:31,041][87426] Updated weights for policy 1, policy_version 217870 (0.0012) -[2023-11-28 05:55:31,289][87424] Updated weights for policy 0, policy_version 218297 (0.0007) -[2023-11-28 05:55:31,410][87426] Updated weights for policy 1, policy_version 217880 (0.0009) -[2023-11-28 05:55:33,324][87424] Updated weights for policy 0, policy_version 218307 (0.0009) -[2023-11-28 05:55:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 111665152. Throughput: 0: 2737.0, 1: 2647.2. Samples: 111677904. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:33,445][86177] Avg episode reward: [(0, '-492.300'), (1, '-505.780')] -[2023-11-28 05:55:33,703][87424] Updated weights for policy 0, policy_version 218317 (0.0012) -[2023-11-28 05:55:34,020][87426] Updated weights for policy 1, policy_version 217890 (0.0010) -[2023-11-28 05:55:34,090][87424] Updated weights for policy 0, policy_version 218327 (0.0012) -[2023-11-28 05:55:34,391][87426] Updated weights for policy 1, policy_version 217900 (0.0008) -[2023-11-28 05:55:34,784][87426] Updated weights for policy 1, policy_version 217910 (0.0009) -[2023-11-28 05:55:35,151][87426] Updated weights for policy 1, policy_version 217920 (0.0012) -[2023-11-28 05:55:36,261][87424] Updated weights for policy 0, policy_version 218337 (0.0009) -[2023-11-28 05:55:36,658][87424] Updated weights for policy 0, policy_version 218347 (0.0008) -[2023-11-28 05:55:37,027][87424] Updated weights for policy 0, policy_version 218357 (0.0008) -[2023-11-28 05:55:37,127][87426] Updated weights for policy 1, policy_version 217930 (0.0012) -[2023-11-28 05:55:37,407][87424] Updated weights for policy 0, policy_version 218367 (0.0009) -[2023-11-28 05:55:37,503][87426] Updated weights for policy 1, policy_version 217940 (0.0011) -[2023-11-28 05:55:37,872][87426] Updated weights for policy 1, policy_version 217950 (0.0010) -[2023-11-28 05:55:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 111697920. Throughput: 0: 2751.8, 1: 2660.4. Samples: 111710700. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:38,445][86177] Avg episode reward: [(0, '-491.330'), (1, '-504.520')] -[2023-11-28 05:55:39,512][87424] Updated weights for policy 0, policy_version 218377 (0.0012) -[2023-11-28 05:55:39,892][87424] Updated weights for policy 0, policy_version 218387 (0.0011) -[2023-11-28 05:55:39,928][87426] Updated weights for policy 1, policy_version 217960 (0.0009) -[2023-11-28 05:55:40,268][87424] Updated weights for policy 0, policy_version 218397 (0.0010) -[2023-11-28 05:55:40,300][87426] Updated weights for policy 1, policy_version 217970 (0.0011) -[2023-11-28 05:55:40,676][87426] Updated weights for policy 1, policy_version 217980 (0.0012) -[2023-11-28 05:55:42,509][87424] Updated weights for policy 0, policy_version 218407 (0.0011) -[2023-11-28 05:55:42,890][87424] Updated weights for policy 0, policy_version 218417 (0.0012) -[2023-11-28 05:55:43,084][87426] Updated weights for policy 1, policy_version 217990 (0.0010) -[2023-11-28 05:55:43,267][87424] Updated weights for policy 0, policy_version 218427 (0.0010) -[2023-11-28 05:55:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 111714304. Throughput: 0: 2750.1, 1: 2676.9. Samples: 111735128. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:43,445][86177] Avg episode reward: [(0, '-490.650'), (1, '-524.630')] -[2023-11-28 05:55:43,451][87426] Updated weights for policy 1, policy_version 218000 (0.0010) -[2023-11-28 05:55:43,828][87426] Updated weights for policy 1, policy_version 218010 (0.0012) -[2023-11-28 05:55:45,637][87426] Updated weights for policy 1, policy_version 218020 (0.0011) -[2023-11-28 05:55:45,829][87424] Updated weights for policy 0, policy_version 218437 (0.0010) -[2023-11-28 05:55:46,017][87426] Updated weights for policy 1, policy_version 218030 (0.0007) -[2023-11-28 05:55:46,204][87424] Updated weights for policy 0, policy_version 218447 (0.0012) -[2023-11-28 05:55:46,397][87426] Updated weights for policy 1, policy_version 218040 (0.0008) -[2023-11-28 05:55:46,581][87424] Updated weights for policy 0, policy_version 218457 (0.0008) -[2023-11-28 05:55:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 111747072. Throughput: 0: 2703.1, 1: 2694.0. Samples: 111758644. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:48,445][86177] Avg episode reward: [(0, '-491.540'), (1, '-531.660')] -[2023-11-28 05:55:48,768][87426] Updated weights for policy 1, policy_version 218050 (0.0008) -[2023-11-28 05:55:48,960][87424] Updated weights for policy 0, policy_version 218467 (0.0012) -[2023-11-28 05:55:49,152][87426] Updated weights for policy 1, policy_version 218060 (0.0011) -[2023-11-28 05:55:49,338][87424] Updated weights for policy 0, policy_version 218477 (0.0011) -[2023-11-28 05:55:49,536][87426] Updated weights for policy 1, policy_version 218070 (0.0012) -[2023-11-28 05:55:49,744][87424] Updated weights for policy 0, policy_version 218487 (0.0009) -[2023-11-28 05:55:49,914][87426] Updated weights for policy 1, policy_version 218080 (0.0009) -[2023-11-28 05:55:51,993][87424] Updated weights for policy 0, policy_version 218497 (0.0010) -[2023-11-28 05:55:52,317][87426] Updated weights for policy 1, policy_version 218090 (0.0012) -[2023-11-28 05:55:52,384][87424] Updated weights for policy 0, policy_version 218507 (0.0009) -[2023-11-28 05:55:52,691][87426] Updated weights for policy 1, policy_version 218100 (0.0011) -[2023-11-28 05:55:52,759][87424] Updated weights for policy 0, policy_version 218517 (0.0008) -[2023-11-28 05:55:53,072][87426] Updated weights for policy 1, policy_version 218110 (0.0012) -[2023-11-28 05:55:53,140][87424] Updated weights for policy 0, policy_version 218527 (0.0010) -[2023-11-28 05:55:53,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 111779840. Throughput: 0: 2701.7, 1: 2710.5. Samples: 111791064. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:53,445][86177] Avg episode reward: [(0, '-492.470'), (1, '-530.870')] -[2023-11-28 05:55:55,115][87426] Updated weights for policy 1, policy_version 218120 (0.0011) -[2023-11-28 05:55:55,205][87424] Updated weights for policy 0, policy_version 218537 (0.0011) -[2023-11-28 05:55:55,503][87426] Updated weights for policy 1, policy_version 218130 (0.0011) -[2023-11-28 05:55:55,601][87424] Updated weights for policy 0, policy_version 218547 (0.0011) -[2023-11-28 05:55:55,887][87426] Updated weights for policy 1, policy_version 218140 (0.0012) -[2023-11-28 05:55:55,984][87424] Updated weights for policy 0, policy_version 218557 (0.0011) -[2023-11-28 05:55:57,678][87426] Updated weights for policy 1, policy_version 218150 (0.0009) -[2023-11-28 05:55:58,051][87426] Updated weights for policy 1, policy_version 218160 (0.0007) -[2023-11-28 05:55:58,141][87424] Updated weights for policy 0, policy_version 218567 (0.0008) -[2023-11-28 05:55:58,428][87426] Updated weights for policy 1, policy_version 218170 (0.0009) -[2023-11-28 05:55:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 111796224. Throughput: 0: 2692.7, 1: 2737.6. Samples: 111817128. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:55:58,445][86177] Avg episode reward: [(0, '-498.140'), (1, '-529.940')] -[2023-11-28 05:55:58,520][87424] Updated weights for policy 0, policy_version 218577 (0.0008) -[2023-11-28 05:55:58,918][87424] Updated weights for policy 0, policy_version 218587 (0.0008) -[2023-11-28 05:56:00,567][87426] Updated weights for policy 1, policy_version 218180 (0.0011) -[2023-11-28 05:56:00,943][87426] Updated weights for policy 1, policy_version 218190 (0.0009) -[2023-11-28 05:56:01,324][87426] Updated weights for policy 1, policy_version 218200 (0.0008) -[2023-11-28 05:56:01,342][87424] Updated weights for policy 0, policy_version 218597 (0.0010) -[2023-11-28 05:56:01,719][87424] Updated weights for policy 0, policy_version 218607 (0.0009) -[2023-11-28 05:56:02,102][87424] Updated weights for policy 0, policy_version 218617 (0.0012) -[2023-11-28 05:56:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 111828992. Throughput: 0: 2684.3, 1: 2747.8. Samples: 111840972. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:56:03,445][86177] Avg episode reward: [(0, '-498.600'), (1, '-521.170')] -[2023-11-28 05:56:03,576][87426] Updated weights for policy 1, policy_version 218210 (0.0008) -[2023-11-28 05:56:03,954][87426] Updated weights for policy 1, policy_version 218220 (0.0008) -[2023-11-28 05:56:04,284][87424] Updated weights for policy 0, policy_version 218627 (0.0012) -[2023-11-28 05:56:04,333][87426] Updated weights for policy 1, policy_version 218230 (0.0007) -[2023-11-28 05:56:04,669][87424] Updated weights for policy 0, policy_version 218637 (0.0012) -[2023-11-28 05:56:04,708][87426] Updated weights for policy 1, policy_version 218240 (0.0010) -[2023-11-28 05:56:05,043][87424] Updated weights for policy 0, policy_version 218647 (0.0012) -[2023-11-28 05:56:06,832][87426] Updated weights for policy 1, policy_version 218250 (0.0012) -[2023-11-28 05:56:07,207][87426] Updated weights for policy 1, policy_version 218260 (0.0012) -[2023-11-28 05:56:07,531][87424] Updated weights for policy 0, policy_version 218657 (0.0012) -[2023-11-28 05:56:07,590][87426] Updated weights for policy 1, policy_version 218270 (0.0012) -[2023-11-28 05:56:07,921][87424] Updated weights for policy 0, policy_version 218667 (0.0012) -[2023-11-28 05:56:08,293][87424] Updated weights for policy 0, policy_version 218677 (0.0012) -[2023-11-28 05:56:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 111853568. Throughput: 0: 2677.6, 1: 2783.2. Samples: 111874540. Policy #0 lag: (min: 31.0, avg: 47.5, max: 77.0) -[2023-11-28 05:56:08,445][86177] Avg episode reward: [(0, '-517.320'), (1, '-513.190')] -[2023-11-28 05:56:08,676][87424] Updated weights for policy 0, policy_version 218687 (0.0009) -[2023-11-28 05:56:09,618][87426] Updated weights for policy 1, policy_version 218280 (0.0008) -[2023-11-28 05:56:09,988][87426] Updated weights for policy 1, policy_version 218290 (0.0010) -[2023-11-28 05:56:10,371][87426] Updated weights for policy 1, policy_version 218300 (0.0010) -[2023-11-28 05:56:11,195][87424] Updated weights for policy 0, policy_version 218697 (0.0009) -[2023-11-28 05:56:11,569][87424] Updated weights for policy 0, policy_version 218707 (0.0008) -[2023-11-28 05:56:11,952][87424] Updated weights for policy 0, policy_version 218717 (0.0009) -[2023-11-28 05:56:12,774][87426] Updated weights for policy 1, policy_version 218310 (0.0011) -[2023-11-28 05:56:13,150][87426] Updated weights for policy 1, policy_version 218320 (0.0012) -[2023-11-28 05:56:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 111878144. Throughput: 0: 2675.7, 1: 2747.6. Samples: 111898240. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:13,445][86177] Avg episode reward: [(0, '-516.880'), (1, '-513.090')] -[2023-11-28 05:56:13,531][87426] Updated weights for policy 1, policy_version 218330 (0.0012) -[2023-11-28 05:56:13,973][87424] Updated weights for policy 0, policy_version 218727 (0.0012) -[2023-11-28 05:56:14,350][87424] Updated weights for policy 0, policy_version 218737 (0.0012) -[2023-11-28 05:56:14,738][87424] Updated weights for policy 0, policy_version 218747 (0.0012) -[2023-11-28 05:56:15,722][87426] Updated weights for policy 1, policy_version 218340 (0.0010) -[2023-11-28 05:56:16,100][87426] Updated weights for policy 1, policy_version 218350 (0.0011) -[2023-11-28 05:56:16,477][87426] Updated weights for policy 1, policy_version 218360 (0.0008) -[2023-11-28 05:56:16,864][87424] Updated weights for policy 0, policy_version 218757 (0.0012) -[2023-11-28 05:56:17,242][87424] Updated weights for policy 0, policy_version 218767 (0.0011) -[2023-11-28 05:56:17,629][87424] Updated weights for policy 0, policy_version 218777 (0.0012) -[2023-11-28 05:56:18,436][87426] Updated weights for policy 1, policy_version 218370 (0.0010) -[2023-11-28 05:56:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 111910912. Throughput: 0: 2681.9, 1: 2746.7. Samples: 111922192. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:18,446][86177] Avg episode reward: [(0, '-514.580'), (1, '-514.560')] -[2023-11-28 05:56:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000218784_56008704.pth... -[2023-11-28 05:56:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000216256_55361536.pth -[2023-11-28 05:56:18,812][87426] Updated weights for policy 1, policy_version 218380 (0.0009) -[2023-11-28 05:56:19,193][87426] Updated weights for policy 1, policy_version 218390 (0.0008) -[2023-11-28 05:56:19,444][87424] Updated weights for policy 0, policy_version 218787 (0.0010) -[2023-11-28 05:56:19,576][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000218400_55910400.pth... -[2023-11-28 05:56:19,576][87426] Updated weights for policy 1, policy_version 218400 (0.0009) -[2023-11-28 05:56:19,621][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000215840_55255040.pth -[2023-11-28 05:56:19,822][87424] Updated weights for policy 0, policy_version 218797 (0.0008) -[2023-11-28 05:56:20,204][87424] Updated weights for policy 0, policy_version 218807 (0.0010) -[2023-11-28 05:56:22,062][87426] Updated weights for policy 1, policy_version 218410 (0.0010) -[2023-11-28 05:56:22,438][87426] Updated weights for policy 1, policy_version 218420 (0.0011) -[2023-11-28 05:56:22,571][87424] Updated weights for policy 0, policy_version 218817 (0.0010) -[2023-11-28 05:56:22,841][87426] Updated weights for policy 1, policy_version 218430 (0.0011) -[2023-11-28 05:56:22,949][87424] Updated weights for policy 0, policy_version 218827 (0.0011) -[2023-11-28 05:56:23,327][87424] Updated weights for policy 0, policy_version 218837 (0.0010) -[2023-11-28 05:56:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 111935488. Throughput: 0: 2686.3, 1: 2749.3. Samples: 111955304. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:23,446][86177] Avg episode reward: [(0, '-514.570'), (1, '-508.500')] -[2023-11-28 05:56:23,709][87424] Updated weights for policy 0, policy_version 218847 (0.0011) -[2023-11-28 05:56:25,162][87426] Updated weights for policy 1, policy_version 218440 (0.0011) -[2023-11-28 05:56:25,407][87424] Updated weights for policy 0, policy_version 218857 (0.0008) -[2023-11-28 05:56:25,538][87426] Updated weights for policy 1, policy_version 218450 (0.0010) -[2023-11-28 05:56:25,795][87424] Updated weights for policy 0, policy_version 218867 (0.0009) -[2023-11-28 05:56:25,917][87426] Updated weights for policy 1, policy_version 218460 (0.0008) -[2023-11-28 05:56:26,170][87424] Updated weights for policy 0, policy_version 218877 (0.0010) -[2023-11-28 05:56:27,874][87424] Updated weights for policy 0, policy_version 218887 (0.0010) -[2023-11-28 05:56:28,021][87426] Updated weights for policy 1, policy_version 218470 (0.0009) -[2023-11-28 05:56:28,256][87424] Updated weights for policy 0, policy_version 218897 (0.0007) -[2023-11-28 05:56:28,397][87426] Updated weights for policy 1, policy_version 218480 (0.0007) -[2023-11-28 05:56:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 111960064. Throughput: 0: 2700.4, 1: 2737.2. Samples: 111979820. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:28,445][86177] Avg episode reward: [(0, '-496.390'), (1, '-518.600')] -[2023-11-28 05:56:28,638][87424] Updated weights for policy 0, policy_version 218907 (0.0009) -[2023-11-28 05:56:28,782][87426] Updated weights for policy 1, policy_version 218490 (0.0007) -[2023-11-28 05:56:30,577][87424] Updated weights for policy 0, policy_version 218917 (0.0009) -[2023-11-28 05:56:30,963][87424] Updated weights for policy 0, policy_version 218927 (0.0009) -[2023-11-28 05:56:31,055][87426] Updated weights for policy 1, policy_version 218500 (0.0011) -[2023-11-28 05:56:31,335][87424] Updated weights for policy 0, policy_version 218937 (0.0011) -[2023-11-28 05:56:31,440][87426] Updated weights for policy 1, policy_version 218510 (0.0011) -[2023-11-28 05:56:31,810][87426] Updated weights for policy 1, policy_version 218520 (0.0010) -[2023-11-28 05:56:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 111992832. Throughput: 0: 2752.4, 1: 2729.2. Samples: 112005316. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:33,445][86177] Avg episode reward: [(0, '-492.280'), (1, '-514.490')] -[2023-11-28 05:56:33,658][87426] Updated weights for policy 1, policy_version 218530 (0.0010) -[2023-11-28 05:56:33,784][87424] Updated weights for policy 0, policy_version 218947 (0.0011) -[2023-11-28 05:56:34,037][87426] Updated weights for policy 1, policy_version 218540 (0.0012) -[2023-11-28 05:56:34,175][87424] Updated weights for policy 0, policy_version 218957 (0.0009) -[2023-11-28 05:56:34,413][87426] Updated weights for policy 1, policy_version 218550 (0.0009) -[2023-11-28 05:56:34,543][87424] Updated weights for policy 0, policy_version 218967 (0.0009) -[2023-11-28 05:56:34,784][87426] Updated weights for policy 1, policy_version 218560 (0.0009) -[2023-11-28 05:56:37,006][87426] Updated weights for policy 1, policy_version 218570 (0.0008) -[2023-11-28 05:56:37,149][87424] Updated weights for policy 0, policy_version 218977 (0.0009) -[2023-11-28 05:56:37,395][87426] Updated weights for policy 1, policy_version 218580 (0.0009) -[2023-11-28 05:56:37,528][87424] Updated weights for policy 0, policy_version 218987 (0.0011) -[2023-11-28 05:56:37,773][87426] Updated weights for policy 1, policy_version 218590 (0.0009) -[2023-11-28 05:56:37,914][87424] Updated weights for policy 0, policy_version 218997 (0.0010) -[2023-11-28 05:56:38,301][87424] Updated weights for policy 0, policy_version 219007 (0.0007) -[2023-11-28 05:56:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 112025600. Throughput: 0: 2727.7, 1: 2738.3. Samples: 112037036. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:38,445][86177] Avg episode reward: [(0, '-496.140'), (1, '-556.520')] -[2023-11-28 05:56:39,690][87426] Updated weights for policy 1, policy_version 218600 (0.0011) -[2023-11-28 05:56:40,084][87426] Updated weights for policy 1, policy_version 218610 (0.0012) -[2023-11-28 05:56:40,325][87424] Updated weights for policy 0, policy_version 219017 (0.0011) -[2023-11-28 05:56:40,462][87426] Updated weights for policy 1, policy_version 218620 (0.0012) -[2023-11-28 05:56:40,714][87424] Updated weights for policy 0, policy_version 219027 (0.0011) -[2023-11-28 05:56:41,087][87424] Updated weights for policy 0, policy_version 219037 (0.0012) -[2023-11-28 05:56:42,518][87426] Updated weights for policy 1, policy_version 218630 (0.0011) -[2023-11-28 05:56:42,893][87426] Updated weights for policy 1, policy_version 218640 (0.0012) -[2023-11-28 05:56:43,272][87426] Updated weights for policy 1, policy_version 218650 (0.0012) -[2023-11-28 05:56:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 112041984. Throughput: 0: 2711.3, 1: 2727.7. Samples: 112061884. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:43,445][86177] Avg episode reward: [(0, '-497.590'), (1, '-548.170')] -[2023-11-28 05:56:43,544][87424] Updated weights for policy 0, policy_version 219047 (0.0010) -[2023-11-28 05:56:43,924][87424] Updated weights for policy 0, policy_version 219057 (0.0007) -[2023-11-28 05:56:44,319][87424] Updated weights for policy 0, policy_version 219067 (0.0007) -[2023-11-28 05:56:45,714][87426] Updated weights for policy 1, policy_version 218660 (0.0011) -[2023-11-28 05:56:46,093][87426] Updated weights for policy 1, policy_version 218670 (0.0011) -[2023-11-28 05:56:46,466][87426] Updated weights for policy 1, policy_version 218680 (0.0012) -[2023-11-28 05:56:46,839][87424] Updated weights for policy 0, policy_version 219077 (0.0008) -[2023-11-28 05:56:47,219][87424] Updated weights for policy 0, policy_version 219087 (0.0008) -[2023-11-28 05:56:47,595][87424] Updated weights for policy 0, policy_version 219097 (0.0012) -[2023-11-28 05:56:48,196][87426] Updated weights for policy 1, policy_version 218690 (0.0012) -[2023-11-28 05:56:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 112074752. Throughput: 0: 2705.5, 1: 2732.3. Samples: 112085672. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:48,446][86177] Avg episode reward: [(0, '-500.130'), (1, '-546.580')] -[2023-11-28 05:56:48,571][87426] Updated weights for policy 1, policy_version 218700 (0.0012) -[2023-11-28 05:56:48,957][87426] Updated weights for policy 1, policy_version 218710 (0.0012) -[2023-11-28 05:56:49,331][87426] Updated weights for policy 1, policy_version 218720 (0.0011) -[2023-11-28 05:56:49,788][87424] Updated weights for policy 0, policy_version 219107 (0.0011) -[2023-11-28 05:56:50,173][87424] Updated weights for policy 0, policy_version 219117 (0.0012) -[2023-11-28 05:56:50,550][87424] Updated weights for policy 0, policy_version 219127 (0.0011) -[2023-11-28 05:56:51,453][87426] Updated weights for policy 1, policy_version 218730 (0.0010) -[2023-11-28 05:56:51,830][87426] Updated weights for policy 1, policy_version 218740 (0.0009) -[2023-11-28 05:56:52,209][87426] Updated weights for policy 1, policy_version 218750 (0.0008) -[2023-11-28 05:56:53,120][87424] Updated weights for policy 0, policy_version 219137 (0.0012) -[2023-11-28 05:56:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 112099328. Throughput: 0: 2687.2, 1: 2725.7. Samples: 112118120. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:53,445][86177] Avg episode reward: [(0, '-500.260'), (1, '-547.260')] -[2023-11-28 05:56:53,497][87424] Updated weights for policy 0, policy_version 219147 (0.0010) -[2023-11-28 05:56:53,883][87424] Updated weights for policy 0, policy_version 219157 (0.0010) -[2023-11-28 05:56:54,259][87424] Updated weights for policy 0, policy_version 219167 (0.0008) -[2023-11-28 05:56:54,454][87426] Updated weights for policy 1, policy_version 218760 (0.0008) -[2023-11-28 05:56:54,828][87426] Updated weights for policy 1, policy_version 218770 (0.0007) -[2023-11-28 05:56:55,219][87426] Updated weights for policy 1, policy_version 218780 (0.0008) -[2023-11-28 05:56:56,821][87424] Updated weights for policy 0, policy_version 219177 (0.0010) -[2023-11-28 05:56:57,197][87424] Updated weights for policy 0, policy_version 219187 (0.0010) -[2023-11-28 05:56:57,295][87426] Updated weights for policy 1, policy_version 218790 (0.0011) -[2023-11-28 05:56:57,580][87424] Updated weights for policy 0, policy_version 219197 (0.0007) -[2023-11-28 05:56:57,691][87426] Updated weights for policy 1, policy_version 218800 (0.0012) -[2023-11-28 05:56:58,062][87426] Updated weights for policy 1, policy_version 218810 (0.0011) -[2023-11-28 05:56:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 112132096. Throughput: 0: 2672.2, 1: 2734.8. Samples: 112141556. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:56:58,445][86177] Avg episode reward: [(0, '-498.620'), (1, '-521.130')] -[2023-11-28 05:56:59,243][87424] Updated weights for policy 0, policy_version 219207 (0.0010) -[2023-11-28 05:56:59,613][87424] Updated weights for policy 0, policy_version 219217 (0.0011) -[2023-11-28 05:56:59,997][87424] Updated weights for policy 0, policy_version 219227 (0.0012) -[2023-11-28 05:57:00,283][87426] Updated weights for policy 1, policy_version 218820 (0.0010) -[2023-11-28 05:57:00,661][87426] Updated weights for policy 1, policy_version 218830 (0.0008) -[2023-11-28 05:57:01,049][87426] Updated weights for policy 1, policy_version 218840 (0.0007) -[2023-11-28 05:57:02,325][87424] Updated weights for policy 0, policy_version 219237 (0.0011) -[2023-11-28 05:57:02,707][87424] Updated weights for policy 0, policy_version 219247 (0.0011) -[2023-11-28 05:57:03,049][87426] Updated weights for policy 1, policy_version 218850 (0.0008) -[2023-11-28 05:57:03,088][87424] Updated weights for policy 0, policy_version 219257 (0.0010) -[2023-11-28 05:57:03,431][87426] Updated weights for policy 1, policy_version 218860 (0.0011) -[2023-11-28 05:57:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 112156672. Throughput: 0: 2685.4, 1: 2740.6. Samples: 112166356. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:57:03,445][86177] Avg episode reward: [(0, '-499.420'), (1, '-518.330')] -[2023-11-28 05:57:03,809][87426] Updated weights for policy 1, policy_version 218870 (0.0012) -[2023-11-28 05:57:04,182][87426] Updated weights for policy 1, policy_version 218880 (0.0011) -[2023-11-28 05:57:04,846][87424] Updated weights for policy 0, policy_version 219267 (0.0011) -[2023-11-28 05:57:05,235][87424] Updated weights for policy 0, policy_version 219277 (0.0010) -[2023-11-28 05:57:05,618][87424] Updated weights for policy 0, policy_version 219287 (0.0011) -[2023-11-28 05:57:06,664][87426] Updated weights for policy 1, policy_version 218890 (0.0011) -[2023-11-28 05:57:07,042][87426] Updated weights for policy 1, policy_version 218900 (0.0011) -[2023-11-28 05:57:07,417][87426] Updated weights for policy 1, policy_version 218910 (0.0009) -[2023-11-28 05:57:08,035][87424] Updated weights for policy 0, policy_version 219297 (0.0011) -[2023-11-28 05:57:08,418][87424] Updated weights for policy 0, policy_version 219307 (0.0008) -[2023-11-28 05:57:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 112181248. Throughput: 0: 2676.3, 1: 2727.7. Samples: 112198484. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:57:08,445][86177] Avg episode reward: [(0, '-498.830'), (1, '-518.370')] -[2023-11-28 05:57:08,803][87424] Updated weights for policy 0, policy_version 219317 (0.0008) -[2023-11-28 05:57:09,193][87424] Updated weights for policy 0, policy_version 219327 (0.0009) -[2023-11-28 05:57:09,986][87426] Updated weights for policy 1, policy_version 218920 (0.0009) -[2023-11-28 05:57:10,366][87426] Updated weights for policy 1, policy_version 218930 (0.0008) -[2023-11-28 05:57:10,750][87426] Updated weights for policy 1, policy_version 218940 (0.0008) -[2023-11-28 05:57:11,650][87424] Updated weights for policy 0, policy_version 219337 (0.0008) -[2023-11-28 05:57:12,028][87424] Updated weights for policy 0, policy_version 219347 (0.0010) -[2023-11-28 05:57:12,410][87424] Updated weights for policy 0, policy_version 219357 (0.0009) -[2023-11-28 05:57:13,204][87426] Updated weights for policy 1, policy_version 218950 (0.0008) -[2023-11-28 05:57:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 112205824. Throughput: 0: 2654.2, 1: 2732.7. Samples: 112222232. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:57:13,445][86177] Avg episode reward: [(0, '-537.820'), (1, '-512.690')] -[2023-11-28 05:57:13,587][87426] Updated weights for policy 1, policy_version 218960 (0.0008) -[2023-11-28 05:57:13,963][87426] Updated weights for policy 1, policy_version 218970 (0.0007) -[2023-11-28 05:57:14,688][87424] Updated weights for policy 0, policy_version 219367 (0.0011) -[2023-11-28 05:57:15,069][87424] Updated weights for policy 0, policy_version 219377 (0.0012) -[2023-11-28 05:57:15,438][87424] Updated weights for policy 0, policy_version 219387 (0.0012) -[2023-11-28 05:57:15,941][87426] Updated weights for policy 1, policy_version 218980 (0.0009) -[2023-11-28 05:57:16,306][87426] Updated weights for policy 1, policy_version 218990 (0.0012) -[2023-11-28 05:57:16,691][87426] Updated weights for policy 1, policy_version 219000 (0.0012) -[2023-11-28 05:57:17,593][87424] Updated weights for policy 0, policy_version 219397 (0.0011) -[2023-11-28 05:57:17,972][87424] Updated weights for policy 0, policy_version 219407 (0.0012) -[2023-11-28 05:57:18,350][87424] Updated weights for policy 0, policy_version 219417 (0.0012) -[2023-11-28 05:57:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 112230400. Throughput: 0: 2627.9, 1: 2720.7. Samples: 112246004. Policy #0 lag: (min: 31.0, avg: 54.5, max: 63.0) -[2023-11-28 05:57:18,445][86177] Avg episode reward: [(0, '-576.930'), (1, '-509.580')] -[2023-11-28 05:57:18,984][87426] Updated weights for policy 1, policy_version 219010 (0.0012) -[2023-11-28 05:57:19,358][87426] Updated weights for policy 1, policy_version 219020 (0.0012) -[2023-11-28 05:57:19,734][87426] Updated weights for policy 1, policy_version 219030 (0.0011) -[2023-11-28 05:57:20,114][87426] Updated weights for policy 1, policy_version 219040 (0.0012) -[2023-11-28 05:57:20,565][87424] Updated weights for policy 0, policy_version 219427 (0.0011) -[2023-11-28 05:57:20,939][87424] Updated weights for policy 0, policy_version 219437 (0.0008) -[2023-11-28 05:57:21,317][87424] Updated weights for policy 0, policy_version 219447 (0.0011) -[2023-11-28 05:57:22,311][87426] Updated weights for policy 1, policy_version 219050 (0.0010) -[2023-11-28 05:57:22,689][87426] Updated weights for policy 1, policy_version 219060 (0.0007) -[2023-11-28 05:57:23,063][87426] Updated weights for policy 1, policy_version 219070 (0.0011) -[2023-11-28 05:57:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 112263168. Throughput: 0: 2657.2, 1: 2716.1. Samples: 112278836. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:57:23,445][86177] Avg episode reward: [(0, '-573.570'), (1, '-519.510')] -[2023-11-28 05:57:23,665][87424] Updated weights for policy 0, policy_version 219457 (0.0012) -[2023-11-28 05:57:24,040][87424] Updated weights for policy 0, policy_version 219467 (0.0011) -[2023-11-28 05:57:24,430][87424] Updated weights for policy 0, policy_version 219477 (0.0012) -[2023-11-28 05:57:24,803][87424] Updated weights for policy 0, policy_version 219487 (0.0009) -[2023-11-28 05:57:24,925][87426] Updated weights for policy 1, policy_version 219080 (0.0009) -[2023-11-28 05:57:25,306][87426] Updated weights for policy 1, policy_version 219090 (0.0007) -[2023-11-28 05:57:25,681][87426] Updated weights for policy 1, policy_version 219100 (0.0007) -[2023-11-28 05:57:27,154][87424] Updated weights for policy 0, policy_version 219497 (0.0011) -[2023-11-28 05:57:27,410][87426] Updated weights for policy 1, policy_version 219110 (0.0010) -[2023-11-28 05:57:27,537][87424] Updated weights for policy 0, policy_version 219507 (0.0009) -[2023-11-28 05:57:27,789][87426] Updated weights for policy 1, policy_version 219120 (0.0007) -[2023-11-28 05:57:27,918][87424] Updated weights for policy 0, policy_version 219517 (0.0007) -[2023-11-28 05:57:28,169][87426] Updated weights for policy 1, policy_version 219130 (0.0007) -[2023-11-28 05:57:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 112295936. Throughput: 0: 2665.1, 1: 2722.8. Samples: 112304340. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:57:28,445][86177] Avg episode reward: [(0, '-573.890'), (1, '-513.650')] -[2023-11-28 05:57:29,722][87424] Updated weights for policy 0, policy_version 219527 (0.0010) -[2023-11-28 05:57:30,108][87424] Updated weights for policy 0, policy_version 219537 (0.0009) -[2023-11-28 05:57:30,340][87426] Updated weights for policy 1, policy_version 219140 (0.0009) -[2023-11-28 05:57:30,483][87424] Updated weights for policy 0, policy_version 219547 (0.0009) -[2023-11-28 05:57:30,711][87426] Updated weights for policy 1, policy_version 219150 (0.0009) -[2023-11-28 05:57:31,095][87426] Updated weights for policy 1, policy_version 219160 (0.0008) -[2023-11-28 05:57:32,429][87424] Updated weights for policy 0, policy_version 219557 (0.0009) -[2023-11-28 05:57:32,824][87424] Updated weights for policy 0, policy_version 219567 (0.0009) -[2023-11-28 05:57:33,194][87424] Updated weights for policy 0, policy_version 219577 (0.0012) -[2023-11-28 05:57:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 112312320. Throughput: 0: 2682.1, 1: 2734.0. Samples: 112329396. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:57:33,445][86177] Avg episode reward: [(0, '-534.110'), (1, '-514.400')] -[2023-11-28 05:57:33,536][87426] Updated weights for policy 1, policy_version 219170 (0.0007) -[2023-11-28 05:57:33,911][87426] Updated weights for policy 1, policy_version 219180 (0.0007) -[2023-11-28 05:57:34,289][87426] Updated weights for policy 1, policy_version 219190 (0.0010) -[2023-11-28 05:57:34,674][87426] Updated weights for policy 1, policy_version 219200 (0.0008) -[2023-11-28 05:57:35,581][87424] Updated weights for policy 0, policy_version 219587 (0.0012) -[2023-11-28 05:57:35,961][87424] Updated weights for policy 0, policy_version 219597 (0.0012) -[2023-11-28 05:57:36,359][87424] Updated weights for policy 0, policy_version 219607 (0.0012) -[2023-11-28 05:57:36,613][87426] Updated weights for policy 1, policy_version 219210 (0.0009) -[2023-11-28 05:57:36,992][87426] Updated weights for policy 1, policy_version 219220 (0.0008) -[2023-11-28 05:57:37,373][87426] Updated weights for policy 1, policy_version 219230 (0.0008) -[2023-11-28 05:57:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 112345088. Throughput: 0: 2684.1, 1: 2717.2. Samples: 112361180. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:57:38,445][86177] Avg episode reward: [(0, '-495.100'), (1, '-510.780')] -[2023-11-28 05:57:38,635][87424] Updated weights for policy 0, policy_version 219617 (0.0011) -[2023-11-28 05:57:39,029][87424] Updated weights for policy 0, policy_version 219627 (0.0010) -[2023-11-28 05:57:39,408][87424] Updated weights for policy 0, policy_version 219637 (0.0009) -[2023-11-28 05:57:39,740][87426] Updated weights for policy 1, policy_version 219240 (0.0008) -[2023-11-28 05:57:39,797][87424] Updated weights for policy 0, policy_version 219647 (0.0009) -[2023-11-28 05:57:40,118][87426] Updated weights for policy 1, policy_version 219250 (0.0011) -[2023-11-28 05:57:40,496][87426] Updated weights for policy 1, policy_version 219260 (0.0012) -[2023-11-28 05:57:42,094][87424] Updated weights for policy 0, policy_version 219657 (0.0009) -[2023-11-28 05:57:42,475][87424] Updated weights for policy 0, policy_version 219667 (0.0011) -[2023-11-28 05:57:42,659][87426] Updated weights for policy 1, policy_version 219270 (0.0011) -[2023-11-28 05:57:42,856][87424] Updated weights for policy 0, policy_version 219677 (0.0012) -[2023-11-28 05:57:43,038][87426] Updated weights for policy 1, policy_version 219280 (0.0011) -[2023-11-28 05:57:43,414][87426] Updated weights for policy 1, policy_version 219290 (0.0011) -[2023-11-28 05:57:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 112369664. Throughput: 0: 2697.7, 1: 2727.2. Samples: 112385676. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:57:43,445][86177] Avg episode reward: [(0, '-501.030'), (1, '-512.990')] -[2023-11-28 05:57:44,926][87424] Updated weights for policy 0, policy_version 219687 (0.0011) -[2023-11-28 05:57:45,271][87426] Updated weights for policy 1, policy_version 219300 (0.0009) -[2023-11-28 05:57:45,299][87424] Updated weights for policy 0, policy_version 219697 (0.0012) -[2023-11-28 05:57:45,650][87426] Updated weights for policy 1, policy_version 219310 (0.0009) -[2023-11-28 05:57:45,685][87424] Updated weights for policy 0, policy_version 219707 (0.0012) -[2023-11-28 05:57:46,034][87426] Updated weights for policy 1, policy_version 219320 (0.0008) -[2023-11-28 05:57:47,544][87424] Updated weights for policy 0, policy_version 219717 (0.0009) -[2023-11-28 05:57:47,929][87424] Updated weights for policy 0, policy_version 219727 (0.0007) -[2023-11-28 05:57:47,956][87426] Updated weights for policy 1, policy_version 219330 (0.0011) -[2023-11-28 05:57:48,306][87424] Updated weights for policy 0, policy_version 219737 (0.0008) -[2023-11-28 05:57:48,327][87426] Updated weights for policy 1, policy_version 219340 (0.0012) -[2023-11-28 05:57:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 112394240. Throughput: 0: 2703.6, 1: 2732.1. Samples: 112410964. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:57:48,445][86177] Avg episode reward: [(0, '-542.110'), (1, '-506.370')] -[2023-11-28 05:57:48,705][87426] Updated weights for policy 1, policy_version 219350 (0.0009) -[2023-11-28 05:57:49,087][87426] Updated weights for policy 1, policy_version 219360 (0.0008) -[2023-11-28 05:57:50,505][87424] Updated weights for policy 0, policy_version 219747 (0.0008) -[2023-11-28 05:57:50,885][87424] Updated weights for policy 0, policy_version 219757 (0.0011) -[2023-11-28 05:57:51,271][87424] Updated weights for policy 0, policy_version 219767 (0.0010) -[2023-11-28 05:57:51,420][87426] Updated weights for policy 1, policy_version 219370 (0.0012) -[2023-11-28 05:57:51,796][87426] Updated weights for policy 1, policy_version 219380 (0.0011) -[2023-11-28 05:57:52,176][87426] Updated weights for policy 1, policy_version 219390 (0.0010) -[2023-11-28 05:57:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 112427008. Throughput: 0: 2702.9, 1: 2742.1. Samples: 112443512. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:57:53,445][86177] Avg episode reward: [(0, '-541.680'), (1, '-531.140')] -[2023-11-28 05:57:53,730][87424] Updated weights for policy 0, policy_version 219777 (0.0012) -[2023-11-28 05:57:54,116][87424] Updated weights for policy 0, policy_version 219787 (0.0009) -[2023-11-28 05:57:54,495][87426] Updated weights for policy 1, policy_version 219400 (0.0010) -[2023-11-28 05:57:54,503][87424] Updated weights for policy 0, policy_version 219797 (0.0011) -[2023-11-28 05:57:54,876][87426] Updated weights for policy 1, policy_version 219410 (0.0012) -[2023-11-28 05:57:54,894][87424] Updated weights for policy 0, policy_version 219807 (0.0012) -[2023-11-28 05:57:55,256][87426] Updated weights for policy 1, policy_version 219420 (0.0011) -[2023-11-28 05:57:57,045][87424] Updated weights for policy 0, policy_version 219817 (0.0011) -[2023-11-28 05:57:57,171][87426] Updated weights for policy 1, policy_version 219430 (0.0011) -[2023-11-28 05:57:57,427][87424] Updated weights for policy 0, policy_version 219827 (0.0011) -[2023-11-28 05:57:57,560][87426] Updated weights for policy 1, policy_version 219440 (0.0008) -[2023-11-28 05:57:57,807][87424] Updated weights for policy 0, policy_version 219837 (0.0012) -[2023-11-28 05:57:57,933][87426] Updated weights for policy 1, policy_version 219450 (0.0007) -[2023-11-28 05:57:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 112459776. Throughput: 0: 2706.1, 1: 2746.3. Samples: 112467592. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:57:58,445][86177] Avg episode reward: [(0, '-541.950'), (1, '-529.210')] -[2023-11-28 05:57:59,443][87424] Updated weights for policy 0, policy_version 219847 (0.0011) -[2023-11-28 05:57:59,829][87424] Updated weights for policy 0, policy_version 219857 (0.0012) -[2023-11-28 05:58:00,217][87424] Updated weights for policy 0, policy_version 219867 (0.0011) -[2023-11-28 05:58:00,241][87426] Updated weights for policy 1, policy_version 219460 (0.0009) -[2023-11-28 05:58:00,621][87426] Updated weights for policy 1, policy_version 219470 (0.0010) -[2023-11-28 05:58:00,993][87426] Updated weights for policy 1, policy_version 219480 (0.0010) -[2023-11-28 05:58:02,677][87424] Updated weights for policy 0, policy_version 219877 (0.0010) -[2023-11-28 05:58:03,037][87426] Updated weights for policy 1, policy_version 219490 (0.0008) -[2023-11-28 05:58:03,061][87424] Updated weights for policy 0, policy_version 219887 (0.0010) -[2023-11-28 05:58:03,416][87426] Updated weights for policy 1, policy_version 219500 (0.0010) -[2023-11-28 05:58:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 112476160. Throughput: 0: 2734.0, 1: 2752.3. Samples: 112492888. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:58:03,445][86177] Avg episode reward: [(0, '-544.430'), (1, '-533.310')] -[2023-11-28 05:58:03,446][87424] Updated weights for policy 0, policy_version 219897 (0.0011) -[2023-11-28 05:58:03,792][87426] Updated weights for policy 1, policy_version 219510 (0.0011) -[2023-11-28 05:58:04,173][87426] Updated weights for policy 1, policy_version 219520 (0.0012) -[2023-11-28 05:58:05,874][87424] Updated weights for policy 0, policy_version 219907 (0.0009) -[2023-11-28 05:58:06,263][87424] Updated weights for policy 0, policy_version 219917 (0.0011) -[2023-11-28 05:58:06,324][87426] Updated weights for policy 1, policy_version 219530 (0.0010) -[2023-11-28 05:58:06,643][87424] Updated weights for policy 0, policy_version 219927 (0.0008) -[2023-11-28 05:58:06,702][87426] Updated weights for policy 1, policy_version 219540 (0.0009) -[2023-11-28 05:58:07,077][87426] Updated weights for policy 1, policy_version 219550 (0.0012) -[2023-11-28 05:58:08,309][87424] Updated weights for policy 0, policy_version 219937 (0.0010) -[2023-11-28 05:58:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 112508928. Throughput: 0: 2726.7, 1: 2764.8. Samples: 112525952. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:58:08,445][86177] Avg episode reward: [(0, '-504.220'), (1, '-538.600')] -[2023-11-28 05:58:08,686][87424] Updated weights for policy 0, policy_version 219947 (0.0010) -[2023-11-28 05:58:09,055][87426] Updated weights for policy 1, policy_version 219560 (0.0009) -[2023-11-28 05:58:09,073][87424] Updated weights for policy 0, policy_version 219957 (0.0010) -[2023-11-28 05:58:09,434][87426] Updated weights for policy 1, policy_version 219570 (0.0008) -[2023-11-28 05:58:09,451][87424] Updated weights for policy 0, policy_version 219967 (0.0008) -[2023-11-28 05:58:09,819][87426] Updated weights for policy 1, policy_version 219580 (0.0008) -[2023-11-28 05:58:11,832][87426] Updated weights for policy 1, policy_version 219590 (0.0012) -[2023-11-28 05:58:11,852][87424] Updated weights for policy 0, policy_version 219977 (0.0012) -[2023-11-28 05:58:12,213][87426] Updated weights for policy 1, policy_version 219600 (0.0012) -[2023-11-28 05:58:12,227][87424] Updated weights for policy 0, policy_version 219987 (0.0010) -[2023-11-28 05:58:12,592][87426] Updated weights for policy 1, policy_version 219610 (0.0012) -[2023-11-28 05:58:12,614][87424] Updated weights for policy 0, policy_version 219997 (0.0011) -[2023-11-28 05:58:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 112541696. Throughput: 0: 2731.2, 1: 2730.8. Samples: 112550132. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:58:13,445][86177] Avg episode reward: [(0, '-518.670'), (1, '-520.200')] -[2023-11-28 05:58:14,447][87424] Updated weights for policy 0, policy_version 220007 (0.0009) -[2023-11-28 05:58:14,832][87424] Updated weights for policy 0, policy_version 220017 (0.0008) -[2023-11-28 05:58:15,183][87426] Updated weights for policy 1, policy_version 219620 (0.0011) -[2023-11-28 05:58:15,217][87424] Updated weights for policy 0, policy_version 220027 (0.0007) -[2023-11-28 05:58:15,571][87426] Updated weights for policy 1, policy_version 219630 (0.0010) -[2023-11-28 05:58:15,948][87426] Updated weights for policy 1, policy_version 219640 (0.0009) -[2023-11-28 05:58:17,563][87424] Updated weights for policy 0, policy_version 220037 (0.0010) -[2023-11-28 05:58:17,946][87424] Updated weights for policy 0, policy_version 220047 (0.0012) -[2023-11-28 05:58:18,323][87424] Updated weights for policy 0, policy_version 220057 (0.0010) -[2023-11-28 05:58:18,356][87426] Updated weights for policy 1, policy_version 219650 (0.0008) -[2023-11-28 05:58:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 112558080. Throughput: 0: 2727.4, 1: 2723.2. Samples: 112574672. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:58:18,445][86177] Avg episode reward: [(0, '-517.680'), (1, '-524.300')] -[2023-11-28 05:58:18,587][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000220064_56336384.pth... -[2023-11-28 05:58:18,617][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000217504_55681024.pth -[2023-11-28 05:58:18,728][87426] Updated weights for policy 1, policy_version 219660 (0.0011) -[2023-11-28 05:58:19,110][87426] Updated weights for policy 1, policy_version 219670 (0.0008) -[2023-11-28 05:58:19,487][87426] Updated weights for policy 1, policy_version 219680 (0.0008) -[2023-11-28 05:58:19,488][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000219680_56238080.pth... -[2023-11-28 05:58:19,532][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000217120_55582720.pth -[2023-11-28 05:58:20,600][87424] Updated weights for policy 0, policy_version 220067 (0.0009) -[2023-11-28 05:58:20,978][87424] Updated weights for policy 0, policy_version 220077 (0.0011) -[2023-11-28 05:58:21,369][87424] Updated weights for policy 0, policy_version 220087 (0.0008) -[2023-11-28 05:58:21,742][87426] Updated weights for policy 1, policy_version 219690 (0.0011) -[2023-11-28 05:58:22,118][87426] Updated weights for policy 1, policy_version 219700 (0.0012) -[2023-11-28 05:58:22,505][87426] Updated weights for policy 1, policy_version 219710 (0.0012) -[2023-11-28 05:58:23,296][87424] Updated weights for policy 0, policy_version 220097 (0.0009) -[2023-11-28 05:58:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 112590848. Throughput: 0: 2724.2, 1: 2721.2. Samples: 112606220. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:58:23,445][86177] Avg episode reward: [(0, '-506.110'), (1, '-530.420')] -[2023-11-28 05:58:23,669][87424] Updated weights for policy 0, policy_version 220107 (0.0012) -[2023-11-28 05:58:24,048][87424] Updated weights for policy 0, policy_version 220117 (0.0012) -[2023-11-28 05:58:24,429][87424] Updated weights for policy 0, policy_version 220127 (0.0012) -[2023-11-28 05:58:24,682][87426] Updated weights for policy 1, policy_version 219720 (0.0011) -[2023-11-28 05:58:25,065][87426] Updated weights for policy 1, policy_version 219730 (0.0012) -[2023-11-28 05:58:25,442][87426] Updated weights for policy 1, policy_version 219740 (0.0012) -[2023-11-28 05:58:26,913][87424] Updated weights for policy 0, policy_version 220137 (0.0012) -[2023-11-28 05:58:27,109][87426] Updated weights for policy 1, policy_version 219750 (0.0010) -[2023-11-28 05:58:27,289][87424] Updated weights for policy 0, policy_version 220147 (0.0010) -[2023-11-28 05:58:27,483][87426] Updated weights for policy 1, policy_version 219760 (0.0010) -[2023-11-28 05:58:27,680][87424] Updated weights for policy 0, policy_version 220157 (0.0007) -[2023-11-28 05:58:27,862][87426] Updated weights for policy 1, policy_version 219770 (0.0011) -[2023-11-28 05:58:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 112623616. Throughput: 0: 2731.0, 1: 2737.5. Samples: 112631760. Policy #0 lag: (min: 24.0, avg: 38.1, max: 64.0) -[2023-11-28 05:58:28,445][86177] Avg episode reward: [(0, '-505.580'), (1, '-540.240')] -[2023-11-28 05:58:29,602][87424] Updated weights for policy 0, policy_version 220167 (0.0012) -[2023-11-28 05:58:29,983][87424] Updated weights for policy 0, policy_version 220177 (0.0012) -[2023-11-28 05:58:30,333][87426] Updated weights for policy 1, policy_version 219780 (0.0009) -[2023-11-28 05:58:30,377][87424] Updated weights for policy 0, policy_version 220187 (0.0012) -[2023-11-28 05:58:30,720][87426] Updated weights for policy 1, policy_version 219790 (0.0012) -[2023-11-28 05:58:31,100][87426] Updated weights for policy 1, policy_version 219800 (0.0012) -[2023-11-28 05:58:32,876][87424] Updated weights for policy 0, policy_version 220197 (0.0008) -[2023-11-28 05:58:33,260][87424] Updated weights for policy 0, policy_version 220207 (0.0008) -[2023-11-28 05:58:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 112640000. Throughput: 0: 2733.2, 1: 2720.4. Samples: 112656376. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:58:33,445][86177] Avg episode reward: [(0, '-525.650'), (1, '-538.170')] -[2023-11-28 05:58:33,651][87426] Updated weights for policy 1, policy_version 219810 (0.0012) -[2023-11-28 05:58:33,652][87424] Updated weights for policy 0, policy_version 220217 (0.0008) -[2023-11-28 05:58:34,028][87426] Updated weights for policy 1, policy_version 219820 (0.0012) -[2023-11-28 05:58:34,406][87426] Updated weights for policy 1, policy_version 219830 (0.0011) -[2023-11-28 05:58:34,777][87426] Updated weights for policy 1, policy_version 219840 (0.0011) -[2023-11-28 05:58:35,975][87424] Updated weights for policy 0, policy_version 220227 (0.0009) -[2023-11-28 05:58:36,359][87424] Updated weights for policy 0, policy_version 220237 (0.0011) -[2023-11-28 05:58:36,512][87426] Updated weights for policy 1, policy_version 219850 (0.0011) -[2023-11-28 05:58:36,741][87424] Updated weights for policy 0, policy_version 220247 (0.0009) -[2023-11-28 05:58:36,881][87426] Updated weights for policy 1, policy_version 219860 (0.0009) -[2023-11-28 05:58:37,259][87426] Updated weights for policy 1, policy_version 219870 (0.0008) -[2023-11-28 05:58:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 112672768. Throughput: 0: 2730.7, 1: 2719.5. Samples: 112688768. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:58:38,445][86177] Avg episode reward: [(0, '-519.880'), (1, '-537.620')] -[2023-11-28 05:58:38,758][87424] Updated weights for policy 0, policy_version 220257 (0.0011) -[2023-11-28 05:58:39,140][87424] Updated weights for policy 0, policy_version 220267 (0.0012) -[2023-11-28 05:58:39,481][87426] Updated weights for policy 1, policy_version 219880 (0.0010) -[2023-11-28 05:58:39,519][87424] Updated weights for policy 0, policy_version 220277 (0.0011) -[2023-11-28 05:58:39,866][87426] Updated weights for policy 1, policy_version 219890 (0.0010) -[2023-11-28 05:58:39,910][87424] Updated weights for policy 0, policy_version 220287 (0.0009) -[2023-11-28 05:58:40,244][87426] Updated weights for policy 1, policy_version 219900 (0.0012) -[2023-11-28 05:58:42,521][87424] Updated weights for policy 0, policy_version 220297 (0.0010) -[2023-11-28 05:58:42,571][87426] Updated weights for policy 1, policy_version 219910 (0.0011) -[2023-11-28 05:58:42,897][87424] Updated weights for policy 0, policy_version 220307 (0.0011) -[2023-11-28 05:58:42,953][87426] Updated weights for policy 1, policy_version 219920 (0.0011) -[2023-11-28 05:58:43,295][87424] Updated weights for policy 0, policy_version 220317 (0.0011) -[2023-11-28 05:58:43,326][87426] Updated weights for policy 1, policy_version 219930 (0.0011) -[2023-11-28 05:58:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 112697344. Throughput: 0: 2722.1, 1: 2745.7. Samples: 112713644. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:58:43,445][86177] Avg episode reward: [(0, '-542.070'), (1, '-532.560')] -[2023-11-28 05:58:45,145][87424] Updated weights for policy 0, policy_version 220327 (0.0009) -[2023-11-28 05:58:45,522][87424] Updated weights for policy 0, policy_version 220337 (0.0008) -[2023-11-28 05:58:45,832][87426] Updated weights for policy 1, policy_version 219940 (0.0011) -[2023-11-28 05:58:45,906][87424] Updated weights for policy 0, policy_version 220347 (0.0010) -[2023-11-28 05:58:46,210][87426] Updated weights for policy 1, policy_version 219950 (0.0008) -[2023-11-28 05:58:46,595][87426] Updated weights for policy 1, policy_version 219960 (0.0009) -[2023-11-28 05:58:47,925][87424] Updated weights for policy 0, policy_version 220357 (0.0010) -[2023-11-28 05:58:48,299][87426] Updated weights for policy 1, policy_version 219970 (0.0010) -[2023-11-28 05:58:48,314][87424] Updated weights for policy 0, policy_version 220367 (0.0008) -[2023-11-28 05:58:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 112721920. Throughput: 0: 2707.6, 1: 2761.2. Samples: 112738980. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:58:48,445][86177] Avg episode reward: [(0, '-580.530'), (1, '-543.260')] -[2023-11-28 05:58:48,680][87426] Updated weights for policy 1, policy_version 219980 (0.0010) -[2023-11-28 05:58:48,695][87424] Updated weights for policy 0, policy_version 220377 (0.0010) -[2023-11-28 05:58:49,054][87426] Updated weights for policy 1, policy_version 219990 (0.0011) -[2023-11-28 05:58:49,437][87426] Updated weights for policy 1, policy_version 220000 (0.0012) -[2023-11-28 05:58:50,802][87424] Updated weights for policy 0, policy_version 220387 (0.0011) -[2023-11-28 05:58:51,187][87424] Updated weights for policy 0, policy_version 220397 (0.0012) -[2023-11-28 05:58:51,568][87424] Updated weights for policy 0, policy_version 220407 (0.0012) -[2023-11-28 05:58:51,679][87426] Updated weights for policy 1, policy_version 220010 (0.0014) -[2023-11-28 05:58:52,052][87426] Updated weights for policy 1, policy_version 220020 (0.0009) -[2023-11-28 05:58:52,434][87426] Updated weights for policy 1, policy_version 220030 (0.0008) -[2023-11-28 05:58:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 112754688. Throughput: 0: 2709.3, 1: 2747.7. Samples: 112771516. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:58:53,445][86177] Avg episode reward: [(0, '-590.700'), (1, '-535.430')] -[2023-11-28 05:58:53,883][87424] Updated weights for policy 0, policy_version 220417 (0.0011) -[2023-11-28 05:58:54,268][87424] Updated weights for policy 0, policy_version 220427 (0.0012) -[2023-11-28 05:58:54,666][87424] Updated weights for policy 0, policy_version 220437 (0.0011) -[2023-11-28 05:58:54,949][87426] Updated weights for policy 1, policy_version 220040 (0.0010) -[2023-11-28 05:58:55,043][87424] Updated weights for policy 0, policy_version 220447 (0.0008) -[2023-11-28 05:58:55,321][87426] Updated weights for policy 1, policy_version 220050 (0.0008) -[2023-11-28 05:58:55,707][87426] Updated weights for policy 1, policy_version 220060 (0.0007) -[2023-11-28 05:58:57,328][87424] Updated weights for policy 0, policy_version 220457 (0.0008) -[2023-11-28 05:58:57,707][87424] Updated weights for policy 0, policy_version 220467 (0.0009) -[2023-11-28 05:58:57,844][87426] Updated weights for policy 1, policy_version 220070 (0.0010) -[2023-11-28 05:58:58,089][87424] Updated weights for policy 0, policy_version 220477 (0.0009) -[2023-11-28 05:58:58,218][87426] Updated weights for policy 1, policy_version 220080 (0.0010) -[2023-11-28 05:58:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 112779264. Throughput: 0: 2699.3, 1: 2747.9. Samples: 112795256. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:58:58,445][86177] Avg episode reward: [(0, '-622.210'), (1, '-544.840')] -[2023-11-28 05:58:58,596][87426] Updated weights for policy 1, policy_version 220090 (0.0007) -[2023-11-28 05:59:00,432][87424] Updated weights for policy 0, policy_version 220487 (0.0010) -[2023-11-28 05:59:00,813][87424] Updated weights for policy 0, policy_version 220497 (0.0012) -[2023-11-28 05:59:01,034][87426] Updated weights for policy 1, policy_version 220100 (0.0008) -[2023-11-28 05:59:01,199][87424] Updated weights for policy 0, policy_version 220507 (0.0011) -[2023-11-28 05:59:01,417][87426] Updated weights for policy 1, policy_version 220110 (0.0007) -[2023-11-28 05:59:01,797][87426] Updated weights for policy 1, policy_version 220120 (0.0010) -[2023-11-28 05:59:03,351][87424] Updated weights for policy 0, policy_version 220517 (0.0011) -[2023-11-28 05:59:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 112803840. Throughput: 0: 2704.3, 1: 2737.7. Samples: 112819560. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:59:03,445][86177] Avg episode reward: [(0, '-645.010'), (1, '-542.510')] -[2023-11-28 05:59:03,613][87426] Updated weights for policy 1, policy_version 220130 (0.0009) -[2023-11-28 05:59:03,734][87424] Updated weights for policy 0, policy_version 220527 (0.0008) -[2023-11-28 05:59:03,996][87426] Updated weights for policy 1, policy_version 220140 (0.0007) -[2023-11-28 05:59:04,126][87424] Updated weights for policy 0, policy_version 220537 (0.0009) -[2023-11-28 05:59:04,389][87426] Updated weights for policy 1, policy_version 220150 (0.0008) -[2023-11-28 05:59:04,761][87426] Updated weights for policy 1, policy_version 220160 (0.0011) -[2023-11-28 05:59:06,471][87424] Updated weights for policy 0, policy_version 220547 (0.0009) -[2023-11-28 05:59:06,812][87426] Updated weights for policy 1, policy_version 220170 (0.0012) -[2023-11-28 05:59:06,872][87424] Updated weights for policy 0, policy_version 220557 (0.0011) -[2023-11-28 05:59:07,189][87426] Updated weights for policy 1, policy_version 220180 (0.0012) -[2023-11-28 05:59:07,246][87424] Updated weights for policy 0, policy_version 220567 (0.0009) -[2023-11-28 05:59:07,567][87426] Updated weights for policy 1, policy_version 220190 (0.0012) -[2023-11-28 05:59:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 112836608. Throughput: 0: 2703.4, 1: 2747.4. Samples: 112851504. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:59:08,445][86177] Avg episode reward: [(0, '-574.400'), (1, '-521.930')] -[2023-11-28 05:59:09,344][87426] Updated weights for policy 1, policy_version 220200 (0.0011) -[2023-11-28 05:59:09,695][87424] Updated weights for policy 0, policy_version 220577 (0.0010) -[2023-11-28 05:59:09,721][87426] Updated weights for policy 1, policy_version 220210 (0.0008) -[2023-11-28 05:59:10,073][87424] Updated weights for policy 0, policy_version 220587 (0.0011) -[2023-11-28 05:59:10,106][87426] Updated weights for policy 1, policy_version 220220 (0.0010) -[2023-11-28 05:59:10,457][87424] Updated weights for policy 0, policy_version 220597 (0.0011) -[2023-11-28 05:59:10,840][87424] Updated weights for policy 0, policy_version 220607 (0.0011) -[2023-11-28 05:59:12,127][87426] Updated weights for policy 1, policy_version 220230 (0.0011) -[2023-11-28 05:59:12,506][87426] Updated weights for policy 1, policy_version 220240 (0.0011) -[2023-11-28 05:59:12,839][87424] Updated weights for policy 0, policy_version 220617 (0.0011) -[2023-11-28 05:59:12,884][87426] Updated weights for policy 1, policy_version 220250 (0.0011) -[2023-11-28 05:59:13,212][87424] Updated weights for policy 0, policy_version 220627 (0.0012) -[2023-11-28 05:59:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 112861184. Throughput: 0: 2691.5, 1: 2733.8. Samples: 112875896. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:59:13,445][86177] Avg episode reward: [(0, '-575.370'), (1, '-522.440')] -[2023-11-28 05:59:13,593][87424] Updated weights for policy 0, policy_version 220637 (0.0012) -[2023-11-28 05:59:15,432][87426] Updated weights for policy 1, policy_version 220260 (0.0010) -[2023-11-28 05:59:15,730][87424] Updated weights for policy 0, policy_version 220647 (0.0012) -[2023-11-28 05:59:15,810][87426] Updated weights for policy 1, policy_version 220270 (0.0008) -[2023-11-28 05:59:16,115][87424] Updated weights for policy 0, policy_version 220657 (0.0011) -[2023-11-28 05:59:16,192][87426] Updated weights for policy 1, policy_version 220280 (0.0007) -[2023-11-28 05:59:16,508][87424] Updated weights for policy 0, policy_version 220667 (0.0012) -[2023-11-28 05:59:18,422][87424] Updated weights for policy 0, policy_version 220677 (0.0012) -[2023-11-28 05:59:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 112885760. Throughput: 0: 2691.4, 1: 2742.4. Samples: 112900896. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:59:18,446][86177] Avg episode reward: [(0, '-531.970'), (1, '-518.610')] -[2023-11-28 05:59:18,448][87426] Updated weights for policy 1, policy_version 220290 (0.0008) -[2023-11-28 05:59:18,805][87424] Updated weights for policy 0, policy_version 220687 (0.0012) -[2023-11-28 05:59:18,834][87426] Updated weights for policy 1, policy_version 220300 (0.0011) -[2023-11-28 05:59:19,200][87424] Updated weights for policy 0, policy_version 220697 (0.0011) -[2023-11-28 05:59:19,228][87426] Updated weights for policy 1, policy_version 220310 (0.0011) -[2023-11-28 05:59:19,598][87426] Updated weights for policy 1, policy_version 220320 (0.0011) -[2023-11-28 05:59:21,222][87424] Updated weights for policy 0, policy_version 220707 (0.0012) -[2023-11-28 05:59:21,604][87424] Updated weights for policy 0, policy_version 220717 (0.0010) -[2023-11-28 05:59:21,739][87426] Updated weights for policy 1, policy_version 220330 (0.0011) -[2023-11-28 05:59:21,983][87424] Updated weights for policy 0, policy_version 220727 (0.0012) -[2023-11-28 05:59:22,116][87426] Updated weights for policy 1, policy_version 220340 (0.0011) -[2023-11-28 05:59:22,494][87426] Updated weights for policy 1, policy_version 220350 (0.0011) -[2023-11-28 05:59:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 112918528. Throughput: 0: 2706.8, 1: 2747.1. Samples: 112934192. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:59:23,445][86177] Avg episode reward: [(0, '-490.620'), (1, '-515.710')] -[2023-11-28 05:59:24,154][87424] Updated weights for policy 0, policy_version 220737 (0.0012) -[2023-11-28 05:59:24,540][87424] Updated weights for policy 0, policy_version 220747 (0.0011) -[2023-11-28 05:59:24,679][87426] Updated weights for policy 1, policy_version 220360 (0.0010) -[2023-11-28 05:59:24,918][87424] Updated weights for policy 0, policy_version 220757 (0.0009) -[2023-11-28 05:59:25,066][87426] Updated weights for policy 1, policy_version 220370 (0.0011) -[2023-11-28 05:59:25,300][87424] Updated weights for policy 0, policy_version 220767 (0.0007) -[2023-11-28 05:59:25,450][87426] Updated weights for policy 1, policy_version 220380 (0.0010) -[2023-11-28 05:59:27,091][87424] Updated weights for policy 0, policy_version 220777 (0.0011) -[2023-11-28 05:59:27,334][87426] Updated weights for policy 1, policy_version 220390 (0.0011) -[2023-11-28 05:59:27,471][87424] Updated weights for policy 0, policy_version 220787 (0.0012) -[2023-11-28 05:59:27,711][87426] Updated weights for policy 1, policy_version 220400 (0.0012) -[2023-11-28 05:59:27,845][87424] Updated weights for policy 0, policy_version 220797 (0.0012) -[2023-11-28 05:59:28,093][87426] Updated weights for policy 1, policy_version 220410 (0.0011) -[2023-11-28 05:59:28,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 112951296. Throughput: 0: 2731.5, 1: 2718.2. Samples: 112958884. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:59:28,445][86177] Avg episode reward: [(0, '-534.500'), (1, '-514.450')] -[2023-11-28 05:59:29,648][87424] Updated weights for policy 0, policy_version 220807 (0.0010) -[2023-11-28 05:59:30,025][87424] Updated weights for policy 0, policy_version 220817 (0.0009) -[2023-11-28 05:59:30,128][87426] Updated weights for policy 1, policy_version 220420 (0.0011) -[2023-11-28 05:59:30,413][87424] Updated weights for policy 0, policy_version 220827 (0.0011) -[2023-11-28 05:59:30,518][87426] Updated weights for policy 1, policy_version 220430 (0.0011) -[2023-11-28 05:59:30,896][87426] Updated weights for policy 1, policy_version 220440 (0.0011) -[2023-11-28 05:59:32,771][87424] Updated weights for policy 0, policy_version 220837 (0.0010) -[2023-11-28 05:59:33,159][87424] Updated weights for policy 0, policy_version 220847 (0.0012) -[2023-11-28 05:59:33,320][87426] Updated weights for policy 1, policy_version 220450 (0.0008) -[2023-11-28 05:59:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 112967680. Throughput: 0: 2732.9, 1: 2707.2. Samples: 112983784. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:59:33,445][86177] Avg episode reward: [(0, '-537.870'), (1, '-517.740')] -[2023-11-28 05:59:33,537][87424] Updated weights for policy 0, policy_version 220857 (0.0009) -[2023-11-28 05:59:33,714][87426] Updated weights for policy 1, policy_version 220460 (0.0010) -[2023-11-28 05:59:34,093][87426] Updated weights for policy 1, policy_version 220470 (0.0012) -[2023-11-28 05:59:34,466][87426] Updated weights for policy 1, policy_version 220480 (0.0012) -[2023-11-28 05:59:35,921][87424] Updated weights for policy 0, policy_version 220867 (0.0009) -[2023-11-28 05:59:36,307][87424] Updated weights for policy 0, policy_version 220877 (0.0012) -[2023-11-28 05:59:36,335][87426] Updated weights for policy 1, policy_version 220490 (0.0012) -[2023-11-28 05:59:36,694][87424] Updated weights for policy 0, policy_version 220887 (0.0011) -[2023-11-28 05:59:36,710][87426] Updated weights for policy 1, policy_version 220500 (0.0015) -[2023-11-28 05:59:37,091][87426] Updated weights for policy 1, policy_version 220510 (0.0012) -[2023-11-28 05:59:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 113000448. Throughput: 0: 2744.3, 1: 2716.4. Samples: 113017248. Policy #0 lag: (min: 31.0, avg: 52.3, max: 63.0) -[2023-11-28 05:59:38,445][86177] Avg episode reward: [(0, '-537.850'), (1, '-523.060')] -[2023-11-28 05:59:38,517][87424] Updated weights for policy 0, policy_version 220897 (0.0011) -[2023-11-28 05:59:38,892][87424] Updated weights for policy 0, policy_version 220907 (0.0012) -[2023-11-28 05:59:39,144][87426] Updated weights for policy 1, policy_version 220520 (0.0011) -[2023-11-28 05:59:39,277][87424] Updated weights for policy 0, policy_version 220917 (0.0011) -[2023-11-28 05:59:39,520][87426] Updated weights for policy 1, policy_version 220530 (0.0011) -[2023-11-28 05:59:39,664][87424] Updated weights for policy 0, policy_version 220927 (0.0010) -[2023-11-28 05:59:39,897][87426] Updated weights for policy 1, policy_version 220540 (0.0011) -[2023-11-28 05:59:41,836][87424] Updated weights for policy 0, policy_version 220937 (0.0010) -[2023-11-28 05:59:42,196][87426] Updated weights for policy 1, policy_version 220550 (0.0008) -[2023-11-28 05:59:42,212][87424] Updated weights for policy 0, policy_version 220947 (0.0012) -[2023-11-28 05:59:42,572][87426] Updated weights for policy 1, policy_version 220560 (0.0010) -[2023-11-28 05:59:42,602][87424] Updated weights for policy 0, policy_version 220957 (0.0012) -[2023-11-28 05:59:42,957][87426] Updated weights for policy 1, policy_version 220570 (0.0009) -[2023-11-28 05:59:43,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 113033216. Throughput: 0: 2753.9, 1: 2730.2. Samples: 113042040. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 05:59:43,445][86177] Avg episode reward: [(0, '-537.830'), (1, '-522.030')] -[2023-11-28 05:59:44,842][87426] Updated weights for policy 1, policy_version 220580 (0.0010) -[2023-11-28 05:59:45,210][87426] Updated weights for policy 1, policy_version 220590 (0.0010) -[2023-11-28 05:59:45,240][87424] Updated weights for policy 0, policy_version 220967 (0.0010) -[2023-11-28 05:59:45,589][87426] Updated weights for policy 1, policy_version 220600 (0.0008) -[2023-11-28 05:59:45,631][87424] Updated weights for policy 0, policy_version 220977 (0.0011) -[2023-11-28 05:59:46,011][87424] Updated weights for policy 0, policy_version 220987 (0.0010) -[2023-11-28 05:59:47,999][87426] Updated weights for policy 1, policy_version 220610 (0.0009) -[2023-11-28 05:59:48,382][87426] Updated weights for policy 1, policy_version 220620 (0.0008) -[2023-11-28 05:59:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 113049600. Throughput: 0: 2733.2, 1: 2757.9. Samples: 113066656. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 05:59:48,445][86177] Avg episode reward: [(0, '-495.940'), (1, '-523.650')] -[2023-11-28 05:59:48,484][87424] Updated weights for policy 0, policy_version 220997 (0.0007) -[2023-11-28 05:59:48,752][87426] Updated weights for policy 1, policy_version 220630 (0.0007) -[2023-11-28 05:59:48,866][87424] Updated weights for policy 0, policy_version 221007 (0.0008) -[2023-11-28 05:59:49,131][87426] Updated weights for policy 1, policy_version 220640 (0.0008) -[2023-11-28 05:59:49,254][87424] Updated weights for policy 0, policy_version 221017 (0.0007) -[2023-11-28 05:59:51,331][87424] Updated weights for policy 0, policy_version 221027 (0.0007) -[2023-11-28 05:59:51,635][87426] Updated weights for policy 1, policy_version 220650 (0.0011) -[2023-11-28 05:59:51,720][87424] Updated weights for policy 0, policy_version 221037 (0.0010) -[2023-11-28 05:59:52,012][87426] Updated weights for policy 1, policy_version 220660 (0.0011) -[2023-11-28 05:59:52,088][87424] Updated weights for policy 0, policy_version 221047 (0.0012) -[2023-11-28 05:59:52,392][87426] Updated weights for policy 1, policy_version 220670 (0.0011) -[2023-11-28 05:59:53,445][86177] Fps is (10 sec: 4914.8, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 113082368. Throughput: 0: 2744.9, 1: 2754.8. Samples: 113098996. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 05:59:53,446][86177] Avg episode reward: [(0, '-495.470'), (1, '-521.500')] -[2023-11-28 05:59:54,250][87424] Updated weights for policy 0, policy_version 221057 (0.0011) -[2023-11-28 05:59:54,635][87424] Updated weights for policy 0, policy_version 221067 (0.0011) -[2023-11-28 05:59:54,756][87426] Updated weights for policy 1, policy_version 220680 (0.0011) -[2023-11-28 05:59:55,013][87424] Updated weights for policy 0, policy_version 221077 (0.0009) -[2023-11-28 05:59:55,130][87426] Updated weights for policy 1, policy_version 220690 (0.0012) -[2023-11-28 05:59:55,398][87424] Updated weights for policy 0, policy_version 221087 (0.0009) -[2023-11-28 05:59:55,505][87426] Updated weights for policy 1, policy_version 220700 (0.0012) -[2023-11-28 05:59:57,185][87426] Updated weights for policy 1, policy_version 220710 (0.0012) -[2023-11-28 05:59:57,315][87424] Updated weights for policy 0, policy_version 221097 (0.0008) -[2023-11-28 05:59:57,575][87426] Updated weights for policy 1, policy_version 220720 (0.0008) -[2023-11-28 05:59:57,704][87424] Updated weights for policy 0, policy_version 221107 (0.0008) -[2023-11-28 05:59:57,951][87426] Updated weights for policy 1, policy_version 220730 (0.0010) -[2023-11-28 05:59:58,090][87424] Updated weights for policy 0, policy_version 221117 (0.0012) -[2023-11-28 05:59:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 113115136. Throughput: 0: 2750.7, 1: 2748.3. Samples: 113123348. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 05:59:58,445][86177] Avg episode reward: [(0, '-494.850'), (1, '-518.140')] -[2023-11-28 05:59:59,573][87426] Updated weights for policy 1, policy_version 220740 (0.0009) -[2023-11-28 05:59:59,958][87426] Updated weights for policy 1, policy_version 220750 (0.0010) -[2023-11-28 06:00:00,219][87424] Updated weights for policy 0, policy_version 221127 (0.0009) -[2023-11-28 06:00:00,331][87426] Updated weights for policy 1, policy_version 220760 (0.0009) -[2023-11-28 06:00:00,606][87424] Updated weights for policy 0, policy_version 221137 (0.0008) -[2023-11-28 06:00:00,979][87424] Updated weights for policy 0, policy_version 221147 (0.0008) -[2023-11-28 06:00:02,435][87426] Updated weights for policy 1, policy_version 220770 (0.0010) -[2023-11-28 06:00:02,801][87426] Updated weights for policy 1, policy_version 220780 (0.0008) -[2023-11-28 06:00:03,171][87424] Updated weights for policy 0, policy_version 221157 (0.0009) -[2023-11-28 06:00:03,186][87426] Updated weights for policy 1, policy_version 220790 (0.0008) -[2023-11-28 06:00:03,444][86177] Fps is (10 sec: 4915.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 113131520. Throughput: 0: 2744.2, 1: 2755.8. Samples: 113148396. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:03,445][86177] Avg episode reward: [(0, '-499.040'), (1, '-519.200')] -[2023-11-28 06:00:03,547][87424] Updated weights for policy 0, policy_version 221167 (0.0012) -[2023-11-28 06:00:03,556][87426] Updated weights for policy 1, policy_version 220800 (0.0010) -[2023-11-28 06:00:03,934][87424] Updated weights for policy 0, policy_version 221177 (0.0012) -[2023-11-28 06:00:05,440][87426] Updated weights for policy 1, policy_version 220810 (0.0009) -[2023-11-28 06:00:05,812][87426] Updated weights for policy 1, policy_version 220820 (0.0007) -[2023-11-28 06:00:06,190][87426] Updated weights for policy 1, policy_version 220830 (0.0007) -[2023-11-28 06:00:06,303][87424] Updated weights for policy 0, policy_version 221187 (0.0011) -[2023-11-28 06:00:06,687][87424] Updated weights for policy 0, policy_version 221197 (0.0008) -[2023-11-28 06:00:07,068][87424] Updated weights for policy 0, policy_version 221207 (0.0007) -[2023-11-28 06:00:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 113164288. Throughput: 0: 2717.4, 1: 2766.3. Samples: 113180960. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:08,445][86177] Avg episode reward: [(0, '-502.840'), (1, '-517.690')] -[2023-11-28 06:00:08,581][87426] Updated weights for policy 1, policy_version 220840 (0.0007) -[2023-11-28 06:00:08,756][87424] Updated weights for policy 0, policy_version 221217 (0.0008) -[2023-11-28 06:00:08,969][87426] Updated weights for policy 1, policy_version 220850 (0.0008) -[2023-11-28 06:00:09,143][87424] Updated weights for policy 0, policy_version 221227 (0.0008) -[2023-11-28 06:00:09,336][87426] Updated weights for policy 1, policy_version 220860 (0.0007) -[2023-11-28 06:00:09,525][87424] Updated weights for policy 0, policy_version 221237 (0.0008) -[2023-11-28 06:00:09,905][87424] Updated weights for policy 0, policy_version 221247 (0.0009) -[2023-11-28 06:00:11,834][87426] Updated weights for policy 1, policy_version 220870 (0.0010) -[2023-11-28 06:00:12,214][87426] Updated weights for policy 1, policy_version 220880 (0.0010) -[2023-11-28 06:00:12,342][87424] Updated weights for policy 0, policy_version 221257 (0.0011) -[2023-11-28 06:00:12,590][87426] Updated weights for policy 1, policy_version 220890 (0.0011) -[2023-11-28 06:00:12,717][87424] Updated weights for policy 0, policy_version 221267 (0.0011) -[2023-11-28 06:00:13,103][87424] Updated weights for policy 0, policy_version 221277 (0.0011) -[2023-11-28 06:00:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 113197056. Throughput: 0: 2702.7, 1: 2756.2. Samples: 113204532. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:13,445][86177] Avg episode reward: [(0, '-503.500'), (1, '-511.900')] -[2023-11-28 06:00:15,206][87426] Updated weights for policy 1, policy_version 220900 (0.0011) -[2023-11-28 06:00:15,416][87424] Updated weights for policy 0, policy_version 221287 (0.0009) -[2023-11-28 06:00:15,584][87426] Updated weights for policy 1, policy_version 220910 (0.0011) -[2023-11-28 06:00:15,790][87424] Updated weights for policy 0, policy_version 221297 (0.0007) -[2023-11-28 06:00:15,958][87426] Updated weights for policy 1, policy_version 220920 (0.0012) -[2023-11-28 06:00:16,175][87424] Updated weights for policy 0, policy_version 221307 (0.0010) -[2023-11-28 06:00:18,385][87426] Updated weights for policy 1, policy_version 220930 (0.0011) -[2023-11-28 06:00:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 113213440. Throughput: 0: 2689.8, 1: 2733.8. Samples: 113227844. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:18,446][86177] Avg episode reward: [(0, '-500.310'), (1, '-512.930')] -[2023-11-28 06:00:18,462][87424] Updated weights for policy 0, policy_version 221317 (0.0010) -[2023-11-28 06:00:18,762][87426] Updated weights for policy 1, policy_version 220940 (0.0009) -[2023-11-28 06:00:18,844][87424] Updated weights for policy 0, policy_version 221327 (0.0012) -[2023-11-28 06:00:19,145][87426] Updated weights for policy 1, policy_version 220950 (0.0010) -[2023-11-28 06:00:19,228][87424] Updated weights for policy 0, policy_version 221337 (0.0008) -[2023-11-28 06:00:19,487][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000221344_56664064.pth... -[2023-11-28 06:00:19,519][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000218784_56008704.pth -[2023-11-28 06:00:19,528][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000220960_56565760.pth... -[2023-11-28 06:00:19,533][87426] Updated weights for policy 1, policy_version 220960 (0.0011) -[2023-11-28 06:00:19,572][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000218400_55910400.pth -[2023-11-28 06:00:21,488][87424] Updated weights for policy 0, policy_version 221347 (0.0010) -[2023-11-28 06:00:21,690][87426] Updated weights for policy 1, policy_version 220970 (0.0011) -[2023-11-28 06:00:21,874][87424] Updated weights for policy 0, policy_version 221357 (0.0011) -[2023-11-28 06:00:22,066][87426] Updated weights for policy 1, policy_version 220980 (0.0010) -[2023-11-28 06:00:22,258][87424] Updated weights for policy 0, policy_version 221367 (0.0009) -[2023-11-28 06:00:22,435][87426] Updated weights for policy 1, policy_version 220990 (0.0012) -[2023-11-28 06:00:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 113246208. Throughput: 0: 2668.2, 1: 2716.6. Samples: 113259564. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:23,445][86177] Avg episode reward: [(0, '-502.710'), (1, '-516.180')] -[2023-11-28 06:00:24,522][87426] Updated weights for policy 1, policy_version 221000 (0.0008) -[2023-11-28 06:00:24,721][87424] Updated weights for policy 0, policy_version 221377 (0.0011) -[2023-11-28 06:00:24,904][87426] Updated weights for policy 1, policy_version 221010 (0.0008) -[2023-11-28 06:00:25,109][87424] Updated weights for policy 0, policy_version 221387 (0.0010) -[2023-11-28 06:00:25,282][87426] Updated weights for policy 1, policy_version 221020 (0.0009) -[2023-11-28 06:00:25,496][87424] Updated weights for policy 0, policy_version 221397 (0.0012) -[2023-11-28 06:00:25,882][87424] Updated weights for policy 0, policy_version 221407 (0.0009) -[2023-11-28 06:00:27,122][87426] Updated weights for policy 1, policy_version 221030 (0.0012) -[2023-11-28 06:00:27,497][87426] Updated weights for policy 1, policy_version 221040 (0.0011) -[2023-11-28 06:00:27,875][87426] Updated weights for policy 1, policy_version 221050 (0.0011) -[2023-11-28 06:00:28,095][87424] Updated weights for policy 0, policy_version 221417 (0.0008) -[2023-11-28 06:00:28,444][86177] Fps is (10 sec: 5734.7, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 113270784. Throughput: 0: 2656.4, 1: 2734.6. Samples: 113284636. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:28,445][86177] Avg episode reward: [(0, '-503.520'), (1, '-516.150')] -[2023-11-28 06:00:28,478][87424] Updated weights for policy 0, policy_version 221427 (0.0008) -[2023-11-28 06:00:28,865][87424] Updated weights for policy 0, policy_version 221437 (0.0011) -[2023-11-28 06:00:30,163][87426] Updated weights for policy 1, policy_version 221060 (0.0012) -[2023-11-28 06:00:30,541][87426] Updated weights for policy 1, policy_version 221070 (0.0012) -[2023-11-28 06:00:30,920][87426] Updated weights for policy 1, policy_version 221080 (0.0012) -[2023-11-28 06:00:31,048][87424] Updated weights for policy 0, policy_version 221447 (0.0010) -[2023-11-28 06:00:31,423][87424] Updated weights for policy 0, policy_version 221457 (0.0012) -[2023-11-28 06:00:31,817][87424] Updated weights for policy 0, policy_version 221467 (0.0011) -[2023-11-28 06:00:33,157][87426] Updated weights for policy 1, policy_version 221090 (0.0010) -[2023-11-28 06:00:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 113295360. Throughput: 0: 2675.1, 1: 2713.8. Samples: 113309156. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:33,445][86177] Avg episode reward: [(0, '-504.800'), (1, '-522.200')] -[2023-11-28 06:00:33,537][87426] Updated weights for policy 1, policy_version 221100 (0.0011) -[2023-11-28 06:00:33,914][87426] Updated weights for policy 1, policy_version 221110 (0.0012) -[2023-11-28 06:00:34,132][87424] Updated weights for policy 0, policy_version 221477 (0.0010) -[2023-11-28 06:00:34,292][87426] Updated weights for policy 1, policy_version 221120 (0.0010) -[2023-11-28 06:00:34,516][87424] Updated weights for policy 0, policy_version 221487 (0.0011) -[2023-11-28 06:00:34,904][87424] Updated weights for policy 0, policy_version 221497 (0.0012) -[2023-11-28 06:00:36,706][87424] Updated weights for policy 0, policy_version 221507 (0.0012) -[2023-11-28 06:00:36,720][87426] Updated weights for policy 1, policy_version 221130 (0.0008) -[2023-11-28 06:00:37,076][87424] Updated weights for policy 0, policy_version 221517 (0.0011) -[2023-11-28 06:00:37,096][87426] Updated weights for policy 1, policy_version 221140 (0.0007) -[2023-11-28 06:00:37,454][87424] Updated weights for policy 0, policy_version 221527 (0.0010) -[2023-11-28 06:00:37,473][87426] Updated weights for policy 1, policy_version 221150 (0.0008) -[2023-11-28 06:00:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 113328128. Throughput: 0: 2667.2, 1: 2702.9. Samples: 113340644. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:38,445][86177] Avg episode reward: [(0, '-516.470'), (1, '-561.150')] -[2023-11-28 06:00:39,811][87426] Updated weights for policy 1, policy_version 221160 (0.0009) -[2023-11-28 06:00:39,854][87424] Updated weights for policy 0, policy_version 221537 (0.0010) -[2023-11-28 06:00:40,194][87426] Updated weights for policy 1, policy_version 221170 (0.0011) -[2023-11-28 06:00:40,236][87424] Updated weights for policy 0, policy_version 221547 (0.0010) -[2023-11-28 06:00:40,569][87426] Updated weights for policy 1, policy_version 221180 (0.0019) -[2023-11-28 06:00:40,614][87424] Updated weights for policy 0, policy_version 221557 (0.0014) -[2023-11-28 06:00:40,998][87424] Updated weights for policy 0, policy_version 221567 (0.0012) -[2023-11-28 06:00:42,599][87426] Updated weights for policy 1, policy_version 221190 (0.0011) -[2023-11-28 06:00:42,980][87426] Updated weights for policy 1, policy_version 221200 (0.0011) -[2023-11-28 06:00:43,321][87424] Updated weights for policy 0, policy_version 221577 (0.0011) -[2023-11-28 06:00:43,362][87426] Updated weights for policy 1, policy_version 221210 (0.0011) -[2023-11-28 06:00:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.2, 300 sec: 5415.0). Total num frames: 113344512. Throughput: 0: 2664.7, 1: 2687.8. Samples: 113364212. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:43,445][86177] Avg episode reward: [(0, '-515.950'), (1, '-558.180')] -[2023-11-28 06:00:43,696][87424] Updated weights for policy 0, policy_version 221587 (0.0012) -[2023-11-28 06:00:44,076][87424] Updated weights for policy 0, policy_version 221597 (0.0011) -[2023-11-28 06:00:45,467][87426] Updated weights for policy 1, policy_version 221220 (0.0009) -[2023-11-28 06:00:45,837][87426] Updated weights for policy 1, policy_version 221230 (0.0012) -[2023-11-28 06:00:46,217][87426] Updated weights for policy 1, policy_version 221240 (0.0010) -[2023-11-28 06:00:46,332][87424] Updated weights for policy 0, policy_version 221607 (0.0010) -[2023-11-28 06:00:46,713][87424] Updated weights for policy 0, policy_version 221617 (0.0011) -[2023-11-28 06:00:47,103][87424] Updated weights for policy 0, policy_version 221627 (0.0012) -[2023-11-28 06:00:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 113377280. Throughput: 0: 2661.1, 1: 2698.3. Samples: 113389568. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:48,446][86177] Avg episode reward: [(0, '-529.310'), (1, '-554.870')] -[2023-11-28 06:00:48,505][87426] Updated weights for policy 1, policy_version 221250 (0.0008) -[2023-11-28 06:00:48,879][87426] Updated weights for policy 1, policy_version 221260 (0.0012) -[2023-11-28 06:00:49,258][87426] Updated weights for policy 1, policy_version 221270 (0.0012) -[2023-11-28 06:00:49,483][87424] Updated weights for policy 0, policy_version 221637 (0.0011) -[2023-11-28 06:00:49,632][87426] Updated weights for policy 1, policy_version 221280 (0.0010) -[2023-11-28 06:00:49,865][87424] Updated weights for policy 0, policy_version 221647 (0.0012) -[2023-11-28 06:00:50,247][87424] Updated weights for policy 0, policy_version 221657 (0.0012) -[2023-11-28 06:00:51,857][87426] Updated weights for policy 1, policy_version 221290 (0.0009) -[2023-11-28 06:00:52,228][87426] Updated weights for policy 1, policy_version 221300 (0.0009) -[2023-11-28 06:00:52,383][87424] Updated weights for policy 0, policy_version 221667 (0.0011) -[2023-11-28 06:00:52,605][87426] Updated weights for policy 1, policy_version 221310 (0.0011) -[2023-11-28 06:00:52,779][87424] Updated weights for policy 0, policy_version 221677 (0.0011) -[2023-11-28 06:00:53,152][87424] Updated weights for policy 0, policy_version 221687 (0.0011) -[2023-11-28 06:00:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.9, 300 sec: 5442.8). Total num frames: 113401856. Throughput: 0: 2659.8, 1: 2680.5. Samples: 113421276. Policy #0 lag: (min: 31.0, avg: 35.3, max: 60.0) -[2023-11-28 06:00:53,445][86177] Avg episode reward: [(0, '-532.710'), (1, '-551.950')] -[2023-11-28 06:00:54,693][87426] Updated weights for policy 1, policy_version 221320 (0.0011) -[2023-11-28 06:00:55,065][87426] Updated weights for policy 1, policy_version 221330 (0.0007) -[2023-11-28 06:00:55,232][87424] Updated weights for policy 0, policy_version 221697 (0.0011) -[2023-11-28 06:00:55,439][87426] Updated weights for policy 1, policy_version 221340 (0.0007) -[2023-11-28 06:00:55,624][87424] Updated weights for policy 0, policy_version 221707 (0.0012) -[2023-11-28 06:00:56,016][87424] Updated weights for policy 0, policy_version 221717 (0.0012) -[2023-11-28 06:00:56,402][87424] Updated weights for policy 0, policy_version 221727 (0.0012) -[2023-11-28 06:00:57,851][87426] Updated weights for policy 1, policy_version 221350 (0.0007) -[2023-11-28 06:00:58,063][87424] Updated weights for policy 0, policy_version 221737 (0.0008) -[2023-11-28 06:00:58,232][87426] Updated weights for policy 1, policy_version 221360 (0.0007) -[2023-11-28 06:00:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 113426432. Throughput: 0: 2671.5, 1: 2686.1. Samples: 113445624. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:00:58,445][86177] Avg episode reward: [(0, '-521.390'), (1, '-548.410')] -[2023-11-28 06:00:58,453][87424] Updated weights for policy 0, policy_version 221747 (0.0008) -[2023-11-28 06:00:58,614][87426] Updated weights for policy 1, policy_version 221370 (0.0009) -[2023-11-28 06:00:58,833][87424] Updated weights for policy 0, policy_version 221757 (0.0008) -[2023-11-28 06:01:00,594][87426] Updated weights for policy 1, policy_version 221380 (0.0009) -[2023-11-28 06:01:00,909][87424] Updated weights for policy 0, policy_version 221767 (0.0011) -[2023-11-28 06:01:00,964][87426] Updated weights for policy 1, policy_version 221390 (0.0011) -[2023-11-28 06:01:01,288][87424] Updated weights for policy 0, policy_version 221777 (0.0009) -[2023-11-28 06:01:01,340][87426] Updated weights for policy 1, policy_version 221400 (0.0011) -[2023-11-28 06:01:01,669][87424] Updated weights for policy 0, policy_version 221787 (0.0009) -[2023-11-28 06:01:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 113459200. Throughput: 0: 2685.4, 1: 2698.1. Samples: 113470096. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:03,445][86177] Avg episode reward: [(0, '-514.230'), (1, '-518.310')] -[2023-11-28 06:01:03,910][87426] Updated weights for policy 1, policy_version 221410 (0.0011) -[2023-11-28 06:01:03,956][87424] Updated weights for policy 0, policy_version 221797 (0.0011) -[2023-11-28 06:01:04,277][87426] Updated weights for policy 1, policy_version 221420 (0.0009) -[2023-11-28 06:01:04,335][87424] Updated weights for policy 0, policy_version 221807 (0.0012) -[2023-11-28 06:01:04,656][87426] Updated weights for policy 1, policy_version 221430 (0.0010) -[2023-11-28 06:01:04,718][87424] Updated weights for policy 0, policy_version 221817 (0.0011) -[2023-11-28 06:01:05,036][87426] Updated weights for policy 1, policy_version 221440 (0.0011) -[2023-11-28 06:01:06,712][87424] Updated weights for policy 0, policy_version 221827 (0.0011) -[2023-11-28 06:01:07,094][87424] Updated weights for policy 0, policy_version 221837 (0.0011) -[2023-11-28 06:01:07,402][87426] Updated weights for policy 1, policy_version 221450 (0.0010) -[2023-11-28 06:01:07,472][87424] Updated weights for policy 0, policy_version 221847 (0.0012) -[2023-11-28 06:01:07,781][87426] Updated weights for policy 1, policy_version 221460 (0.0010) -[2023-11-28 06:01:08,151][87426] Updated weights for policy 1, policy_version 221470 (0.0010) -[2023-11-28 06:01:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 113491968. Throughput: 0: 2713.2, 1: 2721.2. Samples: 113504116. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:08,445][86177] Avg episode reward: [(0, '-517.000'), (1, '-517.400')] -[2023-11-28 06:01:09,674][87424] Updated weights for policy 0, policy_version 221857 (0.0012) -[2023-11-28 06:01:10,019][87426] Updated weights for policy 1, policy_version 221480 (0.0009) -[2023-11-28 06:01:10,057][87424] Updated weights for policy 0, policy_version 221867 (0.0012) -[2023-11-28 06:01:10,393][87426] Updated weights for policy 1, policy_version 221490 (0.0011) -[2023-11-28 06:01:10,436][87424] Updated weights for policy 0, policy_version 221877 (0.0011) -[2023-11-28 06:01:10,770][87426] Updated weights for policy 1, policy_version 221500 (0.0012) -[2023-11-28 06:01:10,815][87424] Updated weights for policy 0, policy_version 221887 (0.0012) -[2023-11-28 06:01:13,039][87426] Updated weights for policy 1, policy_version 221510 (0.0012) -[2023-11-28 06:01:13,072][87424] Updated weights for policy 0, policy_version 221897 (0.0011) -[2023-11-28 06:01:13,412][87426] Updated weights for policy 1, policy_version 221520 (0.0011) -[2023-11-28 06:01:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 113508352. Throughput: 0: 2718.1, 1: 2680.9. Samples: 113527592. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:13,445][86177] Avg episode reward: [(0, '-512.540'), (1, '-518.160')] -[2023-11-28 06:01:13,445][87424] Updated weights for policy 0, policy_version 221907 (0.0010) -[2023-11-28 06:01:13,789][87426] Updated weights for policy 1, policy_version 221530 (0.0011) -[2023-11-28 06:01:13,835][87424] Updated weights for policy 0, policy_version 221917 (0.0011) -[2023-11-28 06:01:15,929][87426] Updated weights for policy 1, policy_version 221540 (0.0011) -[2023-11-28 06:01:16,302][87426] Updated weights for policy 1, policy_version 221550 (0.0008) -[2023-11-28 06:01:16,323][87424] Updated weights for policy 0, policy_version 221927 (0.0010) -[2023-11-28 06:01:16,694][87426] Updated weights for policy 1, policy_version 221560 (0.0007) -[2023-11-28 06:01:16,711][87424] Updated weights for policy 0, policy_version 221937 (0.0011) -[2023-11-28 06:01:17,087][87424] Updated weights for policy 0, policy_version 221947 (0.0009) -[2023-11-28 06:01:18,444][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 113541120. Throughput: 0: 2706.1, 1: 2692.2. Samples: 113552084. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:18,446][86177] Avg episode reward: [(0, '-512.270'), (1, '-520.350')] -[2023-11-28 06:01:19,081][87424] Updated weights for policy 0, policy_version 221957 (0.0010) -[2023-11-28 06:01:19,093][87426] Updated weights for policy 1, policy_version 221570 (0.0007) -[2023-11-28 06:01:19,465][87424] Updated weights for policy 0, policy_version 221967 (0.0011) -[2023-11-28 06:01:19,468][87426] Updated weights for policy 1, policy_version 221580 (0.0008) -[2023-11-28 06:01:19,842][87424] Updated weights for policy 0, policy_version 221977 (0.0009) -[2023-11-28 06:01:19,846][87426] Updated weights for policy 1, policy_version 221590 (0.0009) -[2023-11-28 06:01:20,223][87426] Updated weights for policy 1, policy_version 221600 (0.0010) -[2023-11-28 06:01:22,128][87426] Updated weights for policy 1, policy_version 221610 (0.0011) -[2023-11-28 06:01:22,365][87424] Updated weights for policy 0, policy_version 221987 (0.0010) -[2023-11-28 06:01:22,505][87426] Updated weights for policy 1, policy_version 221620 (0.0013) -[2023-11-28 06:01:22,761][87424] Updated weights for policy 0, policy_version 221997 (0.0011) -[2023-11-28 06:01:22,886][87426] Updated weights for policy 1, policy_version 221630 (0.0011) -[2023-11-28 06:01:23,135][87424] Updated weights for policy 0, policy_version 222007 (0.0010) -[2023-11-28 06:01:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 113565696. Throughput: 0: 2700.5, 1: 2700.9. Samples: 113583708. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:23,445][86177] Avg episode reward: [(0, '-508.610'), (1, '-514.680')] -[2023-11-28 06:01:24,884][87426] Updated weights for policy 1, policy_version 221640 (0.0010) -[2023-11-28 06:01:25,262][87426] Updated weights for policy 1, policy_version 221650 (0.0008) -[2023-11-28 06:01:25,600][87424] Updated weights for policy 0, policy_version 222017 (0.0007) -[2023-11-28 06:01:25,641][87426] Updated weights for policy 1, policy_version 221660 (0.0007) -[2023-11-28 06:01:25,989][87424] Updated weights for policy 0, policy_version 222027 (0.0008) -[2023-11-28 06:01:26,384][87424] Updated weights for policy 0, policy_version 222037 (0.0009) -[2023-11-28 06:01:26,773][87424] Updated weights for policy 0, policy_version 222047 (0.0010) -[2023-11-28 06:01:27,433][87426] Updated weights for policy 1, policy_version 221670 (0.0008) -[2023-11-28 06:01:27,815][87426] Updated weights for policy 1, policy_version 221680 (0.0007) -[2023-11-28 06:01:28,199][87426] Updated weights for policy 1, policy_version 221690 (0.0007) -[2023-11-28 06:01:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 113598464. Throughput: 0: 2703.7, 1: 2725.2. Samples: 113608508. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:28,445][86177] Avg episode reward: [(0, '-503.230'), (1, '-518.220')] -[2023-11-28 06:01:29,055][87424] Updated weights for policy 0, policy_version 222057 (0.0009) -[2023-11-28 06:01:29,423][87424] Updated weights for policy 0, policy_version 222067 (0.0008) -[2023-11-28 06:01:29,820][87424] Updated weights for policy 0, policy_version 222077 (0.0008) -[2023-11-28 06:01:30,759][87426] Updated weights for policy 1, policy_version 221700 (0.0007) -[2023-11-28 06:01:31,150][87426] Updated weights for policy 1, policy_version 221710 (0.0008) -[2023-11-28 06:01:31,518][87426] Updated weights for policy 1, policy_version 221720 (0.0008) -[2023-11-28 06:01:32,348][87424] Updated weights for policy 0, policy_version 222087 (0.0011) -[2023-11-28 06:01:32,727][87424] Updated weights for policy 0, policy_version 222097 (0.0012) -[2023-11-28 06:01:33,115][87424] Updated weights for policy 0, policy_version 222107 (0.0012) -[2023-11-28 06:01:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 113623040. Throughput: 0: 2706.4, 1: 2697.5. Samples: 113632744. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:33,445][86177] Avg episode reward: [(0, '-503.820'), (1, '-513.620')] -[2023-11-28 06:01:33,629][87426] Updated weights for policy 1, policy_version 221730 (0.0010) -[2023-11-28 06:01:34,029][87426] Updated weights for policy 1, policy_version 221740 (0.0011) -[2023-11-28 06:01:34,409][87426] Updated weights for policy 1, policy_version 221750 (0.0012) -[2023-11-28 06:01:34,788][87426] Updated weights for policy 1, policy_version 221760 (0.0012) -[2023-11-28 06:01:35,333][87424] Updated weights for policy 0, policy_version 222117 (0.0012) -[2023-11-28 06:01:35,721][87424] Updated weights for policy 0, policy_version 222127 (0.0012) -[2023-11-28 06:01:36,097][87424] Updated weights for policy 0, policy_version 222137 (0.0012) -[2023-11-28 06:01:36,714][87426] Updated weights for policy 1, policy_version 221770 (0.0012) -[2023-11-28 06:01:37,089][87426] Updated weights for policy 1, policy_version 221780 (0.0011) -[2023-11-28 06:01:37,466][87426] Updated weights for policy 1, policy_version 221790 (0.0010) -[2023-11-28 06:01:37,989][87424] Updated weights for policy 0, policy_version 222147 (0.0011) -[2023-11-28 06:01:38,377][87424] Updated weights for policy 0, policy_version 222157 (0.0012) -[2023-11-28 06:01:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 113647616. Throughput: 0: 2725.9, 1: 2716.4. Samples: 113666180. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:38,445][86177] Avg episode reward: [(0, '-508.760'), (1, '-506.620')] -[2023-11-28 06:01:38,756][87424] Updated weights for policy 0, policy_version 222167 (0.0012) -[2023-11-28 06:01:39,415][87426] Updated weights for policy 1, policy_version 221800 (0.0008) -[2023-11-28 06:01:39,793][87426] Updated weights for policy 1, policy_version 221810 (0.0009) -[2023-11-28 06:01:40,170][87426] Updated weights for policy 1, policy_version 221820 (0.0011) -[2023-11-28 06:01:40,582][87424] Updated weights for policy 0, policy_version 222177 (0.0012) -[2023-11-28 06:01:40,968][87424] Updated weights for policy 0, policy_version 222187 (0.0010) -[2023-11-28 06:01:41,354][87424] Updated weights for policy 0, policy_version 222197 (0.0008) -[2023-11-28 06:01:41,726][87424] Updated weights for policy 0, policy_version 222207 (0.0009) -[2023-11-28 06:01:42,348][87426] Updated weights for policy 1, policy_version 221830 (0.0011) -[2023-11-28 06:01:42,720][87426] Updated weights for policy 1, policy_version 221840 (0.0008) -[2023-11-28 06:01:43,097][87426] Updated weights for policy 1, policy_version 221850 (0.0011) -[2023-11-28 06:01:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 113680384. Throughput: 0: 2717.7, 1: 2727.8. Samples: 113690672. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:43,445][86177] Avg episode reward: [(0, '-512.850'), (1, '-521.840')] -[2023-11-28 06:01:44,067][87424] Updated weights for policy 0, policy_version 222217 (0.0008) -[2023-11-28 06:01:44,458][87424] Updated weights for policy 0, policy_version 222227 (0.0008) -[2023-11-28 06:01:44,838][87424] Updated weights for policy 0, policy_version 222237 (0.0008) -[2023-11-28 06:01:45,602][87426] Updated weights for policy 1, policy_version 221860 (0.0010) -[2023-11-28 06:01:45,981][87426] Updated weights for policy 1, policy_version 221870 (0.0008) -[2023-11-28 06:01:46,366][87426] Updated weights for policy 1, policy_version 221880 (0.0011) -[2023-11-28 06:01:47,221][87424] Updated weights for policy 0, policy_version 222247 (0.0008) -[2023-11-28 06:01:47,605][87424] Updated weights for policy 0, policy_version 222257 (0.0008) -[2023-11-28 06:01:47,980][87424] Updated weights for policy 0, policy_version 222267 (0.0010) -[2023-11-28 06:01:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 113704960. Throughput: 0: 2698.0, 1: 2733.0. Samples: 113714488. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:48,445][86177] Avg episode reward: [(0, '-514.810'), (1, '-515.840')] -[2023-11-28 06:01:48,644][87426] Updated weights for policy 1, policy_version 221890 (0.0011) -[2023-11-28 06:01:49,015][87426] Updated weights for policy 1, policy_version 221900 (0.0011) -[2023-11-28 06:01:49,396][87426] Updated weights for policy 1, policy_version 221910 (0.0010) -[2023-11-28 06:01:49,774][87426] Updated weights for policy 1, policy_version 221920 (0.0009) -[2023-11-28 06:01:49,876][87424] Updated weights for policy 0, policy_version 222277 (0.0010) -[2023-11-28 06:01:50,247][87424] Updated weights for policy 0, policy_version 222287 (0.0008) -[2023-11-28 06:01:50,630][87424] Updated weights for policy 0, policy_version 222297 (0.0010) -[2023-11-28 06:01:51,939][87426] Updated weights for policy 1, policy_version 221930 (0.0011) -[2023-11-28 06:01:52,315][87426] Updated weights for policy 1, policy_version 221940 (0.0011) -[2023-11-28 06:01:52,656][87424] Updated weights for policy 0, policy_version 222307 (0.0012) -[2023-11-28 06:01:52,697][87426] Updated weights for policy 1, policy_version 221950 (0.0008) -[2023-11-28 06:01:53,040][87424] Updated weights for policy 0, policy_version 222317 (0.0012) -[2023-11-28 06:01:53,411][87424] Updated weights for policy 0, policy_version 222327 (0.0018) -[2023-11-28 06:01:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 113729536. Throughput: 0: 2669.5, 1: 2734.8. Samples: 113747308. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:53,445][86177] Avg episode reward: [(0, '-525.930'), (1, '-515.980')] -[2023-11-28 06:01:55,051][87426] Updated weights for policy 1, policy_version 221960 (0.0010) -[2023-11-28 06:01:55,433][87426] Updated weights for policy 1, policy_version 221970 (0.0007) -[2023-11-28 06:01:55,811][87426] Updated weights for policy 1, policy_version 221980 (0.0007) -[2023-11-28 06:01:55,858][87424] Updated weights for policy 0, policy_version 222337 (0.0012) -[2023-11-28 06:01:56,231][87424] Updated weights for policy 0, policy_version 222347 (0.0011) -[2023-11-28 06:01:56,614][87424] Updated weights for policy 0, policy_version 222357 (0.0007) -[2023-11-28 06:01:57,001][87424] Updated weights for policy 0, policy_version 222367 (0.0008) -[2023-11-28 06:01:57,899][87426] Updated weights for policy 1, policy_version 221990 (0.0009) -[2023-11-28 06:01:58,279][87426] Updated weights for policy 1, policy_version 222000 (0.0010) -[2023-11-28 06:01:58,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 113754112. Throughput: 0: 2675.3, 1: 2760.8. Samples: 113772216. Policy #0 lag: (min: 31.0, avg: 42.5, max: 63.0) -[2023-11-28 06:01:58,446][86177] Avg episode reward: [(0, '-525.640'), (1, '-523.100')] -[2023-11-28 06:01:58,671][87426] Updated weights for policy 1, policy_version 222010 (0.0012) -[2023-11-28 06:01:59,036][87424] Updated weights for policy 0, policy_version 222377 (0.0010) -[2023-11-28 06:01:59,419][87424] Updated weights for policy 0, policy_version 222387 (0.0008) -[2023-11-28 06:01:59,793][87424] Updated weights for policy 0, policy_version 222397 (0.0008) -[2023-11-28 06:02:00,445][87426] Updated weights for policy 1, policy_version 222020 (0.0010) -[2023-11-28 06:02:00,824][87426] Updated weights for policy 1, policy_version 222030 (0.0008) -[2023-11-28 06:02:01,210][87426] Updated weights for policy 1, policy_version 222040 (0.0008) -[2023-11-28 06:02:02,234][87424] Updated weights for policy 0, policy_version 222407 (0.0012) -[2023-11-28 06:02:02,618][87424] Updated weights for policy 0, policy_version 222417 (0.0012) -[2023-11-28 06:02:03,007][87424] Updated weights for policy 0, policy_version 222427 (0.0012) -[2023-11-28 06:02:03,069][87426] Updated weights for policy 1, policy_version 222050 (0.0008) -[2023-11-28 06:02:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 113786880. Throughput: 0: 2670.1, 1: 2766.4. Samples: 113796724. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:03,445][86177] Avg episode reward: [(0, '-519.800'), (1, '-508.900')] -[2023-11-28 06:02:03,449][87426] Updated weights for policy 1, policy_version 222060 (0.0011) -[2023-11-28 06:02:03,826][87426] Updated weights for policy 1, policy_version 222070 (0.0012) -[2023-11-28 06:02:04,201][87426] Updated weights for policy 1, policy_version 222080 (0.0012) -[2023-11-28 06:02:05,192][87424] Updated weights for policy 0, policy_version 222437 (0.0012) -[2023-11-28 06:02:05,582][87424] Updated weights for policy 0, policy_version 222447 (0.0012) -[2023-11-28 06:02:05,971][87424] Updated weights for policy 0, policy_version 222457 (0.0011) -[2023-11-28 06:02:06,001][87426] Updated weights for policy 1, policy_version 222090 (0.0008) -[2023-11-28 06:02:06,377][87426] Updated weights for policy 1, policy_version 222100 (0.0007) -[2023-11-28 06:02:06,750][87426] Updated weights for policy 1, policy_version 222110 (0.0008) -[2023-11-28 06:02:08,126][87424] Updated weights for policy 0, policy_version 222467 (0.0010) -[2023-11-28 06:02:08,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 113811456. Throughput: 0: 2688.4, 1: 2796.8. Samples: 113830540. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:08,445][86177] Avg episode reward: [(0, '-519.270'), (1, '-515.190')] -[2023-11-28 06:02:08,509][87424] Updated weights for policy 0, policy_version 222477 (0.0012) -[2023-11-28 06:02:08,885][87424] Updated weights for policy 0, policy_version 222487 (0.0010) -[2023-11-28 06:02:09,126][87426] Updated weights for policy 1, policy_version 222120 (0.0010) -[2023-11-28 06:02:09,500][87426] Updated weights for policy 1, policy_version 222130 (0.0012) -[2023-11-28 06:02:09,875][87426] Updated weights for policy 1, policy_version 222140 (0.0012) -[2023-11-28 06:02:11,434][87424] Updated weights for policy 0, policy_version 222497 (0.0009) -[2023-11-28 06:02:11,814][87424] Updated weights for policy 0, policy_version 222507 (0.0012) -[2023-11-28 06:02:11,961][87426] Updated weights for policy 1, policy_version 222150 (0.0012) -[2023-11-28 06:02:12,190][87424] Updated weights for policy 0, policy_version 222517 (0.0012) -[2023-11-28 06:02:12,334][87426] Updated weights for policy 1, policy_version 222160 (0.0010) -[2023-11-28 06:02:12,571][87424] Updated weights for policy 0, policy_version 222527 (0.0011) -[2023-11-28 06:02:12,719][87426] Updated weights for policy 1, policy_version 222170 (0.0007) -[2023-11-28 06:02:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 113844224. Throughput: 0: 2686.7, 1: 2765.6. Samples: 113853860. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:13,445][86177] Avg episode reward: [(0, '-512.070'), (1, '-509.560')] -[2023-11-28 06:02:14,842][87424] Updated weights for policy 0, policy_version 222537 (0.0012) -[2023-11-28 06:02:15,223][87424] Updated weights for policy 0, policy_version 222547 (0.0011) -[2023-11-28 06:02:15,263][87426] Updated weights for policy 1, policy_version 222180 (0.0009) -[2023-11-28 06:02:15,614][87424] Updated weights for policy 0, policy_version 222557 (0.0010) -[2023-11-28 06:02:15,645][87426] Updated weights for policy 1, policy_version 222190 (0.0011) -[2023-11-28 06:02:16,017][87426] Updated weights for policy 1, policy_version 222200 (0.0011) -[2023-11-28 06:02:17,569][87424] Updated weights for policy 0, policy_version 222567 (0.0011) -[2023-11-28 06:02:17,941][87424] Updated weights for policy 0, policy_version 222577 (0.0011) -[2023-11-28 06:02:18,332][87424] Updated weights for policy 0, policy_version 222587 (0.0009) -[2023-11-28 06:02:18,346][87426] Updated weights for policy 1, policy_version 222210 (0.0009) -[2023-11-28 06:02:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 113860608. Throughput: 0: 2669.9, 1: 2756.3. Samples: 113876928. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:18,445][86177] Avg episode reward: [(0, '-511.060'), (1, '-513.870')] -[2023-11-28 06:02:18,518][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000222592_56983552.pth... -[2023-11-28 06:02:18,549][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000220064_56336384.pth -[2023-11-28 06:02:18,724][87426] Updated weights for policy 1, policy_version 222220 (0.0009) -[2023-11-28 06:02:19,105][87426] Updated weights for policy 1, policy_version 222230 (0.0011) -[2023-11-28 06:02:19,480][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000222240_56893440.pth... -[2023-11-28 06:02:19,481][87426] Updated weights for policy 1, policy_version 222240 (0.0010) -[2023-11-28 06:02:19,526][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000219680_56238080.pth -[2023-11-28 06:02:20,429][87424] Updated weights for policy 0, policy_version 222597 (0.0011) -[2023-11-28 06:02:20,808][87424] Updated weights for policy 0, policy_version 222607 (0.0012) -[2023-11-28 06:02:21,195][87424] Updated weights for policy 0, policy_version 222617 (0.0012) -[2023-11-28 06:02:21,992][87426] Updated weights for policy 1, policy_version 222250 (0.0010) -[2023-11-28 06:02:22,367][87426] Updated weights for policy 1, policy_version 222260 (0.0010) -[2023-11-28 06:02:22,745][87426] Updated weights for policy 1, policy_version 222270 (0.0011) -[2023-11-28 06:02:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 113893376. Throughput: 0: 2668.1, 1: 2718.2. Samples: 113908564. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:23,445][86177] Avg episode reward: [(0, '-516.490'), (1, '-518.500')] -[2023-11-28 06:02:23,472][87424] Updated weights for policy 0, policy_version 222627 (0.0011) -[2023-11-28 06:02:23,855][87424] Updated weights for policy 0, policy_version 222637 (0.0011) -[2023-11-28 06:02:24,234][87424] Updated weights for policy 0, policy_version 222647 (0.0011) -[2023-11-28 06:02:25,022][87426] Updated weights for policy 1, policy_version 222280 (0.0011) -[2023-11-28 06:02:25,392][87426] Updated weights for policy 1, policy_version 222290 (0.0010) -[2023-11-28 06:02:25,776][87426] Updated weights for policy 1, policy_version 222300 (0.0008) -[2023-11-28 06:02:26,569][87424] Updated weights for policy 0, policy_version 222657 (0.0010) -[2023-11-28 06:02:26,957][87424] Updated weights for policy 0, policy_version 222667 (0.0012) -[2023-11-28 06:02:27,345][87424] Updated weights for policy 0, policy_version 222677 (0.0007) -[2023-11-28 06:02:27,735][87424] Updated weights for policy 0, policy_version 222687 (0.0007) -[2023-11-28 06:02:28,309][87426] Updated weights for policy 1, policy_version 222310 (0.0007) -[2023-11-28 06:02:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 113917952. Throughput: 0: 2676.9, 1: 2687.4. Samples: 113932064. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:28,445][86177] Avg episode reward: [(0, '-518.910'), (1, '-518.600')] -[2023-11-28 06:02:28,684][87426] Updated weights for policy 1, policy_version 222320 (0.0008) -[2023-11-28 06:02:29,063][87426] Updated weights for policy 1, policy_version 222330 (0.0008) -[2023-11-28 06:02:29,821][87424] Updated weights for policy 0, policy_version 222697 (0.0011) -[2023-11-28 06:02:30,212][87424] Updated weights for policy 0, policy_version 222707 (0.0012) -[2023-11-28 06:02:30,597][87424] Updated weights for policy 0, policy_version 222717 (0.0012) -[2023-11-28 06:02:31,308][87426] Updated weights for policy 1, policy_version 222340 (0.0010) -[2023-11-28 06:02:31,684][87426] Updated weights for policy 1, policy_version 222350 (0.0012) -[2023-11-28 06:02:32,065][87426] Updated weights for policy 1, policy_version 222360 (0.0012) -[2023-11-28 06:02:32,332][87424] Updated weights for policy 0, policy_version 222727 (0.0011) -[2023-11-28 06:02:32,703][87424] Updated weights for policy 0, policy_version 222737 (0.0012) -[2023-11-28 06:02:33,088][87424] Updated weights for policy 0, policy_version 222747 (0.0012) -[2023-11-28 06:02:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 113950720. Throughput: 0: 2712.0, 1: 2696.6. Samples: 113957876. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:33,445][86177] Avg episode reward: [(0, '-526.480'), (1, '-523.170')] -[2023-11-28 06:02:34,461][87426] Updated weights for policy 1, policy_version 222370 (0.0009) -[2023-11-28 06:02:34,788][87424] Updated weights for policy 0, policy_version 222757 (0.0010) -[2023-11-28 06:02:34,848][87426] Updated weights for policy 1, policy_version 222380 (0.0010) -[2023-11-28 06:02:35,162][87424] Updated weights for policy 0, policy_version 222767 (0.0010) -[2023-11-28 06:02:35,223][87426] Updated weights for policy 1, policy_version 222390 (0.0011) -[2023-11-28 06:02:35,547][87424] Updated weights for policy 0, policy_version 222777 (0.0009) -[2023-11-28 06:02:35,598][87426] Updated weights for policy 1, policy_version 222400 (0.0012) -[2023-11-28 06:02:37,637][87426] Updated weights for policy 1, policy_version 222410 (0.0012) -[2023-11-28 06:02:38,008][87426] Updated weights for policy 1, policy_version 222420 (0.0011) -[2023-11-28 06:02:38,074][87424] Updated weights for policy 0, policy_version 222787 (0.0009) -[2023-11-28 06:02:38,392][87426] Updated weights for policy 1, policy_version 222430 (0.0011) -[2023-11-28 06:02:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 113967104. Throughput: 0: 2731.6, 1: 2686.5. Samples: 113991124. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:38,445][86177] Avg episode reward: [(0, '-522.510'), (1, '-518.960')] -[2023-11-28 06:02:38,454][87424] Updated weights for policy 0, policy_version 222797 (0.0011) -[2023-11-28 06:02:38,835][87424] Updated weights for policy 0, policy_version 222807 (0.0012) -[2023-11-28 06:02:40,772][87426] Updated weights for policy 1, policy_version 222440 (0.0010) -[2023-11-28 06:02:41,065][87424] Updated weights for policy 0, policy_version 222817 (0.0012) -[2023-11-28 06:02:41,159][87426] Updated weights for policy 1, policy_version 222450 (0.0011) -[2023-11-28 06:02:41,444][87424] Updated weights for policy 0, policy_version 222827 (0.0012) -[2023-11-28 06:02:41,531][87426] Updated weights for policy 1, policy_version 222460 (0.0011) -[2023-11-28 06:02:41,827][87424] Updated weights for policy 0, policy_version 222837 (0.0011) -[2023-11-28 06:02:42,213][87424] Updated weights for policy 0, policy_version 222847 (0.0009) -[2023-11-28 06:02:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 113999872. Throughput: 0: 2726.9, 1: 2667.8. Samples: 114014976. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:43,445][86177] Avg episode reward: [(0, '-513.440'), (1, '-518.000')] -[2023-11-28 06:02:43,924][87426] Updated weights for policy 1, policy_version 222470 (0.0010) -[2023-11-28 06:02:44,252][87424] Updated weights for policy 0, policy_version 222857 (0.0010) -[2023-11-28 06:02:44,304][87426] Updated weights for policy 1, policy_version 222480 (0.0011) -[2023-11-28 06:02:44,632][87424] Updated weights for policy 0, policy_version 222867 (0.0010) -[2023-11-28 06:02:44,681][87426] Updated weights for policy 1, policy_version 222490 (0.0011) -[2023-11-28 06:02:45,019][87424] Updated weights for policy 0, policy_version 222877 (0.0010) -[2023-11-28 06:02:46,584][87426] Updated weights for policy 1, policy_version 222500 (0.0009) -[2023-11-28 06:02:46,961][87426] Updated weights for policy 1, policy_version 222510 (0.0011) -[2023-11-28 06:02:46,988][87424] Updated weights for policy 0, policy_version 222887 (0.0010) -[2023-11-28 06:02:47,337][87426] Updated weights for policy 1, policy_version 222520 (0.0010) -[2023-11-28 06:02:47,376][87424] Updated weights for policy 0, policy_version 222897 (0.0012) -[2023-11-28 06:02:47,758][87424] Updated weights for policy 0, policy_version 222907 (0.0009) -[2023-11-28 06:02:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114032640. Throughput: 0: 2737.5, 1: 2660.2. Samples: 114039620. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:48,445][86177] Avg episode reward: [(0, '-513.650'), (1, '-520.550')] -[2023-11-28 06:02:49,602][87424] Updated weights for policy 0, policy_version 222917 (0.0012) -[2023-11-28 06:02:49,671][87426] Updated weights for policy 1, policy_version 222530 (0.0011) -[2023-11-28 06:02:49,978][87424] Updated weights for policy 0, policy_version 222927 (0.0011) -[2023-11-28 06:02:50,047][87426] Updated weights for policy 1, policy_version 222540 (0.0011) -[2023-11-28 06:02:50,361][87424] Updated weights for policy 0, policy_version 222937 (0.0009) -[2023-11-28 06:02:50,421][87426] Updated weights for policy 1, policy_version 222550 (0.0011) -[2023-11-28 06:02:50,805][87426] Updated weights for policy 1, policy_version 222560 (0.0008) -[2023-11-28 06:02:52,564][87424] Updated weights for policy 0, policy_version 222947 (0.0009) -[2023-11-28 06:02:52,943][87424] Updated weights for policy 0, policy_version 222957 (0.0010) -[2023-11-28 06:02:53,292][87426] Updated weights for policy 1, policy_version 222570 (0.0008) -[2023-11-28 06:02:53,320][87424] Updated weights for policy 0, policy_version 222967 (0.0011) -[2023-11-28 06:02:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 114049024. Throughput: 0: 2736.3, 1: 2624.4. Samples: 114071768. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:53,445][86177] Avg episode reward: [(0, '-507.220'), (1, '-525.510')] -[2023-11-28 06:02:53,675][87426] Updated weights for policy 1, policy_version 222580 (0.0010) -[2023-11-28 06:02:54,049][87426] Updated weights for policy 1, policy_version 222590 (0.0008) -[2023-11-28 06:02:55,872][87424] Updated weights for policy 0, policy_version 222977 (0.0010) -[2023-11-28 06:02:56,263][87424] Updated weights for policy 0, policy_version 222987 (0.0008) -[2023-11-28 06:02:56,584][87426] Updated weights for policy 1, policy_version 222600 (0.0007) -[2023-11-28 06:02:56,639][87424] Updated weights for policy 0, policy_version 222997 (0.0010) -[2023-11-28 06:02:56,946][87426] Updated weights for policy 1, policy_version 222610 (0.0007) -[2023-11-28 06:02:57,024][87424] Updated weights for policy 0, policy_version 223007 (0.0008) -[2023-11-28 06:02:57,331][87426] Updated weights for policy 1, policy_version 222620 (0.0009) -[2023-11-28 06:02:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114081792. Throughput: 0: 2756.3, 1: 2636.8. Samples: 114096552. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:02:58,446][86177] Avg episode reward: [(0, '-544.430'), (1, '-533.410')] -[2023-11-28 06:02:59,129][87426] Updated weights for policy 1, policy_version 222630 (0.0011) -[2023-11-28 06:02:59,213][87424] Updated weights for policy 0, policy_version 223017 (0.0008) -[2023-11-28 06:02:59,510][87426] Updated weights for policy 1, policy_version 222640 (0.0010) -[2023-11-28 06:02:59,596][87424] Updated weights for policy 0, policy_version 223027 (0.0008) -[2023-11-28 06:02:59,893][87426] Updated weights for policy 1, policy_version 222650 (0.0011) -[2023-11-28 06:02:59,989][87424] Updated weights for policy 0, policy_version 223037 (0.0011) -[2023-11-28 06:03:01,963][87424] Updated weights for policy 0, policy_version 223047 (0.0012) -[2023-11-28 06:03:02,077][87426] Updated weights for policy 1, policy_version 222660 (0.0011) -[2023-11-28 06:03:02,336][87424] Updated weights for policy 0, policy_version 223057 (0.0011) -[2023-11-28 06:03:02,458][87426] Updated weights for policy 1, policy_version 222670 (0.0011) -[2023-11-28 06:03:02,724][87424] Updated weights for policy 0, policy_version 223067 (0.0008) -[2023-11-28 06:03:02,834][87426] Updated weights for policy 1, policy_version 222680 (0.0011) -[2023-11-28 06:03:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114114560. Throughput: 0: 2789.8, 1: 2658.9. Samples: 114122120. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:03:03,445][86177] Avg episode reward: [(0, '-542.520'), (1, '-524.720')] -[2023-11-28 06:03:04,619][87424] Updated weights for policy 0, policy_version 223077 (0.0008) -[2023-11-28 06:03:04,939][87426] Updated weights for policy 1, policy_version 222690 (0.0011) -[2023-11-28 06:03:05,001][87424] Updated weights for policy 0, policy_version 223087 (0.0008) -[2023-11-28 06:03:05,311][87426] Updated weights for policy 1, policy_version 222700 (0.0010) -[2023-11-28 06:03:05,388][87424] Updated weights for policy 0, policy_version 223097 (0.0011) -[2023-11-28 06:03:05,689][87426] Updated weights for policy 1, policy_version 222710 (0.0008) -[2023-11-28 06:03:06,076][87426] Updated weights for policy 1, policy_version 222720 (0.0008) -[2023-11-28 06:03:07,743][87424] Updated weights for policy 0, policy_version 223107 (0.0010) -[2023-11-28 06:03:08,121][87424] Updated weights for policy 0, policy_version 223117 (0.0012) -[2023-11-28 06:03:08,392][87426] Updated weights for policy 1, policy_version 222730 (0.0008) -[2023-11-28 06:03:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 114130944. Throughput: 0: 2796.7, 1: 2681.9. Samples: 114155100. Policy #0 lag: (min: 7.0, avg: 22.6, max: 39.0) -[2023-11-28 06:03:08,445][86177] Avg episode reward: [(0, '-542.760'), (1, '-547.150')] -[2023-11-28 06:03:08,513][87424] Updated weights for policy 0, policy_version 223127 (0.0012) -[2023-11-28 06:03:08,778][87426] Updated weights for policy 1, policy_version 222740 (0.0008) -[2023-11-28 06:03:09,153][87426] Updated weights for policy 1, policy_version 222750 (0.0008) -[2023-11-28 06:03:10,801][87424] Updated weights for policy 0, policy_version 223137 (0.0011) -[2023-11-28 06:03:11,143][87426] Updated weights for policy 1, policy_version 222760 (0.0010) -[2023-11-28 06:03:11,174][87424] Updated weights for policy 0, policy_version 223147 (0.0007) -[2023-11-28 06:03:11,519][87426] Updated weights for policy 1, policy_version 222770 (0.0007) -[2023-11-28 06:03:11,558][87424] Updated weights for policy 0, policy_version 223157 (0.0008) -[2023-11-28 06:03:11,894][87426] Updated weights for policy 1, policy_version 222780 (0.0011) -[2023-11-28 06:03:11,937][87424] Updated weights for policy 0, policy_version 223167 (0.0010) -[2023-11-28 06:03:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 114163712. Throughput: 0: 2788.2, 1: 2715.8. Samples: 114179744. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:13,445][86177] Avg episode reward: [(0, '-541.200'), (1, '-541.010')] -[2023-11-28 06:03:13,718][87426] Updated weights for policy 1, policy_version 222790 (0.0012) -[2023-11-28 06:03:14,095][87426] Updated weights for policy 1, policy_version 222800 (0.0010) -[2023-11-28 06:03:14,402][87424] Updated weights for policy 0, policy_version 223177 (0.0012) -[2023-11-28 06:03:14,485][87426] Updated weights for policy 1, policy_version 222810 (0.0009) -[2023-11-28 06:03:14,783][87424] Updated weights for policy 0, policy_version 223187 (0.0013) -[2023-11-28 06:03:15,168][87424] Updated weights for policy 0, policy_version 223197 (0.0011) -[2023-11-28 06:03:16,279][87426] Updated weights for policy 1, policy_version 222820 (0.0010) -[2023-11-28 06:03:16,651][87426] Updated weights for policy 1, policy_version 222830 (0.0007) -[2023-11-28 06:03:17,027][87426] Updated weights for policy 1, policy_version 222840 (0.0007) -[2023-11-28 06:03:17,065][87424] Updated weights for policy 0, policy_version 223207 (0.0011) -[2023-11-28 06:03:17,442][87424] Updated weights for policy 0, policy_version 223217 (0.0008) -[2023-11-28 06:03:17,831][87424] Updated weights for policy 0, policy_version 223227 (0.0007) -[2023-11-28 06:03:18,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 114196480. Throughput: 0: 2746.0, 1: 2701.8. Samples: 114203024. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:18,445][86177] Avg episode reward: [(0, '-504.690'), (1, '-549.560')] -[2023-11-28 06:03:19,552][87426] Updated weights for policy 1, policy_version 222850 (0.0008) -[2023-11-28 06:03:19,915][87424] Updated weights for policy 0, policy_version 223237 (0.0010) -[2023-11-28 06:03:19,934][87426] Updated weights for policy 1, policy_version 222860 (0.0011) -[2023-11-28 06:03:20,301][87424] Updated weights for policy 0, policy_version 223247 (0.0012) -[2023-11-28 06:03:20,313][87426] Updated weights for policy 1, policy_version 222870 (0.0010) -[2023-11-28 06:03:20,671][87424] Updated weights for policy 0, policy_version 223257 (0.0011) -[2023-11-28 06:03:20,686][87426] Updated weights for policy 1, policy_version 222880 (0.0010) -[2023-11-28 06:03:23,218][87424] Updated weights for policy 0, policy_version 223267 (0.0010) -[2023-11-28 06:03:23,259][87426] Updated weights for policy 1, policy_version 222890 (0.0008) -[2023-11-28 06:03:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 114212864. Throughput: 0: 2713.1, 1: 2694.5. Samples: 114234464. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:23,445][86177] Avg episode reward: [(0, '-504.200'), (1, '-550.290')] -[2023-11-28 06:03:23,598][87424] Updated weights for policy 0, policy_version 223277 (0.0009) -[2023-11-28 06:03:23,636][87426] Updated weights for policy 1, policy_version 222900 (0.0009) -[2023-11-28 06:03:23,986][87424] Updated weights for policy 0, policy_version 223287 (0.0012) -[2023-11-28 06:03:24,012][87426] Updated weights for policy 1, policy_version 222910 (0.0010) -[2023-11-28 06:03:25,815][87426] Updated weights for policy 1, policy_version 222920 (0.0012) -[2023-11-28 06:03:26,198][87426] Updated weights for policy 1, policy_version 222930 (0.0012) -[2023-11-28 06:03:26,210][87424] Updated weights for policy 0, policy_version 223297 (0.0012) -[2023-11-28 06:03:26,570][87426] Updated weights for policy 1, policy_version 222940 (0.0012) -[2023-11-28 06:03:26,596][87424] Updated weights for policy 0, policy_version 223307 (0.0012) -[2023-11-28 06:03:26,985][87424] Updated weights for policy 0, policy_version 223317 (0.0011) -[2023-11-28 06:03:27,365][87424] Updated weights for policy 0, policy_version 223327 (0.0012) -[2023-11-28 06:03:28,279][87426] Updated weights for policy 1, policy_version 222950 (0.0011) -[2023-11-28 06:03:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114245632. Throughput: 0: 2716.6, 1: 2752.3. Samples: 114261076. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:28,445][86177] Avg episode reward: [(0, '-497.380'), (1, '-523.940')] -[2023-11-28 06:03:28,654][87426] Updated weights for policy 1, policy_version 222960 (0.0010) -[2023-11-28 06:03:29,044][87426] Updated weights for policy 1, policy_version 222970 (0.0011) -[2023-11-28 06:03:29,053][87424] Updated weights for policy 0, policy_version 223337 (0.0012) -[2023-11-28 06:03:29,431][87424] Updated weights for policy 0, policy_version 223347 (0.0010) -[2023-11-28 06:03:29,810][87424] Updated weights for policy 0, policy_version 223357 (0.0011) -[2023-11-28 06:03:30,763][87426] Updated weights for policy 1, policy_version 222980 (0.0011) -[2023-11-28 06:03:31,141][87426] Updated weights for policy 1, policy_version 222990 (0.0012) -[2023-11-28 06:03:31,517][87426] Updated weights for policy 1, policy_version 223000 (0.0011) -[2023-11-28 06:03:32,173][87424] Updated weights for policy 0, policy_version 223367 (0.0012) -[2023-11-28 06:03:32,547][87424] Updated weights for policy 0, policy_version 223377 (0.0012) -[2023-11-28 06:03:32,929][87424] Updated weights for policy 0, policy_version 223387 (0.0012) -[2023-11-28 06:03:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114278400. Throughput: 0: 2722.8, 1: 2742.9. Samples: 114285580. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:33,445][86177] Avg episode reward: [(0, '-500.030'), (1, '-524.830')] -[2023-11-28 06:03:34,044][87426] Updated weights for policy 1, policy_version 223010 (0.0011) -[2023-11-28 06:03:34,414][87426] Updated weights for policy 1, policy_version 223020 (0.0012) -[2023-11-28 06:03:34,793][87426] Updated weights for policy 1, policy_version 223030 (0.0012) -[2023-11-28 06:03:35,174][87426] Updated weights for policy 1, policy_version 223040 (0.0012) -[2023-11-28 06:03:35,529][87424] Updated weights for policy 0, policy_version 223397 (0.0012) -[2023-11-28 06:03:35,920][87424] Updated weights for policy 0, policy_version 223407 (0.0010) -[2023-11-28 06:03:36,303][87424] Updated weights for policy 0, policy_version 223417 (0.0012) -[2023-11-28 06:03:37,306][87426] Updated weights for policy 1, policy_version 223050 (0.0009) -[2023-11-28 06:03:37,678][87426] Updated weights for policy 1, policy_version 223060 (0.0008) -[2023-11-28 06:03:38,057][87426] Updated weights for policy 1, policy_version 223070 (0.0010) -[2023-11-28 06:03:38,102][87424] Updated weights for policy 0, policy_version 223427 (0.0010) -[2023-11-28 06:03:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 114302976. Throughput: 0: 2738.9, 1: 2774.8. Samples: 114319884. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:38,445][86177] Avg episode reward: [(0, '-499.400'), (1, '-506.020')] -[2023-11-28 06:03:38,484][87424] Updated weights for policy 0, policy_version 223437 (0.0007) -[2023-11-28 06:03:38,870][87424] Updated weights for policy 0, policy_version 223447 (0.0008) -[2023-11-28 06:03:40,030][87426] Updated weights for policy 1, policy_version 223080 (0.0010) -[2023-11-28 06:03:40,402][87426] Updated weights for policy 1, policy_version 223090 (0.0008) -[2023-11-28 06:03:40,785][87426] Updated weights for policy 1, policy_version 223100 (0.0010) -[2023-11-28 06:03:40,987][87424] Updated weights for policy 0, policy_version 223457 (0.0008) -[2023-11-28 06:03:41,375][87424] Updated weights for policy 0, policy_version 223467 (0.0010) -[2023-11-28 06:03:41,759][87424] Updated weights for policy 0, policy_version 223477 (0.0009) -[2023-11-28 06:03:42,140][87424] Updated weights for policy 0, policy_version 223487 (0.0009) -[2023-11-28 06:03:43,361][87426] Updated weights for policy 1, policy_version 223110 (0.0008) -[2023-11-28 06:03:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114327552. Throughput: 0: 2716.2, 1: 2774.9. Samples: 114343652. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:43,445][86177] Avg episode reward: [(0, '-508.670'), (1, '-516.410')] -[2023-11-28 06:03:43,744][87426] Updated weights for policy 1, policy_version 223120 (0.0010) -[2023-11-28 06:03:44,099][87424] Updated weights for policy 0, policy_version 223497 (0.0011) -[2023-11-28 06:03:44,123][87426] Updated weights for policy 1, policy_version 223130 (0.0010) -[2023-11-28 06:03:44,471][87424] Updated weights for policy 0, policy_version 223507 (0.0008) -[2023-11-28 06:03:44,853][87424] Updated weights for policy 0, policy_version 223517 (0.0008) -[2023-11-28 06:03:46,272][87426] Updated weights for policy 1, policy_version 223140 (0.0009) -[2023-11-28 06:03:46,654][87426] Updated weights for policy 1, policy_version 223150 (0.0012) -[2023-11-28 06:03:47,030][87426] Updated weights for policy 1, policy_version 223160 (0.0012) -[2023-11-28 06:03:47,342][87424] Updated weights for policy 0, policy_version 223527 (0.0009) -[2023-11-28 06:03:47,725][87424] Updated weights for policy 0, policy_version 223537 (0.0011) -[2023-11-28 06:03:48,109][87424] Updated weights for policy 0, policy_version 223547 (0.0010) -[2023-11-28 06:03:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114360320. Throughput: 0: 2699.6, 1: 2773.4. Samples: 114368408. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:48,446][86177] Avg episode reward: [(0, '-513.850'), (1, '-518.240')] -[2023-11-28 06:03:49,407][87426] Updated weights for policy 1, policy_version 223170 (0.0010) -[2023-11-28 06:03:49,787][87426] Updated weights for policy 1, policy_version 223180 (0.0008) -[2023-11-28 06:03:50,165][87426] Updated weights for policy 1, policy_version 223190 (0.0007) -[2023-11-28 06:03:50,230][87424] Updated weights for policy 0, policy_version 223557 (0.0010) -[2023-11-28 06:03:50,545][87426] Updated weights for policy 1, policy_version 223200 (0.0009) -[2023-11-28 06:03:50,605][87424] Updated weights for policy 0, policy_version 223567 (0.0011) -[2023-11-28 06:03:50,989][87424] Updated weights for policy 0, policy_version 223577 (0.0012) -[2023-11-28 06:03:53,025][87424] Updated weights for policy 0, policy_version 223587 (0.0011) -[2023-11-28 06:03:53,076][87426] Updated weights for policy 1, policy_version 223210 (0.0010) -[2023-11-28 06:03:53,418][87424] Updated weights for policy 0, policy_version 223597 (0.0011) -[2023-11-28 06:03:53,452][86177] Fps is (10 sec: 4911.6, 60 sec: 5460.7, 300 sec: 5414.9). Total num frames: 114376704. Throughput: 0: 2701.1, 1: 2758.4. Samples: 114400816. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:53,452][86177] Avg episode reward: [(0, '-514.090'), (1, '-515.740')] -[2023-11-28 06:03:53,460][87426] Updated weights for policy 1, policy_version 223220 (0.0009) -[2023-11-28 06:03:53,791][87424] Updated weights for policy 0, policy_version 223607 (0.0011) -[2023-11-28 06:03:53,837][87426] Updated weights for policy 1, policy_version 223230 (0.0014) -[2023-11-28 06:03:55,772][87426] Updated weights for policy 1, policy_version 223240 (0.0009) -[2023-11-28 06:03:56,142][87426] Updated weights for policy 1, policy_version 223250 (0.0007) -[2023-11-28 06:03:56,342][87424] Updated weights for policy 0, policy_version 223617 (0.0012) -[2023-11-28 06:03:56,523][87426] Updated weights for policy 1, policy_version 223260 (0.0008) -[2023-11-28 06:03:56,720][87424] Updated weights for policy 0, policy_version 223627 (0.0012) -[2023-11-28 06:03:57,093][87424] Updated weights for policy 0, policy_version 223637 (0.0012) -[2023-11-28 06:03:57,474][87424] Updated weights for policy 0, policy_version 223647 (0.0012) -[2023-11-28 06:03:58,402][87426] Updated weights for policy 1, policy_version 223270 (0.0010) -[2023-11-28 06:03:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114409472. Throughput: 0: 2700.8, 1: 2772.3. Samples: 114426032. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:03:58,446][86177] Avg episode reward: [(0, '-510.840'), (1, '-514.940')] -[2023-11-28 06:03:58,774][87426] Updated weights for policy 1, policy_version 223280 (0.0012) -[2023-11-28 06:03:59,157][87426] Updated weights for policy 1, policy_version 223290 (0.0011) -[2023-11-28 06:03:59,237][87424] Updated weights for policy 0, policy_version 223657 (0.0011) -[2023-11-28 06:03:59,616][87424] Updated weights for policy 0, policy_version 223667 (0.0007) -[2023-11-28 06:03:59,994][87424] Updated weights for policy 0, policy_version 223677 (0.0008) -[2023-11-28 06:04:01,359][87426] Updated weights for policy 1, policy_version 223300 (0.0011) -[2023-11-28 06:04:01,734][87426] Updated weights for policy 1, policy_version 223310 (0.0012) -[2023-11-28 06:04:02,114][87426] Updated weights for policy 1, policy_version 223320 (0.0008) -[2023-11-28 06:04:02,465][87424] Updated weights for policy 0, policy_version 223687 (0.0009) -[2023-11-28 06:04:02,849][87424] Updated weights for policy 0, policy_version 223697 (0.0011) -[2023-11-28 06:04:03,230][87424] Updated weights for policy 0, policy_version 223707 (0.0012) -[2023-11-28 06:04:03,444][86177] Fps is (10 sec: 6558.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114442240. Throughput: 0: 2721.6, 1: 2774.3. Samples: 114450340. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:04:03,446][86177] Avg episode reward: [(0, '-508.510'), (1, '-508.000')] -[2023-11-28 06:04:04,010][87426] Updated weights for policy 1, policy_version 223330 (0.0009) -[2023-11-28 06:04:04,394][87426] Updated weights for policy 1, policy_version 223340 (0.0010) -[2023-11-28 06:04:04,788][87426] Updated weights for policy 1, policy_version 223350 (0.0010) -[2023-11-28 06:04:05,158][87426] Updated weights for policy 1, policy_version 223360 (0.0008) -[2023-11-28 06:04:05,229][87424] Updated weights for policy 0, policy_version 223717 (0.0011) -[2023-11-28 06:04:05,605][87424] Updated weights for policy 0, policy_version 223727 (0.0012) -[2023-11-28 06:04:06,000][87424] Updated weights for policy 0, policy_version 223737 (0.0012) -[2023-11-28 06:04:07,293][87426] Updated weights for policy 1, policy_version 223370 (0.0012) -[2023-11-28 06:04:07,668][87426] Updated weights for policy 1, policy_version 223380 (0.0012) -[2023-11-28 06:04:08,051][87426] Updated weights for policy 1, policy_version 223390 (0.0012) -[2023-11-28 06:04:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 114466816. Throughput: 0: 2730.0, 1: 2777.6. Samples: 114482308. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:04:08,445][86177] Avg episode reward: [(0, '-504.280'), (1, '-507.030')] -[2023-11-28 06:04:08,578][87424] Updated weights for policy 0, policy_version 223747 (0.0010) -[2023-11-28 06:04:08,957][87424] Updated weights for policy 0, policy_version 223757 (0.0009) -[2023-11-28 06:04:09,337][87424] Updated weights for policy 0, policy_version 223767 (0.0011) -[2023-11-28 06:04:10,670][87426] Updated weights for policy 1, policy_version 223400 (0.0012) -[2023-11-28 06:04:11,050][87426] Updated weights for policy 1, policy_version 223410 (0.0012) -[2023-11-28 06:04:11,421][87426] Updated weights for policy 1, policy_version 223420 (0.0012) -[2023-11-28 06:04:11,454][87424] Updated weights for policy 0, policy_version 223777 (0.0009) -[2023-11-28 06:04:11,845][87424] Updated weights for policy 0, policy_version 223787 (0.0012) -[2023-11-28 06:04:12,224][87424] Updated weights for policy 0, policy_version 223797 (0.0013) -[2023-11-28 06:04:12,605][87424] Updated weights for policy 0, policy_version 223807 (0.0012) -[2023-11-28 06:04:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114491392. Throughput: 0: 2731.1, 1: 2718.0. Samples: 114506284. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:04:13,445][86177] Avg episode reward: [(0, '-498.700'), (1, '-506.940')] -[2023-11-28 06:04:14,001][87426] Updated weights for policy 1, policy_version 223430 (0.0009) -[2023-11-28 06:04:14,378][87426] Updated weights for policy 1, policy_version 223440 (0.0007) -[2023-11-28 06:04:14,763][87426] Updated weights for policy 1, policy_version 223450 (0.0008) -[2023-11-28 06:04:14,929][87424] Updated weights for policy 0, policy_version 223817 (0.0009) -[2023-11-28 06:04:15,309][87424] Updated weights for policy 0, policy_version 223827 (0.0008) -[2023-11-28 06:04:15,696][87424] Updated weights for policy 0, policy_version 223837 (0.0009) -[2023-11-28 06:04:17,016][87426] Updated weights for policy 1, policy_version 223460 (0.0008) -[2023-11-28 06:04:17,395][87426] Updated weights for policy 1, policy_version 223470 (0.0007) -[2023-11-28 06:04:17,782][87426] Updated weights for policy 1, policy_version 223480 (0.0008) -[2023-11-28 06:04:17,801][87424] Updated weights for policy 0, policy_version 223847 (0.0007) -[2023-11-28 06:04:18,182][87424] Updated weights for policy 0, policy_version 223857 (0.0008) -[2023-11-28 06:04:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 114515968. Throughput: 0: 2717.8, 1: 2718.5. Samples: 114530212. Policy #0 lag: (min: 31.0, avg: 49.7, max: 88.0) -[2023-11-28 06:04:18,445][86177] Avg episode reward: [(0, '-494.010'), (1, '-507.570')] -[2023-11-28 06:04:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000223488_57212928.pth... -[2023-11-28 06:04:18,502][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000220960_56565760.pth -[2023-11-28 06:04:18,563][87424] Updated weights for policy 0, policy_version 223867 (0.0007) -[2023-11-28 06:04:18,756][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000223872_57311232.pth... -[2023-11-28 06:04:18,804][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000221344_56664064.pth -[2023-11-28 06:04:19,663][87426] Updated weights for policy 1, policy_version 223490 (0.0008) -[2023-11-28 06:04:20,040][87426] Updated weights for policy 1, policy_version 223500 (0.0012) -[2023-11-28 06:04:20,420][87426] Updated weights for policy 1, policy_version 223510 (0.0012) -[2023-11-28 06:04:20,795][87426] Updated weights for policy 1, policy_version 223520 (0.0010) -[2023-11-28 06:04:20,828][87424] Updated weights for policy 0, policy_version 223877 (0.0010) -[2023-11-28 06:04:21,203][87424] Updated weights for policy 0, policy_version 223887 (0.0011) -[2023-11-28 06:04:21,577][87424] Updated weights for policy 0, policy_version 223897 (0.0009) -[2023-11-28 06:04:22,921][87426] Updated weights for policy 1, policy_version 223530 (0.0011) -[2023-11-28 06:04:23,302][87426] Updated weights for policy 1, policy_version 223540 (0.0008) -[2023-11-28 06:04:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 114540544. Throughput: 0: 2688.2, 1: 2712.3. Samples: 114562904. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:04:23,445][86177] Avg episode reward: [(0, '-494.760'), (1, '-507.180')] -[2023-11-28 06:04:23,681][87426] Updated weights for policy 1, policy_version 223550 (0.0008) -[2023-11-28 06:04:23,864][87424] Updated weights for policy 0, policy_version 223907 (0.0010) -[2023-11-28 06:04:24,251][87424] Updated weights for policy 0, policy_version 223917 (0.0012) -[2023-11-28 06:04:24,645][87424] Updated weights for policy 0, policy_version 223927 (0.0011) -[2023-11-28 06:04:25,420][87426] Updated weights for policy 1, policy_version 223560 (0.0011) -[2023-11-28 06:04:25,787][87426] Updated weights for policy 1, policy_version 223570 (0.0012) -[2023-11-28 06:04:26,168][87426] Updated weights for policy 1, policy_version 223580 (0.0012) -[2023-11-28 06:04:26,452][87424] Updated weights for policy 0, policy_version 223937 (0.0012) -[2023-11-28 06:04:26,847][87424] Updated weights for policy 0, policy_version 223947 (0.0012) -[2023-11-28 06:04:27,234][87424] Updated weights for policy 0, policy_version 223957 (0.0012) -[2023-11-28 06:04:27,626][87424] Updated weights for policy 0, policy_version 223967 (0.0012) -[2023-11-28 06:04:28,297][87426] Updated weights for policy 1, policy_version 223590 (0.0012) -[2023-11-28 06:04:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114573312. Throughput: 0: 2706.4, 1: 2747.2. Samples: 114589064. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:04:28,445][86177] Avg episode reward: [(0, '-495.600'), (1, '-507.450')] -[2023-11-28 06:04:28,668][87426] Updated weights for policy 1, policy_version 223600 (0.0011) -[2023-11-28 06:04:29,053][87426] Updated weights for policy 1, policy_version 223610 (0.0011) -[2023-11-28 06:04:29,280][87424] Updated weights for policy 0, policy_version 223977 (0.0011) -[2023-11-28 06:04:29,666][87424] Updated weights for policy 0, policy_version 223987 (0.0012) -[2023-11-28 06:04:30,058][87424] Updated weights for policy 0, policy_version 223997 (0.0010) -[2023-11-28 06:04:30,754][87426] Updated weights for policy 1, policy_version 223620 (0.0011) -[2023-11-28 06:04:31,138][87426] Updated weights for policy 1, policy_version 223630 (0.0012) -[2023-11-28 06:04:31,513][87426] Updated weights for policy 1, policy_version 223640 (0.0012) -[2023-11-28 06:04:32,370][87424] Updated weights for policy 0, policy_version 224007 (0.0012) -[2023-11-28 06:04:32,756][87424] Updated weights for policy 0, policy_version 224017 (0.0011) -[2023-11-28 06:04:33,132][87424] Updated weights for policy 0, policy_version 224027 (0.0012) -[2023-11-28 06:04:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114606080. Throughput: 0: 2726.9, 1: 2736.6. Samples: 114614268. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:04:33,445][86177] Avg episode reward: [(0, '-497.060'), (1, '-517.510')] -[2023-11-28 06:04:33,568][87426] Updated weights for policy 1, policy_version 223650 (0.0012) -[2023-11-28 06:04:33,939][87426] Updated weights for policy 1, policy_version 223660 (0.0012) -[2023-11-28 06:04:34,313][87426] Updated weights for policy 1, policy_version 223670 (0.0012) -[2023-11-28 06:04:34,691][87426] Updated weights for policy 1, policy_version 223680 (0.0012) -[2023-11-28 06:04:34,973][87424] Updated weights for policy 0, policy_version 224037 (0.0011) -[2023-11-28 06:04:35,358][87424] Updated weights for policy 0, policy_version 224047 (0.0011) -[2023-11-28 06:04:35,738][87424] Updated weights for policy 0, policy_version 224057 (0.0007) -[2023-11-28 06:04:36,671][87426] Updated weights for policy 1, policy_version 223690 (0.0011) -[2023-11-28 06:04:37,049][87426] Updated weights for policy 1, policy_version 223700 (0.0010) -[2023-11-28 06:04:37,430][87426] Updated weights for policy 1, policy_version 223710 (0.0008) -[2023-11-28 06:04:37,999][87424] Updated weights for policy 0, policy_version 224067 (0.0009) -[2023-11-28 06:04:38,381][87424] Updated weights for policy 0, policy_version 224077 (0.0010) -[2023-11-28 06:04:38,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 114630656. Throughput: 0: 2733.8, 1: 2765.5. Samples: 114648244. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:04:38,446][86177] Avg episode reward: [(0, '-498.370'), (1, '-517.650')] -[2023-11-28 06:04:38,776][87424] Updated weights for policy 0, policy_version 224087 (0.0010) -[2023-11-28 06:04:39,380][87426] Updated weights for policy 1, policy_version 223720 (0.0011) -[2023-11-28 06:04:39,759][87426] Updated weights for policy 1, policy_version 223730 (0.0012) -[2023-11-28 06:04:40,136][87426] Updated weights for policy 1, policy_version 223740 (0.0012) -[2023-11-28 06:04:41,284][87424] Updated weights for policy 0, policy_version 224097 (0.0011) -[2023-11-28 06:04:41,664][87424] Updated weights for policy 0, policy_version 224107 (0.0008) -[2023-11-28 06:04:42,051][87424] Updated weights for policy 0, policy_version 224117 (0.0009) -[2023-11-28 06:04:42,433][87424] Updated weights for policy 0, policy_version 224127 (0.0010) -[2023-11-28 06:04:42,436][87426] Updated weights for policy 1, policy_version 223750 (0.0012) -[2023-11-28 06:04:42,810][87426] Updated weights for policy 1, policy_version 223760 (0.0011) -[2023-11-28 06:04:43,191][87426] Updated weights for policy 1, policy_version 223770 (0.0012) -[2023-11-28 06:04:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 114663424. Throughput: 0: 2721.0, 1: 2755.5. Samples: 114672472. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:04:43,445][86177] Avg episode reward: [(0, '-500.430'), (1, '-521.290')] -[2023-11-28 06:04:44,879][87424] Updated weights for policy 0, policy_version 224137 (0.0012) -[2023-11-28 06:04:45,266][87424] Updated weights for policy 0, policy_version 224147 (0.0012) -[2023-11-28 06:04:45,379][87426] Updated weights for policy 1, policy_version 223780 (0.0011) -[2023-11-28 06:04:45,646][87424] Updated weights for policy 0, policy_version 224157 (0.0011) -[2023-11-28 06:04:45,761][87426] Updated weights for policy 1, policy_version 223790 (0.0011) -[2023-11-28 06:04:46,134][87426] Updated weights for policy 1, policy_version 223800 (0.0010) -[2023-11-28 06:04:47,561][87424] Updated weights for policy 0, policy_version 224167 (0.0012) -[2023-11-28 06:04:47,945][87424] Updated weights for policy 0, policy_version 224177 (0.0010) -[2023-11-28 06:04:48,327][87424] Updated weights for policy 0, policy_version 224187 (0.0007) -[2023-11-28 06:04:48,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 114679808. Throughput: 0: 2722.8, 1: 2766.7. Samples: 114697372. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:04:48,446][86177] Avg episode reward: [(0, '-499.260'), (1, '-521.220')] -[2023-11-28 06:04:48,633][87426] Updated weights for policy 1, policy_version 223810 (0.0007) -[2023-11-28 06:04:49,003][87426] Updated weights for policy 1, policy_version 223820 (0.0008) -[2023-11-28 06:04:49,386][87426] Updated weights for policy 1, policy_version 223830 (0.0007) -[2023-11-28 06:04:49,764][87426] Updated weights for policy 1, policy_version 223840 (0.0008) -[2023-11-28 06:04:50,618][87424] Updated weights for policy 0, policy_version 224197 (0.0009) -[2023-11-28 06:04:51,002][87424] Updated weights for policy 0, policy_version 224207 (0.0012) -[2023-11-28 06:04:51,391][87424] Updated weights for policy 0, policy_version 224217 (0.0011) -[2023-11-28 06:04:51,730][87426] Updated weights for policy 1, policy_version 223850 (0.0012) -[2023-11-28 06:04:52,104][87426] Updated weights for policy 1, policy_version 223860 (0.0008) -[2023-11-28 06:04:52,487][87426] Updated weights for policy 1, policy_version 223870 (0.0008) -[2023-11-28 06:04:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5598.6, 300 sec: 5415.1). Total num frames: 114712576. Throughput: 0: 2734.4, 1: 2746.4. Samples: 114728944. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:04:53,445][86177] Avg episode reward: [(0, '-498.130'), (1, '-558.400')] -[2023-11-28 06:04:53,569][87424] Updated weights for policy 0, policy_version 224227 (0.0011) -[2023-11-28 06:04:53,961][87424] Updated weights for policy 0, policy_version 224237 (0.0009) -[2023-11-28 06:04:54,327][87424] Updated weights for policy 0, policy_version 224247 (0.0010) -[2023-11-28 06:04:54,811][87426] Updated weights for policy 1, policy_version 223880 (0.0009) -[2023-11-28 06:04:55,187][87426] Updated weights for policy 1, policy_version 223890 (0.0009) -[2023-11-28 06:04:55,567][87426] Updated weights for policy 1, policy_version 223900 (0.0007) -[2023-11-28 06:04:56,164][87424] Updated weights for policy 0, policy_version 224257 (0.0010) -[2023-11-28 06:04:56,556][87424] Updated weights for policy 0, policy_version 224267 (0.0008) -[2023-11-28 06:04:56,936][87424] Updated weights for policy 0, policy_version 224277 (0.0007) -[2023-11-28 06:04:57,328][87424] Updated weights for policy 0, policy_version 224287 (0.0008) -[2023-11-28 06:04:57,962][87426] Updated weights for policy 1, policy_version 223910 (0.0007) -[2023-11-28 06:04:58,349][87426] Updated weights for policy 1, policy_version 223920 (0.0007) -[2023-11-28 06:04:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114737152. Throughput: 0: 2741.8, 1: 2745.5. Samples: 114753212. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:04:58,445][86177] Avg episode reward: [(0, '-499.340'), (1, '-588.410')] -[2023-11-28 06:04:58,732][87426] Updated weights for policy 1, policy_version 223930 (0.0007) -[2023-11-28 06:04:59,582][87424] Updated weights for policy 0, policy_version 224297 (0.0009) -[2023-11-28 06:04:59,967][87424] Updated weights for policy 0, policy_version 224307 (0.0010) -[2023-11-28 06:05:00,343][87424] Updated weights for policy 0, policy_version 224317 (0.0011) -[2023-11-28 06:05:01,105][87426] Updated weights for policy 1, policy_version 223940 (0.0010) -[2023-11-28 06:05:01,481][87426] Updated weights for policy 1, policy_version 223950 (0.0012) -[2023-11-28 06:05:01,861][87426] Updated weights for policy 1, policy_version 223960 (0.0010) -[2023-11-28 06:05:02,564][87424] Updated weights for policy 0, policy_version 224327 (0.0011) -[2023-11-28 06:05:02,951][87424] Updated weights for policy 0, policy_version 224337 (0.0011) -[2023-11-28 06:05:03,326][87424] Updated weights for policy 0, policy_version 224347 (0.0010) -[2023-11-28 06:05:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 114761728. Throughput: 0: 2748.6, 1: 2741.6. Samples: 114777272. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:05:03,445][86177] Avg episode reward: [(0, '-497.560'), (1, '-590.680')] -[2023-11-28 06:05:04,067][87426] Updated weights for policy 1, policy_version 223970 (0.0011) -[2023-11-28 06:05:04,437][87426] Updated weights for policy 1, policy_version 223980 (0.0010) -[2023-11-28 06:05:04,817][87426] Updated weights for policy 1, policy_version 223990 (0.0007) -[2023-11-28 06:05:05,195][87426] Updated weights for policy 1, policy_version 224000 (0.0008) -[2023-11-28 06:05:05,440][87424] Updated weights for policy 0, policy_version 224357 (0.0010) -[2023-11-28 06:05:05,826][87424] Updated weights for policy 0, policy_version 224367 (0.0011) -[2023-11-28 06:05:06,205][87424] Updated weights for policy 0, policy_version 224377 (0.0011) -[2023-11-28 06:05:07,214][87426] Updated weights for policy 1, policy_version 224010 (0.0012) -[2023-11-28 06:05:07,586][87426] Updated weights for policy 1, policy_version 224020 (0.0012) -[2023-11-28 06:05:07,968][87426] Updated weights for policy 1, policy_version 224030 (0.0012) -[2023-11-28 06:05:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 114794496. Throughput: 0: 2760.2, 1: 2719.0. Samples: 114809468. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:05:08,445][86177] Avg episode reward: [(0, '-498.150'), (1, '-567.230')] -[2023-11-28 06:05:08,632][87424] Updated weights for policy 0, policy_version 224387 (0.0012) -[2023-11-28 06:05:09,014][87424] Updated weights for policy 0, policy_version 224397 (0.0012) -[2023-11-28 06:05:09,402][87424] Updated weights for policy 0, policy_version 224407 (0.0012) -[2023-11-28 06:05:10,481][87426] Updated weights for policy 1, policy_version 224040 (0.0012) -[2023-11-28 06:05:10,857][87426] Updated weights for policy 1, policy_version 224050 (0.0010) -[2023-11-28 06:05:11,240][87426] Updated weights for policy 1, policy_version 224060 (0.0008) -[2023-11-28 06:05:11,278][87424] Updated weights for policy 0, policy_version 224417 (0.0012) -[2023-11-28 06:05:11,663][87424] Updated weights for policy 0, policy_version 224427 (0.0012) -[2023-11-28 06:05:12,051][87424] Updated weights for policy 0, policy_version 224437 (0.0011) -[2023-11-28 06:05:12,454][87424] Updated weights for policy 0, policy_version 224447 (0.0012) -[2023-11-28 06:05:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114819072. Throughput: 0: 2749.3, 1: 2685.4. Samples: 114833628. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:05:13,445][86177] Avg episode reward: [(0, '-501.020'), (1, '-559.260')] -[2023-11-28 06:05:13,468][87426] Updated weights for policy 1, policy_version 224070 (0.0008) -[2023-11-28 06:05:13,854][87426] Updated weights for policy 1, policy_version 224080 (0.0011) -[2023-11-28 06:05:14,230][87426] Updated weights for policy 1, policy_version 224090 (0.0008) -[2023-11-28 06:05:14,987][87424] Updated weights for policy 0, policy_version 224457 (0.0008) -[2023-11-28 06:05:15,371][87424] Updated weights for policy 0, policy_version 224467 (0.0009) -[2023-11-28 06:05:15,747][87424] Updated weights for policy 0, policy_version 224477 (0.0012) -[2023-11-28 06:05:16,736][87426] Updated weights for policy 1, policy_version 224100 (0.0009) -[2023-11-28 06:05:17,107][87426] Updated weights for policy 1, policy_version 224110 (0.0011) -[2023-11-28 06:05:17,481][87424] Updated weights for policy 0, policy_version 224487 (0.0012) -[2023-11-28 06:05:17,489][87426] Updated weights for policy 1, policy_version 224120 (0.0009) -[2023-11-28 06:05:17,866][87424] Updated weights for policy 0, policy_version 224497 (0.0012) -[2023-11-28 06:05:18,242][87424] Updated weights for policy 0, policy_version 224507 (0.0012) -[2023-11-28 06:05:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 114851840. Throughput: 0: 2725.1, 1: 2691.1. Samples: 114857996. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:05:18,445][86177] Avg episode reward: [(0, '-496.440'), (1, '-520.400')] -[2023-11-28 06:05:19,738][87426] Updated weights for policy 1, policy_version 224130 (0.0008) -[2023-11-28 06:05:19,949][87424] Updated weights for policy 0, policy_version 224517 (0.0012) -[2023-11-28 06:05:20,115][87426] Updated weights for policy 1, policy_version 224140 (0.0011) -[2023-11-28 06:05:20,327][87424] Updated weights for policy 0, policy_version 224527 (0.0011) -[2023-11-28 06:05:20,497][87426] Updated weights for policy 1, policy_version 224150 (0.0012) -[2023-11-28 06:05:20,713][87424] Updated weights for policy 0, policy_version 224537 (0.0010) -[2023-11-28 06:05:20,869][87426] Updated weights for policy 1, policy_version 224160 (0.0012) -[2023-11-28 06:05:22,981][87426] Updated weights for policy 1, policy_version 224170 (0.0011) -[2023-11-28 06:05:23,152][87424] Updated weights for policy 0, policy_version 224547 (0.0011) -[2023-11-28 06:05:23,363][87426] Updated weights for policy 1, policy_version 224180 (0.0011) -[2023-11-28 06:05:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 114868224. Throughput: 0: 2699.8, 1: 2682.7. Samples: 114890456. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:05:23,445][86177] Avg episode reward: [(0, '-497.680'), (1, '-516.210')] -[2023-11-28 06:05:23,528][87424] Updated weights for policy 0, policy_version 224557 (0.0009) -[2023-11-28 06:05:23,740][87426] Updated weights for policy 1, policy_version 224190 (0.0011) -[2023-11-28 06:05:23,909][87424] Updated weights for policy 0, policy_version 224567 (0.0008) -[2023-11-28 06:05:26,184][87424] Updated weights for policy 0, policy_version 224577 (0.0008) -[2023-11-28 06:05:26,205][87426] Updated weights for policy 1, policy_version 224200 (0.0010) -[2023-11-28 06:05:26,557][87424] Updated weights for policy 0, policy_version 224587 (0.0011) -[2023-11-28 06:05:26,585][87426] Updated weights for policy 1, policy_version 224210 (0.0011) -[2023-11-28 06:05:26,945][87424] Updated weights for policy 0, policy_version 224597 (0.0011) -[2023-11-28 06:05:26,961][87426] Updated weights for policy 1, policy_version 224220 (0.0010) -[2023-11-28 06:05:27,326][87424] Updated weights for policy 0, policy_version 224607 (0.0009) -[2023-11-28 06:05:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114900992. Throughput: 0: 2736.8, 1: 2684.9. Samples: 114916448. Policy #0 lag: (min: 31.0, avg: 47.2, max: 72.0) -[2023-11-28 06:05:28,445][86177] Avg episode reward: [(0, '-496.870'), (1, '-522.880')] -[2023-11-28 06:05:28,882][87426] Updated weights for policy 1, policy_version 224230 (0.0011) -[2023-11-28 06:05:29,131][87424] Updated weights for policy 0, policy_version 224617 (0.0011) -[2023-11-28 06:05:29,267][87426] Updated weights for policy 1, policy_version 224240 (0.0010) -[2023-11-28 06:05:29,508][87424] Updated weights for policy 0, policy_version 224627 (0.0012) -[2023-11-28 06:05:29,641][87426] Updated weights for policy 1, policy_version 224250 (0.0010) -[2023-11-28 06:05:29,891][87424] Updated weights for policy 0, policy_version 224637 (0.0011) -[2023-11-28 06:05:31,703][87426] Updated weights for policy 1, policy_version 224260 (0.0010) -[2023-11-28 06:05:31,882][87424] Updated weights for policy 0, policy_version 224647 (0.0009) -[2023-11-28 06:05:32,080][87426] Updated weights for policy 1, policy_version 224270 (0.0011) -[2023-11-28 06:05:32,261][87424] Updated weights for policy 0, policy_version 224657 (0.0009) -[2023-11-28 06:05:32,457][87426] Updated weights for policy 1, policy_version 224280 (0.0010) -[2023-11-28 06:05:32,644][87424] Updated weights for policy 0, policy_version 224667 (0.0008) -[2023-11-28 06:05:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 114933760. Throughput: 0: 2746.3, 1: 2692.0. Samples: 114942096. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:05:33,445][86177] Avg episode reward: [(0, '-495.810'), (1, '-523.320')] -[2023-11-28 06:05:34,761][87426] Updated weights for policy 1, policy_version 224290 (0.0008) -[2023-11-28 06:05:35,130][87424] Updated weights for policy 0, policy_version 224677 (0.0008) -[2023-11-28 06:05:35,144][87426] Updated weights for policy 1, policy_version 224300 (0.0010) -[2023-11-28 06:05:35,505][87424] Updated weights for policy 0, policy_version 224687 (0.0009) -[2023-11-28 06:05:35,509][87426] Updated weights for policy 1, policy_version 224310 (0.0011) -[2023-11-28 06:05:35,885][87424] Updated weights for policy 0, policy_version 224697 (0.0009) -[2023-11-28 06:05:35,890][87426] Updated weights for policy 1, policy_version 224320 (0.0011) -[2023-11-28 06:05:37,917][87426] Updated weights for policy 1, policy_version 224330 (0.0010) -[2023-11-28 06:05:37,953][87424] Updated weights for policy 0, policy_version 224707 (0.0009) -[2023-11-28 06:05:38,299][87426] Updated weights for policy 1, policy_version 224340 (0.0010) -[2023-11-28 06:05:38,343][87424] Updated weights for policy 0, policy_version 224717 (0.0012) -[2023-11-28 06:05:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 114950144. Throughput: 0: 2731.8, 1: 2698.8. Samples: 114973320. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:05:38,445][86177] Avg episode reward: [(0, '-497.020'), (1, '-524.580')] -[2023-11-28 06:05:38,675][87426] Updated weights for policy 1, policy_version 224350 (0.0011) -[2023-11-28 06:05:38,721][87424] Updated weights for policy 0, policy_version 224727 (0.0011) -[2023-11-28 06:05:40,923][87426] Updated weights for policy 1, policy_version 224360 (0.0012) -[2023-11-28 06:05:40,968][87424] Updated weights for policy 0, policy_version 224737 (0.0012) -[2023-11-28 06:05:41,302][87426] Updated weights for policy 1, policy_version 224370 (0.0011) -[2023-11-28 06:05:41,359][87424] Updated weights for policy 0, policy_version 224747 (0.0011) -[2023-11-28 06:05:41,680][87426] Updated weights for policy 1, policy_version 224380 (0.0010) -[2023-11-28 06:05:41,738][87424] Updated weights for policy 0, policy_version 224757 (0.0012) -[2023-11-28 06:05:42,120][87424] Updated weights for policy 0, policy_version 224767 (0.0012) -[2023-11-28 06:05:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 114982912. Throughput: 0: 2722.2, 1: 2722.7. Samples: 114998232. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:05:43,445][86177] Avg episode reward: [(0, '-499.770'), (1, '-528.700')] -[2023-11-28 06:05:44,073][87424] Updated weights for policy 0, policy_version 224777 (0.0011) -[2023-11-28 06:05:44,125][87426] Updated weights for policy 1, policy_version 224390 (0.0010) -[2023-11-28 06:05:44,453][87424] Updated weights for policy 0, policy_version 224787 (0.0011) -[2023-11-28 06:05:44,503][87426] Updated weights for policy 1, policy_version 224400 (0.0008) -[2023-11-28 06:05:44,829][87424] Updated weights for policy 0, policy_version 224797 (0.0012) -[2023-11-28 06:05:44,882][87426] Updated weights for policy 1, policy_version 224410 (0.0007) -[2023-11-28 06:05:46,968][87424] Updated weights for policy 0, policy_version 224807 (0.0010) -[2023-11-28 06:05:46,990][87426] Updated weights for policy 1, policy_version 224420 (0.0009) -[2023-11-28 06:05:47,352][87424] Updated weights for policy 0, policy_version 224817 (0.0008) -[2023-11-28 06:05:47,373][87426] Updated weights for policy 1, policy_version 224430 (0.0007) -[2023-11-28 06:05:47,736][87424] Updated weights for policy 0, policy_version 224827 (0.0008) -[2023-11-28 06:05:47,751][87426] Updated weights for policy 1, policy_version 224440 (0.0009) -[2023-11-28 06:05:48,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 115015680. Throughput: 0: 2724.2, 1: 2731.5. Samples: 115022780. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:05:48,445][86177] Avg episode reward: [(0, '-498.400'), (1, '-528.700')] -[2023-11-28 06:05:49,490][87426] Updated weights for policy 1, policy_version 224450 (0.0009) -[2023-11-28 06:05:49,870][87426] Updated weights for policy 1, policy_version 224460 (0.0010) -[2023-11-28 06:05:50,112][87424] Updated weights for policy 0, policy_version 224837 (0.0011) -[2023-11-28 06:05:50,247][87426] Updated weights for policy 1, policy_version 224470 (0.0010) -[2023-11-28 06:05:50,496][87424] Updated weights for policy 0, policy_version 224847 (0.0012) -[2023-11-28 06:05:50,629][87426] Updated weights for policy 1, policy_version 224480 (0.0010) -[2023-11-28 06:05:50,885][87424] Updated weights for policy 0, policy_version 224857 (0.0012) -[2023-11-28 06:05:53,026][87426] Updated weights for policy 1, policy_version 224490 (0.0011) -[2023-11-28 06:05:53,058][87424] Updated weights for policy 0, policy_version 224867 (0.0011) -[2023-11-28 06:05:53,395][87426] Updated weights for policy 1, policy_version 224500 (0.0011) -[2023-11-28 06:05:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 115032064. Throughput: 0: 2740.1, 1: 2738.9. Samples: 115056024. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:05:53,445][86177] Avg episode reward: [(0, '-498.820'), (1, '-525.110')] -[2023-11-28 06:05:53,446][87424] Updated weights for policy 0, policy_version 224877 (0.0010) -[2023-11-28 06:05:53,784][87426] Updated weights for policy 1, policy_version 224510 (0.0011) -[2023-11-28 06:05:53,820][87424] Updated weights for policy 0, policy_version 224887 (0.0011) -[2023-11-28 06:05:55,679][87426] Updated weights for policy 1, policy_version 224520 (0.0011) -[2023-11-28 06:05:56,053][87426] Updated weights for policy 1, policy_version 224530 (0.0011) -[2023-11-28 06:05:56,268][87424] Updated weights for policy 0, policy_version 224897 (0.0012) -[2023-11-28 06:05:56,434][87426] Updated weights for policy 1, policy_version 224540 (0.0011) -[2023-11-28 06:05:56,637][87424] Updated weights for policy 0, policy_version 224907 (0.0010) -[2023-11-28 06:05:57,025][87424] Updated weights for policy 0, policy_version 224917 (0.0007) -[2023-11-28 06:05:57,412][87424] Updated weights for policy 0, policy_version 224927 (0.0007) -[2023-11-28 06:05:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115064832. Throughput: 0: 2737.4, 1: 2777.3. Samples: 115081792. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:05:58,445][86177] Avg episode reward: [(0, '-494.370'), (1, '-526.840')] -[2023-11-28 06:05:58,621][87426] Updated weights for policy 1, policy_version 224550 (0.0012) -[2023-11-28 06:05:58,999][87426] Updated weights for policy 1, policy_version 224560 (0.0012) -[2023-11-28 06:05:59,211][87424] Updated weights for policy 0, policy_version 224937 (0.0012) -[2023-11-28 06:05:59,378][87426] Updated weights for policy 1, policy_version 224570 (0.0009) -[2023-11-28 06:05:59,600][87424] Updated weights for policy 0, policy_version 224947 (0.0008) -[2023-11-28 06:05:59,991][87424] Updated weights for policy 0, policy_version 224957 (0.0009) -[2023-11-28 06:06:01,411][87426] Updated weights for policy 1, policy_version 224580 (0.0008) -[2023-11-28 06:06:01,801][87426] Updated weights for policy 1, policy_version 224590 (0.0011) -[2023-11-28 06:06:01,896][87424] Updated weights for policy 0, policy_version 224967 (0.0009) -[2023-11-28 06:06:02,169][87426] Updated weights for policy 1, policy_version 224600 (0.0011) -[2023-11-28 06:06:02,274][87424] Updated weights for policy 0, policy_version 224977 (0.0011) -[2023-11-28 06:06:02,653][87424] Updated weights for policy 0, policy_version 224987 (0.0011) -[2023-11-28 06:06:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 115097600. Throughput: 0: 2757.5, 1: 2773.1. Samples: 115106872. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:06:03,445][86177] Avg episode reward: [(0, '-494.050'), (1, '-528.770')] -[2023-11-28 06:06:04,024][87426] Updated weights for policy 1, policy_version 224610 (0.0010) -[2023-11-28 06:06:04,398][87426] Updated weights for policy 1, policy_version 224620 (0.0011) -[2023-11-28 06:06:04,706][87424] Updated weights for policy 0, policy_version 224997 (0.0008) -[2023-11-28 06:06:04,774][87426] Updated weights for policy 1, policy_version 224630 (0.0011) -[2023-11-28 06:06:05,091][87424] Updated weights for policy 0, policy_version 225007 (0.0011) -[2023-11-28 06:06:05,149][87426] Updated weights for policy 1, policy_version 224640 (0.0010) -[2023-11-28 06:06:05,477][87424] Updated weights for policy 0, policy_version 225017 (0.0008) -[2023-11-28 06:06:07,308][87426] Updated weights for policy 1, policy_version 224650 (0.0011) -[2023-11-28 06:06:07,695][87426] Updated weights for policy 1, policy_version 224660 (0.0011) -[2023-11-28 06:06:07,724][87424] Updated weights for policy 0, policy_version 225027 (0.0009) -[2023-11-28 06:06:08,083][87426] Updated weights for policy 1, policy_version 224670 (0.0012) -[2023-11-28 06:06:08,120][87424] Updated weights for policy 0, policy_version 225037 (0.0010) -[2023-11-28 06:06:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 115122176. Throughput: 0: 2774.9, 1: 2756.6. Samples: 115139376. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:06:08,446][86177] Avg episode reward: [(0, '-496.590'), (1, '-534.500')] -[2023-11-28 06:06:08,501][87424] Updated weights for policy 0, policy_version 225047 (0.0012) -[2023-11-28 06:06:09,967][87426] Updated weights for policy 1, policy_version 224680 (0.0010) -[2023-11-28 06:06:10,348][87426] Updated weights for policy 1, policy_version 224690 (0.0011) -[2023-11-28 06:06:10,725][87426] Updated weights for policy 1, policy_version 224700 (0.0010) -[2023-11-28 06:06:10,863][87424] Updated weights for policy 0, policy_version 225057 (0.0013) -[2023-11-28 06:06:11,247][87424] Updated weights for policy 0, policy_version 225067 (0.0012) -[2023-11-28 06:06:11,619][87424] Updated weights for policy 0, policy_version 225077 (0.0012) -[2023-11-28 06:06:12,010][87424] Updated weights for policy 0, policy_version 225087 (0.0012) -[2023-11-28 06:06:12,888][87426] Updated weights for policy 1, policy_version 224710 (0.0010) -[2023-11-28 06:06:13,265][87426] Updated weights for policy 1, policy_version 224720 (0.0009) -[2023-11-28 06:06:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115146752. Throughput: 0: 2753.9, 1: 2740.4. Samples: 115163688. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:06:13,445][86177] Avg episode reward: [(0, '-496.970'), (1, '-529.500')] -[2023-11-28 06:06:13,653][87426] Updated weights for policy 1, policy_version 224730 (0.0009) -[2023-11-28 06:06:13,962][87424] Updated weights for policy 0, policy_version 225097 (0.0010) -[2023-11-28 06:06:14,336][87424] Updated weights for policy 0, policy_version 225107 (0.0007) -[2023-11-28 06:06:14,724][87424] Updated weights for policy 0, policy_version 225117 (0.0008) -[2023-11-28 06:06:16,106][87426] Updated weights for policy 1, policy_version 224740 (0.0011) -[2023-11-28 06:06:16,481][87426] Updated weights for policy 1, policy_version 224750 (0.0012) -[2023-11-28 06:06:16,864][87426] Updated weights for policy 1, policy_version 224760 (0.0012) -[2023-11-28 06:06:17,081][87424] Updated weights for policy 0, policy_version 225127 (0.0010) -[2023-11-28 06:06:17,457][87424] Updated weights for policy 0, policy_version 225137 (0.0012) -[2023-11-28 06:06:17,847][87424] Updated weights for policy 0, policy_version 225147 (0.0012) -[2023-11-28 06:06:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 115179520. Throughput: 0: 2734.2, 1: 2744.9. Samples: 115188656. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:06:18,445][86177] Avg episode reward: [(0, '-501.630'), (1, '-532.660')] -[2023-11-28 06:06:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000225152_57638912.pth... -[2023-11-28 06:06:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000222592_56983552.pth -[2023-11-28 06:06:18,600][87426] Updated weights for policy 1, policy_version 224770 (0.0011) -[2023-11-28 06:06:18,984][87426] Updated weights for policy 1, policy_version 224780 (0.0010) -[2023-11-28 06:06:19,358][87426] Updated weights for policy 1, policy_version 224790 (0.0010) -[2023-11-28 06:06:19,736][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000224800_57548800.pth... -[2023-11-28 06:06:19,737][87426] Updated weights for policy 1, policy_version 224800 (0.0008) -[2023-11-28 06:06:19,785][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000222240_56893440.pth -[2023-11-28 06:06:20,004][87424] Updated weights for policy 0, policy_version 225157 (0.0011) -[2023-11-28 06:06:20,383][87424] Updated weights for policy 0, policy_version 225167 (0.0008) -[2023-11-28 06:06:20,773][87424] Updated weights for policy 0, policy_version 225177 (0.0008) -[2023-11-28 06:06:22,250][87426] Updated weights for policy 1, policy_version 224810 (0.0012) -[2023-11-28 06:06:22,628][87426] Updated weights for policy 1, policy_version 224820 (0.0009) -[2023-11-28 06:06:23,004][87426] Updated weights for policy 1, policy_version 224830 (0.0012) -[2023-11-28 06:06:23,143][87424] Updated weights for policy 0, policy_version 225187 (0.0012) -[2023-11-28 06:06:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 115204096. Throughput: 0: 2745.4, 1: 2760.1. Samples: 115221068. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:06:23,445][86177] Avg episode reward: [(0, '-501.950'), (1, '-545.470')] -[2023-11-28 06:06:23,521][87424] Updated weights for policy 0, policy_version 225197 (0.0012) -[2023-11-28 06:06:23,910][87424] Updated weights for policy 0, policy_version 225207 (0.0012) -[2023-11-28 06:06:24,734][87426] Updated weights for policy 1, policy_version 224840 (0.0012) -[2023-11-28 06:06:25,109][87426] Updated weights for policy 1, policy_version 224850 (0.0012) -[2023-11-28 06:06:25,501][87426] Updated weights for policy 1, policy_version 224860 (0.0012) -[2023-11-28 06:06:26,251][87424] Updated weights for policy 0, policy_version 225217 (0.0011) -[2023-11-28 06:06:26,638][87424] Updated weights for policy 0, policy_version 225227 (0.0011) -[2023-11-28 06:06:27,019][87424] Updated weights for policy 0, policy_version 225237 (0.0008) -[2023-11-28 06:06:27,406][87424] Updated weights for policy 0, policy_version 225247 (0.0008) -[2023-11-28 06:06:27,651][87426] Updated weights for policy 1, policy_version 224870 (0.0010) -[2023-11-28 06:06:28,028][87426] Updated weights for policy 1, policy_version 224880 (0.0010) -[2023-11-28 06:06:28,415][87426] Updated weights for policy 1, policy_version 224890 (0.0012) -[2023-11-28 06:06:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 115228672. Throughput: 0: 2744.4, 1: 2765.1. Samples: 115246160. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:06:28,445][86177] Avg episode reward: [(0, '-501.410'), (1, '-541.300')] -[2023-11-28 06:06:29,458][87424] Updated weights for policy 0, policy_version 225257 (0.0011) -[2023-11-28 06:06:29,842][87424] Updated weights for policy 0, policy_version 225267 (0.0008) -[2023-11-28 06:06:30,227][87424] Updated weights for policy 0, policy_version 225277 (0.0011) -[2023-11-28 06:06:30,317][87426] Updated weights for policy 1, policy_version 224900 (0.0011) -[2023-11-28 06:06:30,700][87426] Updated weights for policy 1, policy_version 224910 (0.0011) -[2023-11-28 06:06:31,077][87426] Updated weights for policy 1, policy_version 224920 (0.0010) -[2023-11-28 06:06:32,483][87424] Updated weights for policy 0, policy_version 225287 (0.0008) -[2023-11-28 06:06:32,866][87424] Updated weights for policy 0, policy_version 225297 (0.0008) -[2023-11-28 06:06:33,248][87424] Updated weights for policy 0, policy_version 225307 (0.0011) -[2023-11-28 06:06:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 115261440. Throughput: 0: 2754.5, 1: 2769.5. Samples: 115271360. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:06:33,445][86177] Avg episode reward: [(0, '-501.930'), (1, '-537.990')] -[2023-11-28 06:06:33,583][87426] Updated weights for policy 1, policy_version 224930 (0.0010) -[2023-11-28 06:06:33,963][87426] Updated weights for policy 1, policy_version 224940 (0.0012) -[2023-11-28 06:06:34,341][87426] Updated weights for policy 1, policy_version 224950 (0.0012) -[2023-11-28 06:06:34,717][87426] Updated weights for policy 1, policy_version 224960 (0.0011) -[2023-11-28 06:06:35,192][87424] Updated weights for policy 0, policy_version 225317 (0.0009) -[2023-11-28 06:06:35,573][87424] Updated weights for policy 0, policy_version 225327 (0.0007) -[2023-11-28 06:06:35,956][87424] Updated weights for policy 0, policy_version 225337 (0.0007) -[2023-11-28 06:06:37,227][87426] Updated weights for policy 1, policy_version 224970 (0.0008) -[2023-11-28 06:06:37,594][87426] Updated weights for policy 1, policy_version 224980 (0.0007) -[2023-11-28 06:06:37,969][87426] Updated weights for policy 1, policy_version 224990 (0.0007) -[2023-11-28 06:06:38,019][87424] Updated weights for policy 0, policy_version 225347 (0.0008) -[2023-11-28 06:06:38,395][87424] Updated weights for policy 0, policy_version 225357 (0.0012) -[2023-11-28 06:06:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 115286016. Throughput: 0: 2761.7, 1: 2770.2. Samples: 115304960. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:06:38,445][86177] Avg episode reward: [(0, '-494.980'), (1, '-546.400')] -[2023-11-28 06:06:38,777][87424] Updated weights for policy 0, policy_version 225367 (0.0012) -[2023-11-28 06:06:39,707][87426] Updated weights for policy 1, policy_version 225000 (0.0011) -[2023-11-28 06:06:40,083][87426] Updated weights for policy 1, policy_version 225010 (0.0011) -[2023-11-28 06:06:40,464][87426] Updated weights for policy 1, policy_version 225020 (0.0010) -[2023-11-28 06:06:40,673][87424] Updated weights for policy 0, policy_version 225377 (0.0011) -[2023-11-28 06:06:41,047][87424] Updated weights for policy 0, policy_version 225387 (0.0012) -[2023-11-28 06:06:41,426][87424] Updated weights for policy 0, policy_version 225397 (0.0014) -[2023-11-28 06:06:41,815][87424] Updated weights for policy 0, policy_version 225407 (0.0011) -[2023-11-28 06:06:43,012][87426] Updated weights for policy 1, policy_version 225030 (0.0010) -[2023-11-28 06:06:43,385][87426] Updated weights for policy 1, policy_version 225040 (0.0011) -[2023-11-28 06:06:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115310592. Throughput: 0: 2761.8, 1: 2726.4. Samples: 115328760. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 06:06:43,445][86177] Avg episode reward: [(0, '-494.210'), (1, '-542.920')] -[2023-11-28 06:06:43,768][87426] Updated weights for policy 1, policy_version 225050 (0.0012) -[2023-11-28 06:06:44,369][87424] Updated weights for policy 0, policy_version 225417 (0.0008) -[2023-11-28 06:06:44,761][87424] Updated weights for policy 0, policy_version 225427 (0.0011) -[2023-11-28 06:06:45,140][87424] Updated weights for policy 0, policy_version 225437 (0.0008) -[2023-11-28 06:06:45,562][87426] Updated weights for policy 1, policy_version 225060 (0.0011) -[2023-11-28 06:06:45,948][87426] Updated weights for policy 1, policy_version 225070 (0.0012) -[2023-11-28 06:06:46,341][87426] Updated weights for policy 1, policy_version 225080 (0.0012) -[2023-11-28 06:06:46,953][87424] Updated weights for policy 0, policy_version 225447 (0.0008) -[2023-11-28 06:06:47,332][87424] Updated weights for policy 0, policy_version 225457 (0.0007) -[2023-11-28 06:06:47,714][87424] Updated weights for policy 0, policy_version 225467 (0.0007) -[2023-11-28 06:06:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 115343360. Throughput: 0: 2741.9, 1: 2735.9. Samples: 115353372. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:06:48,445][86177] Avg episode reward: [(0, '-494.260'), (1, '-542.000')] -[2023-11-28 06:06:48,876][87426] Updated weights for policy 1, policy_version 225090 (0.0011) -[2023-11-28 06:06:49,252][87426] Updated weights for policy 1, policy_version 225100 (0.0007) -[2023-11-28 06:06:49,631][87426] Updated weights for policy 1, policy_version 225110 (0.0011) -[2023-11-28 06:06:49,806][87424] Updated weights for policy 0, policy_version 225477 (0.0009) -[2023-11-28 06:06:50,009][87426] Updated weights for policy 1, policy_version 225120 (0.0011) -[2023-11-28 06:06:50,186][87424] Updated weights for policy 0, policy_version 225487 (0.0012) -[2023-11-28 06:06:50,572][87424] Updated weights for policy 0, policy_version 225497 (0.0012) -[2023-11-28 06:06:52,260][87426] Updated weights for policy 1, policy_version 225130 (0.0012) -[2023-11-28 06:06:52,642][87426] Updated weights for policy 1, policy_version 225140 (0.0012) -[2023-11-28 06:06:53,025][87426] Updated weights for policy 1, policy_version 225150 (0.0012) -[2023-11-28 06:06:53,080][87424] Updated weights for policy 0, policy_version 225507 (0.0012) -[2023-11-28 06:06:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 115367936. Throughput: 0: 2726.0, 1: 2720.6. Samples: 115384472. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:06:53,445][86177] Avg episode reward: [(0, '-495.420'), (1, '-557.380')] -[2023-11-28 06:06:53,458][87424] Updated weights for policy 0, policy_version 225517 (0.0011) -[2023-11-28 06:06:53,838][87424] Updated weights for policy 0, policy_version 225527 (0.0010) -[2023-11-28 06:06:55,563][87426] Updated weights for policy 1, policy_version 225160 (0.0009) -[2023-11-28 06:06:55,638][87424] Updated weights for policy 0, policy_version 225537 (0.0011) -[2023-11-28 06:06:55,942][87426] Updated weights for policy 1, policy_version 225170 (0.0011) -[2023-11-28 06:06:56,013][87424] Updated weights for policy 0, policy_version 225547 (0.0008) -[2023-11-28 06:06:56,318][87426] Updated weights for policy 1, policy_version 225180 (0.0011) -[2023-11-28 06:06:56,393][87424] Updated weights for policy 0, policy_version 225557 (0.0009) -[2023-11-28 06:06:56,765][87424] Updated weights for policy 0, policy_version 225567 (0.0012) -[2023-11-28 06:06:58,024][87426] Updated weights for policy 1, policy_version 225190 (0.0009) -[2023-11-28 06:06:58,410][87426] Updated weights for policy 1, policy_version 225200 (0.0007) -[2023-11-28 06:06:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115392512. Throughput: 0: 2723.6, 1: 2738.3. Samples: 115409472. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:06:58,445][86177] Avg episode reward: [(0, '-496.040'), (1, '-544.360')] -[2023-11-28 06:06:58,792][87426] Updated weights for policy 1, policy_version 225210 (0.0007) -[2023-11-28 06:06:59,113][87424] Updated weights for policy 0, policy_version 225577 (0.0011) -[2023-11-28 06:06:59,502][87424] Updated weights for policy 0, policy_version 225587 (0.0012) -[2023-11-28 06:06:59,884][87424] Updated weights for policy 0, policy_version 225597 (0.0011) -[2023-11-28 06:07:00,752][87426] Updated weights for policy 1, policy_version 225220 (0.0009) -[2023-11-28 06:07:01,131][87426] Updated weights for policy 1, policy_version 225230 (0.0007) -[2023-11-28 06:07:01,501][87426] Updated weights for policy 1, policy_version 225240 (0.0008) -[2023-11-28 06:07:02,311][87424] Updated weights for policy 0, policy_version 225607 (0.0010) -[2023-11-28 06:07:02,690][87424] Updated weights for policy 0, policy_version 225617 (0.0011) -[2023-11-28 06:07:03,076][87424] Updated weights for policy 0, policy_version 225627 (0.0011) -[2023-11-28 06:07:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 115425280. Throughput: 0: 2736.6, 1: 2742.0. Samples: 115435192. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:03,445][86177] Avg episode reward: [(0, '-495.310'), (1, '-530.320')] -[2023-11-28 06:07:03,534][87426] Updated weights for policy 1, policy_version 225250 (0.0008) -[2023-11-28 06:07:03,928][87426] Updated weights for policy 1, policy_version 225260 (0.0007) -[2023-11-28 06:07:04,297][87426] Updated weights for policy 1, policy_version 225270 (0.0007) -[2023-11-28 06:07:04,679][87426] Updated weights for policy 1, policy_version 225280 (0.0010) -[2023-11-28 06:07:05,032][87424] Updated weights for policy 0, policy_version 225637 (0.0010) -[2023-11-28 06:07:05,403][87424] Updated weights for policy 0, policy_version 225647 (0.0008) -[2023-11-28 06:07:05,787][87424] Updated weights for policy 0, policy_version 225657 (0.0007) -[2023-11-28 06:07:07,198][87426] Updated weights for policy 1, policy_version 225290 (0.0007) -[2023-11-28 06:07:07,569][87426] Updated weights for policy 1, policy_version 225300 (0.0008) -[2023-11-28 06:07:07,847][87424] Updated weights for policy 0, policy_version 225667 (0.0008) -[2023-11-28 06:07:07,956][87426] Updated weights for policy 1, policy_version 225310 (0.0007) -[2023-11-28 06:07:08,228][87424] Updated weights for policy 0, policy_version 225677 (0.0007) -[2023-11-28 06:07:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 115449856. Throughput: 0: 2725.6, 1: 2719.8. Samples: 115466112. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:08,445][86177] Avg episode reward: [(0, '-496.930'), (1, '-530.930')] -[2023-11-28 06:07:08,614][87424] Updated weights for policy 0, policy_version 225687 (0.0008) -[2023-11-28 06:07:10,474][87426] Updated weights for policy 1, policy_version 225320 (0.0010) -[2023-11-28 06:07:10,627][87424] Updated weights for policy 0, policy_version 225697 (0.0008) -[2023-11-28 06:07:10,844][87426] Updated weights for policy 1, policy_version 225330 (0.0011) -[2023-11-28 06:07:11,009][87424] Updated weights for policy 0, policy_version 225707 (0.0012) -[2023-11-28 06:07:11,227][87426] Updated weights for policy 1, policy_version 225340 (0.0011) -[2023-11-28 06:07:11,394][87424] Updated weights for policy 0, policy_version 225717 (0.0012) -[2023-11-28 06:07:11,778][87424] Updated weights for policy 0, policy_version 225727 (0.0012) -[2023-11-28 06:07:13,331][87426] Updated weights for policy 1, policy_version 225350 (0.0011) -[2023-11-28 06:07:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 115474432. Throughput: 0: 2718.6, 1: 2701.6. Samples: 115490068. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:13,445][86177] Avg episode reward: [(0, '-495.380'), (1, '-525.550')] -[2023-11-28 06:07:13,711][87426] Updated weights for policy 1, policy_version 225360 (0.0012) -[2023-11-28 06:07:14,091][87426] Updated weights for policy 1, policy_version 225370 (0.0008) -[2023-11-28 06:07:14,178][87424] Updated weights for policy 0, policy_version 225737 (0.0009) -[2023-11-28 06:07:14,566][87424] Updated weights for policy 0, policy_version 225747 (0.0007) -[2023-11-28 06:07:14,948][87424] Updated weights for policy 0, policy_version 225757 (0.0007) -[2023-11-28 06:07:16,632][87426] Updated weights for policy 1, policy_version 225380 (0.0007) -[2023-11-28 06:07:17,009][87426] Updated weights for policy 1, policy_version 225390 (0.0007) -[2023-11-28 06:07:17,335][87424] Updated weights for policy 0, policy_version 225767 (0.0010) -[2023-11-28 06:07:17,396][87426] Updated weights for policy 1, policy_version 225400 (0.0011) -[2023-11-28 06:07:17,709][87424] Updated weights for policy 0, policy_version 225777 (0.0009) -[2023-11-28 06:07:18,088][87424] Updated weights for policy 0, policy_version 225787 (0.0008) -[2023-11-28 06:07:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 115507200. Throughput: 0: 2704.4, 1: 2679.3. Samples: 115513628. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:18,445][86177] Avg episode reward: [(0, '-494.260'), (1, '-525.840')] -[2023-11-28 06:07:19,178][87426] Updated weights for policy 1, policy_version 225410 (0.0010) -[2023-11-28 06:07:19,555][87426] Updated weights for policy 1, policy_version 225420 (0.0008) -[2023-11-28 06:07:19,937][87426] Updated weights for policy 1, policy_version 225430 (0.0009) -[2023-11-28 06:07:20,315][87426] Updated weights for policy 1, policy_version 225440 (0.0009) -[2023-11-28 06:07:20,463][87424] Updated weights for policy 0, policy_version 225797 (0.0011) -[2023-11-28 06:07:20,848][87424] Updated weights for policy 0, policy_version 225807 (0.0009) -[2023-11-28 06:07:21,237][87424] Updated weights for policy 0, policy_version 225817 (0.0012) -[2023-11-28 06:07:22,661][87426] Updated weights for policy 1, policy_version 225450 (0.0008) -[2023-11-28 06:07:23,036][87426] Updated weights for policy 1, policy_version 225460 (0.0008) -[2023-11-28 06:07:23,418][87426] Updated weights for policy 1, policy_version 225470 (0.0009) -[2023-11-28 06:07:23,432][87424] Updated weights for policy 0, policy_version 225827 (0.0011) -[2023-11-28 06:07:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 115523584. Throughput: 0: 2684.2, 1: 2655.0. Samples: 115545224. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:23,445][86177] Avg episode reward: [(0, '-493.050'), (1, '-523.940')] -[2023-11-28 06:07:23,820][87424] Updated weights for policy 0, policy_version 225837 (0.0007) -[2023-11-28 06:07:24,199][87424] Updated weights for policy 0, policy_version 225847 (0.0011) -[2023-11-28 06:07:25,652][87426] Updated weights for policy 1, policy_version 225480 (0.0010) -[2023-11-28 06:07:25,941][87424] Updated weights for policy 0, policy_version 225857 (0.0010) -[2023-11-28 06:07:26,030][87426] Updated weights for policy 1, policy_version 225490 (0.0010) -[2023-11-28 06:07:26,326][87424] Updated weights for policy 0, policy_version 225867 (0.0010) -[2023-11-28 06:07:26,417][87426] Updated weights for policy 1, policy_version 225500 (0.0009) -[2023-11-28 06:07:26,712][87424] Updated weights for policy 0, policy_version 225877 (0.0008) -[2023-11-28 06:07:27,094][87424] Updated weights for policy 0, policy_version 225887 (0.0007) -[2023-11-28 06:07:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115556352. Throughput: 0: 2700.2, 1: 2657.1. Samples: 115569836. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:28,445][86177] Avg episode reward: [(0, '-490.170'), (1, '-521.190')] -[2023-11-28 06:07:28,818][87426] Updated weights for policy 1, policy_version 225510 (0.0008) -[2023-11-28 06:07:29,196][87426] Updated weights for policy 1, policy_version 225520 (0.0009) -[2023-11-28 06:07:29,452][87424] Updated weights for policy 0, policy_version 225897 (0.0011) -[2023-11-28 06:07:29,577][87426] Updated weights for policy 1, policy_version 225530 (0.0011) -[2023-11-28 06:07:29,830][87424] Updated weights for policy 0, policy_version 225907 (0.0011) -[2023-11-28 06:07:30,216][87424] Updated weights for policy 0, policy_version 225917 (0.0012) -[2023-11-28 06:07:31,486][87426] Updated weights for policy 1, policy_version 225540 (0.0011) -[2023-11-28 06:07:31,861][87426] Updated weights for policy 1, policy_version 225550 (0.0011) -[2023-11-28 06:07:32,246][87426] Updated weights for policy 1, policy_version 225560 (0.0012) -[2023-11-28 06:07:32,447][87424] Updated weights for policy 0, policy_version 225927 (0.0011) -[2023-11-28 06:07:32,827][87424] Updated weights for policy 0, policy_version 225937 (0.0011) -[2023-11-28 06:07:33,204][87424] Updated weights for policy 0, policy_version 225947 (0.0010) -[2023-11-28 06:07:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 115589120. Throughput: 0: 2702.8, 1: 2669.9. Samples: 115595144. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:33,445][86177] Avg episode reward: [(0, '-491.610'), (1, '-521.960')] -[2023-11-28 06:07:34,637][87426] Updated weights for policy 1, policy_version 225570 (0.0011) -[2023-11-28 06:07:35,015][87426] Updated weights for policy 1, policy_version 225580 (0.0012) -[2023-11-28 06:07:35,401][87426] Updated weights for policy 1, policy_version 225590 (0.0012) -[2023-11-28 06:07:35,475][87424] Updated weights for policy 0, policy_version 225957 (0.0009) -[2023-11-28 06:07:35,773][87426] Updated weights for policy 1, policy_version 225600 (0.0011) -[2023-11-28 06:07:35,854][87424] Updated weights for policy 0, policy_version 225967 (0.0008) -[2023-11-28 06:07:36,235][87424] Updated weights for policy 0, policy_version 225977 (0.0008) -[2023-11-28 06:07:38,097][87426] Updated weights for policy 1, policy_version 225610 (0.0011) -[2023-11-28 06:07:38,126][87424] Updated weights for policy 0, policy_version 225987 (0.0008) -[2023-11-28 06:07:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 115605504. Throughput: 0: 2730.3, 1: 2696.8. Samples: 115628692. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:38,445][86177] Avg episode reward: [(0, '-492.730'), (1, '-527.460')] -[2023-11-28 06:07:38,478][87426] Updated weights for policy 1, policy_version 225620 (0.0008) -[2023-11-28 06:07:38,498][87424] Updated weights for policy 0, policy_version 225997 (0.0009) -[2023-11-28 06:07:38,860][87426] Updated weights for policy 1, policy_version 225630 (0.0011) -[2023-11-28 06:07:38,883][87424] Updated weights for policy 0, policy_version 226007 (0.0008) -[2023-11-28 06:07:40,914][87424] Updated weights for policy 0, policy_version 226017 (0.0012) -[2023-11-28 06:07:41,219][87426] Updated weights for policy 1, policy_version 225640 (0.0011) -[2023-11-28 06:07:41,291][87424] Updated weights for policy 0, policy_version 226027 (0.0012) -[2023-11-28 06:07:41,593][87426] Updated weights for policy 1, policy_version 225650 (0.0011) -[2023-11-28 06:07:41,668][87424] Updated weights for policy 0, policy_version 226037 (0.0011) -[2023-11-28 06:07:41,978][87426] Updated weights for policy 1, policy_version 225660 (0.0010) -[2023-11-28 06:07:42,050][87424] Updated weights for policy 0, policy_version 226047 (0.0010) -[2023-11-28 06:07:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115638272. Throughput: 0: 2734.5, 1: 2685.2. Samples: 115653356. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:43,445][86177] Avg episode reward: [(0, '-495.890'), (1, '-529.350')] -[2023-11-28 06:07:43,904][87426] Updated weights for policy 1, policy_version 225670 (0.0011) -[2023-11-28 06:07:44,284][87426] Updated weights for policy 1, policy_version 225680 (0.0011) -[2023-11-28 06:07:44,473][87424] Updated weights for policy 0, policy_version 226057 (0.0010) -[2023-11-28 06:07:44,667][87426] Updated weights for policy 1, policy_version 225690 (0.0010) -[2023-11-28 06:07:44,857][87424] Updated weights for policy 0, policy_version 226067 (0.0011) -[2023-11-28 06:07:45,233][87424] Updated weights for policy 0, policy_version 226077 (0.0012) -[2023-11-28 06:07:46,648][87426] Updated weights for policy 1, policy_version 225700 (0.0011) -[2023-11-28 06:07:47,033][87426] Updated weights for policy 1, policy_version 225710 (0.0011) -[2023-11-28 06:07:47,246][87424] Updated weights for policy 0, policy_version 226087 (0.0011) -[2023-11-28 06:07:47,414][87426] Updated weights for policy 1, policy_version 225720 (0.0009) -[2023-11-28 06:07:47,626][87424] Updated weights for policy 0, policy_version 226097 (0.0012) -[2023-11-28 06:07:48,001][87424] Updated weights for policy 0, policy_version 226107 (0.0012) -[2023-11-28 06:07:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 115671040. Throughput: 0: 2712.5, 1: 2679.4. Samples: 115677828. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:48,445][86177] Avg episode reward: [(0, '-498.460'), (1, '-526.830')] -[2023-11-28 06:07:49,217][87426] Updated weights for policy 1, policy_version 225730 (0.0010) -[2023-11-28 06:07:49,598][87426] Updated weights for policy 1, policy_version 225740 (0.0012) -[2023-11-28 06:07:49,974][87426] Updated weights for policy 1, policy_version 225750 (0.0010) -[2023-11-28 06:07:50,354][87426] Updated weights for policy 1, policy_version 225760 (0.0011) -[2023-11-28 06:07:50,444][87424] Updated weights for policy 0, policy_version 226117 (0.0011) -[2023-11-28 06:07:50,817][87424] Updated weights for policy 0, policy_version 226127 (0.0011) -[2023-11-28 06:07:51,195][87424] Updated weights for policy 0, policy_version 226137 (0.0010) -[2023-11-28 06:07:52,856][87426] Updated weights for policy 1, policy_version 225770 (0.0009) -[2023-11-28 06:07:53,239][87426] Updated weights for policy 1, policy_version 225780 (0.0011) -[2023-11-28 06:07:53,445][86177] Fps is (10 sec: 4914.9, 60 sec: 5324.7, 300 sec: 5442.8). Total num frames: 115687424. Throughput: 0: 2707.8, 1: 2710.8. Samples: 115709952. Policy #0 lag: (min: 12.0, avg: 24.6, max: 44.0) -[2023-11-28 06:07:53,446][86177] Avg episode reward: [(0, '-522.880'), (1, '-526.040')] -[2023-11-28 06:07:53,506][87424] Updated weights for policy 0, policy_version 226147 (0.0011) -[2023-11-28 06:07:53,638][87426] Updated weights for policy 1, policy_version 225790 (0.0010) -[2023-11-28 06:07:53,911][87424] Updated weights for policy 0, policy_version 226157 (0.0011) -[2023-11-28 06:07:54,283][87424] Updated weights for policy 0, policy_version 226167 (0.0012) -[2023-11-28 06:07:55,479][87426] Updated weights for policy 1, policy_version 225800 (0.0009) -[2023-11-28 06:07:55,855][87426] Updated weights for policy 1, policy_version 225810 (0.0008) -[2023-11-28 06:07:56,078][87424] Updated weights for policy 0, policy_version 226177 (0.0012) -[2023-11-28 06:07:56,232][87426] Updated weights for policy 1, policy_version 225820 (0.0009) -[2023-11-28 06:07:56,455][87424] Updated weights for policy 0, policy_version 226187 (0.0011) -[2023-11-28 06:07:56,828][87424] Updated weights for policy 0, policy_version 226197 (0.0012) -[2023-11-28 06:07:57,208][87424] Updated weights for policy 0, policy_version 226207 (0.0011) -[2023-11-28 06:07:58,034][87426] Updated weights for policy 1, policy_version 225830 (0.0011) -[2023-11-28 06:07:58,402][87426] Updated weights for policy 1, policy_version 225840 (0.0012) -[2023-11-28 06:07:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115720192. Throughput: 0: 2722.4, 1: 2752.5. Samples: 115736440. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:07:58,445][86177] Avg episode reward: [(0, '-522.920'), (1, '-526.620')] -[2023-11-28 06:07:58,795][87426] Updated weights for policy 1, policy_version 225850 (0.0012) -[2023-11-28 06:07:59,630][87424] Updated weights for policy 0, policy_version 226217 (0.0011) -[2023-11-28 06:08:00,006][87424] Updated weights for policy 0, policy_version 226227 (0.0012) -[2023-11-28 06:08:00,393][87424] Updated weights for policy 0, policy_version 226237 (0.0011) -[2023-11-28 06:08:00,758][87426] Updated weights for policy 1, policy_version 225860 (0.0012) -[2023-11-28 06:08:01,144][87426] Updated weights for policy 1, policy_version 225870 (0.0011) -[2023-11-28 06:08:01,536][87426] Updated weights for policy 1, policy_version 225880 (0.0011) -[2023-11-28 06:08:02,363][87424] Updated weights for policy 0, policy_version 226247 (0.0011) -[2023-11-28 06:08:02,750][87424] Updated weights for policy 0, policy_version 226257 (0.0016) -[2023-11-28 06:08:03,136][87424] Updated weights for policy 0, policy_version 226267 (0.0011) -[2023-11-28 06:08:03,372][87426] Updated weights for policy 1, policy_version 225890 (0.0011) -[2023-11-28 06:08:03,444][86177] Fps is (10 sec: 6554.0, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 115752960. Throughput: 0: 2728.5, 1: 2773.4. Samples: 115761216. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:03,445][86177] Avg episode reward: [(0, '-521.630'), (1, '-567.330')] -[2023-11-28 06:08:03,753][87426] Updated weights for policy 1, policy_version 225900 (0.0012) -[2023-11-28 06:08:04,129][87426] Updated weights for policy 1, policy_version 225910 (0.0008) -[2023-11-28 06:08:04,513][87426] Updated weights for policy 1, policy_version 225920 (0.0008) -[2023-11-28 06:08:05,508][87424] Updated weights for policy 0, policy_version 226277 (0.0011) -[2023-11-28 06:08:05,893][87424] Updated weights for policy 0, policy_version 226287 (0.0011) -[2023-11-28 06:08:06,281][87424] Updated weights for policy 0, policy_version 226297 (0.0012) -[2023-11-28 06:08:06,967][87426] Updated weights for policy 1, policy_version 225930 (0.0011) -[2023-11-28 06:08:07,343][87426] Updated weights for policy 1, policy_version 225940 (0.0008) -[2023-11-28 06:08:07,727][87426] Updated weights for policy 1, policy_version 225950 (0.0007) -[2023-11-28 06:08:08,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 115777536. Throughput: 0: 2731.2, 1: 2788.6. Samples: 115793616. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:08,446][86177] Avg episode reward: [(0, '-496.170'), (1, '-567.800')] -[2023-11-28 06:08:08,579][87424] Updated weights for policy 0, policy_version 226307 (0.0012) -[2023-11-28 06:08:08,967][87424] Updated weights for policy 0, policy_version 226317 (0.0012) -[2023-11-28 06:08:09,340][87424] Updated weights for policy 0, policy_version 226327 (0.0011) -[2023-11-28 06:08:10,199][87426] Updated weights for policy 1, policy_version 225960 (0.0008) -[2023-11-28 06:08:10,577][87426] Updated weights for policy 1, policy_version 225970 (0.0009) -[2023-11-28 06:08:10,957][87426] Updated weights for policy 1, policy_version 225980 (0.0010) -[2023-11-28 06:08:11,354][87424] Updated weights for policy 0, policy_version 226337 (0.0011) -[2023-11-28 06:08:11,732][87424] Updated weights for policy 0, policy_version 226347 (0.0009) -[2023-11-28 06:08:12,114][87424] Updated weights for policy 0, policy_version 226357 (0.0012) -[2023-11-28 06:08:12,501][87424] Updated weights for policy 0, policy_version 226367 (0.0013) -[2023-11-28 06:08:13,426][87426] Updated weights for policy 1, policy_version 225990 (0.0012) -[2023-11-28 06:08:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115802112. Throughput: 0: 2725.6, 1: 2772.6. Samples: 115817256. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:13,446][86177] Avg episode reward: [(0, '-495.840'), (1, '-566.630')] -[2023-11-28 06:08:13,798][87426] Updated weights for policy 1, policy_version 226000 (0.0012) -[2023-11-28 06:08:14,175][87426] Updated weights for policy 1, policy_version 226010 (0.0012) -[2023-11-28 06:08:14,580][87424] Updated weights for policy 0, policy_version 226377 (0.0008) -[2023-11-28 06:08:14,968][87424] Updated weights for policy 0, policy_version 226387 (0.0007) -[2023-11-28 06:08:15,351][87424] Updated weights for policy 0, policy_version 226397 (0.0008) -[2023-11-28 06:08:16,171][87426] Updated weights for policy 1, policy_version 226020 (0.0011) -[2023-11-28 06:08:16,558][87426] Updated weights for policy 1, policy_version 226030 (0.0012) -[2023-11-28 06:08:16,936][87426] Updated weights for policy 1, policy_version 226040 (0.0008) -[2023-11-28 06:08:17,601][87424] Updated weights for policy 0, policy_version 226407 (0.0007) -[2023-11-28 06:08:17,982][87424] Updated weights for policy 0, policy_version 226417 (0.0009) -[2023-11-28 06:08:18,368][87424] Updated weights for policy 0, policy_version 226427 (0.0011) -[2023-11-28 06:08:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 115826688. Throughput: 0: 2728.5, 1: 2755.0. Samples: 115841904. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:18,445][86177] Avg episode reward: [(0, '-493.610'), (1, '-599.500')] -[2023-11-28 06:08:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000226048_57868288.pth... -[2023-11-28 06:08:18,502][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000223488_57212928.pth -[2023-11-28 06:08:18,551][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000226432_57966592.pth... -[2023-11-28 06:08:18,598][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000223872_57311232.pth -[2023-11-28 06:08:19,365][87426] Updated weights for policy 1, policy_version 226050 (0.0007) -[2023-11-28 06:08:19,743][87426] Updated weights for policy 1, policy_version 226060 (0.0011) -[2023-11-28 06:08:20,115][87426] Updated weights for policy 1, policy_version 226070 (0.0012) -[2023-11-28 06:08:20,137][87424] Updated weights for policy 0, policy_version 226437 (0.0009) -[2023-11-28 06:08:20,495][87426] Updated weights for policy 1, policy_version 226080 (0.0011) -[2023-11-28 06:08:20,518][87424] Updated weights for policy 0, policy_version 226447 (0.0010) -[2023-11-28 06:08:20,898][87424] Updated weights for policy 0, policy_version 226457 (0.0008) -[2023-11-28 06:08:22,789][87426] Updated weights for policy 1, policy_version 226090 (0.0011) -[2023-11-28 06:08:23,170][87426] Updated weights for policy 1, policy_version 226100 (0.0010) -[2023-11-28 06:08:23,247][87424] Updated weights for policy 0, policy_version 226467 (0.0009) -[2023-11-28 06:08:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115851264. Throughput: 0: 2715.6, 1: 2760.4. Samples: 115875112. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:23,445][86177] Avg episode reward: [(0, '-498.950'), (1, '-581.960')] -[2023-11-28 06:08:23,546][87426] Updated weights for policy 1, policy_version 226110 (0.0011) -[2023-11-28 06:08:23,628][87424] Updated weights for policy 0, policy_version 226477 (0.0009) -[2023-11-28 06:08:24,013][87424] Updated weights for policy 0, policy_version 226487 (0.0011) -[2023-11-28 06:08:25,428][87426] Updated weights for policy 1, policy_version 226120 (0.0012) -[2023-11-28 06:08:25,808][87426] Updated weights for policy 1, policy_version 226130 (0.0012) -[2023-11-28 06:08:26,192][87426] Updated weights for policy 1, policy_version 226140 (0.0012) -[2023-11-28 06:08:26,205][87424] Updated weights for policy 0, policy_version 226497 (0.0012) -[2023-11-28 06:08:26,592][87424] Updated weights for policy 0, policy_version 226507 (0.0012) -[2023-11-28 06:08:26,982][87424] Updated weights for policy 0, policy_version 226517 (0.0012) -[2023-11-28 06:08:27,377][87424] Updated weights for policy 0, policy_version 226527 (0.0012) -[2023-11-28 06:08:28,147][87426] Updated weights for policy 1, policy_version 226150 (0.0010) -[2023-11-28 06:08:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115884032. Throughput: 0: 2705.9, 1: 2783.8. Samples: 115900392. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:28,445][86177] Avg episode reward: [(0, '-498.940'), (1, '-582.340')] -[2023-11-28 06:08:28,521][87426] Updated weights for policy 1, policy_version 226160 (0.0012) -[2023-11-28 06:08:28,897][87426] Updated weights for policy 1, policy_version 226170 (0.0011) -[2023-11-28 06:08:29,723][87424] Updated weights for policy 0, policy_version 226537 (0.0012) -[2023-11-28 06:08:30,105][87424] Updated weights for policy 0, policy_version 226547 (0.0011) -[2023-11-28 06:08:30,488][87424] Updated weights for policy 0, policy_version 226557 (0.0014) -[2023-11-28 06:08:30,970][87426] Updated weights for policy 1, policy_version 226180 (0.0012) -[2023-11-28 06:08:31,351][87426] Updated weights for policy 1, policy_version 226190 (0.0012) -[2023-11-28 06:08:31,728][87426] Updated weights for policy 1, policy_version 226200 (0.0016) -[2023-11-28 06:08:32,497][87424] Updated weights for policy 0, policy_version 226567 (0.0011) -[2023-11-28 06:08:32,877][87424] Updated weights for policy 0, policy_version 226577 (0.0012) -[2023-11-28 06:08:33,248][87424] Updated weights for policy 0, policy_version 226587 (0.0011) -[2023-11-28 06:08:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 115916800. Throughput: 0: 2738.1, 1: 2765.6. Samples: 115925496. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:33,445][86177] Avg episode reward: [(0, '-500.170'), (1, '-581.100')] -[2023-11-28 06:08:34,055][87426] Updated weights for policy 1, policy_version 226210 (0.0010) -[2023-11-28 06:08:34,432][87426] Updated weights for policy 1, policy_version 226220 (0.0007) -[2023-11-28 06:08:34,818][87426] Updated weights for policy 1, policy_version 226230 (0.0008) -[2023-11-28 06:08:35,032][87424] Updated weights for policy 0, policy_version 226597 (0.0010) -[2023-11-28 06:08:35,186][87426] Updated weights for policy 1, policy_version 226240 (0.0008) -[2023-11-28 06:08:35,414][87424] Updated weights for policy 0, policy_version 226607 (0.0008) -[2023-11-28 06:08:35,796][87424] Updated weights for policy 0, policy_version 226617 (0.0009) -[2023-11-28 06:08:37,750][87426] Updated weights for policy 1, policy_version 226250 (0.0007) -[2023-11-28 06:08:38,132][87426] Updated weights for policy 1, policy_version 226260 (0.0008) -[2023-11-28 06:08:38,172][87424] Updated weights for policy 0, policy_version 226627 (0.0008) -[2023-11-28 06:08:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115933184. Throughput: 0: 2775.9, 1: 2730.2. Samples: 115957720. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:38,445][86177] Avg episode reward: [(0, '-498.960'), (1, '-550.720')] -[2023-11-28 06:08:38,517][87426] Updated weights for policy 1, policy_version 226270 (0.0008) -[2023-11-28 06:08:38,551][87424] Updated weights for policy 0, policy_version 226637 (0.0011) -[2023-11-28 06:08:38,942][87424] Updated weights for policy 0, policy_version 226647 (0.0012) -[2023-11-28 06:08:40,857][87424] Updated weights for policy 0, policy_version 226657 (0.0010) -[2023-11-28 06:08:41,031][87426] Updated weights for policy 1, policy_version 226280 (0.0009) -[2023-11-28 06:08:41,240][87424] Updated weights for policy 0, policy_version 226667 (0.0012) -[2023-11-28 06:08:41,403][87426] Updated weights for policy 1, policy_version 226290 (0.0008) -[2023-11-28 06:08:41,633][87424] Updated weights for policy 0, policy_version 226677 (0.0012) -[2023-11-28 06:08:41,782][87426] Updated weights for policy 1, policy_version 226300 (0.0012) -[2023-11-28 06:08:42,009][87424] Updated weights for policy 0, policy_version 226687 (0.0011) -[2023-11-28 06:08:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 115965952. Throughput: 0: 2772.4, 1: 2662.9. Samples: 115981032. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:43,445][86177] Avg episode reward: [(0, '-493.640'), (1, '-533.220')] -[2023-11-28 06:08:44,062][87426] Updated weights for policy 1, policy_version 226310 (0.0012) -[2023-11-28 06:08:44,217][87424] Updated weights for policy 0, policy_version 226697 (0.0010) -[2023-11-28 06:08:44,449][87426] Updated weights for policy 1, policy_version 226320 (0.0012) -[2023-11-28 06:08:44,610][87424] Updated weights for policy 0, policy_version 226707 (0.0007) -[2023-11-28 06:08:44,824][87426] Updated weights for policy 1, policy_version 226330 (0.0010) -[2023-11-28 06:08:44,995][87424] Updated weights for policy 0, policy_version 226717 (0.0008) -[2023-11-28 06:08:46,867][87426] Updated weights for policy 1, policy_version 226340 (0.0011) -[2023-11-28 06:08:47,236][87426] Updated weights for policy 1, policy_version 226350 (0.0011) -[2023-11-28 06:08:47,350][87424] Updated weights for policy 0, policy_version 226727 (0.0011) -[2023-11-28 06:08:47,612][87426] Updated weights for policy 1, policy_version 226360 (0.0011) -[2023-11-28 06:08:47,723][87424] Updated weights for policy 0, policy_version 226737 (0.0008) -[2023-11-28 06:08:48,108][87424] Updated weights for policy 0, policy_version 226747 (0.0012) -[2023-11-28 06:08:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5498.5). Total num frames: 115998720. Throughput: 0: 2768.6, 1: 2670.1. Samples: 116005960. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:48,445][86177] Avg episode reward: [(0, '-490.740'), (1, '-556.770')] -[2023-11-28 06:08:49,391][87426] Updated weights for policy 1, policy_version 226370 (0.0011) -[2023-11-28 06:08:49,774][87426] Updated weights for policy 1, policy_version 226380 (0.0008) -[2023-11-28 06:08:50,153][87426] Updated weights for policy 1, policy_version 226390 (0.0009) -[2023-11-28 06:08:50,360][87424] Updated weights for policy 0, policy_version 226757 (0.0010) -[2023-11-28 06:08:50,536][87426] Updated weights for policy 1, policy_version 226400 (0.0010) -[2023-11-28 06:08:50,740][87424] Updated weights for policy 0, policy_version 226767 (0.0011) -[2023-11-28 06:08:51,120][87424] Updated weights for policy 0, policy_version 226777 (0.0012) -[2023-11-28 06:08:52,358][87426] Updated weights for policy 1, policy_version 226410 (0.0011) -[2023-11-28 06:08:52,723][87426] Updated weights for policy 1, policy_version 226420 (0.0012) -[2023-11-28 06:08:53,099][87426] Updated weights for policy 1, policy_version 226430 (0.0011) -[2023-11-28 06:08:53,364][87424] Updated weights for policy 0, policy_version 226787 (0.0010) -[2023-11-28 06:08:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 116023296. Throughput: 0: 2768.5, 1: 2678.0. Samples: 116038708. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:53,445][86177] Avg episode reward: [(0, '-501.400'), (1, '-552.440')] -[2023-11-28 06:08:53,744][87424] Updated weights for policy 0, policy_version 226797 (0.0011) -[2023-11-28 06:08:54,127][87424] Updated weights for policy 0, policy_version 226807 (0.0012) -[2023-11-28 06:08:55,089][87426] Updated weights for policy 1, policy_version 226440 (0.0008) -[2023-11-28 06:08:55,462][87426] Updated weights for policy 1, policy_version 226450 (0.0008) -[2023-11-28 06:08:55,853][87426] Updated weights for policy 1, policy_version 226460 (0.0007) -[2023-11-28 06:08:56,531][87424] Updated weights for policy 0, policy_version 226817 (0.0010) -[2023-11-28 06:08:56,903][87424] Updated weights for policy 0, policy_version 226827 (0.0007) -[2023-11-28 06:08:57,294][87424] Updated weights for policy 0, policy_version 226837 (0.0010) -[2023-11-28 06:08:57,672][87424] Updated weights for policy 0, policy_version 226847 (0.0008) -[2023-11-28 06:08:58,366][87426] Updated weights for policy 1, policy_version 226470 (0.0007) -[2023-11-28 06:08:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116047872. Throughput: 0: 2744.4, 1: 2705.2. Samples: 116062484. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:08:58,445][86177] Avg episode reward: [(0, '-504.080'), (1, '-549.270')] -[2023-11-28 06:08:58,738][87426] Updated weights for policy 1, policy_version 226480 (0.0010) -[2023-11-28 06:08:59,115][87426] Updated weights for policy 1, policy_version 226490 (0.0011) -[2023-11-28 06:08:59,373][87424] Updated weights for policy 0, policy_version 226857 (0.0011) -[2023-11-28 06:08:59,757][87424] Updated weights for policy 0, policy_version 226867 (0.0012) -[2023-11-28 06:09:00,139][87424] Updated weights for policy 0, policy_version 226877 (0.0012) -[2023-11-28 06:09:01,662][87426] Updated weights for policy 1, policy_version 226500 (0.0009) -[2023-11-28 06:09:02,046][87426] Updated weights for policy 1, policy_version 226510 (0.0010) -[2023-11-28 06:09:02,428][87426] Updated weights for policy 1, policy_version 226520 (0.0010) -[2023-11-28 06:09:02,602][87424] Updated weights for policy 0, policy_version 226887 (0.0008) -[2023-11-28 06:09:02,992][87424] Updated weights for policy 0, policy_version 226897 (0.0008) -[2023-11-28 06:09:03,373][87424] Updated weights for policy 0, policy_version 226907 (0.0008) -[2023-11-28 06:09:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 116072448. Throughput: 0: 2739.1, 1: 2706.2. Samples: 116086944. Policy #0 lag: (min: 31.0, avg: 54.4, max: 95.0) -[2023-11-28 06:09:03,446][86177] Avg episode reward: [(0, '-505.080'), (1, '-559.150')] -[2023-11-28 06:09:04,919][87426] Updated weights for policy 1, policy_version 226530 (0.0010) -[2023-11-28 06:09:05,297][87426] Updated weights for policy 1, policy_version 226540 (0.0009) -[2023-11-28 06:09:05,687][87426] Updated weights for policy 1, policy_version 226550 (0.0007) -[2023-11-28 06:09:05,758][87424] Updated weights for policy 0, policy_version 226917 (0.0009) -[2023-11-28 06:09:06,077][87426] Updated weights for policy 1, policy_version 226560 (0.0007) -[2023-11-28 06:09:06,136][87424] Updated weights for policy 0, policy_version 226927 (0.0011) -[2023-11-28 06:09:06,515][87424] Updated weights for policy 0, policy_version 226937 (0.0007) -[2023-11-28 06:09:08,362][87426] Updated weights for policy 1, policy_version 226570 (0.0012) -[2023-11-28 06:09:08,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 116097024. Throughput: 0: 2723.9, 1: 2678.3. Samples: 116118212. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:08,446][86177] Avg episode reward: [(0, '-509.440'), (1, '-541.040')] -[2023-11-28 06:09:08,651][87424] Updated weights for policy 0, policy_version 226947 (0.0009) -[2023-11-28 06:09:08,747][87426] Updated weights for policy 1, policy_version 226580 (0.0009) -[2023-11-28 06:09:09,035][87424] Updated weights for policy 0, policy_version 226957 (0.0008) -[2023-11-28 06:09:09,131][87426] Updated weights for policy 1, policy_version 226590 (0.0009) -[2023-11-28 06:09:09,420][87424] Updated weights for policy 0, policy_version 226967 (0.0007) -[2023-11-28 06:09:11,478][87426] Updated weights for policy 1, policy_version 226600 (0.0008) -[2023-11-28 06:09:11,494][87424] Updated weights for policy 0, policy_version 226977 (0.0008) -[2023-11-28 06:09:11,849][87426] Updated weights for policy 1, policy_version 226610 (0.0010) -[2023-11-28 06:09:11,877][87424] Updated weights for policy 0, policy_version 226987 (0.0010) -[2023-11-28 06:09:12,233][87426] Updated weights for policy 1, policy_version 226620 (0.0011) -[2023-11-28 06:09:12,259][87424] Updated weights for policy 0, policy_version 226997 (0.0009) -[2023-11-28 06:09:12,642][87424] Updated weights for policy 0, policy_version 227007 (0.0010) -[2023-11-28 06:09:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 116129792. Throughput: 0: 2732.0, 1: 2637.5. Samples: 116142020. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:13,445][86177] Avg episode reward: [(0, '-498.140'), (1, '-538.570')] -[2023-11-28 06:09:14,720][87426] Updated weights for policy 1, policy_version 226630 (0.0011) -[2023-11-28 06:09:15,087][87426] Updated weights for policy 1, policy_version 226640 (0.0009) -[2023-11-28 06:09:15,209][87424] Updated weights for policy 0, policy_version 227017 (0.0011) -[2023-11-28 06:09:15,468][87426] Updated weights for policy 1, policy_version 226650 (0.0009) -[2023-11-28 06:09:15,594][87424] Updated weights for policy 0, policy_version 227027 (0.0012) -[2023-11-28 06:09:15,986][87424] Updated weights for policy 0, policy_version 227037 (0.0012) -[2023-11-28 06:09:17,224][87426] Updated weights for policy 1, policy_version 226660 (0.0012) -[2023-11-28 06:09:17,604][87426] Updated weights for policy 1, policy_version 226670 (0.0011) -[2023-11-28 06:09:17,761][87424] Updated weights for policy 0, policy_version 227047 (0.0009) -[2023-11-28 06:09:17,980][87426] Updated weights for policy 1, policy_version 226680 (0.0011) -[2023-11-28 06:09:18,144][87424] Updated weights for policy 0, policy_version 227057 (0.0009) -[2023-11-28 06:09:18,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 116154368. Throughput: 0: 2698.6, 1: 2649.5. Samples: 116166164. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:18,446][86177] Avg episode reward: [(0, '-514.580'), (1, '-537.590')] -[2023-11-28 06:09:18,526][87424] Updated weights for policy 0, policy_version 227067 (0.0009) -[2023-11-28 06:09:20,031][87426] Updated weights for policy 1, policy_version 226690 (0.0011) -[2023-11-28 06:09:20,410][87426] Updated weights for policy 1, policy_version 226700 (0.0012) -[2023-11-28 06:09:20,726][87424] Updated weights for policy 0, policy_version 227077 (0.0009) -[2023-11-28 06:09:20,791][87426] Updated weights for policy 1, policy_version 226710 (0.0012) -[2023-11-28 06:09:21,118][87424] Updated weights for policy 0, policy_version 227087 (0.0011) -[2023-11-28 06:09:21,171][87426] Updated weights for policy 1, policy_version 226720 (0.0012) -[2023-11-28 06:09:21,504][87424] Updated weights for policy 0, policy_version 227097 (0.0008) -[2023-11-28 06:09:23,376][87424] Updated weights for policy 0, policy_version 227107 (0.0010) -[2023-11-28 06:09:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116178944. Throughput: 0: 2690.3, 1: 2682.7. Samples: 116199508. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:23,446][86177] Avg episode reward: [(0, '-515.180'), (1, '-530.980')] -[2023-11-28 06:09:23,534][87426] Updated weights for policy 1, policy_version 226730 (0.0009) -[2023-11-28 06:09:23,753][87424] Updated weights for policy 0, policy_version 227117 (0.0011) -[2023-11-28 06:09:23,915][87426] Updated weights for policy 1, policy_version 226740 (0.0008) -[2023-11-28 06:09:24,149][87424] Updated weights for policy 0, policy_version 227127 (0.0008) -[2023-11-28 06:09:24,293][87426] Updated weights for policy 1, policy_version 226750 (0.0007) -[2023-11-28 06:09:26,309][87426] Updated weights for policy 1, policy_version 226760 (0.0011) -[2023-11-28 06:09:26,488][87424] Updated weights for policy 0, policy_version 227137 (0.0008) -[2023-11-28 06:09:26,684][87426] Updated weights for policy 1, policy_version 226770 (0.0010) -[2023-11-28 06:09:26,873][87424] Updated weights for policy 0, policy_version 227147 (0.0011) -[2023-11-28 06:09:27,066][87426] Updated weights for policy 1, policy_version 226780 (0.0007) -[2023-11-28 06:09:27,251][87424] Updated weights for policy 0, policy_version 227157 (0.0012) -[2023-11-28 06:09:27,629][87424] Updated weights for policy 0, policy_version 227167 (0.0012) -[2023-11-28 06:09:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116211712. Throughput: 0: 2686.1, 1: 2745.4. Samples: 116225452. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:28,445][86177] Avg episode reward: [(0, '-512.060'), (1, '-538.960')] -[2023-11-28 06:09:28,934][87426] Updated weights for policy 1, policy_version 226790 (0.0010) -[2023-11-28 06:09:29,314][87426] Updated weights for policy 1, policy_version 226800 (0.0012) -[2023-11-28 06:09:29,696][87426] Updated weights for policy 1, policy_version 226810 (0.0012) -[2023-11-28 06:09:29,858][87424] Updated weights for policy 0, policy_version 227177 (0.0009) -[2023-11-28 06:09:30,241][87424] Updated weights for policy 0, policy_version 227187 (0.0011) -[2023-11-28 06:09:30,624][87424] Updated weights for policy 0, policy_version 227197 (0.0009) -[2023-11-28 06:09:32,000][87426] Updated weights for policy 1, policy_version 226820 (0.0010) -[2023-11-28 06:09:32,381][87426] Updated weights for policy 1, policy_version 226830 (0.0008) -[2023-11-28 06:09:32,597][87424] Updated weights for policy 0, policy_version 227207 (0.0010) -[2023-11-28 06:09:32,759][87426] Updated weights for policy 1, policy_version 226840 (0.0010) -[2023-11-28 06:09:32,987][87424] Updated weights for policy 0, policy_version 227217 (0.0011) -[2023-11-28 06:09:33,368][87424] Updated weights for policy 0, policy_version 227227 (0.0012) -[2023-11-28 06:09:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 116236288. Throughput: 0: 2678.6, 1: 2729.6. Samples: 116249328. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:33,445][86177] Avg episode reward: [(0, '-511.730'), (1, '-545.960')] -[2023-11-28 06:09:34,896][87426] Updated weights for policy 1, policy_version 226850 (0.0011) -[2023-11-28 06:09:35,275][87424] Updated weights for policy 0, policy_version 227237 (0.0010) -[2023-11-28 06:09:35,275][87426] Updated weights for policy 1, policy_version 226860 (0.0012) -[2023-11-28 06:09:35,656][87426] Updated weights for policy 1, policy_version 226870 (0.0011) -[2023-11-28 06:09:35,658][87424] Updated weights for policy 0, policy_version 227247 (0.0009) -[2023-11-28 06:09:36,032][87426] Updated weights for policy 1, policy_version 226880 (0.0012) -[2023-11-28 06:09:36,044][87424] Updated weights for policy 0, policy_version 227257 (0.0011) -[2023-11-28 06:09:38,008][87426] Updated weights for policy 1, policy_version 226890 (0.0011) -[2023-11-28 06:09:38,068][87424] Updated weights for policy 0, policy_version 227267 (0.0012) -[2023-11-28 06:09:38,392][87426] Updated weights for policy 1, policy_version 226900 (0.0008) -[2023-11-28 06:09:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 116260864. Throughput: 0: 2689.1, 1: 2733.1. Samples: 116282708. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:38,445][86177] Avg episode reward: [(0, '-496.770'), (1, '-544.450')] -[2023-11-28 06:09:38,447][87424] Updated weights for policy 0, policy_version 227277 (0.0012) -[2023-11-28 06:09:38,770][87426] Updated weights for policy 1, policy_version 226910 (0.0011) -[2023-11-28 06:09:38,838][87424] Updated weights for policy 0, policy_version 227287 (0.0011) -[2023-11-28 06:09:40,956][87424] Updated weights for policy 0, policy_version 227297 (0.0012) -[2023-11-28 06:09:41,168][87426] Updated weights for policy 1, policy_version 226920 (0.0011) -[2023-11-28 06:09:41,337][87424] Updated weights for policy 0, policy_version 227307 (0.0010) -[2023-11-28 06:09:41,558][87426] Updated weights for policy 1, policy_version 226930 (0.0008) -[2023-11-28 06:09:41,718][87424] Updated weights for policy 0, policy_version 227317 (0.0011) -[2023-11-28 06:09:41,935][87426] Updated weights for policy 1, policy_version 226940 (0.0011) -[2023-11-28 06:09:42,103][87424] Updated weights for policy 0, policy_version 227327 (0.0016) -[2023-11-28 06:09:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 116293632. Throughput: 0: 2695.4, 1: 2731.6. Samples: 116306700. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:43,445][86177] Avg episode reward: [(0, '-499.050'), (1, '-555.120')] -[2023-11-28 06:09:43,974][87426] Updated weights for policy 1, policy_version 226950 (0.0010) -[2023-11-28 06:09:44,355][87426] Updated weights for policy 1, policy_version 226960 (0.0011) -[2023-11-28 06:09:44,554][87424] Updated weights for policy 0, policy_version 227337 (0.0011) -[2023-11-28 06:09:44,748][87426] Updated weights for policy 1, policy_version 226970 (0.0010) -[2023-11-28 06:09:44,944][87424] Updated weights for policy 0, policy_version 227347 (0.0012) -[2023-11-28 06:09:45,329][87424] Updated weights for policy 0, policy_version 227357 (0.0012) -[2023-11-28 06:09:47,026][87426] Updated weights for policy 1, policy_version 226980 (0.0007) -[2023-11-28 06:09:47,406][87426] Updated weights for policy 1, policy_version 226990 (0.0007) -[2023-11-28 06:09:47,797][87426] Updated weights for policy 1, policy_version 227000 (0.0009) -[2023-11-28 06:09:47,911][87424] Updated weights for policy 0, policy_version 227367 (0.0009) -[2023-11-28 06:09:48,285][87424] Updated weights for policy 0, policy_version 227377 (0.0011) -[2023-11-28 06:09:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 116318208. Throughput: 0: 2685.8, 1: 2732.4. Samples: 116330760. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:48,445][86177] Avg episode reward: [(0, '-513.520'), (1, '-553.670')] -[2023-11-28 06:09:48,667][87424] Updated weights for policy 0, policy_version 227387 (0.0011) -[2023-11-28 06:09:50,169][87426] Updated weights for policy 1, policy_version 227010 (0.0011) -[2023-11-28 06:09:50,548][87426] Updated weights for policy 1, policy_version 227020 (0.0011) -[2023-11-28 06:09:50,675][87424] Updated weights for policy 0, policy_version 227397 (0.0010) -[2023-11-28 06:09:50,927][87426] Updated weights for policy 1, policy_version 227030 (0.0011) -[2023-11-28 06:09:51,050][87424] Updated weights for policy 0, policy_version 227407 (0.0007) -[2023-11-28 06:09:51,311][87426] Updated weights for policy 1, policy_version 227040 (0.0012) -[2023-11-28 06:09:51,437][87424] Updated weights for policy 0, policy_version 227417 (0.0007) -[2023-11-28 06:09:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 116342784. Throughput: 0: 2684.0, 1: 2740.5. Samples: 116362312. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:53,445][86177] Avg episode reward: [(0, '-523.770'), (1, '-560.680')] -[2023-11-28 06:09:53,664][87426] Updated weights for policy 1, policy_version 227050 (0.0012) -[2023-11-28 06:09:53,954][87424] Updated weights for policy 0, policy_version 227427 (0.0009) -[2023-11-28 06:09:54,041][87426] Updated weights for policy 1, policy_version 227060 (0.0011) -[2023-11-28 06:09:54,343][87424] Updated weights for policy 0, policy_version 227437 (0.0007) -[2023-11-28 06:09:54,424][87426] Updated weights for policy 1, policy_version 227070 (0.0012) -[2023-11-28 06:09:54,727][87424] Updated weights for policy 0, policy_version 227447 (0.0008) -[2023-11-28 06:09:56,978][87426] Updated weights for policy 1, policy_version 227080 (0.0012) -[2023-11-28 06:09:57,231][87424] Updated weights for policy 0, policy_version 227457 (0.0008) -[2023-11-28 06:09:57,352][87426] Updated weights for policy 1, policy_version 227090 (0.0011) -[2023-11-28 06:09:57,613][87424] Updated weights for policy 0, policy_version 227467 (0.0010) -[2023-11-28 06:09:57,740][87426] Updated weights for policy 1, policy_version 227100 (0.0012) -[2023-11-28 06:09:57,998][87424] Updated weights for policy 0, policy_version 227477 (0.0009) -[2023-11-28 06:09:58,382][87424] Updated weights for policy 0, policy_version 227487 (0.0011) -[2023-11-28 06:09:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 116375552. Throughput: 0: 2672.1, 1: 2747.1. Samples: 116385884. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:09:58,445][86177] Avg episode reward: [(0, '-521.840'), (1, '-560.490')] -[2023-11-28 06:09:59,559][87426] Updated weights for policy 1, policy_version 227110 (0.0010) -[2023-11-28 06:09:59,937][87426] Updated weights for policy 1, policy_version 227120 (0.0009) -[2023-11-28 06:10:00,323][87426] Updated weights for policy 1, policy_version 227130 (0.0011) -[2023-11-28 06:10:00,360][87424] Updated weights for policy 0, policy_version 227497 (0.0011) -[2023-11-28 06:10:00,742][87424] Updated weights for policy 0, policy_version 227507 (0.0009) -[2023-11-28 06:10:01,123][87424] Updated weights for policy 0, policy_version 227517 (0.0007) -[2023-11-28 06:10:02,391][87426] Updated weights for policy 1, policy_version 227140 (0.0011) -[2023-11-28 06:10:02,770][87426] Updated weights for policy 1, policy_version 227150 (0.0011) -[2023-11-28 06:10:03,145][87426] Updated weights for policy 1, policy_version 227160 (0.0009) -[2023-11-28 06:10:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 116391936. Throughput: 0: 2685.8, 1: 2754.1. Samples: 116410956. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:10:03,445][86177] Avg episode reward: [(0, '-519.670'), (1, '-537.130')] -[2023-11-28 06:10:03,621][87424] Updated weights for policy 0, policy_version 227527 (0.0008) -[2023-11-28 06:10:04,006][87424] Updated weights for policy 0, policy_version 227537 (0.0008) -[2023-11-28 06:10:04,393][87424] Updated weights for policy 0, policy_version 227547 (0.0009) -[2023-11-28 06:10:05,097][87426] Updated weights for policy 1, policy_version 227170 (0.0008) -[2023-11-28 06:10:05,476][87426] Updated weights for policy 1, policy_version 227180 (0.0007) -[2023-11-28 06:10:05,865][87426] Updated weights for policy 1, policy_version 227190 (0.0010) -[2023-11-28 06:10:06,245][87426] Updated weights for policy 1, policy_version 227200 (0.0011) -[2023-11-28 06:10:06,764][87424] Updated weights for policy 0, policy_version 227557 (0.0010) -[2023-11-28 06:10:07,138][87424] Updated weights for policy 0, policy_version 227567 (0.0010) -[2023-11-28 06:10:07,515][87424] Updated weights for policy 0, policy_version 227577 (0.0008) -[2023-11-28 06:10:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 116424704. Throughput: 0: 2687.6, 1: 2741.4. Samples: 116443812. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:10:08,445][86177] Avg episode reward: [(0, '-491.090'), (1, '-527.150')] -[2023-11-28 06:10:08,769][87426] Updated weights for policy 1, policy_version 227210 (0.0007) -[2023-11-28 06:10:09,157][87426] Updated weights for policy 1, policy_version 227220 (0.0011) -[2023-11-28 06:10:09,432][87424] Updated weights for policy 0, policy_version 227587 (0.0009) -[2023-11-28 06:10:09,530][87426] Updated weights for policy 1, policy_version 227230 (0.0011) -[2023-11-28 06:10:09,805][87424] Updated weights for policy 0, policy_version 227597 (0.0011) -[2023-11-28 06:10:10,183][87424] Updated weights for policy 0, policy_version 227607 (0.0011) -[2023-11-28 06:10:11,768][87426] Updated weights for policy 1, policy_version 227240 (0.0012) -[2023-11-28 06:10:12,169][87426] Updated weights for policy 1, policy_version 227250 (0.0012) -[2023-11-28 06:10:12,552][87426] Updated weights for policy 1, policy_version 227260 (0.0011) -[2023-11-28 06:10:12,637][87424] Updated weights for policy 0, policy_version 227617 (0.0012) -[2023-11-28 06:10:13,014][87424] Updated weights for policy 0, policy_version 227627 (0.0012) -[2023-11-28 06:10:13,394][87424] Updated weights for policy 0, policy_version 227637 (0.0012) -[2023-11-28 06:10:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 116449280. Throughput: 0: 2685.4, 1: 2689.3. Samples: 116467316. Policy #0 lag: (min: 31.0, avg: 51.4, max: 71.0) -[2023-11-28 06:10:13,445][86177] Avg episode reward: [(0, '-520.230'), (1, '-522.560')] -[2023-11-28 06:10:13,783][87424] Updated weights for policy 0, policy_version 227647 (0.0010) -[2023-11-28 06:10:14,603][87426] Updated weights for policy 1, policy_version 227270 (0.0012) -[2023-11-28 06:10:14,992][87426] Updated weights for policy 1, policy_version 227280 (0.0012) -[2023-11-28 06:10:15,366][87426] Updated weights for policy 1, policy_version 227290 (0.0011) -[2023-11-28 06:10:15,649][87424] Updated weights for policy 0, policy_version 227657 (0.0011) -[2023-11-28 06:10:16,023][87424] Updated weights for policy 0, policy_version 227667 (0.0012) -[2023-11-28 06:10:16,407][87424] Updated weights for policy 0, policy_version 227677 (0.0012) -[2023-11-28 06:10:17,470][87426] Updated weights for policy 1, policy_version 227300 (0.0011) -[2023-11-28 06:10:17,850][87426] Updated weights for policy 1, policy_version 227310 (0.0012) -[2023-11-28 06:10:18,231][87426] Updated weights for policy 1, policy_version 227320 (0.0010) -[2023-11-28 06:10:18,246][87424] Updated weights for policy 0, policy_version 227687 (0.0011) -[2023-11-28 06:10:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 116473856. Throughput: 0: 2689.2, 1: 2692.6. Samples: 116491508. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:10:18,445][86177] Avg episode reward: [(0, '-521.770'), (1, '-520.040')] -[2023-11-28 06:10:18,543][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000227328_58195968.pth... -[2023-11-28 06:10:18,591][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000224800_57548800.pth -[2023-11-28 06:10:18,625][87424] Updated weights for policy 0, policy_version 227697 (0.0012) -[2023-11-28 06:10:19,011][87424] Updated weights for policy 0, policy_version 227707 (0.0012) -[2023-11-28 06:10:19,205][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000227712_58294272.pth... -[2023-11-28 06:10:19,235][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000225152_57638912.pth -[2023-11-28 06:10:20,797][87424] Updated weights for policy 0, policy_version 227717 (0.0012) -[2023-11-28 06:10:20,855][87426] Updated weights for policy 1, policy_version 227330 (0.0008) -[2023-11-28 06:10:21,171][87424] Updated weights for policy 0, policy_version 227727 (0.0012) -[2023-11-28 06:10:21,233][87426] Updated weights for policy 1, policy_version 227340 (0.0010) -[2023-11-28 06:10:21,561][87424] Updated weights for policy 0, policy_version 227737 (0.0012) -[2023-11-28 06:10:21,605][87426] Updated weights for policy 1, policy_version 227350 (0.0010) -[2023-11-28 06:10:21,984][87426] Updated weights for policy 1, policy_version 227360 (0.0008) -[2023-11-28 06:10:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 116506624. Throughput: 0: 2680.1, 1: 2666.4. Samples: 116523300. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:10:23,445][86177] Avg episode reward: [(0, '-522.270'), (1, '-523.470')] -[2023-11-28 06:10:23,991][87424] Updated weights for policy 0, policy_version 227747 (0.0011) -[2023-11-28 06:10:24,125][87426] Updated weights for policy 1, policy_version 227370 (0.0012) -[2023-11-28 06:10:24,386][87424] Updated weights for policy 0, policy_version 227757 (0.0009) -[2023-11-28 06:10:24,504][87426] Updated weights for policy 1, policy_version 227380 (0.0011) -[2023-11-28 06:10:24,768][87424] Updated weights for policy 0, policy_version 227767 (0.0010) -[2023-11-28 06:10:24,881][87426] Updated weights for policy 1, policy_version 227390 (0.0009) -[2023-11-28 06:10:26,738][87424] Updated weights for policy 0, policy_version 227777 (0.0012) -[2023-11-28 06:10:26,829][87426] Updated weights for policy 1, policy_version 227400 (0.0010) -[2023-11-28 06:10:27,119][87424] Updated weights for policy 0, policy_version 227787 (0.0012) -[2023-11-28 06:10:27,214][87426] Updated weights for policy 1, policy_version 227410 (0.0007) -[2023-11-28 06:10:27,502][87424] Updated weights for policy 0, policy_version 227797 (0.0012) -[2023-11-28 06:10:27,599][87426] Updated weights for policy 1, policy_version 227420 (0.0007) -[2023-11-28 06:10:27,878][87424] Updated weights for policy 0, policy_version 227807 (0.0012) -[2023-11-28 06:10:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116539392. Throughput: 0: 2692.3, 1: 2687.2. Samples: 116548776. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:10:28,445][86177] Avg episode reward: [(0, '-496.620'), (1, '-521.150')] -[2023-11-28 06:10:29,715][87424] Updated weights for policy 0, policy_version 227817 (0.0010) -[2023-11-28 06:10:29,831][87426] Updated weights for policy 1, policy_version 227430 (0.0010) -[2023-11-28 06:10:30,093][87424] Updated weights for policy 0, policy_version 227827 (0.0010) -[2023-11-28 06:10:30,212][87426] Updated weights for policy 1, policy_version 227440 (0.0011) -[2023-11-28 06:10:30,471][87424] Updated weights for policy 0, policy_version 227837 (0.0011) -[2023-11-28 06:10:30,584][87426] Updated weights for policy 1, policy_version 227450 (0.0009) -[2023-11-28 06:10:32,379][87424] Updated weights for policy 0, policy_version 227847 (0.0010) -[2023-11-28 06:10:32,758][87424] Updated weights for policy 0, policy_version 227857 (0.0007) -[2023-11-28 06:10:33,129][87424] Updated weights for policy 0, policy_version 227867 (0.0009) -[2023-11-28 06:10:33,153][87426] Updated weights for policy 1, policy_version 227460 (0.0009) -[2023-11-28 06:10:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 116563968. Throughput: 0: 2747.3, 1: 2678.0. Samples: 116574900. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:10:33,445][86177] Avg episode reward: [(0, '-494.380'), (1, '-515.930')] -[2023-11-28 06:10:33,531][87426] Updated weights for policy 1, policy_version 227470 (0.0007) -[2023-11-28 06:10:33,912][87426] Updated weights for policy 1, policy_version 227480 (0.0007) -[2023-11-28 06:10:35,285][87424] Updated weights for policy 0, policy_version 227877 (0.0011) -[2023-11-28 06:10:35,668][87424] Updated weights for policy 0, policy_version 227887 (0.0009) -[2023-11-28 06:10:36,055][87426] Updated weights for policy 1, policy_version 227490 (0.0009) -[2023-11-28 06:10:36,061][87424] Updated weights for policy 0, policy_version 227897 (0.0009) -[2023-11-28 06:10:36,427][87426] Updated weights for policy 1, policy_version 227500 (0.0012) -[2023-11-28 06:10:36,807][87426] Updated weights for policy 1, policy_version 227510 (0.0012) -[2023-11-28 06:10:37,183][87426] Updated weights for policy 1, policy_version 227520 (0.0012) -[2023-11-28 06:10:37,970][87424] Updated weights for policy 0, policy_version 227907 (0.0010) -[2023-11-28 06:10:38,353][87424] Updated weights for policy 0, policy_version 227917 (0.0011) -[2023-11-28 06:10:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116588544. Throughput: 0: 2777.2, 1: 2676.0. Samples: 116607704. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:10:38,445][86177] Avg episode reward: [(0, '-504.340'), (1, '-527.940')] -[2023-11-28 06:10:38,744][87424] Updated weights for policy 0, policy_version 227927 (0.0012) -[2023-11-28 06:10:39,006][87426] Updated weights for policy 1, policy_version 227530 (0.0011) -[2023-11-28 06:10:39,379][87426] Updated weights for policy 1, policy_version 227540 (0.0009) -[2023-11-28 06:10:39,759][87426] Updated weights for policy 1, policy_version 227550 (0.0008) -[2023-11-28 06:10:40,911][87424] Updated weights for policy 0, policy_version 227937 (0.0011) -[2023-11-28 06:10:41,308][87424] Updated weights for policy 0, policy_version 227947 (0.0008) -[2023-11-28 06:10:41,700][87424] Updated weights for policy 0, policy_version 227957 (0.0011) -[2023-11-28 06:10:42,081][87424] Updated weights for policy 0, policy_version 227967 (0.0010) -[2023-11-28 06:10:42,161][87426] Updated weights for policy 1, policy_version 227560 (0.0011) -[2023-11-28 06:10:42,551][87426] Updated weights for policy 1, policy_version 227570 (0.0009) -[2023-11-28 06:10:42,920][87426] Updated weights for policy 1, policy_version 227580 (0.0012) -[2023-11-28 06:10:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116621312. Throughput: 0: 2786.9, 1: 2693.2. Samples: 116632488. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:10:43,445][86177] Avg episode reward: [(0, '-505.880'), (1, '-533.610')] -[2023-11-28 06:10:44,601][87424] Updated weights for policy 0, policy_version 227977 (0.0010) -[2023-11-28 06:10:44,669][87426] Updated weights for policy 1, policy_version 227590 (0.0008) -[2023-11-28 06:10:45,006][87424] Updated weights for policy 0, policy_version 227987 (0.0011) -[2023-11-28 06:10:45,054][87426] Updated weights for policy 1, policy_version 227600 (0.0008) -[2023-11-28 06:10:45,385][87424] Updated weights for policy 0, policy_version 227997 (0.0011) -[2023-11-28 06:10:45,431][87426] Updated weights for policy 1, policy_version 227610 (0.0009) -[2023-11-28 06:10:47,523][87426] Updated weights for policy 1, policy_version 227620 (0.0009) -[2023-11-28 06:10:47,877][87424] Updated weights for policy 0, policy_version 228007 (0.0011) -[2023-11-28 06:10:47,899][87426] Updated weights for policy 1, policy_version 227630 (0.0010) -[2023-11-28 06:10:48,257][87424] Updated weights for policy 0, policy_version 228017 (0.0011) -[2023-11-28 06:10:48,280][87426] Updated weights for policy 1, policy_version 227640 (0.0011) -[2023-11-28 06:10:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 116637696. Throughput: 0: 2751.6, 1: 2697.9. Samples: 116656180. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:10:48,445][86177] Avg episode reward: [(0, '-507.480'), (1, '-567.420')] -[2023-11-28 06:10:48,639][87424] Updated weights for policy 0, policy_version 228027 (0.0012) -[2023-11-28 06:10:50,403][87426] Updated weights for policy 1, policy_version 227650 (0.0011) -[2023-11-28 06:10:50,781][87426] Updated weights for policy 1, policy_version 227660 (0.0011) -[2023-11-28 06:10:51,147][87424] Updated weights for policy 0, policy_version 228037 (0.0012) -[2023-11-28 06:10:51,163][87426] Updated weights for policy 1, policy_version 227670 (0.0011) -[2023-11-28 06:10:51,519][87424] Updated weights for policy 0, policy_version 228047 (0.0012) -[2023-11-28 06:10:51,539][87426] Updated weights for policy 1, policy_version 227680 (0.0008) -[2023-11-28 06:10:51,900][87424] Updated weights for policy 0, policy_version 228057 (0.0012) -[2023-11-28 06:10:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116670464. Throughput: 0: 2727.6, 1: 2694.3. Samples: 116687800. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:10:53,445][86177] Avg episode reward: [(0, '-506.340'), (1, '-575.460')] -[2023-11-28 06:10:54,023][87426] Updated weights for policy 1, policy_version 227690 (0.0012) -[2023-11-28 06:10:54,036][87424] Updated weights for policy 0, policy_version 228067 (0.0011) -[2023-11-28 06:10:54,409][87426] Updated weights for policy 1, policy_version 227700 (0.0012) -[2023-11-28 06:10:54,416][87424] Updated weights for policy 0, policy_version 228077 (0.0007) -[2023-11-28 06:10:54,785][87426] Updated weights for policy 1, policy_version 227710 (0.0010) -[2023-11-28 06:10:54,796][87424] Updated weights for policy 0, policy_version 228087 (0.0008) -[2023-11-28 06:10:57,062][87424] Updated weights for policy 0, policy_version 228097 (0.0010) -[2023-11-28 06:10:57,286][87426] Updated weights for policy 1, policy_version 227720 (0.0008) -[2023-11-28 06:10:57,443][87424] Updated weights for policy 0, policy_version 228107 (0.0011) -[2023-11-28 06:10:57,667][87426] Updated weights for policy 1, policy_version 227730 (0.0008) -[2023-11-28 06:10:57,833][87424] Updated weights for policy 0, policy_version 228117 (0.0008) -[2023-11-28 06:10:58,050][87426] Updated weights for policy 1, policy_version 227740 (0.0011) -[2023-11-28 06:10:58,215][87424] Updated weights for policy 0, policy_version 228127 (0.0007) -[2023-11-28 06:10:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116703232. Throughput: 0: 2737.9, 1: 2683.4. Samples: 116711272. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:10:58,447][86177] Avg episode reward: [(0, '-496.720'), (1, '-568.090')] -[2023-11-28 06:11:00,066][87424] Updated weights for policy 0, policy_version 228137 (0.0009) -[2023-11-28 06:11:00,351][87426] Updated weights for policy 1, policy_version 227750 (0.0009) -[2023-11-28 06:11:00,456][87424] Updated weights for policy 0, policy_version 228147 (0.0009) -[2023-11-28 06:11:00,728][87426] Updated weights for policy 1, policy_version 227760 (0.0011) -[2023-11-28 06:11:00,833][87424] Updated weights for policy 0, policy_version 228157 (0.0011) -[2023-11-28 06:11:01,111][87426] Updated weights for policy 1, policy_version 227770 (0.0011) -[2023-11-28 06:11:03,127][87424] Updated weights for policy 0, policy_version 228167 (0.0011) -[2023-11-28 06:11:03,211][87426] Updated weights for policy 1, policy_version 227780 (0.0012) -[2023-11-28 06:11:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 116719616. Throughput: 0: 2748.4, 1: 2689.1. Samples: 116736192. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:11:03,445][86177] Avg episode reward: [(0, '-503.280'), (1, '-564.820')] -[2023-11-28 06:11:03,506][87424] Updated weights for policy 0, policy_version 228177 (0.0011) -[2023-11-28 06:11:03,590][87426] Updated weights for policy 1, policy_version 227790 (0.0009) -[2023-11-28 06:11:03,880][87424] Updated weights for policy 0, policy_version 228187 (0.0011) -[2023-11-28 06:11:03,967][87426] Updated weights for policy 1, policy_version 227800 (0.0009) -[2023-11-28 06:11:05,908][87424] Updated weights for policy 0, policy_version 228197 (0.0011) -[2023-11-28 06:11:06,026][87426] Updated weights for policy 1, policy_version 227810 (0.0010) -[2023-11-28 06:11:06,290][87424] Updated weights for policy 0, policy_version 228207 (0.0008) -[2023-11-28 06:11:06,401][87426] Updated weights for policy 1, policy_version 227820 (0.0009) -[2023-11-28 06:11:06,671][87424] Updated weights for policy 0, policy_version 228217 (0.0010) -[2023-11-28 06:11:06,790][87426] Updated weights for policy 1, policy_version 227830 (0.0008) -[2023-11-28 06:11:07,168][87426] Updated weights for policy 1, policy_version 227840 (0.0011) -[2023-11-28 06:11:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116752384. Throughput: 0: 2754.7, 1: 2729.7. Samples: 116770096. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:11:08,445][86177] Avg episode reward: [(0, '-500.390'), (1, '-538.190')] -[2023-11-28 06:11:08,515][87424] Updated weights for policy 0, policy_version 228227 (0.0010) -[2023-11-28 06:11:08,898][87424] Updated weights for policy 0, policy_version 228237 (0.0008) -[2023-11-28 06:11:09,225][87426] Updated weights for policy 1, policy_version 227850 (0.0013) -[2023-11-28 06:11:09,278][87424] Updated weights for policy 0, policy_version 228247 (0.0010) -[2023-11-28 06:11:09,604][87426] Updated weights for policy 1, policy_version 227860 (0.0011) -[2023-11-28 06:11:09,980][87426] Updated weights for policy 1, policy_version 227870 (0.0012) -[2023-11-28 06:11:11,351][87424] Updated weights for policy 0, policy_version 228257 (0.0010) -[2023-11-28 06:11:11,733][87424] Updated weights for policy 0, policy_version 228267 (0.0009) -[2023-11-28 06:11:12,113][87424] Updated weights for policy 0, policy_version 228277 (0.0012) -[2023-11-28 06:11:12,276][87426] Updated weights for policy 1, policy_version 227880 (0.0012) -[2023-11-28 06:11:12,494][87424] Updated weights for policy 0, policy_version 228287 (0.0011) -[2023-11-28 06:11:12,650][87426] Updated weights for policy 1, policy_version 227890 (0.0010) -[2023-11-28 06:11:13,039][87426] Updated weights for policy 1, policy_version 227900 (0.0012) -[2023-11-28 06:11:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 116785152. Throughput: 0: 2755.7, 1: 2714.9. Samples: 116794956. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:11:13,445][86177] Avg episode reward: [(0, '-507.890'), (1, '-539.540')] -[2023-11-28 06:11:14,947][87424] Updated weights for policy 0, policy_version 228297 (0.0008) -[2023-11-28 06:11:15,012][87426] Updated weights for policy 1, policy_version 227910 (0.0010) -[2023-11-28 06:11:15,339][87424] Updated weights for policy 0, policy_version 228307 (0.0007) -[2023-11-28 06:11:15,386][87426] Updated weights for policy 1, policy_version 227920 (0.0009) -[2023-11-28 06:11:15,713][87424] Updated weights for policy 0, policy_version 228317 (0.0010) -[2023-11-28 06:11:15,767][87426] Updated weights for policy 1, policy_version 227930 (0.0010) -[2023-11-28 06:11:17,892][87426] Updated weights for policy 1, policy_version 227940 (0.0008) -[2023-11-28 06:11:17,998][87424] Updated weights for policy 0, policy_version 228327 (0.0010) -[2023-11-28 06:11:18,266][87426] Updated weights for policy 1, policy_version 227950 (0.0008) -[2023-11-28 06:11:18,387][87424] Updated weights for policy 0, policy_version 228337 (0.0010) -[2023-11-28 06:11:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 116801536. Throughput: 0: 2720.9, 1: 2731.5. Samples: 116820256. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:11:18,445][86177] Avg episode reward: [(0, '-502.000'), (1, '-543.720')] -[2023-11-28 06:11:18,651][87426] Updated weights for policy 1, policy_version 227960 (0.0007) -[2023-11-28 06:11:18,757][87424] Updated weights for policy 0, policy_version 228347 (0.0011) -[2023-11-28 06:11:20,396][87426] Updated weights for policy 1, policy_version 227970 (0.0010) -[2023-11-28 06:11:20,777][87426] Updated weights for policy 1, policy_version 227980 (0.0012) -[2023-11-28 06:11:21,143][87424] Updated weights for policy 0, policy_version 228357 (0.0010) -[2023-11-28 06:11:21,144][87426] Updated weights for policy 1, policy_version 227990 (0.0011) -[2023-11-28 06:11:21,521][87424] Updated weights for policy 0, policy_version 228367 (0.0010) -[2023-11-28 06:11:21,524][87426] Updated weights for policy 1, policy_version 228000 (0.0011) -[2023-11-28 06:11:21,916][87424] Updated weights for policy 0, policy_version 228377 (0.0012) -[2023-11-28 06:11:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116834304. Throughput: 0: 2691.6, 1: 2753.9. Samples: 116852752. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:11:23,445][86177] Avg episode reward: [(0, '-500.120'), (1, '-555.770')] -[2023-11-28 06:11:23,645][87426] Updated weights for policy 1, policy_version 228010 (0.0012) -[2023-11-28 06:11:24,023][87426] Updated weights for policy 1, policy_version 228020 (0.0012) -[2023-11-28 06:11:24,191][87424] Updated weights for policy 0, policy_version 228387 (0.0010) -[2023-11-28 06:11:24,395][87426] Updated weights for policy 1, policy_version 228030 (0.0012) -[2023-11-28 06:11:24,579][87424] Updated weights for policy 0, policy_version 228397 (0.0007) -[2023-11-28 06:11:24,960][87424] Updated weights for policy 0, policy_version 228407 (0.0007) -[2023-11-28 06:11:26,738][87426] Updated weights for policy 1, policy_version 228040 (0.0012) -[2023-11-28 06:11:27,133][87426] Updated weights for policy 1, policy_version 228050 (0.0012) -[2023-11-28 06:11:27,293][87424] Updated weights for policy 0, policy_version 228417 (0.0008) -[2023-11-28 06:11:27,517][87426] Updated weights for policy 1, policy_version 228060 (0.0012) -[2023-11-28 06:11:27,681][87424] Updated weights for policy 0, policy_version 228427 (0.0008) -[2023-11-28 06:11:28,055][87424] Updated weights for policy 0, policy_version 228437 (0.0009) -[2023-11-28 06:11:28,438][87424] Updated weights for policy 0, policy_version 228447 (0.0007) -[2023-11-28 06:11:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 116858880. Throughput: 0: 2682.8, 1: 2760.7. Samples: 116877448. Policy #0 lag: (min: 31.0, avg: 46.6, max: 63.0) -[2023-11-28 06:11:28,445][86177] Avg episode reward: [(0, '-502.030'), (1, '-555.520')] -[2023-11-28 06:11:29,472][87426] Updated weights for policy 1, policy_version 228070 (0.0009) -[2023-11-28 06:11:29,860][87426] Updated weights for policy 1, policy_version 228080 (0.0011) -[2023-11-28 06:11:30,230][87426] Updated weights for policy 1, policy_version 228090 (0.0011) -[2023-11-28 06:11:30,701][87424] Updated weights for policy 0, policy_version 228457 (0.0008) -[2023-11-28 06:11:31,075][87424] Updated weights for policy 0, policy_version 228467 (0.0008) -[2023-11-28 06:11:31,461][87424] Updated weights for policy 0, policy_version 228477 (0.0007) -[2023-11-28 06:11:32,448][87426] Updated weights for policy 1, policy_version 228100 (0.0010) -[2023-11-28 06:11:32,826][87426] Updated weights for policy 1, policy_version 228110 (0.0008) -[2023-11-28 06:11:33,203][87426] Updated weights for policy 1, policy_version 228120 (0.0008) -[2023-11-28 06:11:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 116883456. Throughput: 0: 2703.7, 1: 2760.0. Samples: 116902048. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:11:33,445][86177] Avg episode reward: [(0, '-495.480'), (1, '-542.820')] -[2023-11-28 06:11:33,757][87424] Updated weights for policy 0, policy_version 228487 (0.0007) -[2023-11-28 06:11:34,137][87424] Updated weights for policy 0, policy_version 228497 (0.0007) -[2023-11-28 06:11:34,522][87424] Updated weights for policy 0, policy_version 228507 (0.0007) -[2023-11-28 06:11:35,658][87426] Updated weights for policy 1, policy_version 228130 (0.0009) -[2023-11-28 06:11:36,041][87426] Updated weights for policy 1, policy_version 228140 (0.0007) -[2023-11-28 06:11:36,420][87426] Updated weights for policy 1, policy_version 228150 (0.0007) -[2023-11-28 06:11:36,737][87424] Updated weights for policy 0, policy_version 228517 (0.0010) -[2023-11-28 06:11:36,802][87426] Updated weights for policy 1, policy_version 228160 (0.0008) -[2023-11-28 06:11:37,124][87424] Updated weights for policy 0, policy_version 228527 (0.0011) -[2023-11-28 06:11:37,508][87424] Updated weights for policy 0, policy_version 228537 (0.0008) -[2023-11-28 06:11:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 116916224. Throughput: 0: 2699.2, 1: 2762.1. Samples: 116933560. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:11:38,445][86177] Avg episode reward: [(0, '-494.270'), (1, '-529.130')] -[2023-11-28 06:11:39,087][87426] Updated weights for policy 1, policy_version 228170 (0.0011) -[2023-11-28 06:11:39,466][87426] Updated weights for policy 1, policy_version 228180 (0.0011) -[2023-11-28 06:11:39,849][87426] Updated weights for policy 1, policy_version 228190 (0.0011) -[2023-11-28 06:11:40,044][87424] Updated weights for policy 0, policy_version 228547 (0.0008) -[2023-11-28 06:11:40,433][87424] Updated weights for policy 0, policy_version 228557 (0.0010) -[2023-11-28 06:11:40,820][87424] Updated weights for policy 0, policy_version 228567 (0.0012) -[2023-11-28 06:11:41,840][87426] Updated weights for policy 1, policy_version 228200 (0.0010) -[2023-11-28 06:11:42,217][87426] Updated weights for policy 1, policy_version 228210 (0.0012) -[2023-11-28 06:11:42,593][87426] Updated weights for policy 1, policy_version 228220 (0.0010) -[2023-11-28 06:11:43,265][87424] Updated weights for policy 0, policy_version 228577 (0.0011) -[2023-11-28 06:11:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 116940800. Throughput: 0: 2681.9, 1: 2780.7. Samples: 116957088. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:11:43,445][86177] Avg episode reward: [(0, '-494.360'), (1, '-515.760')] -[2023-11-28 06:11:43,653][87424] Updated weights for policy 0, policy_version 228587 (0.0007) -[2023-11-28 06:11:44,029][87424] Updated weights for policy 0, policy_version 228597 (0.0007) -[2023-11-28 06:11:44,371][87426] Updated weights for policy 1, policy_version 228230 (0.0010) -[2023-11-28 06:11:44,417][87424] Updated weights for policy 0, policy_version 228607 (0.0008) -[2023-11-28 06:11:44,747][87426] Updated weights for policy 1, policy_version 228240 (0.0012) -[2023-11-28 06:11:45,121][87426] Updated weights for policy 1, policy_version 228250 (0.0012) -[2023-11-28 06:11:46,257][87424] Updated weights for policy 0, policy_version 228617 (0.0011) -[2023-11-28 06:11:46,638][87424] Updated weights for policy 0, policy_version 228627 (0.0012) -[2023-11-28 06:11:47,021][87424] Updated weights for policy 0, policy_version 228637 (0.0012) -[2023-11-28 06:11:47,686][87426] Updated weights for policy 1, policy_version 228260 (0.0012) -[2023-11-28 06:11:48,060][87426] Updated weights for policy 1, policy_version 228270 (0.0007) -[2023-11-28 06:11:48,440][87426] Updated weights for policy 1, policy_version 228280 (0.0011) -[2023-11-28 06:11:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 116965376. Throughput: 0: 2659.2, 1: 2773.8. Samples: 116980676. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:11:48,445][86177] Avg episode reward: [(0, '-496.370'), (1, '-523.200')] -[2023-11-28 06:11:49,276][87424] Updated weights for policy 0, policy_version 228647 (0.0011) -[2023-11-28 06:11:49,656][87424] Updated weights for policy 0, policy_version 228657 (0.0011) -[2023-11-28 06:11:50,037][87424] Updated weights for policy 0, policy_version 228667 (0.0012) -[2023-11-28 06:11:50,785][87426] Updated weights for policy 1, policy_version 228290 (0.0009) -[2023-11-28 06:11:51,174][87426] Updated weights for policy 1, policy_version 228300 (0.0012) -[2023-11-28 06:11:51,559][87426] Updated weights for policy 1, policy_version 228310 (0.0012) -[2023-11-28 06:11:51,932][87426] Updated weights for policy 1, policy_version 228320 (0.0012) -[2023-11-28 06:11:52,557][87424] Updated weights for policy 0, policy_version 228677 (0.0012) -[2023-11-28 06:11:52,937][87424] Updated weights for policy 0, policy_version 228687 (0.0012) -[2023-11-28 06:11:53,330][87424] Updated weights for policy 0, policy_version 228697 (0.0009) -[2023-11-28 06:11:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 116989952. Throughput: 0: 2634.8, 1: 2750.5. Samples: 117012432. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:11:53,446][86177] Avg episode reward: [(0, '-495.320'), (1, '-523.170')] -[2023-11-28 06:11:53,780][87426] Updated weights for policy 1, policy_version 228330 (0.0011) -[2023-11-28 06:11:54,164][87426] Updated weights for policy 1, policy_version 228340 (0.0012) -[2023-11-28 06:11:54,534][87426] Updated weights for policy 1, policy_version 228350 (0.0012) -[2023-11-28 06:11:55,811][87424] Updated weights for policy 0, policy_version 228707 (0.0010) -[2023-11-28 06:11:56,196][87424] Updated weights for policy 0, policy_version 228717 (0.0008) -[2023-11-28 06:11:56,364][87426] Updated weights for policy 1, policy_version 228360 (0.0010) -[2023-11-28 06:11:56,581][87424] Updated weights for policy 0, policy_version 228727 (0.0009) -[2023-11-28 06:11:56,751][87426] Updated weights for policy 1, policy_version 228370 (0.0008) -[2023-11-28 06:11:57,123][87426] Updated weights for policy 1, policy_version 228380 (0.0011) -[2023-11-28 06:11:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 117022720. Throughput: 0: 2614.1, 1: 2768.0. Samples: 117037152. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:11:58,445][86177] Avg episode reward: [(0, '-500.510'), (1, '-520.390')] -[2023-11-28 06:11:58,538][87424] Updated weights for policy 0, policy_version 228737 (0.0012) -[2023-11-28 06:11:58,935][87424] Updated weights for policy 0, policy_version 228747 (0.0010) -[2023-11-28 06:11:59,309][87424] Updated weights for policy 0, policy_version 228757 (0.0009) -[2023-11-28 06:11:59,310][87426] Updated weights for policy 1, policy_version 228390 (0.0010) -[2023-11-28 06:11:59,696][87426] Updated weights for policy 1, policy_version 228400 (0.0008) -[2023-11-28 06:11:59,703][87424] Updated weights for policy 0, policy_version 228767 (0.0009) -[2023-11-28 06:12:00,085][87426] Updated weights for policy 1, policy_version 228410 (0.0009) -[2023-11-28 06:12:02,121][87424] Updated weights for policy 0, policy_version 228777 (0.0009) -[2023-11-28 06:12:02,506][87424] Updated weights for policy 0, policy_version 228787 (0.0008) -[2023-11-28 06:12:02,528][87426] Updated weights for policy 1, policy_version 228420 (0.0009) -[2023-11-28 06:12:02,885][87424] Updated weights for policy 0, policy_version 228797 (0.0008) -[2023-11-28 06:12:02,906][87426] Updated weights for policy 1, policy_version 228430 (0.0011) -[2023-11-28 06:12:03,299][87426] Updated weights for policy 1, policy_version 228440 (0.0008) -[2023-11-28 06:12:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 117047296. Throughput: 0: 2628.2, 1: 2750.9. Samples: 117062316. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:12:03,445][86177] Avg episode reward: [(0, '-500.440'), (1, '-522.490')] -[2023-11-28 06:12:04,753][87424] Updated weights for policy 0, policy_version 228807 (0.0011) -[2023-11-28 06:12:05,128][87424] Updated weights for policy 0, policy_version 228817 (0.0012) -[2023-11-28 06:12:05,512][87424] Updated weights for policy 0, policy_version 228827 (0.0012) -[2023-11-28 06:12:05,571][87426] Updated weights for policy 1, policy_version 228450 (0.0008) -[2023-11-28 06:12:05,945][87426] Updated weights for policy 1, policy_version 228460 (0.0011) -[2023-11-28 06:12:06,325][87426] Updated weights for policy 1, policy_version 228470 (0.0009) -[2023-11-28 06:12:06,703][87426] Updated weights for policy 1, policy_version 228480 (0.0011) -[2023-11-28 06:12:07,652][87424] Updated weights for policy 0, policy_version 228837 (0.0010) -[2023-11-28 06:12:08,038][87424] Updated weights for policy 0, policy_version 228847 (0.0007) -[2023-11-28 06:12:08,428][87424] Updated weights for policy 0, policy_version 228857 (0.0008) -[2023-11-28 06:12:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 117071872. Throughput: 0: 2642.2, 1: 2732.8. Samples: 117094628. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:12:08,445][86177] Avg episode reward: [(0, '-539.980'), (1, '-513.960')] -[2023-11-28 06:12:08,495][87426] Updated weights for policy 1, policy_version 228490 (0.0012) -[2023-11-28 06:12:08,872][87426] Updated weights for policy 1, policy_version 228500 (0.0012) -[2023-11-28 06:12:09,260][87426] Updated weights for policy 1, policy_version 228510 (0.0011) -[2023-11-28 06:12:10,109][87424] Updated weights for policy 0, policy_version 228867 (0.0011) -[2023-11-28 06:12:10,498][87424] Updated weights for policy 0, policy_version 228877 (0.0011) -[2023-11-28 06:12:10,871][87424] Updated weights for policy 0, policy_version 228887 (0.0012) -[2023-11-28 06:12:11,275][87426] Updated weights for policy 1, policy_version 228520 (0.0012) -[2023-11-28 06:12:11,672][87426] Updated weights for policy 1, policy_version 228530 (0.0012) -[2023-11-28 06:12:12,047][87426] Updated weights for policy 1, policy_version 228540 (0.0012) -[2023-11-28 06:12:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 117104640. Throughput: 0: 2637.8, 1: 2728.4. Samples: 117118924. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:12:13,445][86177] Avg episode reward: [(0, '-540.780'), (1, '-520.030')] -[2023-11-28 06:12:13,483][87424] Updated weights for policy 0, policy_version 228897 (0.0011) -[2023-11-28 06:12:13,867][87424] Updated weights for policy 0, policy_version 228907 (0.0008) -[2023-11-28 06:12:14,262][87424] Updated weights for policy 0, policy_version 228917 (0.0008) -[2023-11-28 06:12:14,304][87426] Updated weights for policy 1, policy_version 228550 (0.0012) -[2023-11-28 06:12:14,640][87424] Updated weights for policy 0, policy_version 228927 (0.0011) -[2023-11-28 06:12:14,684][87426] Updated weights for policy 1, policy_version 228560 (0.0009) -[2023-11-28 06:12:15,068][87426] Updated weights for policy 1, policy_version 228570 (0.0008) -[2023-11-28 06:12:16,462][87424] Updated weights for policy 0, policy_version 228937 (0.0012) -[2023-11-28 06:12:16,842][87424] Updated weights for policy 0, policy_version 228947 (0.0012) -[2023-11-28 06:12:17,236][87424] Updated weights for policy 0, policy_version 228957 (0.0012) -[2023-11-28 06:12:17,451][87426] Updated weights for policy 1, policy_version 228580 (0.0008) -[2023-11-28 06:12:17,836][87426] Updated weights for policy 1, policy_version 228590 (0.0007) -[2023-11-28 06:12:18,222][87426] Updated weights for policy 1, policy_version 228600 (0.0007) -[2023-11-28 06:12:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 117129216. Throughput: 0: 2664.2, 1: 2711.3. Samples: 117143944. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:12:18,445][86177] Avg episode reward: [(0, '-542.680'), (1, '-520.790')] -[2023-11-28 06:12:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000228960_58613760.pth... -[2023-11-28 06:12:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000226432_57966592.pth -[2023-11-28 06:12:18,511][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000228960_58613760.pth -[2023-11-28 06:12:18,531][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000228608_58523648.pth... -[2023-11-28 06:12:18,579][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000226048_57868288.pth -[2023-11-28 06:12:18,586][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000228608_58523648.pth -[2023-11-28 06:12:19,368][87424] Updated weights for policy 0, policy_version 228967 (0.0012) -[2023-11-28 06:12:19,750][87424] Updated weights for policy 0, policy_version 228977 (0.0012) -[2023-11-28 06:12:20,129][87424] Updated weights for policy 0, policy_version 228987 (0.0009) -[2023-11-28 06:12:20,634][87426] Updated weights for policy 1, policy_version 228610 (0.0008) -[2023-11-28 06:12:21,015][87426] Updated weights for policy 1, policy_version 228620 (0.0010) -[2023-11-28 06:12:21,399][87426] Updated weights for policy 1, policy_version 228630 (0.0008) -[2023-11-28 06:12:21,775][87426] Updated weights for policy 1, policy_version 228640 (0.0008) -[2023-11-28 06:12:22,330][87424] Updated weights for policy 0, policy_version 228997 (0.0008) -[2023-11-28 06:12:22,708][87424] Updated weights for policy 0, policy_version 229007 (0.0008) -[2023-11-28 06:12:23,097][87424] Updated weights for policy 0, policy_version 229017 (0.0010) -[2023-11-28 06:12:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 117161984. Throughput: 0: 2686.4, 1: 2704.1. Samples: 117176132. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:12:23,445][86177] Avg episode reward: [(0, '-542.690'), (1, '-519.060')] -[2023-11-28 06:12:24,138][87426] Updated weights for policy 1, policy_version 228650 (0.0008) -[2023-11-28 06:12:24,524][87426] Updated weights for policy 1, policy_version 228660 (0.0007) -[2023-11-28 06:12:24,898][87426] Updated weights for policy 1, policy_version 228670 (0.0007) -[2023-11-28 06:12:25,371][87424] Updated weights for policy 0, policy_version 229027 (0.0009) -[2023-11-28 06:12:25,755][87424] Updated weights for policy 0, policy_version 229037 (0.0007) -[2023-11-28 06:12:26,152][87424] Updated weights for policy 0, policy_version 229047 (0.0007) -[2023-11-28 06:12:26,976][87426] Updated weights for policy 1, policy_version 228680 (0.0008) -[2023-11-28 06:12:27,354][87426] Updated weights for policy 1, policy_version 228690 (0.0007) -[2023-11-28 06:12:27,732][87426] Updated weights for policy 1, policy_version 228700 (0.0007) -[2023-11-28 06:12:28,333][87424] Updated weights for policy 0, policy_version 229057 (0.0007) -[2023-11-28 06:12:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 117186560. Throughput: 0: 2700.3, 1: 2712.0. Samples: 117200640. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:12:28,445][86177] Avg episode reward: [(0, '-502.580'), (1, '-514.390')] -[2023-11-28 06:12:28,714][87424] Updated weights for policy 0, policy_version 229067 (0.0007) -[2023-11-28 06:12:29,096][87424] Updated weights for policy 0, policy_version 229077 (0.0008) -[2023-11-28 06:12:29,478][87424] Updated weights for policy 0, policy_version 229087 (0.0007) -[2023-11-28 06:12:30,017][87426] Updated weights for policy 1, policy_version 228710 (0.0009) -[2023-11-28 06:12:30,395][87426] Updated weights for policy 1, policy_version 228720 (0.0008) -[2023-11-28 06:12:30,775][87426] Updated weights for policy 1, policy_version 228730 (0.0010) -[2023-11-28 06:12:31,951][87424] Updated weights for policy 0, policy_version 229097 (0.0009) -[2023-11-28 06:12:32,330][87424] Updated weights for policy 0, policy_version 229107 (0.0011) -[2023-11-28 06:12:32,545][87426] Updated weights for policy 1, policy_version 228740 (0.0011) -[2023-11-28 06:12:32,708][87424] Updated weights for policy 0, policy_version 229117 (0.0011) -[2023-11-28 06:12:32,918][87426] Updated weights for policy 1, policy_version 228750 (0.0011) -[2023-11-28 06:12:33,297][87426] Updated weights for policy 1, policy_version 228760 (0.0011) -[2023-11-28 06:12:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 117211136. Throughput: 0: 2693.7, 1: 2711.9. Samples: 117223928. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:12:33,445][86177] Avg episode reward: [(0, '-504.410'), (1, '-509.640')] -[2023-11-28 06:12:34,482][87424] Updated weights for policy 0, policy_version 229127 (0.0011) -[2023-11-28 06:12:34,860][87424] Updated weights for policy 0, policy_version 229137 (0.0008) -[2023-11-28 06:12:35,241][87424] Updated weights for policy 0, policy_version 229147 (0.0008) -[2023-11-28 06:12:35,647][87426] Updated weights for policy 1, policy_version 228770 (0.0012) -[2023-11-28 06:12:36,034][87426] Updated weights for policy 1, policy_version 228780 (0.0011) -[2023-11-28 06:12:36,418][87426] Updated weights for policy 1, policy_version 228790 (0.0009) -[2023-11-28 06:12:36,805][87426] Updated weights for policy 1, policy_version 228800 (0.0008) -[2023-11-28 06:12:37,569][87424] Updated weights for policy 0, policy_version 229157 (0.0010) -[2023-11-28 06:12:37,949][87424] Updated weights for policy 0, policy_version 229167 (0.0012) -[2023-11-28 06:12:38,326][87424] Updated weights for policy 0, policy_version 229177 (0.0012) -[2023-11-28 06:12:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 117235712. Throughput: 0: 2708.9, 1: 2726.5. Samples: 117257024. Policy #0 lag: (min: 31.0, avg: 42.7, max: 63.0) -[2023-11-28 06:12:38,445][86177] Avg episode reward: [(0, '-499.630'), (1, '-511.680')] -[2023-11-28 06:12:38,534][87426] Updated weights for policy 1, policy_version 228810 (0.0008) -[2023-11-28 06:12:38,921][87426] Updated weights for policy 1, policy_version 228820 (0.0012) -[2023-11-28 06:12:39,300][87426] Updated weights for policy 1, policy_version 228830 (0.0012) -[2023-11-28 06:12:40,493][87424] Updated weights for policy 0, policy_version 229187 (0.0010) -[2023-11-28 06:12:40,877][87424] Updated weights for policy 0, policy_version 229197 (0.0010) -[2023-11-28 06:12:41,254][87424] Updated weights for policy 0, policy_version 229207 (0.0012) -[2023-11-28 06:12:41,753][87426] Updated weights for policy 1, policy_version 228840 (0.0011) -[2023-11-28 06:12:42,133][87426] Updated weights for policy 1, policy_version 228850 (0.0011) -[2023-11-28 06:12:42,513][87426] Updated weights for policy 1, policy_version 228860 (0.0011) -[2023-11-28 06:12:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 117268480. Throughput: 0: 2729.5, 1: 2697.5. Samples: 117281368. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:12:43,445][86177] Avg episode reward: [(0, '-497.700'), (1, '-509.410')] -[2023-11-28 06:12:43,471][87424] Updated weights for policy 0, policy_version 229217 (0.0008) -[2023-11-28 06:12:43,872][87424] Updated weights for policy 0, policy_version 229227 (0.0011) -[2023-11-28 06:12:44,250][87424] Updated weights for policy 0, policy_version 229237 (0.0011) -[2023-11-28 06:12:44,636][87424] Updated weights for policy 0, policy_version 229247 (0.0012) -[2023-11-28 06:12:44,809][87426] Updated weights for policy 1, policy_version 228870 (0.0012) -[2023-11-28 06:12:45,194][87426] Updated weights for policy 1, policy_version 228880 (0.0012) -[2023-11-28 06:12:45,568][87426] Updated weights for policy 1, policy_version 228890 (0.0012) -[2023-11-28 06:12:46,742][87424] Updated weights for policy 0, policy_version 229257 (0.0012) -[2023-11-28 06:12:47,113][87424] Updated weights for policy 0, policy_version 229267 (0.0012) -[2023-11-28 06:12:47,218][87426] Updated weights for policy 1, policy_version 228900 (0.0012) -[2023-11-28 06:12:47,498][87424] Updated weights for policy 0, policy_version 229277 (0.0012) -[2023-11-28 06:12:47,595][87426] Updated weights for policy 1, policy_version 228910 (0.0011) -[2023-11-28 06:12:47,974][87426] Updated weights for policy 1, policy_version 228920 (0.0012) -[2023-11-28 06:12:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 117301248. Throughput: 0: 2718.9, 1: 2710.0. Samples: 117306616. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:12:48,445][86177] Avg episode reward: [(0, '-533.310'), (1, '-519.250')] -[2023-11-28 06:12:49,288][87424] Updated weights for policy 0, policy_version 229287 (0.0009) -[2023-11-28 06:12:49,675][87424] Updated weights for policy 0, policy_version 229297 (0.0008) -[2023-11-28 06:12:49,938][87426] Updated weights for policy 1, policy_version 228930 (0.0012) -[2023-11-28 06:12:50,055][87424] Updated weights for policy 0, policy_version 229307 (0.0010) -[2023-11-28 06:12:50,312][87426] Updated weights for policy 1, policy_version 228940 (0.0011) -[2023-11-28 06:12:50,699][87426] Updated weights for policy 1, policy_version 228950 (0.0012) -[2023-11-28 06:12:51,072][87426] Updated weights for policy 1, policy_version 228960 (0.0012) -[2023-11-28 06:12:52,037][87424] Updated weights for policy 0, policy_version 229317 (0.0010) -[2023-11-28 06:12:52,421][87424] Updated weights for policy 0, policy_version 229327 (0.0009) -[2023-11-28 06:12:52,805][87424] Updated weights for policy 0, policy_version 229337 (0.0008) -[2023-11-28 06:12:53,344][87426] Updated weights for policy 1, policy_version 228970 (0.0012) -[2023-11-28 06:12:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 117325824. Throughput: 0: 2722.1, 1: 2725.2. Samples: 117339756. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:12:53,445][86177] Avg episode reward: [(0, '-575.760'), (1, '-533.470')] -[2023-11-28 06:12:53,720][87426] Updated weights for policy 1, policy_version 228980 (0.0012) -[2023-11-28 06:12:54,093][87426] Updated weights for policy 1, policy_version 228990 (0.0012) -[2023-11-28 06:12:55,078][87424] Updated weights for policy 0, policy_version 229347 (0.0010) -[2023-11-28 06:12:55,461][87424] Updated weights for policy 0, policy_version 229357 (0.0009) -[2023-11-28 06:12:55,844][87424] Updated weights for policy 0, policy_version 229367 (0.0007) -[2023-11-28 06:12:56,650][87426] Updated weights for policy 1, policy_version 229000 (0.0012) -[2023-11-28 06:12:57,029][87426] Updated weights for policy 1, policy_version 229010 (0.0011) -[2023-11-28 06:12:57,406][87426] Updated weights for policy 1, policy_version 229020 (0.0008) -[2023-11-28 06:12:58,365][87424] Updated weights for policy 0, policy_version 229377 (0.0007) -[2023-11-28 06:12:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 117350400. Throughput: 0: 2734.3, 1: 2726.8. Samples: 117364672. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:12:58,445][86177] Avg episode reward: [(0, '-602.580'), (1, '-544.360')] -[2023-11-28 06:12:58,740][87424] Updated weights for policy 0, policy_version 229387 (0.0008) -[2023-11-28 06:12:59,123][87424] Updated weights for policy 0, policy_version 229397 (0.0009) -[2023-11-28 06:12:59,509][87424] Updated weights for policy 0, policy_version 229407 (0.0010) -[2023-11-28 06:12:59,518][87426] Updated weights for policy 1, policy_version 229030 (0.0009) -[2023-11-28 06:12:59,893][87426] Updated weights for policy 1, policy_version 229040 (0.0010) -[2023-11-28 06:13:00,277][87426] Updated weights for policy 1, policy_version 229050 (0.0012) -[2023-11-28 06:13:01,920][87426] Updated weights for policy 1, policy_version 229060 (0.0011) -[2023-11-28 06:13:02,077][87424] Updated weights for policy 0, policy_version 229417 (0.0010) -[2023-11-28 06:13:02,300][87426] Updated weights for policy 1, policy_version 229070 (0.0008) -[2023-11-28 06:13:02,460][87424] Updated weights for policy 0, policy_version 229427 (0.0010) -[2023-11-28 06:13:02,692][87426] Updated weights for policy 1, policy_version 229080 (0.0011) -[2023-11-28 06:13:02,849][87424] Updated weights for policy 0, policy_version 229437 (0.0011) -[2023-11-28 06:13:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 117383168. Throughput: 0: 2713.4, 1: 2736.1. Samples: 117389172. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:03,445][86177] Avg episode reward: [(0, '-642.750'), (1, '-542.020')] -[2023-11-28 06:13:04,834][87426] Updated weights for policy 1, policy_version 229090 (0.0012) -[2023-11-28 06:13:05,204][87426] Updated weights for policy 1, policy_version 229100 (0.0011) -[2023-11-28 06:13:05,425][87424] Updated weights for policy 0, policy_version 229447 (0.0012) -[2023-11-28 06:13:05,583][87426] Updated weights for policy 1, policy_version 229110 (0.0012) -[2023-11-28 06:13:05,838][87424] Updated weights for policy 0, policy_version 229457 (0.0012) -[2023-11-28 06:13:05,959][87426] Updated weights for policy 1, policy_version 229120 (0.0011) -[2023-11-28 06:13:06,218][87424] Updated weights for policy 0, policy_version 229467 (0.0012) -[2023-11-28 06:13:08,104][87426] Updated weights for policy 1, policy_version 229130 (0.0012) -[2023-11-28 06:13:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 117399552. Throughput: 0: 2701.3, 1: 2761.2. Samples: 117421948. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:08,445][86177] Avg episode reward: [(0, '-608.440'), (1, '-566.120')] -[2023-11-28 06:13:08,484][87426] Updated weights for policy 1, policy_version 229140 (0.0012) -[2023-11-28 06:13:08,513][87424] Updated weights for policy 0, policy_version 229477 (0.0011) -[2023-11-28 06:13:08,864][87426] Updated weights for policy 1, policy_version 229150 (0.0011) -[2023-11-28 06:13:08,895][87424] Updated weights for policy 0, policy_version 229487 (0.0011) -[2023-11-28 06:13:09,280][87424] Updated weights for policy 0, policy_version 229497 (0.0012) -[2023-11-28 06:13:11,379][87426] Updated weights for policy 1, policy_version 229160 (0.0011) -[2023-11-28 06:13:11,428][87424] Updated weights for policy 0, policy_version 229507 (0.0011) -[2023-11-28 06:13:11,772][87426] Updated weights for policy 1, policy_version 229170 (0.0011) -[2023-11-28 06:13:11,809][87424] Updated weights for policy 0, policy_version 229517 (0.0011) -[2023-11-28 06:13:12,142][87426] Updated weights for policy 1, policy_version 229180 (0.0011) -[2023-11-28 06:13:12,191][87424] Updated weights for policy 0, policy_version 229527 (0.0012) -[2023-11-28 06:13:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 117432320. Throughput: 0: 2697.2, 1: 2750.0. Samples: 117445760. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:13,445][86177] Avg episode reward: [(0, '-561.420'), (1, '-561.160')] -[2023-11-28 06:13:14,442][87424] Updated weights for policy 0, policy_version 229537 (0.0012) -[2023-11-28 06:13:14,582][87426] Updated weights for policy 1, policy_version 229190 (0.0008) -[2023-11-28 06:13:14,820][87424] Updated weights for policy 0, policy_version 229547 (0.0012) -[2023-11-28 06:13:14,960][87426] Updated weights for policy 1, policy_version 229200 (0.0008) -[2023-11-28 06:13:15,200][87424] Updated weights for policy 0, policy_version 229557 (0.0011) -[2023-11-28 06:13:15,355][87426] Updated weights for policy 1, policy_version 229210 (0.0009) -[2023-11-28 06:13:15,586][87424] Updated weights for policy 0, policy_version 229567 (0.0010) -[2023-11-28 06:13:17,614][87424] Updated weights for policy 0, policy_version 229577 (0.0011) -[2023-11-28 06:13:17,825][87426] Updated weights for policy 1, policy_version 229220 (0.0010) -[2023-11-28 06:13:17,998][87424] Updated weights for policy 0, policy_version 229587 (0.0012) -[2023-11-28 06:13:18,197][87426] Updated weights for policy 1, policy_version 229230 (0.0009) -[2023-11-28 06:13:18,375][87424] Updated weights for policy 0, policy_version 229597 (0.0011) -[2023-11-28 06:13:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 117448704. Throughput: 0: 2714.7, 1: 2745.5. Samples: 117469636. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:18,445][86177] Avg episode reward: [(0, '-543.270'), (1, '-552.360')] -[2023-11-28 06:13:18,566][87426] Updated weights for policy 1, policy_version 229240 (0.0010) -[2023-11-28 06:13:20,505][87424] Updated weights for policy 0, policy_version 229607 (0.0011) -[2023-11-28 06:13:20,557][87426] Updated weights for policy 1, policy_version 229250 (0.0012) -[2023-11-28 06:13:20,892][87424] Updated weights for policy 0, policy_version 229617 (0.0016) -[2023-11-28 06:13:20,931][87426] Updated weights for policy 1, policy_version 229260 (0.0012) -[2023-11-28 06:13:21,271][87424] Updated weights for policy 0, policy_version 229627 (0.0015) -[2023-11-28 06:13:21,313][87426] Updated weights for policy 1, policy_version 229270 (0.0011) -[2023-11-28 06:13:21,685][87426] Updated weights for policy 1, policy_version 229280 (0.0010) -[2023-11-28 06:13:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 117481472. Throughput: 0: 2720.5, 1: 2719.0. Samples: 117501804. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:23,445][86177] Avg episode reward: [(0, '-506.290'), (1, '-554.810')] -[2023-11-28 06:13:23,497][87424] Updated weights for policy 0, policy_version 229637 (0.0010) -[2023-11-28 06:13:23,870][87424] Updated weights for policy 0, policy_version 229647 (0.0009) -[2023-11-28 06:13:24,057][87426] Updated weights for policy 1, policy_version 229290 (0.0008) -[2023-11-28 06:13:24,245][87424] Updated weights for policy 0, policy_version 229657 (0.0008) -[2023-11-28 06:13:24,436][87426] Updated weights for policy 1, policy_version 229300 (0.0007) -[2023-11-28 06:13:24,809][87426] Updated weights for policy 1, policy_version 229310 (0.0007) -[2023-11-28 06:13:26,722][87424] Updated weights for policy 0, policy_version 229667 (0.0009) -[2023-11-28 06:13:27,109][87424] Updated weights for policy 0, policy_version 229677 (0.0008) -[2023-11-28 06:13:27,315][87426] Updated weights for policy 1, policy_version 229320 (0.0011) -[2023-11-28 06:13:27,499][87424] Updated weights for policy 0, policy_version 229687 (0.0008) -[2023-11-28 06:13:27,699][87426] Updated weights for policy 1, policy_version 229330 (0.0011) -[2023-11-28 06:13:28,079][87426] Updated weights for policy 1, policy_version 229340 (0.0012) -[2023-11-28 06:13:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 117514240. Throughput: 0: 2709.1, 1: 2719.5. Samples: 117525652. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:28,445][86177] Avg episode reward: [(0, '-504.840'), (1, '-519.400')] -[2023-11-28 06:13:30,031][87424] Updated weights for policy 0, policy_version 229697 (0.0010) -[2023-11-28 06:13:30,247][87426] Updated weights for policy 1, policy_version 229350 (0.0009) -[2023-11-28 06:13:30,406][87424] Updated weights for policy 0, policy_version 229707 (0.0012) -[2023-11-28 06:13:30,615][87426] Updated weights for policy 1, policy_version 229360 (0.0010) -[2023-11-28 06:13:30,790][87424] Updated weights for policy 0, policy_version 229717 (0.0011) -[2023-11-28 06:13:30,998][87426] Updated weights for policy 1, policy_version 229370 (0.0011) -[2023-11-28 06:13:31,173][87424] Updated weights for policy 0, policy_version 229727 (0.0010) -[2023-11-28 06:13:33,212][87426] Updated weights for policy 1, policy_version 229380 (0.0009) -[2023-11-28 06:13:33,373][87424] Updated weights for policy 0, policy_version 229737 (0.0008) -[2023-11-28 06:13:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 117530624. Throughput: 0: 2665.6, 1: 2723.7. Samples: 117549136. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:33,445][86177] Avg episode reward: [(0, '-500.270'), (1, '-513.380')] -[2023-11-28 06:13:33,594][87426] Updated weights for policy 1, policy_version 229390 (0.0009) -[2023-11-28 06:13:33,757][87424] Updated weights for policy 0, policy_version 229747 (0.0009) -[2023-11-28 06:13:33,968][87426] Updated weights for policy 1, policy_version 229400 (0.0007) -[2023-11-28 06:13:34,145][87424] Updated weights for policy 0, policy_version 229757 (0.0012) -[2023-11-28 06:13:35,727][87426] Updated weights for policy 1, policy_version 229410 (0.0008) -[2023-11-28 06:13:36,012][87424] Updated weights for policy 0, policy_version 229767 (0.0011) -[2023-11-28 06:13:36,108][87426] Updated weights for policy 1, policy_version 229420 (0.0011) -[2023-11-28 06:13:36,388][87424] Updated weights for policy 0, policy_version 229777 (0.0011) -[2023-11-28 06:13:36,482][87426] Updated weights for policy 1, policy_version 229430 (0.0011) -[2023-11-28 06:13:36,779][87424] Updated weights for policy 0, policy_version 229787 (0.0011) -[2023-11-28 06:13:36,862][87426] Updated weights for policy 1, policy_version 229440 (0.0009) -[2023-11-28 06:13:38,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 117563392. Throughput: 0: 2660.1, 1: 2738.6. Samples: 117582700. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:38,446][86177] Avg episode reward: [(0, '-500.350'), (1, '-512.630')] -[2023-11-28 06:13:38,690][87424] Updated weights for policy 0, policy_version 229797 (0.0012) -[2023-11-28 06:13:38,741][87426] Updated weights for policy 1, policy_version 229450 (0.0011) -[2023-11-28 06:13:39,067][87424] Updated weights for policy 0, policy_version 229807 (0.0010) -[2023-11-28 06:13:39,112][87426] Updated weights for policy 1, policy_version 229460 (0.0009) -[2023-11-28 06:13:39,441][87424] Updated weights for policy 0, policy_version 229817 (0.0011) -[2023-11-28 06:13:39,497][87426] Updated weights for policy 1, policy_version 229470 (0.0011) -[2023-11-28 06:13:41,295][87424] Updated weights for policy 0, policy_version 229827 (0.0012) -[2023-11-28 06:13:41,631][87426] Updated weights for policy 1, policy_version 229480 (0.0012) -[2023-11-28 06:13:41,687][87424] Updated weights for policy 0, policy_version 229837 (0.0011) -[2023-11-28 06:13:42,000][87426] Updated weights for policy 1, policy_version 229490 (0.0012) -[2023-11-28 06:13:42,063][87424] Updated weights for policy 0, policy_version 229847 (0.0012) -[2023-11-28 06:13:42,390][87426] Updated weights for policy 1, policy_version 229500 (0.0012) -[2023-11-28 06:13:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 117596160. Throughput: 0: 2673.2, 1: 2726.1. Samples: 117607644. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:43,445][86177] Avg episode reward: [(0, '-504.330'), (1, '-515.330')] -[2023-11-28 06:13:44,626][87424] Updated weights for policy 0, policy_version 229857 (0.0012) -[2023-11-28 06:13:44,937][87426] Updated weights for policy 1, policy_version 229510 (0.0010) -[2023-11-28 06:13:45,009][87424] Updated weights for policy 0, policy_version 229867 (0.0011) -[2023-11-28 06:13:45,320][87426] Updated weights for policy 1, policy_version 229520 (0.0008) -[2023-11-28 06:13:45,398][87424] Updated weights for policy 0, policy_version 229877 (0.0009) -[2023-11-28 06:13:45,690][87426] Updated weights for policy 1, policy_version 229530 (0.0011) -[2023-11-28 06:13:45,782][87424] Updated weights for policy 0, policy_version 229887 (0.0012) -[2023-11-28 06:13:47,466][87426] Updated weights for policy 1, policy_version 229540 (0.0011) -[2023-11-28 06:13:47,855][87426] Updated weights for policy 1, policy_version 229550 (0.0012) -[2023-11-28 06:13:48,236][87426] Updated weights for policy 1, policy_version 229560 (0.0011) -[2023-11-28 06:13:48,313][87424] Updated weights for policy 0, policy_version 229897 (0.0010) -[2023-11-28 06:13:48,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 117612544. Throughput: 0: 2652.6, 1: 2712.2. Samples: 117630588. Policy #0 lag: (min: 31.0, avg: 53.1, max: 90.0) -[2023-11-28 06:13:48,445][86177] Avg episode reward: [(0, '-509.590'), (1, '-510.790')] -[2023-11-28 06:13:48,686][87424] Updated weights for policy 0, policy_version 229907 (0.0009) -[2023-11-28 06:13:49,079][87424] Updated weights for policy 0, policy_version 229917 (0.0009) -[2023-11-28 06:13:50,273][87426] Updated weights for policy 1, policy_version 229570 (0.0011) -[2023-11-28 06:13:50,657][87426] Updated weights for policy 1, policy_version 229580 (0.0009) -[2023-11-28 06:13:51,051][87426] Updated weights for policy 1, policy_version 229590 (0.0008) -[2023-11-28 06:13:51,432][87426] Updated weights for policy 1, policy_version 229600 (0.0010) -[2023-11-28 06:13:51,661][87424] Updated weights for policy 0, policy_version 229927 (0.0011) -[2023-11-28 06:13:52,062][87424] Updated weights for policy 0, policy_version 229937 (0.0011) -[2023-11-28 06:13:52,435][87424] Updated weights for policy 0, policy_version 229947 (0.0012) -[2023-11-28 06:13:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 117645312. Throughput: 0: 2620.9, 1: 2717.8. Samples: 117662188. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:13:53,445][86177] Avg episode reward: [(0, '-516.090'), (1, '-516.120')] -[2023-11-28 06:13:53,693][87426] Updated weights for policy 1, policy_version 229610 (0.0009) -[2023-11-28 06:13:54,073][87426] Updated weights for policy 1, policy_version 229620 (0.0008) -[2023-11-28 06:13:54,450][87426] Updated weights for policy 1, policy_version 229630 (0.0008) -[2023-11-28 06:13:54,988][87424] Updated weights for policy 0, policy_version 229957 (0.0012) -[2023-11-28 06:13:55,373][87424] Updated weights for policy 0, policy_version 229967 (0.0012) -[2023-11-28 06:13:55,752][87424] Updated weights for policy 0, policy_version 229977 (0.0008) -[2023-11-28 06:13:56,166][87426] Updated weights for policy 1, policy_version 229640 (0.0011) -[2023-11-28 06:13:56,561][87426] Updated weights for policy 1, policy_version 229650 (0.0012) -[2023-11-28 06:13:56,936][87426] Updated weights for policy 1, policy_version 229660 (0.0012) -[2023-11-28 06:13:57,982][87424] Updated weights for policy 0, policy_version 229987 (0.0011) -[2023-11-28 06:13:58,364][87424] Updated weights for policy 0, policy_version 229997 (0.0009) -[2023-11-28 06:13:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 117669888. Throughput: 0: 2615.1, 1: 2756.0. Samples: 117687460. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:13:58,445][86177] Avg episode reward: [(0, '-522.450'), (1, '-519.440')] -[2023-11-28 06:13:58,722][87426] Updated weights for policy 1, policy_version 229670 (0.0009) -[2023-11-28 06:13:58,750][87424] Updated weights for policy 0, policy_version 230007 (0.0010) -[2023-11-28 06:13:59,114][87426] Updated weights for policy 1, policy_version 229680 (0.0009) -[2023-11-28 06:13:59,483][87426] Updated weights for policy 1, policy_version 229690 (0.0008) -[2023-11-28 06:14:00,839][87424] Updated weights for policy 0, policy_version 230017 (0.0008) -[2023-11-28 06:14:01,220][87424] Updated weights for policy 0, policy_version 230027 (0.0011) -[2023-11-28 06:14:01,597][87424] Updated weights for policy 0, policy_version 230037 (0.0010) -[2023-11-28 06:14:01,781][87426] Updated weights for policy 1, policy_version 229700 (0.0011) -[2023-11-28 06:14:01,983][87424] Updated weights for policy 0, policy_version 230047 (0.0012) -[2023-11-28 06:14:02,157][87426] Updated weights for policy 1, policy_version 229710 (0.0010) -[2023-11-28 06:14:02,539][87426] Updated weights for policy 1, policy_version 229720 (0.0011) -[2023-11-28 06:14:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 117702656. Throughput: 0: 2610.7, 1: 2772.1. Samples: 117711860. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:03,445][86177] Avg episode reward: [(0, '-526.310'), (1, '-514.450')] -[2023-11-28 06:14:04,122][87424] Updated weights for policy 0, policy_version 230057 (0.0008) -[2023-11-28 06:14:04,411][87426] Updated weights for policy 1, policy_version 229730 (0.0012) -[2023-11-28 06:14:04,498][87424] Updated weights for policy 0, policy_version 230067 (0.0009) -[2023-11-28 06:14:04,784][87426] Updated weights for policy 1, policy_version 229740 (0.0010) -[2023-11-28 06:14:04,890][87424] Updated weights for policy 0, policy_version 230077 (0.0012) -[2023-11-28 06:14:05,162][87426] Updated weights for policy 1, policy_version 229750 (0.0008) -[2023-11-28 06:14:05,541][87426] Updated weights for policy 1, policy_version 229760 (0.0007) -[2023-11-28 06:14:07,253][87424] Updated weights for policy 0, policy_version 230087 (0.0008) -[2023-11-28 06:14:07,639][87424] Updated weights for policy 0, policy_version 230097 (0.0010) -[2023-11-28 06:14:07,973][87426] Updated weights for policy 1, policy_version 229770 (0.0012) -[2023-11-28 06:14:08,023][87424] Updated weights for policy 0, policy_version 230107 (0.0012) -[2023-11-28 06:14:08,352][87426] Updated weights for policy 1, policy_version 229780 (0.0012) -[2023-11-28 06:14:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 117727232. Throughput: 0: 2614.2, 1: 2772.3. Samples: 117744196. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:08,445][86177] Avg episode reward: [(0, '-529.910'), (1, '-526.750')] -[2023-11-28 06:14:08,734][87426] Updated weights for policy 1, policy_version 229790 (0.0011) -[2023-11-28 06:14:10,112][87424] Updated weights for policy 0, policy_version 230117 (0.0010) -[2023-11-28 06:14:10,498][87424] Updated weights for policy 0, policy_version 230127 (0.0009) -[2023-11-28 06:14:10,885][87424] Updated weights for policy 0, policy_version 230137 (0.0008) -[2023-11-28 06:14:11,004][87426] Updated weights for policy 1, policy_version 229800 (0.0009) -[2023-11-28 06:14:11,381][87426] Updated weights for policy 1, policy_version 229810 (0.0007) -[2023-11-28 06:14:11,758][87426] Updated weights for policy 1, policy_version 229820 (0.0009) -[2023-11-28 06:14:13,379][87424] Updated weights for policy 0, policy_version 230147 (0.0008) -[2023-11-28 06:14:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 117751808. Throughput: 0: 2634.1, 1: 2772.1. Samples: 117768932. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:13,445][86177] Avg episode reward: [(0, '-533.620'), (1, '-521.290')] -[2023-11-28 06:14:13,767][87424] Updated weights for policy 0, policy_version 230157 (0.0011) -[2023-11-28 06:14:13,918][87426] Updated weights for policy 1, policy_version 229830 (0.0010) -[2023-11-28 06:14:14,150][87424] Updated weights for policy 0, policy_version 230167 (0.0012) -[2023-11-28 06:14:14,298][87426] Updated weights for policy 1, policy_version 229840 (0.0010) -[2023-11-28 06:14:14,682][87426] Updated weights for policy 1, policy_version 229850 (0.0008) -[2023-11-28 06:14:15,848][87424] Updated weights for policy 0, policy_version 230177 (0.0012) -[2023-11-28 06:14:16,229][87424] Updated weights for policy 0, policy_version 230187 (0.0012) -[2023-11-28 06:14:16,608][87424] Updated weights for policy 0, policy_version 230197 (0.0012) -[2023-11-28 06:14:16,826][87426] Updated weights for policy 1, policy_version 229860 (0.0008) -[2023-11-28 06:14:17,002][87424] Updated weights for policy 0, policy_version 230207 (0.0012) -[2023-11-28 06:14:17,209][87426] Updated weights for policy 1, policy_version 229870 (0.0007) -[2023-11-28 06:14:17,592][87426] Updated weights for policy 1, policy_version 229880 (0.0007) -[2023-11-28 06:14:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 117784576. Throughput: 0: 2662.8, 1: 2767.0. Samples: 117793476. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:18,445][86177] Avg episode reward: [(0, '-538.930'), (1, '-518.520')] -[2023-11-28 06:14:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000229888_58851328.pth... -[2023-11-28 06:14:18,501][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000227328_58195968.pth -[2023-11-28 06:14:18,839][87424] Updated weights for policy 0, policy_version 230217 (0.0012) -[2023-11-28 06:14:19,228][87424] Updated weights for policy 0, policy_version 230227 (0.0011) -[2023-11-28 06:14:19,601][87426] Updated weights for policy 1, policy_version 229890 (0.0009) -[2023-11-28 06:14:19,603][87424] Updated weights for policy 0, policy_version 230237 (0.0012) -[2023-11-28 06:14:19,711][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000230240_58941440.pth... -[2023-11-28 06:14:19,743][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000227712_58294272.pth -[2023-11-28 06:14:19,995][87426] Updated weights for policy 1, policy_version 229900 (0.0011) -[2023-11-28 06:14:20,370][87426] Updated weights for policy 1, policy_version 229910 (0.0011) -[2023-11-28 06:14:20,747][87426] Updated weights for policy 1, policy_version 229920 (0.0011) -[2023-11-28 06:14:21,875][87424] Updated weights for policy 0, policy_version 230247 (0.0010) -[2023-11-28 06:14:22,249][87424] Updated weights for policy 0, policy_version 230257 (0.0010) -[2023-11-28 06:14:22,633][87424] Updated weights for policy 0, policy_version 230267 (0.0008) -[2023-11-28 06:14:23,205][87426] Updated weights for policy 1, policy_version 229930 (0.0009) -[2023-11-28 06:14:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 117809152. Throughput: 0: 2647.8, 1: 2751.5. Samples: 117825664. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:23,445][86177] Avg episode reward: [(0, '-532.890'), (1, '-499.450')] -[2023-11-28 06:14:23,587][87426] Updated weights for policy 1, policy_version 229940 (0.0010) -[2023-11-28 06:14:23,969][87426] Updated weights for policy 1, policy_version 229950 (0.0011) -[2023-11-28 06:14:25,161][87424] Updated weights for policy 0, policy_version 230277 (0.0010) -[2023-11-28 06:14:25,540][87424] Updated weights for policy 0, policy_version 230287 (0.0012) -[2023-11-28 06:14:25,926][87424] Updated weights for policy 0, policy_version 230297 (0.0012) -[2023-11-28 06:14:26,342][87426] Updated weights for policy 1, policy_version 229960 (0.0012) -[2023-11-28 06:14:26,718][87426] Updated weights for policy 1, policy_version 229970 (0.0012) -[2023-11-28 06:14:27,093][87426] Updated weights for policy 1, policy_version 229980 (0.0012) -[2023-11-28 06:14:28,000][87424] Updated weights for policy 0, policy_version 230307 (0.0011) -[2023-11-28 06:14:28,384][87424] Updated weights for policy 0, policy_version 230317 (0.0012) -[2023-11-28 06:14:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 117833728. Throughput: 0: 2628.2, 1: 2765.1. Samples: 117850344. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:28,445][86177] Avg episode reward: [(0, '-534.760'), (1, '-500.300')] -[2023-11-28 06:14:28,763][87424] Updated weights for policy 0, policy_version 230327 (0.0012) -[2023-11-28 06:14:29,471][87426] Updated weights for policy 1, policy_version 229990 (0.0012) -[2023-11-28 06:14:29,855][87426] Updated weights for policy 1, policy_version 230000 (0.0012) -[2023-11-28 06:14:30,221][87426] Updated weights for policy 1, policy_version 230010 (0.0012) -[2023-11-28 06:14:30,928][87424] Updated weights for policy 0, policy_version 230337 (0.0012) -[2023-11-28 06:14:31,330][87424] Updated weights for policy 0, policy_version 230347 (0.0012) -[2023-11-28 06:14:31,705][87424] Updated weights for policy 0, policy_version 230357 (0.0012) -[2023-11-28 06:14:32,092][87424] Updated weights for policy 0, policy_version 230367 (0.0012) -[2023-11-28 06:14:32,333][87426] Updated weights for policy 1, policy_version 230020 (0.0011) -[2023-11-28 06:14:32,708][87426] Updated weights for policy 1, policy_version 230030 (0.0010) -[2023-11-28 06:14:33,090][87426] Updated weights for policy 1, policy_version 230040 (0.0011) -[2023-11-28 06:14:33,445][86177] Fps is (10 sec: 5734.1, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 117866496. Throughput: 0: 2668.2, 1: 2763.2. Samples: 117875004. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:33,446][86177] Avg episode reward: [(0, '-524.000'), (1, '-502.070')] -[2023-11-28 06:14:34,531][87424] Updated weights for policy 0, policy_version 230377 (0.0011) -[2023-11-28 06:14:34,913][87424] Updated weights for policy 0, policy_version 230387 (0.0012) -[2023-11-28 06:14:35,237][87426] Updated weights for policy 1, policy_version 230050 (0.0011) -[2023-11-28 06:14:35,293][87424] Updated weights for policy 0, policy_version 230397 (0.0012) -[2023-11-28 06:14:35,610][87426] Updated weights for policy 1, policy_version 230060 (0.0009) -[2023-11-28 06:14:36,004][87426] Updated weights for policy 1, policy_version 230070 (0.0011) -[2023-11-28 06:14:36,377][87426] Updated weights for policy 1, policy_version 230080 (0.0011) -[2023-11-28 06:14:37,556][87424] Updated weights for policy 0, policy_version 230407 (0.0012) -[2023-11-28 06:14:37,934][87424] Updated weights for policy 0, policy_version 230417 (0.0012) -[2023-11-28 06:14:38,326][87424] Updated weights for policy 0, policy_version 230427 (0.0011) -[2023-11-28 06:14:38,374][87426] Updated weights for policy 1, policy_version 230090 (0.0010) -[2023-11-28 06:14:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 117882880. Throughput: 0: 2712.9, 1: 2751.4. Samples: 117908080. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:38,445][86177] Avg episode reward: [(0, '-512.010'), (1, '-506.620')] -[2023-11-28 06:14:38,753][87426] Updated weights for policy 1, policy_version 230100 (0.0007) -[2023-11-28 06:14:39,131][87426] Updated weights for policy 1, policy_version 230110 (0.0011) -[2023-11-28 06:14:40,287][87424] Updated weights for policy 0, policy_version 230437 (0.0012) -[2023-11-28 06:14:40,670][87424] Updated weights for policy 0, policy_version 230447 (0.0019) -[2023-11-28 06:14:40,902][87426] Updated weights for policy 1, policy_version 230120 (0.0010) -[2023-11-28 06:14:41,045][87424] Updated weights for policy 0, policy_version 230457 (0.0010) -[2023-11-28 06:14:41,271][87426] Updated weights for policy 1, policy_version 230130 (0.0008) -[2023-11-28 06:14:41,649][87426] Updated weights for policy 1, policy_version 230140 (0.0009) -[2023-11-28 06:14:43,412][87424] Updated weights for policy 0, policy_version 230467 (0.0009) -[2023-11-28 06:14:43,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 117915648. Throughput: 0: 2717.2, 1: 2724.2. Samples: 117932320. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:43,445][86177] Avg episode reward: [(0, '-519.570'), (1, '-505.510')] -[2023-11-28 06:14:43,801][87424] Updated weights for policy 0, policy_version 230477 (0.0011) -[2023-11-28 06:14:44,164][87426] Updated weights for policy 1, policy_version 230150 (0.0012) -[2023-11-28 06:14:44,177][87424] Updated weights for policy 0, policy_version 230487 (0.0007) -[2023-11-28 06:14:44,536][87426] Updated weights for policy 1, policy_version 230160 (0.0012) -[2023-11-28 06:14:44,919][87426] Updated weights for policy 1, policy_version 230170 (0.0010) -[2023-11-28 06:14:46,149][87424] Updated weights for policy 0, policy_version 230497 (0.0008) -[2023-11-28 06:14:46,552][87424] Updated weights for policy 0, policy_version 230507 (0.0011) -[2023-11-28 06:14:46,929][87424] Updated weights for policy 0, policy_version 230517 (0.0012) -[2023-11-28 06:14:47,320][87424] Updated weights for policy 0, policy_version 230527 (0.0011) -[2023-11-28 06:14:47,509][87426] Updated weights for policy 1, policy_version 230180 (0.0008) -[2023-11-28 06:14:47,886][87426] Updated weights for policy 1, policy_version 230190 (0.0007) -[2023-11-28 06:14:48,266][87426] Updated weights for policy 1, policy_version 230200 (0.0008) -[2023-11-28 06:14:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 117940224. Throughput: 0: 2722.8, 1: 2707.7. Samples: 117956232. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:48,445][86177] Avg episode reward: [(0, '-508.600'), (1, '-505.870')] -[2023-11-28 06:14:49,061][87424] Updated weights for policy 0, policy_version 230537 (0.0012) -[2023-11-28 06:14:49,445][87424] Updated weights for policy 0, policy_version 230547 (0.0012) -[2023-11-28 06:14:49,836][87424] Updated weights for policy 0, policy_version 230557 (0.0016) -[2023-11-28 06:14:50,369][87426] Updated weights for policy 1, policy_version 230210 (0.0008) -[2023-11-28 06:14:50,754][87426] Updated weights for policy 1, policy_version 230220 (0.0013) -[2023-11-28 06:14:51,122][87426] Updated weights for policy 1, policy_version 230230 (0.0012) -[2023-11-28 06:14:51,502][87426] Updated weights for policy 1, policy_version 230240 (0.0008) -[2023-11-28 06:14:52,163][87424] Updated weights for policy 0, policy_version 230567 (0.0012) -[2023-11-28 06:14:52,554][87424] Updated weights for policy 0, policy_version 230577 (0.0012) -[2023-11-28 06:14:52,927][87424] Updated weights for policy 0, policy_version 230587 (0.0011) -[2023-11-28 06:14:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 117972992. Throughput: 0: 2736.5, 1: 2702.8. Samples: 117988968. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:53,445][86177] Avg episode reward: [(0, '-513.990'), (1, '-503.690')] -[2023-11-28 06:14:53,913][87426] Updated weights for policy 1, policy_version 230250 (0.0012) -[2023-11-28 06:14:54,283][87426] Updated weights for policy 1, policy_version 230260 (0.0011) -[2023-11-28 06:14:54,674][87426] Updated weights for policy 1, policy_version 230270 (0.0009) -[2023-11-28 06:14:55,361][87424] Updated weights for policy 0, policy_version 230597 (0.0007) -[2023-11-28 06:14:55,737][87424] Updated weights for policy 0, policy_version 230607 (0.0010) -[2023-11-28 06:14:56,119][87424] Updated weights for policy 0, policy_version 230617 (0.0012) -[2023-11-28 06:14:56,841][87426] Updated weights for policy 1, policy_version 230280 (0.0008) -[2023-11-28 06:14:57,220][87426] Updated weights for policy 1, policy_version 230290 (0.0007) -[2023-11-28 06:14:57,599][87426] Updated weights for policy 1, policy_version 230300 (0.0007) -[2023-11-28 06:14:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 117997568. Throughput: 0: 2716.5, 1: 2708.7. Samples: 118013068. Policy #0 lag: (min: 3.0, avg: 29.2, max: 35.0) -[2023-11-28 06:14:58,445][86177] Avg episode reward: [(0, '-511.530'), (1, '-515.040')] -[2023-11-28 06:14:58,524][87424] Updated weights for policy 0, policy_version 230627 (0.0009) -[2023-11-28 06:14:58,903][87424] Updated weights for policy 0, policy_version 230637 (0.0008) -[2023-11-28 06:14:59,291][87424] Updated weights for policy 0, policy_version 230647 (0.0007) -[2023-11-28 06:14:59,500][87426] Updated weights for policy 1, policy_version 230310 (0.0007) -[2023-11-28 06:14:59,896][87426] Updated weights for policy 1, policy_version 230320 (0.0009) -[2023-11-28 06:15:00,263][87426] Updated weights for policy 1, policy_version 230330 (0.0011) -[2023-11-28 06:15:01,752][87424] Updated weights for policy 0, policy_version 230657 (0.0010) -[2023-11-28 06:15:02,137][87424] Updated weights for policy 0, policy_version 230667 (0.0011) -[2023-11-28 06:15:02,507][87424] Updated weights for policy 0, policy_version 230677 (0.0010) -[2023-11-28 06:15:02,581][87426] Updated weights for policy 1, policy_version 230340 (0.0011) -[2023-11-28 06:15:02,890][87424] Updated weights for policy 0, policy_version 230687 (0.0010) -[2023-11-28 06:15:02,956][87426] Updated weights for policy 1, policy_version 230350 (0.0012) -[2023-11-28 06:15:03,329][87426] Updated weights for policy 1, policy_version 230360 (0.0012) -[2023-11-28 06:15:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 118022144. Throughput: 0: 2702.1, 1: 2705.5. Samples: 118036820. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:03,446][86177] Avg episode reward: [(0, '-505.980'), (1, '-530.770')] -[2023-11-28 06:15:04,894][87424] Updated weights for policy 0, policy_version 230697 (0.0010) -[2023-11-28 06:15:05,269][87424] Updated weights for policy 0, policy_version 230707 (0.0012) -[2023-11-28 06:15:05,428][87426] Updated weights for policy 1, policy_version 230370 (0.0010) -[2023-11-28 06:15:05,657][87424] Updated weights for policy 0, policy_version 230717 (0.0010) -[2023-11-28 06:15:05,810][87426] Updated weights for policy 1, policy_version 230380 (0.0010) -[2023-11-28 06:15:06,186][87426] Updated weights for policy 1, policy_version 230390 (0.0008) -[2023-11-28 06:15:06,568][87426] Updated weights for policy 1, policy_version 230400 (0.0008) -[2023-11-28 06:15:07,513][87424] Updated weights for policy 0, policy_version 230727 (0.0011) -[2023-11-28 06:15:07,888][87424] Updated weights for policy 0, policy_version 230737 (0.0012) -[2023-11-28 06:15:08,264][87424] Updated weights for policy 0, policy_version 230747 (0.0012) -[2023-11-28 06:15:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 118046720. Throughput: 0: 2726.9, 1: 2695.5. Samples: 118069676. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:08,445][86177] Avg episode reward: [(0, '-510.790'), (1, '-527.590')] -[2023-11-28 06:15:08,923][87426] Updated weights for policy 1, policy_version 230410 (0.0008) -[2023-11-28 06:15:09,304][87426] Updated weights for policy 1, policy_version 230420 (0.0010) -[2023-11-28 06:15:09,686][87426] Updated weights for policy 1, policy_version 230430 (0.0011) -[2023-11-28 06:15:10,630][87424] Updated weights for policy 0, policy_version 230757 (0.0010) -[2023-11-28 06:15:11,029][87424] Updated weights for policy 0, policy_version 230767 (0.0011) -[2023-11-28 06:15:11,401][87424] Updated weights for policy 0, policy_version 230777 (0.0012) -[2023-11-28 06:15:12,028][87426] Updated weights for policy 1, policy_version 230440 (0.0012) -[2023-11-28 06:15:12,409][87426] Updated weights for policy 1, policy_version 230450 (0.0010) -[2023-11-28 06:15:12,781][87426] Updated weights for policy 1, policy_version 230460 (0.0013) -[2023-11-28 06:15:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118079488. Throughput: 0: 2724.4, 1: 2670.8. Samples: 118093132. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:13,445][86177] Avg episode reward: [(0, '-511.590'), (1, '-528.150')] -[2023-11-28 06:15:13,688][87424] Updated weights for policy 0, policy_version 230787 (0.0012) -[2023-11-28 06:15:14,071][87424] Updated weights for policy 0, policy_version 230797 (0.0012) -[2023-11-28 06:15:14,462][87424] Updated weights for policy 0, policy_version 230807 (0.0011) -[2023-11-28 06:15:15,370][87426] Updated weights for policy 1, policy_version 230470 (0.0011) -[2023-11-28 06:15:15,743][87426] Updated weights for policy 1, policy_version 230480 (0.0011) -[2023-11-28 06:15:16,124][87426] Updated weights for policy 1, policy_version 230490 (0.0012) -[2023-11-28 06:15:16,343][87424] Updated weights for policy 0, policy_version 230817 (0.0012) -[2023-11-28 06:15:16,719][87424] Updated weights for policy 0, policy_version 230827 (0.0011) -[2023-11-28 06:15:17,097][87424] Updated weights for policy 0, policy_version 230837 (0.0007) -[2023-11-28 06:15:17,481][87424] Updated weights for policy 0, policy_version 230847 (0.0007) -[2023-11-28 06:15:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 118104064. Throughput: 0: 2718.5, 1: 2668.8. Samples: 118117432. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:18,445][86177] Avg episode reward: [(0, '-511.220'), (1, '-521.620')] -[2023-11-28 06:15:18,617][87426] Updated weights for policy 1, policy_version 230500 (0.0012) -[2023-11-28 06:15:18,983][87426] Updated weights for policy 1, policy_version 230510 (0.0009) -[2023-11-28 06:15:19,364][87426] Updated weights for policy 1, policy_version 230520 (0.0011) -[2023-11-28 06:15:19,677][87424] Updated weights for policy 0, policy_version 230857 (0.0010) -[2023-11-28 06:15:20,049][87424] Updated weights for policy 0, policy_version 230867 (0.0010) -[2023-11-28 06:15:20,432][87424] Updated weights for policy 0, policy_version 230877 (0.0010) -[2023-11-28 06:15:21,160][87426] Updated weights for policy 1, policy_version 230530 (0.0010) -[2023-11-28 06:15:21,544][87426] Updated weights for policy 1, policy_version 230540 (0.0009) -[2023-11-28 06:15:21,923][87426] Updated weights for policy 1, policy_version 230550 (0.0013) -[2023-11-28 06:15:22,295][87426] Updated weights for policy 1, policy_version 230560 (0.0012) -[2023-11-28 06:15:22,948][87424] Updated weights for policy 0, policy_version 230887 (0.0011) -[2023-11-28 06:15:23,336][87424] Updated weights for policy 0, policy_version 230897 (0.0012) -[2023-11-28 06:15:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 118128640. Throughput: 0: 2701.8, 1: 2660.0. Samples: 118149360. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:23,445][86177] Avg episode reward: [(0, '-512.330'), (1, '-514.290')] -[2023-11-28 06:15:23,718][87424] Updated weights for policy 0, policy_version 230907 (0.0011) -[2023-11-28 06:15:24,537][87426] Updated weights for policy 1, policy_version 230570 (0.0012) -[2023-11-28 06:15:24,911][87426] Updated weights for policy 1, policy_version 230580 (0.0011) -[2023-11-28 06:15:25,293][87426] Updated weights for policy 1, policy_version 230590 (0.0011) -[2023-11-28 06:15:25,519][87424] Updated weights for policy 0, policy_version 230917 (0.0010) -[2023-11-28 06:15:25,910][87424] Updated weights for policy 0, policy_version 230927 (0.0007) -[2023-11-28 06:15:26,294][87424] Updated weights for policy 0, policy_version 230937 (0.0008) -[2023-11-28 06:15:27,318][87426] Updated weights for policy 1, policy_version 230600 (0.0008) -[2023-11-28 06:15:27,697][87426] Updated weights for policy 1, policy_version 230610 (0.0007) -[2023-11-28 06:15:28,073][87426] Updated weights for policy 1, policy_version 230620 (0.0007) -[2023-11-28 06:15:28,276][87424] Updated weights for policy 0, policy_version 230947 (0.0008) -[2023-11-28 06:15:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 118161408. Throughput: 0: 2727.9, 1: 2677.8. Samples: 118175576. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:28,445][86177] Avg episode reward: [(0, '-502.600'), (1, '-512.850')] -[2023-11-28 06:15:28,661][87424] Updated weights for policy 0, policy_version 230957 (0.0008) -[2023-11-28 06:15:29,040][87424] Updated weights for policy 0, policy_version 230967 (0.0011) -[2023-11-28 06:15:30,192][87426] Updated weights for policy 1, policy_version 230630 (0.0009) -[2023-11-28 06:15:30,565][87426] Updated weights for policy 1, policy_version 230640 (0.0011) -[2023-11-28 06:15:30,946][87426] Updated weights for policy 1, policy_version 230650 (0.0008) -[2023-11-28 06:15:31,081][87424] Updated weights for policy 0, policy_version 230977 (0.0008) -[2023-11-28 06:15:31,457][87424] Updated weights for policy 0, policy_version 230987 (0.0012) -[2023-11-28 06:15:31,845][87424] Updated weights for policy 0, policy_version 230997 (0.0011) -[2023-11-28 06:15:32,235][87424] Updated weights for policy 0, policy_version 231007 (0.0009) -[2023-11-28 06:15:32,994][87426] Updated weights for policy 1, policy_version 230660 (0.0009) -[2023-11-28 06:15:33,371][87426] Updated weights for policy 1, policy_version 230670 (0.0012) -[2023-11-28 06:15:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 118185984. Throughput: 0: 2734.4, 1: 2685.9. Samples: 118200144. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:33,445][86177] Avg episode reward: [(0, '-500.580'), (1, '-514.610')] -[2023-11-28 06:15:33,753][87426] Updated weights for policy 1, policy_version 230680 (0.0012) -[2023-11-28 06:15:34,143][87424] Updated weights for policy 0, policy_version 231017 (0.0011) -[2023-11-28 06:15:34,511][87424] Updated weights for policy 0, policy_version 231027 (0.0012) -[2023-11-28 06:15:34,902][87424] Updated weights for policy 0, policy_version 231037 (0.0012) -[2023-11-28 06:15:35,852][87426] Updated weights for policy 1, policy_version 230690 (0.0012) -[2023-11-28 06:15:36,223][87426] Updated weights for policy 1, policy_version 230700 (0.0009) -[2023-11-28 06:15:36,601][87426] Updated weights for policy 1, policy_version 230710 (0.0010) -[2023-11-28 06:15:36,987][87426] Updated weights for policy 1, policy_version 230720 (0.0011) -[2023-11-28 06:15:37,325][87424] Updated weights for policy 0, policy_version 231047 (0.0012) -[2023-11-28 06:15:37,708][87424] Updated weights for policy 0, policy_version 231057 (0.0012) -[2023-11-28 06:15:38,102][87424] Updated weights for policy 0, policy_version 231067 (0.0012) -[2023-11-28 06:15:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 118218752. Throughput: 0: 2714.2, 1: 2714.8. Samples: 118233272. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:38,445][86177] Avg episode reward: [(0, '-499.970'), (1, '-520.450')] -[2023-11-28 06:15:39,007][87426] Updated weights for policy 1, policy_version 230730 (0.0011) -[2023-11-28 06:15:39,383][87426] Updated weights for policy 1, policy_version 230740 (0.0010) -[2023-11-28 06:15:39,761][87426] Updated weights for policy 1, policy_version 230750 (0.0008) -[2023-11-28 06:15:40,304][87424] Updated weights for policy 0, policy_version 231077 (0.0012) -[2023-11-28 06:15:40,681][87424] Updated weights for policy 0, policy_version 231087 (0.0012) -[2023-11-28 06:15:41,056][87424] Updated weights for policy 0, policy_version 231097 (0.0012) -[2023-11-28 06:15:42,208][87426] Updated weights for policy 1, policy_version 230760 (0.0008) -[2023-11-28 06:15:42,579][87426] Updated weights for policy 1, policy_version 230770 (0.0011) -[2023-11-28 06:15:42,967][87426] Updated weights for policy 1, policy_version 230780 (0.0009) -[2023-11-28 06:15:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118243328. Throughput: 0: 2717.5, 1: 2697.2. Samples: 118256732. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:43,445][86177] Avg episode reward: [(0, '-539.510'), (1, '-521.830')] -[2023-11-28 06:15:43,470][87424] Updated weights for policy 0, policy_version 231107 (0.0012) -[2023-11-28 06:15:43,868][87424] Updated weights for policy 0, policy_version 231117 (0.0012) -[2023-11-28 06:15:44,241][87424] Updated weights for policy 0, policy_version 231127 (0.0012) -[2023-11-28 06:15:45,288][87426] Updated weights for policy 1, policy_version 230790 (0.0011) -[2023-11-28 06:15:45,667][87426] Updated weights for policy 1, policy_version 230800 (0.0012) -[2023-11-28 06:15:46,049][87426] Updated weights for policy 1, policy_version 230810 (0.0012) -[2023-11-28 06:15:46,345][87424] Updated weights for policy 0, policy_version 231137 (0.0012) -[2023-11-28 06:15:46,733][87424] Updated weights for policy 0, policy_version 231147 (0.0012) -[2023-11-28 06:15:47,122][87424] Updated weights for policy 0, policy_version 231157 (0.0012) -[2023-11-28 06:15:47,503][87424] Updated weights for policy 0, policy_version 231167 (0.0012) -[2023-11-28 06:15:47,933][87426] Updated weights for policy 1, policy_version 230820 (0.0012) -[2023-11-28 06:15:48,310][87426] Updated weights for policy 1, policy_version 230830 (0.0010) -[2023-11-28 06:15:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 118267904. Throughput: 0: 2743.2, 1: 2694.8. Samples: 118281528. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:48,445][86177] Avg episode reward: [(0, '-540.560'), (1, '-532.440')] -[2023-11-28 06:15:48,692][87426] Updated weights for policy 1, policy_version 230840 (0.0008) -[2023-11-28 06:15:49,262][87424] Updated weights for policy 0, policy_version 231177 (0.0008) -[2023-11-28 06:15:49,652][87424] Updated weights for policy 0, policy_version 231187 (0.0007) -[2023-11-28 06:15:50,028][87424] Updated weights for policy 0, policy_version 231197 (0.0010) -[2023-11-28 06:15:50,843][87426] Updated weights for policy 1, policy_version 230850 (0.0009) -[2023-11-28 06:15:51,221][87426] Updated weights for policy 1, policy_version 230860 (0.0009) -[2023-11-28 06:15:51,607][87426] Updated weights for policy 1, policy_version 230870 (0.0012) -[2023-11-28 06:15:51,978][87426] Updated weights for policy 1, policy_version 230880 (0.0011) -[2023-11-28 06:15:52,404][87424] Updated weights for policy 0, policy_version 231207 (0.0011) -[2023-11-28 06:15:52,785][87424] Updated weights for policy 0, policy_version 231217 (0.0012) -[2023-11-28 06:15:53,153][87424] Updated weights for policy 0, policy_version 231227 (0.0009) -[2023-11-28 06:15:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 118300672. Throughput: 0: 2729.6, 1: 2725.7. Samples: 118315164. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:53,445][86177] Avg episode reward: [(0, '-545.780'), (1, '-534.220')] -[2023-11-28 06:15:54,459][87426] Updated weights for policy 1, policy_version 230890 (0.0008) -[2023-11-28 06:15:54,844][87426] Updated weights for policy 1, policy_version 230900 (0.0009) -[2023-11-28 06:15:55,221][87426] Updated weights for policy 1, policy_version 230910 (0.0009) -[2023-11-28 06:15:55,590][87424] Updated weights for policy 0, policy_version 231237 (0.0010) -[2023-11-28 06:15:55,981][87424] Updated weights for policy 0, policy_version 231247 (0.0012) -[2023-11-28 06:15:56,365][87424] Updated weights for policy 0, policy_version 231257 (0.0009) -[2023-11-28 06:15:57,294][87426] Updated weights for policy 1, policy_version 230920 (0.0007) -[2023-11-28 06:15:57,680][87426] Updated weights for policy 1, policy_version 230930 (0.0007) -[2023-11-28 06:15:58,055][87426] Updated weights for policy 1, policy_version 230940 (0.0007) -[2023-11-28 06:15:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118325248. Throughput: 0: 2719.7, 1: 2731.7. Samples: 118338448. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:15:58,446][86177] Avg episode reward: [(0, '-549.880'), (1, '-534.140')] -[2023-11-28 06:15:58,923][87424] Updated weights for policy 0, policy_version 231267 (0.0010) -[2023-11-28 06:15:59,309][87424] Updated weights for policy 0, policy_version 231277 (0.0012) -[2023-11-28 06:15:59,685][87424] Updated weights for policy 0, policy_version 231287 (0.0011) -[2023-11-28 06:15:59,949][87426] Updated weights for policy 1, policy_version 230950 (0.0010) -[2023-11-28 06:16:00,328][87426] Updated weights for policy 1, policy_version 230960 (0.0007) -[2023-11-28 06:16:00,711][87426] Updated weights for policy 1, policy_version 230970 (0.0011) -[2023-11-28 06:16:01,853][87424] Updated weights for policy 0, policy_version 231297 (0.0011) -[2023-11-28 06:16:02,233][87424] Updated weights for policy 0, policy_version 231307 (0.0008) -[2023-11-28 06:16:02,624][87424] Updated weights for policy 0, policy_version 231317 (0.0011) -[2023-11-28 06:16:03,012][87424] Updated weights for policy 0, policy_version 231327 (0.0009) -[2023-11-28 06:16:03,112][87426] Updated weights for policy 1, policy_version 230980 (0.0011) -[2023-11-28 06:16:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 118349824. Throughput: 0: 2692.0, 1: 2754.4. Samples: 118362520. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:16:03,445][86177] Avg episode reward: [(0, '-508.590'), (1, '-525.760')] -[2023-11-28 06:16:03,490][87426] Updated weights for policy 1, policy_version 230990 (0.0012) -[2023-11-28 06:16:03,862][87426] Updated weights for policy 1, policy_version 231000 (0.0011) -[2023-11-28 06:16:05,491][87424] Updated weights for policy 0, policy_version 231337 (0.0012) -[2023-11-28 06:16:05,839][87426] Updated weights for policy 1, policy_version 231010 (0.0011) -[2023-11-28 06:16:05,874][87424] Updated weights for policy 0, policy_version 231347 (0.0012) -[2023-11-28 06:16:06,217][87426] Updated weights for policy 1, policy_version 231020 (0.0007) -[2023-11-28 06:16:06,254][87424] Updated weights for policy 0, policy_version 231357 (0.0011) -[2023-11-28 06:16:06,599][87426] Updated weights for policy 1, policy_version 231030 (0.0007) -[2023-11-28 06:16:06,978][87426] Updated weights for policy 1, policy_version 231040 (0.0012) -[2023-11-28 06:16:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 118374400. Throughput: 0: 2674.8, 1: 2757.9. Samples: 118393828. Policy #0 lag: (min: 31.0, avg: 51.6, max: 84.0) -[2023-11-28 06:16:08,445][86177] Avg episode reward: [(0, '-508.480'), (1, '-518.080')] -[2023-11-28 06:16:08,823][87424] Updated weights for policy 0, policy_version 231367 (0.0009) -[2023-11-28 06:16:09,090][87426] Updated weights for policy 1, policy_version 231050 (0.0011) -[2023-11-28 06:16:09,206][87424] Updated weights for policy 0, policy_version 231377 (0.0012) -[2023-11-28 06:16:09,476][87426] Updated weights for policy 1, policy_version 231060 (0.0011) -[2023-11-28 06:16:09,594][87424] Updated weights for policy 0, policy_version 231387 (0.0007) -[2023-11-28 06:16:09,860][87426] Updated weights for policy 1, policy_version 231070 (0.0012) -[2023-11-28 06:16:11,700][87424] Updated weights for policy 0, policy_version 231397 (0.0011) -[2023-11-28 06:16:11,871][87426] Updated weights for policy 1, policy_version 231080 (0.0010) -[2023-11-28 06:16:12,077][87424] Updated weights for policy 0, policy_version 231407 (0.0010) -[2023-11-28 06:16:12,242][87426] Updated weights for policy 1, policy_version 231090 (0.0010) -[2023-11-28 06:16:12,455][87424] Updated weights for policy 0, policy_version 231417 (0.0010) -[2023-11-28 06:16:12,622][87426] Updated weights for policy 1, policy_version 231100 (0.0012) -[2023-11-28 06:16:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118407168. Throughput: 0: 2643.6, 1: 2731.2. Samples: 118417444. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:13,445][86177] Avg episode reward: [(0, '-512.180'), (1, '-521.440')] -[2023-11-28 06:16:14,518][87424] Updated weights for policy 0, policy_version 231427 (0.0011) -[2023-11-28 06:16:14,905][87424] Updated weights for policy 0, policy_version 231437 (0.0011) -[2023-11-28 06:16:15,019][87426] Updated weights for policy 1, policy_version 231110 (0.0009) -[2023-11-28 06:16:15,296][87424] Updated weights for policy 0, policy_version 231447 (0.0012) -[2023-11-28 06:16:15,401][87426] Updated weights for policy 1, policy_version 231120 (0.0009) -[2023-11-28 06:16:15,783][87426] Updated weights for policy 1, policy_version 231130 (0.0011) -[2023-11-28 06:16:17,133][87424] Updated weights for policy 0, policy_version 231457 (0.0011) -[2023-11-28 06:16:17,516][87424] Updated weights for policy 0, policy_version 231467 (0.0008) -[2023-11-28 06:16:17,578][87426] Updated weights for policy 1, policy_version 231140 (0.0012) -[2023-11-28 06:16:17,896][87424] Updated weights for policy 0, policy_version 231477 (0.0010) -[2023-11-28 06:16:17,963][87426] Updated weights for policy 1, policy_version 231150 (0.0008) -[2023-11-28 06:16:18,275][87424] Updated weights for policy 0, policy_version 231487 (0.0010) -[2023-11-28 06:16:18,332][87426] Updated weights for policy 1, policy_version 231160 (0.0007) -[2023-11-28 06:16:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 118431744. Throughput: 0: 2642.8, 1: 2744.6. Samples: 118442576. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:18,445][86177] Avg episode reward: [(0, '-517.190'), (1, '-517.200')] -[2023-11-28 06:16:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000231488_59260928.pth... -[2023-11-28 06:16:18,485][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000228960_58613760.pth -[2023-11-28 06:16:18,635][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000231168_59179008.pth... -[2023-11-28 06:16:18,670][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000228608_58523648.pth -[2023-11-28 06:16:19,963][87426] Updated weights for policy 1, policy_version 231170 (0.0010) -[2023-11-28 06:16:20,331][87424] Updated weights for policy 0, policy_version 231497 (0.0010) -[2023-11-28 06:16:20,342][87426] Updated weights for policy 1, policy_version 231180 (0.0011) -[2023-11-28 06:16:20,712][87424] Updated weights for policy 0, policy_version 231507 (0.0012) -[2023-11-28 06:16:20,718][87426] Updated weights for policy 1, policy_version 231190 (0.0010) -[2023-11-28 06:16:21,091][87426] Updated weights for policy 1, policy_version 231200 (0.0011) -[2023-11-28 06:16:21,092][87424] Updated weights for policy 0, policy_version 231517 (0.0011) -[2023-11-28 06:16:23,173][87424] Updated weights for policy 0, policy_version 231527 (0.0012) -[2023-11-28 06:16:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 118456320. Throughput: 0: 2650.4, 1: 2751.5. Samples: 118476360. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:23,446][86177] Avg episode reward: [(0, '-520.860'), (1, '-522.530')] -[2023-11-28 06:16:23,569][87424] Updated weights for policy 0, policy_version 231537 (0.0010) -[2023-11-28 06:16:23,598][87426] Updated weights for policy 1, policy_version 231210 (0.0009) -[2023-11-28 06:16:23,954][87424] Updated weights for policy 0, policy_version 231547 (0.0011) -[2023-11-28 06:16:23,975][87426] Updated weights for policy 1, policy_version 231220 (0.0010) -[2023-11-28 06:16:24,354][87426] Updated weights for policy 1, policy_version 231230 (0.0011) -[2023-11-28 06:16:26,033][87424] Updated weights for policy 0, policy_version 231557 (0.0010) -[2023-11-28 06:16:26,077][87426] Updated weights for policy 1, policy_version 231240 (0.0011) -[2023-11-28 06:16:26,416][87424] Updated weights for policy 0, policy_version 231567 (0.0008) -[2023-11-28 06:16:26,457][87426] Updated weights for policy 1, policy_version 231250 (0.0011) -[2023-11-28 06:16:26,796][87424] Updated weights for policy 0, policy_version 231577 (0.0011) -[2023-11-28 06:16:26,831][87426] Updated weights for policy 1, policy_version 231260 (0.0010) -[2023-11-28 06:16:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118489088. Throughput: 0: 2676.6, 1: 2769.7. Samples: 118501816. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:28,445][86177] Avg episode reward: [(0, '-520.720'), (1, '-523.900')] -[2023-11-28 06:16:28,590][87424] Updated weights for policy 0, policy_version 231587 (0.0011) -[2023-11-28 06:16:28,968][87426] Updated weights for policy 1, policy_version 231270 (0.0011) -[2023-11-28 06:16:28,974][87424] Updated weights for policy 0, policy_version 231597 (0.0011) -[2023-11-28 06:16:29,348][87426] Updated weights for policy 1, policy_version 231280 (0.0008) -[2023-11-28 06:16:29,355][87424] Updated weights for policy 0, policy_version 231607 (0.0012) -[2023-11-28 06:16:29,725][87426] Updated weights for policy 1, policy_version 231290 (0.0011) -[2023-11-28 06:16:31,665][87424] Updated weights for policy 0, policy_version 231617 (0.0012) -[2023-11-28 06:16:31,948][87426] Updated weights for policy 1, policy_version 231300 (0.0011) -[2023-11-28 06:16:32,038][87424] Updated weights for policy 0, policy_version 231627 (0.0011) -[2023-11-28 06:16:32,337][87426] Updated weights for policy 1, policy_version 231310 (0.0011) -[2023-11-28 06:16:32,428][87424] Updated weights for policy 0, policy_version 231637 (0.0010) -[2023-11-28 06:16:32,715][87426] Updated weights for policy 1, policy_version 231320 (0.0011) -[2023-11-28 06:16:32,814][87424] Updated weights for policy 0, policy_version 231647 (0.0011) -[2023-11-28 06:16:33,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 118521856. Throughput: 0: 2683.1, 1: 2778.9. Samples: 118527320. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:33,445][86177] Avg episode reward: [(0, '-511.840'), (1, '-521.660')] -[2023-11-28 06:16:34,641][87424] Updated weights for policy 0, policy_version 231657 (0.0009) -[2023-11-28 06:16:35,013][87424] Updated weights for policy 0, policy_version 231667 (0.0009) -[2023-11-28 06:16:35,265][87426] Updated weights for policy 1, policy_version 231330 (0.0011) -[2023-11-28 06:16:35,395][87424] Updated weights for policy 0, policy_version 231677 (0.0008) -[2023-11-28 06:16:35,640][87426] Updated weights for policy 1, policy_version 231340 (0.0009) -[2023-11-28 06:16:36,021][87426] Updated weights for policy 1, policy_version 231350 (0.0007) -[2023-11-28 06:16:36,393][87426] Updated weights for policy 1, policy_version 231360 (0.0007) -[2023-11-28 06:16:37,674][87424] Updated weights for policy 0, policy_version 231687 (0.0011) -[2023-11-28 06:16:38,056][87424] Updated weights for policy 0, policy_version 231697 (0.0011) -[2023-11-28 06:16:38,439][87424] Updated weights for policy 0, policy_version 231707 (0.0008) -[2023-11-28 06:16:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 118538240. Throughput: 0: 2682.8, 1: 2741.6. Samples: 118559260. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:38,445][86177] Avg episode reward: [(0, '-512.010'), (1, '-524.690')] -[2023-11-28 06:16:38,791][87426] Updated weights for policy 1, policy_version 231370 (0.0011) -[2023-11-28 06:16:39,161][87426] Updated weights for policy 1, policy_version 231380 (0.0011) -[2023-11-28 06:16:39,543][87426] Updated weights for policy 1, policy_version 231390 (0.0011) -[2023-11-28 06:16:40,944][87424] Updated weights for policy 0, policy_version 231717 (0.0008) -[2023-11-28 06:16:41,326][87424] Updated weights for policy 0, policy_version 231727 (0.0007) -[2023-11-28 06:16:41,710][87424] Updated weights for policy 0, policy_version 231737 (0.0008) -[2023-11-28 06:16:42,098][87426] Updated weights for policy 1, policy_version 231400 (0.0009) -[2023-11-28 06:16:42,474][87426] Updated weights for policy 1, policy_version 231410 (0.0013) -[2023-11-28 06:16:42,852][87426] Updated weights for policy 1, policy_version 231420 (0.0008) -[2023-11-28 06:16:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118571008. Throughput: 0: 2684.5, 1: 2723.2. Samples: 118581796. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:43,446][86177] Avg episode reward: [(0, '-512.230'), (1, '-525.240')] -[2023-11-28 06:16:44,116][87424] Updated weights for policy 0, policy_version 231747 (0.0010) -[2023-11-28 06:16:44,496][87424] Updated weights for policy 0, policy_version 231757 (0.0011) -[2023-11-28 06:16:44,879][87424] Updated weights for policy 0, policy_version 231767 (0.0010) -[2023-11-28 06:16:45,221][87426] Updated weights for policy 1, policy_version 231430 (0.0010) -[2023-11-28 06:16:45,598][87426] Updated weights for policy 1, policy_version 231440 (0.0012) -[2023-11-28 06:16:45,981][87426] Updated weights for policy 1, policy_version 231450 (0.0012) -[2023-11-28 06:16:46,779][87424] Updated weights for policy 0, policy_version 231777 (0.0011) -[2023-11-28 06:16:47,166][87424] Updated weights for policy 0, policy_version 231787 (0.0010) -[2023-11-28 06:16:47,547][87424] Updated weights for policy 0, policy_version 231797 (0.0009) -[2023-11-28 06:16:47,927][87424] Updated weights for policy 0, policy_version 231807 (0.0012) -[2023-11-28 06:16:47,936][87426] Updated weights for policy 1, policy_version 231460 (0.0012) -[2023-11-28 06:16:48,310][87426] Updated weights for policy 1, policy_version 231470 (0.0012) -[2023-11-28 06:16:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118595584. Throughput: 0: 2720.4, 1: 2716.9. Samples: 118607200. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:48,445][86177] Avg episode reward: [(0, '-516.980'), (1, '-521.100')] -[2023-11-28 06:16:48,691][87426] Updated weights for policy 1, policy_version 231480 (0.0012) -[2023-11-28 06:16:49,704][87424] Updated weights for policy 0, policy_version 231817 (0.0011) -[2023-11-28 06:16:50,082][87424] Updated weights for policy 0, policy_version 231827 (0.0009) -[2023-11-28 06:16:50,466][87424] Updated weights for policy 0, policy_version 231837 (0.0011) -[2023-11-28 06:16:51,138][87426] Updated weights for policy 1, policy_version 231490 (0.0011) -[2023-11-28 06:16:51,504][87426] Updated weights for policy 1, policy_version 231500 (0.0012) -[2023-11-28 06:16:51,879][87426] Updated weights for policy 1, policy_version 231510 (0.0010) -[2023-11-28 06:16:52,262][87426] Updated weights for policy 1, policy_version 231520 (0.0011) -[2023-11-28 06:16:52,715][87424] Updated weights for policy 0, policy_version 231847 (0.0009) -[2023-11-28 06:16:53,083][87424] Updated weights for policy 0, policy_version 231857 (0.0010) -[2023-11-28 06:16:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 118620160. Throughput: 0: 2769.3, 1: 2722.5. Samples: 118640960. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:53,445][86177] Avg episode reward: [(0, '-512.870'), (1, '-516.910')] -[2023-11-28 06:16:53,470][87424] Updated weights for policy 0, policy_version 231867 (0.0012) -[2023-11-28 06:16:54,208][87426] Updated weights for policy 1, policy_version 231530 (0.0007) -[2023-11-28 06:16:54,588][87426] Updated weights for policy 1, policy_version 231540 (0.0007) -[2023-11-28 06:16:54,976][87426] Updated weights for policy 1, policy_version 231550 (0.0007) -[2023-11-28 06:16:56,038][87424] Updated weights for policy 0, policy_version 231877 (0.0009) -[2023-11-28 06:16:56,426][87424] Updated weights for policy 0, policy_version 231887 (0.0009) -[2023-11-28 06:16:56,819][87424] Updated weights for policy 0, policy_version 231897 (0.0007) -[2023-11-28 06:16:57,018][87426] Updated weights for policy 1, policy_version 231560 (0.0011) -[2023-11-28 06:16:57,398][87426] Updated weights for policy 1, policy_version 231570 (0.0010) -[2023-11-28 06:16:57,780][87426] Updated weights for policy 1, policy_version 231580 (0.0007) -[2023-11-28 06:16:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 118652928. Throughput: 0: 2758.0, 1: 2730.9. Samples: 118664444. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:16:58,445][86177] Avg episode reward: [(0, '-512.360'), (1, '-519.090')] -[2023-11-28 06:16:58,616][87424] Updated weights for policy 0, policy_version 231907 (0.0009) -[2023-11-28 06:16:59,007][87424] Updated weights for policy 0, policy_version 231917 (0.0012) -[2023-11-28 06:16:59,401][87424] Updated weights for policy 0, policy_version 231927 (0.0011) -[2023-11-28 06:17:00,074][87426] Updated weights for policy 1, policy_version 231590 (0.0010) -[2023-11-28 06:17:00,449][87426] Updated weights for policy 1, policy_version 231600 (0.0011) -[2023-11-28 06:17:00,829][87426] Updated weights for policy 1, policy_version 231610 (0.0011) -[2023-11-28 06:17:01,918][87424] Updated weights for policy 0, policy_version 231937 (0.0012) -[2023-11-28 06:17:02,295][87424] Updated weights for policy 0, policy_version 231947 (0.0008) -[2023-11-28 06:17:02,680][87424] Updated weights for policy 0, policy_version 231957 (0.0007) -[2023-11-28 06:17:03,062][87424] Updated weights for policy 0, policy_version 231967 (0.0008) -[2023-11-28 06:17:03,356][87426] Updated weights for policy 1, policy_version 231620 (0.0010) -[2023-11-28 06:17:03,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118677504. Throughput: 0: 2754.9, 1: 2709.9. Samples: 118688496. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:17:03,446][86177] Avg episode reward: [(0, '-514.310'), (1, '-520.120')] -[2023-11-28 06:17:03,725][87426] Updated weights for policy 1, policy_version 231630 (0.0008) -[2023-11-28 06:17:04,111][87426] Updated weights for policy 1, policy_version 231640 (0.0009) -[2023-11-28 06:17:05,579][87424] Updated weights for policy 0, policy_version 231977 (0.0011) -[2023-11-28 06:17:05,958][87424] Updated weights for policy 0, policy_version 231987 (0.0011) -[2023-11-28 06:17:06,344][87424] Updated weights for policy 0, policy_version 231997 (0.0008) -[2023-11-28 06:17:06,679][87426] Updated weights for policy 1, policy_version 231650 (0.0010) -[2023-11-28 06:17:07,056][87426] Updated weights for policy 1, policy_version 231660 (0.0012) -[2023-11-28 06:17:07,433][87426] Updated weights for policy 1, policy_version 231670 (0.0007) -[2023-11-28 06:17:07,814][87426] Updated weights for policy 1, policy_version 231680 (0.0007) -[2023-11-28 06:17:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 118702080. Throughput: 0: 2731.6, 1: 2682.9. Samples: 118720012. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:17:08,446][86177] Avg episode reward: [(0, '-506.980'), (1, '-522.420')] -[2023-11-28 06:17:08,811][87424] Updated weights for policy 0, policy_version 232007 (0.0012) -[2023-11-28 06:17:09,198][87424] Updated weights for policy 0, policy_version 232017 (0.0012) -[2023-11-28 06:17:09,578][87424] Updated weights for policy 0, policy_version 232027 (0.0012) -[2023-11-28 06:17:09,916][87426] Updated weights for policy 1, policy_version 231690 (0.0011) -[2023-11-28 06:17:10,300][87426] Updated weights for policy 1, policy_version 231700 (0.0012) -[2023-11-28 06:17:10,684][87426] Updated weights for policy 1, policy_version 231710 (0.0012) -[2023-11-28 06:17:11,498][87424] Updated weights for policy 0, policy_version 232037 (0.0011) -[2023-11-28 06:17:11,887][87424] Updated weights for policy 0, policy_version 232047 (0.0011) -[2023-11-28 06:17:12,269][87424] Updated weights for policy 0, policy_version 232057 (0.0011) -[2023-11-28 06:17:12,492][87426] Updated weights for policy 1, policy_version 231720 (0.0010) -[2023-11-28 06:17:12,878][87426] Updated weights for policy 1, policy_version 231730 (0.0008) -[2023-11-28 06:17:13,255][87426] Updated weights for policy 1, policy_version 231740 (0.0012) -[2023-11-28 06:17:13,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118734848. Throughput: 0: 2712.1, 1: 2654.4. Samples: 118743308. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:17:13,445][86177] Avg episode reward: [(0, '-504.810'), (1, '-532.370')] -[2023-11-28 06:17:14,196][87424] Updated weights for policy 0, policy_version 232067 (0.0011) -[2023-11-28 06:17:14,576][87424] Updated weights for policy 0, policy_version 232077 (0.0011) -[2023-11-28 06:17:14,957][87424] Updated weights for policy 0, policy_version 232087 (0.0011) -[2023-11-28 06:17:15,804][87426] Updated weights for policy 1, policy_version 231750 (0.0010) -[2023-11-28 06:17:16,183][87426] Updated weights for policy 1, policy_version 231760 (0.0008) -[2023-11-28 06:17:16,569][87426] Updated weights for policy 1, policy_version 231770 (0.0007) -[2023-11-28 06:17:16,894][87424] Updated weights for policy 0, policy_version 232097 (0.0010) -[2023-11-28 06:17:17,271][87424] Updated weights for policy 0, policy_version 232107 (0.0012) -[2023-11-28 06:17:17,654][87424] Updated weights for policy 0, policy_version 232117 (0.0012) -[2023-11-28 06:17:18,036][87424] Updated weights for policy 0, policy_version 232127 (0.0008) -[2023-11-28 06:17:18,282][87426] Updated weights for policy 1, policy_version 231780 (0.0009) -[2023-11-28 06:17:18,445][86177] Fps is (10 sec: 5734.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 118759424. Throughput: 0: 2699.6, 1: 2663.8. Samples: 118768676. Policy #0 lag: (min: 46.0, avg: 60.1, max: 87.0) -[2023-11-28 06:17:18,446][86177] Avg episode reward: [(0, '-498.190'), (1, '-527.790')] -[2023-11-28 06:17:18,664][87426] Updated weights for policy 1, policy_version 231790 (0.0011) -[2023-11-28 06:17:19,046][87426] Updated weights for policy 1, policy_version 231800 (0.0011) -[2023-11-28 06:17:20,316][87424] Updated weights for policy 0, policy_version 232137 (0.0009) -[2023-11-28 06:17:20,706][87424] Updated weights for policy 0, policy_version 232147 (0.0009) -[2023-11-28 06:17:21,079][87424] Updated weights for policy 0, policy_version 232157 (0.0012) -[2023-11-28 06:17:21,317][87426] Updated weights for policy 1, policy_version 231810 (0.0012) -[2023-11-28 06:17:21,691][87426] Updated weights for policy 1, policy_version 231820 (0.0011) -[2023-11-28 06:17:22,071][87426] Updated weights for policy 1, policy_version 231830 (0.0009) -[2023-11-28 06:17:22,450][87426] Updated weights for policy 1, policy_version 231840 (0.0009) -[2023-11-28 06:17:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 118784000. Throughput: 0: 2683.5, 1: 2676.5. Samples: 118800460. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:17:23,445][86177] Avg episode reward: [(0, '-495.820'), (1, '-522.700')] -[2023-11-28 06:17:23,619][87424] Updated weights for policy 0, policy_version 232167 (0.0012) -[2023-11-28 06:17:24,005][87424] Updated weights for policy 0, policy_version 232177 (0.0011) -[2023-11-28 06:17:24,293][87426] Updated weights for policy 1, policy_version 231850 (0.0008) -[2023-11-28 06:17:24,386][87424] Updated weights for policy 0, policy_version 232187 (0.0010) -[2023-11-28 06:17:24,672][87426] Updated weights for policy 1, policy_version 231860 (0.0010) -[2023-11-28 06:17:25,053][87426] Updated weights for policy 1, policy_version 231870 (0.0011) -[2023-11-28 06:17:26,774][87424] Updated weights for policy 0, policy_version 232197 (0.0009) -[2023-11-28 06:17:27,162][87424] Updated weights for policy 0, policy_version 232207 (0.0011) -[2023-11-28 06:17:27,317][87426] Updated weights for policy 1, policy_version 231880 (0.0008) -[2023-11-28 06:17:27,526][87424] Updated weights for policy 0, policy_version 232217 (0.0011) -[2023-11-28 06:17:27,695][87426] Updated weights for policy 1, policy_version 231890 (0.0007) -[2023-11-28 06:17:28,079][87426] Updated weights for policy 1, policy_version 231900 (0.0007) -[2023-11-28 06:17:28,444][86177] Fps is (10 sec: 5734.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 118816768. Throughput: 0: 2691.5, 1: 2695.2. Samples: 118824196. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:17:28,445][86177] Avg episode reward: [(0, '-501.390'), (1, '-522.180')] -[2023-11-28 06:17:29,488][87424] Updated weights for policy 0, policy_version 232227 (0.0011) -[2023-11-28 06:17:29,866][87424] Updated weights for policy 0, policy_version 232237 (0.0012) -[2023-11-28 06:17:30,248][87424] Updated weights for policy 0, policy_version 232247 (0.0012) -[2023-11-28 06:17:30,623][87426] Updated weights for policy 1, policy_version 231910 (0.0008) -[2023-11-28 06:17:30,994][87426] Updated weights for policy 1, policy_version 231920 (0.0008) -[2023-11-28 06:17:31,376][87426] Updated weights for policy 1, policy_version 231930 (0.0007) -[2023-11-28 06:17:32,682][87424] Updated weights for policy 0, policy_version 232257 (0.0011) -[2023-11-28 06:17:33,068][87424] Updated weights for policy 0, policy_version 232267 (0.0009) -[2023-11-28 06:17:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 118833152. Throughput: 0: 2686.3, 1: 2667.2. Samples: 118848108. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:17:33,445][86177] Avg episode reward: [(0, '-504.200'), (1, '-507.540')] -[2023-11-28 06:17:33,457][87424] Updated weights for policy 0, policy_version 232277 (0.0010) -[2023-11-28 06:17:33,837][87424] Updated weights for policy 0, policy_version 232287 (0.0011) -[2023-11-28 06:17:33,854][87426] Updated weights for policy 1, policy_version 231940 (0.0007) -[2023-11-28 06:17:34,228][87426] Updated weights for policy 1, policy_version 231950 (0.0007) -[2023-11-28 06:17:34,614][87426] Updated weights for policy 1, policy_version 231960 (0.0007) -[2023-11-28 06:17:35,969][87424] Updated weights for policy 0, policy_version 232297 (0.0008) -[2023-11-28 06:17:36,359][87424] Updated weights for policy 0, policy_version 232307 (0.0011) -[2023-11-28 06:17:36,730][87424] Updated weights for policy 0, policy_version 232317 (0.0010) -[2023-11-28 06:17:36,732][87426] Updated weights for policy 1, policy_version 231970 (0.0009) -[2023-11-28 06:17:37,103][87426] Updated weights for policy 1, policy_version 231980 (0.0012) -[2023-11-28 06:17:37,479][87426] Updated weights for policy 1, policy_version 231990 (0.0011) -[2023-11-28 06:17:37,846][87426] Updated weights for policy 1, policy_version 232000 (0.0012) -[2023-11-28 06:17:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 118865920. Throughput: 0: 2673.3, 1: 2661.2. Samples: 118881012. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:17:38,445][86177] Avg episode reward: [(0, '-509.030'), (1, '-519.680')] -[2023-11-28 06:17:38,523][87424] Updated weights for policy 0, policy_version 232327 (0.0010) -[2023-11-28 06:17:38,906][87424] Updated weights for policy 0, policy_version 232337 (0.0011) -[2023-11-28 06:17:39,284][87424] Updated weights for policy 0, policy_version 232347 (0.0009) -[2023-11-28 06:17:40,410][87426] Updated weights for policy 1, policy_version 232010 (0.0012) -[2023-11-28 06:17:40,782][87426] Updated weights for policy 1, policy_version 232020 (0.0010) -[2023-11-28 06:17:41,165][87426] Updated weights for policy 1, policy_version 232030 (0.0008) -[2023-11-28 06:17:41,524][87424] Updated weights for policy 0, policy_version 232357 (0.0012) -[2023-11-28 06:17:41,917][87424] Updated weights for policy 0, policy_version 232367 (0.0012) -[2023-11-28 06:17:42,299][87424] Updated weights for policy 0, policy_version 232377 (0.0012) -[2023-11-28 06:17:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 118890496. Throughput: 0: 2692.6, 1: 2646.6. Samples: 118904708. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:17:43,445][86177] Avg episode reward: [(0, '-512.170'), (1, '-518.570')] -[2023-11-28 06:17:43,707][87426] Updated weights for policy 1, policy_version 232040 (0.0012) -[2023-11-28 06:17:44,100][87426] Updated weights for policy 1, policy_version 232050 (0.0012) -[2023-11-28 06:17:44,481][87426] Updated weights for policy 1, policy_version 232060 (0.0012) -[2023-11-28 06:17:44,816][87424] Updated weights for policy 0, policy_version 232387 (0.0011) -[2023-11-28 06:17:45,198][87424] Updated weights for policy 0, policy_version 232397 (0.0007) -[2023-11-28 06:17:45,579][87424] Updated weights for policy 0, policy_version 232407 (0.0008) -[2023-11-28 06:17:46,851][87426] Updated weights for policy 1, policy_version 232070 (0.0010) -[2023-11-28 06:17:47,222][87426] Updated weights for policy 1, policy_version 232080 (0.0008) -[2023-11-28 06:17:47,594][87424] Updated weights for policy 0, policy_version 232417 (0.0010) -[2023-11-28 06:17:47,605][87426] Updated weights for policy 1, policy_version 232090 (0.0008) -[2023-11-28 06:17:47,986][87424] Updated weights for policy 0, policy_version 232427 (0.0012) -[2023-11-28 06:17:48,365][87424] Updated weights for policy 0, policy_version 232437 (0.0008) -[2023-11-28 06:17:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 118915072. Throughput: 0: 2683.5, 1: 2650.7. Samples: 118928532. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:17:48,445][86177] Avg episode reward: [(0, '-510.820'), (1, '-527.070')] -[2023-11-28 06:17:48,743][87424] Updated weights for policy 0, policy_version 232447 (0.0008) -[2023-11-28 06:17:49,517][87426] Updated weights for policy 1, policy_version 232100 (0.0009) -[2023-11-28 06:17:49,901][87426] Updated weights for policy 1, policy_version 232110 (0.0012) -[2023-11-28 06:17:50,282][87426] Updated weights for policy 1, policy_version 232120 (0.0012) -[2023-11-28 06:17:50,865][87424] Updated weights for policy 0, policy_version 232457 (0.0010) -[2023-11-28 06:17:51,248][87424] Updated weights for policy 0, policy_version 232467 (0.0012) -[2023-11-28 06:17:51,647][87424] Updated weights for policy 0, policy_version 232477 (0.0012) -[2023-11-28 06:17:52,324][87426] Updated weights for policy 1, policy_version 232130 (0.0012) -[2023-11-28 06:17:52,696][87426] Updated weights for policy 1, policy_version 232140 (0.0012) -[2023-11-28 06:17:53,073][87426] Updated weights for policy 1, policy_version 232150 (0.0009) -[2023-11-28 06:17:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 118939648. Throughput: 0: 2697.7, 1: 2663.8. Samples: 118961280. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:17:53,445][86177] Avg episode reward: [(0, '-508.040'), (1, '-537.370')] -[2023-11-28 06:17:53,460][87426] Updated weights for policy 1, policy_version 232160 (0.0010) -[2023-11-28 06:17:53,816][87424] Updated weights for policy 0, policy_version 232487 (0.0012) -[2023-11-28 06:17:54,201][87424] Updated weights for policy 0, policy_version 232497 (0.0012) -[2023-11-28 06:17:54,597][87424] Updated weights for policy 0, policy_version 232507 (0.0012) -[2023-11-28 06:17:55,486][87426] Updated weights for policy 1, policy_version 232170 (0.0008) -[2023-11-28 06:17:55,865][87426] Updated weights for policy 1, policy_version 232180 (0.0007) -[2023-11-28 06:17:56,241][87426] Updated weights for policy 1, policy_version 232190 (0.0007) -[2023-11-28 06:17:57,038][87424] Updated weights for policy 0, policy_version 232517 (0.0008) -[2023-11-28 06:17:57,430][87424] Updated weights for policy 0, policy_version 232527 (0.0007) -[2023-11-28 06:17:57,808][87424] Updated weights for policy 0, policy_version 232537 (0.0009) -[2023-11-28 06:17:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 118972416. Throughput: 0: 2690.8, 1: 2691.5. Samples: 118985512. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:17:58,445][86177] Avg episode reward: [(0, '-504.670'), (1, '-523.340')] -[2023-11-28 06:17:58,638][87426] Updated weights for policy 1, policy_version 232200 (0.0011) -[2023-11-28 06:17:59,024][87426] Updated weights for policy 1, policy_version 232210 (0.0012) -[2023-11-28 06:17:59,401][87426] Updated weights for policy 1, policy_version 232220 (0.0012) -[2023-11-28 06:17:59,894][87424] Updated weights for policy 0, policy_version 232547 (0.0009) -[2023-11-28 06:18:00,271][87424] Updated weights for policy 0, policy_version 232557 (0.0011) -[2023-11-28 06:18:00,649][87424] Updated weights for policy 0, policy_version 232567 (0.0009) -[2023-11-28 06:18:01,423][87426] Updated weights for policy 1, policy_version 232230 (0.0009) -[2023-11-28 06:18:01,806][87426] Updated weights for policy 1, policy_version 232240 (0.0010) -[2023-11-28 06:18:02,191][87426] Updated weights for policy 1, policy_version 232250 (0.0009) -[2023-11-28 06:18:03,011][87424] Updated weights for policy 0, policy_version 232577 (0.0008) -[2023-11-28 06:18:03,385][87424] Updated weights for policy 0, policy_version 232587 (0.0011) -[2023-11-28 06:18:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 118996992. Throughput: 0: 2693.9, 1: 2665.9. Samples: 119009864. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:18:03,445][86177] Avg episode reward: [(0, '-501.050'), (1, '-523.020')] -[2023-11-28 06:18:03,769][87424] Updated weights for policy 0, policy_version 232597 (0.0009) -[2023-11-28 06:18:04,119][87426] Updated weights for policy 1, policy_version 232260 (0.0011) -[2023-11-28 06:18:04,155][87424] Updated weights for policy 0, policy_version 232607 (0.0007) -[2023-11-28 06:18:04,498][87426] Updated weights for policy 1, policy_version 232270 (0.0012) -[2023-11-28 06:18:04,877][87426] Updated weights for policy 1, policy_version 232280 (0.0012) -[2023-11-28 06:18:06,376][87424] Updated weights for policy 0, policy_version 232617 (0.0011) -[2023-11-28 06:18:06,766][87424] Updated weights for policy 0, policy_version 232627 (0.0012) -[2023-11-28 06:18:07,147][87424] Updated weights for policy 0, policy_version 232637 (0.0011) -[2023-11-28 06:18:07,245][87426] Updated weights for policy 1, policy_version 232290 (0.0011) -[2023-11-28 06:18:07,624][87426] Updated weights for policy 1, policy_version 232300 (0.0011) -[2023-11-28 06:18:08,011][87426] Updated weights for policy 1, policy_version 232310 (0.0011) -[2023-11-28 06:18:08,393][87426] Updated weights for policy 1, policy_version 232320 (0.0007) -[2023-11-28 06:18:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 119029760. Throughput: 0: 2692.9, 1: 2702.9. Samples: 119043268. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:18:08,445][86177] Avg episode reward: [(0, '-510.390'), (1, '-523.070')] -[2023-11-28 06:18:09,041][87424] Updated weights for policy 0, policy_version 232647 (0.0010) -[2023-11-28 06:18:09,426][87424] Updated weights for policy 0, policy_version 232657 (0.0008) -[2023-11-28 06:18:09,805][87424] Updated weights for policy 0, policy_version 232667 (0.0008) -[2023-11-28 06:18:10,775][87426] Updated weights for policy 1, policy_version 232330 (0.0012) -[2023-11-28 06:18:11,157][87426] Updated weights for policy 1, policy_version 232340 (0.0011) -[2023-11-28 06:18:11,535][87426] Updated weights for policy 1, policy_version 232350 (0.0011) -[2023-11-28 06:18:12,312][87424] Updated weights for policy 0, policy_version 232677 (0.0011) -[2023-11-28 06:18:12,686][87424] Updated weights for policy 0, policy_version 232687 (0.0012) -[2023-11-28 06:18:13,066][87424] Updated weights for policy 0, policy_version 232697 (0.0010) -[2023-11-28 06:18:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 119054336. Throughput: 0: 2707.4, 1: 2696.2. Samples: 119067356. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:18:13,445][86177] Avg episode reward: [(0, '-512.470'), (1, '-515.310')] -[2023-11-28 06:18:13,892][87426] Updated weights for policy 1, policy_version 232360 (0.0008) -[2023-11-28 06:18:14,270][87426] Updated weights for policy 1, policy_version 232370 (0.0010) -[2023-11-28 06:18:14,653][87426] Updated weights for policy 1, policy_version 232380 (0.0012) -[2023-11-28 06:18:14,800][87424] Updated weights for policy 0, policy_version 232707 (0.0009) -[2023-11-28 06:18:15,176][87424] Updated weights for policy 0, policy_version 232717 (0.0012) -[2023-11-28 06:18:15,557][87424] Updated weights for policy 0, policy_version 232727 (0.0012) -[2023-11-28 06:18:16,591][87426] Updated weights for policy 1, policy_version 232390 (0.0011) -[2023-11-28 06:18:16,975][87426] Updated weights for policy 1, policy_version 232400 (0.0012) -[2023-11-28 06:18:17,354][87426] Updated weights for policy 1, policy_version 232410 (0.0010) -[2023-11-28 06:18:18,060][87424] Updated weights for policy 0, policy_version 232737 (0.0012) -[2023-11-28 06:18:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 119078912. Throughput: 0: 2694.0, 1: 2725.9. Samples: 119092004. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:18:18,445][86177] Avg episode reward: [(0, '-517.850'), (1, '-530.110')] -[2023-11-28 06:18:18,445][87424] Updated weights for policy 0, policy_version 232747 (0.0011) -[2023-11-28 06:18:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000232416_59498496.pth... -[2023-11-28 06:18:18,502][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000229888_58851328.pth -[2023-11-28 06:18:18,829][87424] Updated weights for policy 0, policy_version 232757 (0.0008) -[2023-11-28 06:18:18,902][87426] Updated weights for policy 1, policy_version 232420 (0.0010) -[2023-11-28 06:18:19,208][87424] Updated weights for policy 0, policy_version 232767 (0.0010) -[2023-11-28 06:18:19,246][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000232768_59588608.pth... -[2023-11-28 06:18:19,270][87426] Updated weights for policy 1, policy_version 232430 (0.0010) -[2023-11-28 06:18:19,291][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000230240_58941440.pth -[2023-11-28 06:18:19,646][87426] Updated weights for policy 1, policy_version 232440 (0.0008) -[2023-11-28 06:18:21,478][87424] Updated weights for policy 0, policy_version 232777 (0.0011) -[2023-11-28 06:18:21,852][87424] Updated weights for policy 0, policy_version 232787 (0.0011) -[2023-11-28 06:18:22,021][87426] Updated weights for policy 1, policy_version 232450 (0.0011) -[2023-11-28 06:18:22,235][87424] Updated weights for policy 0, policy_version 232797 (0.0011) -[2023-11-28 06:18:22,401][87426] Updated weights for policy 1, policy_version 232460 (0.0011) -[2023-11-28 06:18:22,778][87426] Updated weights for policy 1, policy_version 232470 (0.0011) -[2023-11-28 06:18:23,154][87426] Updated weights for policy 1, policy_version 232480 (0.0011) -[2023-11-28 06:18:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 119111680. Throughput: 0: 2667.9, 1: 2728.4. Samples: 119123844. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:18:23,445][86177] Avg episode reward: [(0, '-518.680'), (1, '-529.260')] -[2023-11-28 06:18:24,501][87424] Updated weights for policy 0, policy_version 232807 (0.0012) -[2023-11-28 06:18:24,885][87424] Updated weights for policy 0, policy_version 232817 (0.0011) -[2023-11-28 06:18:25,262][87424] Updated weights for policy 0, policy_version 232827 (0.0011) -[2023-11-28 06:18:25,330][87426] Updated weights for policy 1, policy_version 232490 (0.0011) -[2023-11-28 06:18:25,710][87426] Updated weights for policy 1, policy_version 232500 (0.0007) -[2023-11-28 06:18:26,089][87426] Updated weights for policy 1, policy_version 232510 (0.0007) -[2023-11-28 06:18:27,117][87424] Updated weights for policy 0, policy_version 232837 (0.0011) -[2023-11-28 06:18:27,486][87424] Updated weights for policy 0, policy_version 232847 (0.0011) -[2023-11-28 06:18:27,871][87424] Updated weights for policy 0, policy_version 232857 (0.0007) -[2023-11-28 06:18:28,134][87426] Updated weights for policy 1, policy_version 232520 (0.0008) -[2023-11-28 06:18:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 119136256. Throughput: 0: 2678.7, 1: 2766.0. Samples: 119149720. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:18:28,445][86177] Avg episode reward: [(0, '-507.360'), (1, '-522.510')] -[2023-11-28 06:18:28,517][87426] Updated weights for policy 1, policy_version 232530 (0.0008) -[2023-11-28 06:18:28,902][87426] Updated weights for policy 1, policy_version 232540 (0.0008) -[2023-11-28 06:18:30,030][87424] Updated weights for policy 0, policy_version 232867 (0.0008) -[2023-11-28 06:18:30,421][87424] Updated weights for policy 0, policy_version 232877 (0.0009) -[2023-11-28 06:18:30,796][87424] Updated weights for policy 0, policy_version 232887 (0.0009) -[2023-11-28 06:18:31,032][87426] Updated weights for policy 1, policy_version 232550 (0.0009) -[2023-11-28 06:18:31,419][87426] Updated weights for policy 1, policy_version 232560 (0.0009) -[2023-11-28 06:18:31,800][87426] Updated weights for policy 1, policy_version 232570 (0.0008) -[2023-11-28 06:18:33,230][87424] Updated weights for policy 0, policy_version 232897 (0.0008) -[2023-11-28 06:18:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 119160832. Throughput: 0: 2712.7, 1: 2775.7. Samples: 119175512. Policy #0 lag: (min: 31.0, avg: 52.9, max: 83.0) -[2023-11-28 06:18:33,445][86177] Avg episode reward: [(0, '-508.760'), (1, '-519.550')] -[2023-11-28 06:18:33,618][87424] Updated weights for policy 0, policy_version 232907 (0.0007) -[2023-11-28 06:18:33,707][87426] Updated weights for policy 1, policy_version 232580 (0.0008) -[2023-11-28 06:18:33,992][87424] Updated weights for policy 0, policy_version 232917 (0.0008) -[2023-11-28 06:18:34,087][87426] Updated weights for policy 1, policy_version 232590 (0.0009) -[2023-11-28 06:18:34,373][87424] Updated weights for policy 0, policy_version 232927 (0.0007) -[2023-11-28 06:18:34,463][87426] Updated weights for policy 1, policy_version 232600 (0.0012) -[2023-11-28 06:18:36,557][87426] Updated weights for policy 1, policy_version 232610 (0.0011) -[2023-11-28 06:18:36,604][87424] Updated weights for policy 0, policy_version 232937 (0.0007) -[2023-11-28 06:18:36,923][87426] Updated weights for policy 1, policy_version 232620 (0.0010) -[2023-11-28 06:18:36,977][87424] Updated weights for policy 0, policy_version 232947 (0.0010) -[2023-11-28 06:18:37,300][87426] Updated weights for policy 1, policy_version 232630 (0.0011) -[2023-11-28 06:18:37,360][87424] Updated weights for policy 0, policy_version 232957 (0.0011) -[2023-11-28 06:18:37,678][87426] Updated weights for policy 1, policy_version 232640 (0.0011) -[2023-11-28 06:18:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 119193600. Throughput: 0: 2713.2, 1: 2764.4. Samples: 119207768. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:18:38,445][86177] Avg episode reward: [(0, '-512.170'), (1, '-513.660')] -[2023-11-28 06:18:39,308][87424] Updated weights for policy 0, policy_version 232967 (0.0009) -[2023-11-28 06:18:39,429][87426] Updated weights for policy 1, policy_version 232650 (0.0011) -[2023-11-28 06:18:39,688][87424] Updated weights for policy 0, policy_version 232977 (0.0012) -[2023-11-28 06:18:39,814][87426] Updated weights for policy 1, policy_version 232660 (0.0008) -[2023-11-28 06:18:40,071][87424] Updated weights for policy 0, policy_version 232987 (0.0012) -[2023-11-28 06:18:40,184][87426] Updated weights for policy 1, policy_version 232670 (0.0012) -[2023-11-28 06:18:42,584][87426] Updated weights for policy 1, policy_version 232680 (0.0009) -[2023-11-28 06:18:42,695][87424] Updated weights for policy 0, policy_version 232997 (0.0012) -[2023-11-28 06:18:42,977][87426] Updated weights for policy 1, policy_version 232690 (0.0010) -[2023-11-28 06:18:43,082][87424] Updated weights for policy 0, policy_version 233007 (0.0012) -[2023-11-28 06:18:43,352][87426] Updated weights for policy 1, policy_version 232700 (0.0010) -[2023-11-28 06:18:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 119209984. Throughput: 0: 2705.8, 1: 2782.7. Samples: 119232492. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:18:43,445][86177] Avg episode reward: [(0, '-510.200'), (1, '-513.120')] -[2023-11-28 06:18:43,461][87424] Updated weights for policy 0, policy_version 233017 (0.0012) -[2023-11-28 06:18:45,688][87426] Updated weights for policy 1, policy_version 232710 (0.0011) -[2023-11-28 06:18:45,774][87424] Updated weights for policy 0, policy_version 233027 (0.0012) -[2023-11-28 06:18:46,064][87426] Updated weights for policy 1, policy_version 232720 (0.0010) -[2023-11-28 06:18:46,149][87424] Updated weights for policy 0, policy_version 233037 (0.0012) -[2023-11-28 06:18:46,451][87426] Updated weights for policy 1, policy_version 232730 (0.0010) -[2023-11-28 06:18:46,528][87424] Updated weights for policy 0, policy_version 233047 (0.0010) -[2023-11-28 06:18:48,212][87426] Updated weights for policy 1, policy_version 232740 (0.0010) -[2023-11-28 06:18:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 119242752. Throughput: 0: 2679.2, 1: 2808.7. Samples: 119256820. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:18:48,445][86177] Avg episode reward: [(0, '-509.400'), (1, '-514.470')] -[2023-11-28 06:18:48,595][87426] Updated weights for policy 1, policy_version 232750 (0.0007) -[2023-11-28 06:18:48,780][87424] Updated weights for policy 0, policy_version 233057 (0.0007) -[2023-11-28 06:18:48,977][87426] Updated weights for policy 1, policy_version 232760 (0.0011) -[2023-11-28 06:18:49,174][87424] Updated weights for policy 0, policy_version 233067 (0.0008) -[2023-11-28 06:18:49,565][87424] Updated weights for policy 0, policy_version 233077 (0.0008) -[2023-11-28 06:18:49,946][87424] Updated weights for policy 0, policy_version 233087 (0.0010) -[2023-11-28 06:18:51,506][87426] Updated weights for policy 1, policy_version 232770 (0.0010) -[2023-11-28 06:18:51,891][87426] Updated weights for policy 1, policy_version 232780 (0.0011) -[2023-11-28 06:18:52,085][87424] Updated weights for policy 0, policy_version 233097 (0.0011) -[2023-11-28 06:18:52,273][87426] Updated weights for policy 1, policy_version 232790 (0.0012) -[2023-11-28 06:18:52,482][87424] Updated weights for policy 0, policy_version 233107 (0.0011) -[2023-11-28 06:18:52,639][87426] Updated weights for policy 1, policy_version 232800 (0.0011) -[2023-11-28 06:18:52,869][87424] Updated weights for policy 0, policy_version 233117 (0.0011) -[2023-11-28 06:18:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 119275520. Throughput: 0: 2691.3, 1: 2770.4. Samples: 119289044. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:18:53,445][86177] Avg episode reward: [(0, '-501.000'), (1, '-519.140')] -[2023-11-28 06:18:55,007][87426] Updated weights for policy 1, policy_version 232810 (0.0012) -[2023-11-28 06:18:55,098][87424] Updated weights for policy 0, policy_version 233127 (0.0011) -[2023-11-28 06:18:55,380][87426] Updated weights for policy 1, policy_version 232820 (0.0010) -[2023-11-28 06:18:55,475][87424] Updated weights for policy 0, policy_version 233137 (0.0008) -[2023-11-28 06:18:55,767][87426] Updated weights for policy 1, policy_version 232830 (0.0011) -[2023-11-28 06:18:55,861][87424] Updated weights for policy 0, policy_version 233147 (0.0008) -[2023-11-28 06:18:57,538][87426] Updated weights for policy 1, policy_version 232840 (0.0009) -[2023-11-28 06:18:57,924][87426] Updated weights for policy 1, policy_version 232850 (0.0009) -[2023-11-28 06:18:58,265][87424] Updated weights for policy 0, policy_version 233157 (0.0008) -[2023-11-28 06:18:58,297][87426] Updated weights for policy 1, policy_version 232860 (0.0008) -[2023-11-28 06:18:58,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 119291904. Throughput: 0: 2683.2, 1: 2781.3. Samples: 119313260. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:18:58,446][86177] Avg episode reward: [(0, '-496.890'), (1, '-518.020')] -[2023-11-28 06:18:58,651][87424] Updated weights for policy 0, policy_version 233167 (0.0009) -[2023-11-28 06:18:59,036][87424] Updated weights for policy 0, policy_version 233177 (0.0007) -[2023-11-28 06:19:00,397][87426] Updated weights for policy 1, policy_version 232870 (0.0009) -[2023-11-28 06:19:00,773][87426] Updated weights for policy 1, policy_version 232880 (0.0007) -[2023-11-28 06:19:01,157][87426] Updated weights for policy 1, policy_version 232890 (0.0007) -[2023-11-28 06:19:01,252][87424] Updated weights for policy 0, policy_version 233187 (0.0009) -[2023-11-28 06:19:01,634][87424] Updated weights for policy 0, policy_version 233197 (0.0009) -[2023-11-28 06:19:02,016][87424] Updated weights for policy 0, policy_version 233207 (0.0010) -[2023-11-28 06:19:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 119324672. Throughput: 0: 2692.3, 1: 2765.5. Samples: 119337604. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:19:03,445][86177] Avg episode reward: [(0, '-515.630'), (1, '-518.170')] -[2023-11-28 06:19:03,555][87426] Updated weights for policy 1, policy_version 232900 (0.0011) -[2023-11-28 06:19:03,931][87426] Updated weights for policy 1, policy_version 232910 (0.0012) -[2023-11-28 06:19:04,250][87424] Updated weights for policy 0, policy_version 233217 (0.0009) -[2023-11-28 06:19:04,311][87426] Updated weights for policy 1, policy_version 232920 (0.0012) -[2023-11-28 06:19:04,647][87424] Updated weights for policy 0, policy_version 233227 (0.0012) -[2023-11-28 06:19:05,026][87424] Updated weights for policy 0, policy_version 233237 (0.0012) -[2023-11-28 06:19:05,407][87424] Updated weights for policy 0, policy_version 233247 (0.0012) -[2023-11-28 06:19:06,177][87426] Updated weights for policy 1, policy_version 232930 (0.0012) -[2023-11-28 06:19:06,548][87426] Updated weights for policy 1, policy_version 232940 (0.0008) -[2023-11-28 06:19:06,944][87426] Updated weights for policy 1, policy_version 232950 (0.0009) -[2023-11-28 06:19:07,255][87424] Updated weights for policy 0, policy_version 233257 (0.0012) -[2023-11-28 06:19:07,321][87426] Updated weights for policy 1, policy_version 232960 (0.0011) -[2023-11-28 06:19:07,635][87424] Updated weights for policy 0, policy_version 233267 (0.0012) -[2023-11-28 06:19:08,015][87424] Updated weights for policy 0, policy_version 233277 (0.0010) -[2023-11-28 06:19:08,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 119357440. Throughput: 0: 2715.2, 1: 2745.3. Samples: 119369568. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:19:08,445][86177] Avg episode reward: [(0, '-530.660'), (1, '-515.000')] -[2023-11-28 06:19:09,730][87426] Updated weights for policy 1, policy_version 232970 (0.0011) -[2023-11-28 06:19:10,107][87426] Updated weights for policy 1, policy_version 232980 (0.0011) -[2023-11-28 06:19:10,331][87424] Updated weights for policy 0, policy_version 233287 (0.0010) -[2023-11-28 06:19:10,483][87426] Updated weights for policy 1, policy_version 232990 (0.0010) -[2023-11-28 06:19:10,714][87424] Updated weights for policy 0, policy_version 233297 (0.0009) -[2023-11-28 06:19:11,097][87424] Updated weights for policy 0, policy_version 233307 (0.0007) -[2023-11-28 06:19:13,017][87426] Updated weights for policy 1, policy_version 233000 (0.0010) -[2023-11-28 06:19:13,140][87424] Updated weights for policy 0, policy_version 233317 (0.0009) -[2023-11-28 06:19:13,399][87426] Updated weights for policy 1, policy_version 233010 (0.0011) -[2023-11-28 06:19:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 119373824. Throughput: 0: 2703.2, 1: 2715.6. Samples: 119393568. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:19:13,445][86177] Avg episode reward: [(0, '-535.260'), (1, '-528.580')] -[2023-11-28 06:19:13,521][87424] Updated weights for policy 0, policy_version 233327 (0.0012) -[2023-11-28 06:19:13,771][87426] Updated weights for policy 1, policy_version 233020 (0.0007) -[2023-11-28 06:19:13,914][87424] Updated weights for policy 0, policy_version 233337 (0.0011) -[2023-11-28 06:19:15,950][87426] Updated weights for policy 1, policy_version 233030 (0.0010) -[2023-11-28 06:19:15,953][87424] Updated weights for policy 0, policy_version 233347 (0.0011) -[2023-11-28 06:19:16,329][87426] Updated weights for policy 1, policy_version 233040 (0.0011) -[2023-11-28 06:19:16,341][87424] Updated weights for policy 0, policy_version 233357 (0.0009) -[2023-11-28 06:19:16,698][87426] Updated weights for policy 1, policy_version 233050 (0.0011) -[2023-11-28 06:19:16,721][87424] Updated weights for policy 0, policy_version 233367 (0.0007) -[2023-11-28 06:19:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 119406592. Throughput: 0: 2664.0, 1: 2717.2. Samples: 119417668. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:19:18,446][86177] Avg episode reward: [(0, '-532.710'), (1, '-531.750')] -[2023-11-28 06:19:18,977][87426] Updated weights for policy 1, policy_version 233060 (0.0012) -[2023-11-28 06:19:19,123][87424] Updated weights for policy 0, policy_version 233377 (0.0011) -[2023-11-28 06:19:19,357][87426] Updated weights for policy 1, policy_version 233070 (0.0012) -[2023-11-28 06:19:19,495][87424] Updated weights for policy 0, policy_version 233387 (0.0011) -[2023-11-28 06:19:19,736][87426] Updated weights for policy 1, policy_version 233080 (0.0012) -[2023-11-28 06:19:19,872][87424] Updated weights for policy 0, policy_version 233397 (0.0011) -[2023-11-28 06:19:20,258][87424] Updated weights for policy 0, policy_version 233407 (0.0010) -[2023-11-28 06:19:21,986][87426] Updated weights for policy 1, policy_version 233090 (0.0011) -[2023-11-28 06:19:22,362][87426] Updated weights for policy 1, policy_version 233100 (0.0011) -[2023-11-28 06:19:22,633][87424] Updated weights for policy 0, policy_version 233417 (0.0011) -[2023-11-28 06:19:22,745][87426] Updated weights for policy 1, policy_version 233110 (0.0012) -[2023-11-28 06:19:23,013][87424] Updated weights for policy 0, policy_version 233427 (0.0011) -[2023-11-28 06:19:23,118][87426] Updated weights for policy 1, policy_version 233120 (0.0010) -[2023-11-28 06:19:23,403][87424] Updated weights for policy 0, policy_version 233437 (0.0012) -[2023-11-28 06:19:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 119431168. Throughput: 0: 2649.6, 1: 2728.1. Samples: 119449764. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:19:23,445][86177] Avg episode reward: [(0, '-519.540'), (1, '-538.210')] -[2023-11-28 06:19:25,416][87426] Updated weights for policy 1, policy_version 233130 (0.0012) -[2023-11-28 06:19:25,574][87424] Updated weights for policy 0, policy_version 233447 (0.0012) -[2023-11-28 06:19:25,799][87426] Updated weights for policy 1, policy_version 233140 (0.0011) -[2023-11-28 06:19:25,969][87424] Updated weights for policy 0, policy_version 233457 (0.0012) -[2023-11-28 06:19:26,175][87426] Updated weights for policy 1, policy_version 233150 (0.0011) -[2023-11-28 06:19:26,352][87424] Updated weights for policy 0, policy_version 233467 (0.0012) -[2023-11-28 06:19:28,141][87426] Updated weights for policy 1, policy_version 233160 (0.0012) -[2023-11-28 06:19:28,404][87424] Updated weights for policy 0, policy_version 233477 (0.0012) -[2023-11-28 06:19:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 119455744. Throughput: 0: 2659.8, 1: 2718.6. Samples: 119474520. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:19:28,445][86177] Avg episode reward: [(0, '-505.080'), (1, '-528.980')] -[2023-11-28 06:19:28,515][87426] Updated weights for policy 1, policy_version 233170 (0.0011) -[2023-11-28 06:19:28,795][87424] Updated weights for policy 0, policy_version 233487 (0.0011) -[2023-11-28 06:19:28,890][87426] Updated weights for policy 1, policy_version 233180 (0.0008) -[2023-11-28 06:19:29,173][87424] Updated weights for policy 0, policy_version 233497 (0.0009) -[2023-11-28 06:19:30,816][87426] Updated weights for policy 1, policy_version 233190 (0.0011) -[2023-11-28 06:19:31,198][87426] Updated weights for policy 1, policy_version 233200 (0.0012) -[2023-11-28 06:19:31,575][87426] Updated weights for policy 1, policy_version 233210 (0.0011) -[2023-11-28 06:19:31,671][87424] Updated weights for policy 0, policy_version 233507 (0.0008) -[2023-11-28 06:19:32,043][87424] Updated weights for policy 0, policy_version 233517 (0.0011) -[2023-11-28 06:19:32,422][87424] Updated weights for policy 0, policy_version 233527 (0.0009) -[2023-11-28 06:19:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 119488512. Throughput: 0: 2693.2, 1: 2701.3. Samples: 119499572. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:19:33,445][86177] Avg episode reward: [(0, '-498.120'), (1, '-526.370')] -[2023-11-28 06:19:33,881][87426] Updated weights for policy 1, policy_version 233220 (0.0009) -[2023-11-28 06:19:34,260][87426] Updated weights for policy 1, policy_version 233230 (0.0009) -[2023-11-28 06:19:34,319][87424] Updated weights for policy 0, policy_version 233537 (0.0008) -[2023-11-28 06:19:34,639][87426] Updated weights for policy 1, policy_version 233240 (0.0011) -[2023-11-28 06:19:34,700][87424] Updated weights for policy 0, policy_version 233547 (0.0011) -[2023-11-28 06:19:35,083][87424] Updated weights for policy 0, policy_version 233557 (0.0012) -[2023-11-28 06:19:35,467][87424] Updated weights for policy 0, policy_version 233567 (0.0012) -[2023-11-28 06:19:36,734][87426] Updated weights for policy 1, policy_version 233250 (0.0010) -[2023-11-28 06:19:37,111][87426] Updated weights for policy 1, policy_version 233260 (0.0011) -[2023-11-28 06:19:37,486][87426] Updated weights for policy 1, policy_version 233270 (0.0011) -[2023-11-28 06:19:37,850][87424] Updated weights for policy 0, policy_version 233577 (0.0008) -[2023-11-28 06:19:37,864][87426] Updated weights for policy 1, policy_version 233280 (0.0012) -[2023-11-28 06:19:38,229][87424] Updated weights for policy 0, policy_version 233587 (0.0012) -[2023-11-28 06:19:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 119513088. Throughput: 0: 2705.5, 1: 2702.3. Samples: 119532396. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:19:38,445][86177] Avg episode reward: [(0, '-516.970'), (1, '-525.580')] -[2023-11-28 06:19:38,599][87424] Updated weights for policy 0, policy_version 233597 (0.0012) -[2023-11-28 06:19:39,733][87426] Updated weights for policy 1, policy_version 233290 (0.0011) -[2023-11-28 06:19:40,113][87426] Updated weights for policy 1, policy_version 233300 (0.0008) -[2023-11-28 06:19:40,515][87426] Updated weights for policy 1, policy_version 233310 (0.0009) -[2023-11-28 06:19:41,188][87424] Updated weights for policy 0, policy_version 233607 (0.0012) -[2023-11-28 06:19:41,575][87424] Updated weights for policy 0, policy_version 233617 (0.0012) -[2023-11-28 06:19:41,948][87424] Updated weights for policy 0, policy_version 233627 (0.0012) -[2023-11-28 06:19:42,688][87426] Updated weights for policy 1, policy_version 233320 (0.0011) -[2023-11-28 06:19:43,068][87426] Updated weights for policy 1, policy_version 233330 (0.0009) -[2023-11-28 06:19:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 119537664. Throughput: 0: 2709.5, 1: 2715.8. Samples: 119557400. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:19:43,445][86177] Avg episode reward: [(0, '-520.920'), (1, '-520.360')] -[2023-11-28 06:19:43,448][87426] Updated weights for policy 1, policy_version 233340 (0.0007) -[2023-11-28 06:19:44,033][87424] Updated weights for policy 0, policy_version 233637 (0.0011) -[2023-11-28 06:19:44,422][87424] Updated weights for policy 0, policy_version 233647 (0.0010) -[2023-11-28 06:19:44,797][87424] Updated weights for policy 0, policy_version 233657 (0.0012) -[2023-11-28 06:19:45,290][87426] Updated weights for policy 1, policy_version 233350 (0.0010) -[2023-11-28 06:19:45,665][87426] Updated weights for policy 1, policy_version 233360 (0.0011) -[2023-11-28 06:19:46,042][87426] Updated weights for policy 1, policy_version 233370 (0.0012) -[2023-11-28 06:19:47,207][87424] Updated weights for policy 0, policy_version 233667 (0.0012) -[2023-11-28 06:19:47,593][87424] Updated weights for policy 0, policy_version 233677 (0.0011) -[2023-11-28 06:19:47,965][87424] Updated weights for policy 0, policy_version 233687 (0.0011) -[2023-11-28 06:19:48,041][87426] Updated weights for policy 1, policy_version 233380 (0.0010) -[2023-11-28 06:19:48,419][87426] Updated weights for policy 1, policy_version 233390 (0.0008) -[2023-11-28 06:19:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 119570432. Throughput: 0: 2690.5, 1: 2731.6. Samples: 119581600. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:19:48,445][86177] Avg episode reward: [(0, '-523.380'), (1, '-516.150')] -[2023-11-28 06:19:48,793][87426] Updated weights for policy 1, policy_version 233400 (0.0009) -[2023-11-28 06:19:49,621][87424] Updated weights for policy 0, policy_version 233697 (0.0012) -[2023-11-28 06:19:49,998][87424] Updated weights for policy 0, policy_version 233707 (0.0012) -[2023-11-28 06:19:50,380][87424] Updated weights for policy 0, policy_version 233717 (0.0012) -[2023-11-28 06:19:50,768][87424] Updated weights for policy 0, policy_version 233727 (0.0012) -[2023-11-28 06:19:51,065][87426] Updated weights for policy 1, policy_version 233410 (0.0011) -[2023-11-28 06:19:51,449][87426] Updated weights for policy 1, policy_version 233420 (0.0011) -[2023-11-28 06:19:51,824][87426] Updated weights for policy 1, policy_version 233430 (0.0011) -[2023-11-28 06:19:52,227][87426] Updated weights for policy 1, policy_version 233440 (0.0012) -[2023-11-28 06:19:52,930][87424] Updated weights for policy 0, policy_version 233737 (0.0012) -[2023-11-28 06:19:53,307][87424] Updated weights for policy 0, policy_version 233747 (0.0012) -[2023-11-28 06:19:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 119595008. Throughput: 0: 2670.9, 1: 2747.5. Samples: 119613396. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:19:53,445][86177] Avg episode reward: [(0, '-515.660'), (1, '-531.310')] -[2023-11-28 06:19:53,687][87424] Updated weights for policy 0, policy_version 233757 (0.0011) -[2023-11-28 06:19:54,774][87426] Updated weights for policy 1, policy_version 233450 (0.0012) -[2023-11-28 06:19:55,154][87426] Updated weights for policy 1, policy_version 233460 (0.0012) -[2023-11-28 06:19:55,534][87426] Updated weights for policy 1, policy_version 233470 (0.0009) -[2023-11-28 06:19:56,074][87424] Updated weights for policy 0, policy_version 233767 (0.0011) -[2023-11-28 06:19:56,459][87424] Updated weights for policy 0, policy_version 233777 (0.0007) -[2023-11-28 06:19:56,845][87424] Updated weights for policy 0, policy_version 233787 (0.0010) -[2023-11-28 06:19:57,188][87426] Updated weights for policy 1, policy_version 233480 (0.0008) -[2023-11-28 06:19:57,570][87426] Updated weights for policy 1, policy_version 233490 (0.0007) -[2023-11-28 06:19:57,955][87426] Updated weights for policy 1, policy_version 233500 (0.0007) -[2023-11-28 06:19:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 119627776. Throughput: 0: 2669.6, 1: 2777.0. Samples: 119638664. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:19:58,445][86177] Avg episode reward: [(0, '-506.830'), (1, '-524.690')] -[2023-11-28 06:19:58,786][87424] Updated weights for policy 0, policy_version 233797 (0.0012) -[2023-11-28 06:19:59,177][87424] Updated weights for policy 0, policy_version 233807 (0.0012) -[2023-11-28 06:19:59,558][87424] Updated weights for policy 0, policy_version 233817 (0.0012) -[2023-11-28 06:20:00,053][87426] Updated weights for policy 1, policy_version 233510 (0.0009) -[2023-11-28 06:20:00,427][87426] Updated weights for policy 1, policy_version 233520 (0.0010) -[2023-11-28 06:20:00,812][87426] Updated weights for policy 1, policy_version 233530 (0.0009) -[2023-11-28 06:20:01,588][87424] Updated weights for policy 0, policy_version 233827 (0.0012) -[2023-11-28 06:20:01,970][87424] Updated weights for policy 0, policy_version 233837 (0.0011) -[2023-11-28 06:20:02,353][87424] Updated weights for policy 0, policy_version 233847 (0.0012) -[2023-11-28 06:20:03,219][87426] Updated weights for policy 1, policy_version 233540 (0.0009) -[2023-11-28 06:20:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 119652352. Throughput: 0: 2718.3, 1: 2768.9. Samples: 119664592. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:03,445][86177] Avg episode reward: [(0, '-500.690'), (1, '-521.950')] -[2023-11-28 06:20:03,593][87426] Updated weights for policy 1, policy_version 233550 (0.0012) -[2023-11-28 06:20:03,967][87426] Updated weights for policy 1, policy_version 233560 (0.0012) -[2023-11-28 06:20:04,411][87424] Updated weights for policy 0, policy_version 233857 (0.0012) -[2023-11-28 06:20:04,794][87424] Updated weights for policy 0, policy_version 233867 (0.0012) -[2023-11-28 06:20:05,170][87424] Updated weights for policy 0, policy_version 233877 (0.0012) -[2023-11-28 06:20:05,562][87424] Updated weights for policy 0, policy_version 233887 (0.0012) -[2023-11-28 06:20:06,005][87426] Updated weights for policy 1, policy_version 233570 (0.0009) -[2023-11-28 06:20:06,383][87426] Updated weights for policy 1, policy_version 233580 (0.0007) -[2023-11-28 06:20:06,765][87426] Updated weights for policy 1, policy_version 233590 (0.0009) -[2023-11-28 06:20:07,136][87426] Updated weights for policy 1, policy_version 233600 (0.0011) -[2023-11-28 06:20:07,501][87424] Updated weights for policy 0, policy_version 233897 (0.0010) -[2023-11-28 06:20:07,882][87424] Updated weights for policy 0, policy_version 233907 (0.0013) -[2023-11-28 06:20:08,255][87424] Updated weights for policy 0, policy_version 233917 (0.0012) -[2023-11-28 06:20:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 119685120. Throughput: 0: 2747.4, 1: 2756.3. Samples: 119697428. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:08,445][86177] Avg episode reward: [(0, '-498.820'), (1, '-503.530')] -[2023-11-28 06:20:09,543][87426] Updated weights for policy 1, policy_version 233610 (0.0012) -[2023-11-28 06:20:09,931][87426] Updated weights for policy 1, policy_version 233620 (0.0011) -[2023-11-28 06:20:10,205][87424] Updated weights for policy 0, policy_version 233927 (0.0012) -[2023-11-28 06:20:10,307][87426] Updated weights for policy 1, policy_version 233630 (0.0011) -[2023-11-28 06:20:10,581][87424] Updated weights for policy 0, policy_version 233937 (0.0012) -[2023-11-28 06:20:10,971][87424] Updated weights for policy 0, policy_version 233947 (0.0009) -[2023-11-28 06:20:12,623][87426] Updated weights for policy 1, policy_version 233640 (0.0009) -[2023-11-28 06:20:13,006][87426] Updated weights for policy 1, policy_version 233650 (0.0009) -[2023-11-28 06:20:13,383][87426] Updated weights for policy 1, policy_version 233660 (0.0008) -[2023-11-28 06:20:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 119701504. Throughput: 0: 2737.6, 1: 2747.7. Samples: 119721360. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:13,445][86177] Avg episode reward: [(0, '-496.640'), (1, '-501.700')] -[2023-11-28 06:20:13,454][87424] Updated weights for policy 0, policy_version 233957 (0.0008) -[2023-11-28 06:20:13,833][87424] Updated weights for policy 0, policy_version 233967 (0.0007) -[2023-11-28 06:20:14,211][87424] Updated weights for policy 0, policy_version 233977 (0.0008) -[2023-11-28 06:20:15,721][87426] Updated weights for policy 1, policy_version 233670 (0.0010) -[2023-11-28 06:20:16,101][87426] Updated weights for policy 1, policy_version 233680 (0.0010) -[2023-11-28 06:20:16,481][87426] Updated weights for policy 1, policy_version 233690 (0.0010) -[2023-11-28 06:20:16,761][87424] Updated weights for policy 0, policy_version 233987 (0.0009) -[2023-11-28 06:20:17,145][87424] Updated weights for policy 0, policy_version 233997 (0.0012) -[2023-11-28 06:20:17,536][87424] Updated weights for policy 0, policy_version 234007 (0.0012) -[2023-11-28 06:20:18,220][87426] Updated weights for policy 1, policy_version 233700 (0.0008) -[2023-11-28 06:20:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 119734272. Throughput: 0: 2696.1, 1: 2740.7. Samples: 119744228. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:18,445][86177] Avg episode reward: [(0, '-495.430'), (1, '-504.010')] -[2023-11-28 06:20:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000234016_59908096.pth... -[2023-11-28 06:20:18,491][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000231488_59260928.pth -[2023-11-28 06:20:18,604][87426] Updated weights for policy 1, policy_version 233710 (0.0007) -[2023-11-28 06:20:18,989][87426] Updated weights for policy 1, policy_version 233720 (0.0009) -[2023-11-28 06:20:19,289][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000233728_59834368.pth... -[2023-11-28 06:20:19,336][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000231168_59179008.pth -[2023-11-28 06:20:20,107][87424] Updated weights for policy 0, policy_version 234017 (0.0011) -[2023-11-28 06:20:20,486][87424] Updated weights for policy 0, policy_version 234027 (0.0012) -[2023-11-28 06:20:20,867][87424] Updated weights for policy 0, policy_version 234037 (0.0011) -[2023-11-28 06:20:21,181][87426] Updated weights for policy 1, policy_version 233730 (0.0010) -[2023-11-28 06:20:21,254][87424] Updated weights for policy 0, policy_version 234047 (0.0009) -[2023-11-28 06:20:21,569][87426] Updated weights for policy 1, policy_version 233740 (0.0011) -[2023-11-28 06:20:21,951][87426] Updated weights for policy 1, policy_version 233750 (0.0011) -[2023-11-28 06:20:22,328][87426] Updated weights for policy 1, policy_version 233760 (0.0012) -[2023-11-28 06:20:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 119758848. Throughput: 0: 2666.0, 1: 2732.3. Samples: 119775320. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:23,445][86177] Avg episode reward: [(0, '-497.430'), (1, '-512.050')] -[2023-11-28 06:20:23,784][87424] Updated weights for policy 0, policy_version 234057 (0.0011) -[2023-11-28 06:20:24,173][87424] Updated weights for policy 0, policy_version 234067 (0.0009) -[2023-11-28 06:20:24,559][87424] Updated weights for policy 0, policy_version 234077 (0.0010) -[2023-11-28 06:20:24,683][87426] Updated weights for policy 1, policy_version 233770 (0.0011) -[2023-11-28 06:20:25,069][87426] Updated weights for policy 1, policy_version 233780 (0.0012) -[2023-11-28 06:20:25,439][87426] Updated weights for policy 1, policy_version 233790 (0.0012) -[2023-11-28 06:20:26,385][87424] Updated weights for policy 0, policy_version 234087 (0.0011) -[2023-11-28 06:20:26,767][87424] Updated weights for policy 0, policy_version 234097 (0.0011) -[2023-11-28 06:20:27,147][87424] Updated weights for policy 0, policy_version 234107 (0.0012) -[2023-11-28 06:20:27,221][87426] Updated weights for policy 1, policy_version 233800 (0.0011) -[2023-11-28 06:20:27,606][87426] Updated weights for policy 1, policy_version 233810 (0.0010) -[2023-11-28 06:20:27,972][87426] Updated weights for policy 1, policy_version 233820 (0.0012) -[2023-11-28 06:20:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 119791616. Throughput: 0: 2666.3, 1: 2719.5. Samples: 119799760. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:28,445][86177] Avg episode reward: [(0, '-513.170'), (1, '-515.180')] -[2023-11-28 06:20:29,224][87424] Updated weights for policy 0, policy_version 234117 (0.0010) -[2023-11-28 06:20:29,618][87424] Updated weights for policy 0, policy_version 234127 (0.0009) -[2023-11-28 06:20:29,990][87424] Updated weights for policy 0, policy_version 234137 (0.0012) -[2023-11-28 06:20:30,525][87426] Updated weights for policy 1, policy_version 233830 (0.0011) -[2023-11-28 06:20:30,907][87426] Updated weights for policy 1, policy_version 233840 (0.0008) -[2023-11-28 06:20:31,283][87426] Updated weights for policy 1, policy_version 233850 (0.0008) -[2023-11-28 06:20:31,874][87424] Updated weights for policy 0, policy_version 234147 (0.0012) -[2023-11-28 06:20:32,256][87424] Updated weights for policy 0, policy_version 234157 (0.0012) -[2023-11-28 06:20:32,642][87424] Updated weights for policy 0, policy_version 234167 (0.0012) -[2023-11-28 06:20:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 119816192. Throughput: 0: 2718.6, 1: 2710.0. Samples: 119825888. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:33,446][86177] Avg episode reward: [(0, '-512.060'), (1, '-508.490')] -[2023-11-28 06:20:33,708][87426] Updated weights for policy 1, policy_version 233860 (0.0010) -[2023-11-28 06:20:34,084][87426] Updated weights for policy 1, policy_version 233870 (0.0012) -[2023-11-28 06:20:34,462][87426] Updated weights for policy 1, policy_version 233880 (0.0011) -[2023-11-28 06:20:34,562][87424] Updated weights for policy 0, policy_version 234177 (0.0012) -[2023-11-28 06:20:34,935][87424] Updated weights for policy 0, policy_version 234187 (0.0011) -[2023-11-28 06:20:35,322][87424] Updated weights for policy 0, policy_version 234197 (0.0012) -[2023-11-28 06:20:35,699][87424] Updated weights for policy 0, policy_version 234207 (0.0012) -[2023-11-28 06:20:36,409][87426] Updated weights for policy 1, policy_version 233890 (0.0011) -[2023-11-28 06:20:36,793][87426] Updated weights for policy 1, policy_version 233900 (0.0011) -[2023-11-28 06:20:37,172][87426] Updated weights for policy 1, policy_version 233910 (0.0011) -[2023-11-28 06:20:37,549][87426] Updated weights for policy 1, policy_version 233920 (0.0012) -[2023-11-28 06:20:38,253][87424] Updated weights for policy 0, policy_version 234217 (0.0012) -[2023-11-28 06:20:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 119840768. Throughput: 0: 2760.6, 1: 2702.8. Samples: 119859252. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:38,446][86177] Avg episode reward: [(0, '-515.840'), (1, '-511.220')] -[2023-11-28 06:20:38,644][87424] Updated weights for policy 0, policy_version 234227 (0.0010) -[2023-11-28 06:20:39,033][87424] Updated weights for policy 0, policy_version 234237 (0.0009) -[2023-11-28 06:20:40,005][87426] Updated weights for policy 1, policy_version 233930 (0.0011) -[2023-11-28 06:20:40,386][87426] Updated weights for policy 1, policy_version 233940 (0.0012) -[2023-11-28 06:20:40,764][87426] Updated weights for policy 1, policy_version 233950 (0.0011) -[2023-11-28 06:20:40,936][87424] Updated weights for policy 0, policy_version 234247 (0.0010) -[2023-11-28 06:20:41,317][87424] Updated weights for policy 0, policy_version 234257 (0.0008) -[2023-11-28 06:20:41,695][87424] Updated weights for policy 0, policy_version 234267 (0.0010) -[2023-11-28 06:20:42,996][87426] Updated weights for policy 1, policy_version 233960 (0.0011) -[2023-11-28 06:20:43,376][87426] Updated weights for policy 1, policy_version 233970 (0.0012) -[2023-11-28 06:20:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 119865344. Throughput: 0: 2757.1, 1: 2674.9. Samples: 119883104. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:43,445][86177] Avg episode reward: [(0, '-508.380'), (1, '-508.740')] -[2023-11-28 06:20:43,754][87426] Updated weights for policy 1, policy_version 233980 (0.0012) -[2023-11-28 06:20:44,317][87424] Updated weights for policy 0, policy_version 234277 (0.0009) -[2023-11-28 06:20:44,701][87424] Updated weights for policy 0, policy_version 234287 (0.0008) -[2023-11-28 06:20:45,083][87424] Updated weights for policy 0, policy_version 234297 (0.0009) -[2023-11-28 06:20:45,846][87426] Updated weights for policy 1, policy_version 233990 (0.0012) -[2023-11-28 06:20:46,230][87426] Updated weights for policy 1, policy_version 234000 (0.0012) -[2023-11-28 06:20:46,610][87426] Updated weights for policy 1, policy_version 234010 (0.0012) -[2023-11-28 06:20:47,363][87424] Updated weights for policy 0, policy_version 234307 (0.0008) -[2023-11-28 06:20:47,747][87424] Updated weights for policy 0, policy_version 234317 (0.0007) -[2023-11-28 06:20:48,131][87424] Updated weights for policy 0, policy_version 234327 (0.0007) -[2023-11-28 06:20:48,404][87426] Updated weights for policy 1, policy_version 234020 (0.0011) -[2023-11-28 06:20:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 119889920. Throughput: 0: 2725.0, 1: 2697.0. Samples: 119908580. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:48,445][86177] Avg episode reward: [(0, '-510.560'), (1, '-515.540')] -[2023-11-28 06:20:48,788][87426] Updated weights for policy 1, policy_version 234030 (0.0012) -[2023-11-28 06:20:49,160][87426] Updated weights for policy 1, policy_version 234040 (0.0012) -[2023-11-28 06:20:50,154][87424] Updated weights for policy 0, policy_version 234337 (0.0008) -[2023-11-28 06:20:50,535][87424] Updated weights for policy 0, policy_version 234347 (0.0012) -[2023-11-28 06:20:50,917][87424] Updated weights for policy 0, policy_version 234357 (0.0012) -[2023-11-28 06:20:51,298][87424] Updated weights for policy 0, policy_version 234367 (0.0011) -[2023-11-28 06:20:51,367][87426] Updated weights for policy 1, policy_version 234050 (0.0012) -[2023-11-28 06:20:51,744][87426] Updated weights for policy 1, policy_version 234060 (0.0012) -[2023-11-28 06:20:52,121][87426] Updated weights for policy 1, policy_version 234070 (0.0009) -[2023-11-28 06:20:52,499][87426] Updated weights for policy 1, policy_version 234080 (0.0012) -[2023-11-28 06:20:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 119922688. Throughput: 0: 2690.1, 1: 2719.1. Samples: 119940844. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 06:20:53,445][86177] Avg episode reward: [(0, '-510.640'), (1, '-512.150')] -[2023-11-28 06:20:53,653][87424] Updated weights for policy 0, policy_version 234377 (0.0010) -[2023-11-28 06:20:54,034][87424] Updated weights for policy 0, policy_version 234387 (0.0010) -[2023-11-28 06:20:54,412][87424] Updated weights for policy 0, policy_version 234397 (0.0008) -[2023-11-28 06:20:54,777][87426] Updated weights for policy 1, policy_version 234090 (0.0012) -[2023-11-28 06:20:55,149][87426] Updated weights for policy 1, policy_version 234100 (0.0012) -[2023-11-28 06:20:55,531][87426] Updated weights for policy 1, policy_version 234110 (0.0012) -[2023-11-28 06:20:56,793][87424] Updated weights for policy 0, policy_version 234407 (0.0011) -[2023-11-28 06:20:57,165][87424] Updated weights for policy 0, policy_version 234417 (0.0010) -[2023-11-28 06:20:57,546][87424] Updated weights for policy 0, policy_version 234427 (0.0008) -[2023-11-28 06:20:57,946][87426] Updated weights for policy 1, policy_version 234120 (0.0011) -[2023-11-28 06:20:58,325][87426] Updated weights for policy 1, policy_version 234130 (0.0011) -[2023-11-28 06:20:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 119947264. Throughput: 0: 2699.4, 1: 2715.7. Samples: 119965040. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:20:58,445][86177] Avg episode reward: [(0, '-503.900'), (1, '-529.230')] -[2023-11-28 06:20:58,714][87426] Updated weights for policy 1, policy_version 234140 (0.0011) -[2023-11-28 06:20:59,263][87424] Updated weights for policy 0, policy_version 234437 (0.0009) -[2023-11-28 06:20:59,650][87424] Updated weights for policy 0, policy_version 234447 (0.0011) -[2023-11-28 06:21:00,037][87424] Updated weights for policy 0, policy_version 234457 (0.0010) -[2023-11-28 06:21:01,227][87426] Updated weights for policy 1, policy_version 234150 (0.0009) -[2023-11-28 06:21:01,604][87426] Updated weights for policy 1, policy_version 234160 (0.0008) -[2023-11-28 06:21:01,985][87426] Updated weights for policy 1, policy_version 234170 (0.0010) -[2023-11-28 06:21:02,210][87424] Updated weights for policy 0, policy_version 234467 (0.0008) -[2023-11-28 06:21:02,597][87424] Updated weights for policy 0, policy_version 234477 (0.0008) -[2023-11-28 06:21:02,978][87424] Updated weights for policy 0, policy_version 234487 (0.0008) -[2023-11-28 06:21:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 119980032. Throughput: 0: 2737.9, 1: 2730.6. Samples: 119990308. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:03,445][86177] Avg episode reward: [(0, '-497.760'), (1, '-529.830')] -[2023-11-28 06:21:04,019][87426] Updated weights for policy 1, policy_version 234180 (0.0011) -[2023-11-28 06:21:04,426][87426] Updated weights for policy 1, policy_version 234190 (0.0012) -[2023-11-28 06:21:04,796][87426] Updated weights for policy 1, policy_version 234200 (0.0008) -[2023-11-28 06:21:05,214][87424] Updated weights for policy 0, policy_version 234497 (0.0008) -[2023-11-28 06:21:05,595][87424] Updated weights for policy 0, policy_version 234507 (0.0007) -[2023-11-28 06:21:05,983][87424] Updated weights for policy 0, policy_version 234517 (0.0007) -[2023-11-28 06:21:06,363][87424] Updated weights for policy 0, policy_version 234527 (0.0008) -[2023-11-28 06:21:06,480][87426] Updated weights for policy 1, policy_version 234210 (0.0009) -[2023-11-28 06:21:06,865][87426] Updated weights for policy 1, policy_version 234220 (0.0009) -[2023-11-28 06:21:07,242][87426] Updated weights for policy 1, policy_version 234230 (0.0008) -[2023-11-28 06:21:07,620][87426] Updated weights for policy 1, policy_version 234240 (0.0007) -[2023-11-28 06:21:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 120004608. Throughput: 0: 2750.9, 1: 2743.9. Samples: 120022588. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:08,445][86177] Avg episode reward: [(0, '-495.260'), (1, '-522.170')] -[2023-11-28 06:21:08,492][87424] Updated weights for policy 0, policy_version 234537 (0.0008) -[2023-11-28 06:21:08,877][87424] Updated weights for policy 0, policy_version 234547 (0.0008) -[2023-11-28 06:21:09,268][87424] Updated weights for policy 0, policy_version 234557 (0.0008) -[2023-11-28 06:21:09,955][87426] Updated weights for policy 1, policy_version 234250 (0.0009) -[2023-11-28 06:21:10,335][87426] Updated weights for policy 1, policy_version 234260 (0.0007) -[2023-11-28 06:21:10,710][87426] Updated weights for policy 1, policy_version 234270 (0.0012) -[2023-11-28 06:21:11,463][87424] Updated weights for policy 0, policy_version 234567 (0.0010) -[2023-11-28 06:21:11,881][87424] Updated weights for policy 0, policy_version 234577 (0.0011) -[2023-11-28 06:21:12,249][87424] Updated weights for policy 0, policy_version 234587 (0.0012) -[2023-11-28 06:21:12,617][87426] Updated weights for policy 1, policy_version 234280 (0.0012) -[2023-11-28 06:21:12,987][87426] Updated weights for policy 1, policy_version 234290 (0.0012) -[2023-11-28 06:21:13,377][87426] Updated weights for policy 1, policy_version 234300 (0.0011) -[2023-11-28 06:21:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120029184. Throughput: 0: 2740.6, 1: 2724.4. Samples: 120045688. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:13,445][86177] Avg episode reward: [(0, '-494.270'), (1, '-534.150')] -[2023-11-28 06:21:14,211][87424] Updated weights for policy 0, policy_version 234597 (0.0011) -[2023-11-28 06:21:14,591][87424] Updated weights for policy 0, policy_version 234607 (0.0008) -[2023-11-28 06:21:14,979][87424] Updated weights for policy 0, policy_version 234617 (0.0007) -[2023-11-28 06:21:15,748][87426] Updated weights for policy 1, policy_version 234310 (0.0010) -[2023-11-28 06:21:16,116][87426] Updated weights for policy 1, policy_version 234320 (0.0011) -[2023-11-28 06:21:16,497][87426] Updated weights for policy 1, policy_version 234330 (0.0012) -[2023-11-28 06:21:17,334][87424] Updated weights for policy 0, policy_version 234627 (0.0009) -[2023-11-28 06:21:17,729][87424] Updated weights for policy 0, policy_version 234637 (0.0012) -[2023-11-28 06:21:18,113][87424] Updated weights for policy 0, policy_version 234647 (0.0012) -[2023-11-28 06:21:18,441][87426] Updated weights for policy 1, policy_version 234340 (0.0012) -[2023-11-28 06:21:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 120053760. Throughput: 0: 2696.0, 1: 2719.4. Samples: 120069580. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:18,445][86177] Avg episode reward: [(0, '-493.350'), (1, '-517.680')] -[2023-11-28 06:21:18,823][87426] Updated weights for policy 1, policy_version 234350 (0.0012) -[2023-11-28 06:21:19,208][87426] Updated weights for policy 1, policy_version 234360 (0.0012) -[2023-11-28 06:21:20,410][87424] Updated weights for policy 0, policy_version 234657 (0.0012) -[2023-11-28 06:21:20,793][87424] Updated weights for policy 0, policy_version 234667 (0.0012) -[2023-11-28 06:21:21,179][87424] Updated weights for policy 0, policy_version 234677 (0.0010) -[2023-11-28 06:21:21,564][87424] Updated weights for policy 0, policy_version 234687 (0.0011) -[2023-11-28 06:21:21,587][87426] Updated weights for policy 1, policy_version 234370 (0.0012) -[2023-11-28 06:21:21,980][87426] Updated weights for policy 1, policy_version 234380 (0.0009) -[2023-11-28 06:21:22,381][87426] Updated weights for policy 1, policy_version 234390 (0.0010) -[2023-11-28 06:21:22,756][87426] Updated weights for policy 1, policy_version 234400 (0.0012) -[2023-11-28 06:21:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120086528. Throughput: 0: 2656.9, 1: 2734.1. Samples: 120101848. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:23,445][86177] Avg episode reward: [(0, '-494.410'), (1, '-521.270')] -[2023-11-28 06:21:23,647][87424] Updated weights for policy 0, policy_version 234697 (0.0012) -[2023-11-28 06:21:24,025][87424] Updated weights for policy 0, policy_version 234707 (0.0012) -[2023-11-28 06:21:24,405][87424] Updated weights for policy 0, policy_version 234717 (0.0012) -[2023-11-28 06:21:24,907][87426] Updated weights for policy 1, policy_version 234410 (0.0012) -[2023-11-28 06:21:25,295][87426] Updated weights for policy 1, policy_version 234420 (0.0012) -[2023-11-28 06:21:25,672][87426] Updated weights for policy 1, policy_version 234430 (0.0011) -[2023-11-28 06:21:26,384][87424] Updated weights for policy 0, policy_version 234727 (0.0010) -[2023-11-28 06:21:26,767][87424] Updated weights for policy 0, policy_version 234737 (0.0008) -[2023-11-28 06:21:27,156][87424] Updated weights for policy 0, policy_version 234747 (0.0007) -[2023-11-28 06:21:28,253][87426] Updated weights for policy 1, policy_version 234440 (0.0009) -[2023-11-28 06:21:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 120111104. Throughput: 0: 2663.5, 1: 2723.9. Samples: 120125540. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:28,445][86177] Avg episode reward: [(0, '-495.230'), (1, '-529.230')] -[2023-11-28 06:21:28,636][87426] Updated weights for policy 1, policy_version 234450 (0.0008) -[2023-11-28 06:21:29,014][87426] Updated weights for policy 1, policy_version 234460 (0.0008) -[2023-11-28 06:21:29,608][87424] Updated weights for policy 0, policy_version 234757 (0.0007) -[2023-11-28 06:21:29,999][87424] Updated weights for policy 0, policy_version 234767 (0.0008) -[2023-11-28 06:21:30,377][87424] Updated weights for policy 0, policy_version 234777 (0.0012) -[2023-11-28 06:21:30,983][87426] Updated weights for policy 1, policy_version 234470 (0.0010) -[2023-11-28 06:21:31,367][87426] Updated weights for policy 1, policy_version 234480 (0.0012) -[2023-11-28 06:21:31,745][87426] Updated weights for policy 1, policy_version 234490 (0.0013) -[2023-11-28 06:21:32,647][87424] Updated weights for policy 0, policy_version 234787 (0.0012) -[2023-11-28 06:21:33,020][87424] Updated weights for policy 0, policy_version 234797 (0.0011) -[2023-11-28 06:21:33,403][87424] Updated weights for policy 0, policy_version 234807 (0.0012) -[2023-11-28 06:21:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 120135680. Throughput: 0: 2646.7, 1: 2699.4. Samples: 120149152. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:33,445][86177] Avg episode reward: [(0, '-499.200'), (1, '-522.350')] -[2023-11-28 06:21:33,866][87426] Updated weights for policy 1, policy_version 234500 (0.0010) -[2023-11-28 06:21:34,244][87426] Updated weights for policy 1, policy_version 234510 (0.0016) -[2023-11-28 06:21:34,623][87426] Updated weights for policy 1, policy_version 234520 (0.0012) -[2023-11-28 06:21:35,836][87424] Updated weights for policy 0, policy_version 234817 (0.0009) -[2023-11-28 06:21:36,225][87424] Updated weights for policy 0, policy_version 234827 (0.0008) -[2023-11-28 06:21:36,595][87424] Updated weights for policy 0, policy_version 234837 (0.0007) -[2023-11-28 06:21:36,674][87426] Updated weights for policy 1, policy_version 234530 (0.0011) -[2023-11-28 06:21:36,976][87424] Updated weights for policy 0, policy_version 234847 (0.0012) -[2023-11-28 06:21:37,054][87426] Updated weights for policy 1, policy_version 234540 (0.0012) -[2023-11-28 06:21:37,441][87426] Updated weights for policy 1, policy_version 234550 (0.0011) -[2023-11-28 06:21:37,808][87426] Updated weights for policy 1, policy_version 234560 (0.0011) -[2023-11-28 06:21:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 120168448. Throughput: 0: 2672.5, 1: 2695.6. Samples: 120182412. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:38,445][86177] Avg episode reward: [(0, '-499.320'), (1, '-525.740')] -[2023-11-28 06:21:39,046][87424] Updated weights for policy 0, policy_version 234857 (0.0012) -[2023-11-28 06:21:39,428][87424] Updated weights for policy 0, policy_version 234867 (0.0011) -[2023-11-28 06:21:39,730][87426] Updated weights for policy 1, policy_version 234570 (0.0011) -[2023-11-28 06:21:39,804][87424] Updated weights for policy 0, policy_version 234877 (0.0009) -[2023-11-28 06:21:40,113][87426] Updated weights for policy 1, policy_version 234580 (0.0011) -[2023-11-28 06:21:40,484][87426] Updated weights for policy 1, policy_version 234590 (0.0012) -[2023-11-28 06:21:42,160][87424] Updated weights for policy 0, policy_version 234887 (0.0012) -[2023-11-28 06:21:42,426][87426] Updated weights for policy 1, policy_version 234600 (0.0011) -[2023-11-28 06:21:42,536][87424] Updated weights for policy 0, policy_version 234897 (0.0012) -[2023-11-28 06:21:42,806][87426] Updated weights for policy 1, policy_version 234610 (0.0008) -[2023-11-28 06:21:42,916][87424] Updated weights for policy 0, policy_version 234907 (0.0012) -[2023-11-28 06:21:43,185][87426] Updated weights for policy 1, policy_version 234620 (0.0009) -[2023-11-28 06:21:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 120201216. Throughput: 0: 2680.8, 1: 2703.6. Samples: 120207340. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:43,445][86177] Avg episode reward: [(0, '-496.340'), (1, '-526.820')] -[2023-11-28 06:21:45,082][87424] Updated weights for policy 0, policy_version 234917 (0.0011) -[2023-11-28 06:21:45,459][87426] Updated weights for policy 1, policy_version 234630 (0.0009) -[2023-11-28 06:21:45,463][87424] Updated weights for policy 0, policy_version 234927 (0.0008) -[2023-11-28 06:21:45,836][87426] Updated weights for policy 1, policy_version 234640 (0.0009) -[2023-11-28 06:21:45,838][87424] Updated weights for policy 0, policy_version 234937 (0.0010) -[2023-11-28 06:21:46,214][87426] Updated weights for policy 1, policy_version 234650 (0.0011) -[2023-11-28 06:21:47,680][87424] Updated weights for policy 0, policy_version 234947 (0.0010) -[2023-11-28 06:21:48,061][87424] Updated weights for policy 0, policy_version 234957 (0.0008) -[2023-11-28 06:21:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120217600. Throughput: 0: 2652.9, 1: 2720.0. Samples: 120232088. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:48,445][86177] Avg episode reward: [(0, '-490.250'), (1, '-515.930')] -[2023-11-28 06:21:48,447][87424] Updated weights for policy 0, policy_version 234967 (0.0008) -[2023-11-28 06:21:48,830][87426] Updated weights for policy 1, policy_version 234660 (0.0008) -[2023-11-28 06:21:49,209][87426] Updated weights for policy 1, policy_version 234670 (0.0008) -[2023-11-28 06:21:49,586][87426] Updated weights for policy 1, policy_version 234680 (0.0007) -[2023-11-28 06:21:50,580][87424] Updated weights for policy 0, policy_version 234977 (0.0009) -[2023-11-28 06:21:50,956][87424] Updated weights for policy 0, policy_version 234987 (0.0012) -[2023-11-28 06:21:51,342][87424] Updated weights for policy 0, policy_version 234997 (0.0011) -[2023-11-28 06:21:51,507][87426] Updated weights for policy 1, policy_version 234690 (0.0009) -[2023-11-28 06:21:51,729][87424] Updated weights for policy 0, policy_version 235007 (0.0011) -[2023-11-28 06:21:51,894][87426] Updated weights for policy 1, policy_version 234700 (0.0010) -[2023-11-28 06:21:52,257][87426] Updated weights for policy 1, policy_version 234710 (0.0009) -[2023-11-28 06:21:52,636][87426] Updated weights for policy 1, policy_version 234720 (0.0007) -[2023-11-28 06:21:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 120250368. Throughput: 0: 2656.3, 1: 2734.1. Samples: 120265156. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:53,445][86177] Avg episode reward: [(0, '-491.280'), (1, '-517.880')] -[2023-11-28 06:21:54,223][87424] Updated weights for policy 0, policy_version 235017 (0.0008) -[2023-11-28 06:21:54,600][87424] Updated weights for policy 0, policy_version 235027 (0.0009) -[2023-11-28 06:21:54,641][87426] Updated weights for policy 1, policy_version 234730 (0.0012) -[2023-11-28 06:21:54,991][87424] Updated weights for policy 0, policy_version 235037 (0.0009) -[2023-11-28 06:21:55,023][87426] Updated weights for policy 1, policy_version 234740 (0.0011) -[2023-11-28 06:21:55,417][87426] Updated weights for policy 1, policy_version 234750 (0.0011) -[2023-11-28 06:21:57,079][87424] Updated weights for policy 0, policy_version 235047 (0.0012) -[2023-11-28 06:21:57,424][87426] Updated weights for policy 1, policy_version 234760 (0.0012) -[2023-11-28 06:21:57,461][87424] Updated weights for policy 0, policy_version 235057 (0.0012) -[2023-11-28 06:21:57,808][87426] Updated weights for policy 1, policy_version 234770 (0.0012) -[2023-11-28 06:21:57,843][87424] Updated weights for policy 0, policy_version 235067 (0.0010) -[2023-11-28 06:21:58,184][87426] Updated weights for policy 1, policy_version 234780 (0.0012) -[2023-11-28 06:21:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 120283136. Throughput: 0: 2663.8, 1: 2749.8. Samples: 120289300. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:21:58,445][86177] Avg episode reward: [(0, '-492.050'), (1, '-520.190')] -[2023-11-28 06:21:59,755][87424] Updated weights for policy 0, policy_version 235077 (0.0010) -[2023-11-28 06:22:00,139][87424] Updated weights for policy 0, policy_version 235087 (0.0012) -[2023-11-28 06:22:00,341][87426] Updated weights for policy 1, policy_version 234790 (0.0012) -[2023-11-28 06:22:00,518][87424] Updated weights for policy 0, policy_version 235097 (0.0011) -[2023-11-28 06:22:00,713][87426] Updated weights for policy 1, policy_version 234800 (0.0011) -[2023-11-28 06:22:01,107][87426] Updated weights for policy 1, policy_version 234810 (0.0012) -[2023-11-28 06:22:02,448][87424] Updated weights for policy 0, policy_version 235107 (0.0011) -[2023-11-28 06:22:02,828][87424] Updated weights for policy 0, policy_version 235117 (0.0012) -[2023-11-28 06:22:03,130][87426] Updated weights for policy 1, policy_version 234820 (0.0011) -[2023-11-28 06:22:03,208][87424] Updated weights for policy 0, policy_version 235127 (0.0009) -[2023-11-28 06:22:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 120299520. Throughput: 0: 2695.2, 1: 2750.8. Samples: 120314648. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:22:03,445][86177] Avg episode reward: [(0, '-496.990'), (1, '-519.590')] -[2023-11-28 06:22:03,510][87426] Updated weights for policy 1, policy_version 234830 (0.0011) -[2023-11-28 06:22:03,894][87426] Updated weights for policy 1, policy_version 234840 (0.0011) -[2023-11-28 06:22:05,785][87424] Updated weights for policy 0, policy_version 235137 (0.0007) -[2023-11-28 06:22:06,168][87424] Updated weights for policy 0, policy_version 235147 (0.0007) -[2023-11-28 06:22:06,393][87426] Updated weights for policy 1, policy_version 234850 (0.0011) -[2023-11-28 06:22:06,552][87424] Updated weights for policy 0, policy_version 235157 (0.0007) -[2023-11-28 06:22:06,773][87426] Updated weights for policy 1, policy_version 234860 (0.0008) -[2023-11-28 06:22:06,935][87424] Updated weights for policy 0, policy_version 235167 (0.0008) -[2023-11-28 06:22:07,142][87426] Updated weights for policy 1, policy_version 234870 (0.0008) -[2023-11-28 06:22:07,521][87426] Updated weights for policy 1, policy_version 234880 (0.0010) -[2023-11-28 06:22:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 120332288. Throughput: 0: 2694.0, 1: 2739.6. Samples: 120346360. Policy #0 lag: (min: 31.0, avg: 48.3, max: 73.0) -[2023-11-28 06:22:08,445][86177] Avg episode reward: [(0, '-500.530'), (1, '-525.710')] -[2023-11-28 06:22:08,939][87424] Updated weights for policy 0, policy_version 235177 (0.0008) -[2023-11-28 06:22:09,319][87424] Updated weights for policy 0, policy_version 235187 (0.0009) -[2023-11-28 06:22:09,694][87424] Updated weights for policy 0, policy_version 235197 (0.0008) -[2023-11-28 06:22:09,839][87426] Updated weights for policy 1, policy_version 234890 (0.0008) -[2023-11-28 06:22:10,222][87426] Updated weights for policy 1, policy_version 234900 (0.0008) -[2023-11-28 06:22:10,606][87426] Updated weights for policy 1, policy_version 234910 (0.0010) -[2023-11-28 06:22:12,005][87424] Updated weights for policy 0, policy_version 235207 (0.0011) -[2023-11-28 06:22:12,376][87424] Updated weights for policy 0, policy_version 235217 (0.0012) -[2023-11-28 06:22:12,757][87424] Updated weights for policy 0, policy_version 235227 (0.0012) -[2023-11-28 06:22:13,065][87426] Updated weights for policy 1, policy_version 234920 (0.0011) -[2023-11-28 06:22:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120356864. Throughput: 0: 2700.2, 1: 2753.3. Samples: 120370948. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:13,446][86177] Avg episode reward: [(0, '-509.340'), (1, '-527.340')] -[2023-11-28 06:22:13,451][87426] Updated weights for policy 1, policy_version 234930 (0.0011) -[2023-11-28 06:22:13,839][87426] Updated weights for policy 1, policy_version 234940 (0.0007) -[2023-11-28 06:22:14,875][87424] Updated weights for policy 0, policy_version 235237 (0.0013) -[2023-11-28 06:22:15,252][87424] Updated weights for policy 0, policy_version 235247 (0.0011) -[2023-11-28 06:22:15,636][87424] Updated weights for policy 0, policy_version 235257 (0.0011) -[2023-11-28 06:22:15,865][87426] Updated weights for policy 1, policy_version 234950 (0.0010) -[2023-11-28 06:22:16,248][87426] Updated weights for policy 1, policy_version 234960 (0.0011) -[2023-11-28 06:22:16,621][87426] Updated weights for policy 1, policy_version 234970 (0.0010) -[2023-11-28 06:22:17,527][87424] Updated weights for policy 0, policy_version 235267 (0.0011) -[2023-11-28 06:22:17,906][87424] Updated weights for policy 0, policy_version 235277 (0.0011) -[2023-11-28 06:22:18,292][87424] Updated weights for policy 0, policy_version 235287 (0.0012) -[2023-11-28 06:22:18,414][87426] Updated weights for policy 1, policy_version 234980 (0.0007) -[2023-11-28 06:22:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120381440. Throughput: 0: 2714.5, 1: 2763.6. Samples: 120395664. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:18,445][86177] Avg episode reward: [(0, '-507.600'), (1, '-538.010')] -[2023-11-28 06:22:18,636][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000235296_60235776.pth... -[2023-11-28 06:22:18,681][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000232768_59588608.pth -[2023-11-28 06:22:18,801][87426] Updated weights for policy 1, policy_version 234990 (0.0008) -[2023-11-28 06:22:19,175][87426] Updated weights for policy 1, policy_version 235000 (0.0010) -[2023-11-28 06:22:19,475][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000235008_60162048.pth... -[2023-11-28 06:22:19,506][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000232416_59498496.pth -[2023-11-28 06:22:20,788][87424] Updated weights for policy 0, policy_version 235297 (0.0011) -[2023-11-28 06:22:21,167][87424] Updated weights for policy 0, policy_version 235307 (0.0011) -[2023-11-28 06:22:21,323][87426] Updated weights for policy 1, policy_version 235010 (0.0008) -[2023-11-28 06:22:21,553][87424] Updated weights for policy 0, policy_version 235317 (0.0011) -[2023-11-28 06:22:21,694][87426] Updated weights for policy 1, policy_version 235020 (0.0010) -[2023-11-28 06:22:21,924][87424] Updated weights for policy 0, policy_version 235327 (0.0009) -[2023-11-28 06:22:22,081][87426] Updated weights for policy 1, policy_version 235030 (0.0010) -[2023-11-28 06:22:22,455][87426] Updated weights for policy 1, policy_version 235040 (0.0011) -[2023-11-28 06:22:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120414208. Throughput: 0: 2695.9, 1: 2753.6. Samples: 120427640. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:23,445][86177] Avg episode reward: [(0, '-509.470'), (1, '-534.810')] -[2023-11-28 06:22:24,511][87424] Updated weights for policy 0, policy_version 235337 (0.0011) -[2023-11-28 06:22:24,895][87424] Updated weights for policy 0, policy_version 235347 (0.0011) -[2023-11-28 06:22:25,021][87426] Updated weights for policy 1, policy_version 235050 (0.0011) -[2023-11-28 06:22:25,272][87424] Updated weights for policy 0, policy_version 235357 (0.0009) -[2023-11-28 06:22:25,405][87426] Updated weights for policy 1, policy_version 235060 (0.0009) -[2023-11-28 06:22:25,779][87426] Updated weights for policy 1, policy_version 235070 (0.0007) -[2023-11-28 06:22:27,505][87424] Updated weights for policy 0, policy_version 235367 (0.0011) -[2023-11-28 06:22:27,879][87426] Updated weights for policy 1, policy_version 235080 (0.0009) -[2023-11-28 06:22:27,886][87424] Updated weights for policy 0, policy_version 235377 (0.0010) -[2023-11-28 06:22:28,250][87426] Updated weights for policy 1, policy_version 235090 (0.0007) -[2023-11-28 06:22:28,267][87424] Updated weights for policy 0, policy_version 235387 (0.0008) -[2023-11-28 06:22:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 120430592. Throughput: 0: 2696.7, 1: 2758.0. Samples: 120452804. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:28,445][86177] Avg episode reward: [(0, '-509.730'), (1, '-548.990')] -[2023-11-28 06:22:28,630][87426] Updated weights for policy 1, policy_version 235100 (0.0007) -[2023-11-28 06:22:30,453][87424] Updated weights for policy 0, policy_version 235397 (0.0009) -[2023-11-28 06:22:30,837][87424] Updated weights for policy 0, policy_version 235407 (0.0011) -[2023-11-28 06:22:31,019][87426] Updated weights for policy 1, policy_version 235110 (0.0010) -[2023-11-28 06:22:31,226][87424] Updated weights for policy 0, policy_version 235417 (0.0009) -[2023-11-28 06:22:31,406][87426] Updated weights for policy 1, policy_version 235120 (0.0012) -[2023-11-28 06:22:31,776][87426] Updated weights for policy 1, policy_version 235130 (0.0012) -[2023-11-28 06:22:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120463360. Throughput: 0: 2718.0, 1: 2738.5. Samples: 120477628. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:33,445][86177] Avg episode reward: [(0, '-497.000'), (1, '-543.650')] -[2023-11-28 06:22:33,594][87426] Updated weights for policy 1, policy_version 235140 (0.0010) -[2023-11-28 06:22:33,742][87424] Updated weights for policy 0, policy_version 235427 (0.0010) -[2023-11-28 06:22:33,973][87426] Updated weights for policy 1, policy_version 235150 (0.0008) -[2023-11-28 06:22:34,111][87424] Updated weights for policy 0, policy_version 235437 (0.0011) -[2023-11-28 06:22:34,359][87426] Updated weights for policy 1, policy_version 235160 (0.0007) -[2023-11-28 06:22:34,497][87424] Updated weights for policy 0, policy_version 235447 (0.0010) -[2023-11-28 06:22:36,726][87426] Updated weights for policy 1, policy_version 235170 (0.0008) -[2023-11-28 06:22:36,753][87424] Updated weights for policy 0, policy_version 235457 (0.0008) -[2023-11-28 06:22:37,111][87426] Updated weights for policy 1, policy_version 235180 (0.0011) -[2023-11-28 06:22:37,136][87424] Updated weights for policy 0, policy_version 235467 (0.0009) -[2023-11-28 06:22:37,484][87426] Updated weights for policy 1, policy_version 235190 (0.0012) -[2023-11-28 06:22:37,522][87424] Updated weights for policy 0, policy_version 235477 (0.0009) -[2023-11-28 06:22:37,864][87426] Updated weights for policy 1, policy_version 235200 (0.0010) -[2023-11-28 06:22:37,896][87424] Updated weights for policy 0, policy_version 235487 (0.0012) -[2023-11-28 06:22:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 120496128. Throughput: 0: 2705.9, 1: 2723.8. Samples: 120509496. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:38,445][86177] Avg episode reward: [(0, '-506.820'), (1, '-531.440')] -[2023-11-28 06:22:39,630][87426] Updated weights for policy 1, policy_version 235210 (0.0009) -[2023-11-28 06:22:39,801][87424] Updated weights for policy 0, policy_version 235497 (0.0012) -[2023-11-28 06:22:40,010][87426] Updated weights for policy 1, policy_version 235220 (0.0010) -[2023-11-28 06:22:40,195][87424] Updated weights for policy 0, policy_version 235507 (0.0010) -[2023-11-28 06:22:40,403][87426] Updated weights for policy 1, policy_version 235230 (0.0012) -[2023-11-28 06:22:40,571][87424] Updated weights for policy 0, policy_version 235517 (0.0010) -[2023-11-28 06:22:42,724][87426] Updated weights for policy 1, policy_version 235240 (0.0011) -[2023-11-28 06:22:42,756][87424] Updated weights for policy 0, policy_version 235527 (0.0012) -[2023-11-28 06:22:43,107][87426] Updated weights for policy 1, policy_version 235250 (0.0010) -[2023-11-28 06:22:43,131][87424] Updated weights for policy 0, policy_version 235537 (0.0012) -[2023-11-28 06:22:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 120512512. Throughput: 0: 2714.2, 1: 2714.0. Samples: 120533572. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:43,445][86177] Avg episode reward: [(0, '-505.820'), (1, '-526.290')] -[2023-11-28 06:22:43,473][87426] Updated weights for policy 1, policy_version 235260 (0.0011) -[2023-11-28 06:22:43,516][87424] Updated weights for policy 0, policy_version 235547 (0.0011) -[2023-11-28 06:22:45,246][87424] Updated weights for policy 0, policy_version 235557 (0.0012) -[2023-11-28 06:22:45,628][87424] Updated weights for policy 0, policy_version 235567 (0.0012) -[2023-11-28 06:22:46,007][87424] Updated weights for policy 0, policy_version 235577 (0.0011) -[2023-11-28 06:22:46,041][87426] Updated weights for policy 1, policy_version 235270 (0.0009) -[2023-11-28 06:22:46,418][87426] Updated weights for policy 1, policy_version 235280 (0.0007) -[2023-11-28 06:22:46,796][87426] Updated weights for policy 1, policy_version 235290 (0.0007) -[2023-11-28 06:22:48,444][87424] Updated weights for policy 0, policy_version 235587 (0.0010) -[2023-11-28 06:22:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 120545280. Throughput: 0: 2720.8, 1: 2696.8. Samples: 120558440. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:48,445][86177] Avg episode reward: [(0, '-505.340'), (1, '-521.310')] -[2023-11-28 06:22:48,816][87424] Updated weights for policy 0, policy_version 235597 (0.0011) -[2023-11-28 06:22:49,007][87426] Updated weights for policy 1, policy_version 235300 (0.0009) -[2023-11-28 06:22:49,197][87424] Updated weights for policy 0, policy_version 235607 (0.0012) -[2023-11-28 06:22:49,395][87426] Updated weights for policy 1, policy_version 235310 (0.0011) -[2023-11-28 06:22:49,779][87426] Updated weights for policy 1, policy_version 235320 (0.0011) -[2023-11-28 06:22:51,319][87424] Updated weights for policy 0, policy_version 235617 (0.0012) -[2023-11-28 06:22:51,515][87426] Updated weights for policy 1, policy_version 235330 (0.0010) -[2023-11-28 06:22:51,705][87424] Updated weights for policy 0, policy_version 235627 (0.0008) -[2023-11-28 06:22:51,890][87426] Updated weights for policy 1, policy_version 235340 (0.0009) -[2023-11-28 06:22:52,089][87424] Updated weights for policy 0, policy_version 235637 (0.0011) -[2023-11-28 06:22:52,267][87426] Updated weights for policy 1, policy_version 235350 (0.0009) -[2023-11-28 06:22:52,468][87424] Updated weights for policy 0, policy_version 235647 (0.0011) -[2023-11-28 06:22:52,643][87426] Updated weights for policy 1, policy_version 235360 (0.0008) -[2023-11-28 06:22:53,445][86177] Fps is (10 sec: 6553.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 120578048. Throughput: 0: 2720.5, 1: 2724.1. Samples: 120591368. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:53,446][86177] Avg episode reward: [(0, '-520.800'), (1, '-518.870')] -[2023-11-28 06:22:54,818][87424] Updated weights for policy 0, policy_version 235657 (0.0011) -[2023-11-28 06:22:55,147][87426] Updated weights for policy 1, policy_version 235370 (0.0010) -[2023-11-28 06:22:55,191][87424] Updated weights for policy 0, policy_version 235667 (0.0009) -[2023-11-28 06:22:55,525][87426] Updated weights for policy 1, policy_version 235380 (0.0007) -[2023-11-28 06:22:55,578][87424] Updated weights for policy 0, policy_version 235677 (0.0009) -[2023-11-28 06:22:55,904][87426] Updated weights for policy 1, policy_version 235390 (0.0007) -[2023-11-28 06:22:58,038][87426] Updated weights for policy 1, policy_version 235400 (0.0010) -[2023-11-28 06:22:58,104][87424] Updated weights for policy 0, policy_version 235687 (0.0012) -[2023-11-28 06:22:58,422][87426] Updated weights for policy 1, policy_version 235410 (0.0009) -[2023-11-28 06:22:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 120594432. Throughput: 0: 2709.3, 1: 2737.8. Samples: 120616068. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:22:58,445][86177] Avg episode reward: [(0, '-512.210'), (1, '-523.460')] -[2023-11-28 06:22:58,485][87424] Updated weights for policy 0, policy_version 235697 (0.0012) -[2023-11-28 06:22:58,794][87426] Updated weights for policy 1, policy_version 235420 (0.0007) -[2023-11-28 06:22:58,863][87424] Updated weights for policy 0, policy_version 235707 (0.0012) -[2023-11-28 06:23:00,649][87424] Updated weights for policy 0, policy_version 235717 (0.0011) -[2023-11-28 06:23:01,032][87424] Updated weights for policy 0, policy_version 235727 (0.0011) -[2023-11-28 06:23:01,203][87426] Updated weights for policy 1, policy_version 235430 (0.0010) -[2023-11-28 06:23:01,407][87424] Updated weights for policy 0, policy_version 235737 (0.0012) -[2023-11-28 06:23:01,572][87426] Updated weights for policy 1, policy_version 235440 (0.0011) -[2023-11-28 06:23:01,958][87426] Updated weights for policy 1, policy_version 235450 (0.0012) -[2023-11-28 06:23:03,325][87424] Updated weights for policy 0, policy_version 235747 (0.0012) -[2023-11-28 06:23:03,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120627200. Throughput: 0: 2699.1, 1: 2719.6. Samples: 120639504. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:23:03,445][86177] Avg episode reward: [(0, '-512.270'), (1, '-541.590')] -[2023-11-28 06:23:03,701][87424] Updated weights for policy 0, policy_version 235757 (0.0012) -[2023-11-28 06:23:04,080][87424] Updated weights for policy 0, policy_version 235767 (0.0011) -[2023-11-28 06:23:04,236][87426] Updated weights for policy 1, policy_version 235460 (0.0010) -[2023-11-28 06:23:04,618][87426] Updated weights for policy 1, policy_version 235470 (0.0008) -[2023-11-28 06:23:05,002][87426] Updated weights for policy 1, policy_version 235480 (0.0010) -[2023-11-28 06:23:06,386][87424] Updated weights for policy 0, policy_version 235777 (0.0011) -[2023-11-28 06:23:06,776][87424] Updated weights for policy 0, policy_version 235787 (0.0008) -[2023-11-28 06:23:07,157][87424] Updated weights for policy 0, policy_version 235797 (0.0008) -[2023-11-28 06:23:07,529][87426] Updated weights for policy 1, policy_version 235490 (0.0011) -[2023-11-28 06:23:07,540][87424] Updated weights for policy 0, policy_version 235807 (0.0008) -[2023-11-28 06:23:07,906][87426] Updated weights for policy 1, policy_version 235500 (0.0011) -[2023-11-28 06:23:08,279][87426] Updated weights for policy 1, policy_version 235510 (0.0012) -[2023-11-28 06:23:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 120651776. Throughput: 0: 2723.3, 1: 2708.6. Samples: 120672076. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:23:08,445][86177] Avg episode reward: [(0, '-512.540'), (1, '-537.040')] -[2023-11-28 06:23:08,658][87426] Updated weights for policy 1, policy_version 235520 (0.0011) -[2023-11-28 06:23:09,314][87424] Updated weights for policy 0, policy_version 235817 (0.0011) -[2023-11-28 06:23:09,700][87424] Updated weights for policy 0, policy_version 235827 (0.0010) -[2023-11-28 06:23:10,079][87424] Updated weights for policy 0, policy_version 235837 (0.0011) -[2023-11-28 06:23:10,973][87426] Updated weights for policy 1, policy_version 235530 (0.0011) -[2023-11-28 06:23:11,351][87426] Updated weights for policy 1, policy_version 235540 (0.0012) -[2023-11-28 06:23:11,737][87426] Updated weights for policy 1, policy_version 235550 (0.0012) -[2023-11-28 06:23:12,694][87424] Updated weights for policy 0, policy_version 235847 (0.0008) -[2023-11-28 06:23:13,073][87424] Updated weights for policy 0, policy_version 235857 (0.0009) -[2023-11-28 06:23:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 120676352. Throughput: 0: 2718.8, 1: 2685.0. Samples: 120695972. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:23:13,445][86177] Avg episode reward: [(0, '-539.310'), (1, '-527.020')] -[2023-11-28 06:23:13,455][87424] Updated weights for policy 0, policy_version 235867 (0.0011) -[2023-11-28 06:23:13,771][87426] Updated weights for policy 1, policy_version 235560 (0.0011) -[2023-11-28 06:23:14,146][87426] Updated weights for policy 1, policy_version 235570 (0.0011) -[2023-11-28 06:23:14,528][87426] Updated weights for policy 1, policy_version 235580 (0.0007) -[2023-11-28 06:23:15,288][87424] Updated weights for policy 0, policy_version 235877 (0.0012) -[2023-11-28 06:23:15,677][87424] Updated weights for policy 0, policy_version 235887 (0.0011) -[2023-11-28 06:23:16,054][87424] Updated weights for policy 0, policy_version 235897 (0.0009) -[2023-11-28 06:23:16,802][87426] Updated weights for policy 1, policy_version 235590 (0.0008) -[2023-11-28 06:23:17,189][87426] Updated weights for policy 1, policy_version 235600 (0.0010) -[2023-11-28 06:23:17,576][87426] Updated weights for policy 1, policy_version 235610 (0.0009) -[2023-11-28 06:23:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120709120. Throughput: 0: 2712.6, 1: 2682.9. Samples: 120720428. Policy #0 lag: (min: 31.0, avg: 41.0, max: 63.0) -[2023-11-28 06:23:18,445][86177] Avg episode reward: [(0, '-536.570'), (1, '-525.760')] -[2023-11-28 06:23:18,466][87424] Updated weights for policy 0, policy_version 235907 (0.0009) -[2023-11-28 06:23:18,841][87424] Updated weights for policy 0, policy_version 235917 (0.0012) -[2023-11-28 06:23:19,215][87424] Updated weights for policy 0, policy_version 235927 (0.0012) -[2023-11-28 06:23:19,661][87426] Updated weights for policy 1, policy_version 235620 (0.0009) -[2023-11-28 06:23:20,037][87426] Updated weights for policy 1, policy_version 235630 (0.0012) -[2023-11-28 06:23:20,420][87426] Updated weights for policy 1, policy_version 235640 (0.0011) -[2023-11-28 06:23:21,652][87424] Updated weights for policy 0, policy_version 235937 (0.0011) -[2023-11-28 06:23:22,037][87424] Updated weights for policy 0, policy_version 235947 (0.0009) -[2023-11-28 06:23:22,413][87424] Updated weights for policy 0, policy_version 235957 (0.0009) -[2023-11-28 06:23:22,800][87424] Updated weights for policy 0, policy_version 235967 (0.0008) -[2023-11-28 06:23:22,936][87426] Updated weights for policy 1, policy_version 235650 (0.0009) -[2023-11-28 06:23:23,301][87426] Updated weights for policy 1, policy_version 235660 (0.0010) -[2023-11-28 06:23:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 120733696. Throughput: 0: 2728.4, 1: 2677.2. Samples: 120752744. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:23:23,445][86177] Avg episode reward: [(0, '-535.340'), (1, '-552.710')] -[2023-11-28 06:23:23,678][87426] Updated weights for policy 1, policy_version 235670 (0.0008) -[2023-11-28 06:23:24,062][87426] Updated weights for policy 1, policy_version 235680 (0.0008) -[2023-11-28 06:23:25,170][87424] Updated weights for policy 0, policy_version 235977 (0.0011) -[2023-11-28 06:23:25,559][87424] Updated weights for policy 0, policy_version 235987 (0.0012) -[2023-11-28 06:23:25,932][87424] Updated weights for policy 0, policy_version 235997 (0.0012) -[2023-11-28 06:23:26,348][87426] Updated weights for policy 1, policy_version 235690 (0.0012) -[2023-11-28 06:23:26,728][87426] Updated weights for policy 1, policy_version 235700 (0.0012) -[2023-11-28 06:23:27,108][87426] Updated weights for policy 1, policy_version 235710 (0.0011) -[2023-11-28 06:23:27,790][87424] Updated weights for policy 0, policy_version 236007 (0.0010) -[2023-11-28 06:23:28,169][87424] Updated weights for policy 0, policy_version 236017 (0.0007) -[2023-11-28 06:23:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120758272. Throughput: 0: 2722.1, 1: 2672.1. Samples: 120776308. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:23:28,445][86177] Avg episode reward: [(0, '-535.180'), (1, '-552.460')] -[2023-11-28 06:23:28,556][87424] Updated weights for policy 0, policy_version 236027 (0.0007) -[2023-11-28 06:23:29,469][87426] Updated weights for policy 1, policy_version 235720 (0.0008) -[2023-11-28 06:23:29,846][87426] Updated weights for policy 1, policy_version 235730 (0.0009) -[2023-11-28 06:23:30,222][87426] Updated weights for policy 1, policy_version 235740 (0.0012) -[2023-11-28 06:23:30,816][87424] Updated weights for policy 0, policy_version 236037 (0.0010) -[2023-11-28 06:23:31,206][87424] Updated weights for policy 0, policy_version 236047 (0.0012) -[2023-11-28 06:23:31,591][87424] Updated weights for policy 0, policy_version 236057 (0.0012) -[2023-11-28 06:23:32,266][87426] Updated weights for policy 1, policy_version 235750 (0.0010) -[2023-11-28 06:23:32,641][87426] Updated weights for policy 1, policy_version 235760 (0.0010) -[2023-11-28 06:23:33,022][87426] Updated weights for policy 1, policy_version 235770 (0.0010) -[2023-11-28 06:23:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 120791040. Throughput: 0: 2700.4, 1: 2688.5. Samples: 120800944. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:23:33,446][86177] Avg episode reward: [(0, '-494.080'), (1, '-568.400')] -[2023-11-28 06:23:34,038][87424] Updated weights for policy 0, policy_version 236067 (0.0012) -[2023-11-28 06:23:34,416][87424] Updated weights for policy 0, policy_version 236077 (0.0011) -[2023-11-28 06:23:34,749][87426] Updated weights for policy 1, policy_version 235780 (0.0011) -[2023-11-28 06:23:34,802][87424] Updated weights for policy 0, policy_version 236087 (0.0008) -[2023-11-28 06:23:35,126][87426] Updated weights for policy 1, policy_version 235790 (0.0011) -[2023-11-28 06:23:35,509][87426] Updated weights for policy 1, policy_version 235800 (0.0011) -[2023-11-28 06:23:36,853][87424] Updated weights for policy 0, policy_version 236097 (0.0010) -[2023-11-28 06:23:37,231][87424] Updated weights for policy 0, policy_version 236107 (0.0012) -[2023-11-28 06:23:37,273][87426] Updated weights for policy 1, policy_version 235810 (0.0011) -[2023-11-28 06:23:37,616][87424] Updated weights for policy 0, policy_version 236117 (0.0012) -[2023-11-28 06:23:37,653][87426] Updated weights for policy 1, policy_version 235820 (0.0012) -[2023-11-28 06:23:38,006][87424] Updated weights for policy 0, policy_version 236127 (0.0011) -[2023-11-28 06:23:38,027][87426] Updated weights for policy 1, policy_version 235830 (0.0011) -[2023-11-28 06:23:38,398][87426] Updated weights for policy 1, policy_version 235840 (0.0009) -[2023-11-28 06:23:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 120823808. Throughput: 0: 2731.1, 1: 2697.6. Samples: 120835656. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:23:38,445][86177] Avg episode reward: [(0, '-498.450'), (1, '-571.480')] -[2023-11-28 06:23:40,438][87424] Updated weights for policy 0, policy_version 236137 (0.0011) -[2023-11-28 06:23:40,678][87426] Updated weights for policy 1, policy_version 235850 (0.0011) -[2023-11-28 06:23:40,824][87424] Updated weights for policy 0, policy_version 236147 (0.0012) -[2023-11-28 06:23:41,059][87426] Updated weights for policy 1, policy_version 235860 (0.0011) -[2023-11-28 06:23:41,205][87424] Updated weights for policy 0, policy_version 236157 (0.0012) -[2023-11-28 06:23:41,435][87426] Updated weights for policy 1, policy_version 235870 (0.0011) -[2023-11-28 06:23:43,221][87424] Updated weights for policy 0, policy_version 236167 (0.0012) -[2023-11-28 06:23:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120840192. Throughput: 0: 2727.8, 1: 2686.0. Samples: 120859688. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:23:43,445][86177] Avg episode reward: [(0, '-498.120'), (1, '-528.190')] -[2023-11-28 06:23:43,599][87424] Updated weights for policy 0, policy_version 236177 (0.0008) -[2023-11-28 06:23:43,828][87426] Updated weights for policy 1, policy_version 235880 (0.0008) -[2023-11-28 06:23:43,990][87424] Updated weights for policy 0, policy_version 236187 (0.0008) -[2023-11-28 06:23:44,206][87426] Updated weights for policy 1, policy_version 235890 (0.0008) -[2023-11-28 06:23:44,582][87426] Updated weights for policy 1, policy_version 235900 (0.0007) -[2023-11-28 06:23:45,514][87424] Updated weights for policy 0, policy_version 236197 (0.0010) -[2023-11-28 06:23:45,897][87424] Updated weights for policy 0, policy_version 236207 (0.0008) -[2023-11-28 06:23:46,289][87424] Updated weights for policy 0, policy_version 236217 (0.0010) -[2023-11-28 06:23:46,752][87426] Updated weights for policy 1, policy_version 235910 (0.0008) -[2023-11-28 06:23:47,136][87426] Updated weights for policy 1, policy_version 235920 (0.0007) -[2023-11-28 06:23:47,519][87426] Updated weights for policy 1, policy_version 235930 (0.0008) -[2023-11-28 06:23:48,029][87424] Updated weights for policy 0, policy_version 236227 (0.0009) -[2023-11-28 06:23:48,408][87424] Updated weights for policy 0, policy_version 236237 (0.0009) -[2023-11-28 06:23:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 120872960. Throughput: 0: 2750.0, 1: 2688.8. Samples: 120884252. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:23:48,445][86177] Avg episode reward: [(0, '-501.040'), (1, '-527.190')] -[2023-11-28 06:23:48,786][87424] Updated weights for policy 0, policy_version 236247 (0.0008) -[2023-11-28 06:23:49,681][87426] Updated weights for policy 1, policy_version 235940 (0.0008) -[2023-11-28 06:23:50,061][87426] Updated weights for policy 1, policy_version 235950 (0.0008) -[2023-11-28 06:23:50,434][87426] Updated weights for policy 1, policy_version 235960 (0.0008) -[2023-11-28 06:23:51,016][87424] Updated weights for policy 0, policy_version 236257 (0.0008) -[2023-11-28 06:23:51,394][87424] Updated weights for policy 0, policy_version 236267 (0.0012) -[2023-11-28 06:23:51,782][87424] Updated weights for policy 0, policy_version 236277 (0.0012) -[2023-11-28 06:23:52,157][87424] Updated weights for policy 0, policy_version 236287 (0.0012) -[2023-11-28 06:23:52,866][87426] Updated weights for policy 1, policy_version 235970 (0.0011) -[2023-11-28 06:23:53,246][87426] Updated weights for policy 1, policy_version 235980 (0.0010) -[2023-11-28 06:23:53,445][86177] Fps is (10 sec: 5733.8, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 120897536. Throughput: 0: 2744.3, 1: 2698.6. Samples: 120917012. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:23:53,446][86177] Avg episode reward: [(0, '-494.540'), (1, '-516.770')] -[2023-11-28 06:23:53,630][87426] Updated weights for policy 1, policy_version 235990 (0.0011) -[2023-11-28 06:23:54,006][87426] Updated weights for policy 1, policy_version 236000 (0.0012) -[2023-11-28 06:23:54,614][87424] Updated weights for policy 0, policy_version 236297 (0.0011) -[2023-11-28 06:23:55,002][87424] Updated weights for policy 0, policy_version 236307 (0.0012) -[2023-11-28 06:23:55,389][87424] Updated weights for policy 0, policy_version 236317 (0.0012) -[2023-11-28 06:23:56,139][87426] Updated weights for policy 1, policy_version 236010 (0.0008) -[2023-11-28 06:23:56,515][87426] Updated weights for policy 1, policy_version 236020 (0.0007) -[2023-11-28 06:23:56,902][87426] Updated weights for policy 1, policy_version 236030 (0.0007) -[2023-11-28 06:23:57,080][87424] Updated weights for policy 0, policy_version 236327 (0.0012) -[2023-11-28 06:23:57,455][87424] Updated weights for policy 0, policy_version 236337 (0.0012) -[2023-11-28 06:23:57,835][87424] Updated weights for policy 0, policy_version 236347 (0.0008) -[2023-11-28 06:23:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 120930304. Throughput: 0: 2740.2, 1: 2714.2. Samples: 120941420. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:23:58,445][86177] Avg episode reward: [(0, '-492.990'), (1, '-510.000')] -[2023-11-28 06:23:58,653][87426] Updated weights for policy 1, policy_version 236040 (0.0011) -[2023-11-28 06:23:59,031][87426] Updated weights for policy 1, policy_version 236050 (0.0011) -[2023-11-28 06:23:59,412][87426] Updated weights for policy 1, policy_version 236060 (0.0011) -[2023-11-28 06:23:59,918][87424] Updated weights for policy 0, policy_version 236357 (0.0011) -[2023-11-28 06:24:00,309][87424] Updated weights for policy 0, policy_version 236367 (0.0008) -[2023-11-28 06:24:00,681][87424] Updated weights for policy 0, policy_version 236377 (0.0010) -[2023-11-28 06:24:01,800][87426] Updated weights for policy 1, policy_version 236070 (0.0010) -[2023-11-28 06:24:02,174][87426] Updated weights for policy 1, policy_version 236080 (0.0009) -[2023-11-28 06:24:02,560][87426] Updated weights for policy 1, policy_version 236090 (0.0011) -[2023-11-28 06:24:03,180][87424] Updated weights for policy 0, policy_version 236387 (0.0010) -[2023-11-28 06:24:03,444][86177] Fps is (10 sec: 5734.9, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 120954880. Throughput: 0: 2769.6, 1: 2701.3. Samples: 120966620. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:24:03,445][86177] Avg episode reward: [(0, '-496.380'), (1, '-512.150')] -[2023-11-28 06:24:03,560][87424] Updated weights for policy 0, policy_version 236397 (0.0008) -[2023-11-28 06:24:03,944][87424] Updated weights for policy 0, policy_version 236407 (0.0007) -[2023-11-28 06:24:04,403][87426] Updated weights for policy 1, policy_version 236100 (0.0012) -[2023-11-28 06:24:04,784][87426] Updated weights for policy 1, policy_version 236110 (0.0011) -[2023-11-28 06:24:05,170][87426] Updated weights for policy 1, policy_version 236120 (0.0011) -[2023-11-28 06:24:05,971][87424] Updated weights for policy 0, policy_version 236417 (0.0008) -[2023-11-28 06:24:06,356][87424] Updated weights for policy 0, policy_version 236427 (0.0012) -[2023-11-28 06:24:06,743][87424] Updated weights for policy 0, policy_version 236437 (0.0010) -[2023-11-28 06:24:07,129][87424] Updated weights for policy 0, policy_version 236447 (0.0008) -[2023-11-28 06:24:07,315][87426] Updated weights for policy 1, policy_version 236130 (0.0008) -[2023-11-28 06:24:07,693][87426] Updated weights for policy 1, policy_version 236140 (0.0011) -[2023-11-28 06:24:08,065][87426] Updated weights for policy 1, policy_version 236150 (0.0012) -[2023-11-28 06:24:08,444][87426] Updated weights for policy 1, policy_version 236160 (0.0012) -[2023-11-28 06:24:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 120987648. Throughput: 0: 2774.8, 1: 2727.3. Samples: 121000340. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:24:08,445][86177] Avg episode reward: [(0, '-505.770'), (1, '-519.200')] -[2023-11-28 06:24:09,466][87424] Updated weights for policy 0, policy_version 236457 (0.0011) -[2023-11-28 06:24:09,846][87424] Updated weights for policy 0, policy_version 236467 (0.0010) -[2023-11-28 06:24:10,236][87424] Updated weights for policy 0, policy_version 236477 (0.0010) -[2023-11-28 06:24:10,519][87426] Updated weights for policy 1, policy_version 236170 (0.0011) -[2023-11-28 06:24:10,905][87426] Updated weights for policy 1, policy_version 236180 (0.0011) -[2023-11-28 06:24:11,274][87426] Updated weights for policy 1, policy_version 236190 (0.0011) -[2023-11-28 06:24:12,315][87424] Updated weights for policy 0, policy_version 236487 (0.0012) -[2023-11-28 06:24:12,705][87424] Updated weights for policy 0, policy_version 236497 (0.0012) -[2023-11-28 06:24:13,074][87424] Updated weights for policy 0, policy_version 236507 (0.0012) -[2023-11-28 06:24:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 121012224. Throughput: 0: 2763.1, 1: 2744.5. Samples: 121024152. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:24:13,445][86177] Avg episode reward: [(0, '-507.610'), (1, '-519.090')] -[2023-11-28 06:24:13,693][87426] Updated weights for policy 1, policy_version 236200 (0.0010) -[2023-11-28 06:24:14,069][87426] Updated weights for policy 1, policy_version 236210 (0.0007) -[2023-11-28 06:24:14,443][87426] Updated weights for policy 1, policy_version 236220 (0.0011) -[2023-11-28 06:24:15,040][87424] Updated weights for policy 0, policy_version 236517 (0.0011) -[2023-11-28 06:24:15,424][87424] Updated weights for policy 0, policy_version 236527 (0.0011) -[2023-11-28 06:24:15,800][87424] Updated weights for policy 0, policy_version 236537 (0.0012) -[2023-11-28 06:24:16,247][87426] Updated weights for policy 1, policy_version 236230 (0.0011) -[2023-11-28 06:24:16,630][87426] Updated weights for policy 1, policy_version 236240 (0.0011) -[2023-11-28 06:24:17,003][87426] Updated weights for policy 1, policy_version 236250 (0.0010) -[2023-11-28 06:24:17,783][87424] Updated weights for policy 0, policy_version 236547 (0.0010) -[2023-11-28 06:24:18,170][87424] Updated weights for policy 0, policy_version 236557 (0.0007) -[2023-11-28 06:24:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121036800. Throughput: 0: 2782.2, 1: 2767.9. Samples: 121050700. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:24:18,445][86177] Avg episode reward: [(0, '-510.040'), (1, '-526.940')] -[2023-11-28 06:24:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000236256_60481536.pth... -[2023-11-28 06:24:18,496][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000233728_59834368.pth -[2023-11-28 06:24:18,550][87424] Updated weights for policy 0, policy_version 236567 (0.0010) -[2023-11-28 06:24:18,890][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000236576_60563456.pth... -[2023-11-28 06:24:18,936][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000234016_59908096.pth -[2023-11-28 06:24:19,385][87426] Updated weights for policy 1, policy_version 236260 (0.0009) -[2023-11-28 06:24:19,760][87426] Updated weights for policy 1, policy_version 236270 (0.0012) -[2023-11-28 06:24:20,139][87426] Updated weights for policy 1, policy_version 236280 (0.0012) -[2023-11-28 06:24:20,693][87424] Updated weights for policy 0, policy_version 236577 (0.0011) -[2023-11-28 06:24:21,074][87424] Updated weights for policy 0, policy_version 236587 (0.0009) -[2023-11-28 06:24:21,456][87424] Updated weights for policy 0, policy_version 236597 (0.0008) -[2023-11-28 06:24:21,841][87424] Updated weights for policy 0, policy_version 236607 (0.0011) -[2023-11-28 06:24:22,646][87426] Updated weights for policy 1, policy_version 236290 (0.0011) -[2023-11-28 06:24:23,024][87426] Updated weights for policy 1, policy_version 236300 (0.0010) -[2023-11-28 06:24:23,408][87426] Updated weights for policy 1, policy_version 236310 (0.0012) -[2023-11-28 06:24:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121061376. Throughput: 0: 2777.2, 1: 2727.6. Samples: 121083372. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:24:23,445][86177] Avg episode reward: [(0, '-503.840'), (1, '-522.830')] -[2023-11-28 06:24:23,782][87426] Updated weights for policy 1, policy_version 236320 (0.0011) -[2023-11-28 06:24:24,086][87424] Updated weights for policy 0, policy_version 236617 (0.0011) -[2023-11-28 06:24:24,465][87424] Updated weights for policy 0, policy_version 236627 (0.0012) -[2023-11-28 06:24:24,852][87424] Updated weights for policy 0, policy_version 236637 (0.0012) -[2023-11-28 06:24:25,564][87426] Updated weights for policy 1, policy_version 236330 (0.0012) -[2023-11-28 06:24:25,952][87426] Updated weights for policy 1, policy_version 236340 (0.0011) -[2023-11-28 06:24:26,329][87426] Updated weights for policy 1, policy_version 236350 (0.0007) -[2023-11-28 06:24:26,960][87424] Updated weights for policy 0, policy_version 236647 (0.0012) -[2023-11-28 06:24:27,336][87424] Updated weights for policy 0, policy_version 236657 (0.0012) -[2023-11-28 06:24:27,726][87424] Updated weights for policy 0, policy_version 236667 (0.0011) -[2023-11-28 06:24:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 121094144. Throughput: 0: 2783.5, 1: 2763.7. Samples: 121109312. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:24:28,445][86177] Avg episode reward: [(0, '-495.340'), (1, '-514.260')] -[2023-11-28 06:24:28,572][87426] Updated weights for policy 1, policy_version 236360 (0.0011) -[2023-11-28 06:24:28,962][87426] Updated weights for policy 1, policy_version 236370 (0.0012) -[2023-11-28 06:24:29,342][87426] Updated weights for policy 1, policy_version 236380 (0.0012) -[2023-11-28 06:24:29,642][87424] Updated weights for policy 0, policy_version 236677 (0.0010) -[2023-11-28 06:24:30,015][87424] Updated weights for policy 0, policy_version 236687 (0.0012) -[2023-11-28 06:24:30,393][87424] Updated weights for policy 0, policy_version 236697 (0.0012) -[2023-11-28 06:24:31,086][87426] Updated weights for policy 1, policy_version 236390 (0.0009) -[2023-11-28 06:24:31,462][87426] Updated weights for policy 1, policy_version 236400 (0.0008) -[2023-11-28 06:24:31,847][87426] Updated weights for policy 1, policy_version 236410 (0.0011) -[2023-11-28 06:24:32,879][87424] Updated weights for policy 0, policy_version 236707 (0.0012) -[2023-11-28 06:24:33,273][87424] Updated weights for policy 0, policy_version 236717 (0.0012) -[2023-11-28 06:24:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121118720. Throughput: 0: 2779.7, 1: 2783.7. Samples: 121134608. Policy #0 lag: (min: 31.0, avg: 54.6, max: 95.0) -[2023-11-28 06:24:33,445][86177] Avg episode reward: [(0, '-495.840'), (1, '-509.320')] -[2023-11-28 06:24:33,641][87426] Updated weights for policy 1, policy_version 236420 (0.0009) -[2023-11-28 06:24:33,650][87424] Updated weights for policy 0, policy_version 236727 (0.0012) -[2023-11-28 06:24:34,022][87426] Updated weights for policy 1, policy_version 236430 (0.0007) -[2023-11-28 06:24:34,403][87426] Updated weights for policy 1, policy_version 236440 (0.0007) -[2023-11-28 06:24:35,537][87424] Updated weights for policy 0, policy_version 236737 (0.0007) -[2023-11-28 06:24:35,920][87424] Updated weights for policy 0, policy_version 236747 (0.0007) -[2023-11-28 06:24:36,307][87424] Updated weights for policy 0, policy_version 236757 (0.0007) -[2023-11-28 06:24:36,686][87424] Updated weights for policy 0, policy_version 236767 (0.0008) -[2023-11-28 06:24:36,900][87426] Updated weights for policy 1, policy_version 236450 (0.0009) -[2023-11-28 06:24:37,278][87426] Updated weights for policy 1, policy_version 236460 (0.0011) -[2023-11-28 06:24:37,657][87426] Updated weights for policy 1, policy_version 236470 (0.0008) -[2023-11-28 06:24:38,031][87426] Updated weights for policy 1, policy_version 236480 (0.0007) -[2023-11-28 06:24:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 121151488. Throughput: 0: 2767.5, 1: 2804.6. Samples: 121167752. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:24:38,445][86177] Avg episode reward: [(0, '-494.120'), (1, '-509.100')] -[2023-11-28 06:24:38,706][87424] Updated weights for policy 0, policy_version 236777 (0.0008) -[2023-11-28 06:24:39,086][87424] Updated weights for policy 0, policy_version 236787 (0.0010) -[2023-11-28 06:24:39,466][87424] Updated weights for policy 0, policy_version 236797 (0.0011) -[2023-11-28 06:24:39,844][87426] Updated weights for policy 1, policy_version 236490 (0.0010) -[2023-11-28 06:24:40,225][87426] Updated weights for policy 1, policy_version 236500 (0.0012) -[2023-11-28 06:24:40,601][87426] Updated weights for policy 1, policy_version 236510 (0.0008) -[2023-11-28 06:24:42,018][87424] Updated weights for policy 0, policy_version 236807 (0.0011) -[2023-11-28 06:24:42,411][87424] Updated weights for policy 0, policy_version 236817 (0.0012) -[2023-11-28 06:24:42,800][87424] Updated weights for policy 0, policy_version 236827 (0.0010) -[2023-11-28 06:24:43,099][87426] Updated weights for policy 1, policy_version 236520 (0.0011) -[2023-11-28 06:24:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 121176064. Throughput: 0: 2760.2, 1: 2795.3. Samples: 121191416. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:24:43,446][86177] Avg episode reward: [(0, '-494.170'), (1, '-533.580')] -[2023-11-28 06:24:43,472][87426] Updated weights for policy 1, policy_version 236530 (0.0009) -[2023-11-28 06:24:43,854][87426] Updated weights for policy 1, policy_version 236540 (0.0011) -[2023-11-28 06:24:45,331][87424] Updated weights for policy 0, policy_version 236837 (0.0011) -[2023-11-28 06:24:45,698][87426] Updated weights for policy 1, policy_version 236550 (0.0009) -[2023-11-28 06:24:45,713][87424] Updated weights for policy 0, policy_version 236847 (0.0012) -[2023-11-28 06:24:46,084][87426] Updated weights for policy 1, policy_version 236560 (0.0008) -[2023-11-28 06:24:46,096][87424] Updated weights for policy 0, policy_version 236857 (0.0011) -[2023-11-28 06:24:46,455][87426] Updated weights for policy 1, policy_version 236570 (0.0008) -[2023-11-28 06:24:48,350][87424] Updated weights for policy 0, policy_version 236867 (0.0008) -[2023-11-28 06:24:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121200640. Throughput: 0: 2705.5, 1: 2807.4. Samples: 121214700. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:24:48,446][86177] Avg episode reward: [(0, '-495.890'), (1, '-533.750')] -[2023-11-28 06:24:48,476][87426] Updated weights for policy 1, policy_version 236580 (0.0009) -[2023-11-28 06:24:48,731][87424] Updated weights for policy 0, policy_version 236877 (0.0007) -[2023-11-28 06:24:48,850][87426] Updated weights for policy 1, policy_version 236590 (0.0010) -[2023-11-28 06:24:49,116][87424] Updated weights for policy 0, policy_version 236887 (0.0010) -[2023-11-28 06:24:49,231][87426] Updated weights for policy 1, policy_version 236600 (0.0009) -[2023-11-28 06:24:50,975][87424] Updated weights for policy 0, policy_version 236897 (0.0010) -[2023-11-28 06:24:51,361][87424] Updated weights for policy 0, policy_version 236907 (0.0011) -[2023-11-28 06:24:51,396][87426] Updated weights for policy 1, policy_version 236610 (0.0011) -[2023-11-28 06:24:51,747][87424] Updated weights for policy 0, policy_version 236917 (0.0012) -[2023-11-28 06:24:51,769][87426] Updated weights for policy 1, policy_version 236620 (0.0012) -[2023-11-28 06:24:52,120][87424] Updated weights for policy 0, policy_version 236927 (0.0009) -[2023-11-28 06:24:52,152][87426] Updated weights for policy 1, policy_version 236630 (0.0011) -[2023-11-28 06:24:52,523][87426] Updated weights for policy 1, policy_version 236640 (0.0012) -[2023-11-28 06:24:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5598.0, 300 sec: 5442.8). Total num frames: 121233408. Throughput: 0: 2694.2, 1: 2785.4. Samples: 121246924. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:24:53,445][86177] Avg episode reward: [(0, '-502.900'), (1, '-567.400')] -[2023-11-28 06:24:54,270][87424] Updated weights for policy 0, policy_version 236937 (0.0011) -[2023-11-28 06:24:54,649][87424] Updated weights for policy 0, policy_version 236947 (0.0012) -[2023-11-28 06:24:54,817][87426] Updated weights for policy 1, policy_version 236650 (0.0012) -[2023-11-28 06:24:55,033][87424] Updated weights for policy 0, policy_version 236957 (0.0012) -[2023-11-28 06:24:55,191][87426] Updated weights for policy 1, policy_version 236660 (0.0008) -[2023-11-28 06:24:55,576][87426] Updated weights for policy 1, policy_version 236670 (0.0007) -[2023-11-28 06:24:57,226][87424] Updated weights for policy 0, policy_version 236967 (0.0012) -[2023-11-28 06:24:57,601][87424] Updated weights for policy 0, policy_version 236977 (0.0010) -[2023-11-28 06:24:57,702][87426] Updated weights for policy 1, policy_version 236680 (0.0007) -[2023-11-28 06:24:57,982][87424] Updated weights for policy 0, policy_version 236987 (0.0009) -[2023-11-28 06:24:58,079][87426] Updated weights for policy 1, policy_version 236690 (0.0008) -[2023-11-28 06:24:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121257984. Throughput: 0: 2708.5, 1: 2794.9. Samples: 121271808. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:24:58,445][86177] Avg episode reward: [(0, '-514.300'), (1, '-579.500')] -[2023-11-28 06:24:58,462][87426] Updated weights for policy 1, policy_version 236700 (0.0008) -[2023-11-28 06:25:00,292][87424] Updated weights for policy 0, policy_version 236997 (0.0008) -[2023-11-28 06:25:00,671][87424] Updated weights for policy 0, policy_version 237007 (0.0010) -[2023-11-28 06:25:00,706][87426] Updated weights for policy 1, policy_version 236710 (0.0008) -[2023-11-28 06:25:01,053][87424] Updated weights for policy 0, policy_version 237017 (0.0012) -[2023-11-28 06:25:01,077][87426] Updated weights for policy 1, policy_version 236720 (0.0008) -[2023-11-28 06:25:01,462][87426] Updated weights for policy 1, policy_version 236730 (0.0010) -[2023-11-28 06:25:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 121282560. Throughput: 0: 2679.2, 1: 2782.0. Samples: 121296452. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:25:03,445][86177] Avg episode reward: [(0, '-526.510'), (1, '-554.940')] -[2023-11-28 06:25:03,483][87424] Updated weights for policy 0, policy_version 237027 (0.0010) -[2023-11-28 06:25:03,857][87424] Updated weights for policy 0, policy_version 237037 (0.0008) -[2023-11-28 06:25:03,979][87426] Updated weights for policy 1, policy_version 236740 (0.0011) -[2023-11-28 06:25:04,237][87424] Updated weights for policy 0, policy_version 237047 (0.0007) -[2023-11-28 06:25:04,360][87426] Updated weights for policy 1, policy_version 236750 (0.0009) -[2023-11-28 06:25:04,738][87426] Updated weights for policy 1, policy_version 236760 (0.0008) -[2023-11-28 06:25:06,211][87424] Updated weights for policy 0, policy_version 237057 (0.0010) -[2023-11-28 06:25:06,558][87426] Updated weights for policy 1, policy_version 236770 (0.0008) -[2023-11-28 06:25:06,590][87424] Updated weights for policy 0, policy_version 237067 (0.0012) -[2023-11-28 06:25:06,936][87426] Updated weights for policy 1, policy_version 236780 (0.0012) -[2023-11-28 06:25:06,966][87424] Updated weights for policy 0, policy_version 237077 (0.0011) -[2023-11-28 06:25:07,322][87426] Updated weights for policy 1, policy_version 236790 (0.0012) -[2023-11-28 06:25:07,348][87424] Updated weights for policy 0, policy_version 237087 (0.0008) -[2023-11-28 06:25:07,700][87426] Updated weights for policy 1, policy_version 236800 (0.0012) -[2023-11-28 06:25:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 121315328. Throughput: 0: 2672.2, 1: 2776.6. Samples: 121328568. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:25:08,445][86177] Avg episode reward: [(0, '-524.870'), (1, '-555.840')] -[2023-11-28 06:25:09,209][87424] Updated weights for policy 0, policy_version 237097 (0.0012) -[2023-11-28 06:25:09,582][87424] Updated weights for policy 0, policy_version 237107 (0.0012) -[2023-11-28 06:25:09,694][87426] Updated weights for policy 1, policy_version 236810 (0.0011) -[2023-11-28 06:25:09,961][87424] Updated weights for policy 0, policy_version 237117 (0.0011) -[2023-11-28 06:25:10,079][87426] Updated weights for policy 1, policy_version 236820 (0.0010) -[2023-11-28 06:25:10,455][87426] Updated weights for policy 1, policy_version 236830 (0.0010) -[2023-11-28 06:25:12,356][87424] Updated weights for policy 0, policy_version 237127 (0.0011) -[2023-11-28 06:25:12,537][87426] Updated weights for policy 1, policy_version 236840 (0.0011) -[2023-11-28 06:25:12,739][87424] Updated weights for policy 0, policy_version 237137 (0.0010) -[2023-11-28 06:25:12,909][87426] Updated weights for policy 1, policy_version 236850 (0.0011) -[2023-11-28 06:25:13,125][87424] Updated weights for policy 0, policy_version 237147 (0.0011) -[2023-11-28 06:25:13,292][87426] Updated weights for policy 1, policy_version 236860 (0.0010) -[2023-11-28 06:25:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 121348096. Throughput: 0: 2688.6, 1: 2746.1. Samples: 121353876. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:25:13,446][86177] Avg episode reward: [(0, '-516.880'), (1, '-548.680')] -[2023-11-28 06:25:15,032][87424] Updated weights for policy 0, policy_version 237157 (0.0008) -[2023-11-28 06:25:15,330][87426] Updated weights for policy 1, policy_version 236870 (0.0011) -[2023-11-28 06:25:15,408][87424] Updated weights for policy 0, policy_version 237167 (0.0011) -[2023-11-28 06:25:15,718][87426] Updated weights for policy 1, policy_version 236880 (0.0007) -[2023-11-28 06:25:15,783][87424] Updated weights for policy 0, policy_version 237177 (0.0011) -[2023-11-28 06:25:16,092][87426] Updated weights for policy 1, policy_version 236890 (0.0009) -[2023-11-28 06:25:18,167][87424] Updated weights for policy 0, policy_version 237187 (0.0010) -[2023-11-28 06:25:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121364480. Throughput: 0: 2684.3, 1: 2750.2. Samples: 121379164. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:25:18,446][86177] Avg episode reward: [(0, '-505.360'), (1, '-544.050')] -[2023-11-28 06:25:18,483][87426] Updated weights for policy 1, policy_version 236900 (0.0008) -[2023-11-28 06:25:18,557][87424] Updated weights for policy 0, policy_version 237197 (0.0011) -[2023-11-28 06:25:18,863][87426] Updated weights for policy 1, policy_version 236910 (0.0008) -[2023-11-28 06:25:18,941][87424] Updated weights for policy 0, policy_version 237207 (0.0012) -[2023-11-28 06:25:19,242][87426] Updated weights for policy 1, policy_version 236920 (0.0008) -[2023-11-28 06:25:21,175][87424] Updated weights for policy 0, policy_version 237217 (0.0012) -[2023-11-28 06:25:21,305][87426] Updated weights for policy 1, policy_version 236930 (0.0008) -[2023-11-28 06:25:21,559][87424] Updated weights for policy 0, policy_version 237227 (0.0011) -[2023-11-28 06:25:21,680][87426] Updated weights for policy 1, policy_version 236940 (0.0010) -[2023-11-28 06:25:21,944][87424] Updated weights for policy 0, policy_version 237237 (0.0009) -[2023-11-28 06:25:22,065][87426] Updated weights for policy 1, policy_version 236950 (0.0009) -[2023-11-28 06:25:22,324][87424] Updated weights for policy 0, policy_version 237247 (0.0010) -[2023-11-28 06:25:22,428][87426] Updated weights for policy 1, policy_version 236960 (0.0010) -[2023-11-28 06:25:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 121397248. Throughput: 0: 2697.4, 1: 2740.4. Samples: 121412456. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:25:23,445][86177] Avg episode reward: [(0, '-491.340'), (1, '-550.710')] -[2023-11-28 06:25:24,391][87424] Updated weights for policy 0, policy_version 237257 (0.0008) -[2023-11-28 06:25:24,775][87424] Updated weights for policy 0, policy_version 237267 (0.0008) -[2023-11-28 06:25:24,968][87426] Updated weights for policy 1, policy_version 236970 (0.0012) -[2023-11-28 06:25:25,149][87424] Updated weights for policy 0, policy_version 237277 (0.0010) -[2023-11-28 06:25:25,345][87426] Updated weights for policy 1, policy_version 236980 (0.0011) -[2023-11-28 06:25:25,727][87426] Updated weights for policy 1, policy_version 236990 (0.0012) -[2023-11-28 06:25:27,195][87424] Updated weights for policy 0, policy_version 237287 (0.0012) -[2023-11-28 06:25:27,576][87424] Updated weights for policy 0, policy_version 237297 (0.0012) -[2023-11-28 06:25:27,715][87426] Updated weights for policy 1, policy_version 237000 (0.0012) -[2023-11-28 06:25:27,960][87424] Updated weights for policy 0, policy_version 237307 (0.0009) -[2023-11-28 06:25:28,090][87426] Updated weights for policy 1, policy_version 237010 (0.0010) -[2023-11-28 06:25:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121421824. Throughput: 0: 2706.0, 1: 2746.9. Samples: 121436800. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:25:28,445][86177] Avg episode reward: [(0, '-493.000'), (1, '-566.880')] -[2023-11-28 06:25:28,464][87426] Updated weights for policy 1, policy_version 237020 (0.0008) -[2023-11-28 06:25:30,237][87424] Updated weights for policy 0, policy_version 237317 (0.0010) -[2023-11-28 06:25:30,528][87426] Updated weights for policy 1, policy_version 237030 (0.0010) -[2023-11-28 06:25:30,615][87424] Updated weights for policy 0, policy_version 237327 (0.0008) -[2023-11-28 06:25:30,899][87426] Updated weights for policy 1, policy_version 237040 (0.0011) -[2023-11-28 06:25:30,999][87424] Updated weights for policy 0, policy_version 237337 (0.0011) -[2023-11-28 06:25:31,290][87426] Updated weights for policy 1, policy_version 237050 (0.0009) -[2023-11-28 06:25:33,190][87424] Updated weights for policy 0, policy_version 237347 (0.0009) -[2023-11-28 06:25:33,306][87426] Updated weights for policy 1, policy_version 237060 (0.0009) -[2023-11-28 06:25:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121446400. Throughput: 0: 2741.6, 1: 2753.7. Samples: 121461988. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:25:33,445][86177] Avg episode reward: [(0, '-514.680'), (1, '-555.950')] -[2023-11-28 06:25:33,576][87424] Updated weights for policy 0, policy_version 237357 (0.0010) -[2023-11-28 06:25:33,676][87426] Updated weights for policy 1, policy_version 237070 (0.0008) -[2023-11-28 06:25:33,941][87424] Updated weights for policy 0, policy_version 237367 (0.0010) -[2023-11-28 06:25:34,067][87426] Updated weights for policy 1, policy_version 237080 (0.0010) -[2023-11-28 06:25:36,218][87424] Updated weights for policy 0, policy_version 237377 (0.0007) -[2023-11-28 06:25:36,571][87426] Updated weights for policy 1, policy_version 237090 (0.0011) -[2023-11-28 06:25:36,599][87424] Updated weights for policy 0, policy_version 237387 (0.0008) -[2023-11-28 06:25:36,952][87426] Updated weights for policy 1, policy_version 237100 (0.0008) -[2023-11-28 06:25:36,990][87424] Updated weights for policy 0, policy_version 237397 (0.0011) -[2023-11-28 06:25:37,337][87426] Updated weights for policy 1, policy_version 237110 (0.0011) -[2023-11-28 06:25:37,372][87424] Updated weights for policy 0, policy_version 237407 (0.0012) -[2023-11-28 06:25:37,713][87426] Updated weights for policy 1, policy_version 237120 (0.0012) -[2023-11-28 06:25:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 121479168. Throughput: 0: 2738.3, 1: 2734.1. Samples: 121493184. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:25:38,445][86177] Avg episode reward: [(0, '-568.630'), (1, '-565.270')] -[2023-11-28 06:25:39,219][87424] Updated weights for policy 0, policy_version 237417 (0.0012) -[2023-11-28 06:25:39,599][87424] Updated weights for policy 0, policy_version 237427 (0.0012) -[2023-11-28 06:25:39,976][87424] Updated weights for policy 0, policy_version 237437 (0.0010) -[2023-11-28 06:25:40,065][87426] Updated weights for policy 1, policy_version 237130 (0.0011) -[2023-11-28 06:25:40,439][87426] Updated weights for policy 1, policy_version 237140 (0.0010) -[2023-11-28 06:25:40,821][87426] Updated weights for policy 1, policy_version 237150 (0.0009) -[2023-11-28 06:25:42,209][87424] Updated weights for policy 0, policy_version 237447 (0.0010) -[2023-11-28 06:25:42,596][87424] Updated weights for policy 0, policy_version 237457 (0.0010) -[2023-11-28 06:25:42,864][87426] Updated weights for policy 1, policy_version 237160 (0.0009) -[2023-11-28 06:25:42,978][87424] Updated weights for policy 0, policy_version 237467 (0.0011) -[2023-11-28 06:25:43,245][87426] Updated weights for policy 1, policy_version 237170 (0.0011) -[2023-11-28 06:25:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 121503744. Throughput: 0: 2755.8, 1: 2733.2. Samples: 121518812. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 06:25:43,445][86177] Avg episode reward: [(0, '-578.950'), (1, '-582.960')] -[2023-11-28 06:25:43,637][87426] Updated weights for policy 1, policy_version 237180 (0.0010) -[2023-11-28 06:25:45,254][87424] Updated weights for policy 0, policy_version 237477 (0.0012) -[2023-11-28 06:25:45,606][87426] Updated weights for policy 1, policy_version 237190 (0.0010) -[2023-11-28 06:25:45,641][87424] Updated weights for policy 0, policy_version 237487 (0.0011) -[2023-11-28 06:25:45,987][87426] Updated weights for policy 1, policy_version 237200 (0.0011) -[2023-11-28 06:25:46,016][87424] Updated weights for policy 0, policy_version 237497 (0.0011) -[2023-11-28 06:25:46,365][87426] Updated weights for policy 1, policy_version 237210 (0.0008) -[2023-11-28 06:25:47,973][87424] Updated weights for policy 0, policy_version 237507 (0.0012) -[2023-11-28 06:25:48,352][87424] Updated weights for policy 0, policy_version 237517 (0.0012) -[2023-11-28 06:25:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121528320. Throughput: 0: 2748.2, 1: 2727.5. Samples: 121542860. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:25:48,446][86177] Avg episode reward: [(0, '-589.980'), (1, '-593.650')] -[2023-11-28 06:25:48,515][87426] Updated weights for policy 1, policy_version 237220 (0.0009) -[2023-11-28 06:25:48,729][87424] Updated weights for policy 0, policy_version 237527 (0.0011) -[2023-11-28 06:25:48,894][87426] Updated weights for policy 1, policy_version 237230 (0.0011) -[2023-11-28 06:25:49,273][87426] Updated weights for policy 1, policy_version 237240 (0.0011) -[2023-11-28 06:25:50,888][87424] Updated weights for policy 0, policy_version 237537 (0.0010) -[2023-11-28 06:25:51,275][87424] Updated weights for policy 0, policy_version 237547 (0.0012) -[2023-11-28 06:25:51,659][87424] Updated weights for policy 0, policy_version 237557 (0.0012) -[2023-11-28 06:25:51,753][87426] Updated weights for policy 1, policy_version 237250 (0.0011) -[2023-11-28 06:25:52,039][87424] Updated weights for policy 0, policy_version 237567 (0.0016) -[2023-11-28 06:25:52,131][87426] Updated weights for policy 1, policy_version 237260 (0.0010) -[2023-11-28 06:25:52,515][87426] Updated weights for policy 1, policy_version 237270 (0.0011) -[2023-11-28 06:25:52,892][87426] Updated weights for policy 1, policy_version 237280 (0.0012) -[2023-11-28 06:25:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 121561088. Throughput: 0: 2763.3, 1: 2739.1. Samples: 121576176. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:25:53,445][86177] Avg episode reward: [(0, '-588.140'), (1, '-608.950')] -[2023-11-28 06:25:54,124][87424] Updated weights for policy 0, policy_version 237577 (0.0012) -[2023-11-28 06:25:54,514][87424] Updated weights for policy 0, policy_version 237587 (0.0008) -[2023-11-28 06:25:54,889][87426] Updated weights for policy 1, policy_version 237290 (0.0008) -[2023-11-28 06:25:54,891][87424] Updated weights for policy 0, policy_version 237597 (0.0008) -[2023-11-28 06:25:55,268][87426] Updated weights for policy 1, policy_version 237300 (0.0007) -[2023-11-28 06:25:55,646][87426] Updated weights for policy 1, policy_version 237310 (0.0007) -[2023-11-28 06:25:57,034][87424] Updated weights for policy 0, policy_version 237607 (0.0009) -[2023-11-28 06:25:57,412][87424] Updated weights for policy 0, policy_version 237617 (0.0007) -[2023-11-28 06:25:57,806][87424] Updated weights for policy 0, policy_version 237627 (0.0008) -[2023-11-28 06:25:58,153][87426] Updated weights for policy 1, policy_version 237320 (0.0008) -[2023-11-28 06:25:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121585664. Throughput: 0: 2752.7, 1: 2715.0. Samples: 121599924. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:25:58,446][86177] Avg episode reward: [(0, '-535.720'), (1, '-613.790')] -[2023-11-28 06:25:58,533][87426] Updated weights for policy 1, policy_version 237330 (0.0010) -[2023-11-28 06:25:58,899][87426] Updated weights for policy 1, policy_version 237340 (0.0008) -[2023-11-28 06:26:00,245][87424] Updated weights for policy 0, policy_version 237637 (0.0010) -[2023-11-28 06:26:00,623][87424] Updated weights for policy 0, policy_version 237647 (0.0010) -[2023-11-28 06:26:01,007][87424] Updated weights for policy 0, policy_version 237657 (0.0008) -[2023-11-28 06:26:01,532][87426] Updated weights for policy 1, policy_version 237350 (0.0009) -[2023-11-28 06:26:01,910][87426] Updated weights for policy 1, policy_version 237360 (0.0011) -[2023-11-28 06:26:02,289][87426] Updated weights for policy 1, policy_version 237370 (0.0009) -[2023-11-28 06:26:03,369][87424] Updated weights for policy 0, policy_version 237667 (0.0009) -[2023-11-28 06:26:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121610240. Throughput: 0: 2753.4, 1: 2685.3. Samples: 121623904. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:03,445][86177] Avg episode reward: [(0, '-526.500'), (1, '-563.500')] -[2023-11-28 06:26:03,750][87424] Updated weights for policy 0, policy_version 237677 (0.0009) -[2023-11-28 06:26:04,130][87424] Updated weights for policy 0, policy_version 237687 (0.0007) -[2023-11-28 06:26:04,755][87426] Updated weights for policy 1, policy_version 237380 (0.0009) -[2023-11-28 06:26:05,120][87426] Updated weights for policy 1, policy_version 237390 (0.0012) -[2023-11-28 06:26:05,504][87426] Updated weights for policy 1, policy_version 237400 (0.0012) -[2023-11-28 06:26:06,308][87424] Updated weights for policy 0, policy_version 237697 (0.0009) -[2023-11-28 06:26:06,697][87424] Updated weights for policy 0, policy_version 237707 (0.0011) -[2023-11-28 06:26:07,078][87424] Updated weights for policy 0, policy_version 237717 (0.0011) -[2023-11-28 06:26:07,359][87426] Updated weights for policy 1, policy_version 237410 (0.0011) -[2023-11-28 06:26:07,460][87424] Updated weights for policy 0, policy_version 237727 (0.0012) -[2023-11-28 06:26:07,742][87426] Updated weights for policy 1, policy_version 237420 (0.0011) -[2023-11-28 06:26:08,123][87426] Updated weights for policy 1, policy_version 237430 (0.0012) -[2023-11-28 06:26:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 121634816. Throughput: 0: 2744.3, 1: 2667.4. Samples: 121655980. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:08,446][86177] Avg episode reward: [(0, '-539.280'), (1, '-550.600')] -[2023-11-28 06:26:08,497][87426] Updated weights for policy 1, policy_version 237440 (0.0011) -[2023-11-28 06:26:09,172][87424] Updated weights for policy 0, policy_version 237737 (0.0012) -[2023-11-28 06:26:09,560][87424] Updated weights for policy 0, policy_version 237747 (0.0012) -[2023-11-28 06:26:09,936][87424] Updated weights for policy 0, policy_version 237757 (0.0011) -[2023-11-28 06:26:10,623][87426] Updated weights for policy 1, policy_version 237450 (0.0009) -[2023-11-28 06:26:11,002][87426] Updated weights for policy 1, policy_version 237460 (0.0010) -[2023-11-28 06:26:11,377][87426] Updated weights for policy 1, policy_version 237470 (0.0012) -[2023-11-28 06:26:11,977][87424] Updated weights for policy 0, policy_version 237767 (0.0011) -[2023-11-28 06:26:12,365][87424] Updated weights for policy 0, policy_version 237777 (0.0008) -[2023-11-28 06:26:12,753][87424] Updated weights for policy 0, policy_version 237787 (0.0008) -[2023-11-28 06:26:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 121667584. Throughput: 0: 2757.9, 1: 2662.1. Samples: 121680700. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:13,445][86177] Avg episode reward: [(0, '-521.870'), (1, '-517.600')] -[2023-11-28 06:26:13,634][87426] Updated weights for policy 1, policy_version 237480 (0.0009) -[2023-11-28 06:26:14,009][87426] Updated weights for policy 1, policy_version 237490 (0.0007) -[2023-11-28 06:26:14,383][87426] Updated weights for policy 1, policy_version 237500 (0.0009) -[2023-11-28 06:26:14,541][87424] Updated weights for policy 0, policy_version 237797 (0.0010) -[2023-11-28 06:26:14,925][87424] Updated weights for policy 0, policy_version 237807 (0.0008) -[2023-11-28 06:26:15,306][87424] Updated weights for policy 0, policy_version 237817 (0.0012) -[2023-11-28 06:26:16,545][87426] Updated weights for policy 1, policy_version 237510 (0.0007) -[2023-11-28 06:26:16,935][87426] Updated weights for policy 1, policy_version 237520 (0.0008) -[2023-11-28 06:26:17,310][87426] Updated weights for policy 1, policy_version 237530 (0.0007) -[2023-11-28 06:26:17,821][87424] Updated weights for policy 0, policy_version 237827 (0.0008) -[2023-11-28 06:26:18,214][87424] Updated weights for policy 0, policy_version 237837 (0.0008) -[2023-11-28 06:26:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 121692160. Throughput: 0: 2739.4, 1: 2654.8. Samples: 121704728. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:18,445][86177] Avg episode reward: [(0, '-546.410'), (1, '-512.630')] -[2023-11-28 06:26:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000237536_60809216.pth... -[2023-11-28 06:26:18,501][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000235008_60162048.pth -[2023-11-28 06:26:18,592][87424] Updated weights for policy 0, policy_version 237847 (0.0007) -[2023-11-28 06:26:18,952][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000237856_60891136.pth... -[2023-11-28 06:26:18,984][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000235296_60235776.pth -[2023-11-28 06:26:19,654][87426] Updated weights for policy 1, policy_version 237540 (0.0009) -[2023-11-28 06:26:20,030][87426] Updated weights for policy 1, policy_version 237550 (0.0012) -[2023-11-28 06:26:20,406][87426] Updated weights for policy 1, policy_version 237560 (0.0012) -[2023-11-28 06:26:21,108][87424] Updated weights for policy 0, policy_version 237857 (0.0008) -[2023-11-28 06:26:21,495][87424] Updated weights for policy 0, policy_version 237867 (0.0012) -[2023-11-28 06:26:21,877][87424] Updated weights for policy 0, policy_version 237877 (0.0012) -[2023-11-28 06:26:22,269][87424] Updated weights for policy 0, policy_version 237887 (0.0010) -[2023-11-28 06:26:22,791][87426] Updated weights for policy 1, policy_version 237570 (0.0012) -[2023-11-28 06:26:23,176][87426] Updated weights for policy 1, policy_version 237580 (0.0012) -[2023-11-28 06:26:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 121716736. Throughput: 0: 2731.4, 1: 2660.2. Samples: 121735804. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:23,445][86177] Avg episode reward: [(0, '-536.500'), (1, '-509.830')] -[2023-11-28 06:26:23,551][87426] Updated weights for policy 1, policy_version 237590 (0.0012) -[2023-11-28 06:26:23,929][87426] Updated weights for policy 1, policy_version 237600 (0.0012) -[2023-11-28 06:26:24,752][87424] Updated weights for policy 0, policy_version 237897 (0.0012) -[2023-11-28 06:26:25,137][87424] Updated weights for policy 0, policy_version 237907 (0.0012) -[2023-11-28 06:26:25,520][87424] Updated weights for policy 0, policy_version 237917 (0.0012) -[2023-11-28 06:26:25,880][87426] Updated weights for policy 1, policy_version 237610 (0.0012) -[2023-11-28 06:26:26,261][87426] Updated weights for policy 1, policy_version 237620 (0.0012) -[2023-11-28 06:26:26,640][87426] Updated weights for policy 1, policy_version 237630 (0.0012) -[2023-11-28 06:26:27,356][87424] Updated weights for policy 0, policy_version 237927 (0.0008) -[2023-11-28 06:26:27,733][87424] Updated weights for policy 0, policy_version 237937 (0.0008) -[2023-11-28 06:26:28,120][87424] Updated weights for policy 0, policy_version 237947 (0.0011) -[2023-11-28 06:26:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 121749504. Throughput: 0: 2708.2, 1: 2684.5. Samples: 121761484. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:28,445][86177] Avg episode reward: [(0, '-534.780'), (1, '-512.210')] -[2023-11-28 06:26:28,659][87426] Updated weights for policy 1, policy_version 237640 (0.0012) -[2023-11-28 06:26:29,026][87426] Updated weights for policy 1, policy_version 237650 (0.0009) -[2023-11-28 06:26:29,405][87426] Updated weights for policy 1, policy_version 237660 (0.0007) -[2023-11-28 06:26:30,346][87424] Updated weights for policy 0, policy_version 237957 (0.0009) -[2023-11-28 06:26:30,733][87424] Updated weights for policy 0, policy_version 237967 (0.0009) -[2023-11-28 06:26:31,120][87424] Updated weights for policy 0, policy_version 237977 (0.0010) -[2023-11-28 06:26:31,306][87426] Updated weights for policy 1, policy_version 237670 (0.0010) -[2023-11-28 06:26:31,688][87426] Updated weights for policy 1, policy_version 237680 (0.0008) -[2023-11-28 06:26:32,071][87426] Updated weights for policy 1, policy_version 237690 (0.0010) -[2023-11-28 06:26:33,225][87424] Updated weights for policy 0, policy_version 237987 (0.0011) -[2023-11-28 06:26:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121774080. Throughput: 0: 2746.2, 1: 2682.4. Samples: 121787148. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:33,446][86177] Avg episode reward: [(0, '-526.930'), (1, '-512.790')] -[2023-11-28 06:26:33,600][87424] Updated weights for policy 0, policy_version 237997 (0.0012) -[2023-11-28 06:26:33,981][87424] Updated weights for policy 0, policy_version 238007 (0.0012) -[2023-11-28 06:26:34,568][87426] Updated weights for policy 1, policy_version 237700 (0.0011) -[2023-11-28 06:26:34,943][87426] Updated weights for policy 1, policy_version 237710 (0.0012) -[2023-11-28 06:26:35,319][87426] Updated weights for policy 1, policy_version 237720 (0.0012) -[2023-11-28 06:26:36,024][87424] Updated weights for policy 0, policy_version 238017 (0.0012) -[2023-11-28 06:26:36,401][87424] Updated weights for policy 0, policy_version 238027 (0.0012) -[2023-11-28 06:26:36,789][87424] Updated weights for policy 0, policy_version 238037 (0.0012) -[2023-11-28 06:26:37,165][87424] Updated weights for policy 0, policy_version 238047 (0.0012) -[2023-11-28 06:26:37,473][87426] Updated weights for policy 1, policy_version 237730 (0.0012) -[2023-11-28 06:26:37,850][87426] Updated weights for policy 1, policy_version 237740 (0.0011) -[2023-11-28 06:26:38,228][87426] Updated weights for policy 1, policy_version 237750 (0.0011) -[2023-11-28 06:26:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 121798656. Throughput: 0: 2740.5, 1: 2687.3. Samples: 121820424. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:38,445][86177] Avg episode reward: [(0, '-508.140'), (1, '-540.420')] -[2023-11-28 06:26:38,608][87426] Updated weights for policy 1, policy_version 237760 (0.0011) -[2023-11-28 06:26:39,202][87424] Updated weights for policy 0, policy_version 238057 (0.0012) -[2023-11-28 06:26:39,582][87424] Updated weights for policy 0, policy_version 238067 (0.0010) -[2023-11-28 06:26:39,961][87424] Updated weights for policy 0, policy_version 238077 (0.0010) -[2023-11-28 06:26:40,585][87426] Updated weights for policy 1, policy_version 237770 (0.0010) -[2023-11-28 06:26:40,966][87426] Updated weights for policy 1, policy_version 237780 (0.0008) -[2023-11-28 06:26:41,350][87426] Updated weights for policy 1, policy_version 237790 (0.0012) -[2023-11-28 06:26:41,911][87424] Updated weights for policy 0, policy_version 238087 (0.0011) -[2023-11-28 06:26:42,293][87424] Updated weights for policy 0, policy_version 238097 (0.0010) -[2023-11-28 06:26:42,679][87424] Updated weights for policy 0, policy_version 238107 (0.0010) -[2023-11-28 06:26:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 121831424. Throughput: 0: 2755.0, 1: 2714.3. Samples: 121846044. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:43,445][86177] Avg episode reward: [(0, '-492.500'), (1, '-541.930')] -[2023-11-28 06:26:43,501][87426] Updated weights for policy 1, policy_version 237800 (0.0012) -[2023-11-28 06:26:43,876][87426] Updated weights for policy 1, policy_version 237810 (0.0012) -[2023-11-28 06:26:44,263][87426] Updated weights for policy 1, policy_version 237820 (0.0009) -[2023-11-28 06:26:44,779][87424] Updated weights for policy 0, policy_version 238117 (0.0011) -[2023-11-28 06:26:45,164][87424] Updated weights for policy 0, policy_version 238127 (0.0009) -[2023-11-28 06:26:45,544][87424] Updated weights for policy 0, policy_version 238137 (0.0012) -[2023-11-28 06:26:46,152][87426] Updated weights for policy 1, policy_version 237830 (0.0010) -[2023-11-28 06:26:46,524][87426] Updated weights for policy 1, policy_version 237840 (0.0010) -[2023-11-28 06:26:46,915][87426] Updated weights for policy 1, policy_version 237850 (0.0008) -[2023-11-28 06:26:47,498][87424] Updated weights for policy 0, policy_version 238147 (0.0011) -[2023-11-28 06:26:47,889][87424] Updated weights for policy 0, policy_version 238157 (0.0007) -[2023-11-28 06:26:48,279][87424] Updated weights for policy 0, policy_version 238167 (0.0008) -[2023-11-28 06:26:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121856000. Throughput: 0: 2757.1, 1: 2738.1. Samples: 121871188. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:48,445][86177] Avg episode reward: [(0, '-492.930'), (1, '-544.480')] -[2023-11-28 06:26:49,066][87426] Updated weights for policy 1, policy_version 237860 (0.0007) -[2023-11-28 06:26:49,445][87426] Updated weights for policy 1, policy_version 237870 (0.0008) -[2023-11-28 06:26:49,833][87426] Updated weights for policy 1, policy_version 237880 (0.0008) -[2023-11-28 06:26:50,625][87424] Updated weights for policy 0, policy_version 238177 (0.0008) -[2023-11-28 06:26:51,012][87424] Updated weights for policy 0, policy_version 238187 (0.0012) -[2023-11-28 06:26:51,386][87424] Updated weights for policy 0, policy_version 238197 (0.0009) -[2023-11-28 06:26:51,766][87424] Updated weights for policy 0, policy_version 238207 (0.0011) -[2023-11-28 06:26:51,913][87426] Updated weights for policy 1, policy_version 237890 (0.0009) -[2023-11-28 06:26:52,291][87426] Updated weights for policy 1, policy_version 237900 (0.0012) -[2023-11-28 06:26:52,666][87426] Updated weights for policy 1, policy_version 237910 (0.0011) -[2023-11-28 06:26:53,045][87426] Updated weights for policy 1, policy_version 237920 (0.0009) -[2023-11-28 06:26:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121888768. Throughput: 0: 2742.1, 1: 2745.9. Samples: 121902936. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 06:26:53,445][86177] Avg episode reward: [(0, '-532.940'), (1, '-537.270')] -[2023-11-28 06:26:53,780][87424] Updated weights for policy 0, policy_version 238217 (0.0009) -[2023-11-28 06:26:54,167][87424] Updated weights for policy 0, policy_version 238227 (0.0008) -[2023-11-28 06:26:54,548][87424] Updated weights for policy 0, policy_version 238237 (0.0009) -[2023-11-28 06:26:55,507][87426] Updated weights for policy 1, policy_version 237930 (0.0012) -[2023-11-28 06:26:55,879][87426] Updated weights for policy 1, policy_version 237940 (0.0011) -[2023-11-28 06:26:56,262][87426] Updated weights for policy 1, policy_version 237950 (0.0011) -[2023-11-28 06:26:56,789][87424] Updated weights for policy 0, policy_version 238247 (0.0011) -[2023-11-28 06:26:57,172][87424] Updated weights for policy 0, policy_version 238257 (0.0012) -[2023-11-28 06:26:57,559][87424] Updated weights for policy 0, policy_version 238267 (0.0008) -[2023-11-28 06:26:58,101][87426] Updated weights for policy 1, policy_version 237960 (0.0009) -[2023-11-28 06:26:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 121913344. Throughput: 0: 2724.3, 1: 2745.9. Samples: 121926856. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:26:58,445][86177] Avg episode reward: [(0, '-531.510'), (1, '-509.100')] -[2023-11-28 06:26:58,482][87426] Updated weights for policy 1, policy_version 237970 (0.0007) -[2023-11-28 06:26:58,860][87426] Updated weights for policy 1, policy_version 237980 (0.0008) -[2023-11-28 06:26:59,430][87424] Updated weights for policy 0, policy_version 238277 (0.0009) -[2023-11-28 06:26:59,802][87424] Updated weights for policy 0, policy_version 238287 (0.0012) -[2023-11-28 06:27:00,184][87424] Updated weights for policy 0, policy_version 238297 (0.0012) -[2023-11-28 06:27:01,294][87426] Updated weights for policy 1, policy_version 237990 (0.0011) -[2023-11-28 06:27:01,671][87426] Updated weights for policy 1, policy_version 238000 (0.0012) -[2023-11-28 06:27:02,057][87426] Updated weights for policy 1, policy_version 238010 (0.0012) -[2023-11-28 06:27:02,508][87424] Updated weights for policy 0, policy_version 238307 (0.0012) -[2023-11-28 06:27:02,885][87424] Updated weights for policy 0, policy_version 238317 (0.0012) -[2023-11-28 06:27:03,278][87424] Updated weights for policy 0, policy_version 238327 (0.0009) -[2023-11-28 06:27:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121937920. Throughput: 0: 2757.4, 1: 2744.8. Samples: 121952328. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:03,445][86177] Avg episode reward: [(0, '-532.000'), (1, '-510.260')] -[2023-11-28 06:27:04,440][87426] Updated weights for policy 1, policy_version 238020 (0.0011) -[2023-11-28 06:27:04,820][87426] Updated weights for policy 1, policy_version 238030 (0.0011) -[2023-11-28 06:27:05,195][87426] Updated weights for policy 1, policy_version 238040 (0.0010) -[2023-11-28 06:27:05,394][87424] Updated weights for policy 0, policy_version 238337 (0.0009) -[2023-11-28 06:27:05,777][87424] Updated weights for policy 0, policy_version 238347 (0.0010) -[2023-11-28 06:27:06,158][87424] Updated weights for policy 0, policy_version 238357 (0.0007) -[2023-11-28 06:27:06,538][87424] Updated weights for policy 0, policy_version 238367 (0.0007) -[2023-11-28 06:27:07,662][87426] Updated weights for policy 1, policy_version 238050 (0.0010) -[2023-11-28 06:27:08,035][87426] Updated weights for policy 1, policy_version 238060 (0.0012) -[2023-11-28 06:27:08,414][87426] Updated weights for policy 1, policy_version 238070 (0.0012) -[2023-11-28 06:27:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 121962496. Throughput: 0: 2779.0, 1: 2749.3. Samples: 121984580. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:08,445][86177] Avg episode reward: [(0, '-538.940'), (1, '-512.150')] -[2023-11-28 06:27:08,778][87426] Updated weights for policy 1, policy_version 238080 (0.0011) -[2023-11-28 06:27:09,096][87424] Updated weights for policy 0, policy_version 238377 (0.0011) -[2023-11-28 06:27:09,476][87424] Updated weights for policy 0, policy_version 238387 (0.0012) -[2023-11-28 06:27:09,851][87424] Updated weights for policy 0, policy_version 238397 (0.0012) -[2023-11-28 06:27:10,980][87426] Updated weights for policy 1, policy_version 238090 (0.0011) -[2023-11-28 06:27:11,360][87426] Updated weights for policy 1, policy_version 238100 (0.0011) -[2023-11-28 06:27:11,750][87426] Updated weights for policy 1, policy_version 238110 (0.0009) -[2023-11-28 06:27:12,071][87424] Updated weights for policy 0, policy_version 238407 (0.0012) -[2023-11-28 06:27:12,451][87424] Updated weights for policy 0, policy_version 238417 (0.0013) -[2023-11-28 06:27:12,834][87424] Updated weights for policy 0, policy_version 238427 (0.0012) -[2023-11-28 06:27:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 121995264. Throughput: 0: 2776.9, 1: 2696.6. Samples: 122007792. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:13,445][86177] Avg episode reward: [(0, '-499.520'), (1, '-508.140')] -[2023-11-28 06:27:13,937][87426] Updated weights for policy 1, policy_version 238120 (0.0011) -[2023-11-28 06:27:14,317][87426] Updated weights for policy 1, policy_version 238130 (0.0012) -[2023-11-28 06:27:14,690][87426] Updated weights for policy 1, policy_version 238140 (0.0012) -[2023-11-28 06:27:15,171][87424] Updated weights for policy 0, policy_version 238437 (0.0012) -[2023-11-28 06:27:15,552][87424] Updated weights for policy 0, policy_version 238447 (0.0011) -[2023-11-28 06:27:15,935][87424] Updated weights for policy 0, policy_version 238457 (0.0010) -[2023-11-28 06:27:16,913][87426] Updated weights for policy 1, policy_version 238150 (0.0009) -[2023-11-28 06:27:17,293][87426] Updated weights for policy 1, policy_version 238160 (0.0012) -[2023-11-28 06:27:17,668][87426] Updated weights for policy 1, policy_version 238170 (0.0009) -[2023-11-28 06:27:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 122019840. Throughput: 0: 2735.2, 1: 2694.3. Samples: 122031476. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:18,445][86177] Avg episode reward: [(0, '-502.950'), (1, '-510.240')] -[2023-11-28 06:27:18,453][87424] Updated weights for policy 0, policy_version 238467 (0.0008) -[2023-11-28 06:27:18,845][87424] Updated weights for policy 0, policy_version 238477 (0.0010) -[2023-11-28 06:27:19,231][87424] Updated weights for policy 0, policy_version 238487 (0.0008) -[2023-11-28 06:27:19,708][87426] Updated weights for policy 1, policy_version 238180 (0.0009) -[2023-11-28 06:27:20,089][87426] Updated weights for policy 1, policy_version 238190 (0.0011) -[2023-11-28 06:27:20,464][87426] Updated weights for policy 1, policy_version 238200 (0.0008) -[2023-11-28 06:27:21,459][87424] Updated weights for policy 0, policy_version 238497 (0.0008) -[2023-11-28 06:27:21,854][87424] Updated weights for policy 0, policy_version 238507 (0.0010) -[2023-11-28 06:27:22,233][87424] Updated weights for policy 0, policy_version 238517 (0.0010) -[2023-11-28 06:27:22,606][87424] Updated weights for policy 0, policy_version 238527 (0.0011) -[2023-11-28 06:27:22,960][87426] Updated weights for policy 1, policy_version 238210 (0.0011) -[2023-11-28 06:27:23,341][87426] Updated weights for policy 1, policy_version 238220 (0.0012) -[2023-11-28 06:27:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 122044416. Throughput: 0: 2697.5, 1: 2685.0. Samples: 122062636. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:23,445][86177] Avg episode reward: [(0, '-495.150'), (1, '-507.210')] -[2023-11-28 06:27:23,713][87426] Updated weights for policy 1, policy_version 238230 (0.0012) -[2023-11-28 06:27:24,104][87426] Updated weights for policy 1, policy_version 238240 (0.0012) -[2023-11-28 06:27:25,057][87424] Updated weights for policy 0, policy_version 238537 (0.0008) -[2023-11-28 06:27:25,447][87424] Updated weights for policy 0, policy_version 238547 (0.0010) -[2023-11-28 06:27:25,831][87424] Updated weights for policy 0, policy_version 238557 (0.0007) -[2023-11-28 06:27:26,461][87426] Updated weights for policy 1, policy_version 238250 (0.0011) -[2023-11-28 06:27:26,845][87426] Updated weights for policy 1, policy_version 238260 (0.0011) -[2023-11-28 06:27:27,216][87426] Updated weights for policy 1, policy_version 238270 (0.0012) -[2023-11-28 06:27:27,529][87424] Updated weights for policy 0, policy_version 238567 (0.0010) -[2023-11-28 06:27:27,910][87424] Updated weights for policy 0, policy_version 238577 (0.0012) -[2023-11-28 06:27:28,306][87424] Updated weights for policy 0, policy_version 238587 (0.0012) -[2023-11-28 06:27:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 122068992. Throughput: 0: 2682.5, 1: 2697.2. Samples: 122088132. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:28,445][86177] Avg episode reward: [(0, '-493.540'), (1, '-502.890')] -[2023-11-28 06:27:29,034][87426] Updated weights for policy 1, policy_version 238280 (0.0012) -[2023-11-28 06:27:29,414][87426] Updated weights for policy 1, policy_version 238290 (0.0012) -[2023-11-28 06:27:29,798][87426] Updated weights for policy 1, policy_version 238300 (0.0011) -[2023-11-28 06:27:30,078][87424] Updated weights for policy 0, policy_version 238597 (0.0012) -[2023-11-28 06:27:30,468][87424] Updated weights for policy 0, policy_version 238607 (0.0012) -[2023-11-28 06:27:30,853][87424] Updated weights for policy 0, policy_version 238617 (0.0012) -[2023-11-28 06:27:31,627][87426] Updated weights for policy 1, policy_version 238310 (0.0010) -[2023-11-28 06:27:31,999][87426] Updated weights for policy 1, policy_version 238320 (0.0012) -[2023-11-28 06:27:32,382][87426] Updated weights for policy 1, policy_version 238330 (0.0012) -[2023-11-28 06:27:33,134][87424] Updated weights for policy 0, policy_version 238627 (0.0012) -[2023-11-28 06:27:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 122101760. Throughput: 0: 2675.4, 1: 2704.2. Samples: 122113268. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:33,445][86177] Avg episode reward: [(0, '-491.890'), (1, '-503.680')] -[2023-11-28 06:27:33,512][87424] Updated weights for policy 0, policy_version 238637 (0.0012) -[2023-11-28 06:27:33,892][87424] Updated weights for policy 0, policy_version 238647 (0.0008) -[2023-11-28 06:27:34,134][87426] Updated weights for policy 1, policy_version 238340 (0.0012) -[2023-11-28 06:27:34,515][87426] Updated weights for policy 1, policy_version 238350 (0.0012) -[2023-11-28 06:27:34,900][87426] Updated weights for policy 1, policy_version 238360 (0.0012) -[2023-11-28 06:27:36,321][87424] Updated weights for policy 0, policy_version 238657 (0.0008) -[2023-11-28 06:27:36,701][87424] Updated weights for policy 0, policy_version 238667 (0.0011) -[2023-11-28 06:27:37,079][87424] Updated weights for policy 0, policy_version 238677 (0.0011) -[2023-11-28 06:27:37,283][87426] Updated weights for policy 1, policy_version 238370 (0.0012) -[2023-11-28 06:27:37,464][87424] Updated weights for policy 0, policy_version 238687 (0.0011) -[2023-11-28 06:27:37,658][87426] Updated weights for policy 1, policy_version 238380 (0.0012) -[2023-11-28 06:27:38,039][87426] Updated weights for policy 1, policy_version 238390 (0.0012) -[2023-11-28 06:27:38,417][87426] Updated weights for policy 1, policy_version 238400 (0.0009) -[2023-11-28 06:27:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 122134528. Throughput: 0: 2698.1, 1: 2734.2. Samples: 122147392. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:38,445][86177] Avg episode reward: [(0, '-487.520'), (1, '-497.390')] -[2023-11-28 06:27:38,445][87281] Saving new best policy, reward=-487.520! -[2023-11-28 06:27:39,439][87424] Updated weights for policy 0, policy_version 238697 (0.0009) -[2023-11-28 06:27:39,828][87424] Updated weights for policy 0, policy_version 238707 (0.0012) -[2023-11-28 06:27:40,202][87424] Updated weights for policy 0, policy_version 238717 (0.0012) -[2023-11-28 06:27:40,965][87426] Updated weights for policy 1, policy_version 238410 (0.0012) -[2023-11-28 06:27:41,337][87426] Updated weights for policy 1, policy_version 238420 (0.0012) -[2023-11-28 06:27:41,720][87426] Updated weights for policy 1, policy_version 238430 (0.0012) -[2023-11-28 06:27:42,240][87424] Updated weights for policy 0, policy_version 238727 (0.0011) -[2023-11-28 06:27:42,629][87424] Updated weights for policy 0, policy_version 238737 (0.0008) -[2023-11-28 06:27:43,004][87424] Updated weights for policy 0, policy_version 238747 (0.0009) -[2023-11-28 06:27:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 122159104. Throughput: 0: 2704.5, 1: 2719.4. Samples: 122170932. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:43,445][86177] Avg episode reward: [(0, '-496.560'), (1, '-501.160')] -[2023-11-28 06:27:43,926][87426] Updated weights for policy 1, policy_version 238440 (0.0008) -[2023-11-28 06:27:44,314][87426] Updated weights for policy 1, policy_version 238450 (0.0008) -[2023-11-28 06:27:44,691][87426] Updated weights for policy 1, policy_version 238460 (0.0012) -[2023-11-28 06:27:45,361][87424] Updated weights for policy 0, policy_version 238757 (0.0007) -[2023-11-28 06:27:45,747][87424] Updated weights for policy 0, policy_version 238767 (0.0011) -[2023-11-28 06:27:46,131][87424] Updated weights for policy 0, policy_version 238777 (0.0012) -[2023-11-28 06:27:47,180][87426] Updated weights for policy 1, policy_version 238470 (0.0011) -[2023-11-28 06:27:47,552][87426] Updated weights for policy 1, policy_version 238480 (0.0008) -[2023-11-28 06:27:47,939][87426] Updated weights for policy 1, policy_version 238490 (0.0007) -[2023-11-28 06:27:48,437][87424] Updated weights for policy 0, policy_version 238787 (0.0011) -[2023-11-28 06:27:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 122183680. Throughput: 0: 2671.6, 1: 2718.5. Samples: 122194880. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:48,445][86177] Avg episode reward: [(0, '-501.370'), (1, '-503.050')] -[2023-11-28 06:27:48,811][87424] Updated weights for policy 0, policy_version 238797 (0.0012) -[2023-11-28 06:27:49,193][87424] Updated weights for policy 0, policy_version 238807 (0.0011) -[2023-11-28 06:27:50,450][87426] Updated weights for policy 1, policy_version 238500 (0.0009) -[2023-11-28 06:27:50,828][87426] Updated weights for policy 1, policy_version 238510 (0.0012) -[2023-11-28 06:27:51,213][87426] Updated weights for policy 1, policy_version 238520 (0.0012) -[2023-11-28 06:27:51,288][87424] Updated weights for policy 0, policy_version 238817 (0.0011) -[2023-11-28 06:27:51,669][87424] Updated weights for policy 0, policy_version 238827 (0.0009) -[2023-11-28 06:27:52,048][87424] Updated weights for policy 0, policy_version 238837 (0.0012) -[2023-11-28 06:27:52,418][87424] Updated weights for policy 0, policy_version 238847 (0.0011) -[2023-11-28 06:27:53,063][87426] Updated weights for policy 1, policy_version 238530 (0.0011) -[2023-11-28 06:27:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 122208256. Throughput: 0: 2656.7, 1: 2717.2. Samples: 122226408. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:53,445][87426] Updated weights for policy 1, policy_version 238540 (0.0010) -[2023-11-28 06:27:53,445][86177] Avg episode reward: [(0, '-506.320'), (1, '-504.530')] -[2023-11-28 06:27:53,825][87426] Updated weights for policy 1, policy_version 238550 (0.0010) -[2023-11-28 06:27:54,209][87426] Updated weights for policy 1, policy_version 238560 (0.0007) -[2023-11-28 06:27:54,897][87424] Updated weights for policy 0, policy_version 238857 (0.0011) -[2023-11-28 06:27:55,282][87424] Updated weights for policy 0, policy_version 238867 (0.0009) -[2023-11-28 06:27:55,668][87424] Updated weights for policy 0, policy_version 238877 (0.0007) -[2023-11-28 06:27:56,600][87426] Updated weights for policy 1, policy_version 238570 (0.0012) -[2023-11-28 06:27:56,988][87426] Updated weights for policy 1, policy_version 238580 (0.0012) -[2023-11-28 06:27:57,359][87426] Updated weights for policy 1, policy_version 238590 (0.0012) -[2023-11-28 06:27:57,919][87424] Updated weights for policy 0, policy_version 238887 (0.0008) -[2023-11-28 06:27:58,304][87424] Updated weights for policy 0, policy_version 238897 (0.0007) -[2023-11-28 06:27:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 122232832. Throughput: 0: 2651.6, 1: 2709.5. Samples: 122249044. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:27:58,445][86177] Avg episode reward: [(0, '-528.960'), (1, '-504.360')] -[2023-11-28 06:27:58,695][87424] Updated weights for policy 0, policy_version 238907 (0.0008) -[2023-11-28 06:27:59,997][87426] Updated weights for policy 1, policy_version 238600 (0.0012) -[2023-11-28 06:28:00,375][87426] Updated weights for policy 1, policy_version 238610 (0.0012) -[2023-11-28 06:28:00,753][87426] Updated weights for policy 1, policy_version 238620 (0.0012) -[2023-11-28 06:28:00,954][87424] Updated weights for policy 0, policy_version 238917 (0.0009) -[2023-11-28 06:28:01,329][87424] Updated weights for policy 0, policy_version 238927 (0.0011) -[2023-11-28 06:28:01,716][87424] Updated weights for policy 0, policy_version 238937 (0.0009) -[2023-11-28 06:28:02,756][87426] Updated weights for policy 1, policy_version 238630 (0.0009) -[2023-11-28 06:28:03,142][87426] Updated weights for policy 1, policy_version 238640 (0.0008) -[2023-11-28 06:28:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 122257408. Throughput: 0: 2689.2, 1: 2698.2. Samples: 122273912. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:28:03,445][86177] Avg episode reward: [(0, '-559.680'), (1, '-544.050')] -[2023-11-28 06:28:03,523][87426] Updated weights for policy 1, policy_version 238650 (0.0007) -[2023-11-28 06:28:03,827][87424] Updated weights for policy 0, policy_version 238947 (0.0010) -[2023-11-28 06:28:04,205][87424] Updated weights for policy 0, policy_version 238957 (0.0010) -[2023-11-28 06:28:04,596][87424] Updated weights for policy 0, policy_version 238967 (0.0009) -[2023-11-28 06:28:05,562][87426] Updated weights for policy 1, policy_version 238660 (0.0010) -[2023-11-28 06:28:05,942][87426] Updated weights for policy 1, policy_version 238670 (0.0012) -[2023-11-28 06:28:06,323][87426] Updated weights for policy 1, policy_version 238680 (0.0012) -[2023-11-28 06:28:06,730][87424] Updated weights for policy 0, policy_version 238977 (0.0009) -[2023-11-28 06:28:07,106][87424] Updated weights for policy 0, policy_version 238987 (0.0012) -[2023-11-28 06:28:07,489][87424] Updated weights for policy 0, policy_version 238997 (0.0012) -[2023-11-28 06:28:07,865][87424] Updated weights for policy 0, policy_version 239007 (0.0012) -[2023-11-28 06:28:08,256][87426] Updated weights for policy 1, policy_version 238690 (0.0012) -[2023-11-28 06:28:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 122290176. Throughput: 0: 2711.6, 1: 2709.9. Samples: 122306608. Policy #0 lag: (min: 31.0, avg: 42.8, max: 63.0) -[2023-11-28 06:28:08,446][86177] Avg episode reward: [(0, '-559.370'), (1, '-562.610')] -[2023-11-28 06:28:08,644][87426] Updated weights for policy 1, policy_version 238700 (0.0012) -[2023-11-28 06:28:09,020][87426] Updated weights for policy 1, policy_version 238710 (0.0012) -[2023-11-28 06:28:09,399][87426] Updated weights for policy 1, policy_version 238720 (0.0012) -[2023-11-28 06:28:09,959][87424] Updated weights for policy 0, policy_version 239017 (0.0011) -[2023-11-28 06:28:10,339][87424] Updated weights for policy 0, policy_version 239027 (0.0012) -[2023-11-28 06:28:10,724][87424] Updated weights for policy 0, policy_version 239037 (0.0012) -[2023-11-28 06:28:11,792][87426] Updated weights for policy 1, policy_version 238730 (0.0011) -[2023-11-28 06:28:12,170][87426] Updated weights for policy 1, policy_version 238740 (0.0012) -[2023-11-28 06:28:12,547][87426] Updated weights for policy 1, policy_version 238750 (0.0012) -[2023-11-28 06:28:12,971][87424] Updated weights for policy 0, policy_version 239047 (0.0012) -[2023-11-28 06:28:13,358][87424] Updated weights for policy 0, policy_version 239057 (0.0009) -[2023-11-28 06:28:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 122314752. Throughput: 0: 2705.1, 1: 2686.4. Samples: 122330748. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:13,445][86177] Avg episode reward: [(0, '-588.560'), (1, '-564.400')] -[2023-11-28 06:28:13,734][87424] Updated weights for policy 0, policy_version 239067 (0.0008) -[2023-11-28 06:28:14,328][87426] Updated weights for policy 1, policy_version 238760 (0.0012) -[2023-11-28 06:28:14,701][87426] Updated weights for policy 1, policy_version 238770 (0.0012) -[2023-11-28 06:28:15,090][87426] Updated weights for policy 1, policy_version 238780 (0.0012) -[2023-11-28 06:28:16,161][87424] Updated weights for policy 0, policy_version 239077 (0.0007) -[2023-11-28 06:28:16,546][87424] Updated weights for policy 0, policy_version 239087 (0.0007) -[2023-11-28 06:28:16,934][87424] Updated weights for policy 0, policy_version 239097 (0.0007) -[2023-11-28 06:28:17,383][87426] Updated weights for policy 1, policy_version 238790 (0.0011) -[2023-11-28 06:28:17,759][87426] Updated weights for policy 1, policy_version 238800 (0.0012) -[2023-11-28 06:28:18,136][87426] Updated weights for policy 1, policy_version 238810 (0.0012) -[2023-11-28 06:28:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 122347520. Throughput: 0: 2692.0, 1: 2676.1. Samples: 122354832. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:18,445][86177] Avg episode reward: [(0, '-563.690'), (1, '-578.560')] -[2023-11-28 06:28:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000239104_61210624.pth... -[2023-11-28 06:28:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000238816_61136896.pth... -[2023-11-28 06:28:18,497][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000236256_60481536.pth -[2023-11-28 06:28:18,502][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000236576_60563456.pth -[2023-11-28 06:28:18,832][87424] Updated weights for policy 0, policy_version 239107 (0.0009) -[2023-11-28 06:28:19,213][87424] Updated weights for policy 0, policy_version 239117 (0.0012) -[2023-11-28 06:28:19,590][87424] Updated weights for policy 0, policy_version 239127 (0.0012) -[2023-11-28 06:28:20,179][87426] Updated weights for policy 1, policy_version 238820 (0.0011) -[2023-11-28 06:28:20,562][87426] Updated weights for policy 1, policy_version 238830 (0.0008) -[2023-11-28 06:28:20,953][87426] Updated weights for policy 1, policy_version 238840 (0.0008) -[2023-11-28 06:28:22,125][87424] Updated weights for policy 0, policy_version 239137 (0.0011) -[2023-11-28 06:28:22,508][87424] Updated weights for policy 0, policy_version 239147 (0.0012) -[2023-11-28 06:28:22,886][87424] Updated weights for policy 0, policy_version 239157 (0.0011) -[2023-11-28 06:28:23,146][87426] Updated weights for policy 1, policy_version 238850 (0.0009) -[2023-11-28 06:28:23,270][87424] Updated weights for policy 0, policy_version 239167 (0.0008) -[2023-11-28 06:28:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 122372096. Throughput: 0: 2680.4, 1: 2653.5. Samples: 122387420. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:23,445][86177] Avg episode reward: [(0, '-572.710'), (1, '-550.370')] -[2023-11-28 06:28:23,523][87426] Updated weights for policy 1, policy_version 238860 (0.0011) -[2023-11-28 06:28:23,888][87426] Updated weights for policy 1, policy_version 238870 (0.0012) -[2023-11-28 06:28:24,269][87426] Updated weights for policy 1, policy_version 238880 (0.0008) -[2023-11-28 06:28:25,313][87424] Updated weights for policy 0, policy_version 239177 (0.0012) -[2023-11-28 06:28:25,697][87424] Updated weights for policy 0, policy_version 239187 (0.0011) -[2023-11-28 06:28:26,077][87424] Updated weights for policy 0, policy_version 239197 (0.0012) -[2023-11-28 06:28:26,835][87426] Updated weights for policy 1, policy_version 238890 (0.0011) -[2023-11-28 06:28:27,200][87426] Updated weights for policy 1, policy_version 238900 (0.0010) -[2023-11-28 06:28:27,581][87426] Updated weights for policy 1, policy_version 238910 (0.0007) -[2023-11-28 06:28:28,032][87424] Updated weights for policy 0, policy_version 239207 (0.0009) -[2023-11-28 06:28:28,406][87424] Updated weights for policy 0, policy_version 239217 (0.0007) -[2023-11-28 06:28:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 122396672. Throughput: 0: 2696.7, 1: 2651.1. Samples: 122411584. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:28,445][86177] Avg episode reward: [(0, '-552.910'), (1, '-567.700')] -[2023-11-28 06:28:28,792][87424] Updated weights for policy 0, policy_version 239227 (0.0008) -[2023-11-28 06:28:29,663][87426] Updated weights for policy 1, policy_version 238920 (0.0011) -[2023-11-28 06:28:30,037][87426] Updated weights for policy 1, policy_version 238930 (0.0012) -[2023-11-28 06:28:30,417][87426] Updated weights for policy 1, policy_version 238940 (0.0012) -[2023-11-28 06:28:30,968][87424] Updated weights for policy 0, policy_version 239237 (0.0011) -[2023-11-28 06:28:31,342][87424] Updated weights for policy 0, policy_version 239247 (0.0010) -[2023-11-28 06:28:31,718][87424] Updated weights for policy 0, policy_version 239257 (0.0008) -[2023-11-28 06:28:32,459][87426] Updated weights for policy 1, policy_version 238950 (0.0012) -[2023-11-28 06:28:32,846][87426] Updated weights for policy 1, policy_version 238960 (0.0012) -[2023-11-28 06:28:33,227][87426] Updated weights for policy 1, policy_version 238970 (0.0012) -[2023-11-28 06:28:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 122421248. Throughput: 0: 2710.8, 1: 2660.5. Samples: 122436588. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:33,445][86177] Avg episode reward: [(0, '-531.040'), (1, '-552.380')] -[2023-11-28 06:28:33,625][87424] Updated weights for policy 0, policy_version 239267 (0.0012) -[2023-11-28 06:28:34,005][87424] Updated weights for policy 0, policy_version 239277 (0.0012) -[2023-11-28 06:28:34,381][87424] Updated weights for policy 0, policy_version 239287 (0.0012) -[2023-11-28 06:28:35,330][87426] Updated weights for policy 1, policy_version 238980 (0.0012) -[2023-11-28 06:28:35,698][87426] Updated weights for policy 1, policy_version 238990 (0.0009) -[2023-11-28 06:28:36,074][87426] Updated weights for policy 1, policy_version 239000 (0.0007) -[2023-11-28 06:28:36,454][87424] Updated weights for policy 0, policy_version 239297 (0.0012) -[2023-11-28 06:28:36,822][87424] Updated weights for policy 0, policy_version 239307 (0.0012) -[2023-11-28 06:28:37,205][87424] Updated weights for policy 0, policy_version 239317 (0.0012) -[2023-11-28 06:28:37,580][87424] Updated weights for policy 0, policy_version 239327 (0.0012) -[2023-11-28 06:28:38,294][87426] Updated weights for policy 1, policy_version 239010 (0.0008) -[2023-11-28 06:28:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 122454016. Throughput: 0: 2738.1, 1: 2683.1. Samples: 122470360. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:38,445][86177] Avg episode reward: [(0, '-577.440'), (1, '-539.280')] -[2023-11-28 06:28:38,670][87426] Updated weights for policy 1, policy_version 239020 (0.0012) -[2023-11-28 06:28:39,045][87426] Updated weights for policy 1, policy_version 239030 (0.0012) -[2023-11-28 06:28:39,418][87426] Updated weights for policy 1, policy_version 239040 (0.0011) -[2023-11-28 06:28:39,691][87424] Updated weights for policy 0, policy_version 239337 (0.0011) -[2023-11-28 06:28:40,072][87424] Updated weights for policy 0, policy_version 239347 (0.0012) -[2023-11-28 06:28:40,453][87424] Updated weights for policy 0, policy_version 239357 (0.0011) -[2023-11-28 06:28:41,803][87426] Updated weights for policy 1, policy_version 239050 (0.0009) -[2023-11-28 06:28:42,182][87426] Updated weights for policy 1, policy_version 239060 (0.0009) -[2023-11-28 06:28:42,564][87426] Updated weights for policy 1, policy_version 239070 (0.0011) -[2023-11-28 06:28:42,889][87424] Updated weights for policy 0, policy_version 239367 (0.0010) -[2023-11-28 06:28:43,262][87424] Updated weights for policy 0, policy_version 239377 (0.0012) -[2023-11-28 06:28:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 122478592. Throughput: 0: 2754.6, 1: 2695.1. Samples: 122494280. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:43,446][86177] Avg episode reward: [(0, '-576.880'), (1, '-529.110')] -[2023-11-28 06:28:43,656][87424] Updated weights for policy 0, policy_version 239387 (0.0012) -[2023-11-28 06:28:44,770][87426] Updated weights for policy 1, policy_version 239080 (0.0010) -[2023-11-28 06:28:45,143][87426] Updated weights for policy 1, policy_version 239090 (0.0007) -[2023-11-28 06:28:45,522][87426] Updated weights for policy 1, policy_version 239100 (0.0009) -[2023-11-28 06:28:45,855][87424] Updated weights for policy 0, policy_version 239397 (0.0012) -[2023-11-28 06:28:46,241][87424] Updated weights for policy 0, policy_version 239407 (0.0012) -[2023-11-28 06:28:46,626][87424] Updated weights for policy 0, policy_version 239417 (0.0012) -[2023-11-28 06:28:47,562][87426] Updated weights for policy 1, policy_version 239110 (0.0010) -[2023-11-28 06:28:47,943][87426] Updated weights for policy 1, policy_version 239120 (0.0011) -[2023-11-28 06:28:48,329][87426] Updated weights for policy 1, policy_version 239130 (0.0011) -[2023-11-28 06:28:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 122503168. Throughput: 0: 2737.3, 1: 2717.7. Samples: 122519388. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:48,445][86177] Avg episode reward: [(0, '-594.590'), (1, '-497.040')] -[2023-11-28 06:28:48,501][87424] Updated weights for policy 0, policy_version 239427 (0.0012) -[2023-11-28 06:28:48,876][87424] Updated weights for policy 0, policy_version 239437 (0.0011) -[2023-11-28 06:28:49,258][87424] Updated weights for policy 0, policy_version 239447 (0.0012) -[2023-11-28 06:28:50,278][87426] Updated weights for policy 1, policy_version 239140 (0.0012) -[2023-11-28 06:28:50,655][87426] Updated weights for policy 1, policy_version 239150 (0.0011) -[2023-11-28 06:28:51,003][87424] Updated weights for policy 0, policy_version 239457 (0.0012) -[2023-11-28 06:28:51,035][87426] Updated weights for policy 1, policy_version 239160 (0.0011) -[2023-11-28 06:28:51,375][87424] Updated weights for policy 0, policy_version 239467 (0.0011) -[2023-11-28 06:28:51,765][87424] Updated weights for policy 0, policy_version 239477 (0.0012) -[2023-11-28 06:28:52,145][87424] Updated weights for policy 0, policy_version 239487 (0.0012) -[2023-11-28 06:28:53,303][87426] Updated weights for policy 1, policy_version 239170 (0.0010) -[2023-11-28 06:28:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 122535936. Throughput: 0: 2756.1, 1: 2720.9. Samples: 122553072. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:53,445][86177] Avg episode reward: [(0, '-588.550'), (1, '-497.840')] -[2023-11-28 06:28:53,681][87426] Updated weights for policy 1, policy_version 239180 (0.0012) -[2023-11-28 06:28:54,066][87426] Updated weights for policy 1, policy_version 239190 (0.0012) -[2023-11-28 06:28:54,292][87424] Updated weights for policy 0, policy_version 239497 (0.0012) -[2023-11-28 06:28:54,448][87426] Updated weights for policy 1, policy_version 239200 (0.0012) -[2023-11-28 06:28:54,671][87424] Updated weights for policy 0, policy_version 239507 (0.0009) -[2023-11-28 06:28:55,066][87424] Updated weights for policy 0, policy_version 239517 (0.0012) -[2023-11-28 06:28:56,743][87426] Updated weights for policy 1, policy_version 239210 (0.0011) -[2023-11-28 06:28:57,116][87426] Updated weights for policy 1, policy_version 239220 (0.0011) -[2023-11-28 06:28:57,273][87424] Updated weights for policy 0, policy_version 239527 (0.0009) -[2023-11-28 06:28:57,485][87426] Updated weights for policy 1, policy_version 239230 (0.0011) -[2023-11-28 06:28:57,659][87424] Updated weights for policy 0, policy_version 239537 (0.0007) -[2023-11-28 06:28:58,035][87424] Updated weights for policy 0, policy_version 239547 (0.0007) -[2023-11-28 06:28:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 122568704. Throughput: 0: 2750.2, 1: 2719.3. Samples: 122576876. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:28:58,445][86177] Avg episode reward: [(0, '-582.920'), (1, '-496.370')] -[2023-11-28 06:29:00,053][87426] Updated weights for policy 1, policy_version 239240 (0.0011) -[2023-11-28 06:29:00,203][87424] Updated weights for policy 0, policy_version 239557 (0.0009) -[2023-11-28 06:29:00,422][87426] Updated weights for policy 1, policy_version 239250 (0.0011) -[2023-11-28 06:29:00,594][87424] Updated weights for policy 0, policy_version 239567 (0.0010) -[2023-11-28 06:29:00,798][87426] Updated weights for policy 1, policy_version 239260 (0.0011) -[2023-11-28 06:29:00,962][87424] Updated weights for policy 0, policy_version 239577 (0.0011) -[2023-11-28 06:29:02,994][87426] Updated weights for policy 1, policy_version 239270 (0.0009) -[2023-11-28 06:29:03,379][87426] Updated weights for policy 1, policy_version 239280 (0.0007) -[2023-11-28 06:29:03,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 122585088. Throughput: 0: 2764.4, 1: 2721.8. Samples: 122601712. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:29:03,446][86177] Avg episode reward: [(0, '-564.150'), (1, '-529.970')] -[2023-11-28 06:29:03,545][87424] Updated weights for policy 0, policy_version 239587 (0.0007) -[2023-11-28 06:29:03,751][87426] Updated weights for policy 1, policy_version 239290 (0.0008) -[2023-11-28 06:29:03,933][87424] Updated weights for policy 0, policy_version 239597 (0.0007) -[2023-11-28 06:29:04,306][87424] Updated weights for policy 0, policy_version 239607 (0.0010) -[2023-11-28 06:29:06,045][87426] Updated weights for policy 1, policy_version 239300 (0.0008) -[2023-11-28 06:29:06,329][87424] Updated weights for policy 0, policy_version 239617 (0.0009) -[2023-11-28 06:29:06,418][87426] Updated weights for policy 1, policy_version 239310 (0.0009) -[2023-11-28 06:29:06,717][87424] Updated weights for policy 0, policy_version 239627 (0.0008) -[2023-11-28 06:29:06,793][87426] Updated weights for policy 1, policy_version 239320 (0.0009) -[2023-11-28 06:29:07,093][87424] Updated weights for policy 0, policy_version 239637 (0.0008) -[2023-11-28 06:29:07,475][87424] Updated weights for policy 0, policy_version 239647 (0.0008) -[2023-11-28 06:29:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 122617856. Throughput: 0: 2754.9, 1: 2700.4. Samples: 122632912. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:29:08,445][86177] Avg episode reward: [(0, '-547.890'), (1, '-529.430')] -[2023-11-28 06:29:09,332][87426] Updated weights for policy 1, policy_version 239330 (0.0008) -[2023-11-28 06:29:09,453][87424] Updated weights for policy 0, policy_version 239657 (0.0010) -[2023-11-28 06:29:09,707][87426] Updated weights for policy 1, policy_version 239340 (0.0009) -[2023-11-28 06:29:09,829][87424] Updated weights for policy 0, policy_version 239667 (0.0010) -[2023-11-28 06:29:10,097][87426] Updated weights for policy 1, policy_version 239350 (0.0008) -[2023-11-28 06:29:10,219][87424] Updated weights for policy 0, policy_version 239677 (0.0010) -[2023-11-28 06:29:10,471][87426] Updated weights for policy 1, policy_version 239360 (0.0008) -[2023-11-28 06:29:12,430][87426] Updated weights for policy 1, policy_version 239370 (0.0011) -[2023-11-28 06:29:12,716][87424] Updated weights for policy 0, policy_version 239687 (0.0011) -[2023-11-28 06:29:12,801][87426] Updated weights for policy 1, policy_version 239380 (0.0011) -[2023-11-28 06:29:13,092][87424] Updated weights for policy 0, policy_version 239697 (0.0009) -[2023-11-28 06:29:13,171][87426] Updated weights for policy 1, policy_version 239390 (0.0010) -[2023-11-28 06:29:13,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 122642432. Throughput: 0: 2729.2, 1: 2694.8. Samples: 122655664. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:29:13,445][86177] Avg episode reward: [(0, '-507.220'), (1, '-528.890')] -[2023-11-28 06:29:13,467][87424] Updated weights for policy 0, policy_version 239707 (0.0008) -[2023-11-28 06:29:15,510][87424] Updated weights for policy 0, policy_version 239717 (0.0009) -[2023-11-28 06:29:15,532][87426] Updated weights for policy 1, policy_version 239400 (0.0011) -[2023-11-28 06:29:15,883][87424] Updated weights for policy 0, policy_version 239727 (0.0012) -[2023-11-28 06:29:15,908][87426] Updated weights for policy 1, policy_version 239410 (0.0008) -[2023-11-28 06:29:16,261][87424] Updated weights for policy 0, policy_version 239737 (0.0009) -[2023-11-28 06:29:16,285][87426] Updated weights for policy 1, policy_version 239420 (0.0007) -[2023-11-28 06:29:18,373][87424] Updated weights for policy 0, policy_version 239747 (0.0011) -[2023-11-28 06:29:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 122667008. Throughput: 0: 2736.4, 1: 2693.5. Samples: 122680936. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 06:29:18,446][86177] Avg episode reward: [(0, '-542.360'), (1, '-527.250')] -[2023-11-28 06:29:18,492][87426] Updated weights for policy 1, policy_version 239430 (0.0010) -[2023-11-28 06:29:18,751][87424] Updated weights for policy 0, policy_version 239757 (0.0011) -[2023-11-28 06:29:18,866][87426] Updated weights for policy 1, policy_version 239440 (0.0011) -[2023-11-28 06:29:19,124][87424] Updated weights for policy 0, policy_version 239767 (0.0011) -[2023-11-28 06:29:19,244][87426] Updated weights for policy 1, policy_version 239450 (0.0011) -[2023-11-28 06:29:21,340][87424] Updated weights for policy 0, policy_version 239777 (0.0009) -[2023-11-28 06:29:21,719][87424] Updated weights for policy 0, policy_version 239787 (0.0010) -[2023-11-28 06:29:21,822][87426] Updated weights for policy 1, policy_version 239460 (0.0011) -[2023-11-28 06:29:22,106][87424] Updated weights for policy 0, policy_version 239797 (0.0011) -[2023-11-28 06:29:22,213][87426] Updated weights for policy 1, policy_version 239470 (0.0011) -[2023-11-28 06:29:22,492][87424] Updated weights for policy 0, policy_version 239807 (0.0011) -[2023-11-28 06:29:22,584][87426] Updated weights for policy 1, policy_version 239480 (0.0009) -[2023-11-28 06:29:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 122699776. Throughput: 0: 2731.4, 1: 2647.0. Samples: 122712388. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:29:23,445][86177] Avg episode reward: [(0, '-526.230'), (1, '-491.400')] -[2023-11-28 06:29:24,515][87424] Updated weights for policy 0, policy_version 239817 (0.0011) -[2023-11-28 06:29:24,905][87424] Updated weights for policy 0, policy_version 239827 (0.0007) -[2023-11-28 06:29:25,171][87426] Updated weights for policy 1, policy_version 239490 (0.0009) -[2023-11-28 06:29:25,293][87424] Updated weights for policy 0, policy_version 239837 (0.0009) -[2023-11-28 06:29:25,545][87426] Updated weights for policy 1, policy_version 239500 (0.0011) -[2023-11-28 06:29:25,916][87426] Updated weights for policy 1, policy_version 239510 (0.0012) -[2023-11-28 06:29:26,304][87426] Updated weights for policy 1, policy_version 239520 (0.0012) -[2023-11-28 06:29:27,645][87424] Updated weights for policy 0, policy_version 239847 (0.0009) -[2023-11-28 06:29:28,020][87424] Updated weights for policy 0, policy_version 239857 (0.0008) -[2023-11-28 06:29:28,301][87426] Updated weights for policy 1, policy_version 239530 (0.0012) -[2023-11-28 06:29:28,396][87424] Updated weights for policy 0, policy_version 239867 (0.0007) -[2023-11-28 06:29:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 122716160. Throughput: 0: 2729.2, 1: 2677.8. Samples: 122737592. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:29:28,446][86177] Avg episode reward: [(0, '-532.430'), (1, '-499.700')] -[2023-11-28 06:29:28,692][87426] Updated weights for policy 1, policy_version 239540 (0.0012) -[2023-11-28 06:29:29,070][87426] Updated weights for policy 1, policy_version 239550 (0.0012) -[2023-11-28 06:29:30,589][87424] Updated weights for policy 0, policy_version 239877 (0.0010) -[2023-11-28 06:29:30,976][87424] Updated weights for policy 0, policy_version 239887 (0.0009) -[2023-11-28 06:29:31,274][87426] Updated weights for policy 1, policy_version 239560 (0.0011) -[2023-11-28 06:29:31,364][87424] Updated weights for policy 0, policy_version 239897 (0.0007) -[2023-11-28 06:29:31,654][87426] Updated weights for policy 1, policy_version 239570 (0.0011) -[2023-11-28 06:29:32,033][87426] Updated weights for policy 1, policy_version 239580 (0.0012) -[2023-11-28 06:29:33,291][87424] Updated weights for policy 0, policy_version 239907 (0.0012) -[2023-11-28 06:29:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 122748928. Throughput: 0: 2722.8, 1: 2658.1. Samples: 122761528. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:29:33,445][86177] Avg episode reward: [(0, '-532.510'), (1, '-500.350')] -[2023-11-28 06:29:33,689][87424] Updated weights for policy 0, policy_version 239917 (0.0012) -[2023-11-28 06:29:34,073][87424] Updated weights for policy 0, policy_version 239927 (0.0012) -[2023-11-28 06:29:34,391][87426] Updated weights for policy 1, policy_version 239590 (0.0009) -[2023-11-28 06:29:34,768][87426] Updated weights for policy 1, policy_version 239600 (0.0009) -[2023-11-28 06:29:35,149][87426] Updated weights for policy 1, policy_version 239610 (0.0009) -[2023-11-28 06:29:36,557][87424] Updated weights for policy 0, policy_version 239937 (0.0010) -[2023-11-28 06:29:36,805][87426] Updated weights for policy 1, policy_version 239620 (0.0009) -[2023-11-28 06:29:36,938][87424] Updated weights for policy 0, policy_version 239947 (0.0012) -[2023-11-28 06:29:37,191][87426] Updated weights for policy 1, policy_version 239630 (0.0009) -[2023-11-28 06:29:37,325][87424] Updated weights for policy 0, policy_version 239957 (0.0012) -[2023-11-28 06:29:37,562][87426] Updated weights for policy 1, policy_version 239640 (0.0011) -[2023-11-28 06:29:37,699][87424] Updated weights for policy 0, policy_version 239967 (0.0011) -[2023-11-28 06:29:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 122781696. Throughput: 0: 2698.8, 1: 2671.4. Samples: 122794728. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:29:38,445][86177] Avg episode reward: [(0, '-500.340'), (1, '-507.150')] -[2023-11-28 06:29:39,781][87424] Updated weights for policy 0, policy_version 239977 (0.0012) -[2023-11-28 06:29:39,880][87426] Updated weights for policy 1, policy_version 239650 (0.0012) -[2023-11-28 06:29:40,163][87424] Updated weights for policy 0, policy_version 239987 (0.0011) -[2023-11-28 06:29:40,253][87426] Updated weights for policy 1, policy_version 239660 (0.0011) -[2023-11-28 06:29:40,542][87424] Updated weights for policy 0, policy_version 239997 (0.0009) -[2023-11-28 06:29:40,630][87426] Updated weights for policy 1, policy_version 239670 (0.0011) -[2023-11-28 06:29:41,013][87426] Updated weights for policy 1, policy_version 239680 (0.0012) -[2023-11-28 06:29:42,597][87424] Updated weights for policy 0, policy_version 240007 (0.0009) -[2023-11-28 06:29:42,977][87424] Updated weights for policy 0, policy_version 240017 (0.0012) -[2023-11-28 06:29:43,354][87424] Updated weights for policy 0, policy_version 240027 (0.0011) -[2023-11-28 06:29:43,364][87426] Updated weights for policy 1, policy_version 239690 (0.0012) -[2023-11-28 06:29:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 122798080. Throughput: 0: 2718.8, 1: 2676.5. Samples: 122819668. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:29:43,445][86177] Avg episode reward: [(0, '-500.960'), (1, '-506.840')] -[2023-11-28 06:29:43,736][87426] Updated weights for policy 1, policy_version 239700 (0.0011) -[2023-11-28 06:29:44,119][87426] Updated weights for policy 1, policy_version 239710 (0.0012) -[2023-11-28 06:29:45,535][87424] Updated weights for policy 0, policy_version 240037 (0.0012) -[2023-11-28 06:29:45,918][87424] Updated weights for policy 0, policy_version 240047 (0.0012) -[2023-11-28 06:29:46,292][87424] Updated weights for policy 0, policy_version 240057 (0.0012) -[2023-11-28 06:29:46,437][87426] Updated weights for policy 1, policy_version 239720 (0.0009) -[2023-11-28 06:29:46,812][87426] Updated weights for policy 1, policy_version 239730 (0.0007) -[2023-11-28 06:29:47,187][87426] Updated weights for policy 1, policy_version 239740 (0.0008) -[2023-11-28 06:29:48,361][87424] Updated weights for policy 0, policy_version 240067 (0.0011) -[2023-11-28 06:29:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 122830848. Throughput: 0: 2729.7, 1: 2661.4. Samples: 122844308. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:29:48,445][86177] Avg episode reward: [(0, '-494.080'), (1, '-509.750')] -[2023-11-28 06:29:48,746][87424] Updated weights for policy 0, policy_version 240077 (0.0012) -[2023-11-28 06:29:49,016][87426] Updated weights for policy 1, policy_version 239750 (0.0008) -[2023-11-28 06:29:49,123][87424] Updated weights for policy 0, policy_version 240087 (0.0012) -[2023-11-28 06:29:49,394][87426] Updated weights for policy 1, policy_version 239760 (0.0009) -[2023-11-28 06:29:49,778][87426] Updated weights for policy 1, policy_version 239770 (0.0011) -[2023-11-28 06:29:51,131][87424] Updated weights for policy 0, policy_version 240097 (0.0011) -[2023-11-28 06:29:51,445][87426] Updated weights for policy 1, policy_version 239780 (0.0009) -[2023-11-28 06:29:51,514][87424] Updated weights for policy 0, policy_version 240107 (0.0011) -[2023-11-28 06:29:51,826][87426] Updated weights for policy 1, policy_version 239790 (0.0011) -[2023-11-28 06:29:51,906][87424] Updated weights for policy 0, policy_version 240117 (0.0010) -[2023-11-28 06:29:52,204][87426] Updated weights for policy 1, policy_version 239800 (0.0012) -[2023-11-28 06:29:52,287][87424] Updated weights for policy 0, policy_version 240127 (0.0009) -[2023-11-28 06:29:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 122863616. Throughput: 0: 2770.8, 1: 2660.8. Samples: 122877336. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:29:53,445][86177] Avg episode reward: [(0, '-533.640'), (1, '-515.940')] -[2023-11-28 06:29:54,519][87424] Updated weights for policy 0, policy_version 240137 (0.0008) -[2023-11-28 06:29:54,716][87426] Updated weights for policy 1, policy_version 239810 (0.0012) -[2023-11-28 06:29:54,909][87424] Updated weights for policy 0, policy_version 240147 (0.0010) -[2023-11-28 06:29:55,102][87426] Updated weights for policy 1, policy_version 239820 (0.0009) -[2023-11-28 06:29:55,300][87424] Updated weights for policy 0, policy_version 240157 (0.0007) -[2023-11-28 06:29:55,484][87426] Updated weights for policy 1, policy_version 239830 (0.0007) -[2023-11-28 06:29:55,850][87426] Updated weights for policy 1, policy_version 239840 (0.0007) -[2023-11-28 06:29:57,545][87424] Updated weights for policy 0, policy_version 240167 (0.0007) -[2023-11-28 06:29:57,928][87424] Updated weights for policy 0, policy_version 240177 (0.0007) -[2023-11-28 06:29:58,160][87426] Updated weights for policy 1, policy_version 239850 (0.0007) -[2023-11-28 06:29:58,310][87424] Updated weights for policy 0, policy_version 240187 (0.0008) -[2023-11-28 06:29:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 122880000. Throughput: 0: 2782.0, 1: 2690.6. Samples: 122901932. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:29:58,445][86177] Avg episode reward: [(0, '-532.710'), (1, '-508.890')] -[2023-11-28 06:29:58,539][87426] Updated weights for policy 1, policy_version 239860 (0.0009) -[2023-11-28 06:29:58,909][87426] Updated weights for policy 1, policy_version 239870 (0.0008) -[2023-11-28 06:30:00,162][87424] Updated weights for policy 0, policy_version 240197 (0.0010) -[2023-11-28 06:30:00,534][87424] Updated weights for policy 0, policy_version 240207 (0.0012) -[2023-11-28 06:30:00,902][87426] Updated weights for policy 1, policy_version 239880 (0.0011) -[2023-11-28 06:30:00,917][87424] Updated weights for policy 0, policy_version 240217 (0.0011) -[2023-11-28 06:30:01,274][87426] Updated weights for policy 1, policy_version 239890 (0.0012) -[2023-11-28 06:30:01,649][87426] Updated weights for policy 1, policy_version 239900 (0.0012) -[2023-11-28 06:30:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 122912768. Throughput: 0: 2753.3, 1: 2688.8. Samples: 122925832. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:30:03,445][86177] Avg episode reward: [(0, '-534.340'), (1, '-510.010')] -[2023-11-28 06:30:03,487][87424] Updated weights for policy 0, policy_version 240227 (0.0011) -[2023-11-28 06:30:03,872][87424] Updated weights for policy 0, policy_version 240237 (0.0012) -[2023-11-28 06:30:03,900][87426] Updated weights for policy 1, policy_version 239910 (0.0011) -[2023-11-28 06:30:04,259][87424] Updated weights for policy 0, policy_version 240247 (0.0010) -[2023-11-28 06:30:04,271][87426] Updated weights for policy 1, policy_version 239920 (0.0008) -[2023-11-28 06:30:04,653][87426] Updated weights for policy 1, policy_version 239930 (0.0010) -[2023-11-28 06:30:06,600][87426] Updated weights for policy 1, policy_version 239940 (0.0010) -[2023-11-28 06:30:06,730][87424] Updated weights for policy 0, policy_version 240257 (0.0010) -[2023-11-28 06:30:06,971][87426] Updated weights for policy 1, policy_version 239950 (0.0009) -[2023-11-28 06:30:07,118][87424] Updated weights for policy 0, policy_version 240267 (0.0008) -[2023-11-28 06:30:07,348][87426] Updated weights for policy 1, policy_version 239960 (0.0007) -[2023-11-28 06:30:07,489][87424] Updated weights for policy 0, policy_version 240277 (0.0007) -[2023-11-28 06:30:07,877][87424] Updated weights for policy 0, policy_version 240287 (0.0008) -[2023-11-28 06:30:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 122945536. Throughput: 0: 2731.5, 1: 2735.6. Samples: 122958408. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:30:08,446][86177] Avg episode reward: [(0, '-494.450'), (1, '-514.650')] -[2023-11-28 06:30:09,503][87426] Updated weights for policy 1, policy_version 239970 (0.0009) -[2023-11-28 06:30:09,886][87426] Updated weights for policy 1, policy_version 239980 (0.0012) -[2023-11-28 06:30:10,100][87424] Updated weights for policy 0, policy_version 240297 (0.0009) -[2023-11-28 06:30:10,260][87426] Updated weights for policy 1, policy_version 239990 (0.0012) -[2023-11-28 06:30:10,484][87424] Updated weights for policy 0, policy_version 240307 (0.0008) -[2023-11-28 06:30:10,635][87426] Updated weights for policy 1, policy_version 240000 (0.0012) -[2023-11-28 06:30:10,864][87424] Updated weights for policy 0, policy_version 240317 (0.0008) -[2023-11-28 06:30:12,897][87426] Updated weights for policy 1, policy_version 240010 (0.0011) -[2023-11-28 06:30:12,923][87424] Updated weights for policy 0, policy_version 240327 (0.0009) -[2023-11-28 06:30:13,278][87426] Updated weights for policy 1, policy_version 240020 (0.0009) -[2023-11-28 06:30:13,311][87424] Updated weights for policy 0, policy_version 240337 (0.0009) -[2023-11-28 06:30:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 122961920. Throughput: 0: 2726.9, 1: 2703.3. Samples: 122981952. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:30:13,445][86177] Avg episode reward: [(0, '-494.630'), (1, '-506.050')] -[2023-11-28 06:30:13,660][87426] Updated weights for policy 1, policy_version 240030 (0.0010) -[2023-11-28 06:30:13,696][87424] Updated weights for policy 0, policy_version 240347 (0.0008) -[2023-11-28 06:30:15,641][87426] Updated weights for policy 1, policy_version 240040 (0.0011) -[2023-11-28 06:30:15,817][87424] Updated weights for policy 0, policy_version 240357 (0.0011) -[2023-11-28 06:30:16,011][87426] Updated weights for policy 1, policy_version 240050 (0.0009) -[2023-11-28 06:30:16,194][87424] Updated weights for policy 0, policy_version 240367 (0.0008) -[2023-11-28 06:30:16,399][87426] Updated weights for policy 1, policy_version 240060 (0.0009) -[2023-11-28 06:30:16,579][87424] Updated weights for policy 0, policy_version 240377 (0.0011) -[2023-11-28 06:30:18,370][87426] Updated weights for policy 1, policy_version 240070 (0.0010) -[2023-11-28 06:30:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 122994688. Throughput: 0: 2719.9, 1: 2739.8. Samples: 123007216. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:30:18,445][86177] Avg episode reward: [(0, '-494.260'), (1, '-504.330')] -[2023-11-28 06:30:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000240384_61538304.pth... -[2023-11-28 06:30:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000237856_60891136.pth -[2023-11-28 06:30:18,717][87424] Updated weights for policy 0, policy_version 240387 (0.0011) -[2023-11-28 06:30:18,762][87426] Updated weights for policy 1, policy_version 240080 (0.0009) -[2023-11-28 06:30:19,101][87424] Updated weights for policy 0, policy_version 240397 (0.0008) -[2023-11-28 06:30:19,134][87426] Updated weights for policy 1, policy_version 240090 (0.0010) -[2023-11-28 06:30:19,361][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000240096_61464576.pth... -[2023-11-28 06:30:19,400][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000237536_60809216.pth -[2023-11-28 06:30:19,490][87424] Updated weights for policy 0, policy_version 240407 (0.0010) -[2023-11-28 06:30:21,653][87426] Updated weights for policy 1, policy_version 240100 (0.0010) -[2023-11-28 06:30:21,654][87424] Updated weights for policy 0, policy_version 240417 (0.0008) -[2023-11-28 06:30:22,030][87426] Updated weights for policy 1, policy_version 240110 (0.0011) -[2023-11-28 06:30:22,042][87424] Updated weights for policy 0, policy_version 240427 (0.0011) -[2023-11-28 06:30:22,405][87426] Updated weights for policy 1, policy_version 240120 (0.0011) -[2023-11-28 06:30:22,419][87424] Updated weights for policy 0, policy_version 240437 (0.0011) -[2023-11-28 06:30:22,799][87424] Updated weights for policy 0, policy_version 240447 (0.0012) -[2023-11-28 06:30:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 123027456. Throughput: 0: 2715.6, 1: 2708.8. Samples: 123038824. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:30:23,445][86177] Avg episode reward: [(0, '-494.650'), (1, '-509.260')] -[2023-11-28 06:30:24,463][87426] Updated weights for policy 1, policy_version 240130 (0.0010) -[2023-11-28 06:30:24,839][87426] Updated weights for policy 1, policy_version 240140 (0.0012) -[2023-11-28 06:30:25,216][87426] Updated weights for policy 1, policy_version 240150 (0.0012) -[2023-11-28 06:30:25,296][87424] Updated weights for policy 0, policy_version 240457 (0.0011) -[2023-11-28 06:30:25,592][87426] Updated weights for policy 1, policy_version 240160 (0.0012) -[2023-11-28 06:30:25,684][87424] Updated weights for policy 0, policy_version 240467 (0.0012) -[2023-11-28 06:30:26,062][87424] Updated weights for policy 0, policy_version 240477 (0.0012) -[2023-11-28 06:30:28,019][87426] Updated weights for policy 1, policy_version 240170 (0.0012) -[2023-11-28 06:30:28,090][87424] Updated weights for policy 0, policy_version 240487 (0.0012) -[2023-11-28 06:30:28,391][87426] Updated weights for policy 1, policy_version 240180 (0.0007) -[2023-11-28 06:30:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 123043840. Throughput: 0: 2695.6, 1: 2707.0. Samples: 123062784. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:30:28,445][86177] Avg episode reward: [(0, '-491.710'), (1, '-504.010')] -[2023-11-28 06:30:28,470][87424] Updated weights for policy 0, policy_version 240497 (0.0012) -[2023-11-28 06:30:28,777][87426] Updated weights for policy 1, policy_version 240190 (0.0011) -[2023-11-28 06:30:28,846][87424] Updated weights for policy 0, policy_version 240507 (0.0009) -[2023-11-28 06:30:30,988][87424] Updated weights for policy 0, policy_version 240517 (0.0012) -[2023-11-28 06:30:31,102][87426] Updated weights for policy 1, policy_version 240200 (0.0011) -[2023-11-28 06:30:31,361][87424] Updated weights for policy 0, policy_version 240527 (0.0012) -[2023-11-28 06:30:31,469][87426] Updated weights for policy 1, policy_version 240210 (0.0012) -[2023-11-28 06:30:31,744][87424] Updated weights for policy 0, policy_version 240537 (0.0011) -[2023-11-28 06:30:31,853][87426] Updated weights for policy 1, policy_version 240220 (0.0012) -[2023-11-28 06:30:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 123076608. Throughput: 0: 2699.8, 1: 2714.5. Samples: 123087952. Policy #0 lag: (min: 27.0, avg: 45.9, max: 59.0) -[2023-11-28 06:30:33,445][86177] Avg episode reward: [(0, '-493.690'), (1, '-511.380')] -[2023-11-28 06:30:34,021][87424] Updated weights for policy 0, policy_version 240547 (0.0010) -[2023-11-28 06:30:34,027][87426] Updated weights for policy 1, policy_version 240230 (0.0010) -[2023-11-28 06:30:34,406][87424] Updated weights for policy 0, policy_version 240557 (0.0010) -[2023-11-28 06:30:34,407][87426] Updated weights for policy 1, policy_version 240240 (0.0009) -[2023-11-28 06:30:34,790][87424] Updated weights for policy 0, policy_version 240567 (0.0008) -[2023-11-28 06:30:34,792][87426] Updated weights for policy 1, policy_version 240250 (0.0008) -[2023-11-28 06:30:36,949][87426] Updated weights for policy 1, policy_version 240260 (0.0008) -[2023-11-28 06:30:36,993][87424] Updated weights for policy 0, policy_version 240577 (0.0011) -[2023-11-28 06:30:37,327][87426] Updated weights for policy 1, policy_version 240270 (0.0009) -[2023-11-28 06:30:37,374][87424] Updated weights for policy 0, policy_version 240587 (0.0010) -[2023-11-28 06:30:37,709][87426] Updated weights for policy 1, policy_version 240280 (0.0007) -[2023-11-28 06:30:37,758][87424] Updated weights for policy 0, policy_version 240597 (0.0009) -[2023-11-28 06:30:38,147][87424] Updated weights for policy 0, policy_version 240607 (0.0008) -[2023-11-28 06:30:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 123109376. Throughput: 0: 2660.5, 1: 2743.8. Samples: 123120532. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:30:38,445][86177] Avg episode reward: [(0, '-496.670'), (1, '-521.220')] -[2023-11-28 06:30:39,872][87426] Updated weights for policy 1, policy_version 240290 (0.0008) -[2023-11-28 06:30:40,241][87426] Updated weights for policy 1, policy_version 240300 (0.0011) -[2023-11-28 06:30:40,341][87424] Updated weights for policy 0, policy_version 240617 (0.0010) -[2023-11-28 06:30:40,622][87426] Updated weights for policy 1, policy_version 240310 (0.0010) -[2023-11-28 06:30:40,723][87424] Updated weights for policy 0, policy_version 240627 (0.0011) -[2023-11-28 06:30:40,993][87426] Updated weights for policy 1, policy_version 240320 (0.0011) -[2023-11-28 06:30:41,109][87424] Updated weights for policy 0, policy_version 240637 (0.0011) -[2023-11-28 06:30:43,192][87424] Updated weights for policy 0, policy_version 240647 (0.0012) -[2023-11-28 06:30:43,254][87426] Updated weights for policy 1, policy_version 240330 (0.0011) -[2023-11-28 06:30:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 123125760. Throughput: 0: 2672.0, 1: 2733.3. Samples: 123145168. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:30:43,445][86177] Avg episode reward: [(0, '-497.780'), (1, '-515.070')] -[2023-11-28 06:30:43,575][87424] Updated weights for policy 0, policy_version 240657 (0.0007) -[2023-11-28 06:30:43,629][87426] Updated weights for policy 1, policy_version 240340 (0.0011) -[2023-11-28 06:30:43,957][87424] Updated weights for policy 0, policy_version 240667 (0.0008) -[2023-11-28 06:30:44,004][87426] Updated weights for policy 1, policy_version 240350 (0.0009) -[2023-11-28 06:30:45,935][87426] Updated weights for policy 1, policy_version 240360 (0.0011) -[2023-11-28 06:30:46,316][87426] Updated weights for policy 1, policy_version 240370 (0.0016) -[2023-11-28 06:30:46,318][87424] Updated weights for policy 0, policy_version 240677 (0.0010) -[2023-11-28 06:30:46,686][87426] Updated weights for policy 1, policy_version 240380 (0.0011) -[2023-11-28 06:30:46,698][87424] Updated weights for policy 0, policy_version 240687 (0.0012) -[2023-11-28 06:30:47,071][87424] Updated weights for policy 0, policy_version 240697 (0.0008) -[2023-11-28 06:30:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 123158528. Throughput: 0: 2660.6, 1: 2733.2. Samples: 123168552. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:30:48,445][86177] Avg episode reward: [(0, '-498.430'), (1, '-529.340')] -[2023-11-28 06:30:48,833][87426] Updated weights for policy 1, policy_version 240390 (0.0009) -[2023-11-28 06:30:49,207][87426] Updated weights for policy 1, policy_version 240400 (0.0012) -[2023-11-28 06:30:49,290][87424] Updated weights for policy 0, policy_version 240707 (0.0009) -[2023-11-28 06:30:49,576][87426] Updated weights for policy 1, policy_version 240410 (0.0009) -[2023-11-28 06:30:49,675][87424] Updated weights for policy 0, policy_version 240717 (0.0011) -[2023-11-28 06:30:50,053][87424] Updated weights for policy 0, policy_version 240727 (0.0012) -[2023-11-28 06:30:52,018][87426] Updated weights for policy 1, policy_version 240420 (0.0010) -[2023-11-28 06:30:52,401][87426] Updated weights for policy 1, policy_version 240430 (0.0009) -[2023-11-28 06:30:52,482][87424] Updated weights for policy 0, policy_version 240737 (0.0011) -[2023-11-28 06:30:52,775][87426] Updated weights for policy 1, policy_version 240440 (0.0010) -[2023-11-28 06:30:52,864][87424] Updated weights for policy 0, policy_version 240747 (0.0009) -[2023-11-28 06:30:53,248][87424] Updated weights for policy 0, policy_version 240757 (0.0012) -[2023-11-28 06:30:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 123183104. Throughput: 0: 2666.5, 1: 2702.1. Samples: 123199992. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:30:53,445][86177] Avg episode reward: [(0, '-496.050'), (1, '-520.750')] -[2023-11-28 06:30:53,636][87424] Updated weights for policy 0, policy_version 240767 (0.0012) -[2023-11-28 06:30:54,796][87426] Updated weights for policy 1, policy_version 240450 (0.0012) -[2023-11-28 06:30:55,173][87426] Updated weights for policy 1, policy_version 240460 (0.0012) -[2023-11-28 06:30:55,548][87426] Updated weights for policy 1, policy_version 240470 (0.0009) -[2023-11-28 06:30:55,699][87424] Updated weights for policy 0, policy_version 240777 (0.0008) -[2023-11-28 06:30:55,931][87426] Updated weights for policy 1, policy_version 240480 (0.0007) -[2023-11-28 06:30:56,103][87424] Updated weights for policy 0, policy_version 240787 (0.0010) -[2023-11-28 06:30:56,481][87424] Updated weights for policy 0, policy_version 240797 (0.0012) -[2023-11-28 06:30:58,242][87426] Updated weights for policy 1, policy_version 240490 (0.0009) -[2023-11-28 06:30:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 123207680. Throughput: 0: 2677.7, 1: 2740.5. Samples: 123225768. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:30:58,445][86177] Avg episode reward: [(0, '-491.810'), (1, '-519.830')] -[2023-11-28 06:30:58,513][87424] Updated weights for policy 0, policy_version 240807 (0.0009) -[2023-11-28 06:30:58,612][87426] Updated weights for policy 1, policy_version 240500 (0.0007) -[2023-11-28 06:30:58,897][87424] Updated weights for policy 0, policy_version 240817 (0.0010) -[2023-11-28 06:30:58,987][87426] Updated weights for policy 1, policy_version 240510 (0.0012) -[2023-11-28 06:30:59,267][87424] Updated weights for policy 0, policy_version 240827 (0.0011) -[2023-11-28 06:31:00,983][87426] Updated weights for policy 1, policy_version 240520 (0.0011) -[2023-11-28 06:31:01,364][87426] Updated weights for policy 1, policy_version 240530 (0.0010) -[2023-11-28 06:31:01,420][87424] Updated weights for policy 0, policy_version 240837 (0.0012) -[2023-11-28 06:31:01,754][87426] Updated weights for policy 1, policy_version 240540 (0.0009) -[2023-11-28 06:31:01,792][87424] Updated weights for policy 0, policy_version 240847 (0.0010) -[2023-11-28 06:31:02,184][87424] Updated weights for policy 0, policy_version 240857 (0.0009) -[2023-11-28 06:31:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 123240448. Throughput: 0: 2681.7, 1: 2725.5. Samples: 123250540. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:31:03,445][86177] Avg episode reward: [(0, '-491.130'), (1, '-521.640')] -[2023-11-28 06:31:03,741][87426] Updated weights for policy 1, policy_version 240550 (0.0011) -[2023-11-28 06:31:04,136][87426] Updated weights for policy 1, policy_version 240560 (0.0012) -[2023-11-28 06:31:04,501][87426] Updated weights for policy 1, policy_version 240570 (0.0011) -[2023-11-28 06:31:04,693][87424] Updated weights for policy 0, policy_version 240867 (0.0009) -[2023-11-28 06:31:05,068][87424] Updated weights for policy 0, policy_version 240877 (0.0009) -[2023-11-28 06:31:05,445][87424] Updated weights for policy 0, policy_version 240887 (0.0009) -[2023-11-28 06:31:06,940][87426] Updated weights for policy 1, policy_version 240580 (0.0009) -[2023-11-28 06:31:07,321][87426] Updated weights for policy 1, policy_version 240590 (0.0011) -[2023-11-28 06:31:07,699][87426] Updated weights for policy 1, policy_version 240600 (0.0008) -[2023-11-28 06:31:07,838][87424] Updated weights for policy 0, policy_version 240897 (0.0009) -[2023-11-28 06:31:08,218][87424] Updated weights for policy 0, policy_version 240907 (0.0011) -[2023-11-28 06:31:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 123265024. Throughput: 0: 2678.6, 1: 2727.8. Samples: 123282112. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:31:08,445][86177] Avg episode reward: [(0, '-492.460'), (1, '-553.110')] -[2023-11-28 06:31:08,607][87424] Updated weights for policy 0, policy_version 240917 (0.0012) -[2023-11-28 06:31:08,979][87424] Updated weights for policy 0, policy_version 240927 (0.0012) -[2023-11-28 06:31:09,692][87426] Updated weights for policy 1, policy_version 240610 (0.0008) -[2023-11-28 06:31:10,076][87426] Updated weights for policy 1, policy_version 240620 (0.0010) -[2023-11-28 06:31:10,457][87426] Updated weights for policy 1, policy_version 240630 (0.0009) -[2023-11-28 06:31:10,835][87426] Updated weights for policy 1, policy_version 240640 (0.0012) -[2023-11-28 06:31:11,401][87424] Updated weights for policy 0, policy_version 240937 (0.0010) -[2023-11-28 06:31:11,794][87424] Updated weights for policy 0, policy_version 240947 (0.0008) -[2023-11-28 06:31:12,164][87424] Updated weights for policy 0, policy_version 240957 (0.0008) -[2023-11-28 06:31:13,423][87426] Updated weights for policy 1, policy_version 240650 (0.0011) -[2023-11-28 06:31:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 123289600. Throughput: 0: 2683.7, 1: 2716.3. Samples: 123305784. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:31:13,445][86177] Avg episode reward: [(0, '-493.620'), (1, '-553.780')] -[2023-11-28 06:31:13,799][87426] Updated weights for policy 1, policy_version 240660 (0.0009) -[2023-11-28 06:31:14,183][87426] Updated weights for policy 1, policy_version 240670 (0.0007) -[2023-11-28 06:31:14,690][87424] Updated weights for policy 0, policy_version 240967 (0.0011) -[2023-11-28 06:31:15,076][87424] Updated weights for policy 0, policy_version 240977 (0.0012) -[2023-11-28 06:31:15,460][87424] Updated weights for policy 0, policy_version 240987 (0.0010) -[2023-11-28 06:31:16,435][87426] Updated weights for policy 1, policy_version 240680 (0.0009) -[2023-11-28 06:31:16,813][87426] Updated weights for policy 1, policy_version 240690 (0.0008) -[2023-11-28 06:31:17,194][87426] Updated weights for policy 1, policy_version 240700 (0.0007) -[2023-11-28 06:31:17,636][87424] Updated weights for policy 0, policy_version 240997 (0.0008) -[2023-11-28 06:31:18,012][87424] Updated weights for policy 0, policy_version 241007 (0.0011) -[2023-11-28 06:31:18,394][87424] Updated weights for policy 0, policy_version 241017 (0.0012) -[2023-11-28 06:31:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 123314176. Throughput: 0: 2641.2, 1: 2709.5. Samples: 123328732. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:31:18,445][86177] Avg episode reward: [(0, '-492.720'), (1, '-555.940')] -[2023-11-28 06:31:19,368][87426] Updated weights for policy 1, policy_version 240710 (0.0009) -[2023-11-28 06:31:19,770][87426] Updated weights for policy 1, policy_version 240720 (0.0008) -[2023-11-28 06:31:20,121][87426] Updated weights for policy 1, policy_version 240730 (0.0010) -[2023-11-28 06:31:20,478][87424] Updated weights for policy 0, policy_version 241027 (0.0010) -[2023-11-28 06:31:20,873][87424] Updated weights for policy 0, policy_version 241037 (0.0012) -[2023-11-28 06:31:21,249][87424] Updated weights for policy 0, policy_version 241047 (0.0009) -[2023-11-28 06:31:22,520][87426] Updated weights for policy 1, policy_version 240740 (0.0011) -[2023-11-28 06:31:22,895][87426] Updated weights for policy 1, policy_version 240750 (0.0012) -[2023-11-28 06:31:23,277][87426] Updated weights for policy 1, policy_version 240760 (0.0012) -[2023-11-28 06:31:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 123338752. Throughput: 0: 2632.4, 1: 2692.1. Samples: 123360136. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:31:23,445][86177] Avg episode reward: [(0, '-493.380'), (1, '-561.470')] -[2023-11-28 06:31:23,528][87424] Updated weights for policy 0, policy_version 241057 (0.0008) -[2023-11-28 06:31:23,914][87424] Updated weights for policy 0, policy_version 241067 (0.0012) -[2023-11-28 06:31:24,292][87424] Updated weights for policy 0, policy_version 241077 (0.0012) -[2023-11-28 06:31:24,680][87424] Updated weights for policy 0, policy_version 241087 (0.0012) -[2023-11-28 06:31:25,625][87426] Updated weights for policy 1, policy_version 240770 (0.0010) -[2023-11-28 06:31:26,014][87426] Updated weights for policy 1, policy_version 240780 (0.0011) -[2023-11-28 06:31:26,394][87426] Updated weights for policy 1, policy_version 240790 (0.0012) -[2023-11-28 06:31:26,648][87424] Updated weights for policy 0, policy_version 241097 (0.0008) -[2023-11-28 06:31:26,774][87426] Updated weights for policy 1, policy_version 240800 (0.0012) -[2023-11-28 06:31:27,026][87424] Updated weights for policy 0, policy_version 241107 (0.0011) -[2023-11-28 06:31:27,395][87424] Updated weights for policy 0, policy_version 241117 (0.0012) -[2023-11-28 06:31:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 123371520. Throughput: 0: 2615.5, 1: 2716.4. Samples: 123385108. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:31:28,446][86177] Avg episode reward: [(0, '-493.490'), (1, '-522.660')] -[2023-11-28 06:31:28,748][87426] Updated weights for policy 1, policy_version 240810 (0.0012) -[2023-11-28 06:31:29,127][87426] Updated weights for policy 1, policy_version 240820 (0.0012) -[2023-11-28 06:31:29,505][87426] Updated weights for policy 1, policy_version 240830 (0.0012) -[2023-11-28 06:31:29,906][87424] Updated weights for policy 0, policy_version 241127 (0.0010) -[2023-11-28 06:31:30,292][87424] Updated weights for policy 0, policy_version 241137 (0.0011) -[2023-11-28 06:31:30,678][87424] Updated weights for policy 0, policy_version 241147 (0.0009) -[2023-11-28 06:31:31,461][87426] Updated weights for policy 1, policy_version 240840 (0.0012) -[2023-11-28 06:31:31,841][87426] Updated weights for policy 1, policy_version 240850 (0.0008) -[2023-11-28 06:31:32,220][87426] Updated weights for policy 1, policy_version 240860 (0.0008) -[2023-11-28 06:31:32,462][87424] Updated weights for policy 0, policy_version 241157 (0.0008) -[2023-11-28 06:31:32,846][87424] Updated weights for policy 0, policy_version 241167 (0.0008) -[2023-11-28 06:31:33,222][87424] Updated weights for policy 0, policy_version 241177 (0.0010) -[2023-11-28 06:31:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 123396096. Throughput: 0: 2641.4, 1: 2704.4. Samples: 123409116. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:31:33,445][86177] Avg episode reward: [(0, '-495.220'), (1, '-525.920')] -[2023-11-28 06:31:34,494][87426] Updated weights for policy 1, policy_version 240870 (0.0009) -[2023-11-28 06:31:34,872][87426] Updated weights for policy 1, policy_version 240880 (0.0009) -[2023-11-28 06:31:35,248][87426] Updated weights for policy 1, policy_version 240890 (0.0009) -[2023-11-28 06:31:35,766][87424] Updated weights for policy 0, policy_version 241187 (0.0012) -[2023-11-28 06:31:36,155][87424] Updated weights for policy 0, policy_version 241197 (0.0011) -[2023-11-28 06:31:36,529][87424] Updated weights for policy 0, policy_version 241207 (0.0009) -[2023-11-28 06:31:37,568][87426] Updated weights for policy 1, policy_version 240900 (0.0007) -[2023-11-28 06:31:37,940][87426] Updated weights for policy 1, policy_version 240910 (0.0007) -[2023-11-28 06:31:38,318][87426] Updated weights for policy 1, policy_version 240920 (0.0008) -[2023-11-28 06:31:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 123420672. Throughput: 0: 2628.6, 1: 2722.6. Samples: 123440796. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:31:38,445][86177] Avg episode reward: [(0, '-511.270'), (1, '-527.820')] -[2023-11-28 06:31:38,501][87424] Updated weights for policy 0, policy_version 241217 (0.0009) -[2023-11-28 06:31:38,878][87424] Updated weights for policy 0, policy_version 241227 (0.0011) -[2023-11-28 06:31:39,259][87424] Updated weights for policy 0, policy_version 241237 (0.0009) -[2023-11-28 06:31:39,633][87424] Updated weights for policy 0, policy_version 241247 (0.0008) -[2023-11-28 06:31:40,663][87426] Updated weights for policy 1, policy_version 240930 (0.0008) -[2023-11-28 06:31:41,049][87426] Updated weights for policy 1, policy_version 240940 (0.0008) -[2023-11-28 06:31:41,419][87426] Updated weights for policy 1, policy_version 240950 (0.0011) -[2023-11-28 06:31:41,794][87426] Updated weights for policy 1, policy_version 240960 (0.0011) -[2023-11-28 06:31:42,044][87424] Updated weights for policy 0, policy_version 241257 (0.0009) -[2023-11-28 06:31:42,428][87424] Updated weights for policy 0, policy_version 241267 (0.0010) -[2023-11-28 06:31:42,802][87424] Updated weights for policy 0, policy_version 241277 (0.0012) -[2023-11-28 06:31:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 123453440. Throughput: 0: 2609.1, 1: 2685.1. Samples: 123464004. Policy #0 lag: (min: 13.0, avg: 33.5, max: 45.0) -[2023-11-28 06:31:43,445][86177] Avg episode reward: [(0, '-510.420'), (1, '-519.940')] -[2023-11-28 06:31:44,181][87426] Updated weights for policy 1, policy_version 240970 (0.0007) -[2023-11-28 06:31:44,560][87426] Updated weights for policy 1, policy_version 240980 (0.0011) -[2023-11-28 06:31:44,938][87426] Updated weights for policy 1, policy_version 240990 (0.0010) -[2023-11-28 06:31:45,446][87424] Updated weights for policy 0, policy_version 241287 (0.0012) -[2023-11-28 06:31:45,816][87424] Updated weights for policy 0, policy_version 241297 (0.0012) -[2023-11-28 06:31:46,198][87424] Updated weights for policy 0, policy_version 241307 (0.0012) -[2023-11-28 06:31:46,980][87426] Updated weights for policy 1, policy_version 241000 (0.0008) -[2023-11-28 06:31:47,356][87426] Updated weights for policy 1, policy_version 241010 (0.0008) -[2023-11-28 06:31:47,735][87426] Updated weights for policy 1, policy_version 241020 (0.0007) -[2023-11-28 06:31:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 123478016. Throughput: 0: 2611.2, 1: 2665.8. Samples: 123488004. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:31:48,445][86177] Avg episode reward: [(0, '-510.680'), (1, '-538.690')] -[2023-11-28 06:31:48,627][87424] Updated weights for policy 0, policy_version 241317 (0.0011) -[2023-11-28 06:31:49,003][87424] Updated weights for policy 0, policy_version 241327 (0.0009) -[2023-11-28 06:31:49,392][87424] Updated weights for policy 0, policy_version 241337 (0.0011) -[2023-11-28 06:31:50,086][87426] Updated weights for policy 1, policy_version 241030 (0.0010) -[2023-11-28 06:31:50,462][87426] Updated weights for policy 1, policy_version 241040 (0.0012) -[2023-11-28 06:31:50,840][87426] Updated weights for policy 1, policy_version 241050 (0.0011) -[2023-11-28 06:31:51,869][87424] Updated weights for policy 0, policy_version 241347 (0.0011) -[2023-11-28 06:31:52,256][87424] Updated weights for policy 0, policy_version 241357 (0.0011) -[2023-11-28 06:31:52,638][87424] Updated weights for policy 0, policy_version 241367 (0.0011) -[2023-11-28 06:31:53,279][87426] Updated weights for policy 1, policy_version 241060 (0.0011) -[2023-11-28 06:31:53,446][86177] Fps is (10 sec: 4914.2, 60 sec: 5324.6, 300 sec: 5387.2). Total num frames: 123502592. Throughput: 0: 2598.7, 1: 2669.3. Samples: 123519184. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:31:53,447][86177] Avg episode reward: [(0, '-513.330'), (1, '-539.010')] -[2023-11-28 06:31:53,662][87426] Updated weights for policy 1, policy_version 241070 (0.0010) -[2023-11-28 06:31:54,031][87426] Updated weights for policy 1, policy_version 241080 (0.0010) -[2023-11-28 06:31:55,061][87424] Updated weights for policy 0, policy_version 241377 (0.0008) -[2023-11-28 06:31:55,439][87424] Updated weights for policy 0, policy_version 241387 (0.0012) -[2023-11-28 06:31:55,824][87424] Updated weights for policy 0, policy_version 241397 (0.0012) -[2023-11-28 06:31:55,963][87426] Updated weights for policy 1, policy_version 241090 (0.0010) -[2023-11-28 06:31:56,206][87424] Updated weights for policy 0, policy_version 241407 (0.0011) -[2023-11-28 06:31:56,340][87426] Updated weights for policy 1, policy_version 241100 (0.0008) -[2023-11-28 06:31:56,720][87426] Updated weights for policy 1, policy_version 241110 (0.0008) -[2023-11-28 06:31:57,103][87426] Updated weights for policy 1, policy_version 241120 (0.0008) -[2023-11-28 06:31:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 123527168. Throughput: 0: 2594.3, 1: 2686.2. Samples: 123543408. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:31:58,445][86177] Avg episode reward: [(0, '-498.770'), (1, '-561.560')] -[2023-11-28 06:31:58,780][87424] Updated weights for policy 0, policy_version 241417 (0.0007) -[2023-11-28 06:31:59,167][87424] Updated weights for policy 0, policy_version 241427 (0.0010) -[2023-11-28 06:31:59,461][87426] Updated weights for policy 1, policy_version 241130 (0.0010) -[2023-11-28 06:31:59,539][87424] Updated weights for policy 0, policy_version 241437 (0.0008) -[2023-11-28 06:31:59,849][87426] Updated weights for policy 1, policy_version 241140 (0.0010) -[2023-11-28 06:32:00,223][87426] Updated weights for policy 1, policy_version 241150 (0.0012) -[2023-11-28 06:32:01,642][87424] Updated weights for policy 0, policy_version 241447 (0.0010) -[2023-11-28 06:32:02,031][87424] Updated weights for policy 0, policy_version 241457 (0.0011) -[2023-11-28 06:32:02,409][87424] Updated weights for policy 0, policy_version 241467 (0.0010) -[2023-11-28 06:32:02,667][87426] Updated weights for policy 1, policy_version 241160 (0.0011) -[2023-11-28 06:32:03,037][87426] Updated weights for policy 1, policy_version 241170 (0.0012) -[2023-11-28 06:32:03,419][87426] Updated weights for policy 1, policy_version 241180 (0.0012) -[2023-11-28 06:32:03,444][86177] Fps is (10 sec: 4916.1, 60 sec: 5188.2, 300 sec: 5387.3). Total num frames: 123551744. Throughput: 0: 2609.4, 1: 2687.4. Samples: 123567088. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:03,446][86177] Avg episode reward: [(0, '-500.710'), (1, '-562.100')] -[2023-11-28 06:32:04,925][87424] Updated weights for policy 0, policy_version 241477 (0.0010) -[2023-11-28 06:32:05,320][87424] Updated weights for policy 0, policy_version 241487 (0.0012) -[2023-11-28 06:32:05,348][87426] Updated weights for policy 1, policy_version 241190 (0.0012) -[2023-11-28 06:32:05,701][87424] Updated weights for policy 0, policy_version 241497 (0.0011) -[2023-11-28 06:32:05,728][87426] Updated weights for policy 1, policy_version 241200 (0.0011) -[2023-11-28 06:32:06,102][87426] Updated weights for policy 1, policy_version 241210 (0.0010) -[2023-11-28 06:32:07,500][87424] Updated weights for policy 0, policy_version 241507 (0.0012) -[2023-11-28 06:32:07,885][87424] Updated weights for policy 0, policy_version 241517 (0.0012) -[2023-11-28 06:32:08,274][87424] Updated weights for policy 0, policy_version 241527 (0.0011) -[2023-11-28 06:32:08,384][87426] Updated weights for policy 1, policy_version 241220 (0.0009) -[2023-11-28 06:32:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 123576320. Throughput: 0: 2631.7, 1: 2688.0. Samples: 123599524. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:08,445][86177] Avg episode reward: [(0, '-514.530'), (1, '-562.850')] -[2023-11-28 06:32:08,761][87426] Updated weights for policy 1, policy_version 241230 (0.0012) -[2023-11-28 06:32:09,144][87426] Updated weights for policy 1, policy_version 241240 (0.0012) -[2023-11-28 06:32:10,196][87424] Updated weights for policy 0, policy_version 241537 (0.0012) -[2023-11-28 06:32:10,575][87424] Updated weights for policy 0, policy_version 241547 (0.0010) -[2023-11-28 06:32:10,957][87424] Updated weights for policy 0, policy_version 241557 (0.0011) -[2023-11-28 06:32:11,311][87426] Updated weights for policy 1, policy_version 241250 (0.0011) -[2023-11-28 06:32:11,340][87424] Updated weights for policy 0, policy_version 241567 (0.0012) -[2023-11-28 06:32:11,685][87426] Updated weights for policy 1, policy_version 241260 (0.0012) -[2023-11-28 06:32:12,060][87426] Updated weights for policy 1, policy_version 241270 (0.0011) -[2023-11-28 06:32:12,449][87426] Updated weights for policy 1, policy_version 241280 (0.0011) -[2023-11-28 06:32:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 123609088. Throughput: 0: 2643.7, 1: 2664.5. Samples: 123623976. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:13,445][86177] Avg episode reward: [(0, '-530.010'), (1, '-537.570')] -[2023-11-28 06:32:13,683][87424] Updated weights for policy 0, policy_version 241577 (0.0008) -[2023-11-28 06:32:14,064][87424] Updated weights for policy 0, policy_version 241587 (0.0008) -[2023-11-28 06:32:14,448][87424] Updated weights for policy 0, policy_version 241597 (0.0009) -[2023-11-28 06:32:14,845][87426] Updated weights for policy 1, policy_version 241290 (0.0012) -[2023-11-28 06:32:15,220][87426] Updated weights for policy 1, policy_version 241300 (0.0011) -[2023-11-28 06:32:15,601][87426] Updated weights for policy 1, policy_version 241310 (0.0012) -[2023-11-28 06:32:16,338][87424] Updated weights for policy 0, policy_version 241607 (0.0011) -[2023-11-28 06:32:16,714][87424] Updated weights for policy 0, policy_version 241617 (0.0011) -[2023-11-28 06:32:17,101][87424] Updated weights for policy 0, policy_version 241627 (0.0008) -[2023-11-28 06:32:17,476][87426] Updated weights for policy 1, policy_version 241320 (0.0011) -[2023-11-28 06:32:17,860][87426] Updated weights for policy 1, policy_version 241330 (0.0011) -[2023-11-28 06:32:18,230][87426] Updated weights for policy 1, policy_version 241340 (0.0012) -[2023-11-28 06:32:18,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 123641856. Throughput: 0: 2654.6, 1: 2676.7. Samples: 123649024. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:18,445][86177] Avg episode reward: [(0, '-531.410'), (1, '-515.820')] -[2023-11-28 06:32:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000241632_61857792.pth... -[2023-11-28 06:32:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000241344_61784064.pth... -[2023-11-28 06:32:18,504][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000238816_61136896.pth -[2023-11-28 06:32:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000239104_61210624.pth -[2023-11-28 06:32:18,511][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000241344_61784064.pth -[2023-11-28 06:32:18,512][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000241632_61857792.pth -[2023-11-28 06:32:19,093][87424] Updated weights for policy 0, policy_version 241637 (0.0009) -[2023-11-28 06:32:19,473][87424] Updated weights for policy 0, policy_version 241647 (0.0007) -[2023-11-28 06:32:19,856][87424] Updated weights for policy 0, policy_version 241657 (0.0008) -[2023-11-28 06:32:20,273][87426] Updated weights for policy 1, policy_version 241350 (0.0011) -[2023-11-28 06:32:20,650][87426] Updated weights for policy 1, policy_version 241360 (0.0012) -[2023-11-28 06:32:21,036][87426] Updated weights for policy 1, policy_version 241370 (0.0012) -[2023-11-28 06:32:21,778][87424] Updated weights for policy 0, policy_version 241667 (0.0011) -[2023-11-28 06:32:22,152][87424] Updated weights for policy 0, policy_version 241677 (0.0011) -[2023-11-28 06:32:22,542][87424] Updated weights for policy 0, policy_version 241687 (0.0011) -[2023-11-28 06:32:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 123666432. Throughput: 0: 2680.2, 1: 2683.8. Samples: 123682176. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:23,445][86177] Avg episode reward: [(0, '-529.890'), (1, '-517.010')] -[2023-11-28 06:32:23,445][87426] Updated weights for policy 1, policy_version 241380 (0.0011) -[2023-11-28 06:32:23,822][87426] Updated weights for policy 1, policy_version 241390 (0.0012) -[2023-11-28 06:32:24,200][87426] Updated weights for policy 1, policy_version 241400 (0.0008) -[2023-11-28 06:32:24,850][87424] Updated weights for policy 0, policy_version 241697 (0.0012) -[2023-11-28 06:32:25,228][87424] Updated weights for policy 0, policy_version 241707 (0.0012) -[2023-11-28 06:32:25,604][87424] Updated weights for policy 0, policy_version 241717 (0.0012) -[2023-11-28 06:32:25,984][87424] Updated weights for policy 0, policy_version 241727 (0.0012) -[2023-11-28 06:32:26,504][87426] Updated weights for policy 1, policy_version 241410 (0.0008) -[2023-11-28 06:32:26,885][87426] Updated weights for policy 1, policy_version 241420 (0.0011) -[2023-11-28 06:32:27,252][87426] Updated weights for policy 1, policy_version 241430 (0.0007) -[2023-11-28 06:32:27,633][87426] Updated weights for policy 1, policy_version 241440 (0.0007) -[2023-11-28 06:32:27,716][87424] Updated weights for policy 0, policy_version 241737 (0.0010) -[2023-11-28 06:32:28,104][87424] Updated weights for policy 0, policy_version 241747 (0.0012) -[2023-11-28 06:32:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 123691008. Throughput: 0: 2694.9, 1: 2688.7. Samples: 123706268. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:28,445][86177] Avg episode reward: [(0, '-516.300'), (1, '-549.410')] -[2023-11-28 06:32:28,495][87424] Updated weights for policy 0, policy_version 241757 (0.0012) -[2023-11-28 06:32:29,995][87426] Updated weights for policy 1, policy_version 241450 (0.0009) -[2023-11-28 06:32:30,372][87426] Updated weights for policy 1, policy_version 241460 (0.0012) -[2023-11-28 06:32:30,634][87424] Updated weights for policy 0, policy_version 241767 (0.0011) -[2023-11-28 06:32:30,756][87426] Updated weights for policy 1, policy_version 241470 (0.0011) -[2023-11-28 06:32:31,021][87424] Updated weights for policy 0, policy_version 241777 (0.0012) -[2023-11-28 06:32:31,399][87424] Updated weights for policy 0, policy_version 241787 (0.0012) -[2023-11-28 06:32:32,559][87426] Updated weights for policy 1, policy_version 241480 (0.0010) -[2023-11-28 06:32:32,933][87426] Updated weights for policy 1, policy_version 241490 (0.0011) -[2023-11-28 06:32:33,307][87426] Updated weights for policy 1, policy_version 241500 (0.0011) -[2023-11-28 06:32:33,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 123715584. Throughput: 0: 2693.8, 1: 2689.8. Samples: 123730268. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:33,446][86177] Avg episode reward: [(0, '-497.360'), (1, '-547.990')] -[2023-11-28 06:32:33,854][87424] Updated weights for policy 0, policy_version 241797 (0.0009) -[2023-11-28 06:32:34,238][87424] Updated weights for policy 0, policy_version 241807 (0.0007) -[2023-11-28 06:32:34,622][87424] Updated weights for policy 0, policy_version 241817 (0.0007) -[2023-11-28 06:32:35,475][87426] Updated weights for policy 1, policy_version 241510 (0.0009) -[2023-11-28 06:32:35,858][87426] Updated weights for policy 1, policy_version 241520 (0.0007) -[2023-11-28 06:32:36,234][87426] Updated weights for policy 1, policy_version 241530 (0.0008) -[2023-11-28 06:32:36,732][87424] Updated weights for policy 0, policy_version 241827 (0.0012) -[2023-11-28 06:32:37,111][87424] Updated weights for policy 0, policy_version 241837 (0.0012) -[2023-11-28 06:32:37,484][87424] Updated weights for policy 0, policy_version 241847 (0.0010) -[2023-11-28 06:32:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 123748352. Throughput: 0: 2727.8, 1: 2713.4. Samples: 123764028. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:38,445][86177] Avg episode reward: [(0, '-506.990'), (1, '-559.450')] -[2023-11-28 06:32:38,708][87426] Updated weights for policy 1, policy_version 241540 (0.0009) -[2023-11-28 06:32:39,079][87426] Updated weights for policy 1, policy_version 241550 (0.0012) -[2023-11-28 06:32:39,454][87426] Updated weights for policy 1, policy_version 241560 (0.0012) -[2023-11-28 06:32:39,588][87424] Updated weights for policy 0, policy_version 241857 (0.0012) -[2023-11-28 06:32:39,970][87424] Updated weights for policy 0, policy_version 241867 (0.0009) -[2023-11-28 06:32:40,362][87424] Updated weights for policy 0, policy_version 241877 (0.0012) -[2023-11-28 06:32:40,733][87424] Updated weights for policy 0, policy_version 241887 (0.0009) -[2023-11-28 06:32:41,837][87426] Updated weights for policy 1, policy_version 241570 (0.0011) -[2023-11-28 06:32:42,216][87426] Updated weights for policy 1, policy_version 241580 (0.0011) -[2023-11-28 06:32:42,593][87426] Updated weights for policy 1, policy_version 241590 (0.0008) -[2023-11-28 06:32:42,972][87426] Updated weights for policy 1, policy_version 241600 (0.0010) -[2023-11-28 06:32:43,056][87424] Updated weights for policy 0, policy_version 241897 (0.0012) -[2023-11-28 06:32:43,432][87424] Updated weights for policy 0, policy_version 241907 (0.0012) -[2023-11-28 06:32:43,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 123772928. Throughput: 0: 2754.8, 1: 2701.3. Samples: 123788932. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:43,445][86177] Avg episode reward: [(0, '-514.420'), (1, '-567.590')] -[2023-11-28 06:32:43,810][87424] Updated weights for policy 0, policy_version 241917 (0.0011) -[2023-11-28 06:32:44,726][87426] Updated weights for policy 1, policy_version 241610 (0.0012) -[2023-11-28 06:32:45,105][87426] Updated weights for policy 1, policy_version 241620 (0.0012) -[2023-11-28 06:32:45,487][87426] Updated weights for policy 1, policy_version 241630 (0.0012) -[2023-11-28 06:32:46,146][87424] Updated weights for policy 0, policy_version 241927 (0.0012) -[2023-11-28 06:32:46,525][87424] Updated weights for policy 0, policy_version 241937 (0.0012) -[2023-11-28 06:32:46,906][87424] Updated weights for policy 0, policy_version 241947 (0.0012) -[2023-11-28 06:32:47,882][87426] Updated weights for policy 1, policy_version 241640 (0.0012) -[2023-11-28 06:32:48,266][87426] Updated weights for policy 1, policy_version 241650 (0.0012) -[2023-11-28 06:32:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 123797504. Throughput: 0: 2759.1, 1: 2710.4. Samples: 123813216. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:48,445][86177] Avg episode reward: [(0, '-531.410'), (1, '-547.560')] -[2023-11-28 06:32:48,633][87426] Updated weights for policy 1, policy_version 241660 (0.0011) -[2023-11-28 06:32:49,197][87424] Updated weights for policy 0, policy_version 241957 (0.0012) -[2023-11-28 06:32:49,580][87424] Updated weights for policy 0, policy_version 241967 (0.0012) -[2023-11-28 06:32:49,953][87424] Updated weights for policy 0, policy_version 241977 (0.0012) -[2023-11-28 06:32:50,609][87426] Updated weights for policy 1, policy_version 241670 (0.0010) -[2023-11-28 06:32:50,995][87426] Updated weights for policy 1, policy_version 241680 (0.0011) -[2023-11-28 06:32:51,368][87426] Updated weights for policy 1, policy_version 241690 (0.0012) -[2023-11-28 06:32:51,898][87424] Updated weights for policy 0, policy_version 241987 (0.0011) -[2023-11-28 06:32:52,278][87424] Updated weights for policy 0, policy_version 241997 (0.0009) -[2023-11-28 06:32:52,651][87424] Updated weights for policy 0, policy_version 242007 (0.0012) -[2023-11-28 06:32:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.5, 300 sec: 5415.0). Total num frames: 123830272. Throughput: 0: 2757.7, 1: 2731.5. Samples: 123846536. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:53,445][86177] Avg episode reward: [(0, '-526.880'), (1, '-526.700')] -[2023-11-28 06:32:53,716][87426] Updated weights for policy 1, policy_version 241700 (0.0011) -[2023-11-28 06:32:54,101][87426] Updated weights for policy 1, policy_version 241710 (0.0008) -[2023-11-28 06:32:54,476][87426] Updated weights for policy 1, policy_version 241720 (0.0007) -[2023-11-28 06:32:55,104][87424] Updated weights for policy 0, policy_version 242017 (0.0012) -[2023-11-28 06:32:55,484][87424] Updated weights for policy 0, policy_version 242027 (0.0008) -[2023-11-28 06:32:55,878][87424] Updated weights for policy 0, policy_version 242037 (0.0007) -[2023-11-28 06:32:56,279][87424] Updated weights for policy 0, policy_version 242047 (0.0008) -[2023-11-28 06:32:56,320][87426] Updated weights for policy 1, policy_version 241730 (0.0008) -[2023-11-28 06:32:56,699][87426] Updated weights for policy 1, policy_version 241740 (0.0009) -[2023-11-28 06:32:57,077][87426] Updated weights for policy 1, policy_version 241750 (0.0007) -[2023-11-28 06:32:57,455][87426] Updated weights for policy 1, policy_version 241760 (0.0007) -[2023-11-28 06:32:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 123854848. Throughput: 0: 2740.9, 1: 2743.8. Samples: 123870788. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:32:58,445][86177] Avg episode reward: [(0, '-518.250'), (1, '-533.200')] -[2023-11-28 06:32:58,626][87424] Updated weights for policy 0, policy_version 242057 (0.0008) -[2023-11-28 06:32:58,976][87426] Updated weights for policy 1, policy_version 241770 (0.0012) -[2023-11-28 06:32:59,011][87424] Updated weights for policy 0, policy_version 242067 (0.0009) -[2023-11-28 06:32:59,351][87426] Updated weights for policy 1, policy_version 241780 (0.0010) -[2023-11-28 06:32:59,398][87424] Updated weights for policy 0, policy_version 242077 (0.0011) -[2023-11-28 06:32:59,738][87426] Updated weights for policy 1, policy_version 241790 (0.0008) -[2023-11-28 06:33:01,658][87426] Updated weights for policy 1, policy_version 241800 (0.0011) -[2023-11-28 06:33:01,843][87424] Updated weights for policy 0, policy_version 242087 (0.0012) -[2023-11-28 06:33:02,038][87426] Updated weights for policy 1, policy_version 241810 (0.0010) -[2023-11-28 06:33:02,224][87424] Updated weights for policy 0, policy_version 242097 (0.0009) -[2023-11-28 06:33:02,422][87426] Updated weights for policy 1, policy_version 241820 (0.0011) -[2023-11-28 06:33:02,609][87424] Updated weights for policy 0, policy_version 242107 (0.0010) -[2023-11-28 06:33:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 123887616. Throughput: 0: 2723.6, 1: 2752.7. Samples: 123895460. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:03,445][86177] Avg episode reward: [(0, '-509.690'), (1, '-527.200')] -[2023-11-28 06:33:04,394][87426] Updated weights for policy 1, policy_version 241830 (0.0011) -[2023-11-28 06:33:04,511][87424] Updated weights for policy 0, policy_version 242117 (0.0013) -[2023-11-28 06:33:04,781][87426] Updated weights for policy 1, policy_version 241840 (0.0007) -[2023-11-28 06:33:04,900][87424] Updated weights for policy 0, policy_version 242127 (0.0008) -[2023-11-28 06:33:05,153][87426] Updated weights for policy 1, policy_version 241850 (0.0010) -[2023-11-28 06:33:05,279][87424] Updated weights for policy 0, policy_version 242137 (0.0011) -[2023-11-28 06:33:07,030][87426] Updated weights for policy 1, policy_version 241860 (0.0011) -[2023-11-28 06:33:07,402][87426] Updated weights for policy 1, policy_version 241870 (0.0012) -[2023-11-28 06:33:07,408][87424] Updated weights for policy 0, policy_version 242147 (0.0011) -[2023-11-28 06:33:07,780][87426] Updated weights for policy 1, policy_version 241880 (0.0012) -[2023-11-28 06:33:07,793][87424] Updated weights for policy 0, policy_version 242157 (0.0008) -[2023-11-28 06:33:08,174][87424] Updated weights for policy 0, policy_version 242167 (0.0011) -[2023-11-28 06:33:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 123912192. Throughput: 0: 2729.7, 1: 2769.7. Samples: 123929648. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:08,445][86177] Avg episode reward: [(0, '-493.980'), (1, '-514.730')] -[2023-11-28 06:33:09,830][87426] Updated weights for policy 1, policy_version 241890 (0.0011) -[2023-11-28 06:33:10,200][87426] Updated weights for policy 1, policy_version 241900 (0.0011) -[2023-11-28 06:33:10,505][87424] Updated weights for policy 0, policy_version 242177 (0.0012) -[2023-11-28 06:33:10,576][87426] Updated weights for policy 1, policy_version 241910 (0.0010) -[2023-11-28 06:33:10,886][87424] Updated weights for policy 0, policy_version 242187 (0.0008) -[2023-11-28 06:33:10,950][87426] Updated weights for policy 1, policy_version 241920 (0.0011) -[2023-11-28 06:33:11,271][87424] Updated weights for policy 0, policy_version 242197 (0.0012) -[2023-11-28 06:33:11,646][87424] Updated weights for policy 0, policy_version 242207 (0.0010) -[2023-11-28 06:33:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 123936768. Throughput: 0: 2716.4, 1: 2781.1. Samples: 123953656. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:13,445][86177] Avg episode reward: [(0, '-493.310'), (1, '-518.070')] -[2023-11-28 06:33:13,447][87426] Updated weights for policy 1, policy_version 241930 (0.0012) -[2023-11-28 06:33:13,811][87424] Updated weights for policy 0, policy_version 242217 (0.0012) -[2023-11-28 06:33:13,825][87426] Updated weights for policy 1, policy_version 241940 (0.0012) -[2023-11-28 06:33:14,187][87424] Updated weights for policy 0, policy_version 242227 (0.0012) -[2023-11-28 06:33:14,195][87426] Updated weights for policy 1, policy_version 241950 (0.0010) -[2023-11-28 06:33:14,564][87424] Updated weights for policy 0, policy_version 242237 (0.0008) -[2023-11-28 06:33:16,106][87426] Updated weights for policy 1, policy_version 241960 (0.0010) -[2023-11-28 06:33:16,486][87426] Updated weights for policy 1, policy_version 241970 (0.0007) -[2023-11-28 06:33:16,739][87424] Updated weights for policy 0, policy_version 242247 (0.0009) -[2023-11-28 06:33:16,873][87426] Updated weights for policy 1, policy_version 241980 (0.0007) -[2023-11-28 06:33:17,122][87424] Updated weights for policy 0, policy_version 242257 (0.0011) -[2023-11-28 06:33:17,513][87424] Updated weights for policy 0, policy_version 242267 (0.0012) -[2023-11-28 06:33:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 123969536. Throughput: 0: 2705.3, 1: 2781.2. Samples: 123977160. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:18,445][86177] Avg episode reward: [(0, '-494.560'), (1, '-519.840')] -[2023-11-28 06:33:19,063][87426] Updated weights for policy 1, policy_version 241990 (0.0008) -[2023-11-28 06:33:19,433][87426] Updated weights for policy 1, policy_version 242000 (0.0007) -[2023-11-28 06:33:19,810][87426] Updated weights for policy 1, policy_version 242010 (0.0008) -[2023-11-28 06:33:20,108][87424] Updated weights for policy 0, policy_version 242277 (0.0012) -[2023-11-28 06:33:20,480][87424] Updated weights for policy 0, policy_version 242287 (0.0009) -[2023-11-28 06:33:20,864][87424] Updated weights for policy 0, policy_version 242297 (0.0010) -[2023-11-28 06:33:22,182][87426] Updated weights for policy 1, policy_version 242020 (0.0011) -[2023-11-28 06:33:22,561][87426] Updated weights for policy 1, policy_version 242030 (0.0008) -[2023-11-28 06:33:22,918][87424] Updated weights for policy 0, policy_version 242307 (0.0011) -[2023-11-28 06:33:22,943][87426] Updated weights for policy 1, policy_version 242040 (0.0009) -[2023-11-28 06:33:23,290][87424] Updated weights for policy 0, policy_version 242317 (0.0011) -[2023-11-28 06:33:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 123994112. Throughput: 0: 2691.2, 1: 2768.3. Samples: 124009704. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:23,445][86177] Avg episode reward: [(0, '-495.920'), (1, '-518.600')] -[2023-11-28 06:33:23,666][87424] Updated weights for policy 0, policy_version 242327 (0.0012) -[2023-11-28 06:33:25,254][87426] Updated weights for policy 1, policy_version 242050 (0.0011) -[2023-11-28 06:33:25,522][87424] Updated weights for policy 0, policy_version 242337 (0.0012) -[2023-11-28 06:33:25,641][87426] Updated weights for policy 1, policy_version 242060 (0.0007) -[2023-11-28 06:33:25,921][87424] Updated weights for policy 0, policy_version 242347 (0.0011) -[2023-11-28 06:33:26,027][87426] Updated weights for policy 1, policy_version 242070 (0.0008) -[2023-11-28 06:33:26,299][87424] Updated weights for policy 0, policy_version 242357 (0.0012) -[2023-11-28 06:33:26,409][87426] Updated weights for policy 1, policy_version 242080 (0.0007) -[2023-11-28 06:33:26,675][87424] Updated weights for policy 0, policy_version 242367 (0.0012) -[2023-11-28 06:33:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124018688. Throughput: 0: 2673.2, 1: 2799.4. Samples: 124035200. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:28,445][86177] Avg episode reward: [(0, '-493.880'), (1, '-525.860')] -[2023-11-28 06:33:28,480][87426] Updated weights for policy 1, policy_version 242090 (0.0008) -[2023-11-28 06:33:28,861][87426] Updated weights for policy 1, policy_version 242100 (0.0008) -[2023-11-28 06:33:29,076][87424] Updated weights for policy 0, policy_version 242377 (0.0009) -[2023-11-28 06:33:29,239][87426] Updated weights for policy 1, policy_version 242110 (0.0011) -[2023-11-28 06:33:29,462][87424] Updated weights for policy 0, policy_version 242387 (0.0008) -[2023-11-28 06:33:29,851][87424] Updated weights for policy 0, policy_version 242397 (0.0012) -[2023-11-28 06:33:31,058][87426] Updated weights for policy 1, policy_version 242120 (0.0008) -[2023-11-28 06:33:31,435][87426] Updated weights for policy 1, policy_version 242130 (0.0007) -[2023-11-28 06:33:31,810][87426] Updated weights for policy 1, policy_version 242140 (0.0009) -[2023-11-28 06:33:32,239][87424] Updated weights for policy 0, policy_version 242407 (0.0009) -[2023-11-28 06:33:32,620][87424] Updated weights for policy 0, policy_version 242417 (0.0008) -[2023-11-28 06:33:33,006][87424] Updated weights for policy 0, policy_version 242427 (0.0008) -[2023-11-28 06:33:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 124051456. Throughput: 0: 2669.4, 1: 2811.0. Samples: 124059836. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:33,445][86177] Avg episode reward: [(0, '-494.490'), (1, '-530.860')] -[2023-11-28 06:33:34,197][87426] Updated weights for policy 1, policy_version 242150 (0.0009) -[2023-11-28 06:33:34,573][87426] Updated weights for policy 1, policy_version 242160 (0.0007) -[2023-11-28 06:33:34,946][87426] Updated weights for policy 1, policy_version 242170 (0.0011) -[2023-11-28 06:33:35,161][87424] Updated weights for policy 0, policy_version 242437 (0.0009) -[2023-11-28 06:33:35,541][87424] Updated weights for policy 0, policy_version 242447 (0.0012) -[2023-11-28 06:33:35,915][87424] Updated weights for policy 0, policy_version 242457 (0.0008) -[2023-11-28 06:33:36,862][87426] Updated weights for policy 1, policy_version 242180 (0.0011) -[2023-11-28 06:33:37,245][87426] Updated weights for policy 1, policy_version 242190 (0.0012) -[2023-11-28 06:33:37,619][87426] Updated weights for policy 1, policy_version 242200 (0.0012) -[2023-11-28 06:33:37,878][87424] Updated weights for policy 0, policy_version 242467 (0.0009) -[2023-11-28 06:33:38,264][87424] Updated weights for policy 0, policy_version 242477 (0.0011) -[2023-11-28 06:33:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124076032. Throughput: 0: 2701.9, 1: 2812.1. Samples: 124094664. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:38,445][86177] Avg episode reward: [(0, '-500.780'), (1, '-564.130')] -[2023-11-28 06:33:38,648][87424] Updated weights for policy 0, policy_version 242487 (0.0008) -[2023-11-28 06:33:40,133][87426] Updated weights for policy 1, policy_version 242210 (0.0010) -[2023-11-28 06:33:40,516][87426] Updated weights for policy 1, policy_version 242220 (0.0009) -[2023-11-28 06:33:40,896][87426] Updated weights for policy 1, policy_version 242230 (0.0010) -[2023-11-28 06:33:40,928][87424] Updated weights for policy 0, policy_version 242497 (0.0009) -[2023-11-28 06:33:41,270][87426] Updated weights for policy 1, policy_version 242240 (0.0008) -[2023-11-28 06:33:41,303][87424] Updated weights for policy 0, policy_version 242507 (0.0008) -[2023-11-28 06:33:41,686][87424] Updated weights for policy 0, policy_version 242517 (0.0008) -[2023-11-28 06:33:42,085][87424] Updated weights for policy 0, policy_version 242527 (0.0010) -[2023-11-28 06:33:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124100608. Throughput: 0: 2708.0, 1: 2796.5. Samples: 124118492. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:43,445][86177] Avg episode reward: [(0, '-505.490'), (1, '-571.100')] -[2023-11-28 06:33:43,531][87426] Updated weights for policy 1, policy_version 242250 (0.0011) -[2023-11-28 06:33:43,916][87426] Updated weights for policy 1, policy_version 242260 (0.0010) -[2023-11-28 06:33:44,303][87426] Updated weights for policy 1, policy_version 242270 (0.0008) -[2023-11-28 06:33:44,474][87424] Updated weights for policy 0, policy_version 242537 (0.0010) -[2023-11-28 06:33:44,855][87424] Updated weights for policy 0, policy_version 242547 (0.0009) -[2023-11-28 06:33:45,246][87424] Updated weights for policy 0, policy_version 242557 (0.0010) -[2023-11-28 06:33:46,290][87426] Updated weights for policy 1, policy_version 242280 (0.0009) -[2023-11-28 06:33:46,677][87426] Updated weights for policy 1, policy_version 242290 (0.0011) -[2023-11-28 06:33:47,062][87426] Updated weights for policy 1, policy_version 242300 (0.0007) -[2023-11-28 06:33:47,399][87424] Updated weights for policy 0, policy_version 242567 (0.0011) -[2023-11-28 06:33:47,794][87424] Updated weights for policy 0, policy_version 242577 (0.0012) -[2023-11-28 06:33:48,189][87424] Updated weights for policy 0, policy_version 242587 (0.0011) -[2023-11-28 06:33:48,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 124133376. Throughput: 0: 2697.3, 1: 2779.4. Samples: 124141916. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:48,446][86177] Avg episode reward: [(0, '-519.590'), (1, '-562.800')] -[2023-11-28 06:33:49,342][87426] Updated weights for policy 1, policy_version 242310 (0.0010) -[2023-11-28 06:33:49,725][87426] Updated weights for policy 1, policy_version 242320 (0.0012) -[2023-11-28 06:33:50,123][87426] Updated weights for policy 1, policy_version 242330 (0.0009) -[2023-11-28 06:33:50,380][87424] Updated weights for policy 0, policy_version 242597 (0.0011) -[2023-11-28 06:33:50,764][87424] Updated weights for policy 0, policy_version 242607 (0.0011) -[2023-11-28 06:33:51,142][87424] Updated weights for policy 0, policy_version 242617 (0.0011) -[2023-11-28 06:33:52,551][87426] Updated weights for policy 1, policy_version 242340 (0.0009) -[2023-11-28 06:33:52,934][87426] Updated weights for policy 1, policy_version 242350 (0.0011) -[2023-11-28 06:33:53,314][87426] Updated weights for policy 1, policy_version 242360 (0.0010) -[2023-11-28 06:33:53,336][87424] Updated weights for policy 0, policy_version 242627 (0.0012) -[2023-11-28 06:33:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 124149760. Throughput: 0: 2686.1, 1: 2745.7. Samples: 124174080. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:53,445][86177] Avg episode reward: [(0, '-517.780'), (1, '-629.270')] -[2023-11-28 06:33:53,724][87424] Updated weights for policy 0, policy_version 242637 (0.0012) -[2023-11-28 06:33:54,106][87424] Updated weights for policy 0, policy_version 242647 (0.0011) -[2023-11-28 06:33:55,393][87426] Updated weights for policy 1, policy_version 242370 (0.0011) -[2023-11-28 06:33:55,770][87426] Updated weights for policy 1, policy_version 242380 (0.0008) -[2023-11-28 06:33:56,150][87426] Updated weights for policy 1, policy_version 242390 (0.0008) -[2023-11-28 06:33:56,262][87424] Updated weights for policy 0, policy_version 242657 (0.0012) -[2023-11-28 06:33:56,529][87426] Updated weights for policy 1, policy_version 242400 (0.0009) -[2023-11-28 06:33:56,639][87424] Updated weights for policy 0, policy_version 242667 (0.0008) -[2023-11-28 06:33:57,016][87424] Updated weights for policy 0, policy_version 242677 (0.0007) -[2023-11-28 06:33:57,403][87424] Updated weights for policy 0, policy_version 242687 (0.0007) -[2023-11-28 06:33:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124182528. Throughput: 0: 2691.4, 1: 2736.6. Samples: 124197916. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:33:58,445][86177] Avg episode reward: [(0, '-516.120'), (1, '-589.830')] -[2023-11-28 06:33:58,673][87426] Updated weights for policy 1, policy_version 242410 (0.0009) -[2023-11-28 06:33:59,054][87426] Updated weights for policy 1, policy_version 242420 (0.0010) -[2023-11-28 06:33:59,430][87426] Updated weights for policy 1, policy_version 242430 (0.0012) -[2023-11-28 06:33:59,503][87424] Updated weights for policy 0, policy_version 242697 (0.0008) -[2023-11-28 06:33:59,893][87424] Updated weights for policy 0, policy_version 242707 (0.0008) -[2023-11-28 06:34:00,280][87424] Updated weights for policy 0, policy_version 242717 (0.0008) -[2023-11-28 06:34:01,338][87426] Updated weights for policy 1, policy_version 242440 (0.0012) -[2023-11-28 06:34:01,719][87426] Updated weights for policy 1, policy_version 242450 (0.0012) -[2023-11-28 06:34:02,097][87426] Updated weights for policy 1, policy_version 242460 (0.0012) -[2023-11-28 06:34:02,236][87424] Updated weights for policy 0, policy_version 242727 (0.0010) -[2023-11-28 06:34:02,636][87424] Updated weights for policy 0, policy_version 242737 (0.0008) -[2023-11-28 06:34:03,008][87424] Updated weights for policy 0, policy_version 242747 (0.0010) -[2023-11-28 06:34:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124215296. Throughput: 0: 2708.9, 1: 2741.5. Samples: 124222428. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:34:03,445][86177] Avg episode reward: [(0, '-499.210'), (1, '-585.440')] -[2023-11-28 06:34:04,405][87426] Updated weights for policy 1, policy_version 242470 (0.0012) -[2023-11-28 06:34:04,740][87424] Updated weights for policy 0, policy_version 242757 (0.0009) -[2023-11-28 06:34:04,784][87426] Updated weights for policy 1, policy_version 242480 (0.0008) -[2023-11-28 06:34:05,120][87424] Updated weights for policy 0, policy_version 242767 (0.0011) -[2023-11-28 06:34:05,160][87426] Updated weights for policy 1, policy_version 242490 (0.0010) -[2023-11-28 06:34:05,501][87424] Updated weights for policy 0, policy_version 242777 (0.0012) -[2023-11-28 06:34:07,532][87424] Updated weights for policy 0, policy_version 242787 (0.0012) -[2023-11-28 06:34:07,661][87426] Updated weights for policy 1, policy_version 242500 (0.0009) -[2023-11-28 06:34:07,903][87424] Updated weights for policy 0, policy_version 242797 (0.0008) -[2023-11-28 06:34:08,030][87426] Updated weights for policy 1, policy_version 242510 (0.0009) -[2023-11-28 06:34:08,292][87424] Updated weights for policy 0, policy_version 242807 (0.0009) -[2023-11-28 06:34:08,411][87426] Updated weights for policy 1, policy_version 242520 (0.0011) -[2023-11-28 06:34:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 124231680. Throughput: 0: 2737.9, 1: 2742.1. Samples: 124256304. Policy #0 lag: (min: 31.0, avg: 40.1, max: 63.0) -[2023-11-28 06:34:08,445][86177] Avg episode reward: [(0, '-497.660'), (1, '-588.380')] -[2023-11-28 06:34:10,239][87424] Updated weights for policy 0, policy_version 242817 (0.0012) -[2023-11-28 06:34:10,249][87426] Updated weights for policy 1, policy_version 242530 (0.0011) -[2023-11-28 06:34:10,628][87426] Updated weights for policy 1, policy_version 242540 (0.0010) -[2023-11-28 06:34:10,630][87424] Updated weights for policy 0, policy_version 242827 (0.0011) -[2023-11-28 06:34:10,999][87426] Updated weights for policy 1, policy_version 242550 (0.0011) -[2023-11-28 06:34:11,006][87424] Updated weights for policy 0, policy_version 242837 (0.0011) -[2023-11-28 06:34:11,376][87426] Updated weights for policy 1, policy_version 242560 (0.0012) -[2023-11-28 06:34:11,385][87424] Updated weights for policy 0, policy_version 242847 (0.0011) -[2023-11-28 06:34:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124264448. Throughput: 0: 2736.6, 1: 2725.8. Samples: 124281008. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:13,445][86177] Avg episode reward: [(0, '-502.530'), (1, '-521.850')] -[2023-11-28 06:34:13,627][87426] Updated weights for policy 1, policy_version 242570 (0.0011) -[2023-11-28 06:34:13,992][87424] Updated weights for policy 0, policy_version 242857 (0.0009) -[2023-11-28 06:34:14,008][87426] Updated weights for policy 1, policy_version 242580 (0.0010) -[2023-11-28 06:34:14,371][87424] Updated weights for policy 0, policy_version 242867 (0.0007) -[2023-11-28 06:34:14,387][87426] Updated weights for policy 1, policy_version 242590 (0.0007) -[2023-11-28 06:34:14,766][87424] Updated weights for policy 0, policy_version 242877 (0.0008) -[2023-11-28 06:34:16,781][87426] Updated weights for policy 1, policy_version 242600 (0.0011) -[2023-11-28 06:34:17,157][87424] Updated weights for policy 0, policy_version 242887 (0.0009) -[2023-11-28 06:34:17,168][87426] Updated weights for policy 1, policy_version 242610 (0.0010) -[2023-11-28 06:34:17,538][87424] Updated weights for policy 0, policy_version 242897 (0.0010) -[2023-11-28 06:34:17,541][87426] Updated weights for policy 1, policy_version 242620 (0.0008) -[2023-11-28 06:34:17,913][87424] Updated weights for policy 0, policy_version 242907 (0.0011) -[2023-11-28 06:34:18,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 124297216. Throughput: 0: 2732.7, 1: 2697.5. Samples: 124304196. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:18,445][86177] Avg episode reward: [(0, '-506.860'), (1, '-519.360')] -[2023-11-28 06:34:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000242912_62185472.pth... -[2023-11-28 06:34:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000242624_62111744.pth... -[2023-11-28 06:34:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000240384_61538304.pth -[2023-11-28 06:34:18,502][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000240096_61464576.pth -[2023-11-28 06:34:19,794][87424] Updated weights for policy 0, policy_version 242917 (0.0027) -[2023-11-28 06:34:20,057][87426] Updated weights for policy 1, policy_version 242630 (0.0010) -[2023-11-28 06:34:20,149][87424] Updated weights for policy 0, policy_version 242927 (0.0011) -[2023-11-28 06:34:20,433][87426] Updated weights for policy 1, policy_version 242640 (0.0008) -[2023-11-28 06:34:20,535][87424] Updated weights for policy 0, policy_version 242937 (0.0012) -[2023-11-28 06:34:20,815][87426] Updated weights for policy 1, policy_version 242650 (0.0008) -[2023-11-28 06:34:22,668][87424] Updated weights for policy 0, policy_version 242947 (0.0011) -[2023-11-28 06:34:23,048][87424] Updated weights for policy 0, policy_version 242957 (0.0011) -[2023-11-28 06:34:23,051][87426] Updated weights for policy 1, policy_version 242660 (0.0010) -[2023-11-28 06:34:23,425][87426] Updated weights for policy 1, policy_version 242670 (0.0010) -[2023-11-28 06:34:23,435][87424] Updated weights for policy 0, policy_version 242967 (0.0010) -[2023-11-28 06:34:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 124313600. Throughput: 0: 2712.9, 1: 2667.6. Samples: 124336788. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:23,445][86177] Avg episode reward: [(0, '-505.440'), (1, '-504.140')] -[2023-11-28 06:34:23,794][87426] Updated weights for policy 1, policy_version 242680 (0.0007) -[2023-11-28 06:34:25,573][87424] Updated weights for policy 0, policy_version 242977 (0.0011) -[2023-11-28 06:34:25,954][87424] Updated weights for policy 0, policy_version 242987 (0.0012) -[2023-11-28 06:34:26,333][87424] Updated weights for policy 0, policy_version 242997 (0.0012) -[2023-11-28 06:34:26,373][87426] Updated weights for policy 1, policy_version 242690 (0.0008) -[2023-11-28 06:34:26,711][87424] Updated weights for policy 0, policy_version 243007 (0.0012) -[2023-11-28 06:34:26,743][87426] Updated weights for policy 1, policy_version 242700 (0.0011) -[2023-11-28 06:34:27,127][87426] Updated weights for policy 1, policy_version 242710 (0.0009) -[2023-11-28 06:34:27,510][87426] Updated weights for policy 1, policy_version 242720 (0.0007) -[2023-11-28 06:34:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 124346368. Throughput: 0: 2721.2, 1: 2662.9. Samples: 124360776. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:28,445][86177] Avg episode reward: [(0, '-502.760'), (1, '-504.630')] -[2023-11-28 06:34:29,033][87424] Updated weights for policy 0, policy_version 243017 (0.0011) -[2023-11-28 06:34:29,381][87426] Updated weights for policy 1, policy_version 242730 (0.0011) -[2023-11-28 06:34:29,416][87424] Updated weights for policy 0, policy_version 243027 (0.0007) -[2023-11-28 06:34:29,766][87426] Updated weights for policy 1, policy_version 242740 (0.0007) -[2023-11-28 06:34:29,805][87424] Updated weights for policy 0, policy_version 243037 (0.0008) -[2023-11-28 06:34:30,151][87426] Updated weights for policy 1, policy_version 242750 (0.0009) -[2023-11-28 06:34:32,109][87424] Updated weights for policy 0, policy_version 243047 (0.0010) -[2023-11-28 06:34:32,461][87426] Updated weights for policy 1, policy_version 242760 (0.0011) -[2023-11-28 06:34:32,490][87424] Updated weights for policy 0, policy_version 243057 (0.0010) -[2023-11-28 06:34:32,837][87426] Updated weights for policy 1, policy_version 242770 (0.0011) -[2023-11-28 06:34:32,872][87424] Updated weights for policy 0, policy_version 243067 (0.0010) -[2023-11-28 06:34:33,221][87426] Updated weights for policy 1, policy_version 242780 (0.0008) -[2023-11-28 06:34:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 124379136. Throughput: 0: 2746.1, 1: 2653.9. Samples: 124384916. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:33,445][86177] Avg episode reward: [(0, '-492.530'), (1, '-503.460')] -[2023-11-28 06:34:35,189][87424] Updated weights for policy 0, policy_version 243077 (0.0010) -[2023-11-28 06:34:35,579][87424] Updated weights for policy 0, policy_version 243087 (0.0012) -[2023-11-28 06:34:35,689][87426] Updated weights for policy 1, policy_version 242790 (0.0008) -[2023-11-28 06:34:35,962][87424] Updated weights for policy 0, policy_version 243097 (0.0012) -[2023-11-28 06:34:36,069][87426] Updated weights for policy 1, policy_version 242800 (0.0007) -[2023-11-28 06:34:36,446][87426] Updated weights for policy 1, policy_version 242810 (0.0007) -[2023-11-28 06:34:37,617][87424] Updated weights for policy 0, policy_version 243107 (0.0010) -[2023-11-28 06:34:37,992][87424] Updated weights for policy 0, policy_version 243117 (0.0008) -[2023-11-28 06:34:38,374][87424] Updated weights for policy 0, policy_version 243127 (0.0007) -[2023-11-28 06:34:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 124395520. Throughput: 0: 2742.2, 1: 2650.2. Samples: 124416740. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:38,445][86177] Avg episode reward: [(0, '-493.400'), (1, '-509.160')] -[2023-11-28 06:34:38,946][87426] Updated weights for policy 1, policy_version 242820 (0.0009) -[2023-11-28 06:34:39,319][87426] Updated weights for policy 1, policy_version 242830 (0.0011) -[2023-11-28 06:34:39,698][87426] Updated weights for policy 1, policy_version 242840 (0.0012) -[2023-11-28 06:34:40,508][87424] Updated weights for policy 0, policy_version 243137 (0.0008) -[2023-11-28 06:34:40,892][87424] Updated weights for policy 0, policy_version 243147 (0.0008) -[2023-11-28 06:34:41,274][87424] Updated weights for policy 0, policy_version 243157 (0.0008) -[2023-11-28 06:34:41,661][87424] Updated weights for policy 0, policy_version 243167 (0.0009) -[2023-11-28 06:34:42,214][87426] Updated weights for policy 1, policy_version 242850 (0.0012) -[2023-11-28 06:34:42,591][87426] Updated weights for policy 1, policy_version 242860 (0.0011) -[2023-11-28 06:34:42,974][87426] Updated weights for policy 1, policy_version 242870 (0.0011) -[2023-11-28 06:34:43,350][87426] Updated weights for policy 1, policy_version 242880 (0.0012) -[2023-11-28 06:34:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124428288. Throughput: 0: 2745.1, 1: 2643.2. Samples: 124440388. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:43,445][86177] Avg episode reward: [(0, '-493.180'), (1, '-511.730')] -[2023-11-28 06:34:44,191][87424] Updated weights for policy 0, policy_version 243177 (0.0008) -[2023-11-28 06:34:44,573][87424] Updated weights for policy 0, policy_version 243187 (0.0008) -[2023-11-28 06:34:44,960][87424] Updated weights for policy 0, policy_version 243197 (0.0008) -[2023-11-28 06:34:45,083][87426] Updated weights for policy 1, policy_version 242890 (0.0008) -[2023-11-28 06:34:45,461][87426] Updated weights for policy 1, policy_version 242900 (0.0008) -[2023-11-28 06:34:45,850][87426] Updated weights for policy 1, policy_version 242910 (0.0010) -[2023-11-28 06:34:47,296][87424] Updated weights for policy 0, policy_version 243207 (0.0008) -[2023-11-28 06:34:47,682][87424] Updated weights for policy 0, policy_version 243217 (0.0007) -[2023-11-28 06:34:48,073][87424] Updated weights for policy 0, policy_version 243227 (0.0010) -[2023-11-28 06:34:48,096][87426] Updated weights for policy 1, policy_version 242920 (0.0010) -[2023-11-28 06:34:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 124452864. Throughput: 0: 2730.1, 1: 2661.9. Samples: 124465068. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:48,445][86177] Avg episode reward: [(0, '-492.200'), (1, '-514.830')] -[2023-11-28 06:34:48,469][87426] Updated weights for policy 1, policy_version 242930 (0.0012) -[2023-11-28 06:34:48,851][87426] Updated weights for policy 1, policy_version 242940 (0.0011) -[2023-11-28 06:34:50,460][87424] Updated weights for policy 0, policy_version 243237 (0.0011) -[2023-11-28 06:34:50,842][87424] Updated weights for policy 0, policy_version 243247 (0.0008) -[2023-11-28 06:34:50,957][87426] Updated weights for policy 1, policy_version 242950 (0.0011) -[2023-11-28 06:34:51,223][87424] Updated weights for policy 0, policy_version 243257 (0.0011) -[2023-11-28 06:34:51,328][87426] Updated weights for policy 1, policy_version 242960 (0.0012) -[2023-11-28 06:34:51,711][87426] Updated weights for policy 1, policy_version 242970 (0.0012) -[2023-11-28 06:34:53,150][87424] Updated weights for policy 0, policy_version 243267 (0.0011) -[2023-11-28 06:34:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124477440. Throughput: 0: 2711.8, 1: 2642.4. Samples: 124497244. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:53,445][86177] Avg episode reward: [(0, '-491.500'), (1, '-512.320')] -[2023-11-28 06:34:53,523][87424] Updated weights for policy 0, policy_version 243277 (0.0012) -[2023-11-28 06:34:53,909][87424] Updated weights for policy 0, policy_version 243287 (0.0012) -[2023-11-28 06:34:54,320][87426] Updated weights for policy 1, policy_version 242980 (0.0010) -[2023-11-28 06:34:54,702][87426] Updated weights for policy 1, policy_version 242990 (0.0008) -[2023-11-28 06:34:55,087][87426] Updated weights for policy 1, policy_version 243000 (0.0008) -[2023-11-28 06:34:56,022][87424] Updated weights for policy 0, policy_version 243297 (0.0012) -[2023-11-28 06:34:56,410][87424] Updated weights for policy 0, policy_version 243307 (0.0012) -[2023-11-28 06:34:56,708][87426] Updated weights for policy 1, policy_version 243010 (0.0008) -[2023-11-28 06:34:56,793][87424] Updated weights for policy 0, policy_version 243317 (0.0010) -[2023-11-28 06:34:57,077][87426] Updated weights for policy 1, policy_version 243020 (0.0010) -[2023-11-28 06:34:57,170][87424] Updated weights for policy 0, policy_version 243327 (0.0008) -[2023-11-28 06:34:57,456][87426] Updated weights for policy 1, policy_version 243030 (0.0008) -[2023-11-28 06:34:57,840][87426] Updated weights for policy 1, policy_version 243040 (0.0007) -[2023-11-28 06:34:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124510208. Throughput: 0: 2695.6, 1: 2648.1. Samples: 124521476. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:34:58,445][86177] Avg episode reward: [(0, '-490.250'), (1, '-517.830')] -[2023-11-28 06:34:59,641][87424] Updated weights for policy 0, policy_version 243337 (0.0011) -[2023-11-28 06:34:59,684][87426] Updated weights for policy 1, policy_version 243050 (0.0009) -[2023-11-28 06:35:00,031][87424] Updated weights for policy 0, policy_version 243347 (0.0011) -[2023-11-28 06:35:00,060][87426] Updated weights for policy 1, policy_version 243060 (0.0011) -[2023-11-28 06:35:00,402][87424] Updated weights for policy 0, policy_version 243357 (0.0010) -[2023-11-28 06:35:00,442][87426] Updated weights for policy 1, policy_version 243070 (0.0007) -[2023-11-28 06:35:02,574][87426] Updated weights for policy 1, policy_version 243080 (0.0011) -[2023-11-28 06:35:02,900][87424] Updated weights for policy 0, policy_version 243367 (0.0009) -[2023-11-28 06:35:02,951][87426] Updated weights for policy 1, policy_version 243090 (0.0011) -[2023-11-28 06:35:03,284][87424] Updated weights for policy 0, policy_version 243377 (0.0008) -[2023-11-28 06:35:03,340][87426] Updated weights for policy 1, policy_version 243100 (0.0011) -[2023-11-28 06:35:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 124526592. Throughput: 0: 2701.9, 1: 2677.5. Samples: 124546268. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:35:03,445][86177] Avg episode reward: [(0, '-492.660'), (1, '-518.490')] -[2023-11-28 06:35:03,668][87424] Updated weights for policy 0, policy_version 243387 (0.0011) -[2023-11-28 06:35:05,848][87426] Updated weights for policy 1, policy_version 243110 (0.0012) -[2023-11-28 06:35:06,212][87424] Updated weights for policy 0, policy_version 243397 (0.0009) -[2023-11-28 06:35:06,227][87426] Updated weights for policy 1, policy_version 243120 (0.0012) -[2023-11-28 06:35:06,594][87424] Updated weights for policy 0, policy_version 243407 (0.0007) -[2023-11-28 06:35:06,598][87426] Updated weights for policy 1, policy_version 243130 (0.0010) -[2023-11-28 06:35:06,973][87424] Updated weights for policy 0, policy_version 243417 (0.0008) -[2023-11-28 06:35:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124559360. Throughput: 0: 2677.7, 1: 2699.0. Samples: 124578740. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:35:08,445][86177] Avg episode reward: [(0, '-509.360'), (1, '-514.490')] -[2023-11-28 06:35:08,680][87424] Updated weights for policy 0, policy_version 243427 (0.0009) -[2023-11-28 06:35:09,050][87426] Updated weights for policy 1, policy_version 243140 (0.0010) -[2023-11-28 06:35:09,063][87424] Updated weights for policy 0, policy_version 243437 (0.0008) -[2023-11-28 06:35:09,433][87426] Updated weights for policy 1, policy_version 243150 (0.0008) -[2023-11-28 06:35:09,443][87424] Updated weights for policy 0, policy_version 243447 (0.0010) -[2023-11-28 06:35:09,810][87426] Updated weights for policy 1, policy_version 243160 (0.0010) -[2023-11-28 06:35:11,786][87424] Updated weights for policy 0, policy_version 243457 (0.0012) -[2023-11-28 06:35:12,034][87426] Updated weights for policy 1, policy_version 243170 (0.0011) -[2023-11-28 06:35:12,163][87424] Updated weights for policy 0, policy_version 243467 (0.0011) -[2023-11-28 06:35:12,410][87426] Updated weights for policy 1, policy_version 243180 (0.0011) -[2023-11-28 06:35:12,548][87424] Updated weights for policy 0, policy_version 243477 (0.0011) -[2023-11-28 06:35:12,790][87426] Updated weights for policy 1, policy_version 243190 (0.0012) -[2023-11-28 06:35:12,927][87424] Updated weights for policy 0, policy_version 243487 (0.0011) -[2023-11-28 06:35:13,171][87426] Updated weights for policy 1, policy_version 243200 (0.0012) -[2023-11-28 06:35:13,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 124592128. Throughput: 0: 2674.0, 1: 2687.7. Samples: 124602056. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:35:13,446][86177] Avg episode reward: [(0, '-510.900'), (1, '-534.110')] -[2023-11-28 06:35:15,205][87426] Updated weights for policy 1, policy_version 243210 (0.0009) -[2023-11-28 06:35:15,256][87424] Updated weights for policy 0, policy_version 243497 (0.0011) -[2023-11-28 06:35:15,586][87426] Updated weights for policy 1, policy_version 243220 (0.0010) -[2023-11-28 06:35:15,634][87424] Updated weights for policy 0, policy_version 243507 (0.0011) -[2023-11-28 06:35:15,952][87426] Updated weights for policy 1, policy_version 243230 (0.0010) -[2023-11-28 06:35:16,011][87424] Updated weights for policy 0, policy_version 243517 (0.0011) -[2023-11-28 06:35:17,767][87424] Updated weights for policy 0, policy_version 243527 (0.0012) -[2023-11-28 06:35:17,988][87426] Updated weights for policy 1, policy_version 243240 (0.0009) -[2023-11-28 06:35:18,153][87424] Updated weights for policy 0, policy_version 243537 (0.0011) -[2023-11-28 06:35:18,366][87426] Updated weights for policy 1, policy_version 243250 (0.0008) -[2023-11-28 06:35:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 124608512. Throughput: 0: 2661.1, 1: 2704.6. Samples: 124626372. Policy #0 lag: (min: 10.0, avg: 26.6, max: 42.0) -[2023-11-28 06:35:18,445][86177] Avg episode reward: [(0, '-510.210'), (1, '-523.360')] -[2023-11-28 06:35:18,539][87424] Updated weights for policy 0, policy_version 243547 (0.0012) -[2023-11-28 06:35:18,743][87426] Updated weights for policy 1, policy_version 243260 (0.0008) -[2023-11-28 06:35:20,853][87426] Updated weights for policy 1, policy_version 243270 (0.0010) -[2023-11-28 06:35:20,972][87424] Updated weights for policy 0, policy_version 243557 (0.0011) -[2023-11-28 06:35:21,229][87426] Updated weights for policy 1, policy_version 243280 (0.0012) -[2023-11-28 06:35:21,360][87424] Updated weights for policy 0, policy_version 243567 (0.0011) -[2023-11-28 06:35:21,613][87426] Updated weights for policy 1, policy_version 243290 (0.0012) -[2023-11-28 06:35:21,737][87424] Updated weights for policy 0, policy_version 243577 (0.0009) -[2023-11-28 06:35:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124641280. Throughput: 0: 2669.2, 1: 2713.5. Samples: 124658960. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:35:23,445][86177] Avg episode reward: [(0, '-510.590'), (1, '-520.370')] -[2023-11-28 06:35:23,640][87424] Updated weights for policy 0, policy_version 243587 (0.0011) -[2023-11-28 06:35:23,775][87426] Updated weights for policy 1, policy_version 243300 (0.0012) -[2023-11-28 06:35:24,028][87424] Updated weights for policy 0, policy_version 243597 (0.0012) -[2023-11-28 06:35:24,154][87426] Updated weights for policy 1, policy_version 243310 (0.0011) -[2023-11-28 06:35:24,402][87424] Updated weights for policy 0, policy_version 243607 (0.0010) -[2023-11-28 06:35:24,535][87426] Updated weights for policy 1, policy_version 243320 (0.0013) -[2023-11-28 06:35:26,717][87426] Updated weights for policy 1, policy_version 243330 (0.0008) -[2023-11-28 06:35:26,757][87424] Updated weights for policy 0, policy_version 243617 (0.0008) -[2023-11-28 06:35:27,097][87426] Updated weights for policy 1, policy_version 243340 (0.0012) -[2023-11-28 06:35:27,131][87424] Updated weights for policy 0, policy_version 243627 (0.0009) -[2023-11-28 06:35:27,474][87426] Updated weights for policy 1, policy_version 243350 (0.0011) -[2023-11-28 06:35:27,520][87424] Updated weights for policy 0, policy_version 243637 (0.0010) -[2023-11-28 06:35:27,853][87426] Updated weights for policy 1, policy_version 243360 (0.0012) -[2023-11-28 06:35:27,897][87424] Updated weights for policy 0, policy_version 243647 (0.0011) -[2023-11-28 06:35:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124674048. Throughput: 0: 2664.5, 1: 2743.2. Samples: 124683736. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:35:28,445][86177] Avg episode reward: [(0, '-493.280'), (1, '-526.010')] -[2023-11-28 06:35:29,800][87426] Updated weights for policy 1, policy_version 243370 (0.0012) -[2023-11-28 06:35:30,172][87426] Updated weights for policy 1, policy_version 243380 (0.0011) -[2023-11-28 06:35:30,419][87424] Updated weights for policy 0, policy_version 243657 (0.0011) -[2023-11-28 06:35:30,553][87426] Updated weights for policy 1, policy_version 243390 (0.0010) -[2023-11-28 06:35:30,789][87424] Updated weights for policy 0, policy_version 243667 (0.0010) -[2023-11-28 06:35:31,170][87424] Updated weights for policy 0, policy_version 243677 (0.0007) -[2023-11-28 06:35:33,021][87426] Updated weights for policy 1, policy_version 243400 (0.0012) -[2023-11-28 06:35:33,408][87426] Updated weights for policy 1, policy_version 243410 (0.0012) -[2023-11-28 06:35:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 124690432. Throughput: 0: 2666.0, 1: 2743.6. Samples: 124708496. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:35:33,445][86177] Avg episode reward: [(0, '-496.460'), (1, '-521.580')] -[2023-11-28 06:35:33,706][87424] Updated weights for policy 0, policy_version 243687 (0.0008) -[2023-11-28 06:35:33,785][87426] Updated weights for policy 1, policy_version 243420 (0.0011) -[2023-11-28 06:35:34,092][87424] Updated weights for policy 0, policy_version 243697 (0.0007) -[2023-11-28 06:35:34,476][87424] Updated weights for policy 0, policy_version 243707 (0.0007) -[2023-11-28 06:35:35,679][87426] Updated weights for policy 1, policy_version 243430 (0.0010) -[2023-11-28 06:35:36,059][87426] Updated weights for policy 1, policy_version 243440 (0.0011) -[2023-11-28 06:35:36,440][87426] Updated weights for policy 1, policy_version 243450 (0.0012) -[2023-11-28 06:35:37,005][87424] Updated weights for policy 0, policy_version 243717 (0.0010) -[2023-11-28 06:35:37,378][87424] Updated weights for policy 0, policy_version 243727 (0.0012) -[2023-11-28 06:35:37,755][87424] Updated weights for policy 0, policy_version 243737 (0.0009) -[2023-11-28 06:35:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 124723200. Throughput: 0: 2641.9, 1: 2760.5. Samples: 124740352. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:35:38,445][86177] Avg episode reward: [(0, '-496.930'), (1, '-527.860')] -[2023-11-28 06:35:38,801][87426] Updated weights for policy 1, policy_version 243460 (0.0009) -[2023-11-28 06:35:39,179][87426] Updated weights for policy 1, policy_version 243470 (0.0008) -[2023-11-28 06:35:39,557][87426] Updated weights for policy 1, policy_version 243480 (0.0008) -[2023-11-28 06:35:39,816][87424] Updated weights for policy 0, policy_version 243747 (0.0008) -[2023-11-28 06:35:40,191][87424] Updated weights for policy 0, policy_version 243757 (0.0010) -[2023-11-28 06:35:40,573][87424] Updated weights for policy 0, policy_version 243767 (0.0013) -[2023-11-28 06:35:41,785][87426] Updated weights for policy 1, policy_version 243490 (0.0010) -[2023-11-28 06:35:42,167][87426] Updated weights for policy 1, policy_version 243500 (0.0012) -[2023-11-28 06:35:42,540][87426] Updated weights for policy 1, policy_version 243510 (0.0012) -[2023-11-28 06:35:42,916][87426] Updated weights for policy 1, policy_version 243520 (0.0009) -[2023-11-28 06:35:43,193][87424] Updated weights for policy 0, policy_version 243777 (0.0012) -[2023-11-28 06:35:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 124747776. Throughput: 0: 2644.1, 1: 2737.9. Samples: 124763664. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:35:43,446][86177] Avg episode reward: [(0, '-496.230'), (1, '-530.940')] -[2023-11-28 06:35:43,568][87424] Updated weights for policy 0, policy_version 243787 (0.0012) -[2023-11-28 06:35:43,970][87424] Updated weights for policy 0, policy_version 243797 (0.0012) -[2023-11-28 06:35:44,346][87424] Updated weights for policy 0, policy_version 243807 (0.0012) -[2023-11-28 06:35:45,186][87426] Updated weights for policy 1, policy_version 243530 (0.0012) -[2023-11-28 06:35:45,560][87426] Updated weights for policy 1, policy_version 243540 (0.0011) -[2023-11-28 06:35:45,936][87426] Updated weights for policy 1, policy_version 243550 (0.0009) -[2023-11-28 06:35:46,295][87424] Updated weights for policy 0, policy_version 243817 (0.0010) -[2023-11-28 06:35:46,674][87424] Updated weights for policy 0, policy_version 243827 (0.0010) -[2023-11-28 06:35:47,056][87424] Updated weights for policy 0, policy_version 243837 (0.0009) -[2023-11-28 06:35:48,292][87426] Updated weights for policy 1, policy_version 243560 (0.0012) -[2023-11-28 06:35:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 124772352. Throughput: 0: 2658.4, 1: 2730.1. Samples: 124788752. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:35:48,445][86177] Avg episode reward: [(0, '-498.200'), (1, '-531.850')] -[2023-11-28 06:35:48,675][87426] Updated weights for policy 1, policy_version 243570 (0.0010) -[2023-11-28 06:35:48,754][87424] Updated weights for policy 0, policy_version 243847 (0.0008) -[2023-11-28 06:35:49,056][87426] Updated weights for policy 1, policy_version 243580 (0.0010) -[2023-11-28 06:35:49,132][87424] Updated weights for policy 0, policy_version 243857 (0.0010) -[2023-11-28 06:35:49,510][87424] Updated weights for policy 0, policy_version 243867 (0.0011) -[2023-11-28 06:35:50,950][87426] Updated weights for policy 1, policy_version 243590 (0.0010) -[2023-11-28 06:35:51,320][87426] Updated weights for policy 1, policy_version 243600 (0.0009) -[2023-11-28 06:35:51,698][87426] Updated weights for policy 1, policy_version 243610 (0.0009) -[2023-11-28 06:35:52,034][87424] Updated weights for policy 0, policy_version 243877 (0.0010) -[2023-11-28 06:35:52,413][87424] Updated weights for policy 0, policy_version 243887 (0.0008) -[2023-11-28 06:35:52,802][87424] Updated weights for policy 0, policy_version 243897 (0.0010) -[2023-11-28 06:35:53,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 124805120. Throughput: 0: 2674.0, 1: 2715.1. Samples: 124821252. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:35:53,445][86177] Avg episode reward: [(0, '-497.050'), (1, '-532.630')] -[2023-11-28 06:35:53,615][87426] Updated weights for policy 1, policy_version 243620 (0.0011) -[2023-11-28 06:35:53,986][87426] Updated weights for policy 1, policy_version 243630 (0.0011) -[2023-11-28 06:35:54,367][87426] Updated weights for policy 1, policy_version 243640 (0.0012) -[2023-11-28 06:35:54,748][87424] Updated weights for policy 0, policy_version 243907 (0.0011) -[2023-11-28 06:35:55,149][87424] Updated weights for policy 0, policy_version 243917 (0.0012) -[2023-11-28 06:35:55,529][87424] Updated weights for policy 0, policy_version 243927 (0.0012) -[2023-11-28 06:35:56,398][87426] Updated weights for policy 1, policy_version 243650 (0.0012) -[2023-11-28 06:35:56,776][87426] Updated weights for policy 1, policy_version 243660 (0.0012) -[2023-11-28 06:35:57,152][87426] Updated weights for policy 1, policy_version 243670 (0.0012) -[2023-11-28 06:35:57,493][87424] Updated weights for policy 0, policy_version 243937 (0.0011) -[2023-11-28 06:35:57,538][87426] Updated weights for policy 1, policy_version 243680 (0.0011) -[2023-11-28 06:35:57,880][87424] Updated weights for policy 0, policy_version 243947 (0.0012) -[2023-11-28 06:35:58,262][87424] Updated weights for policy 0, policy_version 243957 (0.0012) -[2023-11-28 06:35:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 124829696. Throughput: 0: 2662.0, 1: 2753.2. Samples: 124845736. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:35:58,445][86177] Avg episode reward: [(0, '-495.000'), (1, '-549.000')] -[2023-11-28 06:35:58,650][87424] Updated weights for policy 0, policy_version 243967 (0.0012) -[2023-11-28 06:35:59,719][87426] Updated weights for policy 1, policy_version 243690 (0.0008) -[2023-11-28 06:36:00,099][87426] Updated weights for policy 1, policy_version 243700 (0.0008) -[2023-11-28 06:36:00,401][87424] Updated weights for policy 0, policy_version 243977 (0.0011) -[2023-11-28 06:36:00,480][87426] Updated weights for policy 1, policy_version 243710 (0.0009) -[2023-11-28 06:36:00,787][87424] Updated weights for policy 0, policy_version 243987 (0.0010) -[2023-11-28 06:36:01,161][87424] Updated weights for policy 0, policy_version 243997 (0.0007) -[2023-11-28 06:36:02,603][87426] Updated weights for policy 1, policy_version 243720 (0.0015) -[2023-11-28 06:36:02,986][87426] Updated weights for policy 1, policy_version 243730 (0.0010) -[2023-11-28 06:36:03,371][87426] Updated weights for policy 1, policy_version 243740 (0.0010) -[2023-11-28 06:36:03,444][86177] Fps is (10 sec: 4915.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 124854272. Throughput: 0: 2696.4, 1: 2750.5. Samples: 124871480. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:36:03,445][86177] Avg episode reward: [(0, '-495.400'), (1, '-560.110')] -[2023-11-28 06:36:03,531][87424] Updated weights for policy 0, policy_version 244007 (0.0010) -[2023-11-28 06:36:03,912][87424] Updated weights for policy 0, policy_version 244017 (0.0008) -[2023-11-28 06:36:04,291][87424] Updated weights for policy 0, policy_version 244027 (0.0008) -[2023-11-28 06:36:05,587][87426] Updated weights for policy 1, policy_version 243750 (0.0011) -[2023-11-28 06:36:05,966][87426] Updated weights for policy 1, policy_version 243760 (0.0011) -[2023-11-28 06:36:06,337][87426] Updated weights for policy 1, policy_version 243770 (0.0011) -[2023-11-28 06:36:06,501][87424] Updated weights for policy 0, policy_version 244037 (0.0011) -[2023-11-28 06:36:06,881][87424] Updated weights for policy 0, policy_version 244047 (0.0012) -[2023-11-28 06:36:07,276][87424] Updated weights for policy 0, policy_version 244057 (0.0012) -[2023-11-28 06:36:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124887040. Throughput: 0: 2706.2, 1: 2741.2. Samples: 124904096. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:36:08,445][86177] Avg episode reward: [(0, '-498.660'), (1, '-560.970')] -[2023-11-28 06:36:08,750][87426] Updated weights for policy 1, policy_version 243780 (0.0011) -[2023-11-28 06:36:09,050][87424] Updated weights for policy 0, policy_version 244067 (0.0011) -[2023-11-28 06:36:09,127][87426] Updated weights for policy 1, policy_version 243790 (0.0012) -[2023-11-28 06:36:09,429][87424] Updated weights for policy 0, policy_version 244077 (0.0011) -[2023-11-28 06:36:09,509][87426] Updated weights for policy 1, policy_version 243800 (0.0011) -[2023-11-28 06:36:09,815][87424] Updated weights for policy 0, policy_version 244087 (0.0012) -[2023-11-28 06:36:11,631][87424] Updated weights for policy 0, policy_version 244097 (0.0012) -[2023-11-28 06:36:11,827][87426] Updated weights for policy 1, policy_version 243810 (0.0012) -[2023-11-28 06:36:12,008][87424] Updated weights for policy 0, policy_version 244107 (0.0011) -[2023-11-28 06:36:12,203][87426] Updated weights for policy 1, policy_version 243820 (0.0011) -[2023-11-28 06:36:12,389][87424] Updated weights for policy 0, policy_version 244117 (0.0011) -[2023-11-28 06:36:12,580][87426] Updated weights for policy 1, policy_version 243830 (0.0011) -[2023-11-28 06:36:12,770][87424] Updated weights for policy 0, policy_version 244127 (0.0012) -[2023-11-28 06:36:12,975][87426] Updated weights for policy 1, policy_version 243840 (0.0011) -[2023-11-28 06:36:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 124919808. Throughput: 0: 2714.5, 1: 2721.8. Samples: 124928368. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:36:13,445][86177] Avg episode reward: [(0, '-499.530'), (1, '-542.480')] -[2023-11-28 06:36:14,764][87426] Updated weights for policy 1, policy_version 243850 (0.0009) -[2023-11-28 06:36:15,143][87426] Updated weights for policy 1, policy_version 243860 (0.0007) -[2023-11-28 06:36:15,202][87424] Updated weights for policy 0, policy_version 244137 (0.0009) -[2023-11-28 06:36:15,524][87426] Updated weights for policy 1, policy_version 243870 (0.0010) -[2023-11-28 06:36:15,580][87424] Updated weights for policy 0, policy_version 244147 (0.0011) -[2023-11-28 06:36:15,964][87424] Updated weights for policy 0, policy_version 244157 (0.0012) -[2023-11-28 06:36:17,378][87426] Updated weights for policy 1, policy_version 243880 (0.0010) -[2023-11-28 06:36:17,768][87426] Updated weights for policy 1, policy_version 243890 (0.0009) -[2023-11-28 06:36:17,930][87424] Updated weights for policy 0, policy_version 244167 (0.0012) -[2023-11-28 06:36:18,135][87426] Updated weights for policy 1, policy_version 243900 (0.0010) -[2023-11-28 06:36:18,304][87424] Updated weights for policy 0, policy_version 244177 (0.0012) -[2023-11-28 06:36:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 124944384. Throughput: 0: 2743.3, 1: 2718.7. Samples: 124954284. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:36:18,445][86177] Avg episode reward: [(0, '-498.940'), (1, '-530.630')] -[2023-11-28 06:36:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000243904_62439424.pth... -[2023-11-28 06:36:18,501][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000241344_61784064.pth -[2023-11-28 06:36:18,684][87424] Updated weights for policy 0, policy_version 244187 (0.0012) -[2023-11-28 06:36:18,873][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000244192_62513152.pth... -[2023-11-28 06:36:18,917][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000241632_61857792.pth -[2023-11-28 06:36:20,545][87426] Updated weights for policy 1, policy_version 243910 (0.0010) -[2023-11-28 06:36:20,930][87426] Updated weights for policy 1, policy_version 243920 (0.0008) -[2023-11-28 06:36:21,244][87424] Updated weights for policy 0, policy_version 244197 (0.0012) -[2023-11-28 06:36:21,308][87426] Updated weights for policy 1, policy_version 243930 (0.0010) -[2023-11-28 06:36:21,617][87424] Updated weights for policy 0, policy_version 244207 (0.0012) -[2023-11-28 06:36:22,001][87424] Updated weights for policy 0, policy_version 244217 (0.0012) -[2023-11-28 06:36:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 124968960. Throughput: 0: 2753.4, 1: 2709.6. Samples: 124986188. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:36:23,445][86177] Avg episode reward: [(0, '-519.570'), (1, '-518.300')] -[2023-11-28 06:36:23,841][87426] Updated weights for policy 1, policy_version 243940 (0.0011) -[2023-11-28 06:36:24,160][87424] Updated weights for policy 0, policy_version 244227 (0.0011) -[2023-11-28 06:36:24,205][87426] Updated weights for policy 1, policy_version 243950 (0.0012) -[2023-11-28 06:36:24,546][87424] Updated weights for policy 0, policy_version 244237 (0.0012) -[2023-11-28 06:36:24,581][87426] Updated weights for policy 1, policy_version 243960 (0.0007) -[2023-11-28 06:36:24,920][87424] Updated weights for policy 0, policy_version 244247 (0.0012) -[2023-11-28 06:36:26,525][87426] Updated weights for policy 1, policy_version 243970 (0.0009) -[2023-11-28 06:36:26,900][87426] Updated weights for policy 1, policy_version 243980 (0.0010) -[2023-11-28 06:36:27,275][87426] Updated weights for policy 1, policy_version 243990 (0.0011) -[2023-11-28 06:36:27,344][87424] Updated weights for policy 0, policy_version 244257 (0.0011) -[2023-11-28 06:36:27,650][87426] Updated weights for policy 1, policy_version 244000 (0.0011) -[2023-11-28 06:36:27,730][87424] Updated weights for policy 0, policy_version 244267 (0.0007) -[2023-11-28 06:36:28,120][87424] Updated weights for policy 0, policy_version 244277 (0.0007) -[2023-11-28 06:36:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 124993536. Throughput: 0: 2776.9, 1: 2724.7. Samples: 125011236. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:36:28,445][86177] Avg episode reward: [(0, '-530.510'), (1, '-516.850')] -[2023-11-28 06:36:28,503][87424] Updated weights for policy 0, policy_version 244287 (0.0007) -[2023-11-28 06:36:30,084][87426] Updated weights for policy 1, policy_version 244010 (0.0009) -[2023-11-28 06:36:30,457][87426] Updated weights for policy 1, policy_version 244020 (0.0010) -[2023-11-28 06:36:30,840][87426] Updated weights for policy 1, policy_version 244030 (0.0009) -[2023-11-28 06:36:30,911][87424] Updated weights for policy 0, policy_version 244297 (0.0008) -[2023-11-28 06:36:31,291][87424] Updated weights for policy 0, policy_version 244307 (0.0008) -[2023-11-28 06:36:31,675][87424] Updated weights for policy 0, policy_version 244317 (0.0009) -[2023-11-28 06:36:33,235][87426] Updated weights for policy 1, policy_version 244040 (0.0010) -[2023-11-28 06:36:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125018112. Throughput: 0: 2760.4, 1: 2710.2. Samples: 125034932. Policy #0 lag: (min: 11.0, avg: 32.5, max: 45.0) -[2023-11-28 06:36:33,445][86177] Avg episode reward: [(0, '-529.540'), (1, '-512.590')] -[2023-11-28 06:36:33,613][87426] Updated weights for policy 1, policy_version 244050 (0.0009) -[2023-11-28 06:36:33,980][87426] Updated weights for policy 1, policy_version 244060 (0.0008) -[2023-11-28 06:36:34,041][87424] Updated weights for policy 0, policy_version 244327 (0.0007) -[2023-11-28 06:36:34,429][87424] Updated weights for policy 0, policy_version 244337 (0.0008) -[2023-11-28 06:36:34,812][87424] Updated weights for policy 0, policy_version 244347 (0.0008) -[2023-11-28 06:36:36,389][87426] Updated weights for policy 1, policy_version 244070 (0.0007) -[2023-11-28 06:36:36,780][87426] Updated weights for policy 1, policy_version 244080 (0.0008) -[2023-11-28 06:36:36,970][87424] Updated weights for policy 0, policy_version 244357 (0.0008) -[2023-11-28 06:36:37,155][87426] Updated weights for policy 1, policy_version 244090 (0.0010) -[2023-11-28 06:36:37,342][87424] Updated weights for policy 0, policy_version 244367 (0.0011) -[2023-11-28 06:36:37,724][87424] Updated weights for policy 0, policy_version 244377 (0.0008) -[2023-11-28 06:36:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125050880. Throughput: 0: 2745.3, 1: 2694.5. Samples: 125066040. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:36:38,445][86177] Avg episode reward: [(0, '-512.210'), (1, '-504.860')] -[2023-11-28 06:36:39,150][87426] Updated weights for policy 1, policy_version 244100 (0.0008) -[2023-11-28 06:36:39,431][87424] Updated weights for policy 0, policy_version 244387 (0.0009) -[2023-11-28 06:36:39,531][87426] Updated weights for policy 1, policy_version 244110 (0.0008) -[2023-11-28 06:36:39,812][87424] Updated weights for policy 0, policy_version 244397 (0.0011) -[2023-11-28 06:36:39,913][87426] Updated weights for policy 1, policy_version 244120 (0.0010) -[2023-11-28 06:36:40,186][87424] Updated weights for policy 0, policy_version 244407 (0.0014) -[2023-11-28 06:36:41,824][87426] Updated weights for policy 1, policy_version 244130 (0.0011) -[2023-11-28 06:36:42,196][87426] Updated weights for policy 1, policy_version 244140 (0.0012) -[2023-11-28 06:36:42,578][87426] Updated weights for policy 1, policy_version 244150 (0.0009) -[2023-11-28 06:36:42,744][87424] Updated weights for policy 0, policy_version 244417 (0.0013) -[2023-11-28 06:36:42,960][87426] Updated weights for policy 1, policy_version 244160 (0.0009) -[2023-11-28 06:36:43,130][87424] Updated weights for policy 0, policy_version 244427 (0.0012) -[2023-11-28 06:36:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 125075456. Throughput: 0: 2755.7, 1: 2683.0. Samples: 125090480. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:36:43,445][86177] Avg episode reward: [(0, '-508.840'), (1, '-505.020')] -[2023-11-28 06:36:43,511][87424] Updated weights for policy 0, policy_version 244437 (0.0012) -[2023-11-28 06:36:43,901][87424] Updated weights for policy 0, policy_version 244447 (0.0011) -[2023-11-28 06:36:45,377][87426] Updated weights for policy 1, policy_version 244170 (0.0012) -[2023-11-28 06:36:45,760][87426] Updated weights for policy 1, policy_version 244180 (0.0012) -[2023-11-28 06:36:46,070][87424] Updated weights for policy 0, policy_version 244457 (0.0011) -[2023-11-28 06:36:46,130][87426] Updated weights for policy 1, policy_version 244190 (0.0010) -[2023-11-28 06:36:46,443][87424] Updated weights for policy 0, policy_version 244467 (0.0011) -[2023-11-28 06:36:46,835][87424] Updated weights for policy 0, policy_version 244477 (0.0012) -[2023-11-28 06:36:48,029][87426] Updated weights for policy 1, policy_version 244200 (0.0009) -[2023-11-28 06:36:48,403][87426] Updated weights for policy 1, policy_version 244210 (0.0010) -[2023-11-28 06:36:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125100032. Throughput: 0: 2720.3, 1: 2701.2. Samples: 125115444. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:36:48,445][86177] Avg episode reward: [(0, '-492.970'), (1, '-506.700')] -[2023-11-28 06:36:48,780][87426] Updated weights for policy 1, policy_version 244220 (0.0011) -[2023-11-28 06:36:49,278][87424] Updated weights for policy 0, policy_version 244487 (0.0010) -[2023-11-28 06:36:49,659][87424] Updated weights for policy 0, policy_version 244497 (0.0008) -[2023-11-28 06:36:50,046][87424] Updated weights for policy 0, policy_version 244507 (0.0009) -[2023-11-28 06:36:51,250][87426] Updated weights for policy 1, policy_version 244230 (0.0009) -[2023-11-28 06:36:51,627][87426] Updated weights for policy 1, policy_version 244240 (0.0008) -[2023-11-28 06:36:52,008][87426] Updated weights for policy 1, policy_version 244250 (0.0008) -[2023-11-28 06:36:52,498][87424] Updated weights for policy 0, policy_version 244517 (0.0010) -[2023-11-28 06:36:52,880][87424] Updated weights for policy 0, policy_version 244527 (0.0011) -[2023-11-28 06:36:53,264][87424] Updated weights for policy 0, policy_version 244537 (0.0009) -[2023-11-28 06:36:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 125124608. Throughput: 0: 2681.5, 1: 2718.4. Samples: 125147092. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:36:53,445][86177] Avg episode reward: [(0, '-517.210'), (1, '-515.510')] -[2023-11-28 06:36:54,419][87426] Updated weights for policy 1, policy_version 244260 (0.0008) -[2023-11-28 06:36:54,799][87426] Updated weights for policy 1, policy_version 244270 (0.0007) -[2023-11-28 06:36:55,177][87426] Updated weights for policy 1, policy_version 244280 (0.0007) -[2023-11-28 06:36:55,330][87424] Updated weights for policy 0, policy_version 244547 (0.0010) -[2023-11-28 06:36:55,711][87424] Updated weights for policy 0, policy_version 244557 (0.0012) -[2023-11-28 06:36:56,099][87424] Updated weights for policy 0, policy_version 244567 (0.0012) -[2023-11-28 06:36:57,241][87426] Updated weights for policy 1, policy_version 244290 (0.0008) -[2023-11-28 06:36:57,626][87426] Updated weights for policy 1, policy_version 244300 (0.0008) -[2023-11-28 06:36:58,021][87426] Updated weights for policy 1, policy_version 244310 (0.0007) -[2023-11-28 06:36:58,163][87424] Updated weights for policy 0, policy_version 244577 (0.0011) -[2023-11-28 06:36:58,401][87426] Updated weights for policy 1, policy_version 244320 (0.0008) -[2023-11-28 06:36:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 125157376. Throughput: 0: 2669.9, 1: 2715.9. Samples: 125170728. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:36:58,445][86177] Avg episode reward: [(0, '-519.280'), (1, '-520.070')] -[2023-11-28 06:36:58,556][87424] Updated weights for policy 0, policy_version 244587 (0.0009) -[2023-11-28 06:36:58,934][87424] Updated weights for policy 0, policy_version 244597 (0.0011) -[2023-11-28 06:36:59,315][87424] Updated weights for policy 0, policy_version 244607 (0.0008) -[2023-11-28 06:37:00,880][87426] Updated weights for policy 1, policy_version 244330 (0.0008) -[2023-11-28 06:37:01,260][87426] Updated weights for policy 1, policy_version 244340 (0.0007) -[2023-11-28 06:37:01,486][87424] Updated weights for policy 0, policy_version 244617 (0.0011) -[2023-11-28 06:37:01,652][87426] Updated weights for policy 1, policy_version 244350 (0.0011) -[2023-11-28 06:37:01,863][87424] Updated weights for policy 0, policy_version 244627 (0.0012) -[2023-11-28 06:37:02,249][87424] Updated weights for policy 0, policy_version 244637 (0.0012) -[2023-11-28 06:37:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 125181952. Throughput: 0: 2644.0, 1: 2702.6. Samples: 125194880. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:37:03,445][86177] Avg episode reward: [(0, '-527.310'), (1, '-516.500')] -[2023-11-28 06:37:03,719][87426] Updated weights for policy 1, policy_version 244360 (0.0008) -[2023-11-28 06:37:04,089][87426] Updated weights for policy 1, policy_version 244370 (0.0007) -[2023-11-28 06:37:04,475][87426] Updated weights for policy 1, policy_version 244380 (0.0009) -[2023-11-28 06:37:04,608][87424] Updated weights for policy 0, policy_version 244647 (0.0012) -[2023-11-28 06:37:04,985][87424] Updated weights for policy 0, policy_version 244657 (0.0008) -[2023-11-28 06:37:05,374][87424] Updated weights for policy 0, policy_version 244667 (0.0012) -[2023-11-28 06:37:06,724][87426] Updated weights for policy 1, policy_version 244390 (0.0010) -[2023-11-28 06:37:07,098][87426] Updated weights for policy 1, policy_version 244400 (0.0011) -[2023-11-28 06:37:07,286][87424] Updated weights for policy 0, policy_version 244677 (0.0012) -[2023-11-28 06:37:07,478][87426] Updated weights for policy 1, policy_version 244410 (0.0008) -[2023-11-28 06:37:07,660][87424] Updated weights for policy 0, policy_version 244687 (0.0009) -[2023-11-28 06:37:08,046][87424] Updated weights for policy 0, policy_version 244697 (0.0007) -[2023-11-28 06:37:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 125214720. Throughput: 0: 2661.0, 1: 2713.2. Samples: 125228028. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:37:08,445][86177] Avg episode reward: [(0, '-548.120'), (1, '-510.110')] -[2023-11-28 06:37:09,249][87426] Updated weights for policy 1, policy_version 244420 (0.0008) -[2023-11-28 06:37:09,626][87426] Updated weights for policy 1, policy_version 244430 (0.0007) -[2023-11-28 06:37:10,004][87426] Updated weights for policy 1, policy_version 244440 (0.0010) -[2023-11-28 06:37:10,494][87424] Updated weights for policy 0, policy_version 244707 (0.0009) -[2023-11-28 06:37:10,871][87424] Updated weights for policy 0, policy_version 244717 (0.0012) -[2023-11-28 06:37:11,249][87424] Updated weights for policy 0, policy_version 244727 (0.0012) -[2023-11-28 06:37:12,481][87426] Updated weights for policy 1, policy_version 244450 (0.0008) -[2023-11-28 06:37:12,864][87426] Updated weights for policy 1, policy_version 244460 (0.0010) -[2023-11-28 06:37:13,241][87426] Updated weights for policy 1, policy_version 244470 (0.0008) -[2023-11-28 06:37:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 125231104. Throughput: 0: 2635.5, 1: 2692.5. Samples: 125250996. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:37:13,445][86177] Avg episode reward: [(0, '-538.110'), (1, '-509.280')] -[2023-11-28 06:37:13,596][87424] Updated weights for policy 0, policy_version 244737 (0.0012) -[2023-11-28 06:37:13,618][87426] Updated weights for policy 1, policy_version 244480 (0.0008) -[2023-11-28 06:37:13,983][87424] Updated weights for policy 0, policy_version 244747 (0.0010) -[2023-11-28 06:37:14,355][87424] Updated weights for policy 0, policy_version 244757 (0.0012) -[2023-11-28 06:37:14,733][87424] Updated weights for policy 0, policy_version 244767 (0.0010) -[2023-11-28 06:37:15,897][87426] Updated weights for policy 1, policy_version 244490 (0.0012) -[2023-11-28 06:37:16,272][87426] Updated weights for policy 1, policy_version 244500 (0.0012) -[2023-11-28 06:37:16,645][87426] Updated weights for policy 1, policy_version 244510 (0.0012) -[2023-11-28 06:37:16,993][87424] Updated weights for policy 0, policy_version 244777 (0.0011) -[2023-11-28 06:37:17,383][87424] Updated weights for policy 0, policy_version 244787 (0.0012) -[2023-11-28 06:37:17,764][87424] Updated weights for policy 0, policy_version 244797 (0.0012) -[2023-11-28 06:37:18,369][87426] Updated weights for policy 1, policy_version 244520 (0.0012) -[2023-11-28 06:37:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 125263872. Throughput: 0: 2643.0, 1: 2701.5. Samples: 125275436. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:37:18,445][86177] Avg episode reward: [(0, '-536.730'), (1, '-522.070')] -[2023-11-28 06:37:18,747][87426] Updated weights for policy 1, policy_version 244530 (0.0012) -[2023-11-28 06:37:19,119][87426] Updated weights for policy 1, policy_version 244540 (0.0011) -[2023-11-28 06:37:19,892][87424] Updated weights for policy 0, policy_version 244807 (0.0012) -[2023-11-28 06:37:20,271][87424] Updated weights for policy 0, policy_version 244817 (0.0012) -[2023-11-28 06:37:20,654][87424] Updated weights for policy 0, policy_version 244827 (0.0012) -[2023-11-28 06:37:21,168][87426] Updated weights for policy 1, policy_version 244550 (0.0012) -[2023-11-28 06:37:21,537][87426] Updated weights for policy 1, policy_version 244560 (0.0012) -[2023-11-28 06:37:21,933][87426] Updated weights for policy 1, policy_version 244570 (0.0012) -[2023-11-28 06:37:22,879][87424] Updated weights for policy 0, policy_version 244837 (0.0011) -[2023-11-28 06:37:23,268][87424] Updated weights for policy 0, policy_version 244847 (0.0010) -[2023-11-28 06:37:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 125288448. Throughput: 0: 2638.8, 1: 2734.9. Samples: 125307856. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:37:23,445][86177] Avg episode reward: [(0, '-520.840'), (1, '-538.940')] -[2023-11-28 06:37:23,653][87424] Updated weights for policy 0, policy_version 244857 (0.0011) -[2023-11-28 06:37:23,803][87426] Updated weights for policy 1, policy_version 244580 (0.0010) -[2023-11-28 06:37:24,187][87426] Updated weights for policy 1, policy_version 244590 (0.0007) -[2023-11-28 06:37:24,572][87426] Updated weights for policy 1, policy_version 244600 (0.0008) -[2023-11-28 06:37:25,833][87424] Updated weights for policy 0, policy_version 244867 (0.0010) -[2023-11-28 06:37:26,217][87424] Updated weights for policy 0, policy_version 244877 (0.0007) -[2023-11-28 06:37:26,611][87424] Updated weights for policy 0, policy_version 244887 (0.0008) -[2023-11-28 06:37:26,864][87426] Updated weights for policy 1, policy_version 244610 (0.0011) -[2023-11-28 06:37:27,247][87426] Updated weights for policy 1, policy_version 244620 (0.0007) -[2023-11-28 06:37:27,631][87426] Updated weights for policy 1, policy_version 244630 (0.0008) -[2023-11-28 06:37:28,005][87426] Updated weights for policy 1, policy_version 244640 (0.0007) -[2023-11-28 06:37:28,358][87424] Updated weights for policy 0, policy_version 244897 (0.0010) -[2023-11-28 06:37:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 125321216. Throughput: 0: 2649.1, 1: 2753.6. Samples: 125333600. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:37:28,446][86177] Avg episode reward: [(0, '-524.280'), (1, '-554.590')] -[2023-11-28 06:37:28,740][87424] Updated weights for policy 0, policy_version 244907 (0.0012) -[2023-11-28 06:37:29,130][87424] Updated weights for policy 0, policy_version 244917 (0.0012) -[2023-11-28 06:37:29,511][87424] Updated weights for policy 0, policy_version 244927 (0.0011) -[2023-11-28 06:37:29,613][87426] Updated weights for policy 1, policy_version 244650 (0.0012) -[2023-11-28 06:37:29,992][87426] Updated weights for policy 1, policy_version 244660 (0.0012) -[2023-11-28 06:37:30,373][87426] Updated weights for policy 1, policy_version 244670 (0.0011) -[2023-11-28 06:37:31,522][87424] Updated weights for policy 0, policy_version 244937 (0.0012) -[2023-11-28 06:37:31,901][87424] Updated weights for policy 0, policy_version 244947 (0.0012) -[2023-11-28 06:37:32,286][87424] Updated weights for policy 0, policy_version 244957 (0.0011) -[2023-11-28 06:37:32,665][87426] Updated weights for policy 1, policy_version 244680 (0.0012) -[2023-11-28 06:37:33,038][87426] Updated weights for policy 1, policy_version 244690 (0.0012) -[2023-11-28 06:37:33,417][87426] Updated weights for policy 1, policy_version 244700 (0.0012) -[2023-11-28 06:37:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125345792. Throughput: 0: 2676.5, 1: 2727.9. Samples: 125358644. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:37:33,445][86177] Avg episode reward: [(0, '-507.780'), (1, '-560.660')] -[2023-11-28 06:37:34,181][87424] Updated weights for policy 0, policy_version 244967 (0.0010) -[2023-11-28 06:37:34,562][87424] Updated weights for policy 0, policy_version 244977 (0.0012) -[2023-11-28 06:37:34,948][87424] Updated weights for policy 0, policy_version 244987 (0.0010) -[2023-11-28 06:37:35,893][87426] Updated weights for policy 1, policy_version 244710 (0.0011) -[2023-11-28 06:37:36,271][87426] Updated weights for policy 1, policy_version 244720 (0.0010) -[2023-11-28 06:37:36,650][87426] Updated weights for policy 1, policy_version 244730 (0.0010) -[2023-11-28 06:37:37,443][87424] Updated weights for policy 0, policy_version 244997 (0.0010) -[2023-11-28 06:37:37,822][87424] Updated weights for policy 0, policy_version 245007 (0.0007) -[2023-11-28 06:37:38,204][87424] Updated weights for policy 0, policy_version 245017 (0.0008) -[2023-11-28 06:37:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 125370368. Throughput: 0: 2698.8, 1: 2732.4. Samples: 125391496. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:37:38,445][86177] Avg episode reward: [(0, '-502.220'), (1, '-550.480')] -[2023-11-28 06:37:38,759][87426] Updated weights for policy 1, policy_version 244740 (0.0009) -[2023-11-28 06:37:39,132][87426] Updated weights for policy 1, policy_version 244750 (0.0012) -[2023-11-28 06:37:39,506][87426] Updated weights for policy 1, policy_version 244760 (0.0012) -[2023-11-28 06:37:40,271][87424] Updated weights for policy 0, policy_version 245027 (0.0010) -[2023-11-28 06:37:40,657][87424] Updated weights for policy 0, policy_version 245037 (0.0012) -[2023-11-28 06:37:41,038][87424] Updated weights for policy 0, policy_version 245047 (0.0012) -[2023-11-28 06:37:41,752][87426] Updated weights for policy 1, policy_version 244770 (0.0011) -[2023-11-28 06:37:42,128][87426] Updated weights for policy 1, policy_version 244780 (0.0011) -[2023-11-28 06:37:42,509][87426] Updated weights for policy 1, policy_version 244790 (0.0011) -[2023-11-28 06:37:42,888][87426] Updated weights for policy 1, policy_version 244800 (0.0012) -[2023-11-28 06:37:42,916][87424] Updated weights for policy 0, policy_version 245057 (0.0008) -[2023-11-28 06:37:43,299][87424] Updated weights for policy 0, policy_version 245067 (0.0012) -[2023-11-28 06:37:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 125403136. Throughput: 0: 2701.6, 1: 2745.9. Samples: 125415864. Policy #0 lag: (min: 31.0, avg: 43.4, max: 63.0) -[2023-11-28 06:37:43,445][86177] Avg episode reward: [(0, '-503.130'), (1, '-530.690')] -[2023-11-28 06:37:43,678][87424] Updated weights for policy 0, policy_version 245077 (0.0012) -[2023-11-28 06:37:44,057][87424] Updated weights for policy 0, policy_version 245087 (0.0012) -[2023-11-28 06:37:45,001][87426] Updated weights for policy 1, policy_version 244810 (0.0012) -[2023-11-28 06:37:45,388][87426] Updated weights for policy 1, policy_version 244820 (0.0012) -[2023-11-28 06:37:45,761][87426] Updated weights for policy 1, policy_version 244830 (0.0011) -[2023-11-28 06:37:46,629][87424] Updated weights for policy 0, policy_version 245097 (0.0012) -[2023-11-28 06:37:47,021][87424] Updated weights for policy 0, policy_version 245107 (0.0011) -[2023-11-28 06:37:47,395][87424] Updated weights for policy 0, policy_version 245117 (0.0011) -[2023-11-28 06:37:47,555][87426] Updated weights for policy 1, policy_version 244840 (0.0011) -[2023-11-28 06:37:47,934][87426] Updated weights for policy 1, policy_version 244850 (0.0012) -[2023-11-28 06:37:48,312][87426] Updated weights for policy 1, policy_version 244860 (0.0012) -[2023-11-28 06:37:48,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 125427712. Throughput: 0: 2702.4, 1: 2761.7. Samples: 125440764. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:37:48,446][86177] Avg episode reward: [(0, '-498.770'), (1, '-525.240')] -[2023-11-28 06:37:49,636][87424] Updated weights for policy 0, policy_version 245127 (0.0012) -[2023-11-28 06:37:50,015][87424] Updated weights for policy 0, policy_version 245137 (0.0011) -[2023-11-28 06:37:50,398][87424] Updated weights for policy 0, policy_version 245147 (0.0009) -[2023-11-28 06:37:50,841][87426] Updated weights for policy 1, policy_version 244870 (0.0009) -[2023-11-28 06:37:51,226][87426] Updated weights for policy 1, policy_version 244880 (0.0008) -[2023-11-28 06:37:51,617][87426] Updated weights for policy 1, policy_version 244890 (0.0009) -[2023-11-28 06:37:52,994][87424] Updated weights for policy 0, policy_version 245157 (0.0010) -[2023-11-28 06:37:53,388][87424] Updated weights for policy 0, policy_version 245167 (0.0012) -[2023-11-28 06:37:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 125452288. Throughput: 0: 2719.1, 1: 2762.9. Samples: 125474720. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:37:53,445][86177] Avg episode reward: [(0, '-497.660'), (1, '-518.640')] -[2023-11-28 06:37:53,774][87424] Updated weights for policy 0, policy_version 245177 (0.0011) -[2023-11-28 06:37:53,890][87426] Updated weights for policy 1, policy_version 244900 (0.0010) -[2023-11-28 06:37:54,276][87426] Updated weights for policy 1, policy_version 244910 (0.0008) -[2023-11-28 06:37:54,656][87426] Updated weights for policy 1, policy_version 244920 (0.0007) -[2023-11-28 06:37:55,889][87424] Updated weights for policy 0, policy_version 245187 (0.0011) -[2023-11-28 06:37:56,271][87424] Updated weights for policy 0, policy_version 245197 (0.0007) -[2023-11-28 06:37:56,657][87424] Updated weights for policy 0, policy_version 245207 (0.0008) -[2023-11-28 06:37:56,831][87426] Updated weights for policy 1, policy_version 244930 (0.0007) -[2023-11-28 06:37:57,209][87426] Updated weights for policy 1, policy_version 244940 (0.0009) -[2023-11-28 06:37:57,589][87426] Updated weights for policy 1, policy_version 244950 (0.0007) -[2023-11-28 06:37:57,968][87426] Updated weights for policy 1, policy_version 244960 (0.0007) -[2023-11-28 06:37:58,333][87424] Updated weights for policy 0, policy_version 245217 (0.0011) -[2023-11-28 06:37:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 125485056. Throughput: 0: 2739.0, 1: 2770.8. Samples: 125498936. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:37:58,445][86177] Avg episode reward: [(0, '-496.360'), (1, '-520.520')] -[2023-11-28 06:37:58,721][87424] Updated weights for policy 0, policy_version 245227 (0.0007) -[2023-11-28 06:37:59,097][87424] Updated weights for policy 0, policy_version 245237 (0.0010) -[2023-11-28 06:37:59,483][87424] Updated weights for policy 0, policy_version 245247 (0.0011) -[2023-11-28 06:38:00,213][87426] Updated weights for policy 1, policy_version 244970 (0.0011) -[2023-11-28 06:38:00,597][87426] Updated weights for policy 1, policy_version 244980 (0.0010) -[2023-11-28 06:38:00,972][87426] Updated weights for policy 1, policy_version 244990 (0.0010) -[2023-11-28 06:38:01,892][87424] Updated weights for policy 0, policy_version 245257 (0.0011) -[2023-11-28 06:38:02,269][87424] Updated weights for policy 0, policy_version 245267 (0.0012) -[2023-11-28 06:38:02,653][87424] Updated weights for policy 0, policy_version 245277 (0.0012) -[2023-11-28 06:38:03,152][87426] Updated weights for policy 1, policy_version 245000 (0.0010) -[2023-11-28 06:38:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125509632. Throughput: 0: 2756.5, 1: 2764.0. Samples: 125523856. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:03,445][86177] Avg episode reward: [(0, '-493.420'), (1, '-528.070')] -[2023-11-28 06:38:03,535][87426] Updated weights for policy 1, policy_version 245010 (0.0011) -[2023-11-28 06:38:03,909][87426] Updated weights for policy 1, policy_version 245020 (0.0007) -[2023-11-28 06:38:04,480][87424] Updated weights for policy 0, policy_version 245287 (0.0009) -[2023-11-28 06:38:04,867][87424] Updated weights for policy 0, policy_version 245297 (0.0007) -[2023-11-28 06:38:05,254][87424] Updated weights for policy 0, policy_version 245307 (0.0008) -[2023-11-28 06:38:05,861][87426] Updated weights for policy 1, policy_version 245030 (0.0009) -[2023-11-28 06:38:06,244][87426] Updated weights for policy 1, policy_version 245040 (0.0011) -[2023-11-28 06:38:06,626][87426] Updated weights for policy 1, policy_version 245050 (0.0011) -[2023-11-28 06:38:07,358][87424] Updated weights for policy 0, policy_version 245317 (0.0007) -[2023-11-28 06:38:07,744][87424] Updated weights for policy 0, policy_version 245327 (0.0008) -[2023-11-28 06:38:08,125][87424] Updated weights for policy 0, policy_version 245337 (0.0010) -[2023-11-28 06:38:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 125542400. Throughput: 0: 2763.0, 1: 2751.5. Samples: 125556008. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:08,445][86177] Avg episode reward: [(0, '-494.900'), (1, '-536.580')] -[2023-11-28 06:38:08,829][87426] Updated weights for policy 1, policy_version 245060 (0.0011) -[2023-11-28 06:38:09,225][87426] Updated weights for policy 1, policy_version 245070 (0.0009) -[2023-11-28 06:38:09,593][87426] Updated weights for policy 1, policy_version 245080 (0.0007) -[2023-11-28 06:38:10,657][87424] Updated weights for policy 0, policy_version 245347 (0.0009) -[2023-11-28 06:38:11,037][87424] Updated weights for policy 0, policy_version 245357 (0.0011) -[2023-11-28 06:38:11,420][87424] Updated weights for policy 0, policy_version 245367 (0.0012) -[2023-11-28 06:38:11,534][87426] Updated weights for policy 1, policy_version 245090 (0.0010) -[2023-11-28 06:38:11,912][87426] Updated weights for policy 1, policy_version 245100 (0.0012) -[2023-11-28 06:38:12,283][87426] Updated weights for policy 1, policy_version 245110 (0.0009) -[2023-11-28 06:38:12,655][87426] Updated weights for policy 1, policy_version 245120 (0.0008) -[2023-11-28 06:38:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 125566976. Throughput: 0: 2750.0, 1: 2725.9. Samples: 125580016. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:13,446][86177] Avg episode reward: [(0, '-499.630'), (1, '-538.580')] -[2023-11-28 06:38:13,819][87424] Updated weights for policy 0, policy_version 245377 (0.0012) -[2023-11-28 06:38:14,196][87424] Updated weights for policy 0, policy_version 245387 (0.0012) -[2023-11-28 06:38:14,575][87424] Updated weights for policy 0, policy_version 245397 (0.0011) -[2023-11-28 06:38:14,944][87424] Updated weights for policy 0, policy_version 245407 (0.0012) -[2023-11-28 06:38:15,020][87426] Updated weights for policy 1, policy_version 245130 (0.0011) -[2023-11-28 06:38:15,404][87426] Updated weights for policy 1, policy_version 245140 (0.0012) -[2023-11-28 06:38:15,788][87426] Updated weights for policy 1, policy_version 245150 (0.0012) -[2023-11-28 06:38:17,262][87424] Updated weights for policy 0, policy_version 245417 (0.0012) -[2023-11-28 06:38:17,535][87426] Updated weights for policy 1, policy_version 245160 (0.0011) -[2023-11-28 06:38:17,629][87424] Updated weights for policy 0, policy_version 245427 (0.0010) -[2023-11-28 06:38:17,921][87426] Updated weights for policy 1, policy_version 245170 (0.0008) -[2023-11-28 06:38:18,009][87424] Updated weights for policy 0, policy_version 245437 (0.0011) -[2023-11-28 06:38:18,304][87426] Updated weights for policy 1, policy_version 245180 (0.0011) -[2023-11-28 06:38:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 125591552. Throughput: 0: 2722.3, 1: 2737.0. Samples: 125604312. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:18,445][86177] Avg episode reward: [(0, '-503.620'), (1, '-546.120')] -[2023-11-28 06:38:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000245440_62832640.pth... -[2023-11-28 06:38:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000245184_62767104.pth... -[2023-11-28 06:38:18,489][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000242912_62185472.pth -[2023-11-28 06:38:18,493][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000242624_62111744.pth -[2023-11-28 06:38:20,518][87426] Updated weights for policy 1, policy_version 245190 (0.0011) -[2023-11-28 06:38:20,585][87424] Updated weights for policy 0, policy_version 245447 (0.0010) -[2023-11-28 06:38:20,899][87426] Updated weights for policy 1, policy_version 245200 (0.0011) -[2023-11-28 06:38:20,973][87424] Updated weights for policy 0, policy_version 245457 (0.0011) -[2023-11-28 06:38:21,279][87426] Updated weights for policy 1, policy_version 245210 (0.0012) -[2023-11-28 06:38:21,349][87424] Updated weights for policy 0, policy_version 245467 (0.0011) -[2023-11-28 06:38:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125616128. Throughput: 0: 2691.7, 1: 2730.6. Samples: 125635500. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:23,445][86177] Avg episode reward: [(0, '-507.230'), (1, '-547.920')] -[2023-11-28 06:38:23,571][87424] Updated weights for policy 0, policy_version 245477 (0.0010) -[2023-11-28 06:38:23,617][87426] Updated weights for policy 1, policy_version 245220 (0.0012) -[2023-11-28 06:38:23,957][87424] Updated weights for policy 0, policy_version 245487 (0.0007) -[2023-11-28 06:38:23,993][87426] Updated weights for policy 1, policy_version 245230 (0.0011) -[2023-11-28 06:38:24,340][87424] Updated weights for policy 0, policy_version 245497 (0.0007) -[2023-11-28 06:38:24,368][87426] Updated weights for policy 1, policy_version 245240 (0.0009) -[2023-11-28 06:38:25,988][87424] Updated weights for policy 0, policy_version 245507 (0.0009) -[2023-11-28 06:38:26,367][87424] Updated weights for policy 0, policy_version 245517 (0.0012) -[2023-11-28 06:38:26,753][87424] Updated weights for policy 0, policy_version 245527 (0.0012) -[2023-11-28 06:38:26,835][87426] Updated weights for policy 1, policy_version 245250 (0.0009) -[2023-11-28 06:38:27,213][87426] Updated weights for policy 1, policy_version 245260 (0.0012) -[2023-11-28 06:38:27,601][87426] Updated weights for policy 1, policy_version 245270 (0.0010) -[2023-11-28 06:38:27,989][87426] Updated weights for policy 1, policy_version 245280 (0.0010) -[2023-11-28 06:38:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 125648896. Throughput: 0: 2712.0, 1: 2741.1. Samples: 125661256. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:28,445][86177] Avg episode reward: [(0, '-505.680'), (1, '-545.660')] -[2023-11-28 06:38:28,935][87424] Updated weights for policy 0, policy_version 245537 (0.0012) -[2023-11-28 06:38:29,318][87424] Updated weights for policy 0, policy_version 245547 (0.0012) -[2023-11-28 06:38:29,702][87424] Updated weights for policy 0, policy_version 245557 (0.0011) -[2023-11-28 06:38:30,084][87424] Updated weights for policy 0, policy_version 245567 (0.0012) -[2023-11-28 06:38:30,381][87426] Updated weights for policy 1, policy_version 245290 (0.0008) -[2023-11-28 06:38:30,760][87426] Updated weights for policy 1, policy_version 245300 (0.0008) -[2023-11-28 06:38:31,135][87426] Updated weights for policy 1, policy_version 245310 (0.0007) -[2023-11-28 06:38:32,023][87424] Updated weights for policy 0, policy_version 245577 (0.0010) -[2023-11-28 06:38:32,404][87424] Updated weights for policy 0, policy_version 245587 (0.0011) -[2023-11-28 06:38:32,788][87424] Updated weights for policy 0, policy_version 245597 (0.0007) -[2023-11-28 06:38:33,144][87426] Updated weights for policy 1, policy_version 245320 (0.0011) -[2023-11-28 06:38:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 125673472. Throughput: 0: 2735.1, 1: 2744.4. Samples: 125687340. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:33,446][86177] Avg episode reward: [(0, '-509.710'), (1, '-544.710')] -[2023-11-28 06:38:33,524][87426] Updated weights for policy 1, policy_version 245330 (0.0007) -[2023-11-28 06:38:33,906][87426] Updated weights for policy 1, policy_version 245340 (0.0007) -[2023-11-28 06:38:34,916][87424] Updated weights for policy 0, policy_version 245607 (0.0011) -[2023-11-28 06:38:35,295][87424] Updated weights for policy 0, policy_version 245617 (0.0012) -[2023-11-28 06:38:35,680][87424] Updated weights for policy 0, policy_version 245627 (0.0012) -[2023-11-28 06:38:36,329][87426] Updated weights for policy 1, policy_version 245350 (0.0009) -[2023-11-28 06:38:36,714][87426] Updated weights for policy 1, policy_version 245360 (0.0009) -[2023-11-28 06:38:37,083][87426] Updated weights for policy 1, policy_version 245370 (0.0010) -[2023-11-28 06:38:37,913][87424] Updated weights for policy 0, policy_version 245637 (0.0011) -[2023-11-28 06:38:38,293][87424] Updated weights for policy 0, policy_version 245647 (0.0012) -[2023-11-28 06:38:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125698048. Throughput: 0: 2710.7, 1: 2715.0. Samples: 125718876. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:38,445][86177] Avg episode reward: [(0, '-506.980'), (1, '-544.150')] -[2023-11-28 06:38:38,671][87424] Updated weights for policy 0, policy_version 245657 (0.0012) -[2023-11-28 06:38:38,967][87426] Updated weights for policy 1, policy_version 245380 (0.0009) -[2023-11-28 06:38:39,347][87426] Updated weights for policy 1, policy_version 245390 (0.0012) -[2023-11-28 06:38:39,723][87426] Updated weights for policy 1, policy_version 245400 (0.0012) -[2023-11-28 06:38:40,774][87424] Updated weights for policy 0, policy_version 245667 (0.0012) -[2023-11-28 06:38:41,148][87424] Updated weights for policy 0, policy_version 245677 (0.0010) -[2023-11-28 06:38:41,526][87424] Updated weights for policy 0, policy_version 245687 (0.0009) -[2023-11-28 06:38:42,262][87426] Updated weights for policy 1, policy_version 245410 (0.0012) -[2023-11-28 06:38:42,638][87426] Updated weights for policy 1, policy_version 245420 (0.0012) -[2023-11-28 06:38:43,014][87426] Updated weights for policy 1, policy_version 245430 (0.0012) -[2023-11-28 06:38:43,395][87426] Updated weights for policy 1, policy_version 245440 (0.0012) -[2023-11-28 06:38:43,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125730816. Throughput: 0: 2700.8, 1: 2706.4. Samples: 125742260. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:43,446][86177] Avg episode reward: [(0, '-505.770'), (1, '-524.040')] -[2023-11-28 06:38:43,865][87424] Updated weights for policy 0, policy_version 245697 (0.0010) -[2023-11-28 06:38:44,236][87424] Updated weights for policy 0, policy_version 245707 (0.0011) -[2023-11-28 06:38:44,619][87424] Updated weights for policy 0, policy_version 245717 (0.0007) -[2023-11-28 06:38:44,999][87424] Updated weights for policy 0, policy_version 245727 (0.0009) -[2023-11-28 06:38:45,097][87426] Updated weights for policy 1, policy_version 245450 (0.0008) -[2023-11-28 06:38:45,475][87426] Updated weights for policy 1, policy_version 245460 (0.0012) -[2023-11-28 06:38:45,852][87426] Updated weights for policy 1, policy_version 245470 (0.0012) -[2023-11-28 06:38:47,035][87424] Updated weights for policy 0, policy_version 245737 (0.0008) -[2023-11-28 06:38:47,425][87424] Updated weights for policy 0, policy_version 245747 (0.0008) -[2023-11-28 06:38:47,720][87426] Updated weights for policy 1, policy_version 245480 (0.0011) -[2023-11-28 06:38:47,800][87424] Updated weights for policy 0, policy_version 245757 (0.0008) -[2023-11-28 06:38:48,104][87426] Updated weights for policy 1, policy_version 245490 (0.0011) -[2023-11-28 06:38:48,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 125755392. Throughput: 0: 2700.8, 1: 2721.8. Samples: 125767872. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:48,446][86177] Avg episode reward: [(0, '-514.890'), (1, '-527.440')] -[2023-11-28 06:38:48,484][87426] Updated weights for policy 1, policy_version 245500 (0.0012) -[2023-11-28 06:38:49,451][87424] Updated weights for policy 0, policy_version 245767 (0.0010) -[2023-11-28 06:38:49,823][87424] Updated weights for policy 0, policy_version 245777 (0.0011) -[2023-11-28 06:38:50,202][87424] Updated weights for policy 0, policy_version 245787 (0.0012) -[2023-11-28 06:38:51,041][87426] Updated weights for policy 1, policy_version 245510 (0.0009) -[2023-11-28 06:38:51,429][87426] Updated weights for policy 1, policy_version 245520 (0.0009) -[2023-11-28 06:38:51,794][87426] Updated weights for policy 1, policy_version 245530 (0.0009) -[2023-11-28 06:38:52,764][87424] Updated weights for policy 0, policy_version 245797 (0.0011) -[2023-11-28 06:38:53,145][87424] Updated weights for policy 0, policy_version 245807 (0.0011) -[2023-11-28 06:38:53,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125779968. Throughput: 0: 2702.3, 1: 2705.1. Samples: 125799340. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:53,445][86177] Avg episode reward: [(0, '-506.460'), (1, '-506.020')] -[2023-11-28 06:38:53,528][87424] Updated weights for policy 0, policy_version 245817 (0.0012) -[2023-11-28 06:38:54,264][87426] Updated weights for policy 1, policy_version 245540 (0.0009) -[2023-11-28 06:38:54,647][87426] Updated weights for policy 1, policy_version 245550 (0.0009) -[2023-11-28 06:38:55,023][87426] Updated weights for policy 1, policy_version 245560 (0.0012) -[2023-11-28 06:38:55,364][87424] Updated weights for policy 0, policy_version 245827 (0.0011) -[2023-11-28 06:38:55,750][87424] Updated weights for policy 0, policy_version 245837 (0.0009) -[2023-11-28 06:38:56,137][87424] Updated weights for policy 0, policy_version 245847 (0.0010) -[2023-11-28 06:38:56,835][87426] Updated weights for policy 1, policy_version 245570 (0.0012) -[2023-11-28 06:38:57,216][87426] Updated weights for policy 1, policy_version 245580 (0.0012) -[2023-11-28 06:38:57,591][87426] Updated weights for policy 1, policy_version 245590 (0.0012) -[2023-11-28 06:38:57,974][87426] Updated weights for policy 1, policy_version 245600 (0.0012) -[2023-11-28 06:38:58,088][87424] Updated weights for policy 0, policy_version 245857 (0.0008) -[2023-11-28 06:38:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125812736. Throughput: 0: 2726.8, 1: 2714.8. Samples: 125824884. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 06:38:58,445][86177] Avg episode reward: [(0, '-516.380'), (1, '-508.290')] -[2023-11-28 06:38:58,462][87424] Updated weights for policy 0, policy_version 245867 (0.0012) -[2023-11-28 06:38:58,861][87424] Updated weights for policy 0, policy_version 245877 (0.0011) -[2023-11-28 06:38:59,236][87424] Updated weights for policy 0, policy_version 245887 (0.0007) -[2023-11-28 06:38:59,909][87426] Updated weights for policy 1, policy_version 245610 (0.0010) -[2023-11-28 06:39:00,291][87426] Updated weights for policy 1, policy_version 245620 (0.0011) -[2023-11-28 06:39:00,675][87426] Updated weights for policy 1, policy_version 245630 (0.0010) -[2023-11-28 06:39:01,751][87424] Updated weights for policy 0, policy_version 245897 (0.0008) -[2023-11-28 06:39:02,135][87424] Updated weights for policy 0, policy_version 245907 (0.0009) -[2023-11-28 06:39:02,512][87424] Updated weights for policy 0, policy_version 245917 (0.0008) -[2023-11-28 06:39:02,933][87426] Updated weights for policy 1, policy_version 245640 (0.0011) -[2023-11-28 06:39:03,313][87426] Updated weights for policy 1, policy_version 245650 (0.0012) -[2023-11-28 06:39:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 125837312. Throughput: 0: 2736.3, 1: 2713.1. Samples: 125849532. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:03,445][86177] Avg episode reward: [(0, '-517.190'), (1, '-520.380')] -[2023-11-28 06:39:03,696][87426] Updated weights for policy 1, policy_version 245660 (0.0012) -[2023-11-28 06:39:05,084][87424] Updated weights for policy 0, policy_version 245927 (0.0012) -[2023-11-28 06:39:05,475][87424] Updated weights for policy 0, policy_version 245937 (0.0012) -[2023-11-28 06:39:05,854][87424] Updated weights for policy 0, policy_version 245947 (0.0012) -[2023-11-28 06:39:06,128][87426] Updated weights for policy 1, policy_version 245670 (0.0011) -[2023-11-28 06:39:06,501][87426] Updated weights for policy 1, policy_version 245680 (0.0012) -[2023-11-28 06:39:06,882][87426] Updated weights for policy 1, policy_version 245690 (0.0012) -[2023-11-28 06:39:08,164][87424] Updated weights for policy 0, policy_version 245957 (0.0009) -[2023-11-28 06:39:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 125861888. Throughput: 0: 2762.0, 1: 2700.1. Samples: 125881292. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:08,445][86177] Avg episode reward: [(0, '-510.160'), (1, '-519.600')] -[2023-11-28 06:39:08,543][87424] Updated weights for policy 0, policy_version 245967 (0.0008) -[2023-11-28 06:39:08,924][87424] Updated weights for policy 0, policy_version 245977 (0.0011) -[2023-11-28 06:39:09,245][87426] Updated weights for policy 1, policy_version 245700 (0.0012) -[2023-11-28 06:39:09,619][87426] Updated weights for policy 1, policy_version 245710 (0.0008) -[2023-11-28 06:39:10,008][87426] Updated weights for policy 1, policy_version 245720 (0.0010) -[2023-11-28 06:39:11,378][87424] Updated weights for policy 0, policy_version 245987 (0.0007) -[2023-11-28 06:39:11,755][87424] Updated weights for policy 0, policy_version 245997 (0.0012) -[2023-11-28 06:39:12,133][87424] Updated weights for policy 0, policy_version 246007 (0.0010) -[2023-11-28 06:39:12,174][87426] Updated weights for policy 1, policy_version 245730 (0.0012) -[2023-11-28 06:39:12,550][87426] Updated weights for policy 1, policy_version 245740 (0.0012) -[2023-11-28 06:39:12,928][87426] Updated weights for policy 1, policy_version 245750 (0.0012) -[2023-11-28 06:39:13,309][87426] Updated weights for policy 1, policy_version 245760 (0.0011) -[2023-11-28 06:39:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 125894656. Throughput: 0: 2729.3, 1: 2677.7. Samples: 125904572. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:13,445][86177] Avg episode reward: [(0, '-511.670'), (1, '-516.730')] -[2023-11-28 06:39:14,042][87424] Updated weights for policy 0, policy_version 246017 (0.0011) -[2023-11-28 06:39:14,424][87424] Updated weights for policy 0, policy_version 246027 (0.0007) -[2023-11-28 06:39:14,814][87424] Updated weights for policy 0, policy_version 246037 (0.0007) -[2023-11-28 06:39:15,193][87424] Updated weights for policy 0, policy_version 246047 (0.0010) -[2023-11-28 06:39:15,473][87426] Updated weights for policy 1, policy_version 245770 (0.0011) -[2023-11-28 06:39:15,860][87426] Updated weights for policy 1, policy_version 245780 (0.0012) -[2023-11-28 06:39:16,236][87426] Updated weights for policy 1, policy_version 245790 (0.0011) -[2023-11-28 06:39:17,303][87424] Updated weights for policy 0, policy_version 246057 (0.0012) -[2023-11-28 06:39:17,682][87424] Updated weights for policy 0, policy_version 246067 (0.0012) -[2023-11-28 06:39:18,069][87424] Updated weights for policy 0, policy_version 246077 (0.0012) -[2023-11-28 06:39:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 125919232. Throughput: 0: 2715.9, 1: 2672.3. Samples: 125929808. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:18,445][86177] Avg episode reward: [(0, '-506.870'), (1, '-513.760')] -[2023-11-28 06:39:18,476][87426] Updated weights for policy 1, policy_version 245800 (0.0010) -[2023-11-28 06:39:18,860][87426] Updated weights for policy 1, policy_version 245810 (0.0012) -[2023-11-28 06:39:19,235][87426] Updated weights for policy 1, policy_version 245820 (0.0010) -[2023-11-28 06:39:20,674][87424] Updated weights for policy 0, policy_version 246087 (0.0011) -[2023-11-28 06:39:21,061][87424] Updated weights for policy 0, policy_version 246097 (0.0011) -[2023-11-28 06:39:21,245][87426] Updated weights for policy 1, policy_version 245830 (0.0011) -[2023-11-28 06:39:21,440][87424] Updated weights for policy 0, policy_version 246107 (0.0012) -[2023-11-28 06:39:21,628][87426] Updated weights for policy 1, policy_version 245840 (0.0011) -[2023-11-28 06:39:22,003][87426] Updated weights for policy 1, policy_version 245850 (0.0011) -[2023-11-28 06:39:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 125943808. Throughput: 0: 2695.2, 1: 2709.9. Samples: 125962108. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:23,445][86177] Avg episode reward: [(0, '-505.090'), (1, '-505.490')] -[2023-11-28 06:39:23,931][87424] Updated weights for policy 0, policy_version 246117 (0.0009) -[2023-11-28 06:39:24,283][87426] Updated weights for policy 1, policy_version 245860 (0.0009) -[2023-11-28 06:39:24,312][87424] Updated weights for policy 0, policy_version 246127 (0.0009) -[2023-11-28 06:39:24,663][87426] Updated weights for policy 1, policy_version 245870 (0.0007) -[2023-11-28 06:39:24,697][87424] Updated weights for policy 0, policy_version 246137 (0.0008) -[2023-11-28 06:39:25,040][87426] Updated weights for policy 1, policy_version 245880 (0.0011) -[2023-11-28 06:39:26,859][87426] Updated weights for policy 1, policy_version 245890 (0.0012) -[2023-11-28 06:39:27,139][87424] Updated weights for policy 0, policy_version 246147 (0.0009) -[2023-11-28 06:39:27,247][87426] Updated weights for policy 1, policy_version 245900 (0.0011) -[2023-11-28 06:39:27,523][87424] Updated weights for policy 0, policy_version 246157 (0.0012) -[2023-11-28 06:39:27,629][87426] Updated weights for policy 1, policy_version 245910 (0.0011) -[2023-11-28 06:39:27,895][87424] Updated weights for policy 0, policy_version 246167 (0.0008) -[2023-11-28 06:39:28,003][87426] Updated weights for policy 1, policy_version 245920 (0.0010) -[2023-11-28 06:39:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 125976576. Throughput: 0: 2695.0, 1: 2762.2. Samples: 125987828. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:28,445][86177] Avg episode reward: [(0, '-521.680'), (1, '-523.740')] -[2023-11-28 06:39:29,873][87424] Updated weights for policy 0, policy_version 246177 (0.0008) -[2023-11-28 06:39:30,123][87426] Updated weights for policy 1, policy_version 245930 (0.0010) -[2023-11-28 06:39:30,251][87424] Updated weights for policy 0, policy_version 246187 (0.0011) -[2023-11-28 06:39:30,507][87426] Updated weights for policy 1, policy_version 245940 (0.0009) -[2023-11-28 06:39:30,640][87424] Updated weights for policy 0, policy_version 246197 (0.0010) -[2023-11-28 06:39:30,887][87426] Updated weights for policy 1, policy_version 245950 (0.0013) -[2023-11-28 06:39:31,031][87424] Updated weights for policy 0, policy_version 246207 (0.0012) -[2023-11-28 06:39:32,908][87426] Updated weights for policy 1, policy_version 245960 (0.0008) -[2023-11-28 06:39:33,284][87424] Updated weights for policy 0, policy_version 246217 (0.0011) -[2023-11-28 06:39:33,293][87426] Updated weights for policy 1, policy_version 245970 (0.0008) -[2023-11-28 06:39:33,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 125992960. Throughput: 0: 2690.1, 1: 2758.7. Samples: 126013068. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:33,446][86177] Avg episode reward: [(0, '-522.680'), (1, '-529.250')] -[2023-11-28 06:39:33,664][87424] Updated weights for policy 0, policy_version 246227 (0.0012) -[2023-11-28 06:39:33,671][87426] Updated weights for policy 1, policy_version 245980 (0.0011) -[2023-11-28 06:39:34,045][87424] Updated weights for policy 0, policy_version 246237 (0.0012) -[2023-11-28 06:39:35,845][87424] Updated weights for policy 0, policy_version 246247 (0.0012) -[2023-11-28 06:39:35,910][87426] Updated weights for policy 1, policy_version 245990 (0.0010) -[2023-11-28 06:39:36,235][87424] Updated weights for policy 0, policy_version 246257 (0.0012) -[2023-11-28 06:39:36,277][87426] Updated weights for policy 1, policy_version 246000 (0.0007) -[2023-11-28 06:39:36,616][87424] Updated weights for policy 0, policy_version 246267 (0.0012) -[2023-11-28 06:39:36,654][87426] Updated weights for policy 1, policy_version 246010 (0.0008) -[2023-11-28 06:39:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 126025728. Throughput: 0: 2707.2, 1: 2765.6. Samples: 126045616. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:38,445][86177] Avg episode reward: [(0, '-531.470'), (1, '-543.300')] -[2023-11-28 06:39:38,627][87424] Updated weights for policy 0, policy_version 246277 (0.0011) -[2023-11-28 06:39:39,015][87424] Updated weights for policy 0, policy_version 246287 (0.0012) -[2023-11-28 06:39:39,087][87426] Updated weights for policy 1, policy_version 246020 (0.0011) -[2023-11-28 06:39:39,396][87424] Updated weights for policy 0, policy_version 246297 (0.0012) -[2023-11-28 06:39:39,468][87426] Updated weights for policy 1, policy_version 246030 (0.0012) -[2023-11-28 06:39:39,839][87426] Updated weights for policy 1, policy_version 246040 (0.0011) -[2023-11-28 06:39:41,279][87424] Updated weights for policy 0, policy_version 246307 (0.0010) -[2023-11-28 06:39:41,657][87424] Updated weights for policy 0, policy_version 246317 (0.0009) -[2023-11-28 06:39:41,884][87426] Updated weights for policy 1, policy_version 246050 (0.0010) -[2023-11-28 06:39:42,043][87424] Updated weights for policy 0, policy_version 246327 (0.0010) -[2023-11-28 06:39:42,257][87426] Updated weights for policy 1, policy_version 246060 (0.0009) -[2023-11-28 06:39:42,641][87426] Updated weights for policy 1, policy_version 246070 (0.0009) -[2023-11-28 06:39:43,019][87426] Updated weights for policy 1, policy_version 246080 (0.0012) -[2023-11-28 06:39:43,444][86177] Fps is (10 sec: 6553.9, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 126058496. Throughput: 0: 2687.2, 1: 2752.4. Samples: 126069668. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:43,445][86177] Avg episode reward: [(0, '-530.370'), (1, '-546.050')] -[2023-11-28 06:39:44,445][87424] Updated weights for policy 0, policy_version 246337 (0.0011) -[2023-11-28 06:39:44,826][87424] Updated weights for policy 0, policy_version 246347 (0.0008) -[2023-11-28 06:39:45,125][87426] Updated weights for policy 1, policy_version 246090 (0.0012) -[2023-11-28 06:39:45,204][87424] Updated weights for policy 0, policy_version 246357 (0.0012) -[2023-11-28 06:39:45,501][87426] Updated weights for policy 1, policy_version 246100 (0.0012) -[2023-11-28 06:39:45,586][87424] Updated weights for policy 0, policy_version 246367 (0.0009) -[2023-11-28 06:39:45,882][87426] Updated weights for policy 1, policy_version 246110 (0.0008) -[2023-11-28 06:39:47,542][87424] Updated weights for policy 0, policy_version 246377 (0.0008) -[2023-11-28 06:39:47,833][87426] Updated weights for policy 1, policy_version 246120 (0.0011) -[2023-11-28 06:39:47,917][87424] Updated weights for policy 0, policy_version 246387 (0.0011) -[2023-11-28 06:39:48,221][87426] Updated weights for policy 1, policy_version 246130 (0.0008) -[2023-11-28 06:39:48,299][87424] Updated weights for policy 0, policy_version 246397 (0.0011) -[2023-11-28 06:39:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 126083072. Throughput: 0: 2675.9, 1: 2755.2. Samples: 126093932. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:48,445][86177] Avg episode reward: [(0, '-510.820'), (1, '-532.760')] -[2023-11-28 06:39:48,599][87426] Updated weights for policy 1, policy_version 246140 (0.0011) -[2023-11-28 06:39:50,872][87424] Updated weights for policy 0, policy_version 246407 (0.0009) -[2023-11-28 06:39:50,990][87426] Updated weights for policy 1, policy_version 246150 (0.0010) -[2023-11-28 06:39:51,251][87424] Updated weights for policy 0, policy_version 246417 (0.0008) -[2023-11-28 06:39:51,374][87426] Updated weights for policy 1, policy_version 246160 (0.0011) -[2023-11-28 06:39:51,638][87424] Updated weights for policy 0, policy_version 246427 (0.0010) -[2023-11-28 06:39:51,750][87426] Updated weights for policy 1, policy_version 246170 (0.0013) -[2023-11-28 06:39:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 126107648. Throughput: 0: 2655.6, 1: 2751.8. Samples: 126124624. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:53,445][86177] Avg episode reward: [(0, '-511.610'), (1, '-529.870')] -[2023-11-28 06:39:53,689][87424] Updated weights for policy 0, policy_version 246437 (0.0011) -[2023-11-28 06:39:53,837][87426] Updated weights for policy 1, policy_version 246180 (0.0012) -[2023-11-28 06:39:54,070][87424] Updated weights for policy 0, policy_version 246447 (0.0011) -[2023-11-28 06:39:54,217][87426] Updated weights for policy 1, policy_version 246190 (0.0011) -[2023-11-28 06:39:54,450][87424] Updated weights for policy 0, policy_version 246457 (0.0012) -[2023-11-28 06:39:54,599][87426] Updated weights for policy 1, policy_version 246200 (0.0012) -[2023-11-28 06:39:56,871][87426] Updated weights for policy 1, policy_version 246210 (0.0012) -[2023-11-28 06:39:56,988][87424] Updated weights for policy 0, policy_version 246467 (0.0009) -[2023-11-28 06:39:57,250][87426] Updated weights for policy 1, policy_version 246220 (0.0012) -[2023-11-28 06:39:57,367][87424] Updated weights for policy 0, policy_version 246477 (0.0007) -[2023-11-28 06:39:57,634][87426] Updated weights for policy 1, policy_version 246230 (0.0012) -[2023-11-28 06:39:57,746][87424] Updated weights for policy 0, policy_version 246487 (0.0011) -[2023-11-28 06:39:58,003][87426] Updated weights for policy 1, policy_version 246240 (0.0012) -[2023-11-28 06:39:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 126140416. Throughput: 0: 2656.0, 1: 2774.2. Samples: 126148932. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:39:58,445][86177] Avg episode reward: [(0, '-499.490'), (1, '-533.940')] -[2023-11-28 06:39:59,957][87426] Updated weights for policy 1, policy_version 246250 (0.0011) -[2023-11-28 06:40:00,050][87424] Updated weights for policy 0, policy_version 246497 (0.0011) -[2023-11-28 06:40:00,328][87426] Updated weights for policy 1, policy_version 246260 (0.0012) -[2023-11-28 06:40:00,434][87424] Updated weights for policy 0, policy_version 246507 (0.0010) -[2023-11-28 06:40:00,708][87426] Updated weights for policy 1, policy_version 246270 (0.0011) -[2023-11-28 06:40:00,808][87424] Updated weights for policy 0, policy_version 246517 (0.0008) -[2023-11-28 06:40:01,185][87424] Updated weights for policy 0, policy_version 246527 (0.0008) -[2023-11-28 06:40:03,114][87426] Updated weights for policy 1, policy_version 246280 (0.0012) -[2023-11-28 06:40:03,155][87424] Updated weights for policy 0, policy_version 246537 (0.0008) -[2023-11-28 06:40:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 126156800. Throughput: 0: 2666.3, 1: 2749.9. Samples: 126173536. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:40:03,446][86177] Avg episode reward: [(0, '-504.050'), (1, '-541.550')] -[2023-11-28 06:40:03,503][87426] Updated weights for policy 1, policy_version 246290 (0.0011) -[2023-11-28 06:40:03,538][87424] Updated weights for policy 0, policy_version 246547 (0.0008) -[2023-11-28 06:40:03,878][87426] Updated weights for policy 1, policy_version 246300 (0.0010) -[2023-11-28 06:40:03,921][87424] Updated weights for policy 0, policy_version 246557 (0.0007) -[2023-11-28 06:40:06,341][87424] Updated weights for policy 0, policy_version 246567 (0.0010) -[2023-11-28 06:40:06,434][87426] Updated weights for policy 1, policy_version 246310 (0.0009) -[2023-11-28 06:40:06,721][87424] Updated weights for policy 0, policy_version 246577 (0.0012) -[2023-11-28 06:40:06,807][87426] Updated weights for policy 1, policy_version 246320 (0.0009) -[2023-11-28 06:40:07,096][87424] Updated weights for policy 0, policy_version 246587 (0.0010) -[2023-11-28 06:40:07,190][87426] Updated weights for policy 1, policy_version 246330 (0.0010) -[2023-11-28 06:40:08,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 126189568. Throughput: 0: 2684.5, 1: 2702.1. Samples: 126204508. Policy #0 lag: (min: 31.0, avg: 41.3, max: 63.0) -[2023-11-28 06:40:08,446][86177] Avg episode reward: [(0, '-505.810'), (1, '-537.190')] -[2023-11-28 06:40:08,985][87424] Updated weights for policy 0, policy_version 246597 (0.0011) -[2023-11-28 06:40:09,358][87424] Updated weights for policy 0, policy_version 246607 (0.0011) -[2023-11-28 06:40:09,725][87426] Updated weights for policy 1, policy_version 246340 (0.0008) -[2023-11-28 06:40:09,743][87424] Updated weights for policy 0, policy_version 246617 (0.0011) -[2023-11-28 06:40:10,101][87426] Updated weights for policy 1, policy_version 246350 (0.0011) -[2023-11-28 06:40:10,477][87426] Updated weights for policy 1, policy_version 246360 (0.0012) -[2023-11-28 06:40:12,009][87424] Updated weights for policy 0, policy_version 246627 (0.0012) -[2023-11-28 06:40:12,386][87424] Updated weights for policy 0, policy_version 246637 (0.0012) -[2023-11-28 06:40:12,447][87426] Updated weights for policy 1, policy_version 246370 (0.0011) -[2023-11-28 06:40:12,761][87424] Updated weights for policy 0, policy_version 246647 (0.0012) -[2023-11-28 06:40:12,825][87426] Updated weights for policy 1, policy_version 246380 (0.0009) -[2023-11-28 06:40:13,206][87426] Updated weights for policy 1, policy_version 246390 (0.0009) -[2023-11-28 06:40:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 126214144. Throughput: 0: 2706.4, 1: 2657.8. Samples: 126229216. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:13,445][86177] Avg episode reward: [(0, '-512.660'), (1, '-540.290')] -[2023-11-28 06:40:13,583][87426] Updated weights for policy 1, policy_version 246400 (0.0009) -[2023-11-28 06:40:14,986][87424] Updated weights for policy 0, policy_version 246657 (0.0010) -[2023-11-28 06:40:15,363][87424] Updated weights for policy 0, policy_version 246667 (0.0012) -[2023-11-28 06:40:15,589][87426] Updated weights for policy 1, policy_version 246410 (0.0010) -[2023-11-28 06:40:15,745][87424] Updated weights for policy 0, policy_version 246677 (0.0010) -[2023-11-28 06:40:15,963][87426] Updated weights for policy 1, policy_version 246420 (0.0011) -[2023-11-28 06:40:16,126][87424] Updated weights for policy 0, policy_version 246687 (0.0011) -[2023-11-28 06:40:16,347][87426] Updated weights for policy 1, policy_version 246430 (0.0011) -[2023-11-28 06:40:18,178][87426] Updated weights for policy 1, policy_version 246440 (0.0012) -[2023-11-28 06:40:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 126238720. Throughput: 0: 2685.8, 1: 2662.4. Samples: 126253736. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:18,446][86177] Avg episode reward: [(0, '-520.780'), (1, '-514.460')] -[2023-11-28 06:40:18,556][87426] Updated weights for policy 1, policy_version 246450 (0.0011) -[2023-11-28 06:40:18,574][87424] Updated weights for policy 0, policy_version 246697 (0.0012) -[2023-11-28 06:40:18,934][87426] Updated weights for policy 1, policy_version 246460 (0.0010) -[2023-11-28 06:40:18,958][87424] Updated weights for policy 0, policy_version 246707 (0.0011) -[2023-11-28 06:40:19,084][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000246464_63094784.pth... -[2023-11-28 06:40:19,115][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000243904_62439424.pth -[2023-11-28 06:40:19,337][87424] Updated weights for policy 0, policy_version 246717 (0.0008) -[2023-11-28 06:40:19,450][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000246720_63160320.pth... -[2023-11-28 06:40:19,494][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000244192_62513152.pth -[2023-11-28 06:40:21,536][87426] Updated weights for policy 1, policy_version 246470 (0.0010) -[2023-11-28 06:40:21,910][87424] Updated weights for policy 0, policy_version 246727 (0.0009) -[2023-11-28 06:40:21,916][87426] Updated weights for policy 1, policy_version 246480 (0.0009) -[2023-11-28 06:40:22,289][87426] Updated weights for policy 1, policy_version 246490 (0.0012) -[2023-11-28 06:40:22,292][87424] Updated weights for policy 0, policy_version 246737 (0.0011) -[2023-11-28 06:40:22,677][87424] Updated weights for policy 0, policy_version 246747 (0.0011) -[2023-11-28 06:40:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 126271488. Throughput: 0: 2650.5, 1: 2683.6. Samples: 126285652. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:23,445][86177] Avg episode reward: [(0, '-542.960'), (1, '-502.470')] -[2023-11-28 06:40:24,311][87426] Updated weights for policy 1, policy_version 246500 (0.0010) -[2023-11-28 06:40:24,686][87426] Updated weights for policy 1, policy_version 246510 (0.0012) -[2023-11-28 06:40:24,803][87424] Updated weights for policy 0, policy_version 246757 (0.0011) -[2023-11-28 06:40:25,067][87426] Updated weights for policy 1, policy_version 246520 (0.0010) -[2023-11-28 06:40:25,183][87424] Updated weights for policy 0, policy_version 246767 (0.0011) -[2023-11-28 06:40:25,564][87424] Updated weights for policy 0, policy_version 246777 (0.0010) -[2023-11-28 06:40:27,080][87426] Updated weights for policy 1, policy_version 246530 (0.0008) -[2023-11-28 06:40:27,451][87426] Updated weights for policy 1, policy_version 246540 (0.0012) -[2023-11-28 06:40:27,561][87424] Updated weights for policy 0, policy_version 246787 (0.0012) -[2023-11-28 06:40:27,826][87426] Updated weights for policy 1, policy_version 246550 (0.0008) -[2023-11-28 06:40:27,936][87424] Updated weights for policy 0, policy_version 246797 (0.0010) -[2023-11-28 06:40:28,199][87426] Updated weights for policy 1, policy_version 246560 (0.0007) -[2023-11-28 06:40:28,317][87424] Updated weights for policy 0, policy_version 246807 (0.0011) -[2023-11-28 06:40:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 126296064. Throughput: 0: 2664.4, 1: 2706.3. Samples: 126311348. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:28,445][86177] Avg episode reward: [(0, '-542.750'), (1, '-503.710')] -[2023-11-28 06:40:30,054][87424] Updated weights for policy 0, policy_version 246817 (0.0011) -[2023-11-28 06:40:30,445][87424] Updated weights for policy 0, policy_version 246827 (0.0011) -[2023-11-28 06:40:30,510][87426] Updated weights for policy 1, policy_version 246570 (0.0009) -[2023-11-28 06:40:30,823][87424] Updated weights for policy 0, policy_version 246837 (0.0011) -[2023-11-28 06:40:30,893][87426] Updated weights for policy 1, policy_version 246580 (0.0007) -[2023-11-28 06:40:31,202][87424] Updated weights for policy 0, policy_version 246847 (0.0012) -[2023-11-28 06:40:31,276][87426] Updated weights for policy 1, policy_version 246590 (0.0007) -[2023-11-28 06:40:33,208][87424] Updated weights for policy 0, policy_version 246857 (0.0011) -[2023-11-28 06:40:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 126320640. Throughput: 0: 2707.7, 1: 2689.4. Samples: 126336804. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:33,445][86177] Avg episode reward: [(0, '-525.670'), (1, '-500.940')] -[2023-11-28 06:40:33,468][87426] Updated weights for policy 1, policy_version 246600 (0.0008) -[2023-11-28 06:40:33,585][87424] Updated weights for policy 0, policy_version 246867 (0.0009) -[2023-11-28 06:40:33,846][87426] Updated weights for policy 1, policy_version 246610 (0.0007) -[2023-11-28 06:40:33,961][87424] Updated weights for policy 0, policy_version 246877 (0.0010) -[2023-11-28 06:40:34,224][87426] Updated weights for policy 1, policy_version 246620 (0.0007) -[2023-11-28 06:40:35,785][87424] Updated weights for policy 0, policy_version 246887 (0.0010) -[2023-11-28 06:40:36,180][87424] Updated weights for policy 0, policy_version 246897 (0.0008) -[2023-11-28 06:40:36,447][87426] Updated weights for policy 1, policy_version 246630 (0.0009) -[2023-11-28 06:40:36,567][87424] Updated weights for policy 0, policy_version 246907 (0.0011) -[2023-11-28 06:40:36,823][87426] Updated weights for policy 1, policy_version 246640 (0.0011) -[2023-11-28 06:40:37,206][87426] Updated weights for policy 1, policy_version 246650 (0.0012) -[2023-11-28 06:40:38,375][87424] Updated weights for policy 0, policy_version 246917 (0.0010) -[2023-11-28 06:40:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 126353408. Throughput: 0: 2754.4, 1: 2701.0. Samples: 126370116. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:38,445][86177] Avg episode reward: [(0, '-524.700'), (1, '-499.460')] -[2023-11-28 06:40:38,765][87424] Updated weights for policy 0, policy_version 246927 (0.0012) -[2023-11-28 06:40:39,141][87424] Updated weights for policy 0, policy_version 246937 (0.0009) -[2023-11-28 06:40:39,526][87426] Updated weights for policy 1, policy_version 246660 (0.0012) -[2023-11-28 06:40:39,896][87426] Updated weights for policy 1, policy_version 246670 (0.0011) -[2023-11-28 06:40:40,280][87426] Updated weights for policy 1, policy_version 246680 (0.0011) -[2023-11-28 06:40:41,426][87424] Updated weights for policy 0, policy_version 246947 (0.0009) -[2023-11-28 06:40:41,807][87424] Updated weights for policy 0, policy_version 246957 (0.0010) -[2023-11-28 06:40:42,186][87424] Updated weights for policy 0, policy_version 246967 (0.0009) -[2023-11-28 06:40:42,654][87426] Updated weights for policy 1, policy_version 246690 (0.0011) -[2023-11-28 06:40:43,034][87426] Updated weights for policy 1, policy_version 246700 (0.0012) -[2023-11-28 06:40:43,414][87426] Updated weights for policy 1, policy_version 246710 (0.0012) -[2023-11-28 06:40:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 126377984. Throughput: 0: 2770.3, 1: 2685.1. Samples: 126394424. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:43,445][86177] Avg episode reward: [(0, '-498.990'), (1, '-497.770')] -[2023-11-28 06:40:43,787][87426] Updated weights for policy 1, policy_version 246720 (0.0010) -[2023-11-28 06:40:44,130][87424] Updated weights for policy 0, policy_version 246977 (0.0012) -[2023-11-28 06:40:44,510][87424] Updated weights for policy 0, policy_version 246987 (0.0010) -[2023-11-28 06:40:44,887][87424] Updated weights for policy 0, policy_version 246997 (0.0008) -[2023-11-28 06:40:45,272][87424] Updated weights for policy 0, policy_version 247007 (0.0008) -[2023-11-28 06:40:45,637][87426] Updated weights for policy 1, policy_version 246730 (0.0010) -[2023-11-28 06:40:46,017][87426] Updated weights for policy 1, policy_version 246740 (0.0008) -[2023-11-28 06:40:46,390][87426] Updated weights for policy 1, policy_version 246750 (0.0007) -[2023-11-28 06:40:47,757][87424] Updated weights for policy 0, policy_version 247017 (0.0009) -[2023-11-28 06:40:48,141][87424] Updated weights for policy 0, policy_version 247027 (0.0010) -[2023-11-28 06:40:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 126402560. Throughput: 0: 2753.5, 1: 2701.1. Samples: 126418992. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:48,445][86177] Avg episode reward: [(0, '-498.040'), (1, '-510.790')] -[2023-11-28 06:40:48,517][87424] Updated weights for policy 0, policy_version 247037 (0.0008) -[2023-11-28 06:40:48,541][87426] Updated weights for policy 1, policy_version 246760 (0.0010) -[2023-11-28 06:40:48,914][87426] Updated weights for policy 1, policy_version 246770 (0.0009) -[2023-11-28 06:40:49,291][87426] Updated weights for policy 1, policy_version 246780 (0.0012) -[2023-11-28 06:40:50,730][87424] Updated weights for policy 0, policy_version 247047 (0.0010) -[2023-11-28 06:40:51,111][87424] Updated weights for policy 0, policy_version 247057 (0.0012) -[2023-11-28 06:40:51,494][87424] Updated weights for policy 0, policy_version 247067 (0.0012) -[2023-11-28 06:40:51,585][87426] Updated weights for policy 1, policy_version 246790 (0.0011) -[2023-11-28 06:40:51,954][87426] Updated weights for policy 1, policy_version 246800 (0.0012) -[2023-11-28 06:40:52,336][87426] Updated weights for policy 1, policy_version 246810 (0.0012) -[2023-11-28 06:40:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 126435328. Throughput: 0: 2757.6, 1: 2736.5. Samples: 126451744. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:53,445][86177] Avg episode reward: [(0, '-520.650'), (1, '-507.390')] -[2023-11-28 06:40:54,020][87424] Updated weights for policy 0, policy_version 247077 (0.0011) -[2023-11-28 06:40:54,399][87424] Updated weights for policy 0, policy_version 247087 (0.0008) -[2023-11-28 06:40:54,579][87426] Updated weights for policy 1, policy_version 246820 (0.0012) -[2023-11-28 06:40:54,782][87424] Updated weights for policy 0, policy_version 247097 (0.0010) -[2023-11-28 06:40:54,952][87426] Updated weights for policy 1, policy_version 246830 (0.0012) -[2023-11-28 06:40:55,335][87426] Updated weights for policy 1, policy_version 246840 (0.0007) -[2023-11-28 06:40:56,639][87424] Updated weights for policy 0, policy_version 247107 (0.0012) -[2023-11-28 06:40:57,013][87424] Updated weights for policy 0, policy_version 247117 (0.0011) -[2023-11-28 06:40:57,388][87424] Updated weights for policy 0, policy_version 247127 (0.0012) -[2023-11-28 06:40:57,496][87426] Updated weights for policy 1, policy_version 246850 (0.0008) -[2023-11-28 06:40:57,883][87426] Updated weights for policy 1, policy_version 246860 (0.0011) -[2023-11-28 06:40:58,266][87426] Updated weights for policy 1, policy_version 246870 (0.0012) -[2023-11-28 06:40:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 126459904. Throughput: 0: 2736.1, 1: 2770.5. Samples: 126477012. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:40:58,445][86177] Avg episode reward: [(0, '-520.820'), (1, '-512.060')] -[2023-11-28 06:40:58,639][87426] Updated weights for policy 1, policy_version 246880 (0.0012) -[2023-11-28 06:40:59,696][87424] Updated weights for policy 0, policy_version 247137 (0.0012) -[2023-11-28 06:41:00,070][87424] Updated weights for policy 0, policy_version 247147 (0.0009) -[2023-11-28 06:41:00,459][87424] Updated weights for policy 0, policy_version 247157 (0.0010) -[2023-11-28 06:41:00,735][87426] Updated weights for policy 1, policy_version 246890 (0.0009) -[2023-11-28 06:41:00,843][87424] Updated weights for policy 0, policy_version 247167 (0.0008) -[2023-11-28 06:41:01,123][87426] Updated weights for policy 1, policy_version 246900 (0.0010) -[2023-11-28 06:41:01,495][87426] Updated weights for policy 1, policy_version 246910 (0.0012) -[2023-11-28 06:41:02,963][87424] Updated weights for policy 0, policy_version 247177 (0.0011) -[2023-11-28 06:41:03,354][87424] Updated weights for policy 0, policy_version 247187 (0.0011) -[2023-11-28 06:41:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 126484480. Throughput: 0: 2764.5, 1: 2752.3. Samples: 126501988. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:41:03,445][86177] Avg episode reward: [(0, '-522.330'), (1, '-506.400')] -[2023-11-28 06:41:03,625][87426] Updated weights for policy 1, policy_version 246920 (0.0008) -[2023-11-28 06:41:03,731][87424] Updated weights for policy 0, policy_version 247197 (0.0010) -[2023-11-28 06:41:04,004][87426] Updated weights for policy 1, policy_version 246930 (0.0008) -[2023-11-28 06:41:04,379][87426] Updated weights for policy 1, policy_version 246940 (0.0007) -[2023-11-28 06:41:06,161][87424] Updated weights for policy 0, policy_version 247207 (0.0007) -[2023-11-28 06:41:06,552][87424] Updated weights for policy 0, policy_version 247217 (0.0007) -[2023-11-28 06:41:06,572][87426] Updated weights for policy 1, policy_version 246950 (0.0009) -[2023-11-28 06:41:06,925][87424] Updated weights for policy 0, policy_version 247227 (0.0011) -[2023-11-28 06:41:06,946][87426] Updated weights for policy 1, policy_version 246960 (0.0010) -[2023-11-28 06:41:07,325][87426] Updated weights for policy 1, policy_version 246970 (0.0012) -[2023-11-28 06:41:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 126517248. Throughput: 0: 2770.5, 1: 2733.1. Samples: 126533312. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:41:08,445][86177] Avg episode reward: [(0, '-522.010'), (1, '-499.790')] -[2023-11-28 06:41:09,310][87424] Updated weights for policy 0, policy_version 247237 (0.0011) -[2023-11-28 06:41:09,434][87426] Updated weights for policy 1, policy_version 246980 (0.0010) -[2023-11-28 06:41:09,692][87424] Updated weights for policy 0, policy_version 247247 (0.0008) -[2023-11-28 06:41:09,812][87426] Updated weights for policy 1, policy_version 246990 (0.0008) -[2023-11-28 06:41:10,089][87424] Updated weights for policy 0, policy_version 247257 (0.0010) -[2023-11-28 06:41:10,189][87426] Updated weights for policy 1, policy_version 247000 (0.0010) -[2023-11-28 06:41:12,571][87424] Updated weights for policy 0, policy_version 247267 (0.0010) -[2023-11-28 06:41:12,651][87426] Updated weights for policy 1, policy_version 247010 (0.0011) -[2023-11-28 06:41:12,949][87424] Updated weights for policy 0, policy_version 247277 (0.0009) -[2023-11-28 06:41:13,019][87426] Updated weights for policy 1, policy_version 247020 (0.0010) -[2023-11-28 06:41:13,332][87424] Updated weights for policy 0, policy_version 247287 (0.0012) -[2023-11-28 06:41:13,395][87426] Updated weights for policy 1, policy_version 247030 (0.0009) -[2023-11-28 06:41:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 126533632. Throughput: 0: 2740.3, 1: 2712.9. Samples: 126556740. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:41:13,445][86177] Avg episode reward: [(0, '-501.630'), (1, '-503.370')] -[2023-11-28 06:41:13,779][87426] Updated weights for policy 1, policy_version 247040 (0.0007) -[2023-11-28 06:41:15,111][87424] Updated weights for policy 0, policy_version 247297 (0.0012) -[2023-11-28 06:41:15,486][87424] Updated weights for policy 0, policy_version 247307 (0.0012) -[2023-11-28 06:41:15,874][87424] Updated weights for policy 0, policy_version 247317 (0.0012) -[2023-11-28 06:41:15,940][87426] Updated weights for policy 1, policy_version 247050 (0.0012) -[2023-11-28 06:41:16,265][87424] Updated weights for policy 0, policy_version 247327 (0.0012) -[2023-11-28 06:41:16,314][87426] Updated weights for policy 1, policy_version 247060 (0.0011) -[2023-11-28 06:41:16,691][87426] Updated weights for policy 1, policy_version 247070 (0.0012) -[2023-11-28 06:41:18,201][87424] Updated weights for policy 0, policy_version 247337 (0.0012) -[2023-11-28 06:41:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 126566400. Throughput: 0: 2709.1, 1: 2725.6. Samples: 126581368. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:41:18,445][86177] Avg episode reward: [(0, '-500.250'), (1, '-520.670')] -[2023-11-28 06:41:18,576][87424] Updated weights for policy 0, policy_version 247347 (0.0008) -[2023-11-28 06:41:18,632][87426] Updated weights for policy 1, policy_version 247080 (0.0011) -[2023-11-28 06:41:18,959][87424] Updated weights for policy 0, policy_version 247357 (0.0008) -[2023-11-28 06:41:19,010][87426] Updated weights for policy 1, policy_version 247090 (0.0012) -[2023-11-28 06:41:19,391][87426] Updated weights for policy 1, policy_version 247100 (0.0011) -[2023-11-28 06:41:21,282][87424] Updated weights for policy 0, policy_version 247367 (0.0011) -[2023-11-28 06:41:21,361][87426] Updated weights for policy 1, policy_version 247110 (0.0011) -[2023-11-28 06:41:21,657][87424] Updated weights for policy 0, policy_version 247377 (0.0011) -[2023-11-28 06:41:21,740][87426] Updated weights for policy 1, policy_version 247120 (0.0011) -[2023-11-28 06:41:22,032][87424] Updated weights for policy 0, policy_version 247387 (0.0009) -[2023-11-28 06:41:22,116][87426] Updated weights for policy 1, policy_version 247130 (0.0009) -[2023-11-28 06:41:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 126599168. Throughput: 0: 2683.6, 1: 2734.1. Samples: 126613912. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:41:23,445][86177] Avg episode reward: [(0, '-498.070'), (1, '-521.480')] -[2023-11-28 06:41:24,289][87424] Updated weights for policy 0, policy_version 247397 (0.0010) -[2023-11-28 06:41:24,538][87426] Updated weights for policy 1, policy_version 247140 (0.0011) -[2023-11-28 06:41:24,675][87424] Updated weights for policy 0, policy_version 247407 (0.0012) -[2023-11-28 06:41:24,913][87426] Updated weights for policy 1, policy_version 247150 (0.0008) -[2023-11-28 06:41:25,055][87424] Updated weights for policy 0, policy_version 247417 (0.0010) -[2023-11-28 06:41:25,295][87426] Updated weights for policy 1, policy_version 247160 (0.0010) -[2023-11-28 06:41:26,807][87424] Updated weights for policy 0, policy_version 247427 (0.0010) -[2023-11-28 06:41:27,201][87424] Updated weights for policy 0, policy_version 247437 (0.0007) -[2023-11-28 06:41:27,582][87424] Updated weights for policy 0, policy_version 247447 (0.0009) -[2023-11-28 06:41:27,788][87426] Updated weights for policy 1, policy_version 247170 (0.0012) -[2023-11-28 06:41:28,167][87426] Updated weights for policy 1, policy_version 247180 (0.0009) -[2023-11-28 06:41:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 126623744. Throughput: 0: 2704.6, 1: 2730.4. Samples: 126639000. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:41:28,445][86177] Avg episode reward: [(0, '-497.300'), (1, '-520.230')] -[2023-11-28 06:41:28,546][87426] Updated weights for policy 1, policy_version 247190 (0.0007) -[2023-11-28 06:41:28,920][87426] Updated weights for policy 1, policy_version 247200 (0.0008) -[2023-11-28 06:41:30,106][87424] Updated weights for policy 0, policy_version 247457 (0.0012) -[2023-11-28 06:41:30,488][87424] Updated weights for policy 0, policy_version 247467 (0.0012) -[2023-11-28 06:41:30,828][87426] Updated weights for policy 1, policy_version 247210 (0.0010) -[2023-11-28 06:41:30,862][87424] Updated weights for policy 0, policy_version 247477 (0.0010) -[2023-11-28 06:41:31,197][87426] Updated weights for policy 1, policy_version 247220 (0.0009) -[2023-11-28 06:41:31,243][87424] Updated weights for policy 0, policy_version 247487 (0.0008) -[2023-11-28 06:41:31,579][87426] Updated weights for policy 1, policy_version 247230 (0.0008) -[2023-11-28 06:41:33,201][87424] Updated weights for policy 0, policy_version 247497 (0.0011) -[2023-11-28 06:41:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 126648320. Throughput: 0: 2705.8, 1: 2722.5. Samples: 126663264. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:41:33,445][86177] Avg episode reward: [(0, '-504.800'), (1, '-518.150')] -[2023-11-28 06:41:33,584][87424] Updated weights for policy 0, policy_version 247507 (0.0012) -[2023-11-28 06:41:33,791][87426] Updated weights for policy 1, policy_version 247240 (0.0009) -[2023-11-28 06:41:33,958][87424] Updated weights for policy 0, policy_version 247517 (0.0012) -[2023-11-28 06:41:34,175][87426] Updated weights for policy 1, policy_version 247250 (0.0011) -[2023-11-28 06:41:34,547][87426] Updated weights for policy 1, policy_version 247260 (0.0012) -[2023-11-28 06:41:35,777][87424] Updated weights for policy 0, policy_version 247527 (0.0010) -[2023-11-28 06:41:36,157][87424] Updated weights for policy 0, policy_version 247537 (0.0008) -[2023-11-28 06:41:36,535][87424] Updated weights for policy 0, policy_version 247547 (0.0009) -[2023-11-28 06:41:36,700][87426] Updated weights for policy 1, policy_version 247270 (0.0011) -[2023-11-28 06:41:37,077][87426] Updated weights for policy 1, policy_version 247280 (0.0012) -[2023-11-28 06:41:37,460][87426] Updated weights for policy 1, policy_version 247290 (0.0012) -[2023-11-28 06:41:38,243][87424] Updated weights for policy 0, policy_version 247557 (0.0012) -[2023-11-28 06:41:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 126681088. Throughput: 0: 2738.1, 1: 2703.6. Samples: 126696620. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:41:38,445][86177] Avg episode reward: [(0, '-509.380'), (1, '-512.430')] -[2023-11-28 06:41:38,632][87424] Updated weights for policy 0, policy_version 247567 (0.0012) -[2023-11-28 06:41:39,013][87424] Updated weights for policy 0, policy_version 247577 (0.0012) -[2023-11-28 06:41:39,456][87426] Updated weights for policy 1, policy_version 247300 (0.0011) -[2023-11-28 06:41:39,831][87426] Updated weights for policy 1, policy_version 247310 (0.0009) -[2023-11-28 06:41:40,212][87426] Updated weights for policy 1, policy_version 247320 (0.0011) -[2023-11-28 06:41:41,423][87424] Updated weights for policy 0, policy_version 247587 (0.0011) -[2023-11-28 06:41:41,808][87424] Updated weights for policy 0, policy_version 247597 (0.0010) -[2023-11-28 06:41:42,190][87424] Updated weights for policy 0, policy_version 247607 (0.0012) -[2023-11-28 06:41:42,420][87426] Updated weights for policy 1, policy_version 247330 (0.0011) -[2023-11-28 06:41:42,786][87426] Updated weights for policy 1, policy_version 247340 (0.0011) -[2023-11-28 06:41:43,164][87426] Updated weights for policy 1, policy_version 247350 (0.0012) -[2023-11-28 06:41:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 126705664. Throughput: 0: 2746.1, 1: 2690.2. Samples: 126721648. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:41:43,445][86177] Avg episode reward: [(0, '-510.850'), (1, '-513.950')] -[2023-11-28 06:41:43,546][87426] Updated weights for policy 1, policy_version 247360 (0.0012) -[2023-11-28 06:41:44,298][87424] Updated weights for policy 0, policy_version 247617 (0.0012) -[2023-11-28 06:41:44,672][87424] Updated weights for policy 0, policy_version 247627 (0.0008) -[2023-11-28 06:41:45,056][87424] Updated weights for policy 0, policy_version 247637 (0.0012) -[2023-11-28 06:41:45,291][87426] Updated weights for policy 1, policy_version 247370 (0.0011) -[2023-11-28 06:41:45,437][87424] Updated weights for policy 0, policy_version 247647 (0.0010) -[2023-11-28 06:41:45,676][87426] Updated weights for policy 1, policy_version 247380 (0.0011) -[2023-11-28 06:41:46,045][87426] Updated weights for policy 1, policy_version 247390 (0.0011) -[2023-11-28 06:41:47,109][87424] Updated weights for policy 0, policy_version 247657 (0.0012) -[2023-11-28 06:41:47,497][87424] Updated weights for policy 0, policy_version 247667 (0.0009) -[2023-11-28 06:41:47,871][87424] Updated weights for policy 0, policy_version 247677 (0.0008) -[2023-11-28 06:41:48,192][87426] Updated weights for policy 1, policy_version 247400 (0.0009) -[2023-11-28 06:41:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 126738432. Throughput: 0: 2749.3, 1: 2716.4. Samples: 126747948. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:41:48,445][86177] Avg episode reward: [(0, '-508.710'), (1, '-507.020')] -[2023-11-28 06:41:48,566][87426] Updated weights for policy 1, policy_version 247410 (0.0011) -[2023-11-28 06:41:48,942][87426] Updated weights for policy 1, policy_version 247420 (0.0012) -[2023-11-28 06:41:50,380][87424] Updated weights for policy 0, policy_version 247687 (0.0011) -[2023-11-28 06:41:50,758][87424] Updated weights for policy 0, policy_version 247697 (0.0012) -[2023-11-28 06:41:50,933][87426] Updated weights for policy 1, policy_version 247430 (0.0012) -[2023-11-28 06:41:51,135][87424] Updated weights for policy 0, policy_version 247707 (0.0011) -[2023-11-28 06:41:51,313][87426] Updated weights for policy 1, policy_version 247440 (0.0012) -[2023-11-28 06:41:51,692][87426] Updated weights for policy 1, policy_version 247450 (0.0011) -[2023-11-28 06:41:53,443][87424] Updated weights for policy 0, policy_version 247717 (0.0011) -[2023-11-28 06:41:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 126763008. Throughput: 0: 2762.4, 1: 2735.9. Samples: 126780736. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:41:53,445][86177] Avg episode reward: [(0, '-508.050'), (1, '-502.790')] -[2023-11-28 06:41:53,820][87424] Updated weights for policy 0, policy_version 247727 (0.0011) -[2023-11-28 06:41:53,957][87426] Updated weights for policy 1, policy_version 247460 (0.0012) -[2023-11-28 06:41:54,205][87424] Updated weights for policy 0, policy_version 247737 (0.0011) -[2023-11-28 06:41:54,338][87426] Updated weights for policy 1, policy_version 247470 (0.0012) -[2023-11-28 06:41:54,707][87426] Updated weights for policy 1, policy_version 247480 (0.0011) -[2023-11-28 06:41:56,841][87424] Updated weights for policy 0, policy_version 247747 (0.0011) -[2023-11-28 06:41:56,912][87426] Updated weights for policy 1, policy_version 247490 (0.0011) -[2023-11-28 06:41:57,220][87424] Updated weights for policy 0, policy_version 247757 (0.0009) -[2023-11-28 06:41:57,278][87426] Updated weights for policy 1, policy_version 247500 (0.0008) -[2023-11-28 06:41:57,605][87424] Updated weights for policy 0, policy_version 247767 (0.0008) -[2023-11-28 06:41:57,664][87426] Updated weights for policy 1, policy_version 247510 (0.0010) -[2023-11-28 06:41:58,037][87426] Updated weights for policy 1, policy_version 247520 (0.0012) -[2023-11-28 06:41:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 126795776. Throughput: 0: 2760.9, 1: 2766.0. Samples: 126805452. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:41:58,445][86177] Avg episode reward: [(0, '-505.080'), (1, '-497.920')] -[2023-11-28 06:41:59,635][87424] Updated weights for policy 0, policy_version 247777 (0.0008) -[2023-11-28 06:42:00,021][87424] Updated weights for policy 0, policy_version 247787 (0.0009) -[2023-11-28 06:42:00,051][87426] Updated weights for policy 1, policy_version 247530 (0.0011) -[2023-11-28 06:42:00,403][87424] Updated weights for policy 0, policy_version 247797 (0.0009) -[2023-11-28 06:42:00,429][87426] Updated weights for policy 1, policy_version 247540 (0.0010) -[2023-11-28 06:42:00,784][87424] Updated weights for policy 0, policy_version 247807 (0.0009) -[2023-11-28 06:42:00,813][87426] Updated weights for policy 1, policy_version 247550 (0.0007) -[2023-11-28 06:42:02,665][87424] Updated weights for policy 0, policy_version 247817 (0.0008) -[2023-11-28 06:42:02,843][87426] Updated weights for policy 1, policy_version 247560 (0.0010) -[2023-11-28 06:42:03,048][87424] Updated weights for policy 0, policy_version 247827 (0.0009) -[2023-11-28 06:42:03,227][87426] Updated weights for policy 1, policy_version 247570 (0.0012) -[2023-11-28 06:42:03,428][87424] Updated weights for policy 0, policy_version 247837 (0.0011) -[2023-11-28 06:42:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 126812160. Throughput: 0: 2781.9, 1: 2783.9. Samples: 126831828. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:42:03,445][86177] Avg episode reward: [(0, '-502.970'), (1, '-499.190')] -[2023-11-28 06:42:03,599][87426] Updated weights for policy 1, policy_version 247580 (0.0011) -[2023-11-28 06:42:05,297][87426] Updated weights for policy 1, policy_version 247590 (0.0011) -[2023-11-28 06:42:05,313][87424] Updated weights for policy 0, policy_version 247847 (0.0011) -[2023-11-28 06:42:05,671][87426] Updated weights for policy 1, policy_version 247600 (0.0012) -[2023-11-28 06:42:05,695][87424] Updated weights for policy 0, policy_version 247857 (0.0011) -[2023-11-28 06:42:06,045][87426] Updated weights for policy 1, policy_version 247610 (0.0011) -[2023-11-28 06:42:06,094][87424] Updated weights for policy 0, policy_version 247867 (0.0012) -[2023-11-28 06:42:07,986][87424] Updated weights for policy 0, policy_version 247877 (0.0009) -[2023-11-28 06:42:08,366][87424] Updated weights for policy 0, policy_version 247887 (0.0009) -[2023-11-28 06:42:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 126844928. Throughput: 0: 2818.9, 1: 2779.5. Samples: 126865840. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:42:08,445][86177] Avg episode reward: [(0, '-504.050'), (1, '-503.140')] -[2023-11-28 06:42:08,508][87426] Updated weights for policy 1, policy_version 247620 (0.0011) -[2023-11-28 06:42:08,751][87424] Updated weights for policy 0, policy_version 247897 (0.0011) -[2023-11-28 06:42:08,890][87426] Updated weights for policy 1, policy_version 247630 (0.0009) -[2023-11-28 06:42:09,269][87426] Updated weights for policy 1, policy_version 247640 (0.0011) -[2023-11-28 06:42:11,098][87424] Updated weights for policy 0, policy_version 247907 (0.0010) -[2023-11-28 06:42:11,470][87424] Updated weights for policy 0, policy_version 247917 (0.0008) -[2023-11-28 06:42:11,855][87424] Updated weights for policy 0, policy_version 247927 (0.0010) -[2023-11-28 06:42:11,863][87426] Updated weights for policy 1, policy_version 247650 (0.0012) -[2023-11-28 06:42:12,246][87426] Updated weights for policy 1, policy_version 247660 (0.0011) -[2023-11-28 06:42:12,614][87426] Updated weights for policy 1, policy_version 247670 (0.0011) -[2023-11-28 06:42:13,000][87426] Updated weights for policy 1, policy_version 247680 (0.0010) -[2023-11-28 06:42:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5734.4, 300 sec: 5470.6). Total num frames: 126877696. Throughput: 0: 2801.4, 1: 2776.0. Samples: 126889984. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:42:13,445][86177] Avg episode reward: [(0, '-502.550'), (1, '-507.930')] -[2023-11-28 06:42:14,086][87424] Updated weights for policy 0, policy_version 247937 (0.0010) -[2023-11-28 06:42:14,476][87424] Updated weights for policy 0, policy_version 247947 (0.0007) -[2023-11-28 06:42:14,870][87424] Updated weights for policy 0, policy_version 247957 (0.0010) -[2023-11-28 06:42:15,250][87424] Updated weights for policy 0, policy_version 247967 (0.0010) -[2023-11-28 06:42:15,534][87426] Updated weights for policy 1, policy_version 247690 (0.0009) -[2023-11-28 06:42:15,915][87426] Updated weights for policy 1, policy_version 247700 (0.0011) -[2023-11-28 06:42:16,292][87426] Updated weights for policy 1, policy_version 247710 (0.0011) -[2023-11-28 06:42:17,482][87424] Updated weights for policy 0, policy_version 247977 (0.0012) -[2023-11-28 06:42:17,862][87424] Updated weights for policy 0, policy_version 247987 (0.0012) -[2023-11-28 06:42:17,950][87426] Updated weights for policy 1, policy_version 247720 (0.0007) -[2023-11-28 06:42:18,237][87424] Updated weights for policy 0, policy_version 247997 (0.0012) -[2023-11-28 06:42:18,326][87426] Updated weights for policy 1, policy_version 247730 (0.0007) -[2023-11-28 06:42:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 126902272. Throughput: 0: 2785.9, 1: 2773.7. Samples: 126913444. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:42:18,445][86177] Avg episode reward: [(0, '-502.000'), (1, '-503.110')] -[2023-11-28 06:42:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000248000_63488000.pth... -[2023-11-28 06:42:18,497][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000245440_62832640.pth -[2023-11-28 06:42:18,704][87426] Updated weights for policy 1, policy_version 247740 (0.0007) -[2023-11-28 06:42:18,851][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000247744_63422464.pth... -[2023-11-28 06:42:18,896][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000245184_62767104.pth -[2023-11-28 06:42:20,824][87424] Updated weights for policy 0, policy_version 248007 (0.0012) -[2023-11-28 06:42:20,956][87426] Updated weights for policy 1, policy_version 247750 (0.0010) -[2023-11-28 06:42:21,197][87424] Updated weights for policy 0, policy_version 248017 (0.0010) -[2023-11-28 06:42:21,325][87426] Updated weights for policy 1, policy_version 247760 (0.0011) -[2023-11-28 06:42:21,576][87424] Updated weights for policy 0, policy_version 248027 (0.0011) -[2023-11-28 06:42:21,708][87426] Updated weights for policy 1, policy_version 247770 (0.0010) -[2023-11-28 06:42:23,446][86177] Fps is (10 sec: 4914.5, 60 sec: 5461.2, 300 sec: 5442.8). Total num frames: 126926848. Throughput: 0: 2715.0, 1: 2799.0. Samples: 126944760. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:42:23,446][86177] Avg episode reward: [(0, '-502.190'), (1, '-504.060')] -[2023-11-28 06:42:24,102][87424] Updated weights for policy 0, policy_version 248037 (0.0012) -[2023-11-28 06:42:24,116][87426] Updated weights for policy 1, policy_version 247780 (0.0010) -[2023-11-28 06:42:24,487][87424] Updated weights for policy 0, policy_version 248047 (0.0012) -[2023-11-28 06:42:24,493][87426] Updated weights for policy 1, policy_version 247790 (0.0011) -[2023-11-28 06:42:24,862][87424] Updated weights for policy 0, policy_version 248057 (0.0011) -[2023-11-28 06:42:24,880][87426] Updated weights for policy 1, policy_version 247800 (0.0008) -[2023-11-28 06:42:26,698][87424] Updated weights for policy 0, policy_version 248067 (0.0009) -[2023-11-28 06:42:26,862][87426] Updated weights for policy 1, policy_version 247810 (0.0008) -[2023-11-28 06:42:27,074][87424] Updated weights for policy 0, policy_version 248077 (0.0008) -[2023-11-28 06:42:27,238][87426] Updated weights for policy 1, policy_version 247820 (0.0011) -[2023-11-28 06:42:27,463][87424] Updated weights for policy 0, policy_version 248087 (0.0008) -[2023-11-28 06:42:27,625][87426] Updated weights for policy 1, policy_version 247830 (0.0012) -[2023-11-28 06:42:27,996][87426] Updated weights for policy 1, policy_version 247840 (0.0012) -[2023-11-28 06:42:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 126959616. Throughput: 0: 2713.2, 1: 2791.1. Samples: 126969344. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:42:28,445][86177] Avg episode reward: [(0, '-499.320'), (1, '-503.970')] -[2023-11-28 06:42:29,384][87424] Updated weights for policy 0, policy_version 248097 (0.0008) -[2023-11-28 06:42:29,778][87424] Updated weights for policy 0, policy_version 248107 (0.0011) -[2023-11-28 06:42:30,149][87426] Updated weights for policy 1, policy_version 247850 (0.0010) -[2023-11-28 06:42:30,149][87424] Updated weights for policy 0, policy_version 248117 (0.0011) -[2023-11-28 06:42:30,529][87426] Updated weights for policy 1, policy_version 247860 (0.0008) -[2023-11-28 06:42:30,533][87424] Updated weights for policy 0, policy_version 248127 (0.0012) -[2023-11-28 06:42:30,909][87426] Updated weights for policy 1, policy_version 247870 (0.0010) -[2023-11-28 06:42:32,604][87424] Updated weights for policy 0, policy_version 248137 (0.0008) -[2023-11-28 06:42:32,987][87424] Updated weights for policy 0, policy_version 248147 (0.0008) -[2023-11-28 06:42:33,367][87424] Updated weights for policy 0, policy_version 248157 (0.0007) -[2023-11-28 06:42:33,443][87426] Updated weights for policy 1, policy_version 247880 (0.0008) -[2023-11-28 06:42:33,444][86177] Fps is (10 sec: 4915.9, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 126976000. Throughput: 0: 2701.2, 1: 2771.0. Samples: 126994196. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:42:33,445][86177] Avg episode reward: [(0, '-507.570'), (1, '-500.800')] -[2023-11-28 06:42:33,821][87426] Updated weights for policy 1, policy_version 247890 (0.0007) -[2023-11-28 06:42:34,199][87426] Updated weights for policy 1, policy_version 247900 (0.0007) -[2023-11-28 06:42:35,388][87424] Updated weights for policy 0, policy_version 248167 (0.0011) -[2023-11-28 06:42:35,769][87424] Updated weights for policy 0, policy_version 248177 (0.0011) -[2023-11-28 06:42:36,159][87424] Updated weights for policy 0, policy_version 248187 (0.0011) -[2023-11-28 06:42:36,350][87426] Updated weights for policy 1, policy_version 247910 (0.0007) -[2023-11-28 06:42:36,736][87426] Updated weights for policy 1, policy_version 247920 (0.0009) -[2023-11-28 06:42:37,112][87426] Updated weights for policy 1, policy_version 247930 (0.0009) -[2023-11-28 06:42:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127008768. Throughput: 0: 2730.7, 1: 2755.9. Samples: 127027632. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 06:42:38,445][86177] Avg episode reward: [(0, '-512.960'), (1, '-499.590')] -[2023-11-28 06:42:38,561][87424] Updated weights for policy 0, policy_version 248197 (0.0012) -[2023-11-28 06:42:38,947][87424] Updated weights for policy 0, policy_version 248207 (0.0011) -[2023-11-28 06:42:38,973][87426] Updated weights for policy 1, policy_version 247940 (0.0010) -[2023-11-28 06:42:39,336][87424] Updated weights for policy 0, policy_version 248217 (0.0011) -[2023-11-28 06:42:39,356][87426] Updated weights for policy 1, policy_version 247950 (0.0012) -[2023-11-28 06:42:39,745][87426] Updated weights for policy 1, policy_version 247960 (0.0011) -[2023-11-28 06:42:41,571][87424] Updated weights for policy 0, policy_version 248227 (0.0014) -[2023-11-28 06:42:41,952][87424] Updated weights for policy 0, policy_version 248237 (0.0010) -[2023-11-28 06:42:41,987][87426] Updated weights for policy 1, policy_version 247970 (0.0012) -[2023-11-28 06:42:42,335][87424] Updated weights for policy 0, policy_version 248247 (0.0008) -[2023-11-28 06:42:42,360][87426] Updated weights for policy 1, policy_version 247980 (0.0011) -[2023-11-28 06:42:42,744][87426] Updated weights for policy 1, policy_version 247990 (0.0012) -[2023-11-28 06:42:43,128][87426] Updated weights for policy 1, policy_version 248000 (0.0012) -[2023-11-28 06:42:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 127041536. Throughput: 0: 2749.2, 1: 2714.8. Samples: 127051336. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:42:43,445][86177] Avg episode reward: [(0, '-520.650'), (1, '-498.870')] -[2023-11-28 06:42:44,331][87424] Updated weights for policy 0, policy_version 248257 (0.0007) -[2023-11-28 06:42:44,716][87424] Updated weights for policy 0, policy_version 248267 (0.0009) -[2023-11-28 06:42:45,030][87426] Updated weights for policy 1, policy_version 248010 (0.0010) -[2023-11-28 06:42:45,089][87424] Updated weights for policy 0, policy_version 248277 (0.0010) -[2023-11-28 06:42:45,413][87426] Updated weights for policy 1, policy_version 248020 (0.0008) -[2023-11-28 06:42:45,470][87424] Updated weights for policy 0, policy_version 248287 (0.0012) -[2023-11-28 06:42:45,791][87426] Updated weights for policy 1, policy_version 248030 (0.0011) -[2023-11-28 06:42:47,392][87424] Updated weights for policy 0, policy_version 248297 (0.0010) -[2023-11-28 06:42:47,792][87424] Updated weights for policy 0, policy_version 248307 (0.0010) -[2023-11-28 06:42:48,047][87426] Updated weights for policy 1, policy_version 248040 (0.0011) -[2023-11-28 06:42:48,170][87424] Updated weights for policy 0, policy_version 248317 (0.0007) -[2023-11-28 06:42:48,426][87426] Updated weights for policy 1, policy_version 248050 (0.0011) -[2023-11-28 06:42:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 127066112. Throughput: 0: 2740.5, 1: 2720.3. Samples: 127077564. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:42:48,446][86177] Avg episode reward: [(0, '-520.600'), (1, '-499.530')] -[2023-11-28 06:42:48,797][87426] Updated weights for policy 1, policy_version 248060 (0.0011) -[2023-11-28 06:42:50,506][87424] Updated weights for policy 0, policy_version 248327 (0.0010) -[2023-11-28 06:42:50,886][87424] Updated weights for policy 0, policy_version 248337 (0.0011) -[2023-11-28 06:42:50,967][87426] Updated weights for policy 1, policy_version 248070 (0.0012) -[2023-11-28 06:42:51,272][87424] Updated weights for policy 0, policy_version 248347 (0.0012) -[2023-11-28 06:42:51,342][87426] Updated weights for policy 1, policy_version 248080 (0.0010) -[2023-11-28 06:42:51,724][87426] Updated weights for policy 1, policy_version 248090 (0.0010) -[2023-11-28 06:42:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127090688. Throughput: 0: 2701.1, 1: 2748.1. Samples: 127111052. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:42:53,445][86177] Avg episode reward: [(0, '-509.540'), (1, '-498.270')] -[2023-11-28 06:42:53,834][87426] Updated weights for policy 1, policy_version 248100 (0.0011) -[2023-11-28 06:42:53,857][87424] Updated weights for policy 0, policy_version 248357 (0.0011) -[2023-11-28 06:42:54,214][87426] Updated weights for policy 1, policy_version 248110 (0.0008) -[2023-11-28 06:42:54,230][87424] Updated weights for policy 0, policy_version 248367 (0.0011) -[2023-11-28 06:42:54,602][87424] Updated weights for policy 0, policy_version 248377 (0.0008) -[2023-11-28 06:42:54,604][87426] Updated weights for policy 1, policy_version 248120 (0.0007) -[2023-11-28 06:42:56,340][87426] Updated weights for policy 1, policy_version 248130 (0.0008) -[2023-11-28 06:42:56,686][87424] Updated weights for policy 0, policy_version 248387 (0.0010) -[2023-11-28 06:42:56,726][87426] Updated weights for policy 1, policy_version 248140 (0.0011) -[2023-11-28 06:42:57,063][87424] Updated weights for policy 0, policy_version 248397 (0.0011) -[2023-11-28 06:42:57,099][87426] Updated weights for policy 1, policy_version 248150 (0.0011) -[2023-11-28 06:42:57,445][87424] Updated weights for policy 0, policy_version 248407 (0.0009) -[2023-11-28 06:42:57,484][87426] Updated weights for policy 1, policy_version 248160 (0.0008) -[2023-11-28 06:42:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 127123456. Throughput: 0: 2695.7, 1: 2769.0. Samples: 127135896. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:42:58,445][86177] Avg episode reward: [(0, '-503.660'), (1, '-500.760')] -[2023-11-28 06:42:59,477][87424] Updated weights for policy 0, policy_version 248417 (0.0009) -[2023-11-28 06:42:59,726][87426] Updated weights for policy 1, policy_version 248170 (0.0009) -[2023-11-28 06:42:59,872][87424] Updated weights for policy 0, policy_version 248427 (0.0011) -[2023-11-28 06:43:00,106][87426] Updated weights for policy 1, policy_version 248180 (0.0012) -[2023-11-28 06:43:00,251][87424] Updated weights for policy 0, policy_version 248437 (0.0011) -[2023-11-28 06:43:00,485][87426] Updated weights for policy 1, policy_version 248190 (0.0010) -[2023-11-28 06:43:00,621][87424] Updated weights for policy 0, policy_version 248447 (0.0011) -[2023-11-28 06:43:02,612][87426] Updated weights for policy 1, policy_version 248200 (0.0010) -[2023-11-28 06:43:02,837][87424] Updated weights for policy 0, policy_version 248457 (0.0008) -[2023-11-28 06:43:02,996][87426] Updated weights for policy 1, policy_version 248210 (0.0010) -[2023-11-28 06:43:03,220][87424] Updated weights for policy 0, policy_version 248467 (0.0008) -[2023-11-28 06:43:03,373][87426] Updated weights for policy 1, policy_version 248220 (0.0012) -[2023-11-28 06:43:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 127139840. Throughput: 0: 2722.9, 1: 2774.1. Samples: 127160808. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:03,445][86177] Avg episode reward: [(0, '-499.670'), (1, '-503.620')] -[2023-11-28 06:43:03,600][87424] Updated weights for policy 0, policy_version 248477 (0.0007) -[2023-11-28 06:43:05,321][87426] Updated weights for policy 1, policy_version 248230 (0.0012) -[2023-11-28 06:43:05,599][87424] Updated weights for policy 0, policy_version 248487 (0.0009) -[2023-11-28 06:43:05,696][87426] Updated weights for policy 1, policy_version 248240 (0.0010) -[2023-11-28 06:43:05,980][87424] Updated weights for policy 0, policy_version 248497 (0.0008) -[2023-11-28 06:43:06,070][87426] Updated weights for policy 1, policy_version 248250 (0.0010) -[2023-11-28 06:43:06,357][87424] Updated weights for policy 0, policy_version 248507 (0.0007) -[2023-11-28 06:43:08,378][87424] Updated weights for policy 0, policy_version 248517 (0.0009) -[2023-11-28 06:43:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127172608. Throughput: 0: 2772.4, 1: 2763.1. Samples: 127193848. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:08,445][86177] Avg episode reward: [(0, '-500.650'), (1, '-506.950')] -[2023-11-28 06:43:08,452][87426] Updated weights for policy 1, policy_version 248260 (0.0008) -[2023-11-28 06:43:08,749][87424] Updated weights for policy 0, policy_version 248527 (0.0011) -[2023-11-28 06:43:08,829][87426] Updated weights for policy 1, policy_version 248270 (0.0008) -[2023-11-28 06:43:09,137][87424] Updated weights for policy 0, policy_version 248537 (0.0011) -[2023-11-28 06:43:09,205][87426] Updated weights for policy 1, policy_version 248280 (0.0011) -[2023-11-28 06:43:11,358][87426] Updated weights for policy 1, policy_version 248290 (0.0010) -[2023-11-28 06:43:11,625][87424] Updated weights for policy 0, policy_version 248547 (0.0011) -[2023-11-28 06:43:11,728][87426] Updated weights for policy 1, policy_version 248300 (0.0010) -[2023-11-28 06:43:11,997][87424] Updated weights for policy 0, policy_version 248557 (0.0011) -[2023-11-28 06:43:12,107][87426] Updated weights for policy 1, policy_version 248310 (0.0011) -[2023-11-28 06:43:12,378][87424] Updated weights for policy 0, policy_version 248567 (0.0010) -[2023-11-28 06:43:12,481][87426] Updated weights for policy 1, policy_version 248320 (0.0012) -[2023-11-28 06:43:13,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 127205376. Throughput: 0: 2758.8, 1: 2741.3. Samples: 127216852. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:13,446][86177] Avg episode reward: [(0, '-500.990'), (1, '-513.080')] -[2023-11-28 06:43:14,492][87424] Updated weights for policy 0, policy_version 248577 (0.0012) -[2023-11-28 06:43:14,871][87424] Updated weights for policy 0, policy_version 248587 (0.0009) -[2023-11-28 06:43:14,917][87426] Updated weights for policy 1, policy_version 248330 (0.0012) -[2023-11-28 06:43:15,252][87424] Updated weights for policy 0, policy_version 248597 (0.0008) -[2023-11-28 06:43:15,301][87426] Updated weights for policy 1, policy_version 248340 (0.0012) -[2023-11-28 06:43:15,624][87424] Updated weights for policy 0, policy_version 248607 (0.0010) -[2023-11-28 06:43:15,673][87426] Updated weights for policy 1, policy_version 248350 (0.0011) -[2023-11-28 06:43:17,626][87424] Updated weights for policy 0, policy_version 248617 (0.0010) -[2023-11-28 06:43:17,811][87426] Updated weights for policy 1, policy_version 248360 (0.0011) -[2023-11-28 06:43:18,016][87424] Updated weights for policy 0, policy_version 248627 (0.0010) -[2023-11-28 06:43:18,192][87426] Updated weights for policy 1, policy_version 248370 (0.0008) -[2023-11-28 06:43:18,392][87424] Updated weights for policy 0, policy_version 248637 (0.0012) -[2023-11-28 06:43:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 127221760. Throughput: 0: 2752.5, 1: 2729.1. Samples: 127240864. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:18,445][86177] Avg episode reward: [(0, '-505.250'), (1, '-517.480')] -[2023-11-28 06:43:18,565][87426] Updated weights for policy 1, policy_version 248380 (0.0011) -[2023-11-28 06:43:20,727][87426] Updated weights for policy 1, policy_version 248390 (0.0010) -[2023-11-28 06:43:20,771][87424] Updated weights for policy 0, policy_version 248647 (0.0012) -[2023-11-28 06:43:21,105][87426] Updated weights for policy 1, policy_version 248400 (0.0008) -[2023-11-28 06:43:21,158][87424] Updated weights for policy 0, policy_version 248657 (0.0012) -[2023-11-28 06:43:21,481][87426] Updated weights for policy 1, policy_version 248410 (0.0011) -[2023-11-28 06:43:21,532][87424] Updated weights for policy 0, policy_version 248667 (0.0011) -[2023-11-28 06:43:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.5, 300 sec: 5442.8). Total num frames: 127254528. Throughput: 0: 2718.0, 1: 2722.7. Samples: 127272468. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:23,445][86177] Avg episode reward: [(0, '-525.180'), (1, '-517.390')] -[2023-11-28 06:43:23,820][87424] Updated weights for policy 0, policy_version 248677 (0.0010) -[2023-11-28 06:43:23,939][87426] Updated weights for policy 1, policy_version 248420 (0.0011) -[2023-11-28 06:43:24,211][87424] Updated weights for policy 0, policy_version 248687 (0.0012) -[2023-11-28 06:43:24,315][87426] Updated weights for policy 1, policy_version 248430 (0.0010) -[2023-11-28 06:43:24,588][87424] Updated weights for policy 0, policy_version 248697 (0.0012) -[2023-11-28 06:43:24,691][87426] Updated weights for policy 1, policy_version 248440 (0.0010) -[2023-11-28 06:43:26,472][87426] Updated weights for policy 1, policy_version 248450 (0.0009) -[2023-11-28 06:43:26,842][87424] Updated weights for policy 0, policy_version 248707 (0.0012) -[2023-11-28 06:43:26,842][87426] Updated weights for policy 1, policy_version 248460 (0.0012) -[2023-11-28 06:43:27,220][87426] Updated weights for policy 1, policy_version 248470 (0.0008) -[2023-11-28 06:43:27,233][87424] Updated weights for policy 0, policy_version 248717 (0.0009) -[2023-11-28 06:43:27,596][87426] Updated weights for policy 1, policy_version 248480 (0.0011) -[2023-11-28 06:43:27,611][87424] Updated weights for policy 0, policy_version 248727 (0.0011) -[2023-11-28 06:43:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 127287296. Throughput: 0: 2717.2, 1: 2730.5. Samples: 127296484. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:28,445][86177] Avg episode reward: [(0, '-527.270'), (1, '-507.920')] -[2023-11-28 06:43:29,486][87424] Updated weights for policy 0, policy_version 248737 (0.0012) -[2023-11-28 06:43:29,859][87426] Updated weights for policy 1, policy_version 248490 (0.0011) -[2023-11-28 06:43:29,873][87424] Updated weights for policy 0, policy_version 248747 (0.0010) -[2023-11-28 06:43:30,237][87426] Updated weights for policy 1, policy_version 248500 (0.0011) -[2023-11-28 06:43:30,245][87424] Updated weights for policy 0, policy_version 248757 (0.0010) -[2023-11-28 06:43:30,625][87424] Updated weights for policy 0, policy_version 248767 (0.0011) -[2023-11-28 06:43:30,630][87426] Updated weights for policy 1, policy_version 248510 (0.0010) -[2023-11-28 06:43:32,410][87426] Updated weights for policy 1, policy_version 248520 (0.0011) -[2023-11-28 06:43:32,596][87424] Updated weights for policy 0, policy_version 248777 (0.0010) -[2023-11-28 06:43:32,795][87426] Updated weights for policy 1, policy_version 248530 (0.0011) -[2023-11-28 06:43:32,980][87424] Updated weights for policy 0, policy_version 248787 (0.0011) -[2023-11-28 06:43:33,168][87426] Updated weights for policy 1, policy_version 248540 (0.0012) -[2023-11-28 06:43:33,364][87424] Updated weights for policy 0, policy_version 248797 (0.0011) -[2023-11-28 06:43:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 127311872. Throughput: 0: 2717.9, 1: 2715.5. Samples: 127322064. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:33,445][86177] Avg episode reward: [(0, '-532.190'), (1, '-508.990')] -[2023-11-28 06:43:35,472][87424] Updated weights for policy 0, policy_version 248807 (0.0010) -[2023-11-28 06:43:35,496][87426] Updated weights for policy 1, policy_version 248550 (0.0011) -[2023-11-28 06:43:35,849][87424] Updated weights for policy 0, policy_version 248817 (0.0011) -[2023-11-28 06:43:35,872][87426] Updated weights for policy 1, policy_version 248560 (0.0010) -[2023-11-28 06:43:36,236][87424] Updated weights for policy 0, policy_version 248827 (0.0011) -[2023-11-28 06:43:36,258][87426] Updated weights for policy 1, policy_version 248570 (0.0012) -[2023-11-28 06:43:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127336448. Throughput: 0: 2727.9, 1: 2680.4. Samples: 127354424. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:38,445][86177] Avg episode reward: [(0, '-530.680'), (1, '-503.450')] -[2023-11-28 06:43:38,691][87424] Updated weights for policy 0, policy_version 248837 (0.0008) -[2023-11-28 06:43:38,795][87426] Updated weights for policy 1, policy_version 248580 (0.0010) -[2023-11-28 06:43:39,085][87424] Updated weights for policy 0, policy_version 248847 (0.0009) -[2023-11-28 06:43:39,170][87426] Updated weights for policy 1, policy_version 248590 (0.0011) -[2023-11-28 06:43:39,455][87424] Updated weights for policy 0, policy_version 248857 (0.0008) -[2023-11-28 06:43:39,554][87426] Updated weights for policy 1, policy_version 248600 (0.0012) -[2023-11-28 06:43:41,876][87424] Updated weights for policy 0, policy_version 248867 (0.0009) -[2023-11-28 06:43:42,097][87426] Updated weights for policy 1, policy_version 248610 (0.0009) -[2023-11-28 06:43:42,258][87424] Updated weights for policy 0, policy_version 248877 (0.0011) -[2023-11-28 06:43:42,479][87426] Updated weights for policy 1, policy_version 248620 (0.0011) -[2023-11-28 06:43:42,633][87424] Updated weights for policy 0, policy_version 248887 (0.0011) -[2023-11-28 06:43:42,850][87426] Updated weights for policy 1, policy_version 248630 (0.0012) -[2023-11-28 06:43:43,231][87426] Updated weights for policy 1, policy_version 248640 (0.0011) -[2023-11-28 06:43:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 127369216. Throughput: 0: 2718.1, 1: 2661.7. Samples: 127377988. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:43,445][86177] Avg episode reward: [(0, '-509.620'), (1, '-524.730')] -[2023-11-28 06:43:44,851][87424] Updated weights for policy 0, policy_version 248897 (0.0012) -[2023-11-28 06:43:45,233][87424] Updated weights for policy 0, policy_version 248907 (0.0012) -[2023-11-28 06:43:45,614][87424] Updated weights for policy 0, policy_version 248917 (0.0011) -[2023-11-28 06:43:45,825][87426] Updated weights for policy 1, policy_version 248650 (0.0008) -[2023-11-28 06:43:45,985][87424] Updated weights for policy 0, policy_version 248927 (0.0010) -[2023-11-28 06:43:46,205][87426] Updated weights for policy 1, policy_version 248660 (0.0008) -[2023-11-28 06:43:46,589][87426] Updated weights for policy 1, policy_version 248670 (0.0008) -[2023-11-28 06:43:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 127385600. Throughput: 0: 2678.8, 1: 2668.0. Samples: 127401412. Policy #0 lag: (min: 31.0, avg: 35.9, max: 63.0) -[2023-11-28 06:43:48,445][86177] Avg episode reward: [(0, '-505.990'), (1, '-561.520')] -[2023-11-28 06:43:48,501][87426] Updated weights for policy 1, policy_version 248680 (0.0010) -[2023-11-28 06:43:48,565][87424] Updated weights for policy 0, policy_version 248937 (0.0011) -[2023-11-28 06:43:48,879][87426] Updated weights for policy 1, policy_version 248690 (0.0011) -[2023-11-28 06:43:48,949][87424] Updated weights for policy 0, policy_version 248947 (0.0012) -[2023-11-28 06:43:49,269][87426] Updated weights for policy 1, policy_version 248700 (0.0011) -[2023-11-28 06:43:49,331][87424] Updated weights for policy 0, policy_version 248957 (0.0009) -[2023-11-28 06:43:51,110][87426] Updated weights for policy 1, policy_version 248710 (0.0010) -[2023-11-28 06:43:51,479][87426] Updated weights for policy 1, policy_version 248720 (0.0010) -[2023-11-28 06:43:51,862][87426] Updated weights for policy 1, policy_version 248730 (0.0011) -[2023-11-28 06:43:51,879][87424] Updated weights for policy 0, policy_version 248967 (0.0010) -[2023-11-28 06:43:52,260][87424] Updated weights for policy 0, policy_version 248977 (0.0010) -[2023-11-28 06:43:52,634][87424] Updated weights for policy 0, policy_version 248987 (0.0012) -[2023-11-28 06:43:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127418368. Throughput: 0: 2640.8, 1: 2675.6. Samples: 127433088. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:43:53,445][86177] Avg episode reward: [(0, '-499.920'), (1, '-561.180')] -[2023-11-28 06:43:54,282][87426] Updated weights for policy 1, policy_version 248740 (0.0009) -[2023-11-28 06:43:54,665][87426] Updated weights for policy 1, policy_version 248750 (0.0008) -[2023-11-28 06:43:54,897][87424] Updated weights for policy 0, policy_version 248997 (0.0009) -[2023-11-28 06:43:55,040][87426] Updated weights for policy 1, policy_version 248760 (0.0008) -[2023-11-28 06:43:55,276][87424] Updated weights for policy 0, policy_version 249007 (0.0008) -[2023-11-28 06:43:55,656][87424] Updated weights for policy 0, policy_version 249017 (0.0008) -[2023-11-28 06:43:57,154][87426] Updated weights for policy 1, policy_version 248770 (0.0009) -[2023-11-28 06:43:57,529][87426] Updated weights for policy 1, policy_version 248780 (0.0011) -[2023-11-28 06:43:57,904][87426] Updated weights for policy 1, policy_version 248790 (0.0009) -[2023-11-28 06:43:58,131][87424] Updated weights for policy 0, policy_version 249027 (0.0008) -[2023-11-28 06:43:58,279][87426] Updated weights for policy 1, policy_version 248800 (0.0010) -[2023-11-28 06:43:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 127442944. Throughput: 0: 2646.5, 1: 2682.2. Samples: 127456644. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:43:58,445][86177] Avg episode reward: [(0, '-541.190'), (1, '-562.470')] -[2023-11-28 06:43:58,514][87424] Updated weights for policy 0, policy_version 249037 (0.0008) -[2023-11-28 06:43:58,895][87424] Updated weights for policy 0, policy_version 249047 (0.0008) -[2023-11-28 06:44:00,729][87426] Updated weights for policy 1, policy_version 248810 (0.0008) -[2023-11-28 06:44:01,113][87426] Updated weights for policy 1, policy_version 248820 (0.0008) -[2023-11-28 06:44:01,449][87424] Updated weights for policy 0, policy_version 249057 (0.0008) -[2023-11-28 06:44:01,492][87426] Updated weights for policy 1, policy_version 248830 (0.0012) -[2023-11-28 06:44:01,824][87424] Updated weights for policy 0, policy_version 249067 (0.0011) -[2023-11-28 06:44:02,205][87424] Updated weights for policy 0, policy_version 249077 (0.0012) -[2023-11-28 06:44:02,587][87424] Updated weights for policy 0, policy_version 249087 (0.0012) -[2023-11-28 06:44:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127467520. Throughput: 0: 2633.6, 1: 2692.6. Samples: 127480544. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:03,445][86177] Avg episode reward: [(0, '-539.220'), (1, '-530.950')] -[2023-11-28 06:44:03,566][87426] Updated weights for policy 1, policy_version 248840 (0.0010) -[2023-11-28 06:44:03,937][87426] Updated weights for policy 1, policy_version 248850 (0.0008) -[2023-11-28 06:44:04,330][87426] Updated weights for policy 1, policy_version 248860 (0.0008) -[2023-11-28 06:44:04,475][87424] Updated weights for policy 0, policy_version 249097 (0.0010) -[2023-11-28 06:44:04,853][87424] Updated weights for policy 0, policy_version 249107 (0.0010) -[2023-11-28 06:44:05,242][87424] Updated weights for policy 0, policy_version 249117 (0.0010) -[2023-11-28 06:44:06,430][87426] Updated weights for policy 1, policy_version 248870 (0.0009) -[2023-11-28 06:44:06,813][87426] Updated weights for policy 1, policy_version 248880 (0.0008) -[2023-11-28 06:44:07,196][87426] Updated weights for policy 1, policy_version 248890 (0.0007) -[2023-11-28 06:44:07,520][87424] Updated weights for policy 0, policy_version 249127 (0.0010) -[2023-11-28 06:44:07,904][87424] Updated weights for policy 0, policy_version 249137 (0.0012) -[2023-11-28 06:44:08,282][87424] Updated weights for policy 0, policy_version 249147 (0.0012) -[2023-11-28 06:44:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 127492096. Throughput: 0: 2620.4, 1: 2724.2. Samples: 127512976. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:08,445][86177] Avg episode reward: [(0, '-537.380'), (1, '-512.850')] -[2023-11-28 06:44:09,111][87426] Updated weights for policy 1, policy_version 248900 (0.0009) -[2023-11-28 06:44:09,484][87426] Updated weights for policy 1, policy_version 248910 (0.0012) -[2023-11-28 06:44:09,873][87426] Updated weights for policy 1, policy_version 248920 (0.0009) -[2023-11-28 06:44:10,736][87424] Updated weights for policy 0, policy_version 249157 (0.0012) -[2023-11-28 06:44:11,123][87424] Updated weights for policy 0, policy_version 249167 (0.0011) -[2023-11-28 06:44:11,506][87424] Updated weights for policy 0, policy_version 249177 (0.0012) -[2023-11-28 06:44:11,997][87426] Updated weights for policy 1, policy_version 248930 (0.0010) -[2023-11-28 06:44:12,377][87426] Updated weights for policy 1, policy_version 248940 (0.0011) -[2023-11-28 06:44:12,757][87426] Updated weights for policy 1, policy_version 248950 (0.0009) -[2023-11-28 06:44:13,134][87426] Updated weights for policy 1, policy_version 248960 (0.0011) -[2023-11-28 06:44:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 127524864. Throughput: 0: 2601.3, 1: 2737.1. Samples: 127536716. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:13,445][86177] Avg episode reward: [(0, '-500.530'), (1, '-514.490')] -[2023-11-28 06:44:13,937][87424] Updated weights for policy 0, policy_version 249187 (0.0010) -[2023-11-28 06:44:14,315][87424] Updated weights for policy 0, policy_version 249197 (0.0007) -[2023-11-28 06:44:14,700][87424] Updated weights for policy 0, policy_version 249207 (0.0007) -[2023-11-28 06:44:15,606][87426] Updated weights for policy 1, policy_version 248970 (0.0012) -[2023-11-28 06:44:15,987][87426] Updated weights for policy 1, policy_version 248980 (0.0012) -[2023-11-28 06:44:16,369][87426] Updated weights for policy 1, policy_version 248990 (0.0011) -[2023-11-28 06:44:16,427][87424] Updated weights for policy 0, policy_version 249217 (0.0008) -[2023-11-28 06:44:16,822][87424] Updated weights for policy 0, policy_version 249227 (0.0012) -[2023-11-28 06:44:17,195][87424] Updated weights for policy 0, policy_version 249237 (0.0009) -[2023-11-28 06:44:17,577][87424] Updated weights for policy 0, policy_version 249247 (0.0007) -[2023-11-28 06:44:18,120][87426] Updated weights for policy 1, policy_version 249000 (0.0011) -[2023-11-28 06:44:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127549440. Throughput: 0: 2582.5, 1: 2717.9. Samples: 127560584. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:18,445][86177] Avg episode reward: [(0, '-501.680'), (1, '-544.240')] -[2023-11-28 06:44:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000249248_63807488.pth... -[2023-11-28 06:44:18,502][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000246720_63160320.pth -[2023-11-28 06:44:18,508][87426] Updated weights for policy 1, policy_version 249010 (0.0008) -[2023-11-28 06:44:18,879][87426] Updated weights for policy 1, policy_version 249020 (0.0009) -[2023-11-28 06:44:19,031][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000249024_63750144.pth... -[2023-11-28 06:44:19,075][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000246464_63094784.pth -[2023-11-28 06:44:19,923][87424] Updated weights for policy 0, policy_version 249257 (0.0011) -[2023-11-28 06:44:20,304][87424] Updated weights for policy 0, policy_version 249267 (0.0011) -[2023-11-28 06:44:20,687][87424] Updated weights for policy 0, policy_version 249277 (0.0011) -[2023-11-28 06:44:21,399][87426] Updated weights for policy 1, policy_version 249030 (0.0010) -[2023-11-28 06:44:21,776][87426] Updated weights for policy 1, policy_version 249040 (0.0012) -[2023-11-28 06:44:22,158][87426] Updated weights for policy 1, policy_version 249050 (0.0010) -[2023-11-28 06:44:22,734][87424] Updated weights for policy 0, policy_version 249287 (0.0011) -[2023-11-28 06:44:23,112][87424] Updated weights for policy 0, policy_version 249297 (0.0012) -[2023-11-28 06:44:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 127574016. Throughput: 0: 2609.5, 1: 2723.9. Samples: 127594428. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:23,445][86177] Avg episode reward: [(0, '-501.660'), (1, '-547.860')] -[2023-11-28 06:44:23,488][87424] Updated weights for policy 0, policy_version 249307 (0.0012) -[2023-11-28 06:44:24,577][87426] Updated weights for policy 1, policy_version 249060 (0.0011) -[2023-11-28 06:44:24,961][87426] Updated weights for policy 1, policy_version 249070 (0.0011) -[2023-11-28 06:44:25,258][87424] Updated weights for policy 0, policy_version 249317 (0.0011) -[2023-11-28 06:44:25,335][87426] Updated weights for policy 1, policy_version 249080 (0.0010) -[2023-11-28 06:44:25,637][87424] Updated weights for policy 0, policy_version 249327 (0.0008) -[2023-11-28 06:44:26,023][87424] Updated weights for policy 0, policy_version 249337 (0.0008) -[2023-11-28 06:44:27,035][87426] Updated weights for policy 1, policy_version 249090 (0.0011) -[2023-11-28 06:44:27,408][87426] Updated weights for policy 1, policy_version 249100 (0.0010) -[2023-11-28 06:44:27,787][87426] Updated weights for policy 1, policy_version 249110 (0.0010) -[2023-11-28 06:44:27,998][87424] Updated weights for policy 0, policy_version 249347 (0.0007) -[2023-11-28 06:44:28,167][87426] Updated weights for policy 1, policy_version 249120 (0.0011) -[2023-11-28 06:44:28,385][87424] Updated weights for policy 0, policy_version 249357 (0.0007) -[2023-11-28 06:44:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 127606784. Throughput: 0: 2619.8, 1: 2741.6. Samples: 127619252. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:28,445][86177] Avg episode reward: [(0, '-506.000'), (1, '-543.550')] -[2023-11-28 06:44:28,757][87424] Updated weights for policy 0, policy_version 249367 (0.0007) -[2023-11-28 06:44:30,411][87426] Updated weights for policy 1, policy_version 249130 (0.0012) -[2023-11-28 06:44:30,793][87426] Updated weights for policy 1, policy_version 249140 (0.0012) -[2023-11-28 06:44:31,169][87426] Updated weights for policy 1, policy_version 249150 (0.0012) -[2023-11-28 06:44:31,255][87424] Updated weights for policy 0, policy_version 249377 (0.0010) -[2023-11-28 06:44:31,636][87424] Updated weights for policy 0, policy_version 249387 (0.0011) -[2023-11-28 06:44:32,014][87424] Updated weights for policy 0, policy_version 249397 (0.0010) -[2023-11-28 06:44:32,401][87424] Updated weights for policy 0, policy_version 249407 (0.0008) -[2023-11-28 06:44:33,039][87426] Updated weights for policy 1, policy_version 249160 (0.0011) -[2023-11-28 06:44:33,421][87426] Updated weights for policy 1, policy_version 249170 (0.0011) -[2023-11-28 06:44:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 127631360. Throughput: 0: 2660.8, 1: 2735.9. Samples: 127644264. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:33,445][86177] Avg episode reward: [(0, '-504.410'), (1, '-513.420')] -[2023-11-28 06:44:33,807][87426] Updated weights for policy 1, policy_version 249180 (0.0008) -[2023-11-28 06:44:34,677][87424] Updated weights for policy 0, policy_version 249417 (0.0009) -[2023-11-28 06:44:35,059][87424] Updated weights for policy 0, policy_version 249427 (0.0012) -[2023-11-28 06:44:35,444][87424] Updated weights for policy 0, policy_version 249437 (0.0010) -[2023-11-28 06:44:36,211][87426] Updated weights for policy 1, policy_version 249190 (0.0010) -[2023-11-28 06:44:36,583][87426] Updated weights for policy 1, policy_version 249200 (0.0010) -[2023-11-28 06:44:36,957][87426] Updated weights for policy 1, policy_version 249210 (0.0009) -[2023-11-28 06:44:37,672][87424] Updated weights for policy 0, policy_version 249447 (0.0012) -[2023-11-28 06:44:38,046][87424] Updated weights for policy 0, policy_version 249457 (0.0012) -[2023-11-28 06:44:38,431][87424] Updated weights for policy 0, policy_version 249467 (0.0012) -[2023-11-28 06:44:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 127655936. Throughput: 0: 2679.9, 1: 2712.7. Samples: 127675756. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:38,445][86177] Avg episode reward: [(0, '-509.440'), (1, '-509.700')] -[2023-11-28 06:44:39,558][87426] Updated weights for policy 1, policy_version 249220 (0.0009) -[2023-11-28 06:44:39,939][87426] Updated weights for policy 1, policy_version 249230 (0.0012) -[2023-11-28 06:44:40,314][87426] Updated weights for policy 1, policy_version 249240 (0.0009) -[2023-11-28 06:44:40,473][87424] Updated weights for policy 0, policy_version 249477 (0.0010) -[2023-11-28 06:44:40,851][87424] Updated weights for policy 0, policy_version 249487 (0.0011) -[2023-11-28 06:44:41,238][87424] Updated weights for policy 0, policy_version 249497 (0.0012) -[2023-11-28 06:44:42,305][87426] Updated weights for policy 1, policy_version 249250 (0.0011) -[2023-11-28 06:44:42,677][87426] Updated weights for policy 1, policy_version 249260 (0.0011) -[2023-11-28 06:44:43,057][87426] Updated weights for policy 1, policy_version 249270 (0.0010) -[2023-11-28 06:44:43,433][87426] Updated weights for policy 1, policy_version 249280 (0.0012) -[2023-11-28 06:44:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 127688704. Throughput: 0: 2698.5, 1: 2711.9. Samples: 127700112. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:43,445][86177] Avg episode reward: [(0, '-511.080'), (1, '-510.100')] -[2023-11-28 06:44:43,675][87424] Updated weights for policy 0, policy_version 249507 (0.0011) -[2023-11-28 06:44:44,049][87424] Updated weights for policy 0, policy_version 249517 (0.0011) -[2023-11-28 06:44:44,426][87424] Updated weights for policy 0, policy_version 249527 (0.0011) -[2023-11-28 06:44:45,701][87426] Updated weights for policy 1, policy_version 249290 (0.0012) -[2023-11-28 06:44:46,071][87426] Updated weights for policy 1, policy_version 249300 (0.0012) -[2023-11-28 06:44:46,449][87426] Updated weights for policy 1, policy_version 249310 (0.0011) -[2023-11-28 06:44:46,551][87424] Updated weights for policy 0, policy_version 249537 (0.0012) -[2023-11-28 06:44:46,936][87424] Updated weights for policy 0, policy_version 249547 (0.0012) -[2023-11-28 06:44:47,318][87424] Updated weights for policy 0, policy_version 249557 (0.0008) -[2023-11-28 06:44:47,699][87424] Updated weights for policy 0, policy_version 249567 (0.0008) -[2023-11-28 06:44:48,239][87426] Updated weights for policy 1, policy_version 249320 (0.0008) -[2023-11-28 06:44:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127713280. Throughput: 0: 2710.2, 1: 2729.0. Samples: 127725308. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:48,445][86177] Avg episode reward: [(0, '-511.560'), (1, '-504.840')] -[2023-11-28 06:44:48,618][87426] Updated weights for policy 1, policy_version 249330 (0.0008) -[2023-11-28 06:44:49,000][87426] Updated weights for policy 1, policy_version 249340 (0.0009) -[2023-11-28 06:44:50,193][87424] Updated weights for policy 0, policy_version 249577 (0.0008) -[2023-11-28 06:44:50,566][87424] Updated weights for policy 0, policy_version 249587 (0.0009) -[2023-11-28 06:44:50,951][87424] Updated weights for policy 0, policy_version 249597 (0.0011) -[2023-11-28 06:44:51,080][87426] Updated weights for policy 1, policy_version 249350 (0.0011) -[2023-11-28 06:44:51,449][87426] Updated weights for policy 1, policy_version 249360 (0.0011) -[2023-11-28 06:44:51,830][87426] Updated weights for policy 1, policy_version 249370 (0.0009) -[2023-11-28 06:44:53,183][87424] Updated weights for policy 0, policy_version 249607 (0.0010) -[2023-11-28 06:44:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 127737856. Throughput: 0: 2709.0, 1: 2727.5. Samples: 127757616. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:53,446][86177] Avg episode reward: [(0, '-506.660'), (1, '-505.300')] -[2023-11-28 06:44:53,571][87424] Updated weights for policy 0, policy_version 249617 (0.0011) -[2023-11-28 06:44:53,945][87424] Updated weights for policy 0, policy_version 249627 (0.0009) -[2023-11-28 06:44:54,309][87426] Updated weights for policy 1, policy_version 249380 (0.0012) -[2023-11-28 06:44:54,693][87426] Updated weights for policy 1, policy_version 249390 (0.0012) -[2023-11-28 06:44:55,060][87426] Updated weights for policy 1, policy_version 249400 (0.0010) -[2023-11-28 06:44:56,053][87424] Updated weights for policy 0, policy_version 249637 (0.0010) -[2023-11-28 06:44:56,449][87424] Updated weights for policy 0, policy_version 249647 (0.0012) -[2023-11-28 06:44:56,829][87424] Updated weights for policy 0, policy_version 249657 (0.0012) -[2023-11-28 06:44:57,411][87426] Updated weights for policy 1, policy_version 249410 (0.0011) -[2023-11-28 06:44:57,786][87426] Updated weights for policy 1, policy_version 249420 (0.0011) -[2023-11-28 06:44:58,159][87426] Updated weights for policy 1, policy_version 249430 (0.0012) -[2023-11-28 06:44:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 127762432. Throughput: 0: 2716.9, 1: 2710.2. Samples: 127780936. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:44:58,446][86177] Avg episode reward: [(0, '-505.290'), (1, '-504.870')] -[2023-11-28 06:44:58,531][87426] Updated weights for policy 1, policy_version 249440 (0.0011) -[2023-11-28 06:44:58,734][87424] Updated weights for policy 0, policy_version 249667 (0.0011) -[2023-11-28 06:44:59,117][87424] Updated weights for policy 0, policy_version 249677 (0.0012) -[2023-11-28 06:44:59,499][87424] Updated weights for policy 0, policy_version 249687 (0.0012) -[2023-11-28 06:45:00,406][87426] Updated weights for policy 1, policy_version 249450 (0.0012) -[2023-11-28 06:45:00,781][87426] Updated weights for policy 1, policy_version 249460 (0.0009) -[2023-11-28 06:45:01,166][87426] Updated weights for policy 1, policy_version 249470 (0.0009) -[2023-11-28 06:45:01,594][87424] Updated weights for policy 0, policy_version 249697 (0.0012) -[2023-11-28 06:45:01,972][87424] Updated weights for policy 0, policy_version 249707 (0.0011) -[2023-11-28 06:45:02,353][87424] Updated weights for policy 0, policy_version 249717 (0.0011) -[2023-11-28 06:45:02,734][87424] Updated weights for policy 0, policy_version 249727 (0.0010) -[2023-11-28 06:45:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127795200. Throughput: 0: 2725.1, 1: 2728.7. Samples: 127806004. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 06:45:03,445][86177] Avg episode reward: [(0, '-502.450'), (1, '-506.760')] -[2023-11-28 06:45:03,468][87426] Updated weights for policy 1, policy_version 249480 (0.0011) -[2023-11-28 06:45:03,835][87426] Updated weights for policy 1, policy_version 249490 (0.0011) -[2023-11-28 06:45:04,226][87426] Updated weights for policy 1, policy_version 249500 (0.0011) -[2023-11-28 06:45:05,006][87424] Updated weights for policy 0, policy_version 249737 (0.0012) -[2023-11-28 06:45:05,385][87424] Updated weights for policy 0, policy_version 249747 (0.0012) -[2023-11-28 06:45:05,770][87424] Updated weights for policy 0, policy_version 249757 (0.0011) -[2023-11-28 06:45:05,961][87426] Updated weights for policy 1, policy_version 249510 (0.0009) -[2023-11-28 06:45:06,342][87426] Updated weights for policy 1, policy_version 249520 (0.0011) -[2023-11-28 06:45:06,724][87426] Updated weights for policy 1, policy_version 249530 (0.0008) -[2023-11-28 06:45:08,079][87424] Updated weights for policy 0, policy_version 249767 (0.0012) -[2023-11-28 06:45:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127819776. Throughput: 0: 2706.5, 1: 2736.4. Samples: 127839360. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:08,445][86177] Avg episode reward: [(0, '-500.370'), (1, '-511.720')] -[2023-11-28 06:45:08,449][87424] Updated weights for policy 0, policy_version 249777 (0.0012) -[2023-11-28 06:45:08,556][87426] Updated weights for policy 1, policy_version 249540 (0.0011) -[2023-11-28 06:45:08,827][87424] Updated weights for policy 0, policy_version 249787 (0.0012) -[2023-11-28 06:45:08,926][87426] Updated weights for policy 1, policy_version 249550 (0.0009) -[2023-11-28 06:45:09,304][87426] Updated weights for policy 1, policy_version 249560 (0.0009) -[2023-11-28 06:45:10,957][87424] Updated weights for policy 0, policy_version 249797 (0.0011) -[2023-11-28 06:45:11,350][87424] Updated weights for policy 0, policy_version 249807 (0.0012) -[2023-11-28 06:45:11,725][87424] Updated weights for policy 0, policy_version 249817 (0.0009) -[2023-11-28 06:45:11,845][87426] Updated weights for policy 1, policy_version 249570 (0.0008) -[2023-11-28 06:45:12,214][87426] Updated weights for policy 1, policy_version 249580 (0.0009) -[2023-11-28 06:45:12,591][87426] Updated weights for policy 1, policy_version 249590 (0.0011) -[2023-11-28 06:45:12,973][87426] Updated weights for policy 1, policy_version 249600 (0.0011) -[2023-11-28 06:45:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 127852544. Throughput: 0: 2704.7, 1: 2721.7. Samples: 127863440. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:13,445][86177] Avg episode reward: [(0, '-502.120'), (1, '-522.010')] -[2023-11-28 06:45:14,222][87424] Updated weights for policy 0, policy_version 249827 (0.0011) -[2023-11-28 06:45:14,605][87424] Updated weights for policy 0, policy_version 249837 (0.0012) -[2023-11-28 06:45:14,985][87424] Updated weights for policy 0, policy_version 249847 (0.0011) -[2023-11-28 06:45:14,987][87426] Updated weights for policy 1, policy_version 249610 (0.0008) -[2023-11-28 06:45:15,364][87426] Updated weights for policy 1, policy_version 249620 (0.0008) -[2023-11-28 06:45:15,744][87426] Updated weights for policy 1, policy_version 249630 (0.0008) -[2023-11-28 06:45:17,002][87424] Updated weights for policy 0, policy_version 249857 (0.0010) -[2023-11-28 06:45:17,387][87424] Updated weights for policy 0, policy_version 249867 (0.0011) -[2023-11-28 06:45:17,775][87424] Updated weights for policy 0, policy_version 249877 (0.0012) -[2023-11-28 06:45:17,849][87426] Updated weights for policy 1, policy_version 249640 (0.0007) -[2023-11-28 06:45:18,153][87424] Updated weights for policy 0, policy_version 249887 (0.0012) -[2023-11-28 06:45:18,227][87426] Updated weights for policy 1, policy_version 249650 (0.0008) -[2023-11-28 06:45:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127877120. Throughput: 0: 2675.4, 1: 2738.5. Samples: 127887888. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:18,446][86177] Avg episode reward: [(0, '-499.040'), (1, '-522.640')] -[2023-11-28 06:45:18,609][87426] Updated weights for policy 1, policy_version 249660 (0.0007) -[2023-11-28 06:45:20,437][87424] Updated weights for policy 0, policy_version 249897 (0.0011) -[2023-11-28 06:45:20,710][87426] Updated weights for policy 1, policy_version 249670 (0.0010) -[2023-11-28 06:45:20,824][87424] Updated weights for policy 0, policy_version 249907 (0.0011) -[2023-11-28 06:45:21,080][87426] Updated weights for policy 1, policy_version 249680 (0.0011) -[2023-11-28 06:45:21,196][87424] Updated weights for policy 0, policy_version 249917 (0.0011) -[2023-11-28 06:45:21,469][87426] Updated weights for policy 1, policy_version 249690 (0.0011) -[2023-11-28 06:45:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127901696. Throughput: 0: 2684.2, 1: 2758.4. Samples: 127920672. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:23,445][86177] Avg episode reward: [(0, '-498.270'), (1, '-524.440')] -[2023-11-28 06:45:23,548][87424] Updated weights for policy 0, policy_version 249927 (0.0010) -[2023-11-28 06:45:23,887][87426] Updated weights for policy 1, policy_version 249700 (0.0010) -[2023-11-28 06:45:23,927][87424] Updated weights for policy 0, policy_version 249937 (0.0008) -[2023-11-28 06:45:24,269][87426] Updated weights for policy 1, policy_version 249710 (0.0010) -[2023-11-28 06:45:24,310][87424] Updated weights for policy 0, policy_version 249947 (0.0010) -[2023-11-28 06:45:24,639][87426] Updated weights for policy 1, policy_version 249720 (0.0012) -[2023-11-28 06:45:26,109][87424] Updated weights for policy 0, policy_version 249957 (0.0010) -[2023-11-28 06:45:26,504][87424] Updated weights for policy 0, policy_version 249967 (0.0011) -[2023-11-28 06:45:26,881][87424] Updated weights for policy 0, policy_version 249977 (0.0008) -[2023-11-28 06:45:27,214][87426] Updated weights for policy 1, policy_version 249730 (0.0009) -[2023-11-28 06:45:27,592][87426] Updated weights for policy 1, policy_version 249740 (0.0008) -[2023-11-28 06:45:27,970][87426] Updated weights for policy 1, policy_version 249750 (0.0009) -[2023-11-28 06:45:28,339][87426] Updated weights for policy 1, policy_version 249760 (0.0012) -[2023-11-28 06:45:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 127934464. Throughput: 0: 2678.7, 1: 2756.8. Samples: 127944708. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:28,445][86177] Avg episode reward: [(0, '-496.130'), (1, '-519.860')] -[2023-11-28 06:45:29,367][87424] Updated weights for policy 0, policy_version 249987 (0.0008) -[2023-11-28 06:45:29,748][87424] Updated weights for policy 0, policy_version 249997 (0.0010) -[2023-11-28 06:45:30,130][87424] Updated weights for policy 0, policy_version 250007 (0.0010) -[2023-11-28 06:45:30,200][87426] Updated weights for policy 1, policy_version 249770 (0.0012) -[2023-11-28 06:45:30,578][87426] Updated weights for policy 1, policy_version 249780 (0.0009) -[2023-11-28 06:45:30,965][87426] Updated weights for policy 1, policy_version 249790 (0.0008) -[2023-11-28 06:45:32,239][87424] Updated weights for policy 0, policy_version 250017 (0.0012) -[2023-11-28 06:45:32,611][87424] Updated weights for policy 0, policy_version 250027 (0.0014) -[2023-11-28 06:45:32,993][87424] Updated weights for policy 0, policy_version 250037 (0.0012) -[2023-11-28 06:45:33,258][87426] Updated weights for policy 1, policy_version 249800 (0.0008) -[2023-11-28 06:45:33,375][87424] Updated weights for policy 0, policy_version 250047 (0.0011) -[2023-11-28 06:45:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127959040. Throughput: 0: 2687.8, 1: 2749.6. Samples: 127969992. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:33,445][86177] Avg episode reward: [(0, '-497.180'), (1, '-520.550')] -[2023-11-28 06:45:33,638][87426] Updated weights for policy 1, policy_version 249810 (0.0008) -[2023-11-28 06:45:34,012][87426] Updated weights for policy 1, policy_version 249820 (0.0007) -[2023-11-28 06:45:35,404][87424] Updated weights for policy 0, policy_version 250057 (0.0012) -[2023-11-28 06:45:35,791][87424] Updated weights for policy 0, policy_version 250067 (0.0009) -[2023-11-28 06:45:36,180][87424] Updated weights for policy 0, policy_version 250077 (0.0009) -[2023-11-28 06:45:36,282][87426] Updated weights for policy 1, policy_version 249830 (0.0008) -[2023-11-28 06:45:36,662][87426] Updated weights for policy 1, policy_version 249840 (0.0011) -[2023-11-28 06:45:37,040][87426] Updated weights for policy 1, policy_version 249850 (0.0012) -[2023-11-28 06:45:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 127983616. Throughput: 0: 2706.8, 1: 2735.2. Samples: 128002504. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:38,445][86177] Avg episode reward: [(0, '-497.840'), (1, '-514.410')] -[2023-11-28 06:45:38,584][87424] Updated weights for policy 0, policy_version 250087 (0.0010) -[2023-11-28 06:45:38,973][87424] Updated weights for policy 0, policy_version 250097 (0.0009) -[2023-11-28 06:45:39,276][87426] Updated weights for policy 1, policy_version 249860 (0.0012) -[2023-11-28 06:45:39,356][87424] Updated weights for policy 0, policy_version 250107 (0.0009) -[2023-11-28 06:45:39,664][87426] Updated weights for policy 1, policy_version 249870 (0.0012) -[2023-11-28 06:45:40,041][87426] Updated weights for policy 1, policy_version 249880 (0.0012) -[2023-11-28 06:45:41,434][87424] Updated weights for policy 0, policy_version 250117 (0.0012) -[2023-11-28 06:45:41,818][87424] Updated weights for policy 0, policy_version 250127 (0.0011) -[2023-11-28 06:45:42,200][87424] Updated weights for policy 0, policy_version 250137 (0.0011) -[2023-11-28 06:45:42,560][87426] Updated weights for policy 1, policy_version 249890 (0.0012) -[2023-11-28 06:45:42,935][87426] Updated weights for policy 1, policy_version 249900 (0.0012) -[2023-11-28 06:45:43,315][87426] Updated weights for policy 1, policy_version 249910 (0.0012) -[2023-11-28 06:45:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 128008192. Throughput: 0: 2711.7, 1: 2739.1. Samples: 128026224. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:43,445][86177] Avg episode reward: [(0, '-498.220'), (1, '-516.710')] -[2023-11-28 06:45:43,683][87426] Updated weights for policy 1, policy_version 249920 (0.0012) -[2023-11-28 06:45:44,846][87424] Updated weights for policy 0, policy_version 250147 (0.0011) -[2023-11-28 06:45:45,225][87424] Updated weights for policy 0, policy_version 250157 (0.0011) -[2023-11-28 06:45:45,617][87424] Updated weights for policy 0, policy_version 250167 (0.0012) -[2023-11-28 06:45:45,661][87426] Updated weights for policy 1, policy_version 249930 (0.0010) -[2023-11-28 06:45:46,032][87426] Updated weights for policy 1, policy_version 249940 (0.0008) -[2023-11-28 06:45:46,412][87426] Updated weights for policy 1, policy_version 249950 (0.0010) -[2023-11-28 06:45:48,001][87424] Updated weights for policy 0, policy_version 250177 (0.0012) -[2023-11-28 06:45:48,378][87424] Updated weights for policy 0, policy_version 250187 (0.0009) -[2023-11-28 06:45:48,409][87426] Updated weights for policy 1, policy_version 249960 (0.0012) -[2023-11-28 06:45:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 128032768. Throughput: 0: 2690.4, 1: 2740.1. Samples: 128050376. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:48,445][86177] Avg episode reward: [(0, '-497.750'), (1, '-527.210')] -[2023-11-28 06:45:48,756][87424] Updated weights for policy 0, policy_version 250197 (0.0007) -[2023-11-28 06:45:48,789][87426] Updated weights for policy 1, policy_version 249970 (0.0012) -[2023-11-28 06:45:49,138][87424] Updated weights for policy 0, policy_version 250207 (0.0008) -[2023-11-28 06:45:49,183][87426] Updated weights for policy 1, policy_version 249980 (0.0011) -[2023-11-28 06:45:51,222][87426] Updated weights for policy 1, policy_version 249990 (0.0011) -[2023-11-28 06:45:51,595][87426] Updated weights for policy 1, policy_version 250000 (0.0010) -[2023-11-28 06:45:51,610][87424] Updated weights for policy 0, policy_version 250217 (0.0011) -[2023-11-28 06:45:51,971][87426] Updated weights for policy 1, policy_version 250010 (0.0011) -[2023-11-28 06:45:51,997][87424] Updated weights for policy 0, policy_version 250227 (0.0011) -[2023-11-28 06:45:52,371][87424] Updated weights for policy 0, policy_version 250237 (0.0009) -[2023-11-28 06:45:53,448][86177] Fps is (10 sec: 5732.4, 60 sec: 5461.0, 300 sec: 5442.8). Total num frames: 128065536. Throughput: 0: 2653.2, 1: 2741.7. Samples: 128082148. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:53,448][86177] Avg episode reward: [(0, '-498.330'), (1, '-546.080')] -[2023-11-28 06:45:54,089][87426] Updated weights for policy 1, policy_version 250020 (0.0009) -[2023-11-28 06:45:54,459][87426] Updated weights for policy 1, policy_version 250030 (0.0008) -[2023-11-28 06:45:54,696][87424] Updated weights for policy 0, policy_version 250247 (0.0008) -[2023-11-28 06:45:54,837][87426] Updated weights for policy 1, policy_version 250040 (0.0007) -[2023-11-28 06:45:55,079][87424] Updated weights for policy 0, policy_version 250257 (0.0010) -[2023-11-28 06:45:55,468][87424] Updated weights for policy 0, policy_version 250267 (0.0012) -[2023-11-28 06:45:57,176][87426] Updated weights for policy 1, policy_version 250050 (0.0007) -[2023-11-28 06:45:57,380][87424] Updated weights for policy 0, policy_version 250277 (0.0012) -[2023-11-28 06:45:57,561][87426] Updated weights for policy 1, policy_version 250060 (0.0008) -[2023-11-28 06:45:57,774][87424] Updated weights for policy 0, policy_version 250287 (0.0010) -[2023-11-28 06:45:57,939][87426] Updated weights for policy 1, policy_version 250070 (0.0008) -[2023-11-28 06:45:58,168][87424] Updated weights for policy 0, policy_version 250297 (0.0008) -[2023-11-28 06:45:58,318][87426] Updated weights for policy 1, policy_version 250080 (0.0011) -[2023-11-28 06:45:58,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 128098304. Throughput: 0: 2647.7, 1: 2762.6. Samples: 128106908. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:45:58,446][86177] Avg episode reward: [(0, '-499.030'), (1, '-546.550')] -[2023-11-28 06:46:00,029][87426] Updated weights for policy 1, policy_version 250090 (0.0010) -[2023-11-28 06:46:00,404][87426] Updated weights for policy 1, policy_version 250100 (0.0008) -[2023-11-28 06:46:00,549][87424] Updated weights for policy 0, policy_version 250307 (0.0011) -[2023-11-28 06:46:00,781][87426] Updated weights for policy 1, policy_version 250110 (0.0008) -[2023-11-28 06:46:00,932][87424] Updated weights for policy 0, policy_version 250317 (0.0011) -[2023-11-28 06:46:01,309][87424] Updated weights for policy 0, policy_version 250327 (0.0012) -[2023-11-28 06:46:03,064][87426] Updated weights for policy 1, policy_version 250120 (0.0010) -[2023-11-28 06:46:03,435][87426] Updated weights for policy 1, policy_version 250130 (0.0011) -[2023-11-28 06:46:03,444][86177] Fps is (10 sec: 4916.9, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 128114688. Throughput: 0: 2657.3, 1: 2753.5. Samples: 128131376. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:46:03,445][86177] Avg episode reward: [(0, '-501.720'), (1, '-554.690')] -[2023-11-28 06:46:03,463][87424] Updated weights for policy 0, policy_version 250337 (0.0012) -[2023-11-28 06:46:03,814][87426] Updated weights for policy 1, policy_version 250140 (0.0008) -[2023-11-28 06:46:03,833][87424] Updated weights for policy 0, policy_version 250347 (0.0012) -[2023-11-28 06:46:04,220][87424] Updated weights for policy 0, policy_version 250357 (0.0012) -[2023-11-28 06:46:04,595][87424] Updated weights for policy 0, policy_version 250367 (0.0011) -[2023-11-28 06:46:05,640][87426] Updated weights for policy 1, policy_version 250150 (0.0010) -[2023-11-28 06:46:06,018][87426] Updated weights for policy 1, policy_version 250160 (0.0012) -[2023-11-28 06:46:06,402][87426] Updated weights for policy 1, policy_version 250170 (0.0012) -[2023-11-28 06:46:06,836][87424] Updated weights for policy 0, policy_version 250377 (0.0012) -[2023-11-28 06:46:07,215][87424] Updated weights for policy 0, policy_version 250387 (0.0012) -[2023-11-28 06:46:07,595][87424] Updated weights for policy 0, policy_version 250397 (0.0007) -[2023-11-28 06:46:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 128147456. Throughput: 0: 2666.5, 1: 2753.1. Samples: 128164552. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:46:08,445][86177] Avg episode reward: [(0, '-505.560'), (1, '-555.670')] -[2023-11-28 06:46:08,768][87426] Updated weights for policy 1, policy_version 250180 (0.0012) -[2023-11-28 06:46:09,146][87426] Updated weights for policy 1, policy_version 250190 (0.0010) -[2023-11-28 06:46:09,515][87426] Updated weights for policy 1, policy_version 250200 (0.0009) -[2023-11-28 06:46:09,685][87424] Updated weights for policy 0, policy_version 250407 (0.0008) -[2023-11-28 06:46:10,077][87424] Updated weights for policy 0, policy_version 250417 (0.0010) -[2023-11-28 06:46:10,459][87424] Updated weights for policy 0, policy_version 250427 (0.0012) -[2023-11-28 06:46:12,064][87426] Updated weights for policy 1, policy_version 250210 (0.0012) -[2023-11-28 06:46:12,437][87426] Updated weights for policy 1, policy_version 250220 (0.0011) -[2023-11-28 06:46:12,817][87426] Updated weights for policy 1, policy_version 250230 (0.0011) -[2023-11-28 06:46:12,852][87424] Updated weights for policy 0, policy_version 250437 (0.0011) -[2023-11-28 06:46:13,193][87426] Updated weights for policy 1, policy_version 250240 (0.0010) -[2023-11-28 06:46:13,244][87424] Updated weights for policy 0, policy_version 250447 (0.0010) -[2023-11-28 06:46:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 128172032. Throughput: 0: 2667.6, 1: 2767.5. Samples: 128189288. Policy #0 lag: (min: 2.0, avg: 21.1, max: 34.0) -[2023-11-28 06:46:13,445][86177] Avg episode reward: [(0, '-508.360'), (1, '-556.850')] -[2023-11-28 06:46:13,633][87424] Updated weights for policy 0, policy_version 250457 (0.0012) -[2023-11-28 06:46:15,504][87426] Updated weights for policy 1, policy_version 250250 (0.0012) -[2023-11-28 06:46:15,874][87426] Updated weights for policy 1, policy_version 250260 (0.0012) -[2023-11-28 06:46:15,934][87424] Updated weights for policy 0, policy_version 250467 (0.0011) -[2023-11-28 06:46:16,256][87426] Updated weights for policy 1, policy_version 250270 (0.0011) -[2023-11-28 06:46:16,318][87424] Updated weights for policy 0, policy_version 250477 (0.0011) -[2023-11-28 06:46:16,690][87424] Updated weights for policy 0, policy_version 250487 (0.0008) -[2023-11-28 06:46:17,968][87426] Updated weights for policy 1, policy_version 250280 (0.0008) -[2023-11-28 06:46:18,349][87426] Updated weights for policy 1, policy_version 250290 (0.0010) -[2023-11-28 06:46:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 128196608. Throughput: 0: 2644.3, 1: 2756.9. Samples: 128213048. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:46:18,446][86177] Avg episode reward: [(0, '-552.250'), (1, '-560.510')] -[2023-11-28 06:46:18,581][87424] Updated weights for policy 0, policy_version 250497 (0.0008) -[2023-11-28 06:46:18,726][87426] Updated weights for policy 1, policy_version 250300 (0.0012) -[2023-11-28 06:46:18,874][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000250304_64077824.pth... -[2023-11-28 06:46:18,914][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000247744_63422464.pth -[2023-11-28 06:46:18,961][87424] Updated weights for policy 0, policy_version 250507 (0.0010) -[2023-11-28 06:46:19,338][87424] Updated weights for policy 0, policy_version 250517 (0.0010) -[2023-11-28 06:46:19,732][87424] Updated weights for policy 0, policy_version 250527 (0.0010) -[2023-11-28 06:46:19,770][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000250528_64135168.pth... -[2023-11-28 06:46:19,821][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000248000_63488000.pth -[2023-11-28 06:46:20,907][87426] Updated weights for policy 1, policy_version 250310 (0.0012) -[2023-11-28 06:46:21,293][87426] Updated weights for policy 1, policy_version 250320 (0.0012) -[2023-11-28 06:46:21,671][87426] Updated weights for policy 1, policy_version 250330 (0.0012) -[2023-11-28 06:46:21,796][87424] Updated weights for policy 0, policy_version 250537 (0.0010) -[2023-11-28 06:46:22,192][87424] Updated weights for policy 0, policy_version 250547 (0.0012) -[2023-11-28 06:46:22,560][87424] Updated weights for policy 0, policy_version 250557 (0.0011) -[2023-11-28 06:46:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 128229376. Throughput: 0: 2646.7, 1: 2739.4. Samples: 128244876. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:46:23,445][86177] Avg episode reward: [(0, '-549.230'), (1, '-571.410')] -[2023-11-28 06:46:24,364][87426] Updated weights for policy 1, policy_version 250340 (0.0011) -[2023-11-28 06:46:24,425][87424] Updated weights for policy 0, policy_version 250567 (0.0012) -[2023-11-28 06:46:24,739][87426] Updated weights for policy 1, policy_version 250350 (0.0011) -[2023-11-28 06:46:24,806][87424] Updated weights for policy 0, policy_version 250577 (0.0009) -[2023-11-28 06:46:25,119][87426] Updated weights for policy 1, policy_version 250360 (0.0010) -[2023-11-28 06:46:25,197][87424] Updated weights for policy 0, policy_version 250587 (0.0008) -[2023-11-28 06:46:26,931][87424] Updated weights for policy 0, policy_version 250597 (0.0010) -[2023-11-28 06:46:27,306][87424] Updated weights for policy 0, policy_version 250607 (0.0012) -[2023-11-28 06:46:27,577][87426] Updated weights for policy 1, policy_version 250370 (0.0011) -[2023-11-28 06:46:27,690][87424] Updated weights for policy 0, policy_version 250617 (0.0011) -[2023-11-28 06:46:27,958][87426] Updated weights for policy 1, policy_version 250380 (0.0010) -[2023-11-28 06:46:28,327][87426] Updated weights for policy 1, policy_version 250390 (0.0012) -[2023-11-28 06:46:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 128253952. Throughput: 0: 2673.2, 1: 2742.7. Samples: 128269940. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:46:28,446][86177] Avg episode reward: [(0, '-549.380'), (1, '-594.950')] -[2023-11-28 06:46:28,715][87426] Updated weights for policy 1, policy_version 250400 (0.0012) -[2023-11-28 06:46:29,896][87424] Updated weights for policy 0, policy_version 250627 (0.0011) -[2023-11-28 06:46:30,288][87424] Updated weights for policy 0, policy_version 250637 (0.0009) -[2023-11-28 06:46:30,661][87424] Updated weights for policy 0, policy_version 250647 (0.0009) -[2023-11-28 06:46:31,297][87426] Updated weights for policy 1, policy_version 250410 (0.0008) -[2023-11-28 06:46:31,671][87426] Updated weights for policy 1, policy_version 250420 (0.0009) -[2023-11-28 06:46:32,049][87426] Updated weights for policy 1, policy_version 250430 (0.0008) -[2023-11-28 06:46:32,678][87424] Updated weights for policy 0, policy_version 250657 (0.0007) -[2023-11-28 06:46:33,058][87424] Updated weights for policy 0, policy_version 250667 (0.0009) -[2023-11-28 06:46:33,439][87424] Updated weights for policy 0, policy_version 250677 (0.0010) -[2023-11-28 06:46:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 128278528. Throughput: 0: 2704.9, 1: 2729.5. Samples: 128294924. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:46:33,445][86177] Avg episode reward: [(0, '-507.520'), (1, '-568.550')] -[2023-11-28 06:46:33,819][87424] Updated weights for policy 0, policy_version 250687 (0.0008) -[2023-11-28 06:46:34,076][87426] Updated weights for policy 1, policy_version 250440 (0.0008) -[2023-11-28 06:46:34,455][87426] Updated weights for policy 1, policy_version 250450 (0.0009) -[2023-11-28 06:46:34,843][87426] Updated weights for policy 1, policy_version 250460 (0.0009) -[2023-11-28 06:46:35,791][87424] Updated weights for policy 0, policy_version 250697 (0.0011) -[2023-11-28 06:46:36,176][87424] Updated weights for policy 0, policy_version 250707 (0.0012) -[2023-11-28 06:46:36,579][87424] Updated weights for policy 0, policy_version 250717 (0.0012) -[2023-11-28 06:46:37,053][87426] Updated weights for policy 1, policy_version 250470 (0.0011) -[2023-11-28 06:46:37,426][87426] Updated weights for policy 1, policy_version 250480 (0.0011) -[2023-11-28 06:46:37,815][87426] Updated weights for policy 1, policy_version 250490 (0.0011) -[2023-11-28 06:46:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 128311296. Throughput: 0: 2739.3, 1: 2713.3. Samples: 128327496. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:46:38,445][86177] Avg episode reward: [(0, '-507.910'), (1, '-540.890')] -[2023-11-28 06:46:39,023][87424] Updated weights for policy 0, policy_version 250727 (0.0012) -[2023-11-28 06:46:39,429][87424] Updated weights for policy 0, policy_version 250737 (0.0012) -[2023-11-28 06:46:39,793][87424] Updated weights for policy 0, policy_version 250747 (0.0012) -[2023-11-28 06:46:39,967][87426] Updated weights for policy 1, policy_version 250500 (0.0011) -[2023-11-28 06:46:40,335][87426] Updated weights for policy 1, policy_version 250510 (0.0008) -[2023-11-28 06:46:40,715][87426] Updated weights for policy 1, policy_version 250520 (0.0011) -[2023-11-28 06:46:42,250][87424] Updated weights for policy 0, policy_version 250757 (0.0011) -[2023-11-28 06:46:42,630][87424] Updated weights for policy 0, policy_version 250767 (0.0012) -[2023-11-28 06:46:42,868][87426] Updated weights for policy 1, policy_version 250530 (0.0011) -[2023-11-28 06:46:43,014][87424] Updated weights for policy 0, policy_version 250777 (0.0014) -[2023-11-28 06:46:43,238][87426] Updated weights for policy 1, policy_version 250540 (0.0011) -[2023-11-28 06:46:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 128335872. Throughput: 0: 2748.8, 1: 2698.1. Samples: 128352016. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:46:43,445][86177] Avg episode reward: [(0, '-508.090'), (1, '-535.340')] -[2023-11-28 06:46:43,623][87426] Updated weights for policy 1, policy_version 250550 (0.0009) -[2023-11-28 06:46:44,008][87426] Updated weights for policy 1, policy_version 250560 (0.0010) -[2023-11-28 06:46:45,677][87424] Updated weights for policy 0, policy_version 250787 (0.0011) -[2023-11-28 06:46:45,889][87426] Updated weights for policy 1, policy_version 250570 (0.0011) -[2023-11-28 06:46:46,063][87424] Updated weights for policy 0, policy_version 250797 (0.0011) -[2023-11-28 06:46:46,265][87426] Updated weights for policy 1, policy_version 250580 (0.0010) -[2023-11-28 06:46:46,442][87424] Updated weights for policy 0, policy_version 250807 (0.0008) -[2023-11-28 06:46:46,644][87426] Updated weights for policy 1, policy_version 250590 (0.0007) -[2023-11-28 06:46:48,255][87426] Updated weights for policy 1, policy_version 250600 (0.0008) -[2023-11-28 06:46:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128360448. Throughput: 0: 2735.9, 1: 2683.1. Samples: 128375232. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:46:48,445][86177] Avg episode reward: [(0, '-504.200'), (1, '-500.820')] -[2023-11-28 06:46:48,629][87426] Updated weights for policy 1, policy_version 250610 (0.0010) -[2023-11-28 06:46:48,863][87424] Updated weights for policy 0, policy_version 250817 (0.0008) -[2023-11-28 06:46:49,015][87426] Updated weights for policy 1, policy_version 250620 (0.0009) -[2023-11-28 06:46:49,246][87424] Updated weights for policy 0, policy_version 250827 (0.0010) -[2023-11-28 06:46:49,630][87424] Updated weights for policy 0, policy_version 250837 (0.0009) -[2023-11-28 06:46:50,046][87424] Updated weights for policy 0, policy_version 250848 (0.0010) -[2023-11-28 06:46:51,175][87426] Updated weights for policy 1, policy_version 250630 (0.0011) -[2023-11-28 06:46:51,558][87426] Updated weights for policy 1, policy_version 250640 (0.0008) -[2023-11-28 06:46:51,936][87426] Updated weights for policy 1, policy_version 250650 (0.0011) -[2023-11-28 06:46:52,110][87424] Updated weights for policy 0, policy_version 250858 (0.0011) -[2023-11-28 06:46:52,489][87424] Updated weights for policy 0, policy_version 250868 (0.0011) -[2023-11-28 06:46:52,877][87424] Updated weights for policy 0, policy_version 250878 (0.0012) -[2023-11-28 06:46:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.7, 300 sec: 5415.0). Total num frames: 128393216. Throughput: 0: 2693.7, 1: 2682.1. Samples: 128406464. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:46:53,445][86177] Avg episode reward: [(0, '-499.570'), (1, '-500.030')] -[2023-11-28 06:46:53,935][87426] Updated weights for policy 1, policy_version 250660 (0.0011) -[2023-11-28 06:46:54,308][87426] Updated weights for policy 1, policy_version 250670 (0.0008) -[2023-11-28 06:46:54,687][87426] Updated weights for policy 1, policy_version 250680 (0.0007) -[2023-11-28 06:46:54,988][87424] Updated weights for policy 0, policy_version 250888 (0.0009) -[2023-11-28 06:46:55,378][87424] Updated weights for policy 0, policy_version 250898 (0.0010) -[2023-11-28 06:46:55,757][87424] Updated weights for policy 0, policy_version 250908 (0.0008) -[2023-11-28 06:46:57,256][87426] Updated weights for policy 1, policy_version 250690 (0.0007) -[2023-11-28 06:46:57,406][87424] Updated weights for policy 0, policy_version 250918 (0.0011) -[2023-11-28 06:46:57,635][87426] Updated weights for policy 1, policy_version 250700 (0.0007) -[2023-11-28 06:46:57,787][87424] Updated weights for policy 0, policy_version 250928 (0.0011) -[2023-11-28 06:46:58,018][87426] Updated weights for policy 1, policy_version 250710 (0.0008) -[2023-11-28 06:46:58,173][87424] Updated weights for policy 0, policy_version 250938 (0.0008) -[2023-11-28 06:46:58,400][87426] Updated weights for policy 1, policy_version 250720 (0.0007) -[2023-11-28 06:46:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 128425984. Throughput: 0: 2693.4, 1: 2684.4. Samples: 128431292. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:46:58,445][86177] Avg episode reward: [(0, '-507.850'), (1, '-500.190')] -[2023-11-28 06:47:00,107][87424] Updated weights for policy 0, policy_version 250948 (0.0008) -[2023-11-28 06:47:00,497][87424] Updated weights for policy 0, policy_version 250958 (0.0009) -[2023-11-28 06:47:00,839][87426] Updated weights for policy 1, policy_version 250730 (0.0012) -[2023-11-28 06:47:00,876][87424] Updated weights for policy 0, policy_version 250968 (0.0012) -[2023-11-28 06:47:01,220][87426] Updated weights for policy 1, policy_version 250740 (0.0011) -[2023-11-28 06:47:01,594][87426] Updated weights for policy 1, policy_version 250750 (0.0012) -[2023-11-28 06:47:03,010][87424] Updated weights for policy 0, policy_version 250978 (0.0011) -[2023-11-28 06:47:03,396][87424] Updated weights for policy 0, policy_version 250988 (0.0011) -[2023-11-28 06:47:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128442368. Throughput: 0: 2728.6, 1: 2684.6. Samples: 128456640. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:47:03,445][86177] Avg episode reward: [(0, '-508.230'), (1, '-501.890')] -[2023-11-28 06:47:03,768][87424] Updated weights for policy 0, policy_version 250998 (0.0008) -[2023-11-28 06:47:03,999][87426] Updated weights for policy 1, policy_version 250760 (0.0009) -[2023-11-28 06:47:04,153][87424] Updated weights for policy 0, policy_version 251008 (0.0008) -[2023-11-28 06:47:04,377][87426] Updated weights for policy 1, policy_version 250770 (0.0011) -[2023-11-28 06:47:04,756][87426] Updated weights for policy 1, policy_version 250780 (0.0012) -[2023-11-28 06:47:06,104][87424] Updated weights for policy 0, policy_version 251018 (0.0009) -[2023-11-28 06:47:06,481][87424] Updated weights for policy 0, policy_version 251028 (0.0008) -[2023-11-28 06:47:06,739][87426] Updated weights for policy 1, policy_version 250790 (0.0010) -[2023-11-28 06:47:06,862][87424] Updated weights for policy 0, policy_version 251038 (0.0012) -[2023-11-28 06:47:07,106][87426] Updated weights for policy 1, policy_version 250800 (0.0009) -[2023-11-28 06:47:07,485][87426] Updated weights for policy 1, policy_version 250810 (0.0012) -[2023-11-28 06:47:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 128475136. Throughput: 0: 2753.3, 1: 2694.0. Samples: 128490004. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:47:08,445][86177] Avg episode reward: [(0, '-512.840'), (1, '-503.660')] -[2023-11-28 06:47:08,932][87424] Updated weights for policy 0, policy_version 251048 (0.0009) -[2023-11-28 06:47:09,311][87424] Updated weights for policy 0, policy_version 251058 (0.0008) -[2023-11-28 06:47:09,519][87426] Updated weights for policy 1, policy_version 250820 (0.0011) -[2023-11-28 06:47:09,696][87424] Updated weights for policy 0, policy_version 251068 (0.0007) -[2023-11-28 06:47:09,898][87426] Updated weights for policy 1, policy_version 250830 (0.0012) -[2023-11-28 06:47:10,270][87426] Updated weights for policy 1, policy_version 250840 (0.0012) -[2023-11-28 06:47:11,526][87424] Updated weights for policy 0, policy_version 251078 (0.0009) -[2023-11-28 06:47:11,915][87424] Updated weights for policy 0, policy_version 251088 (0.0010) -[2023-11-28 06:47:12,290][87424] Updated weights for policy 0, policy_version 251098 (0.0012) -[2023-11-28 06:47:12,742][87426] Updated weights for policy 1, policy_version 250850 (0.0010) -[2023-11-28 06:47:13,118][87426] Updated weights for policy 1, policy_version 250860 (0.0011) -[2023-11-28 06:47:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128499712. Throughput: 0: 2741.3, 1: 2701.9. Samples: 128514884. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:47:13,445][86177] Avg episode reward: [(0, '-507.570'), (1, '-509.280')] -[2023-11-28 06:47:13,496][87426] Updated weights for policy 1, policy_version 250870 (0.0012) -[2023-11-28 06:47:13,876][87426] Updated weights for policy 1, policy_version 250880 (0.0011) -[2023-11-28 06:47:14,244][87424] Updated weights for policy 0, policy_version 251108 (0.0011) -[2023-11-28 06:47:14,620][87424] Updated weights for policy 0, policy_version 251118 (0.0012) -[2023-11-28 06:47:15,011][87424] Updated weights for policy 0, policy_version 251128 (0.0011) -[2023-11-28 06:47:15,696][87426] Updated weights for policy 1, policy_version 250890 (0.0012) -[2023-11-28 06:47:16,081][87426] Updated weights for policy 1, policy_version 250900 (0.0012) -[2023-11-28 06:47:16,460][87426] Updated weights for policy 1, policy_version 250910 (0.0012) -[2023-11-28 06:47:17,346][87424] Updated weights for policy 0, policy_version 251138 (0.0011) -[2023-11-28 06:47:17,727][87424] Updated weights for policy 0, policy_version 251148 (0.0007) -[2023-11-28 06:47:18,113][87424] Updated weights for policy 0, policy_version 251158 (0.0008) -[2023-11-28 06:47:18,278][87426] Updated weights for policy 1, policy_version 250920 (0.0011) -[2023-11-28 06:47:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128524288. Throughput: 0: 2734.1, 1: 2728.5. Samples: 128540744. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:47:18,446][86177] Avg episode reward: [(0, '-503.920'), (1, '-509.010')] -[2023-11-28 06:47:18,494][87424] Updated weights for policy 0, policy_version 251168 (0.0011) -[2023-11-28 06:47:18,660][87426] Updated weights for policy 1, policy_version 250930 (0.0007) -[2023-11-28 06:47:19,036][87426] Updated weights for policy 1, policy_version 250940 (0.0008) -[2023-11-28 06:47:20,840][87424] Updated weights for policy 0, policy_version 251178 (0.0010) -[2023-11-28 06:47:21,151][87426] Updated weights for policy 1, policy_version 250950 (0.0011) -[2023-11-28 06:47:21,223][87424] Updated weights for policy 0, policy_version 251188 (0.0011) -[2023-11-28 06:47:21,527][87426] Updated weights for policy 1, policy_version 250960 (0.0008) -[2023-11-28 06:47:21,610][87424] Updated weights for policy 0, policy_version 251198 (0.0011) -[2023-11-28 06:47:21,908][87426] Updated weights for policy 1, policy_version 250970 (0.0009) -[2023-11-28 06:47:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128557056. Throughput: 0: 2704.0, 1: 2725.8. Samples: 128571836. Policy #0 lag: (min: 6.0, avg: 12.0, max: 38.0) -[2023-11-28 06:47:23,445][86177] Avg episode reward: [(0, '-541.560'), (1, '-513.830')] -[2023-11-28 06:47:24,079][87424] Updated weights for policy 0, policy_version 251208 (0.0009) -[2023-11-28 06:47:24,363][87426] Updated weights for policy 1, policy_version 250980 (0.0011) -[2023-11-28 06:47:24,462][87424] Updated weights for policy 0, policy_version 251218 (0.0008) -[2023-11-28 06:47:24,737][87426] Updated weights for policy 1, policy_version 250990 (0.0011) -[2023-11-28 06:47:24,842][87424] Updated weights for policy 0, policy_version 251228 (0.0007) -[2023-11-28 06:47:25,125][87426] Updated weights for policy 1, policy_version 251000 (0.0011) -[2023-11-28 06:47:27,078][87426] Updated weights for policy 1, policy_version 251010 (0.0008) -[2023-11-28 06:47:27,386][87424] Updated weights for policy 0, policy_version 251238 (0.0010) -[2023-11-28 06:47:27,449][87426] Updated weights for policy 1, policy_version 251020 (0.0010) -[2023-11-28 06:47:27,764][87424] Updated weights for policy 0, policy_version 251248 (0.0011) -[2023-11-28 06:47:27,835][87426] Updated weights for policy 1, policy_version 251030 (0.0011) -[2023-11-28 06:47:28,154][87424] Updated weights for policy 0, policy_version 251258 (0.0012) -[2023-11-28 06:47:28,210][87426] Updated weights for policy 1, policy_version 251040 (0.0011) -[2023-11-28 06:47:28,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 128589824. Throughput: 0: 2703.0, 1: 2741.3. Samples: 128597012. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:47:28,445][86177] Avg episode reward: [(0, '-539.160'), (1, '-516.260')] -[2023-11-28 06:47:30,162][87426] Updated weights for policy 1, policy_version 251050 (0.0011) -[2023-11-28 06:47:30,374][87424] Updated weights for policy 0, policy_version 251268 (0.0012) -[2023-11-28 06:47:30,536][87426] Updated weights for policy 1, policy_version 251060 (0.0011) -[2023-11-28 06:47:30,760][87424] Updated weights for policy 0, policy_version 251278 (0.0011) -[2023-11-28 06:47:30,900][87426] Updated weights for policy 1, policy_version 251070 (0.0011) -[2023-11-28 06:47:31,138][87424] Updated weights for policy 0, policy_version 251288 (0.0012) -[2023-11-28 06:47:33,174][87424] Updated weights for policy 0, policy_version 251298 (0.0009) -[2023-11-28 06:47:33,361][87426] Updated weights for policy 1, policy_version 251080 (0.0011) -[2023-11-28 06:47:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 128606208. Throughput: 0: 2712.4, 1: 2745.8. Samples: 128620852. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:47:33,445][86177] Avg episode reward: [(0, '-537.680'), (1, '-519.920')] -[2023-11-28 06:47:33,554][87424] Updated weights for policy 0, policy_version 251308 (0.0011) -[2023-11-28 06:47:33,729][87426] Updated weights for policy 1, policy_version 251090 (0.0012) -[2023-11-28 06:47:33,930][87424] Updated weights for policy 0, policy_version 251318 (0.0007) -[2023-11-28 06:47:34,110][87426] Updated weights for policy 1, policy_version 251100 (0.0011) -[2023-11-28 06:47:34,313][87424] Updated weights for policy 0, policy_version 251328 (0.0008) -[2023-11-28 06:47:36,395][87426] Updated weights for policy 1, policy_version 251110 (0.0011) -[2023-11-28 06:47:36,790][87426] Updated weights for policy 1, policy_version 251120 (0.0008) -[2023-11-28 06:47:36,844][87424] Updated weights for policy 0, policy_version 251338 (0.0010) -[2023-11-28 06:47:37,158][87426] Updated weights for policy 1, policy_version 251130 (0.0009) -[2023-11-28 06:47:37,230][87424] Updated weights for policy 0, policy_version 251348 (0.0012) -[2023-11-28 06:47:37,602][87424] Updated weights for policy 0, policy_version 251358 (0.0011) -[2023-11-28 06:47:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128638976. Throughput: 0: 2718.5, 1: 2740.5. Samples: 128652120. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:47:38,445][86177] Avg episode reward: [(0, '-537.920'), (1, '-519.600')] -[2023-11-28 06:47:39,525][87426] Updated weights for policy 1, policy_version 251140 (0.0009) -[2023-11-28 06:47:39,607][87424] Updated weights for policy 0, policy_version 251368 (0.0010) -[2023-11-28 06:47:39,902][87426] Updated weights for policy 1, policy_version 251150 (0.0011) -[2023-11-28 06:47:39,991][87424] Updated weights for policy 0, policy_version 251378 (0.0011) -[2023-11-28 06:47:40,278][87426] Updated weights for policy 1, policy_version 251160 (0.0008) -[2023-11-28 06:47:40,380][87424] Updated weights for policy 0, policy_version 251388 (0.0012) -[2023-11-28 06:47:42,771][87426] Updated weights for policy 1, policy_version 251170 (0.0010) -[2023-11-28 06:47:42,885][87424] Updated weights for policy 0, policy_version 251398 (0.0010) -[2023-11-28 06:47:43,152][87426] Updated weights for policy 1, policy_version 251180 (0.0011) -[2023-11-28 06:47:43,270][87424] Updated weights for policy 0, policy_version 251408 (0.0011) -[2023-11-28 06:47:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 128655360. Throughput: 0: 2726.6, 1: 2730.5. Samples: 128676860. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:47:43,445][86177] Avg episode reward: [(0, '-496.150'), (1, '-520.560')] -[2023-11-28 06:47:43,537][87426] Updated weights for policy 1, policy_version 251190 (0.0011) -[2023-11-28 06:47:43,654][87424] Updated weights for policy 0, policy_version 251418 (0.0011) -[2023-11-28 06:47:43,914][87426] Updated weights for policy 1, policy_version 251200 (0.0010) -[2023-11-28 06:47:45,603][87426] Updated weights for policy 1, policy_version 251210 (0.0012) -[2023-11-28 06:47:45,950][87424] Updated weights for policy 0, policy_version 251428 (0.0011) -[2023-11-28 06:47:45,972][87426] Updated weights for policy 1, policy_version 251220 (0.0011) -[2023-11-28 06:47:46,337][87424] Updated weights for policy 0, policy_version 251438 (0.0007) -[2023-11-28 06:47:46,351][87426] Updated weights for policy 1, policy_version 251230 (0.0012) -[2023-11-28 06:47:46,724][87424] Updated weights for policy 0, policy_version 251448 (0.0013) -[2023-11-28 06:47:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128688128. Throughput: 0: 2695.1, 1: 2726.6. Samples: 128700616. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:47:48,445][86177] Avg episode reward: [(0, '-496.980'), (1, '-513.170')] -[2023-11-28 06:47:48,487][87426] Updated weights for policy 1, policy_version 251240 (0.0012) -[2023-11-28 06:47:48,541][87424] Updated weights for policy 0, policy_version 251458 (0.0010) -[2023-11-28 06:47:48,863][87426] Updated weights for policy 1, policy_version 251250 (0.0012) -[2023-11-28 06:47:48,916][87424] Updated weights for policy 0, policy_version 251468 (0.0011) -[2023-11-28 06:47:49,247][87426] Updated weights for policy 1, policy_version 251260 (0.0011) -[2023-11-28 06:47:49,294][87424] Updated weights for policy 0, policy_version 251478 (0.0009) -[2023-11-28 06:47:49,679][87424] Updated weights for policy 0, policy_version 251488 (0.0012) -[2023-11-28 06:47:51,512][87426] Updated weights for policy 1, policy_version 251270 (0.0009) -[2023-11-28 06:47:51,888][87426] Updated weights for policy 1, policy_version 251280 (0.0021) -[2023-11-28 06:47:52,256][87424] Updated weights for policy 0, policy_version 251498 (0.0009) -[2023-11-28 06:47:52,265][87426] Updated weights for policy 1, policy_version 251290 (0.0011) -[2023-11-28 06:47:52,636][87424] Updated weights for policy 0, policy_version 251508 (0.0008) -[2023-11-28 06:47:53,027][87424] Updated weights for policy 0, policy_version 251518 (0.0009) -[2023-11-28 06:47:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128720896. Throughput: 0: 2668.6, 1: 2733.5. Samples: 128733100. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:47:53,445][86177] Avg episode reward: [(0, '-495.330'), (1, '-513.960')] -[2023-11-28 06:47:54,568][87426] Updated weights for policy 1, policy_version 251300 (0.0011) -[2023-11-28 06:47:54,952][87426] Updated weights for policy 1, policy_version 251310 (0.0012) -[2023-11-28 06:47:55,329][87426] Updated weights for policy 1, policy_version 251320 (0.0008) -[2023-11-28 06:47:55,510][87424] Updated weights for policy 0, policy_version 251528 (0.0008) -[2023-11-28 06:47:55,885][87424] Updated weights for policy 0, policy_version 251538 (0.0012) -[2023-11-28 06:47:56,269][87424] Updated weights for policy 0, policy_version 251548 (0.0010) -[2023-11-28 06:47:57,839][87426] Updated weights for policy 1, policy_version 251330 (0.0011) -[2023-11-28 06:47:58,215][87426] Updated weights for policy 1, policy_version 251340 (0.0012) -[2023-11-28 06:47:58,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5188.2, 300 sec: 5415.0). Total num frames: 128737280. Throughput: 0: 2642.0, 1: 2723.9. Samples: 128756352. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:47:58,446][86177] Avg episode reward: [(0, '-494.420'), (1, '-507.020')] -[2023-11-28 06:47:58,483][87424] Updated weights for policy 0, policy_version 251558 (0.0010) -[2023-11-28 06:47:58,590][87426] Updated weights for policy 1, policy_version 251350 (0.0007) -[2023-11-28 06:47:58,867][87424] Updated weights for policy 0, policy_version 251568 (0.0012) -[2023-11-28 06:47:58,979][87426] Updated weights for policy 1, policy_version 251360 (0.0008) -[2023-11-28 06:47:59,246][87424] Updated weights for policy 0, policy_version 251578 (0.0008) -[2023-11-28 06:48:00,977][87426] Updated weights for policy 1, policy_version 251370 (0.0012) -[2023-11-28 06:48:01,350][87426] Updated weights for policy 1, policy_version 251380 (0.0011) -[2023-11-28 06:48:01,381][87424] Updated weights for policy 0, policy_version 251588 (0.0007) -[2023-11-28 06:48:01,729][87426] Updated weights for policy 1, policy_version 251390 (0.0011) -[2023-11-28 06:48:01,764][87424] Updated weights for policy 0, policy_version 251598 (0.0009) -[2023-11-28 06:48:02,142][87424] Updated weights for policy 0, policy_version 251608 (0.0012) -[2023-11-28 06:48:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128770048. Throughput: 0: 2637.3, 1: 2694.0. Samples: 128780648. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:48:03,445][86177] Avg episode reward: [(0, '-495.580'), (1, '-510.450')] -[2023-11-28 06:48:03,710][87426] Updated weights for policy 1, policy_version 251400 (0.0012) -[2023-11-28 06:48:04,090][87426] Updated weights for policy 1, policy_version 251410 (0.0012) -[2023-11-28 06:48:04,228][87424] Updated weights for policy 0, policy_version 251618 (0.0012) -[2023-11-28 06:48:04,463][87426] Updated weights for policy 1, policy_version 251420 (0.0012) -[2023-11-28 06:48:04,614][87424] Updated weights for policy 0, policy_version 251628 (0.0011) -[2023-11-28 06:48:04,993][87424] Updated weights for policy 0, policy_version 251638 (0.0012) -[2023-11-28 06:48:05,374][87424] Updated weights for policy 0, policy_version 251648 (0.0012) -[2023-11-28 06:48:06,295][87426] Updated weights for policy 1, policy_version 251430 (0.0012) -[2023-11-28 06:48:06,673][87426] Updated weights for policy 1, policy_version 251440 (0.0012) -[2023-11-28 06:48:07,050][87426] Updated weights for policy 1, policy_version 251450 (0.0012) -[2023-11-28 06:48:07,621][87424] Updated weights for policy 0, policy_version 251658 (0.0011) -[2023-11-28 06:48:08,002][87424] Updated weights for policy 0, policy_version 251668 (0.0012) -[2023-11-28 06:48:08,384][87424] Updated weights for policy 0, policy_version 251678 (0.0008) -[2023-11-28 06:48:08,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 128794624. Throughput: 0: 2669.8, 1: 2710.8. Samples: 128813960. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:48:08,445][86177] Avg episode reward: [(0, '-494.980'), (1, '-536.280')] -[2023-11-28 06:48:08,975][87426] Updated weights for policy 1, policy_version 251460 (0.0011) -[2023-11-28 06:48:09,355][87426] Updated weights for policy 1, policy_version 251470 (0.0011) -[2023-11-28 06:48:09,730][87426] Updated weights for policy 1, policy_version 251480 (0.0012) -[2023-11-28 06:48:10,732][87424] Updated weights for policy 0, policy_version 251688 (0.0011) -[2023-11-28 06:48:11,108][87424] Updated weights for policy 0, policy_version 251698 (0.0012) -[2023-11-28 06:48:11,498][87424] Updated weights for policy 0, policy_version 251708 (0.0012) -[2023-11-28 06:48:12,136][87426] Updated weights for policy 1, policy_version 251490 (0.0010) -[2023-11-28 06:48:12,526][87426] Updated weights for policy 1, policy_version 251500 (0.0011) -[2023-11-28 06:48:12,901][87426] Updated weights for policy 1, policy_version 251510 (0.0011) -[2023-11-28 06:48:13,274][87426] Updated weights for policy 1, policy_version 251520 (0.0010) -[2023-11-28 06:48:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 128827392. Throughput: 0: 2669.8, 1: 2689.3. Samples: 128838168. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:48:13,445][86177] Avg episode reward: [(0, '-497.250'), (1, '-536.330')] -[2023-11-28 06:48:13,527][87424] Updated weights for policy 0, policy_version 251718 (0.0012) -[2023-11-28 06:48:13,902][87424] Updated weights for policy 0, policy_version 251728 (0.0011) -[2023-11-28 06:48:14,283][87424] Updated weights for policy 0, policy_version 251738 (0.0008) -[2023-11-28 06:48:15,845][87426] Updated weights for policy 1, policy_version 251530 (0.0012) -[2023-11-28 06:48:16,217][87426] Updated weights for policy 1, policy_version 251540 (0.0012) -[2023-11-28 06:48:16,486][87424] Updated weights for policy 0, policy_version 251748 (0.0009) -[2023-11-28 06:48:16,585][87426] Updated weights for policy 1, policy_version 251550 (0.0010) -[2023-11-28 06:48:16,867][87424] Updated weights for policy 0, policy_version 251758 (0.0012) -[2023-11-28 06:48:17,259][87424] Updated weights for policy 0, policy_version 251768 (0.0009) -[2023-11-28 06:48:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128851968. Throughput: 0: 2679.6, 1: 2678.0. Samples: 128861944. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:48:18,445][86177] Avg episode reward: [(0, '-501.400'), (1, '-540.070')] -[2023-11-28 06:48:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000251776_64454656.pth... -[2023-11-28 06:48:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000251552_64397312.pth... -[2023-11-28 06:48:18,493][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000249024_63750144.pth -[2023-11-28 06:48:18,499][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000249248_63807488.pth -[2023-11-28 06:48:19,062][87426] Updated weights for policy 1, policy_version 251560 (0.0012) -[2023-11-28 06:48:19,214][87424] Updated weights for policy 0, policy_version 251778 (0.0008) -[2023-11-28 06:48:19,436][87426] Updated weights for policy 1, policy_version 251570 (0.0012) -[2023-11-28 06:48:19,594][87424] Updated weights for policy 0, policy_version 251788 (0.0012) -[2023-11-28 06:48:19,829][87426] Updated weights for policy 1, policy_version 251580 (0.0011) -[2023-11-28 06:48:19,979][87424] Updated weights for policy 0, policy_version 251798 (0.0011) -[2023-11-28 06:48:20,360][87424] Updated weights for policy 0, policy_version 251808 (0.0012) -[2023-11-28 06:48:21,837][87426] Updated weights for policy 1, policy_version 251590 (0.0011) -[2023-11-28 06:48:22,223][87426] Updated weights for policy 1, policy_version 251600 (0.0009) -[2023-11-28 06:48:22,527][87424] Updated weights for policy 0, policy_version 251818 (0.0012) -[2023-11-28 06:48:22,609][87426] Updated weights for policy 1, policy_version 251610 (0.0009) -[2023-11-28 06:48:22,903][87424] Updated weights for policy 0, policy_version 251828 (0.0012) -[2023-11-28 06:48:23,292][87424] Updated weights for policy 0, policy_version 251838 (0.0012) -[2023-11-28 06:48:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 128884736. Throughput: 0: 2712.3, 1: 2676.2. Samples: 128894600. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:48:23,445][86177] Avg episode reward: [(0, '-499.270'), (1, '-541.450')] -[2023-11-28 06:48:25,128][87426] Updated weights for policy 1, policy_version 251620 (0.0011) -[2023-11-28 06:48:25,416][87424] Updated weights for policy 0, policy_version 251848 (0.0009) -[2023-11-28 06:48:25,503][87426] Updated weights for policy 1, policy_version 251630 (0.0012) -[2023-11-28 06:48:25,803][87424] Updated weights for policy 0, policy_version 251858 (0.0011) -[2023-11-28 06:48:25,883][87426] Updated weights for policy 1, policy_version 251640 (0.0007) -[2023-11-28 06:48:26,179][87424] Updated weights for policy 0, policy_version 251868 (0.0011) -[2023-11-28 06:48:28,076][87424] Updated weights for policy 0, policy_version 251878 (0.0012) -[2023-11-28 06:48:28,177][87426] Updated weights for policy 1, policy_version 251650 (0.0008) -[2023-11-28 06:48:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 128901120. Throughput: 0: 2724.1, 1: 2696.1. Samples: 128920768. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:48:28,445][86177] Avg episode reward: [(0, '-501.290'), (1, '-515.410')] -[2023-11-28 06:48:28,456][87424] Updated weights for policy 0, policy_version 251888 (0.0011) -[2023-11-28 06:48:28,560][87426] Updated weights for policy 1, policy_version 251660 (0.0010) -[2023-11-28 06:48:28,844][87424] Updated weights for policy 0, policy_version 251898 (0.0011) -[2023-11-28 06:48:28,932][87426] Updated weights for policy 1, policy_version 251670 (0.0008) -[2023-11-28 06:48:29,310][87426] Updated weights for policy 1, policy_version 251680 (0.0007) -[2023-11-28 06:48:30,893][87424] Updated weights for policy 0, policy_version 251908 (0.0009) -[2023-11-28 06:48:31,284][87424] Updated weights for policy 0, policy_version 251918 (0.0010) -[2023-11-28 06:48:31,441][87426] Updated weights for policy 1, policy_version 251690 (0.0011) -[2023-11-28 06:48:31,665][87424] Updated weights for policy 0, policy_version 251928 (0.0011) -[2023-11-28 06:48:31,812][87426] Updated weights for policy 1, policy_version 251700 (0.0011) -[2023-11-28 06:48:32,192][87426] Updated weights for policy 1, policy_version 251710 (0.0012) -[2023-11-28 06:48:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 128933888. Throughput: 0: 2742.4, 1: 2715.3. Samples: 128946212. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:48:33,445][86177] Avg episode reward: [(0, '-541.120'), (1, '-513.200')] -[2023-11-28 06:48:33,591][87424] Updated weights for policy 0, policy_version 251938 (0.0012) -[2023-11-28 06:48:33,965][87424] Updated weights for policy 0, policy_version 251948 (0.0012) -[2023-11-28 06:48:34,278][87426] Updated weights for policy 1, policy_version 251720 (0.0011) -[2023-11-28 06:48:34,344][87424] Updated weights for policy 0, policy_version 251958 (0.0011) -[2023-11-28 06:48:34,664][87426] Updated weights for policy 1, policy_version 251730 (0.0010) -[2023-11-28 06:48:34,726][87424] Updated weights for policy 0, policy_version 251968 (0.0012) -[2023-11-28 06:48:35,036][87426] Updated weights for policy 1, policy_version 251740 (0.0011) -[2023-11-28 06:48:36,408][87424] Updated weights for policy 0, policy_version 251978 (0.0008) -[2023-11-28 06:48:36,791][87424] Updated weights for policy 0, policy_version 251988 (0.0009) -[2023-11-28 06:48:37,172][87424] Updated weights for policy 0, policy_version 251998 (0.0012) -[2023-11-28 06:48:37,331][87426] Updated weights for policy 1, policy_version 251750 (0.0011) -[2023-11-28 06:48:37,705][87426] Updated weights for policy 1, policy_version 251760 (0.0012) -[2023-11-28 06:48:38,096][87426] Updated weights for policy 1, policy_version 251770 (0.0012) -[2023-11-28 06:48:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128966656. Throughput: 0: 2765.1, 1: 2714.6. Samples: 128979684. Policy #0 lag: (min: 31.0, avg: 38.7, max: 63.0) -[2023-11-28 06:48:38,445][86177] Avg episode reward: [(0, '-543.080'), (1, '-538.780')] -[2023-11-28 06:48:39,396][87424] Updated weights for policy 0, policy_version 252008 (0.0010) -[2023-11-28 06:48:39,779][87424] Updated weights for policy 0, policy_version 252018 (0.0011) -[2023-11-28 06:48:39,864][87426] Updated weights for policy 1, policy_version 251780 (0.0011) -[2023-11-28 06:48:40,157][87424] Updated weights for policy 0, policy_version 252028 (0.0012) -[2023-11-28 06:48:40,239][87426] Updated weights for policy 1, policy_version 251790 (0.0008) -[2023-11-28 06:48:40,617][87426] Updated weights for policy 1, policy_version 251800 (0.0010) -[2023-11-28 06:48:42,648][87424] Updated weights for policy 0, policy_version 252038 (0.0011) -[2023-11-28 06:48:43,021][87424] Updated weights for policy 0, policy_version 252048 (0.0011) -[2023-11-28 06:48:43,112][87426] Updated weights for policy 1, policy_version 251810 (0.0009) -[2023-11-28 06:48:43,406][87424] Updated weights for policy 0, policy_version 252058 (0.0012) -[2023-11-28 06:48:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 128983040. Throughput: 0: 2773.4, 1: 2711.5. Samples: 129003168. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:48:43,445][86177] Avg episode reward: [(0, '-584.040'), (1, '-537.890')] -[2023-11-28 06:48:43,489][87426] Updated weights for policy 1, policy_version 251820 (0.0008) -[2023-11-28 06:48:43,860][87426] Updated weights for policy 1, policy_version 251830 (0.0007) -[2023-11-28 06:48:44,243][87426] Updated weights for policy 1, policy_version 251840 (0.0007) -[2023-11-28 06:48:45,659][87424] Updated weights for policy 0, policy_version 252068 (0.0012) -[2023-11-28 06:48:46,045][87424] Updated weights for policy 0, policy_version 252078 (0.0012) -[2023-11-28 06:48:46,435][87424] Updated weights for policy 0, policy_version 252088 (0.0011) -[2023-11-28 06:48:46,670][87426] Updated weights for policy 1, policy_version 251850 (0.0008) -[2023-11-28 06:48:47,053][87426] Updated weights for policy 1, policy_version 251860 (0.0012) -[2023-11-28 06:48:47,433][87426] Updated weights for policy 1, policy_version 251870 (0.0012) -[2023-11-28 06:48:48,080][87424] Updated weights for policy 0, policy_version 252098 (0.0010) -[2023-11-28 06:48:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 129015808. Throughput: 0: 2771.1, 1: 2717.7. Samples: 129027644. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:48:48,445][86177] Avg episode reward: [(0, '-583.730'), (1, '-545.310')] -[2023-11-28 06:48:48,456][87424] Updated weights for policy 0, policy_version 252108 (0.0012) -[2023-11-28 06:48:48,837][87424] Updated weights for policy 0, policy_version 252118 (0.0009) -[2023-11-28 06:48:49,212][87424] Updated weights for policy 0, policy_version 252128 (0.0011) -[2023-11-28 06:48:49,379][87426] Updated weights for policy 1, policy_version 251880 (0.0011) -[2023-11-28 06:48:49,751][87426] Updated weights for policy 1, policy_version 251890 (0.0011) -[2023-11-28 06:48:50,129][87426] Updated weights for policy 1, policy_version 251900 (0.0008) -[2023-11-28 06:48:51,186][87424] Updated weights for policy 0, policy_version 252138 (0.0010) -[2023-11-28 06:48:51,575][87424] Updated weights for policy 0, policy_version 252148 (0.0008) -[2023-11-28 06:48:51,956][87424] Updated weights for policy 0, policy_version 252158 (0.0010) -[2023-11-28 06:48:52,481][87426] Updated weights for policy 1, policy_version 251910 (0.0008) -[2023-11-28 06:48:52,857][87426] Updated weights for policy 1, policy_version 251920 (0.0010) -[2023-11-28 06:48:53,240][87426] Updated weights for policy 1, policy_version 251930 (0.0010) -[2023-11-28 06:48:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 129040384. Throughput: 0: 2783.1, 1: 2704.9. Samples: 129060920. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:48:53,445][86177] Avg episode reward: [(0, '-582.860'), (1, '-573.900')] -[2023-11-28 06:48:54,019][87424] Updated weights for policy 0, policy_version 252168 (0.0011) -[2023-11-28 06:48:54,411][87424] Updated weights for policy 0, policy_version 252178 (0.0009) -[2023-11-28 06:48:54,788][87424] Updated weights for policy 0, policy_version 252188 (0.0012) -[2023-11-28 06:48:55,713][87426] Updated weights for policy 1, policy_version 251940 (0.0010) -[2023-11-28 06:48:56,095][87426] Updated weights for policy 1, policy_version 251950 (0.0010) -[2023-11-28 06:48:56,476][87426] Updated weights for policy 1, policy_version 251960 (0.0009) -[2023-11-28 06:48:57,403][87424] Updated weights for policy 0, policy_version 252198 (0.0009) -[2023-11-28 06:48:57,796][87424] Updated weights for policy 0, policy_version 252208 (0.0012) -[2023-11-28 06:48:58,169][87424] Updated weights for policy 0, policy_version 252218 (0.0009) -[2023-11-28 06:48:58,223][87426] Updated weights for policy 1, policy_version 251970 (0.0009) -[2023-11-28 06:48:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 129073152. Throughput: 0: 2774.5, 1: 2713.3. Samples: 129085120. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:48:58,445][86177] Avg episode reward: [(0, '-537.330'), (1, '-561.650')] -[2023-11-28 06:48:58,600][87426] Updated weights for policy 1, policy_version 251980 (0.0009) -[2023-11-28 06:48:58,975][87426] Updated weights for policy 1, policy_version 251990 (0.0007) -[2023-11-28 06:48:59,351][87426] Updated weights for policy 1, policy_version 252000 (0.0008) -[2023-11-28 06:49:00,485][87424] Updated weights for policy 0, policy_version 252228 (0.0009) -[2023-11-28 06:49:00,861][87424] Updated weights for policy 0, policy_version 252238 (0.0012) -[2023-11-28 06:49:01,243][87424] Updated weights for policy 0, policy_version 252248 (0.0012) -[2023-11-28 06:49:01,758][87426] Updated weights for policy 1, policy_version 252010 (0.0008) -[2023-11-28 06:49:02,140][87426] Updated weights for policy 1, policy_version 252020 (0.0008) -[2023-11-28 06:49:02,512][87426] Updated weights for policy 1, policy_version 252030 (0.0009) -[2023-11-28 06:49:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 129097728. Throughput: 0: 2754.2, 1: 2717.8. Samples: 129108184. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:03,445][86177] Avg episode reward: [(0, '-515.660'), (1, '-539.840')] -[2023-11-28 06:49:03,791][87424] Updated weights for policy 0, policy_version 252258 (0.0010) -[2023-11-28 06:49:04,177][87424] Updated weights for policy 0, policy_version 252268 (0.0007) -[2023-11-28 06:49:04,562][87424] Updated weights for policy 0, policy_version 252278 (0.0007) -[2023-11-28 06:49:04,717][87426] Updated weights for policy 1, policy_version 252040 (0.0010) -[2023-11-28 06:49:04,936][87424] Updated weights for policy 0, policy_version 252288 (0.0009) -[2023-11-28 06:49:05,098][87426] Updated weights for policy 1, policy_version 252050 (0.0012) -[2023-11-28 06:49:05,470][87426] Updated weights for policy 1, policy_version 252060 (0.0012) -[2023-11-28 06:49:07,197][87426] Updated weights for policy 1, policy_version 252070 (0.0010) -[2023-11-28 06:49:07,414][87424] Updated weights for policy 0, policy_version 252298 (0.0011) -[2023-11-28 06:49:07,583][87426] Updated weights for policy 1, policy_version 252080 (0.0008) -[2023-11-28 06:49:07,792][87424] Updated weights for policy 0, policy_version 252308 (0.0008) -[2023-11-28 06:49:07,955][87426] Updated weights for policy 1, policy_version 252090 (0.0007) -[2023-11-28 06:49:08,172][87424] Updated weights for policy 0, policy_version 252318 (0.0007) -[2023-11-28 06:49:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 129130496. Throughput: 0: 2741.6, 1: 2735.9. Samples: 129141088. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:08,445][86177] Avg episode reward: [(0, '-513.950'), (1, '-530.740')] -[2023-11-28 06:49:10,058][87426] Updated weights for policy 1, policy_version 252100 (0.0009) -[2023-11-28 06:49:10,433][87426] Updated weights for policy 1, policy_version 252110 (0.0009) -[2023-11-28 06:49:10,737][87424] Updated weights for policy 0, policy_version 252328 (0.0011) -[2023-11-28 06:49:10,808][87426] Updated weights for policy 1, policy_version 252120 (0.0010) -[2023-11-28 06:49:11,126][87424] Updated weights for policy 0, policy_version 252338 (0.0012) -[2023-11-28 06:49:11,504][87424] Updated weights for policy 0, policy_version 252348 (0.0012) -[2023-11-28 06:49:13,076][87426] Updated weights for policy 1, policy_version 252130 (0.0011) -[2023-11-28 06:49:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 129146880. Throughput: 0: 2701.1, 1: 2731.6. Samples: 129165240. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:13,445][86177] Avg episode reward: [(0, '-528.990'), (1, '-517.840')] -[2023-11-28 06:49:13,459][87426] Updated weights for policy 1, policy_version 252140 (0.0012) -[2023-11-28 06:49:13,560][87424] Updated weights for policy 0, policy_version 252358 (0.0010) -[2023-11-28 06:49:13,841][87426] Updated weights for policy 1, policy_version 252150 (0.0011) -[2023-11-28 06:49:13,937][87424] Updated weights for policy 0, policy_version 252368 (0.0007) -[2023-11-28 06:49:14,221][87426] Updated weights for policy 1, policy_version 252160 (0.0012) -[2023-11-28 06:49:14,319][87424] Updated weights for policy 0, policy_version 252378 (0.0007) -[2023-11-28 06:49:16,112][87426] Updated weights for policy 1, policy_version 252170 (0.0010) -[2023-11-28 06:49:16,492][87426] Updated weights for policy 1, policy_version 252180 (0.0007) -[2023-11-28 06:49:16,812][87424] Updated weights for policy 0, policy_version 252388 (0.0007) -[2023-11-28 06:49:16,876][87426] Updated weights for policy 1, policy_version 252190 (0.0007) -[2023-11-28 06:49:17,194][87424] Updated weights for policy 0, policy_version 252398 (0.0007) -[2023-11-28 06:49:17,569][87424] Updated weights for policy 0, policy_version 252408 (0.0007) -[2023-11-28 06:49:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 129179648. Throughput: 0: 2680.4, 1: 2734.3. Samples: 129189872. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:18,445][86177] Avg episode reward: [(0, '-533.250'), (1, '-529.800')] -[2023-11-28 06:49:19,140][87426] Updated weights for policy 1, policy_version 252200 (0.0010) -[2023-11-28 06:49:19,523][87426] Updated weights for policy 1, policy_version 252210 (0.0008) -[2023-11-28 06:49:19,877][87424] Updated weights for policy 0, policy_version 252418 (0.0008) -[2023-11-28 06:49:19,903][87426] Updated weights for policy 1, policy_version 252220 (0.0009) -[2023-11-28 06:49:20,262][87424] Updated weights for policy 0, policy_version 252428 (0.0012) -[2023-11-28 06:49:20,649][87424] Updated weights for policy 0, policy_version 252438 (0.0012) -[2023-11-28 06:49:21,027][87424] Updated weights for policy 0, policy_version 252448 (0.0012) -[2023-11-28 06:49:21,983][87426] Updated weights for policy 1, policy_version 252230 (0.0010) -[2023-11-28 06:49:22,362][87426] Updated weights for policy 1, policy_version 252240 (0.0012) -[2023-11-28 06:49:22,739][87426] Updated weights for policy 1, policy_version 252250 (0.0012) -[2023-11-28 06:49:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 129204224. Throughput: 0: 2648.7, 1: 2728.8. Samples: 129221672. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:23,445][86177] Avg episode reward: [(0, '-561.100'), (1, '-523.020')] -[2023-11-28 06:49:23,530][87424] Updated weights for policy 0, policy_version 252458 (0.0010) -[2023-11-28 06:49:23,911][87424] Updated weights for policy 0, policy_version 252468 (0.0008) -[2023-11-28 06:49:24,295][87424] Updated weights for policy 0, policy_version 252478 (0.0008) -[2023-11-28 06:49:24,611][87426] Updated weights for policy 1, policy_version 252260 (0.0012) -[2023-11-28 06:49:24,992][87426] Updated weights for policy 1, policy_version 252270 (0.0012) -[2023-11-28 06:49:25,367][87426] Updated weights for policy 1, policy_version 252280 (0.0009) -[2023-11-28 06:49:26,568][87424] Updated weights for policy 0, policy_version 252488 (0.0008) -[2023-11-28 06:49:26,951][87424] Updated weights for policy 0, policy_version 252498 (0.0008) -[2023-11-28 06:49:27,342][87424] Updated weights for policy 0, policy_version 252508 (0.0007) -[2023-11-28 06:49:27,748][87426] Updated weights for policy 1, policy_version 252290 (0.0009) -[2023-11-28 06:49:28,125][87426] Updated weights for policy 1, policy_version 252300 (0.0012) -[2023-11-28 06:49:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 129228800. Throughput: 0: 2638.8, 1: 2743.3. Samples: 129245364. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:28,445][86177] Avg episode reward: [(0, '-562.220'), (1, '-527.820')] -[2023-11-28 06:49:28,503][87426] Updated weights for policy 1, policy_version 252310 (0.0011) -[2023-11-28 06:49:28,892][87426] Updated weights for policy 1, policy_version 252320 (0.0011) -[2023-11-28 06:49:29,790][87424] Updated weights for policy 0, policy_version 252518 (0.0010) -[2023-11-28 06:49:30,174][87424] Updated weights for policy 0, policy_version 252528 (0.0012) -[2023-11-28 06:49:30,550][87424] Updated weights for policy 0, policy_version 252538 (0.0012) -[2023-11-28 06:49:31,263][87426] Updated weights for policy 1, policy_version 252330 (0.0008) -[2023-11-28 06:49:31,639][87426] Updated weights for policy 1, policy_version 252340 (0.0008) -[2023-11-28 06:49:32,014][87426] Updated weights for policy 1, policy_version 252350 (0.0009) -[2023-11-28 06:49:32,668][87424] Updated weights for policy 0, policy_version 252548 (0.0011) -[2023-11-28 06:49:33,055][87424] Updated weights for policy 0, policy_version 252558 (0.0009) -[2023-11-28 06:49:33,428][87424] Updated weights for policy 0, policy_version 252568 (0.0011) -[2023-11-28 06:49:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 129253376. Throughput: 0: 2613.3, 1: 2745.4. Samples: 129268788. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:33,445][86177] Avg episode reward: [(0, '-556.110'), (1, '-528.420')] -[2023-11-28 06:49:34,460][87426] Updated weights for policy 1, policy_version 252360 (0.0007) -[2023-11-28 06:49:34,841][87426] Updated weights for policy 1, policy_version 252370 (0.0012) -[2023-11-28 06:49:35,217][87426] Updated weights for policy 1, policy_version 252380 (0.0011) -[2023-11-28 06:49:35,607][87424] Updated weights for policy 0, policy_version 252578 (0.0008) -[2023-11-28 06:49:35,991][87424] Updated weights for policy 0, policy_version 252588 (0.0012) -[2023-11-28 06:49:36,379][87424] Updated weights for policy 0, policy_version 252598 (0.0011) -[2023-11-28 06:49:36,753][87424] Updated weights for policy 0, policy_version 252608 (0.0012) -[2023-11-28 06:49:37,196][87426] Updated weights for policy 1, policy_version 252390 (0.0011) -[2023-11-28 06:49:37,576][87426] Updated weights for policy 1, policy_version 252400 (0.0012) -[2023-11-28 06:49:37,952][87426] Updated weights for policy 1, policy_version 252410 (0.0011) -[2023-11-28 06:49:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 129286144. Throughput: 0: 2585.3, 1: 2727.0. Samples: 129299976. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:38,445][86177] Avg episode reward: [(0, '-554.060'), (1, '-512.770')] -[2023-11-28 06:49:39,065][87424] Updated weights for policy 0, policy_version 252618 (0.0012) -[2023-11-28 06:49:39,447][87424] Updated weights for policy 0, policy_version 252628 (0.0012) -[2023-11-28 06:49:39,832][87424] Updated weights for policy 0, policy_version 252638 (0.0012) -[2023-11-28 06:49:40,283][87426] Updated weights for policy 1, policy_version 252420 (0.0011) -[2023-11-28 06:49:40,659][87426] Updated weights for policy 1, policy_version 252430 (0.0009) -[2023-11-28 06:49:41,042][87426] Updated weights for policy 1, policy_version 252440 (0.0008) -[2023-11-28 06:49:42,414][87424] Updated weights for policy 0, policy_version 252648 (0.0012) -[2023-11-28 06:49:42,800][87424] Updated weights for policy 0, policy_version 252658 (0.0011) -[2023-11-28 06:49:43,175][87424] Updated weights for policy 0, policy_version 252668 (0.0012) -[2023-11-28 06:49:43,391][87426] Updated weights for policy 1, policy_version 252450 (0.0007) -[2023-11-28 06:49:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 129310720. Throughput: 0: 2578.5, 1: 2720.3. Samples: 129323564. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:43,445][86177] Avg episode reward: [(0, '-553.310'), (1, '-511.740')] -[2023-11-28 06:49:43,764][87426] Updated weights for policy 1, policy_version 252460 (0.0008) -[2023-11-28 06:49:44,137][87426] Updated weights for policy 1, policy_version 252470 (0.0009) -[2023-11-28 06:49:44,525][87426] Updated weights for policy 1, policy_version 252480 (0.0007) -[2023-11-28 06:49:45,150][87424] Updated weights for policy 0, policy_version 252678 (0.0011) -[2023-11-28 06:49:45,531][87424] Updated weights for policy 0, policy_version 252688 (0.0008) -[2023-11-28 06:49:45,916][87424] Updated weights for policy 0, policy_version 252698 (0.0007) -[2023-11-28 06:49:46,824][87426] Updated weights for policy 1, policy_version 252490 (0.0007) -[2023-11-28 06:49:47,213][87426] Updated weights for policy 1, policy_version 252500 (0.0008) -[2023-11-28 06:49:47,595][87426] Updated weights for policy 1, policy_version 252510 (0.0007) -[2023-11-28 06:49:48,315][87424] Updated weights for policy 0, policy_version 252708 (0.0008) -[2023-11-28 06:49:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 129335296. Throughput: 0: 2587.3, 1: 2740.7. Samples: 129347944. Policy #0 lag: (min: 13.0, avg: 40.0, max: 70.0) -[2023-11-28 06:49:48,445][86177] Avg episode reward: [(0, '-544.370'), (1, '-503.200')] -[2023-11-28 06:49:48,700][87424] Updated weights for policy 0, policy_version 252718 (0.0007) -[2023-11-28 06:49:49,089][87424] Updated weights for policy 0, policy_version 252728 (0.0008) -[2023-11-28 06:49:49,556][87426] Updated weights for policy 1, policy_version 252520 (0.0007) -[2023-11-28 06:49:49,937][87426] Updated weights for policy 1, policy_version 252530 (0.0010) -[2023-11-28 06:49:50,316][87426] Updated weights for policy 1, policy_version 252540 (0.0011) -[2023-11-28 06:49:51,361][87424] Updated weights for policy 0, policy_version 252738 (0.0010) -[2023-11-28 06:49:51,744][87424] Updated weights for policy 0, policy_version 252748 (0.0012) -[2023-11-28 06:49:52,125][87424] Updated weights for policy 0, policy_version 252758 (0.0011) -[2023-11-28 06:49:52,516][87424] Updated weights for policy 0, policy_version 252768 (0.0012) -[2023-11-28 06:49:52,798][87426] Updated weights for policy 1, policy_version 252550 (0.0012) -[2023-11-28 06:49:53,185][87426] Updated weights for policy 1, policy_version 252560 (0.0011) -[2023-11-28 06:49:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 129359872. Throughput: 0: 2573.0, 1: 2713.2. Samples: 129378964. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:49:53,445][86177] Avg episode reward: [(0, '-542.530'), (1, '-507.790')] -[2023-11-28 06:49:53,555][87426] Updated weights for policy 1, policy_version 252570 (0.0010) -[2023-11-28 06:49:54,778][87424] Updated weights for policy 0, policy_version 252778 (0.0012) -[2023-11-28 06:49:55,156][87424] Updated weights for policy 0, policy_version 252788 (0.0011) -[2023-11-28 06:49:55,547][87424] Updated weights for policy 0, policy_version 252798 (0.0009) -[2023-11-28 06:49:55,634][87426] Updated weights for policy 1, policy_version 252580 (0.0010) -[2023-11-28 06:49:56,017][87426] Updated weights for policy 1, policy_version 252590 (0.0010) -[2023-11-28 06:49:56,404][87426] Updated weights for policy 1, policy_version 252600 (0.0009) -[2023-11-28 06:49:57,959][87424] Updated weights for policy 0, policy_version 252808 (0.0012) -[2023-11-28 06:49:58,104][87426] Updated weights for policy 1, policy_version 252610 (0.0010) -[2023-11-28 06:49:58,340][87424] Updated weights for policy 0, policy_version 252818 (0.0012) -[2023-11-28 06:49:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 129384448. Throughput: 0: 2581.3, 1: 2704.6. Samples: 129403104. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:49:58,445][86177] Avg episode reward: [(0, '-539.910'), (1, '-508.740')] -[2023-11-28 06:49:58,481][87426] Updated weights for policy 1, policy_version 252620 (0.0011) -[2023-11-28 06:49:58,727][87424] Updated weights for policy 0, policy_version 252828 (0.0011) -[2023-11-28 06:49:58,881][87426] Updated weights for policy 1, policy_version 252630 (0.0011) -[2023-11-28 06:49:59,233][87426] Updated weights for policy 1, policy_version 252640 (0.0012) -[2023-11-28 06:50:00,710][87424] Updated weights for policy 0, policy_version 252838 (0.0011) -[2023-11-28 06:50:01,091][87424] Updated weights for policy 0, policy_version 252848 (0.0012) -[2023-11-28 06:50:01,477][87424] Updated weights for policy 0, policy_version 252858 (0.0012) -[2023-11-28 06:50:01,894][87426] Updated weights for policy 1, policy_version 252650 (0.0010) -[2023-11-28 06:50:02,275][87426] Updated weights for policy 1, policy_version 252660 (0.0011) -[2023-11-28 06:50:02,648][87426] Updated weights for policy 1, policy_version 252670 (0.0012) -[2023-11-28 06:50:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 129417216. Throughput: 0: 2587.0, 1: 2689.5. Samples: 129427316. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:03,446][86177] Avg episode reward: [(0, '-543.870'), (1, '-508.370')] -[2023-11-28 06:50:03,704][87424] Updated weights for policy 0, policy_version 252868 (0.0011) -[2023-11-28 06:50:04,083][87424] Updated weights for policy 0, policy_version 252878 (0.0012) -[2023-11-28 06:50:04,472][87424] Updated weights for policy 0, policy_version 252888 (0.0012) -[2023-11-28 06:50:04,718][87426] Updated weights for policy 1, policy_version 252680 (0.0012) -[2023-11-28 06:50:05,091][87426] Updated weights for policy 1, policy_version 252690 (0.0012) -[2023-11-28 06:50:05,477][87426] Updated weights for policy 1, policy_version 252700 (0.0012) -[2023-11-28 06:50:06,886][87424] Updated weights for policy 0, policy_version 252898 (0.0011) -[2023-11-28 06:50:07,262][87424] Updated weights for policy 0, policy_version 252908 (0.0007) -[2023-11-28 06:50:07,654][87424] Updated weights for policy 0, policy_version 252918 (0.0008) -[2023-11-28 06:50:07,866][87426] Updated weights for policy 1, policy_version 252710 (0.0011) -[2023-11-28 06:50:08,037][87424] Updated weights for policy 0, policy_version 252928 (0.0008) -[2023-11-28 06:50:08,248][87426] Updated weights for policy 1, policy_version 252720 (0.0008) -[2023-11-28 06:50:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 129441792. Throughput: 0: 2630.8, 1: 2683.2. Samples: 129460800. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:08,445][86177] Avg episode reward: [(0, '-512.420'), (1, '-508.090')] -[2023-11-28 06:50:08,623][87426] Updated weights for policy 1, policy_version 252730 (0.0007) -[2023-11-28 06:50:09,907][87424] Updated weights for policy 0, policy_version 252938 (0.0009) -[2023-11-28 06:50:10,284][87424] Updated weights for policy 0, policy_version 252948 (0.0012) -[2023-11-28 06:50:10,673][87424] Updated weights for policy 0, policy_version 252958 (0.0012) -[2023-11-28 06:50:11,128][87426] Updated weights for policy 1, policy_version 252740 (0.0009) -[2023-11-28 06:50:11,504][87426] Updated weights for policy 1, policy_version 252750 (0.0012) -[2023-11-28 06:50:11,880][87426] Updated weights for policy 1, policy_version 252760 (0.0012) -[2023-11-28 06:50:12,805][87424] Updated weights for policy 0, policy_version 252968 (0.0012) -[2023-11-28 06:50:13,184][87424] Updated weights for policy 0, policy_version 252978 (0.0012) -[2023-11-28 06:50:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129466368. Throughput: 0: 2654.9, 1: 2661.1. Samples: 129484588. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:13,445][86177] Avg episode reward: [(0, '-543.240'), (1, '-511.480')] -[2023-11-28 06:50:13,566][87424] Updated weights for policy 0, policy_version 252988 (0.0012) -[2023-11-28 06:50:13,914][87426] Updated weights for policy 1, policy_version 252770 (0.0009) -[2023-11-28 06:50:14,297][87426] Updated weights for policy 1, policy_version 252780 (0.0008) -[2023-11-28 06:50:14,678][87426] Updated weights for policy 1, policy_version 252790 (0.0008) -[2023-11-28 06:50:15,056][87426] Updated weights for policy 1, policy_version 252800 (0.0009) -[2023-11-28 06:50:15,511][87424] Updated weights for policy 0, policy_version 252998 (0.0012) -[2023-11-28 06:50:15,892][87424] Updated weights for policy 0, policy_version 253008 (0.0012) -[2023-11-28 06:50:16,259][87424] Updated weights for policy 0, policy_version 253018 (0.0012) -[2023-11-28 06:50:16,868][87426] Updated weights for policy 1, policy_version 252810 (0.0012) -[2023-11-28 06:50:17,243][87426] Updated weights for policy 1, policy_version 252820 (0.0012) -[2023-11-28 06:50:17,631][87426] Updated weights for policy 1, policy_version 252830 (0.0012) -[2023-11-28 06:50:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 129499136. Throughput: 0: 2676.9, 1: 2675.9. Samples: 129509664. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:18,445][86177] Avg episode reward: [(0, '-548.360'), (1, '-507.520')] -[2023-11-28 06:50:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000252832_64724992.pth... -[2023-11-28 06:50:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000253024_64774144.pth... -[2023-11-28 06:50:18,485][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000250304_64077824.pth -[2023-11-28 06:50:18,502][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000250528_64135168.pth -[2023-11-28 06:50:18,779][87424] Updated weights for policy 0, policy_version 253028 (0.0010) -[2023-11-28 06:50:19,159][87424] Updated weights for policy 0, policy_version 253038 (0.0012) -[2023-11-28 06:50:19,542][87424] Updated weights for policy 0, policy_version 253048 (0.0012) -[2023-11-28 06:50:20,174][87426] Updated weights for policy 1, policy_version 252840 (0.0012) -[2023-11-28 06:50:20,542][87426] Updated weights for policy 1, policy_version 252850 (0.0012) -[2023-11-28 06:50:20,930][87426] Updated weights for policy 1, policy_version 252860 (0.0012) -[2023-11-28 06:50:21,801][87424] Updated weights for policy 0, policy_version 253058 (0.0012) -[2023-11-28 06:50:22,179][87424] Updated weights for policy 0, policy_version 253068 (0.0011) -[2023-11-28 06:50:22,564][87424] Updated weights for policy 0, policy_version 253078 (0.0011) -[2023-11-28 06:50:22,947][87424] Updated weights for policy 0, policy_version 253088 (0.0010) -[2023-11-28 06:50:23,420][87426] Updated weights for policy 1, policy_version 252870 (0.0012) -[2023-11-28 06:50:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129523712. Throughput: 0: 2673.9, 1: 2684.8. Samples: 129541116. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:23,445][86177] Avg episode reward: [(0, '-544.080'), (1, '-509.310')] -[2023-11-28 06:50:23,793][87426] Updated weights for policy 1, policy_version 252880 (0.0012) -[2023-11-28 06:50:24,163][87426] Updated weights for policy 1, policy_version 252890 (0.0012) -[2023-11-28 06:50:25,104][87424] Updated weights for policy 0, policy_version 253098 (0.0010) -[2023-11-28 06:50:25,486][87424] Updated weights for policy 0, policy_version 253108 (0.0007) -[2023-11-28 06:50:25,875][87424] Updated weights for policy 0, policy_version 253118 (0.0007) -[2023-11-28 06:50:26,382][87426] Updated weights for policy 1, policy_version 252900 (0.0011) -[2023-11-28 06:50:26,761][87426] Updated weights for policy 1, policy_version 252910 (0.0007) -[2023-11-28 06:50:27,140][87426] Updated weights for policy 1, policy_version 252920 (0.0007) -[2023-11-28 06:50:28,153][87424] Updated weights for policy 0, policy_version 253128 (0.0007) -[2023-11-28 06:50:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129548288. Throughput: 0: 2699.7, 1: 2664.4. Samples: 129564948. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:28,445][86177] Avg episode reward: [(0, '-514.090'), (1, '-513.940')] -[2023-11-28 06:50:28,528][87424] Updated weights for policy 0, policy_version 253138 (0.0008) -[2023-11-28 06:50:28,912][87424] Updated weights for policy 0, policy_version 253148 (0.0008) -[2023-11-28 06:50:29,692][87426] Updated weights for policy 1, policy_version 252930 (0.0007) -[2023-11-28 06:50:30,076][87426] Updated weights for policy 1, policy_version 252940 (0.0009) -[2023-11-28 06:50:30,455][87426] Updated weights for policy 1, policy_version 252950 (0.0008) -[2023-11-28 06:50:30,837][87426] Updated weights for policy 1, policy_version 252960 (0.0008) -[2023-11-28 06:50:31,406][87424] Updated weights for policy 0, policy_version 253158 (0.0008) -[2023-11-28 06:50:31,785][87424] Updated weights for policy 0, policy_version 253168 (0.0009) -[2023-11-28 06:50:32,177][87424] Updated weights for policy 0, policy_version 253178 (0.0009) -[2023-11-28 06:50:32,895][87426] Updated weights for policy 1, policy_version 252970 (0.0011) -[2023-11-28 06:50:33,256][87426] Updated weights for policy 1, policy_version 252980 (0.0012) -[2023-11-28 06:50:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129572864. Throughput: 0: 2705.4, 1: 2645.7. Samples: 129588744. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:33,445][86177] Avg episode reward: [(0, '-513.180'), (1, '-515.670')] -[2023-11-28 06:50:33,639][87426] Updated weights for policy 1, policy_version 252990 (0.0012) -[2023-11-28 06:50:34,644][87424] Updated weights for policy 0, policy_version 253188 (0.0007) -[2023-11-28 06:50:35,033][87424] Updated weights for policy 0, policy_version 253198 (0.0011) -[2023-11-28 06:50:35,412][87424] Updated weights for policy 0, policy_version 253208 (0.0012) -[2023-11-28 06:50:35,426][87426] Updated weights for policy 1, policy_version 253000 (0.0012) -[2023-11-28 06:50:35,813][87426] Updated weights for policy 1, policy_version 253010 (0.0007) -[2023-11-28 06:50:36,194][87426] Updated weights for policy 1, policy_version 253020 (0.0007) -[2023-11-28 06:50:37,384][87424] Updated weights for policy 0, policy_version 253218 (0.0011) -[2023-11-28 06:50:37,764][87424] Updated weights for policy 0, policy_version 253228 (0.0012) -[2023-11-28 06:50:38,147][87424] Updated weights for policy 0, policy_version 253238 (0.0010) -[2023-11-28 06:50:38,168][87426] Updated weights for policy 1, policy_version 253030 (0.0008) -[2023-11-28 06:50:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 129597440. Throughput: 0: 2707.0, 1: 2672.7. Samples: 129621052. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:38,445][86177] Avg episode reward: [(0, '-519.240'), (1, '-523.180')] -[2023-11-28 06:50:38,529][87424] Updated weights for policy 0, policy_version 253248 (0.0008) -[2023-11-28 06:50:38,556][87426] Updated weights for policy 1, policy_version 253040 (0.0007) -[2023-11-28 06:50:38,927][87426] Updated weights for policy 1, policy_version 253050 (0.0008) -[2023-11-28 06:50:40,581][87424] Updated weights for policy 0, policy_version 253258 (0.0011) -[2023-11-28 06:50:40,958][87424] Updated weights for policy 0, policy_version 253268 (0.0012) -[2023-11-28 06:50:41,252][87426] Updated weights for policy 1, policy_version 253060 (0.0008) -[2023-11-28 06:50:41,338][87424] Updated weights for policy 0, policy_version 253278 (0.0010) -[2023-11-28 06:50:41,628][87426] Updated weights for policy 1, policy_version 253070 (0.0008) -[2023-11-28 06:50:42,004][87426] Updated weights for policy 1, policy_version 253080 (0.0009) -[2023-11-28 06:50:43,434][87424] Updated weights for policy 0, policy_version 253288 (0.0008) -[2023-11-28 06:50:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 129630208. Throughput: 0: 2713.4, 1: 2673.7. Samples: 129645524. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:43,445][86177] Avg episode reward: [(0, '-533.690'), (1, '-529.260')] -[2023-11-28 06:50:43,812][87424] Updated weights for policy 0, policy_version 253298 (0.0008) -[2023-11-28 06:50:44,197][87424] Updated weights for policy 0, policy_version 253308 (0.0009) -[2023-11-28 06:50:44,383][87426] Updated weights for policy 1, policy_version 253090 (0.0011) -[2023-11-28 06:50:44,773][87426] Updated weights for policy 1, policy_version 253100 (0.0008) -[2023-11-28 06:50:45,148][87426] Updated weights for policy 1, policy_version 253110 (0.0007) -[2023-11-28 06:50:45,517][87426] Updated weights for policy 1, policy_version 253120 (0.0008) -[2023-11-28 06:50:46,649][87424] Updated weights for policy 0, policy_version 253318 (0.0007) -[2023-11-28 06:50:47,032][87424] Updated weights for policy 0, policy_version 253328 (0.0007) -[2023-11-28 06:50:47,423][87424] Updated weights for policy 0, policy_version 253338 (0.0007) -[2023-11-28 06:50:47,977][87426] Updated weights for policy 1, policy_version 253130 (0.0012) -[2023-11-28 06:50:48,357][87426] Updated weights for policy 1, policy_version 253140 (0.0012) -[2023-11-28 06:50:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129654784. Throughput: 0: 2699.7, 1: 2657.0. Samples: 129668368. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:48,445][86177] Avg episode reward: [(0, '-535.750'), (1, '-521.590')] -[2023-11-28 06:50:48,742][87426] Updated weights for policy 1, policy_version 253150 (0.0012) -[2023-11-28 06:50:49,708][87424] Updated weights for policy 0, policy_version 253348 (0.0009) -[2023-11-28 06:50:50,091][87424] Updated weights for policy 0, policy_version 253358 (0.0012) -[2023-11-28 06:50:50,469][87424] Updated weights for policy 0, policy_version 253368 (0.0011) -[2023-11-28 06:50:50,672][87426] Updated weights for policy 1, policy_version 253160 (0.0010) -[2023-11-28 06:50:51,038][87426] Updated weights for policy 1, policy_version 253170 (0.0012) -[2023-11-28 06:50:51,428][87426] Updated weights for policy 1, policy_version 253180 (0.0012) -[2023-11-28 06:50:52,561][87424] Updated weights for policy 0, policy_version 253378 (0.0012) -[2023-11-28 06:50:52,939][87424] Updated weights for policy 0, policy_version 253388 (0.0011) -[2023-11-28 06:50:53,329][87424] Updated weights for policy 0, policy_version 253398 (0.0012) -[2023-11-28 06:50:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 129679360. Throughput: 0: 2671.1, 1: 2653.9. Samples: 129700424. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:53,445][86177] Avg episode reward: [(0, '-536.910'), (1, '-513.520')] -[2023-11-28 06:50:53,707][87424] Updated weights for policy 0, policy_version 253408 (0.0012) -[2023-11-28 06:50:53,872][87426] Updated weights for policy 1, policy_version 253190 (0.0011) -[2023-11-28 06:50:54,243][87426] Updated weights for policy 1, policy_version 253200 (0.0008) -[2023-11-28 06:50:54,624][87426] Updated weights for policy 1, policy_version 253210 (0.0008) -[2023-11-28 06:50:55,862][87424] Updated weights for policy 0, policy_version 253418 (0.0012) -[2023-11-28 06:50:56,241][87424] Updated weights for policy 0, policy_version 253428 (0.0012) -[2023-11-28 06:50:56,626][87424] Updated weights for policy 0, policy_version 253438 (0.0007) -[2023-11-28 06:50:57,214][87426] Updated weights for policy 1, policy_version 253220 (0.0007) -[2023-11-28 06:50:57,593][87426] Updated weights for policy 1, policy_version 253230 (0.0007) -[2023-11-28 06:50:57,975][87426] Updated weights for policy 1, policy_version 253240 (0.0008) -[2023-11-28 06:50:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 129712128. Throughput: 0: 2686.4, 1: 2647.6. Samples: 129724616. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:50:58,445][86177] Avg episode reward: [(0, '-528.090'), (1, '-518.960')] -[2023-11-28 06:50:58,541][87424] Updated weights for policy 0, policy_version 253448 (0.0007) -[2023-11-28 06:50:58,921][87424] Updated weights for policy 0, policy_version 253458 (0.0009) -[2023-11-28 06:50:59,312][87424] Updated weights for policy 0, policy_version 253468 (0.0008) -[2023-11-28 06:50:59,987][87426] Updated weights for policy 1, policy_version 253250 (0.0008) -[2023-11-28 06:51:00,367][87426] Updated weights for policy 1, policy_version 253260 (0.0008) -[2023-11-28 06:51:00,739][87426] Updated weights for policy 1, policy_version 253270 (0.0011) -[2023-11-28 06:51:01,118][87426] Updated weights for policy 1, policy_version 253280 (0.0012) -[2023-11-28 06:51:01,617][87424] Updated weights for policy 0, policy_version 253478 (0.0010) -[2023-11-28 06:51:02,002][87424] Updated weights for policy 0, policy_version 253488 (0.0012) -[2023-11-28 06:51:02,380][87424] Updated weights for policy 0, policy_version 253498 (0.0012) -[2023-11-28 06:51:03,249][87426] Updated weights for policy 1, policy_version 253290 (0.0012) -[2023-11-28 06:51:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129736704. Throughput: 0: 2709.4, 1: 2624.6. Samples: 129749696. Policy #0 lag: (min: 29.0, avg: 55.2, max: 93.0) -[2023-11-28 06:51:03,445][86177] Avg episode reward: [(0, '-523.970'), (1, '-533.660')] -[2023-11-28 06:51:03,619][87426] Updated weights for policy 1, policy_version 253300 (0.0012) -[2023-11-28 06:51:03,998][87426] Updated weights for policy 1, policy_version 253310 (0.0007) -[2023-11-28 06:51:04,533][87424] Updated weights for policy 0, policy_version 253508 (0.0010) -[2023-11-28 06:51:04,916][87424] Updated weights for policy 0, policy_version 253518 (0.0008) -[2023-11-28 06:51:05,296][87424] Updated weights for policy 0, policy_version 253528 (0.0008) -[2023-11-28 06:51:05,929][87426] Updated weights for policy 1, policy_version 253320 (0.0011) -[2023-11-28 06:51:06,297][87426] Updated weights for policy 1, policy_version 253330 (0.0011) -[2023-11-28 06:51:06,681][87426] Updated weights for policy 1, policy_version 253340 (0.0008) -[2023-11-28 06:51:07,383][87424] Updated weights for policy 0, policy_version 253538 (0.0008) -[2023-11-28 06:51:07,770][87424] Updated weights for policy 0, policy_version 253548 (0.0011) -[2023-11-28 06:51:08,156][87424] Updated weights for policy 0, policy_version 253558 (0.0011) -[2023-11-28 06:51:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129761280. Throughput: 0: 2712.3, 1: 2674.1. Samples: 129783504. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:08,445][86177] Avg episode reward: [(0, '-521.490'), (1, '-537.750')] -[2023-11-28 06:51:08,536][87424] Updated weights for policy 0, policy_version 253568 (0.0011) -[2023-11-28 06:51:09,035][87426] Updated weights for policy 1, policy_version 253350 (0.0012) -[2023-11-28 06:51:09,412][87426] Updated weights for policy 1, policy_version 253360 (0.0012) -[2023-11-28 06:51:09,786][87426] Updated weights for policy 1, policy_version 253370 (0.0012) -[2023-11-28 06:51:10,834][87424] Updated weights for policy 0, policy_version 253578 (0.0008) -[2023-11-28 06:51:11,216][87424] Updated weights for policy 0, policy_version 253588 (0.0008) -[2023-11-28 06:51:11,619][87424] Updated weights for policy 0, policy_version 253598 (0.0008) -[2023-11-28 06:51:12,450][87426] Updated weights for policy 1, policy_version 253380 (0.0012) -[2023-11-28 06:51:12,824][87426] Updated weights for policy 1, policy_version 253390 (0.0010) -[2023-11-28 06:51:13,205][87426] Updated weights for policy 1, policy_version 253400 (0.0011) -[2023-11-28 06:51:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129785856. Throughput: 0: 2703.3, 1: 2676.8. Samples: 129807052. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:13,445][86177] Avg episode reward: [(0, '-523.790'), (1, '-539.770')] -[2023-11-28 06:51:13,589][87424] Updated weights for policy 0, policy_version 253608 (0.0011) -[2023-11-28 06:51:13,971][87424] Updated weights for policy 0, policy_version 253618 (0.0009) -[2023-11-28 06:51:14,360][87424] Updated weights for policy 0, policy_version 253628 (0.0009) -[2023-11-28 06:51:15,534][87426] Updated weights for policy 1, policy_version 253410 (0.0009) -[2023-11-28 06:51:15,916][87426] Updated weights for policy 1, policy_version 253420 (0.0008) -[2023-11-28 06:51:16,311][87426] Updated weights for policy 1, policy_version 253430 (0.0011) -[2023-11-28 06:51:16,682][87426] Updated weights for policy 1, policy_version 253440 (0.0012) -[2023-11-28 06:51:16,820][87424] Updated weights for policy 0, policy_version 253638 (0.0008) -[2023-11-28 06:51:17,215][87424] Updated weights for policy 0, policy_version 253648 (0.0007) -[2023-11-28 06:51:17,590][87424] Updated weights for policy 0, policy_version 253658 (0.0008) -[2023-11-28 06:51:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129818624. Throughput: 0: 2698.8, 1: 2685.2. Samples: 129831028. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:18,445][86177] Avg episode reward: [(0, '-525.330'), (1, '-540.930')] -[2023-11-28 06:51:18,893][87426] Updated weights for policy 1, policy_version 253450 (0.0010) -[2023-11-28 06:51:19,271][87426] Updated weights for policy 1, policy_version 253460 (0.0011) -[2023-11-28 06:51:19,655][87426] Updated weights for policy 1, policy_version 253470 (0.0012) -[2023-11-28 06:51:19,863][87424] Updated weights for policy 0, policy_version 253668 (0.0009) -[2023-11-28 06:51:20,246][87424] Updated weights for policy 0, policy_version 253678 (0.0008) -[2023-11-28 06:51:20,618][87424] Updated weights for policy 0, policy_version 253688 (0.0009) -[2023-11-28 06:51:21,620][87426] Updated weights for policy 1, policy_version 253480 (0.0012) -[2023-11-28 06:51:21,996][87426] Updated weights for policy 1, policy_version 253490 (0.0011) -[2023-11-28 06:51:22,372][87426] Updated weights for policy 1, policy_version 253500 (0.0012) -[2023-11-28 06:51:22,741][87424] Updated weights for policy 0, policy_version 253698 (0.0009) -[2023-11-28 06:51:23,121][87424] Updated weights for policy 0, policy_version 253708 (0.0012) -[2023-11-28 06:51:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 129843200. Throughput: 0: 2706.8, 1: 2659.3. Samples: 129862524. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:23,445][86177] Avg episode reward: [(0, '-518.680'), (1, '-520.860')] -[2023-11-28 06:51:23,500][87424] Updated weights for policy 0, policy_version 253718 (0.0012) -[2023-11-28 06:51:23,887][87424] Updated weights for policy 0, policy_version 253728 (0.0012) -[2023-11-28 06:51:24,509][87426] Updated weights for policy 1, policy_version 253510 (0.0010) -[2023-11-28 06:51:24,880][87426] Updated weights for policy 1, policy_version 253520 (0.0007) -[2023-11-28 06:51:25,258][87426] Updated weights for policy 1, policy_version 253530 (0.0010) -[2023-11-28 06:51:26,177][87424] Updated weights for policy 0, policy_version 253738 (0.0008) -[2023-11-28 06:51:26,564][87424] Updated weights for policy 0, policy_version 253748 (0.0012) -[2023-11-28 06:51:26,936][87424] Updated weights for policy 0, policy_version 253758 (0.0012) -[2023-11-28 06:51:27,256][87426] Updated weights for policy 1, policy_version 253540 (0.0009) -[2023-11-28 06:51:27,627][87426] Updated weights for policy 1, policy_version 253550 (0.0011) -[2023-11-28 06:51:28,012][87426] Updated weights for policy 1, policy_version 253560 (0.0009) -[2023-11-28 06:51:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 129875968. Throughput: 0: 2702.9, 1: 2673.1. Samples: 129887448. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:28,445][86177] Avg episode reward: [(0, '-509.800'), (1, '-523.220')] -[2023-11-28 06:51:28,752][87424] Updated weights for policy 0, policy_version 253768 (0.0010) -[2023-11-28 06:51:29,135][87424] Updated weights for policy 0, policy_version 253778 (0.0009) -[2023-11-28 06:51:29,520][87424] Updated weights for policy 0, policy_version 253788 (0.0008) -[2023-11-28 06:51:30,400][87426] Updated weights for policy 1, policy_version 253570 (0.0011) -[2023-11-28 06:51:30,778][87426] Updated weights for policy 1, policy_version 253580 (0.0009) -[2023-11-28 06:51:31,156][87426] Updated weights for policy 1, policy_version 253590 (0.0008) -[2023-11-28 06:51:31,533][87426] Updated weights for policy 1, policy_version 253600 (0.0009) -[2023-11-28 06:51:32,057][87424] Updated weights for policy 0, policy_version 253798 (0.0010) -[2023-11-28 06:51:32,443][87424] Updated weights for policy 0, policy_version 253808 (0.0010) -[2023-11-28 06:51:32,828][87424] Updated weights for policy 0, policy_version 253818 (0.0010) -[2023-11-28 06:51:33,353][87426] Updated weights for policy 1, policy_version 253610 (0.0011) -[2023-11-28 06:51:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 129900544. Throughput: 0: 2712.8, 1: 2678.8. Samples: 129910988. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:33,445][86177] Avg episode reward: [(0, '-512.280'), (1, '-513.740')] -[2023-11-28 06:51:33,734][87426] Updated weights for policy 1, policy_version 253620 (0.0012) -[2023-11-28 06:51:34,108][87426] Updated weights for policy 1, policy_version 253630 (0.0012) -[2023-11-28 06:51:35,083][87424] Updated weights for policy 0, policy_version 253828 (0.0010) -[2023-11-28 06:51:35,463][87424] Updated weights for policy 0, policy_version 253838 (0.0009) -[2023-11-28 06:51:35,846][87424] Updated weights for policy 0, policy_version 253848 (0.0012) -[2023-11-28 06:51:36,151][87426] Updated weights for policy 1, policy_version 253640 (0.0010) -[2023-11-28 06:51:36,529][87426] Updated weights for policy 1, policy_version 253650 (0.0008) -[2023-11-28 06:51:36,907][87426] Updated weights for policy 1, policy_version 253660 (0.0010) -[2023-11-28 06:51:38,131][87424] Updated weights for policy 0, policy_version 253858 (0.0008) -[2023-11-28 06:51:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 129925120. Throughput: 0: 2721.1, 1: 2719.0. Samples: 129945228. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:38,445][86177] Avg episode reward: [(0, '-512.730'), (1, '-513.360')] -[2023-11-28 06:51:38,526][87424] Updated weights for policy 0, policy_version 253868 (0.0012) -[2023-11-28 06:51:38,779][87426] Updated weights for policy 1, policy_version 253670 (0.0012) -[2023-11-28 06:51:38,908][87424] Updated weights for policy 0, policy_version 253878 (0.0011) -[2023-11-28 06:51:39,149][87426] Updated weights for policy 1, policy_version 253680 (0.0011) -[2023-11-28 06:51:39,290][87424] Updated weights for policy 0, policy_version 253888 (0.0011) -[2023-11-28 06:51:39,526][87426] Updated weights for policy 1, policy_version 253690 (0.0010) -[2023-11-28 06:51:41,705][87424] Updated weights for policy 0, policy_version 253898 (0.0009) -[2023-11-28 06:51:41,825][87426] Updated weights for policy 1, policy_version 253700 (0.0009) -[2023-11-28 06:51:42,085][87424] Updated weights for policy 0, policy_version 253908 (0.0009) -[2023-11-28 06:51:42,194][87426] Updated weights for policy 1, policy_version 253710 (0.0011) -[2023-11-28 06:51:42,466][87424] Updated weights for policy 0, policy_version 253918 (0.0011) -[2023-11-28 06:51:42,577][87426] Updated weights for policy 1, policy_version 253720 (0.0011) -[2023-11-28 06:51:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 129957888. Throughput: 0: 2686.8, 1: 2739.9. Samples: 129968820. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:43,445][86177] Avg episode reward: [(0, '-520.800'), (1, '-514.330')] -[2023-11-28 06:51:44,615][87426] Updated weights for policy 1, policy_version 253730 (0.0012) -[2023-11-28 06:51:44,840][87424] Updated weights for policy 0, policy_version 253928 (0.0010) -[2023-11-28 06:51:45,001][87426] Updated weights for policy 1, policy_version 253740 (0.0011) -[2023-11-28 06:51:45,224][87424] Updated weights for policy 0, policy_version 253938 (0.0010) -[2023-11-28 06:51:45,379][87426] Updated weights for policy 1, policy_version 253750 (0.0011) -[2023-11-28 06:51:45,604][87424] Updated weights for policy 0, policy_version 253948 (0.0011) -[2023-11-28 06:51:45,751][87426] Updated weights for policy 1, policy_version 253760 (0.0011) -[2023-11-28 06:51:47,383][87424] Updated weights for policy 0, policy_version 253958 (0.0012) -[2023-11-28 06:51:47,758][87424] Updated weights for policy 0, policy_version 253968 (0.0010) -[2023-11-28 06:51:47,842][87426] Updated weights for policy 1, policy_version 253770 (0.0011) -[2023-11-28 06:51:48,137][87424] Updated weights for policy 0, policy_version 253978 (0.0011) -[2023-11-28 06:51:48,213][87426] Updated weights for policy 1, policy_version 253780 (0.0009) -[2023-11-28 06:51:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 129982464. Throughput: 0: 2666.5, 1: 2746.5. Samples: 129993280. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:48,445][86177] Avg episode reward: [(0, '-518.850'), (1, '-515.050')] -[2023-11-28 06:51:48,589][87426] Updated weights for policy 1, policy_version 253790 (0.0009) -[2023-11-28 06:51:50,349][87424] Updated weights for policy 0, policy_version 253988 (0.0010) -[2023-11-28 06:51:50,739][87424] Updated weights for policy 0, policy_version 253998 (0.0010) -[2023-11-28 06:51:50,825][87426] Updated weights for policy 1, policy_version 253800 (0.0011) -[2023-11-28 06:51:51,116][87424] Updated weights for policy 0, policy_version 254008 (0.0010) -[2023-11-28 06:51:51,202][87426] Updated weights for policy 1, policy_version 253810 (0.0012) -[2023-11-28 06:51:51,577][87426] Updated weights for policy 1, policy_version 253820 (0.0012) -[2023-11-28 06:51:53,363][87424] Updated weights for policy 0, policy_version 254018 (0.0011) -[2023-11-28 06:51:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 130007040. Throughput: 0: 2675.6, 1: 2724.9. Samples: 130026528. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:53,445][86177] Avg episode reward: [(0, '-515.550'), (1, '-512.010')] -[2023-11-28 06:51:53,738][87424] Updated weights for policy 0, policy_version 254028 (0.0012) -[2023-11-28 06:51:53,944][87426] Updated weights for policy 1, policy_version 253830 (0.0010) -[2023-11-28 06:51:54,128][87424] Updated weights for policy 0, policy_version 254038 (0.0011) -[2023-11-28 06:51:54,319][87426] Updated weights for policy 1, policy_version 253840 (0.0010) -[2023-11-28 06:51:54,498][87424] Updated weights for policy 0, policy_version 254048 (0.0010) -[2023-11-28 06:51:54,694][87426] Updated weights for policy 1, policy_version 253850 (0.0012) -[2023-11-28 06:51:56,376][87424] Updated weights for policy 0, policy_version 254058 (0.0012) -[2023-11-28 06:51:56,475][87426] Updated weights for policy 1, policy_version 253860 (0.0010) -[2023-11-28 06:51:56,762][87424] Updated weights for policy 0, policy_version 254068 (0.0007) -[2023-11-28 06:51:56,852][87426] Updated weights for policy 1, policy_version 253870 (0.0007) -[2023-11-28 06:51:57,153][87424] Updated weights for policy 0, policy_version 254078 (0.0007) -[2023-11-28 06:51:57,232][87426] Updated weights for policy 1, policy_version 253880 (0.0008) -[2023-11-28 06:51:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 130039808. Throughput: 0: 2686.1, 1: 2757.0. Samples: 130051992. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:51:58,445][86177] Avg episode reward: [(0, '-513.320'), (1, '-536.000')] -[2023-11-28 06:51:58,820][87424] Updated weights for policy 0, policy_version 254088 (0.0011) -[2023-11-28 06:51:59,199][87424] Updated weights for policy 0, policy_version 254098 (0.0011) -[2023-11-28 06:51:59,587][87424] Updated weights for policy 0, policy_version 254108 (0.0007) -[2023-11-28 06:51:59,780][87426] Updated weights for policy 1, policy_version 253890 (0.0008) -[2023-11-28 06:52:00,160][87426] Updated weights for policy 1, policy_version 253900 (0.0012) -[2023-11-28 06:52:00,533][87426] Updated weights for policy 1, policy_version 253910 (0.0010) -[2023-11-28 06:52:00,921][87426] Updated weights for policy 1, policy_version 253920 (0.0008) -[2023-11-28 06:52:02,064][87424] Updated weights for policy 0, policy_version 254118 (0.0010) -[2023-11-28 06:52:02,442][87424] Updated weights for policy 0, policy_version 254128 (0.0009) -[2023-11-28 06:52:02,828][87424] Updated weights for policy 0, policy_version 254138 (0.0008) -[2023-11-28 06:52:03,308][87426] Updated weights for policy 1, policy_version 253930 (0.0010) -[2023-11-28 06:52:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130064384. Throughput: 0: 2702.3, 1: 2753.2. Samples: 130076524. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:52:03,445][86177] Avg episode reward: [(0, '-548.180'), (1, '-545.930')] -[2023-11-28 06:52:03,685][87426] Updated weights for policy 1, policy_version 253940 (0.0008) -[2023-11-28 06:52:04,066][87426] Updated weights for policy 1, policy_version 253950 (0.0007) -[2023-11-28 06:52:04,925][87424] Updated weights for policy 0, policy_version 254148 (0.0009) -[2023-11-28 06:52:05,303][87424] Updated weights for policy 0, policy_version 254158 (0.0012) -[2023-11-28 06:52:05,682][87424] Updated weights for policy 0, policy_version 254168 (0.0012) -[2023-11-28 06:52:06,419][87426] Updated weights for policy 1, policy_version 253960 (0.0007) -[2023-11-28 06:52:06,796][87426] Updated weights for policy 1, policy_version 253970 (0.0010) -[2023-11-28 06:52:07,175][87426] Updated weights for policy 1, policy_version 253980 (0.0012) -[2023-11-28 06:52:07,505][87424] Updated weights for policy 0, policy_version 254178 (0.0011) -[2023-11-28 06:52:07,891][87424] Updated weights for policy 0, policy_version 254188 (0.0007) -[2023-11-28 06:52:08,264][87424] Updated weights for policy 0, policy_version 254198 (0.0008) -[2023-11-28 06:52:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130088960. Throughput: 0: 2729.1, 1: 2757.4. Samples: 130109416. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:52:08,445][86177] Avg episode reward: [(0, '-550.750'), (1, '-545.640')] -[2023-11-28 06:52:08,637][87424] Updated weights for policy 0, policy_version 254208 (0.0007) -[2023-11-28 06:52:09,799][87426] Updated weights for policy 1, policy_version 253990 (0.0011) -[2023-11-28 06:52:10,174][87426] Updated weights for policy 1, policy_version 254000 (0.0011) -[2023-11-28 06:52:10,554][87426] Updated weights for policy 1, policy_version 254010 (0.0012) -[2023-11-28 06:52:10,777][87424] Updated weights for policy 0, policy_version 254218 (0.0008) -[2023-11-28 06:52:11,163][87424] Updated weights for policy 0, policy_version 254228 (0.0008) -[2023-11-28 06:52:11,542][87424] Updated weights for policy 0, policy_version 254238 (0.0010) -[2023-11-28 06:52:12,913][87426] Updated weights for policy 1, policy_version 254020 (0.0011) -[2023-11-28 06:52:13,289][87426] Updated weights for policy 1, policy_version 254030 (0.0012) -[2023-11-28 06:52:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130113536. Throughput: 0: 2730.5, 1: 2732.4. Samples: 130133276. Policy #0 lag: (min: 40.0, avg: 57.3, max: 59.0) -[2023-11-28 06:52:13,445][86177] Avg episode reward: [(0, '-549.910'), (1, '-545.090')] -[2023-11-28 06:52:13,670][87426] Updated weights for policy 1, policy_version 254040 (0.0012) -[2023-11-28 06:52:13,762][87424] Updated weights for policy 0, policy_version 254248 (0.0011) -[2023-11-28 06:52:14,156][87424] Updated weights for policy 0, policy_version 254258 (0.0008) -[2023-11-28 06:52:14,532][87424] Updated weights for policy 0, policy_version 254268 (0.0009) -[2023-11-28 06:52:15,657][87426] Updated weights for policy 1, policy_version 254050 (0.0010) -[2023-11-28 06:52:16,027][87426] Updated weights for policy 1, policy_version 254060 (0.0012) -[2023-11-28 06:52:16,405][87426] Updated weights for policy 1, policy_version 254070 (0.0012) -[2023-11-28 06:52:16,782][87426] Updated weights for policy 1, policy_version 254080 (0.0010) -[2023-11-28 06:52:17,091][87424] Updated weights for policy 0, policy_version 254278 (0.0011) -[2023-11-28 06:52:17,478][87424] Updated weights for policy 0, policy_version 254288 (0.0012) -[2023-11-28 06:52:17,868][87424] Updated weights for policy 0, policy_version 254298 (0.0011) -[2023-11-28 06:52:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130146304. Throughput: 0: 2743.1, 1: 2743.1. Samples: 130157868. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:52:18,445][86177] Avg episode reward: [(0, '-551.940'), (1, '-547.620')] -[2023-11-28 06:52:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000254304_65101824.pth... -[2023-11-28 06:52:18,477][87426] Updated weights for policy 1, policy_version 254090 (0.0011) -[2023-11-28 06:52:18,487][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000251776_64454656.pth -[2023-11-28 06:52:18,492][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000254304_65101824.pth -[2023-11-28 06:52:18,854][87426] Updated weights for policy 1, policy_version 254100 (0.0010) -[2023-11-28 06:52:19,240][87426] Updated weights for policy 1, policy_version 254110 (0.0010) -[2023-11-28 06:52:19,303][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000254112_65052672.pth... -[2023-11-28 06:52:19,334][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000251552_64397312.pth -[2023-11-28 06:52:19,338][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000254112_65052672.pth -[2023-11-28 06:52:20,173][87424] Updated weights for policy 0, policy_version 254308 (0.0010) -[2023-11-28 06:52:20,552][87424] Updated weights for policy 0, policy_version 254318 (0.0012) -[2023-11-28 06:52:20,939][87424] Updated weights for policy 0, policy_version 254328 (0.0012) -[2023-11-28 06:52:21,485][87426] Updated weights for policy 1, policy_version 254120 (0.0009) -[2023-11-28 06:52:21,875][87426] Updated weights for policy 1, policy_version 254130 (0.0010) -[2023-11-28 06:52:22,247][87426] Updated weights for policy 1, policy_version 254140 (0.0010) -[2023-11-28 06:52:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 130170880. Throughput: 0: 2696.7, 1: 2722.0. Samples: 130189068. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:52:23,445][86177] Avg episode reward: [(0, '-546.320'), (1, '-533.580')] -[2023-11-28 06:52:23,588][87424] Updated weights for policy 0, policy_version 254338 (0.0011) -[2023-11-28 06:52:23,976][87424] Updated weights for policy 0, policy_version 254348 (0.0011) -[2023-11-28 06:52:24,360][87424] Updated weights for policy 0, policy_version 254358 (0.0011) -[2023-11-28 06:52:24,407][87426] Updated weights for policy 1, policy_version 254150 (0.0009) -[2023-11-28 06:52:24,742][87424] Updated weights for policy 0, policy_version 254368 (0.0007) -[2023-11-28 06:52:24,794][87426] Updated weights for policy 1, policy_version 254160 (0.0009) -[2023-11-28 06:52:25,173][87426] Updated weights for policy 1, policy_version 254170 (0.0007) -[2023-11-28 06:52:26,822][87424] Updated weights for policy 0, policy_version 254378 (0.0011) -[2023-11-28 06:52:27,211][87424] Updated weights for policy 0, policy_version 254388 (0.0011) -[2023-11-28 06:52:27,597][87424] Updated weights for policy 0, policy_version 254398 (0.0011) -[2023-11-28 06:52:27,639][87426] Updated weights for policy 1, policy_version 254180 (0.0008) -[2023-11-28 06:52:28,026][87426] Updated weights for policy 1, policy_version 254190 (0.0008) -[2023-11-28 06:52:28,411][87426] Updated weights for policy 1, policy_version 254200 (0.0008) -[2023-11-28 06:52:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 130195456. Throughput: 0: 2697.6, 1: 2724.0. Samples: 130212792. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:52:28,445][86177] Avg episode reward: [(0, '-551.050'), (1, '-530.600')] -[2023-11-28 06:52:29,540][87424] Updated weights for policy 0, policy_version 254408 (0.0012) -[2023-11-28 06:52:29,916][87424] Updated weights for policy 0, policy_version 254418 (0.0012) -[2023-11-28 06:52:30,298][87424] Updated weights for policy 0, policy_version 254428 (0.0012) -[2023-11-28 06:52:30,673][87426] Updated weights for policy 1, policy_version 254210 (0.0009) -[2023-11-28 06:52:31,050][87426] Updated weights for policy 1, policy_version 254220 (0.0009) -[2023-11-28 06:52:31,432][87426] Updated weights for policy 1, policy_version 254230 (0.0008) -[2023-11-28 06:52:31,818][87426] Updated weights for policy 1, policy_version 254240 (0.0009) -[2023-11-28 06:52:32,702][87424] Updated weights for policy 0, policy_version 254438 (0.0010) -[2023-11-28 06:52:33,092][87424] Updated weights for policy 0, policy_version 254448 (0.0009) -[2023-11-28 06:52:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 130220032. Throughput: 0: 2714.0, 1: 2721.6. Samples: 130237884. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:52:33,445][86177] Avg episode reward: [(0, '-552.160'), (1, '-526.980')] -[2023-11-28 06:52:33,466][87424] Updated weights for policy 0, policy_version 254458 (0.0009) -[2023-11-28 06:52:33,691][87426] Updated weights for policy 1, policy_version 254250 (0.0007) -[2023-11-28 06:52:34,066][87426] Updated weights for policy 1, policy_version 254260 (0.0007) -[2023-11-28 06:52:34,450][87426] Updated weights for policy 1, policy_version 254270 (0.0007) -[2023-11-28 06:52:35,543][87424] Updated weights for policy 0, policy_version 254468 (0.0009) -[2023-11-28 06:52:35,918][87424] Updated weights for policy 0, policy_version 254478 (0.0008) -[2023-11-28 06:52:36,297][87424] Updated weights for policy 0, policy_version 254488 (0.0007) -[2023-11-28 06:52:36,899][87426] Updated weights for policy 1, policy_version 254280 (0.0008) -[2023-11-28 06:52:37,271][87426] Updated weights for policy 1, policy_version 254290 (0.0008) -[2023-11-28 06:52:37,650][87426] Updated weights for policy 1, policy_version 254300 (0.0008) -[2023-11-28 06:52:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 130252800. Throughput: 0: 2698.0, 1: 2692.4. Samples: 130269096. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:52:38,445][86177] Avg episode reward: [(0, '-595.600'), (1, '-501.870')] -[2023-11-28 06:52:38,748][87424] Updated weights for policy 0, policy_version 254498 (0.0007) -[2023-11-28 06:52:39,132][87424] Updated weights for policy 0, policy_version 254508 (0.0008) -[2023-11-28 06:52:39,517][87424] Updated weights for policy 0, policy_version 254518 (0.0010) -[2023-11-28 06:52:39,591][87426] Updated weights for policy 1, policy_version 254310 (0.0009) -[2023-11-28 06:52:39,896][87424] Updated weights for policy 0, policy_version 254528 (0.0009) -[2023-11-28 06:52:39,959][87426] Updated weights for policy 1, policy_version 254320 (0.0011) -[2023-11-28 06:52:40,346][87426] Updated weights for policy 1, policy_version 254330 (0.0012) -[2023-11-28 06:52:42,059][87424] Updated weights for policy 0, policy_version 254538 (0.0011) -[2023-11-28 06:52:42,445][87424] Updated weights for policy 0, policy_version 254548 (0.0010) -[2023-11-28 06:52:42,447][87426] Updated weights for policy 1, policy_version 254340 (0.0012) -[2023-11-28 06:52:42,826][87426] Updated weights for policy 1, policy_version 254350 (0.0010) -[2023-11-28 06:52:42,826][87424] Updated weights for policy 0, policy_version 254558 (0.0008) -[2023-11-28 06:52:43,198][87426] Updated weights for policy 1, policy_version 254360 (0.0009) -[2023-11-28 06:52:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 130277376. Throughput: 0: 2674.5, 1: 2666.0. Samples: 130292312. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:52:43,445][86177] Avg episode reward: [(0, '-604.520'), (1, '-517.380')] -[2023-11-28 06:52:45,369][87424] Updated weights for policy 0, policy_version 254568 (0.0010) -[2023-11-28 06:52:45,692][87426] Updated weights for policy 1, policy_version 254370 (0.0011) -[2023-11-28 06:52:45,751][87424] Updated weights for policy 0, policy_version 254578 (0.0012) -[2023-11-28 06:52:46,076][87426] Updated weights for policy 1, policy_version 254380 (0.0012) -[2023-11-28 06:52:46,127][87424] Updated weights for policy 0, policy_version 254588 (0.0012) -[2023-11-28 06:52:46,445][87426] Updated weights for policy 1, policy_version 254390 (0.0011) -[2023-11-28 06:52:46,826][87426] Updated weights for policy 1, policy_version 254400 (0.0010) -[2023-11-28 06:52:48,088][87424] Updated weights for policy 0, policy_version 254598 (0.0008) -[2023-11-28 06:52:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 130301952. Throughput: 0: 2674.6, 1: 2671.6. Samples: 130317104. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:52:48,445][86177] Avg episode reward: [(0, '-601.380'), (1, '-516.510')] -[2023-11-28 06:52:48,466][87424] Updated weights for policy 0, policy_version 254608 (0.0008) -[2023-11-28 06:52:48,856][87424] Updated weights for policy 0, policy_version 254618 (0.0008) -[2023-11-28 06:52:48,891][87426] Updated weights for policy 1, policy_version 254410 (0.0012) -[2023-11-28 06:52:49,267][87426] Updated weights for policy 1, policy_version 254420 (0.0010) -[2023-11-28 06:52:49,652][87426] Updated weights for policy 1, policy_version 254430 (0.0012) -[2023-11-28 06:52:50,828][87424] Updated weights for policy 0, policy_version 254628 (0.0011) -[2023-11-28 06:52:51,215][87424] Updated weights for policy 0, policy_version 254638 (0.0011) -[2023-11-28 06:52:51,593][87424] Updated weights for policy 0, policy_version 254648 (0.0012) -[2023-11-28 06:52:51,788][87426] Updated weights for policy 1, policy_version 254440 (0.0011) -[2023-11-28 06:52:52,170][87426] Updated weights for policy 1, policy_version 254450 (0.0011) -[2023-11-28 06:52:52,550][87426] Updated weights for policy 1, policy_version 254460 (0.0008) -[2023-11-28 06:52:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 130334720. Throughput: 0: 2665.3, 1: 2688.8. Samples: 130350352. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:52:53,445][86177] Avg episode reward: [(0, '-555.160'), (1, '-526.340')] -[2023-11-28 06:52:54,140][87424] Updated weights for policy 0, policy_version 254658 (0.0009) -[2023-11-28 06:52:54,519][87424] Updated weights for policy 0, policy_version 254668 (0.0011) -[2023-11-28 06:52:54,733][87426] Updated weights for policy 1, policy_version 254470 (0.0010) -[2023-11-28 06:52:54,907][87424] Updated weights for policy 0, policy_version 254678 (0.0011) -[2023-11-28 06:52:55,113][87426] Updated weights for policy 1, policy_version 254480 (0.0012) -[2023-11-28 06:52:55,288][87424] Updated weights for policy 0, policy_version 254688 (0.0011) -[2023-11-28 06:52:55,495][87426] Updated weights for policy 1, policy_version 254490 (0.0012) -[2023-11-28 06:52:56,988][87424] Updated weights for policy 0, policy_version 254698 (0.0007) -[2023-11-28 06:52:57,362][87424] Updated weights for policy 0, policy_version 254708 (0.0008) -[2023-11-28 06:52:57,560][87426] Updated weights for policy 1, policy_version 254500 (0.0012) -[2023-11-28 06:52:57,751][87424] Updated weights for policy 0, policy_version 254718 (0.0007) -[2023-11-28 06:52:57,946][87426] Updated weights for policy 1, policy_version 254510 (0.0012) -[2023-11-28 06:52:58,321][87426] Updated weights for policy 1, policy_version 254520 (0.0012) -[2023-11-28 06:52:58,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 130359296. Throughput: 0: 2659.0, 1: 2708.9. Samples: 130374832. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:52:58,446][86177] Avg episode reward: [(0, '-562.120'), (1, '-542.250')] -[2023-11-28 06:52:59,975][87424] Updated weights for policy 0, policy_version 254728 (0.0011) -[2023-11-28 06:53:00,185][87426] Updated weights for policy 1, policy_version 254530 (0.0011) -[2023-11-28 06:53:00,361][87424] Updated weights for policy 0, policy_version 254738 (0.0016) -[2023-11-28 06:53:00,570][87426] Updated weights for policy 1, policy_version 254540 (0.0010) -[2023-11-28 06:53:00,741][87424] Updated weights for policy 0, policy_version 254748 (0.0011) -[2023-11-28 06:53:00,951][87426] Updated weights for policy 1, policy_version 254550 (0.0011) -[2023-11-28 06:53:01,326][87426] Updated weights for policy 1, policy_version 254560 (0.0009) -[2023-11-28 06:53:02,630][87424] Updated weights for policy 0, policy_version 254758 (0.0009) -[2023-11-28 06:53:03,008][87424] Updated weights for policy 0, policy_version 254768 (0.0009) -[2023-11-28 06:53:03,387][87424] Updated weights for policy 0, policy_version 254778 (0.0011) -[2023-11-28 06:53:03,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 130383872. Throughput: 0: 2673.8, 1: 2707.6. Samples: 130400032. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:53:03,446][86177] Avg episode reward: [(0, '-551.730'), (1, '-526.450')] -[2023-11-28 06:53:03,870][87426] Updated weights for policy 1, policy_version 254570 (0.0010) -[2023-11-28 06:53:04,246][87426] Updated weights for policy 1, policy_version 254580 (0.0012) -[2023-11-28 06:53:04,626][87426] Updated weights for policy 1, policy_version 254590 (0.0012) -[2023-11-28 06:53:05,611][87424] Updated weights for policy 0, policy_version 254788 (0.0012) -[2023-11-28 06:53:05,991][87424] Updated weights for policy 0, policy_version 254798 (0.0012) -[2023-11-28 06:53:06,367][87424] Updated weights for policy 0, policy_version 254808 (0.0012) -[2023-11-28 06:53:06,699][87426] Updated weights for policy 1, policy_version 254600 (0.0011) -[2023-11-28 06:53:07,084][87426] Updated weights for policy 1, policy_version 254610 (0.0012) -[2023-11-28 06:53:07,458][87426] Updated weights for policy 1, policy_version 254620 (0.0012) -[2023-11-28 06:53:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130416640. Throughput: 0: 2708.0, 1: 2697.1. Samples: 130432296. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:53:08,445][86177] Avg episode reward: [(0, '-553.920'), (1, '-525.190')] -[2023-11-28 06:53:08,864][87424] Updated weights for policy 0, policy_version 254818 (0.0011) -[2023-11-28 06:53:09,244][87424] Updated weights for policy 0, policy_version 254828 (0.0009) -[2023-11-28 06:53:09,297][87426] Updated weights for policy 1, policy_version 254630 (0.0009) -[2023-11-28 06:53:09,635][87424] Updated weights for policy 0, policy_version 254838 (0.0009) -[2023-11-28 06:53:09,685][87426] Updated weights for policy 1, policy_version 254640 (0.0012) -[2023-11-28 06:53:10,008][87424] Updated weights for policy 0, policy_version 254848 (0.0010) -[2023-11-28 06:53:10,053][87426] Updated weights for policy 1, policy_version 254650 (0.0011) -[2023-11-28 06:53:12,264][87424] Updated weights for policy 0, policy_version 254858 (0.0010) -[2023-11-28 06:53:12,488][87426] Updated weights for policy 1, policy_version 254660 (0.0008) -[2023-11-28 06:53:12,646][87424] Updated weights for policy 0, policy_version 254868 (0.0011) -[2023-11-28 06:53:12,869][87426] Updated weights for policy 1, policy_version 254670 (0.0010) -[2023-11-28 06:53:13,031][87424] Updated weights for policy 0, policy_version 254878 (0.0011) -[2023-11-28 06:53:13,242][87426] Updated weights for policy 1, policy_version 254680 (0.0008) -[2023-11-28 06:53:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130441216. Throughput: 0: 2718.0, 1: 2702.4. Samples: 130456712. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:53:13,445][86177] Avg episode reward: [(0, '-559.530'), (1, '-523.930')] -[2023-11-28 06:53:14,970][87424] Updated weights for policy 0, policy_version 254888 (0.0011) -[2023-11-28 06:53:15,250][87426] Updated weights for policy 1, policy_version 254690 (0.0008) -[2023-11-28 06:53:15,346][87424] Updated weights for policy 0, policy_version 254898 (0.0010) -[2023-11-28 06:53:15,625][87426] Updated weights for policy 1, policy_version 254700 (0.0011) -[2023-11-28 06:53:15,737][87424] Updated weights for policy 0, policy_version 254908 (0.0008) -[2023-11-28 06:53:16,004][87426] Updated weights for policy 1, policy_version 254710 (0.0007) -[2023-11-28 06:53:16,388][87426] Updated weights for policy 1, policy_version 254720 (0.0008) -[2023-11-28 06:53:17,820][87424] Updated weights for policy 0, policy_version 254918 (0.0010) -[2023-11-28 06:53:18,205][87424] Updated weights for policy 0, policy_version 254928 (0.0011) -[2023-11-28 06:53:18,360][87426] Updated weights for policy 1, policy_version 254730 (0.0012) -[2023-11-28 06:53:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 130465792. Throughput: 0: 2717.7, 1: 2695.6. Samples: 130481480. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:53:18,445][86177] Avg episode reward: [(0, '-596.660'), (1, '-512.740')] -[2023-11-28 06:53:18,591][87424] Updated weights for policy 0, policy_version 254938 (0.0011) -[2023-11-28 06:53:18,739][87426] Updated weights for policy 1, policy_version 254740 (0.0011) -[2023-11-28 06:53:19,110][87426] Updated weights for policy 1, policy_version 254750 (0.0011) -[2023-11-28 06:53:20,810][87424] Updated weights for policy 0, policy_version 254948 (0.0011) -[2023-11-28 06:53:21,161][87426] Updated weights for policy 1, policy_version 254760 (0.0010) -[2023-11-28 06:53:21,196][87424] Updated weights for policy 0, policy_version 254958 (0.0011) -[2023-11-28 06:53:21,537][87426] Updated weights for policy 1, policy_version 254770 (0.0011) -[2023-11-28 06:53:21,574][87424] Updated weights for policy 0, policy_version 254968 (0.0011) -[2023-11-28 06:53:21,912][87426] Updated weights for policy 1, policy_version 254780 (0.0012) -[2023-11-28 06:53:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 130498560. Throughput: 0: 2732.3, 1: 2708.8. Samples: 130513944. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:53:23,445][86177] Avg episode reward: [(0, '-553.400'), (1, '-514.010')] -[2023-11-28 06:53:23,458][87424] Updated weights for policy 0, policy_version 254978 (0.0008) -[2023-11-28 06:53:23,840][87424] Updated weights for policy 0, policy_version 254988 (0.0007) -[2023-11-28 06:53:24,222][87424] Updated weights for policy 0, policy_version 254998 (0.0007) -[2023-11-28 06:53:24,311][87426] Updated weights for policy 1, policy_version 254790 (0.0012) -[2023-11-28 06:53:24,610][87424] Updated weights for policy 0, policy_version 255008 (0.0008) -[2023-11-28 06:53:24,687][87426] Updated weights for policy 1, policy_version 254800 (0.0012) -[2023-11-28 06:53:25,064][87426] Updated weights for policy 1, policy_version 254810 (0.0008) -[2023-11-28 06:53:26,421][87424] Updated weights for policy 0, policy_version 255018 (0.0010) -[2023-11-28 06:53:26,802][87424] Updated weights for policy 0, policy_version 255028 (0.0011) -[2023-11-28 06:53:27,181][87424] Updated weights for policy 0, policy_version 255038 (0.0010) -[2023-11-28 06:53:27,546][87426] Updated weights for policy 1, policy_version 254820 (0.0010) -[2023-11-28 06:53:27,937][87426] Updated weights for policy 1, policy_version 254830 (0.0010) -[2023-11-28 06:53:28,313][87426] Updated weights for policy 1, policy_version 254840 (0.0010) -[2023-11-28 06:53:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130523136. Throughput: 0: 2767.7, 1: 2715.4. Samples: 130539052. Policy #0 lag: (min: 31.0, avg: 43.7, max: 63.0) -[2023-11-28 06:53:28,445][86177] Avg episode reward: [(0, '-556.860'), (1, '-512.710')] -[2023-11-28 06:53:29,565][87424] Updated weights for policy 0, policy_version 255048 (0.0010) -[2023-11-28 06:53:29,947][87424] Updated weights for policy 0, policy_version 255058 (0.0010) -[2023-11-28 06:53:30,330][87424] Updated weights for policy 0, policy_version 255068 (0.0009) -[2023-11-28 06:53:30,879][87426] Updated weights for policy 1, policy_version 254850 (0.0010) -[2023-11-28 06:53:31,263][87426] Updated weights for policy 1, policy_version 254860 (0.0007) -[2023-11-28 06:53:31,642][87426] Updated weights for policy 1, policy_version 254870 (0.0009) -[2023-11-28 06:53:32,021][87426] Updated weights for policy 1, policy_version 254880 (0.0011) -[2023-11-28 06:53:32,570][87424] Updated weights for policy 0, policy_version 255078 (0.0009) -[2023-11-28 06:53:32,965][87424] Updated weights for policy 0, policy_version 255088 (0.0011) -[2023-11-28 06:53:33,337][87424] Updated weights for policy 0, policy_version 255098 (0.0008) -[2023-11-28 06:53:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 130547712. Throughput: 0: 2779.8, 1: 2692.2. Samples: 130563344. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:53:33,445][86177] Avg episode reward: [(0, '-563.310'), (1, '-536.290')] -[2023-11-28 06:53:34,505][87426] Updated weights for policy 1, policy_version 254890 (0.0011) -[2023-11-28 06:53:34,879][87426] Updated weights for policy 1, policy_version 254900 (0.0009) -[2023-11-28 06:53:35,198][87424] Updated weights for policy 0, policy_version 255108 (0.0010) -[2023-11-28 06:53:35,254][87426] Updated weights for policy 1, policy_version 254910 (0.0008) -[2023-11-28 06:53:35,581][87424] Updated weights for policy 0, policy_version 255118 (0.0008) -[2023-11-28 06:53:35,975][87424] Updated weights for policy 0, policy_version 255128 (0.0011) -[2023-11-28 06:53:37,800][87426] Updated weights for policy 1, policy_version 254920 (0.0007) -[2023-11-28 06:53:37,804][87424] Updated weights for policy 0, policy_version 255138 (0.0012) -[2023-11-28 06:53:38,186][87426] Updated weights for policy 1, policy_version 254930 (0.0008) -[2023-11-28 06:53:38,200][87424] Updated weights for policy 0, policy_version 255148 (0.0012) -[2023-11-28 06:53:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 130572288. Throughput: 0: 2770.5, 1: 2666.0. Samples: 130594996. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:53:38,445][86177] Avg episode reward: [(0, '-564.550'), (1, '-534.390')] -[2023-11-28 06:53:38,567][87426] Updated weights for policy 1, policy_version 254940 (0.0012) -[2023-11-28 06:53:38,576][87424] Updated weights for policy 0, policy_version 255158 (0.0010) -[2023-11-28 06:53:38,955][87424] Updated weights for policy 0, policy_version 255168 (0.0008) -[2023-11-28 06:53:41,067][87426] Updated weights for policy 1, policy_version 254950 (0.0011) -[2023-11-28 06:53:41,196][87424] Updated weights for policy 0, policy_version 255178 (0.0010) -[2023-11-28 06:53:41,452][87426] Updated weights for policy 1, policy_version 254960 (0.0011) -[2023-11-28 06:53:41,591][87424] Updated weights for policy 0, policy_version 255188 (0.0012) -[2023-11-28 06:53:41,828][87426] Updated weights for policy 1, policy_version 254970 (0.0011) -[2023-11-28 06:53:41,971][87424] Updated weights for policy 0, policy_version 255198 (0.0012) -[2023-11-28 06:53:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130605056. Throughput: 0: 2775.0, 1: 2643.0. Samples: 130618640. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:53:43,445][86177] Avg episode reward: [(0, '-604.090'), (1, '-534.420')] -[2023-11-28 06:53:44,179][87426] Updated weights for policy 1, policy_version 254980 (0.0012) -[2023-11-28 06:53:44,561][87426] Updated weights for policy 1, policy_version 254990 (0.0011) -[2023-11-28 06:53:44,595][87424] Updated weights for policy 0, policy_version 255208 (0.0011) -[2023-11-28 06:53:44,935][87426] Updated weights for policy 1, policy_version 255000 (0.0011) -[2023-11-28 06:53:44,980][87424] Updated weights for policy 0, policy_version 255218 (0.0011) -[2023-11-28 06:53:45,358][87424] Updated weights for policy 0, policy_version 255228 (0.0010) -[2023-11-28 06:53:47,124][87426] Updated weights for policy 1, policy_version 255010 (0.0011) -[2023-11-28 06:53:47,144][87424] Updated weights for policy 0, policy_version 255238 (0.0009) -[2023-11-28 06:53:47,500][87426] Updated weights for policy 1, policy_version 255020 (0.0009) -[2023-11-28 06:53:47,514][87424] Updated weights for policy 0, policy_version 255248 (0.0009) -[2023-11-28 06:53:47,886][87426] Updated weights for policy 1, policy_version 255030 (0.0010) -[2023-11-28 06:53:47,904][87424] Updated weights for policy 0, policy_version 255258 (0.0011) -[2023-11-28 06:53:48,266][87426] Updated weights for policy 1, policy_version 255040 (0.0012) -[2023-11-28 06:53:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 130637824. Throughput: 0: 2770.8, 1: 2642.7. Samples: 130643636. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:53:48,445][86177] Avg episode reward: [(0, '-641.350'), (1, '-535.660')] -[2023-11-28 06:53:50,058][87424] Updated weights for policy 0, policy_version 255268 (0.0009) -[2023-11-28 06:53:50,167][87426] Updated weights for policy 1, policy_version 255050 (0.0011) -[2023-11-28 06:53:50,440][87424] Updated weights for policy 0, policy_version 255278 (0.0011) -[2023-11-28 06:53:50,547][87426] Updated weights for policy 1, policy_version 255060 (0.0011) -[2023-11-28 06:53:50,826][87424] Updated weights for policy 0, policy_version 255288 (0.0010) -[2023-11-28 06:53:50,913][87426] Updated weights for policy 1, policy_version 255070 (0.0011) -[2023-11-28 06:53:53,033][87424] Updated weights for policy 0, policy_version 255298 (0.0011) -[2023-11-28 06:53:53,417][87424] Updated weights for policy 0, policy_version 255308 (0.0012) -[2023-11-28 06:53:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 130654208. Throughput: 0: 2775.8, 1: 2642.8. Samples: 130676136. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:53:53,445][86177] Avg episode reward: [(0, '-763.440'), (1, '-505.480')] -[2023-11-28 06:53:53,449][87426] Updated weights for policy 1, policy_version 255080 (0.0011) -[2023-11-28 06:53:53,799][87424] Updated weights for policy 0, policy_version 255318 (0.0012) -[2023-11-28 06:53:53,832][87426] Updated weights for policy 1, policy_version 255090 (0.0009) -[2023-11-28 06:53:54,177][87424] Updated weights for policy 0, policy_version 255328 (0.0012) -[2023-11-28 06:53:54,212][87426] Updated weights for policy 1, policy_version 255100 (0.0008) -[2023-11-28 06:53:56,240][87424] Updated weights for policy 0, policy_version 255338 (0.0012) -[2023-11-28 06:53:56,314][87426] Updated weights for policy 1, policy_version 255110 (0.0008) -[2023-11-28 06:53:56,629][87424] Updated weights for policy 0, policy_version 255348 (0.0012) -[2023-11-28 06:53:56,692][87426] Updated weights for policy 1, policy_version 255120 (0.0011) -[2023-11-28 06:53:56,996][87424] Updated weights for policy 0, policy_version 255358 (0.0012) -[2023-11-28 06:53:57,064][87426] Updated weights for policy 1, policy_version 255130 (0.0008) -[2023-11-28 06:53:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 130686976. Throughput: 0: 2783.1, 1: 2644.2. Samples: 130700940. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:53:58,445][86177] Avg episode reward: [(0, '-744.230'), (1, '-501.900')] -[2023-11-28 06:53:58,922][87424] Updated weights for policy 0, policy_version 255368 (0.0012) -[2023-11-28 06:53:59,302][87424] Updated weights for policy 0, policy_version 255378 (0.0012) -[2023-11-28 06:53:59,375][87426] Updated weights for policy 1, policy_version 255140 (0.0010) -[2023-11-28 06:53:59,681][87424] Updated weights for policy 0, policy_version 255388 (0.0012) -[2023-11-28 06:53:59,759][87426] Updated weights for policy 1, policy_version 255150 (0.0009) -[2023-11-28 06:54:00,126][87426] Updated weights for policy 1, policy_version 255160 (0.0011) -[2023-11-28 06:54:01,537][87424] Updated weights for policy 0, policy_version 255398 (0.0011) -[2023-11-28 06:54:01,923][87424] Updated weights for policy 0, policy_version 255408 (0.0012) -[2023-11-28 06:54:02,049][87426] Updated weights for policy 1, policy_version 255170 (0.0012) -[2023-11-28 06:54:02,317][87424] Updated weights for policy 0, policy_version 255418 (0.0011) -[2023-11-28 06:54:02,430][87426] Updated weights for policy 1, policy_version 255180 (0.0011) -[2023-11-28 06:54:02,803][87426] Updated weights for policy 1, policy_version 255190 (0.0011) -[2023-11-28 06:54:03,180][87426] Updated weights for policy 1, policy_version 255200 (0.0008) -[2023-11-28 06:54:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 130719744. Throughput: 0: 2784.6, 1: 2668.2. Samples: 130726856. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:54:03,445][86177] Avg episode reward: [(0, '-705.790'), (1, '-495.710')] -[2023-11-28 06:54:04,758][87424] Updated weights for policy 0, policy_version 255428 (0.0011) -[2023-11-28 06:54:05,133][87424] Updated weights for policy 0, policy_version 255438 (0.0012) -[2023-11-28 06:54:05,517][87424] Updated weights for policy 0, policy_version 255448 (0.0012) -[2023-11-28 06:54:05,624][87426] Updated weights for policy 1, policy_version 255210 (0.0010) -[2023-11-28 06:54:05,997][87426] Updated weights for policy 1, policy_version 255220 (0.0011) -[2023-11-28 06:54:06,370][87426] Updated weights for policy 1, policy_version 255230 (0.0012) -[2023-11-28 06:54:08,035][87424] Updated weights for policy 0, policy_version 255458 (0.0012) -[2023-11-28 06:54:08,421][87424] Updated weights for policy 0, policy_version 255468 (0.0012) -[2023-11-28 06:54:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 130736128. Throughput: 0: 2788.5, 1: 2665.3. Samples: 130759368. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:54:08,445][86177] Avg episode reward: [(0, '-704.880'), (1, '-496.660')] -[2023-11-28 06:54:08,549][87426] Updated weights for policy 1, policy_version 255240 (0.0009) -[2023-11-28 06:54:08,798][87424] Updated weights for policy 0, policy_version 255478 (0.0012) -[2023-11-28 06:54:08,929][87426] Updated weights for policy 1, policy_version 255250 (0.0010) -[2023-11-28 06:54:09,176][87424] Updated weights for policy 0, policy_version 255488 (0.0012) -[2023-11-28 06:54:09,313][87426] Updated weights for policy 1, policy_version 255260 (0.0012) -[2023-11-28 06:54:11,055][87424] Updated weights for policy 0, policy_version 255498 (0.0012) -[2023-11-28 06:54:11,429][87426] Updated weights for policy 1, policy_version 255270 (0.0011) -[2023-11-28 06:54:11,440][87424] Updated weights for policy 0, policy_version 255508 (0.0011) -[2023-11-28 06:54:11,802][87426] Updated weights for policy 1, policy_version 255280 (0.0010) -[2023-11-28 06:54:11,829][87424] Updated weights for policy 0, policy_version 255518 (0.0011) -[2023-11-28 06:54:12,180][87426] Updated weights for policy 1, policy_version 255290 (0.0012) -[2023-11-28 06:54:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130768896. Throughput: 0: 2775.4, 1: 2678.6. Samples: 130784480. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:54:13,445][86177] Avg episode reward: [(0, '-582.440'), (1, '-495.010')] -[2023-11-28 06:54:13,873][87424] Updated weights for policy 0, policy_version 255528 (0.0012) -[2023-11-28 06:54:14,258][87424] Updated weights for policy 0, policy_version 255538 (0.0012) -[2023-11-28 06:54:14,308][87426] Updated weights for policy 1, policy_version 255300 (0.0010) -[2023-11-28 06:54:14,639][87424] Updated weights for policy 0, policy_version 255548 (0.0012) -[2023-11-28 06:54:14,684][87426] Updated weights for policy 1, policy_version 255310 (0.0007) -[2023-11-28 06:54:15,058][87426] Updated weights for policy 1, policy_version 255320 (0.0012) -[2023-11-28 06:54:16,551][87424] Updated weights for policy 0, policy_version 255558 (0.0011) -[2023-11-28 06:54:16,934][87424] Updated weights for policy 0, policy_version 255568 (0.0012) -[2023-11-28 06:54:17,319][87424] Updated weights for policy 0, policy_version 255578 (0.0012) -[2023-11-28 06:54:17,329][87426] Updated weights for policy 1, policy_version 255330 (0.0012) -[2023-11-28 06:54:17,705][87426] Updated weights for policy 1, policy_version 255340 (0.0008) -[2023-11-28 06:54:18,099][87426] Updated weights for policy 1, policy_version 255350 (0.0011) -[2023-11-28 06:54:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 130793472. Throughput: 0: 2759.4, 1: 2697.2. Samples: 130808888. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:54:18,445][86177] Avg episode reward: [(0, '-553.240'), (1, '-503.700')] -[2023-11-28 06:54:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000255584_65429504.pth... -[2023-11-28 06:54:18,477][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000255360_65372160.pth... -[2023-11-28 06:54:18,478][87426] Updated weights for policy 1, policy_version 255360 (0.0011) -[2023-11-28 06:54:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000253024_64774144.pth -[2023-11-28 06:54:18,532][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000252832_64724992.pth -[2023-11-28 06:54:19,819][87424] Updated weights for policy 0, policy_version 255588 (0.0011) -[2023-11-28 06:54:20,199][87424] Updated weights for policy 0, policy_version 255598 (0.0011) -[2023-11-28 06:54:20,423][87426] Updated weights for policy 1, policy_version 255370 (0.0011) -[2023-11-28 06:54:20,582][87424] Updated weights for policy 0, policy_version 255608 (0.0009) -[2023-11-28 06:54:20,803][87426] Updated weights for policy 1, policy_version 255380 (0.0012) -[2023-11-28 06:54:21,177][87426] Updated weights for policy 1, policy_version 255390 (0.0011) -[2023-11-28 06:54:22,801][87424] Updated weights for policy 0, policy_version 255618 (0.0011) -[2023-11-28 06:54:23,145][87426] Updated weights for policy 1, policy_version 255400 (0.0011) -[2023-11-28 06:54:23,191][87424] Updated weights for policy 0, policy_version 255628 (0.0008) -[2023-11-28 06:54:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 130818048. Throughput: 0: 2764.6, 1: 2733.1. Samples: 130842392. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:54:23,445][86177] Avg episode reward: [(0, '-509.080'), (1, '-523.210')] -[2023-11-28 06:54:23,526][87426] Updated weights for policy 1, policy_version 255410 (0.0008) -[2023-11-28 06:54:23,568][87424] Updated weights for policy 0, policy_version 255638 (0.0012) -[2023-11-28 06:54:23,912][87426] Updated weights for policy 1, policy_version 255420 (0.0011) -[2023-11-28 06:54:23,956][87424] Updated weights for policy 0, policy_version 255648 (0.0009) -[2023-11-28 06:54:25,709][87424] Updated weights for policy 0, policy_version 255658 (0.0012) -[2023-11-28 06:54:25,916][87426] Updated weights for policy 1, policy_version 255430 (0.0011) -[2023-11-28 06:54:26,089][87424] Updated weights for policy 0, policy_version 255668 (0.0012) -[2023-11-28 06:54:26,293][87426] Updated weights for policy 1, policy_version 255440 (0.0008) -[2023-11-28 06:54:26,474][87424] Updated weights for policy 0, policy_version 255678 (0.0011) -[2023-11-28 06:54:26,683][87426] Updated weights for policy 1, policy_version 255450 (0.0008) -[2023-11-28 06:54:28,397][87426] Updated weights for policy 1, policy_version 255460 (0.0009) -[2023-11-28 06:54:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 130850816. Throughput: 0: 2767.5, 1: 2776.6. Samples: 130868124. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:54:28,446][86177] Avg episode reward: [(0, '-511.770'), (1, '-526.300')] -[2023-11-28 06:54:28,783][87426] Updated weights for policy 1, policy_version 255470 (0.0010) -[2023-11-28 06:54:28,851][87424] Updated weights for policy 0, policy_version 255688 (0.0011) -[2023-11-28 06:54:29,164][87426] Updated weights for policy 1, policy_version 255480 (0.0009) -[2023-11-28 06:54:29,235][87424] Updated weights for policy 0, policy_version 255698 (0.0010) -[2023-11-28 06:54:29,614][87424] Updated weights for policy 0, policy_version 255708 (0.0007) -[2023-11-28 06:54:31,593][87426] Updated weights for policy 1, policy_version 255490 (0.0010) -[2023-11-28 06:54:31,644][87424] Updated weights for policy 0, policy_version 255718 (0.0008) -[2023-11-28 06:54:31,975][87426] Updated weights for policy 1, policy_version 255500 (0.0009) -[2023-11-28 06:54:32,030][87424] Updated weights for policy 0, policy_version 255728 (0.0009) -[2023-11-28 06:54:32,357][87426] Updated weights for policy 1, policy_version 255510 (0.0009) -[2023-11-28 06:54:32,408][87424] Updated weights for policy 0, policy_version 255738 (0.0012) -[2023-11-28 06:54:32,736][87426] Updated weights for policy 1, policy_version 255520 (0.0007) -[2023-11-28 06:54:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 130883584. Throughput: 0: 2745.8, 1: 2767.4. Samples: 130891728. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:54:33,445][86177] Avg episode reward: [(0, '-539.820'), (1, '-528.580')] -[2023-11-28 06:54:34,499][87426] Updated weights for policy 1, policy_version 255530 (0.0012) -[2023-11-28 06:54:34,744][87424] Updated weights for policy 0, policy_version 255748 (0.0011) -[2023-11-28 06:54:34,874][87426] Updated weights for policy 1, policy_version 255540 (0.0011) -[2023-11-28 06:54:35,117][87424] Updated weights for policy 0, policy_version 255758 (0.0011) -[2023-11-28 06:54:35,262][87426] Updated weights for policy 1, policy_version 255550 (0.0010) -[2023-11-28 06:54:35,505][87424] Updated weights for policy 0, policy_version 255768 (0.0012) -[2023-11-28 06:54:37,080][87426] Updated weights for policy 1, policy_version 255560 (0.0009) -[2023-11-28 06:54:37,460][87426] Updated weights for policy 1, policy_version 255570 (0.0008) -[2023-11-28 06:54:37,559][87424] Updated weights for policy 0, policy_version 255778 (0.0012) -[2023-11-28 06:54:37,841][87426] Updated weights for policy 1, policy_version 255580 (0.0008) -[2023-11-28 06:54:37,943][87424] Updated weights for policy 0, policy_version 255788 (0.0012) -[2023-11-28 06:54:38,331][87424] Updated weights for policy 0, policy_version 255798 (0.0011) -[2023-11-28 06:54:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 130908160. Throughput: 0: 2750.9, 1: 2785.4. Samples: 130925272. Policy #0 lag: (min: 21.0, avg: 46.4, max: 64.0) -[2023-11-28 06:54:38,445][86177] Avg episode reward: [(0, '-537.180'), (1, '-528.470')] -[2023-11-28 06:54:38,710][87424] Updated weights for policy 0, policy_version 255808 (0.0012) -[2023-11-28 06:54:40,348][87426] Updated weights for policy 1, policy_version 255590 (0.0008) -[2023-11-28 06:54:40,732][87426] Updated weights for policy 1, policy_version 255600 (0.0009) -[2023-11-28 06:54:41,073][87424] Updated weights for policy 0, policy_version 255818 (0.0011) -[2023-11-28 06:54:41,107][87426] Updated weights for policy 1, policy_version 255610 (0.0012) -[2023-11-28 06:54:41,467][87424] Updated weights for policy 0, policy_version 255828 (0.0012) -[2023-11-28 06:54:41,845][87424] Updated weights for policy 0, policy_version 255838 (0.0011) -[2023-11-28 06:54:43,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 130932736. Throughput: 0: 2734.2, 1: 2779.0. Samples: 130949036. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:54:43,446][86177] Avg episode reward: [(0, '-537.620'), (1, '-530.750')] -[2023-11-28 06:54:43,531][87426] Updated weights for policy 1, policy_version 255620 (0.0012) -[2023-11-28 06:54:43,904][87426] Updated weights for policy 1, policy_version 255630 (0.0011) -[2023-11-28 06:54:44,141][87424] Updated weights for policy 0, policy_version 255848 (0.0011) -[2023-11-28 06:54:44,286][87426] Updated weights for policy 1, policy_version 255640 (0.0012) -[2023-11-28 06:54:44,526][87424] Updated weights for policy 0, policy_version 255858 (0.0012) -[2023-11-28 06:54:44,901][87424] Updated weights for policy 0, policy_version 255868 (0.0010) -[2023-11-28 06:54:46,826][87426] Updated weights for policy 1, policy_version 255650 (0.0011) -[2023-11-28 06:54:47,199][87426] Updated weights for policy 1, policy_version 255660 (0.0011) -[2023-11-28 06:54:47,476][87424] Updated weights for policy 0, policy_version 255878 (0.0010) -[2023-11-28 06:54:47,577][87426] Updated weights for policy 1, policy_version 255670 (0.0011) -[2023-11-28 06:54:47,863][87424] Updated weights for policy 0, policy_version 255888 (0.0012) -[2023-11-28 06:54:47,953][87426] Updated weights for policy 1, policy_version 255680 (0.0010) -[2023-11-28 06:54:48,228][87424] Updated weights for policy 0, policy_version 255898 (0.0012) -[2023-11-28 06:54:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 130957312. Throughput: 0: 2705.2, 1: 2763.6. Samples: 130972948. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:54:48,445][86177] Avg episode reward: [(0, '-535.750'), (1, '-529.270')] -[2023-11-28 06:54:50,040][87426] Updated weights for policy 1, policy_version 255690 (0.0009) -[2023-11-28 06:54:50,313][87424] Updated weights for policy 0, policy_version 255908 (0.0011) -[2023-11-28 06:54:50,413][87426] Updated weights for policy 1, policy_version 255700 (0.0008) -[2023-11-28 06:54:50,692][87424] Updated weights for policy 0, policy_version 255918 (0.0009) -[2023-11-28 06:54:50,792][87426] Updated weights for policy 1, policy_version 255710 (0.0010) -[2023-11-28 06:54:51,074][87424] Updated weights for policy 0, policy_version 255928 (0.0012) -[2023-11-28 06:54:53,134][87424] Updated weights for policy 0, policy_version 255938 (0.0012) -[2023-11-28 06:54:53,226][87426] Updated weights for policy 1, policy_version 255720 (0.0010) -[2023-11-28 06:54:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 130981888. Throughput: 0: 2690.4, 1: 2761.2. Samples: 131004688. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:54:53,445][86177] Avg episode reward: [(0, '-511.860'), (1, '-523.210')] -[2023-11-28 06:54:53,501][87424] Updated weights for policy 0, policy_version 255948 (0.0011) -[2023-11-28 06:54:53,609][87426] Updated weights for policy 1, policy_version 255730 (0.0010) -[2023-11-28 06:54:53,883][87424] Updated weights for policy 0, policy_version 255958 (0.0010) -[2023-11-28 06:54:53,984][87426] Updated weights for policy 1, policy_version 255740 (0.0010) -[2023-11-28 06:54:54,263][87424] Updated weights for policy 0, policy_version 255968 (0.0010) -[2023-11-28 06:54:56,178][87424] Updated weights for policy 0, policy_version 255978 (0.0012) -[2023-11-28 06:54:56,455][87426] Updated weights for policy 1, policy_version 255750 (0.0009) -[2023-11-28 06:54:56,554][87424] Updated weights for policy 0, policy_version 255988 (0.0012) -[2023-11-28 06:54:56,835][87426] Updated weights for policy 1, policy_version 255760 (0.0009) -[2023-11-28 06:54:56,949][87424] Updated weights for policy 0, policy_version 255998 (0.0009) -[2023-11-28 06:54:57,208][87426] Updated weights for policy 1, policy_version 255770 (0.0011) -[2023-11-28 06:54:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 131014656. Throughput: 0: 2684.1, 1: 2726.0. Samples: 131027936. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:54:58,445][86177] Avg episode reward: [(0, '-559.490'), (1, '-520.020')] -[2023-11-28 06:54:58,824][87424] Updated weights for policy 0, policy_version 256008 (0.0011) -[2023-11-28 06:54:59,216][87424] Updated weights for policy 0, policy_version 256018 (0.0008) -[2023-11-28 06:54:59,228][87426] Updated weights for policy 1, policy_version 255780 (0.0010) -[2023-11-28 06:54:59,591][87424] Updated weights for policy 0, policy_version 256028 (0.0011) -[2023-11-28 06:54:59,607][87426] Updated weights for policy 1, policy_version 255790 (0.0010) -[2023-11-28 06:54:59,987][87426] Updated weights for policy 1, policy_version 255800 (0.0010) -[2023-11-28 06:55:01,980][87424] Updated weights for policy 0, policy_version 256038 (0.0011) -[2023-11-28 06:55:02,053][87426] Updated weights for policy 1, policy_version 255810 (0.0011) -[2023-11-28 06:55:02,349][87424] Updated weights for policy 0, policy_version 256048 (0.0012) -[2023-11-28 06:55:02,425][87426] Updated weights for policy 1, policy_version 255820 (0.0011) -[2023-11-28 06:55:02,732][87424] Updated weights for policy 0, policy_version 256058 (0.0011) -[2023-11-28 06:55:02,812][87426] Updated weights for policy 1, policy_version 255830 (0.0010) -[2023-11-28 06:55:03,184][87426] Updated weights for policy 1, policy_version 255840 (0.0012) -[2023-11-28 06:55:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131047424. Throughput: 0: 2709.0, 1: 2720.0. Samples: 131053192. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:03,445][86177] Avg episode reward: [(0, '-565.430'), (1, '-506.870')] -[2023-11-28 06:55:04,870][87424] Updated weights for policy 0, policy_version 256068 (0.0010) -[2023-11-28 06:55:05,255][87424] Updated weights for policy 0, policy_version 256078 (0.0008) -[2023-11-28 06:55:05,378][87426] Updated weights for policy 1, policy_version 255850 (0.0011) -[2023-11-28 06:55:05,640][87424] Updated weights for policy 0, policy_version 256088 (0.0008) -[2023-11-28 06:55:05,760][87426] Updated weights for policy 1, policy_version 255860 (0.0009) -[2023-11-28 06:55:06,138][87426] Updated weights for policy 1, policy_version 255870 (0.0007) -[2023-11-28 06:55:07,657][87424] Updated weights for policy 0, policy_version 256098 (0.0008) -[2023-11-28 06:55:08,039][87424] Updated weights for policy 0, policy_version 256108 (0.0009) -[2023-11-28 06:55:08,282][87426] Updated weights for policy 1, policy_version 255880 (0.0009) -[2023-11-28 06:55:08,429][87424] Updated weights for policy 0, policy_version 256118 (0.0009) -[2023-11-28 06:55:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 131063808. Throughput: 0: 2716.5, 1: 2709.9. Samples: 131086580. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:08,445][86177] Avg episode reward: [(0, '-609.030'), (1, '-513.670')] -[2023-11-28 06:55:08,656][87426] Updated weights for policy 1, policy_version 255890 (0.0010) -[2023-11-28 06:55:08,803][87424] Updated weights for policy 0, policy_version 256128 (0.0008) -[2023-11-28 06:55:09,059][87426] Updated weights for policy 1, policy_version 255900 (0.0008) -[2023-11-28 06:55:11,247][87424] Updated weights for policy 0, policy_version 256138 (0.0008) -[2023-11-28 06:55:11,350][87426] Updated weights for policy 1, policy_version 255910 (0.0009) -[2023-11-28 06:55:11,624][87424] Updated weights for policy 0, policy_version 256148 (0.0011) -[2023-11-28 06:55:11,732][87426] Updated weights for policy 1, policy_version 255920 (0.0009) -[2023-11-28 06:55:12,012][87424] Updated weights for policy 0, policy_version 256158 (0.0011) -[2023-11-28 06:55:12,112][87426] Updated weights for policy 1, policy_version 255930 (0.0012) -[2023-11-28 06:55:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 131096576. Throughput: 0: 2705.3, 1: 2668.0. Samples: 131109924. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:13,445][86177] Avg episode reward: [(0, '-609.500'), (1, '-506.370')] -[2023-11-28 06:55:14,167][87424] Updated weights for policy 0, policy_version 256168 (0.0010) -[2023-11-28 06:55:14,251][87426] Updated weights for policy 1, policy_version 255940 (0.0011) -[2023-11-28 06:55:14,547][87424] Updated weights for policy 0, policy_version 256178 (0.0010) -[2023-11-28 06:55:14,629][87426] Updated weights for policy 1, policy_version 255950 (0.0008) -[2023-11-28 06:55:14,931][87424] Updated weights for policy 0, policy_version 256188 (0.0008) -[2023-11-28 06:55:15,005][87426] Updated weights for policy 1, policy_version 255960 (0.0009) -[2023-11-28 06:55:17,098][87424] Updated weights for policy 0, policy_version 256198 (0.0010) -[2023-11-28 06:55:17,334][87426] Updated weights for policy 1, policy_version 255970 (0.0010) -[2023-11-28 06:55:17,474][87424] Updated weights for policy 0, policy_version 256208 (0.0012) -[2023-11-28 06:55:17,701][87426] Updated weights for policy 1, policy_version 255980 (0.0007) -[2023-11-28 06:55:17,851][87424] Updated weights for policy 0, policy_version 256218 (0.0010) -[2023-11-28 06:55:18,084][87426] Updated weights for policy 1, policy_version 255990 (0.0007) -[2023-11-28 06:55:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 131121152. Throughput: 0: 2715.1, 1: 2666.4. Samples: 131133896. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:18,445][86177] Avg episode reward: [(0, '-561.390'), (1, '-507.790')] -[2023-11-28 06:55:18,463][87426] Updated weights for policy 1, policy_version 256000 (0.0007) -[2023-11-28 06:55:20,343][87424] Updated weights for policy 0, policy_version 256228 (0.0008) -[2023-11-28 06:55:20,722][87424] Updated weights for policy 0, policy_version 256238 (0.0008) -[2023-11-28 06:55:20,937][87426] Updated weights for policy 1, policy_version 256010 (0.0011) -[2023-11-28 06:55:21,104][87424] Updated weights for policy 0, policy_version 256248 (0.0008) -[2023-11-28 06:55:21,317][87426] Updated weights for policy 1, policy_version 256020 (0.0011) -[2023-11-28 06:55:21,710][87426] Updated weights for policy 1, policy_version 256030 (0.0009) -[2023-11-28 06:55:23,236][87424] Updated weights for policy 0, policy_version 256258 (0.0011) -[2023-11-28 06:55:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 131145728. Throughput: 0: 2704.8, 1: 2624.1. Samples: 131165072. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:23,445][86177] Avg episode reward: [(0, '-566.630'), (1, '-506.190')] -[2023-11-28 06:55:23,615][87424] Updated weights for policy 0, policy_version 256268 (0.0012) -[2023-11-28 06:55:23,845][87426] Updated weights for policy 1, policy_version 256040 (0.0010) -[2023-11-28 06:55:24,005][87424] Updated weights for policy 0, policy_version 256278 (0.0010) -[2023-11-28 06:55:24,223][87426] Updated weights for policy 1, policy_version 256050 (0.0009) -[2023-11-28 06:55:24,382][87424] Updated weights for policy 0, policy_version 256288 (0.0009) -[2023-11-28 06:55:24,604][87426] Updated weights for policy 1, policy_version 256060 (0.0007) -[2023-11-28 06:55:26,373][87424] Updated weights for policy 0, policy_version 256298 (0.0012) -[2023-11-28 06:55:26,752][87424] Updated weights for policy 0, policy_version 256308 (0.0011) -[2023-11-28 06:55:27,135][87424] Updated weights for policy 0, policy_version 256318 (0.0008) -[2023-11-28 06:55:27,142][87426] Updated weights for policy 1, policy_version 256070 (0.0010) -[2023-11-28 06:55:27,533][87426] Updated weights for policy 1, policy_version 256080 (0.0010) -[2023-11-28 06:55:27,907][87426] Updated weights for policy 1, policy_version 256090 (0.0009) -[2023-11-28 06:55:28,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131178496. Throughput: 0: 2713.1, 1: 2652.4. Samples: 131190480. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:28,446][86177] Avg episode reward: [(0, '-523.590'), (1, '-521.050')] -[2023-11-28 06:55:29,053][87424] Updated weights for policy 0, policy_version 256328 (0.0008) -[2023-11-28 06:55:29,431][87424] Updated weights for policy 0, policy_version 256338 (0.0010) -[2023-11-28 06:55:29,816][87424] Updated weights for policy 0, policy_version 256348 (0.0008) -[2023-11-28 06:55:30,298][87426] Updated weights for policy 1, policy_version 256100 (0.0009) -[2023-11-28 06:55:30,672][87426] Updated weights for policy 1, policy_version 256110 (0.0012) -[2023-11-28 06:55:31,059][87426] Updated weights for policy 1, policy_version 256120 (0.0012) -[2023-11-28 06:55:32,322][87424] Updated weights for policy 0, policy_version 256358 (0.0011) -[2023-11-28 06:55:32,704][87424] Updated weights for policy 0, policy_version 256368 (0.0007) -[2023-11-28 06:55:33,082][87424] Updated weights for policy 0, policy_version 256378 (0.0010) -[2023-11-28 06:55:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 131203072. Throughput: 0: 2712.3, 1: 2630.2. Samples: 131213364. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:33,446][86177] Avg episode reward: [(0, '-532.110'), (1, '-527.870')] -[2023-11-28 06:55:33,595][87426] Updated weights for policy 1, policy_version 256130 (0.0011) -[2023-11-28 06:55:33,977][87426] Updated weights for policy 1, policy_version 256140 (0.0008) -[2023-11-28 06:55:34,364][87426] Updated weights for policy 1, policy_version 256150 (0.0007) -[2023-11-28 06:55:34,734][87426] Updated weights for policy 1, policy_version 256160 (0.0008) -[2023-11-28 06:55:35,582][87424] Updated weights for policy 0, policy_version 256388 (0.0011) -[2023-11-28 06:55:35,959][87424] Updated weights for policy 0, policy_version 256398 (0.0012) -[2023-11-28 06:55:36,327][87424] Updated weights for policy 0, policy_version 256408 (0.0011) -[2023-11-28 06:55:36,671][87426] Updated weights for policy 1, policy_version 256170 (0.0012) -[2023-11-28 06:55:37,048][87426] Updated weights for policy 1, policy_version 256180 (0.0012) -[2023-11-28 06:55:37,430][87426] Updated weights for policy 1, policy_version 256190 (0.0012) -[2023-11-28 06:55:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 131227648. Throughput: 0: 2689.5, 1: 2632.3. Samples: 131244168. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:38,445][86177] Avg episode reward: [(0, '-532.710'), (1, '-524.910')] -[2023-11-28 06:55:38,945][87424] Updated weights for policy 0, policy_version 256418 (0.0010) -[2023-11-28 06:55:39,332][87424] Updated weights for policy 0, policy_version 256428 (0.0010) -[2023-11-28 06:55:39,715][87424] Updated weights for policy 0, policy_version 256438 (0.0012) -[2023-11-28 06:55:39,844][87426] Updated weights for policy 1, policy_version 256200 (0.0010) -[2023-11-28 06:55:40,087][87424] Updated weights for policy 0, policy_version 256448 (0.0010) -[2023-11-28 06:55:40,225][87426] Updated weights for policy 1, policy_version 256210 (0.0011) -[2023-11-28 06:55:40,606][87426] Updated weights for policy 1, policy_version 256220 (0.0012) -[2023-11-28 06:55:42,243][87424] Updated weights for policy 0, policy_version 256458 (0.0010) -[2023-11-28 06:55:42,628][87424] Updated weights for policy 0, policy_version 256468 (0.0010) -[2023-11-28 06:55:42,785][87426] Updated weights for policy 1, policy_version 256230 (0.0011) -[2023-11-28 06:55:42,999][87424] Updated weights for policy 0, policy_version 256478 (0.0009) -[2023-11-28 06:55:43,153][87426] Updated weights for policy 1, policy_version 256240 (0.0009) -[2023-11-28 06:55:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 131252224. Throughput: 0: 2681.4, 1: 2671.3. Samples: 131268808. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:43,446][86177] Avg episode reward: [(0, '-539.820'), (1, '-527.360')] -[2023-11-28 06:55:43,530][87426] Updated weights for policy 1, policy_version 256250 (0.0008) -[2023-11-28 06:55:45,421][87426] Updated weights for policy 1, policy_version 256260 (0.0009) -[2023-11-28 06:55:45,611][87424] Updated weights for policy 0, policy_version 256488 (0.0011) -[2023-11-28 06:55:45,804][87426] Updated weights for policy 1, policy_version 256270 (0.0011) -[2023-11-28 06:55:45,989][87424] Updated weights for policy 0, policy_version 256498 (0.0012) -[2023-11-28 06:55:46,171][87426] Updated weights for policy 1, policy_version 256280 (0.0011) -[2023-11-28 06:55:46,382][87424] Updated weights for policy 0, policy_version 256508 (0.0012) -[2023-11-28 06:55:48,227][87424] Updated weights for policy 0, policy_version 256518 (0.0012) -[2023-11-28 06:55:48,393][87426] Updated weights for policy 1, policy_version 256290 (0.0010) -[2023-11-28 06:55:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 131276800. Throughput: 0: 2634.8, 1: 2680.4. Samples: 131292376. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:48,445][86177] Avg episode reward: [(0, '-539.140'), (1, '-509.700')] -[2023-11-28 06:55:48,612][87424] Updated weights for policy 0, policy_version 256528 (0.0007) -[2023-11-28 06:55:48,762][87426] Updated weights for policy 1, policy_version 256300 (0.0008) -[2023-11-28 06:55:48,996][87424] Updated weights for policy 0, policy_version 256538 (0.0009) -[2023-11-28 06:55:49,148][87426] Updated weights for policy 1, policy_version 256310 (0.0008) -[2023-11-28 06:55:49,525][87426] Updated weights for policy 1, policy_version 256320 (0.0011) -[2023-11-28 06:55:51,019][87424] Updated weights for policy 0, policy_version 256548 (0.0012) -[2023-11-28 06:55:51,391][87424] Updated weights for policy 0, policy_version 256558 (0.0012) -[2023-11-28 06:55:51,514][87426] Updated weights for policy 1, policy_version 256330 (0.0011) -[2023-11-28 06:55:51,770][87424] Updated weights for policy 0, policy_version 256568 (0.0012) -[2023-11-28 06:55:51,883][87426] Updated weights for policy 1, policy_version 256340 (0.0011) -[2023-11-28 06:55:52,266][87426] Updated weights for policy 1, policy_version 256350 (0.0012) -[2023-11-28 06:55:53,446][86177] Fps is (10 sec: 5733.6, 60 sec: 5461.2, 300 sec: 5415.0). Total num frames: 131309568. Throughput: 0: 2655.6, 1: 2658.7. Samples: 131325732. Policy #0 lag: (min: 28.0, avg: 42.3, max: 60.0) -[2023-11-28 06:55:53,447][86177] Avg episode reward: [(0, '-532.860'), (1, '-509.420')] -[2023-11-28 06:55:54,048][87424] Updated weights for policy 0, policy_version 256578 (0.0011) -[2023-11-28 06:55:54,426][87424] Updated weights for policy 0, policy_version 256588 (0.0008) -[2023-11-28 06:55:54,442][87426] Updated weights for policy 1, policy_version 256360 (0.0011) -[2023-11-28 06:55:54,810][87424] Updated weights for policy 0, policy_version 256598 (0.0007) -[2023-11-28 06:55:54,828][87426] Updated weights for policy 1, policy_version 256370 (0.0012) -[2023-11-28 06:55:55,196][87424] Updated weights for policy 0, policy_version 256608 (0.0010) -[2023-11-28 06:55:55,199][87426] Updated weights for policy 1, policy_version 256380 (0.0010) -[2023-11-28 06:55:56,954][87424] Updated weights for policy 0, policy_version 256618 (0.0012) -[2023-11-28 06:55:56,956][87426] Updated weights for policy 1, policy_version 256390 (0.0009) -[2023-11-28 06:55:57,341][87426] Updated weights for policy 1, policy_version 256400 (0.0007) -[2023-11-28 06:55:57,341][87424] Updated weights for policy 0, policy_version 256628 (0.0011) -[2023-11-28 06:55:57,717][87426] Updated weights for policy 1, policy_version 256410 (0.0008) -[2023-11-28 06:55:57,726][87424] Updated weights for policy 0, policy_version 256638 (0.0008) -[2023-11-28 06:55:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131342336. Throughput: 0: 2679.2, 1: 2681.2. Samples: 131351144. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:55:58,445][86177] Avg episode reward: [(0, '-549.380'), (1, '-511.430')] -[2023-11-28 06:55:59,531][87426] Updated weights for policy 1, policy_version 256420 (0.0011) -[2023-11-28 06:55:59,632][87424] Updated weights for policy 0, policy_version 256648 (0.0011) -[2023-11-28 06:55:59,908][87426] Updated weights for policy 1, policy_version 256430 (0.0011) -[2023-11-28 06:56:00,024][87424] Updated weights for policy 0, policy_version 256658 (0.0012) -[2023-11-28 06:56:00,286][87426] Updated weights for policy 1, policy_version 256440 (0.0008) -[2023-11-28 06:56:00,409][87424] Updated weights for policy 0, policy_version 256668 (0.0012) -[2023-11-28 06:56:02,794][87426] Updated weights for policy 1, policy_version 256450 (0.0011) -[2023-11-28 06:56:02,973][87424] Updated weights for policy 0, policy_version 256678 (0.0011) -[2023-11-28 06:56:03,166][87426] Updated weights for policy 1, policy_version 256460 (0.0010) -[2023-11-28 06:56:03,346][87424] Updated weights for policy 0, policy_version 256688 (0.0011) -[2023-11-28 06:56:03,444][86177] Fps is (10 sec: 4915.9, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 131358720. Throughput: 0: 2717.0, 1: 2711.1. Samples: 131378160. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:03,445][86177] Avg episode reward: [(0, '-544.120'), (1, '-511.120')] -[2023-11-28 06:56:03,544][87426] Updated weights for policy 1, policy_version 256470 (0.0011) -[2023-11-28 06:56:03,725][87424] Updated weights for policy 0, policy_version 256698 (0.0010) -[2023-11-28 06:56:03,911][87426] Updated weights for policy 1, policy_version 256480 (0.0011) -[2023-11-28 06:56:05,862][87424] Updated weights for policy 0, policy_version 256708 (0.0009) -[2023-11-28 06:56:05,889][87426] Updated weights for policy 1, policy_version 256490 (0.0009) -[2023-11-28 06:56:06,232][87424] Updated weights for policy 0, policy_version 256718 (0.0012) -[2023-11-28 06:56:06,276][87426] Updated weights for policy 1, policy_version 256500 (0.0012) -[2023-11-28 06:56:06,613][87424] Updated weights for policy 0, policy_version 256728 (0.0011) -[2023-11-28 06:56:06,649][87426] Updated weights for policy 1, policy_version 256510 (0.0011) -[2023-11-28 06:56:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131391488. Throughput: 0: 2711.6, 1: 2745.9. Samples: 131410660. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:08,445][86177] Avg episode reward: [(0, '-540.420'), (1, '-504.090')] -[2023-11-28 06:56:08,792][87424] Updated weights for policy 0, policy_version 256738 (0.0012) -[2023-11-28 06:56:08,887][87426] Updated weights for policy 1, policy_version 256520 (0.0009) -[2023-11-28 06:56:09,164][87424] Updated weights for policy 0, policy_version 256748 (0.0012) -[2023-11-28 06:56:09,262][87426] Updated weights for policy 1, policy_version 256530 (0.0007) -[2023-11-28 06:56:09,550][87424] Updated weights for policy 0, policy_version 256758 (0.0012) -[2023-11-28 06:56:09,642][87426] Updated weights for policy 1, policy_version 256540 (0.0007) -[2023-11-28 06:56:09,927][87424] Updated weights for policy 0, policy_version 256768 (0.0012) -[2023-11-28 06:56:11,788][87424] Updated weights for policy 0, policy_version 256778 (0.0009) -[2023-11-28 06:56:11,960][87426] Updated weights for policy 1, policy_version 256550 (0.0011) -[2023-11-28 06:56:12,161][87424] Updated weights for policy 0, policy_version 256788 (0.0010) -[2023-11-28 06:56:12,337][87426] Updated weights for policy 1, policy_version 256560 (0.0010) -[2023-11-28 06:56:12,542][87424] Updated weights for policy 0, policy_version 256798 (0.0010) -[2023-11-28 06:56:12,724][87426] Updated weights for policy 1, policy_version 256570 (0.0009) -[2023-11-28 06:56:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131424256. Throughput: 0: 2726.2, 1: 2722.4. Samples: 131435668. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:13,445][86177] Avg episode reward: [(0, '-542.110'), (1, '-504.770')] -[2023-11-28 06:56:14,277][87424] Updated weights for policy 0, policy_version 256808 (0.0008) -[2023-11-28 06:56:14,653][87424] Updated weights for policy 0, policy_version 256818 (0.0008) -[2023-11-28 06:56:14,785][87426] Updated weights for policy 1, policy_version 256580 (0.0010) -[2023-11-28 06:56:15,039][87424] Updated weights for policy 0, policy_version 256828 (0.0012) -[2023-11-28 06:56:15,166][87426] Updated weights for policy 1, policy_version 256590 (0.0008) -[2023-11-28 06:56:15,538][87426] Updated weights for policy 1, policy_version 256600 (0.0008) -[2023-11-28 06:56:16,814][87424] Updated weights for policy 0, policy_version 256838 (0.0011) -[2023-11-28 06:56:17,198][87424] Updated weights for policy 0, policy_version 256848 (0.0008) -[2023-11-28 06:56:17,581][87424] Updated weights for policy 0, policy_version 256858 (0.0008) -[2023-11-28 06:56:17,609][87426] Updated weights for policy 1, policy_version 256610 (0.0009) -[2023-11-28 06:56:17,985][87426] Updated weights for policy 1, policy_version 256620 (0.0010) -[2023-11-28 06:56:18,367][87426] Updated weights for policy 1, policy_version 256630 (0.0007) -[2023-11-28 06:56:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131448832. Throughput: 0: 2748.6, 1: 2751.0. Samples: 131460848. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:18,446][86177] Avg episode reward: [(0, '-536.610'), (1, '-510.780')] -[2023-11-28 06:56:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000256864_65757184.pth... -[2023-11-28 06:56:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000254304_65101824.pth -[2023-11-28 06:56:18,739][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000256640_65699840.pth... -[2023-11-28 06:56:18,740][87426] Updated weights for policy 1, policy_version 256640 (0.0007) -[2023-11-28 06:56:18,770][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000254112_65052672.pth -[2023-11-28 06:56:20,051][87424] Updated weights for policy 0, policy_version 256868 (0.0009) -[2023-11-28 06:56:20,438][87424] Updated weights for policy 0, policy_version 256878 (0.0011) -[2023-11-28 06:56:20,812][87424] Updated weights for policy 0, policy_version 256888 (0.0011) -[2023-11-28 06:56:21,264][87426] Updated weights for policy 1, policy_version 256650 (0.0011) -[2023-11-28 06:56:21,644][87426] Updated weights for policy 1, policy_version 256660 (0.0011) -[2023-11-28 06:56:22,030][87426] Updated weights for policy 1, policy_version 256670 (0.0011) -[2023-11-28 06:56:22,828][87424] Updated weights for policy 0, policy_version 256898 (0.0011) -[2023-11-28 06:56:23,200][87424] Updated weights for policy 0, policy_version 256908 (0.0010) -[2023-11-28 06:56:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 131473408. Throughput: 0: 2775.3, 1: 2745.1. Samples: 131492584. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:23,445][86177] Avg episode reward: [(0, '-538.000'), (1, '-512.580')] -[2023-11-28 06:56:23,581][87424] Updated weights for policy 0, policy_version 256918 (0.0007) -[2023-11-28 06:56:23,964][87424] Updated weights for policy 0, policy_version 256928 (0.0007) -[2023-11-28 06:56:24,227][87426] Updated weights for policy 1, policy_version 256680 (0.0008) -[2023-11-28 06:56:24,604][87426] Updated weights for policy 1, policy_version 256690 (0.0009) -[2023-11-28 06:56:24,988][87426] Updated weights for policy 1, policy_version 256700 (0.0009) -[2023-11-28 06:56:26,456][87424] Updated weights for policy 0, policy_version 256938 (0.0011) -[2023-11-28 06:56:26,836][87424] Updated weights for policy 0, policy_version 256948 (0.0011) -[2023-11-28 06:56:27,138][87426] Updated weights for policy 1, policy_version 256710 (0.0009) -[2023-11-28 06:56:27,215][87424] Updated weights for policy 0, policy_version 256958 (0.0010) -[2023-11-28 06:56:27,529][87426] Updated weights for policy 1, policy_version 256720 (0.0012) -[2023-11-28 06:56:27,901][87426] Updated weights for policy 1, policy_version 256730 (0.0012) -[2023-11-28 06:56:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 131506176. Throughput: 0: 2784.3, 1: 2732.9. Samples: 131517080. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:28,445][86177] Avg episode reward: [(0, '-538.690'), (1, '-510.930')] -[2023-11-28 06:56:28,940][87424] Updated weights for policy 0, policy_version 256968 (0.0008) -[2023-11-28 06:56:29,312][87424] Updated weights for policy 0, policy_version 256978 (0.0007) -[2023-11-28 06:56:29,689][87424] Updated weights for policy 0, policy_version 256988 (0.0007) -[2023-11-28 06:56:30,440][87426] Updated weights for policy 1, policy_version 256740 (0.0012) -[2023-11-28 06:56:30,812][87426] Updated weights for policy 1, policy_version 256750 (0.0012) -[2023-11-28 06:56:31,175][87426] Updated weights for policy 1, policy_version 256760 (0.0012) -[2023-11-28 06:56:31,869][87424] Updated weights for policy 0, policy_version 256998 (0.0010) -[2023-11-28 06:56:32,248][87424] Updated weights for policy 0, policy_version 257008 (0.0012) -[2023-11-28 06:56:32,638][87424] Updated weights for policy 0, policy_version 257018 (0.0011) -[2023-11-28 06:56:32,991][87426] Updated weights for policy 1, policy_version 256770 (0.0011) -[2023-11-28 06:56:33,384][87426] Updated weights for policy 1, policy_version 256780 (0.0008) -[2023-11-28 06:56:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131530752. Throughput: 0: 2838.8, 1: 2727.3. Samples: 131542848. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:33,445][86177] Avg episode reward: [(0, '-534.780'), (1, '-511.080')] -[2023-11-28 06:56:33,757][87426] Updated weights for policy 1, policy_version 256790 (0.0007) -[2023-11-28 06:56:34,145][87426] Updated weights for policy 1, policy_version 256800 (0.0008) -[2023-11-28 06:56:34,762][87424] Updated weights for policy 0, policy_version 257028 (0.0011) -[2023-11-28 06:56:35,144][87424] Updated weights for policy 0, policy_version 257038 (0.0009) -[2023-11-28 06:56:35,531][87424] Updated weights for policy 0, policy_version 257048 (0.0008) -[2023-11-28 06:56:35,978][87426] Updated weights for policy 1, policy_version 256810 (0.0012) -[2023-11-28 06:56:36,353][87426] Updated weights for policy 1, policy_version 256820 (0.0010) -[2023-11-28 06:56:36,739][87426] Updated weights for policy 1, policy_version 256830 (0.0008) -[2023-11-28 06:56:37,118][87424] Updated weights for policy 0, policy_version 257058 (0.0008) -[2023-11-28 06:56:37,500][87424] Updated weights for policy 0, policy_version 257068 (0.0010) -[2023-11-28 06:56:37,882][87424] Updated weights for policy 0, policy_version 257078 (0.0010) -[2023-11-28 06:56:38,271][87424] Updated weights for policy 0, policy_version 257088 (0.0011) -[2023-11-28 06:56:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 131563520. Throughput: 0: 2836.9, 1: 2747.1. Samples: 131577004. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:38,445][86177] Avg episode reward: [(0, '-532.060'), (1, '-502.680')] -[2023-11-28 06:56:38,980][87426] Updated weights for policy 1, policy_version 256840 (0.0009) -[2023-11-28 06:56:39,364][87426] Updated weights for policy 1, policy_version 256850 (0.0009) -[2023-11-28 06:56:39,755][87426] Updated weights for policy 1, policy_version 256860 (0.0008) -[2023-11-28 06:56:40,423][87424] Updated weights for policy 0, policy_version 257098 (0.0011) -[2023-11-28 06:56:40,802][87424] Updated weights for policy 0, policy_version 257108 (0.0011) -[2023-11-28 06:56:41,190][87424] Updated weights for policy 0, policy_version 257118 (0.0011) -[2023-11-28 06:56:41,805][87426] Updated weights for policy 1, policy_version 256870 (0.0010) -[2023-11-28 06:56:42,174][87426] Updated weights for policy 1, policy_version 256880 (0.0011) -[2023-11-28 06:56:42,552][87426] Updated weights for policy 1, policy_version 256890 (0.0010) -[2023-11-28 06:56:43,389][87424] Updated weights for policy 0, policy_version 257128 (0.0011) -[2023-11-28 06:56:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 131588096. Throughput: 0: 2813.1, 1: 2731.8. Samples: 131600664. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:43,446][86177] Avg episode reward: [(0, '-540.910'), (1, '-503.570')] -[2023-11-28 06:56:43,768][87424] Updated weights for policy 0, policy_version 257138 (0.0012) -[2023-11-28 06:56:44,154][87424] Updated weights for policy 0, policy_version 257148 (0.0012) -[2023-11-28 06:56:44,458][87426] Updated weights for policy 1, policy_version 256900 (0.0011) -[2023-11-28 06:56:44,832][87426] Updated weights for policy 1, policy_version 256910 (0.0011) -[2023-11-28 06:56:45,216][87426] Updated weights for policy 1, policy_version 256920 (0.0011) -[2023-11-28 06:56:46,607][87424] Updated weights for policy 0, policy_version 257158 (0.0011) -[2023-11-28 06:56:46,992][87424] Updated weights for policy 0, policy_version 257168 (0.0012) -[2023-11-28 06:56:47,379][87424] Updated weights for policy 0, policy_version 257178 (0.0010) -[2023-11-28 06:56:47,487][87426] Updated weights for policy 1, policy_version 256930 (0.0009) -[2023-11-28 06:56:47,873][87426] Updated weights for policy 1, policy_version 256940 (0.0011) -[2023-11-28 06:56:48,249][87426] Updated weights for policy 1, policy_version 256950 (0.0012) -[2023-11-28 06:56:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 131612672. Throughput: 0: 2789.5, 1: 2718.7. Samples: 131626028. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:48,446][86177] Avg episode reward: [(0, '-545.850'), (1, '-508.200')] -[2023-11-28 06:56:48,626][87426] Updated weights for policy 1, policy_version 256960 (0.0012) -[2023-11-28 06:56:49,873][87424] Updated weights for policy 0, policy_version 257188 (0.0011) -[2023-11-28 06:56:50,247][87424] Updated weights for policy 0, policy_version 257198 (0.0012) -[2023-11-28 06:56:50,622][87424] Updated weights for policy 0, policy_version 257208 (0.0012) -[2023-11-28 06:56:51,199][87426] Updated weights for policy 1, policy_version 256970 (0.0012) -[2023-11-28 06:56:51,582][87426] Updated weights for policy 1, policy_version 256980 (0.0012) -[2023-11-28 06:56:51,965][87426] Updated weights for policy 1, policy_version 256990 (0.0012) -[2023-11-28 06:56:52,962][87424] Updated weights for policy 0, policy_version 257218 (0.0012) -[2023-11-28 06:56:53,338][87424] Updated weights for policy 0, policy_version 257228 (0.0012) -[2023-11-28 06:56:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.5, 300 sec: 5415.0). Total num frames: 131637248. Throughput: 0: 2805.3, 1: 2703.9. Samples: 131658576. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:53,445][86177] Avg episode reward: [(0, '-545.210'), (1, '-513.330')] -[2023-11-28 06:56:53,730][87424] Updated weights for policy 0, policy_version 257238 (0.0011) -[2023-11-28 06:56:54,110][87424] Updated weights for policy 0, policy_version 257248 (0.0012) -[2023-11-28 06:56:54,396][87426] Updated weights for policy 1, policy_version 257000 (0.0012) -[2023-11-28 06:56:54,791][87426] Updated weights for policy 1, policy_version 257010 (0.0012) -[2023-11-28 06:56:55,163][87426] Updated weights for policy 1, policy_version 257020 (0.0012) -[2023-11-28 06:56:55,792][87424] Updated weights for policy 0, policy_version 257258 (0.0009) -[2023-11-28 06:56:56,170][87424] Updated weights for policy 0, policy_version 257268 (0.0012) -[2023-11-28 06:56:56,545][87424] Updated weights for policy 0, policy_version 257278 (0.0012) -[2023-11-28 06:56:56,915][87426] Updated weights for policy 1, policy_version 257030 (0.0012) -[2023-11-28 06:56:57,285][87426] Updated weights for policy 1, policy_version 257040 (0.0009) -[2023-11-28 06:56:57,666][87426] Updated weights for policy 1, policy_version 257050 (0.0007) -[2023-11-28 06:56:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131670016. Throughput: 0: 2788.9, 1: 2707.9. Samples: 131683024. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:56:58,445][86177] Avg episode reward: [(0, '-539.210'), (1, '-515.520')] -[2023-11-28 06:56:58,699][87424] Updated weights for policy 0, policy_version 257288 (0.0011) -[2023-11-28 06:56:59,083][87424] Updated weights for policy 0, policy_version 257298 (0.0011) -[2023-11-28 06:56:59,468][87424] Updated weights for policy 0, policy_version 257308 (0.0012) -[2023-11-28 06:56:59,838][87426] Updated weights for policy 1, policy_version 257060 (0.0009) -[2023-11-28 06:57:00,208][87426] Updated weights for policy 1, policy_version 257070 (0.0012) -[2023-11-28 06:57:00,590][87426] Updated weights for policy 1, policy_version 257080 (0.0012) -[2023-11-28 06:57:01,340][87424] Updated weights for policy 0, policy_version 257318 (0.0012) -[2023-11-28 06:57:01,718][87424] Updated weights for policy 0, policy_version 257328 (0.0010) -[2023-11-28 06:57:02,102][87424] Updated weights for policy 0, policy_version 257338 (0.0008) -[2023-11-28 06:57:02,921][87426] Updated weights for policy 1, policy_version 257090 (0.0012) -[2023-11-28 06:57:03,302][87426] Updated weights for policy 1, policy_version 257100 (0.0010) -[2023-11-28 06:57:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 131694592. Throughput: 0: 2780.5, 1: 2706.9. Samples: 131707776. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:57:03,445][86177] Avg episode reward: [(0, '-538.510'), (1, '-513.830')] -[2023-11-28 06:57:03,680][87426] Updated weights for policy 1, policy_version 257110 (0.0007) -[2023-11-28 06:57:04,060][87426] Updated weights for policy 1, policy_version 257120 (0.0007) -[2023-11-28 06:57:04,289][87424] Updated weights for policy 0, policy_version 257348 (0.0009) -[2023-11-28 06:57:04,669][87424] Updated weights for policy 0, policy_version 257358 (0.0008) -[2023-11-28 06:57:05,057][87424] Updated weights for policy 0, policy_version 257368 (0.0011) -[2023-11-28 06:57:06,308][87426] Updated weights for policy 1, policy_version 257130 (0.0011) -[2023-11-28 06:57:06,686][87426] Updated weights for policy 1, policy_version 257140 (0.0012) -[2023-11-28 06:57:07,073][87426] Updated weights for policy 1, policy_version 257150 (0.0011) -[2023-11-28 06:57:07,540][87424] Updated weights for policy 0, policy_version 257378 (0.0011) -[2023-11-28 06:57:07,923][87424] Updated weights for policy 0, policy_version 257388 (0.0011) -[2023-11-28 06:57:08,302][87424] Updated weights for policy 0, policy_version 257398 (0.0011) -[2023-11-28 06:57:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131719168. Throughput: 0: 2767.8, 1: 2714.0. Samples: 131739268. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 06:57:08,445][86177] Avg episode reward: [(0, '-566.730'), (1, '-508.570')] -[2023-11-28 06:57:08,684][87424] Updated weights for policy 0, policy_version 257408 (0.0008) -[2023-11-28 06:57:09,291][87426] Updated weights for policy 1, policy_version 257160 (0.0011) -[2023-11-28 06:57:09,673][87426] Updated weights for policy 1, policy_version 257170 (0.0012) -[2023-11-28 06:57:10,055][87426] Updated weights for policy 1, policy_version 257180 (0.0018) -[2023-11-28 06:57:11,083][87424] Updated weights for policy 0, policy_version 257418 (0.0010) -[2023-11-28 06:57:11,460][87424] Updated weights for policy 0, policy_version 257428 (0.0009) -[2023-11-28 06:57:11,841][87424] Updated weights for policy 0, policy_version 257438 (0.0009) -[2023-11-28 06:57:11,972][87426] Updated weights for policy 1, policy_version 257190 (0.0011) -[2023-11-28 06:57:12,345][87426] Updated weights for policy 1, policy_version 257200 (0.0012) -[2023-11-28 06:57:12,727][87426] Updated weights for policy 1, policy_version 257210 (0.0012) -[2023-11-28 06:57:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131751936. Throughput: 0: 2757.8, 1: 2705.7. Samples: 131762936. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:13,445][86177] Avg episode reward: [(0, '-566.070'), (1, '-515.240')] -[2023-11-28 06:57:13,785][87424] Updated weights for policy 0, policy_version 257448 (0.0011) -[2023-11-28 06:57:14,185][87424] Updated weights for policy 0, policy_version 257458 (0.0012) -[2023-11-28 06:57:14,565][87424] Updated weights for policy 0, policy_version 257468 (0.0012) -[2023-11-28 06:57:15,067][87426] Updated weights for policy 1, policy_version 257220 (0.0012) -[2023-11-28 06:57:15,456][87426] Updated weights for policy 1, policy_version 257230 (0.0012) -[2023-11-28 06:57:15,827][87426] Updated weights for policy 1, policy_version 257240 (0.0011) -[2023-11-28 06:57:16,322][87424] Updated weights for policy 0, policy_version 257478 (0.0009) -[2023-11-28 06:57:16,710][87424] Updated weights for policy 0, policy_version 257488 (0.0009) -[2023-11-28 06:57:17,095][87424] Updated weights for policy 0, policy_version 257498 (0.0011) -[2023-11-28 06:57:18,000][87426] Updated weights for policy 1, policy_version 257250 (0.0012) -[2023-11-28 06:57:18,381][87426] Updated weights for policy 1, policy_version 257260 (0.0012) -[2023-11-28 06:57:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 131776512. Throughput: 0: 2725.9, 1: 2709.2. Samples: 131787424. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:18,445][86177] Avg episode reward: [(0, '-562.140'), (1, '-520.910')] -[2023-11-28 06:57:18,771][87426] Updated weights for policy 1, policy_version 257270 (0.0011) -[2023-11-28 06:57:19,143][87426] Updated weights for policy 1, policy_version 257280 (0.0011) -[2023-11-28 06:57:19,566][87424] Updated weights for policy 0, policy_version 257508 (0.0011) -[2023-11-28 06:57:19,956][87424] Updated weights for policy 0, policy_version 257518 (0.0011) -[2023-11-28 06:57:20,340][87424] Updated weights for policy 0, policy_version 257528 (0.0011) -[2023-11-28 06:57:21,221][87426] Updated weights for policy 1, policy_version 257290 (0.0010) -[2023-11-28 06:57:21,591][87426] Updated weights for policy 1, policy_version 257300 (0.0008) -[2023-11-28 06:57:21,976][87426] Updated weights for policy 1, policy_version 257310 (0.0015) -[2023-11-28 06:57:22,388][87424] Updated weights for policy 0, policy_version 257538 (0.0010) -[2023-11-28 06:57:22,762][87424] Updated weights for policy 0, policy_version 257548 (0.0012) -[2023-11-28 06:57:23,146][87424] Updated weights for policy 0, policy_version 257558 (0.0012) -[2023-11-28 06:57:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131801088. Throughput: 0: 2693.2, 1: 2710.1. Samples: 131820156. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:23,445][86177] Avg episode reward: [(0, '-563.070'), (1, '-517.760')] -[2023-11-28 06:57:23,516][87424] Updated weights for policy 0, policy_version 257568 (0.0012) -[2023-11-28 06:57:23,978][87426] Updated weights for policy 1, policy_version 257320 (0.0012) -[2023-11-28 06:57:24,361][87426] Updated weights for policy 1, policy_version 257330 (0.0012) -[2023-11-28 06:57:24,749][87426] Updated weights for policy 1, policy_version 257340 (0.0012) -[2023-11-28 06:57:26,093][87424] Updated weights for policy 0, policy_version 257578 (0.0007) -[2023-11-28 06:57:26,471][87424] Updated weights for policy 0, policy_version 257588 (0.0007) -[2023-11-28 06:57:26,850][87424] Updated weights for policy 0, policy_version 257598 (0.0007) -[2023-11-28 06:57:27,258][87426] Updated weights for policy 1, policy_version 257350 (0.0010) -[2023-11-28 06:57:27,634][87426] Updated weights for policy 1, policy_version 257360 (0.0007) -[2023-11-28 06:57:28,009][87426] Updated weights for policy 1, policy_version 257370 (0.0007) -[2023-11-28 06:57:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 131833856. Throughput: 0: 2728.0, 1: 2714.8. Samples: 131845588. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:28,445][86177] Avg episode reward: [(0, '-558.410'), (1, '-521.910')] -[2023-11-28 06:57:28,490][87424] Updated weights for policy 0, policy_version 257608 (0.0008) -[2023-11-28 06:57:28,874][87424] Updated weights for policy 0, policy_version 257618 (0.0008) -[2023-11-28 06:57:29,257][87424] Updated weights for policy 0, policy_version 257628 (0.0007) -[2023-11-28 06:57:30,213][87426] Updated weights for policy 1, policy_version 257380 (0.0009) -[2023-11-28 06:57:30,590][87426] Updated weights for policy 1, policy_version 257390 (0.0012) -[2023-11-28 06:57:30,966][87426] Updated weights for policy 1, policy_version 257400 (0.0012) -[2023-11-28 06:57:31,407][87424] Updated weights for policy 0, policy_version 257638 (0.0010) -[2023-11-28 06:57:31,784][87424] Updated weights for policy 0, policy_version 257648 (0.0012) -[2023-11-28 06:57:32,171][87424] Updated weights for policy 0, policy_version 257658 (0.0012) -[2023-11-28 06:57:33,174][87426] Updated weights for policy 1, policy_version 257410 (0.0012) -[2023-11-28 06:57:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131858432. Throughput: 0: 2727.0, 1: 2699.2. Samples: 131870208. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:33,445][86177] Avg episode reward: [(0, '-547.950'), (1, '-518.670')] -[2023-11-28 06:57:33,546][87426] Updated weights for policy 1, policy_version 257420 (0.0012) -[2023-11-28 06:57:33,929][87426] Updated weights for policy 1, policy_version 257430 (0.0012) -[2023-11-28 06:57:34,310][87426] Updated weights for policy 1, policy_version 257440 (0.0010) -[2023-11-28 06:57:34,342][87424] Updated weights for policy 0, policy_version 257668 (0.0011) -[2023-11-28 06:57:34,732][87424] Updated weights for policy 0, policy_version 257678 (0.0008) -[2023-11-28 06:57:35,105][87424] Updated weights for policy 0, policy_version 257688 (0.0012) -[2023-11-28 06:57:36,472][87426] Updated weights for policy 1, policy_version 257450 (0.0011) -[2023-11-28 06:57:36,758][87424] Updated weights for policy 0, policy_version 257698 (0.0011) -[2023-11-28 06:57:36,843][87426] Updated weights for policy 1, policy_version 257460 (0.0012) -[2023-11-28 06:57:37,139][87424] Updated weights for policy 0, policy_version 257708 (0.0010) -[2023-11-28 06:57:37,219][87426] Updated weights for policy 1, policy_version 257470 (0.0012) -[2023-11-28 06:57:37,521][87424] Updated weights for policy 0, policy_version 257718 (0.0009) -[2023-11-28 06:57:37,912][87424] Updated weights for policy 0, policy_version 257728 (0.0007) -[2023-11-28 06:57:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 131891200. Throughput: 0: 2756.0, 1: 2714.7. Samples: 131904760. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:38,445][86177] Avg episode reward: [(0, '-547.510'), (1, '-513.960')] -[2023-11-28 06:57:39,152][87426] Updated weights for policy 1, policy_version 257480 (0.0011) -[2023-11-28 06:57:39,525][87426] Updated weights for policy 1, policy_version 257490 (0.0012) -[2023-11-28 06:57:39,655][87424] Updated weights for policy 0, policy_version 257738 (0.0009) -[2023-11-28 06:57:39,898][87426] Updated weights for policy 1, policy_version 257500 (0.0012) -[2023-11-28 06:57:40,036][87424] Updated weights for policy 0, policy_version 257748 (0.0010) -[2023-11-28 06:57:40,415][87424] Updated weights for policy 0, policy_version 257758 (0.0009) -[2023-11-28 06:57:42,202][87426] Updated weights for policy 1, policy_version 257510 (0.0011) -[2023-11-28 06:57:42,591][87426] Updated weights for policy 1, policy_version 257520 (0.0010) -[2023-11-28 06:57:42,790][87424] Updated weights for policy 0, policy_version 257768 (0.0011) -[2023-11-28 06:57:42,966][87426] Updated weights for policy 1, policy_version 257530 (0.0010) -[2023-11-28 06:57:43,170][87424] Updated weights for policy 0, policy_version 257778 (0.0012) -[2023-11-28 06:57:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 131915776. Throughput: 0: 2755.3, 1: 2728.8. Samples: 131929808. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:43,445][86177] Avg episode reward: [(0, '-549.610'), (1, '-513.690')] -[2023-11-28 06:57:43,546][87424] Updated weights for policy 0, policy_version 257788 (0.0012) -[2023-11-28 06:57:44,710][87426] Updated weights for policy 1, policy_version 257540 (0.0011) -[2023-11-28 06:57:45,096][87426] Updated weights for policy 1, policy_version 257550 (0.0012) -[2023-11-28 06:57:45,467][87426] Updated weights for policy 1, policy_version 257560 (0.0012) -[2023-11-28 06:57:45,945][87424] Updated weights for policy 0, policy_version 257798 (0.0012) -[2023-11-28 06:57:46,319][87424] Updated weights for policy 0, policy_version 257808 (0.0012) -[2023-11-28 06:57:46,704][87424] Updated weights for policy 0, policy_version 257818 (0.0012) -[2023-11-28 06:57:47,730][87426] Updated weights for policy 1, policy_version 257570 (0.0011) -[2023-11-28 06:57:48,110][87426] Updated weights for policy 1, policy_version 257580 (0.0010) -[2023-11-28 06:57:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 131940352. Throughput: 0: 2738.3, 1: 2738.6. Samples: 131954236. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:48,445][86177] Avg episode reward: [(0, '-542.590'), (1, '-544.230')] -[2023-11-28 06:57:48,495][87426] Updated weights for policy 1, policy_version 257590 (0.0008) -[2023-11-28 06:57:48,876][87426] Updated weights for policy 1, policy_version 257600 (0.0008) -[2023-11-28 06:57:49,207][87424] Updated weights for policy 0, policy_version 257828 (0.0011) -[2023-11-28 06:57:49,586][87424] Updated weights for policy 0, policy_version 257838 (0.0010) -[2023-11-28 06:57:49,976][87424] Updated weights for policy 0, policy_version 257848 (0.0009) -[2023-11-28 06:57:51,319][87426] Updated weights for policy 1, policy_version 257610 (0.0008) -[2023-11-28 06:57:51,710][87426] Updated weights for policy 1, policy_version 257620 (0.0008) -[2023-11-28 06:57:52,078][87426] Updated weights for policy 1, policy_version 257630 (0.0009) -[2023-11-28 06:57:52,470][87424] Updated weights for policy 0, policy_version 257858 (0.0010) -[2023-11-28 06:57:52,843][87424] Updated weights for policy 0, policy_version 257868 (0.0009) -[2023-11-28 06:57:53,221][87424] Updated weights for policy 0, policy_version 257878 (0.0009) -[2023-11-28 06:57:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 131964928. Throughput: 0: 2746.1, 1: 2759.6. Samples: 131987024. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:53,445][86177] Avg episode reward: [(0, '-529.170'), (1, '-543.340')] -[2023-11-28 06:57:53,607][87424] Updated weights for policy 0, policy_version 257888 (0.0010) -[2023-11-28 06:57:54,313][87426] Updated weights for policy 1, policy_version 257640 (0.0010) -[2023-11-28 06:57:54,692][87426] Updated weights for policy 1, policy_version 257650 (0.0007) -[2023-11-28 06:57:55,068][87426] Updated weights for policy 1, policy_version 257660 (0.0007) -[2023-11-28 06:57:55,950][87424] Updated weights for policy 0, policy_version 257898 (0.0007) -[2023-11-28 06:57:56,342][87424] Updated weights for policy 0, policy_version 257908 (0.0008) -[2023-11-28 06:57:56,712][87424] Updated weights for policy 0, policy_version 257918 (0.0007) -[2023-11-28 06:57:57,501][87426] Updated weights for policy 1, policy_version 257670 (0.0007) -[2023-11-28 06:57:57,875][87426] Updated weights for policy 1, policy_version 257680 (0.0007) -[2023-11-28 06:57:58,260][87426] Updated weights for policy 1, policy_version 257690 (0.0007) -[2023-11-28 06:57:58,383][87424] Updated weights for policy 0, policy_version 257928 (0.0008) -[2023-11-28 06:57:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 131989504. Throughput: 0: 2762.6, 1: 2751.4. Samples: 132011064. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:57:58,445][86177] Avg episode reward: [(0, '-513.700'), (1, '-555.710')] -[2023-11-28 06:57:58,765][87424] Updated weights for policy 0, policy_version 257938 (0.0007) -[2023-11-28 06:57:59,149][87424] Updated weights for policy 0, policy_version 257948 (0.0010) -[2023-11-28 06:58:00,418][87426] Updated weights for policy 1, policy_version 257700 (0.0009) -[2023-11-28 06:58:00,799][87426] Updated weights for policy 1, policy_version 257710 (0.0011) -[2023-11-28 06:58:01,184][87426] Updated weights for policy 1, policy_version 257720 (0.0012) -[2023-11-28 06:58:01,499][87424] Updated weights for policy 0, policy_version 257958 (0.0011) -[2023-11-28 06:58:01,885][87424] Updated weights for policy 0, policy_version 257968 (0.0011) -[2023-11-28 06:58:02,260][87424] Updated weights for policy 0, policy_version 257978 (0.0012) -[2023-11-28 06:58:03,240][87426] Updated weights for policy 1, policy_version 257730 (0.0011) -[2023-11-28 06:58:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 132022272. Throughput: 0: 2772.0, 1: 2743.9. Samples: 132035640. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:58:03,445][86177] Avg episode reward: [(0, '-553.280'), (1, '-549.000')] -[2023-11-28 06:58:03,612][87426] Updated weights for policy 1, policy_version 257740 (0.0012) -[2023-11-28 06:58:03,994][87426] Updated weights for policy 1, policy_version 257750 (0.0012) -[2023-11-28 06:58:04,372][87426] Updated weights for policy 1, policy_version 257760 (0.0012) -[2023-11-28 06:58:04,504][87424] Updated weights for policy 0, policy_version 257988 (0.0011) -[2023-11-28 06:58:04,878][87424] Updated weights for policy 0, policy_version 257998 (0.0009) -[2023-11-28 06:58:05,275][87424] Updated weights for policy 0, policy_version 258008 (0.0010) -[2023-11-28 06:58:06,482][87426] Updated weights for policy 1, policy_version 257770 (0.0008) -[2023-11-28 06:58:06,855][87426] Updated weights for policy 1, policy_version 257780 (0.0010) -[2023-11-28 06:58:07,074][87424] Updated weights for policy 0, policy_version 258018 (0.0008) -[2023-11-28 06:58:07,232][87426] Updated weights for policy 1, policy_version 257790 (0.0012) -[2023-11-28 06:58:07,458][87424] Updated weights for policy 0, policy_version 258028 (0.0011) -[2023-11-28 06:58:07,835][87424] Updated weights for policy 0, policy_version 258038 (0.0012) -[2023-11-28 06:58:08,215][87424] Updated weights for policy 0, policy_version 258048 (0.0012) -[2023-11-28 06:58:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 132055040. Throughput: 0: 2783.7, 1: 2734.6. Samples: 132068476. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:58:08,445][86177] Avg episode reward: [(0, '-560.720'), (1, '-526.450')] -[2023-11-28 06:58:09,558][87426] Updated weights for policy 1, policy_version 257800 (0.0011) -[2023-11-28 06:58:09,938][87426] Updated weights for policy 1, policy_version 257810 (0.0011) -[2023-11-28 06:58:09,954][87424] Updated weights for policy 0, policy_version 258058 (0.0011) -[2023-11-28 06:58:10,318][87426] Updated weights for policy 1, policy_version 257820 (0.0012) -[2023-11-28 06:58:10,340][87424] Updated weights for policy 0, policy_version 258068 (0.0009) -[2023-11-28 06:58:10,714][87424] Updated weights for policy 0, policy_version 258078 (0.0012) -[2023-11-28 06:58:12,389][87426] Updated weights for policy 1, policy_version 257830 (0.0011) -[2023-11-28 06:58:12,766][87426] Updated weights for policy 1, policy_version 257840 (0.0011) -[2023-11-28 06:58:12,823][87424] Updated weights for policy 0, policy_version 258088 (0.0011) -[2023-11-28 06:58:13,146][87426] Updated weights for policy 1, policy_version 257850 (0.0011) -[2023-11-28 06:58:13,198][87424] Updated weights for policy 0, policy_version 258098 (0.0009) -[2023-11-28 06:58:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 132079616. Throughput: 0: 2766.5, 1: 2744.7. Samples: 132093592. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:58:13,445][86177] Avg episode reward: [(0, '-579.840'), (1, '-526.720')] -[2023-11-28 06:58:13,576][87424] Updated weights for policy 0, policy_version 258108 (0.0008) -[2023-11-28 06:58:14,989][87426] Updated weights for policy 1, policy_version 257860 (0.0012) -[2023-11-28 06:58:15,374][87426] Updated weights for policy 1, policy_version 257870 (0.0009) -[2023-11-28 06:58:15,748][87426] Updated weights for policy 1, policy_version 257880 (0.0012) -[2023-11-28 06:58:15,956][87424] Updated weights for policy 0, policy_version 258118 (0.0008) -[2023-11-28 06:58:16,340][87424] Updated weights for policy 0, policy_version 258128 (0.0007) -[2023-11-28 06:58:16,717][87424] Updated weights for policy 0, policy_version 258138 (0.0007) -[2023-11-28 06:58:18,210][87426] Updated weights for policy 1, policy_version 257890 (0.0009) -[2023-11-28 06:58:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 132104192. Throughput: 0: 2751.5, 1: 2762.4. Samples: 132118336. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 06:58:18,445][86177] Avg episode reward: [(0, '-586.530'), (1, '-511.390')] -[2023-11-28 06:58:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000258144_66084864.pth... -[2023-11-28 06:58:18,502][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000255584_65429504.pth -[2023-11-28 06:58:18,590][87426] Updated weights for policy 1, policy_version 257900 (0.0009) -[2023-11-28 06:58:18,971][87426] Updated weights for policy 1, policy_version 257910 (0.0008) -[2023-11-28 06:58:19,080][87424] Updated weights for policy 0, policy_version 258148 (0.0009) -[2023-11-28 06:58:19,354][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000257920_66027520.pth... -[2023-11-28 06:58:19,357][87426] Updated weights for policy 1, policy_version 257920 (0.0009) -[2023-11-28 06:58:19,384][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000255360_65372160.pth -[2023-11-28 06:58:19,459][87424] Updated weights for policy 0, policy_version 258158 (0.0011) -[2023-11-28 06:58:19,855][87424] Updated weights for policy 0, policy_version 258168 (0.0012) -[2023-11-28 06:58:21,887][87426] Updated weights for policy 1, policy_version 257930 (0.0012) -[2023-11-28 06:58:22,133][87424] Updated weights for policy 0, policy_version 258178 (0.0011) -[2023-11-28 06:58:22,276][87426] Updated weights for policy 1, policy_version 257940 (0.0011) -[2023-11-28 06:58:22,513][87424] Updated weights for policy 0, policy_version 258188 (0.0019) -[2023-11-28 06:58:22,644][87426] Updated weights for policy 1, policy_version 257950 (0.0010) -[2023-11-28 06:58:22,902][87424] Updated weights for policy 0, policy_version 258198 (0.0012) -[2023-11-28 06:58:23,268][87424] Updated weights for policy 0, policy_version 258208 (0.0012) -[2023-11-28 06:58:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 132136960. Throughput: 0: 2713.0, 1: 2719.5. Samples: 132149220. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:58:23,445][86177] Avg episode reward: [(0, '-588.880'), (1, '-504.370')] -[2023-11-28 06:58:25,220][87424] Updated weights for policy 0, policy_version 258218 (0.0009) -[2023-11-28 06:58:25,277][87426] Updated weights for policy 1, policy_version 257960 (0.0012) -[2023-11-28 06:58:25,602][87424] Updated weights for policy 0, policy_version 258228 (0.0008) -[2023-11-28 06:58:25,654][87426] Updated weights for policy 1, policy_version 257970 (0.0009) -[2023-11-28 06:58:25,986][87424] Updated weights for policy 0, policy_version 258238 (0.0010) -[2023-11-28 06:58:26,033][87426] Updated weights for policy 1, policy_version 257980 (0.0010) -[2023-11-28 06:58:27,814][87426] Updated weights for policy 1, policy_version 257990 (0.0010) -[2023-11-28 06:58:27,952][87424] Updated weights for policy 0, policy_version 258248 (0.0009) -[2023-11-28 06:58:28,186][87426] Updated weights for policy 1, policy_version 258000 (0.0009) -[2023-11-28 06:58:28,333][87424] Updated weights for policy 0, policy_version 258258 (0.0007) -[2023-11-28 06:58:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 132153344. Throughput: 0: 2720.9, 1: 2689.3. Samples: 132173268. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:58:28,445][86177] Avg episode reward: [(0, '-575.420'), (1, '-513.780')] -[2023-11-28 06:58:28,560][87426] Updated weights for policy 1, policy_version 258010 (0.0007) -[2023-11-28 06:58:28,717][87424] Updated weights for policy 0, policy_version 258268 (0.0008) -[2023-11-28 06:58:30,738][87426] Updated weights for policy 1, policy_version 258020 (0.0009) -[2023-11-28 06:58:31,108][87426] Updated weights for policy 1, policy_version 258030 (0.0012) -[2023-11-28 06:58:31,146][87424] Updated weights for policy 0, policy_version 258278 (0.0008) -[2023-11-28 06:58:31,493][87426] Updated weights for policy 1, policy_version 258040 (0.0012) -[2023-11-28 06:58:31,531][87424] Updated weights for policy 0, policy_version 258288 (0.0011) -[2023-11-28 06:58:31,912][87424] Updated weights for policy 0, policy_version 258298 (0.0011) -[2023-11-28 06:58:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 132186112. Throughput: 0: 2751.2, 1: 2668.0. Samples: 132198100. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:58:33,445][86177] Avg episode reward: [(0, '-589.390'), (1, '-520.280')] -[2023-11-28 06:58:33,689][87424] Updated weights for policy 0, policy_version 258308 (0.0008) -[2023-11-28 06:58:34,031][87426] Updated weights for policy 1, policy_version 258050 (0.0011) -[2023-11-28 06:58:34,069][87424] Updated weights for policy 0, policy_version 258318 (0.0008) -[2023-11-28 06:58:34,407][87426] Updated weights for policy 1, policy_version 258060 (0.0010) -[2023-11-28 06:58:34,458][87424] Updated weights for policy 0, policy_version 258328 (0.0008) -[2023-11-28 06:58:34,782][87426] Updated weights for policy 1, policy_version 258070 (0.0010) -[2023-11-28 06:58:35,168][87426] Updated weights for policy 1, policy_version 258080 (0.0007) -[2023-11-28 06:58:36,754][87424] Updated weights for policy 0, policy_version 258338 (0.0009) -[2023-11-28 06:58:36,897][87426] Updated weights for policy 1, policy_version 258090 (0.0010) -[2023-11-28 06:58:37,140][87424] Updated weights for policy 0, policy_version 258348 (0.0012) -[2023-11-28 06:58:37,280][87426] Updated weights for policy 1, policy_version 258100 (0.0011) -[2023-11-28 06:58:37,523][87424] Updated weights for policy 0, policy_version 258358 (0.0012) -[2023-11-28 06:58:37,652][87426] Updated weights for policy 1, policy_version 258110 (0.0012) -[2023-11-28 06:58:37,899][87424] Updated weights for policy 0, policy_version 258368 (0.0012) -[2023-11-28 06:58:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 132218880. Throughput: 0: 2760.6, 1: 2672.7. Samples: 132231524. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:58:38,445][86177] Avg episode reward: [(0, '-603.440'), (1, '-524.950')] -[2023-11-28 06:58:39,597][87424] Updated weights for policy 0, policy_version 258378 (0.0011) -[2023-11-28 06:58:39,755][87426] Updated weights for policy 1, policy_version 258120 (0.0009) -[2023-11-28 06:58:39,980][87424] Updated weights for policy 0, policy_version 258388 (0.0011) -[2023-11-28 06:58:40,130][87426] Updated weights for policy 1, policy_version 258130 (0.0012) -[2023-11-28 06:58:40,361][87424] Updated weights for policy 0, policy_version 258398 (0.0011) -[2023-11-28 06:58:40,508][87426] Updated weights for policy 1, policy_version 258140 (0.0012) -[2023-11-28 06:58:42,366][87426] Updated weights for policy 1, policy_version 258150 (0.0011) -[2023-11-28 06:58:42,742][87426] Updated weights for policy 1, policy_version 258160 (0.0012) -[2023-11-28 06:58:42,771][87424] Updated weights for policy 0, policy_version 258408 (0.0010) -[2023-11-28 06:58:43,127][87426] Updated weights for policy 1, policy_version 258170 (0.0011) -[2023-11-28 06:58:43,158][87424] Updated weights for policy 0, policy_version 258418 (0.0011) -[2023-11-28 06:58:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 132243456. Throughput: 0: 2751.9, 1: 2688.4. Samples: 132255876. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:58:43,445][86177] Avg episode reward: [(0, '-627.260'), (1, '-534.380')] -[2023-11-28 06:58:43,541][87424] Updated weights for policy 0, policy_version 258428 (0.0008) -[2023-11-28 06:58:45,411][87426] Updated weights for policy 1, policy_version 258180 (0.0010) -[2023-11-28 06:58:45,658][87424] Updated weights for policy 0, policy_version 258438 (0.0009) -[2023-11-28 06:58:45,779][87426] Updated weights for policy 1, policy_version 258190 (0.0011) -[2023-11-28 06:58:46,045][87424] Updated weights for policy 0, policy_version 258448 (0.0012) -[2023-11-28 06:58:46,158][87426] Updated weights for policy 1, policy_version 258200 (0.0009) -[2023-11-28 06:58:46,421][87424] Updated weights for policy 0, policy_version 258458 (0.0012) -[2023-11-28 06:58:48,063][87426] Updated weights for policy 1, policy_version 258210 (0.0008) -[2023-11-28 06:58:48,438][87426] Updated weights for policy 1, policy_version 258220 (0.0011) -[2023-11-28 06:58:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 132268032. Throughput: 0: 2742.6, 1: 2706.7. Samples: 132280856. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:58:48,445][86177] Avg episode reward: [(0, '-615.210'), (1, '-527.410')] -[2023-11-28 06:58:48,592][87424] Updated weights for policy 0, policy_version 258468 (0.0012) -[2023-11-28 06:58:48,813][87426] Updated weights for policy 1, policy_version 258230 (0.0009) -[2023-11-28 06:58:48,976][87424] Updated weights for policy 0, policy_version 258478 (0.0011) -[2023-11-28 06:58:49,195][87426] Updated weights for policy 1, policy_version 258240 (0.0009) -[2023-11-28 06:58:49,360][87424] Updated weights for policy 0, policy_version 258488 (0.0010) -[2023-11-28 06:58:51,749][87426] Updated weights for policy 1, policy_version 258250 (0.0012) -[2023-11-28 06:58:51,987][87424] Updated weights for policy 0, policy_version 258498 (0.0009) -[2023-11-28 06:58:52,127][87426] Updated weights for policy 1, policy_version 258260 (0.0010) -[2023-11-28 06:58:52,370][87424] Updated weights for policy 0, policy_version 258508 (0.0010) -[2023-11-28 06:58:52,508][87426] Updated weights for policy 1, policy_version 258270 (0.0009) -[2023-11-28 06:58:52,760][87424] Updated weights for policy 0, policy_version 258518 (0.0009) -[2023-11-28 06:58:53,147][87424] Updated weights for policy 0, policy_version 258528 (0.0008) -[2023-11-28 06:58:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 132300800. Throughput: 0: 2714.8, 1: 2714.8. Samples: 132312808. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:58:53,445][86177] Avg episode reward: [(0, '-596.730'), (1, '-530.890')] -[2023-11-28 06:58:54,961][87426] Updated weights for policy 1, policy_version 258280 (0.0007) -[2023-11-28 06:58:55,332][87424] Updated weights for policy 0, policy_version 258538 (0.0008) -[2023-11-28 06:58:55,346][87426] Updated weights for policy 1, policy_version 258290 (0.0008) -[2023-11-28 06:58:55,709][87424] Updated weights for policy 0, policy_version 258548 (0.0007) -[2023-11-28 06:58:55,733][87426] Updated weights for policy 1, policy_version 258300 (0.0007) -[2023-11-28 06:58:56,091][87424] Updated weights for policy 0, policy_version 258558 (0.0007) -[2023-11-28 06:58:57,816][87426] Updated weights for policy 1, policy_version 258310 (0.0007) -[2023-11-28 06:58:58,199][87426] Updated weights for policy 1, policy_version 258320 (0.0008) -[2023-11-28 06:58:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 132317184. Throughput: 0: 2698.8, 1: 2724.0. Samples: 132337616. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:58:58,445][86177] Avg episode reward: [(0, '-553.720'), (1, '-538.360')] -[2023-11-28 06:58:58,546][87424] Updated weights for policy 0, policy_version 258568 (0.0010) -[2023-11-28 06:58:58,584][87426] Updated weights for policy 1, policy_version 258330 (0.0008) -[2023-11-28 06:58:58,918][87424] Updated weights for policy 0, policy_version 258578 (0.0012) -[2023-11-28 06:58:59,299][87424] Updated weights for policy 0, policy_version 258588 (0.0012) -[2023-11-28 06:59:00,575][87426] Updated weights for policy 1, policy_version 258340 (0.0009) -[2023-11-28 06:59:00,954][87426] Updated weights for policy 1, policy_version 258350 (0.0011) -[2023-11-28 06:59:01,333][87426] Updated weights for policy 1, policy_version 258360 (0.0011) -[2023-11-28 06:59:01,655][87424] Updated weights for policy 0, policy_version 258598 (0.0011) -[2023-11-28 06:59:02,042][87424] Updated weights for policy 0, policy_version 258608 (0.0011) -[2023-11-28 06:59:02,432][87424] Updated weights for policy 0, policy_version 258618 (0.0011) -[2023-11-28 06:59:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 132349952. Throughput: 0: 2669.0, 1: 2708.8. Samples: 132360336. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:59:03,445][86177] Avg episode reward: [(0, '-533.640'), (1, '-540.130')] -[2023-11-28 06:59:03,824][87426] Updated weights for policy 1, policy_version 258370 (0.0012) -[2023-11-28 06:59:04,193][87426] Updated weights for policy 1, policy_version 258380 (0.0012) -[2023-11-28 06:59:04,551][87424] Updated weights for policy 0, policy_version 258628 (0.0012) -[2023-11-28 06:59:04,576][87426] Updated weights for policy 1, policy_version 258390 (0.0011) -[2023-11-28 06:59:04,940][87424] Updated weights for policy 0, policy_version 258638 (0.0012) -[2023-11-28 06:59:04,948][87426] Updated weights for policy 1, policy_version 258400 (0.0011) -[2023-11-28 06:59:05,324][87424] Updated weights for policy 0, policy_version 258648 (0.0011) -[2023-11-28 06:59:06,660][87426] Updated weights for policy 1, policy_version 258410 (0.0012) -[2023-11-28 06:59:07,038][87426] Updated weights for policy 1, policy_version 258420 (0.0012) -[2023-11-28 06:59:07,344][87424] Updated weights for policy 0, policy_version 258658 (0.0012) -[2023-11-28 06:59:07,418][87426] Updated weights for policy 1, policy_version 258430 (0.0012) -[2023-11-28 06:59:07,728][87424] Updated weights for policy 0, policy_version 258668 (0.0009) -[2023-11-28 06:59:08,113][87424] Updated weights for policy 0, policy_version 258678 (0.0008) -[2023-11-28 06:59:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 132374528. Throughput: 0: 2688.3, 1: 2761.1. Samples: 132394448. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:59:08,445][86177] Avg episode reward: [(0, '-516.390'), (1, '-548.860')] -[2023-11-28 06:59:08,495][87424] Updated weights for policy 0, policy_version 258688 (0.0008) -[2023-11-28 06:59:09,729][87426] Updated weights for policy 1, policy_version 258440 (0.0008) -[2023-11-28 06:59:10,109][87426] Updated weights for policy 1, policy_version 258450 (0.0008) -[2023-11-28 06:59:10,497][87426] Updated weights for policy 1, policy_version 258460 (0.0010) -[2023-11-28 06:59:10,996][87424] Updated weights for policy 0, policy_version 258698 (0.0011) -[2023-11-28 06:59:11,380][87424] Updated weights for policy 0, policy_version 258708 (0.0008) -[2023-11-28 06:59:11,766][87424] Updated weights for policy 0, policy_version 258718 (0.0009) -[2023-11-28 06:59:12,364][87426] Updated weights for policy 1, policy_version 258470 (0.0011) -[2023-11-28 06:59:12,740][87426] Updated weights for policy 1, policy_version 258480 (0.0012) -[2023-11-28 06:59:13,114][87426] Updated weights for policy 1, policy_version 258490 (0.0011) -[2023-11-28 06:59:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 132407296. Throughput: 0: 2691.4, 1: 2765.4. Samples: 132418824. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:59:13,445][86177] Avg episode reward: [(0, '-528.800'), (1, '-543.520')] -[2023-11-28 06:59:14,216][87424] Updated weights for policy 0, policy_version 258728 (0.0012) -[2023-11-28 06:59:14,594][87424] Updated weights for policy 0, policy_version 258738 (0.0012) -[2023-11-28 06:59:14,975][87424] Updated weights for policy 0, policy_version 258748 (0.0012) -[2023-11-28 06:59:14,991][87426] Updated weights for policy 1, policy_version 258500 (0.0007) -[2023-11-28 06:59:15,366][87426] Updated weights for policy 1, policy_version 258510 (0.0011) -[2023-11-28 06:59:15,745][87426] Updated weights for policy 1, policy_version 258520 (0.0012) -[2023-11-28 06:59:17,144][87424] Updated weights for policy 0, policy_version 258758 (0.0009) -[2023-11-28 06:59:17,522][87424] Updated weights for policy 0, policy_version 258768 (0.0007) -[2023-11-28 06:59:17,905][87424] Updated weights for policy 0, policy_version 258778 (0.0008) -[2023-11-28 06:59:18,114][87426] Updated weights for policy 1, policy_version 258530 (0.0010) -[2023-11-28 06:59:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 132431872. Throughput: 0: 2665.6, 1: 2775.5. Samples: 132442952. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:59:18,446][86177] Avg episode reward: [(0, '-539.460'), (1, '-556.880')] -[2023-11-28 06:59:18,494][87426] Updated weights for policy 1, policy_version 258540 (0.0008) -[2023-11-28 06:59:18,887][87426] Updated weights for policy 1, policy_version 258550 (0.0012) -[2023-11-28 06:59:19,255][87426] Updated weights for policy 1, policy_version 258560 (0.0012) -[2023-11-28 06:59:20,070][87424] Updated weights for policy 0, policy_version 258788 (0.0009) -[2023-11-28 06:59:20,457][87424] Updated weights for policy 0, policy_version 258798 (0.0011) -[2023-11-28 06:59:20,830][87424] Updated weights for policy 0, policy_version 258808 (0.0008) -[2023-11-28 06:59:21,618][87426] Updated weights for policy 1, policy_version 258570 (0.0008) -[2023-11-28 06:59:21,991][87426] Updated weights for policy 1, policy_version 258580 (0.0009) -[2023-11-28 06:59:22,382][87426] Updated weights for policy 1, policy_version 258590 (0.0009) -[2023-11-28 06:59:23,155][87424] Updated weights for policy 0, policy_version 258818 (0.0011) -[2023-11-28 06:59:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 132456448. Throughput: 0: 2643.5, 1: 2741.2. Samples: 132473836. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:59:23,445][86177] Avg episode reward: [(0, '-548.620'), (1, '-555.060')] -[2023-11-28 06:59:23,534][87424] Updated weights for policy 0, policy_version 258828 (0.0010) -[2023-11-28 06:59:23,918][87424] Updated weights for policy 0, policy_version 258838 (0.0007) -[2023-11-28 06:59:24,303][87424] Updated weights for policy 0, policy_version 258848 (0.0007) -[2023-11-28 06:59:24,573][87426] Updated weights for policy 1, policy_version 258600 (0.0011) -[2023-11-28 06:59:24,946][87426] Updated weights for policy 1, policy_version 258610 (0.0011) -[2023-11-28 06:59:25,323][87426] Updated weights for policy 1, policy_version 258620 (0.0011) -[2023-11-28 06:59:26,124][87424] Updated weights for policy 0, policy_version 258858 (0.0011) -[2023-11-28 06:59:26,506][87424] Updated weights for policy 0, policy_version 258868 (0.0012) -[2023-11-28 06:59:26,887][87424] Updated weights for policy 0, policy_version 258878 (0.0007) -[2023-11-28 06:59:27,749][87426] Updated weights for policy 1, policy_version 258630 (0.0011) -[2023-11-28 06:59:28,124][87426] Updated weights for policy 1, policy_version 258640 (0.0007) -[2023-11-28 06:59:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 132481024. Throughput: 0: 2648.1, 1: 2738.5. Samples: 132498272. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:59:28,445][86177] Avg episode reward: [(0, '-567.320'), (1, '-548.510')] -[2023-11-28 06:59:28,509][87426] Updated weights for policy 1, policy_version 258650 (0.0007) -[2023-11-28 06:59:29,308][87424] Updated weights for policy 0, policy_version 258888 (0.0011) -[2023-11-28 06:59:29,691][87424] Updated weights for policy 0, policy_version 258898 (0.0012) -[2023-11-28 06:59:30,074][87424] Updated weights for policy 0, policy_version 258908 (0.0011) -[2023-11-28 06:59:30,927][87426] Updated weights for policy 1, policy_version 258660 (0.0008) -[2023-11-28 06:59:31,293][87426] Updated weights for policy 1, policy_version 258670 (0.0007) -[2023-11-28 06:59:31,668][87426] Updated weights for policy 1, policy_version 258680 (0.0008) -[2023-11-28 06:59:32,240][87424] Updated weights for policy 0, policy_version 258918 (0.0010) -[2023-11-28 06:59:32,615][87424] Updated weights for policy 0, policy_version 258928 (0.0009) -[2023-11-28 06:59:32,996][87424] Updated weights for policy 0, policy_version 258938 (0.0009) -[2023-11-28 06:59:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 132513792. Throughput: 0: 2655.2, 1: 2709.9. Samples: 132522284. Policy #0 lag: (min: 5.0, avg: 29.8, max: 69.0) -[2023-11-28 06:59:33,445][86177] Avg episode reward: [(0, '-561.350'), (1, '-541.570')] -[2023-11-28 06:59:34,006][87426] Updated weights for policy 1, policy_version 258690 (0.0011) -[2023-11-28 06:59:34,383][87426] Updated weights for policy 1, policy_version 258700 (0.0011) -[2023-11-28 06:59:34,762][87426] Updated weights for policy 1, policy_version 258710 (0.0008) -[2023-11-28 06:59:35,130][87424] Updated weights for policy 0, policy_version 258948 (0.0008) -[2023-11-28 06:59:35,139][87426] Updated weights for policy 1, policy_version 258720 (0.0008) -[2023-11-28 06:59:35,514][87424] Updated weights for policy 0, policy_version 258958 (0.0007) -[2023-11-28 06:59:35,890][87424] Updated weights for policy 0, policy_version 258968 (0.0007) -[2023-11-28 06:59:37,569][87426] Updated weights for policy 1, policy_version 258730 (0.0012) -[2023-11-28 06:59:37,942][87426] Updated weights for policy 1, policy_version 258740 (0.0012) -[2023-11-28 06:59:38,117][87424] Updated weights for policy 0, policy_version 258978 (0.0008) -[2023-11-28 06:59:38,335][87426] Updated weights for policy 1, policy_version 258750 (0.0012) -[2023-11-28 06:59:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 132538368. Throughput: 0: 2679.1, 1: 2702.4. Samples: 132554976. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 06:59:38,445][86177] Avg episode reward: [(0, '-556.880'), (1, '-537.270')] -[2023-11-28 06:59:38,496][87424] Updated weights for policy 0, policy_version 258988 (0.0007) -[2023-11-28 06:59:38,884][87424] Updated weights for policy 0, policy_version 258998 (0.0008) -[2023-11-28 06:59:39,257][87424] Updated weights for policy 0, policy_version 259008 (0.0012) -[2023-11-28 06:59:40,626][87426] Updated weights for policy 1, policy_version 258760 (0.0012) -[2023-11-28 06:59:41,005][87426] Updated weights for policy 1, policy_version 258770 (0.0012) -[2023-11-28 06:59:41,287][87424] Updated weights for policy 0, policy_version 259018 (0.0011) -[2023-11-28 06:59:41,374][87426] Updated weights for policy 1, policy_version 258780 (0.0012) -[2023-11-28 06:59:41,659][87424] Updated weights for policy 0, policy_version 259028 (0.0012) -[2023-11-28 06:59:42,048][87424] Updated weights for policy 0, policy_version 259038 (0.0012) -[2023-11-28 06:59:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 132562944. Throughput: 0: 2698.7, 1: 2679.1. Samples: 132579616. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 06:59:43,445][86177] Avg episode reward: [(0, '-544.620'), (1, '-536.590')] -[2023-11-28 06:59:43,972][87426] Updated weights for policy 1, policy_version 258790 (0.0010) -[2023-11-28 06:59:44,241][87424] Updated weights for policy 0, policy_version 259048 (0.0008) -[2023-11-28 06:59:44,352][87426] Updated weights for policy 1, policy_version 258800 (0.0011) -[2023-11-28 06:59:44,634][87424] Updated weights for policy 0, policy_version 259058 (0.0008) -[2023-11-28 06:59:44,726][87426] Updated weights for policy 1, policy_version 258810 (0.0009) -[2023-11-28 06:59:45,003][87424] Updated weights for policy 0, policy_version 259068 (0.0008) -[2023-11-28 06:59:46,746][87426] Updated weights for policy 1, policy_version 258820 (0.0012) -[2023-11-28 06:59:47,119][87426] Updated weights for policy 1, policy_version 258830 (0.0007) -[2023-11-28 06:59:47,503][87426] Updated weights for policy 1, policy_version 258840 (0.0008) -[2023-11-28 06:59:47,503][87424] Updated weights for policy 0, policy_version 259078 (0.0007) -[2023-11-28 06:59:47,896][87424] Updated weights for policy 0, policy_version 259088 (0.0008) -[2023-11-28 06:59:48,272][87424] Updated weights for policy 0, policy_version 259098 (0.0007) -[2023-11-28 06:59:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 132587520. Throughput: 0: 2722.6, 1: 2681.3. Samples: 132603512. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 06:59:48,446][86177] Avg episode reward: [(0, '-578.200'), (1, '-538.810')] -[2023-11-28 06:59:49,889][87426] Updated weights for policy 1, policy_version 258850 (0.0008) -[2023-11-28 06:59:50,261][87426] Updated weights for policy 1, policy_version 258860 (0.0011) -[2023-11-28 06:59:50,637][87426] Updated weights for policy 1, policy_version 258870 (0.0010) -[2023-11-28 06:59:50,782][87424] Updated weights for policy 0, policy_version 259108 (0.0009) -[2023-11-28 06:59:51,009][87426] Updated weights for policy 1, policy_version 258880 (0.0011) -[2023-11-28 06:59:51,171][87424] Updated weights for policy 0, policy_version 259118 (0.0011) -[2023-11-28 06:59:51,557][87424] Updated weights for policy 0, policy_version 259128 (0.0011) -[2023-11-28 06:59:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 132612096. Throughput: 0: 2691.9, 1: 2636.6. Samples: 132634232. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 06:59:53,445][86177] Avg episode reward: [(0, '-630.490'), (1, '-552.150')] -[2023-11-28 06:59:53,488][87426] Updated weights for policy 1, policy_version 258890 (0.0012) -[2023-11-28 06:59:53,870][87426] Updated weights for policy 1, policy_version 258900 (0.0012) -[2023-11-28 06:59:53,905][87424] Updated weights for policy 0, policy_version 259138 (0.0010) -[2023-11-28 06:59:54,242][87426] Updated weights for policy 1, policy_version 258910 (0.0010) -[2023-11-28 06:59:54,289][87424] Updated weights for policy 0, policy_version 259148 (0.0012) -[2023-11-28 06:59:54,666][87424] Updated weights for policy 0, policy_version 259158 (0.0012) -[2023-11-28 06:59:55,050][87424] Updated weights for policy 0, policy_version 259168 (0.0012) -[2023-11-28 06:59:56,217][87426] Updated weights for policy 1, policy_version 258920 (0.0009) -[2023-11-28 06:59:56,584][87426] Updated weights for policy 1, policy_version 258930 (0.0008) -[2023-11-28 06:59:56,782][87424] Updated weights for policy 0, policy_version 259178 (0.0011) -[2023-11-28 06:59:56,975][87426] Updated weights for policy 1, policy_version 258940 (0.0007) -[2023-11-28 06:59:57,158][87424] Updated weights for policy 0, policy_version 259188 (0.0009) -[2023-11-28 06:59:57,547][87424] Updated weights for policy 0, policy_version 259198 (0.0008) -[2023-11-28 06:59:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 132644864. Throughput: 0: 2694.6, 1: 2642.0. Samples: 132658972. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 06:59:58,445][86177] Avg episode reward: [(0, '-668.260'), (1, '-552.320')] -[2023-11-28 06:59:59,016][87426] Updated weights for policy 1, policy_version 258950 (0.0008) -[2023-11-28 06:59:59,398][87426] Updated weights for policy 1, policy_version 258960 (0.0007) -[2023-11-28 06:59:59,779][87426] Updated weights for policy 1, policy_version 258970 (0.0008) -[2023-11-28 06:59:59,929][87424] Updated weights for policy 0, policy_version 259208 (0.0010) -[2023-11-28 07:00:00,317][87424] Updated weights for policy 0, policy_version 259218 (0.0011) -[2023-11-28 07:00:00,699][87424] Updated weights for policy 0, policy_version 259228 (0.0011) -[2023-11-28 07:00:01,844][87426] Updated weights for policy 1, policy_version 258980 (0.0009) -[2023-11-28 07:00:02,214][87426] Updated weights for policy 1, policy_version 258990 (0.0010) -[2023-11-28 07:00:02,593][87426] Updated weights for policy 1, policy_version 259000 (0.0009) -[2023-11-28 07:00:02,793][87424] Updated weights for policy 0, policy_version 259238 (0.0011) -[2023-11-28 07:00:03,170][87424] Updated weights for policy 0, policy_version 259248 (0.0011) -[2023-11-28 07:00:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 132669440. Throughput: 0: 2697.5, 1: 2642.1. Samples: 132683232. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:03,445][86177] Avg episode reward: [(0, '-675.110'), (1, '-551.920')] -[2023-11-28 07:00:03,553][87424] Updated weights for policy 0, policy_version 259258 (0.0008) -[2023-11-28 07:00:05,148][87426] Updated weights for policy 1, policy_version 259010 (0.0011) -[2023-11-28 07:00:05,495][87424] Updated weights for policy 0, policy_version 259268 (0.0009) -[2023-11-28 07:00:05,519][87426] Updated weights for policy 1, policy_version 259020 (0.0012) -[2023-11-28 07:00:05,874][87424] Updated weights for policy 0, policy_version 259278 (0.0011) -[2023-11-28 07:00:05,900][87426] Updated weights for policy 1, policy_version 259030 (0.0011) -[2023-11-28 07:00:06,266][87424] Updated weights for policy 0, policy_version 259288 (0.0009) -[2023-11-28 07:00:06,272][87426] Updated weights for policy 1, policy_version 259040 (0.0012) -[2023-11-28 07:00:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 132694016. Throughput: 0: 2730.7, 1: 2635.5. Samples: 132715312. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:08,445][86177] Avg episode reward: [(0, '-673.270'), (1, '-550.090')] -[2023-11-28 07:00:08,445][87424] Updated weights for policy 0, policy_version 259298 (0.0008) -[2023-11-28 07:00:08,665][87426] Updated weights for policy 1, policy_version 259050 (0.0011) -[2023-11-28 07:00:08,830][87424] Updated weights for policy 0, policy_version 259308 (0.0012) -[2023-11-28 07:00:09,046][87426] Updated weights for policy 1, policy_version 259060 (0.0011) -[2023-11-28 07:00:09,212][87424] Updated weights for policy 0, policy_version 259318 (0.0011) -[2023-11-28 07:00:09,416][87426] Updated weights for policy 1, policy_version 259070 (0.0011) -[2023-11-28 07:00:09,608][87424] Updated weights for policy 0, policy_version 259328 (0.0012) -[2023-11-28 07:00:11,362][87426] Updated weights for policy 1, policy_version 259080 (0.0012) -[2023-11-28 07:00:11,742][87426] Updated weights for policy 1, policy_version 259090 (0.0010) -[2023-11-28 07:00:12,126][87426] Updated weights for policy 1, policy_version 259100 (0.0010) -[2023-11-28 07:00:12,158][87424] Updated weights for policy 0, policy_version 259338 (0.0009) -[2023-11-28 07:00:12,530][87424] Updated weights for policy 0, policy_version 259348 (0.0010) -[2023-11-28 07:00:12,907][87424] Updated weights for policy 0, policy_version 259358 (0.0011) -[2023-11-28 07:00:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 132726784. Throughput: 0: 2720.3, 1: 2646.6. Samples: 132739780. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:13,445][86177] Avg episode reward: [(0, '-611.370'), (1, '-557.260')] -[2023-11-28 07:00:14,309][87426] Updated weights for policy 1, policy_version 259110 (0.0011) -[2023-11-28 07:00:14,685][87426] Updated weights for policy 1, policy_version 259120 (0.0012) -[2023-11-28 07:00:15,080][87426] Updated weights for policy 1, policy_version 259130 (0.0012) -[2023-11-28 07:00:15,534][87424] Updated weights for policy 0, policy_version 259368 (0.0009) -[2023-11-28 07:00:15,917][87424] Updated weights for policy 0, policy_version 259378 (0.0008) -[2023-11-28 07:00:16,307][87424] Updated weights for policy 0, policy_version 259388 (0.0008) -[2023-11-28 07:00:17,535][87426] Updated weights for policy 1, policy_version 259140 (0.0010) -[2023-11-28 07:00:17,917][87426] Updated weights for policy 1, policy_version 259150 (0.0009) -[2023-11-28 07:00:18,296][87426] Updated weights for policy 1, policy_version 259160 (0.0011) -[2023-11-28 07:00:18,328][87424] Updated weights for policy 0, policy_version 259398 (0.0009) -[2023-11-28 07:00:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 132743168. Throughput: 0: 2681.7, 1: 2668.1. Samples: 132763024. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:18,445][86177] Avg episode reward: [(0, '-586.830'), (1, '-544.020')] -[2023-11-28 07:00:18,601][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000259168_66347008.pth... -[2023-11-28 07:00:18,631][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000256640_65699840.pth -[2023-11-28 07:00:18,719][87424] Updated weights for policy 0, policy_version 259408 (0.0009) -[2023-11-28 07:00:19,101][87424] Updated weights for policy 0, policy_version 259418 (0.0012) -[2023-11-28 07:00:19,330][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000259424_66412544.pth... -[2023-11-28 07:00:19,377][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000256864_65757184.pth -[2023-11-28 07:00:20,199][87426] Updated weights for policy 1, policy_version 259170 (0.0011) -[2023-11-28 07:00:20,578][87426] Updated weights for policy 1, policy_version 259180 (0.0010) -[2023-11-28 07:00:20,949][87426] Updated weights for policy 1, policy_version 259190 (0.0011) -[2023-11-28 07:00:21,054][87424] Updated weights for policy 0, policy_version 259428 (0.0012) -[2023-11-28 07:00:21,323][87426] Updated weights for policy 1, policy_version 259200 (0.0011) -[2023-11-28 07:00:21,434][87424] Updated weights for policy 0, policy_version 259438 (0.0011) -[2023-11-28 07:00:21,821][87424] Updated weights for policy 0, policy_version 259448 (0.0012) -[2023-11-28 07:00:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 132775936. Throughput: 0: 2674.1, 1: 2672.4. Samples: 132795564. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:23,445][86177] Avg episode reward: [(0, '-548.880'), (1, '-552.490')] -[2023-11-28 07:00:23,719][87426] Updated weights for policy 1, policy_version 259210 (0.0012) -[2023-11-28 07:00:24,094][87426] Updated weights for policy 1, policy_version 259220 (0.0012) -[2023-11-28 07:00:24,271][87424] Updated weights for policy 0, policy_version 259458 (0.0012) -[2023-11-28 07:00:24,477][87426] Updated weights for policy 1, policy_version 259230 (0.0011) -[2023-11-28 07:00:24,642][87424] Updated weights for policy 0, policy_version 259468 (0.0012) -[2023-11-28 07:00:25,036][87424] Updated weights for policy 0, policy_version 259478 (0.0012) -[2023-11-28 07:00:25,414][87424] Updated weights for policy 0, policy_version 259488 (0.0012) -[2023-11-28 07:00:26,805][87426] Updated weights for policy 1, policy_version 259240 (0.0008) -[2023-11-28 07:00:27,185][87426] Updated weights for policy 1, policy_version 259250 (0.0011) -[2023-11-28 07:00:27,497][87424] Updated weights for policy 0, policy_version 259498 (0.0010) -[2023-11-28 07:00:27,562][87426] Updated weights for policy 1, policy_version 259260 (0.0008) -[2023-11-28 07:00:27,888][87424] Updated weights for policy 0, policy_version 259508 (0.0008) -[2023-11-28 07:00:28,277][87424] Updated weights for policy 0, policy_version 259518 (0.0012) -[2023-11-28 07:00:28,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 132808704. Throughput: 0: 2663.0, 1: 2653.5. Samples: 132818860. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:28,445][86177] Avg episode reward: [(0, '-547.410'), (1, '-554.190')] -[2023-11-28 07:00:29,890][87424] Updated weights for policy 0, policy_version 259528 (0.0011) -[2023-11-28 07:00:30,143][87426] Updated weights for policy 1, policy_version 259270 (0.0010) -[2023-11-28 07:00:30,269][87424] Updated weights for policy 0, policy_version 259538 (0.0010) -[2023-11-28 07:00:30,514][87426] Updated weights for policy 1, policy_version 259280 (0.0010) -[2023-11-28 07:00:30,651][87424] Updated weights for policy 0, policy_version 259548 (0.0009) -[2023-11-28 07:00:30,893][87426] Updated weights for policy 1, policy_version 259290 (0.0010) -[2023-11-28 07:00:32,843][87426] Updated weights for policy 1, policy_version 259300 (0.0009) -[2023-11-28 07:00:33,099][87424] Updated weights for policy 0, policy_version 259558 (0.0010) -[2023-11-28 07:00:33,218][87426] Updated weights for policy 1, policy_version 259310 (0.0008) -[2023-11-28 07:00:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 132825088. Throughput: 0: 2667.7, 1: 2648.9. Samples: 132842756. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:33,445][86177] Avg episode reward: [(0, '-548.320'), (1, '-571.750')] -[2023-11-28 07:00:33,484][87424] Updated weights for policy 0, policy_version 259568 (0.0011) -[2023-11-28 07:00:33,602][87426] Updated weights for policy 1, policy_version 259320 (0.0011) -[2023-11-28 07:00:33,875][87424] Updated weights for policy 0, policy_version 259578 (0.0008) -[2023-11-28 07:00:35,799][87426] Updated weights for policy 1, policy_version 259330 (0.0011) -[2023-11-28 07:00:36,177][87426] Updated weights for policy 1, policy_version 259340 (0.0011) -[2023-11-28 07:00:36,343][87424] Updated weights for policy 0, policy_version 259588 (0.0010) -[2023-11-28 07:00:36,554][87426] Updated weights for policy 1, policy_version 259350 (0.0010) -[2023-11-28 07:00:36,712][87424] Updated weights for policy 0, policy_version 259598 (0.0011) -[2023-11-28 07:00:36,935][87426] Updated weights for policy 1, policy_version 259360 (0.0011) -[2023-11-28 07:00:37,093][87424] Updated weights for policy 0, policy_version 259608 (0.0012) -[2023-11-28 07:00:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 132857856. Throughput: 0: 2691.7, 1: 2662.7. Samples: 132875184. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:38,445][86177] Avg episode reward: [(0, '-551.850'), (1, '-574.250')] -[2023-11-28 07:00:38,857][87424] Updated weights for policy 0, policy_version 259618 (0.0012) -[2023-11-28 07:00:39,128][87426] Updated weights for policy 1, policy_version 259370 (0.0012) -[2023-11-28 07:00:39,239][87424] Updated weights for policy 0, policy_version 259628 (0.0010) -[2023-11-28 07:00:39,509][87426] Updated weights for policy 1, policy_version 259380 (0.0011) -[2023-11-28 07:00:39,621][87424] Updated weights for policy 0, policy_version 259638 (0.0010) -[2023-11-28 07:00:39,887][87426] Updated weights for policy 1, policy_version 259390 (0.0011) -[2023-11-28 07:00:40,007][87424] Updated weights for policy 0, policy_version 259648 (0.0012) -[2023-11-28 07:00:42,078][87426] Updated weights for policy 1, policy_version 259400 (0.0010) -[2023-11-28 07:00:42,453][87426] Updated weights for policy 1, policy_version 259410 (0.0012) -[2023-11-28 07:00:42,454][87424] Updated weights for policy 0, policy_version 259658 (0.0012) -[2023-11-28 07:00:42,829][87424] Updated weights for policy 0, policy_version 259668 (0.0012) -[2023-11-28 07:00:42,838][87426] Updated weights for policy 1, policy_version 259420 (0.0012) -[2023-11-28 07:00:43,208][87424] Updated weights for policy 0, policy_version 259678 (0.0010) -[2023-11-28 07:00:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 132890624. Throughput: 0: 2692.1, 1: 2659.9. Samples: 132899812. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:43,445][86177] Avg episode reward: [(0, '-529.130'), (1, '-550.200')] -[2023-11-28 07:00:45,086][87426] Updated weights for policy 1, policy_version 259430 (0.0011) -[2023-11-28 07:00:45,167][87424] Updated weights for policy 0, policy_version 259688 (0.0011) -[2023-11-28 07:00:45,462][87426] Updated weights for policy 1, policy_version 259440 (0.0011) -[2023-11-28 07:00:45,550][87424] Updated weights for policy 0, policy_version 259698 (0.0010) -[2023-11-28 07:00:45,851][87426] Updated weights for policy 1, policy_version 259450 (0.0011) -[2023-11-28 07:00:45,930][87424] Updated weights for policy 0, policy_version 259708 (0.0011) -[2023-11-28 07:00:47,847][87426] Updated weights for policy 1, policy_version 259460 (0.0011) -[2023-11-28 07:00:48,179][87424] Updated weights for policy 0, policy_version 259718 (0.0010) -[2023-11-28 07:00:48,217][87426] Updated weights for policy 1, policy_version 259470 (0.0011) -[2023-11-28 07:00:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 132907008. Throughput: 0: 2685.1, 1: 2664.8. Samples: 132923976. Policy #0 lag: (min: 1.0, avg: 24.7, max: 33.0) -[2023-11-28 07:00:48,445][86177] Avg episode reward: [(0, '-570.200'), (1, '-562.170')] -[2023-11-28 07:00:48,569][87424] Updated weights for policy 0, policy_version 259728 (0.0011) -[2023-11-28 07:00:48,590][87426] Updated weights for policy 1, policy_version 259480 (0.0012) -[2023-11-28 07:00:48,943][87424] Updated weights for policy 0, policy_version 259738 (0.0009) -[2023-11-28 07:00:50,721][87426] Updated weights for policy 1, policy_version 259490 (0.0011) -[2023-11-28 07:00:51,041][87424] Updated weights for policy 0, policy_version 259748 (0.0011) -[2023-11-28 07:00:51,099][87426] Updated weights for policy 1, policy_version 259500 (0.0008) -[2023-11-28 07:00:51,422][87424] Updated weights for policy 0, policy_version 259758 (0.0008) -[2023-11-28 07:00:51,478][87426] Updated weights for policy 1, policy_version 259510 (0.0008) -[2023-11-28 07:00:51,809][87424] Updated weights for policy 0, policy_version 259768 (0.0010) -[2023-11-28 07:00:51,862][87426] Updated weights for policy 1, policy_version 259520 (0.0010) -[2023-11-28 07:00:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 132939776. Throughput: 0: 2699.1, 1: 2693.0. Samples: 132957956. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:00:53,445][86177] Avg episode reward: [(0, '-563.570'), (1, '-553.040')] -[2023-11-28 07:00:53,894][87424] Updated weights for policy 0, policy_version 259778 (0.0011) -[2023-11-28 07:00:54,141][87426] Updated weights for policy 1, policy_version 259530 (0.0010) -[2023-11-28 07:00:54,276][87424] Updated weights for policy 0, policy_version 259788 (0.0010) -[2023-11-28 07:00:54,510][87426] Updated weights for policy 1, policy_version 259540 (0.0010) -[2023-11-28 07:00:54,669][87424] Updated weights for policy 0, policy_version 259798 (0.0008) -[2023-11-28 07:00:54,890][87426] Updated weights for policy 1, policy_version 259550 (0.0011) -[2023-11-28 07:00:55,038][87424] Updated weights for policy 0, policy_version 259808 (0.0008) -[2023-11-28 07:00:57,109][87426] Updated weights for policy 1, policy_version 259560 (0.0011) -[2023-11-28 07:00:57,255][87424] Updated weights for policy 0, policy_version 259818 (0.0007) -[2023-11-28 07:00:57,484][87426] Updated weights for policy 1, policy_version 259570 (0.0008) -[2023-11-28 07:00:57,632][87424] Updated weights for policy 0, policy_version 259828 (0.0007) -[2023-11-28 07:00:57,864][87426] Updated weights for policy 1, policy_version 259580 (0.0010) -[2023-11-28 07:00:58,023][87424] Updated weights for policy 0, policy_version 259838 (0.0010) -[2023-11-28 07:00:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 132972544. Throughput: 0: 2706.5, 1: 2709.0. Samples: 132983476. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:00:58,445][86177] Avg episode reward: [(0, '-678.420'), (1, '-534.360')] -[2023-11-28 07:00:59,678][87426] Updated weights for policy 1, policy_version 259590 (0.0009) -[2023-11-28 07:00:59,807][87424] Updated weights for policy 0, policy_version 259848 (0.0012) -[2023-11-28 07:01:00,048][87426] Updated weights for policy 1, policy_version 259600 (0.0009) -[2023-11-28 07:01:00,178][87424] Updated weights for policy 0, policy_version 259858 (0.0012) -[2023-11-28 07:01:00,427][87426] Updated weights for policy 1, policy_version 259610 (0.0010) -[2023-11-28 07:01:00,554][87424] Updated weights for policy 0, policy_version 259868 (0.0011) -[2023-11-28 07:01:02,502][87424] Updated weights for policy 0, policy_version 259878 (0.0009) -[2023-11-28 07:01:02,870][87424] Updated weights for policy 0, policy_version 259888 (0.0009) -[2023-11-28 07:01:02,970][87426] Updated weights for policy 1, policy_version 259620 (0.0011) -[2023-11-28 07:01:03,253][87424] Updated weights for policy 0, policy_version 259898 (0.0009) -[2023-11-28 07:01:03,349][87426] Updated weights for policy 1, policy_version 259630 (0.0012) -[2023-11-28 07:01:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 132988928. Throughput: 0: 2753.9, 1: 2710.5. Samples: 133008920. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:03,445][86177] Avg episode reward: [(0, '-677.140'), (1, '-532.530')] -[2023-11-28 07:01:03,726][87426] Updated weights for policy 1, policy_version 259640 (0.0012) -[2023-11-28 07:01:05,392][87424] Updated weights for policy 0, policy_version 259908 (0.0010) -[2023-11-28 07:01:05,760][87426] Updated weights for policy 1, policy_version 259650 (0.0011) -[2023-11-28 07:01:05,763][87424] Updated weights for policy 0, policy_version 259918 (0.0012) -[2023-11-28 07:01:06,134][87426] Updated weights for policy 1, policy_version 259660 (0.0008) -[2023-11-28 07:01:06,140][87424] Updated weights for policy 0, policy_version 259928 (0.0011) -[2023-11-28 07:01:06,520][87426] Updated weights for policy 1, policy_version 259670 (0.0009) -[2023-11-28 07:01:06,886][87426] Updated weights for policy 1, policy_version 259680 (0.0012) -[2023-11-28 07:01:08,268][87424] Updated weights for policy 0, policy_version 259938 (0.0012) -[2023-11-28 07:01:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133021696. Throughput: 0: 2765.5, 1: 2703.6. Samples: 133041672. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:08,445][86177] Avg episode reward: [(0, '-670.060'), (1, '-542.180')] -[2023-11-28 07:01:08,651][87424] Updated weights for policy 0, policy_version 259948 (0.0011) -[2023-11-28 07:01:08,898][87426] Updated weights for policy 1, policy_version 259690 (0.0010) -[2023-11-28 07:01:09,028][87424] Updated weights for policy 0, policy_version 259958 (0.0009) -[2023-11-28 07:01:09,278][87426] Updated weights for policy 1, policy_version 259700 (0.0011) -[2023-11-28 07:01:09,413][87424] Updated weights for policy 0, policy_version 259968 (0.0008) -[2023-11-28 07:01:09,659][87426] Updated weights for policy 1, policy_version 259710 (0.0012) -[2023-11-28 07:01:11,485][87424] Updated weights for policy 0, policy_version 259978 (0.0012) -[2023-11-28 07:01:11,820][87426] Updated weights for policy 1, policy_version 259720 (0.0010) -[2023-11-28 07:01:11,872][87424] Updated weights for policy 0, policy_version 259988 (0.0012) -[2023-11-28 07:01:12,201][87426] Updated weights for policy 1, policy_version 259730 (0.0009) -[2023-11-28 07:01:12,250][87424] Updated weights for policy 0, policy_version 259998 (0.0012) -[2023-11-28 07:01:12,590][87426] Updated weights for policy 1, policy_version 259740 (0.0009) -[2023-11-28 07:01:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133054464. Throughput: 0: 2776.0, 1: 2734.5. Samples: 133066832. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:13,445][86177] Avg episode reward: [(0, '-708.170'), (1, '-539.300')] -[2023-11-28 07:01:14,503][87426] Updated weights for policy 1, policy_version 259750 (0.0010) -[2023-11-28 07:01:14,510][87424] Updated weights for policy 0, policy_version 260008 (0.0010) -[2023-11-28 07:01:14,887][87426] Updated weights for policy 1, policy_version 259760 (0.0009) -[2023-11-28 07:01:14,887][87424] Updated weights for policy 0, policy_version 260018 (0.0012) -[2023-11-28 07:01:15,262][87426] Updated weights for policy 1, policy_version 259770 (0.0008) -[2023-11-28 07:01:15,272][87424] Updated weights for policy 0, policy_version 260028 (0.0012) -[2023-11-28 07:01:17,508][87424] Updated weights for policy 0, policy_version 260038 (0.0010) -[2023-11-28 07:01:17,509][87426] Updated weights for policy 1, policy_version 259780 (0.0010) -[2023-11-28 07:01:17,877][87424] Updated weights for policy 0, policy_version 260048 (0.0009) -[2023-11-28 07:01:17,890][87426] Updated weights for policy 1, policy_version 259790 (0.0012) -[2023-11-28 07:01:18,260][87424] Updated weights for policy 0, policy_version 260058 (0.0007) -[2023-11-28 07:01:18,264][87426] Updated weights for policy 1, policy_version 259800 (0.0011) -[2023-11-28 07:01:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133070848. Throughput: 0: 2776.2, 1: 2739.2. Samples: 133090948. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:18,445][86177] Avg episode reward: [(0, '-587.920'), (1, '-551.580')] -[2023-11-28 07:01:20,450][87424] Updated weights for policy 0, policy_version 260068 (0.0008) -[2023-11-28 07:01:20,827][87424] Updated weights for policy 0, policy_version 260078 (0.0009) -[2023-11-28 07:01:20,890][87426] Updated weights for policy 1, policy_version 259810 (0.0009) -[2023-11-28 07:01:21,212][87424] Updated weights for policy 0, policy_version 260088 (0.0011) -[2023-11-28 07:01:21,248][87426] Updated weights for policy 1, policy_version 259820 (0.0010) -[2023-11-28 07:01:21,639][87426] Updated weights for policy 1, policy_version 259830 (0.0011) -[2023-11-28 07:01:22,010][87426] Updated weights for policy 1, policy_version 259840 (0.0010) -[2023-11-28 07:01:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133103616. Throughput: 0: 2758.7, 1: 2731.4. Samples: 133122236. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:23,445][86177] Avg episode reward: [(0, '-585.900'), (1, '-568.180')] -[2023-11-28 07:01:23,575][87424] Updated weights for policy 0, policy_version 260098 (0.0010) -[2023-11-28 07:01:23,949][87424] Updated weights for policy 0, policy_version 260108 (0.0010) -[2023-11-28 07:01:24,337][87424] Updated weights for policy 0, policy_version 260118 (0.0008) -[2023-11-28 07:01:24,521][87426] Updated weights for policy 1, policy_version 259850 (0.0007) -[2023-11-28 07:01:24,709][87424] Updated weights for policy 0, policy_version 260128 (0.0009) -[2023-11-28 07:01:24,914][87426] Updated weights for policy 1, policy_version 259860 (0.0010) -[2023-11-28 07:01:25,286][87426] Updated weights for policy 1, policy_version 259870 (0.0007) -[2023-11-28 07:01:26,671][87424] Updated weights for policy 0, policy_version 260138 (0.0009) -[2023-11-28 07:01:27,040][87424] Updated weights for policy 0, policy_version 260148 (0.0010) -[2023-11-28 07:01:27,063][87426] Updated weights for policy 1, policy_version 259880 (0.0007) -[2023-11-28 07:01:27,421][87424] Updated weights for policy 0, policy_version 260158 (0.0007) -[2023-11-28 07:01:27,447][87426] Updated weights for policy 1, policy_version 259890 (0.0007) -[2023-11-28 07:01:27,825][87426] Updated weights for policy 1, policy_version 259900 (0.0007) -[2023-11-28 07:01:28,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133136384. Throughput: 0: 2745.2, 1: 2724.3. Samples: 133145940. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:28,445][86177] Avg episode reward: [(0, '-587.810'), (1, '-542.410')] -[2023-11-28 07:01:29,661][87424] Updated weights for policy 0, policy_version 260168 (0.0011) -[2023-11-28 07:01:29,795][87426] Updated weights for policy 1, policy_version 259910 (0.0008) -[2023-11-28 07:01:30,037][87424] Updated weights for policy 0, policy_version 260178 (0.0011) -[2023-11-28 07:01:30,178][87426] Updated weights for policy 1, policy_version 259920 (0.0010) -[2023-11-28 07:01:30,425][87424] Updated weights for policy 0, policy_version 260188 (0.0011) -[2023-11-28 07:01:30,562][87426] Updated weights for policy 1, policy_version 259930 (0.0009) -[2023-11-28 07:01:32,631][87426] Updated weights for policy 1, policy_version 259940 (0.0007) -[2023-11-28 07:01:32,686][87424] Updated weights for policy 0, policy_version 260198 (0.0011) -[2023-11-28 07:01:33,017][87426] Updated weights for policy 1, policy_version 259950 (0.0009) -[2023-11-28 07:01:33,065][87424] Updated weights for policy 0, policy_version 260208 (0.0011) -[2023-11-28 07:01:33,397][87426] Updated weights for policy 1, policy_version 259960 (0.0008) -[2023-11-28 07:01:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 133152768. Throughput: 0: 2749.3, 1: 2727.0. Samples: 133170412. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:33,445][86177] Avg episode reward: [(0, '-552.930'), (1, '-543.960')] -[2023-11-28 07:01:33,449][87424] Updated weights for policy 0, policy_version 260218 (0.0011) -[2023-11-28 07:01:35,588][87424] Updated weights for policy 0, policy_version 260228 (0.0012) -[2023-11-28 07:01:35,701][87426] Updated weights for policy 1, policy_version 259970 (0.0008) -[2023-11-28 07:01:35,973][87424] Updated weights for policy 0, policy_version 260238 (0.0008) -[2023-11-28 07:01:36,075][87426] Updated weights for policy 1, policy_version 259980 (0.0008) -[2023-11-28 07:01:36,358][87424] Updated weights for policy 0, policy_version 260248 (0.0010) -[2023-11-28 07:01:36,455][87426] Updated weights for policy 1, policy_version 259990 (0.0007) -[2023-11-28 07:01:36,834][87426] Updated weights for policy 1, policy_version 260000 (0.0008) -[2023-11-28 07:01:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133185536. Throughput: 0: 2721.7, 1: 2711.8. Samples: 133202464. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:38,445][86177] Avg episode reward: [(0, '-519.870'), (1, '-527.750')] -[2023-11-28 07:01:38,602][87424] Updated weights for policy 0, policy_version 260258 (0.0011) -[2023-11-28 07:01:38,988][87424] Updated weights for policy 0, policy_version 260268 (0.0011) -[2023-11-28 07:01:38,993][87426] Updated weights for policy 1, policy_version 260010 (0.0011) -[2023-11-28 07:01:39,362][87426] Updated weights for policy 1, policy_version 260020 (0.0011) -[2023-11-28 07:01:39,368][87424] Updated weights for policy 0, policy_version 260278 (0.0012) -[2023-11-28 07:01:39,742][87426] Updated weights for policy 1, policy_version 260030 (0.0012) -[2023-11-28 07:01:39,748][87424] Updated weights for policy 0, policy_version 260288 (0.0010) -[2023-11-28 07:01:42,278][87426] Updated weights for policy 1, policy_version 260040 (0.0011) -[2023-11-28 07:01:42,284][87424] Updated weights for policy 0, policy_version 260298 (0.0012) -[2023-11-28 07:01:42,658][87426] Updated weights for policy 1, policy_version 260050 (0.0009) -[2023-11-28 07:01:42,672][87424] Updated weights for policy 0, policy_version 260308 (0.0008) -[2023-11-28 07:01:43,029][87426] Updated weights for policy 1, policy_version 260060 (0.0009) -[2023-11-28 07:01:43,046][87424] Updated weights for policy 0, policy_version 260318 (0.0010) -[2023-11-28 07:01:43,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133218304. Throughput: 0: 2724.7, 1: 2681.3. Samples: 133226748. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:43,445][86177] Avg episode reward: [(0, '-562.180'), (1, '-512.400')] -[2023-11-28 07:01:45,272][87424] Updated weights for policy 0, policy_version 260328 (0.0011) -[2023-11-28 07:01:45,489][87426] Updated weights for policy 1, policy_version 260070 (0.0009) -[2023-11-28 07:01:45,644][87424] Updated weights for policy 0, policy_version 260338 (0.0011) -[2023-11-28 07:01:45,870][87426] Updated weights for policy 1, policy_version 260080 (0.0011) -[2023-11-28 07:01:46,029][87424] Updated weights for policy 0, policy_version 260348 (0.0011) -[2023-11-28 07:01:46,251][87426] Updated weights for policy 1, policy_version 260090 (0.0011) -[2023-11-28 07:01:47,929][87424] Updated weights for policy 0, policy_version 260358 (0.0012) -[2023-11-28 07:01:48,315][87424] Updated weights for policy 0, policy_version 260368 (0.0012) -[2023-11-28 07:01:48,334][87426] Updated weights for policy 1, policy_version 260100 (0.0011) -[2023-11-28 07:01:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133234688. Throughput: 0: 2705.0, 1: 2688.7. Samples: 133251636. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:48,445][86177] Avg episode reward: [(0, '-585.360'), (1, '-518.260')] -[2023-11-28 07:01:48,702][87424] Updated weights for policy 0, policy_version 260378 (0.0012) -[2023-11-28 07:01:48,722][87426] Updated weights for policy 1, policy_version 260110 (0.0011) -[2023-11-28 07:01:49,100][87426] Updated weights for policy 1, policy_version 260120 (0.0012) -[2023-11-28 07:01:50,880][87424] Updated weights for policy 0, policy_version 260388 (0.0012) -[2023-11-28 07:01:51,052][87426] Updated weights for policy 1, policy_version 260130 (0.0010) -[2023-11-28 07:01:51,256][87424] Updated weights for policy 0, policy_version 260398 (0.0011) -[2023-11-28 07:01:51,431][87426] Updated weights for policy 1, policy_version 260140 (0.0008) -[2023-11-28 07:01:51,636][87424] Updated weights for policy 0, policy_version 260408 (0.0012) -[2023-11-28 07:01:51,815][87426] Updated weights for policy 1, policy_version 260150 (0.0011) -[2023-11-28 07:01:52,191][87426] Updated weights for policy 1, policy_version 260160 (0.0008) -[2023-11-28 07:01:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133267456. Throughput: 0: 2704.1, 1: 2712.5. Samples: 133285420. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:53,445][86177] Avg episode reward: [(0, '-587.180'), (1, '-511.880')] -[2023-11-28 07:01:53,729][87424] Updated weights for policy 0, policy_version 260418 (0.0012) -[2023-11-28 07:01:54,105][87424] Updated weights for policy 0, policy_version 260428 (0.0009) -[2023-11-28 07:01:54,486][87424] Updated weights for policy 0, policy_version 260438 (0.0011) -[2023-11-28 07:01:54,756][87426] Updated weights for policy 1, policy_version 260170 (0.0011) -[2023-11-28 07:01:54,864][87424] Updated weights for policy 0, policy_version 260448 (0.0007) -[2023-11-28 07:01:55,133][87426] Updated weights for policy 1, policy_version 260180 (0.0009) -[2023-11-28 07:01:55,522][87426] Updated weights for policy 1, policy_version 260190 (0.0011) -[2023-11-28 07:01:57,184][87426] Updated weights for policy 1, policy_version 260200 (0.0010) -[2023-11-28 07:01:57,256][87424] Updated weights for policy 0, policy_version 260458 (0.0008) -[2023-11-28 07:01:57,550][87426] Updated weights for policy 1, policy_version 260210 (0.0009) -[2023-11-28 07:01:57,639][87424] Updated weights for policy 0, policy_version 260468 (0.0008) -[2023-11-28 07:01:57,939][87426] Updated weights for policy 1, policy_version 260220 (0.0009) -[2023-11-28 07:01:58,019][87424] Updated weights for policy 0, policy_version 260478 (0.0012) -[2023-11-28 07:01:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133300224. Throughput: 0: 2689.9, 1: 2703.1. Samples: 133309516. Policy #0 lag: (min: 12.0, avg: 27.4, max: 44.0) -[2023-11-28 07:01:58,445][86177] Avg episode reward: [(0, '-661.340'), (1, '-516.040')] -[2023-11-28 07:02:00,081][87424] Updated weights for policy 0, policy_version 260488 (0.0010) -[2023-11-28 07:02:00,218][87426] Updated weights for policy 1, policy_version 260230 (0.0008) -[2023-11-28 07:02:00,453][87424] Updated weights for policy 0, policy_version 260498 (0.0010) -[2023-11-28 07:02:00,590][87426] Updated weights for policy 1, policy_version 260240 (0.0010) -[2023-11-28 07:02:00,833][87424] Updated weights for policy 0, policy_version 260508 (0.0011) -[2023-11-28 07:02:00,982][87426] Updated weights for policy 1, policy_version 260250 (0.0011) -[2023-11-28 07:02:03,156][87426] Updated weights for policy 1, policy_version 260260 (0.0012) -[2023-11-28 07:02:03,246][87424] Updated weights for policy 0, policy_version 260518 (0.0011) -[2023-11-28 07:02:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 133316608. Throughput: 0: 2708.8, 1: 2704.0. Samples: 133334524. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:03,445][86177] Avg episode reward: [(0, '-623.560'), (1, '-519.240')] -[2023-11-28 07:02:03,534][87426] Updated weights for policy 1, policy_version 260270 (0.0008) -[2023-11-28 07:02:03,623][87424] Updated weights for policy 0, policy_version 260528 (0.0011) -[2023-11-28 07:02:03,916][87426] Updated weights for policy 1, policy_version 260280 (0.0007) -[2023-11-28 07:02:04,012][87424] Updated weights for policy 0, policy_version 260538 (0.0007) -[2023-11-28 07:02:05,871][87424] Updated weights for policy 0, policy_version 260548 (0.0009) -[2023-11-28 07:02:06,019][87426] Updated weights for policy 1, policy_version 260290 (0.0008) -[2023-11-28 07:02:06,255][87424] Updated weights for policy 0, policy_version 260558 (0.0012) -[2023-11-28 07:02:06,403][87426] Updated weights for policy 1, policy_version 260300 (0.0012) -[2023-11-28 07:02:06,643][87424] Updated weights for policy 0, policy_version 260568 (0.0012) -[2023-11-28 07:02:06,777][87426] Updated weights for policy 1, policy_version 260310 (0.0011) -[2023-11-28 07:02:07,159][87426] Updated weights for policy 1, policy_version 260320 (0.0011) -[2023-11-28 07:02:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133349376. Throughput: 0: 2708.7, 1: 2719.8. Samples: 133366520. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:08,445][86177] Avg episode reward: [(0, '-615.960'), (1, '-524.990')] -[2023-11-28 07:02:08,480][87424] Updated weights for policy 0, policy_version 260578 (0.0011) -[2023-11-28 07:02:08,869][87424] Updated weights for policy 0, policy_version 260588 (0.0011) -[2023-11-28 07:02:09,172][87426] Updated weights for policy 1, policy_version 260330 (0.0012) -[2023-11-28 07:02:09,245][87424] Updated weights for policy 0, policy_version 260598 (0.0012) -[2023-11-28 07:02:09,552][87426] Updated weights for policy 1, policy_version 260340 (0.0012) -[2023-11-28 07:02:09,625][87424] Updated weights for policy 0, policy_version 260608 (0.0012) -[2023-11-28 07:02:09,937][87426] Updated weights for policy 1, policy_version 260350 (0.0010) -[2023-11-28 07:02:11,786][87424] Updated weights for policy 0, policy_version 260618 (0.0012) -[2023-11-28 07:02:12,173][87424] Updated weights for policy 0, policy_version 260628 (0.0011) -[2023-11-28 07:02:12,390][87426] Updated weights for policy 1, policy_version 260360 (0.0010) -[2023-11-28 07:02:12,548][87424] Updated weights for policy 0, policy_version 260638 (0.0011) -[2023-11-28 07:02:12,772][87426] Updated weights for policy 1, policy_version 260370 (0.0010) -[2023-11-28 07:02:13,147][87426] Updated weights for policy 1, policy_version 260380 (0.0009) -[2023-11-28 07:02:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133382144. Throughput: 0: 2721.0, 1: 2733.6. Samples: 133391396. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:13,445][86177] Avg episode reward: [(0, '-652.620'), (1, '-520.520')] -[2023-11-28 07:02:15,045][87424] Updated weights for policy 0, policy_version 260648 (0.0011) -[2023-11-28 07:02:15,138][87426] Updated weights for policy 1, policy_version 260390 (0.0008) -[2023-11-28 07:02:15,418][87424] Updated weights for policy 0, policy_version 260658 (0.0009) -[2023-11-28 07:02:15,516][87426] Updated weights for policy 1, policy_version 260400 (0.0010) -[2023-11-28 07:02:15,800][87424] Updated weights for policy 0, policy_version 260668 (0.0010) -[2023-11-28 07:02:15,895][87426] Updated weights for policy 1, policy_version 260410 (0.0009) -[2023-11-28 07:02:17,600][87424] Updated weights for policy 0, policy_version 260678 (0.0011) -[2023-11-28 07:02:17,963][87426] Updated weights for policy 1, policy_version 260420 (0.0007) -[2023-11-28 07:02:17,976][87424] Updated weights for policy 0, policy_version 260688 (0.0011) -[2023-11-28 07:02:18,344][87426] Updated weights for policy 1, policy_version 260430 (0.0009) -[2023-11-28 07:02:18,360][87424] Updated weights for policy 0, policy_version 260698 (0.0011) -[2023-11-28 07:02:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133398528. Throughput: 0: 2741.8, 1: 2744.7. Samples: 133417304. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:18,445][86177] Avg episode reward: [(0, '-612.480'), (1, '-524.260')] -[2023-11-28 07:02:18,595][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000260704_66740224.pth... -[2023-11-28 07:02:18,643][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000258144_66084864.pth -[2023-11-28 07:02:18,711][87426] Updated weights for policy 1, policy_version 260440 (0.0012) -[2023-11-28 07:02:19,012][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000260448_66674688.pth... -[2023-11-28 07:02:19,043][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000257920_66027520.pth -[2023-11-28 07:02:20,657][87424] Updated weights for policy 0, policy_version 260708 (0.0012) -[2023-11-28 07:02:21,040][87424] Updated weights for policy 0, policy_version 260718 (0.0012) -[2023-11-28 07:02:21,099][87426] Updated weights for policy 1, policy_version 260450 (0.0010) -[2023-11-28 07:02:21,414][87424] Updated weights for policy 0, policy_version 260728 (0.0011) -[2023-11-28 07:02:21,482][87426] Updated weights for policy 1, policy_version 260460 (0.0011) -[2023-11-28 07:02:21,860][87426] Updated weights for policy 1, policy_version 260470 (0.0011) -[2023-11-28 07:02:22,241][87426] Updated weights for policy 1, policy_version 260480 (0.0010) -[2023-11-28 07:02:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133431296. Throughput: 0: 2731.1, 1: 2753.1. Samples: 133449252. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:23,445][86177] Avg episode reward: [(0, '-617.690'), (1, '-519.850')] -[2023-11-28 07:02:23,961][87424] Updated weights for policy 0, policy_version 260738 (0.0009) -[2023-11-28 07:02:24,116][87426] Updated weights for policy 1, policy_version 260490 (0.0008) -[2023-11-28 07:02:24,333][87424] Updated weights for policy 0, policy_version 260748 (0.0008) -[2023-11-28 07:02:24,493][87426] Updated weights for policy 1, policy_version 260500 (0.0012) -[2023-11-28 07:02:24,715][87424] Updated weights for policy 0, policy_version 260758 (0.0008) -[2023-11-28 07:02:24,864][87426] Updated weights for policy 1, policy_version 260510 (0.0010) -[2023-11-28 07:02:25,104][87424] Updated weights for policy 0, policy_version 260768 (0.0011) -[2023-11-28 07:02:26,932][87426] Updated weights for policy 1, policy_version 260520 (0.0008) -[2023-11-28 07:02:27,277][87424] Updated weights for policy 0, policy_version 260778 (0.0012) -[2023-11-28 07:02:27,314][87426] Updated weights for policy 1, policy_version 260530 (0.0007) -[2023-11-28 07:02:27,666][87424] Updated weights for policy 0, policy_version 260788 (0.0012) -[2023-11-28 07:02:27,695][87426] Updated weights for policy 1, policy_version 260540 (0.0007) -[2023-11-28 07:02:28,049][87424] Updated weights for policy 0, policy_version 260798 (0.0008) -[2023-11-28 07:02:28,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133464064. Throughput: 0: 2711.7, 1: 2760.3. Samples: 133472984. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:28,445][86177] Avg episode reward: [(0, '-619.990'), (1, '-525.930')] -[2023-11-28 07:02:30,177][87426] Updated weights for policy 1, policy_version 260550 (0.0010) -[2023-11-28 07:02:30,257][87424] Updated weights for policy 0, policy_version 260808 (0.0011) -[2023-11-28 07:02:30,552][87426] Updated weights for policy 1, policy_version 260560 (0.0011) -[2023-11-28 07:02:30,644][87424] Updated weights for policy 0, policy_version 260818 (0.0009) -[2023-11-28 07:02:30,927][87426] Updated weights for policy 1, policy_version 260570 (0.0011) -[2023-11-28 07:02:31,021][87424] Updated weights for policy 0, policy_version 260828 (0.0009) -[2023-11-28 07:02:32,833][87426] Updated weights for policy 1, policy_version 260580 (0.0012) -[2023-11-28 07:02:32,948][87424] Updated weights for policy 0, policy_version 260838 (0.0009) -[2023-11-28 07:02:33,215][87426] Updated weights for policy 1, policy_version 260590 (0.0011) -[2023-11-28 07:02:33,342][87424] Updated weights for policy 0, policy_version 260848 (0.0011) -[2023-11-28 07:02:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 133480448. Throughput: 0: 2712.6, 1: 2743.3. Samples: 133497152. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:33,445][86177] Avg episode reward: [(0, '-565.260'), (1, '-523.540')] -[2023-11-28 07:02:33,583][87426] Updated weights for policy 1, policy_version 260600 (0.0012) -[2023-11-28 07:02:33,724][87424] Updated weights for policy 0, policy_version 260858 (0.0012) -[2023-11-28 07:02:36,049][87424] Updated weights for policy 0, policy_version 260868 (0.0011) -[2023-11-28 07:02:36,095][87426] Updated weights for policy 1, policy_version 260610 (0.0011) -[2023-11-28 07:02:36,432][87424] Updated weights for policy 0, policy_version 260878 (0.0011) -[2023-11-28 07:02:36,472][87426] Updated weights for policy 1, policy_version 260620 (0.0012) -[2023-11-28 07:02:36,818][87424] Updated weights for policy 0, policy_version 260888 (0.0011) -[2023-11-28 07:02:36,846][87426] Updated weights for policy 1, policy_version 260630 (0.0012) -[2023-11-28 07:02:37,221][87426] Updated weights for policy 1, policy_version 260640 (0.0011) -[2023-11-28 07:02:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133513216. Throughput: 0: 2720.6, 1: 2742.7. Samples: 133531268. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:38,445][86177] Avg episode reward: [(0, '-530.410'), (1, '-542.110')] -[2023-11-28 07:02:38,578][87424] Updated weights for policy 0, policy_version 260898 (0.0012) -[2023-11-28 07:02:38,974][87424] Updated weights for policy 0, policy_version 260908 (0.0012) -[2023-11-28 07:02:39,358][87424] Updated weights for policy 0, policy_version 260918 (0.0012) -[2023-11-28 07:02:39,567][87426] Updated weights for policy 1, policy_version 260650 (0.0011) -[2023-11-28 07:02:39,743][87424] Updated weights for policy 0, policy_version 260928 (0.0011) -[2023-11-28 07:02:39,945][87426] Updated weights for policy 1, policy_version 260660 (0.0011) -[2023-11-28 07:02:40,323][87426] Updated weights for policy 1, policy_version 260670 (0.0008) -[2023-11-28 07:02:42,006][87424] Updated weights for policy 0, policy_version 260938 (0.0012) -[2023-11-28 07:02:42,384][87424] Updated weights for policy 0, policy_version 260948 (0.0011) -[2023-11-28 07:02:42,522][87426] Updated weights for policy 1, policy_version 260680 (0.0012) -[2023-11-28 07:02:42,764][87424] Updated weights for policy 0, policy_version 260958 (0.0009) -[2023-11-28 07:02:42,893][87426] Updated weights for policy 1, policy_version 260690 (0.0010) -[2023-11-28 07:02:43,274][87426] Updated weights for policy 1, policy_version 260700 (0.0012) -[2023-11-28 07:02:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133545984. Throughput: 0: 2734.7, 1: 2734.8. Samples: 133555644. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:43,445][86177] Avg episode reward: [(0, '-581.930'), (1, '-534.910')] -[2023-11-28 07:02:45,092][87426] Updated weights for policy 1, policy_version 260710 (0.0011) -[2023-11-28 07:02:45,231][87424] Updated weights for policy 0, policy_version 260968 (0.0010) -[2023-11-28 07:02:45,459][87426] Updated weights for policy 1, policy_version 260720 (0.0012) -[2023-11-28 07:02:45,611][87424] Updated weights for policy 0, policy_version 260978 (0.0011) -[2023-11-28 07:02:45,836][87426] Updated weights for policy 1, policy_version 260730 (0.0011) -[2023-11-28 07:02:45,993][87424] Updated weights for policy 0, policy_version 260988 (0.0010) -[2023-11-28 07:02:47,532][87426] Updated weights for policy 1, policy_version 260740 (0.0011) -[2023-11-28 07:02:47,912][87426] Updated weights for policy 1, policy_version 260750 (0.0012) -[2023-11-28 07:02:48,152][87424] Updated weights for policy 0, policy_version 260998 (0.0010) -[2023-11-28 07:02:48,303][87426] Updated weights for policy 1, policy_version 260760 (0.0012) -[2023-11-28 07:02:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 133562368. Throughput: 0: 2725.8, 1: 2760.9. Samples: 133581424. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:48,445][86177] Avg episode reward: [(0, '-627.040'), (1, '-524.000')] -[2023-11-28 07:02:48,527][87424] Updated weights for policy 0, policy_version 261008 (0.0011) -[2023-11-28 07:02:48,911][87424] Updated weights for policy 0, policy_version 261018 (0.0011) -[2023-11-28 07:02:50,383][87426] Updated weights for policy 1, policy_version 260770 (0.0012) -[2023-11-28 07:02:50,768][87426] Updated weights for policy 1, policy_version 260780 (0.0010) -[2023-11-28 07:02:50,961][87424] Updated weights for policy 0, policy_version 261028 (0.0011) -[2023-11-28 07:02:51,140][87426] Updated weights for policy 1, policy_version 260790 (0.0011) -[2023-11-28 07:02:51,335][87424] Updated weights for policy 0, policy_version 261038 (0.0012) -[2023-11-28 07:02:51,520][87426] Updated weights for policy 1, policy_version 260800 (0.0010) -[2023-11-28 07:02:51,725][87424] Updated weights for policy 0, policy_version 261048 (0.0012) -[2023-11-28 07:02:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133595136. Throughput: 0: 2740.6, 1: 2777.4. Samples: 133614832. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:53,445][86177] Avg episode reward: [(0, '-629.860'), (1, '-532.990')] -[2023-11-28 07:02:54,095][87424] Updated weights for policy 0, policy_version 261058 (0.0011) -[2023-11-28 07:02:54,104][87426] Updated weights for policy 1, policy_version 260810 (0.0008) -[2023-11-28 07:02:54,472][87424] Updated weights for policy 0, policy_version 261068 (0.0011) -[2023-11-28 07:02:54,488][87426] Updated weights for policy 1, policy_version 260820 (0.0011) -[2023-11-28 07:02:54,856][87424] Updated weights for policy 0, policy_version 261078 (0.0007) -[2023-11-28 07:02:54,857][87426] Updated weights for policy 1, policy_version 260830 (0.0010) -[2023-11-28 07:02:55,244][87424] Updated weights for policy 0, policy_version 261088 (0.0011) -[2023-11-28 07:02:56,697][87426] Updated weights for policy 1, policy_version 260840 (0.0007) -[2023-11-28 07:02:57,077][87426] Updated weights for policy 1, policy_version 260850 (0.0007) -[2023-11-28 07:02:57,468][87426] Updated weights for policy 1, policy_version 260860 (0.0008) -[2023-11-28 07:02:57,727][87424] Updated weights for policy 0, policy_version 261098 (0.0011) -[2023-11-28 07:02:58,109][87424] Updated weights for policy 0, policy_version 261108 (0.0012) -[2023-11-28 07:02:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 133619712. Throughput: 0: 2731.9, 1: 2778.3. Samples: 133639356. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:02:58,445][86177] Avg episode reward: [(0, '-631.810'), (1, '-520.550')] -[2023-11-28 07:02:58,490][87424] Updated weights for policy 0, policy_version 261118 (0.0009) -[2023-11-28 07:02:59,854][87426] Updated weights for policy 1, policy_version 260870 (0.0010) -[2023-11-28 07:03:00,237][87426] Updated weights for policy 1, policy_version 260880 (0.0012) -[2023-11-28 07:03:00,392][87424] Updated weights for policy 0, policy_version 261128 (0.0011) -[2023-11-28 07:03:00,615][87426] Updated weights for policy 1, policy_version 260890 (0.0012) -[2023-11-28 07:03:00,784][87424] Updated weights for policy 0, policy_version 261138 (0.0011) -[2023-11-28 07:03:01,165][87424] Updated weights for policy 0, policy_version 261148 (0.0012) -[2023-11-28 07:03:02,477][87426] Updated weights for policy 1, policy_version 260900 (0.0011) -[2023-11-28 07:03:02,855][87426] Updated weights for policy 1, policy_version 260910 (0.0009) -[2023-11-28 07:03:03,195][87424] Updated weights for policy 0, policy_version 261158 (0.0012) -[2023-11-28 07:03:03,233][87426] Updated weights for policy 1, policy_version 260920 (0.0008) -[2023-11-28 07:03:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 133644288. Throughput: 0: 2724.1, 1: 2756.8. Samples: 133663944. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:03:03,445][86177] Avg episode reward: [(0, '-617.820'), (1, '-520.730')] -[2023-11-28 07:03:03,570][87424] Updated weights for policy 0, policy_version 261168 (0.0012) -[2023-11-28 07:03:03,953][87424] Updated weights for policy 0, policy_version 261178 (0.0012) -[2023-11-28 07:03:05,548][87426] Updated weights for policy 1, policy_version 260930 (0.0008) -[2023-11-28 07:03:05,618][87424] Updated weights for policy 0, policy_version 261188 (0.0012) -[2023-11-28 07:03:05,932][87426] Updated weights for policy 1, policy_version 260940 (0.0010) -[2023-11-28 07:03:06,000][87424] Updated weights for policy 0, policy_version 261198 (0.0009) -[2023-11-28 07:03:06,303][87426] Updated weights for policy 1, policy_version 260950 (0.0008) -[2023-11-28 07:03:06,382][87424] Updated weights for policy 0, policy_version 261208 (0.0011) -[2023-11-28 07:03:06,680][87426] Updated weights for policy 1, policy_version 260960 (0.0010) -[2023-11-28 07:03:08,243][87424] Updated weights for policy 0, policy_version 261218 (0.0011) -[2023-11-28 07:03:08,375][87426] Updated weights for policy 1, policy_version 260970 (0.0012) -[2023-11-28 07:03:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 133677056. Throughput: 0: 2768.0, 1: 2766.9. Samples: 133698324. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:03:08,446][86177] Avg episode reward: [(0, '-555.090'), (1, '-523.550')] -[2023-11-28 07:03:08,628][87424] Updated weights for policy 0, policy_version 261228 (0.0007) -[2023-11-28 07:03:08,750][87426] Updated weights for policy 1, policy_version 260980 (0.0012) -[2023-11-28 07:03:09,005][87424] Updated weights for policy 0, policy_version 261238 (0.0010) -[2023-11-28 07:03:09,136][87426] Updated weights for policy 1, policy_version 260990 (0.0008) -[2023-11-28 07:03:09,383][87424] Updated weights for policy 0, policy_version 261248 (0.0012) -[2023-11-28 07:03:11,263][87426] Updated weights for policy 1, policy_version 261000 (0.0011) -[2023-11-28 07:03:11,638][87426] Updated weights for policy 1, policy_version 261010 (0.0011) -[2023-11-28 07:03:11,706][87424] Updated weights for policy 0, policy_version 261258 (0.0011) -[2023-11-28 07:03:12,011][87426] Updated weights for policy 1, policy_version 261020 (0.0011) -[2023-11-28 07:03:12,087][87424] Updated weights for policy 0, policy_version 261268 (0.0010) -[2023-11-28 07:03:12,460][87424] Updated weights for policy 0, policy_version 261278 (0.0008) -[2023-11-28 07:03:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133709824. Throughput: 0: 2780.4, 1: 2762.5. Samples: 133722412. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 07:03:13,445][86177] Avg episode reward: [(0, '-554.780'), (1, '-514.780')] -[2023-11-28 07:03:14,514][87426] Updated weights for policy 1, policy_version 261030 (0.0009) -[2023-11-28 07:03:14,890][87426] Updated weights for policy 1, policy_version 261040 (0.0007) -[2023-11-28 07:03:15,056][87424] Updated weights for policy 0, policy_version 261288 (0.0011) -[2023-11-28 07:03:15,276][87426] Updated weights for policy 1, policy_version 261050 (0.0010) -[2023-11-28 07:03:15,440][87424] Updated weights for policy 0, policy_version 261298 (0.0012) -[2023-11-28 07:03:15,823][87424] Updated weights for policy 0, policy_version 261308 (0.0011) -[2023-11-28 07:03:17,261][87426] Updated weights for policy 1, policy_version 261060 (0.0009) -[2023-11-28 07:03:17,645][87426] Updated weights for policy 1, policy_version 261070 (0.0009) -[2023-11-28 07:03:17,668][87424] Updated weights for policy 0, policy_version 261318 (0.0011) -[2023-11-28 07:03:18,034][87426] Updated weights for policy 1, policy_version 261080 (0.0011) -[2023-11-28 07:03:18,043][87424] Updated weights for policy 0, policy_version 261328 (0.0010) -[2023-11-28 07:03:18,428][87424] Updated weights for policy 0, policy_version 261338 (0.0008) -[2023-11-28 07:03:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 133734400. Throughput: 0: 2772.9, 1: 2775.3. Samples: 133746820. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:03:18,445][86177] Avg episode reward: [(0, '-579.210'), (1, '-536.440')] -[2023-11-28 07:03:20,503][87426] Updated weights for policy 1, policy_version 261090 (0.0012) -[2023-11-28 07:03:20,879][87426] Updated weights for policy 1, policy_version 261100 (0.0011) -[2023-11-28 07:03:21,012][87424] Updated weights for policy 0, policy_version 261348 (0.0011) -[2023-11-28 07:03:21,255][87426] Updated weights for policy 1, policy_version 261110 (0.0011) -[2023-11-28 07:03:21,385][87424] Updated weights for policy 0, policy_version 261358 (0.0011) -[2023-11-28 07:03:21,629][87426] Updated weights for policy 1, policy_version 261120 (0.0011) -[2023-11-28 07:03:21,769][87424] Updated weights for policy 0, policy_version 261368 (0.0012) -[2023-11-28 07:03:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133758976. Throughput: 0: 2742.5, 1: 2753.3. Samples: 133778580. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:03:23,445][86177] Avg episode reward: [(0, '-539.760'), (1, '-528.460')] -[2023-11-28 07:03:24,020][87426] Updated weights for policy 1, policy_version 261130 (0.0008) -[2023-11-28 07:03:24,100][87424] Updated weights for policy 0, policy_version 261378 (0.0012) -[2023-11-28 07:03:24,397][87426] Updated weights for policy 1, policy_version 261140 (0.0007) -[2023-11-28 07:03:24,484][87424] Updated weights for policy 0, policy_version 261388 (0.0008) -[2023-11-28 07:03:24,780][87426] Updated weights for policy 1, policy_version 261150 (0.0009) -[2023-11-28 07:03:24,871][87424] Updated weights for policy 0, policy_version 261398 (0.0009) -[2023-11-28 07:03:25,258][87424] Updated weights for policy 0, policy_version 261408 (0.0008) -[2023-11-28 07:03:27,217][87426] Updated weights for policy 1, policy_version 261160 (0.0011) -[2023-11-28 07:03:27,556][87424] Updated weights for policy 0, policy_version 261418 (0.0009) -[2023-11-28 07:03:27,598][87426] Updated weights for policy 1, policy_version 261170 (0.0012) -[2023-11-28 07:03:27,938][87424] Updated weights for policy 0, policy_version 261428 (0.0010) -[2023-11-28 07:03:27,978][87426] Updated weights for policy 1, policy_version 261180 (0.0011) -[2023-11-28 07:03:28,323][87424] Updated weights for policy 0, policy_version 261438 (0.0012) -[2023-11-28 07:03:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133791744. Throughput: 0: 2739.0, 1: 2746.2. Samples: 133802480. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:03:28,445][86177] Avg episode reward: [(0, '-542.790'), (1, '-524.290')] -[2023-11-28 07:03:29,873][87426] Updated weights for policy 1, policy_version 261190 (0.0011) -[2023-11-28 07:03:29,878][87424] Updated weights for policy 0, policy_version 261448 (0.0011) -[2023-11-28 07:03:30,247][87426] Updated weights for policy 1, policy_version 261200 (0.0011) -[2023-11-28 07:03:30,255][87424] Updated weights for policy 0, policy_version 261458 (0.0008) -[2023-11-28 07:03:30,623][87426] Updated weights for policy 1, policy_version 261210 (0.0011) -[2023-11-28 07:03:30,635][87424] Updated weights for policy 0, policy_version 261468 (0.0008) -[2023-11-28 07:03:32,383][87426] Updated weights for policy 1, policy_version 261220 (0.0011) -[2023-11-28 07:03:32,681][87424] Updated weights for policy 0, policy_version 261478 (0.0010) -[2023-11-28 07:03:32,763][87426] Updated weights for policy 1, policy_version 261230 (0.0011) -[2023-11-28 07:03:33,069][87424] Updated weights for policy 0, policy_version 261488 (0.0011) -[2023-11-28 07:03:33,139][87426] Updated weights for policy 1, policy_version 261240 (0.0010) -[2023-11-28 07:03:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 133816320. Throughput: 0: 2750.5, 1: 2728.8. Samples: 133827992. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:03:33,445][86177] Avg episode reward: [(0, '-572.510'), (1, '-522.240')] -[2023-11-28 07:03:33,452][87424] Updated weights for policy 0, policy_version 261498 (0.0008) -[2023-11-28 07:03:35,106][87426] Updated weights for policy 1, policy_version 261250 (0.0011) -[2023-11-28 07:03:35,264][87424] Updated weights for policy 0, policy_version 261508 (0.0007) -[2023-11-28 07:03:35,487][87426] Updated weights for policy 1, policy_version 261260 (0.0012) -[2023-11-28 07:03:35,651][87424] Updated weights for policy 0, policy_version 261518 (0.0009) -[2023-11-28 07:03:35,866][87426] Updated weights for policy 1, policy_version 261270 (0.0011) -[2023-11-28 07:03:36,030][87424] Updated weights for policy 0, policy_version 261528 (0.0012) -[2023-11-28 07:03:36,251][87426] Updated weights for policy 1, policy_version 261280 (0.0012) -[2023-11-28 07:03:38,249][87424] Updated weights for policy 0, policy_version 261538 (0.0010) -[2023-11-28 07:03:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133840896. Throughput: 0: 2753.6, 1: 2714.5. Samples: 133860896. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:03:38,445][86177] Avg episode reward: [(0, '-554.720'), (1, '-503.020')] -[2023-11-28 07:03:38,629][87424] Updated weights for policy 0, policy_version 261548 (0.0011) -[2023-11-28 07:03:38,667][87426] Updated weights for policy 1, policy_version 261290 (0.0011) -[2023-11-28 07:03:39,015][87424] Updated weights for policy 0, policy_version 261558 (0.0008) -[2023-11-28 07:03:39,046][87426] Updated weights for policy 1, policy_version 261300 (0.0010) -[2023-11-28 07:03:39,395][87424] Updated weights for policy 0, policy_version 261568 (0.0008) -[2023-11-28 07:03:39,428][87426] Updated weights for policy 1, policy_version 261310 (0.0011) -[2023-11-28 07:03:41,631][87426] Updated weights for policy 1, policy_version 261320 (0.0012) -[2023-11-28 07:03:41,793][87424] Updated weights for policy 0, policy_version 261578 (0.0012) -[2023-11-28 07:03:42,023][87426] Updated weights for policy 1, policy_version 261330 (0.0010) -[2023-11-28 07:03:42,170][87424] Updated weights for policy 0, policy_version 261588 (0.0013) -[2023-11-28 07:03:42,389][87426] Updated weights for policy 1, policy_version 261340 (0.0009) -[2023-11-28 07:03:42,549][87424] Updated weights for policy 0, policy_version 261598 (0.0008) -[2023-11-28 07:03:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133873664. Throughput: 0: 2751.3, 1: 2704.6. Samples: 133884872. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:03:43,445][86177] Avg episode reward: [(0, '-553.920'), (1, '-512.610')] -[2023-11-28 07:03:44,467][87426] Updated weights for policy 1, policy_version 261350 (0.0009) -[2023-11-28 07:03:44,846][87426] Updated weights for policy 1, policy_version 261360 (0.0007) -[2023-11-28 07:03:45,067][87424] Updated weights for policy 0, policy_version 261608 (0.0010) -[2023-11-28 07:03:45,229][87426] Updated weights for policy 1, policy_version 261370 (0.0008) -[2023-11-28 07:03:45,441][87424] Updated weights for policy 0, policy_version 261618 (0.0009) -[2023-11-28 07:03:45,823][87424] Updated weights for policy 0, policy_version 261628 (0.0008) -[2023-11-28 07:03:47,574][87424] Updated weights for policy 0, policy_version 261638 (0.0007) -[2023-11-28 07:03:47,608][87426] Updated weights for policy 1, policy_version 261380 (0.0009) -[2023-11-28 07:03:47,949][87424] Updated weights for policy 0, policy_version 261648 (0.0007) -[2023-11-28 07:03:47,991][87426] Updated weights for policy 1, policy_version 261390 (0.0007) -[2023-11-28 07:03:48,322][87424] Updated weights for policy 0, policy_version 261658 (0.0010) -[2023-11-28 07:03:48,367][87426] Updated weights for policy 1, policy_version 261400 (0.0008) -[2023-11-28 07:03:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 133890048. Throughput: 0: 2745.7, 1: 2707.5. Samples: 133909340. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:03:48,446][86177] Avg episode reward: [(0, '-574.950'), (1, '-515.680')] -[2023-11-28 07:03:50,424][87424] Updated weights for policy 0, policy_version 261668 (0.0010) -[2023-11-28 07:03:50,532][87426] Updated weights for policy 1, policy_version 261410 (0.0008) -[2023-11-28 07:03:50,801][87424] Updated weights for policy 0, policy_version 261678 (0.0011) -[2023-11-28 07:03:50,900][87426] Updated weights for policy 1, policy_version 261420 (0.0009) -[2023-11-28 07:03:51,185][87424] Updated weights for policy 0, policy_version 261688 (0.0012) -[2023-11-28 07:03:51,278][87426] Updated weights for policy 1, policy_version 261430 (0.0010) -[2023-11-28 07:03:51,660][87426] Updated weights for policy 1, policy_version 261440 (0.0012) -[2023-11-28 07:03:53,342][87424] Updated weights for policy 0, policy_version 261698 (0.0011) -[2023-11-28 07:03:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 133922816. Throughput: 0: 2726.3, 1: 2693.8. Samples: 133942228. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:03:53,445][86177] Avg episode reward: [(0, '-555.050'), (1, '-518.910')] -[2023-11-28 07:03:53,730][87424] Updated weights for policy 0, policy_version 261708 (0.0012) -[2023-11-28 07:03:53,919][87426] Updated weights for policy 1, policy_version 261450 (0.0010) -[2023-11-28 07:03:54,101][87424] Updated weights for policy 0, policy_version 261718 (0.0012) -[2023-11-28 07:03:54,300][87426] Updated weights for policy 1, policy_version 261460 (0.0007) -[2023-11-28 07:03:54,479][87424] Updated weights for policy 0, policy_version 261728 (0.0012) -[2023-11-28 07:03:54,683][87426] Updated weights for policy 1, policy_version 261470 (0.0011) -[2023-11-28 07:03:56,319][87424] Updated weights for policy 0, policy_version 261738 (0.0012) -[2023-11-28 07:03:56,601][87426] Updated weights for policy 1, policy_version 261480 (0.0012) -[2023-11-28 07:03:56,706][87424] Updated weights for policy 0, policy_version 261748 (0.0012) -[2023-11-28 07:03:56,989][87426] Updated weights for policy 1, policy_version 261490 (0.0011) -[2023-11-28 07:03:57,088][87424] Updated weights for policy 0, policy_version 261758 (0.0011) -[2023-11-28 07:03:57,353][87426] Updated weights for policy 1, policy_version 261500 (0.0008) -[2023-11-28 07:03:58,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 133955584. Throughput: 0: 2727.7, 1: 2688.4. Samples: 133966136. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:03:58,445][86177] Avg episode reward: [(0, '-544.480'), (1, '-516.180')] -[2023-11-28 07:03:59,350][87424] Updated weights for policy 0, policy_version 261768 (0.0011) -[2023-11-28 07:03:59,703][87426] Updated weights for policy 1, policy_version 261510 (0.0009) -[2023-11-28 07:03:59,727][87424] Updated weights for policy 0, policy_version 261778 (0.0011) -[2023-11-28 07:04:00,080][87426] Updated weights for policy 1, policy_version 261520 (0.0011) -[2023-11-28 07:04:00,114][87424] Updated weights for policy 0, policy_version 261788 (0.0011) -[2023-11-28 07:04:00,461][87426] Updated weights for policy 1, policy_version 261530 (0.0009) -[2023-11-28 07:04:02,691][87424] Updated weights for policy 0, policy_version 261798 (0.0011) -[2023-11-28 07:04:02,766][87426] Updated weights for policy 1, policy_version 261540 (0.0011) -[2023-11-28 07:04:03,070][87424] Updated weights for policy 0, policy_version 261808 (0.0008) -[2023-11-28 07:04:03,145][87426] Updated weights for policy 1, policy_version 261550 (0.0011) -[2023-11-28 07:04:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 133971968. Throughput: 0: 2738.4, 1: 2687.2. Samples: 133990972. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:04:03,445][86177] Avg episode reward: [(0, '-583.400'), (1, '-504.380')] -[2023-11-28 07:04:03,449][87424] Updated weights for policy 0, policy_version 261818 (0.0007) -[2023-11-28 07:04:03,530][87426] Updated weights for policy 1, policy_version 261560 (0.0011) -[2023-11-28 07:04:05,917][87426] Updated weights for policy 1, policy_version 261570 (0.0011) -[2023-11-28 07:04:05,927][87424] Updated weights for policy 0, policy_version 261828 (0.0008) -[2023-11-28 07:04:06,299][87426] Updated weights for policy 1, policy_version 261580 (0.0007) -[2023-11-28 07:04:06,317][87424] Updated weights for policy 0, policy_version 261838 (0.0011) -[2023-11-28 07:04:06,679][87426] Updated weights for policy 1, policy_version 261590 (0.0009) -[2023-11-28 07:04:06,685][87424] Updated weights for policy 0, policy_version 261848 (0.0010) -[2023-11-28 07:04:07,055][87426] Updated weights for policy 1, policy_version 261600 (0.0011) -[2023-11-28 07:04:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 134004736. Throughput: 0: 2730.4, 1: 2678.1. Samples: 134021964. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:04:08,445][86177] Avg episode reward: [(0, '-563.930'), (1, '-492.840')] -[2023-11-28 07:04:08,520][87424] Updated weights for policy 0, policy_version 261858 (0.0009) -[2023-11-28 07:04:08,807][87426] Updated weights for policy 1, policy_version 261610 (0.0011) -[2023-11-28 07:04:08,902][87424] Updated weights for policy 0, policy_version 261868 (0.0011) -[2023-11-28 07:04:09,191][87426] Updated weights for policy 1, policy_version 261620 (0.0010) -[2023-11-28 07:04:09,292][87424] Updated weights for policy 0, policy_version 261878 (0.0012) -[2023-11-28 07:04:09,566][87426] Updated weights for policy 1, policy_version 261630 (0.0011) -[2023-11-28 07:04:09,661][87424] Updated weights for policy 0, policy_version 261888 (0.0010) -[2023-11-28 07:04:12,001][87424] Updated weights for policy 0, policy_version 261898 (0.0010) -[2023-11-28 07:04:12,056][87426] Updated weights for policy 1, policy_version 261640 (0.0012) -[2023-11-28 07:04:12,389][87424] Updated weights for policy 0, policy_version 261908 (0.0010) -[2023-11-28 07:04:12,433][87426] Updated weights for policy 1, policy_version 261650 (0.0008) -[2023-11-28 07:04:12,775][87424] Updated weights for policy 0, policy_version 261918 (0.0010) -[2023-11-28 07:04:12,814][87426] Updated weights for policy 1, policy_version 261660 (0.0008) -[2023-11-28 07:04:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134037504. Throughput: 0: 2715.2, 1: 2695.3. Samples: 134045952. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:04:13,445][86177] Avg episode reward: [(0, '-602.750'), (1, '-494.490')] -[2023-11-28 07:04:14,767][87426] Updated weights for policy 1, policy_version 261670 (0.0010) -[2023-11-28 07:04:14,982][87424] Updated weights for policy 0, policy_version 261928 (0.0011) -[2023-11-28 07:04:15,142][87426] Updated weights for policy 1, policy_version 261680 (0.0011) -[2023-11-28 07:04:15,374][87424] Updated weights for policy 0, policy_version 261938 (0.0011) -[2023-11-28 07:04:15,522][87426] Updated weights for policy 1, policy_version 261690 (0.0010) -[2023-11-28 07:04:15,760][87424] Updated weights for policy 0, policy_version 261948 (0.0011) -[2023-11-28 07:04:17,702][87426] Updated weights for policy 1, policy_version 261700 (0.0010) -[2023-11-28 07:04:17,833][87424] Updated weights for policy 0, policy_version 261958 (0.0012) -[2023-11-28 07:04:18,091][87426] Updated weights for policy 1, policy_version 261710 (0.0008) -[2023-11-28 07:04:18,222][87424] Updated weights for policy 0, policy_version 261968 (0.0012) -[2023-11-28 07:04:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 134053888. Throughput: 0: 2699.5, 1: 2699.3. Samples: 134070944. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:04:18,446][86177] Avg episode reward: [(0, '-604.130'), (1, '-494.650')] -[2023-11-28 07:04:18,468][87426] Updated weights for policy 1, policy_version 261720 (0.0009) -[2023-11-28 07:04:18,600][87424] Updated weights for policy 0, policy_version 261978 (0.0012) -[2023-11-28 07:04:18,770][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000261728_67002368.pth... -[2023-11-28 07:04:18,800][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000259168_66347008.pth -[2023-11-28 07:04:18,827][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000261984_67067904.pth... -[2023-11-28 07:04:18,875][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000259424_66412544.pth -[2023-11-28 07:04:20,823][87424] Updated weights for policy 0, policy_version 261988 (0.0012) -[2023-11-28 07:04:20,962][87426] Updated weights for policy 1, policy_version 261730 (0.0008) -[2023-11-28 07:04:21,207][87424] Updated weights for policy 0, policy_version 261998 (0.0011) -[2023-11-28 07:04:21,335][87426] Updated weights for policy 1, policy_version 261740 (0.0009) -[2023-11-28 07:04:21,592][87424] Updated weights for policy 0, policy_version 262008 (0.0010) -[2023-11-28 07:04:21,716][87426] Updated weights for policy 1, policy_version 261750 (0.0011) -[2023-11-28 07:04:22,094][87426] Updated weights for policy 1, policy_version 261760 (0.0009) -[2023-11-28 07:04:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134086656. Throughput: 0: 2687.5, 1: 2702.9. Samples: 134103464. Policy #0 lag: (min: 31.0, avg: 58.3, max: 79.0) -[2023-11-28 07:04:23,445][86177] Avg episode reward: [(0, '-569.960'), (1, '-500.180')] -[2023-11-28 07:04:23,911][87424] Updated weights for policy 0, policy_version 262018 (0.0010) -[2023-11-28 07:04:24,294][87424] Updated weights for policy 0, policy_version 262028 (0.0010) -[2023-11-28 07:04:24,422][87426] Updated weights for policy 1, policy_version 261770 (0.0007) -[2023-11-28 07:04:24,678][87424] Updated weights for policy 0, policy_version 262038 (0.0009) -[2023-11-28 07:04:24,803][87426] Updated weights for policy 1, policy_version 261780 (0.0009) -[2023-11-28 07:04:25,053][87424] Updated weights for policy 0, policy_version 262048 (0.0010) -[2023-11-28 07:04:25,184][87426] Updated weights for policy 1, policy_version 261790 (0.0011) -[2023-11-28 07:04:27,380][87424] Updated weights for policy 0, policy_version 262058 (0.0012) -[2023-11-28 07:04:27,483][87426] Updated weights for policy 1, policy_version 261800 (0.0008) -[2023-11-28 07:04:27,757][87424] Updated weights for policy 0, policy_version 262068 (0.0011) -[2023-11-28 07:04:27,863][87426] Updated weights for policy 1, policy_version 261810 (0.0007) -[2023-11-28 07:04:28,143][87424] Updated weights for policy 0, policy_version 262078 (0.0011) -[2023-11-28 07:04:28,240][87426] Updated weights for policy 1, policy_version 261820 (0.0008) -[2023-11-28 07:04:28,444][86177] Fps is (10 sec: 6553.9, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134119424. Throughput: 0: 2686.7, 1: 2708.7. Samples: 134127664. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:04:28,445][86177] Avg episode reward: [(0, '-565.700'), (1, '-503.960')] -[2023-11-28 07:04:30,215][87424] Updated weights for policy 0, policy_version 262088 (0.0011) -[2023-11-28 07:04:30,596][87424] Updated weights for policy 0, policy_version 262098 (0.0010) -[2023-11-28 07:04:30,683][87426] Updated weights for policy 1, policy_version 261830 (0.0011) -[2023-11-28 07:04:30,975][87424] Updated weights for policy 0, policy_version 262108 (0.0008) -[2023-11-28 07:04:31,063][87426] Updated weights for policy 1, policy_version 261840 (0.0011) -[2023-11-28 07:04:31,443][87426] Updated weights for policy 1, policy_version 261850 (0.0012) -[2023-11-28 07:04:33,347][87424] Updated weights for policy 0, policy_version 262118 (0.0012) -[2023-11-28 07:04:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 134135808. Throughput: 0: 2686.0, 1: 2700.9. Samples: 134151748. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:04:33,445][86177] Avg episode reward: [(0, '-525.910'), (1, '-509.420')] -[2023-11-28 07:04:33,520][87426] Updated weights for policy 1, policy_version 261860 (0.0010) -[2023-11-28 07:04:33,728][87424] Updated weights for policy 0, policy_version 262128 (0.0012) -[2023-11-28 07:04:33,900][87426] Updated weights for policy 1, policy_version 261870 (0.0007) -[2023-11-28 07:04:34,106][87424] Updated weights for policy 0, policy_version 262138 (0.0007) -[2023-11-28 07:04:34,284][87426] Updated weights for policy 1, policy_version 261880 (0.0007) -[2023-11-28 07:04:36,185][87424] Updated weights for policy 0, policy_version 262148 (0.0007) -[2023-11-28 07:04:36,278][87426] Updated weights for policy 1, policy_version 261890 (0.0007) -[2023-11-28 07:04:36,565][87424] Updated weights for policy 0, policy_version 262158 (0.0008) -[2023-11-28 07:04:36,666][87426] Updated weights for policy 1, policy_version 261900 (0.0008) -[2023-11-28 07:04:36,955][87424] Updated weights for policy 0, policy_version 262168 (0.0010) -[2023-11-28 07:04:37,059][87426] Updated weights for policy 1, policy_version 261910 (0.0012) -[2023-11-28 07:04:37,429][87426] Updated weights for policy 1, policy_version 261920 (0.0009) -[2023-11-28 07:04:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134168576. Throughput: 0: 2660.1, 1: 2709.9. Samples: 134183876. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:04:38,445][86177] Avg episode reward: [(0, '-549.780'), (1, '-511.350')] -[2023-11-28 07:04:38,966][87424] Updated weights for policy 0, policy_version 262178 (0.0011) -[2023-11-28 07:04:39,336][87424] Updated weights for policy 0, policy_version 262188 (0.0012) -[2023-11-28 07:04:39,716][87424] Updated weights for policy 0, policy_version 262198 (0.0010) -[2023-11-28 07:04:39,884][87426] Updated weights for policy 1, policy_version 261930 (0.0011) -[2023-11-28 07:04:40,104][87424] Updated weights for policy 0, policy_version 262208 (0.0008) -[2023-11-28 07:04:40,256][87426] Updated weights for policy 1, policy_version 261940 (0.0011) -[2023-11-28 07:04:40,645][87426] Updated weights for policy 1, policy_version 261950 (0.0009) -[2023-11-28 07:04:42,677][87424] Updated weights for policy 0, policy_version 262218 (0.0009) -[2023-11-28 07:04:43,061][87424] Updated weights for policy 0, policy_version 262228 (0.0011) -[2023-11-28 07:04:43,082][87426] Updated weights for policy 1, policy_version 261960 (0.0011) -[2023-11-28 07:04:43,443][87424] Updated weights for policy 0, policy_version 262238 (0.0008) -[2023-11-28 07:04:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 134184960. Throughput: 0: 2651.1, 1: 2693.2. Samples: 134206632. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:04:43,445][86177] Avg episode reward: [(0, '-546.120'), (1, '-515.800')] -[2023-11-28 07:04:43,461][87426] Updated weights for policy 1, policy_version 261970 (0.0012) -[2023-11-28 07:04:43,834][87426] Updated weights for policy 1, policy_version 261980 (0.0011) -[2023-11-28 07:04:45,772][87426] Updated weights for policy 1, policy_version 261990 (0.0010) -[2023-11-28 07:04:45,799][87424] Updated weights for policy 0, policy_version 262248 (0.0011) -[2023-11-28 07:04:46,155][87426] Updated weights for policy 1, policy_version 262000 (0.0008) -[2023-11-28 07:04:46,184][87424] Updated weights for policy 0, policy_version 262258 (0.0012) -[2023-11-28 07:04:46,539][87426] Updated weights for policy 1, policy_version 262010 (0.0007) -[2023-11-28 07:04:46,565][87424] Updated weights for policy 0, policy_version 262268 (0.0009) -[2023-11-28 07:04:48,320][87426] Updated weights for policy 1, policy_version 262020 (0.0008) -[2023-11-28 07:04:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 134217728. Throughput: 0: 2668.8, 1: 2681.5. Samples: 134231736. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:04:48,445][86177] Avg episode reward: [(0, '-545.360'), (1, '-520.510')] -[2023-11-28 07:04:48,448][87424] Updated weights for policy 0, policy_version 262278 (0.0009) -[2023-11-28 07:04:48,691][87426] Updated weights for policy 1, policy_version 262030 (0.0008) -[2023-11-28 07:04:48,826][87424] Updated weights for policy 0, policy_version 262288 (0.0008) -[2023-11-28 07:04:49,072][87426] Updated weights for policy 1, policy_version 262040 (0.0010) -[2023-11-28 07:04:49,209][87424] Updated weights for policy 0, policy_version 262298 (0.0011) -[2023-11-28 07:04:51,503][87424] Updated weights for policy 0, policy_version 262308 (0.0010) -[2023-11-28 07:04:51,627][87426] Updated weights for policy 1, policy_version 262050 (0.0011) -[2023-11-28 07:04:51,882][87424] Updated weights for policy 0, policy_version 262318 (0.0010) -[2023-11-28 07:04:52,010][87426] Updated weights for policy 1, policy_version 262060 (0.0010) -[2023-11-28 07:04:52,265][87424] Updated weights for policy 0, policy_version 262328 (0.0011) -[2023-11-28 07:04:52,385][87426] Updated weights for policy 1, policy_version 262070 (0.0011) -[2023-11-28 07:04:52,762][87426] Updated weights for policy 1, policy_version 262080 (0.0012) -[2023-11-28 07:04:53,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134250496. Throughput: 0: 2689.5, 1: 2686.9. Samples: 134263904. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:04:53,445][86177] Avg episode reward: [(0, '-573.770'), (1, '-523.900')] -[2023-11-28 07:04:54,555][87424] Updated weights for policy 0, policy_version 262338 (0.0011) -[2023-11-28 07:04:54,898][87426] Updated weights for policy 1, policy_version 262090 (0.0007) -[2023-11-28 07:04:54,939][87424] Updated weights for policy 0, policy_version 262348 (0.0011) -[2023-11-28 07:04:55,286][87426] Updated weights for policy 1, policy_version 262100 (0.0007) -[2023-11-28 07:04:55,319][87424] Updated weights for policy 0, policy_version 262358 (0.0011) -[2023-11-28 07:04:55,670][87426] Updated weights for policy 1, policy_version 262110 (0.0007) -[2023-11-28 07:04:55,705][87424] Updated weights for policy 0, policy_version 262368 (0.0012) -[2023-11-28 07:04:57,426][87424] Updated weights for policy 0, policy_version 262378 (0.0007) -[2023-11-28 07:04:57,690][87426] Updated weights for policy 1, policy_version 262120 (0.0008) -[2023-11-28 07:04:57,806][87424] Updated weights for policy 0, policy_version 262388 (0.0008) -[2023-11-28 07:04:58,064][87426] Updated weights for policy 1, policy_version 262130 (0.0010) -[2023-11-28 07:04:58,181][87424] Updated weights for policy 0, policy_version 262398 (0.0008) -[2023-11-28 07:04:58,443][87426] Updated weights for policy 1, policy_version 262140 (0.0008) -[2023-11-28 07:04:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 134275072. Throughput: 0: 2703.3, 1: 2687.6. Samples: 134288544. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:04:58,445][86177] Avg episode reward: [(0, '-545.900'), (1, '-535.760')] -[2023-11-28 07:05:00,208][87424] Updated weights for policy 0, policy_version 262408 (0.0009) -[2023-11-28 07:05:00,320][87426] Updated weights for policy 1, policy_version 262150 (0.0010) -[2023-11-28 07:05:00,591][87424] Updated weights for policy 0, policy_version 262418 (0.0009) -[2023-11-28 07:05:00,698][87426] Updated weights for policy 1, policy_version 262160 (0.0012) -[2023-11-28 07:05:00,966][87424] Updated weights for policy 0, policy_version 262428 (0.0009) -[2023-11-28 07:05:01,070][87426] Updated weights for policy 1, policy_version 262170 (0.0008) -[2023-11-28 07:05:02,869][87424] Updated weights for policy 0, policy_version 262438 (0.0011) -[2023-11-28 07:05:03,242][87424] Updated weights for policy 0, policy_version 262448 (0.0012) -[2023-11-28 07:05:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134299648. Throughput: 0: 2707.2, 1: 2678.5. Samples: 134313300. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:05:03,445][86177] Avg episode reward: [(0, '-546.780'), (1, '-556.060')] -[2023-11-28 07:05:03,491][87426] Updated weights for policy 1, policy_version 262180 (0.0011) -[2023-11-28 07:05:03,618][87424] Updated weights for policy 0, policy_version 262458 (0.0011) -[2023-11-28 07:05:03,860][87426] Updated weights for policy 1, policy_version 262190 (0.0007) -[2023-11-28 07:05:04,238][87426] Updated weights for policy 1, policy_version 262200 (0.0007) -[2023-11-28 07:05:05,951][87424] Updated weights for policy 0, policy_version 262468 (0.0009) -[2023-11-28 07:05:06,328][87424] Updated weights for policy 0, policy_version 262478 (0.0007) -[2023-11-28 07:05:06,587][87426] Updated weights for policy 1, policy_version 262210 (0.0009) -[2023-11-28 07:05:06,725][87424] Updated weights for policy 0, policy_version 262488 (0.0008) -[2023-11-28 07:05:06,959][87426] Updated weights for policy 1, policy_version 262220 (0.0009) -[2023-11-28 07:05:07,338][87426] Updated weights for policy 1, policy_version 262230 (0.0008) -[2023-11-28 07:05:07,716][87426] Updated weights for policy 1, policy_version 262240 (0.0009) -[2023-11-28 07:05:08,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134332416. Throughput: 0: 2715.7, 1: 2677.9. Samples: 134346180. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:05:08,446][86177] Avg episode reward: [(0, '-553.110'), (1, '-580.370')] -[2023-11-28 07:05:08,721][87424] Updated weights for policy 0, policy_version 262498 (0.0010) -[2023-11-28 07:05:09,091][87424] Updated weights for policy 0, policy_version 262508 (0.0008) -[2023-11-28 07:05:09,476][87424] Updated weights for policy 0, policy_version 262518 (0.0009) -[2023-11-28 07:05:09,857][87424] Updated weights for policy 0, policy_version 262528 (0.0009) -[2023-11-28 07:05:10,295][87426] Updated weights for policy 1, policy_version 262250 (0.0007) -[2023-11-28 07:05:10,678][87426] Updated weights for policy 1, policy_version 262260 (0.0009) -[2023-11-28 07:05:11,062][87426] Updated weights for policy 1, policy_version 262270 (0.0007) -[2023-11-28 07:05:12,420][87424] Updated weights for policy 0, policy_version 262538 (0.0012) -[2023-11-28 07:05:12,804][87424] Updated weights for policy 0, policy_version 262548 (0.0011) -[2023-11-28 07:05:12,966][87426] Updated weights for policy 1, policy_version 262280 (0.0010) -[2023-11-28 07:05:13,184][87424] Updated weights for policy 0, policy_version 262558 (0.0011) -[2023-11-28 07:05:13,346][87426] Updated weights for policy 1, policy_version 262290 (0.0008) -[2023-11-28 07:05:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 134356992. Throughput: 0: 2713.7, 1: 2685.3. Samples: 134370620. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:05:13,445][86177] Avg episode reward: [(0, '-523.170'), (1, '-579.680')] -[2023-11-28 07:05:13,729][87426] Updated weights for policy 1, policy_version 262300 (0.0007) -[2023-11-28 07:05:15,009][87424] Updated weights for policy 0, policy_version 262568 (0.0012) -[2023-11-28 07:05:15,396][87424] Updated weights for policy 0, policy_version 262578 (0.0012) -[2023-11-28 07:05:15,765][87424] Updated weights for policy 0, policy_version 262588 (0.0012) -[2023-11-28 07:05:16,239][87426] Updated weights for policy 1, policy_version 262310 (0.0010) -[2023-11-28 07:05:16,615][87426] Updated weights for policy 1, policy_version 262320 (0.0012) -[2023-11-28 07:05:16,998][87426] Updated weights for policy 1, policy_version 262330 (0.0012) -[2023-11-28 07:05:17,967][87424] Updated weights for policy 0, policy_version 262598 (0.0010) -[2023-11-28 07:05:18,350][87424] Updated weights for policy 0, policy_version 262608 (0.0008) -[2023-11-28 07:05:18,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 134381568. Throughput: 0: 2734.9, 1: 2671.8. Samples: 134395052. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:05:18,446][86177] Avg episode reward: [(0, '-525.870'), (1, '-573.150')] -[2023-11-28 07:05:18,732][87424] Updated weights for policy 0, policy_version 262618 (0.0008) -[2023-11-28 07:05:19,362][87426] Updated weights for policy 1, policy_version 262340 (0.0010) -[2023-11-28 07:05:19,742][87426] Updated weights for policy 1, policy_version 262350 (0.0008) -[2023-11-28 07:05:20,123][87426] Updated weights for policy 1, policy_version 262360 (0.0008) -[2023-11-28 07:05:21,033][87424] Updated weights for policy 0, policy_version 262628 (0.0011) -[2023-11-28 07:05:21,424][87424] Updated weights for policy 0, policy_version 262638 (0.0009) -[2023-11-28 07:05:21,805][87424] Updated weights for policy 0, policy_version 262648 (0.0008) -[2023-11-28 07:05:22,210][87426] Updated weights for policy 1, policy_version 262370 (0.0010) -[2023-11-28 07:05:22,597][87426] Updated weights for policy 1, policy_version 262380 (0.0010) -[2023-11-28 07:05:22,972][87426] Updated weights for policy 1, policy_version 262390 (0.0010) -[2023-11-28 07:05:23,351][87426] Updated weights for policy 1, policy_version 262400 (0.0008) -[2023-11-28 07:05:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134414336. Throughput: 0: 2741.9, 1: 2647.8. Samples: 134426412. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:05:23,445][86177] Avg episode reward: [(0, '-527.260'), (1, '-568.460')] -[2023-11-28 07:05:24,077][87424] Updated weights for policy 0, policy_version 262658 (0.0010) -[2023-11-28 07:05:24,457][87424] Updated weights for policy 0, policy_version 262668 (0.0011) -[2023-11-28 07:05:24,840][87424] Updated weights for policy 0, policy_version 262678 (0.0009) -[2023-11-28 07:05:25,232][87424] Updated weights for policy 0, policy_version 262688 (0.0009) -[2023-11-28 07:05:25,373][87426] Updated weights for policy 1, policy_version 262410 (0.0011) -[2023-11-28 07:05:25,755][87426] Updated weights for policy 1, policy_version 262420 (0.0012) -[2023-11-28 07:05:26,128][87426] Updated weights for policy 1, policy_version 262430 (0.0011) -[2023-11-28 07:05:27,586][87424] Updated weights for policy 0, policy_version 262698 (0.0011) -[2023-11-28 07:05:27,968][87424] Updated weights for policy 0, policy_version 262708 (0.0011) -[2023-11-28 07:05:27,968][87426] Updated weights for policy 1, policy_version 262440 (0.0010) -[2023-11-28 07:05:28,354][87426] Updated weights for policy 1, policy_version 262450 (0.0007) -[2023-11-28 07:05:28,358][87424] Updated weights for policy 0, policy_version 262718 (0.0012) -[2023-11-28 07:05:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 134438912. Throughput: 0: 2739.5, 1: 2686.4. Samples: 134450796. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:05:28,445][86177] Avg episode reward: [(0, '-524.650'), (1, '-569.030')] -[2023-11-28 07:05:28,736][87426] Updated weights for policy 1, policy_version 262460 (0.0007) -[2023-11-28 07:05:30,599][87424] Updated weights for policy 0, policy_version 262728 (0.0011) -[2023-11-28 07:05:30,973][87424] Updated weights for policy 0, policy_version 262738 (0.0012) -[2023-11-28 07:05:31,088][87426] Updated weights for policy 1, policy_version 262470 (0.0011) -[2023-11-28 07:05:31,355][87424] Updated weights for policy 0, policy_version 262748 (0.0012) -[2023-11-28 07:05:31,472][87426] Updated weights for policy 1, policy_version 262480 (0.0008) -[2023-11-28 07:05:31,848][87426] Updated weights for policy 1, policy_version 262490 (0.0011) -[2023-11-28 07:05:33,421][87424] Updated weights for policy 0, policy_version 262758 (0.0010) -[2023-11-28 07:05:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134463488. Throughput: 0: 2730.7, 1: 2680.6. Samples: 134475244. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:05:33,445][86177] Avg episode reward: [(0, '-520.470'), (1, '-563.400')] -[2023-11-28 07:05:33,794][87424] Updated weights for policy 0, policy_version 262768 (0.0009) -[2023-11-28 07:05:34,186][87424] Updated weights for policy 0, policy_version 262778 (0.0009) -[2023-11-28 07:05:34,317][87426] Updated weights for policy 1, policy_version 262500 (0.0012) -[2023-11-28 07:05:34,696][87426] Updated weights for policy 1, policy_version 262510 (0.0011) -[2023-11-28 07:05:35,076][87426] Updated weights for policy 1, policy_version 262520 (0.0012) -[2023-11-28 07:05:36,393][87424] Updated weights for policy 0, policy_version 262788 (0.0010) -[2023-11-28 07:05:36,785][87424] Updated weights for policy 0, policy_version 262798 (0.0009) -[2023-11-28 07:05:37,107][87426] Updated weights for policy 1, policy_version 262530 (0.0011) -[2023-11-28 07:05:37,156][87424] Updated weights for policy 0, policy_version 262808 (0.0010) -[2023-11-28 07:05:37,487][87426] Updated weights for policy 1, policy_version 262540 (0.0011) -[2023-11-28 07:05:37,856][87426] Updated weights for policy 1, policy_version 262550 (0.0012) -[2023-11-28 07:05:38,236][87426] Updated weights for policy 1, policy_version 262560 (0.0012) -[2023-11-28 07:05:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 134496256. Throughput: 0: 2757.6, 1: 2691.2. Samples: 134509100. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:05:38,445][86177] Avg episode reward: [(0, '-527.860'), (1, '-566.410')] -[2023-11-28 07:05:39,211][87424] Updated weights for policy 0, policy_version 262818 (0.0011) -[2023-11-28 07:05:39,586][87424] Updated weights for policy 0, policy_version 262828 (0.0011) -[2023-11-28 07:05:39,978][87424] Updated weights for policy 0, policy_version 262838 (0.0011) -[2023-11-28 07:05:40,349][87424] Updated weights for policy 0, policy_version 262848 (0.0012) -[2023-11-28 07:05:40,752][87426] Updated weights for policy 1, policy_version 262570 (0.0009) -[2023-11-28 07:05:41,134][87426] Updated weights for policy 1, policy_version 262580 (0.0008) -[2023-11-28 07:05:41,508][87426] Updated weights for policy 1, policy_version 262590 (0.0012) -[2023-11-28 07:05:42,536][87424] Updated weights for policy 0, policy_version 262858 (0.0009) -[2023-11-28 07:05:42,916][87424] Updated weights for policy 0, policy_version 262868 (0.0009) -[2023-11-28 07:05:43,310][87424] Updated weights for policy 0, policy_version 262878 (0.0009) -[2023-11-28 07:05:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 134520832. Throughput: 0: 2761.5, 1: 2672.4. Samples: 134533068. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:05:43,445][86177] Avg episode reward: [(0, '-572.980'), (1, '-555.120')] -[2023-11-28 07:05:43,831][87426] Updated weights for policy 1, policy_version 262600 (0.0012) -[2023-11-28 07:05:44,218][87426] Updated weights for policy 1, policy_version 262610 (0.0012) -[2023-11-28 07:05:44,596][87426] Updated weights for policy 1, policy_version 262620 (0.0011) -[2023-11-28 07:05:45,383][87424] Updated weights for policy 0, policy_version 262888 (0.0009) -[2023-11-28 07:05:45,767][87424] Updated weights for policy 0, policy_version 262898 (0.0011) -[2023-11-28 07:05:46,145][87424] Updated weights for policy 0, policy_version 262908 (0.0010) -[2023-11-28 07:05:46,587][87426] Updated weights for policy 1, policy_version 262630 (0.0012) -[2023-11-28 07:05:46,967][87426] Updated weights for policy 1, policy_version 262640 (0.0012) -[2023-11-28 07:05:47,349][87426] Updated weights for policy 1, policy_version 262650 (0.0009) -[2023-11-28 07:05:48,251][87424] Updated weights for policy 0, policy_version 262918 (0.0008) -[2023-11-28 07:05:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134545408. Throughput: 0: 2752.4, 1: 2680.6. Samples: 134557788. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:05:48,445][86177] Avg episode reward: [(0, '-618.990'), (1, '-536.920')] -[2023-11-28 07:05:48,631][87424] Updated weights for policy 0, policy_version 262928 (0.0007) -[2023-11-28 07:05:49,013][87424] Updated weights for policy 0, policy_version 262938 (0.0008) -[2023-11-28 07:05:49,860][87426] Updated weights for policy 1, policy_version 262660 (0.0008) -[2023-11-28 07:05:50,244][87426] Updated weights for policy 1, policy_version 262670 (0.0012) -[2023-11-28 07:05:50,616][87426] Updated weights for policy 1, policy_version 262680 (0.0009) -[2023-11-28 07:05:51,284][87424] Updated weights for policy 0, policy_version 262948 (0.0008) -[2023-11-28 07:05:51,660][87424] Updated weights for policy 0, policy_version 262958 (0.0009) -[2023-11-28 07:05:52,045][87424] Updated weights for policy 0, policy_version 262968 (0.0011) -[2023-11-28 07:05:52,917][87426] Updated weights for policy 1, policy_version 262690 (0.0008) -[2023-11-28 07:05:53,286][87426] Updated weights for policy 1, policy_version 262700 (0.0009) -[2023-11-28 07:05:53,449][86177] Fps is (10 sec: 4913.0, 60 sec: 5324.4, 300 sec: 5415.0). Total num frames: 134569984. Throughput: 0: 2748.0, 1: 2672.0. Samples: 134590104. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:05:53,456][86177] Avg episode reward: [(0, '-625.370'), (1, '-528.590')] -[2023-11-28 07:05:53,662][87426] Updated weights for policy 1, policy_version 262710 (0.0009) -[2023-11-28 07:05:54,041][87426] Updated weights for policy 1, policy_version 262720 (0.0010) -[2023-11-28 07:05:54,451][87424] Updated weights for policy 0, policy_version 262978 (0.0011) -[2023-11-28 07:05:54,837][87424] Updated weights for policy 0, policy_version 262988 (0.0012) -[2023-11-28 07:05:55,209][87424] Updated weights for policy 0, policy_version 262998 (0.0012) -[2023-11-28 07:05:55,590][87424] Updated weights for policy 0, policy_version 263008 (0.0008) -[2023-11-28 07:05:55,943][87426] Updated weights for policy 1, policy_version 262730 (0.0011) -[2023-11-28 07:05:56,332][87426] Updated weights for policy 1, policy_version 262740 (0.0012) -[2023-11-28 07:05:56,715][87426] Updated weights for policy 1, policy_version 262750 (0.0012) -[2023-11-28 07:05:57,244][87424] Updated weights for policy 0, policy_version 263018 (0.0008) -[2023-11-28 07:05:57,630][87424] Updated weights for policy 0, policy_version 263028 (0.0007) -[2023-11-28 07:05:58,016][87424] Updated weights for policy 0, policy_version 263038 (0.0007) -[2023-11-28 07:05:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 134602752. Throughput: 0: 2754.2, 1: 2668.4. Samples: 134614640. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:05:58,445][86177] Avg episode reward: [(0, '-615.060'), (1, '-561.580')] -[2023-11-28 07:05:58,761][87426] Updated weights for policy 1, policy_version 262760 (0.0008) -[2023-11-28 07:05:59,141][87426] Updated weights for policy 1, policy_version 262770 (0.0008) -[2023-11-28 07:05:59,521][87426] Updated weights for policy 1, policy_version 262780 (0.0011) -[2023-11-28 07:06:00,361][87424] Updated weights for policy 0, policy_version 263048 (0.0009) -[2023-11-28 07:06:00,745][87424] Updated weights for policy 0, policy_version 263058 (0.0011) -[2023-11-28 07:06:01,118][87424] Updated weights for policy 0, policy_version 263068 (0.0010) -[2023-11-28 07:06:01,745][87426] Updated weights for policy 1, policy_version 262790 (0.0010) -[2023-11-28 07:06:02,128][87426] Updated weights for policy 1, policy_version 262800 (0.0008) -[2023-11-28 07:06:02,509][87426] Updated weights for policy 1, policy_version 262810 (0.0008) -[2023-11-28 07:06:03,356][87424] Updated weights for policy 0, policy_version 263078 (0.0008) -[2023-11-28 07:06:03,444][86177] Fps is (10 sec: 5737.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134627328. Throughput: 0: 2734.7, 1: 2686.7. Samples: 134639012. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:03,445][86177] Avg episode reward: [(0, '-530.750'), (1, '-546.940')] -[2023-11-28 07:06:03,738][87424] Updated weights for policy 0, policy_version 263088 (0.0010) -[2023-11-28 07:06:04,119][87424] Updated weights for policy 0, policy_version 263098 (0.0007) -[2023-11-28 07:06:04,752][87426] Updated weights for policy 1, policy_version 262820 (0.0009) -[2023-11-28 07:06:05,133][87426] Updated weights for policy 1, policy_version 262830 (0.0010) -[2023-11-28 07:06:05,508][87426] Updated weights for policy 1, policy_version 262840 (0.0007) -[2023-11-28 07:06:05,742][87424] Updated weights for policy 0, policy_version 263108 (0.0007) -[2023-11-28 07:06:06,127][87424] Updated weights for policy 0, policy_version 263118 (0.0007) -[2023-11-28 07:06:06,511][87424] Updated weights for policy 0, policy_version 263128 (0.0007) -[2023-11-28 07:06:07,496][87426] Updated weights for policy 1, policy_version 262850 (0.0008) -[2023-11-28 07:06:07,873][87426] Updated weights for policy 1, policy_version 262860 (0.0008) -[2023-11-28 07:06:08,257][87426] Updated weights for policy 1, policy_version 262870 (0.0007) -[2023-11-28 07:06:08,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 134651904. Throughput: 0: 2744.3, 1: 2734.5. Samples: 134672956. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:08,446][86177] Avg episode reward: [(0, '-555.310'), (1, '-549.690')] -[2023-11-28 07:06:08,638][87426] Updated weights for policy 1, policy_version 262880 (0.0008) -[2023-11-28 07:06:08,852][87424] Updated weights for policy 0, policy_version 263138 (0.0009) -[2023-11-28 07:06:09,237][87424] Updated weights for policy 0, policy_version 263148 (0.0008) -[2023-11-28 07:06:09,622][87424] Updated weights for policy 0, policy_version 263158 (0.0008) -[2023-11-28 07:06:10,001][87424] Updated weights for policy 0, policy_version 263168 (0.0010) -[2023-11-28 07:06:10,954][87426] Updated weights for policy 1, policy_version 262890 (0.0012) -[2023-11-28 07:06:11,324][87426] Updated weights for policy 1, policy_version 262900 (0.0012) -[2023-11-28 07:06:11,695][87426] Updated weights for policy 1, policy_version 262910 (0.0011) -[2023-11-28 07:06:11,910][87424] Updated weights for policy 0, policy_version 263178 (0.0010) -[2023-11-28 07:06:12,291][87424] Updated weights for policy 0, policy_version 263188 (0.0010) -[2023-11-28 07:06:12,679][87424] Updated weights for policy 0, policy_version 263198 (0.0008) -[2023-11-28 07:06:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 134684672. Throughput: 0: 2751.7, 1: 2721.7. Samples: 134697100. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:13,445][86177] Avg episode reward: [(0, '-558.800'), (1, '-590.200')] -[2023-11-28 07:06:13,855][87426] Updated weights for policy 1, policy_version 262920 (0.0011) -[2023-11-28 07:06:14,234][87426] Updated weights for policy 1, policy_version 262930 (0.0012) -[2023-11-28 07:06:14,621][87426] Updated weights for policy 1, policy_version 262940 (0.0008) -[2023-11-28 07:06:15,084][87424] Updated weights for policy 0, policy_version 263208 (0.0011) -[2023-11-28 07:06:15,458][87424] Updated weights for policy 0, policy_version 263218 (0.0012) -[2023-11-28 07:06:15,835][87424] Updated weights for policy 0, policy_version 263228 (0.0012) -[2023-11-28 07:06:16,839][87426] Updated weights for policy 1, policy_version 262950 (0.0009) -[2023-11-28 07:06:17,215][87426] Updated weights for policy 1, policy_version 262960 (0.0007) -[2023-11-28 07:06:17,595][87426] Updated weights for policy 1, policy_version 262970 (0.0010) -[2023-11-28 07:06:17,904][87424] Updated weights for policy 0, policy_version 263238 (0.0011) -[2023-11-28 07:06:18,281][87424] Updated weights for policy 0, policy_version 263248 (0.0011) -[2023-11-28 07:06:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 134709248. Throughput: 0: 2747.1, 1: 2719.3. Samples: 134721232. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:18,445][86177] Avg episode reward: [(0, '-565.660'), (1, '-558.310')] -[2023-11-28 07:06:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000262976_67321856.pth... -[2023-11-28 07:06:18,494][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000260448_66674688.pth -[2023-11-28 07:06:18,660][87424] Updated weights for policy 0, policy_version 263258 (0.0008) -[2023-11-28 07:06:18,891][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000263264_67395584.pth... -[2023-11-28 07:06:18,923][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000260704_66740224.pth -[2023-11-28 07:06:19,632][87426] Updated weights for policy 1, policy_version 262980 (0.0009) -[2023-11-28 07:06:20,004][87426] Updated weights for policy 1, policy_version 262990 (0.0010) -[2023-11-28 07:06:20,380][87426] Updated weights for policy 1, policy_version 263000 (0.0008) -[2023-11-28 07:06:20,991][87424] Updated weights for policy 0, policy_version 263268 (0.0009) -[2023-11-28 07:06:21,374][87424] Updated weights for policy 0, policy_version 263278 (0.0012) -[2023-11-28 07:06:21,749][87424] Updated weights for policy 0, policy_version 263288 (0.0011) -[2023-11-28 07:06:23,005][87426] Updated weights for policy 1, policy_version 263010 (0.0009) -[2023-11-28 07:06:23,384][87426] Updated weights for policy 1, policy_version 263020 (0.0012) -[2023-11-28 07:06:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 134733824. Throughput: 0: 2726.8, 1: 2703.6. Samples: 134753468. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:23,445][86177] Avg episode reward: [(0, '-566.440'), (1, '-576.360')] -[2023-11-28 07:06:23,685][87424] Updated weights for policy 0, policy_version 263298 (0.0010) -[2023-11-28 07:06:23,752][87426] Updated weights for policy 1, policy_version 263030 (0.0010) -[2023-11-28 07:06:24,078][87424] Updated weights for policy 0, policy_version 263308 (0.0009) -[2023-11-28 07:06:24,124][87426] Updated weights for policy 1, policy_version 263040 (0.0007) -[2023-11-28 07:06:24,447][87424] Updated weights for policy 0, policy_version 263318 (0.0007) -[2023-11-28 07:06:24,829][87424] Updated weights for policy 0, policy_version 263328 (0.0008) -[2023-11-28 07:06:26,693][87426] Updated weights for policy 1, policy_version 263050 (0.0007) -[2023-11-28 07:06:27,075][87426] Updated weights for policy 1, policy_version 263060 (0.0007) -[2023-11-28 07:06:27,322][87424] Updated weights for policy 0, policy_version 263338 (0.0009) -[2023-11-28 07:06:27,462][87426] Updated weights for policy 1, policy_version 263070 (0.0007) -[2023-11-28 07:06:27,709][87424] Updated weights for policy 0, policy_version 263348 (0.0007) -[2023-11-28 07:06:28,088][87424] Updated weights for policy 0, policy_version 263358 (0.0008) -[2023-11-28 07:06:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 134766592. Throughput: 0: 2729.1, 1: 2699.2. Samples: 134777340. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:28,445][86177] Avg episode reward: [(0, '-535.030'), (1, '-577.990')] -[2023-11-28 07:06:29,692][87426] Updated weights for policy 1, policy_version 263080 (0.0011) -[2023-11-28 07:06:29,938][87424] Updated weights for policy 0, policy_version 263368 (0.0011) -[2023-11-28 07:06:30,074][87426] Updated weights for policy 1, policy_version 263090 (0.0010) -[2023-11-28 07:06:30,320][87424] Updated weights for policy 0, policy_version 263378 (0.0011) -[2023-11-28 07:06:30,462][87426] Updated weights for policy 1, policy_version 263100 (0.0010) -[2023-11-28 07:06:30,706][87424] Updated weights for policy 0, policy_version 263388 (0.0011) -[2023-11-28 07:06:32,187][87426] Updated weights for policy 1, policy_version 263110 (0.0011) -[2023-11-28 07:06:32,564][87426] Updated weights for policy 1, policy_version 263120 (0.0012) -[2023-11-28 07:06:32,654][87424] Updated weights for policy 0, policy_version 263398 (0.0012) -[2023-11-28 07:06:32,941][87426] Updated weights for policy 1, policy_version 263130 (0.0011) -[2023-11-28 07:06:33,029][87424] Updated weights for policy 0, policy_version 263408 (0.0012) -[2023-11-28 07:06:33,410][87424] Updated weights for policy 0, policy_version 263418 (0.0011) -[2023-11-28 07:06:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134791168. Throughput: 0: 2746.4, 1: 2692.7. Samples: 134802548. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:33,445][86177] Avg episode reward: [(0, '-546.560'), (1, '-570.460')] -[2023-11-28 07:06:35,089][87426] Updated weights for policy 1, policy_version 263140 (0.0011) -[2023-11-28 07:06:35,471][87426] Updated weights for policy 1, policy_version 263150 (0.0009) -[2023-11-28 07:06:35,851][87426] Updated weights for policy 1, policy_version 263160 (0.0007) -[2023-11-28 07:06:35,882][87424] Updated weights for policy 0, policy_version 263428 (0.0010) -[2023-11-28 07:06:36,263][87424] Updated weights for policy 0, policy_version 263438 (0.0007) -[2023-11-28 07:06:36,649][87424] Updated weights for policy 0, policy_version 263448 (0.0007) -[2023-11-28 07:06:38,184][87426] Updated weights for policy 1, policy_version 263170 (0.0008) -[2023-11-28 07:06:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 134815744. Throughput: 0: 2745.3, 1: 2721.1. Samples: 134836068. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:38,445][86177] Avg episode reward: [(0, '-559.920'), (1, '-571.200')] -[2023-11-28 07:06:38,561][87426] Updated weights for policy 1, policy_version 263180 (0.0009) -[2023-11-28 07:06:38,939][87426] Updated weights for policy 1, policy_version 263190 (0.0008) -[2023-11-28 07:06:39,112][87424] Updated weights for policy 0, policy_version 263458 (0.0008) -[2023-11-28 07:06:39,321][87426] Updated weights for policy 1, policy_version 263200 (0.0008) -[2023-11-28 07:06:39,506][87424] Updated weights for policy 0, policy_version 263468 (0.0010) -[2023-11-28 07:06:39,884][87424] Updated weights for policy 0, policy_version 263478 (0.0011) -[2023-11-28 07:06:40,267][87424] Updated weights for policy 0, policy_version 263488 (0.0012) -[2023-11-28 07:06:41,332][87426] Updated weights for policy 1, policy_version 263210 (0.0012) -[2023-11-28 07:06:41,721][87426] Updated weights for policy 1, policy_version 263220 (0.0012) -[2023-11-28 07:06:42,098][87426] Updated weights for policy 1, policy_version 263230 (0.0011) -[2023-11-28 07:06:42,402][87424] Updated weights for policy 0, policy_version 263498 (0.0012) -[2023-11-28 07:06:42,779][87424] Updated weights for policy 0, policy_version 263508 (0.0012) -[2023-11-28 07:06:43,167][87424] Updated weights for policy 0, policy_version 263518 (0.0012) -[2023-11-28 07:06:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 134848512. Throughput: 0: 2740.0, 1: 2702.7. Samples: 134859560. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:43,445][86177] Avg episode reward: [(0, '-559.350'), (1, '-569.470')] -[2023-11-28 07:06:44,211][87426] Updated weights for policy 1, policy_version 263240 (0.0011) -[2023-11-28 07:06:44,581][87426] Updated weights for policy 1, policy_version 263250 (0.0009) -[2023-11-28 07:06:44,965][87426] Updated weights for policy 1, policy_version 263260 (0.0010) -[2023-11-28 07:06:45,364][87424] Updated weights for policy 0, policy_version 263528 (0.0009) -[2023-11-28 07:06:45,744][87424] Updated weights for policy 0, policy_version 263538 (0.0007) -[2023-11-28 07:06:46,128][87424] Updated weights for policy 0, policy_version 263548 (0.0008) -[2023-11-28 07:06:46,943][87426] Updated weights for policy 1, policy_version 263270 (0.0008) -[2023-11-28 07:06:47,321][87426] Updated weights for policy 1, policy_version 263280 (0.0007) -[2023-11-28 07:06:47,709][87426] Updated weights for policy 1, policy_version 263290 (0.0007) -[2023-11-28 07:06:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134873088. Throughput: 0: 2745.2, 1: 2720.9. Samples: 134884988. Policy #0 lag: (min: 33.0, avg: 53.8, max: 82.0) -[2023-11-28 07:06:48,445][86177] Avg episode reward: [(0, '-569.160'), (1, '-588.500')] -[2023-11-28 07:06:48,482][87424] Updated weights for policy 0, policy_version 263558 (0.0010) -[2023-11-28 07:06:48,846][87424] Updated weights for policy 0, policy_version 263568 (0.0011) -[2023-11-28 07:06:49,229][87424] Updated weights for policy 0, policy_version 263578 (0.0012) -[2023-11-28 07:06:49,496][87426] Updated weights for policy 1, policy_version 263300 (0.0008) -[2023-11-28 07:06:49,875][87426] Updated weights for policy 1, policy_version 263310 (0.0012) -[2023-11-28 07:06:50,247][87426] Updated weights for policy 1, policy_version 263320 (0.0012) -[2023-11-28 07:06:51,289][87424] Updated weights for policy 0, policy_version 263588 (0.0010) -[2023-11-28 07:06:51,671][87424] Updated weights for policy 0, policy_version 263598 (0.0011) -[2023-11-28 07:06:52,053][87424] Updated weights for policy 0, policy_version 263608 (0.0011) -[2023-11-28 07:06:52,723][87426] Updated weights for policy 1, policy_version 263330 (0.0009) -[2023-11-28 07:06:53,096][87426] Updated weights for policy 1, policy_version 263340 (0.0009) -[2023-11-28 07:06:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.7, 300 sec: 5415.0). Total num frames: 134897664. Throughput: 0: 2731.7, 1: 2677.5. Samples: 134916368. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:06:53,445][86177] Avg episode reward: [(0, '-560.790'), (1, '-607.550')] -[2023-11-28 07:06:53,479][87426] Updated weights for policy 1, policy_version 263350 (0.0009) -[2023-11-28 07:06:53,857][87426] Updated weights for policy 1, policy_version 263360 (0.0010) -[2023-11-28 07:06:54,453][87424] Updated weights for policy 0, policy_version 263618 (0.0011) -[2023-11-28 07:06:54,842][87424] Updated weights for policy 0, policy_version 263628 (0.0012) -[2023-11-28 07:06:55,230][87424] Updated weights for policy 0, policy_version 263638 (0.0012) -[2023-11-28 07:06:55,598][87424] Updated weights for policy 0, policy_version 263648 (0.0012) -[2023-11-28 07:06:55,949][87426] Updated weights for policy 1, policy_version 263370 (0.0012) -[2023-11-28 07:06:56,332][87426] Updated weights for policy 1, policy_version 263380 (0.0011) -[2023-11-28 07:06:56,713][87426] Updated weights for policy 1, policy_version 263390 (0.0012) -[2023-11-28 07:06:57,655][87424] Updated weights for policy 0, policy_version 263658 (0.0011) -[2023-11-28 07:06:58,037][87424] Updated weights for policy 0, policy_version 263668 (0.0010) -[2023-11-28 07:06:58,422][87424] Updated weights for policy 0, policy_version 263678 (0.0007) -[2023-11-28 07:06:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 134922240. Throughput: 0: 2724.3, 1: 2699.2. Samples: 134941156. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:06:58,445][86177] Avg episode reward: [(0, '-568.960'), (1, '-602.460')] -[2023-11-28 07:06:58,906][87426] Updated weights for policy 1, policy_version 263400 (0.0012) -[2023-11-28 07:06:59,285][87426] Updated weights for policy 1, policy_version 263410 (0.0011) -[2023-11-28 07:06:59,657][87426] Updated weights for policy 1, policy_version 263420 (0.0011) -[2023-11-28 07:07:01,031][87424] Updated weights for policy 0, policy_version 263688 (0.0011) -[2023-11-28 07:07:01,421][87424] Updated weights for policy 0, policy_version 263698 (0.0012) -[2023-11-28 07:07:01,808][87424] Updated weights for policy 0, policy_version 263708 (0.0011) -[2023-11-28 07:07:01,895][87426] Updated weights for policy 1, policy_version 263430 (0.0011) -[2023-11-28 07:07:02,271][87426] Updated weights for policy 1, policy_version 263440 (0.0012) -[2023-11-28 07:07:02,648][87426] Updated weights for policy 1, policy_version 263450 (0.0011) -[2023-11-28 07:07:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 134955008. Throughput: 0: 2706.3, 1: 2710.3. Samples: 134964980. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:03,445][86177] Avg episode reward: [(0, '-566.370'), (1, '-605.140')] -[2023-11-28 07:07:03,856][87424] Updated weights for policy 0, policy_version 263718 (0.0011) -[2023-11-28 07:07:04,233][87424] Updated weights for policy 0, policy_version 263728 (0.0011) -[2023-11-28 07:07:04,588][87426] Updated weights for policy 1, policy_version 263460 (0.0012) -[2023-11-28 07:07:04,622][87424] Updated weights for policy 0, policy_version 263738 (0.0010) -[2023-11-28 07:07:04,969][87426] Updated weights for policy 1, policy_version 263470 (0.0011) -[2023-11-28 07:07:05,352][87426] Updated weights for policy 1, policy_version 263480 (0.0012) -[2023-11-28 07:07:06,829][87424] Updated weights for policy 0, policy_version 263748 (0.0009) -[2023-11-28 07:07:07,209][87424] Updated weights for policy 0, policy_version 263758 (0.0011) -[2023-11-28 07:07:07,594][87424] Updated weights for policy 0, policy_version 263768 (0.0011) -[2023-11-28 07:07:07,878][87426] Updated weights for policy 1, policy_version 263490 (0.0011) -[2023-11-28 07:07:08,254][87426] Updated weights for policy 1, policy_version 263500 (0.0012) -[2023-11-28 07:07:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 134979584. Throughput: 0: 2697.4, 1: 2715.7. Samples: 134997060. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:08,445][86177] Avg episode reward: [(0, '-555.790'), (1, '-605.530')] -[2023-11-28 07:07:08,640][87426] Updated weights for policy 1, policy_version 263510 (0.0012) -[2023-11-28 07:07:09,021][87426] Updated weights for policy 1, policy_version 263520 (0.0011) -[2023-11-28 07:07:09,527][87424] Updated weights for policy 0, policy_version 263778 (0.0011) -[2023-11-28 07:07:09,914][87424] Updated weights for policy 0, policy_version 263788 (0.0011) -[2023-11-28 07:07:10,290][87424] Updated weights for policy 0, policy_version 263798 (0.0010) -[2023-11-28 07:07:10,672][87424] Updated weights for policy 0, policy_version 263808 (0.0012) -[2023-11-28 07:07:11,545][87426] Updated weights for policy 1, policy_version 263530 (0.0012) -[2023-11-28 07:07:11,915][87426] Updated weights for policy 1, policy_version 263540 (0.0012) -[2023-11-28 07:07:12,298][87426] Updated weights for policy 1, policy_version 263550 (0.0012) -[2023-11-28 07:07:13,153][87424] Updated weights for policy 0, policy_version 263818 (0.0012) -[2023-11-28 07:07:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 135004160. Throughput: 0: 2695.5, 1: 2725.1. Samples: 135021264. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:13,445][86177] Avg episode reward: [(0, '-568.560'), (1, '-600.800')] -[2023-11-28 07:07:13,544][87424] Updated weights for policy 0, policy_version 263828 (0.0012) -[2023-11-28 07:07:13,923][87424] Updated weights for policy 0, policy_version 263838 (0.0013) -[2023-11-28 07:07:14,665][87426] Updated weights for policy 1, policy_version 263560 (0.0012) -[2023-11-28 07:07:15,038][87426] Updated weights for policy 1, policy_version 263570 (0.0009) -[2023-11-28 07:07:15,413][87426] Updated weights for policy 1, policy_version 263580 (0.0008) -[2023-11-28 07:07:15,883][87424] Updated weights for policy 0, policy_version 263848 (0.0010) -[2023-11-28 07:07:16,274][87424] Updated weights for policy 0, policy_version 263858 (0.0010) -[2023-11-28 07:07:16,657][87424] Updated weights for policy 0, policy_version 263868 (0.0008) -[2023-11-28 07:07:17,883][87426] Updated weights for policy 1, policy_version 263590 (0.0008) -[2023-11-28 07:07:18,265][87426] Updated weights for policy 1, policy_version 263600 (0.0008) -[2023-11-28 07:07:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 135028736. Throughput: 0: 2677.2, 1: 2714.8. Samples: 135045192. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:18,445][86177] Avg episode reward: [(0, '-542.900'), (1, '-584.720')] -[2023-11-28 07:07:18,642][87426] Updated weights for policy 1, policy_version 263610 (0.0010) -[2023-11-28 07:07:19,085][87424] Updated weights for policy 0, policy_version 263878 (0.0007) -[2023-11-28 07:07:19,470][87424] Updated weights for policy 0, policy_version 263888 (0.0008) -[2023-11-28 07:07:19,861][87424] Updated weights for policy 0, policy_version 263898 (0.0008) -[2023-11-28 07:07:21,164][87426] Updated weights for policy 1, policy_version 263620 (0.0010) -[2023-11-28 07:07:21,530][87426] Updated weights for policy 1, policy_version 263630 (0.0012) -[2023-11-28 07:07:21,908][87426] Updated weights for policy 1, policy_version 263640 (0.0011) -[2023-11-28 07:07:21,930][87424] Updated weights for policy 0, policy_version 263908 (0.0010) -[2023-11-28 07:07:22,314][87424] Updated weights for policy 0, policy_version 263918 (0.0011) -[2023-11-28 07:07:22,695][87424] Updated weights for policy 0, policy_version 263928 (0.0012) -[2023-11-28 07:07:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 135061504. Throughput: 0: 2688.9, 1: 2658.4. Samples: 135076696. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:23,445][86177] Avg episode reward: [(0, '-591.610'), (1, '-573.700')] -[2023-11-28 07:07:23,812][87426] Updated weights for policy 1, policy_version 263650 (0.0011) -[2023-11-28 07:07:24,197][87426] Updated weights for policy 1, policy_version 263660 (0.0010) -[2023-11-28 07:07:24,570][87426] Updated weights for policy 1, policy_version 263670 (0.0011) -[2023-11-28 07:07:24,709][87424] Updated weights for policy 0, policy_version 263938 (0.0012) -[2023-11-28 07:07:24,952][87426] Updated weights for policy 1, policy_version 263680 (0.0009) -[2023-11-28 07:07:25,083][87424] Updated weights for policy 0, policy_version 263948 (0.0012) -[2023-11-28 07:07:25,468][87424] Updated weights for policy 0, policy_version 263958 (0.0012) -[2023-11-28 07:07:25,854][87424] Updated weights for policy 0, policy_version 263968 (0.0012) -[2023-11-28 07:07:27,118][87426] Updated weights for policy 1, policy_version 263690 (0.0007) -[2023-11-28 07:07:27,503][87426] Updated weights for policy 1, policy_version 263700 (0.0007) -[2023-11-28 07:07:27,887][87426] Updated weights for policy 1, policy_version 263710 (0.0007) -[2023-11-28 07:07:28,393][87424] Updated weights for policy 0, policy_version 263978 (0.0007) -[2023-11-28 07:07:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 135086080. Throughput: 0: 2690.7, 1: 2693.5. Samples: 135101848. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:28,445][86177] Avg episode reward: [(0, '-583.670'), (1, '-571.590')] -[2023-11-28 07:07:28,776][87424] Updated weights for policy 0, policy_version 263988 (0.0007) -[2023-11-28 07:07:29,159][87424] Updated weights for policy 0, policy_version 263998 (0.0008) -[2023-11-28 07:07:29,593][87426] Updated weights for policy 1, policy_version 263720 (0.0011) -[2023-11-28 07:07:29,964][87426] Updated weights for policy 1, policy_version 263730 (0.0011) -[2023-11-28 07:07:30,349][87426] Updated weights for policy 1, policy_version 263740 (0.0011) -[2023-11-28 07:07:31,502][87424] Updated weights for policy 0, policy_version 264008 (0.0011) -[2023-11-28 07:07:31,881][87424] Updated weights for policy 0, policy_version 264018 (0.0009) -[2023-11-28 07:07:32,178][87426] Updated weights for policy 1, policy_version 263750 (0.0012) -[2023-11-28 07:07:32,261][87424] Updated weights for policy 0, policy_version 264028 (0.0010) -[2023-11-28 07:07:32,560][87426] Updated weights for policy 1, policy_version 263760 (0.0011) -[2023-11-28 07:07:32,931][87426] Updated weights for policy 1, policy_version 263770 (0.0011) -[2023-11-28 07:07:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 135118848. Throughput: 0: 2678.9, 1: 2679.7. Samples: 135126124. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:33,445][86177] Avg episode reward: [(0, '-597.720'), (1, '-567.270')] -[2023-11-28 07:07:34,159][87424] Updated weights for policy 0, policy_version 264038 (0.0010) -[2023-11-28 07:07:34,538][87424] Updated weights for policy 0, policy_version 264048 (0.0011) -[2023-11-28 07:07:34,918][87424] Updated weights for policy 0, policy_version 264058 (0.0012) -[2023-11-28 07:07:35,475][87426] Updated weights for policy 1, policy_version 263780 (0.0011) -[2023-11-28 07:07:35,856][87426] Updated weights for policy 1, policy_version 263790 (0.0011) -[2023-11-28 07:07:36,228][87426] Updated weights for policy 1, policy_version 263800 (0.0012) -[2023-11-28 07:07:36,886][87424] Updated weights for policy 0, policy_version 264068 (0.0012) -[2023-11-28 07:07:37,260][87424] Updated weights for policy 0, policy_version 264078 (0.0011) -[2023-11-28 07:07:37,637][87424] Updated weights for policy 0, policy_version 264088 (0.0012) -[2023-11-28 07:07:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 135143424. Throughput: 0: 2687.8, 1: 2688.0. Samples: 135158280. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:38,445][86177] Avg episode reward: [(0, '-589.440'), (1, '-564.120')] -[2023-11-28 07:07:38,773][87426] Updated weights for policy 1, policy_version 263810 (0.0012) -[2023-11-28 07:07:39,162][87426] Updated weights for policy 1, policy_version 263820 (0.0011) -[2023-11-28 07:07:39,544][87426] Updated weights for policy 1, policy_version 263830 (0.0008) -[2023-11-28 07:07:39,926][87426] Updated weights for policy 1, policy_version 263840 (0.0008) -[2023-11-28 07:07:40,218][87424] Updated weights for policy 0, policy_version 264098 (0.0009) -[2023-11-28 07:07:40,599][87424] Updated weights for policy 0, policy_version 264108 (0.0009) -[2023-11-28 07:07:40,980][87424] Updated weights for policy 0, policy_version 264118 (0.0009) -[2023-11-28 07:07:41,359][87424] Updated weights for policy 0, policy_version 264128 (0.0008) -[2023-11-28 07:07:41,682][87426] Updated weights for policy 1, policy_version 263850 (0.0012) -[2023-11-28 07:07:42,060][87426] Updated weights for policy 1, policy_version 263860 (0.0009) -[2023-11-28 07:07:42,435][87426] Updated weights for policy 1, policy_version 263870 (0.0010) -[2023-11-28 07:07:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 135168000. Throughput: 0: 2697.4, 1: 2667.3. Samples: 135182568. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:43,445][86177] Avg episode reward: [(0, '-546.470'), (1, '-550.070')] -[2023-11-28 07:07:43,690][87424] Updated weights for policy 0, policy_version 264138 (0.0008) -[2023-11-28 07:07:44,065][87424] Updated weights for policy 0, policy_version 264148 (0.0007) -[2023-11-28 07:07:44,441][87424] Updated weights for policy 0, policy_version 264158 (0.0008) -[2023-11-28 07:07:44,973][87426] Updated weights for policy 1, policy_version 263880 (0.0012) -[2023-11-28 07:07:45,349][87426] Updated weights for policy 1, policy_version 263890 (0.0011) -[2023-11-28 07:07:45,729][87426] Updated weights for policy 1, policy_version 263900 (0.0010) -[2023-11-28 07:07:46,776][87424] Updated weights for policy 0, policy_version 264168 (0.0011) -[2023-11-28 07:07:47,163][87424] Updated weights for policy 0, policy_version 264178 (0.0007) -[2023-11-28 07:07:47,557][87424] Updated weights for policy 0, policy_version 264188 (0.0008) -[2023-11-28 07:07:47,910][87426] Updated weights for policy 1, policy_version 263910 (0.0011) -[2023-11-28 07:07:48,297][87426] Updated weights for policy 1, policy_version 263920 (0.0007) -[2023-11-28 07:07:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 135192576. Throughput: 0: 2681.8, 1: 2662.9. Samples: 135205492. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:48,445][86177] Avg episode reward: [(0, '-545.840'), (1, '-526.250')] -[2023-11-28 07:07:48,676][87426] Updated weights for policy 1, policy_version 263930 (0.0007) -[2023-11-28 07:07:49,844][87424] Updated weights for policy 0, policy_version 264198 (0.0011) -[2023-11-28 07:07:50,228][87424] Updated weights for policy 0, policy_version 264208 (0.0011) -[2023-11-28 07:07:50,614][87424] Updated weights for policy 0, policy_version 264218 (0.0009) -[2023-11-28 07:07:51,154][87426] Updated weights for policy 1, policy_version 263940 (0.0008) -[2023-11-28 07:07:51,524][87426] Updated weights for policy 1, policy_version 263950 (0.0011) -[2023-11-28 07:07:51,904][87426] Updated weights for policy 1, policy_version 263960 (0.0011) -[2023-11-28 07:07:52,924][87424] Updated weights for policy 0, policy_version 264228 (0.0009) -[2023-11-28 07:07:53,315][87424] Updated weights for policy 0, policy_version 264238 (0.0009) -[2023-11-28 07:07:53,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 135217152. Throughput: 0: 2673.9, 1: 2659.2. Samples: 135237052. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:53,445][86177] Avg episode reward: [(0, '-522.310'), (1, '-516.000')] -[2023-11-28 07:07:53,680][87424] Updated weights for policy 0, policy_version 264248 (0.0010) -[2023-11-28 07:07:54,539][87426] Updated weights for policy 1, policy_version 263970 (0.0011) -[2023-11-28 07:07:54,909][87426] Updated weights for policy 1, policy_version 263980 (0.0009) -[2023-11-28 07:07:55,291][87426] Updated weights for policy 1, policy_version 263990 (0.0008) -[2023-11-28 07:07:55,659][87426] Updated weights for policy 1, policy_version 264000 (0.0008) -[2023-11-28 07:07:55,791][87424] Updated weights for policy 0, policy_version 264258 (0.0010) -[2023-11-28 07:07:56,172][87424] Updated weights for policy 0, policy_version 264268 (0.0012) -[2023-11-28 07:07:56,566][87424] Updated weights for policy 0, policy_version 264278 (0.0011) -[2023-11-28 07:07:56,936][87424] Updated weights for policy 0, policy_version 264288 (0.0012) -[2023-11-28 07:07:57,706][87426] Updated weights for policy 1, policy_version 264010 (0.0012) -[2023-11-28 07:07:58,080][87426] Updated weights for policy 1, policy_version 264020 (0.0011) -[2023-11-28 07:07:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 135241728. Throughput: 0: 2660.9, 1: 2657.1. Samples: 135260572. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:07:58,446][86177] Avg episode reward: [(0, '-524.950'), (1, '-516.090')] -[2023-11-28 07:07:58,465][87426] Updated weights for policy 1, policy_version 264030 (0.0011) -[2023-11-28 07:07:58,778][87424] Updated weights for policy 0, policy_version 264298 (0.0011) -[2023-11-28 07:07:59,161][87424] Updated weights for policy 0, policy_version 264308 (0.0011) -[2023-11-28 07:07:59,545][87424] Updated weights for policy 0, policy_version 264318 (0.0009) -[2023-11-28 07:08:00,622][87426] Updated weights for policy 1, policy_version 264040 (0.0011) -[2023-11-28 07:08:01,011][87426] Updated weights for policy 1, policy_version 264050 (0.0012) -[2023-11-28 07:08:01,385][87426] Updated weights for policy 1, policy_version 264060 (0.0012) -[2023-11-28 07:08:01,683][87424] Updated weights for policy 0, policy_version 264328 (0.0011) -[2023-11-28 07:08:02,063][87424] Updated weights for policy 0, policy_version 264338 (0.0009) -[2023-11-28 07:08:02,439][87424] Updated weights for policy 0, policy_version 264348 (0.0009) -[2023-11-28 07:08:03,444][86177] Fps is (10 sec: 5734.7, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 135274496. Throughput: 0: 2666.9, 1: 2658.9. Samples: 135284856. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 07:08:03,445][86177] Avg episode reward: [(0, '-522.130'), (1, '-516.120')] -[2023-11-28 07:08:03,972][87426] Updated weights for policy 1, policy_version 264070 (0.0009) -[2023-11-28 07:08:04,348][87426] Updated weights for policy 1, policy_version 264080 (0.0008) -[2023-11-28 07:08:04,662][87424] Updated weights for policy 0, policy_version 264358 (0.0010) -[2023-11-28 07:08:04,728][87426] Updated weights for policy 1, policy_version 264090 (0.0008) -[2023-11-28 07:08:05,045][87424] Updated weights for policy 0, policy_version 264368 (0.0010) -[2023-11-28 07:08:05,439][87424] Updated weights for policy 0, policy_version 264378 (0.0007) -[2023-11-28 07:08:06,722][87426] Updated weights for policy 1, policy_version 264100 (0.0009) -[2023-11-28 07:08:07,099][87426] Updated weights for policy 1, policy_version 264110 (0.0012) -[2023-11-28 07:08:07,473][87426] Updated weights for policy 1, policy_version 264120 (0.0010) -[2023-11-28 07:08:08,058][87424] Updated weights for policy 0, policy_version 264388 (0.0007) -[2023-11-28 07:08:08,430][87424] Updated weights for policy 0, policy_version 264398 (0.0008) -[2023-11-28 07:08:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 135299072. Throughput: 0: 2628.9, 1: 2697.2. Samples: 135316372. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:08,446][86177] Avg episode reward: [(0, '-519.440'), (1, '-513.270')] -[2023-11-28 07:08:08,815][87424] Updated weights for policy 0, policy_version 264408 (0.0007) -[2023-11-28 07:08:09,291][87426] Updated weights for policy 1, policy_version 264130 (0.0008) -[2023-11-28 07:08:09,664][87426] Updated weights for policy 1, policy_version 264140 (0.0012) -[2023-11-28 07:08:10,038][87426] Updated weights for policy 1, policy_version 264150 (0.0011) -[2023-11-28 07:08:10,409][87426] Updated weights for policy 1, policy_version 264160 (0.0009) -[2023-11-28 07:08:10,931][87424] Updated weights for policy 0, policy_version 264418 (0.0010) -[2023-11-28 07:08:11,305][87424] Updated weights for policy 0, policy_version 264428 (0.0012) -[2023-11-28 07:08:11,686][87424] Updated weights for policy 0, policy_version 264438 (0.0012) -[2023-11-28 07:08:12,063][87424] Updated weights for policy 0, policy_version 264448 (0.0012) -[2023-11-28 07:08:12,630][87426] Updated weights for policy 1, policy_version 264170 (0.0012) -[2023-11-28 07:08:13,006][87426] Updated weights for policy 1, policy_version 264180 (0.0012) -[2023-11-28 07:08:13,377][87426] Updated weights for policy 1, policy_version 264190 (0.0009) -[2023-11-28 07:08:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 135323648. Throughput: 0: 2631.7, 1: 2685.7. Samples: 135341132. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:13,445][86177] Avg episode reward: [(0, '-528.890'), (1, '-520.160')] -[2023-11-28 07:08:14,034][87424] Updated weights for policy 0, policy_version 264458 (0.0010) -[2023-11-28 07:08:14,437][87424] Updated weights for policy 0, policy_version 264468 (0.0011) -[2023-11-28 07:08:14,825][87424] Updated weights for policy 0, policy_version 264478 (0.0012) -[2023-11-28 07:08:15,985][87426] Updated weights for policy 1, policy_version 264200 (0.0011) -[2023-11-28 07:08:16,367][87426] Updated weights for policy 1, policy_version 264210 (0.0012) -[2023-11-28 07:08:16,560][87424] Updated weights for policy 0, policy_version 264488 (0.0011) -[2023-11-28 07:08:16,751][87426] Updated weights for policy 1, policy_version 264220 (0.0012) -[2023-11-28 07:08:16,943][87424] Updated weights for policy 0, policy_version 264498 (0.0011) -[2023-11-28 07:08:17,331][87424] Updated weights for policy 0, policy_version 264508 (0.0007) -[2023-11-28 07:08:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 135356416. Throughput: 0: 2657.8, 1: 2669.9. Samples: 135365868. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:18,445][86177] Avg episode reward: [(0, '-529.610'), (1, '-503.950')] -[2023-11-28 07:08:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000264512_67715072.pth... -[2023-11-28 07:08:18,496][87426] Updated weights for policy 1, policy_version 264230 (0.0012) -[2023-11-28 07:08:18,499][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000261984_67067904.pth -[2023-11-28 07:08:18,874][87426] Updated weights for policy 1, policy_version 264240 (0.0012) -[2023-11-28 07:08:19,254][87426] Updated weights for policy 1, policy_version 264250 (0.0012) -[2023-11-28 07:08:19,478][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000264256_67649536.pth... -[2023-11-28 07:08:19,509][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000261728_67002368.pth -[2023-11-28 07:08:19,641][87424] Updated weights for policy 0, policy_version 264518 (0.0010) -[2023-11-28 07:08:20,032][87424] Updated weights for policy 0, policy_version 264528 (0.0011) -[2023-11-28 07:08:20,418][87424] Updated weights for policy 0, policy_version 264538 (0.0011) -[2023-11-28 07:08:21,588][87426] Updated weights for policy 1, policy_version 264260 (0.0012) -[2023-11-28 07:08:21,966][87426] Updated weights for policy 1, policy_version 264270 (0.0010) -[2023-11-28 07:08:22,347][87426] Updated weights for policy 1, policy_version 264280 (0.0009) -[2023-11-28 07:08:22,789][87424] Updated weights for policy 0, policy_version 264548 (0.0010) -[2023-11-28 07:08:23,159][87424] Updated weights for policy 0, policy_version 264558 (0.0012) -[2023-11-28 07:08:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 135380992. Throughput: 0: 2666.8, 1: 2684.3. Samples: 135399080. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:23,445][86177] Avg episode reward: [(0, '-530.930'), (1, '-555.340')] -[2023-11-28 07:08:23,535][87424] Updated weights for policy 0, policy_version 264568 (0.0012) -[2023-11-28 07:08:24,305][87426] Updated weights for policy 1, policy_version 264290 (0.0009) -[2023-11-28 07:08:24,693][87426] Updated weights for policy 1, policy_version 264300 (0.0011) -[2023-11-28 07:08:25,072][87426] Updated weights for policy 1, policy_version 264310 (0.0010) -[2023-11-28 07:08:25,450][87426] Updated weights for policy 1, policy_version 264320 (0.0011) -[2023-11-28 07:08:25,958][87424] Updated weights for policy 0, policy_version 264578 (0.0011) -[2023-11-28 07:08:26,343][87424] Updated weights for policy 0, policy_version 264588 (0.0012) -[2023-11-28 07:08:26,717][87424] Updated weights for policy 0, policy_version 264598 (0.0012) -[2023-11-28 07:08:27,092][87424] Updated weights for policy 0, policy_version 264608 (0.0011) -[2023-11-28 07:08:27,252][87426] Updated weights for policy 1, policy_version 264330 (0.0011) -[2023-11-28 07:08:27,638][87426] Updated weights for policy 1, policy_version 264340 (0.0012) -[2023-11-28 07:08:28,011][87426] Updated weights for policy 1, policy_version 264350 (0.0011) -[2023-11-28 07:08:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 135413760. Throughput: 0: 2654.9, 1: 2701.5. Samples: 135423608. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:28,445][86177] Avg episode reward: [(0, '-550.370'), (1, '-563.890')] -[2023-11-28 07:08:29,224][87424] Updated weights for policy 0, policy_version 264618 (0.0012) -[2023-11-28 07:08:29,602][87424] Updated weights for policy 0, policy_version 264628 (0.0012) -[2023-11-28 07:08:29,985][87424] Updated weights for policy 0, policy_version 264638 (0.0012) -[2023-11-28 07:08:30,165][87426] Updated weights for policy 1, policy_version 264360 (0.0011) -[2023-11-28 07:08:30,534][87426] Updated weights for policy 1, policy_version 264370 (0.0012) -[2023-11-28 07:08:30,904][87426] Updated weights for policy 1, policy_version 264380 (0.0011) -[2023-11-28 07:08:32,153][87424] Updated weights for policy 0, policy_version 264648 (0.0009) -[2023-11-28 07:08:32,531][87424] Updated weights for policy 0, policy_version 264658 (0.0008) -[2023-11-28 07:08:32,915][87424] Updated weights for policy 0, policy_version 264668 (0.0010) -[2023-11-28 07:08:33,209][87426] Updated weights for policy 1, policy_version 264390 (0.0008) -[2023-11-28 07:08:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 135438336. Throughput: 0: 2691.4, 1: 2707.6. Samples: 135448448. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:33,445][86177] Avg episode reward: [(0, '-537.930'), (1, '-565.830')] -[2023-11-28 07:08:33,592][87426] Updated weights for policy 1, policy_version 264400 (0.0007) -[2023-11-28 07:08:33,969][87426] Updated weights for policy 1, policy_version 264410 (0.0008) -[2023-11-28 07:08:35,466][87424] Updated weights for policy 0, policy_version 264678 (0.0008) -[2023-11-28 07:08:35,850][87424] Updated weights for policy 0, policy_version 264688 (0.0011) -[2023-11-28 07:08:36,213][87426] Updated weights for policy 1, policy_version 264420 (0.0010) -[2023-11-28 07:08:36,239][87424] Updated weights for policy 0, policy_version 264698 (0.0010) -[2023-11-28 07:08:36,597][87426] Updated weights for policy 1, policy_version 264430 (0.0007) -[2023-11-28 07:08:36,976][87426] Updated weights for policy 1, policy_version 264440 (0.0008) -[2023-11-28 07:08:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 135462912. Throughput: 0: 2672.2, 1: 2714.5. Samples: 135479452. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:38,445][86177] Avg episode reward: [(0, '-569.370'), (1, '-563.440')] -[2023-11-28 07:08:38,732][87424] Updated weights for policy 0, policy_version 264708 (0.0007) -[2023-11-28 07:08:39,130][87424] Updated weights for policy 0, policy_version 264718 (0.0008) -[2023-11-28 07:08:39,469][87426] Updated weights for policy 1, policy_version 264450 (0.0010) -[2023-11-28 07:08:39,522][87424] Updated weights for policy 0, policy_version 264728 (0.0009) -[2023-11-28 07:08:39,846][87426] Updated weights for policy 1, policy_version 264460 (0.0012) -[2023-11-28 07:08:40,222][87426] Updated weights for policy 1, policy_version 264470 (0.0012) -[2023-11-28 07:08:40,597][87426] Updated weights for policy 1, policy_version 264480 (0.0012) -[2023-11-28 07:08:41,944][87424] Updated weights for policy 0, policy_version 264738 (0.0010) -[2023-11-28 07:08:42,323][87424] Updated weights for policy 0, policy_version 264748 (0.0012) -[2023-11-28 07:08:42,701][87424] Updated weights for policy 0, policy_version 264758 (0.0011) -[2023-11-28 07:08:42,965][87426] Updated weights for policy 1, policy_version 264490 (0.0011) -[2023-11-28 07:08:43,082][87424] Updated weights for policy 0, policy_version 264768 (0.0011) -[2023-11-28 07:08:43,357][87426] Updated weights for policy 1, policy_version 264500 (0.0011) -[2023-11-28 07:08:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 135487488. Throughput: 0: 2663.4, 1: 2700.6. Samples: 135501952. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:43,445][86177] Avg episode reward: [(0, '-569.400'), (1, '-535.360')] -[2023-11-28 07:08:43,731][87426] Updated weights for policy 1, policy_version 264510 (0.0012) -[2023-11-28 07:08:45,445][87424] Updated weights for policy 0, policy_version 264778 (0.0012) -[2023-11-28 07:08:45,674][87426] Updated weights for policy 1, policy_version 264520 (0.0008) -[2023-11-28 07:08:45,827][87424] Updated weights for policy 0, policy_version 264788 (0.0008) -[2023-11-28 07:08:46,056][87426] Updated weights for policy 1, policy_version 264530 (0.0008) -[2023-11-28 07:08:46,218][87424] Updated weights for policy 0, policy_version 264798 (0.0008) -[2023-11-28 07:08:46,432][87426] Updated weights for policy 1, policy_version 264540 (0.0008) -[2023-11-28 07:08:48,332][87426] Updated weights for policy 1, policy_version 264550 (0.0009) -[2023-11-28 07:08:48,412][87424] Updated weights for policy 0, policy_version 264808 (0.0010) -[2023-11-28 07:08:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 135512064. Throughput: 0: 2670.9, 1: 2722.9. Samples: 135527580. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:48,445][86177] Avg episode reward: [(0, '-594.990'), (1, '-537.090')] -[2023-11-28 07:08:48,715][87426] Updated weights for policy 1, policy_version 264560 (0.0008) -[2023-11-28 07:08:48,787][87424] Updated weights for policy 0, policy_version 264818 (0.0008) -[2023-11-28 07:08:49,092][87426] Updated weights for policy 1, policy_version 264570 (0.0010) -[2023-11-28 07:08:49,171][87424] Updated weights for policy 0, policy_version 264828 (0.0010) -[2023-11-28 07:08:51,082][87424] Updated weights for policy 0, policy_version 264838 (0.0010) -[2023-11-28 07:08:51,136][87426] Updated weights for policy 1, policy_version 264580 (0.0011) -[2023-11-28 07:08:51,462][87424] Updated weights for policy 0, policy_version 264848 (0.0011) -[2023-11-28 07:08:51,510][87426] Updated weights for policy 1, policy_version 264590 (0.0011) -[2023-11-28 07:08:51,845][87424] Updated weights for policy 0, policy_version 264858 (0.0012) -[2023-11-28 07:08:51,894][87426] Updated weights for policy 1, policy_version 264600 (0.0011) -[2023-11-28 07:08:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 135544832. Throughput: 0: 2700.6, 1: 2734.9. Samples: 135560972. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:53,445][86177] Avg episode reward: [(0, '-598.730'), (1, '-538.330')] -[2023-11-28 07:08:53,859][87424] Updated weights for policy 0, policy_version 264868 (0.0010) -[2023-11-28 07:08:54,244][87424] Updated weights for policy 0, policy_version 264878 (0.0007) -[2023-11-28 07:08:54,303][87426] Updated weights for policy 1, policy_version 264610 (0.0009) -[2023-11-28 07:08:54,626][87424] Updated weights for policy 0, policy_version 264888 (0.0008) -[2023-11-28 07:08:54,680][87426] Updated weights for policy 1, policy_version 264620 (0.0008) -[2023-11-28 07:08:55,062][87426] Updated weights for policy 1, policy_version 264630 (0.0009) -[2023-11-28 07:08:55,449][87426] Updated weights for policy 1, policy_version 264640 (0.0008) -[2023-11-28 07:08:56,358][87424] Updated weights for policy 0, policy_version 264898 (0.0009) -[2023-11-28 07:08:56,740][87424] Updated weights for policy 0, policy_version 264908 (0.0012) -[2023-11-28 07:08:57,122][87424] Updated weights for policy 0, policy_version 264918 (0.0011) -[2023-11-28 07:08:57,276][87426] Updated weights for policy 1, policy_version 264650 (0.0011) -[2023-11-28 07:08:57,499][87424] Updated weights for policy 0, policy_version 264928 (0.0008) -[2023-11-28 07:08:57,636][87426] Updated weights for policy 1, policy_version 264660 (0.0011) -[2023-11-28 07:08:58,011][87426] Updated weights for policy 1, policy_version 264670 (0.0012) -[2023-11-28 07:08:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 135577600. Throughput: 0: 2714.3, 1: 2737.4. Samples: 135586460. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:08:58,445][86177] Avg episode reward: [(0, '-563.230'), (1, '-543.010')] -[2023-11-28 07:09:00,029][87424] Updated weights for policy 0, policy_version 264938 (0.0011) -[2023-11-28 07:09:00,035][87426] Updated weights for policy 1, policy_version 264680 (0.0012) -[2023-11-28 07:09:00,411][87424] Updated weights for policy 0, policy_version 264948 (0.0009) -[2023-11-28 07:09:00,417][87426] Updated weights for policy 1, policy_version 264690 (0.0012) -[2023-11-28 07:09:00,799][87424] Updated weights for policy 0, policy_version 264958 (0.0011) -[2023-11-28 07:09:00,799][87426] Updated weights for policy 1, policy_version 264700 (0.0012) -[2023-11-28 07:09:02,895][87426] Updated weights for policy 1, policy_version 264710 (0.0011) -[2023-11-28 07:09:03,017][87424] Updated weights for policy 0, policy_version 264968 (0.0011) -[2023-11-28 07:09:03,285][87426] Updated weights for policy 1, policy_version 264720 (0.0010) -[2023-11-28 07:09:03,398][87424] Updated weights for policy 0, policy_version 264978 (0.0012) -[2023-11-28 07:09:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 135593984. Throughput: 0: 2710.9, 1: 2759.6. Samples: 135612044. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:09:03,445][86177] Avg episode reward: [(0, '-570.920'), (1, '-531.970')] -[2023-11-28 07:09:03,661][87426] Updated weights for policy 1, policy_version 264730 (0.0008) -[2023-11-28 07:09:03,793][87424] Updated weights for policy 0, policy_version 264988 (0.0012) -[2023-11-28 07:09:05,758][87426] Updated weights for policy 1, policy_version 264740 (0.0010) -[2023-11-28 07:09:06,075][87424] Updated weights for policy 0, policy_version 264998 (0.0012) -[2023-11-28 07:09:06,136][87426] Updated weights for policy 1, policy_version 264750 (0.0012) -[2023-11-28 07:09:06,450][87424] Updated weights for policy 0, policy_version 265008 (0.0012) -[2023-11-28 07:09:06,510][87426] Updated weights for policy 1, policy_version 264760 (0.0011) -[2023-11-28 07:09:06,838][87424] Updated weights for policy 0, policy_version 265018 (0.0012) -[2023-11-28 07:09:08,425][87426] Updated weights for policy 1, policy_version 264770 (0.0009) -[2023-11-28 07:09:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 135626752. Throughput: 0: 2689.8, 1: 2779.1. Samples: 135645180. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:09:08,445][86177] Avg episode reward: [(0, '-526.280'), (1, '-526.410')] -[2023-11-28 07:09:08,803][87426] Updated weights for policy 1, policy_version 264780 (0.0007) -[2023-11-28 07:09:09,177][87426] Updated weights for policy 1, policy_version 264790 (0.0010) -[2023-11-28 07:09:09,178][87424] Updated weights for policy 0, policy_version 265028 (0.0011) -[2023-11-28 07:09:09,556][87424] Updated weights for policy 0, policy_version 265038 (0.0010) -[2023-11-28 07:09:09,557][87426] Updated weights for policy 1, policy_version 264800 (0.0008) -[2023-11-28 07:09:09,941][87424] Updated weights for policy 0, policy_version 265048 (0.0008) -[2023-11-28 07:09:11,884][87426] Updated weights for policy 1, policy_version 264810 (0.0010) -[2023-11-28 07:09:12,255][87426] Updated weights for policy 1, policy_version 264820 (0.0012) -[2023-11-28 07:09:12,462][87424] Updated weights for policy 0, policy_version 265058 (0.0008) -[2023-11-28 07:09:12,642][87426] Updated weights for policy 1, policy_version 264830 (0.0009) -[2023-11-28 07:09:12,846][87424] Updated weights for policy 0, policy_version 265068 (0.0012) -[2023-11-28 07:09:13,223][87424] Updated weights for policy 0, policy_version 265078 (0.0012) -[2023-11-28 07:09:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 135651328. Throughput: 0: 2698.3, 1: 2766.2. Samples: 135669512. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:09:13,445][86177] Avg episode reward: [(0, '-563.270'), (1, '-529.210')] -[2023-11-28 07:09:13,599][87424] Updated weights for policy 0, policy_version 265088 (0.0012) -[2023-11-28 07:09:14,883][87426] Updated weights for policy 1, policy_version 264840 (0.0008) -[2023-11-28 07:09:15,260][87426] Updated weights for policy 1, policy_version 264850 (0.0007) -[2023-11-28 07:09:15,643][87426] Updated weights for policy 1, policy_version 264860 (0.0008) -[2023-11-28 07:09:15,659][87424] Updated weights for policy 0, policy_version 265098 (0.0009) -[2023-11-28 07:09:16,040][87424] Updated weights for policy 0, policy_version 265108 (0.0010) -[2023-11-28 07:09:16,429][87424] Updated weights for policy 0, policy_version 265118 (0.0008) -[2023-11-28 07:09:17,771][87426] Updated weights for policy 1, policy_version 264870 (0.0010) -[2023-11-28 07:09:18,156][87426] Updated weights for policy 1, policy_version 264880 (0.0011) -[2023-11-28 07:09:18,202][87424] Updated weights for policy 0, policy_version 265128 (0.0007) -[2023-11-28 07:09:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 135675904. Throughput: 0: 2676.6, 1: 2773.9. Samples: 135693720. Policy #0 lag: (min: 26.0, avg: 54.1, max: 90.0) -[2023-11-28 07:09:18,445][86177] Avg episode reward: [(0, '-562.570'), (1, '-529.100')] -[2023-11-28 07:09:18,521][87426] Updated weights for policy 1, policy_version 264890 (0.0008) -[2023-11-28 07:09:18,593][87424] Updated weights for policy 0, policy_version 265138 (0.0007) -[2023-11-28 07:09:18,979][87424] Updated weights for policy 0, policy_version 265148 (0.0009) -[2023-11-28 07:09:21,102][87426] Updated weights for policy 1, policy_version 264900 (0.0008) -[2023-11-28 07:09:21,447][87424] Updated weights for policy 0, policy_version 265158 (0.0010) -[2023-11-28 07:09:21,479][87426] Updated weights for policy 1, policy_version 264910 (0.0008) -[2023-11-28 07:09:21,836][87424] Updated weights for policy 0, policy_version 265168 (0.0009) -[2023-11-28 07:09:21,855][87426] Updated weights for policy 1, policy_version 264920 (0.0011) -[2023-11-28 07:09:22,213][87424] Updated weights for policy 0, policy_version 265178 (0.0011) -[2023-11-28 07:09:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 135708672. Throughput: 0: 2684.9, 1: 2753.4. Samples: 135724176. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:09:23,445][86177] Avg episode reward: [(0, '-555.080'), (1, '-539.110')] -[2023-11-28 07:09:24,102][87426] Updated weights for policy 1, policy_version 264930 (0.0011) -[2023-11-28 07:09:24,477][87426] Updated weights for policy 1, policy_version 264940 (0.0011) -[2023-11-28 07:09:24,726][87424] Updated weights for policy 0, policy_version 265188 (0.0011) -[2023-11-28 07:09:24,854][87426] Updated weights for policy 1, policy_version 264950 (0.0012) -[2023-11-28 07:09:25,109][87424] Updated weights for policy 0, policy_version 265198 (0.0009) -[2023-11-28 07:09:25,232][87426] Updated weights for policy 1, policy_version 264960 (0.0012) -[2023-11-28 07:09:25,494][87424] Updated weights for policy 0, policy_version 265208 (0.0008) -[2023-11-28 07:09:27,138][87426] Updated weights for policy 1, policy_version 264970 (0.0011) -[2023-11-28 07:09:27,235][87424] Updated weights for policy 0, policy_version 265218 (0.0007) -[2023-11-28 07:09:27,515][87426] Updated weights for policy 1, policy_version 264980 (0.0011) -[2023-11-28 07:09:27,622][87424] Updated weights for policy 0, policy_version 265228 (0.0008) -[2023-11-28 07:09:27,891][87426] Updated weights for policy 1, policy_version 264990 (0.0011) -[2023-11-28 07:09:27,989][87424] Updated weights for policy 0, policy_version 265238 (0.0007) -[2023-11-28 07:09:28,373][87424] Updated weights for policy 0, policy_version 265248 (0.0007) -[2023-11-28 07:09:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 135741440. Throughput: 0: 2699.9, 1: 2802.2. Samples: 135749548. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:09:28,445][86177] Avg episode reward: [(0, '-562.390'), (1, '-535.710')] -[2023-11-28 07:09:29,719][87426] Updated weights for policy 1, policy_version 265000 (0.0011) -[2023-11-28 07:09:30,100][87426] Updated weights for policy 1, policy_version 265010 (0.0009) -[2023-11-28 07:09:30,480][87426] Updated weights for policy 1, policy_version 265020 (0.0009) -[2023-11-28 07:09:30,839][87424] Updated weights for policy 0, policy_version 265258 (0.0011) -[2023-11-28 07:09:31,227][87424] Updated weights for policy 0, policy_version 265268 (0.0008) -[2023-11-28 07:09:31,602][87424] Updated weights for policy 0, policy_version 265278 (0.0008) -[2023-11-28 07:09:32,559][87426] Updated weights for policy 1, policy_version 265030 (0.0009) -[2023-11-28 07:09:32,939][87426] Updated weights for policy 1, policy_version 265040 (0.0008) -[2023-11-28 07:09:33,329][87426] Updated weights for policy 1, policy_version 265050 (0.0008) -[2023-11-28 07:09:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 135757824. Throughput: 0: 2702.5, 1: 2806.3. Samples: 135775476. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:09:33,445][86177] Avg episode reward: [(0, '-527.620'), (1, '-534.240')] -[2023-11-28 07:09:34,054][87424] Updated weights for policy 0, policy_version 265288 (0.0008) -[2023-11-28 07:09:34,437][87424] Updated weights for policy 0, policy_version 265298 (0.0007) -[2023-11-28 07:09:34,823][87424] Updated weights for policy 0, policy_version 265308 (0.0008) -[2023-11-28 07:09:34,829][87426] Updated weights for policy 1, policy_version 265060 (0.0008) -[2023-11-28 07:09:35,214][87426] Updated weights for policy 1, policy_version 265070 (0.0012) -[2023-11-28 07:09:35,583][87426] Updated weights for policy 1, policy_version 265080 (0.0012) -[2023-11-28 07:09:36,907][87424] Updated weights for policy 0, policy_version 265318 (0.0010) -[2023-11-28 07:09:37,295][87424] Updated weights for policy 0, policy_version 265328 (0.0011) -[2023-11-28 07:09:37,673][87424] Updated weights for policy 0, policy_version 265338 (0.0009) -[2023-11-28 07:09:38,153][87426] Updated weights for policy 1, policy_version 265090 (0.0010) -[2023-11-28 07:09:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 135790592. Throughput: 0: 2679.2, 1: 2822.7. Samples: 135808556. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:09:38,445][86177] Avg episode reward: [(0, '-550.060'), (1, '-526.450')] -[2023-11-28 07:09:38,537][87426] Updated weights for policy 1, policy_version 265100 (0.0012) -[2023-11-28 07:09:38,921][87426] Updated weights for policy 1, policy_version 265110 (0.0011) -[2023-11-28 07:09:39,285][87426] Updated weights for policy 1, policy_version 265120 (0.0012) -[2023-11-28 07:09:39,882][87424] Updated weights for policy 0, policy_version 265348 (0.0010) -[2023-11-28 07:09:40,274][87424] Updated weights for policy 0, policy_version 265358 (0.0012) -[2023-11-28 07:09:40,662][87424] Updated weights for policy 0, policy_version 265368 (0.0011) -[2023-11-28 07:09:41,293][87426] Updated weights for policy 1, policy_version 265130 (0.0007) -[2023-11-28 07:09:41,675][87426] Updated weights for policy 1, policy_version 265140 (0.0008) -[2023-11-28 07:09:42,053][87426] Updated weights for policy 1, policy_version 265150 (0.0008) -[2023-11-28 07:09:43,015][87424] Updated weights for policy 0, policy_version 265378 (0.0011) -[2023-11-28 07:09:43,385][87424] Updated weights for policy 0, policy_version 265388 (0.0011) -[2023-11-28 07:09:43,446][86177] Fps is (10 sec: 5733.2, 60 sec: 5461.1, 300 sec: 5415.0). Total num frames: 135815168. Throughput: 0: 2657.3, 1: 2822.7. Samples: 135833072. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:09:43,447][86177] Avg episode reward: [(0, '-559.080'), (1, '-511.050')] -[2023-11-28 07:09:43,760][87424] Updated weights for policy 0, policy_version 265398 (0.0009) -[2023-11-28 07:09:44,088][87426] Updated weights for policy 1, policy_version 265160 (0.0011) -[2023-11-28 07:09:44,143][87424] Updated weights for policy 0, policy_version 265408 (0.0007) -[2023-11-28 07:09:44,467][87426] Updated weights for policy 1, policy_version 265170 (0.0011) -[2023-11-28 07:09:44,853][87426] Updated weights for policy 1, policy_version 265180 (0.0012) -[2023-11-28 07:09:45,938][87424] Updated weights for policy 0, policy_version 265418 (0.0012) -[2023-11-28 07:09:46,316][87424] Updated weights for policy 0, policy_version 265428 (0.0011) -[2023-11-28 07:09:46,690][87424] Updated weights for policy 0, policy_version 265438 (0.0010) -[2023-11-28 07:09:46,996][87426] Updated weights for policy 1, policy_version 265190 (0.0009) -[2023-11-28 07:09:47,380][87426] Updated weights for policy 1, policy_version 265200 (0.0007) -[2023-11-28 07:09:47,759][87426] Updated weights for policy 1, policy_version 265210 (0.0008) -[2023-11-28 07:09:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 135847936. Throughput: 0: 2632.4, 1: 2806.3. Samples: 135856784. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:09:48,445][86177] Avg episode reward: [(0, '-551.690'), (1, '-508.760')] -[2023-11-28 07:09:49,180][87424] Updated weights for policy 0, policy_version 265448 (0.0011) -[2023-11-28 07:09:49,555][87424] Updated weights for policy 0, policy_version 265458 (0.0012) -[2023-11-28 07:09:49,917][87426] Updated weights for policy 1, policy_version 265220 (0.0009) -[2023-11-28 07:09:49,941][87424] Updated weights for policy 0, policy_version 265468 (0.0012) -[2023-11-28 07:09:50,294][87426] Updated weights for policy 1, policy_version 265230 (0.0011) -[2023-11-28 07:09:50,681][87426] Updated weights for policy 1, policy_version 265240 (0.0009) -[2023-11-28 07:09:52,397][87424] Updated weights for policy 0, policy_version 265478 (0.0008) -[2023-11-28 07:09:52,780][87424] Updated weights for policy 0, policy_version 265488 (0.0008) -[2023-11-28 07:09:52,918][87426] Updated weights for policy 1, policy_version 265250 (0.0008) -[2023-11-28 07:09:53,162][87424] Updated weights for policy 0, policy_version 265498 (0.0010) -[2023-11-28 07:09:53,309][87426] Updated weights for policy 1, policy_version 265260 (0.0011) -[2023-11-28 07:09:53,444][86177] Fps is (10 sec: 5735.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 135872512. Throughput: 0: 2628.7, 1: 2776.7. Samples: 135888424. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:09:53,445][86177] Avg episode reward: [(0, '-567.870'), (1, '-508.390')] -[2023-11-28 07:09:53,674][87426] Updated weights for policy 1, policy_version 265270 (0.0012) -[2023-11-28 07:09:54,052][87426] Updated weights for policy 1, policy_version 265280 (0.0012) -[2023-11-28 07:09:55,706][87424] Updated weights for policy 0, policy_version 265508 (0.0011) -[2023-11-28 07:09:56,098][87424] Updated weights for policy 0, policy_version 265518 (0.0012) -[2023-11-28 07:09:56,483][87424] Updated weights for policy 0, policy_version 265528 (0.0012) -[2023-11-28 07:09:56,625][87426] Updated weights for policy 1, policy_version 265290 (0.0011) -[2023-11-28 07:09:57,004][87426] Updated weights for policy 1, policy_version 265300 (0.0009) -[2023-11-28 07:09:57,379][87426] Updated weights for policy 1, policy_version 265310 (0.0007) -[2023-11-28 07:09:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 135897088. Throughput: 0: 2626.6, 1: 2753.0. Samples: 135911592. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:09:58,445][86177] Avg episode reward: [(0, '-579.080'), (1, '-511.620')] -[2023-11-28 07:09:58,972][87424] Updated weights for policy 0, policy_version 265538 (0.0011) -[2023-11-28 07:09:59,359][87424] Updated weights for policy 0, policy_version 265548 (0.0011) -[2023-11-28 07:09:59,737][87424] Updated weights for policy 0, policy_version 265558 (0.0011) -[2023-11-28 07:09:59,804][87426] Updated weights for policy 1, policy_version 265320 (0.0007) -[2023-11-28 07:10:00,117][87424] Updated weights for policy 0, policy_version 265568 (0.0011) -[2023-11-28 07:10:00,185][87426] Updated weights for policy 1, policy_version 265330 (0.0008) -[2023-11-28 07:10:00,561][87426] Updated weights for policy 1, policy_version 265340 (0.0008) -[2023-11-28 07:10:01,955][87424] Updated weights for policy 0, policy_version 265578 (0.0012) -[2023-11-28 07:10:02,348][87424] Updated weights for policy 0, policy_version 265588 (0.0012) -[2023-11-28 07:10:02,730][87424] Updated weights for policy 0, policy_version 265598 (0.0012) -[2023-11-28 07:10:03,022][87426] Updated weights for policy 1, policy_version 265350 (0.0010) -[2023-11-28 07:10:03,404][87426] Updated weights for policy 1, policy_version 265360 (0.0012) -[2023-11-28 07:10:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 135921664. Throughput: 0: 2639.9, 1: 2746.0. Samples: 135936088. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:10:03,446][86177] Avg episode reward: [(0, '-584.420'), (1, '-524.510')] -[2023-11-28 07:10:03,785][87426] Updated weights for policy 1, policy_version 265370 (0.0012) -[2023-11-28 07:10:05,045][87424] Updated weights for policy 0, policy_version 265608 (0.0012) -[2023-11-28 07:10:05,426][87424] Updated weights for policy 0, policy_version 265618 (0.0012) -[2023-11-28 07:10:05,500][87426] Updated weights for policy 1, policy_version 265380 (0.0011) -[2023-11-28 07:10:05,806][87424] Updated weights for policy 0, policy_version 265628 (0.0011) -[2023-11-28 07:10:05,872][87426] Updated weights for policy 1, policy_version 265390 (0.0011) -[2023-11-28 07:10:06,239][87426] Updated weights for policy 1, policy_version 265400 (0.0012) -[2023-11-28 07:10:07,465][87424] Updated weights for policy 0, policy_version 265638 (0.0012) -[2023-11-28 07:10:07,845][87424] Updated weights for policy 0, policy_version 265648 (0.0011) -[2023-11-28 07:10:08,182][87426] Updated weights for policy 1, policy_version 265410 (0.0011) -[2023-11-28 07:10:08,225][87424] Updated weights for policy 0, policy_version 265658 (0.0008) -[2023-11-28 07:10:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 135946240. Throughput: 0: 2664.8, 1: 2761.2. Samples: 135968348. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:10:08,445][86177] Avg episode reward: [(0, '-580.370'), (1, '-524.900')] -[2023-11-28 07:10:08,547][87426] Updated weights for policy 1, policy_version 265420 (0.0010) -[2023-11-28 07:10:08,926][87426] Updated weights for policy 1, policy_version 265430 (0.0008) -[2023-11-28 07:10:09,312][87426] Updated weights for policy 1, policy_version 265440 (0.0007) -[2023-11-28 07:10:10,384][87424] Updated weights for policy 0, policy_version 265668 (0.0008) -[2023-11-28 07:10:10,763][87424] Updated weights for policy 0, policy_version 265678 (0.0010) -[2023-11-28 07:10:11,153][87424] Updated weights for policy 0, policy_version 265688 (0.0008) -[2023-11-28 07:10:11,780][87426] Updated weights for policy 1, policy_version 265450 (0.0009) -[2023-11-28 07:10:12,162][87426] Updated weights for policy 1, policy_version 265460 (0.0009) -[2023-11-28 07:10:12,539][87426] Updated weights for policy 1, policy_version 265470 (0.0008) -[2023-11-28 07:10:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 135979008. Throughput: 0: 2672.7, 1: 2717.5. Samples: 135992108. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:10:13,445][86177] Avg episode reward: [(0, '-566.840'), (1, '-525.290')] -[2023-11-28 07:10:13,563][87424] Updated weights for policy 0, policy_version 265698 (0.0008) -[2023-11-28 07:10:13,938][87424] Updated weights for policy 0, policy_version 265708 (0.0009) -[2023-11-28 07:10:14,315][87424] Updated weights for policy 0, policy_version 265718 (0.0011) -[2023-11-28 07:10:14,704][87424] Updated weights for policy 0, policy_version 265728 (0.0010) -[2023-11-28 07:10:15,102][87426] Updated weights for policy 1, policy_version 265480 (0.0009) -[2023-11-28 07:10:15,493][87426] Updated weights for policy 1, policy_version 265490 (0.0010) -[2023-11-28 07:10:15,869][87426] Updated weights for policy 1, policy_version 265500 (0.0012) -[2023-11-28 07:10:17,169][87424] Updated weights for policy 0, policy_version 265738 (0.0012) -[2023-11-28 07:10:17,561][87424] Updated weights for policy 0, policy_version 265748 (0.0012) -[2023-11-28 07:10:17,864][87426] Updated weights for policy 1, policy_version 265510 (0.0011) -[2023-11-28 07:10:17,942][87424] Updated weights for policy 0, policy_version 265758 (0.0011) -[2023-11-28 07:10:18,242][87426] Updated weights for policy 1, policy_version 265520 (0.0011) -[2023-11-28 07:10:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 136003584. Throughput: 0: 2631.5, 1: 2711.7. Samples: 136015920. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:10:18,446][86177] Avg episode reward: [(0, '-561.850'), (1, '-525.730')] -[2023-11-28 07:10:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000265760_68034560.pth... -[2023-11-28 07:10:18,493][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000263264_67395584.pth -[2023-11-28 07:10:18,631][87426] Updated weights for policy 1, policy_version 265530 (0.0011) -[2023-11-28 07:10:18,852][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000265536_67977216.pth... -[2023-11-28 07:10:18,903][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000262976_67321856.pth -[2023-11-28 07:10:19,777][87424] Updated weights for policy 0, policy_version 265768 (0.0012) -[2023-11-28 07:10:20,156][87424] Updated weights for policy 0, policy_version 265778 (0.0012) -[2023-11-28 07:10:20,531][87424] Updated weights for policy 0, policy_version 265788 (0.0012) -[2023-11-28 07:10:20,858][87426] Updated weights for policy 1, policy_version 265540 (0.0012) -[2023-11-28 07:10:21,237][87426] Updated weights for policy 1, policy_version 265550 (0.0009) -[2023-11-28 07:10:21,614][87426] Updated weights for policy 1, policy_version 265560 (0.0010) -[2023-11-28 07:10:23,044][87424] Updated weights for policy 0, policy_version 265798 (0.0012) -[2023-11-28 07:10:23,428][87424] Updated weights for policy 0, policy_version 265808 (0.0012) -[2023-11-28 07:10:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 136028160. Throughput: 0: 2628.6, 1: 2703.6. Samples: 136048508. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:10:23,445][86177] Avg episode reward: [(0, '-519.880'), (1, '-537.320')] -[2023-11-28 07:10:23,666][87426] Updated weights for policy 1, policy_version 265570 (0.0011) -[2023-11-28 07:10:23,820][87424] Updated weights for policy 0, policy_version 265818 (0.0012) -[2023-11-28 07:10:24,044][87426] Updated weights for policy 1, policy_version 265580 (0.0009) -[2023-11-28 07:10:24,419][87426] Updated weights for policy 1, policy_version 265590 (0.0012) -[2023-11-28 07:10:24,794][87426] Updated weights for policy 1, policy_version 265600 (0.0010) -[2023-11-28 07:10:25,558][87424] Updated weights for policy 0, policy_version 265828 (0.0012) -[2023-11-28 07:10:25,941][87424] Updated weights for policy 0, policy_version 265838 (0.0012) -[2023-11-28 07:10:26,320][87424] Updated weights for policy 0, policy_version 265848 (0.0012) -[2023-11-28 07:10:27,120][87426] Updated weights for policy 1, policy_version 265610 (0.0012) -[2023-11-28 07:10:27,504][87426] Updated weights for policy 1, policy_version 265620 (0.0012) -[2023-11-28 07:10:27,878][87426] Updated weights for policy 1, policy_version 265630 (0.0012) -[2023-11-28 07:10:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 136060928. Throughput: 0: 2645.2, 1: 2686.2. Samples: 136072972. Policy #0 lag: (min: 31.0, avg: 48.2, max: 77.0) -[2023-11-28 07:10:28,445][86177] Avg episode reward: [(0, '-522.240'), (1, '-538.030')] -[2023-11-28 07:10:28,723][87424] Updated weights for policy 0, policy_version 265858 (0.0012) -[2023-11-28 07:10:29,092][87424] Updated weights for policy 0, policy_version 265868 (0.0012) -[2023-11-28 07:10:29,481][87424] Updated weights for policy 0, policy_version 265878 (0.0012) -[2023-11-28 07:10:29,865][87424] Updated weights for policy 0, policy_version 265888 (0.0009) -[2023-11-28 07:10:30,039][87426] Updated weights for policy 1, policy_version 265640 (0.0011) -[2023-11-28 07:10:30,418][87426] Updated weights for policy 1, policy_version 265650 (0.0010) -[2023-11-28 07:10:30,801][87426] Updated weights for policy 1, policy_version 265660 (0.0008) -[2023-11-28 07:10:31,832][87424] Updated weights for policy 0, policy_version 265898 (0.0012) -[2023-11-28 07:10:32,214][87424] Updated weights for policy 0, policy_version 265908 (0.0012) -[2023-11-28 07:10:32,602][87424] Updated weights for policy 0, policy_version 265918 (0.0012) -[2023-11-28 07:10:32,963][87426] Updated weights for policy 1, policy_version 265670 (0.0010) -[2023-11-28 07:10:33,342][87426] Updated weights for policy 1, policy_version 265680 (0.0010) -[2023-11-28 07:10:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 136085504. Throughput: 0: 2683.2, 1: 2692.9. Samples: 136098708. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:10:33,445][86177] Avg episode reward: [(0, '-573.210'), (1, '-544.690')] -[2023-11-28 07:10:33,724][87426] Updated weights for policy 1, policy_version 265690 (0.0008) -[2023-11-28 07:10:34,752][87424] Updated weights for policy 0, policy_version 265928 (0.0009) -[2023-11-28 07:10:35,124][87424] Updated weights for policy 0, policy_version 265938 (0.0011) -[2023-11-28 07:10:35,508][87424] Updated weights for policy 0, policy_version 265948 (0.0012) -[2023-11-28 07:10:35,627][87426] Updated weights for policy 1, policy_version 265700 (0.0009) -[2023-11-28 07:10:36,006][87426] Updated weights for policy 1, policy_version 265710 (0.0012) -[2023-11-28 07:10:36,375][87426] Updated weights for policy 1, policy_version 265720 (0.0012) -[2023-11-28 07:10:37,355][87424] Updated weights for policy 0, policy_version 265958 (0.0012) -[2023-11-28 07:10:37,743][87424] Updated weights for policy 0, policy_version 265968 (0.0012) -[2023-11-28 07:10:38,122][87424] Updated weights for policy 0, policy_version 265978 (0.0012) -[2023-11-28 07:10:38,176][87426] Updated weights for policy 1, policy_version 265730 (0.0012) -[2023-11-28 07:10:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 136118272. Throughput: 0: 2697.8, 1: 2700.0. Samples: 136131324. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:10:38,445][86177] Avg episode reward: [(0, '-568.330'), (1, '-556.480')] -[2023-11-28 07:10:38,556][87426] Updated weights for policy 1, policy_version 265740 (0.0012) -[2023-11-28 07:10:38,933][87426] Updated weights for policy 1, policy_version 265750 (0.0011) -[2023-11-28 07:10:39,320][87426] Updated weights for policy 1, policy_version 265760 (0.0008) -[2023-11-28 07:10:40,601][87424] Updated weights for policy 0, policy_version 265988 (0.0012) -[2023-11-28 07:10:40,978][87424] Updated weights for policy 0, policy_version 265998 (0.0012) -[2023-11-28 07:10:41,356][87424] Updated weights for policy 0, policy_version 266008 (0.0012) -[2023-11-28 07:10:41,829][87426] Updated weights for policy 1, policy_version 265770 (0.0011) -[2023-11-28 07:10:42,210][87426] Updated weights for policy 1, policy_version 265780 (0.0012) -[2023-11-28 07:10:42,593][87426] Updated weights for policy 1, policy_version 265790 (0.0012) -[2023-11-28 07:10:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.5, 300 sec: 5415.1). Total num frames: 136142848. Throughput: 0: 2692.2, 1: 2712.9. Samples: 136154820. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:10:43,445][86177] Avg episode reward: [(0, '-569.300'), (1, '-535.240')] -[2023-11-28 07:10:43,506][87424] Updated weights for policy 0, policy_version 266018 (0.0012) -[2023-11-28 07:10:43,877][87424] Updated weights for policy 0, policy_version 266028 (0.0012) -[2023-11-28 07:10:44,267][87424] Updated weights for policy 0, policy_version 266038 (0.0011) -[2023-11-28 07:10:44,637][87424] Updated weights for policy 0, policy_version 266048 (0.0012) -[2023-11-28 07:10:45,138][87426] Updated weights for policy 1, policy_version 265800 (0.0011) -[2023-11-28 07:10:45,517][87426] Updated weights for policy 1, policy_version 265810 (0.0009) -[2023-11-28 07:10:45,895][87426] Updated weights for policy 1, policy_version 265820 (0.0007) -[2023-11-28 07:10:46,938][87424] Updated weights for policy 0, policy_version 266058 (0.0008) -[2023-11-28 07:10:47,332][87424] Updated weights for policy 0, policy_version 266068 (0.0007) -[2023-11-28 07:10:47,713][87424] Updated weights for policy 0, policy_version 266078 (0.0007) -[2023-11-28 07:10:47,882][87426] Updated weights for policy 1, policy_version 265830 (0.0010) -[2023-11-28 07:10:48,260][87426] Updated weights for policy 1, policy_version 265840 (0.0012) -[2023-11-28 07:10:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 136167424. Throughput: 0: 2701.7, 1: 2707.8. Samples: 136179516. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:10:48,445][86177] Avg episode reward: [(0, '-576.070'), (1, '-542.890')] -[2023-11-28 07:10:48,642][87426] Updated weights for policy 1, policy_version 265850 (0.0010) -[2023-11-28 07:10:50,208][87424] Updated weights for policy 0, policy_version 266088 (0.0011) -[2023-11-28 07:10:50,596][87424] Updated weights for policy 0, policy_version 266098 (0.0011) -[2023-11-28 07:10:50,912][87426] Updated weights for policy 1, policy_version 265860 (0.0011) -[2023-11-28 07:10:50,972][87424] Updated weights for policy 0, policy_version 266108 (0.0011) -[2023-11-28 07:10:51,289][87426] Updated weights for policy 1, policy_version 265870 (0.0011) -[2023-11-28 07:10:51,675][87426] Updated weights for policy 1, policy_version 265880 (0.0011) -[2023-11-28 07:10:52,924][87424] Updated weights for policy 0, policy_version 266118 (0.0010) -[2023-11-28 07:10:53,315][87424] Updated weights for policy 0, policy_version 266128 (0.0012) -[2023-11-28 07:10:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 136192000. Throughput: 0: 2687.2, 1: 2731.5. Samples: 136212188. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:10:53,445][86177] Avg episode reward: [(0, '-586.820'), (1, '-528.880')] -[2023-11-28 07:10:53,686][87424] Updated weights for policy 0, policy_version 266138 (0.0011) -[2023-11-28 07:10:53,875][87426] Updated weights for policy 1, policy_version 265890 (0.0010) -[2023-11-28 07:10:54,251][87426] Updated weights for policy 1, policy_version 265900 (0.0008) -[2023-11-28 07:10:54,637][87426] Updated weights for policy 1, policy_version 265910 (0.0007) -[2023-11-28 07:10:55,019][87426] Updated weights for policy 1, policy_version 265920 (0.0008) -[2023-11-28 07:10:56,115][87424] Updated weights for policy 0, policy_version 266148 (0.0010) -[2023-11-28 07:10:56,502][87424] Updated weights for policy 0, policy_version 266158 (0.0007) -[2023-11-28 07:10:56,879][87424] Updated weights for policy 0, policy_version 266168 (0.0007) -[2023-11-28 07:10:56,883][87426] Updated weights for policy 1, policy_version 265930 (0.0007) -[2023-11-28 07:10:57,261][87426] Updated weights for policy 1, policy_version 265940 (0.0008) -[2023-11-28 07:10:57,643][87426] Updated weights for policy 1, policy_version 265950 (0.0007) -[2023-11-28 07:10:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 136224768. Throughput: 0: 2665.4, 1: 2747.9. Samples: 136235708. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:10:58,445][86177] Avg episode reward: [(0, '-589.880'), (1, '-510.290')] -[2023-11-28 07:10:59,366][87424] Updated weights for policy 0, policy_version 266178 (0.0008) -[2023-11-28 07:10:59,740][87424] Updated weights for policy 0, policy_version 266188 (0.0012) -[2023-11-28 07:11:00,039][87426] Updated weights for policy 1, policy_version 265960 (0.0010) -[2023-11-28 07:11:00,123][87424] Updated weights for policy 0, policy_version 266198 (0.0011) -[2023-11-28 07:11:00,419][87426] Updated weights for policy 1, policy_version 265970 (0.0008) -[2023-11-28 07:11:00,505][87424] Updated weights for policy 0, policy_version 266208 (0.0011) -[2023-11-28 07:11:00,796][87426] Updated weights for policy 1, policy_version 265980 (0.0012) -[2023-11-28 07:11:02,805][87424] Updated weights for policy 0, policy_version 266218 (0.0008) -[2023-11-28 07:11:03,162][87426] Updated weights for policy 1, policy_version 265990 (0.0009) -[2023-11-28 07:11:03,184][87424] Updated weights for policy 0, policy_version 266228 (0.0011) -[2023-11-28 07:11:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 136241152. Throughput: 0: 2713.5, 1: 2732.2. Samples: 136260976. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:11:03,445][86177] Avg episode reward: [(0, '-583.930'), (1, '-504.860')] -[2023-11-28 07:11:03,542][87426] Updated weights for policy 1, policy_version 266000 (0.0007) -[2023-11-28 07:11:03,563][87424] Updated weights for policy 0, policy_version 266238 (0.0009) -[2023-11-28 07:11:03,922][87426] Updated weights for policy 1, policy_version 266010 (0.0007) -[2023-11-28 07:11:05,343][87424] Updated weights for policy 0, policy_version 266248 (0.0008) -[2023-11-28 07:11:05,722][87424] Updated weights for policy 0, policy_version 266258 (0.0007) -[2023-11-28 07:11:06,107][87424] Updated weights for policy 0, policy_version 266268 (0.0009) -[2023-11-28 07:11:06,133][87426] Updated weights for policy 1, policy_version 266020 (0.0009) -[2023-11-28 07:11:06,507][87426] Updated weights for policy 1, policy_version 266030 (0.0007) -[2023-11-28 07:11:06,895][87426] Updated weights for policy 1, policy_version 266040 (0.0010) -[2023-11-28 07:11:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 136273920. Throughput: 0: 2720.6, 1: 2696.1. Samples: 136292260. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:11:08,445][86177] Avg episode reward: [(0, '-576.670'), (1, '-511.390')] -[2023-11-28 07:11:08,513][87424] Updated weights for policy 0, policy_version 266278 (0.0007) -[2023-11-28 07:11:08,904][87424] Updated weights for policy 0, policy_version 266288 (0.0009) -[2023-11-28 07:11:09,241][87426] Updated weights for policy 1, policy_version 266050 (0.0011) -[2023-11-28 07:11:09,286][87424] Updated weights for policy 0, policy_version 266298 (0.0012) -[2023-11-28 07:11:09,616][87426] Updated weights for policy 1, policy_version 266060 (0.0009) -[2023-11-28 07:11:09,995][87426] Updated weights for policy 1, policy_version 266070 (0.0009) -[2023-11-28 07:11:10,375][87426] Updated weights for policy 1, policy_version 266080 (0.0011) -[2023-11-28 07:11:11,599][87424] Updated weights for policy 0, policy_version 266308 (0.0012) -[2023-11-28 07:11:11,984][87424] Updated weights for policy 0, policy_version 266318 (0.0011) -[2023-11-28 07:11:12,269][87426] Updated weights for policy 1, policy_version 266090 (0.0012) -[2023-11-28 07:11:12,366][87424] Updated weights for policy 0, policy_version 266328 (0.0010) -[2023-11-28 07:11:12,650][87426] Updated weights for policy 1, policy_version 266100 (0.0012) -[2023-11-28 07:11:13,027][87426] Updated weights for policy 1, policy_version 266110 (0.0012) -[2023-11-28 07:11:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 136306688. Throughput: 0: 2704.2, 1: 2705.5. Samples: 136316408. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:11:13,445][86177] Avg episode reward: [(0, '-543.460'), (1, '-510.950')] -[2023-11-28 07:11:14,329][87424] Updated weights for policy 0, policy_version 266338 (0.0009) -[2023-11-28 07:11:14,720][87424] Updated weights for policy 0, policy_version 266348 (0.0012) -[2023-11-28 07:11:15,042][87426] Updated weights for policy 1, policy_version 266120 (0.0012) -[2023-11-28 07:11:15,087][87424] Updated weights for policy 0, policy_version 266358 (0.0010) -[2023-11-28 07:11:15,420][87426] Updated weights for policy 1, policy_version 266130 (0.0012) -[2023-11-28 07:11:15,475][87424] Updated weights for policy 0, policy_version 266368 (0.0009) -[2023-11-28 07:11:15,796][87426] Updated weights for policy 1, policy_version 266140 (0.0012) -[2023-11-28 07:11:17,487][87424] Updated weights for policy 0, policy_version 266378 (0.0012) -[2023-11-28 07:11:17,820][87426] Updated weights for policy 1, policy_version 266150 (0.0011) -[2023-11-28 07:11:17,876][87424] Updated weights for policy 0, policy_version 266388 (0.0011) -[2023-11-28 07:11:18,197][87426] Updated weights for policy 1, policy_version 266160 (0.0009) -[2023-11-28 07:11:18,251][87424] Updated weights for policy 0, policy_version 266398 (0.0011) -[2023-11-28 07:11:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 136331264. Throughput: 0: 2688.2, 1: 2723.5. Samples: 136342236. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:11:18,446][86177] Avg episode reward: [(0, '-544.100'), (1, '-510.280')] -[2023-11-28 07:11:18,572][87426] Updated weights for policy 1, policy_version 266170 (0.0007) -[2023-11-28 07:11:20,482][87424] Updated weights for policy 0, policy_version 266408 (0.0011) -[2023-11-28 07:11:20,567][87426] Updated weights for policy 1, policy_version 266180 (0.0008) -[2023-11-28 07:11:20,861][87424] Updated weights for policy 0, policy_version 266418 (0.0010) -[2023-11-28 07:11:20,946][87426] Updated weights for policy 1, policy_version 266190 (0.0009) -[2023-11-28 07:11:21,244][87424] Updated weights for policy 0, policy_version 266428 (0.0010) -[2023-11-28 07:11:21,322][87426] Updated weights for policy 1, policy_version 266200 (0.0009) -[2023-11-28 07:11:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 136355840. Throughput: 0: 2681.1, 1: 2740.8. Samples: 136375308. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:11:23,445][86177] Avg episode reward: [(0, '-570.010'), (1, '-517.470')] -[2023-11-28 07:11:23,570][87424] Updated weights for policy 0, policy_version 266438 (0.0010) -[2023-11-28 07:11:23,681][87426] Updated weights for policy 1, policy_version 266210 (0.0011) -[2023-11-28 07:11:23,950][87424] Updated weights for policy 0, policy_version 266448 (0.0011) -[2023-11-28 07:11:24,064][87426] Updated weights for policy 1, policy_version 266220 (0.0008) -[2023-11-28 07:11:24,331][87424] Updated weights for policy 0, policy_version 266458 (0.0008) -[2023-11-28 07:11:24,438][87426] Updated weights for policy 1, policy_version 266230 (0.0008) -[2023-11-28 07:11:24,824][87426] Updated weights for policy 1, policy_version 266240 (0.0008) -[2023-11-28 07:11:26,812][87424] Updated weights for policy 0, policy_version 266468 (0.0010) -[2023-11-28 07:11:27,194][87424] Updated weights for policy 0, policy_version 266478 (0.0011) -[2023-11-28 07:11:27,270][87426] Updated weights for policy 1, policy_version 266250 (0.0009) -[2023-11-28 07:11:27,576][87424] Updated weights for policy 0, policy_version 266488 (0.0009) -[2023-11-28 07:11:27,651][87426] Updated weights for policy 1, policy_version 266260 (0.0007) -[2023-11-28 07:11:28,038][87426] Updated weights for policy 1, policy_version 266270 (0.0007) -[2023-11-28 07:11:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 136388608. Throughput: 0: 2690.1, 1: 2727.2. Samples: 136398600. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:11:28,445][86177] Avg episode reward: [(0, '-535.460'), (1, '-502.660')] -[2023-11-28 07:11:29,285][87424] Updated weights for policy 0, policy_version 266498 (0.0012) -[2023-11-28 07:11:29,667][87424] Updated weights for policy 0, policy_version 266508 (0.0012) -[2023-11-28 07:11:30,052][87424] Updated weights for policy 0, policy_version 266518 (0.0012) -[2023-11-28 07:11:30,269][87426] Updated weights for policy 1, policy_version 266280 (0.0011) -[2023-11-28 07:11:30,439][87424] Updated weights for policy 0, policy_version 266528 (0.0012) -[2023-11-28 07:11:30,644][87426] Updated weights for policy 1, policy_version 266290 (0.0011) -[2023-11-28 07:11:31,038][87426] Updated weights for policy 1, policy_version 266300 (0.0011) -[2023-11-28 07:11:32,492][87424] Updated weights for policy 0, policy_version 266538 (0.0009) -[2023-11-28 07:11:32,867][87424] Updated weights for policy 0, policy_version 266548 (0.0010) -[2023-11-28 07:11:32,992][87426] Updated weights for policy 1, policy_version 266310 (0.0011) -[2023-11-28 07:11:33,254][87424] Updated weights for policy 0, policy_version 266558 (0.0008) -[2023-11-28 07:11:33,357][87426] Updated weights for policy 1, policy_version 266320 (0.0011) -[2023-11-28 07:11:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 136413184. Throughput: 0: 2709.7, 1: 2722.7. Samples: 136423972. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:11:33,445][86177] Avg episode reward: [(0, '-542.520'), (1, '-502.090')] -[2023-11-28 07:11:33,737][87426] Updated weights for policy 1, policy_version 266330 (0.0008) -[2023-11-28 07:11:35,178][87424] Updated weights for policy 0, policy_version 266568 (0.0011) -[2023-11-28 07:11:35,568][87424] Updated weights for policy 0, policy_version 266578 (0.0011) -[2023-11-28 07:11:35,864][87426] Updated weights for policy 1, policy_version 266340 (0.0010) -[2023-11-28 07:11:35,950][87424] Updated weights for policy 0, policy_version 266588 (0.0007) -[2023-11-28 07:11:36,241][87426] Updated weights for policy 1, policy_version 266350 (0.0012) -[2023-11-28 07:11:36,630][87426] Updated weights for policy 1, policy_version 266360 (0.0012) -[2023-11-28 07:11:37,891][87424] Updated weights for policy 0, policy_version 266598 (0.0010) -[2023-11-28 07:11:38,271][87424] Updated weights for policy 0, policy_version 266608 (0.0012) -[2023-11-28 07:11:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 136437760. Throughput: 0: 2751.6, 1: 2707.2. Samples: 136457836. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:11:38,445][86177] Avg episode reward: [(0, '-548.350'), (1, '-502.330')] -[2023-11-28 07:11:38,653][87424] Updated weights for policy 0, policy_version 266618 (0.0012) -[2023-11-28 07:11:39,108][87426] Updated weights for policy 1, policy_version 266370 (0.0012) -[2023-11-28 07:11:39,489][87426] Updated weights for policy 1, policy_version 266380 (0.0012) -[2023-11-28 07:11:39,866][87426] Updated weights for policy 1, policy_version 266390 (0.0012) -[2023-11-28 07:11:40,243][87426] Updated weights for policy 1, policy_version 266400 (0.0012) -[2023-11-28 07:11:40,842][87424] Updated weights for policy 0, policy_version 266628 (0.0012) -[2023-11-28 07:11:41,221][87424] Updated weights for policy 0, policy_version 266638 (0.0011) -[2023-11-28 07:11:41,602][87424] Updated weights for policy 0, policy_version 266648 (0.0009) -[2023-11-28 07:11:42,651][87426] Updated weights for policy 1, policy_version 266410 (0.0011) -[2023-11-28 07:11:43,026][87426] Updated weights for policy 1, policy_version 266420 (0.0008) -[2023-11-28 07:11:43,408][87426] Updated weights for policy 1, policy_version 266430 (0.0007) -[2023-11-28 07:11:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 136462336. Throughput: 0: 2767.0, 1: 2714.4. Samples: 136482372. Policy #0 lag: (min: 31.0, avg: 40.4, max: 63.0) -[2023-11-28 07:11:43,445][86177] Avg episode reward: [(0, '-541.440'), (1, '-500.720')] -[2023-11-28 07:11:44,204][87424] Updated weights for policy 0, policy_version 266658 (0.0010) -[2023-11-28 07:11:44,589][87424] Updated weights for policy 0, policy_version 266668 (0.0011) -[2023-11-28 07:11:44,972][87424] Updated weights for policy 0, policy_version 266678 (0.0011) -[2023-11-28 07:11:45,355][87424] Updated weights for policy 0, policy_version 266688 (0.0010) -[2023-11-28 07:11:45,843][87426] Updated weights for policy 1, policy_version 266440 (0.0008) -[2023-11-28 07:11:46,225][87426] Updated weights for policy 1, policy_version 266450 (0.0009) -[2023-11-28 07:11:46,601][87426] Updated weights for policy 1, policy_version 266460 (0.0008) -[2023-11-28 07:11:47,544][87424] Updated weights for policy 0, policy_version 266698 (0.0012) -[2023-11-28 07:11:47,920][87424] Updated weights for policy 0, policy_version 266708 (0.0012) -[2023-11-28 07:11:48,124][87426] Updated weights for policy 1, policy_version 266470 (0.0010) -[2023-11-28 07:11:48,303][87424] Updated weights for policy 0, policy_version 266718 (0.0009) -[2023-11-28 07:11:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 136495104. Throughput: 0: 2708.0, 1: 2715.2. Samples: 136505020. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:11:48,445][86177] Avg episode reward: [(0, '-542.520'), (1, '-509.420')] -[2023-11-28 07:11:48,509][87426] Updated weights for policy 1, policy_version 266480 (0.0011) -[2023-11-28 07:11:48,883][87426] Updated weights for policy 1, policy_version 266490 (0.0012) -[2023-11-28 07:11:50,587][87424] Updated weights for policy 0, policy_version 266728 (0.0011) -[2023-11-28 07:11:50,923][87426] Updated weights for policy 1, policy_version 266500 (0.0011) -[2023-11-28 07:11:50,970][87424] Updated weights for policy 0, policy_version 266738 (0.0012) -[2023-11-28 07:11:51,313][87426] Updated weights for policy 1, policy_version 266510 (0.0010) -[2023-11-28 07:11:51,349][87424] Updated weights for policy 0, policy_version 266748 (0.0011) -[2023-11-28 07:11:51,688][87426] Updated weights for policy 1, policy_version 266520 (0.0011) -[2023-11-28 07:11:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 136519680. Throughput: 0: 2711.9, 1: 2750.0. Samples: 136538044. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:11:53,446][86177] Avg episode reward: [(0, '-543.060'), (1, '-508.020')] -[2023-11-28 07:11:53,579][87424] Updated weights for policy 0, policy_version 266758 (0.0011) -[2023-11-28 07:11:53,596][87426] Updated weights for policy 1, policy_version 266530 (0.0011) -[2023-11-28 07:11:53,958][87424] Updated weights for policy 0, policy_version 266768 (0.0011) -[2023-11-28 07:11:53,978][87426] Updated weights for policy 1, policy_version 266540 (0.0010) -[2023-11-28 07:11:54,328][87424] Updated weights for policy 0, policy_version 266778 (0.0007) -[2023-11-28 07:11:54,366][87426] Updated weights for policy 1, policy_version 266550 (0.0007) -[2023-11-28 07:11:54,736][87426] Updated weights for policy 1, policy_version 266560 (0.0007) -[2023-11-28 07:11:56,491][87426] Updated weights for policy 1, policy_version 266570 (0.0009) -[2023-11-28 07:11:56,880][87426] Updated weights for policy 1, policy_version 266580 (0.0008) -[2023-11-28 07:11:56,895][87424] Updated weights for policy 0, policy_version 266788 (0.0007) -[2023-11-28 07:11:57,250][87426] Updated weights for policy 1, policy_version 266590 (0.0007) -[2023-11-28 07:11:57,278][87424] Updated weights for policy 0, policy_version 266798 (0.0008) -[2023-11-28 07:11:57,664][87424] Updated weights for policy 0, policy_version 266808 (0.0007) -[2023-11-28 07:11:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 136552448. Throughput: 0: 2708.9, 1: 2765.9. Samples: 136562772. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:11:58,445][86177] Avg episode reward: [(0, '-527.050'), (1, '-507.600')] -[2023-11-28 07:11:59,452][87424] Updated weights for policy 0, policy_version 266818 (0.0008) -[2023-11-28 07:11:59,669][87426] Updated weights for policy 1, policy_version 266600 (0.0008) -[2023-11-28 07:11:59,834][87424] Updated weights for policy 0, policy_version 266828 (0.0008) -[2023-11-28 07:12:00,050][87426] Updated weights for policy 1, policy_version 266610 (0.0009) -[2023-11-28 07:12:00,215][87424] Updated weights for policy 0, policy_version 266838 (0.0008) -[2023-11-28 07:12:00,440][87426] Updated weights for policy 1, policy_version 266620 (0.0008) -[2023-11-28 07:12:00,602][87424] Updated weights for policy 0, policy_version 266848 (0.0008) -[2023-11-28 07:12:02,610][87426] Updated weights for policy 1, policy_version 266630 (0.0008) -[2023-11-28 07:12:02,987][87426] Updated weights for policy 1, policy_version 266640 (0.0009) -[2023-11-28 07:12:03,049][87424] Updated weights for policy 0, policy_version 266858 (0.0009) -[2023-11-28 07:12:03,374][87426] Updated weights for policy 1, policy_version 266650 (0.0009) -[2023-11-28 07:12:03,423][87424] Updated weights for policy 0, policy_version 266868 (0.0011) -[2023-11-28 07:12:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 136568832. Throughput: 0: 2694.7, 1: 2737.1. Samples: 136586664. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:03,445][86177] Avg episode reward: [(0, '-506.000'), (1, '-500.930')] -[2023-11-28 07:12:03,806][87424] Updated weights for policy 0, policy_version 266878 (0.0010) -[2023-11-28 07:12:05,374][87426] Updated weights for policy 1, policy_version 266660 (0.0009) -[2023-11-28 07:12:05,751][87426] Updated weights for policy 1, policy_version 266670 (0.0011) -[2023-11-28 07:12:05,898][87424] Updated weights for policy 0, policy_version 266888 (0.0010) -[2023-11-28 07:12:06,135][87426] Updated weights for policy 1, policy_version 266680 (0.0010) -[2023-11-28 07:12:06,281][87424] Updated weights for policy 0, policy_version 266898 (0.0007) -[2023-11-28 07:12:06,667][87424] Updated weights for policy 0, policy_version 266908 (0.0007) -[2023-11-28 07:12:08,371][87426] Updated weights for policy 1, policy_version 266690 (0.0011) -[2023-11-28 07:12:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 136601600. Throughput: 0: 2728.5, 1: 2710.0. Samples: 136620044. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:08,445][86177] Avg episode reward: [(0, '-517.730'), (1, '-494.460')] -[2023-11-28 07:12:08,606][87424] Updated weights for policy 0, policy_version 266918 (0.0010) -[2023-11-28 07:12:08,753][87426] Updated weights for policy 1, policy_version 266700 (0.0011) -[2023-11-28 07:12:08,990][87424] Updated weights for policy 0, policy_version 266928 (0.0010) -[2023-11-28 07:12:09,129][87426] Updated weights for policy 1, policy_version 266710 (0.0010) -[2023-11-28 07:12:09,366][87424] Updated weights for policy 0, policy_version 266938 (0.0008) -[2023-11-28 07:12:09,498][87426] Updated weights for policy 1, policy_version 266720 (0.0012) -[2023-11-28 07:12:11,540][87424] Updated weights for policy 0, policy_version 266948 (0.0011) -[2023-11-28 07:12:11,791][87426] Updated weights for policy 1, policy_version 266730 (0.0011) -[2023-11-28 07:12:11,924][87424] Updated weights for policy 0, policy_version 266958 (0.0010) -[2023-11-28 07:12:12,163][87426] Updated weights for policy 1, policy_version 266740 (0.0010) -[2023-11-28 07:12:12,314][87424] Updated weights for policy 0, policy_version 266968 (0.0011) -[2023-11-28 07:12:12,543][87426] Updated weights for policy 1, policy_version 266750 (0.0009) -[2023-11-28 07:12:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 136634368. Throughput: 0: 2727.6, 1: 2729.6. Samples: 136644172. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:13,445][86177] Avg episode reward: [(0, '-527.650'), (1, '-496.410')] -[2023-11-28 07:12:14,550][87424] Updated weights for policy 0, policy_version 266978 (0.0007) -[2023-11-28 07:12:14,933][87424] Updated weights for policy 0, policy_version 266988 (0.0007) -[2023-11-28 07:12:15,144][87426] Updated weights for policy 1, policy_version 266760 (0.0011) -[2023-11-28 07:12:15,330][87424] Updated weights for policy 0, policy_version 266998 (0.0008) -[2023-11-28 07:12:15,524][87426] Updated weights for policy 1, policy_version 266770 (0.0012) -[2023-11-28 07:12:15,708][87424] Updated weights for policy 0, policy_version 267008 (0.0011) -[2023-11-28 07:12:15,905][87426] Updated weights for policy 1, policy_version 266780 (0.0012) -[2023-11-28 07:12:17,576][87426] Updated weights for policy 1, policy_version 266790 (0.0010) -[2023-11-28 07:12:17,966][87426] Updated weights for policy 1, policy_version 266800 (0.0007) -[2023-11-28 07:12:18,102][87424] Updated weights for policy 0, policy_version 267018 (0.0011) -[2023-11-28 07:12:18,347][87426] Updated weights for policy 1, policy_version 266810 (0.0010) -[2023-11-28 07:12:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 136650752. Throughput: 0: 2678.3, 1: 2721.8. Samples: 136666976. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:18,446][86177] Avg episode reward: [(0, '-525.280'), (1, '-492.250')] -[2023-11-28 07:12:18,491][87424] Updated weights for policy 0, policy_version 267028 (0.0007) -[2023-11-28 07:12:18,572][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000266816_68304896.pth... -[2023-11-28 07:12:18,604][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000264256_67649536.pth -[2023-11-28 07:12:18,609][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000266816_68304896.pth -[2023-11-28 07:12:18,874][87424] Updated weights for policy 0, policy_version 267038 (0.0008) -[2023-11-28 07:12:18,949][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000267040_68362240.pth... -[2023-11-28 07:12:18,997][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000264512_67715072.pth -[2023-11-28 07:12:19,004][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000267040_68362240.pth -[2023-11-28 07:12:20,920][87426] Updated weights for policy 1, policy_version 266820 (0.0012) -[2023-11-28 07:12:21,292][87426] Updated weights for policy 1, policy_version 266830 (0.0009) -[2023-11-28 07:12:21,407][87424] Updated weights for policy 0, policy_version 267048 (0.0010) -[2023-11-28 07:12:21,680][87426] Updated weights for policy 1, policy_version 266840 (0.0009) -[2023-11-28 07:12:21,802][87424] Updated weights for policy 0, policy_version 267058 (0.0011) -[2023-11-28 07:12:22,175][87424] Updated weights for policy 0, policy_version 267068 (0.0009) -[2023-11-28 07:12:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 136683520. Throughput: 0: 2637.9, 1: 2732.1. Samples: 136699484. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:23,445][86177] Avg episode reward: [(0, '-516.260'), (1, '-512.200')] -[2023-11-28 07:12:24,186][87426] Updated weights for policy 1, policy_version 266850 (0.0010) -[2023-11-28 07:12:24,553][87426] Updated weights for policy 1, policy_version 266860 (0.0010) -[2023-11-28 07:12:24,683][87424] Updated weights for policy 0, policy_version 267078 (0.0011) -[2023-11-28 07:12:24,938][87426] Updated weights for policy 1, policy_version 266870 (0.0010) -[2023-11-28 07:12:25,058][87424] Updated weights for policy 0, policy_version 267088 (0.0010) -[2023-11-28 07:12:25,311][87426] Updated weights for policy 1, policy_version 266880 (0.0011) -[2023-11-28 07:12:25,434][87424] Updated weights for policy 0, policy_version 267098 (0.0009) -[2023-11-28 07:12:27,126][87424] Updated weights for policy 0, policy_version 267108 (0.0007) -[2023-11-28 07:12:27,509][87424] Updated weights for policy 0, policy_version 267118 (0.0011) -[2023-11-28 07:12:27,659][87426] Updated weights for policy 1, policy_version 266890 (0.0009) -[2023-11-28 07:12:27,890][87424] Updated weights for policy 0, policy_version 267128 (0.0009) -[2023-11-28 07:12:28,040][87426] Updated weights for policy 1, policy_version 266900 (0.0007) -[2023-11-28 07:12:28,424][87426] Updated weights for policy 1, policy_version 266910 (0.0010) -[2023-11-28 07:12:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 136708096. Throughput: 0: 2620.3, 1: 2752.1. Samples: 136724128. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:28,445][86177] Avg episode reward: [(0, '-516.760'), (1, '-520.980')] -[2023-11-28 07:12:30,333][87424] Updated weights for policy 0, policy_version 267138 (0.0008) -[2023-11-28 07:12:30,754][87424] Updated weights for policy 0, policy_version 267148 (0.0010) -[2023-11-28 07:12:30,809][87426] Updated weights for policy 1, policy_version 266920 (0.0010) -[2023-11-28 07:12:31,130][87424] Updated weights for policy 0, policy_version 267158 (0.0007) -[2023-11-28 07:12:31,180][87426] Updated weights for policy 1, policy_version 266930 (0.0011) -[2023-11-28 07:12:31,508][87424] Updated weights for policy 0, policy_version 267168 (0.0008) -[2023-11-28 07:12:31,564][87426] Updated weights for policy 1, policy_version 266940 (0.0012) -[2023-11-28 07:12:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 136732672. Throughput: 0: 2656.0, 1: 2734.2. Samples: 136747580. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:33,445][86177] Avg episode reward: [(0, '-519.180'), (1, '-523.620')] -[2023-11-28 07:12:33,668][87426] Updated weights for policy 1, policy_version 266950 (0.0011) -[2023-11-28 07:12:33,900][87424] Updated weights for policy 0, policy_version 267178 (0.0010) -[2023-11-28 07:12:34,052][87426] Updated weights for policy 1, policy_version 266960 (0.0011) -[2023-11-28 07:12:34,288][87424] Updated weights for policy 0, policy_version 267188 (0.0010) -[2023-11-28 07:12:34,422][87426] Updated weights for policy 1, policy_version 266970 (0.0011) -[2023-11-28 07:12:34,671][87424] Updated weights for policy 0, policy_version 267198 (0.0008) -[2023-11-28 07:12:36,376][87426] Updated weights for policy 1, policy_version 266980 (0.0010) -[2023-11-28 07:12:36,754][87426] Updated weights for policy 1, policy_version 266990 (0.0009) -[2023-11-28 07:12:37,135][87426] Updated weights for policy 1, policy_version 267000 (0.0010) -[2023-11-28 07:12:37,191][87424] Updated weights for policy 0, policy_version 267208 (0.0010) -[2023-11-28 07:12:37,575][87424] Updated weights for policy 0, policy_version 267218 (0.0012) -[2023-11-28 07:12:37,970][87424] Updated weights for policy 0, policy_version 267228 (0.0011) -[2023-11-28 07:12:38,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 136765440. Throughput: 0: 2666.1, 1: 2701.2. Samples: 136779572. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:38,445][86177] Avg episode reward: [(0, '-562.030'), (1, '-520.860')] -[2023-11-28 07:12:39,311][87426] Updated weights for policy 1, policy_version 267010 (0.0011) -[2023-11-28 07:12:39,690][87426] Updated weights for policy 1, policy_version 267020 (0.0007) -[2023-11-28 07:12:40,095][87426] Updated weights for policy 1, policy_version 267030 (0.0010) -[2023-11-28 07:12:40,458][87426] Updated weights for policy 1, policy_version 267040 (0.0011) -[2023-11-28 07:12:40,487][87424] Updated weights for policy 0, policy_version 267238 (0.0009) -[2023-11-28 07:12:40,874][87424] Updated weights for policy 0, policy_version 267248 (0.0008) -[2023-11-28 07:12:41,256][87424] Updated weights for policy 0, policy_version 267258 (0.0008) -[2023-11-28 07:12:42,638][87426] Updated weights for policy 1, policy_version 267050 (0.0011) -[2023-11-28 07:12:43,020][87426] Updated weights for policy 1, policy_version 267060 (0.0010) -[2023-11-28 07:12:43,401][87426] Updated weights for policy 1, policy_version 267070 (0.0008) -[2023-11-28 07:12:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 136781824. Throughput: 0: 2676.6, 1: 2671.9. Samples: 136803456. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:43,445][86177] Avg episode reward: [(0, '-564.770'), (1, '-510.890')] -[2023-11-28 07:12:43,721][87424] Updated weights for policy 0, policy_version 267268 (0.0009) -[2023-11-28 07:12:44,098][87424] Updated weights for policy 0, policy_version 267278 (0.0012) -[2023-11-28 07:12:44,484][87424] Updated weights for policy 0, policy_version 267288 (0.0011) -[2023-11-28 07:12:45,205][87426] Updated weights for policy 1, policy_version 267080 (0.0011) -[2023-11-28 07:12:45,583][87426] Updated weights for policy 1, policy_version 267090 (0.0010) -[2023-11-28 07:12:45,969][87426] Updated weights for policy 1, policy_version 267100 (0.0010) -[2023-11-28 07:12:47,068][87424] Updated weights for policy 0, policy_version 267298 (0.0008) -[2023-11-28 07:12:47,442][87424] Updated weights for policy 0, policy_version 267308 (0.0012) -[2023-11-28 07:12:47,817][87424] Updated weights for policy 0, policy_version 267318 (0.0011) -[2023-11-28 07:12:47,847][87426] Updated weights for policy 1, policy_version 267110 (0.0012) -[2023-11-28 07:12:48,206][87424] Updated weights for policy 0, policy_version 267328 (0.0007) -[2023-11-28 07:12:48,225][87426] Updated weights for policy 1, policy_version 267120 (0.0010) -[2023-11-28 07:12:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 136814592. Throughput: 0: 2650.5, 1: 2686.7. Samples: 136826836. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:48,445][86177] Avg episode reward: [(0, '-566.800'), (1, '-516.700')] -[2023-11-28 07:12:48,614][87426] Updated weights for policy 1, policy_version 267130 (0.0007) -[2023-11-28 07:12:50,545][87426] Updated weights for policy 1, policy_version 267140 (0.0009) -[2023-11-28 07:12:50,795][87424] Updated weights for policy 0, policy_version 267338 (0.0011) -[2023-11-28 07:12:50,924][87426] Updated weights for policy 1, policy_version 267150 (0.0011) -[2023-11-28 07:12:51,169][87424] Updated weights for policy 0, policy_version 267348 (0.0011) -[2023-11-28 07:12:51,299][87426] Updated weights for policy 1, policy_version 267160 (0.0012) -[2023-11-28 07:12:51,553][87424] Updated weights for policy 0, policy_version 267358 (0.0011) -[2023-11-28 07:12:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 136839168. Throughput: 0: 2606.1, 1: 2718.0. Samples: 136859632. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:53,445][86177] Avg episode reward: [(0, '-555.070'), (1, '-521.430')] -[2023-11-28 07:12:53,530][87424] Updated weights for policy 0, policy_version 267368 (0.0011) -[2023-11-28 07:12:53,818][87426] Updated weights for policy 1, policy_version 267170 (0.0011) -[2023-11-28 07:12:53,919][87424] Updated weights for policy 0, policy_version 267378 (0.0012) -[2023-11-28 07:12:54,196][87426] Updated weights for policy 1, policy_version 267180 (0.0012) -[2023-11-28 07:12:54,306][87424] Updated weights for policy 0, policy_version 267388 (0.0012) -[2023-11-28 07:12:54,572][87426] Updated weights for policy 1, policy_version 267190 (0.0012) -[2023-11-28 07:12:54,945][87426] Updated weights for policy 1, policy_version 267200 (0.0012) -[2023-11-28 07:12:56,222][87424] Updated weights for policy 0, policy_version 267398 (0.0012) -[2023-11-28 07:12:56,610][87424] Updated weights for policy 0, policy_version 267408 (0.0012) -[2023-11-28 07:12:56,985][87424] Updated weights for policy 0, policy_version 267418 (0.0011) -[2023-11-28 07:12:57,174][87426] Updated weights for policy 1, policy_version 267210 (0.0012) -[2023-11-28 07:12:57,547][87426] Updated weights for policy 1, policy_version 267220 (0.0010) -[2023-11-28 07:12:57,925][87426] Updated weights for policy 1, policy_version 267230 (0.0008) -[2023-11-28 07:12:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 136871936. Throughput: 0: 2615.5, 1: 2718.4. Samples: 136884200. Policy #0 lag: (min: 23.0, avg: 29.9, max: 55.0) -[2023-11-28 07:12:58,446][86177] Avg episode reward: [(0, '-519.230'), (1, '-532.590')] -[2023-11-28 07:12:59,074][87424] Updated weights for policy 0, policy_version 267428 (0.0011) -[2023-11-28 07:12:59,455][87424] Updated weights for policy 0, policy_version 267438 (0.0012) -[2023-11-28 07:12:59,833][87424] Updated weights for policy 0, policy_version 267448 (0.0011) -[2023-11-28 07:13:00,114][87426] Updated weights for policy 1, policy_version 267240 (0.0009) -[2023-11-28 07:13:00,494][87426] Updated weights for policy 1, policy_version 267250 (0.0008) -[2023-11-28 07:13:00,880][87426] Updated weights for policy 1, policy_version 267260 (0.0008) -[2023-11-28 07:13:01,956][87424] Updated weights for policy 0, policy_version 267458 (0.0012) -[2023-11-28 07:13:02,357][87424] Updated weights for policy 0, policy_version 267468 (0.0011) -[2023-11-28 07:13:02,736][87424] Updated weights for policy 0, policy_version 267478 (0.0007) -[2023-11-28 07:13:03,116][87426] Updated weights for policy 1, policy_version 267270 (0.0010) -[2023-11-28 07:13:03,123][87424] Updated weights for policy 0, policy_version 267488 (0.0008) -[2023-11-28 07:13:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 136896512. Throughput: 0: 2643.1, 1: 2743.1. Samples: 136909356. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:03,445][86177] Avg episode reward: [(0, '-529.420'), (1, '-531.930')] -[2023-11-28 07:13:03,498][87426] Updated weights for policy 1, policy_version 267280 (0.0012) -[2023-11-28 07:13:03,889][87426] Updated weights for policy 1, policy_version 267290 (0.0010) -[2023-11-28 07:13:05,168][87424] Updated weights for policy 0, policy_version 267498 (0.0012) -[2023-11-28 07:13:05,506][87426] Updated weights for policy 1, policy_version 267300 (0.0011) -[2023-11-28 07:13:05,549][87424] Updated weights for policy 0, policy_version 267508 (0.0011) -[2023-11-28 07:13:05,891][87426] Updated weights for policy 1, policy_version 267310 (0.0011) -[2023-11-28 07:13:05,938][87424] Updated weights for policy 0, policy_version 267518 (0.0011) -[2023-11-28 07:13:06,268][87426] Updated weights for policy 1, policy_version 267320 (0.0011) -[2023-11-28 07:13:08,015][87424] Updated weights for policy 0, policy_version 267528 (0.0010) -[2023-11-28 07:13:08,406][87424] Updated weights for policy 0, policy_version 267538 (0.0007) -[2023-11-28 07:13:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 136921088. Throughput: 0: 2650.5, 1: 2742.1. Samples: 136942152. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:08,445][86177] Avg episode reward: [(0, '-523.830'), (1, '-525.170')] -[2023-11-28 07:13:08,536][87426] Updated weights for policy 1, policy_version 267330 (0.0010) -[2023-11-28 07:13:08,794][87424] Updated weights for policy 0, policy_version 267548 (0.0008) -[2023-11-28 07:13:08,917][87426] Updated weights for policy 1, policy_version 267340 (0.0009) -[2023-11-28 07:13:09,280][87426] Updated weights for policy 1, policy_version 267350 (0.0012) -[2023-11-28 07:13:09,657][87426] Updated weights for policy 1, policy_version 267360 (0.0012) -[2023-11-28 07:13:10,738][87424] Updated weights for policy 0, policy_version 267558 (0.0011) -[2023-11-28 07:13:11,121][87424] Updated weights for policy 0, policy_version 267568 (0.0012) -[2023-11-28 07:13:11,494][87424] Updated weights for policy 0, policy_version 267578 (0.0010) -[2023-11-28 07:13:12,042][87426] Updated weights for policy 1, policy_version 267370 (0.0011) -[2023-11-28 07:13:12,417][87426] Updated weights for policy 1, policy_version 267380 (0.0011) -[2023-11-28 07:13:12,791][87426] Updated weights for policy 1, policy_version 267390 (0.0010) -[2023-11-28 07:13:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 136953856. Throughput: 0: 2652.6, 1: 2722.8. Samples: 136966024. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:13,446][86177] Avg episode reward: [(0, '-542.360'), (1, '-490.100')] -[2023-11-28 07:13:13,965][87424] Updated weights for policy 0, policy_version 267588 (0.0010) -[2023-11-28 07:13:14,341][87424] Updated weights for policy 0, policy_version 267598 (0.0012) -[2023-11-28 07:13:14,721][87424] Updated weights for policy 0, policy_version 267608 (0.0012) -[2023-11-28 07:13:14,906][87426] Updated weights for policy 1, policy_version 267400 (0.0009) -[2023-11-28 07:13:15,281][87426] Updated weights for policy 1, policy_version 267410 (0.0008) -[2023-11-28 07:13:15,657][87426] Updated weights for policy 1, policy_version 267420 (0.0012) -[2023-11-28 07:13:17,215][87424] Updated weights for policy 0, policy_version 267618 (0.0012) -[2023-11-28 07:13:17,596][87424] Updated weights for policy 0, policy_version 267628 (0.0011) -[2023-11-28 07:13:17,599][87426] Updated weights for policy 1, policy_version 267430 (0.0012) -[2023-11-28 07:13:17,975][87426] Updated weights for policy 1, policy_version 267440 (0.0012) -[2023-11-28 07:13:17,977][87424] Updated weights for policy 0, policy_version 267638 (0.0008) -[2023-11-28 07:13:18,352][87426] Updated weights for policy 1, policy_version 267450 (0.0011) -[2023-11-28 07:13:18,360][87424] Updated weights for policy 0, policy_version 267648 (0.0009) -[2023-11-28 07:13:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 136978432. Throughput: 0: 2639.3, 1: 2750.2. Samples: 136990108. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:18,446][86177] Avg episode reward: [(0, '-542.850'), (1, '-490.520')] -[2023-11-28 07:13:20,748][87426] Updated weights for policy 1, policy_version 267460 (0.0012) -[2023-11-28 07:13:20,787][87424] Updated weights for policy 0, policy_version 267658 (0.0011) -[2023-11-28 07:13:21,135][87426] Updated weights for policy 1, policy_version 267470 (0.0012) -[2023-11-28 07:13:21,160][87424] Updated weights for policy 0, policy_version 267668 (0.0011) -[2023-11-28 07:13:21,511][87426] Updated weights for policy 1, policy_version 267480 (0.0011) -[2023-11-28 07:13:21,545][87424] Updated weights for policy 0, policy_version 267678 (0.0012) -[2023-11-28 07:13:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 137003008. Throughput: 0: 2635.0, 1: 2761.5. Samples: 137022416. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:23,445][86177] Avg episode reward: [(0, '-546.180'), (1, '-502.630')] -[2023-11-28 07:13:23,472][87424] Updated weights for policy 0, policy_version 267688 (0.0012) -[2023-11-28 07:13:23,814][87426] Updated weights for policy 1, policy_version 267490 (0.0011) -[2023-11-28 07:13:23,855][87424] Updated weights for policy 0, policy_version 267698 (0.0012) -[2023-11-28 07:13:24,199][87426] Updated weights for policy 1, policy_version 267500 (0.0008) -[2023-11-28 07:13:24,238][87424] Updated weights for policy 0, policy_version 267708 (0.0011) -[2023-11-28 07:13:24,572][87426] Updated weights for policy 1, policy_version 267510 (0.0007) -[2023-11-28 07:13:24,955][87426] Updated weights for policy 1, policy_version 267520 (0.0008) -[2023-11-28 07:13:26,074][87424] Updated weights for policy 0, policy_version 267718 (0.0010) -[2023-11-28 07:13:26,459][87424] Updated weights for policy 0, policy_version 267728 (0.0007) -[2023-11-28 07:13:26,845][87424] Updated weights for policy 0, policy_version 267738 (0.0010) -[2023-11-28 07:13:27,363][87426] Updated weights for policy 1, policy_version 267530 (0.0012) -[2023-11-28 07:13:27,732][87426] Updated weights for policy 1, policy_version 267540 (0.0012) -[2023-11-28 07:13:28,116][87426] Updated weights for policy 1, policy_version 267550 (0.0012) -[2023-11-28 07:13:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 137035776. Throughput: 0: 2657.7, 1: 2764.0. Samples: 137047432. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:28,445][86177] Avg episode reward: [(0, '-557.510'), (1, '-529.190')] -[2023-11-28 07:13:29,275][87424] Updated weights for policy 0, policy_version 267748 (0.0010) -[2023-11-28 07:13:29,646][87424] Updated weights for policy 0, policy_version 267758 (0.0007) -[2023-11-28 07:13:30,023][87424] Updated weights for policy 0, policy_version 267768 (0.0010) -[2023-11-28 07:13:30,480][87426] Updated weights for policy 1, policy_version 267560 (0.0010) -[2023-11-28 07:13:30,862][87426] Updated weights for policy 1, policy_version 267570 (0.0010) -[2023-11-28 07:13:31,253][87426] Updated weights for policy 1, policy_version 267580 (0.0007) -[2023-11-28 07:13:32,408][87424] Updated weights for policy 0, policy_version 267778 (0.0010) -[2023-11-28 07:13:32,782][87424] Updated weights for policy 0, policy_version 267788 (0.0009) -[2023-11-28 07:13:33,167][87424] Updated weights for policy 0, policy_version 267798 (0.0011) -[2023-11-28 07:13:33,303][87426] Updated weights for policy 1, policy_version 267590 (0.0010) -[2023-11-28 07:13:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 137052160. Throughput: 0: 2693.5, 1: 2745.6. Samples: 137071596. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:33,445][86177] Avg episode reward: [(0, '-535.660'), (1, '-528.580')] -[2023-11-28 07:13:33,542][87424] Updated weights for policy 0, policy_version 267808 (0.0010) -[2023-11-28 07:13:33,679][87426] Updated weights for policy 1, policy_version 267600 (0.0012) -[2023-11-28 07:13:34,063][87426] Updated weights for policy 1, policy_version 267610 (0.0011) -[2023-11-28 07:13:35,287][87424] Updated weights for policy 0, policy_version 267818 (0.0012) -[2023-11-28 07:13:35,658][87424] Updated weights for policy 0, policy_version 267828 (0.0011) -[2023-11-28 07:13:35,811][87426] Updated weights for policy 1, policy_version 267620 (0.0012) -[2023-11-28 07:13:36,045][87424] Updated weights for policy 0, policy_version 267838 (0.0011) -[2023-11-28 07:13:36,196][87426] Updated weights for policy 1, policy_version 267630 (0.0010) -[2023-11-28 07:13:36,578][87426] Updated weights for policy 1, policy_version 267640 (0.0012) -[2023-11-28 07:13:38,016][87424] Updated weights for policy 0, policy_version 267848 (0.0009) -[2023-11-28 07:13:38,400][87424] Updated weights for policy 0, policy_version 267858 (0.0011) -[2023-11-28 07:13:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 137084928. Throughput: 0: 2738.0, 1: 2725.5. Samples: 137105492. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:38,445][86177] Avg episode reward: [(0, '-538.720'), (1, '-537.970')] -[2023-11-28 07:13:38,778][87424] Updated weights for policy 0, policy_version 267868 (0.0008) -[2023-11-28 07:13:39,018][87426] Updated weights for policy 1, policy_version 267650 (0.0012) -[2023-11-28 07:13:39,402][87426] Updated weights for policy 1, policy_version 267660 (0.0012) -[2023-11-28 07:13:39,777][87426] Updated weights for policy 1, policy_version 267670 (0.0012) -[2023-11-28 07:13:40,152][87426] Updated weights for policy 1, policy_version 267680 (0.0012) -[2023-11-28 07:13:40,906][87424] Updated weights for policy 0, policy_version 267878 (0.0011) -[2023-11-28 07:13:41,285][87424] Updated weights for policy 0, policy_version 267888 (0.0012) -[2023-11-28 07:13:41,681][87424] Updated weights for policy 0, policy_version 267898 (0.0012) -[2023-11-28 07:13:42,579][87426] Updated weights for policy 1, policy_version 267690 (0.0009) -[2023-11-28 07:13:42,958][87426] Updated weights for policy 1, policy_version 267700 (0.0011) -[2023-11-28 07:13:43,333][87426] Updated weights for policy 1, policy_version 267710 (0.0012) -[2023-11-28 07:13:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 137117696. Throughput: 0: 2735.3, 1: 2706.4. Samples: 137129076. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:43,445][86177] Avg episode reward: [(0, '-524.670'), (1, '-509.650')] -[2023-11-28 07:13:43,885][87424] Updated weights for policy 0, policy_version 267908 (0.0011) -[2023-11-28 07:13:44,268][87424] Updated weights for policy 0, policy_version 267918 (0.0009) -[2023-11-28 07:13:44,646][87424] Updated weights for policy 0, policy_version 267928 (0.0008) -[2023-11-28 07:13:45,298][87426] Updated weights for policy 1, policy_version 267720 (0.0012) -[2023-11-28 07:13:45,675][87426] Updated weights for policy 1, policy_version 267730 (0.0012) -[2023-11-28 07:13:46,059][87426] Updated weights for policy 1, policy_version 267740 (0.0012) -[2023-11-28 07:13:46,989][87424] Updated weights for policy 0, policy_version 267938 (0.0008) -[2023-11-28 07:13:47,372][87424] Updated weights for policy 0, policy_version 267948 (0.0011) -[2023-11-28 07:13:47,752][87424] Updated weights for policy 0, policy_version 267958 (0.0011) -[2023-11-28 07:13:47,752][87426] Updated weights for policy 1, policy_version 267750 (0.0012) -[2023-11-28 07:13:48,130][87426] Updated weights for policy 1, policy_version 267760 (0.0012) -[2023-11-28 07:13:48,145][87424] Updated weights for policy 0, policy_version 267968 (0.0012) -[2023-11-28 07:13:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 137142272. Throughput: 0: 2725.2, 1: 2703.8. Samples: 137153664. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:48,446][86177] Avg episode reward: [(0, '-522.810'), (1, '-509.530')] -[2023-11-28 07:13:48,509][87426] Updated weights for policy 1, policy_version 267770 (0.0009) -[2023-11-28 07:13:50,589][87424] Updated weights for policy 0, policy_version 267978 (0.0012) -[2023-11-28 07:13:50,595][87426] Updated weights for policy 1, policy_version 267780 (0.0007) -[2023-11-28 07:13:50,969][87424] Updated weights for policy 0, policy_version 267988 (0.0012) -[2023-11-28 07:13:50,974][87426] Updated weights for policy 1, policy_version 267790 (0.0008) -[2023-11-28 07:13:51,337][87426] Updated weights for policy 1, policy_version 267800 (0.0009) -[2023-11-28 07:13:51,347][87424] Updated weights for policy 0, policy_version 267998 (0.0012) -[2023-11-28 07:13:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 137166848. Throughput: 0: 2719.7, 1: 2714.9. Samples: 137186712. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:53,445][86177] Avg episode reward: [(0, '-572.010'), (1, '-502.560')] -[2023-11-28 07:13:53,458][87424] Updated weights for policy 0, policy_version 268008 (0.0012) -[2023-11-28 07:13:53,842][87424] Updated weights for policy 0, policy_version 268018 (0.0008) -[2023-11-28 07:13:53,864][87426] Updated weights for policy 1, policy_version 267810 (0.0011) -[2023-11-28 07:13:54,223][87424] Updated weights for policy 0, policy_version 268028 (0.0007) -[2023-11-28 07:13:54,243][87426] Updated weights for policy 1, policy_version 267820 (0.0012) -[2023-11-28 07:13:54,624][87426] Updated weights for policy 1, policy_version 267830 (0.0010) -[2023-11-28 07:13:54,995][87426] Updated weights for policy 1, policy_version 267840 (0.0008) -[2023-11-28 07:13:55,974][87424] Updated weights for policy 0, policy_version 268038 (0.0010) -[2023-11-28 07:13:56,367][87424] Updated weights for policy 0, policy_version 268048 (0.0012) -[2023-11-28 07:13:56,745][87424] Updated weights for policy 0, policy_version 268058 (0.0012) -[2023-11-28 07:13:57,117][87426] Updated weights for policy 1, policy_version 267850 (0.0009) -[2023-11-28 07:13:57,503][87426] Updated weights for policy 1, policy_version 267860 (0.0007) -[2023-11-28 07:13:57,876][87426] Updated weights for policy 1, policy_version 267870 (0.0008) -[2023-11-28 07:13:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 137199616. Throughput: 0: 2751.7, 1: 2725.0. Samples: 137212472. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:13:58,445][86177] Avg episode reward: [(0, '-585.170'), (1, '-500.170')] -[2023-11-28 07:13:58,890][87424] Updated weights for policy 0, policy_version 268068 (0.0012) -[2023-11-28 07:13:59,269][87424] Updated weights for policy 0, policy_version 268078 (0.0012) -[2023-11-28 07:13:59,654][87424] Updated weights for policy 0, policy_version 268088 (0.0012) -[2023-11-28 07:13:59,681][87426] Updated weights for policy 1, policy_version 267880 (0.0008) -[2023-11-28 07:14:00,056][87426] Updated weights for policy 1, policy_version 267890 (0.0010) -[2023-11-28 07:14:00,435][87426] Updated weights for policy 1, policy_version 267900 (0.0009) -[2023-11-28 07:14:01,788][87424] Updated weights for policy 0, policy_version 268098 (0.0012) -[2023-11-28 07:14:02,161][87424] Updated weights for policy 0, policy_version 268108 (0.0012) -[2023-11-28 07:14:02,541][87424] Updated weights for policy 0, policy_version 268118 (0.0011) -[2023-11-28 07:14:02,672][87426] Updated weights for policy 1, policy_version 267910 (0.0011) -[2023-11-28 07:14:02,920][87424] Updated weights for policy 0, policy_version 268128 (0.0010) -[2023-11-28 07:14:03,060][87426] Updated weights for policy 1, policy_version 267920 (0.0012) -[2023-11-28 07:14:03,437][87426] Updated weights for policy 1, policy_version 267930 (0.0012) -[2023-11-28 07:14:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 137224192. Throughput: 0: 2745.6, 1: 2709.3. Samples: 137235576. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:14:03,445][86177] Avg episode reward: [(0, '-591.080'), (1, '-491.410')] -[2023-11-28 07:14:05,189][87424] Updated weights for policy 0, policy_version 268138 (0.0012) -[2023-11-28 07:14:05,572][87424] Updated weights for policy 0, policy_version 268148 (0.0012) -[2023-11-28 07:14:05,742][87426] Updated weights for policy 1, policy_version 267940 (0.0012) -[2023-11-28 07:14:05,962][87424] Updated weights for policy 0, policy_version 268158 (0.0009) -[2023-11-28 07:14:06,125][87426] Updated weights for policy 1, policy_version 267950 (0.0012) -[2023-11-28 07:14:06,515][87426] Updated weights for policy 1, policy_version 267960 (0.0008) -[2023-11-28 07:14:08,394][87424] Updated weights for policy 0, policy_version 268168 (0.0008) -[2023-11-28 07:14:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 137248768. Throughput: 0: 2753.2, 1: 2724.4. Samples: 137268908. Policy #0 lag: (min: 22.0, avg: 35.2, max: 63.0) -[2023-11-28 07:14:08,445][86177] Avg episode reward: [(0, '-585.900'), (1, '-493.450')] -[2023-11-28 07:14:08,782][87424] Updated weights for policy 0, policy_version 268178 (0.0007) -[2023-11-28 07:14:08,947][87426] Updated weights for policy 1, policy_version 267970 (0.0009) -[2023-11-28 07:14:09,164][87424] Updated weights for policy 0, policy_version 268188 (0.0007) -[2023-11-28 07:14:09,329][87426] Updated weights for policy 1, policy_version 267980 (0.0012) -[2023-11-28 07:14:09,710][87426] Updated weights for policy 1, policy_version 267990 (0.0011) -[2023-11-28 07:14:10,081][87426] Updated weights for policy 1, policy_version 268000 (0.0011) -[2023-11-28 07:14:11,586][87424] Updated weights for policy 0, policy_version 268198 (0.0011) -[2023-11-28 07:14:11,969][87424] Updated weights for policy 0, policy_version 268208 (0.0009) -[2023-11-28 07:14:12,346][87424] Updated weights for policy 0, policy_version 268218 (0.0010) -[2023-11-28 07:14:12,436][87426] Updated weights for policy 1, policy_version 268010 (0.0011) -[2023-11-28 07:14:12,814][87426] Updated weights for policy 1, policy_version 268020 (0.0012) -[2023-11-28 07:14:13,198][87426] Updated weights for policy 1, policy_version 268030 (0.0008) -[2023-11-28 07:14:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 137281536. Throughput: 0: 2719.1, 1: 2704.8. Samples: 137291508. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:13,445][86177] Avg episode reward: [(0, '-544.780'), (1, '-495.830')] -[2023-11-28 07:14:14,657][87424] Updated weights for policy 0, policy_version 268228 (0.0009) -[2023-11-28 07:14:15,054][87424] Updated weights for policy 0, policy_version 268238 (0.0008) -[2023-11-28 07:14:15,443][87424] Updated weights for policy 0, policy_version 268248 (0.0009) -[2023-11-28 07:14:15,652][87426] Updated weights for policy 1, policy_version 268040 (0.0010) -[2023-11-28 07:14:16,030][87426] Updated weights for policy 1, policy_version 268050 (0.0012) -[2023-11-28 07:14:16,413][87426] Updated weights for policy 1, policy_version 268060 (0.0012) -[2023-11-28 07:14:17,256][87424] Updated weights for policy 0, policy_version 268258 (0.0012) -[2023-11-28 07:14:17,633][87424] Updated weights for policy 0, policy_version 268268 (0.0009) -[2023-11-28 07:14:18,024][87424] Updated weights for policy 0, policy_version 268278 (0.0007) -[2023-11-28 07:14:18,404][87424] Updated weights for policy 0, policy_version 268288 (0.0008) -[2023-11-28 07:14:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 137306112. Throughput: 0: 2717.4, 1: 2709.2. Samples: 137315796. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:18,446][86177] Avg episode reward: [(0, '-530.260'), (1, '-497.620')] -[2023-11-28 07:14:18,460][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000268288_68681728.pth... -[2023-11-28 07:14:18,507][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000265760_68034560.pth -[2023-11-28 07:14:18,663][87426] Updated weights for policy 1, policy_version 268070 (0.0012) -[2023-11-28 07:14:19,045][87426] Updated weights for policy 1, policy_version 268080 (0.0009) -[2023-11-28 07:14:19,429][87426] Updated weights for policy 1, policy_version 268090 (0.0011) -[2023-11-28 07:14:19,647][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000268096_68632576.pth... -[2023-11-28 07:14:19,694][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000265536_67977216.pth -[2023-11-28 07:14:20,841][87424] Updated weights for policy 0, policy_version 268298 (0.0008) -[2023-11-28 07:14:21,222][87424] Updated weights for policy 0, policy_version 268308 (0.0009) -[2023-11-28 07:14:21,472][87426] Updated weights for policy 1, policy_version 268100 (0.0012) -[2023-11-28 07:14:21,600][87424] Updated weights for policy 0, policy_version 268318 (0.0009) -[2023-11-28 07:14:21,851][87426] Updated weights for policy 1, policy_version 268110 (0.0010) -[2023-11-28 07:14:22,236][87426] Updated weights for policy 1, policy_version 268120 (0.0010) -[2023-11-28 07:14:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 137330688. Throughput: 0: 2695.8, 1: 2707.4. Samples: 137348636. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:23,445][86177] Avg episode reward: [(0, '-540.060'), (1, '-539.680')] -[2023-11-28 07:14:23,798][87424] Updated weights for policy 0, policy_version 268328 (0.0012) -[2023-11-28 07:14:24,191][87424] Updated weights for policy 0, policy_version 268338 (0.0011) -[2023-11-28 07:14:24,571][87424] Updated weights for policy 0, policy_version 268348 (0.0008) -[2023-11-28 07:14:24,734][87426] Updated weights for policy 1, policy_version 268130 (0.0008) -[2023-11-28 07:14:25,102][87426] Updated weights for policy 1, policy_version 268140 (0.0007) -[2023-11-28 07:14:25,492][87426] Updated weights for policy 1, policy_version 268150 (0.0009) -[2023-11-28 07:14:25,873][87426] Updated weights for policy 1, policy_version 268160 (0.0007) -[2023-11-28 07:14:26,270][87424] Updated weights for policy 0, policy_version 268358 (0.0011) -[2023-11-28 07:14:26,651][87424] Updated weights for policy 0, policy_version 268368 (0.0010) -[2023-11-28 07:14:27,033][87424] Updated weights for policy 0, policy_version 268378 (0.0009) -[2023-11-28 07:14:28,263][87426] Updated weights for policy 1, policy_version 268170 (0.0007) -[2023-11-28 07:14:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 137355264. Throughput: 0: 2698.3, 1: 2719.9. Samples: 137372896. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:28,445][86177] Avg episode reward: [(0, '-538.740'), (1, '-538.290')] -[2023-11-28 07:14:28,646][87426] Updated weights for policy 1, policy_version 268180 (0.0007) -[2023-11-28 07:14:29,042][87426] Updated weights for policy 1, policy_version 268190 (0.0007) -[2023-11-28 07:14:29,383][87424] Updated weights for policy 0, policy_version 268388 (0.0009) -[2023-11-28 07:14:29,758][87424] Updated weights for policy 0, policy_version 268398 (0.0012) -[2023-11-28 07:14:30,136][87424] Updated weights for policy 0, policy_version 268408 (0.0012) -[2023-11-28 07:14:31,557][87426] Updated weights for policy 1, policy_version 268200 (0.0010) -[2023-11-28 07:14:31,948][87426] Updated weights for policy 1, policy_version 268210 (0.0010) -[2023-11-28 07:14:32,234][87424] Updated weights for policy 0, policy_version 268418 (0.0011) -[2023-11-28 07:14:32,321][87426] Updated weights for policy 1, policy_version 268220 (0.0009) -[2023-11-28 07:14:32,616][87424] Updated weights for policy 0, policy_version 268428 (0.0008) -[2023-11-28 07:14:33,004][87424] Updated weights for policy 0, policy_version 268438 (0.0008) -[2023-11-28 07:14:33,384][87424] Updated weights for policy 0, policy_version 268448 (0.0007) -[2023-11-28 07:14:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 137388032. Throughput: 0: 2709.2, 1: 2698.1. Samples: 137396992. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:33,445][86177] Avg episode reward: [(0, '-544.530'), (1, '-539.800')] -[2023-11-28 07:14:34,348][87426] Updated weights for policy 1, policy_version 268230 (0.0011) -[2023-11-28 07:14:34,736][87426] Updated weights for policy 1, policy_version 268240 (0.0011) -[2023-11-28 07:14:35,123][87426] Updated weights for policy 1, policy_version 268250 (0.0010) -[2023-11-28 07:14:35,874][87424] Updated weights for policy 0, policy_version 268458 (0.0009) -[2023-11-28 07:14:36,241][87424] Updated weights for policy 0, policy_version 268468 (0.0008) -[2023-11-28 07:14:36,621][87424] Updated weights for policy 0, policy_version 268478 (0.0007) -[2023-11-28 07:14:37,281][87426] Updated weights for policy 1, policy_version 268260 (0.0009) -[2023-11-28 07:14:37,659][87426] Updated weights for policy 1, policy_version 268270 (0.0012) -[2023-11-28 07:14:38,043][87426] Updated weights for policy 1, policy_version 268280 (0.0012) -[2023-11-28 07:14:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 137412608. Throughput: 0: 2705.9, 1: 2680.8. Samples: 137429112. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:38,445][86177] Avg episode reward: [(0, '-545.570'), (1, '-538.820')] -[2023-11-28 07:14:38,523][87424] Updated weights for policy 0, policy_version 268488 (0.0009) -[2023-11-28 07:14:38,905][87424] Updated weights for policy 0, policy_version 268498 (0.0008) -[2023-11-28 07:14:39,293][87424] Updated weights for policy 0, policy_version 268508 (0.0009) -[2023-11-28 07:14:40,634][87426] Updated weights for policy 1, policy_version 268290 (0.0012) -[2023-11-28 07:14:41,014][87426] Updated weights for policy 1, policy_version 268300 (0.0012) -[2023-11-28 07:14:41,393][87426] Updated weights for policy 1, policy_version 268310 (0.0012) -[2023-11-28 07:14:41,533][87424] Updated weights for policy 0, policy_version 268518 (0.0011) -[2023-11-28 07:14:41,777][87426] Updated weights for policy 1, policy_version 268320 (0.0012) -[2023-11-28 07:14:41,913][87424] Updated weights for policy 0, policy_version 268528 (0.0009) -[2023-11-28 07:14:42,300][87424] Updated weights for policy 0, policy_version 268538 (0.0010) -[2023-11-28 07:14:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 137437184. Throughput: 0: 2686.7, 1: 2646.1. Samples: 137452448. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:43,445][86177] Avg episode reward: [(0, '-534.740'), (1, '-498.820')] -[2023-11-28 07:14:43,776][87426] Updated weights for policy 1, policy_version 268330 (0.0008) -[2023-11-28 07:14:44,162][87426] Updated weights for policy 1, policy_version 268340 (0.0007) -[2023-11-28 07:14:44,540][87426] Updated weights for policy 1, policy_version 268350 (0.0007) -[2023-11-28 07:14:44,819][87424] Updated weights for policy 0, policy_version 268548 (0.0010) -[2023-11-28 07:14:45,201][87424] Updated weights for policy 0, policy_version 268558 (0.0012) -[2023-11-28 07:14:45,579][87424] Updated weights for policy 0, policy_version 268568 (0.0012) -[2023-11-28 07:14:46,568][87426] Updated weights for policy 1, policy_version 268360 (0.0011) -[2023-11-28 07:14:46,949][87426] Updated weights for policy 1, policy_version 268370 (0.0012) -[2023-11-28 07:14:47,331][87426] Updated weights for policy 1, policy_version 268380 (0.0012) -[2023-11-28 07:14:48,163][87424] Updated weights for policy 0, policy_version 268578 (0.0011) -[2023-11-28 07:14:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 137461760. Throughput: 0: 2687.4, 1: 2663.2. Samples: 137476352. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:48,445][86177] Avg episode reward: [(0, '-544.210'), (1, '-505.280')] -[2023-11-28 07:14:48,548][87424] Updated weights for policy 0, policy_version 268588 (0.0007) -[2023-11-28 07:14:48,931][87424] Updated weights for policy 0, policy_version 268598 (0.0008) -[2023-11-28 07:14:49,312][87424] Updated weights for policy 0, policy_version 268608 (0.0008) -[2023-11-28 07:14:49,605][87426] Updated weights for policy 1, policy_version 268390 (0.0012) -[2023-11-28 07:14:49,981][87426] Updated weights for policy 1, policy_version 268400 (0.0011) -[2023-11-28 07:14:50,374][87426] Updated weights for policy 1, policy_version 268410 (0.0012) -[2023-11-28 07:14:51,374][87424] Updated weights for policy 0, policy_version 268618 (0.0012) -[2023-11-28 07:14:51,751][87424] Updated weights for policy 0, policy_version 268628 (0.0012) -[2023-11-28 07:14:52,127][87424] Updated weights for policy 0, policy_version 268638 (0.0010) -[2023-11-28 07:14:52,755][87426] Updated weights for policy 1, policy_version 268420 (0.0011) -[2023-11-28 07:14:53,136][87426] Updated weights for policy 1, policy_version 268430 (0.0017) -[2023-11-28 07:14:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 137486336. Throughput: 0: 2679.7, 1: 2635.8. Samples: 137508108. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:53,445][86177] Avg episode reward: [(0, '-534.800'), (1, '-502.740')] -[2023-11-28 07:14:53,523][87426] Updated weights for policy 1, policy_version 268440 (0.0012) -[2023-11-28 07:14:54,190][87424] Updated weights for policy 0, policy_version 268648 (0.0012) -[2023-11-28 07:14:54,577][87424] Updated weights for policy 0, policy_version 268658 (0.0012) -[2023-11-28 07:14:54,958][87424] Updated weights for policy 0, policy_version 268668 (0.0012) -[2023-11-28 07:14:55,557][87426] Updated weights for policy 1, policy_version 268450 (0.0011) -[2023-11-28 07:14:55,927][87426] Updated weights for policy 1, policy_version 268460 (0.0007) -[2023-11-28 07:14:56,304][87426] Updated weights for policy 1, policy_version 268470 (0.0007) -[2023-11-28 07:14:56,685][87426] Updated weights for policy 1, policy_version 268480 (0.0007) -[2023-11-28 07:14:56,912][87424] Updated weights for policy 0, policy_version 268678 (0.0012) -[2023-11-28 07:14:57,304][87424] Updated weights for policy 0, policy_version 268688 (0.0012) -[2023-11-28 07:14:57,691][87424] Updated weights for policy 0, policy_version 268698 (0.0011) -[2023-11-28 07:14:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 137519104. Throughput: 0: 2700.7, 1: 2652.5. Samples: 137532404. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:14:58,445][86177] Avg episode reward: [(0, '-529.910'), (1, '-503.370')] -[2023-11-28 07:14:59,215][87426] Updated weights for policy 1, policy_version 268490 (0.0012) -[2023-11-28 07:14:59,454][87424] Updated weights for policy 0, policy_version 268708 (0.0011) -[2023-11-28 07:14:59,594][87426] Updated weights for policy 1, policy_version 268500 (0.0011) -[2023-11-28 07:14:59,851][87424] Updated weights for policy 0, policy_version 268718 (0.0009) -[2023-11-28 07:14:59,971][87426] Updated weights for policy 1, policy_version 268510 (0.0012) -[2023-11-28 07:15:00,228][87424] Updated weights for policy 0, policy_version 268728 (0.0012) -[2023-11-28 07:15:01,712][87426] Updated weights for policy 1, policy_version 268520 (0.0011) -[2023-11-28 07:15:02,092][87426] Updated weights for policy 1, policy_version 268530 (0.0009) -[2023-11-28 07:15:02,471][87426] Updated weights for policy 1, policy_version 268540 (0.0011) -[2023-11-28 07:15:02,576][87424] Updated weights for policy 0, policy_version 268738 (0.0011) -[2023-11-28 07:15:02,953][87424] Updated weights for policy 0, policy_version 268748 (0.0010) -[2023-11-28 07:15:03,344][87424] Updated weights for policy 0, policy_version 268758 (0.0010) -[2023-11-28 07:15:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 137543680. Throughput: 0: 2710.8, 1: 2678.6. Samples: 137558316. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:15:03,445][86177] Avg episode reward: [(0, '-523.210'), (1, '-502.400')] -[2023-11-28 07:15:03,721][87424] Updated weights for policy 0, policy_version 268768 (0.0012) -[2023-11-28 07:15:04,568][87426] Updated weights for policy 1, policy_version 268550 (0.0010) -[2023-11-28 07:15:04,941][87426] Updated weights for policy 1, policy_version 268560 (0.0012) -[2023-11-28 07:15:05,322][87426] Updated weights for policy 1, policy_version 268570 (0.0011) -[2023-11-28 07:15:06,220][87424] Updated weights for policy 0, policy_version 268778 (0.0012) -[2023-11-28 07:15:06,600][87424] Updated weights for policy 0, policy_version 268788 (0.0011) -[2023-11-28 07:15:06,987][87424] Updated weights for policy 0, policy_version 268798 (0.0011) -[2023-11-28 07:15:07,858][87426] Updated weights for policy 1, policy_version 268580 (0.0010) -[2023-11-28 07:15:08,233][87426] Updated weights for policy 1, policy_version 268590 (0.0007) -[2023-11-28 07:15:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 137568256. Throughput: 0: 2703.6, 1: 2675.0. Samples: 137590676. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:15:08,445][86177] Avg episode reward: [(0, '-553.830'), (1, '-498.080')] -[2023-11-28 07:15:08,615][87426] Updated weights for policy 1, policy_version 268600 (0.0007) -[2023-11-28 07:15:09,072][87424] Updated weights for policy 0, policy_version 268808 (0.0009) -[2023-11-28 07:15:09,446][87424] Updated weights for policy 0, policy_version 268818 (0.0009) -[2023-11-28 07:15:09,829][87424] Updated weights for policy 0, policy_version 268828 (0.0012) -[2023-11-28 07:15:11,104][87426] Updated weights for policy 1, policy_version 268610 (0.0010) -[2023-11-28 07:15:11,492][87426] Updated weights for policy 1, policy_version 268620 (0.0008) -[2023-11-28 07:15:11,874][87426] Updated weights for policy 1, policy_version 268630 (0.0009) -[2023-11-28 07:15:12,215][87424] Updated weights for policy 0, policy_version 268838 (0.0009) -[2023-11-28 07:15:12,250][87426] Updated weights for policy 1, policy_version 268640 (0.0011) -[2023-11-28 07:15:12,598][87424] Updated weights for policy 0, policy_version 268848 (0.0009) -[2023-11-28 07:15:12,983][87424] Updated weights for policy 0, policy_version 268858 (0.0008) -[2023-11-28 07:15:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 137601024. Throughput: 0: 2697.2, 1: 2680.4. Samples: 137614884. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:15:13,445][86177] Avg episode reward: [(0, '-557.140'), (1, '-495.380')] -[2023-11-28 07:15:14,238][87426] Updated weights for policy 1, policy_version 268650 (0.0010) -[2023-11-28 07:15:14,612][87426] Updated weights for policy 1, policy_version 268660 (0.0011) -[2023-11-28 07:15:14,990][87426] Updated weights for policy 1, policy_version 268670 (0.0009) -[2023-11-28 07:15:15,404][87424] Updated weights for policy 0, policy_version 268868 (0.0010) -[2023-11-28 07:15:15,802][87424] Updated weights for policy 0, policy_version 268878 (0.0012) -[2023-11-28 07:15:16,172][87424] Updated weights for policy 0, policy_version 268888 (0.0012) -[2023-11-28 07:15:17,018][87426] Updated weights for policy 1, policy_version 268680 (0.0011) -[2023-11-28 07:15:17,405][87426] Updated weights for policy 1, policy_version 268690 (0.0011) -[2023-11-28 07:15:17,775][87426] Updated weights for policy 1, policy_version 268700 (0.0012) -[2023-11-28 07:15:18,066][87424] Updated weights for policy 0, policy_version 268898 (0.0012) -[2023-11-28 07:15:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 137625600. Throughput: 0: 2684.5, 1: 2704.1. Samples: 137639480. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:15:18,445][86177] Avg episode reward: [(0, '-563.120'), (1, '-496.900')] -[2023-11-28 07:15:18,452][87424] Updated weights for policy 0, policy_version 268908 (0.0012) -[2023-11-28 07:15:18,837][87424] Updated weights for policy 0, policy_version 268918 (0.0008) -[2023-11-28 07:15:19,222][87424] Updated weights for policy 0, policy_version 268928 (0.0011) -[2023-11-28 07:15:19,929][87426] Updated weights for policy 1, policy_version 268710 (0.0011) -[2023-11-28 07:15:20,309][87426] Updated weights for policy 1, policy_version 268720 (0.0009) -[2023-11-28 07:15:20,692][87426] Updated weights for policy 1, policy_version 268730 (0.0009) -[2023-11-28 07:15:21,169][87424] Updated weights for policy 0, policy_version 268938 (0.0012) -[2023-11-28 07:15:21,556][87424] Updated weights for policy 0, policy_version 268948 (0.0012) -[2023-11-28 07:15:21,930][87424] Updated weights for policy 0, policy_version 268958 (0.0010) -[2023-11-28 07:15:22,932][87426] Updated weights for policy 1, policy_version 268740 (0.0014) -[2023-11-28 07:15:23,303][87426] Updated weights for policy 1, policy_version 268750 (0.0009) -[2023-11-28 07:15:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 137650176. Throughput: 0: 2703.7, 1: 2699.2. Samples: 137672244. Policy #0 lag: (min: 31.0, avg: 38.1, max: 63.0) -[2023-11-28 07:15:23,445][86177] Avg episode reward: [(0, '-569.090'), (1, '-494.480')] -[2023-11-28 07:15:23,684][87426] Updated weights for policy 1, policy_version 268760 (0.0007) -[2023-11-28 07:15:24,436][87424] Updated weights for policy 0, policy_version 268968 (0.0008) -[2023-11-28 07:15:24,807][87424] Updated weights for policy 0, policy_version 268978 (0.0007) -[2023-11-28 07:15:25,199][87424] Updated weights for policy 0, policy_version 268988 (0.0008) -[2023-11-28 07:15:26,168][87426] Updated weights for policy 1, policy_version 268770 (0.0008) -[2023-11-28 07:15:26,558][87426] Updated weights for policy 1, policy_version 268780 (0.0012) -[2023-11-28 07:15:26,934][87426] Updated weights for policy 1, policy_version 268790 (0.0011) -[2023-11-28 07:15:27,111][87424] Updated weights for policy 0, policy_version 268998 (0.0009) -[2023-11-28 07:15:27,313][87426] Updated weights for policy 1, policy_version 268800 (0.0011) -[2023-11-28 07:15:27,488][87424] Updated weights for policy 0, policy_version 269008 (0.0011) -[2023-11-28 07:15:27,886][87424] Updated weights for policy 0, policy_version 269018 (0.0010) -[2023-11-28 07:15:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 137682944. Throughput: 0: 2711.0, 1: 2722.7. Samples: 137696964. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:15:28,445][86177] Avg episode reward: [(0, '-526.430'), (1, '-496.540')] -[2023-11-28 07:15:29,007][87426] Updated weights for policy 1, policy_version 268810 (0.0012) -[2023-11-28 07:15:29,390][87426] Updated weights for policy 1, policy_version 268820 (0.0012) -[2023-11-28 07:15:29,770][87426] Updated weights for policy 1, policy_version 268830 (0.0012) -[2023-11-28 07:15:29,806][87424] Updated weights for policy 0, policy_version 269028 (0.0010) -[2023-11-28 07:15:30,187][87424] Updated weights for policy 0, policy_version 269038 (0.0011) -[2023-11-28 07:15:30,564][87424] Updated weights for policy 0, policy_version 269048 (0.0011) -[2023-11-28 07:15:32,124][87426] Updated weights for policy 1, policy_version 268840 (0.0012) -[2023-11-28 07:15:32,498][87424] Updated weights for policy 0, policy_version 269058 (0.0010) -[2023-11-28 07:15:32,510][87426] Updated weights for policy 1, policy_version 268850 (0.0009) -[2023-11-28 07:15:32,887][87426] Updated weights for policy 1, policy_version 268860 (0.0010) -[2023-11-28 07:15:32,889][87424] Updated weights for policy 0, policy_version 269068 (0.0010) -[2023-11-28 07:15:33,263][87424] Updated weights for policy 0, policy_version 269078 (0.0012) -[2023-11-28 07:15:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 137707520. Throughput: 0: 2732.9, 1: 2721.2. Samples: 137721788. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:15:33,445][86177] Avg episode reward: [(0, '-525.280'), (1, '-496.980')] -[2023-11-28 07:15:33,645][87424] Updated weights for policy 0, policy_version 269088 (0.0008) -[2023-11-28 07:15:34,732][87426] Updated weights for policy 1, policy_version 268870 (0.0010) -[2023-11-28 07:15:35,108][87426] Updated weights for policy 1, policy_version 268880 (0.0009) -[2023-11-28 07:15:35,489][87426] Updated weights for policy 1, policy_version 268890 (0.0008) -[2023-11-28 07:15:36,122][87424] Updated weights for policy 0, policy_version 269098 (0.0007) -[2023-11-28 07:15:36,508][87424] Updated weights for policy 0, policy_version 269108 (0.0007) -[2023-11-28 07:15:36,899][87424] Updated weights for policy 0, policy_version 269118 (0.0010) -[2023-11-28 07:15:37,307][87426] Updated weights for policy 1, policy_version 268900 (0.0010) -[2023-11-28 07:15:37,691][87426] Updated weights for policy 1, policy_version 268910 (0.0012) -[2023-11-28 07:15:38,062][87426] Updated weights for policy 1, policy_version 268920 (0.0012) -[2023-11-28 07:15:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 137740288. Throughput: 0: 2732.0, 1: 2734.1. Samples: 137754080. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:15:38,445][86177] Avg episode reward: [(0, '-518.490'), (1, '-497.310')] -[2023-11-28 07:15:38,832][87424] Updated weights for policy 0, policy_version 269128 (0.0012) -[2023-11-28 07:15:39,204][87424] Updated weights for policy 0, policy_version 269138 (0.0012) -[2023-11-28 07:15:39,590][87424] Updated weights for policy 0, policy_version 269148 (0.0012) -[2023-11-28 07:15:39,970][87426] Updated weights for policy 1, policy_version 268930 (0.0016) -[2023-11-28 07:15:40,345][87426] Updated weights for policy 1, policy_version 268940 (0.0011) -[2023-11-28 07:15:40,723][87426] Updated weights for policy 1, policy_version 268950 (0.0011) -[2023-11-28 07:15:41,103][87426] Updated weights for policy 1, policy_version 268960 (0.0010) -[2023-11-28 07:15:42,130][87424] Updated weights for policy 0, policy_version 269158 (0.0012) -[2023-11-28 07:15:42,508][87424] Updated weights for policy 0, policy_version 269168 (0.0012) -[2023-11-28 07:15:42,903][87424] Updated weights for policy 0, policy_version 269178 (0.0012) -[2023-11-28 07:15:43,148][87426] Updated weights for policy 1, policy_version 268970 (0.0012) -[2023-11-28 07:15:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 137764864. Throughput: 0: 2723.6, 1: 2740.9. Samples: 137778304. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:15:43,445][86177] Avg episode reward: [(0, '-516.460'), (1, '-499.070')] -[2023-11-28 07:15:43,525][87426] Updated weights for policy 1, policy_version 268980 (0.0012) -[2023-11-28 07:15:43,894][87426] Updated weights for policy 1, policy_version 268990 (0.0012) -[2023-11-28 07:15:45,374][87424] Updated weights for policy 0, policy_version 269188 (0.0010) -[2023-11-28 07:15:45,756][87424] Updated weights for policy 0, policy_version 269198 (0.0009) -[2023-11-28 07:15:46,030][87426] Updated weights for policy 1, policy_version 269000 (0.0012) -[2023-11-28 07:15:46,132][87424] Updated weights for policy 0, policy_version 269208 (0.0010) -[2023-11-28 07:15:46,402][87426] Updated weights for policy 1, policy_version 269010 (0.0010) -[2023-11-28 07:15:46,782][87426] Updated weights for policy 1, policy_version 269020 (0.0007) -[2023-11-28 07:15:48,013][87424] Updated weights for policy 0, policy_version 269218 (0.0009) -[2023-11-28 07:15:48,397][87424] Updated weights for policy 0, policy_version 269228 (0.0007) -[2023-11-28 07:15:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 137789440. Throughput: 0: 2713.4, 1: 2726.0. Samples: 137803088. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:15:48,445][86177] Avg episode reward: [(0, '-514.700'), (1, '-495.920')] -[2023-11-28 07:15:48,779][87424] Updated weights for policy 0, policy_version 269238 (0.0008) -[2023-11-28 07:15:49,158][87424] Updated weights for policy 0, policy_version 269248 (0.0009) -[2023-11-28 07:15:49,318][87426] Updated weights for policy 1, policy_version 269030 (0.0008) -[2023-11-28 07:15:49,697][87426] Updated weights for policy 1, policy_version 269040 (0.0009) -[2023-11-28 07:15:50,075][87426] Updated weights for policy 1, policy_version 269050 (0.0008) -[2023-11-28 07:15:51,423][87424] Updated weights for policy 0, policy_version 269258 (0.0009) -[2023-11-28 07:15:51,803][87424] Updated weights for policy 0, policy_version 269268 (0.0009) -[2023-11-28 07:15:52,183][87424] Updated weights for policy 0, policy_version 269278 (0.0009) -[2023-11-28 07:15:52,589][87426] Updated weights for policy 1, policy_version 269060 (0.0008) -[2023-11-28 07:15:52,977][87426] Updated weights for policy 1, policy_version 269070 (0.0012) -[2023-11-28 07:15:53,355][87426] Updated weights for policy 1, policy_version 269080 (0.0010) -[2023-11-28 07:15:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 137814016. Throughput: 0: 2723.9, 1: 2704.3. Samples: 137834944. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:15:53,445][86177] Avg episode reward: [(0, '-510.860'), (1, '-522.230')] -[2023-11-28 07:15:54,426][87424] Updated weights for policy 0, policy_version 269288 (0.0008) -[2023-11-28 07:15:54,810][87424] Updated weights for policy 0, policy_version 269298 (0.0008) -[2023-11-28 07:15:55,196][87424] Updated weights for policy 0, policy_version 269308 (0.0008) -[2023-11-28 07:15:55,862][87426] Updated weights for policy 1, policy_version 269090 (0.0011) -[2023-11-28 07:15:56,242][87426] Updated weights for policy 1, policy_version 269100 (0.0012) -[2023-11-28 07:15:56,629][87426] Updated weights for policy 1, policy_version 269110 (0.0011) -[2023-11-28 07:15:56,973][87424] Updated weights for policy 0, policy_version 269318 (0.0010) -[2023-11-28 07:15:57,010][87426] Updated weights for policy 1, policy_version 269120 (0.0010) -[2023-11-28 07:15:57,362][87424] Updated weights for policy 0, policy_version 269328 (0.0012) -[2023-11-28 07:15:57,746][87424] Updated weights for policy 0, policy_version 269338 (0.0012) -[2023-11-28 07:15:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 137846784. Throughput: 0: 2726.5, 1: 2731.1. Samples: 137860476. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:15:58,445][86177] Avg episode reward: [(0, '-532.910'), (1, '-524.270')] -[2023-11-28 07:15:59,063][87426] Updated weights for policy 1, policy_version 269130 (0.0008) -[2023-11-28 07:15:59,446][87426] Updated weights for policy 1, policy_version 269140 (0.0012) -[2023-11-28 07:15:59,610][87424] Updated weights for policy 0, policy_version 269348 (0.0010) -[2023-11-28 07:15:59,833][87426] Updated weights for policy 1, policy_version 269150 (0.0015) -[2023-11-28 07:15:59,994][87424] Updated weights for policy 0, policy_version 269358 (0.0010) -[2023-11-28 07:16:00,383][87424] Updated weights for policy 0, policy_version 269368 (0.0010) -[2023-11-28 07:16:02,029][87426] Updated weights for policy 1, policy_version 269160 (0.0011) -[2023-11-28 07:16:02,403][87426] Updated weights for policy 1, policy_version 269170 (0.0011) -[2023-11-28 07:16:02,552][87424] Updated weights for policy 0, policy_version 269378 (0.0009) -[2023-11-28 07:16:02,785][87426] Updated weights for policy 1, policy_version 269180 (0.0012) -[2023-11-28 07:16:02,930][87424] Updated weights for policy 0, policy_version 269388 (0.0011) -[2023-11-28 07:16:03,317][87424] Updated weights for policy 0, policy_version 269398 (0.0011) -[2023-11-28 07:16:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 137871360. Throughput: 0: 2770.8, 1: 2715.3. Samples: 137886356. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:16:03,445][86177] Avg episode reward: [(0, '-526.970'), (1, '-532.040')] -[2023-11-28 07:16:03,697][87424] Updated weights for policy 0, policy_version 269408 (0.0007) -[2023-11-28 07:16:05,222][87426] Updated weights for policy 1, policy_version 269190 (0.0011) -[2023-11-28 07:16:05,603][87426] Updated weights for policy 1, policy_version 269200 (0.0009) -[2023-11-28 07:16:05,649][87424] Updated weights for policy 0, policy_version 269418 (0.0008) -[2023-11-28 07:16:05,989][87426] Updated weights for policy 1, policy_version 269210 (0.0009) -[2023-11-28 07:16:06,033][87424] Updated weights for policy 0, policy_version 269428 (0.0010) -[2023-11-28 07:16:06,414][87424] Updated weights for policy 0, policy_version 269438 (0.0012) -[2023-11-28 07:16:07,908][87426] Updated weights for policy 1, policy_version 269220 (0.0009) -[2023-11-28 07:16:08,293][87426] Updated weights for policy 1, policy_version 269230 (0.0011) -[2023-11-28 07:16:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 137895936. Throughput: 0: 2752.2, 1: 2714.6. Samples: 137918248. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:16:08,446][86177] Avg episode reward: [(0, '-536.200'), (1, '-520.030')] -[2023-11-28 07:16:08,671][87426] Updated weights for policy 1, policy_version 269240 (0.0008) -[2023-11-28 07:16:08,914][87424] Updated weights for policy 0, policy_version 269448 (0.0010) -[2023-11-28 07:16:09,305][87424] Updated weights for policy 0, policy_version 269458 (0.0012) -[2023-11-28 07:16:09,681][87424] Updated weights for policy 0, policy_version 269468 (0.0012) -[2023-11-28 07:16:10,862][87426] Updated weights for policy 1, policy_version 269250 (0.0012) -[2023-11-28 07:16:11,236][87426] Updated weights for policy 1, policy_version 269260 (0.0011) -[2023-11-28 07:16:11,623][87426] Updated weights for policy 1, policy_version 269270 (0.0011) -[2023-11-28 07:16:11,713][87424] Updated weights for policy 0, policy_version 269478 (0.0011) -[2023-11-28 07:16:11,997][87426] Updated weights for policy 1, policy_version 269280 (0.0011) -[2023-11-28 07:16:12,096][87424] Updated weights for policy 0, policy_version 269488 (0.0012) -[2023-11-28 07:16:12,480][87424] Updated weights for policy 0, policy_version 269498 (0.0011) -[2023-11-28 07:16:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 137928704. Throughput: 0: 2735.9, 1: 2695.7. Samples: 137941384. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:16:13,445][86177] Avg episode reward: [(0, '-525.420'), (1, '-528.020')] -[2023-11-28 07:16:14,621][87426] Updated weights for policy 1, policy_version 269290 (0.0007) -[2023-11-28 07:16:14,833][87424] Updated weights for policy 0, policy_version 269508 (0.0010) -[2023-11-28 07:16:14,998][87426] Updated weights for policy 1, policy_version 269300 (0.0007) -[2023-11-28 07:16:15,219][87424] Updated weights for policy 0, policy_version 269518 (0.0008) -[2023-11-28 07:16:15,375][87426] Updated weights for policy 1, policy_version 269310 (0.0008) -[2023-11-28 07:16:15,597][87424] Updated weights for policy 0, policy_version 269528 (0.0009) -[2023-11-28 07:16:17,465][87424] Updated weights for policy 0, policy_version 269538 (0.0010) -[2023-11-28 07:16:17,841][87424] Updated weights for policy 0, policy_version 269548 (0.0011) -[2023-11-28 07:16:17,875][87426] Updated weights for policy 1, policy_version 269320 (0.0011) -[2023-11-28 07:16:18,229][87424] Updated weights for policy 0, policy_version 269558 (0.0010) -[2023-11-28 07:16:18,253][87426] Updated weights for policy 1, policy_version 269330 (0.0012) -[2023-11-28 07:16:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 137945088. Throughput: 0: 2740.6, 1: 2675.8. Samples: 137965528. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:16:18,445][86177] Avg episode reward: [(0, '-511.160'), (1, '-517.930')] -[2023-11-28 07:16:18,605][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000269568_69009408.pth... -[2023-11-28 07:16:18,609][87424] Updated weights for policy 0, policy_version 269568 (0.0007) -[2023-11-28 07:16:18,629][87426] Updated weights for policy 1, policy_version 269340 (0.0012) -[2023-11-28 07:16:18,656][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000267040_68362240.pth -[2023-11-28 07:16:18,779][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000269344_68952064.pth... -[2023-11-28 07:16:18,809][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000266816_68304896.pth -[2023-11-28 07:16:20,481][87426] Updated weights for policy 1, policy_version 269350 (0.0012) -[2023-11-28 07:16:20,857][87426] Updated weights for policy 1, policy_version 269360 (0.0012) -[2023-11-28 07:16:20,996][87424] Updated weights for policy 0, policy_version 269578 (0.0009) -[2023-11-28 07:16:21,241][87426] Updated weights for policy 1, policy_version 269370 (0.0011) -[2023-11-28 07:16:21,385][87424] Updated weights for policy 0, policy_version 269588 (0.0010) -[2023-11-28 07:16:21,755][87424] Updated weights for policy 0, policy_version 269598 (0.0011) -[2023-11-28 07:16:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 137977856. Throughput: 0: 2738.4, 1: 2665.3. Samples: 137997248. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:16:23,445][86177] Avg episode reward: [(0, '-512.070'), (1, '-517.400')] -[2023-11-28 07:16:23,751][87426] Updated weights for policy 1, policy_version 269380 (0.0012) -[2023-11-28 07:16:24,132][87426] Updated weights for policy 1, policy_version 269390 (0.0009) -[2023-11-28 07:16:24,207][87424] Updated weights for policy 0, policy_version 269608 (0.0010) -[2023-11-28 07:16:24,516][87426] Updated weights for policy 1, policy_version 269400 (0.0010) -[2023-11-28 07:16:24,589][87424] Updated weights for policy 0, policy_version 269618 (0.0007) -[2023-11-28 07:16:24,974][87424] Updated weights for policy 0, policy_version 269628 (0.0009) -[2023-11-28 07:16:26,347][87426] Updated weights for policy 1, policy_version 269410 (0.0011) -[2023-11-28 07:16:26,726][87426] Updated weights for policy 1, policy_version 269420 (0.0011) -[2023-11-28 07:16:26,860][87424] Updated weights for policy 0, policy_version 269638 (0.0010) -[2023-11-28 07:16:27,102][87426] Updated weights for policy 1, policy_version 269430 (0.0007) -[2023-11-28 07:16:27,249][87424] Updated weights for policy 0, policy_version 269648 (0.0011) -[2023-11-28 07:16:27,487][87426] Updated weights for policy 1, policy_version 269440 (0.0007) -[2023-11-28 07:16:27,626][87424] Updated weights for policy 0, policy_version 269658 (0.0012) -[2023-11-28 07:16:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 138010624. Throughput: 0: 2741.6, 1: 2690.6. Samples: 138022752. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:16:28,446][86177] Avg episode reward: [(0, '-503.240'), (1, '-500.910')] -[2023-11-28 07:16:29,520][87426] Updated weights for policy 1, policy_version 269450 (0.0008) -[2023-11-28 07:16:29,816][87424] Updated weights for policy 0, policy_version 269668 (0.0010) -[2023-11-28 07:16:29,900][87426] Updated weights for policy 1, policy_version 269460 (0.0009) -[2023-11-28 07:16:30,208][87424] Updated weights for policy 0, policy_version 269678 (0.0011) -[2023-11-28 07:16:30,280][87426] Updated weights for policy 1, policy_version 269470 (0.0012) -[2023-11-28 07:16:30,579][87424] Updated weights for policy 0, policy_version 269688 (0.0010) -[2023-11-28 07:16:32,202][87426] Updated weights for policy 1, policy_version 269480 (0.0010) -[2023-11-28 07:16:32,524][87424] Updated weights for policy 0, policy_version 269698 (0.0011) -[2023-11-28 07:16:32,575][87426] Updated weights for policy 1, policy_version 269490 (0.0008) -[2023-11-28 07:16:32,902][87424] Updated weights for policy 0, policy_version 269708 (0.0012) -[2023-11-28 07:16:32,961][87426] Updated weights for policy 1, policy_version 269500 (0.0008) -[2023-11-28 07:16:33,281][87424] Updated weights for policy 0, policy_version 269718 (0.0012) -[2023-11-28 07:16:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 138035200. Throughput: 0: 2730.5, 1: 2696.5. Samples: 138047304. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:16:33,445][86177] Avg episode reward: [(0, '-500.980'), (1, '-533.140')] -[2023-11-28 07:16:33,667][87424] Updated weights for policy 0, policy_version 269728 (0.0007) -[2023-11-28 07:16:35,512][87426] Updated weights for policy 1, policy_version 269510 (0.0010) -[2023-11-28 07:16:35,888][87426] Updated weights for policy 1, policy_version 269520 (0.0007) -[2023-11-28 07:16:36,259][87424] Updated weights for policy 0, policy_version 269738 (0.0007) -[2023-11-28 07:16:36,272][87426] Updated weights for policy 1, policy_version 269530 (0.0007) -[2023-11-28 07:16:36,645][87424] Updated weights for policy 0, policy_version 269748 (0.0008) -[2023-11-28 07:16:37,035][87424] Updated weights for policy 0, policy_version 269758 (0.0008) -[2023-11-28 07:16:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 138059776. Throughput: 0: 2711.7, 1: 2706.0. Samples: 138078740. Policy #0 lag: (min: 31.0, avg: 39.0, max: 63.0) -[2023-11-28 07:16:38,445][86177] Avg episode reward: [(0, '-504.550'), (1, '-532.550')] -[2023-11-28 07:16:38,739][87426] Updated weights for policy 1, policy_version 269540 (0.0008) -[2023-11-28 07:16:39,107][87426] Updated weights for policy 1, policy_version 269550 (0.0008) -[2023-11-28 07:16:39,486][87426] Updated weights for policy 1, policy_version 269560 (0.0010) -[2023-11-28 07:16:39,550][87424] Updated weights for policy 0, policy_version 269768 (0.0010) -[2023-11-28 07:16:39,934][87424] Updated weights for policy 0, policy_version 269778 (0.0012) -[2023-11-28 07:16:40,310][87424] Updated weights for policy 0, policy_version 269788 (0.0012) -[2023-11-28 07:16:41,786][87426] Updated weights for policy 1, policy_version 269570 (0.0011) -[2023-11-28 07:16:42,168][87426] Updated weights for policy 1, policy_version 269580 (0.0012) -[2023-11-28 07:16:42,457][87424] Updated weights for policy 0, policy_version 269798 (0.0012) -[2023-11-28 07:16:42,539][87426] Updated weights for policy 1, policy_version 269590 (0.0011) -[2023-11-28 07:16:42,848][87424] Updated weights for policy 0, policy_version 269808 (0.0009) -[2023-11-28 07:16:42,912][87426] Updated weights for policy 1, policy_version 269600 (0.0011) -[2023-11-28 07:16:43,230][87424] Updated weights for policy 0, policy_version 269818 (0.0012) -[2023-11-28 07:16:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 138084352. Throughput: 0: 2702.1, 1: 2656.3. Samples: 138101604. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:16:43,445][86177] Avg episode reward: [(0, '-544.760'), (1, '-528.170')] -[2023-11-28 07:16:45,041][87424] Updated weights for policy 0, policy_version 269828 (0.0012) -[2023-11-28 07:16:45,110][87426] Updated weights for policy 1, policy_version 269610 (0.0009) -[2023-11-28 07:16:45,413][87424] Updated weights for policy 0, policy_version 269838 (0.0011) -[2023-11-28 07:16:45,482][87426] Updated weights for policy 1, policy_version 269620 (0.0011) -[2023-11-28 07:16:45,795][87424] Updated weights for policy 0, policy_version 269848 (0.0012) -[2023-11-28 07:16:45,858][87426] Updated weights for policy 1, policy_version 269630 (0.0010) -[2023-11-28 07:16:47,836][87424] Updated weights for policy 0, policy_version 269858 (0.0011) -[2023-11-28 07:16:47,847][87426] Updated weights for policy 1, policy_version 269640 (0.0011) -[2023-11-28 07:16:48,209][87424] Updated weights for policy 0, policy_version 269868 (0.0012) -[2023-11-28 07:16:48,222][87426] Updated weights for policy 1, policy_version 269650 (0.0011) -[2023-11-28 07:16:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 138108928. Throughput: 0: 2686.5, 1: 2664.4. Samples: 138127148. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:16:48,445][86177] Avg episode reward: [(0, '-551.900'), (1, '-531.000')] -[2023-11-28 07:16:48,590][87424] Updated weights for policy 0, policy_version 269878 (0.0012) -[2023-11-28 07:16:48,605][87426] Updated weights for policy 1, policy_version 269660 (0.0011) -[2023-11-28 07:16:48,967][87424] Updated weights for policy 0, policy_version 269888 (0.0011) -[2023-11-28 07:16:50,800][87426] Updated weights for policy 1, policy_version 269670 (0.0011) -[2023-11-28 07:16:51,180][87426] Updated weights for policy 1, policy_version 269680 (0.0011) -[2023-11-28 07:16:51,485][87424] Updated weights for policy 0, policy_version 269898 (0.0011) -[2023-11-28 07:16:51,564][87426] Updated weights for policy 1, policy_version 269690 (0.0011) -[2023-11-28 07:16:51,871][87424] Updated weights for policy 0, policy_version 269908 (0.0011) -[2023-11-28 07:16:52,254][87424] Updated weights for policy 0, policy_version 269918 (0.0009) -[2023-11-28 07:16:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 138141696. Throughput: 0: 2688.8, 1: 2665.3. Samples: 138159184. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:16:53,445][86177] Avg episode reward: [(0, '-574.990'), (1, '-499.300')] -[2023-11-28 07:16:53,733][87426] Updated weights for policy 1, policy_version 269700 (0.0010) -[2023-11-28 07:16:54,109][87426] Updated weights for policy 1, policy_version 269710 (0.0012) -[2023-11-28 07:16:54,427][87424] Updated weights for policy 0, policy_version 269928 (0.0009) -[2023-11-28 07:16:54,488][87426] Updated weights for policy 1, policy_version 269720 (0.0008) -[2023-11-28 07:16:54,806][87424] Updated weights for policy 0, policy_version 269938 (0.0007) -[2023-11-28 07:16:55,188][87424] Updated weights for policy 0, policy_version 269948 (0.0008) -[2023-11-28 07:16:56,257][87426] Updated weights for policy 1, policy_version 269730 (0.0010) -[2023-11-28 07:16:56,630][87426] Updated weights for policy 1, policy_version 269740 (0.0012) -[2023-11-28 07:16:57,015][87426] Updated weights for policy 1, policy_version 269750 (0.0010) -[2023-11-28 07:16:57,399][87426] Updated weights for policy 1, policy_version 269760 (0.0010) -[2023-11-28 07:16:57,414][87424] Updated weights for policy 0, policy_version 269958 (0.0010) -[2023-11-28 07:16:57,794][87424] Updated weights for policy 0, policy_version 269968 (0.0011) -[2023-11-28 07:16:58,175][87424] Updated weights for policy 0, policy_version 269978 (0.0008) -[2023-11-28 07:16:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 138174464. Throughput: 0: 2693.8, 1: 2704.5. Samples: 138184308. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:16:58,445][86177] Avg episode reward: [(0, '-594.240'), (1, '-501.680')] -[2023-11-28 07:16:59,720][87426] Updated weights for policy 1, policy_version 269770 (0.0007) -[2023-11-28 07:17:00,099][87426] Updated weights for policy 1, policy_version 269780 (0.0009) -[2023-11-28 07:17:00,481][87426] Updated weights for policy 1, policy_version 269790 (0.0009) -[2023-11-28 07:17:00,589][87424] Updated weights for policy 0, policy_version 269988 (0.0007) -[2023-11-28 07:17:00,966][87424] Updated weights for policy 0, policy_version 269998 (0.0009) -[2023-11-28 07:17:01,346][87424] Updated weights for policy 0, policy_version 270008 (0.0010) -[2023-11-28 07:17:02,820][87426] Updated weights for policy 1, policy_version 269800 (0.0011) -[2023-11-28 07:17:03,203][87424] Updated weights for policy 0, policy_version 270018 (0.0011) -[2023-11-28 07:17:03,206][87426] Updated weights for policy 1, policy_version 269810 (0.0010) -[2023-11-28 07:17:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 138190848. Throughput: 0: 2680.9, 1: 2709.2. Samples: 138208080. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:03,446][86177] Avg episode reward: [(0, '-552.930'), (1, '-503.360')] -[2023-11-28 07:17:03,577][87426] Updated weights for policy 1, policy_version 269820 (0.0009) -[2023-11-28 07:17:03,588][87424] Updated weights for policy 0, policy_version 270028 (0.0011) -[2023-11-28 07:17:03,965][87424] Updated weights for policy 0, policy_version 270038 (0.0009) -[2023-11-28 07:17:04,343][87424] Updated weights for policy 0, policy_version 270048 (0.0007) -[2023-11-28 07:17:05,176][87426] Updated weights for policy 1, policy_version 269830 (0.0009) -[2023-11-28 07:17:05,546][87426] Updated weights for policy 1, policy_version 269840 (0.0010) -[2023-11-28 07:17:05,925][87426] Updated weights for policy 1, policy_version 269850 (0.0009) -[2023-11-28 07:17:06,725][87424] Updated weights for policy 0, policy_version 270058 (0.0008) -[2023-11-28 07:17:07,113][87424] Updated weights for policy 0, policy_version 270068 (0.0010) -[2023-11-28 07:17:07,500][87424] Updated weights for policy 0, policy_version 270078 (0.0011) -[2023-11-28 07:17:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 138223616. Throughput: 0: 2678.8, 1: 2719.6. Samples: 138240176. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:08,445][86177] Avg episode reward: [(0, '-547.830'), (1, '-500.320')] -[2023-11-28 07:17:08,474][87426] Updated weights for policy 1, policy_version 269860 (0.0010) -[2023-11-28 07:17:08,846][87426] Updated weights for policy 1, policy_version 269870 (0.0009) -[2023-11-28 07:17:09,228][87426] Updated weights for policy 1, policy_version 269880 (0.0008) -[2023-11-28 07:17:10,044][87424] Updated weights for policy 0, policy_version 270088 (0.0011) -[2023-11-28 07:17:10,431][87424] Updated weights for policy 0, policy_version 270098 (0.0011) -[2023-11-28 07:17:10,812][87424] Updated weights for policy 0, policy_version 270108 (0.0008) -[2023-11-28 07:17:11,564][87426] Updated weights for policy 1, policy_version 269890 (0.0008) -[2023-11-28 07:17:11,942][87426] Updated weights for policy 1, policy_version 269900 (0.0010) -[2023-11-28 07:17:12,335][87426] Updated weights for policy 1, policy_version 269910 (0.0011) -[2023-11-28 07:17:12,709][87426] Updated weights for policy 1, policy_version 269920 (0.0011) -[2023-11-28 07:17:13,127][87424] Updated weights for policy 0, policy_version 270118 (0.0010) -[2023-11-28 07:17:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 138248192. Throughput: 0: 2659.2, 1: 2675.2. Samples: 138262800. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:13,445][86177] Avg episode reward: [(0, '-565.360'), (1, '-510.240')] -[2023-11-28 07:17:13,510][87424] Updated weights for policy 0, policy_version 270128 (0.0012) -[2023-11-28 07:17:13,890][87424] Updated weights for policy 0, policy_version 270138 (0.0012) -[2023-11-28 07:17:14,995][87426] Updated weights for policy 1, policy_version 269930 (0.0012) -[2023-11-28 07:17:15,372][87426] Updated weights for policy 1, policy_version 269940 (0.0012) -[2023-11-28 07:17:15,743][87426] Updated weights for policy 1, policy_version 269950 (0.0012) -[2023-11-28 07:17:16,254][87424] Updated weights for policy 0, policy_version 270148 (0.0012) -[2023-11-28 07:17:16,644][87424] Updated weights for policy 0, policy_version 270158 (0.0012) -[2023-11-28 07:17:17,019][87424] Updated weights for policy 0, policy_version 270168 (0.0012) -[2023-11-28 07:17:17,670][87426] Updated weights for policy 1, policy_version 269960 (0.0011) -[2023-11-28 07:17:18,043][87426] Updated weights for policy 1, policy_version 269970 (0.0011) -[2023-11-28 07:17:18,424][87426] Updated weights for policy 1, policy_version 269980 (0.0012) -[2023-11-28 07:17:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 138272768. Throughput: 0: 2664.8, 1: 2675.4. Samples: 138287612. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:18,445][86177] Avg episode reward: [(0, '-526.900'), (1, '-512.110')] -[2023-11-28 07:17:19,075][87424] Updated weights for policy 0, policy_version 270178 (0.0009) -[2023-11-28 07:17:19,464][87424] Updated weights for policy 0, policy_version 270188 (0.0012) -[2023-11-28 07:17:19,852][87424] Updated weights for policy 0, policy_version 270198 (0.0010) -[2023-11-28 07:17:20,238][87424] Updated weights for policy 0, policy_version 270208 (0.0010) -[2023-11-28 07:17:20,537][87426] Updated weights for policy 1, policy_version 269990 (0.0011) -[2023-11-28 07:17:20,920][87426] Updated weights for policy 1, policy_version 270000 (0.0008) -[2023-11-28 07:17:21,300][87426] Updated weights for policy 1, policy_version 270010 (0.0009) -[2023-11-28 07:17:22,251][87424] Updated weights for policy 0, policy_version 270218 (0.0009) -[2023-11-28 07:17:22,630][87424] Updated weights for policy 0, policy_version 270228 (0.0011) -[2023-11-28 07:17:23,023][87424] Updated weights for policy 0, policy_version 270238 (0.0012) -[2023-11-28 07:17:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 138305536. Throughput: 0: 2681.2, 1: 2697.2. Samples: 138320768. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:23,445][86177] Avg episode reward: [(0, '-536.500'), (1, '-511.380')] -[2023-11-28 07:17:23,748][87426] Updated weights for policy 1, policy_version 270020 (0.0009) -[2023-11-28 07:17:24,136][87426] Updated weights for policy 1, policy_version 270030 (0.0012) -[2023-11-28 07:17:24,510][87426] Updated weights for policy 1, policy_version 270040 (0.0011) -[2023-11-28 07:17:24,882][87424] Updated weights for policy 0, policy_version 270248 (0.0012) -[2023-11-28 07:17:25,262][87424] Updated weights for policy 0, policy_version 270258 (0.0010) -[2023-11-28 07:17:25,643][87424] Updated weights for policy 0, policy_version 270268 (0.0007) -[2023-11-28 07:17:26,962][87426] Updated weights for policy 1, policy_version 270050 (0.0009) -[2023-11-28 07:17:27,344][87426] Updated weights for policy 1, policy_version 270060 (0.0007) -[2023-11-28 07:17:27,725][87426] Updated weights for policy 1, policy_version 270070 (0.0010) -[2023-11-28 07:17:28,088][87424] Updated weights for policy 0, policy_version 270278 (0.0009) -[2023-11-28 07:17:28,104][87426] Updated weights for policy 1, policy_version 270080 (0.0009) -[2023-11-28 07:17:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 138330112. Throughput: 0: 2694.7, 1: 2732.5. Samples: 138345828. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:28,445][86177] Avg episode reward: [(0, '-544.240'), (1, '-511.430')] -[2023-11-28 07:17:28,480][87424] Updated weights for policy 0, policy_version 270288 (0.0008) -[2023-11-28 07:17:28,870][87424] Updated weights for policy 0, policy_version 270298 (0.0010) -[2023-11-28 07:17:29,956][87426] Updated weights for policy 1, policy_version 270090 (0.0011) -[2023-11-28 07:17:30,328][87426] Updated weights for policy 1, policy_version 270100 (0.0012) -[2023-11-28 07:17:30,704][87426] Updated weights for policy 1, policy_version 270110 (0.0012) -[2023-11-28 07:17:30,938][87424] Updated weights for policy 0, policy_version 270308 (0.0008) -[2023-11-28 07:17:31,324][87424] Updated weights for policy 0, policy_version 270318 (0.0007) -[2023-11-28 07:17:31,706][87424] Updated weights for policy 0, policy_version 270328 (0.0010) -[2023-11-28 07:17:32,867][87426] Updated weights for policy 1, policy_version 270120 (0.0010) -[2023-11-28 07:17:33,243][87426] Updated weights for policy 1, policy_version 270130 (0.0011) -[2023-11-28 07:17:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 138354688. Throughput: 0: 2669.7, 1: 2733.2. Samples: 138370276. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:33,445][86177] Avg episode reward: [(0, '-565.700'), (1, '-497.470')] -[2023-11-28 07:17:33,628][87426] Updated weights for policy 1, policy_version 270140 (0.0010) -[2023-11-28 07:17:33,928][87424] Updated weights for policy 0, policy_version 270338 (0.0010) -[2023-11-28 07:17:34,310][87424] Updated weights for policy 0, policy_version 270348 (0.0007) -[2023-11-28 07:17:34,691][87424] Updated weights for policy 0, policy_version 270358 (0.0008) -[2023-11-28 07:17:35,073][87424] Updated weights for policy 0, policy_version 270368 (0.0008) -[2023-11-28 07:17:36,096][87426] Updated weights for policy 1, policy_version 270150 (0.0007) -[2023-11-28 07:17:36,468][87426] Updated weights for policy 1, policy_version 270160 (0.0008) -[2023-11-28 07:17:36,864][87426] Updated weights for policy 1, policy_version 270170 (0.0009) -[2023-11-28 07:17:37,128][87424] Updated weights for policy 0, policy_version 270378 (0.0009) -[2023-11-28 07:17:37,507][87424] Updated weights for policy 0, policy_version 270388 (0.0012) -[2023-11-28 07:17:37,889][87424] Updated weights for policy 0, policy_version 270398 (0.0012) -[2023-11-28 07:17:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 138387456. Throughput: 0: 2676.8, 1: 2709.5. Samples: 138401568. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:38,445][86177] Avg episode reward: [(0, '-568.060'), (1, '-495.520')] -[2023-11-28 07:17:39,209][87426] Updated weights for policy 1, policy_version 270180 (0.0010) -[2023-11-28 07:17:39,587][87426] Updated weights for policy 1, policy_version 270190 (0.0009) -[2023-11-28 07:17:39,965][87426] Updated weights for policy 1, policy_version 270200 (0.0012) -[2023-11-28 07:17:40,036][87424] Updated weights for policy 0, policy_version 270408 (0.0012) -[2023-11-28 07:17:40,429][87424] Updated weights for policy 0, policy_version 270418 (0.0011) -[2023-11-28 07:17:40,815][87424] Updated weights for policy 0, policy_version 270428 (0.0012) -[2023-11-28 07:17:42,415][87426] Updated weights for policy 1, policy_version 270210 (0.0012) -[2023-11-28 07:17:42,788][87426] Updated weights for policy 1, policy_version 270220 (0.0011) -[2023-11-28 07:17:43,024][87424] Updated weights for policy 0, policy_version 270438 (0.0011) -[2023-11-28 07:17:43,167][87426] Updated weights for policy 1, policy_version 270230 (0.0010) -[2023-11-28 07:17:43,402][87424] Updated weights for policy 0, policy_version 270448 (0.0011) -[2023-11-28 07:17:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 138403840. Throughput: 0: 2680.4, 1: 2689.0. Samples: 138425928. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:43,445][86177] Avg episode reward: [(0, '-599.360'), (1, '-497.170')] -[2023-11-28 07:17:43,543][87426] Updated weights for policy 1, policy_version 270240 (0.0008) -[2023-11-28 07:17:43,779][87424] Updated weights for policy 0, policy_version 270458 (0.0011) -[2023-11-28 07:17:45,530][87426] Updated weights for policy 1, policy_version 270250 (0.0011) -[2023-11-28 07:17:45,586][87424] Updated weights for policy 0, policy_version 270468 (0.0009) -[2023-11-28 07:17:45,907][87426] Updated weights for policy 1, policy_version 270260 (0.0010) -[2023-11-28 07:17:45,975][87424] Updated weights for policy 0, policy_version 270478 (0.0011) -[2023-11-28 07:17:46,288][87426] Updated weights for policy 1, policy_version 270270 (0.0008) -[2023-11-28 07:17:46,372][87424] Updated weights for policy 0, policy_version 270488 (0.0011) -[2023-11-28 07:17:48,284][87426] Updated weights for policy 1, policy_version 270280 (0.0012) -[2023-11-28 07:17:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 138436608. Throughput: 0: 2700.4, 1: 2699.7. Samples: 138451084. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:48,445][86177] Avg episode reward: [(0, '-613.020'), (1, '-498.580')] -[2023-11-28 07:17:48,663][87426] Updated weights for policy 1, policy_version 270290 (0.0012) -[2023-11-28 07:17:48,694][87424] Updated weights for policy 0, policy_version 270498 (0.0008) -[2023-11-28 07:17:49,044][87426] Updated weights for policy 1, policy_version 270300 (0.0012) -[2023-11-28 07:17:49,071][87424] Updated weights for policy 0, policy_version 270508 (0.0008) -[2023-11-28 07:17:49,454][87424] Updated weights for policy 0, policy_version 270518 (0.0010) -[2023-11-28 07:17:49,834][87424] Updated weights for policy 0, policy_version 270528 (0.0008) -[2023-11-28 07:17:51,517][87426] Updated weights for policy 1, policy_version 270310 (0.0011) -[2023-11-28 07:17:51,909][87426] Updated weights for policy 1, policy_version 270320 (0.0011) -[2023-11-28 07:17:52,080][87424] Updated weights for policy 0, policy_version 270538 (0.0010) -[2023-11-28 07:17:52,278][87426] Updated weights for policy 1, policy_version 270330 (0.0011) -[2023-11-28 07:17:52,462][87424] Updated weights for policy 0, policy_version 270548 (0.0010) -[2023-11-28 07:17:52,846][87424] Updated weights for policy 0, policy_version 270558 (0.0007) -[2023-11-28 07:17:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 138469376. Throughput: 0: 2708.3, 1: 2699.2. Samples: 138483512. Policy #0 lag: (min: 31.0, avg: 45.3, max: 63.0) -[2023-11-28 07:17:53,445][86177] Avg episode reward: [(0, '-600.910'), (1, '-513.870')] -[2023-11-28 07:17:54,505][87426] Updated weights for policy 1, policy_version 270340 (0.0011) -[2023-11-28 07:17:54,884][87426] Updated weights for policy 1, policy_version 270350 (0.0011) -[2023-11-28 07:17:55,257][87426] Updated weights for policy 1, policy_version 270360 (0.0011) -[2023-11-28 07:17:55,341][87424] Updated weights for policy 0, policy_version 270568 (0.0008) -[2023-11-28 07:17:55,729][87424] Updated weights for policy 0, policy_version 270578 (0.0007) -[2023-11-28 07:17:56,114][87424] Updated weights for policy 0, policy_version 270588 (0.0007) -[2023-11-28 07:17:57,339][87426] Updated weights for policy 1, policy_version 270370 (0.0012) -[2023-11-28 07:17:57,712][87426] Updated weights for policy 1, policy_version 270380 (0.0012) -[2023-11-28 07:17:58,101][87426] Updated weights for policy 1, policy_version 270390 (0.0011) -[2023-11-28 07:17:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 138485760. Throughput: 0: 2732.7, 1: 2719.1. Samples: 138508132. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:17:58,445][86177] Avg episode reward: [(0, '-607.850'), (1, '-512.090')] -[2023-11-28 07:17:58,482][87426] Updated weights for policy 1, policy_version 270400 (0.0012) -[2023-11-28 07:17:58,521][87424] Updated weights for policy 0, policy_version 270598 (0.0008) -[2023-11-28 07:17:58,903][87424] Updated weights for policy 0, policy_version 270608 (0.0010) -[2023-11-28 07:17:59,282][87424] Updated weights for policy 0, policy_version 270618 (0.0012) -[2023-11-28 07:18:00,753][87426] Updated weights for policy 1, policy_version 270410 (0.0009) -[2023-11-28 07:18:01,134][87426] Updated weights for policy 1, policy_version 270420 (0.0007) -[2023-11-28 07:18:01,518][87426] Updated weights for policy 1, policy_version 270430 (0.0007) -[2023-11-28 07:18:01,858][87424] Updated weights for policy 0, policy_version 270628 (0.0011) -[2023-11-28 07:18:02,240][87424] Updated weights for policy 0, policy_version 270638 (0.0011) -[2023-11-28 07:18:02,615][87424] Updated weights for policy 0, policy_version 270648 (0.0012) -[2023-11-28 07:18:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 138518528. Throughput: 0: 2714.5, 1: 2714.9. Samples: 138531932. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:03,445][86177] Avg episode reward: [(0, '-565.010'), (1, '-512.680')] -[2023-11-28 07:18:03,816][87426] Updated weights for policy 1, policy_version 270440 (0.0011) -[2023-11-28 07:18:04,190][87426] Updated weights for policy 1, policy_version 270450 (0.0011) -[2023-11-28 07:18:04,384][87424] Updated weights for policy 0, policy_version 270658 (0.0011) -[2023-11-28 07:18:04,566][87426] Updated weights for policy 1, policy_version 270460 (0.0010) -[2023-11-28 07:18:04,759][87424] Updated weights for policy 0, policy_version 270668 (0.0012) -[2023-11-28 07:18:05,143][87424] Updated weights for policy 0, policy_version 270678 (0.0012) -[2023-11-28 07:18:05,515][87424] Updated weights for policy 0, policy_version 270688 (0.0011) -[2023-11-28 07:18:06,859][87426] Updated weights for policy 1, policy_version 270470 (0.0010) -[2023-11-28 07:18:07,234][87426] Updated weights for policy 1, policy_version 270480 (0.0011) -[2023-11-28 07:18:07,397][87424] Updated weights for policy 0, policy_version 270698 (0.0011) -[2023-11-28 07:18:07,616][87426] Updated weights for policy 1, policy_version 270490 (0.0008) -[2023-11-28 07:18:07,779][87424] Updated weights for policy 0, policy_version 270708 (0.0011) -[2023-11-28 07:18:08,146][87424] Updated weights for policy 0, policy_version 270718 (0.0012) -[2023-11-28 07:18:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 138551296. Throughput: 0: 2725.1, 1: 2682.9. Samples: 138564124. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:08,445][86177] Avg episode reward: [(0, '-553.270'), (1, '-512.050')] -[2023-11-28 07:18:09,386][87426] Updated weights for policy 1, policy_version 270500 (0.0009) -[2023-11-28 07:18:09,777][87426] Updated weights for policy 1, policy_version 270510 (0.0012) -[2023-11-28 07:18:09,921][87424] Updated weights for policy 0, policy_version 270728 (0.0012) -[2023-11-28 07:18:10,155][87426] Updated weights for policy 1, policy_version 270520 (0.0011) -[2023-11-28 07:18:10,303][87424] Updated weights for policy 0, policy_version 270738 (0.0012) -[2023-11-28 07:18:10,684][87424] Updated weights for policy 0, policy_version 270748 (0.0011) -[2023-11-28 07:18:12,655][87426] Updated weights for policy 1, policy_version 270530 (0.0009) -[2023-11-28 07:18:13,037][87426] Updated weights for policy 1, policy_version 270540 (0.0010) -[2023-11-28 07:18:13,210][87424] Updated weights for policy 0, policy_version 270758 (0.0011) -[2023-11-28 07:18:13,419][87426] Updated weights for policy 1, policy_version 270550 (0.0012) -[2023-11-28 07:18:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 138567680. Throughput: 0: 2723.6, 1: 2674.5. Samples: 138588740. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:13,445][86177] Avg episode reward: [(0, '-532.250'), (1, '-502.890')] -[2023-11-28 07:18:13,588][87424] Updated weights for policy 0, policy_version 270768 (0.0009) -[2023-11-28 07:18:13,798][87426] Updated weights for policy 1, policy_version 270560 (0.0012) -[2023-11-28 07:18:13,982][87424] Updated weights for policy 0, policy_version 270778 (0.0011) -[2023-11-28 07:18:16,058][87424] Updated weights for policy 0, policy_version 270788 (0.0010) -[2023-11-28 07:18:16,358][87426] Updated weights for policy 1, policy_version 270570 (0.0010) -[2023-11-28 07:18:16,436][87424] Updated weights for policy 0, policy_version 270798 (0.0011) -[2023-11-28 07:18:16,722][87426] Updated weights for policy 1, policy_version 270580 (0.0011) -[2023-11-28 07:18:16,818][87424] Updated weights for policy 0, policy_version 270808 (0.0009) -[2023-11-28 07:18:17,101][87426] Updated weights for policy 1, policy_version 270590 (0.0012) -[2023-11-28 07:18:18,444][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 138600448. Throughput: 0: 2711.4, 1: 2667.7. Samples: 138612336. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:18,446][86177] Avg episode reward: [(0, '-517.020'), (1, '-504.370')] -[2023-11-28 07:18:18,460][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000270816_69328896.pth... -[2023-11-28 07:18:18,460][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000270592_69271552.pth... -[2023-11-28 07:18:18,495][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000268288_68681728.pth -[2023-11-28 07:18:18,498][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000268096_68632576.pth -[2023-11-28 07:18:19,273][87424] Updated weights for policy 0, policy_version 270818 (0.0008) -[2023-11-28 07:18:19,560][87426] Updated weights for policy 1, policy_version 270600 (0.0011) -[2023-11-28 07:18:19,652][87424] Updated weights for policy 0, policy_version 270828 (0.0011) -[2023-11-28 07:18:19,939][87426] Updated weights for policy 1, policy_version 270610 (0.0009) -[2023-11-28 07:18:20,024][87424] Updated weights for policy 0, policy_version 270838 (0.0011) -[2023-11-28 07:18:20,323][87426] Updated weights for policy 1, policy_version 270620 (0.0011) -[2023-11-28 07:18:20,402][87424] Updated weights for policy 0, policy_version 270848 (0.0009) -[2023-11-28 07:18:22,317][87426] Updated weights for policy 1, policy_version 270630 (0.0011) -[2023-11-28 07:18:22,697][87426] Updated weights for policy 1, policy_version 270640 (0.0011) -[2023-11-28 07:18:23,002][87424] Updated weights for policy 0, policy_version 270858 (0.0009) -[2023-11-28 07:18:23,066][87426] Updated weights for policy 1, policy_version 270650 (0.0012) -[2023-11-28 07:18:23,381][87424] Updated weights for policy 0, policy_version 270868 (0.0009) -[2023-11-28 07:18:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 138625024. Throughput: 0: 2711.6, 1: 2692.2. Samples: 138644736. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:23,445][86177] Avg episode reward: [(0, '-521.190'), (1, '-504.440')] -[2023-11-28 07:18:23,761][87424] Updated weights for policy 0, policy_version 270878 (0.0008) -[2023-11-28 07:18:25,038][87426] Updated weights for policy 1, policy_version 270660 (0.0012) -[2023-11-28 07:18:25,413][87426] Updated weights for policy 1, policy_version 270670 (0.0011) -[2023-11-28 07:18:25,633][87424] Updated weights for policy 0, policy_version 270888 (0.0010) -[2023-11-28 07:18:25,792][87426] Updated weights for policy 1, policy_version 270680 (0.0011) -[2023-11-28 07:18:26,025][87424] Updated weights for policy 0, policy_version 270898 (0.0011) -[2023-11-28 07:18:26,415][87424] Updated weights for policy 0, policy_version 270908 (0.0011) -[2023-11-28 07:18:28,059][87426] Updated weights for policy 1, policy_version 270690 (0.0011) -[2023-11-28 07:18:28,248][87424] Updated weights for policy 0, policy_version 270918 (0.0009) -[2023-11-28 07:18:28,437][87426] Updated weights for policy 1, policy_version 270700 (0.0007) -[2023-11-28 07:18:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 138649600. Throughput: 0: 2732.3, 1: 2692.6. Samples: 138670048. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:28,445][86177] Avg episode reward: [(0, '-537.330'), (1, '-508.400')] -[2023-11-28 07:18:28,640][87424] Updated weights for policy 0, policy_version 270928 (0.0007) -[2023-11-28 07:18:28,823][87426] Updated weights for policy 1, policy_version 270710 (0.0008) -[2023-11-28 07:18:29,023][87424] Updated weights for policy 0, policy_version 270938 (0.0010) -[2023-11-28 07:18:29,199][87426] Updated weights for policy 1, policy_version 270720 (0.0008) -[2023-11-28 07:18:31,028][87424] Updated weights for policy 0, policy_version 270948 (0.0010) -[2023-11-28 07:18:31,188][87426] Updated weights for policy 1, policy_version 270730 (0.0012) -[2023-11-28 07:18:31,413][87424] Updated weights for policy 0, policy_version 270958 (0.0012) -[2023-11-28 07:18:31,561][87426] Updated weights for policy 1, policy_version 270740 (0.0012) -[2023-11-28 07:18:31,786][87424] Updated weights for policy 0, policy_version 270968 (0.0011) -[2023-11-28 07:18:31,935][87426] Updated weights for policy 1, policy_version 270750 (0.0011) -[2023-11-28 07:18:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 138682368. Throughput: 0: 2720.7, 1: 2689.0. Samples: 138694520. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:33,445][86177] Avg episode reward: [(0, '-537.100'), (1, '-505.410')] -[2023-11-28 07:18:33,604][87426] Updated weights for policy 1, policy_version 270760 (0.0012) -[2023-11-28 07:18:33,838][87424] Updated weights for policy 0, policy_version 270978 (0.0011) -[2023-11-28 07:18:33,986][87426] Updated weights for policy 1, policy_version 270770 (0.0012) -[2023-11-28 07:18:34,212][87424] Updated weights for policy 0, policy_version 270988 (0.0012) -[2023-11-28 07:18:34,366][87426] Updated weights for policy 1, policy_version 270780 (0.0012) -[2023-11-28 07:18:34,600][87424] Updated weights for policy 0, policy_version 270998 (0.0011) -[2023-11-28 07:18:34,973][87424] Updated weights for policy 0, policy_version 271008 (0.0009) -[2023-11-28 07:18:36,397][87426] Updated weights for policy 1, policy_version 270790 (0.0009) -[2023-11-28 07:18:36,777][87426] Updated weights for policy 1, policy_version 270800 (0.0008) -[2023-11-28 07:18:37,151][87426] Updated weights for policy 1, policy_version 270810 (0.0008) -[2023-11-28 07:18:37,512][87424] Updated weights for policy 0, policy_version 271018 (0.0010) -[2023-11-28 07:18:37,892][87424] Updated weights for policy 0, policy_version 271028 (0.0008) -[2023-11-28 07:18:38,290][87424] Updated weights for policy 0, policy_version 271038 (0.0007) -[2023-11-28 07:18:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 138715136. Throughput: 0: 2717.3, 1: 2700.6. Samples: 138727320. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:38,445][86177] Avg episode reward: [(0, '-537.520'), (1, '-505.450')] -[2023-11-28 07:18:39,466][87426] Updated weights for policy 1, policy_version 270820 (0.0010) -[2023-11-28 07:18:39,848][87426] Updated weights for policy 1, policy_version 270830 (0.0012) -[2023-11-28 07:18:40,228][87426] Updated weights for policy 1, policy_version 270840 (0.0012) -[2023-11-28 07:18:40,696][87424] Updated weights for policy 0, policy_version 271048 (0.0010) -[2023-11-28 07:18:41,079][87424] Updated weights for policy 0, policy_version 271058 (0.0010) -[2023-11-28 07:18:41,458][87424] Updated weights for policy 0, policy_version 271068 (0.0012) -[2023-11-28 07:18:42,880][87426] Updated weights for policy 1, policy_version 270850 (0.0011) -[2023-11-28 07:18:43,249][87426] Updated weights for policy 1, policy_version 270860 (0.0012) -[2023-11-28 07:18:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 138731520. Throughput: 0: 2701.3, 1: 2691.5. Samples: 138750808. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:43,445][86177] Avg episode reward: [(0, '-540.080'), (1, '-502.910')] -[2023-11-28 07:18:43,484][87424] Updated weights for policy 0, policy_version 271078 (0.0012) -[2023-11-28 07:18:43,623][87426] Updated weights for policy 1, policy_version 270870 (0.0011) -[2023-11-28 07:18:43,865][87424] Updated weights for policy 0, policy_version 271088 (0.0011) -[2023-11-28 07:18:44,007][87426] Updated weights for policy 1, policy_version 270880 (0.0012) -[2023-11-28 07:18:44,252][87424] Updated weights for policy 0, policy_version 271098 (0.0012) -[2023-11-28 07:18:46,460][87426] Updated weights for policy 1, policy_version 270890 (0.0012) -[2023-11-28 07:18:46,837][87426] Updated weights for policy 1, policy_version 270900 (0.0010) -[2023-11-28 07:18:46,843][87424] Updated weights for policy 0, policy_version 271108 (0.0012) -[2023-11-28 07:18:47,217][87426] Updated weights for policy 1, policy_version 270910 (0.0009) -[2023-11-28 07:18:47,217][87424] Updated weights for policy 0, policy_version 271118 (0.0011) -[2023-11-28 07:18:47,601][87424] Updated weights for policy 0, policy_version 271128 (0.0011) -[2023-11-28 07:18:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 138764288. Throughput: 0: 2724.6, 1: 2695.9. Samples: 138775856. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:48,445][86177] Avg episode reward: [(0, '-532.670'), (1, '-519.350')] -[2023-11-28 07:18:49,269][87426] Updated weights for policy 1, policy_version 270920 (0.0011) -[2023-11-28 07:18:49,441][87424] Updated weights for policy 0, policy_version 271138 (0.0012) -[2023-11-28 07:18:49,637][87426] Updated weights for policy 1, policy_version 270930 (0.0011) -[2023-11-28 07:18:49,831][87424] Updated weights for policy 0, policy_version 271148 (0.0010) -[2023-11-28 07:18:50,018][87426] Updated weights for policy 1, policy_version 270940 (0.0011) -[2023-11-28 07:18:50,215][87424] Updated weights for policy 0, policy_version 271158 (0.0011) -[2023-11-28 07:18:50,598][87424] Updated weights for policy 0, policy_version 271168 (0.0009) -[2023-11-28 07:18:52,406][87426] Updated weights for policy 1, policy_version 270950 (0.0011) -[2023-11-28 07:18:52,455][87424] Updated weights for policy 0, policy_version 271178 (0.0012) -[2023-11-28 07:18:52,774][87426] Updated weights for policy 1, policy_version 270960 (0.0011) -[2023-11-28 07:18:52,842][87424] Updated weights for policy 0, policy_version 271188 (0.0009) -[2023-11-28 07:18:53,156][87426] Updated weights for policy 1, policy_version 270970 (0.0011) -[2023-11-28 07:18:53,220][87424] Updated weights for policy 0, policy_version 271198 (0.0008) -[2023-11-28 07:18:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 138797056. Throughput: 0: 2697.4, 1: 2730.0. Samples: 138808360. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:53,445][86177] Avg episode reward: [(0, '-524.150'), (1, '-518.270')] -[2023-11-28 07:18:55,050][87426] Updated weights for policy 1, policy_version 270980 (0.0010) -[2023-11-28 07:18:55,438][87426] Updated weights for policy 1, policy_version 270990 (0.0012) -[2023-11-28 07:18:55,587][87424] Updated weights for policy 0, policy_version 271208 (0.0008) -[2023-11-28 07:18:55,807][87426] Updated weights for policy 1, policy_version 271000 (0.0010) -[2023-11-28 07:18:55,975][87424] Updated weights for policy 0, policy_version 271218 (0.0008) -[2023-11-28 07:18:56,357][87424] Updated weights for policy 0, policy_version 271228 (0.0008) -[2023-11-28 07:18:57,851][87426] Updated weights for policy 1, policy_version 271010 (0.0010) -[2023-11-28 07:18:58,228][87426] Updated weights for policy 1, policy_version 271020 (0.0011) -[2023-11-28 07:18:58,409][87424] Updated weights for policy 0, policy_version 271238 (0.0012) -[2023-11-28 07:18:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 138813440. Throughput: 0: 2698.1, 1: 2726.3. Samples: 138832840. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:18:58,445][86177] Avg episode reward: [(0, '-573.540'), (1, '-517.860')] -[2023-11-28 07:18:58,611][87426] Updated weights for policy 1, policy_version 271030 (0.0011) -[2023-11-28 07:18:58,793][87424] Updated weights for policy 0, policy_version 271248 (0.0012) -[2023-11-28 07:18:58,985][87426] Updated weights for policy 1, policy_version 271040 (0.0012) -[2023-11-28 07:18:59,177][87424] Updated weights for policy 0, policy_version 271258 (0.0008) -[2023-11-28 07:19:00,719][87426] Updated weights for policy 1, policy_version 271050 (0.0012) -[2023-11-28 07:19:01,093][87426] Updated weights for policy 1, policy_version 271060 (0.0012) -[2023-11-28 07:19:01,358][87424] Updated weights for policy 0, policy_version 271268 (0.0009) -[2023-11-28 07:19:01,491][87426] Updated weights for policy 1, policy_version 271070 (0.0009) -[2023-11-28 07:19:01,758][87424] Updated weights for policy 0, policy_version 271278 (0.0011) -[2023-11-28 07:19:02,142][87424] Updated weights for policy 0, policy_version 271288 (0.0010) -[2023-11-28 07:19:03,378][87426] Updated weights for policy 1, policy_version 271080 (0.0010) -[2023-11-28 07:19:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 138846208. Throughput: 0: 2730.6, 1: 2734.6. Samples: 138858268. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:19:03,445][86177] Avg episode reward: [(0, '-570.590'), (1, '-515.650')] -[2023-11-28 07:19:03,751][87426] Updated weights for policy 1, policy_version 271090 (0.0009) -[2023-11-28 07:19:04,137][87426] Updated weights for policy 1, policy_version 271100 (0.0010) -[2023-11-28 07:19:04,233][87424] Updated weights for policy 0, policy_version 271298 (0.0009) -[2023-11-28 07:19:04,606][87424] Updated weights for policy 0, policy_version 271308 (0.0012) -[2023-11-28 07:19:04,988][87424] Updated weights for policy 0, policy_version 271318 (0.0012) -[2023-11-28 07:19:05,370][87424] Updated weights for policy 0, policy_version 271328 (0.0011) -[2023-11-28 07:19:05,989][87426] Updated weights for policy 1, policy_version 271110 (0.0010) -[2023-11-28 07:19:06,357][87426] Updated weights for policy 1, policy_version 271120 (0.0011) -[2023-11-28 07:19:06,732][87426] Updated weights for policy 1, policy_version 271130 (0.0012) -[2023-11-28 07:19:07,139][87424] Updated weights for policy 0, policy_version 271338 (0.0011) -[2023-11-28 07:19:07,506][87424] Updated weights for policy 0, policy_version 271348 (0.0012) -[2023-11-28 07:19:07,897][87424] Updated weights for policy 0, policy_version 271358 (0.0012) -[2023-11-28 07:19:08,445][86177] Fps is (10 sec: 6552.8, 60 sec: 5461.2, 300 sec: 5415.0). Total num frames: 138878976. Throughput: 0: 2714.1, 1: 2738.5. Samples: 138890108. Policy #0 lag: (min: 12.0, avg: 24.7, max: 44.0) -[2023-11-28 07:19:08,446][86177] Avg episode reward: [(0, '-566.180'), (1, '-516.540')] -[2023-11-28 07:19:08,936][87426] Updated weights for policy 1, policy_version 271140 (0.0011) -[2023-11-28 07:19:09,316][87426] Updated weights for policy 1, policy_version 271150 (0.0010) -[2023-11-28 07:19:09,695][87426] Updated weights for policy 1, policy_version 271160 (0.0007) -[2023-11-28 07:19:10,164][87424] Updated weights for policy 0, policy_version 271368 (0.0010) -[2023-11-28 07:19:10,545][87424] Updated weights for policy 0, policy_version 271378 (0.0009) -[2023-11-28 07:19:10,936][87424] Updated weights for policy 0, policy_version 271388 (0.0008) -[2023-11-28 07:19:12,178][87426] Updated weights for policy 1, policy_version 271170 (0.0010) -[2023-11-28 07:19:12,547][87426] Updated weights for policy 1, policy_version 271180 (0.0011) -[2023-11-28 07:19:12,923][87426] Updated weights for policy 1, policy_version 271190 (0.0009) -[2023-11-28 07:19:13,300][87426] Updated weights for policy 1, policy_version 271200 (0.0009) -[2023-11-28 07:19:13,352][87424] Updated weights for policy 0, policy_version 271398 (0.0008) -[2023-11-28 07:19:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 138903552. Throughput: 0: 2692.8, 1: 2724.9. Samples: 138913844. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:13,445][86177] Avg episode reward: [(0, '-579.110'), (1, '-522.980')] -[2023-11-28 07:19:13,734][87424] Updated weights for policy 0, policy_version 271408 (0.0010) -[2023-11-28 07:19:14,112][87424] Updated weights for policy 0, policy_version 271418 (0.0009) -[2023-11-28 07:19:15,813][87426] Updated weights for policy 1, policy_version 271210 (0.0008) -[2023-11-28 07:19:16,183][87426] Updated weights for policy 1, policy_version 271220 (0.0008) -[2023-11-28 07:19:16,231][87424] Updated weights for policy 0, policy_version 271428 (0.0009) -[2023-11-28 07:19:16,564][87426] Updated weights for policy 1, policy_version 271230 (0.0011) -[2023-11-28 07:19:16,610][87424] Updated weights for policy 0, policy_version 271438 (0.0011) -[2023-11-28 07:19:16,994][87424] Updated weights for policy 0, policy_version 271448 (0.0010) -[2023-11-28 07:19:18,444][86177] Fps is (10 sec: 4915.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 138928128. Throughput: 0: 2689.5, 1: 2713.9. Samples: 138937672. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:18,446][86177] Avg episode reward: [(0, '-543.490'), (1, '-508.540')] -[2023-11-28 07:19:19,066][87426] Updated weights for policy 1, policy_version 271240 (0.0011) -[2023-11-28 07:19:19,351][87424] Updated weights for policy 0, policy_version 271458 (0.0008) -[2023-11-28 07:19:19,448][87426] Updated weights for policy 1, policy_version 271250 (0.0012) -[2023-11-28 07:19:19,723][87424] Updated weights for policy 0, policy_version 271468 (0.0008) -[2023-11-28 07:19:19,828][87426] Updated weights for policy 1, policy_version 271260 (0.0011) -[2023-11-28 07:19:20,104][87424] Updated weights for policy 0, policy_version 271478 (0.0011) -[2023-11-28 07:19:20,485][87424] Updated weights for policy 0, policy_version 271488 (0.0012) -[2023-11-28 07:19:21,829][87426] Updated weights for policy 1, policy_version 271270 (0.0010) -[2023-11-28 07:19:22,214][87426] Updated weights for policy 1, policy_version 271280 (0.0011) -[2023-11-28 07:19:22,590][87426] Updated weights for policy 1, policy_version 271290 (0.0010) -[2023-11-28 07:19:22,897][87424] Updated weights for policy 0, policy_version 271498 (0.0010) -[2023-11-28 07:19:23,284][87424] Updated weights for policy 0, policy_version 271508 (0.0008) -[2023-11-28 07:19:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 138952704. Throughput: 0: 2676.4, 1: 2721.4. Samples: 138970220. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:23,445][86177] Avg episode reward: [(0, '-526.030'), (1, '-506.650')] -[2023-11-28 07:19:23,662][87424] Updated weights for policy 0, policy_version 271518 (0.0007) -[2023-11-28 07:19:25,122][87426] Updated weights for policy 1, policy_version 271300 (0.0010) -[2023-11-28 07:19:25,496][87426] Updated weights for policy 1, policy_version 271310 (0.0012) -[2023-11-28 07:19:25,881][87426] Updated weights for policy 1, policy_version 271320 (0.0011) -[2023-11-28 07:19:26,004][87424] Updated weights for policy 0, policy_version 271528 (0.0007) -[2023-11-28 07:19:26,392][87424] Updated weights for policy 0, policy_version 271538 (0.0007) -[2023-11-28 07:19:26,779][87424] Updated weights for policy 0, policy_version 271548 (0.0007) -[2023-11-28 07:19:28,320][87426] Updated weights for policy 1, policy_version 271330 (0.0009) -[2023-11-28 07:19:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 138977280. Throughput: 0: 2689.8, 1: 2732.6. Samples: 138994816. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:28,445][86177] Avg episode reward: [(0, '-532.650'), (1, '-544.040')] -[2023-11-28 07:19:28,503][87424] Updated weights for policy 0, policy_version 271558 (0.0007) -[2023-11-28 07:19:28,693][87426] Updated weights for policy 1, policy_version 271340 (0.0007) -[2023-11-28 07:19:28,884][87424] Updated weights for policy 0, policy_version 271568 (0.0008) -[2023-11-28 07:19:29,083][87426] Updated weights for policy 1, policy_version 271350 (0.0007) -[2023-11-28 07:19:29,274][87424] Updated weights for policy 0, policy_version 271578 (0.0009) -[2023-11-28 07:19:29,464][87426] Updated weights for policy 1, policy_version 271360 (0.0008) -[2023-11-28 07:19:31,766][87424] Updated weights for policy 0, policy_version 271588 (0.0011) -[2023-11-28 07:19:31,784][87426] Updated weights for policy 1, policy_version 271370 (0.0011) -[2023-11-28 07:19:32,153][87424] Updated weights for policy 0, policy_version 271598 (0.0010) -[2023-11-28 07:19:32,161][87426] Updated weights for policy 1, policy_version 271380 (0.0010) -[2023-11-28 07:19:32,523][87424] Updated weights for policy 0, policy_version 271608 (0.0008) -[2023-11-28 07:19:32,536][87426] Updated weights for policy 1, policy_version 271390 (0.0011) -[2023-11-28 07:19:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 139010048. Throughput: 0: 2717.7, 1: 2731.9. Samples: 139021088. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:33,445][86177] Avg episode reward: [(0, '-520.790'), (1, '-536.990')] -[2023-11-28 07:19:34,555][87426] Updated weights for policy 1, policy_version 271400 (0.0011) -[2023-11-28 07:19:34,672][87424] Updated weights for policy 0, policy_version 271618 (0.0009) -[2023-11-28 07:19:34,938][87426] Updated weights for policy 1, policy_version 271410 (0.0011) -[2023-11-28 07:19:35,055][87424] Updated weights for policy 0, policy_version 271628 (0.0010) -[2023-11-28 07:19:35,328][87426] Updated weights for policy 1, policy_version 271420 (0.0011) -[2023-11-28 07:19:35,435][87424] Updated weights for policy 0, policy_version 271638 (0.0012) -[2023-11-28 07:19:35,819][87424] Updated weights for policy 0, policy_version 271648 (0.0011) -[2023-11-28 07:19:37,187][87426] Updated weights for policy 1, policy_version 271430 (0.0011) -[2023-11-28 07:19:37,567][87426] Updated weights for policy 1, policy_version 271440 (0.0012) -[2023-11-28 07:19:37,804][87424] Updated weights for policy 0, policy_version 271658 (0.0012) -[2023-11-28 07:19:37,940][87426] Updated weights for policy 1, policy_version 271450 (0.0012) -[2023-11-28 07:19:38,187][87424] Updated weights for policy 0, policy_version 271668 (0.0011) -[2023-11-28 07:19:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 139034624. Throughput: 0: 2758.3, 1: 2708.9. Samples: 139054384. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:38,445][86177] Avg episode reward: [(0, '-527.690'), (1, '-536.230')] -[2023-11-28 07:19:38,571][87424] Updated weights for policy 0, policy_version 271678 (0.0012) -[2023-11-28 07:19:39,876][87426] Updated weights for policy 1, policy_version 271460 (0.0012) -[2023-11-28 07:19:40,255][87426] Updated weights for policy 1, policy_version 271470 (0.0009) -[2023-11-28 07:19:40,627][87426] Updated weights for policy 1, policy_version 271480 (0.0011) -[2023-11-28 07:19:41,026][87424] Updated weights for policy 0, policy_version 271688 (0.0009) -[2023-11-28 07:19:41,409][87424] Updated weights for policy 0, policy_version 271698 (0.0009) -[2023-11-28 07:19:41,799][87424] Updated weights for policy 0, policy_version 271708 (0.0012) -[2023-11-28 07:19:42,979][87426] Updated weights for policy 1, policy_version 271490 (0.0011) -[2023-11-28 07:19:43,362][87426] Updated weights for policy 1, policy_version 271500 (0.0011) -[2023-11-28 07:19:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 139059200. Throughput: 0: 2735.6, 1: 2714.8. Samples: 139078112. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:43,445][86177] Avg episode reward: [(0, '-528.690'), (1, '-539.410')] -[2023-11-28 07:19:43,733][87426] Updated weights for policy 1, policy_version 271510 (0.0011) -[2023-11-28 07:19:44,112][87426] Updated weights for policy 1, policy_version 271520 (0.0011) -[2023-11-28 07:19:44,119][87424] Updated weights for policy 0, policy_version 271718 (0.0009) -[2023-11-28 07:19:44,500][87424] Updated weights for policy 0, policy_version 271728 (0.0008) -[2023-11-28 07:19:44,881][87424] Updated weights for policy 0, policy_version 271738 (0.0011) -[2023-11-28 07:19:46,006][87426] Updated weights for policy 1, policy_version 271530 (0.0012) -[2023-11-28 07:19:46,385][87426] Updated weights for policy 1, policy_version 271540 (0.0012) -[2023-11-28 07:19:46,760][87426] Updated weights for policy 1, policy_version 271550 (0.0011) -[2023-11-28 07:19:46,794][87424] Updated weights for policy 0, policy_version 271748 (0.0012) -[2023-11-28 07:19:47,164][87424] Updated weights for policy 0, policy_version 271758 (0.0008) -[2023-11-28 07:19:47,539][87424] Updated weights for policy 0, policy_version 271768 (0.0009) -[2023-11-28 07:19:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139091968. Throughput: 0: 2710.9, 1: 2716.5. Samples: 139102504. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:48,445][86177] Avg episode reward: [(0, '-524.420'), (1, '-502.900')] -[2023-11-28 07:19:48,511][87426] Updated weights for policy 1, policy_version 271560 (0.0011) -[2023-11-28 07:19:48,890][87426] Updated weights for policy 1, policy_version 271570 (0.0012) -[2023-11-28 07:19:49,266][87426] Updated weights for policy 1, policy_version 271580 (0.0012) -[2023-11-28 07:19:49,548][87424] Updated weights for policy 0, policy_version 271778 (0.0011) -[2023-11-28 07:19:49,934][87424] Updated weights for policy 0, policy_version 271788 (0.0015) -[2023-11-28 07:19:50,310][87424] Updated weights for policy 0, policy_version 271798 (0.0012) -[2023-11-28 07:19:50,691][87424] Updated weights for policy 0, policy_version 271808 (0.0012) -[2023-11-28 07:19:51,258][87426] Updated weights for policy 1, policy_version 271590 (0.0011) -[2023-11-28 07:19:51,636][87426] Updated weights for policy 1, policy_version 271600 (0.0011) -[2023-11-28 07:19:52,013][87426] Updated weights for policy 1, policy_version 271610 (0.0010) -[2023-11-28 07:19:53,072][87424] Updated weights for policy 0, policy_version 271818 (0.0008) -[2023-11-28 07:19:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 139116544. Throughput: 0: 2733.0, 1: 2738.1. Samples: 139136300. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:53,445][86177] Avg episode reward: [(0, '-514.630'), (1, '-534.430')] -[2023-11-28 07:19:53,462][87424] Updated weights for policy 0, policy_version 271828 (0.0009) -[2023-11-28 07:19:53,845][87424] Updated weights for policy 0, policy_version 271838 (0.0010) -[2023-11-28 07:19:54,390][87426] Updated weights for policy 1, policy_version 271620 (0.0010) -[2023-11-28 07:19:54,756][87426] Updated weights for policy 1, policy_version 271630 (0.0011) -[2023-11-28 07:19:55,135][87426] Updated weights for policy 1, policy_version 271640 (0.0007) -[2023-11-28 07:19:56,017][87424] Updated weights for policy 0, policy_version 271848 (0.0008) -[2023-11-28 07:19:56,411][87424] Updated weights for policy 0, policy_version 271858 (0.0007) -[2023-11-28 07:19:56,813][87424] Updated weights for policy 0, policy_version 271868 (0.0007) -[2023-11-28 07:19:57,070][87426] Updated weights for policy 1, policy_version 271650 (0.0008) -[2023-11-28 07:19:57,449][87426] Updated weights for policy 1, policy_version 271660 (0.0012) -[2023-11-28 07:19:57,839][87426] Updated weights for policy 1, policy_version 271670 (0.0010) -[2023-11-28 07:19:58,214][87426] Updated weights for policy 1, policy_version 271680 (0.0007) -[2023-11-28 07:19:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 139149312. Throughput: 0: 2731.7, 1: 2762.7. Samples: 139161092. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:19:58,445][86177] Avg episode reward: [(0, '-511.790'), (1, '-532.400')] -[2023-11-28 07:19:59,095][87424] Updated weights for policy 0, policy_version 271878 (0.0007) -[2023-11-28 07:19:59,477][87424] Updated weights for policy 0, policy_version 271888 (0.0007) -[2023-11-28 07:19:59,862][87424] Updated weights for policy 0, policy_version 271898 (0.0008) -[2023-11-28 07:20:00,525][87426] Updated weights for policy 1, policy_version 271690 (0.0011) -[2023-11-28 07:20:00,898][87426] Updated weights for policy 1, policy_version 271700 (0.0010) -[2023-11-28 07:20:01,280][87426] Updated weights for policy 1, policy_version 271710 (0.0008) -[2023-11-28 07:20:02,324][87424] Updated weights for policy 0, policy_version 271908 (0.0011) -[2023-11-28 07:20:02,706][87424] Updated weights for policy 0, policy_version 271918 (0.0008) -[2023-11-28 07:20:03,102][87424] Updated weights for policy 0, policy_version 271928 (0.0009) -[2023-11-28 07:20:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139173888. Throughput: 0: 2709.3, 1: 2775.8. Samples: 139184504. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:20:03,445][86177] Avg episode reward: [(0, '-511.730'), (1, '-534.130')] -[2023-11-28 07:20:03,579][87426] Updated weights for policy 1, policy_version 271720 (0.0008) -[2023-11-28 07:20:03,954][87426] Updated weights for policy 1, policy_version 271730 (0.0007) -[2023-11-28 07:20:04,338][87426] Updated weights for policy 1, policy_version 271740 (0.0009) -[2023-11-28 07:20:04,843][87424] Updated weights for policy 0, policy_version 271938 (0.0012) -[2023-11-28 07:20:05,225][87424] Updated weights for policy 0, policy_version 271948 (0.0012) -[2023-11-28 07:20:05,601][87424] Updated weights for policy 0, policy_version 271958 (0.0012) -[2023-11-28 07:20:05,991][87424] Updated weights for policy 0, policy_version 271968 (0.0012) -[2023-11-28 07:20:06,248][87426] Updated weights for policy 1, policy_version 271750 (0.0011) -[2023-11-28 07:20:06,617][87426] Updated weights for policy 1, policy_version 271760 (0.0008) -[2023-11-28 07:20:06,998][87426] Updated weights for policy 1, policy_version 271770 (0.0012) -[2023-11-28 07:20:07,772][87424] Updated weights for policy 0, policy_version 271978 (0.0011) -[2023-11-28 07:20:08,151][87424] Updated weights for policy 0, policy_version 271988 (0.0008) -[2023-11-28 07:20:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.9, 300 sec: 5415.0). Total num frames: 139198464. Throughput: 0: 2747.1, 1: 2785.7. Samples: 139219196. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:20:08,445][86177] Avg episode reward: [(0, '-507.850'), (1, '-533.330')] -[2023-11-28 07:20:08,532][87424] Updated weights for policy 0, policy_version 271998 (0.0008) -[2023-11-28 07:20:09,032][87426] Updated weights for policy 1, policy_version 271780 (0.0008) -[2023-11-28 07:20:09,413][87426] Updated weights for policy 1, policy_version 271790 (0.0007) -[2023-11-28 07:20:09,799][87426] Updated weights for policy 1, policy_version 271800 (0.0009) -[2023-11-28 07:20:10,987][87424] Updated weights for policy 0, policy_version 272008 (0.0011) -[2023-11-28 07:20:11,357][87424] Updated weights for policy 0, policy_version 272018 (0.0008) -[2023-11-28 07:20:11,744][87424] Updated weights for policy 0, policy_version 272028 (0.0009) -[2023-11-28 07:20:12,249][87426] Updated weights for policy 1, policy_version 271810 (0.0010) -[2023-11-28 07:20:12,629][87426] Updated weights for policy 1, policy_version 271820 (0.0010) -[2023-11-28 07:20:13,007][87426] Updated weights for policy 1, policy_version 271830 (0.0009) -[2023-11-28 07:20:13,393][87426] Updated weights for policy 1, policy_version 271840 (0.0008) -[2023-11-28 07:20:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139231232. Throughput: 0: 2732.8, 1: 2782.7. Samples: 139243012. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:20:13,445][86177] Avg episode reward: [(0, '-514.180'), (1, '-507.630')] -[2023-11-28 07:20:14,303][87424] Updated weights for policy 0, policy_version 272038 (0.0011) -[2023-11-28 07:20:14,688][87424] Updated weights for policy 0, policy_version 272048 (0.0012) -[2023-11-28 07:20:15,073][87424] Updated weights for policy 0, policy_version 272058 (0.0011) -[2023-11-28 07:20:15,264][87426] Updated weights for policy 1, policy_version 271850 (0.0011) -[2023-11-28 07:20:15,639][87426] Updated weights for policy 1, policy_version 271860 (0.0012) -[2023-11-28 07:20:16,013][87426] Updated weights for policy 1, policy_version 271870 (0.0012) -[2023-11-28 07:20:17,359][87424] Updated weights for policy 0, policy_version 272068 (0.0012) -[2023-11-28 07:20:17,748][87424] Updated weights for policy 0, policy_version 272078 (0.0012) -[2023-11-28 07:20:18,120][87424] Updated weights for policy 0, policy_version 272088 (0.0008) -[2023-11-28 07:20:18,199][87426] Updated weights for policy 1, policy_version 271880 (0.0008) -[2023-11-28 07:20:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 139255808. Throughput: 0: 2669.6, 1: 2780.2. Samples: 139266328. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:20:18,445][86177] Avg episode reward: [(0, '-520.600'), (1, '-509.020')] -[2023-11-28 07:20:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000272096_69656576.pth... -[2023-11-28 07:20:18,483][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000269568_69009408.pth -[2023-11-28 07:20:18,582][87426] Updated weights for policy 1, policy_version 271890 (0.0008) -[2023-11-28 07:20:18,956][87426] Updated weights for policy 1, policy_version 271900 (0.0008) -[2023-11-28 07:20:19,109][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000271904_69607424.pth... -[2023-11-28 07:20:19,156][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000269344_68952064.pth -[2023-11-28 07:20:20,309][87424] Updated weights for policy 0, policy_version 272098 (0.0008) -[2023-11-28 07:20:20,692][87424] Updated weights for policy 0, policy_version 272108 (0.0012) -[2023-11-28 07:20:21,074][87424] Updated weights for policy 0, policy_version 272118 (0.0012) -[2023-11-28 07:20:21,159][87426] Updated weights for policy 1, policy_version 271910 (0.0009) -[2023-11-28 07:20:21,454][87424] Updated weights for policy 0, policy_version 272128 (0.0012) -[2023-11-28 07:20:21,530][87426] Updated weights for policy 1, policy_version 271920 (0.0012) -[2023-11-28 07:20:21,926][87426] Updated weights for policy 1, policy_version 271930 (0.0011) -[2023-11-28 07:20:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 139280384. Throughput: 0: 2639.5, 1: 2782.0. Samples: 139298352. Policy #0 lag: (min: 4.0, avg: 15.9, max: 36.0) -[2023-11-28 07:20:23,445][86177] Avg episode reward: [(0, '-524.050'), (1, '-547.960')] -[2023-11-28 07:20:23,817][87424] Updated weights for policy 0, policy_version 272138 (0.0012) -[2023-11-28 07:20:23,939][87426] Updated weights for policy 1, policy_version 271940 (0.0010) -[2023-11-28 07:20:24,198][87424] Updated weights for policy 0, policy_version 272148 (0.0011) -[2023-11-28 07:20:24,321][87426] Updated weights for policy 1, policy_version 271950 (0.0008) -[2023-11-28 07:20:24,575][87424] Updated weights for policy 0, policy_version 272158 (0.0007) -[2023-11-28 07:20:24,703][87426] Updated weights for policy 1, policy_version 271960 (0.0007) -[2023-11-28 07:20:26,388][87424] Updated weights for policy 0, policy_version 272168 (0.0011) -[2023-11-28 07:20:26,765][87424] Updated weights for policy 0, policy_version 272178 (0.0012) -[2023-11-28 07:20:26,869][87426] Updated weights for policy 1, policy_version 271970 (0.0011) -[2023-11-28 07:20:27,147][87424] Updated weights for policy 0, policy_version 272188 (0.0011) -[2023-11-28 07:20:27,251][87426] Updated weights for policy 1, policy_version 271980 (0.0007) -[2023-11-28 07:20:27,633][87426] Updated weights for policy 1, policy_version 271990 (0.0007) -[2023-11-28 07:20:28,014][87426] Updated weights for policy 1, policy_version 272000 (0.0007) -[2023-11-28 07:20:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 139313152. Throughput: 0: 2658.9, 1: 2791.4. Samples: 139323376. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:20:28,445][86177] Avg episode reward: [(0, '-570.490'), (1, '-547.300')] -[2023-11-28 07:20:29,050][87424] Updated weights for policy 0, policy_version 272198 (0.0009) -[2023-11-28 07:20:29,432][87424] Updated weights for policy 0, policy_version 272208 (0.0010) -[2023-11-28 07:20:29,812][87424] Updated weights for policy 0, policy_version 272218 (0.0011) -[2023-11-28 07:20:30,481][87426] Updated weights for policy 1, policy_version 272010 (0.0011) -[2023-11-28 07:20:30,866][87426] Updated weights for policy 1, policy_version 272020 (0.0012) -[2023-11-28 07:20:31,239][87426] Updated weights for policy 1, policy_version 272030 (0.0011) -[2023-11-28 07:20:31,540][87424] Updated weights for policy 0, policy_version 272228 (0.0011) -[2023-11-28 07:20:31,922][87424] Updated weights for policy 0, policy_version 272238 (0.0011) -[2023-11-28 07:20:32,307][87424] Updated weights for policy 0, policy_version 272248 (0.0010) -[2023-11-28 07:20:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 139337728. Throughput: 0: 2691.5, 1: 2766.9. Samples: 139348132. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:20:33,445][86177] Avg episode reward: [(0, '-605.670'), (1, '-541.150')] -[2023-11-28 07:20:33,715][87426] Updated weights for policy 1, policy_version 272040 (0.0011) -[2023-11-28 07:20:34,107][87426] Updated weights for policy 1, policy_version 272050 (0.0012) -[2023-11-28 07:20:34,399][87424] Updated weights for policy 0, policy_version 272258 (0.0012) -[2023-11-28 07:20:34,479][87426] Updated weights for policy 1, policy_version 272060 (0.0011) -[2023-11-28 07:20:34,781][87424] Updated weights for policy 0, policy_version 272268 (0.0010) -[2023-11-28 07:20:35,157][87424] Updated weights for policy 0, policy_version 272278 (0.0011) -[2023-11-28 07:20:35,541][87424] Updated weights for policy 0, policy_version 272288 (0.0011) -[2023-11-28 07:20:36,718][87426] Updated weights for policy 1, policy_version 272070 (0.0010) -[2023-11-28 07:20:37,095][87426] Updated weights for policy 1, policy_version 272080 (0.0012) -[2023-11-28 07:20:37,496][87426] Updated weights for policy 1, policy_version 272090 (0.0010) -[2023-11-28 07:20:37,658][87424] Updated weights for policy 0, policy_version 272298 (0.0012) -[2023-11-28 07:20:38,045][87424] Updated weights for policy 0, policy_version 272308 (0.0012) -[2023-11-28 07:20:38,426][87424] Updated weights for policy 0, policy_version 272318 (0.0010) -[2023-11-28 07:20:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 139362304. Throughput: 0: 2699.9, 1: 2744.8. Samples: 139381312. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:20:38,445][86177] Avg episode reward: [(0, '-592.680'), (1, '-542.230')] -[2023-11-28 07:20:39,549][87426] Updated weights for policy 1, policy_version 272100 (0.0008) -[2023-11-28 07:20:39,923][87426] Updated weights for policy 1, policy_version 272110 (0.0011) -[2023-11-28 07:20:40,294][87426] Updated weights for policy 1, policy_version 272120 (0.0012) -[2023-11-28 07:20:41,006][87424] Updated weights for policy 0, policy_version 272328 (0.0011) -[2023-11-28 07:20:41,389][87424] Updated weights for policy 0, policy_version 272338 (0.0012) -[2023-11-28 07:20:41,786][87424] Updated weights for policy 0, policy_version 272348 (0.0012) -[2023-11-28 07:20:42,803][87426] Updated weights for policy 1, policy_version 272130 (0.0011) -[2023-11-28 07:20:43,181][87426] Updated weights for policy 1, policy_version 272140 (0.0010) -[2023-11-28 07:20:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 139386880. Throughput: 0: 2691.7, 1: 2727.6. Samples: 139404964. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:20:43,445][86177] Avg episode reward: [(0, '-600.260'), (1, '-502.020')] -[2023-11-28 07:20:43,561][87426] Updated weights for policy 1, policy_version 272150 (0.0012) -[2023-11-28 07:20:43,938][87426] Updated weights for policy 1, policy_version 272160 (0.0012) -[2023-11-28 07:20:44,497][87424] Updated weights for policy 0, policy_version 272358 (0.0009) -[2023-11-28 07:20:44,882][87424] Updated weights for policy 0, policy_version 272368 (0.0009) -[2023-11-28 07:20:45,260][87424] Updated weights for policy 0, policy_version 272378 (0.0012) -[2023-11-28 07:20:45,756][87426] Updated weights for policy 1, policy_version 272170 (0.0009) -[2023-11-28 07:20:46,137][87426] Updated weights for policy 1, policy_version 272180 (0.0008) -[2023-11-28 07:20:46,511][87426] Updated weights for policy 1, policy_version 272190 (0.0008) -[2023-11-28 07:20:47,775][87424] Updated weights for policy 0, policy_version 272388 (0.0010) -[2023-11-28 07:20:48,146][87424] Updated weights for policy 0, policy_version 272398 (0.0008) -[2023-11-28 07:20:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 139411456. Throughput: 0: 2708.3, 1: 2725.1. Samples: 139429004. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:20:48,445][86177] Avg episode reward: [(0, '-563.660'), (1, '-505.100')] -[2023-11-28 07:20:48,528][87424] Updated weights for policy 0, policy_version 272408 (0.0008) -[2023-11-28 07:20:48,710][87426] Updated weights for policy 1, policy_version 272200 (0.0008) -[2023-11-28 07:20:49,087][87426] Updated weights for policy 1, policy_version 272210 (0.0010) -[2023-11-28 07:20:49,474][87426] Updated weights for policy 1, policy_version 272220 (0.0009) -[2023-11-28 07:20:50,468][87424] Updated weights for policy 0, policy_version 272418 (0.0011) -[2023-11-28 07:20:50,848][87424] Updated weights for policy 0, policy_version 272428 (0.0009) -[2023-11-28 07:20:51,230][87424] Updated weights for policy 0, policy_version 272438 (0.0010) -[2023-11-28 07:20:51,605][87424] Updated weights for policy 0, policy_version 272448 (0.0012) -[2023-11-28 07:20:51,915][87426] Updated weights for policy 1, policy_version 272230 (0.0009) -[2023-11-28 07:20:52,293][87426] Updated weights for policy 1, policy_version 272240 (0.0011) -[2023-11-28 07:20:52,674][87426] Updated weights for policy 1, policy_version 272250 (0.0012) -[2023-11-28 07:20:53,445][86177] Fps is (10 sec: 5733.8, 60 sec: 5461.2, 300 sec: 5415.0). Total num frames: 139444224. Throughput: 0: 2677.1, 1: 2674.8. Samples: 139460036. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:20:53,446][86177] Avg episode reward: [(0, '-545.780'), (1, '-505.090')] -[2023-11-28 07:20:54,125][87424] Updated weights for policy 0, policy_version 272458 (0.0012) -[2023-11-28 07:20:54,510][87424] Updated weights for policy 0, policy_version 272468 (0.0011) -[2023-11-28 07:20:54,821][87426] Updated weights for policy 1, policy_version 272260 (0.0010) -[2023-11-28 07:20:54,886][87424] Updated weights for policy 0, policy_version 272478 (0.0009) -[2023-11-28 07:20:55,206][87426] Updated weights for policy 1, policy_version 272270 (0.0009) -[2023-11-28 07:20:55,590][87426] Updated weights for policy 1, policy_version 272280 (0.0007) -[2023-11-28 07:20:56,831][87424] Updated weights for policy 0, policy_version 272488 (0.0010) -[2023-11-28 07:20:57,213][87424] Updated weights for policy 0, policy_version 272498 (0.0012) -[2023-11-28 07:20:57,450][87426] Updated weights for policy 1, policy_version 272290 (0.0008) -[2023-11-28 07:20:57,588][87424] Updated weights for policy 0, policy_version 272508 (0.0010) -[2023-11-28 07:20:57,830][87426] Updated weights for policy 1, policy_version 272300 (0.0016) -[2023-11-28 07:20:58,211][87426] Updated weights for policy 1, policy_version 272310 (0.0011) -[2023-11-28 07:20:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 139468800. Throughput: 0: 2678.6, 1: 2677.4. Samples: 139484032. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:20:58,445][86177] Avg episode reward: [(0, '-549.770'), (1, '-502.790')] -[2023-11-28 07:20:58,589][87426] Updated weights for policy 1, policy_version 272320 (0.0007) -[2023-11-28 07:20:59,226][87424] Updated weights for policy 0, policy_version 272518 (0.0009) -[2023-11-28 07:20:59,609][87424] Updated weights for policy 0, policy_version 272528 (0.0011) -[2023-11-28 07:21:00,008][87424] Updated weights for policy 0, policy_version 272538 (0.0010) -[2023-11-28 07:21:01,009][87426] Updated weights for policy 1, policy_version 272330 (0.0009) -[2023-11-28 07:21:01,388][87426] Updated weights for policy 1, policy_version 272340 (0.0008) -[2023-11-28 07:21:01,771][87426] Updated weights for policy 1, policy_version 272350 (0.0008) -[2023-11-28 07:21:02,452][87424] Updated weights for policy 0, policy_version 272548 (0.0011) -[2023-11-28 07:21:02,830][87424] Updated weights for policy 0, policy_version 272558 (0.0012) -[2023-11-28 07:21:03,212][87424] Updated weights for policy 0, policy_version 272568 (0.0012) -[2023-11-28 07:21:03,444][86177] Fps is (10 sec: 4915.7, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 139493376. Throughput: 0: 2725.8, 1: 2667.2. Samples: 139509012. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:21:03,445][86177] Avg episode reward: [(0, '-543.700'), (1, '-500.070')] -[2023-11-28 07:21:04,094][87426] Updated weights for policy 1, policy_version 272360 (0.0012) -[2023-11-28 07:21:04,463][87426] Updated weights for policy 1, policy_version 272370 (0.0008) -[2023-11-28 07:21:04,844][87426] Updated weights for policy 1, policy_version 272380 (0.0010) -[2023-11-28 07:21:05,612][87424] Updated weights for policy 0, policy_version 272578 (0.0012) -[2023-11-28 07:21:06,006][87424] Updated weights for policy 0, policy_version 272588 (0.0012) -[2023-11-28 07:21:06,394][87424] Updated weights for policy 0, policy_version 272598 (0.0012) -[2023-11-28 07:21:06,776][87424] Updated weights for policy 0, policy_version 272608 (0.0012) -[2023-11-28 07:21:07,100][87426] Updated weights for policy 1, policy_version 272390 (0.0012) -[2023-11-28 07:21:07,472][87426] Updated weights for policy 1, policy_version 272400 (0.0012) -[2023-11-28 07:21:07,856][87426] Updated weights for policy 1, policy_version 272410 (0.0012) -[2023-11-28 07:21:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 139526144. Throughput: 0: 2729.2, 1: 2663.0. Samples: 139541004. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:21:08,445][86177] Avg episode reward: [(0, '-519.680'), (1, '-539.600')] -[2023-11-28 07:21:08,568][87424] Updated weights for policy 0, policy_version 272618 (0.0008) -[2023-11-28 07:21:08,946][87424] Updated weights for policy 0, policy_version 272628 (0.0009) -[2023-11-28 07:21:09,340][87424] Updated weights for policy 0, policy_version 272638 (0.0007) -[2023-11-28 07:21:10,040][87426] Updated weights for policy 1, policy_version 272420 (0.0012) -[2023-11-28 07:21:10,420][87426] Updated weights for policy 1, policy_version 272430 (0.0012) -[2023-11-28 07:21:10,799][87426] Updated weights for policy 1, policy_version 272440 (0.0012) -[2023-11-28 07:21:11,288][87424] Updated weights for policy 0, policy_version 272648 (0.0010) -[2023-11-28 07:21:11,669][87424] Updated weights for policy 0, policy_version 272658 (0.0010) -[2023-11-28 07:21:12,056][87424] Updated weights for policy 0, policy_version 272668 (0.0011) -[2023-11-28 07:21:12,843][87426] Updated weights for policy 1, policy_version 272450 (0.0010) -[2023-11-28 07:21:13,218][87426] Updated weights for policy 1, policy_version 272460 (0.0012) -[2023-11-28 07:21:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 139550720. Throughput: 0: 2747.6, 1: 2657.6. Samples: 139566612. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:21:13,445][86177] Avg episode reward: [(0, '-519.310'), (1, '-540.640')] -[2023-11-28 07:21:13,608][87426] Updated weights for policy 1, policy_version 272470 (0.0012) -[2023-11-28 07:21:13,983][87426] Updated weights for policy 1, policy_version 272480 (0.0009) -[2023-11-28 07:21:13,988][87424] Updated weights for policy 0, policy_version 272678 (0.0011) -[2023-11-28 07:21:14,361][87424] Updated weights for policy 0, policy_version 272688 (0.0011) -[2023-11-28 07:21:14,743][87424] Updated weights for policy 0, policy_version 272698 (0.0011) -[2023-11-28 07:21:16,381][87426] Updated weights for policy 1, policy_version 272490 (0.0012) -[2023-11-28 07:21:16,513][87424] Updated weights for policy 0, policy_version 272708 (0.0009) -[2023-11-28 07:21:16,751][87426] Updated weights for policy 1, policy_version 272500 (0.0011) -[2023-11-28 07:21:16,897][87424] Updated weights for policy 0, policy_version 272718 (0.0011) -[2023-11-28 07:21:17,131][87426] Updated weights for policy 1, policy_version 272510 (0.0008) -[2023-11-28 07:21:17,278][87424] Updated weights for policy 0, policy_version 272728 (0.0009) -[2023-11-28 07:21:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139583488. Throughput: 0: 2744.5, 1: 2678.6. Samples: 139592172. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:21:18,445][86177] Avg episode reward: [(0, '-512.120'), (1, '-539.130')] -[2023-11-28 07:21:19,155][87426] Updated weights for policy 1, policy_version 272520 (0.0008) -[2023-11-28 07:21:19,536][87426] Updated weights for policy 1, policy_version 272530 (0.0008) -[2023-11-28 07:21:19,568][87424] Updated weights for policy 0, policy_version 272738 (0.0009) -[2023-11-28 07:21:19,918][87426] Updated weights for policy 1, policy_version 272540 (0.0011) -[2023-11-28 07:21:19,958][87424] Updated weights for policy 0, policy_version 272748 (0.0011) -[2023-11-28 07:21:20,329][87424] Updated weights for policy 0, policy_version 272758 (0.0012) -[2023-11-28 07:21:20,708][87424] Updated weights for policy 0, policy_version 272768 (0.0012) -[2023-11-28 07:21:22,303][87426] Updated weights for policy 1, policy_version 272550 (0.0011) -[2023-11-28 07:21:22,684][87426] Updated weights for policy 1, policy_version 272560 (0.0008) -[2023-11-28 07:21:23,061][87426] Updated weights for policy 1, policy_version 272570 (0.0010) -[2023-11-28 07:21:23,125][87424] Updated weights for policy 0, policy_version 272778 (0.0010) -[2023-11-28 07:21:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 139608064. Throughput: 0: 2732.0, 1: 2686.8. Samples: 139625156. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:21:23,445][86177] Avg episode reward: [(0, '-507.890'), (1, '-498.880')] -[2023-11-28 07:21:23,496][87424] Updated weights for policy 0, policy_version 272788 (0.0009) -[2023-11-28 07:21:23,878][87424] Updated weights for policy 0, policy_version 272798 (0.0008) -[2023-11-28 07:21:25,174][87426] Updated weights for policy 1, policy_version 272580 (0.0009) -[2023-11-28 07:21:25,552][87426] Updated weights for policy 1, policy_version 272590 (0.0007) -[2023-11-28 07:21:25,932][87426] Updated weights for policy 1, policy_version 272600 (0.0007) -[2023-11-28 07:21:26,213][87424] Updated weights for policy 0, policy_version 272808 (0.0010) -[2023-11-28 07:21:26,593][87424] Updated weights for policy 0, policy_version 272818 (0.0007) -[2023-11-28 07:21:26,973][87424] Updated weights for policy 0, policy_version 272828 (0.0007) -[2023-11-28 07:21:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 139632640. Throughput: 0: 2735.1, 1: 2672.4. Samples: 139648300. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:21:28,445][86177] Avg episode reward: [(0, '-519.040'), (1, '-504.150')] -[2023-11-28 07:21:28,463][87426] Updated weights for policy 1, policy_version 272610 (0.0008) -[2023-11-28 07:21:28,837][87426] Updated weights for policy 1, policy_version 272620 (0.0007) -[2023-11-28 07:21:29,218][87426] Updated weights for policy 1, policy_version 272630 (0.0008) -[2023-11-28 07:21:29,301][87424] Updated weights for policy 0, policy_version 272838 (0.0010) -[2023-11-28 07:21:29,601][87426] Updated weights for policy 1, policy_version 272640 (0.0008) -[2023-11-28 07:21:29,681][87424] Updated weights for policy 0, policy_version 272848 (0.0007) -[2023-11-28 07:21:30,060][87424] Updated weights for policy 0, policy_version 272858 (0.0011) -[2023-11-28 07:21:31,769][87426] Updated weights for policy 1, policy_version 272650 (0.0012) -[2023-11-28 07:21:32,139][87426] Updated weights for policy 1, policy_version 272660 (0.0012) -[2023-11-28 07:21:32,235][87424] Updated weights for policy 0, policy_version 272868 (0.0011) -[2023-11-28 07:21:32,516][87426] Updated weights for policy 1, policy_version 272670 (0.0011) -[2023-11-28 07:21:32,625][87424] Updated weights for policy 0, policy_version 272878 (0.0011) -[2023-11-28 07:21:33,003][87424] Updated weights for policy 0, policy_version 272888 (0.0012) -[2023-11-28 07:21:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139665408. Throughput: 0: 2743.2, 1: 2674.2. Samples: 139672788. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:21:33,445][86177] Avg episode reward: [(0, '-518.860'), (1, '-503.930')] -[2023-11-28 07:21:34,550][87426] Updated weights for policy 1, policy_version 272680 (0.0008) -[2023-11-28 07:21:34,936][87426] Updated weights for policy 1, policy_version 272690 (0.0008) -[2023-11-28 07:21:35,256][87424] Updated weights for policy 0, policy_version 272898 (0.0011) -[2023-11-28 07:21:35,317][87426] Updated weights for policy 1, policy_version 272700 (0.0010) -[2023-11-28 07:21:35,644][87424] Updated weights for policy 0, policy_version 272908 (0.0008) -[2023-11-28 07:21:36,004][87424] Updated weights for policy 0, policy_version 272918 (0.0012) -[2023-11-28 07:21:36,386][87424] Updated weights for policy 0, policy_version 272928 (0.0012) -[2023-11-28 07:21:37,372][87426] Updated weights for policy 1, policy_version 272710 (0.0008) -[2023-11-28 07:21:37,746][87426] Updated weights for policy 1, policy_version 272720 (0.0008) -[2023-11-28 07:21:38,137][87426] Updated weights for policy 1, policy_version 272730 (0.0008) -[2023-11-28 07:21:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139689984. Throughput: 0: 2738.2, 1: 2709.9. Samples: 139705196. Policy #0 lag: (min: 31.0, avg: 51.8, max: 91.0) -[2023-11-28 07:21:38,445][86177] Avg episode reward: [(0, '-521.020'), (1, '-505.070')] -[2023-11-28 07:21:38,788][87424] Updated weights for policy 0, policy_version 272938 (0.0012) -[2023-11-28 07:21:39,167][87424] Updated weights for policy 0, policy_version 272948 (0.0012) -[2023-11-28 07:21:39,553][87424] Updated weights for policy 0, policy_version 272958 (0.0012) -[2023-11-28 07:21:40,418][87426] Updated weights for policy 1, policy_version 272740 (0.0010) -[2023-11-28 07:21:40,792][87426] Updated weights for policy 1, policy_version 272750 (0.0012) -[2023-11-28 07:21:41,161][87426] Updated weights for policy 1, policy_version 272760 (0.0012) -[2023-11-28 07:21:41,889][87424] Updated weights for policy 0, policy_version 272968 (0.0011) -[2023-11-28 07:21:42,271][87424] Updated weights for policy 0, policy_version 272978 (0.0011) -[2023-11-28 07:21:42,658][87424] Updated weights for policy 0, policy_version 272988 (0.0012) -[2023-11-28 07:21:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139714560. Throughput: 0: 2738.0, 1: 2700.3. Samples: 139728756. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:21:43,445][86177] Avg episode reward: [(0, '-522.000'), (1, '-508.140')] -[2023-11-28 07:21:43,466][87426] Updated weights for policy 1, policy_version 272770 (0.0011) -[2023-11-28 07:21:43,845][87426] Updated weights for policy 1, policy_version 272780 (0.0011) -[2023-11-28 07:21:44,234][87426] Updated weights for policy 1, policy_version 272790 (0.0009) -[2023-11-28 07:21:44,615][87426] Updated weights for policy 1, policy_version 272800 (0.0010) -[2023-11-28 07:21:44,817][87424] Updated weights for policy 0, policy_version 272998 (0.0012) -[2023-11-28 07:21:45,209][87424] Updated weights for policy 0, policy_version 273008 (0.0011) -[2023-11-28 07:21:45,593][87424] Updated weights for policy 0, policy_version 273018 (0.0009) -[2023-11-28 07:21:47,061][87426] Updated weights for policy 1, policy_version 272810 (0.0009) -[2023-11-28 07:21:47,431][87426] Updated weights for policy 1, policy_version 272820 (0.0011) -[2023-11-28 07:21:47,745][87424] Updated weights for policy 0, policy_version 273028 (0.0011) -[2023-11-28 07:21:47,811][87426] Updated weights for policy 1, policy_version 272830 (0.0008) -[2023-11-28 07:21:48,126][87424] Updated weights for policy 0, policy_version 273038 (0.0011) -[2023-11-28 07:21:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 139739136. Throughput: 0: 2725.3, 1: 2688.2. Samples: 139752620. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:21:48,445][86177] Avg episode reward: [(0, '-516.820'), (1, '-506.210')] -[2023-11-28 07:21:48,495][87424] Updated weights for policy 0, policy_version 273048 (0.0008) -[2023-11-28 07:21:50,107][87426] Updated weights for policy 1, policy_version 272840 (0.0011) -[2023-11-28 07:21:50,482][87426] Updated weights for policy 1, policy_version 272850 (0.0011) -[2023-11-28 07:21:50,502][87424] Updated weights for policy 0, policy_version 273058 (0.0008) -[2023-11-28 07:21:50,859][87426] Updated weights for policy 1, policy_version 272860 (0.0011) -[2023-11-28 07:21:50,881][87424] Updated weights for policy 0, policy_version 273068 (0.0007) -[2023-11-28 07:21:51,261][87424] Updated weights for policy 0, policy_version 273078 (0.0010) -[2023-11-28 07:21:51,644][87424] Updated weights for policy 0, policy_version 273088 (0.0012) -[2023-11-28 07:21:52,943][87426] Updated weights for policy 1, policy_version 272870 (0.0012) -[2023-11-28 07:21:53,317][87426] Updated weights for policy 1, policy_version 272880 (0.0012) -[2023-11-28 07:21:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.9, 300 sec: 5387.3). Total num frames: 139763712. Throughput: 0: 2731.5, 1: 2684.4. Samples: 139784724. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:21:53,445][86177] Avg episode reward: [(0, '-525.510'), (1, '-512.350')] -[2023-11-28 07:21:53,691][87426] Updated weights for policy 1, policy_version 272890 (0.0012) -[2023-11-28 07:21:54,232][87424] Updated weights for policy 0, policy_version 273098 (0.0008) -[2023-11-28 07:21:54,626][87424] Updated weights for policy 0, policy_version 273108 (0.0010) -[2023-11-28 07:21:54,998][87424] Updated weights for policy 0, policy_version 273118 (0.0012) -[2023-11-28 07:21:55,841][87426] Updated weights for policy 1, policy_version 272900 (0.0010) -[2023-11-28 07:21:56,218][87426] Updated weights for policy 1, policy_version 272910 (0.0007) -[2023-11-28 07:21:56,604][87426] Updated weights for policy 1, policy_version 272920 (0.0010) -[2023-11-28 07:21:56,727][87424] Updated weights for policy 0, policy_version 273128 (0.0012) -[2023-11-28 07:21:57,108][87424] Updated weights for policy 0, policy_version 273138 (0.0012) -[2023-11-28 07:21:57,486][87424] Updated weights for policy 0, policy_version 273148 (0.0012) -[2023-11-28 07:21:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139796480. Throughput: 0: 2715.2, 1: 2696.2. Samples: 139810124. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:21:58,445][86177] Avg episode reward: [(0, '-535.620'), (1, '-513.500')] -[2023-11-28 07:21:58,820][87426] Updated weights for policy 1, policy_version 272930 (0.0010) -[2023-11-28 07:21:59,192][87426] Updated weights for policy 1, policy_version 272940 (0.0011) -[2023-11-28 07:21:59,236][87424] Updated weights for policy 0, policy_version 273158 (0.0012) -[2023-11-28 07:21:59,566][87426] Updated weights for policy 1, policy_version 272950 (0.0010) -[2023-11-28 07:21:59,620][87424] Updated weights for policy 0, policy_version 273168 (0.0011) -[2023-11-28 07:21:59,946][87426] Updated weights for policy 1, policy_version 272960 (0.0010) -[2023-11-28 07:22:00,009][87424] Updated weights for policy 0, policy_version 273178 (0.0010) -[2023-11-28 07:22:02,154][87424] Updated weights for policy 0, policy_version 273188 (0.0009) -[2023-11-28 07:22:02,252][87426] Updated weights for policy 1, policy_version 272970 (0.0011) -[2023-11-28 07:22:02,533][87424] Updated weights for policy 0, policy_version 273198 (0.0012) -[2023-11-28 07:22:02,638][87426] Updated weights for policy 1, policy_version 272980 (0.0007) -[2023-11-28 07:22:02,915][87424] Updated weights for policy 0, policy_version 273208 (0.0010) -[2023-11-28 07:22:03,011][87426] Updated weights for policy 1, policy_version 272990 (0.0010) -[2023-11-28 07:22:03,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 139829248. Throughput: 0: 2712.9, 1: 2696.9. Samples: 139835612. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:03,445][86177] Avg episode reward: [(0, '-534.120'), (1, '-518.030')] -[2023-11-28 07:22:05,161][87426] Updated weights for policy 1, policy_version 273000 (0.0011) -[2023-11-28 07:22:05,234][87424] Updated weights for policy 0, policy_version 273218 (0.0008) -[2023-11-28 07:22:05,537][87426] Updated weights for policy 1, policy_version 273010 (0.0011) -[2023-11-28 07:22:05,616][87424] Updated weights for policy 0, policy_version 273228 (0.0012) -[2023-11-28 07:22:05,917][87426] Updated weights for policy 1, policy_version 273020 (0.0007) -[2023-11-28 07:22:05,999][87424] Updated weights for policy 0, policy_version 273238 (0.0011) -[2023-11-28 07:22:06,371][87424] Updated weights for policy 0, policy_version 273248 (0.0011) -[2023-11-28 07:22:08,224][87426] Updated weights for policy 1, policy_version 273030 (0.0010) -[2023-11-28 07:22:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 139845632. Throughput: 0: 2702.9, 1: 2694.1. Samples: 139868024. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:08,445][86177] Avg episode reward: [(0, '-536.540'), (1, '-516.820')] -[2023-11-28 07:22:08,602][87426] Updated weights for policy 1, policy_version 273040 (0.0007) -[2023-11-28 07:22:08,963][87424] Updated weights for policy 0, policy_version 273258 (0.0008) -[2023-11-28 07:22:08,987][87426] Updated weights for policy 1, policy_version 273050 (0.0009) -[2023-11-28 07:22:09,346][87424] Updated weights for policy 0, policy_version 273268 (0.0008) -[2023-11-28 07:22:09,727][87424] Updated weights for policy 0, policy_version 273278 (0.0007) -[2023-11-28 07:22:11,117][87426] Updated weights for policy 1, policy_version 273060 (0.0011) -[2023-11-28 07:22:11,496][87426] Updated weights for policy 1, policy_version 273070 (0.0012) -[2023-11-28 07:22:11,872][87426] Updated weights for policy 1, policy_version 273080 (0.0012) -[2023-11-28 07:22:11,977][87424] Updated weights for policy 0, policy_version 273288 (0.0010) -[2023-11-28 07:22:12,356][87424] Updated weights for policy 0, policy_version 273298 (0.0011) -[2023-11-28 07:22:12,737][87424] Updated weights for policy 0, policy_version 273308 (0.0011) -[2023-11-28 07:22:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139878400. Throughput: 0: 2697.8, 1: 2718.4. Samples: 139892028. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:13,445][86177] Avg episode reward: [(0, '-530.920'), (1, '-513.460')] -[2023-11-28 07:22:13,795][87426] Updated weights for policy 1, policy_version 273090 (0.0011) -[2023-11-28 07:22:14,181][87426] Updated weights for policy 1, policy_version 273100 (0.0010) -[2023-11-28 07:22:14,527][87424] Updated weights for policy 0, policy_version 273318 (0.0010) -[2023-11-28 07:22:14,557][87426] Updated weights for policy 1, policy_version 273110 (0.0011) -[2023-11-28 07:22:14,891][87424] Updated weights for policy 0, policy_version 273328 (0.0007) -[2023-11-28 07:22:14,923][87426] Updated weights for policy 1, policy_version 273120 (0.0012) -[2023-11-28 07:22:15,275][87424] Updated weights for policy 0, policy_version 273338 (0.0007) -[2023-11-28 07:22:16,850][87426] Updated weights for policy 1, policy_version 273130 (0.0012) -[2023-11-28 07:22:17,222][87426] Updated weights for policy 1, policy_version 273140 (0.0012) -[2023-11-28 07:22:17,604][87426] Updated weights for policy 1, policy_version 273150 (0.0012) -[2023-11-28 07:22:17,811][87424] Updated weights for policy 0, policy_version 273348 (0.0011) -[2023-11-28 07:22:18,197][87424] Updated weights for policy 0, policy_version 273358 (0.0010) -[2023-11-28 07:22:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 139902976. Throughput: 0: 2697.0, 1: 2714.4. Samples: 139916300. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:18,445][86177] Avg episode reward: [(0, '-517.590'), (1, '-516.010')] -[2023-11-28 07:22:18,452][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000273152_69926912.pth... -[2023-11-28 07:22:18,496][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000270592_69271552.pth -[2023-11-28 07:22:18,588][87424] Updated weights for policy 0, policy_version 273368 (0.0011) -[2023-11-28 07:22:18,892][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000273376_69984256.pth... -[2023-11-28 07:22:18,923][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000270816_69328896.pth -[2023-11-28 07:22:19,690][87426] Updated weights for policy 1, policy_version 273160 (0.0011) -[2023-11-28 07:22:20,063][87426] Updated weights for policy 1, policy_version 273170 (0.0012) -[2023-11-28 07:22:20,442][87426] Updated weights for policy 1, policy_version 273180 (0.0012) -[2023-11-28 07:22:20,924][87424] Updated weights for policy 0, policy_version 273378 (0.0009) -[2023-11-28 07:22:21,313][87424] Updated weights for policy 0, policy_version 273388 (0.0011) -[2023-11-28 07:22:21,706][87424] Updated weights for policy 0, policy_version 273398 (0.0010) -[2023-11-28 07:22:22,078][87424] Updated weights for policy 0, policy_version 273408 (0.0012) -[2023-11-28 07:22:22,920][87426] Updated weights for policy 1, policy_version 273190 (0.0011) -[2023-11-28 07:22:23,286][87426] Updated weights for policy 1, policy_version 273200 (0.0010) -[2023-11-28 07:22:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 139927552. Throughput: 0: 2705.2, 1: 2684.5. Samples: 139947736. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:23,445][86177] Avg episode reward: [(0, '-514.340'), (1, '-517.800')] -[2023-11-28 07:22:23,661][87426] Updated weights for policy 1, policy_version 273210 (0.0012) -[2023-11-28 07:22:24,462][87424] Updated weights for policy 0, policy_version 273418 (0.0011) -[2023-11-28 07:22:24,839][87424] Updated weights for policy 0, policy_version 273428 (0.0008) -[2023-11-28 07:22:25,224][87424] Updated weights for policy 0, policy_version 273438 (0.0008) -[2023-11-28 07:22:25,450][87426] Updated weights for policy 1, policy_version 273220 (0.0012) -[2023-11-28 07:22:25,817][87426] Updated weights for policy 1, policy_version 273230 (0.0012) -[2023-11-28 07:22:26,196][87426] Updated weights for policy 1, policy_version 273240 (0.0010) -[2023-11-28 07:22:27,062][87424] Updated weights for policy 0, policy_version 273448 (0.0008) -[2023-11-28 07:22:27,444][87424] Updated weights for policy 0, policy_version 273458 (0.0007) -[2023-11-28 07:22:27,827][87424] Updated weights for policy 0, policy_version 273468 (0.0008) -[2023-11-28 07:22:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 139960320. Throughput: 0: 2705.5, 1: 2703.3. Samples: 139972152. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:28,445][86177] Avg episode reward: [(0, '-508.710'), (1, '-524.210')] -[2023-11-28 07:22:28,696][87426] Updated weights for policy 1, policy_version 273250 (0.0009) -[2023-11-28 07:22:29,072][87426] Updated weights for policy 1, policy_version 273260 (0.0011) -[2023-11-28 07:22:29,456][87426] Updated weights for policy 1, policy_version 273270 (0.0011) -[2023-11-28 07:22:29,828][87426] Updated weights for policy 1, policy_version 273280 (0.0010) -[2023-11-28 07:22:30,293][87424] Updated weights for policy 0, policy_version 273478 (0.0009) -[2023-11-28 07:22:30,672][87424] Updated weights for policy 0, policy_version 273488 (0.0009) -[2023-11-28 07:22:31,059][87424] Updated weights for policy 0, policy_version 273498 (0.0008) -[2023-11-28 07:22:32,263][87426] Updated weights for policy 1, policy_version 273290 (0.0011) -[2023-11-28 07:22:32,642][87426] Updated weights for policy 1, policy_version 273300 (0.0009) -[2023-11-28 07:22:33,029][87426] Updated weights for policy 1, policy_version 273310 (0.0008) -[2023-11-28 07:22:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 139984896. Throughput: 0: 2702.0, 1: 2714.8. Samples: 139996372. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:33,445][86177] Avg episode reward: [(0, '-506.550'), (1, '-522.940')] -[2023-11-28 07:22:33,463][87424] Updated weights for policy 0, policy_version 273508 (0.0009) -[2023-11-28 07:22:33,847][87424] Updated weights for policy 0, policy_version 273518 (0.0010) -[2023-11-28 07:22:34,227][87424] Updated weights for policy 0, policy_version 273528 (0.0007) -[2023-11-28 07:22:34,654][87426] Updated weights for policy 1, policy_version 273320 (0.0010) -[2023-11-28 07:22:35,034][87426] Updated weights for policy 1, policy_version 273330 (0.0010) -[2023-11-28 07:22:35,412][87426] Updated weights for policy 1, policy_version 273340 (0.0007) -[2023-11-28 07:22:36,633][87424] Updated weights for policy 0, policy_version 273538 (0.0010) -[2023-11-28 07:22:37,008][87424] Updated weights for policy 0, policy_version 273548 (0.0011) -[2023-11-28 07:22:37,384][87424] Updated weights for policy 0, policy_version 273558 (0.0011) -[2023-11-28 07:22:37,466][87426] Updated weights for policy 1, policy_version 273350 (0.0010) -[2023-11-28 07:22:37,763][87424] Updated weights for policy 0, policy_version 273568 (0.0007) -[2023-11-28 07:22:37,839][87426] Updated weights for policy 1, policy_version 273360 (0.0011) -[2023-11-28 07:22:38,228][87426] Updated weights for policy 1, policy_version 273370 (0.0012) -[2023-11-28 07:22:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 140009472. Throughput: 0: 2687.6, 1: 2727.0. Samples: 140028376. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:38,445][86177] Avg episode reward: [(0, '-511.150'), (1, '-519.330')] -[2023-11-28 07:22:39,976][87424] Updated weights for policy 0, policy_version 273578 (0.0012) -[2023-11-28 07:22:40,343][87424] Updated weights for policy 0, policy_version 273588 (0.0012) -[2023-11-28 07:22:40,367][87426] Updated weights for policy 1, policy_version 273380 (0.0011) -[2023-11-28 07:22:40,724][87424] Updated weights for policy 0, policy_version 273598 (0.0012) -[2023-11-28 07:22:40,744][87426] Updated weights for policy 1, policy_version 273390 (0.0011) -[2023-11-28 07:22:41,116][87426] Updated weights for policy 1, policy_version 273400 (0.0012) -[2023-11-28 07:22:42,820][87424] Updated weights for policy 0, policy_version 273608 (0.0008) -[2023-11-28 07:22:43,202][87424] Updated weights for policy 0, policy_version 273618 (0.0008) -[2023-11-28 07:22:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 140034048. Throughput: 0: 2668.5, 1: 2709.8. Samples: 140052148. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:43,445][86177] Avg episode reward: [(0, '-514.080'), (1, '-520.070')] -[2023-11-28 07:22:43,540][87426] Updated weights for policy 1, policy_version 273410 (0.0011) -[2023-11-28 07:22:43,576][87424] Updated weights for policy 0, policy_version 273628 (0.0007) -[2023-11-28 07:22:43,924][87426] Updated weights for policy 1, policy_version 273420 (0.0007) -[2023-11-28 07:22:44,303][87426] Updated weights for policy 1, policy_version 273430 (0.0009) -[2023-11-28 07:22:44,679][87426] Updated weights for policy 1, policy_version 273440 (0.0008) -[2023-11-28 07:22:45,591][87424] Updated weights for policy 0, policy_version 273638 (0.0008) -[2023-11-28 07:22:45,982][87424] Updated weights for policy 0, policy_version 273648 (0.0011) -[2023-11-28 07:22:46,367][87424] Updated weights for policy 0, policy_version 273658 (0.0011) -[2023-11-28 07:22:47,184][87426] Updated weights for policy 1, policy_version 273450 (0.0012) -[2023-11-28 07:22:47,560][87426] Updated weights for policy 1, policy_version 273460 (0.0011) -[2023-11-28 07:22:47,938][87426] Updated weights for policy 1, policy_version 273470 (0.0008) -[2023-11-28 07:22:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 140066816. Throughput: 0: 2654.5, 1: 2689.6. Samples: 140076096. Policy #0 lag: (min: 31.0, avg: 38.9, max: 63.0) -[2023-11-28 07:22:48,445][86177] Avg episode reward: [(0, '-516.080'), (1, '-517.290')] -[2023-11-28 07:22:48,630][87424] Updated weights for policy 0, policy_version 273668 (0.0008) -[2023-11-28 07:22:49,013][87424] Updated weights for policy 0, policy_version 273678 (0.0011) -[2023-11-28 07:22:49,396][87424] Updated weights for policy 0, policy_version 273688 (0.0011) -[2023-11-28 07:22:50,261][87426] Updated weights for policy 1, policy_version 273480 (0.0010) -[2023-11-28 07:22:50,636][87426] Updated weights for policy 1, policy_version 273490 (0.0011) -[2023-11-28 07:22:51,004][87426] Updated weights for policy 1, policy_version 273500 (0.0012) -[2023-11-28 07:22:51,780][87424] Updated weights for policy 0, policy_version 273698 (0.0011) -[2023-11-28 07:22:52,165][87424] Updated weights for policy 0, policy_version 273708 (0.0009) -[2023-11-28 07:22:52,546][87424] Updated weights for policy 0, policy_version 273718 (0.0010) -[2023-11-28 07:22:52,928][87424] Updated weights for policy 0, policy_version 273728 (0.0011) -[2023-11-28 07:22:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 140091392. Throughput: 0: 2660.7, 1: 2672.4. Samples: 140108016. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:22:53,445][86177] Avg episode reward: [(0, '-514.630'), (1, '-522.310')] -[2023-11-28 07:22:53,579][87426] Updated weights for policy 1, policy_version 273510 (0.0011) -[2023-11-28 07:22:53,956][87426] Updated weights for policy 1, policy_version 273520 (0.0012) -[2023-11-28 07:22:54,336][87426] Updated weights for policy 1, policy_version 273530 (0.0009) -[2023-11-28 07:22:54,957][87424] Updated weights for policy 0, policy_version 273738 (0.0008) -[2023-11-28 07:22:55,335][87424] Updated weights for policy 0, policy_version 273748 (0.0008) -[2023-11-28 07:22:55,716][87424] Updated weights for policy 0, policy_version 273758 (0.0007) -[2023-11-28 07:22:56,477][87426] Updated weights for policy 1, policy_version 273540 (0.0009) -[2023-11-28 07:22:56,854][87426] Updated weights for policy 1, policy_version 273550 (0.0011) -[2023-11-28 07:22:57,236][87426] Updated weights for policy 1, policy_version 273560 (0.0012) -[2023-11-28 07:22:57,712][87424] Updated weights for policy 0, policy_version 273768 (0.0011) -[2023-11-28 07:22:58,092][87424] Updated weights for policy 0, policy_version 273778 (0.0012) -[2023-11-28 07:22:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 140115968. Throughput: 0: 2680.3, 1: 2666.1. Samples: 140132616. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:22:58,445][86177] Avg episode reward: [(0, '-513.830'), (1, '-521.210')] -[2023-11-28 07:22:58,483][87424] Updated weights for policy 0, policy_version 273788 (0.0009) -[2023-11-28 07:22:59,578][87426] Updated weights for policy 1, policy_version 273570 (0.0009) -[2023-11-28 07:22:59,961][87426] Updated weights for policy 1, policy_version 273580 (0.0012) -[2023-11-28 07:23:00,342][87426] Updated weights for policy 1, policy_version 273590 (0.0012) -[2023-11-28 07:23:00,716][87426] Updated weights for policy 1, policy_version 273600 (0.0011) -[2023-11-28 07:23:00,941][87424] Updated weights for policy 0, policy_version 273798 (0.0010) -[2023-11-28 07:23:01,334][87424] Updated weights for policy 0, policy_version 273808 (0.0008) -[2023-11-28 07:23:01,715][87424] Updated weights for policy 0, policy_version 273818 (0.0009) -[2023-11-28 07:23:02,804][87426] Updated weights for policy 1, policy_version 273610 (0.0012) -[2023-11-28 07:23:03,185][87426] Updated weights for policy 1, policy_version 273620 (0.0011) -[2023-11-28 07:23:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 140140544. Throughput: 0: 2684.8, 1: 2681.9. Samples: 140157800. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:03,445][86177] Avg episode reward: [(0, '-521.590'), (1, '-517.480')] -[2023-11-28 07:23:03,544][87424] Updated weights for policy 0, policy_version 273828 (0.0011) -[2023-11-28 07:23:03,555][87426] Updated weights for policy 1, policy_version 273630 (0.0009) -[2023-11-28 07:23:03,923][87424] Updated weights for policy 0, policy_version 273838 (0.0009) -[2023-11-28 07:23:04,307][87424] Updated weights for policy 0, policy_version 273848 (0.0008) -[2023-11-28 07:23:05,512][87426] Updated weights for policy 1, policy_version 273640 (0.0011) -[2023-11-28 07:23:05,897][87426] Updated weights for policy 1, policy_version 273650 (0.0011) -[2023-11-28 07:23:06,285][87426] Updated weights for policy 1, policy_version 273660 (0.0007) -[2023-11-28 07:23:06,586][87424] Updated weights for policy 0, policy_version 273858 (0.0009) -[2023-11-28 07:23:06,971][87424] Updated weights for policy 0, policy_version 273868 (0.0011) -[2023-11-28 07:23:07,360][87424] Updated weights for policy 0, policy_version 273878 (0.0008) -[2023-11-28 07:23:07,746][87424] Updated weights for policy 0, policy_version 273888 (0.0007) -[2023-11-28 07:23:08,229][87426] Updated weights for policy 1, policy_version 273670 (0.0009) -[2023-11-28 07:23:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 140173312. Throughput: 0: 2709.3, 1: 2709.9. Samples: 140191596. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:08,445][86177] Avg episode reward: [(0, '-523.480'), (1, '-537.490')] -[2023-11-28 07:23:08,610][87426] Updated weights for policy 1, policy_version 273680 (0.0008) -[2023-11-28 07:23:09,007][87426] Updated weights for policy 1, policy_version 273690 (0.0007) -[2023-11-28 07:23:09,920][87424] Updated weights for policy 0, policy_version 273898 (0.0012) -[2023-11-28 07:23:10,297][87424] Updated weights for policy 0, policy_version 273908 (0.0012) -[2023-11-28 07:23:10,694][87424] Updated weights for policy 0, policy_version 273918 (0.0013) -[2023-11-28 07:23:11,227][87426] Updated weights for policy 1, policy_version 273700 (0.0008) -[2023-11-28 07:23:11,612][87426] Updated weights for policy 1, policy_version 273710 (0.0008) -[2023-11-28 07:23:11,978][87426] Updated weights for policy 1, policy_version 273720 (0.0011) -[2023-11-28 07:23:12,857][87424] Updated weights for policy 0, policy_version 273928 (0.0011) -[2023-11-28 07:23:13,248][87424] Updated weights for policy 0, policy_version 273938 (0.0011) -[2023-11-28 07:23:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 140197888. Throughput: 0: 2713.0, 1: 2697.6. Samples: 140215628. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:13,445][86177] Avg episode reward: [(0, '-526.930'), (1, '-538.680')] -[2023-11-28 07:23:13,622][87424] Updated weights for policy 0, policy_version 273948 (0.0012) -[2023-11-28 07:23:13,997][87426] Updated weights for policy 1, policy_version 273730 (0.0010) -[2023-11-28 07:23:14,369][87426] Updated weights for policy 1, policy_version 273740 (0.0012) -[2023-11-28 07:23:14,747][87426] Updated weights for policy 1, policy_version 273750 (0.0008) -[2023-11-28 07:23:15,133][87426] Updated weights for policy 1, policy_version 273760 (0.0010) -[2023-11-28 07:23:15,593][87424] Updated weights for policy 0, policy_version 273958 (0.0008) -[2023-11-28 07:23:15,980][87424] Updated weights for policy 0, policy_version 273968 (0.0010) -[2023-11-28 07:23:16,357][87424] Updated weights for policy 0, policy_version 273978 (0.0012) -[2023-11-28 07:23:17,610][87426] Updated weights for policy 1, policy_version 273770 (0.0007) -[2023-11-28 07:23:18,000][87426] Updated weights for policy 1, policy_version 273780 (0.0008) -[2023-11-28 07:23:18,377][87426] Updated weights for policy 1, policy_version 273790 (0.0012) -[2023-11-28 07:23:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 140222464. Throughput: 0: 2711.9, 1: 2709.3. Samples: 140240328. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:18,445][86177] Avg episode reward: [(0, '-521.860'), (1, '-543.570')] -[2023-11-28 07:23:18,682][87424] Updated weights for policy 0, policy_version 273988 (0.0010) -[2023-11-28 07:23:19,066][87424] Updated weights for policy 0, policy_version 273998 (0.0009) -[2023-11-28 07:23:19,437][87424] Updated weights for policy 0, policy_version 274008 (0.0011) -[2023-11-28 07:23:20,586][87426] Updated weights for policy 1, policy_version 273800 (0.0012) -[2023-11-28 07:23:20,968][87426] Updated weights for policy 1, policy_version 273810 (0.0012) -[2023-11-28 07:23:21,274][87424] Updated weights for policy 0, policy_version 274018 (0.0012) -[2023-11-28 07:23:21,346][87426] Updated weights for policy 1, policy_version 273820 (0.0011) -[2023-11-28 07:23:21,651][87424] Updated weights for policy 0, policy_version 274028 (0.0009) -[2023-11-28 07:23:22,029][87424] Updated weights for policy 0, policy_version 274038 (0.0010) -[2023-11-28 07:23:22,410][87424] Updated weights for policy 0, policy_version 274048 (0.0010) -[2023-11-28 07:23:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 140255232. Throughput: 0: 2715.5, 1: 2694.0. Samples: 140271804. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:23,445][86177] Avg episode reward: [(0, '-522.610'), (1, '-557.310')] -[2023-11-28 07:23:23,738][87426] Updated weights for policy 1, policy_version 273830 (0.0008) -[2023-11-28 07:23:24,121][87426] Updated weights for policy 1, policy_version 273840 (0.0009) -[2023-11-28 07:23:24,501][87426] Updated weights for policy 1, policy_version 273850 (0.0008) -[2023-11-28 07:23:24,513][87424] Updated weights for policy 0, policy_version 274058 (0.0008) -[2023-11-28 07:23:24,898][87424] Updated weights for policy 0, policy_version 274068 (0.0008) -[2023-11-28 07:23:25,276][87424] Updated weights for policy 0, policy_version 274078 (0.0008) -[2023-11-28 07:23:26,244][87426] Updated weights for policy 1, policy_version 273860 (0.0010) -[2023-11-28 07:23:26,624][87426] Updated weights for policy 1, policy_version 273870 (0.0009) -[2023-11-28 07:23:27,009][87426] Updated weights for policy 1, policy_version 273880 (0.0007) -[2023-11-28 07:23:27,511][87424] Updated weights for policy 0, policy_version 274088 (0.0008) -[2023-11-28 07:23:27,897][87424] Updated weights for policy 0, policy_version 274098 (0.0007) -[2023-11-28 07:23:28,280][87424] Updated weights for policy 0, policy_version 274108 (0.0007) -[2023-11-28 07:23:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 140288000. Throughput: 0: 2732.0, 1: 2715.4. Samples: 140297280. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:28,445][86177] Avg episode reward: [(0, '-522.160'), (1, '-538.960')] -[2023-11-28 07:23:29,322][87426] Updated weights for policy 1, policy_version 273890 (0.0008) -[2023-11-28 07:23:29,703][87426] Updated weights for policy 1, policy_version 273900 (0.0010) -[2023-11-28 07:23:30,080][87426] Updated weights for policy 1, policy_version 273910 (0.0009) -[2023-11-28 07:23:30,456][87426] Updated weights for policy 1, policy_version 273920 (0.0009) -[2023-11-28 07:23:30,729][87424] Updated weights for policy 0, policy_version 274118 (0.0010) -[2023-11-28 07:23:31,113][87424] Updated weights for policy 0, policy_version 274128 (0.0009) -[2023-11-28 07:23:31,493][87424] Updated weights for policy 0, policy_version 274138 (0.0007) -[2023-11-28 07:23:32,833][87426] Updated weights for policy 1, policy_version 273930 (0.0011) -[2023-11-28 07:23:33,218][87426] Updated weights for policy 1, policy_version 273940 (0.0007) -[2023-11-28 07:23:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 140304384. Throughput: 0: 2724.1, 1: 2732.5. Samples: 140321644. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:33,445][86177] Avg episode reward: [(0, '-519.940'), (1, '-541.730')] -[2023-11-28 07:23:33,516][87424] Updated weights for policy 0, policy_version 274148 (0.0010) -[2023-11-28 07:23:33,592][87426] Updated weights for policy 1, policy_version 273950 (0.0007) -[2023-11-28 07:23:33,901][87424] Updated weights for policy 0, policy_version 274158 (0.0007) -[2023-11-28 07:23:34,286][87424] Updated weights for policy 0, policy_version 274168 (0.0007) -[2023-11-28 07:23:35,667][87426] Updated weights for policy 1, policy_version 273960 (0.0011) -[2023-11-28 07:23:36,045][87426] Updated weights for policy 1, policy_version 273970 (0.0012) -[2023-11-28 07:23:36,319][87424] Updated weights for policy 0, policy_version 274178 (0.0008) -[2023-11-28 07:23:36,415][87426] Updated weights for policy 1, policy_version 273980 (0.0012) -[2023-11-28 07:23:36,718][87424] Updated weights for policy 0, policy_version 274188 (0.0010) -[2023-11-28 07:23:37,103][87424] Updated weights for policy 0, policy_version 274198 (0.0011) -[2023-11-28 07:23:37,475][87424] Updated weights for policy 0, policy_version 274208 (0.0011) -[2023-11-28 07:23:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 140337152. Throughput: 0: 2719.5, 1: 2751.4. Samples: 140354204. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:38,445][86177] Avg episode reward: [(0, '-518.870'), (1, '-541.780')] -[2023-11-28 07:23:38,447][87426] Updated weights for policy 1, policy_version 273990 (0.0012) -[2023-11-28 07:23:38,827][87426] Updated weights for policy 1, policy_version 274000 (0.0011) -[2023-11-28 07:23:39,209][87426] Updated weights for policy 1, policy_version 274010 (0.0008) -[2023-11-28 07:23:39,987][87424] Updated weights for policy 0, policy_version 274218 (0.0010) -[2023-11-28 07:23:40,366][87424] Updated weights for policy 0, policy_version 274228 (0.0007) -[2023-11-28 07:23:40,747][87424] Updated weights for policy 0, policy_version 274238 (0.0009) -[2023-11-28 07:23:41,764][87426] Updated weights for policy 1, policy_version 274020 (0.0010) -[2023-11-28 07:23:42,147][87426] Updated weights for policy 1, policy_version 274030 (0.0012) -[2023-11-28 07:23:42,519][87426] Updated weights for policy 1, policy_version 274040 (0.0012) -[2023-11-28 07:23:43,300][87424] Updated weights for policy 0, policy_version 274248 (0.0011) -[2023-11-28 07:23:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 140361728. Throughput: 0: 2708.1, 1: 2746.7. Samples: 140378080. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:43,446][86177] Avg episode reward: [(0, '-519.420'), (1, '-528.890')] -[2023-11-28 07:23:43,693][87424] Updated weights for policy 0, policy_version 274258 (0.0012) -[2023-11-28 07:23:44,066][87424] Updated weights for policy 0, policy_version 274268 (0.0012) -[2023-11-28 07:23:44,759][87426] Updated weights for policy 1, policy_version 274050 (0.0012) -[2023-11-28 07:23:45,130][87426] Updated weights for policy 1, policy_version 274060 (0.0012) -[2023-11-28 07:23:45,511][87426] Updated weights for policy 1, policy_version 274070 (0.0011) -[2023-11-28 07:23:45,883][87426] Updated weights for policy 1, policy_version 274080 (0.0011) -[2023-11-28 07:23:46,308][87424] Updated weights for policy 0, policy_version 274278 (0.0012) -[2023-11-28 07:23:46,699][87424] Updated weights for policy 0, policy_version 274288 (0.0012) -[2023-11-28 07:23:47,071][87424] Updated weights for policy 0, policy_version 274298 (0.0012) -[2023-11-28 07:23:47,842][87426] Updated weights for policy 1, policy_version 274090 (0.0012) -[2023-11-28 07:23:48,224][87426] Updated weights for policy 1, policy_version 274100 (0.0011) -[2023-11-28 07:23:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 140386304. Throughput: 0: 2698.3, 1: 2739.3. Samples: 140402492. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:48,445][86177] Avg episode reward: [(0, '-517.070'), (1, '-533.620')] -[2023-11-28 07:23:48,600][87426] Updated weights for policy 1, policy_version 274110 (0.0012) -[2023-11-28 07:23:49,343][87424] Updated weights for policy 0, policy_version 274308 (0.0010) -[2023-11-28 07:23:49,734][87424] Updated weights for policy 0, policy_version 274318 (0.0007) -[2023-11-28 07:23:50,120][87424] Updated weights for policy 0, policy_version 274328 (0.0009) -[2023-11-28 07:23:50,759][87426] Updated weights for policy 1, policy_version 274120 (0.0012) -[2023-11-28 07:23:51,131][87426] Updated weights for policy 1, policy_version 274130 (0.0011) -[2023-11-28 07:23:51,511][87426] Updated weights for policy 1, policy_version 274140 (0.0011) -[2023-11-28 07:23:52,009][87424] Updated weights for policy 0, policy_version 274338 (0.0010) -[2023-11-28 07:23:52,400][87424] Updated weights for policy 0, policy_version 274348 (0.0010) -[2023-11-28 07:23:52,781][87424] Updated weights for policy 0, policy_version 274358 (0.0008) -[2023-11-28 07:23:53,163][87424] Updated weights for policy 0, policy_version 274368 (0.0010) -[2023-11-28 07:23:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 140419072. Throughput: 0: 2699.3, 1: 2740.2. Samples: 140436372. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:53,445][86177] Avg episode reward: [(0, '-530.210'), (1, '-539.110')] -[2023-11-28 07:23:53,485][87426] Updated weights for policy 1, policy_version 274150 (0.0011) -[2023-11-28 07:23:53,865][87426] Updated weights for policy 1, policy_version 274160 (0.0009) -[2023-11-28 07:23:54,251][87426] Updated weights for policy 1, policy_version 274170 (0.0008) -[2023-11-28 07:23:55,532][87424] Updated weights for policy 0, policy_version 274378 (0.0008) -[2023-11-28 07:23:55,906][87424] Updated weights for policy 0, policy_version 274388 (0.0007) -[2023-11-28 07:23:56,293][87424] Updated weights for policy 0, policy_version 274398 (0.0007) -[2023-11-28 07:23:56,779][87426] Updated weights for policy 1, policy_version 274180 (0.0009) -[2023-11-28 07:23:57,155][87426] Updated weights for policy 1, policy_version 274190 (0.0012) -[2023-11-28 07:23:57,529][87426] Updated weights for policy 1, policy_version 274200 (0.0010) -[2023-11-28 07:23:58,099][87424] Updated weights for policy 0, policy_version 274408 (0.0008) -[2023-11-28 07:23:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 140443648. Throughput: 0: 2700.4, 1: 2720.7. Samples: 140459580. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:23:58,445][86177] Avg episode reward: [(0, '-561.520'), (1, '-538.870')] -[2023-11-28 07:23:58,481][87424] Updated weights for policy 0, policy_version 274418 (0.0007) -[2023-11-28 07:23:58,867][87424] Updated weights for policy 0, policy_version 274428 (0.0009) -[2023-11-28 07:23:59,406][87426] Updated weights for policy 1, policy_version 274210 (0.0008) -[2023-11-28 07:23:59,788][87426] Updated weights for policy 1, policy_version 274220 (0.0011) -[2023-11-28 07:24:00,171][87426] Updated weights for policy 1, policy_version 274230 (0.0012) -[2023-11-28 07:24:00,543][87426] Updated weights for policy 1, policy_version 274240 (0.0011) -[2023-11-28 07:24:00,544][87424] Updated weights for policy 0, policy_version 274438 (0.0010) -[2023-11-28 07:24:00,926][87424] Updated weights for policy 0, policy_version 274448 (0.0012) -[2023-11-28 07:24:01,301][87424] Updated weights for policy 0, policy_version 274458 (0.0010) -[2023-11-28 07:24:02,664][87426] Updated weights for policy 1, policy_version 274250 (0.0007) -[2023-11-28 07:24:03,051][87426] Updated weights for policy 1, policy_version 274260 (0.0008) -[2023-11-28 07:24:03,432][87426] Updated weights for policy 1, policy_version 274270 (0.0009) -[2023-11-28 07:24:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 140468224. Throughput: 0: 2689.0, 1: 2716.8. Samples: 140483588. Policy #0 lag: (min: 11.0, avg: 38.4, max: 53.0) -[2023-11-28 07:24:03,445][86177] Avg episode reward: [(0, '-562.280'), (1, '-537.560')] -[2023-11-28 07:24:03,858][87424] Updated weights for policy 0, policy_version 274468 (0.0009) -[2023-11-28 07:24:04,234][87424] Updated weights for policy 0, policy_version 274478 (0.0007) -[2023-11-28 07:24:04,606][87424] Updated weights for policy 0, policy_version 274488 (0.0010) -[2023-11-28 07:24:05,739][87426] Updated weights for policy 1, policy_version 274280 (0.0008) -[2023-11-28 07:24:06,124][87426] Updated weights for policy 1, policy_version 274290 (0.0007) -[2023-11-28 07:24:06,512][87426] Updated weights for policy 1, policy_version 274300 (0.0007) -[2023-11-28 07:24:07,167][87424] Updated weights for policy 0, policy_version 274498 (0.0011) -[2023-11-28 07:24:07,549][87424] Updated weights for policy 0, policy_version 274508 (0.0012) -[2023-11-28 07:24:07,929][87424] Updated weights for policy 0, policy_version 274518 (0.0012) -[2023-11-28 07:24:08,310][87424] Updated weights for policy 0, policy_version 274528 (0.0010) -[2023-11-28 07:24:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 140500992. Throughput: 0: 2701.9, 1: 2746.1. Samples: 140516964. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:08,445][86177] Avg episode reward: [(0, '-583.210'), (1, '-526.930')] -[2023-11-28 07:24:08,874][87426] Updated weights for policy 1, policy_version 274310 (0.0009) -[2023-11-28 07:24:09,252][87426] Updated weights for policy 1, policy_version 274320 (0.0012) -[2023-11-28 07:24:09,631][87426] Updated weights for policy 1, policy_version 274330 (0.0011) -[2023-11-28 07:24:10,587][87424] Updated weights for policy 0, policy_version 274538 (0.0010) -[2023-11-28 07:24:10,972][87424] Updated weights for policy 0, policy_version 274548 (0.0008) -[2023-11-28 07:24:11,354][87424] Updated weights for policy 0, policy_version 274558 (0.0008) -[2023-11-28 07:24:11,850][87426] Updated weights for policy 1, policy_version 274340 (0.0010) -[2023-11-28 07:24:12,230][87426] Updated weights for policy 1, policy_version 274350 (0.0012) -[2023-11-28 07:24:12,606][87426] Updated weights for policy 1, policy_version 274360 (0.0009) -[2023-11-28 07:24:13,427][87424] Updated weights for policy 0, policy_version 274568 (0.0011) -[2023-11-28 07:24:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 140525568. Throughput: 0: 2695.3, 1: 2713.1. Samples: 140540656. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:13,445][86177] Avg episode reward: [(0, '-581.410'), (1, '-544.590')] -[2023-11-28 07:24:13,795][87424] Updated weights for policy 0, policy_version 274578 (0.0012) -[2023-11-28 07:24:14,177][87424] Updated weights for policy 0, policy_version 274588 (0.0011) -[2023-11-28 07:24:14,781][87426] Updated weights for policy 1, policy_version 274370 (0.0009) -[2023-11-28 07:24:15,160][87426] Updated weights for policy 1, policy_version 274380 (0.0011) -[2023-11-28 07:24:15,531][87426] Updated weights for policy 1, policy_version 274390 (0.0011) -[2023-11-28 07:24:15,912][87426] Updated weights for policy 1, policy_version 274400 (0.0011) -[2023-11-28 07:24:15,942][87424] Updated weights for policy 0, policy_version 274598 (0.0011) -[2023-11-28 07:24:16,324][87424] Updated weights for policy 0, policy_version 274608 (0.0009) -[2023-11-28 07:24:16,704][87424] Updated weights for policy 0, policy_version 274618 (0.0009) -[2023-11-28 07:24:17,713][87426] Updated weights for policy 1, policy_version 274410 (0.0011) -[2023-11-28 07:24:18,088][87426] Updated weights for policy 1, policy_version 274420 (0.0011) -[2023-11-28 07:24:18,376][87424] Updated weights for policy 0, policy_version 274628 (0.0007) -[2023-11-28 07:24:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 140550144. Throughput: 0: 2702.6, 1: 2712.5. Samples: 140565324. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:18,445][86177] Avg episode reward: [(0, '-548.700'), (1, '-530.660')] -[2023-11-28 07:24:18,467][87426] Updated weights for policy 1, policy_version 274430 (0.0011) -[2023-11-28 07:24:18,543][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000274432_70254592.pth... -[2023-11-28 07:24:18,591][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000271904_69607424.pth -[2023-11-28 07:24:18,755][87424] Updated weights for policy 0, policy_version 274638 (0.0008) -[2023-11-28 07:24:19,137][87424] Updated weights for policy 0, policy_version 274648 (0.0008) -[2023-11-28 07:24:19,442][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000274656_70311936.pth... -[2023-11-28 07:24:19,490][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000272096_69656576.pth -[2023-11-28 07:24:20,662][87426] Updated weights for policy 1, policy_version 274440 (0.0010) -[2023-11-28 07:24:21,044][87426] Updated weights for policy 1, policy_version 274450 (0.0007) -[2023-11-28 07:24:21,420][87426] Updated weights for policy 1, policy_version 274460 (0.0009) -[2023-11-28 07:24:21,511][87424] Updated weights for policy 0, policy_version 274658 (0.0011) -[2023-11-28 07:24:21,881][87424] Updated weights for policy 0, policy_version 274668 (0.0010) -[2023-11-28 07:24:22,264][87424] Updated weights for policy 0, policy_version 274678 (0.0011) -[2023-11-28 07:24:22,647][87424] Updated weights for policy 0, policy_version 274688 (0.0008) -[2023-11-28 07:24:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 140582912. Throughput: 0: 2710.8, 1: 2703.5. Samples: 140597848. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:23,446][86177] Avg episode reward: [(0, '-550.370'), (1, '-533.570')] -[2023-11-28 07:24:23,918][87426] Updated weights for policy 1, policy_version 274470 (0.0011) -[2023-11-28 07:24:24,290][87426] Updated weights for policy 1, policy_version 274480 (0.0012) -[2023-11-28 07:24:24,671][87426] Updated weights for policy 1, policy_version 274490 (0.0012) -[2023-11-28 07:24:25,265][87424] Updated weights for policy 0, policy_version 274698 (0.0008) -[2023-11-28 07:24:25,645][87424] Updated weights for policy 0, policy_version 274708 (0.0007) -[2023-11-28 07:24:26,029][87424] Updated weights for policy 0, policy_version 274718 (0.0007) -[2023-11-28 07:24:27,239][87426] Updated weights for policy 1, policy_version 274500 (0.0012) -[2023-11-28 07:24:27,617][87426] Updated weights for policy 1, policy_version 274510 (0.0012) -[2023-11-28 07:24:27,779][87424] Updated weights for policy 0, policy_version 274728 (0.0009) -[2023-11-28 07:24:27,989][87426] Updated weights for policy 1, policy_version 274520 (0.0011) -[2023-11-28 07:24:28,159][87424] Updated weights for policy 0, policy_version 274738 (0.0008) -[2023-11-28 07:24:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 140607488. Throughput: 0: 2710.9, 1: 2676.7. Samples: 140620520. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:28,445][86177] Avg episode reward: [(0, '-531.130'), (1, '-538.140')] -[2023-11-28 07:24:28,544][87424] Updated weights for policy 0, policy_version 274748 (0.0012) -[2023-11-28 07:24:30,090][87426] Updated weights for policy 1, policy_version 274530 (0.0011) -[2023-11-28 07:24:30,485][87426] Updated weights for policy 1, policy_version 274540 (0.0012) -[2023-11-28 07:24:30,769][87424] Updated weights for policy 0, policy_version 274758 (0.0011) -[2023-11-28 07:24:30,859][87426] Updated weights for policy 1, policy_version 274550 (0.0010) -[2023-11-28 07:24:31,157][87424] Updated weights for policy 0, policy_version 274768 (0.0007) -[2023-11-28 07:24:31,246][87426] Updated weights for policy 1, policy_version 274560 (0.0010) -[2023-11-28 07:24:31,538][87424] Updated weights for policy 0, policy_version 274778 (0.0007) -[2023-11-28 07:24:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 140632064. Throughput: 0: 2729.8, 1: 2673.2. Samples: 140645628. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:33,445][86177] Avg episode reward: [(0, '-532.320'), (1, '-525.250')] -[2023-11-28 07:24:33,460][87424] Updated weights for policy 0, policy_version 274788 (0.0010) -[2023-11-28 07:24:33,839][87424] Updated weights for policy 0, policy_version 274798 (0.0012) -[2023-11-28 07:24:33,842][87426] Updated weights for policy 1, policy_version 274570 (0.0011) -[2023-11-28 07:24:34,225][87426] Updated weights for policy 1, policy_version 274580 (0.0011) -[2023-11-28 07:24:34,226][87424] Updated weights for policy 0, policy_version 274808 (0.0012) -[2023-11-28 07:24:34,594][87426] Updated weights for policy 1, policy_version 274590 (0.0012) -[2023-11-28 07:24:36,679][87424] Updated weights for policy 0, policy_version 274818 (0.0012) -[2023-11-28 07:24:36,810][87426] Updated weights for policy 1, policy_version 274600 (0.0011) -[2023-11-28 07:24:37,050][87424] Updated weights for policy 0, policy_version 274828 (0.0011) -[2023-11-28 07:24:37,192][87426] Updated weights for policy 1, policy_version 274610 (0.0011) -[2023-11-28 07:24:37,440][87424] Updated weights for policy 0, policy_version 274838 (0.0010) -[2023-11-28 07:24:37,569][87426] Updated weights for policy 1, policy_version 274620 (0.0009) -[2023-11-28 07:24:37,821][87424] Updated weights for policy 0, policy_version 274848 (0.0010) -[2023-11-28 07:24:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 140664832. Throughput: 0: 2745.7, 1: 2638.0. Samples: 140678640. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:38,445][86177] Avg episode reward: [(0, '-529.730'), (1, '-548.130')] -[2023-11-28 07:24:39,262][87426] Updated weights for policy 1, policy_version 274630 (0.0010) -[2023-11-28 07:24:39,498][87424] Updated weights for policy 0, policy_version 274858 (0.0011) -[2023-11-28 07:24:39,652][87426] Updated weights for policy 1, policy_version 274640 (0.0012) -[2023-11-28 07:24:39,878][87424] Updated weights for policy 0, policy_version 274868 (0.0011) -[2023-11-28 07:24:40,028][87426] Updated weights for policy 1, policy_version 274650 (0.0012) -[2023-11-28 07:24:40,262][87424] Updated weights for policy 0, policy_version 274878 (0.0012) -[2023-11-28 07:24:42,065][87426] Updated weights for policy 1, policy_version 274660 (0.0012) -[2023-11-28 07:24:42,365][87424] Updated weights for policy 0, policy_version 274888 (0.0011) -[2023-11-28 07:24:42,440][87426] Updated weights for policy 1, policy_version 274670 (0.0010) -[2023-11-28 07:24:42,751][87424] Updated weights for policy 0, policy_version 274898 (0.0009) -[2023-11-28 07:24:42,827][87426] Updated weights for policy 1, policy_version 274680 (0.0010) -[2023-11-28 07:24:43,135][87424] Updated weights for policy 0, policy_version 274908 (0.0012) -[2023-11-28 07:24:43,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 140697600. Throughput: 0: 2756.1, 1: 2665.3. Samples: 140703544. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:43,445][86177] Avg episode reward: [(0, '-534.700'), (1, '-546.280')] -[2023-11-28 07:24:44,930][87424] Updated weights for policy 0, policy_version 274918 (0.0012) -[2023-11-28 07:24:45,179][87426] Updated weights for policy 1, policy_version 274690 (0.0009) -[2023-11-28 07:24:45,308][87424] Updated weights for policy 0, policy_version 274928 (0.0008) -[2023-11-28 07:24:45,558][87426] Updated weights for policy 1, policy_version 274700 (0.0010) -[2023-11-28 07:24:45,691][87424] Updated weights for policy 0, policy_version 274938 (0.0011) -[2023-11-28 07:24:45,934][87426] Updated weights for policy 1, policy_version 274710 (0.0009) -[2023-11-28 07:24:46,303][87426] Updated weights for policy 1, policy_version 274720 (0.0012) -[2023-11-28 07:24:48,045][87424] Updated weights for policy 0, policy_version 274948 (0.0012) -[2023-11-28 07:24:48,426][87424] Updated weights for policy 0, policy_version 274958 (0.0011) -[2023-11-28 07:24:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 140713984. Throughput: 0: 2795.0, 1: 2663.9. Samples: 140729240. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:48,445][86177] Avg episode reward: [(0, '-537.640'), (1, '-543.620')] -[2023-11-28 07:24:48,814][87424] Updated weights for policy 0, policy_version 274968 (0.0011) -[2023-11-28 07:24:48,916][87426] Updated weights for policy 1, policy_version 274730 (0.0009) -[2023-11-28 07:24:49,300][87426] Updated weights for policy 1, policy_version 274740 (0.0011) -[2023-11-28 07:24:49,670][87426] Updated weights for policy 1, policy_version 274750 (0.0012) -[2023-11-28 07:24:50,718][87424] Updated weights for policy 0, policy_version 274978 (0.0012) -[2023-11-28 07:24:51,086][87424] Updated weights for policy 0, policy_version 274988 (0.0012) -[2023-11-28 07:24:51,471][87424] Updated weights for policy 0, policy_version 274998 (0.0010) -[2023-11-28 07:24:51,853][87424] Updated weights for policy 0, policy_version 275008 (0.0010) -[2023-11-28 07:24:51,931][87426] Updated weights for policy 1, policy_version 274760 (0.0010) -[2023-11-28 07:24:52,304][87426] Updated weights for policy 1, policy_version 274770 (0.0011) -[2023-11-28 07:24:52,687][87426] Updated weights for policy 1, policy_version 274780 (0.0011) -[2023-11-28 07:24:53,450][86177] Fps is (10 sec: 4912.3, 60 sec: 5460.8, 300 sec: 5414.9). Total num frames: 140746752. Throughput: 0: 2808.1, 1: 2648.1. Samples: 140762524. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:53,451][86177] Avg episode reward: [(0, '-577.810'), (1, '-540.800')] -[2023-11-28 07:24:54,353][87424] Updated weights for policy 0, policy_version 275018 (0.0011) -[2023-11-28 07:24:54,746][87424] Updated weights for policy 0, policy_version 275028 (0.0011) -[2023-11-28 07:24:54,992][87426] Updated weights for policy 1, policy_version 274790 (0.0011) -[2023-11-28 07:24:55,120][87424] Updated weights for policy 0, policy_version 275038 (0.0009) -[2023-11-28 07:24:55,366][87426] Updated weights for policy 1, policy_version 274800 (0.0008) -[2023-11-28 07:24:55,751][87426] Updated weights for policy 1, policy_version 274810 (0.0011) -[2023-11-28 07:24:57,507][87426] Updated weights for policy 1, policy_version 274820 (0.0012) -[2023-11-28 07:24:57,648][87424] Updated weights for policy 0, policy_version 275048 (0.0009) -[2023-11-28 07:24:57,869][87426] Updated weights for policy 1, policy_version 274830 (0.0008) -[2023-11-28 07:24:58,030][87424] Updated weights for policy 0, policy_version 275058 (0.0008) -[2023-11-28 07:24:58,247][87426] Updated weights for policy 1, policy_version 274840 (0.0008) -[2023-11-28 07:24:58,413][87424] Updated weights for policy 0, policy_version 275068 (0.0012) -[2023-11-28 07:24:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 140763136. Throughput: 0: 2803.3, 1: 2684.4. Samples: 140787604. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:24:58,445][86177] Avg episode reward: [(0, '-575.690'), (1, '-519.720')] -[2023-11-28 07:25:00,379][87426] Updated weights for policy 1, policy_version 274850 (0.0012) -[2023-11-28 07:25:00,440][87424] Updated weights for policy 0, policy_version 275078 (0.0010) -[2023-11-28 07:25:00,758][87426] Updated weights for policy 1, policy_version 274860 (0.0012) -[2023-11-28 07:25:00,816][87424] Updated weights for policy 0, policy_version 275088 (0.0008) -[2023-11-28 07:25:01,130][87426] Updated weights for policy 1, policy_version 274870 (0.0012) -[2023-11-28 07:25:01,197][87424] Updated weights for policy 0, policy_version 275098 (0.0008) -[2023-11-28 07:25:01,509][87426] Updated weights for policy 1, policy_version 274880 (0.0012) -[2023-11-28 07:25:03,098][87424] Updated weights for policy 0, policy_version 275108 (0.0010) -[2023-11-28 07:25:03,444][86177] Fps is (10 sec: 4918.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 140795904. Throughput: 0: 2797.8, 1: 2683.4. Samples: 140811976. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:25:03,445][86177] Avg episode reward: [(0, '-579.470'), (1, '-518.840')] -[2023-11-28 07:25:03,478][87424] Updated weights for policy 0, policy_version 275118 (0.0012) -[2023-11-28 07:25:03,505][87426] Updated weights for policy 1, policy_version 274890 (0.0012) -[2023-11-28 07:25:03,853][87424] Updated weights for policy 0, policy_version 275128 (0.0012) -[2023-11-28 07:25:03,869][87426] Updated weights for policy 1, policy_version 274900 (0.0011) -[2023-11-28 07:25:04,248][87426] Updated weights for policy 1, policy_version 274910 (0.0011) -[2023-11-28 07:25:05,963][87424] Updated weights for policy 0, policy_version 275138 (0.0012) -[2023-11-28 07:25:06,343][87424] Updated weights for policy 0, policy_version 275148 (0.0012) -[2023-11-28 07:25:06,532][87426] Updated weights for policy 1, policy_version 274920 (0.0011) -[2023-11-28 07:25:06,728][87424] Updated weights for policy 0, policy_version 275158 (0.0012) -[2023-11-28 07:25:06,915][87426] Updated weights for policy 1, policy_version 274930 (0.0011) -[2023-11-28 07:25:07,110][87424] Updated weights for policy 0, policy_version 275168 (0.0011) -[2023-11-28 07:25:07,292][87426] Updated weights for policy 1, policy_version 274940 (0.0012) -[2023-11-28 07:25:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 140828672. Throughput: 0: 2806.0, 1: 2678.1. Samples: 140844632. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:25:08,445][86177] Avg episode reward: [(0, '-579.970'), (1, '-521.700')] -[2023-11-28 07:25:09,208][87424] Updated weights for policy 0, policy_version 275178 (0.0012) -[2023-11-28 07:25:09,309][87426] Updated weights for policy 1, policy_version 274950 (0.0011) -[2023-11-28 07:25:09,583][87424] Updated weights for policy 0, policy_version 275188 (0.0011) -[2023-11-28 07:25:09,685][87426] Updated weights for policy 1, policy_version 274960 (0.0011) -[2023-11-28 07:25:09,967][87424] Updated weights for policy 0, policy_version 275198 (0.0011) -[2023-11-28 07:25:10,079][87426] Updated weights for policy 1, policy_version 274970 (0.0011) -[2023-11-28 07:25:12,118][87424] Updated weights for policy 0, policy_version 275208 (0.0011) -[2023-11-28 07:25:12,184][87426] Updated weights for policy 1, policy_version 274980 (0.0011) -[2023-11-28 07:25:12,498][87424] Updated weights for policy 0, policy_version 275218 (0.0012) -[2023-11-28 07:25:12,557][87426] Updated weights for policy 1, policy_version 274990 (0.0010) -[2023-11-28 07:25:12,879][87424] Updated weights for policy 0, policy_version 275228 (0.0011) -[2023-11-28 07:25:12,933][87426] Updated weights for policy 1, policy_version 275000 (0.0011) -[2023-11-28 07:25:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 140861440. Throughput: 0: 2824.4, 1: 2707.1. Samples: 140869436. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:25:13,445][86177] Avg episode reward: [(0, '-547.200'), (1, '-555.660')] -[2023-11-28 07:25:14,642][87424] Updated weights for policy 0, policy_version 275238 (0.0011) -[2023-11-28 07:25:15,021][87424] Updated weights for policy 0, policy_version 275248 (0.0012) -[2023-11-28 07:25:15,403][87424] Updated weights for policy 0, policy_version 275258 (0.0012) -[2023-11-28 07:25:15,442][87426] Updated weights for policy 1, policy_version 275010 (0.0012) -[2023-11-28 07:25:15,821][87426] Updated weights for policy 1, policy_version 275020 (0.0012) -[2023-11-28 07:25:16,203][87426] Updated weights for policy 1, policy_version 275030 (0.0012) -[2023-11-28 07:25:16,571][87426] Updated weights for policy 1, policy_version 275040 (0.0012) -[2023-11-28 07:25:17,819][87424] Updated weights for policy 0, policy_version 275268 (0.0012) -[2023-11-28 07:25:18,199][87424] Updated weights for policy 0, policy_version 275278 (0.0012) -[2023-11-28 07:25:18,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 140877824. Throughput: 0: 2827.2, 1: 2687.4. Samples: 140893784. Policy #0 lag: (min: 31.0, avg: 46.2, max: 63.0) -[2023-11-28 07:25:18,446][86177] Avg episode reward: [(0, '-544.630'), (1, '-561.510')] -[2023-11-28 07:25:18,576][87424] Updated weights for policy 0, policy_version 275288 (0.0012) -[2023-11-28 07:25:18,691][87426] Updated weights for policy 1, policy_version 275050 (0.0011) -[2023-11-28 07:25:19,084][87426] Updated weights for policy 1, policy_version 275060 (0.0012) -[2023-11-28 07:25:19,459][87426] Updated weights for policy 1, policy_version 275070 (0.0012) -[2023-11-28 07:25:20,641][87424] Updated weights for policy 0, policy_version 275298 (0.0012) -[2023-11-28 07:25:21,015][87424] Updated weights for policy 0, policy_version 275308 (0.0012) -[2023-11-28 07:25:21,397][87424] Updated weights for policy 0, policy_version 275318 (0.0011) -[2023-11-28 07:25:21,491][87426] Updated weights for policy 1, policy_version 275080 (0.0011) -[2023-11-28 07:25:21,782][87424] Updated weights for policy 0, policy_version 275328 (0.0010) -[2023-11-28 07:25:21,862][87426] Updated weights for policy 1, policy_version 275090 (0.0011) -[2023-11-28 07:25:22,238][87426] Updated weights for policy 1, policy_version 275100 (0.0009) -[2023-11-28 07:25:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 140910592. Throughput: 0: 2792.5, 1: 2735.9. Samples: 140927420. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:25:23,446][86177] Avg episode reward: [(0, '-572.290'), (1, '-560.780')] -[2023-11-28 07:25:24,318][87424] Updated weights for policy 0, policy_version 275338 (0.0012) -[2023-11-28 07:25:24,693][87424] Updated weights for policy 0, policy_version 275348 (0.0011) -[2023-11-28 07:25:24,754][87426] Updated weights for policy 1, policy_version 275110 (0.0012) -[2023-11-28 07:25:25,078][87424] Updated weights for policy 0, policy_version 275358 (0.0012) -[2023-11-28 07:25:25,138][87426] Updated weights for policy 1, policy_version 275120 (0.0009) -[2023-11-28 07:25:25,522][87426] Updated weights for policy 1, policy_version 275130 (0.0007) -[2023-11-28 07:25:26,782][87424] Updated weights for policy 0, policy_version 275368 (0.0008) -[2023-11-28 07:25:27,170][87424] Updated weights for policy 0, policy_version 275378 (0.0007) -[2023-11-28 07:25:27,553][87424] Updated weights for policy 0, policy_version 275388 (0.0007) -[2023-11-28 07:25:28,016][87426] Updated weights for policy 1, policy_version 275140 (0.0007) -[2023-11-28 07:25:28,401][87426] Updated weights for policy 1, policy_version 275150 (0.0009) -[2023-11-28 07:25:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 140935168. Throughput: 0: 2787.3, 1: 2716.6. Samples: 140951220. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:25:28,445][86177] Avg episode reward: [(0, '-577.690'), (1, '-575.070')] -[2023-11-28 07:25:28,779][87426] Updated weights for policy 1, policy_version 275160 (0.0011) -[2023-11-28 07:25:29,975][87424] Updated weights for policy 0, policy_version 275398 (0.0009) -[2023-11-28 07:25:30,358][87424] Updated weights for policy 0, policy_version 275408 (0.0011) -[2023-11-28 07:25:30,732][87424] Updated weights for policy 0, policy_version 275418 (0.0012) -[2023-11-28 07:25:30,760][87426] Updated weights for policy 1, policy_version 275170 (0.0009) -[2023-11-28 07:25:31,143][87426] Updated weights for policy 1, policy_version 275180 (0.0009) -[2023-11-28 07:25:31,518][87426] Updated weights for policy 1, policy_version 275190 (0.0007) -[2023-11-28 07:25:31,897][87426] Updated weights for policy 1, policy_version 275200 (0.0009) -[2023-11-28 07:25:33,358][87424] Updated weights for policy 0, policy_version 275428 (0.0011) -[2023-11-28 07:25:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 140959744. Throughput: 0: 2740.4, 1: 2710.3. Samples: 140974520. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:25:33,445][86177] Avg episode reward: [(0, '-576.930'), (1, '-561.500')] -[2023-11-28 07:25:33,742][87424] Updated weights for policy 0, policy_version 275438 (0.0012) -[2023-11-28 07:25:33,979][87426] Updated weights for policy 1, policy_version 275210 (0.0011) -[2023-11-28 07:25:34,124][87424] Updated weights for policy 0, policy_version 275448 (0.0012) -[2023-11-28 07:25:34,366][87426] Updated weights for policy 1, policy_version 275220 (0.0011) -[2023-11-28 07:25:34,745][87426] Updated weights for policy 1, policy_version 275230 (0.0012) -[2023-11-28 07:25:36,348][87424] Updated weights for policy 0, policy_version 275458 (0.0011) -[2023-11-28 07:25:36,733][87424] Updated weights for policy 0, policy_version 275468 (0.0011) -[2023-11-28 07:25:37,110][87424] Updated weights for policy 0, policy_version 275478 (0.0011) -[2023-11-28 07:25:37,187][87426] Updated weights for policy 1, policy_version 275240 (0.0011) -[2023-11-28 07:25:37,491][87424] Updated weights for policy 0, policy_version 275488 (0.0010) -[2023-11-28 07:25:37,572][87426] Updated weights for policy 1, policy_version 275250 (0.0010) -[2023-11-28 07:25:37,945][87426] Updated weights for policy 1, policy_version 275260 (0.0011) -[2023-11-28 07:25:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 140992512. Throughput: 0: 2721.1, 1: 2729.3. Samples: 141007756. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:25:38,445][86177] Avg episode reward: [(0, '-571.630'), (1, '-597.140')] -[2023-11-28 07:25:39,194][87424] Updated weights for policy 0, policy_version 275498 (0.0012) -[2023-11-28 07:25:39,572][87424] Updated weights for policy 0, policy_version 275508 (0.0012) -[2023-11-28 07:25:39,960][87424] Updated weights for policy 0, policy_version 275518 (0.0012) -[2023-11-28 07:25:40,381][87426] Updated weights for policy 1, policy_version 275270 (0.0010) -[2023-11-28 07:25:40,760][87426] Updated weights for policy 1, policy_version 275280 (0.0009) -[2023-11-28 07:25:41,140][87426] Updated weights for policy 1, policy_version 275290 (0.0011) -[2023-11-28 07:25:42,561][87424] Updated weights for policy 0, policy_version 275528 (0.0012) -[2023-11-28 07:25:42,941][87424] Updated weights for policy 0, policy_version 275538 (0.0011) -[2023-11-28 07:25:43,222][87426] Updated weights for policy 1, policy_version 275300 (0.0012) -[2023-11-28 07:25:43,313][87424] Updated weights for policy 0, policy_version 275548 (0.0009) -[2023-11-28 07:25:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 141008896. Throughput: 0: 2724.0, 1: 2706.7. Samples: 141031984. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:25:43,445][86177] Avg episode reward: [(0, '-580.010'), (1, '-601.620')] -[2023-11-28 07:25:43,601][87426] Updated weights for policy 1, policy_version 275310 (0.0010) -[2023-11-28 07:25:43,978][87426] Updated weights for policy 1, policy_version 275320 (0.0007) -[2023-11-28 07:25:45,625][87424] Updated weights for policy 0, policy_version 275558 (0.0009) -[2023-11-28 07:25:45,646][87426] Updated weights for policy 1, policy_version 275330 (0.0008) -[2023-11-28 07:25:45,995][87424] Updated weights for policy 0, policy_version 275568 (0.0007) -[2023-11-28 07:25:46,020][87426] Updated weights for policy 1, policy_version 275340 (0.0010) -[2023-11-28 07:25:46,373][87424] Updated weights for policy 0, policy_version 275578 (0.0008) -[2023-11-28 07:25:46,399][87426] Updated weights for policy 1, policy_version 275350 (0.0010) -[2023-11-28 07:25:46,776][87426] Updated weights for policy 1, policy_version 275360 (0.0011) -[2023-11-28 07:25:48,084][87424] Updated weights for policy 0, policy_version 275588 (0.0011) -[2023-11-28 07:25:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 141041664. Throughput: 0: 2715.1, 1: 2704.8. Samples: 141055872. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:25:48,445][86177] Avg episode reward: [(0, '-540.500'), (1, '-589.720')] -[2023-11-28 07:25:48,472][87424] Updated weights for policy 0, policy_version 275598 (0.0012) -[2023-11-28 07:25:48,856][87424] Updated weights for policy 0, policy_version 275608 (0.0012) -[2023-11-28 07:25:49,201][87426] Updated weights for policy 1, policy_version 275370 (0.0010) -[2023-11-28 07:25:49,575][87426] Updated weights for policy 1, policy_version 275380 (0.0012) -[2023-11-28 07:25:49,953][87426] Updated weights for policy 1, policy_version 275390 (0.0012) -[2023-11-28 07:25:50,991][87424] Updated weights for policy 0, policy_version 275618 (0.0010) -[2023-11-28 07:25:51,371][87424] Updated weights for policy 0, policy_version 275628 (0.0012) -[2023-11-28 07:25:51,761][87424] Updated weights for policy 0, policy_version 275638 (0.0010) -[2023-11-28 07:25:52,135][87424] Updated weights for policy 0, policy_version 275648 (0.0008) -[2023-11-28 07:25:52,497][87426] Updated weights for policy 1, policy_version 275400 (0.0012) -[2023-11-28 07:25:52,876][87426] Updated weights for policy 1, policy_version 275410 (0.0012) -[2023-11-28 07:25:53,259][87426] Updated weights for policy 1, policy_version 275420 (0.0012) -[2023-11-28 07:25:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.9, 300 sec: 5442.8). Total num frames: 141074432. Throughput: 0: 2716.9, 1: 2704.3. Samples: 141088584. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:25:53,445][86177] Avg episode reward: [(0, '-536.870'), (1, '-566.940')] -[2023-11-28 07:25:54,174][87424] Updated weights for policy 0, policy_version 275658 (0.0010) -[2023-11-28 07:25:54,561][87424] Updated weights for policy 0, policy_version 275668 (0.0008) -[2023-11-28 07:25:54,942][87424] Updated weights for policy 0, policy_version 275678 (0.0008) -[2023-11-28 07:25:55,345][87426] Updated weights for policy 1, policy_version 275430 (0.0012) -[2023-11-28 07:25:55,718][87426] Updated weights for policy 1, policy_version 275440 (0.0009) -[2023-11-28 07:25:56,086][87426] Updated weights for policy 1, policy_version 275450 (0.0007) -[2023-11-28 07:25:57,262][87424] Updated weights for policy 0, policy_version 275688 (0.0011) -[2023-11-28 07:25:57,636][87424] Updated weights for policy 0, policy_version 275698 (0.0008) -[2023-11-28 07:25:58,019][87424] Updated weights for policy 0, policy_version 275708 (0.0007) -[2023-11-28 07:25:58,191][87426] Updated weights for policy 1, policy_version 275460 (0.0009) -[2023-11-28 07:25:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 141099008. Throughput: 0: 2703.8, 1: 2720.8. Samples: 141113544. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:25:58,445][86177] Avg episode reward: [(0, '-540.430'), (1, '-529.150')] -[2023-11-28 07:25:58,576][87426] Updated weights for policy 1, policy_version 275470 (0.0012) -[2023-11-28 07:25:58,965][87426] Updated weights for policy 1, policy_version 275480 (0.0010) -[2023-11-28 07:26:00,016][87424] Updated weights for policy 0, policy_version 275718 (0.0008) -[2023-11-28 07:26:00,397][87424] Updated weights for policy 0, policy_version 275728 (0.0008) -[2023-11-28 07:26:00,773][87424] Updated weights for policy 0, policy_version 275738 (0.0009) -[2023-11-28 07:26:00,993][87426] Updated weights for policy 1, policy_version 275490 (0.0009) -[2023-11-28 07:26:01,368][87426] Updated weights for policy 1, policy_version 275500 (0.0012) -[2023-11-28 07:26:01,746][87426] Updated weights for policy 1, policy_version 275510 (0.0012) -[2023-11-28 07:26:02,119][87426] Updated weights for policy 1, policy_version 275520 (0.0012) -[2023-11-28 07:26:03,003][87424] Updated weights for policy 0, policy_version 275748 (0.0011) -[2023-11-28 07:26:03,385][87424] Updated weights for policy 0, policy_version 275758 (0.0012) -[2023-11-28 07:26:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 141123584. Throughput: 0: 2703.3, 1: 2732.6. Samples: 141138400. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:26:03,445][86177] Avg episode reward: [(0, '-541.620'), (1, '-530.510')] -[2023-11-28 07:26:03,772][87424] Updated weights for policy 0, policy_version 275768 (0.0012) -[2023-11-28 07:26:04,526][87426] Updated weights for policy 1, policy_version 275530 (0.0009) -[2023-11-28 07:26:04,916][87426] Updated weights for policy 1, policy_version 275540 (0.0012) -[2023-11-28 07:26:05,302][87426] Updated weights for policy 1, policy_version 275550 (0.0012) -[2023-11-28 07:26:05,625][87424] Updated weights for policy 0, policy_version 275778 (0.0009) -[2023-11-28 07:26:06,003][87424] Updated weights for policy 0, policy_version 275788 (0.0010) -[2023-11-28 07:26:06,390][87424] Updated weights for policy 0, policy_version 275798 (0.0008) -[2023-11-28 07:26:06,772][87424] Updated weights for policy 0, policy_version 275808 (0.0010) -[2023-11-28 07:26:07,178][87426] Updated weights for policy 1, policy_version 275560 (0.0008) -[2023-11-28 07:26:07,556][87426] Updated weights for policy 1, policy_version 275570 (0.0007) -[2023-11-28 07:26:07,931][87426] Updated weights for policy 1, policy_version 275580 (0.0008) -[2023-11-28 07:26:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141156352. Throughput: 0: 2723.3, 1: 2715.6. Samples: 141172168. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:26:08,445][86177] Avg episode reward: [(0, '-574.250'), (1, '-544.950')] -[2023-11-28 07:26:09,152][87424] Updated weights for policy 0, policy_version 275818 (0.0012) -[2023-11-28 07:26:09,529][87424] Updated weights for policy 0, policy_version 275828 (0.0012) -[2023-11-28 07:26:09,864][87426] Updated weights for policy 1, policy_version 275590 (0.0010) -[2023-11-28 07:26:09,927][87424] Updated weights for policy 0, policy_version 275838 (0.0011) -[2023-11-28 07:26:10,249][87426] Updated weights for policy 1, policy_version 275600 (0.0011) -[2023-11-28 07:26:10,628][87426] Updated weights for policy 1, policy_version 275610 (0.0011) -[2023-11-28 07:26:12,150][87424] Updated weights for policy 0, policy_version 275848 (0.0010) -[2023-11-28 07:26:12,524][87424] Updated weights for policy 0, policy_version 275858 (0.0012) -[2023-11-28 07:26:12,917][87424] Updated weights for policy 0, policy_version 275868 (0.0012) -[2023-11-28 07:26:13,235][87426] Updated weights for policy 1, policy_version 275620 (0.0011) -[2023-11-28 07:26:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 141180928. Throughput: 0: 2713.7, 1: 2716.3. Samples: 141195568. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:26:13,445][86177] Avg episode reward: [(0, '-562.070'), (1, '-544.540')] -[2023-11-28 07:26:13,611][87426] Updated weights for policy 1, policy_version 275630 (0.0011) -[2023-11-28 07:26:13,990][87426] Updated weights for policy 1, policy_version 275640 (0.0011) -[2023-11-28 07:26:14,841][87424] Updated weights for policy 0, policy_version 275878 (0.0011) -[2023-11-28 07:26:15,220][87424] Updated weights for policy 0, policy_version 275888 (0.0012) -[2023-11-28 07:26:15,606][87424] Updated weights for policy 0, policy_version 275898 (0.0012) -[2023-11-28 07:26:15,944][87426] Updated weights for policy 1, policy_version 275650 (0.0011) -[2023-11-28 07:26:16,323][87426] Updated weights for policy 1, policy_version 275660 (0.0008) -[2023-11-28 07:26:16,714][87426] Updated weights for policy 1, policy_version 275670 (0.0011) -[2023-11-28 07:26:17,086][87426] Updated weights for policy 1, policy_version 275680 (0.0012) -[2023-11-28 07:26:17,961][87424] Updated weights for policy 0, policy_version 275908 (0.0012) -[2023-11-28 07:26:18,345][87424] Updated weights for policy 0, policy_version 275918 (0.0012) -[2023-11-28 07:26:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 141205504. Throughput: 0: 2750.0, 1: 2722.0. Samples: 141220760. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:26:18,445][86177] Avg episode reward: [(0, '-563.970'), (1, '-542.110')] -[2023-11-28 07:26:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000275680_70574080.pth... -[2023-11-28 07:26:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000273152_69926912.pth -[2023-11-28 07:26:18,723][87424] Updated weights for policy 0, policy_version 275928 (0.0008) -[2023-11-28 07:26:19,046][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000275936_70639616.pth... -[2023-11-28 07:26:19,089][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000273376_69984256.pth -[2023-11-28 07:26:19,308][87426] Updated weights for policy 1, policy_version 275690 (0.0012) -[2023-11-28 07:26:19,686][87426] Updated weights for policy 1, policy_version 275700 (0.0012) -[2023-11-28 07:26:20,066][87426] Updated weights for policy 1, policy_version 275710 (0.0011) -[2023-11-28 07:26:21,192][87424] Updated weights for policy 0, policy_version 275938 (0.0010) -[2023-11-28 07:26:21,589][87424] Updated weights for policy 0, policy_version 275948 (0.0009) -[2023-11-28 07:26:21,957][87424] Updated weights for policy 0, policy_version 275958 (0.0010) -[2023-11-28 07:26:22,012][87426] Updated weights for policy 1, policy_version 275720 (0.0010) -[2023-11-28 07:26:22,337][87424] Updated weights for policy 0, policy_version 275968 (0.0011) -[2023-11-28 07:26:22,394][87426] Updated weights for policy 1, policy_version 275730 (0.0011) -[2023-11-28 07:26:22,763][87426] Updated weights for policy 1, policy_version 275740 (0.0007) -[2023-11-28 07:26:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141238272. Throughput: 0: 2725.2, 1: 2720.9. Samples: 141252828. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:26:23,445][86177] Avg episode reward: [(0, '-559.880'), (1, '-577.980')] -[2023-11-28 07:26:24,477][87424] Updated weights for policy 0, policy_version 275978 (0.0012) -[2023-11-28 07:26:24,747][87426] Updated weights for policy 1, policy_version 275750 (0.0011) -[2023-11-28 07:26:24,851][87424] Updated weights for policy 0, policy_version 275988 (0.0012) -[2023-11-28 07:26:25,119][87426] Updated weights for policy 1, policy_version 275760 (0.0010) -[2023-11-28 07:26:25,244][87424] Updated weights for policy 0, policy_version 275998 (0.0012) -[2023-11-28 07:26:25,501][87426] Updated weights for policy 1, policy_version 275770 (0.0010) -[2023-11-28 07:26:27,118][87424] Updated weights for policy 0, policy_version 276008 (0.0008) -[2023-11-28 07:26:27,431][87426] Updated weights for policy 1, policy_version 275780 (0.0008) -[2023-11-28 07:26:27,506][87424] Updated weights for policy 0, policy_version 276018 (0.0008) -[2023-11-28 07:26:27,805][87426] Updated weights for policy 1, policy_version 275790 (0.0008) -[2023-11-28 07:26:27,881][87424] Updated weights for policy 0, policy_version 276028 (0.0010) -[2023-11-28 07:26:28,185][87426] Updated weights for policy 1, policy_version 275800 (0.0007) -[2023-11-28 07:26:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 141262848. Throughput: 0: 2732.3, 1: 2736.7. Samples: 141278092. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:26:28,445][86177] Avg episode reward: [(0, '-561.550'), (1, '-603.830')] -[2023-11-28 07:26:29,783][87424] Updated weights for policy 0, policy_version 276038 (0.0009) -[2023-11-28 07:26:30,184][87424] Updated weights for policy 0, policy_version 276048 (0.0010) -[2023-11-28 07:26:30,313][87426] Updated weights for policy 1, policy_version 275810 (0.0009) -[2023-11-28 07:26:30,575][87424] Updated weights for policy 0, policy_version 276058 (0.0010) -[2023-11-28 07:26:30,693][87426] Updated weights for policy 1, policy_version 275820 (0.0010) -[2023-11-28 07:26:31,069][87426] Updated weights for policy 1, policy_version 275830 (0.0012) -[2023-11-28 07:26:31,445][87426] Updated weights for policy 1, policy_version 275840 (0.0012) -[2023-11-28 07:26:32,589][87424] Updated weights for policy 0, policy_version 276068 (0.0010) -[2023-11-28 07:26:32,969][87424] Updated weights for policy 0, policy_version 276078 (0.0008) -[2023-11-28 07:26:33,352][87424] Updated weights for policy 0, policy_version 276088 (0.0010) -[2023-11-28 07:26:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 141287424. Throughput: 0: 2761.5, 1: 2731.1. Samples: 141303040. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:26:33,445][86177] Avg episode reward: [(0, '-563.430'), (1, '-617.960')] -[2023-11-28 07:26:33,449][87426] Updated weights for policy 1, policy_version 275850 (0.0011) -[2023-11-28 07:26:33,822][87426] Updated weights for policy 1, policy_version 275860 (0.0009) -[2023-11-28 07:26:34,203][87426] Updated weights for policy 1, policy_version 275870 (0.0007) -[2023-11-28 07:26:35,642][87424] Updated weights for policy 0, policy_version 276098 (0.0011) -[2023-11-28 07:26:36,031][87424] Updated weights for policy 0, policy_version 276108 (0.0012) -[2023-11-28 07:26:36,260][87426] Updated weights for policy 1, policy_version 275880 (0.0007) -[2023-11-28 07:26:36,406][87424] Updated weights for policy 0, policy_version 276118 (0.0009) -[2023-11-28 07:26:36,647][87426] Updated weights for policy 1, policy_version 275890 (0.0008) -[2023-11-28 07:26:36,798][87424] Updated weights for policy 0, policy_version 276128 (0.0008) -[2023-11-28 07:26:37,025][87426] Updated weights for policy 1, policy_version 275900 (0.0010) -[2023-11-28 07:26:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141320192. Throughput: 0: 2748.9, 1: 2743.6. Samples: 141335744. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:26:38,445][86177] Avg episode reward: [(0, '-567.000'), (1, '-625.610')] -[2023-11-28 07:26:39,016][87424] Updated weights for policy 0, policy_version 276138 (0.0009) -[2023-11-28 07:26:39,380][87426] Updated weights for policy 1, policy_version 275910 (0.0010) -[2023-11-28 07:26:39,389][87424] Updated weights for policy 0, policy_version 276148 (0.0011) -[2023-11-28 07:26:39,753][87426] Updated weights for policy 1, policy_version 275920 (0.0011) -[2023-11-28 07:26:39,766][87424] Updated weights for policy 0, policy_version 276158 (0.0011) -[2023-11-28 07:26:40,128][87426] Updated weights for policy 1, policy_version 275930 (0.0012) -[2023-11-28 07:26:42,037][87424] Updated weights for policy 0, policy_version 276168 (0.0010) -[2023-11-28 07:26:42,419][87424] Updated weights for policy 0, policy_version 276178 (0.0011) -[2023-11-28 07:26:42,423][87426] Updated weights for policy 1, policy_version 275940 (0.0012) -[2023-11-28 07:26:42,796][87424] Updated weights for policy 0, policy_version 276188 (0.0012) -[2023-11-28 07:26:42,802][87426] Updated weights for policy 1, policy_version 275950 (0.0011) -[2023-11-28 07:26:43,183][87426] Updated weights for policy 1, policy_version 275960 (0.0012) -[2023-11-28 07:26:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 141344768. Throughput: 0: 2743.3, 1: 2739.9. Samples: 141360288. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:26:43,445][86177] Avg episode reward: [(0, '-611.180'), (1, '-635.210')] -[2023-11-28 07:26:45,035][87424] Updated weights for policy 0, policy_version 276198 (0.0012) -[2023-11-28 07:26:45,193][87426] Updated weights for policy 1, policy_version 275970 (0.0009) -[2023-11-28 07:26:45,413][87424] Updated weights for policy 0, policy_version 276208 (0.0012) -[2023-11-28 07:26:45,570][87426] Updated weights for policy 1, policy_version 275980 (0.0011) -[2023-11-28 07:26:45,803][87424] Updated weights for policy 0, policy_version 276218 (0.0011) -[2023-11-28 07:26:45,950][87426] Updated weights for policy 1, policy_version 275990 (0.0011) -[2023-11-28 07:26:46,328][87426] Updated weights for policy 1, policy_version 276000 (0.0012) -[2023-11-28 07:26:48,280][87424] Updated weights for policy 0, policy_version 276228 (0.0009) -[2023-11-28 07:26:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141369344. Throughput: 0: 2718.0, 1: 2760.0. Samples: 141384908. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:26:48,445][86177] Avg episode reward: [(0, '-569.930'), (1, '-592.850')] -[2023-11-28 07:26:48,659][87424] Updated weights for policy 0, policy_version 276238 (0.0007) -[2023-11-28 07:26:48,854][87426] Updated weights for policy 1, policy_version 276010 (0.0008) -[2023-11-28 07:26:49,038][87424] Updated weights for policy 0, policy_version 276248 (0.0010) -[2023-11-28 07:26:49,241][87426] Updated weights for policy 1, policy_version 276020 (0.0011) -[2023-11-28 07:26:49,607][87426] Updated weights for policy 1, policy_version 276030 (0.0008) -[2023-11-28 07:26:50,939][87424] Updated weights for policy 0, policy_version 276258 (0.0011) -[2023-11-28 07:26:51,322][87424] Updated weights for policy 0, policy_version 276268 (0.0011) -[2023-11-28 07:26:51,484][87426] Updated weights for policy 1, policy_version 276040 (0.0011) -[2023-11-28 07:26:51,703][87424] Updated weights for policy 0, policy_version 276278 (0.0011) -[2023-11-28 07:26:51,869][87426] Updated weights for policy 1, policy_version 276050 (0.0011) -[2023-11-28 07:26:52,085][87424] Updated weights for policy 0, policy_version 276288 (0.0012) -[2023-11-28 07:26:52,241][87426] Updated weights for policy 1, policy_version 276060 (0.0011) -[2023-11-28 07:26:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141402112. Throughput: 0: 2709.5, 1: 2747.5. Samples: 141417732. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:26:53,445][86177] Avg episode reward: [(0, '-573.400'), (1, '-589.320')] -[2023-11-28 07:26:53,910][87424] Updated weights for policy 0, policy_version 276298 (0.0010) -[2023-11-28 07:26:54,293][87424] Updated weights for policy 0, policy_version 276308 (0.0011) -[2023-11-28 07:26:54,441][87426] Updated weights for policy 1, policy_version 276070 (0.0012) -[2023-11-28 07:26:54,674][87424] Updated weights for policy 0, policy_version 276318 (0.0011) -[2023-11-28 07:26:54,820][87426] Updated weights for policy 1, policy_version 276080 (0.0008) -[2023-11-28 07:26:55,191][87426] Updated weights for policy 1, policy_version 276090 (0.0007) -[2023-11-28 07:26:56,673][87424] Updated weights for policy 0, policy_version 276328 (0.0011) -[2023-11-28 07:26:57,059][87424] Updated weights for policy 0, policy_version 276338 (0.0012) -[2023-11-28 07:26:57,439][87424] Updated weights for policy 0, policy_version 276348 (0.0012) -[2023-11-28 07:26:57,511][87426] Updated weights for policy 1, policy_version 276100 (0.0009) -[2023-11-28 07:26:57,891][87426] Updated weights for policy 1, policy_version 276110 (0.0012) -[2023-11-28 07:26:58,273][87426] Updated weights for policy 1, policy_version 276120 (0.0012) -[2023-11-28 07:26:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 141426688. Throughput: 0: 2731.6, 1: 2787.8. Samples: 141443944. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:26:58,445][86177] Avg episode reward: [(0, '-587.820'), (1, '-583.710')] -[2023-11-28 07:26:59,573][87424] Updated weights for policy 0, policy_version 276358 (0.0011) -[2023-11-28 07:26:59,966][87424] Updated weights for policy 0, policy_version 276368 (0.0009) -[2023-11-28 07:27:00,344][87424] Updated weights for policy 0, policy_version 276378 (0.0007) -[2023-11-28 07:27:00,443][87426] Updated weights for policy 1, policy_version 276130 (0.0012) -[2023-11-28 07:27:00,820][87426] Updated weights for policy 1, policy_version 276140 (0.0011) -[2023-11-28 07:27:01,199][87426] Updated weights for policy 1, policy_version 276150 (0.0012) -[2023-11-28 07:27:01,570][87426] Updated weights for policy 1, policy_version 276160 (0.0012) -[2023-11-28 07:27:02,614][87424] Updated weights for policy 0, policy_version 276388 (0.0010) -[2023-11-28 07:27:02,990][87424] Updated weights for policy 0, policy_version 276398 (0.0011) -[2023-11-28 07:27:03,377][87424] Updated weights for policy 0, policy_version 276408 (0.0011) -[2023-11-28 07:27:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141451264. Throughput: 0: 2753.3, 1: 2784.5. Samples: 141469964. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:03,445][86177] Avg episode reward: [(0, '-590.340'), (1, '-531.200')] -[2023-11-28 07:27:03,563][87426] Updated weights for policy 1, policy_version 276170 (0.0011) -[2023-11-28 07:27:03,933][87426] Updated weights for policy 1, policy_version 276180 (0.0011) -[2023-11-28 07:27:04,312][87426] Updated weights for policy 1, policy_version 276190 (0.0007) -[2023-11-28 07:27:05,321][87424] Updated weights for policy 0, policy_version 276418 (0.0010) -[2023-11-28 07:27:05,696][87424] Updated weights for policy 0, policy_version 276428 (0.0009) -[2023-11-28 07:27:06,076][87424] Updated weights for policy 0, policy_version 276438 (0.0008) -[2023-11-28 07:27:06,401][87426] Updated weights for policy 1, policy_version 276200 (0.0010) -[2023-11-28 07:27:06,461][87424] Updated weights for policy 0, policy_version 276448 (0.0011) -[2023-11-28 07:27:06,770][87426] Updated weights for policy 1, policy_version 276210 (0.0012) -[2023-11-28 07:27:07,153][87426] Updated weights for policy 1, policy_version 276220 (0.0010) -[2023-11-28 07:27:08,272][87424] Updated weights for policy 0, policy_version 276458 (0.0008) -[2023-11-28 07:27:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141484032. Throughput: 0: 2799.7, 1: 2757.1. Samples: 141502884. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:08,445][86177] Avg episode reward: [(0, '-604.210'), (1, '-532.600')] -[2023-11-28 07:27:08,654][87424] Updated weights for policy 0, policy_version 276468 (0.0011) -[2023-11-28 07:27:09,034][87424] Updated weights for policy 0, policy_version 276478 (0.0012) -[2023-11-28 07:27:09,600][87426] Updated weights for policy 1, policy_version 276230 (0.0008) -[2023-11-28 07:27:09,982][87426] Updated weights for policy 1, policy_version 276240 (0.0012) -[2023-11-28 07:27:10,364][87426] Updated weights for policy 1, policy_version 276250 (0.0011) -[2023-11-28 07:27:11,269][87424] Updated weights for policy 0, policy_version 276488 (0.0012) -[2023-11-28 07:27:11,656][87424] Updated weights for policy 0, policy_version 276498 (0.0012) -[2023-11-28 07:27:12,042][87424] Updated weights for policy 0, policy_version 276508 (0.0011) -[2023-11-28 07:27:12,430][87426] Updated weights for policy 1, policy_version 276260 (0.0010) -[2023-11-28 07:27:12,814][87426] Updated weights for policy 1, policy_version 276270 (0.0010) -[2023-11-28 07:27:13,187][87426] Updated weights for policy 1, policy_version 276280 (0.0012) -[2023-11-28 07:27:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141508608. Throughput: 0: 2798.3, 1: 2749.3. Samples: 141527736. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:13,445][86177] Avg episode reward: [(0, '-612.250'), (1, '-522.460')] -[2023-11-28 07:27:14,191][87424] Updated weights for policy 0, policy_version 276518 (0.0012) -[2023-11-28 07:27:14,579][87424] Updated weights for policy 0, policy_version 276528 (0.0012) -[2023-11-28 07:27:14,964][87424] Updated weights for policy 0, policy_version 276538 (0.0011) -[2023-11-28 07:27:15,001][87426] Updated weights for policy 1, policy_version 276290 (0.0011) -[2023-11-28 07:27:15,378][87426] Updated weights for policy 1, policy_version 276300 (0.0008) -[2023-11-28 07:27:15,767][87426] Updated weights for policy 1, policy_version 276310 (0.0010) -[2023-11-28 07:27:16,144][87426] Updated weights for policy 1, policy_version 276320 (0.0009) -[2023-11-28 07:27:17,248][87424] Updated weights for policy 0, policy_version 276548 (0.0010) -[2023-11-28 07:27:17,636][87424] Updated weights for policy 0, policy_version 276558 (0.0012) -[2023-11-28 07:27:18,011][87424] Updated weights for policy 0, policy_version 276568 (0.0012) -[2023-11-28 07:27:18,237][87426] Updated weights for policy 1, policy_version 276330 (0.0011) -[2023-11-28 07:27:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 141541376. Throughput: 0: 2773.4, 1: 2763.6. Samples: 141552208. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:18,445][86177] Avg episode reward: [(0, '-635.410'), (1, '-546.260')] -[2023-11-28 07:27:18,615][87426] Updated weights for policy 1, policy_version 276340 (0.0011) -[2023-11-28 07:27:18,992][87426] Updated weights for policy 1, policy_version 276350 (0.0012) -[2023-11-28 07:27:20,114][87424] Updated weights for policy 0, policy_version 276578 (0.0009) -[2023-11-28 07:27:20,501][87424] Updated weights for policy 0, policy_version 276588 (0.0009) -[2023-11-28 07:27:20,873][87424] Updated weights for policy 0, policy_version 276598 (0.0010) -[2023-11-28 07:27:21,144][87426] Updated weights for policy 1, policy_version 276360 (0.0010) -[2023-11-28 07:27:21,256][87424] Updated weights for policy 0, policy_version 276608 (0.0010) -[2023-11-28 07:27:21,521][87426] Updated weights for policy 1, policy_version 276370 (0.0008) -[2023-11-28 07:27:21,907][87426] Updated weights for policy 1, policy_version 276380 (0.0010) -[2023-11-28 07:27:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141565952. Throughput: 0: 2783.1, 1: 2745.6. Samples: 141584536. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:23,445][86177] Avg episode reward: [(0, '-598.230'), (1, '-552.210')] -[2023-11-28 07:27:23,574][87424] Updated weights for policy 0, policy_version 276618 (0.0012) -[2023-11-28 07:27:23,954][87424] Updated weights for policy 0, policy_version 276628 (0.0008) -[2023-11-28 07:27:24,341][87424] Updated weights for policy 0, policy_version 276638 (0.0007) -[2023-11-28 07:27:24,395][87426] Updated weights for policy 1, policy_version 276390 (0.0008) -[2023-11-28 07:27:24,766][87426] Updated weights for policy 1, policy_version 276400 (0.0012) -[2023-11-28 07:27:25,145][87426] Updated weights for policy 1, policy_version 276410 (0.0012) -[2023-11-28 07:27:26,251][87424] Updated weights for policy 0, policy_version 276648 (0.0007) -[2023-11-28 07:27:26,637][87424] Updated weights for policy 0, policy_version 276658 (0.0007) -[2023-11-28 07:27:27,025][87424] Updated weights for policy 0, policy_version 276668 (0.0007) -[2023-11-28 07:27:27,741][87426] Updated weights for policy 1, policy_version 276420 (0.0010) -[2023-11-28 07:27:28,128][87426] Updated weights for policy 1, policy_version 276430 (0.0008) -[2023-11-28 07:27:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141590528. Throughput: 0: 2789.7, 1: 2709.6. Samples: 141607756. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:28,446][86177] Avg episode reward: [(0, '-596.610'), (1, '-549.310')] -[2023-11-28 07:27:28,494][87426] Updated weights for policy 1, policy_version 276440 (0.0007) -[2023-11-28 07:27:28,965][87424] Updated weights for policy 0, policy_version 276678 (0.0008) -[2023-11-28 07:27:29,346][87424] Updated weights for policy 0, policy_version 276688 (0.0008) -[2023-11-28 07:27:29,729][87424] Updated weights for policy 0, policy_version 276698 (0.0010) -[2023-11-28 07:27:30,887][87426] Updated weights for policy 1, policy_version 276450 (0.0008) -[2023-11-28 07:27:31,265][87426] Updated weights for policy 1, policy_version 276460 (0.0011) -[2023-11-28 07:27:31,652][87426] Updated weights for policy 1, policy_version 276470 (0.0011) -[2023-11-28 07:27:32,023][87426] Updated weights for policy 1, policy_version 276480 (0.0009) -[2023-11-28 07:27:32,136][87424] Updated weights for policy 0, policy_version 276708 (0.0009) -[2023-11-28 07:27:32,510][87424] Updated weights for policy 0, policy_version 276718 (0.0009) -[2023-11-28 07:27:32,897][87424] Updated weights for policy 0, policy_version 276728 (0.0011) -[2023-11-28 07:27:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 141623296. Throughput: 0: 2809.5, 1: 2682.7. Samples: 141632060. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:33,445][86177] Avg episode reward: [(0, '-602.830'), (1, '-590.090')] -[2023-11-28 07:27:34,417][87426] Updated weights for policy 1, policy_version 276490 (0.0012) -[2023-11-28 07:27:34,778][87424] Updated weights for policy 0, policy_version 276738 (0.0009) -[2023-11-28 07:27:34,806][87426] Updated weights for policy 1, policy_version 276500 (0.0012) -[2023-11-28 07:27:35,161][87424] Updated weights for policy 0, policy_version 276748 (0.0010) -[2023-11-28 07:27:35,173][87426] Updated weights for policy 1, policy_version 276510 (0.0012) -[2023-11-28 07:27:35,546][87424] Updated weights for policy 0, policy_version 276758 (0.0008) -[2023-11-28 07:27:35,922][87424] Updated weights for policy 0, policy_version 276768 (0.0007) -[2023-11-28 07:27:37,420][87426] Updated weights for policy 1, policy_version 276520 (0.0010) -[2023-11-28 07:27:37,796][87426] Updated weights for policy 1, policy_version 276530 (0.0009) -[2023-11-28 07:27:38,044][87424] Updated weights for policy 0, policy_version 276778 (0.0012) -[2023-11-28 07:27:38,174][87426] Updated weights for policy 1, policy_version 276540 (0.0009) -[2023-11-28 07:27:38,420][87424] Updated weights for policy 0, policy_version 276788 (0.0010) -[2023-11-28 07:27:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 141647872. Throughput: 0: 2815.0, 1: 2682.9. Samples: 141665140. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:38,445][86177] Avg episode reward: [(0, '-603.530'), (1, '-556.710')] -[2023-11-28 07:27:38,803][87424] Updated weights for policy 0, policy_version 276798 (0.0007) -[2023-11-28 07:27:39,743][87426] Updated weights for policy 1, policy_version 276550 (0.0012) -[2023-11-28 07:27:40,117][87426] Updated weights for policy 1, policy_version 276560 (0.0012) -[2023-11-28 07:27:40,501][87426] Updated weights for policy 1, policy_version 276570 (0.0012) -[2023-11-28 07:27:41,211][87424] Updated weights for policy 0, policy_version 276808 (0.0011) -[2023-11-28 07:27:41,590][87424] Updated weights for policy 0, policy_version 276818 (0.0012) -[2023-11-28 07:27:41,975][87424] Updated weights for policy 0, policy_version 276828 (0.0012) -[2023-11-28 07:27:43,092][87426] Updated weights for policy 1, policy_version 276580 (0.0011) -[2023-11-28 07:27:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141672448. Throughput: 0: 2787.8, 1: 2653.0. Samples: 141688780. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:43,445][86177] Avg episode reward: [(0, '-588.280'), (1, '-559.020')] -[2023-11-28 07:27:43,469][87426] Updated weights for policy 1, policy_version 276590 (0.0010) -[2023-11-28 07:27:43,849][87426] Updated weights for policy 1, policy_version 276600 (0.0008) -[2023-11-28 07:27:44,163][87424] Updated weights for policy 0, policy_version 276838 (0.0010) -[2023-11-28 07:27:44,551][87424] Updated weights for policy 0, policy_version 276848 (0.0007) -[2023-11-28 07:27:44,932][87424] Updated weights for policy 0, policy_version 276858 (0.0008) -[2023-11-28 07:27:46,091][87426] Updated weights for policy 1, policy_version 276610 (0.0009) -[2023-11-28 07:27:46,460][87426] Updated weights for policy 1, policy_version 276620 (0.0012) -[2023-11-28 07:27:46,832][87426] Updated weights for policy 1, policy_version 276630 (0.0012) -[2023-11-28 07:27:47,089][87424] Updated weights for policy 0, policy_version 276868 (0.0009) -[2023-11-28 07:27:47,203][87426] Updated weights for policy 1, policy_version 276640 (0.0011) -[2023-11-28 07:27:47,468][87424] Updated weights for policy 0, policy_version 276878 (0.0007) -[2023-11-28 07:27:47,848][87424] Updated weights for policy 0, policy_version 276888 (0.0010) -[2023-11-28 07:27:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 141705216. Throughput: 0: 2751.1, 1: 2664.2. Samples: 141713652. Policy #0 lag: (min: 31.0, avg: 47.3, max: 63.0) -[2023-11-28 07:27:48,445][86177] Avg episode reward: [(0, '-562.610'), (1, '-528.330')] -[2023-11-28 07:27:49,415][87426] Updated weights for policy 1, policy_version 276650 (0.0010) -[2023-11-28 07:27:49,793][87426] Updated weights for policy 1, policy_version 276660 (0.0011) -[2023-11-28 07:27:50,020][87424] Updated weights for policy 0, policy_version 276898 (0.0008) -[2023-11-28 07:27:50,172][87426] Updated weights for policy 1, policy_version 276670 (0.0011) -[2023-11-28 07:27:50,404][87424] Updated weights for policy 0, policy_version 276908 (0.0012) -[2023-11-28 07:27:50,788][87424] Updated weights for policy 0, policy_version 276918 (0.0012) -[2023-11-28 07:27:51,169][87424] Updated weights for policy 0, policy_version 276928 (0.0012) -[2023-11-28 07:27:52,521][87426] Updated weights for policy 1, policy_version 276680 (0.0012) -[2023-11-28 07:27:52,899][87426] Updated weights for policy 1, policy_version 276690 (0.0012) -[2023-11-28 07:27:53,272][87426] Updated weights for policy 1, policy_version 276700 (0.0011) -[2023-11-28 07:27:53,386][87424] Updated weights for policy 0, policy_version 276938 (0.0015) -[2023-11-28 07:27:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 141729792. Throughput: 0: 2724.9, 1: 2669.3. Samples: 141745624. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:27:53,445][86177] Avg episode reward: [(0, '-561.930'), (1, '-530.920')] -[2023-11-28 07:27:53,766][87424] Updated weights for policy 0, policy_version 276948 (0.0012) -[2023-11-28 07:27:54,151][87424] Updated weights for policy 0, policy_version 276958 (0.0012) -[2023-11-28 07:27:55,477][87426] Updated weights for policy 1, policy_version 276710 (0.0011) -[2023-11-28 07:27:55,862][87426] Updated weights for policy 1, policy_version 276720 (0.0011) -[2023-11-28 07:27:56,245][87426] Updated weights for policy 1, policy_version 276730 (0.0011) -[2023-11-28 07:27:56,246][87424] Updated weights for policy 0, policy_version 276968 (0.0011) -[2023-11-28 07:27:56,627][87424] Updated weights for policy 0, policy_version 276978 (0.0011) -[2023-11-28 07:27:57,002][87424] Updated weights for policy 0, policy_version 276988 (0.0012) -[2023-11-28 07:27:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 141754368. Throughput: 0: 2719.4, 1: 2675.8. Samples: 141770520. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:27:58,445][86177] Avg episode reward: [(0, '-619.840'), (1, '-531.130')] -[2023-11-28 07:27:58,538][87426] Updated weights for policy 1, policy_version 276740 (0.0011) -[2023-11-28 07:27:58,921][87426] Updated weights for policy 1, policy_version 276750 (0.0011) -[2023-11-28 07:27:59,290][87424] Updated weights for policy 0, policy_version 276998 (0.0011) -[2023-11-28 07:27:59,300][87426] Updated weights for policy 1, policy_version 276760 (0.0010) -[2023-11-28 07:27:59,665][87424] Updated weights for policy 0, policy_version 277008 (0.0011) -[2023-11-28 07:28:00,049][87424] Updated weights for policy 0, policy_version 277018 (0.0012) -[2023-11-28 07:28:01,349][87426] Updated weights for policy 1, policy_version 276770 (0.0010) -[2023-11-28 07:28:01,731][87426] Updated weights for policy 1, policy_version 276780 (0.0008) -[2023-11-28 07:28:02,112][87426] Updated weights for policy 1, policy_version 276790 (0.0011) -[2023-11-28 07:28:02,180][87424] Updated weights for policy 0, policy_version 277028 (0.0011) -[2023-11-28 07:28:02,489][87426] Updated weights for policy 1, policy_version 276800 (0.0013) -[2023-11-28 07:28:02,559][87424] Updated weights for policy 0, policy_version 277038 (0.0010) -[2023-11-28 07:28:02,943][87424] Updated weights for policy 0, policy_version 277048 (0.0009) -[2023-11-28 07:28:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 141787136. Throughput: 0: 2752.5, 1: 2675.4. Samples: 141796464. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:03,445][86177] Avg episode reward: [(0, '-625.080'), (1, '-527.330')] -[2023-11-28 07:28:04,476][87426] Updated weights for policy 1, policy_version 276810 (0.0011) -[2023-11-28 07:28:04,854][87424] Updated weights for policy 0, policy_version 277058 (0.0012) -[2023-11-28 07:28:04,857][87426] Updated weights for policy 1, policy_version 276820 (0.0010) -[2023-11-28 07:28:05,231][87426] Updated weights for policy 1, policy_version 276830 (0.0008) -[2023-11-28 07:28:05,238][87424] Updated weights for policy 0, policy_version 277068 (0.0011) -[2023-11-28 07:28:05,612][87424] Updated weights for policy 0, policy_version 277078 (0.0007) -[2023-11-28 07:28:05,991][87424] Updated weights for policy 0, policy_version 277088 (0.0012) -[2023-11-28 07:28:07,477][87426] Updated weights for policy 1, policy_version 276840 (0.0011) -[2023-11-28 07:28:07,805][87424] Updated weights for policy 0, policy_version 277098 (0.0007) -[2023-11-28 07:28:07,861][87426] Updated weights for policy 1, policy_version 276850 (0.0011) -[2023-11-28 07:28:08,192][87424] Updated weights for policy 0, policy_version 277108 (0.0008) -[2023-11-28 07:28:08,240][87426] Updated weights for policy 1, policy_version 276860 (0.0012) -[2023-11-28 07:28:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 141811712. Throughput: 0: 2758.0, 1: 2685.3. Samples: 141829488. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:08,445][86177] Avg episode reward: [(0, '-676.300'), (1, '-526.040')] -[2023-11-28 07:28:08,580][87424] Updated weights for policy 0, policy_version 277118 (0.0007) -[2023-11-28 07:28:10,143][87426] Updated weights for policy 1, policy_version 276870 (0.0012) -[2023-11-28 07:28:10,516][87426] Updated weights for policy 1, policy_version 276880 (0.0012) -[2023-11-28 07:28:10,896][87426] Updated weights for policy 1, policy_version 276890 (0.0010) -[2023-11-28 07:28:10,908][87424] Updated weights for policy 0, policy_version 277128 (0.0010) -[2023-11-28 07:28:11,282][87424] Updated weights for policy 0, policy_version 277138 (0.0008) -[2023-11-28 07:28:11,666][87424] Updated weights for policy 0, policy_version 277148 (0.0009) -[2023-11-28 07:28:13,011][87426] Updated weights for policy 1, policy_version 276900 (0.0012) -[2023-11-28 07:28:13,397][87426] Updated weights for policy 1, policy_version 276910 (0.0011) -[2023-11-28 07:28:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 141836288. Throughput: 0: 2761.9, 1: 2724.4. Samples: 141854636. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:13,445][86177] Avg episode reward: [(0, '-674.310'), (1, '-528.120')] -[2023-11-28 07:28:13,783][87426] Updated weights for policy 1, policy_version 276920 (0.0011) -[2023-11-28 07:28:14,183][87424] Updated weights for policy 0, policy_version 277158 (0.0008) -[2023-11-28 07:28:14,564][87424] Updated weights for policy 0, policy_version 277168 (0.0007) -[2023-11-28 07:28:14,939][87424] Updated weights for policy 0, policy_version 277178 (0.0010) -[2023-11-28 07:28:15,951][87426] Updated weights for policy 1, policy_version 276930 (0.0011) -[2023-11-28 07:28:16,326][87426] Updated weights for policy 1, policy_version 276940 (0.0012) -[2023-11-28 07:28:16,700][87426] Updated weights for policy 1, policy_version 276950 (0.0012) -[2023-11-28 07:28:16,752][87424] Updated weights for policy 0, policy_version 277188 (0.0010) -[2023-11-28 07:28:17,084][87426] Updated weights for policy 1, policy_version 276960 (0.0012) -[2023-11-28 07:28:17,129][87424] Updated weights for policy 0, policy_version 277198 (0.0008) -[2023-11-28 07:28:17,510][87424] Updated weights for policy 0, policy_version 277208 (0.0007) -[2023-11-28 07:28:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 141869056. Throughput: 0: 2739.3, 1: 2749.2. Samples: 141879040. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:18,445][86177] Avg episode reward: [(0, '-617.620'), (1, '-530.880')] -[2023-11-28 07:28:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000277216_70967296.pth... -[2023-11-28 07:28:18,502][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000274656_70311936.pth -[2023-11-28 07:28:18,920][87426] Updated weights for policy 1, policy_version 276970 (0.0011) -[2023-11-28 07:28:19,290][87426] Updated weights for policy 1, policy_version 276980 (0.0011) -[2023-11-28 07:28:19,676][87426] Updated weights for policy 1, policy_version 276990 (0.0009) -[2023-11-28 07:28:19,743][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000276992_70909952.pth... -[2023-11-28 07:28:19,760][87424] Updated weights for policy 0, policy_version 277218 (0.0008) -[2023-11-28 07:28:19,790][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000274432_70254592.pth -[2023-11-28 07:28:20,138][87424] Updated weights for policy 0, policy_version 277228 (0.0012) -[2023-11-28 07:28:20,531][87424] Updated weights for policy 0, policy_version 277238 (0.0011) -[2023-11-28 07:28:20,912][87424] Updated weights for policy 0, policy_version 277248 (0.0011) -[2023-11-28 07:28:21,529][87426] Updated weights for policy 1, policy_version 277000 (0.0010) -[2023-11-28 07:28:21,909][87426] Updated weights for policy 1, policy_version 277010 (0.0009) -[2023-11-28 07:28:22,289][87426] Updated weights for policy 1, policy_version 277020 (0.0010) -[2023-11-28 07:28:23,232][87424] Updated weights for policy 0, policy_version 277258 (0.0011) -[2023-11-28 07:28:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 141893632. Throughput: 0: 2723.6, 1: 2778.8. Samples: 141912744. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:23,445][86177] Avg episode reward: [(0, '-653.230'), (1, '-530.810')] -[2023-11-28 07:28:23,605][87424] Updated weights for policy 0, policy_version 277268 (0.0011) -[2023-11-28 07:28:23,988][87424] Updated weights for policy 0, policy_version 277278 (0.0007) -[2023-11-28 07:28:24,714][87426] Updated weights for policy 1, policy_version 277030 (0.0011) -[2023-11-28 07:28:25,097][87426] Updated weights for policy 1, policy_version 277040 (0.0012) -[2023-11-28 07:28:25,477][87426] Updated weights for policy 1, policy_version 277050 (0.0012) -[2023-11-28 07:28:25,929][87424] Updated weights for policy 0, policy_version 277288 (0.0008) -[2023-11-28 07:28:26,314][87424] Updated weights for policy 0, policy_version 277298 (0.0007) -[2023-11-28 07:28:26,696][87424] Updated weights for policy 0, policy_version 277308 (0.0007) -[2023-11-28 07:28:27,310][87426] Updated weights for policy 1, policy_version 277060 (0.0012) -[2023-11-28 07:28:27,694][87426] Updated weights for policy 1, policy_version 277070 (0.0012) -[2023-11-28 07:28:28,078][87426] Updated weights for policy 1, policy_version 277080 (0.0010) -[2023-11-28 07:28:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 141926400. Throughput: 0: 2762.6, 1: 2778.1. Samples: 141938108. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:28,445][86177] Avg episode reward: [(0, '-670.420'), (1, '-529.430')] -[2023-11-28 07:28:28,629][87424] Updated weights for policy 0, policy_version 277318 (0.0010) -[2023-11-28 07:28:29,012][87424] Updated weights for policy 0, policy_version 277328 (0.0012) -[2023-11-28 07:28:29,397][87424] Updated weights for policy 0, policy_version 277338 (0.0011) -[2023-11-28 07:28:30,296][87426] Updated weights for policy 1, policy_version 277090 (0.0008) -[2023-11-28 07:28:30,678][87426] Updated weights for policy 1, policy_version 277100 (0.0011) -[2023-11-28 07:28:31,055][87426] Updated weights for policy 1, policy_version 277110 (0.0009) -[2023-11-28 07:28:31,436][87426] Updated weights for policy 1, policy_version 277120 (0.0008) -[2023-11-28 07:28:31,764][87424] Updated weights for policy 0, policy_version 277348 (0.0009) -[2023-11-28 07:28:32,159][87424] Updated weights for policy 0, policy_version 277358 (0.0011) -[2023-11-28 07:28:32,545][87424] Updated weights for policy 0, policy_version 277368 (0.0011) -[2023-11-28 07:28:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 141950976. Throughput: 0: 2745.0, 1: 2774.7. Samples: 141962040. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:33,445][86177] Avg episode reward: [(0, '-620.160'), (1, '-553.460')] -[2023-11-28 07:28:33,866][87426] Updated weights for policy 1, policy_version 277130 (0.0011) -[2023-11-28 07:28:34,254][87426] Updated weights for policy 1, policy_version 277140 (0.0011) -[2023-11-28 07:28:34,631][87424] Updated weights for policy 0, policy_version 277378 (0.0010) -[2023-11-28 07:28:34,644][87426] Updated weights for policy 1, policy_version 277150 (0.0011) -[2023-11-28 07:28:35,011][87424] Updated weights for policy 0, policy_version 277388 (0.0012) -[2023-11-28 07:28:35,392][87424] Updated weights for policy 0, policy_version 277398 (0.0012) -[2023-11-28 07:28:35,771][87424] Updated weights for policy 0, policy_version 277408 (0.0011) -[2023-11-28 07:28:36,611][87426] Updated weights for policy 1, policy_version 277160 (0.0012) -[2023-11-28 07:28:36,994][87426] Updated weights for policy 1, policy_version 277170 (0.0012) -[2023-11-28 07:28:37,368][87426] Updated weights for policy 1, policy_version 277180 (0.0012) -[2023-11-28 07:28:37,749][87424] Updated weights for policy 0, policy_version 277418 (0.0010) -[2023-11-28 07:28:38,132][87424] Updated weights for policy 0, policy_version 277428 (0.0012) -[2023-11-28 07:28:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 141975552. Throughput: 0: 2766.6, 1: 2786.3. Samples: 141995504. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:38,445][86177] Avg episode reward: [(0, '-663.400'), (1, '-549.390')] -[2023-11-28 07:28:38,513][87424] Updated weights for policy 0, policy_version 277438 (0.0009) -[2023-11-28 07:28:39,311][87426] Updated weights for policy 1, policy_version 277190 (0.0012) -[2023-11-28 07:28:39,698][87426] Updated weights for policy 1, policy_version 277200 (0.0012) -[2023-11-28 07:28:40,066][87426] Updated weights for policy 1, policy_version 277210 (0.0011) -[2023-11-28 07:28:40,563][87424] Updated weights for policy 0, policy_version 277448 (0.0011) -[2023-11-28 07:28:40,940][87424] Updated weights for policy 0, policy_version 277458 (0.0011) -[2023-11-28 07:28:41,322][87424] Updated weights for policy 0, policy_version 277468 (0.0011) -[2023-11-28 07:28:42,583][87426] Updated weights for policy 1, policy_version 277220 (0.0011) -[2023-11-28 07:28:42,959][87426] Updated weights for policy 1, policy_version 277230 (0.0012) -[2023-11-28 07:28:43,340][87426] Updated weights for policy 1, policy_version 277240 (0.0011) -[2023-11-28 07:28:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142000128. Throughput: 0: 2766.2, 1: 2787.3. Samples: 142020428. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:43,445][86177] Avg episode reward: [(0, '-652.840'), (1, '-554.740')] -[2023-11-28 07:28:43,559][87424] Updated weights for policy 0, policy_version 277478 (0.0012) -[2023-11-28 07:28:43,947][87424] Updated weights for policy 0, policy_version 277488 (0.0010) -[2023-11-28 07:28:44,331][87424] Updated weights for policy 0, policy_version 277498 (0.0007) -[2023-11-28 07:28:45,110][87426] Updated weights for policy 1, policy_version 277250 (0.0010) -[2023-11-28 07:28:45,494][87426] Updated weights for policy 1, policy_version 277260 (0.0012) -[2023-11-28 07:28:45,868][87426] Updated weights for policy 1, policy_version 277270 (0.0012) -[2023-11-28 07:28:46,246][87426] Updated weights for policy 1, policy_version 277280 (0.0012) -[2023-11-28 07:28:46,554][87424] Updated weights for policy 0, policy_version 277508 (0.0011) -[2023-11-28 07:28:46,946][87424] Updated weights for policy 0, policy_version 277518 (0.0011) -[2023-11-28 07:28:47,326][87424] Updated weights for policy 0, policy_version 277528 (0.0012) -[2023-11-28 07:28:48,024][87426] Updated weights for policy 1, policy_version 277290 (0.0011) -[2023-11-28 07:28:48,404][87426] Updated weights for policy 1, policy_version 277300 (0.0008) -[2023-11-28 07:28:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142032896. Throughput: 0: 2749.6, 1: 2803.3. Samples: 142046344. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:48,445][86177] Avg episode reward: [(0, '-618.080'), (1, '-550.580')] -[2023-11-28 07:28:48,784][87426] Updated weights for policy 1, policy_version 277310 (0.0007) -[2023-11-28 07:28:49,163][87424] Updated weights for policy 0, policy_version 277538 (0.0011) -[2023-11-28 07:28:49,544][87424] Updated weights for policy 0, policy_version 277548 (0.0011) -[2023-11-28 07:28:49,932][87424] Updated weights for policy 0, policy_version 277558 (0.0012) -[2023-11-28 07:28:50,310][87424] Updated weights for policy 0, policy_version 277568 (0.0012) -[2023-11-28 07:28:50,741][87426] Updated weights for policy 1, policy_version 277320 (0.0011) -[2023-11-28 07:28:51,119][87426] Updated weights for policy 1, policy_version 277330 (0.0012) -[2023-11-28 07:28:51,492][87426] Updated weights for policy 1, policy_version 277340 (0.0011) -[2023-11-28 07:28:52,902][87424] Updated weights for policy 0, policy_version 277578 (0.0009) -[2023-11-28 07:28:53,280][87424] Updated weights for policy 0, policy_version 277588 (0.0009) -[2023-11-28 07:28:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142057472. Throughput: 0: 2732.1, 1: 2836.0. Samples: 142080052. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:53,445][86177] Avg episode reward: [(0, '-620.080'), (1, '-520.330')] -[2023-11-28 07:28:53,661][87424] Updated weights for policy 0, policy_version 277598 (0.0012) -[2023-11-28 07:28:53,772][87426] Updated weights for policy 1, policy_version 277350 (0.0009) -[2023-11-28 07:28:54,157][87426] Updated weights for policy 1, policy_version 277360 (0.0008) -[2023-11-28 07:28:54,536][87426] Updated weights for policy 1, policy_version 277370 (0.0008) -[2023-11-28 07:28:55,985][87424] Updated weights for policy 0, policy_version 277608 (0.0008) -[2023-11-28 07:28:56,373][87424] Updated weights for policy 0, policy_version 277618 (0.0007) -[2023-11-28 07:28:56,574][87426] Updated weights for policy 1, policy_version 277380 (0.0009) -[2023-11-28 07:28:56,755][87424] Updated weights for policy 0, policy_version 277628 (0.0009) -[2023-11-28 07:28:56,959][87426] Updated weights for policy 1, policy_version 277390 (0.0010) -[2023-11-28 07:28:57,335][87426] Updated weights for policy 1, policy_version 277400 (0.0007) -[2023-11-28 07:28:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 142090240. Throughput: 0: 2722.3, 1: 2815.4. Samples: 142103832. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:28:58,445][86177] Avg episode reward: [(0, '-602.260'), (1, '-518.240')] -[2023-11-28 07:28:58,447][87424] Updated weights for policy 0, policy_version 277638 (0.0009) -[2023-11-28 07:28:58,833][87424] Updated weights for policy 0, policy_version 277648 (0.0007) -[2023-11-28 07:28:59,203][87424] Updated weights for policy 0, policy_version 277658 (0.0008) -[2023-11-28 07:28:59,881][87426] Updated weights for policy 1, policy_version 277410 (0.0008) -[2023-11-28 07:29:00,242][87426] Updated weights for policy 1, policy_version 277420 (0.0008) -[2023-11-28 07:29:00,623][87426] Updated weights for policy 1, policy_version 277430 (0.0010) -[2023-11-28 07:29:00,998][87426] Updated weights for policy 1, policy_version 277440 (0.0011) -[2023-11-28 07:29:01,339][87424] Updated weights for policy 0, policy_version 277668 (0.0008) -[2023-11-28 07:29:01,716][87424] Updated weights for policy 0, policy_version 277678 (0.0008) -[2023-11-28 07:29:02,098][87424] Updated weights for policy 0, policy_version 277688 (0.0011) -[2023-11-28 07:29:03,131][87426] Updated weights for policy 1, policy_version 277450 (0.0012) -[2023-11-28 07:29:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142114816. Throughput: 0: 2744.4, 1: 2786.1. Samples: 142127912. Policy #0 lag: (min: 19.0, avg: 44.6, max: 78.0) -[2023-11-28 07:29:03,445][86177] Avg episode reward: [(0, '-641.650'), (1, '-527.980')] -[2023-11-28 07:29:03,508][87426] Updated weights for policy 1, policy_version 277460 (0.0012) -[2023-11-28 07:29:03,874][87426] Updated weights for policy 1, policy_version 277470 (0.0012) -[2023-11-28 07:29:04,195][87424] Updated weights for policy 0, policy_version 277698 (0.0012) -[2023-11-28 07:29:04,587][87424] Updated weights for policy 0, policy_version 277708 (0.0012) -[2023-11-28 07:29:04,961][87424] Updated weights for policy 0, policy_version 277718 (0.0012) -[2023-11-28 07:29:05,333][87424] Updated weights for policy 0, policy_version 277728 (0.0012) -[2023-11-28 07:29:05,949][87426] Updated weights for policy 1, policy_version 277480 (0.0012) -[2023-11-28 07:29:06,342][87426] Updated weights for policy 1, policy_version 277490 (0.0012) -[2023-11-28 07:29:06,716][87426] Updated weights for policy 1, policy_version 277500 (0.0008) -[2023-11-28 07:29:07,841][87424] Updated weights for policy 0, policy_version 277738 (0.0008) -[2023-11-28 07:29:08,225][87424] Updated weights for policy 0, policy_version 277748 (0.0007) -[2023-11-28 07:29:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142139392. Throughput: 0: 2748.9, 1: 2766.7. Samples: 142160944. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:08,445][86177] Avg episode reward: [(0, '-652.450'), (1, '-530.440')] -[2023-11-28 07:29:08,606][87424] Updated weights for policy 0, policy_version 277758 (0.0009) -[2023-11-28 07:29:08,659][87426] Updated weights for policy 1, policy_version 277510 (0.0010) -[2023-11-28 07:29:09,038][87426] Updated weights for policy 1, policy_version 277520 (0.0011) -[2023-11-28 07:29:09,420][87426] Updated weights for policy 1, policy_version 277530 (0.0012) -[2023-11-28 07:29:11,082][87424] Updated weights for policy 0, policy_version 277768 (0.0009) -[2023-11-28 07:29:11,462][87424] Updated weights for policy 0, policy_version 277778 (0.0009) -[2023-11-28 07:29:11,847][87424] Updated weights for policy 0, policy_version 277788 (0.0011) -[2023-11-28 07:29:12,048][87426] Updated weights for policy 1, policy_version 277540 (0.0011) -[2023-11-28 07:29:12,428][87426] Updated weights for policy 1, policy_version 277550 (0.0011) -[2023-11-28 07:29:12,805][87426] Updated weights for policy 1, policy_version 277560 (0.0011) -[2023-11-28 07:29:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 142172160. Throughput: 0: 2715.1, 1: 2754.8. Samples: 142184252. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:13,445][86177] Avg episode reward: [(0, '-651.210'), (1, '-530.610')] -[2023-11-28 07:29:13,729][87424] Updated weights for policy 0, policy_version 277798 (0.0011) -[2023-11-28 07:29:14,113][87424] Updated weights for policy 0, policy_version 277808 (0.0012) -[2023-11-28 07:29:14,487][87424] Updated weights for policy 0, policy_version 277818 (0.0011) -[2023-11-28 07:29:15,234][87426] Updated weights for policy 1, policy_version 277570 (0.0011) -[2023-11-28 07:29:15,608][87426] Updated weights for policy 1, policy_version 277580 (0.0012) -[2023-11-28 07:29:15,989][87426] Updated weights for policy 1, policy_version 277590 (0.0011) -[2023-11-28 07:29:16,371][87426] Updated weights for policy 1, policy_version 277600 (0.0012) -[2023-11-28 07:29:16,568][87424] Updated weights for policy 0, policy_version 277828 (0.0008) -[2023-11-28 07:29:16,950][87424] Updated weights for policy 0, policy_version 277838 (0.0008) -[2023-11-28 07:29:17,353][87424] Updated weights for policy 0, policy_version 277848 (0.0011) -[2023-11-28 07:29:18,115][87426] Updated weights for policy 1, policy_version 277610 (0.0012) -[2023-11-28 07:29:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142196736. Throughput: 0: 2743.6, 1: 2742.8. Samples: 142208932. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:18,446][86177] Avg episode reward: [(0, '-619.660'), (1, '-530.210')] -[2023-11-28 07:29:18,504][87426] Updated weights for policy 1, policy_version 277620 (0.0011) -[2023-11-28 07:29:18,882][87426] Updated weights for policy 1, policy_version 277630 (0.0013) -[2023-11-28 07:29:19,132][87424] Updated weights for policy 0, policy_version 277858 (0.0011) -[2023-11-28 07:29:19,510][87424] Updated weights for policy 0, policy_version 277868 (0.0012) -[2023-11-28 07:29:19,913][87424] Updated weights for policy 0, policy_version 277878 (0.0012) -[2023-11-28 07:29:20,299][87424] Updated weights for policy 0, policy_version 277888 (0.0012) -[2023-11-28 07:29:21,308][87426] Updated weights for policy 1, policy_version 277640 (0.0012) -[2023-11-28 07:29:21,690][87426] Updated weights for policy 1, policy_version 277650 (0.0012) -[2023-11-28 07:29:22,060][87426] Updated weights for policy 1, policy_version 277660 (0.0012) -[2023-11-28 07:29:22,562][87424] Updated weights for policy 0, policy_version 277898 (0.0012) -[2023-11-28 07:29:22,950][87424] Updated weights for policy 0, policy_version 277908 (0.0012) -[2023-11-28 07:29:23,340][87424] Updated weights for policy 0, policy_version 277918 (0.0011) -[2023-11-28 07:29:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 142229504. Throughput: 0: 2734.6, 1: 2753.0. Samples: 142242444. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:23,445][86177] Avg episode reward: [(0, '-572.220'), (1, '-516.770')] -[2023-11-28 07:29:24,290][87426] Updated weights for policy 1, policy_version 277670 (0.0011) -[2023-11-28 07:29:24,652][87426] Updated weights for policy 1, policy_version 277680 (0.0008) -[2023-11-28 07:29:25,033][87426] Updated weights for policy 1, policy_version 277690 (0.0007) -[2023-11-28 07:29:25,329][87424] Updated weights for policy 0, policy_version 277928 (0.0008) -[2023-11-28 07:29:25,712][87424] Updated weights for policy 0, policy_version 277938 (0.0008) -[2023-11-28 07:29:26,088][87424] Updated weights for policy 0, policy_version 277948 (0.0012) -[2023-11-28 07:29:27,057][87426] Updated weights for policy 1, policy_version 277700 (0.0009) -[2023-11-28 07:29:27,440][87426] Updated weights for policy 1, policy_version 277710 (0.0007) -[2023-11-28 07:29:27,781][87424] Updated weights for policy 0, policy_version 277958 (0.0010) -[2023-11-28 07:29:27,817][87426] Updated weights for policy 1, policy_version 277720 (0.0007) -[2023-11-28 07:29:28,166][87424] Updated weights for policy 0, policy_version 277968 (0.0007) -[2023-11-28 07:29:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 142254080. Throughput: 0: 2750.1, 1: 2730.3. Samples: 142267048. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:28,446][86177] Avg episode reward: [(0, '-571.560'), (1, '-518.150')] -[2023-11-28 07:29:28,550][87424] Updated weights for policy 0, policy_version 277978 (0.0008) -[2023-11-28 07:29:30,297][87426] Updated weights for policy 1, policy_version 277730 (0.0008) -[2023-11-28 07:29:30,667][87426] Updated weights for policy 1, policy_version 277740 (0.0012) -[2023-11-28 07:29:30,772][87424] Updated weights for policy 0, policy_version 277988 (0.0009) -[2023-11-28 07:29:31,050][87426] Updated weights for policy 1, policy_version 277750 (0.0011) -[2023-11-28 07:29:31,154][87424] Updated weights for policy 0, policy_version 277998 (0.0012) -[2023-11-28 07:29:31,424][87426] Updated weights for policy 1, policy_version 277760 (0.0007) -[2023-11-28 07:29:31,539][87424] Updated weights for policy 0, policy_version 278008 (0.0012) -[2023-11-28 07:29:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142278656. Throughput: 0: 2743.1, 1: 2694.0. Samples: 142291012. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:33,445][86177] Avg episode reward: [(0, '-608.750'), (1, '-521.280')] -[2023-11-28 07:29:33,526][87426] Updated weights for policy 1, policy_version 277770 (0.0008) -[2023-11-28 07:29:33,676][87424] Updated weights for policy 0, policy_version 278018 (0.0010) -[2023-11-28 07:29:33,910][87426] Updated weights for policy 1, policy_version 277780 (0.0009) -[2023-11-28 07:29:34,057][87424] Updated weights for policy 0, policy_version 278028 (0.0007) -[2023-11-28 07:29:34,280][87426] Updated weights for policy 1, policy_version 277790 (0.0011) -[2023-11-28 07:29:34,441][87424] Updated weights for policy 0, policy_version 278038 (0.0011) -[2023-11-28 07:29:34,817][87424] Updated weights for policy 0, policy_version 278048 (0.0011) -[2023-11-28 07:29:35,996][87426] Updated weights for policy 1, policy_version 277800 (0.0008) -[2023-11-28 07:29:36,388][87426] Updated weights for policy 1, policy_version 277810 (0.0007) -[2023-11-28 07:29:36,762][87426] Updated weights for policy 1, policy_version 277820 (0.0008) -[2023-11-28 07:29:37,270][87424] Updated weights for policy 0, policy_version 278058 (0.0012) -[2023-11-28 07:29:37,646][87424] Updated weights for policy 0, policy_version 278068 (0.0011) -[2023-11-28 07:29:38,031][87424] Updated weights for policy 0, policy_version 278078 (0.0010) -[2023-11-28 07:29:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 142311424. Throughput: 0: 2745.1, 1: 2664.4. Samples: 142323480. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:38,445][86177] Avg episode reward: [(0, '-579.040'), (1, '-522.480')] -[2023-11-28 07:29:39,304][87426] Updated weights for policy 1, policy_version 277830 (0.0008) -[2023-11-28 07:29:39,680][87426] Updated weights for policy 1, policy_version 277840 (0.0007) -[2023-11-28 07:29:40,057][87426] Updated weights for policy 1, policy_version 277850 (0.0009) -[2023-11-28 07:29:40,235][87424] Updated weights for policy 0, policy_version 278088 (0.0009) -[2023-11-28 07:29:40,615][87424] Updated weights for policy 0, policy_version 278098 (0.0009) -[2023-11-28 07:29:41,001][87424] Updated weights for policy 0, policy_version 278108 (0.0008) -[2023-11-28 07:29:42,274][87426] Updated weights for policy 1, policy_version 277860 (0.0012) -[2023-11-28 07:29:42,651][87426] Updated weights for policy 1, policy_version 277870 (0.0012) -[2023-11-28 07:29:43,018][87426] Updated weights for policy 1, policy_version 277880 (0.0010) -[2023-11-28 07:29:43,080][87424] Updated weights for policy 0, policy_version 278118 (0.0010) -[2023-11-28 07:29:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 142336000. Throughput: 0: 2742.9, 1: 2677.9. Samples: 142347768. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:43,445][86177] Avg episode reward: [(0, '-585.780'), (1, '-522.280')] -[2023-11-28 07:29:43,459][87424] Updated weights for policy 0, policy_version 278128 (0.0008) -[2023-11-28 07:29:43,840][87424] Updated weights for policy 0, policy_version 278138 (0.0008) -[2023-11-28 07:29:45,485][87426] Updated weights for policy 1, policy_version 277890 (0.0011) -[2023-11-28 07:29:45,858][87426] Updated weights for policy 1, policy_version 277900 (0.0008) -[2023-11-28 07:29:46,237][87426] Updated weights for policy 1, policy_version 277910 (0.0011) -[2023-11-28 07:29:46,259][87424] Updated weights for policy 0, policy_version 278148 (0.0010) -[2023-11-28 07:29:46,617][87426] Updated weights for policy 1, policy_version 277920 (0.0011) -[2023-11-28 07:29:46,639][87424] Updated weights for policy 0, policy_version 278158 (0.0009) -[2023-11-28 07:29:47,021][87424] Updated weights for policy 0, policy_version 278168 (0.0007) -[2023-11-28 07:29:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.7). Total num frames: 142360576. Throughput: 0: 2733.3, 1: 2711.7. Samples: 142372940. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:48,445][86177] Avg episode reward: [(0, '-594.000'), (1, '-522.070')] -[2023-11-28 07:29:48,455][87426] Updated weights for policy 1, policy_version 277930 (0.0011) -[2023-11-28 07:29:48,829][87426] Updated weights for policy 1, policy_version 277940 (0.0011) -[2023-11-28 07:29:49,210][87426] Updated weights for policy 1, policy_version 277950 (0.0009) -[2023-11-28 07:29:49,246][87424] Updated weights for policy 0, policy_version 278178 (0.0008) -[2023-11-28 07:29:49,625][87424] Updated weights for policy 0, policy_version 278188 (0.0012) -[2023-11-28 07:29:50,009][87424] Updated weights for policy 0, policy_version 278198 (0.0012) -[2023-11-28 07:29:50,394][87424] Updated weights for policy 0, policy_version 278208 (0.0012) -[2023-11-28 07:29:51,360][87426] Updated weights for policy 1, policy_version 277960 (0.0010) -[2023-11-28 07:29:51,730][87426] Updated weights for policy 1, policy_version 277970 (0.0010) -[2023-11-28 07:29:52,116][87426] Updated weights for policy 1, policy_version 277980 (0.0012) -[2023-11-28 07:29:52,878][87424] Updated weights for policy 0, policy_version 278218 (0.0012) -[2023-11-28 07:29:53,267][87424] Updated weights for policy 0, policy_version 278228 (0.0011) -[2023-11-28 07:29:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 142385152. Throughput: 0: 2723.7, 1: 2716.7. Samples: 142405760. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:53,445][86177] Avg episode reward: [(0, '-610.190'), (1, '-517.190')] -[2023-11-28 07:29:53,633][87424] Updated weights for policy 0, policy_version 278238 (0.0011) -[2023-11-28 07:29:54,443][87426] Updated weights for policy 1, policy_version 277990 (0.0012) -[2023-11-28 07:29:54,820][87426] Updated weights for policy 1, policy_version 278000 (0.0012) -[2023-11-28 07:29:55,206][87426] Updated weights for policy 1, policy_version 278010 (0.0012) -[2023-11-28 07:29:56,014][87424] Updated weights for policy 0, policy_version 278248 (0.0011) -[2023-11-28 07:29:56,410][87424] Updated weights for policy 0, policy_version 278258 (0.0007) -[2023-11-28 07:29:56,791][87424] Updated weights for policy 0, policy_version 278268 (0.0007) -[2023-11-28 07:29:56,902][87426] Updated weights for policy 1, policy_version 278020 (0.0011) -[2023-11-28 07:29:57,294][87426] Updated weights for policy 1, policy_version 278030 (0.0012) -[2023-11-28 07:29:57,672][87426] Updated weights for policy 1, policy_version 278040 (0.0008) -[2023-11-28 07:29:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 142417920. Throughput: 0: 2747.3, 1: 2759.1. Samples: 142432040. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:29:58,445][86177] Avg episode reward: [(0, '-595.800'), (1, '-522.960')] -[2023-11-28 07:29:58,609][87424] Updated weights for policy 0, policy_version 278278 (0.0010) -[2023-11-28 07:29:58,989][87424] Updated weights for policy 0, policy_version 278288 (0.0012) -[2023-11-28 07:29:59,378][87424] Updated weights for policy 0, policy_version 278298 (0.0012) -[2023-11-28 07:29:59,652][87426] Updated weights for policy 1, policy_version 278050 (0.0008) -[2023-11-28 07:30:00,035][87426] Updated weights for policy 1, policy_version 278060 (0.0008) -[2023-11-28 07:30:00,414][87426] Updated weights for policy 1, policy_version 278070 (0.0008) -[2023-11-28 07:30:00,794][87426] Updated weights for policy 1, policy_version 278080 (0.0012) -[2023-11-28 07:30:01,296][87424] Updated weights for policy 0, policy_version 278308 (0.0012) -[2023-11-28 07:30:01,677][87424] Updated weights for policy 0, policy_version 278318 (0.0011) -[2023-11-28 07:30:02,053][87424] Updated weights for policy 0, policy_version 278328 (0.0011) -[2023-11-28 07:30:02,565][87426] Updated weights for policy 1, policy_version 278090 (0.0011) -[2023-11-28 07:30:02,941][87426] Updated weights for policy 1, policy_version 278100 (0.0011) -[2023-11-28 07:30:03,310][87426] Updated weights for policy 1, policy_version 278110 (0.0011) -[2023-11-28 07:30:03,445][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 142450688. Throughput: 0: 2726.4, 1: 2789.3. Samples: 142457140. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:30:03,446][86177] Avg episode reward: [(0, '-629.330'), (1, '-522.400')] -[2023-11-28 07:30:04,409][87424] Updated weights for policy 0, policy_version 278338 (0.0012) -[2023-11-28 07:30:04,793][87424] Updated weights for policy 0, policy_version 278348 (0.0012) -[2023-11-28 07:30:05,177][87424] Updated weights for policy 0, policy_version 278358 (0.0012) -[2023-11-28 07:30:05,559][87424] Updated weights for policy 0, policy_version 278368 (0.0012) -[2023-11-28 07:30:05,907][87426] Updated weights for policy 1, policy_version 278120 (0.0012) -[2023-11-28 07:30:06,288][87426] Updated weights for policy 1, policy_version 278130 (0.0012) -[2023-11-28 07:30:06,660][87426] Updated weights for policy 1, policy_version 278140 (0.0012) -[2023-11-28 07:30:08,049][87424] Updated weights for policy 0, policy_version 278378 (0.0012) -[2023-11-28 07:30:08,425][87424] Updated weights for policy 0, policy_version 278388 (0.0012) -[2023-11-28 07:30:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 142467072. Throughput: 0: 2714.4, 1: 2772.9. Samples: 142489372. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:30:08,445][86177] Avg episode reward: [(0, '-658.550'), (1, '-571.100')] -[2023-11-28 07:30:08,651][87426] Updated weights for policy 1, policy_version 278150 (0.0011) -[2023-11-28 07:30:08,800][87424] Updated weights for policy 0, policy_version 278398 (0.0010) -[2023-11-28 07:30:09,026][87426] Updated weights for policy 1, policy_version 278160 (0.0012) -[2023-11-28 07:30:09,418][87426] Updated weights for policy 1, policy_version 278170 (0.0011) -[2023-11-28 07:30:10,970][87424] Updated weights for policy 0, policy_version 278408 (0.0011) -[2023-11-28 07:30:11,346][87424] Updated weights for policy 0, policy_version 278418 (0.0011) -[2023-11-28 07:30:11,393][87426] Updated weights for policy 1, policy_version 278180 (0.0010) -[2023-11-28 07:30:11,741][87424] Updated weights for policy 0, policy_version 278428 (0.0011) -[2023-11-28 07:30:11,774][87426] Updated weights for policy 1, policy_version 278190 (0.0011) -[2023-11-28 07:30:12,145][87426] Updated weights for policy 1, policy_version 278200 (0.0010) -[2023-11-28 07:30:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 142499840. Throughput: 0: 2701.0, 1: 2775.1. Samples: 142513472. Policy #0 lag: (min: 11.0, avg: 39.3, max: 75.0) -[2023-11-28 07:30:13,445][86177] Avg episode reward: [(0, '-639.280'), (1, '-592.850')] -[2023-11-28 07:30:13,738][87424] Updated weights for policy 0, policy_version 278438 (0.0010) -[2023-11-28 07:30:14,120][87424] Updated weights for policy 0, policy_version 278448 (0.0009) -[2023-11-28 07:30:14,155][87426] Updated weights for policy 1, policy_version 278210 (0.0010) -[2023-11-28 07:30:14,500][87424] Updated weights for policy 0, policy_version 278458 (0.0012) -[2023-11-28 07:30:14,530][87426] Updated weights for policy 1, policy_version 278220 (0.0008) -[2023-11-28 07:30:14,907][87426] Updated weights for policy 1, policy_version 278230 (0.0007) -[2023-11-28 07:30:15,286][87426] Updated weights for policy 1, policy_version 278240 (0.0008) -[2023-11-28 07:30:17,094][87424] Updated weights for policy 0, policy_version 278468 (0.0010) -[2023-11-28 07:30:17,257][87426] Updated weights for policy 1, policy_version 278250 (0.0007) -[2023-11-28 07:30:17,473][87424] Updated weights for policy 0, policy_version 278478 (0.0011) -[2023-11-28 07:30:17,637][87426] Updated weights for policy 1, policy_version 278260 (0.0008) -[2023-11-28 07:30:17,856][87424] Updated weights for policy 0, policy_version 278488 (0.0011) -[2023-11-28 07:30:18,020][87426] Updated weights for policy 1, policy_version 278270 (0.0009) -[2023-11-28 07:30:18,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 142532608. Throughput: 0: 2680.3, 1: 2786.4. Samples: 142537016. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:30:18,445][86177] Avg episode reward: [(0, '-685.300'), (1, '-622.220')] -[2023-11-28 07:30:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000278272_71237632.pth... -[2023-11-28 07:30:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000278496_71294976.pth... -[2023-11-28 07:30:18,488][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000275680_70574080.pth -[2023-11-28 07:30:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000275936_70639616.pth -[2023-11-28 07:30:20,313][87426] Updated weights for policy 1, policy_version 278280 (0.0010) -[2023-11-28 07:30:20,471][87424] Updated weights for policy 0, policy_version 278498 (0.0009) -[2023-11-28 07:30:20,684][87426] Updated weights for policy 1, policy_version 278290 (0.0010) -[2023-11-28 07:30:20,848][87424] Updated weights for policy 0, policy_version 278508 (0.0007) -[2023-11-28 07:30:21,065][87426] Updated weights for policy 1, policy_version 278300 (0.0009) -[2023-11-28 07:30:21,229][87424] Updated weights for policy 0, policy_version 278518 (0.0009) -[2023-11-28 07:30:21,635][87424] Updated weights for policy 0, policy_version 278528 (0.0011) -[2023-11-28 07:30:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 142548992. Throughput: 0: 2651.3, 1: 2799.7. Samples: 142568776. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:30:23,445][86177] Avg episode reward: [(0, '-642.820'), (1, '-629.880')] -[2023-11-28 07:30:23,716][87426] Updated weights for policy 1, policy_version 278310 (0.0009) -[2023-11-28 07:30:23,835][87424] Updated weights for policy 0, policy_version 278538 (0.0009) -[2023-11-28 07:30:24,094][87426] Updated weights for policy 1, policy_version 278320 (0.0007) -[2023-11-28 07:30:24,217][87424] Updated weights for policy 0, policy_version 278548 (0.0011) -[2023-11-28 07:30:24,469][87426] Updated weights for policy 1, policy_version 278330 (0.0008) -[2023-11-28 07:30:24,605][87424] Updated weights for policy 0, policy_version 278558 (0.0010) -[2023-11-28 07:30:26,806][87424] Updated weights for policy 0, policy_version 278568 (0.0011) -[2023-11-28 07:30:26,990][87426] Updated weights for policy 1, policy_version 278340 (0.0007) -[2023-11-28 07:30:27,189][87424] Updated weights for policy 0, policy_version 278578 (0.0011) -[2023-11-28 07:30:27,364][87426] Updated weights for policy 1, policy_version 278350 (0.0007) -[2023-11-28 07:30:27,573][87424] Updated weights for policy 0, policy_version 278588 (0.0012) -[2023-11-28 07:30:27,740][87426] Updated weights for policy 1, policy_version 278360 (0.0007) -[2023-11-28 07:30:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5498.4). Total num frames: 142581760. Throughput: 0: 2662.6, 1: 2772.7. Samples: 142592356. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:30:28,445][86177] Avg episode reward: [(0, '-616.960'), (1, '-580.100')] -[2023-11-28 07:30:29,288][87424] Updated weights for policy 0, policy_version 278598 (0.0010) -[2023-11-28 07:30:29,660][87424] Updated weights for policy 0, policy_version 278608 (0.0008) -[2023-11-28 07:30:30,045][87424] Updated weights for policy 0, policy_version 278618 (0.0008) -[2023-11-28 07:30:30,299][87426] Updated weights for policy 1, policy_version 278370 (0.0008) -[2023-11-28 07:30:30,669][87426] Updated weights for policy 1, policy_version 278380 (0.0009) -[2023-11-28 07:30:31,047][87426] Updated weights for policy 1, policy_version 278390 (0.0007) -[2023-11-28 07:30:31,436][87426] Updated weights for policy 1, policy_version 278400 (0.0007) -[2023-11-28 07:30:31,940][87424] Updated weights for policy 0, policy_version 278628 (0.0011) -[2023-11-28 07:30:32,318][87424] Updated weights for policy 0, policy_version 278638 (0.0012) -[2023-11-28 07:30:32,702][87424] Updated weights for policy 0, policy_version 278648 (0.0008) -[2023-11-28 07:30:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142606336. Throughput: 0: 2694.8, 1: 2740.4. Samples: 142617524. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:30:33,445][86177] Avg episode reward: [(0, '-584.650'), (1, '-559.330')] -[2023-11-28 07:30:33,564][87426] Updated weights for policy 1, policy_version 278410 (0.0012) -[2023-11-28 07:30:33,943][87426] Updated weights for policy 1, policy_version 278420 (0.0012) -[2023-11-28 07:30:34,326][87426] Updated weights for policy 1, policy_version 278430 (0.0008) -[2023-11-28 07:30:34,378][87424] Updated weights for policy 0, policy_version 278658 (0.0010) -[2023-11-28 07:30:34,770][87424] Updated weights for policy 0, policy_version 278668 (0.0012) -[2023-11-28 07:30:35,150][87424] Updated weights for policy 0, policy_version 278678 (0.0012) -[2023-11-28 07:30:35,528][87424] Updated weights for policy 0, policy_version 278688 (0.0012) -[2023-11-28 07:30:36,816][87426] Updated weights for policy 1, policy_version 278440 (0.0009) -[2023-11-28 07:30:37,193][87426] Updated weights for policy 1, policy_version 278450 (0.0011) -[2023-11-28 07:30:37,584][87426] Updated weights for policy 1, policy_version 278460 (0.0012) -[2023-11-28 07:30:37,913][87424] Updated weights for policy 0, policy_version 278698 (0.0012) -[2023-11-28 07:30:38,289][87424] Updated weights for policy 0, policy_version 278708 (0.0012) -[2023-11-28 07:30:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5498.4). Total num frames: 142630912. Throughput: 0: 2707.0, 1: 2709.2. Samples: 142649492. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:30:38,445][86177] Avg episode reward: [(0, '-612.180'), (1, '-580.160')] -[2023-11-28 07:30:38,672][87424] Updated weights for policy 0, policy_version 278718 (0.0011) -[2023-11-28 07:30:39,407][87426] Updated weights for policy 1, policy_version 278470 (0.0011) -[2023-11-28 07:30:39,781][87426] Updated weights for policy 1, policy_version 278480 (0.0012) -[2023-11-28 07:30:40,164][87426] Updated weights for policy 1, policy_version 278490 (0.0012) -[2023-11-28 07:30:41,038][87424] Updated weights for policy 0, policy_version 278728 (0.0012) -[2023-11-28 07:30:41,424][87424] Updated weights for policy 0, policy_version 278738 (0.0009) -[2023-11-28 07:30:41,809][87424] Updated weights for policy 0, policy_version 278748 (0.0010) -[2023-11-28 07:30:42,636][87426] Updated weights for policy 1, policy_version 278500 (0.0011) -[2023-11-28 07:30:43,012][87426] Updated weights for policy 1, policy_version 278510 (0.0011) -[2023-11-28 07:30:43,396][87426] Updated weights for policy 1, policy_version 278520 (0.0008) -[2023-11-28 07:30:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 142655488. Throughput: 0: 2701.8, 1: 2666.7. Samples: 142673620. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:30:43,445][86177] Avg episode reward: [(0, '-580.550'), (1, '-549.240')] -[2023-11-28 07:30:43,767][87424] Updated weights for policy 0, policy_version 278758 (0.0012) -[2023-11-28 07:30:44,154][87424] Updated weights for policy 0, policy_version 278768 (0.0012) -[2023-11-28 07:30:44,541][87424] Updated weights for policy 0, policy_version 278778 (0.0010) -[2023-11-28 07:30:45,535][87426] Updated weights for policy 1, policy_version 278530 (0.0012) -[2023-11-28 07:30:45,917][87426] Updated weights for policy 1, policy_version 278540 (0.0012) -[2023-11-28 07:30:46,297][87426] Updated weights for policy 1, policy_version 278550 (0.0011) -[2023-11-28 07:30:46,685][87426] Updated weights for policy 1, policy_version 278560 (0.0012) -[2023-11-28 07:30:46,696][87424] Updated weights for policy 0, policy_version 278788 (0.0012) -[2023-11-28 07:30:47,083][87424] Updated weights for policy 0, policy_version 278798 (0.0008) -[2023-11-28 07:30:47,469][87424] Updated weights for policy 0, policy_version 278808 (0.0007) -[2023-11-28 07:30:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142688256. Throughput: 0: 2719.9, 1: 2652.3. Samples: 142698888. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:30:48,446][86177] Avg episode reward: [(0, '-591.630'), (1, '-602.340')] -[2023-11-28 07:30:48,542][87426] Updated weights for policy 1, policy_version 278570 (0.0012) -[2023-11-28 07:30:48,931][87426] Updated weights for policy 1, policy_version 278580 (0.0011) -[2023-11-28 07:30:49,305][87426] Updated weights for policy 1, policy_version 278590 (0.0008) -[2023-11-28 07:30:49,607][87424] Updated weights for policy 0, policy_version 278818 (0.0008) -[2023-11-28 07:30:49,989][87424] Updated weights for policy 0, policy_version 278828 (0.0010) -[2023-11-28 07:30:50,378][87424] Updated weights for policy 0, policy_version 278838 (0.0008) -[2023-11-28 07:30:50,753][87424] Updated weights for policy 0, policy_version 278848 (0.0008) -[2023-11-28 07:30:51,489][87426] Updated weights for policy 1, policy_version 278600 (0.0009) -[2023-11-28 07:30:51,869][87426] Updated weights for policy 1, policy_version 278610 (0.0009) -[2023-11-28 07:30:52,252][87426] Updated weights for policy 1, policy_version 278620 (0.0010) -[2023-11-28 07:30:53,179][87424] Updated weights for policy 0, policy_version 278858 (0.0009) -[2023-11-28 07:30:53,446][86177] Fps is (10 sec: 5733.1, 60 sec: 5461.1, 300 sec: 5470.5). Total num frames: 142712832. Throughput: 0: 2723.3, 1: 2671.0. Samples: 142732128. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:30:53,447][86177] Avg episode reward: [(0, '-584.670'), (1, '-611.120')] -[2023-11-28 07:30:53,550][87424] Updated weights for policy 0, policy_version 278868 (0.0010) -[2023-11-28 07:30:53,942][87424] Updated weights for policy 0, policy_version 278878 (0.0011) -[2023-11-28 07:30:54,464][87426] Updated weights for policy 1, policy_version 278630 (0.0012) -[2023-11-28 07:30:54,855][87426] Updated weights for policy 1, policy_version 278640 (0.0010) -[2023-11-28 07:30:55,237][87426] Updated weights for policy 1, policy_version 278650 (0.0008) -[2023-11-28 07:30:56,289][87424] Updated weights for policy 0, policy_version 278888 (0.0012) -[2023-11-28 07:30:56,675][87424] Updated weights for policy 0, policy_version 278898 (0.0012) -[2023-11-28 07:30:57,052][87426] Updated weights for policy 1, policy_version 278660 (0.0008) -[2023-11-28 07:30:57,053][87424] Updated weights for policy 0, policy_version 278908 (0.0012) -[2023-11-28 07:30:57,431][87426] Updated weights for policy 1, policy_version 278670 (0.0007) -[2023-11-28 07:30:57,811][87426] Updated weights for policy 1, policy_version 278680 (0.0007) -[2023-11-28 07:30:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 142745600. Throughput: 0: 2720.7, 1: 2693.6. Samples: 142757116. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:30:58,445][86177] Avg episode reward: [(0, '-560.050'), (1, '-609.800')] -[2023-11-28 07:30:59,145][87424] Updated weights for policy 0, policy_version 278918 (0.0011) -[2023-11-28 07:30:59,525][87424] Updated weights for policy 0, policy_version 278928 (0.0012) -[2023-11-28 07:30:59,914][87424] Updated weights for policy 0, policy_version 278938 (0.0012) -[2023-11-28 07:31:00,082][87426] Updated weights for policy 1, policy_version 278690 (0.0008) -[2023-11-28 07:31:00,455][87426] Updated weights for policy 1, policy_version 278700 (0.0011) -[2023-11-28 07:31:00,839][87426] Updated weights for policy 1, policy_version 278710 (0.0008) -[2023-11-28 07:31:01,211][87426] Updated weights for policy 1, policy_version 278720 (0.0007) -[2023-11-28 07:31:01,944][87424] Updated weights for policy 0, policy_version 278948 (0.0012) -[2023-11-28 07:31:02,322][87424] Updated weights for policy 0, policy_version 278958 (0.0012) -[2023-11-28 07:31:02,700][87424] Updated weights for policy 0, policy_version 278968 (0.0012) -[2023-11-28 07:31:03,237][87426] Updated weights for policy 1, policy_version 278730 (0.0011) -[2023-11-28 07:31:03,444][86177] Fps is (10 sec: 5735.7, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 142770176. Throughput: 0: 2738.3, 1: 2697.7. Samples: 142781636. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:31:03,445][86177] Avg episode reward: [(0, '-562.240'), (1, '-618.250')] -[2023-11-28 07:31:03,619][87426] Updated weights for policy 1, policy_version 278740 (0.0009) -[2023-11-28 07:31:04,002][87426] Updated weights for policy 1, policy_version 278750 (0.0007) -[2023-11-28 07:31:04,747][87424] Updated weights for policy 0, policy_version 278978 (0.0011) -[2023-11-28 07:31:05,121][87424] Updated weights for policy 0, policy_version 278988 (0.0011) -[2023-11-28 07:31:05,500][87424] Updated weights for policy 0, policy_version 278998 (0.0012) -[2023-11-28 07:31:05,885][87424] Updated weights for policy 0, policy_version 279008 (0.0012) -[2023-11-28 07:31:06,013][87426] Updated weights for policy 1, policy_version 278760 (0.0011) -[2023-11-28 07:31:06,390][87426] Updated weights for policy 1, policy_version 278770 (0.0012) -[2023-11-28 07:31:06,770][87426] Updated weights for policy 1, policy_version 278780 (0.0011) -[2023-11-28 07:31:08,225][87424] Updated weights for policy 0, policy_version 279018 (0.0010) -[2023-11-28 07:31:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142794752. Throughput: 0: 2787.5, 1: 2686.9. Samples: 142815124. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:31:08,445][86177] Avg episode reward: [(0, '-551.730'), (1, '-587.130')] -[2023-11-28 07:31:08,604][87424] Updated weights for policy 0, policy_version 279028 (0.0011) -[2023-11-28 07:31:08,986][87424] Updated weights for policy 0, policy_version 279038 (0.0011) -[2023-11-28 07:31:08,986][87426] Updated weights for policy 1, policy_version 278790 (0.0010) -[2023-11-28 07:31:09,363][87426] Updated weights for policy 1, policy_version 278800 (0.0011) -[2023-11-28 07:31:09,747][87426] Updated weights for policy 1, policy_version 278810 (0.0012) -[2023-11-28 07:31:10,718][87424] Updated weights for policy 0, policy_version 279048 (0.0011) -[2023-11-28 07:31:11,098][87424] Updated weights for policy 0, policy_version 279058 (0.0012) -[2023-11-28 07:31:11,476][87424] Updated weights for policy 0, policy_version 279068 (0.0012) -[2023-11-28 07:31:12,109][87426] Updated weights for policy 1, policy_version 278820 (0.0012) -[2023-11-28 07:31:12,479][87426] Updated weights for policy 1, policy_version 278830 (0.0012) -[2023-11-28 07:31:12,867][87426] Updated weights for policy 1, policy_version 278840 (0.0012) -[2023-11-28 07:31:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 142827520. Throughput: 0: 2773.2, 1: 2696.7. Samples: 142838504. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:31:13,445][86177] Avg episode reward: [(0, '-590.110'), (1, '-554.230')] -[2023-11-28 07:31:13,629][87424] Updated weights for policy 0, policy_version 279078 (0.0012) -[2023-11-28 07:31:14,016][87424] Updated weights for policy 0, policy_version 279088 (0.0012) -[2023-11-28 07:31:14,410][87424] Updated weights for policy 0, policy_version 279098 (0.0012) -[2023-11-28 07:31:15,339][87426] Updated weights for policy 1, policy_version 278850 (0.0012) -[2023-11-28 07:31:15,718][87426] Updated weights for policy 1, policy_version 278860 (0.0012) -[2023-11-28 07:31:16,089][87426] Updated weights for policy 1, policy_version 278870 (0.0012) -[2023-11-28 07:31:16,451][87424] Updated weights for policy 0, policy_version 279108 (0.0010) -[2023-11-28 07:31:16,466][87426] Updated weights for policy 1, policy_version 278880 (0.0012) -[2023-11-28 07:31:16,834][87424] Updated weights for policy 0, policy_version 279118 (0.0007) -[2023-11-28 07:31:17,224][87424] Updated weights for policy 0, policy_version 279128 (0.0008) -[2023-11-28 07:31:18,212][87426] Updated weights for policy 1, policy_version 278890 (0.0011) -[2023-11-28 07:31:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 142852096. Throughput: 0: 2742.8, 1: 2720.1. Samples: 142863352. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:31:18,445][86177] Avg episode reward: [(0, '-598.680'), (1, '-583.180')] -[2023-11-28 07:31:18,603][87426] Updated weights for policy 1, policy_version 278900 (0.0007) -[2023-11-28 07:31:18,982][87426] Updated weights for policy 1, policy_version 278910 (0.0008) -[2023-11-28 07:31:19,226][87424] Updated weights for policy 0, policy_version 279138 (0.0009) -[2023-11-28 07:31:19,606][87424] Updated weights for policy 0, policy_version 279148 (0.0012) -[2023-11-28 07:31:19,989][87424] Updated weights for policy 0, policy_version 279158 (0.0012) -[2023-11-28 07:31:20,367][87424] Updated weights for policy 0, policy_version 279168 (0.0012) -[2023-11-28 07:31:20,866][87426] Updated weights for policy 1, policy_version 278920 (0.0007) -[2023-11-28 07:31:21,243][87426] Updated weights for policy 1, policy_version 278930 (0.0009) -[2023-11-28 07:31:21,633][87426] Updated weights for policy 1, policy_version 278940 (0.0011) -[2023-11-28 07:31:22,813][87424] Updated weights for policy 0, policy_version 279178 (0.0008) -[2023-11-28 07:31:23,196][87424] Updated weights for policy 0, policy_version 279188 (0.0011) -[2023-11-28 07:31:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142876672. Throughput: 0: 2725.1, 1: 2767.7. Samples: 142896668. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:31:23,446][86177] Avg episode reward: [(0, '-612.650'), (1, '-575.930')] -[2023-11-28 07:31:23,578][87424] Updated weights for policy 0, policy_version 279198 (0.0010) -[2023-11-28 07:31:23,776][87426] Updated weights for policy 1, policy_version 278950 (0.0008) -[2023-11-28 07:31:24,166][87426] Updated weights for policy 1, policy_version 278960 (0.0008) -[2023-11-28 07:31:24,530][87426] Updated weights for policy 1, policy_version 278970 (0.0008) -[2023-11-28 07:31:25,569][87424] Updated weights for policy 0, policy_version 279208 (0.0008) -[2023-11-28 07:31:25,941][87424] Updated weights for policy 0, policy_version 279218 (0.0008) -[2023-11-28 07:31:26,320][87424] Updated weights for policy 0, policy_version 279228 (0.0007) -[2023-11-28 07:31:27,072][87426] Updated weights for policy 1, policy_version 278980 (0.0007) -[2023-11-28 07:31:27,462][87426] Updated weights for policy 1, policy_version 278990 (0.0007) -[2023-11-28 07:31:27,836][87426] Updated weights for policy 1, policy_version 279000 (0.0007) -[2023-11-28 07:31:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 142909440. Throughput: 0: 2723.1, 1: 2761.2. Samples: 142920412. Policy #0 lag: (min: 22.0, avg: 31.4, max: 54.0) -[2023-11-28 07:31:28,445][86177] Avg episode reward: [(0, '-616.380'), (1, '-595.880')] -[2023-11-28 07:31:28,832][87424] Updated weights for policy 0, policy_version 279238 (0.0010) -[2023-11-28 07:31:29,222][87424] Updated weights for policy 0, policy_version 279248 (0.0011) -[2023-11-28 07:31:29,610][87424] Updated weights for policy 0, policy_version 279258 (0.0012) -[2023-11-28 07:31:30,293][87426] Updated weights for policy 1, policy_version 279010 (0.0008) -[2023-11-28 07:31:30,681][87426] Updated weights for policy 1, policy_version 279020 (0.0010) -[2023-11-28 07:31:31,054][87426] Updated weights for policy 1, policy_version 279030 (0.0009) -[2023-11-28 07:31:31,430][87426] Updated weights for policy 1, policy_version 279040 (0.0011) -[2023-11-28 07:31:31,600][87424] Updated weights for policy 0, policy_version 279268 (0.0012) -[2023-11-28 07:31:31,986][87424] Updated weights for policy 0, policy_version 279278 (0.0010) -[2023-11-28 07:31:32,366][87424] Updated weights for policy 0, policy_version 279288 (0.0009) -[2023-11-28 07:31:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142934016. Throughput: 0: 2698.6, 1: 2738.1. Samples: 142943536. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:31:33,445][86177] Avg episode reward: [(0, '-624.900'), (1, '-601.680')] -[2023-11-28 07:31:33,810][87426] Updated weights for policy 1, policy_version 279050 (0.0012) -[2023-11-28 07:31:34,209][87426] Updated weights for policy 1, policy_version 279060 (0.0011) -[2023-11-28 07:31:34,580][87426] Updated weights for policy 1, policy_version 279070 (0.0012) -[2023-11-28 07:31:34,872][87424] Updated weights for policy 0, policy_version 279298 (0.0011) -[2023-11-28 07:31:35,250][87424] Updated weights for policy 0, policy_version 279308 (0.0011) -[2023-11-28 07:31:35,636][87424] Updated weights for policy 0, policy_version 279318 (0.0011) -[2023-11-28 07:31:36,015][87424] Updated weights for policy 0, policy_version 279328 (0.0012) -[2023-11-28 07:31:37,145][87426] Updated weights for policy 1, policy_version 279080 (0.0011) -[2023-11-28 07:31:37,525][87426] Updated weights for policy 1, policy_version 279090 (0.0009) -[2023-11-28 07:31:37,901][87426] Updated weights for policy 1, policy_version 279100 (0.0008) -[2023-11-28 07:31:38,086][87424] Updated weights for policy 0, policy_version 279338 (0.0011) -[2023-11-28 07:31:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142958592. Throughput: 0: 2697.1, 1: 2718.7. Samples: 142975828. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:31:38,445][86177] Avg episode reward: [(0, '-666.780'), (1, '-591.140')] -[2023-11-28 07:31:38,467][87424] Updated weights for policy 0, policy_version 279348 (0.0012) -[2023-11-28 07:31:38,859][87424] Updated weights for policy 0, policy_version 279358 (0.0012) -[2023-11-28 07:31:39,790][87426] Updated weights for policy 1, policy_version 279110 (0.0011) -[2023-11-28 07:31:40,166][87426] Updated weights for policy 1, policy_version 279120 (0.0011) -[2023-11-28 07:31:40,546][87426] Updated weights for policy 1, policy_version 279130 (0.0012) -[2023-11-28 07:31:40,963][87424] Updated weights for policy 0, policy_version 279368 (0.0011) -[2023-11-28 07:31:41,350][87424] Updated weights for policy 0, policy_version 279378 (0.0012) -[2023-11-28 07:31:41,726][87424] Updated weights for policy 0, policy_version 279388 (0.0012) -[2023-11-28 07:31:42,525][87426] Updated weights for policy 1, policy_version 279140 (0.0011) -[2023-11-28 07:31:42,908][87426] Updated weights for policy 1, policy_version 279150 (0.0009) -[2023-11-28 07:31:43,286][87426] Updated weights for policy 1, policy_version 279160 (0.0011) -[2023-11-28 07:31:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 142983168. Throughput: 0: 2705.5, 1: 2714.1. Samples: 143000996. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:31:43,445][86177] Avg episode reward: [(0, '-647.290'), (1, '-609.970')] -[2023-11-28 07:31:43,953][87424] Updated weights for policy 0, policy_version 279398 (0.0012) -[2023-11-28 07:31:44,326][87424] Updated weights for policy 0, policy_version 279408 (0.0012) -[2023-11-28 07:31:44,696][87424] Updated weights for policy 0, policy_version 279418 (0.0012) -[2023-11-28 07:31:45,436][87426] Updated weights for policy 1, policy_version 279170 (0.0009) -[2023-11-28 07:31:45,819][87426] Updated weights for policy 1, policy_version 279180 (0.0012) -[2023-11-28 07:31:46,194][87426] Updated weights for policy 1, policy_version 279190 (0.0012) -[2023-11-28 07:31:46,568][87426] Updated weights for policy 1, policy_version 279200 (0.0008) -[2023-11-28 07:31:46,972][87424] Updated weights for policy 0, policy_version 279428 (0.0010) -[2023-11-28 07:31:47,360][87424] Updated weights for policy 0, policy_version 279438 (0.0007) -[2023-11-28 07:31:47,744][87424] Updated weights for policy 0, policy_version 279448 (0.0007) -[2023-11-28 07:31:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 143015936. Throughput: 0: 2704.6, 1: 2733.6. Samples: 143026356. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:31:48,445][86177] Avg episode reward: [(0, '-680.770'), (1, '-637.640')] -[2023-11-28 07:31:48,464][87426] Updated weights for policy 1, policy_version 279210 (0.0008) -[2023-11-28 07:31:48,846][87426] Updated weights for policy 1, policy_version 279220 (0.0008) -[2023-11-28 07:31:49,226][87426] Updated weights for policy 1, policy_version 279230 (0.0011) -[2023-11-28 07:31:50,102][87424] Updated weights for policy 0, policy_version 279458 (0.0008) -[2023-11-28 07:31:50,481][87424] Updated weights for policy 0, policy_version 279468 (0.0010) -[2023-11-28 07:31:50,851][87424] Updated weights for policy 0, policy_version 279478 (0.0012) -[2023-11-28 07:31:51,237][87424] Updated weights for policy 0, policy_version 279488 (0.0012) -[2023-11-28 07:31:51,378][87426] Updated weights for policy 1, policy_version 279240 (0.0011) -[2023-11-28 07:31:51,745][87426] Updated weights for policy 1, policy_version 279250 (0.0012) -[2023-11-28 07:31:52,127][87426] Updated weights for policy 1, policy_version 279260 (0.0012) -[2023-11-28 07:31:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.5, 300 sec: 5470.6). Total num frames: 143040512. Throughput: 0: 2689.3, 1: 2715.5. Samples: 143058340. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:31:53,445][86177] Avg episode reward: [(0, '-690.400'), (1, '-646.180')] -[2023-11-28 07:31:53,603][87424] Updated weights for policy 0, policy_version 279498 (0.0012) -[2023-11-28 07:31:53,985][87424] Updated weights for policy 0, policy_version 279508 (0.0009) -[2023-11-28 07:31:54,372][87424] Updated weights for policy 0, policy_version 279518 (0.0008) -[2023-11-28 07:31:54,409][87426] Updated weights for policy 1, policy_version 279270 (0.0011) -[2023-11-28 07:31:54,795][87426] Updated weights for policy 1, policy_version 279280 (0.0009) -[2023-11-28 07:31:55,186][87426] Updated weights for policy 1, policy_version 279290 (0.0011) -[2023-11-28 07:31:56,771][87426] Updated weights for policy 1, policy_version 279300 (0.0012) -[2023-11-28 07:31:56,945][87424] Updated weights for policy 0, policy_version 279528 (0.0011) -[2023-11-28 07:31:57,157][87426] Updated weights for policy 1, policy_version 279310 (0.0011) -[2023-11-28 07:31:57,336][87424] Updated weights for policy 0, policy_version 279538 (0.0010) -[2023-11-28 07:31:57,523][87426] Updated weights for policy 1, policy_version 279320 (0.0011) -[2023-11-28 07:31:57,707][87424] Updated weights for policy 0, policy_version 279548 (0.0010) -[2023-11-28 07:31:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 143073280. Throughput: 0: 2687.4, 1: 2765.2. Samples: 143083868. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:31:58,445][86177] Avg episode reward: [(0, '-693.800'), (1, '-619.700')] -[2023-11-28 07:31:59,508][87426] Updated weights for policy 1, policy_version 279330 (0.0011) -[2023-11-28 07:31:59,711][87424] Updated weights for policy 0, policy_version 279558 (0.0009) -[2023-11-28 07:31:59,893][87426] Updated weights for policy 1, policy_version 279340 (0.0009) -[2023-11-28 07:32:00,092][87424] Updated weights for policy 0, policy_version 279568 (0.0012) -[2023-11-28 07:32:00,278][87426] Updated weights for policy 1, policy_version 279350 (0.0011) -[2023-11-28 07:32:00,475][87424] Updated weights for policy 0, policy_version 279578 (0.0012) -[2023-11-28 07:32:00,648][87426] Updated weights for policy 1, policy_version 279360 (0.0010) -[2023-11-28 07:32:02,524][87424] Updated weights for policy 0, policy_version 279588 (0.0011) -[2023-11-28 07:32:02,771][87426] Updated weights for policy 1, policy_version 279370 (0.0009) -[2023-11-28 07:32:02,900][87424] Updated weights for policy 0, policy_version 279598 (0.0012) -[2023-11-28 07:32:03,156][87426] Updated weights for policy 1, policy_version 279380 (0.0010) -[2023-11-28 07:32:03,282][87424] Updated weights for policy 0, policy_version 279608 (0.0012) -[2023-11-28 07:32:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 143089664. Throughput: 0: 2687.5, 1: 2769.2. Samples: 143108904. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:03,445][86177] Avg episode reward: [(0, '-727.650'), (1, '-617.740')] -[2023-11-28 07:32:03,532][87426] Updated weights for policy 1, policy_version 279390 (0.0011) -[2023-11-28 07:32:05,631][87426] Updated weights for policy 1, policy_version 279400 (0.0009) -[2023-11-28 07:32:05,702][87424] Updated weights for policy 0, policy_version 279618 (0.0011) -[2023-11-28 07:32:06,011][87426] Updated weights for policy 1, policy_version 279410 (0.0009) -[2023-11-28 07:32:06,077][87424] Updated weights for policy 0, policy_version 279628 (0.0009) -[2023-11-28 07:32:06,395][87426] Updated weights for policy 1, policy_version 279420 (0.0010) -[2023-11-28 07:32:06,460][87424] Updated weights for policy 0, policy_version 279638 (0.0007) -[2023-11-28 07:32:06,844][87424] Updated weights for policy 0, policy_version 279648 (0.0011) -[2023-11-28 07:32:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143122432. Throughput: 0: 2672.8, 1: 2761.3. Samples: 143141200. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:08,445][86177] Avg episode reward: [(0, '-697.260'), (1, '-604.980')] -[2023-11-28 07:32:08,532][87426] Updated weights for policy 1, policy_version 279430 (0.0011) -[2023-11-28 07:32:08,919][87426] Updated weights for policy 1, policy_version 279440 (0.0011) -[2023-11-28 07:32:09,297][87426] Updated weights for policy 1, policy_version 279450 (0.0012) -[2023-11-28 07:32:09,345][87424] Updated weights for policy 0, policy_version 279658 (0.0009) -[2023-11-28 07:32:09,722][87424] Updated weights for policy 0, policy_version 279668 (0.0012) -[2023-11-28 07:32:10,100][87424] Updated weights for policy 0, policy_version 279678 (0.0012) -[2023-11-28 07:32:11,258][87426] Updated weights for policy 1, policy_version 279460 (0.0010) -[2023-11-28 07:32:11,637][87426] Updated weights for policy 1, policy_version 279470 (0.0010) -[2023-11-28 07:32:12,016][87426] Updated weights for policy 1, policy_version 279480 (0.0009) -[2023-11-28 07:32:12,381][87424] Updated weights for policy 0, policy_version 279688 (0.0012) -[2023-11-28 07:32:12,765][87424] Updated weights for policy 0, policy_version 279698 (0.0008) -[2023-11-28 07:32:13,144][87424] Updated weights for policy 0, policy_version 279708 (0.0011) -[2023-11-28 07:32:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 143155200. Throughput: 0: 2643.6, 1: 2790.2. Samples: 143164932. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:13,445][86177] Avg episode reward: [(0, '-684.300'), (1, '-595.670')] -[2023-11-28 07:32:14,085][87426] Updated weights for policy 1, policy_version 279490 (0.0009) -[2023-11-28 07:32:14,466][87426] Updated weights for policy 1, policy_version 279500 (0.0012) -[2023-11-28 07:32:14,844][87426] Updated weights for policy 1, policy_version 279510 (0.0011) -[2023-11-28 07:32:15,106][87424] Updated weights for policy 0, policy_version 279718 (0.0012) -[2023-11-28 07:32:15,229][87426] Updated weights for policy 1, policy_version 279520 (0.0010) -[2023-11-28 07:32:15,489][87424] Updated weights for policy 0, policy_version 279728 (0.0011) -[2023-11-28 07:32:15,862][87424] Updated weights for policy 0, policy_version 279738 (0.0012) -[2023-11-28 07:32:17,234][87426] Updated weights for policy 1, policy_version 279530 (0.0012) -[2023-11-28 07:32:17,625][87426] Updated weights for policy 1, policy_version 279540 (0.0012) -[2023-11-28 07:32:18,008][87426] Updated weights for policy 1, policy_version 279550 (0.0012) -[2023-11-28 07:32:18,126][87424] Updated weights for policy 0, policy_version 279748 (0.0010) -[2023-11-28 07:32:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143179776. Throughput: 0: 2671.5, 1: 2805.9. Samples: 143190016. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:18,445][86177] Avg episode reward: [(0, '-696.220'), (1, '-596.180')] -[2023-11-28 07:32:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000279552_71565312.pth... -[2023-11-28 07:32:18,486][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000276992_70909952.pth -[2023-11-28 07:32:18,491][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000279552_71565312.pth -[2023-11-28 07:32:18,508][87424] Updated weights for policy 0, policy_version 279758 (0.0007) -[2023-11-28 07:32:18,892][87424] Updated weights for policy 0, policy_version 279768 (0.0008) -[2023-11-28 07:32:19,188][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000279776_71622656.pth... -[2023-11-28 07:32:19,219][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000277216_70967296.pth -[2023-11-28 07:32:19,224][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000279776_71622656.pth -[2023-11-28 07:32:19,885][87426] Updated weights for policy 1, policy_version 279560 (0.0012) -[2023-11-28 07:32:20,263][87426] Updated weights for policy 1, policy_version 279570 (0.0009) -[2023-11-28 07:32:20,647][87426] Updated weights for policy 1, policy_version 279580 (0.0008) -[2023-11-28 07:32:21,285][87424] Updated weights for policy 0, policy_version 279778 (0.0008) -[2023-11-28 07:32:21,663][87424] Updated weights for policy 0, policy_version 279788 (0.0012) -[2023-11-28 07:32:22,047][87424] Updated weights for policy 0, policy_version 279798 (0.0011) -[2023-11-28 07:32:22,430][87424] Updated weights for policy 0, policy_version 279808 (0.0012) -[2023-11-28 07:32:22,923][87426] Updated weights for policy 1, policy_version 279590 (0.0010) -[2023-11-28 07:32:23,300][87426] Updated weights for policy 1, policy_version 279600 (0.0012) -[2023-11-28 07:32:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 143204352. Throughput: 0: 2662.6, 1: 2835.9. Samples: 143223260. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:23,445][86177] Avg episode reward: [(0, '-685.320'), (1, '-607.000')] -[2023-11-28 07:32:23,694][87426] Updated weights for policy 1, policy_version 279610 (0.0011) -[2023-11-28 07:32:24,370][87424] Updated weights for policy 0, policy_version 279818 (0.0012) -[2023-11-28 07:32:24,755][87424] Updated weights for policy 0, policy_version 279828 (0.0012) -[2023-11-28 07:32:25,133][87424] Updated weights for policy 0, policy_version 279838 (0.0012) -[2023-11-28 07:32:25,807][87426] Updated weights for policy 1, policy_version 279620 (0.0011) -[2023-11-28 07:32:26,184][87426] Updated weights for policy 1, policy_version 279630 (0.0011) -[2023-11-28 07:32:26,559][87426] Updated weights for policy 1, policy_version 279640 (0.0009) -[2023-11-28 07:32:27,486][87424] Updated weights for policy 0, policy_version 279848 (0.0012) -[2023-11-28 07:32:27,863][87424] Updated weights for policy 0, policy_version 279858 (0.0012) -[2023-11-28 07:32:28,240][87424] Updated weights for policy 0, policy_version 279868 (0.0012) -[2023-11-28 07:32:28,244][87426] Updated weights for policy 1, policy_version 279650 (0.0011) -[2023-11-28 07:32:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143237120. Throughput: 0: 2666.1, 1: 2845.0. Samples: 143248996. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:28,445][86177] Avg episode reward: [(0, '-723.330'), (1, '-589.400')] -[2023-11-28 07:32:28,627][87426] Updated weights for policy 1, policy_version 279660 (0.0007) -[2023-11-28 07:32:29,020][87426] Updated weights for policy 1, policy_version 279670 (0.0009) -[2023-11-28 07:32:29,399][87426] Updated weights for policy 1, policy_version 279680 (0.0011) -[2023-11-28 07:32:30,096][87424] Updated weights for policy 0, policy_version 279878 (0.0012) -[2023-11-28 07:32:30,472][87424] Updated weights for policy 0, policy_version 279888 (0.0012) -[2023-11-28 07:32:30,852][87424] Updated weights for policy 0, policy_version 279898 (0.0012) -[2023-11-28 07:32:31,603][87426] Updated weights for policy 1, policy_version 279690 (0.0009) -[2023-11-28 07:32:31,973][87426] Updated weights for policy 1, policy_version 279700 (0.0012) -[2023-11-28 07:32:32,354][87426] Updated weights for policy 1, policy_version 279710 (0.0012) -[2023-11-28 07:32:32,725][87424] Updated weights for policy 0, policy_version 279908 (0.0012) -[2023-11-28 07:32:33,102][87424] Updated weights for policy 0, policy_version 279918 (0.0012) -[2023-11-28 07:32:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143261696. Throughput: 0: 2688.4, 1: 2836.7. Samples: 143274984. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:33,445][86177] Avg episode reward: [(0, '-698.510'), (1, '-569.570')] -[2023-11-28 07:32:33,492][87424] Updated weights for policy 0, policy_version 279928 (0.0011) -[2023-11-28 07:32:34,166][87426] Updated weights for policy 1, policy_version 279720 (0.0012) -[2023-11-28 07:32:34,540][87426] Updated weights for policy 1, policy_version 279730 (0.0011) -[2023-11-28 07:32:34,914][87426] Updated weights for policy 1, policy_version 279740 (0.0009) -[2023-11-28 07:32:35,447][87424] Updated weights for policy 0, policy_version 279938 (0.0012) -[2023-11-28 07:32:35,841][87424] Updated weights for policy 0, policy_version 279948 (0.0012) -[2023-11-28 07:32:36,229][87424] Updated weights for policy 0, policy_version 279958 (0.0012) -[2023-11-28 07:32:36,599][87424] Updated weights for policy 0, policy_version 279968 (0.0012) -[2023-11-28 07:32:36,809][87426] Updated weights for policy 1, policy_version 279750 (0.0011) -[2023-11-28 07:32:37,194][87426] Updated weights for policy 1, policy_version 279760 (0.0012) -[2023-11-28 07:32:37,576][87426] Updated weights for policy 1, policy_version 279770 (0.0012) -[2023-11-28 07:32:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 143294464. Throughput: 0: 2690.5, 1: 2890.9. Samples: 143309504. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:38,445][86177] Avg episode reward: [(0, '-746.720'), (1, '-574.130')] -[2023-11-28 07:32:38,639][87424] Updated weights for policy 0, policy_version 279978 (0.0012) -[2023-11-28 07:32:39,015][87424] Updated weights for policy 0, policy_version 279988 (0.0012) -[2023-11-28 07:32:39,400][87424] Updated weights for policy 0, policy_version 279998 (0.0012) -[2023-11-28 07:32:39,658][87426] Updated weights for policy 1, policy_version 279780 (0.0012) -[2023-11-28 07:32:40,037][87426] Updated weights for policy 1, policy_version 279790 (0.0014) -[2023-11-28 07:32:40,427][87426] Updated weights for policy 1, policy_version 279800 (0.0010) -[2023-11-28 07:32:41,500][87424] Updated weights for policy 0, policy_version 280008 (0.0012) -[2023-11-28 07:32:41,891][87424] Updated weights for policy 0, policy_version 280018 (0.0012) -[2023-11-28 07:32:42,278][87424] Updated weights for policy 0, policy_version 280028 (0.0012) -[2023-11-28 07:32:42,693][87426] Updated weights for policy 1, policy_version 279810 (0.0009) -[2023-11-28 07:32:43,073][87426] Updated weights for policy 1, policy_version 279820 (0.0012) -[2023-11-28 07:32:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 143319040. Throughput: 0: 2704.6, 1: 2852.6. Samples: 143333944. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:43,445][86177] Avg episode reward: [(0, '-757.830'), (1, '-575.500')] -[2023-11-28 07:32:43,450][87426] Updated weights for policy 1, policy_version 279830 (0.0012) -[2023-11-28 07:32:43,815][87426] Updated weights for policy 1, policy_version 279840 (0.0012) -[2023-11-28 07:32:44,582][87424] Updated weights for policy 0, policy_version 280038 (0.0009) -[2023-11-28 07:32:44,968][87424] Updated weights for policy 0, policy_version 280048 (0.0007) -[2023-11-28 07:32:45,349][87424] Updated weights for policy 0, policy_version 280058 (0.0008) -[2023-11-28 07:32:46,190][87426] Updated weights for policy 1, policy_version 279850 (0.0012) -[2023-11-28 07:32:46,568][87426] Updated weights for policy 1, policy_version 279860 (0.0012) -[2023-11-28 07:32:46,944][87426] Updated weights for policy 1, policy_version 279870 (0.0009) -[2023-11-28 07:32:47,395][87424] Updated weights for policy 0, policy_version 280068 (0.0011) -[2023-11-28 07:32:47,781][87424] Updated weights for policy 0, policy_version 280078 (0.0008) -[2023-11-28 07:32:48,164][87424] Updated weights for policy 0, policy_version 280088 (0.0007) -[2023-11-28 07:32:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143343616. Throughput: 0: 2704.2, 1: 2846.0. Samples: 143358660. Policy #0 lag: (min: 31.0, avg: 43.0, max: 63.0) -[2023-11-28 07:32:48,445][86177] Avg episode reward: [(0, '-769.400'), (1, '-535.540')] -[2023-11-28 07:32:48,851][87426] Updated weights for policy 1, policy_version 279880 (0.0011) -[2023-11-28 07:32:49,222][87426] Updated weights for policy 1, policy_version 279890 (0.0012) -[2023-11-28 07:32:49,607][87426] Updated weights for policy 1, policy_version 279900 (0.0012) -[2023-11-28 07:32:50,425][87424] Updated weights for policy 0, policy_version 280098 (0.0009) -[2023-11-28 07:32:50,807][87424] Updated weights for policy 0, policy_version 280108 (0.0008) -[2023-11-28 07:32:51,185][87424] Updated weights for policy 0, policy_version 280118 (0.0008) -[2023-11-28 07:32:51,576][87424] Updated weights for policy 0, policy_version 280128 (0.0009) -[2023-11-28 07:32:51,976][87426] Updated weights for policy 1, policy_version 279910 (0.0010) -[2023-11-28 07:32:52,360][87426] Updated weights for policy 1, policy_version 279920 (0.0009) -[2023-11-28 07:32:52,738][87426] Updated weights for policy 1, policy_version 279930 (0.0008) -[2023-11-28 07:32:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 143376384. Throughput: 0: 2749.9, 1: 2826.3. Samples: 143392128. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:32:53,445][86177] Avg episode reward: [(0, '-777.050'), (1, '-529.400')] -[2023-11-28 07:32:53,474][87424] Updated weights for policy 0, policy_version 280138 (0.0011) -[2023-11-28 07:32:53,857][87424] Updated weights for policy 0, policy_version 280148 (0.0010) -[2023-11-28 07:32:54,236][87424] Updated weights for policy 0, policy_version 280158 (0.0009) -[2023-11-28 07:32:55,160][87426] Updated weights for policy 1, policy_version 279940 (0.0010) -[2023-11-28 07:32:55,536][87426] Updated weights for policy 1, policy_version 279950 (0.0011) -[2023-11-28 07:32:55,919][87426] Updated weights for policy 1, policy_version 279960 (0.0012) -[2023-11-28 07:32:56,633][87424] Updated weights for policy 0, policy_version 280168 (0.0007) -[2023-11-28 07:32:57,016][87424] Updated weights for policy 0, policy_version 280178 (0.0007) -[2023-11-28 07:32:57,402][87424] Updated weights for policy 0, policy_version 280188 (0.0007) -[2023-11-28 07:32:58,028][87426] Updated weights for policy 1, policy_version 279970 (0.0012) -[2023-11-28 07:32:58,400][87426] Updated weights for policy 1, policy_version 279980 (0.0012) -[2023-11-28 07:32:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143400960. Throughput: 0: 2752.8, 1: 2816.5. Samples: 143415552. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:32:58,445][86177] Avg episode reward: [(0, '-741.140'), (1, '-532.220')] -[2023-11-28 07:32:58,783][87426] Updated weights for policy 1, policy_version 279990 (0.0011) -[2023-11-28 07:32:59,157][87426] Updated weights for policy 1, policy_version 280000 (0.0009) -[2023-11-28 07:32:59,690][87424] Updated weights for policy 0, policy_version 280198 (0.0010) -[2023-11-28 07:33:00,062][87424] Updated weights for policy 0, policy_version 280208 (0.0012) -[2023-11-28 07:33:00,445][87424] Updated weights for policy 0, policy_version 280218 (0.0009) -[2023-11-28 07:33:01,498][87426] Updated weights for policy 1, policy_version 280010 (0.0007) -[2023-11-28 07:33:01,873][87426] Updated weights for policy 1, policy_version 280020 (0.0010) -[2023-11-28 07:33:02,245][87426] Updated weights for policy 1, policy_version 280030 (0.0011) -[2023-11-28 07:33:02,874][87424] Updated weights for policy 0, policy_version 280228 (0.0011) -[2023-11-28 07:33:03,253][87424] Updated weights for policy 0, policy_version 280238 (0.0011) -[2023-11-28 07:33:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 143425536. Throughput: 0: 2745.4, 1: 2806.2. Samples: 143439840. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:03,445][86177] Avg episode reward: [(0, '-760.000'), (1, '-551.680')] -[2023-11-28 07:33:03,632][87424] Updated weights for policy 0, policy_version 280248 (0.0012) -[2023-11-28 07:33:04,547][87426] Updated weights for policy 1, policy_version 280040 (0.0012) -[2023-11-28 07:33:04,932][87426] Updated weights for policy 1, policy_version 280050 (0.0012) -[2023-11-28 07:33:05,316][87426] Updated weights for policy 1, policy_version 280060 (0.0012) -[2023-11-28 07:33:05,572][87424] Updated weights for policy 0, policy_version 280258 (0.0011) -[2023-11-28 07:33:05,950][87424] Updated weights for policy 0, policy_version 280268 (0.0007) -[2023-11-28 07:33:06,339][87424] Updated weights for policy 0, policy_version 280278 (0.0007) -[2023-11-28 07:33:06,724][87424] Updated weights for policy 0, policy_version 280288 (0.0010) -[2023-11-28 07:33:07,008][87426] Updated weights for policy 1, policy_version 280070 (0.0011) -[2023-11-28 07:33:07,385][87426] Updated weights for policy 1, policy_version 280080 (0.0011) -[2023-11-28 07:33:07,751][87426] Updated weights for policy 1, policy_version 280090 (0.0008) -[2023-11-28 07:33:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 143458304. Throughput: 0: 2744.3, 1: 2786.1. Samples: 143472128. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:08,445][86177] Avg episode reward: [(0, '-668.010'), (1, '-594.150')] -[2023-11-28 07:33:09,016][87424] Updated weights for policy 0, policy_version 280298 (0.0011) -[2023-11-28 07:33:09,401][87424] Updated weights for policy 0, policy_version 280308 (0.0008) -[2023-11-28 07:33:09,793][87424] Updated weights for policy 0, policy_version 280318 (0.0010) -[2023-11-28 07:33:10,236][87426] Updated weights for policy 1, policy_version 280100 (0.0009) -[2023-11-28 07:33:10,613][87426] Updated weights for policy 1, policy_version 280110 (0.0012) -[2023-11-28 07:33:10,989][87426] Updated weights for policy 1, policy_version 280120 (0.0012) -[2023-11-28 07:33:12,319][87424] Updated weights for policy 0, policy_version 280328 (0.0011) -[2023-11-28 07:33:12,700][87424] Updated weights for policy 0, policy_version 280338 (0.0012) -[2023-11-28 07:33:13,076][87424] Updated weights for policy 0, policy_version 280348 (0.0012) -[2023-11-28 07:33:13,265][87426] Updated weights for policy 1, policy_version 280130 (0.0011) -[2023-11-28 07:33:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143482880. Throughput: 0: 2731.6, 1: 2754.0. Samples: 143495848. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:13,445][86177] Avg episode reward: [(0, '-692.070'), (1, '-594.670')] -[2023-11-28 07:33:13,648][87426] Updated weights for policy 1, policy_version 280140 (0.0008) -[2023-11-28 07:33:14,044][87426] Updated weights for policy 1, policy_version 280150 (0.0007) -[2023-11-28 07:33:14,422][87426] Updated weights for policy 1, policy_version 280160 (0.0007) -[2023-11-28 07:33:15,086][87424] Updated weights for policy 0, policy_version 280358 (0.0011) -[2023-11-28 07:33:15,476][87424] Updated weights for policy 0, policy_version 280368 (0.0012) -[2023-11-28 07:33:15,859][87424] Updated weights for policy 0, policy_version 280378 (0.0012) -[2023-11-28 07:33:16,357][87426] Updated weights for policy 1, policy_version 280170 (0.0011) -[2023-11-28 07:33:16,734][87426] Updated weights for policy 1, policy_version 280180 (0.0011) -[2023-11-28 07:33:17,121][87426] Updated weights for policy 1, policy_version 280190 (0.0010) -[2023-11-28 07:33:17,937][87424] Updated weights for policy 0, policy_version 280388 (0.0011) -[2023-11-28 07:33:18,315][87424] Updated weights for policy 0, policy_version 280398 (0.0010) -[2023-11-28 07:33:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143507456. Throughput: 0: 2715.5, 1: 2752.8. Samples: 143521056. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:18,446][86177] Avg episode reward: [(0, '-647.440'), (1, '-587.420')] -[2023-11-28 07:33:18,694][87424] Updated weights for policy 0, policy_version 280408 (0.0007) -[2023-11-28 07:33:19,273][87426] Updated weights for policy 1, policy_version 280200 (0.0011) -[2023-11-28 07:33:19,638][87426] Updated weights for policy 1, policy_version 280210 (0.0012) -[2023-11-28 07:33:20,009][87426] Updated weights for policy 1, policy_version 280220 (0.0011) -[2023-11-28 07:33:20,880][87424] Updated weights for policy 0, policy_version 280418 (0.0010) -[2023-11-28 07:33:21,261][87424] Updated weights for policy 0, policy_version 280428 (0.0011) -[2023-11-28 07:33:21,642][87424] Updated weights for policy 0, policy_version 280438 (0.0012) -[2023-11-28 07:33:22,021][87424] Updated weights for policy 0, policy_version 280448 (0.0011) -[2023-11-28 07:33:22,127][87426] Updated weights for policy 1, policy_version 280230 (0.0010) -[2023-11-28 07:33:22,502][87426] Updated weights for policy 1, policy_version 280240 (0.0011) -[2023-11-28 07:33:22,890][87426] Updated weights for policy 1, policy_version 280250 (0.0012) -[2023-11-28 07:33:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 143540224. Throughput: 0: 2701.7, 1: 2712.1. Samples: 143553124. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:23,445][86177] Avg episode reward: [(0, '-596.010'), (1, '-557.650')] -[2023-11-28 07:33:24,541][87424] Updated weights for policy 0, policy_version 280458 (0.0012) -[2023-11-28 07:33:24,926][87424] Updated weights for policy 0, policy_version 280468 (0.0011) -[2023-11-28 07:33:24,952][87426] Updated weights for policy 1, policy_version 280260 (0.0011) -[2023-11-28 07:33:25,301][87424] Updated weights for policy 0, policy_version 280478 (0.0010) -[2023-11-28 07:33:25,326][87426] Updated weights for policy 1, policy_version 280270 (0.0008) -[2023-11-28 07:33:25,704][87426] Updated weights for policy 1, policy_version 280280 (0.0007) -[2023-11-28 07:33:27,168][87424] Updated weights for policy 0, policy_version 280488 (0.0007) -[2023-11-28 07:33:27,542][87424] Updated weights for policy 0, policy_version 280498 (0.0007) -[2023-11-28 07:33:27,931][87424] Updated weights for policy 0, policy_version 280508 (0.0007) -[2023-11-28 07:33:28,042][87426] Updated weights for policy 1, policy_version 280290 (0.0008) -[2023-11-28 07:33:28,424][87426] Updated weights for policy 1, policy_version 280300 (0.0011) -[2023-11-28 07:33:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143564800. Throughput: 0: 2707.7, 1: 2730.9. Samples: 143578684. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:28,445][86177] Avg episode reward: [(0, '-686.610'), (1, '-525.130')] -[2023-11-28 07:33:28,803][87426] Updated weights for policy 1, policy_version 280310 (0.0012) -[2023-11-28 07:33:29,178][87426] Updated weights for policy 1, policy_version 280320 (0.0011) -[2023-11-28 07:33:30,388][87424] Updated weights for policy 0, policy_version 280518 (0.0007) -[2023-11-28 07:33:30,774][87424] Updated weights for policy 0, policy_version 280528 (0.0011) -[2023-11-28 07:33:31,095][87426] Updated weights for policy 1, policy_version 280330 (0.0007) -[2023-11-28 07:33:31,152][87424] Updated weights for policy 0, policy_version 280538 (0.0012) -[2023-11-28 07:33:31,474][87426] Updated weights for policy 1, policy_version 280340 (0.0012) -[2023-11-28 07:33:31,861][87426] Updated weights for policy 1, policy_version 280350 (0.0010) -[2023-11-28 07:33:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143589376. Throughput: 0: 2703.8, 1: 2715.5. Samples: 143602528. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:33,445][86177] Avg episode reward: [(0, '-653.580'), (1, '-543.360')] -[2023-11-28 07:33:33,506][87424] Updated weights for policy 0, policy_version 280548 (0.0010) -[2023-11-28 07:33:33,885][87424] Updated weights for policy 0, policy_version 280558 (0.0012) -[2023-11-28 07:33:34,092][87426] Updated weights for policy 1, policy_version 280360 (0.0012) -[2023-11-28 07:33:34,276][87424] Updated weights for policy 0, policy_version 280568 (0.0011) -[2023-11-28 07:33:34,473][87426] Updated weights for policy 1, policy_version 280370 (0.0011) -[2023-11-28 07:33:34,855][87426] Updated weights for policy 1, policy_version 280380 (0.0011) -[2023-11-28 07:33:36,437][87424] Updated weights for policy 0, policy_version 280578 (0.0011) -[2023-11-28 07:33:36,819][87424] Updated weights for policy 0, policy_version 280588 (0.0012) -[2023-11-28 07:33:37,205][87424] Updated weights for policy 0, policy_version 280598 (0.0011) -[2023-11-28 07:33:37,263][87426] Updated weights for policy 1, policy_version 280390 (0.0010) -[2023-11-28 07:33:37,585][87424] Updated weights for policy 0, policy_version 280608 (0.0011) -[2023-11-28 07:33:37,647][87426] Updated weights for policy 1, policy_version 280400 (0.0007) -[2023-11-28 07:33:38,025][87426] Updated weights for policy 1, policy_version 280410 (0.0007) -[2023-11-28 07:33:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 143622144. Throughput: 0: 2664.7, 1: 2714.0. Samples: 143634168. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:38,445][86177] Avg episode reward: [(0, '-648.520'), (1, '-536.240')] -[2023-11-28 07:33:39,731][87424] Updated weights for policy 0, policy_version 280618 (0.0012) -[2023-11-28 07:33:40,108][87424] Updated weights for policy 0, policy_version 280628 (0.0011) -[2023-11-28 07:33:40,479][87426] Updated weights for policy 1, policy_version 280420 (0.0009) -[2023-11-28 07:33:40,490][87424] Updated weights for policy 0, policy_version 280638 (0.0011) -[2023-11-28 07:33:40,855][87426] Updated weights for policy 1, policy_version 280430 (0.0011) -[2023-11-28 07:33:41,241][87426] Updated weights for policy 1, policy_version 280440 (0.0008) -[2023-11-28 07:33:42,858][87424] Updated weights for policy 0, policy_version 280648 (0.0012) -[2023-11-28 07:33:43,253][87426] Updated weights for policy 1, policy_version 280450 (0.0008) -[2023-11-28 07:33:43,259][87424] Updated weights for policy 0, policy_version 280658 (0.0011) -[2023-11-28 07:33:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 143638528. Throughput: 0: 2693.5, 1: 2709.4. Samples: 143658684. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:43,445][86177] Avg episode reward: [(0, '-655.290'), (1, '-538.660')] -[2023-11-28 07:33:43,627][87426] Updated weights for policy 1, policy_version 280460 (0.0008) -[2023-11-28 07:33:43,638][87424] Updated weights for policy 0, policy_version 280668 (0.0012) -[2023-11-28 07:33:44,013][87426] Updated weights for policy 1, policy_version 280470 (0.0008) -[2023-11-28 07:33:44,389][87426] Updated weights for policy 1, policy_version 280480 (0.0011) -[2023-11-28 07:33:45,818][87424] Updated weights for policy 0, policy_version 280678 (0.0010) -[2023-11-28 07:33:46,206][87424] Updated weights for policy 0, policy_version 280688 (0.0008) -[2023-11-28 07:33:46,585][87424] Updated weights for policy 0, policy_version 280698 (0.0010) -[2023-11-28 07:33:46,598][87426] Updated weights for policy 1, policy_version 280490 (0.0012) -[2023-11-28 07:33:46,971][87426] Updated weights for policy 1, policy_version 280500 (0.0012) -[2023-11-28 07:33:47,361][87426] Updated weights for policy 1, policy_version 280510 (0.0012) -[2023-11-28 07:33:48,306][87424] Updated weights for policy 0, policy_version 280708 (0.0012) -[2023-11-28 07:33:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143671296. Throughput: 0: 2688.0, 1: 2727.1. Samples: 143683520. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:48,445][86177] Avg episode reward: [(0, '-576.190'), (1, '-531.050')] -[2023-11-28 07:33:48,700][87424] Updated weights for policy 0, policy_version 280718 (0.0012) -[2023-11-28 07:33:49,096][87424] Updated weights for policy 0, policy_version 280728 (0.0012) -[2023-11-28 07:33:49,193][87426] Updated weights for policy 1, policy_version 280520 (0.0012) -[2023-11-28 07:33:49,583][87426] Updated weights for policy 1, policy_version 280530 (0.0012) -[2023-11-28 07:33:49,950][87426] Updated weights for policy 1, policy_version 280540 (0.0011) -[2023-11-28 07:33:50,979][87424] Updated weights for policy 0, policy_version 280738 (0.0012) -[2023-11-28 07:33:51,367][87424] Updated weights for policy 0, policy_version 280748 (0.0012) -[2023-11-28 07:33:51,746][87424] Updated weights for policy 0, policy_version 280758 (0.0012) -[2023-11-28 07:33:52,124][87424] Updated weights for policy 0, policy_version 280768 (0.0012) -[2023-11-28 07:33:52,380][87426] Updated weights for policy 1, policy_version 280550 (0.0009) -[2023-11-28 07:33:52,760][87426] Updated weights for policy 1, policy_version 280560 (0.0007) -[2023-11-28 07:33:53,142][87426] Updated weights for policy 1, policy_version 280570 (0.0009) -[2023-11-28 07:33:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143704064. Throughput: 0: 2720.7, 1: 2716.1. Samples: 143716784. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:53,445][86177] Avg episode reward: [(0, '-580.280'), (1, '-512.190')] -[2023-11-28 07:33:54,583][87424] Updated weights for policy 0, policy_version 280778 (0.0009) -[2023-11-28 07:33:54,963][87424] Updated weights for policy 0, policy_version 280788 (0.0008) -[2023-11-28 07:33:55,348][87424] Updated weights for policy 0, policy_version 280798 (0.0008) -[2023-11-28 07:33:55,606][87426] Updated weights for policy 1, policy_version 280580 (0.0014) -[2023-11-28 07:33:55,985][87426] Updated weights for policy 1, policy_version 280590 (0.0007) -[2023-11-28 07:33:56,374][87426] Updated weights for policy 1, policy_version 280600 (0.0007) -[2023-11-28 07:33:57,355][87424] Updated weights for policy 0, policy_version 280808 (0.0011) -[2023-11-28 07:33:57,732][87424] Updated weights for policy 0, policy_version 280818 (0.0012) -[2023-11-28 07:33:58,109][87424] Updated weights for policy 0, policy_version 280828 (0.0012) -[2023-11-28 07:33:58,417][87426] Updated weights for policy 1, policy_version 280610 (0.0008) -[2023-11-28 07:33:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143728640. Throughput: 0: 2726.7, 1: 2740.9. Samples: 143741888. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:33:58,445][86177] Avg episode reward: [(0, '-570.990'), (1, '-541.580')] -[2023-11-28 07:33:58,807][87426] Updated weights for policy 1, policy_version 280620 (0.0008) -[2023-11-28 07:33:59,183][87426] Updated weights for policy 1, policy_version 280630 (0.0008) -[2023-11-28 07:33:59,562][87426] Updated weights for policy 1, policy_version 280640 (0.0007) -[2023-11-28 07:34:00,319][87424] Updated weights for policy 0, policy_version 280838 (0.0010) -[2023-11-28 07:34:00,697][87424] Updated weights for policy 0, policy_version 280848 (0.0009) -[2023-11-28 07:34:01,082][87424] Updated weights for policy 0, policy_version 280858 (0.0008) -[2023-11-28 07:34:01,669][87426] Updated weights for policy 1, policy_version 280650 (0.0011) -[2023-11-28 07:34:02,049][87426] Updated weights for policy 1, policy_version 280660 (0.0010) -[2023-11-28 07:34:02,427][87426] Updated weights for policy 1, policy_version 280670 (0.0008) -[2023-11-28 07:34:03,202][87424] Updated weights for policy 0, policy_version 280868 (0.0009) -[2023-11-28 07:34:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143753216. Throughput: 0: 2730.0, 1: 2735.5. Samples: 143767000. Policy #0 lag: (min: 31.0, avg: 39.1, max: 63.0) -[2023-11-28 07:34:03,445][86177] Avg episode reward: [(0, '-549.180'), (1, '-544.100')] -[2023-11-28 07:34:03,583][87424] Updated weights for policy 0, policy_version 280878 (0.0012) -[2023-11-28 07:34:03,966][87424] Updated weights for policy 0, policy_version 280888 (0.0009) -[2023-11-28 07:34:04,520][87426] Updated weights for policy 1, policy_version 280680 (0.0009) -[2023-11-28 07:34:04,895][87426] Updated weights for policy 1, policy_version 280690 (0.0011) -[2023-11-28 07:34:05,277][87426] Updated weights for policy 1, policy_version 280700 (0.0012) -[2023-11-28 07:34:06,184][87424] Updated weights for policy 0, policy_version 280898 (0.0008) -[2023-11-28 07:34:06,580][87424] Updated weights for policy 0, policy_version 280908 (0.0007) -[2023-11-28 07:34:06,968][87424] Updated weights for policy 0, policy_version 280918 (0.0010) -[2023-11-28 07:34:07,347][87424] Updated weights for policy 0, policy_version 280928 (0.0011) -[2023-11-28 07:34:07,657][87426] Updated weights for policy 1, policy_version 280710 (0.0009) -[2023-11-28 07:34:08,030][87426] Updated weights for policy 1, policy_version 280720 (0.0011) -[2023-11-28 07:34:08,413][87426] Updated weights for policy 1, policy_version 280730 (0.0009) -[2023-11-28 07:34:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 143777792. Throughput: 0: 2735.3, 1: 2736.0. Samples: 143799332. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:08,445][86177] Avg episode reward: [(0, '-557.490'), (1, '-545.260')] -[2023-11-28 07:34:09,664][87424] Updated weights for policy 0, policy_version 280938 (0.0010) -[2023-11-28 07:34:10,045][87424] Updated weights for policy 0, policy_version 280948 (0.0009) -[2023-11-28 07:34:10,265][87426] Updated weights for policy 1, policy_version 280740 (0.0010) -[2023-11-28 07:34:10,425][87424] Updated weights for policy 0, policy_version 280958 (0.0011) -[2023-11-28 07:34:10,645][87426] Updated weights for policy 1, policy_version 280750 (0.0009) -[2023-11-28 07:34:11,034][87426] Updated weights for policy 1, policy_version 280760 (0.0008) -[2023-11-28 07:34:12,761][87424] Updated weights for policy 0, policy_version 280968 (0.0009) -[2023-11-28 07:34:13,136][87424] Updated weights for policy 0, policy_version 280978 (0.0009) -[2023-11-28 07:34:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 143802368. Throughput: 0: 2719.6, 1: 2699.9. Samples: 143822564. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:13,445][86177] Avg episode reward: [(0, '-541.470'), (1, '-547.870')] -[2023-11-28 07:34:13,525][87424] Updated weights for policy 0, policy_version 280988 (0.0008) -[2023-11-28 07:34:13,556][87426] Updated weights for policy 1, policy_version 280770 (0.0008) -[2023-11-28 07:34:13,931][87426] Updated weights for policy 1, policy_version 280780 (0.0012) -[2023-11-28 07:34:14,313][87426] Updated weights for policy 1, policy_version 280790 (0.0012) -[2023-11-28 07:34:14,696][87426] Updated weights for policy 1, policy_version 280800 (0.0012) -[2023-11-28 07:34:15,282][87424] Updated weights for policy 0, policy_version 280998 (0.0010) -[2023-11-28 07:34:15,659][87424] Updated weights for policy 0, policy_version 281008 (0.0012) -[2023-11-28 07:34:16,052][87424] Updated weights for policy 0, policy_version 281018 (0.0012) -[2023-11-28 07:34:17,086][87426] Updated weights for policy 1, policy_version 280810 (0.0007) -[2023-11-28 07:34:17,467][87426] Updated weights for policy 1, policy_version 280820 (0.0010) -[2023-11-28 07:34:17,853][87426] Updated weights for policy 1, policy_version 280830 (0.0011) -[2023-11-28 07:34:18,082][87424] Updated weights for policy 0, policy_version 281028 (0.0011) -[2023-11-28 07:34:18,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 143835136. Throughput: 0: 2743.0, 1: 2699.0. Samples: 143847420. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:18,445][86177] Avg episode reward: [(0, '-553.480'), (1, '-520.430')] -[2023-11-28 07:34:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000280832_71892992.pth... -[2023-11-28 07:34:18,462][87424] Updated weights for policy 0, policy_version 281038 (0.0012) -[2023-11-28 07:34:18,489][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000278272_71237632.pth -[2023-11-28 07:34:18,856][87424] Updated weights for policy 0, policy_version 281048 (0.0008) -[2023-11-28 07:34:19,153][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000281056_71950336.pth... -[2023-11-28 07:34:19,200][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000278496_71294976.pth -[2023-11-28 07:34:20,050][87426] Updated weights for policy 1, policy_version 280840 (0.0009) -[2023-11-28 07:34:20,428][87426] Updated weights for policy 1, policy_version 280850 (0.0009) -[2023-11-28 07:34:20,810][87426] Updated weights for policy 1, policy_version 280860 (0.0011) -[2023-11-28 07:34:21,134][87424] Updated weights for policy 0, policy_version 281058 (0.0010) -[2023-11-28 07:34:21,511][87424] Updated weights for policy 0, policy_version 281068 (0.0012) -[2023-11-28 07:34:21,893][87424] Updated weights for policy 0, policy_version 281078 (0.0012) -[2023-11-28 07:34:22,270][87424] Updated weights for policy 0, policy_version 281088 (0.0012) -[2023-11-28 07:34:22,733][87426] Updated weights for policy 1, policy_version 280870 (0.0011) -[2023-11-28 07:34:23,111][87426] Updated weights for policy 1, policy_version 280880 (0.0012) -[2023-11-28 07:34:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 143859712. Throughput: 0: 2759.9, 1: 2706.6. Samples: 143880160. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:23,445][86177] Avg episode reward: [(0, '-559.510'), (1, '-519.090')] -[2023-11-28 07:34:23,489][87426] Updated weights for policy 1, policy_version 280890 (0.0012) -[2023-11-28 07:34:24,383][87424] Updated weights for policy 0, policy_version 281098 (0.0012) -[2023-11-28 07:34:24,760][87424] Updated weights for policy 0, policy_version 281108 (0.0011) -[2023-11-28 07:34:25,135][87424] Updated weights for policy 0, policy_version 281118 (0.0012) -[2023-11-28 07:34:25,560][87426] Updated weights for policy 1, policy_version 280900 (0.0012) -[2023-11-28 07:34:25,932][87426] Updated weights for policy 1, policy_version 280910 (0.0010) -[2023-11-28 07:34:26,310][87426] Updated weights for policy 1, policy_version 280920 (0.0009) -[2023-11-28 07:34:26,934][87424] Updated weights for policy 0, policy_version 281128 (0.0012) -[2023-11-28 07:34:27,314][87424] Updated weights for policy 0, policy_version 281138 (0.0012) -[2023-11-28 07:34:27,685][87424] Updated weights for policy 0, policy_version 281148 (0.0012) -[2023-11-28 07:34:28,217][87426] Updated weights for policy 1, policy_version 280930 (0.0011) -[2023-11-28 07:34:28,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 143892480. Throughput: 0: 2754.2, 1: 2741.8. Samples: 143906008. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:28,446][86177] Avg episode reward: [(0, '-560.490'), (1, '-523.340')] -[2023-11-28 07:34:28,585][87426] Updated weights for policy 1, policy_version 280940 (0.0011) -[2023-11-28 07:34:28,972][87426] Updated weights for policy 1, policy_version 280950 (0.0012) -[2023-11-28 07:34:29,294][87424] Updated weights for policy 0, policy_version 281158 (0.0011) -[2023-11-28 07:34:29,342][87426] Updated weights for policy 1, policy_version 280960 (0.0012) -[2023-11-28 07:34:29,672][87424] Updated weights for policy 0, policy_version 281168 (0.0012) -[2023-11-28 07:34:30,055][87424] Updated weights for policy 0, policy_version 281178 (0.0012) -[2023-11-28 07:34:31,239][87426] Updated weights for policy 1, policy_version 280970 (0.0008) -[2023-11-28 07:34:31,625][87426] Updated weights for policy 1, policy_version 280980 (0.0007) -[2023-11-28 07:34:32,008][87426] Updated weights for policy 1, policy_version 280990 (0.0010) -[2023-11-28 07:34:32,587][87424] Updated weights for policy 0, policy_version 281188 (0.0010) -[2023-11-28 07:34:32,969][87424] Updated weights for policy 0, policy_version 281198 (0.0009) -[2023-11-28 07:34:33,344][87424] Updated weights for policy 0, policy_version 281208 (0.0007) -[2023-11-28 07:34:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 143917056. Throughput: 0: 2790.8, 1: 2736.3. Samples: 143932236. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:33,445][86177] Avg episode reward: [(0, '-581.230'), (1, '-519.380')] -[2023-11-28 07:34:34,381][87426] Updated weights for policy 1, policy_version 281000 (0.0007) -[2023-11-28 07:34:34,764][87426] Updated weights for policy 1, policy_version 281010 (0.0008) -[2023-11-28 07:34:35,145][87426] Updated weights for policy 1, policy_version 281020 (0.0009) -[2023-11-28 07:34:35,523][87424] Updated weights for policy 0, policy_version 281218 (0.0008) -[2023-11-28 07:34:35,903][87424] Updated weights for policy 0, policy_version 281228 (0.0008) -[2023-11-28 07:34:36,280][87424] Updated weights for policy 0, policy_version 281238 (0.0007) -[2023-11-28 07:34:36,656][87424] Updated weights for policy 0, policy_version 281248 (0.0008) -[2023-11-28 07:34:37,581][87426] Updated weights for policy 1, policy_version 281030 (0.0008) -[2023-11-28 07:34:37,960][87426] Updated weights for policy 1, policy_version 281040 (0.0007) -[2023-11-28 07:34:38,340][87426] Updated weights for policy 1, policy_version 281050 (0.0007) -[2023-11-28 07:34:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 143941632. Throughput: 0: 2776.0, 1: 2719.8. Samples: 143964096. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:38,445][86177] Avg episode reward: [(0, '-565.670'), (1, '-528.060')] -[2023-11-28 07:34:38,486][87424] Updated weights for policy 0, policy_version 281258 (0.0012) -[2023-11-28 07:34:38,864][87424] Updated weights for policy 0, policy_version 281268 (0.0012) -[2023-11-28 07:34:39,257][87424] Updated weights for policy 0, policy_version 281278 (0.0012) -[2023-11-28 07:34:40,388][87426] Updated weights for policy 1, policy_version 281060 (0.0011) -[2023-11-28 07:34:40,760][87426] Updated weights for policy 1, policy_version 281070 (0.0008) -[2023-11-28 07:34:41,138][87426] Updated weights for policy 1, policy_version 281080 (0.0011) -[2023-11-28 07:34:41,353][87424] Updated weights for policy 0, policy_version 281288 (0.0011) -[2023-11-28 07:34:41,757][87424] Updated weights for policy 0, policy_version 281298 (0.0012) -[2023-11-28 07:34:42,146][87424] Updated weights for policy 0, policy_version 281308 (0.0012) -[2023-11-28 07:34:43,399][87426] Updated weights for policy 1, policy_version 281090 (0.0010) -[2023-11-28 07:34:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 143974400. Throughput: 0: 2787.8, 1: 2719.7. Samples: 143989728. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:43,445][86177] Avg episode reward: [(0, '-578.440'), (1, '-525.970')] -[2023-11-28 07:34:43,783][87426] Updated weights for policy 1, policy_version 281100 (0.0012) -[2023-11-28 07:34:44,158][87426] Updated weights for policy 1, policy_version 281110 (0.0011) -[2023-11-28 07:34:44,350][87424] Updated weights for policy 0, policy_version 281318 (0.0011) -[2023-11-28 07:34:44,529][87426] Updated weights for policy 1, policy_version 281120 (0.0011) -[2023-11-28 07:34:44,738][87424] Updated weights for policy 0, policy_version 281328 (0.0011) -[2023-11-28 07:34:45,124][87424] Updated weights for policy 0, policy_version 281338 (0.0009) -[2023-11-28 07:34:46,409][87426] Updated weights for policy 1, policy_version 281130 (0.0012) -[2023-11-28 07:34:46,784][87426] Updated weights for policy 1, policy_version 281140 (0.0009) -[2023-11-28 07:34:47,165][87426] Updated weights for policy 1, policy_version 281150 (0.0007) -[2023-11-28 07:34:47,319][87424] Updated weights for policy 0, policy_version 281348 (0.0010) -[2023-11-28 07:34:47,698][87424] Updated weights for policy 0, policy_version 281358 (0.0010) -[2023-11-28 07:34:48,080][87424] Updated weights for policy 0, policy_version 281368 (0.0007) -[2023-11-28 07:34:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5498.4). Total num frames: 144007168. Throughput: 0: 2764.5, 1: 2719.6. Samples: 144013788. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:48,446][86177] Avg episode reward: [(0, '-557.820'), (1, '-528.610')] -[2023-11-28 07:34:49,372][87426] Updated weights for policy 1, policy_version 281160 (0.0011) -[2023-11-28 07:34:49,756][87426] Updated weights for policy 1, policy_version 281170 (0.0012) -[2023-11-28 07:34:50,085][87424] Updated weights for policy 0, policy_version 281378 (0.0007) -[2023-11-28 07:34:50,146][87426] Updated weights for policy 1, policy_version 281180 (0.0011) -[2023-11-28 07:34:50,474][87424] Updated weights for policy 0, policy_version 281388 (0.0008) -[2023-11-28 07:34:50,849][87424] Updated weights for policy 0, policy_version 281398 (0.0008) -[2023-11-28 07:34:51,231][87424] Updated weights for policy 0, policy_version 281408 (0.0008) -[2023-11-28 07:34:52,589][87426] Updated weights for policy 1, policy_version 281190 (0.0012) -[2023-11-28 07:34:52,977][87426] Updated weights for policy 1, policy_version 281200 (0.0014) -[2023-11-28 07:34:53,360][87426] Updated weights for policy 1, policy_version 281210 (0.0011) -[2023-11-28 07:34:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 144023552. Throughput: 0: 2767.6, 1: 2704.4. Samples: 144045572. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:53,445][86177] Avg episode reward: [(0, '-551.630'), (1, '-534.620')] -[2023-11-28 07:34:53,692][87424] Updated weights for policy 0, policy_version 281418 (0.0012) -[2023-11-28 07:34:54,078][87424] Updated weights for policy 0, policy_version 281428 (0.0012) -[2023-11-28 07:34:54,459][87424] Updated weights for policy 0, policy_version 281438 (0.0012) -[2023-11-28 07:34:55,505][87426] Updated weights for policy 1, policy_version 281220 (0.0010) -[2023-11-28 07:34:55,881][87426] Updated weights for policy 1, policy_version 281230 (0.0010) -[2023-11-28 07:34:56,268][87426] Updated weights for policy 1, policy_version 281240 (0.0010) -[2023-11-28 07:34:56,842][87424] Updated weights for policy 0, policy_version 281448 (0.0011) -[2023-11-28 07:34:57,236][87424] Updated weights for policy 0, policy_version 281458 (0.0012) -[2023-11-28 07:34:57,614][87424] Updated weights for policy 0, policy_version 281468 (0.0012) -[2023-11-28 07:34:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144056320. Throughput: 0: 2773.2, 1: 2722.2. Samples: 144069860. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:34:58,445][86177] Avg episode reward: [(0, '-575.200'), (1, '-537.050')] -[2023-11-28 07:34:58,558][87426] Updated weights for policy 1, policy_version 281250 (0.0009) -[2023-11-28 07:34:58,944][87426] Updated weights for policy 1, policy_version 281260 (0.0012) -[2023-11-28 07:34:59,323][87426] Updated weights for policy 1, policy_version 281270 (0.0012) -[2023-11-28 07:34:59,649][87424] Updated weights for policy 0, policy_version 281478 (0.0011) -[2023-11-28 07:34:59,699][87426] Updated weights for policy 1, policy_version 281280 (0.0012) -[2023-11-28 07:35:00,029][87424] Updated weights for policy 0, policy_version 281488 (0.0009) -[2023-11-28 07:35:00,406][87424] Updated weights for policy 0, policy_version 281498 (0.0008) -[2023-11-28 07:35:01,766][87426] Updated weights for policy 1, policy_version 281290 (0.0009) -[2023-11-28 07:35:02,141][87426] Updated weights for policy 1, policy_version 281300 (0.0012) -[2023-11-28 07:35:02,490][87424] Updated weights for policy 0, policy_version 281508 (0.0009) -[2023-11-28 07:35:02,515][87426] Updated weights for policy 1, policy_version 281310 (0.0012) -[2023-11-28 07:35:02,876][87424] Updated weights for policy 0, policy_version 281518 (0.0012) -[2023-11-28 07:35:03,249][87424] Updated weights for policy 0, policy_version 281528 (0.0012) -[2023-11-28 07:35:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144080896. Throughput: 0: 2772.1, 1: 2729.8. Samples: 144095004. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:35:03,445][86177] Avg episode reward: [(0, '-563.870'), (1, '-538.130')] -[2023-11-28 07:35:04,830][87426] Updated weights for policy 1, policy_version 281320 (0.0011) -[2023-11-28 07:35:05,048][87424] Updated weights for policy 0, policy_version 281538 (0.0012) -[2023-11-28 07:35:05,214][87426] Updated weights for policy 1, policy_version 281330 (0.0008) -[2023-11-28 07:35:05,431][87424] Updated weights for policy 0, policy_version 281548 (0.0010) -[2023-11-28 07:35:05,591][87426] Updated weights for policy 1, policy_version 281340 (0.0009) -[2023-11-28 07:35:05,808][87424] Updated weights for policy 0, policy_version 281558 (0.0007) -[2023-11-28 07:35:06,181][87424] Updated weights for policy 0, policy_version 281568 (0.0008) -[2023-11-28 07:35:07,507][87426] Updated weights for policy 1, policy_version 281350 (0.0007) -[2023-11-28 07:35:07,884][87426] Updated weights for policy 1, policy_version 281360 (0.0008) -[2023-11-28 07:35:08,266][87426] Updated weights for policy 1, policy_version 281370 (0.0010) -[2023-11-28 07:35:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144105472. Throughput: 0: 2766.9, 1: 2719.8. Samples: 144127064. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:35:08,445][86177] Avg episode reward: [(0, '-566.470'), (1, '-532.040')] -[2023-11-28 07:35:08,689][87424] Updated weights for policy 0, policy_version 281578 (0.0010) -[2023-11-28 07:35:09,090][87424] Updated weights for policy 0, policy_version 281588 (0.0010) -[2023-11-28 07:35:09,477][87424] Updated weights for policy 0, policy_version 281598 (0.0010) -[2023-11-28 07:35:10,784][87426] Updated weights for policy 1, policy_version 281380 (0.0010) -[2023-11-28 07:35:11,152][87426] Updated weights for policy 1, policy_version 281390 (0.0009) -[2023-11-28 07:35:11,532][87426] Updated weights for policy 1, policy_version 281400 (0.0011) -[2023-11-28 07:35:11,984][87424] Updated weights for policy 0, policy_version 281608 (0.0011) -[2023-11-28 07:35:12,360][87424] Updated weights for policy 0, policy_version 281618 (0.0012) -[2023-11-28 07:35:12,745][87424] Updated weights for policy 0, policy_version 281628 (0.0012) -[2023-11-28 07:35:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 144138240. Throughput: 0: 2755.1, 1: 2681.3. Samples: 144150644. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:35:13,445][86177] Avg episode reward: [(0, '-566.780'), (1, '-531.330')] -[2023-11-28 07:35:13,661][87426] Updated weights for policy 1, policy_version 281410 (0.0012) -[2023-11-28 07:35:14,045][87426] Updated weights for policy 1, policy_version 281420 (0.0012) -[2023-11-28 07:35:14,411][87426] Updated weights for policy 1, policy_version 281430 (0.0012) -[2023-11-28 07:35:14,785][87426] Updated weights for policy 1, policy_version 281440 (0.0012) -[2023-11-28 07:35:15,380][87424] Updated weights for policy 0, policy_version 281638 (0.0012) -[2023-11-28 07:35:15,772][87424] Updated weights for policy 0, policy_version 281648 (0.0012) -[2023-11-28 07:35:16,155][87424] Updated weights for policy 0, policy_version 281658 (0.0011) -[2023-11-28 07:35:16,977][87426] Updated weights for policy 1, policy_version 281450 (0.0012) -[2023-11-28 07:35:17,357][87426] Updated weights for policy 1, policy_version 281460 (0.0012) -[2023-11-28 07:35:17,741][87426] Updated weights for policy 1, policy_version 281470 (0.0012) -[2023-11-28 07:35:17,883][87424] Updated weights for policy 0, policy_version 281668 (0.0012) -[2023-11-28 07:35:18,270][87424] Updated weights for policy 0, policy_version 281678 (0.0010) -[2023-11-28 07:35:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144162816. Throughput: 0: 2720.9, 1: 2670.1. Samples: 144174832. Policy #0 lag: (min: 31.0, avg: 37.4, max: 63.0) -[2023-11-28 07:35:18,446][86177] Avg episode reward: [(0, '-561.840'), (1, '-525.230')] -[2023-11-28 07:35:18,655][87424] Updated weights for policy 0, policy_version 281688 (0.0008) -[2023-11-28 07:35:20,314][87426] Updated weights for policy 1, policy_version 281480 (0.0008) -[2023-11-28 07:35:20,696][87426] Updated weights for policy 1, policy_version 281490 (0.0009) -[2023-11-28 07:35:20,980][87424] Updated weights for policy 0, policy_version 281698 (0.0009) -[2023-11-28 07:35:21,082][87426] Updated weights for policy 1, policy_version 281500 (0.0011) -[2023-11-28 07:35:21,350][87424] Updated weights for policy 0, policy_version 281708 (0.0012) -[2023-11-28 07:35:21,731][87424] Updated weights for policy 0, policy_version 281718 (0.0012) -[2023-11-28 07:35:22,111][87424] Updated weights for policy 0, policy_version 281728 (0.0011) -[2023-11-28 07:35:23,009][87426] Updated weights for policy 1, policy_version 281510 (0.0012) -[2023-11-28 07:35:23,389][87426] Updated weights for policy 1, policy_version 281520 (0.0008) -[2023-11-28 07:35:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144187392. Throughput: 0: 2726.8, 1: 2674.8. Samples: 144207164. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:35:23,445][86177] Avg episode reward: [(0, '-538.370'), (1, '-524.430')] -[2023-11-28 07:35:23,764][87426] Updated weights for policy 1, policy_version 281530 (0.0009) -[2023-11-28 07:35:24,210][87424] Updated weights for policy 0, policy_version 281738 (0.0011) -[2023-11-28 07:35:24,595][87424] Updated weights for policy 0, policy_version 281748 (0.0012) -[2023-11-28 07:35:24,975][87424] Updated weights for policy 0, policy_version 281758 (0.0008) -[2023-11-28 07:35:25,656][87426] Updated weights for policy 1, policy_version 281540 (0.0011) -[2023-11-28 07:35:26,024][87426] Updated weights for policy 1, policy_version 281550 (0.0011) -[2023-11-28 07:35:26,405][87426] Updated weights for policy 1, policy_version 281560 (0.0008) -[2023-11-28 07:35:27,146][87424] Updated weights for policy 0, policy_version 281768 (0.0009) -[2023-11-28 07:35:27,537][87424] Updated weights for policy 0, policy_version 281778 (0.0009) -[2023-11-28 07:35:27,912][87424] Updated weights for policy 0, policy_version 281788 (0.0009) -[2023-11-28 07:35:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144220160. Throughput: 0: 2716.9, 1: 2680.3. Samples: 144232600. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:35:28,445][86177] Avg episode reward: [(0, '-542.210'), (1, '-522.910')] -[2023-11-28 07:35:28,874][87426] Updated weights for policy 1, policy_version 281570 (0.0010) -[2023-11-28 07:35:29,254][87426] Updated weights for policy 1, policy_version 281580 (0.0010) -[2023-11-28 07:35:29,423][87424] Updated weights for policy 0, policy_version 281798 (0.0010) -[2023-11-28 07:35:29,643][87426] Updated weights for policy 1, policy_version 281590 (0.0007) -[2023-11-28 07:35:29,797][87424] Updated weights for policy 0, policy_version 281808 (0.0011) -[2023-11-28 07:35:30,011][87426] Updated weights for policy 1, policy_version 281600 (0.0009) -[2023-11-28 07:35:30,181][87424] Updated weights for policy 0, policy_version 281818 (0.0012) -[2023-11-28 07:35:32,057][87426] Updated weights for policy 1, policy_version 281610 (0.0012) -[2023-11-28 07:35:32,115][87424] Updated weights for policy 0, policy_version 281828 (0.0011) -[2023-11-28 07:35:32,435][87426] Updated weights for policy 1, policy_version 281620 (0.0009) -[2023-11-28 07:35:32,496][87424] Updated weights for policy 0, policy_version 281838 (0.0012) -[2023-11-28 07:35:32,813][87426] Updated weights for policy 1, policy_version 281630 (0.0008) -[2023-11-28 07:35:32,873][87424] Updated weights for policy 0, policy_version 281848 (0.0012) -[2023-11-28 07:35:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5498.4). Total num frames: 144252928. Throughput: 0: 2766.4, 1: 2690.1. Samples: 144259332. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:35:33,445][86177] Avg episode reward: [(0, '-547.360'), (1, '-520.280')] -[2023-11-28 07:35:34,627][87424] Updated weights for policy 0, policy_version 281858 (0.0012) -[2023-11-28 07:35:35,014][87424] Updated weights for policy 0, policy_version 281868 (0.0011) -[2023-11-28 07:35:35,059][87426] Updated weights for policy 1, policy_version 281640 (0.0009) -[2023-11-28 07:35:35,390][87424] Updated weights for policy 0, policy_version 281878 (0.0011) -[2023-11-28 07:35:35,433][87426] Updated weights for policy 1, policy_version 281650 (0.0011) -[2023-11-28 07:35:35,768][87424] Updated weights for policy 0, policy_version 281888 (0.0012) -[2023-11-28 07:35:35,822][87426] Updated weights for policy 1, policy_version 281660 (0.0011) -[2023-11-28 07:35:37,902][87426] Updated weights for policy 1, policy_version 281670 (0.0012) -[2023-11-28 07:35:38,280][87426] Updated weights for policy 1, policy_version 281680 (0.0012) -[2023-11-28 07:35:38,332][87424] Updated weights for policy 0, policy_version 281898 (0.0009) -[2023-11-28 07:35:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144269312. Throughput: 0: 2781.9, 1: 2722.0. Samples: 144293244. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:35:38,445][86177] Avg episode reward: [(0, '-582.430'), (1, '-521.990')] -[2023-11-28 07:35:38,664][87426] Updated weights for policy 1, policy_version 281690 (0.0011) -[2023-11-28 07:35:38,710][87424] Updated weights for policy 0, policy_version 281908 (0.0012) -[2023-11-28 07:35:39,095][87424] Updated weights for policy 0, policy_version 281918 (0.0012) -[2023-11-28 07:35:40,840][87426] Updated weights for policy 1, policy_version 281700 (0.0011) -[2023-11-28 07:35:41,224][87426] Updated weights for policy 1, policy_version 281710 (0.0011) -[2023-11-28 07:35:41,417][87424] Updated weights for policy 0, policy_version 281928 (0.0011) -[2023-11-28 07:35:41,604][87426] Updated weights for policy 1, policy_version 281720 (0.0009) -[2023-11-28 07:35:41,793][87424] Updated weights for policy 0, policy_version 281938 (0.0010) -[2023-11-28 07:35:42,170][87424] Updated weights for policy 0, policy_version 281948 (0.0011) -[2023-11-28 07:35:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144302080. Throughput: 0: 2778.0, 1: 2717.3. Samples: 144317148. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:35:43,445][86177] Avg episode reward: [(0, '-622.570'), (1, '-523.830')] -[2023-11-28 07:35:44,166][87426] Updated weights for policy 1, policy_version 281730 (0.0012) -[2023-11-28 07:35:44,475][87424] Updated weights for policy 0, policy_version 281958 (0.0008) -[2023-11-28 07:35:44,538][87426] Updated weights for policy 1, policy_version 281740 (0.0009) -[2023-11-28 07:35:44,857][87424] Updated weights for policy 0, policy_version 281968 (0.0008) -[2023-11-28 07:35:44,918][87426] Updated weights for policy 1, policy_version 281750 (0.0007) -[2023-11-28 07:35:45,241][87424] Updated weights for policy 0, policy_version 281978 (0.0007) -[2023-11-28 07:35:45,290][87426] Updated weights for policy 1, policy_version 281760 (0.0008) -[2023-11-28 07:35:46,873][87424] Updated weights for policy 0, policy_version 281988 (0.0011) -[2023-11-28 07:35:47,259][87424] Updated weights for policy 0, policy_version 281998 (0.0011) -[2023-11-28 07:35:47,597][87426] Updated weights for policy 1, policy_version 281770 (0.0011) -[2023-11-28 07:35:47,643][87424] Updated weights for policy 0, policy_version 282008 (0.0011) -[2023-11-28 07:35:47,968][87426] Updated weights for policy 1, policy_version 281780 (0.0011) -[2023-11-28 07:35:48,356][87426] Updated weights for policy 1, policy_version 281790 (0.0009) -[2023-11-28 07:35:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.4, 300 sec: 5498.4). Total num frames: 144334848. Throughput: 0: 2761.7, 1: 2707.3. Samples: 144341108. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:35:48,445][86177] Avg episode reward: [(0, '-613.350'), (1, '-524.920')] -[2023-11-28 07:35:49,605][87424] Updated weights for policy 0, policy_version 282018 (0.0011) -[2023-11-28 07:35:49,985][87424] Updated weights for policy 0, policy_version 282028 (0.0009) -[2023-11-28 07:35:50,373][87424] Updated weights for policy 0, policy_version 282038 (0.0008) -[2023-11-28 07:35:50,750][87424] Updated weights for policy 0, policy_version 282048 (0.0009) -[2023-11-28 07:35:50,791][87426] Updated weights for policy 1, policy_version 281800 (0.0011) -[2023-11-28 07:35:51,173][87426] Updated weights for policy 1, policy_version 281810 (0.0011) -[2023-11-28 07:35:51,550][87426] Updated weights for policy 1, policy_version 281820 (0.0011) -[2023-11-28 07:35:52,898][87424] Updated weights for policy 0, policy_version 282058 (0.0012) -[2023-11-28 07:35:53,279][87424] Updated weights for policy 0, policy_version 282068 (0.0010) -[2023-11-28 07:35:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144351232. Throughput: 0: 2770.0, 1: 2688.0. Samples: 144372676. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:35:53,445][86177] Avg episode reward: [(0, '-610.300'), (1, '-551.460')] -[2023-11-28 07:35:53,518][87426] Updated weights for policy 1, policy_version 281830 (0.0011) -[2023-11-28 07:35:53,670][87424] Updated weights for policy 0, policy_version 282078 (0.0011) -[2023-11-28 07:35:53,900][87426] Updated weights for policy 1, policy_version 281840 (0.0011) -[2023-11-28 07:35:54,271][87426] Updated weights for policy 1, policy_version 281850 (0.0008) -[2023-11-28 07:35:56,261][87424] Updated weights for policy 0, policy_version 282088 (0.0012) -[2023-11-28 07:35:56,646][87424] Updated weights for policy 0, policy_version 282098 (0.0008) -[2023-11-28 07:35:56,856][87426] Updated weights for policy 1, policy_version 281860 (0.0008) -[2023-11-28 07:35:57,034][87424] Updated weights for policy 0, policy_version 282108 (0.0007) -[2023-11-28 07:35:57,247][87426] Updated weights for policy 1, policy_version 281870 (0.0008) -[2023-11-28 07:35:57,618][87426] Updated weights for policy 1, policy_version 281880 (0.0007) -[2023-11-28 07:35:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144384000. Throughput: 0: 2772.2, 1: 2677.3. Samples: 144395872. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:35:58,445][86177] Avg episode reward: [(0, '-607.450'), (1, '-547.540')] -[2023-11-28 07:35:59,440][87424] Updated weights for policy 0, policy_version 282118 (0.0009) -[2023-11-28 07:35:59,739][87426] Updated weights for policy 1, policy_version 281890 (0.0010) -[2023-11-28 07:35:59,827][87424] Updated weights for policy 0, policy_version 282128 (0.0010) -[2023-11-28 07:36:00,117][87426] Updated weights for policy 1, policy_version 281900 (0.0011) -[2023-11-28 07:36:00,206][87424] Updated weights for policy 0, policy_version 282138 (0.0008) -[2023-11-28 07:36:00,504][87426] Updated weights for policy 1, policy_version 281910 (0.0009) -[2023-11-28 07:36:00,884][87426] Updated weights for policy 1, policy_version 281920 (0.0011) -[2023-11-28 07:36:02,484][87424] Updated weights for policy 0, policy_version 282148 (0.0011) -[2023-11-28 07:36:02,861][87424] Updated weights for policy 0, policy_version 282158 (0.0012) -[2023-11-28 07:36:03,251][87424] Updated weights for policy 0, policy_version 282168 (0.0011) -[2023-11-28 07:36:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 144400384. Throughput: 0: 2769.8, 1: 2676.5. Samples: 144419912. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:36:03,445][86177] Avg episode reward: [(0, '-543.360'), (1, '-546.810')] -[2023-11-28 07:36:03,481][87426] Updated weights for policy 1, policy_version 281930 (0.0010) -[2023-11-28 07:36:03,858][87426] Updated weights for policy 1, policy_version 281940 (0.0012) -[2023-11-28 07:36:04,240][87426] Updated weights for policy 1, policy_version 281950 (0.0012) -[2023-11-28 07:36:05,645][87424] Updated weights for policy 0, policy_version 282178 (0.0012) -[2023-11-28 07:36:06,023][87424] Updated weights for policy 0, policy_version 282188 (0.0010) -[2023-11-28 07:36:06,327][87426] Updated weights for policy 1, policy_version 281960 (0.0010) -[2023-11-28 07:36:06,406][87424] Updated weights for policy 0, policy_version 282198 (0.0007) -[2023-11-28 07:36:06,704][87426] Updated weights for policy 1, policy_version 281970 (0.0009) -[2023-11-28 07:36:06,785][87424] Updated weights for policy 0, policy_version 282208 (0.0009) -[2023-11-28 07:36:07,086][87426] Updated weights for policy 1, policy_version 281980 (0.0011) -[2023-11-28 07:36:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144433152. Throughput: 0: 2762.3, 1: 2692.3. Samples: 144452620. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:36:08,445][86177] Avg episode reward: [(0, '-548.600'), (1, '-549.000')] -[2023-11-28 07:36:08,821][87424] Updated weights for policy 0, policy_version 282218 (0.0007) -[2023-11-28 07:36:09,202][87424] Updated weights for policy 0, policy_version 282228 (0.0008) -[2023-11-28 07:36:09,493][87426] Updated weights for policy 1, policy_version 281990 (0.0009) -[2023-11-28 07:36:09,582][87424] Updated weights for policy 0, policy_version 282238 (0.0012) -[2023-11-28 07:36:09,869][87426] Updated weights for policy 1, policy_version 282000 (0.0009) -[2023-11-28 07:36:10,244][87426] Updated weights for policy 1, policy_version 282010 (0.0012) -[2023-11-28 07:36:11,617][87424] Updated weights for policy 0, policy_version 282248 (0.0011) -[2023-11-28 07:36:12,010][87424] Updated weights for policy 0, policy_version 282258 (0.0009) -[2023-11-28 07:36:12,389][87424] Updated weights for policy 0, policy_version 282268 (0.0008) -[2023-11-28 07:36:12,677][87426] Updated weights for policy 1, policy_version 282020 (0.0012) -[2023-11-28 07:36:13,056][87426] Updated weights for policy 1, policy_version 282030 (0.0009) -[2023-11-28 07:36:13,439][87426] Updated weights for policy 1, policy_version 282040 (0.0008) -[2023-11-28 07:36:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 144457728. Throughput: 0: 2758.1, 1: 2647.6. Samples: 144475856. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:36:13,445][86177] Avg episode reward: [(0, '-602.840'), (1, '-526.940')] -[2023-11-28 07:36:14,204][87424] Updated weights for policy 0, policy_version 282278 (0.0010) -[2023-11-28 07:36:14,585][87424] Updated weights for policy 0, policy_version 282288 (0.0012) -[2023-11-28 07:36:14,973][87424] Updated weights for policy 0, policy_version 282298 (0.0012) -[2023-11-28 07:36:15,719][87426] Updated weights for policy 1, policy_version 282050 (0.0008) -[2023-11-28 07:36:16,104][87426] Updated weights for policy 1, policy_version 282060 (0.0011) -[2023-11-28 07:36:16,484][87426] Updated weights for policy 1, policy_version 282070 (0.0009) -[2023-11-28 07:36:16,877][87426] Updated weights for policy 1, policy_version 282080 (0.0007) -[2023-11-28 07:36:17,083][87424] Updated weights for policy 0, policy_version 282308 (0.0012) -[2023-11-28 07:36:17,467][87424] Updated weights for policy 0, policy_version 282318 (0.0012) -[2023-11-28 07:36:17,850][87424] Updated weights for policy 0, policy_version 282328 (0.0012) -[2023-11-28 07:36:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144490496. Throughput: 0: 2720.6, 1: 2638.2. Samples: 144500480. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:36:18,445][86177] Avg episode reward: [(0, '-607.410'), (1, '-528.010')] -[2023-11-28 07:36:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000282080_72212480.pth... -[2023-11-28 07:36:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000282336_72278016.pth... -[2023-11-28 07:36:18,485][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000279552_71565312.pth -[2023-11-28 07:36:18,499][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000279776_71622656.pth -[2023-11-28 07:36:19,172][87426] Updated weights for policy 1, policy_version 282090 (0.0011) -[2023-11-28 07:36:19,551][87426] Updated weights for policy 1, policy_version 282100 (0.0011) -[2023-11-28 07:36:19,908][87424] Updated weights for policy 0, policy_version 282338 (0.0012) -[2023-11-28 07:36:19,930][87426] Updated weights for policy 1, policy_version 282110 (0.0010) -[2023-11-28 07:36:20,282][87424] Updated weights for policy 0, policy_version 282348 (0.0012) -[2023-11-28 07:36:20,658][87424] Updated weights for policy 0, policy_version 282358 (0.0012) -[2023-11-28 07:36:21,040][87424] Updated weights for policy 0, policy_version 282368 (0.0012) -[2023-11-28 07:36:22,111][87426] Updated weights for policy 1, policy_version 282120 (0.0011) -[2023-11-28 07:36:22,489][87426] Updated weights for policy 1, policy_version 282130 (0.0011) -[2023-11-28 07:36:22,865][87426] Updated weights for policy 1, policy_version 282140 (0.0010) -[2023-11-28 07:36:23,341][87424] Updated weights for policy 0, policy_version 282378 (0.0012) -[2023-11-28 07:36:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144515072. Throughput: 0: 2692.3, 1: 2605.8. Samples: 144531656. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:36:23,445][86177] Avg episode reward: [(0, '-613.970'), (1, '-519.110')] -[2023-11-28 07:36:23,720][87424] Updated weights for policy 0, policy_version 282388 (0.0012) -[2023-11-28 07:36:24,100][87424] Updated weights for policy 0, policy_version 282398 (0.0012) -[2023-11-28 07:36:24,712][87426] Updated weights for policy 1, policy_version 282150 (0.0011) -[2023-11-28 07:36:25,096][87426] Updated weights for policy 1, policy_version 282160 (0.0011) -[2023-11-28 07:36:25,473][87426] Updated weights for policy 1, policy_version 282170 (0.0012) -[2023-11-28 07:36:26,654][87424] Updated weights for policy 0, policy_version 282408 (0.0012) -[2023-11-28 07:36:27,036][87424] Updated weights for policy 0, policy_version 282418 (0.0012) -[2023-11-28 07:36:27,230][87426] Updated weights for policy 1, policy_version 282180 (0.0010) -[2023-11-28 07:36:27,412][87424] Updated weights for policy 0, policy_version 282428 (0.0011) -[2023-11-28 07:36:27,607][87426] Updated weights for policy 1, policy_version 282190 (0.0008) -[2023-11-28 07:36:27,978][87426] Updated weights for policy 1, policy_version 282200 (0.0007) -[2023-11-28 07:36:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144547840. Throughput: 0: 2694.1, 1: 2632.8. Samples: 144556860. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 07:36:28,445][86177] Avg episode reward: [(0, '-621.510'), (1, '-516.740')] -[2023-11-28 07:36:29,269][87424] Updated weights for policy 0, policy_version 282438 (0.0012) -[2023-11-28 07:36:29,649][87424] Updated weights for policy 0, policy_version 282448 (0.0012) -[2023-11-28 07:36:29,860][87426] Updated weights for policy 1, policy_version 282210 (0.0008) -[2023-11-28 07:36:30,021][87424] Updated weights for policy 0, policy_version 282458 (0.0009) -[2023-11-28 07:36:30,242][87426] Updated weights for policy 1, policy_version 282220 (0.0008) -[2023-11-28 07:36:30,617][87426] Updated weights for policy 1, policy_version 282230 (0.0010) -[2023-11-28 07:36:30,990][87426] Updated weights for policy 1, policy_version 282240 (0.0012) -[2023-11-28 07:36:32,331][87424] Updated weights for policy 0, policy_version 282468 (0.0008) -[2023-11-28 07:36:32,719][87424] Updated weights for policy 0, policy_version 282478 (0.0008) -[2023-11-28 07:36:33,101][87424] Updated weights for policy 0, policy_version 282488 (0.0008) -[2023-11-28 07:36:33,412][87426] Updated weights for policy 1, policy_version 282250 (0.0012) -[2023-11-28 07:36:33,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 144572416. Throughput: 0: 2699.5, 1: 2645.1. Samples: 144581620. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:36:33,446][86177] Avg episode reward: [(0, '-614.650'), (1, '-514.770')] -[2023-11-28 07:36:33,780][87426] Updated weights for policy 1, policy_version 282260 (0.0012) -[2023-11-28 07:36:34,150][87426] Updated weights for policy 1, policy_version 282270 (0.0012) -[2023-11-28 07:36:35,485][87424] Updated weights for policy 0, policy_version 282498 (0.0009) -[2023-11-28 07:36:35,877][87424] Updated weights for policy 0, policy_version 282508 (0.0012) -[2023-11-28 07:36:36,104][87426] Updated weights for policy 1, policy_version 282280 (0.0009) -[2023-11-28 07:36:36,251][87424] Updated weights for policy 0, policy_version 282518 (0.0009) -[2023-11-28 07:36:36,487][87426] Updated weights for policy 1, policy_version 282290 (0.0009) -[2023-11-28 07:36:36,632][87424] Updated weights for policy 0, policy_version 282528 (0.0011) -[2023-11-28 07:36:36,866][87426] Updated weights for policy 1, policy_version 282300 (0.0012) -[2023-11-28 07:36:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144596992. Throughput: 0: 2683.9, 1: 2695.6. Samples: 144614752. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:36:38,445][86177] Avg episode reward: [(0, '-564.330'), (1, '-516.870')] -[2023-11-28 07:36:38,969][87424] Updated weights for policy 0, policy_version 282538 (0.0009) -[2023-11-28 07:36:39,244][87426] Updated weights for policy 1, policy_version 282310 (0.0012) -[2023-11-28 07:36:39,348][87424] Updated weights for policy 0, policy_version 282548 (0.0010) -[2023-11-28 07:36:39,613][87426] Updated weights for policy 1, policy_version 282320 (0.0010) -[2023-11-28 07:36:39,731][87424] Updated weights for policy 0, policy_version 282558 (0.0007) -[2023-11-28 07:36:39,995][87426] Updated weights for policy 1, policy_version 282330 (0.0010) -[2023-11-28 07:36:42,046][87426] Updated weights for policy 1, policy_version 282340 (0.0011) -[2023-11-28 07:36:42,145][87424] Updated weights for policy 0, policy_version 282568 (0.0010) -[2023-11-28 07:36:42,430][87426] Updated weights for policy 1, policy_version 282350 (0.0010) -[2023-11-28 07:36:42,532][87424] Updated weights for policy 0, policy_version 282578 (0.0012) -[2023-11-28 07:36:42,812][87426] Updated weights for policy 1, policy_version 282360 (0.0010) -[2023-11-28 07:36:42,910][87424] Updated weights for policy 0, policy_version 282588 (0.0011) -[2023-11-28 07:36:43,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144629760. Throughput: 0: 2679.3, 1: 2724.5. Samples: 144639044. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:36:43,445][86177] Avg episode reward: [(0, '-594.560'), (1, '-515.560')] -[2023-11-28 07:36:45,012][87424] Updated weights for policy 0, policy_version 282598 (0.0010) -[2023-11-28 07:36:45,092][87426] Updated weights for policy 1, policy_version 282370 (0.0011) -[2023-11-28 07:36:45,400][87424] Updated weights for policy 0, policy_version 282608 (0.0011) -[2023-11-28 07:36:45,473][87426] Updated weights for policy 1, policy_version 282380 (0.0011) -[2023-11-28 07:36:45,789][87424] Updated weights for policy 0, policy_version 282618 (0.0012) -[2023-11-28 07:36:45,854][87426] Updated weights for policy 1, policy_version 282390 (0.0011) -[2023-11-28 07:36:46,222][87426] Updated weights for policy 1, policy_version 282400 (0.0008) -[2023-11-28 07:36:48,020][87424] Updated weights for policy 0, policy_version 282628 (0.0011) -[2023-11-28 07:36:48,183][87426] Updated weights for policy 1, policy_version 282410 (0.0007) -[2023-11-28 07:36:48,416][87424] Updated weights for policy 0, policy_version 282638 (0.0012) -[2023-11-28 07:36:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5442.8). Total num frames: 144646144. Throughput: 0: 2681.3, 1: 2741.2. Samples: 144663928. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:36:48,445][86177] Avg episode reward: [(0, '-590.630'), (1, '-515.500')] -[2023-11-28 07:36:48,567][87426] Updated weights for policy 1, policy_version 282420 (0.0009) -[2023-11-28 07:36:48,795][87424] Updated weights for policy 0, policy_version 282648 (0.0011) -[2023-11-28 07:36:48,941][87426] Updated weights for policy 1, policy_version 282430 (0.0010) -[2023-11-28 07:36:50,982][87424] Updated weights for policy 0, policy_version 282658 (0.0012) -[2023-11-28 07:36:51,108][87426] Updated weights for policy 1, policy_version 282440 (0.0010) -[2023-11-28 07:36:51,368][87424] Updated weights for policy 0, policy_version 282668 (0.0009) -[2023-11-28 07:36:51,481][87426] Updated weights for policy 1, policy_version 282450 (0.0010) -[2023-11-28 07:36:51,739][87424] Updated weights for policy 0, policy_version 282678 (0.0011) -[2023-11-28 07:36:51,859][87426] Updated weights for policy 1, policy_version 282460 (0.0012) -[2023-11-28 07:36:52,121][87424] Updated weights for policy 0, policy_version 282688 (0.0009) -[2023-11-28 07:36:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144678912. Throughput: 0: 2657.4, 1: 2777.3. Samples: 144697184. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:36:53,445][86177] Avg episode reward: [(0, '-638.560'), (1, '-514.450')] -[2023-11-28 07:36:54,106][87426] Updated weights for policy 1, policy_version 282470 (0.0009) -[2023-11-28 07:36:54,493][87426] Updated weights for policy 1, policy_version 282480 (0.0008) -[2023-11-28 07:36:54,573][87424] Updated weights for policy 0, policy_version 282698 (0.0011) -[2023-11-28 07:36:54,878][87426] Updated weights for policy 1, policy_version 282490 (0.0008) -[2023-11-28 07:36:54,947][87424] Updated weights for policy 0, policy_version 282708 (0.0011) -[2023-11-28 07:36:55,336][87424] Updated weights for policy 0, policy_version 282718 (0.0011) -[2023-11-28 07:36:56,628][87426] Updated weights for policy 1, policy_version 282500 (0.0008) -[2023-11-28 07:36:57,002][87426] Updated weights for policy 1, policy_version 282510 (0.0010) -[2023-11-28 07:36:57,215][87424] Updated weights for policy 0, policy_version 282728 (0.0010) -[2023-11-28 07:36:57,383][87426] Updated weights for policy 1, policy_version 282520 (0.0011) -[2023-11-28 07:36:57,595][87424] Updated weights for policy 0, policy_version 282738 (0.0007) -[2023-11-28 07:36:57,984][87424] Updated weights for policy 0, policy_version 282748 (0.0008) -[2023-11-28 07:36:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 144711680. Throughput: 0: 2654.4, 1: 2799.5. Samples: 144721284. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:36:58,445][86177] Avg episode reward: [(0, '-630.690'), (1, '-516.650')] -[2023-11-28 07:36:59,831][87426] Updated weights for policy 1, policy_version 282530 (0.0012) -[2023-11-28 07:37:00,210][87426] Updated weights for policy 1, policy_version 282540 (0.0011) -[2023-11-28 07:37:00,240][87424] Updated weights for policy 0, policy_version 282758 (0.0008) -[2023-11-28 07:37:00,580][87426] Updated weights for policy 1, policy_version 282550 (0.0011) -[2023-11-28 07:37:00,625][87424] Updated weights for policy 0, policy_version 282768 (0.0010) -[2023-11-28 07:37:00,959][87426] Updated weights for policy 1, policy_version 282560 (0.0011) -[2023-11-28 07:37:01,014][87424] Updated weights for policy 0, policy_version 282778 (0.0011) -[2023-11-28 07:37:03,037][87424] Updated weights for policy 0, policy_version 282788 (0.0012) -[2023-11-28 07:37:03,214][87426] Updated weights for policy 1, policy_version 282570 (0.0011) -[2023-11-28 07:37:03,410][87424] Updated weights for policy 0, policy_version 282798 (0.0011) -[2023-11-28 07:37:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144728064. Throughput: 0: 2669.9, 1: 2792.2. Samples: 144746272. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:03,445][86177] Avg episode reward: [(0, '-631.800'), (1, '-522.690')] -[2023-11-28 07:37:03,594][87426] Updated weights for policy 1, policy_version 282580 (0.0010) -[2023-11-28 07:37:03,800][87424] Updated weights for policy 0, policy_version 282808 (0.0011) -[2023-11-28 07:37:03,978][87426] Updated weights for policy 1, policy_version 282590 (0.0011) -[2023-11-28 07:37:05,905][87424] Updated weights for policy 0, policy_version 282818 (0.0011) -[2023-11-28 07:37:05,921][87426] Updated weights for policy 1, policy_version 282600 (0.0011) -[2023-11-28 07:37:06,282][87424] Updated weights for policy 0, policy_version 282828 (0.0008) -[2023-11-28 07:37:06,295][87426] Updated weights for policy 1, policy_version 282610 (0.0012) -[2023-11-28 07:37:06,672][87426] Updated weights for policy 1, policy_version 282620 (0.0011) -[2023-11-28 07:37:06,678][87424] Updated weights for policy 0, policy_version 282838 (0.0008) -[2023-11-28 07:37:07,049][87424] Updated weights for policy 0, policy_version 282848 (0.0009) -[2023-11-28 07:37:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144760832. Throughput: 0: 2687.5, 1: 2818.9. Samples: 144779444. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:08,445][86177] Avg episode reward: [(0, '-588.650'), (1, '-521.960')] -[2023-11-28 07:37:08,942][87426] Updated weights for policy 1, policy_version 282630 (0.0010) -[2023-11-28 07:37:09,217][87424] Updated weights for policy 0, policy_version 282858 (0.0012) -[2023-11-28 07:37:09,318][87426] Updated weights for policy 1, policy_version 282640 (0.0011) -[2023-11-28 07:37:09,595][87424] Updated weights for policy 0, policy_version 282868 (0.0008) -[2023-11-28 07:37:09,696][87426] Updated weights for policy 1, policy_version 282650 (0.0008) -[2023-11-28 07:37:09,977][87424] Updated weights for policy 0, policy_version 282878 (0.0010) -[2023-11-28 07:37:11,690][87426] Updated weights for policy 1, policy_version 282660 (0.0010) -[2023-11-28 07:37:12,067][87426] Updated weights for policy 1, policy_version 282670 (0.0011) -[2023-11-28 07:37:12,123][87424] Updated weights for policy 0, policy_version 282888 (0.0008) -[2023-11-28 07:37:12,445][87426] Updated weights for policy 1, policy_version 282680 (0.0011) -[2023-11-28 07:37:12,509][87424] Updated weights for policy 0, policy_version 282898 (0.0010) -[2023-11-28 07:37:12,892][87424] Updated weights for policy 0, policy_version 282908 (0.0010) -[2023-11-28 07:37:13,445][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5470.6). Total num frames: 144793600. Throughput: 0: 2693.4, 1: 2780.9. Samples: 144803204. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:13,446][86177] Avg episode reward: [(0, '-590.700'), (1, '-523.860')] -[2023-11-28 07:37:14,785][87426] Updated weights for policy 1, policy_version 282690 (0.0011) -[2023-11-28 07:37:14,961][87424] Updated weights for policy 0, policy_version 282918 (0.0011) -[2023-11-28 07:37:15,162][87426] Updated weights for policy 1, policy_version 282700 (0.0011) -[2023-11-28 07:37:15,338][87424] Updated weights for policy 0, policy_version 282928 (0.0011) -[2023-11-28 07:37:15,547][87426] Updated weights for policy 1, policy_version 282710 (0.0011) -[2023-11-28 07:37:15,717][87424] Updated weights for policy 0, policy_version 282938 (0.0012) -[2023-11-28 07:37:15,918][87426] Updated weights for policy 1, policy_version 282720 (0.0011) -[2023-11-28 07:37:18,182][87424] Updated weights for policy 0, policy_version 282948 (0.0010) -[2023-11-28 07:37:18,219][87426] Updated weights for policy 1, policy_version 282730 (0.0007) -[2023-11-28 07:37:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 144809984. Throughput: 0: 2681.1, 1: 2776.6. Samples: 144827212. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:18,445][86177] Avg episode reward: [(0, '-584.040'), (1, '-521.750')] -[2023-11-28 07:37:18,562][87424] Updated weights for policy 0, policy_version 282958 (0.0008) -[2023-11-28 07:37:18,597][87426] Updated weights for policy 1, policy_version 282740 (0.0008) -[2023-11-28 07:37:18,949][87424] Updated weights for policy 0, policy_version 282968 (0.0008) -[2023-11-28 07:37:18,977][87426] Updated weights for policy 1, policy_version 282750 (0.0009) -[2023-11-28 07:37:20,929][87426] Updated weights for policy 1, policy_version 282760 (0.0009) -[2023-11-28 07:37:21,047][87424] Updated weights for policy 0, policy_version 282978 (0.0009) -[2023-11-28 07:37:21,309][87426] Updated weights for policy 1, policy_version 282770 (0.0011) -[2023-11-28 07:37:21,430][87424] Updated weights for policy 0, policy_version 282988 (0.0009) -[2023-11-28 07:37:21,684][87426] Updated weights for policy 1, policy_version 282780 (0.0012) -[2023-11-28 07:37:21,803][87424] Updated weights for policy 0, policy_version 282998 (0.0012) -[2023-11-28 07:37:22,187][87424] Updated weights for policy 0, policy_version 283008 (0.0010) -[2023-11-28 07:37:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144842752. Throughput: 0: 2714.0, 1: 2752.8. Samples: 144860760. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:23,445][86177] Avg episode reward: [(0, '-589.940'), (1, '-522.250')] -[2023-11-28 07:37:23,625][87426] Updated weights for policy 1, policy_version 282790 (0.0011) -[2023-11-28 07:37:24,006][87426] Updated weights for policy 1, policy_version 282800 (0.0012) -[2023-11-28 07:37:24,374][87426] Updated weights for policy 1, policy_version 282810 (0.0012) -[2023-11-28 07:37:24,384][87424] Updated weights for policy 0, policy_version 283018 (0.0008) -[2023-11-28 07:37:24,765][87424] Updated weights for policy 0, policy_version 283028 (0.0012) -[2023-11-28 07:37:25,158][87424] Updated weights for policy 0, policy_version 283038 (0.0012) -[2023-11-28 07:37:26,850][87426] Updated weights for policy 1, policy_version 282820 (0.0011) -[2023-11-28 07:37:27,106][87424] Updated weights for policy 0, policy_version 283048 (0.0008) -[2023-11-28 07:37:27,218][87426] Updated weights for policy 1, policy_version 282830 (0.0011) -[2023-11-28 07:37:27,491][87424] Updated weights for policy 0, policy_version 283058 (0.0008) -[2023-11-28 07:37:27,593][87426] Updated weights for policy 1, policy_version 282840 (0.0011) -[2023-11-28 07:37:27,868][87424] Updated weights for policy 0, policy_version 283068 (0.0007) -[2023-11-28 07:37:28,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144875520. Throughput: 0: 2723.8, 1: 2744.0. Samples: 144885096. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:28,445][86177] Avg episode reward: [(0, '-592.760'), (1, '-519.980')] -[2023-11-28 07:37:29,281][87426] Updated weights for policy 1, policy_version 282850 (0.0011) -[2023-11-28 07:37:29,653][87426] Updated weights for policy 1, policy_version 282860 (0.0010) -[2023-11-28 07:37:29,886][87424] Updated weights for policy 0, policy_version 283078 (0.0008) -[2023-11-28 07:37:30,027][87426] Updated weights for policy 1, policy_version 282870 (0.0009) -[2023-11-28 07:37:30,268][87424] Updated weights for policy 0, policy_version 283088 (0.0009) -[2023-11-28 07:37:30,409][87426] Updated weights for policy 1, policy_version 282880 (0.0009) -[2023-11-28 07:37:30,650][87424] Updated weights for policy 0, policy_version 283098 (0.0011) -[2023-11-28 07:37:32,745][87426] Updated weights for policy 1, policy_version 282890 (0.0007) -[2023-11-28 07:37:32,897][87424] Updated weights for policy 0, policy_version 283108 (0.0012) -[2023-11-28 07:37:33,122][87426] Updated weights for policy 1, policy_version 282900 (0.0011) -[2023-11-28 07:37:33,282][87424] Updated weights for policy 0, policy_version 283118 (0.0012) -[2023-11-28 07:37:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 144891904. Throughput: 0: 2729.2, 1: 2749.4. Samples: 144910468. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:33,445][86177] Avg episode reward: [(0, '-581.440'), (1, '-529.630')] -[2023-11-28 07:37:33,509][87426] Updated weights for policy 1, policy_version 282910 (0.0008) -[2023-11-28 07:37:33,661][87424] Updated weights for policy 0, policy_version 283128 (0.0011) -[2023-11-28 07:37:35,270][87426] Updated weights for policy 1, policy_version 282920 (0.0012) -[2023-11-28 07:37:35,649][87426] Updated weights for policy 1, policy_version 282930 (0.0012) -[2023-11-28 07:37:36,020][87424] Updated weights for policy 0, policy_version 283138 (0.0008) -[2023-11-28 07:37:36,025][87426] Updated weights for policy 1, policy_version 282940 (0.0012) -[2023-11-28 07:37:36,411][87424] Updated weights for policy 0, policy_version 283148 (0.0009) -[2023-11-28 07:37:36,793][87424] Updated weights for policy 0, policy_version 283158 (0.0008) -[2023-11-28 07:37:37,179][87424] Updated weights for policy 0, policy_version 283168 (0.0008) -[2023-11-28 07:37:38,210][87426] Updated weights for policy 1, policy_version 282950 (0.0012) -[2023-11-28 07:37:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 144924672. Throughput: 0: 2742.6, 1: 2728.7. Samples: 144943392. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:38,445][86177] Avg episode reward: [(0, '-547.080'), (1, '-566.330')] -[2023-11-28 07:37:38,589][87426] Updated weights for policy 1, policy_version 282960 (0.0011) -[2023-11-28 07:37:38,969][87426] Updated weights for policy 1, policy_version 282970 (0.0011) -[2023-11-28 07:37:39,435][87424] Updated weights for policy 0, policy_version 283178 (0.0012) -[2023-11-28 07:37:39,814][87424] Updated weights for policy 0, policy_version 283188 (0.0011) -[2023-11-28 07:37:40,200][87424] Updated weights for policy 0, policy_version 283198 (0.0009) -[2023-11-28 07:37:41,228][87426] Updated weights for policy 1, policy_version 282980 (0.0011) -[2023-11-28 07:37:41,600][87426] Updated weights for policy 1, policy_version 282990 (0.0011) -[2023-11-28 07:37:41,977][87426] Updated weights for policy 1, policy_version 283000 (0.0012) -[2023-11-28 07:37:42,323][87424] Updated weights for policy 0, policy_version 283208 (0.0010) -[2023-11-28 07:37:42,702][87424] Updated weights for policy 0, policy_version 283218 (0.0010) -[2023-11-28 07:37:43,084][87424] Updated weights for policy 0, policy_version 283228 (0.0010) -[2023-11-28 07:37:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 144957440. Throughput: 0: 2742.1, 1: 2724.8. Samples: 144967292. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:43,445][86177] Avg episode reward: [(0, '-541.510'), (1, '-561.530')] -[2023-11-28 07:37:43,957][87426] Updated weights for policy 1, policy_version 283010 (0.0011) -[2023-11-28 07:37:44,336][87426] Updated weights for policy 1, policy_version 283020 (0.0009) -[2023-11-28 07:37:44,724][87426] Updated weights for policy 1, policy_version 283030 (0.0007) -[2023-11-28 07:37:44,846][87424] Updated weights for policy 0, policy_version 283238 (0.0011) -[2023-11-28 07:37:45,103][87426] Updated weights for policy 1, policy_version 283040 (0.0008) -[2023-11-28 07:37:45,234][87424] Updated weights for policy 0, policy_version 283248 (0.0007) -[2023-11-28 07:37:45,616][87424] Updated weights for policy 0, policy_version 283258 (0.0009) -[2023-11-28 07:37:47,480][87426] Updated weights for policy 1, policy_version 283050 (0.0012) -[2023-11-28 07:37:47,846][87426] Updated weights for policy 1, policy_version 283060 (0.0011) -[2023-11-28 07:37:47,906][87424] Updated weights for policy 0, policy_version 283268 (0.0011) -[2023-11-28 07:37:48,227][87426] Updated weights for policy 1, policy_version 283070 (0.0009) -[2023-11-28 07:37:48,284][87424] Updated weights for policy 0, policy_version 283278 (0.0010) -[2023-11-28 07:37:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 144982016. Throughput: 0: 2741.4, 1: 2724.6. Samples: 144992244. Policy #0 lag: (min: 14.0, avg: 24.5, max: 46.0) -[2023-11-28 07:37:48,445][86177] Avg episode reward: [(0, '-574.060'), (1, '-561.310')] -[2023-11-28 07:37:48,674][87424] Updated weights for policy 0, policy_version 283288 (0.0008) -[2023-11-28 07:37:50,697][87426] Updated weights for policy 1, policy_version 283080 (0.0009) -[2023-11-28 07:37:51,060][87424] Updated weights for policy 0, policy_version 283298 (0.0011) -[2023-11-28 07:37:51,082][87426] Updated weights for policy 1, policy_version 283090 (0.0008) -[2023-11-28 07:37:51,435][87424] Updated weights for policy 0, policy_version 283308 (0.0012) -[2023-11-28 07:37:51,458][87426] Updated weights for policy 1, policy_version 283100 (0.0008) -[2023-11-28 07:37:51,817][87424] Updated weights for policy 0, policy_version 283318 (0.0010) -[2023-11-28 07:37:52,197][87424] Updated weights for policy 0, policy_version 283328 (0.0011) -[2023-11-28 07:37:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145006592. Throughput: 0: 2733.1, 1: 2721.2. Samples: 145024888. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:37:53,445][86177] Avg episode reward: [(0, '-580.030'), (1, '-557.610')] -[2023-11-28 07:37:53,890][87426] Updated weights for policy 1, policy_version 283110 (0.0012) -[2023-11-28 07:37:54,262][87426] Updated weights for policy 1, policy_version 283120 (0.0012) -[2023-11-28 07:37:54,615][87424] Updated weights for policy 0, policy_version 283338 (0.0007) -[2023-11-28 07:37:54,647][87426] Updated weights for policy 1, policy_version 283130 (0.0010) -[2023-11-28 07:37:54,995][87424] Updated weights for policy 0, policy_version 283348 (0.0008) -[2023-11-28 07:37:55,377][87424] Updated weights for policy 0, policy_version 283358 (0.0007) -[2023-11-28 07:37:56,562][87426] Updated weights for policy 1, policy_version 283140 (0.0009) -[2023-11-28 07:37:56,946][87426] Updated weights for policy 1, policy_version 283150 (0.0008) -[2023-11-28 07:37:57,318][87426] Updated weights for policy 1, policy_version 283160 (0.0007) -[2023-11-28 07:37:57,775][87424] Updated weights for policy 0, policy_version 283368 (0.0007) -[2023-11-28 07:37:58,167][87424] Updated weights for policy 0, policy_version 283378 (0.0007) -[2023-11-28 07:37:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 145031168. Throughput: 0: 2721.0, 1: 2742.4. Samples: 145049056. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:37:58,445][86177] Avg episode reward: [(0, '-575.800'), (1, '-520.630')] -[2023-11-28 07:37:58,551][87424] Updated weights for policy 0, policy_version 283388 (0.0008) -[2023-11-28 07:37:58,917][87426] Updated weights for policy 1, policy_version 283170 (0.0009) -[2023-11-28 07:37:59,297][87426] Updated weights for policy 1, policy_version 283180 (0.0009) -[2023-11-28 07:37:59,664][87426] Updated weights for policy 1, policy_version 283190 (0.0007) -[2023-11-28 07:38:00,040][87426] Updated weights for policy 1, policy_version 283200 (0.0009) -[2023-11-28 07:38:00,597][87424] Updated weights for policy 0, policy_version 283398 (0.0009) -[2023-11-28 07:38:00,973][87424] Updated weights for policy 0, policy_version 283408 (0.0011) -[2023-11-28 07:38:01,362][87424] Updated weights for policy 0, policy_version 283418 (0.0012) -[2023-11-28 07:38:02,524][87426] Updated weights for policy 1, policy_version 283210 (0.0009) -[2023-11-28 07:38:02,900][87426] Updated weights for policy 1, policy_version 283220 (0.0008) -[2023-11-28 07:38:03,286][87426] Updated weights for policy 1, policy_version 283230 (0.0008) -[2023-11-28 07:38:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 145063936. Throughput: 0: 2705.1, 1: 2736.1. Samples: 145072068. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:03,446][86177] Avg episode reward: [(0, '-585.260'), (1, '-521.760')] -[2023-11-28 07:38:03,961][87424] Updated weights for policy 0, policy_version 283428 (0.0012) -[2023-11-28 07:38:04,342][87424] Updated weights for policy 0, policy_version 283438 (0.0012) -[2023-11-28 07:38:04,714][87424] Updated weights for policy 0, policy_version 283448 (0.0012) -[2023-11-28 07:38:05,642][87426] Updated weights for policy 1, policy_version 283240 (0.0011) -[2023-11-28 07:38:06,011][87426] Updated weights for policy 1, policy_version 283250 (0.0012) -[2023-11-28 07:38:06,387][87426] Updated weights for policy 1, policy_version 283260 (0.0007) -[2023-11-28 07:38:07,333][87424] Updated weights for policy 0, policy_version 283458 (0.0012) -[2023-11-28 07:38:07,708][87424] Updated weights for policy 0, policy_version 283468 (0.0012) -[2023-11-28 07:38:08,103][87424] Updated weights for policy 0, policy_version 283478 (0.0012) -[2023-11-28 07:38:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 145080320. Throughput: 0: 2659.9, 1: 2743.6. Samples: 145103920. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:08,445][86177] Avg episode reward: [(0, '-595.530'), (1, '-520.800')] -[2023-11-28 07:38:08,473][87424] Updated weights for policy 0, policy_version 283488 (0.0012) -[2023-11-28 07:38:08,629][87426] Updated weights for policy 1, policy_version 283270 (0.0010) -[2023-11-28 07:38:09,005][87426] Updated weights for policy 1, policy_version 283280 (0.0012) -[2023-11-28 07:38:09,370][87426] Updated weights for policy 1, policy_version 283290 (0.0012) -[2023-11-28 07:38:10,490][87424] Updated weights for policy 0, policy_version 283498 (0.0012) -[2023-11-28 07:38:10,872][87424] Updated weights for policy 0, policy_version 283508 (0.0012) -[2023-11-28 07:38:11,245][87424] Updated weights for policy 0, policy_version 283518 (0.0012) -[2023-11-28 07:38:11,732][87426] Updated weights for policy 1, policy_version 283300 (0.0012) -[2023-11-28 07:38:12,108][87426] Updated weights for policy 1, policy_version 283310 (0.0010) -[2023-11-28 07:38:12,493][87426] Updated weights for policy 1, policy_version 283320 (0.0012) -[2023-11-28 07:38:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 145113088. Throughput: 0: 2648.0, 1: 2737.4. Samples: 145127440. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:13,445][86177] Avg episode reward: [(0, '-574.310'), (1, '-521.120')] -[2023-11-28 07:38:13,447][87424] Updated weights for policy 0, policy_version 283528 (0.0011) -[2023-11-28 07:38:13,831][87424] Updated weights for policy 0, policy_version 283538 (0.0011) -[2023-11-28 07:38:14,223][87424] Updated weights for policy 0, policy_version 283548 (0.0011) -[2023-11-28 07:38:14,632][87426] Updated weights for policy 1, policy_version 283330 (0.0011) -[2023-11-28 07:38:15,019][87426] Updated weights for policy 1, policy_version 283340 (0.0008) -[2023-11-28 07:38:15,396][87426] Updated weights for policy 1, policy_version 283350 (0.0008) -[2023-11-28 07:38:15,772][87426] Updated weights for policy 1, policy_version 283360 (0.0012) -[2023-11-28 07:38:16,634][87424] Updated weights for policy 0, policy_version 283558 (0.0009) -[2023-11-28 07:38:17,009][87424] Updated weights for policy 0, policy_version 283568 (0.0012) -[2023-11-28 07:38:17,395][87424] Updated weights for policy 0, policy_version 283578 (0.0012) -[2023-11-28 07:38:17,703][87426] Updated weights for policy 1, policy_version 283370 (0.0011) -[2023-11-28 07:38:18,082][87426] Updated weights for policy 1, policy_version 283380 (0.0012) -[2023-11-28 07:38:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 145137664. Throughput: 0: 2639.4, 1: 2741.6. Samples: 145152612. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:18,445][86177] Avg episode reward: [(0, '-585.530'), (1, '-524.210')] -[2023-11-28 07:38:18,452][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000283584_72597504.pth... -[2023-11-28 07:38:18,460][87426] Updated weights for policy 1, policy_version 283390 (0.0012) -[2023-11-28 07:38:18,499][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000281056_71950336.pth -[2023-11-28 07:38:18,529][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000283392_72548352.pth... -[2023-11-28 07:38:18,560][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000280832_71892992.pth -[2023-11-28 07:38:19,699][87424] Updated weights for policy 0, policy_version 283588 (0.0010) -[2023-11-28 07:38:20,075][87424] Updated weights for policy 0, policy_version 283598 (0.0010) -[2023-11-28 07:38:20,454][87424] Updated weights for policy 0, policy_version 283608 (0.0009) -[2023-11-28 07:38:20,663][87426] Updated weights for policy 1, policy_version 283400 (0.0011) -[2023-11-28 07:38:21,041][87426] Updated weights for policy 1, policy_version 283410 (0.0011) -[2023-11-28 07:38:21,422][87426] Updated weights for policy 1, policy_version 283420 (0.0012) -[2023-11-28 07:38:22,578][87424] Updated weights for policy 0, policy_version 283618 (0.0008) -[2023-11-28 07:38:22,962][87424] Updated weights for policy 0, policy_version 283628 (0.0011) -[2023-11-28 07:38:23,346][87424] Updated weights for policy 0, policy_version 283638 (0.0012) -[2023-11-28 07:38:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 145162240. Throughput: 0: 2647.3, 1: 2707.8. Samples: 145184372. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:23,445][86177] Avg episode reward: [(0, '-619.140'), (1, '-524.500')] -[2023-11-28 07:38:23,611][87426] Updated weights for policy 1, policy_version 283430 (0.0011) -[2023-11-28 07:38:23,728][87424] Updated weights for policy 0, policy_version 283648 (0.0012) -[2023-11-28 07:38:23,979][87426] Updated weights for policy 1, policy_version 283440 (0.0011) -[2023-11-28 07:38:24,353][87426] Updated weights for policy 1, policy_version 283450 (0.0012) -[2023-11-28 07:38:25,763][87424] Updated weights for policy 0, policy_version 283658 (0.0012) -[2023-11-28 07:38:26,150][87424] Updated weights for policy 0, policy_version 283668 (0.0012) -[2023-11-28 07:38:26,375][87426] Updated weights for policy 1, policy_version 283460 (0.0011) -[2023-11-28 07:38:26,531][87424] Updated weights for policy 0, policy_version 283678 (0.0007) -[2023-11-28 07:38:26,754][87426] Updated weights for policy 1, policy_version 283470 (0.0010) -[2023-11-28 07:38:27,134][87426] Updated weights for policy 1, policy_version 283480 (0.0010) -[2023-11-28 07:38:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 145195008. Throughput: 0: 2661.8, 1: 2722.9. Samples: 145209604. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:28,446][86177] Avg episode reward: [(0, '-614.070'), (1, '-525.040')] -[2023-11-28 07:38:28,909][87424] Updated weights for policy 0, policy_version 283688 (0.0010) -[2023-11-28 07:38:29,181][87426] Updated weights for policy 1, policy_version 283490 (0.0011) -[2023-11-28 07:38:29,294][87424] Updated weights for policy 0, policy_version 283698 (0.0007) -[2023-11-28 07:38:29,551][87426] Updated weights for policy 1, policy_version 283500 (0.0011) -[2023-11-28 07:38:29,681][87424] Updated weights for policy 0, policy_version 283708 (0.0011) -[2023-11-28 07:38:29,929][87426] Updated weights for policy 1, policy_version 283510 (0.0011) -[2023-11-28 07:38:30,308][87426] Updated weights for policy 1, policy_version 283520 (0.0011) -[2023-11-28 07:38:31,598][87424] Updated weights for policy 0, policy_version 283718 (0.0010) -[2023-11-28 07:38:31,981][87424] Updated weights for policy 0, policy_version 283728 (0.0010) -[2023-11-28 07:38:32,366][87424] Updated weights for policy 0, policy_version 283738 (0.0011) -[2023-11-28 07:38:32,557][87426] Updated weights for policy 1, policy_version 283530 (0.0010) -[2023-11-28 07:38:32,937][87426] Updated weights for policy 1, policy_version 283540 (0.0010) -[2023-11-28 07:38:33,318][87426] Updated weights for policy 1, policy_version 283550 (0.0011) -[2023-11-28 07:38:33,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 145227776. Throughput: 0: 2670.4, 1: 2737.1. Samples: 145235584. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:33,446][86177] Avg episode reward: [(0, '-624.390'), (1, '-555.640')] -[2023-11-28 07:38:34,626][87424] Updated weights for policy 0, policy_version 283748 (0.0010) -[2023-11-28 07:38:35,006][87424] Updated weights for policy 0, policy_version 283758 (0.0008) -[2023-11-28 07:38:35,052][87426] Updated weights for policy 1, policy_version 283560 (0.0011) -[2023-11-28 07:38:35,397][87424] Updated weights for policy 0, policy_version 283768 (0.0011) -[2023-11-28 07:38:35,438][87426] Updated weights for policy 1, policy_version 283570 (0.0011) -[2023-11-28 07:38:35,807][87426] Updated weights for policy 1, policy_version 283580 (0.0011) -[2023-11-28 07:38:37,067][87424] Updated weights for policy 0, policy_version 283778 (0.0011) -[2023-11-28 07:38:37,443][87424] Updated weights for policy 0, policy_version 283788 (0.0011) -[2023-11-28 07:38:37,829][87424] Updated weights for policy 0, policy_version 283798 (0.0012) -[2023-11-28 07:38:37,959][87426] Updated weights for policy 1, policy_version 283590 (0.0009) -[2023-11-28 07:38:38,213][87424] Updated weights for policy 0, policy_version 283808 (0.0012) -[2023-11-28 07:38:38,345][87426] Updated weights for policy 1, policy_version 283600 (0.0008) -[2023-11-28 07:38:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 145252352. Throughput: 0: 2688.3, 1: 2758.7. Samples: 145270000. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:38,445][86177] Avg episode reward: [(0, '-630.750'), (1, '-556.660')] -[2023-11-28 07:38:38,720][87426] Updated weights for policy 1, policy_version 283610 (0.0007) -[2023-11-28 07:38:40,532][87424] Updated weights for policy 0, policy_version 283818 (0.0012) -[2023-11-28 07:38:40,731][87426] Updated weights for policy 1, policy_version 283620 (0.0009) -[2023-11-28 07:38:40,916][87424] Updated weights for policy 0, policy_version 283828 (0.0012) -[2023-11-28 07:38:41,110][87426] Updated weights for policy 1, policy_version 283630 (0.0012) -[2023-11-28 07:38:41,298][87424] Updated weights for policy 0, policy_version 283838 (0.0012) -[2023-11-28 07:38:41,493][87426] Updated weights for policy 1, policy_version 283640 (0.0012) -[2023-11-28 07:38:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 145276928. Throughput: 0: 2702.6, 1: 2744.2. Samples: 145294160. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:43,445][86177] Avg episode reward: [(0, '-616.560'), (1, '-553.910')] -[2023-11-28 07:38:43,488][87424] Updated weights for policy 0, policy_version 283848 (0.0010) -[2023-11-28 07:38:43,870][87424] Updated weights for policy 0, policy_version 283858 (0.0011) -[2023-11-28 07:38:44,079][87426] Updated weights for policy 1, policy_version 283650 (0.0011) -[2023-11-28 07:38:44,262][87424] Updated weights for policy 0, policy_version 283868 (0.0010) -[2023-11-28 07:38:44,457][87426] Updated weights for policy 1, policy_version 283660 (0.0012) -[2023-11-28 07:38:44,836][87426] Updated weights for policy 1, policy_version 283670 (0.0009) -[2023-11-28 07:38:45,213][87426] Updated weights for policy 1, policy_version 283680 (0.0007) -[2023-11-28 07:38:46,103][87424] Updated weights for policy 0, policy_version 283878 (0.0009) -[2023-11-28 07:38:46,483][87424] Updated weights for policy 0, policy_version 283888 (0.0008) -[2023-11-28 07:38:46,865][87424] Updated weights for policy 0, policy_version 283898 (0.0010) -[2023-11-28 07:38:47,104][87426] Updated weights for policy 1, policy_version 283690 (0.0012) -[2023-11-28 07:38:47,483][87426] Updated weights for policy 1, policy_version 283700 (0.0012) -[2023-11-28 07:38:47,855][87426] Updated weights for policy 1, policy_version 283710 (0.0011) -[2023-11-28 07:38:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145309696. Throughput: 0: 2728.0, 1: 2753.2. Samples: 145318720. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:48,445][86177] Avg episode reward: [(0, '-637.780'), (1, '-551.610')] -[2023-11-28 07:38:48,800][87424] Updated weights for policy 0, policy_version 283908 (0.0012) -[2023-11-28 07:38:49,184][87424] Updated weights for policy 0, policy_version 283918 (0.0010) -[2023-11-28 07:38:49,565][87424] Updated weights for policy 0, policy_version 283928 (0.0012) -[2023-11-28 07:38:50,077][87426] Updated weights for policy 1, policy_version 283720 (0.0010) -[2023-11-28 07:38:50,458][87426] Updated weights for policy 1, policy_version 283730 (0.0011) -[2023-11-28 07:38:50,849][87426] Updated weights for policy 1, policy_version 283740 (0.0008) -[2023-11-28 07:38:51,598][87424] Updated weights for policy 0, policy_version 283938 (0.0012) -[2023-11-28 07:38:51,979][87424] Updated weights for policy 0, policy_version 283948 (0.0012) -[2023-11-28 07:38:52,347][87424] Updated weights for policy 0, policy_version 283958 (0.0012) -[2023-11-28 07:38:52,729][87424] Updated weights for policy 0, policy_version 283968 (0.0012) -[2023-11-28 07:38:53,253][87426] Updated weights for policy 1, policy_version 283750 (0.0010) -[2023-11-28 07:38:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145334272. Throughput: 0: 2768.4, 1: 2730.9. Samples: 145351388. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:53,445][86177] Avg episode reward: [(0, '-646.860'), (1, '-511.730')] -[2023-11-28 07:38:53,642][87426] Updated weights for policy 1, policy_version 283760 (0.0012) -[2023-11-28 07:38:54,023][87426] Updated weights for policy 1, policy_version 283770 (0.0009) -[2023-11-28 07:38:55,228][87424] Updated weights for policy 0, policy_version 283978 (0.0009) -[2023-11-28 07:38:55,614][87424] Updated weights for policy 0, policy_version 283988 (0.0011) -[2023-11-28 07:38:55,999][87424] Updated weights for policy 0, policy_version 283998 (0.0011) -[2023-11-28 07:38:56,520][87426] Updated weights for policy 1, policy_version 283780 (0.0007) -[2023-11-28 07:38:56,895][87426] Updated weights for policy 1, policy_version 283790 (0.0009) -[2023-11-28 07:38:57,282][87426] Updated weights for policy 1, policy_version 283800 (0.0010) -[2023-11-28 07:38:58,046][87424] Updated weights for policy 0, policy_version 284008 (0.0011) -[2023-11-28 07:38:58,425][87424] Updated weights for policy 0, policy_version 284018 (0.0012) -[2023-11-28 07:38:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145358848. Throughput: 0: 2766.2, 1: 2733.5. Samples: 145374928. Policy #0 lag: (min: 2.0, avg: 25.9, max: 38.0) -[2023-11-28 07:38:58,445][86177] Avg episode reward: [(0, '-635.920'), (1, '-515.380')] -[2023-11-28 07:38:58,813][87424] Updated weights for policy 0, policy_version 284028 (0.0012) -[2023-11-28 07:38:59,279][87426] Updated weights for policy 1, policy_version 283810 (0.0010) -[2023-11-28 07:38:59,662][87426] Updated weights for policy 1, policy_version 283820 (0.0012) -[2023-11-28 07:39:00,037][87426] Updated weights for policy 1, policy_version 283830 (0.0010) -[2023-11-28 07:39:00,413][87426] Updated weights for policy 1, policy_version 283840 (0.0008) -[2023-11-28 07:39:01,209][87424] Updated weights for policy 0, policy_version 284038 (0.0010) -[2023-11-28 07:39:01,587][87424] Updated weights for policy 0, policy_version 284048 (0.0009) -[2023-11-28 07:39:01,972][87424] Updated weights for policy 0, policy_version 284058 (0.0010) -[2023-11-28 07:39:02,977][87426] Updated weights for policy 1, policy_version 283850 (0.0008) -[2023-11-28 07:39:03,355][87426] Updated weights for policy 1, policy_version 283860 (0.0007) -[2023-11-28 07:39:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 145383424. Throughput: 0: 2762.8, 1: 2707.8. Samples: 145398788. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:03,445][86177] Avg episode reward: [(0, '-633.830'), (1, '-521.910')] -[2023-11-28 07:39:03,746][87426] Updated weights for policy 1, policy_version 283870 (0.0007) -[2023-11-28 07:39:03,996][87424] Updated weights for policy 0, policy_version 284068 (0.0010) -[2023-11-28 07:39:04,376][87424] Updated weights for policy 0, policy_version 284078 (0.0012) -[2023-11-28 07:39:04,758][87424] Updated weights for policy 0, policy_version 284088 (0.0010) -[2023-11-28 07:39:05,862][87426] Updated weights for policy 1, policy_version 283880 (0.0007) -[2023-11-28 07:39:06,248][87426] Updated weights for policy 1, policy_version 283890 (0.0009) -[2023-11-28 07:39:06,637][87426] Updated weights for policy 1, policy_version 283900 (0.0009) -[2023-11-28 07:39:06,946][87424] Updated weights for policy 0, policy_version 284098 (0.0011) -[2023-11-28 07:39:07,329][87424] Updated weights for policy 0, policy_version 284108 (0.0008) -[2023-11-28 07:39:07,713][87424] Updated weights for policy 0, policy_version 284118 (0.0007) -[2023-11-28 07:39:08,095][87424] Updated weights for policy 0, policy_version 284128 (0.0007) -[2023-11-28 07:39:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 145416192. Throughput: 0: 2774.5, 1: 2733.3. Samples: 145432224. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:08,445][86177] Avg episode reward: [(0, '-646.440'), (1, '-528.090')] -[2023-11-28 07:39:08,459][87426] Updated weights for policy 1, policy_version 283910 (0.0008) -[2023-11-28 07:39:08,835][87426] Updated weights for policy 1, policy_version 283920 (0.0010) -[2023-11-28 07:39:09,220][87426] Updated weights for policy 1, policy_version 283930 (0.0011) -[2023-11-28 07:39:10,189][87424] Updated weights for policy 0, policy_version 284138 (0.0009) -[2023-11-28 07:39:10,575][87424] Updated weights for policy 0, policy_version 284148 (0.0010) -[2023-11-28 07:39:10,949][87424] Updated weights for policy 0, policy_version 284158 (0.0009) -[2023-11-28 07:39:11,809][87426] Updated weights for policy 1, policy_version 283940 (0.0011) -[2023-11-28 07:39:12,188][87426] Updated weights for policy 1, policy_version 283950 (0.0012) -[2023-11-28 07:39:12,562][87426] Updated weights for policy 1, policy_version 283960 (0.0012) -[2023-11-28 07:39:13,085][87424] Updated weights for policy 0, policy_version 284168 (0.0009) -[2023-11-28 07:39:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145440768. Throughput: 0: 2752.1, 1: 2738.4. Samples: 145456676. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:13,445][86177] Avg episode reward: [(0, '-614.560'), (1, '-548.510')] -[2023-11-28 07:39:13,467][87424] Updated weights for policy 0, policy_version 284178 (0.0008) -[2023-11-28 07:39:13,849][87424] Updated weights for policy 0, policy_version 284188 (0.0008) -[2023-11-28 07:39:14,507][87426] Updated weights for policy 1, policy_version 283970 (0.0010) -[2023-11-28 07:39:14,888][87426] Updated weights for policy 1, policy_version 283980 (0.0008) -[2023-11-28 07:39:15,265][87426] Updated weights for policy 1, policy_version 283990 (0.0010) -[2023-11-28 07:39:15,648][87426] Updated weights for policy 1, policy_version 284000 (0.0010) -[2023-11-28 07:39:16,357][87424] Updated weights for policy 0, policy_version 284198 (0.0010) -[2023-11-28 07:39:16,740][87424] Updated weights for policy 0, policy_version 284208 (0.0008) -[2023-11-28 07:39:17,133][87424] Updated weights for policy 0, policy_version 284218 (0.0008) -[2023-11-28 07:39:17,595][87426] Updated weights for policy 1, policy_version 284010 (0.0011) -[2023-11-28 07:39:17,967][87426] Updated weights for policy 1, policy_version 284020 (0.0010) -[2023-11-28 07:39:18,348][87426] Updated weights for policy 1, policy_version 284030 (0.0009) -[2023-11-28 07:39:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 145473536. Throughput: 0: 2713.8, 1: 2738.6. Samples: 145480940. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:18,445][86177] Avg episode reward: [(0, '-639.820'), (1, '-544.660')] -[2023-11-28 07:39:18,935][87424] Updated weights for policy 0, policy_version 284228 (0.0010) -[2023-11-28 07:39:19,310][87424] Updated weights for policy 0, policy_version 284238 (0.0008) -[2023-11-28 07:39:19,693][87424] Updated weights for policy 0, policy_version 284248 (0.0009) -[2023-11-28 07:39:20,839][87426] Updated weights for policy 1, policy_version 284040 (0.0010) -[2023-11-28 07:39:21,218][87426] Updated weights for policy 1, policy_version 284050 (0.0009) -[2023-11-28 07:39:21,596][87426] Updated weights for policy 1, policy_version 284060 (0.0009) -[2023-11-28 07:39:22,024][87424] Updated weights for policy 0, policy_version 284258 (0.0011) -[2023-11-28 07:39:22,409][87424] Updated weights for policy 0, policy_version 284268 (0.0012) -[2023-11-28 07:39:22,779][87424] Updated weights for policy 0, policy_version 284278 (0.0010) -[2023-11-28 07:39:23,166][87424] Updated weights for policy 0, policy_version 284288 (0.0008) -[2023-11-28 07:39:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 145498112. Throughput: 0: 2706.7, 1: 2699.7. Samples: 145513288. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:23,445][86177] Avg episode reward: [(0, '-629.490'), (1, '-555.300')] -[2023-11-28 07:39:23,670][87426] Updated weights for policy 1, policy_version 284070 (0.0012) -[2023-11-28 07:39:24,058][87426] Updated weights for policy 1, policy_version 284080 (0.0011) -[2023-11-28 07:39:24,430][87426] Updated weights for policy 1, policy_version 284090 (0.0007) -[2023-11-28 07:39:25,287][87424] Updated weights for policy 0, policy_version 284298 (0.0010) -[2023-11-28 07:39:25,663][87424] Updated weights for policy 0, policy_version 284308 (0.0012) -[2023-11-28 07:39:26,043][87424] Updated weights for policy 0, policy_version 284318 (0.0012) -[2023-11-28 07:39:26,150][87426] Updated weights for policy 1, policy_version 284100 (0.0008) -[2023-11-28 07:39:26,530][87426] Updated weights for policy 1, policy_version 284110 (0.0007) -[2023-11-28 07:39:26,919][87426] Updated weights for policy 1, policy_version 284120 (0.0007) -[2023-11-28 07:39:28,426][87424] Updated weights for policy 0, policy_version 284328 (0.0011) -[2023-11-28 07:39:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 145522688. Throughput: 0: 2697.9, 1: 2712.3. Samples: 145537616. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:28,445][86177] Avg episode reward: [(0, '-657.440'), (1, '-555.940')] -[2023-11-28 07:39:28,810][87424] Updated weights for policy 0, policy_version 284338 (0.0008) -[2023-11-28 07:39:29,195][87424] Updated weights for policy 0, policy_version 284348 (0.0011) -[2023-11-28 07:39:29,279][87426] Updated weights for policy 1, policy_version 284130 (0.0008) -[2023-11-28 07:39:29,666][87426] Updated weights for policy 1, policy_version 284140 (0.0010) -[2023-11-28 07:39:30,048][87426] Updated weights for policy 1, policy_version 284150 (0.0010) -[2023-11-28 07:39:30,427][87426] Updated weights for policy 1, policy_version 284160 (0.0009) -[2023-11-28 07:39:31,073][87424] Updated weights for policy 0, policy_version 284358 (0.0012) -[2023-11-28 07:39:31,457][87424] Updated weights for policy 0, policy_version 284368 (0.0012) -[2023-11-28 07:39:31,838][87424] Updated weights for policy 0, policy_version 284378 (0.0012) -[2023-11-28 07:39:32,422][87426] Updated weights for policy 1, policy_version 284170 (0.0012) -[2023-11-28 07:39:32,798][87426] Updated weights for policy 1, policy_version 284180 (0.0012) -[2023-11-28 07:39:33,177][87426] Updated weights for policy 1, policy_version 284190 (0.0012) -[2023-11-28 07:39:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 145555456. Throughput: 0: 2728.6, 1: 2717.1. Samples: 145563776. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:33,445][86177] Avg episode reward: [(0, '-668.050'), (1, '-555.580')] -[2023-11-28 07:39:33,809][87424] Updated weights for policy 0, policy_version 284388 (0.0012) -[2023-11-28 07:39:34,183][87424] Updated weights for policy 0, policy_version 284398 (0.0012) -[2023-11-28 07:39:34,555][87424] Updated weights for policy 0, policy_version 284408 (0.0012) -[2023-11-28 07:39:35,070][87426] Updated weights for policy 1, policy_version 284200 (0.0012) -[2023-11-28 07:39:35,450][87426] Updated weights for policy 1, policy_version 284210 (0.0008) -[2023-11-28 07:39:35,832][87426] Updated weights for policy 1, policy_version 284220 (0.0007) -[2023-11-28 07:39:36,890][87424] Updated weights for policy 0, policy_version 284418 (0.0011) -[2023-11-28 07:39:37,268][87424] Updated weights for policy 0, policy_version 284428 (0.0008) -[2023-11-28 07:39:37,648][87424] Updated weights for policy 0, policy_version 284438 (0.0008) -[2023-11-28 07:39:38,033][87424] Updated weights for policy 0, policy_version 284448 (0.0011) -[2023-11-28 07:39:38,050][87426] Updated weights for policy 1, policy_version 284230 (0.0010) -[2023-11-28 07:39:38,430][87426] Updated weights for policy 1, policy_version 284240 (0.0012) -[2023-11-28 07:39:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145580032. Throughput: 0: 2706.7, 1: 2743.6. Samples: 145596648. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:38,445][86177] Avg episode reward: [(0, '-662.950'), (1, '-557.400')] -[2023-11-28 07:39:38,805][87426] Updated weights for policy 1, policy_version 284250 (0.0010) -[2023-11-28 07:39:40,080][87424] Updated weights for policy 0, policy_version 284458 (0.0012) -[2023-11-28 07:39:40,467][87424] Updated weights for policy 0, policy_version 284468 (0.0012) -[2023-11-28 07:39:40,849][87424] Updated weights for policy 0, policy_version 284478 (0.0012) -[2023-11-28 07:39:40,988][87426] Updated weights for policy 1, policy_version 284260 (0.0011) -[2023-11-28 07:39:41,360][87426] Updated weights for policy 1, policy_version 284270 (0.0010) -[2023-11-28 07:39:41,733][87426] Updated weights for policy 1, policy_version 284280 (0.0011) -[2023-11-28 07:39:43,399][87424] Updated weights for policy 0, policy_version 284488 (0.0008) -[2023-11-28 07:39:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 145604608. Throughput: 0: 2725.8, 1: 2755.6. Samples: 145621588. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:43,445][86177] Avg episode reward: [(0, '-625.180'), (1, '-563.190')] -[2023-11-28 07:39:43,783][87424] Updated weights for policy 0, policy_version 284498 (0.0012) -[2023-11-28 07:39:43,894][87426] Updated weights for policy 1, policy_version 284290 (0.0010) -[2023-11-28 07:39:44,172][87424] Updated weights for policy 0, policy_version 284508 (0.0011) -[2023-11-28 07:39:44,264][87426] Updated weights for policy 1, policy_version 284300 (0.0008) -[2023-11-28 07:39:44,643][87426] Updated weights for policy 1, policy_version 284310 (0.0008) -[2023-11-28 07:39:45,026][87426] Updated weights for policy 1, policy_version 284320 (0.0009) -[2023-11-28 07:39:45,964][87424] Updated weights for policy 0, policy_version 284518 (0.0010) -[2023-11-28 07:39:46,347][87424] Updated weights for policy 0, policy_version 284528 (0.0009) -[2023-11-28 07:39:46,732][87424] Updated weights for policy 0, policy_version 284538 (0.0012) -[2023-11-28 07:39:47,151][87426] Updated weights for policy 1, policy_version 284330 (0.0012) -[2023-11-28 07:39:47,533][87426] Updated weights for policy 1, policy_version 284340 (0.0012) -[2023-11-28 07:39:47,913][87426] Updated weights for policy 1, policy_version 284350 (0.0012) -[2023-11-28 07:39:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 145637376. Throughput: 0: 2719.7, 1: 2764.2. Samples: 145645564. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:48,446][86177] Avg episode reward: [(0, '-639.960'), (1, '-547.850')] -[2023-11-28 07:39:49,127][87424] Updated weights for policy 0, policy_version 284548 (0.0011) -[2023-11-28 07:39:49,514][87424] Updated weights for policy 0, policy_version 284558 (0.0008) -[2023-11-28 07:39:49,898][87424] Updated weights for policy 0, policy_version 284568 (0.0009) -[2023-11-28 07:39:50,468][87426] Updated weights for policy 1, policy_version 284360 (0.0011) -[2023-11-28 07:39:50,846][87426] Updated weights for policy 1, policy_version 284370 (0.0011) -[2023-11-28 07:39:51,234][87426] Updated weights for policy 1, policy_version 284380 (0.0010) -[2023-11-28 07:39:51,881][87424] Updated weights for policy 0, policy_version 284578 (0.0012) -[2023-11-28 07:39:52,261][87424] Updated weights for policy 0, policy_version 284588 (0.0012) -[2023-11-28 07:39:52,640][87424] Updated weights for policy 0, policy_version 284598 (0.0012) -[2023-11-28 07:39:53,019][87424] Updated weights for policy 0, policy_version 284608 (0.0011) -[2023-11-28 07:39:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145661952. Throughput: 0: 2707.1, 1: 2741.8. Samples: 145677424. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:53,445][86177] Avg episode reward: [(0, '-676.600'), (1, '-546.490')] -[2023-11-28 07:39:53,614][87426] Updated weights for policy 1, policy_version 284390 (0.0011) -[2023-11-28 07:39:53,997][87426] Updated weights for policy 1, policy_version 284400 (0.0012) -[2023-11-28 07:39:54,379][87426] Updated weights for policy 1, policy_version 284410 (0.0012) -[2023-11-28 07:39:55,345][87424] Updated weights for policy 0, policy_version 284618 (0.0010) -[2023-11-28 07:39:55,728][87424] Updated weights for policy 0, policy_version 284628 (0.0011) -[2023-11-28 07:39:56,116][87424] Updated weights for policy 0, policy_version 284638 (0.0007) -[2023-11-28 07:39:56,219][87426] Updated weights for policy 1, policy_version 284420 (0.0011) -[2023-11-28 07:39:56,606][87426] Updated weights for policy 1, policy_version 284430 (0.0012) -[2023-11-28 07:39:56,993][87426] Updated weights for policy 1, policy_version 284440 (0.0011) -[2023-11-28 07:39:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145686528. Throughput: 0: 2729.4, 1: 2738.6. Samples: 145702736. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:39:58,445][86177] Avg episode reward: [(0, '-630.730'), (1, '-575.980')] -[2023-11-28 07:39:58,649][87424] Updated weights for policy 0, policy_version 284648 (0.0011) -[2023-11-28 07:39:59,037][87424] Updated weights for policy 0, policy_version 284658 (0.0012) -[2023-11-28 07:39:59,413][87424] Updated weights for policy 0, policy_version 284668 (0.0012) -[2023-11-28 07:39:59,578][87426] Updated weights for policy 1, policy_version 284450 (0.0011) -[2023-11-28 07:39:59,964][87426] Updated weights for policy 1, policy_version 284460 (0.0012) -[2023-11-28 07:40:00,341][87426] Updated weights for policy 1, policy_version 284470 (0.0012) -[2023-11-28 07:40:00,722][87426] Updated weights for policy 1, policy_version 284480 (0.0012) -[2023-11-28 07:40:01,494][87424] Updated weights for policy 0, policy_version 284678 (0.0010) -[2023-11-28 07:40:01,883][87424] Updated weights for policy 0, policy_version 284688 (0.0012) -[2023-11-28 07:40:02,261][87424] Updated weights for policy 0, policy_version 284698 (0.0011) -[2023-11-28 07:40:02,584][87426] Updated weights for policy 1, policy_version 284490 (0.0011) -[2023-11-28 07:40:02,961][87426] Updated weights for policy 1, policy_version 284500 (0.0010) -[2023-11-28 07:40:03,342][87426] Updated weights for policy 1, policy_version 284510 (0.0007) -[2023-11-28 07:40:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 145719296. Throughput: 0: 2739.6, 1: 2732.8. Samples: 145727196. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:40:03,445][86177] Avg episode reward: [(0, '-686.120'), (1, '-606.750')] -[2023-11-28 07:40:04,454][87424] Updated weights for policy 0, policy_version 284708 (0.0011) -[2023-11-28 07:40:04,820][87424] Updated weights for policy 0, policy_version 284718 (0.0012) -[2023-11-28 07:40:05,199][87424] Updated weights for policy 0, policy_version 284728 (0.0010) -[2023-11-28 07:40:05,254][87426] Updated weights for policy 1, policy_version 284520 (0.0011) -[2023-11-28 07:40:05,627][87426] Updated weights for policy 1, policy_version 284530 (0.0011) -[2023-11-28 07:40:06,006][87426] Updated weights for policy 1, policy_version 284540 (0.0007) -[2023-11-28 07:40:07,203][87424] Updated weights for policy 0, policy_version 284738 (0.0007) -[2023-11-28 07:40:07,585][87424] Updated weights for policy 0, policy_version 284748 (0.0011) -[2023-11-28 07:40:07,961][87424] Updated weights for policy 0, policy_version 284758 (0.0011) -[2023-11-28 07:40:08,054][87426] Updated weights for policy 1, policy_version 284550 (0.0009) -[2023-11-28 07:40:08,348][87424] Updated weights for policy 0, policy_version 284768 (0.0012) -[2023-11-28 07:40:08,438][87426] Updated weights for policy 1, policy_version 284560 (0.0012) -[2023-11-28 07:40:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145743872. Throughput: 0: 2724.8, 1: 2758.5. Samples: 145760036. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:40:08,445][86177] Avg episode reward: [(0, '-767.930'), (1, '-651.330')] -[2023-11-28 07:40:08,809][87426] Updated weights for policy 1, policy_version 284570 (0.0012) -[2023-11-28 07:40:10,037][87424] Updated weights for policy 0, policy_version 284778 (0.0010) -[2023-11-28 07:40:10,411][87424] Updated weights for policy 0, policy_version 284788 (0.0009) -[2023-11-28 07:40:10,793][87424] Updated weights for policy 0, policy_version 284798 (0.0011) -[2023-11-28 07:40:11,279][87426] Updated weights for policy 1, policy_version 284580 (0.0012) -[2023-11-28 07:40:11,661][87426] Updated weights for policy 1, policy_version 284590 (0.0012) -[2023-11-28 07:40:12,045][87426] Updated weights for policy 1, policy_version 284600 (0.0012) -[2023-11-28 07:40:12,718][87424] Updated weights for policy 0, policy_version 284808 (0.0011) -[2023-11-28 07:40:13,100][87424] Updated weights for policy 0, policy_version 284818 (0.0012) -[2023-11-28 07:40:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145768448. Throughput: 0: 2731.8, 1: 2731.8. Samples: 145783480. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 07:40:13,445][86177] Avg episode reward: [(0, '-875.830'), (1, '-644.930')] -[2023-11-28 07:40:13,485][87424] Updated weights for policy 0, policy_version 284828 (0.0012) -[2023-11-28 07:40:14,337][87426] Updated weights for policy 1, policy_version 284610 (0.0011) -[2023-11-28 07:40:14,707][87426] Updated weights for policy 1, policy_version 284620 (0.0012) -[2023-11-28 07:40:15,100][87426] Updated weights for policy 1, policy_version 284630 (0.0012) -[2023-11-28 07:40:15,479][87426] Updated weights for policy 1, policy_version 284640 (0.0009) -[2023-11-28 07:40:16,095][87424] Updated weights for policy 0, policy_version 284838 (0.0012) -[2023-11-28 07:40:16,473][87424] Updated weights for policy 0, policy_version 284848 (0.0012) -[2023-11-28 07:40:16,852][87424] Updated weights for policy 0, policy_version 284858 (0.0011) -[2023-11-28 07:40:18,009][87426] Updated weights for policy 1, policy_version 284650 (0.0012) -[2023-11-28 07:40:18,385][87426] Updated weights for policy 1, policy_version 284660 (0.0012) -[2023-11-28 07:40:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 145793024. Throughput: 0: 2694.0, 1: 2728.6. Samples: 145807796. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:40:18,445][86177] Avg episode reward: [(0, '-848.440'), (1, '-611.210')] -[2023-11-28 07:40:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000284864_72925184.pth... -[2023-11-28 07:40:18,491][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000282336_72278016.pth -[2023-11-28 07:40:18,766][87426] Updated weights for policy 1, policy_version 284670 (0.0012) -[2023-11-28 07:40:18,768][87424] Updated weights for policy 0, policy_version 284868 (0.0011) -[2023-11-28 07:40:18,832][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000284672_72876032.pth... -[2023-11-28 07:40:18,880][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000282080_72212480.pth -[2023-11-28 07:40:19,148][87424] Updated weights for policy 0, policy_version 284878 (0.0012) -[2023-11-28 07:40:19,531][87424] Updated weights for policy 0, policy_version 284888 (0.0009) -[2023-11-28 07:40:20,618][87426] Updated weights for policy 1, policy_version 284680 (0.0010) -[2023-11-28 07:40:20,990][87426] Updated weights for policy 1, policy_version 284690 (0.0010) -[2023-11-28 07:40:21,372][87426] Updated weights for policy 1, policy_version 284700 (0.0008) -[2023-11-28 07:40:21,993][87424] Updated weights for policy 0, policy_version 284898 (0.0010) -[2023-11-28 07:40:22,381][87424] Updated weights for policy 0, policy_version 284908 (0.0012) -[2023-11-28 07:40:22,753][87424] Updated weights for policy 0, policy_version 284918 (0.0011) -[2023-11-28 07:40:23,136][87424] Updated weights for policy 0, policy_version 284928 (0.0009) -[2023-11-28 07:40:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145825792. Throughput: 0: 2698.7, 1: 2702.9. Samples: 145839724. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:40:23,445][86177] Avg episode reward: [(0, '-843.030'), (1, '-607.290')] -[2023-11-28 07:40:23,760][87426] Updated weights for policy 1, policy_version 284710 (0.0010) -[2023-11-28 07:40:24,132][87426] Updated weights for policy 1, policy_version 284720 (0.0009) -[2023-11-28 07:40:24,510][87426] Updated weights for policy 1, policy_version 284730 (0.0008) -[2023-11-28 07:40:25,460][87424] Updated weights for policy 0, policy_version 284938 (0.0012) -[2023-11-28 07:40:25,833][87424] Updated weights for policy 0, policy_version 284948 (0.0012) -[2023-11-28 07:40:26,222][87424] Updated weights for policy 0, policy_version 284958 (0.0012) -[2023-11-28 07:40:27,068][87426] Updated weights for policy 1, policy_version 284740 (0.0008) -[2023-11-28 07:40:27,462][87426] Updated weights for policy 1, policy_version 284750 (0.0007) -[2023-11-28 07:40:27,830][87426] Updated weights for policy 1, policy_version 284760 (0.0007) -[2023-11-28 07:40:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 145850368. Throughput: 0: 2714.2, 1: 2692.9. Samples: 145864908. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:40:28,445][86177] Avg episode reward: [(0, '-798.740'), (1, '-602.910')] -[2023-11-28 07:40:28,630][87424] Updated weights for policy 0, policy_version 284968 (0.0012) -[2023-11-28 07:40:29,020][87424] Updated weights for policy 0, policy_version 284978 (0.0012) -[2023-11-28 07:40:29,395][87424] Updated weights for policy 0, policy_version 284988 (0.0011) -[2023-11-28 07:40:30,325][87426] Updated weights for policy 1, policy_version 284770 (0.0008) -[2023-11-28 07:40:30,705][87426] Updated weights for policy 1, policy_version 284780 (0.0012) -[2023-11-28 07:40:31,082][87426] Updated weights for policy 1, policy_version 284790 (0.0012) -[2023-11-28 07:40:31,455][87426] Updated weights for policy 1, policy_version 284800 (0.0012) -[2023-11-28 07:40:31,868][87424] Updated weights for policy 0, policy_version 284998 (0.0012) -[2023-11-28 07:40:32,245][87424] Updated weights for policy 0, policy_version 285008 (0.0012) -[2023-11-28 07:40:32,629][87424] Updated weights for policy 0, policy_version 285018 (0.0010) -[2023-11-28 07:40:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 145874944. Throughput: 0: 2726.4, 1: 2671.7. Samples: 145888476. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:40:33,445][86177] Avg episode reward: [(0, '-708.450'), (1, '-562.330')] -[2023-11-28 07:40:33,924][87426] Updated weights for policy 1, policy_version 284810 (0.0009) -[2023-11-28 07:40:34,300][87426] Updated weights for policy 1, policy_version 284820 (0.0011) -[2023-11-28 07:40:34,567][87424] Updated weights for policy 0, policy_version 285028 (0.0011) -[2023-11-28 07:40:34,677][87426] Updated weights for policy 1, policy_version 284830 (0.0012) -[2023-11-28 07:40:34,950][87424] Updated weights for policy 0, policy_version 285038 (0.0008) -[2023-11-28 07:40:35,336][87424] Updated weights for policy 0, policy_version 285048 (0.0008) -[2023-11-28 07:40:37,037][87424] Updated weights for policy 0, policy_version 285058 (0.0008) -[2023-11-28 07:40:37,061][87426] Updated weights for policy 1, policy_version 284840 (0.0009) -[2023-11-28 07:40:37,423][87424] Updated weights for policy 0, policy_version 285068 (0.0008) -[2023-11-28 07:40:37,436][87426] Updated weights for policy 1, policy_version 284850 (0.0012) -[2023-11-28 07:40:37,810][87424] Updated weights for policy 0, policy_version 285078 (0.0010) -[2023-11-28 07:40:37,815][87426] Updated weights for policy 1, policy_version 284860 (0.0011) -[2023-11-28 07:40:38,191][87424] Updated weights for policy 0, policy_version 285088 (0.0012) -[2023-11-28 07:40:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145907712. Throughput: 0: 2746.6, 1: 2674.4. Samples: 145921368. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:40:38,445][86177] Avg episode reward: [(0, '-633.090'), (1, '-568.780')] -[2023-11-28 07:40:39,563][87426] Updated weights for policy 1, policy_version 284870 (0.0011) -[2023-11-28 07:40:39,948][87426] Updated weights for policy 1, policy_version 284880 (0.0012) -[2023-11-28 07:40:40,269][87424] Updated weights for policy 0, policy_version 285098 (0.0012) -[2023-11-28 07:40:40,319][87426] Updated weights for policy 1, policy_version 284890 (0.0009) -[2023-11-28 07:40:40,639][87424] Updated weights for policy 0, policy_version 285108 (0.0011) -[2023-11-28 07:40:41,031][87424] Updated weights for policy 0, policy_version 285118 (0.0012) -[2023-11-28 07:40:42,766][87426] Updated weights for policy 1, policy_version 284900 (0.0010) -[2023-11-28 07:40:43,147][87426] Updated weights for policy 1, policy_version 284910 (0.0012) -[2023-11-28 07:40:43,206][87424] Updated weights for policy 0, policy_version 285128 (0.0008) -[2023-11-28 07:40:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 145924096. Throughput: 0: 2754.4, 1: 2642.9. Samples: 145945616. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:40:43,445][86177] Avg episode reward: [(0, '-598.120'), (1, '-543.760')] -[2023-11-28 07:40:43,532][87426] Updated weights for policy 1, policy_version 284920 (0.0011) -[2023-11-28 07:40:43,594][87424] Updated weights for policy 0, policy_version 285138 (0.0009) -[2023-11-28 07:40:43,982][87424] Updated weights for policy 0, policy_version 285148 (0.0009) -[2023-11-28 07:40:46,114][87426] Updated weights for policy 1, policy_version 284930 (0.0010) -[2023-11-28 07:40:46,199][87424] Updated weights for policy 0, policy_version 285158 (0.0007) -[2023-11-28 07:40:46,489][87426] Updated weights for policy 1, policy_version 284940 (0.0012) -[2023-11-28 07:40:46,577][87424] Updated weights for policy 0, policy_version 285168 (0.0008) -[2023-11-28 07:40:46,862][87426] Updated weights for policy 1, policy_version 284950 (0.0012) -[2023-11-28 07:40:46,956][87424] Updated weights for policy 0, policy_version 285178 (0.0011) -[2023-11-28 07:40:47,245][87426] Updated weights for policy 1, policy_version 284960 (0.0011) -[2023-11-28 07:40:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 145956864. Throughput: 0: 2762.7, 1: 2635.6. Samples: 145970120. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:40:48,445][86177] Avg episode reward: [(0, '-602.120'), (1, '-538.110')] -[2023-11-28 07:40:48,755][87424] Updated weights for policy 0, policy_version 285188 (0.0012) -[2023-11-28 07:40:49,130][87424] Updated weights for policy 0, policy_version 285198 (0.0011) -[2023-11-28 07:40:49,312][87426] Updated weights for policy 1, policy_version 284970 (0.0011) -[2023-11-28 07:40:49,512][87424] Updated weights for policy 0, policy_version 285208 (0.0008) -[2023-11-28 07:40:49,688][87426] Updated weights for policy 1, policy_version 284980 (0.0009) -[2023-11-28 07:40:50,068][87426] Updated weights for policy 1, policy_version 284990 (0.0010) -[2023-11-28 07:40:51,956][87424] Updated weights for policy 0, policy_version 285218 (0.0008) -[2023-11-28 07:40:52,109][87426] Updated weights for policy 1, policy_version 285000 (0.0010) -[2023-11-28 07:40:52,333][87424] Updated weights for policy 0, policy_version 285228 (0.0011) -[2023-11-28 07:40:52,488][87426] Updated weights for policy 1, policy_version 285010 (0.0012) -[2023-11-28 07:40:52,713][87424] Updated weights for policy 0, policy_version 285238 (0.0008) -[2023-11-28 07:40:52,869][87426] Updated weights for policy 1, policy_version 285020 (0.0010) -[2023-11-28 07:40:53,091][87424] Updated weights for policy 0, policy_version 285248 (0.0011) -[2023-11-28 07:40:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 145989632. Throughput: 0: 2769.9, 1: 2616.4. Samples: 146002424. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:40:53,445][86177] Avg episode reward: [(0, '-549.720'), (1, '-552.930')] -[2023-11-28 07:40:54,993][87426] Updated weights for policy 1, policy_version 285030 (0.0010) -[2023-11-28 07:40:55,373][87426] Updated weights for policy 1, policy_version 285040 (0.0008) -[2023-11-28 07:40:55,409][87424] Updated weights for policy 0, policy_version 285258 (0.0011) -[2023-11-28 07:40:55,746][87426] Updated weights for policy 1, policy_version 285050 (0.0007) -[2023-11-28 07:40:55,779][87424] Updated weights for policy 0, policy_version 285268 (0.0011) -[2023-11-28 07:40:56,167][87424] Updated weights for policy 0, policy_version 285278 (0.0012) -[2023-11-28 07:40:57,424][87426] Updated weights for policy 1, policy_version 285060 (0.0008) -[2023-11-28 07:40:57,797][87426] Updated weights for policy 1, policy_version 285070 (0.0007) -[2023-11-28 07:40:58,177][87426] Updated weights for policy 1, policy_version 285080 (0.0008) -[2023-11-28 07:40:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 146006016. Throughput: 0: 2760.0, 1: 2651.0. Samples: 146026976. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:40:58,445][86177] Avg episode reward: [(0, '-606.490'), (1, '-552.890')] -[2023-11-28 07:40:58,740][87424] Updated weights for policy 0, policy_version 285288 (0.0012) -[2023-11-28 07:40:59,128][87424] Updated weights for policy 0, policy_version 285298 (0.0012) -[2023-11-28 07:40:59,513][87424] Updated weights for policy 0, policy_version 285308 (0.0012) -[2023-11-28 07:41:00,709][87426] Updated weights for policy 1, policy_version 285090 (0.0010) -[2023-11-28 07:41:01,088][87426] Updated weights for policy 1, policy_version 285100 (0.0012) -[2023-11-28 07:41:01,371][87424] Updated weights for policy 0, policy_version 285318 (0.0011) -[2023-11-28 07:41:01,461][87426] Updated weights for policy 1, policy_version 285110 (0.0009) -[2023-11-28 07:41:01,753][87424] Updated weights for policy 0, policy_version 285328 (0.0012) -[2023-11-28 07:41:01,843][87426] Updated weights for policy 1, policy_version 285120 (0.0010) -[2023-11-28 07:41:02,130][87424] Updated weights for policy 0, policy_version 285338 (0.0012) -[2023-11-28 07:41:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 146038784. Throughput: 0: 2750.7, 1: 2651.8. Samples: 146050908. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:41:03,445][86177] Avg episode reward: [(0, '-644.480'), (1, '-561.520')] -[2023-11-28 07:41:04,026][87426] Updated weights for policy 1, policy_version 285130 (0.0012) -[2023-11-28 07:41:04,161][87424] Updated weights for policy 0, policy_version 285348 (0.0012) -[2023-11-28 07:41:04,401][87426] Updated weights for policy 1, policy_version 285140 (0.0008) -[2023-11-28 07:41:04,542][87424] Updated weights for policy 0, policy_version 285358 (0.0010) -[2023-11-28 07:41:04,785][87426] Updated weights for policy 1, policy_version 285150 (0.0008) -[2023-11-28 07:41:04,930][87424] Updated weights for policy 0, policy_version 285368 (0.0011) -[2023-11-28 07:41:06,654][87424] Updated weights for policy 0, policy_version 285378 (0.0012) -[2023-11-28 07:41:06,969][87426] Updated weights for policy 1, policy_version 285160 (0.0009) -[2023-11-28 07:41:07,036][87424] Updated weights for policy 0, policy_version 285388 (0.0008) -[2023-11-28 07:41:07,341][87426] Updated weights for policy 1, policy_version 285170 (0.0009) -[2023-11-28 07:41:07,419][87424] Updated weights for policy 0, policy_version 285398 (0.0008) -[2023-11-28 07:41:07,724][87426] Updated weights for policy 1, policy_version 285180 (0.0011) -[2023-11-28 07:41:07,801][87424] Updated weights for policy 0, policy_version 285408 (0.0010) -[2023-11-28 07:41:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 146071552. Throughput: 0: 2763.1, 1: 2674.8. Samples: 146084432. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:41:08,445][86177] Avg episode reward: [(0, '-752.350'), (1, '-578.530')] -[2023-11-28 07:41:09,994][87424] Updated weights for policy 0, policy_version 285418 (0.0008) -[2023-11-28 07:41:10,152][87426] Updated weights for policy 1, policy_version 285190 (0.0011) -[2023-11-28 07:41:10,377][87424] Updated weights for policy 0, policy_version 285428 (0.0008) -[2023-11-28 07:41:10,527][87426] Updated weights for policy 1, policy_version 285200 (0.0011) -[2023-11-28 07:41:10,744][87424] Updated weights for policy 0, policy_version 285438 (0.0010) -[2023-11-28 07:41:10,909][87426] Updated weights for policy 1, policy_version 285210 (0.0011) -[2023-11-28 07:41:12,759][87424] Updated weights for policy 0, policy_version 285448 (0.0012) -[2023-11-28 07:41:13,138][87424] Updated weights for policy 0, policy_version 285458 (0.0011) -[2023-11-28 07:41:13,209][87426] Updated weights for policy 1, policy_version 285220 (0.0011) -[2023-11-28 07:41:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 146087936. Throughput: 0: 2742.8, 1: 2669.3. Samples: 146108456. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:41:13,445][86177] Avg episode reward: [(0, '-754.730'), (1, '-579.760')] -[2023-11-28 07:41:13,509][87424] Updated weights for policy 0, policy_version 285468 (0.0010) -[2023-11-28 07:41:13,588][87426] Updated weights for policy 1, policy_version 285230 (0.0011) -[2023-11-28 07:41:13,963][87426] Updated weights for policy 1, policy_version 285240 (0.0012) -[2023-11-28 07:41:15,929][87426] Updated weights for policy 1, policy_version 285250 (0.0012) -[2023-11-28 07:41:16,011][87424] Updated weights for policy 0, policy_version 285478 (0.0010) -[2023-11-28 07:41:16,311][87426] Updated weights for policy 1, policy_version 285260 (0.0011) -[2023-11-28 07:41:16,383][87424] Updated weights for policy 0, policy_version 285488 (0.0010) -[2023-11-28 07:41:16,689][87426] Updated weights for policy 1, policy_version 285270 (0.0008) -[2023-11-28 07:41:16,766][87424] Updated weights for policy 0, policy_version 285498 (0.0012) -[2023-11-28 07:41:17,068][87426] Updated weights for policy 1, policy_version 285280 (0.0008) -[2023-11-28 07:41:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146120704. Throughput: 0: 2751.8, 1: 2703.0. Samples: 146133944. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:41:18,446][86177] Avg episode reward: [(0, '-750.520'), (1, '-591.640')] -[2023-11-28 07:41:19,013][87424] Updated weights for policy 0, policy_version 285508 (0.0010) -[2023-11-28 07:41:19,325][87426] Updated weights for policy 1, policy_version 285290 (0.0008) -[2023-11-28 07:41:19,401][87424] Updated weights for policy 0, policy_version 285518 (0.0009) -[2023-11-28 07:41:19,703][87426] Updated weights for policy 1, policy_version 285300 (0.0010) -[2023-11-28 07:41:19,788][87424] Updated weights for policy 0, policy_version 285528 (0.0011) -[2023-11-28 07:41:20,080][87426] Updated weights for policy 1, policy_version 285310 (0.0012) -[2023-11-28 07:41:22,040][87424] Updated weights for policy 0, policy_version 285538 (0.0011) -[2023-11-28 07:41:22,436][87424] Updated weights for policy 0, policy_version 285548 (0.0011) -[2023-11-28 07:41:22,567][87426] Updated weights for policy 1, policy_version 285320 (0.0009) -[2023-11-28 07:41:22,820][87424] Updated weights for policy 0, policy_version 285558 (0.0012) -[2023-11-28 07:41:22,951][87426] Updated weights for policy 1, policy_version 285330 (0.0009) -[2023-11-28 07:41:23,205][87424] Updated weights for policy 0, policy_version 285568 (0.0011) -[2023-11-28 07:41:23,321][87426] Updated weights for policy 1, policy_version 285340 (0.0008) -[2023-11-28 07:41:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 146145280. Throughput: 0: 2725.2, 1: 2697.1. Samples: 146165372. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:41:23,445][86177] Avg episode reward: [(0, '-756.560'), (1, '-564.810')] -[2023-11-28 07:41:25,072][87426] Updated weights for policy 1, policy_version 285350 (0.0009) -[2023-11-28 07:41:25,449][87426] Updated weights for policy 1, policy_version 285360 (0.0011) -[2023-11-28 07:41:25,641][87424] Updated weights for policy 0, policy_version 285578 (0.0011) -[2023-11-28 07:41:25,829][87426] Updated weights for policy 1, policy_version 285370 (0.0012) -[2023-11-28 07:41:26,030][87424] Updated weights for policy 0, policy_version 285588 (0.0011) -[2023-11-28 07:41:26,417][87424] Updated weights for policy 0, policy_version 285598 (0.0012) -[2023-11-28 07:41:27,962][87426] Updated weights for policy 1, policy_version 285380 (0.0008) -[2023-11-28 07:41:28,336][87426] Updated weights for policy 1, policy_version 285390 (0.0009) -[2023-11-28 07:41:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 146169856. Throughput: 0: 2704.3, 1: 2752.6. Samples: 146191176. Policy #0 lag: (min: 0.0, avg: 25.1, max: 35.0) -[2023-11-28 07:41:28,445][86177] Avg episode reward: [(0, '-785.950'), (1, '-545.180')] -[2023-11-28 07:41:28,516][87424] Updated weights for policy 0, policy_version 285608 (0.0010) -[2023-11-28 07:41:28,716][87426] Updated weights for policy 1, policy_version 285400 (0.0009) -[2023-11-28 07:41:28,898][87424] Updated weights for policy 0, policy_version 285618 (0.0011) -[2023-11-28 07:41:29,286][87424] Updated weights for policy 0, policy_version 285628 (0.0012) -[2023-11-28 07:41:30,462][87426] Updated weights for policy 1, policy_version 285410 (0.0009) -[2023-11-28 07:41:30,837][87426] Updated weights for policy 1, policy_version 285420 (0.0007) -[2023-11-28 07:41:31,216][87426] Updated weights for policy 1, policy_version 285430 (0.0007) -[2023-11-28 07:41:31,586][87424] Updated weights for policy 0, policy_version 285638 (0.0011) -[2023-11-28 07:41:31,598][87426] Updated weights for policy 1, policy_version 285440 (0.0008) -[2023-11-28 07:41:31,973][87424] Updated weights for policy 0, policy_version 285648 (0.0010) -[2023-11-28 07:41:32,357][87424] Updated weights for policy 0, policy_version 285658 (0.0009) -[2023-11-28 07:41:33,296][87426] Updated weights for policy 1, policy_version 285450 (0.0012) -[2023-11-28 07:41:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146202624. Throughput: 0: 2696.1, 1: 2765.9. Samples: 146215908. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:41:33,445][86177] Avg episode reward: [(0, '-698.970'), (1, '-524.980')] -[2023-11-28 07:41:33,678][87426] Updated weights for policy 1, policy_version 285460 (0.0012) -[2023-11-28 07:41:34,062][87426] Updated weights for policy 1, policy_version 285470 (0.0011) -[2023-11-28 07:41:34,173][87424] Updated weights for policy 0, policy_version 285668 (0.0009) -[2023-11-28 07:41:34,561][87424] Updated weights for policy 0, policy_version 285678 (0.0012) -[2023-11-28 07:41:34,948][87424] Updated weights for policy 0, policy_version 285688 (0.0012) -[2023-11-28 07:41:36,334][87426] Updated weights for policy 1, policy_version 285480 (0.0012) -[2023-11-28 07:41:36,713][87426] Updated weights for policy 1, policy_version 285490 (0.0012) -[2023-11-28 07:41:37,012][87424] Updated weights for policy 0, policy_version 285698 (0.0012) -[2023-11-28 07:41:37,094][87426] Updated weights for policy 1, policy_version 285500 (0.0011) -[2023-11-28 07:41:37,406][87424] Updated weights for policy 0, policy_version 285708 (0.0012) -[2023-11-28 07:41:37,792][87424] Updated weights for policy 0, policy_version 285718 (0.0011) -[2023-11-28 07:41:38,174][87424] Updated weights for policy 0, policy_version 285728 (0.0011) -[2023-11-28 07:41:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146235392. Throughput: 0: 2705.1, 1: 2791.2. Samples: 146249756. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:41:38,445][86177] Avg episode reward: [(0, '-722.310'), (1, '-517.640')] -[2023-11-28 07:41:39,355][87426] Updated weights for policy 1, policy_version 285510 (0.0010) -[2023-11-28 07:41:39,730][87426] Updated weights for policy 1, policy_version 285520 (0.0008) -[2023-11-28 07:41:40,117][87426] Updated weights for policy 1, policy_version 285530 (0.0012) -[2023-11-28 07:41:40,299][87424] Updated weights for policy 0, policy_version 285738 (0.0012) -[2023-11-28 07:41:40,677][87424] Updated weights for policy 0, policy_version 285748 (0.0010) -[2023-11-28 07:41:41,057][87424] Updated weights for policy 0, policy_version 285758 (0.0010) -[2023-11-28 07:41:42,083][87426] Updated weights for policy 1, policy_version 285540 (0.0011) -[2023-11-28 07:41:42,461][87426] Updated weights for policy 1, policy_version 285550 (0.0012) -[2023-11-28 07:41:42,839][87426] Updated weights for policy 1, policy_version 285560 (0.0012) -[2023-11-28 07:41:43,121][87424] Updated weights for policy 0, policy_version 285768 (0.0011) -[2023-11-28 07:41:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 146259968. Throughput: 0: 2711.0, 1: 2773.1. Samples: 146273760. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:41:43,445][86177] Avg episode reward: [(0, '-682.770'), (1, '-602.990')] -[2023-11-28 07:41:43,501][87424] Updated weights for policy 0, policy_version 285778 (0.0012) -[2023-11-28 07:41:43,885][87424] Updated weights for policy 0, policy_version 285788 (0.0012) -[2023-11-28 07:41:45,104][87426] Updated weights for policy 1, policy_version 285570 (0.0011) -[2023-11-28 07:41:45,482][87426] Updated weights for policy 1, policy_version 285580 (0.0012) -[2023-11-28 07:41:45,861][87426] Updated weights for policy 1, policy_version 285590 (0.0009) -[2023-11-28 07:41:45,932][87424] Updated weights for policy 0, policy_version 285798 (0.0011) -[2023-11-28 07:41:46,241][87426] Updated weights for policy 1, policy_version 285600 (0.0008) -[2023-11-28 07:41:46,313][87424] Updated weights for policy 0, policy_version 285808 (0.0011) -[2023-11-28 07:41:46,700][87424] Updated weights for policy 0, policy_version 285818 (0.0011) -[2023-11-28 07:41:48,297][87426] Updated weights for policy 1, policy_version 285610 (0.0008) -[2023-11-28 07:41:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146284544. Throughput: 0: 2728.0, 1: 2775.5. Samples: 146298568. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:41:48,446][86177] Avg episode reward: [(0, '-685.890'), (1, '-604.000')] -[2023-11-28 07:41:48,673][87426] Updated weights for policy 1, policy_version 285620 (0.0008) -[2023-11-28 07:41:48,931][87424] Updated weights for policy 0, policy_version 285828 (0.0009) -[2023-11-28 07:41:49,054][87426] Updated weights for policy 1, policy_version 285630 (0.0010) -[2023-11-28 07:41:49,310][87424] Updated weights for policy 0, policy_version 285838 (0.0011) -[2023-11-28 07:41:49,699][87424] Updated weights for policy 0, policy_version 285848 (0.0012) -[2023-11-28 07:41:50,873][87426] Updated weights for policy 1, policy_version 285640 (0.0011) -[2023-11-28 07:41:51,253][87426] Updated weights for policy 1, policy_version 285650 (0.0011) -[2023-11-28 07:41:51,629][87426] Updated weights for policy 1, policy_version 285660 (0.0012) -[2023-11-28 07:41:51,767][87424] Updated weights for policy 0, policy_version 285858 (0.0012) -[2023-11-28 07:41:52,151][87424] Updated weights for policy 0, policy_version 285868 (0.0012) -[2023-11-28 07:41:52,530][87424] Updated weights for policy 0, policy_version 285878 (0.0011) -[2023-11-28 07:41:52,923][87424] Updated weights for policy 0, policy_version 285888 (0.0012) -[2023-11-28 07:41:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146317312. Throughput: 0: 2727.8, 1: 2756.4. Samples: 146331224. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:41:53,445][86177] Avg episode reward: [(0, '-615.870'), (1, '-652.990')] -[2023-11-28 07:41:53,873][87426] Updated weights for policy 1, policy_version 285670 (0.0010) -[2023-11-28 07:41:54,244][87426] Updated weights for policy 1, policy_version 285680 (0.0011) -[2023-11-28 07:41:54,628][87426] Updated weights for policy 1, policy_version 285690 (0.0009) -[2023-11-28 07:41:55,452][87424] Updated weights for policy 0, policy_version 285898 (0.0012) -[2023-11-28 07:41:55,829][87424] Updated weights for policy 0, policy_version 285908 (0.0012) -[2023-11-28 07:41:56,207][87424] Updated weights for policy 0, policy_version 285918 (0.0012) -[2023-11-28 07:41:57,196][87426] Updated weights for policy 1, policy_version 285700 (0.0008) -[2023-11-28 07:41:57,583][87426] Updated weights for policy 1, policy_version 285710 (0.0008) -[2023-11-28 07:41:57,967][87426] Updated weights for policy 1, policy_version 285720 (0.0011) -[2023-11-28 07:41:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 146341888. Throughput: 0: 2730.9, 1: 2765.7. Samples: 146355800. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:41:58,445][86177] Avg episode reward: [(0, '-606.580'), (1, '-654.030')] -[2023-11-28 07:41:58,632][87424] Updated weights for policy 0, policy_version 285928 (0.0008) -[2023-11-28 07:41:59,021][87424] Updated weights for policy 0, policy_version 285938 (0.0009) -[2023-11-28 07:41:59,393][87424] Updated weights for policy 0, policy_version 285948 (0.0011) -[2023-11-28 07:42:00,233][87426] Updated weights for policy 1, policy_version 285730 (0.0011) -[2023-11-28 07:42:00,608][87426] Updated weights for policy 1, policy_version 285740 (0.0011) -[2023-11-28 07:42:00,982][87426] Updated weights for policy 1, policy_version 285750 (0.0010) -[2023-11-28 07:42:01,362][87426] Updated weights for policy 1, policy_version 285760 (0.0008) -[2023-11-28 07:42:01,501][87424] Updated weights for policy 0, policy_version 285958 (0.0009) -[2023-11-28 07:42:01,881][87424] Updated weights for policy 0, policy_version 285968 (0.0008) -[2023-11-28 07:42:02,272][87424] Updated weights for policy 0, policy_version 285978 (0.0009) -[2023-11-28 07:42:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146366464. Throughput: 0: 2722.7, 1: 2733.7. Samples: 146379480. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:42:03,445][86177] Avg episode reward: [(0, '-617.090'), (1, '-644.320')] -[2023-11-28 07:42:03,789][87426] Updated weights for policy 1, policy_version 285770 (0.0008) -[2023-11-28 07:42:04,061][87424] Updated weights for policy 0, policy_version 285988 (0.0008) -[2023-11-28 07:42:04,179][87426] Updated weights for policy 1, policy_version 285780 (0.0008) -[2023-11-28 07:42:04,431][87424] Updated weights for policy 0, policy_version 285998 (0.0011) -[2023-11-28 07:42:04,563][87426] Updated weights for policy 1, policy_version 285790 (0.0011) -[2023-11-28 07:42:04,819][87424] Updated weights for policy 0, policy_version 286008 (0.0012) -[2023-11-28 07:42:06,296][87426] Updated weights for policy 1, policy_version 285800 (0.0012) -[2023-11-28 07:42:06,675][87426] Updated weights for policy 1, policy_version 285810 (0.0012) -[2023-11-28 07:42:07,057][87426] Updated weights for policy 1, policy_version 285820 (0.0012) -[2023-11-28 07:42:07,379][87424] Updated weights for policy 0, policy_version 286018 (0.0012) -[2023-11-28 07:42:07,748][87424] Updated weights for policy 0, policy_version 286028 (0.0010) -[2023-11-28 07:42:08,135][87424] Updated weights for policy 0, policy_version 286038 (0.0007) -[2023-11-28 07:42:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 146391040. Throughput: 0: 2729.1, 1: 2758.2. Samples: 146412300. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:42:08,445][86177] Avg episode reward: [(0, '-660.860'), (1, '-572.920')] -[2023-11-28 07:42:08,516][87424] Updated weights for policy 0, policy_version 286048 (0.0007) -[2023-11-28 07:42:08,915][87426] Updated weights for policy 1, policy_version 285830 (0.0012) -[2023-11-28 07:42:09,290][87426] Updated weights for policy 1, policy_version 285840 (0.0012) -[2023-11-28 07:42:09,666][87426] Updated weights for policy 1, policy_version 285850 (0.0012) -[2023-11-28 07:42:10,207][87424] Updated weights for policy 0, policy_version 286058 (0.0010) -[2023-11-28 07:42:10,595][87424] Updated weights for policy 0, policy_version 286068 (0.0010) -[2023-11-28 07:42:10,977][87424] Updated weights for policy 0, policy_version 286078 (0.0009) -[2023-11-28 07:42:12,119][87426] Updated weights for policy 1, policy_version 285860 (0.0010) -[2023-11-28 07:42:12,491][87426] Updated weights for policy 1, policy_version 285870 (0.0010) -[2023-11-28 07:42:12,872][87426] Updated weights for policy 1, policy_version 285880 (0.0011) -[2023-11-28 07:42:13,076][87424] Updated weights for policy 0, policy_version 286088 (0.0012) -[2023-11-28 07:42:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 146423808. Throughput: 0: 2731.2, 1: 2721.3. Samples: 146436536. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:42:13,445][86177] Avg episode reward: [(0, '-681.490'), (1, '-627.170')] -[2023-11-28 07:42:13,458][87424] Updated weights for policy 0, policy_version 286098 (0.0012) -[2023-11-28 07:42:13,846][87424] Updated weights for policy 0, policy_version 286108 (0.0012) -[2023-11-28 07:42:15,391][87426] Updated weights for policy 1, policy_version 285890 (0.0009) -[2023-11-28 07:42:15,691][87424] Updated weights for policy 0, policy_version 286118 (0.0011) -[2023-11-28 07:42:15,761][87426] Updated weights for policy 1, policy_version 285900 (0.0012) -[2023-11-28 07:42:16,066][87424] Updated weights for policy 0, policy_version 286128 (0.0011) -[2023-11-28 07:42:16,143][87426] Updated weights for policy 1, policy_version 285910 (0.0009) -[2023-11-28 07:42:16,446][87424] Updated weights for policy 0, policy_version 286138 (0.0011) -[2023-11-28 07:42:16,522][87426] Updated weights for policy 1, policy_version 285920 (0.0008) -[2023-11-28 07:42:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 146448384. Throughput: 0: 2746.7, 1: 2698.9. Samples: 146460960. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:42:18,445][86177] Avg episode reward: [(0, '-745.240'), (1, '-604.870')] -[2023-11-28 07:42:18,527][87424] Updated weights for policy 0, policy_version 286148 (0.0010) -[2023-11-28 07:42:18,628][87426] Updated weights for policy 1, policy_version 285930 (0.0010) -[2023-11-28 07:42:18,921][87424] Updated weights for policy 0, policy_version 286158 (0.0008) -[2023-11-28 07:42:19,003][87426] Updated weights for policy 1, policy_version 285940 (0.0010) -[2023-11-28 07:42:19,297][87424] Updated weights for policy 0, policy_version 286168 (0.0008) -[2023-11-28 07:42:19,383][87426] Updated weights for policy 1, policy_version 285950 (0.0011) -[2023-11-28 07:42:19,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000285952_73203712.pth... -[2023-11-28 07:42:19,488][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000283392_72548352.pth -[2023-11-28 07:42:19,604][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000286176_73261056.pth... -[2023-11-28 07:42:19,651][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000283584_72597504.pth -[2023-11-28 07:42:21,441][87426] Updated weights for policy 1, policy_version 285960 (0.0011) -[2023-11-28 07:42:21,590][87424] Updated weights for policy 0, policy_version 286178 (0.0012) -[2023-11-28 07:42:21,818][87426] Updated weights for policy 1, policy_version 285970 (0.0009) -[2023-11-28 07:42:21,970][87424] Updated weights for policy 0, policy_version 286188 (0.0009) -[2023-11-28 07:42:22,200][87426] Updated weights for policy 1, policy_version 285980 (0.0009) -[2023-11-28 07:42:22,362][87424] Updated weights for policy 0, policy_version 286198 (0.0009) -[2023-11-28 07:42:22,736][87424] Updated weights for policy 0, policy_version 286208 (0.0008) -[2023-11-28 07:42:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 146481152. Throughput: 0: 2737.1, 1: 2677.5. Samples: 146493412. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:42:23,445][86177] Avg episode reward: [(0, '-737.500'), (1, '-598.010')] -[2023-11-28 07:42:24,657][87426] Updated weights for policy 1, policy_version 285990 (0.0009) -[2023-11-28 07:42:24,779][87424] Updated weights for policy 0, policy_version 286218 (0.0011) -[2023-11-28 07:42:25,040][87426] Updated weights for policy 1, policy_version 286000 (0.0009) -[2023-11-28 07:42:25,158][87424] Updated weights for policy 0, policy_version 286228 (0.0012) -[2023-11-28 07:42:25,419][87426] Updated weights for policy 1, policy_version 286010 (0.0007) -[2023-11-28 07:42:25,533][87424] Updated weights for policy 0, policy_version 286238 (0.0011) -[2023-11-28 07:42:27,390][87424] Updated weights for policy 0, policy_version 286248 (0.0012) -[2023-11-28 07:42:27,555][87426] Updated weights for policy 1, policy_version 286020 (0.0008) -[2023-11-28 07:42:27,781][87424] Updated weights for policy 0, policy_version 286258 (0.0008) -[2023-11-28 07:42:27,934][87426] Updated weights for policy 1, policy_version 286030 (0.0008) -[2023-11-28 07:42:28,165][87424] Updated weights for policy 0, policy_version 286268 (0.0010) -[2023-11-28 07:42:28,319][87426] Updated weights for policy 1, policy_version 286040 (0.0007) -[2023-11-28 07:42:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 146505728. Throughput: 0: 2747.6, 1: 2678.5. Samples: 146517936. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:42:28,445][86177] Avg episode reward: [(0, '-727.260'), (1, '-669.690')] -[2023-11-28 07:42:30,461][87424] Updated weights for policy 0, policy_version 286278 (0.0009) -[2023-11-28 07:42:30,730][87426] Updated weights for policy 1, policy_version 286050 (0.0008) -[2023-11-28 07:42:30,836][87424] Updated weights for policy 0, policy_version 286288 (0.0011) -[2023-11-28 07:42:31,108][87426] Updated weights for policy 1, policy_version 286060 (0.0009) -[2023-11-28 07:42:31,217][87424] Updated weights for policy 0, policy_version 286298 (0.0008) -[2023-11-28 07:42:31,490][87426] Updated weights for policy 1, policy_version 286070 (0.0007) -[2023-11-28 07:42:31,857][87426] Updated weights for policy 1, policy_version 286080 (0.0010) -[2023-11-28 07:42:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146530304. Throughput: 0: 2760.3, 1: 2674.9. Samples: 146543152. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:42:33,445][86177] Avg episode reward: [(0, '-685.240'), (1, '-675.830')] -[2023-11-28 07:42:33,641][87424] Updated weights for policy 0, policy_version 286308 (0.0008) -[2023-11-28 07:42:34,023][87424] Updated weights for policy 0, policy_version 286318 (0.0008) -[2023-11-28 07:42:34,341][87426] Updated weights for policy 1, policy_version 286090 (0.0008) -[2023-11-28 07:42:34,405][87424] Updated weights for policy 0, policy_version 286328 (0.0009) -[2023-11-28 07:42:34,716][87426] Updated weights for policy 1, policy_version 286100 (0.0008) -[2023-11-28 07:42:35,104][87426] Updated weights for policy 1, policy_version 286110 (0.0010) -[2023-11-28 07:42:36,382][87424] Updated weights for policy 0, policy_version 286338 (0.0010) -[2023-11-28 07:42:36,762][87424] Updated weights for policy 0, policy_version 286348 (0.0010) -[2023-11-28 07:42:37,142][87424] Updated weights for policy 0, policy_version 286358 (0.0010) -[2023-11-28 07:42:37,527][87424] Updated weights for policy 0, policy_version 286368 (0.0010) -[2023-11-28 07:42:37,609][87426] Updated weights for policy 1, policy_version 286120 (0.0008) -[2023-11-28 07:42:37,994][87426] Updated weights for policy 1, policy_version 286130 (0.0007) -[2023-11-28 07:42:38,377][87426] Updated weights for policy 1, policy_version 286140 (0.0007) -[2023-11-28 07:42:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 146554880. Throughput: 0: 2729.4, 1: 2665.2. Samples: 146573984. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:42:38,445][86177] Avg episode reward: [(0, '-640.920'), (1, '-653.710')] -[2023-11-28 07:42:40,037][87424] Updated weights for policy 0, policy_version 286378 (0.0009) -[2023-11-28 07:42:40,407][87424] Updated weights for policy 0, policy_version 286388 (0.0008) -[2023-11-28 07:42:40,790][87424] Updated weights for policy 0, policy_version 286398 (0.0010) -[2023-11-28 07:42:40,897][87426] Updated weights for policy 1, policy_version 286150 (0.0010) -[2023-11-28 07:42:41,276][87426] Updated weights for policy 1, policy_version 286160 (0.0012) -[2023-11-28 07:42:41,653][87426] Updated weights for policy 1, policy_version 286170 (0.0012) -[2023-11-28 07:42:43,341][87424] Updated weights for policy 0, policy_version 286408 (0.0011) -[2023-11-28 07:42:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 146579456. Throughput: 0: 2715.8, 1: 2649.5. Samples: 146597240. Policy #0 lag: (min: 28.0, avg: 38.8, max: 63.0) -[2023-11-28 07:42:43,445][86177] Avg episode reward: [(0, '-621.450'), (1, '-670.900')] -[2023-11-28 07:42:43,727][87424] Updated weights for policy 0, policy_version 286418 (0.0012) -[2023-11-28 07:42:43,821][87426] Updated weights for policy 1, policy_version 286180 (0.0012) -[2023-11-28 07:42:44,118][87424] Updated weights for policy 0, policy_version 286428 (0.0010) -[2023-11-28 07:42:44,199][87426] Updated weights for policy 1, policy_version 286190 (0.0010) -[2023-11-28 07:42:44,584][87426] Updated weights for policy 1, policy_version 286200 (0.0012) -[2023-11-28 07:42:46,491][87424] Updated weights for policy 0, policy_version 286438 (0.0009) -[2023-11-28 07:42:46,584][87426] Updated weights for policy 1, policy_version 286210 (0.0009) -[2023-11-28 07:42:46,880][87424] Updated weights for policy 0, policy_version 286448 (0.0012) -[2023-11-28 07:42:46,962][87426] Updated weights for policy 1, policy_version 286220 (0.0008) -[2023-11-28 07:42:47,272][87424] Updated weights for policy 0, policy_version 286458 (0.0011) -[2023-11-28 07:42:47,334][87426] Updated weights for policy 1, policy_version 286230 (0.0007) -[2023-11-28 07:42:47,715][87426] Updated weights for policy 1, policy_version 286240 (0.0007) -[2023-11-28 07:42:48,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146612224. Throughput: 0: 2702.6, 1: 2669.3. Samples: 146621220. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:42:48,446][86177] Avg episode reward: [(0, '-655.120'), (1, '-632.510')] -[2023-11-28 07:42:49,358][87424] Updated weights for policy 0, policy_version 286468 (0.0010) -[2023-11-28 07:42:49,756][87424] Updated weights for policy 0, policy_version 286478 (0.0008) -[2023-11-28 07:42:50,018][87426] Updated weights for policy 1, policy_version 286250 (0.0011) -[2023-11-28 07:42:50,134][87424] Updated weights for policy 0, policy_version 286488 (0.0010) -[2023-11-28 07:42:50,390][87426] Updated weights for policy 1, policy_version 286260 (0.0011) -[2023-11-28 07:42:50,775][87426] Updated weights for policy 1, policy_version 286270 (0.0010) -[2023-11-28 07:42:51,940][87424] Updated weights for policy 0, policy_version 286498 (0.0011) -[2023-11-28 07:42:52,322][87424] Updated weights for policy 0, policy_version 286508 (0.0010) -[2023-11-28 07:42:52,704][87424] Updated weights for policy 0, policy_version 286518 (0.0008) -[2023-11-28 07:42:52,983][87426] Updated weights for policy 1, policy_version 286280 (0.0011) -[2023-11-28 07:42:53,083][87424] Updated weights for policy 0, policy_version 286528 (0.0011) -[2023-11-28 07:42:53,356][87426] Updated weights for policy 1, policy_version 286290 (0.0010) -[2023-11-28 07:42:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 146636800. Throughput: 0: 2727.5, 1: 2639.6. Samples: 146653820. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:42:53,445][86177] Avg episode reward: [(0, '-620.450'), (1, '-619.610')] -[2023-11-28 07:42:53,736][87426] Updated weights for policy 1, policy_version 286300 (0.0010) -[2023-11-28 07:42:55,338][87424] Updated weights for policy 0, policy_version 286538 (0.0012) -[2023-11-28 07:42:55,699][87426] Updated weights for policy 1, policy_version 286310 (0.0011) -[2023-11-28 07:42:55,722][87424] Updated weights for policy 0, policy_version 286548 (0.0012) -[2023-11-28 07:42:56,072][87426] Updated weights for policy 1, policy_version 286320 (0.0011) -[2023-11-28 07:42:56,104][87424] Updated weights for policy 0, policy_version 286558 (0.0012) -[2023-11-28 07:42:56,452][87426] Updated weights for policy 1, policy_version 286330 (0.0012) -[2023-11-28 07:42:57,748][87424] Updated weights for policy 0, policy_version 286568 (0.0012) -[2023-11-28 07:42:58,128][87424] Updated weights for policy 0, policy_version 286578 (0.0008) -[2023-11-28 07:42:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 146661376. Throughput: 0: 2740.3, 1: 2677.1. Samples: 146680320. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:42:58,445][86177] Avg episode reward: [(0, '-611.490'), (1, '-574.360')] -[2023-11-28 07:42:58,448][87426] Updated weights for policy 1, policy_version 286340 (0.0011) -[2023-11-28 07:42:58,526][87424] Updated weights for policy 0, policy_version 286588 (0.0008) -[2023-11-28 07:42:58,826][87426] Updated weights for policy 1, policy_version 286350 (0.0007) -[2023-11-28 07:42:59,203][87426] Updated weights for policy 1, policy_version 286360 (0.0011) -[2023-11-28 07:43:00,800][87424] Updated weights for policy 0, policy_version 286598 (0.0010) -[2023-11-28 07:43:01,180][87424] Updated weights for policy 0, policy_version 286608 (0.0011) -[2023-11-28 07:43:01,572][87424] Updated weights for policy 0, policy_version 286618 (0.0011) -[2023-11-28 07:43:01,761][87426] Updated weights for policy 1, policy_version 286370 (0.0008) -[2023-11-28 07:43:02,137][87426] Updated weights for policy 1, policy_version 286380 (0.0009) -[2023-11-28 07:43:02,519][87426] Updated weights for policy 1, policy_version 286390 (0.0008) -[2023-11-28 07:43:02,892][87426] Updated weights for policy 1, policy_version 286400 (0.0009) -[2023-11-28 07:43:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 146694144. Throughput: 0: 2746.5, 1: 2671.5. Samples: 146704768. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:03,445][86177] Avg episode reward: [(0, '-600.000'), (1, '-548.570')] -[2023-11-28 07:43:03,714][87424] Updated weights for policy 0, policy_version 286628 (0.0009) -[2023-11-28 07:43:04,107][87424] Updated weights for policy 0, policy_version 286638 (0.0009) -[2023-11-28 07:43:04,475][87424] Updated weights for policy 0, policy_version 286648 (0.0008) -[2023-11-28 07:43:05,025][87426] Updated weights for policy 1, policy_version 286410 (0.0008) -[2023-11-28 07:43:05,400][87426] Updated weights for policy 1, policy_version 286420 (0.0008) -[2023-11-28 07:43:05,778][87426] Updated weights for policy 1, policy_version 286430 (0.0007) -[2023-11-28 07:43:06,180][87424] Updated weights for policy 0, policy_version 286658 (0.0008) -[2023-11-28 07:43:06,561][87424] Updated weights for policy 0, policy_version 286668 (0.0012) -[2023-11-28 07:43:06,948][87424] Updated weights for policy 0, policy_version 286678 (0.0008) -[2023-11-28 07:43:07,327][87424] Updated weights for policy 0, policy_version 286688 (0.0016) -[2023-11-28 07:43:07,782][87426] Updated weights for policy 1, policy_version 286440 (0.0011) -[2023-11-28 07:43:08,172][87426] Updated weights for policy 1, policy_version 286450 (0.0010) -[2023-11-28 07:43:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146718720. Throughput: 0: 2785.8, 1: 2665.7. Samples: 146738728. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:08,445][86177] Avg episode reward: [(0, '-620.190'), (1, '-542.070')] -[2023-11-28 07:43:08,539][87426] Updated weights for policy 1, policy_version 286460 (0.0010) -[2023-11-28 07:43:09,174][87424] Updated weights for policy 0, policy_version 286698 (0.0011) -[2023-11-28 07:43:09,561][87424] Updated weights for policy 0, policy_version 286708 (0.0011) -[2023-11-28 07:43:09,949][87424] Updated weights for policy 0, policy_version 286718 (0.0009) -[2023-11-28 07:43:10,913][87426] Updated weights for policy 1, policy_version 286470 (0.0012) -[2023-11-28 07:43:11,295][87426] Updated weights for policy 1, policy_version 286480 (0.0011) -[2023-11-28 07:43:11,687][87426] Updated weights for policy 1, policy_version 286490 (0.0009) -[2023-11-28 07:43:12,079][87424] Updated weights for policy 0, policy_version 286728 (0.0011) -[2023-11-28 07:43:12,467][87424] Updated weights for policy 0, policy_version 286738 (0.0012) -[2023-11-28 07:43:12,845][87424] Updated weights for policy 0, policy_version 286748 (0.0012) -[2023-11-28 07:43:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 146751488. Throughput: 0: 2794.3, 1: 2667.3. Samples: 146763708. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:13,445][86177] Avg episode reward: [(0, '-610.890'), (1, '-556.140')] -[2023-11-28 07:43:14,180][87426] Updated weights for policy 1, policy_version 286500 (0.0011) -[2023-11-28 07:43:14,558][87426] Updated weights for policy 1, policy_version 286510 (0.0008) -[2023-11-28 07:43:14,934][87426] Updated weights for policy 1, policy_version 286520 (0.0008) -[2023-11-28 07:43:15,016][87424] Updated weights for policy 0, policy_version 286758 (0.0009) -[2023-11-28 07:43:15,408][87424] Updated weights for policy 0, policy_version 286768 (0.0009) -[2023-11-28 07:43:15,780][87424] Updated weights for policy 0, policy_version 286778 (0.0010) -[2023-11-28 07:43:16,744][87426] Updated weights for policy 1, policy_version 286530 (0.0011) -[2023-11-28 07:43:17,121][87426] Updated weights for policy 1, policy_version 286540 (0.0013) -[2023-11-28 07:43:17,503][87426] Updated weights for policy 1, policy_version 286550 (0.0007) -[2023-11-28 07:43:17,881][87426] Updated weights for policy 1, policy_version 286560 (0.0007) -[2023-11-28 07:43:18,274][87424] Updated weights for policy 0, policy_version 286788 (0.0009) -[2023-11-28 07:43:18,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 146776064. Throughput: 0: 2761.0, 1: 2676.6. Samples: 146787844. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:18,446][86177] Avg episode reward: [(0, '-616.750'), (1, '-557.970')] -[2023-11-28 07:43:18,647][87424] Updated weights for policy 0, policy_version 286798 (0.0011) -[2023-11-28 07:43:19,028][87424] Updated weights for policy 0, policy_version 286808 (0.0011) -[2023-11-28 07:43:20,324][87426] Updated weights for policy 1, policy_version 286570 (0.0008) -[2023-11-28 07:43:20,706][87426] Updated weights for policy 1, policy_version 286580 (0.0008) -[2023-11-28 07:43:21,082][87426] Updated weights for policy 1, policy_version 286590 (0.0008) -[2023-11-28 07:43:21,569][87424] Updated weights for policy 0, policy_version 286818 (0.0011) -[2023-11-28 07:43:21,939][87424] Updated weights for policy 0, policy_version 286828 (0.0013) -[2023-11-28 07:43:22,324][87424] Updated weights for policy 0, policy_version 286838 (0.0009) -[2023-11-28 07:43:22,705][87424] Updated weights for policy 0, policy_version 286848 (0.0011) -[2023-11-28 07:43:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 146800640. Throughput: 0: 2770.0, 1: 2669.1. Samples: 146818748. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:23,445][86177] Avg episode reward: [(0, '-614.390'), (1, '-578.960')] -[2023-11-28 07:43:23,631][87426] Updated weights for policy 1, policy_version 286600 (0.0011) -[2023-11-28 07:43:24,015][87426] Updated weights for policy 1, policy_version 286610 (0.0012) -[2023-11-28 07:43:24,390][87426] Updated weights for policy 1, policy_version 286620 (0.0011) -[2023-11-28 07:43:25,105][87424] Updated weights for policy 0, policy_version 286858 (0.0011) -[2023-11-28 07:43:25,487][87424] Updated weights for policy 0, policy_version 286868 (0.0011) -[2023-11-28 07:43:25,868][87424] Updated weights for policy 0, policy_version 286878 (0.0012) -[2023-11-28 07:43:26,188][87426] Updated weights for policy 1, policy_version 286630 (0.0011) -[2023-11-28 07:43:26,560][87426] Updated weights for policy 1, policy_version 286640 (0.0011) -[2023-11-28 07:43:26,932][87426] Updated weights for policy 1, policy_version 286650 (0.0011) -[2023-11-28 07:43:28,250][87424] Updated weights for policy 0, policy_version 286888 (0.0010) -[2023-11-28 07:43:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 146825216. Throughput: 0: 2782.8, 1: 2712.2. Samples: 146844516. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:28,445][86177] Avg episode reward: [(0, '-620.910'), (1, '-659.080')] -[2023-11-28 07:43:28,631][87424] Updated weights for policy 0, policy_version 286898 (0.0009) -[2023-11-28 07:43:28,886][87426] Updated weights for policy 1, policy_version 286660 (0.0012) -[2023-11-28 07:43:29,019][87424] Updated weights for policy 0, policy_version 286908 (0.0011) -[2023-11-28 07:43:29,267][87426] Updated weights for policy 1, policy_version 286670 (0.0011) -[2023-11-28 07:43:29,644][87426] Updated weights for policy 1, policy_version 286680 (0.0012) -[2023-11-28 07:43:30,915][87424] Updated weights for policy 0, policy_version 286918 (0.0012) -[2023-11-28 07:43:31,281][87424] Updated weights for policy 0, policy_version 286928 (0.0012) -[2023-11-28 07:43:31,700][87424] Updated weights for policy 0, policy_version 286939 (0.0009) -[2023-11-28 07:43:31,825][87426] Updated weights for policy 1, policy_version 286690 (0.0012) -[2023-11-28 07:43:32,209][87426] Updated weights for policy 1, policy_version 286700 (0.0011) -[2023-11-28 07:43:32,590][87426] Updated weights for policy 1, policy_version 286710 (0.0011) -[2023-11-28 07:43:32,974][87426] Updated weights for policy 1, policy_version 286720 (0.0011) -[2023-11-28 07:43:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146857984. Throughput: 0: 2787.0, 1: 2717.9. Samples: 146868940. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:33,445][86177] Avg episode reward: [(0, '-649.060'), (1, '-669.990')] -[2023-11-28 07:43:33,566][87424] Updated weights for policy 0, policy_version 286949 (0.0010) -[2023-11-28 07:43:33,948][87424] Updated weights for policy 0, policy_version 286959 (0.0012) -[2023-11-28 07:43:34,327][87424] Updated weights for policy 0, policy_version 286969 (0.0012) -[2023-11-28 07:43:35,084][87426] Updated weights for policy 1, policy_version 286730 (0.0011) -[2023-11-28 07:43:35,456][87426] Updated weights for policy 1, policy_version 286740 (0.0009) -[2023-11-28 07:43:35,840][87426] Updated weights for policy 1, policy_version 286750 (0.0007) -[2023-11-28 07:43:36,556][87424] Updated weights for policy 0, policy_version 286979 (0.0010) -[2023-11-28 07:43:36,942][87424] Updated weights for policy 0, policy_version 286989 (0.0008) -[2023-11-28 07:43:37,317][87424] Updated weights for policy 0, policy_version 286999 (0.0007) -[2023-11-28 07:43:38,309][87426] Updated weights for policy 1, policy_version 286760 (0.0008) -[2023-11-28 07:43:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146882560. Throughput: 0: 2756.4, 1: 2740.4. Samples: 146901176. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:38,445][86177] Avg episode reward: [(0, '-639.180'), (1, '-629.700')] -[2023-11-28 07:43:38,689][87426] Updated weights for policy 1, policy_version 286770 (0.0007) -[2023-11-28 07:43:39,078][87426] Updated weights for policy 1, policy_version 286780 (0.0010) -[2023-11-28 07:43:39,473][87424] Updated weights for policy 0, policy_version 287009 (0.0008) -[2023-11-28 07:43:39,874][87424] Updated weights for policy 0, policy_version 287019 (0.0008) -[2023-11-28 07:43:40,254][87424] Updated weights for policy 0, policy_version 287029 (0.0011) -[2023-11-28 07:43:40,637][87424] Updated weights for policy 0, policy_version 287039 (0.0011) -[2023-11-28 07:43:41,449][87426] Updated weights for policy 1, policy_version 286790 (0.0009) -[2023-11-28 07:43:41,841][87426] Updated weights for policy 1, policy_version 286800 (0.0009) -[2023-11-28 07:43:42,206][87426] Updated weights for policy 1, policy_version 286810 (0.0012) -[2023-11-28 07:43:42,822][87424] Updated weights for policy 0, policy_version 287049 (0.0012) -[2023-11-28 07:43:43,210][87424] Updated weights for policy 0, policy_version 287059 (0.0012) -[2023-11-28 07:43:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 146907136. Throughput: 0: 2752.3, 1: 2687.1. Samples: 146925092. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:43,445][86177] Avg episode reward: [(0, '-644.670'), (1, '-634.280')] -[2023-11-28 07:43:43,595][87424] Updated weights for policy 0, policy_version 287069 (0.0012) -[2023-11-28 07:43:44,330][87426] Updated weights for policy 1, policy_version 286820 (0.0012) -[2023-11-28 07:43:44,707][87426] Updated weights for policy 1, policy_version 286830 (0.0012) -[2023-11-28 07:43:45,080][87426] Updated weights for policy 1, policy_version 286840 (0.0011) -[2023-11-28 07:43:45,406][87424] Updated weights for policy 0, policy_version 287079 (0.0011) -[2023-11-28 07:43:45,786][87424] Updated weights for policy 0, policy_version 287089 (0.0011) -[2023-11-28 07:43:46,167][87424] Updated weights for policy 0, policy_version 287099 (0.0009) -[2023-11-28 07:43:46,881][87426] Updated weights for policy 1, policy_version 286850 (0.0010) -[2023-11-28 07:43:47,261][87426] Updated weights for policy 1, policy_version 286860 (0.0007) -[2023-11-28 07:43:47,639][87426] Updated weights for policy 1, policy_version 286870 (0.0007) -[2023-11-28 07:43:48,016][87426] Updated weights for policy 1, policy_version 286880 (0.0007) -[2023-11-28 07:43:48,283][87424] Updated weights for policy 0, policy_version 287109 (0.0007) -[2023-11-28 07:43:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 146939904. Throughput: 0: 2729.4, 1: 2712.5. Samples: 146949652. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:48,445][86177] Avg episode reward: [(0, '-603.930'), (1, '-618.610')] -[2023-11-28 07:43:48,676][87424] Updated weights for policy 0, policy_version 287119 (0.0011) -[2023-11-28 07:43:49,051][87424] Updated weights for policy 0, policy_version 287129 (0.0010) -[2023-11-28 07:43:50,261][87426] Updated weights for policy 1, policy_version 286890 (0.0010) -[2023-11-28 07:43:50,639][87426] Updated weights for policy 1, policy_version 286900 (0.0012) -[2023-11-28 07:43:51,020][87426] Updated weights for policy 1, policy_version 286910 (0.0009) -[2023-11-28 07:43:51,057][87424] Updated weights for policy 0, policy_version 287139 (0.0011) -[2023-11-28 07:43:51,438][87424] Updated weights for policy 0, policy_version 287149 (0.0012) -[2023-11-28 07:43:51,823][87424] Updated weights for policy 0, policy_version 287159 (0.0010) -[2023-11-28 07:43:53,107][87426] Updated weights for policy 1, policy_version 286920 (0.0011) -[2023-11-28 07:43:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 146964480. Throughput: 0: 2707.7, 1: 2709.6. Samples: 146982508. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:53,445][86177] Avg episode reward: [(0, '-568.790'), (1, '-609.380')] -[2023-11-28 07:43:53,489][87426] Updated weights for policy 1, policy_version 286930 (0.0012) -[2023-11-28 07:43:53,877][87426] Updated weights for policy 1, policy_version 286940 (0.0012) -[2023-11-28 07:43:54,388][87424] Updated weights for policy 0, policy_version 287169 (0.0009) -[2023-11-28 07:43:54,761][87424] Updated weights for policy 0, policy_version 287179 (0.0012) -[2023-11-28 07:43:55,144][87424] Updated weights for policy 0, policy_version 287189 (0.0012) -[2023-11-28 07:43:55,512][87424] Updated weights for policy 0, policy_version 287199 (0.0012) -[2023-11-28 07:43:55,946][87426] Updated weights for policy 1, policy_version 286950 (0.0010) -[2023-11-28 07:43:56,318][87426] Updated weights for policy 1, policy_version 286960 (0.0009) -[2023-11-28 07:43:56,702][87426] Updated weights for policy 1, policy_version 286970 (0.0007) -[2023-11-28 07:43:57,811][87424] Updated weights for policy 0, policy_version 287209 (0.0012) -[2023-11-28 07:43:58,194][87424] Updated weights for policy 0, policy_version 287219 (0.0011) -[2023-11-28 07:43:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 146989056. Throughput: 0: 2677.6, 1: 2715.6. Samples: 147006400. Policy #0 lag: (min: 31.0, avg: 39.7, max: 63.0) -[2023-11-28 07:43:58,445][86177] Avg episode reward: [(0, '-572.770'), (1, '-622.850')] -[2023-11-28 07:43:58,577][87424] Updated weights for policy 0, policy_version 287229 (0.0009) -[2023-11-28 07:43:58,869][87426] Updated weights for policy 1, policy_version 286980 (0.0009) -[2023-11-28 07:43:59,248][87426] Updated weights for policy 1, policy_version 286990 (0.0012) -[2023-11-28 07:43:59,625][87426] Updated weights for policy 1, policy_version 287000 (0.0007) -[2023-11-28 07:44:01,078][87424] Updated weights for policy 0, policy_version 287239 (0.0010) -[2023-11-28 07:44:01,461][87424] Updated weights for policy 0, policy_version 287249 (0.0008) -[2023-11-28 07:44:01,852][87424] Updated weights for policy 0, policy_version 287259 (0.0008) -[2023-11-28 07:44:02,129][87426] Updated weights for policy 1, policy_version 287010 (0.0010) -[2023-11-28 07:44:02,505][87426] Updated weights for policy 1, policy_version 287020 (0.0012) -[2023-11-28 07:44:02,888][87426] Updated weights for policy 1, policy_version 287030 (0.0012) -[2023-11-28 07:44:03,258][87426] Updated weights for policy 1, policy_version 287040 (0.0012) -[2023-11-28 07:44:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147021824. Throughput: 0: 2683.4, 1: 2707.2. Samples: 147030420. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:03,445][86177] Avg episode reward: [(0, '-573.980'), (1, '-613.170')] -[2023-11-28 07:44:04,240][87424] Updated weights for policy 0, policy_version 287269 (0.0010) -[2023-11-28 07:44:04,624][87424] Updated weights for policy 0, policy_version 287279 (0.0012) -[2023-11-28 07:44:05,005][87424] Updated weights for policy 0, policy_version 287289 (0.0012) -[2023-11-28 07:44:05,637][87426] Updated weights for policy 1, policy_version 287050 (0.0012) -[2023-11-28 07:44:06,008][87426] Updated weights for policy 1, policy_version 287060 (0.0012) -[2023-11-28 07:44:06,372][87426] Updated weights for policy 1, policy_version 287070 (0.0012) -[2023-11-28 07:44:07,022][87424] Updated weights for policy 0, policy_version 287299 (0.0011) -[2023-11-28 07:44:07,410][87424] Updated weights for policy 0, policy_version 287309 (0.0012) -[2023-11-28 07:44:07,783][87424] Updated weights for policy 0, policy_version 287319 (0.0012) -[2023-11-28 07:44:08,440][87426] Updated weights for policy 1, policy_version 287080 (0.0009) -[2023-11-28 07:44:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 147046400. Throughput: 0: 2703.0, 1: 2712.7. Samples: 147062456. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:08,445][86177] Avg episode reward: [(0, '-571.020'), (1, '-625.030')] -[2023-11-28 07:44:08,827][87426] Updated weights for policy 1, policy_version 287090 (0.0007) -[2023-11-28 07:44:09,207][87426] Updated weights for policy 1, policy_version 287100 (0.0008) -[2023-11-28 07:44:10,041][87424] Updated weights for policy 0, policy_version 287329 (0.0011) -[2023-11-28 07:44:10,420][87424] Updated weights for policy 0, policy_version 287339 (0.0012) -[2023-11-28 07:44:10,797][87424] Updated weights for policy 0, policy_version 287349 (0.0009) -[2023-11-28 07:44:11,180][87424] Updated weights for policy 0, policy_version 287359 (0.0010) -[2023-11-28 07:44:11,319][87426] Updated weights for policy 1, policy_version 287110 (0.0008) -[2023-11-28 07:44:11,700][87426] Updated weights for policy 1, policy_version 287120 (0.0009) -[2023-11-28 07:44:12,084][87426] Updated weights for policy 1, policy_version 287130 (0.0009) -[2023-11-28 07:44:13,210][87424] Updated weights for policy 0, policy_version 287369 (0.0012) -[2023-11-28 07:44:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 147070976. Throughput: 0: 2691.1, 1: 2674.5. Samples: 147085968. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:13,445][86177] Avg episode reward: [(0, '-562.820'), (1, '-627.760')] -[2023-11-28 07:44:13,587][87424] Updated weights for policy 0, policy_version 287379 (0.0012) -[2023-11-28 07:44:13,971][87424] Updated weights for policy 0, policy_version 287389 (0.0012) -[2023-11-28 07:44:14,454][87426] Updated weights for policy 1, policy_version 287140 (0.0009) -[2023-11-28 07:44:14,841][87426] Updated weights for policy 1, policy_version 287150 (0.0008) -[2023-11-28 07:44:15,225][87426] Updated weights for policy 1, policy_version 287160 (0.0007) -[2023-11-28 07:44:16,040][87424] Updated weights for policy 0, policy_version 287399 (0.0008) -[2023-11-28 07:44:16,419][87424] Updated weights for policy 0, policy_version 287409 (0.0008) -[2023-11-28 07:44:16,795][87424] Updated weights for policy 0, policy_version 287419 (0.0007) -[2023-11-28 07:44:17,183][87426] Updated weights for policy 1, policy_version 287170 (0.0008) -[2023-11-28 07:44:17,570][87426] Updated weights for policy 1, policy_version 287180 (0.0009) -[2023-11-28 07:44:17,940][87426] Updated weights for policy 1, policy_version 287190 (0.0012) -[2023-11-28 07:44:18,313][87426] Updated weights for policy 1, policy_version 287200 (0.0012) -[2023-11-28 07:44:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147103744. Throughput: 0: 2688.1, 1: 2675.5. Samples: 147110300. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:18,446][86177] Avg episode reward: [(0, '-562.900'), (1, '-654.880')] -[2023-11-28 07:44:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000287200_73523200.pth... -[2023-11-28 07:44:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000287424_73580544.pth... -[2023-11-28 07:44:18,497][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000284672_72876032.pth -[2023-11-28 07:44:18,505][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000284864_72925184.pth -[2023-11-28 07:44:18,963][87424] Updated weights for policy 0, policy_version 287429 (0.0009) -[2023-11-28 07:44:19,362][87424] Updated weights for policy 0, policy_version 287439 (0.0012) -[2023-11-28 07:44:19,740][87424] Updated weights for policy 0, policy_version 287449 (0.0012) -[2023-11-28 07:44:20,519][87426] Updated weights for policy 1, policy_version 287210 (0.0009) -[2023-11-28 07:44:20,906][87426] Updated weights for policy 1, policy_version 287220 (0.0008) -[2023-11-28 07:44:21,289][87426] Updated weights for policy 1, policy_version 287230 (0.0011) -[2023-11-28 07:44:21,944][87424] Updated weights for policy 0, policy_version 287459 (0.0012) -[2023-11-28 07:44:22,335][87424] Updated weights for policy 0, policy_version 287469 (0.0010) -[2023-11-28 07:44:22,716][87424] Updated weights for policy 0, policy_version 287479 (0.0012) -[2023-11-28 07:44:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147128320. Throughput: 0: 2695.6, 1: 2667.4. Samples: 147142508. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:23,445][86177] Avg episode reward: [(0, '-578.440'), (1, '-640.570')] -[2023-11-28 07:44:23,868][87426] Updated weights for policy 1, policy_version 287240 (0.0008) -[2023-11-28 07:44:24,259][87426] Updated weights for policy 1, policy_version 287250 (0.0007) -[2023-11-28 07:44:24,638][87426] Updated weights for policy 1, policy_version 287260 (0.0007) -[2023-11-28 07:44:25,039][87424] Updated weights for policy 0, policy_version 287489 (0.0012) -[2023-11-28 07:44:25,412][87424] Updated weights for policy 0, policy_version 287499 (0.0011) -[2023-11-28 07:44:25,800][87424] Updated weights for policy 0, policy_version 287509 (0.0007) -[2023-11-28 07:44:26,177][87424] Updated weights for policy 0, policy_version 287519 (0.0010) -[2023-11-28 07:44:27,121][87426] Updated weights for policy 1, policy_version 287270 (0.0010) -[2023-11-28 07:44:27,508][87426] Updated weights for policy 1, policy_version 287280 (0.0012) -[2023-11-28 07:44:27,881][87426] Updated weights for policy 1, policy_version 287290 (0.0012) -[2023-11-28 07:44:28,370][87424] Updated weights for policy 0, policy_version 287529 (0.0011) -[2023-11-28 07:44:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 147152896. Throughput: 0: 2690.8, 1: 2667.4. Samples: 147166212. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:28,445][86177] Avg episode reward: [(0, '-568.300'), (1, '-620.850')] -[2023-11-28 07:44:28,747][87424] Updated weights for policy 0, policy_version 287539 (0.0007) -[2023-11-28 07:44:29,127][87424] Updated weights for policy 0, policy_version 287549 (0.0010) -[2023-11-28 07:44:29,773][87426] Updated weights for policy 1, policy_version 287300 (0.0012) -[2023-11-28 07:44:30,146][87426] Updated weights for policy 1, policy_version 287310 (0.0010) -[2023-11-28 07:44:30,526][87426] Updated weights for policy 1, policy_version 287320 (0.0012) -[2023-11-28 07:44:31,087][87424] Updated weights for policy 0, policy_version 287559 (0.0012) -[2023-11-28 07:44:31,466][87424] Updated weights for policy 0, policy_version 287569 (0.0012) -[2023-11-28 07:44:31,844][87424] Updated weights for policy 0, policy_version 287579 (0.0011) -[2023-11-28 07:44:32,627][87426] Updated weights for policy 1, policy_version 287330 (0.0012) -[2023-11-28 07:44:33,002][87426] Updated weights for policy 1, policy_version 287340 (0.0011) -[2023-11-28 07:44:33,370][87426] Updated weights for policy 1, policy_version 287350 (0.0007) -[2023-11-28 07:44:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 147177472. Throughput: 0: 2703.6, 1: 2678.7. Samples: 147191856. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:33,445][86177] Avg episode reward: [(0, '-586.690'), (1, '-621.640')] -[2023-11-28 07:44:33,646][87424] Updated weights for policy 0, policy_version 287589 (0.0010) -[2023-11-28 07:44:33,748][87426] Updated weights for policy 1, policy_version 287360 (0.0011) -[2023-11-28 07:44:34,029][87424] Updated weights for policy 0, policy_version 287599 (0.0011) -[2023-11-28 07:44:34,398][87424] Updated weights for policy 0, policy_version 287609 (0.0012) -[2023-11-28 07:44:35,867][87426] Updated weights for policy 1, policy_version 287370 (0.0012) -[2023-11-28 07:44:36,243][87426] Updated weights for policy 1, policy_version 287380 (0.0012) -[2023-11-28 07:44:36,573][87424] Updated weights for policy 0, policy_version 287619 (0.0012) -[2023-11-28 07:44:36,632][87426] Updated weights for policy 1, policy_version 287390 (0.0012) -[2023-11-28 07:44:36,953][87424] Updated weights for policy 0, policy_version 287629 (0.0010) -[2023-11-28 07:44:37,341][87424] Updated weights for policy 0, policy_version 287639 (0.0011) -[2023-11-28 07:44:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147210240. Throughput: 0: 2686.0, 1: 2702.9. Samples: 147225008. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:38,445][86177] Avg episode reward: [(0, '-573.460'), (1, '-603.910')] -[2023-11-28 07:44:38,509][87426] Updated weights for policy 1, policy_version 287400 (0.0007) -[2023-11-28 07:44:38,885][87426] Updated weights for policy 1, policy_version 287410 (0.0008) -[2023-11-28 07:44:39,260][87426] Updated weights for policy 1, policy_version 287420 (0.0008) -[2023-11-28 07:44:39,525][87424] Updated weights for policy 0, policy_version 287649 (0.0009) -[2023-11-28 07:44:39,904][87424] Updated weights for policy 0, policy_version 287659 (0.0011) -[2023-11-28 07:44:40,293][87424] Updated weights for policy 0, policy_version 287669 (0.0009) -[2023-11-28 07:44:40,669][87424] Updated weights for policy 0, policy_version 287679 (0.0011) -[2023-11-28 07:44:41,803][87426] Updated weights for policy 1, policy_version 287430 (0.0010) -[2023-11-28 07:44:42,179][87426] Updated weights for policy 1, policy_version 287440 (0.0012) -[2023-11-28 07:44:42,564][87426] Updated weights for policy 1, policy_version 287450 (0.0012) -[2023-11-28 07:44:43,035][87424] Updated weights for policy 0, policy_version 287689 (0.0012) -[2023-11-28 07:44:43,419][87424] Updated weights for policy 0, policy_version 287699 (0.0012) -[2023-11-28 07:44:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 147234816. Throughput: 0: 2697.9, 1: 2695.3. Samples: 147249092. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:43,445][86177] Avg episode reward: [(0, '-591.350'), (1, '-585.110')] -[2023-11-28 07:44:43,799][87424] Updated weights for policy 0, policy_version 287709 (0.0012) -[2023-11-28 07:44:44,589][87426] Updated weights for policy 1, policy_version 287460 (0.0011) -[2023-11-28 07:44:44,958][87426] Updated weights for policy 1, policy_version 287470 (0.0012) -[2023-11-28 07:44:45,339][87426] Updated weights for policy 1, policy_version 287480 (0.0012) -[2023-11-28 07:44:46,092][87424] Updated weights for policy 0, policy_version 287719 (0.0012) -[2023-11-28 07:44:46,471][87424] Updated weights for policy 0, policy_version 287729 (0.0012) -[2023-11-28 07:44:46,849][87424] Updated weights for policy 0, policy_version 287739 (0.0009) -[2023-11-28 07:44:47,624][87426] Updated weights for policy 1, policy_version 287490 (0.0012) -[2023-11-28 07:44:48,005][87426] Updated weights for policy 1, policy_version 287500 (0.0012) -[2023-11-28 07:44:48,394][87426] Updated weights for policy 1, policy_version 287510 (0.0011) -[2023-11-28 07:44:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 147259392. Throughput: 0: 2698.6, 1: 2711.6. Samples: 147273876. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:48,445][86177] Avg episode reward: [(0, '-594.500'), (1, '-616.200')] -[2023-11-28 07:44:48,768][87426] Updated weights for policy 1, policy_version 287520 (0.0012) -[2023-11-28 07:44:49,202][87424] Updated weights for policy 0, policy_version 287749 (0.0007) -[2023-11-28 07:44:49,574][87424] Updated weights for policy 0, policy_version 287759 (0.0008) -[2023-11-28 07:44:49,945][87424] Updated weights for policy 0, policy_version 287769 (0.0011) -[2023-11-28 07:44:51,203][87426] Updated weights for policy 1, policy_version 287530 (0.0008) -[2023-11-28 07:44:51,575][87426] Updated weights for policy 1, policy_version 287540 (0.0010) -[2023-11-28 07:44:51,949][87426] Updated weights for policy 1, policy_version 287550 (0.0011) -[2023-11-28 07:44:52,108][87424] Updated weights for policy 0, policy_version 287779 (0.0009) -[2023-11-28 07:44:52,501][87424] Updated weights for policy 0, policy_version 287789 (0.0011) -[2023-11-28 07:44:52,878][87424] Updated weights for policy 0, policy_version 287799 (0.0012) -[2023-11-28 07:44:53,448][86177] Fps is (10 sec: 5732.3, 60 sec: 5461.0, 300 sec: 5442.8). Total num frames: 147292160. Throughput: 0: 2682.5, 1: 2714.3. Samples: 147305336. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:53,449][86177] Avg episode reward: [(0, '-584.380'), (1, '-598.090')] -[2023-11-28 07:44:54,071][87426] Updated weights for policy 1, policy_version 287560 (0.0011) -[2023-11-28 07:44:54,441][87426] Updated weights for policy 1, policy_version 287570 (0.0012) -[2023-11-28 07:44:54,819][87426] Updated weights for policy 1, policy_version 287580 (0.0010) -[2023-11-28 07:44:55,164][87424] Updated weights for policy 0, policy_version 287809 (0.0012) -[2023-11-28 07:44:55,534][87424] Updated weights for policy 0, policy_version 287819 (0.0012) -[2023-11-28 07:44:55,914][87424] Updated weights for policy 0, policy_version 287829 (0.0008) -[2023-11-28 07:44:56,293][87424] Updated weights for policy 0, policy_version 287839 (0.0010) -[2023-11-28 07:44:56,979][87426] Updated weights for policy 1, policy_version 287590 (0.0010) -[2023-11-28 07:44:57,357][87426] Updated weights for policy 1, policy_version 287600 (0.0011) -[2023-11-28 07:44:57,739][87426] Updated weights for policy 1, policy_version 287610 (0.0012) -[2023-11-28 07:44:58,191][87424] Updated weights for policy 0, policy_version 287849 (0.0011) -[2023-11-28 07:44:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 147316736. Throughput: 0: 2695.0, 1: 2723.5. Samples: 147329804. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:44:58,445][86177] Avg episode reward: [(0, '-585.970'), (1, '-589.550')] -[2023-11-28 07:44:58,561][87424] Updated weights for policy 0, policy_version 287859 (0.0011) -[2023-11-28 07:44:58,939][87424] Updated weights for policy 0, policy_version 287869 (0.0011) -[2023-11-28 07:45:00,134][87426] Updated weights for policy 1, policy_version 287620 (0.0011) -[2023-11-28 07:45:00,508][87426] Updated weights for policy 1, policy_version 287630 (0.0011) -[2023-11-28 07:45:00,877][87426] Updated weights for policy 1, policy_version 287640 (0.0008) -[2023-11-28 07:45:01,124][87424] Updated weights for policy 0, policy_version 287879 (0.0008) -[2023-11-28 07:45:01,503][87424] Updated weights for policy 0, policy_version 287889 (0.0011) -[2023-11-28 07:45:01,884][87424] Updated weights for policy 0, policy_version 287899 (0.0011) -[2023-11-28 07:45:03,312][87426] Updated weights for policy 1, policy_version 287650 (0.0007) -[2023-11-28 07:45:03,444][86177] Fps is (10 sec: 4917.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 147341312. Throughput: 0: 2726.9, 1: 2711.4. Samples: 147355020. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:45:03,445][86177] Avg episode reward: [(0, '-587.040'), (1, '-590.470')] -[2023-11-28 07:45:03,689][87426] Updated weights for policy 1, policy_version 287660 (0.0007) -[2023-11-28 07:45:04,069][87426] Updated weights for policy 1, policy_version 287670 (0.0007) -[2023-11-28 07:45:04,347][87424] Updated weights for policy 0, policy_version 287909 (0.0010) -[2023-11-28 07:45:04,442][87426] Updated weights for policy 1, policy_version 287680 (0.0009) -[2023-11-28 07:45:04,722][87424] Updated weights for policy 0, policy_version 287919 (0.0008) -[2023-11-28 07:45:05,101][87424] Updated weights for policy 0, policy_version 287929 (0.0008) -[2023-11-28 07:45:06,155][87426] Updated weights for policy 1, policy_version 287690 (0.0011) -[2023-11-28 07:45:06,541][87426] Updated weights for policy 1, policy_version 287700 (0.0008) -[2023-11-28 07:45:06,918][87426] Updated weights for policy 1, policy_version 287710 (0.0009) -[2023-11-28 07:45:07,071][87424] Updated weights for policy 0, policy_version 287939 (0.0009) -[2023-11-28 07:45:07,453][87424] Updated weights for policy 0, policy_version 287949 (0.0012) -[2023-11-28 07:45:07,837][87424] Updated weights for policy 0, policy_version 287959 (0.0012) -[2023-11-28 07:45:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147374080. Throughput: 0: 2727.4, 1: 2726.6. Samples: 147387936. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:45:08,445][86177] Avg episode reward: [(0, '-565.980'), (1, '-584.500')] -[2023-11-28 07:45:08,820][87426] Updated weights for policy 1, policy_version 287720 (0.0012) -[2023-11-28 07:45:09,196][87426] Updated weights for policy 1, policy_version 287730 (0.0012) -[2023-11-28 07:45:09,571][87426] Updated weights for policy 1, policy_version 287740 (0.0012) -[2023-11-28 07:45:10,201][87424] Updated weights for policy 0, policy_version 287969 (0.0012) -[2023-11-28 07:45:10,582][87424] Updated weights for policy 0, policy_version 287979 (0.0011) -[2023-11-28 07:45:10,967][87424] Updated weights for policy 0, policy_version 287989 (0.0011) -[2023-11-28 07:45:11,349][87424] Updated weights for policy 0, policy_version 287999 (0.0012) -[2023-11-28 07:45:11,502][87426] Updated weights for policy 1, policy_version 287750 (0.0012) -[2023-11-28 07:45:11,900][87426] Updated weights for policy 1, policy_version 287760 (0.0012) -[2023-11-28 07:45:12,281][87426] Updated weights for policy 1, policy_version 287770 (0.0011) -[2023-11-28 07:45:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147398656. Throughput: 0: 2728.7, 1: 2751.1. Samples: 147412804. Policy #0 lag: (min: 31.0, avg: 50.9, max: 84.0) -[2023-11-28 07:45:13,445][86177] Avg episode reward: [(0, '-573.630'), (1, '-564.950')] -[2023-11-28 07:45:13,520][87424] Updated weights for policy 0, policy_version 288009 (0.0011) -[2023-11-28 07:45:13,897][87424] Updated weights for policy 0, policy_version 288019 (0.0012) -[2023-11-28 07:45:14,281][87424] Updated weights for policy 0, policy_version 288029 (0.0012) -[2023-11-28 07:45:14,793][87426] Updated weights for policy 1, policy_version 287780 (0.0012) -[2023-11-28 07:45:15,168][87426] Updated weights for policy 1, policy_version 287790 (0.0012) -[2023-11-28 07:45:15,539][87426] Updated weights for policy 1, policy_version 287800 (0.0012) -[2023-11-28 07:45:16,313][87424] Updated weights for policy 0, policy_version 288039 (0.0010) -[2023-11-28 07:45:16,702][87424] Updated weights for policy 0, policy_version 288049 (0.0010) -[2023-11-28 07:45:17,098][87424] Updated weights for policy 0, policy_version 288059 (0.0012) -[2023-11-28 07:45:17,969][87426] Updated weights for policy 1, policy_version 287810 (0.0012) -[2023-11-28 07:45:18,351][87426] Updated weights for policy 1, policy_version 287820 (0.0012) -[2023-11-28 07:45:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 147423232. Throughput: 0: 2731.9, 1: 2731.7. Samples: 147437720. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:45:18,446][86177] Avg episode reward: [(0, '-564.890'), (1, '-567.700')] -[2023-11-28 07:45:18,733][87426] Updated weights for policy 1, policy_version 287830 (0.0012) -[2023-11-28 07:45:19,081][87424] Updated weights for policy 0, policy_version 288069 (0.0009) -[2023-11-28 07:45:19,115][87426] Updated weights for policy 1, policy_version 287840 (0.0012) -[2023-11-28 07:45:19,458][87424] Updated weights for policy 0, policy_version 288079 (0.0008) -[2023-11-28 07:45:19,843][87424] Updated weights for policy 0, policy_version 288089 (0.0008) -[2023-11-28 07:45:21,162][87426] Updated weights for policy 1, policy_version 287850 (0.0012) -[2023-11-28 07:45:21,540][87426] Updated weights for policy 1, policy_version 287860 (0.0012) -[2023-11-28 07:45:21,864][87424] Updated weights for policy 0, policy_version 288099 (0.0010) -[2023-11-28 07:45:21,908][87426] Updated weights for policy 1, policy_version 287870 (0.0012) -[2023-11-28 07:45:22,250][87424] Updated weights for policy 0, policy_version 288109 (0.0011) -[2023-11-28 07:45:22,642][87424] Updated weights for policy 0, policy_version 288119 (0.0012) -[2023-11-28 07:45:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147456000. Throughput: 0: 2750.8, 1: 2697.2. Samples: 147470168. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:45:23,445][86177] Avg episode reward: [(0, '-576.820'), (1, '-606.640')] -[2023-11-28 07:45:24,438][87426] Updated weights for policy 1, policy_version 287880 (0.0010) -[2023-11-28 07:45:24,810][87426] Updated weights for policy 1, policy_version 287890 (0.0008) -[2023-11-28 07:45:25,070][87424] Updated weights for policy 0, policy_version 288129 (0.0011) -[2023-11-28 07:45:25,200][87426] Updated weights for policy 1, policy_version 287900 (0.0008) -[2023-11-28 07:45:25,448][87424] Updated weights for policy 0, policy_version 288139 (0.0007) -[2023-11-28 07:45:25,844][87424] Updated weights for policy 0, policy_version 288149 (0.0012) -[2023-11-28 07:45:26,237][87424] Updated weights for policy 0, policy_version 288159 (0.0010) -[2023-11-28 07:45:26,969][87426] Updated weights for policy 1, policy_version 287910 (0.0008) -[2023-11-28 07:45:27,348][87426] Updated weights for policy 1, policy_version 287920 (0.0007) -[2023-11-28 07:45:27,730][87426] Updated weights for policy 1, policy_version 287930 (0.0007) -[2023-11-28 07:45:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147480576. Throughput: 0: 2746.1, 1: 2702.8. Samples: 147494292. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:45:28,445][86177] Avg episode reward: [(0, '-573.430'), (1, '-575.230')] -[2023-11-28 07:45:28,541][87424] Updated weights for policy 0, policy_version 288169 (0.0009) -[2023-11-28 07:45:28,922][87424] Updated weights for policy 0, policy_version 288179 (0.0008) -[2023-11-28 07:45:29,306][87424] Updated weights for policy 0, policy_version 288189 (0.0007) -[2023-11-28 07:45:30,199][87426] Updated weights for policy 1, policy_version 287940 (0.0009) -[2023-11-28 07:45:30,575][87426] Updated weights for policy 1, policy_version 287950 (0.0011) -[2023-11-28 07:45:30,956][87426] Updated weights for policy 1, policy_version 287960 (0.0011) -[2023-11-28 07:45:31,831][87424] Updated weights for policy 0, policy_version 288199 (0.0010) -[2023-11-28 07:45:32,209][87424] Updated weights for policy 0, policy_version 288209 (0.0024) -[2023-11-28 07:45:32,591][87424] Updated weights for policy 0, policy_version 288219 (0.0012) -[2023-11-28 07:45:32,884][87426] Updated weights for policy 1, policy_version 287970 (0.0008) -[2023-11-28 07:45:33,261][87426] Updated weights for policy 1, policy_version 287980 (0.0011) -[2023-11-28 07:45:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 147505152. Throughput: 0: 2738.7, 1: 2676.3. Samples: 147517548. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:45:33,445][86177] Avg episode reward: [(0, '-555.960'), (1, '-575.710')] -[2023-11-28 07:45:33,649][87426] Updated weights for policy 1, policy_version 287990 (0.0008) -[2023-11-28 07:45:34,034][87426] Updated weights for policy 1, policy_version 288000 (0.0011) -[2023-11-28 07:45:34,491][87424] Updated weights for policy 0, policy_version 288229 (0.0012) -[2023-11-28 07:45:34,871][87424] Updated weights for policy 0, policy_version 288239 (0.0011) -[2023-11-28 07:45:35,253][87424] Updated weights for policy 0, policy_version 288249 (0.0010) -[2023-11-28 07:45:36,099][87426] Updated weights for policy 1, policy_version 288010 (0.0007) -[2023-11-28 07:45:36,474][87426] Updated weights for policy 1, policy_version 288020 (0.0007) -[2023-11-28 07:45:36,853][87426] Updated weights for policy 1, policy_version 288030 (0.0008) -[2023-11-28 07:45:36,887][87424] Updated weights for policy 0, policy_version 288259 (0.0009) -[2023-11-28 07:45:37,273][87424] Updated weights for policy 0, policy_version 288269 (0.0008) -[2023-11-28 07:45:37,649][87424] Updated weights for policy 0, policy_version 288279 (0.0007) -[2023-11-28 07:45:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 147537920. Throughput: 0: 2764.2, 1: 2683.9. Samples: 147550480. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:45:38,445][86177] Avg episode reward: [(0, '-544.150'), (1, '-560.970')] -[2023-11-28 07:45:39,354][87426] Updated weights for policy 1, policy_version 288040 (0.0010) -[2023-11-28 07:45:39,736][87426] Updated weights for policy 1, policy_version 288050 (0.0011) -[2023-11-28 07:45:39,914][87424] Updated weights for policy 0, policy_version 288289 (0.0007) -[2023-11-28 07:45:40,121][87426] Updated weights for policy 1, policy_version 288060 (0.0009) -[2023-11-28 07:45:40,301][87424] Updated weights for policy 0, policy_version 288299 (0.0011) -[2023-11-28 07:45:40,683][87424] Updated weights for policy 0, policy_version 288309 (0.0010) -[2023-11-28 07:45:41,071][87424] Updated weights for policy 0, policy_version 288319 (0.0010) -[2023-11-28 07:45:42,148][87426] Updated weights for policy 1, policy_version 288070 (0.0011) -[2023-11-28 07:45:42,529][87426] Updated weights for policy 1, policy_version 288080 (0.0011) -[2023-11-28 07:45:42,917][87426] Updated weights for policy 1, policy_version 288090 (0.0012) -[2023-11-28 07:45:43,268][87424] Updated weights for policy 0, policy_version 288329 (0.0007) -[2023-11-28 07:45:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147562496. Throughput: 0: 2763.4, 1: 2678.7. Samples: 147574696. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:45:43,445][86177] Avg episode reward: [(0, '-525.370'), (1, '-537.460')] -[2023-11-28 07:45:43,638][87424] Updated weights for policy 0, policy_version 288339 (0.0010) -[2023-11-28 07:45:44,024][87424] Updated weights for policy 0, policy_version 288349 (0.0008) -[2023-11-28 07:45:44,736][87426] Updated weights for policy 1, policy_version 288100 (0.0011) -[2023-11-28 07:45:45,110][87426] Updated weights for policy 1, policy_version 288110 (0.0011) -[2023-11-28 07:45:45,488][87426] Updated weights for policy 1, policy_version 288120 (0.0012) -[2023-11-28 07:45:46,226][87424] Updated weights for policy 0, policy_version 288359 (0.0007) -[2023-11-28 07:45:46,608][87424] Updated weights for policy 0, policy_version 288369 (0.0009) -[2023-11-28 07:45:46,995][87424] Updated weights for policy 0, policy_version 288379 (0.0011) -[2023-11-28 07:45:47,784][87426] Updated weights for policy 1, policy_version 288130 (0.0009) -[2023-11-28 07:45:48,151][87426] Updated weights for policy 1, policy_version 288140 (0.0009) -[2023-11-28 07:45:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 147587072. Throughput: 0: 2739.7, 1: 2705.3. Samples: 147600048. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:45:48,445][86177] Avg episode reward: [(0, '-544.550'), (1, '-539.850')] -[2023-11-28 07:45:48,536][87426] Updated weights for policy 1, policy_version 288150 (0.0010) -[2023-11-28 07:45:48,928][87426] Updated weights for policy 1, policy_version 288160 (0.0008) -[2023-11-28 07:45:49,288][87424] Updated weights for policy 0, policy_version 288389 (0.0010) -[2023-11-28 07:45:49,659][87424] Updated weights for policy 0, policy_version 288399 (0.0010) -[2023-11-28 07:45:50,039][87424] Updated weights for policy 0, policy_version 288409 (0.0011) -[2023-11-28 07:45:51,196][87426] Updated weights for policy 1, policy_version 288170 (0.0012) -[2023-11-28 07:45:51,568][87426] Updated weights for policy 1, policy_version 288180 (0.0012) -[2023-11-28 07:45:51,957][87426] Updated weights for policy 1, policy_version 288190 (0.0010) -[2023-11-28 07:45:52,087][87424] Updated weights for policy 0, policy_version 288419 (0.0012) -[2023-11-28 07:45:52,471][87424] Updated weights for policy 0, policy_version 288429 (0.0012) -[2023-11-28 07:45:52,847][87424] Updated weights for policy 0, policy_version 288439 (0.0011) -[2023-11-28 07:45:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.7, 300 sec: 5470.6). Total num frames: 147619840. Throughput: 0: 2725.2, 1: 2698.8. Samples: 147632020. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:45:53,445][86177] Avg episode reward: [(0, '-566.380'), (1, '-560.120')] -[2023-11-28 07:45:54,140][87426] Updated weights for policy 1, policy_version 288200 (0.0011) -[2023-11-28 07:45:54,519][87426] Updated weights for policy 1, policy_version 288210 (0.0011) -[2023-11-28 07:45:54,898][87426] Updated weights for policy 1, policy_version 288220 (0.0012) -[2023-11-28 07:45:55,114][87424] Updated weights for policy 0, policy_version 288449 (0.0009) -[2023-11-28 07:45:55,496][87424] Updated weights for policy 0, policy_version 288459 (0.0007) -[2023-11-28 07:45:55,881][87424] Updated weights for policy 0, policy_version 288469 (0.0008) -[2023-11-28 07:45:56,257][87424] Updated weights for policy 0, policy_version 288479 (0.0007) -[2023-11-28 07:45:56,793][87426] Updated weights for policy 1, policy_version 288230 (0.0009) -[2023-11-28 07:45:57,183][87426] Updated weights for policy 1, policy_version 288240 (0.0008) -[2023-11-28 07:45:57,563][87426] Updated weights for policy 1, policy_version 288250 (0.0007) -[2023-11-28 07:45:58,251][87424] Updated weights for policy 0, policy_version 288489 (0.0007) -[2023-11-28 07:45:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147644416. Throughput: 0: 2713.7, 1: 2704.5. Samples: 147656624. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:45:58,446][86177] Avg episode reward: [(0, '-587.840'), (1, '-560.100')] -[2023-11-28 07:45:58,643][87424] Updated weights for policy 0, policy_version 288499 (0.0008) -[2023-11-28 07:45:59,027][87424] Updated weights for policy 0, policy_version 288509 (0.0009) -[2023-11-28 07:45:59,897][87426] Updated weights for policy 1, policy_version 288260 (0.0008) -[2023-11-28 07:46:00,269][87426] Updated weights for policy 1, policy_version 288270 (0.0008) -[2023-11-28 07:46:00,643][87426] Updated weights for policy 1, policy_version 288280 (0.0009) -[2023-11-28 07:46:01,143][87424] Updated weights for policy 0, policy_version 288519 (0.0011) -[2023-11-28 07:46:01,514][87424] Updated weights for policy 0, policy_version 288529 (0.0011) -[2023-11-28 07:46:01,903][87424] Updated weights for policy 0, policy_version 288539 (0.0012) -[2023-11-28 07:46:02,861][87426] Updated weights for policy 1, policy_version 288290 (0.0009) -[2023-11-28 07:46:03,237][87426] Updated weights for policy 1, policy_version 288300 (0.0012) -[2023-11-28 07:46:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 147668992. Throughput: 0: 2707.1, 1: 2701.9. Samples: 147681124. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:46:03,445][86177] Avg episode reward: [(0, '-584.040'), (1, '-553.210')] -[2023-11-28 07:46:03,626][87426] Updated weights for policy 1, policy_version 288310 (0.0011) -[2023-11-28 07:46:03,732][87424] Updated weights for policy 0, policy_version 288549 (0.0012) -[2023-11-28 07:46:03,995][87426] Updated weights for policy 1, policy_version 288320 (0.0010) -[2023-11-28 07:46:04,108][87424] Updated weights for policy 0, policy_version 288559 (0.0009) -[2023-11-28 07:46:04,489][87424] Updated weights for policy 0, policy_version 288569 (0.0008) -[2023-11-28 07:46:06,266][87426] Updated weights for policy 1, policy_version 288330 (0.0007) -[2023-11-28 07:46:06,657][87426] Updated weights for policy 1, policy_version 288340 (0.0007) -[2023-11-28 07:46:06,939][87424] Updated weights for policy 0, policy_version 288579 (0.0009) -[2023-11-28 07:46:07,028][87426] Updated weights for policy 1, policy_version 288350 (0.0009) -[2023-11-28 07:46:07,313][87424] Updated weights for policy 0, policy_version 288589 (0.0011) -[2023-11-28 07:46:07,696][87424] Updated weights for policy 0, policy_version 288599 (0.0012) -[2023-11-28 07:46:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 147701760. Throughput: 0: 2708.7, 1: 2729.5. Samples: 147714888. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:46:08,445][86177] Avg episode reward: [(0, '-566.310'), (1, '-540.770')] -[2023-11-28 07:46:08,817][87426] Updated weights for policy 1, policy_version 288360 (0.0012) -[2023-11-28 07:46:09,197][87426] Updated weights for policy 1, policy_version 288370 (0.0011) -[2023-11-28 07:46:09,577][87426] Updated weights for policy 1, policy_version 288380 (0.0012) -[2023-11-28 07:46:10,034][87424] Updated weights for policy 0, policy_version 288609 (0.0011) -[2023-11-28 07:46:10,410][87424] Updated weights for policy 0, policy_version 288619 (0.0016) -[2023-11-28 07:46:10,797][87424] Updated weights for policy 0, policy_version 288629 (0.0011) -[2023-11-28 07:46:11,177][87424] Updated weights for policy 0, policy_version 288639 (0.0010) -[2023-11-28 07:46:11,828][87426] Updated weights for policy 1, policy_version 288390 (0.0011) -[2023-11-28 07:46:12,201][87426] Updated weights for policy 1, policy_version 288400 (0.0009) -[2023-11-28 07:46:12,581][87426] Updated weights for policy 1, policy_version 288410 (0.0011) -[2023-11-28 07:46:13,277][87424] Updated weights for policy 0, policy_version 288649 (0.0010) -[2023-11-28 07:46:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147726336. Throughput: 0: 2713.8, 1: 2732.7. Samples: 147739384. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:46:13,445][86177] Avg episode reward: [(0, '-600.980'), (1, '-508.700')] -[2023-11-28 07:46:13,657][87424] Updated weights for policy 0, policy_version 288659 (0.0009) -[2023-11-28 07:46:14,036][87424] Updated weights for policy 0, policy_version 288669 (0.0007) -[2023-11-28 07:46:14,758][87426] Updated weights for policy 1, policy_version 288420 (0.0012) -[2023-11-28 07:46:15,131][87426] Updated weights for policy 1, policy_version 288430 (0.0011) -[2023-11-28 07:46:15,510][87426] Updated weights for policy 1, policy_version 288440 (0.0010) -[2023-11-28 07:46:16,241][87424] Updated weights for policy 0, policy_version 288679 (0.0010) -[2023-11-28 07:46:16,620][87424] Updated weights for policy 0, policy_version 288689 (0.0012) -[2023-11-28 07:46:16,996][87424] Updated weights for policy 0, policy_version 288699 (0.0012) -[2023-11-28 07:46:17,776][87426] Updated weights for policy 1, policy_version 288450 (0.0010) -[2023-11-28 07:46:18,161][87426] Updated weights for policy 1, policy_version 288460 (0.0007) -[2023-11-28 07:46:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147750912. Throughput: 0: 2740.8, 1: 2736.1. Samples: 147764008. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:46:18,445][86177] Avg episode reward: [(0, '-590.670'), (1, '-520.600')] -[2023-11-28 07:46:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000288704_73908224.pth... -[2023-11-28 07:46:18,487][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000286176_73261056.pth -[2023-11-28 07:46:18,546][87426] Updated weights for policy 1, policy_version 288470 (0.0007) -[2023-11-28 07:46:18,924][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000288480_73850880.pth... -[2023-11-28 07:46:18,924][87426] Updated weights for policy 1, policy_version 288480 (0.0008) -[2023-11-28 07:46:18,946][87424] Updated weights for policy 0, policy_version 288709 (0.0009) -[2023-11-28 07:46:18,956][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000285952_73203712.pth -[2023-11-28 07:46:19,327][87424] Updated weights for policy 0, policy_version 288719 (0.0012) -[2023-11-28 07:46:19,711][87424] Updated weights for policy 0, policy_version 288729 (0.0012) -[2023-11-28 07:46:21,152][87426] Updated weights for policy 1, policy_version 288490 (0.0008) -[2023-11-28 07:46:21,520][87426] Updated weights for policy 1, policy_version 288500 (0.0008) -[2023-11-28 07:46:21,902][87426] Updated weights for policy 1, policy_version 288510 (0.0010) -[2023-11-28 07:46:22,229][87424] Updated weights for policy 0, policy_version 288739 (0.0012) -[2023-11-28 07:46:22,615][87424] Updated weights for policy 0, policy_version 288749 (0.0008) -[2023-11-28 07:46:23,001][87424] Updated weights for policy 0, policy_version 288759 (0.0009) -[2023-11-28 07:46:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 147783680. Throughput: 0: 2730.4, 1: 2745.8. Samples: 147796908. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:46:23,445][86177] Avg episode reward: [(0, '-610.650'), (1, '-539.010')] -[2023-11-28 07:46:24,260][87426] Updated weights for policy 1, policy_version 288520 (0.0008) -[2023-11-28 07:46:24,635][87426] Updated weights for policy 1, policy_version 288530 (0.0008) -[2023-11-28 07:46:24,650][87424] Updated weights for policy 0, policy_version 288769 (0.0010) -[2023-11-28 07:46:25,016][87426] Updated weights for policy 1, policy_version 288540 (0.0010) -[2023-11-28 07:46:25,025][87424] Updated weights for policy 0, policy_version 288779 (0.0010) -[2023-11-28 07:46:25,407][87424] Updated weights for policy 0, policy_version 288789 (0.0011) -[2023-11-28 07:46:25,781][87424] Updated weights for policy 0, policy_version 288799 (0.0012) -[2023-11-28 07:46:27,410][87426] Updated weights for policy 1, policy_version 288550 (0.0009) -[2023-11-28 07:46:27,799][87426] Updated weights for policy 1, policy_version 288560 (0.0008) -[2023-11-28 07:46:27,878][87424] Updated weights for policy 0, policy_version 288809 (0.0008) -[2023-11-28 07:46:28,177][87426] Updated weights for policy 1, policy_version 288570 (0.0009) -[2023-11-28 07:46:28,272][87424] Updated weights for policy 0, policy_version 288819 (0.0010) -[2023-11-28 07:46:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147808256. Throughput: 0: 2716.8, 1: 2743.8. Samples: 147820424. Policy #0 lag: (min: 19.0, avg: 42.2, max: 51.0) -[2023-11-28 07:46:28,445][86177] Avg episode reward: [(0, '-607.710'), (1, '-550.320')] -[2023-11-28 07:46:28,654][87424] Updated weights for policy 0, policy_version 288829 (0.0011) -[2023-11-28 07:46:30,508][87426] Updated weights for policy 1, policy_version 288580 (0.0012) -[2023-11-28 07:46:30,883][87426] Updated weights for policy 1, policy_version 288590 (0.0010) -[2023-11-28 07:46:31,223][87424] Updated weights for policy 0, policy_version 288839 (0.0009) -[2023-11-28 07:46:31,262][87426] Updated weights for policy 1, policy_version 288600 (0.0008) -[2023-11-28 07:46:31,610][87424] Updated weights for policy 0, policy_version 288849 (0.0008) -[2023-11-28 07:46:31,988][87424] Updated weights for policy 0, policy_version 288859 (0.0011) -[2023-11-28 07:46:33,265][87426] Updated weights for policy 1, policy_version 288610 (0.0008) -[2023-11-28 07:46:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 147832832. Throughput: 0: 2722.5, 1: 2728.9. Samples: 147845360. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:46:33,445][86177] Avg episode reward: [(0, '-584.940'), (1, '-584.540')] -[2023-11-28 07:46:33,637][87426] Updated weights for policy 1, policy_version 288620 (0.0011) -[2023-11-28 07:46:34,015][87426] Updated weights for policy 1, policy_version 288630 (0.0011) -[2023-11-28 07:46:34,396][87426] Updated weights for policy 1, policy_version 288640 (0.0011) -[2023-11-28 07:46:34,506][87424] Updated weights for policy 0, policy_version 288869 (0.0009) -[2023-11-28 07:46:34,882][87424] Updated weights for policy 0, policy_version 288879 (0.0008) -[2023-11-28 07:46:35,273][87424] Updated weights for policy 0, policy_version 288889 (0.0008) -[2023-11-28 07:46:36,557][87426] Updated weights for policy 1, policy_version 288650 (0.0010) -[2023-11-28 07:46:36,935][87426] Updated weights for policy 1, policy_version 288660 (0.0009) -[2023-11-28 07:46:37,190][87424] Updated weights for policy 0, policy_version 288899 (0.0008) -[2023-11-28 07:46:37,313][87426] Updated weights for policy 1, policy_version 288670 (0.0008) -[2023-11-28 07:46:37,573][87424] Updated weights for policy 0, policy_version 288909 (0.0012) -[2023-11-28 07:46:37,954][87424] Updated weights for policy 0, policy_version 288919 (0.0012) -[2023-11-28 07:46:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147865600. Throughput: 0: 2731.2, 1: 2748.8. Samples: 147878620. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:46:38,445][86177] Avg episode reward: [(0, '-561.910'), (1, '-583.180')] -[2023-11-28 07:46:38,990][87426] Updated weights for policy 1, policy_version 288680 (0.0011) -[2023-11-28 07:46:39,369][87426] Updated weights for policy 1, policy_version 288690 (0.0011) -[2023-11-28 07:46:39,749][87426] Updated weights for policy 1, policy_version 288700 (0.0008) -[2023-11-28 07:46:39,921][87424] Updated weights for policy 0, policy_version 288929 (0.0012) -[2023-11-28 07:46:40,313][87424] Updated weights for policy 0, policy_version 288939 (0.0012) -[2023-11-28 07:46:40,692][87424] Updated weights for policy 0, policy_version 288949 (0.0010) -[2023-11-28 07:46:41,067][87424] Updated weights for policy 0, policy_version 288959 (0.0009) -[2023-11-28 07:46:41,858][87426] Updated weights for policy 1, policy_version 288710 (0.0011) -[2023-11-28 07:46:42,227][87426] Updated weights for policy 1, policy_version 288720 (0.0012) -[2023-11-28 07:46:42,612][87426] Updated weights for policy 1, policy_version 288730 (0.0012) -[2023-11-28 07:46:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147890176. Throughput: 0: 2748.4, 1: 2744.9. Samples: 147903820. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:46:43,445][86177] Avg episode reward: [(0, '-534.680'), (1, '-585.320')] -[2023-11-28 07:46:43,597][87424] Updated weights for policy 0, policy_version 288969 (0.0012) -[2023-11-28 07:46:43,989][87424] Updated weights for policy 0, policy_version 288979 (0.0012) -[2023-11-28 07:46:44,376][87424] Updated weights for policy 0, policy_version 288989 (0.0012) -[2023-11-28 07:46:44,735][87426] Updated weights for policy 1, policy_version 288740 (0.0012) -[2023-11-28 07:46:45,120][87426] Updated weights for policy 1, policy_version 288750 (0.0012) -[2023-11-28 07:46:45,494][87426] Updated weights for policy 1, policy_version 288760 (0.0009) -[2023-11-28 07:46:46,577][87424] Updated weights for policy 0, policy_version 288999 (0.0012) -[2023-11-28 07:46:46,955][87424] Updated weights for policy 0, policy_version 289009 (0.0012) -[2023-11-28 07:46:47,330][87424] Updated weights for policy 0, policy_version 289019 (0.0010) -[2023-11-28 07:46:47,820][87426] Updated weights for policy 1, policy_version 288770 (0.0008) -[2023-11-28 07:46:48,201][87426] Updated weights for policy 1, policy_version 288780 (0.0008) -[2023-11-28 07:46:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 147914752. Throughput: 0: 2731.7, 1: 2746.2. Samples: 147927632. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:46:48,445][86177] Avg episode reward: [(0, '-542.360'), (1, '-570.820')] -[2023-11-28 07:46:48,583][87426] Updated weights for policy 1, policy_version 288790 (0.0008) -[2023-11-28 07:46:48,963][87426] Updated weights for policy 1, policy_version 288800 (0.0008) -[2023-11-28 07:46:49,472][87424] Updated weights for policy 0, policy_version 289029 (0.0010) -[2023-11-28 07:46:49,852][87424] Updated weights for policy 0, policy_version 289039 (0.0011) -[2023-11-28 07:46:50,235][87424] Updated weights for policy 0, policy_version 289049 (0.0008) -[2023-11-28 07:46:50,995][87426] Updated weights for policy 1, policy_version 288810 (0.0011) -[2023-11-28 07:46:51,388][87426] Updated weights for policy 1, policy_version 288820 (0.0008) -[2023-11-28 07:46:51,761][87426] Updated weights for policy 1, policy_version 288830 (0.0010) -[2023-11-28 07:46:52,707][87424] Updated weights for policy 0, policy_version 289059 (0.0011) -[2023-11-28 07:46:53,088][87424] Updated weights for policy 0, policy_version 289069 (0.0008) -[2023-11-28 07:46:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 147939328. Throughput: 0: 2724.1, 1: 2726.6. Samples: 147960168. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:46:53,446][86177] Avg episode reward: [(0, '-556.250'), (1, '-547.400')] -[2023-11-28 07:46:53,473][87424] Updated weights for policy 0, policy_version 289079 (0.0009) -[2023-11-28 07:46:54,308][87426] Updated weights for policy 1, policy_version 288840 (0.0008) -[2023-11-28 07:46:54,686][87426] Updated weights for policy 1, policy_version 288850 (0.0009) -[2023-11-28 07:46:55,069][87426] Updated weights for policy 1, policy_version 288860 (0.0008) -[2023-11-28 07:46:55,724][87424] Updated weights for policy 0, policy_version 289089 (0.0009) -[2023-11-28 07:46:56,105][87424] Updated weights for policy 0, policy_version 289099 (0.0011) -[2023-11-28 07:46:56,503][87424] Updated weights for policy 0, policy_version 289109 (0.0012) -[2023-11-28 07:46:56,891][87424] Updated weights for policy 0, policy_version 289119 (0.0012) -[2023-11-28 07:46:57,062][87426] Updated weights for policy 1, policy_version 288870 (0.0010) -[2023-11-28 07:46:57,437][87426] Updated weights for policy 1, policy_version 288880 (0.0012) -[2023-11-28 07:46:57,815][87426] Updated weights for policy 1, policy_version 288890 (0.0012) -[2023-11-28 07:46:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 147972096. Throughput: 0: 2718.8, 1: 2740.0. Samples: 147985028. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:46:58,445][86177] Avg episode reward: [(0, '-536.320'), (1, '-542.430')] -[2023-11-28 07:46:58,689][87424] Updated weights for policy 0, policy_version 289129 (0.0012) -[2023-11-28 07:46:59,069][87424] Updated weights for policy 0, policy_version 289139 (0.0012) -[2023-11-28 07:46:59,446][87424] Updated weights for policy 0, policy_version 289149 (0.0010) -[2023-11-28 07:46:59,753][87426] Updated weights for policy 1, policy_version 288900 (0.0011) -[2023-11-28 07:47:00,133][87426] Updated weights for policy 1, policy_version 288910 (0.0009) -[2023-11-28 07:47:00,501][87426] Updated weights for policy 1, policy_version 288920 (0.0008) -[2023-11-28 07:47:01,435][87424] Updated weights for policy 0, policy_version 289159 (0.0011) -[2023-11-28 07:47:01,842][87424] Updated weights for policy 0, policy_version 289169 (0.0011) -[2023-11-28 07:47:02,214][87424] Updated weights for policy 0, policy_version 289179 (0.0010) -[2023-11-28 07:47:02,571][87426] Updated weights for policy 1, policy_version 288930 (0.0008) -[2023-11-28 07:47:02,955][87426] Updated weights for policy 1, policy_version 288940 (0.0012) -[2023-11-28 07:47:03,339][87426] Updated weights for policy 1, policy_version 288950 (0.0012) -[2023-11-28 07:47:03,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 147996672. Throughput: 0: 2713.7, 1: 2762.5. Samples: 148010436. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:47:03,446][86177] Avg episode reward: [(0, '-583.020'), (1, '-594.300')] -[2023-11-28 07:47:03,717][87426] Updated weights for policy 1, policy_version 288960 (0.0012) -[2023-11-28 07:47:04,479][87424] Updated weights for policy 0, policy_version 289189 (0.0010) -[2023-11-28 07:47:04,868][87424] Updated weights for policy 0, policy_version 289199 (0.0007) -[2023-11-28 07:47:05,244][87424] Updated weights for policy 0, policy_version 289209 (0.0007) -[2023-11-28 07:47:06,301][87426] Updated weights for policy 1, policy_version 288970 (0.0008) -[2023-11-28 07:47:06,681][87426] Updated weights for policy 1, policy_version 288980 (0.0008) -[2023-11-28 07:47:07,062][87426] Updated weights for policy 1, policy_version 288990 (0.0007) -[2023-11-28 07:47:07,293][87424] Updated weights for policy 0, policy_version 289219 (0.0008) -[2023-11-28 07:47:07,674][87424] Updated weights for policy 0, policy_version 289229 (0.0011) -[2023-11-28 07:47:08,058][87424] Updated weights for policy 0, policy_version 289239 (0.0008) -[2023-11-28 07:47:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148029440. Throughput: 0: 2725.0, 1: 2738.2. Samples: 148042752. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:47:08,445][86177] Avg episode reward: [(0, '-576.630'), (1, '-584.790')] -[2023-11-28 07:47:09,459][87426] Updated weights for policy 1, policy_version 289000 (0.0011) -[2023-11-28 07:47:09,835][87426] Updated weights for policy 1, policy_version 289010 (0.0012) -[2023-11-28 07:47:10,075][87424] Updated weights for policy 0, policy_version 289249 (0.0008) -[2023-11-28 07:47:10,224][87426] Updated weights for policy 1, policy_version 289020 (0.0011) -[2023-11-28 07:47:10,458][87424] Updated weights for policy 0, policy_version 289259 (0.0011) -[2023-11-28 07:47:10,843][87424] Updated weights for policy 0, policy_version 289269 (0.0008) -[2023-11-28 07:47:11,236][87424] Updated weights for policy 0, policy_version 289279 (0.0008) -[2023-11-28 07:47:12,472][87426] Updated weights for policy 1, policy_version 289030 (0.0010) -[2023-11-28 07:47:12,851][87426] Updated weights for policy 1, policy_version 289040 (0.0008) -[2023-11-28 07:47:13,237][87426] Updated weights for policy 1, policy_version 289050 (0.0012) -[2023-11-28 07:47:13,401][87424] Updated weights for policy 0, policy_version 289289 (0.0011) -[2023-11-28 07:47:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 148045824. Throughput: 0: 2732.5, 1: 2737.7. Samples: 148066580. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:47:13,445][86177] Avg episode reward: [(0, '-624.180'), (1, '-603.950')] -[2023-11-28 07:47:13,780][87424] Updated weights for policy 0, policy_version 289299 (0.0008) -[2023-11-28 07:47:14,156][87424] Updated weights for policy 0, policy_version 289309 (0.0011) -[2023-11-28 07:47:15,349][87426] Updated weights for policy 1, policy_version 289060 (0.0010) -[2023-11-28 07:47:15,730][87426] Updated weights for policy 1, policy_version 289070 (0.0012) -[2023-11-28 07:47:16,113][87426] Updated weights for policy 1, policy_version 289080 (0.0012) -[2023-11-28 07:47:16,408][87424] Updated weights for policy 0, policy_version 289319 (0.0012) -[2023-11-28 07:47:16,791][87424] Updated weights for policy 0, policy_version 289329 (0.0012) -[2023-11-28 07:47:17,180][87424] Updated weights for policy 0, policy_version 289339 (0.0012) -[2023-11-28 07:47:18,283][87426] Updated weights for policy 1, policy_version 289090 (0.0011) -[2023-11-28 07:47:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 148078592. Throughput: 0: 2720.7, 1: 2747.8. Samples: 148091444. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:47:18,445][86177] Avg episode reward: [(0, '-662.980'), (1, '-609.550')] -[2023-11-28 07:47:18,658][87426] Updated weights for policy 1, policy_version 289100 (0.0010) -[2023-11-28 07:47:19,047][87426] Updated weights for policy 1, policy_version 289110 (0.0010) -[2023-11-28 07:47:19,326][87424] Updated weights for policy 0, policy_version 289349 (0.0012) -[2023-11-28 07:47:19,421][87426] Updated weights for policy 1, policy_version 289120 (0.0008) -[2023-11-28 07:47:19,713][87424] Updated weights for policy 0, policy_version 289359 (0.0011) -[2023-11-28 07:47:20,088][87424] Updated weights for policy 0, policy_version 289369 (0.0010) -[2023-11-28 07:47:21,743][87426] Updated weights for policy 1, policy_version 289130 (0.0012) -[2023-11-28 07:47:22,127][87426] Updated weights for policy 1, policy_version 289140 (0.0010) -[2023-11-28 07:47:22,496][87426] Updated weights for policy 1, policy_version 289150 (0.0010) -[2023-11-28 07:47:22,518][87424] Updated weights for policy 0, policy_version 289379 (0.0009) -[2023-11-28 07:47:22,903][87424] Updated weights for policy 0, policy_version 289389 (0.0011) -[2023-11-28 07:47:23,284][87424] Updated weights for policy 0, policy_version 289399 (0.0012) -[2023-11-28 07:47:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 148103168. Throughput: 0: 2729.0, 1: 2737.4. Samples: 148124608. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:47:23,445][86177] Avg episode reward: [(0, '-628.490'), (1, '-667.820')] -[2023-11-28 07:47:24,730][87426] Updated weights for policy 1, policy_version 289160 (0.0008) -[2023-11-28 07:47:25,034][87424] Updated weights for policy 0, policy_version 289409 (0.0011) -[2023-11-28 07:47:25,108][87426] Updated weights for policy 1, policy_version 289170 (0.0010) -[2023-11-28 07:47:25,428][87424] Updated weights for policy 0, policy_version 289419 (0.0008) -[2023-11-28 07:47:25,491][87426] Updated weights for policy 1, policy_version 289180 (0.0009) -[2023-11-28 07:47:25,808][87424] Updated weights for policy 0, policy_version 289429 (0.0012) -[2023-11-28 07:47:26,186][87424] Updated weights for policy 0, policy_version 289439 (0.0011) -[2023-11-28 07:47:27,773][87426] Updated weights for policy 1, policy_version 289190 (0.0008) -[2023-11-28 07:47:27,935][87424] Updated weights for policy 0, policy_version 289449 (0.0010) -[2023-11-28 07:47:28,155][87426] Updated weights for policy 1, policy_version 289200 (0.0007) -[2023-11-28 07:47:28,324][87424] Updated weights for policy 0, policy_version 289459 (0.0008) -[2023-11-28 07:47:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 148127744. Throughput: 0: 2725.8, 1: 2714.7. Samples: 148148640. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:47:28,445][86177] Avg episode reward: [(0, '-632.190'), (1, '-638.670')] -[2023-11-28 07:47:28,524][87426] Updated weights for policy 1, policy_version 289210 (0.0010) -[2023-11-28 07:47:28,711][87424] Updated weights for policy 0, policy_version 289469 (0.0011) -[2023-11-28 07:47:30,394][87426] Updated weights for policy 1, policy_version 289220 (0.0008) -[2023-11-28 07:47:30,771][87426] Updated weights for policy 1, policy_version 289230 (0.0011) -[2023-11-28 07:47:30,917][87424] Updated weights for policy 0, policy_version 289479 (0.0011) -[2023-11-28 07:47:31,148][87426] Updated weights for policy 1, policy_version 289240 (0.0012) -[2023-11-28 07:47:31,308][87424] Updated weights for policy 0, policy_version 289489 (0.0011) -[2023-11-28 07:47:31,681][87424] Updated weights for policy 0, policy_version 289499 (0.0009) -[2023-11-28 07:47:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148160512. Throughput: 0: 2767.3, 1: 2715.9. Samples: 148174376. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:47:33,445][86177] Avg episode reward: [(0, '-617.910'), (1, '-623.200')] -[2023-11-28 07:47:33,540][87424] Updated weights for policy 0, policy_version 289509 (0.0011) -[2023-11-28 07:47:33,610][87426] Updated weights for policy 1, policy_version 289250 (0.0010) -[2023-11-28 07:47:33,928][87424] Updated weights for policy 0, policy_version 289519 (0.0011) -[2023-11-28 07:47:33,993][87426] Updated weights for policy 1, policy_version 289260 (0.0011) -[2023-11-28 07:47:34,318][87424] Updated weights for policy 0, policy_version 289529 (0.0008) -[2023-11-28 07:47:34,392][87426] Updated weights for policy 1, policy_version 289270 (0.0011) -[2023-11-28 07:47:34,781][87426] Updated weights for policy 1, policy_version 289280 (0.0010) -[2023-11-28 07:47:36,635][87424] Updated weights for policy 0, policy_version 289539 (0.0008) -[2023-11-28 07:47:37,019][87424] Updated weights for policy 0, policy_version 289549 (0.0011) -[2023-11-28 07:47:37,259][87426] Updated weights for policy 1, policy_version 289290 (0.0011) -[2023-11-28 07:47:37,399][87424] Updated weights for policy 0, policy_version 289559 (0.0010) -[2023-11-28 07:47:37,639][87426] Updated weights for policy 1, policy_version 289300 (0.0011) -[2023-11-28 07:47:38,011][87426] Updated weights for policy 1, policy_version 289310 (0.0012) -[2023-11-28 07:47:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 148193280. Throughput: 0: 2780.2, 1: 2703.6. Samples: 148206936. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:47:38,445][86177] Avg episode reward: [(0, '-599.370'), (1, '-631.260')] -[2023-11-28 07:47:39,133][87424] Updated weights for policy 0, policy_version 289569 (0.0010) -[2023-11-28 07:47:39,513][87424] Updated weights for policy 0, policy_version 289579 (0.0012) -[2023-11-28 07:47:39,863][87426] Updated weights for policy 1, policy_version 289320 (0.0011) -[2023-11-28 07:47:39,894][87424] Updated weights for policy 0, policy_version 289589 (0.0012) -[2023-11-28 07:47:40,235][87426] Updated weights for policy 1, policy_version 289330 (0.0011) -[2023-11-28 07:47:40,283][87424] Updated weights for policy 0, policy_version 289599 (0.0011) -[2023-11-28 07:47:40,615][87426] Updated weights for policy 1, policy_version 289340 (0.0010) -[2023-11-28 07:47:42,500][87426] Updated weights for policy 1, policy_version 289350 (0.0010) -[2023-11-28 07:47:42,628][87424] Updated weights for policy 0, policy_version 289609 (0.0008) -[2023-11-28 07:47:42,876][87426] Updated weights for policy 1, policy_version 289360 (0.0012) -[2023-11-28 07:47:43,008][87424] Updated weights for policy 0, policy_version 289619 (0.0010) -[2023-11-28 07:47:43,251][87426] Updated weights for policy 1, policy_version 289370 (0.0012) -[2023-11-28 07:47:43,394][87424] Updated weights for policy 0, policy_version 289629 (0.0012) -[2023-11-28 07:47:43,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 148209664. Throughput: 0: 2780.1, 1: 2690.9. Samples: 148231224. Policy #0 lag: (min: 31.0, avg: 41.5, max: 63.0) -[2023-11-28 07:47:43,446][86177] Avg episode reward: [(0, '-578.960'), (1, '-571.170')] -[2023-11-28 07:47:45,363][87426] Updated weights for policy 1, policy_version 289380 (0.0012) -[2023-11-28 07:47:45,610][87424] Updated weights for policy 0, policy_version 289639 (0.0009) -[2023-11-28 07:47:45,746][87426] Updated weights for policy 1, policy_version 289390 (0.0012) -[2023-11-28 07:47:45,994][87424] Updated weights for policy 0, policy_version 289649 (0.0012) -[2023-11-28 07:47:46,128][87426] Updated weights for policy 1, policy_version 289400 (0.0010) -[2023-11-28 07:47:46,374][87424] Updated weights for policy 0, policy_version 289659 (0.0008) -[2023-11-28 07:47:48,359][87426] Updated weights for policy 1, policy_version 289410 (0.0008) -[2023-11-28 07:47:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148242432. Throughput: 0: 2785.3, 1: 2689.9. Samples: 148256820. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:47:48,446][86177] Avg episode reward: [(0, '-586.860'), (1, '-550.880')] -[2023-11-28 07:47:48,657][87424] Updated weights for policy 0, policy_version 289669 (0.0009) -[2023-11-28 07:47:48,741][87426] Updated weights for policy 1, policy_version 289420 (0.0011) -[2023-11-28 07:47:49,043][87424] Updated weights for policy 0, policy_version 289679 (0.0012) -[2023-11-28 07:47:49,119][87426] Updated weights for policy 1, policy_version 289430 (0.0012) -[2023-11-28 07:47:49,440][87424] Updated weights for policy 0, policy_version 289689 (0.0011) -[2023-11-28 07:47:49,489][87426] Updated weights for policy 1, policy_version 289440 (0.0012) -[2023-11-28 07:47:51,554][87426] Updated weights for policy 1, policy_version 289450 (0.0009) -[2023-11-28 07:47:51,893][87424] Updated weights for policy 0, policy_version 289699 (0.0011) -[2023-11-28 07:47:51,929][87426] Updated weights for policy 1, policy_version 289460 (0.0010) -[2023-11-28 07:47:52,272][87424] Updated weights for policy 0, policy_version 289709 (0.0009) -[2023-11-28 07:47:52,314][87426] Updated weights for policy 1, policy_version 289470 (0.0010) -[2023-11-28 07:47:52,645][87424] Updated weights for policy 0, policy_version 289719 (0.0012) -[2023-11-28 07:47:53,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 148275200. Throughput: 0: 2756.0, 1: 2718.8. Samples: 148289116. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:47:53,445][86177] Avg episode reward: [(0, '-584.720'), (1, '-549.080')] -[2023-11-28 07:47:54,492][87426] Updated weights for policy 1, policy_version 289480 (0.0009) -[2023-11-28 07:47:54,840][87424] Updated weights for policy 0, policy_version 289729 (0.0012) -[2023-11-28 07:47:54,877][87426] Updated weights for policy 1, policy_version 289490 (0.0010) -[2023-11-28 07:47:55,221][87424] Updated weights for policy 0, policy_version 289739 (0.0011) -[2023-11-28 07:47:55,256][87426] Updated weights for policy 1, policy_version 289500 (0.0007) -[2023-11-28 07:47:55,612][87424] Updated weights for policy 0, policy_version 289749 (0.0009) -[2023-11-28 07:47:56,002][87424] Updated weights for policy 0, policy_version 289759 (0.0009) -[2023-11-28 07:47:57,181][87426] Updated weights for policy 1, policy_version 289510 (0.0007) -[2023-11-28 07:47:57,561][87426] Updated weights for policy 1, policy_version 289520 (0.0007) -[2023-11-28 07:47:57,949][87426] Updated weights for policy 1, policy_version 289530 (0.0008) -[2023-11-28 07:47:58,306][87424] Updated weights for policy 0, policy_version 289769 (0.0012) -[2023-11-28 07:47:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148299776. Throughput: 0: 2760.8, 1: 2734.0. Samples: 148313848. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:47:58,446][86177] Avg episode reward: [(0, '-567.880'), (1, '-525.180')] -[2023-11-28 07:47:58,683][87424] Updated weights for policy 0, policy_version 289779 (0.0012) -[2023-11-28 07:47:59,069][87424] Updated weights for policy 0, policy_version 289789 (0.0012) -[2023-11-28 07:48:00,338][87426] Updated weights for policy 1, policy_version 289540 (0.0009) -[2023-11-28 07:48:00,723][87426] Updated weights for policy 1, policy_version 289550 (0.0011) -[2023-11-28 07:48:01,111][87426] Updated weights for policy 1, policy_version 289560 (0.0011) -[2023-11-28 07:48:01,459][87424] Updated weights for policy 0, policy_version 289799 (0.0011) -[2023-11-28 07:48:01,841][87424] Updated weights for policy 0, policy_version 289809 (0.0012) -[2023-11-28 07:48:02,219][87424] Updated weights for policy 0, policy_version 289819 (0.0012) -[2023-11-28 07:48:03,035][87426] Updated weights for policy 1, policy_version 289570 (0.0012) -[2023-11-28 07:48:03,412][87426] Updated weights for policy 1, policy_version 289580 (0.0012) -[2023-11-28 07:48:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148324352. Throughput: 0: 2759.3, 1: 2716.1. Samples: 148337836. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:03,445][86177] Avg episode reward: [(0, '-578.440'), (1, '-524.800')] -[2023-11-28 07:48:03,794][87426] Updated weights for policy 1, policy_version 289590 (0.0010) -[2023-11-28 07:48:04,174][87426] Updated weights for policy 1, policy_version 289600 (0.0008) -[2023-11-28 07:48:04,315][87424] Updated weights for policy 0, policy_version 289829 (0.0010) -[2023-11-28 07:48:04,709][87424] Updated weights for policy 0, policy_version 289839 (0.0009) -[2023-11-28 07:48:05,083][87424] Updated weights for policy 0, policy_version 289849 (0.0010) -[2023-11-28 07:48:06,568][87426] Updated weights for policy 1, policy_version 289610 (0.0011) -[2023-11-28 07:48:06,942][87426] Updated weights for policy 1, policy_version 289620 (0.0011) -[2023-11-28 07:48:06,952][87424] Updated weights for policy 0, policy_version 289859 (0.0009) -[2023-11-28 07:48:07,324][87426] Updated weights for policy 1, policy_version 289630 (0.0011) -[2023-11-28 07:48:07,341][87424] Updated weights for policy 0, policy_version 289869 (0.0011) -[2023-11-28 07:48:07,721][87424] Updated weights for policy 0, policy_version 289879 (0.0012) -[2023-11-28 07:48:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148357120. Throughput: 0: 2755.8, 1: 2704.3. Samples: 148370312. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:08,445][86177] Avg episode reward: [(0, '-595.340'), (1, '-525.000')] -[2023-11-28 07:48:09,244][87426] Updated weights for policy 1, policy_version 289640 (0.0008) -[2023-11-28 07:48:09,521][87424] Updated weights for policy 0, policy_version 289889 (0.0011) -[2023-11-28 07:48:09,621][87426] Updated weights for policy 1, policy_version 289650 (0.0009) -[2023-11-28 07:48:09,902][87424] Updated weights for policy 0, policy_version 289899 (0.0008) -[2023-11-28 07:48:10,006][87426] Updated weights for policy 1, policy_version 289660 (0.0012) -[2023-11-28 07:48:10,283][87424] Updated weights for policy 0, policy_version 289909 (0.0012) -[2023-11-28 07:48:10,655][87424] Updated weights for policy 0, policy_version 289919 (0.0012) -[2023-11-28 07:48:12,557][87426] Updated weights for policy 1, policy_version 289670 (0.0009) -[2023-11-28 07:48:12,938][87426] Updated weights for policy 1, policy_version 289680 (0.0011) -[2023-11-28 07:48:13,083][87424] Updated weights for policy 0, policy_version 289929 (0.0011) -[2023-11-28 07:48:13,327][87426] Updated weights for policy 1, policy_version 289690 (0.0011) -[2023-11-28 07:48:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 148373504. Throughput: 0: 2740.6, 1: 2709.8. Samples: 148393908. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:13,445][86177] Avg episode reward: [(0, '-559.070'), (1, '-565.000')] -[2023-11-28 07:48:13,464][87424] Updated weights for policy 0, policy_version 289939 (0.0008) -[2023-11-28 07:48:13,830][87424] Updated weights for policy 0, policy_version 289949 (0.0010) -[2023-11-28 07:48:15,513][87426] Updated weights for policy 1, policy_version 289700 (0.0011) -[2023-11-28 07:48:15,895][87426] Updated weights for policy 1, policy_version 289710 (0.0011) -[2023-11-28 07:48:16,052][87424] Updated weights for policy 0, policy_version 289959 (0.0011) -[2023-11-28 07:48:16,276][87426] Updated weights for policy 1, policy_version 289720 (0.0008) -[2023-11-28 07:48:16,432][87424] Updated weights for policy 0, policy_version 289969 (0.0011) -[2023-11-28 07:48:16,801][87424] Updated weights for policy 0, policy_version 289979 (0.0012) -[2023-11-28 07:48:18,287][87426] Updated weights for policy 1, policy_version 289730 (0.0007) -[2023-11-28 07:48:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148406272. Throughput: 0: 2717.9, 1: 2722.0. Samples: 148419168. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:18,445][86177] Avg episode reward: [(0, '-593.440'), (1, '-565.240')] -[2023-11-28 07:48:18,664][87426] Updated weights for policy 1, policy_version 289740 (0.0009) -[2023-11-28 07:48:18,692][87424] Updated weights for policy 0, policy_version 289989 (0.0011) -[2023-11-28 07:48:19,038][87426] Updated weights for policy 1, policy_version 289750 (0.0009) -[2023-11-28 07:48:19,070][87424] Updated weights for policy 0, policy_version 289999 (0.0013) -[2023-11-28 07:48:19,414][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000289760_74178560.pth... -[2023-11-28 07:48:19,416][87426] Updated weights for policy 1, policy_version 289760 (0.0008) -[2023-11-28 07:48:19,452][87424] Updated weights for policy 0, policy_version 290009 (0.0012) -[2023-11-28 07:48:19,462][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000287200_73523200.pth -[2023-11-28 07:48:19,718][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000290016_74244096.pth... -[2023-11-28 07:48:19,752][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000287424_73580544.pth -[2023-11-28 07:48:21,751][87426] Updated weights for policy 1, policy_version 289770 (0.0013) -[2023-11-28 07:48:21,838][87424] Updated weights for policy 0, policy_version 290019 (0.0012) -[2023-11-28 07:48:22,138][87426] Updated weights for policy 1, policy_version 289780 (0.0012) -[2023-11-28 07:48:22,222][87424] Updated weights for policy 0, policy_version 290029 (0.0011) -[2023-11-28 07:48:22,515][87426] Updated weights for policy 1, policy_version 289790 (0.0012) -[2023-11-28 07:48:22,601][87424] Updated weights for policy 0, policy_version 290039 (0.0011) -[2023-11-28 07:48:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 148439040. Throughput: 0: 2702.6, 1: 2745.8. Samples: 148452112. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:23,446][86177] Avg episode reward: [(0, '-585.780'), (1, '-559.490')] -[2023-11-28 07:48:24,776][87426] Updated weights for policy 1, policy_version 289800 (0.0009) -[2023-11-28 07:48:25,063][87424] Updated weights for policy 0, policy_version 290049 (0.0010) -[2023-11-28 07:48:25,160][87426] Updated weights for policy 1, policy_version 289810 (0.0008) -[2023-11-28 07:48:25,447][87424] Updated weights for policy 0, policy_version 290059 (0.0011) -[2023-11-28 07:48:25,551][87426] Updated weights for policy 1, policy_version 289820 (0.0007) -[2023-11-28 07:48:25,815][87424] Updated weights for policy 0, policy_version 290069 (0.0007) -[2023-11-28 07:48:26,194][87424] Updated weights for policy 0, policy_version 290079 (0.0008) -[2023-11-28 07:48:27,476][87426] Updated weights for policy 1, policy_version 289830 (0.0009) -[2023-11-28 07:48:27,847][87426] Updated weights for policy 1, policy_version 289840 (0.0007) -[2023-11-28 07:48:27,887][87424] Updated weights for policy 0, policy_version 290089 (0.0011) -[2023-11-28 07:48:28,228][87426] Updated weights for policy 1, policy_version 289850 (0.0008) -[2023-11-28 07:48:28,257][87424] Updated weights for policy 0, policy_version 290099 (0.0011) -[2023-11-28 07:48:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 148455424. Throughput: 0: 2703.0, 1: 2754.1. Samples: 148476788. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:28,445][86177] Avg episode reward: [(0, '-573.350'), (1, '-574.720')] -[2023-11-28 07:48:28,647][87424] Updated weights for policy 0, policy_version 290109 (0.0011) -[2023-11-28 07:48:30,201][87426] Updated weights for policy 1, policy_version 289860 (0.0010) -[2023-11-28 07:48:30,576][87426] Updated weights for policy 1, policy_version 289870 (0.0009) -[2023-11-28 07:48:30,964][87426] Updated weights for policy 1, policy_version 289880 (0.0011) -[2023-11-28 07:48:31,015][87424] Updated weights for policy 0, policy_version 290119 (0.0010) -[2023-11-28 07:48:31,394][87424] Updated weights for policy 0, policy_version 290129 (0.0007) -[2023-11-28 07:48:31,783][87424] Updated weights for policy 0, policy_version 290139 (0.0008) -[2023-11-28 07:48:33,225][87426] Updated weights for policy 1, policy_version 289890 (0.0009) -[2023-11-28 07:48:33,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148488192. Throughput: 0: 2697.0, 1: 2753.9. Samples: 148502108. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:33,446][86177] Avg episode reward: [(0, '-558.880'), (1, '-531.960')] -[2023-11-28 07:48:33,607][87426] Updated weights for policy 1, policy_version 289900 (0.0008) -[2023-11-28 07:48:33,985][87426] Updated weights for policy 1, policy_version 289910 (0.0008) -[2023-11-28 07:48:34,005][87424] Updated weights for policy 0, policy_version 290149 (0.0009) -[2023-11-28 07:48:34,364][87426] Updated weights for policy 1, policy_version 289920 (0.0007) -[2023-11-28 07:48:34,378][87424] Updated weights for policy 0, policy_version 290159 (0.0008) -[2023-11-28 07:48:34,758][87424] Updated weights for policy 0, policy_version 290169 (0.0009) -[2023-11-28 07:48:36,587][87426] Updated weights for policy 1, policy_version 289930 (0.0012) -[2023-11-28 07:48:36,817][87424] Updated weights for policy 0, policy_version 290179 (0.0011) -[2023-11-28 07:48:36,980][87426] Updated weights for policy 1, policy_version 289940 (0.0011) -[2023-11-28 07:48:37,214][87424] Updated weights for policy 0, policy_version 290189 (0.0012) -[2023-11-28 07:48:37,364][87426] Updated weights for policy 1, policy_version 289950 (0.0012) -[2023-11-28 07:48:37,581][87424] Updated weights for policy 0, policy_version 290199 (0.0012) -[2023-11-28 07:48:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 148520960. Throughput: 0: 2698.0, 1: 2737.9. Samples: 148533732. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:38,445][86177] Avg episode reward: [(0, '-517.560'), (1, '-535.370')] -[2023-11-28 07:48:39,196][87426] Updated weights for policy 1, policy_version 289960 (0.0011) -[2023-11-28 07:48:39,579][87426] Updated weights for policy 1, policy_version 289970 (0.0012) -[2023-11-28 07:48:39,818][87424] Updated weights for policy 0, policy_version 290209 (0.0012) -[2023-11-28 07:48:39,947][87426] Updated weights for policy 1, policy_version 289980 (0.0011) -[2023-11-28 07:48:40,201][87424] Updated weights for policy 0, policy_version 290219 (0.0010) -[2023-11-28 07:48:40,581][87424] Updated weights for policy 0, policy_version 290229 (0.0009) -[2023-11-28 07:48:40,962][87424] Updated weights for policy 0, policy_version 290239 (0.0008) -[2023-11-28 07:48:42,375][87426] Updated weights for policy 1, policy_version 289990 (0.0009) -[2023-11-28 07:48:42,754][87426] Updated weights for policy 1, policy_version 290000 (0.0008) -[2023-11-28 07:48:43,008][87424] Updated weights for policy 0, policy_version 290249 (0.0009) -[2023-11-28 07:48:43,138][87426] Updated weights for policy 1, policy_version 290010 (0.0011) -[2023-11-28 07:48:43,389][87424] Updated weights for policy 0, policy_version 290259 (0.0011) -[2023-11-28 07:48:43,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 148545536. Throughput: 0: 2701.1, 1: 2735.8. Samples: 148558508. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:43,445][86177] Avg episode reward: [(0, '-517.360'), (1, '-535.440')] -[2023-11-28 07:48:43,776][87424] Updated weights for policy 0, policy_version 290269 (0.0009) -[2023-11-28 07:48:44,988][87426] Updated weights for policy 1, policy_version 290020 (0.0011) -[2023-11-28 07:48:45,371][87426] Updated weights for policy 1, policy_version 290030 (0.0010) -[2023-11-28 07:48:45,748][87426] Updated weights for policy 1, policy_version 290040 (0.0008) -[2023-11-28 07:48:46,192][87424] Updated weights for policy 0, policy_version 290279 (0.0011) -[2023-11-28 07:48:46,574][87424] Updated weights for policy 0, policy_version 290289 (0.0012) -[2023-11-28 07:48:46,963][87424] Updated weights for policy 0, policy_version 290299 (0.0012) -[2023-11-28 07:48:48,040][87426] Updated weights for policy 1, policy_version 290050 (0.0009) -[2023-11-28 07:48:48,420][87426] Updated weights for policy 1, policy_version 290060 (0.0010) -[2023-11-28 07:48:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148570112. Throughput: 0: 2732.5, 1: 2738.3. Samples: 148584024. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:48,445][86177] Avg episode reward: [(0, '-527.030'), (1, '-533.070')] -[2023-11-28 07:48:48,794][87426] Updated weights for policy 1, policy_version 290070 (0.0012) -[2023-11-28 07:48:49,082][87424] Updated weights for policy 0, policy_version 290309 (0.0011) -[2023-11-28 07:48:49,161][87426] Updated weights for policy 1, policy_version 290080 (0.0011) -[2023-11-28 07:48:49,455][87424] Updated weights for policy 0, policy_version 290319 (0.0011) -[2023-11-28 07:48:49,836][87424] Updated weights for policy 0, policy_version 290329 (0.0012) -[2023-11-28 07:48:51,714][87426] Updated weights for policy 1, policy_version 290090 (0.0011) -[2023-11-28 07:48:52,098][87426] Updated weights for policy 1, policy_version 290100 (0.0010) -[2023-11-28 07:48:52,316][87424] Updated weights for policy 0, policy_version 290339 (0.0011) -[2023-11-28 07:48:52,467][87426] Updated weights for policy 1, policy_version 290110 (0.0011) -[2023-11-28 07:48:52,688][87424] Updated weights for policy 0, policy_version 290349 (0.0008) -[2023-11-28 07:48:53,065][87424] Updated weights for policy 0, policy_version 290359 (0.0011) -[2023-11-28 07:48:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 148602880. Throughput: 0: 2710.6, 1: 2737.6. Samples: 148615480. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:53,445][86177] Avg episode reward: [(0, '-579.680'), (1, '-545.020')] -[2023-11-28 07:48:54,469][87426] Updated weights for policy 1, policy_version 290120 (0.0012) -[2023-11-28 07:48:54,847][87426] Updated weights for policy 1, policy_version 290130 (0.0010) -[2023-11-28 07:48:55,231][87426] Updated weights for policy 1, policy_version 290140 (0.0007) -[2023-11-28 07:48:55,561][87424] Updated weights for policy 0, policy_version 290369 (0.0011) -[2023-11-28 07:48:55,947][87424] Updated weights for policy 0, policy_version 290379 (0.0008) -[2023-11-28 07:48:56,340][87424] Updated weights for policy 0, policy_version 290389 (0.0008) -[2023-11-28 07:48:56,722][87424] Updated weights for policy 0, policy_version 290399 (0.0008) -[2023-11-28 07:48:57,570][87426] Updated weights for policy 1, policy_version 290150 (0.0007) -[2023-11-28 07:48:57,950][87426] Updated weights for policy 1, policy_version 290160 (0.0008) -[2023-11-28 07:48:58,329][87426] Updated weights for policy 1, policy_version 290170 (0.0007) -[2023-11-28 07:48:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 148619264. Throughput: 0: 2714.7, 1: 2742.8. Samples: 148639492. Policy #0 lag: (min: 23.0, avg: 34.2, max: 55.0) -[2023-11-28 07:48:58,445][86177] Avg episode reward: [(0, '-600.030'), (1, '-550.550')] -[2023-11-28 07:48:59,147][87424] Updated weights for policy 0, policy_version 290409 (0.0008) -[2023-11-28 07:48:59,529][87424] Updated weights for policy 0, policy_version 290419 (0.0007) -[2023-11-28 07:48:59,920][87424] Updated weights for policy 0, policy_version 290429 (0.0008) -[2023-11-28 07:49:00,642][87426] Updated weights for policy 1, policy_version 290180 (0.0009) -[2023-11-28 07:49:01,018][87426] Updated weights for policy 1, policy_version 290190 (0.0012) -[2023-11-28 07:49:01,398][87426] Updated weights for policy 1, policy_version 290200 (0.0011) -[2023-11-28 07:49:02,166][87424] Updated weights for policy 0, policy_version 290439 (0.0011) -[2023-11-28 07:49:02,536][87424] Updated weights for policy 0, policy_version 290449 (0.0012) -[2023-11-28 07:49:02,919][87424] Updated weights for policy 0, policy_version 290459 (0.0012) -[2023-11-28 07:49:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148652032. Throughput: 0: 2695.6, 1: 2714.9. Samples: 148662644. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:03,445][86177] Avg episode reward: [(0, '-625.780'), (1, '-563.760')] -[2023-11-28 07:49:03,959][87426] Updated weights for policy 1, policy_version 290210 (0.0012) -[2023-11-28 07:49:04,341][87426] Updated weights for policy 1, policy_version 290220 (0.0012) -[2023-11-28 07:49:04,719][87426] Updated weights for policy 1, policy_version 290230 (0.0012) -[2023-11-28 07:49:04,905][87424] Updated weights for policy 0, policy_version 290469 (0.0012) -[2023-11-28 07:49:05,088][87426] Updated weights for policy 1, policy_version 290240 (0.0012) -[2023-11-28 07:49:05,293][87424] Updated weights for policy 0, policy_version 290479 (0.0011) -[2023-11-28 07:49:05,666][87424] Updated weights for policy 0, policy_version 290489 (0.0012) -[2023-11-28 07:49:07,254][87426] Updated weights for policy 1, policy_version 290250 (0.0011) -[2023-11-28 07:49:07,637][87426] Updated weights for policy 1, policy_version 290260 (0.0009) -[2023-11-28 07:49:07,711][87424] Updated weights for policy 0, policy_version 290499 (0.0012) -[2023-11-28 07:49:08,018][87426] Updated weights for policy 1, policy_version 290270 (0.0007) -[2023-11-28 07:49:08,094][87424] Updated weights for policy 0, policy_version 290509 (0.0011) -[2023-11-28 07:49:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 148676608. Throughput: 0: 2686.7, 1: 2726.7. Samples: 148695712. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:08,445][86177] Avg episode reward: [(0, '-608.060'), (1, '-552.500')] -[2023-11-28 07:49:08,484][87424] Updated weights for policy 0, policy_version 290519 (0.0012) -[2023-11-28 07:49:09,863][87426] Updated weights for policy 1, policy_version 290280 (0.0008) -[2023-11-28 07:49:10,230][87426] Updated weights for policy 1, policy_version 290290 (0.0012) -[2023-11-28 07:49:10,616][87426] Updated weights for policy 1, policy_version 290300 (0.0011) -[2023-11-28 07:49:11,021][87424] Updated weights for policy 0, policy_version 290529 (0.0012) -[2023-11-28 07:49:11,407][87424] Updated weights for policy 0, policy_version 290539 (0.0012) -[2023-11-28 07:49:11,785][87424] Updated weights for policy 0, policy_version 290549 (0.0012) -[2023-11-28 07:49:12,179][87424] Updated weights for policy 0, policy_version 290559 (0.0012) -[2023-11-28 07:49:12,602][87426] Updated weights for policy 1, policy_version 290310 (0.0009) -[2023-11-28 07:49:12,982][87426] Updated weights for policy 1, policy_version 290320 (0.0011) -[2023-11-28 07:49:13,356][87426] Updated weights for policy 1, policy_version 290330 (0.0009) -[2023-11-28 07:49:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 148701184. Throughput: 0: 2676.8, 1: 2710.3. Samples: 148719208. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:13,445][86177] Avg episode reward: [(0, '-603.070'), (1, '-546.420')] -[2023-11-28 07:49:14,531][87424] Updated weights for policy 0, policy_version 290569 (0.0012) -[2023-11-28 07:49:14,905][87424] Updated weights for policy 0, policy_version 290579 (0.0012) -[2023-11-28 07:49:15,021][87426] Updated weights for policy 1, policy_version 290340 (0.0009) -[2023-11-28 07:49:15,293][87424] Updated weights for policy 0, policy_version 290589 (0.0010) -[2023-11-28 07:49:15,399][87426] Updated weights for policy 1, policy_version 290350 (0.0011) -[2023-11-28 07:49:15,777][87426] Updated weights for policy 1, policy_version 290360 (0.0012) -[2023-11-28 07:49:17,531][87424] Updated weights for policy 0, policy_version 290599 (0.0008) -[2023-11-28 07:49:17,924][87424] Updated weights for policy 0, policy_version 290609 (0.0007) -[2023-11-28 07:49:18,210][87426] Updated weights for policy 1, policy_version 290370 (0.0012) -[2023-11-28 07:49:18,303][87424] Updated weights for policy 0, policy_version 290619 (0.0008) -[2023-11-28 07:49:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 148725760. Throughput: 0: 2647.6, 1: 2691.8. Samples: 148742380. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:18,445][86177] Avg episode reward: [(0, '-566.730'), (1, '-537.660')] -[2023-11-28 07:49:18,589][87426] Updated weights for policy 1, policy_version 290380 (0.0011) -[2023-11-28 07:49:18,975][87426] Updated weights for policy 1, policy_version 290390 (0.0010) -[2023-11-28 07:49:19,348][87426] Updated weights for policy 1, policy_version 290400 (0.0009) -[2023-11-28 07:49:20,569][87424] Updated weights for policy 0, policy_version 290629 (0.0009) -[2023-11-28 07:49:20,949][87424] Updated weights for policy 0, policy_version 290639 (0.0011) -[2023-11-28 07:49:21,329][87424] Updated weights for policy 0, policy_version 290649 (0.0011) -[2023-11-28 07:49:21,647][87426] Updated weights for policy 1, policy_version 290410 (0.0010) -[2023-11-28 07:49:22,035][87426] Updated weights for policy 1, policy_version 290420 (0.0008) -[2023-11-28 07:49:22,415][87426] Updated weights for policy 1, policy_version 290430 (0.0008) -[2023-11-28 07:49:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 148758528. Throughput: 0: 2657.9, 1: 2680.4. Samples: 148773952. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:23,445][86177] Avg episode reward: [(0, '-554.620'), (1, '-529.640')] -[2023-11-28 07:49:23,826][87424] Updated weights for policy 0, policy_version 290659 (0.0011) -[2023-11-28 07:49:24,220][87424] Updated weights for policy 0, policy_version 290669 (0.0012) -[2023-11-28 07:49:24,608][87424] Updated weights for policy 0, policy_version 290679 (0.0009) -[2023-11-28 07:49:24,921][87426] Updated weights for policy 1, policy_version 290440 (0.0008) -[2023-11-28 07:49:25,301][87426] Updated weights for policy 1, policy_version 290450 (0.0007) -[2023-11-28 07:49:25,683][87426] Updated weights for policy 1, policy_version 290460 (0.0007) -[2023-11-28 07:49:26,500][87424] Updated weights for policy 0, policy_version 290689 (0.0008) -[2023-11-28 07:49:26,877][87424] Updated weights for policy 0, policy_version 290699 (0.0008) -[2023-11-28 07:49:27,261][87424] Updated weights for policy 0, policy_version 290709 (0.0007) -[2023-11-28 07:49:27,647][87424] Updated weights for policy 0, policy_version 290719 (0.0007) -[2023-11-28 07:49:27,676][87426] Updated weights for policy 1, policy_version 290470 (0.0007) -[2023-11-28 07:49:28,051][87426] Updated weights for policy 1, policy_version 290480 (0.0008) -[2023-11-28 07:49:28,440][87426] Updated weights for policy 1, policy_version 290490 (0.0007) -[2023-11-28 07:49:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148783104. Throughput: 0: 2651.1, 1: 2705.8. Samples: 148799568. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:28,445][86177] Avg episode reward: [(0, '-575.110'), (1, '-542.680')] -[2023-11-28 07:49:29,688][87424] Updated weights for policy 0, policy_version 290729 (0.0008) -[2023-11-28 07:49:30,074][87424] Updated weights for policy 0, policy_version 290739 (0.0009) -[2023-11-28 07:49:30,461][87424] Updated weights for policy 0, policy_version 290749 (0.0010) -[2023-11-28 07:49:30,820][87426] Updated weights for policy 1, policy_version 290500 (0.0008) -[2023-11-28 07:49:31,202][87426] Updated weights for policy 1, policy_version 290510 (0.0007) -[2023-11-28 07:49:31,580][87426] Updated weights for policy 1, policy_version 290520 (0.0008) -[2023-11-28 07:49:32,686][87424] Updated weights for policy 0, policy_version 290759 (0.0012) -[2023-11-28 07:49:33,066][87424] Updated weights for policy 0, policy_version 290769 (0.0010) -[2023-11-28 07:49:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 148807680. Throughput: 0: 2636.9, 1: 2704.4. Samples: 148824384. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:33,445][86177] Avg episode reward: [(0, '-585.480'), (1, '-537.270')] -[2023-11-28 07:49:33,450][87424] Updated weights for policy 0, policy_version 290779 (0.0007) -[2023-11-28 07:49:33,565][87426] Updated weights for policy 1, policy_version 290530 (0.0011) -[2023-11-28 07:49:33,948][87426] Updated weights for policy 1, policy_version 290540 (0.0012) -[2023-11-28 07:49:34,322][87426] Updated weights for policy 1, policy_version 290550 (0.0010) -[2023-11-28 07:49:34,699][87426] Updated weights for policy 1, policy_version 290560 (0.0008) -[2023-11-28 07:49:35,992][87424] Updated weights for policy 0, policy_version 290789 (0.0010) -[2023-11-28 07:49:36,378][87424] Updated weights for policy 0, policy_version 290799 (0.0012) -[2023-11-28 07:49:36,761][87424] Updated weights for policy 0, policy_version 290809 (0.0012) -[2023-11-28 07:49:37,148][87426] Updated weights for policy 1, policy_version 290570 (0.0009) -[2023-11-28 07:49:37,531][87426] Updated weights for policy 1, policy_version 290580 (0.0012) -[2023-11-28 07:49:37,900][87426] Updated weights for policy 1, policy_version 290590 (0.0012) -[2023-11-28 07:49:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 148840448. Throughput: 0: 2629.6, 1: 2697.2. Samples: 148855188. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:38,445][86177] Avg episode reward: [(0, '-580.800'), (1, '-542.780')] -[2023-11-28 07:49:39,046][87424] Updated weights for policy 0, policy_version 290819 (0.0011) -[2023-11-28 07:49:39,415][87424] Updated weights for policy 0, policy_version 290829 (0.0008) -[2023-11-28 07:49:39,794][87424] Updated weights for policy 0, policy_version 290839 (0.0012) -[2023-11-28 07:49:40,017][87426] Updated weights for policy 1, policy_version 290600 (0.0026) -[2023-11-28 07:49:40,386][87426] Updated weights for policy 1, policy_version 290610 (0.0008) -[2023-11-28 07:49:40,772][87426] Updated weights for policy 1, policy_version 290620 (0.0011) -[2023-11-28 07:49:42,098][87424] Updated weights for policy 0, policy_version 290849 (0.0012) -[2023-11-28 07:49:42,493][87424] Updated weights for policy 0, policy_version 290859 (0.0009) -[2023-11-28 07:49:42,707][87426] Updated weights for policy 1, policy_version 290630 (0.0012) -[2023-11-28 07:49:42,873][87424] Updated weights for policy 0, policy_version 290869 (0.0012) -[2023-11-28 07:49:43,081][87426] Updated weights for policy 1, policy_version 290640 (0.0011) -[2023-11-28 07:49:43,245][87424] Updated weights for policy 0, policy_version 290879 (0.0011) -[2023-11-28 07:49:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 148865024. Throughput: 0: 2629.6, 1: 2686.9. Samples: 148878736. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:43,445][86177] Avg episode reward: [(0, '-557.960'), (1, '-555.030')] -[2023-11-28 07:49:43,462][87426] Updated weights for policy 1, policy_version 290650 (0.0012) -[2023-11-28 07:49:45,281][87424] Updated weights for policy 0, policy_version 290889 (0.0011) -[2023-11-28 07:49:45,658][87424] Updated weights for policy 0, policy_version 290899 (0.0012) -[2023-11-28 07:49:45,983][87426] Updated weights for policy 1, policy_version 290660 (0.0011) -[2023-11-28 07:49:46,053][87424] Updated weights for policy 0, policy_version 290909 (0.0007) -[2023-11-28 07:49:46,361][87426] Updated weights for policy 1, policy_version 290670 (0.0008) -[2023-11-28 07:49:46,744][87426] Updated weights for policy 1, policy_version 290680 (0.0007) -[2023-11-28 07:49:48,237][87424] Updated weights for policy 0, policy_version 290919 (0.0009) -[2023-11-28 07:49:48,321][87426] Updated weights for policy 1, policy_version 290690 (0.0007) -[2023-11-28 07:49:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 148889600. Throughput: 0: 2645.7, 1: 2715.0. Samples: 148903876. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:48,446][86177] Avg episode reward: [(0, '-533.260'), (1, '-555.580')] -[2023-11-28 07:49:48,630][87424] Updated weights for policy 0, policy_version 290929 (0.0008) -[2023-11-28 07:49:48,697][87426] Updated weights for policy 1, policy_version 290700 (0.0010) -[2023-11-28 07:49:49,009][87424] Updated weights for policy 0, policy_version 290939 (0.0009) -[2023-11-28 07:49:49,071][87426] Updated weights for policy 1, policy_version 290710 (0.0009) -[2023-11-28 07:49:49,444][87426] Updated weights for policy 1, policy_version 290720 (0.0012) -[2023-11-28 07:49:51,158][87424] Updated weights for policy 0, policy_version 290949 (0.0010) -[2023-11-28 07:49:51,537][87424] Updated weights for policy 0, policy_version 290959 (0.0008) -[2023-11-28 07:49:51,551][87426] Updated weights for policy 1, policy_version 290730 (0.0010) -[2023-11-28 07:49:51,923][87424] Updated weights for policy 0, policy_version 290969 (0.0011) -[2023-11-28 07:49:51,931][87426] Updated weights for policy 1, policy_version 290740 (0.0011) -[2023-11-28 07:49:52,312][87426] Updated weights for policy 1, policy_version 290750 (0.0012) -[2023-11-28 07:49:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 148922368. Throughput: 0: 2647.2, 1: 2722.8. Samples: 148937364. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:53,445][86177] Avg episode reward: [(0, '-530.270'), (1, '-554.830')] -[2023-11-28 07:49:54,216][87424] Updated weights for policy 0, policy_version 290979 (0.0011) -[2023-11-28 07:49:54,607][87424] Updated weights for policy 0, policy_version 290989 (0.0012) -[2023-11-28 07:49:54,657][87426] Updated weights for policy 1, policy_version 290760 (0.0010) -[2023-11-28 07:49:54,985][87424] Updated weights for policy 0, policy_version 290999 (0.0012) -[2023-11-28 07:49:55,034][87426] Updated weights for policy 1, policy_version 290770 (0.0011) -[2023-11-28 07:49:55,411][87426] Updated weights for policy 1, policy_version 290780 (0.0011) -[2023-11-28 07:49:56,974][87424] Updated weights for policy 0, policy_version 291009 (0.0012) -[2023-11-28 07:49:57,348][87424] Updated weights for policy 0, policy_version 291019 (0.0012) -[2023-11-28 07:49:57,732][87424] Updated weights for policy 0, policy_version 291029 (0.0011) -[2023-11-28 07:49:57,761][87426] Updated weights for policy 1, policy_version 290790 (0.0011) -[2023-11-28 07:49:58,109][87424] Updated weights for policy 0, policy_version 291039 (0.0011) -[2023-11-28 07:49:58,148][87426] Updated weights for policy 1, policy_version 290800 (0.0011) -[2023-11-28 07:49:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 148946944. Throughput: 0: 2666.7, 1: 2730.7. Samples: 148962088. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:49:58,446][86177] Avg episode reward: [(0, '-532.610'), (1, '-556.310')] -[2023-11-28 07:49:58,532][87426] Updated weights for policy 1, policy_version 290810 (0.0012) -[2023-11-28 07:50:00,088][87424] Updated weights for policy 0, policy_version 291049 (0.0009) -[2023-11-28 07:50:00,375][87426] Updated weights for policy 1, policy_version 290820 (0.0011) -[2023-11-28 07:50:00,470][87424] Updated weights for policy 0, policy_version 291059 (0.0008) -[2023-11-28 07:50:00,759][87426] Updated weights for policy 1, policy_version 290830 (0.0009) -[2023-11-28 07:50:00,853][87424] Updated weights for policy 0, policy_version 291069 (0.0011) -[2023-11-28 07:50:01,144][87426] Updated weights for policy 1, policy_version 290840 (0.0011) -[2023-11-28 07:50:02,823][87424] Updated weights for policy 0, policy_version 291079 (0.0012) -[2023-11-28 07:50:03,213][87424] Updated weights for policy 0, policy_version 291089 (0.0012) -[2023-11-28 07:50:03,374][87426] Updated weights for policy 1, policy_version 290850 (0.0012) -[2023-11-28 07:50:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 148971520. Throughput: 0: 2731.9, 1: 2735.3. Samples: 148988404. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:50:03,445][86177] Avg episode reward: [(0, '-529.340'), (1, '-566.610')] -[2023-11-28 07:50:03,593][87424] Updated weights for policy 0, policy_version 291099 (0.0011) -[2023-11-28 07:50:03,748][87426] Updated weights for policy 1, policy_version 290860 (0.0011) -[2023-11-28 07:50:04,127][87426] Updated weights for policy 1, policy_version 290870 (0.0010) -[2023-11-28 07:50:04,508][87426] Updated weights for policy 1, policy_version 290880 (0.0008) -[2023-11-28 07:50:05,521][87424] Updated weights for policy 0, policy_version 291109 (0.0011) -[2023-11-28 07:50:05,903][87424] Updated weights for policy 0, policy_version 291119 (0.0011) -[2023-11-28 07:50:06,287][87424] Updated weights for policy 0, policy_version 291129 (0.0007) -[2023-11-28 07:50:07,052][87426] Updated weights for policy 1, policy_version 290890 (0.0012) -[2023-11-28 07:50:07,425][87426] Updated weights for policy 1, policy_version 290900 (0.0011) -[2023-11-28 07:50:07,812][87426] Updated weights for policy 1, policy_version 290910 (0.0012) -[2023-11-28 07:50:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 149004288. Throughput: 0: 2738.1, 1: 2737.3. Samples: 149020348. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:50:08,446][86177] Avg episode reward: [(0, '-536.110'), (1, '-554.000')] -[2023-11-28 07:50:08,477][87424] Updated weights for policy 0, policy_version 291139 (0.0008) -[2023-11-28 07:50:08,874][87424] Updated weights for policy 0, policy_version 291149 (0.0008) -[2023-11-28 07:50:09,267][87424] Updated weights for policy 0, policy_version 291159 (0.0011) -[2023-11-28 07:50:10,017][87426] Updated weights for policy 1, policy_version 290920 (0.0012) -[2023-11-28 07:50:10,403][87426] Updated weights for policy 1, policy_version 290930 (0.0012) -[2023-11-28 07:50:10,781][87426] Updated weights for policy 1, policy_version 290940 (0.0012) -[2023-11-28 07:50:11,514][87424] Updated weights for policy 0, policy_version 291169 (0.0012) -[2023-11-28 07:50:11,901][87424] Updated weights for policy 0, policy_version 291179 (0.0010) -[2023-11-28 07:50:12,290][87424] Updated weights for policy 0, policy_version 291189 (0.0012) -[2023-11-28 07:50:12,657][87424] Updated weights for policy 0, policy_version 291199 (0.0009) -[2023-11-28 07:50:12,884][87426] Updated weights for policy 1, policy_version 290950 (0.0010) -[2023-11-28 07:50:13,258][87426] Updated weights for policy 1, policy_version 290960 (0.0010) -[2023-11-28 07:50:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 149028864. Throughput: 0: 2738.5, 1: 2704.4. Samples: 149044496. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:50:13,445][86177] Avg episode reward: [(0, '-534.130'), (1, '-550.060')] -[2023-11-28 07:50:13,634][87426] Updated weights for policy 1, policy_version 290970 (0.0011) -[2023-11-28 07:50:14,733][87424] Updated weights for policy 0, policy_version 291209 (0.0011) -[2023-11-28 07:50:15,112][87424] Updated weights for policy 0, policy_version 291219 (0.0012) -[2023-11-28 07:50:15,490][87424] Updated weights for policy 0, policy_version 291229 (0.0011) -[2023-11-28 07:50:16,190][87426] Updated weights for policy 1, policy_version 290980 (0.0011) -[2023-11-28 07:50:16,560][87426] Updated weights for policy 1, policy_version 290990 (0.0007) -[2023-11-28 07:50:16,938][87426] Updated weights for policy 1, policy_version 291000 (0.0007) -[2023-11-28 07:50:17,986][87424] Updated weights for policy 0, policy_version 291239 (0.0010) -[2023-11-28 07:50:18,367][87424] Updated weights for policy 0, policy_version 291249 (0.0012) -[2023-11-28 07:50:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 149053440. Throughput: 0: 2715.3, 1: 2709.7. Samples: 149068508. Policy #0 lag: (min: 31.0, avg: 38.2, max: 63.0) -[2023-11-28 07:50:18,445][86177] Avg episode reward: [(0, '-546.120'), (1, '-548.330')] -[2023-11-28 07:50:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000291008_74498048.pth... -[2023-11-28 07:50:18,491][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000288480_73850880.pth -[2023-11-28 07:50:18,741][87424] Updated weights for policy 0, policy_version 291259 (0.0012) -[2023-11-28 07:50:18,934][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000291264_74563584.pth... -[2023-11-28 07:50:18,983][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000288704_73908224.pth -[2023-11-28 07:50:19,434][87426] Updated weights for policy 1, policy_version 291010 (0.0007) -[2023-11-28 07:50:19,808][87426] Updated weights for policy 1, policy_version 291020 (0.0008) -[2023-11-28 07:50:20,184][87426] Updated weights for policy 1, policy_version 291030 (0.0008) -[2023-11-28 07:50:20,566][87426] Updated weights for policy 1, policy_version 291040 (0.0010) -[2023-11-28 07:50:20,844][87424] Updated weights for policy 0, policy_version 291269 (0.0010) -[2023-11-28 07:50:21,222][87424] Updated weights for policy 0, policy_version 291279 (0.0009) -[2023-11-28 07:50:21,601][87424] Updated weights for policy 0, policy_version 291289 (0.0011) -[2023-11-28 07:50:22,742][87426] Updated weights for policy 1, policy_version 291050 (0.0009) -[2023-11-28 07:50:23,119][87426] Updated weights for policy 1, policy_version 291060 (0.0010) -[2023-11-28 07:50:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149078016. Throughput: 0: 2717.1, 1: 2702.6. Samples: 149099072. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:50:23,445][86177] Avg episode reward: [(0, '-562.050'), (1, '-563.310')] -[2023-11-28 07:50:23,493][87426] Updated weights for policy 1, policy_version 291070 (0.0010) -[2023-11-28 07:50:24,155][87424] Updated weights for policy 0, policy_version 291299 (0.0011) -[2023-11-28 07:50:24,535][87424] Updated weights for policy 0, policy_version 291309 (0.0008) -[2023-11-28 07:50:24,905][87424] Updated weights for policy 0, policy_version 291319 (0.0007) -[2023-11-28 07:50:26,060][87426] Updated weights for policy 1, policy_version 291080 (0.0010) -[2023-11-28 07:50:26,437][87426] Updated weights for policy 1, policy_version 291090 (0.0011) -[2023-11-28 07:50:26,813][87426] Updated weights for policy 1, policy_version 291100 (0.0011) -[2023-11-28 07:50:27,464][87424] Updated weights for policy 0, policy_version 291329 (0.0007) -[2023-11-28 07:50:27,840][87424] Updated weights for policy 0, policy_version 291339 (0.0007) -[2023-11-28 07:50:28,227][87424] Updated weights for policy 0, policy_version 291349 (0.0007) -[2023-11-28 07:50:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149102592. Throughput: 0: 2705.4, 1: 2713.8. Samples: 149122600. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:50:28,445][86177] Avg episode reward: [(0, '-565.660'), (1, '-597.760')] -[2023-11-28 07:50:28,624][87424] Updated weights for policy 0, policy_version 291359 (0.0012) -[2023-11-28 07:50:28,958][87426] Updated weights for policy 1, policy_version 291110 (0.0010) -[2023-11-28 07:50:29,339][87426] Updated weights for policy 1, policy_version 291120 (0.0007) -[2023-11-28 07:50:29,711][87426] Updated weights for policy 1, policy_version 291130 (0.0011) -[2023-11-28 07:50:31,175][87424] Updated weights for policy 0, policy_version 291369 (0.0011) -[2023-11-28 07:50:31,564][87424] Updated weights for policy 0, policy_version 291379 (0.0009) -[2023-11-28 07:50:31,934][87426] Updated weights for policy 1, policy_version 291140 (0.0010) -[2023-11-28 07:50:31,949][87424] Updated weights for policy 0, policy_version 291389 (0.0009) -[2023-11-28 07:50:32,308][87426] Updated weights for policy 1, policy_version 291150 (0.0008) -[2023-11-28 07:50:32,696][87426] Updated weights for policy 1, policy_version 291160 (0.0008) -[2023-11-28 07:50:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 149135360. Throughput: 0: 2682.0, 1: 2692.6. Samples: 149145732. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:50:33,446][86177] Avg episode reward: [(0, '-564.760'), (1, '-603.900')] -[2023-11-28 07:50:34,488][87424] Updated weights for policy 0, policy_version 291399 (0.0010) -[2023-11-28 07:50:34,723][87426] Updated weights for policy 1, policy_version 291170 (0.0009) -[2023-11-28 07:50:34,877][87424] Updated weights for policy 0, policy_version 291409 (0.0011) -[2023-11-28 07:50:35,104][87426] Updated weights for policy 1, policy_version 291180 (0.0010) -[2023-11-28 07:50:35,250][87424] Updated weights for policy 0, policy_version 291419 (0.0008) -[2023-11-28 07:50:35,485][87426] Updated weights for policy 1, policy_version 291190 (0.0012) -[2023-11-28 07:50:35,863][87426] Updated weights for policy 1, policy_version 291200 (0.0012) -[2023-11-28 07:50:37,625][87426] Updated weights for policy 1, policy_version 291210 (0.0008) -[2023-11-28 07:50:37,629][87424] Updated weights for policy 0, policy_version 291429 (0.0009) -[2023-11-28 07:50:38,000][87424] Updated weights for policy 0, policy_version 291439 (0.0007) -[2023-11-28 07:50:38,012][87426] Updated weights for policy 1, policy_version 291220 (0.0008) -[2023-11-28 07:50:38,377][87426] Updated weights for policy 1, policy_version 291230 (0.0010) -[2023-11-28 07:50:38,386][87424] Updated weights for policy 0, policy_version 291449 (0.0008) -[2023-11-28 07:50:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 149151744. Throughput: 0: 2664.1, 1: 2698.5. Samples: 149178680. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:50:38,446][86177] Avg episode reward: [(0, '-561.630'), (1, '-632.300')] -[2023-11-28 07:50:40,075][87426] Updated weights for policy 1, policy_version 291240 (0.0013) -[2023-11-28 07:50:40,461][87426] Updated weights for policy 1, policy_version 291250 (0.0010) -[2023-11-28 07:50:40,756][87424] Updated weights for policy 0, policy_version 291459 (0.0008) -[2023-11-28 07:50:40,835][87426] Updated weights for policy 1, policy_version 291260 (0.0008) -[2023-11-28 07:50:41,129][87424] Updated weights for policy 0, policy_version 291469 (0.0011) -[2023-11-28 07:50:41,513][87424] Updated weights for policy 0, policy_version 291479 (0.0009) -[2023-11-28 07:50:43,307][87426] Updated weights for policy 1, policy_version 291270 (0.0009) -[2023-11-28 07:50:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149184512. Throughput: 0: 2645.4, 1: 2685.2. Samples: 149201964. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:50:43,445][86177] Avg episode reward: [(0, '-547.470'), (1, '-635.630')] -[2023-11-28 07:50:43,628][87424] Updated weights for policy 0, policy_version 291489 (0.0010) -[2023-11-28 07:50:43,685][87426] Updated weights for policy 1, policy_version 291280 (0.0007) -[2023-11-28 07:50:44,012][87424] Updated weights for policy 0, policy_version 291499 (0.0010) -[2023-11-28 07:50:44,067][87426] Updated weights for policy 1, policy_version 291290 (0.0011) -[2023-11-28 07:50:44,397][87424] Updated weights for policy 0, policy_version 291509 (0.0007) -[2023-11-28 07:50:44,780][87424] Updated weights for policy 0, policy_version 291519 (0.0007) -[2023-11-28 07:50:45,968][87426] Updated weights for policy 1, policy_version 291300 (0.0011) -[2023-11-28 07:50:46,348][87426] Updated weights for policy 1, policy_version 291310 (0.0012) -[2023-11-28 07:50:46,725][87426] Updated weights for policy 1, policy_version 291320 (0.0012) -[2023-11-28 07:50:47,188][87424] Updated weights for policy 0, policy_version 291529 (0.0011) -[2023-11-28 07:50:47,570][87424] Updated weights for policy 0, policy_version 291539 (0.0012) -[2023-11-28 07:50:47,949][87424] Updated weights for policy 0, policy_version 291549 (0.0012) -[2023-11-28 07:50:48,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 149217280. Throughput: 0: 2596.4, 1: 2693.2. Samples: 149226436. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:50:48,445][86177] Avg episode reward: [(0, '-544.980'), (1, '-642.280')] -[2023-11-28 07:50:48,992][87426] Updated weights for policy 1, policy_version 291330 (0.0009) -[2023-11-28 07:50:49,360][87426] Updated weights for policy 1, policy_version 291340 (0.0012) -[2023-11-28 07:50:49,737][87426] Updated weights for policy 1, policy_version 291350 (0.0012) -[2023-11-28 07:50:50,117][87426] Updated weights for policy 1, policy_version 291360 (0.0010) -[2023-11-28 07:50:50,475][87424] Updated weights for policy 0, policy_version 291559 (0.0011) -[2023-11-28 07:50:50,867][87424] Updated weights for policy 0, policy_version 291569 (0.0007) -[2023-11-28 07:50:51,236][87424] Updated weights for policy 0, policy_version 291579 (0.0008) -[2023-11-28 07:50:52,285][87426] Updated weights for policy 1, policy_version 291370 (0.0009) -[2023-11-28 07:50:52,669][87426] Updated weights for policy 1, policy_version 291380 (0.0011) -[2023-11-28 07:50:53,047][87426] Updated weights for policy 1, policy_version 291390 (0.0011) -[2023-11-28 07:50:53,291][87424] Updated weights for policy 0, policy_version 291589 (0.0008) -[2023-11-28 07:50:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149241856. Throughput: 0: 2574.0, 1: 2721.6. Samples: 149258648. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:50:53,445][86177] Avg episode reward: [(0, '-535.820'), (1, '-606.090')] -[2023-11-28 07:50:53,672][87424] Updated weights for policy 0, policy_version 291599 (0.0011) -[2023-11-28 07:50:54,048][87424] Updated weights for policy 0, policy_version 291609 (0.0011) -[2023-11-28 07:50:55,473][87426] Updated weights for policy 1, policy_version 291400 (0.0009) -[2023-11-28 07:50:55,857][87426] Updated weights for policy 1, policy_version 291410 (0.0011) -[2023-11-28 07:50:56,237][87426] Updated weights for policy 1, policy_version 291420 (0.0011) -[2023-11-28 07:50:56,337][87424] Updated weights for policy 0, policy_version 291619 (0.0010) -[2023-11-28 07:50:56,713][87424] Updated weights for policy 0, policy_version 291629 (0.0007) -[2023-11-28 07:50:57,089][87424] Updated weights for policy 0, policy_version 291639 (0.0007) -[2023-11-28 07:50:57,931][87426] Updated weights for policy 1, policy_version 291430 (0.0012) -[2023-11-28 07:50:58,305][87426] Updated weights for policy 1, policy_version 291440 (0.0012) -[2023-11-28 07:50:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149266432. Throughput: 0: 2570.7, 1: 2755.6. Samples: 149284176. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:50:58,445][86177] Avg episode reward: [(0, '-546.880'), (1, '-597.170')] -[2023-11-28 07:50:58,688][87426] Updated weights for policy 1, policy_version 291450 (0.0012) -[2023-11-28 07:50:58,907][87424] Updated weights for policy 0, policy_version 291649 (0.0008) -[2023-11-28 07:50:59,295][87424] Updated weights for policy 0, policy_version 291659 (0.0011) -[2023-11-28 07:50:59,672][87424] Updated weights for policy 0, policy_version 291669 (0.0011) -[2023-11-28 07:51:00,055][87424] Updated weights for policy 0, policy_version 291679 (0.0011) -[2023-11-28 07:51:00,970][87426] Updated weights for policy 1, policy_version 291460 (0.0010) -[2023-11-28 07:51:01,345][87426] Updated weights for policy 1, policy_version 291470 (0.0010) -[2023-11-28 07:51:01,724][87426] Updated weights for policy 1, policy_version 291480 (0.0010) -[2023-11-28 07:51:02,066][87424] Updated weights for policy 0, policy_version 291689 (0.0010) -[2023-11-28 07:51:02,440][87424] Updated weights for policy 0, policy_version 291699 (0.0011) -[2023-11-28 07:51:02,821][87424] Updated weights for policy 0, policy_version 291709 (0.0012) -[2023-11-28 07:51:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 149299200. Throughput: 0: 2595.4, 1: 2762.3. Samples: 149309604. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:51:03,445][86177] Avg episode reward: [(0, '-551.020'), (1, '-609.310')] -[2023-11-28 07:51:03,913][87426] Updated weights for policy 1, policy_version 291490 (0.0011) -[2023-11-28 07:51:04,294][87426] Updated weights for policy 1, policy_version 291500 (0.0011) -[2023-11-28 07:51:04,665][87426] Updated weights for policy 1, policy_version 291510 (0.0012) -[2023-11-28 07:51:05,048][87426] Updated weights for policy 1, policy_version 291520 (0.0008) -[2023-11-28 07:51:05,095][87424] Updated weights for policy 0, policy_version 291719 (0.0010) -[2023-11-28 07:51:05,474][87424] Updated weights for policy 0, policy_version 291729 (0.0008) -[2023-11-28 07:51:05,858][87424] Updated weights for policy 0, policy_version 291739 (0.0008) -[2023-11-28 07:51:07,007][87426] Updated weights for policy 1, policy_version 291530 (0.0012) -[2023-11-28 07:51:07,378][87426] Updated weights for policy 1, policy_version 291540 (0.0012) -[2023-11-28 07:51:07,755][87426] Updated weights for policy 1, policy_version 291550 (0.0012) -[2023-11-28 07:51:08,312][87424] Updated weights for policy 0, policy_version 291749 (0.0007) -[2023-11-28 07:51:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149323776. Throughput: 0: 2612.0, 1: 2786.1. Samples: 149341988. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:51:08,445][86177] Avg episode reward: [(0, '-561.570'), (1, '-601.210')] -[2023-11-28 07:51:08,693][87424] Updated weights for policy 0, policy_version 291759 (0.0008) -[2023-11-28 07:51:09,082][87424] Updated weights for policy 0, policy_version 291769 (0.0008) -[2023-11-28 07:51:09,996][87426] Updated weights for policy 1, policy_version 291560 (0.0011) -[2023-11-28 07:51:10,384][87426] Updated weights for policy 1, policy_version 291570 (0.0010) -[2023-11-28 07:51:10,757][87426] Updated weights for policy 1, policy_version 291580 (0.0009) -[2023-11-28 07:51:11,240][87424] Updated weights for policy 0, policy_version 291779 (0.0009) -[2023-11-28 07:51:11,633][87424] Updated weights for policy 0, policy_version 291789 (0.0009) -[2023-11-28 07:51:12,013][87424] Updated weights for policy 0, policy_version 291799 (0.0011) -[2023-11-28 07:51:12,786][87426] Updated weights for policy 1, policy_version 291590 (0.0010) -[2023-11-28 07:51:13,159][87426] Updated weights for policy 1, policy_version 291600 (0.0008) -[2023-11-28 07:51:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149348352. Throughput: 0: 2629.9, 1: 2785.5. Samples: 149366292. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:51:13,445][86177] Avg episode reward: [(0, '-565.030'), (1, '-644.910')] -[2023-11-28 07:51:13,537][87426] Updated weights for policy 1, policy_version 291610 (0.0007) -[2023-11-28 07:51:13,962][87424] Updated weights for policy 0, policy_version 291809 (0.0009) -[2023-11-28 07:51:14,340][87424] Updated weights for policy 0, policy_version 291819 (0.0007) -[2023-11-28 07:51:14,733][87424] Updated weights for policy 0, policy_version 291829 (0.0008) -[2023-11-28 07:51:15,121][87424] Updated weights for policy 0, policy_version 291839 (0.0010) -[2023-11-28 07:51:16,072][87426] Updated weights for policy 1, policy_version 291620 (0.0008) -[2023-11-28 07:51:16,454][87426] Updated weights for policy 1, policy_version 291630 (0.0008) -[2023-11-28 07:51:16,830][87426] Updated weights for policy 1, policy_version 291640 (0.0008) -[2023-11-28 07:51:17,626][87424] Updated weights for policy 0, policy_version 291849 (0.0008) -[2023-11-28 07:51:18,006][87424] Updated weights for policy 0, policy_version 291859 (0.0007) -[2023-11-28 07:51:18,388][87424] Updated weights for policy 0, policy_version 291869 (0.0008) -[2023-11-28 07:51:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 149372928. Throughput: 0: 2646.0, 1: 2786.1. Samples: 149390180. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:51:18,446][86177] Avg episode reward: [(0, '-572.820'), (1, '-687.190')] -[2023-11-28 07:51:18,511][87426] Updated weights for policy 1, policy_version 291650 (0.0009) -[2023-11-28 07:51:18,893][87426] Updated weights for policy 1, policy_version 291660 (0.0012) -[2023-11-28 07:51:19,273][87426] Updated weights for policy 1, policy_version 291670 (0.0012) -[2023-11-28 07:51:19,654][87426] Updated weights for policy 1, policy_version 291680 (0.0012) -[2023-11-28 07:51:20,541][87424] Updated weights for policy 0, policy_version 291879 (0.0009) -[2023-11-28 07:51:20,919][87424] Updated weights for policy 0, policy_version 291889 (0.0010) -[2023-11-28 07:51:21,304][87424] Updated weights for policy 0, policy_version 291899 (0.0008) -[2023-11-28 07:51:21,705][87426] Updated weights for policy 1, policy_version 291690 (0.0011) -[2023-11-28 07:51:22,077][87426] Updated weights for policy 1, policy_version 291700 (0.0011) -[2023-11-28 07:51:22,459][87426] Updated weights for policy 1, policy_version 291710 (0.0008) -[2023-11-28 07:51:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 149405696. Throughput: 0: 2676.3, 1: 2754.1. Samples: 149423044. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:51:23,445][86177] Avg episode reward: [(0, '-554.710'), (1, '-716.830')] -[2023-11-28 07:51:23,470][87424] Updated weights for policy 0, policy_version 291909 (0.0010) -[2023-11-28 07:51:23,849][87424] Updated weights for policy 0, policy_version 291919 (0.0012) -[2023-11-28 07:51:24,236][87424] Updated weights for policy 0, policy_version 291929 (0.0012) -[2023-11-28 07:51:24,519][87426] Updated weights for policy 1, policy_version 291720 (0.0011) -[2023-11-28 07:51:24,904][87426] Updated weights for policy 1, policy_version 291730 (0.0012) -[2023-11-28 07:51:25,282][87426] Updated weights for policy 1, policy_version 291740 (0.0012) -[2023-11-28 07:51:26,028][87424] Updated weights for policy 0, policy_version 291939 (0.0007) -[2023-11-28 07:51:26,411][87424] Updated weights for policy 0, policy_version 291949 (0.0007) -[2023-11-28 07:51:26,798][87424] Updated weights for policy 0, policy_version 291959 (0.0011) -[2023-11-28 07:51:27,390][87426] Updated weights for policy 1, policy_version 291750 (0.0010) -[2023-11-28 07:51:27,762][87426] Updated weights for policy 1, policy_version 291760 (0.0010) -[2023-11-28 07:51:28,136][87426] Updated weights for policy 1, policy_version 291770 (0.0007) -[2023-11-28 07:51:28,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 149438464. Throughput: 0: 2691.1, 1: 2781.8. Samples: 149448244. Policy #0 lag: (min: 31.0, avg: 50.2, max: 82.0) -[2023-11-28 07:51:28,445][86177] Avg episode reward: [(0, '-547.960'), (1, '-655.250')] -[2023-11-28 07:51:28,817][87424] Updated weights for policy 0, policy_version 291969 (0.0010) -[2023-11-28 07:51:29,204][87424] Updated weights for policy 0, policy_version 291979 (0.0008) -[2023-11-28 07:51:29,593][87424] Updated weights for policy 0, policy_version 291989 (0.0009) -[2023-11-28 07:51:29,962][87424] Updated weights for policy 0, policy_version 291999 (0.0008) -[2023-11-28 07:51:30,673][87426] Updated weights for policy 1, policy_version 291780 (0.0009) -[2023-11-28 07:51:31,053][87426] Updated weights for policy 1, policy_version 291790 (0.0011) -[2023-11-28 07:51:31,429][87426] Updated weights for policy 1, policy_version 291800 (0.0011) -[2023-11-28 07:51:32,498][87424] Updated weights for policy 0, policy_version 292009 (0.0010) -[2023-11-28 07:51:32,879][87424] Updated weights for policy 0, policy_version 292019 (0.0011) -[2023-11-28 07:51:33,270][87424] Updated weights for policy 0, policy_version 292029 (0.0010) -[2023-11-28 07:51:33,327][87426] Updated weights for policy 1, policy_version 291810 (0.0010) -[2023-11-28 07:51:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 149463040. Throughput: 0: 2698.2, 1: 2759.5. Samples: 149472036. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:51:33,445][86177] Avg episode reward: [(0, '-555.300'), (1, '-650.980')] -[2023-11-28 07:51:33,707][87426] Updated weights for policy 1, policy_version 291820 (0.0011) -[2023-11-28 07:51:34,078][87426] Updated weights for policy 1, policy_version 291830 (0.0012) -[2023-11-28 07:51:34,457][87426] Updated weights for policy 1, policy_version 291840 (0.0009) -[2023-11-28 07:51:35,547][87424] Updated weights for policy 0, policy_version 292039 (0.0010) -[2023-11-28 07:51:35,923][87424] Updated weights for policy 0, policy_version 292049 (0.0012) -[2023-11-28 07:51:36,311][87424] Updated weights for policy 0, policy_version 292059 (0.0008) -[2023-11-28 07:51:36,874][87426] Updated weights for policy 1, policy_version 291850 (0.0012) -[2023-11-28 07:51:37,252][87426] Updated weights for policy 1, policy_version 291860 (0.0012) -[2023-11-28 07:51:37,633][87426] Updated weights for policy 1, policy_version 291870 (0.0012) -[2023-11-28 07:51:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 149487616. Throughput: 0: 2707.4, 1: 2728.8. Samples: 149503276. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:51:38,446][87424] Updated weights for policy 0, policy_version 292069 (0.0010) -[2023-11-28 07:51:38,445][86177] Avg episode reward: [(0, '-554.310'), (1, '-762.070')] -[2023-11-28 07:51:38,825][87424] Updated weights for policy 0, policy_version 292079 (0.0012) -[2023-11-28 07:51:39,207][87424] Updated weights for policy 0, policy_version 292089 (0.0012) -[2023-11-28 07:51:39,892][87426] Updated weights for policy 1, policy_version 291880 (0.0012) -[2023-11-28 07:51:40,270][87426] Updated weights for policy 1, policy_version 291890 (0.0012) -[2023-11-28 07:51:40,646][87426] Updated weights for policy 1, policy_version 291900 (0.0012) -[2023-11-28 07:51:41,748][87424] Updated weights for policy 0, policy_version 292099 (0.0012) -[2023-11-28 07:51:42,135][87424] Updated weights for policy 0, policy_version 292109 (0.0010) -[2023-11-28 07:51:42,515][87424] Updated weights for policy 0, policy_version 292119 (0.0011) -[2023-11-28 07:51:42,904][87426] Updated weights for policy 1, policy_version 291910 (0.0011) -[2023-11-28 07:51:43,287][87426] Updated weights for policy 1, policy_version 291920 (0.0012) -[2023-11-28 07:51:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 149512192. Throughput: 0: 2703.5, 1: 2720.7. Samples: 149528264. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:51:43,445][86177] Avg episode reward: [(0, '-559.670'), (1, '-730.580')] -[2023-11-28 07:51:43,672][87426] Updated weights for policy 1, policy_version 291930 (0.0011) -[2023-11-28 07:51:44,462][87424] Updated weights for policy 0, policy_version 292129 (0.0010) -[2023-11-28 07:51:44,847][87424] Updated weights for policy 0, policy_version 292139 (0.0011) -[2023-11-28 07:51:45,221][87424] Updated weights for policy 0, policy_version 292149 (0.0012) -[2023-11-28 07:51:45,606][87424] Updated weights for policy 0, policy_version 292159 (0.0012) -[2023-11-28 07:51:46,233][87426] Updated weights for policy 1, policy_version 291940 (0.0008) -[2023-11-28 07:51:46,626][87426] Updated weights for policy 1, policy_version 291950 (0.0008) -[2023-11-28 07:51:46,999][87426] Updated weights for policy 1, policy_version 291960 (0.0008) -[2023-11-28 07:51:47,767][87424] Updated weights for policy 0, policy_version 292169 (0.0009) -[2023-11-28 07:51:48,161][87424] Updated weights for policy 0, policy_version 292179 (0.0011) -[2023-11-28 07:51:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149536768. Throughput: 0: 2690.9, 1: 2691.5. Samples: 149551812. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:51:48,445][86177] Avg episode reward: [(0, '-562.800'), (1, '-769.520')] -[2023-11-28 07:51:48,547][87424] Updated weights for policy 0, policy_version 292189 (0.0008) -[2023-11-28 07:51:49,534][87426] Updated weights for policy 1, policy_version 291970 (0.0008) -[2023-11-28 07:51:49,913][87426] Updated weights for policy 1, policy_version 291980 (0.0010) -[2023-11-28 07:51:50,301][87426] Updated weights for policy 1, policy_version 291990 (0.0008) -[2023-11-28 07:51:50,679][87426] Updated weights for policy 1, policy_version 292000 (0.0008) -[2023-11-28 07:51:50,808][87424] Updated weights for policy 0, policy_version 292199 (0.0009) -[2023-11-28 07:51:51,186][87424] Updated weights for policy 0, policy_version 292209 (0.0011) -[2023-11-28 07:51:51,576][87424] Updated weights for policy 0, policy_version 292219 (0.0011) -[2023-11-28 07:51:52,872][87426] Updated weights for policy 1, policy_version 292010 (0.0012) -[2023-11-28 07:51:53,251][87426] Updated weights for policy 1, policy_version 292020 (0.0012) -[2023-11-28 07:51:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 149561344. Throughput: 0: 2709.4, 1: 2681.7. Samples: 149584588. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:51:53,445][86177] Avg episode reward: [(0, '-578.290'), (1, '-721.150')] -[2023-11-28 07:51:53,627][87426] Updated weights for policy 1, policy_version 292030 (0.0012) -[2023-11-28 07:51:53,779][87424] Updated weights for policy 0, policy_version 292229 (0.0010) -[2023-11-28 07:51:54,163][87424] Updated weights for policy 0, policy_version 292239 (0.0011) -[2023-11-28 07:51:54,548][87424] Updated weights for policy 0, policy_version 292249 (0.0009) -[2023-11-28 07:51:55,662][87426] Updated weights for policy 1, policy_version 292040 (0.0011) -[2023-11-28 07:51:56,042][87426] Updated weights for policy 1, policy_version 292050 (0.0011) -[2023-11-28 07:51:56,428][87426] Updated weights for policy 1, policy_version 292060 (0.0010) -[2023-11-28 07:51:57,025][87424] Updated weights for policy 0, policy_version 292259 (0.0010) -[2023-11-28 07:51:57,405][87424] Updated weights for policy 0, policy_version 292269 (0.0007) -[2023-11-28 07:51:57,779][87424] Updated weights for policy 0, policy_version 292279 (0.0007) -[2023-11-28 07:51:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 149594112. Throughput: 0: 2700.4, 1: 2691.4. Samples: 149608924. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:51:58,445][86177] Avg episode reward: [(0, '-579.370'), (1, '-612.660')] -[2023-11-28 07:51:58,788][87426] Updated weights for policy 1, policy_version 292070 (0.0008) -[2023-11-28 07:51:59,167][87426] Updated weights for policy 1, policy_version 292080 (0.0008) -[2023-11-28 07:51:59,557][87426] Updated weights for policy 1, policy_version 292090 (0.0007) -[2023-11-28 07:51:59,850][87424] Updated weights for policy 0, policy_version 292289 (0.0008) -[2023-11-28 07:52:00,227][87424] Updated weights for policy 0, policy_version 292299 (0.0012) -[2023-11-28 07:52:00,600][87424] Updated weights for policy 0, policy_version 292309 (0.0012) -[2023-11-28 07:52:00,988][87424] Updated weights for policy 0, policy_version 292319 (0.0012) -[2023-11-28 07:52:01,592][87426] Updated weights for policy 1, policy_version 292100 (0.0009) -[2023-11-28 07:52:01,973][87426] Updated weights for policy 1, policy_version 292110 (0.0012) -[2023-11-28 07:52:02,349][87426] Updated weights for policy 1, policy_version 292120 (0.0012) -[2023-11-28 07:52:03,347][87424] Updated weights for policy 0, policy_version 292329 (0.0011) -[2023-11-28 07:52:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 149618688. Throughput: 0: 2696.3, 1: 2706.9. Samples: 149633320. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:03,445][86177] Avg episode reward: [(0, '-561.430'), (1, '-581.130')] -[2023-11-28 07:52:03,732][87424] Updated weights for policy 0, policy_version 292339 (0.0011) -[2023-11-28 07:52:04,123][87424] Updated weights for policy 0, policy_version 292349 (0.0012) -[2023-11-28 07:52:04,317][87426] Updated weights for policy 1, policy_version 292130 (0.0011) -[2023-11-28 07:52:04,691][87426] Updated weights for policy 1, policy_version 292140 (0.0012) -[2023-11-28 07:52:05,071][87426] Updated weights for policy 1, policy_version 292150 (0.0011) -[2023-11-28 07:52:05,444][87426] Updated weights for policy 1, policy_version 292160 (0.0008) -[2023-11-28 07:52:05,979][87424] Updated weights for policy 0, policy_version 292359 (0.0010) -[2023-11-28 07:52:06,356][87424] Updated weights for policy 0, policy_version 292369 (0.0007) -[2023-11-28 07:52:06,737][87424] Updated weights for policy 0, policy_version 292379 (0.0008) -[2023-11-28 07:52:07,316][87426] Updated weights for policy 1, policy_version 292170 (0.0012) -[2023-11-28 07:52:07,699][87426] Updated weights for policy 1, policy_version 292180 (0.0012) -[2023-11-28 07:52:08,074][87426] Updated weights for policy 1, policy_version 292190 (0.0012) -[2023-11-28 07:52:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 149651456. Throughput: 0: 2675.3, 1: 2703.2. Samples: 149665076. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:08,445][86177] Avg episode reward: [(0, '-545.220'), (1, '-602.430')] -[2023-11-28 07:52:09,084][87424] Updated weights for policy 0, policy_version 292389 (0.0007) -[2023-11-28 07:52:09,460][87424] Updated weights for policy 0, policy_version 292399 (0.0008) -[2023-11-28 07:52:09,846][87424] Updated weights for policy 0, policy_version 292409 (0.0009) -[2023-11-28 07:52:10,374][87426] Updated weights for policy 1, policy_version 292200 (0.0012) -[2023-11-28 07:52:10,742][87426] Updated weights for policy 1, policy_version 292210 (0.0010) -[2023-11-28 07:52:11,120][87426] Updated weights for policy 1, policy_version 292220 (0.0008) -[2023-11-28 07:52:12,226][87424] Updated weights for policy 0, policy_version 292419 (0.0011) -[2023-11-28 07:52:12,609][87424] Updated weights for policy 0, policy_version 292429 (0.0010) -[2023-11-28 07:52:12,988][87424] Updated weights for policy 0, policy_version 292439 (0.0011) -[2023-11-28 07:52:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 149676032. Throughput: 0: 2671.7, 1: 2678.4. Samples: 149689000. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:13,446][86177] Avg episode reward: [(0, '-544.500'), (1, '-609.630')] -[2023-11-28 07:52:13,478][87426] Updated weights for policy 1, policy_version 292230 (0.0008) -[2023-11-28 07:52:13,858][87426] Updated weights for policy 1, policy_version 292240 (0.0012) -[2023-11-28 07:52:14,243][87426] Updated weights for policy 1, policy_version 292250 (0.0008) -[2023-11-28 07:52:14,819][87424] Updated weights for policy 0, policy_version 292449 (0.0008) -[2023-11-28 07:52:15,208][87424] Updated weights for policy 0, policy_version 292459 (0.0008) -[2023-11-28 07:52:15,591][87424] Updated weights for policy 0, policy_version 292469 (0.0010) -[2023-11-28 07:52:15,977][87424] Updated weights for policy 0, policy_version 292479 (0.0011) -[2023-11-28 07:52:16,817][87426] Updated weights for policy 1, policy_version 292260 (0.0010) -[2023-11-28 07:52:17,187][87426] Updated weights for policy 1, policy_version 292270 (0.0007) -[2023-11-28 07:52:17,572][87426] Updated weights for policy 1, policy_version 292280 (0.0007) -[2023-11-28 07:52:18,324][87424] Updated weights for policy 0, policy_version 292489 (0.0010) -[2023-11-28 07:52:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 149700608. Throughput: 0: 2686.5, 1: 2688.7. Samples: 149713920. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:18,446][86177] Avg episode reward: [(0, '-519.590'), (1, '-597.340')] -[2023-11-28 07:52:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000292288_74825728.pth... -[2023-11-28 07:52:18,494][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000289760_74178560.pth -[2023-11-28 07:52:18,498][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000292288_74825728.pth -[2023-11-28 07:52:18,709][87424] Updated weights for policy 0, policy_version 292499 (0.0007) -[2023-11-28 07:52:19,100][87424] Updated weights for policy 0, policy_version 292509 (0.0009) -[2023-11-28 07:52:19,213][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000292512_74883072.pth... -[2023-11-28 07:52:19,244][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000290016_74244096.pth -[2023-11-28 07:52:19,249][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000292512_74883072.pth -[2023-11-28 07:52:20,097][87426] Updated weights for policy 1, policy_version 292290 (0.0008) -[2023-11-28 07:52:20,478][87426] Updated weights for policy 1, policy_version 292300 (0.0011) -[2023-11-28 07:52:20,853][87426] Updated weights for policy 1, policy_version 292310 (0.0010) -[2023-11-28 07:52:21,223][87426] Updated weights for policy 1, policy_version 292320 (0.0012) -[2023-11-28 07:52:21,601][87424] Updated weights for policy 0, policy_version 292519 (0.0009) -[2023-11-28 07:52:21,995][87424] Updated weights for policy 0, policy_version 292529 (0.0011) -[2023-11-28 07:52:22,374][87424] Updated weights for policy 0, policy_version 292539 (0.0011) -[2023-11-28 07:52:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149725184. Throughput: 0: 2669.7, 1: 2682.9. Samples: 149744140. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:23,445][86177] Avg episode reward: [(0, '-523.760'), (1, '-625.870')] -[2023-11-28 07:52:23,466][87426] Updated weights for policy 1, policy_version 292330 (0.0012) -[2023-11-28 07:52:23,843][87426] Updated weights for policy 1, policy_version 292340 (0.0012) -[2023-11-28 07:52:24,238][87426] Updated weights for policy 1, policy_version 292350 (0.0011) -[2023-11-28 07:52:24,416][87424] Updated weights for policy 0, policy_version 292549 (0.0012) -[2023-11-28 07:52:24,789][87424] Updated weights for policy 0, policy_version 292559 (0.0012) -[2023-11-28 07:52:25,176][87424] Updated weights for policy 0, policy_version 292569 (0.0012) -[2023-11-28 07:52:26,340][87426] Updated weights for policy 1, policy_version 292360 (0.0012) -[2023-11-28 07:52:26,713][87426] Updated weights for policy 1, policy_version 292370 (0.0012) -[2023-11-28 07:52:27,085][87426] Updated weights for policy 1, policy_version 292380 (0.0011) -[2023-11-28 07:52:27,183][87424] Updated weights for policy 0, policy_version 292579 (0.0011) -[2023-11-28 07:52:27,573][87424] Updated weights for policy 0, policy_version 292589 (0.0012) -[2023-11-28 07:52:27,948][87424] Updated weights for policy 0, policy_version 292599 (0.0012) -[2023-11-28 07:52:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149757952. Throughput: 0: 2689.4, 1: 2668.4. Samples: 149769364. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:28,445][86177] Avg episode reward: [(0, '-540.080'), (1, '-585.150')] -[2023-11-28 07:52:28,984][87426] Updated weights for policy 1, policy_version 292390 (0.0011) -[2023-11-28 07:52:29,356][87426] Updated weights for policy 1, policy_version 292400 (0.0010) -[2023-11-28 07:52:29,670][87424] Updated weights for policy 0, policy_version 292609 (0.0011) -[2023-11-28 07:52:29,742][87426] Updated weights for policy 1, policy_version 292410 (0.0008) -[2023-11-28 07:52:30,044][87424] Updated weights for policy 0, policy_version 292619 (0.0012) -[2023-11-28 07:52:30,438][87424] Updated weights for policy 0, policy_version 292629 (0.0012) -[2023-11-28 07:52:30,812][87424] Updated weights for policy 0, policy_version 292639 (0.0009) -[2023-11-28 07:52:31,781][87426] Updated weights for policy 1, policy_version 292420 (0.0011) -[2023-11-28 07:52:32,166][87426] Updated weights for policy 1, policy_version 292430 (0.0011) -[2023-11-28 07:52:32,541][87426] Updated weights for policy 1, policy_version 292440 (0.0009) -[2023-11-28 07:52:32,838][87424] Updated weights for policy 0, policy_version 292649 (0.0011) -[2023-11-28 07:52:33,230][87424] Updated weights for policy 0, policy_version 292659 (0.0011) -[2023-11-28 07:52:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 149782528. Throughput: 0: 2714.4, 1: 2700.6. Samples: 149795488. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:33,445][86177] Avg episode reward: [(0, '-532.670'), (1, '-574.090')] -[2023-11-28 07:52:33,612][87424] Updated weights for policy 0, policy_version 292669 (0.0011) -[2023-11-28 07:52:34,611][87426] Updated weights for policy 1, policy_version 292450 (0.0011) -[2023-11-28 07:52:34,991][87426] Updated weights for policy 1, policy_version 292460 (0.0010) -[2023-11-28 07:52:35,379][87426] Updated weights for policy 1, policy_version 292470 (0.0007) -[2023-11-28 07:52:35,751][87426] Updated weights for policy 1, policy_version 292480 (0.0008) -[2023-11-28 07:52:35,863][87424] Updated weights for policy 0, policy_version 292679 (0.0011) -[2023-11-28 07:52:36,245][87424] Updated weights for policy 0, policy_version 292689 (0.0011) -[2023-11-28 07:52:36,623][87424] Updated weights for policy 0, policy_version 292699 (0.0009) -[2023-11-28 07:52:38,249][87426] Updated weights for policy 1, policy_version 292490 (0.0011) -[2023-11-28 07:52:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 149807104. Throughput: 0: 2713.4, 1: 2713.0. Samples: 149828776. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:38,445][86177] Avg episode reward: [(0, '-532.840'), (1, '-598.400')] -[2023-11-28 07:52:38,548][87424] Updated weights for policy 0, policy_version 292709 (0.0008) -[2023-11-28 07:52:38,634][87426] Updated weights for policy 1, policy_version 292500 (0.0012) -[2023-11-28 07:52:38,941][87424] Updated weights for policy 0, policy_version 292719 (0.0009) -[2023-11-28 07:52:39,010][87426] Updated weights for policy 1, policy_version 292510 (0.0012) -[2023-11-28 07:52:39,328][87424] Updated weights for policy 0, policy_version 292729 (0.0011) -[2023-11-28 07:52:41,496][87426] Updated weights for policy 1, policy_version 292520 (0.0010) -[2023-11-28 07:52:41,572][87424] Updated weights for policy 0, policy_version 292739 (0.0012) -[2023-11-28 07:52:41,875][87426] Updated weights for policy 1, policy_version 292530 (0.0011) -[2023-11-28 07:52:41,961][87424] Updated weights for policy 0, policy_version 292749 (0.0011) -[2023-11-28 07:52:42,265][87426] Updated weights for policy 1, policy_version 292540 (0.0011) -[2023-11-28 07:52:42,339][87424] Updated weights for policy 0, policy_version 292759 (0.0012) -[2023-11-28 07:52:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 149839872. Throughput: 0: 2730.0, 1: 2687.5. Samples: 149852712. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:43,445][86177] Avg episode reward: [(0, '-540.650'), (1, '-561.080')] -[2023-11-28 07:52:44,145][87426] Updated weights for policy 1, policy_version 292550 (0.0008) -[2023-11-28 07:52:44,442][87424] Updated weights for policy 0, policy_version 292769 (0.0011) -[2023-11-28 07:52:44,530][87426] Updated weights for policy 1, policy_version 292560 (0.0007) -[2023-11-28 07:52:44,828][87424] Updated weights for policy 0, policy_version 292779 (0.0008) -[2023-11-28 07:52:44,903][87426] Updated weights for policy 1, policy_version 292570 (0.0007) -[2023-11-28 07:52:45,202][87424] Updated weights for policy 0, policy_version 292789 (0.0008) -[2023-11-28 07:52:45,583][87424] Updated weights for policy 0, policy_version 292799 (0.0009) -[2023-11-28 07:52:46,796][87426] Updated weights for policy 1, policy_version 292580 (0.0011) -[2023-11-28 07:52:47,179][87426] Updated weights for policy 1, policy_version 292590 (0.0011) -[2023-11-28 07:52:47,561][87426] Updated weights for policy 1, policy_version 292600 (0.0012) -[2023-11-28 07:52:47,794][87424] Updated weights for policy 0, policy_version 292809 (0.0008) -[2023-11-28 07:52:48,187][87424] Updated weights for policy 0, policy_version 292819 (0.0008) -[2023-11-28 07:52:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 149864448. Throughput: 0: 2730.7, 1: 2693.4. Samples: 149877404. Policy #0 lag: (min: 15.0, avg: 23.1, max: 47.0) -[2023-11-28 07:52:48,445][86177] Avg episode reward: [(0, '-526.020'), (1, '-543.200')] -[2023-11-28 07:52:48,565][87424] Updated weights for policy 0, policy_version 292829 (0.0008) -[2023-11-28 07:52:49,783][87426] Updated weights for policy 1, policy_version 292610 (0.0011) -[2023-11-28 07:52:50,153][87426] Updated weights for policy 1, policy_version 292620 (0.0010) -[2023-11-28 07:52:50,543][87426] Updated weights for policy 1, policy_version 292630 (0.0010) -[2023-11-28 07:52:50,915][87426] Updated weights for policy 1, policy_version 292640 (0.0009) -[2023-11-28 07:52:50,974][87424] Updated weights for policy 0, policy_version 292839 (0.0011) -[2023-11-28 07:52:51,354][87424] Updated weights for policy 0, policy_version 292849 (0.0012) -[2023-11-28 07:52:51,742][87424] Updated weights for policy 0, policy_version 292859 (0.0012) -[2023-11-28 07:52:52,967][87426] Updated weights for policy 1, policy_version 292650 (0.0012) -[2023-11-28 07:52:53,344][87426] Updated weights for policy 1, policy_version 292660 (0.0012) -[2023-11-28 07:52:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 149889024. Throughput: 0: 2746.0, 1: 2717.2. Samples: 149910920. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:52:53,445][86177] Avg episode reward: [(0, '-526.280'), (1, '-541.070')] -[2023-11-28 07:52:53,726][87426] Updated weights for policy 1, policy_version 292670 (0.0010) -[2023-11-28 07:52:53,922][87424] Updated weights for policy 0, policy_version 292869 (0.0012) -[2023-11-28 07:52:54,311][87424] Updated weights for policy 0, policy_version 292879 (0.0012) -[2023-11-28 07:52:54,698][87424] Updated weights for policy 0, policy_version 292889 (0.0012) -[2023-11-28 07:52:55,593][87426] Updated weights for policy 1, policy_version 292680 (0.0009) -[2023-11-28 07:52:55,986][87426] Updated weights for policy 1, policy_version 292690 (0.0007) -[2023-11-28 07:52:56,382][87426] Updated weights for policy 1, policy_version 292700 (0.0012) -[2023-11-28 07:52:56,890][87424] Updated weights for policy 0, policy_version 292899 (0.0011) -[2023-11-28 07:52:57,267][87424] Updated weights for policy 0, policy_version 292909 (0.0007) -[2023-11-28 07:52:57,657][87424] Updated weights for policy 0, policy_version 292919 (0.0007) -[2023-11-28 07:52:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 149921792. Throughput: 0: 2739.8, 1: 2728.4. Samples: 149935072. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:52:58,445][86177] Avg episode reward: [(0, '-529.130'), (1, '-581.890')] -[2023-11-28 07:52:58,461][87426] Updated weights for policy 1, policy_version 292710 (0.0009) -[2023-11-28 07:52:58,842][87426] Updated weights for policy 1, policy_version 292720 (0.0008) -[2023-11-28 07:52:59,220][87426] Updated weights for policy 1, policy_version 292730 (0.0008) -[2023-11-28 07:53:00,174][87424] Updated weights for policy 0, policy_version 292929 (0.0008) -[2023-11-28 07:53:00,566][87424] Updated weights for policy 0, policy_version 292939 (0.0012) -[2023-11-28 07:53:00,944][87424] Updated weights for policy 0, policy_version 292949 (0.0012) -[2023-11-28 07:53:01,310][87424] Updated weights for policy 0, policy_version 292959 (0.0011) -[2023-11-28 07:53:01,426][87426] Updated weights for policy 1, policy_version 292740 (0.0009) -[2023-11-28 07:53:01,813][87426] Updated weights for policy 1, policy_version 292750 (0.0013) -[2023-11-28 07:53:02,177][87426] Updated weights for policy 1, policy_version 292760 (0.0012) -[2023-11-28 07:53:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 149946368. Throughput: 0: 2713.3, 1: 2733.2. Samples: 149959012. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:03,445][86177] Avg episode reward: [(0, '-514.890'), (1, '-605.340')] -[2023-11-28 07:53:03,447][87424] Updated weights for policy 0, policy_version 292969 (0.0012) -[2023-11-28 07:53:03,836][87424] Updated weights for policy 0, policy_version 292979 (0.0011) -[2023-11-28 07:53:04,132][87426] Updated weights for policy 1, policy_version 292770 (0.0009) -[2023-11-28 07:53:04,221][87424] Updated weights for policy 0, policy_version 292989 (0.0007) -[2023-11-28 07:53:04,518][87426] Updated weights for policy 1, policy_version 292780 (0.0007) -[2023-11-28 07:53:04,897][87426] Updated weights for policy 1, policy_version 292790 (0.0008) -[2023-11-28 07:53:05,274][87426] Updated weights for policy 1, policy_version 292800 (0.0007) -[2023-11-28 07:53:06,682][87424] Updated weights for policy 0, policy_version 292999 (0.0009) -[2023-11-28 07:53:07,066][87424] Updated weights for policy 0, policy_version 293009 (0.0012) -[2023-11-28 07:53:07,432][87426] Updated weights for policy 1, policy_version 292810 (0.0012) -[2023-11-28 07:53:07,444][87424] Updated weights for policy 0, policy_version 293019 (0.0011) -[2023-11-28 07:53:07,803][87426] Updated weights for policy 1, policy_version 292820 (0.0010) -[2023-11-28 07:53:08,188][87426] Updated weights for policy 1, policy_version 292830 (0.0012) -[2023-11-28 07:53:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 149979136. Throughput: 0: 2728.7, 1: 2773.1. Samples: 149991720. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:08,445][86177] Avg episode reward: [(0, '-514.640'), (1, '-654.690')] -[2023-11-28 07:53:09,136][87424] Updated weights for policy 0, policy_version 293029 (0.0011) -[2023-11-28 07:53:09,513][87424] Updated weights for policy 0, policy_version 293039 (0.0012) -[2023-11-28 07:53:09,912][87424] Updated weights for policy 0, policy_version 293049 (0.0011) -[2023-11-28 07:53:10,146][87426] Updated weights for policy 1, policy_version 292840 (0.0010) -[2023-11-28 07:53:10,536][87426] Updated weights for policy 1, policy_version 292850 (0.0008) -[2023-11-28 07:53:10,917][87426] Updated weights for policy 1, policy_version 292860 (0.0011) -[2023-11-28 07:53:12,250][87424] Updated weights for policy 0, policy_version 293059 (0.0010) -[2023-11-28 07:53:12,636][87424] Updated weights for policy 0, policy_version 293069 (0.0012) -[2023-11-28 07:53:13,008][87424] Updated weights for policy 0, policy_version 293079 (0.0011) -[2023-11-28 07:53:13,145][87426] Updated weights for policy 1, policy_version 292870 (0.0009) -[2023-11-28 07:53:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 150003712. Throughput: 0: 2717.5, 1: 2775.4. Samples: 150016544. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:13,445][86177] Avg episode reward: [(0, '-508.900'), (1, '-693.220')] -[2023-11-28 07:53:13,527][87426] Updated weights for policy 1, policy_version 292880 (0.0010) -[2023-11-28 07:53:13,912][87426] Updated weights for policy 1, policy_version 292890 (0.0011) -[2023-11-28 07:53:14,810][87424] Updated weights for policy 0, policy_version 293089 (0.0011) -[2023-11-28 07:53:15,197][87424] Updated weights for policy 0, policy_version 293099 (0.0012) -[2023-11-28 07:53:15,587][87424] Updated weights for policy 0, policy_version 293109 (0.0012) -[2023-11-28 07:53:15,958][87424] Updated weights for policy 0, policy_version 293119 (0.0011) -[2023-11-28 07:53:15,969][87426] Updated weights for policy 1, policy_version 292900 (0.0012) -[2023-11-28 07:53:16,341][87426] Updated weights for policy 1, policy_version 292910 (0.0011) -[2023-11-28 07:53:16,715][87426] Updated weights for policy 1, policy_version 292920 (0.0012) -[2023-11-28 07:53:17,794][87424] Updated weights for policy 0, policy_version 293129 (0.0012) -[2023-11-28 07:53:18,179][87424] Updated weights for policy 0, policy_version 293139 (0.0012) -[2023-11-28 07:53:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 150028288. Throughput: 0: 2715.3, 1: 2761.0. Samples: 150041920. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:18,445][86177] Avg episode reward: [(0, '-505.690'), (1, '-753.030')] -[2023-11-28 07:53:18,563][87424] Updated weights for policy 0, policy_version 293149 (0.0012) -[2023-11-28 07:53:18,705][87426] Updated weights for policy 1, policy_version 292930 (0.0012) -[2023-11-28 07:53:19,075][87426] Updated weights for policy 1, policy_version 292940 (0.0012) -[2023-11-28 07:53:19,461][87426] Updated weights for policy 1, policy_version 292950 (0.0012) -[2023-11-28 07:53:19,833][87426] Updated weights for policy 1, policy_version 292960 (0.0011) -[2023-11-28 07:53:21,020][87424] Updated weights for policy 0, policy_version 293159 (0.0011) -[2023-11-28 07:53:21,412][87424] Updated weights for policy 0, policy_version 293169 (0.0011) -[2023-11-28 07:53:21,787][87424] Updated weights for policy 0, policy_version 293179 (0.0012) -[2023-11-28 07:53:22,297][87426] Updated weights for policy 1, policy_version 292970 (0.0009) -[2023-11-28 07:53:22,674][87426] Updated weights for policy 1, policy_version 292980 (0.0008) -[2023-11-28 07:53:23,053][87426] Updated weights for policy 1, policy_version 292990 (0.0008) -[2023-11-28 07:53:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 150061056. Throughput: 0: 2692.2, 1: 2758.3. Samples: 150074048. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:23,445][86177] Avg episode reward: [(0, '-520.220'), (1, '-771.070')] -[2023-11-28 07:53:24,454][87424] Updated weights for policy 0, policy_version 293189 (0.0012) -[2023-11-28 07:53:24,836][87424] Updated weights for policy 0, policy_version 293199 (0.0011) -[2023-11-28 07:53:24,878][87426] Updated weights for policy 1, policy_version 293000 (0.0012) -[2023-11-28 07:53:25,225][87424] Updated weights for policy 0, policy_version 293209 (0.0009) -[2023-11-28 07:53:25,255][87426] Updated weights for policy 1, policy_version 293010 (0.0012) -[2023-11-28 07:53:25,633][87426] Updated weights for policy 1, policy_version 293020 (0.0012) -[2023-11-28 07:53:27,758][87426] Updated weights for policy 1, policy_version 293030 (0.0012) -[2023-11-28 07:53:27,771][87424] Updated weights for policy 0, policy_version 293219 (0.0008) -[2023-11-28 07:53:28,139][87426] Updated weights for policy 1, policy_version 293040 (0.0011) -[2023-11-28 07:53:28,151][87424] Updated weights for policy 0, policy_version 293229 (0.0008) -[2023-11-28 07:53:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 150077440. Throughput: 0: 2691.8, 1: 2798.8. Samples: 150099788. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:28,445][86177] Avg episode reward: [(0, '-557.180'), (1, '-833.010')] -[2023-11-28 07:53:28,521][87426] Updated weights for policy 1, policy_version 293050 (0.0008) -[2023-11-28 07:53:28,535][87424] Updated weights for policy 0, policy_version 293239 (0.0009) -[2023-11-28 07:53:30,510][87426] Updated weights for policy 1, policy_version 293060 (0.0009) -[2023-11-28 07:53:30,605][87424] Updated weights for policy 0, policy_version 293249 (0.0012) -[2023-11-28 07:53:30,888][87426] Updated weights for policy 1, policy_version 293070 (0.0011) -[2023-11-28 07:53:30,992][87424] Updated weights for policy 0, policy_version 293259 (0.0011) -[2023-11-28 07:53:31,259][87426] Updated weights for policy 1, policy_version 293080 (0.0011) -[2023-11-28 07:53:31,374][87424] Updated weights for policy 0, policy_version 293269 (0.0010) -[2023-11-28 07:53:31,754][87424] Updated weights for policy 0, policy_version 293279 (0.0010) -[2023-11-28 07:53:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 150110208. Throughput: 0: 2691.4, 1: 2782.8. Samples: 150123744. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:33,446][86177] Avg episode reward: [(0, '-564.820'), (1, '-833.490')] -[2023-11-28 07:53:33,682][87426] Updated weights for policy 1, policy_version 293090 (0.0010) -[2023-11-28 07:53:33,688][87424] Updated weights for policy 0, policy_version 293289 (0.0008) -[2023-11-28 07:53:34,063][87426] Updated weights for policy 1, policy_version 293100 (0.0008) -[2023-11-28 07:53:34,072][87424] Updated weights for policy 0, policy_version 293299 (0.0008) -[2023-11-28 07:53:34,446][87426] Updated weights for policy 1, policy_version 293110 (0.0007) -[2023-11-28 07:53:34,453][87424] Updated weights for policy 0, policy_version 293309 (0.0010) -[2023-11-28 07:53:34,823][87426] Updated weights for policy 1, policy_version 293120 (0.0011) -[2023-11-28 07:53:36,749][87424] Updated weights for policy 0, policy_version 293319 (0.0010) -[2023-11-28 07:53:36,802][87426] Updated weights for policy 1, policy_version 293130 (0.0011) -[2023-11-28 07:53:37,133][87424] Updated weights for policy 0, policy_version 293329 (0.0011) -[2023-11-28 07:53:37,182][87426] Updated weights for policy 1, policy_version 293140 (0.0012) -[2023-11-28 07:53:37,525][87424] Updated weights for policy 0, policy_version 293339 (0.0011) -[2023-11-28 07:53:37,564][87426] Updated weights for policy 1, policy_version 293150 (0.0010) -[2023-11-28 07:53:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 150142976. Throughput: 0: 2683.4, 1: 2763.3. Samples: 150156020. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:38,446][86177] Avg episode reward: [(0, '-570.880'), (1, '-920.870')] -[2023-11-28 07:53:39,398][87426] Updated weights for policy 1, policy_version 293160 (0.0007) -[2023-11-28 07:53:39,774][87426] Updated weights for policy 1, policy_version 293170 (0.0012) -[2023-11-28 07:53:39,962][87424] Updated weights for policy 0, policy_version 293349 (0.0008) -[2023-11-28 07:53:40,152][87426] Updated weights for policy 1, policy_version 293180 (0.0011) -[2023-11-28 07:53:40,344][87424] Updated weights for policy 0, policy_version 293359 (0.0010) -[2023-11-28 07:53:40,721][87424] Updated weights for policy 0, policy_version 293369 (0.0008) -[2023-11-28 07:53:42,211][87426] Updated weights for policy 1, policy_version 293190 (0.0011) -[2023-11-28 07:53:42,588][87426] Updated weights for policy 1, policy_version 293200 (0.0012) -[2023-11-28 07:53:42,921][87424] Updated weights for policy 0, policy_version 293379 (0.0008) -[2023-11-28 07:53:42,969][87426] Updated weights for policy 1, policy_version 293210 (0.0011) -[2023-11-28 07:53:43,311][87424] Updated weights for policy 0, policy_version 293389 (0.0009) -[2023-11-28 07:53:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 150167552. Throughput: 0: 2675.0, 1: 2774.7. Samples: 150180308. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:43,445][86177] Avg episode reward: [(0, '-557.790'), (1, '-960.560')] -[2023-11-28 07:53:43,708][87424] Updated weights for policy 0, policy_version 293399 (0.0008) -[2023-11-28 07:53:45,536][87426] Updated weights for policy 1, policy_version 293220 (0.0011) -[2023-11-28 07:53:45,908][87426] Updated weights for policy 1, policy_version 293230 (0.0011) -[2023-11-28 07:53:46,049][87424] Updated weights for policy 0, policy_version 293409 (0.0008) -[2023-11-28 07:53:46,280][87426] Updated weights for policy 1, policy_version 293240 (0.0011) -[2023-11-28 07:53:46,429][87424] Updated weights for policy 0, policy_version 293419 (0.0010) -[2023-11-28 07:53:46,814][87424] Updated weights for policy 0, policy_version 293429 (0.0011) -[2023-11-28 07:53:47,198][87424] Updated weights for policy 0, policy_version 293439 (0.0011) -[2023-11-28 07:53:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 150192128. Throughput: 0: 2678.8, 1: 2770.9. Samples: 150204252. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:48,446][86177] Avg episode reward: [(0, '-522.590'), (1, '-968.240')] -[2023-11-28 07:53:48,501][87426] Updated weights for policy 1, policy_version 293250 (0.0010) -[2023-11-28 07:53:48,874][87426] Updated weights for policy 1, policy_version 293260 (0.0011) -[2023-11-28 07:53:48,982][87424] Updated weights for policy 0, policy_version 293449 (0.0010) -[2023-11-28 07:53:49,262][87426] Updated weights for policy 1, policy_version 293270 (0.0011) -[2023-11-28 07:53:49,364][87424] Updated weights for policy 0, policy_version 293459 (0.0012) -[2023-11-28 07:53:49,643][87426] Updated weights for policy 1, policy_version 293280 (0.0008) -[2023-11-28 07:53:49,746][87424] Updated weights for policy 0, policy_version 293469 (0.0008) -[2023-11-28 07:53:51,905][87426] Updated weights for policy 1, policy_version 293290 (0.0012) -[2023-11-28 07:53:51,966][87424] Updated weights for policy 0, policy_version 293479 (0.0011) -[2023-11-28 07:53:52,285][87426] Updated weights for policy 1, policy_version 293300 (0.0011) -[2023-11-28 07:53:52,349][87424] Updated weights for policy 0, policy_version 293489 (0.0010) -[2023-11-28 07:53:52,661][87426] Updated weights for policy 1, policy_version 293310 (0.0010) -[2023-11-28 07:53:52,725][87424] Updated weights for policy 0, policy_version 293499 (0.0010) -[2023-11-28 07:53:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 150224896. Throughput: 0: 2695.3, 1: 2765.8. Samples: 150237468. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:53,445][86177] Avg episode reward: [(0, '-535.920'), (1, '-975.420')] -[2023-11-28 07:53:54,690][87426] Updated weights for policy 1, policy_version 293320 (0.0008) -[2023-11-28 07:53:54,979][87424] Updated weights for policy 0, policy_version 293509 (0.0010) -[2023-11-28 07:53:55,070][87426] Updated weights for policy 1, policy_version 293330 (0.0007) -[2023-11-28 07:53:55,372][87424] Updated weights for policy 0, policy_version 293519 (0.0010) -[2023-11-28 07:53:55,449][87426] Updated weights for policy 1, policy_version 293340 (0.0009) -[2023-11-28 07:53:55,757][87424] Updated weights for policy 0, policy_version 293529 (0.0011) -[2023-11-28 07:53:57,111][87426] Updated weights for policy 1, policy_version 293350 (0.0011) -[2023-11-28 07:53:57,490][87426] Updated weights for policy 1, policy_version 293360 (0.0011) -[2023-11-28 07:53:57,872][87426] Updated weights for policy 1, policy_version 293370 (0.0007) -[2023-11-28 07:53:58,272][87424] Updated weights for policy 0, policy_version 293539 (0.0012) -[2023-11-28 07:53:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 150249472. Throughput: 0: 2691.4, 1: 2785.2. Samples: 150262992. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:53:58,445][86177] Avg episode reward: [(0, '-533.530'), (1, '-1050.730')] -[2023-11-28 07:53:58,656][87424] Updated weights for policy 0, policy_version 293549 (0.0012) -[2023-11-28 07:53:59,042][87424] Updated weights for policy 0, policy_version 293559 (0.0008) -[2023-11-28 07:54:00,051][87426] Updated weights for policy 1, policy_version 293380 (0.0007) -[2023-11-28 07:54:00,427][87426] Updated weights for policy 1, policy_version 293390 (0.0009) -[2023-11-28 07:54:00,807][87426] Updated weights for policy 1, policy_version 293400 (0.0008) -[2023-11-28 07:54:01,222][87424] Updated weights for policy 0, policy_version 293569 (0.0010) -[2023-11-28 07:54:01,612][87424] Updated weights for policy 0, policy_version 293579 (0.0012) -[2023-11-28 07:54:02,003][87424] Updated weights for policy 0, policy_version 293589 (0.0009) -[2023-11-28 07:54:02,391][87424] Updated weights for policy 0, policy_version 293599 (0.0012) -[2023-11-28 07:54:03,010][87426] Updated weights for policy 1, policy_version 293410 (0.0008) -[2023-11-28 07:54:03,396][87426] Updated weights for policy 1, policy_version 293420 (0.0011) -[2023-11-28 07:54:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 150274048. Throughput: 0: 2662.4, 1: 2797.2. Samples: 150287600. Policy #0 lag: (min: 31.0, avg: 42.6, max: 63.0) -[2023-11-28 07:54:03,445][86177] Avg episode reward: [(0, '-531.720'), (1, '-1043.190')] -[2023-11-28 07:54:03,775][87426] Updated weights for policy 1, policy_version 293430 (0.0012) -[2023-11-28 07:54:04,152][87426] Updated weights for policy 1, policy_version 293440 (0.0012) -[2023-11-28 07:54:04,471][87424] Updated weights for policy 0, policy_version 293609 (0.0011) -[2023-11-28 07:54:04,858][87424] Updated weights for policy 0, policy_version 293619 (0.0012) -[2023-11-28 07:54:05,242][87424] Updated weights for policy 0, policy_version 293629 (0.0012) -[2023-11-28 07:54:06,428][87426] Updated weights for policy 1, policy_version 293450 (0.0012) -[2023-11-28 07:54:06,813][87426] Updated weights for policy 1, policy_version 293460 (0.0011) -[2023-11-28 07:54:07,178][87426] Updated weights for policy 1, policy_version 293470 (0.0010) -[2023-11-28 07:54:07,565][87424] Updated weights for policy 0, policy_version 293639 (0.0012) -[2023-11-28 07:54:07,950][87424] Updated weights for policy 0, policy_version 293649 (0.0012) -[2023-11-28 07:54:08,332][87424] Updated weights for policy 0, policy_version 293659 (0.0012) -[2023-11-28 07:54:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 150298624. Throughput: 0: 2679.8, 1: 2790.6. Samples: 150320216. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:08,445][86177] Avg episode reward: [(0, '-530.810'), (1, '-1104.610')] -[2023-11-28 07:54:09,661][87426] Updated weights for policy 1, policy_version 293480 (0.0007) -[2023-11-28 07:54:10,042][87426] Updated weights for policy 1, policy_version 293490 (0.0010) -[2023-11-28 07:54:10,425][87426] Updated weights for policy 1, policy_version 293500 (0.0009) -[2023-11-28 07:54:10,535][87424] Updated weights for policy 0, policy_version 293669 (0.0013) -[2023-11-28 07:54:10,908][87424] Updated weights for policy 0, policy_version 293679 (0.0012) -[2023-11-28 07:54:11,293][87424] Updated weights for policy 0, policy_version 293689 (0.0012) -[2023-11-28 07:54:12,305][87426] Updated weights for policy 1, policy_version 293510 (0.0012) -[2023-11-28 07:54:12,689][87426] Updated weights for policy 1, policy_version 293520 (0.0011) -[2023-11-28 07:54:13,067][87426] Updated weights for policy 1, policy_version 293530 (0.0011) -[2023-11-28 07:54:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 150331392. Throughput: 0: 2685.6, 1: 2759.3. Samples: 150344808. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:13,445][86177] Avg episode reward: [(0, '-505.460'), (1, '-1141.930')] -[2023-11-28 07:54:13,454][87424] Updated weights for policy 0, policy_version 293699 (0.0012) -[2023-11-28 07:54:13,836][87424] Updated weights for policy 0, policy_version 293709 (0.0007) -[2023-11-28 07:54:14,221][87424] Updated weights for policy 0, policy_version 293719 (0.0007) -[2023-11-28 07:54:15,387][87426] Updated weights for policy 1, policy_version 293540 (0.0010) -[2023-11-28 07:54:15,764][87426] Updated weights for policy 1, policy_version 293550 (0.0010) -[2023-11-28 07:54:16,148][87426] Updated weights for policy 1, policy_version 293560 (0.0008) -[2023-11-28 07:54:16,619][87424] Updated weights for policy 0, policy_version 293729 (0.0008) -[2023-11-28 07:54:16,997][87424] Updated weights for policy 0, policy_version 293739 (0.0012) -[2023-11-28 07:54:17,386][87424] Updated weights for policy 0, policy_version 293749 (0.0012) -[2023-11-28 07:54:17,764][87424] Updated weights for policy 0, policy_version 293759 (0.0012) -[2023-11-28 07:54:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 150355968. Throughput: 0: 2679.6, 1: 2765.5. Samples: 150368776. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:18,446][86177] Avg episode reward: [(0, '-504.370'), (1, '-1182.640')] -[2023-11-28 07:54:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000293568_75153408.pth... -[2023-11-28 07:54:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000293760_75202560.pth... -[2023-11-28 07:54:18,488][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000291008_74498048.pth -[2023-11-28 07:54:18,491][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000291264_74563584.pth -[2023-11-28 07:54:18,689][87426] Updated weights for policy 1, policy_version 293570 (0.0008) -[2023-11-28 07:54:19,070][87426] Updated weights for policy 1, policy_version 293580 (0.0012) -[2023-11-28 07:54:19,457][87426] Updated weights for policy 1, policy_version 293590 (0.0011) -[2023-11-28 07:54:19,655][87424] Updated weights for policy 0, policy_version 293769 (0.0011) -[2023-11-28 07:54:19,827][87426] Updated weights for policy 1, policy_version 293600 (0.0012) -[2023-11-28 07:54:20,039][87424] Updated weights for policy 0, policy_version 293779 (0.0010) -[2023-11-28 07:54:20,421][87424] Updated weights for policy 0, policy_version 293789 (0.0009) -[2023-11-28 07:54:21,910][87426] Updated weights for policy 1, policy_version 293610 (0.0012) -[2023-11-28 07:54:22,285][87426] Updated weights for policy 1, policy_version 293620 (0.0011) -[2023-11-28 07:54:22,659][87426] Updated weights for policy 1, policy_version 293630 (0.0011) -[2023-11-28 07:54:22,747][87424] Updated weights for policy 0, policy_version 293799 (0.0012) -[2023-11-28 07:54:23,126][87424] Updated weights for policy 0, policy_version 293809 (0.0010) -[2023-11-28 07:54:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 150380544. Throughput: 0: 2676.9, 1: 2740.5. Samples: 150399804. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:23,445][86177] Avg episode reward: [(0, '-501.920'), (1, '-1292.910')] -[2023-11-28 07:54:23,507][87424] Updated weights for policy 0, policy_version 293819 (0.0010) -[2023-11-28 07:54:25,026][87426] Updated weights for policy 1, policy_version 293640 (0.0011) -[2023-11-28 07:54:25,370][87424] Updated weights for policy 0, policy_version 293829 (0.0010) -[2023-11-28 07:54:25,407][87426] Updated weights for policy 1, policy_version 293650 (0.0011) -[2023-11-28 07:54:25,762][87424] Updated weights for policy 0, policy_version 293839 (0.0007) -[2023-11-28 07:54:25,780][87426] Updated weights for policy 1, policy_version 293660 (0.0008) -[2023-11-28 07:54:26,133][87424] Updated weights for policy 0, policy_version 293849 (0.0007) -[2023-11-28 07:54:27,707][87426] Updated weights for policy 1, policy_version 293670 (0.0008) -[2023-11-28 07:54:28,042][87424] Updated weights for policy 0, policy_version 293859 (0.0008) -[2023-11-28 07:54:28,082][87426] Updated weights for policy 1, policy_version 293680 (0.0011) -[2023-11-28 07:54:28,437][87424] Updated weights for policy 0, policy_version 293869 (0.0008) -[2023-11-28 07:54:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 150405120. Throughput: 0: 2706.4, 1: 2743.5. Samples: 150425552. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:28,445][86177] Avg episode reward: [(0, '-516.310'), (1, '-1409.960')] -[2023-11-28 07:54:28,462][87426] Updated weights for policy 1, policy_version 293690 (0.0009) -[2023-11-28 07:54:28,826][87424] Updated weights for policy 0, policy_version 293879 (0.0012) -[2023-11-28 07:54:30,855][87426] Updated weights for policy 1, policy_version 293700 (0.0009) -[2023-11-28 07:54:31,231][87426] Updated weights for policy 1, policy_version 293710 (0.0010) -[2023-11-28 07:54:31,288][87424] Updated weights for policy 0, policy_version 293889 (0.0012) -[2023-11-28 07:54:31,610][87426] Updated weights for policy 1, policy_version 293720 (0.0008) -[2023-11-28 07:54:31,672][87424] Updated weights for policy 0, policy_version 293899 (0.0012) -[2023-11-28 07:54:32,048][87424] Updated weights for policy 0, policy_version 293909 (0.0011) -[2023-11-28 07:54:32,429][87424] Updated weights for policy 0, policy_version 293919 (0.0010) -[2023-11-28 07:54:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 150437888. Throughput: 0: 2728.3, 1: 2732.5. Samples: 150449988. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:33,445][86177] Avg episode reward: [(0, '-517.320'), (1, '-1496.130')] -[2023-11-28 07:54:33,606][87426] Updated weights for policy 1, policy_version 293730 (0.0011) -[2023-11-28 07:54:33,989][87426] Updated weights for policy 1, policy_version 293740 (0.0012) -[2023-11-28 07:54:34,361][87426] Updated weights for policy 1, policy_version 293750 (0.0012) -[2023-11-28 07:54:34,732][87424] Updated weights for policy 0, policy_version 293929 (0.0012) -[2023-11-28 07:54:34,740][87426] Updated weights for policy 1, policy_version 293760 (0.0011) -[2023-11-28 07:54:35,107][87424] Updated weights for policy 0, policy_version 293939 (0.0011) -[2023-11-28 07:54:35,487][87424] Updated weights for policy 0, policy_version 293949 (0.0012) -[2023-11-28 07:54:37,239][87426] Updated weights for policy 1, policy_version 293770 (0.0011) -[2023-11-28 07:54:37,554][87424] Updated weights for policy 0, policy_version 293959 (0.0011) -[2023-11-28 07:54:37,622][87426] Updated weights for policy 1, policy_version 293780 (0.0011) -[2023-11-28 07:54:37,943][87424] Updated weights for policy 0, policy_version 293969 (0.0012) -[2023-11-28 07:54:37,996][87426] Updated weights for policy 1, policy_version 293790 (0.0008) -[2023-11-28 07:54:38,325][87424] Updated weights for policy 0, policy_version 293979 (0.0008) -[2023-11-28 07:54:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 150462464. Throughput: 0: 2729.3, 1: 2713.1. Samples: 150482376. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:38,445][86177] Avg episode reward: [(0, '-517.080'), (1, '-1637.450')] -[2023-11-28 07:54:40,133][87426] Updated weights for policy 1, policy_version 293800 (0.0009) -[2023-11-28 07:54:40,517][87426] Updated weights for policy 1, policy_version 293810 (0.0010) -[2023-11-28 07:54:40,736][87424] Updated weights for policy 0, policy_version 293989 (0.0008) -[2023-11-28 07:54:40,901][87426] Updated weights for policy 1, policy_version 293820 (0.0012) -[2023-11-28 07:54:41,109][87424] Updated weights for policy 0, policy_version 293999 (0.0008) -[2023-11-28 07:54:41,497][87424] Updated weights for policy 0, policy_version 294009 (0.0012) -[2023-11-28 07:54:43,119][87426] Updated weights for policy 1, policy_version 293830 (0.0010) -[2023-11-28 07:54:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 150487040. Throughput: 0: 2732.9, 1: 2696.1. Samples: 150507296. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:43,445][86177] Avg episode reward: [(0, '-519.630'), (1, '-1717.450')] -[2023-11-28 07:54:43,499][87426] Updated weights for policy 1, policy_version 293840 (0.0008) -[2023-11-28 07:54:43,878][87426] Updated weights for policy 1, policy_version 293850 (0.0008) -[2023-11-28 07:54:44,045][87424] Updated weights for policy 0, policy_version 294019 (0.0012) -[2023-11-28 07:54:44,417][87424] Updated weights for policy 0, policy_version 294029 (0.0012) -[2023-11-28 07:54:44,799][87424] Updated weights for policy 0, policy_version 294039 (0.0012) -[2023-11-28 07:54:46,326][87426] Updated weights for policy 1, policy_version 293860 (0.0010) -[2023-11-28 07:54:46,648][87424] Updated weights for policy 0, policy_version 294049 (0.0012) -[2023-11-28 07:54:46,712][87426] Updated weights for policy 1, policy_version 293870 (0.0012) -[2023-11-28 07:54:47,025][87424] Updated weights for policy 0, policy_version 294059 (0.0010) -[2023-11-28 07:54:47,082][87426] Updated weights for policy 1, policy_version 293880 (0.0012) -[2023-11-28 07:54:47,411][87424] Updated weights for policy 0, policy_version 294069 (0.0007) -[2023-11-28 07:54:47,804][87424] Updated weights for policy 0, policy_version 294079 (0.0007) -[2023-11-28 07:54:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 150519808. Throughput: 0: 2736.3, 1: 2676.9. Samples: 150531196. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:48,445][86177] Avg episode reward: [(0, '-504.820'), (1, '-1732.770')] -[2023-11-28 07:54:48,912][87426] Updated weights for policy 1, policy_version 293890 (0.0011) -[2023-11-28 07:54:49,289][87426] Updated weights for policy 1, policy_version 293900 (0.0011) -[2023-11-28 07:54:49,333][87424] Updated weights for policy 0, policy_version 294089 (0.0010) -[2023-11-28 07:54:49,664][87426] Updated weights for policy 1, policy_version 293910 (0.0011) -[2023-11-28 07:54:49,711][87424] Updated weights for policy 0, policy_version 294099 (0.0012) -[2023-11-28 07:54:50,035][87426] Updated weights for policy 1, policy_version 293920 (0.0011) -[2023-11-28 07:54:50,084][87424] Updated weights for policy 0, policy_version 294109 (0.0011) -[2023-11-28 07:54:52,342][87426] Updated weights for policy 1, policy_version 293930 (0.0011) -[2023-11-28 07:54:52,651][87424] Updated weights for policy 0, policy_version 294119 (0.0009) -[2023-11-28 07:54:52,728][87426] Updated weights for policy 1, policy_version 293940 (0.0011) -[2023-11-28 07:54:53,029][87424] Updated weights for policy 0, policy_version 294129 (0.0011) -[2023-11-28 07:54:53,091][87426] Updated weights for policy 1, policy_version 293950 (0.0012) -[2023-11-28 07:54:53,411][87424] Updated weights for policy 0, policy_version 294139 (0.0017) -[2023-11-28 07:54:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 150544384. Throughput: 0: 2721.8, 1: 2694.1. Samples: 150563928. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:53,445][86177] Avg episode reward: [(0, '-504.700'), (1, '-1837.030')] -[2023-11-28 07:54:55,361][87426] Updated weights for policy 1, policy_version 293960 (0.0008) -[2023-11-28 07:54:55,438][87424] Updated weights for policy 0, policy_version 294149 (0.0009) -[2023-11-28 07:54:55,753][87426] Updated weights for policy 1, policy_version 293970 (0.0011) -[2023-11-28 07:54:55,823][87424] Updated weights for policy 0, policy_version 294159 (0.0007) -[2023-11-28 07:54:56,140][87426] Updated weights for policy 1, policy_version 293980 (0.0011) -[2023-11-28 07:54:56,216][87424] Updated weights for policy 0, policy_version 294169 (0.0007) -[2023-11-28 07:54:58,134][87426] Updated weights for policy 1, policy_version 293990 (0.0008) -[2023-11-28 07:54:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 150568960. Throughput: 0: 2705.0, 1: 2695.6. Samples: 150587836. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:54:58,445][86177] Avg episode reward: [(0, '-506.020'), (1, '-1924.750')] -[2023-11-28 07:54:58,504][87426] Updated weights for policy 1, policy_version 294000 (0.0008) -[2023-11-28 07:54:58,556][87424] Updated weights for policy 0, policy_version 294179 (0.0009) -[2023-11-28 07:54:58,887][87426] Updated weights for policy 1, policy_version 294010 (0.0011) -[2023-11-28 07:54:58,937][87424] Updated weights for policy 0, policy_version 294189 (0.0011) -[2023-11-28 07:54:59,311][87424] Updated weights for policy 0, policy_version 294199 (0.0012) -[2023-11-28 07:55:00,719][87426] Updated weights for policy 1, policy_version 294020 (0.0008) -[2023-11-28 07:55:01,098][87426] Updated weights for policy 1, policy_version 294030 (0.0008) -[2023-11-28 07:55:01,295][87424] Updated weights for policy 0, policy_version 294209 (0.0009) -[2023-11-28 07:55:01,481][87426] Updated weights for policy 1, policy_version 294040 (0.0008) -[2023-11-28 07:55:01,674][87424] Updated weights for policy 0, policy_version 294219 (0.0012) -[2023-11-28 07:55:02,055][87424] Updated weights for policy 0, policy_version 294229 (0.0011) -[2023-11-28 07:55:02,434][87424] Updated weights for policy 0, policy_version 294239 (0.0012) -[2023-11-28 07:55:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 150601728. Throughput: 0: 2724.1, 1: 2691.4. Samples: 150612472. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:55:03,445][86177] Avg episode reward: [(0, '-505.990'), (1, '-1997.660')] -[2023-11-28 07:55:03,761][87426] Updated weights for policy 1, policy_version 294050 (0.0010) -[2023-11-28 07:55:04,141][87426] Updated weights for policy 1, policy_version 294060 (0.0010) -[2023-11-28 07:55:04,520][87426] Updated weights for policy 1, policy_version 294070 (0.0009) -[2023-11-28 07:55:04,704][87424] Updated weights for policy 0, policy_version 294249 (0.0011) -[2023-11-28 07:55:04,899][87426] Updated weights for policy 1, policy_version 294080 (0.0012) -[2023-11-28 07:55:05,092][87424] Updated weights for policy 0, policy_version 294259 (0.0012) -[2023-11-28 07:55:05,468][87424] Updated weights for policy 0, policy_version 294269 (0.0012) -[2023-11-28 07:55:07,085][87426] Updated weights for policy 1, policy_version 294090 (0.0012) -[2023-11-28 07:55:07,207][87424] Updated weights for policy 0, policy_version 294279 (0.0009) -[2023-11-28 07:55:07,460][87426] Updated weights for policy 1, policy_version 294100 (0.0010) -[2023-11-28 07:55:07,591][87424] Updated weights for policy 0, policy_version 294289 (0.0009) -[2023-11-28 07:55:07,841][87426] Updated weights for policy 1, policy_version 294110 (0.0011) -[2023-11-28 07:55:07,978][87424] Updated weights for policy 0, policy_version 294299 (0.0007) -[2023-11-28 07:55:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 150634496. Throughput: 0: 2741.3, 1: 2748.1. Samples: 150646828. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:55:08,445][86177] Avg episode reward: [(0, '-505.050'), (1, '-2131.980')] -[2023-11-28 07:55:10,271][87424] Updated weights for policy 0, policy_version 294309 (0.0010) -[2023-11-28 07:55:10,384][87426] Updated weights for policy 1, policy_version 294120 (0.0011) -[2023-11-28 07:55:10,652][87424] Updated weights for policy 0, policy_version 294319 (0.0011) -[2023-11-28 07:55:10,762][87426] Updated weights for policy 1, policy_version 294130 (0.0011) -[2023-11-28 07:55:11,039][87424] Updated weights for policy 0, policy_version 294329 (0.0010) -[2023-11-28 07:55:11,143][87426] Updated weights for policy 1, policy_version 294140 (0.0011) -[2023-11-28 07:55:13,232][87424] Updated weights for policy 0, policy_version 294339 (0.0011) -[2023-11-28 07:55:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 150650880. Throughput: 0: 2734.0, 1: 2710.7. Samples: 150670564. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:55:13,445][86177] Avg episode reward: [(0, '-510.780'), (1, '-2098.480')] -[2023-11-28 07:55:13,473][87426] Updated weights for policy 1, policy_version 294150 (0.0012) -[2023-11-28 07:55:13,608][87424] Updated weights for policy 0, policy_version 294349 (0.0008) -[2023-11-28 07:55:13,853][87426] Updated weights for policy 1, policy_version 294160 (0.0011) -[2023-11-28 07:55:13,981][87424] Updated weights for policy 0, policy_version 294359 (0.0008) -[2023-11-28 07:55:14,233][87426] Updated weights for policy 1, policy_version 294170 (0.0008) -[2023-11-28 07:55:15,693][87424] Updated weights for policy 0, policy_version 294369 (0.0010) -[2023-11-28 07:55:16,078][87424] Updated weights for policy 0, policy_version 294379 (0.0012) -[2023-11-28 07:55:16,453][87426] Updated weights for policy 1, policy_version 294180 (0.0010) -[2023-11-28 07:55:16,470][87424] Updated weights for policy 0, policy_version 294389 (0.0010) -[2023-11-28 07:55:16,824][87426] Updated weights for policy 1, policy_version 294190 (0.0011) -[2023-11-28 07:55:16,853][87424] Updated weights for policy 0, policy_version 294399 (0.0012) -[2023-11-28 07:55:17,208][87426] Updated weights for policy 1, policy_version 294200 (0.0007) -[2023-11-28 07:55:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 150683648. Throughput: 0: 2729.3, 1: 2712.4. Samples: 150694868. Policy #0 lag: (min: 12.0, avg: 29.1, max: 44.0) -[2023-11-28 07:55:18,445][86177] Avg episode reward: [(0, '-510.640'), (1, '-2073.610')] -[2023-11-28 07:55:18,634][87424] Updated weights for policy 0, policy_version 294409 (0.0008) -[2023-11-28 07:55:19,018][87424] Updated weights for policy 0, policy_version 294419 (0.0008) -[2023-11-28 07:55:19,405][87424] Updated weights for policy 0, policy_version 294429 (0.0009) -[2023-11-28 07:55:19,707][87426] Updated weights for policy 1, policy_version 294210 (0.0009) -[2023-11-28 07:55:20,070][87426] Updated weights for policy 1, policy_version 294220 (0.0011) -[2023-11-28 07:55:20,453][87426] Updated weights for policy 1, policy_version 294230 (0.0012) -[2023-11-28 07:55:20,817][87426] Updated weights for policy 1, policy_version 294240 (0.0012) -[2023-11-28 07:55:21,837][87424] Updated weights for policy 0, policy_version 294439 (0.0012) -[2023-11-28 07:55:22,217][87424] Updated weights for policy 0, policy_version 294449 (0.0012) -[2023-11-28 07:55:22,595][87424] Updated weights for policy 0, policy_version 294459 (0.0010) -[2023-11-28 07:55:22,776][87426] Updated weights for policy 1, policy_version 294250 (0.0008) -[2023-11-28 07:55:23,157][87426] Updated weights for policy 1, policy_version 294260 (0.0009) -[2023-11-28 07:55:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 150708224. Throughput: 0: 2722.6, 1: 2697.7. Samples: 150726288. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:55:23,445][86177] Avg episode reward: [(0, '-519.740'), (1, '-2095.950')] -[2023-11-28 07:55:23,541][87426] Updated weights for policy 1, policy_version 294270 (0.0009) -[2023-11-28 07:55:24,702][87424] Updated weights for policy 0, policy_version 294469 (0.0012) -[2023-11-28 07:55:25,077][87424] Updated weights for policy 0, policy_version 294479 (0.0012) -[2023-11-28 07:55:25,449][87424] Updated weights for policy 0, policy_version 294489 (0.0011) -[2023-11-28 07:55:25,779][87426] Updated weights for policy 1, policy_version 294280 (0.0008) -[2023-11-28 07:55:26,158][87426] Updated weights for policy 1, policy_version 294290 (0.0007) -[2023-11-28 07:55:26,539][87426] Updated weights for policy 1, policy_version 294300 (0.0008) -[2023-11-28 07:55:27,668][87424] Updated weights for policy 0, policy_version 294499 (0.0012) -[2023-11-28 07:55:28,046][87424] Updated weights for policy 0, policy_version 294509 (0.0011) -[2023-11-28 07:55:28,166][87426] Updated weights for policy 1, policy_version 294310 (0.0009) -[2023-11-28 07:55:28,415][87424] Updated weights for policy 0, policy_version 294519 (0.0011) -[2023-11-28 07:55:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 150732800. Throughput: 0: 2726.0, 1: 2746.2. Samples: 150753544. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:55:28,445][86177] Avg episode reward: [(0, '-522.000'), (1, '-2122.710')] -[2023-11-28 07:55:28,537][87426] Updated weights for policy 1, policy_version 294320 (0.0008) -[2023-11-28 07:55:28,926][87426] Updated weights for policy 1, policy_version 294330 (0.0008) -[2023-11-28 07:55:30,451][87424] Updated weights for policy 0, policy_version 294529 (0.0011) -[2023-11-28 07:55:30,827][87424] Updated weights for policy 0, policy_version 294539 (0.0012) -[2023-11-28 07:55:31,075][87426] Updated weights for policy 1, policy_version 294340 (0.0009) -[2023-11-28 07:55:31,211][87424] Updated weights for policy 0, policy_version 294549 (0.0011) -[2023-11-28 07:55:31,453][87426] Updated weights for policy 1, policy_version 294350 (0.0008) -[2023-11-28 07:55:31,597][87424] Updated weights for policy 0, policy_version 294559 (0.0011) -[2023-11-28 07:55:31,833][87426] Updated weights for policy 1, policy_version 294360 (0.0008) -[2023-11-28 07:55:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 150765568. Throughput: 0: 2748.5, 1: 2749.8. Samples: 150778616. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:55:33,445][86177] Avg episode reward: [(0, '-513.920'), (1, '-2093.580')] -[2023-11-28 07:55:33,576][87424] Updated weights for policy 0, policy_version 294569 (0.0009) -[2023-11-28 07:55:33,965][87424] Updated weights for policy 0, policy_version 294579 (0.0008) -[2023-11-28 07:55:34,221][87426] Updated weights for policy 1, policy_version 294370 (0.0010) -[2023-11-28 07:55:34,347][87424] Updated weights for policy 0, policy_version 294589 (0.0007) -[2023-11-28 07:55:34,595][87426] Updated weights for policy 1, policy_version 294380 (0.0010) -[2023-11-28 07:55:34,972][87426] Updated weights for policy 1, policy_version 294390 (0.0012) -[2023-11-28 07:55:35,350][87426] Updated weights for policy 1, policy_version 294400 (0.0012) -[2023-11-28 07:55:36,665][87424] Updated weights for policy 0, policy_version 294599 (0.0010) -[2023-11-28 07:55:37,032][87424] Updated weights for policy 0, policy_version 294609 (0.0012) -[2023-11-28 07:55:37,060][87426] Updated weights for policy 1, policy_version 294410 (0.0007) -[2023-11-28 07:55:37,418][87424] Updated weights for policy 0, policy_version 294619 (0.0012) -[2023-11-28 07:55:37,440][87426] Updated weights for policy 1, policy_version 294420 (0.0009) -[2023-11-28 07:55:37,815][87426] Updated weights for policy 1, policy_version 294430 (0.0011) -[2023-11-28 07:55:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 150798336. Throughput: 0: 2778.9, 1: 2752.2. Samples: 150812828. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:55:38,445][86177] Avg episode reward: [(0, '-520.100'), (1, '-1966.380')] -[2023-11-28 07:55:39,531][87424] Updated weights for policy 0, policy_version 294629 (0.0011) -[2023-11-28 07:55:39,660][87426] Updated weights for policy 1, policy_version 294440 (0.0012) -[2023-11-28 07:55:39,908][87424] Updated weights for policy 0, policy_version 294639 (0.0009) -[2023-11-28 07:55:40,037][87426] Updated weights for policy 1, policy_version 294450 (0.0012) -[2023-11-28 07:55:40,284][87424] Updated weights for policy 0, policy_version 294649 (0.0011) -[2023-11-28 07:55:40,409][87426] Updated weights for policy 1, policy_version 294460 (0.0012) -[2023-11-28 07:55:42,563][87424] Updated weights for policy 0, policy_version 294659 (0.0011) -[2023-11-28 07:55:42,713][87426] Updated weights for policy 1, policy_version 294470 (0.0010) -[2023-11-28 07:55:42,955][87424] Updated weights for policy 0, policy_version 294669 (0.0012) -[2023-11-28 07:55:43,087][87426] Updated weights for policy 1, policy_version 294480 (0.0010) -[2023-11-28 07:55:43,326][87424] Updated weights for policy 0, policy_version 294679 (0.0019) -[2023-11-28 07:55:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 150814720. Throughput: 0: 2785.0, 1: 2765.0. Samples: 150837584. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:55:43,445][86177] Avg episode reward: [(0, '-513.180'), (1, '-1843.010')] -[2023-11-28 07:55:43,473][87426] Updated weights for policy 1, policy_version 294490 (0.0010) -[2023-11-28 07:55:45,390][87424] Updated weights for policy 0, policy_version 294689 (0.0010) -[2023-11-28 07:55:45,771][87424] Updated weights for policy 0, policy_version 294699 (0.0009) -[2023-11-28 07:55:45,841][87426] Updated weights for policy 1, policy_version 294500 (0.0009) -[2023-11-28 07:55:46,158][87424] Updated weights for policy 0, policy_version 294709 (0.0008) -[2023-11-28 07:55:46,214][87426] Updated weights for policy 1, policy_version 294510 (0.0008) -[2023-11-28 07:55:46,532][87424] Updated weights for policy 0, policy_version 294719 (0.0007) -[2023-11-28 07:55:46,606][87426] Updated weights for policy 1, policy_version 294520 (0.0008) -[2023-11-28 07:55:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 150847488. Throughput: 0: 2781.5, 1: 2775.8. Samples: 150862552. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:55:48,446][86177] Avg episode reward: [(0, '-514.360'), (1, '-1817.080')] -[2023-11-28 07:55:48,627][87424] Updated weights for policy 0, policy_version 294729 (0.0010) -[2023-11-28 07:55:49,015][87424] Updated weights for policy 0, policy_version 294739 (0.0010) -[2023-11-28 07:55:49,107][87426] Updated weights for policy 1, policy_version 294530 (0.0008) -[2023-11-28 07:55:49,391][87424] Updated weights for policy 0, policy_version 294749 (0.0011) -[2023-11-28 07:55:49,478][87426] Updated weights for policy 1, policy_version 294540 (0.0011) -[2023-11-28 07:55:49,862][87426] Updated weights for policy 1, policy_version 294550 (0.0008) -[2023-11-28 07:55:50,240][87426] Updated weights for policy 1, policy_version 294560 (0.0009) -[2023-11-28 07:55:51,540][87424] Updated weights for policy 0, policy_version 294759 (0.0011) -[2023-11-28 07:55:51,924][87424] Updated weights for policy 0, policy_version 294769 (0.0012) -[2023-11-28 07:55:52,163][87426] Updated weights for policy 1, policy_version 294570 (0.0012) -[2023-11-28 07:55:52,303][87424] Updated weights for policy 0, policy_version 294779 (0.0011) -[2023-11-28 07:55:52,541][87426] Updated weights for policy 1, policy_version 294580 (0.0011) -[2023-11-28 07:55:52,920][87426] Updated weights for policy 1, policy_version 294590 (0.0010) -[2023-11-28 07:55:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 150880256. Throughput: 0: 2767.2, 1: 2735.3. Samples: 150894440. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:55:53,445][86177] Avg episode reward: [(0, '-521.460'), (1, '-1823.330')] -[2023-11-28 07:55:54,769][87424] Updated weights for policy 0, policy_version 294789 (0.0009) -[2023-11-28 07:55:55,151][87424] Updated weights for policy 0, policy_version 294799 (0.0011) -[2023-11-28 07:55:55,191][87426] Updated weights for policy 1, policy_version 294600 (0.0009) -[2023-11-28 07:55:55,543][87424] Updated weights for policy 0, policy_version 294809 (0.0012) -[2023-11-28 07:55:55,572][87426] Updated weights for policy 1, policy_version 294610 (0.0007) -[2023-11-28 07:55:55,960][87426] Updated weights for policy 1, policy_version 294620 (0.0007) -[2023-11-28 07:55:57,740][87424] Updated weights for policy 0, policy_version 294819 (0.0012) -[2023-11-28 07:55:58,119][87424] Updated weights for policy 0, policy_version 294829 (0.0012) -[2023-11-28 07:55:58,160][87426] Updated weights for policy 1, policy_version 294630 (0.0010) -[2023-11-28 07:55:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 150896640. Throughput: 0: 2762.0, 1: 2760.8. Samples: 150919092. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:55:58,445][86177] Avg episode reward: [(0, '-559.060'), (1, '-1787.430')] -[2023-11-28 07:55:58,500][87424] Updated weights for policy 0, policy_version 294839 (0.0010) -[2023-11-28 07:55:58,540][87426] Updated weights for policy 1, policy_version 294640 (0.0009) -[2023-11-28 07:55:58,918][87426] Updated weights for policy 1, policy_version 294650 (0.0009) -[2023-11-28 07:56:00,618][87426] Updated weights for policy 1, policy_version 294660 (0.0009) -[2023-11-28 07:56:00,987][87426] Updated weights for policy 1, policy_version 294670 (0.0012) -[2023-11-28 07:56:01,007][87424] Updated weights for policy 0, policy_version 294849 (0.0009) -[2023-11-28 07:56:01,374][87426] Updated weights for policy 1, policy_version 294680 (0.0008) -[2023-11-28 07:56:01,384][87424] Updated weights for policy 0, policy_version 294859 (0.0007) -[2023-11-28 07:56:01,764][87424] Updated weights for policy 0, policy_version 294869 (0.0009) -[2023-11-28 07:56:02,148][87424] Updated weights for policy 0, policy_version 294879 (0.0010) -[2023-11-28 07:56:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 150929408. Throughput: 0: 2744.4, 1: 2789.6. Samples: 150943896. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:56:03,445][86177] Avg episode reward: [(0, '-560.100'), (1, '-1858.330')] -[2023-11-28 07:56:03,520][87426] Updated weights for policy 1, policy_version 294690 (0.0013) -[2023-11-28 07:56:03,908][87426] Updated weights for policy 1, policy_version 294700 (0.0012) -[2023-11-28 07:56:04,278][87426] Updated weights for policy 1, policy_version 294710 (0.0010) -[2023-11-28 07:56:04,365][87424] Updated weights for policy 0, policy_version 294889 (0.0008) -[2023-11-28 07:56:04,664][87426] Updated weights for policy 1, policy_version 294720 (0.0011) -[2023-11-28 07:56:04,747][87424] Updated weights for policy 0, policy_version 294899 (0.0011) -[2023-11-28 07:56:05,121][87424] Updated weights for policy 0, policy_version 294909 (0.0012) -[2023-11-28 07:56:06,893][87424] Updated weights for policy 0, policy_version 294919 (0.0012) -[2023-11-28 07:56:07,155][87426] Updated weights for policy 1, policy_version 294730 (0.0010) -[2023-11-28 07:56:07,281][87424] Updated weights for policy 0, policy_version 294929 (0.0011) -[2023-11-28 07:56:07,534][87426] Updated weights for policy 1, policy_version 294740 (0.0011) -[2023-11-28 07:56:07,657][87424] Updated weights for policy 0, policy_version 294939 (0.0011) -[2023-11-28 07:56:07,911][87426] Updated weights for policy 1, policy_version 294750 (0.0012) -[2023-11-28 07:56:08,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 150962176. Throughput: 0: 2748.9, 1: 2813.4. Samples: 150976592. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:56:08,446][86177] Avg episode reward: [(0, '-564.080'), (1, '-1839.420')] -[2023-11-28 07:56:09,817][87424] Updated weights for policy 0, policy_version 294949 (0.0012) -[2023-11-28 07:56:09,892][87426] Updated weights for policy 1, policy_version 294760 (0.0011) -[2023-11-28 07:56:10,195][87424] Updated weights for policy 0, policy_version 294959 (0.0012) -[2023-11-28 07:56:10,272][87426] Updated weights for policy 1, policy_version 294770 (0.0011) -[2023-11-28 07:56:10,576][87424] Updated weights for policy 0, policy_version 294969 (0.0012) -[2023-11-28 07:56:10,646][87426] Updated weights for policy 1, policy_version 294780 (0.0010) -[2023-11-28 07:56:12,789][87424] Updated weights for policy 0, policy_version 294979 (0.0012) -[2023-11-28 07:56:13,170][87424] Updated weights for policy 0, policy_version 294989 (0.0011) -[2023-11-28 07:56:13,189][87426] Updated weights for policy 1, policy_version 294790 (0.0009) -[2023-11-28 07:56:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 150978560. Throughput: 0: 2750.2, 1: 2741.8. Samples: 151000684. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:56:13,445][86177] Avg episode reward: [(0, '-524.410'), (1, '-1858.450')] -[2023-11-28 07:56:13,561][87426] Updated weights for policy 1, policy_version 294800 (0.0008) -[2023-11-28 07:56:13,563][87424] Updated weights for policy 0, policy_version 294999 (0.0008) -[2023-11-28 07:56:13,947][87426] Updated weights for policy 1, policy_version 294810 (0.0008) -[2023-11-28 07:56:15,377][87424] Updated weights for policy 0, policy_version 295009 (0.0008) -[2023-11-28 07:56:15,762][87424] Updated weights for policy 0, policy_version 295019 (0.0012) -[2023-11-28 07:56:16,129][87426] Updated weights for policy 1, policy_version 294820 (0.0012) -[2023-11-28 07:56:16,132][87424] Updated weights for policy 0, policy_version 295029 (0.0011) -[2023-11-28 07:56:16,506][87426] Updated weights for policy 1, policy_version 294830 (0.0012) -[2023-11-28 07:56:16,523][87424] Updated weights for policy 0, policy_version 295039 (0.0011) -[2023-11-28 07:56:16,891][87426] Updated weights for policy 1, policy_version 294840 (0.0012) -[2023-11-28 07:56:18,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151011328. Throughput: 0: 2733.7, 1: 2739.8. Samples: 151024924. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:56:18,445][86177] Avg episode reward: [(0, '-518.160'), (1, '-1918.890')] -[2023-11-28 07:56:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000295040_75530240.pth... -[2023-11-28 07:56:18,496][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000292512_74883072.pth -[2023-11-28 07:56:18,558][87426] Updated weights for policy 1, policy_version 294850 (0.0012) -[2023-11-28 07:56:18,941][87426] Updated weights for policy 1, policy_version 294860 (0.0010) -[2023-11-28 07:56:18,970][87424] Updated weights for policy 0, policy_version 295049 (0.0012) -[2023-11-28 07:56:19,316][87426] Updated weights for policy 1, policy_version 294870 (0.0011) -[2023-11-28 07:56:19,345][87424] Updated weights for policy 0, policy_version 295059 (0.0010) -[2023-11-28 07:56:19,694][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000294880_75489280.pth... -[2023-11-28 07:56:19,696][87426] Updated weights for policy 1, policy_version 294880 (0.0011) -[2023-11-28 07:56:19,731][87424] Updated weights for policy 0, policy_version 295069 (0.0010) -[2023-11-28 07:56:19,740][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000292288_74825728.pth -[2023-11-28 07:56:21,398][87426] Updated weights for policy 1, policy_version 294890 (0.0008) -[2023-11-28 07:56:21,783][87426] Updated weights for policy 1, policy_version 294900 (0.0009) -[2023-11-28 07:56:22,159][87426] Updated weights for policy 1, policy_version 294910 (0.0011) -[2023-11-28 07:56:22,187][87424] Updated weights for policy 0, policy_version 295079 (0.0012) -[2023-11-28 07:56:22,571][87424] Updated weights for policy 0, policy_version 295089 (0.0012) -[2023-11-28 07:56:22,952][87424] Updated weights for policy 0, policy_version 295099 (0.0012) -[2023-11-28 07:56:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 151044096. Throughput: 0: 2694.7, 1: 2736.0. Samples: 151057208. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:56:23,445][86177] Avg episode reward: [(0, '-529.620'), (1, '-1875.970')] -[2023-11-28 07:56:24,427][87426] Updated weights for policy 1, policy_version 294920 (0.0008) -[2023-11-28 07:56:24,811][87426] Updated weights for policy 1, policy_version 294930 (0.0007) -[2023-11-28 07:56:25,195][87426] Updated weights for policy 1, policy_version 294940 (0.0007) -[2023-11-28 07:56:25,370][87424] Updated weights for policy 0, policy_version 295109 (0.0011) -[2023-11-28 07:56:25,751][87424] Updated weights for policy 0, policy_version 295119 (0.0011) -[2023-11-28 07:56:26,133][87424] Updated weights for policy 0, policy_version 295129 (0.0007) -[2023-11-28 07:56:26,862][87426] Updated weights for policy 1, policy_version 294950 (0.0011) -[2023-11-28 07:56:27,240][87426] Updated weights for policy 1, policy_version 294960 (0.0007) -[2023-11-28 07:56:27,614][87426] Updated weights for policy 1, policy_version 294970 (0.0010) -[2023-11-28 07:56:28,258][87424] Updated weights for policy 0, policy_version 295139 (0.0007) -[2023-11-28 07:56:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 151068672. Throughput: 0: 2694.1, 1: 2755.3. Samples: 151082808. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:56:28,445][86177] Avg episode reward: [(0, '-529.410'), (1, '-1787.330')] -[2023-11-28 07:56:28,640][87424] Updated weights for policy 0, policy_version 295149 (0.0009) -[2023-11-28 07:56:29,021][87424] Updated weights for policy 0, policy_version 295159 (0.0010) -[2023-11-28 07:56:29,513][87426] Updated weights for policy 1, policy_version 294980 (0.0010) -[2023-11-28 07:56:29,892][87426] Updated weights for policy 1, policy_version 294990 (0.0010) -[2023-11-28 07:56:30,265][87426] Updated weights for policy 1, policy_version 295000 (0.0008) -[2023-11-28 07:56:31,097][87424] Updated weights for policy 0, policy_version 295169 (0.0012) -[2023-11-28 07:56:31,476][87424] Updated weights for policy 0, policy_version 295179 (0.0011) -[2023-11-28 07:56:31,856][87424] Updated weights for policy 0, policy_version 295189 (0.0012) -[2023-11-28 07:56:32,244][87424] Updated weights for policy 0, policy_version 295199 (0.0012) -[2023-11-28 07:56:32,517][87426] Updated weights for policy 1, policy_version 295010 (0.0010) -[2023-11-28 07:56:32,883][87426] Updated weights for policy 1, policy_version 295020 (0.0012) -[2023-11-28 07:56:33,262][87426] Updated weights for policy 1, policy_version 295030 (0.0012) -[2023-11-28 07:56:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151093248. Throughput: 0: 2700.7, 1: 2745.4. Samples: 151107628. Policy #0 lag: (min: 4.0, avg: 24.9, max: 54.0) -[2023-11-28 07:56:33,445][86177] Avg episode reward: [(0, '-529.280'), (1, '-1710.680')] -[2023-11-28 07:56:33,635][87426] Updated weights for policy 1, policy_version 295040 (0.0012) -[2023-11-28 07:56:34,677][87424] Updated weights for policy 0, policy_version 295209 (0.0008) -[2023-11-28 07:56:35,061][87424] Updated weights for policy 0, policy_version 295219 (0.0009) -[2023-11-28 07:56:35,445][87424] Updated weights for policy 0, policy_version 295229 (0.0009) -[2023-11-28 07:56:36,246][87426] Updated weights for policy 1, policy_version 295050 (0.0012) -[2023-11-28 07:56:36,624][87426] Updated weights for policy 1, policy_version 295060 (0.0012) -[2023-11-28 07:56:37,001][87426] Updated weights for policy 1, policy_version 295070 (0.0012) -[2023-11-28 07:56:37,865][87424] Updated weights for policy 0, policy_version 295239 (0.0010) -[2023-11-28 07:56:38,252][87424] Updated weights for policy 0, policy_version 295249 (0.0012) -[2023-11-28 07:56:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 151117824. Throughput: 0: 2699.3, 1: 2742.7. Samples: 151139328. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:56:38,445][86177] Avg episode reward: [(0, '-528.310'), (1, '-1735.890')] -[2023-11-28 07:56:38,619][87424] Updated weights for policy 0, policy_version 295259 (0.0012) -[2023-11-28 07:56:39,246][87426] Updated weights for policy 1, policy_version 295080 (0.0008) -[2023-11-28 07:56:39,625][87426] Updated weights for policy 1, policy_version 295090 (0.0008) -[2023-11-28 07:56:40,004][87426] Updated weights for policy 1, policy_version 295100 (0.0008) -[2023-11-28 07:56:40,747][87424] Updated weights for policy 0, policy_version 295269 (0.0011) -[2023-11-28 07:56:41,127][87424] Updated weights for policy 0, policy_version 295279 (0.0011) -[2023-11-28 07:56:41,506][87424] Updated weights for policy 0, policy_version 295289 (0.0012) -[2023-11-28 07:56:42,398][87426] Updated weights for policy 1, policy_version 295110 (0.0009) -[2023-11-28 07:56:42,776][87426] Updated weights for policy 1, policy_version 295120 (0.0011) -[2023-11-28 07:56:43,154][87426] Updated weights for policy 1, policy_version 295130 (0.0013) -[2023-11-28 07:56:43,426][87424] Updated weights for policy 0, policy_version 295299 (0.0012) -[2023-11-28 07:56:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 151150592. Throughput: 0: 2682.8, 1: 2735.1. Samples: 151162900. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:56:43,445][86177] Avg episode reward: [(0, '-551.010'), (1, '-1697.710')] -[2023-11-28 07:56:43,806][87424] Updated weights for policy 0, policy_version 295309 (0.0012) -[2023-11-28 07:56:44,193][87424] Updated weights for policy 0, policy_version 295319 (0.0012) -[2023-11-28 07:56:45,252][87426] Updated weights for policy 1, policy_version 295140 (0.0010) -[2023-11-28 07:56:45,634][87426] Updated weights for policy 1, policy_version 295150 (0.0008) -[2023-11-28 07:56:46,013][87426] Updated weights for policy 1, policy_version 295160 (0.0008) -[2023-11-28 07:56:46,330][87424] Updated weights for policy 0, policy_version 295329 (0.0011) -[2023-11-28 07:56:46,711][87424] Updated weights for policy 0, policy_version 295339 (0.0007) -[2023-11-28 07:56:47,094][87424] Updated weights for policy 0, policy_version 295349 (0.0008) -[2023-11-28 07:56:47,483][87424] Updated weights for policy 0, policy_version 295359 (0.0008) -[2023-11-28 07:56:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151175168. Throughput: 0: 2683.0, 1: 2720.4. Samples: 151187052. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:56:48,445][86177] Avg episode reward: [(0, '-549.370'), (1, '-1552.910')] -[2023-11-28 07:56:48,469][87426] Updated weights for policy 1, policy_version 295170 (0.0008) -[2023-11-28 07:56:48,842][87426] Updated weights for policy 1, policy_version 295180 (0.0008) -[2023-11-28 07:56:49,223][87426] Updated weights for policy 1, policy_version 295190 (0.0007) -[2023-11-28 07:56:49,599][87426] Updated weights for policy 1, policy_version 295200 (0.0007) -[2023-11-28 07:56:49,821][87424] Updated weights for policy 0, policy_version 295369 (0.0008) -[2023-11-28 07:56:50,212][87424] Updated weights for policy 0, policy_version 295379 (0.0008) -[2023-11-28 07:56:50,585][87424] Updated weights for policy 0, policy_version 295389 (0.0009) -[2023-11-28 07:56:51,976][87426] Updated weights for policy 1, policy_version 295210 (0.0012) -[2023-11-28 07:56:52,348][87426] Updated weights for policy 1, policy_version 295220 (0.0013) -[2023-11-28 07:56:52,723][87426] Updated weights for policy 1, policy_version 295230 (0.0012) -[2023-11-28 07:56:53,014][87424] Updated weights for policy 0, policy_version 295399 (0.0010) -[2023-11-28 07:56:53,405][87424] Updated weights for policy 0, policy_version 295409 (0.0011) -[2023-11-28 07:56:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 151199744. Throughput: 0: 2673.9, 1: 2703.3. Samples: 151218564. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:56:53,445][86177] Avg episode reward: [(0, '-550.200'), (1, '-1404.900')] -[2023-11-28 07:56:53,780][87424] Updated weights for policy 0, policy_version 295419 (0.0011) -[2023-11-28 07:56:55,214][87426] Updated weights for policy 1, policy_version 295240 (0.0011) -[2023-11-28 07:56:55,585][87426] Updated weights for policy 1, policy_version 295250 (0.0011) -[2023-11-28 07:56:55,739][87424] Updated weights for policy 0, policy_version 295429 (0.0011) -[2023-11-28 07:56:55,962][87426] Updated weights for policy 1, policy_version 295260 (0.0012) -[2023-11-28 07:56:56,111][87424] Updated weights for policy 0, policy_version 295439 (0.0011) -[2023-11-28 07:56:56,487][87424] Updated weights for policy 0, policy_version 295449 (0.0012) -[2023-11-28 07:56:57,653][87426] Updated weights for policy 1, policy_version 295270 (0.0011) -[2023-11-28 07:56:58,037][87426] Updated weights for policy 1, policy_version 295280 (0.0012) -[2023-11-28 07:56:58,416][87426] Updated weights for policy 1, policy_version 295290 (0.0012) -[2023-11-28 07:56:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151224320. Throughput: 0: 2672.4, 1: 2731.7. Samples: 151243872. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:56:58,445][86177] Avg episode reward: [(0, '-546.400'), (1, '-1219.690')] -[2023-11-28 07:56:58,949][87424] Updated weights for policy 0, policy_version 295459 (0.0012) -[2023-11-28 07:56:59,337][87424] Updated weights for policy 0, policy_version 295469 (0.0011) -[2023-11-28 07:56:59,720][87424] Updated weights for policy 0, policy_version 295479 (0.0008) -[2023-11-28 07:57:00,221][87426] Updated weights for policy 1, policy_version 295300 (0.0012) -[2023-11-28 07:57:00,595][87426] Updated weights for policy 1, policy_version 295310 (0.0011) -[2023-11-28 07:57:00,973][87426] Updated weights for policy 1, policy_version 295320 (0.0011) -[2023-11-28 07:57:01,472][87424] Updated weights for policy 0, policy_version 295489 (0.0009) -[2023-11-28 07:57:01,853][87424] Updated weights for policy 0, policy_version 295499 (0.0009) -[2023-11-28 07:57:02,242][87424] Updated weights for policy 0, policy_version 295509 (0.0008) -[2023-11-28 07:57:02,616][87424] Updated weights for policy 0, policy_version 295519 (0.0008) -[2023-11-28 07:57:03,070][87426] Updated weights for policy 1, policy_version 295330 (0.0012) -[2023-11-28 07:57:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151257088. Throughput: 0: 2701.0, 1: 2742.1. Samples: 151269864. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:03,445][86177] Avg episode reward: [(0, '-522.280'), (1, '-1260.130')] -[2023-11-28 07:57:03,447][87426] Updated weights for policy 1, policy_version 295340 (0.0012) -[2023-11-28 07:57:03,828][87426] Updated weights for policy 1, policy_version 295350 (0.0012) -[2023-11-28 07:57:04,203][87426] Updated weights for policy 1, policy_version 295360 (0.0012) -[2023-11-28 07:57:04,945][87424] Updated weights for policy 0, policy_version 295529 (0.0007) -[2023-11-28 07:57:05,333][87424] Updated weights for policy 0, policy_version 295539 (0.0010) -[2023-11-28 07:57:05,720][87424] Updated weights for policy 0, policy_version 295549 (0.0008) -[2023-11-28 07:57:06,206][87426] Updated weights for policy 1, policy_version 295370 (0.0010) -[2023-11-28 07:57:06,573][87426] Updated weights for policy 1, policy_version 295380 (0.0007) -[2023-11-28 07:57:06,959][87426] Updated weights for policy 1, policy_version 295390 (0.0008) -[2023-11-28 07:57:08,001][87424] Updated weights for policy 0, policy_version 295559 (0.0010) -[2023-11-28 07:57:08,385][87424] Updated weights for policy 0, policy_version 295569 (0.0008) -[2023-11-28 07:57:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 151281664. Throughput: 0: 2715.6, 1: 2725.3. Samples: 151302048. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:08,445][86177] Avg episode reward: [(0, '-534.870'), (1, '-1152.270')] -[2023-11-28 07:57:08,770][87424] Updated weights for policy 0, policy_version 295579 (0.0010) -[2023-11-28 07:57:08,946][87426] Updated weights for policy 1, policy_version 295400 (0.0011) -[2023-11-28 07:57:09,324][87426] Updated weights for policy 1, policy_version 295410 (0.0012) -[2023-11-28 07:57:09,700][87426] Updated weights for policy 1, policy_version 295420 (0.0012) -[2023-11-28 07:57:11,024][87424] Updated weights for policy 0, policy_version 295589 (0.0010) -[2023-11-28 07:57:11,410][87424] Updated weights for policy 0, policy_version 295599 (0.0008) -[2023-11-28 07:57:11,793][87424] Updated weights for policy 0, policy_version 295609 (0.0009) -[2023-11-28 07:57:12,128][87426] Updated weights for policy 1, policy_version 295430 (0.0009) -[2023-11-28 07:57:12,517][87426] Updated weights for policy 1, policy_version 295440 (0.0008) -[2023-11-28 07:57:12,885][87426] Updated weights for policy 1, policy_version 295450 (0.0009) -[2023-11-28 07:57:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 151314432. Throughput: 0: 2711.0, 1: 2691.6. Samples: 151325928. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:13,445][86177] Avg episode reward: [(0, '-531.650'), (1, '-1135.970')] -[2023-11-28 07:57:13,995][87424] Updated weights for policy 0, policy_version 295619 (0.0009) -[2023-11-28 07:57:14,376][87424] Updated weights for policy 0, policy_version 295629 (0.0009) -[2023-11-28 07:57:14,744][87424] Updated weights for policy 0, policy_version 295639 (0.0012) -[2023-11-28 07:57:15,384][87426] Updated weights for policy 1, policy_version 295460 (0.0012) -[2023-11-28 07:57:15,761][87426] Updated weights for policy 1, policy_version 295470 (0.0012) -[2023-11-28 07:57:16,142][87426] Updated weights for policy 1, policy_version 295480 (0.0010) -[2023-11-28 07:57:16,698][87424] Updated weights for policy 0, policy_version 295649 (0.0011) -[2023-11-28 07:57:17,092][87424] Updated weights for policy 0, policy_version 295659 (0.0010) -[2023-11-28 07:57:17,464][87424] Updated weights for policy 0, policy_version 295669 (0.0009) -[2023-11-28 07:57:17,836][87426] Updated weights for policy 1, policy_version 295490 (0.0009) -[2023-11-28 07:57:17,848][87424] Updated weights for policy 0, policy_version 295679 (0.0007) -[2023-11-28 07:57:18,205][87426] Updated weights for policy 1, policy_version 295500 (0.0009) -[2023-11-28 07:57:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151339008. Throughput: 0: 2701.3, 1: 2715.2. Samples: 151351372. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:18,445][86177] Avg episode reward: [(0, '-570.170'), (1, '-1017.600')] -[2023-11-28 07:57:18,584][87426] Updated weights for policy 1, policy_version 295510 (0.0008) -[2023-11-28 07:57:18,962][87426] Updated weights for policy 1, policy_version 295520 (0.0008) -[2023-11-28 07:57:20,188][87424] Updated weights for policy 0, policy_version 295689 (0.0008) -[2023-11-28 07:57:20,564][87424] Updated weights for policy 0, policy_version 295699 (0.0010) -[2023-11-28 07:57:20,952][87424] Updated weights for policy 0, policy_version 295709 (0.0012) -[2023-11-28 07:57:21,231][87426] Updated weights for policy 1, policy_version 295530 (0.0011) -[2023-11-28 07:57:21,612][87426] Updated weights for policy 1, policy_version 295540 (0.0012) -[2023-11-28 07:57:21,985][87426] Updated weights for policy 1, policy_version 295550 (0.0012) -[2023-11-28 07:57:22,887][87424] Updated weights for policy 0, policy_version 295719 (0.0012) -[2023-11-28 07:57:23,271][87424] Updated weights for policy 0, policy_version 295729 (0.0012) -[2023-11-28 07:57:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 151363584. Throughput: 0: 2703.6, 1: 2715.9. Samples: 151383204. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:23,445][86177] Avg episode reward: [(0, '-563.140'), (1, '-978.130')] -[2023-11-28 07:57:23,650][87424] Updated weights for policy 0, policy_version 295739 (0.0012) -[2023-11-28 07:57:24,239][87426] Updated weights for policy 1, policy_version 295560 (0.0012) -[2023-11-28 07:57:24,612][87426] Updated weights for policy 1, policy_version 295570 (0.0010) -[2023-11-28 07:57:24,993][87426] Updated weights for policy 1, policy_version 295580 (0.0011) -[2023-11-28 07:57:25,807][87424] Updated weights for policy 0, policy_version 295749 (0.0012) -[2023-11-28 07:57:26,185][87424] Updated weights for policy 0, policy_version 295759 (0.0012) -[2023-11-28 07:57:26,575][87424] Updated weights for policy 0, policy_version 295769 (0.0012) -[2023-11-28 07:57:26,925][87426] Updated weights for policy 1, policy_version 295590 (0.0012) -[2023-11-28 07:57:27,300][87426] Updated weights for policy 1, policy_version 295600 (0.0011) -[2023-11-28 07:57:27,684][87426] Updated weights for policy 1, policy_version 295610 (0.0011) -[2023-11-28 07:57:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151396352. Throughput: 0: 2730.0, 1: 2744.1. Samples: 151409232. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:28,445][86177] Avg episode reward: [(0, '-565.320'), (1, '-952.340')] -[2023-11-28 07:57:28,891][87424] Updated weights for policy 0, policy_version 295779 (0.0011) -[2023-11-28 07:57:29,280][87424] Updated weights for policy 0, policy_version 295789 (0.0008) -[2023-11-28 07:57:29,651][87424] Updated weights for policy 0, policy_version 295799 (0.0007) -[2023-11-28 07:57:30,001][87426] Updated weights for policy 1, policy_version 295620 (0.0010) -[2023-11-28 07:57:30,380][87426] Updated weights for policy 1, policy_version 295630 (0.0007) -[2023-11-28 07:57:30,763][87426] Updated weights for policy 1, policy_version 295640 (0.0011) -[2023-11-28 07:57:31,506][87424] Updated weights for policy 0, policy_version 295809 (0.0010) -[2023-11-28 07:57:31,889][87424] Updated weights for policy 0, policy_version 295819 (0.0009) -[2023-11-28 07:57:32,275][87424] Updated weights for policy 0, policy_version 295829 (0.0009) -[2023-11-28 07:57:32,662][87424] Updated weights for policy 0, policy_version 295839 (0.0010) -[2023-11-28 07:57:32,696][87426] Updated weights for policy 1, policy_version 295650 (0.0008) -[2023-11-28 07:57:33,078][87426] Updated weights for policy 1, policy_version 295660 (0.0009) -[2023-11-28 07:57:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151420928. Throughput: 0: 2733.2, 1: 2740.6. Samples: 151433372. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:33,446][86177] Avg episode reward: [(0, '-562.660'), (1, '-841.860')] -[2023-11-28 07:57:33,452][87426] Updated weights for policy 1, policy_version 295670 (0.0007) -[2023-11-28 07:57:33,829][87426] Updated weights for policy 1, policy_version 295680 (0.0007) -[2023-11-28 07:57:34,780][87424] Updated weights for policy 0, policy_version 295849 (0.0011) -[2023-11-28 07:57:35,161][87424] Updated weights for policy 0, policy_version 295859 (0.0011) -[2023-11-28 07:57:35,545][87424] Updated weights for policy 0, policy_version 295869 (0.0011) -[2023-11-28 07:57:35,809][87426] Updated weights for policy 1, policy_version 295690 (0.0012) -[2023-11-28 07:57:36,183][87426] Updated weights for policy 1, policy_version 295700 (0.0011) -[2023-11-28 07:57:36,556][87426] Updated weights for policy 1, policy_version 295710 (0.0012) -[2023-11-28 07:57:37,441][87424] Updated weights for policy 0, policy_version 295879 (0.0011) -[2023-11-28 07:57:37,828][87424] Updated weights for policy 0, policy_version 295889 (0.0011) -[2023-11-28 07:57:38,206][87424] Updated weights for policy 0, policy_version 295899 (0.0011) -[2023-11-28 07:57:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 151453696. Throughput: 0: 2739.7, 1: 2787.6. Samples: 151467292. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:38,445][86177] Avg episode reward: [(0, '-526.780'), (1, '-849.030')] -[2023-11-28 07:57:38,742][87426] Updated weights for policy 1, policy_version 295720 (0.0011) -[2023-11-28 07:57:39,115][87426] Updated weights for policy 1, policy_version 295730 (0.0011) -[2023-11-28 07:57:39,506][87426] Updated weights for policy 1, policy_version 295740 (0.0008) -[2023-11-28 07:57:40,330][87424] Updated weights for policy 0, policy_version 295909 (0.0008) -[2023-11-28 07:57:40,715][87424] Updated weights for policy 0, policy_version 295919 (0.0010) -[2023-11-28 07:57:41,104][87424] Updated weights for policy 0, policy_version 295929 (0.0008) -[2023-11-28 07:57:41,784][87426] Updated weights for policy 1, policy_version 295750 (0.0009) -[2023-11-28 07:57:42,153][87426] Updated weights for policy 1, policy_version 295760 (0.0012) -[2023-11-28 07:57:42,539][87426] Updated weights for policy 1, policy_version 295770 (0.0012) -[2023-11-28 07:57:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151478272. Throughput: 0: 2734.9, 1: 2761.4. Samples: 151491208. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:43,445][86177] Avg episode reward: [(0, '-533.590'), (1, '-879.220')] -[2023-11-28 07:57:43,645][87424] Updated weights for policy 0, policy_version 295939 (0.0009) -[2023-11-28 07:57:44,022][87424] Updated weights for policy 0, policy_version 295949 (0.0012) -[2023-11-28 07:57:44,404][87424] Updated weights for policy 0, policy_version 295959 (0.0012) -[2023-11-28 07:57:44,560][87426] Updated weights for policy 1, policy_version 295780 (0.0012) -[2023-11-28 07:57:44,936][87426] Updated weights for policy 1, policy_version 295790 (0.0009) -[2023-11-28 07:57:45,312][87426] Updated weights for policy 1, policy_version 295800 (0.0008) -[2023-11-28 07:57:46,953][87424] Updated weights for policy 0, policy_version 295969 (0.0010) -[2023-11-28 07:57:47,334][87424] Updated weights for policy 0, policy_version 295979 (0.0010) -[2023-11-28 07:57:47,712][87426] Updated weights for policy 1, policy_version 295810 (0.0011) -[2023-11-28 07:57:47,714][87424] Updated weights for policy 0, policy_version 295989 (0.0008) -[2023-11-28 07:57:48,087][87426] Updated weights for policy 1, policy_version 295820 (0.0010) -[2023-11-28 07:57:48,096][87424] Updated weights for policy 0, policy_version 295999 (0.0007) -[2023-11-28 07:57:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151502848. Throughput: 0: 2702.8, 1: 2751.3. Samples: 151515300. Policy #0 lag: (min: 51.0, avg: 60.6, max: 88.0) -[2023-11-28 07:57:48,445][86177] Avg episode reward: [(0, '-527.380'), (1, '-884.710')] -[2023-11-28 07:57:48,464][87426] Updated weights for policy 1, policy_version 295830 (0.0007) -[2023-11-28 07:57:48,851][87426] Updated weights for policy 1, policy_version 295840 (0.0007) -[2023-11-28 07:57:49,960][87424] Updated weights for policy 0, policy_version 296009 (0.0009) -[2023-11-28 07:57:50,333][87424] Updated weights for policy 0, policy_version 296019 (0.0009) -[2023-11-28 07:57:50,724][87424] Updated weights for policy 0, policy_version 296029 (0.0008) -[2023-11-28 07:57:51,370][87426] Updated weights for policy 1, policy_version 295850 (0.0009) -[2023-11-28 07:57:51,746][87426] Updated weights for policy 1, policy_version 295860 (0.0011) -[2023-11-28 07:57:52,130][87426] Updated weights for policy 1, policy_version 295870 (0.0011) -[2023-11-28 07:57:52,881][87424] Updated weights for policy 0, policy_version 296039 (0.0010) -[2023-11-28 07:57:53,261][87424] Updated weights for policy 0, policy_version 296049 (0.0012) -[2023-11-28 07:57:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151527424. Throughput: 0: 2706.8, 1: 2727.6. Samples: 151546592. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:57:53,445][86177] Avg episode reward: [(0, '-541.390'), (1, '-810.640')] -[2023-11-28 07:57:53,643][87424] Updated weights for policy 0, policy_version 296059 (0.0012) -[2023-11-28 07:57:54,395][87426] Updated weights for policy 1, policy_version 295880 (0.0010) -[2023-11-28 07:57:54,783][87426] Updated weights for policy 1, policy_version 295890 (0.0011) -[2023-11-28 07:57:55,167][87426] Updated weights for policy 1, policy_version 295900 (0.0011) -[2023-11-28 07:57:56,176][87424] Updated weights for policy 0, policy_version 296069 (0.0013) -[2023-11-28 07:57:56,563][87424] Updated weights for policy 0, policy_version 296079 (0.0012) -[2023-11-28 07:57:56,952][87424] Updated weights for policy 0, policy_version 296089 (0.0010) -[2023-11-28 07:57:57,643][87426] Updated weights for policy 1, policy_version 295910 (0.0012) -[2023-11-28 07:57:58,025][87426] Updated weights for policy 1, policy_version 295920 (0.0012) -[2023-11-28 07:57:58,404][87426] Updated weights for policy 1, policy_version 295930 (0.0009) -[2023-11-28 07:57:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151552000. Throughput: 0: 2709.1, 1: 2729.1. Samples: 151570648. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:57:58,446][86177] Avg episode reward: [(0, '-543.660'), (1, '-854.120')] -[2023-11-28 07:57:58,892][87424] Updated weights for policy 0, policy_version 296099 (0.0007) -[2023-11-28 07:57:59,273][87424] Updated weights for policy 0, policy_version 296109 (0.0008) -[2023-11-28 07:57:59,657][87424] Updated weights for policy 0, policy_version 296119 (0.0007) -[2023-11-28 07:58:00,600][87426] Updated weights for policy 1, policy_version 295940 (0.0009) -[2023-11-28 07:58:00,979][87426] Updated weights for policy 1, policy_version 295950 (0.0012) -[2023-11-28 07:58:01,359][87426] Updated weights for policy 1, policy_version 295960 (0.0012) -[2023-11-28 07:58:02,050][87424] Updated weights for policy 0, policy_version 296129 (0.0009) -[2023-11-28 07:58:02,437][87424] Updated weights for policy 0, policy_version 296139 (0.0012) -[2023-11-28 07:58:02,813][87424] Updated weights for policy 0, policy_version 296149 (0.0012) -[2023-11-28 07:58:03,192][87424] Updated weights for policy 0, policy_version 296159 (0.0012) -[2023-11-28 07:58:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151584768. Throughput: 0: 2720.3, 1: 2701.9. Samples: 151595376. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:03,446][86177] Avg episode reward: [(0, '-537.030'), (1, '-939.760')] -[2023-11-28 07:58:03,519][87426] Updated weights for policy 1, policy_version 295970 (0.0012) -[2023-11-28 07:58:03,890][87426] Updated weights for policy 1, policy_version 295980 (0.0010) -[2023-11-28 07:58:04,270][87426] Updated weights for policy 1, policy_version 295990 (0.0007) -[2023-11-28 07:58:04,645][87426] Updated weights for policy 1, policy_version 296000 (0.0011) -[2023-11-28 07:58:05,609][87424] Updated weights for policy 0, policy_version 296169 (0.0012) -[2023-11-28 07:58:05,989][87424] Updated weights for policy 0, policy_version 296179 (0.0012) -[2023-11-28 07:58:06,376][87424] Updated weights for policy 0, policy_version 296189 (0.0011) -[2023-11-28 07:58:06,737][87426] Updated weights for policy 1, policy_version 296010 (0.0012) -[2023-11-28 07:58:07,124][87426] Updated weights for policy 1, policy_version 296020 (0.0010) -[2023-11-28 07:58:07,498][87426] Updated weights for policy 1, policy_version 296030 (0.0011) -[2023-11-28 07:58:08,340][87424] Updated weights for policy 0, policy_version 296199 (0.0011) -[2023-11-28 07:58:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151609344. Throughput: 0: 2727.5, 1: 2728.2. Samples: 151628708. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:08,446][86177] Avg episode reward: [(0, '-530.000'), (1, '-815.320')] -[2023-11-28 07:58:08,723][87424] Updated weights for policy 0, policy_version 296209 (0.0011) -[2023-11-28 07:58:09,105][87424] Updated weights for policy 0, policy_version 296219 (0.0010) -[2023-11-28 07:58:09,303][87426] Updated weights for policy 1, policy_version 296040 (0.0010) -[2023-11-28 07:58:09,680][87426] Updated weights for policy 1, policy_version 296050 (0.0007) -[2023-11-28 07:58:10,067][87426] Updated weights for policy 1, policy_version 296060 (0.0011) -[2023-11-28 07:58:10,984][87424] Updated weights for policy 0, policy_version 296229 (0.0011) -[2023-11-28 07:58:11,369][87424] Updated weights for policy 0, policy_version 296239 (0.0010) -[2023-11-28 07:58:11,747][87424] Updated weights for policy 0, policy_version 296249 (0.0012) -[2023-11-28 07:58:12,068][87426] Updated weights for policy 1, policy_version 296070 (0.0012) -[2023-11-28 07:58:12,445][87426] Updated weights for policy 1, policy_version 296080 (0.0009) -[2023-11-28 07:58:12,833][87426] Updated weights for policy 1, policy_version 296090 (0.0012) -[2023-11-28 07:58:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151642112. Throughput: 0: 2713.2, 1: 2721.3. Samples: 151653784. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:13,445][86177] Avg episode reward: [(0, '-522.110'), (1, '-800.010')] -[2023-11-28 07:58:14,054][87424] Updated weights for policy 0, policy_version 296259 (0.0012) -[2023-11-28 07:58:14,442][87424] Updated weights for policy 0, policy_version 296269 (0.0012) -[2023-11-28 07:58:14,783][87426] Updated weights for policy 1, policy_version 296100 (0.0012) -[2023-11-28 07:58:14,821][87424] Updated weights for policy 0, policy_version 296279 (0.0007) -[2023-11-28 07:58:15,160][87426] Updated weights for policy 1, policy_version 296110 (0.0011) -[2023-11-28 07:58:15,544][87426] Updated weights for policy 1, policy_version 296120 (0.0012) -[2023-11-28 07:58:16,596][87424] Updated weights for policy 0, policy_version 296289 (0.0008) -[2023-11-28 07:58:16,974][87424] Updated weights for policy 0, policy_version 296299 (0.0008) -[2023-11-28 07:58:17,354][87424] Updated weights for policy 0, policy_version 296309 (0.0010) -[2023-11-28 07:58:17,733][87424] Updated weights for policy 0, policy_version 296319 (0.0011) -[2023-11-28 07:58:17,812][87426] Updated weights for policy 1, policy_version 296130 (0.0012) -[2023-11-28 07:58:18,186][87426] Updated weights for policy 1, policy_version 296140 (0.0012) -[2023-11-28 07:58:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151666688. Throughput: 0: 2719.7, 1: 2733.1. Samples: 151678748. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:18,445][86177] Avg episode reward: [(0, '-526.050'), (1, '-820.060')] -[2023-11-28 07:58:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000296320_75857920.pth... -[2023-11-28 07:58:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000293760_75202560.pth -[2023-11-28 07:58:18,565][87426] Updated weights for policy 1, policy_version 296150 (0.0012) -[2023-11-28 07:58:18,942][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000296160_75816960.pth... -[2023-11-28 07:58:18,944][87426] Updated weights for policy 1, policy_version 296160 (0.0012) -[2023-11-28 07:58:18,990][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000293568_75153408.pth -[2023-11-28 07:58:19,792][87424] Updated weights for policy 0, policy_version 296329 (0.0012) -[2023-11-28 07:58:20,170][87424] Updated weights for policy 0, policy_version 296339 (0.0012) -[2023-11-28 07:58:20,549][87424] Updated weights for policy 0, policy_version 296349 (0.0012) -[2023-11-28 07:58:21,055][87426] Updated weights for policy 1, policy_version 296170 (0.0012) -[2023-11-28 07:58:21,444][87426] Updated weights for policy 1, policy_version 296180 (0.0012) -[2023-11-28 07:58:21,817][87426] Updated weights for policy 1, policy_version 296190 (0.0012) -[2023-11-28 07:58:22,651][87424] Updated weights for policy 0, policy_version 296359 (0.0012) -[2023-11-28 07:58:23,037][87424] Updated weights for policy 0, policy_version 296369 (0.0012) -[2023-11-28 07:58:23,418][87424] Updated weights for policy 0, policy_version 296379 (0.0010) -[2023-11-28 07:58:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151691264. Throughput: 0: 2728.4, 1: 2701.8. Samples: 151711648. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:23,445][86177] Avg episode reward: [(0, '-549.970'), (1, '-809.180')] -[2023-11-28 07:58:24,139][87426] Updated weights for policy 1, policy_version 296200 (0.0011) -[2023-11-28 07:58:24,509][87426] Updated weights for policy 1, policy_version 296210 (0.0011) -[2023-11-28 07:58:24,899][87426] Updated weights for policy 1, policy_version 296220 (0.0010) -[2023-11-28 07:58:25,905][87424] Updated weights for policy 0, policy_version 296389 (0.0011) -[2023-11-28 07:58:26,291][87424] Updated weights for policy 0, policy_version 296399 (0.0008) -[2023-11-28 07:58:26,677][87424] Updated weights for policy 0, policy_version 296409 (0.0008) -[2023-11-28 07:58:26,921][87426] Updated weights for policy 1, policy_version 296230 (0.0009) -[2023-11-28 07:58:27,313][87426] Updated weights for policy 1, policy_version 296240 (0.0008) -[2023-11-28 07:58:27,696][87426] Updated weights for policy 1, policy_version 296250 (0.0008) -[2023-11-28 07:58:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151724032. Throughput: 0: 2720.0, 1: 2736.4. Samples: 151736748. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:28,445][86177] Avg episode reward: [(0, '-550.810'), (1, '-843.730')] -[2023-11-28 07:58:28,501][87424] Updated weights for policy 0, policy_version 296419 (0.0009) -[2023-11-28 07:58:28,885][87424] Updated weights for policy 0, policy_version 296429 (0.0012) -[2023-11-28 07:58:29,262][87424] Updated weights for policy 0, policy_version 296439 (0.0012) -[2023-11-28 07:58:29,863][87426] Updated weights for policy 1, policy_version 296260 (0.0008) -[2023-11-28 07:58:30,243][87426] Updated weights for policy 1, policy_version 296270 (0.0008) -[2023-11-28 07:58:30,629][87426] Updated weights for policy 1, policy_version 296280 (0.0009) -[2023-11-28 07:58:31,764][87424] Updated weights for policy 0, policy_version 296449 (0.0012) -[2023-11-28 07:58:32,141][87424] Updated weights for policy 0, policy_version 296459 (0.0012) -[2023-11-28 07:58:32,525][87424] Updated weights for policy 0, policy_version 296469 (0.0012) -[2023-11-28 07:58:32,835][87426] Updated weights for policy 1, policy_version 296290 (0.0008) -[2023-11-28 07:58:32,895][87424] Updated weights for policy 0, policy_version 296479 (0.0011) -[2023-11-28 07:58:33,215][87426] Updated weights for policy 1, policy_version 296300 (0.0011) -[2023-11-28 07:58:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151748608. Throughput: 0: 2730.9, 1: 2735.2. Samples: 151761276. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:33,446][86177] Avg episode reward: [(0, '-553.460'), (1, '-837.990')] -[2023-11-28 07:58:33,603][87426] Updated weights for policy 1, policy_version 296310 (0.0011) -[2023-11-28 07:58:33,988][87426] Updated weights for policy 1, policy_version 296320 (0.0011) -[2023-11-28 07:58:35,301][87424] Updated weights for policy 0, policy_version 296489 (0.0011) -[2023-11-28 07:58:35,689][87424] Updated weights for policy 0, policy_version 296499 (0.0010) -[2023-11-28 07:58:36,064][87424] Updated weights for policy 0, policy_version 296509 (0.0009) -[2023-11-28 07:58:36,367][87426] Updated weights for policy 1, policy_version 296330 (0.0007) -[2023-11-28 07:58:36,759][87426] Updated weights for policy 1, policy_version 296340 (0.0008) -[2023-11-28 07:58:37,133][87426] Updated weights for policy 1, policy_version 296350 (0.0012) -[2023-11-28 07:58:38,068][87424] Updated weights for policy 0, policy_version 296519 (0.0008) -[2023-11-28 07:58:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 151773184. Throughput: 0: 2712.4, 1: 2745.8. Samples: 151792212. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:38,445][86177] Avg episode reward: [(0, '-555.930'), (1, '-788.070')] -[2023-11-28 07:58:38,447][87424] Updated weights for policy 0, policy_version 296529 (0.0008) -[2023-11-28 07:58:38,838][87424] Updated weights for policy 0, policy_version 296539 (0.0008) -[2023-11-28 07:58:39,449][87426] Updated weights for policy 1, policy_version 296360 (0.0012) -[2023-11-28 07:58:39,821][87426] Updated weights for policy 1, policy_version 296370 (0.0012) -[2023-11-28 07:58:40,196][87426] Updated weights for policy 1, policy_version 296380 (0.0012) -[2023-11-28 07:58:41,051][87424] Updated weights for policy 0, policy_version 296549 (0.0012) -[2023-11-28 07:58:41,434][87424] Updated weights for policy 0, policy_version 296559 (0.0012) -[2023-11-28 07:58:41,823][87424] Updated weights for policy 0, policy_version 296569 (0.0011) -[2023-11-28 07:58:42,316][87426] Updated weights for policy 1, policy_version 296390 (0.0011) -[2023-11-28 07:58:42,692][87426] Updated weights for policy 1, policy_version 296400 (0.0011) -[2023-11-28 07:58:43,073][87426] Updated weights for policy 1, policy_version 296410 (0.0011) -[2023-11-28 07:58:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151805952. Throughput: 0: 2707.2, 1: 2748.4. Samples: 151816148. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:43,445][86177] Avg episode reward: [(0, '-542.660'), (1, '-719.690')] -[2023-11-28 07:58:44,206][87424] Updated weights for policy 0, policy_version 296579 (0.0010) -[2023-11-28 07:58:44,592][87424] Updated weights for policy 0, policy_version 296589 (0.0012) -[2023-11-28 07:58:44,985][87424] Updated weights for policy 0, policy_version 296599 (0.0011) -[2023-11-28 07:58:45,555][87426] Updated weights for policy 1, policy_version 296420 (0.0011) -[2023-11-28 07:58:45,941][87426] Updated weights for policy 1, policy_version 296430 (0.0008) -[2023-11-28 07:58:46,317][87426] Updated weights for policy 1, policy_version 296440 (0.0008) -[2023-11-28 07:58:47,429][87424] Updated weights for policy 0, policy_version 296609 (0.0010) -[2023-11-28 07:58:47,814][87424] Updated weights for policy 0, policy_version 296619 (0.0008) -[2023-11-28 07:58:48,020][87426] Updated weights for policy 1, policy_version 296450 (0.0011) -[2023-11-28 07:58:48,201][87424] Updated weights for policy 0, policy_version 296629 (0.0008) -[2023-11-28 07:58:48,399][87426] Updated weights for policy 1, policy_version 296460 (0.0010) -[2023-11-28 07:58:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 151822336. Throughput: 0: 2692.5, 1: 2747.4. Samples: 151840168. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:48,445][86177] Avg episode reward: [(0, '-535.710'), (1, '-606.330')] -[2023-11-28 07:58:48,580][87424] Updated weights for policy 0, policy_version 296639 (0.0008) -[2023-11-28 07:58:48,776][87426] Updated weights for policy 1, policy_version 296470 (0.0010) -[2023-11-28 07:58:49,154][87426] Updated weights for policy 1, policy_version 296480 (0.0008) -[2023-11-28 07:58:50,959][87424] Updated weights for policy 0, policy_version 296649 (0.0011) -[2023-11-28 07:58:51,034][87426] Updated weights for policy 1, policy_version 296490 (0.0011) -[2023-11-28 07:58:51,341][87424] Updated weights for policy 0, policy_version 296659 (0.0012) -[2023-11-28 07:58:51,402][87426] Updated weights for policy 1, policy_version 296500 (0.0009) -[2023-11-28 07:58:51,723][87424] Updated weights for policy 0, policy_version 296669 (0.0012) -[2023-11-28 07:58:51,787][87426] Updated weights for policy 1, policy_version 296510 (0.0010) -[2023-11-28 07:58:53,445][86177] Fps is (10 sec: 4914.7, 60 sec: 5461.2, 300 sec: 5442.8). Total num frames: 151855104. Throughput: 0: 2657.8, 1: 2765.5. Samples: 151872764. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:53,446][86177] Avg episode reward: [(0, '-556.770'), (1, '-568.560')] -[2023-11-28 07:58:53,991][87426] Updated weights for policy 1, policy_version 296520 (0.0011) -[2023-11-28 07:58:54,146][87424] Updated weights for policy 0, policy_version 296679 (0.0010) -[2023-11-28 07:58:54,365][87426] Updated weights for policy 1, policy_version 296530 (0.0012) -[2023-11-28 07:58:54,523][87424] Updated weights for policy 0, policy_version 296689 (0.0011) -[2023-11-28 07:58:54,745][87426] Updated weights for policy 1, policy_version 296540 (0.0012) -[2023-11-28 07:58:54,911][87424] Updated weights for policy 0, policy_version 296699 (0.0011) -[2023-11-28 07:58:57,003][87426] Updated weights for policy 1, policy_version 296550 (0.0011) -[2023-11-28 07:58:57,180][87424] Updated weights for policy 0, policy_version 296709 (0.0008) -[2023-11-28 07:58:57,384][87426] Updated weights for policy 1, policy_version 296560 (0.0012) -[2023-11-28 07:58:57,564][87424] Updated weights for policy 0, policy_version 296719 (0.0008) -[2023-11-28 07:58:57,759][87426] Updated weights for policy 1, policy_version 296570 (0.0010) -[2023-11-28 07:58:57,947][87424] Updated weights for policy 0, policy_version 296729 (0.0009) -[2023-11-28 07:58:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 151887872. Throughput: 0: 2658.5, 1: 2752.7. Samples: 151897288. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:58:58,446][86177] Avg episode reward: [(0, '-560.890'), (1, '-590.650')] -[2023-11-28 07:59:00,022][87424] Updated weights for policy 0, policy_version 296739 (0.0010) -[2023-11-28 07:59:00,241][87426] Updated weights for policy 1, policy_version 296580 (0.0009) -[2023-11-28 07:59:00,403][87424] Updated weights for policy 0, policy_version 296749 (0.0008) -[2023-11-28 07:59:00,610][87426] Updated weights for policy 1, policy_version 296590 (0.0010) -[2023-11-28 07:59:00,792][87424] Updated weights for policy 0, policy_version 296759 (0.0008) -[2023-11-28 07:59:00,992][87426] Updated weights for policy 1, policy_version 296600 (0.0008) -[2023-11-28 07:59:02,869][87424] Updated weights for policy 0, policy_version 296769 (0.0008) -[2023-11-28 07:59:03,031][87426] Updated weights for policy 1, policy_version 296610 (0.0007) -[2023-11-28 07:59:03,246][87424] Updated weights for policy 0, policy_version 296779 (0.0011) -[2023-11-28 07:59:03,409][87426] Updated weights for policy 1, policy_version 296620 (0.0007) -[2023-11-28 07:59:03,444][86177] Fps is (10 sec: 4915.8, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 151904256. Throughput: 0: 2657.3, 1: 2738.8. Samples: 151921568. Policy #0 lag: (min: 29.0, avg: 48.6, max: 70.0) -[2023-11-28 07:59:03,445][86177] Avg episode reward: [(0, '-632.180'), (1, '-578.960')] -[2023-11-28 07:59:03,628][87424] Updated weights for policy 0, policy_version 296789 (0.0008) -[2023-11-28 07:59:03,788][87426] Updated weights for policy 1, policy_version 296630 (0.0008) -[2023-11-28 07:59:04,018][87424] Updated weights for policy 0, policy_version 296799 (0.0008) -[2023-11-28 07:59:04,172][87426] Updated weights for policy 1, policy_version 296640 (0.0010) -[2023-11-28 07:59:05,921][87426] Updated weights for policy 1, policy_version 296650 (0.0009) -[2023-11-28 07:59:06,298][87426] Updated weights for policy 1, policy_version 296660 (0.0007) -[2023-11-28 07:59:06,574][87424] Updated weights for policy 0, policy_version 296809 (0.0008) -[2023-11-28 07:59:06,680][87426] Updated weights for policy 1, policy_version 296670 (0.0008) -[2023-11-28 07:59:06,953][87424] Updated weights for policy 0, policy_version 296819 (0.0008) -[2023-11-28 07:59:07,329][87424] Updated weights for policy 0, policy_version 296829 (0.0009) -[2023-11-28 07:59:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 151937024. Throughput: 0: 2625.7, 1: 2758.7. Samples: 151953944. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:08,445][86177] Avg episode reward: [(0, '-624.790'), (1, '-565.040')] -[2023-11-28 07:59:08,653][87426] Updated weights for policy 1, policy_version 296680 (0.0011) -[2023-11-28 07:59:09,033][87426] Updated weights for policy 1, policy_version 296690 (0.0012) -[2023-11-28 07:59:09,411][87426] Updated weights for policy 1, policy_version 296700 (0.0011) -[2023-11-28 07:59:09,492][87424] Updated weights for policy 0, policy_version 296839 (0.0010) -[2023-11-28 07:59:09,870][87424] Updated weights for policy 0, policy_version 296849 (0.0012) -[2023-11-28 07:59:10,252][87424] Updated weights for policy 0, policy_version 296859 (0.0012) -[2023-11-28 07:59:11,985][87426] Updated weights for policy 1, policy_version 296710 (0.0011) -[2023-11-28 07:59:12,146][87424] Updated weights for policy 0, policy_version 296869 (0.0010) -[2023-11-28 07:59:12,359][87426] Updated weights for policy 1, policy_version 296720 (0.0011) -[2023-11-28 07:59:12,530][87424] Updated weights for policy 0, policy_version 296879 (0.0010) -[2023-11-28 07:59:12,744][87426] Updated weights for policy 1, policy_version 296730 (0.0011) -[2023-11-28 07:59:12,908][87424] Updated weights for policy 0, policy_version 296889 (0.0011) -[2023-11-28 07:59:13,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 151969792. Throughput: 0: 2654.2, 1: 2718.6. Samples: 151978524. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:13,446][86177] Avg episode reward: [(0, '-629.870'), (1, '-574.090')] -[2023-11-28 07:59:15,140][87424] Updated weights for policy 0, policy_version 296899 (0.0008) -[2023-11-28 07:59:15,160][87426] Updated weights for policy 1, policy_version 296740 (0.0012) -[2023-11-28 07:59:15,518][87424] Updated weights for policy 0, policy_version 296909 (0.0010) -[2023-11-28 07:59:15,535][87426] Updated weights for policy 1, policy_version 296750 (0.0011) -[2023-11-28 07:59:15,896][87424] Updated weights for policy 0, policy_version 296919 (0.0012) -[2023-11-28 07:59:15,911][87426] Updated weights for policy 1, policy_version 296760 (0.0009) -[2023-11-28 07:59:17,884][87424] Updated weights for policy 0, policy_version 296929 (0.0011) -[2023-11-28 07:59:17,951][87426] Updated weights for policy 1, policy_version 296770 (0.0008) -[2023-11-28 07:59:18,267][87424] Updated weights for policy 0, policy_version 296939 (0.0012) -[2023-11-28 07:59:18,316][87426] Updated weights for policy 1, policy_version 296780 (0.0011) -[2023-11-28 07:59:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 151986176. Throughput: 0: 2654.4, 1: 2715.7. Samples: 152002932. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:18,445][86177] Avg episode reward: [(0, '-607.160'), (1, '-589.670')] -[2023-11-28 07:59:18,649][87424] Updated weights for policy 0, policy_version 296949 (0.0012) -[2023-11-28 07:59:18,696][87426] Updated weights for policy 1, policy_version 296790 (0.0011) -[2023-11-28 07:59:19,028][87424] Updated weights for policy 0, policy_version 296959 (0.0012) -[2023-11-28 07:59:19,071][87426] Updated weights for policy 1, policy_version 296800 (0.0012) -[2023-11-28 07:59:20,778][87424] Updated weights for policy 0, policy_version 296969 (0.0012) -[2023-11-28 07:59:21,171][87424] Updated weights for policy 0, policy_version 296979 (0.0012) -[2023-11-28 07:59:21,486][87426] Updated weights for policy 1, policy_version 296810 (0.0009) -[2023-11-28 07:59:21,544][87424] Updated weights for policy 0, policy_version 296989 (0.0012) -[2023-11-28 07:59:21,863][87426] Updated weights for policy 1, policy_version 296820 (0.0011) -[2023-11-28 07:59:22,251][87426] Updated weights for policy 1, policy_version 296830 (0.0012) -[2023-11-28 07:59:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 152018944. Throughput: 0: 2681.8, 1: 2717.4. Samples: 152035176. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:23,445][86177] Avg episode reward: [(0, '-609.430'), (1, '-568.260')] -[2023-11-28 07:59:23,989][87424] Updated weights for policy 0, policy_version 296999 (0.0011) -[2023-11-28 07:59:24,316][87426] Updated weights for policy 1, policy_version 296840 (0.0011) -[2023-11-28 07:59:24,371][87424] Updated weights for policy 0, policy_version 297009 (0.0012) -[2023-11-28 07:59:24,698][87426] Updated weights for policy 1, policy_version 296850 (0.0011) -[2023-11-28 07:59:24,772][87424] Updated weights for policy 0, policy_version 297019 (0.0010) -[2023-11-28 07:59:25,072][87426] Updated weights for policy 1, policy_version 296860 (0.0011) -[2023-11-28 07:59:26,599][87424] Updated weights for policy 0, policy_version 297029 (0.0012) -[2023-11-28 07:59:26,994][87424] Updated weights for policy 0, policy_version 297039 (0.0007) -[2023-11-28 07:59:27,384][87424] Updated weights for policy 0, policy_version 297049 (0.0007) -[2023-11-28 07:59:27,502][87426] Updated weights for policy 1, policy_version 296870 (0.0009) -[2023-11-28 07:59:27,899][87426] Updated weights for policy 1, policy_version 296880 (0.0007) -[2023-11-28 07:59:28,268][87426] Updated weights for policy 1, policy_version 296890 (0.0008) -[2023-11-28 07:59:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 152043520. Throughput: 0: 2702.9, 1: 2710.0. Samples: 152059728. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:28,445][86177] Avg episode reward: [(0, '-535.010'), (1, '-626.890')] -[2023-11-28 07:59:29,864][87424] Updated weights for policy 0, policy_version 297059 (0.0009) -[2023-11-28 07:59:30,234][87424] Updated weights for policy 0, policy_version 297069 (0.0012) -[2023-11-28 07:59:30,614][87424] Updated weights for policy 0, policy_version 297079 (0.0011) -[2023-11-28 07:59:30,648][87426] Updated weights for policy 1, policy_version 296900 (0.0009) -[2023-11-28 07:59:31,023][87426] Updated weights for policy 1, policy_version 296910 (0.0009) -[2023-11-28 07:59:31,407][87426] Updated weights for policy 1, policy_version 296920 (0.0008) -[2023-11-28 07:59:32,554][87424] Updated weights for policy 0, policy_version 297089 (0.0009) -[2023-11-28 07:59:32,934][87424] Updated weights for policy 0, policy_version 297099 (0.0008) -[2023-11-28 07:59:33,315][87424] Updated weights for policy 0, policy_version 297109 (0.0007) -[2023-11-28 07:59:33,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 152068096. Throughput: 0: 2705.2, 1: 2722.6. Samples: 152084424. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:33,446][86177] Avg episode reward: [(0, '-537.680'), (1, '-625.150')] -[2023-11-28 07:59:33,657][87426] Updated weights for policy 1, policy_version 296930 (0.0009) -[2023-11-28 07:59:33,701][87424] Updated weights for policy 0, policy_version 297119 (0.0007) -[2023-11-28 07:59:34,031][87426] Updated weights for policy 1, policy_version 296940 (0.0011) -[2023-11-28 07:59:34,407][87426] Updated weights for policy 1, policy_version 296950 (0.0011) -[2023-11-28 07:59:34,786][87426] Updated weights for policy 1, policy_version 296960 (0.0012) -[2023-11-28 07:59:35,768][87424] Updated weights for policy 0, policy_version 297129 (0.0008) -[2023-11-28 07:59:36,151][87424] Updated weights for policy 0, policy_version 297139 (0.0008) -[2023-11-28 07:59:36,537][87424] Updated weights for policy 0, policy_version 297149 (0.0007) -[2023-11-28 07:59:37,206][87426] Updated weights for policy 1, policy_version 296970 (0.0009) -[2023-11-28 07:59:37,578][87426] Updated weights for policy 1, policy_version 296980 (0.0010) -[2023-11-28 07:59:37,967][87426] Updated weights for policy 1, policy_version 296990 (0.0011) -[2023-11-28 07:59:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 152100864. Throughput: 0: 2764.8, 1: 2676.0. Samples: 152117592. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:38,445][86177] Avg episode reward: [(0, '-541.970'), (1, '-633.970')] -[2023-11-28 07:59:38,638][87424] Updated weights for policy 0, policy_version 297159 (0.0011) -[2023-11-28 07:59:39,027][87424] Updated weights for policy 0, policy_version 297169 (0.0011) -[2023-11-28 07:59:39,414][87424] Updated weights for policy 0, policy_version 297179 (0.0012) -[2023-11-28 07:59:40,558][87426] Updated weights for policy 1, policy_version 297000 (0.0011) -[2023-11-28 07:59:40,940][87426] Updated weights for policy 1, policy_version 297010 (0.0012) -[2023-11-28 07:59:41,313][87426] Updated weights for policy 1, policy_version 297020 (0.0012) -[2023-11-28 07:59:41,535][87424] Updated weights for policy 0, policy_version 297189 (0.0012) -[2023-11-28 07:59:41,911][87424] Updated weights for policy 0, policy_version 297199 (0.0012) -[2023-11-28 07:59:42,290][87424] Updated weights for policy 0, policy_version 297209 (0.0012) -[2023-11-28 07:59:43,357][87426] Updated weights for policy 1, policy_version 297030 (0.0011) -[2023-11-28 07:59:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 152125440. Throughput: 0: 2760.6, 1: 2668.5. Samples: 152141600. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:43,446][86177] Avg episode reward: [(0, '-547.960'), (1, '-621.720')] -[2023-11-28 07:59:43,739][87426] Updated weights for policy 1, policy_version 297040 (0.0009) -[2023-11-28 07:59:44,119][87426] Updated weights for policy 1, policy_version 297050 (0.0007) -[2023-11-28 07:59:44,590][87424] Updated weights for policy 0, policy_version 297219 (0.0012) -[2023-11-28 07:59:44,975][87424] Updated weights for policy 0, policy_version 297229 (0.0012) -[2023-11-28 07:59:45,367][87424] Updated weights for policy 0, policy_version 297239 (0.0011) -[2023-11-28 07:59:46,432][87426] Updated weights for policy 1, policy_version 297060 (0.0008) -[2023-11-28 07:59:46,797][87426] Updated weights for policy 1, policy_version 297070 (0.0007) -[2023-11-28 07:59:47,177][87426] Updated weights for policy 1, policy_version 297080 (0.0007) -[2023-11-28 07:59:47,840][87424] Updated weights for policy 0, policy_version 297249 (0.0008) -[2023-11-28 07:59:48,220][87424] Updated weights for policy 0, policy_version 297259 (0.0012) -[2023-11-28 07:59:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 152150016. Throughput: 0: 2758.2, 1: 2668.0. Samples: 152165748. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:48,446][86177] Avg episode reward: [(0, '-656.490'), (1, '-612.260')] -[2023-11-28 07:59:48,594][87424] Updated weights for policy 0, policy_version 297269 (0.0012) -[2023-11-28 07:59:48,975][87424] Updated weights for policy 0, policy_version 297279 (0.0012) -[2023-11-28 07:59:49,532][87426] Updated weights for policy 1, policy_version 297090 (0.0008) -[2023-11-28 07:59:49,908][87426] Updated weights for policy 1, policy_version 297100 (0.0012) -[2023-11-28 07:59:50,290][87426] Updated weights for policy 1, policy_version 297110 (0.0007) -[2023-11-28 07:59:50,667][87426] Updated weights for policy 1, policy_version 297120 (0.0009) -[2023-11-28 07:59:51,100][87424] Updated weights for policy 0, policy_version 297289 (0.0009) -[2023-11-28 07:59:51,486][87424] Updated weights for policy 0, policy_version 297299 (0.0008) -[2023-11-28 07:59:51,855][87424] Updated weights for policy 0, policy_version 297309 (0.0009) -[2023-11-28 07:59:53,061][87426] Updated weights for policy 1, policy_version 297130 (0.0012) -[2023-11-28 07:59:53,441][87426] Updated weights for policy 1, policy_version 297140 (0.0012) -[2023-11-28 07:59:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.9, 300 sec: 5442.8). Total num frames: 152174592. Throughput: 0: 2779.4, 1: 2631.6. Samples: 152197440. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:53,445][86177] Avg episode reward: [(0, '-699.850'), (1, '-555.530')] -[2023-11-28 07:59:53,811][87426] Updated weights for policy 1, policy_version 297150 (0.0013) -[2023-11-28 07:59:53,914][87424] Updated weights for policy 0, policy_version 297319 (0.0010) -[2023-11-28 07:59:54,282][87424] Updated weights for policy 0, policy_version 297329 (0.0007) -[2023-11-28 07:59:54,668][87424] Updated weights for policy 0, policy_version 297339 (0.0010) -[2023-11-28 07:59:56,368][87426] Updated weights for policy 1, policy_version 297160 (0.0008) -[2023-11-28 07:59:56,737][87426] Updated weights for policy 1, policy_version 297170 (0.0010) -[2023-11-28 07:59:56,751][87424] Updated weights for policy 0, policy_version 297349 (0.0008) -[2023-11-28 07:59:57,114][87426] Updated weights for policy 1, policy_version 297180 (0.0009) -[2023-11-28 07:59:57,131][87424] Updated weights for policy 0, policy_version 297359 (0.0007) -[2023-11-28 07:59:57,517][87424] Updated weights for policy 0, policy_version 297369 (0.0007) -[2023-11-28 07:59:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 152207360. Throughput: 0: 2767.3, 1: 2616.3. Samples: 152220784. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 07:59:58,445][86177] Avg episode reward: [(0, '-704.110'), (1, '-553.340')] -[2023-11-28 07:59:59,560][87426] Updated weights for policy 1, policy_version 297190 (0.0009) -[2023-11-28 07:59:59,689][87424] Updated weights for policy 0, policy_version 297379 (0.0009) -[2023-11-28 07:59:59,941][87426] Updated weights for policy 1, policy_version 297200 (0.0011) -[2023-11-28 08:00:00,071][87424] Updated weights for policy 0, policy_version 297389 (0.0010) -[2023-11-28 08:00:00,319][87426] Updated weights for policy 1, policy_version 297210 (0.0009) -[2023-11-28 08:00:00,451][87424] Updated weights for policy 0, policy_version 297399 (0.0009) -[2023-11-28 08:00:02,355][87426] Updated weights for policy 1, policy_version 297220 (0.0010) -[2023-11-28 08:00:02,599][87424] Updated weights for policy 0, policy_version 297409 (0.0011) -[2023-11-28 08:00:02,731][87426] Updated weights for policy 1, policy_version 297230 (0.0011) -[2023-11-28 08:00:02,989][87424] Updated weights for policy 0, policy_version 297419 (0.0011) -[2023-11-28 08:00:03,103][87426] Updated weights for policy 1, policy_version 297240 (0.0010) -[2023-11-28 08:00:03,370][87424] Updated weights for policy 0, policy_version 297429 (0.0011) -[2023-11-28 08:00:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 152231936. Throughput: 0: 2778.6, 1: 2613.0. Samples: 152245552. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 08:00:03,445][86177] Avg episode reward: [(0, '-760.540'), (1, '-527.190')] -[2023-11-28 08:00:03,733][87424] Updated weights for policy 0, policy_version 297439 (0.0010) -[2023-11-28 08:00:05,357][87426] Updated weights for policy 1, policy_version 297250 (0.0008) -[2023-11-28 08:00:05,742][87426] Updated weights for policy 1, policy_version 297260 (0.0008) -[2023-11-28 08:00:06,121][87426] Updated weights for policy 1, policy_version 297270 (0.0009) -[2023-11-28 08:00:06,128][87424] Updated weights for policy 0, policy_version 297449 (0.0007) -[2023-11-28 08:00:06,492][87426] Updated weights for policy 1, policy_version 297280 (0.0007) -[2023-11-28 08:00:06,514][87424] Updated weights for policy 0, policy_version 297459 (0.0007) -[2023-11-28 08:00:06,894][87424] Updated weights for policy 0, policy_version 297469 (0.0010) -[2023-11-28 08:00:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 152256512. Throughput: 0: 2760.2, 1: 2624.4. Samples: 152277480. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 08:00:08,445][86177] Avg episode reward: [(0, '-737.140'), (1, '-541.820')] -[2023-11-28 08:00:08,939][87426] Updated weights for policy 1, policy_version 297290 (0.0009) -[2023-11-28 08:00:09,183][87424] Updated weights for policy 0, policy_version 297479 (0.0011) -[2023-11-28 08:00:09,319][87426] Updated weights for policy 1, policy_version 297300 (0.0011) -[2023-11-28 08:00:09,553][87424] Updated weights for policy 0, policy_version 297489 (0.0011) -[2023-11-28 08:00:09,701][87426] Updated weights for policy 1, policy_version 297310 (0.0012) -[2023-11-28 08:00:09,940][87424] Updated weights for policy 0, policy_version 297499 (0.0012) -[2023-11-28 08:00:11,714][87426] Updated weights for policy 1, policy_version 297320 (0.0010) -[2023-11-28 08:00:12,091][87426] Updated weights for policy 1, policy_version 297330 (0.0011) -[2023-11-28 08:00:12,337][87424] Updated weights for policy 0, policy_version 297509 (0.0010) -[2023-11-28 08:00:12,469][87426] Updated weights for policy 1, policy_version 297340 (0.0012) -[2023-11-28 08:00:12,718][87424] Updated weights for policy 0, policy_version 297519 (0.0007) -[2023-11-28 08:00:13,102][87424] Updated weights for policy 0, policy_version 297529 (0.0009) -[2023-11-28 08:00:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 152289280. Throughput: 0: 2727.7, 1: 2619.3. Samples: 152300344. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 08:00:13,445][86177] Avg episode reward: [(0, '-629.590'), (1, '-553.010')] -[2023-11-28 08:00:14,961][87426] Updated weights for policy 1, policy_version 297350 (0.0010) -[2023-11-28 08:00:15,333][87426] Updated weights for policy 1, policy_version 297360 (0.0010) -[2023-11-28 08:00:15,367][87424] Updated weights for policy 0, policy_version 297539 (0.0011) -[2023-11-28 08:00:15,704][87426] Updated weights for policy 1, policy_version 297370 (0.0009) -[2023-11-28 08:00:15,747][87424] Updated weights for policy 0, policy_version 297549 (0.0012) -[2023-11-28 08:00:16,122][87424] Updated weights for policy 0, policy_version 297559 (0.0010) -[2023-11-28 08:00:18,009][87426] Updated weights for policy 1, policy_version 297380 (0.0009) -[2023-11-28 08:00:18,182][87424] Updated weights for policy 0, policy_version 297569 (0.0007) -[2023-11-28 08:00:18,404][87426] Updated weights for policy 1, policy_version 297390 (0.0008) -[2023-11-28 08:00:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 152305664. Throughput: 0: 2724.6, 1: 2607.0. Samples: 152324348. Policy #0 lag: (min: 31.0, avg: 42.0, max: 63.0) -[2023-11-28 08:00:18,445][86177] Avg episode reward: [(0, '-624.570'), (1, '-563.850')] -[2023-11-28 08:00:18,564][87424] Updated weights for policy 0, policy_version 297579 (0.0008) -[2023-11-28 08:00:18,778][87426] Updated weights for policy 1, policy_version 297400 (0.0007) -[2023-11-28 08:00:18,946][87424] Updated weights for policy 0, policy_version 297589 (0.0011) -[2023-11-28 08:00:19,082][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000297408_76136448.pth... -[2023-11-28 08:00:19,113][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000294880_75489280.pth -[2023-11-28 08:00:19,334][87424] Updated weights for policy 0, policy_version 297599 (0.0012) -[2023-11-28 08:00:19,363][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000297600_76185600.pth... -[2023-11-28 08:00:19,394][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000295040_75530240.pth -[2023-11-28 08:00:21,243][87426] Updated weights for policy 1, policy_version 297410 (0.0010) -[2023-11-28 08:00:21,629][87426] Updated weights for policy 1, policy_version 297420 (0.0011) -[2023-11-28 08:00:21,765][87424] Updated weights for policy 0, policy_version 297609 (0.0011) -[2023-11-28 08:00:22,005][87426] Updated weights for policy 1, policy_version 297430 (0.0011) -[2023-11-28 08:00:22,152][87424] Updated weights for policy 0, policy_version 297619 (0.0011) -[2023-11-28 08:00:22,383][87426] Updated weights for policy 1, policy_version 297440 (0.0011) -[2023-11-28 08:00:22,527][87424] Updated weights for policy 0, policy_version 297629 (0.0010) -[2023-11-28 08:00:23,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 152338432. Throughput: 0: 2672.5, 1: 2612.4. Samples: 152355416. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:00:23,446][86177] Avg episode reward: [(0, '-619.230'), (1, '-551.110')] -[2023-11-28 08:00:24,311][87426] Updated weights for policy 1, policy_version 297450 (0.0012) -[2023-11-28 08:00:24,690][87426] Updated weights for policy 1, policy_version 297460 (0.0012) -[2023-11-28 08:00:25,071][87426] Updated weights for policy 1, policy_version 297470 (0.0012) -[2023-11-28 08:00:25,121][87424] Updated weights for policy 0, policy_version 297639 (0.0010) -[2023-11-28 08:00:25,510][87424] Updated weights for policy 0, policy_version 297649 (0.0009) -[2023-11-28 08:00:25,882][87424] Updated weights for policy 0, policy_version 297659 (0.0008) -[2023-11-28 08:00:27,130][87426] Updated weights for policy 1, policy_version 297480 (0.0012) -[2023-11-28 08:00:27,501][87426] Updated weights for policy 1, policy_version 297490 (0.0012) -[2023-11-28 08:00:27,817][87424] Updated weights for policy 0, policy_version 297669 (0.0009) -[2023-11-28 08:00:27,875][87426] Updated weights for policy 1, policy_version 297500 (0.0011) -[2023-11-28 08:00:28,206][87424] Updated weights for policy 0, policy_version 297679 (0.0008) -[2023-11-28 08:00:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 152363008. Throughput: 0: 2665.3, 1: 2619.2. Samples: 152379400. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:00:28,445][86177] Avg episode reward: [(0, '-587.150'), (1, '-538.450')] -[2023-11-28 08:00:28,587][87424] Updated weights for policy 0, policy_version 297689 (0.0007) -[2023-11-28 08:00:29,502][87426] Updated weights for policy 1, policy_version 297510 (0.0012) -[2023-11-28 08:00:29,876][87426] Updated weights for policy 1, policy_version 297520 (0.0010) -[2023-11-28 08:00:30,250][87426] Updated weights for policy 1, policy_version 297530 (0.0009) -[2023-11-28 08:00:30,475][87424] Updated weights for policy 0, policy_version 297699 (0.0011) -[2023-11-28 08:00:30,852][87424] Updated weights for policy 0, policy_version 297709 (0.0011) -[2023-11-28 08:00:31,237][87424] Updated weights for policy 0, policy_version 297719 (0.0008) -[2023-11-28 08:00:32,647][87426] Updated weights for policy 1, policy_version 297540 (0.0010) -[2023-11-28 08:00:33,037][87426] Updated weights for policy 1, policy_version 297550 (0.0012) -[2023-11-28 08:00:33,419][87426] Updated weights for policy 1, policy_version 297560 (0.0011) -[2023-11-28 08:00:33,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 152387584. Throughput: 0: 2672.1, 1: 2622.3. Samples: 152403996. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:00:33,445][86177] Avg episode reward: [(0, '-611.650'), (1, '-527.990')] -[2023-11-28 08:00:33,626][87424] Updated weights for policy 0, policy_version 297729 (0.0008) -[2023-11-28 08:00:34,011][87424] Updated weights for policy 0, policy_version 297739 (0.0007) -[2023-11-28 08:00:34,400][87424] Updated weights for policy 0, policy_version 297749 (0.0008) -[2023-11-28 08:00:34,787][87424] Updated weights for policy 0, policy_version 297759 (0.0008) -[2023-11-28 08:00:35,568][87426] Updated weights for policy 1, policy_version 297570 (0.0010) -[2023-11-28 08:00:35,938][87426] Updated weights for policy 1, policy_version 297580 (0.0011) -[2023-11-28 08:00:36,313][87426] Updated weights for policy 1, policy_version 297590 (0.0009) -[2023-11-28 08:00:36,685][87426] Updated weights for policy 1, policy_version 297600 (0.0011) -[2023-11-28 08:00:37,093][87424] Updated weights for policy 0, policy_version 297769 (0.0009) -[2023-11-28 08:00:37,475][87424] Updated weights for policy 0, policy_version 297779 (0.0011) -[2023-11-28 08:00:37,862][87424] Updated weights for policy 0, policy_version 297789 (0.0011) -[2023-11-28 08:00:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 152420352. Throughput: 0: 2656.2, 1: 2635.6. Samples: 152435568. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:00:38,445][86177] Avg episode reward: [(0, '-679.880'), (1, '-550.230')] -[2023-11-28 08:00:39,328][87426] Updated weights for policy 1, policy_version 297610 (0.0011) -[2023-11-28 08:00:39,710][87426] Updated weights for policy 1, policy_version 297620 (0.0012) -[2023-11-28 08:00:40,061][87424] Updated weights for policy 0, policy_version 297799 (0.0010) -[2023-11-28 08:00:40,083][87426] Updated weights for policy 1, policy_version 297630 (0.0011) -[2023-11-28 08:00:40,439][87424] Updated weights for policy 0, policy_version 297809 (0.0012) -[2023-11-28 08:00:40,810][87424] Updated weights for policy 0, policy_version 297819 (0.0012) -[2023-11-28 08:00:42,425][87426] Updated weights for policy 1, policy_version 297640 (0.0011) -[2023-11-28 08:00:42,802][87426] Updated weights for policy 1, policy_version 297650 (0.0008) -[2023-11-28 08:00:43,177][87426] Updated weights for policy 1, policy_version 297660 (0.0009) -[2023-11-28 08:00:43,430][87424] Updated weights for policy 0, policy_version 297829 (0.0011) -[2023-11-28 08:00:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 152444928. Throughput: 0: 2656.4, 1: 2654.1. Samples: 152459760. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:00:43,446][86177] Avg episode reward: [(0, '-643.870'), (1, '-544.630')] -[2023-11-28 08:00:43,813][87424] Updated weights for policy 0, policy_version 297839 (0.0012) -[2023-11-28 08:00:44,195][87424] Updated weights for policy 0, policy_version 297849 (0.0009) -[2023-11-28 08:00:45,345][87426] Updated weights for policy 1, policy_version 297670 (0.0011) -[2023-11-28 08:00:45,727][87426] Updated weights for policy 1, policy_version 297680 (0.0011) -[2023-11-28 08:00:46,103][87426] Updated weights for policy 1, policy_version 297690 (0.0008) -[2023-11-28 08:00:46,625][87424] Updated weights for policy 0, policy_version 297859 (0.0011) -[2023-11-28 08:00:47,016][87424] Updated weights for policy 0, policy_version 297869 (0.0007) -[2023-11-28 08:00:47,390][87424] Updated weights for policy 0, policy_version 297879 (0.0007) -[2023-11-28 08:00:48,099][87426] Updated weights for policy 1, policy_version 297700 (0.0007) -[2023-11-28 08:00:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 152469504. Throughput: 0: 2616.5, 1: 2667.1. Samples: 152483316. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:00:48,445][86177] Avg episode reward: [(0, '-639.880'), (1, '-554.510')] -[2023-11-28 08:00:48,479][87426] Updated weights for policy 1, policy_version 297710 (0.0007) -[2023-11-28 08:00:48,864][87426] Updated weights for policy 1, policy_version 297720 (0.0007) -[2023-11-28 08:00:49,185][87424] Updated weights for policy 0, policy_version 297889 (0.0007) -[2023-11-28 08:00:49,564][87424] Updated weights for policy 0, policy_version 297899 (0.0008) -[2023-11-28 08:00:49,937][87424] Updated weights for policy 0, policy_version 297909 (0.0009) -[2023-11-28 08:00:50,331][87424] Updated weights for policy 0, policy_version 297919 (0.0011) -[2023-11-28 08:00:51,261][87426] Updated weights for policy 1, policy_version 297730 (0.0009) -[2023-11-28 08:00:51,635][87426] Updated weights for policy 1, policy_version 297740 (0.0012) -[2023-11-28 08:00:52,013][87426] Updated weights for policy 1, policy_version 297750 (0.0011) -[2023-11-28 08:00:52,277][87424] Updated weights for policy 0, policy_version 297929 (0.0011) -[2023-11-28 08:00:52,393][87426] Updated weights for policy 1, policy_version 297760 (0.0011) -[2023-11-28 08:00:52,662][87424] Updated weights for policy 0, policy_version 297939 (0.0012) -[2023-11-28 08:00:53,043][87424] Updated weights for policy 0, policy_version 297949 (0.0011) -[2023-11-28 08:00:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 152502272. Throughput: 0: 2613.2, 1: 2665.3. Samples: 152515016. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:00:53,445][86177] Avg episode reward: [(0, '-640.320'), (1, '-562.370')] -[2023-11-28 08:00:54,730][87426] Updated weights for policy 1, policy_version 297770 (0.0009) -[2023-11-28 08:00:55,057][87424] Updated weights for policy 0, policy_version 297959 (0.0009) -[2023-11-28 08:00:55,104][87426] Updated weights for policy 1, policy_version 297780 (0.0007) -[2023-11-28 08:00:55,444][87424] Updated weights for policy 0, policy_version 297969 (0.0007) -[2023-11-28 08:00:55,478][87426] Updated weights for policy 1, policy_version 297790 (0.0008) -[2023-11-28 08:00:55,825][87424] Updated weights for policy 0, policy_version 297979 (0.0008) -[2023-11-28 08:00:57,508][87426] Updated weights for policy 1, policy_version 297800 (0.0011) -[2023-11-28 08:00:57,879][87426] Updated weights for policy 1, policy_version 297810 (0.0012) -[2023-11-28 08:00:58,248][87424] Updated weights for policy 0, policy_version 297989 (0.0011) -[2023-11-28 08:00:58,261][87426] Updated weights for policy 1, policy_version 297820 (0.0012) -[2023-11-28 08:00:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 152526848. Throughput: 0: 2641.9, 1: 2683.5. Samples: 152539988. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:00:58,446][86177] Avg episode reward: [(0, '-593.710'), (1, '-557.470')] -[2023-11-28 08:00:58,630][87424] Updated weights for policy 0, policy_version 297999 (0.0011) -[2023-11-28 08:00:59,005][87424] Updated weights for policy 0, policy_version 298009 (0.0012) -[2023-11-28 08:01:00,239][87426] Updated weights for policy 1, policy_version 297830 (0.0011) -[2023-11-28 08:01:00,616][87426] Updated weights for policy 1, policy_version 297840 (0.0012) -[2023-11-28 08:01:00,975][87424] Updated weights for policy 0, policy_version 298019 (0.0010) -[2023-11-28 08:01:00,993][87426] Updated weights for policy 1, policy_version 297850 (0.0010) -[2023-11-28 08:01:01,356][87424] Updated weights for policy 0, policy_version 298029 (0.0008) -[2023-11-28 08:01:01,740][87424] Updated weights for policy 0, policy_version 298039 (0.0009) -[2023-11-28 08:01:03,074][87426] Updated weights for policy 1, policy_version 297860 (0.0007) -[2023-11-28 08:01:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 152551424. Throughput: 0: 2672.2, 1: 2698.8. Samples: 152566040. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:01:03,445][86177] Avg episode reward: [(0, '-602.900'), (1, '-565.520')] -[2023-11-28 08:01:03,457][87426] Updated weights for policy 1, policy_version 297870 (0.0007) -[2023-11-28 08:01:03,836][87426] Updated weights for policy 1, policy_version 297880 (0.0007) -[2023-11-28 08:01:04,241][87424] Updated weights for policy 0, policy_version 298049 (0.0010) -[2023-11-28 08:01:04,630][87424] Updated weights for policy 0, policy_version 298059 (0.0011) -[2023-11-28 08:01:05,000][87424] Updated weights for policy 0, policy_version 298069 (0.0009) -[2023-11-28 08:01:05,382][87424] Updated weights for policy 0, policy_version 298079 (0.0012) -[2023-11-28 08:01:06,269][87426] Updated weights for policy 1, policy_version 297890 (0.0008) -[2023-11-28 08:01:06,659][87426] Updated weights for policy 1, policy_version 297900 (0.0012) -[2023-11-28 08:01:07,044][87426] Updated weights for policy 1, policy_version 297910 (0.0011) -[2023-11-28 08:01:07,216][87424] Updated weights for policy 0, policy_version 298089 (0.0012) -[2023-11-28 08:01:07,413][87426] Updated weights for policy 1, policy_version 297920 (0.0011) -[2023-11-28 08:01:07,601][87424] Updated weights for policy 0, policy_version 298099 (0.0011) -[2023-11-28 08:01:07,982][87424] Updated weights for policy 0, policy_version 298109 (0.0012) -[2023-11-28 08:01:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 152584192. Throughput: 0: 2699.5, 1: 2699.8. Samples: 152598384. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:01:08,445][86177] Avg episode reward: [(0, '-639.750'), (1, '-575.610')] -[2023-11-28 08:01:09,437][87426] Updated weights for policy 1, policy_version 297930 (0.0012) -[2023-11-28 08:01:09,823][87426] Updated weights for policy 1, policy_version 297940 (0.0012) -[2023-11-28 08:01:10,101][87424] Updated weights for policy 0, policy_version 298119 (0.0011) -[2023-11-28 08:01:10,203][87426] Updated weights for policy 1, policy_version 297950 (0.0011) -[2023-11-28 08:01:10,487][87424] Updated weights for policy 0, policy_version 298129 (0.0012) -[2023-11-28 08:01:10,863][87424] Updated weights for policy 0, policy_version 298139 (0.0012) -[2023-11-28 08:01:12,421][87426] Updated weights for policy 1, policy_version 297960 (0.0009) -[2023-11-28 08:01:12,803][87426] Updated weights for policy 1, policy_version 297970 (0.0008) -[2023-11-28 08:01:13,174][87426] Updated weights for policy 1, policy_version 297980 (0.0010) -[2023-11-28 08:01:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 152608768. Throughput: 0: 2722.3, 1: 2695.5. Samples: 152623204. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:01:13,445][86177] Avg episode reward: [(0, '-676.260'), (1, '-581.250')] -[2023-11-28 08:01:13,468][87424] Updated weights for policy 0, policy_version 298149 (0.0011) -[2023-11-28 08:01:13,857][87424] Updated weights for policy 0, policy_version 298159 (0.0010) -[2023-11-28 08:01:14,238][87424] Updated weights for policy 0, policy_version 298169 (0.0012) -[2023-11-28 08:01:15,053][87426] Updated weights for policy 1, policy_version 297990 (0.0008) -[2023-11-28 08:01:15,418][87426] Updated weights for policy 1, policy_version 298000 (0.0009) -[2023-11-28 08:01:15,801][87426] Updated weights for policy 1, policy_version 298010 (0.0010) -[2023-11-28 08:01:16,158][87424] Updated weights for policy 0, policy_version 298179 (0.0011) -[2023-11-28 08:01:16,543][87424] Updated weights for policy 0, policy_version 298189 (0.0008) -[2023-11-28 08:01:16,922][87424] Updated weights for policy 0, policy_version 298199 (0.0007) -[2023-11-28 08:01:18,043][87426] Updated weights for policy 1, policy_version 298020 (0.0011) -[2023-11-28 08:01:18,426][87426] Updated weights for policy 1, policy_version 298030 (0.0011) -[2023-11-28 08:01:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 152633344. Throughput: 0: 2710.7, 1: 2705.7. Samples: 152647732. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:01:18,445][86177] Avg episode reward: [(0, '-677.960'), (1, '-571.760')] -[2023-11-28 08:01:18,803][87426] Updated weights for policy 1, policy_version 298040 (0.0011) -[2023-11-28 08:01:19,372][87424] Updated weights for policy 0, policy_version 298209 (0.0008) -[2023-11-28 08:01:19,754][87424] Updated weights for policy 0, policy_version 298219 (0.0012) -[2023-11-28 08:01:20,141][87424] Updated weights for policy 0, policy_version 298229 (0.0012) -[2023-11-28 08:01:20,521][87424] Updated weights for policy 0, policy_version 298239 (0.0011) -[2023-11-28 08:01:20,554][87426] Updated weights for policy 1, policy_version 298050 (0.0011) -[2023-11-28 08:01:20,929][87426] Updated weights for policy 1, policy_version 298060 (0.0011) -[2023-11-28 08:01:21,300][87426] Updated weights for policy 1, policy_version 298070 (0.0011) -[2023-11-28 08:01:21,681][87426] Updated weights for policy 1, policy_version 298080 (0.0011) -[2023-11-28 08:01:22,860][87424] Updated weights for policy 0, policy_version 298249 (0.0010) -[2023-11-28 08:01:23,242][87424] Updated weights for policy 0, policy_version 298259 (0.0012) -[2023-11-28 08:01:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 152657920. Throughput: 0: 2706.8, 1: 2748.6. Samples: 152681064. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:01:23,445][86177] Avg episode reward: [(0, '-640.630'), (1, '-557.280')] -[2023-11-28 08:01:23,623][87424] Updated weights for policy 0, policy_version 298269 (0.0012) -[2023-11-28 08:01:23,695][87426] Updated weights for policy 1, policy_version 298090 (0.0011) -[2023-11-28 08:01:24,069][87426] Updated weights for policy 1, policy_version 298100 (0.0008) -[2023-11-28 08:01:24,453][87426] Updated weights for policy 1, policy_version 298110 (0.0007) -[2023-11-28 08:01:25,537][87424] Updated weights for policy 0, policy_version 298279 (0.0012) -[2023-11-28 08:01:25,910][87424] Updated weights for policy 0, policy_version 298289 (0.0011) -[2023-11-28 08:01:26,291][87424] Updated weights for policy 0, policy_version 298299 (0.0012) -[2023-11-28 08:01:26,351][87426] Updated weights for policy 1, policy_version 298120 (0.0011) -[2023-11-28 08:01:26,732][87426] Updated weights for policy 1, policy_version 298130 (0.0010) -[2023-11-28 08:01:27,113][87426] Updated weights for policy 1, policy_version 298140 (0.0011) -[2023-11-28 08:01:28,087][87424] Updated weights for policy 0, policy_version 298309 (0.0012) -[2023-11-28 08:01:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 152690688. Throughput: 0: 2708.5, 1: 2780.3. Samples: 152706752. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:01:28,445][86177] Avg episode reward: [(0, '-567.070'), (1, '-527.000')] -[2023-11-28 08:01:28,461][87424] Updated weights for policy 0, policy_version 298319 (0.0012) -[2023-11-28 08:01:28,829][87424] Updated weights for policy 0, policy_version 298329 (0.0009) -[2023-11-28 08:01:28,981][87426] Updated weights for policy 1, policy_version 298150 (0.0011) -[2023-11-28 08:01:29,364][87426] Updated weights for policy 1, policy_version 298160 (0.0011) -[2023-11-28 08:01:29,744][87426] Updated weights for policy 1, policy_version 298170 (0.0009) -[2023-11-28 08:01:30,878][87424] Updated weights for policy 0, policy_version 298339 (0.0010) -[2023-11-28 08:01:31,258][87424] Updated weights for policy 0, policy_version 298349 (0.0008) -[2023-11-28 08:01:31,639][87424] Updated weights for policy 0, policy_version 298359 (0.0010) -[2023-11-28 08:01:32,173][87426] Updated weights for policy 1, policy_version 298180 (0.0010) -[2023-11-28 08:01:32,554][87426] Updated weights for policy 1, policy_version 298190 (0.0008) -[2023-11-28 08:01:32,937][87426] Updated weights for policy 1, policy_version 298200 (0.0009) -[2023-11-28 08:01:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 152723456. Throughput: 0: 2742.9, 1: 2773.5. Samples: 152731556. Policy #0 lag: (min: 31.0, avg: 52.1, max: 95.0) -[2023-11-28 08:01:33,445][86177] Avg episode reward: [(0, '-539.910'), (1, '-519.740')] -[2023-11-28 08:01:33,624][87424] Updated weights for policy 0, policy_version 298369 (0.0010) -[2023-11-28 08:01:34,002][87424] Updated weights for policy 0, policy_version 298379 (0.0012) -[2023-11-28 08:01:34,392][87424] Updated weights for policy 0, policy_version 298389 (0.0011) -[2023-11-28 08:01:34,760][87424] Updated weights for policy 0, policy_version 298399 (0.0012) -[2023-11-28 08:01:35,074][87426] Updated weights for policy 1, policy_version 298210 (0.0009) -[2023-11-28 08:01:35,450][87426] Updated weights for policy 1, policy_version 298220 (0.0012) -[2023-11-28 08:01:35,822][87426] Updated weights for policy 1, policy_version 298230 (0.0012) -[2023-11-28 08:01:36,193][87426] Updated weights for policy 1, policy_version 298240 (0.0012) -[2023-11-28 08:01:36,475][87424] Updated weights for policy 0, policy_version 298409 (0.0012) -[2023-11-28 08:01:36,864][87424] Updated weights for policy 0, policy_version 298419 (0.0012) -[2023-11-28 08:01:37,247][87424] Updated weights for policy 0, policy_version 298429 (0.0012) -[2023-11-28 08:01:38,218][87426] Updated weights for policy 1, policy_version 298250 (0.0012) -[2023-11-28 08:01:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 152748032. Throughput: 0: 2776.1, 1: 2794.4. Samples: 152765688. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:01:38,445][86177] Avg episode reward: [(0, '-578.220'), (1, '-531.040')] -[2023-11-28 08:01:38,600][87426] Updated weights for policy 1, policy_version 298260 (0.0012) -[2023-11-28 08:01:38,978][87426] Updated weights for policy 1, policy_version 298270 (0.0011) -[2023-11-28 08:01:39,278][87424] Updated weights for policy 0, policy_version 298439 (0.0011) -[2023-11-28 08:01:39,656][87424] Updated weights for policy 0, policy_version 298449 (0.0008) -[2023-11-28 08:01:40,040][87424] Updated weights for policy 0, policy_version 298459 (0.0010) -[2023-11-28 08:01:41,581][87426] Updated weights for policy 1, policy_version 298280 (0.0011) -[2023-11-28 08:01:41,958][87426] Updated weights for policy 1, policy_version 298290 (0.0010) -[2023-11-28 08:01:42,344][87426] Updated weights for policy 1, policy_version 298300 (0.0010) -[2023-11-28 08:01:42,544][87424] Updated weights for policy 0, policy_version 298469 (0.0010) -[2023-11-28 08:01:42,922][87424] Updated weights for policy 0, policy_version 298479 (0.0012) -[2023-11-28 08:01:43,299][87424] Updated weights for policy 0, policy_version 298489 (0.0012) -[2023-11-28 08:01:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 152772608. Throughput: 0: 2766.6, 1: 2783.8. Samples: 152789756. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:01:43,446][86177] Avg episode reward: [(0, '-576.110'), (1, '-529.880')] -[2023-11-28 08:01:44,401][87426] Updated weights for policy 1, policy_version 298310 (0.0010) -[2023-11-28 08:01:44,788][87426] Updated weights for policy 1, policy_version 298320 (0.0010) -[2023-11-28 08:01:45,169][87426] Updated weights for policy 1, policy_version 298330 (0.0007) -[2023-11-28 08:01:45,350][87424] Updated weights for policy 0, policy_version 298499 (0.0011) -[2023-11-28 08:01:45,741][87424] Updated weights for policy 0, policy_version 298509 (0.0011) -[2023-11-28 08:01:46,114][87424] Updated weights for policy 0, policy_version 298519 (0.0012) -[2023-11-28 08:01:47,083][87426] Updated weights for policy 1, policy_version 298340 (0.0011) -[2023-11-28 08:01:47,464][87426] Updated weights for policy 1, policy_version 298350 (0.0009) -[2023-11-28 08:01:47,843][87426] Updated weights for policy 1, policy_version 298360 (0.0007) -[2023-11-28 08:01:48,268][87424] Updated weights for policy 0, policy_version 298529 (0.0011) -[2023-11-28 08:01:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 152805376. Throughput: 0: 2733.1, 1: 2785.6. Samples: 152814380. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:01:48,445][86177] Avg episode reward: [(0, '-583.120'), (1, '-541.070')] -[2023-11-28 08:01:48,655][87424] Updated weights for policy 0, policy_version 298539 (0.0007) -[2023-11-28 08:01:49,040][87424] Updated weights for policy 0, policy_version 298549 (0.0008) -[2023-11-28 08:01:49,418][87424] Updated weights for policy 0, policy_version 298559 (0.0009) -[2023-11-28 08:01:50,294][87426] Updated weights for policy 1, policy_version 298370 (0.0008) -[2023-11-28 08:01:50,681][87426] Updated weights for policy 1, policy_version 298380 (0.0012) -[2023-11-28 08:01:51,052][87426] Updated weights for policy 1, policy_version 298390 (0.0012) -[2023-11-28 08:01:51,427][87424] Updated weights for policy 0, policy_version 298569 (0.0011) -[2023-11-28 08:01:51,428][87426] Updated weights for policy 1, policy_version 298400 (0.0008) -[2023-11-28 08:01:51,798][87424] Updated weights for policy 0, policy_version 298579 (0.0012) -[2023-11-28 08:01:52,177][87424] Updated weights for policy 0, policy_version 298589 (0.0011) -[2023-11-28 08:01:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 152829952. Throughput: 0: 2723.4, 1: 2769.8. Samples: 152845576. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:01:53,446][86177] Avg episode reward: [(0, '-579.550'), (1, '-534.720')] -[2023-11-28 08:01:53,979][87426] Updated weights for policy 1, policy_version 298410 (0.0011) -[2023-11-28 08:01:54,369][87426] Updated weights for policy 1, policy_version 298420 (0.0010) -[2023-11-28 08:01:54,482][87424] Updated weights for policy 0, policy_version 298599 (0.0010) -[2023-11-28 08:01:54,752][87426] Updated weights for policy 1, policy_version 298430 (0.0008) -[2023-11-28 08:01:54,858][87424] Updated weights for policy 0, policy_version 298609 (0.0011) -[2023-11-28 08:01:55,249][87424] Updated weights for policy 0, policy_version 298619 (0.0012) -[2023-11-28 08:01:57,218][87426] Updated weights for policy 1, policy_version 298440 (0.0008) -[2023-11-28 08:01:57,603][87426] Updated weights for policy 1, policy_version 298450 (0.0007) -[2023-11-28 08:01:57,796][87424] Updated weights for policy 0, policy_version 298629 (0.0012) -[2023-11-28 08:01:57,989][87426] Updated weights for policy 1, policy_version 298460 (0.0009) -[2023-11-28 08:01:58,176][87424] Updated weights for policy 0, policy_version 298639 (0.0008) -[2023-11-28 08:01:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 152854528. Throughput: 0: 2707.1, 1: 2770.3. Samples: 152869688. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:01:58,446][86177] Avg episode reward: [(0, '-557.820'), (1, '-527.290')] -[2023-11-28 08:01:58,560][87424] Updated weights for policy 0, policy_version 298649 (0.0008) -[2023-11-28 08:02:00,185][87426] Updated weights for policy 1, policy_version 298470 (0.0009) -[2023-11-28 08:02:00,565][87426] Updated weights for policy 1, policy_version 298480 (0.0010) -[2023-11-28 08:02:00,872][87424] Updated weights for policy 0, policy_version 298659 (0.0009) -[2023-11-28 08:02:00,939][87426] Updated weights for policy 1, policy_version 298490 (0.0011) -[2023-11-28 08:02:01,261][87424] Updated weights for policy 0, policy_version 298669 (0.0008) -[2023-11-28 08:02:01,639][87424] Updated weights for policy 0, policy_version 298679 (0.0009) -[2023-11-28 08:02:03,126][87426] Updated weights for policy 1, policy_version 298500 (0.0009) -[2023-11-28 08:02:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 152879104. Throughput: 0: 2692.4, 1: 2750.4. Samples: 152892660. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:03,446][86177] Avg episode reward: [(0, '-623.290'), (1, '-518.310')] -[2023-11-28 08:02:03,505][87426] Updated weights for policy 1, policy_version 298510 (0.0012) -[2023-11-28 08:02:03,880][87426] Updated weights for policy 1, policy_version 298520 (0.0012) -[2023-11-28 08:02:04,039][87424] Updated weights for policy 0, policy_version 298689 (0.0012) -[2023-11-28 08:02:04,422][87424] Updated weights for policy 0, policy_version 298699 (0.0008) -[2023-11-28 08:02:04,805][87424] Updated weights for policy 0, policy_version 298709 (0.0011) -[2023-11-28 08:02:05,184][87424] Updated weights for policy 0, policy_version 298719 (0.0011) -[2023-11-28 08:02:05,802][87426] Updated weights for policy 1, policy_version 298530 (0.0012) -[2023-11-28 08:02:06,182][87426] Updated weights for policy 1, policy_version 298540 (0.0012) -[2023-11-28 08:02:06,555][87426] Updated weights for policy 1, policy_version 298550 (0.0012) -[2023-11-28 08:02:06,932][87426] Updated weights for policy 1, policy_version 298560 (0.0011) -[2023-11-28 08:02:07,333][87424] Updated weights for policy 0, policy_version 298729 (0.0012) -[2023-11-28 08:02:07,719][87424] Updated weights for policy 0, policy_version 298739 (0.0012) -[2023-11-28 08:02:08,103][87424] Updated weights for policy 0, policy_version 298749 (0.0012) -[2023-11-28 08:02:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 152911872. Throughput: 0: 2707.0, 1: 2722.0. Samples: 152925372. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:08,445][86177] Avg episode reward: [(0, '-619.860'), (1, '-507.540')] -[2023-11-28 08:02:09,301][87426] Updated weights for policy 1, policy_version 298570 (0.0007) -[2023-11-28 08:02:09,681][87426] Updated weights for policy 1, policy_version 298580 (0.0007) -[2023-11-28 08:02:10,071][87426] Updated weights for policy 1, policy_version 298590 (0.0011) -[2023-11-28 08:02:10,589][87424] Updated weights for policy 0, policy_version 298759 (0.0010) -[2023-11-28 08:02:10,970][87424] Updated weights for policy 0, policy_version 298769 (0.0010) -[2023-11-28 08:02:11,363][87424] Updated weights for policy 0, policy_version 298779 (0.0011) -[2023-11-28 08:02:12,038][87426] Updated weights for policy 1, policy_version 298600 (0.0010) -[2023-11-28 08:02:12,411][87426] Updated weights for policy 1, policy_version 298610 (0.0009) -[2023-11-28 08:02:12,798][87426] Updated weights for policy 1, policy_version 298620 (0.0008) -[2023-11-28 08:02:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 152936448. Throughput: 0: 2692.7, 1: 2689.7. Samples: 152948960. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:13,445][86177] Avg episode reward: [(0, '-626.710'), (1, '-511.070')] -[2023-11-28 08:02:13,887][87424] Updated weights for policy 0, policy_version 298789 (0.0009) -[2023-11-28 08:02:14,273][87424] Updated weights for policy 0, policy_version 298799 (0.0008) -[2023-11-28 08:02:14,650][87424] Updated weights for policy 0, policy_version 298809 (0.0007) -[2023-11-28 08:02:15,207][87426] Updated weights for policy 1, policy_version 298630 (0.0011) -[2023-11-28 08:02:15,591][87426] Updated weights for policy 1, policy_version 298640 (0.0011) -[2023-11-28 08:02:15,976][87426] Updated weights for policy 1, policy_version 298650 (0.0011) -[2023-11-28 08:02:17,048][87424] Updated weights for policy 0, policy_version 298819 (0.0010) -[2023-11-28 08:02:17,427][87424] Updated weights for policy 0, policy_version 298829 (0.0011) -[2023-11-28 08:02:17,817][87424] Updated weights for policy 0, policy_version 298839 (0.0012) -[2023-11-28 08:02:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 152961024. Throughput: 0: 2654.5, 1: 2689.2. Samples: 152972020. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:18,445][86177] Avg episode reward: [(0, '-618.450'), (1, '-510.130')] -[2023-11-28 08:02:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000298848_76505088.pth... -[2023-11-28 08:02:18,485][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000296320_75857920.pth -[2023-11-28 08:02:18,542][87426] Updated weights for policy 1, policy_version 298660 (0.0010) -[2023-11-28 08:02:18,913][87426] Updated weights for policy 1, policy_version 298670 (0.0012) -[2023-11-28 08:02:19,289][87426] Updated weights for policy 1, policy_version 298680 (0.0012) -[2023-11-28 08:02:19,592][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000298688_76464128.pth... -[2023-11-28 08:02:19,638][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000296160_75816960.pth -[2023-11-28 08:02:19,656][87424] Updated weights for policy 0, policy_version 298849 (0.0012) -[2023-11-28 08:02:20,039][87424] Updated weights for policy 0, policy_version 298859 (0.0011) -[2023-11-28 08:02:20,425][87424] Updated weights for policy 0, policy_version 298869 (0.0007) -[2023-11-28 08:02:20,798][87424] Updated weights for policy 0, policy_version 298879 (0.0008) -[2023-11-28 08:02:21,357][87426] Updated weights for policy 1, policy_version 298690 (0.0012) -[2023-11-28 08:02:21,726][87426] Updated weights for policy 1, policy_version 298700 (0.0011) -[2023-11-28 08:02:22,105][87426] Updated weights for policy 1, policy_version 298710 (0.0011) -[2023-11-28 08:02:22,480][87426] Updated weights for policy 1, policy_version 298720 (0.0011) -[2023-11-28 08:02:23,173][87424] Updated weights for policy 0, policy_version 298889 (0.0009) -[2023-11-28 08:02:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 152985600. Throughput: 0: 2641.7, 1: 2654.6. Samples: 153004020. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:23,445][86177] Avg episode reward: [(0, '-578.100'), (1, '-516.000')] -[2023-11-28 08:02:23,565][87424] Updated weights for policy 0, policy_version 298899 (0.0007) -[2023-11-28 08:02:23,932][87424] Updated weights for policy 0, policy_version 298909 (0.0008) -[2023-11-28 08:02:24,655][87426] Updated weights for policy 1, policy_version 298730 (0.0012) -[2023-11-28 08:02:25,035][87426] Updated weights for policy 1, policy_version 298740 (0.0012) -[2023-11-28 08:02:25,421][87426] Updated weights for policy 1, policy_version 298750 (0.0008) -[2023-11-28 08:02:26,501][87424] Updated weights for policy 0, policy_version 298919 (0.0009) -[2023-11-28 08:02:26,889][87424] Updated weights for policy 0, policy_version 298929 (0.0008) -[2023-11-28 08:02:27,265][87424] Updated weights for policy 0, policy_version 298939 (0.0007) -[2023-11-28 08:02:27,901][87426] Updated weights for policy 1, policy_version 298760 (0.0011) -[2023-11-28 08:02:28,286][87426] Updated weights for policy 1, policy_version 298770 (0.0012) -[2023-11-28 08:02:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153010176. Throughput: 0: 2637.7, 1: 2649.5. Samples: 153027680. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:28,445][86177] Avg episode reward: [(0, '-554.020'), (1, '-521.010')] -[2023-11-28 08:02:28,661][87426] Updated weights for policy 1, policy_version 298780 (0.0011) -[2023-11-28 08:02:28,946][87424] Updated weights for policy 0, policy_version 298949 (0.0008) -[2023-11-28 08:02:29,321][87424] Updated weights for policy 0, policy_version 298959 (0.0009) -[2023-11-28 08:02:29,706][87424] Updated weights for policy 0, policy_version 298969 (0.0009) -[2023-11-28 08:02:30,466][87426] Updated weights for policy 1, policy_version 298790 (0.0012) -[2023-11-28 08:02:30,847][87426] Updated weights for policy 1, policy_version 298800 (0.0012) -[2023-11-28 08:02:31,220][87426] Updated weights for policy 1, policy_version 298810 (0.0012) -[2023-11-28 08:02:31,802][87424] Updated weights for policy 0, policy_version 298979 (0.0010) -[2023-11-28 08:02:32,180][87424] Updated weights for policy 0, policy_version 298989 (0.0009) -[2023-11-28 08:02:32,560][87424] Updated weights for policy 0, policy_version 298999 (0.0009) -[2023-11-28 08:02:33,268][87426] Updated weights for policy 1, policy_version 298820 (0.0011) -[2023-11-28 08:02:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153042944. Throughput: 0: 2678.5, 1: 2635.6. Samples: 153053516. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:33,445][86177] Avg episode reward: [(0, '-606.350'), (1, '-529.480')] -[2023-11-28 08:02:33,651][87426] Updated weights for policy 1, policy_version 298830 (0.0009) -[2023-11-28 08:02:34,029][87426] Updated weights for policy 1, policy_version 298840 (0.0007) -[2023-11-28 08:02:34,971][87424] Updated weights for policy 0, policy_version 299009 (0.0009) -[2023-11-28 08:02:35,358][87424] Updated weights for policy 0, policy_version 299019 (0.0011) -[2023-11-28 08:02:35,746][87424] Updated weights for policy 0, policy_version 299029 (0.0010) -[2023-11-28 08:02:36,132][87424] Updated weights for policy 0, policy_version 299039 (0.0012) -[2023-11-28 08:02:36,395][87426] Updated weights for policy 1, policy_version 298850 (0.0008) -[2023-11-28 08:02:36,767][87426] Updated weights for policy 1, policy_version 298860 (0.0009) -[2023-11-28 08:02:37,149][87426] Updated weights for policy 1, policy_version 298870 (0.0009) -[2023-11-28 08:02:37,529][87426] Updated weights for policy 1, policy_version 298880 (0.0008) -[2023-11-28 08:02:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153067520. Throughput: 0: 2669.8, 1: 2656.2. Samples: 153085244. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:38,445][86177] Avg episode reward: [(0, '-590.240'), (1, '-525.880')] -[2023-11-28 08:02:38,534][87424] Updated weights for policy 0, policy_version 299049 (0.0009) -[2023-11-28 08:02:38,903][87424] Updated weights for policy 0, policy_version 299059 (0.0008) -[2023-11-28 08:02:39,278][87424] Updated weights for policy 0, policy_version 299069 (0.0012) -[2023-11-28 08:02:39,572][87426] Updated weights for policy 1, policy_version 298890 (0.0011) -[2023-11-28 08:02:39,958][87426] Updated weights for policy 1, policy_version 298900 (0.0012) -[2023-11-28 08:02:40,326][87426] Updated weights for policy 1, policy_version 298910 (0.0012) -[2023-11-28 08:02:41,793][87424] Updated weights for policy 0, policy_version 299079 (0.0011) -[2023-11-28 08:02:42,181][87424] Updated weights for policy 0, policy_version 299089 (0.0009) -[2023-11-28 08:02:42,566][87424] Updated weights for policy 0, policy_version 299099 (0.0011) -[2023-11-28 08:02:42,696][87426] Updated weights for policy 1, policy_version 298920 (0.0012) -[2023-11-28 08:02:43,077][87426] Updated weights for policy 1, policy_version 298930 (0.0011) -[2023-11-28 08:02:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153092096. Throughput: 0: 2665.2, 1: 2640.5. Samples: 153108448. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:43,445][86177] Avg episode reward: [(0, '-615.050'), (1, '-520.920')] -[2023-11-28 08:02:43,462][87426] Updated weights for policy 1, policy_version 298940 (0.0011) -[2023-11-28 08:02:44,706][87424] Updated weights for policy 0, policy_version 299109 (0.0008) -[2023-11-28 08:02:45,076][87424] Updated weights for policy 0, policy_version 299119 (0.0007) -[2023-11-28 08:02:45,457][87424] Updated weights for policy 0, policy_version 299129 (0.0008) -[2023-11-28 08:02:45,765][87426] Updated weights for policy 1, policy_version 298950 (0.0010) -[2023-11-28 08:02:46,139][87426] Updated weights for policy 1, policy_version 298960 (0.0007) -[2023-11-28 08:02:46,522][87426] Updated weights for policy 1, policy_version 298970 (0.0007) -[2023-11-28 08:02:47,526][87424] Updated weights for policy 0, policy_version 299139 (0.0011) -[2023-11-28 08:02:47,902][87424] Updated weights for policy 0, policy_version 299149 (0.0011) -[2023-11-28 08:02:48,288][87424] Updated weights for policy 0, policy_version 299159 (0.0010) -[2023-11-28 08:02:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 153116672. Throughput: 0: 2679.7, 1: 2671.3. Samples: 153133452. Policy #0 lag: (min: 23.0, avg: 40.0, max: 64.0) -[2023-11-28 08:02:48,445][86177] Avg episode reward: [(0, '-616.890'), (1, '-524.520')] -[2023-11-28 08:02:48,927][87426] Updated weights for policy 1, policy_version 298980 (0.0010) -[2023-11-28 08:02:49,303][87426] Updated weights for policy 1, policy_version 298990 (0.0011) -[2023-11-28 08:02:49,669][87426] Updated weights for policy 1, policy_version 299000 (0.0011) -[2023-11-28 08:02:50,775][87424] Updated weights for policy 0, policy_version 299169 (0.0010) -[2023-11-28 08:02:51,161][87424] Updated weights for policy 0, policy_version 299179 (0.0009) -[2023-11-28 08:02:51,554][87424] Updated weights for policy 0, policy_version 299189 (0.0009) -[2023-11-28 08:02:51,943][87424] Updated weights for policy 0, policy_version 299199 (0.0011) -[2023-11-28 08:02:52,075][87426] Updated weights for policy 1, policy_version 299010 (0.0009) -[2023-11-28 08:02:52,446][87426] Updated weights for policy 1, policy_version 299020 (0.0012) -[2023-11-28 08:02:52,834][87426] Updated weights for policy 1, policy_version 299030 (0.0012) -[2023-11-28 08:02:53,207][87426] Updated weights for policy 1, policy_version 299040 (0.0011) -[2023-11-28 08:02:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 153149440. Throughput: 0: 2671.2, 1: 2650.7. Samples: 153164856. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:02:53,445][86177] Avg episode reward: [(0, '-654.960'), (1, '-527.780')] -[2023-11-28 08:02:54,087][87424] Updated weights for policy 0, policy_version 299209 (0.0008) -[2023-11-28 08:02:54,473][87424] Updated weights for policy 0, policy_version 299219 (0.0010) -[2023-11-28 08:02:54,841][87424] Updated weights for policy 0, policy_version 299229 (0.0008) -[2023-11-28 08:02:55,485][87426] Updated weights for policy 1, policy_version 299050 (0.0009) -[2023-11-28 08:02:55,865][87426] Updated weights for policy 1, policy_version 299060 (0.0011) -[2023-11-28 08:02:56,231][87426] Updated weights for policy 1, policy_version 299070 (0.0011) -[2023-11-28 08:02:56,757][87424] Updated weights for policy 0, policy_version 299239 (0.0009) -[2023-11-28 08:02:57,131][87424] Updated weights for policy 0, policy_version 299249 (0.0009) -[2023-11-28 08:02:57,513][87424] Updated weights for policy 0, policy_version 299259 (0.0008) -[2023-11-28 08:02:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153174016. Throughput: 0: 2677.5, 1: 2661.4. Samples: 153189212. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:02:58,445][86177] Avg episode reward: [(0, '-640.870'), (1, '-527.800')] -[2023-11-28 08:02:58,635][87426] Updated weights for policy 1, policy_version 299080 (0.0011) -[2023-11-28 08:02:59,013][87426] Updated weights for policy 1, policy_version 299090 (0.0012) -[2023-11-28 08:02:59,276][87424] Updated weights for policy 0, policy_version 299269 (0.0010) -[2023-11-28 08:02:59,391][87426] Updated weights for policy 1, policy_version 299100 (0.0011) -[2023-11-28 08:02:59,650][87424] Updated weights for policy 0, policy_version 299279 (0.0012) -[2023-11-28 08:03:00,031][87424] Updated weights for policy 0, policy_version 299289 (0.0012) -[2023-11-28 08:03:01,427][87426] Updated weights for policy 1, policy_version 299110 (0.0008) -[2023-11-28 08:03:01,810][87426] Updated weights for policy 1, policy_version 299120 (0.0011) -[2023-11-28 08:03:02,179][87426] Updated weights for policy 1, policy_version 299130 (0.0011) -[2023-11-28 08:03:02,418][87424] Updated weights for policy 0, policy_version 299299 (0.0010) -[2023-11-28 08:03:02,794][87424] Updated weights for policy 0, policy_version 299309 (0.0008) -[2023-11-28 08:03:03,185][87424] Updated weights for policy 0, policy_version 299319 (0.0007) -[2023-11-28 08:03:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153198592. Throughput: 0: 2726.5, 1: 2681.3. Samples: 153215372. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:03,445][86177] Avg episode reward: [(0, '-614.040'), (1, '-534.290')] -[2023-11-28 08:03:04,477][87426] Updated weights for policy 1, policy_version 299140 (0.0009) -[2023-11-28 08:03:04,856][87426] Updated weights for policy 1, policy_version 299150 (0.0010) -[2023-11-28 08:03:04,993][87424] Updated weights for policy 0, policy_version 299329 (0.0012) -[2023-11-28 08:03:05,239][87426] Updated weights for policy 1, policy_version 299160 (0.0012) -[2023-11-28 08:03:05,369][87424] Updated weights for policy 0, policy_version 299339 (0.0011) -[2023-11-28 08:03:05,754][87424] Updated weights for policy 0, policy_version 299349 (0.0007) -[2023-11-28 08:03:06,138][87424] Updated weights for policy 0, policy_version 299359 (0.0011) -[2023-11-28 08:03:07,366][87426] Updated weights for policy 1, policy_version 299170 (0.0008) -[2023-11-28 08:03:07,750][87426] Updated weights for policy 1, policy_version 299180 (0.0009) -[2023-11-28 08:03:08,092][87424] Updated weights for policy 0, policy_version 299369 (0.0008) -[2023-11-28 08:03:08,123][87426] Updated weights for policy 1, policy_version 299190 (0.0007) -[2023-11-28 08:03:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 153223168. Throughput: 0: 2740.6, 1: 2683.6. Samples: 153248108. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:08,445][86177] Avg episode reward: [(0, '-618.810'), (1, '-510.360')] -[2023-11-28 08:03:08,475][87424] Updated weights for policy 0, policy_version 299379 (0.0009) -[2023-11-28 08:03:08,501][87426] Updated weights for policy 1, policy_version 299200 (0.0008) -[2023-11-28 08:03:08,857][87424] Updated weights for policy 0, policy_version 299389 (0.0008) -[2023-11-28 08:03:10,822][87426] Updated weights for policy 1, policy_version 299210 (0.0008) -[2023-11-28 08:03:11,138][87424] Updated weights for policy 0, policy_version 299399 (0.0010) -[2023-11-28 08:03:11,206][87426] Updated weights for policy 1, policy_version 299220 (0.0010) -[2023-11-28 08:03:11,529][87424] Updated weights for policy 0, policy_version 299409 (0.0008) -[2023-11-28 08:03:11,585][87426] Updated weights for policy 1, policy_version 299230 (0.0011) -[2023-11-28 08:03:11,902][87424] Updated weights for policy 0, policy_version 299419 (0.0010) -[2023-11-28 08:03:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153255936. Throughput: 0: 2736.2, 1: 2696.3. Samples: 153272140. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:13,445][86177] Avg episode reward: [(0, '-635.980'), (1, '-509.180')] -[2023-11-28 08:03:13,910][87426] Updated weights for policy 1, policy_version 299240 (0.0010) -[2023-11-28 08:03:13,985][87424] Updated weights for policy 0, policy_version 299429 (0.0011) -[2023-11-28 08:03:14,297][87426] Updated weights for policy 1, policy_version 299250 (0.0009) -[2023-11-28 08:03:14,362][87424] Updated weights for policy 0, policy_version 299439 (0.0011) -[2023-11-28 08:03:14,667][87426] Updated weights for policy 1, policy_version 299260 (0.0007) -[2023-11-28 08:03:14,742][87424] Updated weights for policy 0, policy_version 299449 (0.0009) -[2023-11-28 08:03:16,811][87426] Updated weights for policy 1, policy_version 299270 (0.0010) -[2023-11-28 08:03:17,153][87424] Updated weights for policy 0, policy_version 299459 (0.0008) -[2023-11-28 08:03:17,188][87426] Updated weights for policy 1, policy_version 299280 (0.0012) -[2023-11-28 08:03:17,533][87424] Updated weights for policy 0, policy_version 299469 (0.0011) -[2023-11-28 08:03:17,570][87426] Updated weights for policy 1, policy_version 299290 (0.0010) -[2023-11-28 08:03:17,907][87424] Updated weights for policy 0, policy_version 299479 (0.0009) -[2023-11-28 08:03:18,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 153288704. Throughput: 0: 2706.8, 1: 2687.1. Samples: 153296244. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:18,445][86177] Avg episode reward: [(0, '-641.460'), (1, '-504.970')] -[2023-11-28 08:03:19,537][87426] Updated weights for policy 1, policy_version 299300 (0.0012) -[2023-11-28 08:03:19,914][87426] Updated weights for policy 1, policy_version 299310 (0.0012) -[2023-11-28 08:03:19,986][87424] Updated weights for policy 0, policy_version 299489 (0.0008) -[2023-11-28 08:03:20,287][87426] Updated weights for policy 1, policy_version 299320 (0.0011) -[2023-11-28 08:03:20,373][87424] Updated weights for policy 0, policy_version 299499 (0.0012) -[2023-11-28 08:03:20,749][87424] Updated weights for policy 0, policy_version 299509 (0.0008) -[2023-11-28 08:03:21,127][87424] Updated weights for policy 0, policy_version 299519 (0.0010) -[2023-11-28 08:03:22,617][87426] Updated weights for policy 1, policy_version 299330 (0.0010) -[2023-11-28 08:03:23,000][87426] Updated weights for policy 1, policy_version 299340 (0.0012) -[2023-11-28 08:03:23,363][87426] Updated weights for policy 1, policy_version 299350 (0.0011) -[2023-11-28 08:03:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 153305088. Throughput: 0: 2717.8, 1: 2686.6. Samples: 153328440. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:23,445][86177] Avg episode reward: [(0, '-634.440'), (1, '-503.460')] -[2023-11-28 08:03:23,717][87424] Updated weights for policy 0, policy_version 299529 (0.0011) -[2023-11-28 08:03:23,740][87426] Updated weights for policy 1, policy_version 299360 (0.0011) -[2023-11-28 08:03:24,097][87424] Updated weights for policy 0, policy_version 299539 (0.0012) -[2023-11-28 08:03:24,473][87424] Updated weights for policy 0, policy_version 299549 (0.0010) -[2023-11-28 08:03:25,860][87426] Updated weights for policy 1, policy_version 299370 (0.0008) -[2023-11-28 08:03:26,234][87426] Updated weights for policy 1, policy_version 299380 (0.0008) -[2023-11-28 08:03:26,606][87426] Updated weights for policy 1, policy_version 299390 (0.0008) -[2023-11-28 08:03:26,720][87424] Updated weights for policy 0, policy_version 299559 (0.0011) -[2023-11-28 08:03:27,095][87424] Updated weights for policy 0, policy_version 299569 (0.0009) -[2023-11-28 08:03:27,477][87424] Updated weights for policy 0, policy_version 299579 (0.0008) -[2023-11-28 08:03:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 153337856. Throughput: 0: 2733.1, 1: 2719.6. Samples: 153353816. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:28,445][86177] Avg episode reward: [(0, '-721.340'), (1, '-515.320')] -[2023-11-28 08:03:28,480][87426] Updated weights for policy 1, policy_version 299400 (0.0008) -[2023-11-28 08:03:28,867][87426] Updated weights for policy 1, policy_version 299410 (0.0008) -[2023-11-28 08:03:29,133][87424] Updated weights for policy 0, policy_version 299589 (0.0007) -[2023-11-28 08:03:29,243][87426] Updated weights for policy 1, policy_version 299420 (0.0010) -[2023-11-28 08:03:29,517][87424] Updated weights for policy 0, policy_version 299599 (0.0008) -[2023-11-28 08:03:29,909][87424] Updated weights for policy 0, policy_version 299609 (0.0010) -[2023-11-28 08:03:31,372][87426] Updated weights for policy 1, policy_version 299430 (0.0011) -[2023-11-28 08:03:31,743][87426] Updated weights for policy 1, policy_version 299440 (0.0012) -[2023-11-28 08:03:32,070][87424] Updated weights for policy 0, policy_version 299619 (0.0011) -[2023-11-28 08:03:32,115][87426] Updated weights for policy 1, policy_version 299450 (0.0011) -[2023-11-28 08:03:32,451][87424] Updated weights for policy 0, policy_version 299629 (0.0011) -[2023-11-28 08:03:32,833][87424] Updated weights for policy 0, policy_version 299639 (0.0012) -[2023-11-28 08:03:33,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 153370624. Throughput: 0: 2759.3, 1: 2702.0. Samples: 153379208. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:33,445][86177] Avg episode reward: [(0, '-752.780'), (1, '-515.520')] -[2023-11-28 08:03:34,182][87426] Updated weights for policy 1, policy_version 299460 (0.0010) -[2023-11-28 08:03:34,558][87426] Updated weights for policy 1, policy_version 299470 (0.0012) -[2023-11-28 08:03:34,807][87424] Updated weights for policy 0, policy_version 299649 (0.0012) -[2023-11-28 08:03:34,923][87426] Updated weights for policy 1, policy_version 299480 (0.0011) -[2023-11-28 08:03:35,186][87424] Updated weights for policy 0, policy_version 299659 (0.0010) -[2023-11-28 08:03:35,570][87424] Updated weights for policy 0, policy_version 299669 (0.0010) -[2023-11-28 08:03:35,955][87424] Updated weights for policy 0, policy_version 299679 (0.0007) -[2023-11-28 08:03:37,126][87426] Updated weights for policy 1, policy_version 299490 (0.0011) -[2023-11-28 08:03:37,501][87426] Updated weights for policy 1, policy_version 299500 (0.0012) -[2023-11-28 08:03:37,873][87426] Updated weights for policy 1, policy_version 299510 (0.0011) -[2023-11-28 08:03:37,973][87424] Updated weights for policy 0, policy_version 299689 (0.0010) -[2023-11-28 08:03:38,236][87426] Updated weights for policy 1, policy_version 299520 (0.0011) -[2023-11-28 08:03:38,354][87424] Updated weights for policy 0, policy_version 299699 (0.0007) -[2023-11-28 08:03:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 153395200. Throughput: 0: 2786.7, 1: 2714.1. Samples: 153412392. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:38,445][86177] Avg episode reward: [(0, '-711.760'), (1, '-515.500')] -[2023-11-28 08:03:38,740][87424] Updated weights for policy 0, policy_version 299709 (0.0009) -[2023-11-28 08:03:40,563][87426] Updated weights for policy 1, policy_version 299530 (0.0011) -[2023-11-28 08:03:40,941][87426] Updated weights for policy 1, policy_version 299540 (0.0010) -[2023-11-28 08:03:41,103][87424] Updated weights for policy 0, policy_version 299719 (0.0011) -[2023-11-28 08:03:41,322][87426] Updated weights for policy 1, policy_version 299550 (0.0007) -[2023-11-28 08:03:41,494][87424] Updated weights for policy 0, policy_version 299729 (0.0009) -[2023-11-28 08:03:41,865][87424] Updated weights for policy 0, policy_version 299739 (0.0010) -[2023-11-28 08:03:43,323][87426] Updated weights for policy 1, policy_version 299560 (0.0007) -[2023-11-28 08:03:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 153419776. Throughput: 0: 2786.7, 1: 2717.7. Samples: 153436908. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:43,445][86177] Avg episode reward: [(0, '-725.090'), (1, '-515.010')] -[2023-11-28 08:03:43,700][87426] Updated weights for policy 1, policy_version 299570 (0.0009) -[2023-11-28 08:03:43,999][87424] Updated weights for policy 0, policy_version 299749 (0.0012) -[2023-11-28 08:03:44,088][87426] Updated weights for policy 1, policy_version 299580 (0.0007) -[2023-11-28 08:03:44,382][87424] Updated weights for policy 0, policy_version 299759 (0.0008) -[2023-11-28 08:03:44,769][87424] Updated weights for policy 0, policy_version 299769 (0.0009) -[2023-11-28 08:03:46,444][87426] Updated weights for policy 1, policy_version 299590 (0.0007) -[2023-11-28 08:03:46,569][87424] Updated weights for policy 0, policy_version 299779 (0.0011) -[2023-11-28 08:03:46,824][87426] Updated weights for policy 1, policy_version 299600 (0.0007) -[2023-11-28 08:03:46,947][87424] Updated weights for policy 0, policy_version 299789 (0.0008) -[2023-11-28 08:03:47,201][87426] Updated weights for policy 1, policy_version 299610 (0.0007) -[2023-11-28 08:03:47,321][87424] Updated weights for policy 0, policy_version 299799 (0.0008) -[2023-11-28 08:03:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 153452544. Throughput: 0: 2767.0, 1: 2698.4. Samples: 153461316. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:48,445][86177] Avg episode reward: [(0, '-750.020'), (1, '-546.010')] -[2023-11-28 08:03:49,251][87424] Updated weights for policy 0, policy_version 299809 (0.0008) -[2023-11-28 08:03:49,583][87426] Updated weights for policy 1, policy_version 299620 (0.0008) -[2023-11-28 08:03:49,628][87424] Updated weights for policy 0, policy_version 299819 (0.0011) -[2023-11-28 08:03:49,960][87426] Updated weights for policy 1, policy_version 299630 (0.0009) -[2023-11-28 08:03:50,006][87424] Updated weights for policy 0, policy_version 299829 (0.0010) -[2023-11-28 08:03:50,347][87426] Updated weights for policy 1, policy_version 299640 (0.0012) -[2023-11-28 08:03:50,395][87424] Updated weights for policy 0, policy_version 299839 (0.0008) -[2023-11-28 08:03:52,535][87424] Updated weights for policy 0, policy_version 299849 (0.0009) -[2023-11-28 08:03:52,668][87426] Updated weights for policy 1, policy_version 299650 (0.0011) -[2023-11-28 08:03:52,909][87424] Updated weights for policy 0, policy_version 299859 (0.0009) -[2023-11-28 08:03:53,047][87426] Updated weights for policy 1, policy_version 299660 (0.0012) -[2023-11-28 08:03:53,297][87424] Updated weights for policy 0, policy_version 299869 (0.0011) -[2023-11-28 08:03:53,423][87426] Updated weights for policy 1, policy_version 299670 (0.0011) -[2023-11-28 08:03:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 153477120. Throughput: 0: 2740.8, 1: 2707.0. Samples: 153493260. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:53,445][86177] Avg episode reward: [(0, '-677.320'), (1, '-542.580')] -[2023-11-28 08:03:53,799][87426] Updated weights for policy 1, policy_version 299680 (0.0011) -[2023-11-28 08:03:55,741][87424] Updated weights for policy 0, policy_version 299879 (0.0011) -[2023-11-28 08:03:55,931][87426] Updated weights for policy 1, policy_version 299690 (0.0011) -[2023-11-28 08:03:56,131][87424] Updated weights for policy 0, policy_version 299889 (0.0011) -[2023-11-28 08:03:56,319][87426] Updated weights for policy 1, policy_version 299700 (0.0010) -[2023-11-28 08:03:56,513][87424] Updated weights for policy 0, policy_version 299899 (0.0012) -[2023-11-28 08:03:56,688][87426] Updated weights for policy 1, policy_version 299710 (0.0011) -[2023-11-28 08:03:58,297][87424] Updated weights for policy 0, policy_version 299909 (0.0012) -[2023-11-28 08:03:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 153501696. Throughput: 0: 2759.3, 1: 2699.5. Samples: 153517784. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:03:58,445][86177] Avg episode reward: [(0, '-698.730'), (1, '-542.570')] -[2023-11-28 08:03:58,545][87426] Updated weights for policy 1, policy_version 299720 (0.0008) -[2023-11-28 08:03:58,681][87424] Updated weights for policy 0, policy_version 299919 (0.0012) -[2023-11-28 08:03:58,934][87426] Updated weights for policy 1, policy_version 299730 (0.0009) -[2023-11-28 08:03:59,062][87424] Updated weights for policy 0, policy_version 299929 (0.0011) -[2023-11-28 08:03:59,316][87426] Updated weights for policy 1, policy_version 299740 (0.0012) -[2023-11-28 08:04:01,192][87424] Updated weights for policy 0, policy_version 299939 (0.0010) -[2023-11-28 08:04:01,585][87424] Updated weights for policy 0, policy_version 299949 (0.0008) -[2023-11-28 08:04:01,857][87426] Updated weights for policy 1, policy_version 299750 (0.0016) -[2023-11-28 08:04:01,965][87424] Updated weights for policy 0, policy_version 299959 (0.0008) -[2023-11-28 08:04:02,236][87426] Updated weights for policy 1, policy_version 299760 (0.0012) -[2023-11-28 08:04:02,617][87426] Updated weights for policy 1, policy_version 299770 (0.0012) -[2023-11-28 08:04:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 153534464. Throughput: 0: 2776.8, 1: 2695.3. Samples: 153542488. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:04:03,445][86177] Avg episode reward: [(0, '-667.490'), (1, '-542.600')] -[2023-11-28 08:04:03,790][87424] Updated weights for policy 0, policy_version 299969 (0.0011) -[2023-11-28 08:04:04,159][87424] Updated weights for policy 0, policy_version 299979 (0.0011) -[2023-11-28 08:04:04,539][87424] Updated weights for policy 0, policy_version 299989 (0.0011) -[2023-11-28 08:04:04,811][87426] Updated weights for policy 1, policy_version 299780 (0.0012) -[2023-11-28 08:04:04,921][87424] Updated weights for policy 0, policy_version 299999 (0.0012) -[2023-11-28 08:04:05,186][87426] Updated weights for policy 1, policy_version 299790 (0.0012) -[2023-11-28 08:04:05,569][87426] Updated weights for policy 1, policy_version 299800 (0.0011) -[2023-11-28 08:04:06,619][87424] Updated weights for policy 0, policy_version 300009 (0.0012) -[2023-11-28 08:04:07,002][87424] Updated weights for policy 0, policy_version 300019 (0.0012) -[2023-11-28 08:04:07,390][87424] Updated weights for policy 0, policy_version 300029 (0.0011) -[2023-11-28 08:04:07,686][87426] Updated weights for policy 1, policy_version 299810 (0.0007) -[2023-11-28 08:04:08,074][87426] Updated weights for policy 1, policy_version 299820 (0.0011) -[2023-11-28 08:04:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 153559040. Throughput: 0: 2790.8, 1: 2708.9. Samples: 153575924. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:08,445][86177] Avg episode reward: [(0, '-658.870'), (1, '-507.840')] -[2023-11-28 08:04:08,455][87426] Updated weights for policy 1, policy_version 299830 (0.0008) -[2023-11-28 08:04:08,834][87426] Updated weights for policy 1, policy_version 299840 (0.0007) -[2023-11-28 08:04:09,891][87424] Updated weights for policy 0, policy_version 300039 (0.0011) -[2023-11-28 08:04:10,277][87424] Updated weights for policy 0, policy_version 300049 (0.0011) -[2023-11-28 08:04:10,657][87424] Updated weights for policy 0, policy_version 300059 (0.0010) -[2023-11-28 08:04:11,177][87426] Updated weights for policy 1, policy_version 299850 (0.0012) -[2023-11-28 08:04:11,565][87426] Updated weights for policy 1, policy_version 299860 (0.0009) -[2023-11-28 08:04:11,947][87426] Updated weights for policy 1, policy_version 299870 (0.0009) -[2023-11-28 08:04:12,879][87424] Updated weights for policy 0, policy_version 300069 (0.0011) -[2023-11-28 08:04:13,263][87424] Updated weights for policy 0, policy_version 300079 (0.0008) -[2023-11-28 08:04:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 153583616. Throughput: 0: 2778.1, 1: 2684.0. Samples: 153599608. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:13,445][86177] Avg episode reward: [(0, '-687.140'), (1, '-509.910')] -[2023-11-28 08:04:13,644][87424] Updated weights for policy 0, policy_version 300089 (0.0007) -[2023-11-28 08:04:14,333][87426] Updated weights for policy 1, policy_version 299880 (0.0007) -[2023-11-28 08:04:14,712][87426] Updated weights for policy 1, policy_version 299890 (0.0007) -[2023-11-28 08:04:15,087][87426] Updated weights for policy 1, policy_version 299900 (0.0008) -[2023-11-28 08:04:16,086][87424] Updated weights for policy 0, policy_version 300099 (0.0009) -[2023-11-28 08:04:16,470][87424] Updated weights for policy 0, policy_version 300109 (0.0012) -[2023-11-28 08:04:16,842][87424] Updated weights for policy 0, policy_version 300119 (0.0012) -[2023-11-28 08:04:17,209][87426] Updated weights for policy 1, policy_version 299910 (0.0010) -[2023-11-28 08:04:17,583][87426] Updated weights for policy 1, policy_version 299920 (0.0012) -[2023-11-28 08:04:17,957][87426] Updated weights for policy 1, policy_version 299930 (0.0016) -[2023-11-28 08:04:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 153616384. Throughput: 0: 2761.9, 1: 2678.1. Samples: 153624012. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:18,446][86177] Avg episode reward: [(0, '-664.220'), (1, '-506.720')] -[2023-11-28 08:04:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000300128_76832768.pth... -[2023-11-28 08:04:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000299936_76783616.pth... -[2023-11-28 08:04:18,497][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000297408_76136448.pth -[2023-11-28 08:04:18,504][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000297600_76185600.pth -[2023-11-28 08:04:19,108][87424] Updated weights for policy 0, policy_version 300129 (0.0012) -[2023-11-28 08:04:19,488][87424] Updated weights for policy 0, policy_version 300139 (0.0012) -[2023-11-28 08:04:19,876][87424] Updated weights for policy 0, policy_version 300149 (0.0012) -[2023-11-28 08:04:19,881][87426] Updated weights for policy 1, policy_version 299940 (0.0016) -[2023-11-28 08:04:20,247][87426] Updated weights for policy 1, policy_version 299950 (0.0011) -[2023-11-28 08:04:20,253][87424] Updated weights for policy 0, policy_version 300159 (0.0012) -[2023-11-28 08:04:20,623][87426] Updated weights for policy 1, policy_version 299960 (0.0011) -[2023-11-28 08:04:22,484][87424] Updated weights for policy 0, policy_version 300169 (0.0012) -[2023-11-28 08:04:22,757][87426] Updated weights for policy 1, policy_version 299970 (0.0012) -[2023-11-28 08:04:22,859][87424] Updated weights for policy 0, policy_version 300179 (0.0011) -[2023-11-28 08:04:23,132][87426] Updated weights for policy 1, policy_version 299980 (0.0012) -[2023-11-28 08:04:23,245][87424] Updated weights for policy 0, policy_version 300189 (0.0012) -[2023-11-28 08:04:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 153640960. Throughput: 0: 2738.6, 1: 2689.8. Samples: 153656668. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:23,445][86177] Avg episode reward: [(0, '-739.180'), (1, '-510.660')] -[2023-11-28 08:04:23,515][87426] Updated weights for policy 1, policy_version 299990 (0.0012) -[2023-11-28 08:04:23,894][87426] Updated weights for policy 1, policy_version 300000 (0.0011) -[2023-11-28 08:04:25,699][87426] Updated weights for policy 1, policy_version 300010 (0.0011) -[2023-11-28 08:04:25,858][87424] Updated weights for policy 0, policy_version 300199 (0.0012) -[2023-11-28 08:04:26,080][87426] Updated weights for policy 1, policy_version 300020 (0.0011) -[2023-11-28 08:04:26,238][87424] Updated weights for policy 0, policy_version 300209 (0.0011) -[2023-11-28 08:04:26,463][87426] Updated weights for policy 1, policy_version 300030 (0.0008) -[2023-11-28 08:04:26,622][87424] Updated weights for policy 0, policy_version 300219 (0.0012) -[2023-11-28 08:04:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 153665536. Throughput: 0: 2735.7, 1: 2692.8. Samples: 153681192. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:28,445][86177] Avg episode reward: [(0, '-776.610'), (1, '-508.760')] -[2023-11-28 08:04:28,862][87424] Updated weights for policy 0, policy_version 300229 (0.0010) -[2023-11-28 08:04:28,946][87426] Updated weights for policy 1, policy_version 300040 (0.0010) -[2023-11-28 08:04:29,239][87424] Updated weights for policy 0, policy_version 300239 (0.0009) -[2023-11-28 08:04:29,326][87426] Updated weights for policy 1, policy_version 300050 (0.0007) -[2023-11-28 08:04:29,626][87424] Updated weights for policy 0, policy_version 300249 (0.0011) -[2023-11-28 08:04:29,705][87426] Updated weights for policy 1, policy_version 300060 (0.0008) -[2023-11-28 08:04:31,781][87426] Updated weights for policy 1, policy_version 300070 (0.0012) -[2023-11-28 08:04:31,844][87424] Updated weights for policy 0, policy_version 300259 (0.0012) -[2023-11-28 08:04:32,162][87426] Updated weights for policy 1, policy_version 300080 (0.0009) -[2023-11-28 08:04:32,231][87424] Updated weights for policy 0, policy_version 300269 (0.0012) -[2023-11-28 08:04:32,542][87426] Updated weights for policy 1, policy_version 300090 (0.0009) -[2023-11-28 08:04:32,611][87424] Updated weights for policy 0, policy_version 300279 (0.0010) -[2023-11-28 08:04:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 153698304. Throughput: 0: 2738.7, 1: 2708.5. Samples: 153706440. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:33,445][86177] Avg episode reward: [(0, '-776.400'), (1, '-509.840')] -[2023-11-28 08:04:34,798][87424] Updated weights for policy 0, policy_version 300289 (0.0011) -[2023-11-28 08:04:35,010][87426] Updated weights for policy 1, policy_version 300100 (0.0009) -[2023-11-28 08:04:35,179][87424] Updated weights for policy 0, policy_version 300299 (0.0012) -[2023-11-28 08:04:35,390][87426] Updated weights for policy 1, policy_version 300110 (0.0011) -[2023-11-28 08:04:35,561][87424] Updated weights for policy 0, policy_version 300309 (0.0011) -[2023-11-28 08:04:35,760][87426] Updated weights for policy 1, policy_version 300120 (0.0008) -[2023-11-28 08:04:35,931][87424] Updated weights for policy 0, policy_version 300319 (0.0011) -[2023-11-28 08:04:37,945][87424] Updated weights for policy 0, policy_version 300329 (0.0012) -[2023-11-28 08:04:37,950][87426] Updated weights for policy 1, policy_version 300130 (0.0011) -[2023-11-28 08:04:38,330][87424] Updated weights for policy 0, policy_version 300339 (0.0009) -[2023-11-28 08:04:38,336][87426] Updated weights for policy 1, policy_version 300140 (0.0012) -[2023-11-28 08:04:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153714688. Throughput: 0: 2746.4, 1: 2724.4. Samples: 153739448. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:38,445][86177] Avg episode reward: [(0, '-767.060'), (1, '-509.900')] -[2023-11-28 08:04:38,710][87426] Updated weights for policy 1, policy_version 300150 (0.0009) -[2023-11-28 08:04:38,715][87424] Updated weights for policy 0, policy_version 300349 (0.0009) -[2023-11-28 08:04:39,090][87426] Updated weights for policy 1, policy_version 300160 (0.0011) -[2023-11-28 08:04:41,040][87424] Updated weights for policy 0, policy_version 300359 (0.0010) -[2023-11-28 08:04:41,417][87424] Updated weights for policy 0, policy_version 300369 (0.0009) -[2023-11-28 08:04:41,539][87426] Updated weights for policy 1, policy_version 300170 (0.0011) -[2023-11-28 08:04:41,808][87424] Updated weights for policy 0, policy_version 300379 (0.0011) -[2023-11-28 08:04:41,914][87426] Updated weights for policy 1, policy_version 300180 (0.0011) -[2023-11-28 08:04:42,293][87426] Updated weights for policy 1, policy_version 300190 (0.0011) -[2023-11-28 08:04:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 153747456. Throughput: 0: 2730.9, 1: 2714.9. Samples: 153762840. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:43,445][86177] Avg episode reward: [(0, '-764.610'), (1, '-509.500')] -[2023-11-28 08:04:44,027][87424] Updated weights for policy 0, policy_version 300389 (0.0011) -[2023-11-28 08:04:44,382][87426] Updated weights for policy 1, policy_version 300200 (0.0011) -[2023-11-28 08:04:44,410][87424] Updated weights for policy 0, policy_version 300399 (0.0007) -[2023-11-28 08:04:44,768][87426] Updated weights for policy 1, policy_version 300210 (0.0007) -[2023-11-28 08:04:44,799][87424] Updated weights for policy 0, policy_version 300409 (0.0007) -[2023-11-28 08:04:45,141][87426] Updated weights for policy 1, policy_version 300220 (0.0008) -[2023-11-28 08:04:46,714][87424] Updated weights for policy 0, policy_version 300419 (0.0009) -[2023-11-28 08:04:47,091][87424] Updated weights for policy 0, policy_version 300429 (0.0008) -[2023-11-28 08:04:47,470][87424] Updated weights for policy 0, policy_version 300439 (0.0008) -[2023-11-28 08:04:47,514][87426] Updated weights for policy 1, policy_version 300230 (0.0008) -[2023-11-28 08:04:47,902][87426] Updated weights for policy 1, policy_version 300240 (0.0007) -[2023-11-28 08:04:48,282][87426] Updated weights for policy 1, policy_version 300250 (0.0008) -[2023-11-28 08:04:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 153772032. Throughput: 0: 2701.3, 1: 2724.0. Samples: 153786628. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:48,446][86177] Avg episode reward: [(0, '-841.670'), (1, '-509.450')] -[2023-11-28 08:04:49,936][87424] Updated weights for policy 0, policy_version 300449 (0.0008) -[2023-11-28 08:04:50,309][87424] Updated weights for policy 0, policy_version 300459 (0.0008) -[2023-11-28 08:04:50,604][87426] Updated weights for policy 1, policy_version 300260 (0.0010) -[2023-11-28 08:04:50,690][87424] Updated weights for policy 0, policy_version 300469 (0.0011) -[2023-11-28 08:04:50,977][87426] Updated weights for policy 1, policy_version 300270 (0.0011) -[2023-11-28 08:04:51,069][87424] Updated weights for policy 0, policy_version 300479 (0.0012) -[2023-11-28 08:04:51,351][87426] Updated weights for policy 1, policy_version 300280 (0.0011) -[2023-11-28 08:04:53,248][87424] Updated weights for policy 0, policy_version 300489 (0.0008) -[2023-11-28 08:04:53,334][87426] Updated weights for policy 1, policy_version 300290 (0.0011) -[2023-11-28 08:04:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153796608. Throughput: 0: 2684.9, 1: 2695.7. Samples: 153818052. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:53,445][86177] Avg episode reward: [(0, '-850.280'), (1, '-507.490')] -[2023-11-28 08:04:53,633][87424] Updated weights for policy 0, policy_version 300499 (0.0011) -[2023-11-28 08:04:53,713][87426] Updated weights for policy 1, policy_version 300300 (0.0010) -[2023-11-28 08:04:54,011][87424] Updated weights for policy 0, policy_version 300509 (0.0010) -[2023-11-28 08:04:54,097][87426] Updated weights for policy 1, policy_version 300310 (0.0009) -[2023-11-28 08:04:54,477][87426] Updated weights for policy 1, policy_version 300320 (0.0011) -[2023-11-28 08:04:56,249][87424] Updated weights for policy 0, policy_version 300519 (0.0011) -[2023-11-28 08:04:56,318][87426] Updated weights for policy 1, policy_version 300330 (0.0012) -[2023-11-28 08:04:56,636][87424] Updated weights for policy 0, policy_version 300529 (0.0011) -[2023-11-28 08:04:56,698][87426] Updated weights for policy 1, policy_version 300340 (0.0010) -[2023-11-28 08:04:57,007][87424] Updated weights for policy 0, policy_version 300539 (0.0011) -[2023-11-28 08:04:57,071][87426] Updated weights for policy 1, policy_version 300350 (0.0007) -[2023-11-28 08:04:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 153829376. Throughput: 0: 2696.3, 1: 2713.4. Samples: 153843044. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:04:58,445][86177] Avg episode reward: [(0, '-831.950'), (1, '-512.900')] -[2023-11-28 08:04:59,233][87424] Updated weights for policy 0, policy_version 300549 (0.0011) -[2023-11-28 08:04:59,524][87426] Updated weights for policy 1, policy_version 300360 (0.0011) -[2023-11-28 08:04:59,611][87424] Updated weights for policy 0, policy_version 300559 (0.0007) -[2023-11-28 08:04:59,906][87426] Updated weights for policy 1, policy_version 300370 (0.0011) -[2023-11-28 08:04:59,990][87424] Updated weights for policy 0, policy_version 300569 (0.0009) -[2023-11-28 08:05:00,291][87426] Updated weights for policy 1, policy_version 300380 (0.0008) -[2023-11-28 08:05:01,841][87424] Updated weights for policy 0, policy_version 300579 (0.0009) -[2023-11-28 08:05:02,224][87424] Updated weights for policy 0, policy_version 300589 (0.0009) -[2023-11-28 08:05:02,607][87424] Updated weights for policy 0, policy_version 300599 (0.0008) -[2023-11-28 08:05:02,661][87426] Updated weights for policy 1, policy_version 300390 (0.0009) -[2023-11-28 08:05:03,040][87426] Updated weights for policy 1, policy_version 300400 (0.0010) -[2023-11-28 08:05:03,421][87426] Updated weights for policy 1, policy_version 300410 (0.0009) -[2023-11-28 08:05:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 153853952. Throughput: 0: 2682.6, 1: 2723.7. Samples: 153867296. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:05:03,445][86177] Avg episode reward: [(0, '-764.860'), (1, '-520.240')] -[2023-11-28 08:05:04,741][87424] Updated weights for policy 0, policy_version 300609 (0.0009) -[2023-11-28 08:05:05,126][87424] Updated weights for policy 0, policy_version 300619 (0.0012) -[2023-11-28 08:05:05,360][87426] Updated weights for policy 1, policy_version 300420 (0.0009) -[2023-11-28 08:05:05,507][87424] Updated weights for policy 0, policy_version 300629 (0.0012) -[2023-11-28 08:05:05,742][87426] Updated weights for policy 1, policy_version 300430 (0.0008) -[2023-11-28 08:05:05,895][87424] Updated weights for policy 0, policy_version 300639 (0.0012) -[2023-11-28 08:05:06,121][87426] Updated weights for policy 1, policy_version 300440 (0.0007) -[2023-11-28 08:05:07,823][87424] Updated weights for policy 0, policy_version 300649 (0.0009) -[2023-11-28 08:05:08,205][87424] Updated weights for policy 0, policy_version 300659 (0.0007) -[2023-11-28 08:05:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 153878528. Throughput: 0: 2693.1, 1: 2721.5. Samples: 153900324. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:05:08,446][86177] Avg episode reward: [(0, '-798.830'), (1, '-520.430')] -[2023-11-28 08:05:08,595][87424] Updated weights for policy 0, policy_version 300669 (0.0007) -[2023-11-28 08:05:08,614][87426] Updated weights for policy 1, policy_version 300450 (0.0007) -[2023-11-28 08:05:08,999][87426] Updated weights for policy 1, policy_version 300460 (0.0009) -[2023-11-28 08:05:09,364][87426] Updated weights for policy 1, policy_version 300470 (0.0012) -[2023-11-28 08:05:09,740][87426] Updated weights for policy 1, policy_version 300480 (0.0012) -[2023-11-28 08:05:10,846][87424] Updated weights for policy 0, policy_version 300679 (0.0010) -[2023-11-28 08:05:11,229][87424] Updated weights for policy 0, policy_version 300689 (0.0010) -[2023-11-28 08:05:11,615][87424] Updated weights for policy 0, policy_version 300699 (0.0009) -[2023-11-28 08:05:12,109][87426] Updated weights for policy 1, policy_version 300490 (0.0010) -[2023-11-28 08:05:12,491][87426] Updated weights for policy 1, policy_version 300500 (0.0010) -[2023-11-28 08:05:12,863][87426] Updated weights for policy 1, policy_version 300510 (0.0011) -[2023-11-28 08:05:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 153911296. Throughput: 0: 2694.8, 1: 2690.8. Samples: 153923540. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:05:13,445][86177] Avg episode reward: [(0, '-812.780'), (1, '-519.350')] -[2023-11-28 08:05:14,160][87424] Updated weights for policy 0, policy_version 300709 (0.0012) -[2023-11-28 08:05:14,538][87424] Updated weights for policy 0, policy_version 300719 (0.0012) -[2023-11-28 08:05:14,907][87426] Updated weights for policy 1, policy_version 300520 (0.0010) -[2023-11-28 08:05:14,911][87424] Updated weights for policy 0, policy_version 300729 (0.0010) -[2023-11-28 08:05:15,284][87426] Updated weights for policy 1, policy_version 300530 (0.0009) -[2023-11-28 08:05:15,664][87426] Updated weights for policy 1, policy_version 300540 (0.0009) -[2023-11-28 08:05:16,982][87424] Updated weights for policy 0, policy_version 300739 (0.0010) -[2023-11-28 08:05:17,366][87424] Updated weights for policy 0, policy_version 300749 (0.0007) -[2023-11-28 08:05:17,752][87424] Updated weights for policy 0, policy_version 300759 (0.0009) -[2023-11-28 08:05:17,760][87426] Updated weights for policy 1, policy_version 300550 (0.0010) -[2023-11-28 08:05:18,139][87426] Updated weights for policy 1, policy_version 300560 (0.0010) -[2023-11-28 08:05:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 153935872. Throughput: 0: 2678.9, 1: 2684.5. Samples: 153947792. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:05:18,445][86177] Avg episode reward: [(0, '-892.590'), (1, '-511.260')] -[2023-11-28 08:05:18,526][87426] Updated weights for policy 1, policy_version 300570 (0.0007) -[2023-11-28 08:05:19,407][87424] Updated weights for policy 0, policy_version 300769 (0.0011) -[2023-11-28 08:05:19,789][87424] Updated weights for policy 0, policy_version 300779 (0.0008) -[2023-11-28 08:05:20,167][87424] Updated weights for policy 0, policy_version 300789 (0.0010) -[2023-11-28 08:05:20,491][87426] Updated weights for policy 1, policy_version 300580 (0.0008) -[2023-11-28 08:05:20,554][87424] Updated weights for policy 0, policy_version 300799 (0.0011) -[2023-11-28 08:05:20,865][87426] Updated weights for policy 1, policy_version 300590 (0.0012) -[2023-11-28 08:05:21,252][87426] Updated weights for policy 1, policy_version 300600 (0.0010) -[2023-11-28 08:05:22,974][87424] Updated weights for policy 0, policy_version 300809 (0.0012) -[2023-11-28 08:05:23,358][87424] Updated weights for policy 0, policy_version 300819 (0.0012) -[2023-11-28 08:05:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 153960448. Throughput: 0: 2680.8, 1: 2670.5. Samples: 153980256. Policy #0 lag: (min: 20.0, avg: 36.3, max: 52.0) -[2023-11-28 08:05:23,445][86177] Avg episode reward: [(0, '-932.160'), (1, '-511.210')] -[2023-11-28 08:05:23,738][87424] Updated weights for policy 0, policy_version 300829 (0.0011) -[2023-11-28 08:05:23,782][87426] Updated weights for policy 1, policy_version 300610 (0.0010) -[2023-11-28 08:05:24,162][87426] Updated weights for policy 1, policy_version 300620 (0.0008) -[2023-11-28 08:05:24,538][87426] Updated weights for policy 1, policy_version 300630 (0.0007) -[2023-11-28 08:05:24,917][87426] Updated weights for policy 1, policy_version 300640 (0.0009) -[2023-11-28 08:05:25,748][87424] Updated weights for policy 0, policy_version 300839 (0.0009) -[2023-11-28 08:05:26,130][87424] Updated weights for policy 0, policy_version 300849 (0.0007) -[2023-11-28 08:05:26,519][87424] Updated weights for policy 0, policy_version 300859 (0.0008) -[2023-11-28 08:05:27,098][87426] Updated weights for policy 1, policy_version 300650 (0.0010) -[2023-11-28 08:05:27,480][87426] Updated weights for policy 1, policy_version 300660 (0.0007) -[2023-11-28 08:05:27,862][87426] Updated weights for policy 1, policy_version 300670 (0.0008) -[2023-11-28 08:05:28,426][87424] Updated weights for policy 0, policy_version 300869 (0.0011) -[2023-11-28 08:05:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 153993216. Throughput: 0: 2701.5, 1: 2686.4. Samples: 154005296. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:05:28,445][86177] Avg episode reward: [(0, '-1081.560'), (1, '-514.250')] -[2023-11-28 08:05:28,793][87424] Updated weights for policy 0, policy_version 300879 (0.0011) -[2023-11-28 08:05:29,171][87424] Updated weights for policy 0, policy_version 300889 (0.0011) -[2023-11-28 08:05:30,051][87426] Updated weights for policy 1, policy_version 300680 (0.0012) -[2023-11-28 08:05:30,429][87426] Updated weights for policy 1, policy_version 300690 (0.0012) -[2023-11-28 08:05:30,802][87426] Updated weights for policy 1, policy_version 300700 (0.0012) -[2023-11-28 08:05:31,321][87424] Updated weights for policy 0, policy_version 300899 (0.0011) -[2023-11-28 08:05:31,709][87424] Updated weights for policy 0, policy_version 300909 (0.0008) -[2023-11-28 08:05:32,095][87424] Updated weights for policy 0, policy_version 300919 (0.0008) -[2023-11-28 08:05:32,981][87426] Updated weights for policy 1, policy_version 300710 (0.0009) -[2023-11-28 08:05:33,358][87426] Updated weights for policy 1, policy_version 300720 (0.0008) -[2023-11-28 08:05:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 154017792. Throughput: 0: 2736.0, 1: 2694.5. Samples: 154031000. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:05:33,445][86177] Avg episode reward: [(0, '-1123.160'), (1, '-518.550')] -[2023-11-28 08:05:33,739][87426] Updated weights for policy 1, policy_version 300730 (0.0007) -[2023-11-28 08:05:34,577][87424] Updated weights for policy 0, policy_version 300929 (0.0010) -[2023-11-28 08:05:34,957][87424] Updated weights for policy 0, policy_version 300939 (0.0010) -[2023-11-28 08:05:35,338][87424] Updated weights for policy 0, policy_version 300949 (0.0010) -[2023-11-28 08:05:35,718][87424] Updated weights for policy 0, policy_version 300959 (0.0011) -[2023-11-28 08:05:36,269][87426] Updated weights for policy 1, policy_version 300740 (0.0008) -[2023-11-28 08:05:36,654][87426] Updated weights for policy 1, policy_version 300750 (0.0009) -[2023-11-28 08:05:37,033][87426] Updated weights for policy 1, policy_version 300760 (0.0008) -[2023-11-28 08:05:37,967][87424] Updated weights for policy 0, policy_version 300969 (0.0008) -[2023-11-28 08:05:38,340][87424] Updated weights for policy 0, policy_version 300979 (0.0008) -[2023-11-28 08:05:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 154042368. Throughput: 0: 2759.7, 1: 2696.5. Samples: 154063584. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:05:38,445][86177] Avg episode reward: [(0, '-1165.460'), (1, '-518.290')] -[2023-11-28 08:05:38,731][87424] Updated weights for policy 0, policy_version 300989 (0.0008) -[2023-11-28 08:05:39,217][87426] Updated weights for policy 1, policy_version 300770 (0.0007) -[2023-11-28 08:05:39,609][87426] Updated weights for policy 1, policy_version 300780 (0.0007) -[2023-11-28 08:05:39,999][87426] Updated weights for policy 1, policy_version 300790 (0.0009) -[2023-11-28 08:05:40,372][87426] Updated weights for policy 1, policy_version 300800 (0.0011) -[2023-11-28 08:05:40,989][87424] Updated weights for policy 0, policy_version 300999 (0.0010) -[2023-11-28 08:05:41,374][87424] Updated weights for policy 0, policy_version 301009 (0.0007) -[2023-11-28 08:05:41,761][87424] Updated weights for policy 0, policy_version 301019 (0.0009) -[2023-11-28 08:05:42,465][87426] Updated weights for policy 1, policy_version 300810 (0.0011) -[2023-11-28 08:05:42,854][87426] Updated weights for policy 1, policy_version 300820 (0.0011) -[2023-11-28 08:05:43,225][87426] Updated weights for policy 1, policy_version 300830 (0.0012) -[2023-11-28 08:05:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 154075136. Throughput: 0: 2748.4, 1: 2673.2. Samples: 154087016. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:05:43,445][86177] Avg episode reward: [(0, '-1279.030'), (1, '-509.420')] -[2023-11-28 08:05:43,909][87424] Updated weights for policy 0, policy_version 301029 (0.0011) -[2023-11-28 08:05:44,286][87424] Updated weights for policy 0, policy_version 301039 (0.0012) -[2023-11-28 08:05:44,661][87424] Updated weights for policy 0, policy_version 301049 (0.0012) -[2023-11-28 08:05:45,615][87426] Updated weights for policy 1, policy_version 300840 (0.0012) -[2023-11-28 08:05:45,977][87426] Updated weights for policy 1, policy_version 300850 (0.0012) -[2023-11-28 08:05:46,369][87426] Updated weights for policy 1, policy_version 300860 (0.0012) -[2023-11-28 08:05:46,701][87424] Updated weights for policy 0, policy_version 301059 (0.0012) -[2023-11-28 08:05:47,086][87424] Updated weights for policy 0, policy_version 301069 (0.0012) -[2023-11-28 08:05:47,466][87424] Updated weights for policy 0, policy_version 301079 (0.0012) -[2023-11-28 08:05:48,184][87426] Updated weights for policy 1, policy_version 300870 (0.0011) -[2023-11-28 08:05:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 154099712. Throughput: 0: 2754.2, 1: 2655.7. Samples: 154110744. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:05:48,445][86177] Avg episode reward: [(0, '-1320.990'), (1, '-516.410')] -[2023-11-28 08:05:48,548][87426] Updated weights for policy 1, policy_version 300880 (0.0009) -[2023-11-28 08:05:48,929][87426] Updated weights for policy 1, policy_version 300890 (0.0011) -[2023-11-28 08:05:49,243][87424] Updated weights for policy 0, policy_version 301089 (0.0012) -[2023-11-28 08:05:49,629][87424] Updated weights for policy 0, policy_version 301099 (0.0012) -[2023-11-28 08:05:50,013][87424] Updated weights for policy 0, policy_version 301109 (0.0012) -[2023-11-28 08:05:50,395][87424] Updated weights for policy 0, policy_version 301119 (0.0012) -[2023-11-28 08:05:51,217][87426] Updated weights for policy 1, policy_version 300900 (0.0009) -[2023-11-28 08:05:51,594][87426] Updated weights for policy 1, policy_version 300910 (0.0008) -[2023-11-28 08:05:51,979][87426] Updated weights for policy 1, policy_version 300920 (0.0010) -[2023-11-28 08:05:52,720][87424] Updated weights for policy 0, policy_version 301129 (0.0012) -[2023-11-28 08:05:53,093][87424] Updated weights for policy 0, policy_version 301139 (0.0012) -[2023-11-28 08:05:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 154124288. Throughput: 0: 2763.0, 1: 2670.6. Samples: 154144836. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:05:53,445][86177] Avg episode reward: [(0, '-1315.620'), (1, '-518.690')] -[2023-11-28 08:05:53,469][87424] Updated weights for policy 0, policy_version 301149 (0.0012) -[2023-11-28 08:05:54,229][87426] Updated weights for policy 1, policy_version 300930 (0.0010) -[2023-11-28 08:05:54,615][87426] Updated weights for policy 1, policy_version 300940 (0.0012) -[2023-11-28 08:05:54,995][87426] Updated weights for policy 1, policy_version 300950 (0.0012) -[2023-11-28 08:05:55,370][87426] Updated weights for policy 1, policy_version 300960 (0.0012) -[2023-11-28 08:05:55,723][87424] Updated weights for policy 0, policy_version 301159 (0.0009) -[2023-11-28 08:05:56,108][87424] Updated weights for policy 0, policy_version 301169 (0.0007) -[2023-11-28 08:05:56,506][87424] Updated weights for policy 0, policy_version 301179 (0.0007) -[2023-11-28 08:05:57,195][87426] Updated weights for policy 1, policy_version 300970 (0.0012) -[2023-11-28 08:05:57,562][87426] Updated weights for policy 1, policy_version 300980 (0.0012) -[2023-11-28 08:05:57,936][87426] Updated weights for policy 1, policy_version 300990 (0.0012) -[2023-11-28 08:05:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 154157056. Throughput: 0: 2769.9, 1: 2700.0. Samples: 154169688. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:05:58,446][86177] Avg episode reward: [(0, '-1245.150'), (1, '-525.540')] -[2023-11-28 08:05:58,584][87424] Updated weights for policy 0, policy_version 301189 (0.0008) -[2023-11-28 08:05:58,959][87424] Updated weights for policy 0, policy_version 301199 (0.0010) -[2023-11-28 08:05:59,347][87424] Updated weights for policy 0, policy_version 301209 (0.0012) -[2023-11-28 08:06:00,361][87426] Updated weights for policy 1, policy_version 301000 (0.0009) -[2023-11-28 08:06:00,744][87426] Updated weights for policy 1, policy_version 301010 (0.0012) -[2023-11-28 08:06:01,119][87426] Updated weights for policy 1, policy_version 301020 (0.0011) -[2023-11-28 08:06:01,172][87424] Updated weights for policy 0, policy_version 301219 (0.0012) -[2023-11-28 08:06:01,551][87424] Updated weights for policy 0, policy_version 301229 (0.0012) -[2023-11-28 08:06:01,943][87424] Updated weights for policy 0, policy_version 301239 (0.0011) -[2023-11-28 08:06:03,203][87426] Updated weights for policy 1, policy_version 301030 (0.0011) -[2023-11-28 08:06:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 154181632. Throughput: 0: 2790.7, 1: 2686.6. Samples: 154194268. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:06:03,445][86177] Avg episode reward: [(0, '-1142.130'), (1, '-525.850')] -[2023-11-28 08:06:03,579][87426] Updated weights for policy 1, policy_version 301040 (0.0011) -[2023-11-28 08:06:03,971][87426] Updated weights for policy 1, policy_version 301050 (0.0010) -[2023-11-28 08:06:04,220][87424] Updated weights for policy 0, policy_version 301249 (0.0011) -[2023-11-28 08:06:04,586][87424] Updated weights for policy 0, policy_version 301259 (0.0008) -[2023-11-28 08:06:04,972][87424] Updated weights for policy 0, policy_version 301269 (0.0010) -[2023-11-28 08:06:05,345][87424] Updated weights for policy 0, policy_version 301279 (0.0012) -[2023-11-28 08:06:06,394][87426] Updated weights for policy 1, policy_version 301060 (0.0011) -[2023-11-28 08:06:06,763][87426] Updated weights for policy 1, policy_version 301070 (0.0010) -[2023-11-28 08:06:07,145][87426] Updated weights for policy 1, policy_version 301080 (0.0009) -[2023-11-28 08:06:07,861][87424] Updated weights for policy 0, policy_version 301289 (0.0010) -[2023-11-28 08:06:08,255][87424] Updated weights for policy 0, policy_version 301299 (0.0009) -[2023-11-28 08:06:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 154206208. Throughput: 0: 2791.6, 1: 2690.0. Samples: 154226932. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:06:08,445][86177] Avg episode reward: [(0, '-1143.180'), (1, '-514.610')] -[2023-11-28 08:06:08,630][87424] Updated weights for policy 0, policy_version 301309 (0.0007) -[2023-11-28 08:06:08,963][87426] Updated weights for policy 1, policy_version 301090 (0.0008) -[2023-11-28 08:06:09,344][87426] Updated weights for policy 1, policy_version 301100 (0.0011) -[2023-11-28 08:06:09,717][87426] Updated weights for policy 1, policy_version 301110 (0.0010) -[2023-11-28 08:06:10,100][87426] Updated weights for policy 1, policy_version 301120 (0.0010) -[2023-11-28 08:06:10,543][87424] Updated weights for policy 0, policy_version 301319 (0.0010) -[2023-11-28 08:06:10,917][87424] Updated weights for policy 0, policy_version 301329 (0.0011) -[2023-11-28 08:06:11,297][87424] Updated weights for policy 0, policy_version 301339 (0.0007) -[2023-11-28 08:06:12,550][87426] Updated weights for policy 1, policy_version 301130 (0.0012) -[2023-11-28 08:06:12,915][87426] Updated weights for policy 1, policy_version 301140 (0.0012) -[2023-11-28 08:06:13,146][87424] Updated weights for policy 0, policy_version 301349 (0.0009) -[2023-11-28 08:06:13,290][87426] Updated weights for policy 1, policy_version 301150 (0.0011) -[2023-11-28 08:06:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 154238976. Throughput: 0: 2768.8, 1: 2690.7. Samples: 154250972. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:06:13,446][86177] Avg episode reward: [(0, '-1024.010'), (1, '-516.930')] -[2023-11-28 08:06:13,527][87424] Updated weights for policy 0, policy_version 301359 (0.0009) -[2023-11-28 08:06:13,908][87424] Updated weights for policy 0, policy_version 301369 (0.0010) -[2023-11-28 08:06:15,935][87426] Updated weights for policy 1, policy_version 301160 (0.0011) -[2023-11-28 08:06:16,306][87426] Updated weights for policy 1, policy_version 301170 (0.0011) -[2023-11-28 08:06:16,445][87424] Updated weights for policy 0, policy_version 301379 (0.0011) -[2023-11-28 08:06:16,690][87426] Updated weights for policy 1, policy_version 301180 (0.0012) -[2023-11-28 08:06:16,831][87424] Updated weights for policy 0, policy_version 301389 (0.0009) -[2023-11-28 08:06:17,208][87424] Updated weights for policy 0, policy_version 301399 (0.0007) -[2023-11-28 08:06:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 154263552. Throughput: 0: 2745.8, 1: 2681.2. Samples: 154275216. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:06:18,446][86177] Avg episode reward: [(0, '-1104.350'), (1, '-524.780')] -[2023-11-28 08:06:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000301408_77160448.pth... -[2023-11-28 08:06:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000298848_76505088.pth -[2023-11-28 08:06:18,700][87426] Updated weights for policy 1, policy_version 301190 (0.0009) -[2023-11-28 08:06:19,079][87426] Updated weights for policy 1, policy_version 301200 (0.0008) -[2023-11-28 08:06:19,457][87426] Updated weights for policy 1, policy_version 301210 (0.0007) -[2023-11-28 08:06:19,615][87424] Updated weights for policy 0, policy_version 301409 (0.0008) -[2023-11-28 08:06:19,681][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000301216_77111296.pth... -[2023-11-28 08:06:19,711][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000298688_76464128.pth -[2023-11-28 08:06:19,991][87424] Updated weights for policy 0, policy_version 301419 (0.0012) -[2023-11-28 08:06:20,371][87424] Updated weights for policy 0, policy_version 301429 (0.0009) -[2023-11-28 08:06:20,758][87424] Updated weights for policy 0, policy_version 301439 (0.0009) -[2023-11-28 08:06:21,469][87426] Updated weights for policy 1, policy_version 301220 (0.0009) -[2023-11-28 08:06:21,844][87426] Updated weights for policy 1, policy_version 301230 (0.0010) -[2023-11-28 08:06:22,235][87426] Updated weights for policy 1, policy_version 301240 (0.0009) -[2023-11-28 08:06:22,688][87424] Updated weights for policy 0, policy_version 301449 (0.0011) -[2023-11-28 08:06:23,069][87424] Updated weights for policy 0, policy_version 301459 (0.0012) -[2023-11-28 08:06:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 154288128. Throughput: 0: 2721.2, 1: 2706.1. Samples: 154307816. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:06:23,445][86177] Avg episode reward: [(0, '-1025.410'), (1, '-526.170')] -[2023-11-28 08:06:23,451][87424] Updated weights for policy 0, policy_version 301469 (0.0012) -[2023-11-28 08:06:24,673][87426] Updated weights for policy 1, policy_version 301250 (0.0008) -[2023-11-28 08:06:25,053][87426] Updated weights for policy 1, policy_version 301260 (0.0010) -[2023-11-28 08:06:25,246][87424] Updated weights for policy 0, policy_version 301479 (0.0012) -[2023-11-28 08:06:25,449][87426] Updated weights for policy 1, policy_version 301270 (0.0011) -[2023-11-28 08:06:25,631][87424] Updated weights for policy 0, policy_version 301489 (0.0011) -[2023-11-28 08:06:25,820][87426] Updated weights for policy 1, policy_version 301280 (0.0011) -[2023-11-28 08:06:26,011][87424] Updated weights for policy 0, policy_version 301499 (0.0012) -[2023-11-28 08:06:27,557][87426] Updated weights for policy 1, policy_version 301290 (0.0012) -[2023-11-28 08:06:27,653][87424] Updated weights for policy 0, policy_version 301509 (0.0012) -[2023-11-28 08:06:27,942][87426] Updated weights for policy 1, policy_version 301300 (0.0011) -[2023-11-28 08:06:28,038][87424] Updated weights for policy 0, policy_version 301519 (0.0012) -[2023-11-28 08:06:28,322][87426] Updated weights for policy 1, policy_version 301310 (0.0011) -[2023-11-28 08:06:28,424][87424] Updated weights for policy 0, policy_version 301529 (0.0012) -[2023-11-28 08:06:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 154320896. Throughput: 0: 2751.0, 1: 2743.1. Samples: 154334252. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:06:28,445][86177] Avg episode reward: [(0, '-985.360'), (1, '-526.800')] -[2023-11-28 08:06:30,810][87426] Updated weights for policy 1, policy_version 301320 (0.0011) -[2023-11-28 08:06:30,860][87424] Updated weights for policy 0, policy_version 301539 (0.0011) -[2023-11-28 08:06:31,201][87426] Updated weights for policy 1, policy_version 301330 (0.0011) -[2023-11-28 08:06:31,253][87424] Updated weights for policy 0, policy_version 301549 (0.0009) -[2023-11-28 08:06:31,591][87426] Updated weights for policy 1, policy_version 301340 (0.0011) -[2023-11-28 08:06:31,626][87424] Updated weights for policy 0, policy_version 301559 (0.0010) -[2023-11-28 08:06:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 154345472. Throughput: 0: 2760.4, 1: 2743.3. Samples: 154358412. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:06:33,445][86177] Avg episode reward: [(0, '-978.040'), (1, '-521.880')] -[2023-11-28 08:06:33,491][87426] Updated weights for policy 1, policy_version 301350 (0.0011) -[2023-11-28 08:06:33,873][87426] Updated weights for policy 1, policy_version 301360 (0.0012) -[2023-11-28 08:06:34,059][87424] Updated weights for policy 0, policy_version 301569 (0.0009) -[2023-11-28 08:06:34,253][87426] Updated weights for policy 1, policy_version 301370 (0.0009) -[2023-11-28 08:06:34,445][87424] Updated weights for policy 0, policy_version 301579 (0.0012) -[2023-11-28 08:06:34,840][87424] Updated weights for policy 0, policy_version 301589 (0.0012) -[2023-11-28 08:06:35,221][87424] Updated weights for policy 0, policy_version 301599 (0.0012) -[2023-11-28 08:06:36,391][87426] Updated weights for policy 1, policy_version 301380 (0.0008) -[2023-11-28 08:06:36,774][87426] Updated weights for policy 1, policy_version 301390 (0.0009) -[2023-11-28 08:06:37,162][87426] Updated weights for policy 1, policy_version 301400 (0.0010) -[2023-11-28 08:06:37,854][87424] Updated weights for policy 0, policy_version 301609 (0.0010) -[2023-11-28 08:06:38,239][87424] Updated weights for policy 0, policy_version 301619 (0.0008) -[2023-11-28 08:06:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 154370048. Throughput: 0: 2763.2, 1: 2737.9. Samples: 154392384. Policy #0 lag: (min: 13.0, avg: 22.0, max: 45.0) -[2023-11-28 08:06:38,445][86177] Avg episode reward: [(0, '-975.730'), (1, '-511.260')] -[2023-11-28 08:06:38,614][87424] Updated weights for policy 0, policy_version 301629 (0.0007) -[2023-11-28 08:06:39,295][87426] Updated weights for policy 1, policy_version 301410 (0.0011) -[2023-11-28 08:06:39,676][87426] Updated weights for policy 1, policy_version 301420 (0.0012) -[2023-11-28 08:06:40,054][87426] Updated weights for policy 1, policy_version 301430 (0.0012) -[2023-11-28 08:06:40,437][87426] Updated weights for policy 1, policy_version 301440 (0.0012) -[2023-11-28 08:06:40,895][87424] Updated weights for policy 0, policy_version 301639 (0.0010) -[2023-11-28 08:06:41,279][87424] Updated weights for policy 0, policy_version 301649 (0.0012) -[2023-11-28 08:06:41,655][87424] Updated weights for policy 0, policy_version 301659 (0.0012) -[2023-11-28 08:06:42,305][87426] Updated weights for policy 1, policy_version 301450 (0.0012) -[2023-11-28 08:06:42,681][87426] Updated weights for policy 1, policy_version 301460 (0.0012) -[2023-11-28 08:06:43,065][87426] Updated weights for policy 1, policy_version 301470 (0.0012) -[2023-11-28 08:06:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 154402816. Throughput: 0: 2767.5, 1: 2722.1. Samples: 154416720. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:06:43,446][86177] Avg episode reward: [(0, '-1013.620'), (1, '-511.000')] -[2023-11-28 08:06:43,701][87424] Updated weights for policy 0, policy_version 301669 (0.0010) -[2023-11-28 08:06:44,080][87424] Updated weights for policy 0, policy_version 301679 (0.0009) -[2023-11-28 08:06:44,463][87424] Updated weights for policy 0, policy_version 301689 (0.0007) -[2023-11-28 08:06:45,643][87426] Updated weights for policy 1, policy_version 301480 (0.0011) -[2023-11-28 08:06:46,032][87426] Updated weights for policy 1, policy_version 301490 (0.0010) -[2023-11-28 08:06:46,410][87426] Updated weights for policy 1, policy_version 301500 (0.0009) -[2023-11-28 08:06:46,628][87424] Updated weights for policy 0, policy_version 301699 (0.0010) -[2023-11-28 08:06:47,004][87424] Updated weights for policy 0, policy_version 301709 (0.0012) -[2023-11-28 08:06:47,386][87424] Updated weights for policy 0, policy_version 301719 (0.0010) -[2023-11-28 08:06:48,201][87426] Updated weights for policy 1, policy_version 301510 (0.0011) -[2023-11-28 08:06:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 154427392. Throughput: 0: 2743.7, 1: 2723.7. Samples: 154440300. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:06:48,445][86177] Avg episode reward: [(0, '-974.240'), (1, '-512.460')] -[2023-11-28 08:06:48,580][87426] Updated weights for policy 1, policy_version 301520 (0.0008) -[2023-11-28 08:06:48,963][87426] Updated weights for policy 1, policy_version 301530 (0.0008) -[2023-11-28 08:06:49,476][87424] Updated weights for policy 0, policy_version 301729 (0.0011) -[2023-11-28 08:06:49,867][87424] Updated weights for policy 0, policy_version 301739 (0.0011) -[2023-11-28 08:06:50,243][87424] Updated weights for policy 0, policy_version 301749 (0.0008) -[2023-11-28 08:06:50,623][87424] Updated weights for policy 0, policy_version 301759 (0.0008) -[2023-11-28 08:06:51,445][87426] Updated weights for policy 1, policy_version 301540 (0.0008) -[2023-11-28 08:06:51,828][87426] Updated weights for policy 1, policy_version 301550 (0.0010) -[2023-11-28 08:06:52,199][87426] Updated weights for policy 1, policy_version 301560 (0.0009) -[2023-11-28 08:06:52,655][87424] Updated weights for policy 0, policy_version 301769 (0.0011) -[2023-11-28 08:06:53,031][87424] Updated weights for policy 0, policy_version 301779 (0.0012) -[2023-11-28 08:06:53,413][87424] Updated weights for policy 0, policy_version 301789 (0.0012) -[2023-11-28 08:06:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 154451968. Throughput: 0: 2751.8, 1: 2709.1. Samples: 154472672. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:06:53,445][86177] Avg episode reward: [(0, '-902.070'), (1, '-507.490')] -[2023-11-28 08:06:54,466][87426] Updated weights for policy 1, policy_version 301570 (0.0008) -[2023-11-28 08:06:54,847][87426] Updated weights for policy 1, policy_version 301580 (0.0008) -[2023-11-28 08:06:55,222][87426] Updated weights for policy 1, policy_version 301590 (0.0011) -[2023-11-28 08:06:55,604][87426] Updated weights for policy 1, policy_version 301600 (0.0012) -[2023-11-28 08:06:55,652][87424] Updated weights for policy 0, policy_version 301799 (0.0009) -[2023-11-28 08:06:56,039][87424] Updated weights for policy 0, policy_version 301809 (0.0007) -[2023-11-28 08:06:56,423][87424] Updated weights for policy 0, policy_version 301819 (0.0007) -[2023-11-28 08:06:57,623][87426] Updated weights for policy 1, policy_version 301610 (0.0011) -[2023-11-28 08:06:58,005][87426] Updated weights for policy 1, policy_version 301620 (0.0012) -[2023-11-28 08:06:58,337][87424] Updated weights for policy 0, policy_version 301829 (0.0007) -[2023-11-28 08:06:58,393][87426] Updated weights for policy 1, policy_version 301630 (0.0010) -[2023-11-28 08:06:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 154476544. Throughput: 0: 2762.6, 1: 2713.0. Samples: 154497372. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:06:58,445][86177] Avg episode reward: [(0, '-944.010'), (1, '-508.950')] -[2023-11-28 08:06:58,721][87424] Updated weights for policy 0, policy_version 301839 (0.0007) -[2023-11-28 08:06:59,115][87424] Updated weights for policy 0, policy_version 301849 (0.0010) -[2023-11-28 08:07:00,296][87426] Updated weights for policy 1, policy_version 301640 (0.0011) -[2023-11-28 08:07:00,676][87426] Updated weights for policy 1, policy_version 301650 (0.0009) -[2023-11-28 08:07:01,053][87426] Updated weights for policy 1, policy_version 301660 (0.0011) -[2023-11-28 08:07:01,156][87424] Updated weights for policy 0, policy_version 301859 (0.0011) -[2023-11-28 08:07:01,538][87424] Updated weights for policy 0, policy_version 301869 (0.0012) -[2023-11-28 08:07:01,925][87424] Updated weights for policy 0, policy_version 301879 (0.0011) -[2023-11-28 08:07:03,440][87426] Updated weights for policy 1, policy_version 301670 (0.0009) -[2023-11-28 08:07:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 154509312. Throughput: 0: 2772.3, 1: 2723.5. Samples: 154522524. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:03,445][86177] Avg episode reward: [(0, '-965.520'), (1, '-517.980')] -[2023-11-28 08:07:03,814][87426] Updated weights for policy 1, policy_version 301680 (0.0011) -[2023-11-28 08:07:04,089][87424] Updated weights for policy 0, policy_version 301889 (0.0012) -[2023-11-28 08:07:04,194][87426] Updated weights for policy 1, policy_version 301690 (0.0009) -[2023-11-28 08:07:04,473][87424] Updated weights for policy 0, policy_version 301899 (0.0012) -[2023-11-28 08:07:04,866][87424] Updated weights for policy 0, policy_version 301909 (0.0012) -[2023-11-28 08:07:05,246][87424] Updated weights for policy 0, policy_version 301919 (0.0012) -[2023-11-28 08:07:06,751][87426] Updated weights for policy 1, policy_version 301700 (0.0008) -[2023-11-28 08:07:06,985][87424] Updated weights for policy 0, policy_version 301929 (0.0012) -[2023-11-28 08:07:07,140][87426] Updated weights for policy 1, policy_version 301710 (0.0008) -[2023-11-28 08:07:07,368][87424] Updated weights for policy 0, policy_version 301939 (0.0012) -[2023-11-28 08:07:07,508][87426] Updated weights for policy 1, policy_version 301720 (0.0008) -[2023-11-28 08:07:07,749][87424] Updated weights for policy 0, policy_version 301949 (0.0012) -[2023-11-28 08:07:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 154542080. Throughput: 0: 2797.1, 1: 2713.2. Samples: 154555780. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:08,445][86177] Avg episode reward: [(0, '-919.760'), (1, '-523.240')] -[2023-11-28 08:07:09,544][87426] Updated weights for policy 1, policy_version 301730 (0.0011) -[2023-11-28 08:07:09,560][87424] Updated weights for policy 0, policy_version 301959 (0.0011) -[2023-11-28 08:07:09,925][87426] Updated weights for policy 1, policy_version 301740 (0.0012) -[2023-11-28 08:07:09,943][87424] Updated weights for policy 0, policy_version 301969 (0.0011) -[2023-11-28 08:07:10,306][87426] Updated weights for policy 1, policy_version 301750 (0.0012) -[2023-11-28 08:07:10,329][87424] Updated weights for policy 0, policy_version 301979 (0.0011) -[2023-11-28 08:07:10,673][87426] Updated weights for policy 1, policy_version 301760 (0.0008) -[2023-11-28 08:07:12,493][87424] Updated weights for policy 0, policy_version 301989 (0.0012) -[2023-11-28 08:07:12,862][87426] Updated weights for policy 1, policy_version 301770 (0.0011) -[2023-11-28 08:07:12,867][87424] Updated weights for policy 0, policy_version 301999 (0.0010) -[2023-11-28 08:07:13,239][87426] Updated weights for policy 1, policy_version 301780 (0.0011) -[2023-11-28 08:07:13,248][87424] Updated weights for policy 0, policy_version 302009 (0.0011) -[2023-11-28 08:07:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 154558464. Throughput: 0: 2788.1, 1: 2685.0. Samples: 154580540. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:13,446][86177] Avg episode reward: [(0, '-922.010'), (1, '-526.990')] -[2023-11-28 08:07:13,614][87426] Updated weights for policy 1, policy_version 301790 (0.0012) -[2023-11-28 08:07:15,357][87424] Updated weights for policy 0, policy_version 302019 (0.0010) -[2023-11-28 08:07:15,739][87424] Updated weights for policy 0, policy_version 302029 (0.0009) -[2023-11-28 08:07:16,051][87426] Updated weights for policy 1, policy_version 301800 (0.0012) -[2023-11-28 08:07:16,120][87424] Updated weights for policy 0, policy_version 302039 (0.0009) -[2023-11-28 08:07:16,427][87426] Updated weights for policy 1, policy_version 301810 (0.0012) -[2023-11-28 08:07:16,807][87426] Updated weights for policy 1, policy_version 301820 (0.0011) -[2023-11-28 08:07:17,782][87424] Updated weights for policy 0, policy_version 302049 (0.0007) -[2023-11-28 08:07:18,163][87424] Updated weights for policy 0, policy_version 302059 (0.0008) -[2023-11-28 08:07:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 154591232. Throughput: 0: 2799.9, 1: 2689.2. Samples: 154605424. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:18,445][86177] Avg episode reward: [(0, '-921.540'), (1, '-530.230')] -[2023-11-28 08:07:18,544][87424] Updated weights for policy 0, policy_version 302069 (0.0007) -[2023-11-28 08:07:18,755][87426] Updated weights for policy 1, policy_version 301830 (0.0011) -[2023-11-28 08:07:18,926][87424] Updated weights for policy 0, policy_version 302079 (0.0007) -[2023-11-28 08:07:19,131][87426] Updated weights for policy 1, policy_version 301840 (0.0011) -[2023-11-28 08:07:19,511][87426] Updated weights for policy 1, policy_version 301850 (0.0012) -[2023-11-28 08:07:20,983][87424] Updated weights for policy 0, policy_version 302089 (0.0011) -[2023-11-28 08:07:21,357][87424] Updated weights for policy 0, policy_version 302099 (0.0012) -[2023-11-28 08:07:21,743][87424] Updated weights for policy 0, policy_version 302109 (0.0012) -[2023-11-28 08:07:21,832][87426] Updated weights for policy 1, policy_version 301860 (0.0012) -[2023-11-28 08:07:22,209][87426] Updated weights for policy 1, policy_version 301870 (0.0011) -[2023-11-28 08:07:22,583][87426] Updated weights for policy 1, policy_version 301880 (0.0011) -[2023-11-28 08:07:23,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 154624000. Throughput: 0: 2793.5, 1: 2668.3. Samples: 154638164. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:23,445][86177] Avg episode reward: [(0, '-997.280'), (1, '-521.040')] -[2023-11-28 08:07:24,198][87424] Updated weights for policy 0, policy_version 302119 (0.0012) -[2023-11-28 08:07:24,576][87424] Updated weights for policy 0, policy_version 302129 (0.0012) -[2023-11-28 08:07:24,954][87424] Updated weights for policy 0, policy_version 302139 (0.0012) -[2023-11-28 08:07:25,089][87426] Updated weights for policy 1, policy_version 301890 (0.0010) -[2023-11-28 08:07:25,464][87426] Updated weights for policy 1, policy_version 301900 (0.0008) -[2023-11-28 08:07:25,848][87426] Updated weights for policy 1, policy_version 301910 (0.0007) -[2023-11-28 08:07:26,229][87426] Updated weights for policy 1, policy_version 301920 (0.0007) -[2023-11-28 08:07:27,251][87424] Updated weights for policy 0, policy_version 302149 (0.0010) -[2023-11-28 08:07:27,638][87424] Updated weights for policy 0, policy_version 302159 (0.0007) -[2023-11-28 08:07:28,026][87424] Updated weights for policy 0, policy_version 302169 (0.0008) -[2023-11-28 08:07:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 154648576. Throughput: 0: 2777.0, 1: 2683.9. Samples: 154662460. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:28,445][86177] Avg episode reward: [(0, '-1108.300'), (1, '-514.750')] -[2023-11-28 08:07:28,504][87426] Updated weights for policy 1, policy_version 301930 (0.0008) -[2023-11-28 08:07:28,881][87426] Updated weights for policy 1, policy_version 301940 (0.0008) -[2023-11-28 08:07:29,260][87426] Updated weights for policy 1, policy_version 301950 (0.0007) -[2023-11-28 08:07:30,287][87424] Updated weights for policy 0, policy_version 302179 (0.0009) -[2023-11-28 08:07:30,668][87424] Updated weights for policy 0, policy_version 302189 (0.0010) -[2023-11-28 08:07:31,054][87424] Updated weights for policy 0, policy_version 302199 (0.0008) -[2023-11-28 08:07:31,368][87426] Updated weights for policy 1, policy_version 301960 (0.0010) -[2023-11-28 08:07:31,745][87426] Updated weights for policy 1, policy_version 301970 (0.0008) -[2023-11-28 08:07:32,124][87426] Updated weights for policy 1, policy_version 301980 (0.0008) -[2023-11-28 08:07:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 154673152. Throughput: 0: 2798.8, 1: 2696.1. Samples: 154687572. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:33,445][86177] Avg episode reward: [(0, '-1084.390'), (1, '-509.060')] -[2023-11-28 08:07:33,459][87424] Updated weights for policy 0, policy_version 302209 (0.0008) -[2023-11-28 08:07:33,845][87424] Updated weights for policy 0, policy_version 302219 (0.0012) -[2023-11-28 08:07:34,230][87424] Updated weights for policy 0, policy_version 302229 (0.0012) -[2023-11-28 08:07:34,468][87426] Updated weights for policy 1, policy_version 301990 (0.0010) -[2023-11-28 08:07:34,608][87424] Updated weights for policy 0, policy_version 302239 (0.0012) -[2023-11-28 08:07:34,847][87426] Updated weights for policy 1, policy_version 302000 (0.0010) -[2023-11-28 08:07:35,238][87426] Updated weights for policy 1, policy_version 302010 (0.0010) -[2023-11-28 08:07:36,586][87424] Updated weights for policy 0, policy_version 302249 (0.0011) -[2023-11-28 08:07:36,938][87426] Updated weights for policy 1, policy_version 302020 (0.0010) -[2023-11-28 08:07:36,961][87424] Updated weights for policy 0, policy_version 302259 (0.0008) -[2023-11-28 08:07:37,305][87426] Updated weights for policy 1, policy_version 302030 (0.0012) -[2023-11-28 08:07:37,340][87424] Updated weights for policy 0, policy_version 302269 (0.0011) -[2023-11-28 08:07:37,677][87426] Updated weights for policy 1, policy_version 302040 (0.0012) -[2023-11-28 08:07:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 154705920. Throughput: 0: 2795.5, 1: 2698.0. Samples: 154719876. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:38,445][86177] Avg episode reward: [(0, '-1005.190'), (1, '-519.080')] -[2023-11-28 08:07:39,008][87424] Updated weights for policy 0, policy_version 302279 (0.0012) -[2023-11-28 08:07:39,378][87424] Updated weights for policy 0, policy_version 302289 (0.0012) -[2023-11-28 08:07:39,762][87424] Updated weights for policy 0, policy_version 302299 (0.0012) -[2023-11-28 08:07:40,147][87426] Updated weights for policy 1, policy_version 302050 (0.0012) -[2023-11-28 08:07:40,515][87426] Updated weights for policy 1, policy_version 302060 (0.0012) -[2023-11-28 08:07:40,890][87426] Updated weights for policy 1, policy_version 302070 (0.0012) -[2023-11-28 08:07:41,263][87426] Updated weights for policy 1, policy_version 302080 (0.0012) -[2023-11-28 08:07:42,061][87424] Updated weights for policy 0, policy_version 302309 (0.0011) -[2023-11-28 08:07:42,439][87424] Updated weights for policy 0, policy_version 302319 (0.0009) -[2023-11-28 08:07:42,822][87424] Updated weights for policy 0, policy_version 302329 (0.0008) -[2023-11-28 08:07:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 154730496. Throughput: 0: 2798.9, 1: 2680.9. Samples: 154743964. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:43,445][86177] Avg episode reward: [(0, '-1030.400'), (1, '-518.170')] -[2023-11-28 08:07:43,898][87426] Updated weights for policy 1, policy_version 302090 (0.0012) -[2023-11-28 08:07:44,268][87426] Updated weights for policy 1, policy_version 302100 (0.0012) -[2023-11-28 08:07:44,639][87426] Updated weights for policy 1, policy_version 302110 (0.0011) -[2023-11-28 08:07:45,327][87424] Updated weights for policy 0, policy_version 302339 (0.0010) -[2023-11-28 08:07:45,714][87424] Updated weights for policy 0, policy_version 302349 (0.0012) -[2023-11-28 08:07:46,104][87424] Updated weights for policy 0, policy_version 302359 (0.0012) -[2023-11-28 08:07:46,632][87426] Updated weights for policy 1, policy_version 302120 (0.0011) -[2023-11-28 08:07:47,018][87426] Updated weights for policy 1, policy_version 302130 (0.0011) -[2023-11-28 08:07:47,399][87426] Updated weights for policy 1, policy_version 302140 (0.0011) -[2023-11-28 08:07:48,126][87424] Updated weights for policy 0, policy_version 302369 (0.0012) -[2023-11-28 08:07:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 154755072. Throughput: 0: 2784.8, 1: 2690.7. Samples: 154768920. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:48,445][86177] Avg episode reward: [(0, '-991.170'), (1, '-519.550')] -[2023-11-28 08:07:48,505][87424] Updated weights for policy 0, policy_version 302379 (0.0007) -[2023-11-28 08:07:48,889][87424] Updated weights for policy 0, policy_version 302389 (0.0009) -[2023-11-28 08:07:49,027][87426] Updated weights for policy 1, policy_version 302150 (0.0008) -[2023-11-28 08:07:49,268][87424] Updated weights for policy 0, policy_version 302399 (0.0012) -[2023-11-28 08:07:49,406][87426] Updated weights for policy 1, policy_version 302160 (0.0007) -[2023-11-28 08:07:49,785][87426] Updated weights for policy 1, policy_version 302170 (0.0009) -[2023-11-28 08:07:51,404][87424] Updated weights for policy 0, policy_version 302409 (0.0012) -[2023-11-28 08:07:51,791][87424] Updated weights for policy 0, policy_version 302419 (0.0011) -[2023-11-28 08:07:52,170][87424] Updated weights for policy 0, policy_version 302429 (0.0011) -[2023-11-28 08:07:52,231][87426] Updated weights for policy 1, policy_version 302180 (0.0011) -[2023-11-28 08:07:52,616][87426] Updated weights for policy 1, policy_version 302190 (0.0008) -[2023-11-28 08:07:52,983][87426] Updated weights for policy 1, policy_version 302200 (0.0009) -[2023-11-28 08:07:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 154787840. Throughput: 0: 2757.2, 1: 2696.3. Samples: 154801184. Policy #0 lag: (min: 13.0, avg: 33.2, max: 45.0) -[2023-11-28 08:07:53,445][86177] Avg episode reward: [(0, '-844.510'), (1, '-519.140')] -[2023-11-28 08:07:54,365][87424] Updated weights for policy 0, policy_version 302439 (0.0011) -[2023-11-28 08:07:54,744][87424] Updated weights for policy 0, policy_version 302449 (0.0012) -[2023-11-28 08:07:55,128][87424] Updated weights for policy 0, policy_version 302459 (0.0012) -[2023-11-28 08:07:55,376][87426] Updated weights for policy 1, policy_version 302210 (0.0009) -[2023-11-28 08:07:55,751][87426] Updated weights for policy 1, policy_version 302220 (0.0011) -[2023-11-28 08:07:56,141][87426] Updated weights for policy 1, policy_version 302230 (0.0012) -[2023-11-28 08:07:56,510][87426] Updated weights for policy 1, policy_version 302240 (0.0012) -[2023-11-28 08:07:57,329][87424] Updated weights for policy 0, policy_version 302469 (0.0012) -[2023-11-28 08:07:57,720][87424] Updated weights for policy 0, policy_version 302479 (0.0012) -[2023-11-28 08:07:58,097][87424] Updated weights for policy 0, policy_version 302489 (0.0012) -[2023-11-28 08:07:58,366][87426] Updated weights for policy 1, policy_version 302250 (0.0007) -[2023-11-28 08:07:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 154812416. Throughput: 0: 2746.0, 1: 2704.5. Samples: 154825812. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:07:58,445][86177] Avg episode reward: [(0, '-803.730'), (1, '-519.630')] -[2023-11-28 08:07:58,747][87426] Updated weights for policy 1, policy_version 302260 (0.0007) -[2023-11-28 08:07:59,123][87426] Updated weights for policy 1, policy_version 302270 (0.0008) -[2023-11-28 08:07:59,879][87424] Updated weights for policy 0, policy_version 302499 (0.0012) -[2023-11-28 08:08:00,260][87424] Updated weights for policy 0, policy_version 302509 (0.0012) -[2023-11-28 08:08:00,643][87424] Updated weights for policy 0, policy_version 302519 (0.0012) -[2023-11-28 08:08:01,053][87426] Updated weights for policy 1, policy_version 302280 (0.0011) -[2023-11-28 08:08:01,438][87426] Updated weights for policy 1, policy_version 302290 (0.0012) -[2023-11-28 08:08:01,812][87426] Updated weights for policy 1, policy_version 302300 (0.0012) -[2023-11-28 08:08:02,708][87424] Updated weights for policy 0, policy_version 302529 (0.0011) -[2023-11-28 08:08:03,101][87424] Updated weights for policy 0, policy_version 302539 (0.0011) -[2023-11-28 08:08:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 154836992. Throughput: 0: 2760.1, 1: 2709.3. Samples: 154851548. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:03,445][86177] Avg episode reward: [(0, '-767.760'), (1, '-535.380')] -[2023-11-28 08:08:03,482][87424] Updated weights for policy 0, policy_version 302549 (0.0010) -[2023-11-28 08:08:03,736][87426] Updated weights for policy 1, policy_version 302310 (0.0010) -[2023-11-28 08:08:03,863][87424] Updated weights for policy 0, policy_version 302559 (0.0008) -[2023-11-28 08:08:04,115][87426] Updated weights for policy 1, policy_version 302320 (0.0007) -[2023-11-28 08:08:04,494][87426] Updated weights for policy 1, policy_version 302330 (0.0008) -[2023-11-28 08:08:05,540][87424] Updated weights for policy 0, policy_version 302569 (0.0012) -[2023-11-28 08:08:05,937][87424] Updated weights for policy 0, policy_version 302579 (0.0011) -[2023-11-28 08:08:06,313][87424] Updated weights for policy 0, policy_version 302589 (0.0011) -[2023-11-28 08:08:06,893][87426] Updated weights for policy 1, policy_version 302340 (0.0008) -[2023-11-28 08:08:07,277][87426] Updated weights for policy 1, policy_version 302350 (0.0007) -[2023-11-28 08:08:07,646][87426] Updated weights for policy 1, policy_version 302360 (0.0008) -[2023-11-28 08:08:08,407][87424] Updated weights for policy 0, policy_version 302599 (0.0012) -[2023-11-28 08:08:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 154869760. Throughput: 0: 2763.7, 1: 2713.4. Samples: 154884636. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:08,445][86177] Avg episode reward: [(0, '-814.030'), (1, '-546.010')] -[2023-11-28 08:08:08,787][87424] Updated weights for policy 0, policy_version 302609 (0.0012) -[2023-11-28 08:08:09,171][87424] Updated weights for policy 0, policy_version 302619 (0.0012) -[2023-11-28 08:08:09,290][87426] Updated weights for policy 1, policy_version 302370 (0.0011) -[2023-11-28 08:08:09,668][87426] Updated weights for policy 1, policy_version 302380 (0.0011) -[2023-11-28 08:08:10,049][87426] Updated weights for policy 1, policy_version 302390 (0.0011) -[2023-11-28 08:08:10,427][87426] Updated weights for policy 1, policy_version 302400 (0.0009) -[2023-11-28 08:08:11,290][87424] Updated weights for policy 0, policy_version 302629 (0.0012) -[2023-11-28 08:08:11,677][87424] Updated weights for policy 0, policy_version 302639 (0.0012) -[2023-11-28 08:08:12,052][87424] Updated weights for policy 0, policy_version 302649 (0.0009) -[2023-11-28 08:08:12,927][87426] Updated weights for policy 1, policy_version 302410 (0.0011) -[2023-11-28 08:08:13,308][87426] Updated weights for policy 1, policy_version 302420 (0.0012) -[2023-11-28 08:08:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 154894336. Throughput: 0: 2774.0, 1: 2710.6. Samples: 154909268. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:13,445][86177] Avg episode reward: [(0, '-839.970'), (1, '-546.480')] -[2023-11-28 08:08:13,679][87426] Updated weights for policy 1, policy_version 302430 (0.0007) -[2023-11-28 08:08:14,534][87424] Updated weights for policy 0, policy_version 302659 (0.0010) -[2023-11-28 08:08:14,901][87424] Updated weights for policy 0, policy_version 302669 (0.0009) -[2023-11-28 08:08:15,282][87424] Updated weights for policy 0, policy_version 302679 (0.0011) -[2023-11-28 08:08:16,278][87426] Updated weights for policy 1, policy_version 302440 (0.0011) -[2023-11-28 08:08:16,663][87426] Updated weights for policy 1, policy_version 302450 (0.0012) -[2023-11-28 08:08:17,051][87426] Updated weights for policy 1, policy_version 302460 (0.0012) -[2023-11-28 08:08:17,622][87424] Updated weights for policy 0, policy_version 302689 (0.0012) -[2023-11-28 08:08:18,016][87424] Updated weights for policy 0, policy_version 302699 (0.0008) -[2023-11-28 08:08:18,398][87424] Updated weights for policy 0, policy_version 302709 (0.0009) -[2023-11-28 08:08:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 154918912. Throughput: 0: 2743.7, 1: 2714.4. Samples: 154933188. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:18,445][86177] Avg episode reward: [(0, '-804.800'), (1, '-545.680')] -[2023-11-28 08:08:18,682][87426] Updated weights for policy 1, policy_version 302470 (0.0009) -[2023-11-28 08:08:18,775][87424] Updated weights for policy 0, policy_version 302719 (0.0009) -[2023-11-28 08:08:18,812][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000302720_77496320.pth... -[2023-11-28 08:08:18,843][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000300128_76832768.pth -[2023-11-28 08:08:19,057][87426] Updated weights for policy 1, policy_version 302480 (0.0008) -[2023-11-28 08:08:19,444][87426] Updated weights for policy 1, policy_version 302490 (0.0009) -[2023-11-28 08:08:19,657][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000302496_77438976.pth... -[2023-11-28 08:08:19,687][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000299936_76783616.pth -[2023-11-28 08:08:21,270][87424] Updated weights for policy 0, policy_version 302729 (0.0012) -[2023-11-28 08:08:21,645][87424] Updated weights for policy 0, policy_version 302739 (0.0010) -[2023-11-28 08:08:21,711][87426] Updated weights for policy 1, policy_version 302500 (0.0012) -[2023-11-28 08:08:22,034][87424] Updated weights for policy 0, policy_version 302749 (0.0010) -[2023-11-28 08:08:22,090][87426] Updated weights for policy 1, policy_version 302510 (0.0009) -[2023-11-28 08:08:22,468][87426] Updated weights for policy 1, policy_version 302520 (0.0008) -[2023-11-28 08:08:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 154951680. Throughput: 0: 2709.5, 1: 2730.8. Samples: 154964688. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:23,445][86177] Avg episode reward: [(0, '-941.070'), (1, '-552.410')] -[2023-11-28 08:08:24,627][87424] Updated weights for policy 0, policy_version 302759 (0.0008) -[2023-11-28 08:08:25,013][87424] Updated weights for policy 0, policy_version 302769 (0.0007) -[2023-11-28 08:08:25,071][87426] Updated weights for policy 1, policy_version 302530 (0.0008) -[2023-11-28 08:08:25,395][87424] Updated weights for policy 0, policy_version 302779 (0.0007) -[2023-11-28 08:08:25,445][87426] Updated weights for policy 1, policy_version 302540 (0.0008) -[2023-11-28 08:08:25,832][87426] Updated weights for policy 1, policy_version 302550 (0.0008) -[2023-11-28 08:08:26,203][87426] Updated weights for policy 1, policy_version 302560 (0.0007) -[2023-11-28 08:08:27,803][87424] Updated weights for policy 0, policy_version 302789 (0.0010) -[2023-11-28 08:08:28,185][87424] Updated weights for policy 0, policy_version 302799 (0.0011) -[2023-11-28 08:08:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 154968064. Throughput: 0: 2697.2, 1: 2758.8. Samples: 154989488. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:28,445][86177] Avg episode reward: [(0, '-972.650'), (1, '-552.540')] -[2023-11-28 08:08:28,571][87424] Updated weights for policy 0, policy_version 302809 (0.0012) -[2023-11-28 08:08:28,578][87426] Updated weights for policy 1, policy_version 302570 (0.0007) -[2023-11-28 08:08:28,957][87426] Updated weights for policy 1, policy_version 302580 (0.0008) -[2023-11-28 08:08:29,340][87426] Updated weights for policy 1, policy_version 302590 (0.0007) -[2023-11-28 08:08:30,969][87424] Updated weights for policy 0, policy_version 302819 (0.0011) -[2023-11-28 08:08:31,356][87424] Updated weights for policy 0, policy_version 302829 (0.0008) -[2023-11-28 08:08:31,688][87426] Updated weights for policy 1, policy_version 302600 (0.0009) -[2023-11-28 08:08:31,740][87424] Updated weights for policy 0, policy_version 302839 (0.0011) -[2023-11-28 08:08:32,069][87426] Updated weights for policy 1, policy_version 302610 (0.0011) -[2023-11-28 08:08:32,453][87426] Updated weights for policy 1, policy_version 302620 (0.0011) -[2023-11-28 08:08:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 155000832. Throughput: 0: 2664.4, 1: 2734.8. Samples: 155011888. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:33,445][86177] Avg episode reward: [(0, '-972.420'), (1, '-559.900')] -[2023-11-28 08:08:33,589][87424] Updated weights for policy 0, policy_version 302849 (0.0010) -[2023-11-28 08:08:33,979][87424] Updated weights for policy 0, policy_version 302859 (0.0008) -[2023-11-28 08:08:34,364][87424] Updated weights for policy 0, policy_version 302869 (0.0007) -[2023-11-28 08:08:34,373][87426] Updated weights for policy 1, policy_version 302630 (0.0011) -[2023-11-28 08:08:34,747][87424] Updated weights for policy 0, policy_version 302879 (0.0008) -[2023-11-28 08:08:34,755][87426] Updated weights for policy 1, policy_version 302640 (0.0012) -[2023-11-28 08:08:35,139][87426] Updated weights for policy 1, policy_version 302650 (0.0011) -[2023-11-28 08:08:36,831][87426] Updated weights for policy 1, policy_version 302660 (0.0010) -[2023-11-28 08:08:36,868][87424] Updated weights for policy 0, policy_version 302889 (0.0009) -[2023-11-28 08:08:37,212][87426] Updated weights for policy 1, policy_version 302670 (0.0009) -[2023-11-28 08:08:37,254][87424] Updated weights for policy 0, policy_version 302899 (0.0010) -[2023-11-28 08:08:37,590][87426] Updated weights for policy 1, policy_version 302680 (0.0010) -[2023-11-28 08:08:37,625][87424] Updated weights for policy 0, policy_version 302909 (0.0011) -[2023-11-28 08:08:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 155033600. Throughput: 0: 2666.1, 1: 2742.3. Samples: 155044564. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:38,445][86177] Avg episode reward: [(0, '-934.940'), (1, '-558.170')] -[2023-11-28 08:08:39,441][87426] Updated weights for policy 1, policy_version 302690 (0.0009) -[2023-11-28 08:08:39,457][87424] Updated weights for policy 0, policy_version 302919 (0.0011) -[2023-11-28 08:08:39,817][87426] Updated weights for policy 1, policy_version 302700 (0.0011) -[2023-11-28 08:08:39,835][87424] Updated weights for policy 0, policy_version 302929 (0.0011) -[2023-11-28 08:08:40,201][87426] Updated weights for policy 1, policy_version 302710 (0.0011) -[2023-11-28 08:08:40,219][87424] Updated weights for policy 0, policy_version 302939 (0.0012) -[2023-11-28 08:08:40,571][87426] Updated weights for policy 1, policy_version 302720 (0.0011) -[2023-11-28 08:08:42,342][87424] Updated weights for policy 0, policy_version 302949 (0.0012) -[2023-11-28 08:08:42,721][87424] Updated weights for policy 0, policy_version 302959 (0.0010) -[2023-11-28 08:08:43,115][87424] Updated weights for policy 0, policy_version 302969 (0.0010) -[2023-11-28 08:08:43,140][87426] Updated weights for policy 1, policy_version 302730 (0.0010) -[2023-11-28 08:08:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 155058176. Throughput: 0: 2670.2, 1: 2731.6. Samples: 155068892. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:43,445][86177] Avg episode reward: [(0, '-909.500'), (1, '-537.850')] -[2023-11-28 08:08:43,516][87426] Updated weights for policy 1, policy_version 302740 (0.0009) -[2023-11-28 08:08:43,890][87426] Updated weights for policy 1, policy_version 302750 (0.0010) -[2023-11-28 08:08:45,278][87424] Updated weights for policy 0, policy_version 302979 (0.0011) -[2023-11-28 08:08:45,648][87424] Updated weights for policy 0, policy_version 302989 (0.0009) -[2023-11-28 08:08:46,036][87424] Updated weights for policy 0, policy_version 302999 (0.0007) -[2023-11-28 08:08:46,401][87426] Updated weights for policy 1, policy_version 302760 (0.0007) -[2023-11-28 08:08:46,785][87426] Updated weights for policy 1, policy_version 302770 (0.0008) -[2023-11-28 08:08:47,171][87426] Updated weights for policy 1, policy_version 302780 (0.0009) -[2023-11-28 08:08:48,314][87424] Updated weights for policy 0, policy_version 303009 (0.0008) -[2023-11-28 08:08:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 155082752. Throughput: 0: 2654.7, 1: 2714.0. Samples: 155093140. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:48,445][86177] Avg episode reward: [(0, '-883.280'), (1, '-528.570')] -[2023-11-28 08:08:48,691][87424] Updated weights for policy 0, policy_version 303019 (0.0009) -[2023-11-28 08:08:49,073][87424] Updated weights for policy 0, policy_version 303029 (0.0009) -[2023-11-28 08:08:49,456][87424] Updated weights for policy 0, policy_version 303039 (0.0011) -[2023-11-28 08:08:49,654][87426] Updated weights for policy 1, policy_version 302790 (0.0007) -[2023-11-28 08:08:50,034][87426] Updated weights for policy 1, policy_version 302800 (0.0011) -[2023-11-28 08:08:50,416][87426] Updated weights for policy 1, policy_version 302810 (0.0011) -[2023-11-28 08:08:51,621][87424] Updated weights for policy 0, policy_version 303049 (0.0010) -[2023-11-28 08:08:51,995][87424] Updated weights for policy 0, policy_version 303059 (0.0012) -[2023-11-28 08:08:52,383][87424] Updated weights for policy 0, policy_version 303069 (0.0010) -[2023-11-28 08:08:52,640][87426] Updated weights for policy 1, policy_version 302820 (0.0011) -[2023-11-28 08:08:53,014][87426] Updated weights for policy 1, policy_version 302830 (0.0010) -[2023-11-28 08:08:53,395][87426] Updated weights for policy 1, policy_version 302840 (0.0010) -[2023-11-28 08:08:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 155107328. Throughput: 0: 2646.9, 1: 2696.3. Samples: 155125080. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:53,445][86177] Avg episode reward: [(0, '-705.280'), (1, '-524.740')] -[2023-11-28 08:08:54,788][87424] Updated weights for policy 0, policy_version 303079 (0.0010) -[2023-11-28 08:08:55,171][87424] Updated weights for policy 0, policy_version 303089 (0.0012) -[2023-11-28 08:08:55,550][87424] Updated weights for policy 0, policy_version 303099 (0.0011) -[2023-11-28 08:08:55,919][87426] Updated weights for policy 1, policy_version 302850 (0.0012) -[2023-11-28 08:08:56,296][87426] Updated weights for policy 1, policy_version 302860 (0.0012) -[2023-11-28 08:08:56,679][87426] Updated weights for policy 1, policy_version 302870 (0.0011) -[2023-11-28 08:08:57,067][87426] Updated weights for policy 1, policy_version 302880 (0.0007) -[2023-11-28 08:08:57,475][87424] Updated weights for policy 0, policy_version 303109 (0.0009) -[2023-11-28 08:08:57,862][87424] Updated weights for policy 0, policy_version 303119 (0.0007) -[2023-11-28 08:08:58,245][87424] Updated weights for policy 0, policy_version 303129 (0.0008) -[2023-11-28 08:08:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 155131904. Throughput: 0: 2646.1, 1: 2712.0. Samples: 155150380. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:08:58,445][86177] Avg episode reward: [(0, '-717.170'), (1, '-554.980')] -[2023-11-28 08:08:59,055][87426] Updated weights for policy 1, policy_version 302890 (0.0012) -[2023-11-28 08:08:59,430][87426] Updated weights for policy 1, policy_version 302900 (0.0012) -[2023-11-28 08:08:59,823][87426] Updated weights for policy 1, policy_version 302910 (0.0012) -[2023-11-28 08:09:00,014][87424] Updated weights for policy 0, policy_version 303139 (0.0009) -[2023-11-28 08:09:00,387][87424] Updated weights for policy 0, policy_version 303149 (0.0012) -[2023-11-28 08:09:00,777][87424] Updated weights for policy 0, policy_version 303159 (0.0008) -[2023-11-28 08:09:01,883][87426] Updated weights for policy 1, policy_version 302920 (0.0011) -[2023-11-28 08:09:02,263][87426] Updated weights for policy 1, policy_version 302930 (0.0011) -[2023-11-28 08:09:02,650][87426] Updated weights for policy 1, policy_version 302940 (0.0012) -[2023-11-28 08:09:02,988][87424] Updated weights for policy 0, policy_version 303169 (0.0009) -[2023-11-28 08:09:03,379][87424] Updated weights for policy 0, policy_version 303179 (0.0010) -[2023-11-28 08:09:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 155164672. Throughput: 0: 2694.4, 1: 2721.7. Samples: 155176912. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:09:03,445][86177] Avg episode reward: [(0, '-722.650'), (1, '-557.310')] -[2023-11-28 08:09:03,767][87424] Updated weights for policy 0, policy_version 303189 (0.0011) -[2023-11-28 08:09:04,151][87424] Updated weights for policy 0, policy_version 303199 (0.0012) -[2023-11-28 08:09:05,107][87426] Updated weights for policy 1, policy_version 302950 (0.0012) -[2023-11-28 08:09:05,482][87426] Updated weights for policy 1, policy_version 302960 (0.0009) -[2023-11-28 08:09:05,862][87426] Updated weights for policy 1, policy_version 302970 (0.0011) -[2023-11-28 08:09:06,277][87424] Updated weights for policy 0, policy_version 303209 (0.0008) -[2023-11-28 08:09:06,663][87424] Updated weights for policy 0, policy_version 303219 (0.0008) -[2023-11-28 08:09:07,046][87424] Updated weights for policy 0, policy_version 303229 (0.0011) -[2023-11-28 08:09:08,394][87426] Updated weights for policy 1, policy_version 302980 (0.0011) -[2023-11-28 08:09:08,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 155189248. Throughput: 0: 2731.8, 1: 2716.2. Samples: 155209848. Policy #0 lag: (min: 31.0, avg: 48.0, max: 63.0) -[2023-11-28 08:09:08,446][86177] Avg episode reward: [(0, '-688.070'), (1, '-556.810')] -[2023-11-28 08:09:08,790][87426] Updated weights for policy 1, policy_version 302990 (0.0012) -[2023-11-28 08:09:09,167][87426] Updated weights for policy 1, policy_version 303000 (0.0012) -[2023-11-28 08:09:09,529][87424] Updated weights for policy 0, policy_version 303239 (0.0009) -[2023-11-28 08:09:09,902][87424] Updated weights for policy 0, policy_version 303249 (0.0012) -[2023-11-28 08:09:10,289][87424] Updated weights for policy 0, policy_version 303259 (0.0012) -[2023-11-28 08:09:11,157][87426] Updated weights for policy 1, policy_version 303010 (0.0012) -[2023-11-28 08:09:11,522][87426] Updated weights for policy 1, policy_version 303020 (0.0009) -[2023-11-28 08:09:11,909][87426] Updated weights for policy 1, policy_version 303030 (0.0011) -[2023-11-28 08:09:12,279][87426] Updated weights for policy 1, policy_version 303040 (0.0011) -[2023-11-28 08:09:12,507][87424] Updated weights for policy 0, policy_version 303269 (0.0011) -[2023-11-28 08:09:12,879][87424] Updated weights for policy 0, policy_version 303279 (0.0011) -[2023-11-28 08:09:13,259][87424] Updated weights for policy 0, policy_version 303289 (0.0012) -[2023-11-28 08:09:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 155213824. Throughput: 0: 2725.8, 1: 2694.0. Samples: 155233380. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:13,445][86177] Avg episode reward: [(0, '-708.940'), (1, '-559.090')] -[2023-11-28 08:09:14,528][87426] Updated weights for policy 1, policy_version 303050 (0.0007) -[2023-11-28 08:09:14,902][87426] Updated weights for policy 1, policy_version 303060 (0.0008) -[2023-11-28 08:09:15,237][87424] Updated weights for policy 0, policy_version 303299 (0.0011) -[2023-11-28 08:09:15,287][87426] Updated weights for policy 1, policy_version 303070 (0.0008) -[2023-11-28 08:09:15,617][87424] Updated weights for policy 0, policy_version 303309 (0.0011) -[2023-11-28 08:09:16,011][87424] Updated weights for policy 0, policy_version 303319 (0.0011) -[2023-11-28 08:09:17,377][87426] Updated weights for policy 1, policy_version 303080 (0.0008) -[2023-11-28 08:09:17,764][87426] Updated weights for policy 1, policy_version 303090 (0.0010) -[2023-11-28 08:09:18,128][87426] Updated weights for policy 1, policy_version 303100 (0.0011) -[2023-11-28 08:09:18,321][87424] Updated weights for policy 0, policy_version 303329 (0.0010) -[2023-11-28 08:09:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 155246592. Throughput: 0: 2750.9, 1: 2695.6. Samples: 155256980. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:18,445][86177] Avg episode reward: [(0, '-744.470'), (1, '-545.840')] -[2023-11-28 08:09:18,704][87424] Updated weights for policy 0, policy_version 303339 (0.0007) -[2023-11-28 08:09:19,085][87424] Updated weights for policy 0, policy_version 303349 (0.0009) -[2023-11-28 08:09:19,480][87424] Updated weights for policy 0, policy_version 303359 (0.0010) -[2023-11-28 08:09:20,533][87426] Updated weights for policy 1, policy_version 303110 (0.0011) -[2023-11-28 08:09:20,911][87426] Updated weights for policy 1, policy_version 303120 (0.0009) -[2023-11-28 08:09:21,287][87426] Updated weights for policy 1, policy_version 303130 (0.0008) -[2023-11-28 08:09:21,699][87424] Updated weights for policy 0, policy_version 303369 (0.0011) -[2023-11-28 08:09:22,081][87424] Updated weights for policy 0, policy_version 303379 (0.0009) -[2023-11-28 08:09:22,467][87424] Updated weights for policy 0, policy_version 303389 (0.0010) -[2023-11-28 08:09:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 155271168. Throughput: 0: 2739.7, 1: 2673.4. Samples: 155288156. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:23,445][86177] Avg episode reward: [(0, '-762.360'), (1, '-548.080')] -[2023-11-28 08:09:23,533][87426] Updated weights for policy 1, policy_version 303140 (0.0009) -[2023-11-28 08:09:23,908][87426] Updated weights for policy 1, policy_version 303150 (0.0010) -[2023-11-28 08:09:24,297][87426] Updated weights for policy 1, policy_version 303160 (0.0012) -[2023-11-28 08:09:24,510][87424] Updated weights for policy 0, policy_version 303399 (0.0012) -[2023-11-28 08:09:24,891][87424] Updated weights for policy 0, policy_version 303409 (0.0011) -[2023-11-28 08:09:25,277][87424] Updated weights for policy 0, policy_version 303419 (0.0011) -[2023-11-28 08:09:25,997][87426] Updated weights for policy 1, policy_version 303170 (0.0011) -[2023-11-28 08:09:26,384][87426] Updated weights for policy 1, policy_version 303180 (0.0007) -[2023-11-28 08:09:26,775][87426] Updated weights for policy 1, policy_version 303190 (0.0008) -[2023-11-28 08:09:27,144][87426] Updated weights for policy 1, policy_version 303200 (0.0007) -[2023-11-28 08:09:27,788][87424] Updated weights for policy 0, policy_version 303429 (0.0008) -[2023-11-28 08:09:28,166][87424] Updated weights for policy 0, policy_version 303439 (0.0007) -[2023-11-28 08:09:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 155295744. Throughput: 0: 2728.7, 1: 2706.2. Samples: 155313464. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:28,445][86177] Avg episode reward: [(0, '-821.550'), (1, '-545.960')] -[2023-11-28 08:09:28,555][87424] Updated weights for policy 0, policy_version 303449 (0.0009) -[2023-11-28 08:09:28,979][87426] Updated weights for policy 1, policy_version 303210 (0.0008) -[2023-11-28 08:09:29,356][87426] Updated weights for policy 1, policy_version 303220 (0.0011) -[2023-11-28 08:09:29,728][87426] Updated weights for policy 1, policy_version 303230 (0.0011) -[2023-11-28 08:09:30,775][87424] Updated weights for policy 0, policy_version 303459 (0.0010) -[2023-11-28 08:09:31,149][87424] Updated weights for policy 0, policy_version 303469 (0.0008) -[2023-11-28 08:09:31,536][87424] Updated weights for policy 0, policy_version 303479 (0.0007) -[2023-11-28 08:09:31,606][87426] Updated weights for policy 1, policy_version 303240 (0.0008) -[2023-11-28 08:09:31,976][87426] Updated weights for policy 1, policy_version 303250 (0.0010) -[2023-11-28 08:09:32,353][87426] Updated weights for policy 1, policy_version 303260 (0.0009) -[2023-11-28 08:09:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 155328512. Throughput: 0: 2698.7, 1: 2719.8. Samples: 155336972. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:33,445][86177] Avg episode reward: [(0, '-900.370'), (1, '-549.930')] -[2023-11-28 08:09:34,042][87424] Updated weights for policy 0, policy_version 303489 (0.0011) -[2023-11-28 08:09:34,421][87424] Updated weights for policy 0, policy_version 303499 (0.0007) -[2023-11-28 08:09:34,809][87424] Updated weights for policy 0, policy_version 303509 (0.0008) -[2023-11-28 08:09:34,840][87426] Updated weights for policy 1, policy_version 303270 (0.0008) -[2023-11-28 08:09:35,187][87424] Updated weights for policy 0, policy_version 303519 (0.0010) -[2023-11-28 08:09:35,205][87426] Updated weights for policy 1, policy_version 303280 (0.0008) -[2023-11-28 08:09:35,582][87426] Updated weights for policy 1, policy_version 303290 (0.0008) -[2023-11-28 08:09:37,617][87424] Updated weights for policy 0, policy_version 303529 (0.0008) -[2023-11-28 08:09:38,004][87424] Updated weights for policy 0, policy_version 303539 (0.0009) -[2023-11-28 08:09:38,096][87426] Updated weights for policy 1, policy_version 303300 (0.0009) -[2023-11-28 08:09:38,385][87424] Updated weights for policy 0, policy_version 303549 (0.0008) -[2023-11-28 08:09:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 155344896. Throughput: 0: 2706.8, 1: 2730.2. Samples: 155369748. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:38,445][86177] Avg episode reward: [(0, '-886.270'), (1, '-531.240')] -[2023-11-28 08:09:38,478][87426] Updated weights for policy 1, policy_version 303310 (0.0010) -[2023-11-28 08:09:38,869][87426] Updated weights for policy 1, policy_version 303320 (0.0012) -[2023-11-28 08:09:40,729][87424] Updated weights for policy 0, policy_version 303559 (0.0012) -[2023-11-28 08:09:41,106][87424] Updated weights for policy 0, policy_version 303569 (0.0012) -[2023-11-28 08:09:41,421][87426] Updated weights for policy 1, policy_version 303330 (0.0010) -[2023-11-28 08:09:41,499][87424] Updated weights for policy 0, policy_version 303579 (0.0010) -[2023-11-28 08:09:41,809][87426] Updated weights for policy 1, policy_version 303340 (0.0011) -[2023-11-28 08:09:42,180][87426] Updated weights for policy 1, policy_version 303350 (0.0012) -[2023-11-28 08:09:42,558][87426] Updated weights for policy 1, policy_version 303360 (0.0012) -[2023-11-28 08:09:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 155377664. Throughput: 0: 2703.5, 1: 2690.7. Samples: 155393116. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:43,445][86177] Avg episode reward: [(0, '-834.740'), (1, '-538.980')] -[2023-11-28 08:09:43,502][87424] Updated weights for policy 0, policy_version 303589 (0.0008) -[2023-11-28 08:09:43,902][87424] Updated weights for policy 0, policy_version 303599 (0.0007) -[2023-11-28 08:09:44,275][87424] Updated weights for policy 0, policy_version 303609 (0.0008) -[2023-11-28 08:09:44,873][87426] Updated weights for policy 1, policy_version 303370 (0.0008) -[2023-11-28 08:09:45,258][87426] Updated weights for policy 1, policy_version 303380 (0.0008) -[2023-11-28 08:09:45,635][87426] Updated weights for policy 1, policy_version 303390 (0.0008) -[2023-11-28 08:09:46,644][87424] Updated weights for policy 0, policy_version 303619 (0.0007) -[2023-11-28 08:09:47,019][87424] Updated weights for policy 0, policy_version 303629 (0.0007) -[2023-11-28 08:09:47,404][87424] Updated weights for policy 0, policy_version 303639 (0.0009) -[2023-11-28 08:09:47,658][87426] Updated weights for policy 1, policy_version 303400 (0.0007) -[2023-11-28 08:09:48,040][87426] Updated weights for policy 1, policy_version 303410 (0.0008) -[2023-11-28 08:09:48,417][87426] Updated weights for policy 1, policy_version 303420 (0.0008) -[2023-11-28 08:09:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 155402240. Throughput: 0: 2653.3, 1: 2672.6. Samples: 155416580. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:48,445][86177] Avg episode reward: [(0, '-814.490'), (1, '-539.290')] -[2023-11-28 08:09:49,889][87424] Updated weights for policy 0, policy_version 303649 (0.0010) -[2023-11-28 08:09:50,275][87424] Updated weights for policy 0, policy_version 303659 (0.0012) -[2023-11-28 08:09:50,581][87426] Updated weights for policy 1, policy_version 303430 (0.0009) -[2023-11-28 08:09:50,642][87424] Updated weights for policy 0, policy_version 303669 (0.0011) -[2023-11-28 08:09:50,965][87426] Updated weights for policy 1, policy_version 303440 (0.0008) -[2023-11-28 08:09:51,024][87424] Updated weights for policy 0, policy_version 303679 (0.0010) -[2023-11-28 08:09:51,339][87426] Updated weights for policy 1, policy_version 303450 (0.0009) -[2023-11-28 08:09:53,193][87426] Updated weights for policy 1, policy_version 303460 (0.0009) -[2023-11-28 08:09:53,315][87424] Updated weights for policy 0, policy_version 303689 (0.0011) -[2023-11-28 08:09:53,448][86177] Fps is (10 sec: 4913.4, 60 sec: 5324.5, 300 sec: 5415.0). Total num frames: 155426816. Throughput: 0: 2628.6, 1: 2698.1. Samples: 155449568. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:53,449][86177] Avg episode reward: [(0, '-731.760'), (1, '-532.690')] -[2023-11-28 08:09:53,580][87426] Updated weights for policy 1, policy_version 303470 (0.0010) -[2023-11-28 08:09:53,703][87424] Updated weights for policy 0, policy_version 303699 (0.0010) -[2023-11-28 08:09:53,955][87426] Updated weights for policy 1, policy_version 303480 (0.0012) -[2023-11-28 08:09:54,082][87424] Updated weights for policy 0, policy_version 303709 (0.0011) -[2023-11-28 08:09:56,010][87424] Updated weights for policy 0, policy_version 303719 (0.0010) -[2023-11-28 08:09:56,218][87426] Updated weights for policy 1, policy_version 303490 (0.0011) -[2023-11-28 08:09:56,391][87424] Updated weights for policy 0, policy_version 303729 (0.0008) -[2023-11-28 08:09:56,599][87426] Updated weights for policy 1, policy_version 303500 (0.0012) -[2023-11-28 08:09:56,769][87424] Updated weights for policy 0, policy_version 303739 (0.0008) -[2023-11-28 08:09:56,984][87426] Updated weights for policy 1, policy_version 303510 (0.0008) -[2023-11-28 08:09:57,375][87426] Updated weights for policy 1, policy_version 303520 (0.0008) -[2023-11-28 08:09:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 155459584. Throughput: 0: 2658.7, 1: 2710.5. Samples: 155474992. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:09:58,445][86177] Avg episode reward: [(0, '-675.160'), (1, '-526.820')] -[2023-11-28 08:09:58,690][87424] Updated weights for policy 0, policy_version 303749 (0.0010) -[2023-11-28 08:09:59,060][87424] Updated weights for policy 0, policy_version 303759 (0.0010) -[2023-11-28 08:09:59,187][87426] Updated weights for policy 1, policy_version 303530 (0.0008) -[2023-11-28 08:09:59,441][87424] Updated weights for policy 0, policy_version 303769 (0.0008) -[2023-11-28 08:09:59,559][87426] Updated weights for policy 1, policy_version 303540 (0.0008) -[2023-11-28 08:09:59,941][87426] Updated weights for policy 1, policy_version 303550 (0.0009) -[2023-11-28 08:10:01,653][87424] Updated weights for policy 0, policy_version 303779 (0.0009) -[2023-11-28 08:10:02,044][87424] Updated weights for policy 0, policy_version 303789 (0.0012) -[2023-11-28 08:10:02,112][87426] Updated weights for policy 1, policy_version 303560 (0.0010) -[2023-11-28 08:10:02,421][87424] Updated weights for policy 0, policy_version 303799 (0.0012) -[2023-11-28 08:10:02,496][87426] Updated weights for policy 1, policy_version 303570 (0.0011) -[2023-11-28 08:10:02,873][87426] Updated weights for policy 1, policy_version 303580 (0.0011) -[2023-11-28 08:10:03,444][86177] Fps is (10 sec: 6556.0, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 155492352. Throughput: 0: 2665.4, 1: 2721.1. Samples: 155499372. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:10:03,445][86177] Avg episode reward: [(0, '-637.060'), (1, '-539.420')] -[2023-11-28 08:10:04,745][87424] Updated weights for policy 0, policy_version 303809 (0.0008) -[2023-11-28 08:10:05,123][87424] Updated weights for policy 0, policy_version 303819 (0.0009) -[2023-11-28 08:10:05,314][87426] Updated weights for policy 1, policy_version 303590 (0.0010) -[2023-11-28 08:10:05,509][87424] Updated weights for policy 0, policy_version 303829 (0.0008) -[2023-11-28 08:10:05,679][87426] Updated weights for policy 1, policy_version 303600 (0.0010) -[2023-11-28 08:10:05,887][87424] Updated weights for policy 0, policy_version 303839 (0.0007) -[2023-11-28 08:10:06,079][87426] Updated weights for policy 1, policy_version 303610 (0.0011) -[2023-11-28 08:10:07,475][87424] Updated weights for policy 0, policy_version 303849 (0.0008) -[2023-11-28 08:10:07,867][87424] Updated weights for policy 0, policy_version 303859 (0.0007) -[2023-11-28 08:10:08,239][87424] Updated weights for policy 0, policy_version 303869 (0.0007) -[2023-11-28 08:10:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 155516928. Throughput: 0: 2701.2, 1: 2702.0. Samples: 155531304. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:10:08,445][86177] Avg episode reward: [(0, '-603.860'), (1, '-545.430')] -[2023-11-28 08:10:08,625][87426] Updated weights for policy 1, policy_version 303620 (0.0010) -[2023-11-28 08:10:08,989][87426] Updated weights for policy 1, policy_version 303630 (0.0010) -[2023-11-28 08:10:09,374][87426] Updated weights for policy 1, policy_version 303640 (0.0007) -[2023-11-28 08:10:10,520][87424] Updated weights for policy 0, policy_version 303879 (0.0010) -[2023-11-28 08:10:10,896][87424] Updated weights for policy 0, policy_version 303889 (0.0008) -[2023-11-28 08:10:11,275][87424] Updated weights for policy 0, policy_version 303899 (0.0011) -[2023-11-28 08:10:11,585][87426] Updated weights for policy 1, policy_version 303650 (0.0010) -[2023-11-28 08:10:11,976][87426] Updated weights for policy 1, policy_version 303660 (0.0011) -[2023-11-28 08:10:12,349][87426] Updated weights for policy 1, policy_version 303670 (0.0011) -[2023-11-28 08:10:12,723][87426] Updated weights for policy 1, policy_version 303680 (0.0012) -[2023-11-28 08:10:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 155541504. Throughput: 0: 2716.0, 1: 2661.6. Samples: 155555456. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:10:13,445][86177] Avg episode reward: [(0, '-622.240'), (1, '-563.510')] -[2023-11-28 08:10:13,860][87424] Updated weights for policy 0, policy_version 303909 (0.0012) -[2023-11-28 08:10:14,240][87424] Updated weights for policy 0, policy_version 303919 (0.0011) -[2023-11-28 08:10:14,607][87426] Updated weights for policy 1, policy_version 303690 (0.0011) -[2023-11-28 08:10:14,619][87424] Updated weights for policy 0, policy_version 303929 (0.0012) -[2023-11-28 08:10:14,987][87426] Updated weights for policy 1, policy_version 303700 (0.0011) -[2023-11-28 08:10:15,376][87426] Updated weights for policy 1, policy_version 303710 (0.0012) -[2023-11-28 08:10:16,854][87424] Updated weights for policy 0, policy_version 303939 (0.0011) -[2023-11-28 08:10:17,248][87424] Updated weights for policy 0, policy_version 303949 (0.0010) -[2023-11-28 08:10:17,635][87424] Updated weights for policy 0, policy_version 303959 (0.0010) -[2023-11-28 08:10:17,846][87426] Updated weights for policy 1, policy_version 303720 (0.0012) -[2023-11-28 08:10:18,241][87426] Updated weights for policy 1, policy_version 303730 (0.0012) -[2023-11-28 08:10:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 155566080. Throughput: 0: 2721.9, 1: 2667.4. Samples: 155579492. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:10:18,445][86177] Avg episode reward: [(0, '-658.870'), (1, '-576.110')] -[2023-11-28 08:10:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000303968_77815808.pth... -[2023-11-28 08:10:18,499][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000301408_77160448.pth -[2023-11-28 08:10:18,615][87426] Updated weights for policy 1, policy_version 303740 (0.0012) -[2023-11-28 08:10:18,771][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000303744_77758464.pth... -[2023-11-28 08:10:18,817][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000301216_77111296.pth -[2023-11-28 08:10:20,203][87424] Updated weights for policy 0, policy_version 303969 (0.0011) -[2023-11-28 08:10:20,589][87424] Updated weights for policy 0, policy_version 303979 (0.0009) -[2023-11-28 08:10:20,975][87424] Updated weights for policy 0, policy_version 303989 (0.0011) -[2023-11-28 08:10:21,173][87426] Updated weights for policy 1, policy_version 303750 (0.0011) -[2023-11-28 08:10:21,358][87424] Updated weights for policy 0, policy_version 303999 (0.0010) -[2023-11-28 08:10:21,547][87426] Updated weights for policy 1, policy_version 303760 (0.0011) -[2023-11-28 08:10:21,932][87426] Updated weights for policy 1, policy_version 303770 (0.0012) -[2023-11-28 08:10:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 155590656. Throughput: 0: 2697.5, 1: 2656.9. Samples: 155610696. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 08:10:23,445][86177] Avg episode reward: [(0, '-627.240'), (1, '-539.750')] -[2023-11-28 08:10:23,569][87424] Updated weights for policy 0, policy_version 304009 (0.0008) -[2023-11-28 08:10:23,955][87424] Updated weights for policy 0, policy_version 304019 (0.0007) -[2023-11-28 08:10:24,331][87424] Updated weights for policy 0, policy_version 304029 (0.0007) -[2023-11-28 08:10:24,408][87426] Updated weights for policy 1, policy_version 303780 (0.0010) -[2023-11-28 08:10:24,792][87426] Updated weights for policy 1, policy_version 303790 (0.0007) -[2023-11-28 08:10:25,168][87426] Updated weights for policy 1, policy_version 303800 (0.0007) -[2023-11-28 08:10:26,723][87424] Updated weights for policy 0, policy_version 304039 (0.0009) -[2023-11-28 08:10:27,111][87424] Updated weights for policy 0, policy_version 304049 (0.0011) -[2023-11-28 08:10:27,493][87424] Updated weights for policy 0, policy_version 304059 (0.0007) -[2023-11-28 08:10:27,663][87426] Updated weights for policy 1, policy_version 303810 (0.0008) -[2023-11-28 08:10:28,045][87426] Updated weights for policy 1, policy_version 303820 (0.0007) -[2023-11-28 08:10:28,421][87426] Updated weights for policy 1, policy_version 303830 (0.0008) -[2023-11-28 08:10:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 155615232. Throughput: 0: 2687.8, 1: 2674.8. Samples: 155634436. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:10:28,445][86177] Avg episode reward: [(0, '-633.450'), (1, '-540.460')] -[2023-11-28 08:10:28,802][87426] Updated weights for policy 1, policy_version 303840 (0.0009) -[2023-11-28 08:10:29,806][87424] Updated weights for policy 0, policy_version 304069 (0.0009) -[2023-11-28 08:10:30,191][87424] Updated weights for policy 0, policy_version 304079 (0.0011) -[2023-11-28 08:10:30,566][87424] Updated weights for policy 0, policy_version 304089 (0.0011) -[2023-11-28 08:10:31,037][87426] Updated weights for policy 1, policy_version 303850 (0.0011) -[2023-11-28 08:10:31,418][87426] Updated weights for policy 1, policy_version 303860 (0.0012) -[2023-11-28 08:10:31,792][87426] Updated weights for policy 1, policy_version 303870 (0.0012) -[2023-11-28 08:10:32,534][87424] Updated weights for policy 0, policy_version 304099 (0.0012) -[2023-11-28 08:10:32,914][87424] Updated weights for policy 0, policy_version 304109 (0.0012) -[2023-11-28 08:10:33,306][87424] Updated weights for policy 0, policy_version 304119 (0.0012) -[2023-11-28 08:10:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 155639808. Throughput: 0: 2703.0, 1: 2664.3. Samples: 155658108. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:10:33,446][86177] Avg episode reward: [(0, '-705.670'), (1, '-521.710')] -[2023-11-28 08:10:33,876][87426] Updated weights for policy 1, policy_version 303880 (0.0008) -[2023-11-28 08:10:34,262][87426] Updated weights for policy 1, policy_version 303890 (0.0009) -[2023-11-28 08:10:34,646][87426] Updated weights for policy 1, policy_version 303900 (0.0007) -[2023-11-28 08:10:35,039][87424] Updated weights for policy 0, policy_version 304129 (0.0012) -[2023-11-28 08:10:35,427][87424] Updated weights for policy 0, policy_version 304139 (0.0011) -[2023-11-28 08:10:35,809][87424] Updated weights for policy 0, policy_version 304149 (0.0008) -[2023-11-28 08:10:36,187][87424] Updated weights for policy 0, policy_version 304159 (0.0007) -[2023-11-28 08:10:36,721][87426] Updated weights for policy 1, policy_version 303910 (0.0011) -[2023-11-28 08:10:37,098][87426] Updated weights for policy 1, policy_version 303920 (0.0012) -[2023-11-28 08:10:37,476][87426] Updated weights for policy 1, policy_version 303930 (0.0012) -[2023-11-28 08:10:38,205][87424] Updated weights for policy 0, policy_version 304169 (0.0010) -[2023-11-28 08:10:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 155672576. Throughput: 0: 2727.0, 1: 2630.0. Samples: 155690612. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:10:38,446][86177] Avg episode reward: [(0, '-710.650'), (1, '-510.480')] -[2023-11-28 08:10:38,575][87424] Updated weights for policy 0, policy_version 304179 (0.0012) -[2023-11-28 08:10:38,960][87424] Updated weights for policy 0, policy_version 304189 (0.0012) -[2023-11-28 08:10:39,990][87426] Updated weights for policy 1, policy_version 303940 (0.0011) -[2023-11-28 08:10:40,370][87426] Updated weights for policy 1, policy_version 303950 (0.0008) -[2023-11-28 08:10:40,750][87426] Updated weights for policy 1, policy_version 303960 (0.0008) -[2023-11-28 08:10:41,132][87424] Updated weights for policy 0, policy_version 304199 (0.0012) -[2023-11-28 08:10:41,509][87424] Updated weights for policy 0, policy_version 304209 (0.0009) -[2023-11-28 08:10:41,898][87424] Updated weights for policy 0, policy_version 304219 (0.0012) -[2023-11-28 08:10:43,085][87426] Updated weights for policy 1, policy_version 303970 (0.0010) -[2023-11-28 08:10:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 155697152. Throughput: 0: 2707.0, 1: 2608.3. Samples: 155714184. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:10:43,445][86177] Avg episode reward: [(0, '-758.790'), (1, '-510.880')] -[2023-11-28 08:10:43,458][87426] Updated weights for policy 1, policy_version 303980 (0.0012) -[2023-11-28 08:10:43,829][87426] Updated weights for policy 1, policy_version 303990 (0.0012) -[2023-11-28 08:10:43,881][87424] Updated weights for policy 0, policy_version 304229 (0.0010) -[2023-11-28 08:10:44,211][87426] Updated weights for policy 1, policy_version 304000 (0.0010) -[2023-11-28 08:10:44,269][87424] Updated weights for policy 0, policy_version 304239 (0.0012) -[2023-11-28 08:10:44,645][87424] Updated weights for policy 0, policy_version 304249 (0.0012) -[2023-11-28 08:10:46,164][87426] Updated weights for policy 1, policy_version 304010 (0.0012) -[2023-11-28 08:10:46,550][87426] Updated weights for policy 1, policy_version 304020 (0.0011) -[2023-11-28 08:10:46,687][87424] Updated weights for policy 0, policy_version 304259 (0.0012) -[2023-11-28 08:10:46,919][87426] Updated weights for policy 1, policy_version 304030 (0.0011) -[2023-11-28 08:10:47,069][87424] Updated weights for policy 0, policy_version 304269 (0.0012) -[2023-11-28 08:10:47,450][87424] Updated weights for policy 0, policy_version 304279 (0.0012) -[2023-11-28 08:10:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 155729920. Throughput: 0: 2725.9, 1: 2621.7. Samples: 155740012. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:10:48,445][86177] Avg episode reward: [(0, '-789.110'), (1, '-507.950')] -[2023-11-28 08:10:49,133][87426] Updated weights for policy 1, policy_version 304040 (0.0009) -[2023-11-28 08:10:49,510][87426] Updated weights for policy 1, policy_version 304050 (0.0008) -[2023-11-28 08:10:49,658][87424] Updated weights for policy 0, policy_version 304289 (0.0011) -[2023-11-28 08:10:49,896][87426] Updated weights for policy 1, policy_version 304060 (0.0011) -[2023-11-28 08:10:50,040][87424] Updated weights for policy 0, policy_version 304299 (0.0010) -[2023-11-28 08:10:50,421][87424] Updated weights for policy 0, policy_version 304309 (0.0009) -[2023-11-28 08:10:50,807][87424] Updated weights for policy 0, policy_version 304319 (0.0012) -[2023-11-28 08:10:51,782][87426] Updated weights for policy 1, policy_version 304070 (0.0012) -[2023-11-28 08:10:52,155][87426] Updated weights for policy 1, policy_version 304080 (0.0012) -[2023-11-28 08:10:52,527][87426] Updated weights for policy 1, policy_version 304090 (0.0012) -[2023-11-28 08:10:52,877][87424] Updated weights for policy 0, policy_version 304329 (0.0008) -[2023-11-28 08:10:53,255][87424] Updated weights for policy 0, policy_version 304339 (0.0010) -[2023-11-28 08:10:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.7, 300 sec: 5415.1). Total num frames: 155754496. Throughput: 0: 2699.4, 1: 2644.2. Samples: 155771764. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:10:53,445][86177] Avg episode reward: [(0, '-794.250'), (1, '-507.550')] -[2023-11-28 08:10:53,637][87424] Updated weights for policy 0, policy_version 304349 (0.0009) -[2023-11-28 08:10:54,780][87426] Updated weights for policy 1, policy_version 304100 (0.0010) -[2023-11-28 08:10:55,162][87426] Updated weights for policy 1, policy_version 304110 (0.0011) -[2023-11-28 08:10:55,540][87426] Updated weights for policy 1, policy_version 304120 (0.0012) -[2023-11-28 08:10:55,996][87424] Updated weights for policy 0, policy_version 304359 (0.0010) -[2023-11-28 08:10:56,387][87424] Updated weights for policy 0, policy_version 304369 (0.0011) -[2023-11-28 08:10:56,768][87424] Updated weights for policy 0, policy_version 304379 (0.0009) -[2023-11-28 08:10:57,782][87426] Updated weights for policy 1, policy_version 304130 (0.0012) -[2023-11-28 08:10:58,151][87426] Updated weights for policy 1, policy_version 304140 (0.0012) -[2023-11-28 08:10:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 155779072. Throughput: 0: 2686.7, 1: 2668.8. Samples: 155796452. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:10:58,445][86177] Avg episode reward: [(0, '-708.670'), (1, '-503.620')] -[2023-11-28 08:10:58,530][87426] Updated weights for policy 1, policy_version 304150 (0.0011) -[2023-11-28 08:10:58,911][87426] Updated weights for policy 1, policy_version 304160 (0.0012) -[2023-11-28 08:10:59,020][87424] Updated weights for policy 0, policy_version 304389 (0.0010) -[2023-11-28 08:10:59,396][87424] Updated weights for policy 0, policy_version 304399 (0.0009) -[2023-11-28 08:10:59,789][87424] Updated weights for policy 0, policy_version 304409 (0.0008) -[2023-11-28 08:11:00,961][87426] Updated weights for policy 1, policy_version 304170 (0.0012) -[2023-11-28 08:11:01,340][87426] Updated weights for policy 1, policy_version 304180 (0.0011) -[2023-11-28 08:11:01,713][87426] Updated weights for policy 1, policy_version 304190 (0.0011) -[2023-11-28 08:11:01,899][87424] Updated weights for policy 0, policy_version 304419 (0.0010) -[2023-11-28 08:11:02,283][87424] Updated weights for policy 0, policy_version 304429 (0.0008) -[2023-11-28 08:11:02,671][87424] Updated weights for policy 0, policy_version 304439 (0.0008) -[2023-11-28 08:11:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 155811840. Throughput: 0: 2706.5, 1: 2657.5. Samples: 155820872. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:11:03,445][86177] Avg episode reward: [(0, '-715.000'), (1, '-502.520')] -[2023-11-28 08:11:04,128][87426] Updated weights for policy 1, policy_version 304200 (0.0009) -[2023-11-28 08:11:04,506][87426] Updated weights for policy 1, policy_version 304210 (0.0009) -[2023-11-28 08:11:04,886][87426] Updated weights for policy 1, policy_version 304220 (0.0011) -[2023-11-28 08:11:05,035][87424] Updated weights for policy 0, policy_version 304449 (0.0010) -[2023-11-28 08:11:05,412][87424] Updated weights for policy 0, policy_version 304459 (0.0012) -[2023-11-28 08:11:05,795][87424] Updated weights for policy 0, policy_version 304469 (0.0012) -[2023-11-28 08:11:06,178][87424] Updated weights for policy 0, policy_version 304479 (0.0011) -[2023-11-28 08:11:07,046][87426] Updated weights for policy 1, policy_version 304230 (0.0009) -[2023-11-28 08:11:07,423][87426] Updated weights for policy 1, policy_version 304240 (0.0007) -[2023-11-28 08:11:07,803][87426] Updated weights for policy 1, policy_version 304250 (0.0008) -[2023-11-28 08:11:07,914][87424] Updated weights for policy 0, policy_version 304489 (0.0011) -[2023-11-28 08:11:08,298][87424] Updated weights for policy 0, policy_version 304499 (0.0009) -[2023-11-28 08:11:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 155836416. Throughput: 0: 2732.9, 1: 2662.8. Samples: 155853504. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:11:08,445][86177] Avg episode reward: [(0, '-693.280'), (1, '-526.090')] -[2023-11-28 08:11:08,681][87424] Updated weights for policy 0, policy_version 304509 (0.0009) -[2023-11-28 08:11:10,186][87426] Updated weights for policy 1, policy_version 304260 (0.0009) -[2023-11-28 08:11:10,561][87426] Updated weights for policy 1, policy_version 304270 (0.0009) -[2023-11-28 08:11:10,813][87424] Updated weights for policy 0, policy_version 304519 (0.0011) -[2023-11-28 08:11:10,938][87426] Updated weights for policy 1, policy_version 304280 (0.0011) -[2023-11-28 08:11:11,189][87424] Updated weights for policy 0, policy_version 304529 (0.0012) -[2023-11-28 08:11:11,570][87424] Updated weights for policy 0, policy_version 304539 (0.0011) -[2023-11-28 08:11:13,150][87426] Updated weights for policy 1, policy_version 304290 (0.0011) -[2023-11-28 08:11:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 155860992. Throughput: 0: 2730.0, 1: 2676.3. Samples: 155877720. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:11:13,445][86177] Avg episode reward: [(0, '-644.240'), (1, '-530.500')] -[2023-11-28 08:11:13,528][87426] Updated weights for policy 1, policy_version 304300 (0.0012) -[2023-11-28 08:11:13,916][87426] Updated weights for policy 1, policy_version 304310 (0.0011) -[2023-11-28 08:11:14,092][87424] Updated weights for policy 0, policy_version 304549 (0.0010) -[2023-11-28 08:11:14,303][87426] Updated weights for policy 1, policy_version 304320 (0.0011) -[2023-11-28 08:11:14,473][87424] Updated weights for policy 0, policy_version 304559 (0.0012) -[2023-11-28 08:11:14,854][87424] Updated weights for policy 0, policy_version 304569 (0.0011) -[2023-11-28 08:11:16,196][87426] Updated weights for policy 1, policy_version 304330 (0.0012) -[2023-11-28 08:11:16,569][87426] Updated weights for policy 1, policy_version 304340 (0.0012) -[2023-11-28 08:11:16,944][87426] Updated weights for policy 1, policy_version 304350 (0.0012) -[2023-11-28 08:11:17,234][87424] Updated weights for policy 0, policy_version 304579 (0.0011) -[2023-11-28 08:11:17,625][87424] Updated weights for policy 0, policy_version 304589 (0.0012) -[2023-11-28 08:11:18,002][87424] Updated weights for policy 0, policy_version 304599 (0.0011) -[2023-11-28 08:11:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 155893760. Throughput: 0: 2733.4, 1: 2685.6. Samples: 155901964. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:11:18,446][86177] Avg episode reward: [(0, '-666.440'), (1, '-536.630')] -[2023-11-28 08:11:19,332][87426] Updated weights for policy 1, policy_version 304360 (0.0012) -[2023-11-28 08:11:19,710][87426] Updated weights for policy 1, policy_version 304370 (0.0012) -[2023-11-28 08:11:19,765][87424] Updated weights for policy 0, policy_version 304609 (0.0012) -[2023-11-28 08:11:20,088][87426] Updated weights for policy 1, policy_version 304380 (0.0011) -[2023-11-28 08:11:20,143][87424] Updated weights for policy 0, policy_version 304619 (0.0011) -[2023-11-28 08:11:20,530][87424] Updated weights for policy 0, policy_version 304629 (0.0009) -[2023-11-28 08:11:20,906][87424] Updated weights for policy 0, policy_version 304639 (0.0009) -[2023-11-28 08:11:22,531][87426] Updated weights for policy 1, policy_version 304390 (0.0009) -[2023-11-28 08:11:22,919][87426] Updated weights for policy 1, policy_version 304400 (0.0009) -[2023-11-28 08:11:22,959][87424] Updated weights for policy 0, policy_version 304649 (0.0010) -[2023-11-28 08:11:23,292][87426] Updated weights for policy 1, policy_version 304410 (0.0010) -[2023-11-28 08:11:23,340][87424] Updated weights for policy 0, policy_version 304659 (0.0011) -[2023-11-28 08:11:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 155910144. Throughput: 0: 2722.0, 1: 2683.2. Samples: 155933848. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:11:23,446][86177] Avg episode reward: [(0, '-621.760'), (1, '-532.880')] -[2023-11-28 08:11:23,728][87424] Updated weights for policy 0, policy_version 304669 (0.0012) -[2023-11-28 08:11:25,249][87426] Updated weights for policy 1, policy_version 304420 (0.0009) -[2023-11-28 08:11:25,629][87426] Updated weights for policy 1, policy_version 304430 (0.0012) -[2023-11-28 08:11:26,014][87426] Updated weights for policy 1, policy_version 304440 (0.0012) -[2023-11-28 08:11:26,245][87424] Updated weights for policy 0, policy_version 304679 (0.0012) -[2023-11-28 08:11:26,634][87424] Updated weights for policy 0, policy_version 304689 (0.0012) -[2023-11-28 08:11:27,021][87424] Updated weights for policy 0, policy_version 304699 (0.0012) -[2023-11-28 08:11:28,055][87426] Updated weights for policy 1, policy_version 304450 (0.0012) -[2023-11-28 08:11:28,428][87426] Updated weights for policy 1, policy_version 304460 (0.0011) -[2023-11-28 08:11:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 155942912. Throughput: 0: 2712.2, 1: 2711.0. Samples: 155958228. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:11:28,445][86177] Avg episode reward: [(0, '-631.710'), (1, '-511.040')] -[2023-11-28 08:11:28,806][87426] Updated weights for policy 1, policy_version 304470 (0.0007) -[2023-11-28 08:11:29,189][87426] Updated weights for policy 1, policy_version 304480 (0.0008) -[2023-11-28 08:11:29,260][87424] Updated weights for policy 0, policy_version 304709 (0.0011) -[2023-11-28 08:11:29,639][87424] Updated weights for policy 0, policy_version 304719 (0.0012) -[2023-11-28 08:11:30,024][87424] Updated weights for policy 0, policy_version 304729 (0.0009) -[2023-11-28 08:11:31,368][87426] Updated weights for policy 1, policy_version 304490 (0.0009) -[2023-11-28 08:11:31,749][87426] Updated weights for policy 1, policy_version 304500 (0.0010) -[2023-11-28 08:11:31,813][87424] Updated weights for policy 0, policy_version 304739 (0.0010) -[2023-11-28 08:11:32,138][87426] Updated weights for policy 1, policy_version 304510 (0.0012) -[2023-11-28 08:11:32,196][87424] Updated weights for policy 0, policy_version 304749 (0.0011) -[2023-11-28 08:11:32,572][87424] Updated weights for policy 0, policy_version 304759 (0.0011) -[2023-11-28 08:11:33,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 155975680. Throughput: 0: 2715.2, 1: 2695.8. Samples: 155983508. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:11:33,445][86177] Avg episode reward: [(0, '-643.150'), (1, '-508.500')] -[2023-11-28 08:11:34,506][87426] Updated weights for policy 1, policy_version 304520 (0.0011) -[2023-11-28 08:11:34,611][87424] Updated weights for policy 0, policy_version 304769 (0.0008) -[2023-11-28 08:11:34,889][87426] Updated weights for policy 1, policy_version 304530 (0.0008) -[2023-11-28 08:11:35,002][87424] Updated weights for policy 0, policy_version 304779 (0.0011) -[2023-11-28 08:11:35,259][87426] Updated weights for policy 1, policy_version 304540 (0.0011) -[2023-11-28 08:11:35,375][87424] Updated weights for policy 0, policy_version 304789 (0.0012) -[2023-11-28 08:11:35,758][87424] Updated weights for policy 0, policy_version 304799 (0.0012) -[2023-11-28 08:11:37,492][87426] Updated weights for policy 1, policy_version 304550 (0.0010) -[2023-11-28 08:11:37,869][87426] Updated weights for policy 1, policy_version 304560 (0.0012) -[2023-11-28 08:11:38,018][87424] Updated weights for policy 0, policy_version 304809 (0.0011) -[2023-11-28 08:11:38,253][87426] Updated weights for policy 1, policy_version 304570 (0.0011) -[2023-11-28 08:11:38,401][87424] Updated weights for policy 0, policy_version 304819 (0.0012) -[2023-11-28 08:11:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 155992064. Throughput: 0: 2744.5, 1: 2724.8. Samples: 156017880. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:11:38,445][86177] Avg episode reward: [(0, '-689.290'), (1, '-508.130')] -[2023-11-28 08:11:38,781][87424] Updated weights for policy 0, policy_version 304829 (0.0012) -[2023-11-28 08:11:40,199][87426] Updated weights for policy 1, policy_version 304580 (0.0010) -[2023-11-28 08:11:40,567][87426] Updated weights for policy 1, policy_version 304590 (0.0008) -[2023-11-28 08:11:40,950][87426] Updated weights for policy 1, policy_version 304600 (0.0009) -[2023-11-28 08:11:41,328][87424] Updated weights for policy 0, policy_version 304839 (0.0010) -[2023-11-28 08:11:41,703][87424] Updated weights for policy 0, policy_version 304849 (0.0011) -[2023-11-28 08:11:42,076][87424] Updated weights for policy 0, policy_version 304859 (0.0010) -[2023-11-28 08:11:43,154][87426] Updated weights for policy 1, policy_version 304610 (0.0009) -[2023-11-28 08:11:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156024832. Throughput: 0: 2742.0, 1: 2721.7. Samples: 156042316. Policy #0 lag: (min: 31.0, avg: 44.2, max: 63.0) -[2023-11-28 08:11:43,445][86177] Avg episode reward: [(0, '-675.200'), (1, '-507.760')] -[2023-11-28 08:11:43,525][87426] Updated weights for policy 1, policy_version 304620 (0.0010) -[2023-11-28 08:11:43,904][87426] Updated weights for policy 1, policy_version 304630 (0.0008) -[2023-11-28 08:11:44,047][87424] Updated weights for policy 0, policy_version 304869 (0.0010) -[2023-11-28 08:11:44,291][87426] Updated weights for policy 1, policy_version 304640 (0.0007) -[2023-11-28 08:11:44,427][87424] Updated weights for policy 0, policy_version 304879 (0.0012) -[2023-11-28 08:11:44,819][87424] Updated weights for policy 0, policy_version 304889 (0.0012) -[2023-11-28 08:11:46,197][87426] Updated weights for policy 1, policy_version 304650 (0.0012) -[2023-11-28 08:11:46,575][87426] Updated weights for policy 1, policy_version 304660 (0.0012) -[2023-11-28 08:11:46,957][87426] Updated weights for policy 1, policy_version 304670 (0.0012) -[2023-11-28 08:11:47,065][87424] Updated weights for policy 0, policy_version 304899 (0.0012) -[2023-11-28 08:11:47,450][87424] Updated weights for policy 0, policy_version 304909 (0.0012) -[2023-11-28 08:11:47,821][87424] Updated weights for policy 0, policy_version 304919 (0.0011) -[2023-11-28 08:11:48,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 156057600. Throughput: 0: 2725.1, 1: 2742.2. Samples: 156066904. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:11:48,446][86177] Avg episode reward: [(0, '-645.950'), (1, '-504.980')] -[2023-11-28 08:11:48,966][87426] Updated weights for policy 1, policy_version 304680 (0.0011) -[2023-11-28 08:11:49,355][87426] Updated weights for policy 1, policy_version 304690 (0.0011) -[2023-11-28 08:11:49,733][87426] Updated weights for policy 1, policy_version 304700 (0.0012) -[2023-11-28 08:11:49,976][87424] Updated weights for policy 0, policy_version 304929 (0.0010) -[2023-11-28 08:11:50,374][87424] Updated weights for policy 0, policy_version 304939 (0.0012) -[2023-11-28 08:11:50,753][87424] Updated weights for policy 0, policy_version 304949 (0.0012) -[2023-11-28 08:11:51,137][87424] Updated weights for policy 0, policy_version 304959 (0.0011) -[2023-11-28 08:11:52,039][87426] Updated weights for policy 1, policy_version 304710 (0.0009) -[2023-11-28 08:11:52,417][87426] Updated weights for policy 1, policy_version 304720 (0.0009) -[2023-11-28 08:11:52,790][87426] Updated weights for policy 1, policy_version 304730 (0.0008) -[2023-11-28 08:11:53,392][87424] Updated weights for policy 0, policy_version 304969 (0.0011) -[2023-11-28 08:11:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 156082176. Throughput: 0: 2698.8, 1: 2749.1. Samples: 156098656. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:11:53,445][86177] Avg episode reward: [(0, '-664.640'), (1, '-506.840')] -[2023-11-28 08:11:53,766][87424] Updated weights for policy 0, policy_version 304979 (0.0010) -[2023-11-28 08:11:54,150][87424] Updated weights for policy 0, policy_version 304989 (0.0007) -[2023-11-28 08:11:54,865][87426] Updated weights for policy 1, policy_version 304740 (0.0010) -[2023-11-28 08:11:55,244][87426] Updated weights for policy 1, policy_version 304750 (0.0011) -[2023-11-28 08:11:55,615][87426] Updated weights for policy 1, policy_version 304760 (0.0012) -[2023-11-28 08:11:55,862][87424] Updated weights for policy 0, policy_version 304999 (0.0008) -[2023-11-28 08:11:56,244][87424] Updated weights for policy 0, policy_version 305009 (0.0007) -[2023-11-28 08:11:56,628][87424] Updated weights for policy 0, policy_version 305019 (0.0007) -[2023-11-28 08:11:57,872][87426] Updated weights for policy 1, policy_version 304770 (0.0012) -[2023-11-28 08:11:58,261][87426] Updated weights for policy 1, policy_version 304780 (0.0011) -[2023-11-28 08:11:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156106752. Throughput: 0: 2718.7, 1: 2745.4. Samples: 156123604. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:11:58,445][86177] Avg episode reward: [(0, '-666.370'), (1, '-504.530')] -[2023-11-28 08:11:58,638][87426] Updated weights for policy 1, policy_version 304790 (0.0012) -[2023-11-28 08:11:58,750][87424] Updated weights for policy 0, policy_version 305029 (0.0009) -[2023-11-28 08:11:59,008][87426] Updated weights for policy 1, policy_version 304800 (0.0010) -[2023-11-28 08:11:59,134][87424] Updated weights for policy 0, policy_version 305039 (0.0009) -[2023-11-28 08:11:59,507][87424] Updated weights for policy 0, policy_version 305049 (0.0008) -[2023-11-28 08:12:00,984][87426] Updated weights for policy 1, policy_version 304810 (0.0011) -[2023-11-28 08:12:01,369][87426] Updated weights for policy 1, policy_version 304820 (0.0012) -[2023-11-28 08:12:01,703][87424] Updated weights for policy 0, policy_version 305059 (0.0009) -[2023-11-28 08:12:01,736][87426] Updated weights for policy 1, policy_version 304830 (0.0011) -[2023-11-28 08:12:02,088][87424] Updated weights for policy 0, policy_version 305069 (0.0008) -[2023-11-28 08:12:02,472][87424] Updated weights for policy 0, policy_version 305079 (0.0008) -[2023-11-28 08:12:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156139520. Throughput: 0: 2741.3, 1: 2741.5. Samples: 156148692. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:03,445][86177] Avg episode reward: [(0, '-666.100'), (1, '-505.750')] -[2023-11-28 08:12:04,074][87426] Updated weights for policy 1, policy_version 304840 (0.0011) -[2023-11-28 08:12:04,452][87426] Updated weights for policy 1, policy_version 304850 (0.0012) -[2023-11-28 08:12:04,463][87424] Updated weights for policy 0, policy_version 305089 (0.0008) -[2023-11-28 08:12:04,830][87426] Updated weights for policy 1, policy_version 304860 (0.0012) -[2023-11-28 08:12:04,842][87424] Updated weights for policy 0, policy_version 305099 (0.0008) -[2023-11-28 08:12:05,224][87424] Updated weights for policy 0, policy_version 305109 (0.0010) -[2023-11-28 08:12:05,606][87424] Updated weights for policy 0, policy_version 305119 (0.0011) -[2023-11-28 08:12:06,782][87426] Updated weights for policy 1, policy_version 304870 (0.0010) -[2023-11-28 08:12:07,161][87426] Updated weights for policy 1, policy_version 304880 (0.0008) -[2023-11-28 08:12:07,548][87426] Updated weights for policy 1, policy_version 304890 (0.0008) -[2023-11-28 08:12:07,809][87424] Updated weights for policy 0, policy_version 305129 (0.0010) -[2023-11-28 08:12:08,193][87424] Updated weights for policy 0, policy_version 305139 (0.0010) -[2023-11-28 08:12:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 156164096. Throughput: 0: 2766.3, 1: 2770.1. Samples: 156182984. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:08,445][86177] Avg episode reward: [(0, '-692.540'), (1, '-507.720')] -[2023-11-28 08:12:08,580][87424] Updated weights for policy 0, policy_version 305149 (0.0008) -[2023-11-28 08:12:09,950][87426] Updated weights for policy 1, policy_version 304900 (0.0012) -[2023-11-28 08:12:10,327][87426] Updated weights for policy 1, policy_version 304910 (0.0011) -[2023-11-28 08:12:10,661][87424] Updated weights for policy 0, policy_version 305159 (0.0008) -[2023-11-28 08:12:10,714][87426] Updated weights for policy 1, policy_version 304920 (0.0012) -[2023-11-28 08:12:11,042][87424] Updated weights for policy 0, policy_version 305169 (0.0008) -[2023-11-28 08:12:11,427][87424] Updated weights for policy 0, policy_version 305179 (0.0007) -[2023-11-28 08:12:12,663][87426] Updated weights for policy 1, policy_version 304930 (0.0011) -[2023-11-28 08:12:13,048][87426] Updated weights for policy 1, policy_version 304940 (0.0010) -[2023-11-28 08:12:13,432][87426] Updated weights for policy 1, policy_version 304950 (0.0012) -[2023-11-28 08:12:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156188672. Throughput: 0: 2777.0, 1: 2753.9. Samples: 156207116. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:13,445][86177] Avg episode reward: [(0, '-744.280'), (1, '-500.770')] -[2023-11-28 08:12:13,821][87426] Updated weights for policy 1, policy_version 304960 (0.0012) -[2023-11-28 08:12:13,858][87424] Updated weights for policy 0, policy_version 305189 (0.0010) -[2023-11-28 08:12:14,242][87424] Updated weights for policy 0, policy_version 305199 (0.0008) -[2023-11-28 08:12:14,625][87424] Updated weights for policy 0, policy_version 305209 (0.0007) -[2023-11-28 08:12:15,925][87426] Updated weights for policy 1, policy_version 304970 (0.0012) -[2023-11-28 08:12:16,306][87426] Updated weights for policy 1, policy_version 304980 (0.0011) -[2023-11-28 08:12:16,682][87426] Updated weights for policy 1, policy_version 304990 (0.0012) -[2023-11-28 08:12:16,869][87424] Updated weights for policy 0, policy_version 305219 (0.0010) -[2023-11-28 08:12:17,262][87424] Updated weights for policy 0, policy_version 305229 (0.0011) -[2023-11-28 08:12:17,631][87424] Updated weights for policy 0, policy_version 305239 (0.0009) -[2023-11-28 08:12:18,410][87426] Updated weights for policy 1, policy_version 305000 (0.0011) -[2023-11-28 08:12:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 156221440. Throughput: 0: 2748.0, 1: 2763.6. Samples: 156231532. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:18,445][86177] Avg episode reward: [(0, '-760.240'), (1, '-503.140')] -[2023-11-28 08:12:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000305248_78143488.pth... -[2023-11-28 08:12:18,490][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000302720_77496320.pth -[2023-11-28 08:12:18,495][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000305248_78143488.pth -[2023-11-28 08:12:18,799][87426] Updated weights for policy 1, policy_version 305010 (0.0011) -[2023-11-28 08:12:19,175][87426] Updated weights for policy 1, policy_version 305020 (0.0012) -[2023-11-28 08:12:19,326][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000305024_78086144.pth... -[2023-11-28 08:12:19,374][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000302496_77438976.pth -[2023-11-28 08:12:19,381][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000305024_78086144.pth -[2023-11-28 08:12:20,125][87424] Updated weights for policy 0, policy_version 305249 (0.0009) -[2023-11-28 08:12:20,520][87424] Updated weights for policy 0, policy_version 305259 (0.0011) -[2023-11-28 08:12:20,903][87424] Updated weights for policy 0, policy_version 305269 (0.0009) -[2023-11-28 08:12:21,282][87424] Updated weights for policy 0, policy_version 305279 (0.0010) -[2023-11-28 08:12:21,347][87426] Updated weights for policy 1, policy_version 305030 (0.0009) -[2023-11-28 08:12:21,728][87426] Updated weights for policy 1, policy_version 305040 (0.0008) -[2023-11-28 08:12:22,102][87426] Updated weights for policy 1, policy_version 305050 (0.0008) -[2023-11-28 08:12:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 156246016. Throughput: 0: 2713.7, 1: 2754.9. Samples: 156263968. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:23,445][86177] Avg episode reward: [(0, '-714.760'), (1, '-506.090')] -[2023-11-28 08:12:23,723][87424] Updated weights for policy 0, policy_version 305289 (0.0011) -[2023-11-28 08:12:24,105][87424] Updated weights for policy 0, policy_version 305299 (0.0009) -[2023-11-28 08:12:24,398][87426] Updated weights for policy 1, policy_version 305060 (0.0012) -[2023-11-28 08:12:24,495][87424] Updated weights for policy 0, policy_version 305309 (0.0011) -[2023-11-28 08:12:24,775][87426] Updated weights for policy 1, policy_version 305070 (0.0012) -[2023-11-28 08:12:25,164][87426] Updated weights for policy 1, policy_version 305080 (0.0012) -[2023-11-28 08:12:26,442][87424] Updated weights for policy 0, policy_version 305319 (0.0011) -[2023-11-28 08:12:26,814][87424] Updated weights for policy 0, policy_version 305329 (0.0010) -[2023-11-28 08:12:27,183][87426] Updated weights for policy 1, policy_version 305090 (0.0011) -[2023-11-28 08:12:27,195][87424] Updated weights for policy 0, policy_version 305339 (0.0011) -[2023-11-28 08:12:27,564][87426] Updated weights for policy 1, policy_version 305100 (0.0011) -[2023-11-28 08:12:27,936][87426] Updated weights for policy 1, policy_version 305110 (0.0010) -[2023-11-28 08:12:28,315][87426] Updated weights for policy 1, policy_version 305120 (0.0007) -[2023-11-28 08:12:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 156278784. Throughput: 0: 2726.4, 1: 2792.5. Samples: 156290668. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:28,445][86177] Avg episode reward: [(0, '-664.530'), (1, '-505.930')] -[2023-11-28 08:12:28,859][87424] Updated weights for policy 0, policy_version 305349 (0.0012) -[2023-11-28 08:12:29,240][87424] Updated weights for policy 0, policy_version 305359 (0.0012) -[2023-11-28 08:12:29,615][87424] Updated weights for policy 0, policy_version 305369 (0.0011) -[2023-11-28 08:12:30,144][87426] Updated weights for policy 1, policy_version 305130 (0.0011) -[2023-11-28 08:12:30,515][87426] Updated weights for policy 1, policy_version 305140 (0.0012) -[2023-11-28 08:12:30,903][87426] Updated weights for policy 1, policy_version 305150 (0.0012) -[2023-11-28 08:12:31,577][87424] Updated weights for policy 0, policy_version 305379 (0.0012) -[2023-11-28 08:12:31,954][87424] Updated weights for policy 0, policy_version 305389 (0.0012) -[2023-11-28 08:12:32,344][87424] Updated weights for policy 0, policy_version 305399 (0.0011) -[2023-11-28 08:12:33,434][87426] Updated weights for policy 1, policy_version 305160 (0.0012) -[2023-11-28 08:12:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 156303360. Throughput: 0: 2752.4, 1: 2788.4. Samples: 156316236. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:33,445][86177] Avg episode reward: [(0, '-636.810'), (1, '-517.960')] -[2023-11-28 08:12:33,814][87426] Updated weights for policy 1, policy_version 305170 (0.0012) -[2023-11-28 08:12:34,194][87426] Updated weights for policy 1, policy_version 305180 (0.0012) -[2023-11-28 08:12:34,324][87424] Updated weights for policy 0, policy_version 305409 (0.0011) -[2023-11-28 08:12:34,708][87424] Updated weights for policy 0, policy_version 305419 (0.0008) -[2023-11-28 08:12:35,087][87424] Updated weights for policy 0, policy_version 305429 (0.0011) -[2023-11-28 08:12:35,469][87424] Updated weights for policy 0, policy_version 305439 (0.0012) -[2023-11-28 08:12:36,304][87426] Updated weights for policy 1, policy_version 305190 (0.0010) -[2023-11-28 08:12:36,683][87426] Updated weights for policy 1, policy_version 305200 (0.0008) -[2023-11-28 08:12:37,067][87426] Updated weights for policy 1, policy_version 305210 (0.0010) -[2023-11-28 08:12:37,620][87424] Updated weights for policy 0, policy_version 305449 (0.0009) -[2023-11-28 08:12:38,006][87424] Updated weights for policy 0, policy_version 305459 (0.0007) -[2023-11-28 08:12:38,384][87424] Updated weights for policy 0, policy_version 305469 (0.0008) -[2023-11-28 08:12:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 156327936. Throughput: 0: 2787.3, 1: 2783.4. Samples: 156349336. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:38,446][86177] Avg episode reward: [(0, '-638.540'), (1, '-523.320')] -[2023-11-28 08:12:39,318][87426] Updated weights for policy 1, policy_version 305220 (0.0011) -[2023-11-28 08:12:39,696][87426] Updated weights for policy 1, policy_version 305230 (0.0011) -[2023-11-28 08:12:40,083][87426] Updated weights for policy 1, policy_version 305240 (0.0011) -[2023-11-28 08:12:40,625][87424] Updated weights for policy 0, policy_version 305479 (0.0010) -[2023-11-28 08:12:41,011][87424] Updated weights for policy 0, policy_version 305489 (0.0008) -[2023-11-28 08:12:41,405][87424] Updated weights for policy 0, policy_version 305499 (0.0007) -[2023-11-28 08:12:42,423][87426] Updated weights for policy 1, policy_version 305250 (0.0012) -[2023-11-28 08:12:42,803][87426] Updated weights for policy 1, policy_version 305260 (0.0012) -[2023-11-28 08:12:43,178][87426] Updated weights for policy 1, policy_version 305270 (0.0012) -[2023-11-28 08:12:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156352512. Throughput: 0: 2773.2, 1: 2768.5. Samples: 156372984. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:43,445][86177] Avg episode reward: [(0, '-624.830'), (1, '-519.130')] -[2023-11-28 08:12:43,557][87426] Updated weights for policy 1, policy_version 305280 (0.0010) -[2023-11-28 08:12:43,566][87424] Updated weights for policy 0, policy_version 305509 (0.0010) -[2023-11-28 08:12:43,965][87424] Updated weights for policy 0, policy_version 305519 (0.0012) -[2023-11-28 08:12:44,342][87424] Updated weights for policy 0, policy_version 305529 (0.0012) -[2023-11-28 08:12:45,492][87426] Updated weights for policy 1, policy_version 305290 (0.0011) -[2023-11-28 08:12:45,881][87426] Updated weights for policy 1, policy_version 305300 (0.0011) -[2023-11-28 08:12:46,254][87426] Updated weights for policy 1, policy_version 305310 (0.0011) -[2023-11-28 08:12:46,832][87424] Updated weights for policy 0, policy_version 305539 (0.0010) -[2023-11-28 08:12:47,223][87424] Updated weights for policy 0, policy_version 305549 (0.0008) -[2023-11-28 08:12:47,600][87424] Updated weights for policy 0, policy_version 305559 (0.0008) -[2023-11-28 08:12:48,375][87426] Updated weights for policy 1, policy_version 305320 (0.0011) -[2023-11-28 08:12:48,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 156385280. Throughput: 0: 2728.9, 1: 2782.3. Samples: 156396696. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:48,446][86177] Avg episode reward: [(0, '-663.310'), (1, '-519.700')] -[2023-11-28 08:12:48,761][87426] Updated weights for policy 1, policy_version 305330 (0.0012) -[2023-11-28 08:12:49,137][87426] Updated weights for policy 1, policy_version 305340 (0.0012) -[2023-11-28 08:12:49,947][87424] Updated weights for policy 0, policy_version 305569 (0.0009) -[2023-11-28 08:12:50,333][87424] Updated weights for policy 0, policy_version 305579 (0.0011) -[2023-11-28 08:12:50,707][87424] Updated weights for policy 0, policy_version 305589 (0.0011) -[2023-11-28 08:12:51,088][87424] Updated weights for policy 0, policy_version 305599 (0.0010) -[2023-11-28 08:12:51,156][87426] Updated weights for policy 1, policy_version 305350 (0.0012) -[2023-11-28 08:12:51,545][87426] Updated weights for policy 1, policy_version 305360 (0.0012) -[2023-11-28 08:12:51,926][87426] Updated weights for policy 1, policy_version 305370 (0.0012) -[2023-11-28 08:12:53,225][87424] Updated weights for policy 0, policy_version 305609 (0.0008) -[2023-11-28 08:12:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156409856. Throughput: 0: 2692.7, 1: 2767.5. Samples: 156428692. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:53,445][86177] Avg episode reward: [(0, '-640.140'), (1, '-510.850')] -[2023-11-28 08:12:53,609][87424] Updated weights for policy 0, policy_version 305619 (0.0010) -[2023-11-28 08:12:53,990][87424] Updated weights for policy 0, policy_version 305629 (0.0012) -[2023-11-28 08:12:54,162][87426] Updated weights for policy 1, policy_version 305380 (0.0010) -[2023-11-28 08:12:54,542][87426] Updated weights for policy 1, policy_version 305390 (0.0007) -[2023-11-28 08:12:54,921][87426] Updated weights for policy 1, policy_version 305400 (0.0008) -[2023-11-28 08:12:56,264][87424] Updated weights for policy 0, policy_version 305639 (0.0012) -[2023-11-28 08:12:56,639][87424] Updated weights for policy 0, policy_version 305649 (0.0008) -[2023-11-28 08:12:57,026][87424] Updated weights for policy 0, policy_version 305659 (0.0008) -[2023-11-28 08:12:57,078][87426] Updated weights for policy 1, policy_version 305410 (0.0009) -[2023-11-28 08:12:57,460][87426] Updated weights for policy 1, policy_version 305420 (0.0012) -[2023-11-28 08:12:57,847][87426] Updated weights for policy 1, policy_version 305430 (0.0012) -[2023-11-28 08:12:58,222][87426] Updated weights for policy 1, policy_version 305440 (0.0012) -[2023-11-28 08:12:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 156442624. Throughput: 0: 2699.4, 1: 2760.4. Samples: 156452808. Policy #0 lag: (min: 45.0, avg: 50.7, max: 76.0) -[2023-11-28 08:12:58,445][86177] Avg episode reward: [(0, '-609.120'), (1, '-504.510')] -[2023-11-28 08:12:58,873][87424] Updated weights for policy 0, policy_version 305669 (0.0008) -[2023-11-28 08:12:59,248][87424] Updated weights for policy 0, policy_version 305679 (0.0012) -[2023-11-28 08:12:59,632][87424] Updated weights for policy 0, policy_version 305689 (0.0010) -[2023-11-28 08:13:00,168][87426] Updated weights for policy 1, policy_version 305450 (0.0012) -[2023-11-28 08:13:00,542][87426] Updated weights for policy 1, policy_version 305460 (0.0012) -[2023-11-28 08:13:00,912][87426] Updated weights for policy 1, policy_version 305470 (0.0012) -[2023-11-28 08:13:01,847][87424] Updated weights for policy 0, policy_version 305699 (0.0011) -[2023-11-28 08:13:02,225][87424] Updated weights for policy 0, policy_version 305709 (0.0011) -[2023-11-28 08:13:02,599][87424] Updated weights for policy 0, policy_version 305719 (0.0011) -[2023-11-28 08:13:03,283][87426] Updated weights for policy 1, policy_version 305480 (0.0012) -[2023-11-28 08:13:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156467200. Throughput: 0: 2738.0, 1: 2752.4. Samples: 156478600. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:03,445][86177] Avg episode reward: [(0, '-606.420'), (1, '-503.760')] -[2023-11-28 08:13:03,658][87426] Updated weights for policy 1, policy_version 305490 (0.0012) -[2023-11-28 08:13:04,037][87426] Updated weights for policy 1, policy_version 305500 (0.0011) -[2023-11-28 08:13:04,583][87424] Updated weights for policy 0, policy_version 305729 (0.0011) -[2023-11-28 08:13:04,962][87424] Updated weights for policy 0, policy_version 305739 (0.0012) -[2023-11-28 08:13:05,347][87424] Updated weights for policy 0, policy_version 305749 (0.0012) -[2023-11-28 08:13:05,731][87424] Updated weights for policy 0, policy_version 305759 (0.0008) -[2023-11-28 08:13:06,529][87426] Updated weights for policy 1, policy_version 305510 (0.0007) -[2023-11-28 08:13:06,912][87426] Updated weights for policy 1, policy_version 305520 (0.0011) -[2023-11-28 08:13:07,291][87426] Updated weights for policy 1, policy_version 305530 (0.0012) -[2023-11-28 08:13:08,252][87424] Updated weights for policy 0, policy_version 305769 (0.0008) -[2023-11-28 08:13:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156491776. Throughput: 0: 2725.7, 1: 2717.8. Samples: 156508924. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:08,446][86177] Avg episode reward: [(0, '-587.960'), (1, '-504.500')] -[2023-11-28 08:13:08,634][87424] Updated weights for policy 0, policy_version 305779 (0.0008) -[2023-11-28 08:13:09,020][87424] Updated weights for policy 0, policy_version 305789 (0.0010) -[2023-11-28 08:13:09,615][87426] Updated weights for policy 1, policy_version 305540 (0.0012) -[2023-11-28 08:13:09,991][87426] Updated weights for policy 1, policy_version 305550 (0.0012) -[2023-11-28 08:13:10,368][87426] Updated weights for policy 1, policy_version 305560 (0.0010) -[2023-11-28 08:13:11,148][87424] Updated weights for policy 0, policy_version 305799 (0.0011) -[2023-11-28 08:13:11,522][87424] Updated weights for policy 0, policy_version 305809 (0.0009) -[2023-11-28 08:13:11,911][87424] Updated weights for policy 0, policy_version 305819 (0.0016) -[2023-11-28 08:13:12,618][87426] Updated weights for policy 1, policy_version 305570 (0.0009) -[2023-11-28 08:13:12,995][87426] Updated weights for policy 1, policy_version 305580 (0.0010) -[2023-11-28 08:13:13,385][87426] Updated weights for policy 1, policy_version 305590 (0.0007) -[2023-11-28 08:13:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 156516352. Throughput: 0: 2716.4, 1: 2659.1. Samples: 156532568. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:13,445][86177] Avg episode reward: [(0, '-585.360'), (1, '-503.200')] -[2023-11-28 08:13:13,758][87426] Updated weights for policy 1, policy_version 305600 (0.0007) -[2023-11-28 08:13:14,000][87424] Updated weights for policy 0, policy_version 305829 (0.0012) -[2023-11-28 08:13:14,383][87424] Updated weights for policy 0, policy_version 305839 (0.0011) -[2023-11-28 08:13:14,757][87424] Updated weights for policy 0, policy_version 305849 (0.0012) -[2023-11-28 08:13:15,828][87426] Updated weights for policy 1, policy_version 305610 (0.0012) -[2023-11-28 08:13:16,209][87426] Updated weights for policy 1, policy_version 305620 (0.0012) -[2023-11-28 08:13:16,590][87426] Updated weights for policy 1, policy_version 305630 (0.0012) -[2023-11-28 08:13:17,149][87424] Updated weights for policy 0, policy_version 305859 (0.0012) -[2023-11-28 08:13:17,541][87424] Updated weights for policy 0, policy_version 305869 (0.0012) -[2023-11-28 08:13:17,913][87424] Updated weights for policy 0, policy_version 305879 (0.0012) -[2023-11-28 08:13:18,295][87426] Updated weights for policy 1, policy_version 305640 (0.0010) -[2023-11-28 08:13:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 156549120. Throughput: 0: 2711.0, 1: 2672.1. Samples: 156558476. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:18,446][86177] Avg episode reward: [(0, '-581.600'), (1, '-535.010')] -[2023-11-28 08:13:18,674][87426] Updated weights for policy 1, policy_version 305650 (0.0011) -[2023-11-28 08:13:19,047][87426] Updated weights for policy 1, policy_version 305660 (0.0011) -[2023-11-28 08:13:19,904][87424] Updated weights for policy 0, policy_version 305889 (0.0011) -[2023-11-28 08:13:20,295][87424] Updated weights for policy 0, policy_version 305899 (0.0012) -[2023-11-28 08:13:20,673][87424] Updated weights for policy 0, policy_version 305909 (0.0011) -[2023-11-28 08:13:21,067][87424] Updated weights for policy 0, policy_version 305919 (0.0010) -[2023-11-28 08:13:21,456][87426] Updated weights for policy 1, policy_version 305670 (0.0012) -[2023-11-28 08:13:21,826][87426] Updated weights for policy 1, policy_version 305680 (0.0012) -[2023-11-28 08:13:22,204][87426] Updated weights for policy 1, policy_version 305690 (0.0012) -[2023-11-28 08:13:23,312][87424] Updated weights for policy 0, policy_version 305929 (0.0012) -[2023-11-28 08:13:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 156573696. Throughput: 0: 2691.2, 1: 2695.8. Samples: 156591748. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:23,445][86177] Avg episode reward: [(0, '-617.750'), (1, '-536.770')] -[2023-11-28 08:13:23,688][87424] Updated weights for policy 0, policy_version 305939 (0.0012) -[2023-11-28 08:13:24,074][87424] Updated weights for policy 0, policy_version 305949 (0.0012) -[2023-11-28 08:13:24,676][87426] Updated weights for policy 1, policy_version 305700 (0.0012) -[2023-11-28 08:13:25,045][87426] Updated weights for policy 1, policy_version 305710 (0.0012) -[2023-11-28 08:13:25,426][87426] Updated weights for policy 1, policy_version 305720 (0.0012) -[2023-11-28 08:13:26,146][87424] Updated weights for policy 0, policy_version 305959 (0.0008) -[2023-11-28 08:13:26,537][87424] Updated weights for policy 0, policy_version 305969 (0.0007) -[2023-11-28 08:13:26,927][87424] Updated weights for policy 0, policy_version 305979 (0.0007) -[2023-11-28 08:13:27,837][87426] Updated weights for policy 1, policy_version 305730 (0.0012) -[2023-11-28 08:13:28,212][87426] Updated weights for policy 1, policy_version 305740 (0.0012) -[2023-11-28 08:13:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 156598272. Throughput: 0: 2701.4, 1: 2703.2. Samples: 156616192. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:28,445][86177] Avg episode reward: [(0, '-611.700'), (1, '-537.570')] -[2023-11-28 08:13:28,586][87426] Updated weights for policy 1, policy_version 305750 (0.0010) -[2023-11-28 08:13:28,963][87426] Updated weights for policy 1, policy_version 305760 (0.0008) -[2023-11-28 08:13:29,076][87424] Updated weights for policy 0, policy_version 305989 (0.0007) -[2023-11-28 08:13:29,458][87424] Updated weights for policy 0, policy_version 305999 (0.0008) -[2023-11-28 08:13:29,843][87424] Updated weights for policy 0, policy_version 306009 (0.0011) -[2023-11-28 08:13:30,942][87426] Updated weights for policy 1, policy_version 305770 (0.0012) -[2023-11-28 08:13:31,316][87426] Updated weights for policy 1, policy_version 305780 (0.0012) -[2023-11-28 08:13:31,707][87426] Updated weights for policy 1, policy_version 305790 (0.0011) -[2023-11-28 08:13:32,318][87424] Updated weights for policy 0, policy_version 306019 (0.0010) -[2023-11-28 08:13:32,704][87424] Updated weights for policy 0, policy_version 306029 (0.0007) -[2023-11-28 08:13:33,073][87424] Updated weights for policy 0, policy_version 306039 (0.0014) -[2023-11-28 08:13:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156631040. Throughput: 0: 2713.9, 1: 2690.2. Samples: 156639876. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:33,445][86177] Avg episode reward: [(0, '-587.800'), (1, '-539.210')] -[2023-11-28 08:13:34,310][87426] Updated weights for policy 1, policy_version 305800 (0.0011) -[2023-11-28 08:13:34,691][87426] Updated weights for policy 1, policy_version 305810 (0.0012) -[2023-11-28 08:13:35,069][87426] Updated weights for policy 1, policy_version 305820 (0.0012) -[2023-11-28 08:13:35,435][87424] Updated weights for policy 0, policy_version 306049 (0.0008) -[2023-11-28 08:13:35,819][87424] Updated weights for policy 0, policy_version 306059 (0.0011) -[2023-11-28 08:13:36,210][87424] Updated weights for policy 0, policy_version 306069 (0.0008) -[2023-11-28 08:13:36,582][87424] Updated weights for policy 0, policy_version 306079 (0.0009) -[2023-11-28 08:13:36,847][87426] Updated weights for policy 1, policy_version 305830 (0.0012) -[2023-11-28 08:13:37,218][87426] Updated weights for policy 1, policy_version 305840 (0.0012) -[2023-11-28 08:13:37,599][87426] Updated weights for policy 1, policy_version 305850 (0.0012) -[2023-11-28 08:13:38,429][87424] Updated weights for policy 0, policy_version 306089 (0.0008) -[2023-11-28 08:13:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 156655616. Throughput: 0: 2721.1, 1: 2712.1. Samples: 156673184. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:38,445][86177] Avg episode reward: [(0, '-600.080'), (1, '-515.680')] -[2023-11-28 08:13:38,805][87424] Updated weights for policy 0, policy_version 306099 (0.0008) -[2023-11-28 08:13:39,190][87424] Updated weights for policy 0, policy_version 306109 (0.0009) -[2023-11-28 08:13:40,037][87426] Updated weights for policy 1, policy_version 305860 (0.0011) -[2023-11-28 08:13:40,421][87426] Updated weights for policy 1, policy_version 305870 (0.0011) -[2023-11-28 08:13:40,797][87426] Updated weights for policy 1, policy_version 305880 (0.0011) -[2023-11-28 08:13:41,573][87424] Updated weights for policy 0, policy_version 306119 (0.0011) -[2023-11-28 08:13:41,945][87424] Updated weights for policy 0, policy_version 306129 (0.0010) -[2023-11-28 08:13:42,330][87424] Updated weights for policy 0, policy_version 306139 (0.0011) -[2023-11-28 08:13:43,153][87426] Updated weights for policy 1, policy_version 305890 (0.0010) -[2023-11-28 08:13:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 156680192. Throughput: 0: 2706.5, 1: 2698.0. Samples: 156696008. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:43,445][86177] Avg episode reward: [(0, '-586.020'), (1, '-516.870')] -[2023-11-28 08:13:43,534][87426] Updated weights for policy 1, policy_version 305900 (0.0011) -[2023-11-28 08:13:43,914][87426] Updated weights for policy 1, policy_version 305910 (0.0007) -[2023-11-28 08:13:44,293][87426] Updated weights for policy 1, policy_version 305920 (0.0008) -[2023-11-28 08:13:44,808][87424] Updated weights for policy 0, policy_version 306149 (0.0011) -[2023-11-28 08:13:45,194][87424] Updated weights for policy 0, policy_version 306159 (0.0012) -[2023-11-28 08:13:45,568][87424] Updated weights for policy 0, policy_version 306169 (0.0012) -[2023-11-28 08:13:46,444][87426] Updated weights for policy 1, policy_version 305930 (0.0012) -[2023-11-28 08:13:46,827][87426] Updated weights for policy 1, policy_version 305940 (0.0011) -[2023-11-28 08:13:47,199][87426] Updated weights for policy 1, policy_version 305950 (0.0011) -[2023-11-28 08:13:47,536][87424] Updated weights for policy 0, policy_version 306179 (0.0012) -[2023-11-28 08:13:47,928][87424] Updated weights for policy 0, policy_version 306189 (0.0012) -[2023-11-28 08:13:48,313][87424] Updated weights for policy 0, policy_version 306199 (0.0012) -[2023-11-28 08:13:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 156704768. Throughput: 0: 2657.7, 1: 2688.5. Samples: 156719180. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:48,445][86177] Avg episode reward: [(0, '-591.100'), (1, '-513.840')] -[2023-11-28 08:13:49,576][87426] Updated weights for policy 1, policy_version 305960 (0.0011) -[2023-11-28 08:13:49,953][87426] Updated weights for policy 1, policy_version 305970 (0.0011) -[2023-11-28 08:13:50,341][87426] Updated weights for policy 1, policy_version 305980 (0.0008) -[2023-11-28 08:13:50,439][87424] Updated weights for policy 0, policy_version 306209 (0.0011) -[2023-11-28 08:13:50,824][87424] Updated weights for policy 0, policy_version 306219 (0.0009) -[2023-11-28 08:13:51,215][87424] Updated weights for policy 0, policy_version 306229 (0.0010) -[2023-11-28 08:13:51,596][87424] Updated weights for policy 0, policy_version 306239 (0.0012) -[2023-11-28 08:13:52,372][87426] Updated weights for policy 1, policy_version 305990 (0.0010) -[2023-11-28 08:13:52,749][87426] Updated weights for policy 1, policy_version 306000 (0.0010) -[2023-11-28 08:13:53,124][87426] Updated weights for policy 1, policy_version 306010 (0.0009) -[2023-11-28 08:13:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 156737536. Throughput: 0: 2666.3, 1: 2725.2. Samples: 156751540. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:53,445][86177] Avg episode reward: [(0, '-678.700'), (1, '-518.060')] -[2023-11-28 08:13:54,014][87424] Updated weights for policy 0, policy_version 306249 (0.0012) -[2023-11-28 08:13:54,392][87424] Updated weights for policy 0, policy_version 306259 (0.0008) -[2023-11-28 08:13:54,773][87424] Updated weights for policy 0, policy_version 306269 (0.0007) -[2023-11-28 08:13:55,441][87426] Updated weights for policy 1, policy_version 306020 (0.0009) -[2023-11-28 08:13:55,823][87426] Updated weights for policy 1, policy_version 306030 (0.0008) -[2023-11-28 08:13:56,214][87426] Updated weights for policy 1, policy_version 306040 (0.0007) -[2023-11-28 08:13:57,297][87424] Updated weights for policy 0, policy_version 306279 (0.0008) -[2023-11-28 08:13:57,673][87424] Updated weights for policy 0, policy_version 306289 (0.0008) -[2023-11-28 08:13:58,051][87424] Updated weights for policy 0, policy_version 306299 (0.0007) -[2023-11-28 08:13:58,326][87426] Updated weights for policy 1, policy_version 306050 (0.0008) -[2023-11-28 08:13:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 156762112. Throughput: 0: 2661.0, 1: 2753.0. Samples: 156776196. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:13:58,445][86177] Avg episode reward: [(0, '-680.370'), (1, '-518.540')] -[2023-11-28 08:13:58,707][87426] Updated weights for policy 1, policy_version 306060 (0.0008) -[2023-11-28 08:13:59,094][87426] Updated weights for policy 1, policy_version 306070 (0.0008) -[2023-11-28 08:13:59,475][87426] Updated weights for policy 1, policy_version 306080 (0.0010) -[2023-11-28 08:13:59,844][87424] Updated weights for policy 0, policy_version 306309 (0.0008) -[2023-11-28 08:14:00,221][87424] Updated weights for policy 0, policy_version 306319 (0.0009) -[2023-11-28 08:14:00,606][87424] Updated weights for policy 0, policy_version 306329 (0.0008) -[2023-11-28 08:14:01,301][87426] Updated weights for policy 1, policy_version 306090 (0.0008) -[2023-11-28 08:14:01,698][87426] Updated weights for policy 1, policy_version 306100 (0.0010) -[2023-11-28 08:14:02,075][87426] Updated weights for policy 1, policy_version 306110 (0.0008) -[2023-11-28 08:14:03,037][87424] Updated weights for policy 0, policy_version 306339 (0.0009) -[2023-11-28 08:14:03,419][87424] Updated weights for policy 0, policy_version 306349 (0.0012) -[2023-11-28 08:14:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 156786688. Throughput: 0: 2641.9, 1: 2738.7. Samples: 156800600. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:14:03,446][86177] Avg episode reward: [(0, '-676.810'), (1, '-552.210')] -[2023-11-28 08:14:03,799][87424] Updated weights for policy 0, policy_version 306359 (0.0011) -[2023-11-28 08:14:04,037][87426] Updated weights for policy 1, policy_version 306120 (0.0011) -[2023-11-28 08:14:04,421][87426] Updated weights for policy 1, policy_version 306130 (0.0012) -[2023-11-28 08:14:04,797][87426] Updated weights for policy 1, policy_version 306140 (0.0012) -[2023-11-28 08:14:06,317][87424] Updated weights for policy 0, policy_version 306369 (0.0011) -[2023-11-28 08:14:06,705][87424] Updated weights for policy 0, policy_version 306379 (0.0011) -[2023-11-28 08:14:06,811][87426] Updated weights for policy 1, policy_version 306150 (0.0011) -[2023-11-28 08:14:07,082][87424] Updated weights for policy 0, policy_version 306389 (0.0011) -[2023-11-28 08:14:07,197][87426] Updated weights for policy 1, policy_version 306160 (0.0011) -[2023-11-28 08:14:07,465][87424] Updated weights for policy 0, policy_version 306399 (0.0008) -[2023-11-28 08:14:07,577][87426] Updated weights for policy 1, policy_version 306170 (0.0012) -[2023-11-28 08:14:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 156819456. Throughput: 0: 2630.2, 1: 2714.2. Samples: 156832248. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:14:08,445][86177] Avg episode reward: [(0, '-633.330'), (1, '-555.300')] -[2023-11-28 08:14:09,927][87424] Updated weights for policy 0, policy_version 306409 (0.0011) -[2023-11-28 08:14:10,140][87426] Updated weights for policy 1, policy_version 306180 (0.0011) -[2023-11-28 08:14:10,308][87424] Updated weights for policy 0, policy_version 306419 (0.0008) -[2023-11-28 08:14:10,523][87426] Updated weights for policy 1, policy_version 306190 (0.0011) -[2023-11-28 08:14:10,686][87424] Updated weights for policy 0, policy_version 306429 (0.0010) -[2023-11-28 08:14:10,900][87426] Updated weights for policy 1, policy_version 306200 (0.0011) -[2023-11-28 08:14:12,772][87424] Updated weights for policy 0, policy_version 306439 (0.0012) -[2023-11-28 08:14:13,150][87424] Updated weights for policy 0, policy_version 306449 (0.0012) -[2023-11-28 08:14:13,381][87426] Updated weights for policy 1, policy_version 306210 (0.0012) -[2023-11-28 08:14:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 156835840. Throughput: 0: 2628.0, 1: 2710.1. Samples: 156856408. Policy #0 lag: (min: 31.0, avg: 38.8, max: 63.0) -[2023-11-28 08:14:13,445][86177] Avg episode reward: [(0, '-583.720'), (1, '-571.250')] -[2023-11-28 08:14:13,536][87424] Updated weights for policy 0, policy_version 306459 (0.0009) -[2023-11-28 08:14:13,760][87426] Updated weights for policy 1, policy_version 306220 (0.0011) -[2023-11-28 08:14:14,144][87426] Updated weights for policy 1, policy_version 306230 (0.0011) -[2023-11-28 08:14:14,517][87426] Updated weights for policy 1, policy_version 306240 (0.0012) -[2023-11-28 08:14:16,105][87424] Updated weights for policy 0, policy_version 306469 (0.0009) -[2023-11-28 08:14:16,506][87424] Updated weights for policy 0, policy_version 306479 (0.0011) -[2023-11-28 08:14:16,879][87424] Updated weights for policy 0, policy_version 306489 (0.0012) -[2023-11-28 08:14:16,919][87426] Updated weights for policy 1, policy_version 306250 (0.0009) -[2023-11-28 08:14:17,304][87426] Updated weights for policy 1, policy_version 306260 (0.0008) -[2023-11-28 08:14:17,683][87426] Updated weights for policy 1, policy_version 306270 (0.0007) -[2023-11-28 08:14:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 156868608. Throughput: 0: 2635.6, 1: 2702.0. Samples: 156880072. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:14:18,446][86177] Avg episode reward: [(0, '-533.250'), (1, '-613.370')] -[2023-11-28 08:14:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000306496_78462976.pth... -[2023-11-28 08:14:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000306272_78405632.pth... -[2023-11-28 08:14:18,489][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000303968_77815808.pth -[2023-11-28 08:14:18,505][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000303744_77758464.pth -[2023-11-28 08:14:19,248][87424] Updated weights for policy 0, policy_version 306499 (0.0009) -[2023-11-28 08:14:19,629][87424] Updated weights for policy 0, policy_version 306509 (0.0007) -[2023-11-28 08:14:20,014][87424] Updated weights for policy 0, policy_version 306519 (0.0010) -[2023-11-28 08:14:20,123][87426] Updated weights for policy 1, policy_version 306280 (0.0012) -[2023-11-28 08:14:20,491][87426] Updated weights for policy 1, policy_version 306290 (0.0011) -[2023-11-28 08:14:20,878][87426] Updated weights for policy 1, policy_version 306300 (0.0012) -[2023-11-28 08:14:22,166][87424] Updated weights for policy 0, policy_version 306529 (0.0010) -[2023-11-28 08:14:22,561][87424] Updated weights for policy 0, policy_version 306539 (0.0011) -[2023-11-28 08:14:22,853][87426] Updated weights for policy 1, policy_version 306310 (0.0012) -[2023-11-28 08:14:22,943][87424] Updated weights for policy 0, policy_version 306549 (0.0011) -[2023-11-28 08:14:23,227][87426] Updated weights for policy 1, policy_version 306320 (0.0008) -[2023-11-28 08:14:23,320][87424] Updated weights for policy 0, policy_version 306559 (0.0011) -[2023-11-28 08:14:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 156893184. Throughput: 0: 2636.7, 1: 2658.9. Samples: 156911488. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:14:23,445][86177] Avg episode reward: [(0, '-540.680'), (1, '-575.580')] -[2023-11-28 08:14:23,607][87426] Updated weights for policy 1, policy_version 306330 (0.0012) -[2023-11-28 08:14:25,227][87424] Updated weights for policy 0, policy_version 306569 (0.0012) -[2023-11-28 08:14:25,344][87426] Updated weights for policy 1, policy_version 306340 (0.0010) -[2023-11-28 08:14:25,619][87424] Updated weights for policy 0, policy_version 306579 (0.0012) -[2023-11-28 08:14:25,731][87426] Updated weights for policy 1, policy_version 306350 (0.0011) -[2023-11-28 08:14:25,993][87424] Updated weights for policy 0, policy_version 306589 (0.0011) -[2023-11-28 08:14:26,099][87426] Updated weights for policy 1, policy_version 306360 (0.0010) -[2023-11-28 08:14:28,021][87424] Updated weights for policy 0, policy_version 306599 (0.0010) -[2023-11-28 08:14:28,394][87424] Updated weights for policy 0, policy_version 306609 (0.0011) -[2023-11-28 08:14:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 156917760. Throughput: 0: 2656.4, 1: 2702.7. Samples: 156937168. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:14:28,445][87426] Updated weights for policy 1, policy_version 306370 (0.0011) -[2023-11-28 08:14:28,445][86177] Avg episode reward: [(0, '-562.920'), (1, '-577.540')] -[2023-11-28 08:14:28,776][87424] Updated weights for policy 0, policy_version 306619 (0.0011) -[2023-11-28 08:14:28,826][87426] Updated weights for policy 1, policy_version 306380 (0.0009) -[2023-11-28 08:14:29,228][87426] Updated weights for policy 1, policy_version 306390 (0.0011) -[2023-11-28 08:14:29,604][87426] Updated weights for policy 1, policy_version 306400 (0.0010) -[2023-11-28 08:14:30,886][87424] Updated weights for policy 0, policy_version 306629 (0.0012) -[2023-11-28 08:14:31,264][87424] Updated weights for policy 0, policy_version 306639 (0.0011) -[2023-11-28 08:14:31,503][87426] Updated weights for policy 1, policy_version 306410 (0.0012) -[2023-11-28 08:14:31,646][87424] Updated weights for policy 0, policy_version 306649 (0.0011) -[2023-11-28 08:14:31,884][87426] Updated weights for policy 1, policy_version 306420 (0.0009) -[2023-11-28 08:14:32,259][87426] Updated weights for policy 1, policy_version 306430 (0.0008) -[2023-11-28 08:14:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 156950528. Throughput: 0: 2687.5, 1: 2702.4. Samples: 156961724. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:14:33,445][86177] Avg episode reward: [(0, '-570.190'), (1, '-556.700')] -[2023-11-28 08:14:33,599][87424] Updated weights for policy 0, policy_version 306659 (0.0010) -[2023-11-28 08:14:33,970][87424] Updated weights for policy 0, policy_version 306669 (0.0008) -[2023-11-28 08:14:34,351][87424] Updated weights for policy 0, policy_version 306679 (0.0008) -[2023-11-28 08:14:34,685][87426] Updated weights for policy 1, policy_version 306440 (0.0011) -[2023-11-28 08:14:35,065][87426] Updated weights for policy 1, policy_version 306450 (0.0010) -[2023-11-28 08:14:35,437][87426] Updated weights for policy 1, policy_version 306460 (0.0009) -[2023-11-28 08:14:36,453][87424] Updated weights for policy 0, policy_version 306689 (0.0009) -[2023-11-28 08:14:36,840][87424] Updated weights for policy 0, policy_version 306699 (0.0011) -[2023-11-28 08:14:37,118][87426] Updated weights for policy 1, policy_version 306470 (0.0011) -[2023-11-28 08:14:37,225][87424] Updated weights for policy 0, policy_version 306709 (0.0009) -[2023-11-28 08:14:37,495][87426] Updated weights for policy 1, policy_version 306480 (0.0010) -[2023-11-28 08:14:37,612][87424] Updated weights for policy 0, policy_version 306719 (0.0012) -[2023-11-28 08:14:37,879][87426] Updated weights for policy 1, policy_version 306490 (0.0007) -[2023-11-28 08:14:38,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 156983296. Throughput: 0: 2692.1, 1: 2683.4. Samples: 156993436. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:14:38,446][86177] Avg episode reward: [(0, '-575.430'), (1, '-518.720')] -[2023-11-28 08:14:39,877][87424] Updated weights for policy 0, policy_version 306729 (0.0012) -[2023-11-28 08:14:40,271][87424] Updated weights for policy 0, policy_version 306739 (0.0010) -[2023-11-28 08:14:40,300][87426] Updated weights for policy 1, policy_version 306500 (0.0008) -[2023-11-28 08:14:40,642][87424] Updated weights for policy 0, policy_version 306749 (0.0011) -[2023-11-28 08:14:40,672][87426] Updated weights for policy 1, policy_version 306510 (0.0011) -[2023-11-28 08:14:41,054][87426] Updated weights for policy 1, policy_version 306520 (0.0009) -[2023-11-28 08:14:42,912][87424] Updated weights for policy 0, policy_version 306759 (0.0010) -[2023-11-28 08:14:43,289][87426] Updated weights for policy 1, policy_version 306530 (0.0008) -[2023-11-28 08:14:43,297][87424] Updated weights for policy 0, policy_version 306769 (0.0011) -[2023-11-28 08:14:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 156999680. Throughput: 0: 2708.8, 1: 2664.4. Samples: 157017988. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:14:43,445][86177] Avg episode reward: [(0, '-575.570'), (1, '-517.810')] -[2023-11-28 08:14:43,671][87426] Updated weights for policy 1, policy_version 306540 (0.0011) -[2023-11-28 08:14:43,679][87424] Updated weights for policy 0, policy_version 306779 (0.0010) -[2023-11-28 08:14:44,057][87426] Updated weights for policy 1, policy_version 306550 (0.0012) -[2023-11-28 08:14:44,429][87426] Updated weights for policy 1, policy_version 306560 (0.0012) -[2023-11-28 08:14:45,361][87424] Updated weights for policy 0, policy_version 306789 (0.0012) -[2023-11-28 08:14:45,741][87424] Updated weights for policy 0, policy_version 306799 (0.0012) -[2023-11-28 08:14:46,124][87424] Updated weights for policy 0, policy_version 306809 (0.0012) -[2023-11-28 08:14:46,598][87426] Updated weights for policy 1, policy_version 306570 (0.0011) -[2023-11-28 08:14:46,979][87426] Updated weights for policy 1, policy_version 306580 (0.0012) -[2023-11-28 08:14:47,356][87426] Updated weights for policy 1, policy_version 306590 (0.0012) -[2023-11-28 08:14:48,117][87424] Updated weights for policy 0, policy_version 306819 (0.0012) -[2023-11-28 08:14:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.9). Total num frames: 157032448. Throughput: 0: 2724.5, 1: 2670.4. Samples: 157043372. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:14:48,445][86177] Avg episode reward: [(0, '-554.470'), (1, '-514.940')] -[2023-11-28 08:14:48,496][87424] Updated weights for policy 0, policy_version 306829 (0.0012) -[2023-11-28 08:14:48,878][87424] Updated weights for policy 0, policy_version 306839 (0.0012) -[2023-11-28 08:14:49,814][87426] Updated weights for policy 1, policy_version 306600 (0.0010) -[2023-11-28 08:14:50,195][87426] Updated weights for policy 1, policy_version 306610 (0.0011) -[2023-11-28 08:14:50,581][87426] Updated weights for policy 1, policy_version 306620 (0.0009) -[2023-11-28 08:14:51,068][87424] Updated weights for policy 0, policy_version 306849 (0.0012) -[2023-11-28 08:14:51,449][87424] Updated weights for policy 0, policy_version 306859 (0.0012) -[2023-11-28 08:14:51,829][87424] Updated weights for policy 0, policy_version 306869 (0.0012) -[2023-11-28 08:14:52,208][87424] Updated weights for policy 0, policy_version 306879 (0.0009) -[2023-11-28 08:14:53,009][87426] Updated weights for policy 1, policy_version 306630 (0.0011) -[2023-11-28 08:14:53,378][87426] Updated weights for policy 1, policy_version 306640 (0.0012) -[2023-11-28 08:14:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 157057024. Throughput: 0: 2750.4, 1: 2678.0. Samples: 157076528. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:14:53,445][86177] Avg episode reward: [(0, '-547.250'), (1, '-514.110')] -[2023-11-28 08:14:53,758][87426] Updated weights for policy 1, policy_version 306650 (0.0012) -[2023-11-28 08:14:54,262][87424] Updated weights for policy 0, policy_version 306889 (0.0011) -[2023-11-28 08:14:54,641][87424] Updated weights for policy 0, policy_version 306899 (0.0011) -[2023-11-28 08:14:55,018][87424] Updated weights for policy 0, policy_version 306909 (0.0010) -[2023-11-28 08:14:55,719][87426] Updated weights for policy 1, policy_version 306660 (0.0010) -[2023-11-28 08:14:56,093][87426] Updated weights for policy 1, policy_version 306670 (0.0012) -[2023-11-28 08:14:56,466][87426] Updated weights for policy 1, policy_version 306680 (0.0012) -[2023-11-28 08:14:57,310][87424] Updated weights for policy 0, policy_version 306919 (0.0011) -[2023-11-28 08:14:57,697][87424] Updated weights for policy 0, policy_version 306929 (0.0012) -[2023-11-28 08:14:58,074][87424] Updated weights for policy 0, policy_version 306939 (0.0012) -[2023-11-28 08:14:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 157089792. Throughput: 0: 2737.9, 1: 2685.8. Samples: 157100472. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:14:58,445][86177] Avg episode reward: [(0, '-558.370'), (1, '-525.550')] -[2023-11-28 08:14:58,873][87426] Updated weights for policy 1, policy_version 306690 (0.0010) -[2023-11-28 08:14:59,264][87426] Updated weights for policy 1, policy_version 306700 (0.0008) -[2023-11-28 08:14:59,633][87426] Updated weights for policy 1, policy_version 306710 (0.0008) -[2023-11-28 08:14:59,793][87424] Updated weights for policy 0, policy_version 306949 (0.0010) -[2023-11-28 08:15:00,013][87426] Updated weights for policy 1, policy_version 306720 (0.0011) -[2023-11-28 08:15:00,176][87424] Updated weights for policy 0, policy_version 306959 (0.0008) -[2023-11-28 08:15:00,563][87424] Updated weights for policy 0, policy_version 306969 (0.0010) -[2023-11-28 08:15:02,465][87426] Updated weights for policy 1, policy_version 306730 (0.0011) -[2023-11-28 08:15:02,839][87426] Updated weights for policy 1, policy_version 306740 (0.0012) -[2023-11-28 08:15:02,918][87424] Updated weights for policy 0, policy_version 306979 (0.0011) -[2023-11-28 08:15:03,213][87426] Updated weights for policy 1, policy_version 306750 (0.0011) -[2023-11-28 08:15:03,291][87424] Updated weights for policy 0, policy_version 306989 (0.0007) -[2023-11-28 08:15:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 157114368. Throughput: 0: 2759.0, 1: 2695.7. Samples: 157125536. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:15:03,445][86177] Avg episode reward: [(0, '-557.190'), (1, '-522.680')] -[2023-11-28 08:15:03,681][87424] Updated weights for policy 0, policy_version 306999 (0.0009) -[2023-11-28 08:15:05,253][87426] Updated weights for policy 1, policy_version 306760 (0.0009) -[2023-11-28 08:15:05,633][87426] Updated weights for policy 1, policy_version 306770 (0.0008) -[2023-11-28 08:15:06,015][87426] Updated weights for policy 1, policy_version 306780 (0.0007) -[2023-11-28 08:15:06,222][87424] Updated weights for policy 0, policy_version 307009 (0.0009) -[2023-11-28 08:15:06,600][87424] Updated weights for policy 0, policy_version 307019 (0.0009) -[2023-11-28 08:15:06,986][87424] Updated weights for policy 0, policy_version 307029 (0.0010) -[2023-11-28 08:15:07,363][87424] Updated weights for policy 0, policy_version 307039 (0.0010) -[2023-11-28 08:15:08,210][87426] Updated weights for policy 1, policy_version 306790 (0.0010) -[2023-11-28 08:15:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 157138944. Throughput: 0: 2742.3, 1: 2714.8. Samples: 157157056. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:15:08,445][86177] Avg episode reward: [(0, '-556.500'), (1, '-522.770')] -[2023-11-28 08:15:08,584][87426] Updated weights for policy 1, policy_version 306800 (0.0011) -[2023-11-28 08:15:08,966][87426] Updated weights for policy 1, policy_version 306810 (0.0012) -[2023-11-28 08:15:09,253][87424] Updated weights for policy 0, policy_version 307049 (0.0008) -[2023-11-28 08:15:09,629][87424] Updated weights for policy 0, policy_version 307059 (0.0007) -[2023-11-28 08:15:10,017][87424] Updated weights for policy 0, policy_version 307069 (0.0010) -[2023-11-28 08:15:11,155][87426] Updated weights for policy 1, policy_version 306820 (0.0011) -[2023-11-28 08:15:11,529][87426] Updated weights for policy 1, policy_version 306830 (0.0012) -[2023-11-28 08:15:11,904][87426] Updated weights for policy 1, policy_version 306840 (0.0012) -[2023-11-28 08:15:12,413][87424] Updated weights for policy 0, policy_version 307079 (0.0012) -[2023-11-28 08:15:12,788][87424] Updated weights for policy 0, policy_version 307089 (0.0013) -[2023-11-28 08:15:13,173][87424] Updated weights for policy 0, policy_version 307099 (0.0012) -[2023-11-28 08:15:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 157171712. Throughput: 0: 2740.3, 1: 2688.2. Samples: 157181448. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:15:13,446][86177] Avg episode reward: [(0, '-574.590'), (1, '-537.130')] -[2023-11-28 08:15:14,062][87426] Updated weights for policy 1, policy_version 306850 (0.0012) -[2023-11-28 08:15:14,446][87426] Updated weights for policy 1, policy_version 306860 (0.0012) -[2023-11-28 08:15:14,840][87426] Updated weights for policy 1, policy_version 306870 (0.0007) -[2023-11-28 08:15:15,225][87426] Updated weights for policy 1, policy_version 306880 (0.0008) -[2023-11-28 08:15:15,683][87424] Updated weights for policy 0, policy_version 307109 (0.0010) -[2023-11-28 08:15:16,068][87424] Updated weights for policy 0, policy_version 307119 (0.0008) -[2023-11-28 08:15:16,449][87424] Updated weights for policy 0, policy_version 307129 (0.0007) -[2023-11-28 08:15:17,400][87426] Updated weights for policy 1, policy_version 306890 (0.0008) -[2023-11-28 08:15:17,778][87426] Updated weights for policy 1, policy_version 306900 (0.0012) -[2023-11-28 08:15:18,160][87426] Updated weights for policy 1, policy_version 306910 (0.0012) -[2023-11-28 08:15:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157196288. Throughput: 0: 2716.9, 1: 2705.0. Samples: 157205708. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:15:18,445][86177] Avg episode reward: [(0, '-556.170'), (1, '-525.420')] -[2023-11-28 08:15:18,651][87424] Updated weights for policy 0, policy_version 307139 (0.0009) -[2023-11-28 08:15:19,028][87424] Updated weights for policy 0, policy_version 307149 (0.0012) -[2023-11-28 08:15:19,411][87424] Updated weights for policy 0, policy_version 307159 (0.0012) -[2023-11-28 08:15:20,112][87426] Updated weights for policy 1, policy_version 306920 (0.0009) -[2023-11-28 08:15:20,485][87426] Updated weights for policy 1, policy_version 306930 (0.0009) -[2023-11-28 08:15:20,869][87426] Updated weights for policy 1, policy_version 306940 (0.0011) -[2023-11-28 08:15:21,664][87424] Updated weights for policy 0, policy_version 307169 (0.0012) -[2023-11-28 08:15:22,043][87424] Updated weights for policy 0, policy_version 307179 (0.0012) -[2023-11-28 08:15:22,422][87424] Updated weights for policy 0, policy_version 307189 (0.0012) -[2023-11-28 08:15:22,797][87424] Updated weights for policy 0, policy_version 307199 (0.0012) -[2023-11-28 08:15:23,422][87426] Updated weights for policy 1, policy_version 306950 (0.0011) -[2023-11-28 08:15:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157220864. Throughput: 0: 2738.5, 1: 2714.0. Samples: 157238796. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:15:23,445][86177] Avg episode reward: [(0, '-549.820'), (1, '-527.190')] -[2023-11-28 08:15:23,794][87426] Updated weights for policy 1, policy_version 306960 (0.0010) -[2023-11-28 08:15:24,171][87426] Updated weights for policy 1, policy_version 306970 (0.0009) -[2023-11-28 08:15:24,792][87424] Updated weights for policy 0, policy_version 307209 (0.0008) -[2023-11-28 08:15:25,168][87424] Updated weights for policy 0, policy_version 307219 (0.0011) -[2023-11-28 08:15:25,553][87424] Updated weights for policy 0, policy_version 307229 (0.0009) -[2023-11-28 08:15:26,632][87426] Updated weights for policy 1, policy_version 306980 (0.0008) -[2023-11-28 08:15:27,001][87426] Updated weights for policy 1, policy_version 306990 (0.0008) -[2023-11-28 08:15:27,134][87424] Updated weights for policy 0, policy_version 307239 (0.0011) -[2023-11-28 08:15:27,377][87426] Updated weights for policy 1, policy_version 307000 (0.0007) -[2023-11-28 08:15:27,518][87424] Updated weights for policy 0, policy_version 307249 (0.0007) -[2023-11-28 08:15:27,896][87424] Updated weights for policy 0, policy_version 307259 (0.0007) -[2023-11-28 08:15:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 157253632. Throughput: 0: 2746.9, 1: 2707.7. Samples: 157263448. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:15:28,445][86177] Avg episode reward: [(0, '-548.980'), (1, '-533.680')] -[2023-11-28 08:15:29,261][87426] Updated weights for policy 1, policy_version 307010 (0.0008) -[2023-11-28 08:15:29,647][87426] Updated weights for policy 1, policy_version 307020 (0.0011) -[2023-11-28 08:15:30,020][87426] Updated weights for policy 1, policy_version 307030 (0.0011) -[2023-11-28 08:15:30,193][87424] Updated weights for policy 0, policy_version 307269 (0.0010) -[2023-11-28 08:15:30,390][87426] Updated weights for policy 1, policy_version 307040 (0.0011) -[2023-11-28 08:15:30,574][87424] Updated weights for policy 0, policy_version 307279 (0.0010) -[2023-11-28 08:15:30,953][87424] Updated weights for policy 0, policy_version 307289 (0.0008) -[2023-11-28 08:15:32,888][87424] Updated weights for policy 0, policy_version 307299 (0.0011) -[2023-11-28 08:15:32,932][87426] Updated weights for policy 1, policy_version 307050 (0.0011) -[2023-11-28 08:15:33,271][87424] Updated weights for policy 0, policy_version 307309 (0.0011) -[2023-11-28 08:15:33,306][87426] Updated weights for policy 1, policy_version 307060 (0.0011) -[2023-11-28 08:15:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 157270016. Throughput: 0: 2770.5, 1: 2692.3. Samples: 157289196. Policy #0 lag: (min: 31.0, avg: 40.6, max: 63.0) -[2023-11-28 08:15:33,445][86177] Avg episode reward: [(0, '-537.300'), (1, '-532.870')] -[2023-11-28 08:15:33,657][87424] Updated weights for policy 0, policy_version 307319 (0.0011) -[2023-11-28 08:15:33,679][87426] Updated weights for policy 1, policy_version 307070 (0.0012) -[2023-11-28 08:15:35,678][87426] Updated weights for policy 1, policy_version 307080 (0.0012) -[2023-11-28 08:15:35,745][87424] Updated weights for policy 0, policy_version 307329 (0.0011) -[2023-11-28 08:15:36,058][87426] Updated weights for policy 1, policy_version 307090 (0.0012) -[2023-11-28 08:15:36,124][87424] Updated weights for policy 0, policy_version 307339 (0.0010) -[2023-11-28 08:15:36,434][87426] Updated weights for policy 1, policy_version 307100 (0.0010) -[2023-11-28 08:15:36,505][87424] Updated weights for policy 0, policy_version 307349 (0.0012) -[2023-11-28 08:15:36,887][87424] Updated weights for policy 0, policy_version 307359 (0.0012) -[2023-11-28 08:15:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 157302784. Throughput: 0: 2765.2, 1: 2698.1. Samples: 157322380. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:15:38,445][86177] Avg episode reward: [(0, '-548.760'), (1, '-527.700')] -[2023-11-28 08:15:38,850][87424] Updated weights for policy 0, policy_version 307369 (0.0009) -[2023-11-28 08:15:38,885][87426] Updated weights for policy 1, policy_version 307110 (0.0009) -[2023-11-28 08:15:39,230][87424] Updated weights for policy 0, policy_version 307379 (0.0011) -[2023-11-28 08:15:39,268][87426] Updated weights for policy 1, policy_version 307120 (0.0008) -[2023-11-28 08:15:39,610][87424] Updated weights for policy 0, policy_version 307389 (0.0011) -[2023-11-28 08:15:39,652][87426] Updated weights for policy 1, policy_version 307130 (0.0008) -[2023-11-28 08:15:41,717][87426] Updated weights for policy 1, policy_version 307140 (0.0010) -[2023-11-28 08:15:41,774][87424] Updated weights for policy 0, policy_version 307399 (0.0011) -[2023-11-28 08:15:42,096][87426] Updated weights for policy 1, policy_version 307150 (0.0012) -[2023-11-28 08:15:42,167][87424] Updated weights for policy 0, policy_version 307409 (0.0012) -[2023-11-28 08:15:42,469][87426] Updated weights for policy 1, policy_version 307160 (0.0011) -[2023-11-28 08:15:42,552][87424] Updated weights for policy 0, policy_version 307419 (0.0012) -[2023-11-28 08:15:43,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 157335552. Throughput: 0: 2785.6, 1: 2689.5. Samples: 157346852. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:15:43,446][86177] Avg episode reward: [(0, '-556.300'), (1, '-530.960')] -[2023-11-28 08:15:44,488][87426] Updated weights for policy 1, policy_version 307170 (0.0010) -[2023-11-28 08:15:44,613][87424] Updated weights for policy 0, policy_version 307429 (0.0010) -[2023-11-28 08:15:44,863][87426] Updated weights for policy 1, policy_version 307180 (0.0011) -[2023-11-28 08:15:44,995][87424] Updated weights for policy 0, policy_version 307439 (0.0009) -[2023-11-28 08:15:45,247][87426] Updated weights for policy 1, policy_version 307190 (0.0011) -[2023-11-28 08:15:45,378][87424] Updated weights for policy 0, policy_version 307449 (0.0011) -[2023-11-28 08:15:45,623][87426] Updated weights for policy 1, policy_version 307200 (0.0011) -[2023-11-28 08:15:47,622][87424] Updated weights for policy 0, policy_version 307459 (0.0010) -[2023-11-28 08:15:47,778][87426] Updated weights for policy 1, policy_version 307210 (0.0012) -[2023-11-28 08:15:47,995][87424] Updated weights for policy 0, policy_version 307469 (0.0007) -[2023-11-28 08:15:48,159][87426] Updated weights for policy 1, policy_version 307220 (0.0011) -[2023-11-28 08:15:48,381][87424] Updated weights for policy 0, policy_version 307479 (0.0007) -[2023-11-28 08:15:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 157351936. Throughput: 0: 2776.6, 1: 2702.6. Samples: 157372100. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:15:48,446][86177] Avg episode reward: [(0, '-564.490'), (1, '-526.620')] -[2023-11-28 08:15:48,534][87426] Updated weights for policy 1, policy_version 307230 (0.0012) -[2023-11-28 08:15:50,454][87424] Updated weights for policy 0, policy_version 307489 (0.0008) -[2023-11-28 08:15:50,545][87426] Updated weights for policy 1, policy_version 307240 (0.0012) -[2023-11-28 08:15:50,833][87424] Updated weights for policy 0, policy_version 307499 (0.0011) -[2023-11-28 08:15:50,921][87426] Updated weights for policy 1, policy_version 307250 (0.0011) -[2023-11-28 08:15:51,218][87424] Updated weights for policy 0, policy_version 307509 (0.0011) -[2023-11-28 08:15:51,308][87426] Updated weights for policy 1, policy_version 307260 (0.0012) -[2023-11-28 08:15:51,596][87424] Updated weights for policy 0, policy_version 307519 (0.0009) -[2023-11-28 08:15:53,296][87426] Updated weights for policy 1, policy_version 307270 (0.0012) -[2023-11-28 08:15:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157384704. Throughput: 0: 2800.9, 1: 2735.6. Samples: 157406196. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:15:53,445][86177] Avg episode reward: [(0, '-560.350'), (1, '-512.190')] -[2023-11-28 08:15:53,683][87426] Updated weights for policy 1, policy_version 307280 (0.0012) -[2023-11-28 08:15:53,914][87424] Updated weights for policy 0, policy_version 307529 (0.0010) -[2023-11-28 08:15:54,056][87426] Updated weights for policy 1, policy_version 307290 (0.0011) -[2023-11-28 08:15:54,290][87424] Updated weights for policy 0, policy_version 307539 (0.0012) -[2023-11-28 08:15:54,673][87424] Updated weights for policy 0, policy_version 307549 (0.0012) -[2023-11-28 08:15:56,009][87426] Updated weights for policy 1, policy_version 307300 (0.0010) -[2023-11-28 08:15:56,390][87426] Updated weights for policy 1, policy_version 307310 (0.0007) -[2023-11-28 08:15:56,769][87426] Updated weights for policy 1, policy_version 307320 (0.0007) -[2023-11-28 08:15:57,156][87424] Updated weights for policy 0, policy_version 307559 (0.0009) -[2023-11-28 08:15:57,544][87424] Updated weights for policy 0, policy_version 307569 (0.0007) -[2023-11-28 08:15:57,923][87424] Updated weights for policy 0, policy_version 307579 (0.0007) -[2023-11-28 08:15:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157417472. Throughput: 0: 2781.1, 1: 2741.0. Samples: 157429940. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:15:58,445][86177] Avg episode reward: [(0, '-554.510'), (1, '-520.580')] -[2023-11-28 08:15:58,847][87426] Updated weights for policy 1, policy_version 307330 (0.0007) -[2023-11-28 08:15:59,237][87426] Updated weights for policy 1, policy_version 307340 (0.0007) -[2023-11-28 08:15:59,611][87426] Updated weights for policy 1, policy_version 307350 (0.0008) -[2023-11-28 08:15:59,988][87426] Updated weights for policy 1, policy_version 307360 (0.0010) -[2023-11-28 08:16:00,268][87424] Updated weights for policy 0, policy_version 307589 (0.0009) -[2023-11-28 08:16:00,647][87424] Updated weights for policy 0, policy_version 307599 (0.0012) -[2023-11-28 08:16:01,037][87424] Updated weights for policy 0, policy_version 307609 (0.0012) -[2023-11-28 08:16:02,413][87426] Updated weights for policy 1, policy_version 307370 (0.0012) -[2023-11-28 08:16:02,794][87426] Updated weights for policy 1, policy_version 307380 (0.0012) -[2023-11-28 08:16:03,169][87426] Updated weights for policy 1, policy_version 307390 (0.0010) -[2023-11-28 08:16:03,332][87424] Updated weights for policy 0, policy_version 307619 (0.0010) -[2023-11-28 08:16:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157442048. Throughput: 0: 2779.7, 1: 2738.0. Samples: 157454004. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:03,445][86177] Avg episode reward: [(0, '-553.240'), (1, '-518.830')] -[2023-11-28 08:16:03,715][87424] Updated weights for policy 0, policy_version 307629 (0.0007) -[2023-11-28 08:16:04,092][87424] Updated weights for policy 0, policy_version 307639 (0.0007) -[2023-11-28 08:16:05,741][87426] Updated weights for policy 1, policy_version 307400 (0.0008) -[2023-11-28 08:16:05,802][87424] Updated weights for policy 0, policy_version 307649 (0.0008) -[2023-11-28 08:16:06,129][87426] Updated weights for policy 1, policy_version 307410 (0.0007) -[2023-11-28 08:16:06,176][87424] Updated weights for policy 0, policy_version 307659 (0.0010) -[2023-11-28 08:16:06,519][87426] Updated weights for policy 1, policy_version 307420 (0.0007) -[2023-11-28 08:16:06,547][87424] Updated weights for policy 0, policy_version 307669 (0.0011) -[2023-11-28 08:16:06,934][87424] Updated weights for policy 0, policy_version 307679 (0.0011) -[2023-11-28 08:16:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157466624. Throughput: 0: 2774.6, 1: 2715.2. Samples: 157485836. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:08,445][86177] Avg episode reward: [(0, '-547.570'), (1, '-529.780')] -[2023-11-28 08:16:08,501][87426] Updated weights for policy 1, policy_version 307430 (0.0008) -[2023-11-28 08:16:08,887][87426] Updated weights for policy 1, policy_version 307440 (0.0008) -[2023-11-28 08:16:09,264][87426] Updated weights for policy 1, policy_version 307450 (0.0008) -[2023-11-28 08:16:09,309][87424] Updated weights for policy 0, policy_version 307689 (0.0012) -[2023-11-28 08:16:09,690][87424] Updated weights for policy 0, policy_version 307699 (0.0011) -[2023-11-28 08:16:10,076][87424] Updated weights for policy 0, policy_version 307709 (0.0012) -[2023-11-28 08:16:11,337][87426] Updated weights for policy 1, policy_version 307460 (0.0012) -[2023-11-28 08:16:11,721][87426] Updated weights for policy 1, policy_version 307470 (0.0011) -[2023-11-28 08:16:12,089][87426] Updated weights for policy 1, policy_version 307480 (0.0011) -[2023-11-28 08:16:12,241][87424] Updated weights for policy 0, policy_version 307719 (0.0011) -[2023-11-28 08:16:12,631][87424] Updated weights for policy 0, policy_version 307729 (0.0012) -[2023-11-28 08:16:13,004][87424] Updated weights for policy 0, policy_version 307739 (0.0011) -[2023-11-28 08:16:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157499392. Throughput: 0: 2753.3, 1: 2733.6. Samples: 157510360. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:13,445][86177] Avg episode reward: [(0, '-546.010'), (1, '-531.440')] -[2023-11-28 08:16:14,064][87426] Updated weights for policy 1, policy_version 307490 (0.0011) -[2023-11-28 08:16:14,450][87426] Updated weights for policy 1, policy_version 307500 (0.0012) -[2023-11-28 08:16:14,824][87426] Updated weights for policy 1, policy_version 307510 (0.0012) -[2023-11-28 08:16:14,942][87424] Updated weights for policy 0, policy_version 307749 (0.0008) -[2023-11-28 08:16:15,193][87426] Updated weights for policy 1, policy_version 307520 (0.0011) -[2023-11-28 08:16:15,316][87424] Updated weights for policy 0, policy_version 307759 (0.0007) -[2023-11-28 08:16:15,697][87424] Updated weights for policy 0, policy_version 307769 (0.0011) -[2023-11-28 08:16:17,288][87426] Updated weights for policy 1, policy_version 307530 (0.0012) -[2023-11-28 08:16:17,663][87426] Updated weights for policy 1, policy_version 307540 (0.0012) -[2023-11-28 08:16:17,982][87424] Updated weights for policy 0, policy_version 307779 (0.0012) -[2023-11-28 08:16:18,043][87426] Updated weights for policy 1, policy_version 307550 (0.0012) -[2023-11-28 08:16:18,363][87424] Updated weights for policy 0, policy_version 307789 (0.0007) -[2023-11-28 08:16:18,445][86177] Fps is (10 sec: 5734.1, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 157523968. Throughput: 0: 2718.1, 1: 2754.8. Samples: 157535480. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:18,446][86177] Avg episode reward: [(0, '-545.950'), (1, '-519.310')] -[2023-11-28 08:16:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000307552_78733312.pth... -[2023-11-28 08:16:18,505][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000305024_78086144.pth -[2023-11-28 08:16:18,750][87424] Updated weights for policy 0, policy_version 307799 (0.0008) -[2023-11-28 08:16:19,093][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000307808_78798848.pth... -[2023-11-28 08:16:19,129][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000305248_78143488.pth -[2023-11-28 08:16:19,817][87426] Updated weights for policy 1, policy_version 307560 (0.0009) -[2023-11-28 08:16:20,193][87426] Updated weights for policy 1, policy_version 307570 (0.0011) -[2023-11-28 08:16:20,574][87426] Updated weights for policy 1, policy_version 307580 (0.0012) -[2023-11-28 08:16:20,913][87424] Updated weights for policy 0, policy_version 307809 (0.0011) -[2023-11-28 08:16:21,294][87424] Updated weights for policy 0, policy_version 307819 (0.0012) -[2023-11-28 08:16:21,681][87424] Updated weights for policy 0, policy_version 307829 (0.0011) -[2023-11-28 08:16:22,054][87424] Updated weights for policy 0, policy_version 307839 (0.0011) -[2023-11-28 08:16:22,574][87426] Updated weights for policy 1, policy_version 307590 (0.0011) -[2023-11-28 08:16:22,966][87426] Updated weights for policy 1, policy_version 307600 (0.0010) -[2023-11-28 08:16:23,348][87426] Updated weights for policy 1, policy_version 307610 (0.0012) -[2023-11-28 08:16:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157548544. Throughput: 0: 2705.8, 1: 2758.3. Samples: 157568264. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:23,445][86177] Avg episode reward: [(0, '-541.960'), (1, '-507.180')] -[2023-11-28 08:16:24,021][87424] Updated weights for policy 0, policy_version 307849 (0.0011) -[2023-11-28 08:16:24,407][87424] Updated weights for policy 0, policy_version 307859 (0.0012) -[2023-11-28 08:16:24,800][87424] Updated weights for policy 0, policy_version 307869 (0.0012) -[2023-11-28 08:16:25,627][87426] Updated weights for policy 1, policy_version 307620 (0.0010) -[2023-11-28 08:16:26,014][87426] Updated weights for policy 1, policy_version 307630 (0.0007) -[2023-11-28 08:16:26,398][87426] Updated weights for policy 1, policy_version 307640 (0.0009) -[2023-11-28 08:16:27,086][87424] Updated weights for policy 0, policy_version 307879 (0.0009) -[2023-11-28 08:16:27,477][87424] Updated weights for policy 0, policy_version 307889 (0.0007) -[2023-11-28 08:16:27,869][87424] Updated weights for policy 0, policy_version 307899 (0.0007) -[2023-11-28 08:16:28,324][87426] Updated weights for policy 1, policy_version 307650 (0.0008) -[2023-11-28 08:16:28,444][86177] Fps is (10 sec: 5734.8, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157581312. Throughput: 0: 2708.3, 1: 2773.8. Samples: 157593544. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:28,445][86177] Avg episode reward: [(0, '-546.520'), (1, '-506.990')] -[2023-11-28 08:16:28,696][87426] Updated weights for policy 1, policy_version 307660 (0.0012) -[2023-11-28 08:16:29,079][87426] Updated weights for policy 1, policy_version 307670 (0.0012) -[2023-11-28 08:16:29,452][87426] Updated weights for policy 1, policy_version 307680 (0.0012) -[2023-11-28 08:16:30,348][87424] Updated weights for policy 0, policy_version 307909 (0.0009) -[2023-11-28 08:16:30,720][87424] Updated weights for policy 0, policy_version 307919 (0.0012) -[2023-11-28 08:16:31,109][87424] Updated weights for policy 0, policy_version 307929 (0.0010) -[2023-11-28 08:16:32,088][87426] Updated weights for policy 1, policy_version 307690 (0.0012) -[2023-11-28 08:16:32,461][87426] Updated weights for policy 1, policy_version 307700 (0.0012) -[2023-11-28 08:16:32,843][87426] Updated weights for policy 1, policy_version 307710 (0.0011) -[2023-11-28 08:16:32,879][87424] Updated weights for policy 0, policy_version 307939 (0.0011) -[2023-11-28 08:16:33,261][87424] Updated weights for policy 0, policy_version 307949 (0.0009) -[2023-11-28 08:16:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 157605888. Throughput: 0: 2708.3, 1: 2751.6. Samples: 157617792. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:33,445][86177] Avg episode reward: [(0, '-551.080'), (1, '-510.330')] -[2023-11-28 08:16:33,644][87424] Updated weights for policy 0, policy_version 307959 (0.0011) -[2023-11-28 08:16:34,824][87426] Updated weights for policy 1, policy_version 307720 (0.0010) -[2023-11-28 08:16:35,203][87426] Updated weights for policy 1, policy_version 307730 (0.0009) -[2023-11-28 08:16:35,349][87424] Updated weights for policy 0, policy_version 307969 (0.0012) -[2023-11-28 08:16:35,588][87426] Updated weights for policy 1, policy_version 307740 (0.0009) -[2023-11-28 08:16:35,732][87424] Updated weights for policy 0, policy_version 307979 (0.0011) -[2023-11-28 08:16:36,126][87424] Updated weights for policy 0, policy_version 307989 (0.0012) -[2023-11-28 08:16:36,497][87424] Updated weights for policy 0, policy_version 307999 (0.0012) -[2023-11-28 08:16:38,064][87426] Updated weights for policy 1, policy_version 307750 (0.0011) -[2023-11-28 08:16:38,385][87424] Updated weights for policy 0, policy_version 308009 (0.0012) -[2023-11-28 08:16:38,444][87426] Updated weights for policy 1, policy_version 307760 (0.0011) -[2023-11-28 08:16:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157630464. Throughput: 0: 2710.7, 1: 2733.7. Samples: 157651192. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:38,445][86177] Avg episode reward: [(0, '-562.750'), (1, '-510.980')] -[2023-11-28 08:16:38,761][87424] Updated weights for policy 0, policy_version 308019 (0.0012) -[2023-11-28 08:16:38,831][87426] Updated weights for policy 1, policy_version 307770 (0.0011) -[2023-11-28 08:16:39,143][87424] Updated weights for policy 0, policy_version 308029 (0.0012) -[2023-11-28 08:16:40,779][87426] Updated weights for policy 1, policy_version 307780 (0.0011) -[2023-11-28 08:16:41,143][87426] Updated weights for policy 1, policy_version 307790 (0.0011) -[2023-11-28 08:16:41,368][87424] Updated weights for policy 0, policy_version 308039 (0.0010) -[2023-11-28 08:16:41,521][87426] Updated weights for policy 1, policy_version 307800 (0.0010) -[2023-11-28 08:16:41,761][87424] Updated weights for policy 0, policy_version 308049 (0.0011) -[2023-11-28 08:16:42,131][87424] Updated weights for policy 0, policy_version 308059 (0.0011) -[2023-11-28 08:16:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157663232. Throughput: 0: 2716.6, 1: 2738.1. Samples: 157675404. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:43,445][86177] Avg episode reward: [(0, '-563.560'), (1, '-510.450')] -[2023-11-28 08:16:43,657][87426] Updated weights for policy 1, policy_version 307810 (0.0011) -[2023-11-28 08:16:44,037][87426] Updated weights for policy 1, policy_version 307820 (0.0011) -[2023-11-28 08:16:44,299][87424] Updated weights for policy 0, policy_version 308069 (0.0011) -[2023-11-28 08:16:44,411][87426] Updated weights for policy 1, policy_version 307830 (0.0007) -[2023-11-28 08:16:44,677][87424] Updated weights for policy 0, policy_version 308079 (0.0008) -[2023-11-28 08:16:44,792][87426] Updated weights for policy 1, policy_version 307840 (0.0008) -[2023-11-28 08:16:45,056][87424] Updated weights for policy 0, policy_version 308089 (0.0009) -[2023-11-28 08:16:47,338][87426] Updated weights for policy 1, policy_version 307850 (0.0010) -[2023-11-28 08:16:47,602][87424] Updated weights for policy 0, policy_version 308099 (0.0009) -[2023-11-28 08:16:47,710][87426] Updated weights for policy 1, policy_version 307860 (0.0012) -[2023-11-28 08:16:47,983][87424] Updated weights for policy 0, policy_version 308109 (0.0008) -[2023-11-28 08:16:48,089][87426] Updated weights for policy 1, policy_version 307870 (0.0012) -[2023-11-28 08:16:48,377][87424] Updated weights for policy 0, policy_version 308119 (0.0007) -[2023-11-28 08:16:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 157687808. Throughput: 0: 2721.6, 1: 2729.8. Samples: 157699316. Policy #0 lag: (min: 29.0, avg: 45.6, max: 72.0) -[2023-11-28 08:16:48,445][86177] Avg episode reward: [(0, '-560.620'), (1, '-515.310')] -[2023-11-28 08:16:49,818][87426] Updated weights for policy 1, policy_version 307880 (0.0012) -[2023-11-28 08:16:50,200][87426] Updated weights for policy 1, policy_version 307890 (0.0009) -[2023-11-28 08:16:50,579][87426] Updated weights for policy 1, policy_version 307900 (0.0010) -[2023-11-28 08:16:50,878][87424] Updated weights for policy 0, policy_version 308129 (0.0009) -[2023-11-28 08:16:51,253][87424] Updated weights for policy 0, policy_version 308139 (0.0010) -[2023-11-28 08:16:51,631][87424] Updated weights for policy 0, policy_version 308149 (0.0010) -[2023-11-28 08:16:52,036][87424] Updated weights for policy 0, policy_version 308159 (0.0012) -[2023-11-28 08:16:53,083][87426] Updated weights for policy 1, policy_version 307910 (0.0008) -[2023-11-28 08:16:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157712384. Throughput: 0: 2718.6, 1: 2750.9. Samples: 157731964. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:16:53,445][86177] Avg episode reward: [(0, '-544.590'), (1, '-514.240')] -[2023-11-28 08:16:53,461][87426] Updated weights for policy 1, policy_version 307920 (0.0010) -[2023-11-28 08:16:53,839][87426] Updated weights for policy 1, policy_version 307930 (0.0012) -[2023-11-28 08:16:53,865][87424] Updated weights for policy 0, policy_version 308169 (0.0011) -[2023-11-28 08:16:54,254][87424] Updated weights for policy 0, policy_version 308179 (0.0012) -[2023-11-28 08:16:54,636][87424] Updated weights for policy 0, policy_version 308189 (0.0012) -[2023-11-28 08:16:55,599][87426] Updated weights for policy 1, policy_version 307940 (0.0011) -[2023-11-28 08:16:55,973][87426] Updated weights for policy 1, policy_version 307950 (0.0012) -[2023-11-28 08:16:56,345][87426] Updated weights for policy 1, policy_version 307960 (0.0012) -[2023-11-28 08:16:57,054][87424] Updated weights for policy 0, policy_version 308199 (0.0009) -[2023-11-28 08:16:57,435][87424] Updated weights for policy 0, policy_version 308209 (0.0007) -[2023-11-28 08:16:57,828][87424] Updated weights for policy 0, policy_version 308219 (0.0008) -[2023-11-28 08:16:58,238][87426] Updated weights for policy 1, policy_version 307970 (0.0012) -[2023-11-28 08:16:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157745152. Throughput: 0: 2725.4, 1: 2753.8. Samples: 157756924. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:16:58,445][86177] Avg episode reward: [(0, '-573.610'), (1, '-510.320')] -[2023-11-28 08:16:58,618][87426] Updated weights for policy 1, policy_version 307980 (0.0012) -[2023-11-28 08:16:58,985][87426] Updated weights for policy 1, policy_version 307990 (0.0012) -[2023-11-28 08:16:59,371][87426] Updated weights for policy 1, policy_version 308000 (0.0012) -[2023-11-28 08:17:00,098][87424] Updated weights for policy 0, policy_version 308229 (0.0010) -[2023-11-28 08:17:00,486][87424] Updated weights for policy 0, policy_version 308239 (0.0012) -[2023-11-28 08:17:00,864][87424] Updated weights for policy 0, policy_version 308249 (0.0011) -[2023-11-28 08:17:01,269][87426] Updated weights for policy 1, policy_version 308010 (0.0010) -[2023-11-28 08:17:01,651][87426] Updated weights for policy 1, policy_version 308020 (0.0008) -[2023-11-28 08:17:02,022][87426] Updated weights for policy 1, policy_version 308030 (0.0009) -[2023-11-28 08:17:02,844][87424] Updated weights for policy 0, policy_version 308259 (0.0011) -[2023-11-28 08:17:03,224][87424] Updated weights for policy 0, policy_version 308269 (0.0011) -[2023-11-28 08:17:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157769728. Throughput: 0: 2729.7, 1: 2748.7. Samples: 157782008. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:03,446][86177] Avg episode reward: [(0, '-567.920'), (1, '-510.460')] -[2023-11-28 08:17:03,599][87424] Updated weights for policy 0, policy_version 308279 (0.0011) -[2023-11-28 08:17:04,315][87426] Updated weights for policy 1, policy_version 308040 (0.0008) -[2023-11-28 08:17:04,696][87426] Updated weights for policy 1, policy_version 308050 (0.0011) -[2023-11-28 08:17:05,074][87426] Updated weights for policy 1, policy_version 308060 (0.0010) -[2023-11-28 08:17:05,565][87424] Updated weights for policy 0, policy_version 308289 (0.0011) -[2023-11-28 08:17:05,944][87424] Updated weights for policy 0, policy_version 308299 (0.0010) -[2023-11-28 08:17:06,338][87424] Updated weights for policy 0, policy_version 308309 (0.0011) -[2023-11-28 08:17:06,728][87424] Updated weights for policy 0, policy_version 308319 (0.0011) -[2023-11-28 08:17:06,963][87426] Updated weights for policy 1, policy_version 308070 (0.0011) -[2023-11-28 08:17:07,335][87426] Updated weights for policy 1, policy_version 308080 (0.0011) -[2023-11-28 08:17:07,710][87426] Updated weights for policy 1, policy_version 308090 (0.0012) -[2023-11-28 08:17:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 157802496. Throughput: 0: 2741.9, 1: 2746.9. Samples: 157815260. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:08,445][86177] Avg episode reward: [(0, '-575.210'), (1, '-507.370')] -[2023-11-28 08:17:08,753][87424] Updated weights for policy 0, policy_version 308329 (0.0012) -[2023-11-28 08:17:09,131][87424] Updated weights for policy 0, policy_version 308339 (0.0011) -[2023-11-28 08:17:09,519][87424] Updated weights for policy 0, policy_version 308349 (0.0011) -[2023-11-28 08:17:09,863][87426] Updated weights for policy 1, policy_version 308100 (0.0011) -[2023-11-28 08:17:10,245][87426] Updated weights for policy 1, policy_version 308110 (0.0008) -[2023-11-28 08:17:10,627][87426] Updated weights for policy 1, policy_version 308120 (0.0009) -[2023-11-28 08:17:11,786][87424] Updated weights for policy 0, policy_version 308359 (0.0011) -[2023-11-28 08:17:12,177][87424] Updated weights for policy 0, policy_version 308369 (0.0009) -[2023-11-28 08:17:12,559][87424] Updated weights for policy 0, policy_version 308379 (0.0008) -[2023-11-28 08:17:13,135][87426] Updated weights for policy 1, policy_version 308130 (0.0012) -[2023-11-28 08:17:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157827072. Throughput: 0: 2735.0, 1: 2746.0. Samples: 157840192. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:13,445][86177] Avg episode reward: [(0, '-574.130'), (1, '-510.570')] -[2023-11-28 08:17:13,518][87426] Updated weights for policy 1, policy_version 308140 (0.0012) -[2023-11-28 08:17:13,900][87426] Updated weights for policy 1, policy_version 308150 (0.0012) -[2023-11-28 08:17:14,278][87426] Updated weights for policy 1, policy_version 308160 (0.0008) -[2023-11-28 08:17:14,772][87424] Updated weights for policy 0, policy_version 308389 (0.0009) -[2023-11-28 08:17:15,150][87424] Updated weights for policy 0, policy_version 308399 (0.0008) -[2023-11-28 08:17:15,537][87424] Updated weights for policy 0, policy_version 308409 (0.0010) -[2023-11-28 08:17:16,288][87426] Updated weights for policy 1, policy_version 308170 (0.0012) -[2023-11-28 08:17:16,671][87426] Updated weights for policy 1, policy_version 308180 (0.0011) -[2023-11-28 08:17:17,045][87426] Updated weights for policy 1, policy_version 308190 (0.0007) -[2023-11-28 08:17:17,826][87424] Updated weights for policy 0, policy_version 308419 (0.0011) -[2023-11-28 08:17:18,210][87424] Updated weights for policy 0, policy_version 308429 (0.0007) -[2023-11-28 08:17:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 157851648. Throughput: 0: 2726.5, 1: 2742.1. Samples: 157863880. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:18,446][86177] Avg episode reward: [(0, '-545.570'), (1, '-514.490')] -[2023-11-28 08:17:18,594][87424] Updated weights for policy 0, policy_version 308439 (0.0007) -[2023-11-28 08:17:19,540][87426] Updated weights for policy 1, policy_version 308200 (0.0011) -[2023-11-28 08:17:19,922][87426] Updated weights for policy 1, policy_version 308210 (0.0012) -[2023-11-28 08:17:20,297][87426] Updated weights for policy 1, policy_version 308220 (0.0012) -[2023-11-28 08:17:20,739][87424] Updated weights for policy 0, policy_version 308449 (0.0009) -[2023-11-28 08:17:21,112][87424] Updated weights for policy 0, policy_version 308459 (0.0012) -[2023-11-28 08:17:21,489][87424] Updated weights for policy 0, policy_version 308469 (0.0012) -[2023-11-28 08:17:21,875][87424] Updated weights for policy 0, policy_version 308479 (0.0012) -[2023-11-28 08:17:22,731][87426] Updated weights for policy 1, policy_version 308230 (0.0012) -[2023-11-28 08:17:23,109][87426] Updated weights for policy 1, policy_version 308240 (0.0009) -[2023-11-28 08:17:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 157876224. Throughput: 0: 2718.8, 1: 2719.8. Samples: 157895928. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:23,445][86177] Avg episode reward: [(0, '-547.150'), (1, '-520.120')] -[2023-11-28 08:17:23,492][87426] Updated weights for policy 1, policy_version 308250 (0.0007) -[2023-11-28 08:17:23,867][87424] Updated weights for policy 0, policy_version 308489 (0.0011) -[2023-11-28 08:17:24,250][87424] Updated weights for policy 0, policy_version 308499 (0.0012) -[2023-11-28 08:17:24,633][87424] Updated weights for policy 0, policy_version 308509 (0.0012) -[2023-11-28 08:17:25,989][87426] Updated weights for policy 1, policy_version 308260 (0.0008) -[2023-11-28 08:17:26,360][87426] Updated weights for policy 1, policy_version 308270 (0.0008) -[2023-11-28 08:17:26,740][87426] Updated weights for policy 1, policy_version 308280 (0.0009) -[2023-11-28 08:17:26,821][87424] Updated weights for policy 0, policy_version 308519 (0.0011) -[2023-11-28 08:17:27,204][87424] Updated weights for policy 0, policy_version 308529 (0.0012) -[2023-11-28 08:17:27,586][87424] Updated weights for policy 0, policy_version 308539 (0.0012) -[2023-11-28 08:17:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157908992. Throughput: 0: 2721.8, 1: 2718.5. Samples: 157920216. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:28,445][86177] Avg episode reward: [(0, '-545.800'), (1, '-513.970')] -[2023-11-28 08:17:28,964][87426] Updated weights for policy 1, policy_version 308290 (0.0008) -[2023-11-28 08:17:29,334][87426] Updated weights for policy 1, policy_version 308300 (0.0011) -[2023-11-28 08:17:29,708][87426] Updated weights for policy 1, policy_version 308310 (0.0011) -[2023-11-28 08:17:30,050][87424] Updated weights for policy 0, policy_version 308549 (0.0011) -[2023-11-28 08:17:30,081][87426] Updated weights for policy 1, policy_version 308320 (0.0011) -[2023-11-28 08:17:30,432][87424] Updated weights for policy 0, policy_version 308559 (0.0012) -[2023-11-28 08:17:30,807][87424] Updated weights for policy 0, policy_version 308569 (0.0012) -[2023-11-28 08:17:32,147][87426] Updated weights for policy 1, policy_version 308330 (0.0009) -[2023-11-28 08:17:32,525][87426] Updated weights for policy 1, policy_version 308340 (0.0009) -[2023-11-28 08:17:32,829][87424] Updated weights for policy 0, policy_version 308579 (0.0009) -[2023-11-28 08:17:32,907][87426] Updated weights for policy 1, policy_version 308350 (0.0009) -[2023-11-28 08:17:33,213][87424] Updated weights for policy 0, policy_version 308589 (0.0012) -[2023-11-28 08:17:33,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157933568. Throughput: 0: 2751.2, 1: 2736.0. Samples: 157946240. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:33,446][86177] Avg episode reward: [(0, '-550.690'), (1, '-513.860')] -[2023-11-28 08:17:33,598][87424] Updated weights for policy 0, policy_version 308599 (0.0011) -[2023-11-28 08:17:35,267][87426] Updated weights for policy 1, policy_version 308360 (0.0011) -[2023-11-28 08:17:35,429][87424] Updated weights for policy 0, policy_version 308609 (0.0011) -[2023-11-28 08:17:35,639][87426] Updated weights for policy 1, policy_version 308370 (0.0011) -[2023-11-28 08:17:35,797][87424] Updated weights for policy 0, policy_version 308619 (0.0011) -[2023-11-28 08:17:36,013][87426] Updated weights for policy 1, policy_version 308380 (0.0010) -[2023-11-28 08:17:36,184][87424] Updated weights for policy 0, policy_version 308629 (0.0012) -[2023-11-28 08:17:36,567][87424] Updated weights for policy 0, policy_version 308639 (0.0012) -[2023-11-28 08:17:37,901][87426] Updated weights for policy 1, policy_version 308390 (0.0011) -[2023-11-28 08:17:38,287][87426] Updated weights for policy 1, policy_version 308400 (0.0012) -[2023-11-28 08:17:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157958144. Throughput: 0: 2740.6, 1: 2746.7. Samples: 157978892. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:38,446][86177] Avg episode reward: [(0, '-553.690'), (1, '-517.910')] -[2023-11-28 08:17:38,670][87426] Updated weights for policy 1, policy_version 308410 (0.0012) -[2023-11-28 08:17:39,102][87424] Updated weights for policy 0, policy_version 308649 (0.0009) -[2023-11-28 08:17:39,483][87424] Updated weights for policy 0, policy_version 308659 (0.0008) -[2023-11-28 08:17:39,865][87424] Updated weights for policy 0, policy_version 308669 (0.0011) -[2023-11-28 08:17:40,650][87426] Updated weights for policy 1, policy_version 308420 (0.0011) -[2023-11-28 08:17:41,018][87426] Updated weights for policy 1, policy_version 308430 (0.0012) -[2023-11-28 08:17:41,396][87426] Updated weights for policy 1, policy_version 308440 (0.0012) -[2023-11-28 08:17:41,730][87424] Updated weights for policy 0, policy_version 308679 (0.0011) -[2023-11-28 08:17:42,115][87424] Updated weights for policy 0, policy_version 308689 (0.0012) -[2023-11-28 08:17:42,494][87424] Updated weights for policy 0, policy_version 308699 (0.0009) -[2023-11-28 08:17:43,405][87426] Updated weights for policy 1, policy_version 308450 (0.0011) -[2023-11-28 08:17:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 157990912. Throughput: 0: 2745.7, 1: 2727.1. Samples: 158003200. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:43,445][86177] Avg episode reward: [(0, '-568.530'), (1, '-512.980')] -[2023-11-28 08:17:43,782][87426] Updated weights for policy 1, policy_version 308460 (0.0007) -[2023-11-28 08:17:44,166][87426] Updated weights for policy 1, policy_version 308470 (0.0007) -[2023-11-28 08:17:44,549][87426] Updated weights for policy 1, policy_version 308480 (0.0007) -[2023-11-28 08:17:45,095][87424] Updated weights for policy 0, policy_version 308709 (0.0008) -[2023-11-28 08:17:45,480][87424] Updated weights for policy 0, policy_version 308719 (0.0010) -[2023-11-28 08:17:45,853][87424] Updated weights for policy 0, policy_version 308729 (0.0012) -[2023-11-28 08:17:46,843][87426] Updated weights for policy 1, policy_version 308490 (0.0008) -[2023-11-28 08:17:47,225][87426] Updated weights for policy 1, policy_version 308500 (0.0008) -[2023-11-28 08:17:47,608][87426] Updated weights for policy 1, policy_version 308510 (0.0007) -[2023-11-28 08:17:47,876][87424] Updated weights for policy 0, policy_version 308739 (0.0011) -[2023-11-28 08:17:48,255][87424] Updated weights for policy 0, policy_version 308749 (0.0011) -[2023-11-28 08:17:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158015488. Throughput: 0: 2750.0, 1: 2708.0. Samples: 158027616. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:48,445][86177] Avg episode reward: [(0, '-596.160'), (1, '-513.560')] -[2023-11-28 08:17:48,632][87424] Updated weights for policy 0, policy_version 308759 (0.0008) -[2023-11-28 08:17:50,012][87426] Updated weights for policy 1, policy_version 308520 (0.0010) -[2023-11-28 08:17:50,393][87426] Updated weights for policy 1, policy_version 308530 (0.0008) -[2023-11-28 08:17:50,492][87424] Updated weights for policy 0, policy_version 308769 (0.0008) -[2023-11-28 08:17:50,768][87426] Updated weights for policy 1, policy_version 308540 (0.0010) -[2023-11-28 08:17:50,871][87424] Updated weights for policy 0, policy_version 308779 (0.0012) -[2023-11-28 08:17:51,252][87424] Updated weights for policy 0, policy_version 308789 (0.0010) -[2023-11-28 08:17:51,634][87424] Updated weights for policy 0, policy_version 308799 (0.0011) -[2023-11-28 08:17:52,976][87426] Updated weights for policy 1, policy_version 308550 (0.0008) -[2023-11-28 08:17:53,359][87426] Updated weights for policy 1, policy_version 308560 (0.0009) -[2023-11-28 08:17:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 158040064. Throughput: 0: 2745.5, 1: 2677.3. Samples: 158059288. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:53,445][86177] Avg episode reward: [(0, '-590.650'), (1, '-517.080')] -[2023-11-28 08:17:53,730][87424] Updated weights for policy 0, policy_version 308809 (0.0011) -[2023-11-28 08:17:53,750][87426] Updated weights for policy 1, policy_version 308570 (0.0011) -[2023-11-28 08:17:54,107][87424] Updated weights for policy 0, policy_version 308819 (0.0008) -[2023-11-28 08:17:54,495][87424] Updated weights for policy 0, policy_version 308829 (0.0008) -[2023-11-28 08:17:56,334][87426] Updated weights for policy 1, policy_version 308580 (0.0009) -[2023-11-28 08:17:56,712][87426] Updated weights for policy 1, policy_version 308590 (0.0010) -[2023-11-28 08:17:56,959][87424] Updated weights for policy 0, policy_version 308839 (0.0010) -[2023-11-28 08:17:57,098][87426] Updated weights for policy 1, policy_version 308600 (0.0011) -[2023-11-28 08:17:57,345][87424] Updated weights for policy 0, policy_version 308849 (0.0008) -[2023-11-28 08:17:57,734][87424] Updated weights for policy 0, policy_version 308859 (0.0010) -[2023-11-28 08:17:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158072832. Throughput: 0: 2738.9, 1: 2643.4. Samples: 158082396. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:17:58,445][86177] Avg episode reward: [(0, '-566.670'), (1, '-510.160')] -[2023-11-28 08:17:59,586][87426] Updated weights for policy 1, policy_version 308610 (0.0008) -[2023-11-28 08:17:59,771][87424] Updated weights for policy 0, policy_version 308869 (0.0012) -[2023-11-28 08:17:59,970][87426] Updated weights for policy 1, policy_version 308620 (0.0010) -[2023-11-28 08:18:00,159][87424] Updated weights for policy 0, policy_version 308879 (0.0011) -[2023-11-28 08:18:00,350][87426] Updated weights for policy 1, policy_version 308630 (0.0009) -[2023-11-28 08:18:00,528][87424] Updated weights for policy 0, policy_version 308889 (0.0010) -[2023-11-28 08:18:00,716][87426] Updated weights for policy 1, policy_version 308640 (0.0010) -[2023-11-28 08:18:02,946][87424] Updated weights for policy 0, policy_version 308899 (0.0011) -[2023-11-28 08:18:03,004][87426] Updated weights for policy 1, policy_version 308650 (0.0009) -[2023-11-28 08:18:03,335][87424] Updated weights for policy 0, policy_version 308909 (0.0011) -[2023-11-28 08:18:03,386][87426] Updated weights for policy 1, policy_version 308660 (0.0011) -[2023-11-28 08:18:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 158089216. Throughput: 0: 2759.9, 1: 2643.2. Samples: 158107020. Policy #0 lag: (min: 31.0, avg: 39.3, max: 63.0) -[2023-11-28 08:18:03,445][86177] Avg episode reward: [(0, '-563.700'), (1, '-511.400')] -[2023-11-28 08:18:03,709][87424] Updated weights for policy 0, policy_version 308919 (0.0012) -[2023-11-28 08:18:03,766][87426] Updated weights for policy 1, policy_version 308670 (0.0010) -[2023-11-28 08:18:05,543][87424] Updated weights for policy 0, policy_version 308929 (0.0011) -[2023-11-28 08:18:05,927][87424] Updated weights for policy 0, policy_version 308939 (0.0012) -[2023-11-28 08:18:06,008][87426] Updated weights for policy 1, policy_version 308680 (0.0011) -[2023-11-28 08:18:06,307][87424] Updated weights for policy 0, policy_version 308949 (0.0010) -[2023-11-28 08:18:06,390][87426] Updated weights for policy 1, policy_version 308690 (0.0012) -[2023-11-28 08:18:06,688][87424] Updated weights for policy 0, policy_version 308959 (0.0008) -[2023-11-28 08:18:06,758][87426] Updated weights for policy 1, policy_version 308700 (0.0012) -[2023-11-28 08:18:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 158121984. Throughput: 0: 2752.0, 1: 2653.4. Samples: 158139172. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:08,445][86177] Avg episode reward: [(0, '-543.500'), (1, '-513.510')] -[2023-11-28 08:18:08,676][87426] Updated weights for policy 1, policy_version 308710 (0.0010) -[2023-11-28 08:18:08,834][87424] Updated weights for policy 0, policy_version 308969 (0.0011) -[2023-11-28 08:18:09,048][87426] Updated weights for policy 1, policy_version 308720 (0.0011) -[2023-11-28 08:18:09,220][87424] Updated weights for policy 0, policy_version 308979 (0.0011) -[2023-11-28 08:18:09,432][87426] Updated weights for policy 1, policy_version 308730 (0.0011) -[2023-11-28 08:18:09,600][87424] Updated weights for policy 0, policy_version 308989 (0.0007) -[2023-11-28 08:18:11,705][87424] Updated weights for policy 0, policy_version 308999 (0.0009) -[2023-11-28 08:18:11,968][87426] Updated weights for policy 1, policy_version 308740 (0.0011) -[2023-11-28 08:18:12,079][87424] Updated weights for policy 0, policy_version 309009 (0.0010) -[2023-11-28 08:18:12,341][87426] Updated weights for policy 1, policy_version 308750 (0.0010) -[2023-11-28 08:18:12,463][87424] Updated weights for policy 0, policy_version 309019 (0.0010) -[2023-11-28 08:18:12,722][87426] Updated weights for policy 1, policy_version 308760 (0.0009) -[2023-11-28 08:18:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158154752. Throughput: 0: 2754.1, 1: 2663.3. Samples: 158164000. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:13,445][86177] Avg episode reward: [(0, '-548.590'), (1, '-508.140')] -[2023-11-28 08:18:14,647][87424] Updated weights for policy 0, policy_version 309029 (0.0010) -[2023-11-28 08:18:15,033][87424] Updated weights for policy 0, policy_version 309039 (0.0010) -[2023-11-28 08:18:15,273][87426] Updated weights for policy 1, policy_version 308770 (0.0010) -[2023-11-28 08:18:15,425][87424] Updated weights for policy 0, policy_version 309049 (0.0012) -[2023-11-28 08:18:15,643][87426] Updated weights for policy 1, policy_version 308780 (0.0008) -[2023-11-28 08:18:16,020][87426] Updated weights for policy 1, policy_version 308790 (0.0009) -[2023-11-28 08:18:16,401][87426] Updated weights for policy 1, policy_version 308800 (0.0011) -[2023-11-28 08:18:17,459][87424] Updated weights for policy 0, policy_version 309059 (0.0012) -[2023-11-28 08:18:17,853][87424] Updated weights for policy 0, policy_version 309069 (0.0011) -[2023-11-28 08:18:18,233][87424] Updated weights for policy 0, policy_version 309079 (0.0010) -[2023-11-28 08:18:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 158171136. Throughput: 0: 2750.3, 1: 2649.4. Samples: 158189228. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:18,445][86177] Avg episode reward: [(0, '-558.280'), (1, '-506.210')] -[2023-11-28 08:18:18,537][87426] Updated weights for policy 1, policy_version 308810 (0.0011) -[2023-11-28 08:18:18,570][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000309088_79126528.pth... -[2023-11-28 08:18:18,601][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000306496_78462976.pth -[2023-11-28 08:18:18,931][87426] Updated weights for policy 1, policy_version 308820 (0.0012) -[2023-11-28 08:18:19,319][87426] Updated weights for policy 1, policy_version 308830 (0.0011) -[2023-11-28 08:18:19,394][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000308832_79060992.pth... -[2023-11-28 08:18:19,428][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000306272_78405632.pth -[2023-11-28 08:18:20,642][87424] Updated weights for policy 0, policy_version 309089 (0.0009) -[2023-11-28 08:18:21,022][87424] Updated weights for policy 0, policy_version 309099 (0.0009) -[2023-11-28 08:18:21,407][87424] Updated weights for policy 0, policy_version 309109 (0.0011) -[2023-11-28 08:18:21,672][87426] Updated weights for policy 1, policy_version 308840 (0.0012) -[2023-11-28 08:18:21,787][87424] Updated weights for policy 0, policy_version 309119 (0.0012) -[2023-11-28 08:18:22,054][87426] Updated weights for policy 1, policy_version 308850 (0.0012) -[2023-11-28 08:18:22,429][87426] Updated weights for policy 1, policy_version 308860 (0.0012) -[2023-11-28 08:18:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158203904. Throughput: 0: 2745.7, 1: 2618.4. Samples: 158220276. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:23,445][86177] Avg episode reward: [(0, '-569.100'), (1, '-527.170')] -[2023-11-28 08:18:23,864][87424] Updated weights for policy 0, policy_version 309129 (0.0012) -[2023-11-28 08:18:24,246][87424] Updated weights for policy 0, policy_version 309139 (0.0012) -[2023-11-28 08:18:24,584][87426] Updated weights for policy 1, policy_version 308870 (0.0012) -[2023-11-28 08:18:24,630][87424] Updated weights for policy 0, policy_version 309149 (0.0010) -[2023-11-28 08:18:24,964][87426] Updated weights for policy 1, policy_version 308880 (0.0012) -[2023-11-28 08:18:25,349][87426] Updated weights for policy 1, policy_version 308890 (0.0012) -[2023-11-28 08:18:26,727][87424] Updated weights for policy 0, policy_version 309159 (0.0008) -[2023-11-28 08:18:27,105][87424] Updated weights for policy 0, policy_version 309169 (0.0007) -[2023-11-28 08:18:27,455][87426] Updated weights for policy 1, policy_version 308900 (0.0012) -[2023-11-28 08:18:27,485][87424] Updated weights for policy 0, policy_version 309179 (0.0007) -[2023-11-28 08:18:27,839][87426] Updated weights for policy 1, policy_version 308910 (0.0012) -[2023-11-28 08:18:28,226][87426] Updated weights for policy 1, policy_version 308920 (0.0012) -[2023-11-28 08:18:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 158228480. Throughput: 0: 2742.6, 1: 2642.4. Samples: 158245524. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:28,445][86177] Avg episode reward: [(0, '-558.530'), (1, '-524.650')] -[2023-11-28 08:18:29,642][87424] Updated weights for policy 0, policy_version 309189 (0.0007) -[2023-11-28 08:18:29,870][87426] Updated weights for policy 1, policy_version 308930 (0.0011) -[2023-11-28 08:18:30,026][87424] Updated weights for policy 0, policy_version 309199 (0.0010) -[2023-11-28 08:18:30,241][87426] Updated weights for policy 1, policy_version 308940 (0.0009) -[2023-11-28 08:18:30,398][87424] Updated weights for policy 0, policy_version 309209 (0.0012) -[2023-11-28 08:18:30,621][87426] Updated weights for policy 1, policy_version 308950 (0.0008) -[2023-11-28 08:18:31,001][87426] Updated weights for policy 1, policy_version 308960 (0.0012) -[2023-11-28 08:18:32,247][87424] Updated weights for policy 0, policy_version 309219 (0.0011) -[2023-11-28 08:18:32,636][87424] Updated weights for policy 0, policy_version 309229 (0.0010) -[2023-11-28 08:18:33,014][87424] Updated weights for policy 0, policy_version 309239 (0.0010) -[2023-11-28 08:18:33,340][87426] Updated weights for policy 1, policy_version 308970 (0.0008) -[2023-11-28 08:18:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158261248. Throughput: 0: 2763.1, 1: 2640.7. Samples: 158270788. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:33,446][86177] Avg episode reward: [(0, '-564.860'), (1, '-536.760')] -[2023-11-28 08:18:33,731][87426] Updated weights for policy 1, policy_version 308980 (0.0008) -[2023-11-28 08:18:34,106][87426] Updated weights for policy 1, policy_version 308990 (0.0011) -[2023-11-28 08:18:35,367][87424] Updated weights for policy 0, policy_version 309249 (0.0011) -[2023-11-28 08:18:35,726][87426] Updated weights for policy 1, policy_version 309000 (0.0009) -[2023-11-28 08:18:35,757][87424] Updated weights for policy 0, policy_version 309259 (0.0009) -[2023-11-28 08:18:36,102][87426] Updated weights for policy 1, policy_version 309010 (0.0008) -[2023-11-28 08:18:36,136][87424] Updated weights for policy 0, policy_version 309269 (0.0008) -[2023-11-28 08:18:36,487][87426] Updated weights for policy 1, policy_version 309020 (0.0010) -[2023-11-28 08:18:36,508][87424] Updated weights for policy 0, policy_version 309279 (0.0009) -[2023-11-28 08:18:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158285824. Throughput: 0: 2749.1, 1: 2687.4. Samples: 158303932. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:38,445][86177] Avg episode reward: [(0, '-552.960'), (1, '-562.200')] -[2023-11-28 08:18:38,550][87426] Updated weights for policy 1, policy_version 309030 (0.0010) -[2023-11-28 08:18:38,927][87426] Updated weights for policy 1, policy_version 309040 (0.0011) -[2023-11-28 08:18:38,972][87424] Updated weights for policy 0, policy_version 309289 (0.0010) -[2023-11-28 08:18:39,306][87426] Updated weights for policy 1, policy_version 309050 (0.0011) -[2023-11-28 08:18:39,355][87424] Updated weights for policy 0, policy_version 309299 (0.0011) -[2023-11-28 08:18:39,739][87424] Updated weights for policy 0, policy_version 309309 (0.0011) -[2023-11-28 08:18:41,842][87426] Updated weights for policy 1, policy_version 309060 (0.0010) -[2023-11-28 08:18:42,205][87424] Updated weights for policy 0, policy_version 309319 (0.0011) -[2023-11-28 08:18:42,215][87426] Updated weights for policy 1, policy_version 309070 (0.0009) -[2023-11-28 08:18:42,593][87424] Updated weights for policy 0, policy_version 309329 (0.0011) -[2023-11-28 08:18:42,595][87426] Updated weights for policy 1, policy_version 309080 (0.0011) -[2023-11-28 08:18:42,969][87424] Updated weights for policy 0, policy_version 309339 (0.0011) -[2023-11-28 08:18:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 158318592. Throughput: 0: 2739.2, 1: 2714.5. Samples: 158327812. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:43,445][86177] Avg episode reward: [(0, '-545.080'), (1, '-544.200')] -[2023-11-28 08:18:44,979][87424] Updated weights for policy 0, policy_version 309349 (0.0012) -[2023-11-28 08:18:45,082][87426] Updated weights for policy 1, policy_version 309090 (0.0011) -[2023-11-28 08:18:45,364][87424] Updated weights for policy 0, policy_version 309359 (0.0011) -[2023-11-28 08:18:45,481][87426] Updated weights for policy 1, policy_version 309100 (0.0011) -[2023-11-28 08:18:45,746][87424] Updated weights for policy 0, policy_version 309369 (0.0010) -[2023-11-28 08:18:45,854][87426] Updated weights for policy 1, policy_version 309110 (0.0010) -[2023-11-28 08:18:46,230][87426] Updated weights for policy 1, policy_version 309120 (0.0011) -[2023-11-28 08:18:48,020][87426] Updated weights for policy 1, policy_version 309130 (0.0009) -[2023-11-28 08:18:48,151][87424] Updated weights for policy 0, policy_version 309379 (0.0007) -[2023-11-28 08:18:48,400][87426] Updated weights for policy 1, policy_version 309140 (0.0012) -[2023-11-28 08:18:48,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 158334976. Throughput: 0: 2708.8, 1: 2725.4. Samples: 158351560. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:48,446][86177] Avg episode reward: [(0, '-542.670'), (1, '-547.580')] -[2023-11-28 08:18:48,529][87424] Updated weights for policy 0, policy_version 309389 (0.0007) -[2023-11-28 08:18:48,778][87426] Updated weights for policy 1, policy_version 309150 (0.0008) -[2023-11-28 08:18:48,917][87424] Updated weights for policy 0, policy_version 309399 (0.0008) -[2023-11-28 08:18:50,763][87424] Updated weights for policy 0, policy_version 309409 (0.0008) -[2023-11-28 08:18:51,152][87424] Updated weights for policy 0, policy_version 309419 (0.0012) -[2023-11-28 08:18:51,382][87426] Updated weights for policy 1, policy_version 309160 (0.0010) -[2023-11-28 08:18:51,523][87424] Updated weights for policy 0, policy_version 309429 (0.0011) -[2023-11-28 08:18:51,759][87426] Updated weights for policy 1, policy_version 309170 (0.0010) -[2023-11-28 08:18:51,905][87424] Updated weights for policy 0, policy_version 309439 (0.0011) -[2023-11-28 08:18:52,129][87426] Updated weights for policy 1, policy_version 309180 (0.0012) -[2023-11-28 08:18:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158367744. Throughput: 0: 2726.5, 1: 2707.3. Samples: 158383692. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:53,445][86177] Avg episode reward: [(0, '-537.120'), (1, '-530.900')] -[2023-11-28 08:18:54,242][87424] Updated weights for policy 0, policy_version 309449 (0.0010) -[2023-11-28 08:18:54,431][87426] Updated weights for policy 1, policy_version 309190 (0.0012) -[2023-11-28 08:18:54,629][87424] Updated weights for policy 0, policy_version 309459 (0.0008) -[2023-11-28 08:18:54,807][87426] Updated weights for policy 1, policy_version 309200 (0.0012) -[2023-11-28 08:18:55,009][87424] Updated weights for policy 0, policy_version 309469 (0.0007) -[2023-11-28 08:18:55,195][87426] Updated weights for policy 1, policy_version 309210 (0.0012) -[2023-11-28 08:18:57,199][87424] Updated weights for policy 0, policy_version 309479 (0.0009) -[2023-11-28 08:18:57,360][87426] Updated weights for policy 1, policy_version 309220 (0.0010) -[2023-11-28 08:18:57,576][87424] Updated weights for policy 0, policy_version 309489 (0.0010) -[2023-11-28 08:18:57,736][87426] Updated weights for policy 1, policy_version 309230 (0.0008) -[2023-11-28 08:18:57,951][87424] Updated weights for policy 0, policy_version 309499 (0.0012) -[2023-11-28 08:18:58,113][87426] Updated weights for policy 1, policy_version 309240 (0.0007) -[2023-11-28 08:18:58,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 158400512. Throughput: 0: 2725.7, 1: 2693.7. Samples: 158407872. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:18:58,445][86177] Avg episode reward: [(0, '-540.390'), (1, '-532.640')] -[2023-11-28 08:18:59,863][87424] Updated weights for policy 0, policy_version 309509 (0.0008) -[2023-11-28 08:19:00,246][87424] Updated weights for policy 0, policy_version 309519 (0.0007) -[2023-11-28 08:19:00,475][87426] Updated weights for policy 1, policy_version 309250 (0.0008) -[2023-11-28 08:19:00,626][87424] Updated weights for policy 0, policy_version 309529 (0.0008) -[2023-11-28 08:19:00,849][87426] Updated weights for policy 1, policy_version 309260 (0.0009) -[2023-11-28 08:19:01,229][87426] Updated weights for policy 1, policy_version 309270 (0.0007) -[2023-11-28 08:19:01,604][87426] Updated weights for policy 1, policy_version 309280 (0.0008) -[2023-11-28 08:19:02,646][87424] Updated weights for policy 0, policy_version 309539 (0.0010) -[2023-11-28 08:19:03,030][87424] Updated weights for policy 0, policy_version 309549 (0.0011) -[2023-11-28 08:19:03,417][87424] Updated weights for policy 0, policy_version 309559 (0.0012) -[2023-11-28 08:19:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 158416896. Throughput: 0: 2726.8, 1: 2675.8. Samples: 158432344. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:19:03,445][86177] Avg episode reward: [(0, '-548.490'), (1, '-534.520')] -[2023-11-28 08:19:04,059][87426] Updated weights for policy 1, policy_version 309290 (0.0009) -[2023-11-28 08:19:04,450][87426] Updated weights for policy 1, policy_version 309300 (0.0007) -[2023-11-28 08:19:04,830][87426] Updated weights for policy 1, policy_version 309310 (0.0011) -[2023-11-28 08:19:05,588][87424] Updated weights for policy 0, policy_version 309569 (0.0012) -[2023-11-28 08:19:05,970][87424] Updated weights for policy 0, policy_version 309579 (0.0011) -[2023-11-28 08:19:06,361][87424] Updated weights for policy 0, policy_version 309589 (0.0009) -[2023-11-28 08:19:06,736][87424] Updated weights for policy 0, policy_version 309599 (0.0010) -[2023-11-28 08:19:07,198][87426] Updated weights for policy 1, policy_version 309320 (0.0011) -[2023-11-28 08:19:07,575][87426] Updated weights for policy 1, policy_version 309330 (0.0012) -[2023-11-28 08:19:07,958][87426] Updated weights for policy 1, policy_version 309340 (0.0012) -[2023-11-28 08:19:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 158449664. Throughput: 0: 2735.3, 1: 2689.2. Samples: 158464380. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:19:08,445][86177] Avg episode reward: [(0, '-553.770'), (1, '-532.080')] -[2023-11-28 08:19:09,032][87424] Updated weights for policy 0, policy_version 309609 (0.0011) -[2023-11-28 08:19:09,425][87424] Updated weights for policy 0, policy_version 309619 (0.0012) -[2023-11-28 08:19:09,811][87424] Updated weights for policy 0, policy_version 309629 (0.0012) -[2023-11-28 08:19:10,380][87426] Updated weights for policy 1, policy_version 309350 (0.0012) -[2023-11-28 08:19:10,758][87426] Updated weights for policy 1, policy_version 309360 (0.0012) -[2023-11-28 08:19:11,149][87426] Updated weights for policy 1, policy_version 309370 (0.0011) -[2023-11-28 08:19:11,724][87424] Updated weights for policy 0, policy_version 309639 (0.0010) -[2023-11-28 08:19:12,107][87424] Updated weights for policy 0, policy_version 309649 (0.0014) -[2023-11-28 08:19:12,484][87424] Updated weights for policy 0, policy_version 309659 (0.0012) -[2023-11-28 08:19:13,239][87426] Updated weights for policy 1, policy_version 309380 (0.0011) -[2023-11-28 08:19:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 158474240. Throughput: 0: 2740.7, 1: 2656.1. Samples: 158488380. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:19:13,445][86177] Avg episode reward: [(0, '-552.630'), (1, '-527.270')] -[2023-11-28 08:19:13,627][87426] Updated weights for policy 1, policy_version 309390 (0.0008) -[2023-11-28 08:19:14,010][87426] Updated weights for policy 1, policy_version 309400 (0.0007) -[2023-11-28 08:19:14,807][87424] Updated weights for policy 0, policy_version 309669 (0.0010) -[2023-11-28 08:19:15,194][87424] Updated weights for policy 0, policy_version 309679 (0.0008) -[2023-11-28 08:19:15,578][87424] Updated weights for policy 0, policy_version 309689 (0.0009) -[2023-11-28 08:19:16,577][87426] Updated weights for policy 1, policy_version 309410 (0.0008) -[2023-11-28 08:19:16,952][87426] Updated weights for policy 1, policy_version 309420 (0.0011) -[2023-11-28 08:19:17,324][87426] Updated weights for policy 1, policy_version 309430 (0.0011) -[2023-11-28 08:19:17,690][87424] Updated weights for policy 0, policy_version 309699 (0.0009) -[2023-11-28 08:19:17,699][87426] Updated weights for policy 1, policy_version 309440 (0.0012) -[2023-11-28 08:19:18,066][87424] Updated weights for policy 0, policy_version 309709 (0.0012) -[2023-11-28 08:19:18,440][87424] Updated weights for policy 0, policy_version 309719 (0.0012) -[2023-11-28 08:19:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158498816. Throughput: 0: 2714.6, 1: 2661.1. Samples: 158512692. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:19:18,445][86177] Avg episode reward: [(0, '-550.420'), (1, '-517.090')] -[2023-11-28 08:19:19,547][87426] Updated weights for policy 1, policy_version 309450 (0.0008) -[2023-11-28 08:19:19,926][87426] Updated weights for policy 1, policy_version 309460 (0.0009) -[2023-11-28 08:19:20,317][87426] Updated weights for policy 1, policy_version 309470 (0.0008) -[2023-11-28 08:19:20,821][87424] Updated weights for policy 0, policy_version 309729 (0.0012) -[2023-11-28 08:19:21,194][87424] Updated weights for policy 0, policy_version 309739 (0.0010) -[2023-11-28 08:19:21,572][87424] Updated weights for policy 0, policy_version 309749 (0.0011) -[2023-11-28 08:19:21,954][87424] Updated weights for policy 0, policy_version 309759 (0.0017) -[2023-11-28 08:19:22,518][87426] Updated weights for policy 1, policy_version 309480 (0.0011) -[2023-11-28 08:19:22,895][87426] Updated weights for policy 1, policy_version 309490 (0.0010) -[2023-11-28 08:19:23,277][87426] Updated weights for policy 1, policy_version 309500 (0.0009) -[2023-11-28 08:19:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 158531584. Throughput: 0: 2712.1, 1: 2644.5. Samples: 158544980. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:19:23,445][86177] Avg episode reward: [(0, '-542.190'), (1, '-520.810')] -[2023-11-28 08:19:24,166][87424] Updated weights for policy 0, policy_version 309769 (0.0008) -[2023-11-28 08:19:24,547][87424] Updated weights for policy 0, policy_version 309779 (0.0008) -[2023-11-28 08:19:24,928][87424] Updated weights for policy 0, policy_version 309789 (0.0008) -[2023-11-28 08:19:25,429][87426] Updated weights for policy 1, policy_version 309510 (0.0009) -[2023-11-28 08:19:25,818][87426] Updated weights for policy 1, policy_version 309520 (0.0007) -[2023-11-28 08:19:26,197][87426] Updated weights for policy 1, policy_version 309530 (0.0007) -[2023-11-28 08:19:27,009][87424] Updated weights for policy 0, policy_version 309799 (0.0011) -[2023-11-28 08:19:27,396][87424] Updated weights for policy 0, policy_version 309809 (0.0012) -[2023-11-28 08:19:27,784][87424] Updated weights for policy 0, policy_version 309819 (0.0012) -[2023-11-28 08:19:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158556160. Throughput: 0: 2715.6, 1: 2653.2. Samples: 158569408. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:19:28,445][86177] Avg episode reward: [(0, '-536.630'), (1, '-518.670')] -[2023-11-28 08:19:28,516][87426] Updated weights for policy 1, policy_version 309540 (0.0009) -[2023-11-28 08:19:28,899][87426] Updated weights for policy 1, policy_version 309550 (0.0011) -[2023-11-28 08:19:29,276][87426] Updated weights for policy 1, policy_version 309560 (0.0007) -[2023-11-28 08:19:30,364][87424] Updated weights for policy 0, policy_version 309829 (0.0011) -[2023-11-28 08:19:30,744][87424] Updated weights for policy 0, policy_version 309839 (0.0009) -[2023-11-28 08:19:30,989][87426] Updated weights for policy 1, policy_version 309570 (0.0008) -[2023-11-28 08:19:31,129][87424] Updated weights for policy 0, policy_version 309849 (0.0007) -[2023-11-28 08:19:31,373][87426] Updated weights for policy 1, policy_version 309580 (0.0009) -[2023-11-28 08:19:31,752][87426] Updated weights for policy 1, policy_version 309590 (0.0008) -[2023-11-28 08:19:32,128][87426] Updated weights for policy 1, policy_version 309600 (0.0009) -[2023-11-28 08:19:33,379][87424] Updated weights for policy 0, policy_version 309859 (0.0009) -[2023-11-28 08:19:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 158580736. Throughput: 0: 2713.2, 1: 2662.8. Samples: 158593480. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:19:33,445][86177] Avg episode reward: [(0, '-532.160'), (1, '-525.950')] -[2023-11-28 08:19:33,767][87424] Updated weights for policy 0, policy_version 309869 (0.0012) -[2023-11-28 08:19:34,143][87424] Updated weights for policy 0, policy_version 309879 (0.0012) -[2023-11-28 08:19:34,296][87426] Updated weights for policy 1, policy_version 309610 (0.0009) -[2023-11-28 08:19:34,679][87426] Updated weights for policy 1, policy_version 309620 (0.0008) -[2023-11-28 08:19:35,054][87426] Updated weights for policy 1, policy_version 309630 (0.0012) -[2023-11-28 08:19:36,404][87424] Updated weights for policy 0, policy_version 309889 (0.0012) -[2023-11-28 08:19:36,780][87424] Updated weights for policy 0, policy_version 309899 (0.0012) -[2023-11-28 08:19:37,171][87424] Updated weights for policy 0, policy_version 309909 (0.0012) -[2023-11-28 08:19:37,340][87426] Updated weights for policy 1, policy_version 309640 (0.0011) -[2023-11-28 08:19:37,558][87424] Updated weights for policy 0, policy_version 309919 (0.0012) -[2023-11-28 08:19:37,711][87426] Updated weights for policy 1, policy_version 309650 (0.0009) -[2023-11-28 08:19:38,098][87426] Updated weights for policy 1, policy_version 309660 (0.0010) -[2023-11-28 08:19:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 158613504. Throughput: 0: 2695.8, 1: 2695.9. Samples: 158626320. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:19:38,445][86177] Avg episode reward: [(0, '-536.920'), (1, '-530.750')] -[2023-11-28 08:19:39,642][87424] Updated weights for policy 0, policy_version 309929 (0.0011) -[2023-11-28 08:19:40,024][87424] Updated weights for policy 0, policy_version 309939 (0.0010) -[2023-11-28 08:19:40,416][87424] Updated weights for policy 0, policy_version 309949 (0.0009) -[2023-11-28 08:19:40,600][87426] Updated weights for policy 1, policy_version 309670 (0.0009) -[2023-11-28 08:19:40,980][87426] Updated weights for policy 1, policy_version 309680 (0.0011) -[2023-11-28 08:19:41,359][87426] Updated weights for policy 1, policy_version 309690 (0.0008) -[2023-11-28 08:19:43,055][87424] Updated weights for policy 0, policy_version 309959 (0.0011) -[2023-11-28 08:19:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 158629888. Throughput: 0: 2703.2, 1: 2681.1. Samples: 158650164. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:19:43,445][86177] Avg episode reward: [(0, '-559.780'), (1, '-521.460')] -[2023-11-28 08:19:43,446][87424] Updated weights for policy 0, policy_version 309969 (0.0011) -[2023-11-28 08:19:43,574][87426] Updated weights for policy 1, policy_version 309700 (0.0008) -[2023-11-28 08:19:43,839][87424] Updated weights for policy 0, policy_version 309979 (0.0011) -[2023-11-28 08:19:43,946][87426] Updated weights for policy 1, policy_version 309710 (0.0009) -[2023-11-28 08:19:44,320][87426] Updated weights for policy 1, policy_version 309720 (0.0011) -[2023-11-28 08:19:45,638][87424] Updated weights for policy 0, policy_version 309989 (0.0011) -[2023-11-28 08:19:46,020][87424] Updated weights for policy 0, policy_version 309999 (0.0011) -[2023-11-28 08:19:46,407][87424] Updated weights for policy 0, policy_version 310009 (0.0011) -[2023-11-28 08:19:46,656][87426] Updated weights for policy 1, policy_version 309730 (0.0008) -[2023-11-28 08:19:47,049][87426] Updated weights for policy 1, policy_version 309740 (0.0012) -[2023-11-28 08:19:47,427][87426] Updated weights for policy 1, policy_version 309750 (0.0012) -[2023-11-28 08:19:47,793][87426] Updated weights for policy 1, policy_version 309760 (0.0011) -[2023-11-28 08:19:48,129][87424] Updated weights for policy 0, policy_version 310019 (0.0012) -[2023-11-28 08:19:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158662656. Throughput: 0: 2668.6, 1: 2688.6. Samples: 158673420. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:19:48,445][86177] Avg episode reward: [(0, '-557.740'), (1, '-526.030')] -[2023-11-28 08:19:48,520][87424] Updated weights for policy 0, policy_version 310029 (0.0008) -[2023-11-28 08:19:48,901][87424] Updated weights for policy 0, policy_version 310039 (0.0008) -[2023-11-28 08:19:50,109][87426] Updated weights for policy 1, policy_version 309770 (0.0011) -[2023-11-28 08:19:50,488][87426] Updated weights for policy 1, policy_version 309780 (0.0012) -[2023-11-28 08:19:50,875][87426] Updated weights for policy 1, policy_version 309790 (0.0011) -[2023-11-28 08:19:51,149][87424] Updated weights for policy 0, policy_version 310049 (0.0010) -[2023-11-28 08:19:51,523][87424] Updated weights for policy 0, policy_version 310059 (0.0012) -[2023-11-28 08:19:51,916][87424] Updated weights for policy 0, policy_version 310069 (0.0012) -[2023-11-28 08:19:52,290][87424] Updated weights for policy 0, policy_version 310079 (0.0012) -[2023-11-28 08:19:53,256][87426] Updated weights for policy 1, policy_version 309800 (0.0011) -[2023-11-28 08:19:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 158687232. Throughput: 0: 2678.3, 1: 2685.1. Samples: 158705732. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:19:53,445][86177] Avg episode reward: [(0, '-563.130'), (1, '-521.490')] -[2023-11-28 08:19:53,632][87426] Updated weights for policy 1, policy_version 309810 (0.0011) -[2023-11-28 08:19:54,014][87426] Updated weights for policy 1, policy_version 309820 (0.0011) -[2023-11-28 08:19:54,451][87424] Updated weights for policy 0, policy_version 310089 (0.0012) -[2023-11-28 08:19:54,833][87424] Updated weights for policy 0, policy_version 310099 (0.0012) -[2023-11-28 08:19:55,216][87424] Updated weights for policy 0, policy_version 310109 (0.0012) -[2023-11-28 08:19:56,388][87426] Updated weights for policy 1, policy_version 309830 (0.0011) -[2023-11-28 08:19:56,766][87426] Updated weights for policy 1, policy_version 309840 (0.0011) -[2023-11-28 08:19:57,145][87426] Updated weights for policy 1, policy_version 309850 (0.0012) -[2023-11-28 08:19:57,502][87424] Updated weights for policy 0, policy_version 310119 (0.0008) -[2023-11-28 08:19:57,882][87424] Updated weights for policy 0, policy_version 310129 (0.0008) -[2023-11-28 08:19:58,261][87424] Updated weights for policy 0, policy_version 310139 (0.0008) -[2023-11-28 08:19:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 158711808. Throughput: 0: 2668.8, 1: 2704.3. Samples: 158730168. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:19:58,445][86177] Avg episode reward: [(0, '-557.630'), (1, '-531.890')] -[2023-11-28 08:19:59,371][87426] Updated weights for policy 1, policy_version 309860 (0.0010) -[2023-11-28 08:19:59,752][87426] Updated weights for policy 1, policy_version 309870 (0.0010) -[2023-11-28 08:20:00,133][87426] Updated weights for policy 1, policy_version 309880 (0.0011) -[2023-11-28 08:20:00,696][87424] Updated weights for policy 0, policy_version 310149 (0.0008) -[2023-11-28 08:20:01,076][87424] Updated weights for policy 0, policy_version 310159 (0.0008) -[2023-11-28 08:20:01,462][87424] Updated weights for policy 0, policy_version 310169 (0.0008) -[2023-11-28 08:20:02,020][87426] Updated weights for policy 1, policy_version 309890 (0.0011) -[2023-11-28 08:20:02,404][87426] Updated weights for policy 1, policy_version 309900 (0.0010) -[2023-11-28 08:20:02,777][87426] Updated weights for policy 1, policy_version 309910 (0.0012) -[2023-11-28 08:20:03,163][87426] Updated weights for policy 1, policy_version 309920 (0.0012) -[2023-11-28 08:20:03,297][87424] Updated weights for policy 0, policy_version 310179 (0.0009) -[2023-11-28 08:20:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158744576. Throughput: 0: 2679.8, 1: 2714.3. Samples: 158755428. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:20:03,445][86177] Avg episode reward: [(0, '-544.630'), (1, '-543.340')] -[2023-11-28 08:20:03,686][87424] Updated weights for policy 0, policy_version 310189 (0.0010) -[2023-11-28 08:20:04,079][87424] Updated weights for policy 0, policy_version 310199 (0.0008) -[2023-11-28 08:20:05,472][87426] Updated weights for policy 1, policy_version 309930 (0.0012) -[2023-11-28 08:20:05,838][87426] Updated weights for policy 1, policy_version 309940 (0.0010) -[2023-11-28 08:20:05,959][87424] Updated weights for policy 0, policy_version 310209 (0.0008) -[2023-11-28 08:20:06,225][87426] Updated weights for policy 1, policy_version 309950 (0.0007) -[2023-11-28 08:20:06,335][87424] Updated weights for policy 0, policy_version 310219 (0.0007) -[2023-11-28 08:20:06,714][87424] Updated weights for policy 0, policy_version 310229 (0.0008) -[2023-11-28 08:20:07,095][87424] Updated weights for policy 0, policy_version 310239 (0.0009) -[2023-11-28 08:20:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 158769152. Throughput: 0: 2713.4, 1: 2707.2. Samples: 158788908. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:20:08,445][86177] Avg episode reward: [(0, '-546.000'), (1, '-542.640')] -[2023-11-28 08:20:08,682][87426] Updated weights for policy 1, policy_version 309960 (0.0007) -[2023-11-28 08:20:09,068][87426] Updated weights for policy 1, policy_version 309970 (0.0008) -[2023-11-28 08:20:09,446][87426] Updated weights for policy 1, policy_version 309980 (0.0008) -[2023-11-28 08:20:09,514][87424] Updated weights for policy 0, policy_version 310249 (0.0009) -[2023-11-28 08:20:09,898][87424] Updated weights for policy 0, policy_version 310259 (0.0010) -[2023-11-28 08:20:10,292][87424] Updated weights for policy 0, policy_version 310269 (0.0009) -[2023-11-28 08:20:11,586][87426] Updated weights for policy 1, policy_version 309990 (0.0008) -[2023-11-28 08:20:11,963][87426] Updated weights for policy 1, policy_version 310000 (0.0012) -[2023-11-28 08:20:12,339][87426] Updated weights for policy 1, policy_version 310010 (0.0011) -[2023-11-28 08:20:12,508][87424] Updated weights for policy 0, policy_version 310279 (0.0011) -[2023-11-28 08:20:12,892][87424] Updated weights for policy 0, policy_version 310289 (0.0009) -[2023-11-28 08:20:13,279][87424] Updated weights for policy 0, policy_version 310299 (0.0008) -[2023-11-28 08:20:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 158793728. Throughput: 0: 2707.6, 1: 2686.3. Samples: 158812132. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:20:13,445][86177] Avg episode reward: [(0, '-543.120'), (1, '-546.140')] -[2023-11-28 08:20:14,334][87426] Updated weights for policy 1, policy_version 310020 (0.0011) -[2023-11-28 08:20:14,722][87426] Updated weights for policy 1, policy_version 310030 (0.0007) -[2023-11-28 08:20:15,113][87426] Updated weights for policy 1, policy_version 310040 (0.0009) -[2023-11-28 08:20:15,638][87424] Updated weights for policy 0, policy_version 310309 (0.0008) -[2023-11-28 08:20:16,015][87424] Updated weights for policy 0, policy_version 310319 (0.0008) -[2023-11-28 08:20:16,397][87424] Updated weights for policy 0, policy_version 310329 (0.0008) -[2023-11-28 08:20:17,342][87426] Updated weights for policy 1, policy_version 310050 (0.0008) -[2023-11-28 08:20:17,723][87426] Updated weights for policy 1, policy_version 310060 (0.0009) -[2023-11-28 08:20:18,108][87426] Updated weights for policy 1, policy_version 310070 (0.0011) -[2023-11-28 08:20:18,342][87424] Updated weights for policy 0, policy_version 310339 (0.0009) -[2023-11-28 08:20:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 158818304. Throughput: 0: 2722.6, 1: 2676.3. Samples: 158836428. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:20:18,445][86177] Avg episode reward: [(0, '-551.060'), (1, '-547.260')] -[2023-11-28 08:20:18,487][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000310080_79380480.pth... -[2023-11-28 08:20:18,488][87426] Updated weights for policy 1, policy_version 310080 (0.0008) -[2023-11-28 08:20:18,530][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000307552_78733312.pth -[2023-11-28 08:20:18,729][87424] Updated weights for policy 0, policy_version 310349 (0.0009) -[2023-11-28 08:20:19,101][87424] Updated weights for policy 0, policy_version 310359 (0.0008) -[2023-11-28 08:20:19,442][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000310368_79454208.pth... -[2023-11-28 08:20:19,473][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000307808_78798848.pth -[2023-11-28 08:20:21,010][87426] Updated weights for policy 1, policy_version 310090 (0.0009) -[2023-11-28 08:20:21,392][87426] Updated weights for policy 1, policy_version 310100 (0.0010) -[2023-11-28 08:20:21,395][87424] Updated weights for policy 0, policy_version 310369 (0.0008) -[2023-11-28 08:20:21,764][87426] Updated weights for policy 1, policy_version 310110 (0.0012) -[2023-11-28 08:20:21,775][87424] Updated weights for policy 0, policy_version 310379 (0.0011) -[2023-11-28 08:20:22,166][87424] Updated weights for policy 0, policy_version 310389 (0.0011) -[2023-11-28 08:20:22,549][87424] Updated weights for policy 0, policy_version 310399 (0.0012) -[2023-11-28 08:20:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 158851072. Throughput: 0: 2726.0, 1: 2643.3. Samples: 158867936. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:20:23,445][86177] Avg episode reward: [(0, '-539.230'), (1, '-535.000')] -[2023-11-28 08:20:24,185][87426] Updated weights for policy 1, policy_version 310120 (0.0012) -[2023-11-28 08:20:24,555][87426] Updated weights for policy 1, policy_version 310130 (0.0012) -[2023-11-28 08:20:24,686][87424] Updated weights for policy 0, policy_version 310409 (0.0009) -[2023-11-28 08:20:24,939][87426] Updated weights for policy 1, policy_version 310140 (0.0012) -[2023-11-28 08:20:25,073][87424] Updated weights for policy 0, policy_version 310419 (0.0008) -[2023-11-28 08:20:25,463][87424] Updated weights for policy 0, policy_version 310429 (0.0008) -[2023-11-28 08:20:26,816][87426] Updated weights for policy 1, policy_version 310150 (0.0011) -[2023-11-28 08:20:27,200][87426] Updated weights for policy 1, policy_version 310160 (0.0007) -[2023-11-28 08:20:27,585][87426] Updated weights for policy 1, policy_version 310170 (0.0007) -[2023-11-28 08:20:27,831][87424] Updated weights for policy 0, policy_version 310439 (0.0007) -[2023-11-28 08:20:28,223][87424] Updated weights for policy 0, policy_version 310449 (0.0007) -[2023-11-28 08:20:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 158875648. Throughput: 0: 2732.3, 1: 2662.7. Samples: 158892936. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:20:28,445][86177] Avg episode reward: [(0, '-540.820'), (1, '-532.410')] -[2023-11-28 08:20:28,619][87424] Updated weights for policy 0, policy_version 310459 (0.0009) -[2023-11-28 08:20:29,918][87426] Updated weights for policy 1, policy_version 310180 (0.0008) -[2023-11-28 08:20:30,303][87426] Updated weights for policy 1, policy_version 310190 (0.0008) -[2023-11-28 08:20:30,678][87426] Updated weights for policy 1, policy_version 310200 (0.0008) -[2023-11-28 08:20:30,956][87424] Updated weights for policy 0, policy_version 310469 (0.0009) -[2023-11-28 08:20:31,347][87424] Updated weights for policy 0, policy_version 310479 (0.0007) -[2023-11-28 08:20:31,728][87424] Updated weights for policy 0, policy_version 310489 (0.0008) -[2023-11-28 08:20:32,877][87426] Updated weights for policy 1, policy_version 310210 (0.0008) -[2023-11-28 08:20:33,259][87426] Updated weights for policy 1, policy_version 310220 (0.0012) -[2023-11-28 08:20:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 158900224. Throughput: 0: 2730.2, 1: 2672.1. Samples: 158916524. Policy #0 lag: (min: 53.0, avg: 61.5, max: 88.0) -[2023-11-28 08:20:33,445][86177] Avg episode reward: [(0, '-535.950'), (1, '-550.380')] -[2023-11-28 08:20:33,640][87426] Updated weights for policy 1, policy_version 310230 (0.0012) -[2023-11-28 08:20:33,801][87424] Updated weights for policy 0, policy_version 310499 (0.0010) -[2023-11-28 08:20:34,006][87426] Updated weights for policy 1, policy_version 310240 (0.0012) -[2023-11-28 08:20:34,189][87424] Updated weights for policy 0, policy_version 310509 (0.0012) -[2023-11-28 08:20:34,568][87424] Updated weights for policy 0, policy_version 310519 (0.0008) -[2023-11-28 08:20:36,371][87424] Updated weights for policy 0, policy_version 310529 (0.0010) -[2023-11-28 08:20:36,559][87426] Updated weights for policy 1, policy_version 310250 (0.0011) -[2023-11-28 08:20:36,756][87424] Updated weights for policy 0, policy_version 310539 (0.0009) -[2023-11-28 08:20:36,945][87426] Updated weights for policy 1, policy_version 310260 (0.0011) -[2023-11-28 08:20:37,128][87424] Updated weights for policy 0, policy_version 310549 (0.0012) -[2023-11-28 08:20:37,324][87426] Updated weights for policy 1, policy_version 310270 (0.0010) -[2023-11-28 08:20:37,505][87424] Updated weights for policy 0, policy_version 310559 (0.0011) -[2023-11-28 08:20:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 158932992. Throughput: 0: 2743.4, 1: 2670.6. Samples: 158949360. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:20:38,445][86177] Avg episode reward: [(0, '-530.390'), (1, '-550.690')] -[2023-11-28 08:20:39,418][87424] Updated weights for policy 0, policy_version 310569 (0.0012) -[2023-11-28 08:20:39,795][87424] Updated weights for policy 0, policy_version 310579 (0.0012) -[2023-11-28 08:20:39,806][87426] Updated weights for policy 1, policy_version 310280 (0.0011) -[2023-11-28 08:20:40,183][87424] Updated weights for policy 0, policy_version 310589 (0.0012) -[2023-11-28 08:20:40,194][87426] Updated weights for policy 1, policy_version 310290 (0.0010) -[2023-11-28 08:20:40,559][87426] Updated weights for policy 1, policy_version 310300 (0.0009) -[2023-11-28 08:20:41,910][87424] Updated weights for policy 0, policy_version 310599 (0.0012) -[2023-11-28 08:20:42,284][87424] Updated weights for policy 0, policy_version 310609 (0.0011) -[2023-11-28 08:20:42,666][87424] Updated weights for policy 0, policy_version 310619 (0.0011) -[2023-11-28 08:20:42,924][87426] Updated weights for policy 1, policy_version 310310 (0.0011) -[2023-11-28 08:20:43,299][87426] Updated weights for policy 1, policy_version 310320 (0.0011) -[2023-11-28 08:20:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 158957568. Throughput: 0: 2759.1, 1: 2658.0. Samples: 158973936. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:20:43,445][86177] Avg episode reward: [(0, '-531.190'), (1, '-563.860')] -[2023-11-28 08:20:43,672][87426] Updated weights for policy 1, policy_version 310330 (0.0008) -[2023-11-28 08:20:45,141][87424] Updated weights for policy 0, policy_version 310629 (0.0012) -[2023-11-28 08:20:45,454][87426] Updated weights for policy 1, policy_version 310340 (0.0009) -[2023-11-28 08:20:45,529][87424] Updated weights for policy 0, policy_version 310639 (0.0010) -[2023-11-28 08:20:45,832][87426] Updated weights for policy 1, policy_version 310350 (0.0011) -[2023-11-28 08:20:45,914][87424] Updated weights for policy 0, policy_version 310649 (0.0011) -[2023-11-28 08:20:46,206][87426] Updated weights for policy 1, policy_version 310360 (0.0011) -[2023-11-28 08:20:48,035][87426] Updated weights for policy 1, policy_version 310370 (0.0008) -[2023-11-28 08:20:48,096][87424] Updated weights for policy 0, policy_version 310659 (0.0010) -[2023-11-28 08:20:48,414][87426] Updated weights for policy 1, policy_version 310380 (0.0012) -[2023-11-28 08:20:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 158982144. Throughput: 0: 2752.7, 1: 2651.5. Samples: 158998620. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:20:48,446][86177] Avg episode reward: [(0, '-539.520'), (1, '-579.380')] -[2023-11-28 08:20:48,471][87424] Updated weights for policy 0, policy_version 310669 (0.0007) -[2023-11-28 08:20:48,791][87426] Updated weights for policy 1, policy_version 310390 (0.0012) -[2023-11-28 08:20:48,854][87424] Updated weights for policy 0, policy_version 310679 (0.0008) -[2023-11-28 08:20:49,169][87426] Updated weights for policy 1, policy_version 310400 (0.0010) -[2023-11-28 08:20:51,214][87424] Updated weights for policy 0, policy_version 310689 (0.0008) -[2023-11-28 08:20:51,366][87426] Updated weights for policy 1, policy_version 310410 (0.0010) -[2023-11-28 08:20:51,604][87424] Updated weights for policy 0, policy_version 310699 (0.0008) -[2023-11-28 08:20:51,746][87426] Updated weights for policy 1, policy_version 310420 (0.0010) -[2023-11-28 08:20:51,977][87424] Updated weights for policy 0, policy_version 310709 (0.0011) -[2023-11-28 08:20:52,124][87426] Updated weights for policy 1, policy_version 310430 (0.0008) -[2023-11-28 08:20:52,359][87424] Updated weights for policy 0, policy_version 310719 (0.0011) -[2023-11-28 08:20:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 159014912. Throughput: 0: 2710.8, 1: 2676.5. Samples: 159031336. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:20:53,445][86177] Avg episode reward: [(0, '-544.260'), (1, '-581.270')] -[2023-11-28 08:20:54,375][87426] Updated weights for policy 1, policy_version 310440 (0.0008) -[2023-11-28 08:20:54,752][87426] Updated weights for policy 1, policy_version 310450 (0.0007) -[2023-11-28 08:20:54,957][87424] Updated weights for policy 0, policy_version 310729 (0.0012) -[2023-11-28 08:20:55,136][87426] Updated weights for policy 1, policy_version 310460 (0.0010) -[2023-11-28 08:20:55,330][87424] Updated weights for policy 0, policy_version 310739 (0.0009) -[2023-11-28 08:20:55,715][87424] Updated weights for policy 0, policy_version 310749 (0.0008) -[2023-11-28 08:20:57,527][87426] Updated weights for policy 1, policy_version 310470 (0.0011) -[2023-11-28 08:20:57,607][87424] Updated weights for policy 0, policy_version 310759 (0.0008) -[2023-11-28 08:20:57,901][87426] Updated weights for policy 1, policy_version 310480 (0.0010) -[2023-11-28 08:20:57,988][87424] Updated weights for policy 0, policy_version 310769 (0.0007) -[2023-11-28 08:20:58,283][87426] Updated weights for policy 1, policy_version 310490 (0.0008) -[2023-11-28 08:20:58,366][87424] Updated weights for policy 0, policy_version 310779 (0.0007) -[2023-11-28 08:20:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159031296. Throughput: 0: 2726.3, 1: 2677.2. Samples: 159055292. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:20:58,445][86177] Avg episode reward: [(0, '-540.050'), (1, '-561.600')] -[2023-11-28 08:21:00,359][87426] Updated weights for policy 1, policy_version 310500 (0.0009) -[2023-11-28 08:21:00,511][87424] Updated weights for policy 0, policy_version 310789 (0.0009) -[2023-11-28 08:21:00,742][87426] Updated weights for policy 1, policy_version 310510 (0.0008) -[2023-11-28 08:21:00,890][87424] Updated weights for policy 0, policy_version 310799 (0.0008) -[2023-11-28 08:21:01,121][87426] Updated weights for policy 1, policy_version 310520 (0.0008) -[2023-11-28 08:21:01,270][87424] Updated weights for policy 0, policy_version 310809 (0.0009) -[2023-11-28 08:21:03,385][87424] Updated weights for policy 0, policy_version 310819 (0.0008) -[2023-11-28 08:21:03,430][87426] Updated weights for policy 1, policy_version 310530 (0.0008) -[2023-11-28 08:21:03,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 159064064. Throughput: 0: 2724.3, 1: 2677.3. Samples: 159079504. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:03,446][86177] Avg episode reward: [(0, '-552.190'), (1, '-596.770')] -[2023-11-28 08:21:03,763][87424] Updated weights for policy 0, policy_version 310829 (0.0007) -[2023-11-28 08:21:03,799][87426] Updated weights for policy 1, policy_version 310540 (0.0009) -[2023-11-28 08:21:04,144][87424] Updated weights for policy 0, policy_version 310839 (0.0010) -[2023-11-28 08:21:04,179][87426] Updated weights for policy 1, policy_version 310550 (0.0011) -[2023-11-28 08:21:04,557][87426] Updated weights for policy 1, policy_version 310560 (0.0010) -[2023-11-28 08:21:06,323][87424] Updated weights for policy 0, policy_version 310849 (0.0010) -[2023-11-28 08:21:06,707][87424] Updated weights for policy 0, policy_version 310859 (0.0008) -[2023-11-28 08:21:07,088][87424] Updated weights for policy 0, policy_version 310869 (0.0012) -[2023-11-28 08:21:07,111][87426] Updated weights for policy 1, policy_version 310570 (0.0010) -[2023-11-28 08:21:07,476][87424] Updated weights for policy 0, policy_version 310879 (0.0011) -[2023-11-28 08:21:07,484][87426] Updated weights for policy 1, policy_version 310580 (0.0012) -[2023-11-28 08:21:07,860][87426] Updated weights for policy 1, policy_version 310590 (0.0012) -[2023-11-28 08:21:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 159096832. Throughput: 0: 2716.1, 1: 2666.6. Samples: 159110156. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:08,445][86177] Avg episode reward: [(0, '-548.970'), (1, '-606.910')] -[2023-11-28 08:21:09,637][87424] Updated weights for policy 0, policy_version 310889 (0.0012) -[2023-11-28 08:21:09,798][87426] Updated weights for policy 1, policy_version 310600 (0.0011) -[2023-11-28 08:21:10,016][87424] Updated weights for policy 0, policy_version 310899 (0.0011) -[2023-11-28 08:21:10,179][87426] Updated weights for policy 1, policy_version 310610 (0.0012) -[2023-11-28 08:21:10,398][87424] Updated weights for policy 0, policy_version 310909 (0.0009) -[2023-11-28 08:21:10,562][87426] Updated weights for policy 1, policy_version 310620 (0.0012) -[2023-11-28 08:21:12,716][87426] Updated weights for policy 1, policy_version 310630 (0.0011) -[2023-11-28 08:21:12,847][87424] Updated weights for policy 0, policy_version 310919 (0.0011) -[2023-11-28 08:21:13,104][87426] Updated weights for policy 1, policy_version 310640 (0.0011) -[2023-11-28 08:21:13,225][87424] Updated weights for policy 0, policy_version 310929 (0.0011) -[2023-11-28 08:21:13,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159113216. Throughput: 0: 2691.1, 1: 2653.5. Samples: 159133444. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:13,445][86177] Avg episode reward: [(0, '-544.250'), (1, '-599.410')] -[2023-11-28 08:21:13,483][87426] Updated weights for policy 1, policy_version 310650 (0.0012) -[2023-11-28 08:21:13,608][87424] Updated weights for policy 0, policy_version 310939 (0.0009) -[2023-11-28 08:21:16,004][87424] Updated weights for policy 0, policy_version 310949 (0.0010) -[2023-11-28 08:21:16,014][87426] Updated weights for policy 1, policy_version 310660 (0.0011) -[2023-11-28 08:21:16,383][87424] Updated weights for policy 0, policy_version 310959 (0.0011) -[2023-11-28 08:21:16,402][87426] Updated weights for policy 1, policy_version 310670 (0.0007) -[2023-11-28 08:21:16,771][87426] Updated weights for policy 1, policy_version 310680 (0.0007) -[2023-11-28 08:21:16,773][87424] Updated weights for policy 0, policy_version 310969 (0.0011) -[2023-11-28 08:21:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 159145984. Throughput: 0: 2689.5, 1: 2657.2. Samples: 159157124. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:18,445][86177] Avg episode reward: [(0, '-549.470'), (1, '-613.450')] -[2023-11-28 08:21:18,512][87426] Updated weights for policy 1, policy_version 310690 (0.0008) -[2023-11-28 08:21:18,904][87426] Updated weights for policy 1, policy_version 310700 (0.0012) -[2023-11-28 08:21:19,013][87424] Updated weights for policy 0, policy_version 310979 (0.0009) -[2023-11-28 08:21:19,281][87426] Updated weights for policy 1, policy_version 310710 (0.0008) -[2023-11-28 08:21:19,404][87424] Updated weights for policy 0, policy_version 310989 (0.0012) -[2023-11-28 08:21:19,652][87426] Updated weights for policy 1, policy_version 310720 (0.0010) -[2023-11-28 08:21:19,794][87424] Updated weights for policy 0, policy_version 310999 (0.0010) -[2023-11-28 08:21:21,906][87424] Updated weights for policy 0, policy_version 311009 (0.0009) -[2023-11-28 08:21:22,158][87426] Updated weights for policy 1, policy_version 310730 (0.0010) -[2023-11-28 08:21:22,287][87424] Updated weights for policy 0, policy_version 311019 (0.0010) -[2023-11-28 08:21:22,534][87426] Updated weights for policy 1, policy_version 310740 (0.0009) -[2023-11-28 08:21:22,666][87424] Updated weights for policy 0, policy_version 311029 (0.0008) -[2023-11-28 08:21:22,923][87426] Updated weights for policy 1, policy_version 310750 (0.0010) -[2023-11-28 08:21:23,050][87424] Updated weights for policy 0, policy_version 311039 (0.0009) -[2023-11-28 08:21:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 159178752. Throughput: 0: 2660.5, 1: 2657.2. Samples: 159188660. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:23,445][86177] Avg episode reward: [(0, '-548.130'), (1, '-612.550')] -[2023-11-28 08:21:25,351][87426] Updated weights for policy 1, policy_version 310760 (0.0011) -[2023-11-28 08:21:25,533][87424] Updated weights for policy 0, policy_version 311049 (0.0011) -[2023-11-28 08:21:25,737][87426] Updated weights for policy 1, policy_version 310770 (0.0011) -[2023-11-28 08:21:25,925][87424] Updated weights for policy 0, policy_version 311059 (0.0011) -[2023-11-28 08:21:26,115][87426] Updated weights for policy 1, policy_version 310780 (0.0011) -[2023-11-28 08:21:26,305][87424] Updated weights for policy 0, policy_version 311069 (0.0011) -[2023-11-28 08:21:27,738][87426] Updated weights for policy 1, policy_version 310790 (0.0011) -[2023-11-28 08:21:28,114][87426] Updated weights for policy 1, policy_version 310800 (0.0011) -[2023-11-28 08:21:28,386][87424] Updated weights for policy 0, policy_version 311079 (0.0009) -[2023-11-28 08:21:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159195136. Throughput: 0: 2639.1, 1: 2703.4. Samples: 159214348. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:28,445][86177] Avg episode reward: [(0, '-531.040'), (1, '-600.190')] -[2023-11-28 08:21:28,505][87426] Updated weights for policy 1, policy_version 310810 (0.0008) -[2023-11-28 08:21:28,768][87424] Updated weights for policy 0, policy_version 311089 (0.0007) -[2023-11-28 08:21:29,158][87424] Updated weights for policy 0, policy_version 311099 (0.0010) -[2023-11-28 08:21:30,845][87426] Updated weights for policy 1, policy_version 310820 (0.0009) -[2023-11-28 08:21:31,219][87426] Updated weights for policy 1, policy_version 310830 (0.0012) -[2023-11-28 08:21:31,366][87424] Updated weights for policy 0, policy_version 311109 (0.0009) -[2023-11-28 08:21:31,597][87426] Updated weights for policy 1, policy_version 310840 (0.0011) -[2023-11-28 08:21:31,749][87424] Updated weights for policy 0, policy_version 311119 (0.0009) -[2023-11-28 08:21:32,135][87424] Updated weights for policy 0, policy_version 311129 (0.0008) -[2023-11-28 08:21:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 159227904. Throughput: 0: 2643.2, 1: 2698.8. Samples: 159239008. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:33,445][86177] Avg episode reward: [(0, '-533.190'), (1, '-586.410')] -[2023-11-28 08:21:33,592][87426] Updated weights for policy 1, policy_version 310850 (0.0010) -[2023-11-28 08:21:33,966][87426] Updated weights for policy 1, policy_version 310860 (0.0008) -[2023-11-28 08:21:34,001][87424] Updated weights for policy 0, policy_version 311139 (0.0008) -[2023-11-28 08:21:34,339][87426] Updated weights for policy 1, policy_version 310870 (0.0008) -[2023-11-28 08:21:34,376][87424] Updated weights for policy 0, policy_version 311149 (0.0007) -[2023-11-28 08:21:34,705][87426] Updated weights for policy 1, policy_version 310880 (0.0008) -[2023-11-28 08:21:34,758][87424] Updated weights for policy 0, policy_version 311159 (0.0008) -[2023-11-28 08:21:36,684][87424] Updated weights for policy 0, policy_version 311169 (0.0009) -[2023-11-28 08:21:37,064][87424] Updated weights for policy 0, policy_version 311179 (0.0011) -[2023-11-28 08:21:37,142][87426] Updated weights for policy 1, policy_version 310890 (0.0011) -[2023-11-28 08:21:37,444][87424] Updated weights for policy 0, policy_version 311189 (0.0012) -[2023-11-28 08:21:37,522][87426] Updated weights for policy 1, policy_version 310900 (0.0007) -[2023-11-28 08:21:37,823][87424] Updated weights for policy 0, policy_version 311199 (0.0008) -[2023-11-28 08:21:37,907][87426] Updated weights for policy 1, policy_version 310910 (0.0007) -[2023-11-28 08:21:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 159260672. Throughput: 0: 2672.4, 1: 2655.0. Samples: 159271072. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:38,445][86177] Avg episode reward: [(0, '-531.450'), (1, '-627.260')] -[2023-11-28 08:21:40,281][87426] Updated weights for policy 1, policy_version 310920 (0.0009) -[2023-11-28 08:21:40,385][87424] Updated weights for policy 0, policy_version 311209 (0.0009) -[2023-11-28 08:21:40,667][87426] Updated weights for policy 1, policy_version 310930 (0.0011) -[2023-11-28 08:21:40,765][87424] Updated weights for policy 0, policy_version 311219 (0.0010) -[2023-11-28 08:21:41,034][87426] Updated weights for policy 1, policy_version 310940 (0.0008) -[2023-11-28 08:21:41,148][87424] Updated weights for policy 0, policy_version 311229 (0.0011) -[2023-11-28 08:21:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159277056. Throughput: 0: 2672.3, 1: 2649.6. Samples: 159294776. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:43,445][86177] Avg episode reward: [(0, '-541.320'), (1, '-659.380')] -[2023-11-28 08:21:43,520][87426] Updated weights for policy 1, policy_version 310950 (0.0010) -[2023-11-28 08:21:43,597][87424] Updated weights for policy 0, policy_version 311239 (0.0011) -[2023-11-28 08:21:43,889][87426] Updated weights for policy 1, policy_version 310960 (0.0010) -[2023-11-28 08:21:43,973][87424] Updated weights for policy 0, policy_version 311249 (0.0011) -[2023-11-28 08:21:44,273][87426] Updated weights for policy 1, policy_version 310970 (0.0011) -[2023-11-28 08:21:44,349][87424] Updated weights for policy 0, policy_version 311259 (0.0012) -[2023-11-28 08:21:46,338][87426] Updated weights for policy 1, policy_version 310980 (0.0009) -[2023-11-28 08:21:46,486][87424] Updated weights for policy 0, policy_version 311269 (0.0012) -[2023-11-28 08:21:46,717][87426] Updated weights for policy 1, policy_version 310990 (0.0010) -[2023-11-28 08:21:46,871][87424] Updated weights for policy 0, policy_version 311279 (0.0009) -[2023-11-28 08:21:47,091][87426] Updated weights for policy 1, policy_version 311000 (0.0009) -[2023-11-28 08:21:47,247][87424] Updated weights for policy 0, policy_version 311289 (0.0008) -[2023-11-28 08:21:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 159309824. Throughput: 0: 2680.8, 1: 2658.2. Samples: 159319756. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:48,445][86177] Avg episode reward: [(0, '-542.590'), (1, '-685.300')] -[2023-11-28 08:21:49,096][87426] Updated weights for policy 1, policy_version 311010 (0.0007) -[2023-11-28 08:21:49,457][87424] Updated weights for policy 0, policy_version 311299 (0.0009) -[2023-11-28 08:21:49,477][87426] Updated weights for policy 1, policy_version 311020 (0.0009) -[2023-11-28 08:21:49,838][87424] Updated weights for policy 0, policy_version 311309 (0.0009) -[2023-11-28 08:21:49,861][87426] Updated weights for policy 1, policy_version 311030 (0.0011) -[2023-11-28 08:21:50,217][87424] Updated weights for policy 0, policy_version 311319 (0.0012) -[2023-11-28 08:21:50,235][87426] Updated weights for policy 1, policy_version 311040 (0.0012) -[2023-11-28 08:21:52,118][87426] Updated weights for policy 1, policy_version 311050 (0.0009) -[2023-11-28 08:21:52,496][87426] Updated weights for policy 1, policy_version 311060 (0.0011) -[2023-11-28 08:21:52,583][87424] Updated weights for policy 0, policy_version 311329 (0.0010) -[2023-11-28 08:21:52,875][87426] Updated weights for policy 1, policy_version 311070 (0.0011) -[2023-11-28 08:21:52,959][87424] Updated weights for policy 0, policy_version 311339 (0.0010) -[2023-11-28 08:21:53,341][87424] Updated weights for policy 0, policy_version 311349 (0.0011) -[2023-11-28 08:21:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159334400. Throughput: 0: 2675.7, 1: 2706.4. Samples: 159352352. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 08:21:53,445][86177] Avg episode reward: [(0, '-543.820'), (1, '-682.930')] -[2023-11-28 08:21:53,727][87424] Updated weights for policy 0, policy_version 311359 (0.0010) -[2023-11-28 08:21:55,431][87426] Updated weights for policy 1, policy_version 311080 (0.0008) -[2023-11-28 08:21:55,488][87424] Updated weights for policy 0, policy_version 311369 (0.0012) -[2023-11-28 08:21:55,807][87426] Updated weights for policy 1, policy_version 311090 (0.0008) -[2023-11-28 08:21:55,865][87424] Updated weights for policy 0, policy_version 311379 (0.0010) -[2023-11-28 08:21:56,187][87426] Updated weights for policy 1, policy_version 311100 (0.0008) -[2023-11-28 08:21:56,248][87424] Updated weights for policy 0, policy_version 311389 (0.0008) -[2023-11-28 08:21:58,122][87424] Updated weights for policy 0, policy_version 311399 (0.0010) -[2023-11-28 08:21:58,173][87426] Updated weights for policy 1, policy_version 311110 (0.0009) -[2023-11-28 08:21:58,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 159358976. Throughput: 0: 2704.8, 1: 2725.4. Samples: 159377804. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:21:58,446][86177] Avg episode reward: [(0, '-542.980'), (1, '-688.900')] -[2023-11-28 08:21:58,513][87424] Updated weights for policy 0, policy_version 311409 (0.0010) -[2023-11-28 08:21:58,564][87426] Updated weights for policy 1, policy_version 311120 (0.0007) -[2023-11-28 08:21:58,901][87424] Updated weights for policy 0, policy_version 311419 (0.0010) -[2023-11-28 08:21:58,948][87426] Updated weights for policy 1, policy_version 311130 (0.0008) -[2023-11-28 08:22:01,282][87426] Updated weights for policy 1, policy_version 311140 (0.0010) -[2023-11-28 08:22:01,326][87424] Updated weights for policy 0, policy_version 311429 (0.0010) -[2023-11-28 08:22:01,669][87426] Updated weights for policy 1, policy_version 311150 (0.0011) -[2023-11-28 08:22:01,702][87424] Updated weights for policy 0, policy_version 311439 (0.0009) -[2023-11-28 08:22:02,046][87426] Updated weights for policy 1, policy_version 311160 (0.0010) -[2023-11-28 08:22:02,089][87424] Updated weights for policy 0, policy_version 311449 (0.0011) -[2023-11-28 08:22:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 159391744. Throughput: 0: 2724.1, 1: 2736.8. Samples: 159402864. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:03,445][86177] Avg episode reward: [(0, '-551.470'), (1, '-644.660')] -[2023-11-28 08:22:03,936][87426] Updated weights for policy 1, policy_version 311170 (0.0010) -[2023-11-28 08:22:04,321][87426] Updated weights for policy 1, policy_version 311180 (0.0010) -[2023-11-28 08:22:04,417][87424] Updated weights for policy 0, policy_version 311459 (0.0011) -[2023-11-28 08:22:04,696][87426] Updated weights for policy 1, policy_version 311190 (0.0010) -[2023-11-28 08:22:04,793][87424] Updated weights for policy 0, policy_version 311469 (0.0010) -[2023-11-28 08:22:05,073][87426] Updated weights for policy 1, policy_version 311200 (0.0009) -[2023-11-28 08:22:05,166][87424] Updated weights for policy 0, policy_version 311479 (0.0012) -[2023-11-28 08:22:06,946][87424] Updated weights for policy 0, policy_version 311489 (0.0012) -[2023-11-28 08:22:07,328][87424] Updated weights for policy 0, policy_version 311499 (0.0012) -[2023-11-28 08:22:07,640][87426] Updated weights for policy 1, policy_version 311210 (0.0011) -[2023-11-28 08:22:07,718][87424] Updated weights for policy 0, policy_version 311509 (0.0012) -[2023-11-28 08:22:08,023][87426] Updated weights for policy 1, policy_version 311220 (0.0011) -[2023-11-28 08:22:08,087][87424] Updated weights for policy 0, policy_version 311519 (0.0011) -[2023-11-28 08:22:08,404][87426] Updated weights for policy 1, policy_version 311230 (0.0012) -[2023-11-28 08:22:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159416320. Throughput: 0: 2732.0, 1: 2756.8. Samples: 159435656. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:08,445][86177] Avg episode reward: [(0, '-546.050'), (1, '-656.300')] -[2023-11-28 08:22:10,247][87426] Updated weights for policy 1, policy_version 311240 (0.0009) -[2023-11-28 08:22:10,495][87424] Updated weights for policy 0, policy_version 311529 (0.0011) -[2023-11-28 08:22:10,625][87426] Updated weights for policy 1, policy_version 311250 (0.0010) -[2023-11-28 08:22:10,886][87424] Updated weights for policy 0, policy_version 311539 (0.0010) -[2023-11-28 08:22:11,007][87426] Updated weights for policy 1, policy_version 311260 (0.0010) -[2023-11-28 08:22:11,268][87424] Updated weights for policy 0, policy_version 311549 (0.0012) -[2023-11-28 08:22:13,039][87426] Updated weights for policy 1, policy_version 311270 (0.0011) -[2023-11-28 08:22:13,413][87426] Updated weights for policy 1, policy_version 311280 (0.0011) -[2023-11-28 08:22:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 159440896. Throughput: 0: 2736.7, 1: 2720.9. Samples: 159459940. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:13,445][86177] Avg episode reward: [(0, '-545.770'), (1, '-646.880')] -[2023-11-28 08:22:13,522][87424] Updated weights for policy 0, policy_version 311559 (0.0012) -[2023-11-28 08:22:13,786][87426] Updated weights for policy 1, policy_version 311290 (0.0011) -[2023-11-28 08:22:13,907][87424] Updated weights for policy 0, policy_version 311569 (0.0012) -[2023-11-28 08:22:14,284][87424] Updated weights for policy 0, policy_version 311579 (0.0012) -[2023-11-28 08:22:16,153][87426] Updated weights for policy 1, policy_version 311300 (0.0011) -[2023-11-28 08:22:16,529][87426] Updated weights for policy 1, policy_version 311310 (0.0012) -[2023-11-28 08:22:16,644][87424] Updated weights for policy 0, policy_version 311589 (0.0010) -[2023-11-28 08:22:16,909][87426] Updated weights for policy 1, policy_version 311320 (0.0012) -[2023-11-28 08:22:17,029][87424] Updated weights for policy 0, policy_version 311599 (0.0008) -[2023-11-28 08:22:17,415][87424] Updated weights for policy 0, policy_version 311609 (0.0008) -[2023-11-28 08:22:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 159473664. Throughput: 0: 2726.0, 1: 2727.1. Samples: 159484400. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:18,445][86177] Avg episode reward: [(0, '-545.840'), (1, '-659.600')] -[2023-11-28 08:22:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000311616_79773696.pth... -[2023-11-28 08:22:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000311328_79699968.pth... -[2023-11-28 08:22:18,510][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000308832_79060992.pth -[2023-11-28 08:22:18,511][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000309088_79126528.pth -[2023-11-28 08:22:18,865][87426] Updated weights for policy 1, policy_version 311330 (0.0008) -[2023-11-28 08:22:19,241][87426] Updated weights for policy 1, policy_version 311340 (0.0008) -[2023-11-28 08:22:19,282][87424] Updated weights for policy 0, policy_version 311619 (0.0008) -[2023-11-28 08:22:19,626][87426] Updated weights for policy 1, policy_version 311350 (0.0010) -[2023-11-28 08:22:19,664][87424] Updated weights for policy 0, policy_version 311629 (0.0010) -[2023-11-28 08:22:19,992][87426] Updated weights for policy 1, policy_version 311360 (0.0009) -[2023-11-28 08:22:20,040][87424] Updated weights for policy 0, policy_version 311639 (0.0011) -[2023-11-28 08:22:21,846][87426] Updated weights for policy 1, policy_version 311370 (0.0011) -[2023-11-28 08:22:22,228][87426] Updated weights for policy 1, policy_version 311380 (0.0012) -[2023-11-28 08:22:22,398][87424] Updated weights for policy 0, policy_version 311649 (0.0011) -[2023-11-28 08:22:22,610][87426] Updated weights for policy 1, policy_version 311390 (0.0010) -[2023-11-28 08:22:22,783][87424] Updated weights for policy 0, policy_version 311659 (0.0011) -[2023-11-28 08:22:23,170][87424] Updated weights for policy 0, policy_version 311669 (0.0012) -[2023-11-28 08:22:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159498240. Throughput: 0: 2707.9, 1: 2745.8. Samples: 159516488. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:23,445][86177] Avg episode reward: [(0, '-532.980'), (1, '-667.320')] -[2023-11-28 08:22:23,552][87424] Updated weights for policy 0, policy_version 311679 (0.0012) -[2023-11-28 08:22:24,933][87426] Updated weights for policy 1, policy_version 311400 (0.0011) -[2023-11-28 08:22:25,307][87426] Updated weights for policy 1, policy_version 311410 (0.0012) -[2023-11-28 08:22:25,686][87426] Updated weights for policy 1, policy_version 311420 (0.0012) -[2023-11-28 08:22:25,871][87424] Updated weights for policy 0, policy_version 311689 (0.0011) -[2023-11-28 08:22:26,256][87424] Updated weights for policy 0, policy_version 311699 (0.0012) -[2023-11-28 08:22:26,642][87424] Updated weights for policy 0, policy_version 311709 (0.0012) -[2023-11-28 08:22:27,732][87426] Updated weights for policy 1, policy_version 311430 (0.0012) -[2023-11-28 08:22:28,109][87426] Updated weights for policy 1, policy_version 311440 (0.0012) -[2023-11-28 08:22:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 159522816. Throughput: 0: 2717.2, 1: 2791.1. Samples: 159542652. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:28,445][86177] Avg episode reward: [(0, '-541.850'), (1, '-645.870')] -[2023-11-28 08:22:28,495][87426] Updated weights for policy 1, policy_version 311450 (0.0012) -[2023-11-28 08:22:28,921][87424] Updated weights for policy 0, policy_version 311719 (0.0011) -[2023-11-28 08:22:29,301][87424] Updated weights for policy 0, policy_version 311729 (0.0007) -[2023-11-28 08:22:29,686][87424] Updated weights for policy 0, policy_version 311739 (0.0009) -[2023-11-28 08:22:30,711][87426] Updated weights for policy 1, policy_version 311460 (0.0010) -[2023-11-28 08:22:31,088][87426] Updated weights for policy 1, policy_version 311470 (0.0008) -[2023-11-28 08:22:31,468][87426] Updated weights for policy 1, policy_version 311480 (0.0010) -[2023-11-28 08:22:31,557][87424] Updated weights for policy 0, policy_version 311749 (0.0011) -[2023-11-28 08:22:31,930][87424] Updated weights for policy 0, policy_version 311759 (0.0012) -[2023-11-28 08:22:32,310][87424] Updated weights for policy 0, policy_version 311769 (0.0012) -[2023-11-28 08:22:33,342][87426] Updated weights for policy 1, policy_version 311490 (0.0009) -[2023-11-28 08:22:33,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 159555584. Throughput: 0: 2716.8, 1: 2786.5. Samples: 159567404. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:33,446][86177] Avg episode reward: [(0, '-540.020'), (1, '-651.320')] -[2023-11-28 08:22:33,721][87426] Updated weights for policy 1, policy_version 311500 (0.0011) -[2023-11-28 08:22:34,106][87426] Updated weights for policy 1, policy_version 311510 (0.0012) -[2023-11-28 08:22:34,129][87424] Updated weights for policy 0, policy_version 311779 (0.0012) -[2023-11-28 08:22:34,487][87426] Updated weights for policy 1, policy_version 311520 (0.0011) -[2023-11-28 08:22:34,513][87424] Updated weights for policy 0, policy_version 311789 (0.0008) -[2023-11-28 08:22:34,889][87424] Updated weights for policy 0, policy_version 311799 (0.0010) -[2023-11-28 08:22:36,958][87424] Updated weights for policy 0, policy_version 311809 (0.0012) -[2023-11-28 08:22:36,996][87426] Updated weights for policy 1, policy_version 311530 (0.0008) -[2023-11-28 08:22:37,334][87424] Updated weights for policy 0, policy_version 311819 (0.0008) -[2023-11-28 08:22:37,387][87426] Updated weights for policy 1, policy_version 311540 (0.0007) -[2023-11-28 08:22:37,715][87424] Updated weights for policy 0, policy_version 311829 (0.0008) -[2023-11-28 08:22:37,759][87426] Updated weights for policy 1, policy_version 311550 (0.0007) -[2023-11-28 08:22:38,100][87424] Updated weights for policy 0, policy_version 311839 (0.0008) -[2023-11-28 08:22:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 159588352. Throughput: 0: 2748.5, 1: 2760.4. Samples: 159600256. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:38,446][86177] Avg episode reward: [(0, '-537.890'), (1, '-617.000')] -[2023-11-28 08:22:39,876][87426] Updated weights for policy 1, policy_version 311560 (0.0009) -[2023-11-28 08:22:40,252][87426] Updated weights for policy 1, policy_version 311570 (0.0010) -[2023-11-28 08:22:40,295][87424] Updated weights for policy 0, policy_version 311849 (0.0011) -[2023-11-28 08:22:40,627][87426] Updated weights for policy 1, policy_version 311580 (0.0010) -[2023-11-28 08:22:40,681][87424] Updated weights for policy 0, policy_version 311859 (0.0013) -[2023-11-28 08:22:41,055][87424] Updated weights for policy 0, policy_version 311869 (0.0012) -[2023-11-28 08:22:43,237][87426] Updated weights for policy 1, policy_version 311590 (0.0008) -[2023-11-28 08:22:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 159604736. Throughput: 0: 2725.9, 1: 2745.7. Samples: 159624024. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:43,445][86177] Avg episode reward: [(0, '-556.480'), (1, '-597.980')] -[2023-11-28 08:22:43,606][87424] Updated weights for policy 0, policy_version 311879 (0.0012) -[2023-11-28 08:22:43,616][87426] Updated weights for policy 1, policy_version 311600 (0.0007) -[2023-11-28 08:22:43,994][87424] Updated weights for policy 0, policy_version 311889 (0.0010) -[2023-11-28 08:22:44,004][87426] Updated weights for policy 1, policy_version 311610 (0.0010) -[2023-11-28 08:22:44,378][87424] Updated weights for policy 0, policy_version 311899 (0.0007) -[2023-11-28 08:22:45,850][87426] Updated weights for policy 1, policy_version 311620 (0.0012) -[2023-11-28 08:22:46,230][87426] Updated weights for policy 1, policy_version 311630 (0.0012) -[2023-11-28 08:22:46,610][87426] Updated weights for policy 1, policy_version 311640 (0.0011) -[2023-11-28 08:22:46,723][87424] Updated weights for policy 0, policy_version 311909 (0.0008) -[2023-11-28 08:22:47,119][87424] Updated weights for policy 0, policy_version 311919 (0.0010) -[2023-11-28 08:22:47,488][87424] Updated weights for policy 0, policy_version 311929 (0.0009) -[2023-11-28 08:22:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 159637504. Throughput: 0: 2708.3, 1: 2733.2. Samples: 159647736. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:48,445][86177] Avg episode reward: [(0, '-554.360'), (1, '-545.300')] -[2023-11-28 08:22:48,778][87426] Updated weights for policy 1, policy_version 311650 (0.0008) -[2023-11-28 08:22:49,148][87426] Updated weights for policy 1, policy_version 311660 (0.0012) -[2023-11-28 08:22:49,524][87426] Updated weights for policy 1, policy_version 311670 (0.0012) -[2023-11-28 08:22:49,899][87426] Updated weights for policy 1, policy_version 311680 (0.0011) -[2023-11-28 08:22:49,967][87424] Updated weights for policy 0, policy_version 311939 (0.0009) -[2023-11-28 08:22:50,351][87424] Updated weights for policy 0, policy_version 311949 (0.0012) -[2023-11-28 08:22:50,725][87424] Updated weights for policy 0, policy_version 311959 (0.0009) -[2023-11-28 08:22:51,733][87426] Updated weights for policy 1, policy_version 311690 (0.0012) -[2023-11-28 08:22:52,108][87426] Updated weights for policy 1, policy_version 311700 (0.0009) -[2023-11-28 08:22:52,488][87426] Updated weights for policy 1, policy_version 311710 (0.0010) -[2023-11-28 08:22:52,708][87424] Updated weights for policy 0, policy_version 311969 (0.0008) -[2023-11-28 08:22:53,081][87424] Updated weights for policy 0, policy_version 311979 (0.0012) -[2023-11-28 08:22:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 159662080. Throughput: 0: 2711.6, 1: 2732.2. Samples: 159680624. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:53,445][86177] Avg episode reward: [(0, '-554.100'), (1, '-554.380')] -[2023-11-28 08:22:53,458][87424] Updated weights for policy 0, policy_version 311989 (0.0012) -[2023-11-28 08:22:53,843][87424] Updated weights for policy 0, policy_version 311999 (0.0012) -[2023-11-28 08:22:54,761][87426] Updated weights for policy 1, policy_version 311720 (0.0010) -[2023-11-28 08:22:55,140][87426] Updated weights for policy 1, policy_version 311730 (0.0011) -[2023-11-28 08:22:55,526][87426] Updated weights for policy 1, policy_version 311740 (0.0011) -[2023-11-28 08:22:56,572][87424] Updated weights for policy 0, policy_version 312009 (0.0008) -[2023-11-28 08:22:56,946][87424] Updated weights for policy 0, policy_version 312019 (0.0011) -[2023-11-28 08:22:57,260][87426] Updated weights for policy 1, policy_version 311750 (0.0011) -[2023-11-28 08:22:57,326][87424] Updated weights for policy 0, policy_version 312029 (0.0007) -[2023-11-28 08:22:57,647][87426] Updated weights for policy 1, policy_version 311760 (0.0012) -[2023-11-28 08:22:58,017][87426] Updated weights for policy 1, policy_version 311770 (0.0012) -[2023-11-28 08:22:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 159694848. Throughput: 0: 2690.0, 1: 2740.7. Samples: 159704324. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:22:58,445][86177] Avg episode reward: [(0, '-558.390'), (1, '-571.560')] -[2023-11-28 08:22:59,143][87424] Updated weights for policy 0, policy_version 312039 (0.0012) -[2023-11-28 08:22:59,518][87424] Updated weights for policy 0, policy_version 312049 (0.0012) -[2023-11-28 08:22:59,902][87424] Updated weights for policy 0, policy_version 312059 (0.0012) -[2023-11-28 08:23:00,257][87426] Updated weights for policy 1, policy_version 311780 (0.0012) -[2023-11-28 08:23:00,633][87426] Updated weights for policy 1, policy_version 311790 (0.0009) -[2023-11-28 08:23:01,014][87426] Updated weights for policy 1, policy_version 311800 (0.0008) -[2023-11-28 08:23:02,465][87424] Updated weights for policy 0, policy_version 312069 (0.0011) -[2023-11-28 08:23:02,840][87424] Updated weights for policy 0, policy_version 312079 (0.0011) -[2023-11-28 08:23:03,202][87426] Updated weights for policy 1, policy_version 311810 (0.0007) -[2023-11-28 08:23:03,225][87424] Updated weights for policy 0, policy_version 312089 (0.0012) -[2023-11-28 08:23:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159711232. Throughput: 0: 2672.1, 1: 2758.5. Samples: 159728776. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:23:03,446][86177] Avg episode reward: [(0, '-546.840'), (1, '-576.610')] -[2023-11-28 08:23:03,583][87426] Updated weights for policy 1, policy_version 311820 (0.0008) -[2023-11-28 08:23:03,966][87426] Updated weights for policy 1, policy_version 311830 (0.0008) -[2023-11-28 08:23:04,349][87426] Updated weights for policy 1, policy_version 311840 (0.0008) -[2023-11-28 08:23:05,711][87424] Updated weights for policy 0, policy_version 312099 (0.0007) -[2023-11-28 08:23:06,101][87424] Updated weights for policy 0, policy_version 312109 (0.0010) -[2023-11-28 08:23:06,216][87426] Updated weights for policy 1, policy_version 311850 (0.0009) -[2023-11-28 08:23:06,476][87424] Updated weights for policy 0, policy_version 312119 (0.0007) -[2023-11-28 08:23:06,596][87426] Updated weights for policy 1, policy_version 311860 (0.0007) -[2023-11-28 08:23:06,978][87426] Updated weights for policy 1, policy_version 311870 (0.0009) -[2023-11-28 08:23:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 159744000. Throughput: 0: 2665.5, 1: 2780.9. Samples: 159761576. Policy #0 lag: (min: 31.0, avg: 37.7, max: 63.0) -[2023-11-28 08:23:08,446][86177] Avg episode reward: [(0, '-570.030'), (1, '-580.290')] -[2023-11-28 08:23:08,903][87424] Updated weights for policy 0, policy_version 312129 (0.0008) -[2023-11-28 08:23:09,234][87426] Updated weights for policy 1, policy_version 311880 (0.0011) -[2023-11-28 08:23:09,288][87424] Updated weights for policy 0, policy_version 312139 (0.0008) -[2023-11-28 08:23:09,612][87426] Updated weights for policy 1, policy_version 311890 (0.0011) -[2023-11-28 08:23:09,672][87424] Updated weights for policy 0, policy_version 312149 (0.0008) -[2023-11-28 08:23:09,995][87426] Updated weights for policy 1, policy_version 311900 (0.0011) -[2023-11-28 08:23:10,050][87424] Updated weights for policy 0, policy_version 312159 (0.0010) -[2023-11-28 08:23:11,970][87424] Updated weights for policy 0, policy_version 312169 (0.0014) -[2023-11-28 08:23:12,286][87426] Updated weights for policy 1, policy_version 311910 (0.0011) -[2023-11-28 08:23:12,348][87424] Updated weights for policy 0, policy_version 312179 (0.0012) -[2023-11-28 08:23:12,661][87426] Updated weights for policy 1, policy_version 311920 (0.0010) -[2023-11-28 08:23:12,728][87424] Updated weights for policy 0, policy_version 312189 (0.0012) -[2023-11-28 08:23:13,037][87426] Updated weights for policy 1, policy_version 311930 (0.0010) -[2023-11-28 08:23:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 159776768. Throughput: 0: 2653.2, 1: 2750.3. Samples: 159785808. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:13,445][86177] Avg episode reward: [(0, '-569.390'), (1, '-566.190')] -[2023-11-28 08:23:14,590][87424] Updated weights for policy 0, policy_version 312199 (0.0012) -[2023-11-28 08:23:14,774][87426] Updated weights for policy 1, policy_version 311940 (0.0009) -[2023-11-28 08:23:14,974][87424] Updated weights for policy 0, policy_version 312209 (0.0011) -[2023-11-28 08:23:15,159][87426] Updated weights for policy 1, policy_version 311950 (0.0010) -[2023-11-28 08:23:15,360][87424] Updated weights for policy 0, policy_version 312219 (0.0011) -[2023-11-28 08:23:15,538][87426] Updated weights for policy 1, policy_version 311960 (0.0011) -[2023-11-28 08:23:17,395][87426] Updated weights for policy 1, policy_version 311970 (0.0011) -[2023-11-28 08:23:17,771][87426] Updated weights for policy 1, policy_version 311980 (0.0011) -[2023-11-28 08:23:17,928][87424] Updated weights for policy 0, policy_version 312229 (0.0011) -[2023-11-28 08:23:18,154][87426] Updated weights for policy 1, policy_version 311990 (0.0012) -[2023-11-28 08:23:18,302][87424] Updated weights for policy 0, policy_version 312239 (0.0009) -[2023-11-28 08:23:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159793152. Throughput: 0: 2646.0, 1: 2751.7. Samples: 159810304. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:18,445][86177] Avg episode reward: [(0, '-561.510'), (1, '-597.440')] -[2023-11-28 08:23:18,527][87426] Updated weights for policy 1, policy_version 312000 (0.0012) -[2023-11-28 08:23:18,691][87424] Updated weights for policy 0, policy_version 312249 (0.0008) -[2023-11-28 08:23:20,868][87424] Updated weights for policy 0, policy_version 312259 (0.0009) -[2023-11-28 08:23:20,939][87426] Updated weights for policy 1, policy_version 312010 (0.0011) -[2023-11-28 08:23:21,253][87424] Updated weights for policy 0, policy_version 312269 (0.0010) -[2023-11-28 08:23:21,312][87426] Updated weights for policy 1, policy_version 312020 (0.0011) -[2023-11-28 08:23:21,634][87424] Updated weights for policy 0, policy_version 312279 (0.0009) -[2023-11-28 08:23:21,704][87426] Updated weights for policy 1, policy_version 312030 (0.0012) -[2023-11-28 08:23:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 159825920. Throughput: 0: 2619.5, 1: 2787.1. Samples: 159843552. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:23,445][86177] Avg episode reward: [(0, '-559.370'), (1, '-597.140')] -[2023-11-28 08:23:23,724][87426] Updated weights for policy 1, policy_version 312040 (0.0012) -[2023-11-28 08:23:23,849][87424] Updated weights for policy 0, policy_version 312289 (0.0011) -[2023-11-28 08:23:24,108][87426] Updated weights for policy 1, policy_version 312050 (0.0011) -[2023-11-28 08:23:24,247][87424] Updated weights for policy 0, policy_version 312299 (0.0012) -[2023-11-28 08:23:24,494][87426] Updated weights for policy 1, policy_version 312060 (0.0009) -[2023-11-28 08:23:24,627][87424] Updated weights for policy 0, policy_version 312309 (0.0012) -[2023-11-28 08:23:25,004][87424] Updated weights for policy 0, policy_version 312319 (0.0012) -[2023-11-28 08:23:26,747][87426] Updated weights for policy 1, policy_version 312070 (0.0009) -[2023-11-28 08:23:27,127][87426] Updated weights for policy 1, policy_version 312080 (0.0009) -[2023-11-28 08:23:27,293][87424] Updated weights for policy 0, policy_version 312329 (0.0010) -[2023-11-28 08:23:27,507][87426] Updated weights for policy 1, policy_version 312090 (0.0011) -[2023-11-28 08:23:27,688][87424] Updated weights for policy 0, policy_version 312339 (0.0008) -[2023-11-28 08:23:28,067][87424] Updated weights for policy 0, policy_version 312349 (0.0007) -[2023-11-28 08:23:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 159858688. Throughput: 0: 2615.5, 1: 2807.8. Samples: 159868072. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:28,446][86177] Avg episode reward: [(0, '-532.070'), (1, '-612.420')] -[2023-11-28 08:23:29,858][87426] Updated weights for policy 1, policy_version 312100 (0.0011) -[2023-11-28 08:23:30,168][87424] Updated weights for policy 0, policy_version 312359 (0.0010) -[2023-11-28 08:23:30,229][87426] Updated weights for policy 1, policy_version 312110 (0.0011) -[2023-11-28 08:23:30,543][87424] Updated weights for policy 0, policy_version 312369 (0.0014) -[2023-11-28 08:23:30,611][87426] Updated weights for policy 1, policy_version 312120 (0.0011) -[2023-11-28 08:23:30,928][87424] Updated weights for policy 0, policy_version 312379 (0.0009) -[2023-11-28 08:23:32,694][87426] Updated weights for policy 1, policy_version 312130 (0.0010) -[2023-11-28 08:23:33,076][87426] Updated weights for policy 1, policy_version 312140 (0.0011) -[2023-11-28 08:23:33,101][87424] Updated weights for policy 0, policy_version 312389 (0.0009) -[2023-11-28 08:23:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159875072. Throughput: 0: 2642.6, 1: 2795.5. Samples: 159892448. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:33,445][86177] Avg episode reward: [(0, '-535.420'), (1, '-624.840')] -[2023-11-28 08:23:33,452][87426] Updated weights for policy 1, policy_version 312150 (0.0009) -[2023-11-28 08:23:33,480][87424] Updated weights for policy 0, policy_version 312399 (0.0009) -[2023-11-28 08:23:33,828][87426] Updated weights for policy 1, policy_version 312160 (0.0007) -[2023-11-28 08:23:33,869][87424] Updated weights for policy 0, policy_version 312409 (0.0011) -[2023-11-28 08:23:35,897][87426] Updated weights for policy 1, policy_version 312170 (0.0007) -[2023-11-28 08:23:36,273][87426] Updated weights for policy 1, policy_version 312180 (0.0007) -[2023-11-28 08:23:36,313][87424] Updated weights for policy 0, policy_version 312419 (0.0012) -[2023-11-28 08:23:36,649][87426] Updated weights for policy 1, policy_version 312190 (0.0011) -[2023-11-28 08:23:36,710][87424] Updated weights for policy 0, policy_version 312429 (0.0011) -[2023-11-28 08:23:37,080][87424] Updated weights for policy 0, policy_version 312439 (0.0010) -[2023-11-28 08:23:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159907840. Throughput: 0: 2614.6, 1: 2785.3. Samples: 159923620. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:38,445][86177] Avg episode reward: [(0, '-543.420'), (1, '-570.930')] -[2023-11-28 08:23:39,103][87426] Updated weights for policy 1, policy_version 312200 (0.0009) -[2023-11-28 08:23:39,164][87424] Updated weights for policy 0, policy_version 312449 (0.0011) -[2023-11-28 08:23:39,482][87426] Updated weights for policy 1, policy_version 312210 (0.0011) -[2023-11-28 08:23:39,545][87424] Updated weights for policy 0, policy_version 312459 (0.0011) -[2023-11-28 08:23:39,858][87426] Updated weights for policy 1, policy_version 312220 (0.0011) -[2023-11-28 08:23:39,929][87424] Updated weights for policy 0, policy_version 312469 (0.0011) -[2023-11-28 08:23:40,306][87424] Updated weights for policy 0, policy_version 312479 (0.0011) -[2023-11-28 08:23:42,379][87426] Updated weights for policy 1, policy_version 312230 (0.0011) -[2023-11-28 08:23:42,733][87424] Updated weights for policy 0, policy_version 312489 (0.0011) -[2023-11-28 08:23:42,750][87426] Updated weights for policy 1, policy_version 312240 (0.0007) -[2023-11-28 08:23:43,115][87424] Updated weights for policy 0, policy_version 312499 (0.0009) -[2023-11-28 08:23:43,126][87426] Updated weights for policy 1, policy_version 312250 (0.0010) -[2023-11-28 08:23:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 159932416. Throughput: 0: 2647.4, 1: 2750.2. Samples: 159947216. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:43,445][86177] Avg episode reward: [(0, '-573.100'), (1, '-593.200')] -[2023-11-28 08:23:43,496][87424] Updated weights for policy 0, policy_version 312509 (0.0008) -[2023-11-28 08:23:45,192][87426] Updated weights for policy 1, policy_version 312260 (0.0011) -[2023-11-28 08:23:45,567][87426] Updated weights for policy 1, policy_version 312270 (0.0010) -[2023-11-28 08:23:45,945][87426] Updated weights for policy 1, policy_version 312280 (0.0008) -[2023-11-28 08:23:46,035][87424] Updated weights for policy 0, policy_version 312519 (0.0010) -[2023-11-28 08:23:46,421][87424] Updated weights for policy 0, policy_version 312529 (0.0012) -[2023-11-28 08:23:46,803][87424] Updated weights for policy 0, policy_version 312539 (0.0012) -[2023-11-28 08:23:48,249][87426] Updated weights for policy 1, policy_version 312290 (0.0011) -[2023-11-28 08:23:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 159956992. Throughput: 0: 2646.8, 1: 2749.8. Samples: 159971620. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:48,445][86177] Avg episode reward: [(0, '-573.020'), (1, '-559.910')] -[2023-11-28 08:23:48,492][87424] Updated weights for policy 0, policy_version 312549 (0.0012) -[2023-11-28 08:23:48,625][87426] Updated weights for policy 1, policy_version 312300 (0.0011) -[2023-11-28 08:23:48,877][87424] Updated weights for policy 0, policy_version 312559 (0.0011) -[2023-11-28 08:23:49,001][87426] Updated weights for policy 1, policy_version 312310 (0.0011) -[2023-11-28 08:23:49,254][87424] Updated weights for policy 0, policy_version 312569 (0.0012) -[2023-11-28 08:23:49,378][87426] Updated weights for policy 1, policy_version 312320 (0.0012) -[2023-11-28 08:23:51,577][87424] Updated weights for policy 0, policy_version 312579 (0.0012) -[2023-11-28 08:23:51,869][87426] Updated weights for policy 1, policy_version 312330 (0.0012) -[2023-11-28 08:23:51,941][87424] Updated weights for policy 0, policy_version 312589 (0.0012) -[2023-11-28 08:23:52,250][87426] Updated weights for policy 1, policy_version 312340 (0.0011) -[2023-11-28 08:23:52,325][87424] Updated weights for policy 0, policy_version 312599 (0.0012) -[2023-11-28 08:23:52,628][87426] Updated weights for policy 1, policy_version 312350 (0.0012) -[2023-11-28 08:23:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 159989760. Throughput: 0: 2655.0, 1: 2702.5. Samples: 160002664. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:53,445][86177] Avg episode reward: [(0, '-567.790'), (1, '-551.480')] -[2023-11-28 08:23:54,572][87424] Updated weights for policy 0, policy_version 312609 (0.0011) -[2023-11-28 08:23:54,676][87426] Updated weights for policy 1, policy_version 312360 (0.0009) -[2023-11-28 08:23:54,950][87424] Updated weights for policy 0, policy_version 312619 (0.0009) -[2023-11-28 08:23:55,058][87426] Updated weights for policy 1, policy_version 312370 (0.0009) -[2023-11-28 08:23:55,337][87424] Updated weights for policy 0, policy_version 312629 (0.0007) -[2023-11-28 08:23:55,432][87426] Updated weights for policy 1, policy_version 312380 (0.0009) -[2023-11-28 08:23:55,712][87424] Updated weights for policy 0, policy_version 312639 (0.0008) -[2023-11-28 08:23:57,278][87426] Updated weights for policy 1, policy_version 312390 (0.0007) -[2023-11-28 08:23:57,667][87426] Updated weights for policy 1, policy_version 312400 (0.0007) -[2023-11-28 08:23:58,046][87426] Updated weights for policy 1, policy_version 312410 (0.0008) -[2023-11-28 08:23:58,083][87424] Updated weights for policy 0, policy_version 312649 (0.0008) -[2023-11-28 08:23:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 160014336. Throughput: 0: 2651.4, 1: 2722.0. Samples: 160027612. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:23:58,445][86177] Avg episode reward: [(0, '-568.500'), (1, '-537.500')] -[2023-11-28 08:23:58,468][87424] Updated weights for policy 0, policy_version 312659 (0.0008) -[2023-11-28 08:23:58,849][87424] Updated weights for policy 0, policy_version 312669 (0.0008) -[2023-11-28 08:24:00,529][87426] Updated weights for policy 1, policy_version 312420 (0.0009) -[2023-11-28 08:24:00,907][87426] Updated weights for policy 1, policy_version 312430 (0.0012) -[2023-11-28 08:24:01,284][87426] Updated weights for policy 1, policy_version 312440 (0.0010) -[2023-11-28 08:24:01,314][87424] Updated weights for policy 0, policy_version 312679 (0.0012) -[2023-11-28 08:24:01,687][87424] Updated weights for policy 0, policy_version 312689 (0.0012) -[2023-11-28 08:24:02,070][87424] Updated weights for policy 0, policy_version 312699 (0.0012) -[2023-11-28 08:24:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 160038912. Throughput: 0: 2644.8, 1: 2718.4. Samples: 160051648. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:24:03,445][86177] Avg episode reward: [(0, '-537.140'), (1, '-509.570')] -[2023-11-28 08:24:03,733][87426] Updated weights for policy 1, policy_version 312450 (0.0008) -[2023-11-28 08:24:04,106][87426] Updated weights for policy 1, policy_version 312460 (0.0007) -[2023-11-28 08:24:04,250][87424] Updated weights for policy 0, policy_version 312709 (0.0012) -[2023-11-28 08:24:04,479][87426] Updated weights for policy 1, policy_version 312470 (0.0010) -[2023-11-28 08:24:04,637][87424] Updated weights for policy 0, policy_version 312719 (0.0014) -[2023-11-28 08:24:04,858][87426] Updated weights for policy 1, policy_version 312480 (0.0011) -[2023-11-28 08:24:05,014][87424] Updated weights for policy 0, policy_version 312729 (0.0010) -[2023-11-28 08:24:07,297][87426] Updated weights for policy 1, policy_version 312490 (0.0012) -[2023-11-28 08:24:07,365][87424] Updated weights for policy 0, policy_version 312739 (0.0011) -[2023-11-28 08:24:07,685][87426] Updated weights for policy 1, policy_version 312500 (0.0011) -[2023-11-28 08:24:07,738][87424] Updated weights for policy 0, policy_version 312749 (0.0010) -[2023-11-28 08:24:08,054][87426] Updated weights for policy 1, policy_version 312510 (0.0011) -[2023-11-28 08:24:08,127][87424] Updated weights for policy 0, policy_version 312759 (0.0012) -[2023-11-28 08:24:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 160063488. Throughput: 0: 2661.7, 1: 2692.8. Samples: 160084504. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:24:08,445][86177] Avg episode reward: [(0, '-536.460'), (1, '-503.930')] -[2023-11-28 08:24:09,910][87426] Updated weights for policy 1, policy_version 312520 (0.0012) -[2023-11-28 08:24:10,190][87424] Updated weights for policy 0, policy_version 312769 (0.0009) -[2023-11-28 08:24:10,289][87426] Updated weights for policy 1, policy_version 312530 (0.0012) -[2023-11-28 08:24:10,581][87424] Updated weights for policy 0, policy_version 312779 (0.0011) -[2023-11-28 08:24:10,668][87426] Updated weights for policy 1, policy_version 312540 (0.0010) -[2023-11-28 08:24:10,956][87424] Updated weights for policy 0, policy_version 312789 (0.0011) -[2023-11-28 08:24:11,335][87424] Updated weights for policy 0, policy_version 312799 (0.0011) -[2023-11-28 08:24:12,884][87426] Updated weights for policy 1, policy_version 312550 (0.0009) -[2023-11-28 08:24:13,263][87426] Updated weights for policy 1, policy_version 312560 (0.0010) -[2023-11-28 08:24:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 160088064. Throughput: 0: 2668.3, 1: 2681.3. Samples: 160108804. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:24:13,445][86177] Avg episode reward: [(0, '-534.390'), (1, '-508.260')] -[2023-11-28 08:24:13,644][87426] Updated weights for policy 1, policy_version 312570 (0.0010) -[2023-11-28 08:24:13,804][87424] Updated weights for policy 0, policy_version 312809 (0.0010) -[2023-11-28 08:24:14,200][87424] Updated weights for policy 0, policy_version 312819 (0.0007) -[2023-11-28 08:24:14,574][87424] Updated weights for policy 0, policy_version 312829 (0.0007) -[2023-11-28 08:24:15,527][87426] Updated weights for policy 1, policy_version 312580 (0.0009) -[2023-11-28 08:24:15,894][87426] Updated weights for policy 1, policy_version 312590 (0.0007) -[2023-11-28 08:24:16,281][87426] Updated weights for policy 1, policy_version 312600 (0.0008) -[2023-11-28 08:24:16,800][87424] Updated weights for policy 0, policy_version 312839 (0.0009) -[2023-11-28 08:24:17,185][87424] Updated weights for policy 0, policy_version 312849 (0.0012) -[2023-11-28 08:24:17,568][87424] Updated weights for policy 0, policy_version 312859 (0.0012) -[2023-11-28 08:24:18,163][87426] Updated weights for policy 1, policy_version 312610 (0.0010) -[2023-11-28 08:24:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 160120832. Throughput: 0: 2640.4, 1: 2681.5. Samples: 160131936. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:24:18,445][86177] Avg episode reward: [(0, '-533.180'), (1, '-509.790')] -[2023-11-28 08:24:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000312864_80093184.pth... -[2023-11-28 08:24:18,502][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000310368_79454208.pth -[2023-11-28 08:24:18,542][87426] Updated weights for policy 1, policy_version 312620 (0.0007) -[2023-11-28 08:24:18,923][87426] Updated weights for policy 1, policy_version 312630 (0.0009) -[2023-11-28 08:24:19,303][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000312640_80035840.pth... -[2023-11-28 08:24:19,304][87426] Updated weights for policy 1, policy_version 312640 (0.0008) -[2023-11-28 08:24:19,347][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000310080_79380480.pth -[2023-11-28 08:24:19,906][87424] Updated weights for policy 0, policy_version 312869 (0.0010) -[2023-11-28 08:24:20,281][87424] Updated weights for policy 0, policy_version 312879 (0.0009) -[2023-11-28 08:24:20,663][87424] Updated weights for policy 0, policy_version 312889 (0.0011) -[2023-11-28 08:24:21,791][87426] Updated weights for policy 1, policy_version 312650 (0.0010) -[2023-11-28 08:24:22,172][87426] Updated weights for policy 1, policy_version 312660 (0.0012) -[2023-11-28 08:24:22,552][87426] Updated weights for policy 1, policy_version 312670 (0.0012) -[2023-11-28 08:24:23,140][87424] Updated weights for policy 0, policy_version 312899 (0.0011) -[2023-11-28 08:24:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 160145408. Throughput: 0: 2649.2, 1: 2684.2. Samples: 160163624. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:24:23,445][86177] Avg episode reward: [(0, '-532.820'), (1, '-507.840')] -[2023-11-28 08:24:23,517][87424] Updated weights for policy 0, policy_version 312909 (0.0008) -[2023-11-28 08:24:23,895][87424] Updated weights for policy 0, policy_version 312919 (0.0007) -[2023-11-28 08:24:24,676][87426] Updated weights for policy 1, policy_version 312680 (0.0012) -[2023-11-28 08:24:25,052][87426] Updated weights for policy 1, policy_version 312690 (0.0010) -[2023-11-28 08:24:25,434][87426] Updated weights for policy 1, policy_version 312700 (0.0008) -[2023-11-28 08:24:25,671][87424] Updated weights for policy 0, policy_version 312929 (0.0010) -[2023-11-28 08:24:26,053][87424] Updated weights for policy 0, policy_version 312939 (0.0012) -[2023-11-28 08:24:26,444][87424] Updated weights for policy 0, policy_version 312949 (0.0012) -[2023-11-28 08:24:26,819][87424] Updated weights for policy 0, policy_version 312959 (0.0012) -[2023-11-28 08:24:27,523][87426] Updated weights for policy 1, policy_version 312710 (0.0010) -[2023-11-28 08:24:27,913][87426] Updated weights for policy 1, policy_version 312720 (0.0010) -[2023-11-28 08:24:28,296][87426] Updated weights for policy 1, policy_version 312730 (0.0010) -[2023-11-28 08:24:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 160169984. Throughput: 0: 2650.1, 1: 2730.9. Samples: 160189364. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:24:28,445][86177] Avg episode reward: [(0, '-527.500'), (1, '-513.580')] -[2023-11-28 08:24:28,566][87424] Updated weights for policy 0, policy_version 312969 (0.0012) -[2023-11-28 08:24:28,950][87424] Updated weights for policy 0, policy_version 312979 (0.0012) -[2023-11-28 08:24:29,333][87424] Updated weights for policy 0, policy_version 312989 (0.0012) -[2023-11-28 08:24:30,066][87426] Updated weights for policy 1, policy_version 312740 (0.0010) -[2023-11-28 08:24:30,455][87426] Updated weights for policy 1, policy_version 312750 (0.0011) -[2023-11-28 08:24:30,823][87426] Updated weights for policy 1, policy_version 312760 (0.0011) -[2023-11-28 08:24:31,179][87424] Updated weights for policy 0, policy_version 312999 (0.0011) -[2023-11-28 08:24:31,560][87424] Updated weights for policy 0, policy_version 313009 (0.0008) -[2023-11-28 08:24:31,945][87424] Updated weights for policy 0, policy_version 313019 (0.0011) -[2023-11-28 08:24:33,137][87426] Updated weights for policy 1, policy_version 312770 (0.0011) -[2023-11-28 08:24:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 160202752. Throughput: 0: 2686.3, 1: 2708.7. Samples: 160214396. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:24:33,445][86177] Avg episode reward: [(0, '-533.430'), (1, '-517.160')] -[2023-11-28 08:24:33,517][87426] Updated weights for policy 1, policy_version 312780 (0.0008) -[2023-11-28 08:24:33,897][87426] Updated weights for policy 1, policy_version 312790 (0.0007) -[2023-11-28 08:24:34,265][87426] Updated weights for policy 1, policy_version 312800 (0.0007) -[2023-11-28 08:24:34,333][87424] Updated weights for policy 0, policy_version 313029 (0.0010) -[2023-11-28 08:24:34,703][87424] Updated weights for policy 0, policy_version 313039 (0.0012) -[2023-11-28 08:24:35,084][87424] Updated weights for policy 0, policy_version 313049 (0.0010) -[2023-11-28 08:24:36,133][87426] Updated weights for policy 1, policy_version 312810 (0.0008) -[2023-11-28 08:24:36,517][87426] Updated weights for policy 1, policy_version 312820 (0.0007) -[2023-11-28 08:24:36,899][87426] Updated weights for policy 1, policy_version 312830 (0.0010) -[2023-11-28 08:24:37,329][87424] Updated weights for policy 0, policy_version 313059 (0.0009) -[2023-11-28 08:24:37,709][87424] Updated weights for policy 0, policy_version 313069 (0.0012) -[2023-11-28 08:24:38,091][87424] Updated weights for policy 0, policy_version 313079 (0.0011) -[2023-11-28 08:24:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 160235520. Throughput: 0: 2694.8, 1: 2746.7. Samples: 160247528. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:24:38,445][86177] Avg episode reward: [(0, '-532.190'), (1, '-515.010')] -[2023-11-28 08:24:38,979][87426] Updated weights for policy 1, policy_version 312840 (0.0009) -[2023-11-28 08:24:39,347][87426] Updated weights for policy 1, policy_version 312850 (0.0011) -[2023-11-28 08:24:39,728][87426] Updated weights for policy 1, policy_version 312860 (0.0009) -[2023-11-28 08:24:40,444][87424] Updated weights for policy 0, policy_version 313089 (0.0011) -[2023-11-28 08:24:40,829][87424] Updated weights for policy 0, policy_version 313099 (0.0008) -[2023-11-28 08:24:41,211][87424] Updated weights for policy 0, policy_version 313109 (0.0009) -[2023-11-28 08:24:41,590][87424] Updated weights for policy 0, policy_version 313119 (0.0012) -[2023-11-28 08:24:41,980][87426] Updated weights for policy 1, policy_version 312870 (0.0011) -[2023-11-28 08:24:42,352][87426] Updated weights for policy 1, policy_version 312880 (0.0009) -[2023-11-28 08:24:42,731][87426] Updated weights for policy 1, policy_version 312890 (0.0008) -[2023-11-28 08:24:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 160260096. Throughput: 0: 2691.3, 1: 2737.3. Samples: 160271900. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:24:43,445][86177] Avg episode reward: [(0, '-533.810'), (1, '-513.900')] -[2023-11-28 08:24:43,634][87424] Updated weights for policy 0, policy_version 313129 (0.0008) -[2023-11-28 08:24:44,020][87424] Updated weights for policy 0, policy_version 313139 (0.0007) -[2023-11-28 08:24:44,404][87424] Updated weights for policy 0, policy_version 313149 (0.0007) -[2023-11-28 08:24:44,951][87426] Updated weights for policy 1, policy_version 312900 (0.0011) -[2023-11-28 08:24:45,325][87426] Updated weights for policy 1, policy_version 312910 (0.0008) -[2023-11-28 08:24:45,704][87426] Updated weights for policy 1, policy_version 312920 (0.0012) -[2023-11-28 08:24:46,575][87424] Updated weights for policy 0, policy_version 313159 (0.0008) -[2023-11-28 08:24:46,963][87424] Updated weights for policy 0, policy_version 313169 (0.0011) -[2023-11-28 08:24:47,345][87424] Updated weights for policy 0, policy_version 313179 (0.0008) -[2023-11-28 08:24:47,866][87426] Updated weights for policy 1, policy_version 312930 (0.0011) -[2023-11-28 08:24:48,242][87426] Updated weights for policy 1, policy_version 312940 (0.0009) -[2023-11-28 08:24:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 160284672. Throughput: 0: 2722.5, 1: 2727.5. Samples: 160296900. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:24:48,445][86177] Avg episode reward: [(0, '-532.410'), (1, '-499.910')] -[2023-11-28 08:24:48,622][87426] Updated weights for policy 1, policy_version 312950 (0.0010) -[2023-11-28 08:24:48,996][87426] Updated weights for policy 1, policy_version 312960 (0.0012) -[2023-11-28 08:24:49,050][87424] Updated weights for policy 0, policy_version 313189 (0.0008) -[2023-11-28 08:24:49,448][87424] Updated weights for policy 0, policy_version 313199 (0.0009) -[2023-11-28 08:24:49,841][87424] Updated weights for policy 0, policy_version 313209 (0.0011) -[2023-11-28 08:24:50,998][87426] Updated weights for policy 1, policy_version 312970 (0.0010) -[2023-11-28 08:24:51,382][87426] Updated weights for policy 1, policy_version 312980 (0.0008) -[2023-11-28 08:24:51,766][87426] Updated weights for policy 1, policy_version 312990 (0.0010) -[2023-11-28 08:24:52,319][87424] Updated weights for policy 0, policy_version 313219 (0.0009) -[2023-11-28 08:24:52,710][87424] Updated weights for policy 0, policy_version 313229 (0.0011) -[2023-11-28 08:24:53,094][87424] Updated weights for policy 0, policy_version 313239 (0.0012) -[2023-11-28 08:24:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 160317440. Throughput: 0: 2709.2, 1: 2744.3. Samples: 160329916. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:24:53,445][86177] Avg episode reward: [(0, '-539.010'), (1, '-511.250')] -[2023-11-28 08:24:53,838][87426] Updated weights for policy 1, policy_version 313000 (0.0010) -[2023-11-28 08:24:54,226][87426] Updated weights for policy 1, policy_version 313010 (0.0009) -[2023-11-28 08:24:54,599][87426] Updated weights for policy 1, policy_version 313020 (0.0010) -[2023-11-28 08:24:55,753][87424] Updated weights for policy 0, policy_version 313249 (0.0012) -[2023-11-28 08:24:56,136][87424] Updated weights for policy 0, policy_version 313259 (0.0010) -[2023-11-28 08:24:56,530][87424] Updated weights for policy 0, policy_version 313269 (0.0012) -[2023-11-28 08:24:56,898][87424] Updated weights for policy 0, policy_version 313279 (0.0011) -[2023-11-28 08:24:57,032][87426] Updated weights for policy 1, policy_version 313030 (0.0011) -[2023-11-28 08:24:57,405][87426] Updated weights for policy 1, policy_version 313040 (0.0012) -[2023-11-28 08:24:57,775][87426] Updated weights for policy 1, policy_version 313050 (0.0012) -[2023-11-28 08:24:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 160342016. Throughput: 0: 2688.2, 1: 2723.5. Samples: 160352328. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:24:58,445][86177] Avg episode reward: [(0, '-545.020'), (1, '-510.710')] -[2023-11-28 08:24:59,410][87424] Updated weights for policy 0, policy_version 313289 (0.0012) -[2023-11-28 08:24:59,799][87424] Updated weights for policy 0, policy_version 313299 (0.0011) -[2023-11-28 08:24:59,930][87426] Updated weights for policy 1, policy_version 313060 (0.0012) -[2023-11-28 08:25:00,194][87424] Updated weights for policy 0, policy_version 313309 (0.0012) -[2023-11-28 08:25:00,303][87426] Updated weights for policy 1, policy_version 313070 (0.0012) -[2023-11-28 08:25:00,680][87426] Updated weights for policy 1, policy_version 313080 (0.0016) -[2023-11-28 08:25:03,002][87424] Updated weights for policy 0, policy_version 313319 (0.0012) -[2023-11-28 08:25:03,379][87424] Updated weights for policy 0, policy_version 313329 (0.0012) -[2023-11-28 08:25:03,444][86177] Fps is (10 sec: 4096.0, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 160358400. Throughput: 0: 2656.2, 1: 2695.6. Samples: 160372768. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:25:03,445][86177] Avg episode reward: [(0, '-555.350'), (1, '-515.140')] -[2023-11-28 08:25:03,750][87424] Updated weights for policy 0, policy_version 313339 (0.0012) -[2023-11-28 08:25:03,786][87426] Updated weights for policy 1, policy_version 313090 (0.0016) -[2023-11-28 08:25:04,173][87426] Updated weights for policy 1, policy_version 313100 (0.0011) -[2023-11-28 08:25:04,551][87426] Updated weights for policy 1, policy_version 313110 (0.0012) -[2023-11-28 08:25:04,927][87426] Updated weights for policy 1, policy_version 313120 (0.0011) -[2023-11-28 08:25:06,043][87424] Updated weights for policy 0, policy_version 313349 (0.0012) -[2023-11-28 08:25:06,430][87424] Updated weights for policy 0, policy_version 313359 (0.0012) -[2023-11-28 08:25:06,813][87424] Updated weights for policy 0, policy_version 313369 (0.0012) -[2023-11-28 08:25:07,351][87426] Updated weights for policy 1, policy_version 313130 (0.0012) -[2023-11-28 08:25:07,738][87426] Updated weights for policy 1, policy_version 313140 (0.0011) -[2023-11-28 08:25:08,114][87426] Updated weights for policy 1, policy_version 313150 (0.0011) -[2023-11-28 08:25:08,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 160391168. Throughput: 0: 2640.2, 1: 2677.8. Samples: 160402932. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:25:08,445][86177] Avg episode reward: [(0, '-551.440'), (1, '-526.680')] -[2023-11-28 08:25:09,397][87424] Updated weights for policy 0, policy_version 313379 (0.0011) -[2023-11-28 08:25:09,777][87424] Updated weights for policy 0, policy_version 313389 (0.0012) -[2023-11-28 08:25:10,177][87424] Updated weights for policy 0, policy_version 313399 (0.0011) -[2023-11-28 08:25:10,790][87426] Updated weights for policy 1, policy_version 313160 (0.0011) -[2023-11-28 08:25:11,157][87426] Updated weights for policy 1, policy_version 313170 (0.0011) -[2023-11-28 08:25:11,545][87426] Updated weights for policy 1, policy_version 313180 (0.0012) -[2023-11-28 08:25:12,981][87424] Updated weights for policy 0, policy_version 313409 (0.0012) -[2023-11-28 08:25:13,372][87424] Updated weights for policy 0, policy_version 313419 (0.0013) -[2023-11-28 08:25:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 160407552. Throughput: 0: 2601.8, 1: 2599.2. Samples: 160423408. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:25:13,445][86177] Avg episode reward: [(0, '-550.680'), (1, '-528.190')] -[2023-11-28 08:25:13,752][87424] Updated weights for policy 0, policy_version 313429 (0.0011) -[2023-11-28 08:25:14,136][87424] Updated weights for policy 0, policy_version 313439 (0.0011) -[2023-11-28 08:25:14,450][87426] Updated weights for policy 1, policy_version 313190 (0.0012) -[2023-11-28 08:25:14,824][87426] Updated weights for policy 1, policy_version 313200 (0.0012) -[2023-11-28 08:25:15,205][87426] Updated weights for policy 1, policy_version 313210 (0.0012) -[2023-11-28 08:25:16,791][87424] Updated weights for policy 0, policy_version 313449 (0.0011) -[2023-11-28 08:25:17,185][87424] Updated weights for policy 0, policy_version 313459 (0.0012) -[2023-11-28 08:25:17,567][87424] Updated weights for policy 0, policy_version 313469 (0.0012) -[2023-11-28 08:25:17,800][87426] Updated weights for policy 1, policy_version 313220 (0.0012) -[2023-11-28 08:25:18,178][87426] Updated weights for policy 1, policy_version 313230 (0.0012) -[2023-11-28 08:25:18,444][86177] Fps is (10 sec: 4096.1, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 160432128. Throughput: 0: 2547.1, 1: 2577.6. Samples: 160445008. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:25:18,445][86177] Avg episode reward: [(0, '-548.430'), (1, '-533.500')] -[2023-11-28 08:25:18,557][87426] Updated weights for policy 1, policy_version 313240 (0.0012) -[2023-11-28 08:25:20,093][87424] Updated weights for policy 0, policy_version 313479 (0.0012) -[2023-11-28 08:25:20,472][87424] Updated weights for policy 0, policy_version 313489 (0.0012) -[2023-11-28 08:25:20,852][87424] Updated weights for policy 0, policy_version 313499 (0.0011) -[2023-11-28 08:25:21,017][87426] Updated weights for policy 1, policy_version 313250 (0.0012) -[2023-11-28 08:25:21,391][87426] Updated weights for policy 1, policy_version 313260 (0.0011) -[2023-11-28 08:25:21,771][87426] Updated weights for policy 1, policy_version 313270 (0.0011) -[2023-11-28 08:25:22,147][87426] Updated weights for policy 1, policy_version 313280 (0.0012) -[2023-11-28 08:25:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 160456704. Throughput: 0: 2498.5, 1: 2520.4. Samples: 160473380. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:25:23,445][86177] Avg episode reward: [(0, '-542.340'), (1, '-535.610')] -[2023-11-28 08:25:23,523][87424] Updated weights for policy 0, policy_version 313509 (0.0013) -[2023-11-28 08:25:23,897][87424] Updated weights for policy 0, policy_version 313519 (0.0012) -[2023-11-28 08:25:24,289][87424] Updated weights for policy 0, policy_version 313529 (0.0011) -[2023-11-28 08:25:24,756][87426] Updated weights for policy 1, policy_version 313290 (0.0012) -[2023-11-28 08:25:25,126][87426] Updated weights for policy 1, policy_version 313300 (0.0010) -[2023-11-28 08:25:25,501][87426] Updated weights for policy 1, policy_version 313310 (0.0011) -[2023-11-28 08:25:26,706][87424] Updated weights for policy 0, policy_version 313539 (0.0010) -[2023-11-28 08:25:27,091][87424] Updated weights for policy 0, policy_version 313549 (0.0012) -[2023-11-28 08:25:27,474][87424] Updated weights for policy 0, policy_version 313559 (0.0012) -[2023-11-28 08:25:28,173][87426] Updated weights for policy 1, policy_version 313320 (0.0011) -[2023-11-28 08:25:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 160481280. Throughput: 0: 2485.8, 1: 2478.2. Samples: 160495280. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:25:28,445][86177] Avg episode reward: [(0, '-539.560'), (1, '-532.810')] -[2023-11-28 08:25:28,558][87426] Updated weights for policy 1, policy_version 313330 (0.0011) -[2023-11-28 08:25:28,935][87426] Updated weights for policy 1, policy_version 313340 (0.0011) -[2023-11-28 08:25:29,648][87424] Updated weights for policy 0, policy_version 313569 (0.0011) -[2023-11-28 08:25:30,029][87424] Updated weights for policy 0, policy_version 313579 (0.0011) -[2023-11-28 08:25:30,410][87424] Updated weights for policy 0, policy_version 313589 (0.0011) -[2023-11-28 08:25:30,797][87424] Updated weights for policy 0, policy_version 313599 (0.0014) -[2023-11-28 08:25:31,420][87426] Updated weights for policy 1, policy_version 313350 (0.0011) -[2023-11-28 08:25:31,795][87426] Updated weights for policy 1, policy_version 313360 (0.0011) -[2023-11-28 08:25:32,183][87426] Updated weights for policy 1, policy_version 313370 (0.0011) -[2023-11-28 08:25:33,267][87424] Updated weights for policy 0, policy_version 313609 (0.0011) -[2023-11-28 08:25:33,446][86177] Fps is (10 sec: 4914.2, 60 sec: 5051.6, 300 sec: 5331.7). Total num frames: 160505856. Throughput: 0: 2432.5, 1: 2475.9. Samples: 160517788. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:25:33,447][86177] Avg episode reward: [(0, '-575.020'), (1, '-515.120')] -[2023-11-28 08:25:33,650][87424] Updated weights for policy 0, policy_version 313619 (0.0012) -[2023-11-28 08:25:34,034][87424] Updated weights for policy 0, policy_version 313629 (0.0012) -[2023-11-28 08:25:34,694][87426] Updated weights for policy 1, policy_version 313380 (0.0010) -[2023-11-28 08:25:35,075][87426] Updated weights for policy 1, policy_version 313390 (0.0011) -[2023-11-28 08:25:35,453][87426] Updated weights for policy 1, policy_version 313400 (0.0011) -[2023-11-28 08:25:36,121][87424] Updated weights for policy 0, policy_version 313639 (0.0012) -[2023-11-28 08:25:36,513][87424] Updated weights for policy 0, policy_version 313649 (0.0012) -[2023-11-28 08:25:36,888][87424] Updated weights for policy 0, policy_version 313659 (0.0012) -[2023-11-28 08:25:37,819][87426] Updated weights for policy 1, policy_version 313410 (0.0009) -[2023-11-28 08:25:38,195][87426] Updated weights for policy 1, policy_version 313420 (0.0012) -[2023-11-28 08:25:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5331.7). Total num frames: 160530432. Throughput: 0: 2424.7, 1: 2434.6. Samples: 160548584. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:25:38,445][86177] Avg episode reward: [(0, '-571.750'), (1, '-504.700')] -[2023-11-28 08:25:38,569][87426] Updated weights for policy 1, policy_version 313430 (0.0012) -[2023-11-28 08:25:38,946][87426] Updated weights for policy 1, policy_version 313440 (0.0011) -[2023-11-28 08:25:39,426][87424] Updated weights for policy 0, policy_version 313669 (0.0012) -[2023-11-28 08:25:39,814][87424] Updated weights for policy 0, policy_version 313679 (0.0012) -[2023-11-28 08:25:40,189][87424] Updated weights for policy 0, policy_version 313689 (0.0012) -[2023-11-28 08:25:41,734][87426] Updated weights for policy 1, policy_version 313450 (0.0012) -[2023-11-28 08:25:42,114][87426] Updated weights for policy 1, policy_version 313460 (0.0012) -[2023-11-28 08:25:42,483][87426] Updated weights for policy 1, policy_version 313470 (0.0012) -[2023-11-28 08:25:43,019][87424] Updated weights for policy 0, policy_version 313699 (0.0015) -[2023-11-28 08:25:43,406][87424] Updated weights for policy 0, policy_version 313709 (0.0012) -[2023-11-28 08:25:43,444][86177] Fps is (10 sec: 4916.2, 60 sec: 4915.2, 300 sec: 5331.7). Total num frames: 160555008. Throughput: 0: 2420.8, 1: 2392.4. Samples: 160568924. Policy #0 lag: (min: 31.0, avg: 51.7, max: 87.0) -[2023-11-28 08:25:43,445][86177] Avg episode reward: [(0, '-576.450'), (1, '-526.160')] -[2023-11-28 08:25:43,785][87424] Updated weights for policy 0, policy_version 313719 (0.0011) -[2023-11-28 08:25:45,248][87426] Updated weights for policy 1, policy_version 313480 (0.0012) -[2023-11-28 08:25:45,631][87426] Updated weights for policy 1, policy_version 313490 (0.0012) -[2023-11-28 08:25:46,005][87426] Updated weights for policy 1, policy_version 313500 (0.0011) -[2023-11-28 08:25:46,402][87424] Updated weights for policy 0, policy_version 313729 (0.0011) -[2023-11-28 08:25:46,782][87424] Updated weights for policy 0, policy_version 313739 (0.0011) -[2023-11-28 08:25:47,167][87424] Updated weights for policy 0, policy_version 313749 (0.0010) -[2023-11-28 08:25:47,550][87424] Updated weights for policy 0, policy_version 313759 (0.0011) -[2023-11-28 08:25:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5304.0). Total num frames: 160579584. Throughput: 0: 2426.5, 1: 2411.8. Samples: 160590492. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:25:48,445][86177] Avg episode reward: [(0, '-577.580'), (1, '-523.590')] -[2023-11-28 08:25:48,571][87426] Updated weights for policy 1, policy_version 313510 (0.0010) -[2023-11-28 08:25:48,946][87426] Updated weights for policy 1, policy_version 313520 (0.0010) -[2023-11-28 08:25:49,335][87426] Updated weights for policy 1, policy_version 313530 (0.0012) -[2023-11-28 08:25:49,828][87424] Updated weights for policy 0, policy_version 313769 (0.0011) -[2023-11-28 08:25:50,201][87424] Updated weights for policy 0, policy_version 313779 (0.0011) -[2023-11-28 08:25:50,586][87424] Updated weights for policy 0, policy_version 313789 (0.0011) -[2023-11-28 08:25:51,823][87426] Updated weights for policy 1, policy_version 313540 (0.0011) -[2023-11-28 08:25:52,209][87426] Updated weights for policy 1, policy_version 313550 (0.0012) -[2023-11-28 08:25:52,587][87426] Updated weights for policy 1, policy_version 313560 (0.0010) -[2023-11-28 08:25:53,223][87424] Updated weights for policy 0, policy_version 313799 (0.0011) -[2023-11-28 08:25:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4778.7, 300 sec: 5331.7). Total num frames: 160604160. Throughput: 0: 2424.9, 1: 2386.5. Samples: 160619444. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:25:53,445][86177] Avg episode reward: [(0, '-547.860'), (1, '-535.860')] -[2023-11-28 08:25:53,606][87424] Updated weights for policy 0, policy_version 313809 (0.0011) -[2023-11-28 08:25:53,985][87424] Updated weights for policy 0, policy_version 313819 (0.0012) -[2023-11-28 08:25:55,219][87426] Updated weights for policy 1, policy_version 313570 (0.0012) -[2023-11-28 08:25:55,599][87426] Updated weights for policy 1, policy_version 313580 (0.0011) -[2023-11-28 08:25:55,980][87426] Updated weights for policy 1, policy_version 313590 (0.0011) -[2023-11-28 08:25:56,365][87426] Updated weights for policy 1, policy_version 313600 (0.0012) -[2023-11-28 08:25:56,661][87424] Updated weights for policy 0, policy_version 313829 (0.0011) -[2023-11-28 08:25:57,040][87424] Updated weights for policy 0, policy_version 313839 (0.0011) -[2023-11-28 08:25:57,415][87424] Updated weights for policy 0, policy_version 313849 (0.0009) -[2023-11-28 08:25:58,294][87426] Updated weights for policy 1, policy_version 313610 (0.0012) -[2023-11-28 08:25:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 4778.6, 300 sec: 5304.0). Total num frames: 160628736. Throughput: 0: 2432.6, 1: 2446.8. Samples: 160642984. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:25:58,446][86177] Avg episode reward: [(0, '-549.240'), (1, '-552.630')] -[2023-11-28 08:25:58,670][87426] Updated weights for policy 1, policy_version 313620 (0.0012) -[2023-11-28 08:25:59,051][87426] Updated weights for policy 1, policy_version 313630 (0.0012) -[2023-11-28 08:25:59,346][87424] Updated weights for policy 0, policy_version 313859 (0.0012) -[2023-11-28 08:25:59,730][87424] Updated weights for policy 0, policy_version 313869 (0.0011) -[2023-11-28 08:26:00,120][87424] Updated weights for policy 0, policy_version 313879 (0.0011) -[2023-11-28 08:26:01,420][87426] Updated weights for policy 1, policy_version 313640 (0.0009) -[2023-11-28 08:26:01,788][87426] Updated weights for policy 1, policy_version 313650 (0.0009) -[2023-11-28 08:26:02,171][87426] Updated weights for policy 1, policy_version 313660 (0.0009) -[2023-11-28 08:26:02,610][87424] Updated weights for policy 0, policy_version 313889 (0.0012) -[2023-11-28 08:26:02,986][87424] Updated weights for policy 0, policy_version 313899 (0.0010) -[2023-11-28 08:26:03,363][87424] Updated weights for policy 0, policy_version 313909 (0.0010) -[2023-11-28 08:26:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5276.2). Total num frames: 160653312. Throughput: 0: 2454.0, 1: 2475.8. Samples: 160666848. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:03,445][86177] Avg episode reward: [(0, '-539.710'), (1, '-542.460')] -[2023-11-28 08:26:03,741][87424] Updated weights for policy 0, policy_version 313919 (0.0011) -[2023-11-28 08:26:04,757][87426] Updated weights for policy 1, policy_version 313670 (0.0010) -[2023-11-28 08:26:05,126][87426] Updated weights for policy 1, policy_version 313680 (0.0012) -[2023-11-28 08:26:05,501][87426] Updated weights for policy 1, policy_version 313690 (0.0011) -[2023-11-28 08:26:06,417][87424] Updated weights for policy 0, policy_version 313929 (0.0010) -[2023-11-28 08:26:06,806][87424] Updated weights for policy 0, policy_version 313939 (0.0011) -[2023-11-28 08:26:07,175][87424] Updated weights for policy 0, policy_version 313949 (0.0012) -[2023-11-28 08:26:07,850][87426] Updated weights for policy 1, policy_version 313700 (0.0009) -[2023-11-28 08:26:08,235][87426] Updated weights for policy 1, policy_version 313710 (0.0011) -[2023-11-28 08:26:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 4778.7, 300 sec: 5304.0). Total num frames: 160677888. Throughput: 0: 2465.7, 1: 2492.0. Samples: 160696476. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:08,445][86177] Avg episode reward: [(0, '-543.870'), (1, '-537.190')] -[2023-11-28 08:26:08,618][87426] Updated weights for policy 1, policy_version 313720 (0.0013) -[2023-11-28 08:26:09,391][87424] Updated weights for policy 0, policy_version 313959 (0.0016) -[2023-11-28 08:26:09,769][87424] Updated weights for policy 0, policy_version 313969 (0.0011) -[2023-11-28 08:26:10,159][87424] Updated weights for policy 0, policy_version 313979 (0.0011) -[2023-11-28 08:26:11,405][87426] Updated weights for policy 1, policy_version 313730 (0.0013) -[2023-11-28 08:26:11,780][87426] Updated weights for policy 1, policy_version 313740 (0.0010) -[2023-11-28 08:26:12,156][87426] Updated weights for policy 1, policy_version 313750 (0.0010) -[2023-11-28 08:26:12,537][87426] Updated weights for policy 1, policy_version 313760 (0.0013) -[2023-11-28 08:26:13,052][87424] Updated weights for policy 0, policy_version 313989 (0.0012) -[2023-11-28 08:26:13,434][87424] Updated weights for policy 0, policy_version 313999 (0.0012) -[2023-11-28 08:26:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5276.2). Total num frames: 160702464. Throughput: 0: 2449.6, 1: 2466.9. Samples: 160716524. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:13,445][86177] Avg episode reward: [(0, '-539.850'), (1, '-540.780')] -[2023-11-28 08:26:13,822][87424] Updated weights for policy 0, policy_version 314009 (0.0012) -[2023-11-28 08:26:15,024][87426] Updated weights for policy 1, policy_version 313770 (0.0012) -[2023-11-28 08:26:15,402][87426] Updated weights for policy 1, policy_version 313780 (0.0012) -[2023-11-28 08:26:15,774][87426] Updated weights for policy 1, policy_version 313790 (0.0011) -[2023-11-28 08:26:16,303][87424] Updated weights for policy 0, policy_version 314019 (0.0012) -[2023-11-28 08:26:16,688][87424] Updated weights for policy 0, policy_version 314029 (0.0012) -[2023-11-28 08:26:17,070][87424] Updated weights for policy 0, policy_version 314039 (0.0012) -[2023-11-28 08:26:18,285][87426] Updated weights for policy 1, policy_version 313800 (0.0011) -[2023-11-28 08:26:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5248.4). Total num frames: 160727040. Throughput: 0: 2448.0, 1: 2463.2. Samples: 160738784. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:18,445][86177] Avg episode reward: [(0, '-540.040'), (1, '-552.140')] -[2023-11-28 08:26:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000314048_80396288.pth... -[2023-11-28 08:26:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000311616_79773696.pth -[2023-11-28 08:26:18,670][87426] Updated weights for policy 1, policy_version 313810 (0.0011) -[2023-11-28 08:26:19,046][87426] Updated weights for policy 1, policy_version 313820 (0.0012) -[2023-11-28 08:26:19,198][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000313824_80338944.pth... -[2023-11-28 08:26:19,249][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000311328_79699968.pth -[2023-11-28 08:26:19,623][87424] Updated weights for policy 0, policy_version 314049 (0.0012) -[2023-11-28 08:26:20,003][87424] Updated weights for policy 0, policy_version 314059 (0.0011) -[2023-11-28 08:26:20,389][87424] Updated weights for policy 0, policy_version 314069 (0.0014) -[2023-11-28 08:26:20,772][87424] Updated weights for policy 0, policy_version 314079 (0.0012) -[2023-11-28 08:26:21,592][87426] Updated weights for policy 1, policy_version 313830 (0.0012) -[2023-11-28 08:26:21,976][87426] Updated weights for policy 1, policy_version 313840 (0.0010) -[2023-11-28 08:26:22,346][87426] Updated weights for policy 1, policy_version 313850 (0.0011) -[2023-11-28 08:26:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5276.2). Total num frames: 160751616. Throughput: 0: 2414.8, 1: 2433.2. Samples: 160766744. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:23,445][86177] Avg episode reward: [(0, '-541.000'), (1, '-549.410')] -[2023-11-28 08:26:23,678][87424] Updated weights for policy 0, policy_version 314089 (0.0012) -[2023-11-28 08:26:24,052][87424] Updated weights for policy 0, policy_version 314099 (0.0011) -[2023-11-28 08:26:24,434][87424] Updated weights for policy 0, policy_version 314109 (0.0011) -[2023-11-28 08:26:25,333][87426] Updated weights for policy 1, policy_version 313860 (0.0011) -[2023-11-28 08:26:25,711][87426] Updated weights for policy 1, policy_version 313870 (0.0010) -[2023-11-28 08:26:26,089][87426] Updated weights for policy 1, policy_version 313880 (0.0010) -[2023-11-28 08:26:26,862][87424] Updated weights for policy 0, policy_version 314119 (0.0014) -[2023-11-28 08:26:27,251][87424] Updated weights for policy 0, policy_version 314129 (0.0011) -[2023-11-28 08:26:27,623][87424] Updated weights for policy 0, policy_version 314139 (0.0010) -[2023-11-28 08:26:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5248.4). Total num frames: 160776192. Throughput: 0: 2418.4, 1: 2466.0. Samples: 160788720. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:28,445][86177] Avg episode reward: [(0, '-538.850'), (1, '-565.210')] -[2023-11-28 08:26:28,566][87426] Updated weights for policy 1, policy_version 313890 (0.0010) -[2023-11-28 08:26:28,952][87426] Updated weights for policy 1, policy_version 313900 (0.0011) -[2023-11-28 08:26:29,330][87426] Updated weights for policy 1, policy_version 313910 (0.0013) -[2023-11-28 08:26:29,706][87426] Updated weights for policy 1, policy_version 313920 (0.0012) -[2023-11-28 08:26:29,916][87424] Updated weights for policy 0, policy_version 314149 (0.0011) -[2023-11-28 08:26:30,296][87424] Updated weights for policy 0, policy_version 314159 (0.0011) -[2023-11-28 08:26:30,678][87424] Updated weights for policy 0, policy_version 314169 (0.0012) -[2023-11-28 08:26:32,299][87426] Updated weights for policy 1, policy_version 313930 (0.0011) -[2023-11-28 08:26:32,675][87426] Updated weights for policy 1, policy_version 313940 (0.0011) -[2023-11-28 08:26:33,055][87426] Updated weights for policy 1, policy_version 313950 (0.0011) -[2023-11-28 08:26:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.4, 300 sec: 5220.7). Total num frames: 160800768. Throughput: 0: 2425.4, 1: 2459.3. Samples: 160810304. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:33,445][86177] Avg episode reward: [(0, '-538.510'), (1, '-569.790')] -[2023-11-28 08:26:33,470][87424] Updated weights for policy 0, policy_version 314179 (0.0012) -[2023-11-28 08:26:33,841][87424] Updated weights for policy 0, policy_version 314189 (0.0010) -[2023-11-28 08:26:34,227][87424] Updated weights for policy 0, policy_version 314199 (0.0010) -[2023-11-28 08:26:35,831][87426] Updated weights for policy 1, policy_version 313960 (0.0012) -[2023-11-28 08:26:36,212][87426] Updated weights for policy 1, policy_version 313970 (0.0013) -[2023-11-28 08:26:36,578][87424] Updated weights for policy 0, policy_version 314209 (0.0010) -[2023-11-28 08:26:36,597][87426] Updated weights for policy 1, policy_version 313980 (0.0011) -[2023-11-28 08:26:36,957][87424] Updated weights for policy 0, policy_version 314219 (0.0011) -[2023-11-28 08:26:37,344][87424] Updated weights for policy 0, policy_version 314229 (0.0012) -[2023-11-28 08:26:37,721][87424] Updated weights for policy 0, policy_version 314239 (0.0011) -[2023-11-28 08:26:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5248.4). Total num frames: 160825344. Throughput: 0: 2429.7, 1: 2465.2. Samples: 160839716. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:38,445][86177] Avg episode reward: [(0, '-538.660'), (1, '-565.920')] -[2023-11-28 08:26:39,000][87426] Updated weights for policy 1, policy_version 313990 (0.0012) -[2023-11-28 08:26:39,374][87426] Updated weights for policy 1, policy_version 314000 (0.0012) -[2023-11-28 08:26:39,756][87426] Updated weights for policy 1, policy_version 314010 (0.0010) -[2023-11-28 08:26:40,059][87424] Updated weights for policy 0, policy_version 314249 (0.0012) -[2023-11-28 08:26:40,423][87424] Updated weights for policy 0, policy_version 314259 (0.0012) -[2023-11-28 08:26:40,804][87424] Updated weights for policy 0, policy_version 314269 (0.0012) -[2023-11-28 08:26:42,335][87426] Updated weights for policy 1, policy_version 314020 (0.0011) -[2023-11-28 08:26:42,712][87426] Updated weights for policy 1, policy_version 314030 (0.0011) -[2023-11-28 08:26:43,092][87426] Updated weights for policy 1, policy_version 314040 (0.0010) -[2023-11-28 08:26:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5220.7). Total num frames: 160849920. Throughput: 0: 2436.5, 1: 2418.2. Samples: 160861444. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:43,445][86177] Avg episode reward: [(0, '-538.410'), (1, '-555.050')] -[2023-11-28 08:26:43,727][87424] Updated weights for policy 0, policy_version 314279 (0.0010) -[2023-11-28 08:26:44,107][87424] Updated weights for policy 0, policy_version 314289 (0.0010) -[2023-11-28 08:26:44,486][87424] Updated weights for policy 0, policy_version 314299 (0.0010) -[2023-11-28 08:26:45,509][87426] Updated weights for policy 1, policy_version 314050 (0.0010) -[2023-11-28 08:26:45,891][87426] Updated weights for policy 1, policy_version 314060 (0.0011) -[2023-11-28 08:26:46,264][87426] Updated weights for policy 1, policy_version 314070 (0.0011) -[2023-11-28 08:26:46,645][87426] Updated weights for policy 1, policy_version 314080 (0.0012) -[2023-11-28 08:26:46,986][87424] Updated weights for policy 0, policy_version 314309 (0.0010) -[2023-11-28 08:26:47,370][87424] Updated weights for policy 0, policy_version 314319 (0.0011) -[2023-11-28 08:26:47,752][87424] Updated weights for policy 0, policy_version 314329 (0.0012) -[2023-11-28 08:26:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5220.7). Total num frames: 160874496. Throughput: 0: 2420.6, 1: 2400.9. Samples: 160883816. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:48,445][86177] Avg episode reward: [(0, '-540.070'), (1, '-571.660')] -[2023-11-28 08:26:49,085][87426] Updated weights for policy 1, policy_version 314090 (0.0012) -[2023-11-28 08:26:49,465][87426] Updated weights for policy 1, policy_version 314100 (0.0012) -[2023-11-28 08:26:49,843][87426] Updated weights for policy 1, policy_version 314110 (0.0012) -[2023-11-28 08:26:50,102][87424] Updated weights for policy 0, policy_version 314339 (0.0012) -[2023-11-28 08:26:50,481][87424] Updated weights for policy 0, policy_version 314349 (0.0011) -[2023-11-28 08:26:50,859][87424] Updated weights for policy 0, policy_version 314359 (0.0011) -[2023-11-28 08:26:52,618][87426] Updated weights for policy 1, policy_version 314120 (0.0011) -[2023-11-28 08:26:52,995][87426] Updated weights for policy 1, policy_version 314130 (0.0013) -[2023-11-28 08:26:53,383][87426] Updated weights for policy 1, policy_version 314140 (0.0011) -[2023-11-28 08:26:53,444][86177] Fps is (10 sec: 4096.0, 60 sec: 4778.7, 300 sec: 5192.9). Total num frames: 160890880. Throughput: 0: 2408.4, 1: 2385.4. Samples: 160912200. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:53,445][86177] Avg episode reward: [(0, '-538.540'), (1, '-590.360')] -[2023-11-28 08:26:53,691][87424] Updated weights for policy 0, policy_version 314369 (0.0012) -[2023-11-28 08:26:54,076][87424] Updated weights for policy 0, policy_version 314379 (0.0012) -[2023-11-28 08:26:54,456][87424] Updated weights for policy 0, policy_version 314389 (0.0011) -[2023-11-28 08:26:54,839][87424] Updated weights for policy 0, policy_version 314399 (0.0011) -[2023-11-28 08:26:56,202][87426] Updated weights for policy 1, policy_version 314150 (0.0012) -[2023-11-28 08:26:56,584][87426] Updated weights for policy 1, policy_version 314160 (0.0012) -[2023-11-28 08:26:56,955][87426] Updated weights for policy 1, policy_version 314170 (0.0012) -[2023-11-28 08:26:57,510][87424] Updated weights for policy 0, policy_version 314409 (0.0010) -[2023-11-28 08:26:57,892][87424] Updated weights for policy 0, policy_version 314419 (0.0010) -[2023-11-28 08:26:58,262][87424] Updated weights for policy 0, policy_version 314429 (0.0012) -[2023-11-28 08:26:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5192.9). Total num frames: 160923648. Throughput: 0: 2416.0, 1: 2384.7. Samples: 160932556. Policy #0 lag: (min: 31.0, avg: 38.3, max: 63.0) -[2023-11-28 08:26:58,445][86177] Avg episode reward: [(0, '-538.390'), (1, '-592.350')] -[2023-11-28 08:26:59,464][87426] Updated weights for policy 1, policy_version 314180 (0.0011) -[2023-11-28 08:26:59,849][87426] Updated weights for policy 1, policy_version 314190 (0.0011) -[2023-11-28 08:27:00,231][87426] Updated weights for policy 1, policy_version 314200 (0.0011) -[2023-11-28 08:27:00,583][87424] Updated weights for policy 0, policy_version 314439 (0.0010) -[2023-11-28 08:27:00,962][87424] Updated weights for policy 0, policy_version 314449 (0.0011) -[2023-11-28 08:27:01,344][87424] Updated weights for policy 0, policy_version 314459 (0.0011) -[2023-11-28 08:27:02,693][87426] Updated weights for policy 1, policy_version 314210 (0.0012) -[2023-11-28 08:27:03,075][87426] Updated weights for policy 1, policy_version 314220 (0.0012) -[2023-11-28 08:27:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4778.7, 300 sec: 5165.1). Total num frames: 160940032. Throughput: 0: 2415.6, 1: 2384.8. Samples: 160954800. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:03,445][86177] Avg episode reward: [(0, '-540.190'), (1, '-574.630')] -[2023-11-28 08:27:03,460][87426] Updated weights for policy 1, policy_version 314230 (0.0012) -[2023-11-28 08:27:03,699][87424] Updated weights for policy 0, policy_version 314469 (0.0012) -[2023-11-28 08:27:03,834][87426] Updated weights for policy 1, policy_version 314240 (0.0011) -[2023-11-28 08:27:04,079][87424] Updated weights for policy 0, policy_version 314479 (0.0012) -[2023-11-28 08:27:04,463][87424] Updated weights for policy 0, policy_version 314489 (0.0012) -[2023-11-28 08:27:06,387][87426] Updated weights for policy 1, policy_version 314250 (0.0012) -[2023-11-28 08:27:06,770][87426] Updated weights for policy 1, policy_version 314260 (0.0012) -[2023-11-28 08:27:07,032][87424] Updated weights for policy 0, policy_version 314499 (0.0011) -[2023-11-28 08:27:07,146][87426] Updated weights for policy 1, policy_version 314270 (0.0012) -[2023-11-28 08:27:07,407][87424] Updated weights for policy 0, policy_version 314509 (0.0011) -[2023-11-28 08:27:07,788][87424] Updated weights for policy 0, policy_version 314519 (0.0011) -[2023-11-28 08:27:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5192.9). Total num frames: 160972800. Throughput: 0: 2455.4, 1: 2409.2. Samples: 160985652. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:08,445][86177] Avg episode reward: [(0, '-542.480'), (1, '-581.100')] -[2023-11-28 08:27:09,407][87426] Updated weights for policy 1, policy_version 314280 (0.0012) -[2023-11-28 08:27:09,784][87426] Updated weights for policy 1, policy_version 314290 (0.0011) -[2023-11-28 08:27:09,815][87424] Updated weights for policy 0, policy_version 314529 (0.0010) -[2023-11-28 08:27:10,177][87426] Updated weights for policy 1, policy_version 314300 (0.0010) -[2023-11-28 08:27:10,196][87424] Updated weights for policy 0, policy_version 314539 (0.0011) -[2023-11-28 08:27:10,579][87424] Updated weights for policy 0, policy_version 314549 (0.0011) -[2023-11-28 08:27:10,962][87424] Updated weights for policy 0, policy_version 314559 (0.0009) -[2023-11-28 08:27:12,446][87426] Updated weights for policy 1, policy_version 314310 (0.0010) -[2023-11-28 08:27:12,824][87426] Updated weights for policy 1, policy_version 314320 (0.0010) -[2023-11-28 08:27:13,203][87426] Updated weights for policy 1, policy_version 314330 (0.0011) -[2023-11-28 08:27:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 4915.2, 300 sec: 5165.1). Total num frames: 160997376. Throughput: 0: 2463.8, 1: 2417.8. Samples: 161008392. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:13,445][86177] Avg episode reward: [(0, '-544.490'), (1, '-578.980')] -[2023-11-28 08:27:13,556][87424] Updated weights for policy 0, policy_version 314569 (0.0012) -[2023-11-28 08:27:13,931][87424] Updated weights for policy 0, policy_version 314579 (0.0012) -[2023-11-28 08:27:14,318][87424] Updated weights for policy 0, policy_version 314589 (0.0012) -[2023-11-28 08:27:15,326][87426] Updated weights for policy 1, policy_version 314340 (0.0011) -[2023-11-28 08:27:15,707][87426] Updated weights for policy 1, policy_version 314350 (0.0011) -[2023-11-28 08:27:16,088][87426] Updated weights for policy 1, policy_version 314360 (0.0011) -[2023-11-28 08:27:16,870][87424] Updated weights for policy 0, policy_version 314599 (0.0010) -[2023-11-28 08:27:17,252][87424] Updated weights for policy 0, policy_version 314609 (0.0011) -[2023-11-28 08:27:17,634][87424] Updated weights for policy 0, policy_version 314619 (0.0011) -[2023-11-28 08:27:17,888][87426] Updated weights for policy 1, policy_version 314370 (0.0011) -[2023-11-28 08:27:18,258][87426] Updated weights for policy 1, policy_version 314380 (0.0011) -[2023-11-28 08:27:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 4915.2, 300 sec: 5165.1). Total num frames: 161021952. Throughput: 0: 2476.6, 1: 2451.5. Samples: 161032072. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:18,446][86177] Avg episode reward: [(0, '-546.880'), (1, '-559.910')] -[2023-11-28 08:27:18,640][87426] Updated weights for policy 1, policy_version 314390 (0.0012) -[2023-11-28 08:27:19,019][87426] Updated weights for policy 1, policy_version 314400 (0.0011) -[2023-11-28 08:27:20,234][87424] Updated weights for policy 0, policy_version 314629 (0.0009) -[2023-11-28 08:27:20,622][87424] Updated weights for policy 0, policy_version 314639 (0.0011) -[2023-11-28 08:27:20,999][87424] Updated weights for policy 0, policy_version 314649 (0.0011) -[2023-11-28 08:27:21,186][87426] Updated weights for policy 1, policy_version 314410 (0.0011) -[2023-11-28 08:27:21,559][87426] Updated weights for policy 1, policy_version 314420 (0.0012) -[2023-11-28 08:27:21,943][87426] Updated weights for policy 1, policy_version 314430 (0.0012) -[2023-11-28 08:27:23,101][87424] Updated weights for policy 0, policy_version 314659 (0.0011) -[2023-11-28 08:27:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 5165.1). Total num frames: 161046528. Throughput: 0: 2496.1, 1: 2505.9. Samples: 161064804. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:23,445][86177] Avg episode reward: [(0, '-553.130'), (1, '-586.480')] -[2023-11-28 08:27:23,478][87424] Updated weights for policy 0, policy_version 314669 (0.0013) -[2023-11-28 08:27:23,854][87424] Updated weights for policy 0, policy_version 314679 (0.0012) -[2023-11-28 08:27:24,109][87426] Updated weights for policy 1, policy_version 314440 (0.0008) -[2023-11-28 08:27:24,488][87426] Updated weights for policy 1, policy_version 314450 (0.0008) -[2023-11-28 08:27:24,859][87426] Updated weights for policy 1, policy_version 314460 (0.0007) -[2023-11-28 08:27:26,316][87424] Updated weights for policy 0, policy_version 314689 (0.0011) -[2023-11-28 08:27:26,700][87426] Updated weights for policy 1, policy_version 314470 (0.0009) -[2023-11-28 08:27:26,701][87424] Updated weights for policy 0, policy_version 314699 (0.0009) -[2023-11-28 08:27:27,079][87424] Updated weights for policy 0, policy_version 314709 (0.0011) -[2023-11-28 08:27:27,080][87426] Updated weights for policy 1, policy_version 314480 (0.0010) -[2023-11-28 08:27:27,466][87424] Updated weights for policy 0, policy_version 314719 (0.0011) -[2023-11-28 08:27:27,466][87426] Updated weights for policy 1, policy_version 314490 (0.0010) -[2023-11-28 08:27:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5051.7, 300 sec: 5165.1). Total num frames: 161079296. Throughput: 0: 2513.4, 1: 2568.0. Samples: 161090108. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:28,445][86177] Avg episode reward: [(0, '-551.400'), (1, '-626.260')] -[2023-11-28 08:27:29,224][87424] Updated weights for policy 0, policy_version 314729 (0.0012) -[2023-11-28 08:27:29,602][87424] Updated weights for policy 0, policy_version 314739 (0.0011) -[2023-11-28 08:27:29,876][87426] Updated weights for policy 1, policy_version 314500 (0.0011) -[2023-11-28 08:27:29,983][87424] Updated weights for policy 0, policy_version 314749 (0.0011) -[2023-11-28 08:27:30,259][87426] Updated weights for policy 1, policy_version 314510 (0.0011) -[2023-11-28 08:27:30,637][87426] Updated weights for policy 1, policy_version 314520 (0.0010) -[2023-11-28 08:27:31,941][87424] Updated weights for policy 0, policy_version 314759 (0.0011) -[2023-11-28 08:27:32,336][87424] Updated weights for policy 0, policy_version 314769 (0.0010) -[2023-11-28 08:27:32,722][87424] Updated weights for policy 0, policy_version 314779 (0.0009) -[2023-11-28 08:27:33,071][87426] Updated weights for policy 1, policy_version 314530 (0.0008) -[2023-11-28 08:27:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5051.7, 300 sec: 5137.4). Total num frames: 161103872. Throughput: 0: 2571.9, 1: 2579.2. Samples: 161115616. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:33,445][86177] Avg episode reward: [(0, '-547.410'), (1, '-638.630')] -[2023-11-28 08:27:33,449][87426] Updated weights for policy 1, policy_version 314540 (0.0007) -[2023-11-28 08:27:33,829][87426] Updated weights for policy 1, policy_version 314550 (0.0007) -[2023-11-28 08:27:34,212][87426] Updated weights for policy 1, policy_version 314560 (0.0008) -[2023-11-28 08:27:34,834][87424] Updated weights for policy 0, policy_version 314789 (0.0011) -[2023-11-28 08:27:35,224][87424] Updated weights for policy 0, policy_version 314799 (0.0012) -[2023-11-28 08:27:35,608][87424] Updated weights for policy 0, policy_version 314809 (0.0012) -[2023-11-28 08:27:36,111][87426] Updated weights for policy 1, policy_version 314570 (0.0012) -[2023-11-28 08:27:36,488][87426] Updated weights for policy 1, policy_version 314580 (0.0009) -[2023-11-28 08:27:36,871][87426] Updated weights for policy 1, policy_version 314590 (0.0008) -[2023-11-28 08:27:37,801][87424] Updated weights for policy 0, policy_version 314819 (0.0010) -[2023-11-28 08:27:38,170][87424] Updated weights for policy 0, policy_version 314829 (0.0008) -[2023-11-28 08:27:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5051.7, 300 sec: 5165.1). Total num frames: 161128448. Throughput: 0: 2629.7, 1: 2618.0. Samples: 161148344. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:38,445][86177] Avg episode reward: [(0, '-541.300'), (1, '-652.690')] -[2023-11-28 08:27:38,547][87424] Updated weights for policy 0, policy_version 314839 (0.0007) -[2023-11-28 08:27:39,014][87426] Updated weights for policy 1, policy_version 314600 (0.0010) -[2023-11-28 08:27:39,396][87426] Updated weights for policy 1, policy_version 314610 (0.0012) -[2023-11-28 08:27:39,763][87426] Updated weights for policy 1, policy_version 314620 (0.0011) -[2023-11-28 08:27:40,689][87424] Updated weights for policy 0, policy_version 314849 (0.0009) -[2023-11-28 08:27:41,055][87424] Updated weights for policy 0, policy_version 314859 (0.0008) -[2023-11-28 08:27:41,437][87424] Updated weights for policy 0, policy_version 314869 (0.0008) -[2023-11-28 08:27:41,828][87424] Updated weights for policy 0, policy_version 314879 (0.0011) -[2023-11-28 08:27:42,241][87426] Updated weights for policy 1, policy_version 314630 (0.0011) -[2023-11-28 08:27:42,622][87426] Updated weights for policy 1, policy_version 314640 (0.0012) -[2023-11-28 08:27:43,007][87426] Updated weights for policy 1, policy_version 314650 (0.0012) -[2023-11-28 08:27:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5165.1). Total num frames: 161161216. Throughput: 0: 2654.7, 1: 2670.2. Samples: 161172176. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:43,446][86177] Avg episode reward: [(0, '-526.890'), (1, '-632.600')] -[2023-11-28 08:27:44,045][87424] Updated weights for policy 0, policy_version 314889 (0.0012) -[2023-11-28 08:27:44,425][87424] Updated weights for policy 0, policy_version 314899 (0.0012) -[2023-11-28 08:27:44,809][87424] Updated weights for policy 0, policy_version 314909 (0.0011) -[2023-11-28 08:27:44,983][87426] Updated weights for policy 1, policy_version 314660 (0.0011) -[2023-11-28 08:27:45,372][87426] Updated weights for policy 1, policy_version 314670 (0.0012) -[2023-11-28 08:27:45,768][87426] Updated weights for policy 1, policy_version 314680 (0.0011) -[2023-11-28 08:27:47,121][87424] Updated weights for policy 0, policy_version 314919 (0.0009) -[2023-11-28 08:27:47,509][87424] Updated weights for policy 0, policy_version 314929 (0.0007) -[2023-11-28 08:27:47,896][87426] Updated weights for policy 1, policy_version 314690 (0.0011) -[2023-11-28 08:27:47,901][87424] Updated weights for policy 0, policy_version 314939 (0.0008) -[2023-11-28 08:27:48,264][87426] Updated weights for policy 1, policy_version 314700 (0.0007) -[2023-11-28 08:27:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5165.1). Total num frames: 161185792. Throughput: 0: 2671.1, 1: 2693.6. Samples: 161196212. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:48,445][86177] Avg episode reward: [(0, '-526.250'), (1, '-594.900')] -[2023-11-28 08:27:48,650][87426] Updated weights for policy 1, policy_version 314710 (0.0008) -[2023-11-28 08:27:49,021][87426] Updated weights for policy 1, policy_version 314720 (0.0009) -[2023-11-28 08:27:50,283][87424] Updated weights for policy 0, policy_version 314949 (0.0007) -[2023-11-28 08:27:50,666][87424] Updated weights for policy 0, policy_version 314959 (0.0008) -[2023-11-28 08:27:51,048][87424] Updated weights for policy 0, policy_version 314969 (0.0009) -[2023-11-28 08:27:51,357][87426] Updated weights for policy 1, policy_version 314730 (0.0011) -[2023-11-28 08:27:51,729][87426] Updated weights for policy 1, policy_version 314740 (0.0012) -[2023-11-28 08:27:52,101][87426] Updated weights for policy 1, policy_version 314750 (0.0011) -[2023-11-28 08:27:53,207][87424] Updated weights for policy 0, policy_version 314979 (0.0011) -[2023-11-28 08:27:53,445][86177] Fps is (10 sec: 4914.8, 60 sec: 5324.7, 300 sec: 5137.3). Total num frames: 161210368. Throughput: 0: 2684.3, 1: 2729.5. Samples: 161229280. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:53,446][86177] Avg episode reward: [(0, '-531.560'), (1, '-577.350')] -[2023-11-28 08:27:53,587][87424] Updated weights for policy 0, policy_version 314989 (0.0010) -[2023-11-28 08:27:53,964][87424] Updated weights for policy 0, policy_version 314999 (0.0010) -[2023-11-28 08:27:54,272][87426] Updated weights for policy 1, policy_version 314760 (0.0009) -[2023-11-28 08:27:54,651][87426] Updated weights for policy 1, policy_version 314770 (0.0012) -[2023-11-28 08:27:55,026][87426] Updated weights for policy 1, policy_version 314780 (0.0009) -[2023-11-28 08:27:55,721][87424] Updated weights for policy 0, policy_version 315009 (0.0010) -[2023-11-28 08:27:56,101][87424] Updated weights for policy 0, policy_version 315019 (0.0010) -[2023-11-28 08:27:56,488][87424] Updated weights for policy 0, policy_version 315029 (0.0011) -[2023-11-28 08:27:56,860][87424] Updated weights for policy 0, policy_version 315039 (0.0012) -[2023-11-28 08:27:57,386][87426] Updated weights for policy 1, policy_version 314790 (0.0007) -[2023-11-28 08:27:57,769][87426] Updated weights for policy 1, policy_version 314800 (0.0007) -[2023-11-28 08:27:58,152][87426] Updated weights for policy 1, policy_version 314810 (0.0007) -[2023-11-28 08:27:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5192.9). Total num frames: 161243136. Throughput: 0: 2710.8, 1: 2743.5. Samples: 161253832. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:27:58,445][86177] Avg episode reward: [(0, '-534.250'), (1, '-558.770')] -[2023-11-28 08:27:58,841][87424] Updated weights for policy 0, policy_version 315049 (0.0012) -[2023-11-28 08:27:59,238][87424] Updated weights for policy 0, policy_version 315059 (0.0011) -[2023-11-28 08:27:59,613][87424] Updated weights for policy 0, policy_version 315069 (0.0011) -[2023-11-28 08:28:00,626][87426] Updated weights for policy 1, policy_version 314820 (0.0007) -[2023-11-28 08:28:01,001][87426] Updated weights for policy 1, policy_version 314830 (0.0008) -[2023-11-28 08:28:01,386][87426] Updated weights for policy 1, policy_version 314840 (0.0007) -[2023-11-28 08:28:02,015][87424] Updated weights for policy 0, policy_version 315079 (0.0010) -[2023-11-28 08:28:02,390][87424] Updated weights for policy 0, policy_version 315089 (0.0010) -[2023-11-28 08:28:02,775][87424] Updated weights for policy 0, policy_version 315099 (0.0011) -[2023-11-28 08:28:03,444][86177] Fps is (10 sec: 5735.0, 60 sec: 5461.3, 300 sec: 5165.1). Total num frames: 161267712. Throughput: 0: 2750.3, 1: 2726.8. Samples: 161278540. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:28:03,445][86177] Avg episode reward: [(0, '-543.990'), (1, '-594.730')] -[2023-11-28 08:28:03,719][87426] Updated weights for policy 1, policy_version 314850 (0.0009) -[2023-11-28 08:28:04,098][87426] Updated weights for policy 1, policy_version 314860 (0.0011) -[2023-11-28 08:28:04,470][87426] Updated weights for policy 1, policy_version 314870 (0.0009) -[2023-11-28 08:28:04,856][87426] Updated weights for policy 1, policy_version 314880 (0.0008) -[2023-11-28 08:28:05,339][87424] Updated weights for policy 0, policy_version 315109 (0.0009) -[2023-11-28 08:28:05,721][87424] Updated weights for policy 0, policy_version 315119 (0.0007) -[2023-11-28 08:28:06,101][87424] Updated weights for policy 0, policy_version 315129 (0.0008) -[2023-11-28 08:28:06,798][87426] Updated weights for policy 1, policy_version 314890 (0.0009) -[2023-11-28 08:28:07,170][87426] Updated weights for policy 1, policy_version 314900 (0.0008) -[2023-11-28 08:28:07,557][87426] Updated weights for policy 1, policy_version 314910 (0.0008) -[2023-11-28 08:28:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5137.4). Total num frames: 161292288. Throughput: 0: 2749.8, 1: 2707.9. Samples: 161310400. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:28:08,445][86177] Avg episode reward: [(0, '-538.170'), (1, '-583.460')] -[2023-11-28 08:28:08,622][87424] Updated weights for policy 0, policy_version 315139 (0.0007) -[2023-11-28 08:28:09,008][87424] Updated weights for policy 0, policy_version 315149 (0.0010) -[2023-11-28 08:28:09,386][87424] Updated weights for policy 0, policy_version 315159 (0.0009) -[2023-11-28 08:28:09,605][87426] Updated weights for policy 1, policy_version 314920 (0.0011) -[2023-11-28 08:28:09,984][87426] Updated weights for policy 1, policy_version 314930 (0.0012) -[2023-11-28 08:28:10,368][87426] Updated weights for policy 1, policy_version 314940 (0.0011) -[2023-11-28 08:28:11,743][87424] Updated weights for policy 0, policy_version 315169 (0.0011) -[2023-11-28 08:28:12,120][87424] Updated weights for policy 0, policy_version 315179 (0.0011) -[2023-11-28 08:28:12,500][87424] Updated weights for policy 0, policy_version 315189 (0.0011) -[2023-11-28 08:28:12,888][87424] Updated weights for policy 0, policy_version 315199 (0.0012) -[2023-11-28 08:28:12,907][87426] Updated weights for policy 1, policy_version 314950 (0.0010) -[2023-11-28 08:28:13,286][87426] Updated weights for policy 1, policy_version 314960 (0.0011) -[2023-11-28 08:28:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5165.1). Total num frames: 161316864. Throughput: 0: 2736.7, 1: 2696.7. Samples: 161334612. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:28:13,445][86177] Avg episode reward: [(0, '-538.210'), (1, '-573.970')] -[2023-11-28 08:28:13,667][87426] Updated weights for policy 1, policy_version 314970 (0.0011) -[2023-11-28 08:28:14,749][87424] Updated weights for policy 0, policy_version 315209 (0.0012) -[2023-11-28 08:28:15,125][87424] Updated weights for policy 0, policy_version 315219 (0.0012) -[2023-11-28 08:28:15,468][87426] Updated weights for policy 1, policy_version 314980 (0.0011) -[2023-11-28 08:28:15,507][87424] Updated weights for policy 0, policy_version 315229 (0.0012) -[2023-11-28 08:28:15,851][87426] Updated weights for policy 1, policy_version 314990 (0.0012) -[2023-11-28 08:28:16,219][87426] Updated weights for policy 1, policy_version 315000 (0.0011) -[2023-11-28 08:28:17,758][87424] Updated weights for policy 0, policy_version 315239 (0.0011) -[2023-11-28 08:28:18,075][87426] Updated weights for policy 1, policy_version 315010 (0.0011) -[2023-11-28 08:28:18,137][87424] Updated weights for policy 0, policy_version 315249 (0.0008) -[2023-11-28 08:28:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5137.4). Total num frames: 161341440. Throughput: 0: 2729.3, 1: 2701.4. Samples: 161360000. Policy #0 lag: (min: 31.0, avg: 44.4, max: 63.0) -[2023-11-28 08:28:18,445][86177] Avg episode reward: [(0, '-531.070'), (1, '-589.850')] -[2023-11-28 08:28:18,453][87426] Updated weights for policy 1, policy_version 315020 (0.0011) -[2023-11-28 08:28:18,520][87424] Updated weights for policy 0, policy_version 315259 (0.0007) -[2023-11-28 08:28:18,714][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000315264_80707584.pth... -[2023-11-28 08:28:18,757][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000312864_80093184.pth -[2023-11-28 08:28:18,831][87426] Updated weights for policy 1, policy_version 315030 (0.0009) -[2023-11-28 08:28:19,209][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000315040_80650240.pth... -[2023-11-28 08:28:19,210][87426] Updated weights for policy 1, policy_version 315040 (0.0012) -[2023-11-28 08:28:19,255][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000312640_80035840.pth -[2023-11-28 08:28:20,708][87424] Updated weights for policy 0, policy_version 315269 (0.0010) -[2023-11-28 08:28:21,088][87424] Updated weights for policy 0, policy_version 315279 (0.0012) -[2023-11-28 08:28:21,466][87424] Updated weights for policy 0, policy_version 315289 (0.0011) -[2023-11-28 08:28:21,603][87426] Updated weights for policy 1, policy_version 315050 (0.0012) -[2023-11-28 08:28:21,984][87426] Updated weights for policy 1, policy_version 315060 (0.0015) -[2023-11-28 08:28:22,359][87426] Updated weights for policy 1, policy_version 315070 (0.0010) -[2023-11-28 08:28:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5137.4). Total num frames: 161374208. Throughput: 0: 2714.2, 1: 2706.0. Samples: 161392252. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:28:23,445][86177] Avg episode reward: [(0, '-539.170'), (1, '-565.050')] -[2023-11-28 08:28:23,535][87424] Updated weights for policy 0, policy_version 315299 (0.0012) -[2023-11-28 08:28:23,910][87424] Updated weights for policy 0, policy_version 315309 (0.0012) -[2023-11-28 08:28:24,285][87424] Updated weights for policy 0, policy_version 315319 (0.0012) -[2023-11-28 08:28:24,721][87426] Updated weights for policy 1, policy_version 315080 (0.0011) -[2023-11-28 08:28:25,090][87426] Updated weights for policy 1, policy_version 315090 (0.0012) -[2023-11-28 08:28:25,466][87426] Updated weights for policy 1, policy_version 315100 (0.0012) -[2023-11-28 08:28:26,045][87424] Updated weights for policy 0, policy_version 315329 (0.0011) -[2023-11-28 08:28:26,431][87424] Updated weights for policy 0, policy_version 315339 (0.0012) -[2023-11-28 08:28:26,808][87424] Updated weights for policy 0, policy_version 315349 (0.0012) -[2023-11-28 08:28:27,190][87424] Updated weights for policy 0, policy_version 315359 (0.0012) -[2023-11-28 08:28:27,532][87426] Updated weights for policy 1, policy_version 315110 (0.0012) -[2023-11-28 08:28:27,909][87426] Updated weights for policy 1, policy_version 315120 (0.0011) -[2023-11-28 08:28:28,280][87426] Updated weights for policy 1, policy_version 315130 (0.0011) -[2023-11-28 08:28:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5165.1). Total num frames: 161398784. Throughput: 0: 2723.7, 1: 2723.7. Samples: 161417312. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:28:28,445][86177] Avg episode reward: [(0, '-551.100'), (1, '-531.820')] -[2023-11-28 08:28:29,512][87424] Updated weights for policy 0, policy_version 315369 (0.0012) -[2023-11-28 08:28:29,897][87424] Updated weights for policy 0, policy_version 315379 (0.0010) -[2023-11-28 08:28:30,273][87424] Updated weights for policy 0, policy_version 315389 (0.0011) -[2023-11-28 08:28:30,485][87426] Updated weights for policy 1, policy_version 315140 (0.0011) -[2023-11-28 08:28:30,860][87426] Updated weights for policy 1, policy_version 315150 (0.0010) -[2023-11-28 08:28:31,239][87426] Updated weights for policy 1, policy_version 315160 (0.0011) -[2023-11-28 08:28:32,725][87424] Updated weights for policy 0, policy_version 315399 (0.0011) -[2023-11-28 08:28:33,107][87424] Updated weights for policy 0, policy_version 315409 (0.0011) -[2023-11-28 08:28:33,439][87426] Updated weights for policy 1, policy_version 315170 (0.0012) -[2023-11-28 08:28:33,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5137.4). Total num frames: 161423360. Throughput: 0: 2719.6, 1: 2712.3. Samples: 161440652. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:28:33,446][86177] Avg episode reward: [(0, '-576.540'), (1, '-537.370')] -[2023-11-28 08:28:33,487][87424] Updated weights for policy 0, policy_version 315419 (0.0012) -[2023-11-28 08:28:33,821][87426] Updated weights for policy 1, policy_version 315180 (0.0011) -[2023-11-28 08:28:34,203][87426] Updated weights for policy 1, policy_version 315190 (0.0011) -[2023-11-28 08:28:34,588][87426] Updated weights for policy 1, policy_version 315200 (0.0012) -[2023-11-28 08:28:35,341][87424] Updated weights for policy 0, policy_version 315429 (0.0011) -[2023-11-28 08:28:35,720][87424] Updated weights for policy 0, policy_version 315439 (0.0012) -[2023-11-28 08:28:36,097][87424] Updated weights for policy 0, policy_version 315449 (0.0012) -[2023-11-28 08:28:36,721][87426] Updated weights for policy 1, policy_version 315210 (0.0011) -[2023-11-28 08:28:37,098][87426] Updated weights for policy 1, policy_version 315220 (0.0011) -[2023-11-28 08:28:37,475][87426] Updated weights for policy 1, policy_version 315230 (0.0010) -[2023-11-28 08:28:38,105][87424] Updated weights for policy 0, policy_version 315459 (0.0010) -[2023-11-28 08:28:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5165.1). Total num frames: 161456128. Throughput: 0: 2715.4, 1: 2712.2. Samples: 161473516. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:28:38,445][86177] Avg episode reward: [(0, '-608.570'), (1, '-537.220')] -[2023-11-28 08:28:38,494][87424] Updated weights for policy 0, policy_version 315469 (0.0007) -[2023-11-28 08:28:38,868][87424] Updated weights for policy 0, policy_version 315479 (0.0009) -[2023-11-28 08:28:39,801][87426] Updated weights for policy 1, policy_version 315240 (0.0009) -[2023-11-28 08:28:40,177][87426] Updated weights for policy 1, policy_version 315250 (0.0010) -[2023-11-28 08:28:40,559][87426] Updated weights for policy 1, policy_version 315260 (0.0010) -[2023-11-28 08:28:41,077][87424] Updated weights for policy 0, policy_version 315489 (0.0010) -[2023-11-28 08:28:41,459][87424] Updated weights for policy 0, policy_version 315499 (0.0008) -[2023-11-28 08:28:41,839][87424] Updated weights for policy 0, policy_version 315509 (0.0011) -[2023-11-28 08:28:42,224][87424] Updated weights for policy 0, policy_version 315519 (0.0009) -[2023-11-28 08:28:42,850][87426] Updated weights for policy 1, policy_version 315270 (0.0009) -[2023-11-28 08:28:43,226][87426] Updated weights for policy 1, policy_version 315280 (0.0008) -[2023-11-28 08:28:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5165.1). Total num frames: 161480704. Throughput: 0: 2709.4, 1: 2718.6. Samples: 161498092. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:28:43,445][86177] Avg episode reward: [(0, '-596.130'), (1, '-509.260')] -[2023-11-28 08:28:43,602][87426] Updated weights for policy 1, policy_version 315290 (0.0010) -[2023-11-28 08:28:44,087][87424] Updated weights for policy 0, policy_version 315529 (0.0011) -[2023-11-28 08:28:44,466][87424] Updated weights for policy 0, policy_version 315539 (0.0012) -[2023-11-28 08:28:44,846][87424] Updated weights for policy 0, policy_version 315549 (0.0012) -[2023-11-28 08:28:45,273][87426] Updated weights for policy 1, policy_version 315300 (0.0010) -[2023-11-28 08:28:45,651][87426] Updated weights for policy 1, policy_version 315310 (0.0012) -[2023-11-28 08:28:46,017][87426] Updated weights for policy 1, policy_version 315320 (0.0012) -[2023-11-28 08:28:46,987][87424] Updated weights for policy 0, policy_version 315559 (0.0012) -[2023-11-28 08:28:47,375][87424] Updated weights for policy 0, policy_version 315569 (0.0012) -[2023-11-28 08:28:47,752][87424] Updated weights for policy 0, policy_version 315579 (0.0012) -[2023-11-28 08:28:47,834][87426] Updated weights for policy 1, policy_version 315330 (0.0011) -[2023-11-28 08:28:48,214][87426] Updated weights for policy 1, policy_version 315340 (0.0007) -[2023-11-28 08:28:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5165.1). Total num frames: 161513472. Throughput: 0: 2698.8, 1: 2736.0. Samples: 161523108. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:28:48,445][86177] Avg episode reward: [(0, '-596.140'), (1, '-550.370')] -[2023-11-28 08:28:48,606][87426] Updated weights for policy 1, policy_version 315350 (0.0007) -[2023-11-28 08:28:48,983][87426] Updated weights for policy 1, policy_version 315360 (0.0009) -[2023-11-28 08:28:50,077][87424] Updated weights for policy 0, policy_version 315589 (0.0012) -[2023-11-28 08:28:50,458][87424] Updated weights for policy 0, policy_version 315599 (0.0012) -[2023-11-28 08:28:50,835][87424] Updated weights for policy 0, policy_version 315609 (0.0012) -[2023-11-28 08:28:51,114][87426] Updated weights for policy 1, policy_version 315370 (0.0009) -[2023-11-28 08:28:51,487][87426] Updated weights for policy 1, policy_version 315380 (0.0008) -[2023-11-28 08:28:51,869][87426] Updated weights for policy 1, policy_version 315390 (0.0010) -[2023-11-28 08:28:53,001][87424] Updated weights for policy 0, policy_version 315619 (0.0012) -[2023-11-28 08:28:53,374][87424] Updated weights for policy 0, policy_version 315629 (0.0012) -[2023-11-28 08:28:53,445][86177] Fps is (10 sec: 5733.7, 60 sec: 5461.3, 300 sec: 5165.1). Total num frames: 161538048. Throughput: 0: 2709.5, 1: 2741.2. Samples: 161555688. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:28:53,446][86177] Avg episode reward: [(0, '-574.630'), (1, '-562.810')] -[2023-11-28 08:28:53,755][87424] Updated weights for policy 0, policy_version 315639 (0.0012) -[2023-11-28 08:28:54,273][87426] Updated weights for policy 1, policy_version 315400 (0.0010) -[2023-11-28 08:28:54,651][87426] Updated weights for policy 1, policy_version 315410 (0.0008) -[2023-11-28 08:28:55,034][87426] Updated weights for policy 1, policy_version 315420 (0.0008) -[2023-11-28 08:28:56,320][87424] Updated weights for policy 0, policy_version 315649 (0.0010) -[2023-11-28 08:28:56,705][87424] Updated weights for policy 0, policy_version 315659 (0.0007) -[2023-11-28 08:28:57,081][87424] Updated weights for policy 0, policy_version 315669 (0.0010) -[2023-11-28 08:28:57,457][87424] Updated weights for policy 0, policy_version 315679 (0.0012) -[2023-11-28 08:28:57,534][87426] Updated weights for policy 1, policy_version 315430 (0.0007) -[2023-11-28 08:28:57,925][87426] Updated weights for policy 1, policy_version 315440 (0.0010) -[2023-11-28 08:28:58,294][87426] Updated weights for policy 1, policy_version 315450 (0.0008) -[2023-11-28 08:28:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5165.1). Total num frames: 161562624. Throughput: 0: 2714.1, 1: 2714.3. Samples: 161578892. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:28:58,445][86177] Avg episode reward: [(0, '-548.350'), (1, '-573.430')] -[2023-11-28 08:28:59,781][87424] Updated weights for policy 0, policy_version 315689 (0.0011) -[2023-11-28 08:29:00,161][87424] Updated weights for policy 0, policy_version 315699 (0.0007) -[2023-11-28 08:29:00,548][87424] Updated weights for policy 0, policy_version 315709 (0.0009) -[2023-11-28 08:29:00,638][87426] Updated weights for policy 1, policy_version 315460 (0.0008) -[2023-11-28 08:29:01,011][87426] Updated weights for policy 1, policy_version 315470 (0.0009) -[2023-11-28 08:29:01,389][87426] Updated weights for policy 1, policy_version 315480 (0.0008) -[2023-11-28 08:29:02,582][87424] Updated weights for policy 0, policy_version 315719 (0.0011) -[2023-11-28 08:29:02,962][87424] Updated weights for policy 0, policy_version 315729 (0.0008) -[2023-11-28 08:29:03,356][87424] Updated weights for policy 0, policy_version 315739 (0.0008) -[2023-11-28 08:29:03,444][86177] Fps is (10 sec: 4915.8, 60 sec: 5324.8, 300 sec: 5165.1). Total num frames: 161587200. Throughput: 0: 2701.3, 1: 2704.5. Samples: 161603260. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:29:03,445][86177] Avg episode reward: [(0, '-545.900'), (1, '-635.970')] -[2023-11-28 08:29:03,797][87426] Updated weights for policy 1, policy_version 315490 (0.0009) -[2023-11-28 08:29:04,159][87426] Updated weights for policy 1, policy_version 315500 (0.0011) -[2023-11-28 08:29:04,553][87426] Updated weights for policy 1, policy_version 315510 (0.0011) -[2023-11-28 08:29:04,926][87426] Updated weights for policy 1, policy_version 315520 (0.0012) -[2023-11-28 08:29:05,737][87424] Updated weights for policy 0, policy_version 315749 (0.0007) -[2023-11-28 08:29:06,139][87424] Updated weights for policy 0, policy_version 315759 (0.0007) -[2023-11-28 08:29:06,518][87424] Updated weights for policy 0, policy_version 315769 (0.0008) -[2023-11-28 08:29:07,086][87426] Updated weights for policy 1, policy_version 315530 (0.0012) -[2023-11-28 08:29:07,455][87426] Updated weights for policy 1, policy_version 315540 (0.0011) -[2023-11-28 08:29:07,840][87426] Updated weights for policy 1, policy_version 315550 (0.0012) -[2023-11-28 08:29:08,407][87424] Updated weights for policy 0, policy_version 315779 (0.0010) -[2023-11-28 08:29:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5192.9). Total num frames: 161619968. Throughput: 0: 2729.3, 1: 2702.7. Samples: 161636692. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:29:08,445][86177] Avg episode reward: [(0, '-539.720'), (1, '-641.030')] -[2023-11-28 08:29:08,792][87424] Updated weights for policy 0, policy_version 315789 (0.0012) -[2023-11-28 08:29:09,179][87424] Updated weights for policy 0, policy_version 315799 (0.0012) -[2023-11-28 08:29:10,090][87426] Updated weights for policy 1, policy_version 315560 (0.0012) -[2023-11-28 08:29:10,471][87426] Updated weights for policy 1, policy_version 315570 (0.0012) -[2023-11-28 08:29:10,848][87426] Updated weights for policy 1, policy_version 315580 (0.0012) -[2023-11-28 08:29:11,242][87424] Updated weights for policy 0, policy_version 315809 (0.0011) -[2023-11-28 08:29:11,619][87424] Updated weights for policy 0, policy_version 315819 (0.0012) -[2023-11-28 08:29:12,007][87424] Updated weights for policy 0, policy_version 315829 (0.0012) -[2023-11-28 08:29:12,391][87424] Updated weights for policy 0, policy_version 315839 (0.0012) -[2023-11-28 08:29:12,816][87426] Updated weights for policy 1, policy_version 315590 (0.0012) -[2023-11-28 08:29:13,189][87426] Updated weights for policy 1, policy_version 315600 (0.0020) -[2023-11-28 08:29:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5165.1). Total num frames: 161644544. Throughput: 0: 2725.5, 1: 2687.2. Samples: 161660884. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:29:13,445][86177] Avg episode reward: [(0, '-545.780'), (1, '-662.060')] -[2023-11-28 08:29:13,567][87426] Updated weights for policy 1, policy_version 315610 (0.0012) -[2023-11-28 08:29:14,953][87424] Updated weights for policy 0, policy_version 315849 (0.0012) -[2023-11-28 08:29:15,341][87424] Updated weights for policy 0, policy_version 315859 (0.0011) -[2023-11-28 08:29:15,717][87424] Updated weights for policy 0, policy_version 315869 (0.0008) -[2023-11-28 08:29:16,002][87426] Updated weights for policy 1, policy_version 315620 (0.0012) -[2023-11-28 08:29:16,375][87426] Updated weights for policy 1, policy_version 315630 (0.0012) -[2023-11-28 08:29:16,759][87426] Updated weights for policy 1, policy_version 315640 (0.0011) -[2023-11-28 08:29:18,093][87424] Updated weights for policy 0, policy_version 315879 (0.0008) -[2023-11-28 08:29:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5165.1). Total num frames: 161669120. Throughput: 0: 2728.5, 1: 2698.9. Samples: 161684888. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:29:18,446][86177] Avg episode reward: [(0, '-554.900'), (1, '-645.910')] -[2023-11-28 08:29:18,471][87424] Updated weights for policy 0, policy_version 315889 (0.0009) -[2023-11-28 08:29:18,850][87424] Updated weights for policy 0, policy_version 315899 (0.0008) -[2023-11-28 08:29:18,962][87426] Updated weights for policy 1, policy_version 315650 (0.0009) -[2023-11-28 08:29:19,336][87426] Updated weights for policy 1, policy_version 315660 (0.0011) -[2023-11-28 08:29:19,723][87426] Updated weights for policy 1, policy_version 315670 (0.0011) -[2023-11-28 08:29:20,096][87426] Updated weights for policy 1, policy_version 315680 (0.0012) -[2023-11-28 08:29:20,929][87424] Updated weights for policy 0, policy_version 315909 (0.0010) -[2023-11-28 08:29:21,314][87424] Updated weights for policy 0, policy_version 315919 (0.0012) -[2023-11-28 08:29:21,694][87424] Updated weights for policy 0, policy_version 315929 (0.0012) -[2023-11-28 08:29:22,524][87426] Updated weights for policy 1, policy_version 315690 (0.0012) -[2023-11-28 08:29:22,906][87426] Updated weights for policy 1, policy_version 315700 (0.0012) -[2023-11-28 08:29:23,277][87426] Updated weights for policy 1, policy_version 315710 (0.0010) -[2023-11-28 08:29:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5192.9). Total num frames: 161701888. Throughput: 0: 2735.0, 1: 2677.8. Samples: 161717092. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:29:23,445][86177] Avg episode reward: [(0, '-558.710'), (1, '-593.330')] -[2023-11-28 08:29:23,881][87424] Updated weights for policy 0, policy_version 315939 (0.0012) -[2023-11-28 08:29:24,262][87424] Updated weights for policy 0, policy_version 315949 (0.0012) -[2023-11-28 08:29:24,641][87424] Updated weights for policy 0, policy_version 315959 (0.0012) -[2023-11-28 08:29:25,804][87426] Updated weights for policy 1, policy_version 315720 (0.0008) -[2023-11-28 08:29:26,184][87426] Updated weights for policy 1, policy_version 315730 (0.0007) -[2023-11-28 08:29:26,400][87424] Updated weights for policy 0, policy_version 315969 (0.0012) -[2023-11-28 08:29:26,556][87426] Updated weights for policy 1, policy_version 315740 (0.0008) -[2023-11-28 08:29:26,780][87424] Updated weights for policy 0, policy_version 315979 (0.0009) -[2023-11-28 08:29:27,167][87424] Updated weights for policy 0, policy_version 315989 (0.0007) -[2023-11-28 08:29:27,560][87424] Updated weights for policy 0, policy_version 315999 (0.0007) -[2023-11-28 08:29:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5165.1). Total num frames: 161726464. Throughput: 0: 2748.2, 1: 2642.9. Samples: 161740692. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:29:28,445][86177] Avg episode reward: [(0, '-562.910'), (1, '-553.340')] -[2023-11-28 08:29:29,064][87426] Updated weights for policy 1, policy_version 315750 (0.0008) -[2023-11-28 08:29:29,440][87426] Updated weights for policy 1, policy_version 315760 (0.0007) -[2023-11-28 08:29:29,618][87424] Updated weights for policy 0, policy_version 316009 (0.0011) -[2023-11-28 08:29:29,826][87426] Updated weights for policy 1, policy_version 315770 (0.0008) -[2023-11-28 08:29:29,998][87424] Updated weights for policy 0, policy_version 316019 (0.0010) -[2023-11-28 08:29:30,407][87424] Updated weights for policy 0, policy_version 316029 (0.0007) -[2023-11-28 08:29:32,108][87424] Updated weights for policy 0, policy_version 316039 (0.0011) -[2023-11-28 08:29:32,283][87426] Updated weights for policy 1, policy_version 315780 (0.0011) -[2023-11-28 08:29:32,485][87424] Updated weights for policy 0, policy_version 316049 (0.0011) -[2023-11-28 08:29:32,664][87426] Updated weights for policy 1, policy_version 315790 (0.0011) -[2023-11-28 08:29:32,869][87424] Updated weights for policy 0, policy_version 316059 (0.0009) -[2023-11-28 08:29:33,049][87426] Updated weights for policy 1, policy_version 315800 (0.0011) -[2023-11-28 08:29:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5165.1). Total num frames: 161759232. Throughput: 0: 2772.6, 1: 2623.0. Samples: 161765912. Policy #0 lag: (min: 31.0, avg: 45.9, max: 68.0) -[2023-11-28 08:29:33,445][86177] Avg episode reward: [(0, '-549.290'), (1, '-566.670')] -[2023-11-28 08:29:35,058][87426] Updated weights for policy 1, policy_version 315810 (0.0012) -[2023-11-28 08:29:35,410][87424] Updated weights for policy 0, policy_version 316069 (0.0007) -[2023-11-28 08:29:35,437][87426] Updated weights for policy 1, policy_version 315820 (0.0011) -[2023-11-28 08:29:35,793][87424] Updated weights for policy 0, policy_version 316079 (0.0011) -[2023-11-28 08:29:35,817][87426] Updated weights for policy 1, policy_version 315830 (0.0007) -[2023-11-28 08:29:36,171][87424] Updated weights for policy 0, policy_version 316089 (0.0010) -[2023-11-28 08:29:36,195][87426] Updated weights for policy 1, policy_version 315840 (0.0009) -[2023-11-28 08:29:38,020][87424] Updated weights for policy 0, policy_version 316099 (0.0010) -[2023-11-28 08:29:38,397][87424] Updated weights for policy 0, policy_version 316109 (0.0011) -[2023-11-28 08:29:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5137.4). Total num frames: 161775616. Throughput: 0: 2785.4, 1: 2623.0. Samples: 161799060. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:29:38,445][86177] Avg episode reward: [(0, '-538.710'), (1, '-557.930')] -[2023-11-28 08:29:38,716][87426] Updated weights for policy 1, policy_version 315850 (0.0009) -[2023-11-28 08:29:38,791][87424] Updated weights for policy 0, policy_version 316119 (0.0011) -[2023-11-28 08:29:39,090][87426] Updated weights for policy 1, policy_version 315860 (0.0009) -[2023-11-28 08:29:39,471][87426] Updated weights for policy 1, policy_version 315870 (0.0008) -[2023-11-28 08:29:41,071][87424] Updated weights for policy 0, policy_version 316129 (0.0011) -[2023-11-28 08:29:41,456][87424] Updated weights for policy 0, policy_version 316139 (0.0011) -[2023-11-28 08:29:41,842][87424] Updated weights for policy 0, policy_version 316149 (0.0012) -[2023-11-28 08:29:41,889][87426] Updated weights for policy 1, policy_version 315880 (0.0011) -[2023-11-28 08:29:42,223][87424] Updated weights for policy 0, policy_version 316159 (0.0011) -[2023-11-28 08:29:42,267][87426] Updated weights for policy 1, policy_version 315890 (0.0010) -[2023-11-28 08:29:42,646][87426] Updated weights for policy 1, policy_version 315900 (0.0007) -[2023-11-28 08:29:43,444][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5165.1). Total num frames: 161808384. Throughput: 0: 2783.8, 1: 2613.4. Samples: 161821768. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:29:43,446][86177] Avg episode reward: [(0, '-568.890'), (1, '-578.150')] -[2023-11-28 08:29:44,156][87424] Updated weights for policy 0, policy_version 316169 (0.0012) -[2023-11-28 08:29:44,545][87424] Updated weights for policy 0, policy_version 316179 (0.0011) -[2023-11-28 08:29:44,638][87426] Updated weights for policy 1, policy_version 315910 (0.0010) -[2023-11-28 08:29:44,932][87424] Updated weights for policy 0, policy_version 316189 (0.0012) -[2023-11-28 08:29:45,021][87426] Updated weights for policy 1, policy_version 315920 (0.0012) -[2023-11-28 08:29:45,384][87426] Updated weights for policy 1, policy_version 315930 (0.0011) -[2023-11-28 08:29:46,717][87424] Updated weights for policy 0, policy_version 316199 (0.0012) -[2023-11-28 08:29:47,090][87424] Updated weights for policy 0, policy_version 316209 (0.0012) -[2023-11-28 08:29:47,477][87424] Updated weights for policy 0, policy_version 316219 (0.0012) -[2023-11-28 08:29:47,885][87426] Updated weights for policy 1, policy_version 315940 (0.0010) -[2023-11-28 08:29:48,259][87426] Updated weights for policy 1, policy_version 315950 (0.0011) -[2023-11-28 08:29:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5137.4). Total num frames: 161832960. Throughput: 0: 2779.0, 1: 2628.5. Samples: 161846600. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:29:48,445][86177] Avg episode reward: [(0, '-588.220'), (1, '-581.710')] -[2023-11-28 08:29:48,649][87426] Updated weights for policy 1, policy_version 315960 (0.0012) -[2023-11-28 08:29:49,284][87424] Updated weights for policy 0, policy_version 316229 (0.0010) -[2023-11-28 08:29:49,662][87424] Updated weights for policy 0, policy_version 316239 (0.0007) -[2023-11-28 08:29:50,040][87424] Updated weights for policy 0, policy_version 316249 (0.0009) -[2023-11-28 08:29:51,041][87426] Updated weights for policy 1, policy_version 315970 (0.0011) -[2023-11-28 08:29:51,415][87426] Updated weights for policy 1, policy_version 315980 (0.0011) -[2023-11-28 08:29:51,796][87426] Updated weights for policy 1, policy_version 315990 (0.0009) -[2023-11-28 08:29:52,169][87426] Updated weights for policy 1, policy_version 316000 (0.0008) -[2023-11-28 08:29:52,565][87424] Updated weights for policy 0, policy_version 316259 (0.0011) -[2023-11-28 08:29:52,948][87424] Updated weights for policy 0, policy_version 316269 (0.0011) -[2023-11-28 08:29:53,331][87424] Updated weights for policy 0, policy_version 316279 (0.0011) -[2023-11-28 08:29:53,445][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.9, 300 sec: 5137.4). Total num frames: 161857536. Throughput: 0: 2747.5, 1: 2623.2. Samples: 161878372. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:29:53,446][86177] Avg episode reward: [(0, '-603.860'), (1, '-605.910')] -[2023-11-28 08:29:54,245][87426] Updated weights for policy 1, policy_version 316010 (0.0012) -[2023-11-28 08:29:54,618][87426] Updated weights for policy 1, policy_version 316020 (0.0008) -[2023-11-28 08:29:54,999][87426] Updated weights for policy 1, policy_version 316030 (0.0007) -[2023-11-28 08:29:55,871][87424] Updated weights for policy 0, policy_version 316289 (0.0009) -[2023-11-28 08:29:56,255][87424] Updated weights for policy 0, policy_version 316299 (0.0012) -[2023-11-28 08:29:56,643][87424] Updated weights for policy 0, policy_version 316309 (0.0009) -[2023-11-28 08:29:56,853][87426] Updated weights for policy 1, policy_version 316040 (0.0008) -[2023-11-28 08:29:57,035][87424] Updated weights for policy 0, policy_version 316319 (0.0009) -[2023-11-28 08:29:57,233][87426] Updated weights for policy 1, policy_version 316050 (0.0007) -[2023-11-28 08:29:57,609][87426] Updated weights for policy 1, policy_version 316060 (0.0007) -[2023-11-28 08:29:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5192.9). Total num frames: 161890304. Throughput: 0: 2741.9, 1: 2640.5. Samples: 161903096. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:29:58,446][86177] Avg episode reward: [(0, '-628.370'), (1, '-564.910')] -[2023-11-28 08:29:59,055][87424] Updated weights for policy 0, policy_version 316329 (0.0012) -[2023-11-28 08:29:59,434][87424] Updated weights for policy 0, policy_version 316339 (0.0007) -[2023-11-28 08:29:59,672][87426] Updated weights for policy 1, policy_version 316070 (0.0007) -[2023-11-28 08:29:59,814][87424] Updated weights for policy 0, policy_version 316349 (0.0008) -[2023-11-28 08:30:00,045][87426] Updated weights for policy 1, policy_version 316080 (0.0008) -[2023-11-28 08:30:00,433][87426] Updated weights for policy 1, policy_version 316090 (0.0008) -[2023-11-28 08:30:02,278][87424] Updated weights for policy 0, policy_version 316359 (0.0009) -[2023-11-28 08:30:02,659][87424] Updated weights for policy 0, policy_version 316369 (0.0011) -[2023-11-28 08:30:02,800][87426] Updated weights for policy 1, policy_version 316100 (0.0009) -[2023-11-28 08:30:03,039][87424] Updated weights for policy 0, policy_version 316379 (0.0012) -[2023-11-28 08:30:03,184][87426] Updated weights for policy 1, policy_version 316110 (0.0010) -[2023-11-28 08:30:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5165.1). Total num frames: 161914880. Throughput: 0: 2771.0, 1: 2629.7. Samples: 161927920. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:03,445][86177] Avg episode reward: [(0, '-605.850'), (1, '-599.280')] -[2023-11-28 08:30:03,563][87426] Updated weights for policy 1, policy_version 316120 (0.0012) -[2023-11-28 08:30:05,119][87424] Updated weights for policy 0, policy_version 316389 (0.0011) -[2023-11-28 08:30:05,496][87424] Updated weights for policy 0, policy_version 316399 (0.0012) -[2023-11-28 08:30:05,813][87426] Updated weights for policy 1, policy_version 316130 (0.0012) -[2023-11-28 08:30:05,877][87424] Updated weights for policy 0, policy_version 316409 (0.0011) -[2023-11-28 08:30:06,191][87426] Updated weights for policy 1, policy_version 316140 (0.0009) -[2023-11-28 08:30:06,582][87426] Updated weights for policy 1, policy_version 316150 (0.0007) -[2023-11-28 08:30:06,971][87426] Updated weights for policy 1, policy_version 316160 (0.0011) -[2023-11-28 08:30:08,194][87424] Updated weights for policy 0, policy_version 316419 (0.0012) -[2023-11-28 08:30:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5192.9). Total num frames: 161939456. Throughput: 0: 2760.4, 1: 2640.0. Samples: 161960112. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:08,445][86177] Avg episode reward: [(0, '-610.730'), (1, '-620.800')] -[2023-11-28 08:30:08,577][87424] Updated weights for policy 0, policy_version 316429 (0.0012) -[2023-11-28 08:30:08,923][87426] Updated weights for policy 1, policy_version 316170 (0.0008) -[2023-11-28 08:30:08,947][87424] Updated weights for policy 0, policy_version 316439 (0.0010) -[2023-11-28 08:30:09,302][87426] Updated weights for policy 1, policy_version 316180 (0.0007) -[2023-11-28 08:30:09,695][87426] Updated weights for policy 1, policy_version 316190 (0.0007) -[2023-11-28 08:30:11,136][87424] Updated weights for policy 0, policy_version 316449 (0.0008) -[2023-11-28 08:30:11,505][87424] Updated weights for policy 0, policy_version 316459 (0.0012) -[2023-11-28 08:30:11,630][87426] Updated weights for policy 1, policy_version 316200 (0.0009) -[2023-11-28 08:30:11,878][87424] Updated weights for policy 0, policy_version 316469 (0.0010) -[2023-11-28 08:30:12,005][87426] Updated weights for policy 1, policy_version 316210 (0.0009) -[2023-11-28 08:30:12,259][87424] Updated weights for policy 0, policy_version 316479 (0.0011) -[2023-11-28 08:30:12,390][87426] Updated weights for policy 1, policy_version 316220 (0.0009) -[2023-11-28 08:30:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5220.7). Total num frames: 161972224. Throughput: 0: 2741.3, 1: 2675.9. Samples: 161984468. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:13,445][86177] Avg episode reward: [(0, '-586.390'), (1, '-622.020')] -[2023-11-28 08:30:14,771][87424] Updated weights for policy 0, policy_version 316489 (0.0011) -[2023-11-28 08:30:14,853][87426] Updated weights for policy 1, policy_version 316230 (0.0009) -[2023-11-28 08:30:15,148][87424] Updated weights for policy 0, policy_version 316499 (0.0009) -[2023-11-28 08:30:15,230][87426] Updated weights for policy 1, policy_version 316240 (0.0008) -[2023-11-28 08:30:15,528][87424] Updated weights for policy 0, policy_version 316509 (0.0008) -[2023-11-28 08:30:15,610][87426] Updated weights for policy 1, policy_version 316250 (0.0010) -[2023-11-28 08:30:17,315][87424] Updated weights for policy 0, policy_version 316519 (0.0011) -[2023-11-28 08:30:17,713][87424] Updated weights for policy 0, policy_version 316529 (0.0012) -[2023-11-28 08:30:17,969][87426] Updated weights for policy 1, policy_version 316260 (0.0012) -[2023-11-28 08:30:18,087][87424] Updated weights for policy 0, policy_version 316539 (0.0012) -[2023-11-28 08:30:18,353][87426] Updated weights for policy 1, policy_version 316270 (0.0012) -[2023-11-28 08:30:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5220.7). Total num frames: 161996800. Throughput: 0: 2693.9, 1: 2684.3. Samples: 162007936. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:18,445][86177] Avg episode reward: [(0, '-563.140'), (1, '-605.320')] -[2023-11-28 08:30:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000316544_81035264.pth... -[2023-11-28 08:30:18,483][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000314048_80396288.pth -[2023-11-28 08:30:18,730][87426] Updated weights for policy 1, policy_version 316280 (0.0008) -[2023-11-28 08:30:19,026][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000316288_80969728.pth... -[2023-11-28 08:30:19,057][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000313824_80338944.pth -[2023-11-28 08:30:20,453][87424] Updated weights for policy 0, policy_version 316549 (0.0011) -[2023-11-28 08:30:20,832][87424] Updated weights for policy 0, policy_version 316559 (0.0011) -[2023-11-28 08:30:21,210][87424] Updated weights for policy 0, policy_version 316569 (0.0010) -[2023-11-28 08:30:21,275][87426] Updated weights for policy 1, policy_version 316290 (0.0009) -[2023-11-28 08:30:21,657][87426] Updated weights for policy 1, policy_version 316300 (0.0011) -[2023-11-28 08:30:22,042][87426] Updated weights for policy 1, policy_version 316310 (0.0011) -[2023-11-28 08:30:22,413][87426] Updated weights for policy 1, policy_version 316320 (0.0012) -[2023-11-28 08:30:23,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5220.7). Total num frames: 162021376. Throughput: 0: 2673.8, 1: 2682.1. Samples: 162040076. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:23,446][86177] Avg episode reward: [(0, '-582.520'), (1, '-656.800')] -[2023-11-28 08:30:23,769][87424] Updated weights for policy 0, policy_version 316579 (0.0011) -[2023-11-28 08:30:24,167][87424] Updated weights for policy 0, policy_version 316589 (0.0009) -[2023-11-28 08:30:24,296][87426] Updated weights for policy 1, policy_version 316330 (0.0012) -[2023-11-28 08:30:24,539][87424] Updated weights for policy 0, policy_version 316599 (0.0012) -[2023-11-28 08:30:24,673][87426] Updated weights for policy 1, policy_version 316340 (0.0011) -[2023-11-28 08:30:25,042][87426] Updated weights for policy 1, policy_version 316350 (0.0008) -[2023-11-28 08:30:26,426][87424] Updated weights for policy 0, policy_version 316609 (0.0011) -[2023-11-28 08:30:26,728][87426] Updated weights for policy 1, policy_version 316360 (0.0007) -[2023-11-28 08:30:26,807][87424] Updated weights for policy 0, policy_version 316619 (0.0011) -[2023-11-28 08:30:27,111][87426] Updated weights for policy 1, policy_version 316370 (0.0009) -[2023-11-28 08:30:27,193][87424] Updated weights for policy 0, policy_version 316629 (0.0012) -[2023-11-28 08:30:27,491][87426] Updated weights for policy 1, policy_version 316380 (0.0008) -[2023-11-28 08:30:27,576][87424] Updated weights for policy 0, policy_version 316639 (0.0011) -[2023-11-28 08:30:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5248.5). Total num frames: 162054144. Throughput: 0: 2678.5, 1: 2726.8. Samples: 162065004. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:28,445][86177] Avg episode reward: [(0, '-574.100'), (1, '-631.010')] -[2023-11-28 08:30:29,920][87424] Updated weights for policy 0, policy_version 316649 (0.0010) -[2023-11-28 08:30:29,949][87426] Updated weights for policy 1, policy_version 316390 (0.0009) -[2023-11-28 08:30:30,298][87424] Updated weights for policy 0, policy_version 316659 (0.0009) -[2023-11-28 08:30:30,328][87426] Updated weights for policy 1, policy_version 316400 (0.0012) -[2023-11-28 08:30:30,674][87424] Updated weights for policy 0, policy_version 316669 (0.0009) -[2023-11-28 08:30:30,694][87426] Updated weights for policy 1, policy_version 316410 (0.0011) -[2023-11-28 08:30:32,971][87424] Updated weights for policy 0, policy_version 316679 (0.0010) -[2023-11-28 08:30:33,308][87426] Updated weights for policy 1, policy_version 316420 (0.0011) -[2023-11-28 08:30:33,360][87424] Updated weights for policy 0, policy_version 316689 (0.0011) -[2023-11-28 08:30:33,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.2, 300 sec: 5220.7). Total num frames: 162070528. Throughput: 0: 2670.6, 1: 2708.0. Samples: 162088640. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:33,446][86177] Avg episode reward: [(0, '-566.440'), (1, '-602.960')] -[2023-11-28 08:30:33,691][87426] Updated weights for policy 1, policy_version 316430 (0.0010) -[2023-11-28 08:30:33,733][87424] Updated weights for policy 0, policy_version 316699 (0.0012) -[2023-11-28 08:30:34,056][87426] Updated weights for policy 1, policy_version 316440 (0.0011) -[2023-11-28 08:30:35,819][87424] Updated weights for policy 0, policy_version 316709 (0.0012) -[2023-11-28 08:30:36,004][87426] Updated weights for policy 1, policy_version 316450 (0.0012) -[2023-11-28 08:30:36,208][87424] Updated weights for policy 0, policy_version 316719 (0.0011) -[2023-11-28 08:30:36,388][87426] Updated weights for policy 1, policy_version 316460 (0.0011) -[2023-11-28 08:30:36,583][87424] Updated weights for policy 0, policy_version 316729 (0.0010) -[2023-11-28 08:30:36,764][87426] Updated weights for policy 1, policy_version 316470 (0.0011) -[2023-11-28 08:30:37,139][87426] Updated weights for policy 1, policy_version 316480 (0.0012) -[2023-11-28 08:30:38,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5248.4). Total num frames: 162103296. Throughput: 0: 2677.5, 1: 2702.7. Samples: 162120484. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:38,445][86177] Avg episode reward: [(0, '-560.770'), (1, '-648.010')] -[2023-11-28 08:30:38,841][87424] Updated weights for policy 0, policy_version 316739 (0.0010) -[2023-11-28 08:30:39,222][87424] Updated weights for policy 0, policy_version 316749 (0.0011) -[2023-11-28 08:30:39,605][87424] Updated weights for policy 0, policy_version 316759 (0.0010) -[2023-11-28 08:30:39,633][87426] Updated weights for policy 1, policy_version 316490 (0.0009) -[2023-11-28 08:30:40,012][87426] Updated weights for policy 1, policy_version 316500 (0.0011) -[2023-11-28 08:30:40,384][87426] Updated weights for policy 1, policy_version 316510 (0.0012) -[2023-11-28 08:30:41,770][87424] Updated weights for policy 0, policy_version 316769 (0.0010) -[2023-11-28 08:30:42,161][87424] Updated weights for policy 0, policy_version 316779 (0.0014) -[2023-11-28 08:30:42,532][87424] Updated weights for policy 0, policy_version 316789 (0.0011) -[2023-11-28 08:30:42,714][87426] Updated weights for policy 1, policy_version 316520 (0.0010) -[2023-11-28 08:30:42,923][87424] Updated weights for policy 0, policy_version 316799 (0.0011) -[2023-11-28 08:30:43,091][87426] Updated weights for policy 1, policy_version 316530 (0.0011) -[2023-11-28 08:30:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5248.4). Total num frames: 162127872. Throughput: 0: 2673.9, 1: 2682.4. Samples: 162144128. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:43,445][86177] Avg episode reward: [(0, '-537.690'), (1, '-580.590')] -[2023-11-28 08:30:43,475][87426] Updated weights for policy 1, policy_version 316540 (0.0007) -[2023-11-28 08:30:45,266][87424] Updated weights for policy 0, policy_version 316809 (0.0011) -[2023-11-28 08:30:45,302][87426] Updated weights for policy 1, policy_version 316550 (0.0011) -[2023-11-28 08:30:45,649][87424] Updated weights for policy 0, policy_version 316819 (0.0014) -[2023-11-28 08:30:45,679][87426] Updated weights for policy 1, policy_version 316560 (0.0010) -[2023-11-28 08:30:46,025][87424] Updated weights for policy 0, policy_version 316829 (0.0009) -[2023-11-28 08:30:46,055][87426] Updated weights for policy 1, policy_version 316570 (0.0007) -[2023-11-28 08:30:47,991][87424] Updated weights for policy 0, policy_version 316839 (0.0007) -[2023-11-28 08:30:48,375][87424] Updated weights for policy 0, policy_version 316849 (0.0007) -[2023-11-28 08:30:48,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5248.4). Total num frames: 162152448. Throughput: 0: 2650.2, 1: 2681.6. Samples: 162167852. Policy #0 lag: (min: 20.0, avg: 47.5, max: 80.0) -[2023-11-28 08:30:48,445][86177] Avg episode reward: [(0, '-531.510'), (1, '-583.070')] -[2023-11-28 08:30:48,508][87426] Updated weights for policy 1, policy_version 316580 (0.0009) -[2023-11-28 08:30:48,750][87424] Updated weights for policy 0, policy_version 316859 (0.0007) -[2023-11-28 08:30:48,886][87426] Updated weights for policy 1, policy_version 316590 (0.0009) -[2023-11-28 08:30:49,265][87426] Updated weights for policy 1, policy_version 316600 (0.0007) -[2023-11-28 08:30:51,001][87424] Updated weights for policy 0, policy_version 316869 (0.0010) -[2023-11-28 08:30:51,385][87424] Updated weights for policy 0, policy_version 316879 (0.0011) -[2023-11-28 08:30:51,611][87426] Updated weights for policy 1, policy_version 316610 (0.0008) -[2023-11-28 08:30:51,759][87424] Updated weights for policy 0, policy_version 316889 (0.0012) -[2023-11-28 08:30:51,986][87426] Updated weights for policy 1, policy_version 316620 (0.0011) -[2023-11-28 08:30:52,364][87426] Updated weights for policy 1, policy_version 316630 (0.0012) -[2023-11-28 08:30:52,739][87426] Updated weights for policy 1, policy_version 316640 (0.0012) -[2023-11-28 08:30:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5276.2). Total num frames: 162185216. Throughput: 0: 2651.8, 1: 2699.6. Samples: 162200924. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:30:53,445][86177] Avg episode reward: [(0, '-531.580'), (1, '-596.200')] -[2023-11-28 08:30:53,864][87424] Updated weights for policy 0, policy_version 316899 (0.0010) -[2023-11-28 08:30:54,248][87424] Updated weights for policy 0, policy_version 316909 (0.0011) -[2023-11-28 08:30:54,631][87424] Updated weights for policy 0, policy_version 316919 (0.0012) -[2023-11-28 08:30:55,039][87426] Updated weights for policy 1, policy_version 316650 (0.0012) -[2023-11-28 08:30:55,417][87426] Updated weights for policy 1, policy_version 316660 (0.0010) -[2023-11-28 08:30:55,805][87426] Updated weights for policy 1, policy_version 316670 (0.0007) -[2023-11-28 08:30:56,990][87424] Updated weights for policy 0, policy_version 316929 (0.0012) -[2023-11-28 08:30:57,374][87424] Updated weights for policy 0, policy_version 316939 (0.0012) -[2023-11-28 08:30:57,744][87424] Updated weights for policy 0, policy_version 316949 (0.0010) -[2023-11-28 08:30:57,893][87426] Updated weights for policy 1, policy_version 316680 (0.0011) -[2023-11-28 08:30:58,124][87424] Updated weights for policy 0, policy_version 316959 (0.0008) -[2023-11-28 08:30:58,268][87426] Updated weights for policy 1, policy_version 316690 (0.0010) -[2023-11-28 08:30:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5276.2). Total num frames: 162209792. Throughput: 0: 2651.1, 1: 2703.5. Samples: 162225424. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:30:58,445][86177] Avg episode reward: [(0, '-529.780'), (1, '-573.560')] -[2023-11-28 08:30:58,656][87426] Updated weights for policy 1, policy_version 316700 (0.0007) -[2023-11-28 08:31:00,103][87424] Updated weights for policy 0, policy_version 316969 (0.0008) -[2023-11-28 08:31:00,489][87424] Updated weights for policy 0, policy_version 316979 (0.0008) -[2023-11-28 08:31:00,661][87426] Updated weights for policy 1, policy_version 316710 (0.0011) -[2023-11-28 08:31:00,866][87424] Updated weights for policy 0, policy_version 316989 (0.0007) -[2023-11-28 08:31:01,033][87426] Updated weights for policy 1, policy_version 316720 (0.0012) -[2023-11-28 08:31:01,408][87426] Updated weights for policy 1, policy_version 316730 (0.0012) -[2023-11-28 08:31:03,166][87424] Updated weights for policy 0, policy_version 316999 (0.0008) -[2023-11-28 08:31:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5276.2). Total num frames: 162234368. Throughput: 0: 2673.6, 1: 2698.5. Samples: 162249680. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:03,445][86177] Avg episode reward: [(0, '-530.200'), (1, '-541.990')] -[2023-11-28 08:31:03,466][87426] Updated weights for policy 1, policy_version 316740 (0.0010) -[2023-11-28 08:31:03,552][87424] Updated weights for policy 0, policy_version 317009 (0.0009) -[2023-11-28 08:31:03,847][87426] Updated weights for policy 1, policy_version 316750 (0.0007) -[2023-11-28 08:31:03,937][87424] Updated weights for policy 0, policy_version 317019 (0.0008) -[2023-11-28 08:31:04,225][87426] Updated weights for policy 1, policy_version 316760 (0.0009) -[2023-11-28 08:31:06,036][87424] Updated weights for policy 0, policy_version 317029 (0.0011) -[2023-11-28 08:31:06,415][87424] Updated weights for policy 0, policy_version 317039 (0.0008) -[2023-11-28 08:31:06,716][87426] Updated weights for policy 1, policy_version 316770 (0.0012) -[2023-11-28 08:31:06,789][87424] Updated weights for policy 0, policy_version 317049 (0.0009) -[2023-11-28 08:31:07,097][87426] Updated weights for policy 1, policy_version 316780 (0.0009) -[2023-11-28 08:31:07,486][87426] Updated weights for policy 1, policy_version 316790 (0.0009) -[2023-11-28 08:31:07,857][87426] Updated weights for policy 1, policy_version 316800 (0.0008) -[2023-11-28 08:31:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5304.0). Total num frames: 162267136. Throughput: 0: 2682.5, 1: 2706.4. Samples: 162282576. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:08,446][86177] Avg episode reward: [(0, '-533.960'), (1, '-529.650')] -[2023-11-28 08:31:08,698][87424] Updated weights for policy 0, policy_version 317059 (0.0011) -[2023-11-28 08:31:09,068][87424] Updated weights for policy 0, policy_version 317069 (0.0010) -[2023-11-28 08:31:09,458][87424] Updated weights for policy 0, policy_version 317079 (0.0010) -[2023-11-28 08:31:09,896][87426] Updated weights for policy 1, policy_version 316810 (0.0011) -[2023-11-28 08:31:10,276][87426] Updated weights for policy 1, policy_version 316820 (0.0012) -[2023-11-28 08:31:10,660][87426] Updated weights for policy 1, policy_version 316830 (0.0012) -[2023-11-28 08:31:11,669][87424] Updated weights for policy 0, policy_version 317089 (0.0009) -[2023-11-28 08:31:12,044][87424] Updated weights for policy 0, policy_version 317099 (0.0012) -[2023-11-28 08:31:12,432][87424] Updated weights for policy 0, policy_version 317109 (0.0012) -[2023-11-28 08:31:12,815][87424] Updated weights for policy 0, policy_version 317119 (0.0012) -[2023-11-28 08:31:13,154][87426] Updated weights for policy 1, policy_version 316840 (0.0011) -[2023-11-28 08:31:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 162291712. Throughput: 0: 2696.6, 1: 2690.1. Samples: 162307408. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:13,445][86177] Avg episode reward: [(0, '-536.170'), (1, '-522.340')] -[2023-11-28 08:31:13,538][87426] Updated weights for policy 1, policy_version 316850 (0.0008) -[2023-11-28 08:31:13,912][87426] Updated weights for policy 1, policy_version 316860 (0.0011) -[2023-11-28 08:31:14,837][87424] Updated weights for policy 0, policy_version 317129 (0.0012) -[2023-11-28 08:31:15,207][87424] Updated weights for policy 0, policy_version 317139 (0.0009) -[2023-11-28 08:31:15,585][87424] Updated weights for policy 0, policy_version 317149 (0.0010) -[2023-11-28 08:31:15,688][87426] Updated weights for policy 1, policy_version 316870 (0.0011) -[2023-11-28 08:31:16,067][87426] Updated weights for policy 1, policy_version 316880 (0.0011) -[2023-11-28 08:31:16,441][87426] Updated weights for policy 1, policy_version 316890 (0.0011) -[2023-11-28 08:31:17,921][87424] Updated weights for policy 0, policy_version 317159 (0.0009) -[2023-11-28 08:31:18,303][87426] Updated weights for policy 1, policy_version 316900 (0.0010) -[2023-11-28 08:31:18,312][87424] Updated weights for policy 0, policy_version 317169 (0.0007) -[2023-11-28 08:31:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 162316288. Throughput: 0: 2713.0, 1: 2699.1. Samples: 162332184. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:18,445][86177] Avg episode reward: [(0, '-538.650'), (1, '-538.100')] -[2023-11-28 08:31:18,681][87426] Updated weights for policy 1, policy_version 316910 (0.0010) -[2023-11-28 08:31:18,689][87424] Updated weights for policy 0, policy_version 317179 (0.0010) -[2023-11-28 08:31:19,064][87426] Updated weights for policy 1, policy_version 316920 (0.0011) -[2023-11-28 08:31:20,660][87424] Updated weights for policy 0, policy_version 317189 (0.0008) -[2023-11-28 08:31:21,036][87424] Updated weights for policy 0, policy_version 317199 (0.0008) -[2023-11-28 08:31:21,417][87424] Updated weights for policy 0, policy_version 317209 (0.0011) -[2023-11-28 08:31:21,550][87426] Updated weights for policy 1, policy_version 316930 (0.0012) -[2023-11-28 08:31:21,922][87426] Updated weights for policy 1, policy_version 316940 (0.0012) -[2023-11-28 08:31:22,307][87426] Updated weights for policy 1, policy_version 316950 (0.0012) -[2023-11-28 08:31:22,678][87426] Updated weights for policy 1, policy_version 316960 (0.0012) -[2023-11-28 08:31:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5331.7). Total num frames: 162349056. Throughput: 0: 2716.2, 1: 2715.0. Samples: 162364884. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:23,445][86177] Avg episode reward: [(0, '-537.000'), (1, '-531.670')] -[2023-11-28 08:31:23,757][87424] Updated weights for policy 0, policy_version 317219 (0.0011) -[2023-11-28 08:31:24,134][87424] Updated weights for policy 0, policy_version 317229 (0.0011) -[2023-11-28 08:31:24,520][87424] Updated weights for policy 0, policy_version 317239 (0.0011) -[2023-11-28 08:31:25,160][87426] Updated weights for policy 1, policy_version 316970 (0.0011) -[2023-11-28 08:31:25,534][87426] Updated weights for policy 1, policy_version 316980 (0.0012) -[2023-11-28 08:31:25,919][87426] Updated weights for policy 1, policy_version 316990 (0.0012) -[2023-11-28 08:31:26,322][87424] Updated weights for policy 0, policy_version 317249 (0.0011) -[2023-11-28 08:31:26,717][87424] Updated weights for policy 0, policy_version 317259 (0.0011) -[2023-11-28 08:31:27,085][87424] Updated weights for policy 0, policy_version 317269 (0.0007) -[2023-11-28 08:31:27,465][87424] Updated weights for policy 0, policy_version 317279 (0.0007) -[2023-11-28 08:31:27,976][87426] Updated weights for policy 1, policy_version 317000 (0.0009) -[2023-11-28 08:31:28,358][87426] Updated weights for policy 1, policy_version 317010 (0.0007) -[2023-11-28 08:31:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 162373632. Throughput: 0: 2735.0, 1: 2735.2. Samples: 162390288. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:28,445][86177] Avg episode reward: [(0, '-531.150'), (1, '-526.080')] -[2023-11-28 08:31:28,740][87426] Updated weights for policy 1, policy_version 317020 (0.0007) -[2023-11-28 08:31:29,954][87424] Updated weights for policy 0, policy_version 317289 (0.0010) -[2023-11-28 08:31:30,336][87424] Updated weights for policy 0, policy_version 317299 (0.0011) -[2023-11-28 08:31:30,595][87426] Updated weights for policy 1, policy_version 317030 (0.0011) -[2023-11-28 08:31:30,722][87424] Updated weights for policy 0, policy_version 317309 (0.0012) -[2023-11-28 08:31:30,967][87426] Updated weights for policy 1, policy_version 317040 (0.0011) -[2023-11-28 08:31:31,350][87426] Updated weights for policy 1, policy_version 317050 (0.0012) -[2023-11-28 08:31:32,513][87424] Updated weights for policy 0, policy_version 317319 (0.0009) -[2023-11-28 08:31:32,899][87424] Updated weights for policy 0, policy_version 317329 (0.0008) -[2023-11-28 08:31:33,276][87424] Updated weights for policy 0, policy_version 317339 (0.0007) -[2023-11-28 08:31:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5331.7). Total num frames: 162398208. Throughput: 0: 2757.9, 1: 2731.0. Samples: 162414852. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:33,445][86177] Avg episode reward: [(0, '-524.920'), (1, '-572.950')] -[2023-11-28 08:31:33,903][87426] Updated weights for policy 1, policy_version 317060 (0.0010) -[2023-11-28 08:31:34,273][87426] Updated weights for policy 1, policy_version 317070 (0.0008) -[2023-11-28 08:31:34,656][87426] Updated weights for policy 1, policy_version 317080 (0.0008) -[2023-11-28 08:31:35,085][87424] Updated weights for policy 0, policy_version 317349 (0.0008) -[2023-11-28 08:31:35,464][87424] Updated weights for policy 0, policy_version 317359 (0.0012) -[2023-11-28 08:31:35,844][87424] Updated weights for policy 0, policy_version 317369 (0.0012) -[2023-11-28 08:31:36,564][87426] Updated weights for policy 1, policy_version 317090 (0.0010) -[2023-11-28 08:31:36,941][87426] Updated weights for policy 1, policy_version 317100 (0.0012) -[2023-11-28 08:31:37,316][87426] Updated weights for policy 1, policy_version 317110 (0.0012) -[2023-11-28 08:31:37,694][87426] Updated weights for policy 1, policy_version 317120 (0.0012) -[2023-11-28 08:31:38,160][87424] Updated weights for policy 0, policy_version 317379 (0.0009) -[2023-11-28 08:31:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5359.5). Total num frames: 162430976. Throughput: 0: 2786.3, 1: 2692.4. Samples: 162447468. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:38,445][86177] Avg episode reward: [(0, '-522.410'), (1, '-559.750')] -[2023-11-28 08:31:38,546][87424] Updated weights for policy 0, policy_version 317389 (0.0007) -[2023-11-28 08:31:38,939][87424] Updated weights for policy 0, policy_version 317399 (0.0008) -[2023-11-28 08:31:40,106][87426] Updated weights for policy 1, policy_version 317130 (0.0008) -[2023-11-28 08:31:40,492][87426] Updated weights for policy 1, policy_version 317140 (0.0008) -[2023-11-28 08:31:40,871][87426] Updated weights for policy 1, policy_version 317150 (0.0008) -[2023-11-28 08:31:41,179][87424] Updated weights for policy 0, policy_version 317409 (0.0011) -[2023-11-28 08:31:41,563][87424] Updated weights for policy 0, policy_version 317419 (0.0011) -[2023-11-28 08:31:41,944][87424] Updated weights for policy 0, policy_version 317429 (0.0010) -[2023-11-28 08:31:42,323][87424] Updated weights for policy 0, policy_version 317439 (0.0009) -[2023-11-28 08:31:43,111][87426] Updated weights for policy 1, policy_version 317160 (0.0008) -[2023-11-28 08:31:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 162455552. Throughput: 0: 2794.4, 1: 2684.6. Samples: 162471980. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:43,445][86177] Avg episode reward: [(0, '-527.220'), (1, '-591.730')] -[2023-11-28 08:31:43,488][87426] Updated weights for policy 1, policy_version 317170 (0.0009) -[2023-11-28 08:31:43,875][87426] Updated weights for policy 1, policy_version 317180 (0.0010) -[2023-11-28 08:31:44,541][87424] Updated weights for policy 0, policy_version 317449 (0.0011) -[2023-11-28 08:31:44,922][87424] Updated weights for policy 0, policy_version 317459 (0.0011) -[2023-11-28 08:31:45,298][87424] Updated weights for policy 0, policy_version 317469 (0.0009) -[2023-11-28 08:31:46,296][87426] Updated weights for policy 1, policy_version 317190 (0.0010) -[2023-11-28 08:31:46,673][87426] Updated weights for policy 1, policy_version 317200 (0.0012) -[2023-11-28 08:31:47,049][87426] Updated weights for policy 1, policy_version 317210 (0.0012) -[2023-11-28 08:31:47,517][87424] Updated weights for policy 0, policy_version 317479 (0.0008) -[2023-11-28 08:31:47,899][87424] Updated weights for policy 0, policy_version 317489 (0.0008) -[2023-11-28 08:31:48,286][87424] Updated weights for policy 0, policy_version 317499 (0.0009) -[2023-11-28 08:31:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 162480128. Throughput: 0: 2769.2, 1: 2695.7. Samples: 162495604. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:48,445][86177] Avg episode reward: [(0, '-534.300'), (1, '-600.150')] -[2023-11-28 08:31:49,130][87426] Updated weights for policy 1, policy_version 317220 (0.0012) -[2023-11-28 08:31:49,513][87426] Updated weights for policy 1, policy_version 317230 (0.0011) -[2023-11-28 08:31:49,885][87426] Updated weights for policy 1, policy_version 317240 (0.0011) -[2023-11-28 08:31:50,543][87424] Updated weights for policy 0, policy_version 317509 (0.0009) -[2023-11-28 08:31:50,924][87424] Updated weights for policy 0, policy_version 317519 (0.0012) -[2023-11-28 08:31:51,303][87424] Updated weights for policy 0, policy_version 317529 (0.0012) -[2023-11-28 08:31:52,132][87426] Updated weights for policy 1, policy_version 317250 (0.0011) -[2023-11-28 08:31:52,509][87426] Updated weights for policy 1, policy_version 317260 (0.0011) -[2023-11-28 08:31:52,889][87426] Updated weights for policy 1, policy_version 317270 (0.0012) -[2023-11-28 08:31:53,178][87424] Updated weights for policy 0, policy_version 317539 (0.0012) -[2023-11-28 08:31:53,268][87426] Updated weights for policy 1, policy_version 317280 (0.0011) -[2023-11-28 08:31:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 162512896. Throughput: 0: 2774.1, 1: 2686.1. Samples: 162528280. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:53,445][86177] Avg episode reward: [(0, '-538.580'), (1, '-583.780')] -[2023-11-28 08:31:53,567][87424] Updated weights for policy 0, policy_version 317549 (0.0010) -[2023-11-28 08:31:53,951][87424] Updated weights for policy 0, policy_version 317559 (0.0010) -[2023-11-28 08:31:55,435][87426] Updated weights for policy 1, policy_version 317290 (0.0012) -[2023-11-28 08:31:55,815][87426] Updated weights for policy 1, policy_version 317300 (0.0008) -[2023-11-28 08:31:55,993][87424] Updated weights for policy 0, policy_version 317569 (0.0011) -[2023-11-28 08:31:56,189][87426] Updated weights for policy 1, policy_version 317310 (0.0009) -[2023-11-28 08:31:56,385][87424] Updated weights for policy 0, policy_version 317579 (0.0012) -[2023-11-28 08:31:56,763][87424] Updated weights for policy 0, policy_version 317589 (0.0012) -[2023-11-28 08:31:57,149][87424] Updated weights for policy 0, policy_version 317599 (0.0012) -[2023-11-28 08:31:57,954][87426] Updated weights for policy 1, policy_version 317320 (0.0011) -[2023-11-28 08:31:58,325][87426] Updated weights for policy 1, policy_version 317330 (0.0012) -[2023-11-28 08:31:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 162537472. Throughput: 0: 2772.6, 1: 2694.5. Samples: 162553428. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:31:58,445][86177] Avg episode reward: [(0, '-538.910'), (1, '-586.430')] -[2023-11-28 08:31:58,705][87426] Updated weights for policy 1, policy_version 317340 (0.0012) -[2023-11-28 08:31:59,238][87424] Updated weights for policy 0, policy_version 317609 (0.0008) -[2023-11-28 08:31:59,620][87424] Updated weights for policy 0, policy_version 317619 (0.0008) -[2023-11-28 08:32:00,011][87424] Updated weights for policy 0, policy_version 317629 (0.0010) -[2023-11-28 08:32:01,241][87426] Updated weights for policy 1, policy_version 317350 (0.0010) -[2023-11-28 08:32:01,616][87426] Updated weights for policy 1, policy_version 317360 (0.0008) -[2023-11-28 08:32:01,994][87426] Updated weights for policy 1, policy_version 317370 (0.0010) -[2023-11-28 08:32:02,088][87424] Updated weights for policy 0, policy_version 317639 (0.0010) -[2023-11-28 08:32:02,474][87424] Updated weights for policy 0, policy_version 317649 (0.0009) -[2023-11-28 08:32:02,850][87424] Updated weights for policy 0, policy_version 317659 (0.0010) -[2023-11-28 08:32:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 162570240. Throughput: 0: 2778.9, 1: 2699.9. Samples: 162578732. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:32:03,445][86177] Avg episode reward: [(0, '-534.700'), (1, '-547.040')] -[2023-11-28 08:32:04,198][87426] Updated weights for policy 1, policy_version 317380 (0.0010) -[2023-11-28 08:32:04,584][87426] Updated weights for policy 1, policy_version 317390 (0.0010) -[2023-11-28 08:32:04,774][87424] Updated weights for policy 0, policy_version 317669 (0.0011) -[2023-11-28 08:32:04,963][87426] Updated weights for policy 1, policy_version 317400 (0.0011) -[2023-11-28 08:32:05,167][87424] Updated weights for policy 0, policy_version 317679 (0.0011) -[2023-11-28 08:32:05,544][87424] Updated weights for policy 0, policy_version 317689 (0.0011) -[2023-11-28 08:32:07,345][87426] Updated weights for policy 1, policy_version 317410 (0.0012) -[2023-11-28 08:32:07,471][87424] Updated weights for policy 0, policy_version 317699 (0.0011) -[2023-11-28 08:32:07,723][87426] Updated weights for policy 1, policy_version 317420 (0.0011) -[2023-11-28 08:32:07,859][87424] Updated weights for policy 0, policy_version 317709 (0.0012) -[2023-11-28 08:32:08,106][87426] Updated weights for policy 1, policy_version 317430 (0.0010) -[2023-11-28 08:32:08,241][87424] Updated weights for policy 0, policy_version 317719 (0.0011) -[2023-11-28 08:32:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 162586624. Throughput: 0: 2802.0, 1: 2704.2. Samples: 162612660. Policy #0 lag: (min: 31.0, avg: 52.6, max: 91.0) -[2023-11-28 08:32:08,445][86177] Avg episode reward: [(0, '-525.220'), (1, '-538.320')] -[2023-11-28 08:32:08,487][87426] Updated weights for policy 1, policy_version 317440 (0.0011) -[2023-11-28 08:32:10,284][87426] Updated weights for policy 1, policy_version 317450 (0.0009) -[2023-11-28 08:32:10,599][87424] Updated weights for policy 0, policy_version 317729 (0.0012) -[2023-11-28 08:32:10,664][87426] Updated weights for policy 1, policy_version 317460 (0.0010) -[2023-11-28 08:32:10,978][87424] Updated weights for policy 0, policy_version 317739 (0.0011) -[2023-11-28 08:32:11,037][87426] Updated weights for policy 1, policy_version 317470 (0.0016) -[2023-11-28 08:32:11,359][87424] Updated weights for policy 0, policy_version 317749 (0.0011) -[2023-11-28 08:32:11,741][87424] Updated weights for policy 0, policy_version 317759 (0.0010) -[2023-11-28 08:32:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 162619392. Throughput: 0: 2790.1, 1: 2696.6. Samples: 162637188. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:13,445][86177] Avg episode reward: [(0, '-520.680'), (1, '-545.300')] -[2023-11-28 08:32:13,500][87426] Updated weights for policy 1, policy_version 317480 (0.0012) -[2023-11-28 08:32:13,761][87424] Updated weights for policy 0, policy_version 317769 (0.0010) -[2023-11-28 08:32:13,873][87426] Updated weights for policy 1, policy_version 317490 (0.0011) -[2023-11-28 08:32:14,145][87424] Updated weights for policy 0, policy_version 317779 (0.0010) -[2023-11-28 08:32:14,251][87426] Updated weights for policy 1, policy_version 317500 (0.0011) -[2023-11-28 08:32:14,531][87424] Updated weights for policy 0, policy_version 317789 (0.0007) -[2023-11-28 08:32:16,725][87426] Updated weights for policy 1, policy_version 317510 (0.0009) -[2023-11-28 08:32:16,769][87424] Updated weights for policy 0, policy_version 317799 (0.0010) -[2023-11-28 08:32:17,107][87426] Updated weights for policy 1, policy_version 317520 (0.0007) -[2023-11-28 08:32:17,149][87424] Updated weights for policy 0, policy_version 317809 (0.0011) -[2023-11-28 08:32:17,484][87426] Updated weights for policy 1, policy_version 317530 (0.0008) -[2023-11-28 08:32:17,530][87424] Updated weights for policy 0, policy_version 317819 (0.0008) -[2023-11-28 08:32:18,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 162652160. Throughput: 0: 2788.8, 1: 2699.5. Samples: 162661824. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:18,446][86177] Avg episode reward: [(0, '-520.760'), (1, '-544.030')] -[2023-11-28 08:32:18,458][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000317536_81289216.pth... -[2023-11-28 08:32:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000317824_81362944.pth... -[2023-11-28 08:32:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000315264_80707584.pth -[2023-11-28 08:32:18,497][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000317824_81362944.pth -[2023-11-28 08:32:18,498][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000315040_80650240.pth -[2023-11-28 08:32:18,504][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000317536_81289216.pth -[2023-11-28 08:32:19,513][87424] Updated weights for policy 0, policy_version 317829 (0.0010) -[2023-11-28 08:32:19,708][87426] Updated weights for policy 1, policy_version 317540 (0.0008) -[2023-11-28 08:32:19,892][87424] Updated weights for policy 0, policy_version 317839 (0.0010) -[2023-11-28 08:32:20,079][87426] Updated weights for policy 1, policy_version 317550 (0.0011) -[2023-11-28 08:32:20,273][87424] Updated weights for policy 0, policy_version 317849 (0.0008) -[2023-11-28 08:32:20,462][87426] Updated weights for policy 1, policy_version 317560 (0.0012) -[2023-11-28 08:32:22,191][87424] Updated weights for policy 0, policy_version 317859 (0.0010) -[2023-11-28 08:32:22,565][87424] Updated weights for policy 0, policy_version 317869 (0.0009) -[2023-11-28 08:32:22,855][87426] Updated weights for policy 1, policy_version 317570 (0.0011) -[2023-11-28 08:32:22,948][87424] Updated weights for policy 0, policy_version 317879 (0.0010) -[2023-11-28 08:32:23,236][87426] Updated weights for policy 1, policy_version 317580 (0.0008) -[2023-11-28 08:32:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 162676736. Throughput: 0: 2752.5, 1: 2708.8. Samples: 162693224. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:23,445][86177] Avg episode reward: [(0, '-518.480'), (1, '-548.540')] -[2023-11-28 08:32:23,608][87426] Updated weights for policy 1, policy_version 317590 (0.0010) -[2023-11-28 08:32:23,992][87426] Updated weights for policy 1, policy_version 317600 (0.0011) -[2023-11-28 08:32:25,394][87424] Updated weights for policy 0, policy_version 317889 (0.0012) -[2023-11-28 08:32:25,774][87424] Updated weights for policy 0, policy_version 317899 (0.0012) -[2023-11-28 08:32:26,148][87424] Updated weights for policy 0, policy_version 317909 (0.0012) -[2023-11-28 08:32:26,274][87426] Updated weights for policy 1, policy_version 317610 (0.0011) -[2023-11-28 08:32:26,540][87424] Updated weights for policy 0, policy_version 317919 (0.0012) -[2023-11-28 08:32:26,648][87426] Updated weights for policy 1, policy_version 317620 (0.0012) -[2023-11-28 08:32:27,034][87426] Updated weights for policy 1, policy_version 317630 (0.0011) -[2023-11-28 08:32:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 162701312. Throughput: 0: 2748.3, 1: 2724.0. Samples: 162718232. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:28,446][86177] Avg episode reward: [(0, '-519.720'), (1, '-552.410')] -[2023-11-28 08:32:28,576][87424] Updated weights for policy 0, policy_version 317929 (0.0011) -[2023-11-28 08:32:28,855][87426] Updated weights for policy 1, policy_version 317640 (0.0011) -[2023-11-28 08:32:28,954][87424] Updated weights for policy 0, policy_version 317939 (0.0010) -[2023-11-28 08:32:29,232][87426] Updated weights for policy 1, policy_version 317650 (0.0008) -[2023-11-28 08:32:29,338][87424] Updated weights for policy 0, policy_version 317949 (0.0010) -[2023-11-28 08:32:29,607][87426] Updated weights for policy 1, policy_version 317660 (0.0007) -[2023-11-28 08:32:31,405][87426] Updated weights for policy 1, policy_version 317670 (0.0009) -[2023-11-28 08:32:31,554][87424] Updated weights for policy 0, policy_version 317959 (0.0011) -[2023-11-28 08:32:31,779][87426] Updated weights for policy 1, policy_version 317680 (0.0011) -[2023-11-28 08:32:31,941][87424] Updated weights for policy 0, policy_version 317969 (0.0012) -[2023-11-28 08:32:32,158][87426] Updated weights for policy 1, policy_version 317690 (0.0012) -[2023-11-28 08:32:32,320][87424] Updated weights for policy 0, policy_version 317979 (0.0011) -[2023-11-28 08:32:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 162734080. Throughput: 0: 2780.5, 1: 2724.4. Samples: 162743324. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:33,445][86177] Avg episode reward: [(0, '-515.760'), (1, '-551.420')] -[2023-11-28 08:32:34,189][87426] Updated weights for policy 1, policy_version 317700 (0.0010) -[2023-11-28 08:32:34,568][87426] Updated weights for policy 1, policy_version 317710 (0.0008) -[2023-11-28 08:32:34,601][87424] Updated weights for policy 0, policy_version 317989 (0.0009) -[2023-11-28 08:32:34,949][87426] Updated weights for policy 1, policy_version 317720 (0.0008) -[2023-11-28 08:32:34,981][87424] Updated weights for policy 0, policy_version 317999 (0.0012) -[2023-11-28 08:32:35,359][87424] Updated weights for policy 0, policy_version 318009 (0.0011) -[2023-11-28 08:32:36,503][87426] Updated weights for policy 1, policy_version 317730 (0.0008) -[2023-11-28 08:32:36,891][87426] Updated weights for policy 1, policy_version 317740 (0.0011) -[2023-11-28 08:32:37,271][87426] Updated weights for policy 1, policy_version 317750 (0.0009) -[2023-11-28 08:32:37,481][87424] Updated weights for policy 0, policy_version 318019 (0.0011) -[2023-11-28 08:32:37,646][87426] Updated weights for policy 1, policy_version 317760 (0.0010) -[2023-11-28 08:32:37,863][87424] Updated weights for policy 0, policy_version 318029 (0.0009) -[2023-11-28 08:32:38,256][87424] Updated weights for policy 0, policy_version 318039 (0.0008) -[2023-11-28 08:32:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 162758656. Throughput: 0: 2781.1, 1: 2736.6. Samples: 162776576. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:38,446][86177] Avg episode reward: [(0, '-516.110'), (1, '-543.450')] -[2023-11-28 08:32:40,032][87426] Updated weights for policy 1, policy_version 317770 (0.0011) -[2023-11-28 08:32:40,110][87424] Updated weights for policy 0, policy_version 318049 (0.0009) -[2023-11-28 08:32:40,408][87426] Updated weights for policy 1, policy_version 317780 (0.0010) -[2023-11-28 08:32:40,497][87424] Updated weights for policy 0, policy_version 318059 (0.0011) -[2023-11-28 08:32:40,795][87426] Updated weights for policy 1, policy_version 317790 (0.0011) -[2023-11-28 08:32:40,876][87424] Updated weights for policy 0, policy_version 318069 (0.0012) -[2023-11-28 08:32:41,260][87424] Updated weights for policy 0, policy_version 318079 (0.0012) -[2023-11-28 08:32:43,040][87426] Updated weights for policy 1, policy_version 317800 (0.0010) -[2023-11-28 08:32:43,424][87426] Updated weights for policy 1, policy_version 317810 (0.0008) -[2023-11-28 08:32:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 162783232. Throughput: 0: 2771.6, 1: 2731.6. Samples: 162801076. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:43,445][86177] Avg episode reward: [(0, '-519.910'), (1, '-551.300')] -[2023-11-28 08:32:43,803][87426] Updated weights for policy 1, policy_version 317820 (0.0008) -[2023-11-28 08:32:43,907][87424] Updated weights for policy 0, policy_version 318089 (0.0011) -[2023-11-28 08:32:44,287][87424] Updated weights for policy 0, policy_version 318099 (0.0012) -[2023-11-28 08:32:44,668][87424] Updated weights for policy 0, policy_version 318109 (0.0012) -[2023-11-28 08:32:46,289][87426] Updated weights for policy 1, policy_version 317830 (0.0010) -[2023-11-28 08:32:46,672][87426] Updated weights for policy 1, policy_version 317840 (0.0012) -[2023-11-28 08:32:47,047][87426] Updated weights for policy 1, policy_version 317850 (0.0011) -[2023-11-28 08:32:47,305][87424] Updated weights for policy 0, policy_version 318119 (0.0011) -[2023-11-28 08:32:47,689][87424] Updated weights for policy 0, policy_version 318129 (0.0012) -[2023-11-28 08:32:48,074][87424] Updated weights for policy 0, policy_version 318139 (0.0012) -[2023-11-28 08:32:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 162816000. Throughput: 0: 2745.7, 1: 2715.7. Samples: 162824496. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:48,445][86177] Avg episode reward: [(0, '-519.770'), (1, '-556.260')] -[2023-11-28 08:32:49,114][87426] Updated weights for policy 1, policy_version 317860 (0.0012) -[2023-11-28 08:32:49,495][87426] Updated weights for policy 1, policy_version 317870 (0.0012) -[2023-11-28 08:32:49,866][87426] Updated weights for policy 1, policy_version 317880 (0.0012) -[2023-11-28 08:32:50,269][87424] Updated weights for policy 0, policy_version 318149 (0.0010) -[2023-11-28 08:32:50,652][87424] Updated weights for policy 0, policy_version 318159 (0.0011) -[2023-11-28 08:32:51,033][87424] Updated weights for policy 0, policy_version 318169 (0.0012) -[2023-11-28 08:32:51,772][87426] Updated weights for policy 1, policy_version 317890 (0.0011) -[2023-11-28 08:32:52,143][87426] Updated weights for policy 1, policy_version 317900 (0.0012) -[2023-11-28 08:32:52,525][87426] Updated weights for policy 1, policy_version 317910 (0.0012) -[2023-11-28 08:32:52,900][87426] Updated weights for policy 1, policy_version 317920 (0.0012) -[2023-11-28 08:32:53,158][87424] Updated weights for policy 0, policy_version 318179 (0.0010) -[2023-11-28 08:32:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 162840576. Throughput: 0: 2714.7, 1: 2730.1. Samples: 162857676. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:53,445][86177] Avg episode reward: [(0, '-530.620'), (1, '-565.380')] -[2023-11-28 08:32:53,547][87424] Updated weights for policy 0, policy_version 318189 (0.0010) -[2023-11-28 08:32:53,939][87424] Updated weights for policy 0, policy_version 318199 (0.0009) -[2023-11-28 08:32:55,046][87426] Updated weights for policy 1, policy_version 317930 (0.0008) -[2023-11-28 08:32:55,425][87426] Updated weights for policy 1, policy_version 317940 (0.0007) -[2023-11-28 08:32:55,811][87426] Updated weights for policy 1, policy_version 317950 (0.0007) -[2023-11-28 08:32:56,312][87424] Updated weights for policy 0, policy_version 318209 (0.0008) -[2023-11-28 08:32:56,705][87424] Updated weights for policy 0, policy_version 318219 (0.0011) -[2023-11-28 08:32:57,081][87424] Updated weights for policy 0, policy_version 318229 (0.0011) -[2023-11-28 08:32:57,473][87424] Updated weights for policy 0, policy_version 318239 (0.0007) -[2023-11-28 08:32:58,303][87426] Updated weights for policy 1, policy_version 317960 (0.0008) -[2023-11-28 08:32:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 162865152. Throughput: 0: 2707.1, 1: 2718.8. Samples: 162881356. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:32:58,445][86177] Avg episode reward: [(0, '-531.540'), (1, '-569.870')] -[2023-11-28 08:32:58,682][87426] Updated weights for policy 1, policy_version 317970 (0.0007) -[2023-11-28 08:32:59,066][87426] Updated weights for policy 1, policy_version 317980 (0.0010) -[2023-11-28 08:32:59,602][87424] Updated weights for policy 0, policy_version 318249 (0.0010) -[2023-11-28 08:32:59,980][87424] Updated weights for policy 0, policy_version 318259 (0.0011) -[2023-11-28 08:33:00,367][87424] Updated weights for policy 0, policy_version 318269 (0.0012) -[2023-11-28 08:33:01,361][87426] Updated weights for policy 1, policy_version 317990 (0.0010) -[2023-11-28 08:33:01,736][87426] Updated weights for policy 1, policy_version 318000 (0.0011) -[2023-11-28 08:33:02,110][87426] Updated weights for policy 1, policy_version 318010 (0.0011) -[2023-11-28 08:33:02,224][87424] Updated weights for policy 0, policy_version 318279 (0.0009) -[2023-11-28 08:33:02,612][87424] Updated weights for policy 0, policy_version 318289 (0.0011) -[2023-11-28 08:33:02,986][87424] Updated weights for policy 0, policy_version 318299 (0.0012) -[2023-11-28 08:33:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 162897920. Throughput: 0: 2712.7, 1: 2727.8. Samples: 162906644. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:33:03,445][86177] Avg episode reward: [(0, '-532.280'), (1, '-571.910')] -[2023-11-28 08:33:04,221][87426] Updated weights for policy 1, policy_version 318020 (0.0010) -[2023-11-28 08:33:04,599][87426] Updated weights for policy 1, policy_version 318030 (0.0008) -[2023-11-28 08:33:04,978][87426] Updated weights for policy 1, policy_version 318040 (0.0009) -[2023-11-28 08:33:04,997][87424] Updated weights for policy 0, policy_version 318309 (0.0012) -[2023-11-28 08:33:05,382][87424] Updated weights for policy 0, policy_version 318319 (0.0012) -[2023-11-28 08:33:05,768][87424] Updated weights for policy 0, policy_version 318329 (0.0009) -[2023-11-28 08:33:07,543][87426] Updated weights for policy 1, policy_version 318050 (0.0011) -[2023-11-28 08:33:07,900][87424] Updated weights for policy 0, policy_version 318339 (0.0010) -[2023-11-28 08:33:07,913][87426] Updated weights for policy 1, policy_version 318060 (0.0008) -[2023-11-28 08:33:08,290][87426] Updated weights for policy 1, policy_version 318070 (0.0007) -[2023-11-28 08:33:08,295][87424] Updated weights for policy 0, policy_version 318349 (0.0010) -[2023-11-28 08:33:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 162914304. Throughput: 0: 2742.3, 1: 2733.7. Samples: 162939644. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:33:08,445][86177] Avg episode reward: [(0, '-524.780'), (1, '-568.020')] -[2023-11-28 08:33:08,666][87424] Updated weights for policy 0, policy_version 318359 (0.0011) -[2023-11-28 08:33:08,671][87426] Updated weights for policy 1, policy_version 318080 (0.0009) -[2023-11-28 08:33:10,772][87424] Updated weights for policy 0, policy_version 318369 (0.0009) -[2023-11-28 08:33:11,154][87424] Updated weights for policy 0, policy_version 318379 (0.0008) -[2023-11-28 08:33:11,176][87426] Updated weights for policy 1, policy_version 318090 (0.0011) -[2023-11-28 08:33:11,537][87424] Updated weights for policy 0, policy_version 318389 (0.0011) -[2023-11-28 08:33:11,546][87426] Updated weights for policy 1, policy_version 318100 (0.0011) -[2023-11-28 08:33:11,918][87424] Updated weights for policy 0, policy_version 318399 (0.0011) -[2023-11-28 08:33:11,922][87426] Updated weights for policy 1, policy_version 318110 (0.0009) -[2023-11-28 08:33:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 162947072. Throughput: 0: 2736.6, 1: 2706.9. Samples: 162963192. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:33:13,445][86177] Avg episode reward: [(0, '-525.180'), (1, '-550.270')] -[2023-11-28 08:33:14,013][87424] Updated weights for policy 0, policy_version 318409 (0.0008) -[2023-11-28 08:33:14,386][87424] Updated weights for policy 0, policy_version 318419 (0.0008) -[2023-11-28 08:33:14,387][87426] Updated weights for policy 1, policy_version 318120 (0.0007) -[2023-11-28 08:33:14,768][87424] Updated weights for policy 0, policy_version 318429 (0.0009) -[2023-11-28 08:33:14,770][87426] Updated weights for policy 1, policy_version 318130 (0.0009) -[2023-11-28 08:33:15,143][87426] Updated weights for policy 1, policy_version 318140 (0.0011) -[2023-11-28 08:33:16,904][87424] Updated weights for policy 0, policy_version 318439 (0.0009) -[2023-11-28 08:33:17,126][87426] Updated weights for policy 1, policy_version 318150 (0.0012) -[2023-11-28 08:33:17,285][87424] Updated weights for policy 0, policy_version 318449 (0.0010) -[2023-11-28 08:33:17,508][87426] Updated weights for policy 1, policy_version 318160 (0.0012) -[2023-11-28 08:33:17,670][87424] Updated weights for policy 0, policy_version 318459 (0.0008) -[2023-11-28 08:33:17,889][87426] Updated weights for policy 1, policy_version 318170 (0.0012) -[2023-11-28 08:33:18,445][86177] Fps is (10 sec: 6553.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 162979840. Throughput: 0: 2743.6, 1: 2695.8. Samples: 162988100. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:33:18,446][86177] Avg episode reward: [(0, '-517.600'), (1, '-554.260')] -[2023-11-28 08:33:19,569][87424] Updated weights for policy 0, policy_version 318469 (0.0010) -[2023-11-28 08:33:19,949][87424] Updated weights for policy 0, policy_version 318479 (0.0008) -[2023-11-28 08:33:20,095][87426] Updated weights for policy 1, policy_version 318180 (0.0011) -[2023-11-28 08:33:20,329][87424] Updated weights for policy 0, policy_version 318489 (0.0010) -[2023-11-28 08:33:20,473][87426] Updated weights for policy 1, policy_version 318190 (0.0010) -[2023-11-28 08:33:20,850][87426] Updated weights for policy 1, policy_version 318200 (0.0012) -[2023-11-28 08:33:22,673][87424] Updated weights for policy 0, policy_version 318499 (0.0011) -[2023-11-28 08:33:23,045][87424] Updated weights for policy 0, policy_version 318509 (0.0012) -[2023-11-28 08:33:23,298][87426] Updated weights for policy 1, policy_version 318210 (0.0012) -[2023-11-28 08:33:23,430][87424] Updated weights for policy 0, policy_version 318519 (0.0011) -[2023-11-28 08:33:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 162996224. Throughput: 0: 2743.8, 1: 2682.3. Samples: 163020748. Policy #0 lag: (min: 12.0, avg: 26.3, max: 44.0) -[2023-11-28 08:33:23,445][86177] Avg episode reward: [(0, '-520.340'), (1, '-553.060')] -[2023-11-28 08:33:23,666][87426] Updated weights for policy 1, policy_version 318220 (0.0011) -[2023-11-28 08:33:24,038][87426] Updated weights for policy 1, policy_version 318230 (0.0012) -[2023-11-28 08:33:24,421][87426] Updated weights for policy 1, policy_version 318240 (0.0012) -[2023-11-28 08:33:25,440][87424] Updated weights for policy 0, policy_version 318529 (0.0010) -[2023-11-28 08:33:25,818][87424] Updated weights for policy 0, policy_version 318539 (0.0007) -[2023-11-28 08:33:26,197][87424] Updated weights for policy 0, policy_version 318549 (0.0010) -[2023-11-28 08:33:26,580][87424] Updated weights for policy 0, policy_version 318559 (0.0010) -[2023-11-28 08:33:26,777][87426] Updated weights for policy 1, policy_version 318250 (0.0011) -[2023-11-28 08:33:27,161][87426] Updated weights for policy 1, policy_version 318260 (0.0012) -[2023-11-28 08:33:27,541][87426] Updated weights for policy 1, policy_version 318270 (0.0012) -[2023-11-28 08:33:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163028992. Throughput: 0: 2734.5, 1: 2678.7. Samples: 163044672. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:33:28,446][86177] Avg episode reward: [(0, '-520.720'), (1, '-537.590')] -[2023-11-28 08:33:28,709][87424] Updated weights for policy 0, policy_version 318569 (0.0009) -[2023-11-28 08:33:29,082][87424] Updated weights for policy 0, policy_version 318579 (0.0010) -[2023-11-28 08:33:29,209][87426] Updated weights for policy 1, policy_version 318280 (0.0010) -[2023-11-28 08:33:29,472][87424] Updated weights for policy 0, policy_version 318589 (0.0011) -[2023-11-28 08:33:29,588][87426] Updated weights for policy 1, policy_version 318290 (0.0007) -[2023-11-28 08:33:29,968][87426] Updated weights for policy 1, policy_version 318300 (0.0008) -[2023-11-28 08:33:31,665][87424] Updated weights for policy 0, policy_version 318599 (0.0010) -[2023-11-28 08:33:32,039][87426] Updated weights for policy 1, policy_version 318310 (0.0010) -[2023-11-28 08:33:32,052][87424] Updated weights for policy 0, policy_version 318609 (0.0011) -[2023-11-28 08:33:32,417][87426] Updated weights for policy 1, policy_version 318320 (0.0011) -[2023-11-28 08:33:32,427][87424] Updated weights for policy 0, policy_version 318619 (0.0010) -[2023-11-28 08:33:32,801][87426] Updated weights for policy 1, policy_version 318330 (0.0011) -[2023-11-28 08:33:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163061760. Throughput: 0: 2751.6, 1: 2700.9. Samples: 163069856. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:33:33,445][86177] Avg episode reward: [(0, '-520.260'), (1, '-526.250')] -[2023-11-28 08:33:34,606][87424] Updated weights for policy 0, policy_version 318629 (0.0009) -[2023-11-28 08:33:34,982][87426] Updated weights for policy 1, policy_version 318340 (0.0011) -[2023-11-28 08:33:34,984][87424] Updated weights for policy 0, policy_version 318639 (0.0012) -[2023-11-28 08:33:35,355][87426] Updated weights for policy 1, policy_version 318350 (0.0011) -[2023-11-28 08:33:35,357][87424] Updated weights for policy 0, policy_version 318649 (0.0012) -[2023-11-28 08:33:35,728][87426] Updated weights for policy 1, policy_version 318360 (0.0011) -[2023-11-28 08:33:37,172][87424] Updated weights for policy 0, policy_version 318659 (0.0012) -[2023-11-28 08:33:37,557][87424] Updated weights for policy 0, policy_version 318669 (0.0012) -[2023-11-28 08:33:37,931][87424] Updated weights for policy 0, policy_version 318679 (0.0012) -[2023-11-28 08:33:37,950][87426] Updated weights for policy 1, policy_version 318370 (0.0011) -[2023-11-28 08:33:38,335][87426] Updated weights for policy 1, policy_version 318380 (0.0009) -[2023-11-28 08:33:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163086336. Throughput: 0: 2773.8, 1: 2673.1. Samples: 163102784. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:33:38,446][86177] Avg episode reward: [(0, '-521.840'), (1, '-528.940')] -[2023-11-28 08:33:38,727][87426] Updated weights for policy 1, policy_version 318390 (0.0011) -[2023-11-28 08:33:39,092][87426] Updated weights for policy 1, policy_version 318400 (0.0012) -[2023-11-28 08:33:40,538][87424] Updated weights for policy 0, policy_version 318689 (0.0012) -[2023-11-28 08:33:40,912][87424] Updated weights for policy 0, policy_version 318699 (0.0010) -[2023-11-28 08:33:41,129][87426] Updated weights for policy 1, policy_version 318410 (0.0010) -[2023-11-28 08:33:41,291][87424] Updated weights for policy 0, policy_version 318709 (0.0012) -[2023-11-28 08:33:41,499][87426] Updated weights for policy 1, policy_version 318420 (0.0007) -[2023-11-28 08:33:41,676][87424] Updated weights for policy 0, policy_version 318719 (0.0012) -[2023-11-28 08:33:41,877][87426] Updated weights for policy 1, policy_version 318430 (0.0012) -[2023-11-28 08:33:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 163110912. Throughput: 0: 2782.0, 1: 2678.8. Samples: 163127088. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:33:43,445][86177] Avg episode reward: [(0, '-523.770'), (1, '-533.610')] -[2023-11-28 08:33:43,919][87424] Updated weights for policy 0, policy_version 318729 (0.0012) -[2023-11-28 08:33:44,231][87426] Updated weights for policy 1, policy_version 318440 (0.0009) -[2023-11-28 08:33:44,306][87424] Updated weights for policy 0, policy_version 318739 (0.0012) -[2023-11-28 08:33:44,615][87426] Updated weights for policy 1, policy_version 318450 (0.0007) -[2023-11-28 08:33:44,689][87424] Updated weights for policy 0, policy_version 318749 (0.0012) -[2023-11-28 08:33:44,996][87426] Updated weights for policy 1, policy_version 318460 (0.0007) -[2023-11-28 08:33:46,707][87424] Updated weights for policy 0, policy_version 318759 (0.0011) -[2023-11-28 08:33:46,977][87426] Updated weights for policy 1, policy_version 318470 (0.0007) -[2023-11-28 08:33:47,094][87424] Updated weights for policy 0, policy_version 318769 (0.0011) -[2023-11-28 08:33:47,348][87426] Updated weights for policy 1, policy_version 318480 (0.0009) -[2023-11-28 08:33:47,476][87424] Updated weights for policy 0, policy_version 318779 (0.0011) -[2023-11-28 08:33:47,738][87426] Updated weights for policy 1, policy_version 318490 (0.0011) -[2023-11-28 08:33:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163143680. Throughput: 0: 2755.8, 1: 2678.7. Samples: 163151200. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:33:48,445][86177] Avg episode reward: [(0, '-575.620'), (1, '-569.620')] -[2023-11-28 08:33:49,567][87424] Updated weights for policy 0, policy_version 318789 (0.0009) -[2023-11-28 08:33:49,944][87424] Updated weights for policy 0, policy_version 318799 (0.0010) -[2023-11-28 08:33:50,092][87426] Updated weights for policy 1, policy_version 318500 (0.0012) -[2023-11-28 08:33:50,324][87424] Updated weights for policy 0, policy_version 318809 (0.0011) -[2023-11-28 08:33:50,473][87426] Updated weights for policy 1, policy_version 318510 (0.0011) -[2023-11-28 08:33:50,850][87426] Updated weights for policy 1, policy_version 318520 (0.0009) -[2023-11-28 08:33:52,426][87424] Updated weights for policy 0, policy_version 318819 (0.0011) -[2023-11-28 08:33:52,814][87424] Updated weights for policy 0, policy_version 318829 (0.0011) -[2023-11-28 08:33:53,189][87424] Updated weights for policy 0, policy_version 318839 (0.0008) -[2023-11-28 08:33:53,384][87426] Updated weights for policy 1, policy_version 318530 (0.0009) -[2023-11-28 08:33:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 163160064. Throughput: 0: 2744.3, 1: 2665.2. Samples: 163183072. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:33:53,445][86177] Avg episode reward: [(0, '-600.920'), (1, '-578.050')] -[2023-11-28 08:33:53,773][87426] Updated weights for policy 1, policy_version 318540 (0.0012) -[2023-11-28 08:33:54,148][87426] Updated weights for policy 1, policy_version 318550 (0.0012) -[2023-11-28 08:33:54,527][87426] Updated weights for policy 1, policy_version 318560 (0.0012) -[2023-11-28 08:33:55,102][87424] Updated weights for policy 0, policy_version 318849 (0.0011) -[2023-11-28 08:33:55,491][87424] Updated weights for policy 0, policy_version 318859 (0.0011) -[2023-11-28 08:33:55,870][87424] Updated weights for policy 0, policy_version 318869 (0.0012) -[2023-11-28 08:33:56,231][87426] Updated weights for policy 1, policy_version 318570 (0.0011) -[2023-11-28 08:33:56,253][87424] Updated weights for policy 0, policy_version 318879 (0.0011) -[2023-11-28 08:33:56,610][87426] Updated weights for policy 1, policy_version 318580 (0.0011) -[2023-11-28 08:33:56,992][87426] Updated weights for policy 1, policy_version 318590 (0.0011) -[2023-11-28 08:33:58,257][87424] Updated weights for policy 0, policy_version 318889 (0.0011) -[2023-11-28 08:33:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163192832. Throughput: 0: 2762.9, 1: 2688.3. Samples: 163208500. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:33:58,446][86177] Avg episode reward: [(0, '-601.430'), (1, '-624.710')] -[2023-11-28 08:33:58,653][87424] Updated weights for policy 0, policy_version 318899 (0.0011) -[2023-11-28 08:33:59,032][87424] Updated weights for policy 0, policy_version 318909 (0.0011) -[2023-11-28 08:33:59,463][87426] Updated weights for policy 1, policy_version 318600 (0.0011) -[2023-11-28 08:33:59,862][87426] Updated weights for policy 1, policy_version 318610 (0.0011) -[2023-11-28 08:34:00,244][87426] Updated weights for policy 1, policy_version 318620 (0.0012) -[2023-11-28 08:34:01,287][87424] Updated weights for policy 0, policy_version 318919 (0.0009) -[2023-11-28 08:34:01,673][87424] Updated weights for policy 0, policy_version 318929 (0.0009) -[2023-11-28 08:34:02,053][87424] Updated weights for policy 0, policy_version 318939 (0.0008) -[2023-11-28 08:34:02,288][87426] Updated weights for policy 1, policy_version 318630 (0.0011) -[2023-11-28 08:34:02,673][87426] Updated weights for policy 1, policy_version 318640 (0.0012) -[2023-11-28 08:34:03,041][87426] Updated weights for policy 1, policy_version 318650 (0.0009) -[2023-11-28 08:34:03,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163225600. Throughput: 0: 2765.4, 1: 2688.6. Samples: 163233532. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:34:03,445][86177] Avg episode reward: [(0, '-603.260'), (1, '-612.030')] -[2023-11-28 08:34:03,881][87424] Updated weights for policy 0, policy_version 318949 (0.0010) -[2023-11-28 08:34:04,274][87424] Updated weights for policy 0, policy_version 318959 (0.0012) -[2023-11-28 08:34:04,642][87424] Updated weights for policy 0, policy_version 318969 (0.0008) -[2023-11-28 08:34:05,183][87426] Updated weights for policy 1, policy_version 318660 (0.0007) -[2023-11-28 08:34:05,577][87426] Updated weights for policy 1, policy_version 318670 (0.0007) -[2023-11-28 08:34:05,946][87426] Updated weights for policy 1, policy_version 318680 (0.0007) -[2023-11-28 08:34:06,826][87424] Updated weights for policy 0, policy_version 318979 (0.0009) -[2023-11-28 08:34:07,210][87424] Updated weights for policy 0, policy_version 318989 (0.0012) -[2023-11-28 08:34:07,592][87424] Updated weights for policy 0, policy_version 318999 (0.0011) -[2023-11-28 08:34:08,212][87426] Updated weights for policy 1, policy_version 318690 (0.0008) -[2023-11-28 08:34:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 163250176. Throughput: 0: 2768.5, 1: 2684.1. Samples: 163266116. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:34:08,445][86177] Avg episode reward: [(0, '-550.680'), (1, '-567.990')] -[2023-11-28 08:34:08,599][87426] Updated weights for policy 1, policy_version 318700 (0.0012) -[2023-11-28 08:34:08,974][87426] Updated weights for policy 1, policy_version 318710 (0.0012) -[2023-11-28 08:34:09,349][87426] Updated weights for policy 1, policy_version 318720 (0.0012) -[2023-11-28 08:34:09,582][87424] Updated weights for policy 0, policy_version 319009 (0.0012) -[2023-11-28 08:34:09,959][87424] Updated weights for policy 0, policy_version 319019 (0.0012) -[2023-11-28 08:34:10,343][87424] Updated weights for policy 0, policy_version 319029 (0.0010) -[2023-11-28 08:34:10,731][87424] Updated weights for policy 0, policy_version 319039 (0.0011) -[2023-11-28 08:34:11,802][87426] Updated weights for policy 1, policy_version 318730 (0.0010) -[2023-11-28 08:34:12,178][87426] Updated weights for policy 1, policy_version 318740 (0.0008) -[2023-11-28 08:34:12,551][87426] Updated weights for policy 1, policy_version 318750 (0.0008) -[2023-11-28 08:34:13,233][87424] Updated weights for policy 0, policy_version 319049 (0.0009) -[2023-11-28 08:34:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163274752. Throughput: 0: 2790.1, 1: 2666.8. Samples: 163290228. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:34:13,445][86177] Avg episode reward: [(0, '-520.300'), (1, '-559.170')] -[2023-11-28 08:34:13,613][87424] Updated weights for policy 0, policy_version 319059 (0.0008) -[2023-11-28 08:34:13,990][87424] Updated weights for policy 0, policy_version 319069 (0.0007) -[2023-11-28 08:34:14,953][87426] Updated weights for policy 1, policy_version 318760 (0.0008) -[2023-11-28 08:34:15,345][87426] Updated weights for policy 1, policy_version 318770 (0.0008) -[2023-11-28 08:34:15,730][87426] Updated weights for policy 1, policy_version 318780 (0.0008) -[2023-11-28 08:34:16,522][87424] Updated weights for policy 0, policy_version 319079 (0.0007) -[2023-11-28 08:34:16,903][87424] Updated weights for policy 0, policy_version 319089 (0.0007) -[2023-11-28 08:34:17,284][87424] Updated weights for policy 0, policy_version 319099 (0.0007) -[2023-11-28 08:34:18,138][87426] Updated weights for policy 1, policy_version 318790 (0.0010) -[2023-11-28 08:34:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 163299328. Throughput: 0: 2775.2, 1: 2649.7. Samples: 163313976. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:34:18,445][86177] Avg episode reward: [(0, '-516.820'), (1, '-500.740')] -[2023-11-28 08:34:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000319104_81690624.pth... -[2023-11-28 08:34:18,489][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000316544_81035264.pth -[2023-11-28 08:34:18,513][87426] Updated weights for policy 1, policy_version 318800 (0.0011) -[2023-11-28 08:34:18,889][87426] Updated weights for policy 1, policy_version 318810 (0.0009) -[2023-11-28 08:34:19,013][87424] Updated weights for policy 0, policy_version 319109 (0.0009) -[2023-11-28 08:34:19,113][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000318816_81616896.pth... -[2023-11-28 08:34:19,152][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000316288_80969728.pth -[2023-11-28 08:34:19,392][87424] Updated weights for policy 0, policy_version 319119 (0.0012) -[2023-11-28 08:34:19,769][87424] Updated weights for policy 0, policy_version 319129 (0.0012) -[2023-11-28 08:34:21,414][87426] Updated weights for policy 1, policy_version 318820 (0.0010) -[2023-11-28 08:34:21,793][87426] Updated weights for policy 1, policy_version 318830 (0.0012) -[2023-11-28 08:34:21,887][87424] Updated weights for policy 0, policy_version 319139 (0.0012) -[2023-11-28 08:34:22,162][87426] Updated weights for policy 1, policy_version 318840 (0.0009) -[2023-11-28 08:34:22,261][87424] Updated weights for policy 0, policy_version 319149 (0.0010) -[2023-11-28 08:34:22,648][87424] Updated weights for policy 0, policy_version 319159 (0.0011) -[2023-11-28 08:34:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 163332096. Throughput: 0: 2748.3, 1: 2638.0. Samples: 163345164. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:34:23,445][86177] Avg episode reward: [(0, '-517.620'), (1, '-509.720')] -[2023-11-28 08:34:24,514][87424] Updated weights for policy 0, policy_version 319169 (0.0012) -[2023-11-28 08:34:24,574][87426] Updated weights for policy 1, policy_version 318850 (0.0011) -[2023-11-28 08:34:24,894][87424] Updated weights for policy 0, policy_version 319179 (0.0011) -[2023-11-28 08:34:24,963][87426] Updated weights for policy 1, policy_version 318860 (0.0011) -[2023-11-28 08:34:25,281][87424] Updated weights for policy 0, policy_version 319189 (0.0011) -[2023-11-28 08:34:25,343][87426] Updated weights for policy 1, policy_version 318870 (0.0012) -[2023-11-28 08:34:25,664][87424] Updated weights for policy 0, policy_version 319199 (0.0010) -[2023-11-28 08:34:25,718][87426] Updated weights for policy 1, policy_version 318880 (0.0010) -[2023-11-28 08:34:27,335][87426] Updated weights for policy 1, policy_version 318890 (0.0011) -[2023-11-28 08:34:27,673][87424] Updated weights for policy 0, policy_version 319209 (0.0011) -[2023-11-28 08:34:27,713][87426] Updated weights for policy 1, policy_version 318900 (0.0011) -[2023-11-28 08:34:28,052][87424] Updated weights for policy 0, policy_version 319219 (0.0010) -[2023-11-28 08:34:28,100][87426] Updated weights for policy 1, policy_version 318910 (0.0011) -[2023-11-28 08:34:28,438][87424] Updated weights for policy 0, policy_version 319229 (0.0011) -[2023-11-28 08:34:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 163356672. Throughput: 0: 2761.0, 1: 2653.9. Samples: 163370756. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:34:28,445][86177] Avg episode reward: [(0, '-519.740'), (1, '-528.760')] -[2023-11-28 08:34:29,955][87426] Updated weights for policy 1, policy_version 318920 (0.0009) -[2023-11-28 08:34:30,333][87426] Updated weights for policy 1, policy_version 318930 (0.0008) -[2023-11-28 08:34:30,709][87426] Updated weights for policy 1, policy_version 318940 (0.0009) -[2023-11-28 08:34:30,887][87424] Updated weights for policy 0, policy_version 319239 (0.0010) -[2023-11-28 08:34:31,265][87424] Updated weights for policy 0, policy_version 319249 (0.0008) -[2023-11-28 08:34:31,645][87424] Updated weights for policy 0, policy_version 319259 (0.0008) -[2023-11-28 08:34:33,103][87426] Updated weights for policy 1, policy_version 318950 (0.0011) -[2023-11-28 08:34:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 163381248. Throughput: 0: 2770.7, 1: 2670.1. Samples: 163396036. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:34:33,445][86177] Avg episode reward: [(0, '-517.490'), (1, '-544.290')] -[2023-11-28 08:34:33,483][87426] Updated weights for policy 1, policy_version 318960 (0.0011) -[2023-11-28 08:34:33,861][87426] Updated weights for policy 1, policy_version 318970 (0.0008) -[2023-11-28 08:34:34,147][87424] Updated weights for policy 0, policy_version 319269 (0.0008) -[2023-11-28 08:34:34,528][87424] Updated weights for policy 0, policy_version 319279 (0.0007) -[2023-11-28 08:34:34,922][87424] Updated weights for policy 0, policy_version 319289 (0.0011) -[2023-11-28 08:34:36,226][87426] Updated weights for policy 1, policy_version 318980 (0.0011) -[2023-11-28 08:34:36,608][87426] Updated weights for policy 1, policy_version 318990 (0.0009) -[2023-11-28 08:34:36,991][87426] Updated weights for policy 1, policy_version 319000 (0.0008) -[2023-11-28 08:34:37,223][87424] Updated weights for policy 0, policy_version 319299 (0.0012) -[2023-11-28 08:34:37,599][87424] Updated weights for policy 0, policy_version 319309 (0.0012) -[2023-11-28 08:34:37,981][87424] Updated weights for policy 0, policy_version 319319 (0.0012) -[2023-11-28 08:34:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163414016. Throughput: 0: 2764.5, 1: 2689.7. Samples: 163428512. Policy #0 lag: (min: 31.0, avg: 47.0, max: 63.0) -[2023-11-28 08:34:38,445][86177] Avg episode reward: [(0, '-518.780'), (1, '-549.620')] -[2023-11-28 08:34:38,798][87426] Updated weights for policy 1, policy_version 319010 (0.0007) -[2023-11-28 08:34:39,166][87426] Updated weights for policy 1, policy_version 319020 (0.0011) -[2023-11-28 08:34:39,542][87426] Updated weights for policy 1, policy_version 319030 (0.0008) -[2023-11-28 08:34:39,919][87426] Updated weights for policy 1, policy_version 319040 (0.0010) -[2023-11-28 08:34:39,989][87424] Updated weights for policy 0, policy_version 319329 (0.0012) -[2023-11-28 08:34:40,362][87424] Updated weights for policy 0, policy_version 319339 (0.0012) -[2023-11-28 08:34:40,736][87424] Updated weights for policy 0, policy_version 319349 (0.0012) -[2023-11-28 08:34:41,118][87424] Updated weights for policy 0, policy_version 319359 (0.0012) -[2023-11-28 08:34:42,095][87426] Updated weights for policy 1, policy_version 319050 (0.0012) -[2023-11-28 08:34:42,475][87426] Updated weights for policy 1, policy_version 319060 (0.0012) -[2023-11-28 08:34:42,856][87426] Updated weights for policy 1, policy_version 319070 (0.0012) -[2023-11-28 08:34:43,260][87424] Updated weights for policy 0, policy_version 319369 (0.0009) -[2023-11-28 08:34:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163438592. Throughput: 0: 2746.6, 1: 2688.3. Samples: 163453068. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:34:43,445][86177] Avg episode reward: [(0, '-531.000'), (1, '-542.120')] -[2023-11-28 08:34:43,646][87424] Updated weights for policy 0, policy_version 319379 (0.0008) -[2023-11-28 08:34:44,019][87424] Updated weights for policy 0, policy_version 319389 (0.0009) -[2023-11-28 08:34:44,960][87426] Updated weights for policy 1, policy_version 319080 (0.0012) -[2023-11-28 08:34:45,337][87426] Updated weights for policy 1, policy_version 319090 (0.0012) -[2023-11-28 08:34:45,717][87426] Updated weights for policy 1, policy_version 319100 (0.0011) -[2023-11-28 08:34:45,868][87424] Updated weights for policy 0, policy_version 319399 (0.0010) -[2023-11-28 08:34:46,247][87424] Updated weights for policy 0, policy_version 319409 (0.0011) -[2023-11-28 08:34:46,625][87424] Updated weights for policy 0, policy_version 319419 (0.0010) -[2023-11-28 08:34:48,170][87426] Updated weights for policy 1, policy_version 319110 (0.0012) -[2023-11-28 08:34:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 163463168. Throughput: 0: 2725.6, 1: 2692.2. Samples: 163477332. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:34:48,445][86177] Avg episode reward: [(0, '-530.970'), (1, '-533.340')] -[2023-11-28 08:34:48,558][87426] Updated weights for policy 1, policy_version 319120 (0.0010) -[2023-11-28 08:34:48,628][87424] Updated weights for policy 0, policy_version 319429 (0.0009) -[2023-11-28 08:34:48,934][87426] Updated weights for policy 1, policy_version 319130 (0.0012) -[2023-11-28 08:34:49,004][87424] Updated weights for policy 0, policy_version 319439 (0.0009) -[2023-11-28 08:34:49,395][87424] Updated weights for policy 0, policy_version 319449 (0.0010) -[2023-11-28 08:34:50,690][87426] Updated weights for policy 1, policy_version 319140 (0.0010) -[2023-11-28 08:34:51,070][87426] Updated weights for policy 1, policy_version 319150 (0.0007) -[2023-11-28 08:34:51,450][87426] Updated weights for policy 1, policy_version 319160 (0.0008) -[2023-11-28 08:34:51,913][87424] Updated weights for policy 0, policy_version 319459 (0.0009) -[2023-11-28 08:34:52,292][87424] Updated weights for policy 0, policy_version 319469 (0.0011) -[2023-11-28 08:34:52,672][87424] Updated weights for policy 0, policy_version 319479 (0.0007) -[2023-11-28 08:34:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 163495936. Throughput: 0: 2704.4, 1: 2690.4. Samples: 163508880. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:34:53,445][86177] Avg episode reward: [(0, '-532.290'), (1, '-524.700')] -[2023-11-28 08:34:53,974][87426] Updated weights for policy 1, policy_version 319170 (0.0010) -[2023-11-28 08:34:54,349][87426] Updated weights for policy 1, policy_version 319180 (0.0012) -[2023-11-28 08:34:54,723][87426] Updated weights for policy 1, policy_version 319190 (0.0010) -[2023-11-28 08:34:54,980][87424] Updated weights for policy 0, policy_version 319489 (0.0009) -[2023-11-28 08:34:55,101][87426] Updated weights for policy 1, policy_version 319200 (0.0007) -[2023-11-28 08:34:55,365][87424] Updated weights for policy 0, policy_version 319499 (0.0012) -[2023-11-28 08:34:55,738][87424] Updated weights for policy 0, policy_version 319509 (0.0012) -[2023-11-28 08:34:56,124][87424] Updated weights for policy 0, policy_version 319519 (0.0012) -[2023-11-28 08:34:57,294][87426] Updated weights for policy 1, policy_version 319210 (0.0009) -[2023-11-28 08:34:57,673][87426] Updated weights for policy 1, policy_version 319220 (0.0007) -[2023-11-28 08:34:58,052][87426] Updated weights for policy 1, policy_version 319230 (0.0010) -[2023-11-28 08:34:58,165][87424] Updated weights for policy 0, policy_version 319529 (0.0010) -[2023-11-28 08:34:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 163520512. Throughput: 0: 2700.1, 1: 2707.0. Samples: 163533548. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:34:58,445][86177] Avg episode reward: [(0, '-532.350'), (1, '-520.100')] -[2023-11-28 08:34:58,555][87424] Updated weights for policy 0, policy_version 319539 (0.0007) -[2023-11-28 08:34:58,943][87424] Updated weights for policy 0, policy_version 319549 (0.0008) -[2023-11-28 08:35:00,107][87426] Updated weights for policy 1, policy_version 319240 (0.0010) -[2023-11-28 08:35:00,493][87426] Updated weights for policy 1, policy_version 319250 (0.0012) -[2023-11-28 08:35:00,867][87426] Updated weights for policy 1, policy_version 319260 (0.0012) -[2023-11-28 08:35:01,251][87424] Updated weights for policy 0, policy_version 319559 (0.0011) -[2023-11-28 08:35:01,635][87424] Updated weights for policy 0, policy_version 319569 (0.0012) -[2023-11-28 08:35:02,018][87424] Updated weights for policy 0, policy_version 319579 (0.0012) -[2023-11-28 08:35:03,041][87426] Updated weights for policy 1, policy_version 319270 (0.0012) -[2023-11-28 08:35:03,424][87426] Updated weights for policy 1, policy_version 319280 (0.0012) -[2023-11-28 08:35:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 163545088. Throughput: 0: 2726.5, 1: 2721.4. Samples: 163559132. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:03,445][86177] Avg episode reward: [(0, '-523.940'), (1, '-523.300')] -[2023-11-28 08:35:03,800][87426] Updated weights for policy 1, policy_version 319290 (0.0012) -[2023-11-28 08:35:04,264][87424] Updated weights for policy 0, policy_version 319589 (0.0012) -[2023-11-28 08:35:04,644][87424] Updated weights for policy 0, policy_version 319599 (0.0010) -[2023-11-28 08:35:05,027][87424] Updated weights for policy 0, policy_version 319609 (0.0012) -[2023-11-28 08:35:06,188][87426] Updated weights for policy 1, policy_version 319300 (0.0011) -[2023-11-28 08:35:06,565][87426] Updated weights for policy 1, policy_version 319310 (0.0012) -[2023-11-28 08:35:06,627][87424] Updated weights for policy 0, policy_version 319619 (0.0012) -[2023-11-28 08:35:06,942][87426] Updated weights for policy 1, policy_version 319320 (0.0008) -[2023-11-28 08:35:07,005][87424] Updated weights for policy 0, policy_version 319629 (0.0012) -[2023-11-28 08:35:07,386][87424] Updated weights for policy 0, policy_version 319639 (0.0011) -[2023-11-28 08:35:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163577856. Throughput: 0: 2745.9, 1: 2736.6. Samples: 163591876. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:08,445][86177] Avg episode reward: [(0, '-524.410'), (1, '-517.490')] -[2023-11-28 08:35:09,483][87426] Updated weights for policy 1, policy_version 319330 (0.0012) -[2023-11-28 08:35:09,852][87426] Updated weights for policy 1, policy_version 319340 (0.0011) -[2023-11-28 08:35:09,916][87424] Updated weights for policy 0, policy_version 319649 (0.0012) -[2023-11-28 08:35:10,232][87426] Updated weights for policy 1, policy_version 319350 (0.0010) -[2023-11-28 08:35:10,293][87424] Updated weights for policy 0, policy_version 319659 (0.0012) -[2023-11-28 08:35:10,619][87426] Updated weights for policy 1, policy_version 319360 (0.0009) -[2023-11-28 08:35:10,678][87424] Updated weights for policy 0, policy_version 319669 (0.0011) -[2023-11-28 08:35:11,061][87424] Updated weights for policy 0, policy_version 319679 (0.0012) -[2023-11-28 08:35:12,894][87426] Updated weights for policy 1, policy_version 319370 (0.0009) -[2023-11-28 08:35:13,280][87426] Updated weights for policy 1, policy_version 319380 (0.0012) -[2023-11-28 08:35:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 163594240. Throughput: 0: 2744.7, 1: 2727.3. Samples: 163616996. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:13,445][86177] Avg episode reward: [(0, '-524.530'), (1, '-516.730')] -[2023-11-28 08:35:13,486][87424] Updated weights for policy 0, policy_version 319689 (0.0009) -[2023-11-28 08:35:13,647][87426] Updated weights for policy 1, policy_version 319390 (0.0010) -[2023-11-28 08:35:13,859][87424] Updated weights for policy 0, policy_version 319699 (0.0012) -[2023-11-28 08:35:14,236][87424] Updated weights for policy 0, policy_version 319709 (0.0010) -[2023-11-28 08:35:15,619][87426] Updated weights for policy 1, policy_version 319400 (0.0011) -[2023-11-28 08:35:15,846][87424] Updated weights for policy 0, policy_version 319719 (0.0012) -[2023-11-28 08:35:15,999][87426] Updated weights for policy 1, policy_version 319410 (0.0012) -[2023-11-28 08:35:16,227][87424] Updated weights for policy 0, policy_version 319729 (0.0011) -[2023-11-28 08:35:16,381][87426] Updated weights for policy 1, policy_version 319420 (0.0012) -[2023-11-28 08:35:16,602][87424] Updated weights for policy 0, policy_version 319739 (0.0011) -[2023-11-28 08:35:18,161][87426] Updated weights for policy 1, policy_version 319430 (0.0011) -[2023-11-28 08:35:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163627008. Throughput: 0: 2734.4, 1: 2708.2. Samples: 163640952. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:18,446][86177] Avg episode reward: [(0, '-524.260'), (1, '-527.260')] -[2023-11-28 08:35:18,501][87424] Updated weights for policy 0, policy_version 319749 (0.0011) -[2023-11-28 08:35:18,542][87426] Updated weights for policy 1, policy_version 319440 (0.0011) -[2023-11-28 08:35:18,876][87424] Updated weights for policy 0, policy_version 319759 (0.0011) -[2023-11-28 08:35:18,930][87426] Updated weights for policy 1, policy_version 319450 (0.0008) -[2023-11-28 08:35:19,264][87424] Updated weights for policy 0, policy_version 319769 (0.0012) -[2023-11-28 08:35:21,395][87424] Updated weights for policy 0, policy_version 319779 (0.0012) -[2023-11-28 08:35:21,456][87426] Updated weights for policy 1, policy_version 319460 (0.0009) -[2023-11-28 08:35:21,781][87424] Updated weights for policy 0, policy_version 319789 (0.0009) -[2023-11-28 08:35:21,839][87426] Updated weights for policy 1, policy_version 319470 (0.0011) -[2023-11-28 08:35:22,165][87424] Updated weights for policy 0, policy_version 319799 (0.0010) -[2023-11-28 08:35:22,216][87426] Updated weights for policy 1, policy_version 319480 (0.0015) -[2023-11-28 08:35:23,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163659776. Throughput: 0: 2747.4, 1: 2704.5. Samples: 163673848. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:23,445][86177] Avg episode reward: [(0, '-519.660'), (1, '-553.140')] -[2023-11-28 08:35:24,316][87426] Updated weights for policy 1, policy_version 319490 (0.0010) -[2023-11-28 08:35:24,550][87424] Updated weights for policy 0, policy_version 319809 (0.0011) -[2023-11-28 08:35:24,694][87426] Updated weights for policy 1, policy_version 319500 (0.0011) -[2023-11-28 08:35:24,932][87424] Updated weights for policy 0, policy_version 319819 (0.0011) -[2023-11-28 08:35:25,073][87426] Updated weights for policy 1, policy_version 319510 (0.0010) -[2023-11-28 08:35:25,316][87424] Updated weights for policy 0, policy_version 319829 (0.0012) -[2023-11-28 08:35:25,453][87426] Updated weights for policy 1, policy_version 319520 (0.0007) -[2023-11-28 08:35:25,714][87424] Updated weights for policy 0, policy_version 319839 (0.0012) -[2023-11-28 08:35:27,336][87426] Updated weights for policy 1, policy_version 319530 (0.0010) -[2023-11-28 08:35:27,613][87424] Updated weights for policy 0, policy_version 319849 (0.0011) -[2023-11-28 08:35:27,721][87426] Updated weights for policy 1, policy_version 319540 (0.0007) -[2023-11-28 08:35:27,986][87424] Updated weights for policy 0, policy_version 319859 (0.0012) -[2023-11-28 08:35:28,104][87426] Updated weights for policy 1, policy_version 319550 (0.0008) -[2023-11-28 08:35:28,368][87424] Updated weights for policy 0, policy_version 319869 (0.0012) -[2023-11-28 08:35:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 163684352. Throughput: 0: 2743.1, 1: 2719.3. Samples: 163698876. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:28,445][86177] Avg episode reward: [(0, '-519.740'), (1, '-546.180')] -[2023-11-28 08:35:30,086][87426] Updated weights for policy 1, policy_version 319560 (0.0010) -[2023-11-28 08:35:30,462][87426] Updated weights for policy 1, policy_version 319570 (0.0009) -[2023-11-28 08:35:30,842][87426] Updated weights for policy 1, policy_version 319580 (0.0011) -[2023-11-28 08:35:30,900][87424] Updated weights for policy 0, policy_version 319879 (0.0010) -[2023-11-28 08:35:31,282][87424] Updated weights for policy 0, policy_version 319889 (0.0012) -[2023-11-28 08:35:31,661][87424] Updated weights for policy 0, policy_version 319899 (0.0012) -[2023-11-28 08:35:32,853][87426] Updated weights for policy 1, policy_version 319590 (0.0010) -[2023-11-28 08:35:33,235][87426] Updated weights for policy 1, policy_version 319600 (0.0012) -[2023-11-28 08:35:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163708928. Throughput: 0: 2728.5, 1: 2734.5. Samples: 163723168. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:33,445][86177] Avg episode reward: [(0, '-526.600'), (1, '-543.420')] -[2023-11-28 08:35:33,625][87426] Updated weights for policy 1, policy_version 319610 (0.0012) -[2023-11-28 08:35:33,916][87424] Updated weights for policy 0, policy_version 319909 (0.0012) -[2023-11-28 08:35:34,304][87424] Updated weights for policy 0, policy_version 319919 (0.0012) -[2023-11-28 08:35:34,687][87424] Updated weights for policy 0, policy_version 319929 (0.0011) -[2023-11-28 08:35:35,731][87426] Updated weights for policy 1, policy_version 319620 (0.0011) -[2023-11-28 08:35:36,101][87426] Updated weights for policy 1, policy_version 319630 (0.0007) -[2023-11-28 08:35:36,475][87426] Updated weights for policy 1, policy_version 319640 (0.0008) -[2023-11-28 08:35:37,229][87424] Updated weights for policy 0, policy_version 319939 (0.0008) -[2023-11-28 08:35:37,611][87424] Updated weights for policy 0, policy_version 319949 (0.0007) -[2023-11-28 08:35:37,992][87424] Updated weights for policy 0, policy_version 319959 (0.0007) -[2023-11-28 08:35:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 163741696. Throughput: 0: 2726.1, 1: 2756.8. Samples: 163755612. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:38,445][86177] Avg episode reward: [(0, '-524.640'), (1, '-514.050')] -[2023-11-28 08:35:39,084][87426] Updated weights for policy 1, policy_version 319650 (0.0010) -[2023-11-28 08:35:39,468][87426] Updated weights for policy 1, policy_version 319660 (0.0012) -[2023-11-28 08:35:39,843][87426] Updated weights for policy 1, policy_version 319670 (0.0010) -[2023-11-28 08:35:40,219][87426] Updated weights for policy 1, policy_version 319680 (0.0009) -[2023-11-28 08:35:40,415][87424] Updated weights for policy 0, policy_version 319969 (0.0008) -[2023-11-28 08:35:40,806][87424] Updated weights for policy 0, policy_version 319979 (0.0011) -[2023-11-28 08:35:41,178][87424] Updated weights for policy 0, policy_version 319989 (0.0012) -[2023-11-28 08:35:41,564][87424] Updated weights for policy 0, policy_version 319999 (0.0012) -[2023-11-28 08:35:42,156][87426] Updated weights for policy 1, policy_version 319690 (0.0010) -[2023-11-28 08:35:42,538][87426] Updated weights for policy 1, policy_version 319700 (0.0011) -[2023-11-28 08:35:42,908][87426] Updated weights for policy 1, policy_version 319710 (0.0010) -[2023-11-28 08:35:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 163766272. Throughput: 0: 2730.5, 1: 2729.9. Samples: 163779264. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:43,445][86177] Avg episode reward: [(0, '-535.400'), (1, '-513.120')] -[2023-11-28 08:35:43,675][87424] Updated weights for policy 0, policy_version 320009 (0.0008) -[2023-11-28 08:35:44,060][87424] Updated weights for policy 0, policy_version 320019 (0.0008) -[2023-11-28 08:35:44,440][87424] Updated weights for policy 0, policy_version 320029 (0.0008) -[2023-11-28 08:35:45,386][87426] Updated weights for policy 1, policy_version 319720 (0.0009) -[2023-11-28 08:35:45,768][87426] Updated weights for policy 1, policy_version 319730 (0.0011) -[2023-11-28 08:35:46,147][87426] Updated weights for policy 1, policy_version 319740 (0.0010) -[2023-11-28 08:35:46,838][87424] Updated weights for policy 0, policy_version 320039 (0.0008) -[2023-11-28 08:35:47,219][87424] Updated weights for policy 0, policy_version 320049 (0.0008) -[2023-11-28 08:35:47,611][87424] Updated weights for policy 0, policy_version 320059 (0.0008) -[2023-11-28 08:35:48,291][87426] Updated weights for policy 1, policy_version 319750 (0.0010) -[2023-11-28 08:35:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163790848. Throughput: 0: 2685.5, 1: 2722.7. Samples: 163802500. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:48,446][86177] Avg episode reward: [(0, '-536.400'), (1, '-552.850')] -[2023-11-28 08:35:48,668][87426] Updated weights for policy 1, policy_version 319760 (0.0012) -[2023-11-28 08:35:49,051][87426] Updated weights for policy 1, policy_version 319770 (0.0011) -[2023-11-28 08:35:49,669][87424] Updated weights for policy 0, policy_version 320069 (0.0007) -[2023-11-28 08:35:50,049][87424] Updated weights for policy 0, policy_version 320079 (0.0008) -[2023-11-28 08:35:50,434][87424] Updated weights for policy 0, policy_version 320089 (0.0009) -[2023-11-28 08:35:51,601][87426] Updated weights for policy 1, policy_version 319780 (0.0011) -[2023-11-28 08:35:51,970][87426] Updated weights for policy 1, policy_version 319790 (0.0012) -[2023-11-28 08:35:52,349][87426] Updated weights for policy 1, policy_version 319800 (0.0012) -[2023-11-28 08:35:52,405][87424] Updated weights for policy 0, policy_version 320099 (0.0008) -[2023-11-28 08:35:52,786][87424] Updated weights for policy 0, policy_version 320109 (0.0011) -[2023-11-28 08:35:53,164][87424] Updated weights for policy 0, policy_version 320119 (0.0012) -[2023-11-28 08:35:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 163815424. Throughput: 0: 2669.2, 1: 2708.5. Samples: 163833876. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:53,445][86177] Avg episode reward: [(0, '-532.860'), (1, '-550.460')] -[2023-11-28 08:35:54,985][87426] Updated weights for policy 1, policy_version 319810 (0.0010) -[2023-11-28 08:35:55,363][87426] Updated weights for policy 1, policy_version 319820 (0.0010) -[2023-11-28 08:35:55,618][87424] Updated weights for policy 0, policy_version 320129 (0.0009) -[2023-11-28 08:35:55,733][87426] Updated weights for policy 1, policy_version 319830 (0.0010) -[2023-11-28 08:35:56,000][87424] Updated weights for policy 0, policy_version 320139 (0.0011) -[2023-11-28 08:35:56,106][87426] Updated weights for policy 1, policy_version 319840 (0.0007) -[2023-11-28 08:35:56,396][87424] Updated weights for policy 0, policy_version 320149 (0.0011) -[2023-11-28 08:35:56,782][87424] Updated weights for policy 0, policy_version 320159 (0.0011) -[2023-11-28 08:35:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 163840000. Throughput: 0: 2662.6, 1: 2670.5. Samples: 163856984. Policy #0 lag: (min: 31.0, avg: 46.1, max: 63.0) -[2023-11-28 08:35:58,445][86177] Avg episode reward: [(0, '-523.500'), (1, '-544.370')] -[2023-11-28 08:35:58,610][87426] Updated weights for policy 1, policy_version 319850 (0.0007) -[2023-11-28 08:35:58,808][87424] Updated weights for policy 0, policy_version 320169 (0.0007) -[2023-11-28 08:35:58,986][87426] Updated weights for policy 1, policy_version 319860 (0.0008) -[2023-11-28 08:35:59,192][87424] Updated weights for policy 0, policy_version 320179 (0.0009) -[2023-11-28 08:35:59,363][87426] Updated weights for policy 1, policy_version 319870 (0.0010) -[2023-11-28 08:35:59,575][87424] Updated weights for policy 0, policy_version 320189 (0.0008) -[2023-11-28 08:36:01,539][87426] Updated weights for policy 1, policy_version 319880 (0.0011) -[2023-11-28 08:36:01,917][87426] Updated weights for policy 1, policy_version 319890 (0.0011) -[2023-11-28 08:36:02,105][87424] Updated weights for policy 0, policy_version 320199 (0.0010) -[2023-11-28 08:36:02,292][87426] Updated weights for policy 1, policy_version 319900 (0.0010) -[2023-11-28 08:36:02,486][87424] Updated weights for policy 0, policy_version 320209 (0.0012) -[2023-11-28 08:36:02,864][87424] Updated weights for policy 0, policy_version 320219 (0.0008) -[2023-11-28 08:36:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163872768. Throughput: 0: 2677.0, 1: 2661.6. Samples: 163881188. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:03,445][86177] Avg episode reward: [(0, '-523.140'), (1, '-560.010')] -[2023-11-28 08:36:04,331][87426] Updated weights for policy 1, policy_version 319910 (0.0012) -[2023-11-28 08:36:04,708][87426] Updated weights for policy 1, policy_version 319920 (0.0012) -[2023-11-28 08:36:05,090][87426] Updated weights for policy 1, policy_version 319930 (0.0012) -[2023-11-28 08:36:05,209][87424] Updated weights for policy 0, policy_version 320229 (0.0009) -[2023-11-28 08:36:05,588][87424] Updated weights for policy 0, policy_version 320239 (0.0012) -[2023-11-28 08:36:05,973][87424] Updated weights for policy 0, policy_version 320249 (0.0012) -[2023-11-28 08:36:07,320][87426] Updated weights for policy 1, policy_version 319940 (0.0011) -[2023-11-28 08:36:07,605][87424] Updated weights for policy 0, policy_version 320259 (0.0012) -[2023-11-28 08:36:07,692][87426] Updated weights for policy 1, policy_version 319950 (0.0011) -[2023-11-28 08:36:07,979][87424] Updated weights for policy 0, policy_version 320269 (0.0011) -[2023-11-28 08:36:08,072][87426] Updated weights for policy 1, policy_version 319960 (0.0008) -[2023-11-28 08:36:08,365][87424] Updated weights for policy 0, policy_version 320279 (0.0012) -[2023-11-28 08:36:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 163897344. Throughput: 0: 2671.5, 1: 2663.0. Samples: 163913904. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:08,445][86177] Avg episode reward: [(0, '-519.070'), (1, '-586.070')] -[2023-11-28 08:36:10,399][87424] Updated weights for policy 0, policy_version 320289 (0.0011) -[2023-11-28 08:36:10,614][87426] Updated weights for policy 1, policy_version 319970 (0.0007) -[2023-11-28 08:36:10,782][87424] Updated weights for policy 0, policy_version 320299 (0.0011) -[2023-11-28 08:36:10,999][87426] Updated weights for policy 1, policy_version 319980 (0.0012) -[2023-11-28 08:36:11,157][87424] Updated weights for policy 0, policy_version 320309 (0.0011) -[2023-11-28 08:36:11,368][87426] Updated weights for policy 1, policy_version 319990 (0.0011) -[2023-11-28 08:36:11,531][87424] Updated weights for policy 0, policy_version 320319 (0.0012) -[2023-11-28 08:36:11,745][87426] Updated weights for policy 1, policy_version 320000 (0.0011) -[2023-11-28 08:36:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163921920. Throughput: 0: 2668.0, 1: 2623.7. Samples: 163937004. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:13,445][86177] Avg episode reward: [(0, '-517.540'), (1, '-553.590')] -[2023-11-28 08:36:13,625][87424] Updated weights for policy 0, policy_version 320329 (0.0011) -[2023-11-28 08:36:13,828][87426] Updated weights for policy 1, policy_version 320010 (0.0012) -[2023-11-28 08:36:14,006][87424] Updated weights for policy 0, policy_version 320339 (0.0008) -[2023-11-28 08:36:14,215][87426] Updated weights for policy 1, policy_version 320020 (0.0011) -[2023-11-28 08:36:14,382][87424] Updated weights for policy 0, policy_version 320349 (0.0008) -[2023-11-28 08:36:14,583][87426] Updated weights for policy 1, policy_version 320030 (0.0012) -[2023-11-28 08:36:16,226][87424] Updated weights for policy 0, policy_version 320359 (0.0010) -[2023-11-28 08:36:16,610][87424] Updated weights for policy 0, policy_version 320369 (0.0012) -[2023-11-28 08:36:16,682][87426] Updated weights for policy 1, policy_version 320040 (0.0012) -[2023-11-28 08:36:16,984][87424] Updated weights for policy 0, policy_version 320379 (0.0012) -[2023-11-28 08:36:17,063][87426] Updated weights for policy 1, policy_version 320050 (0.0012) -[2023-11-28 08:36:17,450][87426] Updated weights for policy 1, policy_version 320060 (0.0012) -[2023-11-28 08:36:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 163954688. Throughput: 0: 2709.2, 1: 2606.3. Samples: 163962368. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:18,445][86177] Avg episode reward: [(0, '-513.360'), (1, '-584.650')] -[2023-11-28 08:36:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000320064_81936384.pth... -[2023-11-28 08:36:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000320384_82018304.pth... -[2023-11-28 08:36:18,491][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000317824_81362944.pth -[2023-11-28 08:36:18,504][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000317536_81289216.pth -[2023-11-28 08:36:19,056][87424] Updated weights for policy 0, policy_version 320389 (0.0012) -[2023-11-28 08:36:19,438][87424] Updated weights for policy 0, policy_version 320399 (0.0012) -[2023-11-28 08:36:19,833][87424] Updated weights for policy 0, policy_version 320409 (0.0008) -[2023-11-28 08:36:19,853][87426] Updated weights for policy 1, policy_version 320070 (0.0016) -[2023-11-28 08:36:20,236][87426] Updated weights for policy 1, policy_version 320080 (0.0011) -[2023-11-28 08:36:20,613][87426] Updated weights for policy 1, policy_version 320090 (0.0010) -[2023-11-28 08:36:21,943][87424] Updated weights for policy 0, policy_version 320419 (0.0011) -[2023-11-28 08:36:22,327][87424] Updated weights for policy 0, policy_version 320429 (0.0012) -[2023-11-28 08:36:22,714][87424] Updated weights for policy 0, policy_version 320439 (0.0012) -[2023-11-28 08:36:23,113][87426] Updated weights for policy 1, policy_version 320100 (0.0009) -[2023-11-28 08:36:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 163979264. Throughput: 0: 2744.7, 1: 2582.7. Samples: 163995344. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:23,445][86177] Avg episode reward: [(0, '-512.530'), (1, '-589.940')] -[2023-11-28 08:36:23,495][87426] Updated weights for policy 1, policy_version 320110 (0.0009) -[2023-11-28 08:36:23,873][87426] Updated weights for policy 1, policy_version 320120 (0.0010) -[2023-11-28 08:36:24,917][87424] Updated weights for policy 0, policy_version 320449 (0.0011) -[2023-11-28 08:36:25,303][87424] Updated weights for policy 0, policy_version 320459 (0.0009) -[2023-11-28 08:36:25,688][87424] Updated weights for policy 0, policy_version 320469 (0.0008) -[2023-11-28 08:36:26,064][87424] Updated weights for policy 0, policy_version 320479 (0.0007) -[2023-11-28 08:36:26,406][87426] Updated weights for policy 1, policy_version 320130 (0.0009) -[2023-11-28 08:36:26,778][87426] Updated weights for policy 1, policy_version 320140 (0.0007) -[2023-11-28 08:36:27,148][87426] Updated weights for policy 1, policy_version 320150 (0.0009) -[2023-11-28 08:36:27,532][87426] Updated weights for policy 1, policy_version 320160 (0.0007) -[2023-11-28 08:36:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 164003840. Throughput: 0: 2730.9, 1: 2601.6. Samples: 164019228. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:28,445][86177] Avg episode reward: [(0, '-514.430'), (1, '-563.130')] -[2023-11-28 08:36:28,555][87424] Updated weights for policy 0, policy_version 320489 (0.0008) -[2023-11-28 08:36:28,940][87424] Updated weights for policy 0, policy_version 320499 (0.0008) -[2023-11-28 08:36:29,323][87424] Updated weights for policy 0, policy_version 320509 (0.0007) -[2023-11-28 08:36:30,058][87426] Updated weights for policy 1, policy_version 320170 (0.0012) -[2023-11-28 08:36:30,442][87426] Updated weights for policy 1, policy_version 320180 (0.0011) -[2023-11-28 08:36:30,822][87426] Updated weights for policy 1, policy_version 320190 (0.0011) -[2023-11-28 08:36:31,416][87424] Updated weights for policy 0, policy_version 320519 (0.0011) -[2023-11-28 08:36:31,796][87424] Updated weights for policy 0, policy_version 320529 (0.0012) -[2023-11-28 08:36:32,174][87424] Updated weights for policy 0, policy_version 320539 (0.0012) -[2023-11-28 08:36:33,286][87426] Updated weights for policy 1, policy_version 320200 (0.0008) -[2023-11-28 08:36:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 164028416. Throughput: 0: 2753.3, 1: 2587.2. Samples: 164042820. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:33,445][86177] Avg episode reward: [(0, '-523.810'), (1, '-549.360')] -[2023-11-28 08:36:33,664][87426] Updated weights for policy 1, policy_version 320210 (0.0008) -[2023-11-28 08:36:34,049][87426] Updated weights for policy 1, policy_version 320220 (0.0009) -[2023-11-28 08:36:34,434][87424] Updated weights for policy 0, policy_version 320549 (0.0012) -[2023-11-28 08:36:34,810][87424] Updated weights for policy 0, policy_version 320559 (0.0012) -[2023-11-28 08:36:35,195][87424] Updated weights for policy 0, policy_version 320569 (0.0011) -[2023-11-28 08:36:36,084][87426] Updated weights for policy 1, policy_version 320230 (0.0011) -[2023-11-28 08:36:36,462][87426] Updated weights for policy 1, policy_version 320240 (0.0012) -[2023-11-28 08:36:36,847][87426] Updated weights for policy 1, policy_version 320250 (0.0012) -[2023-11-28 08:36:37,415][87424] Updated weights for policy 0, policy_version 320579 (0.0010) -[2023-11-28 08:36:37,802][87424] Updated weights for policy 0, policy_version 320589 (0.0008) -[2023-11-28 08:36:38,179][87424] Updated weights for policy 0, policy_version 320599 (0.0008) -[2023-11-28 08:36:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 164052992. Throughput: 0: 2770.5, 1: 2611.1. Samples: 164076048. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:38,445][86177] Avg episode reward: [(0, '-525.370'), (1, '-542.360')] -[2023-11-28 08:36:38,807][87426] Updated weights for policy 1, policy_version 320260 (0.0012) -[2023-11-28 08:36:39,178][87426] Updated weights for policy 1, policy_version 320270 (0.0010) -[2023-11-28 08:36:39,565][87426] Updated weights for policy 1, policy_version 320280 (0.0010) -[2023-11-28 08:36:40,437][87424] Updated weights for policy 0, policy_version 320609 (0.0008) -[2023-11-28 08:36:40,818][87424] Updated weights for policy 0, policy_version 320619 (0.0010) -[2023-11-28 08:36:41,207][87424] Updated weights for policy 0, policy_version 320629 (0.0008) -[2023-11-28 08:36:41,596][87424] Updated weights for policy 0, policy_version 320639 (0.0008) -[2023-11-28 08:36:41,610][87426] Updated weights for policy 1, policy_version 320290 (0.0009) -[2023-11-28 08:36:41,992][87426] Updated weights for policy 1, policy_version 320300 (0.0012) -[2023-11-28 08:36:42,363][87426] Updated weights for policy 1, policy_version 320310 (0.0012) -[2023-11-28 08:36:42,745][87426] Updated weights for policy 1, policy_version 320320 (0.0011) -[2023-11-28 08:36:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 164085760. Throughput: 0: 2751.3, 1: 2636.3. Samples: 164099428. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:43,445][86177] Avg episode reward: [(0, '-547.850'), (1, '-556.300')] -[2023-11-28 08:36:43,523][87424] Updated weights for policy 0, policy_version 320649 (0.0012) -[2023-11-28 08:36:43,902][87424] Updated weights for policy 0, policy_version 320659 (0.0012) -[2023-11-28 08:36:44,287][87424] Updated weights for policy 0, policy_version 320669 (0.0012) -[2023-11-28 08:36:45,237][87426] Updated weights for policy 1, policy_version 320330 (0.0007) -[2023-11-28 08:36:45,619][87426] Updated weights for policy 1, policy_version 320340 (0.0010) -[2023-11-28 08:36:45,999][87426] Updated weights for policy 1, policy_version 320350 (0.0009) -[2023-11-28 08:36:46,872][87424] Updated weights for policy 0, policy_version 320679 (0.0009) -[2023-11-28 08:36:47,247][87424] Updated weights for policy 0, policy_version 320689 (0.0008) -[2023-11-28 08:36:47,633][87424] Updated weights for policy 0, policy_version 320699 (0.0008) -[2023-11-28 08:36:47,720][87426] Updated weights for policy 1, policy_version 320360 (0.0009) -[2023-11-28 08:36:48,100][87426] Updated weights for policy 1, policy_version 320370 (0.0012) -[2023-11-28 08:36:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 164110336. Throughput: 0: 2736.4, 1: 2658.5. Samples: 164123956. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:48,445][86177] Avg episode reward: [(0, '-544.550'), (1, '-550.410')] -[2023-11-28 08:36:48,489][87426] Updated weights for policy 1, policy_version 320380 (0.0012) -[2023-11-28 08:36:49,583][87424] Updated weights for policy 0, policy_version 320709 (0.0010) -[2023-11-28 08:36:49,958][87424] Updated weights for policy 0, policy_version 320719 (0.0012) -[2023-11-28 08:36:50,355][87424] Updated weights for policy 0, policy_version 320729 (0.0012) -[2023-11-28 08:36:50,725][87426] Updated weights for policy 1, policy_version 320390 (0.0012) -[2023-11-28 08:36:51,097][87426] Updated weights for policy 1, policy_version 320400 (0.0012) -[2023-11-28 08:36:51,480][87426] Updated weights for policy 1, policy_version 320410 (0.0011) -[2023-11-28 08:36:52,854][87424] Updated weights for policy 0, policy_version 320739 (0.0012) -[2023-11-28 08:36:53,233][87424] Updated weights for policy 0, policy_version 320749 (0.0009) -[2023-11-28 08:36:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 164134912. Throughput: 0: 2736.2, 1: 2684.6. Samples: 164157840. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:53,445][86177] Avg episode reward: [(0, '-533.060'), (1, '-552.230')] -[2023-11-28 08:36:53,530][87426] Updated weights for policy 1, policy_version 320420 (0.0017) -[2023-11-28 08:36:53,614][87424] Updated weights for policy 0, policy_version 320759 (0.0011) -[2023-11-28 08:36:53,904][87426] Updated weights for policy 1, policy_version 320430 (0.0011) -[2023-11-28 08:36:54,284][87426] Updated weights for policy 1, policy_version 320440 (0.0012) -[2023-11-28 08:36:55,430][87424] Updated weights for policy 0, policy_version 320769 (0.0012) -[2023-11-28 08:36:55,814][87424] Updated weights for policy 0, policy_version 320779 (0.0012) -[2023-11-28 08:36:56,196][87424] Updated weights for policy 0, policy_version 320789 (0.0012) -[2023-11-28 08:36:56,434][87426] Updated weights for policy 1, policy_version 320450 (0.0011) -[2023-11-28 08:36:56,576][87424] Updated weights for policy 0, policy_version 320799 (0.0012) -[2023-11-28 08:36:56,824][87426] Updated weights for policy 1, policy_version 320460 (0.0007) -[2023-11-28 08:36:57,191][87426] Updated weights for policy 1, policy_version 320470 (0.0007) -[2023-11-28 08:36:57,567][87426] Updated weights for policy 1, policy_version 320480 (0.0008) -[2023-11-28 08:36:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 164167680. Throughput: 0: 2752.1, 1: 2691.5. Samples: 164181964. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:36:58,445][86177] Avg episode reward: [(0, '-518.850'), (1, '-554.340')] -[2023-11-28 08:36:58,622][87424] Updated weights for policy 0, policy_version 320809 (0.0009) -[2023-11-28 08:36:58,992][87424] Updated weights for policy 0, policy_version 320819 (0.0011) -[2023-11-28 08:36:59,374][87424] Updated weights for policy 0, policy_version 320829 (0.0011) -[2023-11-28 08:36:59,935][87426] Updated weights for policy 1, policy_version 320490 (0.0010) -[2023-11-28 08:37:00,315][87426] Updated weights for policy 1, policy_version 320500 (0.0011) -[2023-11-28 08:37:00,693][87426] Updated weights for policy 1, policy_version 320510 (0.0011) -[2023-11-28 08:37:01,395][87424] Updated weights for policy 0, policy_version 320839 (0.0011) -[2023-11-28 08:37:01,781][87424] Updated weights for policy 0, policy_version 320849 (0.0012) -[2023-11-28 08:37:02,156][87424] Updated weights for policy 0, policy_version 320859 (0.0012) -[2023-11-28 08:37:03,288][87426] Updated weights for policy 1, policy_version 320520 (0.0010) -[2023-11-28 08:37:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 164192256. Throughput: 0: 2739.8, 1: 2700.7. Samples: 164207192. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:37:03,445][86177] Avg episode reward: [(0, '-511.910'), (1, '-526.050')] -[2023-11-28 08:37:03,672][87426] Updated weights for policy 1, policy_version 320530 (0.0011) -[2023-11-28 08:37:04,046][87426] Updated weights for policy 1, policy_version 320540 (0.0012) -[2023-11-28 08:37:04,345][87424] Updated weights for policy 0, policy_version 320869 (0.0010) -[2023-11-28 08:37:04,736][87424] Updated weights for policy 0, policy_version 320879 (0.0008) -[2023-11-28 08:37:05,121][87424] Updated weights for policy 0, policy_version 320889 (0.0009) -[2023-11-28 08:37:05,799][87426] Updated weights for policy 1, policy_version 320550 (0.0009) -[2023-11-28 08:37:06,172][87426] Updated weights for policy 1, policy_version 320560 (0.0009) -[2023-11-28 08:37:06,561][87426] Updated weights for policy 1, policy_version 320570 (0.0007) -[2023-11-28 08:37:06,990][87424] Updated weights for policy 0, policy_version 320899 (0.0011) -[2023-11-28 08:37:07,362][87424] Updated weights for policy 0, policy_version 320909 (0.0012) -[2023-11-28 08:37:07,742][87424] Updated weights for policy 0, policy_version 320919 (0.0012) -[2023-11-28 08:37:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 164225024. Throughput: 0: 2730.6, 1: 2701.6. Samples: 164239792. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:37:08,445][86177] Avg episode reward: [(0, '-515.440'), (1, '-548.120')] -[2023-11-28 08:37:09,076][87426] Updated weights for policy 1, policy_version 320580 (0.0008) -[2023-11-28 08:37:09,454][87426] Updated weights for policy 1, policy_version 320590 (0.0007) -[2023-11-28 08:37:09,830][87426] Updated weights for policy 1, policy_version 320600 (0.0008) -[2023-11-28 08:37:09,972][87424] Updated weights for policy 0, policy_version 320929 (0.0012) -[2023-11-28 08:37:10,355][87424] Updated weights for policy 0, policy_version 320939 (0.0010) -[2023-11-28 08:37:10,736][87424] Updated weights for policy 0, policy_version 320949 (0.0008) -[2023-11-28 08:37:11,116][87424] Updated weights for policy 0, policy_version 320959 (0.0007) -[2023-11-28 08:37:12,035][87426] Updated weights for policy 1, policy_version 320610 (0.0010) -[2023-11-28 08:37:12,426][87426] Updated weights for policy 1, policy_version 320620 (0.0011) -[2023-11-28 08:37:12,807][87426] Updated weights for policy 1, policy_version 320630 (0.0011) -[2023-11-28 08:37:13,187][87426] Updated weights for policy 1, policy_version 320640 (0.0011) -[2023-11-28 08:37:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 164249600. Throughput: 0: 2719.3, 1: 2700.7. Samples: 164263128. Policy #0 lag: (min: 31.0, avg: 43.5, max: 63.0) -[2023-11-28 08:37:13,445][86177] Avg episode reward: [(0, '-516.300'), (1, '-532.440')] -[2023-11-28 08:37:13,544][87424] Updated weights for policy 0, policy_version 320969 (0.0007) -[2023-11-28 08:37:13,927][87424] Updated weights for policy 0, policy_version 320979 (0.0008) -[2023-11-28 08:37:14,303][87424] Updated weights for policy 0, policy_version 320989 (0.0012) -[2023-11-28 08:37:15,258][87426] Updated weights for policy 1, policy_version 320650 (0.0011) -[2023-11-28 08:37:15,633][87426] Updated weights for policy 1, policy_version 320660 (0.0010) -[2023-11-28 08:37:16,008][87426] Updated weights for policy 1, policy_version 320670 (0.0009) -[2023-11-28 08:37:16,210][87424] Updated weights for policy 0, policy_version 320999 (0.0012) -[2023-11-28 08:37:16,593][87424] Updated weights for policy 0, policy_version 321009 (0.0012) -[2023-11-28 08:37:16,987][87424] Updated weights for policy 0, policy_version 321019 (0.0012) -[2023-11-28 08:37:17,988][87426] Updated weights for policy 1, policy_version 320680 (0.0011) -[2023-11-28 08:37:18,364][87426] Updated weights for policy 1, policy_version 320690 (0.0012) -[2023-11-28 08:37:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 164274176. Throughput: 0: 2720.4, 1: 2728.4. Samples: 164288016. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:37:18,445][86177] Avg episode reward: [(0, '-512.620'), (1, '-519.700')] -[2023-11-28 08:37:18,742][87426] Updated weights for policy 1, policy_version 320700 (0.0012) -[2023-11-28 08:37:19,228][87424] Updated weights for policy 0, policy_version 321029 (0.0010) -[2023-11-28 08:37:19,610][87424] Updated weights for policy 0, policy_version 321039 (0.0007) -[2023-11-28 08:37:19,997][87424] Updated weights for policy 0, policy_version 321049 (0.0009) -[2023-11-28 08:37:21,249][87426] Updated weights for policy 1, policy_version 320710 (0.0012) -[2023-11-28 08:37:21,625][87426] Updated weights for policy 1, policy_version 320720 (0.0011) -[2023-11-28 08:37:21,999][87426] Updated weights for policy 1, policy_version 320730 (0.0010) -[2023-11-28 08:37:22,536][87424] Updated weights for policy 0, policy_version 321059 (0.0010) -[2023-11-28 08:37:22,926][87424] Updated weights for policy 0, policy_version 321069 (0.0008) -[2023-11-28 08:37:23,298][87424] Updated weights for policy 0, policy_version 321079 (0.0008) -[2023-11-28 08:37:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 164298752. Throughput: 0: 2685.8, 1: 2721.6. Samples: 164319380. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:37:23,445][86177] Avg episode reward: [(0, '-511.510'), (1, '-547.860')] -[2023-11-28 08:37:24,665][87426] Updated weights for policy 1, policy_version 320740 (0.0008) -[2023-11-28 08:37:25,034][87426] Updated weights for policy 1, policy_version 320750 (0.0008) -[2023-11-28 08:37:25,410][87426] Updated weights for policy 1, policy_version 320760 (0.0008) -[2023-11-28 08:37:25,830][87424] Updated weights for policy 0, policy_version 321089 (0.0008) -[2023-11-28 08:37:26,212][87424] Updated weights for policy 0, policy_version 321099 (0.0012) -[2023-11-28 08:37:26,597][87424] Updated weights for policy 0, policy_version 321109 (0.0012) -[2023-11-28 08:37:26,992][87424] Updated weights for policy 0, policy_version 321119 (0.0012) -[2023-11-28 08:37:27,141][87426] Updated weights for policy 1, policy_version 320770 (0.0009) -[2023-11-28 08:37:27,510][87426] Updated weights for policy 1, policy_version 320780 (0.0008) -[2023-11-28 08:37:27,891][87426] Updated weights for policy 1, policy_version 320790 (0.0008) -[2023-11-28 08:37:28,273][87426] Updated weights for policy 1, policy_version 320800 (0.0008) -[2023-11-28 08:37:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 164331520. Throughput: 0: 2703.6, 1: 2713.4. Samples: 164343192. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:37:28,445][86177] Avg episode reward: [(0, '-520.330'), (1, '-550.470')] -[2023-11-28 08:37:28,927][87424] Updated weights for policy 0, policy_version 321129 (0.0009) -[2023-11-28 08:37:29,308][87424] Updated weights for policy 0, policy_version 321139 (0.0008) -[2023-11-28 08:37:29,703][87424] Updated weights for policy 0, policy_version 321149 (0.0007) -[2023-11-28 08:37:30,725][87426] Updated weights for policy 1, policy_version 320810 (0.0012) -[2023-11-28 08:37:31,096][87426] Updated weights for policy 1, policy_version 320820 (0.0012) -[2023-11-28 08:37:31,453][87424] Updated weights for policy 0, policy_version 321159 (0.0009) -[2023-11-28 08:37:31,475][87426] Updated weights for policy 1, policy_version 320830 (0.0011) -[2023-11-28 08:37:31,835][87424] Updated weights for policy 0, policy_version 321169 (0.0008) -[2023-11-28 08:37:32,214][87424] Updated weights for policy 0, policy_version 321179 (0.0009) -[2023-11-28 08:37:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 164356096. Throughput: 0: 2746.2, 1: 2690.0. Samples: 164368584. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:37:33,445][86177] Avg episode reward: [(0, '-529.750'), (1, '-549.640')] -[2023-11-28 08:37:33,968][87424] Updated weights for policy 0, policy_version 321189 (0.0010) -[2023-11-28 08:37:34,021][87426] Updated weights for policy 1, policy_version 320840 (0.0011) -[2023-11-28 08:37:34,340][87424] Updated weights for policy 0, policy_version 321199 (0.0010) -[2023-11-28 08:37:34,401][87426] Updated weights for policy 1, policy_version 320850 (0.0008) -[2023-11-28 08:37:34,724][87424] Updated weights for policy 0, policy_version 321209 (0.0012) -[2023-11-28 08:37:34,781][87426] Updated weights for policy 1, policy_version 320860 (0.0008) -[2023-11-28 08:37:36,647][87426] Updated weights for policy 1, policy_version 320870 (0.0008) -[2023-11-28 08:37:37,018][87426] Updated weights for policy 1, policy_version 320880 (0.0008) -[2023-11-28 08:37:37,084][87424] Updated weights for policy 0, policy_version 321219 (0.0012) -[2023-11-28 08:37:37,398][87426] Updated weights for policy 1, policy_version 320890 (0.0008) -[2023-11-28 08:37:37,462][87424] Updated weights for policy 0, policy_version 321229 (0.0012) -[2023-11-28 08:37:37,849][87424] Updated weights for policy 0, policy_version 321239 (0.0011) -[2023-11-28 08:37:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 164388864. Throughput: 0: 2747.1, 1: 2669.9. Samples: 164401604. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:37:38,445][86177] Avg episode reward: [(0, '-559.500'), (1, '-572.140')] -[2023-11-28 08:37:39,159][87426] Updated weights for policy 1, policy_version 320900 (0.0011) -[2023-11-28 08:37:39,533][87426] Updated weights for policy 1, policy_version 320910 (0.0011) -[2023-11-28 08:37:39,836][87424] Updated weights for policy 0, policy_version 321249 (0.0008) -[2023-11-28 08:37:39,918][87426] Updated weights for policy 1, policy_version 320920 (0.0012) -[2023-11-28 08:37:40,224][87424] Updated weights for policy 0, policy_version 321259 (0.0011) -[2023-11-28 08:37:40,604][87424] Updated weights for policy 0, policy_version 321269 (0.0012) -[2023-11-28 08:37:40,987][87424] Updated weights for policy 0, policy_version 321279 (0.0012) -[2023-11-28 08:37:42,374][87426] Updated weights for policy 1, policy_version 320930 (0.0011) -[2023-11-28 08:37:42,746][87426] Updated weights for policy 1, policy_version 320940 (0.0012) -[2023-11-28 08:37:43,119][87426] Updated weights for policy 1, policy_version 320950 (0.0011) -[2023-11-28 08:37:43,419][87424] Updated weights for policy 0, policy_version 321289 (0.0011) -[2023-11-28 08:37:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 164405248. Throughput: 0: 2738.8, 1: 2684.8. Samples: 164426024. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:37:43,445][86177] Avg episode reward: [(0, '-559.160'), (1, '-574.220')] -[2023-11-28 08:37:43,498][87426] Updated weights for policy 1, policy_version 320960 (0.0011) -[2023-11-28 08:37:43,798][87424] Updated weights for policy 0, policy_version 321299 (0.0012) -[2023-11-28 08:37:44,181][87424] Updated weights for policy 0, policy_version 321309 (0.0009) -[2023-11-28 08:37:45,550][87426] Updated weights for policy 1, policy_version 320970 (0.0008) -[2023-11-28 08:37:45,934][87426] Updated weights for policy 1, policy_version 320980 (0.0007) -[2023-11-28 08:37:46,306][87426] Updated weights for policy 1, policy_version 320990 (0.0009) -[2023-11-28 08:37:46,401][87424] Updated weights for policy 0, policy_version 321319 (0.0010) -[2023-11-28 08:37:46,791][87424] Updated weights for policy 0, policy_version 321329 (0.0012) -[2023-11-28 08:37:47,177][87424] Updated weights for policy 0, policy_version 321339 (0.0012) -[2023-11-28 08:37:48,013][87426] Updated weights for policy 1, policy_version 321000 (0.0008) -[2023-11-28 08:37:48,404][87426] Updated weights for policy 1, policy_version 321010 (0.0011) -[2023-11-28 08:37:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 164438016. Throughput: 0: 2723.8, 1: 2690.0. Samples: 164450816. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:37:48,445][86177] Avg episode reward: [(0, '-553.330'), (1, '-552.220')] -[2023-11-28 08:37:48,778][87426] Updated weights for policy 1, policy_version 321020 (0.0009) -[2023-11-28 08:37:49,540][87424] Updated weights for policy 0, policy_version 321349 (0.0010) -[2023-11-28 08:37:49,914][87424] Updated weights for policy 0, policy_version 321359 (0.0008) -[2023-11-28 08:37:50,298][87424] Updated weights for policy 0, policy_version 321369 (0.0008) -[2023-11-28 08:37:51,160][87426] Updated weights for policy 1, policy_version 321030 (0.0010) -[2023-11-28 08:37:51,539][87426] Updated weights for policy 1, policy_version 321040 (0.0012) -[2023-11-28 08:37:51,933][87426] Updated weights for policy 1, policy_version 321050 (0.0011) -[2023-11-28 08:37:52,768][87424] Updated weights for policy 0, policy_version 321379 (0.0011) -[2023-11-28 08:37:53,151][87424] Updated weights for policy 0, policy_version 321389 (0.0012) -[2023-11-28 08:37:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 164462592. Throughput: 0: 2694.8, 1: 2696.4. Samples: 164482392. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:37:53,445][86177] Avg episode reward: [(0, '-556.130'), (1, '-553.360')] -[2023-11-28 08:37:53,542][87424] Updated weights for policy 0, policy_version 321399 (0.0012) -[2023-11-28 08:37:54,105][87426] Updated weights for policy 1, policy_version 321060 (0.0009) -[2023-11-28 08:37:54,486][87426] Updated weights for policy 1, policy_version 321070 (0.0008) -[2023-11-28 08:37:54,874][87426] Updated weights for policy 1, policy_version 321080 (0.0007) -[2023-11-28 08:37:56,065][87424] Updated weights for policy 0, policy_version 321409 (0.0011) -[2023-11-28 08:37:56,438][87424] Updated weights for policy 0, policy_version 321419 (0.0007) -[2023-11-28 08:37:56,821][87424] Updated weights for policy 0, policy_version 321429 (0.0007) -[2023-11-28 08:37:57,201][87426] Updated weights for policy 1, policy_version 321090 (0.0008) -[2023-11-28 08:37:57,204][87424] Updated weights for policy 0, policy_version 321439 (0.0007) -[2023-11-28 08:37:57,572][87426] Updated weights for policy 1, policy_version 321100 (0.0008) -[2023-11-28 08:37:57,948][87426] Updated weights for policy 1, policy_version 321110 (0.0008) -[2023-11-28 08:37:58,329][87426] Updated weights for policy 1, policy_version 321120 (0.0007) -[2023-11-28 08:37:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 164495360. Throughput: 0: 2685.2, 1: 2690.1. Samples: 164505016. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:37:58,445][86177] Avg episode reward: [(0, '-527.640'), (1, '-534.040')] -[2023-11-28 08:37:59,597][87424] Updated weights for policy 0, policy_version 321449 (0.0011) -[2023-11-28 08:37:59,978][87424] Updated weights for policy 0, policy_version 321459 (0.0012) -[2023-11-28 08:38:00,356][87424] Updated weights for policy 0, policy_version 321469 (0.0012) -[2023-11-28 08:38:00,597][87426] Updated weights for policy 1, policy_version 321130 (0.0009) -[2023-11-28 08:38:00,980][87426] Updated weights for policy 1, policy_version 321140 (0.0007) -[2023-11-28 08:38:01,361][87426] Updated weights for policy 1, policy_version 321150 (0.0007) -[2023-11-28 08:38:02,232][87424] Updated weights for policy 0, policy_version 321479 (0.0009) -[2023-11-28 08:38:02,613][87424] Updated weights for policy 0, policy_version 321489 (0.0008) -[2023-11-28 08:38:02,987][87424] Updated weights for policy 0, policy_version 321499 (0.0009) -[2023-11-28 08:38:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 164519936. Throughput: 0: 2695.9, 1: 2678.5. Samples: 164529864. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:38:03,445][86177] Avg episode reward: [(0, '-520.730'), (1, '-532.520')] -[2023-11-28 08:38:03,611][87426] Updated weights for policy 1, policy_version 321160 (0.0008) -[2023-11-28 08:38:03,986][87426] Updated weights for policy 1, policy_version 321170 (0.0007) -[2023-11-28 08:38:04,365][87426] Updated weights for policy 1, policy_version 321180 (0.0008) -[2023-11-28 08:38:05,206][87424] Updated weights for policy 0, policy_version 321509 (0.0009) -[2023-11-28 08:38:05,591][87424] Updated weights for policy 0, policy_version 321519 (0.0007) -[2023-11-28 08:38:05,971][87424] Updated weights for policy 0, policy_version 321529 (0.0007) -[2023-11-28 08:38:06,691][87426] Updated weights for policy 1, policy_version 321190 (0.0010) -[2023-11-28 08:38:07,065][87426] Updated weights for policy 1, policy_version 321200 (0.0011) -[2023-11-28 08:38:07,444][87426] Updated weights for policy 1, policy_version 321210 (0.0010) -[2023-11-28 08:38:08,412][87424] Updated weights for policy 0, policy_version 321539 (0.0009) -[2023-11-28 08:38:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 164544512. Throughput: 0: 2728.7, 1: 2671.0. Samples: 164562368. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:38:08,446][86177] Avg episode reward: [(0, '-519.400'), (1, '-531.950')] -[2023-11-28 08:38:08,785][87424] Updated weights for policy 0, policy_version 321549 (0.0012) -[2023-11-28 08:38:09,171][87424] Updated weights for policy 0, policy_version 321559 (0.0011) -[2023-11-28 08:38:09,276][87426] Updated weights for policy 1, policy_version 321220 (0.0010) -[2023-11-28 08:38:09,665][87426] Updated weights for policy 1, policy_version 321230 (0.0012) -[2023-11-28 08:38:10,051][87426] Updated weights for policy 1, policy_version 321240 (0.0009) -[2023-11-28 08:38:11,318][87424] Updated weights for policy 0, policy_version 321569 (0.0011) -[2023-11-28 08:38:11,708][87424] Updated weights for policy 0, policy_version 321579 (0.0012) -[2023-11-28 08:38:11,763][87426] Updated weights for policy 1, policy_version 321250 (0.0009) -[2023-11-28 08:38:12,083][87424] Updated weights for policy 0, policy_version 321589 (0.0012) -[2023-11-28 08:38:12,143][87426] Updated weights for policy 1, policy_version 321260 (0.0012) -[2023-11-28 08:38:12,465][87424] Updated weights for policy 0, policy_version 321599 (0.0011) -[2023-11-28 08:38:12,522][87426] Updated weights for policy 1, policy_version 321270 (0.0010) -[2023-11-28 08:38:12,901][87426] Updated weights for policy 1, policy_version 321280 (0.0012) -[2023-11-28 08:38:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 164577280. Throughput: 0: 2715.9, 1: 2702.9. Samples: 164587040. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:38:13,445][86177] Avg episode reward: [(0, '-520.220'), (1, '-533.660')] -[2023-11-28 08:38:14,652][87424] Updated weights for policy 0, policy_version 321609 (0.0012) -[2023-11-28 08:38:15,037][87424] Updated weights for policy 0, policy_version 321619 (0.0012) -[2023-11-28 08:38:15,416][87424] Updated weights for policy 0, policy_version 321629 (0.0011) -[2023-11-28 08:38:15,470][87426] Updated weights for policy 1, policy_version 321290 (0.0011) -[2023-11-28 08:38:15,854][87426] Updated weights for policy 1, policy_version 321300 (0.0012) -[2023-11-28 08:38:16,228][87426] Updated weights for policy 1, policy_version 321310 (0.0011) -[2023-11-28 08:38:17,248][87424] Updated weights for policy 0, policy_version 321639 (0.0011) -[2023-11-28 08:38:17,631][87424] Updated weights for policy 0, policy_version 321649 (0.0011) -[2023-11-28 08:38:18,017][87424] Updated weights for policy 0, policy_version 321659 (0.0011) -[2023-11-28 08:38:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 164601856. Throughput: 0: 2686.6, 1: 2717.4. Samples: 164611764. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:38:18,445][86177] Avg episode reward: [(0, '-520.560'), (1, '-495.380')] -[2023-11-28 08:38:18,451][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000321664_82345984.pth... -[2023-11-28 08:38:18,468][87426] Updated weights for policy 1, policy_version 321320 (0.0011) -[2023-11-28 08:38:18,498][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000319104_81690624.pth -[2023-11-28 08:38:18,853][87426] Updated weights for policy 1, policy_version 321330 (0.0008) -[2023-11-28 08:38:19,227][87426] Updated weights for policy 1, policy_version 321340 (0.0011) -[2023-11-28 08:38:19,366][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000321344_82264064.pth... -[2023-11-28 08:38:19,397][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000318816_81616896.pth -[2023-11-28 08:38:20,199][87424] Updated weights for policy 0, policy_version 321669 (0.0012) -[2023-11-28 08:38:20,580][87424] Updated weights for policy 0, policy_version 321679 (0.0012) -[2023-11-28 08:38:20,963][87424] Updated weights for policy 0, policy_version 321689 (0.0012) -[2023-11-28 08:38:21,448][87426] Updated weights for policy 1, policy_version 321350 (0.0011) -[2023-11-28 08:38:21,826][87426] Updated weights for policy 1, policy_version 321360 (0.0015) -[2023-11-28 08:38:22,203][87426] Updated weights for policy 1, policy_version 321370 (0.0009) -[2023-11-28 08:38:23,427][87424] Updated weights for policy 0, policy_version 321699 (0.0012) -[2023-11-28 08:38:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 164626432. Throughput: 0: 2657.1, 1: 2710.9. Samples: 164643164. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:38:23,445][86177] Avg episode reward: [(0, '-518.370'), (1, '-494.230')] -[2023-11-28 08:38:23,817][87424] Updated weights for policy 0, policy_version 321709 (0.0011) -[2023-11-28 08:38:24,189][87424] Updated weights for policy 0, policy_version 321719 (0.0010) -[2023-11-28 08:38:24,796][87426] Updated weights for policy 1, policy_version 321380 (0.0008) -[2023-11-28 08:38:25,187][87426] Updated weights for policy 1, policy_version 321390 (0.0007) -[2023-11-28 08:38:25,559][87426] Updated weights for policy 1, policy_version 321400 (0.0009) -[2023-11-28 08:38:26,033][87424] Updated weights for policy 0, policy_version 321729 (0.0007) -[2023-11-28 08:38:26,426][87424] Updated weights for policy 0, policy_version 321739 (0.0008) -[2023-11-28 08:38:26,797][87424] Updated weights for policy 0, policy_version 321749 (0.0007) -[2023-11-28 08:38:27,182][87424] Updated weights for policy 0, policy_version 321759 (0.0008) -[2023-11-28 08:38:27,311][87426] Updated weights for policy 1, policy_version 321410 (0.0012) -[2023-11-28 08:38:27,701][87426] Updated weights for policy 1, policy_version 321420 (0.0007) -[2023-11-28 08:38:28,094][87426] Updated weights for policy 1, policy_version 321430 (0.0010) -[2023-11-28 08:38:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 164651008. Throughput: 0: 2676.7, 1: 2710.8. Samples: 164668460. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:38:28,445][86177] Avg episode reward: [(0, '-521.680'), (1, '-496.050')] -[2023-11-28 08:38:28,466][87426] Updated weights for policy 1, policy_version 321440 (0.0011) -[2023-11-28 08:38:29,441][87424] Updated weights for policy 0, policy_version 321769 (0.0011) -[2023-11-28 08:38:29,824][87424] Updated weights for policy 0, policy_version 321779 (0.0012) -[2023-11-28 08:38:30,207][87424] Updated weights for policy 0, policy_version 321789 (0.0011) -[2023-11-28 08:38:30,244][87426] Updated weights for policy 1, policy_version 321450 (0.0012) -[2023-11-28 08:38:30,619][87426] Updated weights for policy 1, policy_version 321460 (0.0012) -[2023-11-28 08:38:30,996][87426] Updated weights for policy 1, policy_version 321470 (0.0012) -[2023-11-28 08:38:32,748][87424] Updated weights for policy 0, policy_version 321799 (0.0009) -[2023-11-28 08:38:33,136][87424] Updated weights for policy 0, policy_version 321809 (0.0008) -[2023-11-28 08:38:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 164675584. Throughput: 0: 2673.8, 1: 2706.0. Samples: 164692908. Policy #0 lag: (min: 22.0, avg: 44.4, max: 59.0) -[2023-11-28 08:38:33,445][86177] Avg episode reward: [(0, '-521.750'), (1, '-501.830')] -[2023-11-28 08:38:33,515][87424] Updated weights for policy 0, policy_version 321819 (0.0008) -[2023-11-28 08:38:33,542][87426] Updated weights for policy 1, policy_version 321480 (0.0009) -[2023-11-28 08:38:33,920][87426] Updated weights for policy 1, policy_version 321490 (0.0007) -[2023-11-28 08:38:34,295][87426] Updated weights for policy 1, policy_version 321500 (0.0007) -[2023-11-28 08:38:35,349][87424] Updated weights for policy 0, policy_version 321829 (0.0008) -[2023-11-28 08:38:35,742][87424] Updated weights for policy 0, policy_version 321839 (0.0011) -[2023-11-28 08:38:36,124][87424] Updated weights for policy 0, policy_version 321849 (0.0012) -[2023-11-28 08:38:36,711][87426] Updated weights for policy 1, policy_version 321510 (0.0009) -[2023-11-28 08:38:37,083][87426] Updated weights for policy 1, policy_version 321520 (0.0011) -[2023-11-28 08:38:37,452][87426] Updated weights for policy 1, policy_version 321530 (0.0011) -[2023-11-28 08:38:38,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 164708352. Throughput: 0: 2682.9, 1: 2696.9. Samples: 164724484. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:38:38,446][86177] Avg episode reward: [(0, '-521.910'), (1, '-513.420')] -[2023-11-28 08:38:38,606][87424] Updated weights for policy 0, policy_version 321859 (0.0010) -[2023-11-28 08:38:38,990][87424] Updated weights for policy 0, policy_version 321869 (0.0009) -[2023-11-28 08:38:39,368][87424] Updated weights for policy 0, policy_version 321879 (0.0008) -[2023-11-28 08:38:40,019][87426] Updated weights for policy 1, policy_version 321540 (0.0010) -[2023-11-28 08:38:40,385][87426] Updated weights for policy 1, policy_version 321550 (0.0011) -[2023-11-28 08:38:40,764][87426] Updated weights for policy 1, policy_version 321560 (0.0008) -[2023-11-28 08:38:41,686][87424] Updated weights for policy 0, policy_version 321889 (0.0010) -[2023-11-28 08:38:42,065][87424] Updated weights for policy 0, policy_version 321899 (0.0012) -[2023-11-28 08:38:42,450][87424] Updated weights for policy 0, policy_version 321909 (0.0011) -[2023-11-28 08:38:42,828][87424] Updated weights for policy 0, policy_version 321919 (0.0010) -[2023-11-28 08:38:43,336][87426] Updated weights for policy 1, policy_version 321570 (0.0009) -[2023-11-28 08:38:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 164732928. Throughput: 0: 2687.3, 1: 2702.9. Samples: 164747576. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:38:43,445][86177] Avg episode reward: [(0, '-522.010'), (1, '-525.730')] -[2023-11-28 08:38:43,704][87426] Updated weights for policy 1, policy_version 321580 (0.0008) -[2023-11-28 08:38:44,086][87426] Updated weights for policy 1, policy_version 321590 (0.0008) -[2023-11-28 08:38:44,470][87426] Updated weights for policy 1, policy_version 321600 (0.0009) -[2023-11-28 08:38:45,240][87424] Updated weights for policy 0, policy_version 321929 (0.0011) -[2023-11-28 08:38:45,624][87424] Updated weights for policy 0, policy_version 321939 (0.0008) -[2023-11-28 08:38:46,009][87424] Updated weights for policy 0, policy_version 321949 (0.0012) -[2023-11-28 08:38:47,019][87426] Updated weights for policy 1, policy_version 321610 (0.0009) -[2023-11-28 08:38:47,409][87426] Updated weights for policy 1, policy_version 321620 (0.0007) -[2023-11-28 08:38:47,784][87426] Updated weights for policy 1, policy_version 321630 (0.0007) -[2023-11-28 08:38:48,297][87424] Updated weights for policy 0, policy_version 321959 (0.0009) -[2023-11-28 08:38:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 164757504. Throughput: 0: 2664.7, 1: 2696.8. Samples: 164771132. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:38:48,445][86177] Avg episode reward: [(0, '-518.300'), (1, '-525.300')] -[2023-11-28 08:38:48,681][87424] Updated weights for policy 0, policy_version 321969 (0.0008) -[2023-11-28 08:38:49,068][87424] Updated weights for policy 0, policy_version 321979 (0.0008) -[2023-11-28 08:38:50,307][87426] Updated weights for policy 1, policy_version 321640 (0.0011) -[2023-11-28 08:38:50,689][87426] Updated weights for policy 1, policy_version 321650 (0.0010) -[2023-11-28 08:38:51,066][87426] Updated weights for policy 1, policy_version 321660 (0.0007) -[2023-11-28 08:38:51,429][87424] Updated weights for policy 0, policy_version 321989 (0.0010) -[2023-11-28 08:38:51,815][87424] Updated weights for policy 0, policy_version 321999 (0.0010) -[2023-11-28 08:38:52,196][87424] Updated weights for policy 0, policy_version 322009 (0.0008) -[2023-11-28 08:38:53,207][87426] Updated weights for policy 1, policy_version 321670 (0.0011) -[2023-11-28 08:38:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 164782080. Throughput: 0: 2652.6, 1: 2675.0. Samples: 164802112. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:38:53,445][86177] Avg episode reward: [(0, '-520.550'), (1, '-517.700')] -[2023-11-28 08:38:53,575][87426] Updated weights for policy 1, policy_version 321680 (0.0012) -[2023-11-28 08:38:53,957][87426] Updated weights for policy 1, policy_version 321690 (0.0011) -[2023-11-28 08:38:54,382][87424] Updated weights for policy 0, policy_version 322019 (0.0009) -[2023-11-28 08:38:54,759][87424] Updated weights for policy 0, policy_version 322029 (0.0012) -[2023-11-28 08:38:55,146][87424] Updated weights for policy 0, policy_version 322039 (0.0012) -[2023-11-28 08:38:55,818][87426] Updated weights for policy 1, policy_version 321700 (0.0010) -[2023-11-28 08:38:56,195][87426] Updated weights for policy 1, policy_version 321710 (0.0007) -[2023-11-28 08:38:56,575][87426] Updated weights for policy 1, policy_version 321720 (0.0010) -[2023-11-28 08:38:57,029][87424] Updated weights for policy 0, policy_version 322049 (0.0012) -[2023-11-28 08:38:57,405][87424] Updated weights for policy 0, policy_version 322059 (0.0010) -[2023-11-28 08:38:57,786][87424] Updated weights for policy 0, policy_version 322069 (0.0008) -[2023-11-28 08:38:58,170][87424] Updated weights for policy 0, policy_version 322079 (0.0008) -[2023-11-28 08:38:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 164814848. Throughput: 0: 2657.9, 1: 2677.4. Samples: 164827128. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:38:58,445][86177] Avg episode reward: [(0, '-527.770'), (1, '-506.600')] -[2023-11-28 08:38:58,561][87426] Updated weights for policy 1, policy_version 321730 (0.0011) -[2023-11-28 08:38:58,943][87426] Updated weights for policy 1, policy_version 321740 (0.0008) -[2023-11-28 08:38:59,315][87426] Updated weights for policy 1, policy_version 321750 (0.0007) -[2023-11-28 08:38:59,697][87426] Updated weights for policy 1, policy_version 321760 (0.0008) -[2023-11-28 08:39:00,497][87424] Updated weights for policy 0, policy_version 322089 (0.0011) -[2023-11-28 08:39:00,876][87424] Updated weights for policy 0, policy_version 322099 (0.0011) -[2023-11-28 08:39:01,259][87424] Updated weights for policy 0, policy_version 322109 (0.0012) -[2023-11-28 08:39:02,114][87426] Updated weights for policy 1, policy_version 321770 (0.0012) -[2023-11-28 08:39:02,496][87426] Updated weights for policy 1, policy_version 321780 (0.0012) -[2023-11-28 08:39:02,886][87426] Updated weights for policy 1, policy_version 321790 (0.0012) -[2023-11-28 08:39:03,340][87424] Updated weights for policy 0, policy_version 322119 (0.0011) -[2023-11-28 08:39:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 164839424. Throughput: 0: 2655.0, 1: 2661.3. Samples: 164851000. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:03,445][86177] Avg episode reward: [(0, '-527.380'), (1, '-516.590')] -[2023-11-28 08:39:03,723][87424] Updated weights for policy 0, policy_version 322129 (0.0009) -[2023-11-28 08:39:04,109][87424] Updated weights for policy 0, policy_version 322139 (0.0009) -[2023-11-28 08:39:04,835][87426] Updated weights for policy 1, policy_version 321800 (0.0009) -[2023-11-28 08:39:05,219][87426] Updated weights for policy 1, policy_version 321810 (0.0010) -[2023-11-28 08:39:05,601][87426] Updated weights for policy 1, policy_version 321820 (0.0007) -[2023-11-28 08:39:05,982][87424] Updated weights for policy 0, policy_version 322149 (0.0012) -[2023-11-28 08:39:06,363][87424] Updated weights for policy 0, policy_version 322159 (0.0012) -[2023-11-28 08:39:06,747][87424] Updated weights for policy 0, policy_version 322169 (0.0012) -[2023-11-28 08:39:07,665][87426] Updated weights for policy 1, policy_version 321830 (0.0011) -[2023-11-28 08:39:08,039][87426] Updated weights for policy 1, policy_version 321840 (0.0014) -[2023-11-28 08:39:08,412][87426] Updated weights for policy 1, policy_version 321850 (0.0014) -[2023-11-28 08:39:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 164864000. Throughput: 0: 2675.5, 1: 2686.7. Samples: 164884460. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:08,445][86177] Avg episode reward: [(0, '-529.810'), (1, '-536.250')] -[2023-11-28 08:39:09,195][87424] Updated weights for policy 0, policy_version 322179 (0.0011) -[2023-11-28 08:39:09,580][87424] Updated weights for policy 0, policy_version 322189 (0.0008) -[2023-11-28 08:39:09,965][87424] Updated weights for policy 0, policy_version 322199 (0.0010) -[2023-11-28 08:39:10,817][87426] Updated weights for policy 1, policy_version 321860 (0.0012) -[2023-11-28 08:39:11,206][87426] Updated weights for policy 1, policy_version 321870 (0.0012) -[2023-11-28 08:39:11,574][87426] Updated weights for policy 1, policy_version 321880 (0.0010) -[2023-11-28 08:39:12,278][87424] Updated weights for policy 0, policy_version 322209 (0.0011) -[2023-11-28 08:39:12,654][87424] Updated weights for policy 0, policy_version 322219 (0.0012) -[2023-11-28 08:39:13,036][87424] Updated weights for policy 0, policy_version 322229 (0.0012) -[2023-11-28 08:39:13,413][87424] Updated weights for policy 0, policy_version 322239 (0.0010) -[2023-11-28 08:39:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 164888576. Throughput: 0: 2653.4, 1: 2671.9. Samples: 164908100. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:13,445][86177] Avg episode reward: [(0, '-526.710'), (1, '-537.530')] -[2023-11-28 08:39:13,664][87426] Updated weights for policy 1, policy_version 321890 (0.0009) -[2023-11-28 08:39:14,048][87426] Updated weights for policy 1, policy_version 321900 (0.0010) -[2023-11-28 08:39:14,418][87426] Updated weights for policy 1, policy_version 321910 (0.0008) -[2023-11-28 08:39:14,799][87426] Updated weights for policy 1, policy_version 321920 (0.0008) -[2023-11-28 08:39:15,278][87424] Updated weights for policy 0, policy_version 322249 (0.0011) -[2023-11-28 08:39:15,655][87424] Updated weights for policy 0, policy_version 322259 (0.0012) -[2023-11-28 08:39:16,030][87424] Updated weights for policy 0, policy_version 322269 (0.0012) -[2023-11-28 08:39:17,031][87426] Updated weights for policy 1, policy_version 321930 (0.0012) -[2023-11-28 08:39:17,402][87426] Updated weights for policy 1, policy_version 321940 (0.0012) -[2023-11-28 08:39:17,769][87426] Updated weights for policy 1, policy_version 321950 (0.0011) -[2023-11-28 08:39:18,116][87424] Updated weights for policy 0, policy_version 322279 (0.0012) -[2023-11-28 08:39:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 164921344. Throughput: 0: 2660.3, 1: 2678.3. Samples: 164933144. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:18,446][86177] Avg episode reward: [(0, '-526.070'), (1, '-552.060')] -[2023-11-28 08:39:18,497][87424] Updated weights for policy 0, policy_version 322289 (0.0011) -[2023-11-28 08:39:18,878][87424] Updated weights for policy 0, policy_version 322299 (0.0011) -[2023-11-28 08:39:20,297][87426] Updated weights for policy 1, policy_version 321960 (0.0012) -[2023-11-28 08:39:20,677][87426] Updated weights for policy 1, policy_version 321970 (0.0011) -[2023-11-28 08:39:20,851][87424] Updated weights for policy 0, policy_version 322309 (0.0012) -[2023-11-28 08:39:21,053][87426] Updated weights for policy 1, policy_version 321980 (0.0012) -[2023-11-28 08:39:21,231][87424] Updated weights for policy 0, policy_version 322319 (0.0012) -[2023-11-28 08:39:21,610][87424] Updated weights for policy 0, policy_version 322329 (0.0011) -[2023-11-28 08:39:23,166][87426] Updated weights for policy 1, policy_version 321990 (0.0011) -[2023-11-28 08:39:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 164945920. Throughput: 0: 2687.4, 1: 2684.7. Samples: 164966228. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:23,445][86177] Avg episode reward: [(0, '-534.990'), (1, '-561.680')] -[2023-11-28 08:39:23,546][87426] Updated weights for policy 1, policy_version 322000 (0.0011) -[2023-11-28 08:39:23,924][87426] Updated weights for policy 1, policy_version 322010 (0.0011) -[2023-11-28 08:39:24,065][87424] Updated weights for policy 0, policy_version 322339 (0.0009) -[2023-11-28 08:39:24,449][87424] Updated weights for policy 0, policy_version 322349 (0.0012) -[2023-11-28 08:39:24,831][87424] Updated weights for policy 0, policy_version 322359 (0.0012) -[2023-11-28 08:39:25,826][87426] Updated weights for policy 1, policy_version 322020 (0.0011) -[2023-11-28 08:39:26,208][87426] Updated weights for policy 1, policy_version 322030 (0.0011) -[2023-11-28 08:39:26,588][87426] Updated weights for policy 1, policy_version 322040 (0.0011) -[2023-11-28 08:39:26,606][87424] Updated weights for policy 0, policy_version 322369 (0.0011) -[2023-11-28 08:39:26,985][87424] Updated weights for policy 0, policy_version 322379 (0.0012) -[2023-11-28 08:39:27,369][87424] Updated weights for policy 0, policy_version 322389 (0.0012) -[2023-11-28 08:39:27,757][87424] Updated weights for policy 0, policy_version 322399 (0.0012) -[2023-11-28 08:39:28,233][87426] Updated weights for policy 1, policy_version 322050 (0.0012) -[2023-11-28 08:39:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 164978688. Throughput: 0: 2698.1, 1: 2704.3. Samples: 164990680. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:28,445][86177] Avg episode reward: [(0, '-532.810'), (1, '-573.410')] -[2023-11-28 08:39:28,618][87426] Updated weights for policy 1, policy_version 322060 (0.0011) -[2023-11-28 08:39:28,990][87426] Updated weights for policy 1, policy_version 322070 (0.0011) -[2023-11-28 08:39:29,369][87426] Updated weights for policy 1, policy_version 322080 (0.0012) -[2023-11-28 08:39:30,296][87424] Updated weights for policy 0, policy_version 322409 (0.0018) -[2023-11-28 08:39:30,679][87424] Updated weights for policy 0, policy_version 322419 (0.0008) -[2023-11-28 08:39:31,063][87424] Updated weights for policy 0, policy_version 322429 (0.0008) -[2023-11-28 08:39:31,392][87426] Updated weights for policy 1, policy_version 322090 (0.0011) -[2023-11-28 08:39:31,761][87426] Updated weights for policy 1, policy_version 322100 (0.0011) -[2023-11-28 08:39:32,148][87426] Updated weights for policy 1, policy_version 322110 (0.0012) -[2023-11-28 08:39:33,404][87424] Updated weights for policy 0, policy_version 322439 (0.0010) -[2023-11-28 08:39:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165003264. Throughput: 0: 2709.2, 1: 2708.6. Samples: 165014932. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:33,446][86177] Avg episode reward: [(0, '-523.900'), (1, '-565.660')] -[2023-11-28 08:39:33,785][87424] Updated weights for policy 0, policy_version 322449 (0.0012) -[2023-11-28 08:39:34,156][87424] Updated weights for policy 0, policy_version 322459 (0.0012) -[2023-11-28 08:39:34,487][87426] Updated weights for policy 1, policy_version 322120 (0.0011) -[2023-11-28 08:39:34,858][87426] Updated weights for policy 1, policy_version 322130 (0.0012) -[2023-11-28 08:39:35,237][87426] Updated weights for policy 1, policy_version 322140 (0.0012) -[2023-11-28 08:39:36,201][87424] Updated weights for policy 0, policy_version 322469 (0.0012) -[2023-11-28 08:39:36,577][87424] Updated weights for policy 0, policy_version 322479 (0.0009) -[2023-11-28 08:39:36,958][87424] Updated weights for policy 0, policy_version 322489 (0.0008) -[2023-11-28 08:39:37,588][87426] Updated weights for policy 1, policy_version 322150 (0.0011) -[2023-11-28 08:39:37,964][87426] Updated weights for policy 1, policy_version 322160 (0.0012) -[2023-11-28 08:39:38,346][87426] Updated weights for policy 1, policy_version 322170 (0.0012) -[2023-11-28 08:39:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165027840. Throughput: 0: 2711.0, 1: 2751.6. Samples: 165047932. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:38,445][86177] Avg episode reward: [(0, '-522.690'), (1, '-568.940')] -[2023-11-28 08:39:39,287][87424] Updated weights for policy 0, policy_version 322499 (0.0011) -[2023-11-28 08:39:39,660][87424] Updated weights for policy 0, policy_version 322509 (0.0011) -[2023-11-28 08:39:40,060][87424] Updated weights for policy 0, policy_version 322519 (0.0010) -[2023-11-28 08:39:40,799][87426] Updated weights for policy 1, policy_version 322180 (0.0012) -[2023-11-28 08:39:41,176][87426] Updated weights for policy 1, policy_version 322190 (0.0012) -[2023-11-28 08:39:41,558][87426] Updated weights for policy 1, policy_version 322200 (0.0012) -[2023-11-28 08:39:42,101][87424] Updated weights for policy 0, policy_version 322529 (0.0012) -[2023-11-28 08:39:42,482][87424] Updated weights for policy 0, policy_version 322539 (0.0011) -[2023-11-28 08:39:42,855][87424] Updated weights for policy 0, policy_version 322549 (0.0011) -[2023-11-28 08:39:43,235][87424] Updated weights for policy 0, policy_version 322559 (0.0009) -[2023-11-28 08:39:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 165060608. Throughput: 0: 2720.1, 1: 2712.4. Samples: 165071592. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:43,445][86177] Avg episode reward: [(0, '-512.010'), (1, '-548.700')] -[2023-11-28 08:39:43,971][87426] Updated weights for policy 1, policy_version 322210 (0.0012) -[2023-11-28 08:39:44,346][87426] Updated weights for policy 1, policy_version 322220 (0.0008) -[2023-11-28 08:39:44,723][87426] Updated weights for policy 1, policy_version 322230 (0.0007) -[2023-11-28 08:39:45,097][87426] Updated weights for policy 1, policy_version 322240 (0.0008) -[2023-11-28 08:39:45,531][87424] Updated weights for policy 0, policy_version 322569 (0.0010) -[2023-11-28 08:39:45,905][87424] Updated weights for policy 0, policy_version 322579 (0.0010) -[2023-11-28 08:39:46,285][87424] Updated weights for policy 0, policy_version 322589 (0.0009) -[2023-11-28 08:39:47,600][87426] Updated weights for policy 1, policy_version 322250 (0.0008) -[2023-11-28 08:39:47,981][87426] Updated weights for policy 1, policy_version 322260 (0.0008) -[2023-11-28 08:39:48,285][87424] Updated weights for policy 0, policy_version 322599 (0.0009) -[2023-11-28 08:39:48,370][87426] Updated weights for policy 1, policy_version 322270 (0.0008) -[2023-11-28 08:39:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165085184. Throughput: 0: 2727.2, 1: 2722.6. Samples: 165096240. Policy #0 lag: (min: 11.0, avg: 42.3, max: 73.0) -[2023-11-28 08:39:48,445][86177] Avg episode reward: [(0, '-516.690'), (1, '-540.450')] -[2023-11-28 08:39:48,667][87424] Updated weights for policy 0, policy_version 322609 (0.0007) -[2023-11-28 08:39:49,057][87424] Updated weights for policy 0, policy_version 322619 (0.0009) -[2023-11-28 08:39:50,524][87426] Updated weights for policy 1, policy_version 322280 (0.0010) -[2023-11-28 08:39:50,901][87426] Updated weights for policy 1, policy_version 322290 (0.0010) -[2023-11-28 08:39:51,276][87426] Updated weights for policy 1, policy_version 322300 (0.0010) -[2023-11-28 08:39:51,328][87424] Updated weights for policy 0, policy_version 322629 (0.0009) -[2023-11-28 08:39:51,709][87424] Updated weights for policy 0, policy_version 322639 (0.0009) -[2023-11-28 08:39:52,093][87424] Updated weights for policy 0, policy_version 322649 (0.0010) -[2023-11-28 08:39:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165109760. Throughput: 0: 2724.6, 1: 2684.9. Samples: 165127888. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:39:53,445][86177] Avg episode reward: [(0, '-515.930'), (1, '-536.690')] -[2023-11-28 08:39:53,536][87426] Updated weights for policy 1, policy_version 322310 (0.0010) -[2023-11-28 08:39:53,912][87426] Updated weights for policy 1, policy_version 322320 (0.0011) -[2023-11-28 08:39:54,295][87426] Updated weights for policy 1, policy_version 322330 (0.0012) -[2023-11-28 08:39:54,483][87424] Updated weights for policy 0, policy_version 322659 (0.0010) -[2023-11-28 08:39:54,867][87424] Updated weights for policy 0, policy_version 322669 (0.0008) -[2023-11-28 08:39:55,253][87424] Updated weights for policy 0, policy_version 322679 (0.0009) -[2023-11-28 08:39:56,307][87426] Updated weights for policy 1, policy_version 322340 (0.0011) -[2023-11-28 08:39:56,689][87426] Updated weights for policy 1, policy_version 322350 (0.0012) -[2023-11-28 08:39:57,073][87426] Updated weights for policy 1, policy_version 322360 (0.0012) -[2023-11-28 08:39:57,539][87424] Updated weights for policy 0, policy_version 322689 (0.0008) -[2023-11-28 08:39:57,925][87424] Updated weights for policy 0, policy_version 322699 (0.0011) -[2023-11-28 08:39:58,316][87424] Updated weights for policy 0, policy_version 322709 (0.0010) -[2023-11-28 08:39:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165134336. Throughput: 0: 2721.4, 1: 2721.7. Samples: 165153040. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:39:58,445][86177] Avg episode reward: [(0, '-518.230'), (1, '-530.740')] -[2023-11-28 08:39:58,696][87424] Updated weights for policy 0, policy_version 322719 (0.0010) -[2023-11-28 08:39:58,766][87426] Updated weights for policy 1, policy_version 322370 (0.0011) -[2023-11-28 08:39:59,145][87426] Updated weights for policy 1, policy_version 322380 (0.0007) -[2023-11-28 08:39:59,526][87426] Updated weights for policy 1, policy_version 322390 (0.0011) -[2023-11-28 08:39:59,905][87426] Updated weights for policy 1, policy_version 322400 (0.0012) -[2023-11-28 08:40:01,167][87424] Updated weights for policy 0, policy_version 322729 (0.0008) -[2023-11-28 08:40:01,543][87424] Updated weights for policy 0, policy_version 322739 (0.0007) -[2023-11-28 08:40:01,935][87424] Updated weights for policy 0, policy_version 322749 (0.0011) -[2023-11-28 08:40:02,419][87426] Updated weights for policy 1, policy_version 322410 (0.0011) -[2023-11-28 08:40:02,802][87426] Updated weights for policy 1, policy_version 322420 (0.0012) -[2023-11-28 08:40:03,171][87426] Updated weights for policy 1, policy_version 322430 (0.0012) -[2023-11-28 08:40:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165167104. Throughput: 0: 2691.6, 1: 2708.0. Samples: 165176124. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:03,445][86177] Avg episode reward: [(0, '-519.130'), (1, '-531.570')] -[2023-11-28 08:40:03,921][87424] Updated weights for policy 0, policy_version 322759 (0.0008) -[2023-11-28 08:40:04,310][87424] Updated weights for policy 0, policy_version 322769 (0.0008) -[2023-11-28 08:40:04,686][87424] Updated weights for policy 0, policy_version 322779 (0.0008) -[2023-11-28 08:40:05,122][87426] Updated weights for policy 1, policy_version 322440 (0.0009) -[2023-11-28 08:40:05,507][87426] Updated weights for policy 1, policy_version 322450 (0.0010) -[2023-11-28 08:40:05,880][87426] Updated weights for policy 1, policy_version 322460 (0.0008) -[2023-11-28 08:40:06,979][87424] Updated weights for policy 0, policy_version 322789 (0.0010) -[2023-11-28 08:40:07,361][87424] Updated weights for policy 0, policy_version 322799 (0.0012) -[2023-11-28 08:40:07,745][87424] Updated weights for policy 0, policy_version 322809 (0.0012) -[2023-11-28 08:40:08,246][87426] Updated weights for policy 1, policy_version 322470 (0.0011) -[2023-11-28 08:40:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 165191680. Throughput: 0: 2680.2, 1: 2711.6. Samples: 165208856. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:08,445][86177] Avg episode reward: [(0, '-514.890'), (1, '-577.170')] -[2023-11-28 08:40:08,614][87426] Updated weights for policy 1, policy_version 322480 (0.0012) -[2023-11-28 08:40:08,993][87426] Updated weights for policy 1, policy_version 322490 (0.0012) -[2023-11-28 08:40:09,992][87424] Updated weights for policy 0, policy_version 322819 (0.0012) -[2023-11-28 08:40:10,371][87424] Updated weights for policy 0, policy_version 322829 (0.0011) -[2023-11-28 08:40:10,752][87424] Updated weights for policy 0, policy_version 322839 (0.0008) -[2023-11-28 08:40:11,485][87426] Updated weights for policy 1, policy_version 322500 (0.0010) -[2023-11-28 08:40:11,863][87426] Updated weights for policy 1, policy_version 322510 (0.0010) -[2023-11-28 08:40:12,236][87426] Updated weights for policy 1, policy_version 322520 (0.0011) -[2023-11-28 08:40:12,961][87424] Updated weights for policy 0, policy_version 322849 (0.0008) -[2023-11-28 08:40:13,339][87424] Updated weights for policy 0, policy_version 322859 (0.0008) -[2023-11-28 08:40:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165216256. Throughput: 0: 2677.2, 1: 2683.6. Samples: 165231916. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:13,445][86177] Avg episode reward: [(0, '-521.230'), (1, '-578.150')] -[2023-11-28 08:40:13,727][87424] Updated weights for policy 0, policy_version 322869 (0.0009) -[2023-11-28 08:40:14,107][87424] Updated weights for policy 0, policy_version 322879 (0.0011) -[2023-11-28 08:40:14,785][87426] Updated weights for policy 1, policy_version 322530 (0.0010) -[2023-11-28 08:40:15,160][87426] Updated weights for policy 1, policy_version 322540 (0.0007) -[2023-11-28 08:40:15,540][87426] Updated weights for policy 1, policy_version 322550 (0.0009) -[2023-11-28 08:40:15,918][87426] Updated weights for policy 1, policy_version 322560 (0.0010) -[2023-11-28 08:40:16,243][87424] Updated weights for policy 0, policy_version 322889 (0.0007) -[2023-11-28 08:40:16,625][87424] Updated weights for policy 0, policy_version 322899 (0.0008) -[2023-11-28 08:40:17,001][87424] Updated weights for policy 0, policy_version 322909 (0.0008) -[2023-11-28 08:40:17,730][87426] Updated weights for policy 1, policy_version 322570 (0.0010) -[2023-11-28 08:40:18,107][87426] Updated weights for policy 1, policy_version 322580 (0.0008) -[2023-11-28 08:40:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 165240832. Throughput: 0: 2690.2, 1: 2674.2. Samples: 165256332. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:18,445][86177] Avg episode reward: [(0, '-516.520'), (1, '-566.360')] -[2023-11-28 08:40:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000322912_82665472.pth... -[2023-11-28 08:40:18,488][87426] Updated weights for policy 1, policy_version 322590 (0.0007) -[2023-11-28 08:40:18,500][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000320384_82018304.pth -[2023-11-28 08:40:18,563][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000322592_82583552.pth... -[2023-11-28 08:40:18,611][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000320064_81936384.pth -[2023-11-28 08:40:18,972][87424] Updated weights for policy 0, policy_version 322919 (0.0009) -[2023-11-28 08:40:19,355][87424] Updated weights for policy 0, policy_version 322929 (0.0009) -[2023-11-28 08:40:19,738][87424] Updated weights for policy 0, policy_version 322939 (0.0012) -[2023-11-28 08:40:20,736][87426] Updated weights for policy 1, policy_version 322600 (0.0011) -[2023-11-28 08:40:21,108][87426] Updated weights for policy 1, policy_version 322610 (0.0012) -[2023-11-28 08:40:21,487][87426] Updated weights for policy 1, policy_version 322620 (0.0011) -[2023-11-28 08:40:22,318][87424] Updated weights for policy 0, policy_version 322949 (0.0012) -[2023-11-28 08:40:22,697][87424] Updated weights for policy 0, policy_version 322959 (0.0012) -[2023-11-28 08:40:23,086][87424] Updated weights for policy 0, policy_version 322969 (0.0010) -[2023-11-28 08:40:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165273600. Throughput: 0: 2686.8, 1: 2670.8. Samples: 165289024. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:23,445][86177] Avg episode reward: [(0, '-519.460'), (1, '-579.680')] -[2023-11-28 08:40:23,753][87426] Updated weights for policy 1, policy_version 322630 (0.0012) -[2023-11-28 08:40:24,135][87426] Updated weights for policy 1, policy_version 322640 (0.0012) -[2023-11-28 08:40:24,511][87426] Updated weights for policy 1, policy_version 322650 (0.0012) -[2023-11-28 08:40:25,142][87424] Updated weights for policy 0, policy_version 322979 (0.0011) -[2023-11-28 08:40:25,533][87424] Updated weights for policy 0, policy_version 322989 (0.0011) -[2023-11-28 08:40:25,901][87424] Updated weights for policy 0, policy_version 322999 (0.0012) -[2023-11-28 08:40:26,323][87426] Updated weights for policy 1, policy_version 322660 (0.0011) -[2023-11-28 08:40:26,705][87426] Updated weights for policy 1, policy_version 322670 (0.0007) -[2023-11-28 08:40:27,078][87426] Updated weights for policy 1, policy_version 322680 (0.0008) -[2023-11-28 08:40:28,122][87424] Updated weights for policy 0, policy_version 323009 (0.0012) -[2023-11-28 08:40:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165298176. Throughput: 0: 2697.8, 1: 2696.4. Samples: 165314328. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:28,445][86177] Avg episode reward: [(0, '-522.570'), (1, '-561.350')] -[2023-11-28 08:40:28,507][87424] Updated weights for policy 0, policy_version 323019 (0.0011) -[2023-11-28 08:40:28,888][87424] Updated weights for policy 0, policy_version 323029 (0.0010) -[2023-11-28 08:40:29,248][87426] Updated weights for policy 1, policy_version 322690 (0.0008) -[2023-11-28 08:40:29,274][87424] Updated weights for policy 0, policy_version 323039 (0.0012) -[2023-11-28 08:40:29,630][87426] Updated weights for policy 1, policy_version 322700 (0.0009) -[2023-11-28 08:40:30,022][87426] Updated weights for policy 1, policy_version 322710 (0.0009) -[2023-11-28 08:40:30,404][87426] Updated weights for policy 1, policy_version 322720 (0.0008) -[2023-11-28 08:40:31,537][87424] Updated weights for policy 0, policy_version 323049 (0.0011) -[2023-11-28 08:40:31,923][87424] Updated weights for policy 0, policy_version 323059 (0.0009) -[2023-11-28 08:40:32,282][87426] Updated weights for policy 1, policy_version 322730 (0.0009) -[2023-11-28 08:40:32,300][87424] Updated weights for policy 0, policy_version 323069 (0.0011) -[2023-11-28 08:40:32,667][87426] Updated weights for policy 1, policy_version 322740 (0.0008) -[2023-11-28 08:40:33,047][87426] Updated weights for policy 1, policy_version 322750 (0.0008) -[2023-11-28 08:40:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165330944. Throughput: 0: 2697.1, 1: 2705.9. Samples: 165339372. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:33,445][86177] Avg episode reward: [(0, '-518.810'), (1, '-529.080')] -[2023-11-28 08:40:34,616][87424] Updated weights for policy 0, policy_version 323079 (0.0009) -[2023-11-28 08:40:35,007][87424] Updated weights for policy 0, policy_version 323089 (0.0009) -[2023-11-28 08:40:35,376][87424] Updated weights for policy 0, policy_version 323099 (0.0009) -[2023-11-28 08:40:35,560][87426] Updated weights for policy 1, policy_version 322760 (0.0008) -[2023-11-28 08:40:35,937][87426] Updated weights for policy 1, policy_version 322770 (0.0007) -[2023-11-28 08:40:36,312][87426] Updated weights for policy 1, policy_version 322780 (0.0007) -[2023-11-28 08:40:37,442][87424] Updated weights for policy 0, policy_version 323109 (0.0010) -[2023-11-28 08:40:37,822][87424] Updated weights for policy 0, policy_version 323119 (0.0009) -[2023-11-28 08:40:38,205][87424] Updated weights for policy 0, policy_version 323129 (0.0008) -[2023-11-28 08:40:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 165347328. Throughput: 0: 2696.7, 1: 2715.2. Samples: 165371424. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:38,445][86177] Avg episode reward: [(0, '-520.640'), (1, '-565.440')] -[2023-11-28 08:40:38,696][87426] Updated weights for policy 1, policy_version 322790 (0.0010) -[2023-11-28 08:40:39,063][87426] Updated weights for policy 1, policy_version 322800 (0.0012) -[2023-11-28 08:40:39,445][87426] Updated weights for policy 1, policy_version 322810 (0.0012) -[2023-11-28 08:40:40,119][87424] Updated weights for policy 0, policy_version 323139 (0.0008) -[2023-11-28 08:40:40,502][87424] Updated weights for policy 0, policy_version 323149 (0.0009) -[2023-11-28 08:40:40,882][87424] Updated weights for policy 0, policy_version 323159 (0.0008) -[2023-11-28 08:40:41,406][87426] Updated weights for policy 1, policy_version 322820 (0.0010) -[2023-11-28 08:40:41,786][87426] Updated weights for policy 1, policy_version 322830 (0.0011) -[2023-11-28 08:40:42,165][87426] Updated weights for policy 1, policy_version 322840 (0.0012) -[2023-11-28 08:40:43,379][87424] Updated weights for policy 0, policy_version 323169 (0.0012) -[2023-11-28 08:40:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165380096. Throughput: 0: 2711.6, 1: 2696.2. Samples: 165396388. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:43,445][86177] Avg episode reward: [(0, '-517.660'), (1, '-569.100')] -[2023-11-28 08:40:43,762][87424] Updated weights for policy 0, policy_version 323179 (0.0012) -[2023-11-28 08:40:44,138][87424] Updated weights for policy 0, policy_version 323189 (0.0011) -[2023-11-28 08:40:44,521][87424] Updated weights for policy 0, policy_version 323199 (0.0012) -[2023-11-28 08:40:44,547][87426] Updated weights for policy 1, policy_version 322850 (0.0011) -[2023-11-28 08:40:44,924][87426] Updated weights for policy 1, policy_version 322860 (0.0008) -[2023-11-28 08:40:45,299][87426] Updated weights for policy 1, policy_version 322870 (0.0008) -[2023-11-28 08:40:45,680][87426] Updated weights for policy 1, policy_version 322880 (0.0008) -[2023-11-28 08:40:46,691][87424] Updated weights for policy 0, policy_version 323209 (0.0012) -[2023-11-28 08:40:47,071][87424] Updated weights for policy 0, policy_version 323219 (0.0012) -[2023-11-28 08:40:47,453][87424] Updated weights for policy 0, policy_version 323229 (0.0012) -[2023-11-28 08:40:47,671][87426] Updated weights for policy 1, policy_version 322890 (0.0007) -[2023-11-28 08:40:48,050][87426] Updated weights for policy 1, policy_version 322900 (0.0009) -[2023-11-28 08:40:48,431][87426] Updated weights for policy 1, policy_version 322910 (0.0010) -[2023-11-28 08:40:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165404672. Throughput: 0: 2730.6, 1: 2706.0. Samples: 165420772. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:48,446][86177] Avg episode reward: [(0, '-517.360'), (1, '-561.450')] -[2023-11-28 08:40:49,388][87424] Updated weights for policy 0, policy_version 323239 (0.0012) -[2023-11-28 08:40:49,768][87424] Updated weights for policy 0, policy_version 323249 (0.0012) -[2023-11-28 08:40:50,151][87424] Updated weights for policy 0, policy_version 323259 (0.0008) -[2023-11-28 08:40:50,487][87426] Updated weights for policy 1, policy_version 322920 (0.0009) -[2023-11-28 08:40:50,869][87426] Updated weights for policy 1, policy_version 322930 (0.0008) -[2023-11-28 08:40:51,251][87426] Updated weights for policy 1, policy_version 322940 (0.0008) -[2023-11-28 08:40:52,184][87424] Updated weights for policy 0, policy_version 323269 (0.0010) -[2023-11-28 08:40:52,564][87424] Updated weights for policy 0, policy_version 323279 (0.0011) -[2023-11-28 08:40:52,947][87424] Updated weights for policy 0, policy_version 323289 (0.0014) -[2023-11-28 08:40:53,445][86177] Fps is (10 sec: 5734.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 165437440. Throughput: 0: 2734.1, 1: 2716.7. Samples: 165454144. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:53,446][86177] Avg episode reward: [(0, '-527.580'), (1, '-569.260')] -[2023-11-28 08:40:53,606][87426] Updated weights for policy 1, policy_version 322950 (0.0010) -[2023-11-28 08:40:53,983][87426] Updated weights for policy 1, policy_version 322960 (0.0012) -[2023-11-28 08:40:54,363][87426] Updated weights for policy 1, policy_version 322970 (0.0012) -[2023-11-28 08:40:55,196][87424] Updated weights for policy 0, policy_version 323299 (0.0010) -[2023-11-28 08:40:55,578][87424] Updated weights for policy 0, policy_version 323309 (0.0008) -[2023-11-28 08:40:55,968][87424] Updated weights for policy 0, policy_version 323319 (0.0010) -[2023-11-28 08:40:56,975][87426] Updated weights for policy 1, policy_version 322980 (0.0012) -[2023-11-28 08:40:57,356][87426] Updated weights for policy 1, policy_version 322990 (0.0012) -[2023-11-28 08:40:57,738][87426] Updated weights for policy 1, policy_version 323000 (0.0011) -[2023-11-28 08:40:58,240][87424] Updated weights for policy 0, policy_version 323329 (0.0008) -[2023-11-28 08:40:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165462016. Throughput: 0: 2748.5, 1: 2707.1. Samples: 165477420. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:40:58,445][86177] Avg episode reward: [(0, '-526.750'), (1, '-546.770')] -[2023-11-28 08:40:58,626][87424] Updated weights for policy 0, policy_version 323339 (0.0011) -[2023-11-28 08:40:59,009][87424] Updated weights for policy 0, policy_version 323349 (0.0011) -[2023-11-28 08:40:59,385][87424] Updated weights for policy 0, policy_version 323359 (0.0011) -[2023-11-28 08:40:59,441][87426] Updated weights for policy 1, policy_version 323010 (0.0012) -[2023-11-28 08:40:59,831][87426] Updated weights for policy 1, policy_version 323020 (0.0012) -[2023-11-28 08:41:00,217][87426] Updated weights for policy 1, policy_version 323030 (0.0012) -[2023-11-28 08:41:00,597][87426] Updated weights for policy 1, policy_version 323040 (0.0010) -[2023-11-28 08:41:01,490][87424] Updated weights for policy 0, policy_version 323369 (0.0008) -[2023-11-28 08:41:01,872][87424] Updated weights for policy 0, policy_version 323379 (0.0011) -[2023-11-28 08:41:02,254][87424] Updated weights for policy 0, policy_version 323389 (0.0008) -[2023-11-28 08:41:02,928][87426] Updated weights for policy 1, policy_version 323050 (0.0008) -[2023-11-28 08:41:03,305][87426] Updated weights for policy 1, policy_version 323060 (0.0007) -[2023-11-28 08:41:03,444][86177] Fps is (10 sec: 4915.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165486592. Throughput: 0: 2731.2, 1: 2733.1. Samples: 165502224. Policy #0 lag: (min: 23.0, avg: 32.3, max: 55.0) -[2023-11-28 08:41:03,445][86177] Avg episode reward: [(0, '-529.410'), (1, '-530.600')] -[2023-11-28 08:41:03,685][87426] Updated weights for policy 1, policy_version 323070 (0.0009) -[2023-11-28 08:41:04,658][87424] Updated weights for policy 0, policy_version 323399 (0.0010) -[2023-11-28 08:41:05,040][87424] Updated weights for policy 0, policy_version 323409 (0.0009) -[2023-11-28 08:41:05,409][87424] Updated weights for policy 0, policy_version 323419 (0.0010) -[2023-11-28 08:41:05,496][87426] Updated weights for policy 1, policy_version 323080 (0.0007) -[2023-11-28 08:41:05,871][87426] Updated weights for policy 1, policy_version 323090 (0.0007) -[2023-11-28 08:41:06,252][87426] Updated weights for policy 1, policy_version 323100 (0.0007) -[2023-11-28 08:41:07,613][87424] Updated weights for policy 0, policy_version 323429 (0.0012) -[2023-11-28 08:41:07,996][87424] Updated weights for policy 0, policy_version 323439 (0.0009) -[2023-11-28 08:41:08,138][87426] Updated weights for policy 1, policy_version 323110 (0.0008) -[2023-11-28 08:41:08,383][87424] Updated weights for policy 0, policy_version 323449 (0.0009) -[2023-11-28 08:41:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165511168. Throughput: 0: 2729.5, 1: 2730.3. Samples: 165534716. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:08,445][86177] Avg episode reward: [(0, '-528.020'), (1, '-538.560')] -[2023-11-28 08:41:08,511][87426] Updated weights for policy 1, policy_version 323120 (0.0011) -[2023-11-28 08:41:08,891][87426] Updated weights for policy 1, policy_version 323130 (0.0011) -[2023-11-28 08:41:10,764][87424] Updated weights for policy 0, policy_version 323459 (0.0010) -[2023-11-28 08:41:11,148][87424] Updated weights for policy 0, policy_version 323469 (0.0012) -[2023-11-28 08:41:11,177][87426] Updated weights for policy 1, policy_version 323140 (0.0011) -[2023-11-28 08:41:11,532][87424] Updated weights for policy 0, policy_version 323479 (0.0012) -[2023-11-28 08:41:11,558][87426] Updated weights for policy 1, policy_version 323150 (0.0011) -[2023-11-28 08:41:11,936][87426] Updated weights for policy 1, policy_version 323160 (0.0010) -[2023-11-28 08:41:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165543936. Throughput: 0: 2709.9, 1: 2710.8. Samples: 165558260. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:13,445][86177] Avg episode reward: [(0, '-519.160'), (1, '-554.190')] -[2023-11-28 08:41:14,022][87424] Updated weights for policy 0, policy_version 323489 (0.0012) -[2023-11-28 08:41:14,330][87426] Updated weights for policy 1, policy_version 323170 (0.0010) -[2023-11-28 08:41:14,405][87424] Updated weights for policy 0, policy_version 323499 (0.0009) -[2023-11-28 08:41:14,709][87426] Updated weights for policy 1, policy_version 323180 (0.0009) -[2023-11-28 08:41:14,784][87424] Updated weights for policy 0, policy_version 323509 (0.0008) -[2023-11-28 08:41:15,087][87426] Updated weights for policy 1, policy_version 323190 (0.0008) -[2023-11-28 08:41:15,173][87424] Updated weights for policy 0, policy_version 323519 (0.0008) -[2023-11-28 08:41:15,473][87426] Updated weights for policy 1, policy_version 323200 (0.0010) -[2023-11-28 08:41:17,034][87424] Updated weights for policy 0, policy_version 323529 (0.0012) -[2023-11-28 08:41:17,414][87424] Updated weights for policy 0, policy_version 323539 (0.0011) -[2023-11-28 08:41:17,650][87426] Updated weights for policy 1, policy_version 323210 (0.0012) -[2023-11-28 08:41:17,797][87424] Updated weights for policy 0, policy_version 323549 (0.0008) -[2023-11-28 08:41:18,031][87426] Updated weights for policy 1, policy_version 323220 (0.0010) -[2023-11-28 08:41:18,402][87426] Updated weights for policy 1, policy_version 323230 (0.0008) -[2023-11-28 08:41:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165568512. Throughput: 0: 2693.8, 1: 2715.7. Samples: 165582796. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:18,445][86177] Avg episode reward: [(0, '-526.130'), (1, '-557.330')] -[2023-11-28 08:41:19,949][87424] Updated weights for policy 0, policy_version 323559 (0.0010) -[2023-11-28 08:41:20,333][87424] Updated weights for policy 0, policy_version 323569 (0.0011) -[2023-11-28 08:41:20,705][87424] Updated weights for policy 0, policy_version 323579 (0.0011) -[2023-11-28 08:41:20,907][87426] Updated weights for policy 1, policy_version 323240 (0.0008) -[2023-11-28 08:41:21,284][87426] Updated weights for policy 1, policy_version 323250 (0.0012) -[2023-11-28 08:41:21,659][87426] Updated weights for policy 1, policy_version 323260 (0.0011) -[2023-11-28 08:41:23,062][87424] Updated weights for policy 0, policy_version 323589 (0.0010) -[2023-11-28 08:41:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165593088. Throughput: 0: 2702.9, 1: 2712.2. Samples: 165615104. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:23,445][86177] Avg episode reward: [(0, '-530.260'), (1, '-565.730')] -[2023-11-28 08:41:23,447][87424] Updated weights for policy 0, policy_version 323599 (0.0011) -[2023-11-28 08:41:23,618][87426] Updated weights for policy 1, policy_version 323270 (0.0010) -[2023-11-28 08:41:23,828][87424] Updated weights for policy 0, policy_version 323609 (0.0010) -[2023-11-28 08:41:23,997][87426] Updated weights for policy 1, policy_version 323280 (0.0012) -[2023-11-28 08:41:24,370][87426] Updated weights for policy 1, policy_version 323290 (0.0011) -[2023-11-28 08:41:25,694][87424] Updated weights for policy 0, policy_version 323619 (0.0012) -[2023-11-28 08:41:26,073][87424] Updated weights for policy 0, policy_version 323629 (0.0012) -[2023-11-28 08:41:26,450][87424] Updated weights for policy 0, policy_version 323639 (0.0012) -[2023-11-28 08:41:26,637][87426] Updated weights for policy 1, policy_version 323300 (0.0009) -[2023-11-28 08:41:27,017][87426] Updated weights for policy 1, policy_version 323310 (0.0011) -[2023-11-28 08:41:27,401][87426] Updated weights for policy 1, policy_version 323320 (0.0012) -[2023-11-28 08:41:28,050][87424] Updated weights for policy 0, policy_version 323649 (0.0011) -[2023-11-28 08:41:28,434][87424] Updated weights for policy 0, policy_version 323659 (0.0010) -[2023-11-28 08:41:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 165625856. Throughput: 0: 2707.4, 1: 2697.9. Samples: 165639624. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:28,445][86177] Avg episode reward: [(0, '-525.170'), (1, '-550.340')] -[2023-11-28 08:41:28,819][87424] Updated weights for policy 0, policy_version 323669 (0.0010) -[2023-11-28 08:41:29,210][87424] Updated weights for policy 0, policy_version 323679 (0.0008) -[2023-11-28 08:41:29,933][87426] Updated weights for policy 1, policy_version 323330 (0.0011) -[2023-11-28 08:41:30,324][87426] Updated weights for policy 1, policy_version 323340 (0.0008) -[2023-11-28 08:41:30,702][87426] Updated weights for policy 1, policy_version 323350 (0.0012) -[2023-11-28 08:41:31,078][87426] Updated weights for policy 1, policy_version 323360 (0.0011) -[2023-11-28 08:41:31,440][87424] Updated weights for policy 0, policy_version 323689 (0.0007) -[2023-11-28 08:41:31,825][87424] Updated weights for policy 0, policy_version 323699 (0.0010) -[2023-11-28 08:41:32,209][87424] Updated weights for policy 0, policy_version 323709 (0.0010) -[2023-11-28 08:41:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 165650432. Throughput: 0: 2711.4, 1: 2672.8. Samples: 165663060. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:33,445][86177] Avg episode reward: [(0, '-521.120'), (1, '-542.170')] -[2023-11-28 08:41:33,687][87426] Updated weights for policy 1, policy_version 323370 (0.0008) -[2023-11-28 08:41:34,058][87426] Updated weights for policy 1, policy_version 323380 (0.0010) -[2023-11-28 08:41:34,437][87426] Updated weights for policy 1, policy_version 323390 (0.0008) -[2023-11-28 08:41:34,534][87424] Updated weights for policy 0, policy_version 323719 (0.0008) -[2023-11-28 08:41:34,915][87424] Updated weights for policy 0, policy_version 323729 (0.0011) -[2023-11-28 08:41:35,295][87424] Updated weights for policy 0, policy_version 323739 (0.0012) -[2023-11-28 08:41:36,829][87426] Updated weights for policy 1, policy_version 323400 (0.0011) -[2023-11-28 08:41:37,098][87424] Updated weights for policy 0, policy_version 323749 (0.0011) -[2023-11-28 08:41:37,200][87426] Updated weights for policy 1, policy_version 323410 (0.0010) -[2023-11-28 08:41:37,477][87424] Updated weights for policy 0, policy_version 323759 (0.0011) -[2023-11-28 08:41:37,571][87426] Updated weights for policy 1, policy_version 323420 (0.0012) -[2023-11-28 08:41:37,864][87424] Updated weights for policy 0, policy_version 323769 (0.0008) -[2023-11-28 08:41:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 165683200. Throughput: 0: 2728.9, 1: 2641.2. Samples: 165695796. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:38,445][86177] Avg episode reward: [(0, '-521.480'), (1, '-543.730')] -[2023-11-28 08:41:39,639][87426] Updated weights for policy 1, policy_version 323430 (0.0011) -[2023-11-28 08:41:40,009][87426] Updated weights for policy 1, policy_version 323440 (0.0012) -[2023-11-28 08:41:40,105][87424] Updated weights for policy 0, policy_version 323779 (0.0009) -[2023-11-28 08:41:40,394][87426] Updated weights for policy 1, policy_version 323450 (0.0011) -[2023-11-28 08:41:40,479][87424] Updated weights for policy 0, policy_version 323789 (0.0012) -[2023-11-28 08:41:40,870][87424] Updated weights for policy 0, policy_version 323799 (0.0009) -[2023-11-28 08:41:42,849][87426] Updated weights for policy 1, policy_version 323460 (0.0012) -[2023-11-28 08:41:42,921][87424] Updated weights for policy 0, policy_version 323809 (0.0008) -[2023-11-28 08:41:43,226][87426] Updated weights for policy 1, policy_version 323470 (0.0012) -[2023-11-28 08:41:43,310][87424] Updated weights for policy 0, policy_version 323819 (0.0009) -[2023-11-28 08:41:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165699584. Throughput: 0: 2725.0, 1: 2668.5. Samples: 165720128. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:43,445][86177] Avg episode reward: [(0, '-519.700'), (1, '-534.130')] -[2023-11-28 08:41:43,612][87426] Updated weights for policy 1, policy_version 323480 (0.0010) -[2023-11-28 08:41:43,688][87424] Updated weights for policy 0, policy_version 323829 (0.0009) -[2023-11-28 08:41:44,063][87424] Updated weights for policy 0, policy_version 323839 (0.0012) -[2023-11-28 08:41:45,594][87426] Updated weights for policy 1, policy_version 323490 (0.0011) -[2023-11-28 08:41:45,970][87426] Updated weights for policy 1, policy_version 323500 (0.0012) -[2023-11-28 08:41:46,073][87424] Updated weights for policy 0, policy_version 323849 (0.0011) -[2023-11-28 08:41:46,353][87426] Updated weights for policy 1, policy_version 323510 (0.0010) -[2023-11-28 08:41:46,462][87424] Updated weights for policy 0, policy_version 323859 (0.0010) -[2023-11-28 08:41:46,728][87426] Updated weights for policy 1, policy_version 323520 (0.0008) -[2023-11-28 08:41:46,842][87424] Updated weights for policy 0, policy_version 323869 (0.0008) -[2023-11-28 08:41:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 165732352. Throughput: 0: 2744.4, 1: 2668.4. Samples: 165745804. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:48,445][86177] Avg episode reward: [(0, '-521.060'), (1, '-524.060')] -[2023-11-28 08:41:48,710][87426] Updated weights for policy 1, policy_version 323530 (0.0008) -[2023-11-28 08:41:49,095][87426] Updated weights for policy 1, policy_version 323540 (0.0010) -[2023-11-28 08:41:49,104][87424] Updated weights for policy 0, policy_version 323879 (0.0011) -[2023-11-28 08:41:49,479][87426] Updated weights for policy 1, policy_version 323550 (0.0012) -[2023-11-28 08:41:49,489][87424] Updated weights for policy 0, policy_version 323889 (0.0012) -[2023-11-28 08:41:49,870][87424] Updated weights for policy 0, policy_version 323899 (0.0012) -[2023-11-28 08:41:51,543][87426] Updated weights for policy 1, policy_version 323560 (0.0008) -[2023-11-28 08:41:51,940][87426] Updated weights for policy 1, policy_version 323570 (0.0012) -[2023-11-28 08:41:52,307][87426] Updated weights for policy 1, policy_version 323580 (0.0009) -[2023-11-28 08:41:52,440][87424] Updated weights for policy 0, policy_version 323909 (0.0010) -[2023-11-28 08:41:52,823][87424] Updated weights for policy 0, policy_version 323919 (0.0008) -[2023-11-28 08:41:53,206][87424] Updated weights for policy 0, policy_version 323929 (0.0008) -[2023-11-28 08:41:53,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 165756928. Throughput: 0: 2754.9, 1: 2673.1. Samples: 165778980. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:53,445][86177] Avg episode reward: [(0, '-522.460'), (1, '-509.060')] -[2023-11-28 08:41:54,581][87426] Updated weights for policy 1, policy_version 323590 (0.0008) -[2023-11-28 08:41:54,958][87426] Updated weights for policy 1, policy_version 323600 (0.0009) -[2023-11-28 08:41:55,336][87426] Updated weights for policy 1, policy_version 323610 (0.0010) -[2023-11-28 08:41:55,761][87424] Updated weights for policy 0, policy_version 323939 (0.0010) -[2023-11-28 08:41:56,138][87424] Updated weights for policy 0, policy_version 323949 (0.0008) -[2023-11-28 08:41:56,518][87424] Updated weights for policy 0, policy_version 323959 (0.0008) -[2023-11-28 08:41:56,914][87426] Updated weights for policy 1, policy_version 323620 (0.0008) -[2023-11-28 08:41:57,291][87426] Updated weights for policy 1, policy_version 323630 (0.0007) -[2023-11-28 08:41:57,669][87426] Updated weights for policy 1, policy_version 323640 (0.0007) -[2023-11-28 08:41:58,425][87424] Updated weights for policy 0, policy_version 323969 (0.0007) -[2023-11-28 08:41:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 165789696. Throughput: 0: 2741.8, 1: 2689.6. Samples: 165802672. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:41:58,445][86177] Avg episode reward: [(0, '-519.330'), (1, '-528.360')] -[2023-11-28 08:41:58,799][87424] Updated weights for policy 0, policy_version 323979 (0.0008) -[2023-11-28 08:41:59,178][87424] Updated weights for policy 0, policy_version 323989 (0.0008) -[2023-11-28 08:41:59,564][87424] Updated weights for policy 0, policy_version 323999 (0.0008) -[2023-11-28 08:41:59,884][87426] Updated weights for policy 1, policy_version 323650 (0.0009) -[2023-11-28 08:42:00,262][87426] Updated weights for policy 1, policy_version 323660 (0.0012) -[2023-11-28 08:42:00,641][87426] Updated weights for policy 1, policy_version 323670 (0.0009) -[2023-11-28 08:42:01,019][87426] Updated weights for policy 1, policy_version 323680 (0.0008) -[2023-11-28 08:42:02,119][87424] Updated weights for policy 0, policy_version 324009 (0.0010) -[2023-11-28 08:42:02,502][87424] Updated weights for policy 0, policy_version 324019 (0.0011) -[2023-11-28 08:42:02,824][87426] Updated weights for policy 1, policy_version 323690 (0.0011) -[2023-11-28 08:42:02,878][87424] Updated weights for policy 0, policy_version 324029 (0.0011) -[2023-11-28 08:42:03,202][87426] Updated weights for policy 1, policy_version 323700 (0.0011) -[2023-11-28 08:42:03,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165814272. Throughput: 0: 2731.9, 1: 2693.2. Samples: 165826924. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:42:03,445][86177] Avg episode reward: [(0, '-518.210'), (1, '-552.940')] -[2023-11-28 08:42:03,579][87426] Updated weights for policy 1, policy_version 323710 (0.0012) -[2023-11-28 08:42:05,029][87424] Updated weights for policy 0, policy_version 324039 (0.0011) -[2023-11-28 08:42:05,403][87424] Updated weights for policy 0, policy_version 324049 (0.0012) -[2023-11-28 08:42:05,790][87424] Updated weights for policy 0, policy_version 324059 (0.0011) -[2023-11-28 08:42:05,907][87426] Updated weights for policy 1, policy_version 323720 (0.0011) -[2023-11-28 08:42:06,293][87426] Updated weights for policy 1, policy_version 323730 (0.0012) -[2023-11-28 08:42:06,666][87426] Updated weights for policy 1, policy_version 323740 (0.0012) -[2023-11-28 08:42:07,675][87424] Updated weights for policy 0, policy_version 324069 (0.0009) -[2023-11-28 08:42:08,063][87424] Updated weights for policy 0, policy_version 324079 (0.0008) -[2023-11-28 08:42:08,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165838848. Throughput: 0: 2742.6, 1: 2702.3. Samples: 165860124. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:42:08,446][86177] Avg episode reward: [(0, '-519.710'), (1, '-566.700')] -[2023-11-28 08:42:08,446][87424] Updated weights for policy 0, policy_version 324089 (0.0007) -[2023-11-28 08:42:09,119][87426] Updated weights for policy 1, policy_version 323750 (0.0012) -[2023-11-28 08:42:09,491][87426] Updated weights for policy 1, policy_version 323760 (0.0012) -[2023-11-28 08:42:09,863][87426] Updated weights for policy 1, policy_version 323770 (0.0011) -[2023-11-28 08:42:10,628][87424] Updated weights for policy 0, policy_version 324099 (0.0008) -[2023-11-28 08:42:11,011][87424] Updated weights for policy 0, policy_version 324109 (0.0011) -[2023-11-28 08:42:11,395][87424] Updated weights for policy 0, policy_version 324119 (0.0012) -[2023-11-28 08:42:11,867][87426] Updated weights for policy 1, policy_version 323780 (0.0011) -[2023-11-28 08:42:12,245][87426] Updated weights for policy 1, policy_version 323790 (0.0011) -[2023-11-28 08:42:12,624][87426] Updated weights for policy 1, policy_version 323800 (0.0010) -[2023-11-28 08:42:13,431][87424] Updated weights for policy 0, policy_version 324129 (0.0012) -[2023-11-28 08:42:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 165871616. Throughput: 0: 2724.0, 1: 2712.3. Samples: 165884256. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:42:13,445][86177] Avg episode reward: [(0, '-516.060'), (1, '-596.470')] -[2023-11-28 08:42:13,812][87424] Updated weights for policy 0, policy_version 324139 (0.0012) -[2023-11-28 08:42:14,192][87424] Updated weights for policy 0, policy_version 324149 (0.0012) -[2023-11-28 08:42:14,572][87424] Updated weights for policy 0, policy_version 324159 (0.0010) -[2023-11-28 08:42:15,201][87426] Updated weights for policy 1, policy_version 323810 (0.0010) -[2023-11-28 08:42:15,585][87426] Updated weights for policy 1, policy_version 323820 (0.0010) -[2023-11-28 08:42:15,968][87426] Updated weights for policy 1, policy_version 323830 (0.0012) -[2023-11-28 08:42:16,344][87426] Updated weights for policy 1, policy_version 323840 (0.0012) -[2023-11-28 08:42:17,047][87424] Updated weights for policy 0, policy_version 324169 (0.0007) -[2023-11-28 08:42:17,423][87424] Updated weights for policy 0, policy_version 324179 (0.0008) -[2023-11-28 08:42:17,818][87424] Updated weights for policy 0, policy_version 324189 (0.0008) -[2023-11-28 08:42:18,064][87426] Updated weights for policy 1, policy_version 323850 (0.0012) -[2023-11-28 08:42:18,434][87426] Updated weights for policy 1, policy_version 323860 (0.0012) -[2023-11-28 08:42:18,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 165896192. Throughput: 0: 2718.2, 1: 2734.3. Samples: 165908424. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:42:18,445][86177] Avg episode reward: [(0, '-517.900'), (1, '-572.020')] -[2023-11-28 08:42:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000324192_82993152.pth... -[2023-11-28 08:42:18,500][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000321664_82345984.pth -[2023-11-28 08:42:18,818][87426] Updated weights for policy 1, policy_version 323870 (0.0012) -[2023-11-28 08:42:18,890][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000323872_82911232.pth... -[2023-11-28 08:42:18,922][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000321344_82264064.pth -[2023-11-28 08:42:20,046][87424] Updated weights for policy 0, policy_version 324199 (0.0011) -[2023-11-28 08:42:20,428][87424] Updated weights for policy 0, policy_version 324209 (0.0010) -[2023-11-28 08:42:20,811][87424] Updated weights for policy 0, policy_version 324219 (0.0011) -[2023-11-28 08:42:21,272][87426] Updated weights for policy 1, policy_version 323880 (0.0009) -[2023-11-28 08:42:21,656][87426] Updated weights for policy 1, policy_version 323890 (0.0010) -[2023-11-28 08:42:22,030][87426] Updated weights for policy 1, policy_version 323900 (0.0011) -[2023-11-28 08:42:23,151][87424] Updated weights for policy 0, policy_version 324229 (0.0012) -[2023-11-28 08:42:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165920768. Throughput: 0: 2669.2, 1: 2748.5. Samples: 165939596. Policy #0 lag: (min: 31.0, avg: 54.9, max: 95.0) -[2023-11-28 08:42:23,446][86177] Avg episode reward: [(0, '-526.090'), (1, '-553.210')] -[2023-11-28 08:42:23,532][87424] Updated weights for policy 0, policy_version 324239 (0.0011) -[2023-11-28 08:42:23,918][87424] Updated weights for policy 0, policy_version 324249 (0.0012) -[2023-11-28 08:42:24,380][87426] Updated weights for policy 1, policy_version 323910 (0.0011) -[2023-11-28 08:42:24,752][87426] Updated weights for policy 1, policy_version 323920 (0.0011) -[2023-11-28 08:42:25,138][87426] Updated weights for policy 1, policy_version 323930 (0.0012) -[2023-11-28 08:42:25,939][87424] Updated weights for policy 0, policy_version 324259 (0.0011) -[2023-11-28 08:42:26,318][87424] Updated weights for policy 0, policy_version 324269 (0.0012) -[2023-11-28 08:42:26,713][87424] Updated weights for policy 0, policy_version 324279 (0.0011) -[2023-11-28 08:42:26,875][87426] Updated weights for policy 1, policy_version 323940 (0.0011) -[2023-11-28 08:42:27,245][87426] Updated weights for policy 1, policy_version 323950 (0.0007) -[2023-11-28 08:42:27,636][87426] Updated weights for policy 1, policy_version 323960 (0.0007) -[2023-11-28 08:42:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 165953536. Throughput: 0: 2674.8, 1: 2781.6. Samples: 165965668. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:42:28,445][86177] Avg episode reward: [(0, '-523.730'), (1, '-563.360')] -[2023-11-28 08:42:29,099][87424] Updated weights for policy 0, policy_version 324289 (0.0008) -[2023-11-28 08:42:29,485][87424] Updated weights for policy 0, policy_version 324299 (0.0012) -[2023-11-28 08:42:29,740][87426] Updated weights for policy 1, policy_version 323970 (0.0011) -[2023-11-28 08:42:29,863][87424] Updated weights for policy 0, policy_version 324309 (0.0011) -[2023-11-28 08:42:30,119][87426] Updated weights for policy 1, policy_version 323980 (0.0011) -[2023-11-28 08:42:30,246][87424] Updated weights for policy 0, policy_version 324319 (0.0011) -[2023-11-28 08:42:30,511][87426] Updated weights for policy 1, policy_version 323990 (0.0011) -[2023-11-28 08:42:30,890][87426] Updated weights for policy 1, policy_version 324000 (0.0007) -[2023-11-28 08:42:32,222][87424] Updated weights for policy 0, policy_version 324329 (0.0010) -[2023-11-28 08:42:32,597][87424] Updated weights for policy 0, policy_version 324339 (0.0008) -[2023-11-28 08:42:32,976][87424] Updated weights for policy 0, policy_version 324349 (0.0009) -[2023-11-28 08:42:33,408][87426] Updated weights for policy 1, policy_version 324010 (0.0008) -[2023-11-28 08:42:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 165978112. Throughput: 0: 2668.8, 1: 2757.8. Samples: 165990000. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:42:33,445][86177] Avg episode reward: [(0, '-522.920'), (1, '-532.290')] -[2023-11-28 08:42:33,790][87426] Updated weights for policy 1, policy_version 324020 (0.0007) -[2023-11-28 08:42:34,176][87426] Updated weights for policy 1, policy_version 324030 (0.0011) -[2023-11-28 08:42:35,344][87424] Updated weights for policy 0, policy_version 324359 (0.0010) -[2023-11-28 08:42:35,728][87424] Updated weights for policy 0, policy_version 324369 (0.0008) -[2023-11-28 08:42:36,103][87424] Updated weights for policy 0, policy_version 324379 (0.0010) -[2023-11-28 08:42:36,263][87426] Updated weights for policy 1, policy_version 324040 (0.0008) -[2023-11-28 08:42:36,635][87426] Updated weights for policy 1, policy_version 324050 (0.0008) -[2023-11-28 08:42:37,013][87426] Updated weights for policy 1, policy_version 324060 (0.0011) -[2023-11-28 08:42:38,349][87424] Updated weights for policy 0, policy_version 324389 (0.0012) -[2023-11-28 08:42:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 166002688. Throughput: 0: 2664.2, 1: 2736.0. Samples: 166021988. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:42:38,445][86177] Avg episode reward: [(0, '-515.670'), (1, '-553.000')] -[2023-11-28 08:42:38,744][87424] Updated weights for policy 0, policy_version 324399 (0.0012) -[2023-11-28 08:42:39,120][87424] Updated weights for policy 0, policy_version 324409 (0.0012) -[2023-11-28 08:42:39,424][87426] Updated weights for policy 1, policy_version 324070 (0.0011) -[2023-11-28 08:42:39,811][87426] Updated weights for policy 1, policy_version 324080 (0.0012) -[2023-11-28 08:42:40,185][87426] Updated weights for policy 1, policy_version 324090 (0.0010) -[2023-11-28 08:42:41,217][87424] Updated weights for policy 0, policy_version 324419 (0.0010) -[2023-11-28 08:42:41,606][87424] Updated weights for policy 0, policy_version 324429 (0.0008) -[2023-11-28 08:42:41,997][87424] Updated weights for policy 0, policy_version 324439 (0.0011) -[2023-11-28 08:42:42,462][87426] Updated weights for policy 1, policy_version 324100 (0.0011) -[2023-11-28 08:42:42,843][87426] Updated weights for policy 1, policy_version 324110 (0.0011) -[2023-11-28 08:42:43,220][87426] Updated weights for policy 1, policy_version 324120 (0.0008) -[2023-11-28 08:42:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 166027264. Throughput: 0: 2680.0, 1: 2728.4. Samples: 166046048. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:42:43,445][86177] Avg episode reward: [(0, '-514.580'), (1, '-546.800')] -[2023-11-28 08:42:44,332][87424] Updated weights for policy 0, policy_version 324449 (0.0012) -[2023-11-28 08:42:44,709][87424] Updated weights for policy 0, policy_version 324459 (0.0011) -[2023-11-28 08:42:45,095][87424] Updated weights for policy 0, policy_version 324469 (0.0011) -[2023-11-28 08:42:45,474][87424] Updated weights for policy 0, policy_version 324479 (0.0012) -[2023-11-28 08:42:45,788][87426] Updated weights for policy 1, policy_version 324130 (0.0009) -[2023-11-28 08:42:46,165][87426] Updated weights for policy 1, policy_version 324140 (0.0008) -[2023-11-28 08:42:46,553][87426] Updated weights for policy 1, policy_version 324150 (0.0008) -[2023-11-28 08:42:46,943][87426] Updated weights for policy 1, policy_version 324160 (0.0007) -[2023-11-28 08:42:47,379][87424] Updated weights for policy 0, policy_version 324489 (0.0012) -[2023-11-28 08:42:47,759][87424] Updated weights for policy 0, policy_version 324499 (0.0012) -[2023-11-28 08:42:48,141][87424] Updated weights for policy 0, policy_version 324509 (0.0011) -[2023-11-28 08:42:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 166060032. Throughput: 0: 2694.7, 1: 2722.1. Samples: 166070680. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:42:48,446][86177] Avg episode reward: [(0, '-529.860'), (1, '-537.180')] -[2023-11-28 08:42:48,580][87426] Updated weights for policy 1, policy_version 324170 (0.0007) -[2023-11-28 08:42:48,963][87426] Updated weights for policy 1, policy_version 324180 (0.0009) -[2023-11-28 08:42:49,341][87426] Updated weights for policy 1, policy_version 324190 (0.0011) -[2023-11-28 08:42:50,328][87424] Updated weights for policy 0, policy_version 324519 (0.0011) -[2023-11-28 08:42:50,704][87424] Updated weights for policy 0, policy_version 324529 (0.0010) -[2023-11-28 08:42:51,095][87424] Updated weights for policy 0, policy_version 324539 (0.0011) -[2023-11-28 08:42:51,601][87426] Updated weights for policy 1, policy_version 324200 (0.0011) -[2023-11-28 08:42:51,975][87426] Updated weights for policy 1, policy_version 324210 (0.0012) -[2023-11-28 08:42:52,362][87426] Updated weights for policy 1, policy_version 324220 (0.0011) -[2023-11-28 08:42:53,338][87424] Updated weights for policy 0, policy_version 324549 (0.0012) -[2023-11-28 08:42:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 166084608. Throughput: 0: 2685.7, 1: 2706.0. Samples: 166102752. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:42:53,445][86177] Avg episode reward: [(0, '-534.100'), (1, '-534.620')] -[2023-11-28 08:42:53,718][87424] Updated weights for policy 0, policy_version 324559 (0.0012) -[2023-11-28 08:42:54,093][87424] Updated weights for policy 0, policy_version 324569 (0.0011) -[2023-11-28 08:42:54,470][87426] Updated weights for policy 1, policy_version 324230 (0.0011) -[2023-11-28 08:42:54,845][87426] Updated weights for policy 1, policy_version 324240 (0.0012) -[2023-11-28 08:42:55,221][87426] Updated weights for policy 1, policy_version 324250 (0.0012) -[2023-11-28 08:42:56,044][87424] Updated weights for policy 0, policy_version 324579 (0.0008) -[2023-11-28 08:42:56,421][87424] Updated weights for policy 0, policy_version 324589 (0.0009) -[2023-11-28 08:42:56,812][87424] Updated weights for policy 0, policy_version 324599 (0.0009) -[2023-11-28 08:42:56,915][87426] Updated weights for policy 1, policy_version 324260 (0.0011) -[2023-11-28 08:42:57,292][87426] Updated weights for policy 1, policy_version 324270 (0.0007) -[2023-11-28 08:42:57,677][87426] Updated weights for policy 1, policy_version 324280 (0.0010) -[2023-11-28 08:42:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 166117376. Throughput: 0: 2700.4, 1: 2721.3. Samples: 166128236. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:42:58,445][86177] Avg episode reward: [(0, '-534.450'), (1, '-509.060')] -[2023-11-28 08:42:59,179][87424] Updated weights for policy 0, policy_version 324609 (0.0010) -[2023-11-28 08:42:59,567][87424] Updated weights for policy 0, policy_version 324619 (0.0010) -[2023-11-28 08:42:59,955][87424] Updated weights for policy 0, policy_version 324629 (0.0011) -[2023-11-28 08:43:00,070][87426] Updated weights for policy 1, policy_version 324290 (0.0012) -[2023-11-28 08:43:00,339][87424] Updated weights for policy 0, policy_version 324639 (0.0007) -[2023-11-28 08:43:00,449][87426] Updated weights for policy 1, policy_version 324300 (0.0011) -[2023-11-28 08:43:00,836][87426] Updated weights for policy 1, policy_version 324310 (0.0012) -[2023-11-28 08:43:01,221][87426] Updated weights for policy 1, policy_version 324320 (0.0012) -[2023-11-28 08:43:02,224][87424] Updated weights for policy 0, policy_version 324649 (0.0012) -[2023-11-28 08:43:02,601][87424] Updated weights for policy 0, policy_version 324659 (0.0012) -[2023-11-28 08:43:02,978][87424] Updated weights for policy 0, policy_version 324669 (0.0012) -[2023-11-28 08:43:03,259][87426] Updated weights for policy 1, policy_version 324330 (0.0011) -[2023-11-28 08:43:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 166141952. Throughput: 0: 2728.2, 1: 2719.3. Samples: 166153560. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:43:03,445][86177] Avg episode reward: [(0, '-539.770'), (1, '-521.700')] -[2023-11-28 08:43:03,635][87426] Updated weights for policy 1, policy_version 324340 (0.0012) -[2023-11-28 08:43:04,012][87426] Updated weights for policy 1, policy_version 324350 (0.0012) -[2023-11-28 08:43:04,841][87424] Updated weights for policy 0, policy_version 324679 (0.0012) -[2023-11-28 08:43:05,224][87424] Updated weights for policy 0, policy_version 324689 (0.0012) -[2023-11-28 08:43:05,606][87424] Updated weights for policy 0, policy_version 324699 (0.0012) -[2023-11-28 08:43:05,969][87426] Updated weights for policy 1, policy_version 324360 (0.0012) -[2023-11-28 08:43:06,353][87426] Updated weights for policy 1, policy_version 324370 (0.0012) -[2023-11-28 08:43:06,726][87426] Updated weights for policy 1, policy_version 324380 (0.0011) -[2023-11-28 08:43:07,415][87424] Updated weights for policy 0, policy_version 324709 (0.0012) -[2023-11-28 08:43:07,790][87424] Updated weights for policy 0, policy_version 324719 (0.0012) -[2023-11-28 08:43:08,173][87424] Updated weights for policy 0, policy_version 324729 (0.0012) -[2023-11-28 08:43:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 166174720. Throughput: 0: 2766.0, 1: 2750.9. Samples: 166187856. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:43:08,445][86177] Avg episode reward: [(0, '-532.180'), (1, '-530.100')] -[2023-11-28 08:43:09,141][87426] Updated weights for policy 1, policy_version 324390 (0.0010) -[2023-11-28 08:43:09,518][87426] Updated weights for policy 1, policy_version 324400 (0.0011) -[2023-11-28 08:43:09,878][87424] Updated weights for policy 0, policy_version 324739 (0.0012) -[2023-11-28 08:43:09,906][87426] Updated weights for policy 1, policy_version 324410 (0.0011) -[2023-11-28 08:43:10,266][87424] Updated weights for policy 0, policy_version 324749 (0.0012) -[2023-11-28 08:43:10,638][87424] Updated weights for policy 0, policy_version 324759 (0.0012) -[2023-11-28 08:43:12,309][87426] Updated weights for policy 1, policy_version 324420 (0.0009) -[2023-11-28 08:43:12,685][87426] Updated weights for policy 1, policy_version 324430 (0.0012) -[2023-11-28 08:43:12,988][87424] Updated weights for policy 0, policy_version 324769 (0.0012) -[2023-11-28 08:43:13,064][87426] Updated weights for policy 1, policy_version 324440 (0.0011) -[2023-11-28 08:43:13,370][87424] Updated weights for policy 0, policy_version 324779 (0.0010) -[2023-11-28 08:43:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 166199296. Throughput: 0: 2754.6, 1: 2712.7. Samples: 166211696. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:43:13,445][86177] Avg episode reward: [(0, '-535.680'), (1, '-527.650')] -[2023-11-28 08:43:13,755][87424] Updated weights for policy 0, policy_version 324789 (0.0011) -[2023-11-28 08:43:14,138][87424] Updated weights for policy 0, policy_version 324799 (0.0011) -[2023-11-28 08:43:15,335][87426] Updated weights for policy 1, policy_version 324450 (0.0008) -[2023-11-28 08:43:15,724][87426] Updated weights for policy 1, policy_version 324460 (0.0007) -[2023-11-28 08:43:16,094][87426] Updated weights for policy 1, policy_version 324470 (0.0009) -[2023-11-28 08:43:16,470][87426] Updated weights for policy 1, policy_version 324480 (0.0011) -[2023-11-28 08:43:16,530][87424] Updated weights for policy 0, policy_version 324809 (0.0011) -[2023-11-28 08:43:16,914][87424] Updated weights for policy 0, policy_version 324819 (0.0012) -[2023-11-28 08:43:17,293][87424] Updated weights for policy 0, policy_version 324829 (0.0012) -[2023-11-28 08:43:18,107][87426] Updated weights for policy 1, policy_version 324490 (0.0010) -[2023-11-28 08:43:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 166223872. Throughput: 0: 2745.1, 1: 2734.0. Samples: 166236556. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:43:18,445][86177] Avg episode reward: [(0, '-539.010'), (1, '-522.590')] -[2023-11-28 08:43:18,493][87426] Updated weights for policy 1, policy_version 324500 (0.0011) -[2023-11-28 08:43:18,871][87426] Updated weights for policy 1, policy_version 324510 (0.0011) -[2023-11-28 08:43:19,566][87424] Updated weights for policy 0, policy_version 324839 (0.0011) -[2023-11-28 08:43:19,941][87424] Updated weights for policy 0, policy_version 324849 (0.0008) -[2023-11-28 08:43:20,319][87424] Updated weights for policy 0, policy_version 324859 (0.0008) -[2023-11-28 08:43:21,183][87426] Updated weights for policy 1, policy_version 324520 (0.0009) -[2023-11-28 08:43:21,564][87426] Updated weights for policy 1, policy_version 324530 (0.0011) -[2023-11-28 08:43:21,939][87426] Updated weights for policy 1, policy_version 324540 (0.0010) -[2023-11-28 08:43:22,656][87424] Updated weights for policy 0, policy_version 324869 (0.0009) -[2023-11-28 08:43:23,038][87424] Updated weights for policy 0, policy_version 324879 (0.0011) -[2023-11-28 08:43:23,424][87424] Updated weights for policy 0, policy_version 324889 (0.0012) -[2023-11-28 08:43:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 166248448. Throughput: 0: 2754.0, 1: 2746.5. Samples: 166269512. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:43:23,445][86177] Avg episode reward: [(0, '-535.920'), (1, '-527.790')] -[2023-11-28 08:43:24,307][87426] Updated weights for policy 1, policy_version 324550 (0.0010) -[2023-11-28 08:43:24,686][87426] Updated weights for policy 1, policy_version 324560 (0.0008) -[2023-11-28 08:43:25,067][87426] Updated weights for policy 1, policy_version 324570 (0.0008) -[2023-11-28 08:43:25,314][87424] Updated weights for policy 0, policy_version 324899 (0.0012) -[2023-11-28 08:43:25,700][87424] Updated weights for policy 0, policy_version 324909 (0.0011) -[2023-11-28 08:43:26,070][87424] Updated weights for policy 0, policy_version 324919 (0.0011) -[2023-11-28 08:43:27,093][87426] Updated weights for policy 1, policy_version 324580 (0.0007) -[2023-11-28 08:43:27,479][87426] Updated weights for policy 1, policy_version 324590 (0.0011) -[2023-11-28 08:43:27,856][87426] Updated weights for policy 1, policy_version 324600 (0.0012) -[2023-11-28 08:43:28,325][87424] Updated weights for policy 0, policy_version 324929 (0.0012) -[2023-11-28 08:43:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 166281216. Throughput: 0: 2753.1, 1: 2751.3. Samples: 166293748. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:43:28,445][86177] Avg episode reward: [(0, '-536.130'), (1, '-528.460')] -[2023-11-28 08:43:28,711][87424] Updated weights for policy 0, policy_version 324939 (0.0012) -[2023-11-28 08:43:29,084][87424] Updated weights for policy 0, policy_version 324949 (0.0012) -[2023-11-28 08:43:29,464][87424] Updated weights for policy 0, policy_version 324959 (0.0010) -[2023-11-28 08:43:30,388][87426] Updated weights for policy 1, policy_version 324610 (0.0012) -[2023-11-28 08:43:30,761][87426] Updated weights for policy 1, policy_version 324620 (0.0008) -[2023-11-28 08:43:31,142][87426] Updated weights for policy 1, policy_version 324630 (0.0007) -[2023-11-28 08:43:31,522][87426] Updated weights for policy 1, policy_version 324640 (0.0007) -[2023-11-28 08:43:31,751][87424] Updated weights for policy 0, policy_version 324969 (0.0009) -[2023-11-28 08:43:32,132][87424] Updated weights for policy 0, policy_version 324979 (0.0009) -[2023-11-28 08:43:32,515][87424] Updated weights for policy 0, policy_version 324989 (0.0009) -[2023-11-28 08:43:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 166305792. Throughput: 0: 2781.9, 1: 2738.4. Samples: 166319092. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:43:33,445][86177] Avg episode reward: [(0, '-529.890'), (1, '-514.110')] -[2023-11-28 08:43:33,671][87426] Updated weights for policy 1, policy_version 324650 (0.0010) -[2023-11-28 08:43:34,059][87426] Updated weights for policy 1, policy_version 324660 (0.0011) -[2023-11-28 08:43:34,446][87426] Updated weights for policy 1, policy_version 324670 (0.0007) -[2023-11-28 08:43:34,710][87424] Updated weights for policy 0, policy_version 324999 (0.0008) -[2023-11-28 08:43:35,101][87424] Updated weights for policy 0, policy_version 325009 (0.0008) -[2023-11-28 08:43:35,475][87424] Updated weights for policy 0, policy_version 325019 (0.0011) -[2023-11-28 08:43:36,509][87426] Updated weights for policy 1, policy_version 324680 (0.0008) -[2023-11-28 08:43:36,885][87426] Updated weights for policy 1, policy_version 324690 (0.0011) -[2023-11-28 08:43:37,265][87426] Updated weights for policy 1, policy_version 324700 (0.0012) -[2023-11-28 08:43:37,397][87424] Updated weights for policy 0, policy_version 325029 (0.0012) -[2023-11-28 08:43:37,784][87424] Updated weights for policy 0, policy_version 325039 (0.0012) -[2023-11-28 08:43:38,158][87424] Updated weights for policy 0, policy_version 325049 (0.0012) -[2023-11-28 08:43:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 166338560. Throughput: 0: 2781.6, 1: 2747.8. Samples: 166351576. Policy #0 lag: (min: 31.0, avg: 48.8, max: 82.0) -[2023-11-28 08:43:38,445][86177] Avg episode reward: [(0, '-531.420'), (1, '-509.840')] -[2023-11-28 08:43:39,323][87426] Updated weights for policy 1, policy_version 324710 (0.0008) -[2023-11-28 08:43:39,703][87426] Updated weights for policy 1, policy_version 324720 (0.0007) -[2023-11-28 08:43:40,078][87426] Updated weights for policy 1, policy_version 324730 (0.0012) -[2023-11-28 08:43:40,086][87424] Updated weights for policy 0, policy_version 325059 (0.0011) -[2023-11-28 08:43:40,479][87424] Updated weights for policy 0, policy_version 325069 (0.0012) -[2023-11-28 08:43:40,859][87424] Updated weights for policy 0, policy_version 325079 (0.0009) -[2023-11-28 08:43:41,923][87426] Updated weights for policy 1, policy_version 324740 (0.0012) -[2023-11-28 08:43:42,305][87426] Updated weights for policy 1, policy_version 324750 (0.0009) -[2023-11-28 08:43:42,683][87426] Updated weights for policy 1, policy_version 324760 (0.0012) -[2023-11-28 08:43:43,420][87424] Updated weights for policy 0, policy_version 325089 (0.0008) -[2023-11-28 08:43:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 166363136. Throughput: 0: 2768.2, 1: 2737.4. Samples: 166375988. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:43:43,445][86177] Avg episode reward: [(0, '-529.340'), (1, '-493.150')] -[2023-11-28 08:43:43,803][87424] Updated weights for policy 0, policy_version 325099 (0.0012) -[2023-11-28 08:43:44,185][87424] Updated weights for policy 0, policy_version 325109 (0.0012) -[2023-11-28 08:43:44,559][87424] Updated weights for policy 0, policy_version 325119 (0.0012) -[2023-11-28 08:43:45,166][87426] Updated weights for policy 1, policy_version 324770 (0.0012) -[2023-11-28 08:43:45,545][87426] Updated weights for policy 1, policy_version 324780 (0.0011) -[2023-11-28 08:43:45,927][87426] Updated weights for policy 1, policy_version 324790 (0.0012) -[2023-11-28 08:43:46,308][87426] Updated weights for policy 1, policy_version 324800 (0.0011) -[2023-11-28 08:43:46,524][87424] Updated weights for policy 0, policy_version 325129 (0.0008) -[2023-11-28 08:43:46,908][87424] Updated weights for policy 0, policy_version 325139 (0.0008) -[2023-11-28 08:43:47,295][87424] Updated weights for policy 0, policy_version 325149 (0.0007) -[2023-11-28 08:43:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 166387712. Throughput: 0: 2747.2, 1: 2737.3. Samples: 166400364. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:43:48,445][86177] Avg episode reward: [(0, '-523.300'), (1, '-493.950')] -[2023-11-28 08:43:48,707][87426] Updated weights for policy 1, policy_version 324810 (0.0011) -[2023-11-28 08:43:49,089][87426] Updated weights for policy 1, policy_version 324820 (0.0011) -[2023-11-28 08:43:49,156][87424] Updated weights for policy 0, policy_version 325159 (0.0010) -[2023-11-28 08:43:49,457][87426] Updated weights for policy 1, policy_version 324830 (0.0012) -[2023-11-28 08:43:49,535][87424] Updated weights for policy 0, policy_version 325169 (0.0011) -[2023-11-28 08:43:49,918][87424] Updated weights for policy 0, policy_version 325179 (0.0012) -[2023-11-28 08:43:51,544][87426] Updated weights for policy 1, policy_version 324840 (0.0009) -[2023-11-28 08:43:51,846][87424] Updated weights for policy 0, policy_version 325189 (0.0012) -[2023-11-28 08:43:51,913][87426] Updated weights for policy 1, policy_version 324850 (0.0011) -[2023-11-28 08:43:52,234][87424] Updated weights for policy 0, policy_version 325199 (0.0011) -[2023-11-28 08:43:52,294][87426] Updated weights for policy 1, policy_version 324860 (0.0009) -[2023-11-28 08:43:52,616][87424] Updated weights for policy 0, policy_version 325209 (0.0011) -[2023-11-28 08:43:53,445][86177] Fps is (10 sec: 5733.9, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 166420480. Throughput: 0: 2733.3, 1: 2705.6. Samples: 166432612. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:43:53,446][86177] Avg episode reward: [(0, '-523.270'), (1, '-497.480')] -[2023-11-28 08:43:54,831][87426] Updated weights for policy 1, policy_version 324870 (0.0010) -[2023-11-28 08:43:55,095][87424] Updated weights for policy 0, policy_version 325219 (0.0012) -[2023-11-28 08:43:55,212][87426] Updated weights for policy 1, policy_version 324880 (0.0011) -[2023-11-28 08:43:55,472][87424] Updated weights for policy 0, policy_version 325229 (0.0011) -[2023-11-28 08:43:55,605][87426] Updated weights for policy 1, policy_version 324890 (0.0010) -[2023-11-28 08:43:55,847][87424] Updated weights for policy 0, policy_version 325239 (0.0012) -[2023-11-28 08:43:57,541][87426] Updated weights for policy 1, policy_version 324900 (0.0009) -[2023-11-28 08:43:57,762][87424] Updated weights for policy 0, policy_version 325249 (0.0011) -[2023-11-28 08:43:57,921][87426] Updated weights for policy 1, policy_version 324910 (0.0010) -[2023-11-28 08:43:58,147][87424] Updated weights for policy 0, policy_version 325259 (0.0007) -[2023-11-28 08:43:58,302][87426] Updated weights for policy 1, policy_version 324920 (0.0009) -[2023-11-28 08:43:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 166436864. Throughput: 0: 2726.2, 1: 2711.5. Samples: 166456392. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:43:58,445][86177] Avg episode reward: [(0, '-517.030'), (1, '-498.250')] -[2023-11-28 08:43:58,536][87424] Updated weights for policy 0, policy_version 325269 (0.0010) -[2023-11-28 08:43:58,924][87424] Updated weights for policy 0, policy_version 325279 (0.0012) -[2023-11-28 08:44:00,436][87426] Updated weights for policy 1, policy_version 324930 (0.0011) -[2023-11-28 08:44:00,624][87424] Updated weights for policy 0, policy_version 325289 (0.0012) -[2023-11-28 08:44:00,816][87426] Updated weights for policy 1, policy_version 324940 (0.0011) -[2023-11-28 08:44:01,009][87424] Updated weights for policy 0, policy_version 325299 (0.0007) -[2023-11-28 08:44:01,200][87426] Updated weights for policy 1, policy_version 324950 (0.0007) -[2023-11-28 08:44:01,386][87424] Updated weights for policy 0, policy_version 325309 (0.0007) -[2023-11-28 08:44:01,584][87426] Updated weights for policy 1, policy_version 324960 (0.0008) -[2023-11-28 08:44:03,444][86177] Fps is (10 sec: 4915.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 166469632. Throughput: 0: 2764.1, 1: 2689.2. Samples: 166481956. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:03,446][86177] Avg episode reward: [(0, '-518.150'), (1, '-515.210')] -[2023-11-28 08:44:03,904][87424] Updated weights for policy 0, policy_version 325319 (0.0010) -[2023-11-28 08:44:03,971][87426] Updated weights for policy 1, policy_version 324970 (0.0012) -[2023-11-28 08:44:04,283][87424] Updated weights for policy 0, policy_version 325329 (0.0012) -[2023-11-28 08:44:04,351][87426] Updated weights for policy 1, policy_version 324980 (0.0012) -[2023-11-28 08:44:04,671][87424] Updated weights for policy 0, policy_version 325339 (0.0012) -[2023-11-28 08:44:04,727][87426] Updated weights for policy 1, policy_version 324990 (0.0008) -[2023-11-28 08:44:06,998][87424] Updated weights for policy 0, policy_version 325349 (0.0011) -[2023-11-28 08:44:07,296][87426] Updated weights for policy 1, policy_version 325000 (0.0011) -[2023-11-28 08:44:07,388][87424] Updated weights for policy 0, policy_version 325359 (0.0012) -[2023-11-28 08:44:07,666][87426] Updated weights for policy 1, policy_version 325010 (0.0012) -[2023-11-28 08:44:07,773][87424] Updated weights for policy 0, policy_version 325369 (0.0012) -[2023-11-28 08:44:08,048][87426] Updated weights for policy 1, policy_version 325020 (0.0012) -[2023-11-28 08:44:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 166502400. Throughput: 0: 2744.3, 1: 2688.9. Samples: 166514004. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:08,445][86177] Avg episode reward: [(0, '-522.050'), (1, '-516.960')] -[2023-11-28 08:44:09,774][87426] Updated weights for policy 1, policy_version 325030 (0.0012) -[2023-11-28 08:44:09,798][87424] Updated weights for policy 0, policy_version 325379 (0.0012) -[2023-11-28 08:44:10,153][87426] Updated weights for policy 1, policy_version 325040 (0.0012) -[2023-11-28 08:44:10,194][87424] Updated weights for policy 0, policy_version 325389 (0.0009) -[2023-11-28 08:44:10,531][87426] Updated weights for policy 1, policy_version 325050 (0.0012) -[2023-11-28 08:44:10,574][87424] Updated weights for policy 0, policy_version 325399 (0.0009) -[2023-11-28 08:44:12,765][87424] Updated weights for policy 0, policy_version 325409 (0.0008) -[2023-11-28 08:44:13,062][87426] Updated weights for policy 1, policy_version 325060 (0.0011) -[2023-11-28 08:44:13,143][87424] Updated weights for policy 0, policy_version 325419 (0.0009) -[2023-11-28 08:44:13,442][87426] Updated weights for policy 1, policy_version 325070 (0.0011) -[2023-11-28 08:44:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 166518784. Throughput: 0: 2757.6, 1: 2680.1. Samples: 166538444. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:13,445][86177] Avg episode reward: [(0, '-523.070'), (1, '-516.090')] -[2023-11-28 08:44:13,532][87424] Updated weights for policy 0, policy_version 325429 (0.0008) -[2023-11-28 08:44:13,825][87426] Updated weights for policy 1, policy_version 325080 (0.0010) -[2023-11-28 08:44:13,908][87424] Updated weights for policy 0, policy_version 325439 (0.0008) -[2023-11-28 08:44:15,685][87426] Updated weights for policy 1, policy_version 325090 (0.0012) -[2023-11-28 08:44:16,064][87426] Updated weights for policy 1, policy_version 325100 (0.0011) -[2023-11-28 08:44:16,286][87424] Updated weights for policy 0, policy_version 325449 (0.0008) -[2023-11-28 08:44:16,441][87426] Updated weights for policy 1, policy_version 325110 (0.0011) -[2023-11-28 08:44:16,667][87424] Updated weights for policy 0, policy_version 325459 (0.0007) -[2023-11-28 08:44:16,828][87426] Updated weights for policy 1, policy_version 325120 (0.0011) -[2023-11-28 08:44:17,047][87424] Updated weights for policy 0, policy_version 325469 (0.0012) -[2023-11-28 08:44:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 166551552. Throughput: 0: 2734.2, 1: 2688.1. Samples: 166563096. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:18,446][86177] Avg episode reward: [(0, '-523.140'), (1, '-516.830')] -[2023-11-28 08:44:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000325472_83320832.pth... -[2023-11-28 08:44:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000325120_83230720.pth... -[2023-11-28 08:44:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000322912_82665472.pth -[2023-11-28 08:44:18,504][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000322592_82583552.pth -[2023-11-28 08:44:19,036][87426] Updated weights for policy 1, policy_version 325130 (0.0012) -[2023-11-28 08:44:19,420][87426] Updated weights for policy 1, policy_version 325140 (0.0012) -[2023-11-28 08:44:19,539][87424] Updated weights for policy 0, policy_version 325479 (0.0011) -[2023-11-28 08:44:19,799][87426] Updated weights for policy 1, policy_version 325150 (0.0011) -[2023-11-28 08:44:19,928][87424] Updated weights for policy 0, policy_version 325489 (0.0012) -[2023-11-28 08:44:20,300][87424] Updated weights for policy 0, policy_version 325499 (0.0011) -[2023-11-28 08:44:22,110][87426] Updated weights for policy 1, policy_version 325160 (0.0012) -[2023-11-28 08:44:22,370][87424] Updated weights for policy 0, policy_version 325509 (0.0010) -[2023-11-28 08:44:22,485][87426] Updated weights for policy 1, policy_version 325170 (0.0011) -[2023-11-28 08:44:22,744][87424] Updated weights for policy 0, policy_version 325519 (0.0011) -[2023-11-28 08:44:22,863][87426] Updated weights for policy 1, policy_version 325180 (0.0010) -[2023-11-28 08:44:23,132][87424] Updated weights for policy 0, policy_version 325529 (0.0012) -[2023-11-28 08:44:23,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 166584320. Throughput: 0: 2714.0, 1: 2689.3. Samples: 166594724. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:23,445][86177] Avg episode reward: [(0, '-535.550'), (1, '-501.580')] -[2023-11-28 08:44:24,962][87426] Updated weights for policy 1, policy_version 325190 (0.0011) -[2023-11-28 08:44:25,079][87424] Updated weights for policy 0, policy_version 325539 (0.0012) -[2023-11-28 08:44:25,344][87426] Updated weights for policy 1, policy_version 325200 (0.0009) -[2023-11-28 08:44:25,457][87424] Updated weights for policy 0, policy_version 325549 (0.0011) -[2023-11-28 08:44:25,722][87426] Updated weights for policy 1, policy_version 325210 (0.0011) -[2023-11-28 08:44:25,837][87424] Updated weights for policy 0, policy_version 325559 (0.0010) -[2023-11-28 08:44:27,906][87426] Updated weights for policy 1, policy_version 325220 (0.0010) -[2023-11-28 08:44:27,935][87424] Updated weights for policy 0, policy_version 325569 (0.0012) -[2023-11-28 08:44:28,289][87426] Updated weights for policy 1, policy_version 325230 (0.0011) -[2023-11-28 08:44:28,322][87424] Updated weights for policy 0, policy_version 325579 (0.0011) -[2023-11-28 08:44:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 166600704. Throughput: 0: 2735.1, 1: 2698.5. Samples: 166620500. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:28,445][86177] Avg episode reward: [(0, '-599.720'), (1, '-514.920')] -[2023-11-28 08:44:28,665][87426] Updated weights for policy 1, policy_version 325240 (0.0009) -[2023-11-28 08:44:28,700][87424] Updated weights for policy 0, policy_version 325589 (0.0011) -[2023-11-28 08:44:29,082][87424] Updated weights for policy 0, policy_version 325599 (0.0012) -[2023-11-28 08:44:30,586][87426] Updated weights for policy 1, policy_version 325250 (0.0010) -[2023-11-28 08:44:30,866][87424] Updated weights for policy 0, policy_version 325609 (0.0012) -[2023-11-28 08:44:30,967][87426] Updated weights for policy 1, policy_version 325260 (0.0011) -[2023-11-28 08:44:31,251][87424] Updated weights for policy 0, policy_version 325619 (0.0012) -[2023-11-28 08:44:31,342][87426] Updated weights for policy 1, policy_version 325270 (0.0011) -[2023-11-28 08:44:31,631][87424] Updated weights for policy 0, policy_version 325629 (0.0012) -[2023-11-28 08:44:31,716][87426] Updated weights for policy 1, policy_version 325280 (0.0010) -[2023-11-28 08:44:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 166633472. Throughput: 0: 2740.9, 1: 2683.2. Samples: 166644448. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:33,445][86177] Avg episode reward: [(0, '-599.690'), (1, '-536.850')] -[2023-11-28 08:44:33,767][87426] Updated weights for policy 1, policy_version 325290 (0.0010) -[2023-11-28 08:44:33,971][87424] Updated weights for policy 0, policy_version 325639 (0.0010) -[2023-11-28 08:44:34,154][87426] Updated weights for policy 1, policy_version 325300 (0.0010) -[2023-11-28 08:44:34,351][87424] Updated weights for policy 0, policy_version 325649 (0.0010) -[2023-11-28 08:44:34,540][87426] Updated weights for policy 1, policy_version 325310 (0.0010) -[2023-11-28 08:44:34,741][87424] Updated weights for policy 0, policy_version 325659 (0.0012) -[2023-11-28 08:44:36,467][87426] Updated weights for policy 1, policy_version 325320 (0.0008) -[2023-11-28 08:44:36,839][87426] Updated weights for policy 1, policy_version 325330 (0.0010) -[2023-11-28 08:44:37,227][87426] Updated weights for policy 1, policy_version 325340 (0.0011) -[2023-11-28 08:44:37,266][87424] Updated weights for policy 0, policy_version 325669 (0.0011) -[2023-11-28 08:44:37,649][87424] Updated weights for policy 0, policy_version 325679 (0.0009) -[2023-11-28 08:44:38,033][87424] Updated weights for policy 0, policy_version 325689 (0.0007) -[2023-11-28 08:44:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 166666240. Throughput: 0: 2751.7, 1: 2712.6. Samples: 166678500. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:38,445][86177] Avg episode reward: [(0, '-599.340'), (1, '-536.030')] -[2023-11-28 08:44:39,320][87426] Updated weights for policy 1, policy_version 325350 (0.0007) -[2023-11-28 08:44:39,701][87426] Updated weights for policy 1, policy_version 325360 (0.0007) -[2023-11-28 08:44:40,075][87426] Updated weights for policy 1, policy_version 325370 (0.0011) -[2023-11-28 08:44:40,176][87424] Updated weights for policy 0, policy_version 325699 (0.0009) -[2023-11-28 08:44:40,553][87424] Updated weights for policy 0, policy_version 325709 (0.0011) -[2023-11-28 08:44:40,934][87424] Updated weights for policy 0, policy_version 325719 (0.0008) -[2023-11-28 08:44:42,457][87426] Updated weights for policy 1, policy_version 325380 (0.0011) -[2023-11-28 08:44:42,837][87426] Updated weights for policy 1, policy_version 325390 (0.0012) -[2023-11-28 08:44:43,117][87424] Updated weights for policy 0, policy_version 325729 (0.0008) -[2023-11-28 08:44:43,213][87426] Updated weights for policy 1, policy_version 325400 (0.0009) -[2023-11-28 08:44:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 166682624. Throughput: 0: 2755.9, 1: 2718.4. Samples: 166702736. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:43,445][86177] Avg episode reward: [(0, '-586.800'), (1, '-519.570')] -[2023-11-28 08:44:43,490][87424] Updated weights for policy 0, policy_version 325739 (0.0011) -[2023-11-28 08:44:43,874][87424] Updated weights for policy 0, policy_version 325749 (0.0008) -[2023-11-28 08:44:44,250][87424] Updated weights for policy 0, policy_version 325759 (0.0009) -[2023-11-28 08:44:45,440][87426] Updated weights for policy 1, policy_version 325410 (0.0010) -[2023-11-28 08:44:45,810][87426] Updated weights for policy 1, policy_version 325420 (0.0012) -[2023-11-28 08:44:46,193][87426] Updated weights for policy 1, policy_version 325430 (0.0012) -[2023-11-28 08:44:46,568][87426] Updated weights for policy 1, policy_version 325440 (0.0010) -[2023-11-28 08:44:46,744][87424] Updated weights for policy 0, policy_version 325769 (0.0011) -[2023-11-28 08:44:47,120][87424] Updated weights for policy 0, policy_version 325779 (0.0012) -[2023-11-28 08:44:47,508][87424] Updated weights for policy 0, policy_version 325789 (0.0012) -[2023-11-28 08:44:48,386][87426] Updated weights for policy 1, policy_version 325450 (0.0008) -[2023-11-28 08:44:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 166715392. Throughput: 0: 2709.1, 1: 2736.4. Samples: 166727000. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:48,445][86177] Avg episode reward: [(0, '-515.940'), (1, '-517.250')] -[2023-11-28 08:44:48,765][87426] Updated weights for policy 1, policy_version 325460 (0.0007) -[2023-11-28 08:44:49,149][87426] Updated weights for policy 1, policy_version 325470 (0.0011) -[2023-11-28 08:44:49,623][87424] Updated weights for policy 0, policy_version 325799 (0.0011) -[2023-11-28 08:44:50,007][87424] Updated weights for policy 0, policy_version 325809 (0.0010) -[2023-11-28 08:44:50,379][87424] Updated weights for policy 0, policy_version 325819 (0.0011) -[2023-11-28 08:44:51,583][87426] Updated weights for policy 1, policy_version 325480 (0.0011) -[2023-11-28 08:44:51,962][87426] Updated weights for policy 1, policy_version 325490 (0.0009) -[2023-11-28 08:44:52,333][87424] Updated weights for policy 0, policy_version 325829 (0.0011) -[2023-11-28 08:44:52,342][87426] Updated weights for policy 1, policy_version 325500 (0.0009) -[2023-11-28 08:44:52,721][87424] Updated weights for policy 0, policy_version 325839 (0.0012) -[2023-11-28 08:44:53,096][87424] Updated weights for policy 0, policy_version 325849 (0.0012) -[2023-11-28 08:44:53,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 166748160. Throughput: 0: 2713.5, 1: 2743.2. Samples: 166759556. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:53,445][86177] Avg episode reward: [(0, '-516.630'), (1, '-501.630')] -[2023-11-28 08:44:54,598][87426] Updated weights for policy 1, policy_version 325510 (0.0011) -[2023-11-28 08:44:54,979][87426] Updated weights for policy 1, policy_version 325520 (0.0011) -[2023-11-28 08:44:55,354][87426] Updated weights for policy 1, policy_version 325530 (0.0012) -[2023-11-28 08:44:55,357][87424] Updated weights for policy 0, policy_version 325859 (0.0012) -[2023-11-28 08:44:55,743][87424] Updated weights for policy 0, policy_version 325869 (0.0011) -[2023-11-28 08:44:56,110][87424] Updated weights for policy 0, policy_version 325879 (0.0012) -[2023-11-28 08:44:57,140][87426] Updated weights for policy 1, policy_version 325540 (0.0011) -[2023-11-28 08:44:57,513][87426] Updated weights for policy 1, policy_version 325550 (0.0011) -[2023-11-28 08:44:57,886][87426] Updated weights for policy 1, policy_version 325560 (0.0011) -[2023-11-28 08:44:58,098][87424] Updated weights for policy 0, policy_version 325889 (0.0012) -[2023-11-28 08:44:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 166772736. Throughput: 0: 2698.8, 1: 2777.7. Samples: 166784884. Policy #0 lag: (min: 31.0, avg: 53.9, max: 92.0) -[2023-11-28 08:44:58,445][86177] Avg episode reward: [(0, '-515.950'), (1, '-516.700')] -[2023-11-28 08:44:58,475][87424] Updated weights for policy 0, policy_version 325899 (0.0008) -[2023-11-28 08:44:58,859][87424] Updated weights for policy 0, policy_version 325909 (0.0008) -[2023-11-28 08:44:59,231][87424] Updated weights for policy 0, policy_version 325919 (0.0008) -[2023-11-28 08:44:59,773][87426] Updated weights for policy 1, policy_version 325570 (0.0011) -[2023-11-28 08:45:00,161][87426] Updated weights for policy 1, policy_version 325580 (0.0012) -[2023-11-28 08:45:00,533][87426] Updated weights for policy 1, policy_version 325590 (0.0012) -[2023-11-28 08:45:00,914][87426] Updated weights for policy 1, policy_version 325600 (0.0009) -[2023-11-28 08:45:01,552][87424] Updated weights for policy 0, policy_version 325929 (0.0009) -[2023-11-28 08:45:01,935][87424] Updated weights for policy 0, policy_version 325939 (0.0009) -[2023-11-28 08:45:02,327][87424] Updated weights for policy 0, policy_version 325949 (0.0010) -[2023-11-28 08:45:03,230][87426] Updated weights for policy 1, policy_version 325610 (0.0011) -[2023-11-28 08:45:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 166797312. Throughput: 0: 2697.7, 1: 2779.2. Samples: 166809556. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:03,446][86177] Avg episode reward: [(0, '-516.460'), (1, '-517.260')] -[2023-11-28 08:45:03,595][87426] Updated weights for policy 1, policy_version 325620 (0.0009) -[2023-11-28 08:45:03,967][87426] Updated weights for policy 1, policy_version 325630 (0.0007) -[2023-11-28 08:45:04,482][87424] Updated weights for policy 0, policy_version 325959 (0.0010) -[2023-11-28 08:45:04,873][87424] Updated weights for policy 0, policy_version 325969 (0.0008) -[2023-11-28 08:45:05,242][87424] Updated weights for policy 0, policy_version 325979 (0.0008) -[2023-11-28 08:45:06,459][87426] Updated weights for policy 1, policy_version 325640 (0.0008) -[2023-11-28 08:45:06,842][87426] Updated weights for policy 1, policy_version 325650 (0.0008) -[2023-11-28 08:45:07,025][87424] Updated weights for policy 0, policy_version 325989 (0.0011) -[2023-11-28 08:45:07,226][87426] Updated weights for policy 1, policy_version 325660 (0.0009) -[2023-11-28 08:45:07,405][87424] Updated weights for policy 0, policy_version 325999 (0.0012) -[2023-11-28 08:45:07,785][87424] Updated weights for policy 0, policy_version 326009 (0.0012) -[2023-11-28 08:45:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 166830080. Throughput: 0: 2724.8, 1: 2766.7. Samples: 166841840. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:08,445][86177] Avg episode reward: [(0, '-518.100'), (1, '-517.990')] -[2023-11-28 08:45:09,330][87426] Updated weights for policy 1, policy_version 325670 (0.0011) -[2023-11-28 08:45:09,707][87426] Updated weights for policy 1, policy_version 325680 (0.0012) -[2023-11-28 08:45:10,089][87426] Updated weights for policy 1, policy_version 325690 (0.0010) -[2023-11-28 08:45:10,238][87424] Updated weights for policy 0, policy_version 326019 (0.0011) -[2023-11-28 08:45:10,631][87424] Updated weights for policy 0, policy_version 326029 (0.0010) -[2023-11-28 08:45:11,012][87424] Updated weights for policy 0, policy_version 326039 (0.0012) -[2023-11-28 08:45:12,229][87426] Updated weights for policy 1, policy_version 325700 (0.0012) -[2023-11-28 08:45:12,621][87426] Updated weights for policy 1, policy_version 325710 (0.0009) -[2023-11-28 08:45:12,992][87426] Updated weights for policy 1, policy_version 325720 (0.0008) -[2023-11-28 08:45:13,089][87424] Updated weights for policy 0, policy_version 326049 (0.0012) -[2023-11-28 08:45:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 166854656. Throughput: 0: 2731.2, 1: 2750.7. Samples: 166867184. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:13,445][86177] Avg episode reward: [(0, '-519.170'), (1, '-494.560')] -[2023-11-28 08:45:13,473][87424] Updated weights for policy 0, policy_version 326059 (0.0012) -[2023-11-28 08:45:13,849][87424] Updated weights for policy 0, policy_version 326069 (0.0008) -[2023-11-28 08:45:14,239][87424] Updated weights for policy 0, policy_version 326079 (0.0012) -[2023-11-28 08:45:15,376][87426] Updated weights for policy 1, policy_version 325730 (0.0007) -[2023-11-28 08:45:15,755][87426] Updated weights for policy 1, policy_version 325740 (0.0009) -[2023-11-28 08:45:16,132][87426] Updated weights for policy 1, policy_version 325750 (0.0011) -[2023-11-28 08:45:16,233][87424] Updated weights for policy 0, policy_version 326089 (0.0008) -[2023-11-28 08:45:16,506][87426] Updated weights for policy 1, policy_version 325760 (0.0012) -[2023-11-28 08:45:16,613][87424] Updated weights for policy 0, policy_version 326099 (0.0011) -[2023-11-28 08:45:17,000][87424] Updated weights for policy 0, policy_version 326109 (0.0012) -[2023-11-28 08:45:18,283][87426] Updated weights for policy 1, policy_version 325770 (0.0011) -[2023-11-28 08:45:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 166879232. Throughput: 0: 2741.1, 1: 2770.1. Samples: 166892456. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:18,445][86177] Avg episode reward: [(0, '-524.380'), (1, '-494.300')] -[2023-11-28 08:45:18,673][87426] Updated weights for policy 1, policy_version 325780 (0.0012) -[2023-11-28 08:45:19,052][87426] Updated weights for policy 1, policy_version 325790 (0.0012) -[2023-11-28 08:45:19,544][87424] Updated weights for policy 0, policy_version 326119 (0.0009) -[2023-11-28 08:45:19,939][87424] Updated weights for policy 0, policy_version 326129 (0.0009) -[2023-11-28 08:45:20,312][87424] Updated weights for policy 0, policy_version 326139 (0.0008) -[2023-11-28 08:45:21,577][87426] Updated weights for policy 1, policy_version 325800 (0.0011) -[2023-11-28 08:45:21,960][87426] Updated weights for policy 1, policy_version 325810 (0.0010) -[2023-11-28 08:45:22,339][87426] Updated weights for policy 1, policy_version 325820 (0.0010) -[2023-11-28 08:45:22,432][87424] Updated weights for policy 0, policy_version 326149 (0.0009) -[2023-11-28 08:45:22,809][87424] Updated weights for policy 0, policy_version 326159 (0.0008) -[2023-11-28 08:45:23,185][87424] Updated weights for policy 0, policy_version 326169 (0.0011) -[2023-11-28 08:45:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 166903808. Throughput: 0: 2733.7, 1: 2757.0. Samples: 166925580. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:23,445][86177] Avg episode reward: [(0, '-524.190'), (1, '-494.610')] -[2023-11-28 08:45:24,844][87426] Updated weights for policy 1, policy_version 325830 (0.0011) -[2023-11-28 08:45:25,066][87424] Updated weights for policy 0, policy_version 326179 (0.0010) -[2023-11-28 08:45:25,212][87426] Updated weights for policy 1, policy_version 325840 (0.0011) -[2023-11-28 08:45:25,439][87424] Updated weights for policy 0, policy_version 326189 (0.0010) -[2023-11-28 08:45:25,592][87426] Updated weights for policy 1, policy_version 325850 (0.0009) -[2023-11-28 08:45:25,825][87424] Updated weights for policy 0, policy_version 326199 (0.0008) -[2023-11-28 08:45:27,796][87424] Updated weights for policy 0, policy_version 326209 (0.0007) -[2023-11-28 08:45:28,144][87426] Updated weights for policy 1, policy_version 325860 (0.0008) -[2023-11-28 08:45:28,180][87424] Updated weights for policy 0, policy_version 326219 (0.0007) -[2023-11-28 08:45:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 166928384. Throughput: 0: 2753.3, 1: 2738.8. Samples: 166949884. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:28,445][86177] Avg episode reward: [(0, '-520.310'), (1, '-494.960')] -[2023-11-28 08:45:28,527][87426] Updated weights for policy 1, policy_version 325870 (0.0007) -[2023-11-28 08:45:28,567][87424] Updated weights for policy 0, policy_version 326229 (0.0007) -[2023-11-28 08:45:28,909][87426] Updated weights for policy 1, policy_version 325880 (0.0008) -[2023-11-28 08:45:28,947][87424] Updated weights for policy 0, policy_version 326239 (0.0008) -[2023-11-28 08:45:31,087][87426] Updated weights for policy 1, policy_version 325890 (0.0008) -[2023-11-28 08:45:31,253][87424] Updated weights for policy 0, policy_version 326249 (0.0009) -[2023-11-28 08:45:31,466][87426] Updated weights for policy 1, policy_version 325900 (0.0009) -[2023-11-28 08:45:31,627][87424] Updated weights for policy 0, policy_version 326259 (0.0012) -[2023-11-28 08:45:31,834][87426] Updated weights for policy 1, policy_version 325910 (0.0010) -[2023-11-28 08:45:32,007][87424] Updated weights for policy 0, policy_version 326269 (0.0011) -[2023-11-28 08:45:32,213][87426] Updated weights for policy 1, policy_version 325920 (0.0010) -[2023-11-28 08:45:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 166961152. Throughput: 0: 2742.5, 1: 2721.3. Samples: 166972872. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:33,445][86177] Avg episode reward: [(0, '-522.090'), (1, '-492.410')] -[2023-11-28 08:45:34,146][87424] Updated weights for policy 0, policy_version 326279 (0.0012) -[2023-11-28 08:45:34,522][87424] Updated weights for policy 0, policy_version 326289 (0.0011) -[2023-11-28 08:45:34,578][87426] Updated weights for policy 1, policy_version 325930 (0.0011) -[2023-11-28 08:45:34,900][87424] Updated weights for policy 0, policy_version 326299 (0.0011) -[2023-11-28 08:45:34,971][87426] Updated weights for policy 1, policy_version 325940 (0.0008) -[2023-11-28 08:45:35,343][87426] Updated weights for policy 1, policy_version 325950 (0.0009) -[2023-11-28 08:45:37,326][87426] Updated weights for policy 1, policy_version 325960 (0.0011) -[2023-11-28 08:45:37,376][87424] Updated weights for policy 0, policy_version 326309 (0.0012) -[2023-11-28 08:45:37,708][87426] Updated weights for policy 1, policy_version 325970 (0.0012) -[2023-11-28 08:45:37,763][87424] Updated weights for policy 0, policy_version 326319 (0.0012) -[2023-11-28 08:45:38,087][87426] Updated weights for policy 1, policy_version 325980 (0.0011) -[2023-11-28 08:45:38,142][87424] Updated weights for policy 0, policy_version 326329 (0.0008) -[2023-11-28 08:45:38,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 166993920. Throughput: 0: 2735.8, 1: 2729.2. Samples: 167005480. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:38,445][86177] Avg episode reward: [(0, '-520.720'), (1, '-494.430')] -[2023-11-28 08:45:39,834][87426] Updated weights for policy 1, policy_version 325990 (0.0010) -[2023-11-28 08:45:40,213][87426] Updated weights for policy 1, policy_version 326000 (0.0011) -[2023-11-28 08:45:40,593][87426] Updated weights for policy 1, policy_version 326010 (0.0010) -[2023-11-28 08:45:40,639][87424] Updated weights for policy 0, policy_version 326339 (0.0011) -[2023-11-28 08:45:41,013][87424] Updated weights for policy 0, policy_version 326349 (0.0010) -[2023-11-28 08:45:41,401][87424] Updated weights for policy 0, policy_version 326359 (0.0008) -[2023-11-28 08:45:42,934][87426] Updated weights for policy 1, policy_version 326020 (0.0010) -[2023-11-28 08:45:43,308][87426] Updated weights for policy 1, policy_version 326030 (0.0010) -[2023-11-28 08:45:43,360][87424] Updated weights for policy 0, policy_version 326369 (0.0010) -[2023-11-28 08:45:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167010304. Throughput: 0: 2735.3, 1: 2698.0. Samples: 167029384. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:43,446][86177] Avg episode reward: [(0, '-513.850'), (1, '-494.650')] -[2023-11-28 08:45:43,682][87426] Updated weights for policy 1, policy_version 326040 (0.0011) -[2023-11-28 08:45:43,738][87424] Updated weights for policy 0, policy_version 326379 (0.0008) -[2023-11-28 08:45:44,121][87424] Updated weights for policy 0, policy_version 326389 (0.0011) -[2023-11-28 08:45:44,508][87424] Updated weights for policy 0, policy_version 326399 (0.0012) -[2023-11-28 08:45:45,733][87426] Updated weights for policy 1, policy_version 326050 (0.0011) -[2023-11-28 08:45:46,105][87426] Updated weights for policy 1, policy_version 326060 (0.0012) -[2023-11-28 08:45:46,489][87426] Updated weights for policy 1, policy_version 326070 (0.0011) -[2023-11-28 08:45:46,607][87424] Updated weights for policy 0, policy_version 326409 (0.0011) -[2023-11-28 08:45:46,865][87426] Updated weights for policy 1, policy_version 326080 (0.0011) -[2023-11-28 08:45:46,989][87424] Updated weights for policy 0, policy_version 326419 (0.0012) -[2023-11-28 08:45:47,373][87424] Updated weights for policy 0, policy_version 326429 (0.0012) -[2023-11-28 08:45:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167043072. Throughput: 0: 2743.4, 1: 2692.5. Samples: 167054172. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:48,446][86177] Avg episode reward: [(0, '-511.910'), (1, '-495.610')] -[2023-11-28 08:45:49,107][87426] Updated weights for policy 1, policy_version 326090 (0.0010) -[2023-11-28 08:45:49,487][87424] Updated weights for policy 0, policy_version 326439 (0.0011) -[2023-11-28 08:45:49,495][87426] Updated weights for policy 1, policy_version 326100 (0.0011) -[2023-11-28 08:45:49,861][87426] Updated weights for policy 1, policy_version 326110 (0.0011) -[2023-11-28 08:45:49,867][87424] Updated weights for policy 0, policy_version 326449 (0.0008) -[2023-11-28 08:45:50,253][87424] Updated weights for policy 0, policy_version 326459 (0.0012) -[2023-11-28 08:45:51,732][87426] Updated weights for policy 1, policy_version 326120 (0.0011) -[2023-11-28 08:45:52,107][87426] Updated weights for policy 1, policy_version 326130 (0.0011) -[2023-11-28 08:45:52,484][87426] Updated weights for policy 1, policy_version 326140 (0.0009) -[2023-11-28 08:45:52,489][87424] Updated weights for policy 0, policy_version 326469 (0.0012) -[2023-11-28 08:45:52,876][87424] Updated weights for policy 0, policy_version 326479 (0.0012) -[2023-11-28 08:45:53,246][87424] Updated weights for policy 0, policy_version 326489 (0.0012) -[2023-11-28 08:45:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 167067648. Throughput: 0: 2736.4, 1: 2707.7. Samples: 167086828. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:53,445][86177] Avg episode reward: [(0, '-511.870'), (1, '-517.660')] -[2023-11-28 08:45:54,801][87426] Updated weights for policy 1, policy_version 326150 (0.0007) -[2023-11-28 08:45:55,181][87426] Updated weights for policy 1, policy_version 326160 (0.0009) -[2023-11-28 08:45:55,470][87424] Updated weights for policy 0, policy_version 326499 (0.0011) -[2023-11-28 08:45:55,563][87426] Updated weights for policy 1, policy_version 326170 (0.0009) -[2023-11-28 08:45:55,854][87424] Updated weights for policy 0, policy_version 326509 (0.0010) -[2023-11-28 08:45:56,237][87424] Updated weights for policy 0, policy_version 326519 (0.0007) -[2023-11-28 08:45:57,936][87426] Updated weights for policy 1, policy_version 326180 (0.0009) -[2023-11-28 08:45:58,314][87426] Updated weights for policy 1, policy_version 326190 (0.0012) -[2023-11-28 08:45:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 167092224. Throughput: 0: 2712.2, 1: 2684.9. Samples: 167110052. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:45:58,445][86177] Avg episode reward: [(0, '-513.920'), (1, '-517.900')] -[2023-11-28 08:45:58,485][87424] Updated weights for policy 0, policy_version 326529 (0.0007) -[2023-11-28 08:45:58,685][87426] Updated weights for policy 1, policy_version 326200 (0.0011) -[2023-11-28 08:45:58,868][87424] Updated weights for policy 0, policy_version 326539 (0.0011) -[2023-11-28 08:45:59,246][87424] Updated weights for policy 0, policy_version 326549 (0.0012) -[2023-11-28 08:45:59,634][87424] Updated weights for policy 0, policy_version 326559 (0.0010) -[2023-11-28 08:46:01,295][87426] Updated weights for policy 1, policy_version 326210 (0.0011) -[2023-11-28 08:46:01,666][87426] Updated weights for policy 1, policy_version 326220 (0.0011) -[2023-11-28 08:46:01,842][87424] Updated weights for policy 0, policy_version 326569 (0.0010) -[2023-11-28 08:46:02,051][87426] Updated weights for policy 1, policy_version 326230 (0.0011) -[2023-11-28 08:46:02,230][87424] Updated weights for policy 0, policy_version 326579 (0.0009) -[2023-11-28 08:46:02,427][87426] Updated weights for policy 1, policy_version 326240 (0.0012) -[2023-11-28 08:46:02,601][87424] Updated weights for policy 0, policy_version 326589 (0.0007) -[2023-11-28 08:46:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 167124992. Throughput: 0: 2696.5, 1: 2673.0. Samples: 167134084. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:46:03,445][86177] Avg episode reward: [(0, '-515.940'), (1, '-518.670')] -[2023-11-28 08:46:04,752][87426] Updated weights for policy 1, policy_version 326250 (0.0011) -[2023-11-28 08:46:05,109][87424] Updated weights for policy 0, policy_version 326599 (0.0010) -[2023-11-28 08:46:05,130][87426] Updated weights for policy 1, policy_version 326260 (0.0010) -[2023-11-28 08:46:05,492][87424] Updated weights for policy 0, policy_version 326609 (0.0008) -[2023-11-28 08:46:05,509][87426] Updated weights for policy 1, policy_version 326270 (0.0011) -[2023-11-28 08:46:05,879][87424] Updated weights for policy 0, policy_version 326619 (0.0007) -[2023-11-28 08:46:07,581][87424] Updated weights for policy 0, policy_version 326629 (0.0008) -[2023-11-28 08:46:07,919][87426] Updated weights for policy 1, policy_version 326280 (0.0008) -[2023-11-28 08:46:07,961][87424] Updated weights for policy 0, policy_version 326639 (0.0008) -[2023-11-28 08:46:08,303][87426] Updated weights for policy 1, policy_version 326290 (0.0010) -[2023-11-28 08:46:08,347][87424] Updated weights for policy 0, policy_version 326649 (0.0010) -[2023-11-28 08:46:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 167141376. Throughput: 0: 2688.1, 1: 2668.1. Samples: 167166608. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:46:08,445][86177] Avg episode reward: [(0, '-519.100'), (1, '-499.730')] -[2023-11-28 08:46:08,679][87426] Updated weights for policy 1, policy_version 326300 (0.0009) -[2023-11-28 08:46:10,542][87426] Updated weights for policy 1, policy_version 326310 (0.0009) -[2023-11-28 08:46:10,689][87424] Updated weights for policy 0, policy_version 326659 (0.0011) -[2023-11-28 08:46:10,915][87426] Updated weights for policy 1, policy_version 326320 (0.0011) -[2023-11-28 08:46:11,082][87424] Updated weights for policy 0, policy_version 326669 (0.0012) -[2023-11-28 08:46:11,297][87426] Updated weights for policy 1, policy_version 326330 (0.0010) -[2023-11-28 08:46:11,453][87424] Updated weights for policy 0, policy_version 326679 (0.0011) -[2023-11-28 08:46:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 167174144. Throughput: 0: 2663.6, 1: 2675.7. Samples: 167190152. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 08:46:13,445][86177] Avg episode reward: [(0, '-533.800'), (1, '-498.600')] -[2023-11-28 08:46:13,622][87426] Updated weights for policy 1, policy_version 326340 (0.0010) -[2023-11-28 08:46:13,730][87424] Updated weights for policy 0, policy_version 326689 (0.0011) -[2023-11-28 08:46:13,993][87426] Updated weights for policy 1, policy_version 326350 (0.0008) -[2023-11-28 08:46:14,115][87424] Updated weights for policy 0, policy_version 326699 (0.0011) -[2023-11-28 08:46:14,373][87426] Updated weights for policy 1, policy_version 326360 (0.0008) -[2023-11-28 08:46:14,496][87424] Updated weights for policy 0, policy_version 326709 (0.0011) -[2023-11-28 08:46:14,879][87424] Updated weights for policy 0, policy_version 326719 (0.0012) -[2023-11-28 08:46:16,652][87426] Updated weights for policy 1, policy_version 326370 (0.0009) -[2023-11-28 08:46:17,027][87426] Updated weights for policy 1, policy_version 326380 (0.0011) -[2023-11-28 08:46:17,123][87424] Updated weights for policy 0, policy_version 326729 (0.0011) -[2023-11-28 08:46:17,406][87426] Updated weights for policy 1, policy_version 326390 (0.0011) -[2023-11-28 08:46:17,505][87424] Updated weights for policy 0, policy_version 326739 (0.0009) -[2023-11-28 08:46:17,788][87426] Updated weights for policy 1, policy_version 326400 (0.0012) -[2023-11-28 08:46:17,888][87424] Updated weights for policy 0, policy_version 326749 (0.0008) -[2023-11-28 08:46:18,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 167206912. Throughput: 0: 2711.9, 1: 2680.9. Samples: 167215548. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:46:18,445][86177] Avg episode reward: [(0, '-553.240'), (1, '-543.500')] -[2023-11-28 08:46:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000326400_83558400.pth... -[2023-11-28 08:46:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000326752_83648512.pth... -[2023-11-28 08:46:18,506][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000323872_82911232.pth -[2023-11-28 08:46:18,507][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000324192_82993152.pth -[2023-11-28 08:46:19,638][87424] Updated weights for policy 0, policy_version 326759 (0.0009) -[2023-11-28 08:46:19,715][87426] Updated weights for policy 1, policy_version 326410 (0.0009) -[2023-11-28 08:46:20,031][87424] Updated weights for policy 0, policy_version 326769 (0.0011) -[2023-11-28 08:46:20,101][87426] Updated weights for policy 1, policy_version 326420 (0.0010) -[2023-11-28 08:46:20,410][87424] Updated weights for policy 0, policy_version 326779 (0.0011) -[2023-11-28 08:46:20,482][87426] Updated weights for policy 1, policy_version 326430 (0.0011) -[2023-11-28 08:46:22,857][87426] Updated weights for policy 1, policy_version 326440 (0.0010) -[2023-11-28 08:46:22,955][87424] Updated weights for policy 0, policy_version 326789 (0.0010) -[2023-11-28 08:46:23,236][87426] Updated weights for policy 1, policy_version 326450 (0.0010) -[2023-11-28 08:46:23,335][87424] Updated weights for policy 0, policy_version 326799 (0.0011) -[2023-11-28 08:46:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 167223296. Throughput: 0: 2724.2, 1: 2663.4. Samples: 167247920. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:46:23,445][86177] Avg episode reward: [(0, '-554.610'), (1, '-542.510')] -[2023-11-28 08:46:23,611][87426] Updated weights for policy 1, policy_version 326460 (0.0011) -[2023-11-28 08:46:23,722][87424] Updated weights for policy 0, policy_version 326809 (0.0010) -[2023-11-28 08:46:25,551][87426] Updated weights for policy 1, policy_version 326470 (0.0011) -[2023-11-28 08:46:25,825][87424] Updated weights for policy 0, policy_version 326819 (0.0008) -[2023-11-28 08:46:25,929][87426] Updated weights for policy 1, policy_version 326480 (0.0011) -[2023-11-28 08:46:26,202][87424] Updated weights for policy 0, policy_version 326829 (0.0012) -[2023-11-28 08:46:26,302][87426] Updated weights for policy 1, policy_version 326490 (0.0010) -[2023-11-28 08:46:26,585][87424] Updated weights for policy 0, policy_version 326839 (0.0011) -[2023-11-28 08:46:28,237][87426] Updated weights for policy 1, policy_version 326500 (0.0008) -[2023-11-28 08:46:28,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167256064. Throughput: 0: 2722.5, 1: 2680.0. Samples: 167272496. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:46:28,446][86177] Avg episode reward: [(0, '-555.210'), (1, '-541.850')] -[2023-11-28 08:46:28,618][87426] Updated weights for policy 1, policy_version 326510 (0.0010) -[2023-11-28 08:46:28,681][87424] Updated weights for policy 0, policy_version 326849 (0.0012) -[2023-11-28 08:46:28,990][87426] Updated weights for policy 1, policy_version 326520 (0.0009) -[2023-11-28 08:46:29,066][87424] Updated weights for policy 0, policy_version 326859 (0.0008) -[2023-11-28 08:46:29,441][87424] Updated weights for policy 0, policy_version 326869 (0.0007) -[2023-11-28 08:46:29,831][87424] Updated weights for policy 0, policy_version 326879 (0.0008) -[2023-11-28 08:46:31,361][87426] Updated weights for policy 1, policy_version 326530 (0.0008) -[2023-11-28 08:46:31,734][87426] Updated weights for policy 1, policy_version 326540 (0.0009) -[2023-11-28 08:46:32,119][87426] Updated weights for policy 1, policy_version 326550 (0.0008) -[2023-11-28 08:46:32,249][87424] Updated weights for policy 0, policy_version 326889 (0.0011) -[2023-11-28 08:46:32,492][87426] Updated weights for policy 1, policy_version 326560 (0.0008) -[2023-11-28 08:46:32,632][87424] Updated weights for policy 0, policy_version 326899 (0.0011) -[2023-11-28 08:46:33,006][87424] Updated weights for policy 0, policy_version 326909 (0.0012) -[2023-11-28 08:46:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167288832. Throughput: 0: 2711.7, 1: 2671.3. Samples: 167296408. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:46:33,445][86177] Avg episode reward: [(0, '-538.950'), (1, '-495.250')] -[2023-11-28 08:46:34,394][87426] Updated weights for policy 1, policy_version 326570 (0.0009) -[2023-11-28 08:46:34,779][87426] Updated weights for policy 1, policy_version 326580 (0.0010) -[2023-11-28 08:46:34,971][87424] Updated weights for policy 0, policy_version 326919 (0.0011) -[2023-11-28 08:46:35,158][87426] Updated weights for policy 1, policy_version 326590 (0.0009) -[2023-11-28 08:46:35,350][87424] Updated weights for policy 0, policy_version 326929 (0.0010) -[2023-11-28 08:46:35,741][87424] Updated weights for policy 0, policy_version 326939 (0.0007) -[2023-11-28 08:46:37,300][87426] Updated weights for policy 1, policy_version 326600 (0.0012) -[2023-11-28 08:46:37,522][87424] Updated weights for policy 0, policy_version 326949 (0.0010) -[2023-11-28 08:46:37,691][87426] Updated weights for policy 1, policy_version 326610 (0.0011) -[2023-11-28 08:46:37,907][87424] Updated weights for policy 0, policy_version 326959 (0.0008) -[2023-11-28 08:46:38,060][87426] Updated weights for policy 1, policy_version 326620 (0.0012) -[2023-11-28 08:46:38,290][87424] Updated weights for policy 0, policy_version 326969 (0.0007) -[2023-11-28 08:46:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 167313408. Throughput: 0: 2719.6, 1: 2704.1. Samples: 167330892. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:46:38,445][86177] Avg episode reward: [(0, '-518.830'), (1, '-493.250')] -[2023-11-28 08:46:40,366][87426] Updated weights for policy 1, policy_version 326630 (0.0011) -[2023-11-28 08:46:40,478][87424] Updated weights for policy 0, policy_version 326979 (0.0009) -[2023-11-28 08:46:40,737][87426] Updated weights for policy 1, policy_version 326640 (0.0016) -[2023-11-28 08:46:40,850][87424] Updated weights for policy 0, policy_version 326989 (0.0012) -[2023-11-28 08:46:41,121][87426] Updated weights for policy 1, policy_version 326650 (0.0010) -[2023-11-28 08:46:41,229][87424] Updated weights for policy 0, policy_version 326999 (0.0012) -[2023-11-28 08:46:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 167337984. Throughput: 0: 2717.0, 1: 2723.2. Samples: 167354860. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:46:43,445][86177] Avg episode reward: [(0, '-519.050'), (1, '-494.000')] -[2023-11-28 08:46:43,557][87426] Updated weights for policy 1, policy_version 326660 (0.0010) -[2023-11-28 08:46:43,689][87424] Updated weights for policy 0, policy_version 327009 (0.0012) -[2023-11-28 08:46:43,927][87426] Updated weights for policy 1, policy_version 326670 (0.0007) -[2023-11-28 08:46:44,076][87424] Updated weights for policy 0, policy_version 327019 (0.0012) -[2023-11-28 08:46:44,306][87426] Updated weights for policy 1, policy_version 326680 (0.0008) -[2023-11-28 08:46:44,460][87424] Updated weights for policy 0, policy_version 327029 (0.0011) -[2023-11-28 08:46:44,844][87424] Updated weights for policy 0, policy_version 327039 (0.0012) -[2023-11-28 08:46:46,712][87424] Updated weights for policy 0, policy_version 327049 (0.0012) -[2023-11-28 08:46:46,786][87426] Updated weights for policy 1, policy_version 326690 (0.0008) -[2023-11-28 08:46:47,087][87424] Updated weights for policy 0, policy_version 327059 (0.0011) -[2023-11-28 08:46:47,152][87426] Updated weights for policy 1, policy_version 326700 (0.0011) -[2023-11-28 08:46:47,468][87424] Updated weights for policy 0, policy_version 327069 (0.0008) -[2023-11-28 08:46:47,529][87426] Updated weights for policy 1, policy_version 326710 (0.0007) -[2023-11-28 08:46:47,906][87426] Updated weights for policy 1, policy_version 326720 (0.0007) -[2023-11-28 08:46:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 167370752. Throughput: 0: 2736.1, 1: 2721.2. Samples: 167379660. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:46:48,445][86177] Avg episode reward: [(0, '-524.650'), (1, '-495.360')] -[2023-11-28 08:46:49,553][87424] Updated weights for policy 0, policy_version 327079 (0.0010) -[2023-11-28 08:46:49,944][87424] Updated weights for policy 0, policy_version 327089 (0.0011) -[2023-11-28 08:46:50,314][87424] Updated weights for policy 0, policy_version 327099 (0.0010) -[2023-11-28 08:46:50,508][87426] Updated weights for policy 1, policy_version 326730 (0.0010) -[2023-11-28 08:46:50,889][87426] Updated weights for policy 1, policy_version 326740 (0.0008) -[2023-11-28 08:46:51,270][87426] Updated weights for policy 1, policy_version 326750 (0.0010) -[2023-11-28 08:46:52,559][87424] Updated weights for policy 0, policy_version 327109 (0.0011) -[2023-11-28 08:46:52,934][87424] Updated weights for policy 0, policy_version 327119 (0.0009) -[2023-11-28 08:46:53,318][87424] Updated weights for policy 0, policy_version 327129 (0.0011) -[2023-11-28 08:46:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 167387136. Throughput: 0: 2747.1, 1: 2700.4. Samples: 167411748. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:46:53,445][86177] Avg episode reward: [(0, '-535.780'), (1, '-497.670')] -[2023-11-28 08:46:53,460][87426] Updated weights for policy 1, policy_version 326760 (0.0010) -[2023-11-28 08:46:53,842][87426] Updated weights for policy 1, policy_version 326770 (0.0011) -[2023-11-28 08:46:54,223][87426] Updated weights for policy 1, policy_version 326780 (0.0012) -[2023-11-28 08:46:55,590][87424] Updated weights for policy 0, policy_version 327139 (0.0011) -[2023-11-28 08:46:55,967][87424] Updated weights for policy 0, policy_version 327149 (0.0010) -[2023-11-28 08:46:55,977][87426] Updated weights for policy 1, policy_version 326790 (0.0011) -[2023-11-28 08:46:56,352][87424] Updated weights for policy 0, policy_version 327159 (0.0010) -[2023-11-28 08:46:56,356][87426] Updated weights for policy 1, policy_version 326800 (0.0011) -[2023-11-28 08:46:56,735][87426] Updated weights for policy 1, policy_version 326810 (0.0011) -[2023-11-28 08:46:58,157][87424] Updated weights for policy 0, policy_version 327169 (0.0012) -[2023-11-28 08:46:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167419904. Throughput: 0: 2755.2, 1: 2719.0. Samples: 167436492. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:46:58,445][86177] Avg episode reward: [(0, '-537.450'), (1, '-498.660')] -[2023-11-28 08:46:58,526][87424] Updated weights for policy 0, policy_version 327179 (0.0011) -[2023-11-28 08:46:58,906][87424] Updated weights for policy 0, policy_version 327189 (0.0008) -[2023-11-28 08:46:59,224][87426] Updated weights for policy 1, policy_version 326820 (0.0011) -[2023-11-28 08:46:59,283][87424] Updated weights for policy 0, policy_version 327199 (0.0007) -[2023-11-28 08:46:59,596][87426] Updated weights for policy 1, policy_version 326830 (0.0011) -[2023-11-28 08:46:59,975][87426] Updated weights for policy 1, policy_version 326840 (0.0011) -[2023-11-28 08:47:01,459][87424] Updated weights for policy 0, policy_version 327209 (0.0008) -[2023-11-28 08:47:01,833][87424] Updated weights for policy 0, policy_version 327219 (0.0010) -[2023-11-28 08:47:02,021][87426] Updated weights for policy 1, policy_version 326850 (0.0008) -[2023-11-28 08:47:02,218][87424] Updated weights for policy 0, policy_version 327229 (0.0010) -[2023-11-28 08:47:02,401][87426] Updated weights for policy 1, policy_version 326860 (0.0010) -[2023-11-28 08:47:02,795][87426] Updated weights for policy 1, policy_version 326870 (0.0007) -[2023-11-28 08:47:03,167][87426] Updated weights for policy 1, policy_version 326880 (0.0007) -[2023-11-28 08:47:03,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 167452672. Throughput: 0: 2761.0, 1: 2723.6. Samples: 167462356. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:47:03,445][86177] Avg episode reward: [(0, '-538.590'), (1, '-497.320')] -[2023-11-28 08:47:04,568][87424] Updated weights for policy 0, policy_version 327239 (0.0011) -[2023-11-28 08:47:04,946][87424] Updated weights for policy 0, policy_version 327249 (0.0011) -[2023-11-28 08:47:05,173][87426] Updated weights for policy 1, policy_version 326890 (0.0009) -[2023-11-28 08:47:05,332][87424] Updated weights for policy 0, policy_version 327259 (0.0011) -[2023-11-28 08:47:05,550][87426] Updated weights for policy 1, policy_version 326900 (0.0012) -[2023-11-28 08:47:05,943][87426] Updated weights for policy 1, policy_version 326910 (0.0011) -[2023-11-28 08:47:07,264][87424] Updated weights for policy 0, policy_version 327269 (0.0012) -[2023-11-28 08:47:07,640][87424] Updated weights for policy 0, policy_version 327279 (0.0012) -[2023-11-28 08:47:08,029][87424] Updated weights for policy 0, policy_version 327289 (0.0012) -[2023-11-28 08:47:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 167477248. Throughput: 0: 2764.6, 1: 2705.1. Samples: 167494056. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:47:08,445][86177] Avg episode reward: [(0, '-530.860'), (1, '-496.520')] -[2023-11-28 08:47:08,463][87426] Updated weights for policy 1, policy_version 326920 (0.0008) -[2023-11-28 08:47:08,850][87426] Updated weights for policy 1, policy_version 326930 (0.0009) -[2023-11-28 08:47:09,223][87426] Updated weights for policy 1, policy_version 326940 (0.0011) -[2023-11-28 08:47:10,430][87424] Updated weights for policy 0, policy_version 327299 (0.0011) -[2023-11-28 08:47:10,817][87424] Updated weights for policy 0, policy_version 327309 (0.0010) -[2023-11-28 08:47:11,190][87424] Updated weights for policy 0, policy_version 327319 (0.0011) -[2023-11-28 08:47:11,710][87426] Updated weights for policy 1, policy_version 326950 (0.0011) -[2023-11-28 08:47:12,086][87426] Updated weights for policy 1, policy_version 326960 (0.0011) -[2023-11-28 08:47:12,457][87426] Updated weights for policy 1, policy_version 326970 (0.0011) -[2023-11-28 08:47:13,350][87424] Updated weights for policy 0, policy_version 327329 (0.0009) -[2023-11-28 08:47:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167501824. Throughput: 0: 2767.0, 1: 2676.6. Samples: 167517460. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:47:13,445][86177] Avg episode reward: [(0, '-520.350'), (1, '-494.190')] -[2023-11-28 08:47:13,736][87424] Updated weights for policy 0, policy_version 327339 (0.0012) -[2023-11-28 08:47:14,121][87424] Updated weights for policy 0, policy_version 327349 (0.0012) -[2023-11-28 08:47:14,452][87426] Updated weights for policy 1, policy_version 326980 (0.0011) -[2023-11-28 08:47:14,501][87424] Updated weights for policy 0, policy_version 327359 (0.0010) -[2023-11-28 08:47:14,832][87426] Updated weights for policy 1, policy_version 326990 (0.0011) -[2023-11-28 08:47:15,203][87426] Updated weights for policy 1, policy_version 327000 (0.0007) -[2023-11-28 08:47:16,248][87424] Updated weights for policy 0, policy_version 327369 (0.0008) -[2023-11-28 08:47:16,625][87424] Updated weights for policy 0, policy_version 327379 (0.0008) -[2023-11-28 08:47:17,010][87426] Updated weights for policy 1, policy_version 327010 (0.0011) -[2023-11-28 08:47:17,015][87424] Updated weights for policy 0, policy_version 327389 (0.0009) -[2023-11-28 08:47:17,388][87426] Updated weights for policy 1, policy_version 327020 (0.0012) -[2023-11-28 08:47:17,766][87426] Updated weights for policy 1, policy_version 327030 (0.0012) -[2023-11-28 08:47:18,150][87426] Updated weights for policy 1, policy_version 327040 (0.0012) -[2023-11-28 08:47:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 167534592. Throughput: 0: 2757.0, 1: 2694.4. Samples: 167541720. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:47:18,445][86177] Avg episode reward: [(0, '-522.710'), (1, '-492.560')] -[2023-11-28 08:47:18,855][87424] Updated weights for policy 0, policy_version 327399 (0.0009) -[2023-11-28 08:47:19,238][87424] Updated weights for policy 0, policy_version 327409 (0.0009) -[2023-11-28 08:47:19,619][87424] Updated weights for policy 0, policy_version 327419 (0.0012) -[2023-11-28 08:47:20,623][87426] Updated weights for policy 1, policy_version 327050 (0.0012) -[2023-11-28 08:47:21,001][87426] Updated weights for policy 1, policy_version 327060 (0.0011) -[2023-11-28 08:47:21,384][87426] Updated weights for policy 1, policy_version 327070 (0.0010) -[2023-11-28 08:47:21,951][87424] Updated weights for policy 0, policy_version 327429 (0.0012) -[2023-11-28 08:47:22,342][87424] Updated weights for policy 0, policy_version 327439 (0.0011) -[2023-11-28 08:47:22,719][87424] Updated weights for policy 0, policy_version 327449 (0.0008) -[2023-11-28 08:47:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 167559168. Throughput: 0: 2760.7, 1: 2660.4. Samples: 167574840. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:47:23,445][86177] Avg episode reward: [(0, '-529.560'), (1, '-492.950')] -[2023-11-28 08:47:23,511][87426] Updated weights for policy 1, policy_version 327080 (0.0012) -[2023-11-28 08:47:23,886][87426] Updated weights for policy 1, policy_version 327090 (0.0011) -[2023-11-28 08:47:24,267][87426] Updated weights for policy 1, policy_version 327100 (0.0012) -[2023-11-28 08:47:25,062][87424] Updated weights for policy 0, policy_version 327459 (0.0011) -[2023-11-28 08:47:25,443][87424] Updated weights for policy 0, policy_version 327469 (0.0012) -[2023-11-28 08:47:25,836][87424] Updated weights for policy 0, policy_version 327479 (0.0011) -[2023-11-28 08:47:26,629][87426] Updated weights for policy 1, policy_version 327110 (0.0009) -[2023-11-28 08:47:27,011][87426] Updated weights for policy 1, policy_version 327120 (0.0008) -[2023-11-28 08:47:27,404][87426] Updated weights for policy 1, policy_version 327130 (0.0010) -[2023-11-28 08:47:28,239][87424] Updated weights for policy 0, policy_version 327489 (0.0008) -[2023-11-28 08:47:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 167583744. Throughput: 0: 2766.8, 1: 2654.8. Samples: 167598828. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:47:28,445][86177] Avg episode reward: [(0, '-568.220'), (1, '-491.310')] -[2023-11-28 08:47:28,610][87424] Updated weights for policy 0, policy_version 327499 (0.0012) -[2023-11-28 08:47:29,002][87424] Updated weights for policy 0, policy_version 327509 (0.0012) -[2023-11-28 08:47:29,263][87426] Updated weights for policy 1, policy_version 327140 (0.0009) -[2023-11-28 08:47:29,379][87424] Updated weights for policy 0, policy_version 327519 (0.0011) -[2023-11-28 08:47:29,639][87426] Updated weights for policy 1, policy_version 327150 (0.0011) -[2023-11-28 08:47:30,017][87426] Updated weights for policy 1, policy_version 327160 (0.0010) -[2023-11-28 08:47:31,794][87424] Updated weights for policy 0, policy_version 327529 (0.0012) -[2023-11-28 08:47:32,179][87424] Updated weights for policy 0, policy_version 327539 (0.0011) -[2023-11-28 08:47:32,492][87426] Updated weights for policy 1, policy_version 327170 (0.0008) -[2023-11-28 08:47:32,553][87424] Updated weights for policy 0, policy_version 327549 (0.0009) -[2023-11-28 08:47:32,869][87426] Updated weights for policy 1, policy_version 327180 (0.0011) -[2023-11-28 08:47:33,237][87426] Updated weights for policy 1, policy_version 327190 (0.0012) -[2023-11-28 08:47:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 167608320. Throughput: 0: 2746.1, 1: 2659.4. Samples: 167622908. Policy #0 lag: (min: 6.0, avg: 21.6, max: 38.0) -[2023-11-28 08:47:33,445][86177] Avg episode reward: [(0, '-569.130'), (1, '-493.690')] -[2023-11-28 08:47:33,614][87426] Updated weights for policy 1, policy_version 327200 (0.0012) -[2023-11-28 08:47:34,741][87424] Updated weights for policy 0, policy_version 327559 (0.0009) -[2023-11-28 08:47:35,132][87424] Updated weights for policy 0, policy_version 327569 (0.0008) -[2023-11-28 08:47:35,470][87426] Updated weights for policy 1, policy_version 327210 (0.0010) -[2023-11-28 08:47:35,518][87424] Updated weights for policy 0, policy_version 327579 (0.0009) -[2023-11-28 08:47:35,857][87426] Updated weights for policy 1, policy_version 327220 (0.0012) -[2023-11-28 08:47:36,224][87426] Updated weights for policy 1, policy_version 327230 (0.0012) -[2023-11-28 08:47:37,377][87424] Updated weights for policy 0, policy_version 327589 (0.0011) -[2023-11-28 08:47:37,765][87424] Updated weights for policy 0, policy_version 327599 (0.0012) -[2023-11-28 08:47:38,142][87424] Updated weights for policy 0, policy_version 327609 (0.0009) -[2023-11-28 08:47:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 167641088. Throughput: 0: 2745.7, 1: 2686.5. Samples: 167656196. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:47:38,445][86177] Avg episode reward: [(0, '-569.790'), (1, '-495.760')] -[2023-11-28 08:47:38,816][87426] Updated weights for policy 1, policy_version 327240 (0.0012) -[2023-11-28 08:47:39,197][87426] Updated weights for policy 1, policy_version 327250 (0.0009) -[2023-11-28 08:47:39,576][87426] Updated weights for policy 1, policy_version 327260 (0.0011) -[2023-11-28 08:47:40,167][87424] Updated weights for policy 0, policy_version 327619 (0.0008) -[2023-11-28 08:47:40,546][87424] Updated weights for policy 0, policy_version 327629 (0.0010) -[2023-11-28 08:47:40,926][87424] Updated weights for policy 0, policy_version 327639 (0.0008) -[2023-11-28 08:47:41,558][87426] Updated weights for policy 1, policy_version 327270 (0.0010) -[2023-11-28 08:47:41,939][87426] Updated weights for policy 1, policy_version 327280 (0.0010) -[2023-11-28 08:47:42,307][87426] Updated weights for policy 1, policy_version 327290 (0.0011) -[2023-11-28 08:47:43,337][87424] Updated weights for policy 0, policy_version 327649 (0.0007) -[2023-11-28 08:47:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167665664. Throughput: 0: 2740.8, 1: 2660.2. Samples: 167679536. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:47:43,445][86177] Avg episode reward: [(0, '-561.850'), (1, '-498.560')] -[2023-11-28 08:47:43,719][87424] Updated weights for policy 0, policy_version 327659 (0.0007) -[2023-11-28 08:47:44,105][87424] Updated weights for policy 0, policy_version 327669 (0.0008) -[2023-11-28 08:47:44,492][87424] Updated weights for policy 0, policy_version 327679 (0.0007) -[2023-11-28 08:47:44,905][87426] Updated weights for policy 1, policy_version 327300 (0.0009) -[2023-11-28 08:47:45,281][87426] Updated weights for policy 1, policy_version 327310 (0.0007) -[2023-11-28 08:47:45,663][87426] Updated weights for policy 1, policy_version 327320 (0.0011) -[2023-11-28 08:47:46,753][87424] Updated weights for policy 0, policy_version 327689 (0.0011) -[2023-11-28 08:47:47,138][87424] Updated weights for policy 0, policy_version 327699 (0.0012) -[2023-11-28 08:47:47,434][87426] Updated weights for policy 1, policy_version 327330 (0.0012) -[2023-11-28 08:47:47,530][87424] Updated weights for policy 0, policy_version 327709 (0.0012) -[2023-11-28 08:47:47,811][87426] Updated weights for policy 1, policy_version 327340 (0.0011) -[2023-11-28 08:47:48,190][87426] Updated weights for policy 1, policy_version 327350 (0.0007) -[2023-11-28 08:47:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 167690240. Throughput: 0: 2705.3, 1: 2646.6. Samples: 167703192. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:47:48,445][86177] Avg episode reward: [(0, '-521.720'), (1, '-503.180')] -[2023-11-28 08:47:48,568][87426] Updated weights for policy 1, policy_version 327360 (0.0010) -[2023-11-28 08:47:49,427][87424] Updated weights for policy 0, policy_version 327719 (0.0012) -[2023-11-28 08:47:49,809][87424] Updated weights for policy 0, policy_version 327729 (0.0011) -[2023-11-28 08:47:50,184][87424] Updated weights for policy 0, policy_version 327739 (0.0012) -[2023-11-28 08:47:51,008][87426] Updated weights for policy 1, policy_version 327370 (0.0010) -[2023-11-28 08:47:51,391][87426] Updated weights for policy 1, policy_version 327380 (0.0012) -[2023-11-28 08:47:51,772][87426] Updated weights for policy 1, policy_version 327390 (0.0012) -[2023-11-28 08:47:52,703][87424] Updated weights for policy 0, policy_version 327749 (0.0011) -[2023-11-28 08:47:53,095][87424] Updated weights for policy 0, policy_version 327759 (0.0012) -[2023-11-28 08:47:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 167714816. Throughput: 0: 2710.2, 1: 2658.8. Samples: 167735664. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:47:53,445][86177] Avg episode reward: [(0, '-513.020'), (1, '-502.120')] -[2023-11-28 08:47:53,471][87424] Updated weights for policy 0, policy_version 327769 (0.0011) -[2023-11-28 08:47:54,392][87426] Updated weights for policy 1, policy_version 327400 (0.0009) -[2023-11-28 08:47:54,772][87426] Updated weights for policy 1, policy_version 327410 (0.0011) -[2023-11-28 08:47:55,151][87426] Updated weights for policy 1, policy_version 327420 (0.0011) -[2023-11-28 08:47:55,675][87424] Updated weights for policy 0, policy_version 327779 (0.0012) -[2023-11-28 08:47:56,057][87424] Updated weights for policy 0, policy_version 327789 (0.0012) -[2023-11-28 08:47:56,433][87424] Updated weights for policy 0, policy_version 327799 (0.0012) -[2023-11-28 08:47:56,846][87426] Updated weights for policy 1, policy_version 327430 (0.0010) -[2023-11-28 08:47:57,223][87426] Updated weights for policy 1, policy_version 327440 (0.0011) -[2023-11-28 08:47:57,604][87426] Updated weights for policy 1, policy_version 327450 (0.0011) -[2023-11-28 08:47:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167747584. Throughput: 0: 2703.6, 1: 2700.3. Samples: 167760636. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:47:58,446][86177] Avg episode reward: [(0, '-511.290'), (1, '-504.910')] -[2023-11-28 08:47:58,556][87424] Updated weights for policy 0, policy_version 327809 (0.0011) -[2023-11-28 08:47:58,928][87424] Updated weights for policy 0, policy_version 327819 (0.0008) -[2023-11-28 08:47:59,321][87424] Updated weights for policy 0, policy_version 327829 (0.0010) -[2023-11-28 08:47:59,687][87424] Updated weights for policy 0, policy_version 327839 (0.0010) -[2023-11-28 08:47:59,760][87426] Updated weights for policy 1, policy_version 327460 (0.0012) -[2023-11-28 08:48:00,139][87426] Updated weights for policy 1, policy_version 327470 (0.0011) -[2023-11-28 08:48:00,517][87426] Updated weights for policy 1, policy_version 327480 (0.0012) -[2023-11-28 08:48:02,060][87424] Updated weights for policy 0, policy_version 327849 (0.0008) -[2023-11-28 08:48:02,446][87424] Updated weights for policy 0, policy_version 327859 (0.0009) -[2023-11-28 08:48:02,543][87426] Updated weights for policy 1, policy_version 327490 (0.0011) -[2023-11-28 08:48:02,828][87424] Updated weights for policy 0, policy_version 327869 (0.0009) -[2023-11-28 08:48:02,926][87426] Updated weights for policy 1, policy_version 327500 (0.0011) -[2023-11-28 08:48:03,310][87426] Updated weights for policy 1, policy_version 327510 (0.0010) -[2023-11-28 08:48:03,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 167772160. Throughput: 0: 2694.6, 1: 2710.8. Samples: 167784964. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:03,445][86177] Avg episode reward: [(0, '-511.970'), (1, '-503.090')] -[2023-11-28 08:48:03,688][87426] Updated weights for policy 1, policy_version 327520 (0.0011) -[2023-11-28 08:48:05,370][87424] Updated weights for policy 0, policy_version 327879 (0.0011) -[2023-11-28 08:48:05,760][87424] Updated weights for policy 0, policy_version 327889 (0.0011) -[2023-11-28 08:48:05,762][87426] Updated weights for policy 1, policy_version 327530 (0.0010) -[2023-11-28 08:48:06,130][87424] Updated weights for policy 0, policy_version 327899 (0.0010) -[2023-11-28 08:48:06,143][87426] Updated weights for policy 1, policy_version 327540 (0.0009) -[2023-11-28 08:48:06,516][87426] Updated weights for policy 1, policy_version 327550 (0.0009) -[2023-11-28 08:48:08,013][87424] Updated weights for policy 0, policy_version 327909 (0.0010) -[2023-11-28 08:48:08,400][87424] Updated weights for policy 0, policy_version 327919 (0.0007) -[2023-11-28 08:48:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 167796736. Throughput: 0: 2674.0, 1: 2729.2. Samples: 167817988. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:08,446][86177] Avg episode reward: [(0, '-509.300'), (1, '-504.150')] -[2023-11-28 08:48:08,797][87424] Updated weights for policy 0, policy_version 327929 (0.0009) -[2023-11-28 08:48:08,972][87426] Updated weights for policy 1, policy_version 327560 (0.0009) -[2023-11-28 08:48:09,350][87426] Updated weights for policy 1, policy_version 327570 (0.0011) -[2023-11-28 08:48:09,735][87426] Updated weights for policy 1, policy_version 327580 (0.0008) -[2023-11-28 08:48:11,124][87424] Updated weights for policy 0, policy_version 327939 (0.0010) -[2023-11-28 08:48:11,495][87424] Updated weights for policy 0, policy_version 327949 (0.0012) -[2023-11-28 08:48:11,811][87426] Updated weights for policy 1, policy_version 327590 (0.0011) -[2023-11-28 08:48:11,880][87424] Updated weights for policy 0, policy_version 327959 (0.0011) -[2023-11-28 08:48:12,189][87426] Updated weights for policy 1, policy_version 327600 (0.0009) -[2023-11-28 08:48:12,567][87426] Updated weights for policy 1, policy_version 327610 (0.0012) -[2023-11-28 08:48:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167829504. Throughput: 0: 2662.4, 1: 2733.5. Samples: 167841644. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:13,445][86177] Avg episode reward: [(0, '-510.950'), (1, '-505.560')] -[2023-11-28 08:48:14,098][87424] Updated weights for policy 0, policy_version 327969 (0.0011) -[2023-11-28 08:48:14,481][87424] Updated weights for policy 0, policy_version 327979 (0.0012) -[2023-11-28 08:48:14,849][87426] Updated weights for policy 1, policy_version 327620 (0.0009) -[2023-11-28 08:48:14,856][87424] Updated weights for policy 0, policy_version 327989 (0.0011) -[2023-11-28 08:48:15,223][87424] Updated weights for policy 0, policy_version 327999 (0.0011) -[2023-11-28 08:48:15,229][87426] Updated weights for policy 1, policy_version 327630 (0.0010) -[2023-11-28 08:48:15,613][87426] Updated weights for policy 1, policy_version 327640 (0.0011) -[2023-11-28 08:48:17,364][87426] Updated weights for policy 1, policy_version 327650 (0.0012) -[2023-11-28 08:48:17,536][87424] Updated weights for policy 0, policy_version 328009 (0.0010) -[2023-11-28 08:48:17,741][87426] Updated weights for policy 1, policy_version 327660 (0.0012) -[2023-11-28 08:48:17,916][87424] Updated weights for policy 0, policy_version 328019 (0.0008) -[2023-11-28 08:48:18,120][87426] Updated weights for policy 1, policy_version 327670 (0.0012) -[2023-11-28 08:48:18,303][87424] Updated weights for policy 0, policy_version 328029 (0.0008) -[2023-11-28 08:48:18,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 167854080. Throughput: 0: 2657.1, 1: 2727.2. Samples: 167865200. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:18,446][86177] Avg episode reward: [(0, '-511.940'), (1, '-501.870')] -[2023-11-28 08:48:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000328032_83976192.pth... -[2023-11-28 08:48:18,492][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000327680_83886080.pth... -[2023-11-28 08:48:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000325472_83320832.pth -[2023-11-28 08:48:18,494][87426] Updated weights for policy 1, policy_version 327680 (0.0010) -[2023-11-28 08:48:18,521][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000325120_83230720.pth -[2023-11-28 08:48:20,539][87426] Updated weights for policy 1, policy_version 327690 (0.0011) -[2023-11-28 08:48:20,735][87424] Updated weights for policy 0, policy_version 328039 (0.0011) -[2023-11-28 08:48:20,923][87426] Updated weights for policy 1, policy_version 327700 (0.0009) -[2023-11-28 08:48:21,111][87424] Updated weights for policy 0, policy_version 328049 (0.0012) -[2023-11-28 08:48:21,303][87426] Updated weights for policy 1, policy_version 327710 (0.0012) -[2023-11-28 08:48:21,493][87424] Updated weights for policy 0, policy_version 328059 (0.0012) -[2023-11-28 08:48:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 167878656. Throughput: 0: 2627.1, 1: 2722.5. Samples: 167896928. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:23,445][86177] Avg episode reward: [(0, '-511.420'), (1, '-505.350')] -[2023-11-28 08:48:23,549][87426] Updated weights for policy 1, policy_version 327720 (0.0012) -[2023-11-28 08:48:23,930][87426] Updated weights for policy 1, policy_version 327730 (0.0010) -[2023-11-28 08:48:24,044][87424] Updated weights for policy 0, policy_version 328069 (0.0012) -[2023-11-28 08:48:24,315][87426] Updated weights for policy 1, policy_version 327740 (0.0011) -[2023-11-28 08:48:24,421][87424] Updated weights for policy 0, policy_version 328079 (0.0011) -[2023-11-28 08:48:24,802][87424] Updated weights for policy 0, policy_version 328089 (0.0008) -[2023-11-28 08:48:26,639][87424] Updated weights for policy 0, policy_version 328099 (0.0009) -[2023-11-28 08:48:26,713][87426] Updated weights for policy 1, policy_version 327750 (0.0012) -[2023-11-28 08:48:27,019][87424] Updated weights for policy 0, policy_version 328109 (0.0010) -[2023-11-28 08:48:27,093][87426] Updated weights for policy 1, policy_version 327760 (0.0008) -[2023-11-28 08:48:27,400][87424] Updated weights for policy 0, policy_version 328119 (0.0007) -[2023-11-28 08:48:27,467][87426] Updated weights for policy 1, policy_version 327770 (0.0007) -[2023-11-28 08:48:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 167911424. Throughput: 0: 2634.0, 1: 2727.1. Samples: 167920784. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:28,445][86177] Avg episode reward: [(0, '-511.390'), (1, '-501.700')] -[2023-11-28 08:48:29,667][87426] Updated weights for policy 1, policy_version 327780 (0.0009) -[2023-11-28 08:48:29,984][87424] Updated weights for policy 0, policy_version 328129 (0.0008) -[2023-11-28 08:48:30,046][87426] Updated weights for policy 1, policy_version 327790 (0.0009) -[2023-11-28 08:48:30,374][87424] Updated weights for policy 0, policy_version 328139 (0.0011) -[2023-11-28 08:48:30,428][87426] Updated weights for policy 1, policy_version 327800 (0.0008) -[2023-11-28 08:48:30,749][87424] Updated weights for policy 0, policy_version 328149 (0.0011) -[2023-11-28 08:48:31,136][87424] Updated weights for policy 0, policy_version 328159 (0.0012) -[2023-11-28 08:48:32,634][87426] Updated weights for policy 1, policy_version 327810 (0.0010) -[2023-11-28 08:48:33,010][87426] Updated weights for policy 1, policy_version 327820 (0.0009) -[2023-11-28 08:48:33,382][87426] Updated weights for policy 1, policy_version 327830 (0.0008) -[2023-11-28 08:48:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 167927808. Throughput: 0: 2622.8, 1: 2743.8. Samples: 167944688. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:33,445][86177] Avg episode reward: [(0, '-508.780'), (1, '-505.300')] -[2023-11-28 08:48:33,608][87424] Updated weights for policy 0, policy_version 328169 (0.0009) -[2023-11-28 08:48:33,759][87426] Updated weights for policy 1, policy_version 327840 (0.0009) -[2023-11-28 08:48:33,979][87424] Updated weights for policy 0, policy_version 328179 (0.0012) -[2023-11-28 08:48:34,350][87424] Updated weights for policy 0, policy_version 328189 (0.0012) -[2023-11-28 08:48:35,883][87426] Updated weights for policy 1, policy_version 327850 (0.0011) -[2023-11-28 08:48:36,266][87426] Updated weights for policy 1, policy_version 327860 (0.0012) -[2023-11-28 08:48:36,534][87424] Updated weights for policy 0, policy_version 328199 (0.0009) -[2023-11-28 08:48:36,649][87426] Updated weights for policy 1, policy_version 327870 (0.0011) -[2023-11-28 08:48:36,918][87424] Updated weights for policy 0, policy_version 328209 (0.0010) -[2023-11-28 08:48:37,299][87424] Updated weights for policy 0, policy_version 328219 (0.0011) -[2023-11-28 08:48:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 167960576. Throughput: 0: 2595.1, 1: 2769.2. Samples: 167977060. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:38,445][86177] Avg episode reward: [(0, '-509.030'), (1, '-502.950')] -[2023-11-28 08:48:38,666][87426] Updated weights for policy 1, policy_version 327880 (0.0011) -[2023-11-28 08:48:39,041][87426] Updated weights for policy 1, policy_version 327890 (0.0008) -[2023-11-28 08:48:39,430][87426] Updated weights for policy 1, policy_version 327900 (0.0011) -[2023-11-28 08:48:39,431][87424] Updated weights for policy 0, policy_version 328229 (0.0011) -[2023-11-28 08:48:39,807][87424] Updated weights for policy 0, policy_version 328239 (0.0012) -[2023-11-28 08:48:40,188][87424] Updated weights for policy 0, policy_version 328249 (0.0009) -[2023-11-28 08:48:41,289][87426] Updated weights for policy 1, policy_version 327910 (0.0011) -[2023-11-28 08:48:41,667][87426] Updated weights for policy 1, policy_version 327920 (0.0012) -[2023-11-28 08:48:42,040][87426] Updated weights for policy 1, policy_version 327930 (0.0012) -[2023-11-28 08:48:42,618][87424] Updated weights for policy 0, policy_version 328259 (0.0009) -[2023-11-28 08:48:42,999][87424] Updated weights for policy 0, policy_version 328269 (0.0012) -[2023-11-28 08:48:43,381][87424] Updated weights for policy 0, policy_version 328279 (0.0010) -[2023-11-28 08:48:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 167985152. Throughput: 0: 2611.7, 1: 2757.3. Samples: 168002240. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:43,445][86177] Avg episode reward: [(0, '-509.080'), (1, '-502.070')] -[2023-11-28 08:48:43,981][87426] Updated weights for policy 1, policy_version 327940 (0.0012) -[2023-11-28 08:48:44,369][87426] Updated weights for policy 1, policy_version 327950 (0.0012) -[2023-11-28 08:48:44,746][87426] Updated weights for policy 1, policy_version 327960 (0.0012) -[2023-11-28 08:48:45,461][87424] Updated weights for policy 0, policy_version 328289 (0.0012) -[2023-11-28 08:48:45,834][87424] Updated weights for policy 0, policy_version 328299 (0.0012) -[2023-11-28 08:48:46,216][87424] Updated weights for policy 0, policy_version 328309 (0.0012) -[2023-11-28 08:48:46,598][87424] Updated weights for policy 0, policy_version 328319 (0.0012) -[2023-11-28 08:48:46,857][87426] Updated weights for policy 1, policy_version 327970 (0.0012) -[2023-11-28 08:48:47,232][87426] Updated weights for policy 1, policy_version 327980 (0.0012) -[2023-11-28 08:48:47,612][87426] Updated weights for policy 1, policy_version 327990 (0.0012) -[2023-11-28 08:48:47,991][87426] Updated weights for policy 1, policy_version 328000 (0.0012) -[2023-11-28 08:48:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 168017920. Throughput: 0: 2642.2, 1: 2759.7. Samples: 168028052. Policy #0 lag: (min: 56.0, avg: 63.0, max: 88.0) -[2023-11-28 08:48:48,445][86177] Avg episode reward: [(0, '-510.170'), (1, '-500.910')] -[2023-11-28 08:48:48,467][87424] Updated weights for policy 0, policy_version 328329 (0.0012) -[2023-11-28 08:48:48,862][87424] Updated weights for policy 0, policy_version 328339 (0.0012) -[2023-11-28 08:48:49,242][87424] Updated weights for policy 0, policy_version 328349 (0.0012) -[2023-11-28 08:48:49,950][87426] Updated weights for policy 1, policy_version 328010 (0.0010) -[2023-11-28 08:48:50,328][87426] Updated weights for policy 1, policy_version 328020 (0.0008) -[2023-11-28 08:48:50,700][87426] Updated weights for policy 1, policy_version 328030 (0.0012) -[2023-11-28 08:48:51,178][87424] Updated weights for policy 0, policy_version 328359 (0.0012) -[2023-11-28 08:48:51,550][87424] Updated weights for policy 0, policy_version 328369 (0.0012) -[2023-11-28 08:48:51,932][87424] Updated weights for policy 0, policy_version 328379 (0.0011) -[2023-11-28 08:48:53,181][87426] Updated weights for policy 1, policy_version 328040 (0.0012) -[2023-11-28 08:48:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168042496. Throughput: 0: 2678.0, 1: 2743.9. Samples: 168061972. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:48:53,445][86177] Avg episode reward: [(0, '-525.650'), (1, '-497.130')] -[2023-11-28 08:48:53,557][87426] Updated weights for policy 1, policy_version 328050 (0.0010) -[2023-11-28 08:48:53,928][87424] Updated weights for policy 0, policy_version 328389 (0.0011) -[2023-11-28 08:48:53,934][87426] Updated weights for policy 1, policy_version 328060 (0.0010) -[2023-11-28 08:48:54,306][87424] Updated weights for policy 0, policy_version 328399 (0.0010) -[2023-11-28 08:48:54,702][87424] Updated weights for policy 0, policy_version 328409 (0.0011) -[2023-11-28 08:48:56,562][87426] Updated weights for policy 1, policy_version 328070 (0.0009) -[2023-11-28 08:48:56,681][87424] Updated weights for policy 0, policy_version 328419 (0.0011) -[2023-11-28 08:48:56,942][87426] Updated weights for policy 1, policy_version 328080 (0.0007) -[2023-11-28 08:48:57,068][87424] Updated weights for policy 0, policy_version 328429 (0.0008) -[2023-11-28 08:48:57,318][87426] Updated weights for policy 1, policy_version 328090 (0.0008) -[2023-11-28 08:48:57,460][87424] Updated weights for policy 0, policy_version 328439 (0.0007) -[2023-11-28 08:48:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168075264. Throughput: 0: 2681.8, 1: 2760.2. Samples: 168086532. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:48:58,445][86177] Avg episode reward: [(0, '-528.700'), (1, '-498.070')] -[2023-11-28 08:48:59,072][87426] Updated weights for policy 1, policy_version 328100 (0.0009) -[2023-11-28 08:48:59,453][87426] Updated weights for policy 1, policy_version 328110 (0.0012) -[2023-11-28 08:48:59,728][87424] Updated weights for policy 0, policy_version 328449 (0.0008) -[2023-11-28 08:48:59,825][87426] Updated weights for policy 1, policy_version 328120 (0.0011) -[2023-11-28 08:49:00,107][87424] Updated weights for policy 0, policy_version 328459 (0.0009) -[2023-11-28 08:49:00,487][87424] Updated weights for policy 0, policy_version 328469 (0.0008) -[2023-11-28 08:49:00,868][87424] Updated weights for policy 0, policy_version 328479 (0.0007) -[2023-11-28 08:49:01,869][87426] Updated weights for policy 1, policy_version 328130 (0.0010) -[2023-11-28 08:49:02,257][87426] Updated weights for policy 1, policy_version 328140 (0.0011) -[2023-11-28 08:49:02,628][87426] Updated weights for policy 1, policy_version 328150 (0.0009) -[2023-11-28 08:49:02,817][87424] Updated weights for policy 0, policy_version 328489 (0.0010) -[2023-11-28 08:49:03,003][87426] Updated weights for policy 1, policy_version 328160 (0.0008) -[2023-11-28 08:49:03,198][87424] Updated weights for policy 0, policy_version 328499 (0.0008) -[2023-11-28 08:49:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 168099840. Throughput: 0: 2715.0, 1: 2775.7. Samples: 168112280. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:03,445][86177] Avg episode reward: [(0, '-525.810'), (1, '-499.440')] -[2023-11-28 08:49:03,578][87424] Updated weights for policy 0, policy_version 328509 (0.0008) -[2023-11-28 08:49:05,143][87426] Updated weights for policy 1, policy_version 328170 (0.0012) -[2023-11-28 08:49:05,414][87424] Updated weights for policy 0, policy_version 328519 (0.0010) -[2023-11-28 08:49:05,528][87426] Updated weights for policy 1, policy_version 328180 (0.0010) -[2023-11-28 08:49:05,800][87424] Updated weights for policy 0, policy_version 328529 (0.0008) -[2023-11-28 08:49:05,914][87426] Updated weights for policy 1, policy_version 328190 (0.0011) -[2023-11-28 08:49:06,179][87424] Updated weights for policy 0, policy_version 328539 (0.0007) -[2023-11-28 08:49:08,235][87426] Updated weights for policy 1, policy_version 328200 (0.0011) -[2023-11-28 08:49:08,358][87424] Updated weights for policy 0, policy_version 328549 (0.0009) -[2023-11-28 08:49:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 168124416. Throughput: 0: 2747.5, 1: 2757.2. Samples: 168144640. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:08,445][86177] Avg episode reward: [(0, '-526.200'), (1, '-500.460')] -[2023-11-28 08:49:08,622][87426] Updated weights for policy 1, policy_version 328210 (0.0011) -[2023-11-28 08:49:08,751][87424] Updated weights for policy 0, policy_version 328559 (0.0011) -[2023-11-28 08:49:09,004][87426] Updated weights for policy 1, policy_version 328220 (0.0012) -[2023-11-28 08:49:09,136][87424] Updated weights for policy 0, policy_version 328569 (0.0012) -[2023-11-28 08:49:11,112][87426] Updated weights for policy 1, policy_version 328230 (0.0009) -[2023-11-28 08:49:11,389][87424] Updated weights for policy 0, policy_version 328579 (0.0010) -[2023-11-28 08:49:11,492][87426] Updated weights for policy 1, policy_version 328240 (0.0007) -[2023-11-28 08:49:11,769][87424] Updated weights for policy 0, policy_version 328589 (0.0011) -[2023-11-28 08:49:11,877][87426] Updated weights for policy 1, policy_version 328250 (0.0011) -[2023-11-28 08:49:12,144][87424] Updated weights for policy 0, policy_version 328599 (0.0011) -[2023-11-28 08:49:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168157184. Throughput: 0: 2751.1, 1: 2761.4. Samples: 168168848. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:13,445][86177] Avg episode reward: [(0, '-517.990'), (1, '-497.890')] -[2023-11-28 08:49:14,172][87424] Updated weights for policy 0, policy_version 328609 (0.0012) -[2023-11-28 08:49:14,234][87426] Updated weights for policy 1, policy_version 328260 (0.0011) -[2023-11-28 08:49:14,549][87424] Updated weights for policy 0, policy_version 328619 (0.0008) -[2023-11-28 08:49:14,617][87426] Updated weights for policy 1, policy_version 328270 (0.0007) -[2023-11-28 08:49:14,933][87424] Updated weights for policy 0, policy_version 328629 (0.0007) -[2023-11-28 08:49:14,998][87426] Updated weights for policy 1, policy_version 328280 (0.0007) -[2023-11-28 08:49:15,310][87424] Updated weights for policy 0, policy_version 328639 (0.0008) -[2023-11-28 08:49:16,982][87426] Updated weights for policy 1, policy_version 328290 (0.0008) -[2023-11-28 08:49:17,373][87426] Updated weights for policy 1, policy_version 328300 (0.0010) -[2023-11-28 08:49:17,748][87426] Updated weights for policy 1, policy_version 328310 (0.0007) -[2023-11-28 08:49:17,784][87424] Updated weights for policy 0, policy_version 328649 (0.0011) -[2023-11-28 08:49:18,130][87426] Updated weights for policy 1, policy_version 328320 (0.0007) -[2023-11-28 08:49:18,160][87424] Updated weights for policy 0, policy_version 328659 (0.0011) -[2023-11-28 08:49:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 168181760. Throughput: 0: 2780.3, 1: 2747.0. Samples: 168193416. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:18,445][86177] Avg episode reward: [(0, '-516.210'), (1, '-499.320')] -[2023-11-28 08:49:18,539][87424] Updated weights for policy 0, policy_version 328669 (0.0008) -[2023-11-28 08:49:20,244][87426] Updated weights for policy 1, policy_version 328330 (0.0010) -[2023-11-28 08:49:20,601][87424] Updated weights for policy 0, policy_version 328679 (0.0009) -[2023-11-28 08:49:20,624][87426] Updated weights for policy 1, policy_version 328340 (0.0010) -[2023-11-28 08:49:20,983][87424] Updated weights for policy 0, policy_version 328689 (0.0011) -[2023-11-28 08:49:21,005][87426] Updated weights for policy 1, policy_version 328350 (0.0009) -[2023-11-28 08:49:21,360][87424] Updated weights for policy 0, policy_version 328699 (0.0010) -[2023-11-28 08:49:23,422][87424] Updated weights for policy 0, policy_version 328709 (0.0012) -[2023-11-28 08:49:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168206336. Throughput: 0: 2791.6, 1: 2743.8. Samples: 168226152. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:23,445][86177] Avg episode reward: [(0, '-515.960'), (1, '-500.310')] -[2023-11-28 08:49:23,530][87426] Updated weights for policy 1, policy_version 328360 (0.0011) -[2023-11-28 08:49:23,799][87424] Updated weights for policy 0, policy_version 328719 (0.0012) -[2023-11-28 08:49:23,909][87426] Updated weights for policy 1, policy_version 328370 (0.0012) -[2023-11-28 08:49:24,185][87424] Updated weights for policy 0, policy_version 328729 (0.0012) -[2023-11-28 08:49:24,294][87426] Updated weights for policy 1, policy_version 328380 (0.0011) -[2023-11-28 08:49:26,142][87426] Updated weights for policy 1, policy_version 328390 (0.0011) -[2023-11-28 08:49:26,533][87426] Updated weights for policy 1, policy_version 328400 (0.0011) -[2023-11-28 08:49:26,571][87424] Updated weights for policy 0, policy_version 328739 (0.0011) -[2023-11-28 08:49:26,909][87426] Updated weights for policy 1, policy_version 328410 (0.0011) -[2023-11-28 08:49:26,937][87424] Updated weights for policy 0, policy_version 328749 (0.0012) -[2023-11-28 08:49:27,312][87424] Updated weights for policy 0, policy_version 328759 (0.0012) -[2023-11-28 08:49:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168239104. Throughput: 0: 2786.7, 1: 2718.7. Samples: 168249980. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:28,445][86177] Avg episode reward: [(0, '-511.580'), (1, '-501.270')] -[2023-11-28 08:49:29,311][87426] Updated weights for policy 1, policy_version 328420 (0.0011) -[2023-11-28 08:49:29,692][87426] Updated weights for policy 1, policy_version 328430 (0.0012) -[2023-11-28 08:49:29,927][87424] Updated weights for policy 0, policy_version 328769 (0.0012) -[2023-11-28 08:49:30,062][87426] Updated weights for policy 1, policy_version 328440 (0.0011) -[2023-11-28 08:49:30,307][87424] Updated weights for policy 0, policy_version 328779 (0.0012) -[2023-11-28 08:49:30,696][87424] Updated weights for policy 0, policy_version 328789 (0.0012) -[2023-11-28 08:49:31,074][87424] Updated weights for policy 0, policy_version 328799 (0.0012) -[2023-11-28 08:49:32,115][87426] Updated weights for policy 1, policy_version 328450 (0.0011) -[2023-11-28 08:49:32,494][87426] Updated weights for policy 1, policy_version 328460 (0.0011) -[2023-11-28 08:49:32,872][87426] Updated weights for policy 1, policy_version 328470 (0.0011) -[2023-11-28 08:49:32,991][87424] Updated weights for policy 0, policy_version 328809 (0.0010) -[2023-11-28 08:49:33,241][87426] Updated weights for policy 1, policy_version 328480 (0.0011) -[2023-11-28 08:49:33,376][87424] Updated weights for policy 0, policy_version 328819 (0.0010) -[2023-11-28 08:49:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 168263680. Throughput: 0: 2766.7, 1: 2700.5. Samples: 168274076. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:33,445][86177] Avg episode reward: [(0, '-514.980'), (1, '-506.650')] -[2023-11-28 08:49:33,766][87424] Updated weights for policy 0, policy_version 328829 (0.0010) -[2023-11-28 08:49:35,406][87426] Updated weights for policy 1, policy_version 328490 (0.0011) -[2023-11-28 08:49:35,785][87426] Updated weights for policy 1, policy_version 328500 (0.0011) -[2023-11-28 08:49:35,870][87424] Updated weights for policy 0, policy_version 328839 (0.0011) -[2023-11-28 08:49:36,156][87426] Updated weights for policy 1, policy_version 328510 (0.0012) -[2023-11-28 08:49:36,242][87424] Updated weights for policy 0, policy_version 328849 (0.0009) -[2023-11-28 08:49:36,628][87424] Updated weights for policy 0, policy_version 328859 (0.0011) -[2023-11-28 08:49:38,085][87426] Updated weights for policy 1, policy_version 328520 (0.0010) -[2023-11-28 08:49:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168288256. Throughput: 0: 2735.0, 1: 2724.3. Samples: 168307640. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:38,445][86177] Avg episode reward: [(0, '-520.190'), (1, '-502.360')] -[2023-11-28 08:49:38,467][87426] Updated weights for policy 1, policy_version 328530 (0.0007) -[2023-11-28 08:49:38,850][87426] Updated weights for policy 1, policy_version 328540 (0.0008) -[2023-11-28 08:49:39,074][87424] Updated weights for policy 0, policy_version 328869 (0.0012) -[2023-11-28 08:49:39,454][87424] Updated weights for policy 0, policy_version 328879 (0.0012) -[2023-11-28 08:49:39,837][87424] Updated weights for policy 0, policy_version 328889 (0.0012) -[2023-11-28 08:49:40,831][87426] Updated weights for policy 1, policy_version 328550 (0.0011) -[2023-11-28 08:49:41,221][87426] Updated weights for policy 1, policy_version 328560 (0.0012) -[2023-11-28 08:49:41,600][87426] Updated weights for policy 1, policy_version 328570 (0.0012) -[2023-11-28 08:49:42,248][87424] Updated weights for policy 0, policy_version 328899 (0.0012) -[2023-11-28 08:49:42,628][87424] Updated weights for policy 0, policy_version 328909 (0.0012) -[2023-11-28 08:49:43,008][87424] Updated weights for policy 0, policy_version 328919 (0.0011) -[2023-11-28 08:49:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 168321024. Throughput: 0: 2733.7, 1: 2743.0. Samples: 168332984. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:43,445][86177] Avg episode reward: [(0, '-519.890'), (1, '-525.790')] -[2023-11-28 08:49:43,629][87426] Updated weights for policy 1, policy_version 328580 (0.0011) -[2023-11-28 08:49:44,006][87426] Updated weights for policy 1, policy_version 328590 (0.0010) -[2023-11-28 08:49:44,390][87426] Updated weights for policy 1, policy_version 328600 (0.0007) -[2023-11-28 08:49:45,087][87424] Updated weights for policy 0, policy_version 328929 (0.0011) -[2023-11-28 08:49:45,479][87424] Updated weights for policy 0, policy_version 328939 (0.0010) -[2023-11-28 08:49:45,848][87424] Updated weights for policy 0, policy_version 328949 (0.0011) -[2023-11-28 08:49:46,233][87424] Updated weights for policy 0, policy_version 328959 (0.0011) -[2023-11-28 08:49:46,687][87426] Updated weights for policy 1, policy_version 328610 (0.0008) -[2023-11-28 08:49:47,085][87426] Updated weights for policy 1, policy_version 328620 (0.0011) -[2023-11-28 08:49:47,455][87426] Updated weights for policy 1, policy_version 328630 (0.0011) -[2023-11-28 08:49:47,837][87426] Updated weights for policy 1, policy_version 328640 (0.0011) -[2023-11-28 08:49:48,236][87424] Updated weights for policy 0, policy_version 328969 (0.0011) -[2023-11-28 08:49:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 168345600. Throughput: 0: 2701.2, 1: 2735.8. Samples: 168356948. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:48,445][86177] Avg episode reward: [(0, '-518.630'), (1, '-527.650')] -[2023-11-28 08:49:48,619][87424] Updated weights for policy 0, policy_version 328979 (0.0010) -[2023-11-28 08:49:48,998][87424] Updated weights for policy 0, policy_version 328989 (0.0008) -[2023-11-28 08:49:50,378][87426] Updated weights for policy 1, policy_version 328650 (0.0011) -[2023-11-28 08:49:50,764][87426] Updated weights for policy 1, policy_version 328660 (0.0011) -[2023-11-28 08:49:51,136][87426] Updated weights for policy 1, policy_version 328670 (0.0011) -[2023-11-28 08:49:51,279][87424] Updated weights for policy 0, policy_version 328999 (0.0008) -[2023-11-28 08:49:51,672][87424] Updated weights for policy 0, policy_version 329009 (0.0009) -[2023-11-28 08:49:52,059][87424] Updated weights for policy 0, policy_version 329019 (0.0011) -[2023-11-28 08:49:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 168370176. Throughput: 0: 2694.8, 1: 2732.1. Samples: 168388852. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:53,445][86177] Avg episode reward: [(0, '-521.370'), (1, '-546.470')] -[2023-11-28 08:49:53,677][87426] Updated weights for policy 1, policy_version 328680 (0.0012) -[2023-11-28 08:49:54,053][87426] Updated weights for policy 1, policy_version 328690 (0.0012) -[2023-11-28 08:49:54,327][87424] Updated weights for policy 0, policy_version 329029 (0.0012) -[2023-11-28 08:49:54,441][87426] Updated weights for policy 1, policy_version 328700 (0.0009) -[2023-11-28 08:49:54,712][87424] Updated weights for policy 0, policy_version 329039 (0.0010) -[2023-11-28 08:49:55,099][87424] Updated weights for policy 0, policy_version 329049 (0.0012) -[2023-11-28 08:49:56,446][87426] Updated weights for policy 1, policy_version 328710 (0.0010) -[2023-11-28 08:49:56,828][87426] Updated weights for policy 1, policy_version 328720 (0.0008) -[2023-11-28 08:49:57,201][87424] Updated weights for policy 0, policy_version 329059 (0.0010) -[2023-11-28 08:49:57,219][87426] Updated weights for policy 1, policy_version 328730 (0.0007) -[2023-11-28 08:49:57,581][87424] Updated weights for policy 0, policy_version 329069 (0.0012) -[2023-11-28 08:49:57,961][87424] Updated weights for policy 0, policy_version 329079 (0.0012) -[2023-11-28 08:49:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168402944. Throughput: 0: 2690.8, 1: 2733.3. Samples: 168412936. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:49:58,445][86177] Avg episode reward: [(0, '-521.450'), (1, '-563.130')] -[2023-11-28 08:49:59,397][87426] Updated weights for policy 1, policy_version 328740 (0.0009) -[2023-11-28 08:49:59,769][87426] Updated weights for policy 1, policy_version 328750 (0.0009) -[2023-11-28 08:50:00,163][87426] Updated weights for policy 1, policy_version 328760 (0.0009) -[2023-11-28 08:50:00,293][87424] Updated weights for policy 0, policy_version 329089 (0.0011) -[2023-11-28 08:50:00,679][87424] Updated weights for policy 0, policy_version 329099 (0.0011) -[2023-11-28 08:50:01,062][87424] Updated weights for policy 0, policy_version 329109 (0.0011) -[2023-11-28 08:50:01,448][87424] Updated weights for policy 0, policy_version 329119 (0.0012) -[2023-11-28 08:50:02,377][87426] Updated weights for policy 1, policy_version 328770 (0.0010) -[2023-11-28 08:50:02,754][87426] Updated weights for policy 1, policy_version 328780 (0.0012) -[2023-11-28 08:50:03,125][87426] Updated weights for policy 1, policy_version 328790 (0.0011) -[2023-11-28 08:50:03,291][87424] Updated weights for policy 0, policy_version 329129 (0.0011) -[2023-11-28 08:50:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 168419328. Throughput: 0: 2682.5, 1: 2749.3. Samples: 168437844. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:50:03,445][86177] Avg episode reward: [(0, '-523.850'), (1, '-564.810')] -[2023-11-28 08:50:03,502][87426] Updated weights for policy 1, policy_version 328800 (0.0011) -[2023-11-28 08:50:03,674][87424] Updated weights for policy 0, policy_version 329139 (0.0011) -[2023-11-28 08:50:04,056][87424] Updated weights for policy 0, policy_version 329149 (0.0012) -[2023-11-28 08:50:05,509][87426] Updated weights for policy 1, policy_version 328810 (0.0010) -[2023-11-28 08:50:05,891][87426] Updated weights for policy 1, policy_version 328820 (0.0008) -[2023-11-28 08:50:06,276][87426] Updated weights for policy 1, policy_version 328830 (0.0009) -[2023-11-28 08:50:06,581][87424] Updated weights for policy 0, policy_version 329159 (0.0009) -[2023-11-28 08:50:06,973][87424] Updated weights for policy 0, policy_version 329169 (0.0010) -[2023-11-28 08:50:07,346][87424] Updated weights for policy 0, policy_version 329179 (0.0008) -[2023-11-28 08:50:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 168452096. Throughput: 0: 2690.4, 1: 2723.8. Samples: 168469792. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:50:08,445][86177] Avg episode reward: [(0, '-521.180'), (1, '-557.620')] -[2023-11-28 08:50:08,747][87426] Updated weights for policy 1, policy_version 328840 (0.0007) -[2023-11-28 08:50:09,118][87426] Updated weights for policy 1, policy_version 328850 (0.0010) -[2023-11-28 08:50:09,503][87426] Updated weights for policy 1, policy_version 328860 (0.0010) -[2023-11-28 08:50:09,650][87424] Updated weights for policy 0, policy_version 329189 (0.0010) -[2023-11-28 08:50:10,033][87424] Updated weights for policy 0, policy_version 329199 (0.0010) -[2023-11-28 08:50:10,416][87424] Updated weights for policy 0, policy_version 329209 (0.0009) -[2023-11-28 08:50:12,053][87426] Updated weights for policy 1, policy_version 328870 (0.0012) -[2023-11-28 08:50:12,166][87424] Updated weights for policy 0, policy_version 329219 (0.0009) -[2023-11-28 08:50:12,436][87426] Updated weights for policy 1, policy_version 328880 (0.0011) -[2023-11-28 08:50:12,548][87424] Updated weights for policy 0, policy_version 329229 (0.0010) -[2023-11-28 08:50:12,813][87426] Updated weights for policy 1, policy_version 328890 (0.0010) -[2023-11-28 08:50:12,932][87424] Updated weights for policy 0, policy_version 329239 (0.0012) -[2023-11-28 08:50:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168484864. Throughput: 0: 2698.8, 1: 2717.5. Samples: 168493712. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:13,445][86177] Avg episode reward: [(0, '-530.790'), (1, '-552.810')] -[2023-11-28 08:50:15,041][87424] Updated weights for policy 0, policy_version 329249 (0.0012) -[2023-11-28 08:50:15,301][87426] Updated weights for policy 1, policy_version 328900 (0.0010) -[2023-11-28 08:50:15,422][87424] Updated weights for policy 0, policy_version 329259 (0.0010) -[2023-11-28 08:50:15,682][87426] Updated weights for policy 1, policy_version 328910 (0.0010) -[2023-11-28 08:50:15,794][87424] Updated weights for policy 0, policy_version 329269 (0.0010) -[2023-11-28 08:50:16,062][87426] Updated weights for policy 1, policy_version 328920 (0.0010) -[2023-11-28 08:50:16,178][87424] Updated weights for policy 0, policy_version 329279 (0.0010) -[2023-11-28 08:50:18,144][87426] Updated weights for policy 1, policy_version 328930 (0.0011) -[2023-11-28 08:50:18,194][87424] Updated weights for policy 0, policy_version 329289 (0.0011) -[2023-11-28 08:50:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 168501248. Throughput: 0: 2719.6, 1: 2716.7. Samples: 168518712. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:18,445][86177] Avg episode reward: [(0, '-528.050'), (1, '-557.390')] -[2023-11-28 08:50:18,522][87426] Updated weights for policy 1, policy_version 328940 (0.0011) -[2023-11-28 08:50:18,572][87424] Updated weights for policy 0, policy_version 329299 (0.0011) -[2023-11-28 08:50:18,908][87426] Updated weights for policy 1, policy_version 328950 (0.0011) -[2023-11-28 08:50:18,972][87424] Updated weights for policy 0, policy_version 329309 (0.0012) -[2023-11-28 08:50:19,076][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000329312_84303872.pth... -[2023-11-28 08:50:19,107][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000326752_83648512.pth -[2023-11-28 08:50:19,278][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000328960_84213760.pth... -[2023-11-28 08:50:19,280][87426] Updated weights for policy 1, policy_version 328960 (0.0012) -[2023-11-28 08:50:19,309][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000326400_83558400.pth -[2023-11-28 08:50:21,106][87424] Updated weights for policy 0, policy_version 329319 (0.0012) -[2023-11-28 08:50:21,487][87424] Updated weights for policy 0, policy_version 329329 (0.0011) -[2023-11-28 08:50:21,570][87426] Updated weights for policy 1, policy_version 328970 (0.0011) -[2023-11-28 08:50:21,866][87424] Updated weights for policy 0, policy_version 329339 (0.0012) -[2023-11-28 08:50:21,948][87426] Updated weights for policy 1, policy_version 328980 (0.0012) -[2023-11-28 08:50:22,323][87426] Updated weights for policy 1, policy_version 328990 (0.0012) -[2023-11-28 08:50:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168534016. Throughput: 0: 2713.9, 1: 2683.2. Samples: 168550512. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:23,445][86177] Avg episode reward: [(0, '-528.070'), (1, '-561.950')] -[2023-11-28 08:50:24,114][87426] Updated weights for policy 1, policy_version 329000 (0.0010) -[2023-11-28 08:50:24,488][87426] Updated weights for policy 1, policy_version 329010 (0.0011) -[2023-11-28 08:50:24,563][87424] Updated weights for policy 0, policy_version 329349 (0.0013) -[2023-11-28 08:50:24,868][87426] Updated weights for policy 1, policy_version 329020 (0.0010) -[2023-11-28 08:50:24,948][87424] Updated weights for policy 0, policy_version 329359 (0.0011) -[2023-11-28 08:50:25,324][87424] Updated weights for policy 0, policy_version 329369 (0.0012) -[2023-11-28 08:50:27,055][87426] Updated weights for policy 1, policy_version 329030 (0.0008) -[2023-11-28 08:50:27,243][87424] Updated weights for policy 0, policy_version 329379 (0.0012) -[2023-11-28 08:50:27,445][87426] Updated weights for policy 1, policy_version 329040 (0.0007) -[2023-11-28 08:50:27,629][87424] Updated weights for policy 0, policy_version 329389 (0.0012) -[2023-11-28 08:50:27,836][87426] Updated weights for policy 1, policy_version 329050 (0.0007) -[2023-11-28 08:50:28,012][87424] Updated weights for policy 0, policy_version 329399 (0.0012) -[2023-11-28 08:50:28,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168566784. Throughput: 0: 2705.4, 1: 2667.6. Samples: 168574772. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:28,446][86177] Avg episode reward: [(0, '-545.360'), (1, '-553.090')] -[2023-11-28 08:50:29,714][87426] Updated weights for policy 1, policy_version 329060 (0.0011) -[2023-11-28 08:50:30,093][87426] Updated weights for policy 1, policy_version 329070 (0.0009) -[2023-11-28 08:50:30,155][87424] Updated weights for policy 0, policy_version 329409 (0.0009) -[2023-11-28 08:50:30,470][87426] Updated weights for policy 1, policy_version 329080 (0.0008) -[2023-11-28 08:50:30,535][87424] Updated weights for policy 0, policy_version 329419 (0.0010) -[2023-11-28 08:50:30,918][87424] Updated weights for policy 0, policy_version 329429 (0.0008) -[2023-11-28 08:50:31,298][87424] Updated weights for policy 0, policy_version 329439 (0.0007) -[2023-11-28 08:50:32,721][87426] Updated weights for policy 1, policy_version 329090 (0.0009) -[2023-11-28 08:50:33,099][87426] Updated weights for policy 1, policy_version 329100 (0.0012) -[2023-11-28 08:50:33,409][87424] Updated weights for policy 0, policy_version 329449 (0.0007) -[2023-11-28 08:50:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 168583168. Throughput: 0: 2723.2, 1: 2660.0. Samples: 168599192. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:33,445][86177] Avg episode reward: [(0, '-527.950'), (1, '-561.960')] -[2023-11-28 08:50:33,481][87426] Updated weights for policy 1, policy_version 329110 (0.0011) -[2023-11-28 08:50:33,794][87424] Updated weights for policy 0, policy_version 329459 (0.0007) -[2023-11-28 08:50:33,861][87426] Updated weights for policy 1, policy_version 329120 (0.0012) -[2023-11-28 08:50:34,183][87424] Updated weights for policy 0, policy_version 329469 (0.0007) -[2023-11-28 08:50:36,256][87426] Updated weights for policy 1, policy_version 329130 (0.0007) -[2023-11-28 08:50:36,610][87424] Updated weights for policy 0, policy_version 329479 (0.0010) -[2023-11-28 08:50:36,638][87426] Updated weights for policy 1, policy_version 329140 (0.0008) -[2023-11-28 08:50:36,997][87424] Updated weights for policy 0, policy_version 329489 (0.0011) -[2023-11-28 08:50:37,025][87426] Updated weights for policy 1, policy_version 329150 (0.0011) -[2023-11-28 08:50:37,370][87424] Updated weights for policy 0, policy_version 329499 (0.0010) -[2023-11-28 08:50:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168615936. Throughput: 0: 2714.0, 1: 2678.3. Samples: 168631504. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:38,445][86177] Avg episode reward: [(0, '-526.290'), (1, '-569.870')] -[2023-11-28 08:50:39,347][87424] Updated weights for policy 0, policy_version 329509 (0.0012) -[2023-11-28 08:50:39,501][87426] Updated weights for policy 1, policy_version 329160 (0.0011) -[2023-11-28 08:50:39,727][87424] Updated weights for policy 0, policy_version 329519 (0.0011) -[2023-11-28 08:50:39,881][87426] Updated weights for policy 1, policy_version 329170 (0.0011) -[2023-11-28 08:50:40,113][87424] Updated weights for policy 0, policy_version 329529 (0.0011) -[2023-11-28 08:50:40,264][87426] Updated weights for policy 1, policy_version 329180 (0.0011) -[2023-11-28 08:50:42,572][87426] Updated weights for policy 1, policy_version 329190 (0.0009) -[2023-11-28 08:50:42,646][87424] Updated weights for policy 0, policy_version 329539 (0.0011) -[2023-11-28 08:50:42,947][87426] Updated weights for policy 1, policy_version 329200 (0.0012) -[2023-11-28 08:50:43,027][87424] Updated weights for policy 0, policy_version 329549 (0.0011) -[2023-11-28 08:50:43,330][87426] Updated weights for policy 1, policy_version 329210 (0.0009) -[2023-11-28 08:50:43,412][87424] Updated weights for policy 0, policy_version 329559 (0.0011) -[2023-11-28 08:50:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 168632320. Throughput: 0: 2730.5, 1: 2664.4. Samples: 168655704. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:43,445][86177] Avg episode reward: [(0, '-525.180'), (1, '-548.170')] -[2023-11-28 08:50:45,226][87424] Updated weights for policy 0, policy_version 329569 (0.0009) -[2023-11-28 08:50:45,606][87424] Updated weights for policy 0, policy_version 329579 (0.0010) -[2023-11-28 08:50:45,768][87426] Updated weights for policy 1, policy_version 329220 (0.0008) -[2023-11-28 08:50:45,995][87424] Updated weights for policy 0, policy_version 329589 (0.0012) -[2023-11-28 08:50:46,142][87426] Updated weights for policy 1, policy_version 329230 (0.0011) -[2023-11-28 08:50:46,373][87424] Updated weights for policy 0, policy_version 329599 (0.0010) -[2023-11-28 08:50:46,529][87426] Updated weights for policy 1, policy_version 329240 (0.0008) -[2023-11-28 08:50:48,152][87424] Updated weights for policy 0, policy_version 329609 (0.0011) -[2023-11-28 08:50:48,395][87426] Updated weights for policy 1, policy_version 329250 (0.0007) -[2023-11-28 08:50:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 168665088. Throughput: 0: 2722.8, 1: 2642.3. Samples: 168679272. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:48,445][86177] Avg episode reward: [(0, '-517.630'), (1, '-558.730')] -[2023-11-28 08:50:48,537][87424] Updated weights for policy 0, policy_version 329619 (0.0011) -[2023-11-28 08:50:48,770][87426] Updated weights for policy 1, policy_version 329260 (0.0008) -[2023-11-28 08:50:48,921][87424] Updated weights for policy 0, policy_version 329629 (0.0011) -[2023-11-28 08:50:49,146][87426] Updated weights for policy 1, policy_version 329270 (0.0008) -[2023-11-28 08:50:49,526][87426] Updated weights for policy 1, policy_version 329280 (0.0007) -[2023-11-28 08:50:50,891][87424] Updated weights for policy 0, policy_version 329639 (0.0008) -[2023-11-28 08:50:51,277][87424] Updated weights for policy 0, policy_version 329649 (0.0009) -[2023-11-28 08:50:51,661][87424] Updated weights for policy 0, policy_version 329659 (0.0011) -[2023-11-28 08:50:51,808][87426] Updated weights for policy 1, policy_version 329290 (0.0012) -[2023-11-28 08:50:52,187][87426] Updated weights for policy 1, policy_version 329300 (0.0012) -[2023-11-28 08:50:52,577][87426] Updated weights for policy 1, policy_version 329310 (0.0012) -[2023-11-28 08:50:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168697856. Throughput: 0: 2753.5, 1: 2654.6. Samples: 168713156. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:53,445][86177] Avg episode reward: [(0, '-518.090'), (1, '-566.510')] -[2023-11-28 08:50:53,680][87424] Updated weights for policy 0, policy_version 329669 (0.0010) -[2023-11-28 08:50:54,054][87424] Updated weights for policy 0, policy_version 329679 (0.0012) -[2023-11-28 08:50:54,442][87424] Updated weights for policy 0, policy_version 329689 (0.0012) -[2023-11-28 08:50:54,952][87426] Updated weights for policy 1, policy_version 329320 (0.0009) -[2023-11-28 08:50:55,330][87426] Updated weights for policy 1, policy_version 329330 (0.0009) -[2023-11-28 08:50:55,718][87426] Updated weights for policy 1, policy_version 329340 (0.0007) -[2023-11-28 08:50:56,916][87424] Updated weights for policy 0, policy_version 329699 (0.0010) -[2023-11-28 08:50:57,296][87424] Updated weights for policy 0, policy_version 329709 (0.0007) -[2023-11-28 08:50:57,674][87424] Updated weights for policy 0, policy_version 329719 (0.0008) -[2023-11-28 08:50:58,113][87426] Updated weights for policy 1, policy_version 329350 (0.0008) -[2023-11-28 08:50:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 168722432. Throughput: 0: 2743.6, 1: 2666.5. Samples: 168737168. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:50:58,445][86177] Avg episode reward: [(0, '-517.640'), (1, '-572.640')] -[2023-11-28 08:50:58,495][87426] Updated weights for policy 1, policy_version 329360 (0.0007) -[2023-11-28 08:50:58,881][87426] Updated weights for policy 1, policy_version 329370 (0.0008) -[2023-11-28 08:50:59,998][87424] Updated weights for policy 0, policy_version 329729 (0.0008) -[2023-11-28 08:51:00,384][87424] Updated weights for policy 0, policy_version 329739 (0.0012) -[2023-11-28 08:51:00,756][87424] Updated weights for policy 0, policy_version 329749 (0.0012) -[2023-11-28 08:51:01,139][87424] Updated weights for policy 0, policy_version 329759 (0.0012) -[2023-11-28 08:51:01,461][87426] Updated weights for policy 1, policy_version 329380 (0.0010) -[2023-11-28 08:51:01,839][87426] Updated weights for policy 1, policy_version 329390 (0.0008) -[2023-11-28 08:51:02,222][87426] Updated weights for policy 1, policy_version 329400 (0.0009) -[2023-11-28 08:51:03,427][87424] Updated weights for policy 0, policy_version 329769 (0.0009) -[2023-11-28 08:51:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168747008. Throughput: 0: 2716.0, 1: 2646.3. Samples: 168760016. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:51:03,445][86177] Avg episode reward: [(0, '-523.190'), (1, '-604.230')] -[2023-11-28 08:51:03,806][87424] Updated weights for policy 0, policy_version 329779 (0.0007) -[2023-11-28 08:51:04,191][87424] Updated weights for policy 0, policy_version 329789 (0.0007) -[2023-11-28 08:51:04,603][87426] Updated weights for policy 1, policy_version 329410 (0.0009) -[2023-11-28 08:51:04,983][87426] Updated weights for policy 1, policy_version 329420 (0.0012) -[2023-11-28 08:51:05,362][87426] Updated weights for policy 1, policy_version 329430 (0.0012) -[2023-11-28 08:51:05,731][87426] Updated weights for policy 1, policy_version 329440 (0.0012) -[2023-11-28 08:51:06,080][87424] Updated weights for policy 0, policy_version 329799 (0.0010) -[2023-11-28 08:51:06,469][87424] Updated weights for policy 0, policy_version 329809 (0.0011) -[2023-11-28 08:51:06,854][87424] Updated weights for policy 0, policy_version 329819 (0.0009) -[2023-11-28 08:51:08,218][87426] Updated weights for policy 1, policy_version 329450 (0.0012) -[2023-11-28 08:51:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 168771584. Throughput: 0: 2729.8, 1: 2635.6. Samples: 168791956. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:51:08,446][86177] Avg episode reward: [(0, '-518.040'), (1, '-592.590')] -[2023-11-28 08:51:08,598][87426] Updated weights for policy 1, policy_version 329460 (0.0012) -[2023-11-28 08:51:08,975][87426] Updated weights for policy 1, policy_version 329470 (0.0011) -[2023-11-28 08:51:09,093][87424] Updated weights for policy 0, policy_version 329829 (0.0007) -[2023-11-28 08:51:09,479][87424] Updated weights for policy 0, policy_version 329839 (0.0009) -[2023-11-28 08:51:09,851][87424] Updated weights for policy 0, policy_version 329849 (0.0009) -[2023-11-28 08:51:11,031][87426] Updated weights for policy 1, policy_version 329480 (0.0012) -[2023-11-28 08:51:11,407][87426] Updated weights for policy 1, policy_version 329490 (0.0011) -[2023-11-28 08:51:11,791][87426] Updated weights for policy 1, policy_version 329500 (0.0010) -[2023-11-28 08:51:11,955][87424] Updated weights for policy 0, policy_version 329859 (0.0012) -[2023-11-28 08:51:12,342][87424] Updated weights for policy 0, policy_version 329869 (0.0010) -[2023-11-28 08:51:12,715][87424] Updated weights for policy 0, policy_version 329879 (0.0012) -[2023-11-28 08:51:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 168804352. Throughput: 0: 2746.5, 1: 2615.3. Samples: 168816052. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:51:13,445][86177] Avg episode reward: [(0, '-559.630'), (1, '-582.760')] -[2023-11-28 08:51:13,829][87426] Updated weights for policy 1, policy_version 329510 (0.0010) -[2023-11-28 08:51:14,215][87426] Updated weights for policy 1, policy_version 329520 (0.0007) -[2023-11-28 08:51:14,591][87426] Updated weights for policy 1, policy_version 329530 (0.0007) -[2023-11-28 08:51:14,902][87424] Updated weights for policy 0, policy_version 329889 (0.0012) -[2023-11-28 08:51:15,286][87424] Updated weights for policy 0, policy_version 329899 (0.0011) -[2023-11-28 08:51:15,686][87424] Updated weights for policy 0, policy_version 329909 (0.0011) -[2023-11-28 08:51:16,064][87424] Updated weights for policy 0, policy_version 329919 (0.0009) -[2023-11-28 08:51:16,692][87426] Updated weights for policy 1, policy_version 329540 (0.0009) -[2023-11-28 08:51:17,067][87426] Updated weights for policy 1, policy_version 329550 (0.0012) -[2023-11-28 08:51:17,450][87426] Updated weights for policy 1, policy_version 329560 (0.0011) -[2023-11-28 08:51:18,115][87424] Updated weights for policy 0, policy_version 329929 (0.0012) -[2023-11-28 08:51:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168828928. Throughput: 0: 2737.2, 1: 2630.3. Samples: 168840728. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:51:18,445][86177] Avg episode reward: [(0, '-560.330'), (1, '-560.400')] -[2023-11-28 08:51:18,489][87424] Updated weights for policy 0, policy_version 329939 (0.0012) -[2023-11-28 08:51:18,873][87424] Updated weights for policy 0, policy_version 329949 (0.0012) -[2023-11-28 08:51:19,761][87426] Updated weights for policy 1, policy_version 329570 (0.0012) -[2023-11-28 08:51:20,144][87426] Updated weights for policy 1, policy_version 329580 (0.0012) -[2023-11-28 08:51:20,512][87426] Updated weights for policy 1, policy_version 329590 (0.0012) -[2023-11-28 08:51:20,894][87426] Updated weights for policy 1, policy_version 329600 (0.0012) -[2023-11-28 08:51:21,382][87424] Updated weights for policy 0, policy_version 329959 (0.0011) -[2023-11-28 08:51:21,766][87424] Updated weights for policy 0, policy_version 329969 (0.0012) -[2023-11-28 08:51:22,147][87424] Updated weights for policy 0, policy_version 329979 (0.0008) -[2023-11-28 08:51:22,869][87426] Updated weights for policy 1, policy_version 329610 (0.0012) -[2023-11-28 08:51:23,237][87426] Updated weights for policy 1, policy_version 329620 (0.0011) -[2023-11-28 08:51:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 168853504. Throughput: 0: 2727.7, 1: 2655.2. Samples: 168873736. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:51:23,445][86177] Avg episode reward: [(0, '-555.110'), (1, '-572.540')] -[2023-11-28 08:51:23,610][87426] Updated weights for policy 1, policy_version 329630 (0.0011) -[2023-11-28 08:51:24,382][87424] Updated weights for policy 0, policy_version 329989 (0.0010) -[2023-11-28 08:51:24,756][87424] Updated weights for policy 0, policy_version 329999 (0.0008) -[2023-11-28 08:51:25,133][87424] Updated weights for policy 0, policy_version 330009 (0.0009) -[2023-11-28 08:51:25,328][87426] Updated weights for policy 1, policy_version 329640 (0.0010) -[2023-11-28 08:51:25,704][87426] Updated weights for policy 1, policy_version 329650 (0.0011) -[2023-11-28 08:51:26,074][87426] Updated weights for policy 1, policy_version 329660 (0.0009) -[2023-11-28 08:51:27,336][87424] Updated weights for policy 0, policy_version 330019 (0.0008) -[2023-11-28 08:51:27,722][87424] Updated weights for policy 0, policy_version 330029 (0.0007) -[2023-11-28 08:51:28,103][87424] Updated weights for policy 0, policy_version 330039 (0.0011) -[2023-11-28 08:51:28,216][87426] Updated weights for policy 1, policy_version 329670 (0.0009) -[2023-11-28 08:51:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 168878080. Throughput: 0: 2706.8, 1: 2680.3. Samples: 168898124. Policy #0 lag: (min: 26.0, avg: 54.2, max: 58.0) -[2023-11-28 08:51:28,446][86177] Avg episode reward: [(0, '-556.590'), (1, '-571.330')] -[2023-11-28 08:51:28,598][87426] Updated weights for policy 1, policy_version 329680 (0.0008) -[2023-11-28 08:51:28,979][87426] Updated weights for policy 1, policy_version 329690 (0.0008) -[2023-11-28 08:51:29,849][87424] Updated weights for policy 0, policy_version 330049 (0.0012) -[2023-11-28 08:51:30,231][87424] Updated weights for policy 0, policy_version 330059 (0.0008) -[2023-11-28 08:51:30,613][87424] Updated weights for policy 0, policy_version 330069 (0.0008) -[2023-11-28 08:51:30,996][87424] Updated weights for policy 0, policy_version 330079 (0.0007) -[2023-11-28 08:51:31,445][87426] Updated weights for policy 1, policy_version 329700 (0.0009) -[2023-11-28 08:51:31,809][87426] Updated weights for policy 1, policy_version 329710 (0.0011) -[2023-11-28 08:51:32,192][87426] Updated weights for policy 1, policy_version 329720 (0.0011) -[2023-11-28 08:51:33,365][87424] Updated weights for policy 0, policy_version 330089 (0.0007) -[2023-11-28 08:51:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 168910848. Throughput: 0: 2715.4, 1: 2680.5. Samples: 168922088. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:51:33,445][86177] Avg episode reward: [(0, '-513.660'), (1, '-573.670')] -[2023-11-28 08:51:33,754][87424] Updated weights for policy 0, policy_version 330099 (0.0009) -[2023-11-28 08:51:34,133][87424] Updated weights for policy 0, policy_version 330109 (0.0011) -[2023-11-28 08:51:34,427][87426] Updated weights for policy 1, policy_version 329730 (0.0011) -[2023-11-28 08:51:34,810][87426] Updated weights for policy 1, policy_version 329740 (0.0009) -[2023-11-28 08:51:35,187][87426] Updated weights for policy 1, policy_version 329750 (0.0011) -[2023-11-28 08:51:35,567][87426] Updated weights for policy 1, policy_version 329760 (0.0011) -[2023-11-28 08:51:36,435][87424] Updated weights for policy 0, policy_version 330119 (0.0011) -[2023-11-28 08:51:36,820][87424] Updated weights for policy 0, policy_version 330129 (0.0011) -[2023-11-28 08:51:37,189][87424] Updated weights for policy 0, policy_version 330139 (0.0012) -[2023-11-28 08:51:38,032][87426] Updated weights for policy 1, policy_version 329770 (0.0007) -[2023-11-28 08:51:38,415][87426] Updated weights for policy 1, policy_version 329780 (0.0010) -[2023-11-28 08:51:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 168935424. Throughput: 0: 2709.4, 1: 2682.4. Samples: 168955788. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:51:38,445][86177] Avg episode reward: [(0, '-511.190'), (1, '-556.980')] -[2023-11-28 08:51:38,789][87426] Updated weights for policy 1, policy_version 329790 (0.0012) -[2023-11-28 08:51:38,968][87424] Updated weights for policy 0, policy_version 330149 (0.0012) -[2023-11-28 08:51:39,344][87424] Updated weights for policy 0, policy_version 330159 (0.0012) -[2023-11-28 08:51:39,718][87424] Updated weights for policy 0, policy_version 330169 (0.0012) -[2023-11-28 08:51:41,228][87426] Updated weights for policy 1, policy_version 329800 (0.0011) -[2023-11-28 08:51:41,606][87426] Updated weights for policy 1, policy_version 329810 (0.0012) -[2023-11-28 08:51:41,982][87426] Updated weights for policy 1, policy_version 329820 (0.0012) -[2023-11-28 08:51:42,213][87424] Updated weights for policy 0, policy_version 330179 (0.0012) -[2023-11-28 08:51:42,598][87424] Updated weights for policy 0, policy_version 330189 (0.0011) -[2023-11-28 08:51:42,979][87424] Updated weights for policy 0, policy_version 330199 (0.0011) -[2023-11-28 08:51:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 168968192. Throughput: 0: 2716.4, 1: 2681.8. Samples: 168980084. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:51:43,445][86177] Avg episode reward: [(0, '-516.920'), (1, '-516.240')] -[2023-11-28 08:51:44,170][87426] Updated weights for policy 1, policy_version 329830 (0.0011) -[2023-11-28 08:51:44,553][87426] Updated weights for policy 1, policy_version 329840 (0.0007) -[2023-11-28 08:51:44,930][87426] Updated weights for policy 1, policy_version 329850 (0.0007) -[2023-11-28 08:51:45,210][87424] Updated weights for policy 0, policy_version 330209 (0.0011) -[2023-11-28 08:51:45,594][87424] Updated weights for policy 0, policy_version 330219 (0.0012) -[2023-11-28 08:51:45,974][87424] Updated weights for policy 0, policy_version 330229 (0.0009) -[2023-11-28 08:51:46,362][87424] Updated weights for policy 0, policy_version 330239 (0.0007) -[2023-11-28 08:51:46,851][87426] Updated weights for policy 1, policy_version 329860 (0.0009) -[2023-11-28 08:51:47,228][87426] Updated weights for policy 1, policy_version 329870 (0.0012) -[2023-11-28 08:51:47,611][87426] Updated weights for policy 1, policy_version 329880 (0.0012) -[2023-11-28 08:51:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 168992768. Throughput: 0: 2721.8, 1: 2701.2. Samples: 169004048. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:51:48,446][86177] Avg episode reward: [(0, '-520.040'), (1, '-519.420')] -[2023-11-28 08:51:48,558][87424] Updated weights for policy 0, policy_version 330249 (0.0009) -[2023-11-28 08:51:48,940][87424] Updated weights for policy 0, policy_version 330259 (0.0008) -[2023-11-28 08:51:49,316][87424] Updated weights for policy 0, policy_version 330269 (0.0009) -[2023-11-28 08:51:49,778][87426] Updated weights for policy 1, policy_version 329890 (0.0012) -[2023-11-28 08:51:50,155][87426] Updated weights for policy 1, policy_version 329900 (0.0012) -[2023-11-28 08:51:50,532][87426] Updated weights for policy 1, policy_version 329910 (0.0012) -[2023-11-28 08:51:50,906][87426] Updated weights for policy 1, policy_version 329920 (0.0012) -[2023-11-28 08:51:51,695][87424] Updated weights for policy 0, policy_version 330279 (0.0011) -[2023-11-28 08:51:52,074][87424] Updated weights for policy 0, policy_version 330289 (0.0012) -[2023-11-28 08:51:52,451][87424] Updated weights for policy 0, policy_version 330299 (0.0012) -[2023-11-28 08:51:53,041][87426] Updated weights for policy 1, policy_version 329930 (0.0008) -[2023-11-28 08:51:53,418][87426] Updated weights for policy 1, policy_version 329940 (0.0009) -[2023-11-28 08:51:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 169017344. Throughput: 0: 2697.6, 1: 2721.9. Samples: 169035832. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:51:53,445][86177] Avg episode reward: [(0, '-520.910'), (1, '-529.010')] -[2023-11-28 08:51:53,801][87426] Updated weights for policy 1, policy_version 329950 (0.0009) -[2023-11-28 08:51:54,568][87424] Updated weights for policy 0, policy_version 330309 (0.0010) -[2023-11-28 08:51:54,952][87424] Updated weights for policy 0, policy_version 330319 (0.0007) -[2023-11-28 08:51:55,329][87424] Updated weights for policy 0, policy_version 330329 (0.0011) -[2023-11-28 08:51:56,136][87426] Updated weights for policy 1, policy_version 329960 (0.0010) -[2023-11-28 08:51:56,507][87426] Updated weights for policy 1, policy_version 329970 (0.0010) -[2023-11-28 08:51:56,878][87426] Updated weights for policy 1, policy_version 329980 (0.0010) -[2023-11-28 08:51:57,438][87424] Updated weights for policy 0, policy_version 330339 (0.0011) -[2023-11-28 08:51:57,824][87424] Updated weights for policy 0, policy_version 330349 (0.0010) -[2023-11-28 08:51:58,197][87424] Updated weights for policy 0, policy_version 330359 (0.0010) -[2023-11-28 08:51:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 169041920. Throughput: 0: 2703.6, 1: 2742.8. Samples: 169061136. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:51:58,445][86177] Avg episode reward: [(0, '-524.820'), (1, '-542.000')] -[2023-11-28 08:51:58,929][87426] Updated weights for policy 1, policy_version 329990 (0.0010) -[2023-11-28 08:51:59,298][87426] Updated weights for policy 1, policy_version 330000 (0.0007) -[2023-11-28 08:51:59,677][87426] Updated weights for policy 1, policy_version 330010 (0.0008) -[2023-11-28 08:52:00,590][87424] Updated weights for policy 0, policy_version 330369 (0.0011) -[2023-11-28 08:52:00,970][87424] Updated weights for policy 0, policy_version 330379 (0.0008) -[2023-11-28 08:52:01,352][87424] Updated weights for policy 0, policy_version 330389 (0.0007) -[2023-11-28 08:52:01,448][87426] Updated weights for policy 1, policy_version 330020 (0.0009) -[2023-11-28 08:52:01,735][87424] Updated weights for policy 0, policy_version 330399 (0.0008) -[2023-11-28 08:52:01,830][87426] Updated weights for policy 1, policy_version 330030 (0.0010) -[2023-11-28 08:52:02,206][87426] Updated weights for policy 1, policy_version 330040 (0.0012) -[2023-11-28 08:52:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 169074688. Throughput: 0: 2715.9, 1: 2752.2. Samples: 169086792. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:52:03,445][86177] Avg episode reward: [(0, '-516.540'), (1, '-561.220')] -[2023-11-28 08:52:04,150][87424] Updated weights for policy 0, policy_version 330409 (0.0008) -[2023-11-28 08:52:04,530][87424] Updated weights for policy 0, policy_version 330419 (0.0008) -[2023-11-28 08:52:04,731][87426] Updated weights for policy 1, policy_version 330050 (0.0011) -[2023-11-28 08:52:04,914][87424] Updated weights for policy 0, policy_version 330429 (0.0008) -[2023-11-28 08:52:05,111][87426] Updated weights for policy 1, policy_version 330060 (0.0011) -[2023-11-28 08:52:05,491][87426] Updated weights for policy 1, policy_version 330070 (0.0012) -[2023-11-28 08:52:05,876][87426] Updated weights for policy 1, policy_version 330080 (0.0012) -[2023-11-28 08:52:06,658][87424] Updated weights for policy 0, policy_version 330439 (0.0012) -[2023-11-28 08:52:07,046][87424] Updated weights for policy 0, policy_version 330449 (0.0012) -[2023-11-28 08:52:07,421][87424] Updated weights for policy 0, policy_version 330459 (0.0012) -[2023-11-28 08:52:07,807][87426] Updated weights for policy 1, policy_version 330090 (0.0008) -[2023-11-28 08:52:08,182][87426] Updated weights for policy 1, policy_version 330100 (0.0011) -[2023-11-28 08:52:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 169099264. Throughput: 0: 2722.1, 1: 2743.0. Samples: 169119668. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:52:08,445][86177] Avg episode reward: [(0, '-512.920'), (1, '-557.960')] -[2023-11-28 08:52:08,565][87426] Updated weights for policy 1, policy_version 330110 (0.0012) -[2023-11-28 08:52:10,012][87424] Updated weights for policy 0, policy_version 330469 (0.0012) -[2023-11-28 08:52:10,390][87424] Updated weights for policy 0, policy_version 330479 (0.0012) -[2023-11-28 08:52:10,771][87424] Updated weights for policy 0, policy_version 330489 (0.0010) -[2023-11-28 08:52:10,878][87426] Updated weights for policy 1, policy_version 330120 (0.0011) -[2023-11-28 08:52:11,261][87426] Updated weights for policy 1, policy_version 330130 (0.0011) -[2023-11-28 08:52:11,635][87426] Updated weights for policy 1, policy_version 330140 (0.0012) -[2023-11-28 08:52:12,826][87424] Updated weights for policy 0, policy_version 330499 (0.0011) -[2023-11-28 08:52:13,204][87424] Updated weights for policy 0, policy_version 330509 (0.0011) -[2023-11-28 08:52:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 169123840. Throughput: 0: 2720.3, 1: 2739.2. Samples: 169143800. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:52:13,445][86177] Avg episode reward: [(0, '-513.670'), (1, '-570.050')] -[2023-11-28 08:52:13,597][87424] Updated weights for policy 0, policy_version 330519 (0.0011) -[2023-11-28 08:52:13,915][87426] Updated weights for policy 1, policy_version 330150 (0.0010) -[2023-11-28 08:52:14,294][87426] Updated weights for policy 1, policy_version 330160 (0.0010) -[2023-11-28 08:52:14,674][87426] Updated weights for policy 1, policy_version 330170 (0.0009) -[2023-11-28 08:52:15,585][87424] Updated weights for policy 0, policy_version 330529 (0.0010) -[2023-11-28 08:52:15,969][87424] Updated weights for policy 0, policy_version 330539 (0.0009) -[2023-11-28 08:52:16,355][87424] Updated weights for policy 0, policy_version 330549 (0.0011) -[2023-11-28 08:52:16,662][87426] Updated weights for policy 1, policy_version 330180 (0.0008) -[2023-11-28 08:52:16,745][87424] Updated weights for policy 0, policy_version 330559 (0.0007) -[2023-11-28 08:52:17,040][87426] Updated weights for policy 1, policy_version 330190 (0.0008) -[2023-11-28 08:52:17,418][87426] Updated weights for policy 1, policy_version 330200 (0.0012) -[2023-11-28 08:52:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 169156608. Throughput: 0: 2728.4, 1: 2764.7. Samples: 169169276. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:52:18,445][86177] Avg episode reward: [(0, '-512.650'), (1, '-556.690')] -[2023-11-28 08:52:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000330208_84533248.pth... -[2023-11-28 08:52:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000327680_83886080.pth -[2023-11-28 08:52:18,496][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000330208_84533248.pth -[2023-11-28 08:52:18,816][87424] Updated weights for policy 0, policy_version 330569 (0.0011) -[2023-11-28 08:52:19,199][87424] Updated weights for policy 0, policy_version 330579 (0.0012) -[2023-11-28 08:52:19,283][87426] Updated weights for policy 1, policy_version 330210 (0.0011) -[2023-11-28 08:52:19,576][87424] Updated weights for policy 0, policy_version 330589 (0.0012) -[2023-11-28 08:52:19,664][87426] Updated weights for policy 1, policy_version 330220 (0.0009) -[2023-11-28 08:52:19,690][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000330592_84631552.pth... -[2023-11-28 08:52:19,737][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000328032_83976192.pth -[2023-11-28 08:52:19,744][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000330592_84631552.pth -[2023-11-28 08:52:20,044][87426] Updated weights for policy 1, policy_version 330230 (0.0010) -[2023-11-28 08:52:20,423][87426] Updated weights for policy 1, policy_version 330240 (0.0012) -[2023-11-28 08:52:21,782][87424] Updated weights for policy 0, policy_version 330599 (0.0012) -[2023-11-28 08:52:22,162][87424] Updated weights for policy 0, policy_version 330609 (0.0010) -[2023-11-28 08:52:22,552][87424] Updated weights for policy 0, policy_version 330619 (0.0010) -[2023-11-28 08:52:22,553][87426] Updated weights for policy 1, policy_version 330250 (0.0011) -[2023-11-28 08:52:22,934][87426] Updated weights for policy 1, policy_version 330260 (0.0010) -[2023-11-28 08:52:23,315][87426] Updated weights for policy 1, policy_version 330270 (0.0008) -[2023-11-28 08:52:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 169189376. Throughput: 0: 2689.4, 1: 2757.6. Samples: 169200904. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:52:23,445][86177] Avg episode reward: [(0, '-513.280'), (1, '-537.210')] -[2023-11-28 08:52:24,622][87424] Updated weights for policy 0, policy_version 330629 (0.0009) -[2023-11-28 08:52:24,999][87424] Updated weights for policy 0, policy_version 330639 (0.0009) -[2023-11-28 08:52:25,383][87424] Updated weights for policy 0, policy_version 330649 (0.0011) -[2023-11-28 08:52:25,751][87426] Updated weights for policy 1, policy_version 330280 (0.0009) -[2023-11-28 08:52:26,135][87426] Updated weights for policy 1, policy_version 330290 (0.0007) -[2023-11-28 08:52:26,524][87426] Updated weights for policy 1, policy_version 330300 (0.0007) -[2023-11-28 08:52:27,783][87424] Updated weights for policy 0, policy_version 330659 (0.0010) -[2023-11-28 08:52:28,175][87424] Updated weights for policy 0, policy_version 330669 (0.0012) -[2023-11-28 08:52:28,291][87426] Updated weights for policy 1, policy_version 330310 (0.0007) -[2023-11-28 08:52:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 169205760. Throughput: 0: 2694.3, 1: 2773.6. Samples: 169226140. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:52:28,445][86177] Avg episode reward: [(0, '-514.700'), (1, '-565.310')] -[2023-11-28 08:52:28,548][87424] Updated weights for policy 0, policy_version 330679 (0.0012) -[2023-11-28 08:52:28,660][87426] Updated weights for policy 1, policy_version 330320 (0.0007) -[2023-11-28 08:52:29,040][87426] Updated weights for policy 1, policy_version 330330 (0.0008) -[2023-11-28 08:52:30,342][87424] Updated weights for policy 0, policy_version 330689 (0.0011) -[2023-11-28 08:52:30,720][87424] Updated weights for policy 0, policy_version 330699 (0.0010) -[2023-11-28 08:52:30,987][87426] Updated weights for policy 1, policy_version 330340 (0.0008) -[2023-11-28 08:52:31,107][87424] Updated weights for policy 0, policy_version 330709 (0.0010) -[2023-11-28 08:52:31,374][87426] Updated weights for policy 1, policy_version 330350 (0.0007) -[2023-11-28 08:52:31,485][87424] Updated weights for policy 0, policy_version 330719 (0.0012) -[2023-11-28 08:52:31,759][87426] Updated weights for policy 1, policy_version 330360 (0.0008) -[2023-11-28 08:52:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 169238528. Throughput: 0: 2712.4, 1: 2761.7. Samples: 169250380. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:52:33,445][86177] Avg episode reward: [(0, '-516.500'), (1, '-523.510')] -[2023-11-28 08:52:33,478][87426] Updated weights for policy 1, policy_version 330370 (0.0011) -[2023-11-28 08:52:33,513][87424] Updated weights for policy 0, policy_version 330729 (0.0011) -[2023-11-28 08:52:33,854][87426] Updated weights for policy 1, policy_version 330380 (0.0010) -[2023-11-28 08:52:33,893][87424] Updated weights for policy 0, policy_version 330739 (0.0008) -[2023-11-28 08:52:34,227][87426] Updated weights for policy 1, policy_version 330390 (0.0010) -[2023-11-28 08:52:34,285][87424] Updated weights for policy 0, policy_version 330749 (0.0011) -[2023-11-28 08:52:34,604][87426] Updated weights for policy 1, policy_version 330400 (0.0012) -[2023-11-28 08:52:36,573][87424] Updated weights for policy 0, policy_version 330759 (0.0011) -[2023-11-28 08:52:36,941][87424] Updated weights for policy 0, policy_version 330769 (0.0008) -[2023-11-28 08:52:37,074][87426] Updated weights for policy 1, policy_version 330410 (0.0011) -[2023-11-28 08:52:37,329][87424] Updated weights for policy 0, policy_version 330779 (0.0011) -[2023-11-28 08:52:37,448][87426] Updated weights for policy 1, policy_version 330420 (0.0011) -[2023-11-28 08:52:37,827][87426] Updated weights for policy 1, policy_version 330430 (0.0012) -[2023-11-28 08:52:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 169271296. Throughput: 0: 2734.2, 1: 2778.9. Samples: 169283924. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:52:38,445][86177] Avg episode reward: [(0, '-520.160'), (1, '-525.380')] -[2023-11-28 08:52:39,406][87424] Updated weights for policy 0, policy_version 330789 (0.0012) -[2023-11-28 08:52:39,802][87424] Updated weights for policy 0, policy_version 330799 (0.0011) -[2023-11-28 08:52:39,865][87426] Updated weights for policy 1, policy_version 330440 (0.0012) -[2023-11-28 08:52:40,175][87424] Updated weights for policy 0, policy_version 330809 (0.0011) -[2023-11-28 08:52:40,238][87426] Updated weights for policy 1, policy_version 330450 (0.0012) -[2023-11-28 08:52:40,617][87426] Updated weights for policy 1, policy_version 330460 (0.0012) -[2023-11-28 08:52:42,404][87424] Updated weights for policy 0, policy_version 330819 (0.0011) -[2023-11-28 08:52:42,612][87426] Updated weights for policy 1, policy_version 330470 (0.0011) -[2023-11-28 08:52:42,783][87424] Updated weights for policy 0, policy_version 330829 (0.0012) -[2023-11-28 08:52:42,992][87426] Updated weights for policy 1, policy_version 330480 (0.0012) -[2023-11-28 08:52:43,164][87424] Updated weights for policy 0, policy_version 330839 (0.0012) -[2023-11-28 08:52:43,365][87426] Updated weights for policy 1, policy_version 330490 (0.0011) -[2023-11-28 08:52:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 169287680. Throughput: 0: 2731.2, 1: 2775.8. Samples: 169308952. Policy #0 lag: (min: 31.0, avg: 37.9, max: 63.0) -[2023-11-28 08:52:43,445][86177] Avg episode reward: [(0, '-518.670'), (1, '-536.100')] -[2023-11-28 08:52:45,309][87426] Updated weights for policy 1, policy_version 330500 (0.0011) -[2023-11-28 08:52:45,565][87424] Updated weights for policy 0, policy_version 330849 (0.0012) -[2023-11-28 08:52:45,690][87426] Updated weights for policy 1, policy_version 330510 (0.0008) -[2023-11-28 08:52:45,937][87424] Updated weights for policy 0, policy_version 330859 (0.0010) -[2023-11-28 08:52:46,065][87426] Updated weights for policy 1, policy_version 330520 (0.0008) -[2023-11-28 08:52:46,314][87424] Updated weights for policy 0, policy_version 330869 (0.0009) -[2023-11-28 08:52:46,696][87424] Updated weights for policy 0, policy_version 330879 (0.0007) -[2023-11-28 08:52:48,141][87426] Updated weights for policy 1, policy_version 330530 (0.0008) -[2023-11-28 08:52:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 169320448. Throughput: 0: 2721.4, 1: 2781.9. Samples: 169334440. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:52:48,445][86177] Avg episode reward: [(0, '-522.690'), (1, '-511.990')] -[2023-11-28 08:52:48,513][87426] Updated weights for policy 1, policy_version 330540 (0.0007) -[2023-11-28 08:52:48,576][87424] Updated weights for policy 0, policy_version 330889 (0.0009) -[2023-11-28 08:52:48,891][87426] Updated weights for policy 1, policy_version 330550 (0.0010) -[2023-11-28 08:52:48,965][87424] Updated weights for policy 0, policy_version 330899 (0.0009) -[2023-11-28 08:52:49,270][87426] Updated weights for policy 1, policy_version 330560 (0.0010) -[2023-11-28 08:52:49,341][87424] Updated weights for policy 0, policy_version 330909 (0.0010) -[2023-11-28 08:52:51,223][87426] Updated weights for policy 1, policy_version 330570 (0.0012) -[2023-11-28 08:52:51,518][87424] Updated weights for policy 0, policy_version 330919 (0.0011) -[2023-11-28 08:52:51,594][87426] Updated weights for policy 1, policy_version 330580 (0.0011) -[2023-11-28 08:52:51,898][87424] Updated weights for policy 0, policy_version 330929 (0.0011) -[2023-11-28 08:52:51,974][87426] Updated weights for policy 1, policy_version 330590 (0.0012) -[2023-11-28 08:52:52,283][87424] Updated weights for policy 0, policy_version 330939 (0.0011) -[2023-11-28 08:52:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 169353216. Throughput: 0: 2729.6, 1: 2785.7. Samples: 169367856. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:52:53,445][86177] Avg episode reward: [(0, '-514.850'), (1, '-512.770')] -[2023-11-28 08:52:54,160][87426] Updated weights for policy 1, policy_version 330600 (0.0009) -[2023-11-28 08:52:54,540][87426] Updated weights for policy 1, policy_version 330610 (0.0008) -[2023-11-28 08:52:54,622][87424] Updated weights for policy 0, policy_version 330949 (0.0007) -[2023-11-28 08:52:54,923][87426] Updated weights for policy 1, policy_version 330620 (0.0007) -[2023-11-28 08:52:55,007][87424] Updated weights for policy 0, policy_version 330959 (0.0008) -[2023-11-28 08:52:55,387][87424] Updated weights for policy 0, policy_version 330969 (0.0011) -[2023-11-28 08:52:56,935][87426] Updated weights for policy 1, policy_version 330630 (0.0010) -[2023-11-28 08:52:57,316][87426] Updated weights for policy 1, policy_version 330640 (0.0012) -[2023-11-28 08:52:57,480][87424] Updated weights for policy 0, policy_version 330979 (0.0010) -[2023-11-28 08:52:57,700][87426] Updated weights for policy 1, policy_version 330650 (0.0011) -[2023-11-28 08:52:57,865][87424] Updated weights for policy 0, policy_version 330989 (0.0009) -[2023-11-28 08:52:58,235][87424] Updated weights for policy 0, policy_version 330999 (0.0012) -[2023-11-28 08:52:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 169377792. Throughput: 0: 2731.9, 1: 2802.8. Samples: 169392860. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:52:58,445][86177] Avg episode reward: [(0, '-517.230'), (1, '-503.960')] -[2023-11-28 08:52:59,414][87426] Updated weights for policy 1, policy_version 330660 (0.0010) -[2023-11-28 08:52:59,796][87426] Updated weights for policy 1, policy_version 330670 (0.0008) -[2023-11-28 08:52:59,948][87424] Updated weights for policy 0, policy_version 331009 (0.0012) -[2023-11-28 08:53:00,167][87426] Updated weights for policy 1, policy_version 330680 (0.0008) -[2023-11-28 08:53:00,323][87424] Updated weights for policy 0, policy_version 331019 (0.0011) -[2023-11-28 08:53:00,714][87424] Updated weights for policy 0, policy_version 331029 (0.0011) -[2023-11-28 08:53:01,095][87424] Updated weights for policy 0, policy_version 331039 (0.0012) -[2023-11-28 08:53:01,886][87426] Updated weights for policy 1, policy_version 330690 (0.0011) -[2023-11-28 08:53:02,261][87426] Updated weights for policy 1, policy_version 330700 (0.0011) -[2023-11-28 08:53:02,642][87426] Updated weights for policy 1, policy_version 330710 (0.0012) -[2023-11-28 08:53:03,016][87426] Updated weights for policy 1, policy_version 330720 (0.0011) -[2023-11-28 08:53:03,285][87424] Updated weights for policy 0, policy_version 331049 (0.0008) -[2023-11-28 08:53:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 169410560. Throughput: 0: 2726.4, 1: 2822.3. Samples: 169418968. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:03,446][86177] Avg episode reward: [(0, '-521.860'), (1, '-509.940')] -[2023-11-28 08:53:03,665][87424] Updated weights for policy 0, policy_version 331059 (0.0007) -[2023-11-28 08:53:04,043][87424] Updated weights for policy 0, policy_version 331069 (0.0007) -[2023-11-28 08:53:05,399][87426] Updated weights for policy 1, policy_version 330730 (0.0007) -[2023-11-28 08:53:05,782][87426] Updated weights for policy 1, policy_version 330740 (0.0007) -[2023-11-28 08:53:06,161][87426] Updated weights for policy 1, policy_version 330750 (0.0007) -[2023-11-28 08:53:06,570][87424] Updated weights for policy 0, policy_version 331079 (0.0009) -[2023-11-28 08:53:06,939][87424] Updated weights for policy 0, policy_version 331089 (0.0011) -[2023-11-28 08:53:07,318][87424] Updated weights for policy 0, policy_version 331099 (0.0009) -[2023-11-28 08:53:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 169435136. Throughput: 0: 2718.7, 1: 2821.0. Samples: 169450188. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:08,445][86177] Avg episode reward: [(0, '-522.660'), (1, '-508.950')] -[2023-11-28 08:53:08,700][87426] Updated weights for policy 1, policy_version 330760 (0.0009) -[2023-11-28 08:53:09,093][87426] Updated weights for policy 1, policy_version 330770 (0.0012) -[2023-11-28 08:53:09,476][87426] Updated weights for policy 1, policy_version 330780 (0.0012) -[2023-11-28 08:53:09,927][87424] Updated weights for policy 0, policy_version 331109 (0.0010) -[2023-11-28 08:53:10,300][87424] Updated weights for policy 0, policy_version 331119 (0.0010) -[2023-11-28 08:53:10,680][87424] Updated weights for policy 0, policy_version 331129 (0.0012) -[2023-11-28 08:53:11,830][87426] Updated weights for policy 1, policy_version 330790 (0.0012) -[2023-11-28 08:53:12,203][87426] Updated weights for policy 1, policy_version 330800 (0.0012) -[2023-11-28 08:53:12,589][87426] Updated weights for policy 1, policy_version 330810 (0.0010) -[2023-11-28 08:53:13,221][87424] Updated weights for policy 0, policy_version 331139 (0.0011) -[2023-11-28 08:53:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 169459712. Throughput: 0: 2704.2, 1: 2800.0. Samples: 169473828. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:13,445][86177] Avg episode reward: [(0, '-525.290'), (1, '-509.120')] -[2023-11-28 08:53:13,602][87424] Updated weights for policy 0, policy_version 331149 (0.0012) -[2023-11-28 08:53:13,987][87424] Updated weights for policy 0, policy_version 331159 (0.0012) -[2023-11-28 08:53:14,414][87426] Updated weights for policy 1, policy_version 330820 (0.0012) -[2023-11-28 08:53:14,797][87426] Updated weights for policy 1, policy_version 330830 (0.0012) -[2023-11-28 08:53:15,162][87426] Updated weights for policy 1, policy_version 330840 (0.0012) -[2023-11-28 08:53:16,040][87424] Updated weights for policy 0, policy_version 331169 (0.0011) -[2023-11-28 08:53:16,423][87424] Updated weights for policy 0, policy_version 331179 (0.0012) -[2023-11-28 08:53:16,801][87424] Updated weights for policy 0, policy_version 331189 (0.0012) -[2023-11-28 08:53:17,185][87424] Updated weights for policy 0, policy_version 331199 (0.0011) -[2023-11-28 08:53:17,546][87426] Updated weights for policy 1, policy_version 330850 (0.0011) -[2023-11-28 08:53:17,932][87426] Updated weights for policy 1, policy_version 330860 (0.0008) -[2023-11-28 08:53:18,308][87426] Updated weights for policy 1, policy_version 330870 (0.0011) -[2023-11-28 08:53:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 169484288. Throughput: 0: 2693.2, 1: 2821.1. Samples: 169498528. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:18,446][86177] Avg episode reward: [(0, '-523.430'), (1, '-498.860')] -[2023-11-28 08:53:18,672][87426] Updated weights for policy 1, policy_version 330880 (0.0012) -[2023-11-28 08:53:19,363][87424] Updated weights for policy 0, policy_version 331209 (0.0010) -[2023-11-28 08:53:19,745][87424] Updated weights for policy 0, policy_version 331219 (0.0008) -[2023-11-28 08:53:20,121][87424] Updated weights for policy 0, policy_version 331229 (0.0012) -[2023-11-28 08:53:21,090][87426] Updated weights for policy 1, policy_version 330890 (0.0012) -[2023-11-28 08:53:21,470][87426] Updated weights for policy 1, policy_version 330900 (0.0012) -[2023-11-28 08:53:21,858][87426] Updated weights for policy 1, policy_version 330910 (0.0012) -[2023-11-28 08:53:22,458][87424] Updated weights for policy 0, policy_version 331239 (0.0010) -[2023-11-28 08:53:22,831][87424] Updated weights for policy 0, policy_version 331249 (0.0008) -[2023-11-28 08:53:23,212][87424] Updated weights for policy 0, policy_version 331259 (0.0012) -[2023-11-28 08:53:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 169517056. Throughput: 0: 2682.2, 1: 2806.0. Samples: 169530896. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:23,445][86177] Avg episode reward: [(0, '-520.040'), (1, '-499.040')] -[2023-11-28 08:53:24,051][87426] Updated weights for policy 1, policy_version 330920 (0.0012) -[2023-11-28 08:53:24,429][87426] Updated weights for policy 1, policy_version 330930 (0.0012) -[2023-11-28 08:53:24,812][87426] Updated weights for policy 1, policy_version 330940 (0.0012) -[2023-11-28 08:53:25,358][87424] Updated weights for policy 0, policy_version 331269 (0.0011) -[2023-11-28 08:53:25,735][87424] Updated weights for policy 0, policy_version 331279 (0.0012) -[2023-11-28 08:53:26,118][87424] Updated weights for policy 0, policy_version 331289 (0.0011) -[2023-11-28 08:53:26,667][87426] Updated weights for policy 1, policy_version 330950 (0.0012) -[2023-11-28 08:53:27,035][87426] Updated weights for policy 1, policy_version 330960 (0.0012) -[2023-11-28 08:53:27,404][87426] Updated weights for policy 1, policy_version 330970 (0.0012) -[2023-11-28 08:53:28,168][87424] Updated weights for policy 0, policy_version 331299 (0.0012) -[2023-11-28 08:53:28,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.8, 300 sec: 5470.6). Total num frames: 169541632. Throughput: 0: 2686.6, 1: 2798.2. Samples: 169555768. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:28,446][86177] Avg episode reward: [(0, '-519.240'), (1, '-520.370')] -[2023-11-28 08:53:28,556][87424] Updated weights for policy 0, policy_version 331309 (0.0011) -[2023-11-28 08:53:28,939][87424] Updated weights for policy 0, policy_version 331319 (0.0010) -[2023-11-28 08:53:29,557][87426] Updated weights for policy 1, policy_version 330980 (0.0012) -[2023-11-28 08:53:29,933][87426] Updated weights for policy 1, policy_version 330990 (0.0011) -[2023-11-28 08:53:30,318][87426] Updated weights for policy 1, policy_version 331000 (0.0008) -[2023-11-28 08:53:30,851][87424] Updated weights for policy 0, policy_version 331329 (0.0012) -[2023-11-28 08:53:31,231][87424] Updated weights for policy 0, policy_version 331339 (0.0011) -[2023-11-28 08:53:31,609][87424] Updated weights for policy 0, policy_version 331349 (0.0011) -[2023-11-28 08:53:31,989][87424] Updated weights for policy 0, policy_version 331359 (0.0012) -[2023-11-28 08:53:32,107][87426] Updated weights for policy 1, policy_version 331010 (0.0012) -[2023-11-28 08:53:32,487][87426] Updated weights for policy 1, policy_version 331020 (0.0010) -[2023-11-28 08:53:32,870][87426] Updated weights for policy 1, policy_version 331030 (0.0011) -[2023-11-28 08:53:33,243][87426] Updated weights for policy 1, policy_version 331040 (0.0011) -[2023-11-28 08:53:33,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5470.6). Total num frames: 169574400. Throughput: 0: 2691.4, 1: 2774.3. Samples: 169580396. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:33,446][86177] Avg episode reward: [(0, '-538.090'), (1, '-515.230')] -[2023-11-28 08:53:33,974][87424] Updated weights for policy 0, policy_version 331369 (0.0008) -[2023-11-28 08:53:34,364][87424] Updated weights for policy 0, policy_version 331379 (0.0007) -[2023-11-28 08:53:34,749][87424] Updated weights for policy 0, policy_version 331389 (0.0008) -[2023-11-28 08:53:35,597][87426] Updated weights for policy 1, policy_version 331050 (0.0012) -[2023-11-28 08:53:35,970][87426] Updated weights for policy 1, policy_version 331060 (0.0012) -[2023-11-28 08:53:36,342][87426] Updated weights for policy 1, policy_version 331070 (0.0012) -[2023-11-28 08:53:36,521][87424] Updated weights for policy 0, policy_version 331399 (0.0010) -[2023-11-28 08:53:36,903][87424] Updated weights for policy 0, policy_version 331409 (0.0011) -[2023-11-28 08:53:37,287][87424] Updated weights for policy 0, policy_version 331419 (0.0012) -[2023-11-28 08:53:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 169598976. Throughput: 0: 2722.9, 1: 2748.6. Samples: 169614076. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:38,445][86177] Avg episode reward: [(0, '-538.240'), (1, '-520.010')] -[2023-11-28 08:53:38,739][87426] Updated weights for policy 1, policy_version 331080 (0.0008) -[2023-11-28 08:53:39,118][87426] Updated weights for policy 1, policy_version 331090 (0.0009) -[2023-11-28 08:53:39,504][87426] Updated weights for policy 1, policy_version 331100 (0.0010) -[2023-11-28 08:53:39,722][87424] Updated weights for policy 0, policy_version 331429 (0.0009) -[2023-11-28 08:53:40,109][87424] Updated weights for policy 0, policy_version 331439 (0.0009) -[2023-11-28 08:53:40,494][87424] Updated weights for policy 0, policy_version 331449 (0.0009) -[2023-11-28 08:53:42,068][87426] Updated weights for policy 1, policy_version 331110 (0.0010) -[2023-11-28 08:53:42,450][87426] Updated weights for policy 1, policy_version 331120 (0.0012) -[2023-11-28 08:53:42,813][87424] Updated weights for policy 0, policy_version 331459 (0.0012) -[2023-11-28 08:53:42,815][87426] Updated weights for policy 1, policy_version 331130 (0.0010) -[2023-11-28 08:53:43,200][87424] Updated weights for policy 0, policy_version 331469 (0.0011) -[2023-11-28 08:53:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 169623552. Throughput: 0: 2719.4, 1: 2716.4. Samples: 169637472. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:43,445][86177] Avg episode reward: [(0, '-540.300'), (1, '-527.010')] -[2023-11-28 08:53:43,580][87424] Updated weights for policy 0, policy_version 331479 (0.0011) -[2023-11-28 08:53:45,268][87426] Updated weights for policy 1, policy_version 331140 (0.0010) -[2023-11-28 08:53:45,652][87426] Updated weights for policy 1, policy_version 331150 (0.0012) -[2023-11-28 08:53:45,937][87424] Updated weights for policy 0, policy_version 331489 (0.0009) -[2023-11-28 08:53:46,034][87426] Updated weights for policy 1, policy_version 331160 (0.0012) -[2023-11-28 08:53:46,327][87424] Updated weights for policy 0, policy_version 331499 (0.0011) -[2023-11-28 08:53:46,713][87424] Updated weights for policy 0, policy_version 331509 (0.0011) -[2023-11-28 08:53:47,095][87424] Updated weights for policy 0, policy_version 331519 (0.0012) -[2023-11-28 08:53:48,380][87426] Updated weights for policy 1, policy_version 331170 (0.0011) -[2023-11-28 08:53:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 169648128. Throughput: 0: 2723.4, 1: 2682.1. Samples: 169662212. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:48,445][86177] Avg episode reward: [(0, '-539.170'), (1, '-506.740')] -[2023-11-28 08:53:48,596][87424] Updated weights for policy 0, policy_version 331529 (0.0012) -[2023-11-28 08:53:48,772][87426] Updated weights for policy 1, policy_version 331180 (0.0011) -[2023-11-28 08:53:48,978][87424] Updated weights for policy 0, policy_version 331539 (0.0012) -[2023-11-28 08:53:49,141][87426] Updated weights for policy 1, policy_version 331190 (0.0011) -[2023-11-28 08:53:49,371][87424] Updated weights for policy 0, policy_version 331549 (0.0011) -[2023-11-28 08:53:49,520][87426] Updated weights for policy 1, policy_version 331200 (0.0011) -[2023-11-28 08:53:51,199][87424] Updated weights for policy 0, policy_version 331559 (0.0012) -[2023-11-28 08:53:51,586][87424] Updated weights for policy 0, policy_version 331569 (0.0012) -[2023-11-28 08:53:51,868][87426] Updated weights for policy 1, policy_version 331210 (0.0012) -[2023-11-28 08:53:51,953][87424] Updated weights for policy 0, policy_version 331579 (0.0011) -[2023-11-28 08:53:52,242][87426] Updated weights for policy 1, policy_version 331220 (0.0010) -[2023-11-28 08:53:52,620][87426] Updated weights for policy 1, policy_version 331230 (0.0008) -[2023-11-28 08:53:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 169680896. Throughput: 0: 2756.7, 1: 2675.4. Samples: 169694632. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:53,445][86177] Avg episode reward: [(0, '-518.980'), (1, '-505.500')] -[2023-11-28 08:53:54,145][87424] Updated weights for policy 0, policy_version 331589 (0.0010) -[2023-11-28 08:53:54,522][87424] Updated weights for policy 0, policy_version 331599 (0.0008) -[2023-11-28 08:53:54,719][87426] Updated weights for policy 1, policy_version 331240 (0.0010) -[2023-11-28 08:53:54,901][87424] Updated weights for policy 0, policy_version 331609 (0.0008) -[2023-11-28 08:53:55,097][87426] Updated weights for policy 1, policy_version 331250 (0.0011) -[2023-11-28 08:53:55,472][87426] Updated weights for policy 1, policy_version 331260 (0.0012) -[2023-11-28 08:53:57,080][87424] Updated weights for policy 0, policy_version 331619 (0.0009) -[2023-11-28 08:53:57,386][87426] Updated weights for policy 1, policy_version 331270 (0.0009) -[2023-11-28 08:53:57,464][87424] Updated weights for policy 0, policy_version 331629 (0.0011) -[2023-11-28 08:53:57,765][87426] Updated weights for policy 1, policy_version 331280 (0.0008) -[2023-11-28 08:53:57,850][87424] Updated weights for policy 0, policy_version 331639 (0.0011) -[2023-11-28 08:53:58,151][87426] Updated weights for policy 1, policy_version 331290 (0.0010) -[2023-11-28 08:53:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 169713664. Throughput: 0: 2759.8, 1: 2698.0. Samples: 169719432. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:53:58,445][86177] Avg episode reward: [(0, '-527.110'), (1, '-508.560')] -[2023-11-28 08:53:59,803][87424] Updated weights for policy 0, policy_version 331649 (0.0011) -[2023-11-28 08:54:00,175][87424] Updated weights for policy 0, policy_version 331659 (0.0012) -[2023-11-28 08:54:00,405][87426] Updated weights for policy 1, policy_version 331300 (0.0007) -[2023-11-28 08:54:00,558][87424] Updated weights for policy 0, policy_version 331669 (0.0011) -[2023-11-28 08:54:00,792][87426] Updated weights for policy 1, policy_version 331310 (0.0009) -[2023-11-28 08:54:00,935][87424] Updated weights for policy 0, policy_version 331679 (0.0011) -[2023-11-28 08:54:01,173][87426] Updated weights for policy 1, policy_version 331320 (0.0012) -[2023-11-28 08:54:03,128][87424] Updated weights for policy 0, policy_version 331689 (0.0012) -[2023-11-28 08:54:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 169730048. Throughput: 0: 2792.4, 1: 2694.6. Samples: 169745440. Policy #0 lag: (min: 31.0, avg: 38.4, max: 63.0) -[2023-11-28 08:54:03,445][86177] Avg episode reward: [(0, '-527.860'), (1, '-507.760')] -[2023-11-28 08:54:03,510][87424] Updated weights for policy 0, policy_version 331699 (0.0012) -[2023-11-28 08:54:03,513][87426] Updated weights for policy 1, policy_version 331330 (0.0012) -[2023-11-28 08:54:03,897][87426] Updated weights for policy 1, policy_version 331340 (0.0007) -[2023-11-28 08:54:03,900][87424] Updated weights for policy 0, policy_version 331709 (0.0011) -[2023-11-28 08:54:04,293][87426] Updated weights for policy 1, policy_version 331350 (0.0007) -[2023-11-28 08:54:04,661][87426] Updated weights for policy 1, policy_version 331360 (0.0009) -[2023-11-28 08:54:06,205][87424] Updated weights for policy 0, policy_version 331719 (0.0010) -[2023-11-28 08:54:06,452][87426] Updated weights for policy 1, policy_version 331370 (0.0009) -[2023-11-28 08:54:06,593][87424] Updated weights for policy 0, policy_version 331729 (0.0007) -[2023-11-28 08:54:06,824][87426] Updated weights for policy 1, policy_version 331380 (0.0009) -[2023-11-28 08:54:06,968][87424] Updated weights for policy 0, policy_version 331739 (0.0009) -[2023-11-28 08:54:07,211][87426] Updated weights for policy 1, policy_version 331390 (0.0010) -[2023-11-28 08:54:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 169762816. Throughput: 0: 2789.4, 1: 2702.2. Samples: 169778020. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:08,445][86177] Avg episode reward: [(0, '-535.640'), (1, '-512.150')] -[2023-11-28 08:54:08,969][87424] Updated weights for policy 0, policy_version 331749 (0.0011) -[2023-11-28 08:54:09,350][87424] Updated weights for policy 0, policy_version 331759 (0.0011) -[2023-11-28 08:54:09,534][87426] Updated weights for policy 1, policy_version 331400 (0.0007) -[2023-11-28 08:54:09,730][87424] Updated weights for policy 0, policy_version 331769 (0.0010) -[2023-11-28 08:54:09,920][87426] Updated weights for policy 1, policy_version 331410 (0.0008) -[2023-11-28 08:54:10,293][87426] Updated weights for policy 1, policy_version 331420 (0.0012) -[2023-11-28 08:54:12,069][87424] Updated weights for policy 0, policy_version 331779 (0.0010) -[2023-11-28 08:54:12,383][87426] Updated weights for policy 1, policy_version 331430 (0.0011) -[2023-11-28 08:54:12,463][87424] Updated weights for policy 0, policy_version 331789 (0.0018) -[2023-11-28 08:54:12,759][87426] Updated weights for policy 1, policy_version 331440 (0.0009) -[2023-11-28 08:54:12,835][87424] Updated weights for policy 0, policy_version 331799 (0.0011) -[2023-11-28 08:54:13,144][87426] Updated weights for policy 1, policy_version 331450 (0.0011) -[2023-11-28 08:54:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 169795584. Throughput: 0: 2789.1, 1: 2688.4. Samples: 169802252. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:13,445][86177] Avg episode reward: [(0, '-535.870'), (1, '-516.160')] -[2023-11-28 08:54:15,117][87426] Updated weights for policy 1, policy_version 331460 (0.0012) -[2023-11-28 08:54:15,443][87424] Updated weights for policy 0, policy_version 331809 (0.0012) -[2023-11-28 08:54:15,488][87426] Updated weights for policy 1, policy_version 331470 (0.0012) -[2023-11-28 08:54:15,817][87424] Updated weights for policy 0, policy_version 331819 (0.0011) -[2023-11-28 08:54:15,867][87426] Updated weights for policy 1, policy_version 331480 (0.0011) -[2023-11-28 08:54:16,199][87424] Updated weights for policy 0, policy_version 331829 (0.0010) -[2023-11-28 08:54:16,583][87424] Updated weights for policy 0, policy_version 331839 (0.0007) -[2023-11-28 08:54:17,956][87426] Updated weights for policy 1, policy_version 331490 (0.0011) -[2023-11-28 08:54:18,330][87426] Updated weights for policy 1, policy_version 331500 (0.0012) -[2023-11-28 08:54:18,431][87424] Updated weights for policy 0, policy_version 331849 (0.0011) -[2023-11-28 08:54:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 169811968. Throughput: 0: 2771.0, 1: 2710.1. Samples: 169827044. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:18,445][86177] Avg episode reward: [(0, '-545.540'), (1, '-507.960')] -[2023-11-28 08:54:18,707][87426] Updated weights for policy 1, policy_version 331510 (0.0012) -[2023-11-28 08:54:18,817][87424] Updated weights for policy 0, policy_version 331859 (0.0007) -[2023-11-28 08:54:19,079][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000331520_84869120.pth... -[2023-11-28 08:54:19,081][87426] Updated weights for policy 1, policy_version 331520 (0.0012) -[2023-11-28 08:54:19,126][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000328960_84213760.pth -[2023-11-28 08:54:19,203][87424] Updated weights for policy 0, policy_version 331869 (0.0009) -[2023-11-28 08:54:19,314][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000331872_84959232.pth... -[2023-11-28 08:54:19,362][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000329312_84303872.pth -[2023-11-28 08:54:21,004][87426] Updated weights for policy 1, policy_version 331530 (0.0012) -[2023-11-28 08:54:21,316][87424] Updated weights for policy 0, policy_version 331879 (0.0010) -[2023-11-28 08:54:21,393][87426] Updated weights for policy 1, policy_version 331540 (0.0011) -[2023-11-28 08:54:21,700][87424] Updated weights for policy 0, policy_version 331889 (0.0011) -[2023-11-28 08:54:21,765][87426] Updated weights for policy 1, policy_version 331550 (0.0012) -[2023-11-28 08:54:22,080][87424] Updated weights for policy 0, policy_version 331899 (0.0009) -[2023-11-28 08:54:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 169844736. Throughput: 0: 2755.6, 1: 2738.8. Samples: 169861324. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:23,445][86177] Avg episode reward: [(0, '-545.840'), (1, '-504.490')] -[2023-11-28 08:54:23,976][87426] Updated weights for policy 1, policy_version 331560 (0.0010) -[2023-11-28 08:54:24,131][87424] Updated weights for policy 0, policy_version 331909 (0.0009) -[2023-11-28 08:54:24,360][87426] Updated weights for policy 1, policy_version 331570 (0.0010) -[2023-11-28 08:54:24,519][87424] Updated weights for policy 0, policy_version 331919 (0.0009) -[2023-11-28 08:54:24,740][87426] Updated weights for policy 1, policy_version 331580 (0.0010) -[2023-11-28 08:54:24,904][87424] Updated weights for policy 0, policy_version 331929 (0.0011) -[2023-11-28 08:54:26,503][87426] Updated weights for policy 1, policy_version 331590 (0.0011) -[2023-11-28 08:54:26,878][87426] Updated weights for policy 1, policy_version 331600 (0.0012) -[2023-11-28 08:54:27,251][87426] Updated weights for policy 1, policy_version 331610 (0.0011) -[2023-11-28 08:54:27,274][87424] Updated weights for policy 0, policy_version 331939 (0.0011) -[2023-11-28 08:54:27,658][87424] Updated weights for policy 0, policy_version 331949 (0.0011) -[2023-11-28 08:54:28,033][87424] Updated weights for policy 0, policy_version 331959 (0.0012) -[2023-11-28 08:54:28,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 169877504. Throughput: 0: 2776.5, 1: 2775.4. Samples: 169887312. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:28,446][86177] Avg episode reward: [(0, '-566.460'), (1, '-501.940')] -[2023-11-28 08:54:29,018][87426] Updated weights for policy 1, policy_version 331620 (0.0011) -[2023-11-28 08:54:29,400][87426] Updated weights for policy 1, policy_version 331630 (0.0012) -[2023-11-28 08:54:29,773][87426] Updated weights for policy 1, policy_version 331640 (0.0012) -[2023-11-28 08:54:30,279][87424] Updated weights for policy 0, policy_version 331969 (0.0011) -[2023-11-28 08:54:30,665][87424] Updated weights for policy 0, policy_version 331979 (0.0008) -[2023-11-28 08:54:31,040][87424] Updated weights for policy 0, policy_version 331989 (0.0007) -[2023-11-28 08:54:31,430][87424] Updated weights for policy 0, policy_version 331999 (0.0007) -[2023-11-28 08:54:31,962][87426] Updated weights for policy 1, policy_version 331650 (0.0012) -[2023-11-28 08:54:32,329][87426] Updated weights for policy 1, policy_version 331660 (0.0012) -[2023-11-28 08:54:32,711][87426] Updated weights for policy 1, policy_version 331670 (0.0012) -[2023-11-28 08:54:33,080][87426] Updated weights for policy 1, policy_version 331680 (0.0012) -[2023-11-28 08:54:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 169902080. Throughput: 0: 2765.8, 1: 2791.2. Samples: 169912276. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:33,445][86177] Avg episode reward: [(0, '-550.030'), (1, '-518.850')] -[2023-11-28 08:54:33,636][87424] Updated weights for policy 0, policy_version 332009 (0.0007) -[2023-11-28 08:54:34,027][87424] Updated weights for policy 0, policy_version 332019 (0.0007) -[2023-11-28 08:54:34,401][87424] Updated weights for policy 0, policy_version 332029 (0.0008) -[2023-11-28 08:54:35,402][87426] Updated weights for policy 1, policy_version 331690 (0.0011) -[2023-11-28 08:54:35,774][87426] Updated weights for policy 1, policy_version 331700 (0.0010) -[2023-11-28 08:54:36,154][87426] Updated weights for policy 1, policy_version 331710 (0.0007) -[2023-11-28 08:54:36,657][87424] Updated weights for policy 0, policy_version 332039 (0.0008) -[2023-11-28 08:54:37,041][87424] Updated weights for policy 0, policy_version 332049 (0.0008) -[2023-11-28 08:54:37,428][87424] Updated weights for policy 0, policy_version 332059 (0.0008) -[2023-11-28 08:54:38,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 169926656. Throughput: 0: 2755.0, 1: 2791.2. Samples: 169944212. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:38,445][86177] Avg episode reward: [(0, '-546.370'), (1, '-518.750')] -[2023-11-28 08:54:38,455][87426] Updated weights for policy 1, policy_version 331720 (0.0011) -[2023-11-28 08:54:38,826][87426] Updated weights for policy 1, policy_version 331730 (0.0011) -[2023-11-28 08:54:39,215][87426] Updated weights for policy 1, policy_version 331740 (0.0012) -[2023-11-28 08:54:39,246][87424] Updated weights for policy 0, policy_version 332069 (0.0007) -[2023-11-28 08:54:39,639][87424] Updated weights for policy 0, policy_version 332079 (0.0009) -[2023-11-28 08:54:40,014][87424] Updated weights for policy 0, policy_version 332089 (0.0012) -[2023-11-28 08:54:41,377][87426] Updated weights for policy 1, policy_version 331750 (0.0012) -[2023-11-28 08:54:41,751][87426] Updated weights for policy 1, policy_version 331760 (0.0011) -[2023-11-28 08:54:42,128][87426] Updated weights for policy 1, policy_version 331770 (0.0012) -[2023-11-28 08:54:42,271][87424] Updated weights for policy 0, policy_version 332099 (0.0011) -[2023-11-28 08:54:42,654][87424] Updated weights for policy 0, policy_version 332109 (0.0012) -[2023-11-28 08:54:43,041][87424] Updated weights for policy 0, policy_version 332119 (0.0011) -[2023-11-28 08:54:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 169959424. Throughput: 0: 2752.7, 1: 2784.4. Samples: 169968604. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:43,445][86177] Avg episode reward: [(0, '-542.100'), (1, '-529.370')] -[2023-11-28 08:54:44,204][87426] Updated weights for policy 1, policy_version 331780 (0.0011) -[2023-11-28 08:54:44,588][87426] Updated weights for policy 1, policy_version 331790 (0.0012) -[2023-11-28 08:54:44,763][87424] Updated weights for policy 0, policy_version 332129 (0.0010) -[2023-11-28 08:54:44,971][87426] Updated weights for policy 1, policy_version 331800 (0.0012) -[2023-11-28 08:54:45,148][87424] Updated weights for policy 0, policy_version 332139 (0.0011) -[2023-11-28 08:54:45,540][87424] Updated weights for policy 0, policy_version 332149 (0.0011) -[2023-11-28 08:54:45,919][87424] Updated weights for policy 0, policy_version 332159 (0.0012) -[2023-11-28 08:54:47,285][87426] Updated weights for policy 1, policy_version 331810 (0.0009) -[2023-11-28 08:54:47,657][87426] Updated weights for policy 1, policy_version 331820 (0.0011) -[2023-11-28 08:54:47,936][87424] Updated weights for policy 0, policy_version 332169 (0.0012) -[2023-11-28 08:54:48,037][87426] Updated weights for policy 1, policy_version 331830 (0.0012) -[2023-11-28 08:54:48,324][87424] Updated weights for policy 0, policy_version 332179 (0.0012) -[2023-11-28 08:54:48,423][87426] Updated weights for policy 1, policy_version 331840 (0.0012) -[2023-11-28 08:54:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 169984000. Throughput: 0: 2745.6, 1: 2778.7. Samples: 169994032. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:48,445][86177] Avg episode reward: [(0, '-550.690'), (1, '-576.860')] -[2023-11-28 08:54:48,712][87424] Updated weights for policy 0, policy_version 332189 (0.0012) -[2023-11-28 08:54:50,740][87426] Updated weights for policy 1, policy_version 331850 (0.0011) -[2023-11-28 08:54:51,029][87424] Updated weights for policy 0, policy_version 332199 (0.0012) -[2023-11-28 08:54:51,120][87426] Updated weights for policy 1, policy_version 331860 (0.0011) -[2023-11-28 08:54:51,417][87424] Updated weights for policy 0, policy_version 332209 (0.0011) -[2023-11-28 08:54:51,502][87426] Updated weights for policy 1, policy_version 331870 (0.0011) -[2023-11-28 08:54:51,803][87424] Updated weights for policy 0, policy_version 332219 (0.0012) -[2023-11-28 08:54:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 170008576. Throughput: 0: 2762.1, 1: 2772.5. Samples: 170027072. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:53,445][86177] Avg episode reward: [(0, '-576.840'), (1, '-571.570')] -[2023-11-28 08:54:53,810][87424] Updated weights for policy 0, policy_version 332229 (0.0012) -[2023-11-28 08:54:53,976][87426] Updated weights for policy 1, policy_version 331880 (0.0009) -[2023-11-28 08:54:54,188][87424] Updated weights for policy 0, policy_version 332239 (0.0011) -[2023-11-28 08:54:54,355][87426] Updated weights for policy 1, policy_version 331890 (0.0011) -[2023-11-28 08:54:54,570][87424] Updated weights for policy 0, policy_version 332249 (0.0011) -[2023-11-28 08:54:54,729][87426] Updated weights for policy 1, policy_version 331900 (0.0011) -[2023-11-28 08:54:56,472][87424] Updated weights for policy 0, policy_version 332259 (0.0011) -[2023-11-28 08:54:56,587][87426] Updated weights for policy 1, policy_version 331910 (0.0011) -[2023-11-28 08:54:56,864][87424] Updated weights for policy 0, policy_version 332269 (0.0009) -[2023-11-28 08:54:56,959][87426] Updated weights for policy 1, policy_version 331920 (0.0012) -[2023-11-28 08:54:57,237][87424] Updated weights for policy 0, policy_version 332279 (0.0008) -[2023-11-28 08:54:57,343][87426] Updated weights for policy 1, policy_version 331930 (0.0011) -[2023-11-28 08:54:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 170041344. Throughput: 0: 2762.0, 1: 2778.4. Samples: 170051568. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:54:58,445][86177] Avg episode reward: [(0, '-576.240'), (1, '-566.400')] -[2023-11-28 08:54:59,706][87424] Updated weights for policy 0, policy_version 332289 (0.0008) -[2023-11-28 08:54:59,810][87426] Updated weights for policy 1, policy_version 331940 (0.0010) -[2023-11-28 08:55:00,089][87424] Updated weights for policy 0, policy_version 332299 (0.0010) -[2023-11-28 08:55:00,180][87426] Updated weights for policy 1, policy_version 331950 (0.0009) -[2023-11-28 08:55:00,473][87424] Updated weights for policy 0, policy_version 332309 (0.0012) -[2023-11-28 08:55:00,571][87426] Updated weights for policy 1, policy_version 331960 (0.0010) -[2023-11-28 08:55:00,857][87424] Updated weights for policy 0, policy_version 332319 (0.0011) -[2023-11-28 08:55:02,674][87424] Updated weights for policy 0, policy_version 332329 (0.0012) -[2023-11-28 08:55:02,710][87426] Updated weights for policy 1, policy_version 331970 (0.0012) -[2023-11-28 08:55:03,059][87424] Updated weights for policy 0, policy_version 332339 (0.0010) -[2023-11-28 08:55:03,090][87426] Updated weights for policy 1, policy_version 331980 (0.0011) -[2023-11-28 08:55:03,433][87424] Updated weights for policy 0, policy_version 332349 (0.0007) -[2023-11-28 08:55:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 170057728. Throughput: 0: 2795.5, 1: 2743.9. Samples: 170076316. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:55:03,445][86177] Avg episode reward: [(0, '-583.030'), (1, '-574.270')] -[2023-11-28 08:55:03,462][87426] Updated weights for policy 1, policy_version 331990 (0.0011) -[2023-11-28 08:55:03,841][87426] Updated weights for policy 1, policy_version 332000 (0.0012) -[2023-11-28 08:55:05,823][87424] Updated weights for policy 0, policy_version 332359 (0.0011) -[2023-11-28 08:55:06,171][87426] Updated weights for policy 1, policy_version 332010 (0.0008) -[2023-11-28 08:55:06,206][87424] Updated weights for policy 0, policy_version 332369 (0.0012) -[2023-11-28 08:55:06,543][87426] Updated weights for policy 1, policy_version 332020 (0.0008) -[2023-11-28 08:55:06,585][87424] Updated weights for policy 0, policy_version 332379 (0.0011) -[2023-11-28 08:55:06,918][87426] Updated weights for policy 1, policy_version 332030 (0.0011) -[2023-11-28 08:55:08,236][87424] Updated weights for policy 0, policy_version 332389 (0.0010) -[2023-11-28 08:55:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 170090496. Throughput: 0: 2789.8, 1: 2727.6. Samples: 170109608. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:55:08,445][86177] Avg episode reward: [(0, '-570.800'), (1, '-540.790')] -[2023-11-28 08:55:08,628][87424] Updated weights for policy 0, policy_version 332399 (0.0008) -[2023-11-28 08:55:09,009][87424] Updated weights for policy 0, policy_version 332409 (0.0009) -[2023-11-28 08:55:09,288][87426] Updated weights for policy 1, policy_version 332040 (0.0011) -[2023-11-28 08:55:09,662][87426] Updated weights for policy 1, policy_version 332050 (0.0012) -[2023-11-28 08:55:10,047][87426] Updated weights for policy 1, policy_version 332060 (0.0012) -[2023-11-28 08:55:11,110][87424] Updated weights for policy 0, policy_version 332419 (0.0010) -[2023-11-28 08:55:11,495][87424] Updated weights for policy 0, policy_version 332429 (0.0012) -[2023-11-28 08:55:11,873][87424] Updated weights for policy 0, policy_version 332439 (0.0010) -[2023-11-28 08:55:12,231][87426] Updated weights for policy 1, policy_version 332070 (0.0010) -[2023-11-28 08:55:12,611][87426] Updated weights for policy 1, policy_version 332080 (0.0011) -[2023-11-28 08:55:12,988][87426] Updated weights for policy 1, policy_version 332090 (0.0011) -[2023-11-28 08:55:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 170123264. Throughput: 0: 2782.3, 1: 2691.5. Samples: 170133632. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:55:13,445][86177] Avg episode reward: [(0, '-553.980'), (1, '-532.360')] -[2023-11-28 08:55:14,345][87424] Updated weights for policy 0, policy_version 332449 (0.0011) -[2023-11-28 08:55:14,728][87424] Updated weights for policy 0, policy_version 332459 (0.0010) -[2023-11-28 08:55:15,109][87424] Updated weights for policy 0, policy_version 332469 (0.0007) -[2023-11-28 08:55:15,329][87426] Updated weights for policy 1, policy_version 332100 (0.0011) -[2023-11-28 08:55:15,494][87424] Updated weights for policy 0, policy_version 332479 (0.0009) -[2023-11-28 08:55:15,697][87426] Updated weights for policy 1, policy_version 332110 (0.0012) -[2023-11-28 08:55:16,076][87426] Updated weights for policy 1, policy_version 332120 (0.0011) -[2023-11-28 08:55:17,682][87424] Updated weights for policy 0, policy_version 332489 (0.0012) -[2023-11-28 08:55:18,005][87426] Updated weights for policy 1, policy_version 332130 (0.0009) -[2023-11-28 08:55:18,063][87424] Updated weights for policy 0, policy_version 332499 (0.0012) -[2023-11-28 08:55:18,396][87426] Updated weights for policy 1, policy_version 332140 (0.0011) -[2023-11-28 08:55:18,443][87424] Updated weights for policy 0, policy_version 332509 (0.0012) -[2023-11-28 08:55:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 170139648. Throughput: 0: 2792.5, 1: 2679.6. Samples: 170158520. Policy #0 lag: (min: 27.0, avg: 42.4, max: 59.0) -[2023-11-28 08:55:18,445][86177] Avg episode reward: [(0, '-557.330'), (1, '-533.990')] -[2023-11-28 08:55:18,768][87426] Updated weights for policy 1, policy_version 332150 (0.0011) -[2023-11-28 08:55:19,147][87426] Updated weights for policy 1, policy_version 332160 (0.0010) -[2023-11-28 08:55:20,925][87424] Updated weights for policy 0, policy_version 332519 (0.0009) -[2023-11-28 08:55:21,305][87424] Updated weights for policy 0, policy_version 332529 (0.0010) -[2023-11-28 08:55:21,563][87426] Updated weights for policy 1, policy_version 332170 (0.0009) -[2023-11-28 08:55:21,682][87424] Updated weights for policy 0, policy_version 332539 (0.0011) -[2023-11-28 08:55:21,939][87426] Updated weights for policy 1, policy_version 332180 (0.0011) -[2023-11-28 08:55:22,317][87426] Updated weights for policy 1, policy_version 332190 (0.0011) -[2023-11-28 08:55:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 170172416. Throughput: 0: 2777.9, 1: 2677.9. Samples: 170189720. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:55:23,445][86177] Avg episode reward: [(0, '-549.470'), (1, '-526.980')] -[2023-11-28 08:55:23,999][87424] Updated weights for policy 0, policy_version 332549 (0.0010) -[2023-11-28 08:55:24,386][87424] Updated weights for policy 0, policy_version 332559 (0.0008) -[2023-11-28 08:55:24,465][87426] Updated weights for policy 1, policy_version 332200 (0.0011) -[2023-11-28 08:55:24,771][87424] Updated weights for policy 0, policy_version 332569 (0.0008) -[2023-11-28 08:55:24,850][87426] Updated weights for policy 1, policy_version 332210 (0.0011) -[2023-11-28 08:55:25,224][87426] Updated weights for policy 1, policy_version 332220 (0.0011) -[2023-11-28 08:55:27,333][87424] Updated weights for policy 0, policy_version 332579 (0.0008) -[2023-11-28 08:55:27,493][87426] Updated weights for policy 1, policy_version 332230 (0.0012) -[2023-11-28 08:55:27,704][87424] Updated weights for policy 0, policy_version 332589 (0.0007) -[2023-11-28 08:55:27,862][87426] Updated weights for policy 1, policy_version 332240 (0.0012) -[2023-11-28 08:55:28,086][87424] Updated weights for policy 0, policy_version 332599 (0.0009) -[2023-11-28 08:55:28,244][87426] Updated weights for policy 1, policy_version 332250 (0.0012) -[2023-11-28 08:55:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 170196992. Throughput: 0: 2773.7, 1: 2696.9. Samples: 170214780. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:55:28,445][86177] Avg episode reward: [(0, '-545.500'), (1, '-526.400')] -[2023-11-28 08:55:29,872][87424] Updated weights for policy 0, policy_version 332609 (0.0009) -[2023-11-28 08:55:30,244][87424] Updated weights for policy 0, policy_version 332619 (0.0012) -[2023-11-28 08:55:30,514][87426] Updated weights for policy 1, policy_version 332260 (0.0012) -[2023-11-28 08:55:30,625][87424] Updated weights for policy 0, policy_version 332629 (0.0010) -[2023-11-28 08:55:30,900][87426] Updated weights for policy 1, policy_version 332270 (0.0008) -[2023-11-28 08:55:31,014][87424] Updated weights for policy 0, policy_version 332639 (0.0012) -[2023-11-28 08:55:31,274][87426] Updated weights for policy 1, policy_version 332280 (0.0009) -[2023-11-28 08:55:32,783][87424] Updated weights for policy 0, policy_version 332649 (0.0012) -[2023-11-28 08:55:33,159][87424] Updated weights for policy 0, policy_version 332659 (0.0012) -[2023-11-28 08:55:33,332][87426] Updated weights for policy 1, policy_version 332290 (0.0009) -[2023-11-28 08:55:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 170221568. Throughput: 0: 2751.2, 1: 2683.8. Samples: 170238608. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:55:33,445][86177] Avg episode reward: [(0, '-529.090'), (1, '-525.990')] -[2023-11-28 08:55:33,542][87424] Updated weights for policy 0, policy_version 332669 (0.0010) -[2023-11-28 08:55:33,710][87426] Updated weights for policy 1, policy_version 332300 (0.0012) -[2023-11-28 08:55:34,092][87426] Updated weights for policy 1, policy_version 332310 (0.0011) -[2023-11-28 08:55:34,473][87426] Updated weights for policy 1, policy_version 332320 (0.0012) -[2023-11-28 08:55:35,711][87424] Updated weights for policy 0, policy_version 332679 (0.0010) -[2023-11-28 08:55:36,099][87424] Updated weights for policy 0, policy_version 332689 (0.0009) -[2023-11-28 08:55:36,467][87426] Updated weights for policy 1, policy_version 332330 (0.0012) -[2023-11-28 08:55:36,485][87424] Updated weights for policy 0, policy_version 332699 (0.0011) -[2023-11-28 08:55:36,841][87426] Updated weights for policy 1, policy_version 332340 (0.0011) -[2023-11-28 08:55:37,215][87426] Updated weights for policy 1, policy_version 332350 (0.0012) -[2023-11-28 08:55:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5498.4). Total num frames: 170254336. Throughput: 0: 2750.6, 1: 2694.8. Samples: 170272112. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:55:38,445][86177] Avg episode reward: [(0, '-531.790'), (1, '-523.520')] -[2023-11-28 08:55:38,719][87424] Updated weights for policy 0, policy_version 332709 (0.0011) -[2023-11-28 08:55:39,115][87424] Updated weights for policy 0, policy_version 332719 (0.0012) -[2023-11-28 08:55:39,372][87426] Updated weights for policy 1, policy_version 332360 (0.0012) -[2023-11-28 08:55:39,493][87424] Updated weights for policy 0, policy_version 332729 (0.0015) -[2023-11-28 08:55:39,758][87426] Updated weights for policy 1, policy_version 332370 (0.0009) -[2023-11-28 08:55:40,134][87426] Updated weights for policy 1, policy_version 332380 (0.0009) -[2023-11-28 08:55:41,716][87424] Updated weights for policy 0, policy_version 332739 (0.0013) -[2023-11-28 08:55:42,128][87424] Updated weights for policy 0, policy_version 332749 (0.0010) -[2023-11-28 08:55:42,499][87424] Updated weights for policy 0, policy_version 332759 (0.0009) -[2023-11-28 08:55:42,641][87426] Updated weights for policy 1, policy_version 332390 (0.0010) -[2023-11-28 08:55:43,011][87426] Updated weights for policy 1, policy_version 332400 (0.0011) -[2023-11-28 08:55:43,387][87426] Updated weights for policy 1, policy_version 332410 (0.0009) -[2023-11-28 08:55:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 170278912. Throughput: 0: 2735.5, 1: 2686.9. Samples: 170295576. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:55:43,445][86177] Avg episode reward: [(0, '-531.440'), (1, '-534.630')] -[2023-11-28 08:55:44,856][87424] Updated weights for policy 0, policy_version 332769 (0.0010) -[2023-11-28 08:55:45,237][87424] Updated weights for policy 0, policy_version 332779 (0.0008) -[2023-11-28 08:55:45,617][87424] Updated weights for policy 0, policy_version 332789 (0.0010) -[2023-11-28 08:55:45,820][87426] Updated weights for policy 1, policy_version 332420 (0.0011) -[2023-11-28 08:55:45,995][87424] Updated weights for policy 0, policy_version 332799 (0.0011) -[2023-11-28 08:55:46,187][87426] Updated weights for policy 1, policy_version 332430 (0.0011) -[2023-11-28 08:55:46,567][87426] Updated weights for policy 1, policy_version 332440 (0.0012) -[2023-11-28 08:55:48,004][87424] Updated weights for policy 0, policy_version 332809 (0.0012) -[2023-11-28 08:55:48,389][87424] Updated weights for policy 0, policy_version 332819 (0.0012) -[2023-11-28 08:55:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 170303488. Throughput: 0: 2701.1, 1: 2691.5. Samples: 170318980. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:55:48,445][86177] Avg episode reward: [(0, '-530.170'), (1, '-532.460')] -[2023-11-28 08:55:48,769][87424] Updated weights for policy 0, policy_version 332829 (0.0012) -[2023-11-28 08:55:48,985][87426] Updated weights for policy 1, policy_version 332450 (0.0012) -[2023-11-28 08:55:49,362][87426] Updated weights for policy 1, policy_version 332460 (0.0007) -[2023-11-28 08:55:49,748][87426] Updated weights for policy 1, policy_version 332470 (0.0008) -[2023-11-28 08:55:50,124][87426] Updated weights for policy 1, policy_version 332480 (0.0011) -[2023-11-28 08:55:51,170][87424] Updated weights for policy 0, policy_version 332839 (0.0009) -[2023-11-28 08:55:51,544][87424] Updated weights for policy 0, policy_version 332849 (0.0009) -[2023-11-28 08:55:51,923][87424] Updated weights for policy 0, policy_version 332859 (0.0009) -[2023-11-28 08:55:52,690][87426] Updated weights for policy 1, policy_version 332490 (0.0007) -[2023-11-28 08:55:53,061][87426] Updated weights for policy 1, policy_version 332500 (0.0009) -[2023-11-28 08:55:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 170328064. Throughput: 0: 2686.3, 1: 2688.5. Samples: 170351476. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:55:53,445][86177] Avg episode reward: [(0, '-531.450'), (1, '-535.940')] -[2023-11-28 08:55:53,449][87426] Updated weights for policy 1, policy_version 332510 (0.0010) -[2023-11-28 08:55:54,225][87424] Updated weights for policy 0, policy_version 332869 (0.0011) -[2023-11-28 08:55:54,610][87424] Updated weights for policy 0, policy_version 332879 (0.0012) -[2023-11-28 08:55:55,003][87424] Updated weights for policy 0, policy_version 332889 (0.0012) -[2023-11-28 08:55:55,573][87426] Updated weights for policy 1, policy_version 332520 (0.0010) -[2023-11-28 08:55:55,956][87426] Updated weights for policy 1, policy_version 332530 (0.0007) -[2023-11-28 08:55:56,331][87426] Updated weights for policy 1, policy_version 332540 (0.0007) -[2023-11-28 08:55:56,611][87424] Updated weights for policy 0, policy_version 332899 (0.0012) -[2023-11-28 08:55:56,995][87424] Updated weights for policy 0, policy_version 332909 (0.0012) -[2023-11-28 08:55:57,378][87424] Updated weights for policy 0, policy_version 332919 (0.0012) -[2023-11-28 08:55:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 170360832. Throughput: 0: 2682.4, 1: 2681.2. Samples: 170374992. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:55:58,445][86177] Avg episode reward: [(0, '-533.830'), (1, '-543.270')] -[2023-11-28 08:55:58,462][87426] Updated weights for policy 1, policy_version 332550 (0.0008) -[2023-11-28 08:55:58,832][87426] Updated weights for policy 1, policy_version 332560 (0.0007) -[2023-11-28 08:55:59,213][87426] Updated weights for policy 1, policy_version 332570 (0.0011) -[2023-11-28 08:55:59,810][87424] Updated weights for policy 0, policy_version 332929 (0.0012) -[2023-11-28 08:56:00,184][87424] Updated weights for policy 0, policy_version 332939 (0.0012) -[2023-11-28 08:56:00,568][87424] Updated weights for policy 0, policy_version 332949 (0.0011) -[2023-11-28 08:56:00,946][87424] Updated weights for policy 0, policy_version 332959 (0.0016) -[2023-11-28 08:56:01,520][87426] Updated weights for policy 1, policy_version 332580 (0.0012) -[2023-11-28 08:56:01,898][87426] Updated weights for policy 1, policy_version 332590 (0.0012) -[2023-11-28 08:56:02,284][87426] Updated weights for policy 1, policy_version 332600 (0.0012) -[2023-11-28 08:56:02,828][87424] Updated weights for policy 0, policy_version 332969 (0.0008) -[2023-11-28 08:56:03,213][87424] Updated weights for policy 0, policy_version 332979 (0.0008) -[2023-11-28 08:56:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 170385408. Throughput: 0: 2689.5, 1: 2674.0. Samples: 170399880. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:56:03,445][86177] Avg episode reward: [(0, '-535.830'), (1, '-542.770')] -[2023-11-28 08:56:03,596][87424] Updated weights for policy 0, policy_version 332989 (0.0008) -[2023-11-28 08:56:04,737][87426] Updated weights for policy 1, policy_version 332610 (0.0011) -[2023-11-28 08:56:05,113][87426] Updated weights for policy 1, policy_version 332620 (0.0012) -[2023-11-28 08:56:05,478][87426] Updated weights for policy 1, policy_version 332630 (0.0012) -[2023-11-28 08:56:05,855][87426] Updated weights for policy 1, policy_version 332640 (0.0010) -[2023-11-28 08:56:05,990][87424] Updated weights for policy 0, policy_version 332999 (0.0008) -[2023-11-28 08:56:06,387][87424] Updated weights for policy 0, policy_version 333009 (0.0007) -[2023-11-28 08:56:06,769][87424] Updated weights for policy 0, policy_version 333019 (0.0008) -[2023-11-28 08:56:08,153][87426] Updated weights for policy 1, policy_version 332650 (0.0012) -[2023-11-28 08:56:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 170409984. Throughput: 0: 2716.0, 1: 2682.2. Samples: 170432640. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:56:08,445][86177] Avg episode reward: [(0, '-532.300'), (1, '-534.280')] -[2023-11-28 08:56:08,531][87426] Updated weights for policy 1, policy_version 332660 (0.0012) -[2023-11-28 08:56:08,897][87426] Updated weights for policy 1, policy_version 332670 (0.0012) -[2023-11-28 08:56:09,275][87424] Updated weights for policy 0, policy_version 333029 (0.0010) -[2023-11-28 08:56:09,656][87424] Updated weights for policy 0, policy_version 333039 (0.0012) -[2023-11-28 08:56:10,043][87424] Updated weights for policy 0, policy_version 333049 (0.0012) -[2023-11-28 08:56:11,161][87426] Updated weights for policy 1, policy_version 332680 (0.0011) -[2023-11-28 08:56:11,543][87426] Updated weights for policy 1, policy_version 332690 (0.0011) -[2023-11-28 08:56:11,935][87426] Updated weights for policy 1, policy_version 332700 (0.0012) -[2023-11-28 08:56:12,495][87424] Updated weights for policy 0, policy_version 333059 (0.0012) -[2023-11-28 08:56:12,864][87424] Updated weights for policy 0, policy_version 333069 (0.0012) -[2023-11-28 08:56:13,262][87424] Updated weights for policy 0, policy_version 333079 (0.0012) -[2023-11-28 08:56:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5442.8). Total num frames: 170434560. Throughput: 0: 2709.2, 1: 2652.2. Samples: 170456040. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:56:13,445][86177] Avg episode reward: [(0, '-538.270'), (1, '-528.080')] -[2023-11-28 08:56:13,882][87426] Updated weights for policy 1, policy_version 332710 (0.0012) -[2023-11-28 08:56:14,261][87426] Updated weights for policy 1, policy_version 332720 (0.0012) -[2023-11-28 08:56:14,642][87426] Updated weights for policy 1, policy_version 332730 (0.0012) -[2023-11-28 08:56:15,166][87424] Updated weights for policy 0, policy_version 333089 (0.0011) -[2023-11-28 08:56:15,544][87424] Updated weights for policy 0, policy_version 333099 (0.0010) -[2023-11-28 08:56:15,933][87424] Updated weights for policy 0, policy_version 333109 (0.0009) -[2023-11-28 08:56:16,317][87424] Updated weights for policy 0, policy_version 333119 (0.0008) -[2023-11-28 08:56:17,166][87426] Updated weights for policy 1, policy_version 332740 (0.0012) -[2023-11-28 08:56:17,532][87426] Updated weights for policy 1, policy_version 332750 (0.0011) -[2023-11-28 08:56:17,920][87426] Updated weights for policy 1, policy_version 332760 (0.0015) -[2023-11-28 08:56:18,063][87424] Updated weights for policy 0, policy_version 333129 (0.0008) -[2023-11-28 08:56:18,435][87424] Updated weights for policy 0, policy_version 333139 (0.0011) -[2023-11-28 08:56:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 170467328. Throughput: 0: 2724.7, 1: 2657.1. Samples: 170480788. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:56:18,445][86177] Avg episode reward: [(0, '-540.720'), (1, '-519.680')] -[2023-11-28 08:56:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000332768_85188608.pth... -[2023-11-28 08:56:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000330208_84533248.pth -[2023-11-28 08:56:18,822][87424] Updated weights for policy 0, policy_version 333149 (0.0012) -[2023-11-28 08:56:18,929][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000333152_85286912.pth... -[2023-11-28 08:56:18,975][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000330592_84631552.pth -[2023-11-28 08:56:19,854][87426] Updated weights for policy 1, policy_version 332770 (0.0009) -[2023-11-28 08:56:20,231][87426] Updated weights for policy 1, policy_version 332780 (0.0012) -[2023-11-28 08:56:20,617][87426] Updated weights for policy 1, policy_version 332790 (0.0012) -[2023-11-28 08:56:20,986][87426] Updated weights for policy 1, policy_version 332800 (0.0011) -[2023-11-28 08:56:21,000][87424] Updated weights for policy 0, policy_version 333159 (0.0009) -[2023-11-28 08:56:21,383][87424] Updated weights for policy 0, policy_version 333169 (0.0009) -[2023-11-28 08:56:21,757][87424] Updated weights for policy 0, policy_version 333179 (0.0010) -[2023-11-28 08:56:23,132][87426] Updated weights for policy 1, policy_version 332810 (0.0012) -[2023-11-28 08:56:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5470.6). Total num frames: 170491904. Throughput: 0: 2712.5, 1: 2647.2. Samples: 170513300. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:56:23,445][86177] Avg episode reward: [(0, '-546.380'), (1, '-523.840')] -[2023-11-28 08:56:23,508][87426] Updated weights for policy 1, policy_version 332820 (0.0012) -[2023-11-28 08:56:23,884][87426] Updated weights for policy 1, policy_version 332830 (0.0012) -[2023-11-28 08:56:24,197][87424] Updated weights for policy 0, policy_version 333189 (0.0010) -[2023-11-28 08:56:24,582][87424] Updated weights for policy 0, policy_version 333199 (0.0012) -[2023-11-28 08:56:24,966][87424] Updated weights for policy 0, policy_version 333209 (0.0012) -[2023-11-28 08:56:25,539][87426] Updated weights for policy 1, policy_version 332840 (0.0012) -[2023-11-28 08:56:25,919][87426] Updated weights for policy 1, policy_version 332850 (0.0012) -[2023-11-28 08:56:26,303][87426] Updated weights for policy 1, policy_version 332860 (0.0008) -[2023-11-28 08:56:27,368][87424] Updated weights for policy 0, policy_version 333219 (0.0012) -[2023-11-28 08:56:27,741][87424] Updated weights for policy 0, policy_version 333229 (0.0011) -[2023-11-28 08:56:28,118][87424] Updated weights for policy 0, policy_version 333239 (0.0012) -[2023-11-28 08:56:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 170516480. Throughput: 0: 2705.5, 1: 2659.2. Samples: 170536988. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:56:28,445][86177] Avg episode reward: [(0, '-545.090'), (1, '-580.340')] -[2023-11-28 08:56:28,755][87426] Updated weights for policy 1, policy_version 332870 (0.0010) -[2023-11-28 08:56:29,124][87426] Updated weights for policy 1, policy_version 332880 (0.0010) -[2023-11-28 08:56:29,503][87426] Updated weights for policy 1, policy_version 332890 (0.0011) -[2023-11-28 08:56:30,429][87424] Updated weights for policy 0, policy_version 333249 (0.0011) -[2023-11-28 08:56:30,813][87424] Updated weights for policy 0, policy_version 333259 (0.0007) -[2023-11-28 08:56:31,197][87424] Updated weights for policy 0, policy_version 333269 (0.0009) -[2023-11-28 08:56:31,582][87424] Updated weights for policy 0, policy_version 333279 (0.0009) -[2023-11-28 08:56:32,036][87426] Updated weights for policy 1, policy_version 332900 (0.0010) -[2023-11-28 08:56:32,413][87426] Updated weights for policy 1, policy_version 332910 (0.0012) -[2023-11-28 08:56:32,793][87426] Updated weights for policy 1, policy_version 332920 (0.0012) -[2023-11-28 08:56:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5470.6). Total num frames: 170549248. Throughput: 0: 2701.7, 1: 2652.9. Samples: 170559936. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:56:33,445][86177] Avg episode reward: [(0, '-540.370'), (1, '-596.860')] -[2023-11-28 08:56:33,593][87424] Updated weights for policy 0, policy_version 333289 (0.0008) -[2023-11-28 08:56:33,976][87424] Updated weights for policy 0, policy_version 333299 (0.0009) -[2023-11-28 08:56:34,359][87424] Updated weights for policy 0, policy_version 333309 (0.0008) -[2023-11-28 08:56:35,342][87426] Updated weights for policy 1, policy_version 332930 (0.0010) -[2023-11-28 08:56:35,730][87426] Updated weights for policy 1, policy_version 332940 (0.0011) -[2023-11-28 08:56:36,107][87426] Updated weights for policy 1, policy_version 332950 (0.0011) -[2023-11-28 08:56:36,489][87426] Updated weights for policy 1, policy_version 332960 (0.0009) -[2023-11-28 08:56:36,507][87424] Updated weights for policy 0, policy_version 333319 (0.0007) -[2023-11-28 08:56:36,895][87424] Updated weights for policy 0, policy_version 333329 (0.0008) -[2023-11-28 08:56:37,281][87424] Updated weights for policy 0, policy_version 333339 (0.0007) -[2023-11-28 08:56:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 170573824. Throughput: 0: 2695.6, 1: 2631.9. Samples: 170591216. Policy #0 lag: (min: 21.0, avg: 36.2, max: 53.0) -[2023-11-28 08:56:38,445][86177] Avg episode reward: [(0, '-531.650'), (1, '-596.450')] -[2023-11-28 08:56:38,520][87426] Updated weights for policy 1, policy_version 332970 (0.0010) -[2023-11-28 08:56:38,897][87426] Updated weights for policy 1, policy_version 332980 (0.0008) -[2023-11-28 08:56:39,271][87426] Updated weights for policy 1, policy_version 332990 (0.0008) -[2023-11-28 08:56:39,307][87424] Updated weights for policy 0, policy_version 333349 (0.0010) -[2023-11-28 08:56:39,689][87424] Updated weights for policy 0, policy_version 333359 (0.0008) -[2023-11-28 08:56:40,078][87424] Updated weights for policy 0, policy_version 333369 (0.0010) -[2023-11-28 08:56:41,436][87426] Updated weights for policy 1, policy_version 333000 (0.0011) -[2023-11-28 08:56:41,814][87426] Updated weights for policy 1, policy_version 333010 (0.0012) -[2023-11-28 08:56:42,202][87426] Updated weights for policy 1, policy_version 333020 (0.0012) -[2023-11-28 08:56:42,526][87424] Updated weights for policy 0, policy_version 333379 (0.0012) -[2023-11-28 08:56:42,903][87424] Updated weights for policy 0, policy_version 333389 (0.0012) -[2023-11-28 08:56:43,292][87424] Updated weights for policy 0, policy_version 333399 (0.0012) -[2023-11-28 08:56:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 170598400. Throughput: 0: 2686.3, 1: 2626.1. Samples: 170614052. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:56:43,445][86177] Avg episode reward: [(0, '-530.870'), (1, '-598.010')] -[2023-11-28 08:56:44,638][87426] Updated weights for policy 1, policy_version 333030 (0.0012) -[2023-11-28 08:56:45,022][87426] Updated weights for policy 1, policy_version 333040 (0.0012) -[2023-11-28 08:56:45,399][87426] Updated weights for policy 1, policy_version 333050 (0.0012) -[2023-11-28 08:56:45,431][87424] Updated weights for policy 0, policy_version 333409 (0.0009) -[2023-11-28 08:56:45,814][87424] Updated weights for policy 0, policy_version 333419 (0.0008) -[2023-11-28 08:56:46,185][87424] Updated weights for policy 0, policy_version 333429 (0.0008) -[2023-11-28 08:56:46,568][87424] Updated weights for policy 0, policy_version 333439 (0.0012) -[2023-11-28 08:56:47,144][87426] Updated weights for policy 1, policy_version 333060 (0.0011) -[2023-11-28 08:56:47,512][87426] Updated weights for policy 1, policy_version 333070 (0.0010) -[2023-11-28 08:56:47,901][87426] Updated weights for policy 1, policy_version 333080 (0.0007) -[2023-11-28 08:56:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5470.6). Total num frames: 170631168. Throughput: 0: 2665.8, 1: 2632.1. Samples: 170638284. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:56:48,445][86177] Avg episode reward: [(0, '-537.110'), (1, '-608.040')] -[2023-11-28 08:56:48,690][87424] Updated weights for policy 0, policy_version 333449 (0.0012) -[2023-11-28 08:56:49,072][87424] Updated weights for policy 0, policy_version 333459 (0.0011) -[2023-11-28 08:56:49,453][87424] Updated weights for policy 0, policy_version 333469 (0.0012) -[2023-11-28 08:56:50,390][87426] Updated weights for policy 1, policy_version 333090 (0.0008) -[2023-11-28 08:56:50,768][87426] Updated weights for policy 1, policy_version 333100 (0.0012) -[2023-11-28 08:56:51,135][87426] Updated weights for policy 1, policy_version 333110 (0.0011) -[2023-11-28 08:56:51,511][87426] Updated weights for policy 1, policy_version 333120 (0.0012) -[2023-11-28 08:56:51,733][87424] Updated weights for policy 0, policy_version 333479 (0.0012) -[2023-11-28 08:56:52,122][87424] Updated weights for policy 0, policy_version 333489 (0.0010) -[2023-11-28 08:56:52,496][87424] Updated weights for policy 0, policy_version 333499 (0.0012) -[2023-11-28 08:56:53,445][86177] Fps is (10 sec: 5733.8, 60 sec: 5461.2, 300 sec: 5470.6). Total num frames: 170655744. Throughput: 0: 2650.1, 1: 2626.4. Samples: 170670088. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:56:53,446][86177] Avg episode reward: [(0, '-538.020'), (1, '-584.600')] -[2023-11-28 08:56:53,785][87426] Updated weights for policy 1, policy_version 333130 (0.0012) -[2023-11-28 08:56:54,169][87426] Updated weights for policy 1, policy_version 333140 (0.0010) -[2023-11-28 08:56:54,533][87426] Updated weights for policy 1, policy_version 333150 (0.0011) -[2023-11-28 08:56:54,936][87424] Updated weights for policy 0, policy_version 333509 (0.0011) -[2023-11-28 08:56:55,319][87424] Updated weights for policy 0, policy_version 333519 (0.0011) -[2023-11-28 08:56:55,690][87424] Updated weights for policy 0, policy_version 333529 (0.0013) -[2023-11-28 08:56:57,287][87426] Updated weights for policy 1, policy_version 333160 (0.0012) -[2023-11-28 08:56:57,667][87426] Updated weights for policy 1, policy_version 333170 (0.0011) -[2023-11-28 08:56:58,043][87426] Updated weights for policy 1, policy_version 333180 (0.0012) -[2023-11-28 08:56:58,217][87424] Updated weights for policy 0, policy_version 333539 (0.0010) -[2023-11-28 08:56:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 170680320. Throughput: 0: 2649.4, 1: 2595.8. Samples: 170692076. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:56:58,445][86177] Avg episode reward: [(0, '-537.780'), (1, '-613.430')] -[2023-11-28 08:56:58,606][87424] Updated weights for policy 0, policy_version 333549 (0.0012) -[2023-11-28 08:56:58,980][87424] Updated weights for policy 0, policy_version 333559 (0.0012) -[2023-11-28 08:56:59,935][87426] Updated weights for policy 1, policy_version 333190 (0.0012) -[2023-11-28 08:57:00,316][87426] Updated weights for policy 1, policy_version 333200 (0.0012) -[2023-11-28 08:57:00,700][87426] Updated weights for policy 1, policy_version 333210 (0.0011) -[2023-11-28 08:57:01,457][87424] Updated weights for policy 0, policy_version 333569 (0.0011) -[2023-11-28 08:57:01,837][87424] Updated weights for policy 0, policy_version 333579 (0.0010) -[2023-11-28 08:57:02,227][87424] Updated weights for policy 0, policy_version 333589 (0.0012) -[2023-11-28 08:57:02,601][87424] Updated weights for policy 0, policy_version 333599 (0.0012) -[2023-11-28 08:57:03,168][87426] Updated weights for policy 1, policy_version 333220 (0.0009) -[2023-11-28 08:57:03,444][86177] Fps is (10 sec: 4915.7, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 170704896. Throughput: 0: 2631.7, 1: 2610.3. Samples: 170716680. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:03,445][86177] Avg episode reward: [(0, '-532.800'), (1, '-663.100')] -[2023-11-28 08:57:03,555][87426] Updated weights for policy 1, policy_version 333230 (0.0009) -[2023-11-28 08:57:03,923][87426] Updated weights for policy 1, policy_version 333240 (0.0012) -[2023-11-28 08:57:04,681][87424] Updated weights for policy 0, policy_version 333609 (0.0012) -[2023-11-28 08:57:05,066][87424] Updated weights for policy 0, policy_version 333619 (0.0012) -[2023-11-28 08:57:05,441][87424] Updated weights for policy 0, policy_version 333629 (0.0012) -[2023-11-28 08:57:06,330][87426] Updated weights for policy 1, policy_version 333250 (0.0011) -[2023-11-28 08:57:06,707][87426] Updated weights for policy 1, policy_version 333260 (0.0011) -[2023-11-28 08:57:07,089][87426] Updated weights for policy 1, policy_version 333270 (0.0012) -[2023-11-28 08:57:07,454][87426] Updated weights for policy 1, policy_version 333280 (0.0012) -[2023-11-28 08:57:07,884][87424] Updated weights for policy 0, policy_version 333639 (0.0012) -[2023-11-28 08:57:08,265][87424] Updated weights for policy 0, policy_version 333649 (0.0011) -[2023-11-28 08:57:08,447][86177] Fps is (10 sec: 4914.1, 60 sec: 5324.6, 300 sec: 5442.8). Total num frames: 170729472. Throughput: 0: 2630.7, 1: 2599.4. Samples: 170748668. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:08,447][86177] Avg episode reward: [(0, '-543.080'), (1, '-655.200')] -[2023-11-28 08:57:08,647][87424] Updated weights for policy 0, policy_version 333659 (0.0010) -[2023-11-28 08:57:09,939][87426] Updated weights for policy 1, policy_version 333290 (0.0023) -[2023-11-28 08:57:10,321][87426] Updated weights for policy 1, policy_version 333300 (0.0012) -[2023-11-28 08:57:10,689][87426] Updated weights for policy 1, policy_version 333310 (0.0011) -[2023-11-28 08:57:11,188][87424] Updated weights for policy 0, policy_version 333669 (0.0011) -[2023-11-28 08:57:11,569][87424] Updated weights for policy 0, policy_version 333679 (0.0011) -[2023-11-28 08:57:11,976][87424] Updated weights for policy 0, policy_version 333689 (0.0015) -[2023-11-28 08:57:13,320][87426] Updated weights for policy 1, policy_version 333320 (0.0009) -[2023-11-28 08:57:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 170754048. Throughput: 0: 2627.2, 1: 2572.6. Samples: 170770980. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:13,445][86177] Avg episode reward: [(0, '-549.040'), (1, '-638.670')] -[2023-11-28 08:57:13,701][87426] Updated weights for policy 1, policy_version 333330 (0.0010) -[2023-11-28 08:57:14,076][87426] Updated weights for policy 1, policy_version 333340 (0.0010) -[2023-11-28 08:57:14,552][87424] Updated weights for policy 0, policy_version 333699 (0.0012) -[2023-11-28 08:57:14,932][87424] Updated weights for policy 0, policy_version 333709 (0.0012) -[2023-11-28 08:57:15,313][87424] Updated weights for policy 0, policy_version 333719 (0.0011) -[2023-11-28 08:57:16,391][87426] Updated weights for policy 1, policy_version 333350 (0.0010) -[2023-11-28 08:57:16,778][87426] Updated weights for policy 1, policy_version 333360 (0.0009) -[2023-11-28 08:57:17,150][87426] Updated weights for policy 1, policy_version 333370 (0.0010) -[2023-11-28 08:57:17,961][87424] Updated weights for policy 0, policy_version 333729 (0.0012) -[2023-11-28 08:57:18,343][87424] Updated weights for policy 0, policy_version 333739 (0.0009) -[2023-11-28 08:57:18,444][86177] Fps is (10 sec: 4916.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 170778624. Throughput: 0: 2594.2, 1: 2577.0. Samples: 170792640. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:18,445][86177] Avg episode reward: [(0, '-553.160'), (1, '-652.900')] -[2023-11-28 08:57:18,733][87424] Updated weights for policy 0, policy_version 333749 (0.0009) -[2023-11-28 08:57:19,109][87424] Updated weights for policy 0, policy_version 333759 (0.0009) -[2023-11-28 08:57:19,390][87426] Updated weights for policy 1, policy_version 333380 (0.0010) -[2023-11-28 08:57:19,772][87426] Updated weights for policy 1, policy_version 333390 (0.0009) -[2023-11-28 08:57:20,146][87426] Updated weights for policy 1, policy_version 333400 (0.0011) -[2023-11-28 08:57:21,569][87424] Updated weights for policy 0, policy_version 333769 (0.0025) -[2023-11-28 08:57:21,937][87424] Updated weights for policy 0, policy_version 333779 (0.0011) -[2023-11-28 08:57:22,317][87424] Updated weights for policy 0, policy_version 333789 (0.0012) -[2023-11-28 08:57:22,952][87426] Updated weights for policy 1, policy_version 333410 (0.0012) -[2023-11-28 08:57:23,329][87426] Updated weights for policy 1, policy_version 333420 (0.0011) -[2023-11-28 08:57:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 170803200. Throughput: 0: 2568.0, 1: 2560.4. Samples: 170821996. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:23,445][86177] Avg episode reward: [(0, '-552.440'), (1, '-620.730')] -[2023-11-28 08:57:23,709][87426] Updated weights for policy 1, policy_version 333430 (0.0011) -[2023-11-28 08:57:24,088][87426] Updated weights for policy 1, policy_version 333440 (0.0011) -[2023-11-28 08:57:24,612][87424] Updated weights for policy 0, policy_version 333799 (0.0010) -[2023-11-28 08:57:24,987][87424] Updated weights for policy 0, policy_version 333809 (0.0012) -[2023-11-28 08:57:25,365][87424] Updated weights for policy 0, policy_version 333819 (0.0009) -[2023-11-28 08:57:26,684][87426] Updated weights for policy 1, policy_version 333450 (0.0010) -[2023-11-28 08:57:27,052][87426] Updated weights for policy 1, policy_version 333460 (0.0011) -[2023-11-28 08:57:27,438][87426] Updated weights for policy 1, policy_version 333470 (0.0010) -[2023-11-28 08:57:27,750][87424] Updated weights for policy 0, policy_version 333829 (0.0009) -[2023-11-28 08:57:28,144][87424] Updated weights for policy 0, policy_version 333839 (0.0009) -[2023-11-28 08:57:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 170827776. Throughput: 0: 2567.1, 1: 2558.3. Samples: 170844696. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:28,445][86177] Avg episode reward: [(0, '-544.330'), (1, '-642.140')] -[2023-11-28 08:57:28,517][87424] Updated weights for policy 0, policy_version 333849 (0.0008) -[2023-11-28 08:57:29,877][87426] Updated weights for policy 1, policy_version 333480 (0.0011) -[2023-11-28 08:57:30,258][87426] Updated weights for policy 1, policy_version 333490 (0.0012) -[2023-11-28 08:57:30,475][87424] Updated weights for policy 0, policy_version 333859 (0.0009) -[2023-11-28 08:57:30,636][87426] Updated weights for policy 1, policy_version 333500 (0.0011) -[2023-11-28 08:57:30,844][87424] Updated weights for policy 0, policy_version 333869 (0.0009) -[2023-11-28 08:57:31,229][87424] Updated weights for policy 0, policy_version 333879 (0.0008) -[2023-11-28 08:57:33,050][87426] Updated weights for policy 1, policy_version 333510 (0.0011) -[2023-11-28 08:57:33,422][87426] Updated weights for policy 1, policy_version 333520 (0.0011) -[2023-11-28 08:57:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5051.7, 300 sec: 5359.5). Total num frames: 170852352. Throughput: 0: 2562.8, 1: 2543.2. Samples: 170868056. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:33,445][86177] Avg episode reward: [(0, '-532.460'), (1, '-677.030')] -[2023-11-28 08:57:33,806][87426] Updated weights for policy 1, policy_version 333530 (0.0009) -[2023-11-28 08:57:33,809][87424] Updated weights for policy 0, policy_version 333889 (0.0009) -[2023-11-28 08:57:34,200][87424] Updated weights for policy 0, policy_version 333899 (0.0012) -[2023-11-28 08:57:34,574][87424] Updated weights for policy 0, policy_version 333909 (0.0012) -[2023-11-28 08:57:34,955][87424] Updated weights for policy 0, policy_version 333919 (0.0012) -[2023-11-28 08:57:35,863][87426] Updated weights for policy 1, policy_version 333540 (0.0010) -[2023-11-28 08:57:36,236][87426] Updated weights for policy 1, policy_version 333550 (0.0012) -[2023-11-28 08:57:36,608][87426] Updated weights for policy 1, policy_version 333560 (0.0012) -[2023-11-28 08:57:37,363][87424] Updated weights for policy 0, policy_version 333929 (0.0010) -[2023-11-28 08:57:37,747][87424] Updated weights for policy 0, policy_version 333939 (0.0010) -[2023-11-28 08:57:38,124][87424] Updated weights for policy 0, policy_version 333949 (0.0010) -[2023-11-28 08:57:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 170885120. Throughput: 0: 2558.5, 1: 2538.9. Samples: 170899468. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:38,445][86177] Avg episode reward: [(0, '-541.440'), (1, '-677.640')] -[2023-11-28 08:57:38,872][87426] Updated weights for policy 1, policy_version 333570 (0.0014) -[2023-11-28 08:57:39,256][87426] Updated weights for policy 1, policy_version 333580 (0.0011) -[2023-11-28 08:57:39,633][87426] Updated weights for policy 1, policy_version 333590 (0.0010) -[2023-11-28 08:57:40,008][87426] Updated weights for policy 1, policy_version 333600 (0.0009) -[2023-11-28 08:57:40,485][87424] Updated weights for policy 0, policy_version 333959 (0.0011) -[2023-11-28 08:57:40,872][87424] Updated weights for policy 0, policy_version 333969 (0.0012) -[2023-11-28 08:57:41,245][87424] Updated weights for policy 0, policy_version 333979 (0.0012) -[2023-11-28 08:57:42,430][87426] Updated weights for policy 1, policy_version 333610 (0.0010) -[2023-11-28 08:57:42,806][87426] Updated weights for policy 1, policy_version 333620 (0.0011) -[2023-11-28 08:57:43,180][87426] Updated weights for policy 1, policy_version 333630 (0.0010) -[2023-11-28 08:57:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 170909696. Throughput: 0: 2559.1, 1: 2553.2. Samples: 170922128. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:43,445][86177] Avg episode reward: [(0, '-581.230'), (1, '-615.540')] -[2023-11-28 08:57:43,626][87424] Updated weights for policy 0, policy_version 333989 (0.0011) -[2023-11-28 08:57:44,009][87424] Updated weights for policy 0, policy_version 333999 (0.0010) -[2023-11-28 08:57:44,386][87424] Updated weights for policy 0, policy_version 334009 (0.0010) -[2023-11-28 08:57:45,807][87426] Updated weights for policy 1, policy_version 333640 (0.0011) -[2023-11-28 08:57:46,189][87426] Updated weights for policy 1, policy_version 333650 (0.0011) -[2023-11-28 08:57:46,516][87424] Updated weights for policy 0, policy_version 334019 (0.0010) -[2023-11-28 08:57:46,567][87426] Updated weights for policy 1, policy_version 333660 (0.0008) -[2023-11-28 08:57:46,900][87424] Updated weights for policy 0, policy_version 334029 (0.0008) -[2023-11-28 08:57:47,288][87424] Updated weights for policy 0, policy_version 334039 (0.0007) -[2023-11-28 08:57:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5051.7, 300 sec: 5359.5). Total num frames: 170934272. Throughput: 0: 2552.9, 1: 2536.8. Samples: 170945716. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:48,446][86177] Avg episode reward: [(0, '-597.400'), (1, '-591.710')] -[2023-11-28 08:57:48,807][87426] Updated weights for policy 1, policy_version 333670 (0.0008) -[2023-11-28 08:57:49,187][87426] Updated weights for policy 1, policy_version 333680 (0.0010) -[2023-11-28 08:57:49,564][87426] Updated weights for policy 1, policy_version 333690 (0.0009) -[2023-11-28 08:57:49,619][87424] Updated weights for policy 0, policy_version 334049 (0.0008) -[2023-11-28 08:57:49,998][87424] Updated weights for policy 0, policy_version 334059 (0.0012) -[2023-11-28 08:57:50,382][87424] Updated weights for policy 0, policy_version 334069 (0.0012) -[2023-11-28 08:57:50,776][87424] Updated weights for policy 0, policy_version 334079 (0.0012) -[2023-11-28 08:57:51,873][87426] Updated weights for policy 1, policy_version 333700 (0.0009) -[2023-11-28 08:57:52,257][87426] Updated weights for policy 1, policy_version 333710 (0.0009) -[2023-11-28 08:57:52,637][87426] Updated weights for policy 1, policy_version 333720 (0.0009) -[2023-11-28 08:57:52,988][87424] Updated weights for policy 0, policy_version 334089 (0.0012) -[2023-11-28 08:57:53,370][87424] Updated weights for policy 0, policy_version 334099 (0.0009) -[2023-11-28 08:57:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5051.8, 300 sec: 5359.5). Total num frames: 170958848. Throughput: 0: 2547.3, 1: 2555.4. Samples: 170978280. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:53,445][86177] Avg episode reward: [(0, '-600.640'), (1, '-557.270')] -[2023-11-28 08:57:53,757][87424] Updated weights for policy 0, policy_version 334109 (0.0011) -[2023-11-28 08:57:54,626][87426] Updated weights for policy 1, policy_version 333730 (0.0011) -[2023-11-28 08:57:55,007][87426] Updated weights for policy 1, policy_version 333740 (0.0011) -[2023-11-28 08:57:55,401][87426] Updated weights for policy 1, policy_version 333750 (0.0011) -[2023-11-28 08:57:55,780][87426] Updated weights for policy 1, policy_version 333760 (0.0012) -[2023-11-28 08:57:56,065][87424] Updated weights for policy 0, policy_version 334119 (0.0012) -[2023-11-28 08:57:56,446][87424] Updated weights for policy 0, policy_version 334129 (0.0011) -[2023-11-28 08:57:56,831][87424] Updated weights for policy 0, policy_version 334139 (0.0012) -[2023-11-28 08:57:57,845][87426] Updated weights for policy 1, policy_version 333770 (0.0012) -[2023-11-28 08:57:58,222][87426] Updated weights for policy 1, policy_version 333780 (0.0011) -[2023-11-28 08:57:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5051.7, 300 sec: 5331.7). Total num frames: 170983424. Throughput: 0: 2555.7, 1: 2596.4. Samples: 171002828. Policy #0 lag: (min: 31.0, avg: 39.8, max: 63.0) -[2023-11-28 08:57:58,445][86177] Avg episode reward: [(0, '-593.400'), (1, '-532.940')] -[2023-11-28 08:57:58,599][87426] Updated weights for policy 1, policy_version 333790 (0.0011) -[2023-11-28 08:57:59,110][87424] Updated weights for policy 0, policy_version 334149 (0.0012) -[2023-11-28 08:57:59,490][87424] Updated weights for policy 0, policy_version 334159 (0.0012) -[2023-11-28 08:57:59,871][87424] Updated weights for policy 0, policy_version 334169 (0.0011) -[2023-11-28 08:58:00,340][87426] Updated weights for policy 1, policy_version 333800 (0.0012) -[2023-11-28 08:58:00,723][87426] Updated weights for policy 1, policy_version 333810 (0.0011) -[2023-11-28 08:58:01,099][87426] Updated weights for policy 1, policy_version 333820 (0.0010) -[2023-11-28 08:58:01,994][87424] Updated weights for policy 0, policy_version 334179 (0.0012) -[2023-11-28 08:58:02,371][87424] Updated weights for policy 0, policy_version 334189 (0.0012) -[2023-11-28 08:58:02,747][87424] Updated weights for policy 0, policy_version 334199 (0.0012) -[2023-11-28 08:58:03,335][87426] Updated weights for policy 1, policy_version 333830 (0.0010) -[2023-11-28 08:58:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 171016192. Throughput: 0: 2604.6, 1: 2617.2. Samples: 171027624. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:03,445][86177] Avg episode reward: [(0, '-590.270'), (1, '-531.200')] -[2023-11-28 08:58:03,712][87426] Updated weights for policy 1, policy_version 333840 (0.0012) -[2023-11-28 08:58:04,094][87426] Updated weights for policy 1, policy_version 333850 (0.0012) -[2023-11-28 08:58:04,702][87424] Updated weights for policy 0, policy_version 334209 (0.0011) -[2023-11-28 08:58:05,084][87424] Updated weights for policy 0, policy_version 334219 (0.0012) -[2023-11-28 08:58:05,458][87424] Updated weights for policy 0, policy_version 334229 (0.0009) -[2023-11-28 08:58:05,840][87424] Updated weights for policy 0, policy_version 334239 (0.0007) -[2023-11-28 08:58:06,655][87426] Updated weights for policy 1, policy_version 333860 (0.0012) -[2023-11-28 08:58:07,037][87426] Updated weights for policy 1, policy_version 333870 (0.0012) -[2023-11-28 08:58:07,414][87426] Updated weights for policy 1, policy_version 333880 (0.0011) -[2023-11-28 08:58:08,242][87424] Updated weights for policy 0, policy_version 334249 (0.0008) -[2023-11-28 08:58:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5188.5, 300 sec: 5359.5). Total num frames: 171040768. Throughput: 0: 2629.7, 1: 2638.8. Samples: 171059080. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:08,445][86177] Avg episode reward: [(0, '-535.960'), (1, '-546.120')] -[2023-11-28 08:58:08,623][87424] Updated weights for policy 0, policy_version 334259 (0.0010) -[2023-11-28 08:58:09,013][87424] Updated weights for policy 0, policy_version 334269 (0.0008) -[2023-11-28 08:58:09,232][87426] Updated weights for policy 1, policy_version 333890 (0.0011) -[2023-11-28 08:58:09,612][87426] Updated weights for policy 1, policy_version 333900 (0.0012) -[2023-11-28 08:58:09,980][87426] Updated weights for policy 1, policy_version 333910 (0.0011) -[2023-11-28 08:58:10,366][87426] Updated weights for policy 1, policy_version 333920 (0.0011) -[2023-11-28 08:58:11,470][87424] Updated weights for policy 0, policy_version 334279 (0.0008) -[2023-11-28 08:58:11,853][87424] Updated weights for policy 0, policy_version 334289 (0.0010) -[2023-11-28 08:58:12,238][87424] Updated weights for policy 0, policy_version 334299 (0.0009) -[2023-11-28 08:58:12,982][87426] Updated weights for policy 1, policy_version 333930 (0.0010) -[2023-11-28 08:58:13,362][87426] Updated weights for policy 1, policy_version 333940 (0.0008) -[2023-11-28 08:58:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 171065344. Throughput: 0: 2645.2, 1: 2651.0. Samples: 171083028. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:13,445][86177] Avg episode reward: [(0, '-542.100'), (1, '-560.740')] -[2023-11-28 08:58:13,742][87426] Updated weights for policy 1, policy_version 333950 (0.0010) -[2023-11-28 08:58:14,073][87424] Updated weights for policy 0, policy_version 334309 (0.0011) -[2023-11-28 08:58:14,451][87424] Updated weights for policy 0, policy_version 334319 (0.0008) -[2023-11-28 08:58:14,833][87424] Updated weights for policy 0, policy_version 334329 (0.0007) -[2023-11-28 08:58:15,931][87426] Updated weights for policy 1, policy_version 333960 (0.0011) -[2023-11-28 08:58:16,302][87426] Updated weights for policy 1, policy_version 333970 (0.0011) -[2023-11-28 08:58:16,686][87426] Updated weights for policy 1, policy_version 333980 (0.0011) -[2023-11-28 08:58:17,084][87424] Updated weights for policy 0, policy_version 334339 (0.0007) -[2023-11-28 08:58:17,467][87424] Updated weights for policy 0, policy_version 334349 (0.0009) -[2023-11-28 08:58:17,848][87424] Updated weights for policy 0, policy_version 334359 (0.0009) -[2023-11-28 08:58:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 171098112. Throughput: 0: 2649.4, 1: 2664.2. Samples: 171107168. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:18,445][86177] Avg episode reward: [(0, '-546.650'), (1, '-608.180')] -[2023-11-28 08:58:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000334368_85598208.pth... -[2023-11-28 08:58:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000333984_85499904.pth... -[2023-11-28 08:58:18,490][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000331872_84959232.pth -[2023-11-28 08:58:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000331520_84869120.pth -[2023-11-28 08:58:18,858][87426] Updated weights for policy 1, policy_version 333990 (0.0009) -[2023-11-28 08:58:19,226][87426] Updated weights for policy 1, policy_version 334000 (0.0008) -[2023-11-28 08:58:19,610][87426] Updated weights for policy 1, policy_version 334010 (0.0007) -[2023-11-28 08:58:20,266][87424] Updated weights for policy 0, policy_version 334369 (0.0008) -[2023-11-28 08:58:20,646][87424] Updated weights for policy 0, policy_version 334379 (0.0009) -[2023-11-28 08:58:21,022][87424] Updated weights for policy 0, policy_version 334389 (0.0009) -[2023-11-28 08:58:21,406][87424] Updated weights for policy 0, policy_version 334399 (0.0010) -[2023-11-28 08:58:21,902][87426] Updated weights for policy 1, policy_version 334020 (0.0010) -[2023-11-28 08:58:22,285][87426] Updated weights for policy 1, policy_version 334030 (0.0012) -[2023-11-28 08:58:22,658][87426] Updated weights for policy 1, policy_version 334040 (0.0008) -[2023-11-28 08:58:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 171122688. Throughput: 0: 2631.6, 1: 2660.3. Samples: 171137600. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:23,445][86177] Avg episode reward: [(0, '-584.650'), (1, '-619.810')] -[2023-11-28 08:58:24,010][87424] Updated weights for policy 0, policy_version 334409 (0.0012) -[2023-11-28 08:58:24,377][87424] Updated weights for policy 0, policy_version 334419 (0.0008) -[2023-11-28 08:58:24,590][87426] Updated weights for policy 1, policy_version 334050 (0.0009) -[2023-11-28 08:58:24,760][87424] Updated weights for policy 0, policy_version 334429 (0.0008) -[2023-11-28 08:58:24,968][87426] Updated weights for policy 1, policy_version 334060 (0.0012) -[2023-11-28 08:58:25,342][87426] Updated weights for policy 1, policy_version 334070 (0.0012) -[2023-11-28 08:58:25,717][87426] Updated weights for policy 1, policy_version 334080 (0.0012) -[2023-11-28 08:58:26,941][87424] Updated weights for policy 0, policy_version 334439 (0.0010) -[2023-11-28 08:58:27,317][87424] Updated weights for policy 0, policy_version 334449 (0.0009) -[2023-11-28 08:58:27,697][87424] Updated weights for policy 0, policy_version 334459 (0.0007) -[2023-11-28 08:58:28,316][87426] Updated weights for policy 1, policy_version 334090 (0.0011) -[2023-11-28 08:58:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171147264. Throughput: 0: 2640.8, 1: 2694.3. Samples: 171162208. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:28,445][86177] Avg episode reward: [(0, '-581.390'), (1, '-633.840')] -[2023-11-28 08:58:28,706][87426] Updated weights for policy 1, policy_version 334100 (0.0012) -[2023-11-28 08:58:29,079][87426] Updated weights for policy 1, policy_version 334110 (0.0012) -[2023-11-28 08:58:29,667][87424] Updated weights for policy 0, policy_version 334469 (0.0008) -[2023-11-28 08:58:30,045][87424] Updated weights for policy 0, policy_version 334479 (0.0010) -[2023-11-28 08:58:30,426][87424] Updated weights for policy 0, policy_version 334489 (0.0010) -[2023-11-28 08:58:31,039][87426] Updated weights for policy 1, policy_version 334120 (0.0012) -[2023-11-28 08:58:31,412][87426] Updated weights for policy 1, policy_version 334130 (0.0012) -[2023-11-28 08:58:31,790][87426] Updated weights for policy 1, policy_version 334140 (0.0012) -[2023-11-28 08:58:32,267][87424] Updated weights for policy 0, policy_version 334499 (0.0009) -[2023-11-28 08:58:32,644][87424] Updated weights for policy 0, policy_version 334509 (0.0008) -[2023-11-28 08:58:33,031][87424] Updated weights for policy 0, policy_version 334519 (0.0010) -[2023-11-28 08:58:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 171180032. Throughput: 0: 2675.2, 1: 2700.5. Samples: 171187620. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:33,445][86177] Avg episode reward: [(0, '-583.920'), (1, '-624.890')] -[2023-11-28 08:58:33,792][87426] Updated weights for policy 1, policy_version 334150 (0.0011) -[2023-11-28 08:58:34,179][87426] Updated weights for policy 1, policy_version 334160 (0.0009) -[2023-11-28 08:58:34,566][87426] Updated weights for policy 1, policy_version 334170 (0.0007) -[2023-11-28 08:58:35,444][87424] Updated weights for policy 0, policy_version 334529 (0.0010) -[2023-11-28 08:58:35,823][87424] Updated weights for policy 0, policy_version 334539 (0.0012) -[2023-11-28 08:58:36,199][87424] Updated weights for policy 0, policy_version 334549 (0.0011) -[2023-11-28 08:58:36,585][87424] Updated weights for policy 0, policy_version 334559 (0.0012) -[2023-11-28 08:58:36,766][87426] Updated weights for policy 1, policy_version 334180 (0.0011) -[2023-11-28 08:58:37,142][87426] Updated weights for policy 1, policy_version 334190 (0.0012) -[2023-11-28 08:58:37,516][87426] Updated weights for policy 1, policy_version 334200 (0.0012) -[2023-11-28 08:58:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 171204608. Throughput: 0: 2675.3, 1: 2703.6. Samples: 171220332. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:38,445][86177] Avg episode reward: [(0, '-578.520'), (1, '-603.620')] -[2023-11-28 08:58:39,055][87424] Updated weights for policy 0, policy_version 334569 (0.0011) -[2023-11-28 08:58:39,443][87424] Updated weights for policy 0, policy_version 334579 (0.0008) -[2023-11-28 08:58:39,829][87424] Updated weights for policy 0, policy_version 334589 (0.0008) -[2023-11-28 08:58:39,890][87426] Updated weights for policy 1, policy_version 334210 (0.0009) -[2023-11-28 08:58:40,262][87426] Updated weights for policy 1, policy_version 334220 (0.0010) -[2023-11-28 08:58:40,644][87426] Updated weights for policy 1, policy_version 334230 (0.0008) -[2023-11-28 08:58:41,024][87426] Updated weights for policy 1, policy_version 334240 (0.0009) -[2023-11-28 08:58:41,838][87424] Updated weights for policy 0, policy_version 334599 (0.0011) -[2023-11-28 08:58:42,199][87424] Updated weights for policy 0, policy_version 334609 (0.0012) -[2023-11-28 08:58:42,584][87424] Updated weights for policy 0, policy_version 334619 (0.0012) -[2023-11-28 08:58:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 171229184. Throughput: 0: 2691.5, 1: 2679.6. Samples: 171244528. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:43,446][86177] Avg episode reward: [(0, '-556.970'), (1, '-575.470')] -[2023-11-28 08:58:43,552][87426] Updated weights for policy 1, policy_version 334250 (0.0011) -[2023-11-28 08:58:43,931][87426] Updated weights for policy 1, policy_version 334260 (0.0007) -[2023-11-28 08:58:44,313][87426] Updated weights for policy 1, policy_version 334270 (0.0008) -[2023-11-28 08:58:45,146][87424] Updated weights for policy 0, policy_version 334629 (0.0011) -[2023-11-28 08:58:45,533][87424] Updated weights for policy 0, policy_version 334639 (0.0010) -[2023-11-28 08:58:45,907][87424] Updated weights for policy 0, policy_version 334649 (0.0009) -[2023-11-28 08:58:46,882][87426] Updated weights for policy 1, policy_version 334280 (0.0012) -[2023-11-28 08:58:47,264][87426] Updated weights for policy 1, policy_version 334290 (0.0012) -[2023-11-28 08:58:47,645][87426] Updated weights for policy 1, policy_version 334300 (0.0012) -[2023-11-28 08:58:48,140][87424] Updated weights for policy 0, policy_version 334659 (0.0011) -[2023-11-28 08:58:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171253760. Throughput: 0: 2660.1, 1: 2652.5. Samples: 171266692. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:48,445][86177] Avg episode reward: [(0, '-587.000'), (1, '-541.980')] -[2023-11-28 08:58:48,514][87424] Updated weights for policy 0, policy_version 334669 (0.0012) -[2023-11-28 08:58:48,884][87424] Updated weights for policy 0, policy_version 334679 (0.0012) -[2023-11-28 08:58:49,783][87426] Updated weights for policy 1, policy_version 334310 (0.0012) -[2023-11-28 08:58:50,162][87426] Updated weights for policy 1, policy_version 334320 (0.0008) -[2023-11-28 08:58:50,547][87426] Updated weights for policy 1, policy_version 334330 (0.0008) -[2023-11-28 08:58:51,272][87424] Updated weights for policy 0, policy_version 334689 (0.0011) -[2023-11-28 08:58:51,682][87424] Updated weights for policy 0, policy_version 334699 (0.0011) -[2023-11-28 08:58:52,061][87424] Updated weights for policy 0, policy_version 334709 (0.0012) -[2023-11-28 08:58:52,441][87426] Updated weights for policy 1, policy_version 334340 (0.0011) -[2023-11-28 08:58:52,443][87424] Updated weights for policy 0, policy_version 334719 (0.0012) -[2023-11-28 08:58:52,821][87426] Updated weights for policy 1, policy_version 334350 (0.0010) -[2023-11-28 08:58:53,205][87426] Updated weights for policy 1, policy_version 334360 (0.0008) -[2023-11-28 08:58:53,446][86177] Fps is (10 sec: 4914.6, 60 sec: 5324.7, 300 sec: 5303.9). Total num frames: 171278336. Throughput: 0: 2661.5, 1: 2649.0. Samples: 171298060. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:53,446][86177] Avg episode reward: [(0, '-587.850'), (1, '-540.290')] -[2023-11-28 08:58:54,687][87424] Updated weights for policy 0, policy_version 334729 (0.0008) -[2023-11-28 08:58:55,065][87424] Updated weights for policy 0, policy_version 334739 (0.0008) -[2023-11-28 08:58:55,452][87424] Updated weights for policy 0, policy_version 334749 (0.0007) -[2023-11-28 08:58:55,731][87426] Updated weights for policy 1, policy_version 334370 (0.0009) -[2023-11-28 08:58:56,105][87426] Updated weights for policy 1, policy_version 334380 (0.0008) -[2023-11-28 08:58:56,481][87426] Updated weights for policy 1, policy_version 334390 (0.0009) -[2023-11-28 08:58:56,856][87426] Updated weights for policy 1, policy_version 334400 (0.0007) -[2023-11-28 08:58:57,384][87424] Updated weights for policy 0, policy_version 334759 (0.0010) -[2023-11-28 08:58:57,759][87424] Updated weights for policy 0, policy_version 334769 (0.0012) -[2023-11-28 08:58:58,151][87424] Updated weights for policy 0, policy_version 334779 (0.0012) -[2023-11-28 08:58:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 171311104. Throughput: 0: 2663.2, 1: 2644.1. Samples: 171321856. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:58:58,445][86177] Avg episode reward: [(0, '-596.090'), (1, '-538.050')] -[2023-11-28 08:58:58,894][87426] Updated weights for policy 1, policy_version 334410 (0.0008) -[2023-11-28 08:58:59,256][87426] Updated weights for policy 1, policy_version 334420 (0.0012) -[2023-11-28 08:58:59,629][87426] Updated weights for policy 1, policy_version 334430 (0.0010) -[2023-11-28 08:59:00,510][87424] Updated weights for policy 0, policy_version 334789 (0.0011) -[2023-11-28 08:59:00,890][87424] Updated weights for policy 0, policy_version 334799 (0.0009) -[2023-11-28 08:59:01,271][87424] Updated weights for policy 0, policy_version 334809 (0.0009) -[2023-11-28 08:59:01,958][87426] Updated weights for policy 1, policy_version 334440 (0.0011) -[2023-11-28 08:59:02,334][87426] Updated weights for policy 1, policy_version 334450 (0.0012) -[2023-11-28 08:59:02,708][87426] Updated weights for policy 1, policy_version 334460 (0.0008) -[2023-11-28 08:59:03,340][87424] Updated weights for policy 0, policy_version 334819 (0.0011) -[2023-11-28 08:59:03,444][86177] Fps is (10 sec: 5735.1, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171335680. Throughput: 0: 2651.7, 1: 2658.3. Samples: 171346120. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:59:03,446][86177] Avg episode reward: [(0, '-622.560'), (1, '-520.730')] -[2023-11-28 08:59:03,716][87424] Updated weights for policy 0, policy_version 334829 (0.0012) -[2023-11-28 08:59:04,097][87424] Updated weights for policy 0, policy_version 334839 (0.0011) -[2023-11-28 08:59:05,263][87426] Updated weights for policy 1, policy_version 334470 (0.0011) -[2023-11-28 08:59:05,646][87426] Updated weights for policy 1, policy_version 334480 (0.0012) -[2023-11-28 08:59:06,018][87426] Updated weights for policy 1, policy_version 334490 (0.0011) -[2023-11-28 08:59:06,171][87424] Updated weights for policy 0, policy_version 334849 (0.0012) -[2023-11-28 08:59:06,550][87424] Updated weights for policy 0, policy_version 334859 (0.0011) -[2023-11-28 08:59:06,932][87424] Updated weights for policy 0, policy_version 334869 (0.0011) -[2023-11-28 08:59:07,312][87424] Updated weights for policy 0, policy_version 334879 (0.0011) -[2023-11-28 08:59:08,173][87426] Updated weights for policy 1, policy_version 334500 (0.0008) -[2023-11-28 08:59:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 171360256. Throughput: 0: 2684.6, 1: 2688.5. Samples: 171379392. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:59:08,445][86177] Avg episode reward: [(0, '-643.130'), (1, '-524.310')] -[2023-11-28 08:59:08,543][87426] Updated weights for policy 1, policy_version 334510 (0.0009) -[2023-11-28 08:59:08,916][87426] Updated weights for policy 1, policy_version 334520 (0.0009) -[2023-11-28 08:59:09,624][87424] Updated weights for policy 0, policy_version 334889 (0.0012) -[2023-11-28 08:59:10,016][87424] Updated weights for policy 0, policy_version 334899 (0.0012) -[2023-11-28 08:59:10,405][87424] Updated weights for policy 0, policy_version 334909 (0.0012) -[2023-11-28 08:59:10,899][87426] Updated weights for policy 1, policy_version 334530 (0.0008) -[2023-11-28 08:59:11,276][87426] Updated weights for policy 1, policy_version 334540 (0.0012) -[2023-11-28 08:59:11,653][87426] Updated weights for policy 1, policy_version 334550 (0.0012) -[2023-11-28 08:59:12,042][87426] Updated weights for policy 1, policy_version 334560 (0.0012) -[2023-11-28 08:59:12,487][87424] Updated weights for policy 0, policy_version 334919 (0.0010) -[2023-11-28 08:59:12,871][87424] Updated weights for policy 0, policy_version 334929 (0.0010) -[2023-11-28 08:59:13,262][87424] Updated weights for policy 0, policy_version 334939 (0.0011) -[2023-11-28 08:59:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 171393024. Throughput: 0: 2681.2, 1: 2667.8. Samples: 171402916. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:59:13,446][86177] Avg episode reward: [(0, '-621.410'), (1, '-537.010')] -[2023-11-28 08:59:14,062][87426] Updated weights for policy 1, policy_version 334570 (0.0012) -[2023-11-28 08:59:14,441][87426] Updated weights for policy 1, policy_version 334580 (0.0012) -[2023-11-28 08:59:14,812][87426] Updated weights for policy 1, policy_version 334590 (0.0012) -[2023-11-28 08:59:15,293][87424] Updated weights for policy 0, policy_version 334949 (0.0011) -[2023-11-28 08:59:15,669][87424] Updated weights for policy 0, policy_version 334959 (0.0008) -[2023-11-28 08:59:16,060][87424] Updated weights for policy 0, policy_version 334969 (0.0012) -[2023-11-28 08:59:17,228][87426] Updated weights for policy 1, policy_version 334600 (0.0012) -[2023-11-28 08:59:17,614][87426] Updated weights for policy 1, policy_version 334610 (0.0012) -[2023-11-28 08:59:17,884][87424] Updated weights for policy 0, policy_version 334979 (0.0011) -[2023-11-28 08:59:17,983][87426] Updated weights for policy 1, policy_version 334620 (0.0011) -[2023-11-28 08:59:18,258][87424] Updated weights for policy 0, policy_version 334989 (0.0010) -[2023-11-28 08:59:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171417600. Throughput: 0: 2662.8, 1: 2661.2. Samples: 171427200. Policy #0 lag: (min: 31.0, avg: 37.2, max: 63.0) -[2023-11-28 08:59:18,445][86177] Avg episode reward: [(0, '-632.360'), (1, '-524.870')] -[2023-11-28 08:59:18,643][87424] Updated weights for policy 0, policy_version 334999 (0.0007) -[2023-11-28 08:59:20,037][87426] Updated weights for policy 1, policy_version 334630 (0.0010) -[2023-11-28 08:59:20,432][87426] Updated weights for policy 1, policy_version 334640 (0.0008) -[2023-11-28 08:59:20,784][87424] Updated weights for policy 0, policy_version 335009 (0.0012) -[2023-11-28 08:59:20,808][87426] Updated weights for policy 1, policy_version 334650 (0.0008) -[2023-11-28 08:59:21,176][87424] Updated weights for policy 0, policy_version 335019 (0.0011) -[2023-11-28 08:59:21,560][87424] Updated weights for policy 0, policy_version 335029 (0.0012) -[2023-11-28 08:59:21,934][87424] Updated weights for policy 0, policy_version 335039 (0.0012) -[2023-11-28 08:59:22,914][87426] Updated weights for policy 1, policy_version 334660 (0.0010) -[2023-11-28 08:59:23,292][87426] Updated weights for policy 1, policy_version 334670 (0.0012) -[2023-11-28 08:59:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 171442176. Throughput: 0: 2683.6, 1: 2648.4. Samples: 171460272. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:59:23,445][86177] Avg episode reward: [(0, '-611.530'), (1, '-521.070')] -[2023-11-28 08:59:23,679][87426] Updated weights for policy 1, policy_version 334680 (0.0012) -[2023-11-28 08:59:24,200][87424] Updated weights for policy 0, policy_version 335049 (0.0011) -[2023-11-28 08:59:24,593][87424] Updated weights for policy 0, policy_version 335059 (0.0012) -[2023-11-28 08:59:24,977][87424] Updated weights for policy 0, policy_version 335069 (0.0012) -[2023-11-28 08:59:25,833][87426] Updated weights for policy 1, policy_version 334690 (0.0011) -[2023-11-28 08:59:26,213][87426] Updated weights for policy 1, policy_version 334700 (0.0008) -[2023-11-28 08:59:26,587][87426] Updated weights for policy 1, policy_version 334710 (0.0007) -[2023-11-28 08:59:26,968][87426] Updated weights for policy 1, policy_version 334720 (0.0007) -[2023-11-28 08:59:27,264][87424] Updated weights for policy 0, policy_version 335079 (0.0012) -[2023-11-28 08:59:27,633][87424] Updated weights for policy 0, policy_version 335089 (0.0012) -[2023-11-28 08:59:28,021][87424] Updated weights for policy 0, policy_version 335099 (0.0012) -[2023-11-28 08:59:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5331.7). Total num frames: 171474944. Throughput: 0: 2674.2, 1: 2699.7. Samples: 171486352. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:59:28,445][86177] Avg episode reward: [(0, '-616.120'), (1, '-527.470')] -[2023-11-28 08:59:28,852][87426] Updated weights for policy 1, policy_version 334730 (0.0008) -[2023-11-28 08:59:29,227][87426] Updated weights for policy 1, policy_version 334740 (0.0011) -[2023-11-28 08:59:29,602][87426] Updated weights for policy 1, policy_version 334750 (0.0011) -[2023-11-28 08:59:30,658][87424] Updated weights for policy 0, policy_version 335109 (0.0012) -[2023-11-28 08:59:31,048][87424] Updated weights for policy 0, policy_version 335119 (0.0012) -[2023-11-28 08:59:31,433][87424] Updated weights for policy 0, policy_version 335129 (0.0011) -[2023-11-28 08:59:31,701][87426] Updated weights for policy 1, policy_version 334760 (0.0011) -[2023-11-28 08:59:32,092][87426] Updated weights for policy 1, policy_version 334770 (0.0010) -[2023-11-28 08:59:32,461][87426] Updated weights for policy 1, policy_version 334780 (0.0009) -[2023-11-28 08:59:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171499520. Throughput: 0: 2685.9, 1: 2743.2. Samples: 171511000. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:59:33,445][86177] Avg episode reward: [(0, '-611.260'), (1, '-514.110')] -[2023-11-28 08:59:33,684][87424] Updated weights for policy 0, policy_version 335139 (0.0011) -[2023-11-28 08:59:34,067][87424] Updated weights for policy 0, policy_version 335149 (0.0007) -[2023-11-28 08:59:34,393][87426] Updated weights for policy 1, policy_version 334790 (0.0007) -[2023-11-28 08:59:34,460][87424] Updated weights for policy 0, policy_version 335159 (0.0007) -[2023-11-28 08:59:34,770][87426] Updated weights for policy 1, policy_version 334800 (0.0008) -[2023-11-28 08:59:35,143][87426] Updated weights for policy 1, policy_version 334810 (0.0008) -[2023-11-28 08:59:36,365][87424] Updated weights for policy 0, policy_version 335169 (0.0008) -[2023-11-28 08:59:36,744][87424] Updated weights for policy 0, policy_version 335179 (0.0011) -[2023-11-28 08:59:37,127][87424] Updated weights for policy 0, policy_version 335189 (0.0010) -[2023-11-28 08:59:37,503][87424] Updated weights for policy 0, policy_version 335199 (0.0012) -[2023-11-28 08:59:37,633][87426] Updated weights for policy 1, policy_version 334820 (0.0009) -[2023-11-28 08:59:38,009][87426] Updated weights for policy 1, policy_version 334830 (0.0012) -[2023-11-28 08:59:38,392][87426] Updated weights for policy 1, policy_version 334840 (0.0012) -[2023-11-28 08:59:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 171524096. Throughput: 0: 2697.9, 1: 2768.8. Samples: 171544052. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:59:38,445][86177] Avg episode reward: [(0, '-616.950'), (1, '-515.450')] -[2023-11-28 08:59:39,418][87424] Updated weights for policy 0, policy_version 335209 (0.0012) -[2023-11-28 08:59:39,802][87424] Updated weights for policy 0, policy_version 335219 (0.0012) -[2023-11-28 08:59:40,188][87424] Updated weights for policy 0, policy_version 335229 (0.0012) -[2023-11-28 08:59:40,825][87426] Updated weights for policy 1, policy_version 334850 (0.0010) -[2023-11-28 08:59:41,210][87426] Updated weights for policy 1, policy_version 334860 (0.0008) -[2023-11-28 08:59:41,578][87426] Updated weights for policy 1, policy_version 334870 (0.0008) -[2023-11-28 08:59:41,960][87426] Updated weights for policy 1, policy_version 334880 (0.0011) -[2023-11-28 08:59:42,470][87424] Updated weights for policy 0, policy_version 335239 (0.0012) -[2023-11-28 08:59:42,866][87424] Updated weights for policy 0, policy_version 335249 (0.0012) -[2023-11-28 08:59:43,238][87424] Updated weights for policy 0, policy_version 335259 (0.0012) -[2023-11-28 08:59:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5331.7). Total num frames: 171556864. Throughput: 0: 2708.3, 1: 2772.7. Samples: 171568500. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:59:43,445][86177] Avg episode reward: [(0, '-611.630'), (1, '-541.140')] -[2023-11-28 08:59:44,129][87426] Updated weights for policy 1, policy_version 334890 (0.0007) -[2023-11-28 08:59:44,508][87426] Updated weights for policy 1, policy_version 334900 (0.0007) -[2023-11-28 08:59:44,886][87426] Updated weights for policy 1, policy_version 334910 (0.0007) -[2023-11-28 08:59:45,745][87424] Updated weights for policy 0, policy_version 335269 (0.0012) -[2023-11-28 08:59:46,127][87424] Updated weights for policy 0, policy_version 335279 (0.0011) -[2023-11-28 08:59:46,508][87424] Updated weights for policy 0, policy_version 335289 (0.0011) -[2023-11-28 08:59:47,079][87426] Updated weights for policy 1, policy_version 334920 (0.0011) -[2023-11-28 08:59:47,462][87426] Updated weights for policy 1, policy_version 334930 (0.0012) -[2023-11-28 08:59:47,835][87426] Updated weights for policy 1, policy_version 334940 (0.0012) -[2023-11-28 08:59:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 171581440. Throughput: 0: 2718.5, 1: 2753.4. Samples: 171592356. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:59:48,446][86177] Avg episode reward: [(0, '-591.220'), (1, '-530.770')] -[2023-11-28 08:59:48,747][87424] Updated weights for policy 0, policy_version 335299 (0.0011) -[2023-11-28 08:59:49,131][87424] Updated weights for policy 0, policy_version 335309 (0.0012) -[2023-11-28 08:59:49,506][87424] Updated weights for policy 0, policy_version 335319 (0.0012) -[2023-11-28 08:59:50,022][87426] Updated weights for policy 1, policy_version 334950 (0.0011) -[2023-11-28 08:59:50,403][87426] Updated weights for policy 1, policy_version 334960 (0.0012) -[2023-11-28 08:59:50,776][87426] Updated weights for policy 1, policy_version 334970 (0.0007) -[2023-11-28 08:59:51,716][87424] Updated weights for policy 0, policy_version 335329 (0.0012) -[2023-11-28 08:59:52,096][87424] Updated weights for policy 0, policy_version 335339 (0.0010) -[2023-11-28 08:59:52,476][87424] Updated weights for policy 0, policy_version 335349 (0.0008) -[2023-11-28 08:59:52,861][87424] Updated weights for policy 0, policy_version 335359 (0.0008) -[2023-11-28 08:59:53,176][87426] Updated weights for policy 1, policy_version 334980 (0.0009) -[2023-11-28 08:59:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.5, 300 sec: 5304.0). Total num frames: 171606016. Throughput: 0: 2730.2, 1: 2726.0. Samples: 171624924. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:59:53,445][86177] Avg episode reward: [(0, '-623.600'), (1, '-522.800')] -[2023-11-28 08:59:53,559][87426] Updated weights for policy 1, policy_version 334990 (0.0011) -[2023-11-28 08:59:53,932][87426] Updated weights for policy 1, policy_version 335000 (0.0012) -[2023-11-28 08:59:55,331][87424] Updated weights for policy 0, policy_version 335369 (0.0010) -[2023-11-28 08:59:55,711][87424] Updated weights for policy 0, policy_version 335379 (0.0007) -[2023-11-28 08:59:56,107][87424] Updated weights for policy 0, policy_version 335389 (0.0007) -[2023-11-28 08:59:56,298][87426] Updated weights for policy 1, policy_version 335010 (0.0010) -[2023-11-28 08:59:56,675][87426] Updated weights for policy 1, policy_version 335020 (0.0012) -[2023-11-28 08:59:57,046][87426] Updated weights for policy 1, policy_version 335030 (0.0012) -[2023-11-28 08:59:57,424][87426] Updated weights for policy 1, policy_version 335040 (0.0009) -[2023-11-28 08:59:58,221][87424] Updated weights for policy 0, policy_version 335399 (0.0008) -[2023-11-28 08:59:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171630592. Throughput: 0: 2736.5, 1: 2715.3. Samples: 171648248. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 08:59:58,445][86177] Avg episode reward: [(0, '-598.200'), (1, '-528.360')] -[2023-11-28 08:59:58,597][87424] Updated weights for policy 0, policy_version 335409 (0.0008) -[2023-11-28 08:59:58,979][87424] Updated weights for policy 0, policy_version 335419 (0.0008) -[2023-11-28 08:59:59,850][87426] Updated weights for policy 1, policy_version 335050 (0.0011) -[2023-11-28 09:00:00,225][87426] Updated weights for policy 1, policy_version 335060 (0.0011) -[2023-11-28 09:00:00,607][87426] Updated weights for policy 1, policy_version 335070 (0.0011) -[2023-11-28 09:00:01,232][87424] Updated weights for policy 0, policy_version 335429 (0.0011) -[2023-11-28 09:00:01,620][87424] Updated weights for policy 0, policy_version 335439 (0.0012) -[2023-11-28 09:00:02,002][87424] Updated weights for policy 0, policy_version 335449 (0.0011) -[2023-11-28 09:00:02,970][87426] Updated weights for policy 1, policy_version 335080 (0.0012) -[2023-11-28 09:00:03,342][87426] Updated weights for policy 1, policy_version 335090 (0.0012) -[2023-11-28 09:00:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 171655168. Throughput: 0: 2716.5, 1: 2704.9. Samples: 171671164. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:00:03,446][86177] Avg episode reward: [(0, '-612.150'), (1, '-504.210')] -[2023-11-28 09:00:03,714][87426] Updated weights for policy 1, policy_version 335100 (0.0012) -[2023-11-28 09:00:03,809][87424] Updated weights for policy 0, policy_version 335459 (0.0011) -[2023-11-28 09:00:04,190][87424] Updated weights for policy 0, policy_version 335469 (0.0012) -[2023-11-28 09:00:04,579][87424] Updated weights for policy 0, policy_version 335479 (0.0012) -[2023-11-28 09:00:05,628][87426] Updated weights for policy 1, policy_version 335110 (0.0011) -[2023-11-28 09:00:06,008][87426] Updated weights for policy 1, policy_version 335120 (0.0011) -[2023-11-28 09:00:06,285][87424] Updated weights for policy 0, policy_version 335489 (0.0012) -[2023-11-28 09:00:06,387][87426] Updated weights for policy 1, policy_version 335130 (0.0012) -[2023-11-28 09:00:06,666][87424] Updated weights for policy 0, policy_version 335499 (0.0011) -[2023-11-28 09:00:07,050][87424] Updated weights for policy 0, policy_version 335509 (0.0011) -[2023-11-28 09:00:07,428][87424] Updated weights for policy 0, policy_version 335519 (0.0011) -[2023-11-28 09:00:08,340][87426] Updated weights for policy 1, policy_version 335140 (0.0011) -[2023-11-28 09:00:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5304.0). Total num frames: 171687936. Throughput: 0: 2689.9, 1: 2700.4. Samples: 171702832. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:00:08,445][86177] Avg episode reward: [(0, '-683.200'), (1, '-503.110')] -[2023-11-28 09:00:08,721][87426] Updated weights for policy 1, policy_version 335150 (0.0011) -[2023-11-28 09:00:09,102][87426] Updated weights for policy 1, policy_version 335160 (0.0010) -[2023-11-28 09:00:09,568][87424] Updated weights for policy 0, policy_version 335529 (0.0011) -[2023-11-28 09:00:09,941][87424] Updated weights for policy 0, policy_version 335539 (0.0012) -[2023-11-28 09:00:10,331][87424] Updated weights for policy 0, policy_version 335549 (0.0011) -[2023-11-28 09:00:11,554][87426] Updated weights for policy 1, policy_version 335170 (0.0011) -[2023-11-28 09:00:11,931][87426] Updated weights for policy 1, policy_version 335180 (0.0012) -[2023-11-28 09:00:12,323][87426] Updated weights for policy 1, policy_version 335190 (0.0012) -[2023-11-28 09:00:12,693][87426] Updated weights for policy 1, policy_version 335200 (0.0010) -[2023-11-28 09:00:12,806][87424] Updated weights for policy 0, policy_version 335559 (0.0011) -[2023-11-28 09:00:13,189][87424] Updated weights for policy 0, policy_version 335569 (0.0012) -[2023-11-28 09:00:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171712512. Throughput: 0: 2694.0, 1: 2667.4. Samples: 171727612. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:00:13,445][86177] Avg episode reward: [(0, '-661.950'), (1, '-521.160')] -[2023-11-28 09:00:13,572][87424] Updated weights for policy 0, policy_version 335579 (0.0012) -[2023-11-28 09:00:14,610][87426] Updated weights for policy 1, policy_version 335210 (0.0008) -[2023-11-28 09:00:15,004][87426] Updated weights for policy 1, policy_version 335220 (0.0011) -[2023-11-28 09:00:15,398][87426] Updated weights for policy 1, policy_version 335230 (0.0011) -[2023-11-28 09:00:16,132][87424] Updated weights for policy 0, policy_version 335589 (0.0012) -[2023-11-28 09:00:16,513][87424] Updated weights for policy 0, policy_version 335599 (0.0012) -[2023-11-28 09:00:16,892][87424] Updated weights for policy 0, policy_version 335609 (0.0009) -[2023-11-28 09:00:17,447][87426] Updated weights for policy 1, policy_version 335240 (0.0012) -[2023-11-28 09:00:17,817][87426] Updated weights for policy 1, policy_version 335250 (0.0007) -[2023-11-28 09:00:18,200][87426] Updated weights for policy 1, policy_version 335260 (0.0007) -[2023-11-28 09:00:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 171745280. Throughput: 0: 2681.8, 1: 2653.2. Samples: 171751076. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:00:18,446][86177] Avg episode reward: [(0, '-671.670'), (1, '-516.510')] -[2023-11-28 09:00:18,459][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000335616_85917696.pth... -[2023-11-28 09:00:18,459][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000335264_85827584.pth... -[2023-11-28 09:00:18,491][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000332768_85188608.pth -[2023-11-28 09:00:18,505][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000333152_85286912.pth -[2023-11-28 09:00:19,421][87424] Updated weights for policy 0, policy_version 335619 (0.0008) -[2023-11-28 09:00:19,797][87424] Updated weights for policy 0, policy_version 335629 (0.0011) -[2023-11-28 09:00:20,173][87424] Updated weights for policy 0, policy_version 335639 (0.0012) -[2023-11-28 09:00:20,707][87426] Updated weights for policy 1, policy_version 335270 (0.0010) -[2023-11-28 09:00:21,083][87426] Updated weights for policy 1, policy_version 335280 (0.0012) -[2023-11-28 09:00:21,460][87426] Updated weights for policy 1, policy_version 335290 (0.0012) -[2023-11-28 09:00:22,437][87424] Updated weights for policy 0, policy_version 335649 (0.0012) -[2023-11-28 09:00:22,815][87424] Updated weights for policy 0, policy_version 335659 (0.0012) -[2023-11-28 09:00:23,192][87424] Updated weights for policy 0, policy_version 335669 (0.0011) -[2023-11-28 09:00:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 171761664. Throughput: 0: 2673.1, 1: 2623.4. Samples: 171782392. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:00:23,445][86177] Avg episode reward: [(0, '-690.640'), (1, '-518.470')] -[2023-11-28 09:00:23,487][87426] Updated weights for policy 1, policy_version 335300 (0.0011) -[2023-11-28 09:00:23,571][87424] Updated weights for policy 0, policy_version 335679 (0.0010) -[2023-11-28 09:00:23,873][87426] Updated weights for policy 1, policy_version 335310 (0.0009) -[2023-11-28 09:00:24,248][87426] Updated weights for policy 1, policy_version 335320 (0.0010) -[2023-11-28 09:00:25,567][87424] Updated weights for policy 0, policy_version 335689 (0.0008) -[2023-11-28 09:00:25,947][87424] Updated weights for policy 0, policy_version 335699 (0.0007) -[2023-11-28 09:00:26,333][87424] Updated weights for policy 0, policy_version 335709 (0.0007) -[2023-11-28 09:00:26,548][87426] Updated weights for policy 1, policy_version 335330 (0.0008) -[2023-11-28 09:00:26,932][87426] Updated weights for policy 1, policy_version 335340 (0.0012) -[2023-11-28 09:00:27,309][87426] Updated weights for policy 1, policy_version 335350 (0.0012) -[2023-11-28 09:00:27,683][87426] Updated weights for policy 1, policy_version 335360 (0.0011) -[2023-11-28 09:00:28,348][87424] Updated weights for policy 0, policy_version 335719 (0.0008) -[2023-11-28 09:00:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171794432. Throughput: 0: 2653.9, 1: 2636.9. Samples: 171806588. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:00:28,446][86177] Avg episode reward: [(0, '-590.370'), (1, '-518.450')] -[2023-11-28 09:00:28,718][87424] Updated weights for policy 0, policy_version 335729 (0.0007) -[2023-11-28 09:00:29,109][87424] Updated weights for policy 0, policy_version 335739 (0.0010) -[2023-11-28 09:00:30,311][87426] Updated weights for policy 1, policy_version 335370 (0.0012) -[2023-11-28 09:00:30,689][87426] Updated weights for policy 1, policy_version 335380 (0.0012) -[2023-11-28 09:00:31,068][87426] Updated weights for policy 1, policy_version 335390 (0.0011) -[2023-11-28 09:00:31,489][87424] Updated weights for policy 0, policy_version 335749 (0.0010) -[2023-11-28 09:00:31,868][87424] Updated weights for policy 0, policy_version 335759 (0.0010) -[2023-11-28 09:00:32,253][87424] Updated weights for policy 0, policy_version 335769 (0.0009) -[2023-11-28 09:00:33,393][87426] Updated weights for policy 1, policy_version 335400 (0.0011) -[2023-11-28 09:00:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 171819008. Throughput: 0: 2643.6, 1: 2637.2. Samples: 171829992. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:00:33,445][86177] Avg episode reward: [(0, '-593.750'), (1, '-508.280')] -[2023-11-28 09:00:33,772][87426] Updated weights for policy 1, policy_version 335410 (0.0011) -[2023-11-28 09:00:34,155][87426] Updated weights for policy 1, policy_version 335420 (0.0011) -[2023-11-28 09:00:34,267][87424] Updated weights for policy 0, policy_version 335779 (0.0008) -[2023-11-28 09:00:34,646][87424] Updated weights for policy 0, policy_version 335789 (0.0012) -[2023-11-28 09:00:35,029][87424] Updated weights for policy 0, policy_version 335799 (0.0012) -[2023-11-28 09:00:36,108][87426] Updated weights for policy 1, policy_version 335430 (0.0008) -[2023-11-28 09:00:36,479][87426] Updated weights for policy 1, policy_version 335440 (0.0010) -[2023-11-28 09:00:36,857][87426] Updated weights for policy 1, policy_version 335450 (0.0012) -[2023-11-28 09:00:37,509][87424] Updated weights for policy 0, policy_version 335809 (0.0012) -[2023-11-28 09:00:37,896][87424] Updated weights for policy 0, policy_version 335819 (0.0012) -[2023-11-28 09:00:38,289][87424] Updated weights for policy 0, policy_version 335829 (0.0012) -[2023-11-28 09:00:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 171843584. Throughput: 0: 2628.8, 1: 2653.2. Samples: 171862616. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:00:38,445][86177] Avg episode reward: [(0, '-622.000'), (1, '-511.220')] -[2023-11-28 09:00:38,667][87424] Updated weights for policy 0, policy_version 335839 (0.0012) -[2023-11-28 09:00:38,760][87426] Updated weights for policy 1, policy_version 335460 (0.0011) -[2023-11-28 09:00:39,138][87426] Updated weights for policy 1, policy_version 335470 (0.0012) -[2023-11-28 09:00:39,512][87426] Updated weights for policy 1, policy_version 335480 (0.0009) -[2023-11-28 09:00:40,638][87424] Updated weights for policy 0, policy_version 335849 (0.0012) -[2023-11-28 09:00:41,016][87424] Updated weights for policy 0, policy_version 335859 (0.0012) -[2023-11-28 09:00:41,392][87424] Updated weights for policy 0, policy_version 335869 (0.0010) -[2023-11-28 09:00:41,802][87426] Updated weights for policy 1, policy_version 335490 (0.0011) -[2023-11-28 09:00:42,185][87426] Updated weights for policy 1, policy_version 335500 (0.0011) -[2023-11-28 09:00:42,562][87426] Updated weights for policy 1, policy_version 335510 (0.0011) -[2023-11-28 09:00:42,928][87426] Updated weights for policy 1, policy_version 335520 (0.0010) -[2023-11-28 09:00:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171876352. Throughput: 0: 2631.8, 1: 2676.0. Samples: 171887100. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:00:43,445][86177] Avg episode reward: [(0, '-595.770'), (1, '-513.410')] -[2023-11-28 09:00:43,967][87424] Updated weights for policy 0, policy_version 335879 (0.0008) -[2023-11-28 09:00:44,349][87424] Updated weights for policy 0, policy_version 335889 (0.0008) -[2023-11-28 09:00:44,726][87424] Updated weights for policy 0, policy_version 335899 (0.0011) -[2023-11-28 09:00:44,981][87426] Updated weights for policy 1, policy_version 335530 (0.0010) -[2023-11-28 09:00:45,356][87426] Updated weights for policy 1, policy_version 335540 (0.0009) -[2023-11-28 09:00:45,738][87426] Updated weights for policy 1, policy_version 335550 (0.0008) -[2023-11-28 09:00:47,196][87424] Updated weights for policy 0, policy_version 335909 (0.0012) -[2023-11-28 09:00:47,576][87424] Updated weights for policy 0, policy_version 335919 (0.0012) -[2023-11-28 09:00:47,953][87424] Updated weights for policy 0, policy_version 335929 (0.0010) -[2023-11-28 09:00:48,118][87426] Updated weights for policy 1, policy_version 335560 (0.0008) -[2023-11-28 09:00:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 171900928. Throughput: 0: 2620.6, 1: 2709.9. Samples: 171911036. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:00:48,445][86177] Avg episode reward: [(0, '-592.020'), (1, '-518.510')] -[2023-11-28 09:00:48,498][87426] Updated weights for policy 1, policy_version 335570 (0.0009) -[2023-11-28 09:00:48,887][87426] Updated weights for policy 1, policy_version 335580 (0.0008) -[2023-11-28 09:00:50,461][87424] Updated weights for policy 0, policy_version 335939 (0.0007) -[2023-11-28 09:00:50,842][87424] Updated weights for policy 0, policy_version 335949 (0.0010) -[2023-11-28 09:00:50,844][87426] Updated weights for policy 1, policy_version 335590 (0.0011) -[2023-11-28 09:00:51,219][87424] Updated weights for policy 0, policy_version 335959 (0.0010) -[2023-11-28 09:00:51,220][87426] Updated weights for policy 1, policy_version 335600 (0.0011) -[2023-11-28 09:00:51,598][87426] Updated weights for policy 1, policy_version 335610 (0.0009) -[2023-11-28 09:00:53,414][87424] Updated weights for policy 0, policy_version 335969 (0.0009) -[2023-11-28 09:00:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 171925504. Throughput: 0: 2611.3, 1: 2712.1. Samples: 171942384. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:00:53,445][86177] Avg episode reward: [(0, '-590.000'), (1, '-507.170')] -[2023-11-28 09:00:53,761][87426] Updated weights for policy 1, policy_version 335620 (0.0011) -[2023-11-28 09:00:53,790][87424] Updated weights for policy 0, policy_version 335979 (0.0011) -[2023-11-28 09:00:54,135][87426] Updated weights for policy 1, policy_version 335630 (0.0011) -[2023-11-28 09:00:54,179][87424] Updated weights for policy 0, policy_version 335989 (0.0011) -[2023-11-28 09:00:54,513][87426] Updated weights for policy 1, policy_version 335640 (0.0010) -[2023-11-28 09:00:54,564][87424] Updated weights for policy 0, policy_version 335999 (0.0011) -[2023-11-28 09:00:56,749][87424] Updated weights for policy 0, policy_version 336009 (0.0008) -[2023-11-28 09:00:56,787][87426] Updated weights for policy 1, policy_version 335650 (0.0008) -[2023-11-28 09:00:57,135][87424] Updated weights for policy 0, policy_version 336019 (0.0007) -[2023-11-28 09:00:57,169][87426] Updated weights for policy 1, policy_version 335660 (0.0009) -[2023-11-28 09:00:57,523][87424] Updated weights for policy 0, policy_version 336029 (0.0007) -[2023-11-28 09:00:57,552][87426] Updated weights for policy 1, policy_version 335670 (0.0007) -[2023-11-28 09:00:57,934][87426] Updated weights for policy 1, policy_version 335680 (0.0008) -[2023-11-28 09:00:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 171958272. Throughput: 0: 2624.4, 1: 2703.8. Samples: 171967380. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:00:58,445][86177] Avg episode reward: [(0, '-594.370'), (1, '-505.120')] -[2023-11-28 09:00:59,325][87424] Updated weights for policy 0, policy_version 336039 (0.0011) -[2023-11-28 09:00:59,708][87424] Updated weights for policy 0, policy_version 336049 (0.0012) -[2023-11-28 09:01:00,038][87426] Updated weights for policy 1, policy_version 335690 (0.0010) -[2023-11-28 09:01:00,099][87424] Updated weights for policy 0, policy_version 336059 (0.0012) -[2023-11-28 09:01:00,416][87426] Updated weights for policy 1, policy_version 335700 (0.0010) -[2023-11-28 09:01:00,796][87426] Updated weights for policy 1, policy_version 335710 (0.0010) -[2023-11-28 09:01:02,270][87424] Updated weights for policy 0, policy_version 336069 (0.0011) -[2023-11-28 09:01:02,653][87424] Updated weights for policy 0, policy_version 336079 (0.0010) -[2023-11-28 09:01:03,043][87424] Updated weights for policy 0, policy_version 336089 (0.0009) -[2023-11-28 09:01:03,276][87426] Updated weights for policy 1, policy_version 335720 (0.0011) -[2023-11-28 09:01:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 171982848. Throughput: 0: 2690.7, 1: 2698.8. Samples: 171993600. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:03,445][86177] Avg episode reward: [(0, '-569.260'), (1, '-501.220')] -[2023-11-28 09:01:03,650][87426] Updated weights for policy 1, policy_version 335730 (0.0012) -[2023-11-28 09:01:04,022][87426] Updated weights for policy 1, policy_version 335740 (0.0011) -[2023-11-28 09:01:05,160][87424] Updated weights for policy 0, policy_version 336099 (0.0011) -[2023-11-28 09:01:05,531][87424] Updated weights for policy 0, policy_version 336109 (0.0012) -[2023-11-28 09:01:05,919][87424] Updated weights for policy 0, policy_version 336119 (0.0011) -[2023-11-28 09:01:06,465][87426] Updated weights for policy 1, policy_version 335750 (0.0011) -[2023-11-28 09:01:06,829][87426] Updated weights for policy 1, policy_version 335760 (0.0011) -[2023-11-28 09:01:07,206][87426] Updated weights for policy 1, policy_version 335770 (0.0011) -[2023-11-28 09:01:08,036][87424] Updated weights for policy 0, policy_version 336129 (0.0012) -[2023-11-28 09:01:08,426][87424] Updated weights for policy 0, policy_version 336139 (0.0012) -[2023-11-28 09:01:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 172007424. Throughput: 0: 2709.5, 1: 2708.9. Samples: 172026220. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:08,445][86177] Avg episode reward: [(0, '-570.150'), (1, '-500.490')] -[2023-11-28 09:01:08,810][87424] Updated weights for policy 0, policy_version 336149 (0.0011) -[2023-11-28 09:01:09,102][87426] Updated weights for policy 1, policy_version 335780 (0.0010) -[2023-11-28 09:01:09,191][87424] Updated weights for policy 0, policy_version 336159 (0.0012) -[2023-11-28 09:01:09,490][87426] Updated weights for policy 1, policy_version 335790 (0.0012) -[2023-11-28 09:01:09,864][87426] Updated weights for policy 1, policy_version 335800 (0.0010) -[2023-11-28 09:01:11,716][87424] Updated weights for policy 0, policy_version 336169 (0.0012) -[2023-11-28 09:01:12,093][87424] Updated weights for policy 0, policy_version 336179 (0.0010) -[2023-11-28 09:01:12,358][87426] Updated weights for policy 1, policy_version 335810 (0.0009) -[2023-11-28 09:01:12,487][87424] Updated weights for policy 0, policy_version 336189 (0.0008) -[2023-11-28 09:01:12,742][87426] Updated weights for policy 1, policy_version 335820 (0.0010) -[2023-11-28 09:01:13,122][87426] Updated weights for policy 1, policy_version 335830 (0.0010) -[2023-11-28 09:01:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 172032000. Throughput: 0: 2706.2, 1: 2695.4. Samples: 172049660. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:13,445][86177] Avg episode reward: [(0, '-570.040'), (1, '-502.160')] -[2023-11-28 09:01:13,504][87426] Updated weights for policy 1, policy_version 335840 (0.0008) -[2023-11-28 09:01:14,663][87424] Updated weights for policy 0, policy_version 336199 (0.0011) -[2023-11-28 09:01:15,044][87424] Updated weights for policy 0, policy_version 336209 (0.0012) -[2023-11-28 09:01:15,426][87424] Updated weights for policy 0, policy_version 336219 (0.0011) -[2023-11-28 09:01:16,069][87426] Updated weights for policy 1, policy_version 335850 (0.0008) -[2023-11-28 09:01:16,449][87426] Updated weights for policy 1, policy_version 335860 (0.0007) -[2023-11-28 09:01:16,831][87426] Updated weights for policy 1, policy_version 335870 (0.0007) -[2023-11-28 09:01:17,550][87424] Updated weights for policy 0, policy_version 336229 (0.0011) -[2023-11-28 09:01:17,930][87424] Updated weights for policy 0, policy_version 336239 (0.0008) -[2023-11-28 09:01:18,321][87424] Updated weights for policy 0, policy_version 336249 (0.0007) -[2023-11-28 09:01:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5304.0). Total num frames: 172056576. Throughput: 0: 2711.1, 1: 2703.4. Samples: 172073644. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:18,446][86177] Avg episode reward: [(0, '-576.880'), (1, '-504.970')] -[2023-11-28 09:01:19,106][87426] Updated weights for policy 1, policy_version 335880 (0.0010) -[2023-11-28 09:01:19,482][87426] Updated weights for policy 1, policy_version 335890 (0.0011) -[2023-11-28 09:01:19,860][87426] Updated weights for policy 1, policy_version 335900 (0.0010) -[2023-11-28 09:01:20,472][87424] Updated weights for policy 0, policy_version 336259 (0.0008) -[2023-11-28 09:01:20,854][87424] Updated weights for policy 0, policy_version 336269 (0.0011) -[2023-11-28 09:01:21,233][87424] Updated weights for policy 0, policy_version 336279 (0.0011) -[2023-11-28 09:01:22,048][87426] Updated weights for policy 1, policy_version 335910 (0.0009) -[2023-11-28 09:01:22,434][87426] Updated weights for policy 1, policy_version 335920 (0.0010) -[2023-11-28 09:01:22,813][87426] Updated weights for policy 1, policy_version 335930 (0.0011) -[2023-11-28 09:01:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 172089344. Throughput: 0: 2697.0, 1: 2674.1. Samples: 172104316. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:23,445][86177] Avg episode reward: [(0, '-560.120'), (1, '-503.040')] -[2023-11-28 09:01:23,714][87424] Updated weights for policy 0, policy_version 336289 (0.0011) -[2023-11-28 09:01:24,096][87424] Updated weights for policy 0, policy_version 336299 (0.0012) -[2023-11-28 09:01:24,502][87424] Updated weights for policy 0, policy_version 336309 (0.0012) -[2023-11-28 09:01:24,758][87426] Updated weights for policy 1, policy_version 335940 (0.0010) -[2023-11-28 09:01:24,871][87424] Updated weights for policy 0, policy_version 336319 (0.0012) -[2023-11-28 09:01:25,136][87426] Updated weights for policy 1, policy_version 335950 (0.0011) -[2023-11-28 09:01:25,518][87426] Updated weights for policy 1, policy_version 335960 (0.0012) -[2023-11-28 09:01:26,622][87424] Updated weights for policy 0, policy_version 336329 (0.0011) -[2023-11-28 09:01:27,003][87424] Updated weights for policy 0, policy_version 336339 (0.0012) -[2023-11-28 09:01:27,386][87424] Updated weights for policy 0, policy_version 336349 (0.0008) -[2023-11-28 09:01:28,022][87426] Updated weights for policy 1, policy_version 335970 (0.0011) -[2023-11-28 09:01:28,398][87426] Updated weights for policy 1, policy_version 335980 (0.0007) -[2023-11-28 09:01:28,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 172113920. Throughput: 0: 2707.5, 1: 2686.8. Samples: 172129848. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:28,446][86177] Avg episode reward: [(0, '-555.430'), (1, '-503.540')] -[2023-11-28 09:01:28,777][87426] Updated weights for policy 1, policy_version 335990 (0.0007) -[2023-11-28 09:01:29,155][87426] Updated weights for policy 1, policy_version 336000 (0.0009) -[2023-11-28 09:01:29,173][87424] Updated weights for policy 0, policy_version 336359 (0.0007) -[2023-11-28 09:01:29,563][87424] Updated weights for policy 0, policy_version 336369 (0.0008) -[2023-11-28 09:01:29,948][87424] Updated weights for policy 0, policy_version 336379 (0.0010) -[2023-11-28 09:01:31,474][87426] Updated weights for policy 1, policy_version 336010 (0.0012) -[2023-11-28 09:01:31,695][87424] Updated weights for policy 0, policy_version 336389 (0.0012) -[2023-11-28 09:01:31,847][87426] Updated weights for policy 1, policy_version 336020 (0.0012) -[2023-11-28 09:01:32,073][87424] Updated weights for policy 0, policy_version 336399 (0.0009) -[2023-11-28 09:01:32,233][87426] Updated weights for policy 1, policy_version 336030 (0.0009) -[2023-11-28 09:01:32,452][87424] Updated weights for policy 0, policy_version 336409 (0.0009) -[2023-11-28 09:01:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 172146688. Throughput: 0: 2767.3, 1: 2667.7. Samples: 172155612. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:33,445][86177] Avg episode reward: [(0, '-569.320'), (1, '-501.250')] -[2023-11-28 09:01:34,493][87426] Updated weights for policy 1, policy_version 336040 (0.0010) -[2023-11-28 09:01:34,871][87426] Updated weights for policy 1, policy_version 336050 (0.0009) -[2023-11-28 09:01:34,908][87424] Updated weights for policy 0, policy_version 336419 (0.0007) -[2023-11-28 09:01:35,250][87426] Updated weights for policy 1, policy_version 336060 (0.0011) -[2023-11-28 09:01:35,286][87424] Updated weights for policy 0, policy_version 336429 (0.0010) -[2023-11-28 09:01:35,672][87424] Updated weights for policy 0, policy_version 336439 (0.0008) -[2023-11-28 09:01:37,315][87426] Updated weights for policy 1, policy_version 336070 (0.0011) -[2023-11-28 09:01:37,688][87426] Updated weights for policy 1, policy_version 336080 (0.0011) -[2023-11-28 09:01:38,054][87424] Updated weights for policy 0, policy_version 336449 (0.0008) -[2023-11-28 09:01:38,065][87426] Updated weights for policy 1, policy_version 336090 (0.0011) -[2023-11-28 09:01:38,445][87424] Updated weights for policy 0, policy_version 336459 (0.0009) -[2023-11-28 09:01:38,446][86177] Fps is (10 sec: 5733.6, 60 sec: 5461.2, 300 sec: 5331.7). Total num frames: 172171264. Throughput: 0: 2799.0, 1: 2681.7. Samples: 172189024. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:38,447][86177] Avg episode reward: [(0, '-569.800'), (1, '-499.400')] -[2023-11-28 09:01:38,818][87424] Updated weights for policy 0, policy_version 336469 (0.0010) -[2023-11-28 09:01:39,199][87424] Updated weights for policy 0, policy_version 336479 (0.0012) -[2023-11-28 09:01:40,249][87426] Updated weights for policy 1, policy_version 336100 (0.0010) -[2023-11-28 09:01:40,638][87426] Updated weights for policy 1, policy_version 336110 (0.0012) -[2023-11-28 09:01:41,006][87426] Updated weights for policy 1, policy_version 336120 (0.0012) -[2023-11-28 09:01:41,356][87424] Updated weights for policy 0, policy_version 336489 (0.0009) -[2023-11-28 09:01:41,739][87424] Updated weights for policy 0, policy_version 336499 (0.0010) -[2023-11-28 09:01:42,120][87424] Updated weights for policy 0, policy_version 336509 (0.0010) -[2023-11-28 09:01:43,399][87426] Updated weights for policy 1, policy_version 336130 (0.0007) -[2023-11-28 09:01:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 172195840. Throughput: 0: 2785.9, 1: 2669.1. Samples: 172212856. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:43,445][86177] Avg episode reward: [(0, '-566.410'), (1, '-501.330')] -[2023-11-28 09:01:43,778][87426] Updated weights for policy 1, policy_version 336140 (0.0007) -[2023-11-28 09:01:44,152][87426] Updated weights for policy 1, policy_version 336150 (0.0008) -[2023-11-28 09:01:44,345][87424] Updated weights for policy 0, policy_version 336519 (0.0009) -[2023-11-28 09:01:44,527][87426] Updated weights for policy 1, policy_version 336160 (0.0009) -[2023-11-28 09:01:44,748][87424] Updated weights for policy 0, policy_version 336529 (0.0012) -[2023-11-28 09:01:45,123][87424] Updated weights for policy 0, policy_version 336539 (0.0012) -[2023-11-28 09:01:46,960][87426] Updated weights for policy 1, policy_version 336170 (0.0011) -[2023-11-28 09:01:47,182][87424] Updated weights for policy 0, policy_version 336549 (0.0012) -[2023-11-28 09:01:47,336][87426] Updated weights for policy 1, policy_version 336180 (0.0012) -[2023-11-28 09:01:47,566][87424] Updated weights for policy 0, policy_version 336559 (0.0010) -[2023-11-28 09:01:47,721][87426] Updated weights for policy 1, policy_version 336190 (0.0011) -[2023-11-28 09:01:47,936][87424] Updated weights for policy 0, policy_version 336569 (0.0011) -[2023-11-28 09:01:48,444][86177] Fps is (10 sec: 5735.3, 60 sec: 5461.3, 300 sec: 5331.8). Total num frames: 172228608. Throughput: 0: 2755.7, 1: 2653.8. Samples: 172237028. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:48,445][86177] Avg episode reward: [(0, '-569.800'), (1, '-503.370')] -[2023-11-28 09:01:49,478][87426] Updated weights for policy 1, policy_version 336200 (0.0011) -[2023-11-28 09:01:49,853][87426] Updated weights for policy 1, policy_version 336210 (0.0011) -[2023-11-28 09:01:49,994][87424] Updated weights for policy 0, policy_version 336579 (0.0012) -[2023-11-28 09:01:50,230][87426] Updated weights for policy 1, policy_version 336220 (0.0012) -[2023-11-28 09:01:50,374][87424] Updated weights for policy 0, policy_version 336589 (0.0012) -[2023-11-28 09:01:50,750][87424] Updated weights for policy 0, policy_version 336599 (0.0012) -[2023-11-28 09:01:52,725][87426] Updated weights for policy 1, policy_version 336230 (0.0012) -[2023-11-28 09:01:52,786][87424] Updated weights for policy 0, policy_version 336609 (0.0012) -[2023-11-28 09:01:53,103][87426] Updated weights for policy 1, policy_version 336240 (0.0011) -[2023-11-28 09:01:53,173][87424] Updated weights for policy 0, policy_version 336619 (0.0009) -[2023-11-28 09:01:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 172244992. Throughput: 0: 2735.2, 1: 2666.4. Samples: 172269292. Policy #0 lag: (min: 11.0, avg: 24.4, max: 43.0) -[2023-11-28 09:01:53,445][86177] Avg episode reward: [(0, '-564.370'), (1, '-502.410')] -[2023-11-28 09:01:53,489][87426] Updated weights for policy 1, policy_version 336250 (0.0011) -[2023-11-28 09:01:53,555][87424] Updated weights for policy 0, policy_version 336629 (0.0010) -[2023-11-28 09:01:53,922][87424] Updated weights for policy 0, policy_version 336639 (0.0010) -[2023-11-28 09:01:55,968][87426] Updated weights for policy 1, policy_version 336260 (0.0011) -[2023-11-28 09:01:56,343][87426] Updated weights for policy 1, policy_version 336270 (0.0011) -[2023-11-28 09:01:56,542][87424] Updated weights for policy 0, policy_version 336649 (0.0008) -[2023-11-28 09:01:56,719][87426] Updated weights for policy 1, policy_version 336280 (0.0011) -[2023-11-28 09:01:56,928][87424] Updated weights for policy 0, policy_version 336659 (0.0008) -[2023-11-28 09:01:57,319][87424] Updated weights for policy 0, policy_version 336669 (0.0012) -[2023-11-28 09:01:58,416][87426] Updated weights for policy 1, policy_version 336290 (0.0012) -[2023-11-28 09:01:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 172277760. Throughput: 0: 2717.9, 1: 2676.6. Samples: 172292412. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:01:58,445][86177] Avg episode reward: [(0, '-557.780'), (1, '-505.740')] -[2023-11-28 09:01:58,800][87426] Updated weights for policy 1, policy_version 336300 (0.0008) -[2023-11-28 09:01:59,186][87426] Updated weights for policy 1, policy_version 336310 (0.0008) -[2023-11-28 09:01:59,386][87424] Updated weights for policy 0, policy_version 336679 (0.0011) -[2023-11-28 09:01:59,557][87426] Updated weights for policy 1, policy_version 336320 (0.0009) -[2023-11-28 09:01:59,765][87424] Updated weights for policy 0, policy_version 336689 (0.0008) -[2023-11-28 09:02:00,143][87424] Updated weights for policy 0, policy_version 336699 (0.0008) -[2023-11-28 09:02:01,714][87426] Updated weights for policy 1, policy_version 336330 (0.0009) -[2023-11-28 09:02:02,092][87426] Updated weights for policy 1, policy_version 336340 (0.0008) -[2023-11-28 09:02:02,283][87424] Updated weights for policy 0, policy_version 336709 (0.0009) -[2023-11-28 09:02:02,476][87426] Updated weights for policy 1, policy_version 336350 (0.0011) -[2023-11-28 09:02:02,661][87424] Updated weights for policy 0, policy_version 336719 (0.0011) -[2023-11-28 09:02:03,035][87424] Updated weights for policy 0, policy_version 336729 (0.0012) -[2023-11-28 09:02:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5359.6). Total num frames: 172310528. Throughput: 0: 2744.4, 1: 2666.8. Samples: 172317144. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:03,445][86177] Avg episode reward: [(0, '-559.450'), (1, '-503.570')] -[2023-11-28 09:02:04,425][87426] Updated weights for policy 1, policy_version 336360 (0.0012) -[2023-11-28 09:02:04,804][87426] Updated weights for policy 1, policy_version 336370 (0.0012) -[2023-11-28 09:02:04,924][87424] Updated weights for policy 0, policy_version 336739 (0.0011) -[2023-11-28 09:02:05,188][87426] Updated weights for policy 1, policy_version 336380 (0.0010) -[2023-11-28 09:02:05,306][87424] Updated weights for policy 0, policy_version 336749 (0.0011) -[2023-11-28 09:02:05,685][87424] Updated weights for policy 0, policy_version 336759 (0.0008) -[2023-11-28 09:02:07,296][87426] Updated weights for policy 1, policy_version 336390 (0.0010) -[2023-11-28 09:02:07,671][87426] Updated weights for policy 1, policy_version 336400 (0.0012) -[2023-11-28 09:02:07,992][87424] Updated weights for policy 0, policy_version 336769 (0.0007) -[2023-11-28 09:02:08,050][87426] Updated weights for policy 1, policy_version 336410 (0.0010) -[2023-11-28 09:02:08,370][87424] Updated weights for policy 0, policy_version 336779 (0.0011) -[2023-11-28 09:02:08,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 172335104. Throughput: 0: 2773.1, 1: 2706.0. Samples: 172350880. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:08,446][86177] Avg episode reward: [(0, '-574.350'), (1, '-503.790')] -[2023-11-28 09:02:08,750][87424] Updated weights for policy 0, policy_version 336789 (0.0011) -[2023-11-28 09:02:09,129][87424] Updated weights for policy 0, policy_version 336799 (0.0009) -[2023-11-28 09:02:10,441][87426] Updated weights for policy 1, policy_version 336420 (0.0009) -[2023-11-28 09:02:10,821][87426] Updated weights for policy 1, policy_version 336430 (0.0012) -[2023-11-28 09:02:11,194][87426] Updated weights for policy 1, policy_version 336440 (0.0011) -[2023-11-28 09:02:11,504][87424] Updated weights for policy 0, policy_version 336809 (0.0011) -[2023-11-28 09:02:11,887][87424] Updated weights for policy 0, policy_version 336819 (0.0011) -[2023-11-28 09:02:12,269][87424] Updated weights for policy 0, policy_version 336829 (0.0009) -[2023-11-28 09:02:13,308][87426] Updated weights for policy 1, policy_version 336450 (0.0011) -[2023-11-28 09:02:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5359.5). Total num frames: 172359680. Throughput: 0: 2753.0, 1: 2684.9. Samples: 172374552. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:13,445][86177] Avg episode reward: [(0, '-577.500'), (1, '-520.300')] -[2023-11-28 09:02:13,679][87426] Updated weights for policy 1, policy_version 336460 (0.0016) -[2023-11-28 09:02:14,055][87426] Updated weights for policy 1, policy_version 336470 (0.0011) -[2023-11-28 09:02:14,434][87426] Updated weights for policy 1, policy_version 336480 (0.0012) -[2023-11-28 09:02:14,599][87424] Updated weights for policy 0, policy_version 336839 (0.0012) -[2023-11-28 09:02:14,972][87424] Updated weights for policy 0, policy_version 336849 (0.0012) -[2023-11-28 09:02:15,363][87424] Updated weights for policy 0, policy_version 336859 (0.0012) -[2023-11-28 09:02:16,524][87426] Updated weights for policy 1, policy_version 336490 (0.0010) -[2023-11-28 09:02:16,902][87426] Updated weights for policy 1, policy_version 336500 (0.0008) -[2023-11-28 09:02:17,286][87426] Updated weights for policy 1, policy_version 336510 (0.0007) -[2023-11-28 09:02:17,534][87424] Updated weights for policy 0, policy_version 336869 (0.0012) -[2023-11-28 09:02:17,910][87424] Updated weights for policy 0, policy_version 336879 (0.0011) -[2023-11-28 09:02:18,290][87424] Updated weights for policy 0, policy_version 336889 (0.0007) -[2023-11-28 09:02:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 172384256. Throughput: 0: 2725.7, 1: 2702.3. Samples: 172399872. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:18,445][86177] Avg episode reward: [(0, '-591.430'), (1, '-519.120')] -[2023-11-28 09:02:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000336512_86147072.pth... -[2023-11-28 09:02:18,488][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000333984_85499904.pth -[2023-11-28 09:02:18,555][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000336896_86245376.pth... -[2023-11-28 09:02:18,599][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000334368_85598208.pth -[2023-11-28 09:02:19,268][87426] Updated weights for policy 1, policy_version 336520 (0.0011) -[2023-11-28 09:02:19,645][87426] Updated weights for policy 1, policy_version 336530 (0.0010) -[2023-11-28 09:02:20,025][87426] Updated weights for policy 1, policy_version 336540 (0.0010) -[2023-11-28 09:02:20,275][87424] Updated weights for policy 0, policy_version 336899 (0.0009) -[2023-11-28 09:02:20,651][87424] Updated weights for policy 0, policy_version 336909 (0.0011) -[2023-11-28 09:02:21,032][87424] Updated weights for policy 0, policy_version 336919 (0.0011) -[2023-11-28 09:02:22,583][87426] Updated weights for policy 1, policy_version 336550 (0.0012) -[2023-11-28 09:02:22,962][87426] Updated weights for policy 1, policy_version 336560 (0.0012) -[2023-11-28 09:02:23,344][87426] Updated weights for policy 1, policy_version 336570 (0.0012) -[2023-11-28 09:02:23,410][87424] Updated weights for policy 0, policy_version 336929 (0.0009) -[2023-11-28 09:02:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 172408832. Throughput: 0: 2722.5, 1: 2682.6. Samples: 172432244. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:23,445][86177] Avg episode reward: [(0, '-667.040'), (1, '-534.920')] -[2023-11-28 09:02:23,783][87424] Updated weights for policy 0, policy_version 336939 (0.0008) -[2023-11-28 09:02:24,166][87424] Updated weights for policy 0, policy_version 336949 (0.0007) -[2023-11-28 09:02:24,546][87424] Updated weights for policy 0, policy_version 336959 (0.0008) -[2023-11-28 09:02:25,922][87426] Updated weights for policy 1, policy_version 336580 (0.0011) -[2023-11-28 09:02:26,188][87424] Updated weights for policy 0, policy_version 336969 (0.0009) -[2023-11-28 09:02:26,302][87426] Updated weights for policy 1, policy_version 336590 (0.0008) -[2023-11-28 09:02:26,577][87424] Updated weights for policy 0, policy_version 336979 (0.0008) -[2023-11-28 09:02:26,685][87426] Updated weights for policy 1, policy_version 336600 (0.0010) -[2023-11-28 09:02:26,957][87424] Updated weights for policy 0, policy_version 336989 (0.0010) -[2023-11-28 09:02:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 172441600. Throughput: 0: 2734.0, 1: 2687.2. Samples: 172456808. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:28,445][86177] Avg episode reward: [(0, '-669.620'), (1, '-538.030')] -[2023-11-28 09:02:28,489][87424] Updated weights for policy 0, policy_version 336999 (0.0007) -[2023-11-28 09:02:28,611][87426] Updated weights for policy 1, policy_version 336610 (0.0008) -[2023-11-28 09:02:28,873][87424] Updated weights for policy 0, policy_version 337009 (0.0008) -[2023-11-28 09:02:28,999][87426] Updated weights for policy 1, policy_version 336620 (0.0008) -[2023-11-28 09:02:29,262][87424] Updated weights for policy 0, policy_version 337019 (0.0011) -[2023-11-28 09:02:29,374][87426] Updated weights for policy 1, policy_version 336630 (0.0010) -[2023-11-28 09:02:29,748][87426] Updated weights for policy 1, policy_version 336640 (0.0008) -[2023-11-28 09:02:31,713][87424] Updated weights for policy 0, policy_version 337029 (0.0010) -[2023-11-28 09:02:31,835][87426] Updated weights for policy 1, policy_version 336650 (0.0012) -[2023-11-28 09:02:32,091][87424] Updated weights for policy 0, policy_version 337039 (0.0009) -[2023-11-28 09:02:32,211][87426] Updated weights for policy 1, policy_version 336660 (0.0011) -[2023-11-28 09:02:32,464][87424] Updated weights for policy 0, policy_version 337049 (0.0011) -[2023-11-28 09:02:32,590][87426] Updated weights for policy 1, policy_version 336670 (0.0008) -[2023-11-28 09:02:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172474368. Throughput: 0: 2740.4, 1: 2702.0. Samples: 172481940. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:33,445][86177] Avg episode reward: [(0, '-636.370'), (1, '-520.380')] -[2023-11-28 09:02:34,477][87424] Updated weights for policy 0, policy_version 337059 (0.0012) -[2023-11-28 09:02:34,848][87426] Updated weights for policy 1, policy_version 336680 (0.0009) -[2023-11-28 09:02:34,872][87424] Updated weights for policy 0, policy_version 337069 (0.0012) -[2023-11-28 09:02:35,228][87426] Updated weights for policy 1, policy_version 336690 (0.0011) -[2023-11-28 09:02:35,242][87424] Updated weights for policy 0, policy_version 337079 (0.0012) -[2023-11-28 09:02:35,608][87426] Updated weights for policy 1, policy_version 336700 (0.0009) -[2023-11-28 09:02:37,529][87424] Updated weights for policy 0, policy_version 337089 (0.0012) -[2023-11-28 09:02:37,572][87426] Updated weights for policy 1, policy_version 336710 (0.0009) -[2023-11-28 09:02:37,911][87424] Updated weights for policy 0, policy_version 337099 (0.0012) -[2023-11-28 09:02:37,950][87426] Updated weights for policy 1, policy_version 336720 (0.0009) -[2023-11-28 09:02:38,292][87424] Updated weights for policy 0, policy_version 337109 (0.0012) -[2023-11-28 09:02:38,329][87426] Updated weights for policy 1, policy_version 336730 (0.0007) -[2023-11-28 09:02:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.9, 300 sec: 5359.5). Total num frames: 172490752. Throughput: 0: 2769.1, 1: 2692.0. Samples: 172515044. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:38,446][86177] Avg episode reward: [(0, '-625.520'), (1, '-528.560')] -[2023-11-28 09:02:38,680][87424] Updated weights for policy 0, policy_version 337119 (0.0010) -[2023-11-28 09:02:40,610][87426] Updated weights for policy 1, policy_version 336740 (0.0009) -[2023-11-28 09:02:40,781][87424] Updated weights for policy 0, policy_version 337129 (0.0011) -[2023-11-28 09:02:40,977][87426] Updated weights for policy 1, policy_version 336750 (0.0012) -[2023-11-28 09:02:41,160][87424] Updated weights for policy 0, policy_version 337139 (0.0012) -[2023-11-28 09:02:41,359][87426] Updated weights for policy 1, policy_version 336760 (0.0008) -[2023-11-28 09:02:41,540][87424] Updated weights for policy 0, policy_version 337149 (0.0011) -[2023-11-28 09:02:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172523520. Throughput: 0: 2784.3, 1: 2684.6. Samples: 172538512. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:43,445][86177] Avg episode reward: [(0, '-542.660'), (1, '-531.360')] -[2023-11-28 09:02:43,657][87424] Updated weights for policy 0, policy_version 337159 (0.0009) -[2023-11-28 09:02:43,970][87426] Updated weights for policy 1, policy_version 336770 (0.0009) -[2023-11-28 09:02:44,042][87424] Updated weights for policy 0, policy_version 337169 (0.0010) -[2023-11-28 09:02:44,345][87426] Updated weights for policy 1, policy_version 336780 (0.0008) -[2023-11-28 09:02:44,426][87424] Updated weights for policy 0, policy_version 337179 (0.0011) -[2023-11-28 09:02:44,723][87426] Updated weights for policy 1, policy_version 336790 (0.0009) -[2023-11-28 09:02:45,100][87426] Updated weights for policy 1, policy_version 336800 (0.0008) -[2023-11-28 09:02:46,535][87424] Updated weights for policy 0, policy_version 337189 (0.0011) -[2023-11-28 09:02:46,906][87424] Updated weights for policy 0, policy_version 337199 (0.0011) -[2023-11-28 09:02:47,295][87424] Updated weights for policy 0, policy_version 337209 (0.0012) -[2023-11-28 09:02:47,437][87426] Updated weights for policy 1, policy_version 336810 (0.0011) -[2023-11-28 09:02:47,815][87426] Updated weights for policy 1, policy_version 336820 (0.0011) -[2023-11-28 09:02:48,189][87426] Updated weights for policy 1, policy_version 336830 (0.0009) -[2023-11-28 09:02:48,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 172556288. Throughput: 0: 2779.2, 1: 2692.4. Samples: 172563368. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:48,445][86177] Avg episode reward: [(0, '-563.610'), (1, '-526.180')] -[2023-11-28 09:02:49,519][87424] Updated weights for policy 0, policy_version 337219 (0.0012) -[2023-11-28 09:02:49,896][87424] Updated weights for policy 0, policy_version 337229 (0.0012) -[2023-11-28 09:02:50,282][87424] Updated weights for policy 0, policy_version 337239 (0.0011) -[2023-11-28 09:02:50,432][87426] Updated weights for policy 1, policy_version 336840 (0.0011) -[2023-11-28 09:02:50,818][87426] Updated weights for policy 1, policy_version 336850 (0.0011) -[2023-11-28 09:02:51,194][87426] Updated weights for policy 1, policy_version 336860 (0.0012) -[2023-11-28 09:02:52,710][87424] Updated weights for policy 0, policy_version 337249 (0.0009) -[2023-11-28 09:02:53,091][87424] Updated weights for policy 0, policy_version 337259 (0.0008) -[2023-11-28 09:02:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172572672. Throughput: 0: 2748.4, 1: 2668.2. Samples: 172594624. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:53,445][86177] Avg episode reward: [(0, '-554.810'), (1, '-529.050')] -[2023-11-28 09:02:53,472][87424] Updated weights for policy 0, policy_version 337269 (0.0009) -[2023-11-28 09:02:53,499][87426] Updated weights for policy 1, policy_version 336870 (0.0011) -[2023-11-28 09:02:53,852][87424] Updated weights for policy 0, policy_version 337279 (0.0010) -[2023-11-28 09:02:53,878][87426] Updated weights for policy 1, policy_version 336880 (0.0009) -[2023-11-28 09:02:54,255][87426] Updated weights for policy 1, policy_version 336890 (0.0008) -[2023-11-28 09:02:56,323][87424] Updated weights for policy 0, policy_version 337289 (0.0012) -[2023-11-28 09:02:56,602][87426] Updated weights for policy 1, policy_version 336900 (0.0008) -[2023-11-28 09:02:56,701][87424] Updated weights for policy 0, policy_version 337299 (0.0012) -[2023-11-28 09:02:56,977][87426] Updated weights for policy 1, policy_version 336910 (0.0008) -[2023-11-28 09:02:57,084][87424] Updated weights for policy 0, policy_version 337309 (0.0010) -[2023-11-28 09:02:57,360][87426] Updated weights for policy 1, policy_version 336920 (0.0007) -[2023-11-28 09:02:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172605440. Throughput: 0: 2741.4, 1: 2665.4. Samples: 172617860. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:02:58,445][86177] Avg episode reward: [(0, '-553.670'), (1, '-509.060')] -[2023-11-28 09:02:58,813][87424] Updated weights for policy 0, policy_version 337319 (0.0010) -[2023-11-28 09:02:59,197][87424] Updated weights for policy 0, policy_version 337329 (0.0011) -[2023-11-28 09:02:59,575][87424] Updated weights for policy 0, policy_version 337339 (0.0009) -[2023-11-28 09:02:59,788][87426] Updated weights for policy 1, policy_version 336930 (0.0008) -[2023-11-28 09:03:00,163][87426] Updated weights for policy 1, policy_version 336940 (0.0011) -[2023-11-28 09:03:00,543][87426] Updated weights for policy 1, policy_version 336950 (0.0011) -[2023-11-28 09:03:00,925][87426] Updated weights for policy 1, policy_version 336960 (0.0011) -[2023-11-28 09:03:01,849][87424] Updated weights for policy 0, policy_version 337349 (0.0008) -[2023-11-28 09:03:02,240][87424] Updated weights for policy 0, policy_version 337359 (0.0010) -[2023-11-28 09:03:02,624][87424] Updated weights for policy 0, policy_version 337369 (0.0007) -[2023-11-28 09:03:03,072][87426] Updated weights for policy 1, policy_version 336970 (0.0009) -[2023-11-28 09:03:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 172630016. Throughput: 0: 2741.2, 1: 2639.2. Samples: 172641988. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:03:03,445][86177] Avg episode reward: [(0, '-559.070'), (1, '-517.660')] -[2023-11-28 09:03:03,458][87426] Updated weights for policy 1, policy_version 336980 (0.0010) -[2023-11-28 09:03:03,831][87426] Updated weights for policy 1, policy_version 336990 (0.0007) -[2023-11-28 09:03:04,696][87424] Updated weights for policy 0, policy_version 337379 (0.0009) -[2023-11-28 09:03:05,073][87424] Updated weights for policy 0, policy_version 337389 (0.0011) -[2023-11-28 09:03:05,453][87424] Updated weights for policy 0, policy_version 337399 (0.0010) -[2023-11-28 09:03:05,689][87426] Updated weights for policy 1, policy_version 337000 (0.0011) -[2023-11-28 09:03:06,084][87426] Updated weights for policy 1, policy_version 337010 (0.0011) -[2023-11-28 09:03:06,469][87426] Updated weights for policy 1, policy_version 337020 (0.0007) -[2023-11-28 09:03:07,884][87424] Updated weights for policy 0, policy_version 337409 (0.0008) -[2023-11-28 09:03:08,276][87424] Updated weights for policy 0, policy_version 337419 (0.0009) -[2023-11-28 09:03:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 172654592. Throughput: 0: 2731.6, 1: 2657.2. Samples: 172674744. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:03:08,446][86177] Avg episode reward: [(0, '-586.190'), (1, '-518.470')] -[2023-11-28 09:03:08,660][87424] Updated weights for policy 0, policy_version 337429 (0.0008) -[2023-11-28 09:03:08,741][87426] Updated weights for policy 1, policy_version 337030 (0.0008) -[2023-11-28 09:03:09,041][87424] Updated weights for policy 0, policy_version 337439 (0.0009) -[2023-11-28 09:03:09,119][87426] Updated weights for policy 1, policy_version 337040 (0.0009) -[2023-11-28 09:03:09,498][87426] Updated weights for policy 1, policy_version 337050 (0.0007) -[2023-11-28 09:03:11,563][87424] Updated weights for policy 0, policy_version 337449 (0.0010) -[2023-11-28 09:03:11,578][87426] Updated weights for policy 1, policy_version 337060 (0.0009) -[2023-11-28 09:03:11,946][87424] Updated weights for policy 0, policy_version 337459 (0.0011) -[2023-11-28 09:03:11,975][87426] Updated weights for policy 1, policy_version 337070 (0.0011) -[2023-11-28 09:03:12,326][87424] Updated weights for policy 0, policy_version 337469 (0.0011) -[2023-11-28 09:03:12,355][87426] Updated weights for policy 1, policy_version 337080 (0.0010) -[2023-11-28 09:03:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172687360. Throughput: 0: 2703.0, 1: 2664.8. Samples: 172698360. Policy #0 lag: (min: 13.0, avg: 28.8, max: 48.0) -[2023-11-28 09:03:13,445][86177] Avg episode reward: [(0, '-564.610'), (1, '-520.590')] -[2023-11-28 09:03:14,404][87424] Updated weights for policy 0, policy_version 337479 (0.0011) -[2023-11-28 09:03:14,759][87426] Updated weights for policy 1, policy_version 337090 (0.0009) -[2023-11-28 09:03:14,788][87424] Updated weights for policy 0, policy_version 337489 (0.0011) -[2023-11-28 09:03:15,140][87426] Updated weights for policy 1, policy_version 337100 (0.0012) -[2023-11-28 09:03:15,177][87424] Updated weights for policy 0, policy_version 337499 (0.0011) -[2023-11-28 09:03:15,520][87426] Updated weights for policy 1, policy_version 337110 (0.0011) -[2023-11-28 09:03:15,893][87426] Updated weights for policy 1, policy_version 337120 (0.0011) -[2023-11-28 09:03:17,396][87424] Updated weights for policy 0, policy_version 337509 (0.0012) -[2023-11-28 09:03:17,777][87424] Updated weights for policy 0, policy_version 337519 (0.0012) -[2023-11-28 09:03:18,150][87424] Updated weights for policy 0, policy_version 337529 (0.0011) -[2023-11-28 09:03:18,179][87426] Updated weights for policy 1, policy_version 337130 (0.0011) -[2023-11-28 09:03:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172711936. Throughput: 0: 2691.6, 1: 2663.7. Samples: 172722932. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:03:18,445][86177] Avg episode reward: [(0, '-571.390'), (1, '-525.850')] -[2023-11-28 09:03:18,554][87426] Updated weights for policy 1, policy_version 337140 (0.0009) -[2023-11-28 09:03:18,937][87426] Updated weights for policy 1, policy_version 337150 (0.0008) -[2023-11-28 09:03:20,262][87424] Updated weights for policy 0, policy_version 337539 (0.0011) -[2023-11-28 09:03:20,643][87424] Updated weights for policy 0, policy_version 337549 (0.0012) -[2023-11-28 09:03:21,027][87424] Updated weights for policy 0, policy_version 337559 (0.0012) -[2023-11-28 09:03:21,048][87426] Updated weights for policy 1, policy_version 337160 (0.0011) -[2023-11-28 09:03:21,423][87426] Updated weights for policy 1, policy_version 337170 (0.0010) -[2023-11-28 09:03:21,800][87426] Updated weights for policy 1, policy_version 337180 (0.0009) -[2023-11-28 09:03:23,279][87424] Updated weights for policy 0, policy_version 337569 (0.0012) -[2023-11-28 09:03:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172736512. Throughput: 0: 2668.5, 1: 2686.5. Samples: 172756016. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:03:23,445][86177] Avg episode reward: [(0, '-579.840'), (1, '-519.290')] -[2023-11-28 09:03:23,657][87424] Updated weights for policy 0, policy_version 337579 (0.0008) -[2023-11-28 09:03:23,970][87426] Updated weights for policy 1, policy_version 337190 (0.0011) -[2023-11-28 09:03:24,032][87424] Updated weights for policy 0, policy_version 337589 (0.0008) -[2023-11-28 09:03:24,353][87426] Updated weights for policy 1, policy_version 337200 (0.0009) -[2023-11-28 09:03:24,416][87424] Updated weights for policy 0, policy_version 337599 (0.0007) -[2023-11-28 09:03:24,723][87426] Updated weights for policy 1, policy_version 337210 (0.0007) -[2023-11-28 09:03:26,664][87426] Updated weights for policy 1, policy_version 337220 (0.0009) -[2023-11-28 09:03:26,758][87424] Updated weights for policy 0, policy_version 337609 (0.0010) -[2023-11-28 09:03:27,034][87426] Updated weights for policy 1, policy_version 337230 (0.0011) -[2023-11-28 09:03:27,143][87424] Updated weights for policy 0, policy_version 337619 (0.0008) -[2023-11-28 09:03:27,416][87426] Updated weights for policy 1, policy_version 337240 (0.0012) -[2023-11-28 09:03:27,528][87424] Updated weights for policy 0, policy_version 337629 (0.0008) -[2023-11-28 09:03:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172769280. Throughput: 0: 2676.7, 1: 2698.1. Samples: 172780380. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:03:28,445][86177] Avg episode reward: [(0, '-574.620'), (1, '-514.940')] -[2023-11-28 09:03:29,393][87424] Updated weights for policy 0, policy_version 337639 (0.0010) -[2023-11-28 09:03:29,786][87424] Updated weights for policy 0, policy_version 337649 (0.0010) -[2023-11-28 09:03:29,892][87426] Updated weights for policy 1, policy_version 337250 (0.0011) -[2023-11-28 09:03:30,163][87424] Updated weights for policy 0, policy_version 337659 (0.0009) -[2023-11-28 09:03:30,266][87426] Updated weights for policy 1, policy_version 337260 (0.0008) -[2023-11-28 09:03:30,653][87426] Updated weights for policy 1, policy_version 337270 (0.0010) -[2023-11-28 09:03:31,024][87426] Updated weights for policy 1, policy_version 337280 (0.0012) -[2023-11-28 09:03:32,354][87424] Updated weights for policy 0, policy_version 337669 (0.0011) -[2023-11-28 09:03:32,733][87424] Updated weights for policy 0, policy_version 337679 (0.0011) -[2023-11-28 09:03:33,106][87424] Updated weights for policy 0, policy_version 337689 (0.0011) -[2023-11-28 09:03:33,393][87426] Updated weights for policy 1, policy_version 337290 (0.0011) -[2023-11-28 09:03:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 172793856. Throughput: 0: 2667.6, 1: 2691.4. Samples: 172804520. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:03:33,445][86177] Avg episode reward: [(0, '-566.060'), (1, '-521.500')] -[2023-11-28 09:03:33,774][87426] Updated weights for policy 1, policy_version 337300 (0.0012) -[2023-11-28 09:03:34,158][87426] Updated weights for policy 1, policy_version 337310 (0.0012) -[2023-11-28 09:03:35,346][87424] Updated weights for policy 0, policy_version 337699 (0.0010) -[2023-11-28 09:03:35,725][87424] Updated weights for policy 0, policy_version 337709 (0.0007) -[2023-11-28 09:03:36,094][87426] Updated weights for policy 1, policy_version 337320 (0.0012) -[2023-11-28 09:03:36,111][87424] Updated weights for policy 0, policy_version 337719 (0.0007) -[2023-11-28 09:03:36,473][87426] Updated weights for policy 1, policy_version 337330 (0.0012) -[2023-11-28 09:03:36,855][87426] Updated weights for policy 1, policy_version 337340 (0.0012) -[2023-11-28 09:03:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 172818432. Throughput: 0: 2672.6, 1: 2717.3. Samples: 172837172. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:03:38,445][86177] Avg episode reward: [(0, '-555.280'), (1, '-518.740')] -[2023-11-28 09:03:38,574][87426] Updated weights for policy 1, policy_version 337350 (0.0010) -[2023-11-28 09:03:38,592][87424] Updated weights for policy 0, policy_version 337729 (0.0008) -[2023-11-28 09:03:38,970][87426] Updated weights for policy 1, policy_version 337360 (0.0012) -[2023-11-28 09:03:38,974][87424] Updated weights for policy 0, policy_version 337739 (0.0011) -[2023-11-28 09:03:39,342][87426] Updated weights for policy 1, policy_version 337370 (0.0010) -[2023-11-28 09:03:39,346][87424] Updated weights for policy 0, policy_version 337749 (0.0011) -[2023-11-28 09:03:39,735][87424] Updated weights for policy 0, policy_version 337759 (0.0012) -[2023-11-28 09:03:41,526][87426] Updated weights for policy 1, policy_version 337380 (0.0010) -[2023-11-28 09:03:41,768][87424] Updated weights for policy 0, policy_version 337769 (0.0012) -[2023-11-28 09:03:41,910][87426] Updated weights for policy 1, policy_version 337390 (0.0011) -[2023-11-28 09:03:42,161][87424] Updated weights for policy 0, policy_version 337779 (0.0011) -[2023-11-28 09:03:42,280][87426] Updated weights for policy 1, policy_version 337400 (0.0011) -[2023-11-28 09:03:42,525][87424] Updated weights for policy 0, policy_version 337789 (0.0011) -[2023-11-28 09:03:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 172851200. Throughput: 0: 2685.4, 1: 2722.3. Samples: 172861208. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:03:43,445][86177] Avg episode reward: [(0, '-552.690'), (1, '-520.090')] -[2023-11-28 09:03:44,311][87426] Updated weights for policy 1, policy_version 337410 (0.0011) -[2023-11-28 09:03:44,691][87426] Updated weights for policy 1, policy_version 337420 (0.0012) -[2023-11-28 09:03:45,043][87424] Updated weights for policy 0, policy_version 337799 (0.0011) -[2023-11-28 09:03:45,068][87426] Updated weights for policy 1, policy_version 337430 (0.0009) -[2023-11-28 09:03:45,425][87424] Updated weights for policy 0, policy_version 337809 (0.0009) -[2023-11-28 09:03:45,453][87426] Updated weights for policy 1, policy_version 337440 (0.0009) -[2023-11-28 09:03:45,809][87424] Updated weights for policy 0, policy_version 337819 (0.0007) -[2023-11-28 09:03:47,989][87426] Updated weights for policy 1, policy_version 337450 (0.0007) -[2023-11-28 09:03:48,290][87424] Updated weights for policy 0, policy_version 337829 (0.0008) -[2023-11-28 09:03:48,381][87426] Updated weights for policy 1, policy_version 337460 (0.0007) -[2023-11-28 09:03:48,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5188.2, 300 sec: 5387.3). Total num frames: 172867584. Throughput: 0: 2672.2, 1: 2739.5. Samples: 172885516. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:03:48,446][86177] Avg episode reward: [(0, '-532.680'), (1, '-574.270')] -[2023-11-28 09:03:48,670][87424] Updated weights for policy 0, policy_version 337839 (0.0008) -[2023-11-28 09:03:48,764][87426] Updated weights for policy 1, policy_version 337470 (0.0008) -[2023-11-28 09:03:49,053][87424] Updated weights for policy 0, policy_version 337849 (0.0010) -[2023-11-28 09:03:50,889][87426] Updated weights for policy 1, policy_version 337480 (0.0011) -[2023-11-28 09:03:51,270][87426] Updated weights for policy 1, policy_version 337490 (0.0012) -[2023-11-28 09:03:51,610][87424] Updated weights for policy 0, policy_version 337859 (0.0012) -[2023-11-28 09:03:51,649][87426] Updated weights for policy 1, policy_version 337500 (0.0012) -[2023-11-28 09:03:51,983][87424] Updated weights for policy 0, policy_version 337869 (0.0010) -[2023-11-28 09:03:52,384][87424] Updated weights for policy 0, policy_version 337879 (0.0012) -[2023-11-28 09:03:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172900352. Throughput: 0: 2654.7, 1: 2731.9. Samples: 172917140. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:03:53,445][86177] Avg episode reward: [(0, '-541.000'), (1, '-560.460')] -[2023-11-28 09:03:53,929][87426] Updated weights for policy 1, policy_version 337510 (0.0011) -[2023-11-28 09:03:54,305][87426] Updated weights for policy 1, policy_version 337520 (0.0011) -[2023-11-28 09:03:54,435][87424] Updated weights for policy 0, policy_version 337889 (0.0011) -[2023-11-28 09:03:54,675][87426] Updated weights for policy 1, policy_version 337530 (0.0011) -[2023-11-28 09:03:54,823][87424] Updated weights for policy 0, policy_version 337899 (0.0011) -[2023-11-28 09:03:55,204][87424] Updated weights for policy 0, policy_version 337909 (0.0012) -[2023-11-28 09:03:55,580][87424] Updated weights for policy 0, policy_version 337919 (0.0010) -[2023-11-28 09:03:56,632][87426] Updated weights for policy 1, policy_version 337540 (0.0012) -[2023-11-28 09:03:57,016][87426] Updated weights for policy 1, policy_version 337550 (0.0012) -[2023-11-28 09:03:57,383][87426] Updated weights for policy 1, policy_version 337560 (0.0012) -[2023-11-28 09:03:57,734][87424] Updated weights for policy 0, policy_version 337929 (0.0011) -[2023-11-28 09:03:58,116][87424] Updated weights for policy 0, policy_version 337939 (0.0012) -[2023-11-28 09:03:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 172924928. Throughput: 0: 2670.9, 1: 2763.1. Samples: 172942892. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:03:58,445][86177] Avg episode reward: [(0, '-553.090'), (1, '-561.830')] -[2023-11-28 09:03:58,489][87424] Updated weights for policy 0, policy_version 337949 (0.0009) -[2023-11-28 09:03:59,385][87426] Updated weights for policy 1, policy_version 337570 (0.0011) -[2023-11-28 09:03:59,762][87426] Updated weights for policy 1, policy_version 337580 (0.0008) -[2023-11-28 09:04:00,147][87426] Updated weights for policy 1, policy_version 337590 (0.0008) -[2023-11-28 09:04:00,529][87426] Updated weights for policy 1, policy_version 337600 (0.0009) -[2023-11-28 09:04:00,748][87424] Updated weights for policy 0, policy_version 337959 (0.0011) -[2023-11-28 09:04:01,126][87424] Updated weights for policy 0, policy_version 337969 (0.0012) -[2023-11-28 09:04:01,522][87424] Updated weights for policy 0, policy_version 337979 (0.0012) -[2023-11-28 09:04:02,812][87426] Updated weights for policy 1, policy_version 337610 (0.0008) -[2023-11-28 09:04:03,194][87426] Updated weights for policy 1, policy_version 337620 (0.0010) -[2023-11-28 09:04:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 172949504. Throughput: 0: 2663.7, 1: 2769.1. Samples: 172967412. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:04:03,445][86177] Avg episode reward: [(0, '-553.250'), (1, '-568.560')] -[2023-11-28 09:04:03,584][87426] Updated weights for policy 1, policy_version 337630 (0.0008) -[2023-11-28 09:04:03,894][87424] Updated weights for policy 0, policy_version 337989 (0.0012) -[2023-11-28 09:04:04,284][87424] Updated weights for policy 0, policy_version 337999 (0.0012) -[2023-11-28 09:04:04,656][87424] Updated weights for policy 0, policy_version 338009 (0.0009) -[2023-11-28 09:04:05,527][87426] Updated weights for policy 1, policy_version 337640 (0.0007) -[2023-11-28 09:04:05,915][87426] Updated weights for policy 1, policy_version 337650 (0.0008) -[2023-11-28 09:04:06,279][87426] Updated weights for policy 1, policy_version 337660 (0.0012) -[2023-11-28 09:04:06,413][87424] Updated weights for policy 0, policy_version 338019 (0.0009) -[2023-11-28 09:04:06,789][87424] Updated weights for policy 0, policy_version 338029 (0.0011) -[2023-11-28 09:04:07,177][87424] Updated weights for policy 0, policy_version 338039 (0.0011) -[2023-11-28 09:04:08,228][87426] Updated weights for policy 1, policy_version 337670 (0.0008) -[2023-11-28 09:04:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 172982272. Throughput: 0: 2673.4, 1: 2778.3. Samples: 173001344. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:04:08,445][86177] Avg episode reward: [(0, '-600.670'), (1, '-515.330')] -[2023-11-28 09:04:08,600][87426] Updated weights for policy 1, policy_version 337680 (0.0007) -[2023-11-28 09:04:08,980][87426] Updated weights for policy 1, policy_version 337690 (0.0009) -[2023-11-28 09:04:09,093][87424] Updated weights for policy 0, policy_version 338049 (0.0011) -[2023-11-28 09:04:09,472][87424] Updated weights for policy 0, policy_version 338059 (0.0010) -[2023-11-28 09:04:09,850][87424] Updated weights for policy 0, policy_version 338069 (0.0010) -[2023-11-28 09:04:10,235][87424] Updated weights for policy 0, policy_version 338079 (0.0012) -[2023-11-28 09:04:11,008][87426] Updated weights for policy 1, policy_version 337700 (0.0012) -[2023-11-28 09:04:11,384][87426] Updated weights for policy 1, policy_version 337710 (0.0012) -[2023-11-28 09:04:11,776][87426] Updated weights for policy 1, policy_version 337720 (0.0012) -[2023-11-28 09:04:12,491][87424] Updated weights for policy 0, policy_version 338089 (0.0010) -[2023-11-28 09:04:12,877][87424] Updated weights for policy 0, policy_version 338099 (0.0011) -[2023-11-28 09:04:13,251][87424] Updated weights for policy 0, policy_version 338109 (0.0010) -[2023-11-28 09:04:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 173015040. Throughput: 0: 2683.6, 1: 2797.6. Samples: 173027032. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:04:13,445][86177] Avg episode reward: [(0, '-639.100'), (1, '-520.350')] -[2023-11-28 09:04:13,898][87426] Updated weights for policy 1, policy_version 337730 (0.0012) -[2023-11-28 09:04:14,271][87426] Updated weights for policy 1, policy_version 337740 (0.0012) -[2023-11-28 09:04:14,645][87426] Updated weights for policy 1, policy_version 337750 (0.0008) -[2023-11-28 09:04:15,024][87426] Updated weights for policy 1, policy_version 337760 (0.0007) -[2023-11-28 09:04:15,326][87424] Updated weights for policy 0, policy_version 338119 (0.0012) -[2023-11-28 09:04:15,707][87424] Updated weights for policy 0, policy_version 338129 (0.0010) -[2023-11-28 09:04:16,103][87424] Updated weights for policy 0, policy_version 338139 (0.0008) -[2023-11-28 09:04:16,939][87426] Updated weights for policy 1, policy_version 337770 (0.0012) -[2023-11-28 09:04:17,317][87426] Updated weights for policy 1, policy_version 337780 (0.0012) -[2023-11-28 09:04:17,697][87426] Updated weights for policy 1, policy_version 337790 (0.0012) -[2023-11-28 09:04:18,046][87424] Updated weights for policy 0, policy_version 338149 (0.0010) -[2023-11-28 09:04:18,432][87424] Updated weights for policy 0, policy_version 338159 (0.0009) -[2023-11-28 09:04:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 173039616. Throughput: 0: 2684.8, 1: 2808.9. Samples: 173051736. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:04:18,445][86177] Avg episode reward: [(0, '-616.560'), (1, '-531.390')] -[2023-11-28 09:04:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000337792_86474752.pth... -[2023-11-28 09:04:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000335264_85827584.pth -[2023-11-28 09:04:18,815][87424] Updated weights for policy 0, policy_version 338169 (0.0010) -[2023-11-28 09:04:19,082][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000338176_86573056.pth... -[2023-11-28 09:04:19,112][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000335616_85917696.pth -[2023-11-28 09:04:20,181][87426] Updated weights for policy 1, policy_version 337800 (0.0010) -[2023-11-28 09:04:20,547][87426] Updated weights for policy 1, policy_version 337810 (0.0010) -[2023-11-28 09:04:20,924][87426] Updated weights for policy 1, policy_version 337820 (0.0012) -[2023-11-28 09:04:21,316][87424] Updated weights for policy 0, policy_version 338179 (0.0010) -[2023-11-28 09:04:21,693][87424] Updated weights for policy 0, policy_version 338189 (0.0012) -[2023-11-28 09:04:22,076][87424] Updated weights for policy 0, policy_version 338199 (0.0012) -[2023-11-28 09:04:23,230][87426] Updated weights for policy 1, policy_version 337830 (0.0011) -[2023-11-28 09:04:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 173064192. Throughput: 0: 2668.9, 1: 2780.4. Samples: 173082392. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:04:23,445][86177] Avg episode reward: [(0, '-615.140'), (1, '-537.630')] -[2023-11-28 09:04:23,607][87426] Updated weights for policy 1, policy_version 337840 (0.0007) -[2023-11-28 09:04:23,986][87426] Updated weights for policy 1, policy_version 337850 (0.0007) -[2023-11-28 09:04:24,271][87424] Updated weights for policy 0, policy_version 338209 (0.0011) -[2023-11-28 09:04:24,658][87424] Updated weights for policy 0, policy_version 338219 (0.0008) -[2023-11-28 09:04:25,036][87424] Updated weights for policy 0, policy_version 338229 (0.0008) -[2023-11-28 09:04:25,418][87424] Updated weights for policy 0, policy_version 338239 (0.0008) -[2023-11-28 09:04:25,965][87426] Updated weights for policy 1, policy_version 337860 (0.0007) -[2023-11-28 09:04:26,348][87426] Updated weights for policy 1, policy_version 337870 (0.0007) -[2023-11-28 09:04:26,730][87426] Updated weights for policy 1, policy_version 337880 (0.0007) -[2023-11-28 09:04:27,915][87424] Updated weights for policy 0, policy_version 338249 (0.0007) -[2023-11-28 09:04:28,288][87424] Updated weights for policy 0, policy_version 338259 (0.0007) -[2023-11-28 09:04:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 173088768. Throughput: 0: 2676.7, 1: 2792.9. Samples: 173107340. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:04:28,445][86177] Avg episode reward: [(0, '-570.310'), (1, '-541.900')] -[2023-11-28 09:04:28,668][87424] Updated weights for policy 0, policy_version 338269 (0.0008) -[2023-11-28 09:04:29,157][87426] Updated weights for policy 1, policy_version 337890 (0.0008) -[2023-11-28 09:04:29,535][87426] Updated weights for policy 1, policy_version 337900 (0.0012) -[2023-11-28 09:04:29,906][87426] Updated weights for policy 1, policy_version 337910 (0.0012) -[2023-11-28 09:04:30,282][87426] Updated weights for policy 1, policy_version 337920 (0.0011) -[2023-11-28 09:04:30,500][87424] Updated weights for policy 0, policy_version 338279 (0.0010) -[2023-11-28 09:04:30,882][87424] Updated weights for policy 0, policy_version 338289 (0.0008) -[2023-11-28 09:04:31,264][87424] Updated weights for policy 0, policy_version 338299 (0.0008) -[2023-11-28 09:04:32,375][87426] Updated weights for policy 1, policy_version 337930 (0.0012) -[2023-11-28 09:04:32,753][87426] Updated weights for policy 1, policy_version 337940 (0.0012) -[2023-11-28 09:04:33,132][87426] Updated weights for policy 1, policy_version 337950 (0.0012) -[2023-11-28 09:04:33,177][87424] Updated weights for policy 0, policy_version 338309 (0.0010) -[2023-11-28 09:04:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 173121536. Throughput: 0: 2694.3, 1: 2793.5. Samples: 173132468. Policy #0 lag: (min: 34.0, avg: 41.3, max: 58.0) -[2023-11-28 09:04:33,445][86177] Avg episode reward: [(0, '-526.050'), (1, '-542.380')] -[2023-11-28 09:04:33,570][87424] Updated weights for policy 0, policy_version 338319 (0.0012) -[2023-11-28 09:04:33,953][87424] Updated weights for policy 0, policy_version 338329 (0.0010) -[2023-11-28 09:04:35,082][87426] Updated weights for policy 1, policy_version 337960 (0.0011) -[2023-11-28 09:04:35,462][87426] Updated weights for policy 1, policy_version 337970 (0.0008) -[2023-11-28 09:04:35,748][87424] Updated weights for policy 0, policy_version 338339 (0.0010) -[2023-11-28 09:04:35,851][87426] Updated weights for policy 1, policy_version 337980 (0.0007) -[2023-11-28 09:04:36,128][87424] Updated weights for policy 0, policy_version 338349 (0.0008) -[2023-11-28 09:04:36,526][87424] Updated weights for policy 0, policy_version 338359 (0.0008) -[2023-11-28 09:04:37,820][87426] Updated weights for policy 1, policy_version 337990 (0.0010) -[2023-11-28 09:04:38,205][87426] Updated weights for policy 1, policy_version 338000 (0.0012) -[2023-11-28 09:04:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 173146112. Throughput: 0: 2715.5, 1: 2805.5. Samples: 173165588. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:04:38,445][86177] Avg episode reward: [(0, '-534.770'), (1, '-570.430')] -[2023-11-28 09:04:38,580][87426] Updated weights for policy 1, policy_version 338010 (0.0012) -[2023-11-28 09:04:38,907][87424] Updated weights for policy 0, policy_version 338369 (0.0009) -[2023-11-28 09:04:39,289][87424] Updated weights for policy 0, policy_version 338379 (0.0012) -[2023-11-28 09:04:39,665][87424] Updated weights for policy 0, policy_version 338389 (0.0012) -[2023-11-28 09:04:40,044][87424] Updated weights for policy 0, policy_version 338399 (0.0011) -[2023-11-28 09:04:41,149][87426] Updated weights for policy 1, policy_version 338020 (0.0010) -[2023-11-28 09:04:41,526][87426] Updated weights for policy 1, policy_version 338030 (0.0010) -[2023-11-28 09:04:41,903][87426] Updated weights for policy 1, policy_version 338040 (0.0009) -[2023-11-28 09:04:42,641][87424] Updated weights for policy 0, policy_version 338409 (0.0012) -[2023-11-28 09:04:43,027][87424] Updated weights for policy 0, policy_version 338419 (0.0012) -[2023-11-28 09:04:43,403][87424] Updated weights for policy 0, policy_version 338429 (0.0010) -[2023-11-28 09:04:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 173170688. Throughput: 0: 2699.5, 1: 2760.2. Samples: 173188576. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:04:43,445][86177] Avg episode reward: [(0, '-535.030'), (1, '-571.300')] -[2023-11-28 09:04:43,957][87426] Updated weights for policy 1, policy_version 338050 (0.0009) -[2023-11-28 09:04:44,336][87426] Updated weights for policy 1, policy_version 338060 (0.0009) -[2023-11-28 09:04:44,716][87426] Updated weights for policy 1, policy_version 338070 (0.0008) -[2023-11-28 09:04:45,089][87426] Updated weights for policy 1, policy_version 338080 (0.0007) -[2023-11-28 09:04:45,646][87424] Updated weights for policy 0, policy_version 338439 (0.0011) -[2023-11-28 09:04:46,029][87424] Updated weights for policy 0, policy_version 338449 (0.0012) -[2023-11-28 09:04:46,419][87424] Updated weights for policy 0, policy_version 338459 (0.0012) -[2023-11-28 09:04:47,517][87426] Updated weights for policy 1, policy_version 338090 (0.0012) -[2023-11-28 09:04:47,896][87426] Updated weights for policy 1, policy_version 338100 (0.0012) -[2023-11-28 09:04:48,274][87426] Updated weights for policy 1, policy_version 338110 (0.0012) -[2023-11-28 09:04:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 173203456. Throughput: 0: 2710.8, 1: 2745.6. Samples: 173212948. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:04:48,445][86177] Avg episode reward: [(0, '-536.360'), (1, '-579.660')] -[2023-11-28 09:04:48,454][87424] Updated weights for policy 0, policy_version 338469 (0.0010) -[2023-11-28 09:04:48,829][87424] Updated weights for policy 0, policy_version 338479 (0.0008) -[2023-11-28 09:04:49,210][87424] Updated weights for policy 0, policy_version 338489 (0.0011) -[2023-11-28 09:04:50,453][87426] Updated weights for policy 1, policy_version 338120 (0.0011) -[2023-11-28 09:04:50,829][87426] Updated weights for policy 1, policy_version 338130 (0.0011) -[2023-11-28 09:04:51,211][87426] Updated weights for policy 1, policy_version 338140 (0.0012) -[2023-11-28 09:04:51,404][87424] Updated weights for policy 0, policy_version 338499 (0.0010) -[2023-11-28 09:04:51,793][87424] Updated weights for policy 0, policy_version 338509 (0.0010) -[2023-11-28 09:04:52,171][87424] Updated weights for policy 0, policy_version 338519 (0.0009) -[2023-11-28 09:04:53,313][87426] Updated weights for policy 1, policy_version 338150 (0.0011) -[2023-11-28 09:04:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 173228032. Throughput: 0: 2719.4, 1: 2724.6. Samples: 173246324. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:04:53,445][86177] Avg episode reward: [(0, '-534.110'), (1, '-575.900')] -[2023-11-28 09:04:53,692][87426] Updated weights for policy 1, policy_version 338160 (0.0011) -[2023-11-28 09:04:54,070][87426] Updated weights for policy 1, policy_version 338170 (0.0008) -[2023-11-28 09:04:54,255][87424] Updated weights for policy 0, policy_version 338529 (0.0010) -[2023-11-28 09:04:54,631][87424] Updated weights for policy 0, policy_version 338539 (0.0012) -[2023-11-28 09:04:55,014][87424] Updated weights for policy 0, policy_version 338549 (0.0012) -[2023-11-28 09:04:55,392][87424] Updated weights for policy 0, policy_version 338559 (0.0012) -[2023-11-28 09:04:56,246][87426] Updated weights for policy 1, policy_version 338180 (0.0007) -[2023-11-28 09:04:56,626][87426] Updated weights for policy 1, policy_version 338190 (0.0007) -[2023-11-28 09:04:57,010][87426] Updated weights for policy 1, policy_version 338200 (0.0008) -[2023-11-28 09:04:57,995][87424] Updated weights for policy 0, policy_version 338569 (0.0008) -[2023-11-28 09:04:58,382][87424] Updated weights for policy 0, policy_version 338579 (0.0007) -[2023-11-28 09:04:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 173252608. Throughput: 0: 2698.5, 1: 2719.9. Samples: 173270860. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:04:58,445][86177] Avg episode reward: [(0, '-531.390'), (1, '-563.340')] -[2023-11-28 09:04:58,767][87424] Updated weights for policy 0, policy_version 338589 (0.0007) -[2023-11-28 09:04:59,366][87426] Updated weights for policy 1, policy_version 338210 (0.0008) -[2023-11-28 09:04:59,735][87426] Updated weights for policy 1, policy_version 338220 (0.0009) -[2023-11-28 09:05:00,120][87426] Updated weights for policy 1, policy_version 338230 (0.0011) -[2023-11-28 09:05:00,493][87426] Updated weights for policy 1, policy_version 338240 (0.0010) -[2023-11-28 09:05:01,082][87424] Updated weights for policy 0, policy_version 338599 (0.0010) -[2023-11-28 09:05:01,463][87424] Updated weights for policy 0, policy_version 338609 (0.0009) -[2023-11-28 09:05:01,845][87424] Updated weights for policy 0, policy_version 338619 (0.0009) -[2023-11-28 09:05:02,694][87426] Updated weights for policy 1, policy_version 338250 (0.0010) -[2023-11-28 09:05:03,069][87426] Updated weights for policy 1, policy_version 338260 (0.0010) -[2023-11-28 09:05:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 173277184. Throughput: 0: 2688.5, 1: 2713.4. Samples: 173294824. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:03,446][86177] Avg episode reward: [(0, '-563.130'), (1, '-626.850')] -[2023-11-28 09:05:03,457][87426] Updated weights for policy 1, policy_version 338270 (0.0011) -[2023-11-28 09:05:04,242][87424] Updated weights for policy 0, policy_version 338629 (0.0010) -[2023-11-28 09:05:04,625][87424] Updated weights for policy 0, policy_version 338639 (0.0016) -[2023-11-28 09:05:05,002][87424] Updated weights for policy 0, policy_version 338649 (0.0012) -[2023-11-28 09:05:05,120][87426] Updated weights for policy 1, policy_version 338280 (0.0011) -[2023-11-28 09:05:05,490][87426] Updated weights for policy 1, policy_version 338290 (0.0008) -[2023-11-28 09:05:05,876][87426] Updated weights for policy 1, policy_version 338300 (0.0007) -[2023-11-28 09:05:07,113][87424] Updated weights for policy 0, policy_version 338659 (0.0011) -[2023-11-28 09:05:07,492][87424] Updated weights for policy 0, policy_version 338669 (0.0007) -[2023-11-28 09:05:07,872][87424] Updated weights for policy 0, policy_version 338679 (0.0008) -[2023-11-28 09:05:08,162][87426] Updated weights for policy 1, policy_version 338310 (0.0008) -[2023-11-28 09:05:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 173309952. Throughput: 0: 2710.8, 1: 2728.0. Samples: 173327140. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:08,445][86177] Avg episode reward: [(0, '-563.690'), (1, '-615.780')] -[2023-11-28 09:05:08,543][87426] Updated weights for policy 1, policy_version 338320 (0.0007) -[2023-11-28 09:05:08,922][87426] Updated weights for policy 1, policy_version 338330 (0.0008) -[2023-11-28 09:05:09,977][87424] Updated weights for policy 0, policy_version 338689 (0.0008) -[2023-11-28 09:05:10,366][87424] Updated weights for policy 0, policy_version 338699 (0.0009) -[2023-11-28 09:05:10,737][87424] Updated weights for policy 0, policy_version 338709 (0.0011) -[2023-11-28 09:05:11,115][87424] Updated weights for policy 0, policy_version 338719 (0.0011) -[2023-11-28 09:05:11,502][87426] Updated weights for policy 1, policy_version 338340 (0.0009) -[2023-11-28 09:05:11,878][87426] Updated weights for policy 1, policy_version 338350 (0.0012) -[2023-11-28 09:05:12,253][87426] Updated weights for policy 1, policy_version 338360 (0.0012) -[2023-11-28 09:05:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 173334528. Throughput: 0: 2705.8, 1: 2706.4. Samples: 173350888. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:13,445][86177] Avg episode reward: [(0, '-566.470'), (1, '-636.590')] -[2023-11-28 09:05:13,559][87424] Updated weights for policy 0, policy_version 338729 (0.0008) -[2023-11-28 09:05:13,945][87424] Updated weights for policy 0, policy_version 338739 (0.0007) -[2023-11-28 09:05:14,190][87426] Updated weights for policy 1, policy_version 338370 (0.0012) -[2023-11-28 09:05:14,328][87424] Updated weights for policy 0, policy_version 338749 (0.0007) -[2023-11-28 09:05:14,559][87426] Updated weights for policy 1, policy_version 338380 (0.0011) -[2023-11-28 09:05:14,941][87426] Updated weights for policy 1, policy_version 338390 (0.0012) -[2023-11-28 09:05:15,326][87426] Updated weights for policy 1, policy_version 338400 (0.0012) -[2023-11-28 09:05:16,691][87424] Updated weights for policy 0, policy_version 338759 (0.0011) -[2023-11-28 09:05:17,007][87426] Updated weights for policy 1, policy_version 338410 (0.0007) -[2023-11-28 09:05:17,085][87424] Updated weights for policy 0, policy_version 338769 (0.0012) -[2023-11-28 09:05:17,390][87426] Updated weights for policy 1, policy_version 338420 (0.0008) -[2023-11-28 09:05:17,465][87424] Updated weights for policy 0, policy_version 338779 (0.0009) -[2023-11-28 09:05:17,768][87426] Updated weights for policy 1, policy_version 338430 (0.0008) -[2023-11-28 09:05:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 173367296. Throughput: 0: 2677.9, 1: 2714.8. Samples: 173375140. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:18,445][86177] Avg episode reward: [(0, '-569.410'), (1, '-642.370')] -[2023-11-28 09:05:19,599][87426] Updated weights for policy 1, policy_version 338440 (0.0011) -[2023-11-28 09:05:19,907][87424] Updated weights for policy 0, policy_version 338789 (0.0009) -[2023-11-28 09:05:19,984][87426] Updated weights for policy 1, policy_version 338450 (0.0012) -[2023-11-28 09:05:20,280][87424] Updated weights for policy 0, policy_version 338799 (0.0008) -[2023-11-28 09:05:20,365][87426] Updated weights for policy 1, policy_version 338460 (0.0011) -[2023-11-28 09:05:20,661][87424] Updated weights for policy 0, policy_version 338809 (0.0010) -[2023-11-28 09:05:22,915][87426] Updated weights for policy 1, policy_version 338470 (0.0012) -[2023-11-28 09:05:23,089][87424] Updated weights for policy 0, policy_version 338819 (0.0009) -[2023-11-28 09:05:23,275][87426] Updated weights for policy 1, policy_version 338480 (0.0011) -[2023-11-28 09:05:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 173383680. Throughput: 0: 2647.1, 1: 2717.6. Samples: 173407000. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:23,445][86177] Avg episode reward: [(0, '-571.770'), (1, '-547.800')] -[2023-11-28 09:05:23,471][87424] Updated weights for policy 0, policy_version 338829 (0.0010) -[2023-11-28 09:05:23,662][87426] Updated weights for policy 1, policy_version 338490 (0.0012) -[2023-11-28 09:05:23,846][87424] Updated weights for policy 0, policy_version 338839 (0.0010) -[2023-11-28 09:05:25,775][87426] Updated weights for policy 1, policy_version 338500 (0.0010) -[2023-11-28 09:05:25,815][87424] Updated weights for policy 0, policy_version 338849 (0.0011) -[2023-11-28 09:05:26,155][87426] Updated weights for policy 1, policy_version 338510 (0.0011) -[2023-11-28 09:05:26,198][87424] Updated weights for policy 0, policy_version 338859 (0.0009) -[2023-11-28 09:05:26,538][87426] Updated weights for policy 1, policy_version 338520 (0.0010) -[2023-11-28 09:05:26,592][87424] Updated weights for policy 0, policy_version 338869 (0.0011) -[2023-11-28 09:05:26,979][87424] Updated weights for policy 0, policy_version 338879 (0.0010) -[2023-11-28 09:05:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 173416448. Throughput: 0: 2671.5, 1: 2744.5. Samples: 173432296. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:28,446][86177] Avg episode reward: [(0, '-545.850'), (1, '-541.610')] -[2023-11-28 09:05:28,886][87426] Updated weights for policy 1, policy_version 338530 (0.0010) -[2023-11-28 09:05:29,259][87426] Updated weights for policy 1, policy_version 338540 (0.0010) -[2023-11-28 09:05:29,293][87424] Updated weights for policy 0, policy_version 338889 (0.0010) -[2023-11-28 09:05:29,640][87426] Updated weights for policy 1, policy_version 338550 (0.0011) -[2023-11-28 09:05:29,678][87424] Updated weights for policy 0, policy_version 338899 (0.0011) -[2023-11-28 09:05:30,019][87426] Updated weights for policy 1, policy_version 338560 (0.0011) -[2023-11-28 09:05:30,066][87424] Updated weights for policy 0, policy_version 338909 (0.0012) -[2023-11-28 09:05:31,956][87424] Updated weights for policy 0, policy_version 338919 (0.0011) -[2023-11-28 09:05:31,975][87426] Updated weights for policy 1, policy_version 338570 (0.0011) -[2023-11-28 09:05:32,337][87424] Updated weights for policy 0, policy_version 338929 (0.0012) -[2023-11-28 09:05:32,354][87426] Updated weights for policy 1, policy_version 338580 (0.0009) -[2023-11-28 09:05:32,725][87424] Updated weights for policy 0, policy_version 338939 (0.0011) -[2023-11-28 09:05:32,730][87426] Updated weights for policy 1, policy_version 338590 (0.0011) -[2023-11-28 09:05:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 173449216. Throughput: 0: 2667.8, 1: 2753.2. Samples: 173456892. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:33,445][86177] Avg episode reward: [(0, '-544.420'), (1, '-547.510')] -[2023-11-28 09:05:34,509][87424] Updated weights for policy 0, policy_version 338949 (0.0009) -[2023-11-28 09:05:34,891][87424] Updated weights for policy 0, policy_version 338959 (0.0010) -[2023-11-28 09:05:34,995][87426] Updated weights for policy 1, policy_version 338600 (0.0010) -[2023-11-28 09:05:35,273][87424] Updated weights for policy 0, policy_version 338969 (0.0011) -[2023-11-28 09:05:35,379][87426] Updated weights for policy 1, policy_version 338610 (0.0011) -[2023-11-28 09:05:35,762][87426] Updated weights for policy 1, policy_version 338620 (0.0012) -[2023-11-28 09:05:36,893][87424] Updated weights for policy 0, policy_version 338979 (0.0011) -[2023-11-28 09:05:37,274][87424] Updated weights for policy 0, policy_version 338989 (0.0012) -[2023-11-28 09:05:37,654][87424] Updated weights for policy 0, policy_version 338999 (0.0012) -[2023-11-28 09:05:38,059][87426] Updated weights for policy 1, policy_version 338630 (0.0012) -[2023-11-28 09:05:38,434][87426] Updated weights for policy 1, policy_version 338640 (0.0012) -[2023-11-28 09:05:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 173473792. Throughput: 0: 2695.2, 1: 2744.9. Samples: 173491128. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:38,445][86177] Avg episode reward: [(0, '-538.480'), (1, '-556.790')] -[2023-11-28 09:05:38,805][87426] Updated weights for policy 1, policy_version 338650 (0.0012) -[2023-11-28 09:05:39,444][87424] Updated weights for policy 0, policy_version 339009 (0.0011) -[2023-11-28 09:05:39,814][87424] Updated weights for policy 0, policy_version 339019 (0.0008) -[2023-11-28 09:05:40,208][87424] Updated weights for policy 0, policy_version 339029 (0.0010) -[2023-11-28 09:05:40,582][87424] Updated weights for policy 0, policy_version 339039 (0.0011) -[2023-11-28 09:05:41,060][87426] Updated weights for policy 1, policy_version 338660 (0.0012) -[2023-11-28 09:05:41,437][87426] Updated weights for policy 1, policy_version 338670 (0.0012) -[2023-11-28 09:05:41,828][87426] Updated weights for policy 1, policy_version 338680 (0.0012) -[2023-11-28 09:05:42,726][87424] Updated weights for policy 0, policy_version 339049 (0.0011) -[2023-11-28 09:05:43,109][87424] Updated weights for policy 0, policy_version 339059 (0.0012) -[2023-11-28 09:05:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 173498368. Throughput: 0: 2716.9, 1: 2717.6. Samples: 173515412. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:43,445][86177] Avg episode reward: [(0, '-565.810'), (1, '-554.030')] -[2023-11-28 09:05:43,492][87424] Updated weights for policy 0, policy_version 339069 (0.0012) -[2023-11-28 09:05:44,170][87426] Updated weights for policy 1, policy_version 338690 (0.0012) -[2023-11-28 09:05:44,557][87426] Updated weights for policy 1, policy_version 338700 (0.0012) -[2023-11-28 09:05:44,936][87426] Updated weights for policy 1, policy_version 338710 (0.0012) -[2023-11-28 09:05:45,276][87424] Updated weights for policy 0, policy_version 339079 (0.0012) -[2023-11-28 09:05:45,304][87426] Updated weights for policy 1, policy_version 338720 (0.0011) -[2023-11-28 09:05:45,655][87424] Updated weights for policy 0, policy_version 339089 (0.0012) -[2023-11-28 09:05:46,033][87424] Updated weights for policy 0, policy_version 339099 (0.0012) -[2023-11-28 09:05:47,366][87426] Updated weights for policy 1, policy_version 338730 (0.0007) -[2023-11-28 09:05:47,748][87426] Updated weights for policy 1, policy_version 338740 (0.0007) -[2023-11-28 09:05:48,122][87426] Updated weights for policy 1, policy_version 338750 (0.0007) -[2023-11-28 09:05:48,432][87424] Updated weights for policy 0, policy_version 339109 (0.0012) -[2023-11-28 09:05:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 173531136. Throughput: 0: 2745.8, 1: 2729.1. Samples: 173541192. Policy #0 lag: (min: 14.0, avg: 33.0, max: 55.0) -[2023-11-28 09:05:48,446][86177] Avg episode reward: [(0, '-562.670'), (1, '-563.940')] -[2023-11-28 09:05:48,814][87424] Updated weights for policy 0, policy_version 339119 (0.0012) -[2023-11-28 09:05:49,211][87424] Updated weights for policy 0, policy_version 339129 (0.0012) -[2023-11-28 09:05:50,302][87426] Updated weights for policy 1, policy_version 338760 (0.0011) -[2023-11-28 09:05:50,680][87426] Updated weights for policy 1, policy_version 338770 (0.0010) -[2023-11-28 09:05:51,071][87426] Updated weights for policy 1, policy_version 338780 (0.0010) -[2023-11-28 09:05:51,618][87424] Updated weights for policy 0, policy_version 339139 (0.0011) -[2023-11-28 09:05:51,999][87424] Updated weights for policy 0, policy_version 339149 (0.0011) -[2023-11-28 09:05:52,390][87424] Updated weights for policy 0, policy_version 339159 (0.0012) -[2023-11-28 09:05:53,188][87426] Updated weights for policy 1, policy_version 338790 (0.0011) -[2023-11-28 09:05:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 173555712. Throughput: 0: 2729.5, 1: 2733.1. Samples: 173572956. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:05:53,445][86177] Avg episode reward: [(0, '-561.820'), (1, '-569.790')] -[2023-11-28 09:05:53,565][87426] Updated weights for policy 1, policy_version 338800 (0.0012) -[2023-11-28 09:05:53,950][87426] Updated weights for policy 1, policy_version 338810 (0.0012) -[2023-11-28 09:05:54,431][87424] Updated weights for policy 0, policy_version 339169 (0.0012) -[2023-11-28 09:05:54,808][87424] Updated weights for policy 0, policy_version 339179 (0.0012) -[2023-11-28 09:05:55,178][87424] Updated weights for policy 0, policy_version 339189 (0.0012) -[2023-11-28 09:05:55,554][87424] Updated weights for policy 0, policy_version 339199 (0.0011) -[2023-11-28 09:05:56,190][87426] Updated weights for policy 1, policy_version 338820 (0.0009) -[2023-11-28 09:05:56,570][87426] Updated weights for policy 1, policy_version 338830 (0.0007) -[2023-11-28 09:05:56,950][87426] Updated weights for policy 1, policy_version 338840 (0.0007) -[2023-11-28 09:05:57,671][87424] Updated weights for policy 0, policy_version 339209 (0.0011) -[2023-11-28 09:05:58,039][87424] Updated weights for policy 0, policy_version 339219 (0.0011) -[2023-11-28 09:05:58,425][87424] Updated weights for policy 0, policy_version 339229 (0.0012) -[2023-11-28 09:05:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 173580288. Throughput: 0: 2731.9, 1: 2754.0. Samples: 173597756. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:05:58,445][86177] Avg episode reward: [(0, '-566.110'), (1, '-585.320')] -[2023-11-28 09:05:58,941][87426] Updated weights for policy 1, policy_version 338850 (0.0007) -[2023-11-28 09:05:59,335][87426] Updated weights for policy 1, policy_version 338860 (0.0009) -[2023-11-28 09:05:59,703][87426] Updated weights for policy 1, policy_version 338870 (0.0007) -[2023-11-28 09:06:00,077][87426] Updated weights for policy 1, policy_version 338880 (0.0010) -[2023-11-28 09:06:00,365][87424] Updated weights for policy 0, policy_version 339239 (0.0009) -[2023-11-28 09:06:00,746][87424] Updated weights for policy 0, policy_version 339249 (0.0010) -[2023-11-28 09:06:01,125][87424] Updated weights for policy 0, policy_version 339259 (0.0007) -[2023-11-28 09:06:02,578][87426] Updated weights for policy 1, policy_version 338890 (0.0012) -[2023-11-28 09:06:02,952][87426] Updated weights for policy 1, policy_version 338900 (0.0012) -[2023-11-28 09:06:03,285][87424] Updated weights for policy 0, policy_version 339269 (0.0007) -[2023-11-28 09:06:03,331][87426] Updated weights for policy 1, policy_version 338910 (0.0011) -[2023-11-28 09:06:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 173613056. Throughput: 0: 2784.6, 1: 2736.2. Samples: 173623576. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:03,445][86177] Avg episode reward: [(0, '-536.810'), (1, '-585.820')] -[2023-11-28 09:06:03,660][87424] Updated weights for policy 0, policy_version 339279 (0.0010) -[2023-11-28 09:06:04,039][87424] Updated weights for policy 0, policy_version 339289 (0.0008) -[2023-11-28 09:06:05,253][87426] Updated weights for policy 1, policy_version 338920 (0.0009) -[2023-11-28 09:06:05,627][87426] Updated weights for policy 1, policy_version 338930 (0.0008) -[2023-11-28 09:06:06,007][87426] Updated weights for policy 1, policy_version 338940 (0.0007) -[2023-11-28 09:06:06,545][87424] Updated weights for policy 0, policy_version 339299 (0.0009) -[2023-11-28 09:06:06,939][87424] Updated weights for policy 0, policy_version 339309 (0.0012) -[2023-11-28 09:06:07,320][87424] Updated weights for policy 0, policy_version 339319 (0.0012) -[2023-11-28 09:06:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 173637632. Throughput: 0: 2810.8, 1: 2714.7. Samples: 173655644. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:08,445][86177] Avg episode reward: [(0, '-535.070'), (1, '-608.340')] -[2023-11-28 09:06:08,455][87426] Updated weights for policy 1, policy_version 338950 (0.0007) -[2023-11-28 09:06:08,836][87426] Updated weights for policy 1, policy_version 338960 (0.0011) -[2023-11-28 09:06:09,158][87424] Updated weights for policy 0, policy_version 339329 (0.0011) -[2023-11-28 09:06:09,210][87426] Updated weights for policy 1, policy_version 338970 (0.0012) -[2023-11-28 09:06:09,536][87424] Updated weights for policy 0, policy_version 339339 (0.0008) -[2023-11-28 09:06:09,909][87424] Updated weights for policy 0, policy_version 339349 (0.0009) -[2023-11-28 09:06:10,294][87424] Updated weights for policy 0, policy_version 339359 (0.0011) -[2023-11-28 09:06:11,461][87426] Updated weights for policy 1, policy_version 338980 (0.0011) -[2023-11-28 09:06:11,858][87426] Updated weights for policy 1, policy_version 338990 (0.0012) -[2023-11-28 09:06:12,109][87424] Updated weights for policy 0, policy_version 339369 (0.0009) -[2023-11-28 09:06:12,232][87426] Updated weights for policy 1, policy_version 339000 (0.0012) -[2023-11-28 09:06:12,489][87424] Updated weights for policy 0, policy_version 339379 (0.0011) -[2023-11-28 09:06:12,871][87424] Updated weights for policy 0, policy_version 339389 (0.0009) -[2023-11-28 09:06:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5470.6). Total num frames: 173670400. Throughput: 0: 2817.7, 1: 2692.5. Samples: 173680252. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:13,445][86177] Avg episode reward: [(0, '-544.730'), (1, '-592.400')] -[2023-11-28 09:06:14,349][87426] Updated weights for policy 1, policy_version 339010 (0.0012) -[2023-11-28 09:06:14,620][87424] Updated weights for policy 0, policy_version 339399 (0.0012) -[2023-11-28 09:06:14,734][87426] Updated weights for policy 1, policy_version 339020 (0.0010) -[2023-11-28 09:06:15,007][87424] Updated weights for policy 0, policy_version 339409 (0.0010) -[2023-11-28 09:06:15,118][87426] Updated weights for policy 1, policy_version 339030 (0.0011) -[2023-11-28 09:06:15,384][87424] Updated weights for policy 0, policy_version 339419 (0.0010) -[2023-11-28 09:06:15,495][87426] Updated weights for policy 1, policy_version 339040 (0.0011) -[2023-11-28 09:06:17,433][87426] Updated weights for policy 1, policy_version 339050 (0.0007) -[2023-11-28 09:06:17,528][87424] Updated weights for policy 0, policy_version 339429 (0.0009) -[2023-11-28 09:06:17,817][87426] Updated weights for policy 1, policy_version 339060 (0.0008) -[2023-11-28 09:06:17,911][87424] Updated weights for policy 0, policy_version 339439 (0.0009) -[2023-11-28 09:06:18,193][87426] Updated weights for policy 1, policy_version 339070 (0.0008) -[2023-11-28 09:06:18,296][87424] Updated weights for policy 0, policy_version 339449 (0.0011) -[2023-11-28 09:06:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 173694976. Throughput: 0: 2841.7, 1: 2690.3. Samples: 173705832. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:18,446][86177] Avg episode reward: [(0, '-540.130'), (1, '-588.740')] -[2023-11-28 09:06:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000339072_86802432.pth... -[2023-11-28 09:06:18,502][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000336512_86147072.pth -[2023-11-28 09:06:18,551][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000339456_86900736.pth... -[2023-11-28 09:06:18,581][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000336896_86245376.pth -[2023-11-28 09:06:20,444][87426] Updated weights for policy 1, policy_version 339080 (0.0010) -[2023-11-28 09:06:20,774][87424] Updated weights for policy 0, policy_version 339459 (0.0011) -[2023-11-28 09:06:20,821][87426] Updated weights for policy 1, policy_version 339090 (0.0011) -[2023-11-28 09:06:21,163][87424] Updated weights for policy 0, policy_version 339469 (0.0012) -[2023-11-28 09:06:21,205][87426] Updated weights for policy 1, policy_version 339100 (0.0011) -[2023-11-28 09:06:21,544][87424] Updated weights for policy 0, policy_version 339479 (0.0012) -[2023-11-28 09:06:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 173719552. Throughput: 0: 2774.8, 1: 2684.4. Samples: 173736796. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:23,445][86177] Avg episode reward: [(0, '-541.530'), (1, '-568.210')] -[2023-11-28 09:06:23,746][87426] Updated weights for policy 1, policy_version 339110 (0.0010) -[2023-11-28 09:06:23,828][87424] Updated weights for policy 0, policy_version 339489 (0.0012) -[2023-11-28 09:06:24,119][87426] Updated weights for policy 1, policy_version 339120 (0.0009) -[2023-11-28 09:06:24,208][87424] Updated weights for policy 0, policy_version 339499 (0.0010) -[2023-11-28 09:06:24,513][87426] Updated weights for policy 1, policy_version 339130 (0.0008) -[2023-11-28 09:06:24,590][87424] Updated weights for policy 0, policy_version 339509 (0.0012) -[2023-11-28 09:06:24,971][87424] Updated weights for policy 0, policy_version 339519 (0.0009) -[2023-11-28 09:06:26,732][87424] Updated weights for policy 0, policy_version 339529 (0.0011) -[2023-11-28 09:06:26,790][87426] Updated weights for policy 1, policy_version 339140 (0.0009) -[2023-11-28 09:06:27,111][87424] Updated weights for policy 0, policy_version 339539 (0.0012) -[2023-11-28 09:06:27,161][87426] Updated weights for policy 1, policy_version 339150 (0.0007) -[2023-11-28 09:06:27,496][87424] Updated weights for policy 0, policy_version 339549 (0.0012) -[2023-11-28 09:06:27,539][87426] Updated weights for policy 1, policy_version 339160 (0.0008) -[2023-11-28 09:06:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 173752320. Throughput: 0: 2772.3, 1: 2681.9. Samples: 173760848. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:28,446][86177] Avg episode reward: [(0, '-532.970'), (1, '-578.960')] -[2023-11-28 09:06:29,686][87424] Updated weights for policy 0, policy_version 339559 (0.0012) -[2023-11-28 09:06:29,766][87426] Updated weights for policy 1, policy_version 339170 (0.0008) -[2023-11-28 09:06:30,069][87424] Updated weights for policy 0, policy_version 339569 (0.0010) -[2023-11-28 09:06:30,152][87426] Updated weights for policy 1, policy_version 339180 (0.0011) -[2023-11-28 09:06:30,456][87424] Updated weights for policy 0, policy_version 339579 (0.0011) -[2023-11-28 09:06:30,529][87426] Updated weights for policy 1, policy_version 339190 (0.0008) -[2023-11-28 09:06:30,901][87426] Updated weights for policy 1, policy_version 339200 (0.0009) -[2023-11-28 09:06:32,919][87426] Updated weights for policy 1, policy_version 339210 (0.0010) -[2023-11-28 09:06:33,011][87424] Updated weights for policy 0, policy_version 339589 (0.0011) -[2023-11-28 09:06:33,302][87426] Updated weights for policy 1, policy_version 339220 (0.0011) -[2023-11-28 09:06:33,392][87424] Updated weights for policy 0, policy_version 339599 (0.0010) -[2023-11-28 09:06:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 173768704. Throughput: 0: 2773.3, 1: 2681.8. Samples: 173786672. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:33,445][86177] Avg episode reward: [(0, '-530.070'), (1, '-556.450')] -[2023-11-28 09:06:33,682][87426] Updated weights for policy 1, policy_version 339230 (0.0011) -[2023-11-28 09:06:33,768][87424] Updated weights for policy 0, policy_version 339609 (0.0012) -[2023-11-28 09:06:35,295][87426] Updated weights for policy 1, policy_version 339240 (0.0012) -[2023-11-28 09:06:35,667][87426] Updated weights for policy 1, policy_version 339250 (0.0012) -[2023-11-28 09:06:35,848][87424] Updated weights for policy 0, policy_version 339619 (0.0012) -[2023-11-28 09:06:36,055][87426] Updated weights for policy 1, policy_version 339260 (0.0011) -[2023-11-28 09:06:36,228][87424] Updated weights for policy 0, policy_version 339629 (0.0009) -[2023-11-28 09:06:36,610][87424] Updated weights for policy 0, policy_version 339639 (0.0008) -[2023-11-28 09:06:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 173801472. Throughput: 0: 2800.1, 1: 2710.4. Samples: 173820928. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:38,445][86177] Avg episode reward: [(0, '-530.720'), (1, '-562.380')] -[2023-11-28 09:06:38,535][87426] Updated weights for policy 1, policy_version 339270 (0.0012) -[2023-11-28 09:06:38,924][87426] Updated weights for policy 1, policy_version 339280 (0.0008) -[2023-11-28 09:06:38,955][87424] Updated weights for policy 0, policy_version 339649 (0.0008) -[2023-11-28 09:06:39,296][87426] Updated weights for policy 1, policy_version 339290 (0.0009) -[2023-11-28 09:06:39,348][87424] Updated weights for policy 0, policy_version 339659 (0.0008) -[2023-11-28 09:06:39,720][87424] Updated weights for policy 0, policy_version 339669 (0.0008) -[2023-11-28 09:06:40,098][87424] Updated weights for policy 0, policy_version 339679 (0.0010) -[2023-11-28 09:06:41,464][87426] Updated weights for policy 1, policy_version 339300 (0.0008) -[2023-11-28 09:06:41,844][87426] Updated weights for policy 1, policy_version 339310 (0.0010) -[2023-11-28 09:06:42,092][87424] Updated weights for policy 0, policy_version 339689 (0.0012) -[2023-11-28 09:06:42,221][87426] Updated weights for policy 1, policy_version 339320 (0.0010) -[2023-11-28 09:06:42,468][87424] Updated weights for policy 0, policy_version 339699 (0.0012) -[2023-11-28 09:06:42,845][87424] Updated weights for policy 0, policy_version 339709 (0.0012) -[2023-11-28 09:06:43,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 173834240. Throughput: 0: 2782.8, 1: 2695.0. Samples: 173844260. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:43,445][86177] Avg episode reward: [(0, '-527.110'), (1, '-575.880')] -[2023-11-28 09:06:44,160][87426] Updated weights for policy 1, policy_version 339330 (0.0010) -[2023-11-28 09:06:44,556][87426] Updated weights for policy 1, policy_version 339340 (0.0012) -[2023-11-28 09:06:44,632][87424] Updated weights for policy 0, policy_version 339719 (0.0009) -[2023-11-28 09:06:44,932][87426] Updated weights for policy 1, policy_version 339350 (0.0011) -[2023-11-28 09:06:45,014][87424] Updated weights for policy 0, policy_version 339729 (0.0007) -[2023-11-28 09:06:45,310][87426] Updated weights for policy 1, policy_version 339360 (0.0011) -[2023-11-28 09:06:45,404][87424] Updated weights for policy 0, policy_version 339739 (0.0008) -[2023-11-28 09:06:47,609][87424] Updated weights for policy 0, policy_version 339749 (0.0010) -[2023-11-28 09:06:47,695][87426] Updated weights for policy 1, policy_version 339370 (0.0009) -[2023-11-28 09:06:47,985][87424] Updated weights for policy 0, policy_version 339759 (0.0011) -[2023-11-28 09:06:48,072][87426] Updated weights for policy 1, policy_version 339380 (0.0011) -[2023-11-28 09:06:48,373][87424] Updated weights for policy 0, policy_version 339769 (0.0012) -[2023-11-28 09:06:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 173850624. Throughput: 0: 2745.2, 1: 2688.5. Samples: 173868096. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:48,445][86177] Avg episode reward: [(0, '-534.820'), (1, '-584.140')] -[2023-11-28 09:06:48,449][87426] Updated weights for policy 1, policy_version 339390 (0.0012) -[2023-11-28 09:06:50,591][87426] Updated weights for policy 1, policy_version 339400 (0.0010) -[2023-11-28 09:06:50,704][87424] Updated weights for policy 0, policy_version 339779 (0.0010) -[2023-11-28 09:06:50,966][87426] Updated weights for policy 1, policy_version 339410 (0.0011) -[2023-11-28 09:06:51,093][87424] Updated weights for policy 0, policy_version 339789 (0.0010) -[2023-11-28 09:06:51,351][87426] Updated weights for policy 1, policy_version 339420 (0.0011) -[2023-11-28 09:06:51,478][87424] Updated weights for policy 0, policy_version 339799 (0.0011) -[2023-11-28 09:06:53,448][86177] Fps is (10 sec: 4913.2, 60 sec: 5461.0, 300 sec: 5442.7). Total num frames: 173883392. Throughput: 0: 2738.1, 1: 2684.8. Samples: 173899696. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:53,449][86177] Avg episode reward: [(0, '-537.410'), (1, '-601.470')] -[2023-11-28 09:06:53,487][87424] Updated weights for policy 0, policy_version 339809 (0.0012) -[2023-11-28 09:06:53,652][87426] Updated weights for policy 1, policy_version 339430 (0.0010) -[2023-11-28 09:06:53,871][87424] Updated weights for policy 0, policy_version 339819 (0.0011) -[2023-11-28 09:06:54,028][87426] Updated weights for policy 1, policy_version 339440 (0.0012) -[2023-11-28 09:06:54,248][87424] Updated weights for policy 0, policy_version 339829 (0.0012) -[2023-11-28 09:06:54,393][87426] Updated weights for policy 1, policy_version 339450 (0.0007) -[2023-11-28 09:06:54,628][87424] Updated weights for policy 0, policy_version 339839 (0.0010) -[2023-11-28 09:06:56,970][87426] Updated weights for policy 1, policy_version 339460 (0.0010) -[2023-11-28 09:06:57,241][87424] Updated weights for policy 0, policy_version 339849 (0.0011) -[2023-11-28 09:06:57,354][87426] Updated weights for policy 1, policy_version 339470 (0.0007) -[2023-11-28 09:06:57,624][87424] Updated weights for policy 0, policy_version 339859 (0.0007) -[2023-11-28 09:06:57,732][87426] Updated weights for policy 1, policy_version 339480 (0.0007) -[2023-11-28 09:06:58,004][87424] Updated weights for policy 0, policy_version 339869 (0.0008) -[2023-11-28 09:06:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 173916160. Throughput: 0: 2718.9, 1: 2691.9. Samples: 173923736. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:06:58,445][86177] Avg episode reward: [(0, '-540.750'), (1, '-639.740')] -[2023-11-28 09:07:00,068][87426] Updated weights for policy 1, policy_version 339490 (0.0008) -[2023-11-28 09:07:00,446][87426] Updated weights for policy 1, policy_version 339500 (0.0007) -[2023-11-28 09:07:00,576][87424] Updated weights for policy 0, policy_version 339879 (0.0009) -[2023-11-28 09:07:00,826][87426] Updated weights for policy 1, policy_version 339510 (0.0008) -[2023-11-28 09:07:00,949][87424] Updated weights for policy 0, policy_version 339889 (0.0012) -[2023-11-28 09:07:01,209][87426] Updated weights for policy 1, policy_version 339520 (0.0008) -[2023-11-28 09:07:01,337][87424] Updated weights for policy 0, policy_version 339899 (0.0010) -[2023-11-28 09:07:03,363][87424] Updated weights for policy 0, policy_version 339909 (0.0008) -[2023-11-28 09:07:03,444][86177] Fps is (10 sec: 4917.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 173932544. Throughput: 0: 2682.5, 1: 2670.9. Samples: 173946732. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:07:03,445][86177] Avg episode reward: [(0, '-549.360'), (1, '-647.350')] -[2023-11-28 09:07:03,721][87426] Updated weights for policy 1, policy_version 339530 (0.0012) -[2023-11-28 09:07:03,752][87424] Updated weights for policy 0, policy_version 339919 (0.0010) -[2023-11-28 09:07:04,087][87426] Updated weights for policy 1, policy_version 339540 (0.0011) -[2023-11-28 09:07:04,133][87424] Updated weights for policy 0, policy_version 339929 (0.0008) -[2023-11-28 09:07:04,468][87426] Updated weights for policy 1, policy_version 339550 (0.0012) -[2023-11-28 09:07:06,433][87424] Updated weights for policy 0, policy_version 339939 (0.0011) -[2023-11-28 09:07:06,813][87424] Updated weights for policy 0, policy_version 339949 (0.0011) -[2023-11-28 09:07:07,068][87426] Updated weights for policy 1, policy_version 339560 (0.0009) -[2023-11-28 09:07:07,190][87424] Updated weights for policy 0, policy_version 339959 (0.0011) -[2023-11-28 09:07:07,448][87426] Updated weights for policy 1, policy_version 339570 (0.0009) -[2023-11-28 09:07:07,828][87426] Updated weights for policy 1, policy_version 339580 (0.0007) -[2023-11-28 09:07:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 173965312. Throughput: 0: 2708.5, 1: 2664.5. Samples: 173978584. Policy #0 lag: (min: 23.0, avg: 30.5, max: 55.0) -[2023-11-28 09:07:08,445][86177] Avg episode reward: [(0, '-546.870'), (1, '-635.680')] -[2023-11-28 09:07:09,393][87424] Updated weights for policy 0, policy_version 339969 (0.0011) -[2023-11-28 09:07:09,770][87424] Updated weights for policy 0, policy_version 339979 (0.0011) -[2023-11-28 09:07:10,163][87424] Updated weights for policy 0, policy_version 339989 (0.0009) -[2023-11-28 09:07:10,354][87426] Updated weights for policy 1, policy_version 339590 (0.0010) -[2023-11-28 09:07:10,541][87424] Updated weights for policy 0, policy_version 339999 (0.0010) -[2023-11-28 09:07:10,733][87426] Updated weights for policy 1, policy_version 339600 (0.0008) -[2023-11-28 09:07:11,115][87426] Updated weights for policy 1, policy_version 339610 (0.0009) -[2023-11-28 09:07:12,801][87424] Updated weights for policy 0, policy_version 340009 (0.0012) -[2023-11-28 09:07:13,188][87424] Updated weights for policy 0, policy_version 340019 (0.0010) -[2023-11-28 09:07:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.1). Total num frames: 173981696. Throughput: 0: 2719.5, 1: 2668.1. Samples: 174003288. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:13,445][86177] Avg episode reward: [(0, '-547.740'), (1, '-638.330')] -[2023-11-28 09:07:13,570][87424] Updated weights for policy 0, policy_version 340029 (0.0012) -[2023-11-28 09:07:13,685][87426] Updated weights for policy 1, policy_version 339620 (0.0009) -[2023-11-28 09:07:14,066][87426] Updated weights for policy 1, policy_version 339630 (0.0007) -[2023-11-28 09:07:14,443][87426] Updated weights for policy 1, policy_version 339640 (0.0007) -[2023-11-28 09:07:15,406][87424] Updated weights for policy 0, policy_version 340039 (0.0012) -[2023-11-28 09:07:15,790][87424] Updated weights for policy 0, policy_version 340049 (0.0011) -[2023-11-28 09:07:16,167][87424] Updated weights for policy 0, policy_version 340059 (0.0012) -[2023-11-28 09:07:16,239][87426] Updated weights for policy 1, policy_version 339650 (0.0007) -[2023-11-28 09:07:16,624][87426] Updated weights for policy 1, policy_version 339660 (0.0010) -[2023-11-28 09:07:17,014][87426] Updated weights for policy 1, policy_version 339670 (0.0009) -[2023-11-28 09:07:17,387][87426] Updated weights for policy 1, policy_version 339680 (0.0007) -[2023-11-28 09:07:17,811][87424] Updated weights for policy 0, policy_version 340069 (0.0010) -[2023-11-28 09:07:18,195][87424] Updated weights for policy 0, policy_version 340079 (0.0007) -[2023-11-28 09:07:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 174014464. Throughput: 0: 2701.3, 1: 2663.2. Samples: 174028072. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:18,445][86177] Avg episode reward: [(0, '-545.840'), (1, '-625.670')] -[2023-11-28 09:07:18,572][87424] Updated weights for policy 0, policy_version 340089 (0.0008) -[2023-11-28 09:07:19,798][87426] Updated weights for policy 1, policy_version 339690 (0.0010) -[2023-11-28 09:07:20,170][87426] Updated weights for policy 1, policy_version 339700 (0.0012) -[2023-11-28 09:07:20,553][87426] Updated weights for policy 1, policy_version 339710 (0.0011) -[2023-11-28 09:07:20,689][87424] Updated weights for policy 0, policy_version 340099 (0.0009) -[2023-11-28 09:07:21,059][87424] Updated weights for policy 0, policy_version 340109 (0.0012) -[2023-11-28 09:07:21,443][87424] Updated weights for policy 0, policy_version 340119 (0.0012) -[2023-11-28 09:07:22,675][87426] Updated weights for policy 1, policy_version 339720 (0.0012) -[2023-11-28 09:07:23,039][87426] Updated weights for policy 1, policy_version 339730 (0.0009) -[2023-11-28 09:07:23,419][87426] Updated weights for policy 1, policy_version 339740 (0.0008) -[2023-11-28 09:07:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 174039040. Throughput: 0: 2678.9, 1: 2625.2. Samples: 174059612. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:23,445][86177] Avg episode reward: [(0, '-541.970'), (1, '-623.060')] -[2023-11-28 09:07:24,042][87424] Updated weights for policy 0, policy_version 340129 (0.0011) -[2023-11-28 09:07:24,427][87424] Updated weights for policy 0, policy_version 340139 (0.0007) -[2023-11-28 09:07:24,818][87424] Updated weights for policy 0, policy_version 340149 (0.0008) -[2023-11-28 09:07:25,202][87424] Updated weights for policy 0, policy_version 340159 (0.0009) -[2023-11-28 09:07:25,421][87426] Updated weights for policy 1, policy_version 339750 (0.0010) -[2023-11-28 09:07:25,791][87426] Updated weights for policy 1, policy_version 339760 (0.0007) -[2023-11-28 09:07:26,177][87426] Updated weights for policy 1, policy_version 339770 (0.0007) -[2023-11-28 09:07:27,681][87424] Updated weights for policy 0, policy_version 340169 (0.0011) -[2023-11-28 09:07:28,076][87424] Updated weights for policy 0, policy_version 340179 (0.0011) -[2023-11-28 09:07:28,281][87426] Updated weights for policy 1, policy_version 339780 (0.0009) -[2023-11-28 09:07:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 174063616. Throughput: 0: 2679.0, 1: 2629.2. Samples: 174083132. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:28,445][86177] Avg episode reward: [(0, '-539.510'), (1, '-621.250')] -[2023-11-28 09:07:28,455][87424] Updated weights for policy 0, policy_version 340189 (0.0009) -[2023-11-28 09:07:28,657][87426] Updated weights for policy 1, policy_version 339790 (0.0008) -[2023-11-28 09:07:29,042][87426] Updated weights for policy 1, policy_version 339800 (0.0008) -[2023-11-28 09:07:30,780][87424] Updated weights for policy 0, policy_version 340199 (0.0010) -[2023-11-28 09:07:31,157][87424] Updated weights for policy 0, policy_version 340209 (0.0012) -[2023-11-28 09:07:31,352][87426] Updated weights for policy 1, policy_version 339810 (0.0008) -[2023-11-28 09:07:31,538][87424] Updated weights for policy 0, policy_version 340219 (0.0008) -[2023-11-28 09:07:31,725][87426] Updated weights for policy 1, policy_version 339820 (0.0009) -[2023-11-28 09:07:32,105][87426] Updated weights for policy 1, policy_version 339830 (0.0008) -[2023-11-28 09:07:32,488][87426] Updated weights for policy 1, policy_version 339840 (0.0008) -[2023-11-28 09:07:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 174096384. Throughput: 0: 2678.0, 1: 2638.2. Samples: 174107324. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:33,445][86177] Avg episode reward: [(0, '-536.950'), (1, '-648.940')] -[2023-11-28 09:07:33,954][87424] Updated weights for policy 0, policy_version 340229 (0.0008) -[2023-11-28 09:07:34,319][87426] Updated weights for policy 1, policy_version 339850 (0.0008) -[2023-11-28 09:07:34,334][87424] Updated weights for policy 0, policy_version 340239 (0.0009) -[2023-11-28 09:07:34,706][87426] Updated weights for policy 1, policy_version 339860 (0.0008) -[2023-11-28 09:07:34,707][87424] Updated weights for policy 0, policy_version 340249 (0.0010) -[2023-11-28 09:07:35,090][87426] Updated weights for policy 1, policy_version 339870 (0.0009) -[2023-11-28 09:07:37,056][87424] Updated weights for policy 0, policy_version 340259 (0.0011) -[2023-11-28 09:07:37,449][87424] Updated weights for policy 0, policy_version 340269 (0.0012) -[2023-11-28 09:07:37,548][87426] Updated weights for policy 1, policy_version 339880 (0.0008) -[2023-11-28 09:07:37,842][87424] Updated weights for policy 0, policy_version 340279 (0.0011) -[2023-11-28 09:07:37,932][87426] Updated weights for policy 1, policy_version 339890 (0.0008) -[2023-11-28 09:07:38,305][87426] Updated weights for policy 1, policy_version 339900 (0.0008) -[2023-11-28 09:07:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 174120960. Throughput: 0: 2692.1, 1: 2626.9. Samples: 174139028. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:38,445][86177] Avg episode reward: [(0, '-530.240'), (1, '-655.430')] -[2023-11-28 09:07:40,168][87426] Updated weights for policy 1, policy_version 339910 (0.0010) -[2023-11-28 09:07:40,272][87424] Updated weights for policy 0, policy_version 340289 (0.0010) -[2023-11-28 09:07:40,548][87426] Updated weights for policy 1, policy_version 339920 (0.0011) -[2023-11-28 09:07:40,647][87424] Updated weights for policy 0, policy_version 340299 (0.0011) -[2023-11-28 09:07:40,915][87426] Updated weights for policy 1, policy_version 339930 (0.0011) -[2023-11-28 09:07:41,035][87424] Updated weights for policy 0, policy_version 340309 (0.0010) -[2023-11-28 09:07:41,414][87424] Updated weights for policy 0, policy_version 340319 (0.0011) -[2023-11-28 09:07:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 174145536. Throughput: 0: 2686.5, 1: 2628.2. Samples: 174162896. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:43,445][86177] Avg episode reward: [(0, '-528.740'), (1, '-668.410')] -[2023-11-28 09:07:43,445][87426] Updated weights for policy 1, policy_version 339940 (0.0011) -[2023-11-28 09:07:43,539][87424] Updated weights for policy 0, policy_version 340329 (0.0011) -[2023-11-28 09:07:43,818][87426] Updated weights for policy 1, policy_version 339950 (0.0012) -[2023-11-28 09:07:43,912][87424] Updated weights for policy 0, policy_version 340339 (0.0012) -[2023-11-28 09:07:44,193][87426] Updated weights for policy 1, policy_version 339960 (0.0011) -[2023-11-28 09:07:44,300][87424] Updated weights for policy 0, policy_version 340349 (0.0007) -[2023-11-28 09:07:46,526][87426] Updated weights for policy 1, policy_version 339970 (0.0011) -[2023-11-28 09:07:46,719][87424] Updated weights for policy 0, policy_version 340359 (0.0010) -[2023-11-28 09:07:46,898][87426] Updated weights for policy 1, policy_version 339980 (0.0008) -[2023-11-28 09:07:47,105][87424] Updated weights for policy 0, policy_version 340369 (0.0008) -[2023-11-28 09:07:47,281][87426] Updated weights for policy 1, policy_version 339990 (0.0008) -[2023-11-28 09:07:47,497][87424] Updated weights for policy 0, policy_version 340379 (0.0007) -[2023-11-28 09:07:47,662][87426] Updated weights for policy 1, policy_version 340000 (0.0011) -[2023-11-28 09:07:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 174178304. Throughput: 0: 2701.6, 1: 2640.3. Samples: 174187116. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:48,445][86177] Avg episode reward: [(0, '-533.750'), (1, '-649.060')] -[2023-11-28 09:07:49,579][87424] Updated weights for policy 0, policy_version 340389 (0.0009) -[2023-11-28 09:07:49,696][87426] Updated weights for policy 1, policy_version 340010 (0.0012) -[2023-11-28 09:07:49,986][87424] Updated weights for policy 0, policy_version 340399 (0.0011) -[2023-11-28 09:07:50,076][87426] Updated weights for policy 1, policy_version 340020 (0.0011) -[2023-11-28 09:07:50,367][87424] Updated weights for policy 0, policy_version 340409 (0.0012) -[2023-11-28 09:07:50,460][87426] Updated weights for policy 1, policy_version 340030 (0.0011) -[2023-11-28 09:07:52,755][87424] Updated weights for policy 0, policy_version 340419 (0.0011) -[2023-11-28 09:07:52,875][87426] Updated weights for policy 1, policy_version 340040 (0.0010) -[2023-11-28 09:07:53,123][87424] Updated weights for policy 0, policy_version 340429 (0.0011) -[2023-11-28 09:07:53,243][87426] Updated weights for policy 1, policy_version 340050 (0.0009) -[2023-11-28 09:07:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.6, 300 sec: 5387.3). Total num frames: 174194688. Throughput: 0: 2692.7, 1: 2669.8. Samples: 174219896. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:53,445][86177] Avg episode reward: [(0, '-530.840'), (1, '-646.290')] -[2023-11-28 09:07:53,512][87424] Updated weights for policy 0, policy_version 340439 (0.0010) -[2023-11-28 09:07:53,620][87426] Updated weights for policy 1, policy_version 340060 (0.0011) -[2023-11-28 09:07:55,226][87424] Updated weights for policy 0, policy_version 340449 (0.0009) -[2023-11-28 09:07:55,607][87424] Updated weights for policy 0, policy_version 340459 (0.0007) -[2023-11-28 09:07:55,987][87424] Updated weights for policy 0, policy_version 340469 (0.0008) -[2023-11-28 09:07:56,024][87426] Updated weights for policy 1, policy_version 340070 (0.0009) -[2023-11-28 09:07:56,362][87424] Updated weights for policy 0, policy_version 340479 (0.0008) -[2023-11-28 09:07:56,395][87426] Updated weights for policy 1, policy_version 340080 (0.0008) -[2023-11-28 09:07:56,779][87426] Updated weights for policy 1, policy_version 340090 (0.0012) -[2023-11-28 09:07:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.2, 300 sec: 5415.0). Total num frames: 174227456. Throughput: 0: 2672.9, 1: 2680.4. Samples: 174244188. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:07:58,445][86177] Avg episode reward: [(0, '-532.530'), (1, '-628.520')] -[2023-11-28 09:07:58,553][87424] Updated weights for policy 0, policy_version 340489 (0.0012) -[2023-11-28 09:07:58,931][87424] Updated weights for policy 0, policy_version 340499 (0.0011) -[2023-11-28 09:07:59,283][87426] Updated weights for policy 1, policy_version 340100 (0.0010) -[2023-11-28 09:07:59,320][87424] Updated weights for policy 0, policy_version 340509 (0.0011) -[2023-11-28 09:07:59,665][87426] Updated weights for policy 1, policy_version 340110 (0.0007) -[2023-11-28 09:08:00,042][87426] Updated weights for policy 1, policy_version 340120 (0.0009) -[2023-11-28 09:08:01,794][87424] Updated weights for policy 0, policy_version 340519 (0.0010) -[2023-11-28 09:08:02,181][87424] Updated weights for policy 0, policy_version 340529 (0.0009) -[2023-11-28 09:08:02,555][87424] Updated weights for policy 0, policy_version 340539 (0.0009) -[2023-11-28 09:08:02,584][87426] Updated weights for policy 1, policy_version 340130 (0.0008) -[2023-11-28 09:08:02,952][87426] Updated weights for policy 1, policy_version 340140 (0.0008) -[2023-11-28 09:08:03,336][87426] Updated weights for policy 1, policy_version 340150 (0.0008) -[2023-11-28 09:08:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 174252032. Throughput: 0: 2644.3, 1: 2672.3. Samples: 174267316. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:08:03,445][86177] Avg episode reward: [(0, '-534.520'), (1, '-610.400')] -[2023-11-28 09:08:03,716][87426] Updated weights for policy 1, policy_version 340160 (0.0008) -[2023-11-28 09:08:05,134][87424] Updated weights for policy 0, policy_version 340549 (0.0012) -[2023-11-28 09:08:05,517][87424] Updated weights for policy 0, policy_version 340559 (0.0011) -[2023-11-28 09:08:05,899][87424] Updated weights for policy 0, policy_version 340569 (0.0008) -[2023-11-28 09:08:05,969][87426] Updated weights for policy 1, policy_version 340170 (0.0007) -[2023-11-28 09:08:06,353][87426] Updated weights for policy 1, policy_version 340180 (0.0008) -[2023-11-28 09:08:06,729][87426] Updated weights for policy 1, policy_version 340190 (0.0008) -[2023-11-28 09:08:07,995][87424] Updated weights for policy 0, policy_version 340579 (0.0009) -[2023-11-28 09:08:08,373][87424] Updated weights for policy 0, policy_version 340589 (0.0012) -[2023-11-28 09:08:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 174276608. Throughput: 0: 2657.9, 1: 2670.0. Samples: 174299364. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:08:08,445][86177] Avg episode reward: [(0, '-526.410'), (1, '-588.700')] -[2023-11-28 09:08:08,617][87426] Updated weights for policy 1, policy_version 340200 (0.0009) -[2023-11-28 09:08:08,754][87424] Updated weights for policy 0, policy_version 340599 (0.0011) -[2023-11-28 09:08:09,001][87426] Updated weights for policy 1, policy_version 340210 (0.0012) -[2023-11-28 09:08:09,380][87426] Updated weights for policy 1, policy_version 340220 (0.0008) -[2023-11-28 09:08:10,716][87424] Updated weights for policy 0, policy_version 340609 (0.0011) -[2023-11-28 09:08:11,103][87424] Updated weights for policy 0, policy_version 340619 (0.0011) -[2023-11-28 09:08:11,461][87426] Updated weights for policy 1, policy_version 340230 (0.0009) -[2023-11-28 09:08:11,487][87424] Updated weights for policy 0, policy_version 340629 (0.0009) -[2023-11-28 09:08:11,847][87426] Updated weights for policy 1, policy_version 340240 (0.0011) -[2023-11-28 09:08:11,870][87424] Updated weights for policy 0, policy_version 340639 (0.0011) -[2023-11-28 09:08:12,230][87426] Updated weights for policy 1, policy_version 340250 (0.0011) -[2023-11-28 09:08:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 174309376. Throughput: 0: 2680.4, 1: 2687.9. Samples: 174324704. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:08:13,445][86177] Avg episode reward: [(0, '-541.870'), (1, '-570.900')] -[2023-11-28 09:08:14,208][87424] Updated weights for policy 0, policy_version 340649 (0.0009) -[2023-11-28 09:08:14,480][87426] Updated weights for policy 1, policy_version 340260 (0.0008) -[2023-11-28 09:08:14,599][87424] Updated weights for policy 0, policy_version 340659 (0.0010) -[2023-11-28 09:08:14,868][87426] Updated weights for policy 1, policy_version 340270 (0.0007) -[2023-11-28 09:08:14,977][87424] Updated weights for policy 0, policy_version 340669 (0.0011) -[2023-11-28 09:08:15,236][87426] Updated weights for policy 1, policy_version 340280 (0.0009) -[2023-11-28 09:08:17,206][87426] Updated weights for policy 1, policy_version 340290 (0.0009) -[2023-11-28 09:08:17,304][87424] Updated weights for policy 0, policy_version 340679 (0.0012) -[2023-11-28 09:08:17,581][87426] Updated weights for policy 1, policy_version 340300 (0.0007) -[2023-11-28 09:08:17,671][87424] Updated weights for policy 0, policy_version 340689 (0.0011) -[2023-11-28 09:08:17,962][87426] Updated weights for policy 1, policy_version 340310 (0.0010) -[2023-11-28 09:08:18,053][87424] Updated weights for policy 0, policy_version 340699 (0.0012) -[2023-11-28 09:08:18,336][87426] Updated weights for policy 1, policy_version 340320 (0.0011) -[2023-11-28 09:08:18,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 174342144. Throughput: 0: 2674.8, 1: 2690.1. Samples: 174348748. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:08:18,445][86177] Avg episode reward: [(0, '-541.350'), (1, '-604.730')] -[2023-11-28 09:08:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000340320_87121920.pth... -[2023-11-28 09:08:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000340704_87220224.pth... -[2023-11-28 09:08:18,503][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000337792_86474752.pth -[2023-11-28 09:08:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000338176_86573056.pth -[2023-11-28 09:08:19,949][87424] Updated weights for policy 0, policy_version 340709 (0.0011) -[2023-11-28 09:08:20,328][87424] Updated weights for policy 0, policy_version 340719 (0.0008) -[2023-11-28 09:08:20,708][87424] Updated weights for policy 0, policy_version 340729 (0.0012) -[2023-11-28 09:08:20,741][87426] Updated weights for policy 1, policy_version 340330 (0.0011) -[2023-11-28 09:08:21,117][87426] Updated weights for policy 1, policy_version 340340 (0.0011) -[2023-11-28 09:08:21,501][87426] Updated weights for policy 1, policy_version 340350 (0.0012) -[2023-11-28 09:08:22,864][87424] Updated weights for policy 0, policy_version 340739 (0.0011) -[2023-11-28 09:08:23,246][87424] Updated weights for policy 0, policy_version 340749 (0.0012) -[2023-11-28 09:08:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 174358528. Throughput: 0: 2684.9, 1: 2684.6. Samples: 174380656. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:08:23,445][86177] Avg episode reward: [(0, '-542.340'), (1, '-589.000')] -[2023-11-28 09:08:23,634][87424] Updated weights for policy 0, policy_version 340759 (0.0012) -[2023-11-28 09:08:24,100][87426] Updated weights for policy 1, policy_version 340360 (0.0012) -[2023-11-28 09:08:24,483][87426] Updated weights for policy 1, policy_version 340370 (0.0007) -[2023-11-28 09:08:24,870][87426] Updated weights for policy 1, policy_version 340380 (0.0009) -[2023-11-28 09:08:25,323][87424] Updated weights for policy 0, policy_version 340769 (0.0012) -[2023-11-28 09:08:25,708][87424] Updated weights for policy 0, policy_version 340779 (0.0012) -[2023-11-28 09:08:26,081][87424] Updated weights for policy 0, policy_version 340789 (0.0012) -[2023-11-28 09:08:26,458][87424] Updated weights for policy 0, policy_version 340799 (0.0012) -[2023-11-28 09:08:27,047][87426] Updated weights for policy 1, policy_version 340390 (0.0010) -[2023-11-28 09:08:27,425][87426] Updated weights for policy 1, policy_version 340400 (0.0012) -[2023-11-28 09:08:27,811][87426] Updated weights for policy 1, policy_version 340410 (0.0011) -[2023-11-28 09:08:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 174391296. Throughput: 0: 2702.8, 1: 2673.4. Samples: 174404828. Policy #0 lag: (min: 4.0, avg: 22.8, max: 37.0) -[2023-11-28 09:08:28,446][86177] Avg episode reward: [(0, '-538.750'), (1, '-576.450')] -[2023-11-28 09:08:28,779][87424] Updated weights for policy 0, policy_version 340809 (0.0012) -[2023-11-28 09:08:29,162][87424] Updated weights for policy 0, policy_version 340819 (0.0011) -[2023-11-28 09:08:29,547][87424] Updated weights for policy 0, policy_version 340829 (0.0011) -[2023-11-28 09:08:30,061][87426] Updated weights for policy 1, policy_version 340420 (0.0011) -[2023-11-28 09:08:30,441][87426] Updated weights for policy 1, policy_version 340430 (0.0012) -[2023-11-28 09:08:30,817][87426] Updated weights for policy 1, policy_version 340440 (0.0012) -[2023-11-28 09:08:31,927][87424] Updated weights for policy 0, policy_version 340839 (0.0011) -[2023-11-28 09:08:32,308][87424] Updated weights for policy 0, policy_version 340849 (0.0009) -[2023-11-28 09:08:32,683][87424] Updated weights for policy 0, policy_version 340859 (0.0008) -[2023-11-28 09:08:33,203][87426] Updated weights for policy 1, policy_version 340450 (0.0012) -[2023-11-28 09:08:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 174415872. Throughput: 0: 2692.9, 1: 2678.6. Samples: 174428832. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:08:33,445][86177] Avg episode reward: [(0, '-530.470'), (1, '-571.240')] -[2023-11-28 09:08:33,580][87426] Updated weights for policy 1, policy_version 340460 (0.0012) -[2023-11-28 09:08:33,957][87426] Updated weights for policy 1, policy_version 340470 (0.0011) -[2023-11-28 09:08:34,345][87426] Updated weights for policy 1, policy_version 340480 (0.0011) -[2023-11-28 09:08:34,767][87424] Updated weights for policy 0, policy_version 340869 (0.0010) -[2023-11-28 09:08:35,155][87424] Updated weights for policy 0, policy_version 340879 (0.0012) -[2023-11-28 09:08:35,531][87424] Updated weights for policy 0, policy_version 340889 (0.0009) -[2023-11-28 09:08:36,239][87426] Updated weights for policy 1, policy_version 340490 (0.0012) -[2023-11-28 09:08:36,619][87426] Updated weights for policy 1, policy_version 340500 (0.0012) -[2023-11-28 09:08:36,996][87426] Updated weights for policy 1, policy_version 340510 (0.0011) -[2023-11-28 09:08:38,002][87424] Updated weights for policy 0, policy_version 340899 (0.0009) -[2023-11-28 09:08:38,390][87424] Updated weights for policy 0, policy_version 340909 (0.0010) -[2023-11-28 09:08:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 174440448. Throughput: 0: 2677.5, 1: 2661.9. Samples: 174460168. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:08:38,445][86177] Avg episode reward: [(0, '-539.890'), (1, '-518.730')] -[2023-11-28 09:08:38,768][87424] Updated weights for policy 0, policy_version 340919 (0.0010) -[2023-11-28 09:08:38,990][87426] Updated weights for policy 1, policy_version 340520 (0.0011) -[2023-11-28 09:08:39,361][87426] Updated weights for policy 1, policy_version 340530 (0.0012) -[2023-11-28 09:08:39,742][87426] Updated weights for policy 1, policy_version 340540 (0.0012) -[2023-11-28 09:08:40,652][87424] Updated weights for policy 0, policy_version 340929 (0.0009) -[2023-11-28 09:08:41,029][87424] Updated weights for policy 0, policy_version 340939 (0.0009) -[2023-11-28 09:08:41,412][87424] Updated weights for policy 0, policy_version 340949 (0.0007) -[2023-11-28 09:08:41,792][87424] Updated weights for policy 0, policy_version 340959 (0.0010) -[2023-11-28 09:08:41,876][87426] Updated weights for policy 1, policy_version 340550 (0.0011) -[2023-11-28 09:08:42,249][87426] Updated weights for policy 1, policy_version 340560 (0.0012) -[2023-11-28 09:08:42,636][87426] Updated weights for policy 1, policy_version 340570 (0.0012) -[2023-11-28 09:08:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 174473216. Throughput: 0: 2679.7, 1: 2670.2. Samples: 174484932. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:08:43,445][86177] Avg episode reward: [(0, '-545.830'), (1, '-521.270')] -[2023-11-28 09:08:43,882][87424] Updated weights for policy 0, policy_version 340969 (0.0012) -[2023-11-28 09:08:44,267][87424] Updated weights for policy 0, policy_version 340979 (0.0012) -[2023-11-28 09:08:44,493][87426] Updated weights for policy 1, policy_version 340580 (0.0011) -[2023-11-28 09:08:44,645][87424] Updated weights for policy 0, policy_version 340989 (0.0012) -[2023-11-28 09:08:44,872][87426] Updated weights for policy 1, policy_version 340590 (0.0009) -[2023-11-28 09:08:45,248][87426] Updated weights for policy 1, policy_version 340600 (0.0007) -[2023-11-28 09:08:47,040][87424] Updated weights for policy 0, policy_version 340999 (0.0012) -[2023-11-28 09:08:47,419][87424] Updated weights for policy 0, policy_version 341009 (0.0012) -[2023-11-28 09:08:47,647][87426] Updated weights for policy 1, policy_version 340610 (0.0011) -[2023-11-28 09:08:47,803][87424] Updated weights for policy 0, policy_version 341019 (0.0011) -[2023-11-28 09:08:48,028][87426] Updated weights for policy 1, policy_version 340620 (0.0011) -[2023-11-28 09:08:48,413][87426] Updated weights for policy 1, policy_version 340630 (0.0012) -[2023-11-28 09:08:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 174497792. Throughput: 0: 2726.8, 1: 2691.8. Samples: 174511152. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:08:48,445][86177] Avg episode reward: [(0, '-552.160'), (1, '-517.270')] -[2023-11-28 09:08:48,804][87426] Updated weights for policy 1, policy_version 340640 (0.0012) -[2023-11-28 09:08:49,996][87424] Updated weights for policy 0, policy_version 341029 (0.0011) -[2023-11-28 09:08:50,390][87424] Updated weights for policy 0, policy_version 341039 (0.0008) -[2023-11-28 09:08:50,773][87424] Updated weights for policy 0, policy_version 341049 (0.0012) -[2023-11-28 09:08:51,057][87426] Updated weights for policy 1, policy_version 340650 (0.0009) -[2023-11-28 09:08:51,435][87426] Updated weights for policy 1, policy_version 340660 (0.0012) -[2023-11-28 09:08:51,815][87426] Updated weights for policy 1, policy_version 340670 (0.0011) -[2023-11-28 09:08:53,224][87424] Updated weights for policy 0, policy_version 341059 (0.0010) -[2023-11-28 09:08:53,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 174522368. Throughput: 0: 2721.8, 1: 2715.0. Samples: 174544024. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:08:53,445][86177] Avg episode reward: [(0, '-549.100'), (1, '-514.250')] -[2023-11-28 09:08:53,620][87424] Updated weights for policy 0, policy_version 341069 (0.0010) -[2023-11-28 09:08:53,881][87426] Updated weights for policy 1, policy_version 340680 (0.0011) -[2023-11-28 09:08:53,999][87424] Updated weights for policy 0, policy_version 341079 (0.0011) -[2023-11-28 09:08:54,268][87426] Updated weights for policy 1, policy_version 340690 (0.0011) -[2023-11-28 09:08:54,645][87426] Updated weights for policy 1, policy_version 340700 (0.0007) -[2023-11-28 09:08:56,339][87424] Updated weights for policy 0, policy_version 341089 (0.0011) -[2023-11-28 09:08:56,718][87424] Updated weights for policy 0, policy_version 341099 (0.0010) -[2023-11-28 09:08:56,773][87426] Updated weights for policy 1, policy_version 340710 (0.0008) -[2023-11-28 09:08:57,100][87424] Updated weights for policy 0, policy_version 341109 (0.0008) -[2023-11-28 09:08:57,163][87426] Updated weights for policy 1, policy_version 340720 (0.0007) -[2023-11-28 09:08:57,488][87424] Updated weights for policy 0, policy_version 341119 (0.0007) -[2023-11-28 09:08:57,548][87426] Updated weights for policy 1, policy_version 340730 (0.0007) -[2023-11-28 09:08:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 174555136. Throughput: 0: 2705.2, 1: 2701.1. Samples: 174567988. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:08:58,445][86177] Avg episode reward: [(0, '-542.650'), (1, '-521.380')] -[2023-11-28 09:08:59,214][87426] Updated weights for policy 1, policy_version 340740 (0.0007) -[2023-11-28 09:08:59,234][87424] Updated weights for policy 0, policy_version 341129 (0.0008) -[2023-11-28 09:08:59,591][87426] Updated weights for policy 1, policy_version 340750 (0.0008) -[2023-11-28 09:08:59,618][87424] Updated weights for policy 0, policy_version 341139 (0.0007) -[2023-11-28 09:08:59,982][87426] Updated weights for policy 1, policy_version 340760 (0.0009) -[2023-11-28 09:09:00,004][87424] Updated weights for policy 0, policy_version 341149 (0.0011) -[2023-11-28 09:09:01,846][87426] Updated weights for policy 1, policy_version 340770 (0.0009) -[2023-11-28 09:09:01,968][87424] Updated weights for policy 0, policy_version 341159 (0.0009) -[2023-11-28 09:09:02,230][87426] Updated weights for policy 1, policy_version 340780 (0.0009) -[2023-11-28 09:09:02,343][87424] Updated weights for policy 0, policy_version 341169 (0.0011) -[2023-11-28 09:09:02,601][87426] Updated weights for policy 1, policy_version 340790 (0.0010) -[2023-11-28 09:09:02,727][87424] Updated weights for policy 0, policy_version 341179 (0.0011) -[2023-11-28 09:09:02,979][87426] Updated weights for policy 1, policy_version 340800 (0.0010) -[2023-11-28 09:09:03,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 174587904. Throughput: 0: 2728.2, 1: 2711.1. Samples: 174593516. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:03,445][86177] Avg episode reward: [(0, '-571.890'), (1, '-539.100')] -[2023-11-28 09:09:04,720][87426] Updated weights for policy 1, policy_version 340810 (0.0012) -[2023-11-28 09:09:05,101][87426] Updated weights for policy 1, policy_version 340820 (0.0012) -[2023-11-28 09:09:05,266][87424] Updated weights for policy 0, policy_version 341189 (0.0012) -[2023-11-28 09:09:05,479][87426] Updated weights for policy 1, policy_version 340830 (0.0010) -[2023-11-28 09:09:05,649][87424] Updated weights for policy 0, policy_version 341199 (0.0009) -[2023-11-28 09:09:06,034][87424] Updated weights for policy 0, policy_version 341209 (0.0008) -[2023-11-28 09:09:07,930][87426] Updated weights for policy 1, policy_version 340840 (0.0007) -[2023-11-28 09:09:08,314][87426] Updated weights for policy 1, policy_version 340850 (0.0008) -[2023-11-28 09:09:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 174604288. Throughput: 0: 2709.8, 1: 2748.6. Samples: 174626284. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:08,445][86177] Avg episode reward: [(0, '-569.610'), (1, '-552.580')] -[2023-11-28 09:09:08,453][87424] Updated weights for policy 0, policy_version 341219 (0.0008) -[2023-11-28 09:09:08,693][87426] Updated weights for policy 1, policy_version 340860 (0.0007) -[2023-11-28 09:09:08,864][87424] Updated weights for policy 0, policy_version 341229 (0.0009) -[2023-11-28 09:09:09,221][87424] Updated weights for policy 0, policy_version 341239 (0.0011) -[2023-11-28 09:09:11,014][87426] Updated weights for policy 1, policy_version 340870 (0.0012) -[2023-11-28 09:09:11,385][87426] Updated weights for policy 1, policy_version 340880 (0.0008) -[2023-11-28 09:09:11,500][87424] Updated weights for policy 0, policy_version 341249 (0.0011) -[2023-11-28 09:09:11,763][87426] Updated weights for policy 1, policy_version 340890 (0.0010) -[2023-11-28 09:09:11,884][87424] Updated weights for policy 0, policy_version 341259 (0.0011) -[2023-11-28 09:09:12,269][87424] Updated weights for policy 0, policy_version 341269 (0.0008) -[2023-11-28 09:09:12,646][87424] Updated weights for policy 0, policy_version 341279 (0.0010) -[2023-11-28 09:09:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 174637056. Throughput: 0: 2689.7, 1: 2762.0. Samples: 174650152. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:13,445][86177] Avg episode reward: [(0, '-563.480'), (1, '-568.480')] -[2023-11-28 09:09:14,024][87426] Updated weights for policy 1, policy_version 340900 (0.0012) -[2023-11-28 09:09:14,413][87426] Updated weights for policy 1, policy_version 340910 (0.0012) -[2023-11-28 09:09:14,790][87426] Updated weights for policy 1, policy_version 340920 (0.0011) -[2023-11-28 09:09:15,051][87424] Updated weights for policy 0, policy_version 341289 (0.0008) -[2023-11-28 09:09:15,442][87424] Updated weights for policy 0, policy_version 341299 (0.0010) -[2023-11-28 09:09:15,828][87424] Updated weights for policy 0, policy_version 341309 (0.0012) -[2023-11-28 09:09:17,217][87426] Updated weights for policy 1, policy_version 340930 (0.0012) -[2023-11-28 09:09:17,594][87426] Updated weights for policy 1, policy_version 340940 (0.0008) -[2023-11-28 09:09:17,741][87424] Updated weights for policy 0, policy_version 341319 (0.0009) -[2023-11-28 09:09:17,972][87426] Updated weights for policy 1, policy_version 340950 (0.0009) -[2023-11-28 09:09:18,127][87424] Updated weights for policy 0, policy_version 341329 (0.0007) -[2023-11-28 09:09:18,353][87426] Updated weights for policy 1, policy_version 340960 (0.0007) -[2023-11-28 09:09:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 174661632. Throughput: 0: 2705.1, 1: 2766.2. Samples: 174675040. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:18,445][86177] Avg episode reward: [(0, '-559.240'), (1, '-569.030')] -[2023-11-28 09:09:18,499][87424] Updated weights for policy 0, policy_version 341339 (0.0007) -[2023-11-28 09:09:20,455][87426] Updated weights for policy 1, policy_version 340970 (0.0008) -[2023-11-28 09:09:20,628][87424] Updated weights for policy 0, policy_version 341349 (0.0010) -[2023-11-28 09:09:20,823][87426] Updated weights for policy 1, policy_version 340980 (0.0008) -[2023-11-28 09:09:21,013][87424] Updated weights for policy 0, policy_version 341359 (0.0012) -[2023-11-28 09:09:21,201][87426] Updated weights for policy 1, policy_version 340990 (0.0009) -[2023-11-28 09:09:21,392][87424] Updated weights for policy 0, policy_version 341369 (0.0012) -[2023-11-28 09:09:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 174686208. Throughput: 0: 2710.8, 1: 2763.5. Samples: 174706512. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:23,445][86177] Avg episode reward: [(0, '-526.030'), (1, '-561.370')] -[2023-11-28 09:09:23,580][87426] Updated weights for policy 1, policy_version 341000 (0.0010) -[2023-11-28 09:09:23,744][87424] Updated weights for policy 0, policy_version 341379 (0.0012) -[2023-11-28 09:09:23,958][87426] Updated weights for policy 1, policy_version 341010 (0.0010) -[2023-11-28 09:09:24,124][87424] Updated weights for policy 0, policy_version 341389 (0.0010) -[2023-11-28 09:09:24,337][87426] Updated weights for policy 1, policy_version 341020 (0.0008) -[2023-11-28 09:09:24,506][87424] Updated weights for policy 0, policy_version 341399 (0.0008) -[2023-11-28 09:09:26,309][87424] Updated weights for policy 0, policy_version 341409 (0.0007) -[2023-11-28 09:09:26,352][87426] Updated weights for policy 1, policy_version 341030 (0.0009) -[2023-11-28 09:09:26,694][87424] Updated weights for policy 0, policy_version 341419 (0.0008) -[2023-11-28 09:09:26,723][87426] Updated weights for policy 1, policy_version 341040 (0.0012) -[2023-11-28 09:09:27,083][87424] Updated weights for policy 0, policy_version 341429 (0.0011) -[2023-11-28 09:09:27,115][87426] Updated weights for policy 1, policy_version 341050 (0.0011) -[2023-11-28 09:09:27,454][87424] Updated weights for policy 0, policy_version 341439 (0.0008) -[2023-11-28 09:09:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 174718976. Throughput: 0: 2712.1, 1: 2762.8. Samples: 174731300. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:28,445][86177] Avg episode reward: [(0, '-526.950'), (1, '-538.110')] -[2023-11-28 09:09:29,055][87424] Updated weights for policy 0, policy_version 341449 (0.0011) -[2023-11-28 09:09:29,161][87426] Updated weights for policy 1, policy_version 341060 (0.0010) -[2023-11-28 09:09:29,429][87424] Updated weights for policy 0, policy_version 341459 (0.0011) -[2023-11-28 09:09:29,537][87426] Updated weights for policy 1, policy_version 341070 (0.0011) -[2023-11-28 09:09:29,801][87424] Updated weights for policy 0, policy_version 341469 (0.0011) -[2023-11-28 09:09:29,912][87426] Updated weights for policy 1, policy_version 341080 (0.0012) -[2023-11-28 09:09:31,732][87426] Updated weights for policy 1, policy_version 341090 (0.0011) -[2023-11-28 09:09:32,101][87426] Updated weights for policy 1, policy_version 341100 (0.0011) -[2023-11-28 09:09:32,193][87424] Updated weights for policy 0, policy_version 341479 (0.0010) -[2023-11-28 09:09:32,479][87426] Updated weights for policy 1, policy_version 341110 (0.0012) -[2023-11-28 09:09:32,572][87424] Updated weights for policy 0, policy_version 341489 (0.0011) -[2023-11-28 09:09:32,848][87426] Updated weights for policy 1, policy_version 341120 (0.0012) -[2023-11-28 09:09:32,962][87424] Updated weights for policy 0, policy_version 341499 (0.0012) -[2023-11-28 09:09:33,445][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 174751744. Throughput: 0: 2696.8, 1: 2750.6. Samples: 174756284. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:33,446][86177] Avg episode reward: [(0, '-527.290'), (1, '-540.190')] -[2023-11-28 09:09:34,810][87426] Updated weights for policy 1, policy_version 341130 (0.0012) -[2023-11-28 09:09:35,186][87424] Updated weights for policy 0, policy_version 341509 (0.0010) -[2023-11-28 09:09:35,189][87426] Updated weights for policy 1, policy_version 341140 (0.0011) -[2023-11-28 09:09:35,566][87424] Updated weights for policy 0, policy_version 341519 (0.0008) -[2023-11-28 09:09:35,569][87426] Updated weights for policy 1, policy_version 341150 (0.0011) -[2023-11-28 09:09:35,939][87424] Updated weights for policy 0, policy_version 341529 (0.0007) -[2023-11-28 09:09:38,030][87426] Updated weights for policy 1, policy_version 341160 (0.0011) -[2023-11-28 09:09:38,171][87424] Updated weights for policy 0, policy_version 341539 (0.0008) -[2023-11-28 09:09:38,412][87426] Updated weights for policy 1, policy_version 341170 (0.0011) -[2023-11-28 09:09:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 174768128. Throughput: 0: 2703.8, 1: 2757.4. Samples: 174789776. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:38,445][86177] Avg episode reward: [(0, '-528.310'), (1, '-541.100')] -[2023-11-28 09:09:38,550][87424] Updated weights for policy 0, policy_version 341549 (0.0009) -[2023-11-28 09:09:38,788][87426] Updated weights for policy 1, policy_version 341180 (0.0012) -[2023-11-28 09:09:38,933][87424] Updated weights for policy 0, policy_version 341559 (0.0008) -[2023-11-28 09:09:41,241][87424] Updated weights for policy 0, policy_version 341569 (0.0011) -[2023-11-28 09:09:41,304][87426] Updated weights for policy 1, policy_version 341190 (0.0011) -[2023-11-28 09:09:41,629][87424] Updated weights for policy 0, policy_version 341579 (0.0011) -[2023-11-28 09:09:41,684][87426] Updated weights for policy 1, policy_version 341200 (0.0012) -[2023-11-28 09:09:42,015][87424] Updated weights for policy 0, policy_version 341589 (0.0012) -[2023-11-28 09:09:42,065][87426] Updated weights for policy 1, policy_version 341210 (0.0010) -[2023-11-28 09:09:42,388][87424] Updated weights for policy 0, policy_version 341599 (0.0010) -[2023-11-28 09:09:43,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 174800896. Throughput: 0: 2705.2, 1: 2760.8. Samples: 174813960. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:43,445][86177] Avg episode reward: [(0, '-522.070'), (1, '-534.390')] -[2023-11-28 09:09:44,610][87426] Updated weights for policy 1, policy_version 341220 (0.0011) -[2023-11-28 09:09:44,814][87424] Updated weights for policy 0, policy_version 341609 (0.0010) -[2023-11-28 09:09:44,989][87426] Updated weights for policy 1, policy_version 341230 (0.0011) -[2023-11-28 09:09:45,193][87424] Updated weights for policy 0, policy_version 341619 (0.0009) -[2023-11-28 09:09:45,364][87426] Updated weights for policy 1, policy_version 341240 (0.0008) -[2023-11-28 09:09:45,575][87424] Updated weights for policy 0, policy_version 341629 (0.0011) -[2023-11-28 09:09:47,498][87424] Updated weights for policy 0, policy_version 341639 (0.0009) -[2023-11-28 09:09:47,817][87426] Updated weights for policy 1, policy_version 341250 (0.0009) -[2023-11-28 09:09:47,884][87424] Updated weights for policy 0, policy_version 341649 (0.0007) -[2023-11-28 09:09:48,198][87426] Updated weights for policy 1, policy_version 341260 (0.0007) -[2023-11-28 09:09:48,259][87424] Updated weights for policy 0, policy_version 341659 (0.0007) -[2023-11-28 09:09:48,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 174817280. Throughput: 0: 2676.7, 1: 2738.1. Samples: 174837184. Policy #0 lag: (min: 31.0, avg: 40.8, max: 63.0) -[2023-11-28 09:09:48,446][86177] Avg episode reward: [(0, '-524.070'), (1, '-535.250')] -[2023-11-28 09:09:48,578][87426] Updated weights for policy 1, policy_version 341270 (0.0008) -[2023-11-28 09:09:48,959][87426] Updated weights for policy 1, policy_version 341280 (0.0007) -[2023-11-28 09:09:50,552][87424] Updated weights for policy 0, policy_version 341669 (0.0008) -[2023-11-28 09:09:50,934][87424] Updated weights for policy 0, policy_version 341679 (0.0008) -[2023-11-28 09:09:51,071][87426] Updated weights for policy 1, policy_version 341290 (0.0011) -[2023-11-28 09:09:51,319][87424] Updated weights for policy 0, policy_version 341689 (0.0009) -[2023-11-28 09:09:51,450][87426] Updated weights for policy 1, policy_version 341300 (0.0011) -[2023-11-28 09:09:51,827][87426] Updated weights for policy 1, policy_version 341310 (0.0009) -[2023-11-28 09:09:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 174850048. Throughput: 0: 2683.1, 1: 2701.4. Samples: 174868588. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:09:53,445][86177] Avg episode reward: [(0, '-525.230'), (1, '-553.640')] -[2023-11-28 09:09:53,555][87424] Updated weights for policy 0, policy_version 341699 (0.0011) -[2023-11-28 09:09:53,940][87424] Updated weights for policy 0, policy_version 341709 (0.0012) -[2023-11-28 09:09:54,089][87426] Updated weights for policy 1, policy_version 341320 (0.0011) -[2023-11-28 09:09:54,326][87424] Updated weights for policy 0, policy_version 341719 (0.0011) -[2023-11-28 09:09:54,467][87426] Updated weights for policy 1, policy_version 341330 (0.0008) -[2023-11-28 09:09:54,849][87426] Updated weights for policy 1, policy_version 341340 (0.0012) -[2023-11-28 09:09:56,684][87424] Updated weights for policy 0, policy_version 341729 (0.0011) -[2023-11-28 09:09:57,058][87424] Updated weights for policy 0, policy_version 341739 (0.0010) -[2023-11-28 09:09:57,116][87426] Updated weights for policy 1, policy_version 341350 (0.0011) -[2023-11-28 09:09:57,435][87424] Updated weights for policy 0, policy_version 341749 (0.0012) -[2023-11-28 09:09:57,497][87426] Updated weights for policy 1, policy_version 341360 (0.0011) -[2023-11-28 09:09:57,815][87424] Updated weights for policy 0, policy_version 341759 (0.0008) -[2023-11-28 09:09:57,881][87426] Updated weights for policy 1, policy_version 341370 (0.0011) -[2023-11-28 09:09:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 174882816. Throughput: 0: 2684.4, 1: 2716.7. Samples: 174893204. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:09:58,445][86177] Avg episode reward: [(0, '-526.190'), (1, '-563.990')] -[2023-11-28 09:10:00,199][87426] Updated weights for policy 1, policy_version 341380 (0.0010) -[2023-11-28 09:10:00,384][87424] Updated weights for policy 0, policy_version 341769 (0.0008) -[2023-11-28 09:10:00,569][87426] Updated weights for policy 1, policy_version 341390 (0.0011) -[2023-11-28 09:10:00,763][87424] Updated weights for policy 0, policy_version 341779 (0.0011) -[2023-11-28 09:10:00,952][87426] Updated weights for policy 1, policy_version 341400 (0.0011) -[2023-11-28 09:10:01,147][87424] Updated weights for policy 0, policy_version 341789 (0.0012) -[2023-11-28 09:10:03,004][87426] Updated weights for policy 1, policy_version 341410 (0.0009) -[2023-11-28 09:10:03,377][87426] Updated weights for policy 1, policy_version 341420 (0.0011) -[2023-11-28 09:10:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 174899200. Throughput: 0: 2649.0, 1: 2704.9. Samples: 174915964. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:03,445][86177] Avg episode reward: [(0, '-527.100'), (1, '-565.610')] -[2023-11-28 09:10:03,570][87424] Updated weights for policy 0, policy_version 341799 (0.0010) -[2023-11-28 09:10:03,756][87426] Updated weights for policy 1, policy_version 341430 (0.0012) -[2023-11-28 09:10:03,942][87424] Updated weights for policy 0, policy_version 341809 (0.0010) -[2023-11-28 09:10:04,131][87426] Updated weights for policy 1, policy_version 341440 (0.0012) -[2023-11-28 09:10:04,331][87424] Updated weights for policy 0, policy_version 341819 (0.0008) -[2023-11-28 09:10:06,196][87424] Updated weights for policy 0, policy_version 341829 (0.0008) -[2023-11-28 09:10:06,363][87426] Updated weights for policy 1, policy_version 341450 (0.0007) -[2023-11-28 09:10:06,593][87424] Updated weights for policy 0, policy_version 341839 (0.0008) -[2023-11-28 09:10:06,741][87426] Updated weights for policy 1, policy_version 341460 (0.0010) -[2023-11-28 09:10:06,965][87424] Updated weights for policy 0, policy_version 341849 (0.0011) -[2023-11-28 09:10:07,116][87426] Updated weights for policy 1, policy_version 341470 (0.0010) -[2023-11-28 09:10:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 174931968. Throughput: 0: 2683.5, 1: 2718.1. Samples: 174949584. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:08,445][86177] Avg episode reward: [(0, '-523.650'), (1, '-585.300')] -[2023-11-28 09:10:09,114][87426] Updated weights for policy 1, policy_version 341480 (0.0012) -[2023-11-28 09:10:09,490][87426] Updated weights for policy 1, policy_version 341490 (0.0008) -[2023-11-28 09:10:09,506][87424] Updated weights for policy 0, policy_version 341859 (0.0011) -[2023-11-28 09:10:09,859][87426] Updated weights for policy 1, policy_version 341500 (0.0009) -[2023-11-28 09:10:09,878][87424] Updated weights for policy 0, policy_version 341869 (0.0011) -[2023-11-28 09:10:10,270][87424] Updated weights for policy 0, policy_version 341879 (0.0013) -[2023-11-28 09:10:11,975][87426] Updated weights for policy 1, policy_version 341510 (0.0012) -[2023-11-28 09:10:12,356][87426] Updated weights for policy 1, policy_version 341520 (0.0012) -[2023-11-28 09:10:12,515][87424] Updated weights for policy 0, policy_version 341889 (0.0010) -[2023-11-28 09:10:12,736][87426] Updated weights for policy 1, policy_version 341530 (0.0011) -[2023-11-28 09:10:12,903][87424] Updated weights for policy 0, policy_version 341899 (0.0011) -[2023-11-28 09:10:13,285][87424] Updated weights for policy 0, policy_version 341909 (0.0009) -[2023-11-28 09:10:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 174956544. Throughput: 0: 2678.8, 1: 2713.6. Samples: 174973956. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:13,445][86177] Avg episode reward: [(0, '-519.700'), (1, '-614.580')] -[2023-11-28 09:10:13,664][87424] Updated weights for policy 0, policy_version 341919 (0.0012) -[2023-11-28 09:10:15,247][87426] Updated weights for policy 1, policy_version 341540 (0.0011) -[2023-11-28 09:10:15,624][87426] Updated weights for policy 1, policy_version 341550 (0.0011) -[2023-11-28 09:10:15,691][87424] Updated weights for policy 0, policy_version 341929 (0.0009) -[2023-11-28 09:10:16,005][87426] Updated weights for policy 1, policy_version 341560 (0.0008) -[2023-11-28 09:10:16,076][87424] Updated weights for policy 0, policy_version 341939 (0.0008) -[2023-11-28 09:10:16,459][87424] Updated weights for policy 0, policy_version 341949 (0.0010) -[2023-11-28 09:10:18,089][87426] Updated weights for policy 1, policy_version 341570 (0.0008) -[2023-11-28 09:10:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 174981120. Throughput: 0: 2679.0, 1: 2704.2. Samples: 174998528. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:18,445][86177] Avg episode reward: [(0, '-520.730'), (1, '-598.600')] -[2023-11-28 09:10:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000341952_87539712.pth... -[2023-11-28 09:10:18,468][87426] Updated weights for policy 1, policy_version 341580 (0.0008) -[2023-11-28 09:10:18,496][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000339456_86900736.pth -[2023-11-28 09:10:18,854][87426] Updated weights for policy 1, policy_version 341590 (0.0009) -[2023-11-28 09:10:18,892][87424] Updated weights for policy 0, policy_version 341959 (0.0008) -[2023-11-28 09:10:19,223][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000341600_87449600.pth... -[2023-11-28 09:10:19,225][87426] Updated weights for policy 1, policy_version 341600 (0.0011) -[2023-11-28 09:10:19,254][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000339072_86802432.pth -[2023-11-28 09:10:19,278][87424] Updated weights for policy 0, policy_version 341969 (0.0010) -[2023-11-28 09:10:19,654][87424] Updated weights for policy 0, policy_version 341979 (0.0012) -[2023-11-28 09:10:21,224][87426] Updated weights for policy 1, policy_version 341610 (0.0011) -[2023-11-28 09:10:21,412][87424] Updated weights for policy 0, policy_version 341989 (0.0012) -[2023-11-28 09:10:21,599][87426] Updated weights for policy 1, policy_version 341620 (0.0011) -[2023-11-28 09:10:21,791][87424] Updated weights for policy 0, policy_version 341999 (0.0011) -[2023-11-28 09:10:21,979][87426] Updated weights for policy 1, policy_version 341630 (0.0011) -[2023-11-28 09:10:22,167][87424] Updated weights for policy 0, policy_version 342009 (0.0012) -[2023-11-28 09:10:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 175013888. Throughput: 0: 2650.3, 1: 2679.4. Samples: 175029612. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:23,445][86177] Avg episode reward: [(0, '-513.220'), (1, '-605.020')] -[2023-11-28 09:10:24,082][87426] Updated weights for policy 1, policy_version 341640 (0.0011) -[2023-11-28 09:10:24,460][87426] Updated weights for policy 1, policy_version 341650 (0.0011) -[2023-11-28 09:10:24,521][87424] Updated weights for policy 0, policy_version 342019 (0.0012) -[2023-11-28 09:10:24,845][87426] Updated weights for policy 1, policy_version 341660 (0.0009) -[2023-11-28 09:10:24,906][87424] Updated weights for policy 0, policy_version 342029 (0.0010) -[2023-11-28 09:10:25,288][87424] Updated weights for policy 0, policy_version 342039 (0.0008) -[2023-11-28 09:10:27,298][87426] Updated weights for policy 1, policy_version 341670 (0.0008) -[2023-11-28 09:10:27,538][87424] Updated weights for policy 0, policy_version 342049 (0.0008) -[2023-11-28 09:10:27,679][87426] Updated weights for policy 1, policy_version 341680 (0.0007) -[2023-11-28 09:10:27,918][87424] Updated weights for policy 0, policy_version 342059 (0.0008) -[2023-11-28 09:10:28,063][87426] Updated weights for policy 1, policy_version 341690 (0.0009) -[2023-11-28 09:10:28,302][87424] Updated weights for policy 0, policy_version 342069 (0.0008) -[2023-11-28 09:10:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 175038464. Throughput: 0: 2668.3, 1: 2676.5. Samples: 175054476. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:28,445][86177] Avg episode reward: [(0, '-518.850'), (1, '-590.040')] -[2023-11-28 09:10:28,683][87424] Updated weights for policy 0, policy_version 342079 (0.0007) -[2023-11-28 09:10:29,710][87426] Updated weights for policy 1, policy_version 341700 (0.0011) -[2023-11-28 09:10:30,092][87426] Updated weights for policy 1, policy_version 341710 (0.0012) -[2023-11-28 09:10:30,471][87426] Updated weights for policy 1, policy_version 341720 (0.0011) -[2023-11-28 09:10:30,845][87424] Updated weights for policy 0, policy_version 342089 (0.0007) -[2023-11-28 09:10:31,226][87424] Updated weights for policy 0, policy_version 342099 (0.0008) -[2023-11-28 09:10:31,608][87424] Updated weights for policy 0, policy_version 342109 (0.0010) -[2023-11-28 09:10:32,239][87426] Updated weights for policy 1, policy_version 341730 (0.0011) -[2023-11-28 09:10:32,623][87426] Updated weights for policy 1, policy_version 341740 (0.0011) -[2023-11-28 09:10:32,999][87426] Updated weights for policy 1, policy_version 341750 (0.0010) -[2023-11-28 09:10:33,385][87426] Updated weights for policy 1, policy_version 341760 (0.0011) -[2023-11-28 09:10:33,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 175071232. Throughput: 0: 2681.2, 1: 2690.4. Samples: 175078904. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:33,446][86177] Avg episode reward: [(0, '-520.170'), (1, '-546.490')] -[2023-11-28 09:10:33,933][87424] Updated weights for policy 0, policy_version 342119 (0.0012) -[2023-11-28 09:10:34,302][87424] Updated weights for policy 0, policy_version 342129 (0.0012) -[2023-11-28 09:10:34,686][87424] Updated weights for policy 0, policy_version 342139 (0.0011) -[2023-11-28 09:10:35,313][87426] Updated weights for policy 1, policy_version 341770 (0.0011) -[2023-11-28 09:10:35,697][87426] Updated weights for policy 1, policy_version 341780 (0.0012) -[2023-11-28 09:10:36,090][87426] Updated weights for policy 1, policy_version 341790 (0.0012) -[2023-11-28 09:10:37,200][87424] Updated weights for policy 0, policy_version 342149 (0.0009) -[2023-11-28 09:10:37,576][87424] Updated weights for policy 0, policy_version 342159 (0.0008) -[2023-11-28 09:10:37,941][87426] Updated weights for policy 1, policy_version 341800 (0.0012) -[2023-11-28 09:10:37,959][87424] Updated weights for policy 0, policy_version 342169 (0.0007) -[2023-11-28 09:10:38,317][87426] Updated weights for policy 1, policy_version 341810 (0.0012) -[2023-11-28 09:10:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 175095808. Throughput: 0: 2656.4, 1: 2743.6. Samples: 175111588. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:38,445][86177] Avg episode reward: [(0, '-517.990'), (1, '-548.340')] -[2023-11-28 09:10:38,701][87426] Updated weights for policy 1, policy_version 341820 (0.0012) -[2023-11-28 09:10:40,077][87424] Updated weights for policy 0, policy_version 342179 (0.0011) -[2023-11-28 09:10:40,460][87424] Updated weights for policy 0, policy_version 342189 (0.0011) -[2023-11-28 09:10:40,841][87424] Updated weights for policy 0, policy_version 342199 (0.0011) -[2023-11-28 09:10:41,200][87426] Updated weights for policy 1, policy_version 341830 (0.0009) -[2023-11-28 09:10:41,578][87426] Updated weights for policy 1, policy_version 341840 (0.0008) -[2023-11-28 09:10:41,957][87426] Updated weights for policy 1, policy_version 341850 (0.0010) -[2023-11-28 09:10:43,114][87424] Updated weights for policy 0, policy_version 342209 (0.0010) -[2023-11-28 09:10:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 175120384. Throughput: 0: 2663.7, 1: 2735.5. Samples: 175136172. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:43,445][86177] Avg episode reward: [(0, '-513.750'), (1, '-544.210')] -[2023-11-28 09:10:43,496][87424] Updated weights for policy 0, policy_version 342219 (0.0012) -[2023-11-28 09:10:43,882][87424] Updated weights for policy 0, policy_version 342229 (0.0011) -[2023-11-28 09:10:43,986][87426] Updated weights for policy 1, policy_version 341860 (0.0010) -[2023-11-28 09:10:44,264][87424] Updated weights for policy 0, policy_version 342239 (0.0012) -[2023-11-28 09:10:44,366][87426] Updated weights for policy 1, policy_version 341870 (0.0012) -[2023-11-28 09:10:44,740][87426] Updated weights for policy 1, policy_version 341880 (0.0012) -[2023-11-28 09:10:46,528][87424] Updated weights for policy 0, policy_version 342249 (0.0011) -[2023-11-28 09:10:46,915][87424] Updated weights for policy 0, policy_version 342259 (0.0012) -[2023-11-28 09:10:47,295][87424] Updated weights for policy 0, policy_version 342269 (0.0012) -[2023-11-28 09:10:47,305][87426] Updated weights for policy 1, policy_version 341890 (0.0012) -[2023-11-28 09:10:47,679][87426] Updated weights for policy 1, policy_version 341900 (0.0008) -[2023-11-28 09:10:48,059][87426] Updated weights for policy 1, policy_version 341910 (0.0007) -[2023-11-28 09:10:48,440][87426] Updated weights for policy 1, policy_version 341920 (0.0007) -[2023-11-28 09:10:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 175153152. Throughput: 0: 2690.2, 1: 2743.9. Samples: 175160500. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:48,445][86177] Avg episode reward: [(0, '-512.420'), (1, '-540.350')] -[2023-11-28 09:10:49,716][87424] Updated weights for policy 0, policy_version 342279 (0.0008) -[2023-11-28 09:10:50,094][87424] Updated weights for policy 0, policy_version 342289 (0.0011) -[2023-11-28 09:10:50,473][87424] Updated weights for policy 0, policy_version 342299 (0.0011) -[2023-11-28 09:10:50,727][87426] Updated weights for policy 1, policy_version 341930 (0.0011) -[2023-11-28 09:10:51,112][87426] Updated weights for policy 1, policy_version 341940 (0.0012) -[2023-11-28 09:10:51,487][87426] Updated weights for policy 1, policy_version 341950 (0.0010) -[2023-11-28 09:10:53,041][87424] Updated weights for policy 0, policy_version 342309 (0.0009) -[2023-11-28 09:10:53,417][87426] Updated weights for policy 1, policy_version 341960 (0.0010) -[2023-11-28 09:10:53,427][87424] Updated weights for policy 0, policy_version 342319 (0.0010) -[2023-11-28 09:10:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 175169536. Throughput: 0: 2667.6, 1: 2755.7. Samples: 175193632. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:53,445][86177] Avg episode reward: [(0, '-515.260'), (1, '-521.860')] -[2023-11-28 09:10:53,795][87426] Updated weights for policy 1, policy_version 341970 (0.0011) -[2023-11-28 09:10:53,814][87424] Updated weights for policy 0, policy_version 342329 (0.0010) -[2023-11-28 09:10:54,181][87426] Updated weights for policy 1, policy_version 341980 (0.0008) -[2023-11-28 09:10:55,825][87424] Updated weights for policy 0, policy_version 342339 (0.0009) -[2023-11-28 09:10:55,977][87426] Updated weights for policy 1, policy_version 341990 (0.0011) -[2023-11-28 09:10:56,204][87424] Updated weights for policy 0, policy_version 342349 (0.0008) -[2023-11-28 09:10:56,354][87426] Updated weights for policy 1, policy_version 342000 (0.0008) -[2023-11-28 09:10:56,594][87424] Updated weights for policy 0, policy_version 342359 (0.0012) -[2023-11-28 09:10:56,735][87426] Updated weights for policy 1, policy_version 342010 (0.0010) -[2023-11-28 09:10:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 175202304. Throughput: 0: 2659.5, 1: 2789.0. Samples: 175219136. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:10:58,445][86177] Avg episode reward: [(0, '-517.340'), (1, '-528.900')] -[2023-11-28 09:10:58,574][87426] Updated weights for policy 1, policy_version 342020 (0.0012) -[2023-11-28 09:10:58,750][87424] Updated weights for policy 0, policy_version 342369 (0.0011) -[2023-11-28 09:10:58,954][87426] Updated weights for policy 1, policy_version 342030 (0.0011) -[2023-11-28 09:10:59,134][87424] Updated weights for policy 0, policy_version 342379 (0.0010) -[2023-11-28 09:10:59,331][87426] Updated weights for policy 1, policy_version 342040 (0.0010) -[2023-11-28 09:10:59,520][87424] Updated weights for policy 0, policy_version 342389 (0.0007) -[2023-11-28 09:10:59,911][87424] Updated weights for policy 0, policy_version 342399 (0.0010) -[2023-11-28 09:11:01,820][87426] Updated weights for policy 1, policy_version 342050 (0.0012) -[2023-11-28 09:11:02,191][87426] Updated weights for policy 1, policy_version 342060 (0.0011) -[2023-11-28 09:11:02,383][87424] Updated weights for policy 0, policy_version 342409 (0.0010) -[2023-11-28 09:11:02,570][87426] Updated weights for policy 1, policy_version 342070 (0.0008) -[2023-11-28 09:11:02,756][87424] Updated weights for policy 0, policy_version 342419 (0.0011) -[2023-11-28 09:11:02,946][87426] Updated weights for policy 1, policy_version 342080 (0.0008) -[2023-11-28 09:11:03,152][87424] Updated weights for policy 0, policy_version 342429 (0.0012) -[2023-11-28 09:11:03,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 175235072. Throughput: 0: 2653.0, 1: 2802.2. Samples: 175244012. Policy #0 lag: (min: 31.0, avg: 35.6, max: 63.0) -[2023-11-28 09:11:03,446][86177] Avg episode reward: [(0, '-517.300'), (1, '-543.450')] -[2023-11-28 09:11:04,739][87426] Updated weights for policy 1, policy_version 342090 (0.0012) -[2023-11-28 09:11:05,119][87426] Updated weights for policy 1, policy_version 342100 (0.0012) -[2023-11-28 09:11:05,480][87424] Updated weights for policy 0, policy_version 342439 (0.0011) -[2023-11-28 09:11:05,497][87426] Updated weights for policy 1, policy_version 342110 (0.0011) -[2023-11-28 09:11:05,858][87424] Updated weights for policy 0, policy_version 342449 (0.0012) -[2023-11-28 09:11:06,234][87424] Updated weights for policy 0, policy_version 342459 (0.0012) -[2023-11-28 09:11:07,695][87426] Updated weights for policy 1, policy_version 342120 (0.0011) -[2023-11-28 09:11:08,071][87426] Updated weights for policy 1, policy_version 342130 (0.0011) -[2023-11-28 09:11:08,348][87424] Updated weights for policy 0, policy_version 342469 (0.0011) -[2023-11-28 09:11:08,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 175251456. Throughput: 0: 2659.8, 1: 2803.6. Samples: 175275468. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:08,445][86177] Avg episode reward: [(0, '-520.230'), (1, '-571.930')] -[2023-11-28 09:11:08,452][87426] Updated weights for policy 1, policy_version 342140 (0.0009) -[2023-11-28 09:11:08,733][87424] Updated weights for policy 0, policy_version 342479 (0.0011) -[2023-11-28 09:11:09,113][87424] Updated weights for policy 0, policy_version 342489 (0.0012) -[2023-11-28 09:11:10,584][87426] Updated weights for policy 1, policy_version 342150 (0.0012) -[2023-11-28 09:11:10,966][87426] Updated weights for policy 1, policy_version 342160 (0.0012) -[2023-11-28 09:11:10,991][87424] Updated weights for policy 0, policy_version 342499 (0.0012) -[2023-11-28 09:11:11,342][87426] Updated weights for policy 1, policy_version 342170 (0.0011) -[2023-11-28 09:11:11,378][87424] Updated weights for policy 0, policy_version 342509 (0.0012) -[2023-11-28 09:11:11,759][87424] Updated weights for policy 0, policy_version 342519 (0.0012) -[2023-11-28 09:11:13,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 175284224. Throughput: 0: 2653.2, 1: 2811.8. Samples: 175300400. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:13,445][86177] Avg episode reward: [(0, '-517.740'), (1, '-580.400')] -[2023-11-28 09:11:13,615][87426] Updated weights for policy 1, policy_version 342180 (0.0011) -[2023-11-28 09:11:13,994][87426] Updated weights for policy 1, policy_version 342190 (0.0012) -[2023-11-28 09:11:14,308][87424] Updated weights for policy 0, policy_version 342529 (0.0012) -[2023-11-28 09:11:14,367][87426] Updated weights for policy 1, policy_version 342200 (0.0010) -[2023-11-28 09:11:14,692][87424] Updated weights for policy 0, policy_version 342539 (0.0012) -[2023-11-28 09:11:15,070][87424] Updated weights for policy 0, policy_version 342549 (0.0012) -[2023-11-28 09:11:15,458][87424] Updated weights for policy 0, policy_version 342559 (0.0012) -[2023-11-28 09:11:16,834][87426] Updated weights for policy 1, policy_version 342210 (0.0009) -[2023-11-28 09:11:17,212][87426] Updated weights for policy 1, policy_version 342220 (0.0010) -[2023-11-28 09:11:17,439][87424] Updated weights for policy 0, policy_version 342569 (0.0011) -[2023-11-28 09:11:17,579][87426] Updated weights for policy 1, policy_version 342230 (0.0010) -[2023-11-28 09:11:17,816][87424] Updated weights for policy 0, policy_version 342579 (0.0010) -[2023-11-28 09:11:17,961][87426] Updated weights for policy 1, policy_version 342240 (0.0008) -[2023-11-28 09:11:18,202][87424] Updated weights for policy 0, policy_version 342589 (0.0008) -[2023-11-28 09:11:18,445][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 175316992. Throughput: 0: 2642.2, 1: 2795.3. Samples: 175323592. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:18,446][86177] Avg episode reward: [(0, '-516.230'), (1, '-610.170')] -[2023-11-28 09:11:20,365][87426] Updated weights for policy 1, policy_version 342250 (0.0011) -[2023-11-28 09:11:20,672][87424] Updated weights for policy 0, policy_version 342599 (0.0011) -[2023-11-28 09:11:20,751][87426] Updated weights for policy 1, policy_version 342260 (0.0012) -[2023-11-28 09:11:21,054][87424] Updated weights for policy 0, policy_version 342609 (0.0012) -[2023-11-28 09:11:21,117][87426] Updated weights for policy 1, policy_version 342270 (0.0012) -[2023-11-28 09:11:21,437][87424] Updated weights for policy 0, policy_version 342619 (0.0012) -[2023-11-28 09:11:23,224][87426] Updated weights for policy 1, policy_version 342280 (0.0012) -[2023-11-28 09:11:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 175333376. Throughput: 0: 2648.3, 1: 2744.3. Samples: 175354252. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:23,445][86177] Avg episode reward: [(0, '-515.540'), (1, '-623.540')] -[2023-11-28 09:11:23,595][87426] Updated weights for policy 1, policy_version 342290 (0.0012) -[2023-11-28 09:11:23,962][87424] Updated weights for policy 0, policy_version 342629 (0.0011) -[2023-11-28 09:11:23,975][87426] Updated weights for policy 1, policy_version 342300 (0.0011) -[2023-11-28 09:11:24,345][87424] Updated weights for policy 0, policy_version 342639 (0.0012) -[2023-11-28 09:11:24,724][87424] Updated weights for policy 0, policy_version 342649 (0.0012) -[2023-11-28 09:11:25,809][87426] Updated weights for policy 1, policy_version 342310 (0.0008) -[2023-11-28 09:11:26,186][87426] Updated weights for policy 1, policy_version 342320 (0.0007) -[2023-11-28 09:11:26,478][87424] Updated weights for policy 0, policy_version 342659 (0.0012) -[2023-11-28 09:11:26,564][87426] Updated weights for policy 1, policy_version 342330 (0.0008) -[2023-11-28 09:11:26,854][87424] Updated weights for policy 0, policy_version 342669 (0.0011) -[2023-11-28 09:11:27,240][87424] Updated weights for policy 0, policy_version 342679 (0.0008) -[2023-11-28 09:11:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 175366144. Throughput: 0: 2658.9, 1: 2764.5. Samples: 175380224. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:28,445][86177] Avg episode reward: [(0, '-513.570'), (1, '-608.360')] -[2023-11-28 09:11:28,564][87426] Updated weights for policy 1, policy_version 342340 (0.0009) -[2023-11-28 09:11:28,936][87426] Updated weights for policy 1, policy_version 342350 (0.0008) -[2023-11-28 09:11:29,318][87426] Updated weights for policy 1, policy_version 342360 (0.0007) -[2023-11-28 09:11:29,568][87424] Updated weights for policy 0, policy_version 342689 (0.0008) -[2023-11-28 09:11:29,964][87424] Updated weights for policy 0, policy_version 342699 (0.0012) -[2023-11-28 09:11:30,352][87424] Updated weights for policy 0, policy_version 342709 (0.0012) -[2023-11-28 09:11:30,735][87424] Updated weights for policy 0, policy_version 342719 (0.0012) -[2023-11-28 09:11:31,418][87426] Updated weights for policy 1, policy_version 342370 (0.0009) -[2023-11-28 09:11:31,789][87426] Updated weights for policy 1, policy_version 342380 (0.0011) -[2023-11-28 09:11:32,174][87426] Updated weights for policy 1, policy_version 342390 (0.0011) -[2023-11-28 09:11:32,547][87426] Updated weights for policy 1, policy_version 342400 (0.0008) -[2023-11-28 09:11:32,693][87424] Updated weights for policy 0, policy_version 342729 (0.0011) -[2023-11-28 09:11:33,075][87424] Updated weights for policy 0, policy_version 342739 (0.0012) -[2023-11-28 09:11:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 175390720. Throughput: 0: 2657.9, 1: 2769.0. Samples: 175404712. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:33,445][86177] Avg episode reward: [(0, '-515.990'), (1, '-584.570')] -[2023-11-28 09:11:33,456][87424] Updated weights for policy 0, policy_version 342749 (0.0012) -[2023-11-28 09:11:34,653][87426] Updated weights for policy 1, policy_version 342410 (0.0008) -[2023-11-28 09:11:35,020][87426] Updated weights for policy 1, policy_version 342420 (0.0011) -[2023-11-28 09:11:35,219][87424] Updated weights for policy 0, policy_version 342759 (0.0011) -[2023-11-28 09:11:35,399][87426] Updated weights for policy 1, policy_version 342430 (0.0010) -[2023-11-28 09:11:35,597][87424] Updated weights for policy 0, policy_version 342769 (0.0008) -[2023-11-28 09:11:35,989][87424] Updated weights for policy 0, policy_version 342779 (0.0008) -[2023-11-28 09:11:37,848][87426] Updated weights for policy 1, policy_version 342440 (0.0010) -[2023-11-28 09:11:38,229][87426] Updated weights for policy 1, policy_version 342450 (0.0012) -[2023-11-28 09:11:38,246][87424] Updated weights for policy 0, policy_version 342789 (0.0008) -[2023-11-28 09:11:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 175415296. Throughput: 0: 2677.8, 1: 2735.0. Samples: 175437208. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:38,445][86177] Avg episode reward: [(0, '-519.670'), (1, '-626.820')] -[2023-11-28 09:11:38,611][87426] Updated weights for policy 1, policy_version 342460 (0.0011) -[2023-11-28 09:11:38,629][87424] Updated weights for policy 0, policy_version 342799 (0.0011) -[2023-11-28 09:11:39,012][87424] Updated weights for policy 0, policy_version 342809 (0.0012) -[2023-11-28 09:11:41,070][87426] Updated weights for policy 1, policy_version 342470 (0.0011) -[2023-11-28 09:11:41,223][87424] Updated weights for policy 0, policy_version 342819 (0.0011) -[2023-11-28 09:11:41,448][87426] Updated weights for policy 1, policy_version 342480 (0.0012) -[2023-11-28 09:11:41,609][87424] Updated weights for policy 0, policy_version 342829 (0.0009) -[2023-11-28 09:11:41,834][87426] Updated weights for policy 1, policy_version 342490 (0.0011) -[2023-11-28 09:11:42,000][87424] Updated weights for policy 0, policy_version 342839 (0.0011) -[2023-11-28 09:11:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 175448064. Throughput: 0: 2684.1, 1: 2682.4. Samples: 175460628. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:43,445][86177] Avg episode reward: [(0, '-519.030'), (1, '-625.350')] -[2023-11-28 09:11:44,198][87426] Updated weights for policy 1, policy_version 342500 (0.0010) -[2023-11-28 09:11:44,217][87424] Updated weights for policy 0, policy_version 342849 (0.0009) -[2023-11-28 09:11:44,586][87426] Updated weights for policy 1, policy_version 342510 (0.0011) -[2023-11-28 09:11:44,608][87424] Updated weights for policy 0, policy_version 342859 (0.0011) -[2023-11-28 09:11:44,969][87426] Updated weights for policy 1, policy_version 342520 (0.0010) -[2023-11-28 09:11:44,981][87424] Updated weights for policy 0, policy_version 342869 (0.0011) -[2023-11-28 09:11:45,378][87424] Updated weights for policy 0, policy_version 342879 (0.0011) -[2023-11-28 09:11:46,897][87426] Updated weights for policy 1, policy_version 342530 (0.0008) -[2023-11-28 09:11:47,278][87426] Updated weights for policy 1, policy_version 342540 (0.0009) -[2023-11-28 09:11:47,470][87424] Updated weights for policy 0, policy_version 342889 (0.0012) -[2023-11-28 09:11:47,658][87426] Updated weights for policy 1, policy_version 342550 (0.0009) -[2023-11-28 09:11:47,855][87424] Updated weights for policy 0, policy_version 342899 (0.0011) -[2023-11-28 09:11:48,043][87426] Updated weights for policy 1, policy_version 342560 (0.0010) -[2023-11-28 09:11:48,251][87424] Updated weights for policy 0, policy_version 342909 (0.0012) -[2023-11-28 09:11:48,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 175480832. Throughput: 0: 2669.4, 1: 2678.4. Samples: 175484664. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:48,446][86177] Avg episode reward: [(0, '-517.850'), (1, '-631.040')] -[2023-11-28 09:11:50,341][87426] Updated weights for policy 1, policy_version 342570 (0.0011) -[2023-11-28 09:11:50,472][87424] Updated weights for policy 0, policy_version 342919 (0.0012) -[2023-11-28 09:11:50,725][87426] Updated weights for policy 1, policy_version 342580 (0.0008) -[2023-11-28 09:11:50,843][87424] Updated weights for policy 0, policy_version 342929 (0.0012) -[2023-11-28 09:11:51,102][87426] Updated weights for policy 1, policy_version 342590 (0.0008) -[2023-11-28 09:11:51,227][87424] Updated weights for policy 0, policy_version 342939 (0.0009) -[2023-11-28 09:11:53,231][87424] Updated weights for policy 0, policy_version 342949 (0.0011) -[2023-11-28 09:11:53,445][86177] Fps is (10 sec: 4914.9, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 175497216. Throughput: 0: 2695.5, 1: 2682.4. Samples: 175517476. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:53,445][86177] Avg episode reward: [(0, '-517.260'), (1, '-634.510')] -[2023-11-28 09:11:53,568][87426] Updated weights for policy 1, policy_version 342600 (0.0011) -[2023-11-28 09:11:53,610][87424] Updated weights for policy 0, policy_version 342959 (0.0009) -[2023-11-28 09:11:53,936][87426] Updated weights for policy 1, policy_version 342610 (0.0012) -[2023-11-28 09:11:53,984][87424] Updated weights for policy 0, policy_version 342969 (0.0011) -[2023-11-28 09:11:54,320][87426] Updated weights for policy 1, policy_version 342620 (0.0010) -[2023-11-28 09:11:56,237][87424] Updated weights for policy 0, policy_version 342979 (0.0010) -[2023-11-28 09:11:56,611][87424] Updated weights for policy 0, policy_version 342989 (0.0008) -[2023-11-28 09:11:56,812][87426] Updated weights for policy 1, policy_version 342630 (0.0008) -[2023-11-28 09:11:56,986][87424] Updated weights for policy 0, policy_version 342999 (0.0007) -[2023-11-28 09:11:57,182][87426] Updated weights for policy 1, policy_version 342640 (0.0007) -[2023-11-28 09:11:57,574][87426] Updated weights for policy 1, policy_version 342650 (0.0011) -[2023-11-28 09:11:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 175529984. Throughput: 0: 2686.4, 1: 2664.3. Samples: 175541180. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:11:58,445][86177] Avg episode reward: [(0, '-519.290'), (1, '-595.440')] -[2023-11-28 09:11:59,208][87424] Updated weights for policy 0, policy_version 343009 (0.0009) -[2023-11-28 09:11:59,590][87424] Updated weights for policy 0, policy_version 343019 (0.0008) -[2023-11-28 09:11:59,859][87426] Updated weights for policy 1, policy_version 342660 (0.0011) -[2023-11-28 09:11:59,990][87424] Updated weights for policy 0, policy_version 343029 (0.0011) -[2023-11-28 09:12:00,230][87426] Updated weights for policy 1, policy_version 342670 (0.0011) -[2023-11-28 09:12:00,370][87424] Updated weights for policy 0, policy_version 343039 (0.0010) -[2023-11-28 09:12:00,607][87426] Updated weights for policy 1, policy_version 342680 (0.0012) -[2023-11-28 09:12:02,540][87426] Updated weights for policy 1, policy_version 342690 (0.0012) -[2023-11-28 09:12:02,860][87424] Updated weights for policy 0, policy_version 343049 (0.0010) -[2023-11-28 09:12:02,914][87426] Updated weights for policy 1, policy_version 342700 (0.0011) -[2023-11-28 09:12:03,241][87424] Updated weights for policy 0, policy_version 343059 (0.0011) -[2023-11-28 09:12:03,292][87426] Updated weights for policy 1, policy_version 342710 (0.0010) -[2023-11-28 09:12:03,445][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 175546368. Throughput: 0: 2703.5, 1: 2680.1. Samples: 175565852. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:12:03,446][86177] Avg episode reward: [(0, '-540.300'), (1, '-600.270')] -[2023-11-28 09:12:03,626][87424] Updated weights for policy 0, policy_version 343069 (0.0012) -[2023-11-28 09:12:03,676][87426] Updated weights for policy 1, policy_version 342720 (0.0011) -[2023-11-28 09:12:05,603][87424] Updated weights for policy 0, policy_version 343079 (0.0009) -[2023-11-28 09:12:05,984][87424] Updated weights for policy 0, policy_version 343089 (0.0009) -[2023-11-28 09:12:06,030][87426] Updated weights for policy 1, policy_version 342730 (0.0007) -[2023-11-28 09:12:06,353][87424] Updated weights for policy 0, policy_version 343099 (0.0007) -[2023-11-28 09:12:06,402][87426] Updated weights for policy 1, policy_version 342740 (0.0007) -[2023-11-28 09:12:06,793][87426] Updated weights for policy 1, policy_version 342750 (0.0008) -[2023-11-28 09:12:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 175579136. Throughput: 0: 2716.9, 1: 2729.4. Samples: 175599336. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:12:08,445][86177] Avg episode reward: [(0, '-538.410'), (1, '-582.930')] -[2023-11-28 09:12:08,592][87426] Updated weights for policy 1, policy_version 342760 (0.0009) -[2023-11-28 09:12:08,817][87424] Updated weights for policy 0, policy_version 343109 (0.0008) -[2023-11-28 09:12:08,971][87426] Updated weights for policy 1, policy_version 342770 (0.0011) -[2023-11-28 09:12:09,195][87424] Updated weights for policy 0, policy_version 343119 (0.0009) -[2023-11-28 09:12:09,349][87426] Updated weights for policy 1, policy_version 342780 (0.0009) -[2023-11-28 09:12:09,575][87424] Updated weights for policy 0, policy_version 343129 (0.0010) -[2023-11-28 09:12:11,566][87426] Updated weights for policy 1, policy_version 342790 (0.0011) -[2023-11-28 09:12:11,886][87424] Updated weights for policy 0, policy_version 343139 (0.0010) -[2023-11-28 09:12:11,947][87426] Updated weights for policy 1, policy_version 342800 (0.0010) -[2023-11-28 09:12:12,268][87424] Updated weights for policy 0, policy_version 343149 (0.0009) -[2023-11-28 09:12:12,334][87426] Updated weights for policy 1, policy_version 342810 (0.0010) -[2023-11-28 09:12:12,654][87424] Updated weights for policy 0, policy_version 343159 (0.0011) -[2023-11-28 09:12:13,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 175611904. Throughput: 0: 2697.0, 1: 2709.9. Samples: 175623536. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:12:13,445][86177] Avg episode reward: [(0, '-539.530'), (1, '-606.640')] -[2023-11-28 09:12:14,410][87426] Updated weights for policy 1, policy_version 342820 (0.0010) -[2023-11-28 09:12:14,781][87424] Updated weights for policy 0, policy_version 343169 (0.0011) -[2023-11-28 09:12:14,789][87426] Updated weights for policy 1, policy_version 342830 (0.0008) -[2023-11-28 09:12:15,166][87424] Updated weights for policy 0, policy_version 343179 (0.0011) -[2023-11-28 09:12:15,180][87426] Updated weights for policy 1, policy_version 342840 (0.0010) -[2023-11-28 09:12:15,543][87424] Updated weights for policy 0, policy_version 343189 (0.0012) -[2023-11-28 09:12:15,927][87424] Updated weights for policy 0, policy_version 343199 (0.0012) -[2023-11-28 09:12:16,952][87426] Updated weights for policy 1, policy_version 342850 (0.0010) -[2023-11-28 09:12:17,331][87426] Updated weights for policy 1, policy_version 342860 (0.0011) -[2023-11-28 09:12:17,722][87426] Updated weights for policy 1, policy_version 342870 (0.0011) -[2023-11-28 09:12:18,006][87424] Updated weights for policy 0, policy_version 343209 (0.0011) -[2023-11-28 09:12:18,099][87426] Updated weights for policy 1, policy_version 342880 (0.0011) -[2023-11-28 09:12:18,389][87424] Updated weights for policy 0, policy_version 343219 (0.0010) -[2023-11-28 09:12:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 175636480. Throughput: 0: 2695.7, 1: 2729.6. Samples: 175648848. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:12:18,445][86177] Avg episode reward: [(0, '-532.860'), (1, '-605.840')] -[2023-11-28 09:12:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000342880_87777280.pth... -[2023-11-28 09:12:18,491][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000340320_87121920.pth -[2023-11-28 09:12:18,496][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000342880_87777280.pth -[2023-11-28 09:12:18,771][87424] Updated weights for policy 0, policy_version 343229 (0.0007) -[2023-11-28 09:12:18,885][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000343232_87867392.pth... -[2023-11-28 09:12:18,933][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000340704_87220224.pth -[2023-11-28 09:12:18,941][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000343232_87867392.pth -[2023-11-28 09:12:19,788][87426] Updated weights for policy 1, policy_version 342890 (0.0012) -[2023-11-28 09:12:20,159][87426] Updated weights for policy 1, policy_version 342900 (0.0010) -[2023-11-28 09:12:20,540][87426] Updated weights for policy 1, policy_version 342910 (0.0012) -[2023-11-28 09:12:21,186][87424] Updated weights for policy 0, policy_version 343239 (0.0009) -[2023-11-28 09:12:21,569][87424] Updated weights for policy 0, policy_version 343249 (0.0011) -[2023-11-28 09:12:21,952][87424] Updated weights for policy 0, policy_version 343259 (0.0011) -[2023-11-28 09:12:22,383][87426] Updated weights for policy 1, policy_version 342920 (0.0010) -[2023-11-28 09:12:22,757][87426] Updated weights for policy 1, policy_version 342930 (0.0010) -[2023-11-28 09:12:23,138][87426] Updated weights for policy 1, policy_version 342940 (0.0011) -[2023-11-28 09:12:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 175669248. Throughput: 0: 2677.9, 1: 2764.7. Samples: 175682128. Policy #0 lag: (min: 31.0, avg: 35.2, max: 63.0) -[2023-11-28 09:12:23,446][86177] Avg episode reward: [(0, '-512.350'), (1, '-552.530')] -[2023-11-28 09:12:24,233][87424] Updated weights for policy 0, policy_version 343269 (0.0009) -[2023-11-28 09:12:24,610][87424] Updated weights for policy 0, policy_version 343279 (0.0007) -[2023-11-28 09:12:24,999][87424] Updated weights for policy 0, policy_version 343289 (0.0007) -[2023-11-28 09:12:25,437][87426] Updated weights for policy 1, policy_version 342950 (0.0011) -[2023-11-28 09:12:25,822][87426] Updated weights for policy 1, policy_version 342960 (0.0012) -[2023-11-28 09:12:26,202][87426] Updated weights for policy 1, policy_version 342970 (0.0011) -[2023-11-28 09:12:27,447][87424] Updated weights for policy 0, policy_version 343299 (0.0008) -[2023-11-28 09:12:27,833][87424] Updated weights for policy 0, policy_version 343309 (0.0008) -[2023-11-28 09:12:28,210][87424] Updated weights for policy 0, policy_version 343319 (0.0008) -[2023-11-28 09:12:28,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 175685632. Throughput: 0: 2669.8, 1: 2788.7. Samples: 175706260. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:12:28,446][86177] Avg episode reward: [(0, '-512.640'), (1, '-562.910')] -[2023-11-28 09:12:28,523][87426] Updated weights for policy 1, policy_version 342980 (0.0011) -[2023-11-28 09:12:28,897][87426] Updated weights for policy 1, policy_version 342990 (0.0008) -[2023-11-28 09:12:29,275][87426] Updated weights for policy 1, policy_version 343000 (0.0011) -[2023-11-28 09:12:30,573][87424] Updated weights for policy 0, policy_version 343329 (0.0008) -[2023-11-28 09:12:30,955][87424] Updated weights for policy 0, policy_version 343339 (0.0008) -[2023-11-28 09:12:31,337][87424] Updated weights for policy 0, policy_version 343349 (0.0007) -[2023-11-28 09:12:31,338][87426] Updated weights for policy 1, policy_version 343010 (0.0008) -[2023-11-28 09:12:31,718][87424] Updated weights for policy 0, policy_version 343359 (0.0009) -[2023-11-28 09:12:31,729][87426] Updated weights for policy 1, policy_version 343020 (0.0009) -[2023-11-28 09:12:32,109][87426] Updated weights for policy 1, policy_version 343030 (0.0009) -[2023-11-28 09:12:32,486][87426] Updated weights for policy 1, policy_version 343040 (0.0010) -[2023-11-28 09:12:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 175718400. Throughput: 0: 2656.4, 1: 2793.5. Samples: 175729908. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:12:33,445][86177] Avg episode reward: [(0, '-509.080'), (1, '-539.210')] -[2023-11-28 09:12:33,929][87424] Updated weights for policy 0, policy_version 343369 (0.0011) -[2023-11-28 09:12:34,315][87424] Updated weights for policy 0, policy_version 343379 (0.0011) -[2023-11-28 09:12:34,549][87426] Updated weights for policy 1, policy_version 343050 (0.0007) -[2023-11-28 09:12:34,697][87424] Updated weights for policy 0, policy_version 343389 (0.0010) -[2023-11-28 09:12:34,921][87426] Updated weights for policy 1, policy_version 343060 (0.0008) -[2023-11-28 09:12:35,300][87426] Updated weights for policy 1, policy_version 343070 (0.0010) -[2023-11-28 09:12:36,795][87424] Updated weights for policy 0, policy_version 343399 (0.0010) -[2023-11-28 09:12:36,965][87426] Updated weights for policy 1, policy_version 343080 (0.0008) -[2023-11-28 09:12:37,182][87424] Updated weights for policy 0, policy_version 343409 (0.0011) -[2023-11-28 09:12:37,348][87426] Updated weights for policy 1, policy_version 343090 (0.0009) -[2023-11-28 09:12:37,564][87424] Updated weights for policy 0, policy_version 343419 (0.0012) -[2023-11-28 09:12:37,718][87426] Updated weights for policy 1, policy_version 343100 (0.0009) -[2023-11-28 09:12:38,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 175751168. Throughput: 0: 2657.5, 1: 2791.1. Samples: 175762660. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:12:38,445][86177] Avg episode reward: [(0, '-505.470'), (1, '-529.150')] -[2023-11-28 09:12:39,630][87424] Updated weights for policy 0, policy_version 343429 (0.0011) -[2023-11-28 09:12:39,799][87426] Updated weights for policy 1, policy_version 343110 (0.0012) -[2023-11-28 09:12:40,006][87424] Updated weights for policy 0, policy_version 343439 (0.0011) -[2023-11-28 09:12:40,179][87426] Updated weights for policy 1, policy_version 343120 (0.0011) -[2023-11-28 09:12:40,391][87424] Updated weights for policy 0, policy_version 343449 (0.0010) -[2023-11-28 09:12:40,561][87426] Updated weights for policy 1, policy_version 343130 (0.0009) -[2023-11-28 09:12:42,611][87424] Updated weights for policy 0, policy_version 343459 (0.0010) -[2023-11-28 09:12:42,992][87424] Updated weights for policy 0, policy_version 343469 (0.0012) -[2023-11-28 09:12:43,193][87426] Updated weights for policy 1, policy_version 343140 (0.0010) -[2023-11-28 09:12:43,375][87424] Updated weights for policy 0, policy_version 343479 (0.0012) -[2023-11-28 09:12:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 175767552. Throughput: 0: 2668.0, 1: 2802.7. Samples: 175787360. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:12:43,445][86177] Avg episode reward: [(0, '-508.670'), (1, '-568.110')] -[2023-11-28 09:12:43,574][87426] Updated weights for policy 1, policy_version 343150 (0.0009) -[2023-11-28 09:12:43,961][87426] Updated weights for policy 1, policy_version 343160 (0.0007) -[2023-11-28 09:12:45,341][87424] Updated weights for policy 0, policy_version 343489 (0.0011) -[2023-11-28 09:12:45,718][87424] Updated weights for policy 0, policy_version 343499 (0.0008) -[2023-11-28 09:12:46,101][87424] Updated weights for policy 0, policy_version 343509 (0.0008) -[2023-11-28 09:12:46,342][87426] Updated weights for policy 1, policy_version 343170 (0.0007) -[2023-11-28 09:12:46,483][87424] Updated weights for policy 0, policy_version 343519 (0.0010) -[2023-11-28 09:12:46,720][87426] Updated weights for policy 1, policy_version 343180 (0.0007) -[2023-11-28 09:12:47,100][87426] Updated weights for policy 1, policy_version 343190 (0.0007) -[2023-11-28 09:12:47,475][87426] Updated weights for policy 1, policy_version 343200 (0.0007) -[2023-11-28 09:12:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 175800320. Throughput: 0: 2681.4, 1: 2798.6. Samples: 175812448. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:12:48,445][86177] Avg episode reward: [(0, '-508.760'), (1, '-589.730')] -[2023-11-28 09:12:48,554][87424] Updated weights for policy 0, policy_version 343529 (0.0012) -[2023-11-28 09:12:48,943][87424] Updated weights for policy 0, policy_version 343539 (0.0012) -[2023-11-28 09:12:49,321][87424] Updated weights for policy 0, policy_version 343549 (0.0012) -[2023-11-28 09:12:49,912][87426] Updated weights for policy 1, policy_version 343210 (0.0008) -[2023-11-28 09:12:50,286][87426] Updated weights for policy 1, policy_version 343220 (0.0007) -[2023-11-28 09:12:50,661][87426] Updated weights for policy 1, policy_version 343230 (0.0008) -[2023-11-28 09:12:51,660][87424] Updated weights for policy 0, policy_version 343559 (0.0011) -[2023-11-28 09:12:52,051][87424] Updated weights for policy 0, policy_version 343569 (0.0010) -[2023-11-28 09:12:52,422][87424] Updated weights for policy 0, policy_version 343579 (0.0010) -[2023-11-28 09:12:52,991][87426] Updated weights for policy 1, policy_version 343240 (0.0011) -[2023-11-28 09:12:53,375][87426] Updated weights for policy 1, policy_version 343250 (0.0011) -[2023-11-28 09:12:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 175824896. Throughput: 0: 2686.7, 1: 2779.5. Samples: 175845316. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:12:53,445][86177] Avg episode reward: [(0, '-512.850'), (1, '-591.550')] -[2023-11-28 09:12:53,750][87426] Updated weights for policy 1, policy_version 343260 (0.0012) -[2023-11-28 09:12:54,443][87424] Updated weights for policy 0, policy_version 343589 (0.0011) -[2023-11-28 09:12:54,828][87424] Updated weights for policy 0, policy_version 343599 (0.0011) -[2023-11-28 09:12:55,214][87424] Updated weights for policy 0, policy_version 343609 (0.0011) -[2023-11-28 09:12:55,736][87426] Updated weights for policy 1, policy_version 343270 (0.0009) -[2023-11-28 09:12:56,109][87426] Updated weights for policy 1, policy_version 343280 (0.0007) -[2023-11-28 09:12:56,494][87426] Updated weights for policy 1, policy_version 343290 (0.0007) -[2023-11-28 09:12:57,376][87424] Updated weights for policy 0, policy_version 343619 (0.0010) -[2023-11-28 09:12:57,760][87424] Updated weights for policy 0, policy_version 343629 (0.0009) -[2023-11-28 09:12:58,134][87424] Updated weights for policy 0, policy_version 343639 (0.0010) -[2023-11-28 09:12:58,415][87426] Updated weights for policy 1, policy_version 343300 (0.0009) -[2023-11-28 09:12:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 175849472. Throughput: 0: 2690.1, 1: 2790.4. Samples: 175870160. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:12:58,445][86177] Avg episode reward: [(0, '-514.170'), (1, '-581.210')] -[2023-11-28 09:12:58,800][87426] Updated weights for policy 1, policy_version 343310 (0.0012) -[2023-11-28 09:12:59,172][87426] Updated weights for policy 1, policy_version 343320 (0.0012) -[2023-11-28 09:13:00,286][87424] Updated weights for policy 0, policy_version 343649 (0.0011) -[2023-11-28 09:13:00,674][87424] Updated weights for policy 0, policy_version 343659 (0.0011) -[2023-11-28 09:13:01,052][87424] Updated weights for policy 0, policy_version 343669 (0.0012) -[2023-11-28 09:13:01,261][87426] Updated weights for policy 1, policy_version 343330 (0.0011) -[2023-11-28 09:13:01,440][87424] Updated weights for policy 0, policy_version 343679 (0.0011) -[2023-11-28 09:13:01,639][87426] Updated weights for policy 1, policy_version 343340 (0.0011) -[2023-11-28 09:13:02,015][87426] Updated weights for policy 1, policy_version 343350 (0.0012) -[2023-11-28 09:13:02,394][87426] Updated weights for policy 1, policy_version 343360 (0.0010) -[2023-11-28 09:13:03,325][87424] Updated weights for policy 0, policy_version 343689 (0.0012) -[2023-11-28 09:13:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 175882240. Throughput: 0: 2703.8, 1: 2766.7. Samples: 175895020. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:13:03,445][86177] Avg episode reward: [(0, '-517.550'), (1, '-505.560')] -[2023-11-28 09:13:03,694][87424] Updated weights for policy 0, policy_version 343699 (0.0012) -[2023-11-28 09:13:04,086][87424] Updated weights for policy 0, policy_version 343709 (0.0011) -[2023-11-28 09:13:04,235][87426] Updated weights for policy 1, policy_version 343370 (0.0007) -[2023-11-28 09:13:04,615][87426] Updated weights for policy 1, policy_version 343380 (0.0007) -[2023-11-28 09:13:04,995][87426] Updated weights for policy 1, policy_version 343390 (0.0008) -[2023-11-28 09:13:06,353][87424] Updated weights for policy 0, policy_version 343719 (0.0011) -[2023-11-28 09:13:06,728][87424] Updated weights for policy 0, policy_version 343729 (0.0011) -[2023-11-28 09:13:06,771][87426] Updated weights for policy 1, policy_version 343400 (0.0009) -[2023-11-28 09:13:07,109][87424] Updated weights for policy 0, policy_version 343739 (0.0012) -[2023-11-28 09:13:07,151][87426] Updated weights for policy 1, policy_version 343410 (0.0009) -[2023-11-28 09:13:07,527][87426] Updated weights for policy 1, policy_version 343420 (0.0012) -[2023-11-28 09:13:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5442.8). Total num frames: 175915008. Throughput: 0: 2701.6, 1: 2780.0. Samples: 175928800. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:13:08,446][86177] Avg episode reward: [(0, '-523.100'), (1, '-512.610')] -[2023-11-28 09:13:08,967][87424] Updated weights for policy 0, policy_version 343749 (0.0012) -[2023-11-28 09:13:09,353][87424] Updated weights for policy 0, policy_version 343759 (0.0012) -[2023-11-28 09:13:09,730][87424] Updated weights for policy 0, policy_version 343769 (0.0012) -[2023-11-28 09:13:09,886][87426] Updated weights for policy 1, policy_version 343430 (0.0011) -[2023-11-28 09:13:10,252][87426] Updated weights for policy 1, policy_version 343440 (0.0011) -[2023-11-28 09:13:10,643][87426] Updated weights for policy 1, policy_version 343450 (0.0010) -[2023-11-28 09:13:12,117][87424] Updated weights for policy 0, policy_version 343779 (0.0012) -[2023-11-28 09:13:12,431][87426] Updated weights for policy 1, policy_version 343460 (0.0010) -[2023-11-28 09:13:12,501][87424] Updated weights for policy 0, policy_version 343789 (0.0012) -[2023-11-28 09:13:12,810][87426] Updated weights for policy 1, policy_version 343470 (0.0011) -[2023-11-28 09:13:12,883][87424] Updated weights for policy 0, policy_version 343799 (0.0012) -[2023-11-28 09:13:13,185][87426] Updated weights for policy 1, policy_version 343480 (0.0012) -[2023-11-28 09:13:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 175939584. Throughput: 0: 2718.6, 1: 2753.3. Samples: 175952492. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:13:13,445][86177] Avg episode reward: [(0, '-522.300'), (1, '-514.180')] -[2023-11-28 09:13:15,473][87424] Updated weights for policy 0, policy_version 343809 (0.0011) -[2023-11-28 09:13:15,722][87426] Updated weights for policy 1, policy_version 343490 (0.0012) -[2023-11-28 09:13:15,858][87424] Updated weights for policy 0, policy_version 343819 (0.0008) -[2023-11-28 09:13:16,100][87426] Updated weights for policy 1, policy_version 343500 (0.0011) -[2023-11-28 09:13:16,243][87424] Updated weights for policy 0, policy_version 343829 (0.0008) -[2023-11-28 09:13:16,483][87426] Updated weights for policy 1, policy_version 343510 (0.0011) -[2023-11-28 09:13:16,621][87424] Updated weights for policy 0, policy_version 343839 (0.0008) -[2023-11-28 09:13:16,863][87426] Updated weights for policy 1, policy_version 343520 (0.0011) -[2023-11-28 09:13:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 175964160. Throughput: 0: 2720.4, 1: 2732.0. Samples: 175975268. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:13:18,445][86177] Avg episode reward: [(0, '-521.010'), (1, '-528.160')] -[2023-11-28 09:13:18,700][87424] Updated weights for policy 0, policy_version 343849 (0.0009) -[2023-11-28 09:13:19,081][87424] Updated weights for policy 0, policy_version 343859 (0.0008) -[2023-11-28 09:13:19,320][87426] Updated weights for policy 1, policy_version 343530 (0.0012) -[2023-11-28 09:13:19,469][87424] Updated weights for policy 0, policy_version 343869 (0.0008) -[2023-11-28 09:13:19,700][87426] Updated weights for policy 1, policy_version 343540 (0.0012) -[2023-11-28 09:13:20,073][87426] Updated weights for policy 1, policy_version 343550 (0.0012) -[2023-11-28 09:13:21,585][87424] Updated weights for policy 0, policy_version 343879 (0.0012) -[2023-11-28 09:13:21,968][87424] Updated weights for policy 0, policy_version 343889 (0.0012) -[2023-11-28 09:13:22,338][87424] Updated weights for policy 0, policy_version 343899 (0.0012) -[2023-11-28 09:13:22,502][87426] Updated weights for policy 1, policy_version 343560 (0.0009) -[2023-11-28 09:13:22,891][87426] Updated weights for policy 1, policy_version 343570 (0.0010) -[2023-11-28 09:13:23,263][87426] Updated weights for policy 1, policy_version 343580 (0.0010) -[2023-11-28 09:13:23,445][86177] Fps is (10 sec: 5733.9, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 175996928. Throughput: 0: 2726.4, 1: 2754.9. Samples: 176009324. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:13:23,446][86177] Avg episode reward: [(0, '-517.700'), (1, '-533.380')] -[2023-11-28 09:13:24,897][87424] Updated weights for policy 0, policy_version 343909 (0.0011) -[2023-11-28 09:13:25,285][87424] Updated weights for policy 0, policy_version 343919 (0.0010) -[2023-11-28 09:13:25,661][87424] Updated weights for policy 0, policy_version 343929 (0.0012) -[2023-11-28 09:13:25,665][87426] Updated weights for policy 1, policy_version 343590 (0.0011) -[2023-11-28 09:13:26,048][87426] Updated weights for policy 1, policy_version 343600 (0.0012) -[2023-11-28 09:13:26,431][87426] Updated weights for policy 1, policy_version 343610 (0.0011) -[2023-11-28 09:13:27,644][87424] Updated weights for policy 0, policy_version 343939 (0.0012) -[2023-11-28 09:13:28,028][87424] Updated weights for policy 0, policy_version 343949 (0.0012) -[2023-11-28 09:13:28,312][87426] Updated weights for policy 1, policy_version 343620 (0.0011) -[2023-11-28 09:13:28,410][87424] Updated weights for policy 0, policy_version 343959 (0.0010) -[2023-11-28 09:13:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 176013312. Throughput: 0: 2718.5, 1: 2756.4. Samples: 176033728. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:13:28,445][86177] Avg episode reward: [(0, '-515.390'), (1, '-531.740')] -[2023-11-28 09:13:28,680][87426] Updated weights for policy 1, policy_version 343630 (0.0007) -[2023-11-28 09:13:29,057][87426] Updated weights for policy 1, policy_version 343640 (0.0011) -[2023-11-28 09:13:30,490][87424] Updated weights for policy 0, policy_version 343969 (0.0009) -[2023-11-28 09:13:30,870][87424] Updated weights for policy 0, policy_version 343979 (0.0012) -[2023-11-28 09:13:31,254][87424] Updated weights for policy 0, policy_version 343989 (0.0012) -[2023-11-28 09:13:31,321][87426] Updated weights for policy 1, policy_version 343650 (0.0009) -[2023-11-28 09:13:31,627][87424] Updated weights for policy 0, policy_version 343999 (0.0011) -[2023-11-28 09:13:31,703][87426] Updated weights for policy 1, policy_version 343660 (0.0009) -[2023-11-28 09:13:32,079][87426] Updated weights for policy 1, policy_version 343670 (0.0012) -[2023-11-28 09:13:32,452][87426] Updated weights for policy 1, policy_version 343680 (0.0011) -[2023-11-28 09:13:33,445][86177] Fps is (10 sec: 4915.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 176046080. Throughput: 0: 2695.9, 1: 2753.4. Samples: 176057668. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:13:33,446][86177] Avg episode reward: [(0, '-513.110'), (1, '-530.280')] -[2023-11-28 09:13:34,096][87424] Updated weights for policy 0, policy_version 344009 (0.0008) -[2023-11-28 09:13:34,484][87424] Updated weights for policy 0, policy_version 344019 (0.0008) -[2023-11-28 09:13:34,869][87424] Updated weights for policy 0, policy_version 344029 (0.0010) -[2023-11-28 09:13:34,946][87426] Updated weights for policy 1, policy_version 343690 (0.0012) -[2023-11-28 09:13:35,327][87426] Updated weights for policy 1, policy_version 343700 (0.0011) -[2023-11-28 09:13:35,704][87426] Updated weights for policy 1, policy_version 343710 (0.0011) -[2023-11-28 09:13:37,515][87424] Updated weights for policy 0, policy_version 344039 (0.0010) -[2023-11-28 09:13:37,894][87424] Updated weights for policy 0, policy_version 344049 (0.0011) -[2023-11-28 09:13:38,202][87426] Updated weights for policy 1, policy_version 343720 (0.0011) -[2023-11-28 09:13:38,272][87424] Updated weights for policy 0, policy_version 344059 (0.0011) -[2023-11-28 09:13:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 176062464. Throughput: 0: 2682.5, 1: 2715.7. Samples: 176088236. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:13:38,445][86177] Avg episode reward: [(0, '-511.800'), (1, '-515.740')] -[2023-11-28 09:13:38,584][87426] Updated weights for policy 1, policy_version 343730 (0.0011) -[2023-11-28 09:13:38,955][87426] Updated weights for policy 1, policy_version 343740 (0.0011) -[2023-11-28 09:13:40,911][87424] Updated weights for policy 0, policy_version 344069 (0.0011) -[2023-11-28 09:13:41,288][87424] Updated weights for policy 0, policy_version 344079 (0.0009) -[2023-11-28 09:13:41,611][87426] Updated weights for policy 1, policy_version 343750 (0.0012) -[2023-11-28 09:13:41,667][87424] Updated weights for policy 0, policy_version 344089 (0.0009) -[2023-11-28 09:13:41,990][87426] Updated weights for policy 1, policy_version 343760 (0.0010) -[2023-11-28 09:13:42,368][87426] Updated weights for policy 1, policy_version 343770 (0.0011) -[2023-11-28 09:13:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 176095232. Throughput: 0: 2676.7, 1: 2649.7. Samples: 176109848. Policy #0 lag: (min: 31.0, avg: 43.1, max: 63.0) -[2023-11-28 09:13:43,445][86177] Avg episode reward: [(0, '-514.570'), (1, '-511.320')] -[2023-11-28 09:13:43,800][87424] Updated weights for policy 0, policy_version 344099 (0.0012) -[2023-11-28 09:13:44,183][87424] Updated weights for policy 0, policy_version 344109 (0.0012) -[2023-11-28 09:13:44,567][87424] Updated weights for policy 0, policy_version 344119 (0.0011) -[2023-11-28 09:13:44,962][87426] Updated weights for policy 1, policy_version 343780 (0.0012) -[2023-11-28 09:13:45,356][87426] Updated weights for policy 1, policy_version 343790 (0.0012) -[2023-11-28 09:13:45,731][87426] Updated weights for policy 1, policy_version 343800 (0.0013) -[2023-11-28 09:13:46,578][87424] Updated weights for policy 0, policy_version 344129 (0.0012) -[2023-11-28 09:13:46,960][87424] Updated weights for policy 0, policy_version 344139 (0.0012) -[2023-11-28 09:13:47,343][87424] Updated weights for policy 0, policy_version 344149 (0.0012) -[2023-11-28 09:13:47,725][87424] Updated weights for policy 0, policy_version 344159 (0.0012) -[2023-11-28 09:13:47,876][87426] Updated weights for policy 1, policy_version 343810 (0.0011) -[2023-11-28 09:13:48,265][87426] Updated weights for policy 1, policy_version 343820 (0.0007) -[2023-11-28 09:13:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 176119808. Throughput: 0: 2666.7, 1: 2627.6. Samples: 176133260. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:13:48,445][86177] Avg episode reward: [(0, '-513.860'), (1, '-505.060')] -[2023-11-28 09:13:48,628][87426] Updated weights for policy 1, policy_version 343830 (0.0008) -[2023-11-28 09:13:49,005][87426] Updated weights for policy 1, policy_version 343840 (0.0009) -[2023-11-28 09:13:49,769][87424] Updated weights for policy 0, policy_version 344169 (0.0012) -[2023-11-28 09:13:50,145][87424] Updated weights for policy 0, policy_version 344179 (0.0011) -[2023-11-28 09:13:50,527][87424] Updated weights for policy 0, policy_version 344189 (0.0010) -[2023-11-28 09:13:51,145][87426] Updated weights for policy 1, policy_version 343850 (0.0012) -[2023-11-28 09:13:51,519][87426] Updated weights for policy 1, policy_version 343860 (0.0012) -[2023-11-28 09:13:51,898][87426] Updated weights for policy 1, policy_version 343870 (0.0012) -[2023-11-28 09:13:52,907][87424] Updated weights for policy 0, policy_version 344199 (0.0009) -[2023-11-28 09:13:53,295][87424] Updated weights for policy 0, policy_version 344209 (0.0011) -[2023-11-28 09:13:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 176144384. Throughput: 0: 2666.6, 1: 2596.5. Samples: 176165640. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:13:53,446][86177] Avg episode reward: [(0, '-513.880'), (1, '-505.550')] -[2023-11-28 09:13:53,683][87424] Updated weights for policy 0, policy_version 344219 (0.0013) -[2023-11-28 09:13:54,268][87426] Updated weights for policy 1, policy_version 343880 (0.0012) -[2023-11-28 09:13:54,639][87426] Updated weights for policy 1, policy_version 343890 (0.0010) -[2023-11-28 09:13:55,040][87426] Updated weights for policy 1, policy_version 343900 (0.0009) -[2023-11-28 09:13:56,166][87424] Updated weights for policy 0, policy_version 344229 (0.0009) -[2023-11-28 09:13:56,547][87424] Updated weights for policy 0, policy_version 344239 (0.0008) -[2023-11-28 09:13:56,932][87424] Updated weights for policy 0, policy_version 344249 (0.0008) -[2023-11-28 09:13:57,086][87426] Updated weights for policy 1, policy_version 343910 (0.0010) -[2023-11-28 09:13:57,456][87426] Updated weights for policy 1, policy_version 343920 (0.0012) -[2023-11-28 09:13:57,846][87426] Updated weights for policy 1, policy_version 343930 (0.0012) -[2023-11-28 09:13:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 176177152. Throughput: 0: 2647.6, 1: 2624.8. Samples: 176189752. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:13:58,445][86177] Avg episode reward: [(0, '-507.130'), (1, '-500.820')] -[2023-11-28 09:13:58,660][87424] Updated weights for policy 0, policy_version 344259 (0.0011) -[2023-11-28 09:13:59,032][87424] Updated weights for policy 0, policy_version 344269 (0.0012) -[2023-11-28 09:13:59,409][87424] Updated weights for policy 0, policy_version 344279 (0.0012) -[2023-11-28 09:14:00,052][87426] Updated weights for policy 1, policy_version 343940 (0.0012) -[2023-11-28 09:14:00,423][87426] Updated weights for policy 1, policy_version 343950 (0.0011) -[2023-11-28 09:14:00,811][87426] Updated weights for policy 1, policy_version 343960 (0.0009) -[2023-11-28 09:14:01,493][87424] Updated weights for policy 0, policy_version 344289 (0.0012) -[2023-11-28 09:14:01,874][87424] Updated weights for policy 0, policy_version 344299 (0.0012) -[2023-11-28 09:14:02,247][87424] Updated weights for policy 0, policy_version 344309 (0.0012) -[2023-11-28 09:14:02,633][87424] Updated weights for policy 0, policy_version 344319 (0.0012) -[2023-11-28 09:14:02,792][87426] Updated weights for policy 1, policy_version 343970 (0.0009) -[2023-11-28 09:14:03,167][87426] Updated weights for policy 1, policy_version 343980 (0.0011) -[2023-11-28 09:14:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 176201728. Throughput: 0: 2679.2, 1: 2646.7. Samples: 176214936. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:03,445][86177] Avg episode reward: [(0, '-514.920'), (1, '-536.590')] -[2023-11-28 09:14:03,543][87426] Updated weights for policy 1, policy_version 343990 (0.0011) -[2023-11-28 09:14:03,923][87426] Updated weights for policy 1, policy_version 344000 (0.0011) -[2023-11-28 09:14:04,829][87424] Updated weights for policy 0, policy_version 344329 (0.0012) -[2023-11-28 09:14:05,208][87424] Updated weights for policy 0, policy_version 344339 (0.0011) -[2023-11-28 09:14:05,597][87424] Updated weights for policy 0, policy_version 344349 (0.0007) -[2023-11-28 09:14:06,253][87426] Updated weights for policy 1, policy_version 344010 (0.0012) -[2023-11-28 09:14:06,628][87426] Updated weights for policy 1, policy_version 344020 (0.0011) -[2023-11-28 09:14:07,012][87426] Updated weights for policy 1, policy_version 344030 (0.0011) -[2023-11-28 09:14:07,828][87424] Updated weights for policy 0, policy_version 344359 (0.0008) -[2023-11-28 09:14:08,208][87424] Updated weights for policy 0, policy_version 344369 (0.0008) -[2023-11-28 09:14:08,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 176226304. Throughput: 0: 2660.0, 1: 2621.9. Samples: 176247008. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:08,446][86177] Avg episode reward: [(0, '-516.630'), (1, '-547.780')] -[2023-11-28 09:14:08,596][87424] Updated weights for policy 0, policy_version 344379 (0.0007) -[2023-11-28 09:14:08,715][87426] Updated weights for policy 1, policy_version 344040 (0.0009) -[2023-11-28 09:14:09,092][87426] Updated weights for policy 1, policy_version 344050 (0.0008) -[2023-11-28 09:14:09,470][87426] Updated weights for policy 1, policy_version 344060 (0.0010) -[2023-11-28 09:14:11,017][87424] Updated weights for policy 0, policy_version 344389 (0.0010) -[2023-11-28 09:14:11,398][87424] Updated weights for policy 0, policy_version 344399 (0.0011) -[2023-11-28 09:14:11,499][87426] Updated weights for policy 1, policy_version 344070 (0.0010) -[2023-11-28 09:14:11,772][87424] Updated weights for policy 0, policy_version 344409 (0.0011) -[2023-11-28 09:14:11,875][87426] Updated weights for policy 1, policy_version 344080 (0.0010) -[2023-11-28 09:14:12,251][87426] Updated weights for policy 1, policy_version 344090 (0.0012) -[2023-11-28 09:14:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 176259072. Throughput: 0: 2653.5, 1: 2592.6. Samples: 176269804. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:13,445][86177] Avg episode reward: [(0, '-518.150'), (1, '-548.930')] -[2023-11-28 09:14:14,222][87424] Updated weights for policy 0, policy_version 344419 (0.0010) -[2023-11-28 09:14:14,602][87424] Updated weights for policy 0, policy_version 344429 (0.0008) -[2023-11-28 09:14:14,681][87426] Updated weights for policy 1, policy_version 344100 (0.0012) -[2023-11-28 09:14:14,977][87424] Updated weights for policy 0, policy_version 344439 (0.0008) -[2023-11-28 09:14:15,053][87426] Updated weights for policy 1, policy_version 344110 (0.0010) -[2023-11-28 09:14:15,434][87426] Updated weights for policy 1, policy_version 344120 (0.0012) -[2023-11-28 09:14:17,427][87424] Updated weights for policy 0, policy_version 344449 (0.0009) -[2023-11-28 09:14:17,821][87424] Updated weights for policy 0, policy_version 344459 (0.0012) -[2023-11-28 09:14:18,005][87426] Updated weights for policy 1, policy_version 344130 (0.0012) -[2023-11-28 09:14:18,198][87424] Updated weights for policy 0, policy_version 344469 (0.0009) -[2023-11-28 09:14:18,390][87426] Updated weights for policy 1, policy_version 344140 (0.0012) -[2023-11-28 09:14:18,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.2, 300 sec: 5387.3). Total num frames: 176275456. Throughput: 0: 2637.2, 1: 2582.3. Samples: 176292544. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:18,446][86177] Avg episode reward: [(0, '-517.340'), (1, '-558.490')] -[2023-11-28 09:14:18,577][87424] Updated weights for policy 0, policy_version 344479 (0.0010) -[2023-11-28 09:14:18,613][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000344480_88186880.pth... -[2023-11-28 09:14:18,656][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000341952_87539712.pth -[2023-11-28 09:14:18,773][87426] Updated weights for policy 1, policy_version 344150 (0.0012) -[2023-11-28 09:14:19,155][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000344160_88104960.pth... -[2023-11-28 09:14:19,155][87426] Updated weights for policy 1, policy_version 344160 (0.0009) -[2023-11-28 09:14:19,203][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000341600_87449600.pth -[2023-11-28 09:14:20,810][87424] Updated weights for policy 0, policy_version 344489 (0.0012) -[2023-11-28 09:14:21,187][87424] Updated weights for policy 0, policy_version 344499 (0.0012) -[2023-11-28 09:14:21,571][87424] Updated weights for policy 0, policy_version 344509 (0.0012) -[2023-11-28 09:14:21,774][87426] Updated weights for policy 1, policy_version 344170 (0.0012) -[2023-11-28 09:14:22,149][87426] Updated weights for policy 1, policy_version 344180 (0.0011) -[2023-11-28 09:14:22,527][87426] Updated weights for policy 1, policy_version 344190 (0.0011) -[2023-11-28 09:14:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 176308224. Throughput: 0: 2633.4, 1: 2599.2. Samples: 176323704. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:23,445][86177] Avg episode reward: [(0, '-511.250'), (1, '-526.660')] -[2023-11-28 09:14:23,970][87424] Updated weights for policy 0, policy_version 344519 (0.0012) -[2023-11-28 09:14:24,352][87424] Updated weights for policy 0, policy_version 344529 (0.0009) -[2023-11-28 09:14:24,733][87424] Updated weights for policy 0, policy_version 344539 (0.0008) -[2023-11-28 09:14:25,157][87426] Updated weights for policy 1, policy_version 344200 (0.0009) -[2023-11-28 09:14:25,535][87426] Updated weights for policy 1, policy_version 344210 (0.0008) -[2023-11-28 09:14:25,922][87426] Updated weights for policy 1, policy_version 344220 (0.0011) -[2023-11-28 09:14:26,855][87424] Updated weights for policy 0, policy_version 344549 (0.0010) -[2023-11-28 09:14:27,235][87424] Updated weights for policy 0, policy_version 344559 (0.0007) -[2023-11-28 09:14:27,617][87424] Updated weights for policy 0, policy_version 344569 (0.0008) -[2023-11-28 09:14:27,677][87426] Updated weights for policy 1, policy_version 344230 (0.0011) -[2023-11-28 09:14:28,056][87426] Updated weights for policy 1, policy_version 344240 (0.0011) -[2023-11-28 09:14:28,432][87426] Updated weights for policy 1, policy_version 344250 (0.0012) -[2023-11-28 09:14:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176332800. Throughput: 0: 2641.9, 1: 2656.5. Samples: 176348276. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:28,445][86177] Avg episode reward: [(0, '-509.480'), (1, '-518.330')] -[2023-11-28 09:14:29,444][87424] Updated weights for policy 0, policy_version 344579 (0.0009) -[2023-11-28 09:14:29,827][87424] Updated weights for policy 0, policy_version 344589 (0.0011) -[2023-11-28 09:14:30,207][87424] Updated weights for policy 0, policy_version 344599 (0.0011) -[2023-11-28 09:14:30,791][87426] Updated weights for policy 1, policy_version 344260 (0.0012) -[2023-11-28 09:14:31,171][87426] Updated weights for policy 1, policy_version 344270 (0.0012) -[2023-11-28 09:14:31,546][87426] Updated weights for policy 1, policy_version 344280 (0.0012) -[2023-11-28 09:14:32,382][87424] Updated weights for policy 0, policy_version 344609 (0.0012) -[2023-11-28 09:14:32,761][87424] Updated weights for policy 0, policy_version 344619 (0.0011) -[2023-11-28 09:14:33,149][87424] Updated weights for policy 0, policy_version 344629 (0.0011) -[2023-11-28 09:14:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 176357376. Throughput: 0: 2664.3, 1: 2676.0. Samples: 176373572. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:33,446][86177] Avg episode reward: [(0, '-512.900'), (1, '-514.720')] -[2023-11-28 09:14:33,533][87424] Updated weights for policy 0, policy_version 344639 (0.0010) -[2023-11-28 09:14:34,203][87426] Updated weights for policy 1, policy_version 344290 (0.0011) -[2023-11-28 09:14:34,580][87426] Updated weights for policy 1, policy_version 344300 (0.0011) -[2023-11-28 09:14:34,958][87426] Updated weights for policy 1, policy_version 344310 (0.0011) -[2023-11-28 09:14:35,334][87426] Updated weights for policy 1, policy_version 344320 (0.0007) -[2023-11-28 09:14:35,362][87424] Updated weights for policy 0, policy_version 344649 (0.0009) -[2023-11-28 09:14:35,745][87424] Updated weights for policy 0, policy_version 344659 (0.0011) -[2023-11-28 09:14:36,137][87424] Updated weights for policy 0, policy_version 344669 (0.0009) -[2023-11-28 09:14:37,817][87426] Updated weights for policy 1, policy_version 344330 (0.0012) -[2023-11-28 09:14:38,196][87426] Updated weights for policy 1, policy_version 344340 (0.0011) -[2023-11-28 09:14:38,269][87424] Updated weights for policy 0, policy_version 344679 (0.0010) -[2023-11-28 09:14:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176381952. Throughput: 0: 2680.2, 1: 2661.7. Samples: 176406024. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:38,445][86177] Avg episode reward: [(0, '-516.460'), (1, '-512.230')] -[2023-11-28 09:14:38,577][87426] Updated weights for policy 1, policy_version 344350 (0.0011) -[2023-11-28 09:14:38,641][87424] Updated weights for policy 0, policy_version 344689 (0.0011) -[2023-11-28 09:14:39,024][87424] Updated weights for policy 0, policy_version 344699 (0.0016) -[2023-11-28 09:14:40,942][87426] Updated weights for policy 1, policy_version 344360 (0.0012) -[2023-11-28 09:14:41,328][87426] Updated weights for policy 1, policy_version 344370 (0.0011) -[2023-11-28 09:14:41,512][87424] Updated weights for policy 0, policy_version 344709 (0.0008) -[2023-11-28 09:14:41,707][87426] Updated weights for policy 1, policy_version 344380 (0.0011) -[2023-11-28 09:14:41,889][87424] Updated weights for policy 0, policy_version 344719 (0.0011) -[2023-11-28 09:14:42,295][87424] Updated weights for policy 0, policy_version 344729 (0.0022) -[2023-11-28 09:14:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 176414720. Throughput: 0: 2686.4, 1: 2634.4. Samples: 176429188. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:43,445][86177] Avg episode reward: [(0, '-519.620'), (1, '-511.070')] -[2023-11-28 09:14:43,957][87426] Updated weights for policy 1, policy_version 344390 (0.0011) -[2023-11-28 09:14:44,339][87426] Updated weights for policy 1, policy_version 344400 (0.0012) -[2023-11-28 09:14:44,620][87424] Updated weights for policy 0, policy_version 344739 (0.0012) -[2023-11-28 09:14:44,726][87426] Updated weights for policy 1, policy_version 344410 (0.0012) -[2023-11-28 09:14:45,014][87424] Updated weights for policy 0, policy_version 344749 (0.0010) -[2023-11-28 09:14:45,386][87424] Updated weights for policy 0, policy_version 344759 (0.0009) -[2023-11-28 09:14:46,637][87426] Updated weights for policy 1, policy_version 344420 (0.0011) -[2023-11-28 09:14:47,016][87426] Updated weights for policy 1, policy_version 344430 (0.0008) -[2023-11-28 09:14:47,399][87426] Updated weights for policy 1, policy_version 344440 (0.0007) -[2023-11-28 09:14:48,027][87424] Updated weights for policy 0, policy_version 344769 (0.0010) -[2023-11-28 09:14:48,411][87424] Updated weights for policy 0, policy_version 344779 (0.0008) -[2023-11-28 09:14:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 176439296. Throughput: 0: 2660.2, 1: 2630.4. Samples: 176453012. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:48,445][86177] Avg episode reward: [(0, '-523.000'), (1, '-550.190')] -[2023-11-28 09:14:48,796][87424] Updated weights for policy 0, policy_version 344789 (0.0008) -[2023-11-28 09:14:49,174][87424] Updated weights for policy 0, policy_version 344799 (0.0011) -[2023-11-28 09:14:49,451][87426] Updated weights for policy 1, policy_version 344450 (0.0008) -[2023-11-28 09:14:49,830][87426] Updated weights for policy 1, policy_version 344460 (0.0011) -[2023-11-28 09:14:50,205][87426] Updated weights for policy 1, policy_version 344470 (0.0012) -[2023-11-28 09:14:50,587][87426] Updated weights for policy 1, policy_version 344480 (0.0012) -[2023-11-28 09:14:51,481][87424] Updated weights for policy 0, policy_version 344809 (0.0010) -[2023-11-28 09:14:51,863][87424] Updated weights for policy 0, policy_version 344819 (0.0010) -[2023-11-28 09:14:52,248][87424] Updated weights for policy 0, policy_version 344829 (0.0012) -[2023-11-28 09:14:52,624][87426] Updated weights for policy 1, policy_version 344490 (0.0011) -[2023-11-28 09:14:53,012][87426] Updated weights for policy 1, policy_version 344500 (0.0010) -[2023-11-28 09:14:53,385][87426] Updated weights for policy 1, policy_version 344510 (0.0011) -[2023-11-28 09:14:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176463872. Throughput: 0: 2655.0, 1: 2622.9. Samples: 176484516. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:53,445][86177] Avg episode reward: [(0, '-527.120'), (1, '-556.700')] -[2023-11-28 09:14:54,640][87424] Updated weights for policy 0, policy_version 344839 (0.0009) -[2023-11-28 09:14:55,021][87424] Updated weights for policy 0, policy_version 344849 (0.0008) -[2023-11-28 09:14:55,407][87424] Updated weights for policy 0, policy_version 344859 (0.0010) -[2023-11-28 09:14:55,540][87426] Updated weights for policy 1, policy_version 344520 (0.0012) -[2023-11-28 09:14:55,930][87426] Updated weights for policy 1, policy_version 344530 (0.0012) -[2023-11-28 09:14:56,307][87426] Updated weights for policy 1, policy_version 344540 (0.0012) -[2023-11-28 09:14:57,557][87424] Updated weights for policy 0, policy_version 344869 (0.0010) -[2023-11-28 09:14:57,940][87424] Updated weights for policy 0, policy_version 344879 (0.0007) -[2023-11-28 09:14:58,333][87424] Updated weights for policy 0, policy_version 344889 (0.0007) -[2023-11-28 09:14:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 176488448. Throughput: 0: 2657.6, 1: 2672.1. Samples: 176509640. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:14:58,445][86177] Avg episode reward: [(0, '-526.960'), (1, '-557.420')] -[2023-11-28 09:14:58,515][87426] Updated weights for policy 1, policy_version 344550 (0.0012) -[2023-11-28 09:14:58,890][87426] Updated weights for policy 1, policy_version 344560 (0.0011) -[2023-11-28 09:14:59,267][87426] Updated weights for policy 1, policy_version 344570 (0.0011) -[2023-11-28 09:15:00,176][87424] Updated weights for policy 0, policy_version 344899 (0.0008) -[2023-11-28 09:15:00,548][87424] Updated weights for policy 0, policy_version 344909 (0.0010) -[2023-11-28 09:15:00,927][87424] Updated weights for policy 0, policy_version 344919 (0.0008) -[2023-11-28 09:15:01,362][87426] Updated weights for policy 1, policy_version 344580 (0.0010) -[2023-11-28 09:15:01,753][87426] Updated weights for policy 1, policy_version 344590 (0.0009) -[2023-11-28 09:15:02,123][87426] Updated weights for policy 1, policy_version 344600 (0.0009) -[2023-11-28 09:15:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 176521216. Throughput: 0: 2681.8, 1: 2684.8. Samples: 176534040. Policy #0 lag: (min: 30.0, avg: 50.3, max: 66.0) -[2023-11-28 09:15:03,445][86177] Avg episode reward: [(0, '-521.960'), (1, '-557.960')] -[2023-11-28 09:15:03,485][87424] Updated weights for policy 0, policy_version 344929 (0.0008) -[2023-11-28 09:15:03,874][87424] Updated weights for policy 0, policy_version 344939 (0.0007) -[2023-11-28 09:15:04,246][87424] Updated weights for policy 0, policy_version 344949 (0.0007) -[2023-11-28 09:15:04,511][87426] Updated weights for policy 1, policy_version 344610 (0.0010) -[2023-11-28 09:15:04,627][87424] Updated weights for policy 0, policy_version 344959 (0.0011) -[2023-11-28 09:15:04,879][87426] Updated weights for policy 1, policy_version 344620 (0.0012) -[2023-11-28 09:15:05,262][87426] Updated weights for policy 1, policy_version 344630 (0.0011) -[2023-11-28 09:15:05,636][87426] Updated weights for policy 1, policy_version 344640 (0.0007) -[2023-11-28 09:15:06,445][87424] Updated weights for policy 0, policy_version 344969 (0.0012) -[2023-11-28 09:15:06,821][87424] Updated weights for policy 0, policy_version 344979 (0.0011) -[2023-11-28 09:15:07,202][87424] Updated weights for policy 0, policy_version 344989 (0.0012) -[2023-11-28 09:15:08,047][87426] Updated weights for policy 1, policy_version 344650 (0.0009) -[2023-11-28 09:15:08,422][87426] Updated weights for policy 1, policy_version 344660 (0.0011) -[2023-11-28 09:15:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 176545792. Throughput: 0: 2688.9, 1: 2696.3. Samples: 176566036. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:08,445][86177] Avg episode reward: [(0, '-516.300'), (1, '-518.530')] -[2023-11-28 09:15:08,802][87426] Updated weights for policy 1, policy_version 344670 (0.0012) -[2023-11-28 09:15:09,678][87424] Updated weights for policy 0, policy_version 344999 (0.0011) -[2023-11-28 09:15:10,057][87424] Updated weights for policy 0, policy_version 345009 (0.0010) -[2023-11-28 09:15:10,436][87424] Updated weights for policy 0, policy_version 345019 (0.0011) -[2023-11-28 09:15:10,738][87426] Updated weights for policy 1, policy_version 344680 (0.0011) -[2023-11-28 09:15:11,125][87426] Updated weights for policy 1, policy_version 344690 (0.0012) -[2023-11-28 09:15:11,499][87426] Updated weights for policy 1, policy_version 344700 (0.0012) -[2023-11-28 09:15:12,911][87424] Updated weights for policy 0, policy_version 345029 (0.0012) -[2023-11-28 09:15:13,293][87424] Updated weights for policy 0, policy_version 345039 (0.0012) -[2023-11-28 09:15:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 176570368. Throughput: 0: 2698.1, 1: 2678.4. Samples: 176590220. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:13,445][86177] Avg episode reward: [(0, '-518.300'), (1, '-529.680')] -[2023-11-28 09:15:13,671][87424] Updated weights for policy 0, policy_version 345049 (0.0012) -[2023-11-28 09:15:13,950][87426] Updated weights for policy 1, policy_version 344710 (0.0012) -[2023-11-28 09:15:14,323][87426] Updated weights for policy 1, policy_version 344720 (0.0012) -[2023-11-28 09:15:14,710][87426] Updated weights for policy 1, policy_version 344730 (0.0010) -[2023-11-28 09:15:15,654][87424] Updated weights for policy 0, policy_version 345059 (0.0011) -[2023-11-28 09:15:16,031][87424] Updated weights for policy 0, policy_version 345069 (0.0011) -[2023-11-28 09:15:16,406][87424] Updated weights for policy 0, policy_version 345079 (0.0012) -[2023-11-28 09:15:16,839][87426] Updated weights for policy 1, policy_version 344740 (0.0007) -[2023-11-28 09:15:17,205][87426] Updated weights for policy 1, policy_version 344750 (0.0007) -[2023-11-28 09:15:17,581][87426] Updated weights for policy 1, policy_version 344760 (0.0007) -[2023-11-28 09:15:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 176603136. Throughput: 0: 2669.8, 1: 2674.8. Samples: 176614076. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:18,445][86177] Avg episode reward: [(0, '-529.830'), (1, '-539.470')] -[2023-11-28 09:15:18,570][87424] Updated weights for policy 0, policy_version 345089 (0.0011) -[2023-11-28 09:15:18,959][87424] Updated weights for policy 0, policy_version 345099 (0.0012) -[2023-11-28 09:15:19,338][87424] Updated weights for policy 0, policy_version 345109 (0.0012) -[2023-11-28 09:15:19,717][87424] Updated weights for policy 0, policy_version 345119 (0.0012) -[2023-11-28 09:15:19,977][87426] Updated weights for policy 1, policy_version 344770 (0.0008) -[2023-11-28 09:15:20,357][87426] Updated weights for policy 1, policy_version 344780 (0.0012) -[2023-11-28 09:15:20,730][87426] Updated weights for policy 1, policy_version 344790 (0.0012) -[2023-11-28 09:15:21,111][87426] Updated weights for policy 1, policy_version 344800 (0.0011) -[2023-11-28 09:15:21,686][87424] Updated weights for policy 0, policy_version 345129 (0.0011) -[2023-11-28 09:15:22,062][87424] Updated weights for policy 0, policy_version 345139 (0.0011) -[2023-11-28 09:15:22,439][87424] Updated weights for policy 0, policy_version 345149 (0.0012) -[2023-11-28 09:15:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 176627712. Throughput: 0: 2658.4, 1: 2657.9. Samples: 176645256. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:23,445][86177] Avg episode reward: [(0, '-531.050'), (1, '-545.420')] -[2023-11-28 09:15:23,864][87426] Updated weights for policy 1, policy_version 344810 (0.0012) -[2023-11-28 09:15:24,236][87426] Updated weights for policy 1, policy_version 344820 (0.0012) -[2023-11-28 09:15:24,623][87426] Updated weights for policy 1, policy_version 344830 (0.0012) -[2023-11-28 09:15:24,708][87424] Updated weights for policy 0, policy_version 345159 (0.0012) -[2023-11-28 09:15:25,083][87424] Updated weights for policy 0, policy_version 345169 (0.0012) -[2023-11-28 09:15:25,464][87424] Updated weights for policy 0, policy_version 345179 (0.0012) -[2023-11-28 09:15:26,941][87426] Updated weights for policy 1, policy_version 344840 (0.0008) -[2023-11-28 09:15:27,319][87426] Updated weights for policy 1, policy_version 344850 (0.0007) -[2023-11-28 09:15:27,693][87426] Updated weights for policy 1, policy_version 344860 (0.0007) -[2023-11-28 09:15:27,968][87424] Updated weights for policy 0, policy_version 345189 (0.0012) -[2023-11-28 09:15:28,337][87424] Updated weights for policy 0, policy_version 345199 (0.0010) -[2023-11-28 09:15:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176652288. Throughput: 0: 2672.4, 1: 2672.2. Samples: 176669696. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:28,445][86177] Avg episode reward: [(0, '-529.710'), (1, '-557.220')] -[2023-11-28 09:15:28,720][87424] Updated weights for policy 0, policy_version 345209 (0.0010) -[2023-11-28 09:15:29,893][87426] Updated weights for policy 1, policy_version 344870 (0.0008) -[2023-11-28 09:15:30,268][87426] Updated weights for policy 1, policy_version 344880 (0.0012) -[2023-11-28 09:15:30,617][87424] Updated weights for policy 0, policy_version 345219 (0.0011) -[2023-11-28 09:15:30,651][87426] Updated weights for policy 1, policy_version 344890 (0.0011) -[2023-11-28 09:15:30,990][87424] Updated weights for policy 0, policy_version 345229 (0.0009) -[2023-11-28 09:15:31,370][87424] Updated weights for policy 0, policy_version 345239 (0.0007) -[2023-11-28 09:15:32,881][87426] Updated weights for policy 1, policy_version 344900 (0.0009) -[2023-11-28 09:15:33,263][87426] Updated weights for policy 1, policy_version 344910 (0.0007) -[2023-11-28 09:15:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176676864. Throughput: 0: 2686.2, 1: 2666.0. Samples: 176693864. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:33,445][86177] Avg episode reward: [(0, '-509.820'), (1, '-543.640')] -[2023-11-28 09:15:33,636][87426] Updated weights for policy 1, policy_version 344920 (0.0008) -[2023-11-28 09:15:33,658][87424] Updated weights for policy 0, policy_version 345249 (0.0009) -[2023-11-28 09:15:34,038][87424] Updated weights for policy 0, policy_version 345259 (0.0010) -[2023-11-28 09:15:34,425][87424] Updated weights for policy 0, policy_version 345269 (0.0011) -[2023-11-28 09:15:34,810][87424] Updated weights for policy 0, policy_version 345279 (0.0012) -[2023-11-28 09:15:35,494][87426] Updated weights for policy 1, policy_version 344930 (0.0011) -[2023-11-28 09:15:35,876][87426] Updated weights for policy 1, policy_version 344940 (0.0010) -[2023-11-28 09:15:36,258][87426] Updated weights for policy 1, policy_version 344950 (0.0010) -[2023-11-28 09:15:36,644][87426] Updated weights for policy 1, policy_version 344960 (0.0012) -[2023-11-28 09:15:37,132][87424] Updated weights for policy 0, policy_version 345289 (0.0011) -[2023-11-28 09:15:37,516][87424] Updated weights for policy 0, policy_version 345299 (0.0010) -[2023-11-28 09:15:37,895][87424] Updated weights for policy 0, policy_version 345309 (0.0008) -[2023-11-28 09:15:38,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 176709632. Throughput: 0: 2692.4, 1: 2682.4. Samples: 176726384. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:38,446][86177] Avg episode reward: [(0, '-508.570'), (1, '-528.770')] -[2023-11-28 09:15:38,975][87426] Updated weights for policy 1, policy_version 344970 (0.0012) -[2023-11-28 09:15:39,353][87426] Updated weights for policy 1, policy_version 344980 (0.0012) -[2023-11-28 09:15:39,675][87424] Updated weights for policy 0, policy_version 345319 (0.0010) -[2023-11-28 09:15:39,729][87426] Updated weights for policy 1, policy_version 344990 (0.0009) -[2023-11-28 09:15:40,057][87424] Updated weights for policy 0, policy_version 345329 (0.0010) -[2023-11-28 09:15:40,444][87424] Updated weights for policy 0, policy_version 345339 (0.0009) -[2023-11-28 09:15:41,885][87426] Updated weights for policy 1, policy_version 345000 (0.0010) -[2023-11-28 09:15:42,262][87426] Updated weights for policy 1, policy_version 345010 (0.0011) -[2023-11-28 09:15:42,629][87426] Updated weights for policy 1, policy_version 345020 (0.0009) -[2023-11-28 09:15:43,023][87424] Updated weights for policy 0, policy_version 345349 (0.0010) -[2023-11-28 09:15:43,408][87424] Updated weights for policy 0, policy_version 345359 (0.0008) -[2023-11-28 09:15:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176734208. Throughput: 0: 2695.2, 1: 2636.2. Samples: 176749552. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:43,445][86177] Avg episode reward: [(0, '-507.560'), (1, '-523.240')] -[2023-11-28 09:15:43,793][87424] Updated weights for policy 0, policy_version 345369 (0.0009) -[2023-11-28 09:15:44,986][87426] Updated weights for policy 1, policy_version 345030 (0.0011) -[2023-11-28 09:15:45,357][87426] Updated weights for policy 1, policy_version 345040 (0.0008) -[2023-11-28 09:15:45,735][87426] Updated weights for policy 1, policy_version 345050 (0.0010) -[2023-11-28 09:15:46,151][87424] Updated weights for policy 0, policy_version 345379 (0.0009) -[2023-11-28 09:15:46,526][87424] Updated weights for policy 0, policy_version 345389 (0.0012) -[2023-11-28 09:15:46,903][87424] Updated weights for policy 0, policy_version 345399 (0.0012) -[2023-11-28 09:15:47,984][87426] Updated weights for policy 1, policy_version 345060 (0.0011) -[2023-11-28 09:15:48,355][87426] Updated weights for policy 1, policy_version 345070 (0.0012) -[2023-11-28 09:15:48,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 176758784. Throughput: 0: 2659.5, 1: 2652.9. Samples: 176773096. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:48,445][86177] Avg episode reward: [(0, '-509.780'), (1, '-514.910')] -[2023-11-28 09:15:48,749][87426] Updated weights for policy 1, policy_version 345080 (0.0012) -[2023-11-28 09:15:49,243][87424] Updated weights for policy 0, policy_version 345409 (0.0012) -[2023-11-28 09:15:49,618][87424] Updated weights for policy 0, policy_version 345419 (0.0011) -[2023-11-28 09:15:50,004][87424] Updated weights for policy 0, policy_version 345429 (0.0011) -[2023-11-28 09:15:50,379][87424] Updated weights for policy 0, policy_version 345439 (0.0011) -[2023-11-28 09:15:51,339][87426] Updated weights for policy 1, policy_version 345090 (0.0010) -[2023-11-28 09:15:51,719][87426] Updated weights for policy 1, policy_version 345100 (0.0012) -[2023-11-28 09:15:52,110][87426] Updated weights for policy 1, policy_version 345110 (0.0010) -[2023-11-28 09:15:52,506][87426] Updated weights for policy 1, policy_version 345120 (0.0011) -[2023-11-28 09:15:52,797][87424] Updated weights for policy 0, policy_version 345449 (0.0009) -[2023-11-28 09:15:53,174][87424] Updated weights for policy 0, policy_version 345459 (0.0010) -[2023-11-28 09:15:53,445][86177] Fps is (10 sec: 4914.8, 60 sec: 5324.7, 300 sec: 5359.5). Total num frames: 176783360. Throughput: 0: 2672.0, 1: 2636.0. Samples: 176804900. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:53,446][86177] Avg episode reward: [(0, '-508.730'), (1, '-509.390')] -[2023-11-28 09:15:53,551][87424] Updated weights for policy 0, policy_version 345469 (0.0011) -[2023-11-28 09:15:54,764][87426] Updated weights for policy 1, policy_version 345130 (0.0012) -[2023-11-28 09:15:55,145][87426] Updated weights for policy 1, policy_version 345140 (0.0012) -[2023-11-28 09:15:55,519][87426] Updated weights for policy 1, policy_version 345150 (0.0010) -[2023-11-28 09:15:55,581][87424] Updated weights for policy 0, policy_version 345479 (0.0010) -[2023-11-28 09:15:55,973][87424] Updated weights for policy 0, policy_version 345489 (0.0009) -[2023-11-28 09:15:56,357][87424] Updated weights for policy 0, policy_version 345499 (0.0014) -[2023-11-28 09:15:57,359][87426] Updated weights for policy 1, policy_version 345160 (0.0010) -[2023-11-28 09:15:57,734][87426] Updated weights for policy 1, policy_version 345170 (0.0008) -[2023-11-28 09:15:58,119][87426] Updated weights for policy 1, policy_version 345180 (0.0007) -[2023-11-28 09:15:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 176816128. Throughput: 0: 2668.9, 1: 2653.8. Samples: 176829740. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:15:58,445][86177] Avg episode reward: [(0, '-509.380'), (1, '-517.380')] -[2023-11-28 09:15:58,708][87424] Updated weights for policy 0, policy_version 345509 (0.0010) -[2023-11-28 09:15:59,088][87424] Updated weights for policy 0, policy_version 345519 (0.0008) -[2023-11-28 09:15:59,468][87424] Updated weights for policy 0, policy_version 345529 (0.0008) -[2023-11-28 09:16:00,285][87426] Updated weights for policy 1, policy_version 345190 (0.0007) -[2023-11-28 09:16:00,662][87426] Updated weights for policy 1, policy_version 345200 (0.0010) -[2023-11-28 09:16:01,045][87426] Updated weights for policy 1, policy_version 345210 (0.0010) -[2023-11-28 09:16:01,829][87424] Updated weights for policy 0, policy_version 345539 (0.0009) -[2023-11-28 09:16:02,211][87424] Updated weights for policy 0, policy_version 345549 (0.0011) -[2023-11-28 09:16:02,599][87424] Updated weights for policy 0, policy_version 345559 (0.0012) -[2023-11-28 09:16:02,897][87426] Updated weights for policy 1, policy_version 345220 (0.0009) -[2023-11-28 09:16:03,273][87426] Updated weights for policy 1, policy_version 345230 (0.0008) -[2023-11-28 09:16:03,444][86177] Fps is (10 sec: 5734.9, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 176840704. Throughput: 0: 2666.3, 1: 2653.5. Samples: 176853468. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:16:03,445][86177] Avg episode reward: [(0, '-544.430'), (1, '-515.860')] -[2023-11-28 09:16:03,649][87426] Updated weights for policy 1, policy_version 345240 (0.0007) -[2023-11-28 09:16:04,949][87424] Updated weights for policy 0, policy_version 345569 (0.0011) -[2023-11-28 09:16:05,330][87424] Updated weights for policy 0, policy_version 345579 (0.0008) -[2023-11-28 09:16:05,709][87424] Updated weights for policy 0, policy_version 345589 (0.0007) -[2023-11-28 09:16:05,947][87426] Updated weights for policy 1, policy_version 345250 (0.0007) -[2023-11-28 09:16:06,084][87424] Updated weights for policy 0, policy_version 345599 (0.0007) -[2023-11-28 09:16:06,333][87426] Updated weights for policy 1, policy_version 345260 (0.0007) -[2023-11-28 09:16:06,714][87426] Updated weights for policy 1, policy_version 345270 (0.0008) -[2023-11-28 09:16:07,085][87426] Updated weights for policy 1, policy_version 345280 (0.0008) -[2023-11-28 09:16:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176865280. Throughput: 0: 2650.6, 1: 2663.1. Samples: 176884372. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:16:08,445][86177] Avg episode reward: [(0, '-541.570'), (1, '-515.970')] -[2023-11-28 09:16:08,640][87424] Updated weights for policy 0, policy_version 345609 (0.0008) -[2023-11-28 09:16:09,021][87424] Updated weights for policy 0, policy_version 345619 (0.0008) -[2023-11-28 09:16:09,407][87424] Updated weights for policy 0, policy_version 345629 (0.0007) -[2023-11-28 09:16:09,584][87426] Updated weights for policy 1, policy_version 345290 (0.0008) -[2023-11-28 09:16:09,962][87426] Updated weights for policy 1, policy_version 345300 (0.0009) -[2023-11-28 09:16:10,335][87426] Updated weights for policy 1, policy_version 345310 (0.0008) -[2023-11-28 09:16:11,681][87424] Updated weights for policy 0, policy_version 345639 (0.0011) -[2023-11-28 09:16:12,059][87424] Updated weights for policy 0, policy_version 345649 (0.0011) -[2023-11-28 09:16:12,443][87424] Updated weights for policy 0, policy_version 345659 (0.0011) -[2023-11-28 09:16:12,714][87426] Updated weights for policy 1, policy_version 345320 (0.0011) -[2023-11-28 09:16:13,091][87426] Updated weights for policy 1, policy_version 345330 (0.0012) -[2023-11-28 09:16:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 176889856. Throughput: 0: 2631.8, 1: 2674.2. Samples: 176908468. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:16:13,445][86177] Avg episode reward: [(0, '-545.090'), (1, '-520.390')] -[2023-11-28 09:16:13,473][87426] Updated weights for policy 1, policy_version 345340 (0.0010) -[2023-11-28 09:16:14,951][87424] Updated weights for policy 0, policy_version 345669 (0.0012) -[2023-11-28 09:16:15,346][87424] Updated weights for policy 0, policy_version 345679 (0.0016) -[2023-11-28 09:16:15,389][87426] Updated weights for policy 1, policy_version 345350 (0.0011) -[2023-11-28 09:16:15,727][87424] Updated weights for policy 0, policy_version 345689 (0.0014) -[2023-11-28 09:16:15,762][87426] Updated weights for policy 1, policy_version 345360 (0.0012) -[2023-11-28 09:16:16,140][87426] Updated weights for policy 1, policy_version 345370 (0.0011) -[2023-11-28 09:16:17,878][87424] Updated weights for policy 0, policy_version 345699 (0.0008) -[2023-11-28 09:16:18,259][87424] Updated weights for policy 0, policy_version 345709 (0.0009) -[2023-11-28 09:16:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 176914432. Throughput: 0: 2608.4, 1: 2673.3. Samples: 176931540. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:16:18,445][86177] Avg episode reward: [(0, '-549.170'), (1, '-522.300')] -[2023-11-28 09:16:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000345376_88416256.pth... -[2023-11-28 09:16:18,498][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000342880_87777280.pth -[2023-11-28 09:16:18,635][87424] Updated weights for policy 0, policy_version 345719 (0.0011) -[2023-11-28 09:16:18,761][87426] Updated weights for policy 1, policy_version 345380 (0.0011) -[2023-11-28 09:16:18,978][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000345728_88506368.pth... -[2023-11-28 09:16:19,021][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000343232_87867392.pth -[2023-11-28 09:16:19,147][87426] Updated weights for policy 1, policy_version 345390 (0.0009) -[2023-11-28 09:16:19,518][87426] Updated weights for policy 1, policy_version 345400 (0.0010) -[2023-11-28 09:16:20,853][87424] Updated weights for policy 0, policy_version 345729 (0.0011) -[2023-11-28 09:16:21,239][87424] Updated weights for policy 0, policy_version 345739 (0.0012) -[2023-11-28 09:16:21,432][87426] Updated weights for policy 1, policy_version 345410 (0.0010) -[2023-11-28 09:16:21,618][87424] Updated weights for policy 0, policy_version 345749 (0.0011) -[2023-11-28 09:16:21,801][87426] Updated weights for policy 1, policy_version 345420 (0.0011) -[2023-11-28 09:16:22,006][87424] Updated weights for policy 0, policy_version 345759 (0.0012) -[2023-11-28 09:16:22,188][87426] Updated weights for policy 1, policy_version 345430 (0.0012) -[2023-11-28 09:16:22,565][87426] Updated weights for policy 1, policy_version 345440 (0.0012) -[2023-11-28 09:16:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176947200. Throughput: 0: 2611.7, 1: 2654.2. Samples: 176963344. Policy #0 lag: (min: 31.0, avg: 40.5, max: 63.0) -[2023-11-28 09:16:23,445][86177] Avg episode reward: [(0, '-518.240'), (1, '-525.470')] -[2023-11-28 09:16:24,168][87424] Updated weights for policy 0, policy_version 345769 (0.0012) -[2023-11-28 09:16:24,537][87424] Updated weights for policy 0, policy_version 345779 (0.0011) -[2023-11-28 09:16:24,926][87424] Updated weights for policy 0, policy_version 345789 (0.0011) -[2023-11-28 09:16:25,201][87426] Updated weights for policy 1, policy_version 345450 (0.0010) -[2023-11-28 09:16:25,582][87426] Updated weights for policy 1, policy_version 345460 (0.0008) -[2023-11-28 09:16:25,962][87426] Updated weights for policy 1, policy_version 345470 (0.0008) -[2023-11-28 09:16:26,891][87424] Updated weights for policy 0, policy_version 345799 (0.0011) -[2023-11-28 09:16:27,286][87424] Updated weights for policy 0, policy_version 345809 (0.0011) -[2023-11-28 09:16:27,672][87424] Updated weights for policy 0, policy_version 345819 (0.0012) -[2023-11-28 09:16:28,326][87426] Updated weights for policy 1, policy_version 345480 (0.0011) -[2023-11-28 09:16:28,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176971776. Throughput: 0: 2611.9, 1: 2677.3. Samples: 176987568. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:16:28,446][86177] Avg episode reward: [(0, '-518.390'), (1, '-532.890')] -[2023-11-28 09:16:28,713][87426] Updated weights for policy 1, policy_version 345490 (0.0011) -[2023-11-28 09:16:29,088][87426] Updated weights for policy 1, policy_version 345500 (0.0009) -[2023-11-28 09:16:30,106][87424] Updated weights for policy 0, policy_version 345829 (0.0011) -[2023-11-28 09:16:30,481][87424] Updated weights for policy 0, policy_version 345839 (0.0009) -[2023-11-28 09:16:30,869][87424] Updated weights for policy 0, policy_version 345849 (0.0009) -[2023-11-28 09:16:31,411][87426] Updated weights for policy 1, policy_version 345510 (0.0008) -[2023-11-28 09:16:31,802][87426] Updated weights for policy 1, policy_version 345520 (0.0008) -[2023-11-28 09:16:32,177][87426] Updated weights for policy 1, policy_version 345530 (0.0010) -[2023-11-28 09:16:33,273][87424] Updated weights for policy 0, policy_version 345859 (0.0009) -[2023-11-28 09:16:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 176996352. Throughput: 0: 2639.9, 1: 2649.2. Samples: 177011104. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:16:33,445][86177] Avg episode reward: [(0, '-556.000'), (1, '-565.390')] -[2023-11-28 09:16:33,651][87424] Updated weights for policy 0, policy_version 345869 (0.0012) -[2023-11-28 09:16:34,014][87426] Updated weights for policy 1, policy_version 345540 (0.0011) -[2023-11-28 09:16:34,040][87424] Updated weights for policy 0, policy_version 345879 (0.0012) -[2023-11-28 09:16:34,389][87426] Updated weights for policy 1, policy_version 345550 (0.0010) -[2023-11-28 09:16:34,786][87426] Updated weights for policy 1, policy_version 345560 (0.0009) -[2023-11-28 09:16:36,145][87424] Updated weights for policy 0, policy_version 345889 (0.0011) -[2023-11-28 09:16:36,523][87424] Updated weights for policy 0, policy_version 345899 (0.0007) -[2023-11-28 09:16:36,905][87424] Updated weights for policy 0, policy_version 345909 (0.0010) -[2023-11-28 09:16:37,149][87426] Updated weights for policy 1, policy_version 345570 (0.0012) -[2023-11-28 09:16:37,300][87424] Updated weights for policy 0, policy_version 345919 (0.0011) -[2023-11-28 09:16:37,532][87426] Updated weights for policy 1, policy_version 345580 (0.0010) -[2023-11-28 09:16:37,909][87426] Updated weights for policy 1, policy_version 345590 (0.0007) -[2023-11-28 09:16:38,289][87426] Updated weights for policy 1, policy_version 345600 (0.0008) -[2023-11-28 09:16:38,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177029120. Throughput: 0: 2632.9, 1: 2657.5. Samples: 177042964. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:16:38,445][86177] Avg episode reward: [(0, '-554.240'), (1, '-578.630')] -[2023-11-28 09:16:39,306][87424] Updated weights for policy 0, policy_version 345929 (0.0011) -[2023-11-28 09:16:39,686][87424] Updated weights for policy 0, policy_version 345939 (0.0009) -[2023-11-28 09:16:40,071][87424] Updated weights for policy 0, policy_version 345949 (0.0011) -[2023-11-28 09:16:40,613][87426] Updated weights for policy 1, policy_version 345610 (0.0010) -[2023-11-28 09:16:40,992][87426] Updated weights for policy 1, policy_version 345620 (0.0011) -[2023-11-28 09:16:41,371][87426] Updated weights for policy 1, policy_version 345630 (0.0008) -[2023-11-28 09:16:42,494][87424] Updated weights for policy 0, policy_version 345959 (0.0010) -[2023-11-28 09:16:42,879][87424] Updated weights for policy 0, policy_version 345969 (0.0009) -[2023-11-28 09:16:43,244][87424] Updated weights for policy 0, policy_version 345979 (0.0009) -[2023-11-28 09:16:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177053696. Throughput: 0: 2624.3, 1: 2639.0. Samples: 177066588. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:16:43,445][86177] Avg episode reward: [(0, '-546.790'), (1, '-610.620')] -[2023-11-28 09:16:43,544][87426] Updated weights for policy 1, policy_version 345640 (0.0011) -[2023-11-28 09:16:43,922][87426] Updated weights for policy 1, policy_version 345650 (0.0011) -[2023-11-28 09:16:44,294][87426] Updated weights for policy 1, policy_version 345660 (0.0008) -[2023-11-28 09:16:45,287][87424] Updated weights for policy 0, policy_version 345989 (0.0012) -[2023-11-28 09:16:45,666][87424] Updated weights for policy 0, policy_version 345999 (0.0012) -[2023-11-28 09:16:46,038][87424] Updated weights for policy 0, policy_version 346009 (0.0012) -[2023-11-28 09:16:46,738][87426] Updated weights for policy 1, policy_version 345670 (0.0011) -[2023-11-28 09:16:47,110][87426] Updated weights for policy 1, policy_version 345680 (0.0012) -[2023-11-28 09:16:47,486][87426] Updated weights for policy 1, policy_version 345690 (0.0011) -[2023-11-28 09:16:48,279][87424] Updated weights for policy 0, policy_version 346019 (0.0012) -[2023-11-28 09:16:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177078272. Throughput: 0: 2639.1, 1: 2649.8. Samples: 177091468. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:16:48,445][86177] Avg episode reward: [(0, '-547.700'), (1, '-598.410')] -[2023-11-28 09:16:48,658][87424] Updated weights for policy 0, policy_version 346029 (0.0012) -[2023-11-28 09:16:49,042][87424] Updated weights for policy 0, policy_version 346039 (0.0012) -[2023-11-28 09:16:49,440][87426] Updated weights for policy 1, policy_version 345700 (0.0012) -[2023-11-28 09:16:49,812][87426] Updated weights for policy 1, policy_version 345710 (0.0011) -[2023-11-28 09:16:50,196][87426] Updated weights for policy 1, policy_version 345720 (0.0011) -[2023-11-28 09:16:51,313][87424] Updated weights for policy 0, policy_version 346049 (0.0011) -[2023-11-28 09:16:51,696][87424] Updated weights for policy 0, policy_version 346059 (0.0011) -[2023-11-28 09:16:52,075][87424] Updated weights for policy 0, policy_version 346069 (0.0011) -[2023-11-28 09:16:52,451][87424] Updated weights for policy 0, policy_version 346079 (0.0016) -[2023-11-28 09:16:52,532][87426] Updated weights for policy 1, policy_version 345730 (0.0011) -[2023-11-28 09:16:52,908][87426] Updated weights for policy 1, policy_version 345740 (0.0008) -[2023-11-28 09:16:53,292][87426] Updated weights for policy 1, policy_version 345750 (0.0008) -[2023-11-28 09:16:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.9, 300 sec: 5331.7). Total num frames: 177102848. Throughput: 0: 2644.4, 1: 2663.1. Samples: 177123212. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:16:53,445][86177] Avg episode reward: [(0, '-511.380'), (1, '-579.860')] -[2023-11-28 09:16:53,674][87426] Updated weights for policy 1, policy_version 345760 (0.0010) -[2023-11-28 09:16:54,784][87424] Updated weights for policy 0, policy_version 346089 (0.0008) -[2023-11-28 09:16:55,173][87424] Updated weights for policy 0, policy_version 346099 (0.0011) -[2023-11-28 09:16:55,543][87424] Updated weights for policy 0, policy_version 346109 (0.0012) -[2023-11-28 09:16:55,819][87426] Updated weights for policy 1, policy_version 345770 (0.0007) -[2023-11-28 09:16:56,193][87426] Updated weights for policy 1, policy_version 345780 (0.0007) -[2023-11-28 09:16:56,564][87426] Updated weights for policy 1, policy_version 345790 (0.0007) -[2023-11-28 09:16:57,628][87424] Updated weights for policy 0, policy_version 346119 (0.0012) -[2023-11-28 09:16:58,003][87424] Updated weights for policy 0, policy_version 346129 (0.0008) -[2023-11-28 09:16:58,385][87424] Updated weights for policy 0, policy_version 346139 (0.0008) -[2023-11-28 09:16:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.2, 300 sec: 5359.5). Total num frames: 177127424. Throughput: 0: 2653.7, 1: 2649.6. Samples: 177147116. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:16:58,445][86177] Avg episode reward: [(0, '-515.480'), (1, '-555.730')] -[2023-11-28 09:16:58,901][87426] Updated weights for policy 1, policy_version 345800 (0.0008) -[2023-11-28 09:16:59,288][87426] Updated weights for policy 1, policy_version 345810 (0.0011) -[2023-11-28 09:16:59,664][87426] Updated weights for policy 1, policy_version 345820 (0.0012) -[2023-11-28 09:17:00,379][87424] Updated weights for policy 0, policy_version 346149 (0.0010) -[2023-11-28 09:17:00,766][87424] Updated weights for policy 0, policy_version 346159 (0.0012) -[2023-11-28 09:17:01,140][87424] Updated weights for policy 0, policy_version 346169 (0.0012) -[2023-11-28 09:17:01,826][87426] Updated weights for policy 1, policy_version 345830 (0.0012) -[2023-11-28 09:17:02,206][87426] Updated weights for policy 1, policy_version 345840 (0.0013) -[2023-11-28 09:17:02,581][87426] Updated weights for policy 1, policy_version 345850 (0.0012) -[2023-11-28 09:17:03,270][87424] Updated weights for policy 0, policy_version 346179 (0.0012) -[2023-11-28 09:17:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177160192. Throughput: 0: 2690.1, 1: 2654.4. Samples: 177172044. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:17:03,445][86177] Avg episode reward: [(0, '-520.760'), (1, '-581.160')] -[2023-11-28 09:17:03,655][87424] Updated weights for policy 0, policy_version 346189 (0.0008) -[2023-11-28 09:17:04,038][87424] Updated weights for policy 0, policy_version 346199 (0.0007) -[2023-11-28 09:17:05,035][87426] Updated weights for policy 1, policy_version 345860 (0.0010) -[2023-11-28 09:17:05,416][87426] Updated weights for policy 1, policy_version 345870 (0.0011) -[2023-11-28 09:17:05,794][87426] Updated weights for policy 1, policy_version 345880 (0.0011) -[2023-11-28 09:17:05,981][87424] Updated weights for policy 0, policy_version 346209 (0.0008) -[2023-11-28 09:17:06,382][87424] Updated weights for policy 0, policy_version 346219 (0.0012) -[2023-11-28 09:17:06,760][87424] Updated weights for policy 0, policy_version 346229 (0.0012) -[2023-11-28 09:17:07,143][87424] Updated weights for policy 0, policy_version 346239 (0.0012) -[2023-11-28 09:17:07,847][87426] Updated weights for policy 1, policy_version 345890 (0.0011) -[2023-11-28 09:17:08,231][87426] Updated weights for policy 1, policy_version 345900 (0.0012) -[2023-11-28 09:17:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177184768. Throughput: 0: 2707.0, 1: 2669.4. Samples: 177205284. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:17:08,445][86177] Avg episode reward: [(0, '-519.440'), (1, '-552.880')] -[2023-11-28 09:17:08,611][87426] Updated weights for policy 1, policy_version 345910 (0.0012) -[2023-11-28 09:17:08,982][87426] Updated weights for policy 1, policy_version 345920 (0.0011) -[2023-11-28 09:17:09,209][87424] Updated weights for policy 0, policy_version 346249 (0.0008) -[2023-11-28 09:17:09,584][87424] Updated weights for policy 0, policy_version 346259 (0.0007) -[2023-11-28 09:17:09,972][87424] Updated weights for policy 0, policy_version 346269 (0.0010) -[2023-11-28 09:17:11,467][87426] Updated weights for policy 1, policy_version 345930 (0.0012) -[2023-11-28 09:17:11,848][87426] Updated weights for policy 1, policy_version 345940 (0.0011) -[2023-11-28 09:17:12,226][87426] Updated weights for policy 1, policy_version 345950 (0.0011) -[2023-11-28 09:17:12,323][87424] Updated weights for policy 0, policy_version 346279 (0.0011) -[2023-11-28 09:17:12,708][87424] Updated weights for policy 0, policy_version 346289 (0.0011) -[2023-11-28 09:17:13,085][87424] Updated weights for policy 0, policy_version 346299 (0.0010) -[2023-11-28 09:17:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 177217536. Throughput: 0: 2718.3, 1: 2649.1. Samples: 177229100. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:17:13,445][86177] Avg episode reward: [(0, '-515.420'), (1, '-553.780')] -[2023-11-28 09:17:14,177][87426] Updated weights for policy 1, policy_version 345960 (0.0008) -[2023-11-28 09:17:14,564][87426] Updated weights for policy 1, policy_version 345970 (0.0011) -[2023-11-28 09:17:14,933][87426] Updated weights for policy 1, policy_version 345980 (0.0007) -[2023-11-28 09:17:15,608][87424] Updated weights for policy 0, policy_version 346309 (0.0010) -[2023-11-28 09:17:15,989][87424] Updated weights for policy 0, policy_version 346319 (0.0010) -[2023-11-28 09:17:16,374][87424] Updated weights for policy 0, policy_version 346329 (0.0012) -[2023-11-28 09:17:17,436][87426] Updated weights for policy 1, policy_version 345990 (0.0009) -[2023-11-28 09:17:17,820][87426] Updated weights for policy 1, policy_version 346000 (0.0007) -[2023-11-28 09:17:18,195][87426] Updated weights for policy 1, policy_version 346010 (0.0007) -[2023-11-28 09:17:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 177242112. Throughput: 0: 2695.2, 1: 2658.2. Samples: 177252008. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:17:18,445][86177] Avg episode reward: [(0, '-510.000'), (1, '-569.300')] -[2023-11-28 09:17:18,621][87424] Updated weights for policy 0, policy_version 346339 (0.0009) -[2023-11-28 09:17:19,006][87424] Updated weights for policy 0, policy_version 346349 (0.0009) -[2023-11-28 09:17:19,384][87424] Updated weights for policy 0, policy_version 346359 (0.0011) -[2023-11-28 09:17:20,586][87426] Updated weights for policy 1, policy_version 346020 (0.0009) -[2023-11-28 09:17:20,962][87426] Updated weights for policy 1, policy_version 346030 (0.0012) -[2023-11-28 09:17:21,339][87426] Updated weights for policy 1, policy_version 346040 (0.0012) -[2023-11-28 09:17:21,441][87424] Updated weights for policy 0, policy_version 346369 (0.0010) -[2023-11-28 09:17:21,820][87424] Updated weights for policy 0, policy_version 346379 (0.0011) -[2023-11-28 09:17:22,209][87424] Updated weights for policy 0, policy_version 346389 (0.0012) -[2023-11-28 09:17:22,583][87424] Updated weights for policy 0, policy_version 346399 (0.0012) -[2023-11-28 09:17:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177266688. Throughput: 0: 2676.2, 1: 2654.9. Samples: 177282864. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:17:23,445][86177] Avg episode reward: [(0, '-510.970'), (1, '-592.360')] -[2023-11-28 09:17:23,670][87426] Updated weights for policy 1, policy_version 346050 (0.0011) -[2023-11-28 09:17:24,047][87426] Updated weights for policy 1, policy_version 346060 (0.0011) -[2023-11-28 09:17:24,423][87426] Updated weights for policy 1, policy_version 346070 (0.0012) -[2023-11-28 09:17:24,681][87424] Updated weights for policy 0, policy_version 346409 (0.0011) -[2023-11-28 09:17:24,803][87426] Updated weights for policy 1, policy_version 346080 (0.0008) -[2023-11-28 09:17:25,059][87424] Updated weights for policy 0, policy_version 346419 (0.0012) -[2023-11-28 09:17:25,445][87424] Updated weights for policy 0, policy_version 346429 (0.0011) -[2023-11-28 09:17:26,699][87426] Updated weights for policy 1, policy_version 346090 (0.0012) -[2023-11-28 09:17:27,083][87426] Updated weights for policy 1, policy_version 346100 (0.0012) -[2023-11-28 09:17:27,465][87426] Updated weights for policy 1, policy_version 346110 (0.0012) -[2023-11-28 09:17:27,672][87424] Updated weights for policy 0, policy_version 346439 (0.0010) -[2023-11-28 09:17:28,054][87424] Updated weights for policy 0, policy_version 346449 (0.0012) -[2023-11-28 09:17:28,444][87424] Updated weights for policy 0, policy_version 346459 (0.0011) -[2023-11-28 09:17:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177291264. Throughput: 0: 2695.6, 1: 2676.5. Samples: 177308332. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:17:28,445][86177] Avg episode reward: [(0, '-509.090'), (1, '-595.250')] -[2023-11-28 09:17:29,373][87426] Updated weights for policy 1, policy_version 346120 (0.0012) -[2023-11-28 09:17:29,755][87426] Updated weights for policy 1, policy_version 346130 (0.0012) -[2023-11-28 09:17:30,123][87426] Updated weights for policy 1, policy_version 346140 (0.0012) -[2023-11-28 09:17:30,955][87424] Updated weights for policy 0, policy_version 346469 (0.0011) -[2023-11-28 09:17:31,336][87424] Updated weights for policy 0, policy_version 346479 (0.0012) -[2023-11-28 09:17:31,721][87424] Updated weights for policy 0, policy_version 346489 (0.0011) -[2023-11-28 09:17:32,394][87426] Updated weights for policy 1, policy_version 346150 (0.0011) -[2023-11-28 09:17:32,772][87426] Updated weights for policy 1, policy_version 346160 (0.0012) -[2023-11-28 09:17:33,146][87426] Updated weights for policy 1, policy_version 346170 (0.0012) -[2023-11-28 09:17:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 177324032. Throughput: 0: 2683.5, 1: 2682.2. Samples: 177332928. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:17:33,445][86177] Avg episode reward: [(0, '-510.020'), (1, '-588.750')] -[2023-11-28 09:17:34,092][87424] Updated weights for policy 0, policy_version 346499 (0.0012) -[2023-11-28 09:17:34,480][87424] Updated weights for policy 0, policy_version 346509 (0.0012) -[2023-11-28 09:17:34,875][87424] Updated weights for policy 0, policy_version 346519 (0.0011) -[2023-11-28 09:17:34,957][87426] Updated weights for policy 1, policy_version 346180 (0.0012) -[2023-11-28 09:17:35,324][87426] Updated weights for policy 1, policy_version 346190 (0.0011) -[2023-11-28 09:17:35,704][87426] Updated weights for policy 1, policy_version 346200 (0.0011) -[2023-11-28 09:17:37,002][87424] Updated weights for policy 0, policy_version 346529 (0.0012) -[2023-11-28 09:17:37,383][87424] Updated weights for policy 0, policy_version 346539 (0.0010) -[2023-11-28 09:17:37,766][87424] Updated weights for policy 0, policy_version 346549 (0.0008) -[2023-11-28 09:17:37,790][87426] Updated weights for policy 1, policy_version 346210 (0.0009) -[2023-11-28 09:17:38,144][87424] Updated weights for policy 0, policy_version 346559 (0.0008) -[2023-11-28 09:17:38,175][87426] Updated weights for policy 1, policy_version 346220 (0.0008) -[2023-11-28 09:17:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177348608. Throughput: 0: 2686.4, 1: 2715.5. Samples: 177366296. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:17:38,445][86177] Avg episode reward: [(0, '-516.250'), (1, '-584.530')] -[2023-11-28 09:17:38,548][87426] Updated weights for policy 1, policy_version 346230 (0.0008) -[2023-11-28 09:17:38,931][87426] Updated weights for policy 1, policy_version 346240 (0.0009) -[2023-11-28 09:17:40,498][87424] Updated weights for policy 0, policy_version 346569 (0.0016) -[2023-11-28 09:17:40,877][87424] Updated weights for policy 0, policy_version 346579 (0.0012) -[2023-11-28 09:17:40,885][87426] Updated weights for policy 1, policy_version 346250 (0.0012) -[2023-11-28 09:17:41,250][87424] Updated weights for policy 0, policy_version 346589 (0.0008) -[2023-11-28 09:17:41,265][87426] Updated weights for policy 1, policy_version 346260 (0.0009) -[2023-11-28 09:17:41,652][87426] Updated weights for policy 1, policy_version 346270 (0.0009) -[2023-11-28 09:17:43,404][87424] Updated weights for policy 0, policy_version 346599 (0.0011) -[2023-11-28 09:17:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177373184. Throughput: 0: 2686.4, 1: 2727.1. Samples: 177390724. Policy #0 lag: (min: 6.0, avg: 26.0, max: 61.0) -[2023-11-28 09:17:43,445][86177] Avg episode reward: [(0, '-516.580'), (1, '-558.200')] -[2023-11-28 09:17:43,786][87424] Updated weights for policy 0, policy_version 346609 (0.0009) -[2023-11-28 09:17:43,893][87426] Updated weights for policy 1, policy_version 346280 (0.0011) -[2023-11-28 09:17:44,167][87424] Updated weights for policy 0, policy_version 346619 (0.0007) -[2023-11-28 09:17:44,265][87426] Updated weights for policy 1, policy_version 346290 (0.0010) -[2023-11-28 09:17:44,644][87426] Updated weights for policy 1, policy_version 346300 (0.0011) -[2023-11-28 09:17:46,170][87424] Updated weights for policy 0, policy_version 346629 (0.0010) -[2023-11-28 09:17:46,556][87424] Updated weights for policy 0, policy_version 346639 (0.0012) -[2023-11-28 09:17:46,949][87424] Updated weights for policy 0, policy_version 346649 (0.0009) -[2023-11-28 09:17:47,149][87426] Updated weights for policy 1, policy_version 346310 (0.0009) -[2023-11-28 09:17:47,524][87426] Updated weights for policy 1, policy_version 346320 (0.0007) -[2023-11-28 09:17:47,893][87426] Updated weights for policy 1, policy_version 346330 (0.0007) -[2023-11-28 09:17:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 177405952. Throughput: 0: 2684.4, 1: 2717.8. Samples: 177415140. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:17:48,445][86177] Avg episode reward: [(0, '-516.090'), (1, '-567.850')] -[2023-11-28 09:17:49,227][87424] Updated weights for policy 0, policy_version 346659 (0.0009) -[2023-11-28 09:17:49,610][87424] Updated weights for policy 0, policy_version 346669 (0.0012) -[2023-11-28 09:17:49,999][87424] Updated weights for policy 0, policy_version 346679 (0.0012) -[2023-11-28 09:17:50,433][87426] Updated weights for policy 1, policy_version 346340 (0.0009) -[2023-11-28 09:17:50,803][87426] Updated weights for policy 1, policy_version 346350 (0.0009) -[2023-11-28 09:17:51,187][87426] Updated weights for policy 1, policy_version 346360 (0.0009) -[2023-11-28 09:17:52,304][87424] Updated weights for policy 0, policy_version 346689 (0.0009) -[2023-11-28 09:17:52,689][87424] Updated weights for policy 0, policy_version 346699 (0.0012) -[2023-11-28 09:17:53,080][87424] Updated weights for policy 0, policy_version 346709 (0.0012) -[2023-11-28 09:17:53,330][87426] Updated weights for policy 1, policy_version 346370 (0.0009) -[2023-11-28 09:17:53,448][86177] Fps is (10 sec: 4913.4, 60 sec: 5324.5, 300 sec: 5331.7). Total num frames: 177422336. Throughput: 0: 2659.2, 1: 2690.0. Samples: 177446016. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:17:53,449][86177] Avg episode reward: [(0, '-512.330'), (1, '-561.990')] -[2023-11-28 09:17:53,459][87424] Updated weights for policy 0, policy_version 346719 (0.0011) -[2023-11-28 09:17:53,704][87426] Updated weights for policy 1, policy_version 346380 (0.0010) -[2023-11-28 09:17:54,080][87426] Updated weights for policy 1, policy_version 346390 (0.0009) -[2023-11-28 09:17:54,460][87426] Updated weights for policy 1, policy_version 346400 (0.0007) -[2023-11-28 09:17:55,639][87424] Updated weights for policy 0, policy_version 346729 (0.0012) -[2023-11-28 09:17:56,017][87424] Updated weights for policy 0, policy_version 346739 (0.0011) -[2023-11-28 09:17:56,343][87426] Updated weights for policy 1, policy_version 346410 (0.0009) -[2023-11-28 09:17:56,390][87424] Updated weights for policy 0, policy_version 346749 (0.0011) -[2023-11-28 09:17:56,728][87426] Updated weights for policy 1, policy_version 346420 (0.0007) -[2023-11-28 09:17:57,113][87426] Updated weights for policy 1, policy_version 346430 (0.0007) -[2023-11-28 09:17:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 177455104. Throughput: 0: 2643.6, 1: 2713.9. Samples: 177470188. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:17:58,445][86177] Avg episode reward: [(0, '-513.180'), (1, '-552.170')] -[2023-11-28 09:17:58,736][87424] Updated weights for policy 0, policy_version 346759 (0.0012) -[2023-11-28 09:17:59,114][87424] Updated weights for policy 0, policy_version 346769 (0.0009) -[2023-11-28 09:17:59,369][87426] Updated weights for policy 1, policy_version 346440 (0.0007) -[2023-11-28 09:17:59,502][87424] Updated weights for policy 0, policy_version 346779 (0.0008) -[2023-11-28 09:17:59,748][87426] Updated weights for policy 1, policy_version 346450 (0.0008) -[2023-11-28 09:18:00,116][87426] Updated weights for policy 1, policy_version 346460 (0.0010) -[2023-11-28 09:18:01,397][87424] Updated weights for policy 0, policy_version 346789 (0.0011) -[2023-11-28 09:18:01,774][87424] Updated weights for policy 0, policy_version 346799 (0.0012) -[2023-11-28 09:18:02,156][87424] Updated weights for policy 0, policy_version 346809 (0.0012) -[2023-11-28 09:18:02,314][87426] Updated weights for policy 1, policy_version 346470 (0.0009) -[2023-11-28 09:18:02,699][87426] Updated weights for policy 1, policy_version 346480 (0.0010) -[2023-11-28 09:18:03,072][87426] Updated weights for policy 1, policy_version 346490 (0.0011) -[2023-11-28 09:18:03,444][86177] Fps is (10 sec: 6556.1, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 177487872. Throughput: 0: 2668.5, 1: 2723.8. Samples: 177494660. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:03,445][86177] Avg episode reward: [(0, '-516.210'), (1, '-561.440')] -[2023-11-28 09:18:04,675][87424] Updated weights for policy 0, policy_version 346819 (0.0011) -[2023-11-28 09:18:05,067][87424] Updated weights for policy 0, policy_version 346829 (0.0011) -[2023-11-28 09:18:05,433][87424] Updated weights for policy 0, policy_version 346839 (0.0012) -[2023-11-28 09:18:05,514][87426] Updated weights for policy 1, policy_version 346500 (0.0009) -[2023-11-28 09:18:05,890][87426] Updated weights for policy 1, policy_version 346510 (0.0011) -[2023-11-28 09:18:06,267][87426] Updated weights for policy 1, policy_version 346520 (0.0008) -[2023-11-28 09:18:07,212][87424] Updated weights for policy 0, policy_version 346849 (0.0012) -[2023-11-28 09:18:07,600][87424] Updated weights for policy 0, policy_version 346859 (0.0012) -[2023-11-28 09:18:07,977][87424] Updated weights for policy 0, policy_version 346869 (0.0012) -[2023-11-28 09:18:08,357][87424] Updated weights for policy 0, policy_version 346879 (0.0012) -[2023-11-28 09:18:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 177512448. Throughput: 0: 2710.9, 1: 2717.8. Samples: 177527156. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:08,446][86177] Avg episode reward: [(0, '-539.180'), (1, '-555.610')] -[2023-11-28 09:18:08,831][87426] Updated weights for policy 1, policy_version 346530 (0.0008) -[2023-11-28 09:18:09,216][87426] Updated weights for policy 1, policy_version 346540 (0.0008) -[2023-11-28 09:18:09,590][87426] Updated weights for policy 1, policy_version 346550 (0.0007) -[2023-11-28 09:18:09,968][87426] Updated weights for policy 1, policy_version 346560 (0.0010) -[2023-11-28 09:18:10,347][87424] Updated weights for policy 0, policy_version 346889 (0.0012) -[2023-11-28 09:18:10,729][87424] Updated weights for policy 0, policy_version 346899 (0.0011) -[2023-11-28 09:18:11,119][87424] Updated weights for policy 0, policy_version 346909 (0.0010) -[2023-11-28 09:18:12,223][87426] Updated weights for policy 1, policy_version 346570 (0.0012) -[2023-11-28 09:18:12,606][87426] Updated weights for policy 1, policy_version 346580 (0.0012) -[2023-11-28 09:18:12,986][87426] Updated weights for policy 1, policy_version 346590 (0.0011) -[2023-11-28 09:18:13,256][87424] Updated weights for policy 0, policy_version 346919 (0.0010) -[2023-11-28 09:18:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177537024. Throughput: 0: 2691.4, 1: 2676.9. Samples: 177549904. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:13,445][86177] Avg episode reward: [(0, '-543.350'), (1, '-546.570')] -[2023-11-28 09:18:13,647][87424] Updated weights for policy 0, policy_version 346929 (0.0008) -[2023-11-28 09:18:14,025][87424] Updated weights for policy 0, policy_version 346939 (0.0008) -[2023-11-28 09:18:15,109][87426] Updated weights for policy 1, policy_version 346600 (0.0008) -[2023-11-28 09:18:15,484][87426] Updated weights for policy 1, policy_version 346610 (0.0009) -[2023-11-28 09:18:15,871][87426] Updated weights for policy 1, policy_version 346620 (0.0007) -[2023-11-28 09:18:16,543][87424] Updated weights for policy 0, policy_version 346949 (0.0009) -[2023-11-28 09:18:16,928][87424] Updated weights for policy 0, policy_version 346959 (0.0011) -[2023-11-28 09:18:17,314][87424] Updated weights for policy 0, policy_version 346969 (0.0011) -[2023-11-28 09:18:18,067][87426] Updated weights for policy 1, policy_version 346630 (0.0010) -[2023-11-28 09:18:18,440][87426] Updated weights for policy 1, policy_version 346640 (0.0012) -[2023-11-28 09:18:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 177561600. Throughput: 0: 2675.4, 1: 2663.2. Samples: 177573164. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:18,445][86177] Avg episode reward: [(0, '-544.820'), (1, '-546.310')] -[2023-11-28 09:18:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000346976_88825856.pth... -[2023-11-28 09:18:18,490][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000344480_88186880.pth -[2023-11-28 09:18:18,824][87426] Updated weights for policy 1, policy_version 346650 (0.0012) -[2023-11-28 09:18:19,041][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000346656_88743936.pth... -[2023-11-28 09:18:19,074][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000344160_88104960.pth -[2023-11-28 09:18:19,665][87424] Updated weights for policy 0, policy_version 346979 (0.0011) -[2023-11-28 09:18:20,048][87424] Updated weights for policy 0, policy_version 346989 (0.0011) -[2023-11-28 09:18:20,433][87424] Updated weights for policy 0, policy_version 346999 (0.0012) -[2023-11-28 09:18:21,256][87426] Updated weights for policy 1, policy_version 346660 (0.0012) -[2023-11-28 09:18:21,629][87426] Updated weights for policy 1, policy_version 346670 (0.0009) -[2023-11-28 09:18:22,023][87426] Updated weights for policy 1, policy_version 346680 (0.0011) -[2023-11-28 09:18:22,724][87424] Updated weights for policy 0, policy_version 347009 (0.0012) -[2023-11-28 09:18:23,109][87424] Updated weights for policy 0, policy_version 347019 (0.0012) -[2023-11-28 09:18:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177586176. Throughput: 0: 2689.0, 1: 2613.2. Samples: 177604896. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:23,445][86177] Avg episode reward: [(0, '-531.810'), (1, '-539.100')] -[2023-11-28 09:18:23,492][87424] Updated weights for policy 0, policy_version 347029 (0.0012) -[2023-11-28 09:18:23,886][87424] Updated weights for policy 0, policy_version 347039 (0.0012) -[2023-11-28 09:18:24,272][87426] Updated weights for policy 1, policy_version 346690 (0.0010) -[2023-11-28 09:18:24,654][87426] Updated weights for policy 1, policy_version 346700 (0.0011) -[2023-11-28 09:18:25,034][87426] Updated weights for policy 1, policy_version 346710 (0.0011) -[2023-11-28 09:18:25,414][87426] Updated weights for policy 1, policy_version 346720 (0.0008) -[2023-11-28 09:18:26,146][87424] Updated weights for policy 0, policy_version 347049 (0.0008) -[2023-11-28 09:18:26,526][87424] Updated weights for policy 0, policy_version 347059 (0.0007) -[2023-11-28 09:18:26,911][87424] Updated weights for policy 0, policy_version 347069 (0.0011) -[2023-11-28 09:18:27,386][87426] Updated weights for policy 1, policy_version 346730 (0.0012) -[2023-11-28 09:18:27,782][87426] Updated weights for policy 1, policy_version 346740 (0.0012) -[2023-11-28 09:18:28,156][87426] Updated weights for policy 1, policy_version 346750 (0.0012) -[2023-11-28 09:18:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 177618944. Throughput: 0: 2698.8, 1: 2634.4. Samples: 177630720. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:28,445][86177] Avg episode reward: [(0, '-521.770'), (1, '-575.030')] -[2023-11-28 09:18:28,536][87424] Updated weights for policy 0, policy_version 347079 (0.0012) -[2023-11-28 09:18:28,912][87424] Updated weights for policy 0, policy_version 347089 (0.0012) -[2023-11-28 09:18:29,293][87424] Updated weights for policy 0, policy_version 347099 (0.0011) -[2023-11-28 09:18:30,268][87426] Updated weights for policy 1, policy_version 346760 (0.0011) -[2023-11-28 09:18:30,643][87426] Updated weights for policy 1, policy_version 346770 (0.0010) -[2023-11-28 09:18:31,023][87426] Updated weights for policy 1, policy_version 346780 (0.0007) -[2023-11-28 09:18:31,489][87424] Updated weights for policy 0, policy_version 347109 (0.0008) -[2023-11-28 09:18:31,871][87424] Updated weights for policy 0, policy_version 347119 (0.0009) -[2023-11-28 09:18:32,243][87424] Updated weights for policy 0, policy_version 347129 (0.0009) -[2023-11-28 09:18:33,409][87426] Updated weights for policy 1, policy_version 346790 (0.0007) -[2023-11-28 09:18:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177643520. Throughput: 0: 2716.9, 1: 2647.2. Samples: 177656524. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:33,445][86177] Avg episode reward: [(0, '-525.810'), (1, '-582.950')] -[2023-11-28 09:18:33,796][87426] Updated weights for policy 1, policy_version 346800 (0.0008) -[2023-11-28 09:18:34,175][87426] Updated weights for policy 1, policy_version 346810 (0.0007) -[2023-11-28 09:18:34,320][87424] Updated weights for policy 0, policy_version 347139 (0.0011) -[2023-11-28 09:18:34,696][87424] Updated weights for policy 0, policy_version 347149 (0.0008) -[2023-11-28 09:18:35,074][87424] Updated weights for policy 0, policy_version 347159 (0.0008) -[2023-11-28 09:18:36,621][87426] Updated weights for policy 1, policy_version 346820 (0.0009) -[2023-11-28 09:18:37,000][87426] Updated weights for policy 1, policy_version 346830 (0.0008) -[2023-11-28 09:18:37,379][87426] Updated weights for policy 1, policy_version 346840 (0.0008) -[2023-11-28 09:18:37,398][87424] Updated weights for policy 0, policy_version 347169 (0.0010) -[2023-11-28 09:18:37,777][87424] Updated weights for policy 0, policy_version 347179 (0.0008) -[2023-11-28 09:18:38,156][87424] Updated weights for policy 0, policy_version 347189 (0.0007) -[2023-11-28 09:18:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177668096. Throughput: 0: 2728.3, 1: 2651.2. Samples: 177688076. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:38,445][86177] Avg episode reward: [(0, '-522.610'), (1, '-590.110')] -[2023-11-28 09:18:38,545][87424] Updated weights for policy 0, policy_version 347199 (0.0008) -[2023-11-28 09:18:39,485][87426] Updated weights for policy 1, policy_version 346850 (0.0008) -[2023-11-28 09:18:39,862][87426] Updated weights for policy 1, policy_version 346860 (0.0011) -[2023-11-28 09:18:40,235][87426] Updated weights for policy 1, policy_version 346870 (0.0012) -[2023-11-28 09:18:40,610][87426] Updated weights for policy 1, policy_version 346880 (0.0010) -[2023-11-28 09:18:40,654][87424] Updated weights for policy 0, policy_version 347209 (0.0009) -[2023-11-28 09:18:41,059][87424] Updated weights for policy 0, policy_version 347219 (0.0008) -[2023-11-28 09:18:41,432][87424] Updated weights for policy 0, policy_version 347229 (0.0008) -[2023-11-28 09:18:43,078][87426] Updated weights for policy 1, policy_version 346890 (0.0012) -[2023-11-28 09:18:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177692672. Throughput: 0: 2729.5, 1: 2630.0. Samples: 177711364. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:43,445][86177] Avg episode reward: [(0, '-520.030'), (1, '-599.410')] -[2023-11-28 09:18:43,447][87426] Updated weights for policy 1, policy_version 346900 (0.0011) -[2023-11-28 09:18:43,518][87424] Updated weights for policy 0, policy_version 347239 (0.0010) -[2023-11-28 09:18:43,836][87426] Updated weights for policy 1, policy_version 346910 (0.0011) -[2023-11-28 09:18:43,907][87424] Updated weights for policy 0, policy_version 347249 (0.0012) -[2023-11-28 09:18:44,283][87424] Updated weights for policy 0, policy_version 347259 (0.0012) -[2023-11-28 09:18:45,914][87426] Updated weights for policy 1, policy_version 346920 (0.0012) -[2023-11-28 09:18:46,286][87426] Updated weights for policy 1, policy_version 346930 (0.0012) -[2023-11-28 09:18:46,671][87426] Updated weights for policy 1, policy_version 346940 (0.0012) -[2023-11-28 09:18:46,773][87424] Updated weights for policy 0, policy_version 347269 (0.0010) -[2023-11-28 09:18:47,162][87424] Updated weights for policy 0, policy_version 347279 (0.0007) -[2023-11-28 09:18:47,548][87424] Updated weights for policy 0, policy_version 347289 (0.0007) -[2023-11-28 09:18:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177725440. Throughput: 0: 2704.7, 1: 2652.1. Samples: 177735716. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:48,445][86177] Avg episode reward: [(0, '-513.550'), (1, '-588.080')] -[2023-11-28 09:18:49,126][87426] Updated weights for policy 1, policy_version 346950 (0.0012) -[2023-11-28 09:18:49,501][87426] Updated weights for policy 1, policy_version 346960 (0.0011) -[2023-11-28 09:18:49,618][87424] Updated weights for policy 0, policy_version 347299 (0.0008) -[2023-11-28 09:18:49,890][87426] Updated weights for policy 1, policy_version 346970 (0.0011) -[2023-11-28 09:18:49,997][87424] Updated weights for policy 0, policy_version 347309 (0.0010) -[2023-11-28 09:18:50,375][87424] Updated weights for policy 0, policy_version 347319 (0.0009) -[2023-11-28 09:18:51,786][87426] Updated weights for policy 1, policy_version 346980 (0.0011) -[2023-11-28 09:18:52,156][87426] Updated weights for policy 1, policy_version 346990 (0.0012) -[2023-11-28 09:18:52,540][87426] Updated weights for policy 1, policy_version 347000 (0.0012) -[2023-11-28 09:18:52,732][87424] Updated weights for policy 0, policy_version 347329 (0.0009) -[2023-11-28 09:18:53,113][87424] Updated weights for policy 0, policy_version 347339 (0.0011) -[2023-11-28 09:18:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.7, 300 sec: 5331.7). Total num frames: 177750016. Throughput: 0: 2673.6, 1: 2657.1. Samples: 177767036. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:53,445][86177] Avg episode reward: [(0, '-508.750'), (1, '-575.710')] -[2023-11-28 09:18:53,493][87424] Updated weights for policy 0, policy_version 347349 (0.0010) -[2023-11-28 09:18:53,874][87424] Updated weights for policy 0, policy_version 347359 (0.0010) -[2023-11-28 09:18:54,931][87426] Updated weights for policy 1, policy_version 347010 (0.0011) -[2023-11-28 09:18:55,308][87426] Updated weights for policy 1, policy_version 347020 (0.0010) -[2023-11-28 09:18:55,689][87426] Updated weights for policy 1, policy_version 347030 (0.0007) -[2023-11-28 09:18:55,718][87424] Updated weights for policy 0, policy_version 347369 (0.0010) -[2023-11-28 09:18:56,079][87426] Updated weights for policy 1, policy_version 347040 (0.0008) -[2023-11-28 09:18:56,112][87424] Updated weights for policy 0, policy_version 347379 (0.0010) -[2023-11-28 09:18:56,496][87424] Updated weights for policy 0, policy_version 347389 (0.0008) -[2023-11-28 09:18:58,095][87426] Updated weights for policy 1, policy_version 347050 (0.0012) -[2023-11-28 09:18:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177774592. Throughput: 0: 2706.8, 1: 2688.1. Samples: 177792672. Policy #0 lag: (min: 31.0, avg: 37.1, max: 63.0) -[2023-11-28 09:18:58,446][86177] Avg episode reward: [(0, '-511.950'), (1, '-568.290')] -[2023-11-28 09:18:58,473][87426] Updated weights for policy 1, policy_version 347060 (0.0011) -[2023-11-28 09:18:58,584][87424] Updated weights for policy 0, policy_version 347399 (0.0011) -[2023-11-28 09:18:58,861][87426] Updated weights for policy 1, policy_version 347070 (0.0009) -[2023-11-28 09:18:58,963][87424] Updated weights for policy 0, policy_version 347409 (0.0011) -[2023-11-28 09:18:59,340][87424] Updated weights for policy 0, policy_version 347419 (0.0007) -[2023-11-28 09:19:00,895][87426] Updated weights for policy 1, policy_version 347080 (0.0011) -[2023-11-28 09:19:01,266][87426] Updated weights for policy 1, policy_version 347090 (0.0012) -[2023-11-28 09:19:01,646][87426] Updated weights for policy 1, policy_version 347100 (0.0012) -[2023-11-28 09:19:01,891][87424] Updated weights for policy 0, policy_version 347429 (0.0010) -[2023-11-28 09:19:02,288][87424] Updated weights for policy 0, policy_version 347439 (0.0012) -[2023-11-28 09:19:02,660][87424] Updated weights for policy 0, policy_version 347449 (0.0011) -[2023-11-28 09:19:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177807360. Throughput: 0: 2738.0, 1: 2697.1. Samples: 177817744. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:03,445][86177] Avg episode reward: [(0, '-511.990'), (1, '-557.260')] -[2023-11-28 09:19:03,982][87426] Updated weights for policy 1, policy_version 347110 (0.0011) -[2023-11-28 09:19:04,362][87426] Updated weights for policy 1, policy_version 347120 (0.0012) -[2023-11-28 09:19:04,456][87424] Updated weights for policy 0, policy_version 347459 (0.0012) -[2023-11-28 09:19:04,737][87426] Updated weights for policy 1, policy_version 347130 (0.0012) -[2023-11-28 09:19:04,837][87424] Updated weights for policy 0, policy_version 347469 (0.0008) -[2023-11-28 09:19:05,210][87424] Updated weights for policy 0, policy_version 347479 (0.0008) -[2023-11-28 09:19:06,822][87426] Updated weights for policy 1, policy_version 347140 (0.0011) -[2023-11-28 09:19:07,192][87426] Updated weights for policy 1, policy_version 347150 (0.0010) -[2023-11-28 09:19:07,346][87424] Updated weights for policy 0, policy_version 347489 (0.0008) -[2023-11-28 09:19:07,567][87426] Updated weights for policy 1, policy_version 347160 (0.0012) -[2023-11-28 09:19:07,731][87424] Updated weights for policy 0, policy_version 347499 (0.0012) -[2023-11-28 09:19:08,111][87424] Updated weights for policy 0, policy_version 347509 (0.0008) -[2023-11-28 09:19:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177831936. Throughput: 0: 2745.7, 1: 2725.9. Samples: 177851116. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:08,445][86177] Avg episode reward: [(0, '-517.010'), (1, '-550.070')] -[2023-11-28 09:19:08,497][87424] Updated weights for policy 0, policy_version 347519 (0.0009) -[2023-11-28 09:19:09,512][87426] Updated weights for policy 1, policy_version 347170 (0.0012) -[2023-11-28 09:19:09,898][87426] Updated weights for policy 1, policy_version 347180 (0.0012) -[2023-11-28 09:19:10,280][87426] Updated weights for policy 1, policy_version 347190 (0.0012) -[2023-11-28 09:19:10,654][87426] Updated weights for policy 1, policy_version 347200 (0.0011) -[2023-11-28 09:19:10,727][87424] Updated weights for policy 0, policy_version 347529 (0.0011) -[2023-11-28 09:19:11,116][87424] Updated weights for policy 0, policy_version 347539 (0.0012) -[2023-11-28 09:19:11,497][87424] Updated weights for policy 0, policy_version 347549 (0.0012) -[2023-11-28 09:19:13,239][87426] Updated weights for policy 1, policy_version 347210 (0.0011) -[2023-11-28 09:19:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177856512. Throughput: 0: 2736.0, 1: 2696.1. Samples: 177875164. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:13,445][86177] Avg episode reward: [(0, '-517.270'), (1, '-540.460')] -[2023-11-28 09:19:13,619][87426] Updated weights for policy 1, policy_version 347220 (0.0010) -[2023-11-28 09:19:14,004][87426] Updated weights for policy 1, policy_version 347230 (0.0010) -[2023-11-28 09:19:14,126][87424] Updated weights for policy 0, policy_version 347559 (0.0009) -[2023-11-28 09:19:14,512][87424] Updated weights for policy 0, policy_version 347569 (0.0008) -[2023-11-28 09:19:14,886][87424] Updated weights for policy 0, policy_version 347579 (0.0007) -[2023-11-28 09:19:16,543][87426] Updated weights for policy 1, policy_version 347240 (0.0008) -[2023-11-28 09:19:16,932][87426] Updated weights for policy 1, policy_version 347250 (0.0008) -[2023-11-28 09:19:17,289][87424] Updated weights for policy 0, policy_version 347589 (0.0008) -[2023-11-28 09:19:17,304][87426] Updated weights for policy 1, policy_version 347260 (0.0007) -[2023-11-28 09:19:17,671][87424] Updated weights for policy 0, policy_version 347599 (0.0012) -[2023-11-28 09:19:18,069][87424] Updated weights for policy 0, policy_version 347609 (0.0012) -[2023-11-28 09:19:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 177889280. Throughput: 0: 2679.3, 1: 2684.4. Samples: 177897888. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:18,445][86177] Avg episode reward: [(0, '-519.260'), (1, '-536.650')] -[2023-11-28 09:19:19,250][87426] Updated weights for policy 1, policy_version 347270 (0.0010) -[2023-11-28 09:19:19,628][87426] Updated weights for policy 1, policy_version 347280 (0.0012) -[2023-11-28 09:19:20,009][87426] Updated weights for policy 1, policy_version 347290 (0.0011) -[2023-11-28 09:19:20,061][87424] Updated weights for policy 0, policy_version 347619 (0.0011) -[2023-11-28 09:19:20,441][87424] Updated weights for policy 0, policy_version 347629 (0.0009) -[2023-11-28 09:19:20,832][87424] Updated weights for policy 0, policy_version 347639 (0.0011) -[2023-11-28 09:19:22,627][87426] Updated weights for policy 1, policy_version 347300 (0.0010) -[2023-11-28 09:19:22,998][87426] Updated weights for policy 1, policy_version 347310 (0.0012) -[2023-11-28 09:19:23,101][87424] Updated weights for policy 0, policy_version 347649 (0.0012) -[2023-11-28 09:19:23,383][87426] Updated weights for policy 1, policy_version 347320 (0.0009) -[2023-11-28 09:19:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177905664. Throughput: 0: 2673.3, 1: 2681.9. Samples: 177929056. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:23,445][86177] Avg episode reward: [(0, '-520.290'), (1, '-530.730')] -[2023-11-28 09:19:23,483][87424] Updated weights for policy 0, policy_version 347659 (0.0012) -[2023-11-28 09:19:23,864][87424] Updated weights for policy 0, policy_version 347669 (0.0012) -[2023-11-28 09:19:24,259][87424] Updated weights for policy 0, policy_version 347679 (0.0008) -[2023-11-28 09:19:25,426][87426] Updated weights for policy 1, policy_version 347330 (0.0011) -[2023-11-28 09:19:25,811][87426] Updated weights for policy 1, policy_version 347340 (0.0012) -[2023-11-28 09:19:26,198][87426] Updated weights for policy 1, policy_version 347350 (0.0012) -[2023-11-28 09:19:26,234][87424] Updated weights for policy 0, policy_version 347689 (0.0010) -[2023-11-28 09:19:26,577][87426] Updated weights for policy 1, policy_version 347360 (0.0010) -[2023-11-28 09:19:26,613][87424] Updated weights for policy 0, policy_version 347699 (0.0009) -[2023-11-28 09:19:26,995][87424] Updated weights for policy 0, policy_version 347709 (0.0007) -[2023-11-28 09:19:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 177938432. Throughput: 0: 2681.8, 1: 2710.6. Samples: 177954020. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:28,445][86177] Avg episode reward: [(0, '-519.590'), (1, '-577.360')] -[2023-11-28 09:19:28,765][87426] Updated weights for policy 1, policy_version 347370 (0.0009) -[2023-11-28 09:19:28,963][87424] Updated weights for policy 0, policy_version 347719 (0.0008) -[2023-11-28 09:19:29,158][87426] Updated weights for policy 1, policy_version 347380 (0.0011) -[2023-11-28 09:19:29,334][87424] Updated weights for policy 0, policy_version 347729 (0.0009) -[2023-11-28 09:19:29,539][87426] Updated weights for policy 1, policy_version 347390 (0.0012) -[2023-11-28 09:19:29,716][87424] Updated weights for policy 0, policy_version 347739 (0.0007) -[2023-11-28 09:19:31,760][87424] Updated weights for policy 0, policy_version 347749 (0.0011) -[2023-11-28 09:19:31,880][87426] Updated weights for policy 1, policy_version 347400 (0.0012) -[2023-11-28 09:19:32,138][87424] Updated weights for policy 0, policy_version 347759 (0.0016) -[2023-11-28 09:19:32,255][87426] Updated weights for policy 1, policy_version 347410 (0.0011) -[2023-11-28 09:19:32,522][87424] Updated weights for policy 0, policy_version 347769 (0.0011) -[2023-11-28 09:19:32,634][87426] Updated weights for policy 1, policy_version 347420 (0.0008) -[2023-11-28 09:19:33,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 177971200. Throughput: 0: 2734.3, 1: 2675.6. Samples: 177979164. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:33,446][86177] Avg episode reward: [(0, '-536.200'), (1, '-593.040')] -[2023-11-28 09:19:34,882][87424] Updated weights for policy 0, policy_version 347779 (0.0012) -[2023-11-28 09:19:35,162][87426] Updated weights for policy 1, policy_version 347430 (0.0010) -[2023-11-28 09:19:35,260][87424] Updated weights for policy 0, policy_version 347789 (0.0011) -[2023-11-28 09:19:35,546][87426] Updated weights for policy 1, policy_version 347440 (0.0007) -[2023-11-28 09:19:35,639][87424] Updated weights for policy 0, policy_version 347799 (0.0011) -[2023-11-28 09:19:35,918][87426] Updated weights for policy 1, policy_version 347450 (0.0007) -[2023-11-28 09:19:37,789][87424] Updated weights for policy 0, policy_version 347809 (0.0011) -[2023-11-28 09:19:38,016][87426] Updated weights for policy 1, policy_version 347460 (0.0009) -[2023-11-28 09:19:38,169][87424] Updated weights for policy 0, policy_version 347819 (0.0007) -[2023-11-28 09:19:38,394][87426] Updated weights for policy 1, policy_version 347470 (0.0008) -[2023-11-28 09:19:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 177987584. Throughput: 0: 2746.0, 1: 2668.3. Samples: 178010680. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:38,445][86177] Avg episode reward: [(0, '-530.340'), (1, '-596.590')] -[2023-11-28 09:19:38,547][87424] Updated weights for policy 0, policy_version 347829 (0.0008) -[2023-11-28 09:19:38,771][87426] Updated weights for policy 1, policy_version 347480 (0.0007) -[2023-11-28 09:19:38,940][87424] Updated weights for policy 0, policy_version 347839 (0.0008) -[2023-11-28 09:19:40,837][87426] Updated weights for policy 1, policy_version 347490 (0.0010) -[2023-11-28 09:19:41,213][87426] Updated weights for policy 1, policy_version 347500 (0.0011) -[2023-11-28 09:19:41,412][87424] Updated weights for policy 0, policy_version 347849 (0.0009) -[2023-11-28 09:19:41,590][87426] Updated weights for policy 1, policy_version 347510 (0.0011) -[2023-11-28 09:19:41,792][87424] Updated weights for policy 0, policy_version 347859 (0.0015) -[2023-11-28 09:19:41,971][87426] Updated weights for policy 1, policy_version 347520 (0.0012) -[2023-11-28 09:19:42,179][87424] Updated weights for policy 0, policy_version 347869 (0.0011) -[2023-11-28 09:19:43,445][86177] Fps is (10 sec: 4914.8, 60 sec: 5461.2, 300 sec: 5359.5). Total num frames: 178020352. Throughput: 0: 2711.4, 1: 2673.0. Samples: 178034976. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:43,446][86177] Avg episode reward: [(0, '-526.760'), (1, '-597.770')] -[2023-11-28 09:19:44,114][87426] Updated weights for policy 1, policy_version 347530 (0.0011) -[2023-11-28 09:19:44,350][87424] Updated weights for policy 0, policy_version 347879 (0.0012) -[2023-11-28 09:19:44,504][87426] Updated weights for policy 1, policy_version 347540 (0.0009) -[2023-11-28 09:19:44,744][87424] Updated weights for policy 0, policy_version 347889 (0.0011) -[2023-11-28 09:19:44,873][87426] Updated weights for policy 1, policy_version 347550 (0.0011) -[2023-11-28 09:19:45,131][87424] Updated weights for policy 0, policy_version 347899 (0.0011) -[2023-11-28 09:19:47,368][87426] Updated weights for policy 1, policy_version 347560 (0.0012) -[2023-11-28 09:19:47,691][87424] Updated weights for policy 0, policy_version 347909 (0.0012) -[2023-11-28 09:19:47,749][87426] Updated weights for policy 1, policy_version 347570 (0.0011) -[2023-11-28 09:19:48,069][87424] Updated weights for policy 0, policy_version 347919 (0.0008) -[2023-11-28 09:19:48,138][87426] Updated weights for policy 1, policy_version 347580 (0.0012) -[2023-11-28 09:19:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178044928. Throughput: 0: 2696.7, 1: 2660.7. Samples: 178058828. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:48,445][86177] Avg episode reward: [(0, '-531.710'), (1, '-550.900')] -[2023-11-28 09:19:48,447][87424] Updated weights for policy 0, policy_version 347929 (0.0008) -[2023-11-28 09:19:50,256][87424] Updated weights for policy 0, policy_version 347939 (0.0009) -[2023-11-28 09:19:50,640][87424] Updated weights for policy 0, policy_version 347949 (0.0011) -[2023-11-28 09:19:50,650][87426] Updated weights for policy 1, policy_version 347590 (0.0010) -[2023-11-28 09:19:51,017][87424] Updated weights for policy 0, policy_version 347959 (0.0011) -[2023-11-28 09:19:51,026][87426] Updated weights for policy 1, policy_version 347600 (0.0012) -[2023-11-28 09:19:51,403][87426] Updated weights for policy 1, policy_version 347610 (0.0011) -[2023-11-28 09:19:53,254][87424] Updated weights for policy 0, policy_version 347969 (0.0011) -[2023-11-28 09:19:53,444][86177] Fps is (10 sec: 4915.7, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178069504. Throughput: 0: 2682.0, 1: 2620.4. Samples: 178089728. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:53,445][86177] Avg episode reward: [(0, '-514.560'), (1, '-531.350')] -[2023-11-28 09:19:53,634][87424] Updated weights for policy 0, policy_version 347979 (0.0010) -[2023-11-28 09:19:53,847][87426] Updated weights for policy 1, policy_version 347620 (0.0011) -[2023-11-28 09:19:54,017][87424] Updated weights for policy 0, policy_version 347989 (0.0010) -[2023-11-28 09:19:54,222][87426] Updated weights for policy 1, policy_version 347630 (0.0011) -[2023-11-28 09:19:54,404][87424] Updated weights for policy 0, policy_version 347999 (0.0008) -[2023-11-28 09:19:54,601][87426] Updated weights for policy 1, policy_version 347640 (0.0008) -[2023-11-28 09:19:56,459][87426] Updated weights for policy 1, policy_version 347650 (0.0008) -[2023-11-28 09:19:56,648][87424] Updated weights for policy 0, policy_version 348009 (0.0012) -[2023-11-28 09:19:56,830][87426] Updated weights for policy 1, policy_version 347660 (0.0010) -[2023-11-28 09:19:57,032][87424] Updated weights for policy 0, policy_version 348019 (0.0010) -[2023-11-28 09:19:57,205][87426] Updated weights for policy 1, policy_version 347670 (0.0012) -[2023-11-28 09:19:57,413][87424] Updated weights for policy 0, policy_version 348029 (0.0008) -[2023-11-28 09:19:57,577][87426] Updated weights for policy 1, policy_version 347680 (0.0012) -[2023-11-28 09:19:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 178102272. Throughput: 0: 2680.0, 1: 2622.3. Samples: 178113768. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:19:58,445][86177] Avg episode reward: [(0, '-514.030'), (1, '-540.940')] -[2023-11-28 09:19:59,407][87426] Updated weights for policy 1, policy_version 347690 (0.0012) -[2023-11-28 09:19:59,754][87424] Updated weights for policy 0, policy_version 348039 (0.0011) -[2023-11-28 09:19:59,794][87426] Updated weights for policy 1, policy_version 347700 (0.0012) -[2023-11-28 09:20:00,139][87424] Updated weights for policy 0, policy_version 348049 (0.0011) -[2023-11-28 09:20:00,171][87426] Updated weights for policy 1, policy_version 347710 (0.0011) -[2023-11-28 09:20:00,514][87424] Updated weights for policy 0, policy_version 348059 (0.0012) -[2023-11-28 09:20:02,548][87424] Updated weights for policy 0, policy_version 348069 (0.0010) -[2023-11-28 09:20:02,673][87426] Updated weights for policy 1, policy_version 347720 (0.0011) -[2023-11-28 09:20:02,940][87424] Updated weights for policy 0, policy_version 348079 (0.0009) -[2023-11-28 09:20:03,050][87426] Updated weights for policy 1, policy_version 347730 (0.0011) -[2023-11-28 09:20:03,321][87424] Updated weights for policy 0, policy_version 348089 (0.0010) -[2023-11-28 09:20:03,421][87426] Updated weights for policy 1, policy_version 347740 (0.0011) -[2023-11-28 09:20:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 178118656. Throughput: 0: 2724.2, 1: 2636.2. Samples: 178139104. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:20:03,445][86177] Avg episode reward: [(0, '-533.250'), (1, '-542.420')] -[2023-11-28 09:20:05,398][87426] Updated weights for policy 1, policy_version 347750 (0.0012) -[2023-11-28 09:20:05,783][87426] Updated weights for policy 1, policy_version 347760 (0.0012) -[2023-11-28 09:20:05,875][87424] Updated weights for policy 0, policy_version 348099 (0.0008) -[2023-11-28 09:20:06,166][87426] Updated weights for policy 1, policy_version 347770 (0.0011) -[2023-11-28 09:20:06,255][87424] Updated weights for policy 0, policy_version 348109 (0.0007) -[2023-11-28 09:20:06,643][87424] Updated weights for policy 0, policy_version 348119 (0.0008) -[2023-11-28 09:20:08,386][87426] Updated weights for policy 1, policy_version 347780 (0.0011) -[2023-11-28 09:20:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178151424. Throughput: 0: 2707.9, 1: 2670.2. Samples: 178171072. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:20:08,445][86177] Avg episode reward: [(0, '-532.370'), (1, '-557.910')] -[2023-11-28 09:20:08,755][87426] Updated weights for policy 1, policy_version 347790 (0.0012) -[2023-11-28 09:20:09,004][87424] Updated weights for policy 0, policy_version 348129 (0.0009) -[2023-11-28 09:20:09,129][87426] Updated weights for policy 1, policy_version 347800 (0.0011) -[2023-11-28 09:20:09,384][87424] Updated weights for policy 0, policy_version 348139 (0.0011) -[2023-11-28 09:20:09,768][87424] Updated weights for policy 0, policy_version 348149 (0.0012) -[2023-11-28 09:20:10,149][87424] Updated weights for policy 0, policy_version 348159 (0.0012) -[2023-11-28 09:20:11,218][87426] Updated weights for policy 1, policy_version 347810 (0.0011) -[2023-11-28 09:20:11,592][87426] Updated weights for policy 1, policy_version 347820 (0.0011) -[2023-11-28 09:20:11,977][87426] Updated weights for policy 1, policy_version 347830 (0.0011) -[2023-11-28 09:20:12,326][87424] Updated weights for policy 0, policy_version 348169 (0.0011) -[2023-11-28 09:20:12,362][87426] Updated weights for policy 1, policy_version 347840 (0.0012) -[2023-11-28 09:20:12,696][87424] Updated weights for policy 0, policy_version 348179 (0.0011) -[2023-11-28 09:20:13,078][87424] Updated weights for policy 0, policy_version 348189 (0.0012) -[2023-11-28 09:20:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 178184192. Throughput: 0: 2698.7, 1: 2670.0. Samples: 178195608. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:20:13,445][86177] Avg episode reward: [(0, '-536.710'), (1, '-561.860')] -[2023-11-28 09:20:14,416][87426] Updated weights for policy 1, policy_version 347850 (0.0012) -[2023-11-28 09:20:14,795][87426] Updated weights for policy 1, policy_version 347860 (0.0012) -[2023-11-28 09:20:15,173][87426] Updated weights for policy 1, policy_version 347870 (0.0011) -[2023-11-28 09:20:15,437][87424] Updated weights for policy 0, policy_version 348199 (0.0012) -[2023-11-28 09:20:15,815][87424] Updated weights for policy 0, policy_version 348209 (0.0012) -[2023-11-28 09:20:16,196][87424] Updated weights for policy 0, policy_version 348219 (0.0012) -[2023-11-28 09:20:17,395][87426] Updated weights for policy 1, policy_version 347880 (0.0008) -[2023-11-28 09:20:17,774][87426] Updated weights for policy 1, policy_version 347890 (0.0011) -[2023-11-28 09:20:18,159][87426] Updated weights for policy 1, policy_version 347900 (0.0012) -[2023-11-28 09:20:18,196][87424] Updated weights for policy 0, policy_version 348229 (0.0010) -[2023-11-28 09:20:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178208768. Throughput: 0: 2660.6, 1: 2682.0. Samples: 178219580. Policy #0 lag: (min: 31.0, avg: 38.6, max: 63.0) -[2023-11-28 09:20:18,445][86177] Avg episode reward: [(0, '-535.650'), (1, '-599.120')] -[2023-11-28 09:20:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000347904_89063424.pth... -[2023-11-28 09:20:18,484][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000345376_88416256.pth -[2023-11-28 09:20:18,579][87424] Updated weights for policy 0, policy_version 348239 (0.0012) -[2023-11-28 09:20:18,968][87424] Updated weights for policy 0, policy_version 348249 (0.0012) -[2023-11-28 09:20:19,228][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000348256_89153536.pth... -[2023-11-28 09:20:19,259][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000345728_88506368.pth -[2023-11-28 09:20:20,233][87426] Updated weights for policy 1, policy_version 347910 (0.0012) -[2023-11-28 09:20:20,614][87426] Updated weights for policy 1, policy_version 347920 (0.0010) -[2023-11-28 09:20:21,001][87426] Updated weights for policy 1, policy_version 347930 (0.0008) -[2023-11-28 09:20:21,518][87424] Updated weights for policy 0, policy_version 348259 (0.0012) -[2023-11-28 09:20:21,916][87424] Updated weights for policy 0, policy_version 348269 (0.0011) -[2023-11-28 09:20:22,294][87424] Updated weights for policy 0, policy_version 348279 (0.0014) -[2023-11-28 09:20:23,274][87426] Updated weights for policy 1, policy_version 347940 (0.0011) -[2023-11-28 09:20:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 178233344. Throughput: 0: 2632.2, 1: 2701.8. Samples: 178250708. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:20:23,445][86177] Avg episode reward: [(0, '-526.300'), (1, '-597.140')] -[2023-11-28 09:20:23,649][87426] Updated weights for policy 1, policy_version 347950 (0.0012) -[2023-11-28 09:20:24,030][87426] Updated weights for policy 1, policy_version 347960 (0.0013) -[2023-11-28 09:20:24,387][87424] Updated weights for policy 0, policy_version 348289 (0.0010) -[2023-11-28 09:20:24,767][87424] Updated weights for policy 0, policy_version 348299 (0.0007) -[2023-11-28 09:20:25,155][87424] Updated weights for policy 0, policy_version 348309 (0.0008) -[2023-11-28 09:20:25,525][87424] Updated weights for policy 0, policy_version 348319 (0.0008) -[2023-11-28 09:20:26,449][87426] Updated weights for policy 1, policy_version 347970 (0.0009) -[2023-11-28 09:20:26,823][87426] Updated weights for policy 1, policy_version 347980 (0.0012) -[2023-11-28 09:20:27,198][87426] Updated weights for policy 1, policy_version 347990 (0.0012) -[2023-11-28 09:20:27,587][87426] Updated weights for policy 1, policy_version 348000 (0.0012) -[2023-11-28 09:20:27,831][87424] Updated weights for policy 0, policy_version 348329 (0.0012) -[2023-11-28 09:20:28,209][87424] Updated weights for policy 0, policy_version 348339 (0.0012) -[2023-11-28 09:20:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178257920. Throughput: 0: 2652.1, 1: 2710.5. Samples: 178276288. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:20:28,445][86177] Avg episode reward: [(0, '-518.180'), (1, '-598.480')] -[2023-11-28 09:20:28,603][87424] Updated weights for policy 0, policy_version 348349 (0.0012) -[2023-11-28 09:20:29,251][87426] Updated weights for policy 1, policy_version 348010 (0.0010) -[2023-11-28 09:20:29,628][87426] Updated weights for policy 1, policy_version 348020 (0.0011) -[2023-11-28 09:20:30,011][87426] Updated weights for policy 1, policy_version 348030 (0.0010) -[2023-11-28 09:20:30,829][87424] Updated weights for policy 0, policy_version 348359 (0.0012) -[2023-11-28 09:20:31,206][87424] Updated weights for policy 0, policy_version 348369 (0.0011) -[2023-11-28 09:20:31,585][87424] Updated weights for policy 0, policy_version 348379 (0.0012) -[2023-11-28 09:20:32,357][87426] Updated weights for policy 1, policy_version 348040 (0.0010) -[2023-11-28 09:20:32,742][87426] Updated weights for policy 1, policy_version 348050 (0.0010) -[2023-11-28 09:20:33,128][87426] Updated weights for policy 1, policy_version 348060 (0.0009) -[2023-11-28 09:20:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178290688. Throughput: 0: 2632.4, 1: 2733.9. Samples: 178300308. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:20:33,445][86177] Avg episode reward: [(0, '-524.200'), (1, '-595.930')] -[2023-11-28 09:20:34,034][87424] Updated weights for policy 0, policy_version 348389 (0.0010) -[2023-11-28 09:20:34,412][87424] Updated weights for policy 0, policy_version 348399 (0.0009) -[2023-11-28 09:20:34,800][87424] Updated weights for policy 0, policy_version 348409 (0.0008) -[2023-11-28 09:20:34,832][87426] Updated weights for policy 1, policy_version 348070 (0.0009) -[2023-11-28 09:20:35,211][87426] Updated weights for policy 1, policy_version 348080 (0.0011) -[2023-11-28 09:20:35,589][87426] Updated weights for policy 1, policy_version 348090 (0.0009) -[2023-11-28 09:20:37,236][87424] Updated weights for policy 0, policy_version 348419 (0.0008) -[2023-11-28 09:20:37,622][87424] Updated weights for policy 0, policy_version 348429 (0.0011) -[2023-11-28 09:20:37,983][87426] Updated weights for policy 1, policy_version 348100 (0.0009) -[2023-11-28 09:20:38,006][87424] Updated weights for policy 0, policy_version 348439 (0.0012) -[2023-11-28 09:20:38,365][87426] Updated weights for policy 1, policy_version 348110 (0.0007) -[2023-11-28 09:20:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 178315264. Throughput: 0: 2617.0, 1: 2752.5. Samples: 178331356. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:20:38,445][86177] Avg episode reward: [(0, '-530.910'), (1, '-611.500')] -[2023-11-28 09:20:38,745][87426] Updated weights for policy 1, policy_version 348120 (0.0007) -[2023-11-28 09:20:40,634][87424] Updated weights for policy 0, policy_version 348449 (0.0011) -[2023-11-28 09:20:41,010][87424] Updated weights for policy 0, policy_version 348459 (0.0012) -[2023-11-28 09:20:41,268][87426] Updated weights for policy 1, policy_version 348130 (0.0009) -[2023-11-28 09:20:41,386][87424] Updated weights for policy 0, policy_version 348469 (0.0010) -[2023-11-28 09:20:41,636][87426] Updated weights for policy 1, policy_version 348140 (0.0012) -[2023-11-28 09:20:41,765][87424] Updated weights for policy 0, policy_version 348479 (0.0010) -[2023-11-28 09:20:42,017][87426] Updated weights for policy 1, policy_version 348150 (0.0012) -[2023-11-28 09:20:42,390][87426] Updated weights for policy 1, policy_version 348160 (0.0011) -[2023-11-28 09:20:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.9, 300 sec: 5359.5). Total num frames: 178339840. Throughput: 0: 2600.7, 1: 2752.8. Samples: 178354676. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:20:43,445][86177] Avg episode reward: [(0, '-524.110'), (1, '-624.770')] -[2023-11-28 09:20:44,035][87424] Updated weights for policy 0, policy_version 348489 (0.0012) -[2023-11-28 09:20:44,406][87426] Updated weights for policy 1, policy_version 348170 (0.0011) -[2023-11-28 09:20:44,426][87424] Updated weights for policy 0, policy_version 348499 (0.0012) -[2023-11-28 09:20:44,783][87426] Updated weights for policy 1, policy_version 348180 (0.0011) -[2023-11-28 09:20:44,798][87424] Updated weights for policy 0, policy_version 348509 (0.0012) -[2023-11-28 09:20:45,160][87426] Updated weights for policy 1, policy_version 348190 (0.0012) -[2023-11-28 09:20:46,935][87424] Updated weights for policy 0, policy_version 348519 (0.0012) -[2023-11-28 09:20:47,022][87426] Updated weights for policy 1, policy_version 348200 (0.0010) -[2023-11-28 09:20:47,317][87424] Updated weights for policy 0, policy_version 348529 (0.0009) -[2023-11-28 09:20:47,402][87426] Updated weights for policy 1, policy_version 348210 (0.0009) -[2023-11-28 09:20:47,700][87424] Updated weights for policy 0, policy_version 348539 (0.0007) -[2023-11-28 09:20:47,786][87426] Updated weights for policy 1, policy_version 348220 (0.0008) -[2023-11-28 09:20:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 178372608. Throughput: 0: 2583.0, 1: 2753.0. Samples: 178379224. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:20:48,445][86177] Avg episode reward: [(0, '-523.610'), (1, '-619.480')] -[2023-11-28 09:20:49,980][87424] Updated weights for policy 0, policy_version 348549 (0.0009) -[2023-11-28 09:20:50,155][87426] Updated weights for policy 1, policy_version 348230 (0.0008) -[2023-11-28 09:20:50,354][87424] Updated weights for policy 0, policy_version 348559 (0.0008) -[2023-11-28 09:20:50,528][87426] Updated weights for policy 1, policy_version 348240 (0.0009) -[2023-11-28 09:20:50,737][87424] Updated weights for policy 0, policy_version 348569 (0.0011) -[2023-11-28 09:20:50,909][87426] Updated weights for policy 1, policy_version 348250 (0.0008) -[2023-11-28 09:20:53,169][87424] Updated weights for policy 0, policy_version 348579 (0.0011) -[2023-11-28 09:20:53,258][87426] Updated weights for policy 1, policy_version 348260 (0.0009) -[2023-11-28 09:20:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 178388992. Throughput: 0: 2581.9, 1: 2736.1. Samples: 178410380. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:20:53,445][86177] Avg episode reward: [(0, '-514.140'), (1, '-621.990')] -[2023-11-28 09:20:53,541][87424] Updated weights for policy 0, policy_version 348589 (0.0011) -[2023-11-28 09:20:53,634][87426] Updated weights for policy 1, policy_version 348270 (0.0010) -[2023-11-28 09:20:53,925][87424] Updated weights for policy 0, policy_version 348599 (0.0011) -[2023-11-28 09:20:54,012][87426] Updated weights for policy 1, policy_version 348280 (0.0011) -[2023-11-28 09:20:55,855][87424] Updated weights for policy 0, policy_version 348609 (0.0011) -[2023-11-28 09:20:56,216][87426] Updated weights for policy 1, policy_version 348290 (0.0012) -[2023-11-28 09:20:56,229][87424] Updated weights for policy 0, policy_version 348619 (0.0012) -[2023-11-28 09:20:56,596][87426] Updated weights for policy 1, policy_version 348300 (0.0009) -[2023-11-28 09:20:56,609][87424] Updated weights for policy 0, policy_version 348629 (0.0012) -[2023-11-28 09:20:56,982][87426] Updated weights for policy 1, policy_version 348310 (0.0010) -[2023-11-28 09:20:56,993][87424] Updated weights for policy 0, policy_version 348639 (0.0012) -[2023-11-28 09:20:57,354][87426] Updated weights for policy 1, policy_version 348320 (0.0011) -[2023-11-28 09:20:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178421760. Throughput: 0: 2596.1, 1: 2731.3. Samples: 178435340. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:20:58,445][86177] Avg episode reward: [(0, '-549.350'), (1, '-582.340')] -[2023-11-28 09:20:58,673][87424] Updated weights for policy 0, policy_version 348649 (0.0012) -[2023-11-28 09:20:59,053][87424] Updated weights for policy 0, policy_version 348659 (0.0015) -[2023-11-28 09:20:59,422][87426] Updated weights for policy 1, policy_version 348330 (0.0009) -[2023-11-28 09:20:59,431][87424] Updated weights for policy 0, policy_version 348669 (0.0010) -[2023-11-28 09:20:59,812][87426] Updated weights for policy 1, policy_version 348340 (0.0011) -[2023-11-28 09:21:00,191][87426] Updated weights for policy 1, policy_version 348350 (0.0009) -[2023-11-28 09:21:01,647][87424] Updated weights for policy 0, policy_version 348679 (0.0010) -[2023-11-28 09:21:02,035][87424] Updated weights for policy 0, policy_version 348689 (0.0016) -[2023-11-28 09:21:02,404][87424] Updated weights for policy 0, policy_version 348699 (0.0009) -[2023-11-28 09:21:02,599][87426] Updated weights for policy 1, policy_version 348360 (0.0011) -[2023-11-28 09:21:02,986][87426] Updated weights for policy 1, policy_version 348370 (0.0012) -[2023-11-28 09:21:03,354][87426] Updated weights for policy 1, policy_version 348380 (0.0012) -[2023-11-28 09:21:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 178446336. Throughput: 0: 2619.6, 1: 2737.5. Samples: 178460648. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:21:03,445][86177] Avg episode reward: [(0, '-568.850'), (1, '-566.890')] -[2023-11-28 09:21:04,507][87424] Updated weights for policy 0, policy_version 348709 (0.0009) -[2023-11-28 09:21:04,887][87424] Updated weights for policy 0, policy_version 348719 (0.0011) -[2023-11-28 09:21:05,269][87424] Updated weights for policy 0, policy_version 348729 (0.0011) -[2023-11-28 09:21:05,509][87426] Updated weights for policy 1, policy_version 348390 (0.0010) -[2023-11-28 09:21:05,887][87426] Updated weights for policy 1, policy_version 348400 (0.0008) -[2023-11-28 09:21:06,274][87426] Updated weights for policy 1, policy_version 348410 (0.0011) -[2023-11-28 09:21:07,566][87424] Updated weights for policy 0, policy_version 348739 (0.0010) -[2023-11-28 09:21:07,937][87424] Updated weights for policy 0, policy_version 348749 (0.0012) -[2023-11-28 09:21:08,327][87424] Updated weights for policy 0, policy_version 348759 (0.0011) -[2023-11-28 09:21:08,354][87426] Updated weights for policy 1, policy_version 348420 (0.0009) -[2023-11-28 09:21:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178470912. Throughput: 0: 2651.0, 1: 2744.0. Samples: 178493484. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:21:08,445][86177] Avg episode reward: [(0, '-566.630'), (1, '-557.210')] -[2023-11-28 09:21:08,732][87426] Updated weights for policy 1, policy_version 348430 (0.0007) -[2023-11-28 09:21:09,108][87426] Updated weights for policy 1, policy_version 348440 (0.0011) -[2023-11-28 09:21:10,667][87424] Updated weights for policy 0, policy_version 348769 (0.0011) -[2023-11-28 09:21:11,054][87424] Updated weights for policy 0, policy_version 348779 (0.0012) -[2023-11-28 09:21:11,410][87426] Updated weights for policy 1, policy_version 348450 (0.0011) -[2023-11-28 09:21:11,425][87424] Updated weights for policy 0, policy_version 348789 (0.0010) -[2023-11-28 09:21:11,788][87426] Updated weights for policy 1, policy_version 348460 (0.0010) -[2023-11-28 09:21:11,814][87424] Updated weights for policy 0, policy_version 348799 (0.0009) -[2023-11-28 09:21:12,177][87426] Updated weights for policy 1, policy_version 348470 (0.0009) -[2023-11-28 09:21:12,548][87426] Updated weights for policy 1, policy_version 348480 (0.0011) -[2023-11-28 09:21:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 178503680. Throughput: 0: 2635.2, 1: 2712.3. Samples: 178516924. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:21:13,445][86177] Avg episode reward: [(0, '-558.060'), (1, '-582.360')] -[2023-11-28 09:21:13,881][87424] Updated weights for policy 0, policy_version 348809 (0.0012) -[2023-11-28 09:21:14,257][87424] Updated weights for policy 0, policy_version 348819 (0.0011) -[2023-11-28 09:21:14,639][87424] Updated weights for policy 0, policy_version 348829 (0.0011) -[2023-11-28 09:21:15,128][87426] Updated weights for policy 1, policy_version 348490 (0.0008) -[2023-11-28 09:21:15,504][87426] Updated weights for policy 1, policy_version 348500 (0.0010) -[2023-11-28 09:21:15,883][87426] Updated weights for policy 1, policy_version 348510 (0.0008) -[2023-11-28 09:21:17,020][87424] Updated weights for policy 0, policy_version 348839 (0.0012) -[2023-11-28 09:21:17,392][87424] Updated weights for policy 0, policy_version 348849 (0.0012) -[2023-11-28 09:21:17,769][87424] Updated weights for policy 0, policy_version 348859 (0.0010) -[2023-11-28 09:21:17,848][87426] Updated weights for policy 1, policy_version 348520 (0.0007) -[2023-11-28 09:21:18,227][87426] Updated weights for policy 1, policy_version 348530 (0.0007) -[2023-11-28 09:21:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178528256. Throughput: 0: 2660.6, 1: 2691.7. Samples: 178541164. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:21:18,445][86177] Avg episode reward: [(0, '-526.080'), (1, '-575.000')] -[2023-11-28 09:21:18,607][87426] Updated weights for policy 1, policy_version 348540 (0.0009) -[2023-11-28 09:21:19,873][87424] Updated weights for policy 0, policy_version 348869 (0.0009) -[2023-11-28 09:21:20,255][87424] Updated weights for policy 0, policy_version 348879 (0.0011) -[2023-11-28 09:21:20,635][87424] Updated weights for policy 0, policy_version 348889 (0.0010) -[2023-11-28 09:21:20,857][87426] Updated weights for policy 1, policy_version 348550 (0.0010) -[2023-11-28 09:21:21,236][87426] Updated weights for policy 1, policy_version 348560 (0.0011) -[2023-11-28 09:21:21,615][87426] Updated weights for policy 1, policy_version 348570 (0.0009) -[2023-11-28 09:21:23,051][87424] Updated weights for policy 0, policy_version 348899 (0.0008) -[2023-11-28 09:21:23,442][87424] Updated weights for policy 0, policy_version 348909 (0.0011) -[2023-11-28 09:21:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178552832. Throughput: 0: 2667.8, 1: 2689.4. Samples: 178572432. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:21:23,446][86177] Avg episode reward: [(0, '-511.790'), (1, '-564.720')] -[2023-11-28 09:21:23,824][87424] Updated weights for policy 0, policy_version 348919 (0.0008) -[2023-11-28 09:21:23,963][87426] Updated weights for policy 1, policy_version 348580 (0.0011) -[2023-11-28 09:21:24,340][87426] Updated weights for policy 1, policy_version 348590 (0.0011) -[2023-11-28 09:21:24,715][87426] Updated weights for policy 1, policy_version 348600 (0.0009) -[2023-11-28 09:21:26,064][87424] Updated weights for policy 0, policy_version 348929 (0.0008) -[2023-11-28 09:21:26,440][87424] Updated weights for policy 0, policy_version 348939 (0.0008) -[2023-11-28 09:21:26,548][87426] Updated weights for policy 1, policy_version 348610 (0.0009) -[2023-11-28 09:21:26,824][87424] Updated weights for policy 0, policy_version 348949 (0.0011) -[2023-11-28 09:21:26,920][87426] Updated weights for policy 1, policy_version 348620 (0.0010) -[2023-11-28 09:21:27,215][87424] Updated weights for policy 0, policy_version 348959 (0.0009) -[2023-11-28 09:21:27,294][87426] Updated weights for policy 1, policy_version 348630 (0.0008) -[2023-11-28 09:21:27,665][87426] Updated weights for policy 1, policy_version 348640 (0.0007) -[2023-11-28 09:21:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 178585600. Throughput: 0: 2677.5, 1: 2691.4. Samples: 178596276. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:21:28,445][86177] Avg episode reward: [(0, '-519.530'), (1, '-569.410')] -[2023-11-28 09:21:29,736][87424] Updated weights for policy 0, policy_version 348969 (0.0011) -[2023-11-28 09:21:30,022][87426] Updated weights for policy 1, policy_version 348650 (0.0010) -[2023-11-28 09:21:30,118][87424] Updated weights for policy 0, policy_version 348979 (0.0011) -[2023-11-28 09:21:30,405][87426] Updated weights for policy 1, policy_version 348660 (0.0010) -[2023-11-28 09:21:30,498][87424] Updated weights for policy 0, policy_version 348989 (0.0016) -[2023-11-28 09:21:30,776][87426] Updated weights for policy 1, policy_version 348670 (0.0010) -[2023-11-28 09:21:32,702][87424] Updated weights for policy 0, policy_version 348999 (0.0012) -[2023-11-28 09:21:33,084][87424] Updated weights for policy 0, policy_version 349009 (0.0011) -[2023-11-28 09:21:33,215][87426] Updated weights for policy 1, policy_version 348680 (0.0008) -[2023-11-28 09:21:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 178601984. Throughput: 0: 2660.9, 1: 2675.9. Samples: 178619380. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:21:33,445][86177] Avg episode reward: [(0, '-531.430'), (1, '-531.750')] -[2023-11-28 09:21:33,456][87424] Updated weights for policy 0, policy_version 349019 (0.0011) -[2023-11-28 09:21:33,612][87426] Updated weights for policy 1, policy_version 348690 (0.0008) -[2023-11-28 09:21:33,997][87426] Updated weights for policy 1, policy_version 348700 (0.0011) -[2023-11-28 09:21:35,813][87424] Updated weights for policy 0, policy_version 349029 (0.0012) -[2023-11-28 09:21:36,186][87424] Updated weights for policy 0, policy_version 349039 (0.0012) -[2023-11-28 09:21:36,240][87426] Updated weights for policy 1, policy_version 348710 (0.0010) -[2023-11-28 09:21:36,574][87424] Updated weights for policy 0, policy_version 349049 (0.0012) -[2023-11-28 09:21:36,613][87426] Updated weights for policy 1, policy_version 348720 (0.0010) -[2023-11-28 09:21:37,019][87426] Updated weights for policy 1, policy_version 348730 (0.0010) -[2023-11-28 09:21:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178634752. Throughput: 0: 2671.0, 1: 2673.6. Samples: 178650888. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:21:38,445][86177] Avg episode reward: [(0, '-532.600'), (1, '-520.400')] -[2023-11-28 09:21:39,051][87426] Updated weights for policy 1, policy_version 348740 (0.0010) -[2023-11-28 09:21:39,200][87424] Updated weights for policy 0, policy_version 349059 (0.0011) -[2023-11-28 09:21:39,425][87426] Updated weights for policy 1, policy_version 348750 (0.0010) -[2023-11-28 09:21:39,588][87424] Updated weights for policy 0, policy_version 349069 (0.0010) -[2023-11-28 09:21:39,805][87426] Updated weights for policy 1, policy_version 348760 (0.0011) -[2023-11-28 09:21:39,971][87424] Updated weights for policy 0, policy_version 349079 (0.0012) -[2023-11-28 09:21:41,971][87426] Updated weights for policy 1, policy_version 348770 (0.0010) -[2023-11-28 09:21:42,344][87426] Updated weights for policy 1, policy_version 348780 (0.0012) -[2023-11-28 09:21:42,662][87424] Updated weights for policy 0, policy_version 349089 (0.0011) -[2023-11-28 09:21:42,721][87426] Updated weights for policy 1, policy_version 348790 (0.0011) -[2023-11-28 09:21:43,040][87424] Updated weights for policy 0, policy_version 349099 (0.0012) -[2023-11-28 09:21:43,095][87426] Updated weights for policy 1, policy_version 348800 (0.0011) -[2023-11-28 09:21:43,430][87424] Updated weights for policy 0, policy_version 349109 (0.0008) -[2023-11-28 09:21:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178659328. Throughput: 0: 2639.3, 1: 2661.1. Samples: 178673856. Policy #0 lag: (min: 31.0, avg: 55.8, max: 95.0) -[2023-11-28 09:21:43,445][86177] Avg episode reward: [(0, '-531.040'), (1, '-532.330')] -[2023-11-28 09:21:43,802][87424] Updated weights for policy 0, policy_version 349119 (0.0011) -[2023-11-28 09:21:45,523][87426] Updated weights for policy 1, policy_version 348810 (0.0011) -[2023-11-28 09:21:45,652][87424] Updated weights for policy 0, policy_version 349129 (0.0012) -[2023-11-28 09:21:45,900][87426] Updated weights for policy 1, policy_version 348820 (0.0011) -[2023-11-28 09:21:46,034][87424] Updated weights for policy 0, policy_version 349139 (0.0011) -[2023-11-28 09:21:46,278][87426] Updated weights for policy 1, policy_version 348830 (0.0011) -[2023-11-28 09:21:46,419][87424] Updated weights for policy 0, policy_version 349149 (0.0010) -[2023-11-28 09:21:48,288][87426] Updated weights for policy 1, policy_version 348840 (0.0009) -[2023-11-28 09:21:48,305][87424] Updated weights for policy 0, policy_version 349159 (0.0008) -[2023-11-28 09:21:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 178683904. Throughput: 0: 2608.1, 1: 2645.5. Samples: 178697060. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:21:48,445][86177] Avg episode reward: [(0, '-531.270'), (1, '-529.620')] -[2023-11-28 09:21:48,676][87426] Updated weights for policy 1, policy_version 348850 (0.0012) -[2023-11-28 09:21:48,680][87424] Updated weights for policy 0, policy_version 349169 (0.0009) -[2023-11-28 09:21:49,048][87426] Updated weights for policy 1, policy_version 348860 (0.0011) -[2023-11-28 09:21:49,062][87424] Updated weights for policy 0, policy_version 349179 (0.0011) -[2023-11-28 09:21:51,431][87424] Updated weights for policy 0, policy_version 349189 (0.0010) -[2023-11-28 09:21:51,645][87426] Updated weights for policy 1, policy_version 348870 (0.0011) -[2023-11-28 09:21:51,812][87424] Updated weights for policy 0, policy_version 349199 (0.0013) -[2023-11-28 09:21:52,021][87426] Updated weights for policy 1, policy_version 348880 (0.0010) -[2023-11-28 09:21:52,197][87424] Updated weights for policy 0, policy_version 349209 (0.0011) -[2023-11-28 09:21:52,400][87426] Updated weights for policy 1, policy_version 348890 (0.0011) -[2023-11-28 09:21:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 178716672. Throughput: 0: 2620.4, 1: 2634.8. Samples: 178729968. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:21:53,445][86177] Avg episode reward: [(0, '-525.210'), (1, '-516.600')] -[2023-11-28 09:21:54,448][87424] Updated weights for policy 0, policy_version 349219 (0.0011) -[2023-11-28 09:21:54,650][87426] Updated weights for policy 1, policy_version 348900 (0.0009) -[2023-11-28 09:21:54,829][87424] Updated weights for policy 0, policy_version 349229 (0.0012) -[2023-11-28 09:21:55,023][87426] Updated weights for policy 1, policy_version 348910 (0.0010) -[2023-11-28 09:21:55,211][87424] Updated weights for policy 0, policy_version 349239 (0.0010) -[2023-11-28 09:21:55,408][87426] Updated weights for policy 1, policy_version 348920 (0.0012) -[2023-11-28 09:21:57,205][87424] Updated weights for policy 0, policy_version 349249 (0.0011) -[2023-11-28 09:21:57,428][87426] Updated weights for policy 1, policy_version 348930 (0.0011) -[2023-11-28 09:21:57,583][87424] Updated weights for policy 0, policy_version 349259 (0.0012) -[2023-11-28 09:21:57,805][87426] Updated weights for policy 1, policy_version 348940 (0.0011) -[2023-11-28 09:21:57,965][87424] Updated weights for policy 0, policy_version 349269 (0.0007) -[2023-11-28 09:21:58,171][87426] Updated weights for policy 1, policy_version 348950 (0.0010) -[2023-11-28 09:21:58,346][87424] Updated weights for policy 0, policy_version 349279 (0.0007) -[2023-11-28 09:21:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178741248. Throughput: 0: 2625.0, 1: 2660.6. Samples: 178754776. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:21:58,445][86177] Avg episode reward: [(0, '-523.520'), (1, '-526.120')] -[2023-11-28 09:21:58,550][87426] Updated weights for policy 1, policy_version 348960 (0.0011) -[2023-11-28 09:22:00,139][87424] Updated weights for policy 0, policy_version 349289 (0.0011) -[2023-11-28 09:22:00,513][87424] Updated weights for policy 0, policy_version 349299 (0.0012) -[2023-11-28 09:22:00,897][87424] Updated weights for policy 0, policy_version 349309 (0.0011) -[2023-11-28 09:22:01,199][87426] Updated weights for policy 1, policy_version 348970 (0.0008) -[2023-11-28 09:22:01,584][87426] Updated weights for policy 1, policy_version 348980 (0.0008) -[2023-11-28 09:22:01,968][87426] Updated weights for policy 1, policy_version 348990 (0.0009) -[2023-11-28 09:22:03,344][87424] Updated weights for policy 0, policy_version 349319 (0.0011) -[2023-11-28 09:22:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178765824. Throughput: 0: 2643.6, 1: 2664.2. Samples: 178780012. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:03,445][86177] Avg episode reward: [(0, '-531.770'), (1, '-519.510')] -[2023-11-28 09:22:03,726][87424] Updated weights for policy 0, policy_version 349329 (0.0012) -[2023-11-28 09:22:04,112][87424] Updated weights for policy 0, policy_version 349339 (0.0012) -[2023-11-28 09:22:04,396][87426] Updated weights for policy 1, policy_version 349000 (0.0009) -[2023-11-28 09:22:04,770][87426] Updated weights for policy 1, policy_version 349010 (0.0011) -[2023-11-28 09:22:05,156][87426] Updated weights for policy 1, policy_version 349020 (0.0011) -[2023-11-28 09:22:06,357][87424] Updated weights for policy 0, policy_version 349349 (0.0011) -[2023-11-28 09:22:06,743][87424] Updated weights for policy 0, policy_version 349359 (0.0011) -[2023-11-28 09:22:06,825][87426] Updated weights for policy 1, policy_version 349030 (0.0010) -[2023-11-28 09:22:07,126][87424] Updated weights for policy 0, policy_version 349369 (0.0012) -[2023-11-28 09:22:07,196][87426] Updated weights for policy 1, policy_version 349040 (0.0011) -[2023-11-28 09:22:07,581][87426] Updated weights for policy 1, policy_version 349050 (0.0011) -[2023-11-28 09:22:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 178798592. Throughput: 0: 2640.4, 1: 2674.8. Samples: 178811612. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:08,445][86177] Avg episode reward: [(0, '-537.350'), (1, '-520.310')] -[2023-11-28 09:22:09,611][87424] Updated weights for policy 0, policy_version 349379 (0.0009) -[2023-11-28 09:22:09,636][87426] Updated weights for policy 1, policy_version 349060 (0.0008) -[2023-11-28 09:22:09,985][87424] Updated weights for policy 0, policy_version 349389 (0.0010) -[2023-11-28 09:22:10,015][87426] Updated weights for policy 1, policy_version 349070 (0.0011) -[2023-11-28 09:22:10,367][87424] Updated weights for policy 0, policy_version 349399 (0.0010) -[2023-11-28 09:22:10,383][87426] Updated weights for policy 1, policy_version 349080 (0.0011) -[2023-11-28 09:22:12,347][87424] Updated weights for policy 0, policy_version 349409 (0.0009) -[2023-11-28 09:22:12,509][87426] Updated weights for policy 1, policy_version 349090 (0.0012) -[2023-11-28 09:22:12,732][87424] Updated weights for policy 0, policy_version 349419 (0.0012) -[2023-11-28 09:22:12,891][87426] Updated weights for policy 1, policy_version 349100 (0.0010) -[2023-11-28 09:22:13,100][87424] Updated weights for policy 0, policy_version 349429 (0.0011) -[2023-11-28 09:22:13,262][87426] Updated weights for policy 1, policy_version 349110 (0.0010) -[2023-11-28 09:22:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 178814976. Throughput: 0: 2644.8, 1: 2671.8. Samples: 178835524. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:13,445][86177] Avg episode reward: [(0, '-530.230'), (1, '-563.110')] -[2023-11-28 09:22:13,489][87424] Updated weights for policy 0, policy_version 349439 (0.0009) -[2023-11-28 09:22:13,636][87426] Updated weights for policy 1, policy_version 349120 (0.0011) -[2023-11-28 09:22:15,329][87424] Updated weights for policy 0, policy_version 349449 (0.0012) -[2023-11-28 09:22:15,693][87424] Updated weights for policy 0, policy_version 349459 (0.0011) -[2023-11-28 09:22:15,910][87426] Updated weights for policy 1, policy_version 349130 (0.0012) -[2023-11-28 09:22:16,070][87424] Updated weights for policy 0, policy_version 349469 (0.0011) -[2023-11-28 09:22:16,287][87426] Updated weights for policy 1, policy_version 349140 (0.0012) -[2023-11-28 09:22:16,661][87426] Updated weights for policy 1, policy_version 349150 (0.0012) -[2023-11-28 09:22:18,413][87424] Updated weights for policy 0, policy_version 349479 (0.0011) -[2023-11-28 09:22:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178847744. Throughput: 0: 2682.2, 1: 2681.0. Samples: 178860724. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:18,445][86177] Avg episode reward: [(0, '-530.400'), (1, '-560.200')] -[2023-11-28 09:22:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000349152_89382912.pth... -[2023-11-28 09:22:18,501][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000346656_88743936.pth -[2023-11-28 09:22:18,795][87424] Updated weights for policy 0, policy_version 349489 (0.0011) -[2023-11-28 09:22:18,992][87426] Updated weights for policy 1, policy_version 349160 (0.0011) -[2023-11-28 09:22:19,174][87424] Updated weights for policy 0, policy_version 349499 (0.0011) -[2023-11-28 09:22:19,361][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000349504_89473024.pth... -[2023-11-28 09:22:19,379][87426] Updated weights for policy 1, policy_version 349170 (0.0010) -[2023-11-28 09:22:19,393][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000346976_88825856.pth -[2023-11-28 09:22:19,751][87426] Updated weights for policy 1, policy_version 349180 (0.0008) -[2023-11-28 09:22:21,442][87424] Updated weights for policy 0, policy_version 349509 (0.0011) -[2023-11-28 09:22:21,791][87426] Updated weights for policy 1, policy_version 349190 (0.0011) -[2023-11-28 09:22:21,823][87424] Updated weights for policy 0, policy_version 349519 (0.0018) -[2023-11-28 09:22:22,179][87426] Updated weights for policy 1, policy_version 349200 (0.0011) -[2023-11-28 09:22:22,192][87424] Updated weights for policy 0, policy_version 349529 (0.0011) -[2023-11-28 09:22:22,554][87426] Updated weights for policy 1, policy_version 349210 (0.0009) -[2023-11-28 09:22:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 178880512. Throughput: 0: 2694.4, 1: 2696.0. Samples: 178893456. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:23,445][86177] Avg episode reward: [(0, '-524.460'), (1, '-561.330')] -[2023-11-28 09:22:24,615][87424] Updated weights for policy 0, policy_version 349539 (0.0011) -[2023-11-28 09:22:24,997][87424] Updated weights for policy 0, policy_version 349549 (0.0008) -[2023-11-28 09:22:25,087][87426] Updated weights for policy 1, policy_version 349220 (0.0008) -[2023-11-28 09:22:25,378][87424] Updated weights for policy 0, policy_version 349559 (0.0008) -[2023-11-28 09:22:25,465][87426] Updated weights for policy 1, policy_version 349230 (0.0011) -[2023-11-28 09:22:25,853][87426] Updated weights for policy 1, policy_version 349240 (0.0008) -[2023-11-28 09:22:27,101][87424] Updated weights for policy 0, policy_version 349569 (0.0011) -[2023-11-28 09:22:27,479][87424] Updated weights for policy 0, policy_version 349579 (0.0012) -[2023-11-28 09:22:27,859][87424] Updated weights for policy 0, policy_version 349589 (0.0011) -[2023-11-28 09:22:27,888][87426] Updated weights for policy 1, policy_version 349250 (0.0008) -[2023-11-28 09:22:28,236][87424] Updated weights for policy 0, policy_version 349599 (0.0009) -[2023-11-28 09:22:28,267][87426] Updated weights for policy 1, policy_version 349260 (0.0009) -[2023-11-28 09:22:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 178905088. Throughput: 0: 2719.6, 1: 2698.2. Samples: 178917656. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:28,445][86177] Avg episode reward: [(0, '-527.340'), (1, '-561.550')] -[2023-11-28 09:22:28,643][87426] Updated weights for policy 1, policy_version 349270 (0.0007) -[2023-11-28 09:22:29,019][87426] Updated weights for policy 1, policy_version 349280 (0.0008) -[2023-11-28 09:22:30,831][87424] Updated weights for policy 0, policy_version 349609 (0.0011) -[2023-11-28 09:22:30,891][87426] Updated weights for policy 1, policy_version 349290 (0.0009) -[2023-11-28 09:22:31,213][87424] Updated weights for policy 0, policy_version 349619 (0.0012) -[2023-11-28 09:22:31,275][87426] Updated weights for policy 1, policy_version 349300 (0.0007) -[2023-11-28 09:22:31,590][87424] Updated weights for policy 0, policy_version 349629 (0.0011) -[2023-11-28 09:22:31,666][87426] Updated weights for policy 1, policy_version 349310 (0.0010) -[2023-11-28 09:22:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 178929664. Throughput: 0: 2713.6, 1: 2708.2. Samples: 178941040. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:33,446][86177] Avg episode reward: [(0, '-579.310'), (1, '-523.260')] -[2023-11-28 09:22:33,780][87426] Updated weights for policy 1, policy_version 349320 (0.0008) -[2023-11-28 09:22:33,958][87424] Updated weights for policy 0, policy_version 349639 (0.0010) -[2023-11-28 09:22:34,148][87426] Updated weights for policy 1, policy_version 349330 (0.0008) -[2023-11-28 09:22:34,345][87424] Updated weights for policy 0, policy_version 349649 (0.0008) -[2023-11-28 09:22:34,518][87426] Updated weights for policy 1, policy_version 349340 (0.0008) -[2023-11-28 09:22:34,719][87424] Updated weights for policy 0, policy_version 349659 (0.0008) -[2023-11-28 09:22:36,998][87426] Updated weights for policy 1, policy_version 349350 (0.0008) -[2023-11-28 09:22:37,279][87424] Updated weights for policy 0, policy_version 349669 (0.0008) -[2023-11-28 09:22:37,378][87426] Updated weights for policy 1, policy_version 349360 (0.0011) -[2023-11-28 09:22:37,660][87424] Updated weights for policy 0, policy_version 349679 (0.0010) -[2023-11-28 09:22:37,745][87426] Updated weights for policy 1, policy_version 349370 (0.0011) -[2023-11-28 09:22:38,045][87424] Updated weights for policy 0, policy_version 349689 (0.0011) -[2023-11-28 09:22:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 178962432. Throughput: 0: 2683.2, 1: 2705.2. Samples: 178972448. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:38,445][86177] Avg episode reward: [(0, '-580.120'), (1, '-518.280')] -[2023-11-28 09:22:40,377][87426] Updated weights for policy 1, policy_version 349380 (0.0009) -[2023-11-28 09:22:40,429][87424] Updated weights for policy 0, policy_version 349699 (0.0012) -[2023-11-28 09:22:40,754][87426] Updated weights for policy 1, policy_version 349390 (0.0011) -[2023-11-28 09:22:40,808][87424] Updated weights for policy 0, policy_version 349709 (0.0010) -[2023-11-28 09:22:41,122][87426] Updated weights for policy 1, policy_version 349400 (0.0009) -[2023-11-28 09:22:41,188][87424] Updated weights for policy 0, policy_version 349719 (0.0008) -[2023-11-28 09:22:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 178978816. Throughput: 0: 2676.7, 1: 2696.5. Samples: 178996572. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:43,445][86177] Avg episode reward: [(0, '-587.830'), (1, '-524.660')] -[2023-11-28 09:22:43,670][87426] Updated weights for policy 1, policy_version 349410 (0.0008) -[2023-11-28 09:22:43,709][87424] Updated weights for policy 0, policy_version 349729 (0.0008) -[2023-11-28 09:22:44,051][87426] Updated weights for policy 1, policy_version 349420 (0.0009) -[2023-11-28 09:22:44,087][87424] Updated weights for policy 0, policy_version 349739 (0.0010) -[2023-11-28 09:22:44,437][87426] Updated weights for policy 1, policy_version 349430 (0.0010) -[2023-11-28 09:22:44,472][87424] Updated weights for policy 0, policy_version 349749 (0.0008) -[2023-11-28 09:22:44,816][87426] Updated weights for policy 1, policy_version 349440 (0.0007) -[2023-11-28 09:22:44,852][87424] Updated weights for policy 0, policy_version 349759 (0.0011) -[2023-11-28 09:22:46,840][87426] Updated weights for policy 1, policy_version 349450 (0.0011) -[2023-11-28 09:22:47,086][87424] Updated weights for policy 0, policy_version 349769 (0.0009) -[2023-11-28 09:22:47,217][87426] Updated weights for policy 1, policy_version 349460 (0.0008) -[2023-11-28 09:22:47,470][87424] Updated weights for policy 0, policy_version 349779 (0.0010) -[2023-11-28 09:22:47,595][87426] Updated weights for policy 1, policy_version 349470 (0.0008) -[2023-11-28 09:22:47,860][87424] Updated weights for policy 0, policy_version 349789 (0.0007) -[2023-11-28 09:22:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 179011584. Throughput: 0: 2640.9, 1: 2705.5. Samples: 179020600. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:48,445][86177] Avg episode reward: [(0, '-587.100'), (1, '-517.700')] -[2023-11-28 09:22:49,249][87426] Updated weights for policy 1, policy_version 349480 (0.0011) -[2023-11-28 09:22:49,624][87426] Updated weights for policy 1, policy_version 349490 (0.0012) -[2023-11-28 09:22:49,864][87424] Updated weights for policy 0, policy_version 349799 (0.0011) -[2023-11-28 09:22:50,006][87426] Updated weights for policy 1, policy_version 349500 (0.0011) -[2023-11-28 09:22:50,254][87424] Updated weights for policy 0, policy_version 349809 (0.0010) -[2023-11-28 09:22:50,633][87424] Updated weights for policy 0, policy_version 349819 (0.0010) -[2023-11-28 09:22:52,441][87426] Updated weights for policy 1, policy_version 349510 (0.0010) -[2023-11-28 09:22:52,519][87424] Updated weights for policy 0, policy_version 349829 (0.0009) -[2023-11-28 09:22:52,813][87426] Updated weights for policy 1, policy_version 349520 (0.0009) -[2023-11-28 09:22:52,894][87424] Updated weights for policy 0, policy_version 349839 (0.0011) -[2023-11-28 09:22:53,192][87426] Updated weights for policy 1, policy_version 349530 (0.0011) -[2023-11-28 09:22:53,267][87424] Updated weights for policy 0, policy_version 349849 (0.0011) -[2023-11-28 09:22:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179036160. Throughput: 0: 2665.9, 1: 2714.7. Samples: 179053740. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:53,445][86177] Avg episode reward: [(0, '-543.710'), (1, '-554.090')] -[2023-11-28 09:22:55,151][87424] Updated weights for policy 0, policy_version 349859 (0.0011) -[2023-11-28 09:22:55,525][87424] Updated weights for policy 0, policy_version 349869 (0.0012) -[2023-11-28 09:22:55,812][87426] Updated weights for policy 1, policy_version 349540 (0.0011) -[2023-11-28 09:22:55,915][87424] Updated weights for policy 0, policy_version 349879 (0.0011) -[2023-11-28 09:22:56,199][87426] Updated weights for policy 1, policy_version 349550 (0.0007) -[2023-11-28 09:22:56,571][87426] Updated weights for policy 1, policy_version 349560 (0.0007) -[2023-11-28 09:22:58,254][87424] Updated weights for policy 0, policy_version 349889 (0.0012) -[2023-11-28 09:22:58,433][87426] Updated weights for policy 1, policy_version 349570 (0.0008) -[2023-11-28 09:22:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 179060736. Throughput: 0: 2700.0, 1: 2704.0. Samples: 179078704. Policy #0 lag: (min: 31.0, avg: 53.6, max: 95.0) -[2023-11-28 09:22:58,445][86177] Avg episode reward: [(0, '-547.840'), (1, '-555.920')] -[2023-11-28 09:22:58,639][87424] Updated weights for policy 0, policy_version 349899 (0.0009) -[2023-11-28 09:22:58,813][87426] Updated weights for policy 1, policy_version 349580 (0.0008) -[2023-11-28 09:22:59,020][87424] Updated weights for policy 0, policy_version 349909 (0.0011) -[2023-11-28 09:22:59,188][87426] Updated weights for policy 1, policy_version 349590 (0.0010) -[2023-11-28 09:22:59,396][87424] Updated weights for policy 0, policy_version 349919 (0.0012) -[2023-11-28 09:22:59,567][87426] Updated weights for policy 1, policy_version 349600 (0.0009) -[2023-11-28 09:23:01,538][87424] Updated weights for policy 0, policy_version 349929 (0.0008) -[2023-11-28 09:23:01,921][87424] Updated weights for policy 0, policy_version 349939 (0.0010) -[2023-11-28 09:23:01,971][87426] Updated weights for policy 1, policy_version 349610 (0.0011) -[2023-11-28 09:23:02,305][87424] Updated weights for policy 0, policy_version 349949 (0.0015) -[2023-11-28 09:23:02,354][87426] Updated weights for policy 1, policy_version 349620 (0.0011) -[2023-11-28 09:23:02,741][87426] Updated weights for policy 1, policy_version 349630 (0.0012) -[2023-11-28 09:23:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 179093504. Throughput: 0: 2682.0, 1: 2686.0. Samples: 179102284. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:03,445][86177] Avg episode reward: [(0, '-555.900'), (1, '-544.360')] -[2023-11-28 09:23:04,227][87424] Updated weights for policy 0, policy_version 349959 (0.0012) -[2023-11-28 09:23:04,474][87426] Updated weights for policy 1, policy_version 349640 (0.0009) -[2023-11-28 09:23:04,597][87424] Updated weights for policy 0, policy_version 349969 (0.0012) -[2023-11-28 09:23:04,862][87426] Updated weights for policy 1, policy_version 349650 (0.0009) -[2023-11-28 09:23:04,982][87424] Updated weights for policy 0, policy_version 349979 (0.0011) -[2023-11-28 09:23:05,237][87426] Updated weights for policy 1, policy_version 349660 (0.0011) -[2023-11-28 09:23:07,039][87424] Updated weights for policy 0, policy_version 349989 (0.0010) -[2023-11-28 09:23:07,418][87424] Updated weights for policy 0, policy_version 349999 (0.0010) -[2023-11-28 09:23:07,421][87426] Updated weights for policy 1, policy_version 349670 (0.0012) -[2023-11-28 09:23:07,794][87424] Updated weights for policy 0, policy_version 350009 (0.0008) -[2023-11-28 09:23:07,803][87426] Updated weights for policy 1, policy_version 349680 (0.0011) -[2023-11-28 09:23:08,172][87426] Updated weights for policy 1, policy_version 349690 (0.0011) -[2023-11-28 09:23:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 179126272. Throughput: 0: 2706.4, 1: 2673.4. Samples: 179135548. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:08,445][86177] Avg episode reward: [(0, '-542.140'), (1, '-543.800')] -[2023-11-28 09:23:09,957][87424] Updated weights for policy 0, policy_version 350019 (0.0010) -[2023-11-28 09:23:10,328][87426] Updated weights for policy 1, policy_version 349700 (0.0011) -[2023-11-28 09:23:10,330][87424] Updated weights for policy 0, policy_version 350029 (0.0012) -[2023-11-28 09:23:10,705][87426] Updated weights for policy 1, policy_version 349710 (0.0010) -[2023-11-28 09:23:10,710][87424] Updated weights for policy 0, policy_version 350039 (0.0011) -[2023-11-28 09:23:11,084][87426] Updated weights for policy 1, policy_version 349720 (0.0008) -[2023-11-28 09:23:13,195][87424] Updated weights for policy 0, policy_version 350049 (0.0012) -[2023-11-28 09:23:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 179142656. Throughput: 0: 2710.6, 1: 2672.3. Samples: 179159884. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:13,445][86177] Avg episode reward: [(0, '-545.960'), (1, '-505.600')] -[2023-11-28 09:23:13,575][87424] Updated weights for policy 0, policy_version 350059 (0.0008) -[2023-11-28 09:23:13,678][87426] Updated weights for policy 1, policy_version 349730 (0.0008) -[2023-11-28 09:23:13,954][87424] Updated weights for policy 0, policy_version 350069 (0.0011) -[2023-11-28 09:23:14,049][87426] Updated weights for policy 1, policy_version 349740 (0.0012) -[2023-11-28 09:23:14,332][87424] Updated weights for policy 0, policy_version 350079 (0.0010) -[2023-11-28 09:23:14,430][87426] Updated weights for policy 1, policy_version 349750 (0.0012) -[2023-11-28 09:23:14,803][87426] Updated weights for policy 1, policy_version 349760 (0.0009) -[2023-11-28 09:23:16,267][87424] Updated weights for policy 0, policy_version 350089 (0.0011) -[2023-11-28 09:23:16,647][87424] Updated weights for policy 0, policy_version 350099 (0.0010) -[2023-11-28 09:23:17,027][87424] Updated weights for policy 0, policy_version 350109 (0.0010) -[2023-11-28 09:23:17,045][87426] Updated weights for policy 1, policy_version 349770 (0.0011) -[2023-11-28 09:23:17,425][87426] Updated weights for policy 1, policy_version 349780 (0.0011) -[2023-11-28 09:23:17,803][87426] Updated weights for policy 1, policy_version 349790 (0.0012) -[2023-11-28 09:23:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 179175424. Throughput: 0: 2736.3, 1: 2665.3. Samples: 179184116. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:18,446][86177] Avg episode reward: [(0, '-546.150'), (1, '-505.830')] -[2023-11-28 09:23:19,182][87424] Updated weights for policy 0, policy_version 350119 (0.0011) -[2023-11-28 09:23:19,564][87424] Updated weights for policy 0, policy_version 350129 (0.0012) -[2023-11-28 09:23:19,792][87426] Updated weights for policy 1, policy_version 349800 (0.0009) -[2023-11-28 09:23:19,944][87424] Updated weights for policy 0, policy_version 350139 (0.0011) -[2023-11-28 09:23:20,156][87426] Updated weights for policy 1, policy_version 349810 (0.0020) -[2023-11-28 09:23:20,535][87426] Updated weights for policy 1, policy_version 349820 (0.0012) -[2023-11-28 09:23:22,201][87424] Updated weights for policy 0, policy_version 350149 (0.0011) -[2023-11-28 09:23:22,588][87424] Updated weights for policy 0, policy_version 350159 (0.0009) -[2023-11-28 09:23:22,974][87424] Updated weights for policy 0, policy_version 350169 (0.0011) -[2023-11-28 09:23:23,059][87426] Updated weights for policy 1, policy_version 349830 (0.0012) -[2023-11-28 09:23:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179200000. Throughput: 0: 2751.9, 1: 2657.2. Samples: 179215856. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:23,445][86177] Avg episode reward: [(0, '-555.180'), (1, '-506.990')] -[2023-11-28 09:23:23,449][87426] Updated weights for policy 1, policy_version 349840 (0.0010) -[2023-11-28 09:23:23,825][87426] Updated weights for policy 1, policy_version 349850 (0.0010) -[2023-11-28 09:23:25,075][87424] Updated weights for policy 0, policy_version 350179 (0.0011) -[2023-11-28 09:23:25,454][87424] Updated weights for policy 0, policy_version 350189 (0.0010) -[2023-11-28 09:23:25,840][87424] Updated weights for policy 0, policy_version 350199 (0.0007) -[2023-11-28 09:23:25,897][87426] Updated weights for policy 1, policy_version 349860 (0.0010) -[2023-11-28 09:23:26,272][87426] Updated weights for policy 1, policy_version 349870 (0.0011) -[2023-11-28 09:23:26,652][87426] Updated weights for policy 1, policy_version 349880 (0.0011) -[2023-11-28 09:23:28,071][87424] Updated weights for policy 0, policy_version 350209 (0.0007) -[2023-11-28 09:23:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179224576. Throughput: 0: 2750.3, 1: 2663.5. Samples: 179240192. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:28,445][86177] Avg episode reward: [(0, '-560.390'), (1, '-513.930')] -[2023-11-28 09:23:28,457][87424] Updated weights for policy 0, policy_version 350219 (0.0008) -[2023-11-28 09:23:28,839][87424] Updated weights for policy 0, policy_version 350229 (0.0007) -[2023-11-28 09:23:28,892][87426] Updated weights for policy 1, policy_version 349890 (0.0011) -[2023-11-28 09:23:29,226][87424] Updated weights for policy 0, policy_version 350239 (0.0011) -[2023-11-28 09:23:29,277][87426] Updated weights for policy 1, policy_version 349900 (0.0008) -[2023-11-28 09:23:29,650][87426] Updated weights for policy 1, policy_version 349910 (0.0009) -[2023-11-28 09:23:30,029][87426] Updated weights for policy 1, policy_version 349920 (0.0010) -[2023-11-28 09:23:31,368][87424] Updated weights for policy 0, policy_version 350249 (0.0008) -[2023-11-28 09:23:31,746][87424] Updated weights for policy 0, policy_version 350259 (0.0009) -[2023-11-28 09:23:32,139][87424] Updated weights for policy 0, policy_version 350269 (0.0009) -[2023-11-28 09:23:32,254][87426] Updated weights for policy 1, policy_version 349930 (0.0011) -[2023-11-28 09:23:32,629][87426] Updated weights for policy 1, policy_version 349940 (0.0012) -[2023-11-28 09:23:33,001][87426] Updated weights for policy 1, policy_version 349950 (0.0011) -[2023-11-28 09:23:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 179257344. Throughput: 0: 2780.5, 1: 2647.1. Samples: 179264844. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:33,445][86177] Avg episode reward: [(0, '-563.860'), (1, '-522.030')] -[2023-11-28 09:23:34,023][87424] Updated weights for policy 0, policy_version 350279 (0.0011) -[2023-11-28 09:23:34,407][87424] Updated weights for policy 0, policy_version 350289 (0.0012) -[2023-11-28 09:23:34,784][87424] Updated weights for policy 0, policy_version 350299 (0.0012) -[2023-11-28 09:23:34,940][87426] Updated weights for policy 1, policy_version 349960 (0.0011) -[2023-11-28 09:23:35,315][87426] Updated weights for policy 1, policy_version 349970 (0.0012) -[2023-11-28 09:23:35,702][87426] Updated weights for policy 1, policy_version 349980 (0.0012) -[2023-11-28 09:23:36,670][87424] Updated weights for policy 0, policy_version 350309 (0.0012) -[2023-11-28 09:23:37,049][87424] Updated weights for policy 0, policy_version 350319 (0.0012) -[2023-11-28 09:23:37,423][87424] Updated weights for policy 0, policy_version 350329 (0.0012) -[2023-11-28 09:23:37,590][87426] Updated weights for policy 1, policy_version 349990 (0.0011) -[2023-11-28 09:23:37,961][87426] Updated weights for policy 1, policy_version 350000 (0.0011) -[2023-11-28 09:23:38,342][87426] Updated weights for policy 1, policy_version 350010 (0.0011) -[2023-11-28 09:23:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 179281920. Throughput: 0: 2784.4, 1: 2668.1. Samples: 179299104. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:38,445][86177] Avg episode reward: [(0, '-556.090'), (1, '-572.170')] -[2023-11-28 09:23:39,471][87424] Updated weights for policy 0, policy_version 350339 (0.0012) -[2023-11-28 09:23:39,860][87424] Updated weights for policy 0, policy_version 350349 (0.0010) -[2023-11-28 09:23:40,235][87424] Updated weights for policy 0, policy_version 350359 (0.0012) -[2023-11-28 09:23:40,580][87426] Updated weights for policy 1, policy_version 350020 (0.0011) -[2023-11-28 09:23:40,950][87426] Updated weights for policy 1, policy_version 350030 (0.0012) -[2023-11-28 09:23:41,326][87426] Updated weights for policy 1, policy_version 350040 (0.0012) -[2023-11-28 09:23:42,458][87424] Updated weights for policy 0, policy_version 350369 (0.0012) -[2023-11-28 09:23:42,836][87424] Updated weights for policy 0, policy_version 350379 (0.0012) -[2023-11-28 09:23:43,217][87424] Updated weights for policy 0, policy_version 350389 (0.0012) -[2023-11-28 09:23:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 179306496. Throughput: 0: 2771.2, 1: 2670.7. Samples: 179323588. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:43,445][86177] Avg episode reward: [(0, '-540.130'), (1, '-576.540')] -[2023-11-28 09:23:43,607][87424] Updated weights for policy 0, policy_version 350399 (0.0010) -[2023-11-28 09:23:43,616][87426] Updated weights for policy 1, policy_version 350050 (0.0012) -[2023-11-28 09:23:43,996][87426] Updated weights for policy 1, policy_version 350060 (0.0009) -[2023-11-28 09:23:44,375][87426] Updated weights for policy 1, policy_version 350070 (0.0010) -[2023-11-28 09:23:44,749][87426] Updated weights for policy 1, policy_version 350080 (0.0011) -[2023-11-28 09:23:45,620][87424] Updated weights for policy 0, policy_version 350409 (0.0011) -[2023-11-28 09:23:46,003][87424] Updated weights for policy 0, policy_version 350419 (0.0012) -[2023-11-28 09:23:46,384][87424] Updated weights for policy 0, policy_version 350429 (0.0012) -[2023-11-28 09:23:47,047][87426] Updated weights for policy 1, policy_version 350090 (0.0010) -[2023-11-28 09:23:47,429][87426] Updated weights for policy 1, policy_version 350100 (0.0011) -[2023-11-28 09:23:47,801][87426] Updated weights for policy 1, policy_version 350110 (0.0010) -[2023-11-28 09:23:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 179339264. Throughput: 0: 2780.8, 1: 2691.6. Samples: 179348540. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:48,445][86177] Avg episode reward: [(0, '-548.650'), (1, '-573.000')] -[2023-11-28 09:23:48,588][87424] Updated weights for policy 0, policy_version 350439 (0.0009) -[2023-11-28 09:23:48,968][87424] Updated weights for policy 0, policy_version 350449 (0.0009) -[2023-11-28 09:23:49,352][87424] Updated weights for policy 0, policy_version 350459 (0.0010) -[2023-11-28 09:23:50,375][87426] Updated weights for policy 1, policy_version 350120 (0.0010) -[2023-11-28 09:23:50,750][87426] Updated weights for policy 1, policy_version 350130 (0.0011) -[2023-11-28 09:23:51,138][87426] Updated weights for policy 1, policy_version 350140 (0.0012) -[2023-11-28 09:23:51,639][87424] Updated weights for policy 0, policy_version 350469 (0.0011) -[2023-11-28 09:23:52,010][87424] Updated weights for policy 0, policy_version 350479 (0.0011) -[2023-11-28 09:23:52,395][87424] Updated weights for policy 0, policy_version 350489 (0.0011) -[2023-11-28 09:23:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 179363840. Throughput: 0: 2759.0, 1: 2675.9. Samples: 179380120. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:53,445][86177] Avg episode reward: [(0, '-557.470'), (1, '-566.400')] -[2023-11-28 09:23:53,772][87426] Updated weights for policy 1, policy_version 350150 (0.0010) -[2023-11-28 09:23:54,163][87426] Updated weights for policy 1, policy_version 350160 (0.0011) -[2023-11-28 09:23:54,540][87426] Updated weights for policy 1, policy_version 350170 (0.0012) -[2023-11-28 09:23:54,672][87424] Updated weights for policy 0, policy_version 350499 (0.0007) -[2023-11-28 09:23:55,055][87424] Updated weights for policy 0, policy_version 350509 (0.0010) -[2023-11-28 09:23:55,435][87424] Updated weights for policy 0, policy_version 350519 (0.0007) -[2023-11-28 09:23:57,094][87426] Updated weights for policy 1, policy_version 350180 (0.0009) -[2023-11-28 09:23:57,475][87426] Updated weights for policy 1, policy_version 350190 (0.0012) -[2023-11-28 09:23:57,779][87424] Updated weights for policy 0, policy_version 350529 (0.0009) -[2023-11-28 09:23:57,851][87426] Updated weights for policy 1, policy_version 350200 (0.0011) -[2023-11-28 09:23:58,157][87424] Updated weights for policy 0, policy_version 350539 (0.0012) -[2023-11-28 09:23:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 179388416. Throughput: 0: 2747.4, 1: 2656.3. Samples: 179403048. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:23:58,445][86177] Avg episode reward: [(0, '-569.770'), (1, '-528.110')] -[2023-11-28 09:23:58,541][87424] Updated weights for policy 0, policy_version 350549 (0.0012) -[2023-11-28 09:23:58,927][87424] Updated weights for policy 0, policy_version 350559 (0.0012) -[2023-11-28 09:24:00,049][87426] Updated weights for policy 1, policy_version 350210 (0.0008) -[2023-11-28 09:24:00,424][87426] Updated weights for policy 1, policy_version 350220 (0.0008) -[2023-11-28 09:24:00,804][87426] Updated weights for policy 1, policy_version 350230 (0.0011) -[2023-11-28 09:24:01,076][87424] Updated weights for policy 0, policy_version 350569 (0.0014) -[2023-11-28 09:24:01,184][87426] Updated weights for policy 1, policy_version 350240 (0.0010) -[2023-11-28 09:24:01,449][87424] Updated weights for policy 0, policy_version 350579 (0.0012) -[2023-11-28 09:24:01,827][87424] Updated weights for policy 0, policy_version 350589 (0.0009) -[2023-11-28 09:24:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179412992. Throughput: 0: 2748.6, 1: 2666.8. Samples: 179427808. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:24:03,445][86177] Avg episode reward: [(0, '-569.310'), (1, '-515.400')] -[2023-11-28 09:24:03,616][87426] Updated weights for policy 1, policy_version 350250 (0.0007) -[2023-11-28 09:24:03,990][87426] Updated weights for policy 1, policy_version 350260 (0.0008) -[2023-11-28 09:24:04,350][87424] Updated weights for policy 0, policy_version 350599 (0.0008) -[2023-11-28 09:24:04,371][87426] Updated weights for policy 1, policy_version 350270 (0.0008) -[2023-11-28 09:24:04,723][87424] Updated weights for policy 0, policy_version 350609 (0.0012) -[2023-11-28 09:24:05,109][87424] Updated weights for policy 0, policy_version 350619 (0.0012) -[2023-11-28 09:24:06,238][87426] Updated weights for policy 1, policy_version 350280 (0.0011) -[2023-11-28 09:24:06,607][87426] Updated weights for policy 1, policy_version 350290 (0.0009) -[2023-11-28 09:24:06,985][87426] Updated weights for policy 1, policy_version 350300 (0.0010) -[2023-11-28 09:24:07,512][87424] Updated weights for policy 0, policy_version 350629 (0.0012) -[2023-11-28 09:24:07,882][87424] Updated weights for policy 0, policy_version 350639 (0.0012) -[2023-11-28 09:24:08,270][87424] Updated weights for policy 0, policy_version 350649 (0.0011) -[2023-11-28 09:24:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 179437568. Throughput: 0: 2735.7, 1: 2678.8. Samples: 179459504. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:24:08,445][86177] Avg episode reward: [(0, '-565.700'), (1, '-509.890')] -[2023-11-28 09:24:08,755][87426] Updated weights for policy 1, policy_version 350310 (0.0010) -[2023-11-28 09:24:09,136][87426] Updated weights for policy 1, policy_version 350320 (0.0010) -[2023-11-28 09:24:09,513][87426] Updated weights for policy 1, policy_version 350330 (0.0011) -[2023-11-28 09:24:10,732][87424] Updated weights for policy 0, policy_version 350659 (0.0011) -[2023-11-28 09:24:11,119][87424] Updated weights for policy 0, policy_version 350669 (0.0012) -[2023-11-28 09:24:11,497][87424] Updated weights for policy 0, policy_version 350679 (0.0011) -[2023-11-28 09:24:11,897][87426] Updated weights for policy 1, policy_version 350340 (0.0009) -[2023-11-28 09:24:12,282][87426] Updated weights for policy 1, policy_version 350350 (0.0009) -[2023-11-28 09:24:12,654][87426] Updated weights for policy 1, policy_version 350360 (0.0009) -[2023-11-28 09:24:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 179470336. Throughput: 0: 2731.2, 1: 2669.8. Samples: 179483236. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:24:13,445][86177] Avg episode reward: [(0, '-554.350'), (1, '-509.720')] -[2023-11-28 09:24:13,952][87424] Updated weights for policy 0, policy_version 350689 (0.0011) -[2023-11-28 09:24:14,346][87424] Updated weights for policy 0, policy_version 350699 (0.0012) -[2023-11-28 09:24:14,726][87424] Updated weights for policy 0, policy_version 350709 (0.0012) -[2023-11-28 09:24:15,108][87424] Updated weights for policy 0, policy_version 350719 (0.0012) -[2023-11-28 09:24:15,214][87426] Updated weights for policy 1, policy_version 350370 (0.0009) -[2023-11-28 09:24:15,592][87426] Updated weights for policy 1, policy_version 350380 (0.0012) -[2023-11-28 09:24:15,970][87426] Updated weights for policy 1, policy_version 350390 (0.0012) -[2023-11-28 09:24:16,343][87426] Updated weights for policy 1, policy_version 350400 (0.0012) -[2023-11-28 09:24:17,019][87424] Updated weights for policy 0, policy_version 350729 (0.0009) -[2023-11-28 09:24:17,410][87424] Updated weights for policy 0, policy_version 350739 (0.0011) -[2023-11-28 09:24:17,785][87424] Updated weights for policy 0, policy_version 350749 (0.0012) -[2023-11-28 09:24:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 179494912. Throughput: 0: 2715.0, 1: 2692.7. Samples: 179508192. Policy #0 lag: (min: 31.0, avg: 44.0, max: 63.0) -[2023-11-28 09:24:18,445][86177] Avg episode reward: [(0, '-553.600'), (1, '-508.790')] -[2023-11-28 09:24:18,456][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000350752_89792512.pth... -[2023-11-28 09:24:18,494][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000348256_89153536.pth -[2023-11-28 09:24:18,541][87426] Updated weights for policy 1, policy_version 350410 (0.0012) -[2023-11-28 09:24:18,933][87426] Updated weights for policy 1, policy_version 350420 (0.0011) -[2023-11-28 09:24:19,306][87426] Updated weights for policy 1, policy_version 350430 (0.0012) -[2023-11-28 09:24:19,377][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000350432_89710592.pth... -[2023-11-28 09:24:19,417][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000347904_89063424.pth -[2023-11-28 09:24:20,075][87424] Updated weights for policy 0, policy_version 350759 (0.0016) -[2023-11-28 09:24:20,457][87424] Updated weights for policy 0, policy_version 350769 (0.0012) -[2023-11-28 09:24:20,830][87424] Updated weights for policy 0, policy_version 350779 (0.0012) -[2023-11-28 09:24:21,482][87426] Updated weights for policy 1, policy_version 350440 (0.0011) -[2023-11-28 09:24:21,854][87426] Updated weights for policy 1, policy_version 350450 (0.0011) -[2023-11-28 09:24:22,233][87426] Updated weights for policy 1, policy_version 350460 (0.0012) -[2023-11-28 09:24:23,314][87424] Updated weights for policy 0, policy_version 350789 (0.0010) -[2023-11-28 09:24:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179519488. Throughput: 0: 2673.3, 1: 2670.5. Samples: 179539576. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:24:23,445][86177] Avg episode reward: [(0, '-552.830'), (1, '-508.260')] -[2023-11-28 09:24:23,699][87424] Updated weights for policy 0, policy_version 350799 (0.0007) -[2023-11-28 09:24:24,082][87424] Updated weights for policy 0, policy_version 350809 (0.0008) -[2023-11-28 09:24:24,728][87426] Updated weights for policy 1, policy_version 350470 (0.0012) -[2023-11-28 09:24:25,110][87426] Updated weights for policy 1, policy_version 350480 (0.0012) -[2023-11-28 09:24:25,489][87426] Updated weights for policy 1, policy_version 350490 (0.0012) -[2023-11-28 09:24:26,086][87424] Updated weights for policy 0, policy_version 350819 (0.0009) -[2023-11-28 09:24:26,467][87424] Updated weights for policy 0, policy_version 350829 (0.0010) -[2023-11-28 09:24:26,852][87424] Updated weights for policy 0, policy_version 350839 (0.0008) -[2023-11-28 09:24:27,375][87426] Updated weights for policy 1, policy_version 350500 (0.0011) -[2023-11-28 09:24:27,748][87426] Updated weights for policy 1, policy_version 350510 (0.0011) -[2023-11-28 09:24:28,128][87426] Updated weights for policy 1, policy_version 350520 (0.0012) -[2023-11-28 09:24:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 179552256. Throughput: 0: 2661.6, 1: 2678.8. Samples: 179563904. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:24:28,445][86177] Avg episode reward: [(0, '-547.560'), (1, '-504.860')] -[2023-11-28 09:24:28,718][87424] Updated weights for policy 0, policy_version 350849 (0.0010) -[2023-11-28 09:24:29,090][87424] Updated weights for policy 0, policy_version 350859 (0.0012) -[2023-11-28 09:24:29,464][87424] Updated weights for policy 0, policy_version 350869 (0.0012) -[2023-11-28 09:24:29,764][87426] Updated weights for policy 1, policy_version 350530 (0.0011) -[2023-11-28 09:24:29,846][87424] Updated weights for policy 0, policy_version 350879 (0.0009) -[2023-11-28 09:24:30,131][87426] Updated weights for policy 1, policy_version 350540 (0.0011) -[2023-11-28 09:24:30,513][87426] Updated weights for policy 1, policy_version 350550 (0.0012) -[2023-11-28 09:24:30,896][87426] Updated weights for policy 1, policy_version 350560 (0.0012) -[2023-11-28 09:24:31,866][87424] Updated weights for policy 0, policy_version 350889 (0.0010) -[2023-11-28 09:24:32,252][87424] Updated weights for policy 0, policy_version 350899 (0.0009) -[2023-11-28 09:24:32,638][87424] Updated weights for policy 0, policy_version 350909 (0.0009) -[2023-11-28 09:24:33,417][87426] Updated weights for policy 1, policy_version 350570 (0.0011) -[2023-11-28 09:24:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 179576832. Throughput: 0: 2656.2, 1: 2668.0. Samples: 179588128. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:24:33,445][86177] Avg episode reward: [(0, '-562.670'), (1, '-547.040')] -[2023-11-28 09:24:33,797][87426] Updated weights for policy 1, policy_version 350580 (0.0011) -[2023-11-28 09:24:34,182][87426] Updated weights for policy 1, policy_version 350590 (0.0012) -[2023-11-28 09:24:34,710][87424] Updated weights for policy 0, policy_version 350919 (0.0008) -[2023-11-28 09:24:35,094][87424] Updated weights for policy 0, policy_version 350929 (0.0011) -[2023-11-28 09:24:35,478][87424] Updated weights for policy 0, policy_version 350939 (0.0011) -[2023-11-28 09:24:36,788][87426] Updated weights for policy 1, policy_version 350600 (0.0011) -[2023-11-28 09:24:37,162][87426] Updated weights for policy 1, policy_version 350610 (0.0012) -[2023-11-28 09:24:37,543][87426] Updated weights for policy 1, policy_version 350620 (0.0011) -[2023-11-28 09:24:37,896][87424] Updated weights for policy 0, policy_version 350949 (0.0012) -[2023-11-28 09:24:38,278][87424] Updated weights for policy 0, policy_version 350959 (0.0010) -[2023-11-28 09:24:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179601408. Throughput: 0: 2662.9, 1: 2687.2. Samples: 179620876. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:24:38,445][86177] Avg episode reward: [(0, '-579.660'), (1, '-581.550')] -[2023-11-28 09:24:38,665][87424] Updated weights for policy 0, policy_version 350969 (0.0010) -[2023-11-28 09:24:39,239][87426] Updated weights for policy 1, policy_version 350630 (0.0011) -[2023-11-28 09:24:39,619][87426] Updated weights for policy 1, policy_version 350640 (0.0011) -[2023-11-28 09:24:39,998][87426] Updated weights for policy 1, policy_version 350650 (0.0010) -[2023-11-28 09:24:40,634][87424] Updated weights for policy 0, policy_version 350979 (0.0012) -[2023-11-28 09:24:41,019][87424] Updated weights for policy 0, policy_version 350989 (0.0012) -[2023-11-28 09:24:41,396][87424] Updated weights for policy 0, policy_version 350999 (0.0011) -[2023-11-28 09:24:42,234][87426] Updated weights for policy 1, policy_version 350660 (0.0011) -[2023-11-28 09:24:42,612][87426] Updated weights for policy 1, policy_version 350670 (0.0012) -[2023-11-28 09:24:42,993][87426] Updated weights for policy 1, policy_version 350680 (0.0011) -[2023-11-28 09:24:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 179634176. Throughput: 0: 2662.8, 1: 2716.5. Samples: 179645116. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:24:43,445][86177] Avg episode reward: [(0, '-612.350'), (1, '-602.430')] -[2023-11-28 09:24:43,788][87424] Updated weights for policy 0, policy_version 351009 (0.0011) -[2023-11-28 09:24:44,171][87424] Updated weights for policy 0, policy_version 351019 (0.0012) -[2023-11-28 09:24:44,549][87424] Updated weights for policy 0, policy_version 351029 (0.0012) -[2023-11-28 09:24:44,931][87424] Updated weights for policy 0, policy_version 351039 (0.0011) -[2023-11-28 09:24:45,191][87426] Updated weights for policy 1, policy_version 350690 (0.0008) -[2023-11-28 09:24:45,563][87426] Updated weights for policy 1, policy_version 350700 (0.0012) -[2023-11-28 09:24:45,947][87426] Updated weights for policy 1, policy_version 350710 (0.0012) -[2023-11-28 09:24:46,316][87426] Updated weights for policy 1, policy_version 350720 (0.0011) -[2023-11-28 09:24:47,431][87424] Updated weights for policy 0, policy_version 351049 (0.0012) -[2023-11-28 09:24:47,810][87424] Updated weights for policy 0, policy_version 351059 (0.0012) -[2023-11-28 09:24:48,166][87426] Updated weights for policy 1, policy_version 350730 (0.0008) -[2023-11-28 09:24:48,193][87424] Updated weights for policy 0, policy_version 351069 (0.0009) -[2023-11-28 09:24:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 179658752. Throughput: 0: 2647.9, 1: 2701.2. Samples: 179668520. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:24:48,446][86177] Avg episode reward: [(0, '-606.040'), (1, '-606.240')] -[2023-11-28 09:24:48,547][87426] Updated weights for policy 1, policy_version 350740 (0.0011) -[2023-11-28 09:24:48,922][87426] Updated weights for policy 1, policy_version 350750 (0.0012) -[2023-11-28 09:24:50,194][87424] Updated weights for policy 0, policy_version 351079 (0.0011) -[2023-11-28 09:24:50,589][87424] Updated weights for policy 0, policy_version 351089 (0.0010) -[2023-11-28 09:24:50,965][87424] Updated weights for policy 0, policy_version 351099 (0.0010) -[2023-11-28 09:24:51,499][87426] Updated weights for policy 1, policy_version 350760 (0.0012) -[2023-11-28 09:24:51,883][87426] Updated weights for policy 1, policy_version 350770 (0.0012) -[2023-11-28 09:24:52,254][87426] Updated weights for policy 1, policy_version 350780 (0.0011) -[2023-11-28 09:24:53,091][87424] Updated weights for policy 0, policy_version 351109 (0.0011) -[2023-11-28 09:24:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179683328. Throughput: 0: 2645.3, 1: 2701.9. Samples: 179700128. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:24:53,445][86177] Avg episode reward: [(0, '-603.710'), (1, '-603.250')] -[2023-11-28 09:24:53,475][87424] Updated weights for policy 0, policy_version 351119 (0.0011) -[2023-11-28 09:24:53,855][87424] Updated weights for policy 0, policy_version 351129 (0.0009) -[2023-11-28 09:24:54,706][87426] Updated weights for policy 1, policy_version 350790 (0.0010) -[2023-11-28 09:24:55,086][87426] Updated weights for policy 1, policy_version 350800 (0.0010) -[2023-11-28 09:24:55,466][87426] Updated weights for policy 1, policy_version 350810 (0.0008) -[2023-11-28 09:24:56,092][87424] Updated weights for policy 0, policy_version 351139 (0.0009) -[2023-11-28 09:24:56,477][87424] Updated weights for policy 0, policy_version 351149 (0.0012) -[2023-11-28 09:24:56,850][87424] Updated weights for policy 0, policy_version 351159 (0.0012) -[2023-11-28 09:24:57,798][87426] Updated weights for policy 1, policy_version 350820 (0.0012) -[2023-11-28 09:24:58,180][87426] Updated weights for policy 1, policy_version 350830 (0.0012) -[2023-11-28 09:24:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 179707904. Throughput: 0: 2665.9, 1: 2703.5. Samples: 179724864. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:24:58,446][86177] Avg episode reward: [(0, '-577.490'), (1, '-608.530')] -[2023-11-28 09:24:58,554][87426] Updated weights for policy 1, policy_version 350840 (0.0012) -[2023-11-28 09:24:58,804][87424] Updated weights for policy 0, policy_version 351169 (0.0011) -[2023-11-28 09:24:59,192][87424] Updated weights for policy 0, policy_version 351179 (0.0008) -[2023-11-28 09:24:59,570][87424] Updated weights for policy 0, policy_version 351189 (0.0010) -[2023-11-28 09:24:59,957][87424] Updated weights for policy 0, policy_version 351199 (0.0009) -[2023-11-28 09:25:00,749][87426] Updated weights for policy 1, policy_version 350850 (0.0011) -[2023-11-28 09:25:01,129][87426] Updated weights for policy 1, policy_version 350860 (0.0008) -[2023-11-28 09:25:01,512][87426] Updated weights for policy 1, policy_version 350870 (0.0009) -[2023-11-28 09:25:01,887][87426] Updated weights for policy 1, policy_version 350880 (0.0010) -[2023-11-28 09:25:01,965][87424] Updated weights for policy 0, policy_version 351209 (0.0010) -[2023-11-28 09:25:02,348][87424] Updated weights for policy 0, policy_version 351219 (0.0010) -[2023-11-28 09:25:02,731][87424] Updated weights for policy 0, policy_version 351229 (0.0012) -[2023-11-28 09:25:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 179740672. Throughput: 0: 2691.6, 1: 2675.6. Samples: 179749720. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:25:03,445][86177] Avg episode reward: [(0, '-572.250'), (1, '-596.990')] -[2023-11-28 09:25:03,974][87426] Updated weights for policy 1, policy_version 350890 (0.0012) -[2023-11-28 09:25:04,362][87426] Updated weights for policy 1, policy_version 350900 (0.0011) -[2023-11-28 09:25:04,737][87426] Updated weights for policy 1, policy_version 350910 (0.0011) -[2023-11-28 09:25:05,089][87424] Updated weights for policy 0, policy_version 351239 (0.0012) -[2023-11-28 09:25:05,465][87424] Updated weights for policy 0, policy_version 351249 (0.0011) -[2023-11-28 09:25:05,847][87424] Updated weights for policy 0, policy_version 351259 (0.0008) -[2023-11-28 09:25:06,470][87426] Updated weights for policy 1, policy_version 350920 (0.0012) -[2023-11-28 09:25:06,847][87426] Updated weights for policy 1, policy_version 350930 (0.0012) -[2023-11-28 09:25:07,221][87426] Updated weights for policy 1, policy_version 350940 (0.0012) -[2023-11-28 09:25:07,927][87424] Updated weights for policy 0, policy_version 351269 (0.0010) -[2023-11-28 09:25:08,310][87424] Updated weights for policy 0, policy_version 351279 (0.0008) -[2023-11-28 09:25:08,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 179765248. Throughput: 0: 2726.9, 1: 2689.5. Samples: 179783316. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:25:08,445][86177] Avg episode reward: [(0, '-574.580'), (1, '-594.390')] -[2023-11-28 09:25:08,695][87424] Updated weights for policy 0, policy_version 351289 (0.0008) -[2023-11-28 09:25:09,599][87426] Updated weights for policy 1, policy_version 350950 (0.0010) -[2023-11-28 09:25:09,975][87426] Updated weights for policy 1, policy_version 350960 (0.0011) -[2023-11-28 09:25:10,358][87426] Updated weights for policy 1, policy_version 350970 (0.0011) -[2023-11-28 09:25:11,187][87424] Updated weights for policy 0, policy_version 351299 (0.0010) -[2023-11-28 09:25:11,571][87424] Updated weights for policy 0, policy_version 351309 (0.0012) -[2023-11-28 09:25:11,957][87424] Updated weights for policy 0, policy_version 351319 (0.0012) -[2023-11-28 09:25:12,446][87426] Updated weights for policy 1, policy_version 350980 (0.0010) -[2023-11-28 09:25:12,823][87426] Updated weights for policy 1, policy_version 350990 (0.0012) -[2023-11-28 09:25:13,210][87426] Updated weights for policy 1, policy_version 351000 (0.0011) -[2023-11-28 09:25:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179789824. Throughput: 0: 2710.8, 1: 2691.2. Samples: 179806996. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:25:13,445][86177] Avg episode reward: [(0, '-555.560'), (1, '-599.980')] -[2023-11-28 09:25:14,344][87424] Updated weights for policy 0, policy_version 351329 (0.0011) -[2023-11-28 09:25:14,718][87424] Updated weights for policy 0, policy_version 351339 (0.0012) -[2023-11-28 09:25:15,102][87424] Updated weights for policy 0, policy_version 351349 (0.0012) -[2023-11-28 09:25:15,482][87424] Updated weights for policy 0, policy_version 351359 (0.0012) -[2023-11-28 09:25:15,704][87426] Updated weights for policy 1, policy_version 351010 (0.0008) -[2023-11-28 09:25:16,091][87426] Updated weights for policy 1, policy_version 351020 (0.0009) -[2023-11-28 09:25:16,475][87426] Updated weights for policy 1, policy_version 351030 (0.0011) -[2023-11-28 09:25:16,848][87426] Updated weights for policy 1, policy_version 351040 (0.0012) -[2023-11-28 09:25:18,013][87424] Updated weights for policy 0, policy_version 351369 (0.0009) -[2023-11-28 09:25:18,394][87424] Updated weights for policy 0, policy_version 351379 (0.0008) -[2023-11-28 09:25:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179814400. Throughput: 0: 2691.3, 1: 2703.6. Samples: 179830896. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:25:18,445][86177] Avg episode reward: [(0, '-563.640'), (1, '-643.020')] -[2023-11-28 09:25:18,771][87424] Updated weights for policy 0, policy_version 351389 (0.0008) -[2023-11-28 09:25:18,885][87426] Updated weights for policy 1, policy_version 351050 (0.0008) -[2023-11-28 09:25:19,266][87426] Updated weights for policy 1, policy_version 351060 (0.0008) -[2023-11-28 09:25:19,632][87426] Updated weights for policy 1, policy_version 351070 (0.0008) -[2023-11-28 09:25:21,107][87424] Updated weights for policy 0, policy_version 351399 (0.0011) -[2023-11-28 09:25:21,476][87424] Updated weights for policy 0, policy_version 351409 (0.0011) -[2023-11-28 09:25:21,724][87426] Updated weights for policy 1, policy_version 351080 (0.0010) -[2023-11-28 09:25:21,855][87424] Updated weights for policy 0, policy_version 351419 (0.0012) -[2023-11-28 09:25:22,107][87426] Updated weights for policy 1, policy_version 351090 (0.0011) -[2023-11-28 09:25:22,478][87426] Updated weights for policy 1, policy_version 351100 (0.0012) -[2023-11-28 09:25:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 179847168. Throughput: 0: 2663.6, 1: 2684.3. Samples: 179861532. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:25:23,445][86177] Avg episode reward: [(0, '-537.630'), (1, '-597.760')] -[2023-11-28 09:25:24,311][87424] Updated weights for policy 0, policy_version 351429 (0.0011) -[2023-11-28 09:25:24,702][87424] Updated weights for policy 0, policy_version 351439 (0.0007) -[2023-11-28 09:25:25,083][87424] Updated weights for policy 0, policy_version 351449 (0.0008) -[2023-11-28 09:25:25,107][87426] Updated weights for policy 1, policy_version 351110 (0.0009) -[2023-11-28 09:25:25,485][87426] Updated weights for policy 1, policy_version 351120 (0.0007) -[2023-11-28 09:25:25,861][87426] Updated weights for policy 1, policy_version 351130 (0.0007) -[2023-11-28 09:25:26,797][87424] Updated weights for policy 0, policy_version 351459 (0.0009) -[2023-11-28 09:25:27,184][87424] Updated weights for policy 0, policy_version 351469 (0.0009) -[2023-11-28 09:25:27,562][87424] Updated weights for policy 0, policy_version 351479 (0.0008) -[2023-11-28 09:25:28,059][87426] Updated weights for policy 1, policy_version 351140 (0.0008) -[2023-11-28 09:25:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179871744. Throughput: 0: 2663.5, 1: 2695.6. Samples: 179886276. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:25:28,444][87426] Updated weights for policy 1, policy_version 351150 (0.0008) -[2023-11-28 09:25:28,445][86177] Avg episode reward: [(0, '-543.570'), (1, '-633.990')] -[2023-11-28 09:25:28,815][87426] Updated weights for policy 1, policy_version 351160 (0.0007) -[2023-11-28 09:25:29,412][87424] Updated weights for policy 0, policy_version 351489 (0.0008) -[2023-11-28 09:25:29,806][87424] Updated weights for policy 0, policy_version 351499 (0.0011) -[2023-11-28 09:25:30,176][87424] Updated weights for policy 0, policy_version 351509 (0.0010) -[2023-11-28 09:25:30,559][87424] Updated weights for policy 0, policy_version 351519 (0.0015) -[2023-11-28 09:25:30,645][87426] Updated weights for policy 1, policy_version 351170 (0.0012) -[2023-11-28 09:25:31,024][87426] Updated weights for policy 1, policy_version 351180 (0.0011) -[2023-11-28 09:25:31,399][87426] Updated weights for policy 1, policy_version 351190 (0.0011) -[2023-11-28 09:25:31,783][87426] Updated weights for policy 1, policy_version 351200 (0.0010) -[2023-11-28 09:25:32,835][87424] Updated weights for policy 0, policy_version 351529 (0.0011) -[2023-11-28 09:25:33,220][87424] Updated weights for policy 0, policy_version 351539 (0.0011) -[2023-11-28 09:25:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179896320. Throughput: 0: 2696.3, 1: 2690.0. Samples: 179910900. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:25:33,445][86177] Avg episode reward: [(0, '-541.440'), (1, '-672.010')] -[2023-11-28 09:25:33,599][87424] Updated weights for policy 0, policy_version 351549 (0.0009) -[2023-11-28 09:25:33,643][87426] Updated weights for policy 1, policy_version 351210 (0.0011) -[2023-11-28 09:25:34,029][87426] Updated weights for policy 1, policy_version 351220 (0.0011) -[2023-11-28 09:25:34,403][87426] Updated weights for policy 1, policy_version 351230 (0.0012) -[2023-11-28 09:25:35,526][87424] Updated weights for policy 0, policy_version 351559 (0.0010) -[2023-11-28 09:25:35,916][87424] Updated weights for policy 0, policy_version 351569 (0.0010) -[2023-11-28 09:25:36,308][87424] Updated weights for policy 0, policy_version 351579 (0.0009) -[2023-11-28 09:25:36,879][87426] Updated weights for policy 1, policy_version 351240 (0.0011) -[2023-11-28 09:25:37,252][87426] Updated weights for policy 1, policy_version 351250 (0.0012) -[2023-11-28 09:25:37,618][87426] Updated weights for policy 1, policy_version 351260 (0.0012) -[2023-11-28 09:25:38,366][87424] Updated weights for policy 0, policy_version 351589 (0.0008) -[2023-11-28 09:25:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 179929088. Throughput: 0: 2720.4, 1: 2713.7. Samples: 179944664. Policy #0 lag: (min: 42.0, avg: 52.6, max: 80.0) -[2023-11-28 09:25:38,445][86177] Avg episode reward: [(0, '-528.760'), (1, '-710.390')] -[2023-11-28 09:25:38,748][87424] Updated weights for policy 0, policy_version 351599 (0.0008) -[2023-11-28 09:25:39,129][87424] Updated weights for policy 0, policy_version 351609 (0.0010) -[2023-11-28 09:25:39,794][87426] Updated weights for policy 1, policy_version 351270 (0.0011) -[2023-11-28 09:25:40,176][87426] Updated weights for policy 1, policy_version 351280 (0.0015) -[2023-11-28 09:25:40,554][87426] Updated weights for policy 1, policy_version 351290 (0.0012) -[2023-11-28 09:25:41,635][87424] Updated weights for policy 0, policy_version 351619 (0.0011) -[2023-11-28 09:25:42,011][87424] Updated weights for policy 0, policy_version 351629 (0.0012) -[2023-11-28 09:25:42,391][87424] Updated weights for policy 0, policy_version 351639 (0.0011) -[2023-11-28 09:25:42,540][87426] Updated weights for policy 1, policy_version 351300 (0.0010) -[2023-11-28 09:25:42,914][87426] Updated weights for policy 1, policy_version 351310 (0.0011) -[2023-11-28 09:25:43,295][87426] Updated weights for policy 1, policy_version 351320 (0.0012) -[2023-11-28 09:25:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 179953664. Throughput: 0: 2707.7, 1: 2717.3. Samples: 179968992. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:25:43,445][86177] Avg episode reward: [(0, '-528.070'), (1, '-763.330')] -[2023-11-28 09:25:44,308][87424] Updated weights for policy 0, policy_version 351649 (0.0008) -[2023-11-28 09:25:44,690][87424] Updated weights for policy 0, policy_version 351659 (0.0007) -[2023-11-28 09:25:45,070][87424] Updated weights for policy 0, policy_version 351669 (0.0009) -[2023-11-28 09:25:45,444][87424] Updated weights for policy 0, policy_version 351679 (0.0012) -[2023-11-28 09:25:45,662][87426] Updated weights for policy 1, policy_version 351330 (0.0010) -[2023-11-28 09:25:46,033][87426] Updated weights for policy 1, policy_version 351340 (0.0011) -[2023-11-28 09:25:46,408][87426] Updated weights for policy 1, policy_version 351350 (0.0012) -[2023-11-28 09:25:46,784][87426] Updated weights for policy 1, policy_version 351360 (0.0008) -[2023-11-28 09:25:47,916][87424] Updated weights for policy 0, policy_version 351689 (0.0011) -[2023-11-28 09:25:48,290][87424] Updated weights for policy 0, policy_version 351699 (0.0007) -[2023-11-28 09:25:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 179978240. Throughput: 0: 2682.0, 1: 2742.2. Samples: 179993808. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:25:48,445][86177] Avg episode reward: [(0, '-523.620'), (1, '-806.080')] -[2023-11-28 09:25:48,671][87424] Updated weights for policy 0, policy_version 351709 (0.0010) -[2023-11-28 09:25:49,153][87426] Updated weights for policy 1, policy_version 351370 (0.0010) -[2023-11-28 09:25:49,526][87426] Updated weights for policy 1, policy_version 351380 (0.0010) -[2023-11-28 09:25:49,910][87426] Updated weights for policy 1, policy_version 351390 (0.0008) -[2023-11-28 09:25:51,030][87424] Updated weights for policy 0, policy_version 351719 (0.0009) -[2023-11-28 09:25:51,413][87424] Updated weights for policy 0, policy_version 351729 (0.0009) -[2023-11-28 09:25:51,787][87424] Updated weights for policy 0, policy_version 351739 (0.0010) -[2023-11-28 09:25:51,797][87426] Updated weights for policy 1, policy_version 351400 (0.0009) -[2023-11-28 09:25:52,173][87426] Updated weights for policy 1, policy_version 351410 (0.0011) -[2023-11-28 09:25:52,559][87426] Updated weights for policy 1, policy_version 351420 (0.0008) -[2023-11-28 09:25:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180011008. Throughput: 0: 2644.3, 1: 2736.9. Samples: 180025468. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:25:53,445][86177] Avg episode reward: [(0, '-523.780'), (1, '-744.620')] -[2023-11-28 09:25:54,240][87424] Updated weights for policy 0, policy_version 351749 (0.0011) -[2023-11-28 09:25:54,624][87424] Updated weights for policy 0, policy_version 351759 (0.0012) -[2023-11-28 09:25:54,914][87426] Updated weights for policy 1, policy_version 351430 (0.0008) -[2023-11-28 09:25:54,997][87424] Updated weights for policy 0, policy_version 351769 (0.0009) -[2023-11-28 09:25:55,293][87426] Updated weights for policy 1, policy_version 351440 (0.0008) -[2023-11-28 09:25:55,669][87426] Updated weights for policy 1, policy_version 351450 (0.0007) -[2023-11-28 09:25:56,914][87424] Updated weights for policy 0, policy_version 351779 (0.0009) -[2023-11-28 09:25:57,299][87424] Updated weights for policy 0, policy_version 351789 (0.0012) -[2023-11-28 09:25:57,668][87426] Updated weights for policy 1, policy_version 351460 (0.0008) -[2023-11-28 09:25:57,682][87424] Updated weights for policy 0, policy_version 351799 (0.0012) -[2023-11-28 09:25:58,047][87426] Updated weights for policy 1, policy_version 351470 (0.0010) -[2023-11-28 09:25:58,430][87426] Updated weights for policy 1, policy_version 351480 (0.0012) -[2023-11-28 09:25:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 180035584. Throughput: 0: 2649.8, 1: 2741.9. Samples: 180049620. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:25:58,445][86177] Avg episode reward: [(0, '-528.900'), (1, '-764.310')] -[2023-11-28 09:25:59,656][87424] Updated weights for policy 0, policy_version 351809 (0.0009) -[2023-11-28 09:26:00,031][87424] Updated weights for policy 0, policy_version 351819 (0.0012) -[2023-11-28 09:26:00,411][87424] Updated weights for policy 0, policy_version 351829 (0.0012) -[2023-11-28 09:26:00,541][87426] Updated weights for policy 1, policy_version 351490 (0.0012) -[2023-11-28 09:26:00,799][87424] Updated weights for policy 0, policy_version 351839 (0.0009) -[2023-11-28 09:26:00,927][87426] Updated weights for policy 1, policy_version 351500 (0.0011) -[2023-11-28 09:26:01,307][87426] Updated weights for policy 1, policy_version 351510 (0.0012) -[2023-11-28 09:26:01,669][87426] Updated weights for policy 1, policy_version 351520 (0.0012) -[2023-11-28 09:26:03,212][87424] Updated weights for policy 0, policy_version 351849 (0.0010) -[2023-11-28 09:26:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 180060160. Throughput: 0: 2685.9, 1: 2741.2. Samples: 180075112. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:03,445][86177] Avg episode reward: [(0, '-543.650'), (1, '-664.490')] -[2023-11-28 09:26:03,603][87424] Updated weights for policy 0, policy_version 351859 (0.0008) -[2023-11-28 09:26:03,767][87426] Updated weights for policy 1, policy_version 351530 (0.0012) -[2023-11-28 09:26:03,973][87424] Updated weights for policy 0, policy_version 351869 (0.0008) -[2023-11-28 09:26:04,147][87426] Updated weights for policy 1, policy_version 351540 (0.0012) -[2023-11-28 09:26:04,519][87426] Updated weights for policy 1, policy_version 351550 (0.0012) -[2023-11-28 09:26:06,118][87424] Updated weights for policy 0, policy_version 351879 (0.0010) -[2023-11-28 09:26:06,338][87426] Updated weights for policy 1, policy_version 351560 (0.0009) -[2023-11-28 09:26:06,493][87424] Updated weights for policy 0, policy_version 351889 (0.0011) -[2023-11-28 09:26:06,716][87426] Updated weights for policy 1, policy_version 351570 (0.0009) -[2023-11-28 09:26:06,875][87424] Updated weights for policy 0, policy_version 351899 (0.0011) -[2023-11-28 09:26:07,102][87426] Updated weights for policy 1, policy_version 351580 (0.0010) -[2023-11-28 09:26:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180092928. Throughput: 0: 2702.1, 1: 2770.6. Samples: 180107804. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:08,445][86177] Avg episode reward: [(0, '-549.880'), (1, '-637.900')] -[2023-11-28 09:26:09,069][87426] Updated weights for policy 1, policy_version 351590 (0.0010) -[2023-11-28 09:26:09,318][87424] Updated weights for policy 0, policy_version 351909 (0.0011) -[2023-11-28 09:26:09,445][87426] Updated weights for policy 1, policy_version 351600 (0.0007) -[2023-11-28 09:26:09,690][87424] Updated weights for policy 0, policy_version 351919 (0.0008) -[2023-11-28 09:26:09,822][87426] Updated weights for policy 1, policy_version 351610 (0.0011) -[2023-11-28 09:26:10,068][87424] Updated weights for policy 0, policy_version 351929 (0.0009) -[2023-11-28 09:26:11,916][87426] Updated weights for policy 1, policy_version 351620 (0.0010) -[2023-11-28 09:26:12,003][87424] Updated weights for policy 0, policy_version 351939 (0.0009) -[2023-11-28 09:26:12,289][87426] Updated weights for policy 1, policy_version 351630 (0.0011) -[2023-11-28 09:26:12,384][87424] Updated weights for policy 0, policy_version 351949 (0.0012) -[2023-11-28 09:26:12,677][87426] Updated weights for policy 1, policy_version 351640 (0.0012) -[2023-11-28 09:26:12,765][87424] Updated weights for policy 0, policy_version 351959 (0.0011) -[2023-11-28 09:26:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 180125696. Throughput: 0: 2714.8, 1: 2743.7. Samples: 180131912. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:13,445][86177] Avg episode reward: [(0, '-547.880'), (1, '-582.500')] -[2023-11-28 09:26:14,761][87426] Updated weights for policy 1, policy_version 351650 (0.0012) -[2023-11-28 09:26:15,133][87426] Updated weights for policy 1, policy_version 351660 (0.0012) -[2023-11-28 09:26:15,203][87424] Updated weights for policy 0, policy_version 351969 (0.0009) -[2023-11-28 09:26:15,514][87426] Updated weights for policy 1, policy_version 351670 (0.0011) -[2023-11-28 09:26:15,578][87424] Updated weights for policy 0, policy_version 351979 (0.0016) -[2023-11-28 09:26:15,895][87426] Updated weights for policy 1, policy_version 351680 (0.0012) -[2023-11-28 09:26:15,966][87424] Updated weights for policy 0, policy_version 351989 (0.0012) -[2023-11-28 09:26:16,351][87424] Updated weights for policy 0, policy_version 351999 (0.0012) -[2023-11-28 09:26:18,118][87426] Updated weights for policy 1, policy_version 351690 (0.0010) -[2023-11-28 09:26:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180142080. Throughput: 0: 2706.8, 1: 2771.4. Samples: 180157420. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:18,445][87424] Updated weights for policy 0, policy_version 352009 (0.0011) -[2023-11-28 09:26:18,445][86177] Avg episode reward: [(0, '-538.410'), (1, '-578.810')] -[2023-11-28 09:26:18,495][87426] Updated weights for policy 1, policy_version 351700 (0.0012) -[2023-11-28 09:26:18,824][87424] Updated weights for policy 0, policy_version 352019 (0.0011) -[2023-11-28 09:26:18,874][87426] Updated weights for policy 1, policy_version 351710 (0.0012) -[2023-11-28 09:26:18,945][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000351712_90038272.pth... -[2023-11-28 09:26:18,987][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000349152_89382912.pth -[2023-11-28 09:26:19,203][87424] Updated weights for policy 0, policy_version 352029 (0.0012) -[2023-11-28 09:26:19,309][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000352032_90120192.pth... -[2023-11-28 09:26:19,357][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000349504_89473024.pth -[2023-11-28 09:26:20,762][87426] Updated weights for policy 1, policy_version 351720 (0.0012) -[2023-11-28 09:26:21,138][87426] Updated weights for policy 1, policy_version 351730 (0.0011) -[2023-11-28 09:26:21,197][87424] Updated weights for policy 0, policy_version 352039 (0.0011) -[2023-11-28 09:26:21,517][87426] Updated weights for policy 1, policy_version 351740 (0.0011) -[2023-11-28 09:26:21,583][87424] Updated weights for policy 0, policy_version 352049 (0.0011) -[2023-11-28 09:26:21,963][87424] Updated weights for policy 0, policy_version 352059 (0.0010) -[2023-11-28 09:26:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180174848. Throughput: 0: 2702.7, 1: 2762.4. Samples: 180190592. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:23,445][86177] Avg episode reward: [(0, '-533.840'), (1, '-577.090')] -[2023-11-28 09:26:23,975][87426] Updated weights for policy 1, policy_version 351750 (0.0011) -[2023-11-28 09:26:24,190][87424] Updated weights for policy 0, policy_version 352069 (0.0008) -[2023-11-28 09:26:24,356][87426] Updated weights for policy 1, policy_version 351760 (0.0011) -[2023-11-28 09:26:24,571][87424] Updated weights for policy 0, policy_version 352079 (0.0009) -[2023-11-28 09:26:24,732][87426] Updated weights for policy 1, policy_version 351770 (0.0011) -[2023-11-28 09:26:24,957][87424] Updated weights for policy 0, policy_version 352089 (0.0008) -[2023-11-28 09:26:26,621][87424] Updated weights for policy 0, policy_version 352099 (0.0011) -[2023-11-28 09:26:27,001][87424] Updated weights for policy 0, policy_version 352109 (0.0012) -[2023-11-28 09:26:27,280][87426] Updated weights for policy 1, policy_version 351780 (0.0010) -[2023-11-28 09:26:27,367][87424] Updated weights for policy 0, policy_version 352119 (0.0011) -[2023-11-28 09:26:27,652][87426] Updated weights for policy 1, policy_version 351790 (0.0011) -[2023-11-28 09:26:28,034][87426] Updated weights for policy 1, policy_version 351800 (0.0012) -[2023-11-28 09:26:28,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 180207616. Throughput: 0: 2724.2, 1: 2774.5. Samples: 180216432. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:28,445][86177] Avg episode reward: [(0, '-534.590'), (1, '-598.870')] -[2023-11-28 09:26:29,483][87424] Updated weights for policy 0, policy_version 352129 (0.0011) -[2023-11-28 09:26:29,872][87424] Updated weights for policy 0, policy_version 352139 (0.0010) -[2023-11-28 09:26:30,260][87424] Updated weights for policy 0, policy_version 352149 (0.0008) -[2023-11-28 09:26:30,346][87426] Updated weights for policy 1, policy_version 351810 (0.0012) -[2023-11-28 09:26:30,638][87424] Updated weights for policy 0, policy_version 352159 (0.0010) -[2023-11-28 09:26:30,713][87426] Updated weights for policy 1, policy_version 351820 (0.0011) -[2023-11-28 09:26:31,093][87426] Updated weights for policy 1, policy_version 351830 (0.0012) -[2023-11-28 09:26:31,467][87426] Updated weights for policy 1, policy_version 351840 (0.0012) -[2023-11-28 09:26:32,911][87424] Updated weights for policy 0, policy_version 352169 (0.0012) -[2023-11-28 09:26:33,292][87424] Updated weights for policy 0, policy_version 352179 (0.0012) -[2023-11-28 09:26:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180224000. Throughput: 0: 2752.9, 1: 2758.5. Samples: 180241820. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:33,445][86177] Avg episode reward: [(0, '-536.300'), (1, '-597.980')] -[2023-11-28 09:26:33,670][87424] Updated weights for policy 0, policy_version 352189 (0.0011) -[2023-11-28 09:26:33,861][87426] Updated weights for policy 1, policy_version 351850 (0.0011) -[2023-11-28 09:26:34,232][87426] Updated weights for policy 1, policy_version 351860 (0.0007) -[2023-11-28 09:26:34,600][87426] Updated weights for policy 1, policy_version 351870 (0.0010) -[2023-11-28 09:26:35,929][87424] Updated weights for policy 0, policy_version 352199 (0.0007) -[2023-11-28 09:26:36,307][87424] Updated weights for policy 0, policy_version 352209 (0.0007) -[2023-11-28 09:26:36,690][87424] Updated weights for policy 0, policy_version 352219 (0.0008) -[2023-11-28 09:26:36,853][87426] Updated weights for policy 1, policy_version 351880 (0.0010) -[2023-11-28 09:26:37,239][87426] Updated weights for policy 1, policy_version 351890 (0.0008) -[2023-11-28 09:26:37,614][87426] Updated weights for policy 1, policy_version 351900 (0.0010) -[2023-11-28 09:26:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 180256768. Throughput: 0: 2772.7, 1: 2744.3. Samples: 180273736. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:38,446][86177] Avg episode reward: [(0, '-567.010'), (1, '-626.790')] -[2023-11-28 09:26:38,703][87424] Updated weights for policy 0, policy_version 352229 (0.0011) -[2023-11-28 09:26:39,083][87424] Updated weights for policy 0, policy_version 352239 (0.0011) -[2023-11-28 09:26:39,467][87424] Updated weights for policy 0, policy_version 352249 (0.0012) -[2023-11-28 09:26:39,999][87426] Updated weights for policy 1, policy_version 351910 (0.0011) -[2023-11-28 09:26:40,393][87426] Updated weights for policy 1, policy_version 351920 (0.0012) -[2023-11-28 09:26:40,758][87426] Updated weights for policy 1, policy_version 351930 (0.0012) -[2023-11-28 09:26:41,595][87424] Updated weights for policy 0, policy_version 352259 (0.0011) -[2023-11-28 09:26:41,973][87424] Updated weights for policy 0, policy_version 352269 (0.0011) -[2023-11-28 09:26:42,357][87424] Updated weights for policy 0, policy_version 352279 (0.0012) -[2023-11-28 09:26:43,158][87426] Updated weights for policy 1, policy_version 351940 (0.0012) -[2023-11-28 09:26:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 180281344. Throughput: 0: 2783.1, 1: 2727.6. Samples: 180297600. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:43,445][86177] Avg episode reward: [(0, '-578.900'), (1, '-667.710')] -[2023-11-28 09:26:43,534][87426] Updated weights for policy 1, policy_version 351950 (0.0011) -[2023-11-28 09:26:43,910][87426] Updated weights for policy 1, policy_version 351960 (0.0008) -[2023-11-28 09:26:44,732][87424] Updated weights for policy 0, policy_version 352289 (0.0012) -[2023-11-28 09:26:45,118][87424] Updated weights for policy 0, policy_version 352299 (0.0008) -[2023-11-28 09:26:45,518][87424] Updated weights for policy 0, policy_version 352309 (0.0011) -[2023-11-28 09:26:45,656][87426] Updated weights for policy 1, policy_version 351970 (0.0008) -[2023-11-28 09:26:45,892][87424] Updated weights for policy 0, policy_version 352319 (0.0011) -[2023-11-28 09:26:46,033][87426] Updated weights for policy 1, policy_version 351980 (0.0011) -[2023-11-28 09:26:46,409][87426] Updated weights for policy 1, policy_version 351990 (0.0012) -[2023-11-28 09:26:46,783][87426] Updated weights for policy 1, policy_version 352000 (0.0012) -[2023-11-28 09:26:48,410][87424] Updated weights for policy 0, policy_version 352329 (0.0012) -[2023-11-28 09:26:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180305920. Throughput: 0: 2766.7, 1: 2717.8. Samples: 180321916. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:48,445][86177] Avg episode reward: [(0, '-570.060'), (1, '-627.630')] -[2023-11-28 09:26:48,564][87426] Updated weights for policy 1, policy_version 352010 (0.0011) -[2023-11-28 09:26:48,794][87424] Updated weights for policy 0, policy_version 352339 (0.0011) -[2023-11-28 09:26:48,938][87426] Updated weights for policy 1, policy_version 352020 (0.0010) -[2023-11-28 09:26:49,173][87424] Updated weights for policy 0, policy_version 352349 (0.0012) -[2023-11-28 09:26:49,313][87426] Updated weights for policy 1, policy_version 352030 (0.0011) -[2023-11-28 09:26:51,075][87424] Updated weights for policy 0, policy_version 352359 (0.0012) -[2023-11-28 09:26:51,265][87426] Updated weights for policy 1, policy_version 352040 (0.0010) -[2023-11-28 09:26:51,456][87424] Updated weights for policy 0, policy_version 352369 (0.0012) -[2023-11-28 09:26:51,646][87426] Updated weights for policy 1, policy_version 352050 (0.0011) -[2023-11-28 09:26:51,835][87424] Updated weights for policy 0, policy_version 352379 (0.0012) -[2023-11-28 09:26:52,018][87426] Updated weights for policy 1, policy_version 352060 (0.0010) -[2023-11-28 09:26:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 180338688. Throughput: 0: 2769.1, 1: 2708.2. Samples: 180354280. Policy #0 lag: (min: 31.0, avg: 42.4, max: 63.0) -[2023-11-28 09:26:53,445][86177] Avg episode reward: [(0, '-571.500'), (1, '-627.970')] -[2023-11-28 09:26:54,232][87424] Updated weights for policy 0, policy_version 352389 (0.0009) -[2023-11-28 09:26:54,613][87424] Updated weights for policy 0, policy_version 352399 (0.0009) -[2023-11-28 09:26:54,683][87426] Updated weights for policy 1, policy_version 352070 (0.0011) -[2023-11-28 09:26:54,994][87424] Updated weights for policy 0, policy_version 352409 (0.0012) -[2023-11-28 09:26:55,055][87426] Updated weights for policy 1, policy_version 352080 (0.0010) -[2023-11-28 09:26:55,432][87426] Updated weights for policy 1, policy_version 352090 (0.0008) -[2023-11-28 09:26:57,291][87424] Updated weights for policy 0, policy_version 352419 (0.0009) -[2023-11-28 09:26:57,662][87426] Updated weights for policy 1, policy_version 352100 (0.0009) -[2023-11-28 09:26:57,664][87424] Updated weights for policy 0, policy_version 352429 (0.0011) -[2023-11-28 09:26:58,029][87426] Updated weights for policy 1, policy_version 352110 (0.0010) -[2023-11-28 09:26:58,054][87424] Updated weights for policy 0, policy_version 352439 (0.0010) -[2023-11-28 09:26:58,410][87426] Updated weights for policy 1, policy_version 352120 (0.0009) -[2023-11-28 09:26:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 180363264. Throughput: 0: 2752.4, 1: 2709.3. Samples: 180377692. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:26:58,445][86177] Avg episode reward: [(0, '-547.440'), (1, '-587.780')] -[2023-11-28 09:26:59,967][87424] Updated weights for policy 0, policy_version 352449 (0.0010) -[2023-11-28 09:27:00,356][87424] Updated weights for policy 0, policy_version 352459 (0.0011) -[2023-11-28 09:27:00,736][87424] Updated weights for policy 0, policy_version 352469 (0.0008) -[2023-11-28 09:27:00,997][87426] Updated weights for policy 1, policy_version 352130 (0.0008) -[2023-11-28 09:27:01,128][87424] Updated weights for policy 0, policy_version 352479 (0.0008) -[2023-11-28 09:27:01,382][87426] Updated weights for policy 1, policy_version 352140 (0.0011) -[2023-11-28 09:27:01,752][87426] Updated weights for policy 1, policy_version 352150 (0.0009) -[2023-11-28 09:27:02,133][87426] Updated weights for policy 1, policy_version 352160 (0.0011) -[2023-11-28 09:27:03,443][87424] Updated weights for policy 0, policy_version 352489 (0.0011) -[2023-11-28 09:27:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180387840. Throughput: 0: 2740.4, 1: 2686.4. Samples: 180401624. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:03,445][86177] Avg episode reward: [(0, '-539.210'), (1, '-552.740')] -[2023-11-28 09:27:03,815][87424] Updated weights for policy 0, policy_version 352499 (0.0012) -[2023-11-28 09:27:04,197][87424] Updated weights for policy 0, policy_version 352509 (0.0011) -[2023-11-28 09:27:04,647][87426] Updated weights for policy 1, policy_version 352170 (0.0012) -[2023-11-28 09:27:05,032][87426] Updated weights for policy 1, policy_version 352180 (0.0012) -[2023-11-28 09:27:05,403][87426] Updated weights for policy 1, policy_version 352190 (0.0011) -[2023-11-28 09:27:06,349][87424] Updated weights for policy 0, policy_version 352519 (0.0012) -[2023-11-28 09:27:06,734][87424] Updated weights for policy 0, policy_version 352529 (0.0011) -[2023-11-28 09:27:07,121][87424] Updated weights for policy 0, policy_version 352539 (0.0012) -[2023-11-28 09:27:07,191][87426] Updated weights for policy 1, policy_version 352200 (0.0010) -[2023-11-28 09:27:07,574][87426] Updated weights for policy 1, policy_version 352210 (0.0010) -[2023-11-28 09:27:07,950][87426] Updated weights for policy 1, policy_version 352220 (0.0011) -[2023-11-28 09:27:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 180420608. Throughput: 0: 2735.1, 1: 2669.8. Samples: 180433812. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:08,445][86177] Avg episode reward: [(0, '-549.850'), (1, '-557.650')] -[2023-11-28 09:27:09,214][87424] Updated weights for policy 0, policy_version 352549 (0.0009) -[2023-11-28 09:27:09,604][87424] Updated weights for policy 0, policy_version 352559 (0.0010) -[2023-11-28 09:27:09,641][87426] Updated weights for policy 1, policy_version 352230 (0.0011) -[2023-11-28 09:27:09,994][87424] Updated weights for policy 0, policy_version 352569 (0.0010) -[2023-11-28 09:27:10,015][87426] Updated weights for policy 1, policy_version 352240 (0.0010) -[2023-11-28 09:27:10,401][87426] Updated weights for policy 1, policy_version 352250 (0.0011) -[2023-11-28 09:27:12,550][87424] Updated weights for policy 0, policy_version 352579 (0.0011) -[2023-11-28 09:27:12,567][87426] Updated weights for policy 1, policy_version 352260 (0.0010) -[2023-11-28 09:27:12,931][87424] Updated weights for policy 0, policy_version 352589 (0.0011) -[2023-11-28 09:27:12,932][87426] Updated weights for policy 1, policy_version 352270 (0.0012) -[2023-11-28 09:27:13,309][87426] Updated weights for policy 1, policy_version 352280 (0.0011) -[2023-11-28 09:27:13,313][87424] Updated weights for policy 0, policy_version 352599 (0.0011) -[2023-11-28 09:27:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 180436992. Throughput: 0: 2712.2, 1: 2657.5. Samples: 180458068. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:13,445][86177] Avg episode reward: [(0, '-551.420'), (1, '-594.270')] -[2023-11-28 09:27:15,208][87426] Updated weights for policy 1, policy_version 352290 (0.0011) -[2023-11-28 09:27:15,591][87426] Updated weights for policy 1, policy_version 352300 (0.0012) -[2023-11-28 09:27:15,773][87424] Updated weights for policy 0, policy_version 352609 (0.0010) -[2023-11-28 09:27:15,975][87426] Updated weights for policy 1, policy_version 352310 (0.0011) -[2023-11-28 09:27:16,155][87424] Updated weights for policy 0, policy_version 352619 (0.0009) -[2023-11-28 09:27:16,345][87426] Updated weights for policy 1, policy_version 352320 (0.0010) -[2023-11-28 09:27:16,548][87424] Updated weights for policy 0, policy_version 352629 (0.0008) -[2023-11-28 09:27:16,927][87424] Updated weights for policy 0, policy_version 352639 (0.0008) -[2023-11-28 09:27:18,314][87426] Updated weights for policy 1, policy_version 352330 (0.0009) -[2023-11-28 09:27:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180469760. Throughput: 0: 2662.7, 1: 2674.0. Samples: 180481972. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:18,446][86177] Avg episode reward: [(0, '-559.240'), (1, '-562.470')] -[2023-11-28 09:27:18,699][87426] Updated weights for policy 1, policy_version 352340 (0.0009) -[2023-11-28 09:27:18,836][87424] Updated weights for policy 0, policy_version 352649 (0.0010) -[2023-11-28 09:27:19,078][87426] Updated weights for policy 1, policy_version 352350 (0.0011) -[2023-11-28 09:27:19,214][87424] Updated weights for policy 0, policy_version 352659 (0.0011) -[2023-11-28 09:27:19,590][87424] Updated weights for policy 0, policy_version 352669 (0.0009) -[2023-11-28 09:27:21,687][87426] Updated weights for policy 1, policy_version 352360 (0.0011) -[2023-11-28 09:27:21,843][87424] Updated weights for policy 0, policy_version 352679 (0.0010) -[2023-11-28 09:27:22,063][87426] Updated weights for policy 1, policy_version 352370 (0.0011) -[2023-11-28 09:27:22,253][87424] Updated weights for policy 0, policy_version 352689 (0.0012) -[2023-11-28 09:27:22,439][87426] Updated weights for policy 1, policy_version 352380 (0.0011) -[2023-11-28 09:27:22,620][87424] Updated weights for policy 0, policy_version 352699 (0.0011) -[2023-11-28 09:27:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 180502528. Throughput: 0: 2666.7, 1: 2682.7. Samples: 180514456. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:23,445][86177] Avg episode reward: [(0, '-547.000'), (1, '-555.100')] -[2023-11-28 09:27:24,726][87424] Updated weights for policy 0, policy_version 352709 (0.0011) -[2023-11-28 09:27:25,050][87426] Updated weights for policy 1, policy_version 352390 (0.0012) -[2023-11-28 09:27:25,104][87424] Updated weights for policy 0, policy_version 352719 (0.0009) -[2023-11-28 09:27:25,429][87426] Updated weights for policy 1, policy_version 352400 (0.0011) -[2023-11-28 09:27:25,484][87424] Updated weights for policy 0, policy_version 352729 (0.0012) -[2023-11-28 09:27:25,811][87426] Updated weights for policy 1, policy_version 352410 (0.0012) -[2023-11-28 09:27:27,482][87426] Updated weights for policy 1, policy_version 352420 (0.0012) -[2023-11-28 09:27:27,863][87426] Updated weights for policy 1, policy_version 352430 (0.0011) -[2023-11-28 09:27:27,962][87424] Updated weights for policy 0, policy_version 352739 (0.0012) -[2023-11-28 09:27:28,246][87426] Updated weights for policy 1, policy_version 352440 (0.0011) -[2023-11-28 09:27:28,337][87424] Updated weights for policy 0, policy_version 352749 (0.0011) -[2023-11-28 09:27:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 180518912. Throughput: 0: 2655.8, 1: 2717.2. Samples: 180539388. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:28,445][86177] Avg episode reward: [(0, '-544.190'), (1, '-516.150')] -[2023-11-28 09:27:28,718][87424] Updated weights for policy 0, policy_version 352759 (0.0012) -[2023-11-28 09:27:30,708][87426] Updated weights for policy 1, policy_version 352450 (0.0012) -[2023-11-28 09:27:31,094][87426] Updated weights for policy 1, policy_version 352460 (0.0012) -[2023-11-28 09:27:31,252][87424] Updated weights for policy 0, policy_version 352769 (0.0010) -[2023-11-28 09:27:31,465][87426] Updated weights for policy 1, policy_version 352470 (0.0011) -[2023-11-28 09:27:31,628][87424] Updated weights for policy 0, policy_version 352779 (0.0008) -[2023-11-28 09:27:31,844][87426] Updated weights for policy 1, policy_version 352480 (0.0011) -[2023-11-28 09:27:32,002][87424] Updated weights for policy 0, policy_version 352789 (0.0010) -[2023-11-28 09:27:32,381][87424] Updated weights for policy 0, policy_version 352799 (0.0011) -[2023-11-28 09:27:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 180551680. Throughput: 0: 2639.4, 1: 2727.2. Samples: 180563412. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:33,445][86177] Avg episode reward: [(0, '-562.730'), (1, '-515.350')] -[2023-11-28 09:27:33,776][87426] Updated weights for policy 1, policy_version 352490 (0.0011) -[2023-11-28 09:27:34,147][87426] Updated weights for policy 1, policy_version 352500 (0.0011) -[2023-11-28 09:27:34,532][87426] Updated weights for policy 1, policy_version 352510 (0.0009) -[2023-11-28 09:27:34,618][87424] Updated weights for policy 0, policy_version 352809 (0.0010) -[2023-11-28 09:27:34,989][87424] Updated weights for policy 0, policy_version 352819 (0.0012) -[2023-11-28 09:27:35,359][87424] Updated weights for policy 0, policy_version 352829 (0.0009) -[2023-11-28 09:27:37,041][87426] Updated weights for policy 1, policy_version 352520 (0.0010) -[2023-11-28 09:27:37,423][87426] Updated weights for policy 1, policy_version 352530 (0.0007) -[2023-11-28 09:27:37,808][87426] Updated weights for policy 1, policy_version 352540 (0.0007) -[2023-11-28 09:27:37,875][87424] Updated weights for policy 0, policy_version 352839 (0.0010) -[2023-11-28 09:27:38,264][87424] Updated weights for policy 0, policy_version 352849 (0.0007) -[2023-11-28 09:27:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 180576256. Throughput: 0: 2624.8, 1: 2734.7. Samples: 180595456. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:38,445][86177] Avg episode reward: [(0, '-551.040'), (1, '-517.870')] -[2023-11-28 09:27:38,645][87424] Updated weights for policy 0, policy_version 352859 (0.0008) -[2023-11-28 09:27:40,044][87426] Updated weights for policy 1, policy_version 352550 (0.0010) -[2023-11-28 09:27:40,444][87426] Updated weights for policy 1, policy_version 352560 (0.0011) -[2023-11-28 09:27:40,553][87424] Updated weights for policy 0, policy_version 352869 (0.0010) -[2023-11-28 09:27:40,810][87426] Updated weights for policy 1, policy_version 352570 (0.0011) -[2023-11-28 09:27:40,930][87424] Updated weights for policy 0, policy_version 352879 (0.0011) -[2023-11-28 09:27:41,319][87424] Updated weights for policy 0, policy_version 352889 (0.0009) -[2023-11-28 09:27:43,343][87426] Updated weights for policy 1, policy_version 352580 (0.0010) -[2023-11-28 09:27:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 180600832. Throughput: 0: 2638.8, 1: 2720.3. Samples: 180618852. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:43,445][86177] Avg episode reward: [(0, '-557.940'), (1, '-522.280')] -[2023-11-28 09:27:43,708][87424] Updated weights for policy 0, policy_version 352899 (0.0010) -[2023-11-28 09:27:43,736][87426] Updated weights for policy 1, policy_version 352590 (0.0011) -[2023-11-28 09:27:44,088][87424] Updated weights for policy 0, policy_version 352909 (0.0007) -[2023-11-28 09:27:44,104][87426] Updated weights for policy 1, policy_version 352600 (0.0011) -[2023-11-28 09:27:44,468][87424] Updated weights for policy 0, policy_version 352919 (0.0007) -[2023-11-28 09:27:46,675][87426] Updated weights for policy 1, policy_version 352610 (0.0011) -[2023-11-28 09:27:46,924][87424] Updated weights for policy 0, policy_version 352929 (0.0007) -[2023-11-28 09:27:47,057][87426] Updated weights for policy 1, policy_version 352620 (0.0011) -[2023-11-28 09:27:47,303][87424] Updated weights for policy 0, policy_version 352939 (0.0007) -[2023-11-28 09:27:47,435][87426] Updated weights for policy 1, policy_version 352630 (0.0011) -[2023-11-28 09:27:47,692][87424] Updated weights for policy 0, policy_version 352949 (0.0008) -[2023-11-28 09:27:47,812][87426] Updated weights for policy 1, policy_version 352640 (0.0012) -[2023-11-28 09:27:48,064][87424] Updated weights for policy 0, policy_version 352959 (0.0008) -[2023-11-28 09:27:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 180633600. Throughput: 0: 2620.9, 1: 2734.0. Samples: 180642596. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:48,445][86177] Avg episode reward: [(0, '-549.820'), (1, '-521.450')] -[2023-11-28 09:27:49,572][87426] Updated weights for policy 1, policy_version 352650 (0.0012) -[2023-11-28 09:27:49,942][87426] Updated weights for policy 1, policy_version 352660 (0.0010) -[2023-11-28 09:27:50,324][87426] Updated weights for policy 1, policy_version 352670 (0.0008) -[2023-11-28 09:27:50,704][87424] Updated weights for policy 0, policy_version 352969 (0.0011) -[2023-11-28 09:27:51,093][87424] Updated weights for policy 0, policy_version 352979 (0.0012) -[2023-11-28 09:27:51,465][87424] Updated weights for policy 0, policy_version 352989 (0.0012) -[2023-11-28 09:27:52,156][87426] Updated weights for policy 1, policy_version 352680 (0.0009) -[2023-11-28 09:27:52,534][87426] Updated weights for policy 1, policy_version 352690 (0.0011) -[2023-11-28 09:27:52,918][87426] Updated weights for policy 1, policy_version 352700 (0.0010) -[2023-11-28 09:27:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 180658176. Throughput: 0: 2594.1, 1: 2758.5. Samples: 180674680. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:53,445][86177] Avg episode reward: [(0, '-555.420'), (1, '-525.920')] -[2023-11-28 09:27:53,633][87424] Updated weights for policy 0, policy_version 352999 (0.0011) -[2023-11-28 09:27:54,007][87424] Updated weights for policy 0, policy_version 353009 (0.0010) -[2023-11-28 09:27:54,394][87424] Updated weights for policy 0, policy_version 353019 (0.0010) -[2023-11-28 09:27:55,304][87426] Updated weights for policy 1, policy_version 352710 (0.0012) -[2023-11-28 09:27:55,695][87426] Updated weights for policy 1, policy_version 352720 (0.0012) -[2023-11-28 09:27:56,072][87426] Updated weights for policy 1, policy_version 352730 (0.0012) -[2023-11-28 09:27:56,313][87424] Updated weights for policy 0, policy_version 353029 (0.0011) -[2023-11-28 09:27:56,695][87424] Updated weights for policy 0, policy_version 353039 (0.0012) -[2023-11-28 09:27:57,079][87424] Updated weights for policy 0, policy_version 353049 (0.0012) -[2023-11-28 09:27:58,037][87426] Updated weights for policy 1, policy_version 352740 (0.0012) -[2023-11-28 09:27:58,410][87426] Updated weights for policy 1, policy_version 352750 (0.0011) -[2023-11-28 09:27:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 180682752. Throughput: 0: 2610.0, 1: 2761.1. Samples: 180699772. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:27:58,446][86177] Avg episode reward: [(0, '-539.890'), (1, '-518.860')] -[2023-11-28 09:27:58,793][87426] Updated weights for policy 1, policy_version 352760 (0.0012) -[2023-11-28 09:27:59,133][87424] Updated weights for policy 0, policy_version 353059 (0.0012) -[2023-11-28 09:27:59,506][87424] Updated weights for policy 0, policy_version 353069 (0.0012) -[2023-11-28 09:27:59,895][87424] Updated weights for policy 0, policy_version 353079 (0.0012) -[2023-11-28 09:28:00,734][87426] Updated weights for policy 1, policy_version 352770 (0.0011) -[2023-11-28 09:28:01,113][87426] Updated weights for policy 1, policy_version 352780 (0.0012) -[2023-11-28 09:28:01,488][87426] Updated weights for policy 1, policy_version 352790 (0.0012) -[2023-11-28 09:28:01,865][87426] Updated weights for policy 1, policy_version 352800 (0.0012) -[2023-11-28 09:28:01,943][87424] Updated weights for policy 0, policy_version 353089 (0.0012) -[2023-11-28 09:28:02,324][87424] Updated weights for policy 0, policy_version 353099 (0.0009) -[2023-11-28 09:28:02,700][87424] Updated weights for policy 0, policy_version 353109 (0.0008) -[2023-11-28 09:28:03,085][87424] Updated weights for policy 0, policy_version 353119 (0.0010) -[2023-11-28 09:28:03,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180715520. Throughput: 0: 2652.5, 1: 2734.9. Samples: 180724408. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:28:03,446][86177] Avg episode reward: [(0, '-539.410'), (1, '-522.550')] -[2023-11-28 09:28:04,297][87426] Updated weights for policy 1, policy_version 352810 (0.0012) -[2023-11-28 09:28:04,675][87426] Updated weights for policy 1, policy_version 352820 (0.0012) -[2023-11-28 09:28:05,045][87424] Updated weights for policy 0, policy_version 353129 (0.0011) -[2023-11-28 09:28:05,053][87426] Updated weights for policy 1, policy_version 352830 (0.0011) -[2023-11-28 09:28:05,422][87424] Updated weights for policy 0, policy_version 353139 (0.0012) -[2023-11-28 09:28:05,810][87424] Updated weights for policy 0, policy_version 353149 (0.0012) -[2023-11-28 09:28:07,712][87426] Updated weights for policy 1, policy_version 352840 (0.0012) -[2023-11-28 09:28:08,090][87426] Updated weights for policy 1, policy_version 352850 (0.0011) -[2023-11-28 09:28:08,350][87424] Updated weights for policy 0, policy_version 353159 (0.0007) -[2023-11-28 09:28:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 180731904. Throughput: 0: 2639.9, 1: 2724.1. Samples: 180755836. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:28:08,445][86177] Avg episode reward: [(0, '-544.300'), (1, '-522.550')] -[2023-11-28 09:28:08,467][87426] Updated weights for policy 1, policy_version 352860 (0.0011) -[2023-11-28 09:28:08,732][87424] Updated weights for policy 0, policy_version 353169 (0.0008) -[2023-11-28 09:28:09,121][87424] Updated weights for policy 0, policy_version 353179 (0.0011) -[2023-11-28 09:28:10,940][87426] Updated weights for policy 1, policy_version 352870 (0.0012) -[2023-11-28 09:28:11,290][87424] Updated weights for policy 0, policy_version 353189 (0.0011) -[2023-11-28 09:28:11,314][87426] Updated weights for policy 1, policy_version 352880 (0.0010) -[2023-11-28 09:28:11,661][87424] Updated weights for policy 0, policy_version 353199 (0.0008) -[2023-11-28 09:28:11,689][87426] Updated weights for policy 1, policy_version 352890 (0.0011) -[2023-11-28 09:28:12,044][87424] Updated weights for policy 0, policy_version 353209 (0.0010) -[2023-11-28 09:28:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180764672. Throughput: 0: 2646.6, 1: 2697.4. Samples: 180779868. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:28:13,445][86177] Avg episode reward: [(0, '-529.340'), (1, '-524.060')] -[2023-11-28 09:28:13,836][87426] Updated weights for policy 1, policy_version 352900 (0.0012) -[2023-11-28 09:28:14,112][87424] Updated weights for policy 0, policy_version 353219 (0.0010) -[2023-11-28 09:28:14,206][87426] Updated weights for policy 1, policy_version 352910 (0.0012) -[2023-11-28 09:28:14,483][87424] Updated weights for policy 0, policy_version 353229 (0.0008) -[2023-11-28 09:28:14,587][87426] Updated weights for policy 1, policy_version 352920 (0.0012) -[2023-11-28 09:28:14,873][87424] Updated weights for policy 0, policy_version 353239 (0.0007) -[2023-11-28 09:28:16,972][87426] Updated weights for policy 1, policy_version 352930 (0.0010) -[2023-11-28 09:28:17,277][87424] Updated weights for policy 0, policy_version 353249 (0.0007) -[2023-11-28 09:28:17,353][87426] Updated weights for policy 1, policy_version 352940 (0.0011) -[2023-11-28 09:28:17,658][87424] Updated weights for policy 0, policy_version 353259 (0.0007) -[2023-11-28 09:28:17,736][87426] Updated weights for policy 1, policy_version 352950 (0.0011) -[2023-11-28 09:28:18,038][87424] Updated weights for policy 0, policy_version 353269 (0.0007) -[2023-11-28 09:28:18,106][87426] Updated weights for policy 1, policy_version 352960 (0.0010) -[2023-11-28 09:28:18,419][87424] Updated weights for policy 0, policy_version 353279 (0.0007) -[2023-11-28 09:28:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 180789248. Throughput: 0: 2661.7, 1: 2687.8. Samples: 180804140. Policy #0 lag: (min: 31.0, avg: 47.4, max: 63.0) -[2023-11-28 09:28:18,445][86177] Avg episode reward: [(0, '-536.010'), (1, '-524.830')] -[2023-11-28 09:28:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000352960_90357760.pth... -[2023-11-28 09:28:18,460][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000353280_90439680.pth... -[2023-11-28 09:28:18,491][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000350752_89792512.pth -[2023-11-28 09:28:18,504][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000350432_89710592.pth -[2023-11-28 09:28:20,366][87426] Updated weights for policy 1, policy_version 352970 (0.0011) -[2023-11-28 09:28:20,643][87424] Updated weights for policy 0, policy_version 353289 (0.0009) -[2023-11-28 09:28:20,744][87426] Updated weights for policy 1, policy_version 352980 (0.0009) -[2023-11-28 09:28:21,030][87424] Updated weights for policy 0, policy_version 353299 (0.0008) -[2023-11-28 09:28:21,125][87426] Updated weights for policy 1, policy_version 352990 (0.0010) -[2023-11-28 09:28:21,416][87424] Updated weights for policy 0, policy_version 353309 (0.0011) -[2023-11-28 09:28:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 180813824. Throughput: 0: 2667.8, 1: 2662.2. Samples: 180835308. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:28:23,445][86177] Avg episode reward: [(0, '-529.310'), (1, '-526.940')] -[2023-11-28 09:28:23,622][87426] Updated weights for policy 1, policy_version 353000 (0.0011) -[2023-11-28 09:28:23,813][87424] Updated weights for policy 0, policy_version 353319 (0.0011) -[2023-11-28 09:28:23,998][87426] Updated weights for policy 1, policy_version 353010 (0.0009) -[2023-11-28 09:28:24,186][87424] Updated weights for policy 0, policy_version 353329 (0.0012) -[2023-11-28 09:28:24,382][87426] Updated weights for policy 1, policy_version 353020 (0.0010) -[2023-11-28 09:28:24,569][87424] Updated weights for policy 0, policy_version 353339 (0.0012) -[2023-11-28 09:28:26,182][87426] Updated weights for policy 1, policy_version 353030 (0.0011) -[2023-11-28 09:28:26,562][87426] Updated weights for policy 1, policy_version 353040 (0.0012) -[2023-11-28 09:28:26,713][87424] Updated weights for policy 0, policy_version 353349 (0.0012) -[2023-11-28 09:28:26,932][87426] Updated weights for policy 1, policy_version 353050 (0.0009) -[2023-11-28 09:28:27,102][87424] Updated weights for policy 0, policy_version 353359 (0.0012) -[2023-11-28 09:28:27,477][87424] Updated weights for policy 0, policy_version 353369 (0.0012) -[2023-11-28 09:28:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180846592. Throughput: 0: 2662.7, 1: 2696.4. Samples: 180860008. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:28:28,445][86177] Avg episode reward: [(0, '-528.740'), (1, '-527.280')] -[2023-11-28 09:28:29,352][87426] Updated weights for policy 1, policy_version 353060 (0.0008) -[2023-11-28 09:28:29,442][87424] Updated weights for policy 0, policy_version 353379 (0.0012) -[2023-11-28 09:28:29,731][87426] Updated weights for policy 1, policy_version 353070 (0.0010) -[2023-11-28 09:28:29,821][87424] Updated weights for policy 0, policy_version 353389 (0.0010) -[2023-11-28 09:28:30,112][87426] Updated weights for policy 1, policy_version 353080 (0.0011) -[2023-11-28 09:28:30,215][87424] Updated weights for policy 0, policy_version 353399 (0.0008) -[2023-11-28 09:28:32,341][87426] Updated weights for policy 1, policy_version 353090 (0.0012) -[2023-11-28 09:28:32,342][87424] Updated weights for policy 0, policy_version 353409 (0.0009) -[2023-11-28 09:28:32,722][87424] Updated weights for policy 0, policy_version 353419 (0.0011) -[2023-11-28 09:28:32,726][87426] Updated weights for policy 1, policy_version 353100 (0.0009) -[2023-11-28 09:28:33,101][87426] Updated weights for policy 1, policy_version 353110 (0.0008) -[2023-11-28 09:28:33,104][87424] Updated weights for policy 0, policy_version 353429 (0.0010) -[2023-11-28 09:28:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 180862976. Throughput: 0: 2714.2, 1: 2690.0. Samples: 180885784. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:28:33,445][86177] Avg episode reward: [(0, '-529.610'), (1, '-520.040')] -[2023-11-28 09:28:33,488][87424] Updated weights for policy 0, policy_version 353439 (0.0011) -[2023-11-28 09:28:33,490][87426] Updated weights for policy 1, policy_version 353120 (0.0008) -[2023-11-28 09:28:35,476][87426] Updated weights for policy 1, policy_version 353130 (0.0011) -[2023-11-28 09:28:35,490][87424] Updated weights for policy 0, policy_version 353449 (0.0008) -[2023-11-28 09:28:35,851][87426] Updated weights for policy 1, policy_version 353140 (0.0011) -[2023-11-28 09:28:35,871][87424] Updated weights for policy 0, policy_version 353459 (0.0010) -[2023-11-28 09:28:36,222][87426] Updated weights for policy 1, policy_version 353150 (0.0011) -[2023-11-28 09:28:36,246][87424] Updated weights for policy 0, policy_version 353469 (0.0011) -[2023-11-28 09:28:38,418][87424] Updated weights for policy 0, policy_version 353479 (0.0012) -[2023-11-28 09:28:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 180895744. Throughput: 0: 2753.3, 1: 2677.3. Samples: 180919060. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:28:38,445][86177] Avg episode reward: [(0, '-537.470'), (1, '-519.260')] -[2023-11-28 09:28:38,535][87426] Updated weights for policy 1, policy_version 353160 (0.0008) -[2023-11-28 09:28:38,805][87424] Updated weights for policy 0, policy_version 353489 (0.0012) -[2023-11-28 09:28:38,915][87426] Updated weights for policy 1, policy_version 353170 (0.0009) -[2023-11-28 09:28:39,180][87424] Updated weights for policy 0, policy_version 353499 (0.0012) -[2023-11-28 09:28:39,291][87426] Updated weights for policy 1, policy_version 353180 (0.0011) -[2023-11-28 09:28:41,280][87426] Updated weights for policy 1, policy_version 353190 (0.0010) -[2023-11-28 09:28:41,457][87424] Updated weights for policy 0, policy_version 353509 (0.0011) -[2023-11-28 09:28:41,647][87426] Updated weights for policy 1, policy_version 353200 (0.0011) -[2023-11-28 09:28:41,833][87424] Updated weights for policy 0, policy_version 353519 (0.0012) -[2023-11-28 09:28:42,041][87426] Updated weights for policy 1, policy_version 353210 (0.0012) -[2023-11-28 09:28:42,218][87424] Updated weights for policy 0, policy_version 353529 (0.0011) -[2023-11-28 09:28:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 180928512. Throughput: 0: 2733.4, 1: 2654.9. Samples: 180942248. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:28:43,445][86177] Avg episode reward: [(0, '-551.930'), (1, '-508.950')] -[2023-11-28 09:28:44,273][87424] Updated weights for policy 0, policy_version 353539 (0.0010) -[2023-11-28 09:28:44,650][87424] Updated weights for policy 0, policy_version 353549 (0.0012) -[2023-11-28 09:28:44,653][87426] Updated weights for policy 1, policy_version 353220 (0.0011) -[2023-11-28 09:28:45,027][87426] Updated weights for policy 1, policy_version 353230 (0.0009) -[2023-11-28 09:28:45,041][87424] Updated weights for policy 0, policy_version 353559 (0.0011) -[2023-11-28 09:28:45,407][87426] Updated weights for policy 1, policy_version 353240 (0.0010) -[2023-11-28 09:28:46,889][87424] Updated weights for policy 0, policy_version 353569 (0.0011) -[2023-11-28 09:28:47,267][87424] Updated weights for policy 0, policy_version 353579 (0.0012) -[2023-11-28 09:28:47,582][87426] Updated weights for policy 1, policy_version 353250 (0.0011) -[2023-11-28 09:28:47,649][87424] Updated weights for policy 0, policy_version 353589 (0.0011) -[2023-11-28 09:28:47,963][87426] Updated weights for policy 1, policy_version 353260 (0.0010) -[2023-11-28 09:28:48,030][87424] Updated weights for policy 0, policy_version 353599 (0.0012) -[2023-11-28 09:28:48,347][87426] Updated weights for policy 1, policy_version 353270 (0.0007) -[2023-11-28 09:28:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 180953088. Throughput: 0: 2725.8, 1: 2650.7. Samples: 180966348. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:28:48,445][86177] Avg episode reward: [(0, '-545.970'), (1, '-548.830')] -[2023-11-28 09:28:48,719][87426] Updated weights for policy 1, policy_version 353280 (0.0007) -[2023-11-28 09:28:50,449][87424] Updated weights for policy 0, policy_version 353609 (0.0008) -[2023-11-28 09:28:50,836][87424] Updated weights for policy 0, policy_version 353619 (0.0008) -[2023-11-28 09:28:51,214][87424] Updated weights for policy 0, policy_version 353629 (0.0008) -[2023-11-28 09:28:51,250][87426] Updated weights for policy 1, policy_version 353290 (0.0011) -[2023-11-28 09:28:51,626][87426] Updated weights for policy 1, policy_version 353300 (0.0012) -[2023-11-28 09:28:52,006][87426] Updated weights for policy 1, policy_version 353310 (0.0011) -[2023-11-28 09:28:53,217][87424] Updated weights for policy 0, policy_version 353639 (0.0010) -[2023-11-28 09:28:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 180977664. Throughput: 0: 2726.8, 1: 2653.8. Samples: 180997964. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:28:53,445][86177] Avg episode reward: [(0, '-552.920'), (1, '-550.050')] -[2023-11-28 09:28:53,604][87424] Updated weights for policy 0, policy_version 353649 (0.0009) -[2023-11-28 09:28:53,983][87424] Updated weights for policy 0, policy_version 353659 (0.0010) -[2023-11-28 09:28:54,148][87426] Updated weights for policy 1, policy_version 353320 (0.0008) -[2023-11-28 09:28:54,517][87426] Updated weights for policy 1, policy_version 353330 (0.0007) -[2023-11-28 09:28:54,902][87426] Updated weights for policy 1, policy_version 353340 (0.0007) -[2023-11-28 09:28:56,260][87424] Updated weights for policy 0, policy_version 353669 (0.0010) -[2023-11-28 09:28:56,515][87426] Updated weights for policy 1, policy_version 353350 (0.0010) -[2023-11-28 09:28:56,635][87424] Updated weights for policy 0, policy_version 353679 (0.0010) -[2023-11-28 09:28:56,889][87426] Updated weights for policy 1, policy_version 353360 (0.0010) -[2023-11-28 09:28:57,018][87424] Updated weights for policy 0, policy_version 353689 (0.0012) -[2023-11-28 09:28:57,267][87426] Updated weights for policy 1, policy_version 353370 (0.0007) -[2023-11-28 09:28:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 181010432. Throughput: 0: 2721.3, 1: 2651.8. Samples: 181021660. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:28:58,445][86177] Avg episode reward: [(0, '-538.620'), (1, '-554.420')] -[2023-11-28 09:28:58,770][87424] Updated weights for policy 0, policy_version 353699 (0.0007) -[2023-11-28 09:28:59,163][87424] Updated weights for policy 0, policy_version 353709 (0.0008) -[2023-11-28 09:28:59,547][87424] Updated weights for policy 0, policy_version 353719 (0.0008) -[2023-11-28 09:28:59,746][87426] Updated weights for policy 1, policy_version 353380 (0.0009) -[2023-11-28 09:29:00,121][87426] Updated weights for policy 1, policy_version 353390 (0.0012) -[2023-11-28 09:29:00,496][87426] Updated weights for policy 1, policy_version 353400 (0.0012) -[2023-11-28 09:29:01,617][87424] Updated weights for policy 0, policy_version 353729 (0.0011) -[2023-11-28 09:29:01,994][87424] Updated weights for policy 0, policy_version 353739 (0.0011) -[2023-11-28 09:29:02,372][87424] Updated weights for policy 0, policy_version 353749 (0.0012) -[2023-11-28 09:29:02,763][87424] Updated weights for policy 0, policy_version 353759 (0.0012) -[2023-11-28 09:29:02,793][87426] Updated weights for policy 1, policy_version 353410 (0.0012) -[2023-11-28 09:29:03,165][87426] Updated weights for policy 1, policy_version 353420 (0.0011) -[2023-11-28 09:29:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 181035008. Throughput: 0: 2744.4, 1: 2638.6. Samples: 181046376. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:29:03,445][86177] Avg episode reward: [(0, '-530.800'), (1, '-552.700')] -[2023-11-28 09:29:03,546][87426] Updated weights for policy 1, policy_version 353430 (0.0011) -[2023-11-28 09:29:03,928][87426] Updated weights for policy 1, policy_version 353440 (0.0008) -[2023-11-28 09:29:04,713][87424] Updated weights for policy 0, policy_version 353769 (0.0011) -[2023-11-28 09:29:05,090][87424] Updated weights for policy 0, policy_version 353779 (0.0009) -[2023-11-28 09:29:05,470][87424] Updated weights for policy 0, policy_version 353789 (0.0009) -[2023-11-28 09:29:05,942][87426] Updated weights for policy 1, policy_version 353450 (0.0008) -[2023-11-28 09:29:06,312][87426] Updated weights for policy 1, policy_version 353460 (0.0011) -[2023-11-28 09:29:06,683][87426] Updated weights for policy 1, policy_version 353470 (0.0011) -[2023-11-28 09:29:07,982][87424] Updated weights for policy 0, policy_version 353799 (0.0010) -[2023-11-28 09:29:08,361][87424] Updated weights for policy 0, policy_version 353809 (0.0012) -[2023-11-28 09:29:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 181059584. Throughput: 0: 2771.6, 1: 2651.9. Samples: 181079364. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:29:08,445][86177] Avg episode reward: [(0, '-530.370'), (1, '-556.180')] -[2023-11-28 09:29:08,741][87424] Updated weights for policy 0, policy_version 353819 (0.0012) -[2023-11-28 09:29:09,291][87426] Updated weights for policy 1, policy_version 353480 (0.0010) -[2023-11-28 09:29:09,676][87426] Updated weights for policy 1, policy_version 353490 (0.0011) -[2023-11-28 09:29:10,054][87426] Updated weights for policy 1, policy_version 353500 (0.0011) -[2023-11-28 09:29:11,125][87424] Updated weights for policy 0, policy_version 353829 (0.0011) -[2023-11-28 09:29:11,502][87424] Updated weights for policy 0, policy_version 353839 (0.0009) -[2023-11-28 09:29:11,885][87424] Updated weights for policy 0, policy_version 353849 (0.0010) -[2023-11-28 09:29:12,336][87426] Updated weights for policy 1, policy_version 353510 (0.0011) -[2023-11-28 09:29:12,718][87426] Updated weights for policy 1, policy_version 353520 (0.0011) -[2023-11-28 09:29:13,101][87426] Updated weights for policy 1, policy_version 353530 (0.0011) -[2023-11-28 09:29:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181092352. Throughput: 0: 2763.3, 1: 2601.7. Samples: 181101432. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:29:13,445][86177] Avg episode reward: [(0, '-553.110'), (1, '-554.180')] -[2023-11-28 09:29:13,883][87424] Updated weights for policy 0, policy_version 353859 (0.0011) -[2023-11-28 09:29:14,258][87424] Updated weights for policy 0, policy_version 353869 (0.0012) -[2023-11-28 09:29:14,651][87424] Updated weights for policy 0, policy_version 353879 (0.0012) -[2023-11-28 09:29:15,047][87426] Updated weights for policy 1, policy_version 353540 (0.0012) -[2023-11-28 09:29:15,418][87426] Updated weights for policy 1, policy_version 353550 (0.0012) -[2023-11-28 09:29:15,800][87426] Updated weights for policy 1, policy_version 353560 (0.0012) -[2023-11-28 09:29:16,576][87424] Updated weights for policy 0, policy_version 353889 (0.0012) -[2023-11-28 09:29:16,952][87424] Updated weights for policy 0, policy_version 353899 (0.0011) -[2023-11-28 09:29:17,340][87424] Updated weights for policy 0, policy_version 353909 (0.0011) -[2023-11-28 09:29:17,723][87424] Updated weights for policy 0, policy_version 353919 (0.0012) -[2023-11-28 09:29:17,897][87426] Updated weights for policy 1, policy_version 353570 (0.0012) -[2023-11-28 09:29:18,277][87426] Updated weights for policy 1, policy_version 353580 (0.0011) -[2023-11-28 09:29:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 181116928. Throughput: 0: 2742.5, 1: 2633.9. Samples: 181127724. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:29:18,445][86177] Avg episode reward: [(0, '-552.480'), (1, '-546.840')] -[2023-11-28 09:29:18,658][87426] Updated weights for policy 1, policy_version 353590 (0.0009) -[2023-11-28 09:29:19,038][87426] Updated weights for policy 1, policy_version 353600 (0.0010) -[2023-11-28 09:29:19,675][87424] Updated weights for policy 0, policy_version 353929 (0.0011) -[2023-11-28 09:29:20,056][87424] Updated weights for policy 0, policy_version 353939 (0.0010) -[2023-11-28 09:29:20,444][87424] Updated weights for policy 0, policy_version 353949 (0.0010) -[2023-11-28 09:29:21,227][87426] Updated weights for policy 1, policy_version 353610 (0.0011) -[2023-11-28 09:29:21,605][87426] Updated weights for policy 1, policy_version 353620 (0.0010) -[2023-11-28 09:29:21,978][87426] Updated weights for policy 1, policy_version 353630 (0.0011) -[2023-11-28 09:29:22,929][87424] Updated weights for policy 0, policy_version 353959 (0.0011) -[2023-11-28 09:29:23,311][87424] Updated weights for policy 0, policy_version 353969 (0.0012) -[2023-11-28 09:29:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 181141504. Throughput: 0: 2735.6, 1: 2642.6. Samples: 181161080. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:29:23,446][86177] Avg episode reward: [(0, '-549.660'), (1, '-548.910')] -[2023-11-28 09:29:23,694][87424] Updated weights for policy 0, policy_version 353979 (0.0012) -[2023-11-28 09:29:24,234][87426] Updated weights for policy 1, policy_version 353640 (0.0007) -[2023-11-28 09:29:24,614][87426] Updated weights for policy 1, policy_version 353650 (0.0007) -[2023-11-28 09:29:24,992][87426] Updated weights for policy 1, policy_version 353660 (0.0008) -[2023-11-28 09:29:26,050][87424] Updated weights for policy 0, policy_version 353989 (0.0011) -[2023-11-28 09:29:26,430][87424] Updated weights for policy 0, policy_version 353999 (0.0012) -[2023-11-28 09:29:26,820][87424] Updated weights for policy 0, policy_version 354009 (0.0011) -[2023-11-28 09:29:27,386][87426] Updated weights for policy 1, policy_version 353670 (0.0008) -[2023-11-28 09:29:27,767][87426] Updated weights for policy 1, policy_version 353680 (0.0009) -[2023-11-28 09:29:28,143][87426] Updated weights for policy 1, policy_version 353690 (0.0008) -[2023-11-28 09:29:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181174272. Throughput: 0: 2751.0, 1: 2675.5. Samples: 181186440. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:29:28,445][86177] Avg episode reward: [(0, '-545.110'), (1, '-511.200')] -[2023-11-28 09:29:28,869][87424] Updated weights for policy 0, policy_version 354019 (0.0011) -[2023-11-28 09:29:29,258][87424] Updated weights for policy 0, policy_version 354029 (0.0007) -[2023-11-28 09:29:29,641][87424] Updated weights for policy 0, policy_version 354039 (0.0007) -[2023-11-28 09:29:30,405][87426] Updated weights for policy 1, policy_version 353700 (0.0009) -[2023-11-28 09:29:30,785][87426] Updated weights for policy 1, policy_version 353710 (0.0012) -[2023-11-28 09:29:31,165][87426] Updated weights for policy 1, policy_version 353720 (0.0012) -[2023-11-28 09:29:31,431][87424] Updated weights for policy 0, policy_version 354049 (0.0009) -[2023-11-28 09:29:31,817][87424] Updated weights for policy 0, policy_version 354059 (0.0009) -[2023-11-28 09:29:32,211][87424] Updated weights for policy 0, policy_version 354069 (0.0013) -[2023-11-28 09:29:32,586][87424] Updated weights for policy 0, policy_version 354079 (0.0011) -[2023-11-28 09:29:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 181198848. Throughput: 0: 2759.8, 1: 2685.9. Samples: 181211404. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:29:33,445][86177] Avg episode reward: [(0, '-520.530'), (1, '-521.600')] -[2023-11-28 09:29:33,571][87426] Updated weights for policy 1, policy_version 353730 (0.0011) -[2023-11-28 09:29:33,952][87426] Updated weights for policy 1, policy_version 353740 (0.0008) -[2023-11-28 09:29:34,334][87426] Updated weights for policy 1, policy_version 353750 (0.0007) -[2023-11-28 09:29:34,721][87426] Updated weights for policy 1, policy_version 353760 (0.0012) -[2023-11-28 09:29:34,749][87424] Updated weights for policy 0, policy_version 354089 (0.0012) -[2023-11-28 09:29:35,130][87424] Updated weights for policy 0, policy_version 354099 (0.0012) -[2023-11-28 09:29:35,512][87424] Updated weights for policy 0, policy_version 354109 (0.0012) -[2023-11-28 09:29:37,248][87426] Updated weights for policy 1, policy_version 353770 (0.0012) -[2023-11-28 09:29:37,622][87426] Updated weights for policy 1, policy_version 353780 (0.0012) -[2023-11-28 09:29:37,836][87424] Updated weights for policy 0, policy_version 354119 (0.0011) -[2023-11-28 09:29:37,997][87426] Updated weights for policy 1, policy_version 353790 (0.0011) -[2023-11-28 09:29:38,208][87424] Updated weights for policy 0, policy_version 354129 (0.0011) -[2023-11-28 09:29:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 181223424. Throughput: 0: 2786.4, 1: 2660.1. Samples: 181243056. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 09:29:38,445][86177] Avg episode reward: [(0, '-557.000'), (1, '-528.070')] -[2023-11-28 09:29:38,587][87424] Updated weights for policy 0, policy_version 354139 (0.0008) -[2023-11-28 09:29:40,154][87426] Updated weights for policy 1, policy_version 353800 (0.0012) -[2023-11-28 09:29:40,533][87426] Updated weights for policy 1, policy_version 353810 (0.0012) -[2023-11-28 09:29:40,614][87424] Updated weights for policy 0, policy_version 354149 (0.0009) -[2023-11-28 09:29:40,912][87426] Updated weights for policy 1, policy_version 353820 (0.0011) -[2023-11-28 09:29:40,994][87424] Updated weights for policy 0, policy_version 354159 (0.0011) -[2023-11-28 09:29:41,382][87424] Updated weights for policy 0, policy_version 354169 (0.0008) -[2023-11-28 09:29:43,140][87426] Updated weights for policy 1, policy_version 353830 (0.0012) -[2023-11-28 09:29:43,398][87424] Updated weights for policy 0, policy_version 354179 (0.0009) -[2023-11-28 09:29:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 181248000. Throughput: 0: 2814.0, 1: 2651.6. Samples: 181267608. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:29:43,445][86177] Avg episode reward: [(0, '-558.590'), (1, '-536.890')] -[2023-11-28 09:29:43,516][87426] Updated weights for policy 1, policy_version 353840 (0.0009) -[2023-11-28 09:29:43,774][87424] Updated weights for policy 0, policy_version 354189 (0.0011) -[2023-11-28 09:29:43,886][87426] Updated weights for policy 1, policy_version 353850 (0.0010) -[2023-11-28 09:29:44,159][87424] Updated weights for policy 0, policy_version 354199 (0.0011) -[2023-11-28 09:29:45,885][87426] Updated weights for policy 1, policy_version 353860 (0.0012) -[2023-11-28 09:29:46,093][87424] Updated weights for policy 0, policy_version 354209 (0.0011) -[2023-11-28 09:29:46,266][87426] Updated weights for policy 1, policy_version 353870 (0.0012) -[2023-11-28 09:29:46,467][87424] Updated weights for policy 0, policy_version 354219 (0.0008) -[2023-11-28 09:29:46,641][87426] Updated weights for policy 1, policy_version 353880 (0.0011) -[2023-11-28 09:29:46,838][87424] Updated weights for policy 0, policy_version 354229 (0.0009) -[2023-11-28 09:29:47,242][87424] Updated weights for policy 0, policy_version 354239 (0.0012) -[2023-11-28 09:29:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181280768. Throughput: 0: 2782.1, 1: 2667.0. Samples: 181291588. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:29:48,445][86177] Avg episode reward: [(0, '-564.090'), (1, '-535.420')] -[2023-11-28 09:29:48,877][87424] Updated weights for policy 0, policy_version 354249 (0.0012) -[2023-11-28 09:29:48,890][87426] Updated weights for policy 1, policy_version 353890 (0.0010) -[2023-11-28 09:29:49,256][87424] Updated weights for policy 0, policy_version 354259 (0.0012) -[2023-11-28 09:29:49,274][87426] Updated weights for policy 1, policy_version 353900 (0.0011) -[2023-11-28 09:29:49,643][87424] Updated weights for policy 0, policy_version 354269 (0.0012) -[2023-11-28 09:29:49,654][87426] Updated weights for policy 1, policy_version 353910 (0.0012) -[2023-11-28 09:29:50,029][87426] Updated weights for policy 1, policy_version 353920 (0.0009) -[2023-11-28 09:29:52,109][87424] Updated weights for policy 0, policy_version 354279 (0.0009) -[2023-11-28 09:29:52,271][87426] Updated weights for policy 1, policy_version 353930 (0.0011) -[2023-11-28 09:29:52,486][87424] Updated weights for policy 0, policy_version 354289 (0.0011) -[2023-11-28 09:29:52,652][87426] Updated weights for policy 1, policy_version 353940 (0.0012) -[2023-11-28 09:29:52,864][87424] Updated weights for policy 0, policy_version 354299 (0.0010) -[2023-11-28 09:29:53,028][87426] Updated weights for policy 1, policy_version 353950 (0.0011) -[2023-11-28 09:29:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5442.8). Total num frames: 181313536. Throughput: 0: 2755.7, 1: 2669.0. Samples: 181323476. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:29:53,445][86177] Avg episode reward: [(0, '-566.850'), (1, '-538.520')] -[2023-11-28 09:29:55,079][87426] Updated weights for policy 1, policy_version 353960 (0.0011) -[2023-11-28 09:29:55,407][87424] Updated weights for policy 0, policy_version 354309 (0.0011) -[2023-11-28 09:29:55,457][87426] Updated weights for policy 1, policy_version 353970 (0.0012) -[2023-11-28 09:29:55,781][87424] Updated weights for policy 0, policy_version 354319 (0.0011) -[2023-11-28 09:29:55,843][87426] Updated weights for policy 1, policy_version 353980 (0.0012) -[2023-11-28 09:29:56,168][87424] Updated weights for policy 0, policy_version 354329 (0.0012) -[2023-11-28 09:29:57,812][87426] Updated weights for policy 1, policy_version 353990 (0.0012) -[2023-11-28 09:29:58,102][87424] Updated weights for policy 0, policy_version 354339 (0.0011) -[2023-11-28 09:29:58,192][87426] Updated weights for policy 1, policy_version 354000 (0.0011) -[2023-11-28 09:29:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 181329920. Throughput: 0: 2773.7, 1: 2736.7. Samples: 181349400. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:29:58,445][86177] Avg episode reward: [(0, '-578.700'), (1, '-534.680')] -[2023-11-28 09:29:58,491][87424] Updated weights for policy 0, policy_version 354349 (0.0008) -[2023-11-28 09:29:58,584][87426] Updated weights for policy 1, policy_version 354010 (0.0011) -[2023-11-28 09:29:58,871][87424] Updated weights for policy 0, policy_version 354359 (0.0008) -[2023-11-28 09:30:00,955][87426] Updated weights for policy 1, policy_version 354020 (0.0011) -[2023-11-28 09:30:01,325][87426] Updated weights for policy 1, policy_version 354030 (0.0008) -[2023-11-28 09:30:01,369][87424] Updated weights for policy 0, policy_version 354369 (0.0010) -[2023-11-28 09:30:01,720][87426] Updated weights for policy 1, policy_version 354040 (0.0009) -[2023-11-28 09:30:01,747][87424] Updated weights for policy 0, policy_version 354379 (0.0009) -[2023-11-28 09:30:02,137][87424] Updated weights for policy 0, policy_version 354389 (0.0013) -[2023-11-28 09:30:02,511][87424] Updated weights for policy 0, policy_version 354399 (0.0009) -[2023-11-28 09:30:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 181362688. Throughput: 0: 2756.8, 1: 2714.1. Samples: 181373916. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:03,445][86177] Avg episode reward: [(0, '-545.240'), (1, '-532.400')] -[2023-11-28 09:30:03,926][87426] Updated weights for policy 1, policy_version 354050 (0.0010) -[2023-11-28 09:30:04,310][87426] Updated weights for policy 1, policy_version 354060 (0.0012) -[2023-11-28 09:30:04,689][87426] Updated weights for policy 1, policy_version 354070 (0.0011) -[2023-11-28 09:30:04,907][87424] Updated weights for policy 0, policy_version 354409 (0.0009) -[2023-11-28 09:30:05,058][87426] Updated weights for policy 1, policy_version 354080 (0.0011) -[2023-11-28 09:30:05,284][87424] Updated weights for policy 0, policy_version 354419 (0.0009) -[2023-11-28 09:30:05,663][87424] Updated weights for policy 0, policy_version 354429 (0.0008) -[2023-11-28 09:30:07,308][87426] Updated weights for policy 1, policy_version 354090 (0.0014) -[2023-11-28 09:30:07,678][87426] Updated weights for policy 1, policy_version 354100 (0.0011) -[2023-11-28 09:30:07,688][87424] Updated weights for policy 0, policy_version 354439 (0.0011) -[2023-11-28 09:30:08,058][87426] Updated weights for policy 1, policy_version 354110 (0.0010) -[2023-11-28 09:30:08,070][87424] Updated weights for policy 0, policy_version 354449 (0.0012) -[2023-11-28 09:30:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181387264. Throughput: 0: 2746.5, 1: 2709.1. Samples: 181406580. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:08,445][86177] Avg episode reward: [(0, '-566.250'), (1, '-534.570')] -[2023-11-28 09:30:08,446][87424] Updated weights for policy 0, policy_version 354459 (0.0011) -[2023-11-28 09:30:10,041][87426] Updated weights for policy 1, policy_version 354120 (0.0011) -[2023-11-28 09:30:10,428][87426] Updated weights for policy 1, policy_version 354130 (0.0012) -[2023-11-28 09:30:10,749][87424] Updated weights for policy 0, policy_version 354469 (0.0012) -[2023-11-28 09:30:10,796][87426] Updated weights for policy 1, policy_version 354140 (0.0012) -[2023-11-28 09:30:11,130][87424] Updated weights for policy 0, policy_version 354479 (0.0009) -[2023-11-28 09:30:11,511][87424] Updated weights for policy 0, policy_version 354489 (0.0010) -[2023-11-28 09:30:13,113][87426] Updated weights for policy 1, policy_version 354150 (0.0010) -[2023-11-28 09:30:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 181411840. Throughput: 0: 2738.0, 1: 2690.9. Samples: 181430744. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:13,445][86177] Avg episode reward: [(0, '-570.990'), (1, '-528.100')] -[2023-11-28 09:30:13,490][87426] Updated weights for policy 1, policy_version 354160 (0.0008) -[2023-11-28 09:30:13,542][87424] Updated weights for policy 0, policy_version 354499 (0.0011) -[2023-11-28 09:30:13,867][87426] Updated weights for policy 1, policy_version 354170 (0.0007) -[2023-11-28 09:30:13,916][87424] Updated weights for policy 0, policy_version 354509 (0.0007) -[2023-11-28 09:30:14,294][87424] Updated weights for policy 0, policy_version 354519 (0.0008) -[2023-11-28 09:30:16,344][87426] Updated weights for policy 1, policy_version 354180 (0.0009) -[2023-11-28 09:30:16,371][87424] Updated weights for policy 0, policy_version 354529 (0.0008) -[2023-11-28 09:30:16,724][87426] Updated weights for policy 1, policy_version 354190 (0.0011) -[2023-11-28 09:30:16,753][87424] Updated weights for policy 0, policy_version 354539 (0.0009) -[2023-11-28 09:30:17,104][87426] Updated weights for policy 1, policy_version 354200 (0.0007) -[2023-11-28 09:30:17,142][87424] Updated weights for policy 0, policy_version 354549 (0.0007) -[2023-11-28 09:30:17,520][87424] Updated weights for policy 0, policy_version 354559 (0.0007) -[2023-11-28 09:30:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181444608. Throughput: 0: 2714.3, 1: 2680.2. Samples: 181454156. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:18,445][86177] Avg episode reward: [(0, '-563.910'), (1, '-523.740')] -[2023-11-28 09:30:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000354208_90677248.pth... -[2023-11-28 09:30:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000354560_90767360.pth... -[2023-11-28 09:30:18,486][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000351712_90038272.pth -[2023-11-28 09:30:18,490][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000352032_90120192.pth -[2023-11-28 09:30:19,620][87426] Updated weights for policy 1, policy_version 354210 (0.0008) -[2023-11-28 09:30:19,991][87426] Updated weights for policy 1, policy_version 354220 (0.0009) -[2023-11-28 09:30:19,998][87424] Updated weights for policy 0, policy_version 354569 (0.0010) -[2023-11-28 09:30:20,371][87426] Updated weights for policy 1, policy_version 354230 (0.0012) -[2023-11-28 09:30:20,377][87424] Updated weights for policy 0, policy_version 354579 (0.0012) -[2023-11-28 09:30:20,754][87426] Updated weights for policy 1, policy_version 354240 (0.0010) -[2023-11-28 09:30:20,768][87424] Updated weights for policy 0, policy_version 354589 (0.0012) -[2023-11-28 09:30:22,969][87426] Updated weights for policy 1, policy_version 354250 (0.0012) -[2023-11-28 09:30:23,350][87426] Updated weights for policy 1, policy_version 354260 (0.0011) -[2023-11-28 09:30:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 181460992. Throughput: 0: 2669.7, 1: 2701.1. Samples: 181484744. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:23,445][86177] Avg episode reward: [(0, '-557.540'), (1, '-545.860')] -[2023-11-28 09:30:23,489][87424] Updated weights for policy 0, policy_version 354599 (0.0011) -[2023-11-28 09:30:23,726][87426] Updated weights for policy 1, policy_version 354270 (0.0011) -[2023-11-28 09:30:23,879][87424] Updated weights for policy 0, policy_version 354609 (0.0012) -[2023-11-28 09:30:24,254][87424] Updated weights for policy 0, policy_version 354619 (0.0012) -[2023-11-28 09:30:25,695][87426] Updated weights for policy 1, policy_version 354280 (0.0011) -[2023-11-28 09:30:26,079][87426] Updated weights for policy 1, policy_version 354290 (0.0007) -[2023-11-28 09:30:26,275][87424] Updated weights for policy 0, policy_version 354629 (0.0011) -[2023-11-28 09:30:26,454][87426] Updated weights for policy 1, policy_version 354300 (0.0008) -[2023-11-28 09:30:26,648][87424] Updated weights for policy 0, policy_version 354639 (0.0012) -[2023-11-28 09:30:27,031][87424] Updated weights for policy 0, policy_version 354649 (0.0012) -[2023-11-28 09:30:28,066][87426] Updated weights for policy 1, policy_version 354310 (0.0010) -[2023-11-28 09:30:28,431][87426] Updated weights for policy 1, policy_version 354320 (0.0010) -[2023-11-28 09:30:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 181493760. Throughput: 0: 2660.9, 1: 2726.9. Samples: 181510060. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:28,445][86177] Avg episode reward: [(0, '-524.450'), (1, '-549.510')] -[2023-11-28 09:30:28,814][87426] Updated weights for policy 1, policy_version 354330 (0.0007) -[2023-11-28 09:30:29,006][87424] Updated weights for policy 0, policy_version 354659 (0.0012) -[2023-11-28 09:30:29,381][87424] Updated weights for policy 0, policy_version 354669 (0.0010) -[2023-11-28 09:30:29,760][87424] Updated weights for policy 0, policy_version 354679 (0.0010) -[2023-11-28 09:30:31,047][87426] Updated weights for policy 1, policy_version 354340 (0.0009) -[2023-11-28 09:30:31,427][87426] Updated weights for policy 1, policy_version 354350 (0.0008) -[2023-11-28 09:30:31,694][87424] Updated weights for policy 0, policy_version 354689 (0.0014) -[2023-11-28 09:30:31,803][87426] Updated weights for policy 1, policy_version 354360 (0.0009) -[2023-11-28 09:30:32,084][87424] Updated weights for policy 0, policy_version 354699 (0.0009) -[2023-11-28 09:30:32,457][87424] Updated weights for policy 0, policy_version 354709 (0.0009) -[2023-11-28 09:30:32,841][87424] Updated weights for policy 0, policy_version 354719 (0.0009) -[2023-11-28 09:30:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181526528. Throughput: 0: 2675.8, 1: 2726.8. Samples: 181534704. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:33,445][86177] Avg episode reward: [(0, '-523.550'), (1, '-548.420')] -[2023-11-28 09:30:34,067][87426] Updated weights for policy 1, policy_version 354370 (0.0010) -[2023-11-28 09:30:34,444][87426] Updated weights for policy 1, policy_version 354380 (0.0012) -[2023-11-28 09:30:34,836][87426] Updated weights for policy 1, policy_version 354390 (0.0012) -[2023-11-28 09:30:35,223][87426] Updated weights for policy 1, policy_version 354400 (0.0012) -[2023-11-28 09:30:35,346][87424] Updated weights for policy 0, policy_version 354729 (0.0012) -[2023-11-28 09:30:35,719][87424] Updated weights for policy 0, policy_version 354739 (0.0012) -[2023-11-28 09:30:36,099][87424] Updated weights for policy 0, policy_version 354749 (0.0012) -[2023-11-28 09:30:37,119][87426] Updated weights for policy 1, policy_version 354410 (0.0012) -[2023-11-28 09:30:37,499][87426] Updated weights for policy 1, policy_version 354420 (0.0012) -[2023-11-28 09:30:37,867][87426] Updated weights for policy 1, policy_version 354430 (0.0012) -[2023-11-28 09:30:38,241][87424] Updated weights for policy 0, policy_version 354759 (0.0012) -[2023-11-28 09:30:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181551104. Throughput: 0: 2707.5, 1: 2740.4. Samples: 181568632. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:38,445][86177] Avg episode reward: [(0, '-527.550'), (1, '-545.890')] -[2023-11-28 09:30:38,629][87424] Updated weights for policy 0, policy_version 354769 (0.0012) -[2023-11-28 09:30:39,011][87424] Updated weights for policy 0, policy_version 354779 (0.0011) -[2023-11-28 09:30:39,815][87426] Updated weights for policy 1, policy_version 354440 (0.0011) -[2023-11-28 09:30:40,199][87426] Updated weights for policy 1, policy_version 354450 (0.0011) -[2023-11-28 09:30:40,571][87426] Updated weights for policy 1, policy_version 354460 (0.0012) -[2023-11-28 09:30:41,412][87424] Updated weights for policy 0, policy_version 354789 (0.0009) -[2023-11-28 09:30:41,792][87424] Updated weights for policy 0, policy_version 354799 (0.0010) -[2023-11-28 09:30:42,165][87424] Updated weights for policy 0, policy_version 354809 (0.0011) -[2023-11-28 09:30:43,027][87426] Updated weights for policy 1, policy_version 354470 (0.0011) -[2023-11-28 09:30:43,409][87426] Updated weights for policy 1, policy_version 354480 (0.0008) -[2023-11-28 09:30:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181575680. Throughput: 0: 2691.6, 1: 2706.2. Samples: 181592300. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:43,445][86177] Avg episode reward: [(0, '-527.590'), (1, '-523.990')] -[2023-11-28 09:30:43,784][87426] Updated weights for policy 1, policy_version 354490 (0.0007) -[2023-11-28 09:30:44,486][87424] Updated weights for policy 0, policy_version 354819 (0.0011) -[2023-11-28 09:30:44,870][87424] Updated weights for policy 0, policy_version 354829 (0.0012) -[2023-11-28 09:30:45,259][87424] Updated weights for policy 0, policy_version 354839 (0.0011) -[2023-11-28 09:30:45,941][87426] Updated weights for policy 1, policy_version 354500 (0.0009) -[2023-11-28 09:30:46,320][87426] Updated weights for policy 1, policy_version 354510 (0.0012) -[2023-11-28 09:30:46,697][87426] Updated weights for policy 1, policy_version 354520 (0.0012) -[2023-11-28 09:30:47,161][87424] Updated weights for policy 0, policy_version 354849 (0.0012) -[2023-11-28 09:30:47,553][87424] Updated weights for policy 0, policy_version 354859 (0.0012) -[2023-11-28 09:30:47,929][87424] Updated weights for policy 0, policy_version 354869 (0.0012) -[2023-11-28 09:30:48,306][87424] Updated weights for policy 0, policy_version 354879 (0.0012) -[2023-11-28 09:30:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 181608448. Throughput: 0: 2690.6, 1: 2711.2. Samples: 181616996. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:48,446][86177] Avg episode reward: [(0, '-531.720'), (1, '-514.600')] -[2023-11-28 09:30:49,130][87426] Updated weights for policy 1, policy_version 354530 (0.0012) -[2023-11-28 09:30:49,503][87426] Updated weights for policy 1, policy_version 354540 (0.0011) -[2023-11-28 09:30:49,893][87426] Updated weights for policy 1, policy_version 354550 (0.0012) -[2023-11-28 09:30:50,270][87426] Updated weights for policy 1, policy_version 354560 (0.0010) -[2023-11-28 09:30:50,806][87424] Updated weights for policy 0, policy_version 354889 (0.0012) -[2023-11-28 09:30:51,186][87424] Updated weights for policy 0, policy_version 354899 (0.0009) -[2023-11-28 09:30:51,571][87424] Updated weights for policy 0, policy_version 354909 (0.0012) -[2023-11-28 09:30:52,768][87426] Updated weights for policy 1, policy_version 354570 (0.0011) -[2023-11-28 09:30:53,150][87426] Updated weights for policy 1, policy_version 354580 (0.0011) -[2023-11-28 09:30:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 181624832. Throughput: 0: 2697.0, 1: 2680.9. Samples: 181648584. Policy #0 lag: (min: 6.0, avg: 28.0, max: 46.0) -[2023-11-28 09:30:53,445][86177] Avg episode reward: [(0, '-532.760'), (1, '-528.630')] -[2023-11-28 09:30:53,534][87426] Updated weights for policy 1, policy_version 354590 (0.0011) -[2023-11-28 09:30:53,894][87424] Updated weights for policy 0, policy_version 354919 (0.0011) -[2023-11-28 09:30:54,279][87424] Updated weights for policy 0, policy_version 354929 (0.0007) -[2023-11-28 09:30:54,676][87424] Updated weights for policy 0, policy_version 354939 (0.0007) -[2023-11-28 09:30:55,999][87426] Updated weights for policy 1, policy_version 354600 (0.0011) -[2023-11-28 09:30:56,373][87424] Updated weights for policy 0, policy_version 354949 (0.0007) -[2023-11-28 09:30:56,382][87426] Updated weights for policy 1, policy_version 354610 (0.0009) -[2023-11-28 09:30:56,742][87424] Updated weights for policy 0, policy_version 354959 (0.0007) -[2023-11-28 09:30:56,757][87426] Updated weights for policy 1, policy_version 354620 (0.0007) -[2023-11-28 09:30:57,123][87424] Updated weights for policy 0, policy_version 354969 (0.0007) -[2023-11-28 09:30:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181657600. Throughput: 0: 2695.9, 1: 2670.0. Samples: 181672208. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:30:58,445][86177] Avg episode reward: [(0, '-532.090'), (1, '-529.110')] -[2023-11-28 09:30:58,946][87426] Updated weights for policy 1, policy_version 354630 (0.0008) -[2023-11-28 09:30:59,325][87426] Updated weights for policy 1, policy_version 354640 (0.0007) -[2023-11-28 09:30:59,384][87424] Updated weights for policy 0, policy_version 354979 (0.0008) -[2023-11-28 09:30:59,709][87426] Updated weights for policy 1, policy_version 354650 (0.0008) -[2023-11-28 09:30:59,772][87424] Updated weights for policy 0, policy_version 354989 (0.0011) -[2023-11-28 09:31:00,170][87424] Updated weights for policy 0, policy_version 354999 (0.0010) -[2023-11-28 09:31:01,753][87426] Updated weights for policy 1, policy_version 354660 (0.0011) -[2023-11-28 09:31:02,136][87426] Updated weights for policy 1, policy_version 354670 (0.0012) -[2023-11-28 09:31:02,243][87424] Updated weights for policy 0, policy_version 355009 (0.0010) -[2023-11-28 09:31:02,515][87426] Updated weights for policy 1, policy_version 354680 (0.0011) -[2023-11-28 09:31:02,624][87424] Updated weights for policy 0, policy_version 355019 (0.0011) -[2023-11-28 09:31:03,002][87424] Updated weights for policy 0, policy_version 355029 (0.0011) -[2023-11-28 09:31:03,385][87424] Updated weights for policy 0, policy_version 355039 (0.0012) -[2023-11-28 09:31:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181690368. Throughput: 0: 2711.6, 1: 2682.1. Samples: 181696876. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:03,445][86177] Avg episode reward: [(0, '-525.880'), (1, '-524.190')] -[2023-11-28 09:31:04,336][87426] Updated weights for policy 1, policy_version 354690 (0.0011) -[2023-11-28 09:31:04,716][87426] Updated weights for policy 1, policy_version 354700 (0.0008) -[2023-11-28 09:31:05,090][87426] Updated weights for policy 1, policy_version 354710 (0.0008) -[2023-11-28 09:31:05,465][87426] Updated weights for policy 1, policy_version 354720 (0.0008) -[2023-11-28 09:31:05,605][87424] Updated weights for policy 0, policy_version 355049 (0.0012) -[2023-11-28 09:31:05,981][87424] Updated weights for policy 0, policy_version 355059 (0.0012) -[2023-11-28 09:31:06,369][87424] Updated weights for policy 0, policy_version 355069 (0.0011) -[2023-11-28 09:31:07,960][87426] Updated weights for policy 1, policy_version 354730 (0.0008) -[2023-11-28 09:31:08,239][87424] Updated weights for policy 0, policy_version 355079 (0.0012) -[2023-11-28 09:31:08,348][87426] Updated weights for policy 1, policy_version 354740 (0.0008) -[2023-11-28 09:31:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 181706752. Throughput: 0: 2758.1, 1: 2685.1. Samples: 181729684. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:08,445][86177] Avg episode reward: [(0, '-534.880'), (1, '-536.120')] -[2023-11-28 09:31:08,629][87424] Updated weights for policy 0, policy_version 355089 (0.0008) -[2023-11-28 09:31:08,723][87426] Updated weights for policy 1, policy_version 354750 (0.0011) -[2023-11-28 09:31:09,012][87424] Updated weights for policy 0, policy_version 355099 (0.0009) -[2023-11-28 09:31:11,029][87426] Updated weights for policy 1, policy_version 354760 (0.0011) -[2023-11-28 09:31:11,414][87426] Updated weights for policy 1, policy_version 354770 (0.0009) -[2023-11-28 09:31:11,480][87424] Updated weights for policy 0, policy_version 355109 (0.0010) -[2023-11-28 09:31:11,789][87426] Updated weights for policy 1, policy_version 354780 (0.0010) -[2023-11-28 09:31:11,858][87424] Updated weights for policy 0, policy_version 355119 (0.0010) -[2023-11-28 09:31:12,251][87424] Updated weights for policy 0, policy_version 355129 (0.0010) -[2023-11-28 09:31:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181739520. Throughput: 0: 2735.4, 1: 2667.3. Samples: 181753180. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:13,445][86177] Avg episode reward: [(0, '-524.550'), (1, '-555.820')] -[2023-11-28 09:31:14,279][87426] Updated weights for policy 1, policy_version 354790 (0.0009) -[2023-11-28 09:31:14,412][87424] Updated weights for policy 0, policy_version 355139 (0.0011) -[2023-11-28 09:31:14,669][87426] Updated weights for policy 1, policy_version 354800 (0.0010) -[2023-11-28 09:31:14,796][87424] Updated weights for policy 0, policy_version 355149 (0.0012) -[2023-11-28 09:31:15,041][87426] Updated weights for policy 1, policy_version 354810 (0.0011) -[2023-11-28 09:31:15,185][87424] Updated weights for policy 0, policy_version 355159 (0.0012) -[2023-11-28 09:31:16,895][87426] Updated weights for policy 1, policy_version 354820 (0.0008) -[2023-11-28 09:31:17,203][87424] Updated weights for policy 0, policy_version 355169 (0.0011) -[2023-11-28 09:31:17,273][87426] Updated weights for policy 1, policy_version 354830 (0.0007) -[2023-11-28 09:31:17,582][87424] Updated weights for policy 0, policy_version 355179 (0.0011) -[2023-11-28 09:31:17,648][87426] Updated weights for policy 1, policy_version 354840 (0.0008) -[2023-11-28 09:31:17,965][87424] Updated weights for policy 0, policy_version 355189 (0.0010) -[2023-11-28 09:31:18,347][87424] Updated weights for policy 0, policy_version 355199 (0.0011) -[2023-11-28 09:31:18,444][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 181772288. Throughput: 0: 2723.6, 1: 2676.6. Samples: 181777716. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:18,446][86177] Avg episode reward: [(0, '-521.290'), (1, '-556.040')] -[2023-11-28 09:31:20,055][87424] Updated weights for policy 0, policy_version 355209 (0.0012) -[2023-11-28 09:31:20,113][87426] Updated weights for policy 1, policy_version 354850 (0.0008) -[2023-11-28 09:31:20,438][87424] Updated weights for policy 0, policy_version 355219 (0.0011) -[2023-11-28 09:31:20,491][87426] Updated weights for policy 1, policy_version 354860 (0.0011) -[2023-11-28 09:31:20,828][87424] Updated weights for policy 0, policy_version 355229 (0.0012) -[2023-11-28 09:31:20,868][87426] Updated weights for policy 1, policy_version 354870 (0.0007) -[2023-11-28 09:31:21,242][87426] Updated weights for policy 1, policy_version 354880 (0.0011) -[2023-11-28 09:31:23,162][87424] Updated weights for policy 0, policy_version 355239 (0.0011) -[2023-11-28 09:31:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 181788672. Throughput: 0: 2697.7, 1: 2650.1. Samples: 181809284. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:23,445][86177] Avg episode reward: [(0, '-525.230'), (1, '-562.260')] -[2023-11-28 09:31:23,489][87426] Updated weights for policy 1, policy_version 354890 (0.0012) -[2023-11-28 09:31:23,533][87424] Updated weights for policy 0, policy_version 355249 (0.0009) -[2023-11-28 09:31:23,868][87426] Updated weights for policy 1, policy_version 354900 (0.0012) -[2023-11-28 09:31:23,916][87424] Updated weights for policy 0, policy_version 355259 (0.0008) -[2023-11-28 09:31:24,254][87426] Updated weights for policy 1, policy_version 354910 (0.0012) -[2023-11-28 09:31:26,239][87424] Updated weights for policy 0, policy_version 355269 (0.0007) -[2023-11-28 09:31:26,259][87426] Updated weights for policy 1, policy_version 354920 (0.0011) -[2023-11-28 09:31:26,615][87424] Updated weights for policy 0, policy_version 355279 (0.0008) -[2023-11-28 09:31:26,641][87426] Updated weights for policy 1, policy_version 354930 (0.0011) -[2023-11-28 09:31:26,999][87424] Updated weights for policy 0, policy_version 355289 (0.0007) -[2023-11-28 09:31:27,021][87426] Updated weights for policy 1, policy_version 354940 (0.0012) -[2023-11-28 09:31:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181821440. Throughput: 0: 2692.6, 1: 2666.2. Samples: 181833448. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:28,445][86177] Avg episode reward: [(0, '-514.210'), (1, '-562.670')] -[2023-11-28 09:31:29,283][87426] Updated weights for policy 1, policy_version 354950 (0.0009) -[2023-11-28 09:31:29,462][87424] Updated weights for policy 0, policy_version 355299 (0.0008) -[2023-11-28 09:31:29,669][87426] Updated weights for policy 1, policy_version 354960 (0.0010) -[2023-11-28 09:31:29,852][87424] Updated weights for policy 0, policy_version 355309 (0.0011) -[2023-11-28 09:31:30,048][87426] Updated weights for policy 1, policy_version 354970 (0.0011) -[2023-11-28 09:31:30,222][87424] Updated weights for policy 0, policy_version 355319 (0.0010) -[2023-11-28 09:31:32,184][87426] Updated weights for policy 1, policy_version 354980 (0.0011) -[2023-11-28 09:31:32,570][87426] Updated weights for policy 1, policy_version 354990 (0.0012) -[2023-11-28 09:31:32,670][87424] Updated weights for policy 0, policy_version 355329 (0.0010) -[2023-11-28 09:31:32,948][87426] Updated weights for policy 1, policy_version 355000 (0.0012) -[2023-11-28 09:31:33,047][87424] Updated weights for policy 0, policy_version 355339 (0.0008) -[2023-11-28 09:31:33,437][87424] Updated weights for policy 0, policy_version 355349 (0.0007) -[2023-11-28 09:31:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 181846016. Throughput: 0: 2690.5, 1: 2661.8. Samples: 181857848. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:33,445][86177] Avg episode reward: [(0, '-528.190'), (1, '-561.500')] -[2023-11-28 09:31:33,819][87424] Updated weights for policy 0, policy_version 355359 (0.0007) -[2023-11-28 09:31:35,483][87426] Updated weights for policy 1, policy_version 355010 (0.0011) -[2023-11-28 09:31:35,858][87426] Updated weights for policy 1, policy_version 355020 (0.0012) -[2023-11-28 09:31:36,226][87426] Updated weights for policy 1, policy_version 355030 (0.0011) -[2023-11-28 09:31:36,380][87424] Updated weights for policy 0, policy_version 355369 (0.0009) -[2023-11-28 09:31:36,603][87426] Updated weights for policy 1, policy_version 355040 (0.0012) -[2023-11-28 09:31:36,767][87424] Updated weights for policy 0, policy_version 355379 (0.0010) -[2023-11-28 09:31:37,149][87424] Updated weights for policy 0, policy_version 355389 (0.0010) -[2023-11-28 09:31:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 181870592. Throughput: 0: 2689.2, 1: 2675.6. Samples: 181889996. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:38,445][86177] Avg episode reward: [(0, '-537.160'), (1, '-547.780')] -[2023-11-28 09:31:38,493][87426] Updated weights for policy 1, policy_version 355050 (0.0012) -[2023-11-28 09:31:38,872][87426] Updated weights for policy 1, policy_version 355060 (0.0008) -[2023-11-28 09:31:39,192][87424] Updated weights for policy 0, policy_version 355399 (0.0011) -[2023-11-28 09:31:39,247][87426] Updated weights for policy 1, policy_version 355070 (0.0011) -[2023-11-28 09:31:39,562][87424] Updated weights for policy 0, policy_version 355409 (0.0011) -[2023-11-28 09:31:39,942][87424] Updated weights for policy 0, policy_version 355419 (0.0012) -[2023-11-28 09:31:41,432][87426] Updated weights for policy 1, policy_version 355080 (0.0007) -[2023-11-28 09:31:41,804][87426] Updated weights for policy 1, policy_version 355090 (0.0010) -[2023-11-28 09:31:41,961][87424] Updated weights for policy 0, policy_version 355429 (0.0011) -[2023-11-28 09:31:42,186][87426] Updated weights for policy 1, policy_version 355100 (0.0011) -[2023-11-28 09:31:42,334][87424] Updated weights for policy 0, policy_version 355439 (0.0013) -[2023-11-28 09:31:42,724][87424] Updated weights for policy 0, policy_version 355449 (0.0010) -[2023-11-28 09:31:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 181903360. Throughput: 0: 2709.9, 1: 2672.3. Samples: 181914404. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:43,445][86177] Avg episode reward: [(0, '-535.850'), (1, '-548.870')] -[2023-11-28 09:31:44,748][87426] Updated weights for policy 1, policy_version 355110 (0.0012) -[2023-11-28 09:31:45,121][87426] Updated weights for policy 1, policy_version 355120 (0.0012) -[2023-11-28 09:31:45,193][87424] Updated weights for policy 0, policy_version 355459 (0.0011) -[2023-11-28 09:31:45,509][87426] Updated weights for policy 1, policy_version 355130 (0.0008) -[2023-11-28 09:31:45,576][87424] Updated weights for policy 0, policy_version 355469 (0.0009) -[2023-11-28 09:31:45,953][87424] Updated weights for policy 0, policy_version 355479 (0.0011) -[2023-11-28 09:31:47,802][87424] Updated weights for policy 0, policy_version 355489 (0.0008) -[2023-11-28 09:31:47,993][87426] Updated weights for policy 1, policy_version 355140 (0.0008) -[2023-11-28 09:31:48,178][87424] Updated weights for policy 0, policy_version 355499 (0.0011) -[2023-11-28 09:31:48,372][87426] Updated weights for policy 1, policy_version 355150 (0.0009) -[2023-11-28 09:31:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 181919744. Throughput: 0: 2695.7, 1: 2674.5. Samples: 181938536. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:48,445][86177] Avg episode reward: [(0, '-540.330'), (1, '-534.570')] -[2023-11-28 09:31:48,562][87424] Updated weights for policy 0, policy_version 355509 (0.0011) -[2023-11-28 09:31:48,752][87426] Updated weights for policy 1, policy_version 355160 (0.0008) -[2023-11-28 09:31:48,947][87424] Updated weights for policy 0, policy_version 355519 (0.0008) -[2023-11-28 09:31:50,535][87426] Updated weights for policy 1, policy_version 355170 (0.0011) -[2023-11-28 09:31:50,915][87426] Updated weights for policy 1, policy_version 355180 (0.0012) -[2023-11-28 09:31:51,292][87426] Updated weights for policy 1, policy_version 355190 (0.0011) -[2023-11-28 09:31:51,437][87424] Updated weights for policy 0, policy_version 355529 (0.0011) -[2023-11-28 09:31:51,665][87426] Updated weights for policy 1, policy_version 355200 (0.0011) -[2023-11-28 09:31:51,828][87424] Updated weights for policy 0, policy_version 355539 (0.0012) -[2023-11-28 09:31:52,210][87424] Updated weights for policy 0, policy_version 355549 (0.0009) -[2023-11-28 09:31:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 181952512. Throughput: 0: 2673.0, 1: 2686.4. Samples: 181970856. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:53,445][86177] Avg episode reward: [(0, '-529.830'), (1, '-523.440')] -[2023-11-28 09:31:53,846][87426] Updated weights for policy 1, policy_version 355210 (0.0012) -[2023-11-28 09:31:54,219][87426] Updated weights for policy 1, policy_version 355220 (0.0012) -[2023-11-28 09:31:54,601][87426] Updated weights for policy 1, policy_version 355230 (0.0011) -[2023-11-28 09:31:54,749][87424] Updated weights for policy 0, policy_version 355559 (0.0010) -[2023-11-28 09:31:55,123][87424] Updated weights for policy 0, policy_version 355569 (0.0012) -[2023-11-28 09:31:55,510][87424] Updated weights for policy 0, policy_version 355579 (0.0012) -[2023-11-28 09:31:56,322][87426] Updated weights for policy 1, policy_version 355240 (0.0008) -[2023-11-28 09:31:56,700][87426] Updated weights for policy 1, policy_version 355250 (0.0007) -[2023-11-28 09:31:57,075][87426] Updated weights for policy 1, policy_version 355260 (0.0007) -[2023-11-28 09:31:57,442][87424] Updated weights for policy 0, policy_version 355589 (0.0012) -[2023-11-28 09:31:57,805][87424] Updated weights for policy 0, policy_version 355599 (0.0009) -[2023-11-28 09:31:58,182][87424] Updated weights for policy 0, policy_version 355609 (0.0009) -[2023-11-28 09:31:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 181985280. Throughput: 0: 2672.7, 1: 2718.7. Samples: 181995792. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:31:58,445][86177] Avg episode reward: [(0, '-523.870'), (1, '-510.290')] -[2023-11-28 09:31:59,267][87426] Updated weights for policy 1, policy_version 355270 (0.0009) -[2023-11-28 09:31:59,651][87426] Updated weights for policy 1, policy_version 355280 (0.0007) -[2023-11-28 09:32:00,029][87426] Updated weights for policy 1, policy_version 355290 (0.0010) -[2023-11-28 09:32:00,519][87424] Updated weights for policy 0, policy_version 355619 (0.0011) -[2023-11-28 09:32:00,904][87424] Updated weights for policy 0, policy_version 355629 (0.0012) -[2023-11-28 09:32:01,279][87424] Updated weights for policy 0, policy_version 355639 (0.0012) -[2023-11-28 09:32:02,121][87426] Updated weights for policy 1, policy_version 355300 (0.0011) -[2023-11-28 09:32:02,508][87426] Updated weights for policy 1, policy_version 355310 (0.0012) -[2023-11-28 09:32:02,881][87426] Updated weights for policy 1, policy_version 355320 (0.0012) -[2023-11-28 09:32:03,422][87424] Updated weights for policy 0, policy_version 355649 (0.0011) -[2023-11-28 09:32:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182009856. Throughput: 0: 2674.7, 1: 2718.4. Samples: 182020404. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:32:03,445][86177] Avg episode reward: [(0, '-525.610'), (1, '-505.580')] -[2023-11-28 09:32:03,799][87424] Updated weights for policy 0, policy_version 355659 (0.0010) -[2023-11-28 09:32:04,190][87424] Updated weights for policy 0, policy_version 355669 (0.0010) -[2023-11-28 09:32:04,565][87424] Updated weights for policy 0, policy_version 355679 (0.0012) -[2023-11-28 09:32:04,962][87426] Updated weights for policy 1, policy_version 355330 (0.0009) -[2023-11-28 09:32:05,342][87426] Updated weights for policy 1, policy_version 355340 (0.0011) -[2023-11-28 09:32:05,721][87426] Updated weights for policy 1, policy_version 355350 (0.0011) -[2023-11-28 09:32:06,108][87426] Updated weights for policy 1, policy_version 355360 (0.0012) -[2023-11-28 09:32:06,604][87424] Updated weights for policy 0, policy_version 355689 (0.0012) -[2023-11-28 09:32:06,987][87424] Updated weights for policy 0, policy_version 355699 (0.0012) -[2023-11-28 09:32:07,393][87424] Updated weights for policy 0, policy_version 355709 (0.0012) -[2023-11-28 09:32:08,245][87426] Updated weights for policy 1, policy_version 355370 (0.0008) -[2023-11-28 09:32:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 182034432. Throughput: 0: 2685.3, 1: 2737.2. Samples: 182053296. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:32:08,445][86177] Avg episode reward: [(0, '-527.040'), (1, '-512.100')] -[2023-11-28 09:32:08,612][87426] Updated weights for policy 1, policy_version 355380 (0.0008) -[2023-11-28 09:32:08,993][87426] Updated weights for policy 1, policy_version 355390 (0.0008) -[2023-11-28 09:32:09,133][87424] Updated weights for policy 0, policy_version 355719 (0.0012) -[2023-11-28 09:32:09,505][87424] Updated weights for policy 0, policy_version 355729 (0.0009) -[2023-11-28 09:32:09,888][87424] Updated weights for policy 0, policy_version 355739 (0.0009) -[2023-11-28 09:32:11,553][87426] Updated weights for policy 1, policy_version 355400 (0.0009) -[2023-11-28 09:32:11,940][87426] Updated weights for policy 1, policy_version 355410 (0.0012) -[2023-11-28 09:32:11,994][87424] Updated weights for policy 0, policy_version 355749 (0.0011) -[2023-11-28 09:32:12,306][87426] Updated weights for policy 1, policy_version 355420 (0.0011) -[2023-11-28 09:32:12,374][87424] Updated weights for policy 0, policy_version 355759 (0.0010) -[2023-11-28 09:32:12,764][87424] Updated weights for policy 0, policy_version 355769 (0.0012) -[2023-11-28 09:32:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 182067200. Throughput: 0: 2691.5, 1: 2700.0. Samples: 182076064. Policy #0 lag: (min: 31.0, avg: 52.9, max: 93.0) -[2023-11-28 09:32:13,445][86177] Avg episode reward: [(0, '-525.080'), (1, '-520.210')] -[2023-11-28 09:32:14,747][87426] Updated weights for policy 1, policy_version 355430 (0.0010) -[2023-11-28 09:32:15,122][87426] Updated weights for policy 1, policy_version 355440 (0.0010) -[2023-11-28 09:32:15,129][87424] Updated weights for policy 0, policy_version 355779 (0.0012) -[2023-11-28 09:32:15,499][87426] Updated weights for policy 1, policy_version 355450 (0.0010) -[2023-11-28 09:32:15,502][87424] Updated weights for policy 0, policy_version 355789 (0.0012) -[2023-11-28 09:32:15,882][87424] Updated weights for policy 0, policy_version 355799 (0.0012) -[2023-11-28 09:32:17,627][87424] Updated weights for policy 0, policy_version 355809 (0.0011) -[2023-11-28 09:32:17,918][87426] Updated weights for policy 1, policy_version 355460 (0.0009) -[2023-11-28 09:32:18,021][87424] Updated weights for policy 0, policy_version 355819 (0.0011) -[2023-11-28 09:32:18,305][87426] Updated weights for policy 1, policy_version 355470 (0.0011) -[2023-11-28 09:32:18,392][87424] Updated weights for policy 0, policy_version 355829 (0.0011) -[2023-11-28 09:32:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 182083584. Throughput: 0: 2705.1, 1: 2684.7. Samples: 182100388. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:32:18,445][86177] Avg episode reward: [(0, '-538.860'), (1, '-544.260')] -[2023-11-28 09:32:18,680][87426] Updated weights for policy 1, policy_version 355480 (0.0008) -[2023-11-28 09:32:18,778][87424] Updated weights for policy 0, policy_version 355839 (0.0009) -[2023-11-28 09:32:18,817][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000355840_91095040.pth... -[2023-11-28 09:32:18,865][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000353280_90439680.pth -[2023-11-28 09:32:18,872][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000355840_91095040.pth -[2023-11-28 09:32:18,988][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000355488_91004928.pth... -[2023-11-28 09:32:19,037][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000352960_90357760.pth -[2023-11-28 09:32:19,044][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000355488_91004928.pth -[2023-11-28 09:32:20,654][87426] Updated weights for policy 1, policy_version 355490 (0.0010) -[2023-11-28 09:32:21,039][87426] Updated weights for policy 1, policy_version 355500 (0.0012) -[2023-11-28 09:32:21,216][87424] Updated weights for policy 0, policy_version 355849 (0.0011) -[2023-11-28 09:32:21,405][87426] Updated weights for policy 1, policy_version 355510 (0.0011) -[2023-11-28 09:32:21,594][87424] Updated weights for policy 0, policy_version 355859 (0.0012) -[2023-11-28 09:32:21,788][87426] Updated weights for policy 1, policy_version 355520 (0.0012) -[2023-11-28 09:32:21,976][87424] Updated weights for policy 0, policy_version 355869 (0.0012) -[2023-11-28 09:32:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 182116352. Throughput: 0: 2699.9, 1: 2696.4. Samples: 182132832. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:32:23,445][86177] Avg episode reward: [(0, '-542.030'), (1, '-553.710')] -[2023-11-28 09:32:24,209][87426] Updated weights for policy 1, policy_version 355530 (0.0007) -[2023-11-28 09:32:24,422][87424] Updated weights for policy 0, policy_version 355879 (0.0011) -[2023-11-28 09:32:24,596][87426] Updated weights for policy 1, policy_version 355540 (0.0008) -[2023-11-28 09:32:24,805][87424] Updated weights for policy 0, policy_version 355889 (0.0011) -[2023-11-28 09:32:24,960][87426] Updated weights for policy 1, policy_version 355550 (0.0011) -[2023-11-28 09:32:25,184][87424] Updated weights for policy 0, policy_version 355899 (0.0012) -[2023-11-28 09:32:26,800][87426] Updated weights for policy 1, policy_version 355560 (0.0011) -[2023-11-28 09:32:27,178][87426] Updated weights for policy 1, policy_version 355570 (0.0011) -[2023-11-28 09:32:27,312][87424] Updated weights for policy 0, policy_version 355909 (0.0012) -[2023-11-28 09:32:27,562][87426] Updated weights for policy 1, policy_version 355580 (0.0008) -[2023-11-28 09:32:27,690][87424] Updated weights for policy 0, policy_version 355919 (0.0012) -[2023-11-28 09:32:28,084][87424] Updated weights for policy 0, policy_version 355929 (0.0012) -[2023-11-28 09:32:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 182149120. Throughput: 0: 2676.2, 1: 2729.2. Samples: 182157644. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:32:28,445][86177] Avg episode reward: [(0, '-551.680'), (1, '-553.380')] -[2023-11-28 09:32:29,474][87426] Updated weights for policy 1, policy_version 355590 (0.0010) -[2023-11-28 09:32:29,854][87426] Updated weights for policy 1, policy_version 355600 (0.0012) -[2023-11-28 09:32:30,236][87426] Updated weights for policy 1, policy_version 355610 (0.0010) -[2023-11-28 09:32:30,290][87424] Updated weights for policy 0, policy_version 355939 (0.0010) -[2023-11-28 09:32:30,668][87424] Updated weights for policy 0, policy_version 355949 (0.0009) -[2023-11-28 09:32:31,045][87424] Updated weights for policy 0, policy_version 355959 (0.0009) -[2023-11-28 09:32:32,410][87426] Updated weights for policy 1, policy_version 355620 (0.0011) -[2023-11-28 09:32:32,796][87426] Updated weights for policy 1, policy_version 355630 (0.0011) -[2023-11-28 09:32:33,184][87426] Updated weights for policy 1, policy_version 355640 (0.0011) -[2023-11-28 09:32:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182165504. Throughput: 0: 2697.5, 1: 2739.8. Samples: 182183216. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:32:33,445][86177] Avg episode reward: [(0, '-558.410'), (1, '-544.030')] -[2023-11-28 09:32:33,532][87424] Updated weights for policy 0, policy_version 355969 (0.0009) -[2023-11-28 09:32:33,915][87424] Updated weights for policy 0, policy_version 355979 (0.0007) -[2023-11-28 09:32:34,302][87424] Updated weights for policy 0, policy_version 355989 (0.0007) -[2023-11-28 09:32:34,680][87424] Updated weights for policy 0, policy_version 355999 (0.0008) -[2023-11-28 09:32:35,720][87426] Updated weights for policy 1, policy_version 355650 (0.0011) -[2023-11-28 09:32:36,091][87426] Updated weights for policy 1, policy_version 355660 (0.0011) -[2023-11-28 09:32:36,477][87426] Updated weights for policy 1, policy_version 355670 (0.0011) -[2023-11-28 09:32:36,848][87426] Updated weights for policy 1, policy_version 355680 (0.0010) -[2023-11-28 09:32:36,916][87424] Updated weights for policy 0, policy_version 356009 (0.0013) -[2023-11-28 09:32:37,289][87424] Updated weights for policy 0, policy_version 356019 (0.0010) -[2023-11-28 09:32:37,665][87424] Updated weights for policy 0, policy_version 356029 (0.0007) -[2023-11-28 09:32:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 182198272. Throughput: 0: 2694.1, 1: 2720.8. Samples: 182214528. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:32:38,445][86177] Avg episode reward: [(0, '-565.890'), (1, '-562.340')] -[2023-11-28 09:32:39,259][87426] Updated weights for policy 1, policy_version 355690 (0.0008) -[2023-11-28 09:32:39,580][87424] Updated weights for policy 0, policy_version 356039 (0.0011) -[2023-11-28 09:32:39,643][87426] Updated weights for policy 1, policy_version 355700 (0.0011) -[2023-11-28 09:32:39,962][87424] Updated weights for policy 0, policy_version 356049 (0.0011) -[2023-11-28 09:32:40,021][87426] Updated weights for policy 1, policy_version 355710 (0.0011) -[2023-11-28 09:32:40,341][87424] Updated weights for policy 0, policy_version 356059 (0.0008) -[2023-11-28 09:32:42,261][87426] Updated weights for policy 1, policy_version 355720 (0.0009) -[2023-11-28 09:32:42,643][87426] Updated weights for policy 1, policy_version 355730 (0.0010) -[2023-11-28 09:32:42,731][87424] Updated weights for policy 0, policy_version 356069 (0.0011) -[2023-11-28 09:32:43,017][87426] Updated weights for policy 1, policy_version 355740 (0.0010) -[2023-11-28 09:32:43,105][87424] Updated weights for policy 0, policy_version 356079 (0.0011) -[2023-11-28 09:32:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182222848. Throughput: 0: 2710.5, 1: 2670.9. Samples: 182237956. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:32:43,445][86177] Avg episode reward: [(0, '-559.830'), (1, '-604.880')] -[2023-11-28 09:32:43,485][87424] Updated weights for policy 0, policy_version 356089 (0.0009) -[2023-11-28 09:32:45,484][87426] Updated weights for policy 1, policy_version 355750 (0.0011) -[2023-11-28 09:32:45,870][87426] Updated weights for policy 1, policy_version 355760 (0.0012) -[2023-11-28 09:32:45,965][87424] Updated weights for policy 0, policy_version 356099 (0.0011) -[2023-11-28 09:32:46,246][87426] Updated weights for policy 1, policy_version 355770 (0.0011) -[2023-11-28 09:32:46,337][87424] Updated weights for policy 0, policy_version 356109 (0.0013) -[2023-11-28 09:32:46,727][87424] Updated weights for policy 0, policy_version 356119 (0.0012) -[2023-11-28 09:32:48,230][87426] Updated weights for policy 1, policy_version 355780 (0.0011) -[2023-11-28 09:32:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 182247424. Throughput: 0: 2698.7, 1: 2659.2. Samples: 182261508. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:32:48,446][86177] Avg episode reward: [(0, '-555.900'), (1, '-602.420')] -[2023-11-28 09:32:48,472][87424] Updated weights for policy 0, policy_version 356129 (0.0011) -[2023-11-28 09:32:48,602][87426] Updated weights for policy 1, policy_version 355790 (0.0012) -[2023-11-28 09:32:48,853][87424] Updated weights for policy 0, policy_version 356139 (0.0011) -[2023-11-28 09:32:48,980][87426] Updated weights for policy 1, policy_version 355800 (0.0011) -[2023-11-28 09:32:49,237][87424] Updated weights for policy 0, policy_version 356149 (0.0010) -[2023-11-28 09:32:49,620][87424] Updated weights for policy 0, policy_version 356159 (0.0012) -[2023-11-28 09:32:51,122][87426] Updated weights for policy 1, policy_version 355810 (0.0010) -[2023-11-28 09:32:51,502][87426] Updated weights for policy 1, policy_version 355820 (0.0009) -[2023-11-28 09:32:51,888][87426] Updated weights for policy 1, policy_version 355830 (0.0011) -[2023-11-28 09:32:51,979][87424] Updated weights for policy 0, policy_version 356169 (0.0011) -[2023-11-28 09:32:52,259][87426] Updated weights for policy 1, policy_version 355840 (0.0010) -[2023-11-28 09:32:52,356][87424] Updated weights for policy 0, policy_version 356179 (0.0010) -[2023-11-28 09:32:52,738][87424] Updated weights for policy 0, policy_version 356189 (0.0011) -[2023-11-28 09:32:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 182280192. Throughput: 0: 2687.6, 1: 2683.6. Samples: 182295004. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:32:53,445][86177] Avg episode reward: [(0, '-555.690'), (1, '-615.870')] -[2023-11-28 09:32:54,535][87426] Updated weights for policy 1, policy_version 355850 (0.0007) -[2023-11-28 09:32:54,896][87424] Updated weights for policy 0, policy_version 356199 (0.0010) -[2023-11-28 09:32:54,915][87426] Updated weights for policy 1, policy_version 355860 (0.0008) -[2023-11-28 09:32:55,273][87424] Updated weights for policy 0, policy_version 356209 (0.0008) -[2023-11-28 09:32:55,304][87426] Updated weights for policy 1, policy_version 355870 (0.0007) -[2023-11-28 09:32:55,656][87424] Updated weights for policy 0, policy_version 356219 (0.0007) -[2023-11-28 09:32:57,194][87426] Updated weights for policy 1, policy_version 355880 (0.0011) -[2023-11-28 09:32:57,565][87426] Updated weights for policy 1, policy_version 355890 (0.0011) -[2023-11-28 09:32:57,738][87424] Updated weights for policy 0, policy_version 356229 (0.0008) -[2023-11-28 09:32:57,937][87426] Updated weights for policy 1, policy_version 355900 (0.0011) -[2023-11-28 09:32:58,118][87424] Updated weights for policy 0, policy_version 356239 (0.0007) -[2023-11-28 09:32:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182304768. Throughput: 0: 2698.7, 1: 2703.9. Samples: 182319180. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:32:58,445][86177] Avg episode reward: [(0, '-580.280'), (1, '-577.340')] -[2023-11-28 09:32:58,503][87424] Updated weights for policy 0, policy_version 356249 (0.0007) -[2023-11-28 09:33:00,274][87426] Updated weights for policy 1, policy_version 355910 (0.0010) -[2023-11-28 09:33:00,655][87426] Updated weights for policy 1, policy_version 355920 (0.0010) -[2023-11-28 09:33:00,846][87424] Updated weights for policy 0, policy_version 356259 (0.0008) -[2023-11-28 09:33:01,038][87426] Updated weights for policy 1, policy_version 355930 (0.0011) -[2023-11-28 09:33:01,228][87424] Updated weights for policy 0, policy_version 356269 (0.0011) -[2023-11-28 09:33:01,607][87424] Updated weights for policy 0, policy_version 356279 (0.0012) -[2023-11-28 09:33:03,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 182329344. Throughput: 0: 2676.5, 1: 2697.9. Samples: 182342236. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:33:03,446][86177] Avg episode reward: [(0, '-579.300'), (1, '-538.000')] -[2023-11-28 09:33:03,488][87426] Updated weights for policy 1, policy_version 355940 (0.0009) -[2023-11-28 09:33:03,873][87426] Updated weights for policy 1, policy_version 355950 (0.0011) -[2023-11-28 09:33:03,910][87424] Updated weights for policy 0, policy_version 356289 (0.0012) -[2023-11-28 09:33:04,252][87426] Updated weights for policy 1, policy_version 355960 (0.0012) -[2023-11-28 09:33:04,282][87424] Updated weights for policy 0, policy_version 356299 (0.0010) -[2023-11-28 09:33:04,663][87424] Updated weights for policy 0, policy_version 356309 (0.0011) -[2023-11-28 09:33:05,054][87424] Updated weights for policy 0, policy_version 356319 (0.0012) -[2023-11-28 09:33:06,441][87426] Updated weights for policy 1, policy_version 355970 (0.0011) -[2023-11-28 09:33:06,766][87424] Updated weights for policy 0, policy_version 356329 (0.0011) -[2023-11-28 09:33:06,828][87426] Updated weights for policy 1, policy_version 355980 (0.0011) -[2023-11-28 09:33:07,141][87424] Updated weights for policy 0, policy_version 356339 (0.0011) -[2023-11-28 09:33:07,192][87426] Updated weights for policy 1, policy_version 355990 (0.0011) -[2023-11-28 09:33:07,527][87424] Updated weights for policy 0, policy_version 356349 (0.0012) -[2023-11-28 09:33:07,569][87426] Updated weights for policy 1, policy_version 356000 (0.0011) -[2023-11-28 09:33:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 182362112. Throughput: 0: 2690.0, 1: 2711.3. Samples: 182375892. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:33:08,445][86177] Avg episode reward: [(0, '-583.190'), (1, '-521.410')] -[2023-11-28 09:33:09,352][87426] Updated weights for policy 1, policy_version 356010 (0.0012) -[2023-11-28 09:33:09,724][87426] Updated weights for policy 1, policy_version 356020 (0.0012) -[2023-11-28 09:33:10,042][87424] Updated weights for policy 0, policy_version 356359 (0.0011) -[2023-11-28 09:33:10,105][87426] Updated weights for policy 1, policy_version 356030 (0.0010) -[2023-11-28 09:33:10,426][87424] Updated weights for policy 0, policy_version 356369 (0.0011) -[2023-11-28 09:33:10,812][87424] Updated weights for policy 0, policy_version 356379 (0.0011) -[2023-11-28 09:33:12,761][87426] Updated weights for policy 1, policy_version 356040 (0.0011) -[2023-11-28 09:33:13,029][87424] Updated weights for policy 0, policy_version 356389 (0.0010) -[2023-11-28 09:33:13,133][87426] Updated weights for policy 1, policy_version 356050 (0.0010) -[2023-11-28 09:33:13,399][87424] Updated weights for policy 0, policy_version 356399 (0.0009) -[2023-11-28 09:33:13,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 182378496. Throughput: 0: 2701.5, 1: 2697.6. Samples: 182400604. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:33:13,445][86177] Avg episode reward: [(0, '-581.630'), (1, '-508.940')] -[2023-11-28 09:33:13,516][87426] Updated weights for policy 1, policy_version 356060 (0.0008) -[2023-11-28 09:33:13,788][87424] Updated weights for policy 0, policy_version 356409 (0.0012) -[2023-11-28 09:33:15,738][87424] Updated weights for policy 0, policy_version 356419 (0.0012) -[2023-11-28 09:33:16,072][87426] Updated weights for policy 1, policy_version 356070 (0.0009) -[2023-11-28 09:33:16,123][87424] Updated weights for policy 0, policy_version 356429 (0.0012) -[2023-11-28 09:33:16,447][87426] Updated weights for policy 1, policy_version 356080 (0.0011) -[2023-11-28 09:33:16,504][87424] Updated weights for policy 0, policy_version 356439 (0.0011) -[2023-11-28 09:33:16,824][87426] Updated weights for policy 1, policy_version 356090 (0.0012) -[2023-11-28 09:33:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 182411264. Throughput: 0: 2699.8, 1: 2674.5. Samples: 182425060. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:33:18,445][86177] Avg episode reward: [(0, '-582.950'), (1, '-535.090')] -[2023-11-28 09:33:18,607][87424] Updated weights for policy 0, policy_version 356449 (0.0012) -[2023-11-28 09:33:19,002][87424] Updated weights for policy 0, policy_version 356459 (0.0010) -[2023-11-28 09:33:19,384][87424] Updated weights for policy 0, policy_version 356469 (0.0008) -[2023-11-28 09:33:19,395][87426] Updated weights for policy 1, policy_version 356100 (0.0009) -[2023-11-28 09:33:19,762][87424] Updated weights for policy 0, policy_version 356479 (0.0008) -[2023-11-28 09:33:19,779][87426] Updated weights for policy 1, policy_version 356110 (0.0008) -[2023-11-28 09:33:20,157][87426] Updated weights for policy 1, policy_version 356120 (0.0010) -[2023-11-28 09:33:22,152][87426] Updated weights for policy 1, policy_version 356130 (0.0010) -[2023-11-28 09:33:22,188][87424] Updated weights for policy 0, policy_version 356489 (0.0011) -[2023-11-28 09:33:22,530][87426] Updated weights for policy 1, policy_version 356140 (0.0010) -[2023-11-28 09:33:22,568][87424] Updated weights for policy 0, policy_version 356499 (0.0011) -[2023-11-28 09:33:22,914][87426] Updated weights for policy 1, policy_version 356150 (0.0011) -[2023-11-28 09:33:22,947][87424] Updated weights for policy 0, policy_version 356509 (0.0012) -[2023-11-28 09:33:23,286][87426] Updated weights for policy 1, policy_version 356160 (0.0012) -[2023-11-28 09:33:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 182444032. Throughput: 0: 2707.4, 1: 2661.2. Samples: 182456112. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:33:23,445][86177] Avg episode reward: [(0, '-581.820'), (1, '-537.990')] -[2023-11-28 09:33:25,019][87424] Updated weights for policy 0, policy_version 356519 (0.0010) -[2023-11-28 09:33:25,398][87424] Updated weights for policy 0, policy_version 356529 (0.0010) -[2023-11-28 09:33:25,572][87426] Updated weights for policy 1, policy_version 356170 (0.0009) -[2023-11-28 09:33:25,781][87424] Updated weights for policy 0, policy_version 356539 (0.0007) -[2023-11-28 09:33:25,960][87426] Updated weights for policy 1, policy_version 356180 (0.0007) -[2023-11-28 09:33:26,340][87426] Updated weights for policy 1, policy_version 356190 (0.0007) -[2023-11-28 09:33:28,236][87426] Updated weights for policy 1, policy_version 356200 (0.0007) -[2023-11-28 09:33:28,316][87424] Updated weights for policy 0, policy_version 356549 (0.0008) -[2023-11-28 09:33:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5415.0). Total num frames: 182460416. Throughput: 0: 2703.5, 1: 2691.3. Samples: 182480720. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:33:28,446][86177] Avg episode reward: [(0, '-591.670'), (1, '-538.400')] -[2023-11-28 09:33:28,613][87426] Updated weights for policy 1, policy_version 356210 (0.0007) -[2023-11-28 09:33:28,697][87424] Updated weights for policy 0, policy_version 356559 (0.0007) -[2023-11-28 09:33:28,987][87426] Updated weights for policy 1, policy_version 356220 (0.0008) -[2023-11-28 09:33:29,073][87424] Updated weights for policy 0, policy_version 356569 (0.0009) -[2023-11-28 09:33:31,197][87424] Updated weights for policy 0, policy_version 356579 (0.0008) -[2023-11-28 09:33:31,345][87426] Updated weights for policy 1, policy_version 356230 (0.0007) -[2023-11-28 09:33:31,571][87424] Updated weights for policy 0, policy_version 356589 (0.0011) -[2023-11-28 09:33:31,722][87426] Updated weights for policy 1, policy_version 356240 (0.0008) -[2023-11-28 09:33:31,956][87424] Updated weights for policy 0, policy_version 356599 (0.0012) -[2023-11-28 09:33:32,099][87426] Updated weights for policy 1, policy_version 356250 (0.0012) -[2023-11-28 09:33:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 182493184. Throughput: 0: 2697.3, 1: 2684.8. Samples: 182503704. Policy #0 lag: (min: 30.0, avg: 47.9, max: 77.0) -[2023-11-28 09:33:33,446][86177] Avg episode reward: [(0, '-602.450'), (1, '-538.000')] -[2023-11-28 09:33:34,115][87424] Updated weights for policy 0, policy_version 356609 (0.0011) -[2023-11-28 09:33:34,246][87426] Updated weights for policy 1, policy_version 356260 (0.0011) -[2023-11-28 09:33:34,496][87424] Updated weights for policy 0, policy_version 356619 (0.0007) -[2023-11-28 09:33:34,624][87426] Updated weights for policy 1, policy_version 356270 (0.0007) -[2023-11-28 09:33:34,880][87424] Updated weights for policy 0, policy_version 356629 (0.0011) -[2023-11-28 09:33:35,002][87426] Updated weights for policy 1, policy_version 356280 (0.0010) -[2023-11-28 09:33:35,269][87424] Updated weights for policy 0, policy_version 356639 (0.0011) -[2023-11-28 09:33:36,877][87426] Updated weights for policy 1, policy_version 356290 (0.0011) -[2023-11-28 09:33:37,253][87426] Updated weights for policy 1, policy_version 356300 (0.0012) -[2023-11-28 09:33:37,633][87426] Updated weights for policy 1, policy_version 356310 (0.0012) -[2023-11-28 09:33:37,743][87424] Updated weights for policy 0, policy_version 356649 (0.0011) -[2023-11-28 09:33:38,005][87426] Updated weights for policy 1, policy_version 356320 (0.0010) -[2023-11-28 09:33:38,122][87424] Updated weights for policy 0, policy_version 356659 (0.0011) -[2023-11-28 09:33:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182517760. Throughput: 0: 2699.1, 1: 2662.8. Samples: 182536292. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:33:38,445][86177] Avg episode reward: [(0, '-639.040'), (1, '-552.040')] -[2023-11-28 09:33:38,512][87424] Updated weights for policy 0, policy_version 356669 (0.0009) -[2023-11-28 09:33:39,931][87426] Updated weights for policy 1, policy_version 356330 (0.0010) -[2023-11-28 09:33:40,300][87426] Updated weights for policy 1, policy_version 356340 (0.0010) -[2023-11-28 09:33:40,680][87426] Updated weights for policy 1, policy_version 356350 (0.0008) -[2023-11-28 09:33:40,811][87424] Updated weights for policy 0, policy_version 356679 (0.0011) -[2023-11-28 09:33:41,196][87424] Updated weights for policy 0, policy_version 356689 (0.0012) -[2023-11-28 09:33:41,584][87424] Updated weights for policy 0, policy_version 356699 (0.0012) -[2023-11-28 09:33:42,853][87426] Updated weights for policy 1, policy_version 356360 (0.0011) -[2023-11-28 09:33:43,228][87426] Updated weights for policy 1, policy_version 356370 (0.0011) -[2023-11-28 09:33:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182542336. Throughput: 0: 2682.0, 1: 2677.6. Samples: 182560364. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:33:43,445][86177] Avg episode reward: [(0, '-648.010'), (1, '-533.200')] -[2023-11-28 09:33:43,604][87426] Updated weights for policy 1, policy_version 356380 (0.0012) -[2023-11-28 09:33:44,162][87424] Updated weights for policy 0, policy_version 356709 (0.0012) -[2023-11-28 09:33:44,541][87424] Updated weights for policy 0, policy_version 356719 (0.0012) -[2023-11-28 09:33:44,917][87424] Updated weights for policy 0, policy_version 356729 (0.0012) -[2023-11-28 09:33:45,823][87426] Updated weights for policy 1, policy_version 356390 (0.0012) -[2023-11-28 09:33:46,198][87426] Updated weights for policy 1, policy_version 356400 (0.0011) -[2023-11-28 09:33:46,575][87426] Updated weights for policy 1, policy_version 356410 (0.0012) -[2023-11-28 09:33:47,067][87424] Updated weights for policy 0, policy_version 356739 (0.0012) -[2023-11-28 09:33:47,461][87424] Updated weights for policy 0, policy_version 356749 (0.0012) -[2023-11-28 09:33:47,841][87424] Updated weights for policy 0, policy_version 356759 (0.0011) -[2023-11-28 09:33:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 182575104. Throughput: 0: 2685.1, 1: 2703.5. Samples: 182584720. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:33:48,445][86177] Avg episode reward: [(0, '-635.800'), (1, '-582.280')] -[2023-11-28 09:33:48,676][87426] Updated weights for policy 1, policy_version 356420 (0.0011) -[2023-11-28 09:33:49,052][87426] Updated weights for policy 1, policy_version 356430 (0.0008) -[2023-11-28 09:33:49,443][87426] Updated weights for policy 1, policy_version 356440 (0.0007) -[2023-11-28 09:33:50,192][87424] Updated weights for policy 0, policy_version 356769 (0.0011) -[2023-11-28 09:33:50,572][87424] Updated weights for policy 0, policy_version 356779 (0.0010) -[2023-11-28 09:33:50,951][87424] Updated weights for policy 0, policy_version 356789 (0.0008) -[2023-11-28 09:33:51,334][87424] Updated weights for policy 0, policy_version 356799 (0.0009) -[2023-11-28 09:33:51,749][87426] Updated weights for policy 1, policy_version 356450 (0.0010) -[2023-11-28 09:33:52,137][87426] Updated weights for policy 1, policy_version 356460 (0.0010) -[2023-11-28 09:33:52,501][87426] Updated weights for policy 1, policy_version 356470 (0.0011) -[2023-11-28 09:33:52,879][87426] Updated weights for policy 1, policy_version 356480 (0.0010) -[2023-11-28 09:33:53,442][87424] Updated weights for policy 0, policy_version 356809 (0.0012) -[2023-11-28 09:33:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182599680. Throughput: 0: 2669.0, 1: 2663.4. Samples: 182615848. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:33:53,445][86177] Avg episode reward: [(0, '-638.650'), (1, '-581.520')] -[2023-11-28 09:33:53,824][87424] Updated weights for policy 0, policy_version 356819 (0.0012) -[2023-11-28 09:33:54,205][87424] Updated weights for policy 0, policy_version 356829 (0.0012) -[2023-11-28 09:33:55,070][87426] Updated weights for policy 1, policy_version 356490 (0.0011) -[2023-11-28 09:33:55,458][87426] Updated weights for policy 1, policy_version 356500 (0.0012) -[2023-11-28 09:33:55,830][87426] Updated weights for policy 1, policy_version 356510 (0.0012) -[2023-11-28 09:33:56,523][87424] Updated weights for policy 0, policy_version 356839 (0.0009) -[2023-11-28 09:33:56,902][87424] Updated weights for policy 0, policy_version 356849 (0.0007) -[2023-11-28 09:33:57,298][87424] Updated weights for policy 0, policy_version 356859 (0.0008) -[2023-11-28 09:33:57,745][87426] Updated weights for policy 1, policy_version 356520 (0.0012) -[2023-11-28 09:33:58,131][87426] Updated weights for policy 1, policy_version 356530 (0.0012) -[2023-11-28 09:33:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182624256. Throughput: 0: 2659.6, 1: 2681.0. Samples: 182640932. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:33:58,445][86177] Avg episode reward: [(0, '-628.420'), (1, '-578.440')] -[2023-11-28 09:33:58,507][87426] Updated weights for policy 1, policy_version 356540 (0.0011) -[2023-11-28 09:33:59,049][87424] Updated weights for policy 0, policy_version 356869 (0.0010) -[2023-11-28 09:33:59,438][87424] Updated weights for policy 0, policy_version 356879 (0.0008) -[2023-11-28 09:33:59,822][87424] Updated weights for policy 0, policy_version 356889 (0.0008) -[2023-11-28 09:34:00,921][87426] Updated weights for policy 1, policy_version 356550 (0.0011) -[2023-11-28 09:34:01,296][87426] Updated weights for policy 1, policy_version 356560 (0.0007) -[2023-11-28 09:34:01,674][87426] Updated weights for policy 1, policy_version 356570 (0.0008) -[2023-11-28 09:34:01,792][87424] Updated weights for policy 0, policy_version 356899 (0.0010) -[2023-11-28 09:34:02,173][87424] Updated weights for policy 0, policy_version 356909 (0.0011) -[2023-11-28 09:34:02,552][87424] Updated weights for policy 0, policy_version 356919 (0.0012) -[2023-11-28 09:34:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 182657024. Throughput: 0: 2658.7, 1: 2705.6. Samples: 182666452. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:03,445][86177] Avg episode reward: [(0, '-616.320'), (1, '-582.260')] -[2023-11-28 09:34:03,507][87426] Updated weights for policy 1, policy_version 356580 (0.0009) -[2023-11-28 09:34:03,886][87426] Updated weights for policy 1, policy_version 356590 (0.0007) -[2023-11-28 09:34:04,266][87426] Updated weights for policy 1, policy_version 356600 (0.0007) -[2023-11-28 09:34:04,928][87424] Updated weights for policy 0, policy_version 356929 (0.0012) -[2023-11-28 09:34:05,313][87424] Updated weights for policy 0, policy_version 356939 (0.0009) -[2023-11-28 09:34:05,694][87424] Updated weights for policy 0, policy_version 356949 (0.0007) -[2023-11-28 09:34:06,079][87424] Updated weights for policy 0, policy_version 356959 (0.0007) -[2023-11-28 09:34:06,476][87426] Updated weights for policy 1, policy_version 356610 (0.0008) -[2023-11-28 09:34:06,858][87426] Updated weights for policy 1, policy_version 356620 (0.0008) -[2023-11-28 09:34:07,236][87426] Updated weights for policy 1, policy_version 356630 (0.0008) -[2023-11-28 09:34:07,633][87426] Updated weights for policy 1, policy_version 356640 (0.0008) -[2023-11-28 09:34:08,426][87424] Updated weights for policy 0, policy_version 356969 (0.0011) -[2023-11-28 09:34:08,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182681600. Throughput: 0: 2661.5, 1: 2719.0. Samples: 182698236. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:08,446][86177] Avg episode reward: [(0, '-609.620'), (1, '-538.680')] -[2023-11-28 09:34:08,817][87424] Updated weights for policy 0, policy_version 356979 (0.0012) -[2023-11-28 09:34:09,198][87424] Updated weights for policy 0, policy_version 356989 (0.0012) -[2023-11-28 09:34:10,112][87426] Updated weights for policy 1, policy_version 356650 (0.0011) -[2023-11-28 09:34:10,493][87426] Updated weights for policy 1, policy_version 356660 (0.0011) -[2023-11-28 09:34:10,859][87426] Updated weights for policy 1, policy_version 356670 (0.0010) -[2023-11-28 09:34:11,453][87424] Updated weights for policy 0, policy_version 356999 (0.0012) -[2023-11-28 09:34:11,826][87424] Updated weights for policy 0, policy_version 357009 (0.0012) -[2023-11-28 09:34:12,209][87424] Updated weights for policy 0, policy_version 357019 (0.0012) -[2023-11-28 09:34:13,226][87426] Updated weights for policy 1, policy_version 356680 (0.0011) -[2023-11-28 09:34:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 182706176. Throughput: 0: 2651.2, 1: 2686.4. Samples: 182720912. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:13,445][86177] Avg episode reward: [(0, '-603.670'), (1, '-541.740')] -[2023-11-28 09:34:13,614][87426] Updated weights for policy 1, policy_version 356690 (0.0011) -[2023-11-28 09:34:13,997][87426] Updated weights for policy 1, policy_version 356700 (0.0011) -[2023-11-28 09:34:14,552][87424] Updated weights for policy 0, policy_version 357029 (0.0010) -[2023-11-28 09:34:14,941][87424] Updated weights for policy 0, policy_version 357039 (0.0007) -[2023-11-28 09:34:15,326][87424] Updated weights for policy 0, policy_version 357049 (0.0008) -[2023-11-28 09:34:16,609][87426] Updated weights for policy 1, policy_version 356710 (0.0012) -[2023-11-28 09:34:16,983][87426] Updated weights for policy 1, policy_version 356720 (0.0011) -[2023-11-28 09:34:17,364][87426] Updated weights for policy 1, policy_version 356730 (0.0011) -[2023-11-28 09:34:17,638][87424] Updated weights for policy 0, policy_version 357059 (0.0009) -[2023-11-28 09:34:18,014][87424] Updated weights for policy 0, policy_version 357069 (0.0010) -[2023-11-28 09:34:18,407][87424] Updated weights for policy 0, policy_version 357079 (0.0011) -[2023-11-28 09:34:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182730752. Throughput: 0: 2662.5, 1: 2701.0. Samples: 182745060. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:18,445][86177] Avg episode reward: [(0, '-578.570'), (1, '-555.690')] -[2023-11-28 09:34:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000356736_91324416.pth... -[2023-11-28 09:34:18,493][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000354208_90677248.pth -[2023-11-28 09:34:18,753][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000357088_91414528.pth... -[2023-11-28 09:34:18,789][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000354560_90767360.pth -[2023-11-28 09:34:19,215][87426] Updated weights for policy 1, policy_version 356740 (0.0010) -[2023-11-28 09:34:19,585][87426] Updated weights for policy 1, policy_version 356750 (0.0009) -[2023-11-28 09:34:19,968][87426] Updated weights for policy 1, policy_version 356760 (0.0010) -[2023-11-28 09:34:20,865][87424] Updated weights for policy 0, policy_version 357089 (0.0011) -[2023-11-28 09:34:21,251][87424] Updated weights for policy 0, policy_version 357099 (0.0011) -[2023-11-28 09:34:21,637][87424] Updated weights for policy 0, policy_version 357109 (0.0011) -[2023-11-28 09:34:22,028][87424] Updated weights for policy 0, policy_version 357119 (0.0011) -[2023-11-28 09:34:22,373][87426] Updated weights for policy 1, policy_version 356770 (0.0011) -[2023-11-28 09:34:22,756][87426] Updated weights for policy 1, policy_version 356780 (0.0011) -[2023-11-28 09:34:23,126][87426] Updated weights for policy 1, policy_version 356790 (0.0009) -[2023-11-28 09:34:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 182755328. Throughput: 0: 2644.2, 1: 2688.6. Samples: 182776268. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:23,445][86177] Avg episode reward: [(0, '-601.130'), (1, '-589.220')] -[2023-11-28 09:34:23,509][87426] Updated weights for policy 1, policy_version 356800 (0.0012) -[2023-11-28 09:34:24,104][87424] Updated weights for policy 0, policy_version 357129 (0.0009) -[2023-11-28 09:34:24,491][87424] Updated weights for policy 0, policy_version 357139 (0.0011) -[2023-11-28 09:34:24,868][87424] Updated weights for policy 0, policy_version 357149 (0.0009) -[2023-11-28 09:34:25,707][87426] Updated weights for policy 1, policy_version 356810 (0.0009) -[2023-11-28 09:34:26,090][87426] Updated weights for policy 1, policy_version 356820 (0.0007) -[2023-11-28 09:34:26,475][87426] Updated weights for policy 1, policy_version 356830 (0.0007) -[2023-11-28 09:34:26,979][87424] Updated weights for policy 0, policy_version 357159 (0.0011) -[2023-11-28 09:34:27,356][87424] Updated weights for policy 0, policy_version 357169 (0.0008) -[2023-11-28 09:34:27,736][87424] Updated weights for policy 0, policy_version 357179 (0.0007) -[2023-11-28 09:34:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 182788096. Throughput: 0: 2662.8, 1: 2670.6. Samples: 182800368. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:28,445][86177] Avg episode reward: [(0, '-613.370'), (1, '-597.630')] -[2023-11-28 09:34:28,807][87426] Updated weights for policy 1, policy_version 356840 (0.0011) -[2023-11-28 09:34:29,203][87426] Updated weights for policy 1, policy_version 356850 (0.0012) -[2023-11-28 09:34:29,575][87426] Updated weights for policy 1, policy_version 356860 (0.0012) -[2023-11-28 09:34:29,902][87424] Updated weights for policy 0, policy_version 357189 (0.0009) -[2023-11-28 09:34:30,290][87424] Updated weights for policy 0, policy_version 357199 (0.0011) -[2023-11-28 09:34:30,670][87424] Updated weights for policy 0, policy_version 357209 (0.0011) -[2023-11-28 09:34:31,745][87426] Updated weights for policy 1, policy_version 356870 (0.0011) -[2023-11-28 09:34:32,118][87426] Updated weights for policy 1, policy_version 356880 (0.0011) -[2023-11-28 09:34:32,503][87426] Updated weights for policy 1, policy_version 356890 (0.0011) -[2023-11-28 09:34:32,862][87424] Updated weights for policy 0, policy_version 357219 (0.0012) -[2023-11-28 09:34:33,241][87424] Updated weights for policy 0, policy_version 357229 (0.0011) -[2023-11-28 09:34:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182812672. Throughput: 0: 2687.5, 1: 2653.4. Samples: 182825060. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:33,445][86177] Avg episode reward: [(0, '-616.840'), (1, '-600.850')] -[2023-11-28 09:34:33,621][87424] Updated weights for policy 0, policy_version 357239 (0.0011) -[2023-11-28 09:34:34,538][87426] Updated weights for policy 1, policy_version 356900 (0.0012) -[2023-11-28 09:34:34,922][87426] Updated weights for policy 1, policy_version 356910 (0.0011) -[2023-11-28 09:34:35,305][87426] Updated weights for policy 1, policy_version 356920 (0.0012) -[2023-11-28 09:34:35,571][87424] Updated weights for policy 0, policy_version 357249 (0.0012) -[2023-11-28 09:34:35,955][87424] Updated weights for policy 0, policy_version 357259 (0.0012) -[2023-11-28 09:34:36,330][87424] Updated weights for policy 0, policy_version 357269 (0.0012) -[2023-11-28 09:34:36,726][87424] Updated weights for policy 0, policy_version 357279 (0.0011) -[2023-11-28 09:34:37,841][87426] Updated weights for policy 1, policy_version 356930 (0.0012) -[2023-11-28 09:34:38,215][87426] Updated weights for policy 1, policy_version 356940 (0.0011) -[2023-11-28 09:34:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182837248. Throughput: 0: 2708.4, 1: 2676.2. Samples: 182858152. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:38,445][86177] Avg episode reward: [(0, '-619.630'), (1, '-590.120')] -[2023-11-28 09:34:38,509][87424] Updated weights for policy 0, policy_version 357289 (0.0011) -[2023-11-28 09:34:38,591][87426] Updated weights for policy 1, policy_version 356950 (0.0009) -[2023-11-28 09:34:38,889][87424] Updated weights for policy 0, policy_version 357299 (0.0012) -[2023-11-28 09:34:38,969][87426] Updated weights for policy 1, policy_version 356960 (0.0009) -[2023-11-28 09:34:39,266][87424] Updated weights for policy 0, policy_version 357309 (0.0012) -[2023-11-28 09:34:41,398][87424] Updated weights for policy 0, policy_version 357319 (0.0011) -[2023-11-28 09:34:41,400][87426] Updated weights for policy 1, policy_version 356970 (0.0011) -[2023-11-28 09:34:41,786][87426] Updated weights for policy 1, policy_version 356980 (0.0011) -[2023-11-28 09:34:41,788][87424] Updated weights for policy 0, policy_version 357329 (0.0012) -[2023-11-28 09:34:42,168][87426] Updated weights for policy 1, policy_version 356990 (0.0012) -[2023-11-28 09:34:42,185][87424] Updated weights for policy 0, policy_version 357339 (0.0011) -[2023-11-28 09:34:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 182870016. Throughput: 0: 2712.0, 1: 2640.5. Samples: 182881792. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:43,445][86177] Avg episode reward: [(0, '-646.830'), (1, '-584.050')] -[2023-11-28 09:34:44,225][87426] Updated weights for policy 1, policy_version 357000 (0.0008) -[2023-11-28 09:34:44,604][87426] Updated weights for policy 1, policy_version 357010 (0.0009) -[2023-11-28 09:34:44,768][87424] Updated weights for policy 0, policy_version 357349 (0.0008) -[2023-11-28 09:34:44,976][87426] Updated weights for policy 1, policy_version 357020 (0.0011) -[2023-11-28 09:34:45,148][87424] Updated weights for policy 0, policy_version 357359 (0.0007) -[2023-11-28 09:34:45,535][87424] Updated weights for policy 0, policy_version 357369 (0.0008) -[2023-11-28 09:34:47,149][87426] Updated weights for policy 1, policy_version 357030 (0.0009) -[2023-11-28 09:34:47,529][87426] Updated weights for policy 1, policy_version 357040 (0.0011) -[2023-11-28 09:34:47,660][87424] Updated weights for policy 0, policy_version 357379 (0.0010) -[2023-11-28 09:34:47,900][87426] Updated weights for policy 1, policy_version 357050 (0.0011) -[2023-11-28 09:34:48,042][87424] Updated weights for policy 0, policy_version 357389 (0.0011) -[2023-11-28 09:34:48,420][87424] Updated weights for policy 0, policy_version 357399 (0.0012) -[2023-11-28 09:34:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 182894592. Throughput: 0: 2687.1, 1: 2636.0. Samples: 182905992. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:48,445][86177] Avg episode reward: [(0, '-631.090'), (1, '-547.040')] -[2023-11-28 09:34:50,263][87426] Updated weights for policy 1, policy_version 357060 (0.0011) -[2023-11-28 09:34:50,639][87426] Updated weights for policy 1, policy_version 357070 (0.0012) -[2023-11-28 09:34:50,853][87424] Updated weights for policy 0, policy_version 357409 (0.0011) -[2023-11-28 09:34:51,007][87426] Updated weights for policy 1, policy_version 357080 (0.0012) -[2023-11-28 09:34:51,249][87424] Updated weights for policy 0, policy_version 357419 (0.0009) -[2023-11-28 09:34:51,620][87424] Updated weights for policy 0, policy_version 357429 (0.0009) -[2023-11-28 09:34:52,022][87424] Updated weights for policy 0, policy_version 357439 (0.0013) -[2023-11-28 09:34:53,165][87426] Updated weights for policy 1, policy_version 357090 (0.0011) -[2023-11-28 09:34:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 182919168. Throughput: 0: 2672.8, 1: 2662.1. Samples: 182938304. Policy #0 lag: (min: 13.0, avg: 29.9, max: 45.0) -[2023-11-28 09:34:53,445][86177] Avg episode reward: [(0, '-655.070'), (1, '-533.470')] -[2023-11-28 09:34:53,547][87426] Updated weights for policy 1, policy_version 357100 (0.0011) -[2023-11-28 09:34:53,914][87426] Updated weights for policy 1, policy_version 357110 (0.0011) -[2023-11-28 09:34:54,291][87426] Updated weights for policy 1, policy_version 357120 (0.0011) -[2023-11-28 09:34:54,356][87424] Updated weights for policy 0, policy_version 357449 (0.0012) -[2023-11-28 09:34:54,744][87424] Updated weights for policy 0, policy_version 357459 (0.0011) -[2023-11-28 09:34:55,136][87424] Updated weights for policy 0, policy_version 357469 (0.0011) -[2023-11-28 09:34:56,397][87426] Updated weights for policy 1, policy_version 357130 (0.0007) -[2023-11-28 09:34:56,787][87426] Updated weights for policy 1, policy_version 357140 (0.0007) -[2023-11-28 09:34:57,167][87426] Updated weights for policy 1, policy_version 357150 (0.0010) -[2023-11-28 09:34:57,230][87424] Updated weights for policy 0, policy_version 357479 (0.0008) -[2023-11-28 09:34:57,618][87424] Updated weights for policy 0, policy_version 357489 (0.0008) -[2023-11-28 09:34:58,006][87424] Updated weights for policy 0, policy_version 357499 (0.0010) -[2023-11-28 09:34:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 182951936. Throughput: 0: 2675.5, 1: 2687.8. Samples: 182962264. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:34:58,445][86177] Avg episode reward: [(0, '-638.470'), (1, '-528.870')] -[2023-11-28 09:34:59,494][87426] Updated weights for policy 1, policy_version 357160 (0.0009) -[2023-11-28 09:34:59,882][87426] Updated weights for policy 1, policy_version 357170 (0.0009) -[2023-11-28 09:35:00,148][87424] Updated weights for policy 0, policy_version 357509 (0.0009) -[2023-11-28 09:35:00,262][87426] Updated weights for policy 1, policy_version 357180 (0.0012) -[2023-11-28 09:35:00,527][87424] Updated weights for policy 0, policy_version 357519 (0.0011) -[2023-11-28 09:35:00,911][87424] Updated weights for policy 0, policy_version 357529 (0.0012) -[2023-11-28 09:35:02,598][87426] Updated weights for policy 1, policy_version 357190 (0.0009) -[2023-11-28 09:35:02,974][87426] Updated weights for policy 1, policy_version 357200 (0.0009) -[2023-11-28 09:35:03,350][87426] Updated weights for policy 1, policy_version 357210 (0.0011) -[2023-11-28 09:35:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 182968320. Throughput: 0: 2704.0, 1: 2684.1. Samples: 182987524. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:03,445][86177] Avg episode reward: [(0, '-639.720'), (1, '-543.260')] -[2023-11-28 09:35:03,540][87424] Updated weights for policy 0, policy_version 357539 (0.0010) -[2023-11-28 09:35:03,925][87424] Updated weights for policy 0, policy_version 357549 (0.0007) -[2023-11-28 09:35:04,312][87424] Updated weights for policy 0, policy_version 357559 (0.0009) -[2023-11-28 09:35:05,257][87426] Updated weights for policy 1, policy_version 357220 (0.0011) -[2023-11-28 09:35:05,627][87426] Updated weights for policy 1, policy_version 357230 (0.0009) -[2023-11-28 09:35:06,008][87426] Updated weights for policy 1, policy_version 357240 (0.0007) -[2023-11-28 09:35:06,119][87424] Updated weights for policy 0, policy_version 357569 (0.0011) -[2023-11-28 09:35:06,506][87424] Updated weights for policy 0, policy_version 357579 (0.0012) -[2023-11-28 09:35:06,875][87424] Updated weights for policy 0, policy_version 357589 (0.0012) -[2023-11-28 09:35:07,256][87424] Updated weights for policy 0, policy_version 357599 (0.0012) -[2023-11-28 09:35:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 183001088. Throughput: 0: 2725.3, 1: 2693.2. Samples: 183020100. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:08,445][86177] Avg episode reward: [(0, '-615.920'), (1, '-548.970')] -[2023-11-28 09:35:08,537][87426] Updated weights for policy 1, policy_version 357250 (0.0009) -[2023-11-28 09:35:08,925][87426] Updated weights for policy 1, policy_version 357260 (0.0012) -[2023-11-28 09:35:09,296][87426] Updated weights for policy 1, policy_version 357270 (0.0012) -[2023-11-28 09:35:09,339][87424] Updated weights for policy 0, policy_version 357609 (0.0012) -[2023-11-28 09:35:09,681][87426] Updated weights for policy 1, policy_version 357280 (0.0011) -[2023-11-28 09:35:09,718][87424] Updated weights for policy 0, policy_version 357619 (0.0009) -[2023-11-28 09:35:10,103][87424] Updated weights for policy 0, policy_version 357629 (0.0009) -[2023-11-28 09:35:11,955][87424] Updated weights for policy 0, policy_version 357639 (0.0010) -[2023-11-28 09:35:12,005][87426] Updated weights for policy 1, policy_version 357290 (0.0011) -[2023-11-28 09:35:12,338][87424] Updated weights for policy 0, policy_version 357649 (0.0011) -[2023-11-28 09:35:12,393][87426] Updated weights for policy 1, policy_version 357300 (0.0011) -[2023-11-28 09:35:12,729][87424] Updated weights for policy 0, policy_version 357659 (0.0012) -[2023-11-28 09:35:12,769][87426] Updated weights for policy 1, policy_version 357310 (0.0011) -[2023-11-28 09:35:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 183033856. Throughput: 0: 2729.0, 1: 2675.6. Samples: 183043572. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:13,445][86177] Avg episode reward: [(0, '-590.060'), (1, '-551.900')] -[2023-11-28 09:35:14,716][87424] Updated weights for policy 0, policy_version 357669 (0.0012) -[2023-11-28 09:35:15,100][87424] Updated weights for policy 0, policy_version 357679 (0.0012) -[2023-11-28 09:35:15,257][87426] Updated weights for policy 1, policy_version 357320 (0.0011) -[2023-11-28 09:35:15,488][87424] Updated weights for policy 0, policy_version 357689 (0.0012) -[2023-11-28 09:35:15,640][87426] Updated weights for policy 1, policy_version 357330 (0.0011) -[2023-11-28 09:35:16,027][87426] Updated weights for policy 1, policy_version 357340 (0.0010) -[2023-11-28 09:35:17,890][87424] Updated weights for policy 0, policy_version 357699 (0.0011) -[2023-11-28 09:35:18,269][87424] Updated weights for policy 0, policy_version 357709 (0.0008) -[2023-11-28 09:35:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 183050240. Throughput: 0: 2731.2, 1: 2668.5. Samples: 183068048. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:18,445][86177] Avg episode reward: [(0, '-582.420'), (1, '-581.030')] -[2023-11-28 09:35:18,545][87426] Updated weights for policy 1, policy_version 357350 (0.0008) -[2023-11-28 09:35:18,646][87424] Updated weights for policy 0, policy_version 357719 (0.0009) -[2023-11-28 09:35:18,922][87426] Updated weights for policy 1, policy_version 357360 (0.0008) -[2023-11-28 09:35:19,300][87426] Updated weights for policy 1, policy_version 357370 (0.0010) -[2023-11-28 09:35:20,530][87424] Updated weights for policy 0, policy_version 357729 (0.0010) -[2023-11-28 09:35:20,912][87424] Updated weights for policy 0, policy_version 357739 (0.0008) -[2023-11-28 09:35:21,296][87424] Updated weights for policy 0, policy_version 357749 (0.0008) -[2023-11-28 09:35:21,473][87426] Updated weights for policy 1, policy_version 357380 (0.0011) -[2023-11-28 09:35:21,676][87424] Updated weights for policy 0, policy_version 357759 (0.0010) -[2023-11-28 09:35:21,875][87426] Updated weights for policy 1, policy_version 357390 (0.0010) -[2023-11-28 09:35:22,242][87426] Updated weights for policy 1, policy_version 357400 (0.0011) -[2023-11-28 09:35:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 183083008. Throughput: 0: 2718.6, 1: 2654.6. Samples: 183099944. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:23,445][86177] Avg episode reward: [(0, '-574.080'), (1, '-565.380')] -[2023-11-28 09:35:23,860][87424] Updated weights for policy 0, policy_version 357769 (0.0008) -[2023-11-28 09:35:24,250][87424] Updated weights for policy 0, policy_version 357779 (0.0007) -[2023-11-28 09:35:24,641][87424] Updated weights for policy 0, policy_version 357789 (0.0008) -[2023-11-28 09:35:24,833][87426] Updated weights for policy 1, policy_version 357410 (0.0011) -[2023-11-28 09:35:25,210][87426] Updated weights for policy 1, policy_version 357420 (0.0012) -[2023-11-28 09:35:25,579][87426] Updated weights for policy 1, policy_version 357430 (0.0012) -[2023-11-28 09:35:25,957][87426] Updated weights for policy 1, policy_version 357440 (0.0012) -[2023-11-28 09:35:26,973][87424] Updated weights for policy 0, policy_version 357799 (0.0008) -[2023-11-28 09:35:27,354][87424] Updated weights for policy 0, policy_version 357809 (0.0007) -[2023-11-28 09:35:27,742][87424] Updated weights for policy 0, policy_version 357819 (0.0007) -[2023-11-28 09:35:28,276][87426] Updated weights for policy 1, policy_version 357450 (0.0011) -[2023-11-28 09:35:28,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183107584. Throughput: 0: 2726.3, 1: 2651.6. Samples: 183123800. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:28,446][86177] Avg episode reward: [(0, '-560.140'), (1, '-583.210')] -[2023-11-28 09:35:28,650][87426] Updated weights for policy 1, policy_version 357460 (0.0012) -[2023-11-28 09:35:29,033][87426] Updated weights for policy 1, policy_version 357470 (0.0012) -[2023-11-28 09:35:29,803][87424] Updated weights for policy 0, policy_version 357829 (0.0008) -[2023-11-28 09:35:30,182][87424] Updated weights for policy 0, policy_version 357839 (0.0009) -[2023-11-28 09:35:30,565][87424] Updated weights for policy 0, policy_version 357849 (0.0009) -[2023-11-28 09:35:31,142][87426] Updated weights for policy 1, policy_version 357480 (0.0012) -[2023-11-28 09:35:31,520][87426] Updated weights for policy 1, policy_version 357490 (0.0010) -[2023-11-28 09:35:31,897][87426] Updated weights for policy 1, policy_version 357500 (0.0011) -[2023-11-28 09:35:32,720][87424] Updated weights for policy 0, policy_version 357859 (0.0010) -[2023-11-28 09:35:33,107][87424] Updated weights for policy 0, policy_version 357869 (0.0012) -[2023-11-28 09:35:33,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183132160. Throughput: 0: 2754.2, 1: 2644.9. Samples: 183148952. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:33,446][86177] Avg episode reward: [(0, '-557.020'), (1, '-585.860')] -[2023-11-28 09:35:33,497][87424] Updated weights for policy 0, policy_version 357879 (0.0012) -[2023-11-28 09:35:34,220][87426] Updated weights for policy 1, policy_version 357510 (0.0009) -[2023-11-28 09:35:34,596][87426] Updated weights for policy 1, policy_version 357520 (0.0007) -[2023-11-28 09:35:34,972][87426] Updated weights for policy 1, policy_version 357530 (0.0011) -[2023-11-28 09:35:36,036][87424] Updated weights for policy 0, policy_version 357889 (0.0008) -[2023-11-28 09:35:36,412][87424] Updated weights for policy 0, policy_version 357899 (0.0012) -[2023-11-28 09:35:36,692][87426] Updated weights for policy 1, policy_version 357540 (0.0010) -[2023-11-28 09:35:36,789][87424] Updated weights for policy 0, policy_version 357909 (0.0011) -[2023-11-28 09:35:37,067][87426] Updated weights for policy 1, policy_version 357550 (0.0010) -[2023-11-28 09:35:37,172][87424] Updated weights for policy 0, policy_version 357919 (0.0010) -[2023-11-28 09:35:37,439][87426] Updated weights for policy 1, policy_version 357560 (0.0012) -[2023-11-28 09:35:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 183164928. Throughput: 0: 2746.5, 1: 2642.5. Samples: 183180808. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:38,445][86177] Avg episode reward: [(0, '-552.270'), (1, '-601.410')] -[2023-11-28 09:35:38,973][87424] Updated weights for policy 0, policy_version 357929 (0.0012) -[2023-11-28 09:35:39,355][87424] Updated weights for policy 0, policy_version 357939 (0.0012) -[2023-11-28 09:35:39,735][87424] Updated weights for policy 0, policy_version 357949 (0.0011) -[2023-11-28 09:35:39,773][87426] Updated weights for policy 1, policy_version 357570 (0.0011) -[2023-11-28 09:35:40,146][87426] Updated weights for policy 1, policy_version 357580 (0.0011) -[2023-11-28 09:35:40,526][87426] Updated weights for policy 1, policy_version 357590 (0.0011) -[2023-11-28 09:35:40,906][87426] Updated weights for policy 1, policy_version 357600 (0.0011) -[2023-11-28 09:35:41,885][87424] Updated weights for policy 0, policy_version 357959 (0.0011) -[2023-11-28 09:35:42,276][87424] Updated weights for policy 0, policy_version 357969 (0.0012) -[2023-11-28 09:35:42,657][87424] Updated weights for policy 0, policy_version 357979 (0.0012) -[2023-11-28 09:35:43,043][87426] Updated weights for policy 1, policy_version 357610 (0.0010) -[2023-11-28 09:35:43,422][87426] Updated weights for policy 1, policy_version 357620 (0.0012) -[2023-11-28 09:35:43,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183189504. Throughput: 0: 2759.6, 1: 2659.9. Samples: 183206140. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:43,445][86177] Avg episode reward: [(0, '-566.040'), (1, '-573.400')] -[2023-11-28 09:35:43,799][87426] Updated weights for policy 1, policy_version 357630 (0.0012) -[2023-11-28 09:35:44,811][87424] Updated weights for policy 0, policy_version 357989 (0.0012) -[2023-11-28 09:35:45,186][87424] Updated weights for policy 0, policy_version 357999 (0.0012) -[2023-11-28 09:35:45,583][87424] Updated weights for policy 0, policy_version 358009 (0.0011) -[2023-11-28 09:35:46,324][87426] Updated weights for policy 1, policy_version 357640 (0.0012) -[2023-11-28 09:35:46,696][87426] Updated weights for policy 1, policy_version 357650 (0.0011) -[2023-11-28 09:35:47,071][87426] Updated weights for policy 1, policy_version 357660 (0.0012) -[2023-11-28 09:35:47,376][87424] Updated weights for policy 0, policy_version 358019 (0.0012) -[2023-11-28 09:35:47,761][87424] Updated weights for policy 0, policy_version 358029 (0.0012) -[2023-11-28 09:35:48,144][87424] Updated weights for policy 0, policy_version 358039 (0.0010) -[2023-11-28 09:35:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 183214080. Throughput: 0: 2755.2, 1: 2641.1. Samples: 183230356. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:48,445][86177] Avg episode reward: [(0, '-572.940'), (1, '-600.230')] -[2023-11-28 09:35:49,130][87426] Updated weights for policy 1, policy_version 357670 (0.0010) -[2023-11-28 09:35:49,506][87426] Updated weights for policy 1, policy_version 357680 (0.0009) -[2023-11-28 09:35:49,896][87426] Updated weights for policy 1, policy_version 357690 (0.0010) -[2023-11-28 09:35:49,901][87424] Updated weights for policy 0, policy_version 358049 (0.0009) -[2023-11-28 09:35:50,282][87424] Updated weights for policy 0, policy_version 358059 (0.0011) -[2023-11-28 09:35:50,671][87424] Updated weights for policy 0, policy_version 358069 (0.0009) -[2023-11-28 09:35:51,057][87424] Updated weights for policy 0, policy_version 358079 (0.0007) -[2023-11-28 09:35:51,896][87426] Updated weights for policy 1, policy_version 357700 (0.0011) -[2023-11-28 09:35:52,273][87426] Updated weights for policy 1, policy_version 357710 (0.0014) -[2023-11-28 09:35:52,660][87426] Updated weights for policy 1, policy_version 357720 (0.0010) -[2023-11-28 09:35:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 183246848. Throughput: 0: 2754.1, 1: 2626.2. Samples: 183262216. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:53,445][86177] Avg episode reward: [(0, '-584.910'), (1, '-578.020')] -[2023-11-28 09:35:53,445][87424] Updated weights for policy 0, policy_version 358089 (0.0010) -[2023-11-28 09:35:53,832][87424] Updated weights for policy 0, policy_version 358099 (0.0012) -[2023-11-28 09:35:54,233][87424] Updated weights for policy 0, policy_version 358109 (0.0011) -[2023-11-28 09:35:54,904][87426] Updated weights for policy 1, policy_version 357730 (0.0010) -[2023-11-28 09:35:55,272][87426] Updated weights for policy 1, policy_version 357740 (0.0011) -[2023-11-28 09:35:55,648][87426] Updated weights for policy 1, policy_version 357750 (0.0012) -[2023-11-28 09:35:56,030][87426] Updated weights for policy 1, policy_version 357760 (0.0012) -[2023-11-28 09:35:56,362][87424] Updated weights for policy 0, policy_version 358119 (0.0011) -[2023-11-28 09:35:56,746][87424] Updated weights for policy 0, policy_version 358129 (0.0011) -[2023-11-28 09:35:57,120][87424] Updated weights for policy 0, policy_version 358139 (0.0012) -[2023-11-28 09:35:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183271424. Throughput: 0: 2749.8, 1: 2664.6. Samples: 183287220. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:35:58,445][86177] Avg episode reward: [(0, '-584.720'), (1, '-602.450')] -[2023-11-28 09:35:58,538][87426] Updated weights for policy 1, policy_version 357770 (0.0007) -[2023-11-28 09:35:58,924][87426] Updated weights for policy 1, policy_version 357780 (0.0008) -[2023-11-28 09:35:59,251][87424] Updated weights for policy 0, policy_version 358149 (0.0012) -[2023-11-28 09:35:59,300][87426] Updated weights for policy 1, policy_version 357790 (0.0008) -[2023-11-28 09:35:59,632][87424] Updated weights for policy 0, policy_version 358159 (0.0012) -[2023-11-28 09:36:00,009][87424] Updated weights for policy 0, policy_version 358169 (0.0012) -[2023-11-28 09:36:01,236][87426] Updated weights for policy 1, policy_version 357800 (0.0009) -[2023-11-28 09:36:01,613][87426] Updated weights for policy 1, policy_version 357810 (0.0011) -[2023-11-28 09:36:02,000][87426] Updated weights for policy 1, policy_version 357820 (0.0011) -[2023-11-28 09:36:02,213][87424] Updated weights for policy 0, policy_version 358179 (0.0012) -[2023-11-28 09:36:02,597][87424] Updated weights for policy 0, policy_version 358189 (0.0010) -[2023-11-28 09:36:02,981][87424] Updated weights for policy 0, policy_version 358199 (0.0010) -[2023-11-28 09:36:03,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 183304192. Throughput: 0: 2777.7, 1: 2678.3. Samples: 183313568. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:36:03,446][86177] Avg episode reward: [(0, '-578.490'), (1, '-631.280')] -[2023-11-28 09:36:03,855][87426] Updated weights for policy 1, policy_version 357830 (0.0012) -[2023-11-28 09:36:04,229][87426] Updated weights for policy 1, policy_version 357840 (0.0008) -[2023-11-28 09:36:04,611][87426] Updated weights for policy 1, policy_version 357850 (0.0008) -[2023-11-28 09:36:04,879][87424] Updated weights for policy 0, policy_version 358209 (0.0012) -[2023-11-28 09:36:05,262][87424] Updated weights for policy 0, policy_version 358219 (0.0010) -[2023-11-28 09:36:05,635][87424] Updated weights for policy 0, policy_version 358229 (0.0008) -[2023-11-28 09:36:06,027][87424] Updated weights for policy 0, policy_version 358239 (0.0007) -[2023-11-28 09:36:07,061][87426] Updated weights for policy 1, policy_version 357860 (0.0010) -[2023-11-28 09:36:07,440][87426] Updated weights for policy 1, policy_version 357870 (0.0011) -[2023-11-28 09:36:07,818][87426] Updated weights for policy 1, policy_version 357880 (0.0008) -[2023-11-28 09:36:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 183328768. Throughput: 0: 2774.3, 1: 2701.1. Samples: 183346340. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:36:08,446][86177] Avg episode reward: [(0, '-614.780'), (1, '-605.420')] -[2023-11-28 09:36:08,523][87424] Updated weights for policy 0, policy_version 358249 (0.0011) -[2023-11-28 09:36:08,904][87424] Updated weights for policy 0, policy_version 358259 (0.0011) -[2023-11-28 09:36:09,287][87424] Updated weights for policy 0, policy_version 358269 (0.0011) -[2023-11-28 09:36:09,657][87426] Updated weights for policy 1, policy_version 357890 (0.0008) -[2023-11-28 09:36:10,058][87426] Updated weights for policy 1, policy_version 357900 (0.0011) -[2023-11-28 09:36:10,431][87426] Updated weights for policy 1, policy_version 357910 (0.0011) -[2023-11-28 09:36:10,811][87426] Updated weights for policy 1, policy_version 357920 (0.0012) -[2023-11-28 09:36:11,649][87424] Updated weights for policy 0, policy_version 358279 (0.0010) -[2023-11-28 09:36:12,032][87424] Updated weights for policy 0, policy_version 358289 (0.0009) -[2023-11-28 09:36:12,412][87424] Updated weights for policy 0, policy_version 358299 (0.0011) -[2023-11-28 09:36:12,855][87426] Updated weights for policy 1, policy_version 357930 (0.0009) -[2023-11-28 09:36:13,238][87426] Updated weights for policy 1, policy_version 357940 (0.0011) -[2023-11-28 09:36:13,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183353344. Throughput: 0: 2764.3, 1: 2698.6. Samples: 183369628. Policy #0 lag: (min: 31.0, avg: 40.0, max: 63.0) -[2023-11-28 09:36:13,445][86177] Avg episode reward: [(0, '-615.320'), (1, '-609.680')] -[2023-11-28 09:36:13,617][87426] Updated weights for policy 1, policy_version 357950 (0.0011) -[2023-11-28 09:36:14,435][87424] Updated weights for policy 0, policy_version 358309 (0.0011) -[2023-11-28 09:36:14,817][87424] Updated weights for policy 0, policy_version 358319 (0.0010) -[2023-11-28 09:36:15,206][87424] Updated weights for policy 0, policy_version 358329 (0.0007) -[2023-11-28 09:36:16,177][87426] Updated weights for policy 1, policy_version 357960 (0.0008) -[2023-11-28 09:36:16,559][87426] Updated weights for policy 1, policy_version 357970 (0.0008) -[2023-11-28 09:36:16,943][87426] Updated weights for policy 1, policy_version 357980 (0.0008) -[2023-11-28 09:36:17,293][87424] Updated weights for policy 0, policy_version 358339 (0.0010) -[2023-11-28 09:36:17,687][87424] Updated weights for policy 0, policy_version 358349 (0.0011) -[2023-11-28 09:36:18,061][87424] Updated weights for policy 0, policy_version 358359 (0.0007) -[2023-11-28 09:36:18,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 183386112. Throughput: 0: 2735.6, 1: 2706.2. Samples: 183393832. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:36:18,445][86177] Avg episode reward: [(0, '-638.460'), (1, '-562.610')] -[2023-11-28 09:36:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000357984_91643904.pth... -[2023-11-28 09:36:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000358368_91742208.pth... -[2023-11-28 09:36:18,495][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000355488_91004928.pth -[2023-11-28 09:36:18,497][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000355840_91095040.pth -[2023-11-28 09:36:19,425][87426] Updated weights for policy 1, policy_version 357990 (0.0008) -[2023-11-28 09:36:19,804][87426] Updated weights for policy 1, policy_version 358000 (0.0008) -[2023-11-28 09:36:20,190][87426] Updated weights for policy 1, policy_version 358010 (0.0011) -[2023-11-28 09:36:20,390][87424] Updated weights for policy 0, policy_version 358369 (0.0008) -[2023-11-28 09:36:20,773][87424] Updated weights for policy 0, policy_version 358379 (0.0012) -[2023-11-28 09:36:21,139][87424] Updated weights for policy 0, policy_version 358389 (0.0012) -[2023-11-28 09:36:21,526][87424] Updated weights for policy 0, policy_version 358399 (0.0012) -[2023-11-28 09:36:22,735][87426] Updated weights for policy 1, policy_version 358020 (0.0011) -[2023-11-28 09:36:23,114][87426] Updated weights for policy 1, policy_version 358030 (0.0011) -[2023-11-28 09:36:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183402496. Throughput: 0: 2739.1, 1: 2669.8. Samples: 183424208. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:36:23,445][86177] Avg episode reward: [(0, '-683.150'), (1, '-547.070')] -[2023-11-28 09:36:23,490][87426] Updated weights for policy 1, policy_version 358040 (0.0012) -[2023-11-28 09:36:23,695][87424] Updated weights for policy 0, policy_version 358409 (0.0010) -[2023-11-28 09:36:24,086][87424] Updated weights for policy 0, policy_version 358419 (0.0011) -[2023-11-28 09:36:24,467][87424] Updated weights for policy 0, policy_version 358429 (0.0012) -[2023-11-28 09:36:25,474][87426] Updated weights for policy 1, policy_version 358050 (0.0011) -[2023-11-28 09:36:25,867][87426] Updated weights for policy 1, policy_version 358060 (0.0010) -[2023-11-28 09:36:26,241][87426] Updated weights for policy 1, policy_version 358070 (0.0008) -[2023-11-28 09:36:26,617][87426] Updated weights for policy 1, policy_version 358080 (0.0007) -[2023-11-28 09:36:26,824][87424] Updated weights for policy 0, policy_version 358439 (0.0012) -[2023-11-28 09:36:27,203][87424] Updated weights for policy 0, policy_version 358449 (0.0012) -[2023-11-28 09:36:27,581][87424] Updated weights for policy 0, policy_version 358459 (0.0012) -[2023-11-28 09:36:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 183435264. Throughput: 0: 2742.0, 1: 2668.2. Samples: 183449596. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:36:28,445][86177] Avg episode reward: [(0, '-642.100'), (1, '-548.280')] -[2023-11-28 09:36:28,795][87426] Updated weights for policy 1, policy_version 358090 (0.0011) -[2023-11-28 09:36:29,180][87426] Updated weights for policy 1, policy_version 358100 (0.0012) -[2023-11-28 09:36:29,250][87424] Updated weights for policy 0, policy_version 358469 (0.0012) -[2023-11-28 09:36:29,561][87426] Updated weights for policy 1, policy_version 358110 (0.0012) -[2023-11-28 09:36:29,629][87424] Updated weights for policy 0, policy_version 358479 (0.0011) -[2023-11-28 09:36:30,011][87424] Updated weights for policy 0, policy_version 358489 (0.0012) -[2023-11-28 09:36:31,900][87426] Updated weights for policy 1, policy_version 358120 (0.0011) -[2023-11-28 09:36:32,286][87426] Updated weights for policy 1, policy_version 358130 (0.0010) -[2023-11-28 09:36:32,350][87424] Updated weights for policy 0, policy_version 358499 (0.0011) -[2023-11-28 09:36:32,662][87426] Updated weights for policy 1, policy_version 358140 (0.0009) -[2023-11-28 09:36:32,745][87424] Updated weights for policy 0, policy_version 358509 (0.0012) -[2023-11-28 09:36:33,117][87424] Updated weights for policy 0, policy_version 358519 (0.0012) -[2023-11-28 09:36:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 183459840. Throughput: 0: 2733.0, 1: 2686.4. Samples: 183474228. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:36:33,445][86177] Avg episode reward: [(0, '-621.200'), (1, '-557.990')] -[2023-11-28 09:36:34,679][87426] Updated weights for policy 1, policy_version 358150 (0.0010) -[2023-11-28 09:36:35,049][87426] Updated weights for policy 1, policy_version 358160 (0.0010) -[2023-11-28 09:36:35,427][87426] Updated weights for policy 1, policy_version 358170 (0.0012) -[2023-11-28 09:36:35,509][87424] Updated weights for policy 0, policy_version 358529 (0.0012) -[2023-11-28 09:36:35,900][87424] Updated weights for policy 0, policy_version 358539 (0.0012) -[2023-11-28 09:36:36,283][87424] Updated weights for policy 0, policy_version 358549 (0.0012) -[2023-11-28 09:36:36,672][87424] Updated weights for policy 0, policy_version 358559 (0.0012) -[2023-11-28 09:36:37,636][87426] Updated weights for policy 1, policy_version 358180 (0.0010) -[2023-11-28 09:36:38,009][87426] Updated weights for policy 1, policy_version 358190 (0.0007) -[2023-11-28 09:36:38,386][87426] Updated weights for policy 1, policy_version 358200 (0.0007) -[2023-11-28 09:36:38,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183484416. Throughput: 0: 2722.4, 1: 2698.6. Samples: 183506164. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:36:38,446][86177] Avg episode reward: [(0, '-585.870'), (1, '-562.230')] -[2023-11-28 09:36:39,205][87424] Updated weights for policy 0, policy_version 358569 (0.0012) -[2023-11-28 09:36:39,587][87424] Updated weights for policy 0, policy_version 358579 (0.0011) -[2023-11-28 09:36:39,975][87424] Updated weights for policy 0, policy_version 358589 (0.0011) -[2023-11-28 09:36:40,857][87426] Updated weights for policy 1, policy_version 358210 (0.0008) -[2023-11-28 09:36:41,238][87426] Updated weights for policy 1, policy_version 358220 (0.0012) -[2023-11-28 09:36:41,607][87426] Updated weights for policy 1, policy_version 358230 (0.0012) -[2023-11-28 09:36:41,967][87424] Updated weights for policy 0, policy_version 358599 (0.0010) -[2023-11-28 09:36:41,982][87426] Updated weights for policy 1, policy_version 358240 (0.0012) -[2023-11-28 09:36:42,352][87424] Updated weights for policy 0, policy_version 358609 (0.0012) -[2023-11-28 09:36:42,733][87424] Updated weights for policy 0, policy_version 358619 (0.0011) -[2023-11-28 09:36:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 183517184. Throughput: 0: 2707.3, 1: 2673.0. Samples: 183529332. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:36:43,445][86177] Avg episode reward: [(0, '-556.220'), (1, '-575.950')] -[2023-11-28 09:36:44,576][87426] Updated weights for policy 1, policy_version 358250 (0.0008) -[2023-11-28 09:36:44,952][87426] Updated weights for policy 1, policy_version 358260 (0.0012) -[2023-11-28 09:36:45,133][87424] Updated weights for policy 0, policy_version 358629 (0.0011) -[2023-11-28 09:36:45,329][87426] Updated weights for policy 1, policy_version 358270 (0.0011) -[2023-11-28 09:36:45,509][87424] Updated weights for policy 0, policy_version 358639 (0.0010) -[2023-11-28 09:36:45,897][87424] Updated weights for policy 0, policy_version 358649 (0.0011) -[2023-11-28 09:36:47,352][87426] Updated weights for policy 1, policy_version 358280 (0.0011) -[2023-11-28 09:36:47,729][87426] Updated weights for policy 1, policy_version 358290 (0.0012) -[2023-11-28 09:36:48,055][87424] Updated weights for policy 0, policy_version 358659 (0.0011) -[2023-11-28 09:36:48,112][87426] Updated weights for policy 1, policy_version 358300 (0.0012) -[2023-11-28 09:36:48,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 183541760. Throughput: 0: 2648.3, 1: 2671.1. Samples: 183552940. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:36:48,444][87424] Updated weights for policy 0, policy_version 358669 (0.0011) -[2023-11-28 09:36:48,445][86177] Avg episode reward: [(0, '-556.900'), (1, '-573.750')] -[2023-11-28 09:36:48,822][87424] Updated weights for policy 0, policy_version 358679 (0.0009) -[2023-11-28 09:36:50,073][87426] Updated weights for policy 1, policy_version 358310 (0.0012) -[2023-11-28 09:36:50,455][87426] Updated weights for policy 1, policy_version 358320 (0.0008) -[2023-11-28 09:36:50,840][87426] Updated weights for policy 1, policy_version 358330 (0.0012) -[2023-11-28 09:36:51,395][87424] Updated weights for policy 0, policy_version 358689 (0.0011) -[2023-11-28 09:36:51,793][87424] Updated weights for policy 0, policy_version 358699 (0.0011) -[2023-11-28 09:36:52,170][87424] Updated weights for policy 0, policy_version 358709 (0.0012) -[2023-11-28 09:36:52,551][87424] Updated weights for policy 0, policy_version 358719 (0.0009) -[2023-11-28 09:36:53,264][87426] Updated weights for policy 1, policy_version 358340 (0.0009) -[2023-11-28 09:36:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183566336. Throughput: 0: 2636.6, 1: 2653.6. Samples: 183584400. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:36:53,445][86177] Avg episode reward: [(0, '-576.090'), (1, '-581.390')] -[2023-11-28 09:36:53,642][87426] Updated weights for policy 1, policy_version 358350 (0.0012) -[2023-11-28 09:36:54,024][87426] Updated weights for policy 1, policy_version 358360 (0.0012) -[2023-11-28 09:36:54,758][87424] Updated weights for policy 0, policy_version 358729 (0.0011) -[2023-11-28 09:36:55,144][87424] Updated weights for policy 0, policy_version 358739 (0.0011) -[2023-11-28 09:36:55,529][87424] Updated weights for policy 0, policy_version 358749 (0.0010) -[2023-11-28 09:36:56,086][87426] Updated weights for policy 1, policy_version 358370 (0.0012) -[2023-11-28 09:36:56,463][87426] Updated weights for policy 1, policy_version 358380 (0.0007) -[2023-11-28 09:36:56,854][87426] Updated weights for policy 1, policy_version 358390 (0.0009) -[2023-11-28 09:36:57,224][87426] Updated weights for policy 1, policy_version 358400 (0.0011) -[2023-11-28 09:36:57,478][87424] Updated weights for policy 0, policy_version 358759 (0.0008) -[2023-11-28 09:36:57,862][87424] Updated weights for policy 0, policy_version 358769 (0.0007) -[2023-11-28 09:36:58,237][87424] Updated weights for policy 0, policy_version 358779 (0.0007) -[2023-11-28 09:36:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 183599104. Throughput: 0: 2642.3, 1: 2679.9. Samples: 183609128. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:36:58,445][86177] Avg episode reward: [(0, '-578.590'), (1, '-596.150')] -[2023-11-28 09:36:59,402][87426] Updated weights for policy 1, policy_version 358410 (0.0007) -[2023-11-28 09:36:59,789][87426] Updated weights for policy 1, policy_version 358420 (0.0009) -[2023-11-28 09:37:00,158][87426] Updated weights for policy 1, policy_version 358430 (0.0011) -[2023-11-28 09:37:00,755][87424] Updated weights for policy 0, policy_version 358789 (0.0007) -[2023-11-28 09:37:01,139][87424] Updated weights for policy 0, policy_version 358799 (0.0011) -[2023-11-28 09:37:01,519][87424] Updated weights for policy 0, policy_version 358809 (0.0010) -[2023-11-28 09:37:02,531][87426] Updated weights for policy 1, policy_version 358440 (0.0008) -[2023-11-28 09:37:02,905][87426] Updated weights for policy 1, policy_version 358450 (0.0008) -[2023-11-28 09:37:03,283][87426] Updated weights for policy 1, policy_version 358460 (0.0008) -[2023-11-28 09:37:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 183623680. Throughput: 0: 2636.0, 1: 2670.1. Samples: 183632604. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:37:03,445][86177] Avg episode reward: [(0, '-600.120'), (1, '-571.250')] -[2023-11-28 09:37:04,062][87424] Updated weights for policy 0, policy_version 358819 (0.0013) -[2023-11-28 09:37:04,441][87424] Updated weights for policy 0, policy_version 358829 (0.0008) -[2023-11-28 09:37:04,827][87424] Updated weights for policy 0, policy_version 358839 (0.0008) -[2023-11-28 09:37:05,744][87426] Updated weights for policy 1, policy_version 358470 (0.0010) -[2023-11-28 09:37:06,124][87426] Updated weights for policy 1, policy_version 358480 (0.0012) -[2023-11-28 09:37:06,513][87426] Updated weights for policy 1, policy_version 358490 (0.0012) -[2023-11-28 09:37:07,159][87424] Updated weights for policy 0, policy_version 358849 (0.0008) -[2023-11-28 09:37:07,545][87424] Updated weights for policy 0, policy_version 358859 (0.0008) -[2023-11-28 09:37:07,932][87424] Updated weights for policy 0, policy_version 358869 (0.0008) -[2023-11-28 09:37:08,309][87424] Updated weights for policy 0, policy_version 358879 (0.0008) -[2023-11-28 09:37:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183648256. Throughput: 0: 2631.8, 1: 2688.3. Samples: 183663616. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:37:08,446][86177] Avg episode reward: [(0, '-602.350'), (1, '-554.180')] -[2023-11-28 09:37:08,552][87426] Updated weights for policy 1, policy_version 358500 (0.0010) -[2023-11-28 09:37:08,934][87426] Updated weights for policy 1, policy_version 358510 (0.0008) -[2023-11-28 09:37:09,306][87426] Updated weights for policy 1, policy_version 358520 (0.0009) -[2023-11-28 09:37:10,143][87424] Updated weights for policy 0, policy_version 358889 (0.0012) -[2023-11-28 09:37:10,517][87424] Updated weights for policy 0, policy_version 358899 (0.0012) -[2023-11-28 09:37:10,909][87424] Updated weights for policy 0, policy_version 358909 (0.0011) -[2023-11-28 09:37:11,436][87426] Updated weights for policy 1, policy_version 358530 (0.0009) -[2023-11-28 09:37:11,806][87426] Updated weights for policy 1, policy_version 358540 (0.0012) -[2023-11-28 09:37:12,197][87426] Updated weights for policy 1, policy_version 358550 (0.0012) -[2023-11-28 09:37:12,571][87426] Updated weights for policy 1, policy_version 358560 (0.0012) -[2023-11-28 09:37:13,393][87424] Updated weights for policy 0, policy_version 358919 (0.0011) -[2023-11-28 09:37:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 183672832. Throughput: 0: 2610.1, 1: 2669.7. Samples: 183687188. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:37:13,445][86177] Avg episode reward: [(0, '-602.270'), (1, '-555.970')] -[2023-11-28 09:37:13,777][87424] Updated weights for policy 0, policy_version 358929 (0.0012) -[2023-11-28 09:37:14,161][87424] Updated weights for policy 0, policy_version 358939 (0.0012) -[2023-11-28 09:37:14,796][87426] Updated weights for policy 1, policy_version 358570 (0.0012) -[2023-11-28 09:37:15,177][87426] Updated weights for policy 1, policy_version 358580 (0.0012) -[2023-11-28 09:37:15,557][87426] Updated weights for policy 1, policy_version 358590 (0.0011) -[2023-11-28 09:37:16,495][87424] Updated weights for policy 0, policy_version 358949 (0.0010) -[2023-11-28 09:37:16,876][87424] Updated weights for policy 0, policy_version 358959 (0.0008) -[2023-11-28 09:37:17,260][87424] Updated weights for policy 0, policy_version 358969 (0.0007) -[2023-11-28 09:37:17,768][87426] Updated weights for policy 1, policy_version 358600 (0.0012) -[2023-11-28 09:37:18,146][87426] Updated weights for policy 1, policy_version 358610 (0.0011) -[2023-11-28 09:37:18,445][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 183697408. Throughput: 0: 2614.5, 1: 2673.9. Samples: 183712208. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:37:18,446][86177] Avg episode reward: [(0, '-602.290'), (1, '-563.090')] -[2023-11-28 09:37:18,538][87426] Updated weights for policy 1, policy_version 358620 (0.0012) -[2023-11-28 09:37:19,045][87424] Updated weights for policy 0, policy_version 358979 (0.0010) -[2023-11-28 09:37:19,434][87424] Updated weights for policy 0, policy_version 358989 (0.0012) -[2023-11-28 09:37:19,813][87424] Updated weights for policy 0, policy_version 358999 (0.0011) -[2023-11-28 09:37:20,553][87426] Updated weights for policy 1, policy_version 358630 (0.0010) -[2023-11-28 09:37:20,927][87426] Updated weights for policy 1, policy_version 358640 (0.0011) -[2023-11-28 09:37:21,322][87426] Updated weights for policy 1, policy_version 358650 (0.0009) -[2023-11-28 09:37:22,179][87424] Updated weights for policy 0, policy_version 359009 (0.0010) -[2023-11-28 09:37:22,556][87424] Updated weights for policy 0, policy_version 359019 (0.0009) -[2023-11-28 09:37:22,937][87424] Updated weights for policy 0, policy_version 359029 (0.0011) -[2023-11-28 09:37:23,313][87424] Updated weights for policy 0, policy_version 359039 (0.0008) -[2023-11-28 09:37:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 183730176. Throughput: 0: 2608.8, 1: 2678.3. Samples: 183744084. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:37:23,445][86177] Avg episode reward: [(0, '-615.640'), (1, '-559.870')] -[2023-11-28 09:37:23,723][87426] Updated weights for policy 1, policy_version 358660 (0.0011) -[2023-11-28 09:37:24,104][87426] Updated weights for policy 1, policy_version 358670 (0.0012) -[2023-11-28 09:37:24,494][87426] Updated weights for policy 1, policy_version 358680 (0.0012) -[2023-11-28 09:37:25,668][87424] Updated weights for policy 0, policy_version 359049 (0.0012) -[2023-11-28 09:37:26,062][87424] Updated weights for policy 0, policy_version 359059 (0.0012) -[2023-11-28 09:37:26,444][87424] Updated weights for policy 0, policy_version 359069 (0.0012) -[2023-11-28 09:37:26,854][87426] Updated weights for policy 1, policy_version 358690 (0.0012) -[2023-11-28 09:37:27,231][87426] Updated weights for policy 1, policy_version 358700 (0.0012) -[2023-11-28 09:37:27,609][87426] Updated weights for policy 1, policy_version 358710 (0.0012) -[2023-11-28 09:37:27,979][87426] Updated weights for policy 1, policy_version 358720 (0.0012) -[2023-11-28 09:37:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 183754752. Throughput: 0: 2615.8, 1: 2688.5. Samples: 183768028. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:37:28,445][86177] Avg episode reward: [(0, '-605.870'), (1, '-582.540')] -[2023-11-28 09:37:28,624][87424] Updated weights for policy 0, policy_version 359079 (0.0010) -[2023-11-28 09:37:29,010][87424] Updated weights for policy 0, policy_version 359089 (0.0008) -[2023-11-28 09:37:29,392][87424] Updated weights for policy 0, policy_version 359099 (0.0007) -[2023-11-28 09:37:30,179][87426] Updated weights for policy 1, policy_version 358730 (0.0011) -[2023-11-28 09:37:30,555][87426] Updated weights for policy 1, policy_version 358740 (0.0012) -[2023-11-28 09:37:30,942][87426] Updated weights for policy 1, policy_version 358750 (0.0009) -[2023-11-28 09:37:31,642][87424] Updated weights for policy 0, policy_version 359109 (0.0011) -[2023-11-28 09:37:32,018][87424] Updated weights for policy 0, policy_version 359119 (0.0011) -[2023-11-28 09:37:32,398][87424] Updated weights for policy 0, policy_version 359129 (0.0011) -[2023-11-28 09:37:33,020][87426] Updated weights for policy 1, policy_version 358760 (0.0011) -[2023-11-28 09:37:33,408][87426] Updated weights for policy 1, policy_version 358770 (0.0010) -[2023-11-28 09:37:33,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183779328. Throughput: 0: 2648.2, 1: 2687.3. Samples: 183793036. Policy #0 lag: (min: 39.0, avg: 45.8, max: 71.0) -[2023-11-28 09:37:33,446][86177] Avg episode reward: [(0, '-597.480'), (1, '-582.660')] -[2023-11-28 09:37:33,790][87426] Updated weights for policy 1, policy_version 358780 (0.0007) -[2023-11-28 09:37:34,464][87424] Updated weights for policy 0, policy_version 359139 (0.0010) -[2023-11-28 09:37:34,844][87424] Updated weights for policy 0, policy_version 359149 (0.0012) -[2023-11-28 09:37:35,221][87424] Updated weights for policy 0, policy_version 359159 (0.0012) -[2023-11-28 09:37:35,707][87426] Updated weights for policy 1, policy_version 358790 (0.0008) -[2023-11-28 09:37:36,074][87426] Updated weights for policy 1, policy_version 358800 (0.0007) -[2023-11-28 09:37:36,452][87426] Updated weights for policy 1, policy_version 358810 (0.0008) -[2023-11-28 09:37:37,298][87424] Updated weights for policy 0, policy_version 359169 (0.0012) -[2023-11-28 09:37:37,676][87424] Updated weights for policy 0, policy_version 359179 (0.0010) -[2023-11-28 09:37:38,061][87424] Updated weights for policy 0, policy_version 359189 (0.0007) -[2023-11-28 09:37:38,440][87424] Updated weights for policy 0, policy_version 359199 (0.0007) -[2023-11-28 09:37:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183803904. Throughput: 0: 2668.6, 1: 2710.9. Samples: 183826480. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:37:38,446][86177] Avg episode reward: [(0, '-585.650'), (1, '-568.170')] -[2023-11-28 09:37:38,820][87426] Updated weights for policy 1, policy_version 358820 (0.0008) -[2023-11-28 09:37:39,195][87426] Updated weights for policy 1, policy_version 358830 (0.0009) -[2023-11-28 09:37:39,576][87426] Updated weights for policy 1, policy_version 358840 (0.0008) -[2023-11-28 09:37:40,494][87424] Updated weights for policy 0, policy_version 359209 (0.0010) -[2023-11-28 09:37:40,874][87424] Updated weights for policy 0, policy_version 359219 (0.0011) -[2023-11-28 09:37:41,254][87424] Updated weights for policy 0, policy_version 359229 (0.0011) -[2023-11-28 09:37:42,001][87426] Updated weights for policy 1, policy_version 358850 (0.0010) -[2023-11-28 09:37:42,385][87426] Updated weights for policy 1, policy_version 358860 (0.0012) -[2023-11-28 09:37:42,767][87426] Updated weights for policy 1, policy_version 358870 (0.0012) -[2023-11-28 09:37:43,139][87426] Updated weights for policy 1, policy_version 358880 (0.0012) -[2023-11-28 09:37:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 183836672. Throughput: 0: 2658.6, 1: 2683.0. Samples: 183849500. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:37:43,445][86177] Avg episode reward: [(0, '-578.830'), (1, '-569.810')] -[2023-11-28 09:37:43,821][87424] Updated weights for policy 0, policy_version 359239 (0.0011) -[2023-11-28 09:37:44,205][87424] Updated weights for policy 0, policy_version 359249 (0.0007) -[2023-11-28 09:37:44,594][87424] Updated weights for policy 0, policy_version 359259 (0.0010) -[2023-11-28 09:37:45,122][87426] Updated weights for policy 1, policy_version 358890 (0.0008) -[2023-11-28 09:37:45,501][87426] Updated weights for policy 1, policy_version 358900 (0.0008) -[2023-11-28 09:37:45,882][87426] Updated weights for policy 1, policy_version 358910 (0.0007) -[2023-11-28 09:37:46,452][87424] Updated weights for policy 0, policy_version 359269 (0.0011) -[2023-11-28 09:37:46,839][87424] Updated weights for policy 0, policy_version 359279 (0.0009) -[2023-11-28 09:37:47,219][87424] Updated weights for policy 0, policy_version 359289 (0.0007) -[2023-11-28 09:37:47,631][87426] Updated weights for policy 1, policy_version 358920 (0.0011) -[2023-11-28 09:37:48,010][87426] Updated weights for policy 1, policy_version 358930 (0.0012) -[2023-11-28 09:37:48,386][87426] Updated weights for policy 1, policy_version 358940 (0.0011) -[2023-11-28 09:37:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183861248. Throughput: 0: 2666.4, 1: 2716.0. Samples: 183874812. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:37:48,446][86177] Avg episode reward: [(0, '-573.320'), (1, '-563.950')] -[2023-11-28 09:37:49,492][87424] Updated weights for policy 0, policy_version 359299 (0.0011) -[2023-11-28 09:37:49,880][87424] Updated weights for policy 0, policy_version 359309 (0.0012) -[2023-11-28 09:37:50,254][87424] Updated weights for policy 0, policy_version 359319 (0.0011) -[2023-11-28 09:37:50,579][87426] Updated weights for policy 1, policy_version 358950 (0.0010) -[2023-11-28 09:37:50,965][87426] Updated weights for policy 1, policy_version 358960 (0.0008) -[2023-11-28 09:37:51,349][87426] Updated weights for policy 1, policy_version 358970 (0.0008) -[2023-11-28 09:37:52,703][87424] Updated weights for policy 0, policy_version 359329 (0.0012) -[2023-11-28 09:37:53,077][87424] Updated weights for policy 0, policy_version 359339 (0.0012) -[2023-11-28 09:37:53,215][87426] Updated weights for policy 1, policy_version 358980 (0.0010) -[2023-11-28 09:37:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 183885824. Throughput: 0: 2693.3, 1: 2741.6. Samples: 183908188. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:37:53,445][86177] Avg episode reward: [(0, '-583.900'), (1, '-560.060')] -[2023-11-28 09:37:53,460][87424] Updated weights for policy 0, policy_version 359349 (0.0012) -[2023-11-28 09:37:53,593][87426] Updated weights for policy 1, policy_version 358990 (0.0012) -[2023-11-28 09:37:53,838][87424] Updated weights for policy 0, policy_version 359359 (0.0010) -[2023-11-28 09:37:53,970][87426] Updated weights for policy 1, policy_version 359000 (0.0010) -[2023-11-28 09:37:55,787][87426] Updated weights for policy 1, policy_version 359010 (0.0011) -[2023-11-28 09:37:56,095][87424] Updated weights for policy 0, policy_version 359369 (0.0011) -[2023-11-28 09:37:56,165][87426] Updated weights for policy 1, policy_version 359020 (0.0007) -[2023-11-28 09:37:56,477][87424] Updated weights for policy 0, policy_version 359379 (0.0008) -[2023-11-28 09:37:56,553][87426] Updated weights for policy 1, policy_version 359030 (0.0007) -[2023-11-28 09:37:56,863][87424] Updated weights for policy 0, policy_version 359389 (0.0008) -[2023-11-28 09:37:56,938][87426] Updated weights for policy 1, policy_version 359040 (0.0007) -[2023-11-28 09:37:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 183918592. Throughput: 0: 2702.6, 1: 2763.4. Samples: 183933156. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:37:58,445][86177] Avg episode reward: [(0, '-616.340'), (1, '-575.710')] -[2023-11-28 09:37:58,890][87426] Updated weights for policy 1, policy_version 359050 (0.0008) -[2023-11-28 09:37:59,124][87424] Updated weights for policy 0, policy_version 359399 (0.0009) -[2023-11-28 09:37:59,275][87426] Updated weights for policy 1, policy_version 359060 (0.0009) -[2023-11-28 09:37:59,507][87424] Updated weights for policy 0, policy_version 359409 (0.0011) -[2023-11-28 09:37:59,642][87426] Updated weights for policy 1, policy_version 359070 (0.0007) -[2023-11-28 09:37:59,891][87424] Updated weights for policy 0, policy_version 359419 (0.0008) -[2023-11-28 09:38:01,836][87426] Updated weights for policy 1, policy_version 359080 (0.0011) -[2023-11-28 09:38:02,044][87424] Updated weights for policy 0, policy_version 359429 (0.0012) -[2023-11-28 09:38:02,214][87426] Updated weights for policy 1, policy_version 359090 (0.0011) -[2023-11-28 09:38:02,422][87424] Updated weights for policy 0, policy_version 359439 (0.0011) -[2023-11-28 09:38:02,592][87426] Updated weights for policy 1, policy_version 359100 (0.0010) -[2023-11-28 09:38:02,812][87424] Updated weights for policy 0, policy_version 359449 (0.0011) -[2023-11-28 09:38:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 183951360. Throughput: 0: 2690.0, 1: 2757.9. Samples: 183957360. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:03,445][86177] Avg episode reward: [(0, '-613.900'), (1, '-570.270')] -[2023-11-28 09:38:05,014][87426] Updated weights for policy 1, policy_version 359110 (0.0011) -[2023-11-28 09:38:05,036][87424] Updated weights for policy 0, policy_version 359459 (0.0012) -[2023-11-28 09:38:05,398][87426] Updated weights for policy 1, policy_version 359120 (0.0007) -[2023-11-28 09:38:05,417][87424] Updated weights for policy 0, policy_version 359469 (0.0011) -[2023-11-28 09:38:05,769][87426] Updated weights for policy 1, policy_version 359130 (0.0009) -[2023-11-28 09:38:05,797][87424] Updated weights for policy 0, policy_version 359479 (0.0011) -[2023-11-28 09:38:07,524][87424] Updated weights for policy 0, policy_version 359489 (0.0011) -[2023-11-28 09:38:07,909][87424] Updated weights for policy 0, policy_version 359499 (0.0007) -[2023-11-28 09:38:08,170][87426] Updated weights for policy 1, policy_version 359140 (0.0009) -[2023-11-28 09:38:08,294][87424] Updated weights for policy 0, policy_version 359509 (0.0008) -[2023-11-28 09:38:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 183967744. Throughput: 0: 2712.5, 1: 2754.9. Samples: 183990120. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:08,445][86177] Avg episode reward: [(0, '-622.210'), (1, '-622.730')] -[2023-11-28 09:38:08,556][87426] Updated weights for policy 1, policy_version 359150 (0.0012) -[2023-11-28 09:38:08,673][87424] Updated weights for policy 0, policy_version 359519 (0.0007) -[2023-11-28 09:38:08,931][87426] Updated weights for policy 1, policy_version 359160 (0.0010) -[2023-11-28 09:38:10,890][87424] Updated weights for policy 0, policy_version 359529 (0.0009) -[2023-11-28 09:38:11,273][87424] Updated weights for policy 0, policy_version 359539 (0.0012) -[2023-11-28 09:38:11,508][87426] Updated weights for policy 1, policy_version 359170 (0.0009) -[2023-11-28 09:38:11,655][87424] Updated weights for policy 0, policy_version 359549 (0.0012) -[2023-11-28 09:38:11,888][87426] Updated weights for policy 1, policy_version 359180 (0.0012) -[2023-11-28 09:38:12,268][87426] Updated weights for policy 1, policy_version 359190 (0.0010) -[2023-11-28 09:38:12,647][87426] Updated weights for policy 1, policy_version 359200 (0.0008) -[2023-11-28 09:38:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184000512. Throughput: 0: 2703.3, 1: 2734.8. Samples: 184012740. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:13,445][86177] Avg episode reward: [(0, '-605.230'), (1, '-602.940')] -[2023-11-28 09:38:14,122][87424] Updated weights for policy 0, policy_version 359559 (0.0012) -[2023-11-28 09:38:14,505][87424] Updated weights for policy 0, policy_version 359569 (0.0008) -[2023-11-28 09:38:14,884][87424] Updated weights for policy 0, policy_version 359579 (0.0010) -[2023-11-28 09:38:14,888][87426] Updated weights for policy 1, policy_version 359210 (0.0008) -[2023-11-28 09:38:15,271][87426] Updated weights for policy 1, policy_version 359220 (0.0011) -[2023-11-28 09:38:15,648][87426] Updated weights for policy 1, policy_version 359230 (0.0008) -[2023-11-28 09:38:17,051][87424] Updated weights for policy 0, policy_version 359589 (0.0011) -[2023-11-28 09:38:17,437][87424] Updated weights for policy 0, policy_version 359599 (0.0011) -[2023-11-28 09:38:17,731][87426] Updated weights for policy 1, policy_version 359240 (0.0008) -[2023-11-28 09:38:17,821][87424] Updated weights for policy 0, policy_version 359609 (0.0011) -[2023-11-28 09:38:18,112][87426] Updated weights for policy 1, policy_version 359250 (0.0009) -[2023-11-28 09:38:18,445][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 184025088. Throughput: 0: 2666.7, 1: 2747.1. Samples: 184036656. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:18,446][86177] Avg episode reward: [(0, '-598.140'), (1, '-571.250')] -[2023-11-28 09:38:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000359616_92061696.pth... -[2023-11-28 09:38:18,487][87426] Updated weights for policy 1, policy_version 359260 (0.0007) -[2023-11-28 09:38:18,492][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000357088_91414528.pth -[2023-11-28 09:38:18,637][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000359264_91971584.pth... -[2023-11-28 09:38:18,686][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000356736_91324416.pth -[2023-11-28 09:38:20,098][87424] Updated weights for policy 0, policy_version 359619 (0.0011) -[2023-11-28 09:38:20,267][87426] Updated weights for policy 1, policy_version 359270 (0.0010) -[2023-11-28 09:38:20,482][87424] Updated weights for policy 0, policy_version 359629 (0.0011) -[2023-11-28 09:38:20,640][87426] Updated weights for policy 1, policy_version 359280 (0.0012) -[2023-11-28 09:38:20,857][87424] Updated weights for policy 0, policy_version 359639 (0.0011) -[2023-11-28 09:38:21,017][87426] Updated weights for policy 1, policy_version 359290 (0.0012) -[2023-11-28 09:38:23,321][87424] Updated weights for policy 0, policy_version 359649 (0.0010) -[2023-11-28 09:38:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 184049664. Throughput: 0: 2637.8, 1: 2736.4. Samples: 184068316. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:23,445][86177] Avg episode reward: [(0, '-561.870'), (1, '-590.190')] -[2023-11-28 09:38:23,484][87426] Updated weights for policy 1, policy_version 359300 (0.0012) -[2023-11-28 09:38:23,701][87424] Updated weights for policy 0, policy_version 359659 (0.0011) -[2023-11-28 09:38:23,861][87426] Updated weights for policy 1, policy_version 359310 (0.0012) -[2023-11-28 09:38:24,084][87424] Updated weights for policy 0, policy_version 359669 (0.0011) -[2023-11-28 09:38:24,237][87426] Updated weights for policy 1, policy_version 359320 (0.0012) -[2023-11-28 09:38:24,465][87424] Updated weights for policy 0, policy_version 359679 (0.0010) -[2023-11-28 09:38:26,430][87426] Updated weights for policy 1, policy_version 359330 (0.0012) -[2023-11-28 09:38:26,807][87426] Updated weights for policy 1, policy_version 359340 (0.0012) -[2023-11-28 09:38:26,998][87424] Updated weights for policy 0, policy_version 359689 (0.0011) -[2023-11-28 09:38:27,193][87426] Updated weights for policy 1, policy_version 359350 (0.0011) -[2023-11-28 09:38:27,381][87424] Updated weights for policy 0, policy_version 359699 (0.0012) -[2023-11-28 09:38:27,565][87426] Updated weights for policy 1, policy_version 359360 (0.0011) -[2023-11-28 09:38:27,766][87424] Updated weights for policy 0, policy_version 359709 (0.0012) -[2023-11-28 09:38:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184082432. Throughput: 0: 2637.3, 1: 2780.7. Samples: 184093312. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:28,445][86177] Avg episode reward: [(0, '-574.110'), (1, '-539.980')] -[2023-11-28 09:38:29,302][87426] Updated weights for policy 1, policy_version 359370 (0.0011) -[2023-11-28 09:38:29,684][87426] Updated weights for policy 1, policy_version 359380 (0.0011) -[2023-11-28 09:38:30,059][87426] Updated weights for policy 1, policy_version 359390 (0.0011) -[2023-11-28 09:38:30,099][87424] Updated weights for policy 0, policy_version 359719 (0.0011) -[2023-11-28 09:38:30,476][87424] Updated weights for policy 0, policy_version 359729 (0.0013) -[2023-11-28 09:38:30,861][87424] Updated weights for policy 0, policy_version 359739 (0.0012) -[2023-11-28 09:38:31,971][87426] Updated weights for policy 1, policy_version 359400 (0.0009) -[2023-11-28 09:38:32,350][87426] Updated weights for policy 1, policy_version 359410 (0.0009) -[2023-11-28 09:38:32,728][87426] Updated weights for policy 1, policy_version 359420 (0.0008) -[2023-11-28 09:38:33,022][87424] Updated weights for policy 0, policy_version 359749 (0.0011) -[2023-11-28 09:38:33,401][87424] Updated weights for policy 0, policy_version 359759 (0.0011) -[2023-11-28 09:38:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184107008. Throughput: 0: 2645.7, 1: 2764.3. Samples: 184118260. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:33,446][86177] Avg episode reward: [(0, '-577.200'), (1, '-545.810')] -[2023-11-28 09:38:33,785][87424] Updated weights for policy 0, policy_version 359769 (0.0012) -[2023-11-28 09:38:35,156][87426] Updated weights for policy 1, policy_version 359430 (0.0010) -[2023-11-28 09:38:35,522][87426] Updated weights for policy 1, policy_version 359440 (0.0010) -[2023-11-28 09:38:35,903][87426] Updated weights for policy 1, policy_version 359450 (0.0007) -[2023-11-28 09:38:36,231][87424] Updated weights for policy 0, policy_version 359779 (0.0011) -[2023-11-28 09:38:36,607][87424] Updated weights for policy 0, policy_version 359789 (0.0011) -[2023-11-28 09:38:36,986][87424] Updated weights for policy 0, policy_version 359799 (0.0011) -[2023-11-28 09:38:38,407][87426] Updated weights for policy 1, policy_version 359460 (0.0009) -[2023-11-28 09:38:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184131584. Throughput: 0: 2634.5, 1: 2736.4. Samples: 184149880. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:38,445][86177] Avg episode reward: [(0, '-595.690'), (1, '-563.700')] -[2023-11-28 09:38:38,791][87426] Updated weights for policy 1, policy_version 359470 (0.0011) -[2023-11-28 09:38:38,976][87424] Updated weights for policy 0, policy_version 359809 (0.0011) -[2023-11-28 09:38:39,174][87426] Updated weights for policy 1, policy_version 359480 (0.0009) -[2023-11-28 09:38:39,350][87424] Updated weights for policy 0, policy_version 359819 (0.0012) -[2023-11-28 09:38:39,736][87424] Updated weights for policy 0, policy_version 359829 (0.0010) -[2023-11-28 09:38:40,117][87424] Updated weights for policy 0, policy_version 359839 (0.0012) -[2023-11-28 09:38:41,277][87426] Updated weights for policy 1, policy_version 359490 (0.0010) -[2023-11-28 09:38:41,661][87426] Updated weights for policy 1, policy_version 359500 (0.0011) -[2023-11-28 09:38:42,036][87426] Updated weights for policy 1, policy_version 359510 (0.0012) -[2023-11-28 09:38:42,418][87426] Updated weights for policy 1, policy_version 359520 (0.0011) -[2023-11-28 09:38:42,702][87424] Updated weights for policy 0, policy_version 359849 (0.0011) -[2023-11-28 09:38:43,079][87424] Updated weights for policy 0, policy_version 359859 (0.0012) -[2023-11-28 09:38:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 184156160. Throughput: 0: 2635.5, 1: 2701.9. Samples: 184173336. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:43,445][86177] Avg episode reward: [(0, '-607.490'), (1, '-564.850')] -[2023-11-28 09:38:43,454][87424] Updated weights for policy 0, policy_version 359869 (0.0012) -[2023-11-28 09:38:44,701][87426] Updated weights for policy 1, policy_version 359530 (0.0012) -[2023-11-28 09:38:45,083][87426] Updated weights for policy 1, policy_version 359540 (0.0011) -[2023-11-28 09:38:45,366][87424] Updated weights for policy 0, policy_version 359879 (0.0012) -[2023-11-28 09:38:45,451][87426] Updated weights for policy 1, policy_version 359550 (0.0011) -[2023-11-28 09:38:45,741][87424] Updated weights for policy 0, policy_version 359889 (0.0012) -[2023-11-28 09:38:46,125][87424] Updated weights for policy 0, policy_version 359899 (0.0012) -[2023-11-28 09:38:47,800][87426] Updated weights for policy 1, policy_version 359560 (0.0008) -[2023-11-28 09:38:48,194][87426] Updated weights for policy 1, policy_version 359570 (0.0007) -[2023-11-28 09:38:48,345][87424] Updated weights for policy 0, policy_version 359909 (0.0012) -[2023-11-28 09:38:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 184180736. Throughput: 0: 2645.2, 1: 2698.3. Samples: 184197816. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:48,445][86177] Avg episode reward: [(0, '-585.470'), (1, '-557.550')] -[2023-11-28 09:38:48,566][87426] Updated weights for policy 1, policy_version 359580 (0.0010) -[2023-11-28 09:38:48,725][87424] Updated weights for policy 0, policy_version 359919 (0.0012) -[2023-11-28 09:38:49,123][87424] Updated weights for policy 0, policy_version 359929 (0.0012) -[2023-11-28 09:38:50,940][87426] Updated weights for policy 1, policy_version 359590 (0.0011) -[2023-11-28 09:38:51,293][87424] Updated weights for policy 0, policy_version 359939 (0.0011) -[2023-11-28 09:38:51,316][87426] Updated weights for policy 1, policy_version 359600 (0.0011) -[2023-11-28 09:38:51,666][87424] Updated weights for policy 0, policy_version 359949 (0.0011) -[2023-11-28 09:38:51,709][87426] Updated weights for policy 1, policy_version 359610 (0.0012) -[2023-11-28 09:38:52,051][87424] Updated weights for policy 0, policy_version 359959 (0.0011) -[2023-11-28 09:38:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184213504. Throughput: 0: 2639.7, 1: 2696.0. Samples: 184230228. Policy #0 lag: (min: 31.0, avg: 37.0, max: 63.0) -[2023-11-28 09:38:53,445][86177] Avg episode reward: [(0, '-594.640'), (1, '-545.810')] -[2023-11-28 09:38:54,136][87426] Updated weights for policy 1, policy_version 359620 (0.0010) -[2023-11-28 09:38:54,424][87424] Updated weights for policy 0, policy_version 359969 (0.0011) -[2023-11-28 09:38:54,525][87426] Updated weights for policy 1, policy_version 359630 (0.0007) -[2023-11-28 09:38:54,803][87424] Updated weights for policy 0, policy_version 359979 (0.0012) -[2023-11-28 09:38:54,890][87426] Updated weights for policy 1, policy_version 359640 (0.0007) -[2023-11-28 09:38:55,183][87424] Updated weights for policy 0, policy_version 359989 (0.0012) -[2023-11-28 09:38:55,571][87424] Updated weights for policy 0, policy_version 359999 (0.0012) -[2023-11-28 09:38:57,282][87426] Updated weights for policy 1, policy_version 359650 (0.0008) -[2023-11-28 09:38:57,385][87424] Updated weights for policy 0, policy_version 360009 (0.0012) -[2023-11-28 09:38:57,653][87426] Updated weights for policy 1, policy_version 359660 (0.0012) -[2023-11-28 09:38:57,759][87424] Updated weights for policy 0, policy_version 360019 (0.0012) -[2023-11-28 09:38:58,026][87426] Updated weights for policy 1, policy_version 359670 (0.0010) -[2023-11-28 09:38:58,149][87424] Updated weights for policy 0, policy_version 360029 (0.0012) -[2023-11-28 09:38:58,415][87426] Updated weights for policy 1, policy_version 359680 (0.0008) -[2023-11-28 09:38:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184246272. Throughput: 0: 2653.7, 1: 2715.5. Samples: 184254352. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:38:58,446][86177] Avg episode reward: [(0, '-562.870'), (1, '-561.750')] -[2023-11-28 09:39:00,191][87424] Updated weights for policy 0, policy_version 360039 (0.0010) -[2023-11-28 09:39:00,573][87424] Updated weights for policy 0, policy_version 360049 (0.0009) -[2023-11-28 09:39:00,807][87426] Updated weights for policy 1, policy_version 359690 (0.0008) -[2023-11-28 09:39:00,962][87424] Updated weights for policy 0, policy_version 360059 (0.0008) -[2023-11-28 09:39:01,178][87426] Updated weights for policy 1, policy_version 359700 (0.0008) -[2023-11-28 09:39:01,560][87426] Updated weights for policy 1, policy_version 359710 (0.0009) -[2023-11-28 09:39:03,338][87424] Updated weights for policy 0, policy_version 360069 (0.0011) -[2023-11-28 09:39:03,406][87426] Updated weights for policy 1, policy_version 359720 (0.0010) -[2023-11-28 09:39:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 184262656. Throughput: 0: 2690.4, 1: 2692.7. Samples: 184278896. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:03,446][86177] Avg episode reward: [(0, '-557.630'), (1, '-561.270')] -[2023-11-28 09:39:03,716][87424] Updated weights for policy 0, policy_version 360079 (0.0012) -[2023-11-28 09:39:03,778][87426] Updated weights for policy 1, policy_version 359730 (0.0009) -[2023-11-28 09:39:04,100][87424] Updated weights for policy 0, policy_version 360089 (0.0009) -[2023-11-28 09:39:04,154][87426] Updated weights for policy 1, policy_version 359740 (0.0008) -[2023-11-28 09:39:06,198][87424] Updated weights for policy 0, policy_version 360099 (0.0009) -[2023-11-28 09:39:06,556][87424] Updated weights for policy 0, policy_version 360109 (0.0011) -[2023-11-28 09:39:06,599][87426] Updated weights for policy 1, policy_version 359750 (0.0009) -[2023-11-28 09:39:06,937][87424] Updated weights for policy 0, policy_version 360119 (0.0011) -[2023-11-28 09:39:06,982][87426] Updated weights for policy 1, policy_version 359760 (0.0010) -[2023-11-28 09:39:07,357][87426] Updated weights for policy 1, policy_version 359770 (0.0011) -[2023-11-28 09:39:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 184295424. Throughput: 0: 2703.5, 1: 2683.8. Samples: 184310744. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:08,445][86177] Avg episode reward: [(0, '-586.650'), (1, '-619.600')] -[2023-11-28 09:39:09,368][87424] Updated weights for policy 0, policy_version 360129 (0.0011) -[2023-11-28 09:39:09,545][87426] Updated weights for policy 1, policy_version 359780 (0.0011) -[2023-11-28 09:39:09,753][87424] Updated weights for policy 0, policy_version 360139 (0.0012) -[2023-11-28 09:39:09,926][87426] Updated weights for policy 1, policy_version 359790 (0.0010) -[2023-11-28 09:39:10,136][87424] Updated weights for policy 0, policy_version 360149 (0.0012) -[2023-11-28 09:39:10,308][87426] Updated weights for policy 1, policy_version 359800 (0.0010) -[2023-11-28 09:39:10,515][87424] Updated weights for policy 0, policy_version 360159 (0.0011) -[2023-11-28 09:39:12,585][87424] Updated weights for policy 0, policy_version 360169 (0.0010) -[2023-11-28 09:39:12,600][87426] Updated weights for policy 1, policy_version 359810 (0.0011) -[2023-11-28 09:39:12,975][87424] Updated weights for policy 0, policy_version 360179 (0.0009) -[2023-11-28 09:39:12,977][87426] Updated weights for policy 1, policy_version 359820 (0.0011) -[2023-11-28 09:39:13,351][87424] Updated weights for policy 0, policy_version 360189 (0.0009) -[2023-11-28 09:39:13,361][87426] Updated weights for policy 1, policy_version 359830 (0.0011) -[2023-11-28 09:39:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 184311808. Throughput: 0: 2701.4, 1: 2658.2. Samples: 184334496. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:13,445][86177] Avg episode reward: [(0, '-598.810'), (1, '-619.080')] -[2023-11-28 09:39:13,734][87426] Updated weights for policy 1, policy_version 359840 (0.0011) -[2023-11-28 09:39:15,240][87424] Updated weights for policy 0, policy_version 360199 (0.0010) -[2023-11-28 09:39:15,633][87424] Updated weights for policy 0, policy_version 360209 (0.0011) -[2023-11-28 09:39:15,655][87426] Updated weights for policy 1, policy_version 359850 (0.0011) -[2023-11-28 09:39:16,005][87424] Updated weights for policy 0, policy_version 360219 (0.0012) -[2023-11-28 09:39:16,031][87426] Updated weights for policy 1, policy_version 359860 (0.0010) -[2023-11-28 09:39:16,409][87426] Updated weights for policy 1, policy_version 359870 (0.0009) -[2023-11-28 09:39:17,732][87424] Updated weights for policy 0, policy_version 360229 (0.0011) -[2023-11-28 09:39:18,102][87426] Updated weights for policy 1, policy_version 359880 (0.0007) -[2023-11-28 09:39:18,113][87424] Updated weights for policy 0, policy_version 360239 (0.0012) -[2023-11-28 09:39:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 184344576. Throughput: 0: 2715.9, 1: 2651.6. Samples: 184359796. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:18,445][86177] Avg episode reward: [(0, '-584.940'), (1, '-606.720')] -[2023-11-28 09:39:18,484][87426] Updated weights for policy 1, policy_version 359890 (0.0007) -[2023-11-28 09:39:18,496][87424] Updated weights for policy 0, policy_version 360249 (0.0011) -[2023-11-28 09:39:18,865][87426] Updated weights for policy 1, policy_version 359900 (0.0008) -[2023-11-28 09:39:20,830][87424] Updated weights for policy 0, policy_version 360259 (0.0011) -[2023-11-28 09:39:20,845][87426] Updated weights for policy 1, policy_version 359910 (0.0012) -[2023-11-28 09:39:21,222][87424] Updated weights for policy 0, policy_version 360269 (0.0010) -[2023-11-28 09:39:21,223][87426] Updated weights for policy 1, policy_version 359920 (0.0011) -[2023-11-28 09:39:21,600][87424] Updated weights for policy 0, policy_version 360279 (0.0011) -[2023-11-28 09:39:21,601][87426] Updated weights for policy 1, policy_version 359930 (0.0011) -[2023-11-28 09:39:23,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184377344. Throughput: 0: 2738.4, 1: 2646.5. Samples: 184392200. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:23,445][86177] Avg episode reward: [(0, '-591.550'), (1, '-584.130')] -[2023-11-28 09:39:23,953][87424] Updated weights for policy 0, policy_version 360289 (0.0010) -[2023-11-28 09:39:24,172][87426] Updated weights for policy 1, policy_version 359940 (0.0010) -[2023-11-28 09:39:24,337][87424] Updated weights for policy 0, policy_version 360299 (0.0010) -[2023-11-28 09:39:24,542][87426] Updated weights for policy 1, policy_version 359950 (0.0010) -[2023-11-28 09:39:24,721][87424] Updated weights for policy 0, policy_version 360309 (0.0009) -[2023-11-28 09:39:24,930][87426] Updated weights for policy 1, policy_version 359960 (0.0010) -[2023-11-28 09:39:25,103][87424] Updated weights for policy 0, policy_version 360319 (0.0007) -[2023-11-28 09:39:26,849][87426] Updated weights for policy 1, policy_version 359970 (0.0012) -[2023-11-28 09:39:27,233][87426] Updated weights for policy 1, policy_version 359980 (0.0012) -[2023-11-28 09:39:27,598][87424] Updated weights for policy 0, policy_version 360329 (0.0008) -[2023-11-28 09:39:27,613][87426] Updated weights for policy 1, policy_version 359990 (0.0012) -[2023-11-28 09:39:27,975][87424] Updated weights for policy 0, policy_version 360339 (0.0007) -[2023-11-28 09:39:27,985][87426] Updated weights for policy 1, policy_version 360000 (0.0010) -[2023-11-28 09:39:28,361][87424] Updated weights for policy 0, policy_version 360349 (0.0007) -[2023-11-28 09:39:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 184401920. Throughput: 0: 2738.5, 1: 2656.6. Samples: 184416116. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:28,445][86177] Avg episode reward: [(0, '-563.900'), (1, '-559.790')] -[2023-11-28 09:39:30,442][87426] Updated weights for policy 1, policy_version 360010 (0.0008) -[2023-11-28 09:39:30,543][87424] Updated weights for policy 0, policy_version 360359 (0.0010) -[2023-11-28 09:39:30,819][87426] Updated weights for policy 1, policy_version 360020 (0.0008) -[2023-11-28 09:39:30,913][87424] Updated weights for policy 0, policy_version 360369 (0.0010) -[2023-11-28 09:39:31,201][87426] Updated weights for policy 1, policy_version 360030 (0.0008) -[2023-11-28 09:39:31,300][87424] Updated weights for policy 0, policy_version 360379 (0.0011) -[2023-11-28 09:39:33,372][87426] Updated weights for policy 1, policy_version 360040 (0.0011) -[2023-11-28 09:39:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 184426496. Throughput: 0: 2716.3, 1: 2644.5. Samples: 184439052. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:33,445][86177] Avg episode reward: [(0, '-556.760'), (1, '-526.680')] -[2023-11-28 09:39:33,578][87424] Updated weights for policy 0, policy_version 360389 (0.0010) -[2023-11-28 09:39:33,760][87426] Updated weights for policy 1, policy_version 360050 (0.0009) -[2023-11-28 09:39:33,966][87424] Updated weights for policy 0, policy_version 360399 (0.0010) -[2023-11-28 09:39:34,141][87426] Updated weights for policy 1, policy_version 360060 (0.0008) -[2023-11-28 09:39:34,352][87424] Updated weights for policy 0, policy_version 360409 (0.0010) -[2023-11-28 09:39:36,099][87424] Updated weights for policy 0, policy_version 360419 (0.0009) -[2023-11-28 09:39:36,313][87426] Updated weights for policy 1, policy_version 360070 (0.0007) -[2023-11-28 09:39:36,477][87424] Updated weights for policy 0, policy_version 360429 (0.0009) -[2023-11-28 09:39:36,698][87426] Updated weights for policy 1, policy_version 360080 (0.0009) -[2023-11-28 09:39:36,859][87424] Updated weights for policy 0, policy_version 360439 (0.0010) -[2023-11-28 09:39:37,068][87426] Updated weights for policy 1, policy_version 360090 (0.0008) -[2023-11-28 09:39:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184459264. Throughput: 0: 2695.1, 1: 2656.5. Samples: 184471052. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:38,445][86177] Avg episode reward: [(0, '-565.230'), (1, '-521.190')] -[2023-11-28 09:39:39,156][87424] Updated weights for policy 0, policy_version 360449 (0.0011) -[2023-11-28 09:39:39,463][87426] Updated weights for policy 1, policy_version 360100 (0.0009) -[2023-11-28 09:39:39,535][87424] Updated weights for policy 0, policy_version 360459 (0.0012) -[2023-11-28 09:39:39,845][87426] Updated weights for policy 1, policy_version 360110 (0.0011) -[2023-11-28 09:39:39,917][87424] Updated weights for policy 0, policy_version 360469 (0.0012) -[2023-11-28 09:39:40,214][87426] Updated weights for policy 1, policy_version 360120 (0.0011) -[2023-11-28 09:39:40,294][87424] Updated weights for policy 0, policy_version 360479 (0.0011) -[2023-11-28 09:39:42,662][87424] Updated weights for policy 0, policy_version 360489 (0.0012) -[2023-11-28 09:39:42,813][87426] Updated weights for policy 1, policy_version 360130 (0.0009) -[2023-11-28 09:39:43,041][87424] Updated weights for policy 0, policy_version 360499 (0.0011) -[2023-11-28 09:39:43,185][87426] Updated weights for policy 1, policy_version 360140 (0.0008) -[2023-11-28 09:39:43,422][87424] Updated weights for policy 0, policy_version 360509 (0.0011) -[2023-11-28 09:39:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 184475648. Throughput: 0: 2688.4, 1: 2655.6. Samples: 184494828. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:43,445][86177] Avg episode reward: [(0, '-557.830'), (1, '-527.960')] -[2023-11-28 09:39:43,569][87426] Updated weights for policy 1, policy_version 360150 (0.0011) -[2023-11-28 09:39:43,948][87426] Updated weights for policy 1, policy_version 360160 (0.0008) -[2023-11-28 09:39:45,988][87424] Updated weights for policy 0, policy_version 360519 (0.0011) -[2023-11-28 09:39:46,369][87426] Updated weights for policy 1, policy_version 360170 (0.0011) -[2023-11-28 09:39:46,381][87424] Updated weights for policy 0, policy_version 360529 (0.0009) -[2023-11-28 09:39:46,751][87426] Updated weights for policy 1, policy_version 360180 (0.0011) -[2023-11-28 09:39:46,760][87424] Updated weights for policy 0, policy_version 360539 (0.0011) -[2023-11-28 09:39:47,125][87426] Updated weights for policy 1, policy_version 360190 (0.0012) -[2023-11-28 09:39:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184508416. Throughput: 0: 2663.6, 1: 2672.4. Samples: 184519016. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:48,446][86177] Avg episode reward: [(0, '-555.250'), (1, '-529.020')] -[2023-11-28 09:39:49,118][87426] Updated weights for policy 1, policy_version 360200 (0.0012) -[2023-11-28 09:39:49,285][87424] Updated weights for policy 0, policy_version 360549 (0.0011) -[2023-11-28 09:39:49,503][87426] Updated weights for policy 1, policy_version 360210 (0.0012) -[2023-11-28 09:39:49,666][87424] Updated weights for policy 0, policy_version 360559 (0.0008) -[2023-11-28 09:39:49,870][87426] Updated weights for policy 1, policy_version 360220 (0.0012) -[2023-11-28 09:39:50,046][87424] Updated weights for policy 0, policy_version 360569 (0.0011) -[2023-11-28 09:39:52,153][87426] Updated weights for policy 1, policy_version 360230 (0.0011) -[2023-11-28 09:39:52,530][87426] Updated weights for policy 1, policy_version 360240 (0.0011) -[2023-11-28 09:39:52,608][87424] Updated weights for policy 0, policy_version 360579 (0.0011) -[2023-11-28 09:39:52,910][87426] Updated weights for policy 1, policy_version 360250 (0.0010) -[2023-11-28 09:39:52,984][87424] Updated weights for policy 0, policy_version 360589 (0.0011) -[2023-11-28 09:39:53,367][87424] Updated weights for policy 0, policy_version 360599 (0.0011) -[2023-11-28 09:39:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 184532992. Throughput: 0: 2672.8, 1: 2678.0. Samples: 184551532. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:53,445][86177] Avg episode reward: [(0, '-559.300'), (1, '-536.430')] -[2023-11-28 09:39:55,081][87424] Updated weights for policy 0, policy_version 360609 (0.0012) -[2023-11-28 09:39:55,267][87426] Updated weights for policy 1, policy_version 360260 (0.0009) -[2023-11-28 09:39:55,455][87424] Updated weights for policy 0, policy_version 360619 (0.0011) -[2023-11-28 09:39:55,645][87426] Updated weights for policy 1, policy_version 360270 (0.0011) -[2023-11-28 09:39:55,839][87424] Updated weights for policy 0, policy_version 360629 (0.0012) -[2023-11-28 09:39:56,019][87426] Updated weights for policy 1, policy_version 360280 (0.0012) -[2023-11-28 09:39:56,216][87424] Updated weights for policy 0, policy_version 360639 (0.0011) -[2023-11-28 09:39:58,282][87424] Updated weights for policy 0, policy_version 360649 (0.0012) -[2023-11-28 09:39:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 184557568. Throughput: 0: 2690.7, 1: 2677.4. Samples: 184576060. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:39:58,445][86177] Avg episode reward: [(0, '-565.660'), (1, '-526.270')] -[2023-11-28 09:39:58,518][87426] Updated weights for policy 1, policy_version 360290 (0.0012) -[2023-11-28 09:39:58,651][87424] Updated weights for policy 0, policy_version 360659 (0.0011) -[2023-11-28 09:39:58,886][87426] Updated weights for policy 1, policy_version 360300 (0.0012) -[2023-11-28 09:39:59,022][87424] Updated weights for policy 0, policy_version 360669 (0.0011) -[2023-11-28 09:39:59,260][87426] Updated weights for policy 1, policy_version 360310 (0.0010) -[2023-11-28 09:39:59,638][87426] Updated weights for policy 1, policy_version 360320 (0.0008) -[2023-11-28 09:40:01,156][87424] Updated weights for policy 0, policy_version 360679 (0.0012) -[2023-11-28 09:40:01,541][87424] Updated weights for policy 0, policy_version 360689 (0.0012) -[2023-11-28 09:40:01,760][87426] Updated weights for policy 1, policy_version 360330 (0.0011) -[2023-11-28 09:40:01,921][87424] Updated weights for policy 0, policy_version 360699 (0.0011) -[2023-11-28 09:40:02,141][87426] Updated weights for policy 1, policy_version 360340 (0.0010) -[2023-11-28 09:40:02,513][87426] Updated weights for policy 1, policy_version 360350 (0.0011) -[2023-11-28 09:40:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184590336. Throughput: 0: 2675.4, 1: 2667.5. Samples: 184600224. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:40:03,446][86177] Avg episode reward: [(0, '-567.210'), (1, '-524.570')] -[2023-11-28 09:40:04,221][87424] Updated weights for policy 0, policy_version 360709 (0.0010) -[2023-11-28 09:40:04,594][87424] Updated weights for policy 0, policy_version 360719 (0.0012) -[2023-11-28 09:40:04,981][87424] Updated weights for policy 0, policy_version 360729 (0.0012) -[2023-11-28 09:40:05,107][87426] Updated weights for policy 1, policy_version 360360 (0.0010) -[2023-11-28 09:40:05,492][87426] Updated weights for policy 1, policy_version 360370 (0.0008) -[2023-11-28 09:40:05,873][87426] Updated weights for policy 1, policy_version 360380 (0.0008) -[2023-11-28 09:40:07,048][87424] Updated weights for policy 0, policy_version 360739 (0.0012) -[2023-11-28 09:40:07,424][87424] Updated weights for policy 0, policy_version 360749 (0.0009) -[2023-11-28 09:40:07,807][87424] Updated weights for policy 0, policy_version 360759 (0.0009) -[2023-11-28 09:40:08,006][87426] Updated weights for policy 1, policy_version 360390 (0.0010) -[2023-11-28 09:40:08,385][87426] Updated weights for policy 1, policy_version 360400 (0.0012) -[2023-11-28 09:40:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 184614912. Throughput: 0: 2688.6, 1: 2677.9. Samples: 184633692. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:40:08,445][86177] Avg episode reward: [(0, '-598.250'), (1, '-533.750')] -[2023-11-28 09:40:08,763][87426] Updated weights for policy 1, policy_version 360410 (0.0009) -[2023-11-28 09:40:09,818][87424] Updated weights for policy 0, policy_version 360769 (0.0012) -[2023-11-28 09:40:10,210][87424] Updated weights for policy 0, policy_version 360779 (0.0012) -[2023-11-28 09:40:10,591][87424] Updated weights for policy 0, policy_version 360789 (0.0012) -[2023-11-28 09:40:10,833][87426] Updated weights for policy 1, policy_version 360420 (0.0008) -[2023-11-28 09:40:10,965][87424] Updated weights for policy 0, policy_version 360799 (0.0012) -[2023-11-28 09:40:11,209][87426] Updated weights for policy 1, policy_version 360430 (0.0008) -[2023-11-28 09:40:11,587][87426] Updated weights for policy 1, policy_version 360440 (0.0009) -[2023-11-28 09:40:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184639488. Throughput: 0: 2685.6, 1: 2675.7. Samples: 184657376. Policy #0 lag: (min: 47.0, avg: 61.1, max: 88.0) -[2023-11-28 09:40:13,445][86177] Avg episode reward: [(0, '-599.740'), (1, '-524.810')] -[2023-11-28 09:40:13,508][87426] Updated weights for policy 1, policy_version 360450 (0.0010) -[2023-11-28 09:40:13,603][87424] Updated weights for policy 0, policy_version 360809 (0.0008) -[2023-11-28 09:40:13,890][87426] Updated weights for policy 1, policy_version 360460 (0.0009) -[2023-11-28 09:40:13,981][87424] Updated weights for policy 0, policy_version 360819 (0.0009) -[2023-11-28 09:40:14,260][87426] Updated weights for policy 1, policy_version 360470 (0.0008) -[2023-11-28 09:40:14,355][87424] Updated weights for policy 0, policy_version 360829 (0.0008) -[2023-11-28 09:40:14,651][87426] Updated weights for policy 1, policy_version 360480 (0.0008) -[2023-11-28 09:40:16,652][87424] Updated weights for policy 0, policy_version 360839 (0.0009) -[2023-11-28 09:40:17,033][87424] Updated weights for policy 0, policy_version 360849 (0.0007) -[2023-11-28 09:40:17,184][87426] Updated weights for policy 1, policy_version 360490 (0.0007) -[2023-11-28 09:40:17,411][87424] Updated weights for policy 0, policy_version 360859 (0.0007) -[2023-11-28 09:40:17,571][87426] Updated weights for policy 1, policy_version 360500 (0.0010) -[2023-11-28 09:40:17,947][87426] Updated weights for policy 1, policy_version 360510 (0.0011) -[2023-11-28 09:40:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 184672256. Throughput: 0: 2682.4, 1: 2677.2. Samples: 184680232. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:40:18,445][86177] Avg episode reward: [(0, '-601.870'), (1, '-570.260')] -[2023-11-28 09:40:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000360864_92381184.pth... -[2023-11-28 09:40:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000360512_92291072.pth... -[2023-11-28 09:40:18,500][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000357984_91643904.pth -[2023-11-28 09:40:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000358368_91742208.pth -[2023-11-28 09:40:19,511][87424] Updated weights for policy 0, policy_version 360869 (0.0012) -[2023-11-28 09:40:19,896][87424] Updated weights for policy 0, policy_version 360879 (0.0012) -[2023-11-28 09:40:20,119][87426] Updated weights for policy 1, policy_version 360520 (0.0011) -[2023-11-28 09:40:20,281][87424] Updated weights for policy 0, policy_version 360889 (0.0012) -[2023-11-28 09:40:20,494][87426] Updated weights for policy 1, policy_version 360530 (0.0009) -[2023-11-28 09:40:20,872][87426] Updated weights for policy 1, policy_version 360540 (0.0007) -[2023-11-28 09:40:22,735][87424] Updated weights for policy 0, policy_version 360899 (0.0011) -[2023-11-28 09:40:23,083][87426] Updated weights for policy 1, policy_version 360550 (0.0010) -[2023-11-28 09:40:23,115][87424] Updated weights for policy 0, policy_version 360909 (0.0010) -[2023-11-28 09:40:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 184688640. Throughput: 0: 2684.6, 1: 2651.2. Samples: 184711164. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:40:23,445][86177] Avg episode reward: [(0, '-603.360'), (1, '-560.580')] -[2023-11-28 09:40:23,455][87426] Updated weights for policy 1, policy_version 360560 (0.0011) -[2023-11-28 09:40:23,498][87424] Updated weights for policy 0, policy_version 360919 (0.0010) -[2023-11-28 09:40:23,830][87426] Updated weights for policy 1, policy_version 360570 (0.0011) -[2023-11-28 09:40:25,482][87424] Updated weights for policy 0, policy_version 360929 (0.0011) -[2023-11-28 09:40:25,882][87424] Updated weights for policy 0, policy_version 360939 (0.0012) -[2023-11-28 09:40:26,280][87424] Updated weights for policy 0, policy_version 360949 (0.0012) -[2023-11-28 09:40:26,386][87426] Updated weights for policy 1, policy_version 360580 (0.0011) -[2023-11-28 09:40:26,669][87424] Updated weights for policy 0, policy_version 360959 (0.0010) -[2023-11-28 09:40:26,774][87426] Updated weights for policy 1, policy_version 360590 (0.0011) -[2023-11-28 09:40:27,155][87426] Updated weights for policy 1, policy_version 360600 (0.0012) -[2023-11-28 09:40:28,295][87424] Updated weights for policy 0, policy_version 360969 (0.0010) -[2023-11-28 09:40:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 184721408. Throughput: 0: 2710.9, 1: 2669.1. Samples: 184736928. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:40:28,446][86177] Avg episode reward: [(0, '-583.480'), (1, '-549.760')] -[2023-11-28 09:40:28,674][87424] Updated weights for policy 0, policy_version 360979 (0.0007) -[2023-11-28 09:40:29,002][87426] Updated weights for policy 1, policy_version 360610 (0.0011) -[2023-11-28 09:40:29,057][87424] Updated weights for policy 0, policy_version 360989 (0.0010) -[2023-11-28 09:40:29,379][87426] Updated weights for policy 1, policy_version 360620 (0.0012) -[2023-11-28 09:40:29,763][87426] Updated weights for policy 1, policy_version 360630 (0.0012) -[2023-11-28 09:40:30,144][87426] Updated weights for policy 1, policy_version 360640 (0.0009) -[2023-11-28 09:40:31,460][87424] Updated weights for policy 0, policy_version 360999 (0.0011) -[2023-11-28 09:40:31,860][87424] Updated weights for policy 0, policy_version 361009 (0.0014) -[2023-11-28 09:40:32,240][87424] Updated weights for policy 0, policy_version 361019 (0.0011) -[2023-11-28 09:40:32,374][87426] Updated weights for policy 1, policy_version 360650 (0.0011) -[2023-11-28 09:40:32,763][87426] Updated weights for policy 1, policy_version 360660 (0.0010) -[2023-11-28 09:40:33,140][87426] Updated weights for policy 1, policy_version 360670 (0.0009) -[2023-11-28 09:40:33,445][86177] Fps is (10 sec: 6553.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184754176. Throughput: 0: 2715.1, 1: 2666.1. Samples: 184761172. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:40:33,446][86177] Avg episode reward: [(0, '-576.240'), (1, '-554.070')] -[2023-11-28 09:40:34,053][87424] Updated weights for policy 0, policy_version 361029 (0.0010) -[2023-11-28 09:40:34,434][87424] Updated weights for policy 0, policy_version 361039 (0.0012) -[2023-11-28 09:40:34,815][87424] Updated weights for policy 0, policy_version 361049 (0.0012) -[2023-11-28 09:40:35,122][87426] Updated weights for policy 1, policy_version 360680 (0.0009) -[2023-11-28 09:40:35,493][87426] Updated weights for policy 1, policy_version 360690 (0.0012) -[2023-11-28 09:40:35,869][87426] Updated weights for policy 1, policy_version 360700 (0.0012) -[2023-11-28 09:40:36,952][87424] Updated weights for policy 0, policy_version 361059 (0.0010) -[2023-11-28 09:40:37,343][87424] Updated weights for policy 0, policy_version 361069 (0.0008) -[2023-11-28 09:40:37,722][87424] Updated weights for policy 0, policy_version 361079 (0.0012) -[2023-11-28 09:40:37,818][87426] Updated weights for policy 1, policy_version 360710 (0.0011) -[2023-11-28 09:40:38,197][87426] Updated weights for policy 1, policy_version 360720 (0.0012) -[2023-11-28 09:40:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 184778752. Throughput: 0: 2729.6, 1: 2679.3. Samples: 184794932. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:40:38,445][86177] Avg episode reward: [(0, '-592.650'), (1, '-527.320')] -[2023-11-28 09:40:38,571][87426] Updated weights for policy 1, policy_version 360730 (0.0012) -[2023-11-28 09:40:39,597][87424] Updated weights for policy 0, policy_version 361089 (0.0012) -[2023-11-28 09:40:39,990][87424] Updated weights for policy 0, policy_version 361099 (0.0011) -[2023-11-28 09:40:40,375][87424] Updated weights for policy 0, policy_version 361109 (0.0011) -[2023-11-28 09:40:40,747][87424] Updated weights for policy 0, policy_version 361119 (0.0012) -[2023-11-28 09:40:40,963][87426] Updated weights for policy 1, policy_version 360740 (0.0010) -[2023-11-28 09:40:41,344][87426] Updated weights for policy 1, policy_version 360750 (0.0008) -[2023-11-28 09:40:41,726][87426] Updated weights for policy 1, policy_version 360760 (0.0010) -[2023-11-28 09:40:43,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184803328. Throughput: 0: 2725.6, 1: 2664.0. Samples: 184818592. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:40:43,445][86177] Avg episode reward: [(0, '-590.430'), (1, '-542.010')] -[2023-11-28 09:40:43,511][87424] Updated weights for policy 0, policy_version 361129 (0.0012) -[2023-11-28 09:40:43,886][87424] Updated weights for policy 0, policy_version 361139 (0.0010) -[2023-11-28 09:40:44,034][87426] Updated weights for policy 1, policy_version 360770 (0.0011) -[2023-11-28 09:40:44,260][87424] Updated weights for policy 0, policy_version 361149 (0.0008) -[2023-11-28 09:40:44,424][87426] Updated weights for policy 1, policy_version 360780 (0.0007) -[2023-11-28 09:40:44,794][87426] Updated weights for policy 1, policy_version 360790 (0.0009) -[2023-11-28 09:40:45,169][87426] Updated weights for policy 1, policy_version 360800 (0.0007) -[2023-11-28 09:40:46,071][87424] Updated weights for policy 0, policy_version 361159 (0.0010) -[2023-11-28 09:40:46,451][87424] Updated weights for policy 0, policy_version 361169 (0.0010) -[2023-11-28 09:40:46,838][87424] Updated weights for policy 0, policy_version 361179 (0.0011) -[2023-11-28 09:40:47,673][87426] Updated weights for policy 1, policy_version 360810 (0.0008) -[2023-11-28 09:40:48,052][87426] Updated weights for policy 1, policy_version 360820 (0.0008) -[2023-11-28 09:40:48,438][87426] Updated weights for policy 1, policy_version 360830 (0.0007) -[2023-11-28 09:40:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 184827904. Throughput: 0: 2728.0, 1: 2656.1. Samples: 184842508. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:40:48,445][86177] Avg episode reward: [(0, '-602.410'), (1, '-542.420')] -[2023-11-28 09:40:49,075][87424] Updated weights for policy 0, policy_version 361189 (0.0012) -[2023-11-28 09:40:49,455][87424] Updated weights for policy 0, policy_version 361199 (0.0008) -[2023-11-28 09:40:49,835][87424] Updated weights for policy 0, policy_version 361209 (0.0009) -[2023-11-28 09:40:50,946][87426] Updated weights for policy 1, policy_version 360840 (0.0011) -[2023-11-28 09:40:51,322][87426] Updated weights for policy 1, policy_version 360850 (0.0011) -[2023-11-28 09:40:51,713][87426] Updated weights for policy 1, policy_version 360860 (0.0012) -[2023-11-28 09:40:52,419][87424] Updated weights for policy 0, policy_version 361219 (0.0011) -[2023-11-28 09:40:52,822][87424] Updated weights for policy 0, policy_version 361229 (0.0008) -[2023-11-28 09:40:53,197][87424] Updated weights for policy 0, policy_version 361239 (0.0009) -[2023-11-28 09:40:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 184852480. Throughput: 0: 2696.7, 1: 2635.1. Samples: 184873624. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:40:53,445][86177] Avg episode reward: [(0, '-606.540'), (1, '-540.310')] -[2023-11-28 09:40:54,418][87426] Updated weights for policy 1, policy_version 360870 (0.0011) -[2023-11-28 09:40:54,790][87426] Updated weights for policy 1, policy_version 360880 (0.0012) -[2023-11-28 09:40:55,171][87426] Updated weights for policy 1, policy_version 360890 (0.0012) -[2023-11-28 09:40:55,260][87424] Updated weights for policy 0, policy_version 361249 (0.0011) -[2023-11-28 09:40:55,641][87424] Updated weights for policy 0, policy_version 361259 (0.0008) -[2023-11-28 09:40:56,020][87424] Updated weights for policy 0, policy_version 361269 (0.0008) -[2023-11-28 09:40:56,410][87424] Updated weights for policy 0, policy_version 361279 (0.0008) -[2023-11-28 09:40:57,212][87426] Updated weights for policy 1, policy_version 360900 (0.0012) -[2023-11-28 09:40:57,589][87426] Updated weights for policy 1, policy_version 360910 (0.0012) -[2023-11-28 09:40:57,969][87426] Updated weights for policy 1, policy_version 360920 (0.0012) -[2023-11-28 09:40:58,440][87424] Updated weights for policy 0, policy_version 361289 (0.0011) -[2023-11-28 09:40:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 184885248. Throughput: 0: 2714.2, 1: 2642.0. Samples: 184898408. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:40:58,445][86177] Avg episode reward: [(0, '-576.580'), (1, '-521.630')] -[2023-11-28 09:40:58,812][87424] Updated weights for policy 0, policy_version 361299 (0.0012) -[2023-11-28 09:40:59,194][87424] Updated weights for policy 0, policy_version 361309 (0.0012) -[2023-11-28 09:41:00,517][87426] Updated weights for policy 1, policy_version 360930 (0.0011) -[2023-11-28 09:41:00,889][87426] Updated weights for policy 1, policy_version 360940 (0.0012) -[2023-11-28 09:41:01,213][87424] Updated weights for policy 0, policy_version 361319 (0.0011) -[2023-11-28 09:41:01,263][87426] Updated weights for policy 1, policy_version 360950 (0.0011) -[2023-11-28 09:41:01,590][87424] Updated weights for policy 0, policy_version 361329 (0.0012) -[2023-11-28 09:41:01,633][87426] Updated weights for policy 1, policy_version 360960 (0.0011) -[2023-11-28 09:41:01,969][87424] Updated weights for policy 0, policy_version 361339 (0.0011) -[2023-11-28 09:41:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 184909824. Throughput: 0: 2740.3, 1: 2636.5. Samples: 184922188. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:41:03,445][86177] Avg episode reward: [(0, '-571.070'), (1, '-510.610')] -[2023-11-28 09:41:03,713][87426] Updated weights for policy 1, policy_version 360970 (0.0012) -[2023-11-28 09:41:04,084][87426] Updated weights for policy 1, policy_version 360980 (0.0011) -[2023-11-28 09:41:04,421][87424] Updated weights for policy 0, policy_version 361349 (0.0009) -[2023-11-28 09:41:04,461][87426] Updated weights for policy 1, policy_version 360990 (0.0012) -[2023-11-28 09:41:04,797][87424] Updated weights for policy 0, policy_version 361359 (0.0009) -[2023-11-28 09:41:05,181][87424] Updated weights for policy 0, policy_version 361369 (0.0012) -[2023-11-28 09:41:06,964][87426] Updated weights for policy 1, policy_version 361000 (0.0009) -[2023-11-28 09:41:07,233][87424] Updated weights for policy 0, policy_version 361379 (0.0012) -[2023-11-28 09:41:07,344][87426] Updated weights for policy 1, policy_version 361010 (0.0011) -[2023-11-28 09:41:07,610][87424] Updated weights for policy 0, policy_version 361389 (0.0012) -[2023-11-28 09:41:07,719][87426] Updated weights for policy 1, policy_version 361020 (0.0011) -[2023-11-28 09:41:07,995][87424] Updated weights for policy 0, policy_version 361399 (0.0009) -[2023-11-28 09:41:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 184942592. Throughput: 0: 2749.8, 1: 2645.7. Samples: 184953960. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:41:08,445][86177] Avg episode reward: [(0, '-557.940'), (1, '-513.900')] -[2023-11-28 09:41:09,583][87426] Updated weights for policy 1, policy_version 361030 (0.0010) -[2023-11-28 09:41:09,961][87426] Updated weights for policy 1, policy_version 361040 (0.0012) -[2023-11-28 09:41:10,186][87424] Updated weights for policy 0, policy_version 361409 (0.0008) -[2023-11-28 09:41:10,329][87426] Updated weights for policy 1, policy_version 361050 (0.0011) -[2023-11-28 09:41:10,565][87424] Updated weights for policy 0, policy_version 361419 (0.0011) -[2023-11-28 09:41:10,939][87424] Updated weights for policy 0, policy_version 361429 (0.0011) -[2023-11-28 09:41:11,325][87424] Updated weights for policy 0, policy_version 361439 (0.0011) -[2023-11-28 09:41:12,807][87426] Updated weights for policy 1, policy_version 361060 (0.0011) -[2023-11-28 09:41:13,183][87426] Updated weights for policy 1, policy_version 361070 (0.0012) -[2023-11-28 09:41:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 184958976. Throughput: 0: 2725.7, 1: 2627.8. Samples: 184977836. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:41:13,445][86177] Avg episode reward: [(0, '-554.700'), (1, '-516.650')] -[2023-11-28 09:41:13,568][87426] Updated weights for policy 1, policy_version 361080 (0.0008) -[2023-11-28 09:41:13,901][87424] Updated weights for policy 0, policy_version 361449 (0.0010) -[2023-11-28 09:41:14,294][87424] Updated weights for policy 0, policy_version 361459 (0.0007) -[2023-11-28 09:41:14,664][87424] Updated weights for policy 0, policy_version 361469 (0.0007) -[2023-11-28 09:41:15,633][87426] Updated weights for policy 1, policy_version 361090 (0.0008) -[2023-11-28 09:41:16,010][87426] Updated weights for policy 1, policy_version 361100 (0.0011) -[2023-11-28 09:41:16,387][87426] Updated weights for policy 1, policy_version 361110 (0.0007) -[2023-11-28 09:41:16,766][87426] Updated weights for policy 1, policy_version 361120 (0.0007) -[2023-11-28 09:41:17,083][87424] Updated weights for policy 0, policy_version 361479 (0.0010) -[2023-11-28 09:41:17,469][87424] Updated weights for policy 0, policy_version 361489 (0.0012) -[2023-11-28 09:41:17,845][87424] Updated weights for policy 0, policy_version 361499 (0.0009) -[2023-11-28 09:41:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 184991744. Throughput: 0: 2713.5, 1: 2619.9. Samples: 185001176. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:41:18,445][86177] Avg episode reward: [(0, '-548.410'), (1, '-523.490')] -[2023-11-28 09:41:19,088][87426] Updated weights for policy 1, policy_version 361130 (0.0009) -[2023-11-28 09:41:19,466][87426] Updated weights for policy 1, policy_version 361140 (0.0009) -[2023-11-28 09:41:19,545][87424] Updated weights for policy 0, policy_version 361509 (0.0010) -[2023-11-28 09:41:19,842][87426] Updated weights for policy 1, policy_version 361150 (0.0010) -[2023-11-28 09:41:19,924][87424] Updated weights for policy 0, policy_version 361519 (0.0010) -[2023-11-28 09:41:20,304][87424] Updated weights for policy 0, policy_version 361529 (0.0012) -[2023-11-28 09:41:22,310][87426] Updated weights for policy 1, policy_version 361160 (0.0011) -[2023-11-28 09:41:22,691][87426] Updated weights for policy 1, policy_version 361170 (0.0012) -[2023-11-28 09:41:22,860][87424] Updated weights for policy 0, policy_version 361539 (0.0011) -[2023-11-28 09:41:23,060][87426] Updated weights for policy 1, policy_version 361180 (0.0011) -[2023-11-28 09:41:23,235][87424] Updated weights for policy 0, policy_version 361549 (0.0012) -[2023-11-28 09:41:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 185016320. Throughput: 0: 2698.5, 1: 2576.9. Samples: 185032324. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:41:23,445][86177] Avg episode reward: [(0, '-590.370'), (1, '-521.840')] -[2023-11-28 09:41:23,616][87424] Updated weights for policy 0, policy_version 361559 (0.0012) -[2023-11-28 09:41:25,090][87426] Updated weights for policy 1, policy_version 361190 (0.0011) -[2023-11-28 09:41:25,470][87426] Updated weights for policy 1, policy_version 361200 (0.0012) -[2023-11-28 09:41:25,623][87424] Updated weights for policy 0, policy_version 361569 (0.0012) -[2023-11-28 09:41:25,859][87426] Updated weights for policy 1, policy_version 361210 (0.0012) -[2023-11-28 09:41:26,003][87424] Updated weights for policy 0, policy_version 361579 (0.0011) -[2023-11-28 09:41:26,389][87424] Updated weights for policy 0, policy_version 361589 (0.0012) -[2023-11-28 09:41:26,767][87424] Updated weights for policy 0, policy_version 361599 (0.0012) -[2023-11-28 09:41:27,708][87426] Updated weights for policy 1, policy_version 361220 (0.0011) -[2023-11-28 09:41:28,088][87426] Updated weights for policy 1, policy_version 361230 (0.0009) -[2023-11-28 09:41:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185040896. Throughput: 0: 2706.3, 1: 2618.5. Samples: 185058208. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:41:28,445][86177] Avg episode reward: [(0, '-608.110'), (1, '-525.550')] -[2023-11-28 09:41:28,469][87426] Updated weights for policy 1, policy_version 361240 (0.0008) -[2023-11-28 09:41:28,693][87424] Updated weights for policy 0, policy_version 361609 (0.0012) -[2023-11-28 09:41:29,074][87424] Updated weights for policy 0, policy_version 361619 (0.0011) -[2023-11-28 09:41:29,462][87424] Updated weights for policy 0, policy_version 361629 (0.0008) -[2023-11-28 09:41:30,925][87426] Updated weights for policy 1, policy_version 361250 (0.0010) -[2023-11-28 09:41:31,300][87426] Updated weights for policy 1, policy_version 361260 (0.0012) -[2023-11-28 09:41:31,519][87424] Updated weights for policy 0, policy_version 361639 (0.0011) -[2023-11-28 09:41:31,672][87426] Updated weights for policy 1, policy_version 361270 (0.0011) -[2023-11-28 09:41:31,890][87424] Updated weights for policy 0, policy_version 361649 (0.0010) -[2023-11-28 09:41:32,045][87426] Updated weights for policy 1, policy_version 361280 (0.0011) -[2023-11-28 09:41:32,268][87424] Updated weights for policy 0, policy_version 361659 (0.0011) -[2023-11-28 09:41:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 185073664. Throughput: 0: 2713.2, 1: 2620.1. Samples: 185082504. Policy #0 lag: (min: 27.0, avg: 43.9, max: 59.0) -[2023-11-28 09:41:33,445][86177] Avg episode reward: [(0, '-620.980'), (1, '-525.040')] -[2023-11-28 09:41:34,391][87426] Updated weights for policy 1, policy_version 361290 (0.0007) -[2023-11-28 09:41:34,596][87424] Updated weights for policy 0, policy_version 361669 (0.0008) -[2023-11-28 09:41:34,764][87426] Updated weights for policy 1, policy_version 361300 (0.0011) -[2023-11-28 09:41:34,975][87424] Updated weights for policy 0, policy_version 361679 (0.0010) -[2023-11-28 09:41:35,143][87426] Updated weights for policy 1, policy_version 361310 (0.0010) -[2023-11-28 09:41:35,356][87424] Updated weights for policy 0, policy_version 361689 (0.0010) -[2023-11-28 09:41:37,387][87424] Updated weights for policy 0, policy_version 361699 (0.0009) -[2023-11-28 09:41:37,664][87426] Updated weights for policy 1, policy_version 361320 (0.0012) -[2023-11-28 09:41:37,756][87424] Updated weights for policy 0, policy_version 361709 (0.0010) -[2023-11-28 09:41:38,047][87426] Updated weights for policy 1, policy_version 361330 (0.0010) -[2023-11-28 09:41:38,138][87424] Updated weights for policy 0, policy_version 361719 (0.0007) -[2023-11-28 09:41:38,429][87426] Updated weights for policy 1, policy_version 361340 (0.0012) -[2023-11-28 09:41:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 185090048. Throughput: 0: 2710.8, 1: 2643.3. Samples: 185114556. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:41:38,445][86177] Avg episode reward: [(0, '-659.660'), (1, '-536.800')] -[2023-11-28 09:41:40,653][87424] Updated weights for policy 0, policy_version 361729 (0.0008) -[2023-11-28 09:41:40,696][87426] Updated weights for policy 1, policy_version 361350 (0.0011) -[2023-11-28 09:41:41,027][87424] Updated weights for policy 0, policy_version 361739 (0.0010) -[2023-11-28 09:41:41,077][87426] Updated weights for policy 1, policy_version 361360 (0.0009) -[2023-11-28 09:41:41,420][87424] Updated weights for policy 0, policy_version 361749 (0.0007) -[2023-11-28 09:41:41,459][87426] Updated weights for policy 1, policy_version 361370 (0.0007) -[2023-11-28 09:41:41,808][87424] Updated weights for policy 0, policy_version 361759 (0.0010) -[2023-11-28 09:41:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185122816. Throughput: 0: 2704.6, 1: 2639.5. Samples: 185138892. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:41:43,445][86177] Avg episode reward: [(0, '-651.710'), (1, '-541.710')] -[2023-11-28 09:41:43,773][87426] Updated weights for policy 1, policy_version 361380 (0.0010) -[2023-11-28 09:41:44,154][87426] Updated weights for policy 1, policy_version 361390 (0.0008) -[2023-11-28 09:41:44,169][87424] Updated weights for policy 0, policy_version 361769 (0.0012) -[2023-11-28 09:41:44,538][87426] Updated weights for policy 1, policy_version 361400 (0.0008) -[2023-11-28 09:41:44,546][87424] Updated weights for policy 0, policy_version 361779 (0.0012) -[2023-11-28 09:41:44,932][87424] Updated weights for policy 0, policy_version 361789 (0.0012) -[2023-11-28 09:41:46,636][87426] Updated weights for policy 1, policy_version 361410 (0.0010) -[2023-11-28 09:41:47,019][87426] Updated weights for policy 1, policy_version 361420 (0.0011) -[2023-11-28 09:41:47,091][87424] Updated weights for policy 0, policy_version 361799 (0.0011) -[2023-11-28 09:41:47,410][87426] Updated weights for policy 1, policy_version 361430 (0.0011) -[2023-11-28 09:41:47,469][87424] Updated weights for policy 0, policy_version 361809 (0.0012) -[2023-11-28 09:41:47,787][87426] Updated weights for policy 1, policy_version 361440 (0.0011) -[2023-11-28 09:41:47,854][87424] Updated weights for policy 0, policy_version 361819 (0.0011) -[2023-11-28 09:41:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 185155584. Throughput: 0: 2698.0, 1: 2659.5. Samples: 185163280. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:41:48,445][86177] Avg episode reward: [(0, '-620.140'), (1, '-543.530')] -[2023-11-28 09:41:49,697][87424] Updated weights for policy 0, policy_version 361829 (0.0009) -[2023-11-28 09:41:49,711][87426] Updated weights for policy 1, policy_version 361450 (0.0011) -[2023-11-28 09:41:50,068][87424] Updated weights for policy 0, policy_version 361839 (0.0012) -[2023-11-28 09:41:50,091][87426] Updated weights for policy 1, policy_version 361460 (0.0011) -[2023-11-28 09:41:50,449][87424] Updated weights for policy 0, policy_version 361849 (0.0012) -[2023-11-28 09:41:50,478][87426] Updated weights for policy 1, policy_version 361470 (0.0012) -[2023-11-28 09:41:52,585][87424] Updated weights for policy 0, policy_version 361859 (0.0012) -[2023-11-28 09:41:52,869][87426] Updated weights for policy 1, policy_version 361480 (0.0012) -[2023-11-28 09:41:52,966][87424] Updated weights for policy 0, policy_version 361869 (0.0012) -[2023-11-28 09:41:53,253][87426] Updated weights for policy 1, policy_version 361490 (0.0012) -[2023-11-28 09:41:53,353][87424] Updated weights for policy 0, policy_version 361879 (0.0011) -[2023-11-28 09:41:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 185171968. Throughput: 0: 2693.2, 1: 2677.2. Samples: 185195632. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:41:53,445][86177] Avg episode reward: [(0, '-602.860'), (1, '-559.060')] -[2023-11-28 09:41:53,626][87426] Updated weights for policy 1, policy_version 361500 (0.0011) -[2023-11-28 09:41:55,467][87426] Updated weights for policy 1, policy_version 361510 (0.0012) -[2023-11-28 09:41:55,854][87426] Updated weights for policy 1, policy_version 361520 (0.0011) -[2023-11-28 09:41:55,938][87424] Updated weights for policy 0, policy_version 361889 (0.0011) -[2023-11-28 09:41:56,227][87426] Updated weights for policy 1, policy_version 361530 (0.0012) -[2023-11-28 09:41:56,320][87424] Updated weights for policy 0, policy_version 361899 (0.0007) -[2023-11-28 09:41:56,702][87424] Updated weights for policy 0, policy_version 361909 (0.0007) -[2023-11-28 09:41:57,091][87424] Updated weights for policy 0, policy_version 361919 (0.0008) -[2023-11-28 09:41:58,068][87426] Updated weights for policy 1, policy_version 361540 (0.0011) -[2023-11-28 09:41:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185204736. Throughput: 0: 2675.3, 1: 2710.6. Samples: 185220200. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:41:58,445][86177] Avg episode reward: [(0, '-580.750'), (1, '-551.700')] -[2023-11-28 09:41:58,449][87426] Updated weights for policy 1, policy_version 361550 (0.0011) -[2023-11-28 09:41:58,833][87426] Updated weights for policy 1, policy_version 361560 (0.0011) -[2023-11-28 09:41:59,581][87424] Updated weights for policy 0, policy_version 361929 (0.0008) -[2023-11-28 09:41:59,991][87424] Updated weights for policy 0, policy_version 361939 (0.0010) -[2023-11-28 09:42:00,365][87424] Updated weights for policy 0, policy_version 361949 (0.0012) -[2023-11-28 09:42:01,075][87426] Updated weights for policy 1, policy_version 361570 (0.0009) -[2023-11-28 09:42:01,454][87426] Updated weights for policy 1, policy_version 361580 (0.0012) -[2023-11-28 09:42:01,829][87426] Updated weights for policy 1, policy_version 361590 (0.0012) -[2023-11-28 09:42:02,206][87426] Updated weights for policy 1, policy_version 361600 (0.0010) -[2023-11-28 09:42:02,283][87424] Updated weights for policy 0, policy_version 361959 (0.0012) -[2023-11-28 09:42:02,667][87424] Updated weights for policy 0, policy_version 361969 (0.0012) -[2023-11-28 09:42:03,047][87424] Updated weights for policy 0, policy_version 361979 (0.0012) -[2023-11-28 09:42:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 185237504. Throughput: 0: 2690.6, 1: 2717.0. Samples: 185244516. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:03,445][86177] Avg episode reward: [(0, '-563.980'), (1, '-557.230')] -[2023-11-28 09:42:04,346][87426] Updated weights for policy 1, policy_version 361610 (0.0008) -[2023-11-28 09:42:04,719][87426] Updated weights for policy 1, policy_version 361620 (0.0014) -[2023-11-28 09:42:04,968][87424] Updated weights for policy 0, policy_version 361989 (0.0012) -[2023-11-28 09:42:05,099][87426] Updated weights for policy 1, policy_version 361630 (0.0010) -[2023-11-28 09:42:05,350][87424] Updated weights for policy 0, policy_version 361999 (0.0009) -[2023-11-28 09:42:05,740][87424] Updated weights for policy 0, policy_version 362009 (0.0012) -[2023-11-28 09:42:06,986][87426] Updated weights for policy 1, policy_version 361640 (0.0011) -[2023-11-28 09:42:07,352][87426] Updated weights for policy 1, policy_version 361650 (0.0012) -[2023-11-28 09:42:07,735][87426] Updated weights for policy 1, policy_version 361660 (0.0011) -[2023-11-28 09:42:07,896][87424] Updated weights for policy 0, policy_version 362019 (0.0012) -[2023-11-28 09:42:08,281][87424] Updated weights for policy 0, policy_version 362029 (0.0009) -[2023-11-28 09:42:08,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 185262080. Throughput: 0: 2718.8, 1: 2750.1. Samples: 185278428. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:08,446][86177] Avg episode reward: [(0, '-557.300'), (1, '-560.080')] -[2023-11-28 09:42:08,660][87424] Updated weights for policy 0, policy_version 362039 (0.0007) -[2023-11-28 09:42:09,781][87426] Updated weights for policy 1, policy_version 361670 (0.0012) -[2023-11-28 09:42:10,156][87426] Updated weights for policy 1, policy_version 361680 (0.0012) -[2023-11-28 09:42:10,530][87426] Updated weights for policy 1, policy_version 361690 (0.0012) -[2023-11-28 09:42:10,963][87424] Updated weights for policy 0, policy_version 362049 (0.0010) -[2023-11-28 09:42:11,334][87424] Updated weights for policy 0, policy_version 362059 (0.0010) -[2023-11-28 09:42:11,727][87424] Updated weights for policy 0, policy_version 362069 (0.0011) -[2023-11-28 09:42:12,101][87424] Updated weights for policy 0, policy_version 362079 (0.0011) -[2023-11-28 09:42:12,925][87426] Updated weights for policy 1, policy_version 361700 (0.0012) -[2023-11-28 09:42:13,300][87426] Updated weights for policy 1, policy_version 361710 (0.0012) -[2023-11-28 09:42:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 185286656. Throughput: 0: 2706.1, 1: 2709.1. Samples: 185301888. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:13,445][86177] Avg episode reward: [(0, '-555.250'), (1, '-546.930')] -[2023-11-28 09:42:13,688][87426] Updated weights for policy 1, policy_version 361720 (0.0010) -[2023-11-28 09:42:14,382][87424] Updated weights for policy 0, policy_version 362089 (0.0011) -[2023-11-28 09:42:14,754][87424] Updated weights for policy 0, policy_version 362099 (0.0011) -[2023-11-28 09:42:15,137][87424] Updated weights for policy 0, policy_version 362109 (0.0011) -[2023-11-28 09:42:16,226][87426] Updated weights for policy 1, policy_version 361730 (0.0011) -[2023-11-28 09:42:16,605][87426] Updated weights for policy 1, policy_version 361740 (0.0012) -[2023-11-28 09:42:16,973][87426] Updated weights for policy 1, policy_version 361750 (0.0012) -[2023-11-28 09:42:17,352][87426] Updated weights for policy 1, policy_version 361760 (0.0011) -[2023-11-28 09:42:17,658][87424] Updated weights for policy 0, policy_version 362119 (0.0008) -[2023-11-28 09:42:18,040][87424] Updated weights for policy 0, policy_version 362129 (0.0007) -[2023-11-28 09:42:18,410][87424] Updated weights for policy 0, policy_version 362139 (0.0007) -[2023-11-28 09:42:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185311232. Throughput: 0: 2681.6, 1: 2727.4. Samples: 185325908. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:18,445][86177] Avg episode reward: [(0, '-552.720'), (1, '-545.650')] -[2023-11-28 09:42:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000361760_92610560.pth... -[2023-11-28 09:42:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000359264_91971584.pth -[2023-11-28 09:42:18,601][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000362144_92708864.pth... -[2023-11-28 09:42:18,631][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000359616_92061696.pth -[2023-11-28 09:42:19,745][87426] Updated weights for policy 1, policy_version 361770 (0.0009) -[2023-11-28 09:42:20,114][87426] Updated weights for policy 1, policy_version 361780 (0.0010) -[2023-11-28 09:42:20,504][87426] Updated weights for policy 1, policy_version 361790 (0.0010) -[2023-11-28 09:42:20,896][87424] Updated weights for policy 0, policy_version 362149 (0.0009) -[2023-11-28 09:42:21,282][87424] Updated weights for policy 0, policy_version 362159 (0.0012) -[2023-11-28 09:42:21,669][87424] Updated weights for policy 0, policy_version 362169 (0.0013) -[2023-11-28 09:42:22,862][87426] Updated weights for policy 1, policy_version 361800 (0.0008) -[2023-11-28 09:42:23,234][87426] Updated weights for policy 1, policy_version 361810 (0.0008) -[2023-11-28 09:42:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185335808. Throughput: 0: 2659.1, 1: 2710.0. Samples: 185356168. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:23,445][86177] Avg episode reward: [(0, '-562.390'), (1, '-538.500')] -[2023-11-28 09:42:23,618][87426] Updated weights for policy 1, policy_version 361820 (0.0010) -[2023-11-28 09:42:24,085][87424] Updated weights for policy 0, policy_version 362179 (0.0010) -[2023-11-28 09:42:24,463][87424] Updated weights for policy 0, policy_version 362189 (0.0008) -[2023-11-28 09:42:24,849][87424] Updated weights for policy 0, policy_version 362199 (0.0009) -[2023-11-28 09:42:25,703][87426] Updated weights for policy 1, policy_version 361830 (0.0010) -[2023-11-28 09:42:26,082][87426] Updated weights for policy 1, policy_version 361840 (0.0008) -[2023-11-28 09:42:26,459][87426] Updated weights for policy 1, policy_version 361850 (0.0007) -[2023-11-28 09:42:26,690][87424] Updated weights for policy 0, policy_version 362209 (0.0011) -[2023-11-28 09:42:27,062][87424] Updated weights for policy 0, policy_version 362219 (0.0007) -[2023-11-28 09:42:27,444][87424] Updated weights for policy 0, policy_version 362229 (0.0007) -[2023-11-28 09:42:27,832][87424] Updated weights for policy 0, policy_version 362239 (0.0008) -[2023-11-28 09:42:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 185368576. Throughput: 0: 2648.7, 1: 2706.9. Samples: 185379896. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:28,445][86177] Avg episode reward: [(0, '-585.520'), (1, '-543.470')] -[2023-11-28 09:42:29,045][87426] Updated weights for policy 1, policy_version 361860 (0.0009) -[2023-11-28 09:42:29,432][87426] Updated weights for policy 1, policy_version 361870 (0.0008) -[2023-11-28 09:42:29,817][87426] Updated weights for policy 1, policy_version 361880 (0.0008) -[2023-11-28 09:42:30,274][87424] Updated weights for policy 0, policy_version 362249 (0.0008) -[2023-11-28 09:42:30,652][87424] Updated weights for policy 0, policy_version 362259 (0.0009) -[2023-11-28 09:42:31,034][87424] Updated weights for policy 0, policy_version 362269 (0.0010) -[2023-11-28 09:42:31,703][87426] Updated weights for policy 1, policy_version 361890 (0.0012) -[2023-11-28 09:42:32,073][87426] Updated weights for policy 1, policy_version 361900 (0.0012) -[2023-11-28 09:42:32,455][87426] Updated weights for policy 1, policy_version 361910 (0.0012) -[2023-11-28 09:42:32,826][87426] Updated weights for policy 1, policy_version 361920 (0.0009) -[2023-11-28 09:42:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 185393152. Throughput: 0: 2630.4, 1: 2705.2. Samples: 185403384. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:33,445][86177] Avg episode reward: [(0, '-582.380'), (1, '-543.740')] -[2023-11-28 09:42:33,609][87424] Updated weights for policy 0, policy_version 362279 (0.0012) -[2023-11-28 09:42:33,994][87424] Updated weights for policy 0, policy_version 362289 (0.0011) -[2023-11-28 09:42:34,372][87424] Updated weights for policy 0, policy_version 362299 (0.0012) -[2023-11-28 09:42:34,877][87426] Updated weights for policy 1, policy_version 361930 (0.0012) -[2023-11-28 09:42:35,252][87426] Updated weights for policy 1, policy_version 361940 (0.0012) -[2023-11-28 09:42:35,626][87426] Updated weights for policy 1, policy_version 361950 (0.0012) -[2023-11-28 09:42:36,628][87424] Updated weights for policy 0, policy_version 362309 (0.0012) -[2023-11-28 09:42:37,005][87424] Updated weights for policy 0, policy_version 362319 (0.0012) -[2023-11-28 09:42:37,392][87424] Updated weights for policy 0, policy_version 362329 (0.0012) -[2023-11-28 09:42:37,770][87426] Updated weights for policy 1, policy_version 361960 (0.0010) -[2023-11-28 09:42:38,153][87426] Updated weights for policy 1, policy_version 361970 (0.0008) -[2023-11-28 09:42:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 185417728. Throughput: 0: 2651.5, 1: 2710.4. Samples: 185436920. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:38,446][86177] Avg episode reward: [(0, '-644.120'), (1, '-545.620')] -[2023-11-28 09:42:38,533][87426] Updated weights for policy 1, policy_version 361980 (0.0007) -[2023-11-28 09:42:39,511][87424] Updated weights for policy 0, policy_version 362339 (0.0011) -[2023-11-28 09:42:39,894][87424] Updated weights for policy 0, policy_version 362349 (0.0012) -[2023-11-28 09:42:40,271][87424] Updated weights for policy 0, policy_version 362359 (0.0009) -[2023-11-28 09:42:41,107][87426] Updated weights for policy 1, policy_version 361990 (0.0010) -[2023-11-28 09:42:41,488][87426] Updated weights for policy 1, policy_version 362000 (0.0012) -[2023-11-28 09:42:41,861][87426] Updated weights for policy 1, policy_version 362010 (0.0011) -[2023-11-28 09:42:42,338][87424] Updated weights for policy 0, policy_version 362369 (0.0009) -[2023-11-28 09:42:42,726][87424] Updated weights for policy 0, policy_version 362379 (0.0011) -[2023-11-28 09:42:43,120][87424] Updated weights for policy 0, policy_version 362389 (0.0012) -[2023-11-28 09:42:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185442304. Throughput: 0: 2664.8, 1: 2676.5. Samples: 185460560. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:43,445][86177] Avg episode reward: [(0, '-635.970'), (1, '-537.890')] -[2023-11-28 09:42:43,500][87424] Updated weights for policy 0, policy_version 362399 (0.0012) -[2023-11-28 09:42:44,344][87426] Updated weights for policy 1, policy_version 362020 (0.0011) -[2023-11-28 09:42:44,717][87426] Updated weights for policy 1, policy_version 362030 (0.0012) -[2023-11-28 09:42:45,089][87426] Updated weights for policy 1, policy_version 362040 (0.0008) -[2023-11-28 09:42:45,726][87424] Updated weights for policy 0, policy_version 362409 (0.0009) -[2023-11-28 09:42:46,105][87424] Updated weights for policy 0, policy_version 362419 (0.0010) -[2023-11-28 09:42:46,486][87424] Updated weights for policy 0, policy_version 362429 (0.0012) -[2023-11-28 09:42:47,364][87426] Updated weights for policy 1, policy_version 362050 (0.0010) -[2023-11-28 09:42:47,737][87426] Updated weights for policy 1, policy_version 362060 (0.0008) -[2023-11-28 09:42:48,120][87426] Updated weights for policy 1, policy_version 362070 (0.0011) -[2023-11-28 09:42:48,420][87424] Updated weights for policy 0, policy_version 362439 (0.0012) -[2023-11-28 09:42:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 185466880. Throughput: 0: 2671.8, 1: 2679.4. Samples: 185485320. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:48,445][86177] Avg episode reward: [(0, '-617.240'), (1, '-529.260')] -[2023-11-28 09:42:48,492][87426] Updated weights for policy 1, policy_version 362080 (0.0012) -[2023-11-28 09:42:48,802][87424] Updated weights for policy 0, policy_version 362449 (0.0012) -[2023-11-28 09:42:49,179][87424] Updated weights for policy 0, policy_version 362459 (0.0009) -[2023-11-28 09:42:50,443][87426] Updated weights for policy 1, policy_version 362090 (0.0012) -[2023-11-28 09:42:50,816][87426] Updated weights for policy 1, policy_version 362100 (0.0012) -[2023-11-28 09:42:51,192][87426] Updated weights for policy 1, policy_version 362110 (0.0011) -[2023-11-28 09:42:51,618][87424] Updated weights for policy 0, policy_version 362469 (0.0012) -[2023-11-28 09:42:51,995][87424] Updated weights for policy 0, policy_version 362479 (0.0012) -[2023-11-28 09:42:52,381][87424] Updated weights for policy 0, policy_version 362489 (0.0012) -[2023-11-28 09:42:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 185499648. Throughput: 0: 2646.3, 1: 2676.2. Samples: 185517940. Policy #0 lag: (min: 17.0, avg: 39.3, max: 49.0) -[2023-11-28 09:42:53,445][86177] Avg episode reward: [(0, '-609.060'), (1, '-532.110')] -[2023-11-28 09:42:53,498][87426] Updated weights for policy 1, policy_version 362120 (0.0011) -[2023-11-28 09:42:53,873][87426] Updated weights for policy 1, policy_version 362130 (0.0010) -[2023-11-28 09:42:54,264][87426] Updated weights for policy 1, policy_version 362140 (0.0009) -[2023-11-28 09:42:54,947][87424] Updated weights for policy 0, policy_version 362499 (0.0012) -[2023-11-28 09:42:55,339][87424] Updated weights for policy 0, policy_version 362509 (0.0009) -[2023-11-28 09:42:55,735][87424] Updated weights for policy 0, policy_version 362519 (0.0010) -[2023-11-28 09:42:56,186][87426] Updated weights for policy 1, policy_version 362150 (0.0009) -[2023-11-28 09:42:56,567][87426] Updated weights for policy 1, policy_version 362160 (0.0008) -[2023-11-28 09:42:56,946][87426] Updated weights for policy 1, policy_version 362170 (0.0008) -[2023-11-28 09:42:57,943][87424] Updated weights for policy 0, policy_version 362529 (0.0008) -[2023-11-28 09:42:58,315][87424] Updated weights for policy 0, policy_version 362539 (0.0011) -[2023-11-28 09:42:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 185524224. Throughput: 0: 2636.0, 1: 2707.2. Samples: 185542332. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:42:58,445][86177] Avg episode reward: [(0, '-572.690'), (1, '-529.760')] -[2023-11-28 09:42:58,704][87424] Updated weights for policy 0, policy_version 362549 (0.0012) -[2023-11-28 09:42:59,082][87424] Updated weights for policy 0, policy_version 362559 (0.0011) -[2023-11-28 09:42:59,085][87426] Updated weights for policy 1, policy_version 362180 (0.0009) -[2023-11-28 09:42:59,474][87426] Updated weights for policy 1, policy_version 362190 (0.0012) -[2023-11-28 09:42:59,850][87426] Updated weights for policy 1, policy_version 362200 (0.0008) -[2023-11-28 09:43:01,494][87424] Updated weights for policy 0, policy_version 362569 (0.0008) -[2023-11-28 09:43:01,713][87426] Updated weights for policy 1, policy_version 362210 (0.0009) -[2023-11-28 09:43:01,871][87424] Updated weights for policy 0, policy_version 362579 (0.0010) -[2023-11-28 09:43:02,083][87426] Updated weights for policy 1, policy_version 362220 (0.0011) -[2023-11-28 09:43:02,264][87424] Updated weights for policy 0, policy_version 362589 (0.0011) -[2023-11-28 09:43:02,461][87426] Updated weights for policy 1, policy_version 362230 (0.0011) -[2023-11-28 09:43:02,832][87426] Updated weights for policy 1, policy_version 362240 (0.0011) -[2023-11-28 09:43:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 185556992. Throughput: 0: 2626.5, 1: 2712.5. Samples: 185566164. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:03,445][86177] Avg episode reward: [(0, '-562.670'), (1, '-530.660')] -[2023-11-28 09:43:04,555][87424] Updated weights for policy 0, policy_version 362599 (0.0010) -[2023-11-28 09:43:04,936][87424] Updated weights for policy 0, policy_version 362609 (0.0010) -[2023-11-28 09:43:05,199][87426] Updated weights for policy 1, policy_version 362250 (0.0011) -[2023-11-28 09:43:05,321][87424] Updated weights for policy 0, policy_version 362619 (0.0008) -[2023-11-28 09:43:05,578][87426] Updated weights for policy 1, policy_version 362260 (0.0011) -[2023-11-28 09:43:05,959][87426] Updated weights for policy 1, policy_version 362270 (0.0012) -[2023-11-28 09:43:07,335][87424] Updated weights for policy 0, policy_version 362629 (0.0012) -[2023-11-28 09:43:07,724][87424] Updated weights for policy 0, policy_version 362639 (0.0012) -[2023-11-28 09:43:08,116][87424] Updated weights for policy 0, policy_version 362649 (0.0012) -[2023-11-28 09:43:08,304][87426] Updated weights for policy 1, policy_version 362280 (0.0008) -[2023-11-28 09:43:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185581568. Throughput: 0: 2673.1, 1: 2713.0. Samples: 185598544. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:08,445][86177] Avg episode reward: [(0, '-554.170'), (1, '-511.550')] -[2023-11-28 09:43:08,679][87426] Updated weights for policy 1, policy_version 362290 (0.0007) -[2023-11-28 09:43:09,064][87426] Updated weights for policy 1, policy_version 362300 (0.0008) -[2023-11-28 09:43:09,952][87424] Updated weights for policy 0, policy_version 362659 (0.0012) -[2023-11-28 09:43:10,335][87424] Updated weights for policy 0, policy_version 362669 (0.0012) -[2023-11-28 09:43:10,720][87424] Updated weights for policy 0, policy_version 362679 (0.0009) -[2023-11-28 09:43:11,257][87426] Updated weights for policy 1, policy_version 362310 (0.0010) -[2023-11-28 09:43:11,636][87426] Updated weights for policy 1, policy_version 362320 (0.0011) -[2023-11-28 09:43:12,017][87426] Updated weights for policy 1, policy_version 362330 (0.0009) -[2023-11-28 09:43:13,079][87424] Updated weights for policy 0, policy_version 362689 (0.0009) -[2023-11-28 09:43:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185606144. Throughput: 0: 2678.4, 1: 2706.5. Samples: 185622216. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:13,445][86177] Avg episode reward: [(0, '-552.650'), (1, '-510.620')] -[2023-11-28 09:43:13,457][87424] Updated weights for policy 0, policy_version 362699 (0.0012) -[2023-11-28 09:43:13,850][87424] Updated weights for policy 0, policy_version 362709 (0.0012) -[2023-11-28 09:43:14,103][87426] Updated weights for policy 1, policy_version 362340 (0.0011) -[2023-11-28 09:43:14,231][87424] Updated weights for policy 0, policy_version 362719 (0.0012) -[2023-11-28 09:43:14,488][87426] Updated weights for policy 1, policy_version 362350 (0.0011) -[2023-11-28 09:43:14,872][87426] Updated weights for policy 1, policy_version 362360 (0.0012) -[2023-11-28 09:43:16,040][87424] Updated weights for policy 0, policy_version 362729 (0.0010) -[2023-11-28 09:43:16,422][87424] Updated weights for policy 0, policy_version 362739 (0.0010) -[2023-11-28 09:43:16,803][87424] Updated weights for policy 0, policy_version 362749 (0.0007) -[2023-11-28 09:43:17,422][87426] Updated weights for policy 1, policy_version 362370 (0.0011) -[2023-11-28 09:43:17,802][87426] Updated weights for policy 1, policy_version 362380 (0.0010) -[2023-11-28 09:43:18,173][87426] Updated weights for policy 1, policy_version 362390 (0.0009) -[2023-11-28 09:43:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185630720. Throughput: 0: 2688.8, 1: 2702.4. Samples: 185645988. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:18,445][86177] Avg episode reward: [(0, '-559.670'), (1, '-508.470')] -[2023-11-28 09:43:18,556][87426] Updated weights for policy 1, policy_version 362400 (0.0007) -[2023-11-28 09:43:19,131][87424] Updated weights for policy 0, policy_version 362759 (0.0010) -[2023-11-28 09:43:19,516][87424] Updated weights for policy 0, policy_version 362769 (0.0011) -[2023-11-28 09:43:19,901][87424] Updated weights for policy 0, policy_version 362779 (0.0010) -[2023-11-28 09:43:20,543][87426] Updated weights for policy 1, policy_version 362410 (0.0008) -[2023-11-28 09:43:20,942][87426] Updated weights for policy 1, policy_version 362420 (0.0007) -[2023-11-28 09:43:21,321][87426] Updated weights for policy 1, policy_version 362430 (0.0008) -[2023-11-28 09:43:22,458][87424] Updated weights for policy 0, policy_version 362789 (0.0011) -[2023-11-28 09:43:22,837][87424] Updated weights for policy 0, policy_version 362799 (0.0012) -[2023-11-28 09:43:23,216][87424] Updated weights for policy 0, policy_version 362809 (0.0010) -[2023-11-28 09:43:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 185655296. Throughput: 0: 2646.7, 1: 2693.3. Samples: 185677216. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:23,445][86177] Avg episode reward: [(0, '-565.890'), (1, '-506.750')] -[2023-11-28 09:43:23,761][87426] Updated weights for policy 1, policy_version 362440 (0.0009) -[2023-11-28 09:43:24,136][87426] Updated weights for policy 1, policy_version 362450 (0.0007) -[2023-11-28 09:43:24,518][87426] Updated weights for policy 1, policy_version 362460 (0.0008) -[2023-11-28 09:43:25,765][87424] Updated weights for policy 0, policy_version 362819 (0.0008) -[2023-11-28 09:43:26,148][87424] Updated weights for policy 0, policy_version 362829 (0.0007) -[2023-11-28 09:43:26,530][87424] Updated weights for policy 0, policy_version 362839 (0.0008) -[2023-11-28 09:43:26,873][87426] Updated weights for policy 1, policy_version 362470 (0.0009) -[2023-11-28 09:43:27,245][87426] Updated weights for policy 1, policy_version 362480 (0.0011) -[2023-11-28 09:43:27,636][87426] Updated weights for policy 1, policy_version 362490 (0.0012) -[2023-11-28 09:43:28,248][87424] Updated weights for policy 0, policy_version 362849 (0.0008) -[2023-11-28 09:43:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185688064. Throughput: 0: 2667.3, 1: 2689.6. Samples: 185701620. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:28,445][86177] Avg episode reward: [(0, '-584.900'), (1, '-504.950')] -[2023-11-28 09:43:28,637][87424] Updated weights for policy 0, policy_version 362859 (0.0008) -[2023-11-28 09:43:29,023][87424] Updated weights for policy 0, policy_version 362869 (0.0008) -[2023-11-28 09:43:29,405][87424] Updated weights for policy 0, policy_version 362879 (0.0008) -[2023-11-28 09:43:30,147][87426] Updated weights for policy 1, policy_version 362500 (0.0010) -[2023-11-28 09:43:30,530][87426] Updated weights for policy 1, policy_version 362510 (0.0010) -[2023-11-28 09:43:30,903][87426] Updated weights for policy 1, policy_version 362520 (0.0009) -[2023-11-28 09:43:31,748][87424] Updated weights for policy 0, policy_version 362889 (0.0010) -[2023-11-28 09:43:32,132][87424] Updated weights for policy 0, policy_version 362899 (0.0012) -[2023-11-28 09:43:32,512][87424] Updated weights for policy 0, policy_version 362909 (0.0012) -[2023-11-28 09:43:32,983][87426] Updated weights for policy 1, policy_version 362530 (0.0009) -[2023-11-28 09:43:33,370][87426] Updated weights for policy 1, policy_version 362540 (0.0012) -[2023-11-28 09:43:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185712640. Throughput: 0: 2679.8, 1: 2671.2. Samples: 185726116. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:33,445][86177] Avg episode reward: [(0, '-583.400'), (1, '-502.060')] -[2023-11-28 09:43:33,758][87426] Updated weights for policy 1, policy_version 362550 (0.0012) -[2023-11-28 09:43:34,149][87426] Updated weights for policy 1, policy_version 362560 (0.0011) -[2023-11-28 09:43:34,409][87424] Updated weights for policy 0, policy_version 362919 (0.0009) -[2023-11-28 09:43:34,783][87424] Updated weights for policy 0, policy_version 362929 (0.0008) -[2023-11-28 09:43:35,166][87424] Updated weights for policy 0, policy_version 362939 (0.0009) -[2023-11-28 09:43:36,674][87426] Updated weights for policy 1, policy_version 362570 (0.0012) -[2023-11-28 09:43:37,047][87426] Updated weights for policy 1, policy_version 362580 (0.0011) -[2023-11-28 09:43:37,174][87424] Updated weights for policy 0, policy_version 362949 (0.0010) -[2023-11-28 09:43:37,428][87426] Updated weights for policy 1, policy_version 362590 (0.0011) -[2023-11-28 09:43:37,557][87424] Updated weights for policy 0, policy_version 362959 (0.0012) -[2023-11-28 09:43:37,932][87424] Updated weights for policy 0, policy_version 362969 (0.0012) -[2023-11-28 09:43:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 185745408. Throughput: 0: 2677.9, 1: 2640.6. Samples: 185757272. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:38,445][86177] Avg episode reward: [(0, '-585.660'), (1, '-521.530')] -[2023-11-28 09:43:39,859][87426] Updated weights for policy 1, policy_version 362600 (0.0012) -[2023-11-28 09:43:40,241][87426] Updated weights for policy 1, policy_version 362610 (0.0012) -[2023-11-28 09:43:40,341][87424] Updated weights for policy 0, policy_version 362979 (0.0010) -[2023-11-28 09:43:40,621][87426] Updated weights for policy 1, policy_version 362620 (0.0011) -[2023-11-28 09:43:40,720][87424] Updated weights for policy 0, policy_version 362989 (0.0012) -[2023-11-28 09:43:41,098][87424] Updated weights for policy 0, policy_version 362999 (0.0009) -[2023-11-28 09:43:42,956][87426] Updated weights for policy 1, policy_version 362630 (0.0012) -[2023-11-28 09:43:43,343][87426] Updated weights for policy 1, policy_version 362640 (0.0012) -[2023-11-28 09:43:43,427][87424] Updated weights for policy 0, policy_version 363009 (0.0010) -[2023-11-28 09:43:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185761792. Throughput: 0: 2677.6, 1: 2635.5. Samples: 185781420. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:43,445][86177] Avg episode reward: [(0, '-588.830'), (1, '-542.560')] -[2023-11-28 09:43:43,717][87426] Updated weights for policy 1, policy_version 362650 (0.0010) -[2023-11-28 09:43:43,806][87424] Updated weights for policy 0, policy_version 363019 (0.0010) -[2023-11-28 09:43:44,188][87424] Updated weights for policy 0, policy_version 363029 (0.0012) -[2023-11-28 09:43:44,566][87424] Updated weights for policy 0, policy_version 363039 (0.0012) -[2023-11-28 09:43:46,034][87426] Updated weights for policy 1, policy_version 362660 (0.0011) -[2023-11-28 09:43:46,411][87426] Updated weights for policy 1, policy_version 362670 (0.0012) -[2023-11-28 09:43:46,717][87424] Updated weights for policy 0, policy_version 363049 (0.0012) -[2023-11-28 09:43:46,786][87426] Updated weights for policy 1, policy_version 362680 (0.0008) -[2023-11-28 09:43:47,090][87424] Updated weights for policy 0, policy_version 363059 (0.0011) -[2023-11-28 09:43:47,474][87424] Updated weights for policy 0, policy_version 363069 (0.0012) -[2023-11-28 09:43:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 185794560. Throughput: 0: 2702.1, 1: 2618.7. Samples: 185805600. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:48,445][86177] Avg episode reward: [(0, '-582.390'), (1, '-550.860')] -[2023-11-28 09:43:48,635][87426] Updated weights for policy 1, policy_version 362690 (0.0010) -[2023-11-28 09:43:49,026][87426] Updated weights for policy 1, policy_version 362700 (0.0008) -[2023-11-28 09:43:49,396][87426] Updated weights for policy 1, policy_version 362710 (0.0008) -[2023-11-28 09:43:49,777][87426] Updated weights for policy 1, policy_version 362720 (0.0008) -[2023-11-28 09:43:49,831][87424] Updated weights for policy 0, policy_version 363079 (0.0011) -[2023-11-28 09:43:50,206][87424] Updated weights for policy 0, policy_version 363089 (0.0012) -[2023-11-28 09:43:50,576][87424] Updated weights for policy 0, policy_version 363099 (0.0010) -[2023-11-28 09:43:52,183][87426] Updated weights for policy 1, policy_version 362730 (0.0012) -[2023-11-28 09:43:52,562][87426] Updated weights for policy 1, policy_version 362740 (0.0010) -[2023-11-28 09:43:52,949][87426] Updated weights for policy 1, policy_version 362750 (0.0010) -[2023-11-28 09:43:53,114][87424] Updated weights for policy 0, policy_version 363109 (0.0012) -[2023-11-28 09:43:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 185819136. Throughput: 0: 2678.2, 1: 2637.7. Samples: 185837760. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:53,445][86177] Avg episode reward: [(0, '-577.760'), (1, '-551.360')] -[2023-11-28 09:43:53,485][87424] Updated weights for policy 0, policy_version 363119 (0.0011) -[2023-11-28 09:43:53,871][87424] Updated weights for policy 0, policy_version 363129 (0.0010) -[2023-11-28 09:43:55,370][87426] Updated weights for policy 1, policy_version 362760 (0.0011) -[2023-11-28 09:43:55,756][87426] Updated weights for policy 1, policy_version 362770 (0.0012) -[2023-11-28 09:43:55,932][87424] Updated weights for policy 0, policy_version 363139 (0.0009) -[2023-11-28 09:43:56,133][87426] Updated weights for policy 1, policy_version 362780 (0.0012) -[2023-11-28 09:43:56,312][87424] Updated weights for policy 0, policy_version 363149 (0.0008) -[2023-11-28 09:43:56,689][87424] Updated weights for policy 0, policy_version 363159 (0.0007) -[2023-11-28 09:43:57,838][87426] Updated weights for policy 1, policy_version 362790 (0.0012) -[2023-11-28 09:43:58,211][87426] Updated weights for policy 1, policy_version 362800 (0.0012) -[2023-11-28 09:43:58,336][87424] Updated weights for policy 0, policy_version 363169 (0.0007) -[2023-11-28 09:43:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185843712. Throughput: 0: 2676.5, 1: 2668.2. Samples: 185862728. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:43:58,445][86177] Avg episode reward: [(0, '-607.430'), (1, '-517.430')] -[2023-11-28 09:43:58,592][87426] Updated weights for policy 1, policy_version 362810 (0.0012) -[2023-11-28 09:43:58,718][87424] Updated weights for policy 0, policy_version 363179 (0.0008) -[2023-11-28 09:43:59,093][87424] Updated weights for policy 0, policy_version 363189 (0.0008) -[2023-11-28 09:43:59,471][87424] Updated weights for policy 0, policy_version 363199 (0.0007) -[2023-11-28 09:44:00,816][87426] Updated weights for policy 1, policy_version 362820 (0.0011) -[2023-11-28 09:44:01,205][87426] Updated weights for policy 1, policy_version 362830 (0.0011) -[2023-11-28 09:44:01,578][87426] Updated weights for policy 1, policy_version 362840 (0.0010) -[2023-11-28 09:44:01,934][87424] Updated weights for policy 0, policy_version 363209 (0.0011) -[2023-11-28 09:44:02,315][87424] Updated weights for policy 0, policy_version 363219 (0.0010) -[2023-11-28 09:44:02,696][87424] Updated weights for policy 0, policy_version 363229 (0.0008) -[2023-11-28 09:44:03,340][87426] Updated weights for policy 1, policy_version 362850 (0.0009) -[2023-11-28 09:44:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185876480. Throughput: 0: 2695.6, 1: 2678.7. Samples: 185887832. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:44:03,446][86177] Avg episode reward: [(0, '-597.880'), (1, '-515.590')] -[2023-11-28 09:44:03,711][87426] Updated weights for policy 1, policy_version 362860 (0.0007) -[2023-11-28 09:44:04,098][87426] Updated weights for policy 1, policy_version 362870 (0.0007) -[2023-11-28 09:44:04,474][87426] Updated weights for policy 1, policy_version 362880 (0.0009) -[2023-11-28 09:44:05,047][87424] Updated weights for policy 0, policy_version 363239 (0.0010) -[2023-11-28 09:44:05,430][87424] Updated weights for policy 0, policy_version 363249 (0.0012) -[2023-11-28 09:44:05,810][87424] Updated weights for policy 0, policy_version 363259 (0.0011) -[2023-11-28 09:44:06,782][87426] Updated weights for policy 1, policy_version 362890 (0.0010) -[2023-11-28 09:44:07,155][87426] Updated weights for policy 1, policy_version 362900 (0.0009) -[2023-11-28 09:44:07,540][87426] Updated weights for policy 1, policy_version 362910 (0.0008) -[2023-11-28 09:44:08,220][87424] Updated weights for policy 0, policy_version 363269 (0.0012) -[2023-11-28 09:44:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 185901056. Throughput: 0: 2728.5, 1: 2680.0. Samples: 185920600. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:44:08,445][86177] Avg episode reward: [(0, '-583.660'), (1, '-512.380')] -[2023-11-28 09:44:08,601][87424] Updated weights for policy 0, policy_version 363279 (0.0008) -[2023-11-28 09:44:08,982][87424] Updated weights for policy 0, policy_version 363289 (0.0008) -[2023-11-28 09:44:09,487][87426] Updated weights for policy 1, policy_version 362920 (0.0009) -[2023-11-28 09:44:09,866][87426] Updated weights for policy 1, policy_version 362930 (0.0009) -[2023-11-28 09:44:10,235][87426] Updated weights for policy 1, policy_version 362940 (0.0012) -[2023-11-28 09:44:11,426][87424] Updated weights for policy 0, policy_version 363299 (0.0008) -[2023-11-28 09:44:11,794][87424] Updated weights for policy 0, policy_version 363309 (0.0011) -[2023-11-28 09:44:12,175][87424] Updated weights for policy 0, policy_version 363319 (0.0012) -[2023-11-28 09:44:12,481][87426] Updated weights for policy 1, policy_version 362950 (0.0011) -[2023-11-28 09:44:12,853][87426] Updated weights for policy 1, policy_version 362960 (0.0009) -[2023-11-28 09:44:13,236][87426] Updated weights for policy 1, policy_version 362970 (0.0012) -[2023-11-28 09:44:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 185925632. Throughput: 0: 2701.2, 1: 2688.8. Samples: 185944168. Policy #0 lag: (min: 28.0, avg: 59.7, max: 92.0) -[2023-11-28 09:44:13,445][86177] Avg episode reward: [(0, '-585.390'), (1, '-512.920')] -[2023-11-28 09:44:14,534][87424] Updated weights for policy 0, policy_version 363329 (0.0011) -[2023-11-28 09:44:14,917][87424] Updated weights for policy 0, policy_version 363339 (0.0011) -[2023-11-28 09:44:15,303][87424] Updated weights for policy 0, policy_version 363349 (0.0011) -[2023-11-28 09:44:15,621][87426] Updated weights for policy 1, policy_version 362980 (0.0010) -[2023-11-28 09:44:15,684][87424] Updated weights for policy 0, policy_version 363359 (0.0011) -[2023-11-28 09:44:15,999][87426] Updated weights for policy 1, policy_version 362990 (0.0011) -[2023-11-28 09:44:16,384][87426] Updated weights for policy 1, policy_version 363000 (0.0011) -[2023-11-28 09:44:18,030][87424] Updated weights for policy 0, policy_version 363369 (0.0008) -[2023-11-28 09:44:18,209][87426] Updated weights for policy 1, policy_version 363010 (0.0008) -[2023-11-28 09:44:18,409][87424] Updated weights for policy 0, policy_version 363379 (0.0010) -[2023-11-28 09:44:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 185950208. Throughput: 0: 2660.3, 1: 2709.1. Samples: 185967736. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:44:18,446][86177] Avg episode reward: [(0, '-558.570'), (1, '-513.140')] -[2023-11-28 09:44:18,594][87426] Updated weights for policy 1, policy_version 363020 (0.0008) -[2023-11-28 09:44:18,797][87424] Updated weights for policy 0, policy_version 363389 (0.0011) -[2023-11-28 09:44:18,906][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000363392_93028352.pth... -[2023-11-28 09:44:18,950][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000360864_92381184.pth -[2023-11-28 09:44:18,976][87426] Updated weights for policy 1, policy_version 363030 (0.0008) -[2023-11-28 09:44:19,350][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000363040_92938240.pth... -[2023-11-28 09:44:19,351][87426] Updated weights for policy 1, policy_version 363040 (0.0010) -[2023-11-28 09:44:19,395][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000360512_92291072.pth -[2023-11-28 09:44:20,622][87424] Updated weights for policy 0, policy_version 363399 (0.0011) -[2023-11-28 09:44:20,997][87424] Updated weights for policy 0, policy_version 363409 (0.0011) -[2023-11-28 09:44:21,376][87424] Updated weights for policy 0, policy_version 363419 (0.0015) -[2023-11-28 09:44:21,759][87426] Updated weights for policy 1, policy_version 363050 (0.0009) -[2023-11-28 09:44:22,145][87426] Updated weights for policy 1, policy_version 363060 (0.0011) -[2023-11-28 09:44:22,526][87426] Updated weights for policy 1, policy_version 363070 (0.0010) -[2023-11-28 09:44:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 185982976. Throughput: 0: 2633.6, 1: 2722.8. Samples: 185998308. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:44:23,445][86177] Avg episode reward: [(0, '-549.400'), (1, '-515.650')] -[2023-11-28 09:44:24,021][87424] Updated weights for policy 0, policy_version 363429 (0.0011) -[2023-11-28 09:44:24,399][87424] Updated weights for policy 0, policy_version 363439 (0.0011) -[2023-11-28 09:44:24,574][87426] Updated weights for policy 1, policy_version 363080 (0.0010) -[2023-11-28 09:44:24,775][87424] Updated weights for policy 0, policy_version 363449 (0.0009) -[2023-11-28 09:44:24,954][87426] Updated weights for policy 1, policy_version 363090 (0.0007) -[2023-11-28 09:44:25,339][87426] Updated weights for policy 1, policy_version 363100 (0.0008) -[2023-11-28 09:44:27,026][87424] Updated weights for policy 0, policy_version 363459 (0.0009) -[2023-11-28 09:44:27,410][87424] Updated weights for policy 0, policy_version 363469 (0.0011) -[2023-11-28 09:44:27,554][87426] Updated weights for policy 1, policy_version 363110 (0.0009) -[2023-11-28 09:44:27,783][87424] Updated weights for policy 0, policy_version 363479 (0.0012) -[2023-11-28 09:44:27,944][87426] Updated weights for policy 1, policy_version 363120 (0.0007) -[2023-11-28 09:44:28,332][87426] Updated weights for policy 1, policy_version 363130 (0.0009) -[2023-11-28 09:44:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186007552. Throughput: 0: 2654.2, 1: 2732.3. Samples: 186023812. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:44:28,445][86177] Avg episode reward: [(0, '-554.820'), (1, '-518.880')] -[2023-11-28 09:44:30,023][87424] Updated weights for policy 0, policy_version 363489 (0.0012) -[2023-11-28 09:44:30,239][87426] Updated weights for policy 1, policy_version 363140 (0.0009) -[2023-11-28 09:44:30,405][87424] Updated weights for policy 0, policy_version 363499 (0.0008) -[2023-11-28 09:44:30,611][87426] Updated weights for policy 1, policy_version 363150 (0.0012) -[2023-11-28 09:44:30,786][87424] Updated weights for policy 0, policy_version 363509 (0.0011) -[2023-11-28 09:44:30,989][87426] Updated weights for policy 1, policy_version 363160 (0.0011) -[2023-11-28 09:44:31,171][87424] Updated weights for policy 0, policy_version 363519 (0.0011) -[2023-11-28 09:44:33,169][87426] Updated weights for policy 1, policy_version 363170 (0.0012) -[2023-11-28 09:44:33,269][87424] Updated weights for policy 0, policy_version 363529 (0.0010) -[2023-11-28 09:44:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 186032128. Throughput: 0: 2651.8, 1: 2736.0. Samples: 186048052. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:44:33,445][86177] Avg episode reward: [(0, '-556.680'), (1, '-526.630')] -[2023-11-28 09:44:33,551][87426] Updated weights for policy 1, policy_version 363180 (0.0011) -[2023-11-28 09:44:33,643][87424] Updated weights for policy 0, policy_version 363539 (0.0007) -[2023-11-28 09:44:33,929][87426] Updated weights for policy 1, policy_version 363190 (0.0012) -[2023-11-28 09:44:34,024][87424] Updated weights for policy 0, policy_version 363549 (0.0008) -[2023-11-28 09:44:34,306][87426] Updated weights for policy 1, policy_version 363200 (0.0008) -[2023-11-28 09:44:35,957][87424] Updated weights for policy 0, policy_version 363559 (0.0010) -[2023-11-28 09:44:36,331][87424] Updated weights for policy 0, policy_version 363569 (0.0011) -[2023-11-28 09:44:36,433][87426] Updated weights for policy 1, policy_version 363210 (0.0008) -[2023-11-28 09:44:36,712][87424] Updated weights for policy 0, policy_version 363579 (0.0011) -[2023-11-28 09:44:36,815][87426] Updated weights for policy 1, policy_version 363220 (0.0010) -[2023-11-28 09:44:37,185][87426] Updated weights for policy 1, policy_version 363230 (0.0012) -[2023-11-28 09:44:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 186064896. Throughput: 0: 2683.1, 1: 2753.1. Samples: 186082388. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:44:38,445][86177] Avg episode reward: [(0, '-557.420'), (1, '-524.910')] -[2023-11-28 09:44:38,511][87424] Updated weights for policy 0, policy_version 363589 (0.0011) -[2023-11-28 09:44:38,891][87424] Updated weights for policy 0, policy_version 363599 (0.0012) -[2023-11-28 09:44:39,270][87424] Updated weights for policy 0, policy_version 363609 (0.0012) -[2023-11-28 09:44:39,308][87426] Updated weights for policy 1, policy_version 363240 (0.0012) -[2023-11-28 09:44:39,685][87426] Updated weights for policy 1, policy_version 363250 (0.0011) -[2023-11-28 09:44:40,056][87426] Updated weights for policy 1, policy_version 363260 (0.0011) -[2023-11-28 09:44:41,399][87424] Updated weights for policy 0, policy_version 363619 (0.0012) -[2023-11-28 09:44:41,780][87424] Updated weights for policy 0, policy_version 363629 (0.0012) -[2023-11-28 09:44:42,156][87424] Updated weights for policy 0, policy_version 363639 (0.0012) -[2023-11-28 09:44:42,568][87426] Updated weights for policy 1, policy_version 363270 (0.0009) -[2023-11-28 09:44:42,953][87426] Updated weights for policy 1, policy_version 363280 (0.0010) -[2023-11-28 09:44:43,334][87426] Updated weights for policy 1, policy_version 363290 (0.0009) -[2023-11-28 09:44:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 186089472. Throughput: 0: 2677.9, 1: 2750.9. Samples: 186107024. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:44:43,446][86177] Avg episode reward: [(0, '-598.540'), (1, '-522.850')] -[2023-11-28 09:44:44,781][87424] Updated weights for policy 0, policy_version 363649 (0.0010) -[2023-11-28 09:44:45,161][87424] Updated weights for policy 0, policy_version 363659 (0.0011) -[2023-11-28 09:44:45,243][87426] Updated weights for policy 1, policy_version 363300 (0.0010) -[2023-11-28 09:44:45,541][87424] Updated weights for policy 0, policy_version 363669 (0.0010) -[2023-11-28 09:44:45,622][87426] Updated weights for policy 1, policy_version 363310 (0.0013) -[2023-11-28 09:44:45,922][87424] Updated weights for policy 0, policy_version 363679 (0.0011) -[2023-11-28 09:44:46,001][87426] Updated weights for policy 1, policy_version 363320 (0.0010) -[2023-11-28 09:44:48,018][87424] Updated weights for policy 0, policy_version 363689 (0.0011) -[2023-11-28 09:44:48,403][87424] Updated weights for policy 0, policy_version 363699 (0.0011) -[2023-11-28 09:44:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186114048. Throughput: 0: 2659.1, 1: 2745.4. Samples: 186131036. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:44:48,445][86177] Avg episode reward: [(0, '-593.600'), (1, '-519.870')] -[2023-11-28 09:44:48,483][87426] Updated weights for policy 1, policy_version 363330 (0.0008) -[2023-11-28 09:44:48,794][87424] Updated weights for policy 0, policy_version 363709 (0.0011) -[2023-11-28 09:44:48,865][87426] Updated weights for policy 1, policy_version 363340 (0.0008) -[2023-11-28 09:44:49,236][87426] Updated weights for policy 1, policy_version 363350 (0.0008) -[2023-11-28 09:44:49,616][87426] Updated weights for policy 1, policy_version 363360 (0.0007) -[2023-11-28 09:44:51,058][87424] Updated weights for policy 0, policy_version 363719 (0.0009) -[2023-11-28 09:44:51,439][87424] Updated weights for policy 0, policy_version 363729 (0.0011) -[2023-11-28 09:44:51,824][87424] Updated weights for policy 0, policy_version 363739 (0.0012) -[2023-11-28 09:44:52,056][87426] Updated weights for policy 1, policy_version 363370 (0.0017) -[2023-11-28 09:44:52,443][87426] Updated weights for policy 1, policy_version 363380 (0.0010) -[2023-11-28 09:44:52,813][87426] Updated weights for policy 1, policy_version 363390 (0.0009) -[2023-11-28 09:44:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 186146816. Throughput: 0: 2647.6, 1: 2726.4. Samples: 186162432. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:44:53,445][86177] Avg episode reward: [(0, '-578.900'), (1, '-510.610')] -[2023-11-28 09:44:54,346][87424] Updated weights for policy 0, policy_version 363749 (0.0011) -[2023-11-28 09:44:54,717][87424] Updated weights for policy 0, policy_version 363759 (0.0011) -[2023-11-28 09:44:54,924][87426] Updated weights for policy 1, policy_version 363400 (0.0011) -[2023-11-28 09:44:55,106][87424] Updated weights for policy 0, policy_version 363769 (0.0008) -[2023-11-28 09:44:55,297][87426] Updated weights for policy 1, policy_version 363410 (0.0011) -[2023-11-28 09:44:55,675][87426] Updated weights for policy 1, policy_version 363420 (0.0009) -[2023-11-28 09:44:56,814][87424] Updated weights for policy 0, policy_version 363779 (0.0009) -[2023-11-28 09:44:57,199][87424] Updated weights for policy 0, policy_version 363789 (0.0012) -[2023-11-28 09:44:57,537][87426] Updated weights for policy 1, policy_version 363430 (0.0011) -[2023-11-28 09:44:57,562][87424] Updated weights for policy 0, policy_version 363799 (0.0010) -[2023-11-28 09:44:57,921][87426] Updated weights for policy 1, policy_version 363440 (0.0009) -[2023-11-28 09:44:58,295][87426] Updated weights for policy 1, policy_version 363450 (0.0007) -[2023-11-28 09:44:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5359.5). Total num frames: 186171392. Throughput: 0: 2656.2, 1: 2755.9. Samples: 186187712. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:44:58,445][86177] Avg episode reward: [(0, '-590.560'), (1, '-511.760')] -[2023-11-28 09:44:59,928][87424] Updated weights for policy 0, policy_version 363809 (0.0008) -[2023-11-28 09:45:00,309][87424] Updated weights for policy 0, policy_version 363819 (0.0011) -[2023-11-28 09:45:00,687][87424] Updated weights for policy 0, policy_version 363829 (0.0009) -[2023-11-28 09:45:00,733][87426] Updated weights for policy 1, policy_version 363460 (0.0007) -[2023-11-28 09:45:01,077][87424] Updated weights for policy 0, policy_version 363839 (0.0008) -[2023-11-28 09:45:01,111][87426] Updated weights for policy 1, policy_version 363470 (0.0008) -[2023-11-28 09:45:01,492][87426] Updated weights for policy 1, policy_version 363480 (0.0012) -[2023-11-28 09:45:03,057][87424] Updated weights for policy 0, policy_version 363849 (0.0012) -[2023-11-28 09:45:03,440][87424] Updated weights for policy 0, policy_version 363859 (0.0012) -[2023-11-28 09:45:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186195968. Throughput: 0: 2680.9, 1: 2739.4. Samples: 186211648. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:45:03,445][86177] Avg episode reward: [(0, '-577.360'), (1, '-515.300')] -[2023-11-28 09:45:03,569][87426] Updated weights for policy 1, policy_version 363490 (0.0012) -[2023-11-28 09:45:03,824][87424] Updated weights for policy 0, policy_version 363869 (0.0011) -[2023-11-28 09:45:03,949][87426] Updated weights for policy 1, policy_version 363500 (0.0010) -[2023-11-28 09:45:04,331][87426] Updated weights for policy 1, policy_version 363510 (0.0008) -[2023-11-28 09:45:04,716][87426] Updated weights for policy 1, policy_version 363520 (0.0010) -[2023-11-28 09:45:05,820][87424] Updated weights for policy 0, policy_version 363879 (0.0011) -[2023-11-28 09:45:06,201][87424] Updated weights for policy 0, policy_version 363889 (0.0012) -[2023-11-28 09:45:06,582][87424] Updated weights for policy 0, policy_version 363899 (0.0012) -[2023-11-28 09:45:06,685][87426] Updated weights for policy 1, policy_version 363530 (0.0012) -[2023-11-28 09:45:07,068][87426] Updated weights for policy 1, policy_version 363540 (0.0010) -[2023-11-28 09:45:07,440][87426] Updated weights for policy 1, policy_version 363550 (0.0007) -[2023-11-28 09:45:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 186228736. Throughput: 0: 2714.5, 1: 2755.2. Samples: 186244444. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:45:08,445][86177] Avg episode reward: [(0, '-555.530'), (1, '-517.700')] -[2023-11-28 09:45:09,053][87424] Updated weights for policy 0, policy_version 363909 (0.0011) -[2023-11-28 09:45:09,451][87424] Updated weights for policy 0, policy_version 363919 (0.0011) -[2023-11-28 09:45:09,827][87424] Updated weights for policy 0, policy_version 363929 (0.0012) -[2023-11-28 09:45:09,897][87426] Updated weights for policy 1, policy_version 363560 (0.0010) -[2023-11-28 09:45:10,267][87426] Updated weights for policy 1, policy_version 363570 (0.0011) -[2023-11-28 09:45:10,658][87426] Updated weights for policy 1, policy_version 363580 (0.0011) -[2023-11-28 09:45:11,952][87424] Updated weights for policy 0, policy_version 363939 (0.0010) -[2023-11-28 09:45:12,331][87424] Updated weights for policy 0, policy_version 363949 (0.0012) -[2023-11-28 09:45:12,713][87424] Updated weights for policy 0, policy_version 363959 (0.0012) -[2023-11-28 09:45:12,734][87426] Updated weights for policy 1, policy_version 363590 (0.0011) -[2023-11-28 09:45:13,122][87426] Updated weights for policy 1, policy_version 363600 (0.0011) -[2023-11-28 09:45:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 186253312. Throughput: 0: 2699.3, 1: 2720.8. Samples: 186267716. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:45:13,445][86177] Avg episode reward: [(0, '-557.950'), (1, '-516.490')] -[2023-11-28 09:45:13,513][87426] Updated weights for policy 1, policy_version 363610 (0.0012) -[2023-11-28 09:45:14,843][87424] Updated weights for policy 0, policy_version 363969 (0.0011) -[2023-11-28 09:45:15,223][87424] Updated weights for policy 0, policy_version 363979 (0.0010) -[2023-11-28 09:45:15,605][87424] Updated weights for policy 0, policy_version 363989 (0.0008) -[2023-11-28 09:45:15,709][87426] Updated weights for policy 1, policy_version 363620 (0.0012) -[2023-11-28 09:45:15,983][87424] Updated weights for policy 0, policy_version 363999 (0.0011) -[2023-11-28 09:45:16,087][87426] Updated weights for policy 1, policy_version 363630 (0.0011) -[2023-11-28 09:45:16,469][87426] Updated weights for policy 1, policy_version 363640 (0.0012) -[2023-11-28 09:45:17,873][87424] Updated weights for policy 0, policy_version 364009 (0.0008) -[2023-11-28 09:45:18,255][87424] Updated weights for policy 0, policy_version 364019 (0.0008) -[2023-11-28 09:45:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 186277888. Throughput: 0: 2705.1, 1: 2721.6. Samples: 186292252. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:45:18,445][86177] Avg episode reward: [(0, '-552.810'), (1, '-515.450')] -[2023-11-28 09:45:18,636][87424] Updated weights for policy 0, policy_version 364029 (0.0012) -[2023-11-28 09:45:18,753][87426] Updated weights for policy 1, policy_version 363650 (0.0010) -[2023-11-28 09:45:19,122][87426] Updated weights for policy 1, policy_version 363660 (0.0010) -[2023-11-28 09:45:19,505][87426] Updated weights for policy 1, policy_version 363670 (0.0011) -[2023-11-28 09:45:19,899][87426] Updated weights for policy 1, policy_version 363680 (0.0010) -[2023-11-28 09:45:20,985][87424] Updated weights for policy 0, policy_version 364039 (0.0012) -[2023-11-28 09:45:21,358][87424] Updated weights for policy 0, policy_version 364049 (0.0012) -[2023-11-28 09:45:21,724][87424] Updated weights for policy 0, policy_version 364059 (0.0012) -[2023-11-28 09:45:22,389][87426] Updated weights for policy 1, policy_version 363690 (0.0010) -[2023-11-28 09:45:22,763][87426] Updated weights for policy 1, policy_version 363700 (0.0012) -[2023-11-28 09:45:23,145][87426] Updated weights for policy 1, policy_version 363710 (0.0011) -[2023-11-28 09:45:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 186310656. Throughput: 0: 2683.5, 1: 2691.5. Samples: 186324260. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:45:23,445][86177] Avg episode reward: [(0, '-575.480'), (1, '-521.680')] -[2023-11-28 09:45:24,075][87424] Updated weights for policy 0, policy_version 364069 (0.0011) -[2023-11-28 09:45:24,468][87424] Updated weights for policy 0, policy_version 364079 (0.0007) -[2023-11-28 09:45:24,840][87424] Updated weights for policy 0, policy_version 364089 (0.0008) -[2023-11-28 09:45:25,751][87426] Updated weights for policy 1, policy_version 363720 (0.0007) -[2023-11-28 09:45:26,130][87426] Updated weights for policy 1, policy_version 363730 (0.0007) -[2023-11-28 09:45:26,502][87426] Updated weights for policy 1, policy_version 363740 (0.0007) -[2023-11-28 09:45:27,302][87424] Updated weights for policy 0, policy_version 364099 (0.0012) -[2023-11-28 09:45:27,680][87424] Updated weights for policy 0, policy_version 364109 (0.0011) -[2023-11-28 09:45:28,069][87424] Updated weights for policy 0, policy_version 364119 (0.0012) -[2023-11-28 09:45:28,242][87426] Updated weights for policy 1, policy_version 363750 (0.0007) -[2023-11-28 09:45:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 186335232. Throughput: 0: 2684.5, 1: 2689.2. Samples: 186348840. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:45:28,445][86177] Avg episode reward: [(0, '-570.890'), (1, '-516.680')] -[2023-11-28 09:45:28,630][87426] Updated weights for policy 1, policy_version 363760 (0.0008) -[2023-11-28 09:45:29,016][87426] Updated weights for policy 1, policy_version 363770 (0.0007) -[2023-11-28 09:45:30,587][87424] Updated weights for policy 0, policy_version 364129 (0.0009) -[2023-11-28 09:45:30,965][87424] Updated weights for policy 0, policy_version 364139 (0.0011) -[2023-11-28 09:45:31,098][87426] Updated weights for policy 1, policy_version 363780 (0.0009) -[2023-11-28 09:45:31,337][87424] Updated weights for policy 0, policy_version 364149 (0.0011) -[2023-11-28 09:45:31,466][87426] Updated weights for policy 1, policy_version 363790 (0.0009) -[2023-11-28 09:45:31,727][87424] Updated weights for policy 0, policy_version 364159 (0.0009) -[2023-11-28 09:45:31,846][87426] Updated weights for policy 1, policy_version 363800 (0.0010) -[2023-11-28 09:45:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 186359808. Throughput: 0: 2665.8, 1: 2699.5. Samples: 186372472. Policy #0 lag: (min: 40.0, avg: 52.8, max: 77.0) -[2023-11-28 09:45:33,445][86177] Avg episode reward: [(0, '-571.990'), (1, '-520.070')] -[2023-11-28 09:45:34,012][87426] Updated weights for policy 1, policy_version 363810 (0.0012) -[2023-11-28 09:45:34,050][87424] Updated weights for policy 0, policy_version 364169 (0.0008) -[2023-11-28 09:45:34,385][87426] Updated weights for policy 1, policy_version 363820 (0.0012) -[2023-11-28 09:45:34,432][87424] Updated weights for policy 0, policy_version 364179 (0.0011) -[2023-11-28 09:45:34,763][87426] Updated weights for policy 1, policy_version 363830 (0.0011) -[2023-11-28 09:45:34,821][87424] Updated weights for policy 0, policy_version 364189 (0.0011) -[2023-11-28 09:45:35,147][87426] Updated weights for policy 1, policy_version 363840 (0.0011) -[2023-11-28 09:45:36,621][87424] Updated weights for policy 0, policy_version 364199 (0.0011) -[2023-11-28 09:45:37,004][87424] Updated weights for policy 0, policy_version 364209 (0.0012) -[2023-11-28 09:45:37,237][87426] Updated weights for policy 1, policy_version 363850 (0.0009) -[2023-11-28 09:45:37,385][87424] Updated weights for policy 0, policy_version 364219 (0.0011) -[2023-11-28 09:45:37,613][87426] Updated weights for policy 1, policy_version 363860 (0.0008) -[2023-11-28 09:45:37,986][87426] Updated weights for policy 1, policy_version 363870 (0.0007) -[2023-11-28 09:45:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 186392576. Throughput: 0: 2681.6, 1: 2717.2. Samples: 186405380. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:45:38,445][86177] Avg episode reward: [(0, '-562.380'), (1, '-517.380')] -[2023-11-28 09:45:39,561][87424] Updated weights for policy 0, policy_version 364229 (0.0009) -[2023-11-28 09:45:39,936][87424] Updated weights for policy 0, policy_version 364239 (0.0012) -[2023-11-28 09:45:40,314][87424] Updated weights for policy 0, policy_version 364249 (0.0011) -[2023-11-28 09:45:40,350][87426] Updated weights for policy 1, policy_version 363880 (0.0008) -[2023-11-28 09:45:40,735][87426] Updated weights for policy 1, policy_version 363890 (0.0012) -[2023-11-28 09:45:41,116][87426] Updated weights for policy 1, policy_version 363900 (0.0012) -[2023-11-28 09:45:42,474][87424] Updated weights for policy 0, policy_version 364259 (0.0011) -[2023-11-28 09:45:42,863][87424] Updated weights for policy 0, policy_version 364269 (0.0010) -[2023-11-28 09:45:43,232][87424] Updated weights for policy 0, policy_version 364279 (0.0012) -[2023-11-28 09:45:43,338][87426] Updated weights for policy 1, policy_version 363910 (0.0012) -[2023-11-28 09:45:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186408960. Throughput: 0: 2684.4, 1: 2683.6. Samples: 186429272. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:45:43,445][86177] Avg episode reward: [(0, '-547.470'), (1, '-520.830')] -[2023-11-28 09:45:43,710][87426] Updated weights for policy 1, policy_version 363920 (0.0012) -[2023-11-28 09:45:44,098][87426] Updated weights for policy 1, policy_version 363930 (0.0011) -[2023-11-28 09:45:45,692][87424] Updated weights for policy 0, policy_version 364289 (0.0011) -[2023-11-28 09:45:46,074][87424] Updated weights for policy 0, policy_version 364299 (0.0011) -[2023-11-28 09:45:46,208][87426] Updated weights for policy 1, policy_version 363940 (0.0011) -[2023-11-28 09:45:46,453][87424] Updated weights for policy 0, policy_version 364309 (0.0010) -[2023-11-28 09:45:46,582][87426] Updated weights for policy 1, policy_version 363950 (0.0012) -[2023-11-28 09:45:46,835][87424] Updated weights for policy 0, policy_version 364319 (0.0010) -[2023-11-28 09:45:46,964][87426] Updated weights for policy 1, policy_version 363960 (0.0011) -[2023-11-28 09:45:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 186441728. Throughput: 0: 2671.3, 1: 2691.5. Samples: 186452972. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:45:48,445][86177] Avg episode reward: [(0, '-543.680'), (1, '-563.100')] -[2023-11-28 09:45:48,992][87426] Updated weights for policy 1, policy_version 363970 (0.0012) -[2023-11-28 09:45:49,299][87424] Updated weights for policy 0, policy_version 364329 (0.0011) -[2023-11-28 09:45:49,373][87426] Updated weights for policy 1, policy_version 363980 (0.0009) -[2023-11-28 09:45:49,681][87424] Updated weights for policy 0, policy_version 364339 (0.0010) -[2023-11-28 09:45:49,742][87426] Updated weights for policy 1, policy_version 363990 (0.0008) -[2023-11-28 09:45:50,069][87424] Updated weights for policy 0, policy_version 364349 (0.0011) -[2023-11-28 09:45:50,120][87426] Updated weights for policy 1, policy_version 364000 (0.0010) -[2023-11-28 09:45:52,247][87426] Updated weights for policy 1, policy_version 364010 (0.0009) -[2023-11-28 09:45:52,615][87424] Updated weights for policy 0, policy_version 364359 (0.0010) -[2023-11-28 09:45:52,620][87426] Updated weights for policy 1, policy_version 364020 (0.0008) -[2023-11-28 09:45:52,983][87424] Updated weights for policy 0, policy_version 364369 (0.0011) -[2023-11-28 09:45:53,002][87426] Updated weights for policy 1, policy_version 364030 (0.0009) -[2023-11-28 09:45:53,375][87424] Updated weights for policy 0, policy_version 364379 (0.0011) -[2023-11-28 09:45:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186466304. Throughput: 0: 2628.2, 1: 2701.2. Samples: 186484264. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:45:53,445][86177] Avg episode reward: [(0, '-592.580'), (1, '-559.230')] -[2023-11-28 09:45:55,442][87426] Updated weights for policy 1, policy_version 364040 (0.0009) -[2023-11-28 09:45:55,535][87424] Updated weights for policy 0, policy_version 364389 (0.0011) -[2023-11-28 09:45:55,826][87426] Updated weights for policy 1, policy_version 364050 (0.0009) -[2023-11-28 09:45:55,927][87424] Updated weights for policy 0, policy_version 364399 (0.0012) -[2023-11-28 09:45:56,212][87426] Updated weights for policy 1, policy_version 364060 (0.0011) -[2023-11-28 09:45:56,305][87424] Updated weights for policy 0, policy_version 364409 (0.0011) -[2023-11-28 09:45:58,316][87426] Updated weights for policy 1, policy_version 364070 (0.0011) -[2023-11-28 09:45:58,425][87424] Updated weights for policy 0, policy_version 364419 (0.0011) -[2023-11-28 09:45:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186490880. Throughput: 0: 2649.1, 1: 2725.0. Samples: 186509548. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:45:58,445][86177] Avg episode reward: [(0, '-609.840'), (1, '-553.340')] -[2023-11-28 09:45:58,702][87426] Updated weights for policy 1, policy_version 364080 (0.0008) -[2023-11-28 09:45:58,825][87424] Updated weights for policy 0, policy_version 364429 (0.0011) -[2023-11-28 09:45:59,091][87426] Updated weights for policy 1, policy_version 364090 (0.0008) -[2023-11-28 09:45:59,200][87424] Updated weights for policy 0, policy_version 364439 (0.0012) -[2023-11-28 09:46:01,009][87426] Updated weights for policy 1, policy_version 364100 (0.0010) -[2023-11-28 09:46:01,377][87424] Updated weights for policy 0, policy_version 364449 (0.0012) -[2023-11-28 09:46:01,386][87426] Updated weights for policy 1, policy_version 364110 (0.0008) -[2023-11-28 09:46:01,757][87424] Updated weights for policy 0, policy_version 364459 (0.0010) -[2023-11-28 09:46:01,761][87426] Updated weights for policy 1, policy_version 364120 (0.0010) -[2023-11-28 09:46:02,135][87424] Updated weights for policy 0, policy_version 364469 (0.0009) -[2023-11-28 09:46:02,516][87424] Updated weights for policy 0, policy_version 364479 (0.0010) -[2023-11-28 09:46:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 186523648. Throughput: 0: 2672.3, 1: 2729.1. Samples: 186535320. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:03,445][86177] Avg episode reward: [(0, '-613.830'), (1, '-528.610')] -[2023-11-28 09:46:03,896][87426] Updated weights for policy 1, policy_version 364130 (0.0011) -[2023-11-28 09:46:04,266][87426] Updated weights for policy 1, policy_version 364140 (0.0009) -[2023-11-28 09:46:04,641][87426] Updated weights for policy 1, policy_version 364150 (0.0011) -[2023-11-28 09:46:04,800][87424] Updated weights for policy 0, policy_version 364489 (0.0011) -[2023-11-28 09:46:05,017][87426] Updated weights for policy 1, policy_version 364160 (0.0012) -[2023-11-28 09:46:05,185][87424] Updated weights for policy 0, policy_version 364499 (0.0010) -[2023-11-28 09:46:05,564][87424] Updated weights for policy 0, policy_version 364509 (0.0008) -[2023-11-28 09:46:07,056][87426] Updated weights for policy 1, policy_version 364170 (0.0008) -[2023-11-28 09:46:07,423][87426] Updated weights for policy 1, policy_version 364180 (0.0011) -[2023-11-28 09:46:07,699][87424] Updated weights for policy 0, policy_version 364519 (0.0010) -[2023-11-28 09:46:07,804][87426] Updated weights for policy 1, policy_version 364190 (0.0008) -[2023-11-28 09:46:08,091][87424] Updated weights for policy 0, policy_version 364529 (0.0011) -[2023-11-28 09:46:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 186548224. Throughput: 0: 2674.3, 1: 2738.0. Samples: 186567816. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:08,446][86177] Avg episode reward: [(0, '-608.360'), (1, '-522.620')] -[2023-11-28 09:46:08,461][87424] Updated weights for policy 0, policy_version 364539 (0.0012) -[2023-11-28 09:46:10,092][87426] Updated weights for policy 1, policy_version 364200 (0.0010) -[2023-11-28 09:46:10,477][87426] Updated weights for policy 1, policy_version 364210 (0.0009) -[2023-11-28 09:46:10,740][87424] Updated weights for policy 0, policy_version 364549 (0.0010) -[2023-11-28 09:46:10,855][87426] Updated weights for policy 1, policy_version 364220 (0.0010) -[2023-11-28 09:46:11,123][87424] Updated weights for policy 0, policy_version 364559 (0.0008) -[2023-11-28 09:46:11,509][87424] Updated weights for policy 0, policy_version 364569 (0.0008) -[2023-11-28 09:46:13,107][87426] Updated weights for policy 1, policy_version 364230 (0.0011) -[2023-11-28 09:46:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186572800. Throughput: 0: 2676.3, 1: 2717.5. Samples: 186591564. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:13,446][86177] Avg episode reward: [(0, '-584.140'), (1, '-521.930')] -[2023-11-28 09:46:13,486][87426] Updated weights for policy 1, policy_version 364240 (0.0012) -[2023-11-28 09:46:13,791][87424] Updated weights for policy 0, policy_version 364579 (0.0011) -[2023-11-28 09:46:13,867][87426] Updated weights for policy 1, policy_version 364250 (0.0011) -[2023-11-28 09:46:14,179][87424] Updated weights for policy 0, policy_version 364589 (0.0012) -[2023-11-28 09:46:14,551][87424] Updated weights for policy 0, policy_version 364599 (0.0012) -[2023-11-28 09:46:16,199][87426] Updated weights for policy 1, policy_version 364260 (0.0009) -[2023-11-28 09:46:16,578][87426] Updated weights for policy 1, policy_version 364270 (0.0008) -[2023-11-28 09:46:16,718][87424] Updated weights for policy 0, policy_version 364609 (0.0012) -[2023-11-28 09:46:16,962][87426] Updated weights for policy 1, policy_version 364280 (0.0007) -[2023-11-28 09:46:17,103][87424] Updated weights for policy 0, policy_version 364619 (0.0012) -[2023-11-28 09:46:17,479][87424] Updated weights for policy 0, policy_version 364629 (0.0012) -[2023-11-28 09:46:17,860][87424] Updated weights for policy 0, policy_version 364639 (0.0012) -[2023-11-28 09:46:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 186605568. Throughput: 0: 2691.9, 1: 2722.2. Samples: 186616108. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:18,445][86177] Avg episode reward: [(0, '-587.690'), (1, '-529.100')] -[2023-11-28 09:46:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000364640_93347840.pth... -[2023-11-28 09:46:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000364288_93257728.pth... -[2023-11-28 09:46:18,485][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000362144_92708864.pth -[2023-11-28 09:46:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000361760_92610560.pth -[2023-11-28 09:46:18,828][87426] Updated weights for policy 1, policy_version 364290 (0.0007) -[2023-11-28 09:46:19,209][87426] Updated weights for policy 1, policy_version 364300 (0.0011) -[2023-11-28 09:46:19,590][87426] Updated weights for policy 1, policy_version 364310 (0.0011) -[2023-11-28 09:46:19,959][87426] Updated weights for policy 1, policy_version 364320 (0.0010) -[2023-11-28 09:46:20,207][87424] Updated weights for policy 0, policy_version 364649 (0.0010) -[2023-11-28 09:46:20,575][87424] Updated weights for policy 0, policy_version 364659 (0.0011) -[2023-11-28 09:46:20,961][87424] Updated weights for policy 0, policy_version 364669 (0.0012) -[2023-11-28 09:46:22,540][87426] Updated weights for policy 1, policy_version 364330 (0.0012) -[2023-11-28 09:46:22,928][87426] Updated weights for policy 1, policy_version 364340 (0.0012) -[2023-11-28 09:46:23,307][87426] Updated weights for policy 1, policy_version 364350 (0.0011) -[2023-11-28 09:46:23,340][87424] Updated weights for policy 0, policy_version 364679 (0.0011) -[2023-11-28 09:46:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 186630144. Throughput: 0: 2668.1, 1: 2707.2. Samples: 186647268. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:23,445][86177] Avg episode reward: [(0, '-581.830'), (1, '-520.060')] -[2023-11-28 09:46:23,722][87424] Updated weights for policy 0, policy_version 364689 (0.0012) -[2023-11-28 09:46:24,098][87424] Updated weights for policy 0, policy_version 364699 (0.0011) -[2023-11-28 09:46:25,556][87426] Updated weights for policy 1, policy_version 364360 (0.0008) -[2023-11-28 09:46:25,942][87426] Updated weights for policy 1, policy_version 364370 (0.0007) -[2023-11-28 09:46:26,326][87426] Updated weights for policy 1, policy_version 364380 (0.0007) -[2023-11-28 09:46:26,486][87424] Updated weights for policy 0, policy_version 364709 (0.0009) -[2023-11-28 09:46:26,871][87424] Updated weights for policy 0, policy_version 364719 (0.0012) -[2023-11-28 09:46:27,249][87424] Updated weights for policy 0, policy_version 364729 (0.0012) -[2023-11-28 09:46:28,305][87426] Updated weights for policy 1, policy_version 364390 (0.0008) -[2023-11-28 09:46:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186654720. Throughput: 0: 2653.4, 1: 2730.5. Samples: 186671548. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:28,445][86177] Avg episode reward: [(0, '-594.300'), (1, '-511.380')] -[2023-11-28 09:46:28,683][87426] Updated weights for policy 1, policy_version 364400 (0.0010) -[2023-11-28 09:46:29,061][87426] Updated weights for policy 1, policy_version 364410 (0.0010) -[2023-11-28 09:46:29,357][87424] Updated weights for policy 0, policy_version 364739 (0.0011) -[2023-11-28 09:46:29,742][87424] Updated weights for policy 0, policy_version 364749 (0.0008) -[2023-11-28 09:46:30,122][87424] Updated weights for policy 0, policy_version 364759 (0.0009) -[2023-11-28 09:46:31,125][87426] Updated weights for policy 1, policy_version 364420 (0.0011) -[2023-11-28 09:46:31,509][87426] Updated weights for policy 1, policy_version 364430 (0.0010) -[2023-11-28 09:46:31,901][87426] Updated weights for policy 1, policy_version 364440 (0.0011) -[2023-11-28 09:46:32,503][87424] Updated weights for policy 0, policy_version 364769 (0.0010) -[2023-11-28 09:46:32,886][87424] Updated weights for policy 0, policy_version 364779 (0.0008) -[2023-11-28 09:46:33,267][87424] Updated weights for policy 0, policy_version 364789 (0.0012) -[2023-11-28 09:46:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 186679296. Throughput: 0: 2649.3, 1: 2730.5. Samples: 186695064. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:33,445][86177] Avg episode reward: [(0, '-610.830'), (1, '-512.680')] -[2023-11-28 09:46:33,643][87424] Updated weights for policy 0, policy_version 364799 (0.0012) -[2023-11-28 09:46:33,700][87426] Updated weights for policy 1, policy_version 364450 (0.0008) -[2023-11-28 09:46:34,067][87426] Updated weights for policy 1, policy_version 364460 (0.0007) -[2023-11-28 09:46:34,439][87426] Updated weights for policy 1, policy_version 364470 (0.0007) -[2023-11-28 09:46:34,819][87426] Updated weights for policy 1, policy_version 364480 (0.0010) -[2023-11-28 09:46:35,616][87424] Updated weights for policy 0, policy_version 364809 (0.0012) -[2023-11-28 09:46:36,000][87424] Updated weights for policy 0, policy_version 364819 (0.0012) -[2023-11-28 09:46:36,372][87424] Updated weights for policy 0, policy_version 364829 (0.0012) -[2023-11-28 09:46:36,768][87426] Updated weights for policy 1, policy_version 364490 (0.0012) -[2023-11-28 09:46:37,133][87426] Updated weights for policy 1, policy_version 364500 (0.0012) -[2023-11-28 09:46:37,520][87426] Updated weights for policy 1, policy_version 364510 (0.0012) -[2023-11-28 09:46:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 186712064. Throughput: 0: 2692.7, 1: 2725.1. Samples: 186728064. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:38,445][86177] Avg episode reward: [(0, '-620.960'), (1, '-511.840')] -[2023-11-28 09:46:38,669][87424] Updated weights for policy 0, policy_version 364839 (0.0011) -[2023-11-28 09:46:39,053][87424] Updated weights for policy 0, policy_version 364849 (0.0012) -[2023-11-28 09:46:39,425][87424] Updated weights for policy 0, policy_version 364859 (0.0010) -[2023-11-28 09:46:39,960][87426] Updated weights for policy 1, policy_version 364520 (0.0010) -[2023-11-28 09:46:40,339][87426] Updated weights for policy 1, policy_version 364530 (0.0008) -[2023-11-28 09:46:40,718][87426] Updated weights for policy 1, policy_version 364540 (0.0012) -[2023-11-28 09:46:41,721][87424] Updated weights for policy 0, policy_version 364869 (0.0010) -[2023-11-28 09:46:42,099][87424] Updated weights for policy 0, policy_version 364879 (0.0012) -[2023-11-28 09:46:42,484][87424] Updated weights for policy 0, policy_version 364889 (0.0012) -[2023-11-28 09:46:43,250][87426] Updated weights for policy 1, policy_version 364550 (0.0012) -[2023-11-28 09:46:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 186736640. Throughput: 0: 2682.8, 1: 2720.2. Samples: 186752684. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:43,445][86177] Avg episode reward: [(0, '-609.350'), (1, '-513.260')] -[2023-11-28 09:46:43,632][87426] Updated weights for policy 1, policy_version 364560 (0.0011) -[2023-11-28 09:46:44,009][87426] Updated weights for policy 1, policy_version 364570 (0.0012) -[2023-11-28 09:46:44,627][87424] Updated weights for policy 0, policy_version 364899 (0.0012) -[2023-11-28 09:46:45,014][87424] Updated weights for policy 0, policy_version 364909 (0.0012) -[2023-11-28 09:46:45,386][87424] Updated weights for policy 0, policy_version 364919 (0.0012) -[2023-11-28 09:46:45,920][87426] Updated weights for policy 1, policy_version 364580 (0.0012) -[2023-11-28 09:46:46,307][87426] Updated weights for policy 1, policy_version 364590 (0.0012) -[2023-11-28 09:46:46,679][87426] Updated weights for policy 1, policy_version 364600 (0.0012) -[2023-11-28 09:46:47,561][87424] Updated weights for policy 0, policy_version 364929 (0.0012) -[2023-11-28 09:46:47,941][87424] Updated weights for policy 0, policy_version 364939 (0.0012) -[2023-11-28 09:46:48,325][87424] Updated weights for policy 0, policy_version 364949 (0.0012) -[2023-11-28 09:46:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 186761216. Throughput: 0: 2653.1, 1: 2716.1. Samples: 186776932. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:48,445][86177] Avg episode reward: [(0, '-601.490'), (1, '-521.800')] -[2023-11-28 09:46:48,568][87426] Updated weights for policy 1, policy_version 364610 (0.0011) -[2023-11-28 09:46:48,702][87424] Updated weights for policy 0, policy_version 364959 (0.0012) -[2023-11-28 09:46:48,949][87426] Updated weights for policy 1, policy_version 364620 (0.0012) -[2023-11-28 09:46:49,331][87426] Updated weights for policy 1, policy_version 364630 (0.0007) -[2023-11-28 09:46:49,705][87426] Updated weights for policy 1, policy_version 364640 (0.0012) -[2023-11-28 09:46:51,149][87424] Updated weights for policy 0, policy_version 364969 (0.0013) -[2023-11-28 09:46:51,524][87424] Updated weights for policy 0, policy_version 364979 (0.0011) -[2023-11-28 09:46:51,766][87426] Updated weights for policy 1, policy_version 364650 (0.0010) -[2023-11-28 09:46:51,904][87424] Updated weights for policy 0, policy_version 364989 (0.0012) -[2023-11-28 09:46:52,146][87426] Updated weights for policy 1, policy_version 364660 (0.0010) -[2023-11-28 09:46:52,526][87426] Updated weights for policy 1, policy_version 364670 (0.0008) -[2023-11-28 09:46:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 186793984. Throughput: 0: 2630.4, 1: 2729.5. Samples: 186809012. Policy #0 lag: (min: 19.0, avg: 37.3, max: 52.0) -[2023-11-28 09:46:53,445][86177] Avg episode reward: [(0, '-603.980'), (1, '-522.000')] -[2023-11-28 09:46:54,070][87424] Updated weights for policy 0, policy_version 364999 (0.0012) -[2023-11-28 09:46:54,449][87424] Updated weights for policy 0, policy_version 365009 (0.0012) -[2023-11-28 09:46:54,671][87426] Updated weights for policy 1, policy_version 364680 (0.0008) -[2023-11-28 09:46:54,827][87424] Updated weights for policy 0, policy_version 365019 (0.0007) -[2023-11-28 09:46:55,049][87426] Updated weights for policy 1, policy_version 364690 (0.0008) -[2023-11-28 09:46:55,433][87426] Updated weights for policy 1, policy_version 364700 (0.0007) -[2023-11-28 09:46:57,265][87424] Updated weights for policy 0, policy_version 365029 (0.0009) -[2023-11-28 09:46:57,544][87426] Updated weights for policy 1, policy_version 364710 (0.0010) -[2023-11-28 09:46:57,647][87424] Updated weights for policy 0, policy_version 365039 (0.0012) -[2023-11-28 09:46:57,921][87426] Updated weights for policy 1, policy_version 364720 (0.0012) -[2023-11-28 09:46:58,032][87424] Updated weights for policy 0, policy_version 365049 (0.0012) -[2023-11-28 09:46:58,291][87426] Updated weights for policy 1, policy_version 364730 (0.0012) -[2023-11-28 09:46:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 186818560. Throughput: 0: 2619.4, 1: 2747.3. Samples: 186833064. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:46:58,445][86177] Avg episode reward: [(0, '-584.510'), (1, '-519.720')] -[2023-11-28 09:46:59,886][87424] Updated weights for policy 0, policy_version 365059 (0.0012) -[2023-11-28 09:47:00,269][87424] Updated weights for policy 0, policy_version 365069 (0.0012) -[2023-11-28 09:47:00,336][87426] Updated weights for policy 1, policy_version 364740 (0.0012) -[2023-11-28 09:47:00,653][87424] Updated weights for policy 0, policy_version 365079 (0.0011) -[2023-11-28 09:47:00,741][87426] Updated weights for policy 1, policy_version 364750 (0.0009) -[2023-11-28 09:47:01,112][87426] Updated weights for policy 1, policy_version 364760 (0.0008) -[2023-11-28 09:47:03,168][87424] Updated weights for policy 0, policy_version 365089 (0.0008) -[2023-11-28 09:47:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186843136. Throughput: 0: 2624.9, 1: 2739.8. Samples: 186857520. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:03,445][86177] Avg episode reward: [(0, '-575.790'), (1, '-518.490')] -[2023-11-28 09:47:03,456][87426] Updated weights for policy 1, policy_version 364770 (0.0008) -[2023-11-28 09:47:03,549][87424] Updated weights for policy 0, policy_version 365099 (0.0008) -[2023-11-28 09:47:03,844][87426] Updated weights for policy 1, policy_version 364780 (0.0007) -[2023-11-28 09:47:03,935][87424] Updated weights for policy 0, policy_version 365109 (0.0009) -[2023-11-28 09:47:04,225][87426] Updated weights for policy 1, policy_version 364790 (0.0007) -[2023-11-28 09:47:04,325][87424] Updated weights for policy 0, policy_version 365119 (0.0007) -[2023-11-28 09:47:04,606][87426] Updated weights for policy 1, policy_version 364800 (0.0009) -[2023-11-28 09:47:06,695][87424] Updated weights for policy 0, policy_version 365129 (0.0037) -[2023-11-28 09:47:07,052][87426] Updated weights for policy 1, policy_version 364810 (0.0011) -[2023-11-28 09:47:07,079][87424] Updated weights for policy 0, policy_version 365139 (0.0011) -[2023-11-28 09:47:07,436][87426] Updated weights for policy 1, policy_version 364820 (0.0011) -[2023-11-28 09:47:07,461][87424] Updated weights for policy 0, policy_version 365149 (0.0011) -[2023-11-28 09:47:07,814][87426] Updated weights for policy 1, policy_version 364830 (0.0012) -[2023-11-28 09:47:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 186875904. Throughput: 0: 2617.9, 1: 2730.7. Samples: 186887952. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:08,445][86177] Avg episode reward: [(0, '-564.810'), (1, '-509.460')] -[2023-11-28 09:47:09,258][87424] Updated weights for policy 0, policy_version 365159 (0.0011) -[2023-11-28 09:47:09,641][87424] Updated weights for policy 0, policy_version 365169 (0.0011) -[2023-11-28 09:47:10,022][87424] Updated weights for policy 0, policy_version 365179 (0.0011) -[2023-11-28 09:47:10,091][87426] Updated weights for policy 1, policy_version 364840 (0.0010) -[2023-11-28 09:47:10,474][87426] Updated weights for policy 1, policy_version 364850 (0.0011) -[2023-11-28 09:47:10,845][87426] Updated weights for policy 1, policy_version 364860 (0.0010) -[2023-11-28 09:47:12,249][87424] Updated weights for policy 0, policy_version 365189 (0.0017) -[2023-11-28 09:47:12,631][87424] Updated weights for policy 0, policy_version 365199 (0.0009) -[2023-11-28 09:47:13,012][87426] Updated weights for policy 1, policy_version 364870 (0.0010) -[2023-11-28 09:47:13,015][87424] Updated weights for policy 0, policy_version 365209 (0.0010) -[2023-11-28 09:47:13,391][87426] Updated weights for policy 1, policy_version 364880 (0.0011) -[2023-11-28 09:47:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 186900480. Throughput: 0: 2652.4, 1: 2709.5. Samples: 186912836. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:13,445][86177] Avg episode reward: [(0, '-549.280'), (1, '-506.810')] -[2023-11-28 09:47:13,766][87426] Updated weights for policy 1, policy_version 364890 (0.0010) -[2023-11-28 09:47:14,971][87424] Updated weights for policy 0, policy_version 365219 (0.0010) -[2023-11-28 09:47:15,346][87424] Updated weights for policy 0, policy_version 365229 (0.0010) -[2023-11-28 09:47:15,735][87424] Updated weights for policy 0, policy_version 365239 (0.0011) -[2023-11-28 09:47:16,290][87426] Updated weights for policy 1, policy_version 364900 (0.0009) -[2023-11-28 09:47:16,672][87426] Updated weights for policy 1, policy_version 364910 (0.0012) -[2023-11-28 09:47:17,056][87426] Updated weights for policy 1, policy_version 364920 (0.0012) -[2023-11-28 09:47:17,558][87424] Updated weights for policy 0, policy_version 365249 (0.0012) -[2023-11-28 09:47:17,938][87424] Updated weights for policy 0, policy_version 365259 (0.0012) -[2023-11-28 09:47:18,323][87424] Updated weights for policy 0, policy_version 365269 (0.0011) -[2023-11-28 09:47:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 186925056. Throughput: 0: 2693.2, 1: 2701.5. Samples: 186937828. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:18,446][86177] Avg episode reward: [(0, '-595.340'), (1, '-516.710')] -[2023-11-28 09:47:18,709][87424] Updated weights for policy 0, policy_version 365279 (0.0012) -[2023-11-28 09:47:19,265][87426] Updated weights for policy 1, policy_version 364930 (0.0011) -[2023-11-28 09:47:19,646][87426] Updated weights for policy 1, policy_version 364940 (0.0009) -[2023-11-28 09:47:20,021][87426] Updated weights for policy 1, policy_version 364950 (0.0011) -[2023-11-28 09:47:20,409][87426] Updated weights for policy 1, policy_version 364960 (0.0011) -[2023-11-28 09:47:20,936][87424] Updated weights for policy 0, policy_version 365289 (0.0011) -[2023-11-28 09:47:21,313][87424] Updated weights for policy 0, policy_version 365299 (0.0011) -[2023-11-28 09:47:21,689][87424] Updated weights for policy 0, policy_version 365309 (0.0011) -[2023-11-28 09:47:22,963][87426] Updated weights for policy 1, policy_version 364970 (0.0011) -[2023-11-28 09:47:23,340][87426] Updated weights for policy 1, policy_version 364980 (0.0008) -[2023-11-28 09:47:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 186949632. Throughput: 0: 2690.6, 1: 2692.4. Samples: 186970300. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:23,445][86177] Avg episode reward: [(0, '-595.420'), (1, '-519.290')] -[2023-11-28 09:47:23,718][87426] Updated weights for policy 1, policy_version 364990 (0.0008) -[2023-11-28 09:47:24,000][87424] Updated weights for policy 0, policy_version 365319 (0.0011) -[2023-11-28 09:47:24,367][87424] Updated weights for policy 0, policy_version 365329 (0.0012) -[2023-11-28 09:47:24,751][87424] Updated weights for policy 0, policy_version 365339 (0.0011) -[2023-11-28 09:47:25,573][87426] Updated weights for policy 1, policy_version 365000 (0.0010) -[2023-11-28 09:47:25,964][87426] Updated weights for policy 1, policy_version 365010 (0.0007) -[2023-11-28 09:47:26,335][87426] Updated weights for policy 1, policy_version 365020 (0.0007) -[2023-11-28 09:47:26,735][87424] Updated weights for policy 0, policy_version 365349 (0.0010) -[2023-11-28 09:47:27,118][87424] Updated weights for policy 0, policy_version 365359 (0.0012) -[2023-11-28 09:47:27,506][87424] Updated weights for policy 0, policy_version 365369 (0.0012) -[2023-11-28 09:47:28,166][87426] Updated weights for policy 1, policy_version 365030 (0.0011) -[2023-11-28 09:47:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 186982400. Throughput: 0: 2695.3, 1: 2710.0. Samples: 186995920. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:28,445][86177] Avg episode reward: [(0, '-619.000'), (1, '-521.360')] -[2023-11-28 09:47:28,537][87426] Updated weights for policy 1, policy_version 365040 (0.0007) -[2023-11-28 09:47:28,919][87426] Updated weights for policy 1, policy_version 365050 (0.0008) -[2023-11-28 09:47:29,659][87424] Updated weights for policy 0, policy_version 365379 (0.0010) -[2023-11-28 09:47:30,043][87424] Updated weights for policy 0, policy_version 365389 (0.0008) -[2023-11-28 09:47:30,421][87424] Updated weights for policy 0, policy_version 365399 (0.0008) -[2023-11-28 09:47:31,276][87426] Updated weights for policy 1, policy_version 365060 (0.0009) -[2023-11-28 09:47:31,657][87426] Updated weights for policy 1, policy_version 365070 (0.0012) -[2023-11-28 09:47:32,037][87426] Updated weights for policy 1, policy_version 365080 (0.0012) -[2023-11-28 09:47:32,558][87424] Updated weights for policy 0, policy_version 365409 (0.0009) -[2023-11-28 09:47:32,947][87424] Updated weights for policy 0, policy_version 365419 (0.0012) -[2023-11-28 09:47:33,314][87424] Updated weights for policy 0, policy_version 365429 (0.0008) -[2023-11-28 09:47:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 187006976. Throughput: 0: 2728.0, 1: 2703.6. Samples: 187021352. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:33,445][86177] Avg episode reward: [(0, '-625.430'), (1, '-514.650')] -[2023-11-28 09:47:33,702][87424] Updated weights for policy 0, policy_version 365439 (0.0007) -[2023-11-28 09:47:34,483][87426] Updated weights for policy 1, policy_version 365090 (0.0012) -[2023-11-28 09:47:34,869][87426] Updated weights for policy 1, policy_version 365100 (0.0011) -[2023-11-28 09:47:35,247][87426] Updated weights for policy 1, policy_version 365110 (0.0008) -[2023-11-28 09:47:35,626][87426] Updated weights for policy 1, policy_version 365120 (0.0007) -[2023-11-28 09:47:35,879][87424] Updated weights for policy 0, policy_version 365449 (0.0008) -[2023-11-28 09:47:36,255][87424] Updated weights for policy 0, policy_version 365459 (0.0007) -[2023-11-28 09:47:36,641][87424] Updated weights for policy 0, policy_version 365469 (0.0008) -[2023-11-28 09:47:37,814][87426] Updated weights for policy 1, policy_version 365130 (0.0011) -[2023-11-28 09:47:38,188][87426] Updated weights for policy 1, policy_version 365140 (0.0012) -[2023-11-28 09:47:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187031552. Throughput: 0: 2731.3, 1: 2680.8. Samples: 187052556. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:38,445][86177] Avg episode reward: [(0, '-627.770'), (1, '-510.320')] -[2023-11-28 09:47:38,572][87426] Updated weights for policy 1, policy_version 365150 (0.0012) -[2023-11-28 09:47:38,582][87424] Updated weights for policy 0, policy_version 365479 (0.0009) -[2023-11-28 09:47:38,984][87424] Updated weights for policy 0, policy_version 365489 (0.0009) -[2023-11-28 09:47:39,354][87424] Updated weights for policy 0, policy_version 365499 (0.0012) -[2023-11-28 09:47:40,918][87426] Updated weights for policy 1, policy_version 365160 (0.0011) -[2023-11-28 09:47:41,301][87426] Updated weights for policy 1, policy_version 365170 (0.0012) -[2023-11-28 09:47:41,683][87426] Updated weights for policy 1, policy_version 365180 (0.0011) -[2023-11-28 09:47:41,744][87424] Updated weights for policy 0, policy_version 365509 (0.0011) -[2023-11-28 09:47:42,131][87424] Updated weights for policy 0, policy_version 365519 (0.0009) -[2023-11-28 09:47:42,511][87424] Updated weights for policy 0, policy_version 365529 (0.0012) -[2023-11-28 09:47:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 187064320. Throughput: 0: 2745.6, 1: 2661.2. Samples: 187076372. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:43,445][86177] Avg episode reward: [(0, '-620.410'), (1, '-510.530')] -[2023-11-28 09:47:43,931][87426] Updated weights for policy 1, policy_version 365190 (0.0011) -[2023-11-28 09:47:44,309][87426] Updated weights for policy 1, policy_version 365200 (0.0012) -[2023-11-28 09:47:44,683][87424] Updated weights for policy 0, policy_version 365539 (0.0012) -[2023-11-28 09:47:44,686][87426] Updated weights for policy 1, policy_version 365210 (0.0008) -[2023-11-28 09:47:45,058][87424] Updated weights for policy 0, policy_version 365549 (0.0009) -[2023-11-28 09:47:45,439][87424] Updated weights for policy 0, policy_version 365559 (0.0014) -[2023-11-28 09:47:47,006][87426] Updated weights for policy 1, policy_version 365220 (0.0009) -[2023-11-28 09:47:47,217][87424] Updated weights for policy 0, policy_version 365569 (0.0012) -[2023-11-28 09:47:47,380][87426] Updated weights for policy 1, policy_version 365230 (0.0011) -[2023-11-28 09:47:47,600][87424] Updated weights for policy 0, policy_version 365579 (0.0011) -[2023-11-28 09:47:47,763][87426] Updated weights for policy 1, policy_version 365240 (0.0011) -[2023-11-28 09:47:47,987][87424] Updated weights for policy 0, policy_version 365589 (0.0012) -[2023-11-28 09:47:48,361][87424] Updated weights for policy 0, policy_version 365599 (0.0012) -[2023-11-28 09:47:48,445][86177] Fps is (10 sec: 6553.5, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 187097088. Throughput: 0: 2771.5, 1: 2647.9. Samples: 187101392. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:48,446][86177] Avg episode reward: [(0, '-631.370'), (1, '-508.400')] -[2023-11-28 09:47:49,807][87426] Updated weights for policy 1, policy_version 365250 (0.0011) -[2023-11-28 09:47:50,189][87426] Updated weights for policy 1, policy_version 365260 (0.0011) -[2023-11-28 09:47:50,562][87426] Updated weights for policy 1, policy_version 365270 (0.0011) -[2023-11-28 09:47:50,590][87424] Updated weights for policy 0, policy_version 365609 (0.0012) -[2023-11-28 09:47:50,950][87426] Updated weights for policy 1, policy_version 365280 (0.0012) -[2023-11-28 09:47:50,963][87424] Updated weights for policy 0, policy_version 365619 (0.0012) -[2023-11-28 09:47:51,345][87424] Updated weights for policy 0, policy_version 365629 (0.0012) -[2023-11-28 09:47:53,196][87426] Updated weights for policy 1, policy_version 365290 (0.0012) -[2023-11-28 09:47:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187113472. Throughput: 0: 2793.9, 1: 2660.3. Samples: 187133388. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:53,446][86177] Avg episode reward: [(0, '-620.650'), (1, '-512.670')] -[2023-11-28 09:47:53,573][87426] Updated weights for policy 1, policy_version 365300 (0.0011) -[2023-11-28 09:47:53,846][87424] Updated weights for policy 0, policy_version 365639 (0.0012) -[2023-11-28 09:47:53,962][87426] Updated weights for policy 1, policy_version 365310 (0.0010) -[2023-11-28 09:47:54,234][87424] Updated weights for policy 0, policy_version 365649 (0.0012) -[2023-11-28 09:47:54,608][87424] Updated weights for policy 0, policy_version 365659 (0.0011) -[2023-11-28 09:47:56,521][87426] Updated weights for policy 1, policy_version 365320 (0.0011) -[2023-11-28 09:47:56,721][87424] Updated weights for policy 0, policy_version 365669 (0.0011) -[2023-11-28 09:47:56,918][87426] Updated weights for policy 1, policy_version 365330 (0.0012) -[2023-11-28 09:47:57,107][87424] Updated weights for policy 0, policy_version 365679 (0.0008) -[2023-11-28 09:47:57,289][87426] Updated weights for policy 1, policy_version 365340 (0.0012) -[2023-11-28 09:47:57,493][87424] Updated weights for policy 0, policy_version 365689 (0.0007) -[2023-11-28 09:47:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 187146240. Throughput: 0: 2780.5, 1: 2637.0. Samples: 187156624. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:47:58,445][86177] Avg episode reward: [(0, '-591.960'), (1, '-513.510')] -[2023-11-28 09:47:59,497][87424] Updated weights for policy 0, policy_version 365699 (0.0009) -[2023-11-28 09:47:59,639][87426] Updated weights for policy 1, policy_version 365350 (0.0012) -[2023-11-28 09:47:59,876][87424] Updated weights for policy 0, policy_version 365709 (0.0010) -[2023-11-28 09:48:00,021][87426] Updated weights for policy 1, policy_version 365360 (0.0010) -[2023-11-28 09:48:00,255][87424] Updated weights for policy 0, policy_version 365719 (0.0008) -[2023-11-28 09:48:00,396][87426] Updated weights for policy 1, policy_version 365370 (0.0011) -[2023-11-28 09:48:02,103][87424] Updated weights for policy 0, policy_version 365729 (0.0010) -[2023-11-28 09:48:02,489][87424] Updated weights for policy 0, policy_version 365739 (0.0011) -[2023-11-28 09:48:02,873][87424] Updated weights for policy 0, policy_version 365749 (0.0012) -[2023-11-28 09:48:02,876][87426] Updated weights for policy 1, policy_version 365380 (0.0011) -[2023-11-28 09:48:03,249][87424] Updated weights for policy 0, policy_version 365759 (0.0013) -[2023-11-28 09:48:03,253][87426] Updated weights for policy 1, policy_version 365390 (0.0009) -[2023-11-28 09:48:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 187170816. Throughput: 0: 2801.8, 1: 2644.5. Samples: 187182912. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:48:03,445][86177] Avg episode reward: [(0, '-583.480'), (1, '-515.950')] -[2023-11-28 09:48:03,631][87426] Updated weights for policy 1, policy_version 365400 (0.0008) -[2023-11-28 09:48:05,034][87424] Updated weights for policy 0, policy_version 365769 (0.0008) -[2023-11-28 09:48:05,426][87424] Updated weights for policy 0, policy_version 365779 (0.0010) -[2023-11-28 09:48:05,807][87424] Updated weights for policy 0, policy_version 365789 (0.0010) -[2023-11-28 09:48:05,838][87426] Updated weights for policy 1, policy_version 365410 (0.0011) -[2023-11-28 09:48:06,226][87426] Updated weights for policy 1, policy_version 365420 (0.0011) -[2023-11-28 09:48:06,595][87426] Updated weights for policy 1, policy_version 365430 (0.0009) -[2023-11-28 09:48:06,972][87426] Updated weights for policy 1, policy_version 365440 (0.0009) -[2023-11-28 09:48:07,593][87424] Updated weights for policy 0, policy_version 365799 (0.0011) -[2023-11-28 09:48:07,965][87424] Updated weights for policy 0, policy_version 365809 (0.0007) -[2023-11-28 09:48:08,355][87424] Updated weights for policy 0, policy_version 365819 (0.0007) -[2023-11-28 09:48:08,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187195392. Throughput: 0: 2825.3, 1: 2636.1. Samples: 187216064. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:48:08,446][86177] Avg episode reward: [(0, '-565.400'), (1, '-518.800')] -[2023-11-28 09:48:09,114][87426] Updated weights for policy 1, policy_version 365450 (0.0011) -[2023-11-28 09:48:09,488][87426] Updated weights for policy 1, policy_version 365460 (0.0012) -[2023-11-28 09:48:09,882][87426] Updated weights for policy 1, policy_version 365470 (0.0011) -[2023-11-28 09:48:10,540][87424] Updated weights for policy 0, policy_version 365829 (0.0010) -[2023-11-28 09:48:10,923][87424] Updated weights for policy 0, policy_version 365839 (0.0009) -[2023-11-28 09:48:11,305][87424] Updated weights for policy 0, policy_version 365849 (0.0007) -[2023-11-28 09:48:12,216][87426] Updated weights for policy 1, policy_version 365480 (0.0011) -[2023-11-28 09:48:12,591][87426] Updated weights for policy 1, policy_version 365490 (0.0012) -[2023-11-28 09:48:12,966][87426] Updated weights for policy 1, policy_version 365500 (0.0011) -[2023-11-28 09:48:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 187228160. Throughput: 0: 2813.6, 1: 2606.8. Samples: 187239836. Policy #0 lag: (min: 36.0, avg: 45.2, max: 71.0) -[2023-11-28 09:48:13,445][86177] Avg episode reward: [(0, '-574.650'), (1, '-516.000')] -[2023-11-28 09:48:13,569][87424] Updated weights for policy 0, policy_version 365859 (0.0011) -[2023-11-28 09:48:13,945][87424] Updated weights for policy 0, policy_version 365869 (0.0009) -[2023-11-28 09:48:14,317][87424] Updated weights for policy 0, policy_version 365879 (0.0007) -[2023-11-28 09:48:15,637][87426] Updated weights for policy 1, policy_version 365510 (0.0011) -[2023-11-28 09:48:16,017][87426] Updated weights for policy 1, policy_version 365520 (0.0011) -[2023-11-28 09:48:16,393][87426] Updated weights for policy 1, policy_version 365530 (0.0010) -[2023-11-28 09:48:16,643][87424] Updated weights for policy 0, policy_version 365889 (0.0009) -[2023-11-28 09:48:17,018][87424] Updated weights for policy 0, policy_version 365899 (0.0012) -[2023-11-28 09:48:17,397][87424] Updated weights for policy 0, policy_version 365909 (0.0009) -[2023-11-28 09:48:17,773][87424] Updated weights for policy 0, policy_version 365919 (0.0007) -[2023-11-28 09:48:18,291][87426] Updated weights for policy 1, policy_version 365540 (0.0011) -[2023-11-28 09:48:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 187252736. Throughput: 0: 2784.1, 1: 2594.5. Samples: 187263392. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:48:18,446][86177] Avg episode reward: [(0, '-578.510'), (1, '-516.010')] -[2023-11-28 09:48:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000365920_93675520.pth... -[2023-11-28 09:48:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000363392_93028352.pth -[2023-11-28 09:48:18,658][87426] Updated weights for policy 1, policy_version 365550 (0.0009) -[2023-11-28 09:48:19,034][87426] Updated weights for policy 1, policy_version 365560 (0.0008) -[2023-11-28 09:48:19,334][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000365568_93585408.pth... -[2023-11-28 09:48:19,365][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000363040_92938240.pth -[2023-11-28 09:48:19,719][87424] Updated weights for policy 0, policy_version 365929 (0.0010) -[2023-11-28 09:48:20,099][87424] Updated weights for policy 0, policy_version 365939 (0.0012) -[2023-11-28 09:48:20,472][87424] Updated weights for policy 0, policy_version 365949 (0.0012) -[2023-11-28 09:48:21,261][87426] Updated weights for policy 1, policy_version 365570 (0.0012) -[2023-11-28 09:48:21,643][87426] Updated weights for policy 1, policy_version 365580 (0.0008) -[2023-11-28 09:48:22,012][87426] Updated weights for policy 1, policy_version 365590 (0.0010) -[2023-11-28 09:48:22,385][87426] Updated weights for policy 1, policy_version 365600 (0.0009) -[2023-11-28 09:48:23,084][87424] Updated weights for policy 0, policy_version 365959 (0.0010) -[2023-11-28 09:48:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 187277312. Throughput: 0: 2776.3, 1: 2614.3. Samples: 187295132. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:48:23,445][86177] Avg episode reward: [(0, '-599.340'), (1, '-512.860')] -[2023-11-28 09:48:23,465][87424] Updated weights for policy 0, policy_version 365969 (0.0009) -[2023-11-28 09:48:23,853][87424] Updated weights for policy 0, policy_version 365979 (0.0008) -[2023-11-28 09:48:24,866][87426] Updated weights for policy 1, policy_version 365610 (0.0009) -[2023-11-28 09:48:25,239][87426] Updated weights for policy 1, policy_version 365620 (0.0011) -[2023-11-28 09:48:25,619][87426] Updated weights for policy 1, policy_version 365630 (0.0010) -[2023-11-28 09:48:25,984][87424] Updated weights for policy 0, policy_version 365989 (0.0007) -[2023-11-28 09:48:26,369][87424] Updated weights for policy 0, policy_version 365999 (0.0007) -[2023-11-28 09:48:26,753][87424] Updated weights for policy 0, policy_version 366009 (0.0007) -[2023-11-28 09:48:27,557][87426] Updated weights for policy 1, policy_version 365640 (0.0008) -[2023-11-28 09:48:27,941][87426] Updated weights for policy 1, policy_version 365650 (0.0010) -[2023-11-28 09:48:28,327][87426] Updated weights for policy 1, policy_version 365660 (0.0008) -[2023-11-28 09:48:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187301888. Throughput: 0: 2788.9, 1: 2617.5. Samples: 187319660. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:48:28,445][86177] Avg episode reward: [(0, '-599.310'), (1, '-519.980')] -[2023-11-28 09:48:29,185][87424] Updated weights for policy 0, policy_version 366019 (0.0008) -[2023-11-28 09:48:29,570][87424] Updated weights for policy 0, policy_version 366029 (0.0012) -[2023-11-28 09:48:29,949][87424] Updated weights for policy 0, policy_version 366039 (0.0012) -[2023-11-28 09:48:30,336][87426] Updated weights for policy 1, policy_version 365670 (0.0009) -[2023-11-28 09:48:30,709][87426] Updated weights for policy 1, policy_version 365680 (0.0011) -[2023-11-28 09:48:31,090][87426] Updated weights for policy 1, policy_version 365690 (0.0007) -[2023-11-28 09:48:32,232][87424] Updated weights for policy 0, policy_version 366049 (0.0010) -[2023-11-28 09:48:32,613][87424] Updated weights for policy 0, policy_version 366059 (0.0010) -[2023-11-28 09:48:33,000][87424] Updated weights for policy 0, policy_version 366069 (0.0010) -[2023-11-28 09:48:33,380][87424] Updated weights for policy 0, policy_version 366079 (0.0012) -[2023-11-28 09:48:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 187334656. Throughput: 0: 2763.5, 1: 2635.4. Samples: 187344340. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:48:33,445][86177] Avg episode reward: [(0, '-592.220'), (1, '-519.390')] -[2023-11-28 09:48:33,728][87426] Updated weights for policy 1, policy_version 365700 (0.0009) -[2023-11-28 09:48:34,105][87426] Updated weights for policy 1, policy_version 365710 (0.0012) -[2023-11-28 09:48:34,484][87426] Updated weights for policy 1, policy_version 365720 (0.0012) -[2023-11-28 09:48:35,521][87424] Updated weights for policy 0, policy_version 366089 (0.0008) -[2023-11-28 09:48:35,907][87424] Updated weights for policy 0, policy_version 366099 (0.0007) -[2023-11-28 09:48:36,293][87424] Updated weights for policy 0, policy_version 366109 (0.0007) -[2023-11-28 09:48:36,621][87426] Updated weights for policy 1, policy_version 365730 (0.0009) -[2023-11-28 09:48:36,998][87426] Updated weights for policy 1, policy_version 365740 (0.0012) -[2023-11-28 09:48:37,379][87426] Updated weights for policy 1, policy_version 365750 (0.0011) -[2023-11-28 09:48:37,762][87426] Updated weights for policy 1, policy_version 365760 (0.0012) -[2023-11-28 09:48:38,054][87424] Updated weights for policy 0, policy_version 366119 (0.0010) -[2023-11-28 09:48:38,439][87424] Updated weights for policy 0, policy_version 366129 (0.0012) -[2023-11-28 09:48:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 187359232. Throughput: 0: 2779.7, 1: 2635.6. Samples: 187377080. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:48:38,446][86177] Avg episode reward: [(0, '-615.000'), (1, '-515.670')] -[2023-11-28 09:48:38,826][87424] Updated weights for policy 0, policy_version 366139 (0.0012) -[2023-11-28 09:48:40,158][87426] Updated weights for policy 1, policy_version 365770 (0.0012) -[2023-11-28 09:48:40,536][87426] Updated weights for policy 1, policy_version 365780 (0.0012) -[2023-11-28 09:48:40,923][87426] Updated weights for policy 1, policy_version 365790 (0.0011) -[2023-11-28 09:48:41,059][87424] Updated weights for policy 0, policy_version 366149 (0.0011) -[2023-11-28 09:48:41,435][87424] Updated weights for policy 0, policy_version 366159 (0.0011) -[2023-11-28 09:48:41,813][87424] Updated weights for policy 0, policy_version 366169 (0.0011) -[2023-11-28 09:48:43,272][87426] Updated weights for policy 1, policy_version 365800 (0.0011) -[2023-11-28 09:48:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187383808. Throughput: 0: 2776.0, 1: 2651.7. Samples: 187400872. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:48:43,446][86177] Avg episode reward: [(0, '-604.950'), (1, '-516.020')] -[2023-11-28 09:48:43,654][87426] Updated weights for policy 1, policy_version 365810 (0.0011) -[2023-11-28 09:48:44,042][87426] Updated weights for policy 1, policy_version 365820 (0.0011) -[2023-11-28 09:48:44,350][87424] Updated weights for policy 0, policy_version 366179 (0.0011) -[2023-11-28 09:48:44,735][87424] Updated weights for policy 0, policy_version 366189 (0.0012) -[2023-11-28 09:48:45,119][87424] Updated weights for policy 0, policy_version 366199 (0.0012) -[2023-11-28 09:48:45,981][87426] Updated weights for policy 1, policy_version 365830 (0.0011) -[2023-11-28 09:48:46,358][87426] Updated weights for policy 1, policy_version 365840 (0.0011) -[2023-11-28 09:48:46,735][87426] Updated weights for policy 1, policy_version 365850 (0.0012) -[2023-11-28 09:48:47,430][87424] Updated weights for policy 0, policy_version 366209 (0.0012) -[2023-11-28 09:48:47,804][87424] Updated weights for policy 0, policy_version 366219 (0.0011) -[2023-11-28 09:48:48,182][87424] Updated weights for policy 0, policy_version 366229 (0.0008) -[2023-11-28 09:48:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 187408384. Throughput: 0: 2722.4, 1: 2653.5. Samples: 187424828. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:48:48,445][86177] Avg episode reward: [(0, '-590.950'), (1, '-511.080')] -[2023-11-28 09:48:48,569][87424] Updated weights for policy 0, policy_version 366239 (0.0007) -[2023-11-28 09:48:49,239][87426] Updated weights for policy 1, policy_version 365860 (0.0009) -[2023-11-28 09:48:49,629][87426] Updated weights for policy 1, policy_version 365870 (0.0010) -[2023-11-28 09:48:50,006][87426] Updated weights for policy 1, policy_version 365880 (0.0011) -[2023-11-28 09:48:50,727][87424] Updated weights for policy 0, policy_version 366249 (0.0011) -[2023-11-28 09:48:51,105][87424] Updated weights for policy 0, policy_version 366259 (0.0012) -[2023-11-28 09:48:51,484][87424] Updated weights for policy 0, policy_version 366269 (0.0010) -[2023-11-28 09:48:52,031][87426] Updated weights for policy 1, policy_version 365890 (0.0008) -[2023-11-28 09:48:52,413][87426] Updated weights for policy 1, policy_version 365900 (0.0010) -[2023-11-28 09:48:52,788][87426] Updated weights for policy 1, policy_version 365910 (0.0008) -[2023-11-28 09:48:53,171][87426] Updated weights for policy 1, policy_version 365920 (0.0009) -[2023-11-28 09:48:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 187441152. Throughput: 0: 2672.8, 1: 2666.0. Samples: 187456308. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:48:53,445][86177] Avg episode reward: [(0, '-595.440'), (1, '-511.950')] -[2023-11-28 09:48:53,863][87424] Updated weights for policy 0, policy_version 366279 (0.0011) -[2023-11-28 09:48:54,248][87424] Updated weights for policy 0, policy_version 366289 (0.0011) -[2023-11-28 09:48:54,634][87424] Updated weights for policy 0, policy_version 366299 (0.0011) -[2023-11-28 09:48:55,625][87426] Updated weights for policy 1, policy_version 365930 (0.0009) -[2023-11-28 09:48:56,003][87426] Updated weights for policy 1, policy_version 365940 (0.0011) -[2023-11-28 09:48:56,375][87426] Updated weights for policy 1, policy_version 365950 (0.0011) -[2023-11-28 09:48:56,828][87424] Updated weights for policy 0, policy_version 366309 (0.0012) -[2023-11-28 09:48:57,209][87424] Updated weights for policy 0, policy_version 366319 (0.0010) -[2023-11-28 09:48:57,589][87424] Updated weights for policy 0, policy_version 366329 (0.0007) -[2023-11-28 09:48:58,378][87426] Updated weights for policy 1, policy_version 365960 (0.0012) -[2023-11-28 09:48:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187465728. Throughput: 0: 2669.9, 1: 2689.0. Samples: 187480988. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:48:58,445][86177] Avg episode reward: [(0, '-587.410'), (1, '-512.010')] -[2023-11-28 09:48:58,763][87426] Updated weights for policy 1, policy_version 365970 (0.0012) -[2023-11-28 09:48:59,150][87426] Updated weights for policy 1, policy_version 365980 (0.0012) -[2023-11-28 09:48:59,610][87424] Updated weights for policy 0, policy_version 366339 (0.0008) -[2023-11-28 09:48:59,996][87424] Updated weights for policy 0, policy_version 366349 (0.0009) -[2023-11-28 09:49:00,382][87424] Updated weights for policy 0, policy_version 366359 (0.0008) -[2023-11-28 09:49:01,416][87426] Updated weights for policy 1, policy_version 365990 (0.0008) -[2023-11-28 09:49:01,799][87426] Updated weights for policy 1, policy_version 366000 (0.0009) -[2023-11-28 09:49:02,184][87426] Updated weights for policy 1, policy_version 366010 (0.0012) -[2023-11-28 09:49:02,685][87424] Updated weights for policy 0, policy_version 366369 (0.0008) -[2023-11-28 09:49:03,070][87424] Updated weights for policy 0, policy_version 366379 (0.0010) -[2023-11-28 09:49:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187490304. Throughput: 0: 2660.0, 1: 2693.0. Samples: 187504276. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:49:03,445][86177] Avg episode reward: [(0, '-579.320'), (1, '-509.490')] -[2023-11-28 09:49:03,449][87424] Updated weights for policy 0, policy_version 366389 (0.0008) -[2023-11-28 09:49:03,824][87424] Updated weights for policy 0, policy_version 366399 (0.0008) -[2023-11-28 09:49:04,499][87426] Updated weights for policy 1, policy_version 366020 (0.0012) -[2023-11-28 09:49:04,869][87426] Updated weights for policy 1, policy_version 366030 (0.0012) -[2023-11-28 09:49:05,244][87426] Updated weights for policy 1, policy_version 366040 (0.0012) -[2023-11-28 09:49:06,242][87424] Updated weights for policy 0, policy_version 366409 (0.0008) -[2023-11-28 09:49:06,624][87424] Updated weights for policy 0, policy_version 366419 (0.0008) -[2023-11-28 09:49:07,014][87424] Updated weights for policy 0, policy_version 366429 (0.0012) -[2023-11-28 09:49:07,087][87426] Updated weights for policy 1, policy_version 366050 (0.0011) -[2023-11-28 09:49:07,454][87426] Updated weights for policy 1, policy_version 366060 (0.0009) -[2023-11-28 09:49:07,840][87426] Updated weights for policy 1, policy_version 366070 (0.0011) -[2023-11-28 09:49:08,230][87426] Updated weights for policy 1, policy_version 366080 (0.0011) -[2023-11-28 09:49:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 187523072. Throughput: 0: 2668.9, 1: 2698.3. Samples: 187536656. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:49:08,445][86177] Avg episode reward: [(0, '-570.680'), (1, '-522.940')] -[2023-11-28 09:49:09,555][87424] Updated weights for policy 0, policy_version 366439 (0.0012) -[2023-11-28 09:49:09,937][87424] Updated weights for policy 0, policy_version 366449 (0.0011) -[2023-11-28 09:49:10,318][87424] Updated weights for policy 0, policy_version 366459 (0.0009) -[2023-11-28 09:49:10,730][87426] Updated weights for policy 1, policy_version 366090 (0.0012) -[2023-11-28 09:49:11,113][87426] Updated weights for policy 1, policy_version 366100 (0.0012) -[2023-11-28 09:49:11,493][87426] Updated weights for policy 1, policy_version 366110 (0.0012) -[2023-11-28 09:49:12,675][87424] Updated weights for policy 0, policy_version 366469 (0.0011) -[2023-11-28 09:49:13,046][87424] Updated weights for policy 0, policy_version 366479 (0.0012) -[2023-11-28 09:49:13,419][87424] Updated weights for policy 0, policy_version 366489 (0.0012) -[2023-11-28 09:49:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 187539456. Throughput: 0: 2642.8, 1: 2682.1. Samples: 187559280. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:49:13,445][86177] Avg episode reward: [(0, '-577.670'), (1, '-520.340')] -[2023-11-28 09:49:14,092][87426] Updated weights for policy 1, policy_version 366120 (0.0012) -[2023-11-28 09:49:14,469][87426] Updated weights for policy 1, policy_version 366130 (0.0011) -[2023-11-28 09:49:14,851][87426] Updated weights for policy 1, policy_version 366140 (0.0011) -[2023-11-28 09:49:15,180][87424] Updated weights for policy 0, policy_version 366499 (0.0011) -[2023-11-28 09:49:15,554][87424] Updated weights for policy 0, policy_version 366509 (0.0011) -[2023-11-28 09:49:15,941][87424] Updated weights for policy 0, policy_version 366519 (0.0011) -[2023-11-28 09:49:16,722][87426] Updated weights for policy 1, policy_version 366150 (0.0011) -[2023-11-28 09:49:17,102][87426] Updated weights for policy 1, policy_version 366160 (0.0010) -[2023-11-28 09:49:17,488][87426] Updated weights for policy 1, policy_version 366170 (0.0009) -[2023-11-28 09:49:18,242][87424] Updated weights for policy 0, policy_version 366529 (0.0011) -[2023-11-28 09:49:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187572224. Throughput: 0: 2657.6, 1: 2670.8. Samples: 187584120. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:49:18,445][86177] Avg episode reward: [(0, '-575.280'), (1, '-525.330')] -[2023-11-28 09:49:18,626][87424] Updated weights for policy 0, policy_version 366539 (0.0010) -[2023-11-28 09:49:19,011][87424] Updated weights for policy 0, policy_version 366549 (0.0011) -[2023-11-28 09:49:19,398][87424] Updated weights for policy 0, policy_version 366559 (0.0012) -[2023-11-28 09:49:19,621][87426] Updated weights for policy 1, policy_version 366180 (0.0011) -[2023-11-28 09:49:20,006][87426] Updated weights for policy 1, policy_version 366190 (0.0011) -[2023-11-28 09:49:20,378][87426] Updated weights for policy 1, policy_version 366200 (0.0012) -[2023-11-28 09:49:21,837][87424] Updated weights for policy 0, policy_version 366569 (0.0011) -[2023-11-28 09:49:22,223][87424] Updated weights for policy 0, policy_version 366579 (0.0011) -[2023-11-28 09:49:22,545][87426] Updated weights for policy 1, policy_version 366210 (0.0010) -[2023-11-28 09:49:22,623][87424] Updated weights for policy 0, policy_version 366589 (0.0011) -[2023-11-28 09:49:22,924][87426] Updated weights for policy 1, policy_version 366220 (0.0012) -[2023-11-28 09:49:23,299][87426] Updated weights for policy 1, policy_version 366230 (0.0012) -[2023-11-28 09:49:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187596800. Throughput: 0: 2626.0, 1: 2672.3. Samples: 187615500. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:49:23,445][86177] Avg episode reward: [(0, '-568.690'), (1, '-525.990')] -[2023-11-28 09:49:23,673][87426] Updated weights for policy 1, policy_version 366240 (0.0012) -[2023-11-28 09:49:24,920][87424] Updated weights for policy 0, policy_version 366599 (0.0008) -[2023-11-28 09:49:25,303][87424] Updated weights for policy 0, policy_version 366609 (0.0008) -[2023-11-28 09:49:25,686][87424] Updated weights for policy 0, policy_version 366619 (0.0008) -[2023-11-28 09:49:26,023][87426] Updated weights for policy 1, policy_version 366250 (0.0011) -[2023-11-28 09:49:26,408][87426] Updated weights for policy 1, policy_version 366260 (0.0012) -[2023-11-28 09:49:26,786][87426] Updated weights for policy 1, policy_version 366270 (0.0011) -[2023-11-28 09:49:28,043][87424] Updated weights for policy 0, policy_version 366629 (0.0007) -[2023-11-28 09:49:28,435][87424] Updated weights for policy 0, policy_version 366639 (0.0008) -[2023-11-28 09:49:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187621376. Throughput: 0: 2636.2, 1: 2689.4. Samples: 187640524. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:49:28,445][86177] Avg episode reward: [(0, '-567.140'), (1, '-522.120')] -[2023-11-28 09:49:28,808][87424] Updated weights for policy 0, policy_version 366649 (0.0007) -[2023-11-28 09:49:28,875][87426] Updated weights for policy 1, policy_version 366280 (0.0011) -[2023-11-28 09:49:29,258][87426] Updated weights for policy 1, policy_version 366290 (0.0012) -[2023-11-28 09:49:29,629][87426] Updated weights for policy 1, policy_version 366300 (0.0011) -[2023-11-28 09:49:31,245][87424] Updated weights for policy 0, policy_version 366659 (0.0011) -[2023-11-28 09:49:31,626][87424] Updated weights for policy 0, policy_version 366669 (0.0012) -[2023-11-28 09:49:31,627][87426] Updated weights for policy 1, policy_version 366310 (0.0009) -[2023-11-28 09:49:31,999][87426] Updated weights for policy 1, policy_version 366320 (0.0011) -[2023-11-28 09:49:32,000][87424] Updated weights for policy 0, policy_version 366679 (0.0010) -[2023-11-28 09:49:32,376][87426] Updated weights for policy 1, policy_version 366330 (0.0011) -[2023-11-28 09:49:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187654144. Throughput: 0: 2626.0, 1: 2702.9. Samples: 187664632. Policy #0 lag: (min: 30.0, avg: 42.5, max: 62.0) -[2023-11-28 09:49:33,445][86177] Avg episode reward: [(0, '-563.930'), (1, '-522.480')] -[2023-11-28 09:49:33,959][87424] Updated weights for policy 0, policy_version 366689 (0.0010) -[2023-11-28 09:49:34,332][87424] Updated weights for policy 0, policy_version 366699 (0.0012) -[2023-11-28 09:49:34,714][87424] Updated weights for policy 0, policy_version 366709 (0.0012) -[2023-11-28 09:49:34,845][87426] Updated weights for policy 1, policy_version 366340 (0.0011) -[2023-11-28 09:49:35,092][87424] Updated weights for policy 0, policy_version 366719 (0.0012) -[2023-11-28 09:49:35,218][87426] Updated weights for policy 1, policy_version 366350 (0.0011) -[2023-11-28 09:49:35,599][87426] Updated weights for policy 1, policy_version 366360 (0.0012) -[2023-11-28 09:49:37,324][87424] Updated weights for policy 0, policy_version 366729 (0.0012) -[2023-11-28 09:49:37,398][87426] Updated weights for policy 1, policy_version 366370 (0.0012) -[2023-11-28 09:49:37,705][87424] Updated weights for policy 0, policy_version 366739 (0.0010) -[2023-11-28 09:49:37,773][87426] Updated weights for policy 1, policy_version 366380 (0.0012) -[2023-11-28 09:49:38,095][87424] Updated weights for policy 0, policy_version 366749 (0.0008) -[2023-11-28 09:49:38,145][87426] Updated weights for policy 1, policy_version 366390 (0.0010) -[2023-11-28 09:49:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187678720. Throughput: 0: 2651.3, 1: 2682.1. Samples: 187696312. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:49:38,445][86177] Avg episode reward: [(0, '-566.360'), (1, '-523.120')] -[2023-11-28 09:49:38,526][87426] Updated weights for policy 1, policy_version 366400 (0.0007) -[2023-11-28 09:49:40,425][87424] Updated weights for policy 0, policy_version 366759 (0.0010) -[2023-11-28 09:49:40,806][87424] Updated weights for policy 0, policy_version 366769 (0.0011) -[2023-11-28 09:49:40,966][87426] Updated weights for policy 1, policy_version 366410 (0.0012) -[2023-11-28 09:49:41,201][87424] Updated weights for policy 0, policy_version 366779 (0.0010) -[2023-11-28 09:49:41,346][87426] Updated weights for policy 1, policy_version 366420 (0.0010) -[2023-11-28 09:49:41,734][87426] Updated weights for policy 1, policy_version 366430 (0.0010) -[2023-11-28 09:49:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187703296. Throughput: 0: 2649.2, 1: 2656.9. Samples: 187719760. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:49:43,445][86177] Avg episode reward: [(0, '-584.580'), (1, '-557.390')] -[2023-11-28 09:49:43,658][87424] Updated weights for policy 0, policy_version 366789 (0.0010) -[2023-11-28 09:49:44,023][87426] Updated weights for policy 1, policy_version 366440 (0.0012) -[2023-11-28 09:49:44,039][87424] Updated weights for policy 0, policy_version 366799 (0.0008) -[2023-11-28 09:49:44,404][87426] Updated weights for policy 1, policy_version 366450 (0.0009) -[2023-11-28 09:49:44,419][87424] Updated weights for policy 0, policy_version 366809 (0.0012) -[2023-11-28 09:49:44,773][87426] Updated weights for policy 1, policy_version 366460 (0.0008) -[2023-11-28 09:49:46,528][87424] Updated weights for policy 0, policy_version 366819 (0.0011) -[2023-11-28 09:49:46,909][87424] Updated weights for policy 0, policy_version 366829 (0.0008) -[2023-11-28 09:49:47,085][87426] Updated weights for policy 1, policy_version 366470 (0.0009) -[2023-11-28 09:49:47,289][87424] Updated weights for policy 0, policy_version 366839 (0.0010) -[2023-11-28 09:49:47,461][87426] Updated weights for policy 1, policy_version 366480 (0.0011) -[2023-11-28 09:49:47,839][87426] Updated weights for policy 1, policy_version 366490 (0.0012) -[2023-11-28 09:49:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 187736064. Throughput: 0: 2630.8, 1: 2665.1. Samples: 187742588. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:49:48,445][86177] Avg episode reward: [(0, '-582.550'), (1, '-552.020')] -[2023-11-28 09:49:48,992][87424] Updated weights for policy 0, policy_version 366849 (0.0010) -[2023-11-28 09:49:49,366][87424] Updated weights for policy 0, policy_version 366859 (0.0008) -[2023-11-28 09:49:49,758][87424] Updated weights for policy 0, policy_version 366869 (0.0008) -[2023-11-28 09:49:50,130][87424] Updated weights for policy 0, policy_version 366879 (0.0010) -[2023-11-28 09:49:50,293][87426] Updated weights for policy 1, policy_version 366500 (0.0012) -[2023-11-28 09:49:50,665][87426] Updated weights for policy 1, policy_version 366510 (0.0011) -[2023-11-28 09:49:51,044][87426] Updated weights for policy 1, policy_version 366520 (0.0011) -[2023-11-28 09:49:52,667][87424] Updated weights for policy 0, policy_version 366889 (0.0011) -[2023-11-28 09:49:53,045][87424] Updated weights for policy 0, policy_version 366899 (0.0012) -[2023-11-28 09:49:53,427][87424] Updated weights for policy 0, policy_version 366909 (0.0011) -[2023-11-28 09:49:53,429][87426] Updated weights for policy 1, policy_version 366530 (0.0015) -[2023-11-28 09:49:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 187752448. Throughput: 0: 2645.4, 1: 2646.2. Samples: 187774780. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:49:53,445][86177] Avg episode reward: [(0, '-590.840'), (1, '-555.150')] -[2023-11-28 09:49:53,804][87426] Updated weights for policy 1, policy_version 366540 (0.0012) -[2023-11-28 09:49:54,180][87426] Updated weights for policy 1, policy_version 366550 (0.0012) -[2023-11-28 09:49:54,559][87426] Updated weights for policy 1, policy_version 366560 (0.0012) -[2023-11-28 09:49:55,494][87424] Updated weights for policy 0, policy_version 366919 (0.0012) -[2023-11-28 09:49:55,866][87424] Updated weights for policy 0, policy_version 366929 (0.0012) -[2023-11-28 09:49:56,257][87424] Updated weights for policy 0, policy_version 366939 (0.0011) -[2023-11-28 09:49:56,787][87426] Updated weights for policy 1, policy_version 366570 (0.0007) -[2023-11-28 09:49:57,168][87426] Updated weights for policy 1, policy_version 366580 (0.0007) -[2023-11-28 09:49:57,544][87426] Updated weights for policy 1, policy_version 366590 (0.0011) -[2023-11-28 09:49:58,289][87424] Updated weights for policy 0, policy_version 366949 (0.0012) -[2023-11-28 09:49:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187785216. Throughput: 0: 2676.6, 1: 2689.0. Samples: 187800732. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:49:58,445][86177] Avg episode reward: [(0, '-577.370'), (1, '-553.300')] -[2023-11-28 09:49:58,664][87424] Updated weights for policy 0, policy_version 366959 (0.0012) -[2023-11-28 09:49:59,042][87424] Updated weights for policy 0, policy_version 366969 (0.0011) -[2023-11-28 09:49:59,580][87426] Updated weights for policy 1, policy_version 366600 (0.0008) -[2023-11-28 09:49:59,962][87426] Updated weights for policy 1, policy_version 366610 (0.0009) -[2023-11-28 09:50:00,340][87426] Updated weights for policy 1, policy_version 366620 (0.0011) -[2023-11-28 09:50:01,061][87424] Updated weights for policy 0, policy_version 366979 (0.0011) -[2023-11-28 09:50:01,444][87424] Updated weights for policy 0, policy_version 366989 (0.0012) -[2023-11-28 09:50:01,824][87424] Updated weights for policy 0, policy_version 366999 (0.0012) -[2023-11-28 09:50:02,802][87426] Updated weights for policy 1, policy_version 366630 (0.0010) -[2023-11-28 09:50:03,175][87426] Updated weights for policy 1, policy_version 366640 (0.0011) -[2023-11-28 09:50:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 187809792. Throughput: 0: 2690.1, 1: 2684.1. Samples: 187825956. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:03,445][86177] Avg episode reward: [(0, '-576.750'), (1, '-535.670')] -[2023-11-28 09:50:03,555][87426] Updated weights for policy 1, policy_version 366650 (0.0011) -[2023-11-28 09:50:03,684][87424] Updated weights for policy 0, policy_version 367009 (0.0010) -[2023-11-28 09:50:04,062][87424] Updated weights for policy 0, policy_version 367019 (0.0011) -[2023-11-28 09:50:04,430][87424] Updated weights for policy 0, policy_version 367029 (0.0012) -[2023-11-28 09:50:04,810][87424] Updated weights for policy 0, policy_version 367039 (0.0012) -[2023-11-28 09:50:05,600][87426] Updated weights for policy 1, policy_version 366660 (0.0011) -[2023-11-28 09:50:05,980][87426] Updated weights for policy 1, policy_version 366670 (0.0011) -[2023-11-28 09:50:06,366][87426] Updated weights for policy 1, policy_version 366680 (0.0008) -[2023-11-28 09:50:07,104][87424] Updated weights for policy 0, policy_version 367049 (0.0011) -[2023-11-28 09:50:07,487][87424] Updated weights for policy 0, policy_version 367059 (0.0011) -[2023-11-28 09:50:07,868][87424] Updated weights for policy 0, policy_version 367069 (0.0012) -[2023-11-28 09:50:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 187842560. Throughput: 0: 2693.1, 1: 2678.8. Samples: 187857236. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:08,445][86177] Avg episode reward: [(0, '-570.210'), (1, '-548.980')] -[2023-11-28 09:50:08,455][87426] Updated weights for policy 1, policy_version 366690 (0.0010) -[2023-11-28 09:50:08,830][87426] Updated weights for policy 1, policy_version 366700 (0.0008) -[2023-11-28 09:50:09,211][87426] Updated weights for policy 1, policy_version 366710 (0.0011) -[2023-11-28 09:50:09,591][87426] Updated weights for policy 1, policy_version 366720 (0.0011) -[2023-11-28 09:50:09,763][87424] Updated weights for policy 0, policy_version 367079 (0.0012) -[2023-11-28 09:50:10,142][87424] Updated weights for policy 0, policy_version 367089 (0.0010) -[2023-11-28 09:50:10,533][87424] Updated weights for policy 0, policy_version 367099 (0.0011) -[2023-11-28 09:50:12,188][87426] Updated weights for policy 1, policy_version 366730 (0.0012) -[2023-11-28 09:50:12,560][87426] Updated weights for policy 1, policy_version 366740 (0.0012) -[2023-11-28 09:50:12,794][87424] Updated weights for policy 0, policy_version 367109 (0.0009) -[2023-11-28 09:50:12,938][87426] Updated weights for policy 1, policy_version 366750 (0.0012) -[2023-11-28 09:50:13,179][87424] Updated weights for policy 0, policy_version 367119 (0.0010) -[2023-11-28 09:50:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 187867136. Throughput: 0: 2698.7, 1: 2646.3. Samples: 187881048. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:13,445][86177] Avg episode reward: [(0, '-552.910'), (1, '-555.770')] -[2023-11-28 09:50:13,561][87424] Updated weights for policy 0, policy_version 367129 (0.0011) -[2023-11-28 09:50:15,305][87424] Updated weights for policy 0, policy_version 367139 (0.0010) -[2023-11-28 09:50:15,520][87426] Updated weights for policy 1, policy_version 366760 (0.0010) -[2023-11-28 09:50:15,679][87424] Updated weights for policy 0, policy_version 367149 (0.0012) -[2023-11-28 09:50:15,888][87426] Updated weights for policy 1, policy_version 366770 (0.0011) -[2023-11-28 09:50:16,057][87424] Updated weights for policy 0, policy_version 367159 (0.0012) -[2023-11-28 09:50:16,274][87426] Updated weights for policy 1, policy_version 366780 (0.0011) -[2023-11-28 09:50:18,281][87426] Updated weights for policy 1, policy_version 366790 (0.0012) -[2023-11-28 09:50:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 187891712. Throughput: 0: 2722.0, 1: 2613.7. Samples: 187904740. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:18,446][86177] Avg episode reward: [(0, '-560.200'), (1, '-546.820')] -[2023-11-28 09:50:18,572][87424] Updated weights for policy 0, policy_version 367169 (0.0011) -[2023-11-28 09:50:18,647][87426] Updated weights for policy 1, policy_version 366800 (0.0011) -[2023-11-28 09:50:18,967][87424] Updated weights for policy 0, policy_version 367179 (0.0008) -[2023-11-28 09:50:19,025][87426] Updated weights for policy 1, policy_version 366810 (0.0009) -[2023-11-28 09:50:19,252][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000366816_93904896.pth... -[2023-11-28 09:50:19,288][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000364288_93257728.pth -[2023-11-28 09:50:19,356][87424] Updated weights for policy 0, policy_version 367189 (0.0009) -[2023-11-28 09:50:19,723][87424] Updated weights for policy 0, policy_version 367199 (0.0011) -[2023-11-28 09:50:19,759][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000367200_94003200.pth... -[2023-11-28 09:50:19,807][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000364640_93347840.pth -[2023-11-28 09:50:21,547][87426] Updated weights for policy 1, policy_version 366820 (0.0011) -[2023-11-28 09:50:21,928][87426] Updated weights for policy 1, policy_version 366830 (0.0011) -[2023-11-28 09:50:22,222][87424] Updated weights for policy 0, policy_version 367209 (0.0012) -[2023-11-28 09:50:22,340][87426] Updated weights for policy 1, policy_version 366840 (0.0010) -[2023-11-28 09:50:22,611][87424] Updated weights for policy 0, policy_version 367219 (0.0012) -[2023-11-28 09:50:22,991][87424] Updated weights for policy 0, policy_version 367229 (0.0012) -[2023-11-28 09:50:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 187924480. Throughput: 0: 2703.1, 1: 2635.2. Samples: 187936536. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:23,445][86177] Avg episode reward: [(0, '-556.660'), (1, '-536.570')] -[2023-11-28 09:50:24,451][87426] Updated weights for policy 1, policy_version 366850 (0.0012) -[2023-11-28 09:50:24,835][87426] Updated weights for policy 1, policy_version 366860 (0.0010) -[2023-11-28 09:50:24,864][87424] Updated weights for policy 0, policy_version 367239 (0.0011) -[2023-11-28 09:50:25,210][87426] Updated weights for policy 1, policy_version 366870 (0.0011) -[2023-11-28 09:50:25,240][87424] Updated weights for policy 0, policy_version 367249 (0.0010) -[2023-11-28 09:50:25,583][87426] Updated weights for policy 1, policy_version 366880 (0.0012) -[2023-11-28 09:50:25,618][87424] Updated weights for policy 0, policy_version 367259 (0.0011) -[2023-11-28 09:50:27,595][87426] Updated weights for policy 1, policy_version 366890 (0.0012) -[2023-11-28 09:50:27,595][87424] Updated weights for policy 0, policy_version 367269 (0.0010) -[2023-11-28 09:50:27,971][87426] Updated weights for policy 1, policy_version 366900 (0.0012) -[2023-11-28 09:50:27,977][87424] Updated weights for policy 0, policy_version 367279 (0.0010) -[2023-11-28 09:50:28,354][87426] Updated weights for policy 1, policy_version 366910 (0.0010) -[2023-11-28 09:50:28,360][87424] Updated weights for policy 0, policy_version 367289 (0.0007) -[2023-11-28 09:50:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 187949056. Throughput: 0: 2714.8, 1: 2645.3. Samples: 187960968. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:28,445][86177] Avg episode reward: [(0, '-561.360'), (1, '-516.870')] -[2023-11-28 09:50:30,786][87426] Updated weights for policy 1, policy_version 366920 (0.0011) -[2023-11-28 09:50:30,819][87424] Updated weights for policy 0, policy_version 367299 (0.0009) -[2023-11-28 09:50:31,166][87426] Updated weights for policy 1, policy_version 366930 (0.0012) -[2023-11-28 09:50:31,196][87424] Updated weights for policy 0, policy_version 367309 (0.0010) -[2023-11-28 09:50:31,542][87426] Updated weights for policy 1, policy_version 366940 (0.0011) -[2023-11-28 09:50:31,575][87424] Updated weights for policy 0, policy_version 367319 (0.0011) -[2023-11-28 09:50:33,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 187973632. Throughput: 0: 2758.9, 1: 2636.8. Samples: 187985396. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:33,446][86177] Avg episode reward: [(0, '-563.580'), (1, '-532.280')] -[2023-11-28 09:50:33,610][87424] Updated weights for policy 0, policy_version 367329 (0.0009) -[2023-11-28 09:50:33,992][87424] Updated weights for policy 0, policy_version 367339 (0.0011) -[2023-11-28 09:50:34,022][87426] Updated weights for policy 1, policy_version 366950 (0.0010) -[2023-11-28 09:50:34,377][87424] Updated weights for policy 0, policy_version 367349 (0.0011) -[2023-11-28 09:50:34,409][87426] Updated weights for policy 1, policy_version 366960 (0.0011) -[2023-11-28 09:50:34,753][87424] Updated weights for policy 0, policy_version 367359 (0.0010) -[2023-11-28 09:50:34,796][87426] Updated weights for policy 1, policy_version 366970 (0.0010) -[2023-11-28 09:50:36,657][87426] Updated weights for policy 1, policy_version 366980 (0.0012) -[2023-11-28 09:50:36,791][87424] Updated weights for policy 0, policy_version 367369 (0.0011) -[2023-11-28 09:50:37,035][87426] Updated weights for policy 1, policy_version 366990 (0.0009) -[2023-11-28 09:50:37,174][87424] Updated weights for policy 0, policy_version 367379 (0.0011) -[2023-11-28 09:50:37,409][87426] Updated weights for policy 1, policy_version 367000 (0.0010) -[2023-11-28 09:50:37,565][87424] Updated weights for policy 0, policy_version 367389 (0.0009) -[2023-11-28 09:50:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 188006400. Throughput: 0: 2758.7, 1: 2638.8. Samples: 188017672. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:38,446][86177] Avg episode reward: [(0, '-559.380'), (1, '-554.610')] -[2023-11-28 09:50:39,621][87426] Updated weights for policy 1, policy_version 367010 (0.0009) -[2023-11-28 09:50:39,942][87424] Updated weights for policy 0, policy_version 367399 (0.0010) -[2023-11-28 09:50:39,991][87426] Updated weights for policy 1, policy_version 367020 (0.0011) -[2023-11-28 09:50:40,324][87424] Updated weights for policy 0, policy_version 367409 (0.0012) -[2023-11-28 09:50:40,370][87426] Updated weights for policy 1, policy_version 367030 (0.0011) -[2023-11-28 09:50:40,710][87424] Updated weights for policy 0, policy_version 367419 (0.0011) -[2023-11-28 09:50:40,744][87426] Updated weights for policy 1, policy_version 367040 (0.0011) -[2023-11-28 09:50:42,905][87426] Updated weights for policy 1, policy_version 367050 (0.0010) -[2023-11-28 09:50:42,991][87424] Updated weights for policy 0, policy_version 367429 (0.0011) -[2023-11-28 09:50:43,289][87426] Updated weights for policy 1, policy_version 367060 (0.0012) -[2023-11-28 09:50:43,372][87424] Updated weights for policy 0, policy_version 367439 (0.0011) -[2023-11-28 09:50:43,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188022784. Throughput: 0: 2745.2, 1: 2619.9. Samples: 188042160. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:43,445][86177] Avg episode reward: [(0, '-556.040'), (1, '-562.890')] -[2023-11-28 09:50:43,659][87426] Updated weights for policy 1, policy_version 367070 (0.0012) -[2023-11-28 09:50:43,761][87424] Updated weights for policy 0, policy_version 367449 (0.0011) -[2023-11-28 09:50:45,593][87424] Updated weights for policy 0, policy_version 367459 (0.0011) -[2023-11-28 09:50:45,919][87426] Updated weights for policy 1, policy_version 367080 (0.0011) -[2023-11-28 09:50:45,970][87424] Updated weights for policy 0, policy_version 367469 (0.0012) -[2023-11-28 09:50:46,293][87426] Updated weights for policy 1, policy_version 367090 (0.0011) -[2023-11-28 09:50:46,352][87424] Updated weights for policy 0, policy_version 367479 (0.0011) -[2023-11-28 09:50:46,672][87426] Updated weights for policy 1, policy_version 367100 (0.0008) -[2023-11-28 09:50:48,319][87424] Updated weights for policy 0, policy_version 367489 (0.0011) -[2023-11-28 09:50:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 188055552. Throughput: 0: 2723.6, 1: 2631.2. Samples: 188066920. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:48,445][86177] Avg episode reward: [(0, '-543.940'), (1, '-571.600')] -[2023-11-28 09:50:48,696][87424] Updated weights for policy 0, policy_version 367499 (0.0012) -[2023-11-28 09:50:48,886][87426] Updated weights for policy 1, policy_version 367110 (0.0008) -[2023-11-28 09:50:49,085][87424] Updated weights for policy 0, policy_version 367509 (0.0010) -[2023-11-28 09:50:49,265][87426] Updated weights for policy 1, policy_version 367120 (0.0010) -[2023-11-28 09:50:49,460][87424] Updated weights for policy 0, policy_version 367519 (0.0008) -[2023-11-28 09:50:49,649][87426] Updated weights for policy 1, policy_version 367130 (0.0009) -[2023-11-28 09:50:51,979][87424] Updated weights for policy 0, policy_version 367529 (0.0012) -[2023-11-28 09:50:51,990][87426] Updated weights for policy 1, policy_version 367140 (0.0010) -[2023-11-28 09:50:52,358][87424] Updated weights for policy 0, policy_version 367539 (0.0011) -[2023-11-28 09:50:52,386][87426] Updated weights for policy 1, policy_version 367150 (0.0010) -[2023-11-28 09:50:52,738][87424] Updated weights for policy 0, policy_version 367549 (0.0011) -[2023-11-28 09:50:52,772][87426] Updated weights for policy 1, policy_version 367160 (0.0007) -[2023-11-28 09:50:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 188088320. Throughput: 0: 2733.4, 1: 2633.7. Samples: 188098756. Policy #0 lag: (min: 31.0, avg: 48.0, max: 74.0) -[2023-11-28 09:50:53,445][86177] Avg episode reward: [(0, '-558.790'), (1, '-541.360')] -[2023-11-28 09:50:55,151][87426] Updated weights for policy 1, policy_version 367170 (0.0011) -[2023-11-28 09:50:55,373][87424] Updated weights for policy 0, policy_version 367559 (0.0011) -[2023-11-28 09:50:55,523][87426] Updated weights for policy 1, policy_version 367180 (0.0010) -[2023-11-28 09:50:55,743][87424] Updated weights for policy 0, policy_version 367569 (0.0011) -[2023-11-28 09:50:55,902][87426] Updated weights for policy 1, policy_version 367190 (0.0007) -[2023-11-28 09:50:56,128][87424] Updated weights for policy 0, policy_version 367579 (0.0012) -[2023-11-28 09:50:56,279][87426] Updated weights for policy 1, policy_version 367200 (0.0009) -[2023-11-28 09:50:58,269][87426] Updated weights for policy 1, policy_version 367210 (0.0008) -[2023-11-28 09:50:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188104704. Throughput: 0: 2706.9, 1: 2673.6. Samples: 188123172. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:50:58,445][86177] Avg episode reward: [(0, '-546.230'), (1, '-554.270')] -[2023-11-28 09:50:58,585][87424] Updated weights for policy 0, policy_version 367589 (0.0011) -[2023-11-28 09:50:58,648][87426] Updated weights for policy 1, policy_version 367220 (0.0007) -[2023-11-28 09:50:58,971][87424] Updated weights for policy 0, policy_version 367599 (0.0012) -[2023-11-28 09:50:59,031][87426] Updated weights for policy 1, policy_version 367230 (0.0009) -[2023-11-28 09:50:59,343][87424] Updated weights for policy 0, policy_version 367609 (0.0012) -[2023-11-28 09:51:00,800][87426] Updated weights for policy 1, policy_version 367240 (0.0008) -[2023-11-28 09:51:01,180][87426] Updated weights for policy 1, policy_version 367250 (0.0007) -[2023-11-28 09:51:01,499][87424] Updated weights for policy 0, policy_version 367619 (0.0011) -[2023-11-28 09:51:01,558][87426] Updated weights for policy 1, policy_version 367260 (0.0009) -[2023-11-28 09:51:01,891][87424] Updated weights for policy 0, policy_version 367629 (0.0011) -[2023-11-28 09:51:02,263][87424] Updated weights for policy 0, policy_version 367639 (0.0010) -[2023-11-28 09:51:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 188137472. Throughput: 0: 2711.3, 1: 2689.7. Samples: 188147784. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:03,445][86177] Avg episode reward: [(0, '-581.880'), (1, '-549.580')] -[2023-11-28 09:51:04,105][87426] Updated weights for policy 1, policy_version 367270 (0.0012) -[2023-11-28 09:51:04,342][87424] Updated weights for policy 0, policy_version 367649 (0.0011) -[2023-11-28 09:51:04,483][87426] Updated weights for policy 1, policy_version 367280 (0.0011) -[2023-11-28 09:51:04,728][87424] Updated weights for policy 0, policy_version 367659 (0.0010) -[2023-11-28 09:51:04,856][87426] Updated weights for policy 1, policy_version 367290 (0.0011) -[2023-11-28 09:51:05,105][87424] Updated weights for policy 0, policy_version 367669 (0.0008) -[2023-11-28 09:51:05,488][87424] Updated weights for policy 0, policy_version 367679 (0.0008) -[2023-11-28 09:51:06,689][87426] Updated weights for policy 1, policy_version 367300 (0.0009) -[2023-11-28 09:51:07,069][87426] Updated weights for policy 1, policy_version 367310 (0.0011) -[2023-11-28 09:51:07,213][87424] Updated weights for policy 0, policy_version 367689 (0.0009) -[2023-11-28 09:51:07,443][87426] Updated weights for policy 1, policy_version 367320 (0.0012) -[2023-11-28 09:51:07,596][87424] Updated weights for policy 0, policy_version 367699 (0.0011) -[2023-11-28 09:51:07,976][87424] Updated weights for policy 0, policy_version 367709 (0.0008) -[2023-11-28 09:51:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 188170240. Throughput: 0: 2734.2, 1: 2694.9. Samples: 188180848. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:08,445][86177] Avg episode reward: [(0, '-589.920'), (1, '-551.510')] -[2023-11-28 09:51:10,001][87426] Updated weights for policy 1, policy_version 367330 (0.0010) -[2023-11-28 09:51:10,376][87426] Updated weights for policy 1, policy_version 367340 (0.0012) -[2023-11-28 09:51:10,408][87424] Updated weights for policy 0, policy_version 367719 (0.0010) -[2023-11-28 09:51:10,750][87426] Updated weights for policy 1, policy_version 367350 (0.0011) -[2023-11-28 09:51:10,796][87424] Updated weights for policy 0, policy_version 367729 (0.0009) -[2023-11-28 09:51:11,126][87426] Updated weights for policy 1, policy_version 367360 (0.0011) -[2023-11-28 09:51:11,184][87424] Updated weights for policy 0, policy_version 367739 (0.0009) -[2023-11-28 09:51:13,346][87426] Updated weights for policy 1, policy_version 367370 (0.0011) -[2023-11-28 09:51:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188186624. Throughput: 0: 2740.5, 1: 2687.6. Samples: 188205228. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:13,445][86177] Avg episode reward: [(0, '-602.190'), (1, '-539.870')] -[2023-11-28 09:51:13,726][87426] Updated weights for policy 1, policy_version 367380 (0.0012) -[2023-11-28 09:51:13,740][87424] Updated weights for policy 0, policy_version 367749 (0.0010) -[2023-11-28 09:51:14,108][87426] Updated weights for policy 1, policy_version 367390 (0.0011) -[2023-11-28 09:51:14,127][87424] Updated weights for policy 0, policy_version 367759 (0.0009) -[2023-11-28 09:51:14,507][87424] Updated weights for policy 0, policy_version 367769 (0.0011) -[2023-11-28 09:51:16,520][87426] Updated weights for policy 1, policy_version 367400 (0.0010) -[2023-11-28 09:51:16,713][87424] Updated weights for policy 0, policy_version 367779 (0.0011) -[2023-11-28 09:51:16,883][87426] Updated weights for policy 1, policy_version 367410 (0.0009) -[2023-11-28 09:51:17,093][87424] Updated weights for policy 0, policy_version 367789 (0.0007) -[2023-11-28 09:51:17,261][87426] Updated weights for policy 1, policy_version 367420 (0.0010) -[2023-11-28 09:51:17,474][87424] Updated weights for policy 0, policy_version 367799 (0.0007) -[2023-11-28 09:51:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 188219392. Throughput: 0: 2702.6, 1: 2705.9. Samples: 188228776. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:18,445][86177] Avg episode reward: [(0, '-598.500'), (1, '-574.350')] -[2023-11-28 09:51:19,423][87426] Updated weights for policy 1, policy_version 367430 (0.0008) -[2023-11-28 09:51:19,801][87426] Updated weights for policy 1, policy_version 367440 (0.0008) -[2023-11-28 09:51:20,063][87424] Updated weights for policy 0, policy_version 367809 (0.0008) -[2023-11-28 09:51:20,211][87426] Updated weights for policy 1, policy_version 367450 (0.0011) -[2023-11-28 09:51:20,432][87424] Updated weights for policy 0, policy_version 367819 (0.0010) -[2023-11-28 09:51:20,817][87424] Updated weights for policy 0, policy_version 367829 (0.0012) -[2023-11-28 09:51:21,199][87424] Updated weights for policy 0, policy_version 367839 (0.0012) -[2023-11-28 09:51:22,458][87426] Updated weights for policy 1, policy_version 367460 (0.0010) -[2023-11-28 09:51:22,835][87426] Updated weights for policy 1, policy_version 367470 (0.0012) -[2023-11-28 09:51:23,207][87426] Updated weights for policy 1, policy_version 367480 (0.0009) -[2023-11-28 09:51:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 188235776. Throughput: 0: 2670.2, 1: 2716.9. Samples: 188260092. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:23,445][86177] Avg episode reward: [(0, '-565.410'), (1, '-576.500')] -[2023-11-28 09:51:23,743][87424] Updated weights for policy 0, policy_version 367849 (0.0012) -[2023-11-28 09:51:24,123][87424] Updated weights for policy 0, policy_version 367859 (0.0012) -[2023-11-28 09:51:24,510][87424] Updated weights for policy 0, policy_version 367869 (0.0012) -[2023-11-28 09:51:25,141][87426] Updated weights for policy 1, policy_version 367490 (0.0011) -[2023-11-28 09:51:25,511][87426] Updated weights for policy 1, policy_version 367500 (0.0012) -[2023-11-28 09:51:25,876][87426] Updated weights for policy 1, policy_version 367510 (0.0012) -[2023-11-28 09:51:26,248][87426] Updated weights for policy 1, policy_version 367520 (0.0011) -[2023-11-28 09:51:26,535][87424] Updated weights for policy 0, policy_version 367879 (0.0011) -[2023-11-28 09:51:26,915][87424] Updated weights for policy 0, policy_version 367889 (0.0012) -[2023-11-28 09:51:27,311][87424] Updated weights for policy 0, policy_version 367899 (0.0010) -[2023-11-28 09:51:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 188268544. Throughput: 0: 2670.0, 1: 2723.1. Samples: 188284848. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:28,445][86177] Avg episode reward: [(0, '-567.120'), (1, '-582.150')] -[2023-11-28 09:51:28,681][87426] Updated weights for policy 1, policy_version 367530 (0.0012) -[2023-11-28 09:51:29,063][87426] Updated weights for policy 1, policy_version 367540 (0.0012) -[2023-11-28 09:51:29,446][87426] Updated weights for policy 1, policy_version 367550 (0.0011) -[2023-11-28 09:51:29,531][87424] Updated weights for policy 0, policy_version 367909 (0.0008) -[2023-11-28 09:51:29,916][87424] Updated weights for policy 0, policy_version 367919 (0.0010) -[2023-11-28 09:51:30,299][87424] Updated weights for policy 0, policy_version 367929 (0.0008) -[2023-11-28 09:51:31,484][87426] Updated weights for policy 1, policy_version 367560 (0.0012) -[2023-11-28 09:51:31,857][87426] Updated weights for policy 1, policy_version 367570 (0.0012) -[2023-11-28 09:51:32,244][87426] Updated weights for policy 1, policy_version 367580 (0.0012) -[2023-11-28 09:51:32,468][87424] Updated weights for policy 0, policy_version 367939 (0.0010) -[2023-11-28 09:51:32,857][87424] Updated weights for policy 0, policy_version 367949 (0.0010) -[2023-11-28 09:51:33,241][87424] Updated weights for policy 0, policy_version 367959 (0.0012) -[2023-11-28 09:51:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188293120. Throughput: 0: 2653.1, 1: 2726.2. Samples: 188308988. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:33,445][86177] Avg episode reward: [(0, '-563.830'), (1, '-583.090')] -[2023-11-28 09:51:34,243][87426] Updated weights for policy 1, policy_version 367590 (0.0010) -[2023-11-28 09:51:34,626][87426] Updated weights for policy 1, policy_version 367600 (0.0011) -[2023-11-28 09:51:35,008][87426] Updated weights for policy 1, policy_version 367610 (0.0011) -[2023-11-28 09:51:35,263][87424] Updated weights for policy 0, policy_version 367969 (0.0012) -[2023-11-28 09:51:35,639][87424] Updated weights for policy 0, policy_version 367979 (0.0011) -[2023-11-28 09:51:36,026][87424] Updated weights for policy 0, policy_version 367989 (0.0012) -[2023-11-28 09:51:36,414][87424] Updated weights for policy 0, policy_version 367999 (0.0012) -[2023-11-28 09:51:37,167][87426] Updated weights for policy 1, policy_version 367620 (0.0010) -[2023-11-28 09:51:37,554][87426] Updated weights for policy 1, policy_version 367630 (0.0012) -[2023-11-28 09:51:37,934][87426] Updated weights for policy 1, policy_version 367640 (0.0012) -[2023-11-28 09:51:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 188325888. Throughput: 0: 2656.4, 1: 2743.1. Samples: 188341736. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:38,446][86177] Avg episode reward: [(0, '-564.380'), (1, '-573.290')] -[2023-11-28 09:51:38,986][87424] Updated weights for policy 0, policy_version 368009 (0.0010) -[2023-11-28 09:51:39,366][87424] Updated weights for policy 0, policy_version 368019 (0.0008) -[2023-11-28 09:51:39,755][87424] Updated weights for policy 0, policy_version 368029 (0.0008) -[2023-11-28 09:51:40,128][87426] Updated weights for policy 1, policy_version 367650 (0.0012) -[2023-11-28 09:51:40,505][87426] Updated weights for policy 1, policy_version 367660 (0.0016) -[2023-11-28 09:51:40,892][87426] Updated weights for policy 1, policy_version 367670 (0.0012) -[2023-11-28 09:51:41,271][87426] Updated weights for policy 1, policy_version 367680 (0.0012) -[2023-11-28 09:51:41,723][87424] Updated weights for policy 0, policy_version 368039 (0.0011) -[2023-11-28 09:51:42,112][87424] Updated weights for policy 0, policy_version 368049 (0.0011) -[2023-11-28 09:51:42,493][87424] Updated weights for policy 0, policy_version 368059 (0.0011) -[2023-11-28 09:51:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 188350464. Throughput: 0: 2656.6, 1: 2715.2. Samples: 188364904. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:43,445][86177] Avg episode reward: [(0, '-583.670'), (1, '-590.330')] -[2023-11-28 09:51:43,525][87426] Updated weights for policy 1, policy_version 367690 (0.0010) -[2023-11-28 09:51:43,905][87426] Updated weights for policy 1, policy_version 367700 (0.0012) -[2023-11-28 09:51:44,286][87426] Updated weights for policy 1, policy_version 367710 (0.0012) -[2023-11-28 09:51:44,500][87424] Updated weights for policy 0, policy_version 368069 (0.0011) -[2023-11-28 09:51:44,883][87424] Updated weights for policy 0, policy_version 368079 (0.0012) -[2023-11-28 09:51:45,258][87424] Updated weights for policy 0, policy_version 368089 (0.0012) -[2023-11-28 09:51:46,600][87426] Updated weights for policy 1, policy_version 367720 (0.0012) -[2023-11-28 09:51:46,982][87426] Updated weights for policy 1, policy_version 367730 (0.0012) -[2023-11-28 09:51:47,357][87426] Updated weights for policy 1, policy_version 367740 (0.0012) -[2023-11-28 09:51:47,809][87424] Updated weights for policy 0, policy_version 368099 (0.0010) -[2023-11-28 09:51:48,183][87424] Updated weights for policy 0, policy_version 368109 (0.0008) -[2023-11-28 09:51:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188375040. Throughput: 0: 2643.6, 1: 2719.6. Samples: 188389128. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:48,445][86177] Avg episode reward: [(0, '-592.270'), (1, '-573.750')] -[2023-11-28 09:51:48,567][87424] Updated weights for policy 0, policy_version 368119 (0.0008) -[2023-11-28 09:51:49,819][87426] Updated weights for policy 1, policy_version 367750 (0.0010) -[2023-11-28 09:51:50,186][87426] Updated weights for policy 1, policy_version 367760 (0.0011) -[2023-11-28 09:51:50,574][87426] Updated weights for policy 1, policy_version 367770 (0.0011) -[2023-11-28 09:51:50,948][87424] Updated weights for policy 0, policy_version 368129 (0.0008) -[2023-11-28 09:51:51,326][87424] Updated weights for policy 0, policy_version 368139 (0.0008) -[2023-11-28 09:51:51,714][87424] Updated weights for policy 0, policy_version 368149 (0.0012) -[2023-11-28 09:51:52,081][87424] Updated weights for policy 0, policy_version 368159 (0.0012) -[2023-11-28 09:51:52,962][87426] Updated weights for policy 1, policy_version 367780 (0.0008) -[2023-11-28 09:51:53,341][87426] Updated weights for policy 1, policy_version 367790 (0.0010) -[2023-11-28 09:51:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 188399616. Throughput: 0: 2618.3, 1: 2690.1. Samples: 188419728. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:53,445][86177] Avg episode reward: [(0, '-586.340'), (1, '-581.540')] -[2023-11-28 09:51:53,721][87426] Updated weights for policy 1, policy_version 367800 (0.0011) -[2023-11-28 09:51:54,033][87424] Updated weights for policy 0, policy_version 368169 (0.0011) -[2023-11-28 09:51:54,411][87424] Updated weights for policy 0, policy_version 368179 (0.0009) -[2023-11-28 09:51:54,793][87424] Updated weights for policy 0, policy_version 368189 (0.0008) -[2023-11-28 09:51:56,050][87426] Updated weights for policy 1, policy_version 367810 (0.0010) -[2023-11-28 09:51:56,415][87426] Updated weights for policy 1, policy_version 367820 (0.0012) -[2023-11-28 09:51:56,799][87426] Updated weights for policy 1, policy_version 367830 (0.0012) -[2023-11-28 09:51:57,175][87426] Updated weights for policy 1, policy_version 367840 (0.0012) -[2023-11-28 09:51:57,273][87424] Updated weights for policy 0, policy_version 368199 (0.0010) -[2023-11-28 09:51:57,664][87424] Updated weights for policy 0, policy_version 368209 (0.0012) -[2023-11-28 09:51:58,048][87424] Updated weights for policy 0, policy_version 368219 (0.0012) -[2023-11-28 09:51:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 188432384. Throughput: 0: 2600.8, 1: 2705.8. Samples: 188444024. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:51:58,445][86177] Avg episode reward: [(0, '-586.770'), (1, '-606.090')] -[2023-11-28 09:51:59,128][87426] Updated weights for policy 1, policy_version 367850 (0.0010) -[2023-11-28 09:51:59,511][87426] Updated weights for policy 1, policy_version 367860 (0.0008) -[2023-11-28 09:51:59,891][87426] Updated weights for policy 1, policy_version 367870 (0.0008) -[2023-11-28 09:52:00,370][87424] Updated weights for policy 0, policy_version 368229 (0.0012) -[2023-11-28 09:52:00,747][87424] Updated weights for policy 0, policy_version 368239 (0.0009) -[2023-11-28 09:52:01,132][87424] Updated weights for policy 0, policy_version 368249 (0.0007) -[2023-11-28 09:52:01,869][87426] Updated weights for policy 1, policy_version 367880 (0.0008) -[2023-11-28 09:52:02,247][87426] Updated weights for policy 1, policy_version 367890 (0.0009) -[2023-11-28 09:52:02,621][87426] Updated weights for policy 1, policy_version 367900 (0.0010) -[2023-11-28 09:52:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188456960. Throughput: 0: 2618.8, 1: 2710.0. Samples: 188468576. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:52:03,445][86177] Avg episode reward: [(0, '-587.130'), (1, '-578.720')] -[2023-11-28 09:52:03,583][87424] Updated weights for policy 0, policy_version 368259 (0.0009) -[2023-11-28 09:52:03,974][87424] Updated weights for policy 0, policy_version 368269 (0.0012) -[2023-11-28 09:52:04,346][87424] Updated weights for policy 0, policy_version 368279 (0.0012) -[2023-11-28 09:52:04,726][87426] Updated weights for policy 1, policy_version 367910 (0.0012) -[2023-11-28 09:52:05,129][87426] Updated weights for policy 1, policy_version 367920 (0.0012) -[2023-11-28 09:52:05,498][87426] Updated weights for policy 1, policy_version 367930 (0.0012) -[2023-11-28 09:52:06,261][87424] Updated weights for policy 0, policy_version 368289 (0.0010) -[2023-11-28 09:52:06,647][87424] Updated weights for policy 0, policy_version 368299 (0.0010) -[2023-11-28 09:52:07,026][87424] Updated weights for policy 0, policy_version 368309 (0.0011) -[2023-11-28 09:52:07,336][87426] Updated weights for policy 1, policy_version 367940 (0.0012) -[2023-11-28 09:52:07,406][87424] Updated weights for policy 0, policy_version 368319 (0.0010) -[2023-11-28 09:52:07,710][87426] Updated weights for policy 1, policy_version 367950 (0.0011) -[2023-11-28 09:52:08,086][87426] Updated weights for policy 1, policy_version 367960 (0.0010) -[2023-11-28 09:52:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 188489728. Throughput: 0: 2651.1, 1: 2728.9. Samples: 188502192. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:52:08,445][86177] Avg episode reward: [(0, '-573.850'), (1, '-567.610')] -[2023-11-28 09:52:09,852][87424] Updated weights for policy 0, policy_version 368329 (0.0011) -[2023-11-28 09:52:10,015][87426] Updated weights for policy 1, policy_version 367970 (0.0008) -[2023-11-28 09:52:10,232][87424] Updated weights for policy 0, policy_version 368339 (0.0009) -[2023-11-28 09:52:10,380][87426] Updated weights for policy 1, policy_version 367980 (0.0011) -[2023-11-28 09:52:10,612][87424] Updated weights for policy 0, policy_version 368349 (0.0016) -[2023-11-28 09:52:10,757][87426] Updated weights for policy 1, policy_version 367990 (0.0012) -[2023-11-28 09:52:11,138][87426] Updated weights for policy 1, policy_version 368000 (0.0011) -[2023-11-28 09:52:13,278][87424] Updated weights for policy 0, policy_version 368359 (0.0011) -[2023-11-28 09:52:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188506112. Throughput: 0: 2629.8, 1: 2717.7. Samples: 188525484. Policy #0 lag: (min: 14.0, avg: 21.9, max: 46.0) -[2023-11-28 09:52:13,445][86177] Avg episode reward: [(0, '-551.530'), (1, '-604.360')] -[2023-11-28 09:52:13,600][87426] Updated weights for policy 1, policy_version 368010 (0.0007) -[2023-11-28 09:52:13,655][87424] Updated weights for policy 0, policy_version 368369 (0.0009) -[2023-11-28 09:52:13,989][87426] Updated weights for policy 1, policy_version 368020 (0.0007) -[2023-11-28 09:52:14,039][87424] Updated weights for policy 0, policy_version 368379 (0.0007) -[2023-11-28 09:52:14,369][87426] Updated weights for policy 1, policy_version 368030 (0.0008) -[2023-11-28 09:52:16,350][87424] Updated weights for policy 0, policy_version 368389 (0.0009) -[2023-11-28 09:52:16,627][87426] Updated weights for policy 1, policy_version 368040 (0.0009) -[2023-11-28 09:52:16,729][87424] Updated weights for policy 0, policy_version 368399 (0.0009) -[2023-11-28 09:52:17,003][87426] Updated weights for policy 1, policy_version 368050 (0.0008) -[2023-11-28 09:52:17,112][87424] Updated weights for policy 0, policy_version 368409 (0.0007) -[2023-11-28 09:52:17,389][87426] Updated weights for policy 1, policy_version 368060 (0.0008) -[2023-11-28 09:52:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 188538880. Throughput: 0: 2629.8, 1: 2709.4. Samples: 188549252. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:52:18,446][86177] Avg episode reward: [(0, '-549.750'), (1, '-595.690')] -[2023-11-28 09:52:18,460][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000368416_94314496.pth... -[2023-11-28 09:52:18,460][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000368064_94224384.pth... -[2023-11-28 09:52:18,497][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000365920_93675520.pth -[2023-11-28 09:52:18,497][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000365568_93585408.pth -[2023-11-28 09:52:18,502][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000368416_94314496.pth -[2023-11-28 09:52:18,502][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000368064_94224384.pth -[2023-11-28 09:52:19,391][87426] Updated weights for policy 1, policy_version 368070 (0.0010) -[2023-11-28 09:52:19,488][87424] Updated weights for policy 0, policy_version 368419 (0.0009) -[2023-11-28 09:52:19,771][87426] Updated weights for policy 1, policy_version 368080 (0.0012) -[2023-11-28 09:52:19,869][87424] Updated weights for policy 0, policy_version 368429 (0.0012) -[2023-11-28 09:52:20,146][87426] Updated weights for policy 1, policy_version 368090 (0.0012) -[2023-11-28 09:52:20,257][87424] Updated weights for policy 0, policy_version 368439 (0.0011) -[2023-11-28 09:52:22,134][87426] Updated weights for policy 1, policy_version 368100 (0.0011) -[2023-11-28 09:52:22,522][87426] Updated weights for policy 1, policy_version 368110 (0.0011) -[2023-11-28 09:52:22,839][87424] Updated weights for policy 0, policy_version 368449 (0.0009) -[2023-11-28 09:52:22,893][87426] Updated weights for policy 1, policy_version 368120 (0.0011) -[2023-11-28 09:52:23,219][87424] Updated weights for policy 0, policy_version 368459 (0.0011) -[2023-11-28 09:52:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 188563456. Throughput: 0: 2614.5, 1: 2700.0. Samples: 188580888. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:52:23,445][86177] Avg episode reward: [(0, '-552.010'), (1, '-653.820')] -[2023-11-28 09:52:23,597][87424] Updated weights for policy 0, policy_version 368469 (0.0012) -[2023-11-28 09:52:23,982][87424] Updated weights for policy 0, policy_version 368479 (0.0012) -[2023-11-28 09:52:24,992][87426] Updated weights for policy 1, policy_version 368130 (0.0012) -[2023-11-28 09:52:25,370][87426] Updated weights for policy 1, policy_version 368140 (0.0012) -[2023-11-28 09:52:25,760][87426] Updated weights for policy 1, policy_version 368150 (0.0012) -[2023-11-28 09:52:26,129][87424] Updated weights for policy 0, policy_version 368489 (0.0008) -[2023-11-28 09:52:26,132][87426] Updated weights for policy 1, policy_version 368160 (0.0010) -[2023-11-28 09:52:26,505][87424] Updated weights for policy 0, policy_version 368499 (0.0007) -[2023-11-28 09:52:26,891][87424] Updated weights for policy 0, policy_version 368509 (0.0008) -[2023-11-28 09:52:28,050][87426] Updated weights for policy 1, policy_version 368170 (0.0007) -[2023-11-28 09:52:28,436][87426] Updated weights for policy 1, policy_version 368180 (0.0007) -[2023-11-28 09:52:28,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188588032. Throughput: 0: 2610.3, 1: 2737.6. Samples: 188605560. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:52:28,445][86177] Avg episode reward: [(0, '-542.370'), (1, '-667.330')] -[2023-11-28 09:52:28,585][87424] Updated weights for policy 0, policy_version 368519 (0.0010) -[2023-11-28 09:52:28,812][87426] Updated weights for policy 1, policy_version 368190 (0.0007) -[2023-11-28 09:52:28,970][87424] Updated weights for policy 0, policy_version 368529 (0.0011) -[2023-11-28 09:52:29,354][87424] Updated weights for policy 0, policy_version 368539 (0.0012) -[2023-11-28 09:52:31,296][87424] Updated weights for policy 0, policy_version 368549 (0.0009) -[2023-11-28 09:52:31,308][87426] Updated weights for policy 1, policy_version 368200 (0.0008) -[2023-11-28 09:52:31,673][87424] Updated weights for policy 0, policy_version 368559 (0.0010) -[2023-11-28 09:52:31,684][87426] Updated weights for policy 1, policy_version 368210 (0.0008) -[2023-11-28 09:52:32,057][87424] Updated weights for policy 0, policy_version 368569 (0.0011) -[2023-11-28 09:52:32,061][87426] Updated weights for policy 1, policy_version 368220 (0.0010) -[2023-11-28 09:52:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 188620800. Throughput: 0: 2614.3, 1: 2721.4. Samples: 188629236. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:52:33,445][86177] Avg episode reward: [(0, '-550.480'), (1, '-661.540')] -[2023-11-28 09:52:34,270][87424] Updated weights for policy 0, policy_version 368579 (0.0011) -[2023-11-28 09:52:34,658][87424] Updated weights for policy 0, policy_version 368589 (0.0010) -[2023-11-28 09:52:34,670][87426] Updated weights for policy 1, policy_version 368230 (0.0011) -[2023-11-28 09:52:35,029][87424] Updated weights for policy 0, policy_version 368599 (0.0008) -[2023-11-28 09:52:35,049][87426] Updated weights for policy 1, policy_version 368240 (0.0012) -[2023-11-28 09:52:35,426][87426] Updated weights for policy 1, policy_version 368250 (0.0012) -[2023-11-28 09:52:37,106][87424] Updated weights for policy 0, policy_version 368609 (0.0012) -[2023-11-28 09:52:37,256][87426] Updated weights for policy 1, policy_version 368260 (0.0012) -[2023-11-28 09:52:37,487][87424] Updated weights for policy 0, policy_version 368619 (0.0010) -[2023-11-28 09:52:37,640][87426] Updated weights for policy 1, policy_version 368270 (0.0008) -[2023-11-28 09:52:37,876][87424] Updated weights for policy 0, policy_version 368629 (0.0008) -[2023-11-28 09:52:38,022][87426] Updated weights for policy 1, policy_version 368280 (0.0010) -[2023-11-28 09:52:38,255][87424] Updated weights for policy 0, policy_version 368639 (0.0009) -[2023-11-28 09:52:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 188653568. Throughput: 0: 2657.2, 1: 2756.1. Samples: 188663328. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:52:38,445][86177] Avg episode reward: [(0, '-555.700'), (1, '-621.200')] -[2023-11-28 09:52:39,810][87426] Updated weights for policy 1, policy_version 368290 (0.0012) -[2023-11-28 09:52:40,184][87426] Updated weights for policy 1, policy_version 368300 (0.0012) -[2023-11-28 09:52:40,562][87426] Updated weights for policy 1, policy_version 368310 (0.0011) -[2023-11-28 09:52:40,623][87424] Updated weights for policy 0, policy_version 368649 (0.0011) -[2023-11-28 09:52:40,942][87426] Updated weights for policy 1, policy_version 368320 (0.0008) -[2023-11-28 09:52:41,000][87424] Updated weights for policy 0, policy_version 368659 (0.0012) -[2023-11-28 09:52:41,375][87424] Updated weights for policy 0, policy_version 368669 (0.0012) -[2023-11-28 09:52:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 188669952. Throughput: 0: 2651.0, 1: 2740.4. Samples: 188686636. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:52:43,445][86177] Avg episode reward: [(0, '-589.900'), (1, '-603.880')] -[2023-11-28 09:52:43,512][87426] Updated weights for policy 1, policy_version 368330 (0.0008) -[2023-11-28 09:52:43,734][87424] Updated weights for policy 0, policy_version 368679 (0.0012) -[2023-11-28 09:52:43,891][87426] Updated weights for policy 1, policy_version 368340 (0.0007) -[2023-11-28 09:52:44,103][87424] Updated weights for policy 0, policy_version 368689 (0.0011) -[2023-11-28 09:52:44,274][87426] Updated weights for policy 1, policy_version 368350 (0.0011) -[2023-11-28 09:52:44,485][87424] Updated weights for policy 0, policy_version 368699 (0.0009) -[2023-11-28 09:52:46,600][87424] Updated weights for policy 0, policy_version 368709 (0.0010) -[2023-11-28 09:52:46,667][87426] Updated weights for policy 1, policy_version 368360 (0.0011) -[2023-11-28 09:52:46,979][87424] Updated weights for policy 0, policy_version 368719 (0.0012) -[2023-11-28 09:52:47,050][87426] Updated weights for policy 1, policy_version 368370 (0.0010) -[2023-11-28 09:52:47,356][87424] Updated weights for policy 0, policy_version 368729 (0.0012) -[2023-11-28 09:52:47,420][87426] Updated weights for policy 1, policy_version 368380 (0.0010) -[2023-11-28 09:52:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 188702720. Throughput: 0: 2645.9, 1: 2737.6. Samples: 188710832. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:52:48,445][86177] Avg episode reward: [(0, '-596.360'), (1, '-572.630')] -[2023-11-28 09:52:49,444][87424] Updated weights for policy 0, policy_version 368739 (0.0012) -[2023-11-28 09:52:49,645][87426] Updated weights for policy 1, policy_version 368390 (0.0010) -[2023-11-28 09:52:49,826][87424] Updated weights for policy 0, policy_version 368749 (0.0011) -[2023-11-28 09:52:50,021][87426] Updated weights for policy 1, policy_version 368400 (0.0010) -[2023-11-28 09:52:50,207][87424] Updated weights for policy 0, policy_version 368759 (0.0011) -[2023-11-28 09:52:50,385][87426] Updated weights for policy 1, policy_version 368410 (0.0011) -[2023-11-28 09:52:52,546][87424] Updated weights for policy 0, policy_version 368769 (0.0010) -[2023-11-28 09:52:52,650][87426] Updated weights for policy 1, policy_version 368420 (0.0012) -[2023-11-28 09:52:52,923][87424] Updated weights for policy 0, policy_version 368779 (0.0009) -[2023-11-28 09:52:53,023][87426] Updated weights for policy 1, policy_version 368430 (0.0011) -[2023-11-28 09:52:53,304][87424] Updated weights for policy 0, policy_version 368789 (0.0009) -[2023-11-28 09:52:53,402][87426] Updated weights for policy 1, policy_version 368440 (0.0011) -[2023-11-28 09:52:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 188719104. Throughput: 0: 2643.2, 1: 2706.4. Samples: 188742924. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:52:53,445][86177] Avg episode reward: [(0, '-593.150'), (1, '-550.110')] -[2023-11-28 09:52:53,687][87424] Updated weights for policy 0, policy_version 368799 (0.0010) -[2023-11-28 09:52:55,559][87426] Updated weights for policy 1, policy_version 368450 (0.0010) -[2023-11-28 09:52:55,940][87426] Updated weights for policy 1, policy_version 368460 (0.0010) -[2023-11-28 09:52:56,028][87424] Updated weights for policy 0, policy_version 368809 (0.0008) -[2023-11-28 09:52:56,316][87426] Updated weights for policy 1, policy_version 368470 (0.0008) -[2023-11-28 09:52:56,406][87424] Updated weights for policy 0, policy_version 368819 (0.0008) -[2023-11-28 09:52:56,690][87426] Updated weights for policy 1, policy_version 368480 (0.0009) -[2023-11-28 09:52:56,790][87424] Updated weights for policy 0, policy_version 368829 (0.0008) -[2023-11-28 09:52:58,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188751872. Throughput: 0: 2655.2, 1: 2724.0. Samples: 188767548. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:52:58,446][86177] Avg episode reward: [(0, '-583.480'), (1, '-563.960')] -[2023-11-28 09:52:58,901][87424] Updated weights for policy 0, policy_version 368839 (0.0009) -[2023-11-28 09:52:58,946][87426] Updated weights for policy 1, policy_version 368490 (0.0011) -[2023-11-28 09:52:59,274][87424] Updated weights for policy 0, policy_version 368849 (0.0008) -[2023-11-28 09:52:59,323][87426] Updated weights for policy 1, policy_version 368500 (0.0007) -[2023-11-28 09:52:59,658][87424] Updated weights for policy 0, policy_version 368859 (0.0009) -[2023-11-28 09:52:59,707][87426] Updated weights for policy 1, policy_version 368510 (0.0009) -[2023-11-28 09:53:01,543][87426] Updated weights for policy 1, policy_version 368520 (0.0012) -[2023-11-28 09:53:01,931][87426] Updated weights for policy 1, policy_version 368530 (0.0011) -[2023-11-28 09:53:02,037][87424] Updated weights for policy 0, policy_version 368869 (0.0011) -[2023-11-28 09:53:02,300][87426] Updated weights for policy 1, policy_version 368540 (0.0011) -[2023-11-28 09:53:02,417][87424] Updated weights for policy 0, policy_version 368879 (0.0009) -[2023-11-28 09:53:02,789][87424] Updated weights for policy 0, policy_version 368889 (0.0008) -[2023-11-28 09:53:03,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 188784640. Throughput: 0: 2690.0, 1: 2730.4. Samples: 188793168. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:53:03,445][86177] Avg episode reward: [(0, '-543.370'), (1, '-566.910')] -[2023-11-28 09:53:04,496][87426] Updated weights for policy 1, policy_version 368550 (0.0010) -[2023-11-28 09:53:04,875][87426] Updated weights for policy 1, policy_version 368560 (0.0008) -[2023-11-28 09:53:05,179][87424] Updated weights for policy 0, policy_version 368899 (0.0008) -[2023-11-28 09:53:05,262][87426] Updated weights for policy 1, policy_version 368570 (0.0009) -[2023-11-28 09:53:05,565][87424] Updated weights for policy 0, policy_version 368909 (0.0008) -[2023-11-28 09:53:05,956][87424] Updated weights for policy 0, policy_version 368919 (0.0008) -[2023-11-28 09:53:07,534][87426] Updated weights for policy 1, policy_version 368580 (0.0011) -[2023-11-28 09:53:07,911][87426] Updated weights for policy 1, policy_version 368590 (0.0007) -[2023-11-28 09:53:08,124][87424] Updated weights for policy 0, policy_version 368929 (0.0010) -[2023-11-28 09:53:08,290][87426] Updated weights for policy 1, policy_version 368600 (0.0007) -[2023-11-28 09:53:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 188801024. Throughput: 0: 2696.9, 1: 2738.9. Samples: 188825500. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:53:08,445][86177] Avg episode reward: [(0, '-535.020'), (1, '-568.560')] -[2023-11-28 09:53:08,504][87424] Updated weights for policy 0, policy_version 368939 (0.0008) -[2023-11-28 09:53:08,892][87424] Updated weights for policy 0, policy_version 368949 (0.0008) -[2023-11-28 09:53:09,270][87424] Updated weights for policy 0, policy_version 368959 (0.0009) -[2023-11-28 09:53:10,770][87426] Updated weights for policy 1, policy_version 368610 (0.0009) -[2023-11-28 09:53:11,152][87426] Updated weights for policy 1, policy_version 368620 (0.0011) -[2023-11-28 09:53:11,528][87426] Updated weights for policy 1, policy_version 368630 (0.0012) -[2023-11-28 09:53:11,702][87424] Updated weights for policy 0, policy_version 368969 (0.0008) -[2023-11-28 09:53:11,919][87426] Updated weights for policy 1, policy_version 368640 (0.0010) -[2023-11-28 09:53:12,074][87424] Updated weights for policy 0, policy_version 368979 (0.0010) -[2023-11-28 09:53:12,460][87424] Updated weights for policy 0, policy_version 368989 (0.0010) -[2023-11-28 09:53:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 188833792. Throughput: 0: 2698.1, 1: 2702.3. Samples: 188848580. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:53:13,445][86177] Avg episode reward: [(0, '-528.890'), (1, '-572.740')] -[2023-11-28 09:53:13,834][87426] Updated weights for policy 1, policy_version 368650 (0.0011) -[2023-11-28 09:53:14,216][87426] Updated weights for policy 1, policy_version 368660 (0.0011) -[2023-11-28 09:53:14,593][87426] Updated weights for policy 1, policy_version 368670 (0.0012) -[2023-11-28 09:53:14,770][87424] Updated weights for policy 0, policy_version 368999 (0.0011) -[2023-11-28 09:53:15,156][87424] Updated weights for policy 0, policy_version 369009 (0.0012) -[2023-11-28 09:53:15,530][87424] Updated weights for policy 0, policy_version 369019 (0.0009) -[2023-11-28 09:53:16,636][87426] Updated weights for policy 1, policy_version 368680 (0.0010) -[2023-11-28 09:53:17,015][87426] Updated weights for policy 1, policy_version 368690 (0.0011) -[2023-11-28 09:53:17,395][87426] Updated weights for policy 1, policy_version 368700 (0.0011) -[2023-11-28 09:53:17,854][87424] Updated weights for policy 0, policy_version 369029 (0.0007) -[2023-11-28 09:53:18,231][87424] Updated weights for policy 0, policy_version 369039 (0.0011) -[2023-11-28 09:53:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188858368. Throughput: 0: 2681.2, 1: 2715.1. Samples: 188872068. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:53:18,445][86177] Avg episode reward: [(0, '-529.920'), (1, '-573.960')] -[2023-11-28 09:53:18,616][87424] Updated weights for policy 0, policy_version 369049 (0.0008) -[2023-11-28 09:53:19,658][87426] Updated weights for policy 1, policy_version 368710 (0.0010) -[2023-11-28 09:53:20,030][87426] Updated weights for policy 1, policy_version 368720 (0.0010) -[2023-11-28 09:53:20,412][87426] Updated weights for policy 1, policy_version 368730 (0.0010) -[2023-11-28 09:53:20,958][87424] Updated weights for policy 0, policy_version 369059 (0.0009) -[2023-11-28 09:53:21,338][87424] Updated weights for policy 0, policy_version 369069 (0.0009) -[2023-11-28 09:53:21,718][87424] Updated weights for policy 0, policy_version 369079 (0.0012) -[2023-11-28 09:53:22,955][87426] Updated weights for policy 1, policy_version 368740 (0.0011) -[2023-11-28 09:53:23,330][87426] Updated weights for policy 1, policy_version 368750 (0.0010) -[2023-11-28 09:53:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188882944. Throughput: 0: 2631.0, 1: 2682.2. Samples: 188902424. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:53:23,445][86177] Avg episode reward: [(0, '-532.020'), (1, '-549.740')] -[2023-11-28 09:53:23,703][87426] Updated weights for policy 1, policy_version 368760 (0.0008) -[2023-11-28 09:53:24,152][87424] Updated weights for policy 0, policy_version 369089 (0.0012) -[2023-11-28 09:53:24,534][87424] Updated weights for policy 0, policy_version 369099 (0.0012) -[2023-11-28 09:53:24,921][87424] Updated weights for policy 0, policy_version 369109 (0.0009) -[2023-11-28 09:53:25,297][87424] Updated weights for policy 0, policy_version 369119 (0.0009) -[2023-11-28 09:53:25,688][87426] Updated weights for policy 1, policy_version 368770 (0.0008) -[2023-11-28 09:53:26,060][87426] Updated weights for policy 1, policy_version 368780 (0.0007) -[2023-11-28 09:53:26,432][87426] Updated weights for policy 1, policy_version 368790 (0.0007) -[2023-11-28 09:53:26,812][87426] Updated weights for policy 1, policy_version 368800 (0.0009) -[2023-11-28 09:53:27,159][87424] Updated weights for policy 0, policy_version 369129 (0.0011) -[2023-11-28 09:53:27,542][87424] Updated weights for policy 0, policy_version 369139 (0.0012) -[2023-11-28 09:53:27,929][87424] Updated weights for policy 0, policy_version 369149 (0.0011) -[2023-11-28 09:53:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 188915712. Throughput: 0: 2640.4, 1: 2687.9. Samples: 188926412. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:53:28,445][86177] Avg episode reward: [(0, '-535.610'), (1, '-560.330')] -[2023-11-28 09:53:29,236][87426] Updated weights for policy 1, policy_version 368810 (0.0007) -[2023-11-28 09:53:29,614][87426] Updated weights for policy 1, policy_version 368820 (0.0007) -[2023-11-28 09:53:29,991][87426] Updated weights for policy 1, policy_version 368830 (0.0011) -[2023-11-28 09:53:30,477][87424] Updated weights for policy 0, policy_version 369159 (0.0011) -[2023-11-28 09:53:30,859][87424] Updated weights for policy 0, policy_version 369169 (0.0012) -[2023-11-28 09:53:31,241][87424] Updated weights for policy 0, policy_version 369179 (0.0011) -[2023-11-28 09:53:32,007][87426] Updated weights for policy 1, policy_version 368840 (0.0014) -[2023-11-28 09:53:32,390][87426] Updated weights for policy 1, policy_version 368850 (0.0012) -[2023-11-28 09:53:32,756][87426] Updated weights for policy 1, policy_version 368860 (0.0012) -[2023-11-28 09:53:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188940288. Throughput: 0: 2634.7, 1: 2689.4. Samples: 188950416. Policy #0 lag: (min: 31.0, avg: 37.5, max: 63.0) -[2023-11-28 09:53:33,445][86177] Avg episode reward: [(0, '-558.910'), (1, '-553.590')] -[2023-11-28 09:53:33,586][87424] Updated weights for policy 0, policy_version 369189 (0.0010) -[2023-11-28 09:53:33,984][87424] Updated weights for policy 0, policy_version 369199 (0.0010) -[2023-11-28 09:53:34,354][87424] Updated weights for policy 0, policy_version 369209 (0.0009) -[2023-11-28 09:53:34,767][87426] Updated weights for policy 1, policy_version 368870 (0.0011) -[2023-11-28 09:53:35,150][87426] Updated weights for policy 1, policy_version 368880 (0.0008) -[2023-11-28 09:53:35,523][87426] Updated weights for policy 1, policy_version 368890 (0.0007) -[2023-11-28 09:53:36,570][87424] Updated weights for policy 0, policy_version 369219 (0.0012) -[2023-11-28 09:53:36,948][87424] Updated weights for policy 0, policy_version 369229 (0.0012) -[2023-11-28 09:53:37,336][87424] Updated weights for policy 0, policy_version 369239 (0.0012) -[2023-11-28 09:53:37,815][87426] Updated weights for policy 1, policy_version 368900 (0.0009) -[2023-11-28 09:53:38,197][87426] Updated weights for policy 1, policy_version 368910 (0.0011) -[2023-11-28 09:53:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 188964864. Throughput: 0: 2622.9, 1: 2707.9. Samples: 188982812. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:53:38,445][86177] Avg episode reward: [(0, '-568.400'), (1, '-562.240')] -[2023-11-28 09:53:38,575][87426] Updated weights for policy 1, policy_version 368920 (0.0011) -[2023-11-28 09:53:39,473][87424] Updated weights for policy 0, policy_version 369249 (0.0012) -[2023-11-28 09:53:39,852][87424] Updated weights for policy 0, policy_version 369259 (0.0012) -[2023-11-28 09:53:40,223][87424] Updated weights for policy 0, policy_version 369269 (0.0009) -[2023-11-28 09:53:40,611][87424] Updated weights for policy 0, policy_version 369279 (0.0011) -[2023-11-28 09:53:41,140][87426] Updated weights for policy 1, policy_version 368930 (0.0012) -[2023-11-28 09:53:41,509][87426] Updated weights for policy 1, policy_version 368940 (0.0012) -[2023-11-28 09:53:41,897][87426] Updated weights for policy 1, policy_version 368950 (0.0010) -[2023-11-28 09:53:42,273][87426] Updated weights for policy 1, policy_version 368960 (0.0012) -[2023-11-28 09:53:42,651][87424] Updated weights for policy 0, policy_version 369289 (0.0011) -[2023-11-28 09:53:43,046][87424] Updated weights for policy 0, policy_version 369299 (0.0021) -[2023-11-28 09:53:43,427][87424] Updated weights for policy 0, policy_version 369309 (0.0012) -[2023-11-28 09:53:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 188989440. Throughput: 0: 2641.0, 1: 2685.8. Samples: 189007252. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:53:43,445][86177] Avg episode reward: [(0, '-568.260'), (1, '-581.620')] -[2023-11-28 09:53:44,154][87426] Updated weights for policy 1, policy_version 368970 (0.0007) -[2023-11-28 09:53:44,532][87426] Updated weights for policy 1, policy_version 368980 (0.0007) -[2023-11-28 09:53:44,909][87426] Updated weights for policy 1, policy_version 368990 (0.0008) -[2023-11-28 09:53:46,012][87424] Updated weights for policy 0, policy_version 369319 (0.0011) -[2023-11-28 09:53:46,399][87424] Updated weights for policy 0, policy_version 369329 (0.0011) -[2023-11-28 09:53:46,782][87424] Updated weights for policy 0, policy_version 369339 (0.0012) -[2023-11-28 09:53:47,448][87426] Updated weights for policy 1, policy_version 369000 (0.0010) -[2023-11-28 09:53:47,828][87426] Updated weights for policy 1, policy_version 369010 (0.0007) -[2023-11-28 09:53:48,212][87426] Updated weights for policy 1, policy_version 369020 (0.0007) -[2023-11-28 09:53:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189022208. Throughput: 0: 2608.3, 1: 2678.8. Samples: 189031088. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:53:48,446][86177] Avg episode reward: [(0, '-576.850'), (1, '-597.480')] -[2023-11-28 09:53:48,468][87424] Updated weights for policy 0, policy_version 369349 (0.0012) -[2023-11-28 09:53:48,864][87424] Updated weights for policy 0, policy_version 369359 (0.0012) -[2023-11-28 09:53:49,239][87424] Updated weights for policy 0, policy_version 369369 (0.0010) -[2023-11-28 09:53:50,169][87426] Updated weights for policy 1, policy_version 369030 (0.0010) -[2023-11-28 09:53:50,549][87426] Updated weights for policy 1, policy_version 369040 (0.0011) -[2023-11-28 09:53:50,927][87426] Updated weights for policy 1, policy_version 369050 (0.0012) -[2023-11-28 09:53:51,462][87424] Updated weights for policy 0, policy_version 369379 (0.0009) -[2023-11-28 09:53:51,860][87424] Updated weights for policy 0, policy_version 369389 (0.0012) -[2023-11-28 09:53:52,244][87424] Updated weights for policy 0, policy_version 369399 (0.0011) -[2023-11-28 09:53:53,063][87426] Updated weights for policy 1, policy_version 369060 (0.0011) -[2023-11-28 09:53:53,440][87426] Updated weights for policy 1, policy_version 369070 (0.0011) -[2023-11-28 09:53:53,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 189046784. Throughput: 0: 2610.9, 1: 2662.0. Samples: 189062784. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:53:53,445][86177] Avg episode reward: [(0, '-557.290'), (1, '-587.640')] -[2023-11-28 09:53:53,821][87426] Updated weights for policy 1, policy_version 369080 (0.0010) -[2023-11-28 09:53:54,421][87424] Updated weights for policy 0, policy_version 369409 (0.0010) -[2023-11-28 09:53:54,808][87424] Updated weights for policy 0, policy_version 369419 (0.0011) -[2023-11-28 09:53:55,201][87424] Updated weights for policy 0, policy_version 369429 (0.0010) -[2023-11-28 09:53:55,575][87424] Updated weights for policy 0, policy_version 369439 (0.0009) -[2023-11-28 09:53:56,280][87426] Updated weights for policy 1, policy_version 369090 (0.0011) -[2023-11-28 09:53:56,652][87426] Updated weights for policy 1, policy_version 369100 (0.0010) -[2023-11-28 09:53:57,031][87426] Updated weights for policy 1, policy_version 369110 (0.0008) -[2023-11-28 09:53:57,403][87426] Updated weights for policy 1, policy_version 369120 (0.0007) -[2023-11-28 09:53:57,558][87424] Updated weights for policy 0, policy_version 369449 (0.0010) -[2023-11-28 09:53:57,940][87424] Updated weights for policy 0, policy_version 369459 (0.0012) -[2023-11-28 09:53:58,316][87424] Updated weights for policy 0, policy_version 369469 (0.0011) -[2023-11-28 09:53:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 189079552. Throughput: 0: 2614.7, 1: 2670.2. Samples: 189086404. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:53:58,445][86177] Avg episode reward: [(0, '-555.540'), (1, '-577.650')] -[2023-11-28 09:53:59,577][87426] Updated weights for policy 1, policy_version 369130 (0.0009) -[2023-11-28 09:53:59,952][87426] Updated weights for policy 1, policy_version 369140 (0.0009) -[2023-11-28 09:54:00,331][87426] Updated weights for policy 1, policy_version 369150 (0.0009) -[2023-11-28 09:54:00,621][87424] Updated weights for policy 0, policy_version 369479 (0.0010) -[2023-11-28 09:54:01,005][87424] Updated weights for policy 0, policy_version 369489 (0.0008) -[2023-11-28 09:54:01,375][87424] Updated weights for policy 0, policy_version 369499 (0.0007) -[2023-11-28 09:54:02,743][87426] Updated weights for policy 1, policy_version 369160 (0.0008) -[2023-11-28 09:54:03,121][87426] Updated weights for policy 1, policy_version 369170 (0.0008) -[2023-11-28 09:54:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 189095936. Throughput: 0: 2632.4, 1: 2664.8. Samples: 189110444. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:03,445][86177] Avg episode reward: [(0, '-549.270'), (1, '-598.120')] -[2023-11-28 09:54:03,503][87426] Updated weights for policy 1, policy_version 369180 (0.0008) -[2023-11-28 09:54:03,772][87424] Updated weights for policy 0, policy_version 369509 (0.0008) -[2023-11-28 09:54:04,150][87424] Updated weights for policy 0, policy_version 369519 (0.0007) -[2023-11-28 09:54:04,531][87424] Updated weights for policy 0, policy_version 369529 (0.0008) -[2023-11-28 09:54:06,047][87426] Updated weights for policy 1, policy_version 369190 (0.0007) -[2023-11-28 09:54:06,420][87426] Updated weights for policy 1, policy_version 369200 (0.0008) -[2023-11-28 09:54:06,623][87424] Updated weights for policy 0, policy_version 369539 (0.0009) -[2023-11-28 09:54:06,797][87426] Updated weights for policy 1, policy_version 369210 (0.0010) -[2023-11-28 09:54:07,004][87424] Updated weights for policy 0, policy_version 369549 (0.0012) -[2023-11-28 09:54:07,391][87424] Updated weights for policy 0, policy_version 369559 (0.0011) -[2023-11-28 09:54:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 189128704. Throughput: 0: 2667.8, 1: 2664.1. Samples: 189142360. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:08,445][86177] Avg episode reward: [(0, '-541.350'), (1, '-579.980')] -[2023-11-28 09:54:09,100][87426] Updated weights for policy 1, policy_version 369220 (0.0010) -[2023-11-28 09:54:09,474][87426] Updated weights for policy 1, policy_version 369230 (0.0009) -[2023-11-28 09:54:09,861][87426] Updated weights for policy 1, policy_version 369240 (0.0009) -[2023-11-28 09:54:09,895][87424] Updated weights for policy 0, policy_version 369569 (0.0008) -[2023-11-28 09:54:10,272][87424] Updated weights for policy 0, policy_version 369579 (0.0012) -[2023-11-28 09:54:10,659][87424] Updated weights for policy 0, policy_version 369589 (0.0010) -[2023-11-28 09:54:11,050][87424] Updated weights for policy 0, policy_version 369599 (0.0012) -[2023-11-28 09:54:11,801][87426] Updated weights for policy 1, policy_version 369250 (0.0010) -[2023-11-28 09:54:12,177][87426] Updated weights for policy 1, policy_version 369260 (0.0011) -[2023-11-28 09:54:12,557][87426] Updated weights for policy 1, policy_version 369270 (0.0010) -[2023-11-28 09:54:12,934][87426] Updated weights for policy 1, policy_version 369280 (0.0010) -[2023-11-28 09:54:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189153280. Throughput: 0: 2680.6, 1: 2664.2. Samples: 189166928. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:13,445][86177] Avg episode reward: [(0, '-540.090'), (1, '-578.860')] -[2023-11-28 09:54:13,634][87424] Updated weights for policy 0, policy_version 369609 (0.0012) -[2023-11-28 09:54:14,013][87424] Updated weights for policy 0, policy_version 369619 (0.0012) -[2023-11-28 09:54:14,393][87424] Updated weights for policy 0, policy_version 369629 (0.0012) -[2023-11-28 09:54:15,400][87426] Updated weights for policy 1, policy_version 369290 (0.0012) -[2023-11-28 09:54:15,775][87426] Updated weights for policy 1, policy_version 369300 (0.0012) -[2023-11-28 09:54:16,154][87426] Updated weights for policy 1, policy_version 369310 (0.0012) -[2023-11-28 09:54:16,777][87424] Updated weights for policy 0, policy_version 369639 (0.0012) -[2023-11-28 09:54:17,149][87424] Updated weights for policy 0, policy_version 369649 (0.0011) -[2023-11-28 09:54:17,525][87424] Updated weights for policy 0, policy_version 369659 (0.0012) -[2023-11-28 09:54:18,339][87426] Updated weights for policy 1, policy_version 369320 (0.0011) -[2023-11-28 09:54:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189177856. Throughput: 0: 2687.2, 1: 2647.9. Samples: 189190496. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:18,445][86177] Avg episode reward: [(0, '-539.940'), (1, '-576.330')] -[2023-11-28 09:54:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000369664_94633984.pth... -[2023-11-28 09:54:18,505][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000367200_94003200.pth -[2023-11-28 09:54:18,725][87426] Updated weights for policy 1, policy_version 369330 (0.0012) -[2023-11-28 09:54:19,110][87426] Updated weights for policy 1, policy_version 369340 (0.0010) -[2023-11-28 09:54:19,206][87424] Updated weights for policy 0, policy_version 369669 (0.0012) -[2023-11-28 09:54:19,249][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000369344_94552064.pth... -[2023-11-28 09:54:19,291][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000366816_93904896.pth -[2023-11-28 09:54:19,586][87424] Updated weights for policy 0, policy_version 369679 (0.0012) -[2023-11-28 09:54:19,965][87424] Updated weights for policy 0, policy_version 369689 (0.0012) -[2023-11-28 09:54:21,383][87426] Updated weights for policy 1, policy_version 369350 (0.0008) -[2023-11-28 09:54:21,763][87426] Updated weights for policy 1, policy_version 369360 (0.0008) -[2023-11-28 09:54:22,158][87426] Updated weights for policy 1, policy_version 369370 (0.0010) -[2023-11-28 09:54:22,542][87424] Updated weights for policy 0, policy_version 369699 (0.0011) -[2023-11-28 09:54:22,915][87424] Updated weights for policy 0, policy_version 369709 (0.0011) -[2023-11-28 09:54:23,303][87424] Updated weights for policy 0, policy_version 369719 (0.0012) -[2023-11-28 09:54:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189202432. Throughput: 0: 2689.5, 1: 2651.6. Samples: 189223160. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:23,445][86177] Avg episode reward: [(0, '-543.490'), (1, '-548.370')] -[2023-11-28 09:54:24,189][87426] Updated weights for policy 1, policy_version 369380 (0.0011) -[2023-11-28 09:54:24,565][87426] Updated weights for policy 1, policy_version 369390 (0.0012) -[2023-11-28 09:54:24,957][87426] Updated weights for policy 1, policy_version 369400 (0.0012) -[2023-11-28 09:54:25,553][87424] Updated weights for policy 0, policy_version 369729 (0.0012) -[2023-11-28 09:54:25,937][87424] Updated weights for policy 0, policy_version 369739 (0.0012) -[2023-11-28 09:54:26,320][87424] Updated weights for policy 0, policy_version 369749 (0.0012) -[2023-11-28 09:54:26,696][87424] Updated weights for policy 0, policy_version 369759 (0.0012) -[2023-11-28 09:54:26,926][87426] Updated weights for policy 1, policy_version 369410 (0.0011) -[2023-11-28 09:54:27,298][87426] Updated weights for policy 1, policy_version 369420 (0.0007) -[2023-11-28 09:54:27,675][87426] Updated weights for policy 1, policy_version 369430 (0.0007) -[2023-11-28 09:54:28,049][87426] Updated weights for policy 1, policy_version 369440 (0.0007) -[2023-11-28 09:54:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189235200. Throughput: 0: 2679.4, 1: 2688.3. Samples: 189248796. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:28,445][86177] Avg episode reward: [(0, '-549.280'), (1, '-554.990')] -[2023-11-28 09:54:28,813][87424] Updated weights for policy 0, policy_version 369769 (0.0012) -[2023-11-28 09:54:29,198][87424] Updated weights for policy 0, policy_version 369779 (0.0011) -[2023-11-28 09:54:29,580][87424] Updated weights for policy 0, policy_version 369789 (0.0012) -[2023-11-28 09:54:29,948][87426] Updated weights for policy 1, policy_version 369450 (0.0011) -[2023-11-28 09:54:30,327][87426] Updated weights for policy 1, policy_version 369460 (0.0010) -[2023-11-28 09:54:30,705][87426] Updated weights for policy 1, policy_version 369470 (0.0012) -[2023-11-28 09:54:31,811][87424] Updated weights for policy 0, policy_version 369799 (0.0012) -[2023-11-28 09:54:32,205][87424] Updated weights for policy 0, policy_version 369809 (0.0012) -[2023-11-28 09:54:32,598][87424] Updated weights for policy 0, policy_version 369819 (0.0012) -[2023-11-28 09:54:32,701][87426] Updated weights for policy 1, policy_version 369480 (0.0012) -[2023-11-28 09:54:33,080][87426] Updated weights for policy 1, policy_version 369490 (0.0012) -[2023-11-28 09:54:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189259776. Throughput: 0: 2693.3, 1: 2697.7. Samples: 189273684. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:33,445][86177] Avg episode reward: [(0, '-553.280'), (1, '-638.920')] -[2023-11-28 09:54:33,471][87426] Updated weights for policy 1, policy_version 369500 (0.0012) -[2023-11-28 09:54:34,828][87424] Updated weights for policy 0, policy_version 369829 (0.0011) -[2023-11-28 09:54:35,214][87424] Updated weights for policy 0, policy_version 369839 (0.0009) -[2023-11-28 09:54:35,556][87426] Updated weights for policy 1, policy_version 369510 (0.0012) -[2023-11-28 09:54:35,597][87424] Updated weights for policy 0, policy_version 369849 (0.0010) -[2023-11-28 09:54:35,935][87426] Updated weights for policy 1, policy_version 369520 (0.0012) -[2023-11-28 09:54:36,318][87426] Updated weights for policy 1, policy_version 369530 (0.0012) -[2023-11-28 09:54:37,617][87424] Updated weights for policy 0, policy_version 369859 (0.0011) -[2023-11-28 09:54:38,001][87424] Updated weights for policy 0, policy_version 369869 (0.0012) -[2023-11-28 09:54:38,379][87424] Updated weights for policy 0, policy_version 369879 (0.0012) -[2023-11-28 09:54:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189284352. Throughput: 0: 2701.0, 1: 2724.7. Samples: 189306940. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:38,445][86177] Avg episode reward: [(0, '-549.990'), (1, '-648.580')] -[2023-11-28 09:54:38,590][87426] Updated weights for policy 1, policy_version 369540 (0.0011) -[2023-11-28 09:54:38,968][87426] Updated weights for policy 1, policy_version 369550 (0.0011) -[2023-11-28 09:54:39,352][87426] Updated weights for policy 1, policy_version 369560 (0.0008) -[2023-11-28 09:54:40,863][87424] Updated weights for policy 0, policy_version 369889 (0.0011) -[2023-11-28 09:54:41,247][87424] Updated weights for policy 0, policy_version 369899 (0.0010) -[2023-11-28 09:54:41,638][87424] Updated weights for policy 0, policy_version 369909 (0.0009) -[2023-11-28 09:54:41,838][87426] Updated weights for policy 1, policy_version 369570 (0.0008) -[2023-11-28 09:54:42,008][87424] Updated weights for policy 0, policy_version 369919 (0.0011) -[2023-11-28 09:54:42,206][87426] Updated weights for policy 1, policy_version 369580 (0.0011) -[2023-11-28 09:54:42,586][87426] Updated weights for policy 1, policy_version 369590 (0.0012) -[2023-11-28 09:54:42,963][87426] Updated weights for policy 1, policy_version 369600 (0.0012) -[2023-11-28 09:54:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 189317120. Throughput: 0: 2708.3, 1: 2721.3. Samples: 189330736. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:43,445][86177] Avg episode reward: [(0, '-548.210'), (1, '-633.760')] -[2023-11-28 09:54:44,116][87424] Updated weights for policy 0, policy_version 369929 (0.0011) -[2023-11-28 09:54:44,507][87424] Updated weights for policy 0, policy_version 369939 (0.0010) -[2023-11-28 09:54:44,888][87424] Updated weights for policy 0, policy_version 369949 (0.0008) -[2023-11-28 09:54:45,070][87426] Updated weights for policy 1, policy_version 369610 (0.0009) -[2023-11-28 09:54:45,451][87426] Updated weights for policy 1, policy_version 369620 (0.0009) -[2023-11-28 09:54:45,832][87426] Updated weights for policy 1, policy_version 369630 (0.0007) -[2023-11-28 09:54:46,818][87424] Updated weights for policy 0, policy_version 369959 (0.0009) -[2023-11-28 09:54:47,202][87424] Updated weights for policy 0, policy_version 369969 (0.0009) -[2023-11-28 09:54:47,586][87424] Updated weights for policy 0, policy_version 369979 (0.0011) -[2023-11-28 09:54:48,001][87426] Updated weights for policy 1, policy_version 369640 (0.0009) -[2023-11-28 09:54:48,388][87426] Updated weights for policy 1, policy_version 369650 (0.0008) -[2023-11-28 09:54:48,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 189341696. Throughput: 0: 2717.2, 1: 2738.5. Samples: 189355948. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:48,445][86177] Avg episode reward: [(0, '-550.960'), (1, '-650.250')] -[2023-11-28 09:54:48,768][87426] Updated weights for policy 1, policy_version 369660 (0.0009) -[2023-11-28 09:54:50,105][87424] Updated weights for policy 0, policy_version 369989 (0.0009) -[2023-11-28 09:54:50,483][87424] Updated weights for policy 0, policy_version 369999 (0.0009) -[2023-11-28 09:54:50,675][87426] Updated weights for policy 1, policy_version 369670 (0.0010) -[2023-11-28 09:54:50,863][87424] Updated weights for policy 0, policy_version 370009 (0.0008) -[2023-11-28 09:54:51,056][87426] Updated weights for policy 1, policy_version 369680 (0.0011) -[2023-11-28 09:54:51,427][87426] Updated weights for policy 1, policy_version 369690 (0.0011) -[2023-11-28 09:54:53,279][87424] Updated weights for policy 0, policy_version 370019 (0.0010) -[2023-11-28 09:54:53,445][86177] Fps is (10 sec: 4914.7, 60 sec: 5324.7, 300 sec: 5359.5). Total num frames: 189366272. Throughput: 0: 2687.3, 1: 2765.1. Samples: 189387724. Policy #0 lag: (min: 23.0, avg: 26.2, max: 51.0) -[2023-11-28 09:54:53,446][86177] Avg episode reward: [(0, '-542.180'), (1, '-584.690')] -[2023-11-28 09:54:53,662][87424] Updated weights for policy 0, policy_version 370029 (0.0011) -[2023-11-28 09:54:53,999][87426] Updated weights for policy 1, policy_version 369700 (0.0011) -[2023-11-28 09:54:54,045][87424] Updated weights for policy 0, policy_version 370039 (0.0011) -[2023-11-28 09:54:54,386][87426] Updated weights for policy 1, policy_version 369710 (0.0008) -[2023-11-28 09:54:54,760][87426] Updated weights for policy 1, policy_version 369720 (0.0007) -[2023-11-28 09:54:56,384][87424] Updated weights for policy 0, policy_version 370049 (0.0008) -[2023-11-28 09:54:56,761][87424] Updated weights for policy 0, policy_version 370059 (0.0008) -[2023-11-28 09:54:56,763][87426] Updated weights for policy 1, policy_version 369730 (0.0008) -[2023-11-28 09:54:57,135][87426] Updated weights for policy 1, policy_version 369740 (0.0011) -[2023-11-28 09:54:57,147][87424] Updated weights for policy 0, policy_version 370069 (0.0008) -[2023-11-28 09:54:57,510][87426] Updated weights for policy 1, policy_version 369750 (0.0011) -[2023-11-28 09:54:57,521][87424] Updated weights for policy 0, policy_version 370079 (0.0010) -[2023-11-28 09:54:57,894][87426] Updated weights for policy 1, policy_version 369760 (0.0012) -[2023-11-28 09:54:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 189399040. Throughput: 0: 2667.3, 1: 2779.2. Samples: 189412020. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:54:58,445][86177] Avg episode reward: [(0, '-545.540'), (1, '-585.180')] -[2023-11-28 09:54:59,752][87426] Updated weights for policy 1, policy_version 369770 (0.0012) -[2023-11-28 09:54:59,801][87424] Updated weights for policy 0, policy_version 370089 (0.0011) -[2023-11-28 09:55:00,125][87426] Updated weights for policy 1, policy_version 369780 (0.0011) -[2023-11-28 09:55:00,187][87424] Updated weights for policy 0, policy_version 370099 (0.0008) -[2023-11-28 09:55:00,502][87426] Updated weights for policy 1, policy_version 369790 (0.0010) -[2023-11-28 09:55:00,577][87424] Updated weights for policy 0, policy_version 370109 (0.0009) -[2023-11-28 09:55:02,718][87426] Updated weights for policy 1, policy_version 369800 (0.0011) -[2023-11-28 09:55:02,736][87424] Updated weights for policy 0, policy_version 370119 (0.0010) -[2023-11-28 09:55:03,097][87426] Updated weights for policy 1, policy_version 369810 (0.0009) -[2023-11-28 09:55:03,124][87424] Updated weights for policy 0, policy_version 370129 (0.0009) -[2023-11-28 09:55:03,444][86177] Fps is (10 sec: 4915.8, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 189415424. Throughput: 0: 2664.8, 1: 2787.7. Samples: 189435856. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:03,445][86177] Avg episode reward: [(0, '-559.820'), (1, '-601.730')] -[2023-11-28 09:55:03,480][87426] Updated weights for policy 1, policy_version 369820 (0.0012) -[2023-11-28 09:55:03,501][87424] Updated weights for policy 0, policy_version 370139 (0.0010) -[2023-11-28 09:55:05,193][87424] Updated weights for policy 0, policy_version 370149 (0.0012) -[2023-11-28 09:55:05,427][87426] Updated weights for policy 1, policy_version 369830 (0.0013) -[2023-11-28 09:55:05,577][87424] Updated weights for policy 0, policy_version 370159 (0.0011) -[2023-11-28 09:55:05,809][87426] Updated weights for policy 1, policy_version 369840 (0.0011) -[2023-11-28 09:55:05,956][87424] Updated weights for policy 0, policy_version 370169 (0.0008) -[2023-11-28 09:55:06,197][87426] Updated weights for policy 1, policy_version 369850 (0.0012) -[2023-11-28 09:55:08,212][87424] Updated weights for policy 0, policy_version 370179 (0.0009) -[2023-11-28 09:55:08,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189448192. Throughput: 0: 2691.5, 1: 2793.8. Samples: 189469996. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:08,446][86177] Avg episode reward: [(0, '-544.590'), (1, '-593.340')] -[2023-11-28 09:55:08,467][87426] Updated weights for policy 1, policy_version 369860 (0.0011) -[2023-11-28 09:55:08,594][87424] Updated weights for policy 0, policy_version 370189 (0.0010) -[2023-11-28 09:55:08,847][87426] Updated weights for policy 1, policy_version 369870 (0.0012) -[2023-11-28 09:55:08,964][87424] Updated weights for policy 0, policy_version 370199 (0.0009) -[2023-11-28 09:55:09,217][87426] Updated weights for policy 1, policy_version 369880 (0.0011) -[2023-11-28 09:55:11,338][87424] Updated weights for policy 0, policy_version 370209 (0.0009) -[2023-11-28 09:55:11,436][87426] Updated weights for policy 1, policy_version 369890 (0.0009) -[2023-11-28 09:55:11,721][87424] Updated weights for policy 0, policy_version 370219 (0.0010) -[2023-11-28 09:55:11,830][87426] Updated weights for policy 1, policy_version 369900 (0.0011) -[2023-11-28 09:55:12,104][87424] Updated weights for policy 0, policy_version 370229 (0.0010) -[2023-11-28 09:55:12,220][87426] Updated weights for policy 1, policy_version 369910 (0.0011) -[2023-11-28 09:55:12,482][87424] Updated weights for policy 0, policy_version 370239 (0.0010) -[2023-11-28 09:55:12,591][87426] Updated weights for policy 1, policy_version 369920 (0.0012) -[2023-11-28 09:55:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 189480960. Throughput: 0: 2690.8, 1: 2747.4. Samples: 189493516. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:13,445][86177] Avg episode reward: [(0, '-553.520'), (1, '-578.770')] -[2023-11-28 09:55:14,353][87424] Updated weights for policy 0, policy_version 370249 (0.0012) -[2023-11-28 09:55:14,737][87424] Updated weights for policy 0, policy_version 370259 (0.0009) -[2023-11-28 09:55:15,119][87424] Updated weights for policy 0, policy_version 370269 (0.0008) -[2023-11-28 09:55:15,252][87426] Updated weights for policy 1, policy_version 369930 (0.0012) -[2023-11-28 09:55:15,634][87426] Updated weights for policy 1, policy_version 369940 (0.0012) -[2023-11-28 09:55:16,024][87426] Updated weights for policy 1, policy_version 369950 (0.0012) -[2023-11-28 09:55:17,273][87424] Updated weights for policy 0, policy_version 370279 (0.0010) -[2023-11-28 09:55:17,657][87424] Updated weights for policy 0, policy_version 370289 (0.0012) -[2023-11-28 09:55:18,029][87424] Updated weights for policy 0, policy_version 370299 (0.0012) -[2023-11-28 09:55:18,388][87426] Updated weights for policy 1, policy_version 369960 (0.0010) -[2023-11-28 09:55:18,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 189505536. Throughput: 0: 2703.0, 1: 2721.6. Samples: 189517792. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:18,445][86177] Avg episode reward: [(0, '-566.250'), (1, '-561.890')] -[2023-11-28 09:55:18,761][87426] Updated weights for policy 1, policy_version 369970 (0.0008) -[2023-11-28 09:55:19,139][87426] Updated weights for policy 1, policy_version 369980 (0.0008) -[2023-11-28 09:55:20,443][87424] Updated weights for policy 0, policy_version 370309 (0.0011) -[2023-11-28 09:55:20,825][87424] Updated weights for policy 0, policy_version 370319 (0.0008) -[2023-11-28 09:55:21,205][87424] Updated weights for policy 0, policy_version 370329 (0.0009) -[2023-11-28 09:55:21,332][87426] Updated weights for policy 1, policy_version 369990 (0.0009) -[2023-11-28 09:55:21,709][87426] Updated weights for policy 1, policy_version 370000 (0.0011) -[2023-11-28 09:55:22,089][87426] Updated weights for policy 1, policy_version 370010 (0.0010) -[2023-11-28 09:55:23,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 189530112. Throughput: 0: 2690.6, 1: 2702.9. Samples: 189549648. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:23,446][86177] Avg episode reward: [(0, '-555.490'), (1, '-567.790')] -[2023-11-28 09:55:23,506][87424] Updated weights for policy 0, policy_version 370339 (0.0011) -[2023-11-28 09:55:23,895][87424] Updated weights for policy 0, policy_version 370349 (0.0008) -[2023-11-28 09:55:24,268][87424] Updated weights for policy 0, policy_version 370359 (0.0008) -[2023-11-28 09:55:24,418][87426] Updated weights for policy 1, policy_version 370020 (0.0011) -[2023-11-28 09:55:24,795][87426] Updated weights for policy 1, policy_version 370030 (0.0011) -[2023-11-28 09:55:25,173][87426] Updated weights for policy 1, policy_version 370040 (0.0012) -[2023-11-28 09:55:26,193][87424] Updated weights for policy 0, policy_version 370369 (0.0009) -[2023-11-28 09:55:26,571][87424] Updated weights for policy 0, policy_version 370379 (0.0012) -[2023-11-28 09:55:26,949][87424] Updated weights for policy 0, policy_version 370389 (0.0012) -[2023-11-28 09:55:27,224][87426] Updated weights for policy 1, policy_version 370050 (0.0011) -[2023-11-28 09:55:27,326][87424] Updated weights for policy 0, policy_version 370399 (0.0012) -[2023-11-28 09:55:27,593][87426] Updated weights for policy 1, policy_version 370060 (0.0007) -[2023-11-28 09:55:27,963][87426] Updated weights for policy 1, policy_version 370070 (0.0008) -[2023-11-28 09:55:28,341][87426] Updated weights for policy 1, policy_version 370080 (0.0007) -[2023-11-28 09:55:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 189562880. Throughput: 0: 2694.1, 1: 2707.6. Samples: 189573812. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:28,445][86177] Avg episode reward: [(0, '-556.930'), (1, '-545.420')] -[2023-11-28 09:55:29,679][87424] Updated weights for policy 0, policy_version 370409 (0.0012) -[2023-11-28 09:55:30,058][87424] Updated weights for policy 0, policy_version 370419 (0.0009) -[2023-11-28 09:55:30,445][87424] Updated weights for policy 0, policy_version 370429 (0.0009) -[2023-11-28 09:55:30,594][87426] Updated weights for policy 1, policy_version 370090 (0.0010) -[2023-11-28 09:55:30,973][87426] Updated weights for policy 1, policy_version 370100 (0.0010) -[2023-11-28 09:55:31,353][87426] Updated weights for policy 1, policy_version 370110 (0.0009) -[2023-11-28 09:55:32,986][87424] Updated weights for policy 0, policy_version 370439 (0.0011) -[2023-11-28 09:55:33,366][87424] Updated weights for policy 0, policy_version 370449 (0.0012) -[2023-11-28 09:55:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 189579264. Throughput: 0: 2669.2, 1: 2689.0. Samples: 189597064. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:33,445][86177] Avg episode reward: [(0, '-571.050'), (1, '-544.670')] -[2023-11-28 09:55:33,641][87426] Updated weights for policy 1, policy_version 370120 (0.0008) -[2023-11-28 09:55:33,743][87424] Updated weights for policy 0, policy_version 370459 (0.0010) -[2023-11-28 09:55:34,019][87426] Updated weights for policy 1, policy_version 370130 (0.0007) -[2023-11-28 09:55:34,397][87426] Updated weights for policy 1, policy_version 370140 (0.0007) -[2023-11-28 09:55:35,875][87424] Updated weights for policy 0, policy_version 370469 (0.0008) -[2023-11-28 09:55:36,255][87424] Updated weights for policy 0, policy_version 370479 (0.0011) -[2023-11-28 09:55:36,626][87426] Updated weights for policy 1, policy_version 370150 (0.0008) -[2023-11-28 09:55:36,635][87424] Updated weights for policy 0, policy_version 370489 (0.0008) -[2023-11-28 09:55:37,004][87426] Updated weights for policy 1, policy_version 370160 (0.0008) -[2023-11-28 09:55:37,381][87426] Updated weights for policy 1, policy_version 370170 (0.0008) -[2023-11-28 09:55:38,301][87424] Updated weights for policy 0, policy_version 370499 (0.0010) -[2023-11-28 09:55:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 189612032. Throughput: 0: 2672.7, 1: 2684.5. Samples: 189628792. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:38,445][86177] Avg episode reward: [(0, '-579.010'), (1, '-557.490')] -[2023-11-28 09:55:38,681][87424] Updated weights for policy 0, policy_version 370509 (0.0009) -[2023-11-28 09:55:39,063][87424] Updated weights for policy 0, policy_version 370519 (0.0008) -[2023-11-28 09:55:39,800][87426] Updated weights for policy 1, policy_version 370180 (0.0011) -[2023-11-28 09:55:40,184][87426] Updated weights for policy 1, policy_version 370190 (0.0008) -[2023-11-28 09:55:40,549][87426] Updated weights for policy 1, policy_version 370200 (0.0009) -[2023-11-28 09:55:41,451][87424] Updated weights for policy 0, policy_version 370529 (0.0009) -[2023-11-28 09:55:41,831][87424] Updated weights for policy 0, policy_version 370539 (0.0017) -[2023-11-28 09:55:42,207][87424] Updated weights for policy 0, policy_version 370549 (0.0010) -[2023-11-28 09:55:42,595][87424] Updated weights for policy 0, policy_version 370559 (0.0009) -[2023-11-28 09:55:43,062][87426] Updated weights for policy 1, policy_version 370210 (0.0010) -[2023-11-28 09:55:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189636608. Throughput: 0: 2678.7, 1: 2652.8. Samples: 189651936. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:43,445][86177] Avg episode reward: [(0, '-570.190'), (1, '-531.830')] -[2023-11-28 09:55:43,447][87426] Updated weights for policy 1, policy_version 370220 (0.0012) -[2023-11-28 09:55:43,819][87426] Updated weights for policy 1, policy_version 370230 (0.0008) -[2023-11-28 09:55:44,199][87426] Updated weights for policy 1, policy_version 370240 (0.0007) -[2023-11-28 09:55:44,989][87424] Updated weights for policy 0, policy_version 370569 (0.0009) -[2023-11-28 09:55:45,374][87424] Updated weights for policy 0, policy_version 370579 (0.0008) -[2023-11-28 09:55:45,749][87424] Updated weights for policy 0, policy_version 370589 (0.0009) -[2023-11-28 09:55:46,005][87426] Updated weights for policy 1, policy_version 370250 (0.0011) -[2023-11-28 09:55:46,387][87426] Updated weights for policy 1, policy_version 370260 (0.0007) -[2023-11-28 09:55:46,767][87426] Updated weights for policy 1, policy_version 370270 (0.0007) -[2023-11-28 09:55:47,737][87424] Updated weights for policy 0, policy_version 370599 (0.0007) -[2023-11-28 09:55:48,122][87424] Updated weights for policy 0, policy_version 370609 (0.0007) -[2023-11-28 09:55:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 189661184. Throughput: 0: 2705.7, 1: 2651.5. Samples: 189676928. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:48,445][86177] Avg episode reward: [(0, '-572.480'), (1, '-533.750')] -[2023-11-28 09:55:48,501][87424] Updated weights for policy 0, policy_version 370619 (0.0008) -[2023-11-28 09:55:48,965][87426] Updated weights for policy 1, policy_version 370280 (0.0009) -[2023-11-28 09:55:49,345][87426] Updated weights for policy 1, policy_version 370290 (0.0011) -[2023-11-28 09:55:49,724][87426] Updated weights for policy 1, policy_version 370300 (0.0010) -[2023-11-28 09:55:50,511][87424] Updated weights for policy 0, policy_version 370629 (0.0010) -[2023-11-28 09:55:50,894][87424] Updated weights for policy 0, policy_version 370639 (0.0012) -[2023-11-28 09:55:51,265][87424] Updated weights for policy 0, policy_version 370649 (0.0012) -[2023-11-28 09:55:52,209][87426] Updated weights for policy 1, policy_version 370310 (0.0012) -[2023-11-28 09:55:52,574][87426] Updated weights for policy 1, policy_version 370320 (0.0012) -[2023-11-28 09:55:52,958][87426] Updated weights for policy 1, policy_version 370330 (0.0012) -[2023-11-28 09:55:53,430][87424] Updated weights for policy 0, policy_version 370659 (0.0012) -[2023-11-28 09:55:53,447][86177] Fps is (10 sec: 5732.5, 60 sec: 5461.1, 300 sec: 5387.2). Total num frames: 189693952. Throughput: 0: 2699.2, 1: 2619.3. Samples: 189709344. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:53,448][86177] Avg episode reward: [(0, '-577.010'), (1, '-533.250')] -[2023-11-28 09:55:53,804][87424] Updated weights for policy 0, policy_version 370669 (0.0012) -[2023-11-28 09:55:54,185][87424] Updated weights for policy 0, policy_version 370679 (0.0012) -[2023-11-28 09:55:55,127][87426] Updated weights for policy 1, policy_version 370340 (0.0010) -[2023-11-28 09:55:55,498][87426] Updated weights for policy 1, policy_version 370350 (0.0008) -[2023-11-28 09:55:55,883][87426] Updated weights for policy 1, policy_version 370360 (0.0007) -[2023-11-28 09:55:56,492][87424] Updated weights for policy 0, policy_version 370689 (0.0012) -[2023-11-28 09:55:56,865][87424] Updated weights for policy 0, policy_version 370699 (0.0008) -[2023-11-28 09:55:57,246][87424] Updated weights for policy 0, policy_version 370709 (0.0007) -[2023-11-28 09:55:57,625][87424] Updated weights for policy 0, policy_version 370719 (0.0007) -[2023-11-28 09:55:58,160][87426] Updated weights for policy 1, policy_version 370370 (0.0007) -[2023-11-28 09:55:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189718528. Throughput: 0: 2689.3, 1: 2638.0. Samples: 189733248. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:55:58,445][86177] Avg episode reward: [(0, '-568.540'), (1, '-529.870')] -[2023-11-28 09:55:58,536][87426] Updated weights for policy 1, policy_version 370380 (0.0008) -[2023-11-28 09:55:58,926][87426] Updated weights for policy 1, policy_version 370390 (0.0008) -[2023-11-28 09:55:59,298][87426] Updated weights for policy 1, policy_version 370400 (0.0009) -[2023-11-28 09:55:59,478][87424] Updated weights for policy 0, policy_version 370729 (0.0011) -[2023-11-28 09:55:59,867][87424] Updated weights for policy 0, policy_version 370739 (0.0012) -[2023-11-28 09:56:00,246][87424] Updated weights for policy 0, policy_version 370749 (0.0012) -[2023-11-28 09:56:01,457][87426] Updated weights for policy 1, policy_version 370410 (0.0011) -[2023-11-28 09:56:01,837][87426] Updated weights for policy 1, policy_version 370420 (0.0010) -[2023-11-28 09:56:02,219][87426] Updated weights for policy 1, policy_version 370430 (0.0010) -[2023-11-28 09:56:02,746][87424] Updated weights for policy 0, policy_version 370759 (0.0011) -[2023-11-28 09:56:03,118][87424] Updated weights for policy 0, policy_version 370769 (0.0012) -[2023-11-28 09:56:03,444][86177] Fps is (10 sec: 4916.8, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 189743104. Throughput: 0: 2683.4, 1: 2655.4. Samples: 189758036. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:56:03,445][86177] Avg episode reward: [(0, '-566.350'), (1, '-528.490')] -[2023-11-28 09:56:03,503][87424] Updated weights for policy 0, policy_version 370779 (0.0012) -[2023-11-28 09:56:04,297][87426] Updated weights for policy 1, policy_version 370440 (0.0012) -[2023-11-28 09:56:04,667][87426] Updated weights for policy 1, policy_version 370450 (0.0012) -[2023-11-28 09:56:05,044][87426] Updated weights for policy 1, policy_version 370460 (0.0011) -[2023-11-28 09:56:05,341][87424] Updated weights for policy 0, policy_version 370789 (0.0012) -[2023-11-28 09:56:05,714][87424] Updated weights for policy 0, policy_version 370799 (0.0010) -[2023-11-28 09:56:06,091][87424] Updated weights for policy 0, policy_version 370809 (0.0009) -[2023-11-28 09:56:07,006][87426] Updated weights for policy 1, policy_version 370470 (0.0011) -[2023-11-28 09:56:07,383][87426] Updated weights for policy 1, policy_version 370480 (0.0012) -[2023-11-28 09:56:07,758][87426] Updated weights for policy 1, policy_version 370490 (0.0012) -[2023-11-28 09:56:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 189775872. Throughput: 0: 2689.4, 1: 2665.4. Samples: 189790612. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:56:08,445][86177] Avg episode reward: [(0, '-611.670'), (1, '-530.060')] -[2023-11-28 09:56:08,492][87424] Updated weights for policy 0, policy_version 370819 (0.0009) -[2023-11-28 09:56:08,873][87424] Updated weights for policy 0, policy_version 370829 (0.0012) -[2023-11-28 09:56:09,250][87424] Updated weights for policy 0, policy_version 370839 (0.0012) -[2023-11-28 09:56:10,216][87426] Updated weights for policy 1, policy_version 370500 (0.0009) -[2023-11-28 09:56:10,593][87426] Updated weights for policy 1, policy_version 370510 (0.0012) -[2023-11-28 09:56:10,972][87426] Updated weights for policy 1, policy_version 370520 (0.0011) -[2023-11-28 09:56:11,478][87424] Updated weights for policy 0, policy_version 370849 (0.0009) -[2023-11-28 09:56:11,860][87424] Updated weights for policy 0, policy_version 370859 (0.0010) -[2023-11-28 09:56:12,244][87424] Updated weights for policy 0, policy_version 370869 (0.0012) -[2023-11-28 09:56:12,633][87424] Updated weights for policy 0, policy_version 370879 (0.0011) -[2023-11-28 09:56:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 189800448. Throughput: 0: 2685.0, 1: 2674.0. Samples: 189814964. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:56:13,445][86177] Avg episode reward: [(0, '-589.900'), (1, '-529.760')] -[2023-11-28 09:56:13,514][87426] Updated weights for policy 1, policy_version 370530 (0.0011) -[2023-11-28 09:56:13,897][87426] Updated weights for policy 1, policy_version 370540 (0.0007) -[2023-11-28 09:56:14,273][87426] Updated weights for policy 1, policy_version 370550 (0.0012) -[2023-11-28 09:56:14,653][87426] Updated weights for policy 1, policy_version 370560 (0.0009) -[2023-11-28 09:56:15,163][87424] Updated weights for policy 0, policy_version 370889 (0.0012) -[2023-11-28 09:56:15,548][87424] Updated weights for policy 0, policy_version 370899 (0.0012) -[2023-11-28 09:56:15,934][87424] Updated weights for policy 0, policy_version 370909 (0.0012) -[2023-11-28 09:56:16,606][87426] Updated weights for policy 1, policy_version 370570 (0.0007) -[2023-11-28 09:56:16,983][87426] Updated weights for policy 1, policy_version 370580 (0.0010) -[2023-11-28 09:56:17,358][87426] Updated weights for policy 1, policy_version 370590 (0.0012) -[2023-11-28 09:56:18,420][87424] Updated weights for policy 0, policy_version 370919 (0.0010) -[2023-11-28 09:56:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 189825024. Throughput: 0: 2672.4, 1: 2695.3. Samples: 189838608. Policy #0 lag: (min: 31.0, avg: 34.4, max: 63.0) -[2023-11-28 09:56:18,445][86177] Avg episode reward: [(0, '-582.270'), (1, '-537.620')] -[2023-11-28 09:56:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000370592_94871552.pth... -[2023-11-28 09:56:18,497][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000368064_94224384.pth -[2023-11-28 09:56:18,802][87424] Updated weights for policy 0, policy_version 370929 (0.0008) -[2023-11-28 09:56:19,127][87426] Updated weights for policy 1, policy_version 370600 (0.0010) -[2023-11-28 09:56:19,189][87424] Updated weights for policy 0, policy_version 370939 (0.0012) -[2023-11-28 09:56:19,382][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000370944_94961664.pth... -[2023-11-28 09:56:19,426][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000368416_94314496.pth -[2023-11-28 09:56:19,503][87426] Updated weights for policy 1, policy_version 370610 (0.0008) -[2023-11-28 09:56:19,890][87426] Updated weights for policy 1, policy_version 370620 (0.0012) -[2023-11-28 09:56:21,367][87424] Updated weights for policy 0, policy_version 370949 (0.0010) -[2023-11-28 09:56:21,754][87424] Updated weights for policy 0, policy_version 370959 (0.0012) -[2023-11-28 09:56:21,820][87426] Updated weights for policy 1, policy_version 370630 (0.0011) -[2023-11-28 09:56:22,129][87424] Updated weights for policy 0, policy_version 370969 (0.0012) -[2023-11-28 09:56:22,200][87426] Updated weights for policy 1, policy_version 370640 (0.0010) -[2023-11-28 09:56:22,576][87426] Updated weights for policy 1, policy_version 370650 (0.0011) -[2023-11-28 09:56:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 189857792. Throughput: 0: 2690.4, 1: 2704.4. Samples: 189871556. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:56:23,445][86177] Avg episode reward: [(0, '-581.330'), (1, '-536.930')] -[2023-11-28 09:56:24,248][87424] Updated weights for policy 0, policy_version 370979 (0.0012) -[2023-11-28 09:56:24,494][87426] Updated weights for policy 1, policy_version 370660 (0.0011) -[2023-11-28 09:56:24,628][87424] Updated weights for policy 0, policy_version 370989 (0.0009) -[2023-11-28 09:56:24,868][87426] Updated weights for policy 1, policy_version 370670 (0.0010) -[2023-11-28 09:56:25,005][87424] Updated weights for policy 0, policy_version 370999 (0.0010) -[2023-11-28 09:56:25,252][87426] Updated weights for policy 1, policy_version 370680 (0.0007) -[2023-11-28 09:56:26,970][87424] Updated weights for policy 0, policy_version 371009 (0.0012) -[2023-11-28 09:56:27,357][87424] Updated weights for policy 0, policy_version 371019 (0.0012) -[2023-11-28 09:56:27,442][87426] Updated weights for policy 1, policy_version 370690 (0.0008) -[2023-11-28 09:56:27,732][87424] Updated weights for policy 0, policy_version 371029 (0.0012) -[2023-11-28 09:56:27,813][87426] Updated weights for policy 1, policy_version 370700 (0.0011) -[2023-11-28 09:56:28,114][87424] Updated weights for policy 0, policy_version 371039 (0.0012) -[2023-11-28 09:56:28,186][87426] Updated weights for policy 1, policy_version 370710 (0.0010) -[2023-11-28 09:56:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 189882368. Throughput: 0: 2710.0, 1: 2699.4. Samples: 189895356. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:56:28,445][86177] Avg episode reward: [(0, '-569.560'), (1, '-527.850')] -[2023-11-28 09:56:28,561][87426] Updated weights for policy 1, policy_version 370720 (0.0012) -[2023-11-28 09:56:30,263][87424] Updated weights for policy 0, policy_version 371049 (0.0011) -[2023-11-28 09:56:30,640][87424] Updated weights for policy 0, policy_version 371059 (0.0009) -[2023-11-28 09:56:30,819][87426] Updated weights for policy 1, policy_version 370730 (0.0011) -[2023-11-28 09:56:31,020][87424] Updated weights for policy 0, policy_version 371069 (0.0010) -[2023-11-28 09:56:31,199][87426] Updated weights for policy 1, policy_version 370740 (0.0011) -[2023-11-28 09:56:31,572][87426] Updated weights for policy 1, policy_version 370750 (0.0012) -[2023-11-28 09:56:33,318][87424] Updated weights for policy 0, policy_version 371079 (0.0012) -[2023-11-28 09:56:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 189906944. Throughput: 0: 2707.6, 1: 2701.4. Samples: 189920336. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:56:33,445][86177] Avg episode reward: [(0, '-579.390'), (1, '-528.230')] -[2023-11-28 09:56:33,704][87424] Updated weights for policy 0, policy_version 371089 (0.0011) -[2023-11-28 09:56:33,869][87426] Updated weights for policy 1, policy_version 370760 (0.0011) -[2023-11-28 09:56:34,104][87424] Updated weights for policy 0, policy_version 371099 (0.0010) -[2023-11-28 09:56:34,253][87426] Updated weights for policy 1, policy_version 370770 (0.0007) -[2023-11-28 09:56:34,628][87426] Updated weights for policy 1, policy_version 370780 (0.0007) -[2023-11-28 09:56:36,380][87424] Updated weights for policy 0, policy_version 371109 (0.0010) -[2023-11-28 09:56:36,756][87424] Updated weights for policy 0, policy_version 371119 (0.0012) -[2023-11-28 09:56:36,942][87426] Updated weights for policy 1, policy_version 370790 (0.0011) -[2023-11-28 09:56:37,137][87424] Updated weights for policy 0, policy_version 371129 (0.0011) -[2023-11-28 09:56:37,313][87426] Updated weights for policy 1, policy_version 370800 (0.0011) -[2023-11-28 09:56:37,698][87426] Updated weights for policy 1, policy_version 370810 (0.0011) -[2023-11-28 09:56:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 189939712. Throughput: 0: 2689.4, 1: 2711.0. Samples: 189952348. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:56:38,445][86177] Avg episode reward: [(0, '-587.360'), (1, '-580.970')] -[2023-11-28 09:56:38,827][87424] Updated weights for policy 0, policy_version 371139 (0.0011) -[2023-11-28 09:56:39,215][87424] Updated weights for policy 0, policy_version 371149 (0.0012) -[2023-11-28 09:56:39,588][87424] Updated weights for policy 0, policy_version 371159 (0.0012) -[2023-11-28 09:56:40,111][87426] Updated weights for policy 1, policy_version 370820 (0.0011) -[2023-11-28 09:56:40,489][87426] Updated weights for policy 1, policy_version 370830 (0.0012) -[2023-11-28 09:56:40,869][87426] Updated weights for policy 1, policy_version 370840 (0.0012) -[2023-11-28 09:56:42,076][87424] Updated weights for policy 0, policy_version 371169 (0.0012) -[2023-11-28 09:56:42,459][87424] Updated weights for policy 0, policy_version 371179 (0.0010) -[2023-11-28 09:56:42,841][87424] Updated weights for policy 0, policy_version 371189 (0.0008) -[2023-11-28 09:56:42,904][87426] Updated weights for policy 1, policy_version 370850 (0.0011) -[2023-11-28 09:56:43,222][87424] Updated weights for policy 0, policy_version 371199 (0.0009) -[2023-11-28 09:56:43,286][87426] Updated weights for policy 1, policy_version 370860 (0.0011) -[2023-11-28 09:56:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 189964288. Throughput: 0: 2706.8, 1: 2719.2. Samples: 189977420. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:56:43,446][86177] Avg episode reward: [(0, '-612.170'), (1, '-582.010')] -[2023-11-28 09:56:43,664][87426] Updated weights for policy 1, policy_version 370870 (0.0012) -[2023-11-28 09:56:44,049][87426] Updated weights for policy 1, policy_version 370880 (0.0012) -[2023-11-28 09:56:45,237][87424] Updated weights for policy 0, policy_version 371209 (0.0008) -[2023-11-28 09:56:45,618][87424] Updated weights for policy 0, policy_version 371219 (0.0010) -[2023-11-28 09:56:46,001][87424] Updated weights for policy 0, policy_version 371229 (0.0011) -[2023-11-28 09:56:46,598][87426] Updated weights for policy 1, policy_version 370890 (0.0011) -[2023-11-28 09:56:46,978][87426] Updated weights for policy 1, policy_version 370900 (0.0012) -[2023-11-28 09:56:47,349][87426] Updated weights for policy 1, policy_version 370910 (0.0011) -[2023-11-28 09:56:47,944][87424] Updated weights for policy 0, policy_version 371239 (0.0009) -[2023-11-28 09:56:48,332][87424] Updated weights for policy 0, policy_version 371249 (0.0011) -[2023-11-28 09:56:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 189988864. Throughput: 0: 2694.0, 1: 2717.0. Samples: 190001528. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:56:48,445][86177] Avg episode reward: [(0, '-584.860'), (1, '-587.050')] -[2023-11-28 09:56:48,707][87424] Updated weights for policy 0, policy_version 371259 (0.0011) -[2023-11-28 09:56:49,606][87426] Updated weights for policy 1, policy_version 370920 (0.0012) -[2023-11-28 09:56:49,979][87426] Updated weights for policy 1, policy_version 370930 (0.0012) -[2023-11-28 09:56:50,357][87426] Updated weights for policy 1, policy_version 370940 (0.0011) -[2023-11-28 09:56:51,218][87424] Updated weights for policy 0, policy_version 371269 (0.0010) -[2023-11-28 09:56:51,600][87424] Updated weights for policy 0, policy_version 371279 (0.0012) -[2023-11-28 09:56:52,000][87424] Updated weights for policy 0, policy_version 371289 (0.0011) -[2023-11-28 09:56:53,028][87426] Updated weights for policy 1, policy_version 370950 (0.0010) -[2023-11-28 09:56:53,407][87426] Updated weights for policy 1, policy_version 370960 (0.0010) -[2023-11-28 09:56:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5325.1, 300 sec: 5359.5). Total num frames: 190013440. Throughput: 0: 2677.4, 1: 2711.4. Samples: 190033108. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:56:53,445][86177] Avg episode reward: [(0, '-582.380'), (1, '-569.490')] -[2023-11-28 09:56:53,783][87426] Updated weights for policy 1, policy_version 370970 (0.0010) -[2023-11-28 09:56:54,500][87424] Updated weights for policy 0, policy_version 371299 (0.0011) -[2023-11-28 09:56:54,882][87424] Updated weights for policy 0, policy_version 371309 (0.0012) -[2023-11-28 09:56:55,270][87424] Updated weights for policy 0, policy_version 371319 (0.0012) -[2023-11-28 09:56:55,640][87426] Updated weights for policy 1, policy_version 370980 (0.0010) -[2023-11-28 09:56:56,015][87426] Updated weights for policy 1, policy_version 370990 (0.0012) -[2023-11-28 09:56:56,401][87426] Updated weights for policy 1, policy_version 371000 (0.0012) -[2023-11-28 09:56:57,341][87424] Updated weights for policy 0, policy_version 371329 (0.0012) -[2023-11-28 09:56:57,718][87424] Updated weights for policy 0, policy_version 371339 (0.0012) -[2023-11-28 09:56:58,098][87424] Updated weights for policy 0, policy_version 371349 (0.0012) -[2023-11-28 09:56:58,346][87426] Updated weights for policy 1, policy_version 371010 (0.0012) -[2023-11-28 09:56:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 190038016. Throughput: 0: 2671.6, 1: 2705.7. Samples: 190056940. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:56:58,445][86177] Avg episode reward: [(0, '-573.710'), (1, '-512.930')] -[2023-11-28 09:56:58,485][87424] Updated weights for policy 0, policy_version 371359 (0.0012) -[2023-11-28 09:56:58,722][87426] Updated weights for policy 1, policy_version 371020 (0.0011) -[2023-11-28 09:56:59,100][87426] Updated weights for policy 1, policy_version 371030 (0.0008) -[2023-11-28 09:56:59,476][87426] Updated weights for policy 1, policy_version 371040 (0.0008) -[2023-11-28 09:57:00,986][87424] Updated weights for policy 0, policy_version 371369 (0.0011) -[2023-11-28 09:57:01,370][87424] Updated weights for policy 0, policy_version 371379 (0.0012) -[2023-11-28 09:57:01,738][87424] Updated weights for policy 0, policy_version 371389 (0.0010) -[2023-11-28 09:57:01,742][87426] Updated weights for policy 1, policy_version 371050 (0.0011) -[2023-11-28 09:57:02,119][87426] Updated weights for policy 1, policy_version 371060 (0.0011) -[2023-11-28 09:57:02,499][87426] Updated weights for policy 1, policy_version 371070 (0.0012) -[2023-11-28 09:57:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 190070784. Throughput: 0: 2705.1, 1: 2694.7. Samples: 190081596. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:57:03,445][86177] Avg episode reward: [(0, '-550.870'), (1, '-523.490')] -[2023-11-28 09:57:03,809][87424] Updated weights for policy 0, policy_version 371399 (0.0012) -[2023-11-28 09:57:04,205][87424] Updated weights for policy 0, policy_version 371409 (0.0012) -[2023-11-28 09:57:04,596][87424] Updated weights for policy 0, policy_version 371419 (0.0011) -[2023-11-28 09:57:04,901][87426] Updated weights for policy 1, policy_version 371080 (0.0011) -[2023-11-28 09:57:05,278][87426] Updated weights for policy 1, policy_version 371090 (0.0012) -[2023-11-28 09:57:05,655][87426] Updated weights for policy 1, policy_version 371100 (0.0012) -[2023-11-28 09:57:06,609][87424] Updated weights for policy 0, policy_version 371429 (0.0010) -[2023-11-28 09:57:06,992][87424] Updated weights for policy 0, policy_version 371439 (0.0012) -[2023-11-28 09:57:07,379][87424] Updated weights for policy 0, policy_version 371449 (0.0011) -[2023-11-28 09:57:08,079][87426] Updated weights for policy 1, policy_version 371110 (0.0010) -[2023-11-28 09:57:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190095360. Throughput: 0: 2712.8, 1: 2666.7. Samples: 190113632. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:57:08,445][86177] Avg episode reward: [(0, '-547.060'), (1, '-524.710')] -[2023-11-28 09:57:08,459][87426] Updated weights for policy 1, policy_version 371120 (0.0008) -[2023-11-28 09:57:08,834][87426] Updated weights for policy 1, policy_version 371130 (0.0009) -[2023-11-28 09:57:09,258][87424] Updated weights for policy 0, policy_version 371459 (0.0009) -[2023-11-28 09:57:09,639][87424] Updated weights for policy 0, policy_version 371469 (0.0011) -[2023-11-28 09:57:10,028][87424] Updated weights for policy 0, policy_version 371479 (0.0010) -[2023-11-28 09:57:11,190][87426] Updated weights for policy 1, policy_version 371140 (0.0012) -[2023-11-28 09:57:11,564][87426] Updated weights for policy 1, policy_version 371150 (0.0012) -[2023-11-28 09:57:11,947][87426] Updated weights for policy 1, policy_version 371160 (0.0013) -[2023-11-28 09:57:12,162][87424] Updated weights for policy 0, policy_version 371489 (0.0011) -[2023-11-28 09:57:12,534][87424] Updated weights for policy 0, policy_version 371499 (0.0011) -[2023-11-28 09:57:12,920][87424] Updated weights for policy 0, policy_version 371509 (0.0011) -[2023-11-28 09:57:13,295][87424] Updated weights for policy 0, policy_version 371519 (0.0012) -[2023-11-28 09:57:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 190128128. Throughput: 0: 2702.4, 1: 2670.2. Samples: 190137124. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:57:13,445][86177] Avg episode reward: [(0, '-555.390'), (1, '-532.370')] -[2023-11-28 09:57:14,176][87426] Updated weights for policy 1, policy_version 371170 (0.0012) -[2023-11-28 09:57:14,554][87426] Updated weights for policy 1, policy_version 371180 (0.0009) -[2023-11-28 09:57:14,936][87426] Updated weights for policy 1, policy_version 371190 (0.0009) -[2023-11-28 09:57:15,123][87424] Updated weights for policy 0, policy_version 371529 (0.0011) -[2023-11-28 09:57:15,327][87426] Updated weights for policy 1, policy_version 371200 (0.0011) -[2023-11-28 09:57:15,498][87424] Updated weights for policy 0, policy_version 371539 (0.0012) -[2023-11-28 09:57:15,883][87424] Updated weights for policy 0, policy_version 371549 (0.0012) -[2023-11-28 09:57:17,483][87426] Updated weights for policy 1, policy_version 371210 (0.0007) -[2023-11-28 09:57:17,870][87426] Updated weights for policy 1, policy_version 371220 (0.0008) -[2023-11-28 09:57:18,019][87424] Updated weights for policy 0, policy_version 371559 (0.0011) -[2023-11-28 09:57:18,247][87426] Updated weights for policy 1, policy_version 371230 (0.0009) -[2023-11-28 09:57:18,389][87424] Updated weights for policy 0, policy_version 371569 (0.0011) -[2023-11-28 09:57:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 190152704. Throughput: 0: 2711.7, 1: 2684.3. Samples: 190163156. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:57:18,445][86177] Avg episode reward: [(0, '-566.900'), (1, '-539.340')] -[2023-11-28 09:57:18,767][87424] Updated weights for policy 0, policy_version 371579 (0.0012) -[2023-11-28 09:57:19,986][87426] Updated weights for policy 1, policy_version 371240 (0.0009) -[2023-11-28 09:57:20,360][87426] Updated weights for policy 1, policy_version 371250 (0.0012) -[2023-11-28 09:57:20,746][87426] Updated weights for policy 1, policy_version 371260 (0.0012) -[2023-11-28 09:57:21,237][87424] Updated weights for policy 0, policy_version 371589 (0.0011) -[2023-11-28 09:57:21,635][87424] Updated weights for policy 0, policy_version 371599 (0.0011) -[2023-11-28 09:57:22,015][87424] Updated weights for policy 0, policy_version 371609 (0.0011) -[2023-11-28 09:57:23,066][87426] Updated weights for policy 1, policy_version 371270 (0.0012) -[2023-11-28 09:57:23,433][87426] Updated weights for policy 1, policy_version 371280 (0.0008) -[2023-11-28 09:57:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190177280. Throughput: 0: 2710.8, 1: 2687.6. Samples: 190195280. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:57:23,446][86177] Avg episode reward: [(0, '-580.090'), (1, '-528.830')] -[2023-11-28 09:57:23,814][87426] Updated weights for policy 1, policy_version 371290 (0.0011) -[2023-11-28 09:57:24,111][87424] Updated weights for policy 0, policy_version 371619 (0.0011) -[2023-11-28 09:57:24,498][87424] Updated weights for policy 0, policy_version 371629 (0.0007) -[2023-11-28 09:57:24,883][87424] Updated weights for policy 0, policy_version 371639 (0.0007) -[2023-11-28 09:57:25,789][87426] Updated weights for policy 1, policy_version 371300 (0.0012) -[2023-11-28 09:57:26,176][87426] Updated weights for policy 1, policy_version 371310 (0.0012) -[2023-11-28 09:57:26,552][87426] Updated weights for policy 1, policy_version 371320 (0.0012) -[2023-11-28 09:57:26,867][87424] Updated weights for policy 0, policy_version 371649 (0.0010) -[2023-11-28 09:57:27,252][87424] Updated weights for policy 0, policy_version 371659 (0.0012) -[2023-11-28 09:57:27,637][87424] Updated weights for policy 0, policy_version 371669 (0.0012) -[2023-11-28 09:57:28,015][87424] Updated weights for policy 0, policy_version 371679 (0.0012) -[2023-11-28 09:57:28,253][87426] Updated weights for policy 1, policy_version 371330 (0.0011) -[2023-11-28 09:57:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 190210048. Throughput: 0: 2707.8, 1: 2713.2. Samples: 190221368. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:57:28,445][86177] Avg episode reward: [(0, '-585.460'), (1, '-534.150')] -[2023-11-28 09:57:28,634][87426] Updated weights for policy 1, policy_version 371340 (0.0012) -[2023-11-28 09:57:29,012][87426] Updated weights for policy 1, policy_version 371350 (0.0012) -[2023-11-28 09:57:29,383][87426] Updated weights for policy 1, policy_version 371360 (0.0012) -[2023-11-28 09:57:30,183][87424] Updated weights for policy 0, policy_version 371689 (0.0012) -[2023-11-28 09:57:30,562][87424] Updated weights for policy 0, policy_version 371699 (0.0012) -[2023-11-28 09:57:30,945][87424] Updated weights for policy 0, policy_version 371709 (0.0012) -[2023-11-28 09:57:31,490][87426] Updated weights for policy 1, policy_version 371370 (0.0012) -[2023-11-28 09:57:31,866][87426] Updated weights for policy 1, policy_version 371380 (0.0012) -[2023-11-28 09:57:32,245][87426] Updated weights for policy 1, policy_version 371390 (0.0012) -[2023-11-28 09:57:33,207][87424] Updated weights for policy 0, policy_version 371719 (0.0011) -[2023-11-28 09:57:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 190234624. Throughput: 0: 2712.2, 1: 2715.6. Samples: 190245780. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:57:33,445][86177] Avg episode reward: [(0, '-576.440'), (1, '-530.440')] -[2023-11-28 09:57:33,587][87424] Updated weights for policy 0, policy_version 371729 (0.0012) -[2023-11-28 09:57:33,971][87424] Updated weights for policy 0, policy_version 371739 (0.0010) -[2023-11-28 09:57:34,779][87426] Updated weights for policy 1, policy_version 371400 (0.0011) -[2023-11-28 09:57:35,157][87426] Updated weights for policy 1, policy_version 371410 (0.0009) -[2023-11-28 09:57:35,536][87426] Updated weights for policy 1, policy_version 371420 (0.0011) -[2023-11-28 09:57:36,273][87424] Updated weights for policy 0, policy_version 371749 (0.0007) -[2023-11-28 09:57:36,671][87424] Updated weights for policy 0, policy_version 371759 (0.0008) -[2023-11-28 09:57:37,057][87424] Updated weights for policy 0, policy_version 371769 (0.0012) -[2023-11-28 09:57:37,558][87426] Updated weights for policy 1, policy_version 371430 (0.0010) -[2023-11-28 09:57:37,928][87426] Updated weights for policy 1, policy_version 371440 (0.0012) -[2023-11-28 09:57:38,307][87426] Updated weights for policy 1, policy_version 371450 (0.0012) -[2023-11-28 09:57:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190259200. Throughput: 0: 2727.0, 1: 2718.0. Samples: 190278136. Policy #0 lag: (min: 28.0, avg: 46.3, max: 60.0) -[2023-11-28 09:57:38,445][86177] Avg episode reward: [(0, '-579.150'), (1, '-574.850')] -[2023-11-28 09:57:38,869][87424] Updated weights for policy 0, policy_version 371779 (0.0011) -[2023-11-28 09:57:39,249][87424] Updated weights for policy 0, policy_version 371789 (0.0010) -[2023-11-28 09:57:39,624][87424] Updated weights for policy 0, policy_version 371799 (0.0008) -[2023-11-28 09:57:40,816][87426] Updated weights for policy 1, policy_version 371460 (0.0011) -[2023-11-28 09:57:41,194][87426] Updated weights for policy 1, policy_version 371470 (0.0008) -[2023-11-28 09:57:41,595][87426] Updated weights for policy 1, policy_version 371480 (0.0008) -[2023-11-28 09:57:42,250][87424] Updated weights for policy 0, policy_version 371809 (0.0010) -[2023-11-28 09:57:42,635][87424] Updated weights for policy 0, policy_version 371819 (0.0008) -[2023-11-28 09:57:43,011][87424] Updated weights for policy 0, policy_version 371829 (0.0009) -[2023-11-28 09:57:43,395][87424] Updated weights for policy 0, policy_version 371839 (0.0008) -[2023-11-28 09:57:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 190291968. Throughput: 0: 2742.8, 1: 2703.0. Samples: 190302000. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:57:43,445][86177] Avg episode reward: [(0, '-584.980'), (1, '-592.270')] -[2023-11-28 09:57:44,199][87426] Updated weights for policy 1, policy_version 371490 (0.0011) -[2023-11-28 09:57:44,577][87426] Updated weights for policy 1, policy_version 371500 (0.0012) -[2023-11-28 09:57:44,939][87426] Updated weights for policy 1, policy_version 371510 (0.0012) -[2023-11-28 09:57:45,330][87424] Updated weights for policy 0, policy_version 371849 (0.0011) -[2023-11-28 09:57:45,332][87426] Updated weights for policy 1, policy_version 371520 (0.0012) -[2023-11-28 09:57:45,708][87424] Updated weights for policy 0, policy_version 371859 (0.0012) -[2023-11-28 09:57:46,099][87424] Updated weights for policy 0, policy_version 371869 (0.0012) -[2023-11-28 09:57:47,125][87426] Updated weights for policy 1, policy_version 371530 (0.0010) -[2023-11-28 09:57:47,503][87426] Updated weights for policy 1, policy_version 371540 (0.0008) -[2023-11-28 09:57:47,882][87426] Updated weights for policy 1, policy_version 371550 (0.0007) -[2023-11-28 09:57:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 190316544. Throughput: 0: 2747.7, 1: 2700.2. Samples: 190326752. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:57:48,445][86177] Avg episode reward: [(0, '-571.380'), (1, '-586.400')] -[2023-11-28 09:57:48,580][87424] Updated weights for policy 0, policy_version 371879 (0.0009) -[2023-11-28 09:57:48,965][87424] Updated weights for policy 0, policy_version 371889 (0.0009) -[2023-11-28 09:57:49,343][87424] Updated weights for policy 0, policy_version 371899 (0.0011) -[2023-11-28 09:57:50,083][87426] Updated weights for policy 1, policy_version 371560 (0.0011) -[2023-11-28 09:57:50,460][87426] Updated weights for policy 1, policy_version 371570 (0.0012) -[2023-11-28 09:57:50,839][87426] Updated weights for policy 1, policy_version 371580 (0.0011) -[2023-11-28 09:57:51,453][87424] Updated weights for policy 0, policy_version 371909 (0.0010) -[2023-11-28 09:57:51,844][87424] Updated weights for policy 0, policy_version 371919 (0.0011) -[2023-11-28 09:57:52,222][87424] Updated weights for policy 0, policy_version 371929 (0.0012) -[2023-11-28 09:57:53,396][87426] Updated weights for policy 1, policy_version 371590 (0.0011) -[2023-11-28 09:57:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 190341120. Throughput: 0: 2758.8, 1: 2725.9. Samples: 190360440. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:57:53,445][86177] Avg episode reward: [(0, '-589.960'), (1, '-588.420')] -[2023-11-28 09:57:53,775][87426] Updated weights for policy 1, policy_version 371600 (0.0010) -[2023-11-28 09:57:54,153][87426] Updated weights for policy 1, policy_version 371610 (0.0008) -[2023-11-28 09:57:54,459][87424] Updated weights for policy 0, policy_version 371939 (0.0009) -[2023-11-28 09:57:54,843][87424] Updated weights for policy 0, policy_version 371949 (0.0010) -[2023-11-28 09:57:55,227][87424] Updated weights for policy 0, policy_version 371959 (0.0012) -[2023-11-28 09:57:56,055][87426] Updated weights for policy 1, policy_version 371620 (0.0008) -[2023-11-28 09:57:56,429][87426] Updated weights for policy 1, policy_version 371630 (0.0009) -[2023-11-28 09:57:56,814][87426] Updated weights for policy 1, policy_version 371640 (0.0009) -[2023-11-28 09:57:56,917][87424] Updated weights for policy 0, policy_version 371969 (0.0012) -[2023-11-28 09:57:57,303][87424] Updated weights for policy 0, policy_version 371979 (0.0012) -[2023-11-28 09:57:57,687][87424] Updated weights for policy 0, policy_version 371989 (0.0009) -[2023-11-28 09:57:58,065][87424] Updated weights for policy 0, policy_version 371999 (0.0007) -[2023-11-28 09:57:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 190373888. Throughput: 0: 2759.6, 1: 2750.6. Samples: 190385084. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:57:58,445][86177] Avg episode reward: [(0, '-580.760'), (1, '-531.390')] -[2023-11-28 09:57:58,609][87426] Updated weights for policy 1, policy_version 371650 (0.0012) -[2023-11-28 09:57:58,975][87426] Updated weights for policy 1, policy_version 371660 (0.0012) -[2023-11-28 09:57:59,362][87426] Updated weights for policy 1, policy_version 371670 (0.0012) -[2023-11-28 09:57:59,736][87426] Updated weights for policy 1, policy_version 371680 (0.0012) -[2023-11-28 09:58:00,289][87424] Updated weights for policy 0, policy_version 372009 (0.0012) -[2023-11-28 09:58:00,671][87424] Updated weights for policy 0, policy_version 372019 (0.0012) -[2023-11-28 09:58:01,049][87424] Updated weights for policy 0, policy_version 372029 (0.0012) -[2023-11-28 09:58:01,944][87426] Updated weights for policy 1, policy_version 371690 (0.0011) -[2023-11-28 09:58:02,326][87426] Updated weights for policy 1, policy_version 371700 (0.0009) -[2023-11-28 09:58:02,707][87426] Updated weights for policy 1, policy_version 371710 (0.0008) -[2023-11-28 09:58:03,328][87424] Updated weights for policy 0, policy_version 372039 (0.0009) -[2023-11-28 09:58:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 190398464. Throughput: 0: 2757.1, 1: 2732.3. Samples: 190410180. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:03,445][86177] Avg episode reward: [(0, '-563.420'), (1, '-515.910')] -[2023-11-28 09:58:03,717][87424] Updated weights for policy 0, policy_version 372049 (0.0011) -[2023-11-28 09:58:04,104][87424] Updated weights for policy 0, policy_version 372059 (0.0009) -[2023-11-28 09:58:05,229][87426] Updated weights for policy 1, policy_version 371720 (0.0008) -[2023-11-28 09:58:05,603][87426] Updated weights for policy 1, policy_version 371730 (0.0007) -[2023-11-28 09:58:05,984][87426] Updated weights for policy 1, policy_version 371740 (0.0007) -[2023-11-28 09:58:06,433][87424] Updated weights for policy 0, policy_version 372069 (0.0009) -[2023-11-28 09:58:06,823][87424] Updated weights for policy 0, policy_version 372079 (0.0009) -[2023-11-28 09:58:07,207][87424] Updated weights for policy 0, policy_version 372089 (0.0007) -[2023-11-28 09:58:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 190423040. Throughput: 0: 2761.6, 1: 2703.4. Samples: 190441204. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:08,446][86177] Avg episode reward: [(0, '-576.060'), (1, '-521.100')] -[2023-11-28 09:58:08,523][87426] Updated weights for policy 1, policy_version 371750 (0.0010) -[2023-11-28 09:58:08,904][87426] Updated weights for policy 1, policy_version 371760 (0.0012) -[2023-11-28 09:58:09,284][87426] Updated weights for policy 1, policy_version 371770 (0.0011) -[2023-11-28 09:58:09,397][87424] Updated weights for policy 0, policy_version 372099 (0.0010) -[2023-11-28 09:58:09,775][87424] Updated weights for policy 0, policy_version 372109 (0.0011) -[2023-11-28 09:58:10,157][87424] Updated weights for policy 0, policy_version 372119 (0.0011) -[2023-11-28 09:58:11,773][87426] Updated weights for policy 1, policy_version 371780 (0.0009) -[2023-11-28 09:58:12,152][87426] Updated weights for policy 1, policy_version 371790 (0.0010) -[2023-11-28 09:58:12,527][87426] Updated weights for policy 1, policy_version 371800 (0.0009) -[2023-11-28 09:58:12,706][87424] Updated weights for policy 0, policy_version 372129 (0.0010) -[2023-11-28 09:58:13,088][87424] Updated weights for policy 0, policy_version 372139 (0.0010) -[2023-11-28 09:58:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190447616. Throughput: 0: 2739.9, 1: 2658.5. Samples: 190464296. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:13,445][86177] Avg episode reward: [(0, '-583.860'), (1, '-515.280')] -[2023-11-28 09:58:13,476][87424] Updated weights for policy 0, policy_version 372149 (0.0009) -[2023-11-28 09:58:13,861][87424] Updated weights for policy 0, policy_version 372159 (0.0007) -[2023-11-28 09:58:14,777][87426] Updated weights for policy 1, policy_version 371810 (0.0011) -[2023-11-28 09:58:15,156][87426] Updated weights for policy 1, policy_version 371820 (0.0012) -[2023-11-28 09:58:15,532][87426] Updated weights for policy 1, policy_version 371830 (0.0011) -[2023-11-28 09:58:15,745][87424] Updated weights for policy 0, policy_version 372169 (0.0011) -[2023-11-28 09:58:15,907][87426] Updated weights for policy 1, policy_version 371840 (0.0010) -[2023-11-28 09:58:16,130][87424] Updated weights for policy 0, policy_version 372179 (0.0012) -[2023-11-28 09:58:16,510][87424] Updated weights for policy 0, policy_version 372189 (0.0012) -[2023-11-28 09:58:18,048][87426] Updated weights for policy 1, policy_version 371850 (0.0012) -[2023-11-28 09:58:18,192][87424] Updated weights for policy 0, policy_version 372199 (0.0012) -[2023-11-28 09:58:18,421][87426] Updated weights for policy 1, policy_version 371860 (0.0011) -[2023-11-28 09:58:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190472192. Throughput: 0: 2730.5, 1: 2665.7. Samples: 190488608. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:18,445][86177] Avg episode reward: [(0, '-570.260'), (1, '-524.830')] -[2023-11-28 09:58:18,571][87424] Updated weights for policy 0, policy_version 372209 (0.0011) -[2023-11-28 09:58:18,797][87426] Updated weights for policy 1, policy_version 371870 (0.0011) -[2023-11-28 09:58:18,873][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000371872_95199232.pth... -[2023-11-28 09:58:18,917][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000369344_94552064.pth -[2023-11-28 09:58:18,957][87424] Updated weights for policy 0, policy_version 372219 (0.0011) -[2023-11-28 09:58:19,149][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000372224_95289344.pth... -[2023-11-28 09:58:19,189][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000369664_94633984.pth -[2023-11-28 09:58:21,183][87426] Updated weights for policy 1, policy_version 371880 (0.0011) -[2023-11-28 09:58:21,261][87424] Updated weights for policy 0, policy_version 372229 (0.0011) -[2023-11-28 09:58:21,558][87426] Updated weights for policy 1, policy_version 371890 (0.0011) -[2023-11-28 09:58:21,632][87424] Updated weights for policy 0, policy_version 372239 (0.0011) -[2023-11-28 09:58:21,939][87426] Updated weights for policy 1, policy_version 371900 (0.0014) -[2023-11-28 09:58:22,017][87424] Updated weights for policy 0, policy_version 372249 (0.0010) -[2023-11-28 09:58:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 190504960. Throughput: 0: 2760.7, 1: 2660.8. Samples: 190522104. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:23,445][86177] Avg episode reward: [(0, '-583.410'), (1, '-528.580')] -[2023-11-28 09:58:24,319][87426] Updated weights for policy 1, policy_version 371910 (0.0010) -[2023-11-28 09:58:24,584][87424] Updated weights for policy 0, policy_version 372259 (0.0011) -[2023-11-28 09:58:24,697][87426] Updated weights for policy 1, policy_version 371920 (0.0011) -[2023-11-28 09:58:24,959][87424] Updated weights for policy 0, policy_version 372269 (0.0009) -[2023-11-28 09:58:25,076][87426] Updated weights for policy 1, policy_version 371930 (0.0010) -[2023-11-28 09:58:25,348][87424] Updated weights for policy 0, policy_version 372279 (0.0010) -[2023-11-28 09:58:26,955][87426] Updated weights for policy 1, policy_version 371940 (0.0011) -[2023-11-28 09:58:27,334][87426] Updated weights for policy 1, policy_version 371950 (0.0009) -[2023-11-28 09:58:27,712][87426] Updated weights for policy 1, policy_version 371960 (0.0007) -[2023-11-28 09:58:27,746][87424] Updated weights for policy 0, policy_version 372289 (0.0012) -[2023-11-28 09:58:28,126][87424] Updated weights for policy 0, policy_version 372299 (0.0008) -[2023-11-28 09:58:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190529536. Throughput: 0: 2733.9, 1: 2677.3. Samples: 190545504. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:28,445][86177] Avg episode reward: [(0, '-593.560'), (1, '-527.590')] -[2023-11-28 09:58:28,506][87424] Updated weights for policy 0, policy_version 372309 (0.0007) -[2023-11-28 09:58:28,897][87424] Updated weights for policy 0, policy_version 372319 (0.0009) -[2023-11-28 09:58:29,830][87426] Updated weights for policy 1, policy_version 371970 (0.0008) -[2023-11-28 09:58:30,204][87426] Updated weights for policy 1, policy_version 371980 (0.0012) -[2023-11-28 09:58:30,588][87426] Updated weights for policy 1, policy_version 371990 (0.0012) -[2023-11-28 09:58:30,961][87426] Updated weights for policy 1, policy_version 372000 (0.0011) -[2023-11-28 09:58:31,029][87424] Updated weights for policy 0, policy_version 372329 (0.0011) -[2023-11-28 09:58:31,402][87424] Updated weights for policy 0, policy_version 372339 (0.0011) -[2023-11-28 09:58:31,775][87424] Updated weights for policy 0, policy_version 372349 (0.0012) -[2023-11-28 09:58:33,079][87426] Updated weights for policy 1, policy_version 372010 (0.0009) -[2023-11-28 09:58:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190554112. Throughput: 0: 2723.7, 1: 2690.8. Samples: 190570404. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:33,445][86177] Avg episode reward: [(0, '-575.120'), (1, '-532.120')] -[2023-11-28 09:58:33,459][87426] Updated weights for policy 1, policy_version 372020 (0.0008) -[2023-11-28 09:58:33,838][87426] Updated weights for policy 1, policy_version 372030 (0.0008) -[2023-11-28 09:58:34,034][87424] Updated weights for policy 0, policy_version 372359 (0.0011) -[2023-11-28 09:58:34,423][87424] Updated weights for policy 0, policy_version 372369 (0.0012) -[2023-11-28 09:58:34,811][87424] Updated weights for policy 0, policy_version 372379 (0.0012) -[2023-11-28 09:58:36,047][87426] Updated weights for policy 1, policy_version 372040 (0.0011) -[2023-11-28 09:58:36,426][87426] Updated weights for policy 1, policy_version 372050 (0.0012) -[2023-11-28 09:58:36,776][87424] Updated weights for policy 0, policy_version 372389 (0.0011) -[2023-11-28 09:58:36,802][87426] Updated weights for policy 1, policy_version 372060 (0.0010) -[2023-11-28 09:58:37,159][87424] Updated weights for policy 0, policy_version 372399 (0.0012) -[2023-11-28 09:58:37,542][87424] Updated weights for policy 0, policy_version 372409 (0.0012) -[2023-11-28 09:58:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 190586880. Throughput: 0: 2701.6, 1: 2680.0. Samples: 190602612. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:38,445][86177] Avg episode reward: [(0, '-593.020'), (1, '-523.460')] -[2023-11-28 09:58:38,986][87426] Updated weights for policy 1, policy_version 372070 (0.0009) -[2023-11-28 09:58:39,371][87426] Updated weights for policy 1, policy_version 372080 (0.0012) -[2023-11-28 09:58:39,531][87424] Updated weights for policy 0, policy_version 372419 (0.0011) -[2023-11-28 09:58:39,747][87426] Updated weights for policy 1, policy_version 372090 (0.0011) -[2023-11-28 09:58:39,912][87424] Updated weights for policy 0, policy_version 372429 (0.0010) -[2023-11-28 09:58:40,296][87424] Updated weights for policy 0, policy_version 372439 (0.0012) -[2023-11-28 09:58:41,889][87426] Updated weights for policy 1, policy_version 372100 (0.0011) -[2023-11-28 09:58:42,285][87426] Updated weights for policy 1, policy_version 372110 (0.0011) -[2023-11-28 09:58:42,660][87426] Updated weights for policy 1, policy_version 372120 (0.0010) -[2023-11-28 09:58:42,714][87424] Updated weights for policy 0, policy_version 372449 (0.0010) -[2023-11-28 09:58:43,093][87424] Updated weights for policy 0, policy_version 372459 (0.0009) -[2023-11-28 09:58:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190611456. Throughput: 0: 2689.5, 1: 2672.8. Samples: 190626388. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:43,445][86177] Avg episode reward: [(0, '-590.310'), (1, '-508.850')] -[2023-11-28 09:58:43,481][87424] Updated weights for policy 0, policy_version 372469 (0.0011) -[2023-11-28 09:58:43,866][87424] Updated weights for policy 0, policy_version 372479 (0.0012) -[2023-11-28 09:58:44,592][87426] Updated weights for policy 1, policy_version 372130 (0.0011) -[2023-11-28 09:58:44,966][87426] Updated weights for policy 1, policy_version 372140 (0.0012) -[2023-11-28 09:58:45,339][87426] Updated weights for policy 1, policy_version 372150 (0.0012) -[2023-11-28 09:58:45,720][87426] Updated weights for policy 1, policy_version 372160 (0.0012) -[2023-11-28 09:58:46,246][87424] Updated weights for policy 0, policy_version 372489 (0.0012) -[2023-11-28 09:58:46,617][87424] Updated weights for policy 0, policy_version 372499 (0.0012) -[2023-11-28 09:58:47,000][87424] Updated weights for policy 0, policy_version 372509 (0.0012) -[2023-11-28 09:58:47,818][87426] Updated weights for policy 1, policy_version 372170 (0.0007) -[2023-11-28 09:58:48,192][87426] Updated weights for policy 1, policy_version 372180 (0.0007) -[2023-11-28 09:58:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190636032. Throughput: 0: 2665.5, 1: 2701.4. Samples: 190651692. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:48,445][86177] Avg episode reward: [(0, '-580.830'), (1, '-508.110')] -[2023-11-28 09:58:48,578][87426] Updated weights for policy 1, policy_version 372190 (0.0007) -[2023-11-28 09:58:49,169][87424] Updated weights for policy 0, policy_version 372519 (0.0011) -[2023-11-28 09:58:49,557][87424] Updated weights for policy 0, policy_version 372529 (0.0011) -[2023-11-28 09:58:49,930][87424] Updated weights for policy 0, policy_version 372539 (0.0013) -[2023-11-28 09:58:50,694][87426] Updated weights for policy 1, policy_version 372200 (0.0011) -[2023-11-28 09:58:51,060][87426] Updated weights for policy 1, policy_version 372210 (0.0012) -[2023-11-28 09:58:51,437][87426] Updated weights for policy 1, policy_version 372220 (0.0012) -[2023-11-28 09:58:52,145][87424] Updated weights for policy 0, policy_version 372549 (0.0008) -[2023-11-28 09:58:52,529][87424] Updated weights for policy 0, policy_version 372559 (0.0010) -[2023-11-28 09:58:52,903][87424] Updated weights for policy 0, policy_version 372569 (0.0011) -[2023-11-28 09:58:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 190668800. Throughput: 0: 2666.1, 1: 2736.4. Samples: 190684316. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:53,445][86177] Avg episode reward: [(0, '-593.060'), (1, '-508.960')] -[2023-11-28 09:58:54,009][87426] Updated weights for policy 1, policy_version 372230 (0.0012) -[2023-11-28 09:58:54,385][87426] Updated weights for policy 1, policy_version 372240 (0.0012) -[2023-11-28 09:58:54,754][87426] Updated weights for policy 1, policy_version 372250 (0.0012) -[2023-11-28 09:58:55,392][87424] Updated weights for policy 0, policy_version 372579 (0.0012) -[2023-11-28 09:58:55,767][87424] Updated weights for policy 0, policy_version 372589 (0.0012) -[2023-11-28 09:58:56,162][87424] Updated weights for policy 0, policy_version 372599 (0.0012) -[2023-11-28 09:58:56,585][87426] Updated weights for policy 1, policy_version 372260 (0.0012) -[2023-11-28 09:58:56,970][87426] Updated weights for policy 1, policy_version 372270 (0.0012) -[2023-11-28 09:58:57,349][87426] Updated weights for policy 1, policy_version 372280 (0.0012) -[2023-11-28 09:58:58,211][87424] Updated weights for policy 0, policy_version 372609 (0.0012) -[2023-11-28 09:58:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 190693376. Throughput: 0: 2669.2, 1: 2751.4. Samples: 190708224. Policy #0 lag: (min: 26.0, avg: 42.4, max: 58.0) -[2023-11-28 09:58:58,445][86177] Avg episode reward: [(0, '-633.020'), (1, '-511.720')] -[2023-11-28 09:58:58,599][87424] Updated weights for policy 0, policy_version 372619 (0.0012) -[2023-11-28 09:58:58,987][87424] Updated weights for policy 0, policy_version 372629 (0.0012) -[2023-11-28 09:58:59,367][87424] Updated weights for policy 0, policy_version 372639 (0.0011) -[2023-11-28 09:58:59,485][87426] Updated weights for policy 1, policy_version 372290 (0.0011) -[2023-11-28 09:58:59,874][87426] Updated weights for policy 1, policy_version 372300 (0.0008) -[2023-11-28 09:59:00,257][87426] Updated weights for policy 1, policy_version 372310 (0.0008) -[2023-11-28 09:59:00,632][87426] Updated weights for policy 1, policy_version 372320 (0.0011) -[2023-11-28 09:59:01,719][87424] Updated weights for policy 0, policy_version 372649 (0.0011) -[2023-11-28 09:59:02,098][87424] Updated weights for policy 0, policy_version 372659 (0.0012) -[2023-11-28 09:59:02,484][87424] Updated weights for policy 0, policy_version 372669 (0.0012) -[2023-11-28 09:59:02,800][87426] Updated weights for policy 1, policy_version 372330 (0.0008) -[2023-11-28 09:59:03,185][87426] Updated weights for policy 1, policy_version 372340 (0.0009) -[2023-11-28 09:59:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190717952. Throughput: 0: 2685.3, 1: 2739.5. Samples: 190732724. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:03,445][86177] Avg episode reward: [(0, '-616.200'), (1, '-517.050')] -[2023-11-28 09:59:03,573][87426] Updated weights for policy 1, policy_version 372350 (0.0008) -[2023-11-28 09:59:04,948][87424] Updated weights for policy 0, policy_version 372679 (0.0010) -[2023-11-28 09:59:05,325][87424] Updated weights for policy 0, policy_version 372689 (0.0011) -[2023-11-28 09:59:05,705][87424] Updated weights for policy 0, policy_version 372699 (0.0009) -[2023-11-28 09:59:05,898][87426] Updated weights for policy 1, policy_version 372360 (0.0010) -[2023-11-28 09:59:06,278][87426] Updated weights for policy 1, policy_version 372370 (0.0008) -[2023-11-28 09:59:06,678][87426] Updated weights for policy 1, policy_version 372380 (0.0008) -[2023-11-28 09:59:08,133][87424] Updated weights for policy 0, policy_version 372709 (0.0010) -[2023-11-28 09:59:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190742528. Throughput: 0: 2648.6, 1: 2744.7. Samples: 190764804. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:08,445][86177] Avg episode reward: [(0, '-604.270'), (1, '-514.350')] -[2023-11-28 09:59:08,510][87424] Updated weights for policy 0, policy_version 372719 (0.0012) -[2023-11-28 09:59:08,699][87426] Updated weights for policy 1, policy_version 372390 (0.0008) -[2023-11-28 09:59:08,887][87424] Updated weights for policy 0, policy_version 372729 (0.0011) -[2023-11-28 09:59:09,075][87426] Updated weights for policy 1, policy_version 372400 (0.0008) -[2023-11-28 09:59:09,459][87426] Updated weights for policy 1, policy_version 372410 (0.0008) -[2023-11-28 09:59:11,065][87424] Updated weights for policy 0, policy_version 372739 (0.0009) -[2023-11-28 09:59:11,449][87424] Updated weights for policy 0, policy_version 372749 (0.0011) -[2023-11-28 09:59:11,831][87424] Updated weights for policy 0, policy_version 372759 (0.0009) -[2023-11-28 09:59:11,912][87426] Updated weights for policy 1, policy_version 372420 (0.0009) -[2023-11-28 09:59:12,285][87426] Updated weights for policy 1, policy_version 372430 (0.0012) -[2023-11-28 09:59:12,668][87426] Updated weights for policy 1, policy_version 372440 (0.0012) -[2023-11-28 09:59:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 190775296. Throughput: 0: 2660.5, 1: 2728.8. Samples: 190788024. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:13,445][86177] Avg episode reward: [(0, '-585.320'), (1, '-518.890')] -[2023-11-28 09:59:14,288][87424] Updated weights for policy 0, policy_version 372769 (0.0011) -[2023-11-28 09:59:14,669][87424] Updated weights for policy 0, policy_version 372779 (0.0011) -[2023-11-28 09:59:14,825][87426] Updated weights for policy 1, policy_version 372450 (0.0012) -[2023-11-28 09:59:15,051][87424] Updated weights for policy 0, policy_version 372789 (0.0012) -[2023-11-28 09:59:15,206][87426] Updated weights for policy 1, policy_version 372460 (0.0011) -[2023-11-28 09:59:15,433][87424] Updated weights for policy 0, policy_version 372799 (0.0011) -[2023-11-28 09:59:15,580][87426] Updated weights for policy 1, policy_version 372470 (0.0010) -[2023-11-28 09:59:15,953][87426] Updated weights for policy 1, policy_version 372480 (0.0010) -[2023-11-28 09:59:17,446][87424] Updated weights for policy 0, policy_version 372809 (0.0008) -[2023-11-28 09:59:17,828][87424] Updated weights for policy 0, policy_version 372819 (0.0009) -[2023-11-28 09:59:18,104][87426] Updated weights for policy 1, policy_version 372490 (0.0011) -[2023-11-28 09:59:18,210][87424] Updated weights for policy 0, policy_version 372829 (0.0012) -[2023-11-28 09:59:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 190799872. Throughput: 0: 2639.5, 1: 2731.7. Samples: 190812112. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:18,446][86177] Avg episode reward: [(0, '-536.670'), (1, '-517.950')] -[2023-11-28 09:59:18,486][87426] Updated weights for policy 1, policy_version 372500 (0.0011) -[2023-11-28 09:59:18,881][87426] Updated weights for policy 1, policy_version 372510 (0.0012) -[2023-11-28 09:59:19,925][87424] Updated weights for policy 0, policy_version 372839 (0.0011) -[2023-11-28 09:59:20,306][87424] Updated weights for policy 0, policy_version 372849 (0.0011) -[2023-11-28 09:59:20,690][87424] Updated weights for policy 0, policy_version 372859 (0.0010) -[2023-11-28 09:59:21,425][87426] Updated weights for policy 1, policy_version 372520 (0.0012) -[2023-11-28 09:59:21,809][87426] Updated weights for policy 1, policy_version 372530 (0.0012) -[2023-11-28 09:59:22,190][87426] Updated weights for policy 1, policy_version 372540 (0.0011) -[2023-11-28 09:59:22,721][87424] Updated weights for policy 0, policy_version 372869 (0.0011) -[2023-11-28 09:59:23,101][87424] Updated weights for policy 0, policy_version 372879 (0.0012) -[2023-11-28 09:59:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190824448. Throughput: 0: 2644.7, 1: 2718.8. Samples: 190843968. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:23,445][86177] Avg episode reward: [(0, '-536.230'), (1, '-518.810')] -[2023-11-28 09:59:23,488][87424] Updated weights for policy 0, policy_version 372889 (0.0012) -[2023-11-28 09:59:24,131][87426] Updated weights for policy 1, policy_version 372550 (0.0009) -[2023-11-28 09:59:24,514][87426] Updated weights for policy 1, policy_version 372560 (0.0007) -[2023-11-28 09:59:24,890][87426] Updated weights for policy 1, policy_version 372570 (0.0009) -[2023-11-28 09:59:25,717][87424] Updated weights for policy 0, policy_version 372899 (0.0012) -[2023-11-28 09:59:26,109][87424] Updated weights for policy 0, policy_version 372909 (0.0011) -[2023-11-28 09:59:26,480][87424] Updated weights for policy 0, policy_version 372919 (0.0012) -[2023-11-28 09:59:26,837][87426] Updated weights for policy 1, policy_version 372580 (0.0008) -[2023-11-28 09:59:27,213][87426] Updated weights for policy 1, policy_version 372590 (0.0007) -[2023-11-28 09:59:27,596][87426] Updated weights for policy 1, policy_version 372600 (0.0008) -[2023-11-28 09:59:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 190857216. Throughput: 0: 2660.7, 1: 2750.7. Samples: 190869900. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:28,445][86177] Avg episode reward: [(0, '-564.710'), (1, '-524.320')] -[2023-11-28 09:59:28,628][87424] Updated weights for policy 0, policy_version 372929 (0.0012) -[2023-11-28 09:59:29,004][87424] Updated weights for policy 0, policy_version 372939 (0.0012) -[2023-11-28 09:59:29,391][87424] Updated weights for policy 0, policy_version 372949 (0.0012) -[2023-11-28 09:59:29,432][87426] Updated weights for policy 1, policy_version 372610 (0.0009) -[2023-11-28 09:59:29,761][87424] Updated weights for policy 0, policy_version 372959 (0.0011) -[2023-11-28 09:59:29,815][87426] Updated weights for policy 1, policy_version 372620 (0.0011) -[2023-11-28 09:59:30,190][87426] Updated weights for policy 1, policy_version 372630 (0.0011) -[2023-11-28 09:59:30,563][87426] Updated weights for policy 1, policy_version 372640 (0.0009) -[2023-11-28 09:59:32,217][87424] Updated weights for policy 0, policy_version 372969 (0.0011) -[2023-11-28 09:59:32,599][87424] Updated weights for policy 0, policy_version 372979 (0.0009) -[2023-11-28 09:59:32,898][87426] Updated weights for policy 1, policy_version 372650 (0.0012) -[2023-11-28 09:59:32,983][87424] Updated weights for policy 0, policy_version 372989 (0.0011) -[2023-11-28 09:59:33,272][87426] Updated weights for policy 1, policy_version 372660 (0.0011) -[2023-11-28 09:59:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 190881792. Throughput: 0: 2665.2, 1: 2738.0. Samples: 190894840. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:33,445][86177] Avg episode reward: [(0, '-591.030'), (1, '-513.890')] -[2023-11-28 09:59:33,652][87426] Updated weights for policy 1, policy_version 372670 (0.0012) -[2023-11-28 09:59:34,857][87424] Updated weights for policy 0, policy_version 372999 (0.0011) -[2023-11-28 09:59:35,252][87424] Updated weights for policy 0, policy_version 373009 (0.0011) -[2023-11-28 09:59:35,624][87424] Updated weights for policy 0, policy_version 373019 (0.0011) -[2023-11-28 09:59:35,889][87426] Updated weights for policy 1, policy_version 372680 (0.0012) -[2023-11-28 09:59:36,265][87426] Updated weights for policy 1, policy_version 372690 (0.0012) -[2023-11-28 09:59:36,650][87426] Updated weights for policy 1, policy_version 372700 (0.0009) -[2023-11-28 09:59:37,434][87424] Updated weights for policy 0, policy_version 373029 (0.0011) -[2023-11-28 09:59:37,819][87424] Updated weights for policy 0, policy_version 373039 (0.0012) -[2023-11-28 09:59:38,193][87424] Updated weights for policy 0, policy_version 373049 (0.0012) -[2023-11-28 09:59:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190906368. Throughput: 0: 2679.6, 1: 2717.1. Samples: 190927164. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:38,445][86177] Avg episode reward: [(0, '-591.380'), (1, '-509.670')] -[2023-11-28 09:59:38,705][87426] Updated weights for policy 1, policy_version 372710 (0.0009) -[2023-11-28 09:59:39,077][87426] Updated weights for policy 1, policy_version 372720 (0.0011) -[2023-11-28 09:59:39,457][87426] Updated weights for policy 1, policy_version 372730 (0.0011) -[2023-11-28 09:59:40,302][87424] Updated weights for policy 0, policy_version 373059 (0.0011) -[2023-11-28 09:59:40,685][87424] Updated weights for policy 0, policy_version 373069 (0.0012) -[2023-11-28 09:59:41,068][87424] Updated weights for policy 0, policy_version 373079 (0.0012) -[2023-11-28 09:59:41,651][87426] Updated weights for policy 1, policy_version 372740 (0.0011) -[2023-11-28 09:59:42,028][87426] Updated weights for policy 1, policy_version 372750 (0.0012) -[2023-11-28 09:59:42,405][87426] Updated weights for policy 1, policy_version 372760 (0.0010) -[2023-11-28 09:59:43,201][87424] Updated weights for policy 0, policy_version 373089 (0.0012) -[2023-11-28 09:59:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 190939136. Throughput: 0: 2689.3, 1: 2708.5. Samples: 190951124. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:43,445][86177] Avg episode reward: [(0, '-603.420'), (1, '-515.700')] -[2023-11-28 09:59:43,584][87424] Updated weights for policy 0, policy_version 373099 (0.0012) -[2023-11-28 09:59:43,970][87424] Updated weights for policy 0, policy_version 373109 (0.0011) -[2023-11-28 09:59:44,350][87424] Updated weights for policy 0, policy_version 373119 (0.0011) -[2023-11-28 09:59:44,445][87426] Updated weights for policy 1, policy_version 372770 (0.0010) -[2023-11-28 09:59:44,826][87426] Updated weights for policy 1, policy_version 372780 (0.0007) -[2023-11-28 09:59:45,207][87426] Updated weights for policy 1, policy_version 372790 (0.0009) -[2023-11-28 09:59:45,588][87426] Updated weights for policy 1, policy_version 372800 (0.0009) -[2023-11-28 09:59:46,845][87424] Updated weights for policy 0, policy_version 373129 (0.0010) -[2023-11-28 09:59:47,225][87424] Updated weights for policy 0, policy_version 373139 (0.0008) -[2023-11-28 09:59:47,605][87424] Updated weights for policy 0, policy_version 373149 (0.0007) -[2023-11-28 09:59:48,122][87426] Updated weights for policy 1, policy_version 372810 (0.0007) -[2023-11-28 09:59:48,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 190963712. Throughput: 0: 2673.3, 1: 2726.2. Samples: 190975704. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:48,446][86177] Avg episode reward: [(0, '-575.970'), (1, '-533.210')] -[2023-11-28 09:59:48,506][87426] Updated weights for policy 1, policy_version 372820 (0.0007) -[2023-11-28 09:59:48,901][87426] Updated weights for policy 1, policy_version 372830 (0.0010) -[2023-11-28 09:59:50,159][87424] Updated weights for policy 0, policy_version 373159 (0.0009) -[2023-11-28 09:59:50,547][87424] Updated weights for policy 0, policy_version 373169 (0.0010) -[2023-11-28 09:59:50,931][87424] Updated weights for policy 0, policy_version 373179 (0.0008) -[2023-11-28 09:59:51,246][87426] Updated weights for policy 1, policy_version 372840 (0.0010) -[2023-11-28 09:59:51,622][87426] Updated weights for policy 1, policy_version 372850 (0.0012) -[2023-11-28 09:59:51,996][87426] Updated weights for policy 1, policy_version 372860 (0.0012) -[2023-11-28 09:59:53,062][87424] Updated weights for policy 0, policy_version 373189 (0.0011) -[2023-11-28 09:59:53,441][87424] Updated weights for policy 0, policy_version 373199 (0.0012) -[2023-11-28 09:59:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 190988288. Throughput: 0: 2669.8, 1: 2712.2. Samples: 191006992. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:53,445][86177] Avg episode reward: [(0, '-547.360'), (1, '-546.790')] -[2023-11-28 09:59:53,820][87424] Updated weights for policy 0, policy_version 373209 (0.0011) -[2023-11-28 09:59:54,184][87426] Updated weights for policy 1, policy_version 372870 (0.0009) -[2023-11-28 09:59:54,560][87426] Updated weights for policy 1, policy_version 372880 (0.0008) -[2023-11-28 09:59:54,939][87426] Updated weights for policy 1, policy_version 372890 (0.0007) -[2023-11-28 09:59:56,342][87424] Updated weights for policy 0, policy_version 373219 (0.0011) -[2023-11-28 09:59:56,725][87424] Updated weights for policy 0, policy_version 373229 (0.0008) -[2023-11-28 09:59:57,106][87424] Updated weights for policy 0, policy_version 373239 (0.0009) -[2023-11-28 09:59:57,149][87426] Updated weights for policy 1, policy_version 372900 (0.0009) -[2023-11-28 09:59:57,525][87426] Updated weights for policy 1, policy_version 372910 (0.0012) -[2023-11-28 09:59:57,902][87426] Updated weights for policy 1, policy_version 372920 (0.0012) -[2023-11-28 09:59:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 191021056. Throughput: 0: 2670.8, 1: 2726.8. Samples: 191030916. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 09:59:58,445][86177] Avg episode reward: [(0, '-553.920'), (1, '-546.540')] -[2023-11-28 09:59:59,097][87424] Updated weights for policy 0, policy_version 373249 (0.0008) -[2023-11-28 09:59:59,480][87424] Updated weights for policy 0, policy_version 373259 (0.0012) -[2023-11-28 09:59:59,853][87426] Updated weights for policy 1, policy_version 372930 (0.0012) -[2023-11-28 09:59:59,859][87424] Updated weights for policy 0, policy_version 373269 (0.0011) -[2023-11-28 10:00:00,236][87424] Updated weights for policy 0, policy_version 373279 (0.0012) -[2023-11-28 10:00:00,243][87426] Updated weights for policy 1, policy_version 372940 (0.0010) -[2023-11-28 10:00:00,613][87426] Updated weights for policy 1, policy_version 372950 (0.0012) -[2023-11-28 10:00:00,998][87426] Updated weights for policy 1, policy_version 372960 (0.0012) -[2023-11-28 10:00:02,631][87424] Updated weights for policy 0, policy_version 373289 (0.0011) -[2023-11-28 10:00:03,005][87424] Updated weights for policy 0, policy_version 373299 (0.0011) -[2023-11-28 10:00:03,265][87426] Updated weights for policy 1, policy_version 372970 (0.0010) -[2023-11-28 10:00:03,386][87424] Updated weights for policy 0, policy_version 373309 (0.0010) -[2023-11-28 10:00:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191037440. Throughput: 0: 2707.0, 1: 2709.4. Samples: 191055852. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 10:00:03,445][86177] Avg episode reward: [(0, '-545.690'), (1, '-542.130')] -[2023-11-28 10:00:03,640][87426] Updated weights for policy 1, policy_version 372980 (0.0008) -[2023-11-28 10:00:04,025][87426] Updated weights for policy 1, policy_version 372990 (0.0007) -[2023-11-28 10:00:05,477][87424] Updated weights for policy 0, policy_version 373319 (0.0012) -[2023-11-28 10:00:05,863][87424] Updated weights for policy 0, policy_version 373329 (0.0012) -[2023-11-28 10:00:06,098][87426] Updated weights for policy 1, policy_version 373000 (0.0008) -[2023-11-28 10:00:06,238][87424] Updated weights for policy 0, policy_version 373339 (0.0011) -[2023-11-28 10:00:06,480][87426] Updated weights for policy 1, policy_version 373010 (0.0007) -[2023-11-28 10:00:06,867][87426] Updated weights for policy 1, policy_version 373020 (0.0008) -[2023-11-28 10:00:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 191070208. Throughput: 0: 2694.7, 1: 2758.0. Samples: 191089336. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 10:00:08,445][86177] Avg episode reward: [(0, '-556.420'), (1, '-527.450')] -[2023-11-28 10:00:08,622][87424] Updated weights for policy 0, policy_version 373349 (0.0012) -[2023-11-28 10:00:08,678][87426] Updated weights for policy 1, policy_version 373030 (0.0010) -[2023-11-28 10:00:09,002][87424] Updated weights for policy 0, policy_version 373359 (0.0009) -[2023-11-28 10:00:09,044][87426] Updated weights for policy 1, policy_version 373040 (0.0009) -[2023-11-28 10:00:09,383][87424] Updated weights for policy 0, policy_version 373369 (0.0008) -[2023-11-28 10:00:09,427][87426] Updated weights for policy 1, policy_version 373050 (0.0010) -[2023-11-28 10:00:11,805][87424] Updated weights for policy 0, policy_version 373379 (0.0008) -[2023-11-28 10:00:11,905][87426] Updated weights for policy 1, policy_version 373060 (0.0012) -[2023-11-28 10:00:12,185][87424] Updated weights for policy 0, policy_version 373389 (0.0011) -[2023-11-28 10:00:12,290][87426] Updated weights for policy 1, policy_version 373070 (0.0012) -[2023-11-28 10:00:12,561][87424] Updated weights for policy 0, policy_version 373399 (0.0010) -[2023-11-28 10:00:12,663][87426] Updated weights for policy 1, policy_version 373080 (0.0011) -[2023-11-28 10:00:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 191102976. Throughput: 0: 2675.9, 1: 2730.9. Samples: 191113208. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 10:00:13,445][86177] Avg episode reward: [(0, '-568.430'), (1, '-512.880')] -[2023-11-28 10:00:14,722][87426] Updated weights for policy 1, policy_version 373090 (0.0012) -[2023-11-28 10:00:14,912][87424] Updated weights for policy 0, policy_version 373409 (0.0009) -[2023-11-28 10:00:15,092][87426] Updated weights for policy 1, policy_version 373100 (0.0008) -[2023-11-28 10:00:15,293][87424] Updated weights for policy 0, policy_version 373419 (0.0008) -[2023-11-28 10:00:15,473][87426] Updated weights for policy 1, policy_version 373110 (0.0010) -[2023-11-28 10:00:15,671][87424] Updated weights for policy 0, policy_version 373429 (0.0011) -[2023-11-28 10:00:15,849][87426] Updated weights for policy 1, policy_version 373120 (0.0011) -[2023-11-28 10:00:16,055][87424] Updated weights for policy 0, policy_version 373439 (0.0012) -[2023-11-28 10:00:17,741][87426] Updated weights for policy 1, policy_version 373130 (0.0012) -[2023-11-28 10:00:18,020][87424] Updated weights for policy 0, policy_version 373449 (0.0009) -[2023-11-28 10:00:18,125][87426] Updated weights for policy 1, policy_version 373140 (0.0011) -[2023-11-28 10:00:18,398][87424] Updated weights for policy 0, policy_version 373459 (0.0008) -[2023-11-28 10:00:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191119360. Throughput: 0: 2655.6, 1: 2739.0. Samples: 191137600. Policy #0 lag: (min: 44.0, avg: 50.7, max: 76.0) -[2023-11-28 10:00:18,445][86177] Avg episode reward: [(0, '-585.420'), (1, '-539.290')] -[2023-11-28 10:00:18,487][87426] Updated weights for policy 1, policy_version 373150 (0.0011) -[2023-11-28 10:00:18,561][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000373152_95526912.pth... -[2023-11-28 10:00:18,592][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000370592_94871552.pth -[2023-11-28 10:00:18,771][87424] Updated weights for policy 0, policy_version 373469 (0.0011) -[2023-11-28 10:00:18,889][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000373472_95608832.pth... -[2023-11-28 10:00:18,937][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000370944_94961664.pth -[2023-11-28 10:00:20,509][87426] Updated weights for policy 1, policy_version 373160 (0.0012) -[2023-11-28 10:00:20,811][87424] Updated weights for policy 0, policy_version 373479 (0.0012) -[2023-11-28 10:00:20,891][87426] Updated weights for policy 1, policy_version 373170 (0.0010) -[2023-11-28 10:00:21,201][87424] Updated weights for policy 0, policy_version 373489 (0.0012) -[2023-11-28 10:00:21,261][87426] Updated weights for policy 1, policy_version 373180 (0.0009) -[2023-11-28 10:00:21,576][87424] Updated weights for policy 0, policy_version 373499 (0.0012) -[2023-11-28 10:00:23,281][87426] Updated weights for policy 1, policy_version 373190 (0.0008) -[2023-11-28 10:00:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 191152128. Throughput: 0: 2647.6, 1: 2762.0. Samples: 191170600. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:00:23,445][86177] Avg episode reward: [(0, '-590.100'), (1, '-541.930')] -[2023-11-28 10:00:23,667][87426] Updated weights for policy 1, policy_version 373200 (0.0007) -[2023-11-28 10:00:24,049][87426] Updated weights for policy 1, policy_version 373210 (0.0011) -[2023-11-28 10:00:24,321][87424] Updated weights for policy 0, policy_version 373509 (0.0010) -[2023-11-28 10:00:24,707][87424] Updated weights for policy 0, policy_version 373519 (0.0008) -[2023-11-28 10:00:25,087][87424] Updated weights for policy 0, policy_version 373529 (0.0007) -[2023-11-28 10:00:26,511][87426] Updated weights for policy 1, policy_version 373220 (0.0011) -[2023-11-28 10:00:26,901][87426] Updated weights for policy 1, policy_version 373230 (0.0012) -[2023-11-28 10:00:26,994][87424] Updated weights for policy 0, policy_version 373539 (0.0010) -[2023-11-28 10:00:27,277][87426] Updated weights for policy 1, policy_version 373240 (0.0012) -[2023-11-28 10:00:27,372][87424] Updated weights for policy 0, policy_version 373549 (0.0010) -[2023-11-28 10:00:27,770][87424] Updated weights for policy 0, policy_version 373559 (0.0008) -[2023-11-28 10:00:28,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 191184896. Throughput: 0: 2637.9, 1: 2765.6. Samples: 191194284. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:00:28,445][86177] Avg episode reward: [(0, '-576.650'), (1, '-535.670')] -[2023-11-28 10:00:29,572][87426] Updated weights for policy 1, policy_version 373250 (0.0009) -[2023-11-28 10:00:29,954][87426] Updated weights for policy 1, policy_version 373260 (0.0010) -[2023-11-28 10:00:30,198][87424] Updated weights for policy 0, policy_version 373569 (0.0008) -[2023-11-28 10:00:30,331][87426] Updated weights for policy 1, policy_version 373270 (0.0011) -[2023-11-28 10:00:30,584][87424] Updated weights for policy 0, policy_version 373579 (0.0011) -[2023-11-28 10:00:30,708][87426] Updated weights for policy 1, policy_version 373280 (0.0011) -[2023-11-28 10:00:30,969][87424] Updated weights for policy 0, policy_version 373589 (0.0012) -[2023-11-28 10:00:31,348][87424] Updated weights for policy 0, policy_version 373599 (0.0012) -[2023-11-28 10:00:32,826][87426] Updated weights for policy 1, policy_version 373290 (0.0012) -[2023-11-28 10:00:33,208][87426] Updated weights for policy 1, policy_version 373300 (0.0012) -[2023-11-28 10:00:33,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191201280. Throughput: 0: 2643.9, 1: 2764.0. Samples: 191219060. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:00:33,446][86177] Avg episode reward: [(0, '-570.950'), (1, '-521.480')] -[2023-11-28 10:00:33,581][87426] Updated weights for policy 1, policy_version 373310 (0.0011) -[2023-11-28 10:00:33,655][87424] Updated weights for policy 0, policy_version 373609 (0.0010) -[2023-11-28 10:00:34,029][87424] Updated weights for policy 0, policy_version 373619 (0.0012) -[2023-11-28 10:00:34,420][87424] Updated weights for policy 0, policy_version 373629 (0.0010) -[2023-11-28 10:00:35,349][87426] Updated weights for policy 1, policy_version 373320 (0.0011) -[2023-11-28 10:00:35,739][87426] Updated weights for policy 1, policy_version 373330 (0.0008) -[2023-11-28 10:00:36,126][87426] Updated weights for policy 1, policy_version 373340 (0.0008) -[2023-11-28 10:00:36,576][87424] Updated weights for policy 0, policy_version 373639 (0.0009) -[2023-11-28 10:00:36,958][87424] Updated weights for policy 0, policy_version 373649 (0.0008) -[2023-11-28 10:00:37,337][87424] Updated weights for policy 0, policy_version 373659 (0.0009) -[2023-11-28 10:00:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 191234048. Throughput: 0: 2648.7, 1: 2771.7. Samples: 191250912. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:00:38,445][86177] Avg episode reward: [(0, '-546.050'), (1, '-522.190')] -[2023-11-28 10:00:38,602][87426] Updated weights for policy 1, policy_version 373350 (0.0008) -[2023-11-28 10:00:38,983][87426] Updated weights for policy 1, policy_version 373360 (0.0009) -[2023-11-28 10:00:39,356][87426] Updated weights for policy 1, policy_version 373370 (0.0012) -[2023-11-28 10:00:39,697][87424] Updated weights for policy 0, policy_version 373669 (0.0009) -[2023-11-28 10:00:40,081][87424] Updated weights for policy 0, policy_version 373679 (0.0012) -[2023-11-28 10:00:40,459][87424] Updated weights for policy 0, policy_version 373689 (0.0012) -[2023-11-28 10:00:41,727][87426] Updated weights for policy 1, policy_version 373380 (0.0010) -[2023-11-28 10:00:42,089][87426] Updated weights for policy 1, policy_version 373390 (0.0010) -[2023-11-28 10:00:42,462][87426] Updated weights for policy 1, policy_version 373400 (0.0012) -[2023-11-28 10:00:43,133][87424] Updated weights for policy 0, policy_version 373699 (0.0011) -[2023-11-28 10:00:43,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 191258624. Throughput: 0: 2643.1, 1: 2753.3. Samples: 191273752. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:00:43,445][86177] Avg episode reward: [(0, '-548.420'), (1, '-519.600')] -[2023-11-28 10:00:43,506][87424] Updated weights for policy 0, policy_version 373709 (0.0012) -[2023-11-28 10:00:43,889][87424] Updated weights for policy 0, policy_version 373719 (0.0012) -[2023-11-28 10:00:44,394][87426] Updated weights for policy 1, policy_version 373410 (0.0010) -[2023-11-28 10:00:44,774][87426] Updated weights for policy 1, policy_version 373420 (0.0012) -[2023-11-28 10:00:45,167][87426] Updated weights for policy 1, policy_version 373430 (0.0012) -[2023-11-28 10:00:45,537][87426] Updated weights for policy 1, policy_version 373440 (0.0011) -[2023-11-28 10:00:46,177][87424] Updated weights for policy 0, policy_version 373729 (0.0012) -[2023-11-28 10:00:46,554][87424] Updated weights for policy 0, policy_version 373739 (0.0009) -[2023-11-28 10:00:46,930][87424] Updated weights for policy 0, policy_version 373749 (0.0007) -[2023-11-28 10:00:47,308][87424] Updated weights for policy 0, policy_version 373759 (0.0008) -[2023-11-28 10:00:48,069][87426] Updated weights for policy 1, policy_version 373450 (0.0007) -[2023-11-28 10:00:48,440][87426] Updated weights for policy 1, policy_version 373460 (0.0009) -[2023-11-28 10:00:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191283200. Throughput: 0: 2637.2, 1: 2760.4. Samples: 191298748. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:00:48,445][86177] Avg episode reward: [(0, '-548.350'), (1, '-522.660')] -[2023-11-28 10:00:48,822][87426] Updated weights for policy 1, policy_version 373470 (0.0011) -[2023-11-28 10:00:49,505][87424] Updated weights for policy 0, policy_version 373769 (0.0010) -[2023-11-28 10:00:49,889][87424] Updated weights for policy 0, policy_version 373779 (0.0009) -[2023-11-28 10:00:50,263][87424] Updated weights for policy 0, policy_version 373789 (0.0010) -[2023-11-28 10:00:50,557][87426] Updated weights for policy 1, policy_version 373480 (0.0011) -[2023-11-28 10:00:50,936][87426] Updated weights for policy 1, policy_version 373490 (0.0011) -[2023-11-28 10:00:51,312][87426] Updated weights for policy 1, policy_version 373500 (0.0010) -[2023-11-28 10:00:52,724][87424] Updated weights for policy 0, policy_version 373799 (0.0011) -[2023-11-28 10:00:53,108][87424] Updated weights for policy 0, policy_version 373809 (0.0011) -[2023-11-28 10:00:53,450][86177] Fps is (10 sec: 4912.4, 60 sec: 5324.3, 300 sec: 5387.2). Total num frames: 191307776. Throughput: 0: 2632.1, 1: 2723.0. Samples: 191330348. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:00:53,451][86177] Avg episode reward: [(0, '-550.770'), (1, '-525.760')] -[2023-11-28 10:00:53,491][87424] Updated weights for policy 0, policy_version 373819 (0.0012) -[2023-11-28 10:00:53,587][87426] Updated weights for policy 1, policy_version 373510 (0.0011) -[2023-11-28 10:00:53,971][87426] Updated weights for policy 1, policy_version 373520 (0.0010) -[2023-11-28 10:00:54,352][87426] Updated weights for policy 1, policy_version 373530 (0.0011) -[2023-11-28 10:00:55,721][87424] Updated weights for policy 0, policy_version 373829 (0.0012) -[2023-11-28 10:00:56,100][87424] Updated weights for policy 0, policy_version 373839 (0.0011) -[2023-11-28 10:00:56,475][87424] Updated weights for policy 0, policy_version 373849 (0.0011) -[2023-11-28 10:00:56,801][87426] Updated weights for policy 1, policy_version 373540 (0.0009) -[2023-11-28 10:00:57,186][87426] Updated weights for policy 1, policy_version 373550 (0.0012) -[2023-11-28 10:00:57,559][87426] Updated weights for policy 1, policy_version 373560 (0.0012) -[2023-11-28 10:00:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 191340544. Throughput: 0: 2627.0, 1: 2717.5. Samples: 191353712. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:00:58,446][86177] Avg episode reward: [(0, '-543.400'), (1, '-533.220')] -[2023-11-28 10:00:58,656][87424] Updated weights for policy 0, policy_version 373859 (0.0011) -[2023-11-28 10:00:59,030][87424] Updated weights for policy 0, policy_version 373869 (0.0012) -[2023-11-28 10:00:59,411][87424] Updated weights for policy 0, policy_version 373879 (0.0012) -[2023-11-28 10:00:59,801][87426] Updated weights for policy 1, policy_version 373570 (0.0011) -[2023-11-28 10:01:00,182][87426] Updated weights for policy 1, policy_version 373580 (0.0009) -[2023-11-28 10:01:00,558][87426] Updated weights for policy 1, policy_version 373590 (0.0009) -[2023-11-28 10:01:00,937][87426] Updated weights for policy 1, policy_version 373600 (0.0012) -[2023-11-28 10:01:01,580][87424] Updated weights for policy 0, policy_version 373889 (0.0012) -[2023-11-28 10:01:01,953][87424] Updated weights for policy 0, policy_version 373899 (0.0011) -[2023-11-28 10:01:02,342][87424] Updated weights for policy 0, policy_version 373909 (0.0009) -[2023-11-28 10:01:02,726][87424] Updated weights for policy 0, policy_version 373919 (0.0009) -[2023-11-28 10:01:03,152][87426] Updated weights for policy 1, policy_version 373610 (0.0010) -[2023-11-28 10:01:03,444][86177] Fps is (10 sec: 5737.7, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 191365120. Throughput: 0: 2656.5, 1: 2691.6. Samples: 191378268. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:01:03,445][86177] Avg episode reward: [(0, '-541.640'), (1, '-532.370')] -[2023-11-28 10:01:03,531][87426] Updated weights for policy 1, policy_version 373620 (0.0010) -[2023-11-28 10:01:03,902][87426] Updated weights for policy 1, policy_version 373630 (0.0007) -[2023-11-28 10:01:04,969][87424] Updated weights for policy 0, policy_version 373929 (0.0010) -[2023-11-28 10:01:05,348][87424] Updated weights for policy 0, policy_version 373939 (0.0009) -[2023-11-28 10:01:05,732][87424] Updated weights for policy 0, policy_version 373949 (0.0007) -[2023-11-28 10:01:05,992][87426] Updated weights for policy 1, policy_version 373640 (0.0011) -[2023-11-28 10:01:06,362][87426] Updated weights for policy 1, policy_version 373650 (0.0012) -[2023-11-28 10:01:06,742][87426] Updated weights for policy 1, policy_version 373660 (0.0012) -[2023-11-28 10:01:07,916][87424] Updated weights for policy 0, policy_version 373959 (0.0010) -[2023-11-28 10:01:08,292][87424] Updated weights for policy 0, policy_version 373969 (0.0012) -[2023-11-28 10:01:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191389696. Throughput: 0: 2644.0, 1: 2694.7. Samples: 191410840. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:01:08,445][86177] Avg episode reward: [(0, '-558.750'), (1, '-531.690')] -[2023-11-28 10:01:08,682][87424] Updated weights for policy 0, policy_version 373979 (0.0011) -[2023-11-28 10:01:08,817][87426] Updated weights for policy 1, policy_version 373670 (0.0011) -[2023-11-28 10:01:09,198][87426] Updated weights for policy 1, policy_version 373680 (0.0011) -[2023-11-28 10:01:09,579][87426] Updated weights for policy 1, policy_version 373690 (0.0012) -[2023-11-28 10:01:11,183][87424] Updated weights for policy 0, policy_version 373989 (0.0011) -[2023-11-28 10:01:11,557][87424] Updated weights for policy 0, policy_version 373999 (0.0011) -[2023-11-28 10:01:11,621][87426] Updated weights for policy 1, policy_version 373700 (0.0011) -[2023-11-28 10:01:11,935][87424] Updated weights for policy 0, policy_version 374009 (0.0010) -[2023-11-28 10:01:11,996][87426] Updated weights for policy 1, policy_version 373710 (0.0011) -[2023-11-28 10:01:12,375][87426] Updated weights for policy 1, policy_version 373720 (0.0010) -[2023-11-28 10:01:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 191422464. Throughput: 0: 2642.6, 1: 2698.7. Samples: 191434640. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:01:13,445][86177] Avg episode reward: [(0, '-551.410'), (1, '-536.000')] -[2023-11-28 10:01:14,410][87424] Updated weights for policy 0, policy_version 374019 (0.0011) -[2023-11-28 10:01:14,794][87424] Updated weights for policy 0, policy_version 374029 (0.0011) -[2023-11-28 10:01:14,871][87426] Updated weights for policy 1, policy_version 373730 (0.0011) -[2023-11-28 10:01:15,177][87424] Updated weights for policy 0, policy_version 374039 (0.0008) -[2023-11-28 10:01:15,245][87426] Updated weights for policy 1, policy_version 373740 (0.0011) -[2023-11-28 10:01:15,631][87426] Updated weights for policy 1, policy_version 373750 (0.0011) -[2023-11-28 10:01:16,011][87426] Updated weights for policy 1, policy_version 373760 (0.0012) -[2023-11-28 10:01:17,304][87424] Updated weights for policy 0, policy_version 374049 (0.0011) -[2023-11-28 10:01:17,690][87424] Updated weights for policy 0, policy_version 374059 (0.0008) -[2023-11-28 10:01:18,080][87424] Updated weights for policy 0, policy_version 374069 (0.0008) -[2023-11-28 10:01:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 191438848. Throughput: 0: 2640.1, 1: 2687.1. Samples: 191458784. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:01:18,446][86177] Avg episode reward: [(0, '-540.340'), (1, '-531.360')] -[2023-11-28 10:01:18,466][87426] Updated weights for policy 1, policy_version 373770 (0.0010) -[2023-11-28 10:01:18,469][87424] Updated weights for policy 0, policy_version 374079 (0.0010) -[2023-11-28 10:01:18,852][87426] Updated weights for policy 1, policy_version 373780 (0.0011) -[2023-11-28 10:01:19,228][87426] Updated weights for policy 1, policy_version 373790 (0.0012) -[2023-11-28 10:01:20,372][87424] Updated weights for policy 0, policy_version 374089 (0.0011) -[2023-11-28 10:01:20,752][87424] Updated weights for policy 0, policy_version 374099 (0.0009) -[2023-11-28 10:01:21,134][87424] Updated weights for policy 0, policy_version 374109 (0.0009) -[2023-11-28 10:01:21,580][87426] Updated weights for policy 1, policy_version 373800 (0.0011) -[2023-11-28 10:01:21,950][87426] Updated weights for policy 1, policy_version 373810 (0.0011) -[2023-11-28 10:01:22,325][87426] Updated weights for policy 1, policy_version 373820 (0.0012) -[2023-11-28 10:01:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191471616. Throughput: 0: 2671.3, 1: 2667.4. Samples: 191491152. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:01:23,445][86177] Avg episode reward: [(0, '-524.060'), (1, '-528.430')] -[2023-11-28 10:01:23,671][87424] Updated weights for policy 0, policy_version 374119 (0.0009) -[2023-11-28 10:01:24,049][87424] Updated weights for policy 0, policy_version 374129 (0.0007) -[2023-11-28 10:01:24,428][87424] Updated weights for policy 0, policy_version 374139 (0.0008) -[2023-11-28 10:01:24,484][87426] Updated weights for policy 1, policy_version 373830 (0.0011) -[2023-11-28 10:01:24,856][87426] Updated weights for policy 1, policy_version 373840 (0.0012) -[2023-11-28 10:01:25,235][87426] Updated weights for policy 1, policy_version 373850 (0.0012) -[2023-11-28 10:01:26,261][87424] Updated weights for policy 0, policy_version 374149 (0.0009) -[2023-11-28 10:01:26,645][87424] Updated weights for policy 0, policy_version 374159 (0.0011) -[2023-11-28 10:01:27,028][87424] Updated weights for policy 0, policy_version 374169 (0.0012) -[2023-11-28 10:01:27,403][87426] Updated weights for policy 1, policy_version 373860 (0.0011) -[2023-11-28 10:01:27,778][87426] Updated weights for policy 1, policy_version 373870 (0.0011) -[2023-11-28 10:01:28,151][87426] Updated weights for policy 1, policy_version 373880 (0.0007) -[2023-11-28 10:01:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 191496192. Throughput: 0: 2690.4, 1: 2688.7. Samples: 191515812. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:01:28,445][86177] Avg episode reward: [(0, '-523.430'), (1, '-573.740')] -[2023-11-28 10:01:28,829][87424] Updated weights for policy 0, policy_version 374179 (0.0011) -[2023-11-28 10:01:29,219][87424] Updated weights for policy 0, policy_version 374189 (0.0012) -[2023-11-28 10:01:29,594][87424] Updated weights for policy 0, policy_version 374199 (0.0011) -[2023-11-28 10:01:30,478][87426] Updated weights for policy 1, policy_version 373890 (0.0008) -[2023-11-28 10:01:30,856][87426] Updated weights for policy 1, policy_version 373900 (0.0012) -[2023-11-28 10:01:31,235][87426] Updated weights for policy 1, policy_version 373910 (0.0012) -[2023-11-28 10:01:31,494][87424] Updated weights for policy 0, policy_version 374209 (0.0011) -[2023-11-28 10:01:31,606][87426] Updated weights for policy 1, policy_version 373920 (0.0012) -[2023-11-28 10:01:31,875][87424] Updated weights for policy 0, policy_version 374219 (0.0012) -[2023-11-28 10:01:32,266][87424] Updated weights for policy 0, policy_version 374229 (0.0011) -[2023-11-28 10:01:32,645][87424] Updated weights for policy 0, policy_version 374239 (0.0012) -[2023-11-28 10:01:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 191528960. Throughput: 0: 2701.5, 1: 2676.7. Samples: 191540768. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:01:33,445][86177] Avg episode reward: [(0, '-523.990'), (1, '-568.240')] -[2023-11-28 10:01:34,104][87426] Updated weights for policy 1, policy_version 373930 (0.0012) -[2023-11-28 10:01:34,480][87426] Updated weights for policy 1, policy_version 373940 (0.0012) -[2023-11-28 10:01:34,851][87424] Updated weights for policy 0, policy_version 374249 (0.0009) -[2023-11-28 10:01:34,876][87426] Updated weights for policy 1, policy_version 373950 (0.0010) -[2023-11-28 10:01:35,230][87424] Updated weights for policy 0, policy_version 374259 (0.0009) -[2023-11-28 10:01:35,608][87424] Updated weights for policy 0, policy_version 374269 (0.0012) -[2023-11-28 10:01:37,005][87426] Updated weights for policy 1, policy_version 373960 (0.0012) -[2023-11-28 10:01:37,389][87426] Updated weights for policy 1, policy_version 373970 (0.0012) -[2023-11-28 10:01:37,754][87426] Updated weights for policy 1, policy_version 373980 (0.0011) -[2023-11-28 10:01:37,763][87424] Updated weights for policy 0, policy_version 374279 (0.0011) -[2023-11-28 10:01:38,156][87424] Updated weights for policy 0, policy_version 374289 (0.0007) -[2023-11-28 10:01:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191553536. Throughput: 0: 2717.9, 1: 2668.1. Samples: 191572684. Policy #0 lag: (min: 31.0, avg: 48.0, max: 73.0) -[2023-11-28 10:01:38,445][86177] Avg episode reward: [(0, '-530.040'), (1, '-562.440')] -[2023-11-28 10:01:38,535][87424] Updated weights for policy 0, policy_version 374299 (0.0007) -[2023-11-28 10:01:39,495][87426] Updated weights for policy 1, policy_version 373990 (0.0012) -[2023-11-28 10:01:39,871][87426] Updated weights for policy 1, policy_version 374000 (0.0012) -[2023-11-28 10:01:40,248][87426] Updated weights for policy 1, policy_version 374010 (0.0009) -[2023-11-28 10:01:40,789][87424] Updated weights for policy 0, policy_version 374309 (0.0009) -[2023-11-28 10:01:41,180][87424] Updated weights for policy 0, policy_version 374319 (0.0011) -[2023-11-28 10:01:41,560][87424] Updated weights for policy 0, policy_version 374329 (0.0009) -[2023-11-28 10:01:42,762][87426] Updated weights for policy 1, policy_version 374020 (0.0008) -[2023-11-28 10:01:43,138][87426] Updated weights for policy 1, policy_version 374030 (0.0011) -[2023-11-28 10:01:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191578112. Throughput: 0: 2722.9, 1: 2663.1. Samples: 191596084. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:01:43,445][86177] Avg episode reward: [(0, '-524.140'), (1, '-573.270')] -[2023-11-28 10:01:43,514][87426] Updated weights for policy 1, policy_version 374040 (0.0009) -[2023-11-28 10:01:44,045][87424] Updated weights for policy 0, policy_version 374339 (0.0011) -[2023-11-28 10:01:44,430][87424] Updated weights for policy 0, policy_version 374349 (0.0011) -[2023-11-28 10:01:44,817][87424] Updated weights for policy 0, policy_version 374359 (0.0010) -[2023-11-28 10:01:45,735][87426] Updated weights for policy 1, policy_version 374050 (0.0008) -[2023-11-28 10:01:46,108][87426] Updated weights for policy 1, policy_version 374060 (0.0010) -[2023-11-28 10:01:46,489][87426] Updated weights for policy 1, policy_version 374070 (0.0008) -[2023-11-28 10:01:46,871][87426] Updated weights for policy 1, policy_version 374080 (0.0007) -[2023-11-28 10:01:47,201][87424] Updated weights for policy 0, policy_version 374369 (0.0009) -[2023-11-28 10:01:47,588][87424] Updated weights for policy 0, policy_version 374379 (0.0007) -[2023-11-28 10:01:47,976][87424] Updated weights for policy 0, policy_version 374389 (0.0008) -[2023-11-28 10:01:48,356][87424] Updated weights for policy 0, policy_version 374399 (0.0009) -[2023-11-28 10:01:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 191610880. Throughput: 0: 2695.9, 1: 2679.6. Samples: 191620168. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:01:48,445][86177] Avg episode reward: [(0, '-528.220'), (1, '-616.220')] -[2023-11-28 10:01:49,347][87426] Updated weights for policy 1, policy_version 374090 (0.0010) -[2023-11-28 10:01:49,719][87426] Updated weights for policy 1, policy_version 374100 (0.0010) -[2023-11-28 10:01:50,098][87426] Updated weights for policy 1, policy_version 374110 (0.0011) -[2023-11-28 10:01:50,367][87424] Updated weights for policy 0, policy_version 374409 (0.0015) -[2023-11-28 10:01:50,741][87424] Updated weights for policy 0, policy_version 374419 (0.0012) -[2023-11-28 10:01:51,129][87424] Updated weights for policy 0, policy_version 374429 (0.0010) -[2023-11-28 10:01:52,283][87426] Updated weights for policy 1, policy_version 374120 (0.0011) -[2023-11-28 10:01:52,665][87426] Updated weights for policy 1, policy_version 374130 (0.0011) -[2023-11-28 10:01:53,049][87426] Updated weights for policy 1, policy_version 374140 (0.0010) -[2023-11-28 10:01:53,396][87424] Updated weights for policy 0, policy_version 374439 (0.0010) -[2023-11-28 10:01:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.9, 300 sec: 5415.1). Total num frames: 191635456. Throughput: 0: 2704.8, 1: 2663.1. Samples: 191652396. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:01:53,445][86177] Avg episode reward: [(0, '-533.600'), (1, '-606.180')] -[2023-11-28 10:01:53,777][87424] Updated weights for policy 0, policy_version 374449 (0.0010) -[2023-11-28 10:01:54,159][87424] Updated weights for policy 0, policy_version 374459 (0.0010) -[2023-11-28 10:01:55,202][87426] Updated weights for policy 1, policy_version 374150 (0.0010) -[2023-11-28 10:01:55,579][87426] Updated weights for policy 1, policy_version 374160 (0.0011) -[2023-11-28 10:01:55,964][87426] Updated weights for policy 1, policy_version 374170 (0.0012) -[2023-11-28 10:01:56,568][87424] Updated weights for policy 0, policy_version 374469 (0.0008) -[2023-11-28 10:01:56,945][87424] Updated weights for policy 0, policy_version 374479 (0.0008) -[2023-11-28 10:01:57,325][87424] Updated weights for policy 0, policy_version 374489 (0.0007) -[2023-11-28 10:01:58,202][87426] Updated weights for policy 1, policy_version 374180 (0.0012) -[2023-11-28 10:01:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191660032. Throughput: 0: 2705.3, 1: 2677.5. Samples: 191676868. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:01:58,445][86177] Avg episode reward: [(0, '-531.450'), (1, '-626.610')] -[2023-11-28 10:01:58,572][87426] Updated weights for policy 1, policy_version 374190 (0.0011) -[2023-11-28 10:01:58,957][87426] Updated weights for policy 1, policy_version 374200 (0.0011) -[2023-11-28 10:01:59,446][87424] Updated weights for policy 0, policy_version 374499 (0.0009) -[2023-11-28 10:01:59,821][87424] Updated weights for policy 0, policy_version 374509 (0.0012) -[2023-11-28 10:02:00,208][87424] Updated weights for policy 0, policy_version 374519 (0.0012) -[2023-11-28 10:02:01,151][87426] Updated weights for policy 1, policy_version 374210 (0.0011) -[2023-11-28 10:02:01,530][87426] Updated weights for policy 1, policy_version 374220 (0.0012) -[2023-11-28 10:02:01,902][87426] Updated weights for policy 1, policy_version 374230 (0.0012) -[2023-11-28 10:02:02,284][87426] Updated weights for policy 1, policy_version 374240 (0.0010) -[2023-11-28 10:02:02,534][87424] Updated weights for policy 0, policy_version 374529 (0.0012) -[2023-11-28 10:02:02,925][87424] Updated weights for policy 0, policy_version 374539 (0.0011) -[2023-11-28 10:02:03,304][87424] Updated weights for policy 0, policy_version 374549 (0.0008) -[2023-11-28 10:02:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191684608. Throughput: 0: 2697.1, 1: 2665.5. Samples: 191700100. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:03,445][86177] Avg episode reward: [(0, '-530.670'), (1, '-625.010')] -[2023-11-28 10:02:03,684][87424] Updated weights for policy 0, policy_version 374559 (0.0007) -[2023-11-28 10:02:04,443][87426] Updated weights for policy 1, policy_version 374250 (0.0008) -[2023-11-28 10:02:04,819][87426] Updated weights for policy 1, policy_version 374260 (0.0008) -[2023-11-28 10:02:05,198][87426] Updated weights for policy 1, policy_version 374270 (0.0007) -[2023-11-28 10:02:05,683][87424] Updated weights for policy 0, policy_version 374569 (0.0009) -[2023-11-28 10:02:06,066][87424] Updated weights for policy 0, policy_version 374579 (0.0007) -[2023-11-28 10:02:06,453][87424] Updated weights for policy 0, policy_version 374589 (0.0007) -[2023-11-28 10:02:06,963][87426] Updated weights for policy 1, policy_version 374280 (0.0010) -[2023-11-28 10:02:07,344][87426] Updated weights for policy 1, policy_version 374290 (0.0007) -[2023-11-28 10:02:07,723][87426] Updated weights for policy 1, policy_version 374300 (0.0007) -[2023-11-28 10:02:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 191717376. Throughput: 0: 2674.1, 1: 2705.9. Samples: 191733252. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:08,445][86177] Avg episode reward: [(0, '-526.480'), (1, '-611.400')] -[2023-11-28 10:02:08,821][87424] Updated weights for policy 0, policy_version 374599 (0.0008) -[2023-11-28 10:02:09,208][87424] Updated weights for policy 0, policy_version 374609 (0.0012) -[2023-11-28 10:02:09,584][87424] Updated weights for policy 0, policy_version 374619 (0.0012) -[2023-11-28 10:02:09,760][87426] Updated weights for policy 1, policy_version 374310 (0.0010) -[2023-11-28 10:02:10,138][87426] Updated weights for policy 1, policy_version 374320 (0.0012) -[2023-11-28 10:02:10,516][87426] Updated weights for policy 1, policy_version 374330 (0.0012) -[2023-11-28 10:02:11,864][87424] Updated weights for policy 0, policy_version 374629 (0.0011) -[2023-11-28 10:02:12,248][87424] Updated weights for policy 0, policy_version 374639 (0.0012) -[2023-11-28 10:02:12,629][87424] Updated weights for policy 0, policy_version 374649 (0.0011) -[2023-11-28 10:02:12,746][87426] Updated weights for policy 1, policy_version 374340 (0.0011) -[2023-11-28 10:02:13,132][87426] Updated weights for policy 1, policy_version 374350 (0.0011) -[2023-11-28 10:02:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191741952. Throughput: 0: 2660.6, 1: 2707.2. Samples: 191757364. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:13,445][86177] Avg episode reward: [(0, '-527.150'), (1, '-583.860')] -[2023-11-28 10:02:13,504][87426] Updated weights for policy 1, policy_version 374360 (0.0011) -[2023-11-28 10:02:15,211][87424] Updated weights for policy 0, policy_version 374659 (0.0011) -[2023-11-28 10:02:15,583][87424] Updated weights for policy 0, policy_version 374669 (0.0010) -[2023-11-28 10:02:15,639][87426] Updated weights for policy 1, policy_version 374370 (0.0009) -[2023-11-28 10:02:15,964][87424] Updated weights for policy 0, policy_version 374679 (0.0010) -[2023-11-28 10:02:16,024][87426] Updated weights for policy 1, policy_version 374380 (0.0010) -[2023-11-28 10:02:16,392][87426] Updated weights for policy 1, policy_version 374390 (0.0012) -[2023-11-28 10:02:16,772][87426] Updated weights for policy 1, policy_version 374400 (0.0012) -[2023-11-28 10:02:18,130][87424] Updated weights for policy 0, policy_version 374689 (0.0010) -[2023-11-28 10:02:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 191766528. Throughput: 0: 2624.1, 1: 2712.7. Samples: 191780924. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:18,445][86177] Avg episode reward: [(0, '-541.360'), (1, '-579.380')] -[2023-11-28 10:02:18,506][87424] Updated weights for policy 0, policy_version 374699 (0.0012) -[2023-11-28 10:02:18,600][87426] Updated weights for policy 1, policy_version 374410 (0.0010) -[2023-11-28 10:02:18,910][87424] Updated weights for policy 0, policy_version 374709 (0.0010) -[2023-11-28 10:02:18,967][87426] Updated weights for policy 1, policy_version 374420 (0.0011) -[2023-11-28 10:02:19,287][87424] Updated weights for policy 0, policy_version 374719 (0.0008) -[2023-11-28 10:02:19,322][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000374720_95928320.pth... -[2023-11-28 10:02:19,343][87426] Updated weights for policy 1, policy_version 374430 (0.0011) -[2023-11-28 10:02:19,367][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000372224_95289344.pth -[2023-11-28 10:02:19,416][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000374432_95854592.pth... -[2023-11-28 10:02:19,462][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000371872_95199232.pth -[2023-11-28 10:02:21,441][87424] Updated weights for policy 0, policy_version 374729 (0.0011) -[2023-11-28 10:02:21,814][87426] Updated weights for policy 1, policy_version 374440 (0.0011) -[2023-11-28 10:02:21,823][87424] Updated weights for policy 0, policy_version 374739 (0.0012) -[2023-11-28 10:02:22,196][87426] Updated weights for policy 1, policy_version 374450 (0.0011) -[2023-11-28 10:02:22,204][87424] Updated weights for policy 0, policy_version 374749 (0.0009) -[2023-11-28 10:02:22,568][87426] Updated weights for policy 1, policy_version 374460 (0.0009) -[2023-11-28 10:02:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 191799296. Throughput: 0: 2625.0, 1: 2726.6. Samples: 191813504. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:23,445][86177] Avg episode reward: [(0, '-564.170'), (1, '-554.160')] -[2023-11-28 10:02:24,382][87424] Updated weights for policy 0, policy_version 374759 (0.0008) -[2023-11-28 10:02:24,764][87424] Updated weights for policy 0, policy_version 374769 (0.0009) -[2023-11-28 10:02:24,949][87426] Updated weights for policy 1, policy_version 374470 (0.0009) -[2023-11-28 10:02:25,147][87424] Updated weights for policy 0, policy_version 374779 (0.0008) -[2023-11-28 10:02:25,324][87426] Updated weights for policy 1, policy_version 374480 (0.0011) -[2023-11-28 10:02:25,695][87426] Updated weights for policy 1, policy_version 374490 (0.0012) -[2023-11-28 10:02:27,166][87424] Updated weights for policy 0, policy_version 374789 (0.0010) -[2023-11-28 10:02:27,547][87424] Updated weights for policy 0, policy_version 374799 (0.0007) -[2023-11-28 10:02:27,935][87424] Updated weights for policy 0, policy_version 374809 (0.0007) -[2023-11-28 10:02:28,274][87426] Updated weights for policy 1, policy_version 374500 (0.0011) -[2023-11-28 10:02:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 191823872. Throughput: 0: 2648.0, 1: 2723.5. Samples: 191837800. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:28,446][86177] Avg episode reward: [(0, '-571.170'), (1, '-565.050')] -[2023-11-28 10:02:28,646][87426] Updated weights for policy 1, policy_version 374510 (0.0007) -[2023-11-28 10:02:29,021][87426] Updated weights for policy 1, policy_version 374520 (0.0008) -[2023-11-28 10:02:29,597][87424] Updated weights for policy 0, policy_version 374819 (0.0008) -[2023-11-28 10:02:29,987][87424] Updated weights for policy 0, policy_version 374829 (0.0016) -[2023-11-28 10:02:30,362][87424] Updated weights for policy 0, policy_version 374839 (0.0008) -[2023-11-28 10:02:31,538][87426] Updated weights for policy 1, policy_version 374530 (0.0008) -[2023-11-28 10:02:31,908][87426] Updated weights for policy 1, policy_version 374540 (0.0011) -[2023-11-28 10:02:32,289][87426] Updated weights for policy 1, policy_version 374550 (0.0009) -[2023-11-28 10:02:32,665][87426] Updated weights for policy 1, policy_version 374560 (0.0010) -[2023-11-28 10:02:32,897][87424] Updated weights for policy 0, policy_version 374849 (0.0008) -[2023-11-28 10:02:33,280][87424] Updated weights for policy 0, policy_version 374859 (0.0012) -[2023-11-28 10:02:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191848448. Throughput: 0: 2680.1, 1: 2710.9. Samples: 191862764. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:33,446][86177] Avg episode reward: [(0, '-567.750'), (1, '-556.760')] -[2023-11-28 10:02:33,661][87424] Updated weights for policy 0, policy_version 374869 (0.0012) -[2023-11-28 10:02:34,051][87424] Updated weights for policy 0, policy_version 374879 (0.0010) -[2023-11-28 10:02:34,646][87426] Updated weights for policy 1, policy_version 374570 (0.0012) -[2023-11-28 10:02:35,029][87426] Updated weights for policy 1, policy_version 374580 (0.0011) -[2023-11-28 10:02:35,401][87426] Updated weights for policy 1, policy_version 374590 (0.0011) -[2023-11-28 10:02:36,314][87424] Updated weights for policy 0, policy_version 374889 (0.0008) -[2023-11-28 10:02:36,710][87424] Updated weights for policy 0, policy_version 374899 (0.0007) -[2023-11-28 10:02:37,074][87424] Updated weights for policy 0, policy_version 374909 (0.0009) -[2023-11-28 10:02:37,639][87426] Updated weights for policy 1, policy_version 374600 (0.0012) -[2023-11-28 10:02:38,031][87426] Updated weights for policy 1, policy_version 374610 (0.0012) -[2023-11-28 10:02:38,404][87426] Updated weights for policy 1, policy_version 374620 (0.0012) -[2023-11-28 10:02:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 191873024. Throughput: 0: 2671.0, 1: 2723.3. Samples: 191895140. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:38,445][86177] Avg episode reward: [(0, '-557.110'), (1, '-573.350')] -[2023-11-28 10:02:39,337][87424] Updated weights for policy 0, policy_version 374919 (0.0011) -[2023-11-28 10:02:39,717][87424] Updated weights for policy 0, policy_version 374929 (0.0012) -[2023-11-28 10:02:40,099][87424] Updated weights for policy 0, policy_version 374939 (0.0012) -[2023-11-28 10:02:40,712][87426] Updated weights for policy 1, policy_version 374630 (0.0011) -[2023-11-28 10:02:41,088][87426] Updated weights for policy 1, policy_version 374640 (0.0011) -[2023-11-28 10:02:41,466][87426] Updated weights for policy 1, policy_version 374650 (0.0009) -[2023-11-28 10:02:42,570][87424] Updated weights for policy 0, policy_version 374949 (0.0012) -[2023-11-28 10:02:42,956][87424] Updated weights for policy 0, policy_version 374959 (0.0012) -[2023-11-28 10:02:43,328][87424] Updated weights for policy 0, policy_version 374969 (0.0012) -[2023-11-28 10:02:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 191897600. Throughput: 0: 2685.5, 1: 2702.5. Samples: 191919328. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:43,445][86177] Avg episode reward: [(0, '-537.580'), (1, '-612.320')] -[2023-11-28 10:02:43,654][87426] Updated weights for policy 1, policy_version 374660 (0.0011) -[2023-11-28 10:02:44,019][87426] Updated weights for policy 1, policy_version 374670 (0.0012) -[2023-11-28 10:02:44,407][87426] Updated weights for policy 1, policy_version 374680 (0.0012) -[2023-11-28 10:02:45,424][87424] Updated weights for policy 0, policy_version 374979 (0.0012) -[2023-11-28 10:02:45,816][87424] Updated weights for policy 0, policy_version 374989 (0.0012) -[2023-11-28 10:02:46,204][87424] Updated weights for policy 0, policy_version 374999 (0.0012) -[2023-11-28 10:02:46,425][87426] Updated weights for policy 1, policy_version 374690 (0.0012) -[2023-11-28 10:02:46,789][87426] Updated weights for policy 1, policy_version 374700 (0.0011) -[2023-11-28 10:02:47,169][87426] Updated weights for policy 1, policy_version 374710 (0.0010) -[2023-11-28 10:02:47,547][87426] Updated weights for policy 1, policy_version 374720 (0.0007) -[2023-11-28 10:02:48,044][87424] Updated weights for policy 0, policy_version 375009 (0.0011) -[2023-11-28 10:02:48,428][87424] Updated weights for policy 0, policy_version 375019 (0.0007) -[2023-11-28 10:02:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 191930368. Throughput: 0: 2685.0, 1: 2704.2. Samples: 191942612. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:48,445][86177] Avg episode reward: [(0, '-524.830'), (1, '-582.710')] -[2023-11-28 10:02:48,819][87424] Updated weights for policy 0, policy_version 375029 (0.0010) -[2023-11-28 10:02:49,192][87424] Updated weights for policy 0, policy_version 375039 (0.0008) -[2023-11-28 10:02:49,871][87426] Updated weights for policy 1, policy_version 374730 (0.0012) -[2023-11-28 10:02:50,245][87426] Updated weights for policy 1, policy_version 374740 (0.0012) -[2023-11-28 10:02:50,623][87426] Updated weights for policy 1, policy_version 374750 (0.0012) -[2023-11-28 10:02:51,515][87424] Updated weights for policy 0, policy_version 375049 (0.0012) -[2023-11-28 10:02:51,905][87424] Updated weights for policy 0, policy_version 375059 (0.0012) -[2023-11-28 10:02:52,271][87424] Updated weights for policy 0, policy_version 375069 (0.0009) -[2023-11-28 10:02:53,195][87426] Updated weights for policy 1, policy_version 374760 (0.0012) -[2023-11-28 10:02:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 191954944. Throughput: 0: 2692.8, 1: 2658.9. Samples: 191974080. Policy #0 lag: (min: 15.0, avg: 39.4, max: 56.0) -[2023-11-28 10:02:53,445][86177] Avg episode reward: [(0, '-543.700'), (1, '-582.140')] -[2023-11-28 10:02:53,580][87426] Updated weights for policy 1, policy_version 374770 (0.0009) -[2023-11-28 10:02:53,952][87426] Updated weights for policy 1, policy_version 374780 (0.0011) -[2023-11-28 10:02:54,499][87424] Updated weights for policy 0, policy_version 375079 (0.0010) -[2023-11-28 10:02:54,889][87424] Updated weights for policy 0, policy_version 375089 (0.0012) -[2023-11-28 10:02:55,271][87424] Updated weights for policy 0, policy_version 375099 (0.0012) -[2023-11-28 10:02:56,055][87426] Updated weights for policy 1, policy_version 374790 (0.0012) -[2023-11-28 10:02:56,431][87426] Updated weights for policy 1, policy_version 374800 (0.0012) -[2023-11-28 10:02:56,808][87426] Updated weights for policy 1, policy_version 374810 (0.0012) -[2023-11-28 10:02:57,287][87424] Updated weights for policy 0, policy_version 375109 (0.0012) -[2023-11-28 10:02:57,661][87424] Updated weights for policy 0, policy_version 375119 (0.0012) -[2023-11-28 10:02:58,045][87424] Updated weights for policy 0, policy_version 375129 (0.0012) -[2023-11-28 10:02:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 191987712. Throughput: 0: 2697.8, 1: 2664.6. Samples: 191998672. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:02:58,445][86177] Avg episode reward: [(0, '-550.510'), (1, '-563.400')] -[2023-11-28 10:02:59,043][87426] Updated weights for policy 1, policy_version 374820 (0.0010) -[2023-11-28 10:02:59,422][87426] Updated weights for policy 1, policy_version 374830 (0.0007) -[2023-11-28 10:02:59,806][87426] Updated weights for policy 1, policy_version 374840 (0.0008) -[2023-11-28 10:03:00,267][87424] Updated weights for policy 0, policy_version 375139 (0.0010) -[2023-11-28 10:03:00,655][87424] Updated weights for policy 0, policy_version 375149 (0.0009) -[2023-11-28 10:03:01,033][87424] Updated weights for policy 0, policy_version 375159 (0.0007) -[2023-11-28 10:03:02,388][87426] Updated weights for policy 1, policy_version 374850 (0.0009) -[2023-11-28 10:03:02,767][87426] Updated weights for policy 1, policy_version 374860 (0.0007) -[2023-11-28 10:03:03,155][87426] Updated weights for policy 1, policy_version 374870 (0.0008) -[2023-11-28 10:03:03,335][87424] Updated weights for policy 0, policy_version 375169 (0.0008) -[2023-11-28 10:03:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 192004096. Throughput: 0: 2707.6, 1: 2659.6. Samples: 192022444. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:03,445][86177] Avg episode reward: [(0, '-547.740'), (1, '-513.880')] -[2023-11-28 10:03:03,532][87426] Updated weights for policy 1, policy_version 374880 (0.0011) -[2023-11-28 10:03:03,720][87424] Updated weights for policy 0, policy_version 375179 (0.0011) -[2023-11-28 10:03:04,114][87424] Updated weights for policy 0, policy_version 375189 (0.0011) -[2023-11-28 10:03:04,496][87424] Updated weights for policy 0, policy_version 375199 (0.0011) -[2023-11-28 10:03:05,472][87426] Updated weights for policy 1, policy_version 374890 (0.0008) -[2023-11-28 10:03:05,851][87426] Updated weights for policy 1, policy_version 374900 (0.0008) -[2023-11-28 10:03:06,220][87426] Updated weights for policy 1, policy_version 374910 (0.0007) -[2023-11-28 10:03:06,509][87424] Updated weights for policy 0, policy_version 375209 (0.0008) -[2023-11-28 10:03:06,895][87424] Updated weights for policy 0, policy_version 375219 (0.0009) -[2023-11-28 10:03:07,278][87424] Updated weights for policy 0, policy_version 375229 (0.0007) -[2023-11-28 10:03:08,286][87426] Updated weights for policy 1, policy_version 374920 (0.0008) -[2023-11-28 10:03:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192036864. Throughput: 0: 2702.5, 1: 2673.9. Samples: 192055440. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:08,445][86177] Avg episode reward: [(0, '-555.000'), (1, '-514.080')] -[2023-11-28 10:03:08,660][87426] Updated weights for policy 1, policy_version 374930 (0.0008) -[2023-11-28 10:03:09,045][87426] Updated weights for policy 1, policy_version 374940 (0.0010) -[2023-11-28 10:03:09,341][87424] Updated weights for policy 0, policy_version 375239 (0.0011) -[2023-11-28 10:03:09,723][87424] Updated weights for policy 0, policy_version 375249 (0.0012) -[2023-11-28 10:03:10,101][87424] Updated weights for policy 0, policy_version 375259 (0.0012) -[2023-11-28 10:03:11,418][87426] Updated weights for policy 1, policy_version 374950 (0.0012) -[2023-11-28 10:03:11,787][87426] Updated weights for policy 1, policy_version 374960 (0.0012) -[2023-11-28 10:03:12,167][87426] Updated weights for policy 1, policy_version 374970 (0.0012) -[2023-11-28 10:03:12,450][87424] Updated weights for policy 0, policy_version 375269 (0.0012) -[2023-11-28 10:03:12,834][87424] Updated weights for policy 0, policy_version 375279 (0.0012) -[2023-11-28 10:03:13,211][87424] Updated weights for policy 0, policy_version 375289 (0.0012) -[2023-11-28 10:03:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192061440. Throughput: 0: 2689.4, 1: 2661.7. Samples: 192078600. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:13,445][86177] Avg episode reward: [(0, '-534.070'), (1, '-513.070')] -[2023-11-28 10:03:14,640][87426] Updated weights for policy 1, policy_version 374980 (0.0011) -[2023-11-28 10:03:15,021][87426] Updated weights for policy 1, policy_version 374990 (0.0011) -[2023-11-28 10:03:15,136][87424] Updated weights for policy 0, policy_version 375299 (0.0012) -[2023-11-28 10:03:15,412][87426] Updated weights for policy 1, policy_version 375000 (0.0009) -[2023-11-28 10:03:15,521][87424] Updated weights for policy 0, policy_version 375309 (0.0011) -[2023-11-28 10:03:15,905][87424] Updated weights for policy 0, policy_version 375319 (0.0012) -[2023-11-28 10:03:17,287][87426] Updated weights for policy 1, policy_version 375010 (0.0009) -[2023-11-28 10:03:17,660][87426] Updated weights for policy 1, policy_version 375020 (0.0012) -[2023-11-28 10:03:18,034][87426] Updated weights for policy 1, policy_version 375030 (0.0012) -[2023-11-28 10:03:18,157][87424] Updated weights for policy 0, policy_version 375329 (0.0011) -[2023-11-28 10:03:18,422][87426] Updated weights for policy 1, policy_version 375040 (0.0012) -[2023-11-28 10:03:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 192094208. Throughput: 0: 2675.1, 1: 2655.8. Samples: 192102656. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:18,445][86177] Avg episode reward: [(0, '-542.060'), (1, '-509.930')] -[2023-11-28 10:03:18,541][87424] Updated weights for policy 0, policy_version 375339 (0.0011) -[2023-11-28 10:03:18,929][87424] Updated weights for policy 0, policy_version 375349 (0.0011) -[2023-11-28 10:03:19,301][87424] Updated weights for policy 0, policy_version 375359 (0.0009) -[2023-11-28 10:03:20,131][87426] Updated weights for policy 1, policy_version 375050 (0.0011) -[2023-11-28 10:03:20,504][87426] Updated weights for policy 1, policy_version 375060 (0.0011) -[2023-11-28 10:03:20,882][87426] Updated weights for policy 1, policy_version 375070 (0.0009) -[2023-11-28 10:03:21,753][87424] Updated weights for policy 0, policy_version 375369 (0.0011) -[2023-11-28 10:03:22,132][87424] Updated weights for policy 0, policy_version 375379 (0.0013) -[2023-11-28 10:03:22,513][87424] Updated weights for policy 0, policy_version 375389 (0.0012) -[2023-11-28 10:03:23,333][87426] Updated weights for policy 1, policy_version 375080 (0.0011) -[2023-11-28 10:03:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192118784. Throughput: 0: 2675.0, 1: 2651.7. Samples: 192134844. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:23,445][86177] Avg episode reward: [(0, '-547.000'), (1, '-508.140')] -[2023-11-28 10:03:23,716][87426] Updated weights for policy 1, policy_version 375090 (0.0012) -[2023-11-28 10:03:24,099][87426] Updated weights for policy 1, policy_version 375100 (0.0012) -[2023-11-28 10:03:24,496][87424] Updated weights for policy 0, policy_version 375399 (0.0009) -[2023-11-28 10:03:24,883][87424] Updated weights for policy 0, policy_version 375409 (0.0009) -[2023-11-28 10:03:25,251][87424] Updated weights for policy 0, policy_version 375419 (0.0008) -[2023-11-28 10:03:26,048][87426] Updated weights for policy 1, policy_version 375110 (0.0011) -[2023-11-28 10:03:26,427][87426] Updated weights for policy 1, policy_version 375120 (0.0008) -[2023-11-28 10:03:26,810][87426] Updated weights for policy 1, policy_version 375130 (0.0009) -[2023-11-28 10:03:27,726][87424] Updated weights for policy 0, policy_version 375429 (0.0011) -[2023-11-28 10:03:28,107][87424] Updated weights for policy 0, policy_version 375439 (0.0012) -[2023-11-28 10:03:28,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192143360. Throughput: 0: 2693.6, 1: 2644.2. Samples: 192159528. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:28,446][86177] Avg episode reward: [(0, '-547.370'), (1, '-508.800')] -[2023-11-28 10:03:28,493][87424] Updated weights for policy 0, policy_version 375449 (0.0008) -[2023-11-28 10:03:29,309][87426] Updated weights for policy 1, policy_version 375140 (0.0009) -[2023-11-28 10:03:29,682][87426] Updated weights for policy 1, policy_version 375150 (0.0012) -[2023-11-28 10:03:30,060][87426] Updated weights for policy 1, policy_version 375160 (0.0010) -[2023-11-28 10:03:30,954][87424] Updated weights for policy 0, policy_version 375459 (0.0009) -[2023-11-28 10:03:31,338][87424] Updated weights for policy 0, policy_version 375469 (0.0012) -[2023-11-28 10:03:31,723][87424] Updated weights for policy 0, policy_version 375479 (0.0012) -[2023-11-28 10:03:32,024][87426] Updated weights for policy 1, policy_version 375170 (0.0010) -[2023-11-28 10:03:32,394][87426] Updated weights for policy 1, policy_version 375180 (0.0011) -[2023-11-28 10:03:32,772][87426] Updated weights for policy 1, policy_version 375190 (0.0011) -[2023-11-28 10:03:33,148][87426] Updated weights for policy 1, policy_version 375200 (0.0011) -[2023-11-28 10:03:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192176128. Throughput: 0: 2680.4, 1: 2658.6. Samples: 192182868. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:33,446][86177] Avg episode reward: [(0, '-549.890'), (1, '-510.190')] -[2023-11-28 10:03:33,987][87424] Updated weights for policy 0, policy_version 375489 (0.0010) -[2023-11-28 10:03:34,376][87424] Updated weights for policy 0, policy_version 375499 (0.0011) -[2023-11-28 10:03:34,751][87424] Updated weights for policy 0, policy_version 375509 (0.0008) -[2023-11-28 10:03:35,139][87424] Updated weights for policy 0, policy_version 375519 (0.0009) -[2023-11-28 10:03:35,290][87426] Updated weights for policy 1, policy_version 375210 (0.0011) -[2023-11-28 10:03:35,669][87426] Updated weights for policy 1, policy_version 375220 (0.0009) -[2023-11-28 10:03:36,051][87426] Updated weights for policy 1, policy_version 375230 (0.0007) -[2023-11-28 10:03:37,131][87424] Updated weights for policy 0, policy_version 375529 (0.0012) -[2023-11-28 10:03:37,515][87424] Updated weights for policy 0, policy_version 375539 (0.0011) -[2023-11-28 10:03:37,889][87424] Updated weights for policy 0, policy_version 375549 (0.0010) -[2023-11-28 10:03:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192200704. Throughput: 0: 2673.4, 1: 2685.9. Samples: 192215248. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:38,445][86177] Avg episode reward: [(0, '-553.110'), (1, '-507.300')] -[2023-11-28 10:03:38,580][87426] Updated weights for policy 1, policy_version 375240 (0.0008) -[2023-11-28 10:03:38,973][87426] Updated weights for policy 1, policy_version 375250 (0.0009) -[2023-11-28 10:03:39,337][87426] Updated weights for policy 1, policy_version 375260 (0.0011) -[2023-11-28 10:03:39,915][87424] Updated weights for policy 0, policy_version 375559 (0.0010) -[2023-11-28 10:03:40,298][87424] Updated weights for policy 0, policy_version 375569 (0.0009) -[2023-11-28 10:03:40,672][87424] Updated weights for policy 0, policy_version 375579 (0.0011) -[2023-11-28 10:03:41,914][87426] Updated weights for policy 1, policy_version 375270 (0.0011) -[2023-11-28 10:03:42,288][87426] Updated weights for policy 1, policy_version 375280 (0.0011) -[2023-11-28 10:03:42,667][87426] Updated weights for policy 1, policy_version 375290 (0.0012) -[2023-11-28 10:03:43,179][87424] Updated weights for policy 0, policy_version 375589 (0.0011) -[2023-11-28 10:03:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192225280. Throughput: 0: 2678.7, 1: 2654.3. Samples: 192238656. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:43,445][86177] Avg episode reward: [(0, '-544.980'), (1, '-506.670')] -[2023-11-28 10:03:43,559][87424] Updated weights for policy 0, policy_version 375599 (0.0012) -[2023-11-28 10:03:43,933][87424] Updated weights for policy 0, policy_version 375609 (0.0012) -[2023-11-28 10:03:44,897][87426] Updated weights for policy 1, policy_version 375300 (0.0010) -[2023-11-28 10:03:45,280][87426] Updated weights for policy 1, policy_version 375310 (0.0010) -[2023-11-28 10:03:45,655][87426] Updated weights for policy 1, policy_version 375320 (0.0009) -[2023-11-28 10:03:46,453][87424] Updated weights for policy 0, policy_version 375619 (0.0011) -[2023-11-28 10:03:46,833][87424] Updated weights for policy 0, policy_version 375629 (0.0007) -[2023-11-28 10:03:47,217][87424] Updated weights for policy 0, policy_version 375639 (0.0009) -[2023-11-28 10:03:48,083][87426] Updated weights for policy 1, policy_version 375330 (0.0009) -[2023-11-28 10:03:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 192249856. Throughput: 0: 2687.1, 1: 2677.7. Samples: 192263860. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:48,445][86177] Avg episode reward: [(0, '-543.060'), (1, '-509.070')] -[2023-11-28 10:03:48,461][87426] Updated weights for policy 1, policy_version 375340 (0.0008) -[2023-11-28 10:03:48,844][87426] Updated weights for policy 1, policy_version 375350 (0.0007) -[2023-11-28 10:03:49,218][87424] Updated weights for policy 0, policy_version 375649 (0.0012) -[2023-11-28 10:03:49,227][87426] Updated weights for policy 1, policy_version 375360 (0.0011) -[2023-11-28 10:03:49,598][87424] Updated weights for policy 0, policy_version 375659 (0.0010) -[2023-11-28 10:03:49,979][87424] Updated weights for policy 0, policy_version 375669 (0.0009) -[2023-11-28 10:03:50,364][87424] Updated weights for policy 0, policy_version 375679 (0.0008) -[2023-11-28 10:03:51,155][87426] Updated weights for policy 1, policy_version 375370 (0.0012) -[2023-11-28 10:03:51,531][87426] Updated weights for policy 1, policy_version 375380 (0.0012) -[2023-11-28 10:03:51,902][87426] Updated weights for policy 1, policy_version 375390 (0.0010) -[2023-11-28 10:03:52,689][87424] Updated weights for policy 0, policy_version 375689 (0.0011) -[2023-11-28 10:03:53,070][87424] Updated weights for policy 0, policy_version 375699 (0.0012) -[2023-11-28 10:03:53,439][87424] Updated weights for policy 0, policy_version 375709 (0.0012) -[2023-11-28 10:03:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 192274432. Throughput: 0: 2691.0, 1: 2653.4. Samples: 192295940. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:53,445][86177] Avg episode reward: [(0, '-538.040'), (1, '-505.800')] -[2023-11-28 10:03:54,304][87426] Updated weights for policy 1, policy_version 375400 (0.0011) -[2023-11-28 10:03:54,692][87426] Updated weights for policy 1, policy_version 375410 (0.0008) -[2023-11-28 10:03:55,069][87426] Updated weights for policy 1, policy_version 375420 (0.0008) -[2023-11-28 10:03:55,561][87424] Updated weights for policy 0, policy_version 375719 (0.0012) -[2023-11-28 10:03:55,944][87424] Updated weights for policy 0, policy_version 375729 (0.0011) -[2023-11-28 10:03:56,331][87424] Updated weights for policy 0, policy_version 375739 (0.0010) -[2023-11-28 10:03:56,925][87426] Updated weights for policy 1, policy_version 375430 (0.0010) -[2023-11-28 10:03:57,299][87426] Updated weights for policy 1, policy_version 375440 (0.0011) -[2023-11-28 10:03:57,678][87426] Updated weights for policy 1, policy_version 375450 (0.0011) -[2023-11-28 10:03:58,104][87424] Updated weights for policy 0, policy_version 375749 (0.0010) -[2023-11-28 10:03:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192307200. Throughput: 0: 2689.1, 1: 2688.6. Samples: 192320596. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:03:58,445][86177] Avg episode reward: [(0, '-535.910'), (1, '-505.340')] -[2023-11-28 10:03:58,478][87424] Updated weights for policy 0, policy_version 375759 (0.0007) -[2023-11-28 10:03:58,871][87424] Updated weights for policy 0, policy_version 375769 (0.0008) -[2023-11-28 10:04:00,077][87426] Updated weights for policy 1, policy_version 375460 (0.0012) -[2023-11-28 10:04:00,449][87426] Updated weights for policy 1, policy_version 375470 (0.0016) -[2023-11-28 10:04:00,822][87426] Updated weights for policy 1, policy_version 375480 (0.0010) -[2023-11-28 10:04:01,149][87424] Updated weights for policy 0, policy_version 375779 (0.0009) -[2023-11-28 10:04:01,533][87424] Updated weights for policy 0, policy_version 375789 (0.0012) -[2023-11-28 10:04:01,911][87424] Updated weights for policy 0, policy_version 375799 (0.0009) -[2023-11-28 10:04:02,819][87426] Updated weights for policy 1, policy_version 375490 (0.0010) -[2023-11-28 10:04:03,209][87426] Updated weights for policy 1, policy_version 375500 (0.0011) -[2023-11-28 10:04:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192331776. Throughput: 0: 2703.2, 1: 2689.8. Samples: 192345340. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:04:03,445][86177] Avg episode reward: [(0, '-536.610'), (1, '-499.640')] -[2023-11-28 10:04:03,582][87426] Updated weights for policy 1, policy_version 375510 (0.0011) -[2023-11-28 10:04:03,960][87426] Updated weights for policy 1, policy_version 375520 (0.0008) -[2023-11-28 10:04:04,111][87424] Updated weights for policy 0, policy_version 375809 (0.0011) -[2023-11-28 10:04:04,500][87424] Updated weights for policy 0, policy_version 375819 (0.0011) -[2023-11-28 10:04:04,881][87424] Updated weights for policy 0, policy_version 375829 (0.0009) -[2023-11-28 10:04:05,261][87424] Updated weights for policy 0, policy_version 375839 (0.0012) -[2023-11-28 10:04:05,937][87426] Updated weights for policy 1, policy_version 375530 (0.0011) -[2023-11-28 10:04:06,317][87426] Updated weights for policy 1, policy_version 375540 (0.0012) -[2023-11-28 10:04:06,696][87426] Updated weights for policy 1, policy_version 375550 (0.0012) -[2023-11-28 10:04:07,307][87424] Updated weights for policy 0, policy_version 375849 (0.0008) -[2023-11-28 10:04:07,687][87424] Updated weights for policy 0, policy_version 375859 (0.0008) -[2023-11-28 10:04:08,064][87424] Updated weights for policy 0, policy_version 375869 (0.0008) -[2023-11-28 10:04:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192364544. Throughput: 0: 2738.0, 1: 2701.5. Samples: 192379620. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:04:08,445][86177] Avg episode reward: [(0, '-536.990'), (1, '-499.970')] -[2023-11-28 10:04:08,750][87426] Updated weights for policy 1, policy_version 375560 (0.0012) -[2023-11-28 10:04:09,129][87426] Updated weights for policy 1, policy_version 375570 (0.0012) -[2023-11-28 10:04:09,511][87426] Updated weights for policy 1, policy_version 375580 (0.0012) -[2023-11-28 10:04:09,705][87424] Updated weights for policy 0, policy_version 375879 (0.0009) -[2023-11-28 10:04:10,089][87424] Updated weights for policy 0, policy_version 375889 (0.0011) -[2023-11-28 10:04:10,463][87424] Updated weights for policy 0, policy_version 375899 (0.0010) -[2023-11-28 10:04:11,973][87426] Updated weights for policy 1, policy_version 375590 (0.0011) -[2023-11-28 10:04:12,350][87426] Updated weights for policy 1, policy_version 375600 (0.0012) -[2023-11-28 10:04:12,723][87426] Updated weights for policy 1, policy_version 375610 (0.0012) -[2023-11-28 10:04:12,794][87424] Updated weights for policy 0, policy_version 375909 (0.0011) -[2023-11-28 10:04:13,167][87424] Updated weights for policy 0, policy_version 375919 (0.0012) -[2023-11-28 10:04:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192389120. Throughput: 0: 2701.4, 1: 2715.8. Samples: 192403304. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:04:13,445][86177] Avg episode reward: [(0, '-538.040'), (1, '-502.620')] -[2023-11-28 10:04:13,551][87424] Updated weights for policy 0, policy_version 375929 (0.0012) -[2023-11-28 10:04:14,814][87426] Updated weights for policy 1, policy_version 375620 (0.0012) -[2023-11-28 10:04:15,210][87426] Updated weights for policy 1, policy_version 375630 (0.0012) -[2023-11-28 10:04:15,582][87426] Updated weights for policy 1, policy_version 375640 (0.0012) -[2023-11-28 10:04:15,895][87424] Updated weights for policy 0, policy_version 375939 (0.0012) -[2023-11-28 10:04:16,275][87424] Updated weights for policy 0, policy_version 375949 (0.0012) -[2023-11-28 10:04:16,658][87424] Updated weights for policy 0, policy_version 375959 (0.0012) -[2023-11-28 10:04:17,323][87426] Updated weights for policy 1, policy_version 375650 (0.0011) -[2023-11-28 10:04:17,703][87426] Updated weights for policy 1, policy_version 375660 (0.0009) -[2023-11-28 10:04:18,083][87426] Updated weights for policy 1, policy_version 375670 (0.0008) -[2023-11-28 10:04:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192413696. Throughput: 0: 2721.1, 1: 2733.9. Samples: 192428340. Policy #0 lag: (min: 31.0, avg: 48.8, max: 67.0) -[2023-11-28 10:04:18,446][86177] Avg episode reward: [(0, '-534.510'), (1, '-504.350')] -[2023-11-28 10:04:18,458][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000375968_96247808.pth... -[2023-11-28 10:04:18,478][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000375680_96174080.pth... -[2023-11-28 10:04:18,480][87426] Updated weights for policy 1, policy_version 375680 (0.0011) -[2023-11-28 10:04:18,505][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000373472_95608832.pth -[2023-11-28 10:04:18,524][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000373152_95526912.pth -[2023-11-28 10:04:18,673][87424] Updated weights for policy 0, policy_version 375969 (0.0012) -[2023-11-28 10:04:19,055][87424] Updated weights for policy 0, policy_version 375979 (0.0012) -[2023-11-28 10:04:19,433][87424] Updated weights for policy 0, policy_version 375989 (0.0012) -[2023-11-28 10:04:19,810][87424] Updated weights for policy 0, policy_version 375999 (0.0012) -[2023-11-28 10:04:20,473][87426] Updated weights for policy 1, policy_version 375690 (0.0008) -[2023-11-28 10:04:20,853][87426] Updated weights for policy 1, policy_version 375700 (0.0008) -[2023-11-28 10:04:21,242][87426] Updated weights for policy 1, policy_version 375710 (0.0008) -[2023-11-28 10:04:22,474][87424] Updated weights for policy 0, policy_version 376009 (0.0012) -[2023-11-28 10:04:22,859][87424] Updated weights for policy 0, policy_version 376019 (0.0012) -[2023-11-28 10:04:23,243][87424] Updated weights for policy 0, policy_version 376029 (0.0011) -[2023-11-28 10:04:23,395][87426] Updated weights for policy 1, policy_version 375720 (0.0011) -[2023-11-28 10:04:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192446464. Throughput: 0: 2723.4, 1: 2727.2. Samples: 192460524. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:04:23,445][86177] Avg episode reward: [(0, '-551.480'), (1, '-541.950')] -[2023-11-28 10:04:23,771][87426] Updated weights for policy 1, policy_version 375730 (0.0012) -[2023-11-28 10:04:24,154][87426] Updated weights for policy 1, policy_version 375740 (0.0012) -[2023-11-28 10:04:25,148][87424] Updated weights for policy 0, policy_version 376039 (0.0016) -[2023-11-28 10:04:25,537][87424] Updated weights for policy 0, policy_version 376049 (0.0011) -[2023-11-28 10:04:25,931][87424] Updated weights for policy 0, policy_version 376059 (0.0011) -[2023-11-28 10:04:25,984][87426] Updated weights for policy 1, policy_version 375750 (0.0012) -[2023-11-28 10:04:26,362][87426] Updated weights for policy 1, policy_version 375760 (0.0012) -[2023-11-28 10:04:26,743][87426] Updated weights for policy 1, policy_version 375770 (0.0012) -[2023-11-28 10:04:27,765][87424] Updated weights for policy 0, policy_version 376069 (0.0010) -[2023-11-28 10:04:28,143][87424] Updated weights for policy 0, policy_version 376079 (0.0008) -[2023-11-28 10:04:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192471040. Throughput: 0: 2746.7, 1: 2760.4. Samples: 192486472. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:04:28,445][86177] Avg episode reward: [(0, '-555.720'), (1, '-543.120')] -[2023-11-28 10:04:28,536][87424] Updated weights for policy 0, policy_version 376089 (0.0007) -[2023-11-28 10:04:29,294][87426] Updated weights for policy 1, policy_version 375780 (0.0012) -[2023-11-28 10:04:29,666][87426] Updated weights for policy 1, policy_version 375790 (0.0012) -[2023-11-28 10:04:30,047][87426] Updated weights for policy 1, policy_version 375800 (0.0012) -[2023-11-28 10:04:30,679][87424] Updated weights for policy 0, policy_version 376099 (0.0007) -[2023-11-28 10:04:31,061][87424] Updated weights for policy 0, policy_version 376109 (0.0010) -[2023-11-28 10:04:31,446][87424] Updated weights for policy 0, policy_version 376119 (0.0011) -[2023-11-28 10:04:32,575][87426] Updated weights for policy 1, policy_version 375810 (0.0011) -[2023-11-28 10:04:32,955][87426] Updated weights for policy 1, policy_version 375820 (0.0010) -[2023-11-28 10:04:33,345][87426] Updated weights for policy 1, policy_version 375830 (0.0011) -[2023-11-28 10:04:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192495616. Throughput: 0: 2739.8, 1: 2741.0. Samples: 192510496. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:04:33,445][86177] Avg episode reward: [(0, '-561.260'), (1, '-546.720')] -[2023-11-28 10:04:33,629][87424] Updated weights for policy 0, policy_version 376129 (0.0010) -[2023-11-28 10:04:33,721][87426] Updated weights for policy 1, policy_version 375840 (0.0012) -[2023-11-28 10:04:34,002][87424] Updated weights for policy 0, policy_version 376139 (0.0008) -[2023-11-28 10:04:34,383][87424] Updated weights for policy 0, policy_version 376149 (0.0008) -[2023-11-28 10:04:34,769][87424] Updated weights for policy 0, policy_version 376159 (0.0010) -[2023-11-28 10:04:35,877][87426] Updated weights for policy 1, policy_version 375850 (0.0012) -[2023-11-28 10:04:36,261][87426] Updated weights for policy 1, policy_version 375860 (0.0012) -[2023-11-28 10:04:36,639][87426] Updated weights for policy 1, policy_version 375870 (0.0010) -[2023-11-28 10:04:36,825][87424] Updated weights for policy 0, policy_version 376169 (0.0011) -[2023-11-28 10:04:37,219][87424] Updated weights for policy 0, policy_version 376179 (0.0008) -[2023-11-28 10:04:37,591][87424] Updated weights for policy 0, policy_version 376189 (0.0007) -[2023-11-28 10:04:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192528384. Throughput: 0: 2738.2, 1: 2754.9. Samples: 192543132. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:04:38,445][86177] Avg episode reward: [(0, '-567.110'), (1, '-547.460')] -[2023-11-28 10:04:38,764][87426] Updated weights for policy 1, policy_version 375880 (0.0011) -[2023-11-28 10:04:39,134][87426] Updated weights for policy 1, policy_version 375890 (0.0010) -[2023-11-28 10:04:39,510][87426] Updated weights for policy 1, policy_version 375900 (0.0011) -[2023-11-28 10:04:39,516][87424] Updated weights for policy 0, policy_version 376199 (0.0009) -[2023-11-28 10:04:39,906][87424] Updated weights for policy 0, policy_version 376209 (0.0011) -[2023-11-28 10:04:40,282][87424] Updated weights for policy 0, policy_version 376219 (0.0012) -[2023-11-28 10:04:41,775][87426] Updated weights for policy 1, policy_version 375910 (0.0011) -[2023-11-28 10:04:42,158][87426] Updated weights for policy 1, policy_version 375920 (0.0009) -[2023-11-28 10:04:42,534][87426] Updated weights for policy 1, policy_version 375930 (0.0010) -[2023-11-28 10:04:42,625][87424] Updated weights for policy 0, policy_version 376229 (0.0012) -[2023-11-28 10:04:42,996][87424] Updated weights for policy 0, policy_version 376239 (0.0012) -[2023-11-28 10:04:43,374][87424] Updated weights for policy 0, policy_version 376249 (0.0008) -[2023-11-28 10:04:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192552960. Throughput: 0: 2747.1, 1: 2731.6. Samples: 192567136. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:04:43,445][86177] Avg episode reward: [(0, '-560.770'), (1, '-509.030')] -[2023-11-28 10:04:44,899][87426] Updated weights for policy 1, policy_version 375940 (0.0009) -[2023-11-28 10:04:45,294][87426] Updated weights for policy 1, policy_version 375950 (0.0008) -[2023-11-28 10:04:45,676][87426] Updated weights for policy 1, policy_version 375960 (0.0011) -[2023-11-28 10:04:45,895][87424] Updated weights for policy 0, policy_version 376259 (0.0009) -[2023-11-28 10:04:46,282][87424] Updated weights for policy 0, policy_version 376269 (0.0008) -[2023-11-28 10:04:46,662][87424] Updated weights for policy 0, policy_version 376279 (0.0008) -[2023-11-28 10:04:47,823][87426] Updated weights for policy 1, policy_version 375970 (0.0010) -[2023-11-28 10:04:48,201][87426] Updated weights for policy 1, policy_version 375980 (0.0011) -[2023-11-28 10:04:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192577536. Throughput: 0: 2725.2, 1: 2738.1. Samples: 192591188. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:04:48,445][86177] Avg episode reward: [(0, '-555.600'), (1, '-511.900')] -[2023-11-28 10:04:48,580][87426] Updated weights for policy 1, policy_version 375990 (0.0008) -[2023-11-28 10:04:48,962][87426] Updated weights for policy 1, policy_version 376000 (0.0008) -[2023-11-28 10:04:49,175][87424] Updated weights for policy 0, policy_version 376289 (0.0008) -[2023-11-28 10:04:49,564][87424] Updated weights for policy 0, policy_version 376299 (0.0008) -[2023-11-28 10:04:49,946][87424] Updated weights for policy 0, policy_version 376309 (0.0010) -[2023-11-28 10:04:50,319][87424] Updated weights for policy 0, policy_version 376319 (0.0011) -[2023-11-28 10:04:51,555][87426] Updated weights for policy 1, policy_version 376010 (0.0011) -[2023-11-28 10:04:51,938][87426] Updated weights for policy 1, policy_version 376020 (0.0012) -[2023-11-28 10:04:52,326][87426] Updated weights for policy 1, policy_version 376030 (0.0012) -[2023-11-28 10:04:52,693][87424] Updated weights for policy 0, policy_version 376329 (0.0012) -[2023-11-28 10:04:53,077][87424] Updated weights for policy 0, policy_version 376339 (0.0012) -[2023-11-28 10:04:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 192602112. Throughput: 0: 2699.8, 1: 2722.6. Samples: 192623628. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:04:53,445][86177] Avg episode reward: [(0, '-558.870'), (1, '-506.900')] -[2023-11-28 10:04:53,457][87424] Updated weights for policy 0, policy_version 376349 (0.0012) -[2023-11-28 10:04:54,603][87426] Updated weights for policy 1, policy_version 376040 (0.0009) -[2023-11-28 10:04:54,986][87426] Updated weights for policy 1, policy_version 376050 (0.0007) -[2023-11-28 10:04:55,362][87426] Updated weights for policy 1, policy_version 376060 (0.0010) -[2023-11-28 10:04:55,461][87424] Updated weights for policy 0, policy_version 376359 (0.0012) -[2023-11-28 10:04:55,843][87424] Updated weights for policy 0, policy_version 376369 (0.0008) -[2023-11-28 10:04:56,228][87424] Updated weights for policy 0, policy_version 376379 (0.0008) -[2023-11-28 10:04:57,097][87426] Updated weights for policy 1, policy_version 376070 (0.0011) -[2023-11-28 10:04:57,468][87426] Updated weights for policy 1, policy_version 376080 (0.0012) -[2023-11-28 10:04:57,849][87426] Updated weights for policy 1, policy_version 376090 (0.0012) -[2023-11-28 10:04:58,338][87424] Updated weights for policy 0, policy_version 376389 (0.0009) -[2023-11-28 10:04:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 192634880. Throughput: 0: 2728.8, 1: 2707.0. Samples: 192647916. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:04:58,445][86177] Avg episode reward: [(0, '-566.950'), (1, '-508.140')] -[2023-11-28 10:04:58,722][87424] Updated weights for policy 0, policy_version 376399 (0.0012) -[2023-11-28 10:04:59,095][87424] Updated weights for policy 0, policy_version 376409 (0.0011) -[2023-11-28 10:05:00,219][87426] Updated weights for policy 1, policy_version 376100 (0.0010) -[2023-11-28 10:05:00,589][87426] Updated weights for policy 1, policy_version 376110 (0.0010) -[2023-11-28 10:05:00,970][87426] Updated weights for policy 1, policy_version 376120 (0.0008) -[2023-11-28 10:05:01,713][87424] Updated weights for policy 0, policy_version 376419 (0.0012) -[2023-11-28 10:05:02,099][87424] Updated weights for policy 0, policy_version 376429 (0.0011) -[2023-11-28 10:05:02,469][87424] Updated weights for policy 0, policy_version 376439 (0.0011) -[2023-11-28 10:05:02,902][87426] Updated weights for policy 1, policy_version 376130 (0.0008) -[2023-11-28 10:05:03,291][87426] Updated weights for policy 1, policy_version 376140 (0.0012) -[2023-11-28 10:05:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192659456. Throughput: 0: 2746.1, 1: 2696.3. Samples: 192673244. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:05:03,445][86177] Avg episode reward: [(0, '-588.990'), (1, '-507.130')] -[2023-11-28 10:05:03,657][87426] Updated weights for policy 1, policy_version 376150 (0.0012) -[2023-11-28 10:05:04,038][87426] Updated weights for policy 1, policy_version 376160 (0.0012) -[2023-11-28 10:05:04,669][87424] Updated weights for policy 0, policy_version 376449 (0.0011) -[2023-11-28 10:05:05,067][87424] Updated weights for policy 0, policy_version 376459 (0.0012) -[2023-11-28 10:05:05,449][87424] Updated weights for policy 0, policy_version 376469 (0.0012) -[2023-11-28 10:05:05,823][87424] Updated weights for policy 0, policy_version 376479 (0.0011) -[2023-11-28 10:05:06,266][87426] Updated weights for policy 1, policy_version 376170 (0.0012) -[2023-11-28 10:05:06,651][87426] Updated weights for policy 1, policy_version 376180 (0.0010) -[2023-11-28 10:05:07,026][87426] Updated weights for policy 1, policy_version 376190 (0.0009) -[2023-11-28 10:05:07,457][87424] Updated weights for policy 0, policy_version 376489 (0.0008) -[2023-11-28 10:05:07,836][87424] Updated weights for policy 0, policy_version 376499 (0.0008) -[2023-11-28 10:05:08,219][87424] Updated weights for policy 0, policy_version 376509 (0.0010) -[2023-11-28 10:05:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192692224. Throughput: 0: 2747.8, 1: 2704.6. Samples: 192705884. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:05:08,445][86177] Avg episode reward: [(0, '-622.080'), (1, '-511.100')] -[2023-11-28 10:05:09,430][87426] Updated weights for policy 1, policy_version 376200 (0.0008) -[2023-11-28 10:05:09,815][87426] Updated weights for policy 1, policy_version 376210 (0.0009) -[2023-11-28 10:05:10,192][87426] Updated weights for policy 1, policy_version 376220 (0.0012) -[2023-11-28 10:05:10,306][87424] Updated weights for policy 0, policy_version 376519 (0.0010) -[2023-11-28 10:05:10,695][87424] Updated weights for policy 0, policy_version 376529 (0.0012) -[2023-11-28 10:05:11,080][87424] Updated weights for policy 0, policy_version 376539 (0.0011) -[2023-11-28 10:05:12,273][87426] Updated weights for policy 1, policy_version 376230 (0.0010) -[2023-11-28 10:05:12,652][87426] Updated weights for policy 1, policy_version 376240 (0.0011) -[2023-11-28 10:05:13,045][87426] Updated weights for policy 1, policy_version 376250 (0.0009) -[2023-11-28 10:05:13,324][87424] Updated weights for policy 0, policy_version 376549 (0.0012) -[2023-11-28 10:05:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 192716800. Throughput: 0: 2717.1, 1: 2689.7. Samples: 192729776. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:05:13,445][86177] Avg episode reward: [(0, '-613.290'), (1, '-515.950')] -[2023-11-28 10:05:13,707][87424] Updated weights for policy 0, policy_version 376559 (0.0012) -[2023-11-28 10:05:14,091][87424] Updated weights for policy 0, policy_version 376569 (0.0012) -[2023-11-28 10:05:15,455][87426] Updated weights for policy 1, policy_version 376260 (0.0010) -[2023-11-28 10:05:15,834][87426] Updated weights for policy 1, policy_version 376270 (0.0011) -[2023-11-28 10:05:16,213][87426] Updated weights for policy 1, policy_version 376280 (0.0009) -[2023-11-28 10:05:16,406][87424] Updated weights for policy 0, policy_version 376579 (0.0009) -[2023-11-28 10:05:16,786][87424] Updated weights for policy 0, policy_version 376589 (0.0008) -[2023-11-28 10:05:17,174][87424] Updated weights for policy 0, policy_version 376599 (0.0009) -[2023-11-28 10:05:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 192741376. Throughput: 0: 2705.8, 1: 2696.3. Samples: 192753588. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:05:18,445][86177] Avg episode reward: [(0, '-620.900'), (1, '-514.040')] -[2023-11-28 10:05:18,537][87426] Updated weights for policy 1, policy_version 376290 (0.0008) -[2023-11-28 10:05:18,913][87426] Updated weights for policy 1, policy_version 376300 (0.0012) -[2023-11-28 10:05:19,264][87424] Updated weights for policy 0, policy_version 376609 (0.0011) -[2023-11-28 10:05:19,289][87426] Updated weights for policy 1, policy_version 376310 (0.0011) -[2023-11-28 10:05:19,643][87424] Updated weights for policy 0, policy_version 376619 (0.0011) -[2023-11-28 10:05:19,671][87426] Updated weights for policy 1, policy_version 376320 (0.0012) -[2023-11-28 10:05:20,023][87424] Updated weights for policy 0, policy_version 376629 (0.0011) -[2023-11-28 10:05:20,402][87424] Updated weights for policy 0, policy_version 376639 (0.0012) -[2023-11-28 10:05:22,153][87426] Updated weights for policy 1, policy_version 376330 (0.0009) -[2023-11-28 10:05:22,534][87426] Updated weights for policy 1, policy_version 376340 (0.0011) -[2023-11-28 10:05:22,841][87424] Updated weights for policy 0, policy_version 376649 (0.0011) -[2023-11-28 10:05:22,906][87426] Updated weights for policy 1, policy_version 376350 (0.0009) -[2023-11-28 10:05:23,219][87424] Updated weights for policy 0, policy_version 376659 (0.0012) -[2023-11-28 10:05:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 192765952. Throughput: 0: 2695.0, 1: 2682.8. Samples: 192785136. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:05:23,445][86177] Avg episode reward: [(0, '-581.480'), (1, '-517.420')] -[2023-11-28 10:05:23,592][87424] Updated weights for policy 0, policy_version 376669 (0.0012) -[2023-11-28 10:05:25,083][87426] Updated weights for policy 1, policy_version 376360 (0.0012) -[2023-11-28 10:05:25,468][87426] Updated weights for policy 1, policy_version 376370 (0.0008) -[2023-11-28 10:05:25,527][87424] Updated weights for policy 0, policy_version 376679 (0.0009) -[2023-11-28 10:05:25,840][87426] Updated weights for policy 1, policy_version 376380 (0.0011) -[2023-11-28 10:05:25,907][87424] Updated weights for policy 0, policy_version 376689 (0.0008) -[2023-11-28 10:05:26,300][87424] Updated weights for policy 0, policy_version 376699 (0.0007) -[2023-11-28 10:05:27,732][87426] Updated weights for policy 1, policy_version 376390 (0.0011) -[2023-11-28 10:05:28,103][87426] Updated weights for policy 1, policy_version 376400 (0.0011) -[2023-11-28 10:05:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192790528. Throughput: 0: 2715.6, 1: 2681.7. Samples: 192810012. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:05:28,445][86177] Avg episode reward: [(0, '-605.700'), (1, '-514.460')] -[2023-11-28 10:05:28,488][87426] Updated weights for policy 1, policy_version 376410 (0.0012) -[2023-11-28 10:05:28,495][87424] Updated weights for policy 0, policy_version 376709 (0.0010) -[2023-11-28 10:05:28,874][87424] Updated weights for policy 0, policy_version 376719 (0.0012) -[2023-11-28 10:05:29,258][87424] Updated weights for policy 0, policy_version 376729 (0.0008) -[2023-11-28 10:05:30,802][87426] Updated weights for policy 1, policy_version 376420 (0.0011) -[2023-11-28 10:05:31,182][87426] Updated weights for policy 1, policy_version 376430 (0.0012) -[2023-11-28 10:05:31,459][87424] Updated weights for policy 0, policy_version 376739 (0.0011) -[2023-11-28 10:05:31,562][87426] Updated weights for policy 1, policy_version 376440 (0.0012) -[2023-11-28 10:05:31,840][87424] Updated weights for policy 0, policy_version 376749 (0.0011) -[2023-11-28 10:05:32,210][87424] Updated weights for policy 0, policy_version 376759 (0.0009) -[2023-11-28 10:05:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192823296. Throughput: 0: 2722.5, 1: 2689.2. Samples: 192834712. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:05:33,445][86177] Avg episode reward: [(0, '-623.760'), (1, '-513.150')] -[2023-11-28 10:05:33,584][87426] Updated weights for policy 1, policy_version 376450 (0.0011) -[2023-11-28 10:05:33,962][87426] Updated weights for policy 1, policy_version 376460 (0.0012) -[2023-11-28 10:05:34,340][87426] Updated weights for policy 1, policy_version 376470 (0.0011) -[2023-11-28 10:05:34,358][87424] Updated weights for policy 0, policy_version 376769 (0.0008) -[2023-11-28 10:05:34,722][87426] Updated weights for policy 1, policy_version 376480 (0.0010) -[2023-11-28 10:05:34,750][87424] Updated weights for policy 0, policy_version 376779 (0.0011) -[2023-11-28 10:05:35,125][87424] Updated weights for policy 0, policy_version 376789 (0.0012) -[2023-11-28 10:05:35,503][87424] Updated weights for policy 0, policy_version 376799 (0.0012) -[2023-11-28 10:05:36,457][87426] Updated weights for policy 1, policy_version 376490 (0.0009) -[2023-11-28 10:05:36,837][87426] Updated weights for policy 1, policy_version 376500 (0.0010) -[2023-11-28 10:05:37,217][87426] Updated weights for policy 1, policy_version 376510 (0.0012) -[2023-11-28 10:05:37,257][87424] Updated weights for policy 0, policy_version 376809 (0.0012) -[2023-11-28 10:05:37,650][87424] Updated weights for policy 0, policy_version 376819 (0.0012) -[2023-11-28 10:05:38,039][87424] Updated weights for policy 0, policy_version 376829 (0.0012) -[2023-11-28 10:05:38,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 192856064. Throughput: 0: 2750.1, 1: 2665.3. Samples: 192867324. Policy #0 lag: (min: 31.0, avg: 41.4, max: 63.0) -[2023-11-28 10:05:38,445][86177] Avg episode reward: [(0, '-599.980'), (1, '-561.210')] -[2023-11-28 10:05:39,751][87426] Updated weights for policy 1, policy_version 376520 (0.0012) -[2023-11-28 10:05:40,120][87426] Updated weights for policy 1, policy_version 376530 (0.0011) -[2023-11-28 10:05:40,498][87426] Updated weights for policy 1, policy_version 376540 (0.0010) -[2023-11-28 10:05:40,591][87424] Updated weights for policy 0, policy_version 376839 (0.0011) -[2023-11-28 10:05:40,975][87424] Updated weights for policy 0, policy_version 376849 (0.0012) -[2023-11-28 10:05:41,352][87424] Updated weights for policy 0, policy_version 376859 (0.0012) -[2023-11-28 10:05:42,844][87426] Updated weights for policy 1, policy_version 376550 (0.0010) -[2023-11-28 10:05:43,225][87426] Updated weights for policy 1, policy_version 376560 (0.0011) -[2023-11-28 10:05:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192872448. Throughput: 0: 2728.1, 1: 2701.0. Samples: 192892224. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:05:43,445][86177] Avg episode reward: [(0, '-609.320'), (1, '-553.160')] -[2023-11-28 10:05:43,614][87426] Updated weights for policy 1, policy_version 376570 (0.0011) -[2023-11-28 10:05:43,967][87424] Updated weights for policy 0, policy_version 376869 (0.0011) -[2023-11-28 10:05:44,348][87424] Updated weights for policy 0, policy_version 376879 (0.0009) -[2023-11-28 10:05:44,731][87424] Updated weights for policy 0, policy_version 376889 (0.0010) -[2023-11-28 10:05:46,050][87426] Updated weights for policy 1, policy_version 376580 (0.0010) -[2023-11-28 10:05:46,426][87426] Updated weights for policy 1, policy_version 376590 (0.0011) -[2023-11-28 10:05:46,494][87424] Updated weights for policy 0, policy_version 376899 (0.0009) -[2023-11-28 10:05:46,804][87426] Updated weights for policy 1, policy_version 376600 (0.0011) -[2023-11-28 10:05:46,879][87424] Updated weights for policy 0, policy_version 376909 (0.0012) -[2023-11-28 10:05:47,278][87424] Updated weights for policy 0, policy_version 376919 (0.0011) -[2023-11-28 10:05:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.2). Total num frames: 192905216. Throughput: 0: 2714.4, 1: 2689.1. Samples: 192916404. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:05:48,445][86177] Avg episode reward: [(0, '-551.400'), (1, '-549.150')] -[2023-11-28 10:05:48,551][87426] Updated weights for policy 1, policy_version 376610 (0.0012) -[2023-11-28 10:05:48,929][87426] Updated weights for policy 1, policy_version 376620 (0.0012) -[2023-11-28 10:05:49,304][87426] Updated weights for policy 1, policy_version 376630 (0.0012) -[2023-11-28 10:05:49,346][87424] Updated weights for policy 0, policy_version 376929 (0.0011) -[2023-11-28 10:05:49,683][87426] Updated weights for policy 1, policy_version 376640 (0.0012) -[2023-11-28 10:05:49,720][87424] Updated weights for policy 0, policy_version 376939 (0.0012) -[2023-11-28 10:05:50,097][87424] Updated weights for policy 0, policy_version 376949 (0.0009) -[2023-11-28 10:05:50,481][87424] Updated weights for policy 0, policy_version 376959 (0.0008) -[2023-11-28 10:05:51,465][87426] Updated weights for policy 1, policy_version 376650 (0.0009) -[2023-11-28 10:05:51,840][87426] Updated weights for policy 1, policy_version 376660 (0.0012) -[2023-11-28 10:05:52,224][87426] Updated weights for policy 1, policy_version 376670 (0.0012) -[2023-11-28 10:05:52,779][87424] Updated weights for policy 0, policy_version 376969 (0.0009) -[2023-11-28 10:05:53,148][87424] Updated weights for policy 0, policy_version 376979 (0.0011) -[2023-11-28 10:05:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 192929792. Throughput: 0: 2715.0, 1: 2690.0. Samples: 192949112. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:05:53,445][86177] Avg episode reward: [(0, '-569.960'), (1, '-544.900')] -[2023-11-28 10:05:53,528][87424] Updated weights for policy 0, policy_version 376989 (0.0012) -[2023-11-28 10:05:54,824][87426] Updated weights for policy 1, policy_version 376680 (0.0012) -[2023-11-28 10:05:55,205][87426] Updated weights for policy 1, policy_version 376690 (0.0012) -[2023-11-28 10:05:55,577][87426] Updated weights for policy 1, policy_version 376700 (0.0009) -[2023-11-28 10:05:55,870][87424] Updated weights for policy 0, policy_version 376999 (0.0012) -[2023-11-28 10:05:56,258][87424] Updated weights for policy 0, policy_version 377009 (0.0010) -[2023-11-28 10:05:56,633][87424] Updated weights for policy 0, policy_version 377019 (0.0009) -[2023-11-28 10:05:57,737][87426] Updated weights for policy 1, policy_version 376710 (0.0011) -[2023-11-28 10:05:58,120][87426] Updated weights for policy 1, policy_version 376720 (0.0012) -[2023-11-28 10:05:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 192954368. Throughput: 0: 2718.3, 1: 2698.4. Samples: 192973528. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:05:58,445][86177] Avg episode reward: [(0, '-576.610'), (1, '-496.320')] -[2023-11-28 10:05:58,496][87426] Updated weights for policy 1, policy_version 376730 (0.0012) -[2023-11-28 10:05:59,253][87424] Updated weights for policy 0, policy_version 377029 (0.0011) -[2023-11-28 10:05:59,628][87424] Updated weights for policy 0, policy_version 377039 (0.0012) -[2023-11-28 10:06:00,021][87424] Updated weights for policy 0, policy_version 377049 (0.0015) -[2023-11-28 10:06:01,076][87426] Updated weights for policy 1, policy_version 376740 (0.0011) -[2023-11-28 10:06:01,457][87426] Updated weights for policy 1, policy_version 376750 (0.0010) -[2023-11-28 10:06:01,839][87426] Updated weights for policy 1, policy_version 376760 (0.0010) -[2023-11-28 10:06:02,311][87424] Updated weights for policy 0, policy_version 377059 (0.0009) -[2023-11-28 10:06:02,696][87424] Updated weights for policy 0, policy_version 377069 (0.0011) -[2023-11-28 10:06:03,093][87424] Updated weights for policy 0, policy_version 377079 (0.0011) -[2023-11-28 10:06:03,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 192987136. Throughput: 0: 2707.4, 1: 2681.1. Samples: 192996068. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:03,445][86177] Avg episode reward: [(0, '-569.010'), (1, '-497.610')] -[2023-11-28 10:06:04,187][87426] Updated weights for policy 1, policy_version 376770 (0.0009) -[2023-11-28 10:06:04,555][87426] Updated weights for policy 1, policy_version 376780 (0.0012) -[2023-11-28 10:06:04,934][87426] Updated weights for policy 1, policy_version 376790 (0.0012) -[2023-11-28 10:06:05,073][87424] Updated weights for policy 0, policy_version 377089 (0.0011) -[2023-11-28 10:06:05,306][87426] Updated weights for policy 1, policy_version 376800 (0.0010) -[2023-11-28 10:06:05,451][87424] Updated weights for policy 0, policy_version 377099 (0.0012) -[2023-11-28 10:06:05,831][87424] Updated weights for policy 0, policy_version 377109 (0.0012) -[2023-11-28 10:06:06,218][87424] Updated weights for policy 0, policy_version 377119 (0.0012) -[2023-11-28 10:06:07,410][87426] Updated weights for policy 1, policy_version 376810 (0.0010) -[2023-11-28 10:06:07,793][87426] Updated weights for policy 1, policy_version 376820 (0.0007) -[2023-11-28 10:06:08,177][87426] Updated weights for policy 1, policy_version 376830 (0.0007) -[2023-11-28 10:06:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193011712. Throughput: 0: 2717.4, 1: 2712.1. Samples: 193029464. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:08,445][86177] Avg episode reward: [(0, '-582.810'), (1, '-501.530')] -[2023-11-28 10:06:08,675][87424] Updated weights for policy 0, policy_version 377129 (0.0008) -[2023-11-28 10:06:09,059][87424] Updated weights for policy 0, policy_version 377139 (0.0008) -[2023-11-28 10:06:09,442][87424] Updated weights for policy 0, policy_version 377149 (0.0008) -[2023-11-28 10:06:10,245][87426] Updated weights for policy 1, policy_version 376840 (0.0011) -[2023-11-28 10:06:10,627][87426] Updated weights for policy 1, policy_version 376850 (0.0012) -[2023-11-28 10:06:11,001][87426] Updated weights for policy 1, policy_version 376860 (0.0012) -[2023-11-28 10:06:11,410][87424] Updated weights for policy 0, policy_version 377159 (0.0008) -[2023-11-28 10:06:11,791][87424] Updated weights for policy 0, policy_version 377169 (0.0011) -[2023-11-28 10:06:12,173][87424] Updated weights for policy 0, policy_version 377179 (0.0010) -[2023-11-28 10:06:13,178][87426] Updated weights for policy 1, policy_version 376870 (0.0009) -[2023-11-28 10:06:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 193036288. Throughput: 0: 2691.7, 1: 2723.8. Samples: 193053712. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:13,445][86177] Avg episode reward: [(0, '-588.410'), (1, '-501.180')] -[2023-11-28 10:06:13,567][87426] Updated weights for policy 1, policy_version 376880 (0.0007) -[2023-11-28 10:06:13,940][87426] Updated weights for policy 1, policy_version 376890 (0.0010) -[2023-11-28 10:06:14,520][87424] Updated weights for policy 0, policy_version 377189 (0.0012) -[2023-11-28 10:06:14,906][87424] Updated weights for policy 0, policy_version 377199 (0.0011) -[2023-11-28 10:06:15,285][87424] Updated weights for policy 0, policy_version 377209 (0.0011) -[2023-11-28 10:06:15,915][87426] Updated weights for policy 1, policy_version 376900 (0.0010) -[2023-11-28 10:06:16,301][87426] Updated weights for policy 1, policy_version 376910 (0.0009) -[2023-11-28 10:06:16,686][87426] Updated weights for policy 1, policy_version 376920 (0.0007) -[2023-11-28 10:06:17,685][87424] Updated weights for policy 0, policy_version 377219 (0.0011) -[2023-11-28 10:06:18,070][87424] Updated weights for policy 0, policy_version 377229 (0.0007) -[2023-11-28 10:06:18,404][87426] Updated weights for policy 1, policy_version 376930 (0.0009) -[2023-11-28 10:06:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193060864. Throughput: 0: 2669.4, 1: 2716.6. Samples: 193077084. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:18,445][86177] Avg episode reward: [(0, '-549.010'), (1, '-502.530')] -[2023-11-28 10:06:18,448][87424] Updated weights for policy 0, policy_version 377239 (0.0008) -[2023-11-28 10:06:18,780][87426] Updated weights for policy 1, policy_version 376940 (0.0009) -[2023-11-28 10:06:18,790][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000377248_96575488.pth... -[2023-11-28 10:06:18,820][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000374720_95928320.pth -[2023-11-28 10:06:19,157][87426] Updated weights for policy 1, policy_version 376950 (0.0012) -[2023-11-28 10:06:19,531][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000376960_96501760.pth... -[2023-11-28 10:06:19,533][87426] Updated weights for policy 1, policy_version 376960 (0.0012) -[2023-11-28 10:06:19,561][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000374432_95854592.pth -[2023-11-28 10:06:20,507][87424] Updated weights for policy 0, policy_version 377249 (0.0012) -[2023-11-28 10:06:20,887][87424] Updated weights for policy 0, policy_version 377259 (0.0012) -[2023-11-28 10:06:21,272][87424] Updated weights for policy 0, policy_version 377269 (0.0012) -[2023-11-28 10:06:21,652][87424] Updated weights for policy 0, policy_version 377279 (0.0012) -[2023-11-28 10:06:21,993][87426] Updated weights for policy 1, policy_version 376970 (0.0011) -[2023-11-28 10:06:22,371][87426] Updated weights for policy 1, policy_version 376980 (0.0011) -[2023-11-28 10:06:22,749][87426] Updated weights for policy 1, policy_version 376990 (0.0007) -[2023-11-28 10:06:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 193093632. Throughput: 0: 2639.6, 1: 2724.1. Samples: 193108688. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:23,445][86177] Avg episode reward: [(0, '-551.290'), (1, '-502.370')] -[2023-11-28 10:06:23,692][87424] Updated weights for policy 0, policy_version 377289 (0.0009) -[2023-11-28 10:06:24,073][87424] Updated weights for policy 0, policy_version 377299 (0.0007) -[2023-11-28 10:06:24,450][87424] Updated weights for policy 0, policy_version 377309 (0.0009) -[2023-11-28 10:06:25,105][87426] Updated weights for policy 1, policy_version 377000 (0.0012) -[2023-11-28 10:06:25,481][87426] Updated weights for policy 1, policy_version 377010 (0.0012) -[2023-11-28 10:06:25,866][87426] Updated weights for policy 1, policy_version 377020 (0.0012) -[2023-11-28 10:06:26,785][87424] Updated weights for policy 0, policy_version 377319 (0.0012) -[2023-11-28 10:06:27,169][87424] Updated weights for policy 0, policy_version 377329 (0.0012) -[2023-11-28 10:06:27,555][87424] Updated weights for policy 0, policy_version 377339 (0.0011) -[2023-11-28 10:06:27,645][87426] Updated weights for policy 1, policy_version 377030 (0.0010) -[2023-11-28 10:06:28,016][87426] Updated weights for policy 1, policy_version 377040 (0.0009) -[2023-11-28 10:06:28,403][87426] Updated weights for policy 1, policy_version 377050 (0.0007) -[2023-11-28 10:06:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 193118208. Throughput: 0: 2652.1, 1: 2725.7. Samples: 193134224. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:28,445][86177] Avg episode reward: [(0, '-533.800'), (1, '-500.580')] -[2023-11-28 10:06:29,445][87424] Updated weights for policy 0, policy_version 377349 (0.0010) -[2023-11-28 10:06:29,826][87424] Updated weights for policy 0, policy_version 377359 (0.0010) -[2023-11-28 10:06:30,206][87424] Updated weights for policy 0, policy_version 377369 (0.0011) -[2023-11-28 10:06:30,739][87426] Updated weights for policy 1, policy_version 377060 (0.0010) -[2023-11-28 10:06:31,121][87426] Updated weights for policy 1, policy_version 377070 (0.0012) -[2023-11-28 10:06:31,492][87426] Updated weights for policy 1, policy_version 377080 (0.0012) -[2023-11-28 10:06:31,981][87424] Updated weights for policy 0, policy_version 377379 (0.0010) -[2023-11-28 10:06:32,355][87424] Updated weights for policy 0, policy_version 377389 (0.0012) -[2023-11-28 10:06:32,731][87424] Updated weights for policy 0, policy_version 377399 (0.0012) -[2023-11-28 10:06:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 193150976. Throughput: 0: 2670.5, 1: 2718.9. Samples: 193158928. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:33,445][86177] Avg episode reward: [(0, '-547.890'), (1, '-497.520')] -[2023-11-28 10:06:33,852][87426] Updated weights for policy 1, policy_version 377090 (0.0011) -[2023-11-28 10:06:34,240][87426] Updated weights for policy 1, policy_version 377100 (0.0010) -[2023-11-28 10:06:34,619][87426] Updated weights for policy 1, policy_version 377110 (0.0010) -[2023-11-28 10:06:34,857][87424] Updated weights for policy 0, policy_version 377409 (0.0012) -[2023-11-28 10:06:35,006][87426] Updated weights for policy 1, policy_version 377120 (0.0010) -[2023-11-28 10:06:35,235][87424] Updated weights for policy 0, policy_version 377419 (0.0011) -[2023-11-28 10:06:35,620][87424] Updated weights for policy 0, policy_version 377429 (0.0009) -[2023-11-28 10:06:36,005][87424] Updated weights for policy 0, policy_version 377439 (0.0007) -[2023-11-28 10:06:37,426][87426] Updated weights for policy 1, policy_version 377130 (0.0010) -[2023-11-28 10:06:37,809][87426] Updated weights for policy 1, policy_version 377140 (0.0008) -[2023-11-28 10:06:38,202][87426] Updated weights for policy 1, policy_version 377150 (0.0007) -[2023-11-28 10:06:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 193175552. Throughput: 0: 2676.7, 1: 2705.2. Samples: 193191296. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:38,445][86177] Avg episode reward: [(0, '-562.480'), (1, '-501.840')] -[2023-11-28 10:06:38,448][87424] Updated weights for policy 0, policy_version 377449 (0.0009) -[2023-11-28 10:06:38,833][87424] Updated weights for policy 0, policy_version 377459 (0.0008) -[2023-11-28 10:06:39,212][87424] Updated weights for policy 0, policy_version 377469 (0.0010) -[2023-11-28 10:06:40,382][87426] Updated weights for policy 1, policy_version 377160 (0.0011) -[2023-11-28 10:06:40,757][87426] Updated weights for policy 1, policy_version 377170 (0.0011) -[2023-11-28 10:06:41,134][87426] Updated weights for policy 1, policy_version 377180 (0.0010) -[2023-11-28 10:06:41,288][87424] Updated weights for policy 0, policy_version 377479 (0.0011) -[2023-11-28 10:06:41,684][87424] Updated weights for policy 0, policy_version 377489 (0.0009) -[2023-11-28 10:06:42,057][87424] Updated weights for policy 0, policy_version 377499 (0.0012) -[2023-11-28 10:06:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 193200128. Throughput: 0: 2675.0, 1: 2693.3. Samples: 193215104. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:43,445][86177] Avg episode reward: [(0, '-576.040'), (1, '-499.560')] -[2023-11-28 10:06:43,571][87426] Updated weights for policy 1, policy_version 377190 (0.0010) -[2023-11-28 10:06:43,949][87426] Updated weights for policy 1, policy_version 377200 (0.0012) -[2023-11-28 10:06:44,320][87426] Updated weights for policy 1, policy_version 377210 (0.0011) -[2023-11-28 10:06:44,441][87424] Updated weights for policy 0, policy_version 377509 (0.0010) -[2023-11-28 10:06:44,827][87424] Updated weights for policy 0, policy_version 377519 (0.0007) -[2023-11-28 10:06:45,207][87424] Updated weights for policy 0, policy_version 377529 (0.0008) -[2023-11-28 10:06:46,716][87426] Updated weights for policy 1, policy_version 377220 (0.0009) -[2023-11-28 10:06:47,093][87426] Updated weights for policy 1, policy_version 377230 (0.0012) -[2023-11-28 10:06:47,471][87426] Updated weights for policy 1, policy_version 377240 (0.0012) -[2023-11-28 10:06:47,758][87424] Updated weights for policy 0, policy_version 377539 (0.0010) -[2023-11-28 10:06:48,148][87424] Updated weights for policy 0, policy_version 377549 (0.0011) -[2023-11-28 10:06:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193224704. Throughput: 0: 2690.3, 1: 2706.5. Samples: 193238924. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:48,445][86177] Avg episode reward: [(0, '-572.990'), (1, '-503.130')] -[2023-11-28 10:06:48,521][87424] Updated weights for policy 0, policy_version 377559 (0.0012) -[2023-11-28 10:06:49,727][87426] Updated weights for policy 1, policy_version 377250 (0.0011) -[2023-11-28 10:06:50,118][87426] Updated weights for policy 1, policy_version 377260 (0.0012) -[2023-11-28 10:06:50,504][87426] Updated weights for policy 1, policy_version 377270 (0.0011) -[2023-11-28 10:06:50,685][87424] Updated weights for policy 0, policy_version 377569 (0.0011) -[2023-11-28 10:06:50,878][87426] Updated weights for policy 1, policy_version 377280 (0.0011) -[2023-11-28 10:06:51,066][87424] Updated weights for policy 0, policy_version 377579 (0.0012) -[2023-11-28 10:06:51,444][87424] Updated weights for policy 0, policy_version 377589 (0.0010) -[2023-11-28 10:06:51,823][87424] Updated weights for policy 0, policy_version 377599 (0.0013) -[2023-11-28 10:06:53,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193249280. Throughput: 0: 2690.0, 1: 2675.4. Samples: 193270908. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:53,445][86177] Avg episode reward: [(0, '-608.570'), (1, '-508.470')] -[2023-11-28 10:06:53,532][87426] Updated weights for policy 1, policy_version 377290 (0.0011) -[2023-11-28 10:06:53,902][87426] Updated weights for policy 1, policy_version 377300 (0.0011) -[2023-11-28 10:06:54,281][87426] Updated weights for policy 1, policy_version 377310 (0.0010) -[2023-11-28 10:06:54,384][87424] Updated weights for policy 0, policy_version 377609 (0.0011) -[2023-11-28 10:06:54,767][87424] Updated weights for policy 0, policy_version 377619 (0.0011) -[2023-11-28 10:06:55,152][87424] Updated weights for policy 0, policy_version 377629 (0.0012) -[2023-11-28 10:06:56,169][87426] Updated weights for policy 1, policy_version 377320 (0.0012) -[2023-11-28 10:06:56,552][87426] Updated weights for policy 1, policy_version 377330 (0.0012) -[2023-11-28 10:06:56,925][87426] Updated weights for policy 1, policy_version 377340 (0.0011) -[2023-11-28 10:06:57,205][87424] Updated weights for policy 0, policy_version 377639 (0.0012) -[2023-11-28 10:06:57,578][87424] Updated weights for policy 0, policy_version 377649 (0.0012) -[2023-11-28 10:06:57,967][87424] Updated weights for policy 0, policy_version 377659 (0.0012) -[2023-11-28 10:06:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 193282048. Throughput: 0: 2682.3, 1: 2703.3. Samples: 193296064. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:06:58,445][86177] Avg episode reward: [(0, '-582.660'), (1, '-508.000')] -[2023-11-28 10:06:58,551][87426] Updated weights for policy 1, policy_version 377350 (0.0012) -[2023-11-28 10:06:58,934][87426] Updated weights for policy 1, policy_version 377360 (0.0011) -[2023-11-28 10:06:59,309][87426] Updated weights for policy 1, policy_version 377370 (0.0012) -[2023-11-28 10:07:00,095][87424] Updated weights for policy 0, policy_version 377669 (0.0012) -[2023-11-28 10:07:00,485][87424] Updated weights for policy 0, policy_version 377679 (0.0012) -[2023-11-28 10:07:00,867][87424] Updated weights for policy 0, policy_version 377689 (0.0012) -[2023-11-28 10:07:01,523][87426] Updated weights for policy 1, policy_version 377380 (0.0011) -[2023-11-28 10:07:01,900][87426] Updated weights for policy 1, policy_version 377390 (0.0011) -[2023-11-28 10:07:02,276][87426] Updated weights for policy 1, policy_version 377400 (0.0016) -[2023-11-28 10:07:02,995][87424] Updated weights for policy 0, policy_version 377699 (0.0010) -[2023-11-28 10:07:03,376][87424] Updated weights for policy 0, policy_version 377709 (0.0011) -[2023-11-28 10:07:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193306624. Throughput: 0: 2715.6, 1: 2712.5. Samples: 193321348. Policy #0 lag: (min: 31.0, avg: 41.2, max: 63.0) -[2023-11-28 10:07:03,445][86177] Avg episode reward: [(0, '-605.500'), (1, '-508.410')] -[2023-11-28 10:07:03,754][87424] Updated weights for policy 0, policy_version 377719 (0.0012) -[2023-11-28 10:07:04,573][87426] Updated weights for policy 1, policy_version 377410 (0.0011) -[2023-11-28 10:07:04,955][87426] Updated weights for policy 1, policy_version 377420 (0.0011) -[2023-11-28 10:07:05,332][87426] Updated weights for policy 1, policy_version 377430 (0.0010) -[2023-11-28 10:07:05,694][87424] Updated weights for policy 0, policy_version 377729 (0.0012) -[2023-11-28 10:07:05,705][87426] Updated weights for policy 1, policy_version 377440 (0.0008) -[2023-11-28 10:07:06,076][87424] Updated weights for policy 0, policy_version 377739 (0.0009) -[2023-11-28 10:07:06,450][87424] Updated weights for policy 0, policy_version 377749 (0.0008) -[2023-11-28 10:07:06,837][87424] Updated weights for policy 0, policy_version 377759 (0.0009) -[2023-11-28 10:07:07,596][87426] Updated weights for policy 1, policy_version 377450 (0.0010) -[2023-11-28 10:07:07,969][87426] Updated weights for policy 1, policy_version 377460 (0.0007) -[2023-11-28 10:07:08,353][87426] Updated weights for policy 1, policy_version 377470 (0.0007) -[2023-11-28 10:07:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 193339392. Throughput: 0: 2729.2, 1: 2712.0. Samples: 193353540. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:08,445][86177] Avg episode reward: [(0, '-599.960'), (1, '-506.560')] -[2023-11-28 10:07:08,950][87424] Updated weights for policy 0, policy_version 377769 (0.0011) -[2023-11-28 10:07:09,331][87424] Updated weights for policy 0, policy_version 377779 (0.0011) -[2023-11-28 10:07:09,714][87424] Updated weights for policy 0, policy_version 377789 (0.0012) -[2023-11-28 10:07:10,693][87426] Updated weights for policy 1, policy_version 377480 (0.0010) -[2023-11-28 10:07:11,065][87426] Updated weights for policy 1, policy_version 377490 (0.0011) -[2023-11-28 10:07:11,443][87426] Updated weights for policy 1, policy_version 377500 (0.0010) -[2023-11-28 10:07:12,422][87424] Updated weights for policy 0, policy_version 377799 (0.0010) -[2023-11-28 10:07:12,810][87424] Updated weights for policy 0, policy_version 377809 (0.0008) -[2023-11-28 10:07:13,189][87424] Updated weights for policy 0, policy_version 377819 (0.0010) -[2023-11-28 10:07:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 193363968. Throughput: 0: 2721.1, 1: 2665.4. Samples: 193376616. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:13,445][86177] Avg episode reward: [(0, '-605.340'), (1, '-503.240')] -[2023-11-28 10:07:14,059][87426] Updated weights for policy 1, policy_version 377510 (0.0010) -[2023-11-28 10:07:14,440][87426] Updated weights for policy 1, policy_version 377520 (0.0008) -[2023-11-28 10:07:14,813][87426] Updated weights for policy 1, policy_version 377530 (0.0011) -[2023-11-28 10:07:15,017][87424] Updated weights for policy 0, policy_version 377829 (0.0010) -[2023-11-28 10:07:15,399][87424] Updated weights for policy 0, policy_version 377839 (0.0012) -[2023-11-28 10:07:15,783][87424] Updated weights for policy 0, policy_version 377849 (0.0013) -[2023-11-28 10:07:17,282][87426] Updated weights for policy 1, policy_version 377540 (0.0010) -[2023-11-28 10:07:17,530][87424] Updated weights for policy 0, policy_version 377859 (0.0012) -[2023-11-28 10:07:17,660][87426] Updated weights for policy 1, policy_version 377550 (0.0011) -[2023-11-28 10:07:17,900][87424] Updated weights for policy 0, policy_version 377869 (0.0012) -[2023-11-28 10:07:18,035][87426] Updated weights for policy 1, policy_version 377560 (0.0009) -[2023-11-28 10:07:18,281][87424] Updated weights for policy 0, policy_version 377879 (0.0011) -[2023-11-28 10:07:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 193388544. Throughput: 0: 2708.8, 1: 2665.9. Samples: 193400792. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:18,446][86177] Avg episode reward: [(0, '-587.740'), (1, '-501.370')] -[2023-11-28 10:07:20,044][87426] Updated weights for policy 1, policy_version 377570 (0.0011) -[2023-11-28 10:07:20,410][87426] Updated weights for policy 1, policy_version 377580 (0.0012) -[2023-11-28 10:07:20,766][87424] Updated weights for policy 0, policy_version 377889 (0.0008) -[2023-11-28 10:07:20,788][87426] Updated weights for policy 1, policy_version 377590 (0.0012) -[2023-11-28 10:07:21,137][87424] Updated weights for policy 0, policy_version 377899 (0.0011) -[2023-11-28 10:07:21,167][87426] Updated weights for policy 1, policy_version 377600 (0.0011) -[2023-11-28 10:07:21,527][87424] Updated weights for policy 0, policy_version 377909 (0.0012) -[2023-11-28 10:07:21,902][87424] Updated weights for policy 0, policy_version 377919 (0.0012) -[2023-11-28 10:07:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193413120. Throughput: 0: 2677.2, 1: 2653.4. Samples: 193431172. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:23,445][86177] Avg episode reward: [(0, '-573.150'), (1, '-500.560')] -[2023-11-28 10:07:23,598][87426] Updated weights for policy 1, policy_version 377610 (0.0012) -[2023-11-28 10:07:23,973][87426] Updated weights for policy 1, policy_version 377620 (0.0012) -[2023-11-28 10:07:24,354][87426] Updated weights for policy 1, policy_version 377630 (0.0009) -[2023-11-28 10:07:24,456][87424] Updated weights for policy 0, policy_version 377929 (0.0009) -[2023-11-28 10:07:24,832][87424] Updated weights for policy 0, policy_version 377939 (0.0008) -[2023-11-28 10:07:25,216][87424] Updated weights for policy 0, policy_version 377949 (0.0009) -[2023-11-28 10:07:26,544][87426] Updated weights for policy 1, policy_version 377640 (0.0008) -[2023-11-28 10:07:26,928][87426] Updated weights for policy 1, policy_version 377650 (0.0008) -[2023-11-28 10:07:27,309][87426] Updated weights for policy 1, policy_version 377660 (0.0007) -[2023-11-28 10:07:27,623][87424] Updated weights for policy 0, policy_version 377959 (0.0011) -[2023-11-28 10:07:27,995][87424] Updated weights for policy 0, policy_version 377969 (0.0008) -[2023-11-28 10:07:28,375][87424] Updated weights for policy 0, policy_version 377979 (0.0010) -[2023-11-28 10:07:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193437696. Throughput: 0: 2679.0, 1: 2680.0. Samples: 193456260. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:28,446][86177] Avg episode reward: [(0, '-576.780'), (1, '-505.930')] -[2023-11-28 10:07:29,074][87426] Updated weights for policy 1, policy_version 377670 (0.0008) -[2023-11-28 10:07:29,454][87426] Updated weights for policy 1, policy_version 377680 (0.0007) -[2023-11-28 10:07:29,837][87426] Updated weights for policy 1, policy_version 377690 (0.0008) -[2023-11-28 10:07:30,506][87424] Updated weights for policy 0, policy_version 377989 (0.0010) -[2023-11-28 10:07:30,894][87424] Updated weights for policy 0, policy_version 377999 (0.0009) -[2023-11-28 10:07:31,275][87424] Updated weights for policy 0, policy_version 378009 (0.0009) -[2023-11-28 10:07:32,178][87426] Updated weights for policy 1, policy_version 377700 (0.0011) -[2023-11-28 10:07:32,553][87426] Updated weights for policy 1, policy_version 377710 (0.0008) -[2023-11-28 10:07:32,929][87426] Updated weights for policy 1, policy_version 377720 (0.0010) -[2023-11-28 10:07:33,345][87424] Updated weights for policy 0, policy_version 378019 (0.0009) -[2023-11-28 10:07:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 193470464. Throughput: 0: 2692.1, 1: 2689.1. Samples: 193481076. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:33,445][86177] Avg episode reward: [(0, '-579.970'), (1, '-506.710')] -[2023-11-28 10:07:33,725][87424] Updated weights for policy 0, policy_version 378029 (0.0008) -[2023-11-28 10:07:34,118][87424] Updated weights for policy 0, policy_version 378039 (0.0012) -[2023-11-28 10:07:34,837][87426] Updated weights for policy 1, policy_version 377730 (0.0012) -[2023-11-28 10:07:35,213][87426] Updated weights for policy 1, policy_version 377740 (0.0009) -[2023-11-28 10:07:35,596][87426] Updated weights for policy 1, policy_version 377750 (0.0008) -[2023-11-28 10:07:35,979][87426] Updated weights for policy 1, policy_version 377760 (0.0007) -[2023-11-28 10:07:36,015][87424] Updated weights for policy 0, policy_version 378049 (0.0010) -[2023-11-28 10:07:36,398][87424] Updated weights for policy 0, policy_version 378059 (0.0011) -[2023-11-28 10:07:36,775][87424] Updated weights for policy 0, policy_version 378069 (0.0012) -[2023-11-28 10:07:37,159][87424] Updated weights for policy 0, policy_version 378079 (0.0012) -[2023-11-28 10:07:37,974][87426] Updated weights for policy 1, policy_version 377770 (0.0012) -[2023-11-28 10:07:38,353][87426] Updated weights for policy 1, policy_version 377780 (0.0012) -[2023-11-28 10:07:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 193495040. Throughput: 0: 2703.6, 1: 2718.2. Samples: 193514892. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:38,445][86177] Avg episode reward: [(0, '-558.530'), (1, '-505.820')] -[2023-11-28 10:07:38,733][87426] Updated weights for policy 1, policy_version 377790 (0.0012) -[2023-11-28 10:07:39,132][87424] Updated weights for policy 0, policy_version 378089 (0.0012) -[2023-11-28 10:07:39,522][87424] Updated weights for policy 0, policy_version 378099 (0.0012) -[2023-11-28 10:07:39,891][87424] Updated weights for policy 0, policy_version 378109 (0.0012) -[2023-11-28 10:07:41,371][87426] Updated weights for policy 1, policy_version 377800 (0.0011) -[2023-11-28 10:07:41,758][87426] Updated weights for policy 1, policy_version 377810 (0.0011) -[2023-11-28 10:07:41,866][87424] Updated weights for policy 0, policy_version 378119 (0.0011) -[2023-11-28 10:07:42,128][87426] Updated weights for policy 1, policy_version 377820 (0.0011) -[2023-11-28 10:07:42,243][87424] Updated weights for policy 0, policy_version 378129 (0.0010) -[2023-11-28 10:07:42,629][87424] Updated weights for policy 0, policy_version 378139 (0.0012) -[2023-11-28 10:07:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 193527808. Throughput: 0: 2723.6, 1: 2665.0. Samples: 193538548. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:43,445][86177] Avg episode reward: [(0, '-553.450'), (1, '-503.450')] -[2023-11-28 10:07:44,250][87426] Updated weights for policy 1, policy_version 377830 (0.0011) -[2023-11-28 10:07:44,627][87426] Updated weights for policy 1, policy_version 377840 (0.0012) -[2023-11-28 10:07:44,777][87424] Updated weights for policy 0, policy_version 378149 (0.0009) -[2023-11-28 10:07:45,010][87426] Updated weights for policy 1, policy_version 377850 (0.0011) -[2023-11-28 10:07:45,157][87424] Updated weights for policy 0, policy_version 378159 (0.0009) -[2023-11-28 10:07:45,546][87424] Updated weights for policy 0, policy_version 378169 (0.0012) -[2023-11-28 10:07:47,580][87426] Updated weights for policy 1, policy_version 377860 (0.0011) -[2023-11-28 10:07:47,960][87426] Updated weights for policy 1, policy_version 377870 (0.0009) -[2023-11-28 10:07:48,011][87424] Updated weights for policy 0, policy_version 378179 (0.0011) -[2023-11-28 10:07:48,339][87426] Updated weights for policy 1, policy_version 377880 (0.0008) -[2023-11-28 10:07:48,397][87424] Updated weights for policy 0, policy_version 378189 (0.0011) -[2023-11-28 10:07:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193544192. Throughput: 0: 2722.5, 1: 2652.2. Samples: 193563208. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:48,445][86177] Avg episode reward: [(0, '-593.240'), (1, '-500.430')] -[2023-11-28 10:07:48,770][87424] Updated weights for policy 0, policy_version 378199 (0.0011) -[2023-11-28 10:07:50,615][87426] Updated weights for policy 1, policy_version 377890 (0.0008) -[2023-11-28 10:07:50,991][87426] Updated weights for policy 1, policy_version 377900 (0.0008) -[2023-11-28 10:07:51,325][87424] Updated weights for policy 0, policy_version 378209 (0.0012) -[2023-11-28 10:07:51,358][87426] Updated weights for policy 1, policy_version 377910 (0.0011) -[2023-11-28 10:07:51,705][87424] Updated weights for policy 0, policy_version 378219 (0.0012) -[2023-11-28 10:07:51,739][87426] Updated weights for policy 1, policy_version 377920 (0.0009) -[2023-11-28 10:07:52,086][87424] Updated weights for policy 0, policy_version 378229 (0.0012) -[2023-11-28 10:07:52,467][87424] Updated weights for policy 0, policy_version 378239 (0.0011) -[2023-11-28 10:07:53,452][86177] Fps is (10 sec: 4911.4, 60 sec: 5460.6, 300 sec: 5387.1). Total num frames: 193576960. Throughput: 0: 2704.4, 1: 2639.0. Samples: 193594036. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:53,453][86177] Avg episode reward: [(0, '-590.850'), (1, '-501.400')] -[2023-11-28 10:07:54,049][87426] Updated weights for policy 1, policy_version 377930 (0.0011) -[2023-11-28 10:07:54,421][87426] Updated weights for policy 1, policy_version 377940 (0.0012) -[2023-11-28 10:07:54,728][87424] Updated weights for policy 0, policy_version 378249 (0.0012) -[2023-11-28 10:07:54,800][87426] Updated weights for policy 1, policy_version 377950 (0.0012) -[2023-11-28 10:07:55,110][87424] Updated weights for policy 0, policy_version 378259 (0.0009) -[2023-11-28 10:07:55,489][87424] Updated weights for policy 0, policy_version 378269 (0.0009) -[2023-11-28 10:07:56,826][87426] Updated weights for policy 1, policy_version 377960 (0.0008) -[2023-11-28 10:07:57,210][87426] Updated weights for policy 1, policy_version 377970 (0.0010) -[2023-11-28 10:07:57,589][87426] Updated weights for policy 1, policy_version 377980 (0.0012) -[2023-11-28 10:07:57,728][87424] Updated weights for policy 0, policy_version 378279 (0.0008) -[2023-11-28 10:07:58,105][87424] Updated weights for policy 0, policy_version 378289 (0.0008) -[2023-11-28 10:07:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 193601536. Throughput: 0: 2703.5, 1: 2671.4. Samples: 193618484. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:07:58,445][86177] Avg episode reward: [(0, '-587.170'), (1, '-499.690')] -[2023-11-28 10:07:58,480][87424] Updated weights for policy 0, policy_version 378299 (0.0009) -[2023-11-28 10:07:59,905][87426] Updated weights for policy 1, policy_version 377990 (0.0010) -[2023-11-28 10:08:00,282][87426] Updated weights for policy 1, policy_version 378000 (0.0008) -[2023-11-28 10:08:00,579][87424] Updated weights for policy 0, policy_version 378309 (0.0011) -[2023-11-28 10:08:00,661][87426] Updated weights for policy 1, policy_version 378010 (0.0010) -[2023-11-28 10:08:00,961][87424] Updated weights for policy 0, policy_version 378319 (0.0011) -[2023-11-28 10:08:01,345][87424] Updated weights for policy 0, policy_version 378329 (0.0008) -[2023-11-28 10:08:02,522][87426] Updated weights for policy 1, policy_version 378020 (0.0012) -[2023-11-28 10:08:02,906][87426] Updated weights for policy 1, policy_version 378030 (0.0012) -[2023-11-28 10:08:03,275][87426] Updated weights for policy 1, policy_version 378040 (0.0010) -[2023-11-28 10:08:03,402][87424] Updated weights for policy 0, policy_version 378339 (0.0009) -[2023-11-28 10:08:03,445][86177] Fps is (10 sec: 4918.8, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193626112. Throughput: 0: 2700.8, 1: 2686.7. Samples: 193643232. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:08:03,445][86177] Avg episode reward: [(0, '-596.990'), (1, '-498.760')] -[2023-11-28 10:08:03,777][87424] Updated weights for policy 0, policy_version 378349 (0.0012) -[2023-11-28 10:08:04,163][87424] Updated weights for policy 0, policy_version 378359 (0.0012) -[2023-11-28 10:08:05,241][87426] Updated weights for policy 1, policy_version 378050 (0.0010) -[2023-11-28 10:08:05,615][87426] Updated weights for policy 1, policy_version 378060 (0.0007) -[2023-11-28 10:08:05,993][87426] Updated weights for policy 1, policy_version 378070 (0.0007) -[2023-11-28 10:08:06,376][87426] Updated weights for policy 1, policy_version 378080 (0.0008) -[2023-11-28 10:08:06,402][87424] Updated weights for policy 0, policy_version 378369 (0.0010) -[2023-11-28 10:08:06,780][87424] Updated weights for policy 0, policy_version 378379 (0.0011) -[2023-11-28 10:08:07,162][87424] Updated weights for policy 0, policy_version 378389 (0.0008) -[2023-11-28 10:08:07,551][87424] Updated weights for policy 0, policy_version 378399 (0.0007) -[2023-11-28 10:08:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 193658880. Throughput: 0: 2723.8, 1: 2718.6. Samples: 193676080. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:08:08,445][86177] Avg episode reward: [(0, '-581.010'), (1, '-496.070')] -[2023-11-28 10:08:08,715][87426] Updated weights for policy 1, policy_version 378090 (0.0012) -[2023-11-28 10:08:09,086][87426] Updated weights for policy 1, policy_version 378100 (0.0011) -[2023-11-28 10:08:09,466][87426] Updated weights for policy 1, policy_version 378110 (0.0010) -[2023-11-28 10:08:09,494][87424] Updated weights for policy 0, policy_version 378409 (0.0011) -[2023-11-28 10:08:09,875][87424] Updated weights for policy 0, policy_version 378419 (0.0012) -[2023-11-28 10:08:10,258][87424] Updated weights for policy 0, policy_version 378429 (0.0012) -[2023-11-28 10:08:11,902][87426] Updated weights for policy 1, policy_version 378120 (0.0011) -[2023-11-28 10:08:12,204][87424] Updated weights for policy 0, policy_version 378439 (0.0010) -[2023-11-28 10:08:12,283][87426] Updated weights for policy 1, policy_version 378130 (0.0012) -[2023-11-28 10:08:12,587][87424] Updated weights for policy 0, policy_version 378449 (0.0011) -[2023-11-28 10:08:12,661][87426] Updated weights for policy 1, policy_version 378140 (0.0012) -[2023-11-28 10:08:12,967][87424] Updated weights for policy 0, policy_version 378459 (0.0012) -[2023-11-28 10:08:13,444][86177] Fps is (10 sec: 6553.9, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 193691648. Throughput: 0: 2737.3, 1: 2672.2. Samples: 193699684. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:08:13,445][86177] Avg episode reward: [(0, '-543.570'), (1, '-494.070')] -[2023-11-28 10:08:14,885][87426] Updated weights for policy 1, policy_version 378150 (0.0012) -[2023-11-28 10:08:15,260][87426] Updated weights for policy 1, policy_version 378160 (0.0011) -[2023-11-28 10:08:15,491][87424] Updated weights for policy 0, policy_version 378469 (0.0011) -[2023-11-28 10:08:15,645][87426] Updated weights for policy 1, policy_version 378170 (0.0011) -[2023-11-28 10:08:15,871][87424] Updated weights for policy 0, policy_version 378479 (0.0011) -[2023-11-28 10:08:16,253][87424] Updated weights for policy 0, policy_version 378489 (0.0009) -[2023-11-28 10:08:17,422][87426] Updated weights for policy 1, policy_version 378180 (0.0011) -[2023-11-28 10:08:17,794][87426] Updated weights for policy 1, policy_version 378190 (0.0012) -[2023-11-28 10:08:18,167][87424] Updated weights for policy 0, policy_version 378499 (0.0011) -[2023-11-28 10:08:18,183][87426] Updated weights for policy 1, policy_version 378200 (0.0012) -[2023-11-28 10:08:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193708032. Throughput: 0: 2722.1, 1: 2673.7. Samples: 193723888. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:08:18,445][86177] Avg episode reward: [(0, '-544.060'), (1, '-497.390')] -[2023-11-28 10:08:18,482][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000378208_96821248.pth... -[2023-11-28 10:08:18,530][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000375680_96174080.pth -[2023-11-28 10:08:18,548][87424] Updated weights for policy 0, policy_version 378509 (0.0009) -[2023-11-28 10:08:18,930][87424] Updated weights for policy 0, policy_version 378519 (0.0008) -[2023-11-28 10:08:19,271][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000378528_96903168.pth... -[2023-11-28 10:08:19,318][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000375968_96247808.pth -[2023-11-28 10:08:20,190][87426] Updated weights for policy 1, policy_version 378210 (0.0012) -[2023-11-28 10:08:20,570][87426] Updated weights for policy 1, policy_version 378220 (0.0012) -[2023-11-28 10:08:20,938][87424] Updated weights for policy 0, policy_version 378529 (0.0012) -[2023-11-28 10:08:20,953][87426] Updated weights for policy 1, policy_version 378230 (0.0011) -[2023-11-28 10:08:21,322][87424] Updated weights for policy 0, policy_version 378539 (0.0011) -[2023-11-28 10:08:21,330][87426] Updated weights for policy 1, policy_version 378240 (0.0012) -[2023-11-28 10:08:21,699][87424] Updated weights for policy 0, policy_version 378549 (0.0011) -[2023-11-28 10:08:22,082][87424] Updated weights for policy 0, policy_version 378559 (0.0011) -[2023-11-28 10:08:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 193740800. Throughput: 0: 2727.5, 1: 2661.3. Samples: 193757384. Policy #0 lag: (min: 1.0, avg: 24.1, max: 39.0) -[2023-11-28 10:08:23,445][86177] Avg episode reward: [(0, '-530.500'), (1, '-503.600')] -[2023-11-28 10:08:23,832][87426] Updated weights for policy 1, policy_version 378250 (0.0012) -[2023-11-28 10:08:24,216][87426] Updated weights for policy 1, policy_version 378260 (0.0012) -[2023-11-28 10:08:24,397][87424] Updated weights for policy 0, policy_version 378569 (0.0011) -[2023-11-28 10:08:24,600][87426] Updated weights for policy 1, policy_version 378270 (0.0012) -[2023-11-28 10:08:24,776][87424] Updated weights for policy 0, policy_version 378579 (0.0012) -[2023-11-28 10:08:25,164][87424] Updated weights for policy 0, policy_version 378589 (0.0011) -[2023-11-28 10:08:26,298][87426] Updated weights for policy 1, policy_version 378280 (0.0012) -[2023-11-28 10:08:26,676][87426] Updated weights for policy 1, policy_version 378290 (0.0012) -[2023-11-28 10:08:27,051][87426] Updated weights for policy 1, policy_version 378300 (0.0011) -[2023-11-28 10:08:27,167][87424] Updated weights for policy 0, policy_version 378599 (0.0011) -[2023-11-28 10:08:27,550][87424] Updated weights for policy 0, policy_version 378609 (0.0012) -[2023-11-28 10:08:27,944][87424] Updated weights for policy 0, policy_version 378619 (0.0011) -[2023-11-28 10:08:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5415.1). Total num frames: 193773568. Throughput: 0: 2722.0, 1: 2705.0. Samples: 193782764. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:08:28,445][86177] Avg episode reward: [(0, '-530.330'), (1, '-503.180')] -[2023-11-28 10:08:29,635][87426] Updated weights for policy 1, policy_version 378310 (0.0010) -[2023-11-28 10:08:30,024][87426] Updated weights for policy 1, policy_version 378320 (0.0009) -[2023-11-28 10:08:30,295][87424] Updated weights for policy 0, policy_version 378629 (0.0010) -[2023-11-28 10:08:30,410][87426] Updated weights for policy 1, policy_version 378330 (0.0011) -[2023-11-28 10:08:30,676][87424] Updated weights for policy 0, policy_version 378639 (0.0011) -[2023-11-28 10:08:31,057][87424] Updated weights for policy 0, policy_version 378649 (0.0012) -[2023-11-28 10:08:32,941][87426] Updated weights for policy 1, policy_version 378340 (0.0009) -[2023-11-28 10:08:33,300][87424] Updated weights for policy 0, policy_version 378659 (0.0011) -[2023-11-28 10:08:33,309][87426] Updated weights for policy 1, policy_version 378350 (0.0012) -[2023-11-28 10:08:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193789952. Throughput: 0: 2694.4, 1: 2704.8. Samples: 193806172. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:08:33,445][86177] Avg episode reward: [(0, '-541.470'), (1, '-503.960')] -[2023-11-28 10:08:33,687][87424] Updated weights for policy 0, policy_version 378669 (0.0010) -[2023-11-28 10:08:33,691][87426] Updated weights for policy 1, policy_version 378360 (0.0011) -[2023-11-28 10:08:34,067][87424] Updated weights for policy 0, policy_version 378679 (0.0012) -[2023-11-28 10:08:35,800][87426] Updated weights for policy 1, policy_version 378370 (0.0012) -[2023-11-28 10:08:36,181][87426] Updated weights for policy 1, policy_version 378380 (0.0012) -[2023-11-28 10:08:36,558][87426] Updated weights for policy 1, policy_version 378390 (0.0012) -[2023-11-28 10:08:36,566][87424] Updated weights for policy 0, policy_version 378689 (0.0012) -[2023-11-28 10:08:36,935][87426] Updated weights for policy 1, policy_version 378400 (0.0012) -[2023-11-28 10:08:36,942][87424] Updated weights for policy 0, policy_version 378699 (0.0011) -[2023-11-28 10:08:37,327][87424] Updated weights for policy 0, policy_version 378709 (0.0012) -[2023-11-28 10:08:37,697][87424] Updated weights for policy 0, policy_version 378719 (0.0012) -[2023-11-28 10:08:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5415.1). Total num frames: 193822720. Throughput: 0: 2684.8, 1: 2741.4. Samples: 193838172. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:08:38,445][86177] Avg episode reward: [(0, '-546.390'), (1, '-499.630')] -[2023-11-28 10:08:38,631][87426] Updated weights for policy 1, policy_version 378410 (0.0009) -[2023-11-28 10:08:39,015][87426] Updated weights for policy 1, policy_version 378420 (0.0012) -[2023-11-28 10:08:39,399][87426] Updated weights for policy 1, policy_version 378430 (0.0012) -[2023-11-28 10:08:39,883][87424] Updated weights for policy 0, policy_version 378729 (0.0012) -[2023-11-28 10:08:40,266][87424] Updated weights for policy 0, policy_version 378739 (0.0012) -[2023-11-28 10:08:40,636][87424] Updated weights for policy 0, policy_version 378749 (0.0011) -[2023-11-28 10:08:41,822][87426] Updated weights for policy 1, policy_version 378440 (0.0011) -[2023-11-28 10:08:42,202][87426] Updated weights for policy 1, policy_version 378450 (0.0009) -[2023-11-28 10:08:42,576][87426] Updated weights for policy 1, policy_version 378460 (0.0009) -[2023-11-28 10:08:43,082][87424] Updated weights for policy 0, policy_version 378759 (0.0011) -[2023-11-28 10:08:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 193847296. Throughput: 0: 2699.6, 1: 2719.7. Samples: 193862352. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:08:43,445][86177] Avg episode reward: [(0, '-549.660'), (1, '-498.940')] -[2023-11-28 10:08:43,467][87424] Updated weights for policy 0, policy_version 378769 (0.0008) -[2023-11-28 10:08:43,849][87424] Updated weights for policy 0, policy_version 378779 (0.0010) -[2023-11-28 10:08:44,649][87426] Updated weights for policy 1, policy_version 378470 (0.0009) -[2023-11-28 10:08:45,029][87426] Updated weights for policy 1, policy_version 378480 (0.0008) -[2023-11-28 10:08:45,413][87426] Updated weights for policy 1, policy_version 378490 (0.0008) -[2023-11-28 10:08:46,129][87424] Updated weights for policy 0, policy_version 378789 (0.0008) -[2023-11-28 10:08:46,508][87424] Updated weights for policy 0, policy_version 378799 (0.0007) -[2023-11-28 10:08:46,896][87424] Updated weights for policy 0, policy_version 378809 (0.0012) -[2023-11-28 10:08:47,861][87426] Updated weights for policy 1, policy_version 378500 (0.0009) -[2023-11-28 10:08:48,245][87426] Updated weights for policy 1, policy_version 378510 (0.0011) -[2023-11-28 10:08:48,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 193871872. Throughput: 0: 2679.8, 1: 2709.1. Samples: 193885732. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:08:48,446][86177] Avg episode reward: [(0, '-545.580'), (1, '-497.750')] -[2023-11-28 10:08:48,623][87426] Updated weights for policy 1, policy_version 378520 (0.0012) -[2023-11-28 10:08:48,796][87424] Updated weights for policy 0, policy_version 378819 (0.0012) -[2023-11-28 10:08:49,169][87424] Updated weights for policy 0, policy_version 378829 (0.0011) -[2023-11-28 10:08:49,555][87424] Updated weights for policy 0, policy_version 378839 (0.0011) -[2023-11-28 10:08:51,055][87426] Updated weights for policy 1, policy_version 378530 (0.0010) -[2023-11-28 10:08:51,434][87426] Updated weights for policy 1, policy_version 378540 (0.0012) -[2023-11-28 10:08:51,810][87426] Updated weights for policy 1, policy_version 378550 (0.0012) -[2023-11-28 10:08:51,942][87424] Updated weights for policy 0, policy_version 378849 (0.0011) -[2023-11-28 10:08:52,192][87426] Updated weights for policy 1, policy_version 378560 (0.0009) -[2023-11-28 10:08:52,321][87424] Updated weights for policy 0, policy_version 378859 (0.0010) -[2023-11-28 10:08:52,700][87424] Updated weights for policy 0, policy_version 378869 (0.0011) -[2023-11-28 10:08:53,081][87424] Updated weights for policy 0, policy_version 378879 (0.0011) -[2023-11-28 10:08:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5462.0, 300 sec: 5415.1). Total num frames: 193904640. Throughput: 0: 2670.2, 1: 2680.4. Samples: 193916856. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:08:53,445][86177] Avg episode reward: [(0, '-553.280'), (1, '-500.250')] -[2023-11-28 10:08:54,793][87426] Updated weights for policy 1, policy_version 378570 (0.0008) -[2023-11-28 10:08:55,175][87426] Updated weights for policy 1, policy_version 378580 (0.0010) -[2023-11-28 10:08:55,431][87424] Updated weights for policy 0, policy_version 378889 (0.0012) -[2023-11-28 10:08:55,549][87426] Updated weights for policy 1, policy_version 378590 (0.0012) -[2023-11-28 10:08:55,816][87424] Updated weights for policy 0, policy_version 378899 (0.0007) -[2023-11-28 10:08:56,214][87424] Updated weights for policy 0, policy_version 378909 (0.0007) -[2023-11-28 10:08:57,362][87426] Updated weights for policy 1, policy_version 378600 (0.0012) -[2023-11-28 10:08:57,742][87426] Updated weights for policy 1, policy_version 378610 (0.0011) -[2023-11-28 10:08:58,135][87426] Updated weights for policy 1, policy_version 378620 (0.0009) -[2023-11-28 10:08:58,418][87424] Updated weights for policy 0, policy_version 378919 (0.0007) -[2023-11-28 10:08:58,444][86177] Fps is (10 sec: 5734.7, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 193929216. Throughput: 0: 2677.6, 1: 2708.6. Samples: 193942064. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:08:58,445][86177] Avg episode reward: [(0, '-544.920'), (1, '-497.490')] -[2023-11-28 10:08:58,802][87424] Updated weights for policy 0, policy_version 378929 (0.0008) -[2023-11-28 10:08:59,194][87424] Updated weights for policy 0, policy_version 378939 (0.0010) -[2023-11-28 10:09:00,348][87426] Updated weights for policy 1, policy_version 378630 (0.0009) -[2023-11-28 10:09:00,718][87426] Updated weights for policy 1, policy_version 378640 (0.0012) -[2023-11-28 10:09:01,100][87426] Updated weights for policy 1, policy_version 378650 (0.0012) -[2023-11-28 10:09:01,455][87424] Updated weights for policy 0, policy_version 378949 (0.0011) -[2023-11-28 10:09:01,849][87424] Updated weights for policy 0, policy_version 378959 (0.0011) -[2023-11-28 10:09:02,219][87424] Updated weights for policy 0, policy_version 378969 (0.0009) -[2023-11-28 10:09:03,174][87426] Updated weights for policy 1, policy_version 378660 (0.0010) -[2023-11-28 10:09:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 193953792. Throughput: 0: 2689.7, 1: 2705.3. Samples: 193966660. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:09:03,445][86177] Avg episode reward: [(0, '-540.970'), (1, '-497.590')] -[2023-11-28 10:09:03,553][87426] Updated weights for policy 1, policy_version 378670 (0.0007) -[2023-11-28 10:09:03,934][87426] Updated weights for policy 1, policy_version 378680 (0.0007) -[2023-11-28 10:09:04,672][87424] Updated weights for policy 0, policy_version 378979 (0.0010) -[2023-11-28 10:09:05,045][87424] Updated weights for policy 0, policy_version 378989 (0.0012) -[2023-11-28 10:09:05,420][87424] Updated weights for policy 0, policy_version 378999 (0.0009) -[2023-11-28 10:09:05,955][87426] Updated weights for policy 1, policy_version 378690 (0.0008) -[2023-11-28 10:09:06,334][87426] Updated weights for policy 1, policy_version 378700 (0.0011) -[2023-11-28 10:09:06,711][87426] Updated weights for policy 1, policy_version 378710 (0.0011) -[2023-11-28 10:09:07,095][87426] Updated weights for policy 1, policy_version 378720 (0.0012) -[2023-11-28 10:09:07,687][87424] Updated weights for policy 0, policy_version 379009 (0.0008) -[2023-11-28 10:09:08,062][87424] Updated weights for policy 0, policy_version 379019 (0.0012) -[2023-11-28 10:09:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 193978368. Throughput: 0: 2648.9, 1: 2706.0. Samples: 193998352. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:09:08,445][86177] Avg episode reward: [(0, '-553.330'), (1, '-500.850')] -[2023-11-28 10:09:08,448][87424] Updated weights for policy 0, policy_version 379029 (0.0010) -[2023-11-28 10:09:08,821][87424] Updated weights for policy 0, policy_version 379039 (0.0008) -[2023-11-28 10:09:09,220][87426] Updated weights for policy 1, policy_version 378730 (0.0008) -[2023-11-28 10:09:09,591][87426] Updated weights for policy 1, policy_version 378740 (0.0009) -[2023-11-28 10:09:09,965][87426] Updated weights for policy 1, policy_version 378750 (0.0010) -[2023-11-28 10:09:11,351][87424] Updated weights for policy 0, policy_version 379049 (0.0012) -[2023-11-28 10:09:11,734][87424] Updated weights for policy 0, policy_version 379059 (0.0012) -[2023-11-28 10:09:11,881][87426] Updated weights for policy 1, policy_version 378760 (0.0011) -[2023-11-28 10:09:12,105][87424] Updated weights for policy 0, policy_version 379069 (0.0011) -[2023-11-28 10:09:12,275][87426] Updated weights for policy 1, policy_version 378770 (0.0012) -[2023-11-28 10:09:12,641][87426] Updated weights for policy 1, policy_version 378780 (0.0011) -[2023-11-28 10:09:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 194011136. Throughput: 0: 2626.7, 1: 2697.6. Samples: 194022356. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:09:13,445][86177] Avg episode reward: [(0, '-596.410'), (1, '-501.100')] -[2023-11-28 10:09:14,337][87424] Updated weights for policy 0, policy_version 379079 (0.0011) -[2023-11-28 10:09:14,716][87424] Updated weights for policy 0, policy_version 379089 (0.0012) -[2023-11-28 10:09:15,096][87424] Updated weights for policy 0, policy_version 379099 (0.0012) -[2023-11-28 10:09:15,138][87426] Updated weights for policy 1, policy_version 378790 (0.0011) -[2023-11-28 10:09:15,520][87426] Updated weights for policy 1, policy_version 378800 (0.0010) -[2023-11-28 10:09:15,894][87426] Updated weights for policy 1, policy_version 378810 (0.0012) -[2023-11-28 10:09:17,213][87424] Updated weights for policy 0, policy_version 379109 (0.0011) -[2023-11-28 10:09:17,586][87424] Updated weights for policy 0, policy_version 379119 (0.0012) -[2023-11-28 10:09:17,868][87426] Updated weights for policy 1, policy_version 378820 (0.0012) -[2023-11-28 10:09:17,964][87424] Updated weights for policy 0, policy_version 379129 (0.0011) -[2023-11-28 10:09:18,240][87426] Updated weights for policy 1, policy_version 378830 (0.0011) -[2023-11-28 10:09:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194035712. Throughput: 0: 2650.2, 1: 2691.2. Samples: 194046536. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:09:18,445][86177] Avg episode reward: [(0, '-584.980'), (1, '-501.020')] -[2023-11-28 10:09:18,614][87426] Updated weights for policy 1, policy_version 378840 (0.0012) -[2023-11-28 10:09:20,001][87424] Updated weights for policy 0, policy_version 379139 (0.0014) -[2023-11-28 10:09:20,380][87424] Updated weights for policy 0, policy_version 379149 (0.0010) -[2023-11-28 10:09:20,766][87424] Updated weights for policy 0, policy_version 379159 (0.0012) -[2023-11-28 10:09:20,980][87426] Updated weights for policy 1, policy_version 378850 (0.0011) -[2023-11-28 10:09:21,359][87426] Updated weights for policy 1, policy_version 378860 (0.0011) -[2023-11-28 10:09:21,738][87426] Updated weights for policy 1, policy_version 378870 (0.0011) -[2023-11-28 10:09:22,121][87426] Updated weights for policy 1, policy_version 378880 (0.0012) -[2023-11-28 10:09:23,173][87424] Updated weights for policy 0, policy_version 379169 (0.0012) -[2023-11-28 10:09:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194060288. Throughput: 0: 2662.7, 1: 2685.2. Samples: 194078828. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:09:23,445][86177] Avg episode reward: [(0, '-666.460'), (1, '-502.140')] -[2023-11-28 10:09:23,553][87424] Updated weights for policy 0, policy_version 379179 (0.0010) -[2023-11-28 10:09:23,942][87424] Updated weights for policy 0, policy_version 379189 (0.0008) -[2023-11-28 10:09:24,333][87424] Updated weights for policy 0, policy_version 379199 (0.0008) -[2023-11-28 10:09:24,643][87426] Updated weights for policy 1, policy_version 378890 (0.0009) -[2023-11-28 10:09:25,018][87426] Updated weights for policy 1, policy_version 378900 (0.0010) -[2023-11-28 10:09:25,403][87426] Updated weights for policy 1, policy_version 378910 (0.0008) -[2023-11-28 10:09:26,526][87424] Updated weights for policy 0, policy_version 379209 (0.0011) -[2023-11-28 10:09:26,912][87424] Updated weights for policy 0, policy_version 379219 (0.0012) -[2023-11-28 10:09:27,286][87424] Updated weights for policy 0, policy_version 379229 (0.0012) -[2023-11-28 10:09:27,578][87426] Updated weights for policy 1, policy_version 378920 (0.0009) -[2023-11-28 10:09:27,954][87426] Updated weights for policy 1, policy_version 378930 (0.0008) -[2023-11-28 10:09:28,333][87426] Updated weights for policy 1, policy_version 378940 (0.0007) -[2023-11-28 10:09:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 194084864. Throughput: 0: 2650.8, 1: 2696.5. Samples: 194102984. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:09:28,445][86177] Avg episode reward: [(0, '-661.260'), (1, '-503.710')] -[2023-11-28 10:09:29,085][87424] Updated weights for policy 0, policy_version 379239 (0.0009) -[2023-11-28 10:09:29,460][87424] Updated weights for policy 0, policy_version 379249 (0.0008) -[2023-11-28 10:09:29,853][87424] Updated weights for policy 0, policy_version 379259 (0.0009) -[2023-11-28 10:09:30,662][87426] Updated weights for policy 1, policy_version 378950 (0.0010) -[2023-11-28 10:09:31,044][87426] Updated weights for policy 1, policy_version 378960 (0.0011) -[2023-11-28 10:09:31,414][87426] Updated weights for policy 1, policy_version 378970 (0.0012) -[2023-11-28 10:09:31,935][87424] Updated weights for policy 0, policy_version 379269 (0.0011) -[2023-11-28 10:09:32,329][87424] Updated weights for policy 0, policy_version 379279 (0.0010) -[2023-11-28 10:09:32,700][87424] Updated weights for policy 0, policy_version 379289 (0.0008) -[2023-11-28 10:09:33,290][87426] Updated weights for policy 1, policy_version 378980 (0.0012) -[2023-11-28 10:09:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194117632. Throughput: 0: 2693.6, 1: 2682.9. Samples: 194127672. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:09:33,445][86177] Avg episode reward: [(0, '-633.410'), (1, '-503.450')] -[2023-11-28 10:09:33,666][87426] Updated weights for policy 1, policy_version 378990 (0.0012) -[2023-11-28 10:09:34,043][87426] Updated weights for policy 1, policy_version 379000 (0.0011) -[2023-11-28 10:09:34,505][87424] Updated weights for policy 0, policy_version 379299 (0.0011) -[2023-11-28 10:09:34,875][87424] Updated weights for policy 0, policy_version 379309 (0.0012) -[2023-11-28 10:09:35,265][87424] Updated weights for policy 0, policy_version 379319 (0.0012) -[2023-11-28 10:09:36,535][87426] Updated weights for policy 1, policy_version 379010 (0.0009) -[2023-11-28 10:09:36,915][87426] Updated weights for policy 1, policy_version 379020 (0.0011) -[2023-11-28 10:09:37,298][87426] Updated weights for policy 1, policy_version 379030 (0.0012) -[2023-11-28 10:09:37,407][87424] Updated weights for policy 0, policy_version 379329 (0.0012) -[2023-11-28 10:09:37,663][87426] Updated weights for policy 1, policy_version 379040 (0.0011) -[2023-11-28 10:09:37,783][87424] Updated weights for policy 0, policy_version 379339 (0.0012) -[2023-11-28 10:09:38,163][87424] Updated weights for policy 0, policy_version 379349 (0.0012) -[2023-11-28 10:09:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194142208. Throughput: 0: 2705.8, 1: 2715.6. Samples: 194160820. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:09:38,445][86177] Avg episode reward: [(0, '-626.640'), (1, '-506.670')] -[2023-11-28 10:09:38,552][87424] Updated weights for policy 0, policy_version 379359 (0.0008) -[2023-11-28 10:09:39,553][87426] Updated weights for policy 1, policy_version 379050 (0.0012) -[2023-11-28 10:09:39,927][87426] Updated weights for policy 1, policy_version 379060 (0.0012) -[2023-11-28 10:09:40,310][87426] Updated weights for policy 1, policy_version 379070 (0.0012) -[2023-11-28 10:09:40,832][87424] Updated weights for policy 0, policy_version 379369 (0.0008) -[2023-11-28 10:09:41,210][87424] Updated weights for policy 0, policy_version 379379 (0.0010) -[2023-11-28 10:09:41,592][87424] Updated weights for policy 0, policy_version 379389 (0.0010) -[2023-11-28 10:09:42,823][87426] Updated weights for policy 1, policy_version 379080 (0.0012) -[2023-11-28 10:09:43,198][87426] Updated weights for policy 1, policy_version 379090 (0.0011) -[2023-11-28 10:09:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194166784. Throughput: 0: 2680.3, 1: 2704.2. Samples: 194184364. Policy #0 lag: (min: 10.0, avg: 39.8, max: 70.0) -[2023-11-28 10:09:43,445][86177] Avg episode reward: [(0, '-542.990'), (1, '-504.270')] -[2023-11-28 10:09:43,580][87426] Updated weights for policy 1, policy_version 379100 (0.0009) -[2023-11-28 10:09:44,171][87424] Updated weights for policy 0, policy_version 379399 (0.0011) -[2023-11-28 10:09:44,553][87424] Updated weights for policy 0, policy_version 379409 (0.0012) -[2023-11-28 10:09:44,930][87424] Updated weights for policy 0, policy_version 379419 (0.0012) -[2023-11-28 10:09:45,519][87426] Updated weights for policy 1, policy_version 379110 (0.0011) -[2023-11-28 10:09:45,911][87426] Updated weights for policy 1, policy_version 379120 (0.0012) -[2023-11-28 10:09:46,287][87426] Updated weights for policy 1, policy_version 379130 (0.0012) -[2023-11-28 10:09:47,374][87424] Updated weights for policy 0, policy_version 379429 (0.0012) -[2023-11-28 10:09:47,762][87424] Updated weights for policy 0, policy_version 379439 (0.0012) -[2023-11-28 10:09:48,140][87424] Updated weights for policy 0, policy_version 379449 (0.0011) -[2023-11-28 10:09:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5415.0). Total num frames: 194199552. Throughput: 0: 2662.8, 1: 2710.8. Samples: 194208468. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:09:48,445][86177] Avg episode reward: [(0, '-545.770'), (1, '-500.950')] -[2023-11-28 10:09:48,795][87426] Updated weights for policy 1, policy_version 379140 (0.0012) -[2023-11-28 10:09:49,168][87426] Updated weights for policy 1, policy_version 379150 (0.0012) -[2023-11-28 10:09:49,549][87426] Updated weights for policy 1, policy_version 379160 (0.0012) -[2023-11-28 10:09:50,481][87424] Updated weights for policy 0, policy_version 379459 (0.0012) -[2023-11-28 10:09:50,855][87424] Updated weights for policy 0, policy_version 379469 (0.0012) -[2023-11-28 10:09:51,227][87424] Updated weights for policy 0, policy_version 379479 (0.0012) -[2023-11-28 10:09:51,825][87426] Updated weights for policy 1, policy_version 379170 (0.0011) -[2023-11-28 10:09:52,209][87426] Updated weights for policy 1, policy_version 379180 (0.0010) -[2023-11-28 10:09:52,577][87426] Updated weights for policy 1, policy_version 379190 (0.0012) -[2023-11-28 10:09:52,954][87426] Updated weights for policy 1, policy_version 379200 (0.0012) -[2023-11-28 10:09:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194224128. Throughput: 0: 2683.5, 1: 2689.4. Samples: 194240132. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:09:53,445][86177] Avg episode reward: [(0, '-528.420'), (1, '-499.370')] -[2023-11-28 10:09:53,797][87424] Updated weights for policy 0, policy_version 379489 (0.0012) -[2023-11-28 10:09:54,178][87424] Updated weights for policy 0, policy_version 379499 (0.0008) -[2023-11-28 10:09:54,560][87424] Updated weights for policy 0, policy_version 379509 (0.0008) -[2023-11-28 10:09:54,940][87424] Updated weights for policy 0, policy_version 379519 (0.0007) -[2023-11-28 10:09:55,094][87426] Updated weights for policy 1, policy_version 379210 (0.0008) -[2023-11-28 10:09:55,474][87426] Updated weights for policy 1, policy_version 379220 (0.0008) -[2023-11-28 10:09:55,865][87426] Updated weights for policy 1, policy_version 379230 (0.0008) -[2023-11-28 10:09:57,477][87424] Updated weights for policy 0, policy_version 379529 (0.0011) -[2023-11-28 10:09:57,859][87424] Updated weights for policy 0, policy_version 379539 (0.0010) -[2023-11-28 10:09:58,198][87426] Updated weights for policy 1, policy_version 379240 (0.0009) -[2023-11-28 10:09:58,251][87424] Updated weights for policy 0, policy_version 379549 (0.0008) -[2023-11-28 10:09:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194248704. Throughput: 0: 2686.8, 1: 2713.1. Samples: 194265348. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:09:58,445][86177] Avg episode reward: [(0, '-542.390'), (1, '-500.010')] -[2023-11-28 10:09:58,577][87426] Updated weights for policy 1, policy_version 379250 (0.0007) -[2023-11-28 10:09:58,963][87426] Updated weights for policy 1, policy_version 379260 (0.0008) -[2023-11-28 10:10:00,643][87424] Updated weights for policy 0, policy_version 379559 (0.0011) -[2023-11-28 10:10:01,024][87424] Updated weights for policy 0, policy_version 379569 (0.0011) -[2023-11-28 10:10:01,051][87426] Updated weights for policy 1, policy_version 379270 (0.0009) -[2023-11-28 10:10:01,406][87424] Updated weights for policy 0, policy_version 379579 (0.0012) -[2023-11-28 10:10:01,426][87426] Updated weights for policy 1, policy_version 379280 (0.0008) -[2023-11-28 10:10:01,804][87426] Updated weights for policy 1, policy_version 379290 (0.0010) -[2023-11-28 10:10:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 194273280. Throughput: 0: 2657.4, 1: 2721.0. Samples: 194288564. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:03,445][86177] Avg episode reward: [(0, '-543.730'), (1, '-501.340')] -[2023-11-28 10:10:03,728][87424] Updated weights for policy 0, policy_version 379589 (0.0012) -[2023-11-28 10:10:04,065][87426] Updated weights for policy 1, policy_version 379300 (0.0009) -[2023-11-28 10:10:04,112][87424] Updated weights for policy 0, policy_version 379599 (0.0007) -[2023-11-28 10:10:04,453][87426] Updated weights for policy 1, policy_version 379310 (0.0008) -[2023-11-28 10:10:04,493][87424] Updated weights for policy 0, policy_version 379609 (0.0009) -[2023-11-28 10:10:04,823][87426] Updated weights for policy 1, policy_version 379320 (0.0009) -[2023-11-28 10:10:06,473][87424] Updated weights for policy 0, policy_version 379619 (0.0012) -[2023-11-28 10:10:06,862][87424] Updated weights for policy 0, policy_version 379629 (0.0011) -[2023-11-28 10:10:07,043][87426] Updated weights for policy 1, policy_version 379330 (0.0009) -[2023-11-28 10:10:07,238][87424] Updated weights for policy 0, policy_version 379639 (0.0011) -[2023-11-28 10:10:07,425][87426] Updated weights for policy 1, policy_version 379340 (0.0012) -[2023-11-28 10:10:07,803][87426] Updated weights for policy 1, policy_version 379350 (0.0011) -[2023-11-28 10:10:08,182][87426] Updated weights for policy 1, policy_version 379360 (0.0012) -[2023-11-28 10:10:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194306048. Throughput: 0: 2680.0, 1: 2722.3. Samples: 194321932. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:08,445][86177] Avg episode reward: [(0, '-544.000'), (1, '-502.550')] -[2023-11-28 10:10:09,177][87424] Updated weights for policy 0, policy_version 379649 (0.0011) -[2023-11-28 10:10:09,565][87424] Updated weights for policy 0, policy_version 379659 (0.0009) -[2023-11-28 10:10:09,948][87424] Updated weights for policy 0, policy_version 379669 (0.0009) -[2023-11-28 10:10:10,329][87426] Updated weights for policy 1, policy_version 379370 (0.0011) -[2023-11-28 10:10:10,330][87424] Updated weights for policy 0, policy_version 379679 (0.0011) -[2023-11-28 10:10:10,709][87426] Updated weights for policy 1, policy_version 379380 (0.0011) -[2023-11-28 10:10:11,093][87426] Updated weights for policy 1, policy_version 379390 (0.0010) -[2023-11-28 10:10:12,444][87424] Updated weights for policy 0, policy_version 379689 (0.0013) -[2023-11-28 10:10:12,825][87424] Updated weights for policy 0, policy_version 379699 (0.0012) -[2023-11-28 10:10:13,206][87424] Updated weights for policy 0, policy_version 379709 (0.0012) -[2023-11-28 10:10:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194330624. Throughput: 0: 2681.4, 1: 2720.9. Samples: 194346088. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:13,445][86177] Avg episode reward: [(0, '-544.580'), (1, '-501.430')] -[2023-11-28 10:10:13,447][87426] Updated weights for policy 1, policy_version 379400 (0.0011) -[2023-11-28 10:10:13,829][87426] Updated weights for policy 1, policy_version 379410 (0.0012) -[2023-11-28 10:10:14,213][87426] Updated weights for policy 1, policy_version 379420 (0.0012) -[2023-11-28 10:10:15,214][87424] Updated weights for policy 0, policy_version 379719 (0.0008) -[2023-11-28 10:10:15,600][87424] Updated weights for policy 0, policy_version 379729 (0.0009) -[2023-11-28 10:10:15,986][87424] Updated weights for policy 0, policy_version 379739 (0.0007) -[2023-11-28 10:10:16,455][87426] Updated weights for policy 1, policy_version 379430 (0.0012) -[2023-11-28 10:10:16,838][87426] Updated weights for policy 1, policy_version 379440 (0.0011) -[2023-11-28 10:10:17,210][87426] Updated weights for policy 1, policy_version 379450 (0.0012) -[2023-11-28 10:10:17,950][87424] Updated weights for policy 0, policy_version 379749 (0.0008) -[2023-11-28 10:10:18,333][87424] Updated weights for policy 0, policy_version 379759 (0.0008) -[2023-11-28 10:10:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194355200. Throughput: 0: 2671.7, 1: 2727.6. Samples: 194370644. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:18,446][86177] Avg episode reward: [(0, '-539.160'), (1, '-505.430')] -[2023-11-28 10:10:18,460][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000379456_97140736.pth... -[2023-11-28 10:10:18,502][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000376960_96501760.pth -[2023-11-28 10:10:18,716][87424] Updated weights for policy 0, policy_version 379769 (0.0008) -[2023-11-28 10:10:18,983][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000379776_97222656.pth... -[2023-11-28 10:10:19,031][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000377248_96575488.pth -[2023-11-28 10:10:19,668][87426] Updated weights for policy 1, policy_version 379460 (0.0011) -[2023-11-28 10:10:20,044][87426] Updated weights for policy 1, policy_version 379470 (0.0012) -[2023-11-28 10:10:20,424][87426] Updated weights for policy 1, policy_version 379480 (0.0012) -[2023-11-28 10:10:21,045][87424] Updated weights for policy 0, policy_version 379779 (0.0010) -[2023-11-28 10:10:21,425][87424] Updated weights for policy 0, policy_version 379789 (0.0012) -[2023-11-28 10:10:21,805][87424] Updated weights for policy 0, policy_version 379799 (0.0011) -[2023-11-28 10:10:22,914][87426] Updated weights for policy 1, policy_version 379490 (0.0012) -[2023-11-28 10:10:23,284][87426] Updated weights for policy 1, policy_version 379500 (0.0012) -[2023-11-28 10:10:23,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194379776. Throughput: 0: 2660.4, 1: 2698.6. Samples: 194401980. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:23,446][86177] Avg episode reward: [(0, '-546.840'), (1, '-510.530')] -[2023-11-28 10:10:23,673][87426] Updated weights for policy 1, policy_version 379510 (0.0012) -[2023-11-28 10:10:23,922][87424] Updated weights for policy 0, policy_version 379809 (0.0009) -[2023-11-28 10:10:24,051][87426] Updated weights for policy 1, policy_version 379520 (0.0012) -[2023-11-28 10:10:24,301][87424] Updated weights for policy 0, policy_version 379819 (0.0012) -[2023-11-28 10:10:24,675][87424] Updated weights for policy 0, policy_version 379829 (0.0012) -[2023-11-28 10:10:25,064][87424] Updated weights for policy 0, policy_version 379839 (0.0012) -[2023-11-28 10:10:25,860][87426] Updated weights for policy 1, policy_version 379530 (0.0012) -[2023-11-28 10:10:26,241][87426] Updated weights for policy 1, policy_version 379540 (0.0012) -[2023-11-28 10:10:26,617][87426] Updated weights for policy 1, policy_version 379550 (0.0012) -[2023-11-28 10:10:27,105][87424] Updated weights for policy 0, policy_version 379849 (0.0012) -[2023-11-28 10:10:27,490][87424] Updated weights for policy 0, policy_version 379859 (0.0012) -[2023-11-28 10:10:27,877][87424] Updated weights for policy 0, policy_version 379869 (0.0011) -[2023-11-28 10:10:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194412544. Throughput: 0: 2664.2, 1: 2733.0. Samples: 194427236. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:28,445][86177] Avg episode reward: [(0, '-579.760'), (1, '-513.690')] -[2023-11-28 10:10:28,679][87426] Updated weights for policy 1, policy_version 379560 (0.0012) -[2023-11-28 10:10:29,066][87426] Updated weights for policy 1, policy_version 379570 (0.0009) -[2023-11-28 10:10:29,456][87426] Updated weights for policy 1, policy_version 379580 (0.0008) -[2023-11-28 10:10:30,202][87424] Updated weights for policy 0, policy_version 379879 (0.0011) -[2023-11-28 10:10:30,588][87424] Updated weights for policy 0, policy_version 379889 (0.0012) -[2023-11-28 10:10:30,966][87424] Updated weights for policy 0, policy_version 379899 (0.0012) -[2023-11-28 10:10:31,389][87426] Updated weights for policy 1, policy_version 379590 (0.0007) -[2023-11-28 10:10:31,769][87426] Updated weights for policy 1, policy_version 379600 (0.0009) -[2023-11-28 10:10:32,150][87426] Updated weights for policy 1, policy_version 379610 (0.0010) -[2023-11-28 10:10:33,119][87424] Updated weights for policy 0, policy_version 379909 (0.0011) -[2023-11-28 10:10:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 194437120. Throughput: 0: 2683.2, 1: 2715.9. Samples: 194451428. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:33,445][86177] Avg episode reward: [(0, '-587.000'), (1, '-516.010')] -[2023-11-28 10:10:33,508][87424] Updated weights for policy 0, policy_version 379919 (0.0012) -[2023-11-28 10:10:33,885][87424] Updated weights for policy 0, policy_version 379929 (0.0012) -[2023-11-28 10:10:34,174][87426] Updated weights for policy 1, policy_version 379620 (0.0011) -[2023-11-28 10:10:34,552][87426] Updated weights for policy 1, policy_version 379630 (0.0012) -[2023-11-28 10:10:34,948][87426] Updated weights for policy 1, policy_version 379640 (0.0012) -[2023-11-28 10:10:35,787][87424] Updated weights for policy 0, policy_version 379939 (0.0010) -[2023-11-28 10:10:36,169][87424] Updated weights for policy 0, policy_version 379949 (0.0007) -[2023-11-28 10:10:36,554][87424] Updated weights for policy 0, policy_version 379959 (0.0008) -[2023-11-28 10:10:36,679][87426] Updated weights for policy 1, policy_version 379650 (0.0012) -[2023-11-28 10:10:37,058][87426] Updated weights for policy 1, policy_version 379660 (0.0008) -[2023-11-28 10:10:37,440][87426] Updated weights for policy 1, policy_version 379670 (0.0011) -[2023-11-28 10:10:37,807][87426] Updated weights for policy 1, policy_version 379680 (0.0011) -[2023-11-28 10:10:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 194469888. Throughput: 0: 2699.1, 1: 2740.1. Samples: 194484896. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:38,445][86177] Avg episode reward: [(0, '-591.860'), (1, '-509.490')] -[2023-11-28 10:10:38,686][87424] Updated weights for policy 0, policy_version 379969 (0.0012) -[2023-11-28 10:10:39,070][87424] Updated weights for policy 0, policy_version 379979 (0.0012) -[2023-11-28 10:10:39,457][87424] Updated weights for policy 0, policy_version 379989 (0.0012) -[2023-11-28 10:10:39,844][87424] Updated weights for policy 0, policy_version 379999 (0.0012) -[2023-11-28 10:10:40,203][87426] Updated weights for policy 1, policy_version 379690 (0.0011) -[2023-11-28 10:10:40,576][87426] Updated weights for policy 1, policy_version 379700 (0.0010) -[2023-11-28 10:10:40,961][87426] Updated weights for policy 1, policy_version 379710 (0.0010) -[2023-11-28 10:10:42,103][87424] Updated weights for policy 0, policy_version 380009 (0.0010) -[2023-11-28 10:10:42,484][87424] Updated weights for policy 0, policy_version 380019 (0.0009) -[2023-11-28 10:10:42,874][87424] Updated weights for policy 0, policy_version 380029 (0.0011) -[2023-11-28 10:10:42,986][87426] Updated weights for policy 1, policy_version 379720 (0.0010) -[2023-11-28 10:10:43,362][87426] Updated weights for policy 1, policy_version 379730 (0.0011) -[2023-11-28 10:10:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194494464. Throughput: 0: 2720.5, 1: 2718.4. Samples: 194510100. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:43,445][86177] Avg episode reward: [(0, '-605.010'), (1, '-511.210')] -[2023-11-28 10:10:43,750][87426] Updated weights for policy 1, policy_version 379740 (0.0012) -[2023-11-28 10:10:44,851][87424] Updated weights for policy 0, policy_version 380039 (0.0012) -[2023-11-28 10:10:45,233][87424] Updated weights for policy 0, policy_version 380049 (0.0011) -[2023-11-28 10:10:45,614][87424] Updated weights for policy 0, policy_version 380059 (0.0011) -[2023-11-28 10:10:45,942][87426] Updated weights for policy 1, policy_version 379750 (0.0012) -[2023-11-28 10:10:46,322][87426] Updated weights for policy 1, policy_version 379760 (0.0010) -[2023-11-28 10:10:46,704][87426] Updated weights for policy 1, policy_version 379770 (0.0008) -[2023-11-28 10:10:47,431][87424] Updated weights for policy 0, policy_version 380069 (0.0010) -[2023-11-28 10:10:47,813][87424] Updated weights for policy 0, policy_version 380079 (0.0007) -[2023-11-28 10:10:48,200][87424] Updated weights for policy 0, policy_version 380089 (0.0007) -[2023-11-28 10:10:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194519040. Throughput: 0: 2757.9, 1: 2718.1. Samples: 194534984. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:48,445][86177] Avg episode reward: [(0, '-580.990'), (1, '-510.400')] -[2023-11-28 10:10:48,979][87426] Updated weights for policy 1, policy_version 379780 (0.0009) -[2023-11-28 10:10:49,366][87426] Updated weights for policy 1, policy_version 379790 (0.0010) -[2023-11-28 10:10:49,735][87426] Updated weights for policy 1, policy_version 379800 (0.0008) -[2023-11-28 10:10:50,228][87424] Updated weights for policy 0, policy_version 380099 (0.0008) -[2023-11-28 10:10:50,607][87424] Updated weights for policy 0, policy_version 380109 (0.0012) -[2023-11-28 10:10:50,977][87424] Updated weights for policy 0, policy_version 380119 (0.0012) -[2023-11-28 10:10:52,164][87426] Updated weights for policy 1, policy_version 379810 (0.0012) -[2023-11-28 10:10:52,536][87426] Updated weights for policy 1, policy_version 379820 (0.0012) -[2023-11-28 10:10:52,911][87426] Updated weights for policy 1, policy_version 379830 (0.0011) -[2023-11-28 10:10:53,295][87426] Updated weights for policy 1, policy_version 379840 (0.0011) -[2023-11-28 10:10:53,380][87424] Updated weights for policy 0, policy_version 380129 (0.0012) -[2023-11-28 10:10:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 194551808. Throughput: 0: 2737.8, 1: 2703.8. Samples: 194566804. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:53,445][86177] Avg episode reward: [(0, '-595.610'), (1, '-509.950')] -[2023-11-28 10:10:53,750][87424] Updated weights for policy 0, policy_version 380139 (0.0012) -[2023-11-28 10:10:54,133][87424] Updated weights for policy 0, policy_version 380149 (0.0012) -[2023-11-28 10:10:54,517][87424] Updated weights for policy 0, policy_version 380159 (0.0012) -[2023-11-28 10:10:55,857][87426] Updated weights for policy 1, policy_version 379850 (0.0012) -[2023-11-28 10:10:56,234][87426] Updated weights for policy 1, policy_version 379860 (0.0011) -[2023-11-28 10:10:56,616][87426] Updated weights for policy 1, policy_version 379870 (0.0011) -[2023-11-28 10:10:57,058][87424] Updated weights for policy 0, policy_version 380169 (0.0008) -[2023-11-28 10:10:57,439][87424] Updated weights for policy 0, policy_version 380179 (0.0007) -[2023-11-28 10:10:57,841][87424] Updated weights for policy 0, policy_version 380189 (0.0007) -[2023-11-28 10:10:58,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194576384. Throughput: 0: 2722.7, 1: 2702.4. Samples: 194590220. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:10:58,446][86177] Avg episode reward: [(0, '-586.600'), (1, '-512.960')] -[2023-11-28 10:10:58,525][87426] Updated weights for policy 1, policy_version 379880 (0.0012) -[2023-11-28 10:10:58,896][87426] Updated weights for policy 1, policy_version 379890 (0.0012) -[2023-11-28 10:10:59,279][87426] Updated weights for policy 1, policy_version 379900 (0.0012) -[2023-11-28 10:10:59,694][87424] Updated weights for policy 0, policy_version 380199 (0.0010) -[2023-11-28 10:11:00,068][87424] Updated weights for policy 0, policy_version 380209 (0.0011) -[2023-11-28 10:11:00,447][87424] Updated weights for policy 0, policy_version 380219 (0.0011) -[2023-11-28 10:11:01,448][87426] Updated weights for policy 1, policy_version 379910 (0.0009) -[2023-11-28 10:11:01,829][87426] Updated weights for policy 1, policy_version 379920 (0.0010) -[2023-11-28 10:11:02,203][87426] Updated weights for policy 1, policy_version 379930 (0.0012) -[2023-11-28 10:11:02,692][87424] Updated weights for policy 0, policy_version 380229 (0.0009) -[2023-11-28 10:11:03,078][87424] Updated weights for policy 0, policy_version 380239 (0.0012) -[2023-11-28 10:11:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 194600960. Throughput: 0: 2727.0, 1: 2697.4. Samples: 194614736. Policy #0 lag: (min: 31.0, avg: 38.0, max: 63.0) -[2023-11-28 10:11:03,445][86177] Avg episode reward: [(0, '-570.460'), (1, '-511.420')] -[2023-11-28 10:11:03,453][87424] Updated weights for policy 0, policy_version 380249 (0.0011) -[2023-11-28 10:11:04,744][87426] Updated weights for policy 1, policy_version 379940 (0.0012) -[2023-11-28 10:11:05,122][87426] Updated weights for policy 1, policy_version 379950 (0.0011) -[2023-11-28 10:11:05,499][87426] Updated weights for policy 1, policy_version 379960 (0.0011) -[2023-11-28 10:11:05,637][87424] Updated weights for policy 0, policy_version 380259 (0.0008) -[2023-11-28 10:11:06,023][87424] Updated weights for policy 0, policy_version 380269 (0.0009) -[2023-11-28 10:11:06,400][87424] Updated weights for policy 0, policy_version 380279 (0.0008) -[2023-11-28 10:11:07,655][87426] Updated weights for policy 1, policy_version 379970 (0.0011) -[2023-11-28 10:11:08,029][87426] Updated weights for policy 1, policy_version 379980 (0.0008) -[2023-11-28 10:11:08,409][87426] Updated weights for policy 1, policy_version 379990 (0.0007) -[2023-11-28 10:11:08,444][86177] Fps is (10 sec: 4915.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194625536. Throughput: 0: 2740.2, 1: 2700.8. Samples: 194646824. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:08,445][86177] Avg episode reward: [(0, '-557.970'), (1, '-511.570')] -[2023-11-28 10:11:08,602][87424] Updated weights for policy 0, policy_version 380289 (0.0012) -[2023-11-28 10:11:08,786][87426] Updated weights for policy 1, policy_version 380000 (0.0009) -[2023-11-28 10:11:08,974][87424] Updated weights for policy 0, policy_version 380299 (0.0011) -[2023-11-28 10:11:09,359][87424] Updated weights for policy 0, policy_version 380309 (0.0010) -[2023-11-28 10:11:09,740][87424] Updated weights for policy 0, policy_version 380319 (0.0009) -[2023-11-28 10:11:11,057][87426] Updated weights for policy 1, policy_version 380010 (0.0012) -[2023-11-28 10:11:11,438][87426] Updated weights for policy 1, policy_version 380020 (0.0012) -[2023-11-28 10:11:11,813][87426] Updated weights for policy 1, policy_version 380030 (0.0011) -[2023-11-28 10:11:12,151][87424] Updated weights for policy 0, policy_version 380329 (0.0009) -[2023-11-28 10:11:12,527][87424] Updated weights for policy 0, policy_version 380339 (0.0008) -[2023-11-28 10:11:12,913][87424] Updated weights for policy 0, policy_version 380349 (0.0014) -[2023-11-28 10:11:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 194658304. Throughput: 0: 2734.8, 1: 2674.1. Samples: 194670640. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:13,445][86177] Avg episode reward: [(0, '-534.230'), (1, '-506.780')] -[2023-11-28 10:11:14,071][87426] Updated weights for policy 1, policy_version 380040 (0.0008) -[2023-11-28 10:11:14,456][87426] Updated weights for policy 1, policy_version 380050 (0.0007) -[2023-11-28 10:11:14,837][87426] Updated weights for policy 1, policy_version 380060 (0.0007) -[2023-11-28 10:11:15,468][87424] Updated weights for policy 0, policy_version 380359 (0.0011) -[2023-11-28 10:11:15,840][87424] Updated weights for policy 0, policy_version 380369 (0.0012) -[2023-11-28 10:11:16,221][87424] Updated weights for policy 0, policy_version 380379 (0.0012) -[2023-11-28 10:11:17,098][87426] Updated weights for policy 1, policy_version 380070 (0.0009) -[2023-11-28 10:11:17,472][87426] Updated weights for policy 1, policy_version 380080 (0.0008) -[2023-11-28 10:11:17,855][87426] Updated weights for policy 1, policy_version 380090 (0.0011) -[2023-11-28 10:11:18,149][87424] Updated weights for policy 0, policy_version 380389 (0.0010) -[2023-11-28 10:11:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194682880. Throughput: 0: 2719.6, 1: 2679.8. Samples: 194694404. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:18,445][86177] Avg episode reward: [(0, '-531.050'), (1, '-502.860')] -[2023-11-28 10:11:18,543][87424] Updated weights for policy 0, policy_version 380399 (0.0008) -[2023-11-28 10:11:18,923][87424] Updated weights for policy 0, policy_version 380409 (0.0009) -[2023-11-28 10:11:19,805][87426] Updated weights for policy 1, policy_version 380100 (0.0012) -[2023-11-28 10:11:20,185][87426] Updated weights for policy 1, policy_version 380110 (0.0012) -[2023-11-28 10:11:20,561][87426] Updated weights for policy 1, policy_version 380120 (0.0012) -[2023-11-28 10:11:20,875][87424] Updated weights for policy 0, policy_version 380419 (0.0012) -[2023-11-28 10:11:21,244][87424] Updated weights for policy 0, policy_version 380429 (0.0011) -[2023-11-28 10:11:21,628][87424] Updated weights for policy 0, policy_version 380439 (0.0010) -[2023-11-28 10:11:22,771][87426] Updated weights for policy 1, policy_version 380130 (0.0010) -[2023-11-28 10:11:23,151][87426] Updated weights for policy 1, policy_version 380140 (0.0011) -[2023-11-28 10:11:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 194707456. Throughput: 0: 2714.9, 1: 2675.5. Samples: 194727464. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:23,445][86177] Avg episode reward: [(0, '-534.660'), (1, '-511.670')] -[2023-11-28 10:11:23,531][87426] Updated weights for policy 1, policy_version 380150 (0.0011) -[2023-11-28 10:11:23,803][87424] Updated weights for policy 0, policy_version 380449 (0.0012) -[2023-11-28 10:11:23,911][87426] Updated weights for policy 1, policy_version 380160 (0.0011) -[2023-11-28 10:11:24,174][87424] Updated weights for policy 0, policy_version 380459 (0.0012) -[2023-11-28 10:11:24,563][87424] Updated weights for policy 0, policy_version 380469 (0.0012) -[2023-11-28 10:11:24,959][87424] Updated weights for policy 0, policy_version 380479 (0.0011) -[2023-11-28 10:11:25,835][87426] Updated weights for policy 1, policy_version 380170 (0.0011) -[2023-11-28 10:11:26,214][87426] Updated weights for policy 1, policy_version 380180 (0.0011) -[2023-11-28 10:11:26,595][87426] Updated weights for policy 1, policy_version 380190 (0.0011) -[2023-11-28 10:11:27,152][87424] Updated weights for policy 0, policy_version 380489 (0.0011) -[2023-11-28 10:11:27,551][87424] Updated weights for policy 0, policy_version 380499 (0.0012) -[2023-11-28 10:11:27,935][87424] Updated weights for policy 0, policy_version 380509 (0.0012) -[2023-11-28 10:11:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194740224. Throughput: 0: 2703.6, 1: 2698.4. Samples: 194753192. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:28,445][86177] Avg episode reward: [(0, '-542.550'), (1, '-510.650')] -[2023-11-28 10:11:28,581][87426] Updated weights for policy 1, policy_version 380200 (0.0008) -[2023-11-28 10:11:28,962][87426] Updated weights for policy 1, policy_version 380210 (0.0008) -[2023-11-28 10:11:29,329][87426] Updated weights for policy 1, policy_version 380220 (0.0010) -[2023-11-28 10:11:30,278][87424] Updated weights for policy 0, policy_version 380519 (0.0012) -[2023-11-28 10:11:30,660][87424] Updated weights for policy 0, policy_version 380529 (0.0011) -[2023-11-28 10:11:31,047][87424] Updated weights for policy 0, policy_version 380539 (0.0011) -[2023-11-28 10:11:31,357][87426] Updated weights for policy 1, policy_version 380230 (0.0007) -[2023-11-28 10:11:31,732][87426] Updated weights for policy 1, policy_version 380240 (0.0009) -[2023-11-28 10:11:32,117][87426] Updated weights for policy 1, policy_version 380250 (0.0009) -[2023-11-28 10:11:33,282][87424] Updated weights for policy 0, policy_version 380549 (0.0009) -[2023-11-28 10:11:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194764800. Throughput: 0: 2689.3, 1: 2695.3. Samples: 194777292. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:33,445][86177] Avg episode reward: [(0, '-552.160'), (1, '-511.550')] -[2023-11-28 10:11:33,670][87424] Updated weights for policy 0, policy_version 380559 (0.0008) -[2023-11-28 10:11:34,055][87424] Updated weights for policy 0, policy_version 380569 (0.0008) -[2023-11-28 10:11:34,255][87426] Updated weights for policy 1, policy_version 380260 (0.0011) -[2023-11-28 10:11:34,632][87426] Updated weights for policy 1, policy_version 380270 (0.0012) -[2023-11-28 10:11:35,013][87426] Updated weights for policy 1, policy_version 380280 (0.0009) -[2023-11-28 10:11:36,427][87424] Updated weights for policy 0, policy_version 380579 (0.0009) -[2023-11-28 10:11:36,804][87424] Updated weights for policy 0, policy_version 380589 (0.0012) -[2023-11-28 10:11:37,195][87424] Updated weights for policy 0, policy_version 380599 (0.0011) -[2023-11-28 10:11:37,236][87426] Updated weights for policy 1, policy_version 380290 (0.0009) -[2023-11-28 10:11:37,610][87426] Updated weights for policy 1, policy_version 380300 (0.0007) -[2023-11-28 10:11:37,987][87426] Updated weights for policy 1, policy_version 380310 (0.0008) -[2023-11-28 10:11:38,362][87426] Updated weights for policy 1, policy_version 380320 (0.0009) -[2023-11-28 10:11:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 194797568. Throughput: 0: 2682.0, 1: 2733.0. Samples: 194810476. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:38,446][86177] Avg episode reward: [(0, '-586.720'), (1, '-515.900')] -[2023-11-28 10:11:39,181][87424] Updated weights for policy 0, policy_version 380609 (0.0011) -[2023-11-28 10:11:39,564][87424] Updated weights for policy 0, policy_version 380619 (0.0010) -[2023-11-28 10:11:39,944][87424] Updated weights for policy 0, policy_version 380629 (0.0010) -[2023-11-28 10:11:40,323][87424] Updated weights for policy 0, policy_version 380639 (0.0011) -[2023-11-28 10:11:40,334][87426] Updated weights for policy 1, policy_version 380330 (0.0010) -[2023-11-28 10:11:40,710][87426] Updated weights for policy 1, policy_version 380340 (0.0008) -[2023-11-28 10:11:41,088][87426] Updated weights for policy 1, policy_version 380350 (0.0009) -[2023-11-28 10:11:42,850][87424] Updated weights for policy 0, policy_version 380649 (0.0010) -[2023-11-28 10:11:43,226][87424] Updated weights for policy 0, policy_version 380659 (0.0016) -[2023-11-28 10:11:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194813952. Throughput: 0: 2700.7, 1: 2728.5. Samples: 194834532. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:43,445][86177] Avg episode reward: [(0, '-582.930'), (1, '-504.840')] -[2023-11-28 10:11:43,604][87426] Updated weights for policy 1, policy_version 380360 (0.0011) -[2023-11-28 10:11:43,605][87424] Updated weights for policy 0, policy_version 380669 (0.0009) -[2023-11-28 10:11:43,979][87426] Updated weights for policy 1, policy_version 380370 (0.0008) -[2023-11-28 10:11:44,361][87426] Updated weights for policy 1, policy_version 380380 (0.0007) -[2023-11-28 10:11:46,051][87424] Updated weights for policy 0, policy_version 380679 (0.0010) -[2023-11-28 10:11:46,425][87424] Updated weights for policy 0, policy_version 380689 (0.0011) -[2023-11-28 10:11:46,723][87426] Updated weights for policy 1, policy_version 380390 (0.0009) -[2023-11-28 10:11:46,819][87424] Updated weights for policy 0, policy_version 380699 (0.0011) -[2023-11-28 10:11:47,106][87426] Updated weights for policy 1, policy_version 380400 (0.0009) -[2023-11-28 10:11:47,488][87426] Updated weights for policy 1, policy_version 380410 (0.0009) -[2023-11-28 10:11:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 194846720. Throughput: 0: 2660.7, 1: 2739.5. Samples: 194857744. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:48,445][86177] Avg episode reward: [(0, '-573.060'), (1, '-508.240')] -[2023-11-28 10:11:49,284][87424] Updated weights for policy 0, policy_version 380709 (0.0011) -[2023-11-28 10:11:49,673][87424] Updated weights for policy 0, policy_version 380719 (0.0012) -[2023-11-28 10:11:49,714][87426] Updated weights for policy 1, policy_version 380420 (0.0008) -[2023-11-28 10:11:50,066][87424] Updated weights for policy 0, policy_version 380729 (0.0012) -[2023-11-28 10:11:50,090][87426] Updated weights for policy 1, policy_version 380430 (0.0012) -[2023-11-28 10:11:50,482][87426] Updated weights for policy 1, policy_version 380440 (0.0012) -[2023-11-28 10:11:52,218][87424] Updated weights for policy 0, policy_version 380739 (0.0012) -[2023-11-28 10:11:52,605][87424] Updated weights for policy 0, policy_version 380749 (0.0012) -[2023-11-28 10:11:52,696][87426] Updated weights for policy 1, policy_version 380450 (0.0011) -[2023-11-28 10:11:52,982][87424] Updated weights for policy 0, policy_version 380759 (0.0011) -[2023-11-28 10:11:53,072][87426] Updated weights for policy 1, policy_version 380460 (0.0010) -[2023-11-28 10:11:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194871296. Throughput: 0: 2645.2, 1: 2734.0. Samples: 194888888. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:53,445][86177] Avg episode reward: [(0, '-568.690'), (1, '-509.090')] -[2023-11-28 10:11:53,447][87426] Updated weights for policy 1, policy_version 380470 (0.0009) -[2023-11-28 10:11:53,831][87426] Updated weights for policy 1, policy_version 380480 (0.0010) -[2023-11-28 10:11:54,955][87424] Updated weights for policy 0, policy_version 380769 (0.0011) -[2023-11-28 10:11:55,340][87424] Updated weights for policy 0, policy_version 380779 (0.0008) -[2023-11-28 10:11:55,726][87424] Updated weights for policy 0, policy_version 380789 (0.0012) -[2023-11-28 10:11:55,964][87426] Updated weights for policy 1, policy_version 380490 (0.0008) -[2023-11-28 10:11:56,112][87424] Updated weights for policy 0, policy_version 380799 (0.0008) -[2023-11-28 10:11:56,340][87426] Updated weights for policy 1, policy_version 380500 (0.0008) -[2023-11-28 10:11:56,717][87426] Updated weights for policy 1, policy_version 380510 (0.0008) -[2023-11-28 10:11:58,184][87424] Updated weights for policy 0, policy_version 380809 (0.0011) -[2023-11-28 10:11:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194895872. Throughput: 0: 2659.0, 1: 2731.2. Samples: 194913200. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:11:58,446][86177] Avg episode reward: [(0, '-541.090'), (1, '-505.340')] -[2023-11-28 10:11:58,566][87424] Updated weights for policy 0, policy_version 380819 (0.0011) -[2023-11-28 10:11:58,918][87426] Updated weights for policy 1, policy_version 380520 (0.0010) -[2023-11-28 10:11:58,946][87424] Updated weights for policy 0, policy_version 380829 (0.0010) -[2023-11-28 10:11:59,300][87426] Updated weights for policy 1, policy_version 380530 (0.0011) -[2023-11-28 10:11:59,680][87426] Updated weights for policy 1, policy_version 380540 (0.0012) -[2023-11-28 10:12:01,239][87424] Updated weights for policy 0, policy_version 380839 (0.0011) -[2023-11-28 10:12:01,630][87424] Updated weights for policy 0, policy_version 380849 (0.0012) -[2023-11-28 10:12:02,002][87424] Updated weights for policy 0, policy_version 380859 (0.0012) -[2023-11-28 10:12:02,246][87426] Updated weights for policy 1, policy_version 380550 (0.0011) -[2023-11-28 10:12:02,625][87426] Updated weights for policy 1, policy_version 380560 (0.0008) -[2023-11-28 10:12:03,006][87426] Updated weights for policy 1, policy_version 380570 (0.0009) -[2023-11-28 10:12:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194928640. Throughput: 0: 2668.4, 1: 2725.2. Samples: 194937116. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:12:03,445][86177] Avg episode reward: [(0, '-539.510'), (1, '-506.100')] -[2023-11-28 10:12:04,404][87424] Updated weights for policy 0, policy_version 380869 (0.0010) -[2023-11-28 10:12:04,777][87424] Updated weights for policy 0, policy_version 380879 (0.0012) -[2023-11-28 10:12:05,154][87424] Updated weights for policy 0, policy_version 380889 (0.0012) -[2023-11-28 10:12:05,636][87426] Updated weights for policy 1, policy_version 380580 (0.0008) -[2023-11-28 10:12:06,013][87426] Updated weights for policy 1, policy_version 380590 (0.0008) -[2023-11-28 10:12:06,399][87426] Updated weights for policy 1, policy_version 380600 (0.0008) -[2023-11-28 10:12:07,201][87424] Updated weights for policy 0, policy_version 380899 (0.0012) -[2023-11-28 10:12:07,578][87424] Updated weights for policy 0, policy_version 380909 (0.0011) -[2023-11-28 10:12:07,959][87424] Updated weights for policy 0, policy_version 380919 (0.0007) -[2023-11-28 10:12:08,197][87426] Updated weights for policy 1, policy_version 380610 (0.0009) -[2023-11-28 10:12:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 194953216. Throughput: 0: 2688.0, 1: 2709.7. Samples: 194970360. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:12:08,445][86177] Avg episode reward: [(0, '-540.590'), (1, '-511.710')] -[2023-11-28 10:12:08,577][87426] Updated weights for policy 1, policy_version 380620 (0.0008) -[2023-11-28 10:12:08,957][87426] Updated weights for policy 1, policy_version 380630 (0.0008) -[2023-11-28 10:12:09,338][87426] Updated weights for policy 1, policy_version 380640 (0.0007) -[2023-11-28 10:12:09,904][87424] Updated weights for policy 0, policy_version 380929 (0.0008) -[2023-11-28 10:12:10,287][87424] Updated weights for policy 0, policy_version 380939 (0.0012) -[2023-11-28 10:12:10,664][87424] Updated weights for policy 0, policy_version 380949 (0.0010) -[2023-11-28 10:12:11,044][87424] Updated weights for policy 0, policy_version 380959 (0.0009) -[2023-11-28 10:12:11,601][87426] Updated weights for policy 1, policy_version 380650 (0.0012) -[2023-11-28 10:12:11,976][87426] Updated weights for policy 1, policy_version 380660 (0.0010) -[2023-11-28 10:12:12,364][87426] Updated weights for policy 1, policy_version 380670 (0.0009) -[2023-11-28 10:12:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 194977792. Throughput: 0: 2678.9, 1: 2690.6. Samples: 194994820. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:12:13,445][86177] Avg episode reward: [(0, '-544.670'), (1, '-511.100')] -[2023-11-28 10:12:13,531][87424] Updated weights for policy 0, policy_version 380969 (0.0012) -[2023-11-28 10:12:13,920][87424] Updated weights for policy 0, policy_version 380979 (0.0012) -[2023-11-28 10:12:14,174][87426] Updated weights for policy 1, policy_version 380680 (0.0008) -[2023-11-28 10:12:14,290][87424] Updated weights for policy 0, policy_version 380989 (0.0012) -[2023-11-28 10:12:14,550][87426] Updated weights for policy 1, policy_version 380690 (0.0008) -[2023-11-28 10:12:14,928][87426] Updated weights for policy 1, policy_version 380700 (0.0011) -[2023-11-28 10:12:16,223][87424] Updated weights for policy 0, policy_version 380999 (0.0012) -[2023-11-28 10:12:16,599][87424] Updated weights for policy 0, policy_version 381009 (0.0012) -[2023-11-28 10:12:16,849][87426] Updated weights for policy 1, policy_version 380710 (0.0012) -[2023-11-28 10:12:16,976][87424] Updated weights for policy 0, policy_version 381019 (0.0011) -[2023-11-28 10:12:17,225][87426] Updated weights for policy 1, policy_version 380720 (0.0011) -[2023-11-28 10:12:17,609][87426] Updated weights for policy 1, policy_version 380730 (0.0011) -[2023-11-28 10:12:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 195010560. Throughput: 0: 2666.6, 1: 2706.5. Samples: 195019080. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:12:18,445][86177] Avg episode reward: [(0, '-536.930'), (1, '-514.590')] -[2023-11-28 10:12:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000381024_97542144.pth... -[2023-11-28 10:12:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000380736_97468416.pth... -[2023-11-28 10:12:18,490][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000378208_96821248.pth -[2023-11-28 10:12:18,495][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000380736_97468416.pth -[2023-11-28 10:12:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000378528_96903168.pth -[2023-11-28 10:12:18,510][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000381024_97542144.pth -[2023-11-28 10:12:19,134][87424] Updated weights for policy 0, policy_version 381029 (0.0007) -[2023-11-28 10:12:19,516][87424] Updated weights for policy 0, policy_version 381039 (0.0008) -[2023-11-28 10:12:19,901][87426] Updated weights for policy 1, policy_version 380740 (0.0011) -[2023-11-28 10:12:19,903][87424] Updated weights for policy 0, policy_version 381049 (0.0012) -[2023-11-28 10:12:20,278][87426] Updated weights for policy 1, policy_version 380750 (0.0011) -[2023-11-28 10:12:20,658][87426] Updated weights for policy 1, policy_version 380760 (0.0011) -[2023-11-28 10:12:22,501][87424] Updated weights for policy 0, policy_version 381059 (0.0012) -[2023-11-28 10:12:22,880][87424] Updated weights for policy 0, policy_version 381069 (0.0012) -[2023-11-28 10:12:23,191][87426] Updated weights for policy 1, policy_version 380770 (0.0012) -[2023-11-28 10:12:23,265][87424] Updated weights for policy 0, policy_version 381079 (0.0014) -[2023-11-28 10:12:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195026944. Throughput: 0: 2677.3, 1: 2668.5. Samples: 195051036. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:12:23,445][86177] Avg episode reward: [(0, '-540.240'), (1, '-517.500')] -[2023-11-28 10:12:23,563][87426] Updated weights for policy 1, policy_version 380780 (0.0008) -[2023-11-28 10:12:23,949][87426] Updated weights for policy 1, policy_version 380790 (0.0007) -[2023-11-28 10:12:24,325][87426] Updated weights for policy 1, policy_version 380800 (0.0007) -[2023-11-28 10:12:25,430][87424] Updated weights for policy 0, policy_version 381089 (0.0010) -[2023-11-28 10:12:25,814][87424] Updated weights for policy 0, policy_version 381099 (0.0007) -[2023-11-28 10:12:26,195][87424] Updated weights for policy 0, policy_version 381109 (0.0007) -[2023-11-28 10:12:26,574][87424] Updated weights for policy 0, policy_version 381119 (0.0011) -[2023-11-28 10:12:26,714][87426] Updated weights for policy 1, policy_version 380810 (0.0007) -[2023-11-28 10:12:27,097][87426] Updated weights for policy 1, policy_version 380820 (0.0007) -[2023-11-28 10:12:27,476][87426] Updated weights for policy 1, policy_version 380830 (0.0007) -[2023-11-28 10:12:28,218][87424] Updated weights for policy 0, policy_version 381129 (0.0010) -[2023-11-28 10:12:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195059712. Throughput: 0: 2665.0, 1: 2656.4. Samples: 195073992. Policy #0 lag: (min: 31.0, avg: 42.3, max: 63.0) -[2023-11-28 10:12:28,445][86177] Avg episode reward: [(0, '-541.340'), (1, '-542.360')] -[2023-11-28 10:12:28,605][87424] Updated weights for policy 0, policy_version 381139 (0.0007) -[2023-11-28 10:12:28,987][87424] Updated weights for policy 0, policy_version 381149 (0.0008) -[2023-11-28 10:12:29,699][87426] Updated weights for policy 1, policy_version 380840 (0.0010) -[2023-11-28 10:12:30,078][87426] Updated weights for policy 1, policy_version 380850 (0.0009) -[2023-11-28 10:12:30,459][87426] Updated weights for policy 1, policy_version 380860 (0.0009) -[2023-11-28 10:12:31,412][87424] Updated weights for policy 0, policy_version 381159 (0.0010) -[2023-11-28 10:12:31,791][87424] Updated weights for policy 0, policy_version 381169 (0.0011) -[2023-11-28 10:12:32,186][87424] Updated weights for policy 0, policy_version 381179 (0.0011) -[2023-11-28 10:12:32,732][87426] Updated weights for policy 1, policy_version 380870 (0.0012) -[2023-11-28 10:12:33,106][87426] Updated weights for policy 1, policy_version 380880 (0.0012) -[2023-11-28 10:12:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195084288. Throughput: 0: 2685.3, 1: 2661.3. Samples: 195098336. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:12:33,445][86177] Avg episode reward: [(0, '-545.150'), (1, '-537.250')] -[2023-11-28 10:12:33,487][87426] Updated weights for policy 1, policy_version 380890 (0.0012) -[2023-11-28 10:12:34,413][87424] Updated weights for policy 0, policy_version 381189 (0.0009) -[2023-11-28 10:12:34,799][87424] Updated weights for policy 0, policy_version 381199 (0.0008) -[2023-11-28 10:12:35,175][87424] Updated weights for policy 0, policy_version 381209 (0.0011) -[2023-11-28 10:12:35,378][87426] Updated weights for policy 1, policy_version 380900 (0.0012) -[2023-11-28 10:12:35,760][87426] Updated weights for policy 1, policy_version 380910 (0.0010) -[2023-11-28 10:12:36,135][87426] Updated weights for policy 1, policy_version 380920 (0.0012) -[2023-11-28 10:12:37,022][87424] Updated weights for policy 0, policy_version 381219 (0.0011) -[2023-11-28 10:12:37,397][87424] Updated weights for policy 0, policy_version 381229 (0.0011) -[2023-11-28 10:12:37,779][87424] Updated weights for policy 0, policy_version 381239 (0.0008) -[2023-11-28 10:12:38,136][87426] Updated weights for policy 1, policy_version 380930 (0.0008) -[2023-11-28 10:12:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195117056. Throughput: 0: 2725.1, 1: 2700.7. Samples: 195133048. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:12:38,445][86177] Avg episode reward: [(0, '-545.320'), (1, '-536.170')] -[2023-11-28 10:12:38,511][87426] Updated weights for policy 1, policy_version 380940 (0.0007) -[2023-11-28 10:12:38,887][87426] Updated weights for policy 1, policy_version 380950 (0.0008) -[2023-11-28 10:12:39,269][87426] Updated weights for policy 1, policy_version 380960 (0.0009) -[2023-11-28 10:12:40,378][87424] Updated weights for policy 0, policy_version 381249 (0.0008) -[2023-11-28 10:12:40,754][87424] Updated weights for policy 0, policy_version 381259 (0.0011) -[2023-11-28 10:12:41,134][87424] Updated weights for policy 0, policy_version 381269 (0.0010) -[2023-11-28 10:12:41,516][87424] Updated weights for policy 0, policy_version 381279 (0.0010) -[2023-11-28 10:12:41,644][87426] Updated weights for policy 1, policy_version 380970 (0.0010) -[2023-11-28 10:12:42,021][87426] Updated weights for policy 1, policy_version 380980 (0.0011) -[2023-11-28 10:12:42,406][87426] Updated weights for policy 1, policy_version 380990 (0.0008) -[2023-11-28 10:12:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 195141632. Throughput: 0: 2708.7, 1: 2704.5. Samples: 195156796. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:12:43,445][86177] Avg episode reward: [(0, '-559.380'), (1, '-500.490')] -[2023-11-28 10:12:43,844][87424] Updated weights for policy 0, policy_version 381289 (0.0012) -[2023-11-28 10:12:44,229][87424] Updated weights for policy 0, policy_version 381299 (0.0012) -[2023-11-28 10:12:44,610][87424] Updated weights for policy 0, policy_version 381309 (0.0011) -[2023-11-28 10:12:44,879][87426] Updated weights for policy 1, policy_version 381000 (0.0011) -[2023-11-28 10:12:45,252][87426] Updated weights for policy 1, policy_version 381010 (0.0011) -[2023-11-28 10:12:45,634][87426] Updated weights for policy 1, policy_version 381020 (0.0012) -[2023-11-28 10:12:46,475][87424] Updated weights for policy 0, policy_version 381319 (0.0012) -[2023-11-28 10:12:46,853][87424] Updated weights for policy 0, policy_version 381329 (0.0012) -[2023-11-28 10:12:47,224][87424] Updated weights for policy 0, policy_version 381339 (0.0011) -[2023-11-28 10:12:47,790][87426] Updated weights for policy 1, policy_version 381030 (0.0012) -[2023-11-28 10:12:48,167][87426] Updated weights for policy 1, policy_version 381040 (0.0012) -[2023-11-28 10:12:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.4). Total num frames: 195166208. Throughput: 0: 2709.9, 1: 2705.5. Samples: 195180808. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:12:48,445][86177] Avg episode reward: [(0, '-614.810'), (1, '-499.590')] -[2023-11-28 10:12:48,542][87426] Updated weights for policy 1, policy_version 381050 (0.0008) -[2023-11-28 10:12:49,535][87424] Updated weights for policy 0, policy_version 381349 (0.0010) -[2023-11-28 10:12:49,910][87424] Updated weights for policy 0, policy_version 381359 (0.0011) -[2023-11-28 10:12:50,290][87424] Updated weights for policy 0, policy_version 381369 (0.0009) -[2023-11-28 10:12:50,901][87426] Updated weights for policy 1, policy_version 381060 (0.0007) -[2023-11-28 10:12:51,280][87426] Updated weights for policy 1, policy_version 381070 (0.0009) -[2023-11-28 10:12:51,661][87426] Updated weights for policy 1, policy_version 381080 (0.0011) -[2023-11-28 10:12:52,652][87424] Updated weights for policy 0, policy_version 381379 (0.0012) -[2023-11-28 10:12:53,032][87424] Updated weights for policy 0, policy_version 381389 (0.0012) -[2023-11-28 10:12:53,422][87424] Updated weights for policy 0, policy_version 381399 (0.0012) -[2023-11-28 10:12:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195190784. Throughput: 0: 2671.9, 1: 2700.4. Samples: 195212116. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:12:53,445][86177] Avg episode reward: [(0, '-613.760'), (1, '-502.140')] -[2023-11-28 10:12:54,161][87426] Updated weights for policy 1, policy_version 381090 (0.0012) -[2023-11-28 10:12:54,534][87426] Updated weights for policy 1, policy_version 381100 (0.0012) -[2023-11-28 10:12:54,904][87426] Updated weights for policy 1, policy_version 381110 (0.0012) -[2023-11-28 10:12:55,279][87426] Updated weights for policy 1, policy_version 381120 (0.0009) -[2023-11-28 10:12:55,469][87424] Updated weights for policy 0, policy_version 381409 (0.0010) -[2023-11-28 10:12:55,859][87424] Updated weights for policy 0, policy_version 381419 (0.0007) -[2023-11-28 10:12:56,244][87424] Updated weights for policy 0, policy_version 381429 (0.0008) -[2023-11-28 10:12:56,624][87424] Updated weights for policy 0, policy_version 381439 (0.0007) -[2023-11-28 10:12:57,750][87426] Updated weights for policy 1, policy_version 381130 (0.0008) -[2023-11-28 10:12:58,133][87426] Updated weights for policy 1, policy_version 381140 (0.0007) -[2023-11-28 10:12:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195215360. Throughput: 0: 2688.1, 1: 2673.8. Samples: 195236104. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:12:58,445][86177] Avg episode reward: [(0, '-610.170'), (1, '-504.800')] -[2023-11-28 10:12:58,523][87426] Updated weights for policy 1, policy_version 381150 (0.0008) -[2023-11-28 10:12:59,080][87424] Updated weights for policy 0, policy_version 381449 (0.0010) -[2023-11-28 10:12:59,457][87424] Updated weights for policy 0, policy_version 381459 (0.0011) -[2023-11-28 10:12:59,835][87424] Updated weights for policy 0, policy_version 381469 (0.0012) -[2023-11-28 10:13:00,780][87426] Updated weights for policy 1, policy_version 381160 (0.0011) -[2023-11-28 10:13:01,166][87426] Updated weights for policy 1, policy_version 381170 (0.0012) -[2023-11-28 10:13:01,551][87426] Updated weights for policy 1, policy_version 381180 (0.0012) -[2023-11-28 10:13:02,008][87424] Updated weights for policy 0, policy_version 381479 (0.0011) -[2023-11-28 10:13:02,387][87424] Updated weights for policy 0, policy_version 381489 (0.0008) -[2023-11-28 10:13:02,768][87424] Updated weights for policy 0, policy_version 381499 (0.0008) -[2023-11-28 10:13:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195248128. Throughput: 0: 2706.2, 1: 2661.9. Samples: 195260644. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:03,445][86177] Avg episode reward: [(0, '-607.270'), (1, '-503.950')] -[2023-11-28 10:13:03,508][87426] Updated weights for policy 1, policy_version 381190 (0.0011) -[2023-11-28 10:13:03,889][87426] Updated weights for policy 1, policy_version 381200 (0.0011) -[2023-11-28 10:13:04,267][87426] Updated weights for policy 1, policy_version 381210 (0.0009) -[2023-11-28 10:13:05,179][87424] Updated weights for policy 0, policy_version 381509 (0.0008) -[2023-11-28 10:13:05,563][87424] Updated weights for policy 0, policy_version 381519 (0.0008) -[2023-11-28 10:13:05,945][87424] Updated weights for policy 0, policy_version 381529 (0.0007) -[2023-11-28 10:13:06,554][87426] Updated weights for policy 1, policy_version 381220 (0.0011) -[2023-11-28 10:13:06,938][87426] Updated weights for policy 1, policy_version 381230 (0.0011) -[2023-11-28 10:13:07,310][87426] Updated weights for policy 1, policy_version 381240 (0.0012) -[2023-11-28 10:13:08,440][87424] Updated weights for policy 0, policy_version 381539 (0.0007) -[2023-11-28 10:13:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195272704. Throughput: 0: 2688.0, 1: 2661.1. Samples: 195291748. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:08,446][86177] Avg episode reward: [(0, '-551.090'), (1, '-503.050')] -[2023-11-28 10:13:08,819][87424] Updated weights for policy 0, policy_version 381549 (0.0008) -[2023-11-28 10:13:09,203][87424] Updated weights for policy 0, policy_version 381559 (0.0008) -[2023-11-28 10:13:09,613][87426] Updated weights for policy 1, policy_version 381250 (0.0011) -[2023-11-28 10:13:09,986][87426] Updated weights for policy 1, policy_version 381260 (0.0010) -[2023-11-28 10:13:10,368][87426] Updated weights for policy 1, policy_version 381270 (0.0008) -[2023-11-28 10:13:10,739][87426] Updated weights for policy 1, policy_version 381280 (0.0011) -[2023-11-28 10:13:11,771][87424] Updated weights for policy 0, policy_version 381569 (0.0008) -[2023-11-28 10:13:12,147][87424] Updated weights for policy 0, policy_version 381579 (0.0009) -[2023-11-28 10:13:12,536][87424] Updated weights for policy 0, policy_version 381589 (0.0011) -[2023-11-28 10:13:12,911][87424] Updated weights for policy 0, policy_version 381599 (0.0009) -[2023-11-28 10:13:13,206][87426] Updated weights for policy 1, policy_version 381290 (0.0009) -[2023-11-28 10:13:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195297280. Throughput: 0: 2689.2, 1: 2653.5. Samples: 195314416. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:13,446][86177] Avg episode reward: [(0, '-556.840'), (1, '-501.900')] -[2023-11-28 10:13:13,584][87426] Updated weights for policy 1, policy_version 381300 (0.0009) -[2023-11-28 10:13:13,967][87426] Updated weights for policy 1, policy_version 381310 (0.0010) -[2023-11-28 10:13:14,931][87424] Updated weights for policy 0, policy_version 381609 (0.0011) -[2023-11-28 10:13:15,325][87424] Updated weights for policy 0, policy_version 381619 (0.0009) -[2023-11-28 10:13:15,704][87424] Updated weights for policy 0, policy_version 381629 (0.0008) -[2023-11-28 10:13:15,707][87426] Updated weights for policy 1, policy_version 381320 (0.0011) -[2023-11-28 10:13:16,097][87426] Updated weights for policy 1, policy_version 381330 (0.0011) -[2023-11-28 10:13:16,475][87426] Updated weights for policy 1, policy_version 381340 (0.0011) -[2023-11-28 10:13:17,750][87424] Updated weights for policy 0, policy_version 381639 (0.0010) -[2023-11-28 10:13:18,135][87424] Updated weights for policy 0, policy_version 381649 (0.0007) -[2023-11-28 10:13:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 195321856. Throughput: 0: 2678.4, 1: 2653.0. Samples: 195338248. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:18,445][86177] Avg episode reward: [(0, '-556.060'), (1, '-504.970')] -[2023-11-28 10:13:18,517][87424] Updated weights for policy 0, policy_version 381659 (0.0009) -[2023-11-28 10:13:18,854][87426] Updated weights for policy 1, policy_version 381350 (0.0011) -[2023-11-28 10:13:19,231][87426] Updated weights for policy 1, policy_version 381360 (0.0012) -[2023-11-28 10:13:19,612][87426] Updated weights for policy 1, policy_version 381370 (0.0012) -[2023-11-28 10:13:20,822][87424] Updated weights for policy 0, policy_version 381669 (0.0011) -[2023-11-28 10:13:21,208][87424] Updated weights for policy 0, policy_version 381679 (0.0010) -[2023-11-28 10:13:21,596][87424] Updated weights for policy 0, policy_version 381689 (0.0010) -[2023-11-28 10:13:22,122][87426] Updated weights for policy 1, policy_version 381380 (0.0011) -[2023-11-28 10:13:22,519][87426] Updated weights for policy 1, policy_version 381390 (0.0012) -[2023-11-28 10:13:22,898][87426] Updated weights for policy 1, policy_version 381400 (0.0011) -[2023-11-28 10:13:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 195354624. Throughput: 0: 2636.2, 1: 2617.1. Samples: 195369444. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:23,445][86177] Avg episode reward: [(0, '-556.780'), (1, '-502.230')] -[2023-11-28 10:13:23,814][87424] Updated weights for policy 0, policy_version 381699 (0.0011) -[2023-11-28 10:13:24,195][87424] Updated weights for policy 0, policy_version 381709 (0.0011) -[2023-11-28 10:13:24,577][87424] Updated weights for policy 0, policy_version 381719 (0.0012) -[2023-11-28 10:13:25,534][87426] Updated weights for policy 1, policy_version 381410 (0.0011) -[2023-11-28 10:13:25,931][87426] Updated weights for policy 1, policy_version 381420 (0.0009) -[2023-11-28 10:13:26,309][87426] Updated weights for policy 1, policy_version 381430 (0.0008) -[2023-11-28 10:13:26,685][87426] Updated weights for policy 1, policy_version 381440 (0.0007) -[2023-11-28 10:13:27,032][87424] Updated weights for policy 0, policy_version 381729 (0.0012) -[2023-11-28 10:13:27,412][87424] Updated weights for policy 0, policy_version 381739 (0.0012) -[2023-11-28 10:13:27,801][87424] Updated weights for policy 0, policy_version 381749 (0.0012) -[2023-11-28 10:13:28,200][87424] Updated weights for policy 0, policy_version 381759 (0.0011) -[2023-11-28 10:13:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195379200. Throughput: 0: 2641.4, 1: 2604.7. Samples: 195392872. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:28,445][86177] Avg episode reward: [(0, '-551.240'), (1, '-507.120')] -[2023-11-28 10:13:28,904][87426] Updated weights for policy 1, policy_version 381450 (0.0012) -[2023-11-28 10:13:29,285][87426] Updated weights for policy 1, policy_version 381460 (0.0011) -[2023-11-28 10:13:29,669][87426] Updated weights for policy 1, policy_version 381470 (0.0011) -[2023-11-28 10:13:30,106][87424] Updated weights for policy 0, policy_version 381769 (0.0011) -[2023-11-28 10:13:30,506][87424] Updated weights for policy 0, policy_version 381779 (0.0011) -[2023-11-28 10:13:30,887][87424] Updated weights for policy 0, policy_version 381789 (0.0011) -[2023-11-28 10:13:31,595][87426] Updated weights for policy 1, policy_version 381480 (0.0011) -[2023-11-28 10:13:31,983][87426] Updated weights for policy 1, policy_version 381490 (0.0011) -[2023-11-28 10:13:32,357][87426] Updated weights for policy 1, policy_version 381500 (0.0010) -[2023-11-28 10:13:32,984][87424] Updated weights for policy 0, policy_version 381799 (0.0012) -[2023-11-28 10:13:33,365][87424] Updated weights for policy 0, policy_version 381809 (0.0007) -[2023-11-28 10:13:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195403776. Throughput: 0: 2647.8, 1: 2614.8. Samples: 195417624. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:33,445][86177] Avg episode reward: [(0, '-549.850'), (1, '-502.970')] -[2023-11-28 10:13:33,742][87424] Updated weights for policy 0, policy_version 381819 (0.0008) -[2023-11-28 10:13:34,498][87426] Updated weights for policy 1, policy_version 381510 (0.0008) -[2023-11-28 10:13:34,864][87426] Updated weights for policy 1, policy_version 381520 (0.0008) -[2023-11-28 10:13:35,244][87426] Updated weights for policy 1, policy_version 381530 (0.0009) -[2023-11-28 10:13:36,289][87424] Updated weights for policy 0, policy_version 381829 (0.0007) -[2023-11-28 10:13:36,681][87424] Updated weights for policy 0, policy_version 381839 (0.0008) -[2023-11-28 10:13:37,054][87424] Updated weights for policy 0, policy_version 381849 (0.0009) -[2023-11-28 10:13:37,148][87426] Updated weights for policy 1, policy_version 381540 (0.0010) -[2023-11-28 10:13:37,537][87426] Updated weights for policy 1, policy_version 381550 (0.0011) -[2023-11-28 10:13:37,906][87426] Updated weights for policy 1, policy_version 381560 (0.0012) -[2023-11-28 10:13:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 195436544. Throughput: 0: 2655.8, 1: 2637.4. Samples: 195450312. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:38,445][86177] Avg episode reward: [(0, '-552.540'), (1, '-502.340')] -[2023-11-28 10:13:39,054][87424] Updated weights for policy 0, policy_version 381859 (0.0011) -[2023-11-28 10:13:39,440][87424] Updated weights for policy 0, policy_version 381869 (0.0011) -[2023-11-28 10:13:39,817][87424] Updated weights for policy 0, policy_version 381879 (0.0008) -[2023-11-28 10:13:40,383][87426] Updated weights for policy 1, policy_version 381570 (0.0012) -[2023-11-28 10:13:40,765][87426] Updated weights for policy 1, policy_version 381580 (0.0012) -[2023-11-28 10:13:41,147][87426] Updated weights for policy 1, policy_version 381590 (0.0012) -[2023-11-28 10:13:41,512][87426] Updated weights for policy 1, policy_version 381600 (0.0012) -[2023-11-28 10:13:42,308][87424] Updated weights for policy 0, policy_version 381889 (0.0011) -[2023-11-28 10:13:42,684][87424] Updated weights for policy 0, policy_version 381899 (0.0009) -[2023-11-28 10:13:43,057][87424] Updated weights for policy 0, policy_version 381909 (0.0011) -[2023-11-28 10:13:43,442][87424] Updated weights for policy 0, policy_version 381919 (0.0012) -[2023-11-28 10:13:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 195452928. Throughput: 0: 2648.0, 1: 2619.7. Samples: 195473152. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:43,445][86177] Avg episode reward: [(0, '-552.840'), (1, '-498.710')] -[2023-11-28 10:13:44,002][87426] Updated weights for policy 1, policy_version 381610 (0.0011) -[2023-11-28 10:13:44,387][87426] Updated weights for policy 1, policy_version 381620 (0.0011) -[2023-11-28 10:13:44,772][87426] Updated weights for policy 1, policy_version 381630 (0.0012) -[2023-11-28 10:13:45,410][87424] Updated weights for policy 0, policy_version 381929 (0.0012) -[2023-11-28 10:13:45,789][87424] Updated weights for policy 0, policy_version 381939 (0.0012) -[2023-11-28 10:13:46,174][87424] Updated weights for policy 0, policy_version 381949 (0.0012) -[2023-11-28 10:13:47,149][87426] Updated weights for policy 1, policy_version 381640 (0.0012) -[2023-11-28 10:13:47,521][87426] Updated weights for policy 1, policy_version 381650 (0.0009) -[2023-11-28 10:13:47,905][87426] Updated weights for policy 1, policy_version 381660 (0.0007) -[2023-11-28 10:13:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195485696. Throughput: 0: 2650.5, 1: 2619.0. Samples: 195497772. Policy #0 lag: (min: 1.0, avg: 27.2, max: 44.0) -[2023-11-28 10:13:48,446][86177] Avg episode reward: [(0, '-545.720'), (1, '-498.500')] -[2023-11-28 10:13:48,481][87424] Updated weights for policy 0, policy_version 381959 (0.0009) -[2023-11-28 10:13:48,880][87424] Updated weights for policy 0, policy_version 381969 (0.0008) -[2023-11-28 10:13:49,253][87424] Updated weights for policy 0, policy_version 381979 (0.0012) -[2023-11-28 10:13:50,434][87426] Updated weights for policy 1, policy_version 381670 (0.0010) -[2023-11-28 10:13:50,805][87426] Updated weights for policy 1, policy_version 381680 (0.0012) -[2023-11-28 10:13:51,182][87426] Updated weights for policy 1, policy_version 381690 (0.0012) -[2023-11-28 10:13:51,478][87424] Updated weights for policy 0, policy_version 381989 (0.0012) -[2023-11-28 10:13:51,867][87424] Updated weights for policy 0, policy_version 381999 (0.0012) -[2023-11-28 10:13:52,247][87424] Updated weights for policy 0, policy_version 382009 (0.0012) -[2023-11-28 10:13:53,366][87426] Updated weights for policy 1, policy_version 381700 (0.0012) -[2023-11-28 10:13:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195510272. Throughput: 0: 2653.4, 1: 2606.7. Samples: 195528452. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:13:53,445][86177] Avg episode reward: [(0, '-561.710'), (1, '-498.640')] -[2023-11-28 10:13:53,754][87426] Updated weights for policy 1, policy_version 381710 (0.0011) -[2023-11-28 10:13:54,129][87426] Updated weights for policy 1, policy_version 381720 (0.0008) -[2023-11-28 10:13:54,478][87424] Updated weights for policy 0, policy_version 382019 (0.0012) -[2023-11-28 10:13:54,859][87424] Updated weights for policy 0, policy_version 382029 (0.0011) -[2023-11-28 10:13:55,235][87424] Updated weights for policy 0, policy_version 382039 (0.0007) -[2023-11-28 10:13:56,665][87426] Updated weights for policy 1, policy_version 381730 (0.0007) -[2023-11-28 10:13:57,042][87426] Updated weights for policy 1, policy_version 381740 (0.0008) -[2023-11-28 10:13:57,421][87426] Updated weights for policy 1, policy_version 381750 (0.0007) -[2023-11-28 10:13:57,490][87424] Updated weights for policy 0, policy_version 382049 (0.0009) -[2023-11-28 10:13:57,802][87426] Updated weights for policy 1, policy_version 381760 (0.0007) -[2023-11-28 10:13:57,874][87424] Updated weights for policy 0, policy_version 382059 (0.0011) -[2023-11-28 10:13:58,266][87424] Updated weights for policy 0, policy_version 382069 (0.0010) -[2023-11-28 10:13:58,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195534848. Throughput: 0: 2659.8, 1: 2614.5. Samples: 195551760. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:13:58,446][86177] Avg episode reward: [(0, '-557.580'), (1, '-498.420')] -[2023-11-28 10:13:58,650][87424] Updated weights for policy 0, policy_version 382079 (0.0012) -[2023-11-28 10:14:00,072][87426] Updated weights for policy 1, policy_version 381770 (0.0008) -[2023-11-28 10:14:00,452][87426] Updated weights for policy 1, policy_version 381780 (0.0007) -[2023-11-28 10:14:00,834][87426] Updated weights for policy 1, policy_version 381790 (0.0009) -[2023-11-28 10:14:01,190][87424] Updated weights for policy 0, policy_version 382089 (0.0012) -[2023-11-28 10:14:01,577][87424] Updated weights for policy 0, policy_version 382099 (0.0010) -[2023-11-28 10:14:01,947][87424] Updated weights for policy 0, policy_version 382109 (0.0011) -[2023-11-28 10:14:03,015][87426] Updated weights for policy 1, policy_version 381800 (0.0009) -[2023-11-28 10:14:03,394][87426] Updated weights for policy 1, policy_version 381810 (0.0009) -[2023-11-28 10:14:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 195559424. Throughput: 0: 2664.3, 1: 2604.2. Samples: 195575328. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:03,445][86177] Avg episode reward: [(0, '-559.580'), (1, '-499.740')] -[2023-11-28 10:14:03,776][87426] Updated weights for policy 1, policy_version 381820 (0.0008) -[2023-11-28 10:14:04,204][87424] Updated weights for policy 0, policy_version 382119 (0.0012) -[2023-11-28 10:14:04,586][87424] Updated weights for policy 0, policy_version 382129 (0.0011) -[2023-11-28 10:14:04,968][87424] Updated weights for policy 0, policy_version 382139 (0.0010) -[2023-11-28 10:14:05,677][87426] Updated weights for policy 1, policy_version 381830 (0.0008) -[2023-11-28 10:14:06,060][87426] Updated weights for policy 1, policy_version 381840 (0.0009) -[2023-11-28 10:14:06,443][87426] Updated weights for policy 1, policy_version 381850 (0.0010) -[2023-11-28 10:14:07,380][87424] Updated weights for policy 0, policy_version 382149 (0.0009) -[2023-11-28 10:14:07,759][87424] Updated weights for policy 0, policy_version 382159 (0.0009) -[2023-11-28 10:14:08,130][87424] Updated weights for policy 0, policy_version 382169 (0.0008) -[2023-11-28 10:14:08,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195592192. Throughput: 0: 2646.8, 1: 2621.2. Samples: 195606508. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:08,445][86177] Avg episode reward: [(0, '-556.980'), (1, '-501.820')] -[2023-11-28 10:14:08,770][87426] Updated weights for policy 1, policy_version 381860 (0.0010) -[2023-11-28 10:14:09,155][87426] Updated weights for policy 1, policy_version 381870 (0.0011) -[2023-11-28 10:14:09,523][87426] Updated weights for policy 1, policy_version 381880 (0.0011) -[2023-11-28 10:14:10,635][87424] Updated weights for policy 0, policy_version 382179 (0.0009) -[2023-11-28 10:14:11,014][87424] Updated weights for policy 0, policy_version 382189 (0.0012) -[2023-11-28 10:14:11,396][87424] Updated weights for policy 0, policy_version 382199 (0.0012) -[2023-11-28 10:14:11,570][87426] Updated weights for policy 1, policy_version 381890 (0.0011) -[2023-11-28 10:14:11,950][87426] Updated weights for policy 1, policy_version 381900 (0.0012) -[2023-11-28 10:14:12,325][87426] Updated weights for policy 1, policy_version 381910 (0.0011) -[2023-11-28 10:14:12,703][87426] Updated weights for policy 1, policy_version 381920 (0.0011) -[2023-11-28 10:14:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195616768. Throughput: 0: 2636.6, 1: 2646.2. Samples: 195630600. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:13,445][86177] Avg episode reward: [(0, '-556.660'), (1, '-504.450')] -[2023-11-28 10:14:13,756][87424] Updated weights for policy 0, policy_version 382209 (0.0011) -[2023-11-28 10:14:14,139][87424] Updated weights for policy 0, policy_version 382219 (0.0012) -[2023-11-28 10:14:14,515][87424] Updated weights for policy 0, policy_version 382229 (0.0011) -[2023-11-28 10:14:14,901][87424] Updated weights for policy 0, policy_version 382239 (0.0010) -[2023-11-28 10:14:15,100][87426] Updated weights for policy 1, policy_version 381930 (0.0012) -[2023-11-28 10:14:15,479][87426] Updated weights for policy 1, policy_version 381940 (0.0012) -[2023-11-28 10:14:15,864][87426] Updated weights for policy 1, policy_version 381950 (0.0012) -[2023-11-28 10:14:16,694][87424] Updated weights for policy 0, policy_version 382249 (0.0007) -[2023-11-28 10:14:17,075][87424] Updated weights for policy 0, policy_version 382259 (0.0007) -[2023-11-28 10:14:17,457][87424] Updated weights for policy 0, policy_version 382269 (0.0009) -[2023-11-28 10:14:18,128][87426] Updated weights for policy 1, policy_version 381960 (0.0011) -[2023-11-28 10:14:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195641344. Throughput: 0: 2622.4, 1: 2634.4. Samples: 195654180. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:18,445][86177] Avg episode reward: [(0, '-549.330'), (1, '-504.520')] -[2023-11-28 10:14:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000382272_97861632.pth... -[2023-11-28 10:14:18,487][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000379776_97222656.pth -[2023-11-28 10:14:18,504][87426] Updated weights for policy 1, policy_version 381970 (0.0007) -[2023-11-28 10:14:18,893][87426] Updated weights for policy 1, policy_version 381980 (0.0008) -[2023-11-28 10:14:19,032][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000381984_97787904.pth... -[2023-11-28 10:14:19,062][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000379456_97140736.pth -[2023-11-28 10:14:19,640][87424] Updated weights for policy 0, policy_version 382279 (0.0010) -[2023-11-28 10:14:20,028][87424] Updated weights for policy 0, policy_version 382289 (0.0011) -[2023-11-28 10:14:20,401][87424] Updated weights for policy 0, policy_version 382299 (0.0009) -[2023-11-28 10:14:21,144][87426] Updated weights for policy 1, policy_version 381990 (0.0010) -[2023-11-28 10:14:21,515][87426] Updated weights for policy 1, policy_version 382000 (0.0009) -[2023-11-28 10:14:21,901][87426] Updated weights for policy 1, policy_version 382010 (0.0010) -[2023-11-28 10:14:22,953][87424] Updated weights for policy 0, policy_version 382309 (0.0010) -[2023-11-28 10:14:23,331][87424] Updated weights for policy 0, policy_version 382319 (0.0008) -[2023-11-28 10:14:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 195665920. Throughput: 0: 2601.3, 1: 2621.7. Samples: 195685348. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:23,445][86177] Avg episode reward: [(0, '-572.950'), (1, '-501.920')] -[2023-11-28 10:14:23,722][87424] Updated weights for policy 0, policy_version 382329 (0.0008) -[2023-11-28 10:14:24,051][87426] Updated weights for policy 1, policy_version 382020 (0.0010) -[2023-11-28 10:14:24,433][87426] Updated weights for policy 1, policy_version 382030 (0.0012) -[2023-11-28 10:14:24,804][87426] Updated weights for policy 1, policy_version 382040 (0.0012) -[2023-11-28 10:14:25,851][87424] Updated weights for policy 0, policy_version 382339 (0.0008) -[2023-11-28 10:14:26,239][87424] Updated weights for policy 0, policy_version 382349 (0.0008) -[2023-11-28 10:14:26,615][87424] Updated weights for policy 0, policy_version 382359 (0.0007) -[2023-11-28 10:14:26,999][87426] Updated weights for policy 1, policy_version 382050 (0.0011) -[2023-11-28 10:14:27,381][87426] Updated weights for policy 1, policy_version 382060 (0.0007) -[2023-11-28 10:14:27,767][87426] Updated weights for policy 1, policy_version 382070 (0.0007) -[2023-11-28 10:14:28,151][87426] Updated weights for policy 1, policy_version 382080 (0.0008) -[2023-11-28 10:14:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195698688. Throughput: 0: 2598.0, 1: 2655.4. Samples: 195709556. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:28,446][86177] Avg episode reward: [(0, '-578.660'), (1, '-500.460')] -[2023-11-28 10:14:29,117][87424] Updated weights for policy 0, policy_version 382369 (0.0009) -[2023-11-28 10:14:29,491][87424] Updated weights for policy 0, policy_version 382379 (0.0011) -[2023-11-28 10:14:29,887][87424] Updated weights for policy 0, policy_version 382389 (0.0011) -[2023-11-28 10:14:30,012][87426] Updated weights for policy 1, policy_version 382090 (0.0010) -[2023-11-28 10:14:30,260][87424] Updated weights for policy 0, policy_version 382399 (0.0011) -[2023-11-28 10:14:30,396][87426] Updated weights for policy 1, policy_version 382100 (0.0011) -[2023-11-28 10:14:30,768][87426] Updated weights for policy 1, policy_version 382110 (0.0009) -[2023-11-28 10:14:32,700][87424] Updated weights for policy 0, policy_version 382409 (0.0009) -[2023-11-28 10:14:33,013][87426] Updated weights for policy 1, policy_version 382120 (0.0009) -[2023-11-28 10:14:33,085][87424] Updated weights for policy 0, policy_version 382419 (0.0009) -[2023-11-28 10:14:33,394][87426] Updated weights for policy 1, policy_version 382130 (0.0010) -[2023-11-28 10:14:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 195715072. Throughput: 0: 2566.3, 1: 2649.1. Samples: 195732464. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:33,445][86177] Avg episode reward: [(0, '-576.860'), (1, '-496.460')] -[2023-11-28 10:14:33,469][87424] Updated weights for policy 0, policy_version 382429 (0.0011) -[2023-11-28 10:14:33,775][87426] Updated weights for policy 1, policy_version 382140 (0.0011) -[2023-11-28 10:14:35,873][87424] Updated weights for policy 0, policy_version 382439 (0.0012) -[2023-11-28 10:14:36,191][87426] Updated weights for policy 1, policy_version 382150 (0.0012) -[2023-11-28 10:14:36,258][87424] Updated weights for policy 0, policy_version 382449 (0.0008) -[2023-11-28 10:14:36,560][87426] Updated weights for policy 1, policy_version 382160 (0.0011) -[2023-11-28 10:14:36,649][87424] Updated weights for policy 0, policy_version 382459 (0.0011) -[2023-11-28 10:14:36,946][87426] Updated weights for policy 1, policy_version 382170 (0.0012) -[2023-11-28 10:14:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 195747840. Throughput: 0: 2589.8, 1: 2660.6. Samples: 195764720. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:38,445][86177] Avg episode reward: [(0, '-602.000'), (1, '-496.480')] -[2023-11-28 10:14:39,084][87426] Updated weights for policy 1, policy_version 382180 (0.0012) -[2023-11-28 10:14:39,146][87424] Updated weights for policy 0, policy_version 382469 (0.0012) -[2023-11-28 10:14:39,464][87426] Updated weights for policy 1, policy_version 382190 (0.0011) -[2023-11-28 10:14:39,521][87424] Updated weights for policy 0, policy_version 382479 (0.0011) -[2023-11-28 10:14:39,845][87426] Updated weights for policy 1, policy_version 382200 (0.0011) -[2023-11-28 10:14:39,914][87424] Updated weights for policy 0, policy_version 382489 (0.0010) -[2023-11-28 10:14:41,989][87426] Updated weights for policy 1, policy_version 382210 (0.0009) -[2023-11-28 10:14:42,175][87424] Updated weights for policy 0, policy_version 382499 (0.0012) -[2023-11-28 10:14:42,366][87426] Updated weights for policy 1, policy_version 382220 (0.0009) -[2023-11-28 10:14:42,562][87424] Updated weights for policy 0, policy_version 382509 (0.0011) -[2023-11-28 10:14:42,742][87426] Updated weights for policy 1, policy_version 382230 (0.0008) -[2023-11-28 10:14:42,941][87424] Updated weights for policy 0, policy_version 382519 (0.0012) -[2023-11-28 10:14:43,118][87426] Updated weights for policy 1, policy_version 382240 (0.0016) -[2023-11-28 10:14:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 195780608. Throughput: 0: 2594.8, 1: 2691.0. Samples: 195789616. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:43,445][86177] Avg episode reward: [(0, '-579.690'), (1, '-495.930')] -[2023-11-28 10:14:44,809][87424] Updated weights for policy 0, policy_version 382529 (0.0009) -[2023-11-28 10:14:45,196][87424] Updated weights for policy 0, policy_version 382539 (0.0012) -[2023-11-28 10:14:45,545][87426] Updated weights for policy 1, policy_version 382250 (0.0011) -[2023-11-28 10:14:45,588][87424] Updated weights for policy 0, policy_version 382549 (0.0011) -[2023-11-28 10:14:45,925][87426] Updated weights for policy 1, policy_version 382260 (0.0012) -[2023-11-28 10:14:45,968][87424] Updated weights for policy 0, policy_version 382559 (0.0011) -[2023-11-28 10:14:46,309][87426] Updated weights for policy 1, policy_version 382270 (0.0011) -[2023-11-28 10:14:47,655][87424] Updated weights for policy 0, policy_version 382569 (0.0008) -[2023-11-28 10:14:48,033][87424] Updated weights for policy 0, policy_version 382579 (0.0011) -[2023-11-28 10:14:48,414][87424] Updated weights for policy 0, policy_version 382589 (0.0011) -[2023-11-28 10:14:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 195796992. Throughput: 0: 2614.5, 1: 2701.5. Samples: 195814548. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:48,445][86177] Avg episode reward: [(0, '-579.740'), (1, '-494.130')] -[2023-11-28 10:14:48,710][87426] Updated weights for policy 1, policy_version 382280 (0.0012) -[2023-11-28 10:14:49,089][87426] Updated weights for policy 1, policy_version 382290 (0.0009) -[2023-11-28 10:14:49,463][87426] Updated weights for policy 1, policy_version 382300 (0.0007) -[2023-11-28 10:14:50,905][87424] Updated weights for policy 0, policy_version 382599 (0.0012) -[2023-11-28 10:14:51,280][87424] Updated weights for policy 0, policy_version 382609 (0.0010) -[2023-11-28 10:14:51,657][87424] Updated weights for policy 0, policy_version 382619 (0.0010) -[2023-11-28 10:14:51,706][87426] Updated weights for policy 1, policy_version 382310 (0.0010) -[2023-11-28 10:14:52,083][87426] Updated weights for policy 1, policy_version 382320 (0.0011) -[2023-11-28 10:14:52,465][87426] Updated weights for policy 1, policy_version 382330 (0.0012) -[2023-11-28 10:14:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195829760. Throughput: 0: 2655.8, 1: 2687.2. Samples: 195846944. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:53,445][86177] Avg episode reward: [(0, '-580.430'), (1, '-497.270')] -[2023-11-28 10:14:54,129][87424] Updated weights for policy 0, policy_version 382629 (0.0011) -[2023-11-28 10:14:54,505][87424] Updated weights for policy 0, policy_version 382639 (0.0012) -[2023-11-28 10:14:54,569][87426] Updated weights for policy 1, policy_version 382340 (0.0010) -[2023-11-28 10:14:54,885][87424] Updated weights for policy 0, policy_version 382649 (0.0011) -[2023-11-28 10:14:54,939][87426] Updated weights for policy 1, policy_version 382350 (0.0009) -[2023-11-28 10:14:55,316][87426] Updated weights for policy 1, policy_version 382360 (0.0008) -[2023-11-28 10:14:56,802][87424] Updated weights for policy 0, policy_version 382659 (0.0011) -[2023-11-28 10:14:57,201][87424] Updated weights for policy 0, policy_version 382669 (0.0012) -[2023-11-28 10:14:57,385][87426] Updated weights for policy 1, policy_version 382370 (0.0008) -[2023-11-28 10:14:57,580][87424] Updated weights for policy 0, policy_version 382679 (0.0011) -[2023-11-28 10:14:57,763][87426] Updated weights for policy 1, policy_version 382380 (0.0011) -[2023-11-28 10:14:58,141][87426] Updated weights for policy 1, policy_version 382390 (0.0010) -[2023-11-28 10:14:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195854336. Throughput: 0: 2665.6, 1: 2669.5. Samples: 195870680. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:14:58,445][86177] Avg episode reward: [(0, '-589.640'), (1, '-500.630')] -[2023-11-28 10:14:58,528][87426] Updated weights for policy 1, policy_version 382400 (0.0012) -[2023-11-28 10:14:59,449][87424] Updated weights for policy 0, policy_version 382689 (0.0012) -[2023-11-28 10:14:59,831][87424] Updated weights for policy 0, policy_version 382699 (0.0011) -[2023-11-28 10:15:00,219][87424] Updated weights for policy 0, policy_version 382709 (0.0012) -[2023-11-28 10:15:00,599][87424] Updated weights for policy 0, policy_version 382719 (0.0012) -[2023-11-28 10:15:00,671][87426] Updated weights for policy 1, policy_version 382410 (0.0014) -[2023-11-28 10:15:01,044][87426] Updated weights for policy 1, policy_version 382420 (0.0010) -[2023-11-28 10:15:01,424][87426] Updated weights for policy 1, policy_version 382430 (0.0010) -[2023-11-28 10:15:02,912][87424] Updated weights for policy 0, policy_version 382729 (0.0011) -[2023-11-28 10:15:03,285][87424] Updated weights for policy 0, policy_version 382739 (0.0009) -[2023-11-28 10:15:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 195878912. Throughput: 0: 2683.6, 1: 2668.9. Samples: 195895044. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:15:03,445][86177] Avg episode reward: [(0, '-590.340'), (1, '-498.450')] -[2023-11-28 10:15:03,621][87426] Updated weights for policy 1, policy_version 382440 (0.0011) -[2023-11-28 10:15:03,677][87424] Updated weights for policy 0, policy_version 382749 (0.0007) -[2023-11-28 10:15:03,984][87426] Updated weights for policy 1, policy_version 382450 (0.0009) -[2023-11-28 10:15:04,373][87426] Updated weights for policy 1, policy_version 382460 (0.0010) -[2023-11-28 10:15:05,830][87424] Updated weights for policy 0, policy_version 382759 (0.0011) -[2023-11-28 10:15:06,218][87424] Updated weights for policy 0, policy_version 382769 (0.0012) -[2023-11-28 10:15:06,608][87424] Updated weights for policy 0, policy_version 382779 (0.0012) -[2023-11-28 10:15:06,918][87426] Updated weights for policy 1, policy_version 382470 (0.0011) -[2023-11-28 10:15:07,287][87426] Updated weights for policy 1, policy_version 382480 (0.0011) -[2023-11-28 10:15:07,673][87426] Updated weights for policy 1, policy_version 382490 (0.0012) -[2023-11-28 10:15:08,430][87424] Updated weights for policy 0, policy_version 382789 (0.0012) -[2023-11-28 10:15:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195911680. Throughput: 0: 2711.8, 1: 2684.6. Samples: 195928188. Policy #0 lag: (min: 31.0, avg: 36.9, max: 63.0) -[2023-11-28 10:15:08,445][86177] Avg episode reward: [(0, '-574.550'), (1, '-498.590')] -[2023-11-28 10:15:08,809][87424] Updated weights for policy 0, policy_version 382799 (0.0012) -[2023-11-28 10:15:09,209][87424] Updated weights for policy 0, policy_version 382809 (0.0011) -[2023-11-28 10:15:09,584][87426] Updated weights for policy 1, policy_version 382500 (0.0012) -[2023-11-28 10:15:09,963][87426] Updated weights for policy 1, policy_version 382510 (0.0011) -[2023-11-28 10:15:10,330][87426] Updated weights for policy 1, policy_version 382520 (0.0010) -[2023-11-28 10:15:11,546][87424] Updated weights for policy 0, policy_version 382819 (0.0010) -[2023-11-28 10:15:11,926][87424] Updated weights for policy 0, policy_version 382829 (0.0011) -[2023-11-28 10:15:12,307][87424] Updated weights for policy 0, policy_version 382839 (0.0012) -[2023-11-28 10:15:12,716][87426] Updated weights for policy 1, policy_version 382530 (0.0009) -[2023-11-28 10:15:13,102][87426] Updated weights for policy 1, policy_version 382540 (0.0010) -[2023-11-28 10:15:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195936256. Throughput: 0: 2707.0, 1: 2693.7. Samples: 195952588. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:13,446][86177] Avg episode reward: [(0, '-573.370'), (1, '-498.560')] -[2023-11-28 10:15:13,474][87426] Updated weights for policy 1, policy_version 382550 (0.0007) -[2023-11-28 10:15:13,860][87426] Updated weights for policy 1, policy_version 382560 (0.0007) -[2023-11-28 10:15:14,912][87424] Updated weights for policy 0, policy_version 382849 (0.0012) -[2023-11-28 10:15:15,291][87424] Updated weights for policy 0, policy_version 382859 (0.0012) -[2023-11-28 10:15:15,660][87424] Updated weights for policy 0, policy_version 382869 (0.0012) -[2023-11-28 10:15:15,731][87426] Updated weights for policy 1, policy_version 382570 (0.0011) -[2023-11-28 10:15:16,042][87424] Updated weights for policy 0, policy_version 382879 (0.0012) -[2023-11-28 10:15:16,109][87426] Updated weights for policy 1, policy_version 382580 (0.0011) -[2023-11-28 10:15:16,478][87426] Updated weights for policy 1, policy_version 382590 (0.0011) -[2023-11-28 10:15:17,924][87424] Updated weights for policy 0, policy_version 382889 (0.0012) -[2023-11-28 10:15:18,314][87424] Updated weights for policy 0, policy_version 382899 (0.0012) -[2023-11-28 10:15:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 195960832. Throughput: 0: 2697.9, 1: 2700.5. Samples: 195975396. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:18,445][86177] Avg episode reward: [(0, '-525.000'), (1, '-501.600')] -[2023-11-28 10:15:18,688][87426] Updated weights for policy 1, policy_version 382600 (0.0009) -[2023-11-28 10:15:18,696][87424] Updated weights for policy 0, policy_version 382909 (0.0012) -[2023-11-28 10:15:19,072][87426] Updated weights for policy 1, policy_version 382610 (0.0010) -[2023-11-28 10:15:19,449][87426] Updated weights for policy 1, policy_version 382620 (0.0011) -[2023-11-28 10:15:21,202][87424] Updated weights for policy 0, policy_version 382919 (0.0012) -[2023-11-28 10:15:21,539][87426] Updated weights for policy 1, policy_version 382630 (0.0010) -[2023-11-28 10:15:21,583][87424] Updated weights for policy 0, policy_version 382929 (0.0012) -[2023-11-28 10:15:21,918][87426] Updated weights for policy 1, policy_version 382640 (0.0013) -[2023-11-28 10:15:21,963][87424] Updated weights for policy 0, policy_version 382939 (0.0011) -[2023-11-28 10:15:22,304][87426] Updated weights for policy 1, policy_version 382650 (0.0011) -[2023-11-28 10:15:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 195993600. Throughput: 0: 2682.3, 1: 2731.6. Samples: 196008344. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:23,445][86177] Avg episode reward: [(0, '-530.500'), (1, '-502.380')] -[2023-11-28 10:15:24,452][87424] Updated weights for policy 0, policy_version 382949 (0.0009) -[2023-11-28 10:15:24,694][87426] Updated weights for policy 1, policy_version 382660 (0.0011) -[2023-11-28 10:15:24,844][87424] Updated weights for policy 0, policy_version 382959 (0.0007) -[2023-11-28 10:15:25,069][87426] Updated weights for policy 1, policy_version 382670 (0.0012) -[2023-11-28 10:15:25,223][87424] Updated weights for policy 0, policy_version 382969 (0.0007) -[2023-11-28 10:15:25,447][87426] Updated weights for policy 1, policy_version 382680 (0.0010) -[2023-11-28 10:15:27,208][87426] Updated weights for policy 1, policy_version 382690 (0.0012) -[2023-11-28 10:15:27,464][87424] Updated weights for policy 0, policy_version 382979 (0.0008) -[2023-11-28 10:15:27,583][87426] Updated weights for policy 1, policy_version 382700 (0.0011) -[2023-11-28 10:15:27,857][87424] Updated weights for policy 0, policy_version 382989 (0.0008) -[2023-11-28 10:15:27,967][87426] Updated weights for policy 1, policy_version 382710 (0.0011) -[2023-11-28 10:15:28,226][87424] Updated weights for policy 0, policy_version 382999 (0.0009) -[2023-11-28 10:15:28,337][87426] Updated weights for policy 1, policy_version 382720 (0.0010) -[2023-11-28 10:15:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 196018176. Throughput: 0: 2689.8, 1: 2730.7. Samples: 196033536. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:28,446][86177] Avg episode reward: [(0, '-564.310'), (1, '-502.750')] -[2023-11-28 10:15:29,993][87426] Updated weights for policy 1, policy_version 382730 (0.0010) -[2023-11-28 10:15:30,378][87426] Updated weights for policy 1, policy_version 382740 (0.0011) -[2023-11-28 10:15:30,725][87424] Updated weights for policy 0, policy_version 383009 (0.0007) -[2023-11-28 10:15:30,759][87426] Updated weights for policy 1, policy_version 382750 (0.0011) -[2023-11-28 10:15:31,107][87424] Updated weights for policy 0, policy_version 383019 (0.0008) -[2023-11-28 10:15:31,492][87424] Updated weights for policy 0, policy_version 383029 (0.0007) -[2023-11-28 10:15:31,876][87424] Updated weights for policy 0, policy_version 383039 (0.0009) -[2023-11-28 10:15:32,986][87426] Updated weights for policy 1, policy_version 382760 (0.0010) -[2023-11-28 10:15:33,367][87426] Updated weights for policy 1, policy_version 382770 (0.0012) -[2023-11-28 10:15:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 196042752. Throughput: 0: 2666.7, 1: 2737.8. Samples: 196057748. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:33,445][86177] Avg episode reward: [(0, '-564.050'), (1, '-503.750')] -[2023-11-28 10:15:33,755][87426] Updated weights for policy 1, policy_version 382780 (0.0012) -[2023-11-28 10:15:33,870][87424] Updated weights for policy 0, policy_version 383049 (0.0010) -[2023-11-28 10:15:34,250][87424] Updated weights for policy 0, policy_version 383059 (0.0007) -[2023-11-28 10:15:34,640][87424] Updated weights for policy 0, policy_version 383069 (0.0009) -[2023-11-28 10:15:36,157][87426] Updated weights for policy 1, policy_version 382790 (0.0009) -[2023-11-28 10:15:36,535][87426] Updated weights for policy 1, policy_version 382800 (0.0007) -[2023-11-28 10:15:36,771][87424] Updated weights for policy 0, policy_version 383079 (0.0010) -[2023-11-28 10:15:36,914][87426] Updated weights for policy 1, policy_version 382810 (0.0011) -[2023-11-28 10:15:37,154][87424] Updated weights for policy 0, policy_version 383089 (0.0011) -[2023-11-28 10:15:37,534][87424] Updated weights for policy 0, policy_version 383099 (0.0010) -[2023-11-28 10:15:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 196075520. Throughput: 0: 2660.8, 1: 2736.1. Samples: 196089804. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:38,445][86177] Avg episode reward: [(0, '-576.380'), (1, '-498.940')] -[2023-11-28 10:15:39,459][87426] Updated weights for policy 1, policy_version 382820 (0.0011) -[2023-11-28 10:15:39,557][87424] Updated weights for policy 0, policy_version 383109 (0.0011) -[2023-11-28 10:15:39,838][87426] Updated weights for policy 1, policy_version 382830 (0.0012) -[2023-11-28 10:15:39,935][87424] Updated weights for policy 0, policy_version 383119 (0.0012) -[2023-11-28 10:15:40,216][87426] Updated weights for policy 1, policy_version 382840 (0.0012) -[2023-11-28 10:15:40,323][87424] Updated weights for policy 0, policy_version 383129 (0.0011) -[2023-11-28 10:15:42,670][87426] Updated weights for policy 1, policy_version 382850 (0.0009) -[2023-11-28 10:15:42,721][87424] Updated weights for policy 0, policy_version 383139 (0.0010) -[2023-11-28 10:15:43,050][87426] Updated weights for policy 1, policy_version 382860 (0.0011) -[2023-11-28 10:15:43,095][87424] Updated weights for policy 0, policy_version 383149 (0.0011) -[2023-11-28 10:15:43,424][87426] Updated weights for policy 1, policy_version 382870 (0.0010) -[2023-11-28 10:15:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 196091904. Throughput: 0: 2662.0, 1: 2722.1. Samples: 196112964. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:43,445][86177] Avg episode reward: [(0, '-572.310'), (1, '-502.220')] -[2023-11-28 10:15:43,486][87424] Updated weights for policy 0, policy_version 383159 (0.0010) -[2023-11-28 10:15:43,811][87426] Updated weights for policy 1, policy_version 382880 (0.0010) -[2023-11-28 10:15:45,759][87424] Updated weights for policy 0, policy_version 383169 (0.0008) -[2023-11-28 10:15:46,144][87424] Updated weights for policy 0, policy_version 383179 (0.0010) -[2023-11-28 10:15:46,373][87426] Updated weights for policy 1, policy_version 382890 (0.0007) -[2023-11-28 10:15:46,530][87424] Updated weights for policy 0, policy_version 383189 (0.0009) -[2023-11-28 10:15:46,754][87426] Updated weights for policy 1, policy_version 382900 (0.0010) -[2023-11-28 10:15:46,912][87424] Updated weights for policy 0, policy_version 383199 (0.0012) -[2023-11-28 10:15:47,130][87426] Updated weights for policy 1, policy_version 382910 (0.0008) -[2023-11-28 10:15:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 196124672. Throughput: 0: 2656.1, 1: 2709.3. Samples: 196136488. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:48,445][86177] Avg episode reward: [(0, '-535.490'), (1, '-505.710')] -[2023-11-28 10:15:48,965][87424] Updated weights for policy 0, policy_version 383209 (0.0012) -[2023-11-28 10:15:49,345][87424] Updated weights for policy 0, policy_version 383219 (0.0010) -[2023-11-28 10:15:49,440][87426] Updated weights for policy 1, policy_version 382920 (0.0010) -[2023-11-28 10:15:49,731][87424] Updated weights for policy 0, policy_version 383229 (0.0009) -[2023-11-28 10:15:49,826][87426] Updated weights for policy 1, policy_version 382930 (0.0011) -[2023-11-28 10:15:50,192][87426] Updated weights for policy 1, policy_version 382940 (0.0011) -[2023-11-28 10:15:52,055][87424] Updated weights for policy 0, policy_version 383239 (0.0011) -[2023-11-28 10:15:52,432][87424] Updated weights for policy 0, policy_version 383249 (0.0012) -[2023-11-28 10:15:52,632][87426] Updated weights for policy 1, policy_version 382950 (0.0009) -[2023-11-28 10:15:52,815][87424] Updated weights for policy 0, policy_version 383259 (0.0011) -[2023-11-28 10:15:53,008][87426] Updated weights for policy 1, policy_version 382960 (0.0010) -[2023-11-28 10:15:53,390][87426] Updated weights for policy 1, policy_version 382970 (0.0012) -[2023-11-28 10:15:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196149248. Throughput: 0: 2639.8, 1: 2695.5. Samples: 196168276. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:53,445][86177] Avg episode reward: [(0, '-533.020'), (1, '-507.220')] -[2023-11-28 10:15:55,006][87424] Updated weights for policy 0, policy_version 383269 (0.0009) -[2023-11-28 10:15:55,340][87426] Updated weights for policy 1, policy_version 382980 (0.0012) -[2023-11-28 10:15:55,384][87424] Updated weights for policy 0, policy_version 383279 (0.0010) -[2023-11-28 10:15:55,715][87426] Updated weights for policy 1, policy_version 382990 (0.0010) -[2023-11-28 10:15:55,763][87424] Updated weights for policy 0, policy_version 383289 (0.0011) -[2023-11-28 10:15:56,100][87426] Updated weights for policy 1, policy_version 383000 (0.0009) -[2023-11-28 10:15:58,155][87424] Updated weights for policy 0, policy_version 383299 (0.0008) -[2023-11-28 10:15:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196173824. Throughput: 0: 2655.1, 1: 2693.8. Samples: 196193288. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:15:58,445][86177] Avg episode reward: [(0, '-532.670'), (1, '-507.860')] -[2023-11-28 10:15:58,486][87426] Updated weights for policy 1, policy_version 383010 (0.0009) -[2023-11-28 10:15:58,538][87424] Updated weights for policy 0, policy_version 383309 (0.0008) -[2023-11-28 10:15:58,862][87426] Updated weights for policy 1, policy_version 383020 (0.0010) -[2023-11-28 10:15:58,913][87424] Updated weights for policy 0, policy_version 383319 (0.0011) -[2023-11-28 10:15:59,238][87426] Updated weights for policy 1, policy_version 383030 (0.0016) -[2023-11-28 10:15:59,616][87426] Updated weights for policy 1, policy_version 383040 (0.0010) -[2023-11-28 10:16:00,719][87424] Updated weights for policy 0, policy_version 383329 (0.0009) -[2023-11-28 10:16:01,101][87424] Updated weights for policy 0, policy_version 383339 (0.0012) -[2023-11-28 10:16:01,490][87424] Updated weights for policy 0, policy_version 383349 (0.0012) -[2023-11-28 10:16:01,591][87426] Updated weights for policy 1, policy_version 383050 (0.0011) -[2023-11-28 10:16:01,868][87424] Updated weights for policy 0, policy_version 383359 (0.0011) -[2023-11-28 10:16:01,972][87426] Updated weights for policy 1, policy_version 383060 (0.0009) -[2023-11-28 10:16:02,348][87426] Updated weights for policy 1, policy_version 383070 (0.0010) -[2023-11-28 10:16:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 196206592. Throughput: 0: 2694.1, 1: 2694.7. Samples: 196217892. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:16:03,445][86177] Avg episode reward: [(0, '-529.600'), (1, '-502.250')] -[2023-11-28 10:16:03,685][87424] Updated weights for policy 0, policy_version 383369 (0.0012) -[2023-11-28 10:16:04,057][87424] Updated weights for policy 0, policy_version 383379 (0.0012) -[2023-11-28 10:16:04,450][87424] Updated weights for policy 0, policy_version 383389 (0.0012) -[2023-11-28 10:16:04,738][87426] Updated weights for policy 1, policy_version 383080 (0.0011) -[2023-11-28 10:16:05,117][87426] Updated weights for policy 1, policy_version 383090 (0.0012) -[2023-11-28 10:16:05,500][87426] Updated weights for policy 1, policy_version 383100 (0.0011) -[2023-11-28 10:16:06,859][87424] Updated weights for policy 0, policy_version 383399 (0.0012) -[2023-11-28 10:16:07,238][87424] Updated weights for policy 0, policy_version 383409 (0.0012) -[2023-11-28 10:16:07,454][87426] Updated weights for policy 1, policy_version 383110 (0.0011) -[2023-11-28 10:16:07,620][87424] Updated weights for policy 0, policy_version 383419 (0.0010) -[2023-11-28 10:16:07,831][87426] Updated weights for policy 1, policy_version 383120 (0.0012) -[2023-11-28 10:16:08,203][87426] Updated weights for policy 1, policy_version 383130 (0.0012) -[2023-11-28 10:16:08,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 196239360. Throughput: 0: 2701.4, 1: 2668.7. Samples: 196250000. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:16:08,445][86177] Avg episode reward: [(0, '-539.400'), (1, '-495.730')] -[2023-11-28 10:16:09,878][87424] Updated weights for policy 0, policy_version 383429 (0.0011) -[2023-11-28 10:16:10,256][87424] Updated weights for policy 0, policy_version 383439 (0.0009) -[2023-11-28 10:16:10,451][87426] Updated weights for policy 1, policy_version 383140 (0.0011) -[2023-11-28 10:16:10,635][87424] Updated weights for policy 0, policy_version 383449 (0.0011) -[2023-11-28 10:16:10,837][87426] Updated weights for policy 1, policy_version 383150 (0.0012) -[2023-11-28 10:16:11,213][87426] Updated weights for policy 1, policy_version 383160 (0.0008) -[2023-11-28 10:16:13,017][87424] Updated weights for policy 0, policy_version 383459 (0.0010) -[2023-11-28 10:16:13,400][87424] Updated weights for policy 0, policy_version 383469 (0.0008) -[2023-11-28 10:16:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196255744. Throughput: 0: 2703.2, 1: 2638.9. Samples: 196273932. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:16:13,445][86177] Avg episode reward: [(0, '-541.990'), (1, '-494.730')] -[2023-11-28 10:16:13,527][87426] Updated weights for policy 1, policy_version 383170 (0.0008) -[2023-11-28 10:16:13,787][87424] Updated weights for policy 0, policy_version 383479 (0.0010) -[2023-11-28 10:16:13,905][87426] Updated weights for policy 1, policy_version 383180 (0.0010) -[2023-11-28 10:16:14,284][87426] Updated weights for policy 1, policy_version 383190 (0.0012) -[2023-11-28 10:16:14,675][87426] Updated weights for policy 1, policy_version 383200 (0.0012) -[2023-11-28 10:16:16,109][87424] Updated weights for policy 0, policy_version 383489 (0.0010) -[2023-11-28 10:16:16,490][87424] Updated weights for policy 0, policy_version 383499 (0.0007) -[2023-11-28 10:16:16,867][87424] Updated weights for policy 0, policy_version 383509 (0.0007) -[2023-11-28 10:16:16,940][87426] Updated weights for policy 1, policy_version 383210 (0.0009) -[2023-11-28 10:16:17,249][87424] Updated weights for policy 0, policy_version 383519 (0.0007) -[2023-11-28 10:16:17,306][87426] Updated weights for policy 1, policy_version 383220 (0.0007) -[2023-11-28 10:16:17,693][87426] Updated weights for policy 1, policy_version 383230 (0.0011) -[2023-11-28 10:16:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 196288512. Throughput: 0: 2712.7, 1: 2639.5. Samples: 196298596. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:16:18,445][86177] Avg episode reward: [(0, '-551.430'), (1, '-491.580')] -[2023-11-28 10:16:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000383520_98181120.pth... -[2023-11-28 10:16:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000383232_98107392.pth... -[2023-11-28 10:16:18,492][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000380736_97468416.pth -[2023-11-28 10:16:18,502][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000381024_97542144.pth -[2023-11-28 10:16:19,758][87424] Updated weights for policy 0, policy_version 383529 (0.0010) -[2023-11-28 10:16:19,901][87426] Updated weights for policy 1, policy_version 383240 (0.0011) -[2023-11-28 10:16:20,139][87424] Updated weights for policy 0, policy_version 383539 (0.0012) -[2023-11-28 10:16:20,274][87426] Updated weights for policy 1, policy_version 383250 (0.0012) -[2023-11-28 10:16:20,525][87424] Updated weights for policy 0, policy_version 383549 (0.0010) -[2023-11-28 10:16:20,659][87426] Updated weights for policy 1, policy_version 383260 (0.0011) -[2023-11-28 10:16:23,014][87424] Updated weights for policy 0, policy_version 383559 (0.0009) -[2023-11-28 10:16:23,104][87426] Updated weights for policy 1, policy_version 383270 (0.0010) -[2023-11-28 10:16:23,384][87424] Updated weights for policy 0, policy_version 383569 (0.0007) -[2023-11-28 10:16:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5304.0). Total num frames: 196304896. Throughput: 0: 2703.0, 1: 2637.8. Samples: 196330140. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:16:23,445][86177] Avg episode reward: [(0, '-555.320'), (1, '-494.080')] -[2023-11-28 10:16:23,477][87426] Updated weights for policy 1, policy_version 383280 (0.0011) -[2023-11-28 10:16:23,779][87424] Updated weights for policy 0, policy_version 383579 (0.0011) -[2023-11-28 10:16:23,861][87426] Updated weights for policy 1, policy_version 383290 (0.0011) -[2023-11-28 10:16:25,481][87424] Updated weights for policy 0, policy_version 383589 (0.0009) -[2023-11-28 10:16:25,870][87424] Updated weights for policy 0, policy_version 383599 (0.0007) -[2023-11-28 10:16:26,244][87426] Updated weights for policy 1, policy_version 383300 (0.0011) -[2023-11-28 10:16:26,259][87424] Updated weights for policy 0, policy_version 383609 (0.0009) -[2023-11-28 10:16:26,634][87426] Updated weights for policy 1, policy_version 383310 (0.0011) -[2023-11-28 10:16:27,013][87426] Updated weights for policy 1, policy_version 383320 (0.0012) -[2023-11-28 10:16:27,976][87424] Updated weights for policy 0, policy_version 383619 (0.0012) -[2023-11-28 10:16:28,360][87424] Updated weights for policy 0, policy_version 383629 (0.0007) -[2023-11-28 10:16:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196337664. Throughput: 0: 2708.4, 1: 2652.3. Samples: 196354196. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:16:28,445][86177] Avg episode reward: [(0, '-554.790'), (1, '-494.390')] -[2023-11-28 10:16:28,748][87424] Updated weights for policy 0, policy_version 383639 (0.0008) -[2023-11-28 10:16:29,526][87426] Updated weights for policy 1, policy_version 383330 (0.0012) -[2023-11-28 10:16:29,899][87426] Updated weights for policy 1, policy_version 383340 (0.0011) -[2023-11-28 10:16:30,279][87426] Updated weights for policy 1, policy_version 383350 (0.0011) -[2023-11-28 10:16:30,532][87424] Updated weights for policy 0, policy_version 383649 (0.0011) -[2023-11-28 10:16:30,653][87426] Updated weights for policy 1, policy_version 383360 (0.0010) -[2023-11-28 10:16:30,911][87424] Updated weights for policy 0, policy_version 383659 (0.0012) -[2023-11-28 10:16:31,287][87424] Updated weights for policy 0, policy_version 383669 (0.0012) -[2023-11-28 10:16:31,667][87424] Updated weights for policy 0, policy_version 383679 (0.0011) -[2023-11-28 10:16:32,833][87426] Updated weights for policy 1, policy_version 383370 (0.0012) -[2023-11-28 10:16:33,219][87426] Updated weights for policy 1, policy_version 383380 (0.0012) -[2023-11-28 10:16:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 196362240. Throughput: 0: 2708.6, 1: 2669.1. Samples: 196378484. Policy #0 lag: (min: 31.0, avg: 39.4, max: 63.0) -[2023-11-28 10:16:33,445][86177] Avg episode reward: [(0, '-555.850'), (1, '-495.210')] -[2023-11-28 10:16:33,595][87426] Updated weights for policy 1, policy_version 383390 (0.0010) -[2023-11-28 10:16:33,711][87424] Updated weights for policy 0, policy_version 383689 (0.0012) -[2023-11-28 10:16:34,097][87424] Updated weights for policy 0, policy_version 383699 (0.0012) -[2023-11-28 10:16:34,480][87424] Updated weights for policy 0, policy_version 383709 (0.0012) -[2023-11-28 10:16:36,084][87426] Updated weights for policy 1, policy_version 383400 (0.0011) -[2023-11-28 10:16:36,464][87426] Updated weights for policy 1, policy_version 383410 (0.0012) -[2023-11-28 10:16:36,615][87424] Updated weights for policy 0, policy_version 383719 (0.0012) -[2023-11-28 10:16:36,849][87426] Updated weights for policy 1, policy_version 383420 (0.0011) -[2023-11-28 10:16:36,996][87424] Updated weights for policy 0, policy_version 383729 (0.0011) -[2023-11-28 10:16:37,382][87424] Updated weights for policy 0, policy_version 383739 (0.0011) -[2023-11-28 10:16:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 196395008. Throughput: 0: 2732.4, 1: 2672.6. Samples: 196411504. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:16:38,445][86177] Avg episode reward: [(0, '-557.480'), (1, '-501.720')] -[2023-11-28 10:16:38,796][87426] Updated weights for policy 1, policy_version 383430 (0.0012) -[2023-11-28 10:16:39,169][87426] Updated weights for policy 1, policy_version 383440 (0.0011) -[2023-11-28 10:16:39,546][87426] Updated weights for policy 1, policy_version 383450 (0.0011) -[2023-11-28 10:16:39,961][87424] Updated weights for policy 0, policy_version 383749 (0.0010) -[2023-11-28 10:16:40,342][87424] Updated weights for policy 0, policy_version 383759 (0.0012) -[2023-11-28 10:16:40,724][87424] Updated weights for policy 0, policy_version 383769 (0.0012) -[2023-11-28 10:16:41,582][87426] Updated weights for policy 1, policy_version 383460 (0.0012) -[2023-11-28 10:16:41,938][87426] Updated weights for policy 1, policy_version 383470 (0.0011) -[2023-11-28 10:16:42,321][87426] Updated weights for policy 1, policy_version 383480 (0.0011) -[2023-11-28 10:16:43,254][87424] Updated weights for policy 0, policy_version 383779 (0.0012) -[2023-11-28 10:16:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 196419584. Throughput: 0: 2718.5, 1: 2647.6. Samples: 196434764. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:16:43,445][86177] Avg episode reward: [(0, '-551.090'), (1, '-501.010')] -[2023-11-28 10:16:43,637][87424] Updated weights for policy 0, policy_version 383789 (0.0012) -[2023-11-28 10:16:44,034][87424] Updated weights for policy 0, policy_version 383799 (0.0012) -[2023-11-28 10:16:44,900][87426] Updated weights for policy 1, policy_version 383490 (0.0009) -[2023-11-28 10:16:45,277][87426] Updated weights for policy 1, policy_version 383500 (0.0007) -[2023-11-28 10:16:45,654][87426] Updated weights for policy 1, policy_version 383510 (0.0011) -[2023-11-28 10:16:46,034][87426] Updated weights for policy 1, policy_version 383520 (0.0011) -[2023-11-28 10:16:46,367][87424] Updated weights for policy 0, policy_version 383809 (0.0008) -[2023-11-28 10:16:46,753][87424] Updated weights for policy 0, policy_version 383819 (0.0009) -[2023-11-28 10:16:47,138][87424] Updated weights for policy 0, policy_version 383829 (0.0011) -[2023-11-28 10:16:47,516][87424] Updated weights for policy 0, policy_version 383839 (0.0009) -[2023-11-28 10:16:48,440][87426] Updated weights for policy 1, policy_version 383530 (0.0008) -[2023-11-28 10:16:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196444160. Throughput: 0: 2688.2, 1: 2633.9. Samples: 196457384. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:16:48,445][86177] Avg episode reward: [(0, '-549.990'), (1, '-502.790')] -[2023-11-28 10:16:48,814][87426] Updated weights for policy 1, policy_version 383540 (0.0007) -[2023-11-28 10:16:49,199][87426] Updated weights for policy 1, policy_version 383550 (0.0008) -[2023-11-28 10:16:50,021][87424] Updated weights for policy 0, policy_version 383849 (0.0012) -[2023-11-28 10:16:50,389][87424] Updated weights for policy 0, policy_version 383859 (0.0012) -[2023-11-28 10:16:50,765][87424] Updated weights for policy 0, policy_version 383869 (0.0012) -[2023-11-28 10:16:51,257][87426] Updated weights for policy 1, policy_version 383560 (0.0008) -[2023-11-28 10:16:51,637][87426] Updated weights for policy 1, policy_version 383570 (0.0008) -[2023-11-28 10:16:52,037][87426] Updated weights for policy 1, policy_version 383580 (0.0010) -[2023-11-28 10:16:52,927][87424] Updated weights for policy 0, policy_version 383879 (0.0011) -[2023-11-28 10:16:53,305][87424] Updated weights for policy 0, policy_version 383889 (0.0011) -[2023-11-28 10:16:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196468736. Throughput: 0: 2665.6, 1: 2643.0. Samples: 196488888. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:16:53,445][86177] Avg episode reward: [(0, '-552.170'), (1, '-499.250')] -[2023-11-28 10:16:53,688][87424] Updated weights for policy 0, policy_version 383899 (0.0011) -[2023-11-28 10:16:54,093][87426] Updated weights for policy 1, policy_version 383590 (0.0009) -[2023-11-28 10:16:54,484][87426] Updated weights for policy 1, policy_version 383600 (0.0007) -[2023-11-28 10:16:54,866][87426] Updated weights for policy 1, policy_version 383610 (0.0009) -[2023-11-28 10:16:56,191][87424] Updated weights for policy 0, policy_version 383909 (0.0012) -[2023-11-28 10:16:56,573][87424] Updated weights for policy 0, policy_version 383919 (0.0012) -[2023-11-28 10:16:56,935][87426] Updated weights for policy 1, policy_version 383620 (0.0008) -[2023-11-28 10:16:56,958][87424] Updated weights for policy 0, policy_version 383929 (0.0012) -[2023-11-28 10:16:57,316][87426] Updated weights for policy 1, policy_version 383630 (0.0007) -[2023-11-28 10:16:57,695][87426] Updated weights for policy 1, policy_version 383640 (0.0007) -[2023-11-28 10:16:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 196501504. Throughput: 0: 2659.6, 1: 2685.2. Samples: 196514448. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:16:58,445][86177] Avg episode reward: [(0, '-551.010'), (1, '-496.870')] -[2023-11-28 10:16:59,187][87426] Updated weights for policy 1, policy_version 383650 (0.0007) -[2023-11-28 10:16:59,235][87424] Updated weights for policy 0, policy_version 383939 (0.0010) -[2023-11-28 10:16:59,580][87426] Updated weights for policy 1, policy_version 383660 (0.0011) -[2023-11-28 10:16:59,613][87424] Updated weights for policy 0, policy_version 383949 (0.0007) -[2023-11-28 10:16:59,966][87426] Updated weights for policy 1, policy_version 383670 (0.0010) -[2023-11-28 10:17:00,003][87424] Updated weights for policy 0, policy_version 383959 (0.0010) -[2023-11-28 10:17:00,335][87426] Updated weights for policy 1, policy_version 383680 (0.0008) -[2023-11-28 10:17:02,415][87424] Updated weights for policy 0, policy_version 383969 (0.0012) -[2023-11-28 10:17:02,522][87426] Updated weights for policy 1, policy_version 383690 (0.0010) -[2023-11-28 10:17:02,796][87424] Updated weights for policy 0, policy_version 383979 (0.0012) -[2023-11-28 10:17:02,901][87426] Updated weights for policy 1, policy_version 383700 (0.0011) -[2023-11-28 10:17:03,175][87424] Updated weights for policy 0, policy_version 383989 (0.0011) -[2023-11-28 10:17:03,286][87426] Updated weights for policy 1, policy_version 383710 (0.0011) -[2023-11-28 10:17:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196526080. Throughput: 0: 2669.3, 1: 2687.4. Samples: 196539644. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:03,445][86177] Avg episode reward: [(0, '-551.150'), (1, '-499.100')] -[2023-11-28 10:17:03,556][87424] Updated weights for policy 0, policy_version 383999 (0.0010) -[2023-11-28 10:17:05,385][87424] Updated weights for policy 0, policy_version 384009 (0.0010) -[2023-11-28 10:17:05,449][87426] Updated weights for policy 1, policy_version 383720 (0.0008) -[2023-11-28 10:17:05,773][87424] Updated weights for policy 0, policy_version 384019 (0.0008) -[2023-11-28 10:17:05,829][87426] Updated weights for policy 1, policy_version 383730 (0.0007) -[2023-11-28 10:17:06,165][87424] Updated weights for policy 0, policy_version 384029 (0.0010) -[2023-11-28 10:17:06,212][87426] Updated weights for policy 1, policy_version 383740 (0.0009) -[2023-11-28 10:17:08,129][87424] Updated weights for policy 0, policy_version 384039 (0.0009) -[2023-11-28 10:17:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 196550656. Throughput: 0: 2678.7, 1: 2692.8. Samples: 196571856. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:08,445][86177] Avg episode reward: [(0, '-554.870'), (1, '-513.740')] -[2023-11-28 10:17:08,508][87424] Updated weights for policy 0, policy_version 384049 (0.0010) -[2023-11-28 10:17:08,673][87426] Updated weights for policy 1, policy_version 383750 (0.0009) -[2023-11-28 10:17:08,890][87424] Updated weights for policy 0, policy_version 384059 (0.0009) -[2023-11-28 10:17:09,057][87426] Updated weights for policy 1, policy_version 383760 (0.0011) -[2023-11-28 10:17:09,439][87426] Updated weights for policy 1, policy_version 383770 (0.0012) -[2023-11-28 10:17:11,069][87424] Updated weights for policy 0, policy_version 384069 (0.0010) -[2023-11-28 10:17:11,449][87424] Updated weights for policy 0, policy_version 384079 (0.0012) -[2023-11-28 10:17:11,833][87424] Updated weights for policy 0, policy_version 384089 (0.0012) -[2023-11-28 10:17:11,967][87426] Updated weights for policy 1, policy_version 383780 (0.0011) -[2023-11-28 10:17:12,342][87426] Updated weights for policy 1, policy_version 383790 (0.0010) -[2023-11-28 10:17:12,720][87426] Updated weights for policy 1, policy_version 383800 (0.0011) -[2023-11-28 10:17:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 196583424. Throughput: 0: 2674.9, 1: 2689.2. Samples: 196595580. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:13,445][86177] Avg episode reward: [(0, '-575.940'), (1, '-555.060')] -[2023-11-28 10:17:14,172][87424] Updated weights for policy 0, policy_version 384099 (0.0011) -[2023-11-28 10:17:14,551][87424] Updated weights for policy 0, policy_version 384109 (0.0012) -[2023-11-28 10:17:14,932][87424] Updated weights for policy 0, policy_version 384119 (0.0012) -[2023-11-28 10:17:15,248][87426] Updated weights for policy 1, policy_version 383810 (0.0011) -[2023-11-28 10:17:15,632][87426] Updated weights for policy 1, policy_version 383820 (0.0010) -[2023-11-28 10:17:16,014][87426] Updated weights for policy 1, policy_version 383830 (0.0011) -[2023-11-28 10:17:16,386][87426] Updated weights for policy 1, policy_version 383840 (0.0012) -[2023-11-28 10:17:16,889][87424] Updated weights for policy 0, policy_version 384129 (0.0011) -[2023-11-28 10:17:17,272][87424] Updated weights for policy 0, policy_version 384139 (0.0012) -[2023-11-28 10:17:17,665][87424] Updated weights for policy 0, policy_version 384149 (0.0012) -[2023-11-28 10:17:18,039][87424] Updated weights for policy 0, policy_version 384159 (0.0012) -[2023-11-28 10:17:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 196608000. Throughput: 0: 2674.5, 1: 2673.6. Samples: 196619148. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:18,445][86177] Avg episode reward: [(0, '-569.160'), (1, '-554.470')] -[2023-11-28 10:17:18,721][87426] Updated weights for policy 1, policy_version 383850 (0.0012) -[2023-11-28 10:17:19,093][87426] Updated weights for policy 1, policy_version 383860 (0.0011) -[2023-11-28 10:17:19,494][87426] Updated weights for policy 1, policy_version 383870 (0.0011) -[2023-11-28 10:17:20,082][87424] Updated weights for policy 0, policy_version 384169 (0.0009) -[2023-11-28 10:17:20,459][87424] Updated weights for policy 0, policy_version 384179 (0.0010) -[2023-11-28 10:17:20,849][87424] Updated weights for policy 0, policy_version 384189 (0.0011) -[2023-11-28 10:17:21,675][87426] Updated weights for policy 1, policy_version 383880 (0.0011) -[2023-11-28 10:17:22,051][87426] Updated weights for policy 1, policy_version 383890 (0.0009) -[2023-11-28 10:17:22,430][87426] Updated weights for policy 1, policy_version 383900 (0.0009) -[2023-11-28 10:17:23,435][87424] Updated weights for policy 0, policy_version 384199 (0.0012) -[2023-11-28 10:17:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 196632576. Throughput: 0: 2654.0, 1: 2684.1. Samples: 196651716. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:23,445][86177] Avg episode reward: [(0, '-570.380'), (1, '-556.550')] -[2023-11-28 10:17:23,820][87424] Updated weights for policy 0, policy_version 384209 (0.0012) -[2023-11-28 10:17:24,200][87424] Updated weights for policy 0, policy_version 384219 (0.0012) -[2023-11-28 10:17:24,354][87426] Updated weights for policy 1, policy_version 383910 (0.0008) -[2023-11-28 10:17:24,738][87426] Updated weights for policy 1, policy_version 383920 (0.0009) -[2023-11-28 10:17:25,117][87426] Updated weights for policy 1, policy_version 383930 (0.0009) -[2023-11-28 10:17:26,570][87424] Updated weights for policy 0, policy_version 384229 (0.0010) -[2023-11-28 10:17:26,947][87424] Updated weights for policy 0, policy_version 384239 (0.0007) -[2023-11-28 10:17:27,010][87426] Updated weights for policy 1, policy_version 383940 (0.0007) -[2023-11-28 10:17:27,328][87424] Updated weights for policy 0, policy_version 384249 (0.0008) -[2023-11-28 10:17:27,391][87426] Updated weights for policy 1, policy_version 383950 (0.0008) -[2023-11-28 10:17:27,774][87426] Updated weights for policy 1, policy_version 383960 (0.0007) -[2023-11-28 10:17:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 196665344. Throughput: 0: 2661.3, 1: 2690.8. Samples: 196675608. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:28,445][86177] Avg episode reward: [(0, '-575.950'), (1, '-547.630')] -[2023-11-28 10:17:29,099][87424] Updated weights for policy 0, policy_version 384259 (0.0011) -[2023-11-28 10:17:29,482][87424] Updated weights for policy 0, policy_version 384269 (0.0008) -[2023-11-28 10:17:29,689][87426] Updated weights for policy 1, policy_version 383970 (0.0008) -[2023-11-28 10:17:29,863][87424] Updated weights for policy 0, policy_version 384279 (0.0010) -[2023-11-28 10:17:30,073][87426] Updated weights for policy 1, policy_version 383980 (0.0010) -[2023-11-28 10:17:30,442][87426] Updated weights for policy 1, policy_version 383990 (0.0009) -[2023-11-28 10:17:30,827][87426] Updated weights for policy 1, policy_version 384000 (0.0008) -[2023-11-28 10:17:32,423][87424] Updated weights for policy 0, policy_version 384289 (0.0011) -[2023-11-28 10:17:32,761][87426] Updated weights for policy 1, policy_version 384010 (0.0009) -[2023-11-28 10:17:32,800][87424] Updated weights for policy 0, policy_version 384299 (0.0011) -[2023-11-28 10:17:33,152][87426] Updated weights for policy 1, policy_version 384020 (0.0012) -[2023-11-28 10:17:33,176][87424] Updated weights for policy 0, policy_version 384309 (0.0011) -[2023-11-28 10:17:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5304.0). Total num frames: 196681728. Throughput: 0: 2702.5, 1: 2708.9. Samples: 196700896. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:33,445][86177] Avg episode reward: [(0, '-610.320'), (1, '-507.890')] -[2023-11-28 10:17:33,526][87426] Updated weights for policy 1, policy_version 384030 (0.0012) -[2023-11-28 10:17:33,555][87424] Updated weights for policy 0, policy_version 384319 (0.0012) -[2023-11-28 10:17:35,756][87424] Updated weights for policy 0, policy_version 384329 (0.0009) -[2023-11-28 10:17:36,027][87426] Updated weights for policy 1, policy_version 384040 (0.0011) -[2023-11-28 10:17:36,139][87424] Updated weights for policy 0, policy_version 384339 (0.0011) -[2023-11-28 10:17:36,401][87426] Updated weights for policy 1, policy_version 384050 (0.0009) -[2023-11-28 10:17:36,508][87424] Updated weights for policy 0, policy_version 384349 (0.0011) -[2023-11-28 10:17:36,770][87426] Updated weights for policy 1, policy_version 384060 (0.0011) -[2023-11-28 10:17:38,425][87424] Updated weights for policy 0, policy_version 384359 (0.0009) -[2023-11-28 10:17:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196714496. Throughput: 0: 2714.4, 1: 2686.8. Samples: 196731940. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:38,445][86177] Avg episode reward: [(0, '-581.790'), (1, '-507.570')] -[2023-11-28 10:17:38,806][87424] Updated weights for policy 0, policy_version 384369 (0.0007) -[2023-11-28 10:17:39,187][87424] Updated weights for policy 0, policy_version 384379 (0.0011) -[2023-11-28 10:17:39,334][87426] Updated weights for policy 1, policy_version 384070 (0.0012) -[2023-11-28 10:17:39,712][87426] Updated weights for policy 1, policy_version 384080 (0.0012) -[2023-11-28 10:17:40,094][87426] Updated weights for policy 1, policy_version 384090 (0.0010) -[2023-11-28 10:17:41,453][87424] Updated weights for policy 0, policy_version 384389 (0.0011) -[2023-11-28 10:17:41,821][87424] Updated weights for policy 0, policy_version 384399 (0.0010) -[2023-11-28 10:17:42,202][87424] Updated weights for policy 0, policy_version 384409 (0.0015) -[2023-11-28 10:17:42,732][87426] Updated weights for policy 1, policy_version 384100 (0.0010) -[2023-11-28 10:17:43,116][87426] Updated weights for policy 1, policy_version 384110 (0.0011) -[2023-11-28 10:17:43,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196739072. Throughput: 0: 2710.9, 1: 2658.3. Samples: 196756064. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:43,446][86177] Avg episode reward: [(0, '-582.380'), (1, '-504.200')] -[2023-11-28 10:17:43,484][87426] Updated weights for policy 1, policy_version 384120 (0.0012) -[2023-11-28 10:17:44,484][87424] Updated weights for policy 0, policy_version 384419 (0.0010) -[2023-11-28 10:17:44,873][87424] Updated weights for policy 0, policy_version 384429 (0.0008) -[2023-11-28 10:17:45,254][87424] Updated weights for policy 0, policy_version 384439 (0.0007) -[2023-11-28 10:17:45,455][87426] Updated weights for policy 1, policy_version 384130 (0.0011) -[2023-11-28 10:17:45,843][87426] Updated weights for policy 1, policy_version 384140 (0.0012) -[2023-11-28 10:17:46,213][87426] Updated weights for policy 1, policy_version 384150 (0.0012) -[2023-11-28 10:17:46,585][87426] Updated weights for policy 1, policy_version 384160 (0.0012) -[2023-11-28 10:17:47,163][87424] Updated weights for policy 0, policy_version 384449 (0.0011) -[2023-11-28 10:17:47,546][87424] Updated weights for policy 0, policy_version 384459 (0.0012) -[2023-11-28 10:17:47,938][87424] Updated weights for policy 0, policy_version 384469 (0.0011) -[2023-11-28 10:17:48,255][87426] Updated weights for policy 1, policy_version 384170 (0.0011) -[2023-11-28 10:17:48,317][87424] Updated weights for policy 0, policy_version 384479 (0.0011) -[2023-11-28 10:17:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 196771840. Throughput: 0: 2686.1, 1: 2647.6. Samples: 196779664. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:48,445][86177] Avg episode reward: [(0, '-575.600'), (1, '-503.030')] -[2023-11-28 10:17:48,633][87426] Updated weights for policy 1, policy_version 384180 (0.0012) -[2023-11-28 10:17:49,023][87426] Updated weights for policy 1, policy_version 384190 (0.0012) -[2023-11-28 10:17:50,321][87424] Updated weights for policy 0, policy_version 384489 (0.0011) -[2023-11-28 10:17:50,697][87424] Updated weights for policy 0, policy_version 384499 (0.0011) -[2023-11-28 10:17:51,086][87424] Updated weights for policy 0, policy_version 384509 (0.0010) -[2023-11-28 10:17:51,372][87426] Updated weights for policy 1, policy_version 384200 (0.0011) -[2023-11-28 10:17:51,747][87426] Updated weights for policy 1, policy_version 384210 (0.0009) -[2023-11-28 10:17:52,128][87426] Updated weights for policy 1, policy_version 384220 (0.0012) -[2023-11-28 10:17:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 196796416. Throughput: 0: 2673.0, 1: 2658.8. Samples: 196811784. Policy #0 lag: (min: 32.0, avg: 52.8, max: 80.0) -[2023-11-28 10:17:53,445][86177] Avg episode reward: [(0, '-555.370'), (1, '-536.560')] -[2023-11-28 10:17:53,671][87424] Updated weights for policy 0, policy_version 384519 (0.0012) -[2023-11-28 10:17:54,047][87424] Updated weights for policy 0, policy_version 384529 (0.0011) -[2023-11-28 10:17:54,426][87424] Updated weights for policy 0, policy_version 384539 (0.0012) -[2023-11-28 10:17:54,537][87426] Updated weights for policy 1, policy_version 384230 (0.0011) -[2023-11-28 10:17:54,916][87426] Updated weights for policy 1, policy_version 384240 (0.0012) -[2023-11-28 10:17:55,301][87426] Updated weights for policy 1, policy_version 384250 (0.0012) -[2023-11-28 10:17:56,602][87424] Updated weights for policy 0, policy_version 384549 (0.0009) -[2023-11-28 10:17:56,977][87424] Updated weights for policy 0, policy_version 384559 (0.0011) -[2023-11-28 10:17:57,359][87424] Updated weights for policy 0, policy_version 384569 (0.0011) -[2023-11-28 10:17:57,799][87426] Updated weights for policy 1, policy_version 384260 (0.0012) -[2023-11-28 10:17:58,186][87426] Updated weights for policy 1, policy_version 384270 (0.0009) -[2023-11-28 10:17:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196820992. Throughput: 0: 2678.5, 1: 2670.9. Samples: 196836304. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:17:58,445][86177] Avg episode reward: [(0, '-551.920'), (1, '-537.610')] -[2023-11-28 10:17:58,566][87426] Updated weights for policy 1, policy_version 384280 (0.0010) -[2023-11-28 10:17:59,307][87424] Updated weights for policy 0, policy_version 384579 (0.0011) -[2023-11-28 10:17:59,681][87424] Updated weights for policy 0, policy_version 384589 (0.0008) -[2023-11-28 10:18:00,065][87424] Updated weights for policy 0, policy_version 384599 (0.0008) -[2023-11-28 10:18:00,681][87426] Updated weights for policy 1, policy_version 384290 (0.0010) -[2023-11-28 10:18:01,046][87426] Updated weights for policy 1, policy_version 384300 (0.0007) -[2023-11-28 10:18:01,427][87426] Updated weights for policy 1, policy_version 384310 (0.0007) -[2023-11-28 10:18:01,817][87426] Updated weights for policy 1, policy_version 384320 (0.0009) -[2023-11-28 10:18:02,455][87424] Updated weights for policy 0, policy_version 384609 (0.0008) -[2023-11-28 10:18:02,836][87424] Updated weights for policy 0, policy_version 384619 (0.0008) -[2023-11-28 10:18:03,216][87424] Updated weights for policy 0, policy_version 384629 (0.0008) -[2023-11-28 10:18:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196845568. Throughput: 0: 2691.1, 1: 2691.6. Samples: 196861368. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:03,445][86177] Avg episode reward: [(0, '-566.130'), (1, '-534.400')] -[2023-11-28 10:18:03,600][87424] Updated weights for policy 0, policy_version 384639 (0.0008) -[2023-11-28 10:18:03,927][87426] Updated weights for policy 1, policy_version 384330 (0.0011) -[2023-11-28 10:18:04,308][87426] Updated weights for policy 1, policy_version 384340 (0.0009) -[2023-11-28 10:18:04,692][87426] Updated weights for policy 1, policy_version 384350 (0.0009) -[2023-11-28 10:18:05,722][87424] Updated weights for policy 0, policy_version 384649 (0.0008) -[2023-11-28 10:18:06,106][87424] Updated weights for policy 0, policy_version 384659 (0.0007) -[2023-11-28 10:18:06,488][87424] Updated weights for policy 0, policy_version 384669 (0.0008) -[2023-11-28 10:18:06,888][87426] Updated weights for policy 1, policy_version 384360 (0.0010) -[2023-11-28 10:18:07,278][87426] Updated weights for policy 1, policy_version 384370 (0.0011) -[2023-11-28 10:18:07,656][87426] Updated weights for policy 1, policy_version 384380 (0.0008) -[2023-11-28 10:18:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 196878336. Throughput: 0: 2704.9, 1: 2679.1. Samples: 196893996. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:08,445][86177] Avg episode reward: [(0, '-568.120'), (1, '-555.380')] -[2023-11-28 10:18:08,851][87424] Updated weights for policy 0, policy_version 384679 (0.0008) -[2023-11-28 10:18:09,223][87424] Updated weights for policy 0, policy_version 384689 (0.0011) -[2023-11-28 10:18:09,604][87424] Updated weights for policy 0, policy_version 384699 (0.0011) -[2023-11-28 10:18:09,718][87426] Updated weights for policy 1, policy_version 384390 (0.0010) -[2023-11-28 10:18:10,083][87426] Updated weights for policy 1, policy_version 384400 (0.0011) -[2023-11-28 10:18:10,468][87426] Updated weights for policy 1, policy_version 384410 (0.0012) -[2023-11-28 10:18:12,030][87424] Updated weights for policy 0, policy_version 384709 (0.0010) -[2023-11-28 10:18:12,411][87424] Updated weights for policy 0, policy_version 384719 (0.0011) -[2023-11-28 10:18:12,699][87426] Updated weights for policy 1, policy_version 384420 (0.0011) -[2023-11-28 10:18:12,803][87424] Updated weights for policy 0, policy_version 384729 (0.0011) -[2023-11-28 10:18:13,069][87426] Updated weights for policy 1, policy_version 384430 (0.0011) -[2023-11-28 10:18:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 196902912. Throughput: 0: 2694.7, 1: 2693.8. Samples: 196918092. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:13,445][86177] Avg episode reward: [(0, '-548.260'), (1, '-522.560')] -[2023-11-28 10:18:13,446][87426] Updated weights for policy 1, policy_version 384440 (0.0010) -[2023-11-28 10:18:15,424][87424] Updated weights for policy 0, policy_version 384739 (0.0011) -[2023-11-28 10:18:15,497][87426] Updated weights for policy 1, policy_version 384450 (0.0009) -[2023-11-28 10:18:15,807][87424] Updated weights for policy 0, policy_version 384749 (0.0012) -[2023-11-28 10:18:15,883][87426] Updated weights for policy 1, policy_version 384460 (0.0012) -[2023-11-28 10:18:16,192][87424] Updated weights for policy 0, policy_version 384759 (0.0011) -[2023-11-28 10:18:16,260][87426] Updated weights for policy 1, policy_version 384470 (0.0011) -[2023-11-28 10:18:16,639][87426] Updated weights for policy 1, policy_version 384480 (0.0010) -[2023-11-28 10:18:18,150][87424] Updated weights for policy 0, policy_version 384769 (0.0011) -[2023-11-28 10:18:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 196927488. Throughput: 0: 2645.5, 1: 2705.0. Samples: 196941668. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:18,445][86177] Avg episode reward: [(0, '-550.590'), (1, '-525.080')] -[2023-11-28 10:18:18,537][87424] Updated weights for policy 0, policy_version 384779 (0.0007) -[2023-11-28 10:18:18,674][87426] Updated weights for policy 1, policy_version 384490 (0.0011) -[2023-11-28 10:18:18,924][87424] Updated weights for policy 0, policy_version 384789 (0.0010) -[2023-11-28 10:18:19,063][87426] Updated weights for policy 1, policy_version 384500 (0.0012) -[2023-11-28 10:18:19,303][87424] Updated weights for policy 0, policy_version 384799 (0.0011) -[2023-11-28 10:18:19,340][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000384800_98508800.pth... -[2023-11-28 10:18:19,388][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000382272_97861632.pth -[2023-11-28 10:18:19,441][87426] Updated weights for policy 1, policy_version 384510 (0.0011) -[2023-11-28 10:18:19,515][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000384512_98435072.pth... -[2023-11-28 10:18:19,562][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000381984_97787904.pth -[2023-11-28 10:18:21,466][87424] Updated weights for policy 0, policy_version 384809 (0.0009) -[2023-11-28 10:18:21,695][87426] Updated weights for policy 1, policy_version 384520 (0.0011) -[2023-11-28 10:18:21,846][87424] Updated weights for policy 0, policy_version 384819 (0.0010) -[2023-11-28 10:18:22,079][87426] Updated weights for policy 1, policy_version 384530 (0.0010) -[2023-11-28 10:18:22,229][87424] Updated weights for policy 0, policy_version 384829 (0.0011) -[2023-11-28 10:18:22,449][87426] Updated weights for policy 1, policy_version 384540 (0.0011) -[2023-11-28 10:18:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 196960256. Throughput: 0: 2679.7, 1: 2725.2. Samples: 196975164. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:23,445][86177] Avg episode reward: [(0, '-543.780'), (1, '-527.880')] -[2023-11-28 10:18:24,447][87426] Updated weights for policy 1, policy_version 384550 (0.0010) -[2023-11-28 10:18:24,697][87424] Updated weights for policy 0, policy_version 384839 (0.0010) -[2023-11-28 10:18:24,828][87426] Updated weights for policy 1, policy_version 384560 (0.0011) -[2023-11-28 10:18:25,074][87424] Updated weights for policy 0, policy_version 384849 (0.0011) -[2023-11-28 10:18:25,213][87426] Updated weights for policy 1, policy_version 384570 (0.0010) -[2023-11-28 10:18:25,449][87424] Updated weights for policy 0, policy_version 384859 (0.0010) -[2023-11-28 10:18:27,185][87426] Updated weights for policy 1, policy_version 384580 (0.0010) -[2023-11-28 10:18:27,267][87424] Updated weights for policy 0, policy_version 384869 (0.0010) -[2023-11-28 10:18:27,569][87426] Updated weights for policy 1, policy_version 384590 (0.0007) -[2023-11-28 10:18:27,650][87424] Updated weights for policy 0, policy_version 384879 (0.0007) -[2023-11-28 10:18:27,939][87426] Updated weights for policy 1, policy_version 384600 (0.0009) -[2023-11-28 10:18:28,030][87424] Updated weights for policy 0, policy_version 384889 (0.0007) -[2023-11-28 10:18:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 196993024. Throughput: 0: 2677.3, 1: 2744.5. Samples: 197000044. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:28,445][86177] Avg episode reward: [(0, '-538.380'), (1, '-507.150')] -[2023-11-28 10:18:29,831][87424] Updated weights for policy 0, policy_version 384899 (0.0009) -[2023-11-28 10:18:30,206][87424] Updated weights for policy 0, policy_version 384909 (0.0012) -[2023-11-28 10:18:30,236][87426] Updated weights for policy 1, policy_version 384610 (0.0012) -[2023-11-28 10:18:30,586][87424] Updated weights for policy 0, policy_version 384919 (0.0011) -[2023-11-28 10:18:30,609][87426] Updated weights for policy 1, policy_version 384620 (0.0010) -[2023-11-28 10:18:30,981][87426] Updated weights for policy 1, policy_version 384630 (0.0012) -[2023-11-28 10:18:31,356][87426] Updated weights for policy 1, policy_version 384640 (0.0012) -[2023-11-28 10:18:32,714][87424] Updated weights for policy 0, policy_version 384929 (0.0009) -[2023-11-28 10:18:33,082][87424] Updated weights for policy 0, policy_version 384939 (0.0012) -[2023-11-28 10:18:33,357][87426] Updated weights for policy 1, policy_version 384650 (0.0011) -[2023-11-28 10:18:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 197009408. Throughput: 0: 2709.0, 1: 2756.9. Samples: 197025628. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:33,445][86177] Avg episode reward: [(0, '-537.090'), (1, '-509.410')] -[2023-11-28 10:18:33,468][87424] Updated weights for policy 0, policy_version 384949 (0.0012) -[2023-11-28 10:18:33,740][87426] Updated weights for policy 1, policy_version 384660 (0.0010) -[2023-11-28 10:18:33,838][87424] Updated weights for policy 0, policy_version 384959 (0.0012) -[2023-11-28 10:18:34,127][87426] Updated weights for policy 1, policy_version 384670 (0.0008) -[2023-11-28 10:18:36,208][87426] Updated weights for policy 1, policy_version 384680 (0.0009) -[2023-11-28 10:18:36,238][87424] Updated weights for policy 0, policy_version 384969 (0.0009) -[2023-11-28 10:18:36,596][87426] Updated weights for policy 1, policy_version 384690 (0.0011) -[2023-11-28 10:18:36,622][87424] Updated weights for policy 0, policy_version 384979 (0.0008) -[2023-11-28 10:18:36,967][87426] Updated weights for policy 1, policy_version 384700 (0.0011) -[2023-11-28 10:18:37,001][87424] Updated weights for policy 0, policy_version 384989 (0.0010) -[2023-11-28 10:18:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197042176. Throughput: 0: 2715.2, 1: 2748.3. Samples: 197057640. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:38,445][86177] Avg episode reward: [(0, '-532.260'), (1, '-508.150')] -[2023-11-28 10:18:39,275][87424] Updated weights for policy 0, policy_version 384999 (0.0012) -[2023-11-28 10:18:39,584][87426] Updated weights for policy 1, policy_version 384710 (0.0010) -[2023-11-28 10:18:39,656][87424] Updated weights for policy 0, policy_version 385009 (0.0012) -[2023-11-28 10:18:39,954][87426] Updated weights for policy 1, policy_version 384720 (0.0010) -[2023-11-28 10:18:40,045][87424] Updated weights for policy 0, policy_version 385019 (0.0011) -[2023-11-28 10:18:40,329][87426] Updated weights for policy 1, policy_version 384730 (0.0011) -[2023-11-28 10:18:42,518][87424] Updated weights for policy 0, policy_version 385029 (0.0011) -[2023-11-28 10:18:42,905][87424] Updated weights for policy 0, policy_version 385039 (0.0010) -[2023-11-28 10:18:42,945][87426] Updated weights for policy 1, policy_version 384740 (0.0011) -[2023-11-28 10:18:43,278][87424] Updated weights for policy 0, policy_version 385049 (0.0012) -[2023-11-28 10:18:43,321][87426] Updated weights for policy 1, policy_version 384750 (0.0011) -[2023-11-28 10:18:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 197058560. Throughput: 0: 2708.3, 1: 2706.0. Samples: 197079944. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:43,445][86177] Avg episode reward: [(0, '-532.350'), (1, '-510.890')] -[2023-11-28 10:18:43,702][87426] Updated weights for policy 1, policy_version 384760 (0.0011) -[2023-11-28 10:18:45,474][87424] Updated weights for policy 0, policy_version 385059 (0.0011) -[2023-11-28 10:18:45,853][87424] Updated weights for policy 0, policy_version 385069 (0.0011) -[2023-11-28 10:18:46,172][87426] Updated weights for policy 1, policy_version 384770 (0.0011) -[2023-11-28 10:18:46,232][87424] Updated weights for policy 0, policy_version 385079 (0.0011) -[2023-11-28 10:18:46,538][87426] Updated weights for policy 1, policy_version 384780 (0.0010) -[2023-11-28 10:18:46,930][87426] Updated weights for policy 1, policy_version 384790 (0.0011) -[2023-11-28 10:18:47,295][87426] Updated weights for policy 1, policy_version 384800 (0.0009) -[2023-11-28 10:18:47,898][87424] Updated weights for policy 0, policy_version 385089 (0.0010) -[2023-11-28 10:18:48,280][87424] Updated weights for policy 0, policy_version 385099 (0.0012) -[2023-11-28 10:18:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 197091328. Throughput: 0: 2697.7, 1: 2696.3. Samples: 197104096. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:48,445][86177] Avg episode reward: [(0, '-525.210'), (1, '-512.160')] -[2023-11-28 10:18:48,673][87424] Updated weights for policy 0, policy_version 385109 (0.0012) -[2023-11-28 10:18:49,056][87424] Updated weights for policy 0, policy_version 385119 (0.0011) -[2023-11-28 10:18:49,750][87426] Updated weights for policy 1, policy_version 384810 (0.0012) -[2023-11-28 10:18:50,127][87426] Updated weights for policy 1, policy_version 384820 (0.0012) -[2023-11-28 10:18:50,508][87426] Updated weights for policy 1, policy_version 384830 (0.0012) -[2023-11-28 10:18:51,485][87424] Updated weights for policy 0, policy_version 385129 (0.0011) -[2023-11-28 10:18:51,871][87424] Updated weights for policy 0, policy_version 385139 (0.0011) -[2023-11-28 10:18:52,246][87424] Updated weights for policy 0, policy_version 385149 (0.0011) -[2023-11-28 10:18:53,016][87426] Updated weights for policy 1, policy_version 384840 (0.0009) -[2023-11-28 10:18:53,387][87426] Updated weights for policy 1, policy_version 384850 (0.0009) -[2023-11-28 10:18:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 197115904. Throughput: 0: 2693.6, 1: 2677.9. Samples: 197135712. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:53,445][86177] Avg episode reward: [(0, '-521.740'), (1, '-508.510')] -[2023-11-28 10:18:53,761][87426] Updated weights for policy 1, policy_version 384860 (0.0009) -[2023-11-28 10:18:54,414][87424] Updated weights for policy 0, policy_version 385159 (0.0012) -[2023-11-28 10:18:54,799][87424] Updated weights for policy 0, policy_version 385169 (0.0008) -[2023-11-28 10:18:55,183][87424] Updated weights for policy 0, policy_version 385179 (0.0012) -[2023-11-28 10:18:55,841][87426] Updated weights for policy 1, policy_version 384870 (0.0008) -[2023-11-28 10:18:56,219][87426] Updated weights for policy 1, policy_version 384880 (0.0007) -[2023-11-28 10:18:56,603][87426] Updated weights for policy 1, policy_version 384890 (0.0007) -[2023-11-28 10:18:57,058][87424] Updated weights for policy 0, policy_version 385189 (0.0011) -[2023-11-28 10:18:57,444][87424] Updated weights for policy 0, policy_version 385199 (0.0007) -[2023-11-28 10:18:57,823][87424] Updated weights for policy 0, policy_version 385209 (0.0007) -[2023-11-28 10:18:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197148672. Throughput: 0: 2706.3, 1: 2666.7. Samples: 197159880. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:18:58,445][86177] Avg episode reward: [(0, '-533.730'), (1, '-510.690')] -[2023-11-28 10:18:58,994][87426] Updated weights for policy 1, policy_version 384900 (0.0010) -[2023-11-28 10:18:59,372][87426] Updated weights for policy 1, policy_version 384910 (0.0011) -[2023-11-28 10:18:59,532][87424] Updated weights for policy 0, policy_version 385219 (0.0010) -[2023-11-28 10:18:59,750][87426] Updated weights for policy 1, policy_version 384920 (0.0009) -[2023-11-28 10:18:59,912][87424] Updated weights for policy 0, policy_version 385229 (0.0010) -[2023-11-28 10:19:00,293][87424] Updated weights for policy 0, policy_version 385239 (0.0012) -[2023-11-28 10:19:01,898][87426] Updated weights for policy 1, policy_version 384930 (0.0011) -[2023-11-28 10:19:02,276][87426] Updated weights for policy 1, policy_version 384940 (0.0012) -[2023-11-28 10:19:02,591][87424] Updated weights for policy 0, policy_version 385249 (0.0015) -[2023-11-28 10:19:02,655][87426] Updated weights for policy 1, policy_version 384950 (0.0012) -[2023-11-28 10:19:02,975][87424] Updated weights for policy 0, policy_version 385259 (0.0009) -[2023-11-28 10:19:03,026][87426] Updated weights for policy 1, policy_version 384960 (0.0012) -[2023-11-28 10:19:03,358][87424] Updated weights for policy 0, policy_version 385269 (0.0009) -[2023-11-28 10:19:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 197173248. Throughput: 0: 2787.6, 1: 2646.0. Samples: 197186184. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:19:03,445][86177] Avg episode reward: [(0, '-529.660'), (1, '-516.080')] -[2023-11-28 10:19:03,745][87424] Updated weights for policy 0, policy_version 385279 (0.0008) -[2023-11-28 10:19:05,613][87424] Updated weights for policy 0, policy_version 385289 (0.0011) -[2023-11-28 10:19:05,654][87426] Updated weights for policy 1, policy_version 384970 (0.0011) -[2023-11-28 10:19:05,999][87424] Updated weights for policy 0, policy_version 385299 (0.0008) -[2023-11-28 10:19:06,030][87426] Updated weights for policy 1, policy_version 384980 (0.0011) -[2023-11-28 10:19:06,384][87424] Updated weights for policy 0, policy_version 385309 (0.0008) -[2023-11-28 10:19:06,405][87426] Updated weights for policy 1, policy_version 384990 (0.0009) -[2023-11-28 10:19:08,329][87424] Updated weights for policy 0, policy_version 385319 (0.0011) -[2023-11-28 10:19:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 197197824. Throughput: 0: 2782.8, 1: 2627.5. Samples: 197218628. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:19:08,445][86177] Avg episode reward: [(0, '-533.630'), (1, '-551.810')] -[2023-11-28 10:19:08,576][87426] Updated weights for policy 1, policy_version 385000 (0.0010) -[2023-11-28 10:19:08,717][87424] Updated weights for policy 0, policy_version 385329 (0.0011) -[2023-11-28 10:19:08,951][87426] Updated weights for policy 1, policy_version 385010 (0.0011) -[2023-11-28 10:19:09,091][87424] Updated weights for policy 0, policy_version 385339 (0.0011) -[2023-11-28 10:19:09,326][87426] Updated weights for policy 1, policy_version 385020 (0.0011) -[2023-11-28 10:19:11,497][87424] Updated weights for policy 0, policy_version 385349 (0.0011) -[2023-11-28 10:19:11,617][87426] Updated weights for policy 1, policy_version 385030 (0.0010) -[2023-11-28 10:19:11,881][87424] Updated weights for policy 0, policy_version 385359 (0.0011) -[2023-11-28 10:19:11,994][87426] Updated weights for policy 1, policy_version 385040 (0.0013) -[2023-11-28 10:19:12,266][87424] Updated weights for policy 0, policy_version 385369 (0.0010) -[2023-11-28 10:19:12,373][87426] Updated weights for policy 1, policy_version 385050 (0.0011) -[2023-11-28 10:19:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197230592. Throughput: 0: 2778.1, 1: 2605.8. Samples: 197242320. Policy #0 lag: (min: 3.0, avg: 15.4, max: 35.0) -[2023-11-28 10:19:13,445][86177] Avg episode reward: [(0, '-529.750'), (1, '-551.050')] -[2023-11-28 10:19:14,296][87426] Updated weights for policy 1, policy_version 385060 (0.0010) -[2023-11-28 10:19:14,406][87424] Updated weights for policy 0, policy_version 385379 (0.0011) -[2023-11-28 10:19:14,692][87426] Updated weights for policy 1, policy_version 385070 (0.0008) -[2023-11-28 10:19:14,779][87424] Updated weights for policy 0, policy_version 385389 (0.0011) -[2023-11-28 10:19:15,069][87426] Updated weights for policy 1, policy_version 385080 (0.0010) -[2023-11-28 10:19:15,165][87424] Updated weights for policy 0, policy_version 385399 (0.0012) -[2023-11-28 10:19:16,786][87426] Updated weights for policy 1, policy_version 385090 (0.0012) -[2023-11-28 10:19:17,160][87426] Updated weights for policy 1, policy_version 385100 (0.0013) -[2023-11-28 10:19:17,533][87426] Updated weights for policy 1, policy_version 385110 (0.0009) -[2023-11-28 10:19:17,653][87424] Updated weights for policy 0, policy_version 385409 (0.0013) -[2023-11-28 10:19:17,910][87426] Updated weights for policy 1, policy_version 385120 (0.0007) -[2023-11-28 10:19:18,044][87424] Updated weights for policy 0, policy_version 385419 (0.0011) -[2023-11-28 10:19:18,425][87424] Updated weights for policy 0, policy_version 385429 (0.0014) -[2023-11-28 10:19:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197255168. Throughput: 0: 2756.2, 1: 2596.4. Samples: 197266492. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:19:18,445][86177] Avg episode reward: [(0, '-526.370'), (1, '-569.580')] -[2023-11-28 10:19:18,813][87424] Updated weights for policy 0, policy_version 385439 (0.0011) -[2023-11-28 10:19:20,050][87426] Updated weights for policy 1, policy_version 385130 (0.0011) -[2023-11-28 10:19:20,437][87426] Updated weights for policy 1, policy_version 385140 (0.0009) -[2023-11-28 10:19:20,813][87426] Updated weights for policy 1, policy_version 385150 (0.0009) -[2023-11-28 10:19:21,113][87424] Updated weights for policy 0, policy_version 385449 (0.0011) -[2023-11-28 10:19:21,496][87424] Updated weights for policy 0, policy_version 385459 (0.0008) -[2023-11-28 10:19:21,894][87424] Updated weights for policy 0, policy_version 385469 (0.0011) -[2023-11-28 10:19:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 197279744. Throughput: 0: 2749.9, 1: 2590.2. Samples: 197297944. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:19:23,445][86177] Avg episode reward: [(0, '-524.520'), (1, '-569.140')] -[2023-11-28 10:19:23,458][87426] Updated weights for policy 1, policy_version 385160 (0.0011) -[2023-11-28 10:19:23,837][87426] Updated weights for policy 1, policy_version 385170 (0.0009) -[2023-11-28 10:19:24,218][87426] Updated weights for policy 1, policy_version 385180 (0.0008) -[2023-11-28 10:19:24,386][87424] Updated weights for policy 0, policy_version 385479 (0.0011) -[2023-11-28 10:19:24,763][87424] Updated weights for policy 0, policy_version 385489 (0.0008) -[2023-11-28 10:19:25,147][87424] Updated weights for policy 0, policy_version 385499 (0.0009) -[2023-11-28 10:19:25,811][87426] Updated weights for policy 1, policy_version 385190 (0.0008) -[2023-11-28 10:19:26,197][87426] Updated weights for policy 1, policy_version 385200 (0.0012) -[2023-11-28 10:19:26,579][87426] Updated weights for policy 1, policy_version 385210 (0.0012) -[2023-11-28 10:19:27,120][87424] Updated weights for policy 0, policy_version 385509 (0.0007) -[2023-11-28 10:19:27,497][87424] Updated weights for policy 0, policy_version 385519 (0.0007) -[2023-11-28 10:19:27,877][87424] Updated weights for policy 0, policy_version 385529 (0.0008) -[2023-11-28 10:19:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 197312512. Throughput: 0: 2746.2, 1: 2669.7. Samples: 197323660. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:19:28,445][86177] Avg episode reward: [(0, '-529.250'), (1, '-562.480')] -[2023-11-28 10:19:28,673][87426] Updated weights for policy 1, policy_version 385220 (0.0012) -[2023-11-28 10:19:29,051][87426] Updated weights for policy 1, policy_version 385230 (0.0011) -[2023-11-28 10:19:29,434][87426] Updated weights for policy 1, policy_version 385240 (0.0012) -[2023-11-28 10:19:29,676][87424] Updated weights for policy 0, policy_version 385539 (0.0009) -[2023-11-28 10:19:30,051][87424] Updated weights for policy 0, policy_version 385549 (0.0010) -[2023-11-28 10:19:30,434][87424] Updated weights for policy 0, policy_version 385559 (0.0008) -[2023-11-28 10:19:32,035][87426] Updated weights for policy 1, policy_version 385250 (0.0011) -[2023-11-28 10:19:32,418][87426] Updated weights for policy 1, policy_version 385260 (0.0012) -[2023-11-28 10:19:32,793][87426] Updated weights for policy 1, policy_version 385270 (0.0012) -[2023-11-28 10:19:32,851][87424] Updated weights for policy 0, policy_version 385569 (0.0011) -[2023-11-28 10:19:33,171][87426] Updated weights for policy 1, policy_version 385280 (0.0012) -[2023-11-28 10:19:33,234][87424] Updated weights for policy 0, policy_version 385579 (0.0012) -[2023-11-28 10:19:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197337088. Throughput: 0: 2751.2, 1: 2667.8. Samples: 197347952. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:19:33,445][86177] Avg episode reward: [(0, '-536.250'), (1, '-574.340')] -[2023-11-28 10:19:33,619][87424] Updated weights for policy 0, policy_version 385589 (0.0012) -[2023-11-28 10:19:34,006][87424] Updated weights for policy 0, policy_version 385599 (0.0012) -[2023-11-28 10:19:34,978][87426] Updated weights for policy 1, policy_version 385290 (0.0011) -[2023-11-28 10:19:35,362][87426] Updated weights for policy 1, policy_version 385300 (0.0012) -[2023-11-28 10:19:35,736][87426] Updated weights for policy 1, policy_version 385310 (0.0009) -[2023-11-28 10:19:35,822][87424] Updated weights for policy 0, policy_version 385609 (0.0017) -[2023-11-28 10:19:36,207][87424] Updated weights for policy 0, policy_version 385619 (0.0007) -[2023-11-28 10:19:36,590][87424] Updated weights for policy 0, policy_version 385629 (0.0008) -[2023-11-28 10:19:38,107][87426] Updated weights for policy 1, policy_version 385320 (0.0012) -[2023-11-28 10:19:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 197361664. Throughput: 0: 2742.3, 1: 2691.4. Samples: 197380228. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:19:38,445][86177] Avg episode reward: [(0, '-538.600'), (1, '-572.380')] -[2023-11-28 10:19:38,487][87426] Updated weights for policy 1, policy_version 385330 (0.0011) -[2023-11-28 10:19:38,550][87424] Updated weights for policy 0, policy_version 385639 (0.0010) -[2023-11-28 10:19:38,865][87426] Updated weights for policy 1, policy_version 385340 (0.0008) -[2023-11-28 10:19:38,937][87424] Updated weights for policy 0, policy_version 385649 (0.0012) -[2023-11-28 10:19:39,313][87424] Updated weights for policy 0, policy_version 385659 (0.0011) -[2023-11-28 10:19:41,441][87426] Updated weights for policy 1, policy_version 385350 (0.0012) -[2023-11-28 10:19:41,820][87426] Updated weights for policy 1, policy_version 385360 (0.0012) -[2023-11-28 10:19:41,864][87424] Updated weights for policy 0, policy_version 385669 (0.0009) -[2023-11-28 10:19:42,206][87426] Updated weights for policy 1, policy_version 385370 (0.0011) -[2023-11-28 10:19:42,250][87424] Updated weights for policy 0, policy_version 385679 (0.0016) -[2023-11-28 10:19:42,632][87424] Updated weights for policy 0, policy_version 385689 (0.0011) -[2023-11-28 10:19:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 197394432. Throughput: 0: 2733.6, 1: 2689.9. Samples: 197403936. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:19:43,445][86177] Avg episode reward: [(0, '-539.780'), (1, '-587.740')] -[2023-11-28 10:19:44,167][87426] Updated weights for policy 1, policy_version 385380 (0.0010) -[2023-11-28 10:19:44,538][87426] Updated weights for policy 1, policy_version 385390 (0.0012) -[2023-11-28 10:19:44,921][87426] Updated weights for policy 1, policy_version 385400 (0.0012) -[2023-11-28 10:19:44,977][87424] Updated weights for policy 0, policy_version 385699 (0.0010) -[2023-11-28 10:19:45,359][87424] Updated weights for policy 0, policy_version 385709 (0.0009) -[2023-11-28 10:19:45,736][87424] Updated weights for policy 0, policy_version 385719 (0.0012) -[2023-11-28 10:19:46,948][87426] Updated weights for policy 1, policy_version 385410 (0.0009) -[2023-11-28 10:19:47,322][87426] Updated weights for policy 1, policy_version 385420 (0.0008) -[2023-11-28 10:19:47,711][87426] Updated weights for policy 1, policy_version 385430 (0.0008) -[2023-11-28 10:19:48,095][87426] Updated weights for policy 1, policy_version 385440 (0.0010) -[2023-11-28 10:19:48,222][87424] Updated weights for policy 0, policy_version 385729 (0.0012) -[2023-11-28 10:19:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197419008. Throughput: 0: 2686.2, 1: 2694.3. Samples: 197428308. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:19:48,445][86177] Avg episode reward: [(0, '-541.590'), (1, '-605.150')] -[2023-11-28 10:19:48,603][87424] Updated weights for policy 0, policy_version 385739 (0.0011) -[2023-11-28 10:19:48,980][87424] Updated weights for policy 0, policy_version 385749 (0.0012) -[2023-11-28 10:19:49,359][87424] Updated weights for policy 0, policy_version 385759 (0.0009) -[2023-11-28 10:19:50,498][87426] Updated weights for policy 1, policy_version 385450 (0.0012) -[2023-11-28 10:19:50,871][87426] Updated weights for policy 1, policy_version 385460 (0.0012) -[2023-11-28 10:19:51,253][87426] Updated weights for policy 1, policy_version 385470 (0.0012) -[2023-11-28 10:19:51,590][87424] Updated weights for policy 0, policy_version 385769 (0.0011) -[2023-11-28 10:19:51,968][87424] Updated weights for policy 0, policy_version 385779 (0.0012) -[2023-11-28 10:19:52,358][87424] Updated weights for policy 0, policy_version 385789 (0.0011) -[2023-11-28 10:19:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197443584. Throughput: 0: 2682.3, 1: 2716.6. Samples: 197461580. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:19:53,445][86177] Avg episode reward: [(0, '-540.930'), (1, '-594.010')] -[2023-11-28 10:19:53,730][87426] Updated weights for policy 1, policy_version 385480 (0.0012) -[2023-11-28 10:19:54,113][87426] Updated weights for policy 1, policy_version 385490 (0.0012) -[2023-11-28 10:19:54,499][87426] Updated weights for policy 1, policy_version 385500 (0.0011) -[2023-11-28 10:19:54,653][87424] Updated weights for policy 0, policy_version 385799 (0.0010) -[2023-11-28 10:19:55,025][87424] Updated weights for policy 0, policy_version 385809 (0.0012) -[2023-11-28 10:19:55,419][87424] Updated weights for policy 0, policy_version 385819 (0.0012) -[2023-11-28 10:19:56,977][87426] Updated weights for policy 1, policy_version 385510 (0.0008) -[2023-11-28 10:19:57,141][87424] Updated weights for policy 0, policy_version 385829 (0.0012) -[2023-11-28 10:19:57,359][87426] Updated weights for policy 1, policy_version 385520 (0.0009) -[2023-11-28 10:19:57,515][87424] Updated weights for policy 0, policy_version 385839 (0.0009) -[2023-11-28 10:19:57,731][87426] Updated weights for policy 1, policy_version 385530 (0.0012) -[2023-11-28 10:19:57,905][87424] Updated weights for policy 0, policy_version 385849 (0.0007) -[2023-11-28 10:19:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 197476352. Throughput: 0: 2685.5, 1: 2730.5. Samples: 197486040. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:19:58,445][86177] Avg episode reward: [(0, '-556.990'), (1, '-605.430')] -[2023-11-28 10:19:59,999][87426] Updated weights for policy 1, policy_version 385540 (0.0012) -[2023-11-28 10:20:00,193][87424] Updated weights for policy 0, policy_version 385859 (0.0009) -[2023-11-28 10:20:00,374][87426] Updated weights for policy 1, policy_version 385550 (0.0011) -[2023-11-28 10:20:00,569][87424] Updated weights for policy 0, policy_version 385869 (0.0011) -[2023-11-28 10:20:00,754][87426] Updated weights for policy 1, policy_version 385560 (0.0012) -[2023-11-28 10:20:00,952][87424] Updated weights for policy 0, policy_version 385879 (0.0011) -[2023-11-28 10:20:02,919][87426] Updated weights for policy 1, policy_version 385570 (0.0011) -[2023-11-28 10:20:03,007][87424] Updated weights for policy 0, policy_version 385889 (0.0012) -[2023-11-28 10:20:03,291][87426] Updated weights for policy 1, policy_version 385580 (0.0011) -[2023-11-28 10:20:03,393][87424] Updated weights for policy 0, policy_version 385899 (0.0010) -[2023-11-28 10:20:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 197492736. Throughput: 0: 2710.6, 1: 2724.4. Samples: 197511068. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:20:03,445][86177] Avg episode reward: [(0, '-556.560'), (1, '-581.780')] -[2023-11-28 10:20:03,667][87426] Updated weights for policy 1, policy_version 385590 (0.0012) -[2023-11-28 10:20:03,770][87424] Updated weights for policy 0, policy_version 385909 (0.0011) -[2023-11-28 10:20:04,048][87426] Updated weights for policy 1, policy_version 385600 (0.0012) -[2023-11-28 10:20:04,159][87424] Updated weights for policy 0, policy_version 385919 (0.0012) -[2023-11-28 10:20:05,942][87426] Updated weights for policy 1, policy_version 385610 (0.0011) -[2023-11-28 10:20:06,236][87424] Updated weights for policy 0, policy_version 385929 (0.0011) -[2023-11-28 10:20:06,320][87426] Updated weights for policy 1, policy_version 385620 (0.0011) -[2023-11-28 10:20:06,612][87424] Updated weights for policy 0, policy_version 385939 (0.0012) -[2023-11-28 10:20:06,704][87426] Updated weights for policy 1, policy_version 385630 (0.0012) -[2023-11-28 10:20:07,003][87424] Updated weights for policy 0, policy_version 385949 (0.0012) -[2023-11-28 10:20:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197525504. Throughput: 0: 2738.3, 1: 2737.5. Samples: 197544356. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:20:08,445][86177] Avg episode reward: [(0, '-549.250'), (1, '-542.240')] -[2023-11-28 10:20:08,601][87426] Updated weights for policy 1, policy_version 385640 (0.0011) -[2023-11-28 10:20:08,783][87424] Updated weights for policy 0, policy_version 385959 (0.0012) -[2023-11-28 10:20:08,987][87426] Updated weights for policy 1, policy_version 385650 (0.0012) -[2023-11-28 10:20:09,165][87424] Updated weights for policy 0, policy_version 385969 (0.0012) -[2023-11-28 10:20:09,368][87426] Updated weights for policy 1, policy_version 385660 (0.0011) -[2023-11-28 10:20:09,552][87424] Updated weights for policy 0, policy_version 385979 (0.0012) -[2023-11-28 10:20:11,647][87426] Updated weights for policy 1, policy_version 385670 (0.0011) -[2023-11-28 10:20:11,928][87424] Updated weights for policy 0, policy_version 385989 (0.0012) -[2023-11-28 10:20:12,024][87426] Updated weights for policy 1, policy_version 385680 (0.0012) -[2023-11-28 10:20:12,304][87424] Updated weights for policy 0, policy_version 385999 (0.0012) -[2023-11-28 10:20:12,410][87426] Updated weights for policy 1, policy_version 385690 (0.0011) -[2023-11-28 10:20:12,686][87424] Updated weights for policy 0, policy_version 386009 (0.0012) -[2023-11-28 10:20:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 197558272. Throughput: 0: 2742.6, 1: 2699.0. Samples: 197568532. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:20:13,445][86177] Avg episode reward: [(0, '-552.670'), (1, '-565.270')] -[2023-11-28 10:20:14,270][87426] Updated weights for policy 1, policy_version 385700 (0.0012) -[2023-11-28 10:20:14,649][87426] Updated weights for policy 1, policy_version 385710 (0.0012) -[2023-11-28 10:20:14,773][87424] Updated weights for policy 0, policy_version 386019 (0.0012) -[2023-11-28 10:20:15,028][87426] Updated weights for policy 1, policy_version 385720 (0.0012) -[2023-11-28 10:20:15,158][87424] Updated weights for policy 0, policy_version 386029 (0.0012) -[2023-11-28 10:20:15,540][87424] Updated weights for policy 0, policy_version 386039 (0.0010) -[2023-11-28 10:20:17,446][87424] Updated weights for policy 0, policy_version 386049 (0.0012) -[2023-11-28 10:20:17,584][87426] Updated weights for policy 1, policy_version 385730 (0.0010) -[2023-11-28 10:20:17,817][87424] Updated weights for policy 0, policy_version 386059 (0.0010) -[2023-11-28 10:20:17,962][87426] Updated weights for policy 1, policy_version 385740 (0.0007) -[2023-11-28 10:20:18,203][87424] Updated weights for policy 0, policy_version 386069 (0.0007) -[2023-11-28 10:20:18,348][87426] Updated weights for policy 1, policy_version 385750 (0.0007) -[2023-11-28 10:20:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 197574656. Throughput: 0: 2747.6, 1: 2697.7. Samples: 197592992. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:20:18,445][86177] Avg episode reward: [(0, '-529.920'), (1, '-550.380')] -[2023-11-28 10:20:18,593][87424] Updated weights for policy 0, policy_version 386079 (0.0010) -[2023-11-28 10:20:18,619][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000386080_98836480.pth... -[2023-11-28 10:20:18,652][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000383520_98181120.pth -[2023-11-28 10:20:18,722][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000385760_98754560.pth... -[2023-11-28 10:20:18,723][87426] Updated weights for policy 1, policy_version 385760 (0.0007) -[2023-11-28 10:20:18,754][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000383232_98107392.pth -[2023-11-28 10:20:20,686][87426] Updated weights for policy 1, policy_version 385770 (0.0011) -[2023-11-28 10:20:21,057][87424] Updated weights for policy 0, policy_version 386089 (0.0011) -[2023-11-28 10:20:21,068][87426] Updated weights for policy 1, policy_version 385780 (0.0012) -[2023-11-28 10:20:21,444][87424] Updated weights for policy 0, policy_version 386099 (0.0011) -[2023-11-28 10:20:21,448][87426] Updated weights for policy 1, policy_version 385790 (0.0012) -[2023-11-28 10:20:21,816][87424] Updated weights for policy 0, policy_version 386109 (0.0012) -[2023-11-28 10:20:23,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197607424. Throughput: 0: 2743.4, 1: 2690.8. Samples: 197624768. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:20:23,445][86177] Avg episode reward: [(0, '-529.880'), (1, '-543.690')] -[2023-11-28 10:20:23,539][87426] Updated weights for policy 1, policy_version 385800 (0.0012) -[2023-11-28 10:20:23,925][87426] Updated weights for policy 1, policy_version 385810 (0.0011) -[2023-11-28 10:20:24,064][87424] Updated weights for policy 0, policy_version 386119 (0.0010) -[2023-11-28 10:20:24,304][87426] Updated weights for policy 1, policy_version 385820 (0.0010) -[2023-11-28 10:20:24,447][87424] Updated weights for policy 0, policy_version 386129 (0.0009) -[2023-11-28 10:20:24,831][87424] Updated weights for policy 0, policy_version 386139 (0.0008) -[2023-11-28 10:20:26,741][87424] Updated weights for policy 0, policy_version 386149 (0.0010) -[2023-11-28 10:20:26,856][87426] Updated weights for policy 1, policy_version 385830 (0.0009) -[2023-11-28 10:20:27,126][87424] Updated weights for policy 0, policy_version 386159 (0.0012) -[2023-11-28 10:20:27,248][87426] Updated weights for policy 1, policy_version 385840 (0.0011) -[2023-11-28 10:20:27,508][87424] Updated weights for policy 0, policy_version 386169 (0.0009) -[2023-11-28 10:20:27,632][87426] Updated weights for policy 1, policy_version 385850 (0.0012) -[2023-11-28 10:20:28,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 197640192. Throughput: 0: 2750.7, 1: 2693.5. Samples: 197648924. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:20:28,445][86177] Avg episode reward: [(0, '-526.520'), (1, '-546.970')] -[2023-11-28 10:20:29,343][87424] Updated weights for policy 0, policy_version 386179 (0.0007) -[2023-11-28 10:20:29,720][87424] Updated weights for policy 0, policy_version 386189 (0.0011) -[2023-11-28 10:20:30,006][87426] Updated weights for policy 1, policy_version 385860 (0.0010) -[2023-11-28 10:20:30,097][87424] Updated weights for policy 0, policy_version 386199 (0.0011) -[2023-11-28 10:20:30,381][87426] Updated weights for policy 1, policy_version 385870 (0.0011) -[2023-11-28 10:20:30,754][87426] Updated weights for policy 1, policy_version 385880 (0.0011) -[2023-11-28 10:20:32,495][87424] Updated weights for policy 0, policy_version 386209 (0.0010) -[2023-11-28 10:20:32,877][87424] Updated weights for policy 0, policy_version 386219 (0.0011) -[2023-11-28 10:20:33,189][87426] Updated weights for policy 1, policy_version 385890 (0.0009) -[2023-11-28 10:20:33,255][87424] Updated weights for policy 0, policy_version 386229 (0.0014) -[2023-11-28 10:20:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 197656576. Throughput: 0: 2793.4, 1: 2705.8. Samples: 197675772. Policy #0 lag: (min: 29.0, avg: 43.1, max: 61.0) -[2023-11-28 10:20:33,445][86177] Avg episode reward: [(0, '-519.900'), (1, '-538.920')] -[2023-11-28 10:20:33,556][87426] Updated weights for policy 1, policy_version 385900 (0.0011) -[2023-11-28 10:20:33,630][87424] Updated weights for policy 0, policy_version 386239 (0.0011) -[2023-11-28 10:20:33,939][87426] Updated weights for policy 1, policy_version 385910 (0.0008) -[2023-11-28 10:20:34,322][87426] Updated weights for policy 1, policy_version 385920 (0.0007) -[2023-11-28 10:20:36,131][87426] Updated weights for policy 1, policy_version 385930 (0.0007) -[2023-11-28 10:20:36,173][87424] Updated weights for policy 0, policy_version 386249 (0.0008) -[2023-11-28 10:20:36,528][87426] Updated weights for policy 1, policy_version 385940 (0.0011) -[2023-11-28 10:20:36,554][87424] Updated weights for policy 0, policy_version 386259 (0.0010) -[2023-11-28 10:20:36,899][87426] Updated weights for policy 1, policy_version 385950 (0.0010) -[2023-11-28 10:20:36,946][87424] Updated weights for policy 0, policy_version 386269 (0.0011) -[2023-11-28 10:20:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 197689344. Throughput: 0: 2753.9, 1: 2706.2. Samples: 197707284. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:20:38,445][86177] Avg episode reward: [(0, '-520.980'), (1, '-537.250')] -[2023-11-28 10:20:38,753][87426] Updated weights for policy 1, policy_version 385960 (0.0008) -[2023-11-28 10:20:39,134][87426] Updated weights for policy 1, policy_version 385970 (0.0009) -[2023-11-28 10:20:39,164][87424] Updated weights for policy 0, policy_version 386279 (0.0011) -[2023-11-28 10:20:39,518][87426] Updated weights for policy 1, policy_version 385980 (0.0012) -[2023-11-28 10:20:39,540][87424] Updated weights for policy 0, policy_version 386289 (0.0012) -[2023-11-28 10:20:39,921][87424] Updated weights for policy 0, policy_version 386299 (0.0012) -[2023-11-28 10:20:41,544][87426] Updated weights for policy 1, policy_version 385990 (0.0011) -[2023-11-28 10:20:41,923][87426] Updated weights for policy 1, policy_version 386000 (0.0011) -[2023-11-28 10:20:42,062][87424] Updated weights for policy 0, policy_version 386309 (0.0011) -[2023-11-28 10:20:42,307][87426] Updated weights for policy 1, policy_version 386010 (0.0011) -[2023-11-28 10:20:42,435][87424] Updated weights for policy 0, policy_version 386319 (0.0011) -[2023-11-28 10:20:42,818][87424] Updated weights for policy 0, policy_version 386329 (0.0011) -[2023-11-28 10:20:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 197722112. Throughput: 0: 2753.2, 1: 2701.4. Samples: 197731496. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:20:43,445][86177] Avg episode reward: [(0, '-519.570'), (1, '-524.950')] -[2023-11-28 10:20:44,765][87426] Updated weights for policy 1, policy_version 386020 (0.0012) -[2023-11-28 10:20:45,137][87426] Updated weights for policy 1, policy_version 386030 (0.0012) -[2023-11-28 10:20:45,358][87424] Updated weights for policy 0, policy_version 386339 (0.0010) -[2023-11-28 10:20:45,514][87426] Updated weights for policy 1, policy_version 386040 (0.0011) -[2023-11-28 10:20:45,740][87424] Updated weights for policy 0, policy_version 386349 (0.0010) -[2023-11-28 10:20:46,130][87424] Updated weights for policy 0, policy_version 386359 (0.0012) -[2023-11-28 10:20:48,092][87426] Updated weights for policy 1, policy_version 386050 (0.0011) -[2023-11-28 10:20:48,232][87424] Updated weights for policy 0, policy_version 386369 (0.0011) -[2023-11-28 10:20:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 197738496. Throughput: 0: 2733.9, 1: 2697.2. Samples: 197755464. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:20:48,445][86177] Avg episode reward: [(0, '-524.930'), (1, '-565.720')] -[2023-11-28 10:20:48,465][87426] Updated weights for policy 1, policy_version 386060 (0.0012) -[2023-11-28 10:20:48,612][87424] Updated weights for policy 0, policy_version 386379 (0.0009) -[2023-11-28 10:20:48,840][87426] Updated weights for policy 1, policy_version 386070 (0.0010) -[2023-11-28 10:20:48,993][87424] Updated weights for policy 0, policy_version 386389 (0.0009) -[2023-11-28 10:20:49,218][87426] Updated weights for policy 1, policy_version 386080 (0.0012) -[2023-11-28 10:20:49,381][87424] Updated weights for policy 0, policy_version 386399 (0.0011) -[2023-11-28 10:20:51,319][87426] Updated weights for policy 1, policy_version 386090 (0.0012) -[2023-11-28 10:20:51,596][87424] Updated weights for policy 0, policy_version 386409 (0.0010) -[2023-11-28 10:20:51,700][87426] Updated weights for policy 1, policy_version 386100 (0.0010) -[2023-11-28 10:20:51,981][87424] Updated weights for policy 0, policy_version 386419 (0.0011) -[2023-11-28 10:20:52,078][87426] Updated weights for policy 1, policy_version 386110 (0.0009) -[2023-11-28 10:20:52,355][87424] Updated weights for policy 0, policy_version 386429 (0.0011) -[2023-11-28 10:20:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 197771264. Throughput: 0: 2721.1, 1: 2696.9. Samples: 197788164. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:20:53,445][86177] Avg episode reward: [(0, '-532.980'), (1, '-568.310')] -[2023-11-28 10:20:54,507][87426] Updated weights for policy 1, policy_version 386120 (0.0011) -[2023-11-28 10:20:54,701][87424] Updated weights for policy 0, policy_version 386439 (0.0010) -[2023-11-28 10:20:54,885][87426] Updated weights for policy 1, policy_version 386130 (0.0012) -[2023-11-28 10:20:55,082][87424] Updated weights for policy 0, policy_version 386449 (0.0008) -[2023-11-28 10:20:55,259][87426] Updated weights for policy 1, policy_version 386140 (0.0012) -[2023-11-28 10:20:55,462][87424] Updated weights for policy 0, policy_version 386459 (0.0007) -[2023-11-28 10:20:57,120][87426] Updated weights for policy 1, policy_version 386150 (0.0009) -[2023-11-28 10:20:57,370][87424] Updated weights for policy 0, policy_version 386469 (0.0012) -[2023-11-28 10:20:57,499][87426] Updated weights for policy 1, policy_version 386160 (0.0008) -[2023-11-28 10:20:57,752][87424] Updated weights for policy 0, policy_version 386479 (0.0012) -[2023-11-28 10:20:57,883][87426] Updated weights for policy 1, policy_version 386170 (0.0008) -[2023-11-28 10:20:58,145][87424] Updated weights for policy 0, policy_version 386489 (0.0012) -[2023-11-28 10:20:58,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 197804032. Throughput: 0: 2718.8, 1: 2725.3. Samples: 197813516. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:20:58,445][86177] Avg episode reward: [(0, '-536.560'), (1, '-553.970')] -[2023-11-28 10:20:59,362][87426] Updated weights for policy 1, policy_version 386180 (0.0009) -[2023-11-28 10:20:59,745][87426] Updated weights for policy 1, policy_version 386190 (0.0009) -[2023-11-28 10:20:59,765][87424] Updated weights for policy 0, policy_version 386499 (0.0011) -[2023-11-28 10:21:00,122][87426] Updated weights for policy 1, policy_version 386200 (0.0011) -[2023-11-28 10:21:00,145][87424] Updated weights for policy 0, policy_version 386509 (0.0008) -[2023-11-28 10:21:00,524][87424] Updated weights for policy 0, policy_version 386519 (0.0010) -[2023-11-28 10:21:02,437][87426] Updated weights for policy 1, policy_version 386210 (0.0011) -[2023-11-28 10:21:02,590][87424] Updated weights for policy 0, policy_version 386529 (0.0011) -[2023-11-28 10:21:02,818][87426] Updated weights for policy 1, policy_version 386220 (0.0010) -[2023-11-28 10:21:02,981][87424] Updated weights for policy 0, policy_version 386539 (0.0012) -[2023-11-28 10:21:03,207][87426] Updated weights for policy 1, policy_version 386230 (0.0011) -[2023-11-28 10:21:03,368][87424] Updated weights for policy 0, policy_version 386549 (0.0010) -[2023-11-28 10:21:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 197820416. Throughput: 0: 2724.8, 1: 2741.9. Samples: 197838992. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:03,445][86177] Avg episode reward: [(0, '-546.230'), (1, '-553.300')] -[2023-11-28 10:21:03,581][87426] Updated weights for policy 1, policy_version 386240 (0.0008) -[2023-11-28 10:21:03,745][87424] Updated weights for policy 0, policy_version 386559 (0.0010) -[2023-11-28 10:21:05,622][87426] Updated weights for policy 1, policy_version 386250 (0.0011) -[2023-11-28 10:21:05,899][87424] Updated weights for policy 0, policy_version 386569 (0.0010) -[2023-11-28 10:21:05,991][87426] Updated weights for policy 1, policy_version 386260 (0.0011) -[2023-11-28 10:21:06,286][87424] Updated weights for policy 0, policy_version 386579 (0.0010) -[2023-11-28 10:21:06,373][87426] Updated weights for policy 1, policy_version 386270 (0.0010) -[2023-11-28 10:21:06,671][87424] Updated weights for policy 0, policy_version 386589 (0.0009) -[2023-11-28 10:21:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 197853184. Throughput: 0: 2760.1, 1: 2725.8. Samples: 197871632. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:08,446][86177] Avg episode reward: [(0, '-546.980'), (1, '-512.990')] -[2023-11-28 10:21:08,647][87424] Updated weights for policy 0, policy_version 386599 (0.0012) -[2023-11-28 10:21:08,901][87426] Updated weights for policy 1, policy_version 386280 (0.0008) -[2023-11-28 10:21:09,030][87424] Updated weights for policy 0, policy_version 386609 (0.0012) -[2023-11-28 10:21:09,277][87426] Updated weights for policy 1, policy_version 386290 (0.0009) -[2023-11-28 10:21:09,402][87424] Updated weights for policy 0, policy_version 386619 (0.0010) -[2023-11-28 10:21:09,651][87426] Updated weights for policy 1, policy_version 386300 (0.0007) -[2023-11-28 10:21:11,728][87424] Updated weights for policy 0, policy_version 386629 (0.0011) -[2023-11-28 10:21:12,035][87426] Updated weights for policy 1, policy_version 386310 (0.0010) -[2023-11-28 10:21:12,115][87424] Updated weights for policy 0, policy_version 386639 (0.0011) -[2023-11-28 10:21:12,414][87426] Updated weights for policy 1, policy_version 386320 (0.0011) -[2023-11-28 10:21:12,493][87424] Updated weights for policy 0, policy_version 386649 (0.0012) -[2023-11-28 10:21:12,800][87426] Updated weights for policy 1, policy_version 386330 (0.0009) -[2023-11-28 10:21:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 197885952. Throughput: 0: 2762.6, 1: 2726.3. Samples: 197895924. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:13,445][86177] Avg episode reward: [(0, '-544.480'), (1, '-515.670')] -[2023-11-28 10:21:15,001][87424] Updated weights for policy 0, policy_version 386659 (0.0010) -[2023-11-28 10:21:15,047][87426] Updated weights for policy 1, policy_version 386340 (0.0009) -[2023-11-28 10:21:15,386][87424] Updated weights for policy 0, policy_version 386669 (0.0010) -[2023-11-28 10:21:15,421][87426] Updated weights for policy 1, policy_version 386350 (0.0008) -[2023-11-28 10:21:15,758][87424] Updated weights for policy 0, policy_version 386679 (0.0011) -[2023-11-28 10:21:15,791][87426] Updated weights for policy 1, policy_version 386360 (0.0008) -[2023-11-28 10:21:17,582][87424] Updated weights for policy 0, policy_version 386689 (0.0011) -[2023-11-28 10:21:17,592][87426] Updated weights for policy 1, policy_version 386370 (0.0009) -[2023-11-28 10:21:17,966][87424] Updated weights for policy 0, policy_version 386699 (0.0007) -[2023-11-28 10:21:17,967][87426] Updated weights for policy 1, policy_version 386380 (0.0007) -[2023-11-28 10:21:18,344][87424] Updated weights for policy 0, policy_version 386709 (0.0007) -[2023-11-28 10:21:18,349][87426] Updated weights for policy 1, policy_version 386390 (0.0008) -[2023-11-28 10:21:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 197902336. Throughput: 0: 2701.3, 1: 2733.7. Samples: 197920348. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:18,445][86177] Avg episode reward: [(0, '-556.190'), (1, '-513.460')] -[2023-11-28 10:21:18,721][87424] Updated weights for policy 0, policy_version 386719 (0.0007) -[2023-11-28 10:21:18,730][87426] Updated weights for policy 1, policy_version 386400 (0.0011) -[2023-11-28 10:21:21,109][87424] Updated weights for policy 0, policy_version 386729 (0.0010) -[2023-11-28 10:21:21,205][87426] Updated weights for policy 1, policy_version 386410 (0.0012) -[2023-11-28 10:21:21,487][87424] Updated weights for policy 0, policy_version 386739 (0.0012) -[2023-11-28 10:21:21,584][87426] Updated weights for policy 1, policy_version 386420 (0.0012) -[2023-11-28 10:21:21,868][87424] Updated weights for policy 0, policy_version 386749 (0.0011) -[2023-11-28 10:21:21,972][87426] Updated weights for policy 1, policy_version 386430 (0.0011) -[2023-11-28 10:21:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 197935104. Throughput: 0: 2721.9, 1: 2718.2. Samples: 197952088. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:23,445][86177] Avg episode reward: [(0, '-555.010'), (1, '-513.260')] -[2023-11-28 10:21:23,973][87424] Updated weights for policy 0, policy_version 386759 (0.0012) -[2023-11-28 10:21:24,357][87424] Updated weights for policy 0, policy_version 386769 (0.0012) -[2023-11-28 10:21:24,395][87426] Updated weights for policy 1, policy_version 386440 (0.0009) -[2023-11-28 10:21:24,743][87424] Updated weights for policy 0, policy_version 386779 (0.0012) -[2023-11-28 10:21:24,773][87426] Updated weights for policy 1, policy_version 386450 (0.0008) -[2023-11-28 10:21:25,164][87426] Updated weights for policy 1, policy_version 386460 (0.0007) -[2023-11-28 10:21:27,049][87424] Updated weights for policy 0, policy_version 386789 (0.0012) -[2023-11-28 10:21:27,430][87424] Updated weights for policy 0, policy_version 386799 (0.0011) -[2023-11-28 10:21:27,462][87426] Updated weights for policy 1, policy_version 386470 (0.0010) -[2023-11-28 10:21:27,811][87424] Updated weights for policy 0, policy_version 386809 (0.0009) -[2023-11-28 10:21:27,845][87426] Updated weights for policy 1, policy_version 386480 (0.0009) -[2023-11-28 10:21:28,230][87426] Updated weights for policy 1, policy_version 386490 (0.0008) -[2023-11-28 10:21:28,445][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 197959680. Throughput: 0: 2730.8, 1: 2722.4. Samples: 197976892. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:28,446][86177] Avg episode reward: [(0, '-554.510'), (1, '-509.150')] -[2023-11-28 10:21:29,720][87424] Updated weights for policy 0, policy_version 386819 (0.0008) -[2023-11-28 10:21:30,101][87424] Updated weights for policy 0, policy_version 386829 (0.0008) -[2023-11-28 10:21:30,117][87426] Updated weights for policy 1, policy_version 386500 (0.0009) -[2023-11-28 10:21:30,486][87424] Updated weights for policy 0, policy_version 386839 (0.0009) -[2023-11-28 10:21:30,493][87426] Updated weights for policy 1, policy_version 386510 (0.0010) -[2023-11-28 10:21:30,875][87426] Updated weights for policy 1, policy_version 386520 (0.0008) -[2023-11-28 10:21:32,523][87424] Updated weights for policy 0, policy_version 386849 (0.0008) -[2023-11-28 10:21:32,823][87426] Updated weights for policy 1, policy_version 386530 (0.0008) -[2023-11-28 10:21:32,908][87424] Updated weights for policy 0, policy_version 386859 (0.0012) -[2023-11-28 10:21:33,207][87426] Updated weights for policy 1, policy_version 386540 (0.0011) -[2023-11-28 10:21:33,291][87424] Updated weights for policy 0, policy_version 386869 (0.0011) -[2023-11-28 10:21:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 197984256. Throughput: 0: 2749.1, 1: 2725.6. Samples: 198001824. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:33,445][86177] Avg episode reward: [(0, '-554.990'), (1, '-512.550')] -[2023-11-28 10:21:33,582][87426] Updated weights for policy 1, policy_version 386550 (0.0011) -[2023-11-28 10:21:33,674][87424] Updated weights for policy 0, policy_version 386879 (0.0011) -[2023-11-28 10:21:33,969][87426] Updated weights for policy 1, policy_version 386560 (0.0012) -[2023-11-28 10:21:35,939][87424] Updated weights for policy 0, policy_version 386889 (0.0008) -[2023-11-28 10:21:36,291][87426] Updated weights for policy 1, policy_version 386570 (0.0010) -[2023-11-28 10:21:36,322][87424] Updated weights for policy 0, policy_version 386899 (0.0008) -[2023-11-28 10:21:36,688][87426] Updated weights for policy 1, policy_version 386580 (0.0009) -[2023-11-28 10:21:36,708][87424] Updated weights for policy 0, policy_version 386909 (0.0009) -[2023-11-28 10:21:37,058][87426] Updated weights for policy 1, policy_version 386590 (0.0010) -[2023-11-28 10:21:38,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 198017024. Throughput: 0: 2745.4, 1: 2730.5. Samples: 198034580. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:38,445][86177] Avg episode reward: [(0, '-543.200'), (1, '-539.940')] -[2023-11-28 10:21:38,531][87424] Updated weights for policy 0, policy_version 386919 (0.0010) -[2023-11-28 10:21:38,916][87424] Updated weights for policy 0, policy_version 386929 (0.0011) -[2023-11-28 10:21:39,111][87426] Updated weights for policy 1, policy_version 386600 (0.0011) -[2023-11-28 10:21:39,306][87424] Updated weights for policy 0, policy_version 386939 (0.0011) -[2023-11-28 10:21:39,494][87426] Updated weights for policy 1, policy_version 386610 (0.0010) -[2023-11-28 10:21:39,888][87426] Updated weights for policy 1, policy_version 386620 (0.0010) -[2023-11-28 10:21:41,775][87424] Updated weights for policy 0, policy_version 386949 (0.0010) -[2023-11-28 10:21:42,050][87426] Updated weights for policy 1, policy_version 386630 (0.0011) -[2023-11-28 10:21:42,159][87424] Updated weights for policy 0, policy_version 386959 (0.0011) -[2023-11-28 10:21:42,434][87426] Updated weights for policy 1, policy_version 386640 (0.0011) -[2023-11-28 10:21:42,532][87424] Updated weights for policy 0, policy_version 386969 (0.0011) -[2023-11-28 10:21:42,810][87426] Updated weights for policy 1, policy_version 386650 (0.0011) -[2023-11-28 10:21:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 198049792. Throughput: 0: 2740.2, 1: 2711.2. Samples: 198058828. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:43,445][86177] Avg episode reward: [(0, '-535.130'), (1, '-538.590')] -[2023-11-28 10:21:44,649][87424] Updated weights for policy 0, policy_version 386979 (0.0012) -[2023-11-28 10:21:44,916][87426] Updated weights for policy 1, policy_version 386660 (0.0010) -[2023-11-28 10:21:45,027][87424] Updated weights for policy 0, policy_version 386989 (0.0011) -[2023-11-28 10:21:45,290][87426] Updated weights for policy 1, policy_version 386670 (0.0011) -[2023-11-28 10:21:45,413][87424] Updated weights for policy 0, policy_version 386999 (0.0009) -[2023-11-28 10:21:45,671][87426] Updated weights for policy 1, policy_version 386680 (0.0010) -[2023-11-28 10:21:47,390][87424] Updated weights for policy 0, policy_version 387009 (0.0010) -[2023-11-28 10:21:47,512][87426] Updated weights for policy 1, policy_version 386690 (0.0012) -[2023-11-28 10:21:47,779][87424] Updated weights for policy 0, policy_version 387019 (0.0010) -[2023-11-28 10:21:47,879][87426] Updated weights for policy 1, policy_version 386700 (0.0011) -[2023-11-28 10:21:48,168][87424] Updated weights for policy 0, policy_version 387029 (0.0008) -[2023-11-28 10:21:48,259][87426] Updated weights for policy 1, policy_version 386710 (0.0011) -[2023-11-28 10:21:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 198066176. Throughput: 0: 2722.4, 1: 2721.7. Samples: 198083976. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:48,445][86177] Avg episode reward: [(0, '-532.670'), (1, '-549.410')] -[2023-11-28 10:21:48,538][87424] Updated weights for policy 0, policy_version 387039 (0.0011) -[2023-11-28 10:21:48,640][87426] Updated weights for policy 1, policy_version 386720 (0.0009) -[2023-11-28 10:21:50,661][87424] Updated weights for policy 0, policy_version 387049 (0.0012) -[2023-11-28 10:21:51,038][87424] Updated weights for policy 0, policy_version 387059 (0.0012) -[2023-11-28 10:21:51,071][87426] Updated weights for policy 1, policy_version 386730 (0.0011) -[2023-11-28 10:21:51,407][87424] Updated weights for policy 0, policy_version 387069 (0.0012) -[2023-11-28 10:21:51,439][87426] Updated weights for policy 1, policy_version 386740 (0.0011) -[2023-11-28 10:21:51,821][87426] Updated weights for policy 1, policy_version 386750 (0.0012) -[2023-11-28 10:21:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 198098944. Throughput: 0: 2682.0, 1: 2741.3. Samples: 198115676. Policy #0 lag: (min: 28.0, avg: 46.6, max: 60.0) -[2023-11-28 10:21:53,445][86177] Avg episode reward: [(0, '-525.610'), (1, '-541.310')] -[2023-11-28 10:21:54,025][87424] Updated weights for policy 0, policy_version 387079 (0.0012) -[2023-11-28 10:21:54,415][87424] Updated weights for policy 0, policy_version 387089 (0.0011) -[2023-11-28 10:21:54,480][87426] Updated weights for policy 1, policy_version 386760 (0.0010) -[2023-11-28 10:21:54,795][87424] Updated weights for policy 0, policy_version 387099 (0.0009) -[2023-11-28 10:21:54,865][87426] Updated weights for policy 1, policy_version 386770 (0.0009) -[2023-11-28 10:21:55,243][87426] Updated weights for policy 1, policy_version 386780 (0.0010) -[2023-11-28 10:21:56,901][87424] Updated weights for policy 0, policy_version 387109 (0.0009) -[2023-11-28 10:21:57,286][87424] Updated weights for policy 0, policy_version 387119 (0.0007) -[2023-11-28 10:21:57,671][87424] Updated weights for policy 0, policy_version 387129 (0.0009) -[2023-11-28 10:21:57,761][87426] Updated weights for policy 1, policy_version 386790 (0.0007) -[2023-11-28 10:21:58,131][87426] Updated weights for policy 1, policy_version 386800 (0.0008) -[2023-11-28 10:21:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 198123520. Throughput: 0: 2670.9, 1: 2718.3. Samples: 198138436. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:21:58,445][86177] Avg episode reward: [(0, '-521.360'), (1, '-527.390')] -[2023-11-28 10:21:58,515][87426] Updated weights for policy 1, policy_version 386810 (0.0008) -[2023-11-28 10:21:59,637][87424] Updated weights for policy 0, policy_version 387139 (0.0011) -[2023-11-28 10:22:00,011][87424] Updated weights for policy 0, policy_version 387149 (0.0012) -[2023-11-28 10:22:00,387][87424] Updated weights for policy 0, policy_version 387159 (0.0011) -[2023-11-28 10:22:00,786][87426] Updated weights for policy 1, policy_version 386820 (0.0009) -[2023-11-28 10:22:01,169][87426] Updated weights for policy 1, policy_version 386830 (0.0009) -[2023-11-28 10:22:01,562][87426] Updated weights for policy 1, policy_version 386840 (0.0009) -[2023-11-28 10:22:02,719][87424] Updated weights for policy 0, policy_version 387169 (0.0010) -[2023-11-28 10:22:03,097][87424] Updated weights for policy 0, policy_version 387179 (0.0011) -[2023-11-28 10:22:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 198148096. Throughput: 0: 2707.5, 1: 2698.3. Samples: 198163608. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:03,445][86177] Avg episode reward: [(0, '-525.790'), (1, '-527.130')] -[2023-11-28 10:22:03,476][87424] Updated weights for policy 0, policy_version 387189 (0.0008) -[2023-11-28 10:22:03,647][87426] Updated weights for policy 1, policy_version 386850 (0.0012) -[2023-11-28 10:22:03,858][87424] Updated weights for policy 0, policy_version 387199 (0.0008) -[2023-11-28 10:22:04,031][87426] Updated weights for policy 1, policy_version 386860 (0.0012) -[2023-11-28 10:22:04,405][87426] Updated weights for policy 1, policy_version 386870 (0.0011) -[2023-11-28 10:22:04,786][87426] Updated weights for policy 1, policy_version 386880 (0.0010) -[2023-11-28 10:22:05,978][87424] Updated weights for policy 0, policy_version 387209 (0.0011) -[2023-11-28 10:22:06,363][87424] Updated weights for policy 0, policy_version 387219 (0.0012) -[2023-11-28 10:22:06,741][87424] Updated weights for policy 0, policy_version 387229 (0.0010) -[2023-11-28 10:22:06,867][87426] Updated weights for policy 1, policy_version 386890 (0.0016) -[2023-11-28 10:22:07,240][87426] Updated weights for policy 1, policy_version 386900 (0.0012) -[2023-11-28 10:22:07,626][87426] Updated weights for policy 1, policy_version 386910 (0.0012) -[2023-11-28 10:22:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 198180864. Throughput: 0: 2708.9, 1: 2726.7. Samples: 198196692. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:08,445][86177] Avg episode reward: [(0, '-527.560'), (1, '-607.770')] -[2023-11-28 10:22:09,213][87424] Updated weights for policy 0, policy_version 387239 (0.0010) -[2023-11-28 10:22:09,578][87426] Updated weights for policy 1, policy_version 386920 (0.0012) -[2023-11-28 10:22:09,597][87424] Updated weights for policy 0, policy_version 387249 (0.0011) -[2023-11-28 10:22:09,951][87426] Updated weights for policy 1, policy_version 386930 (0.0011) -[2023-11-28 10:22:09,983][87424] Updated weights for policy 0, policy_version 387259 (0.0010) -[2023-11-28 10:22:10,328][87426] Updated weights for policy 1, policy_version 386940 (0.0011) -[2023-11-28 10:22:11,823][87424] Updated weights for policy 0, policy_version 387269 (0.0012) -[2023-11-28 10:22:12,204][87424] Updated weights for policy 0, policy_version 387279 (0.0011) -[2023-11-28 10:22:12,582][87424] Updated weights for policy 0, policy_version 387289 (0.0011) -[2023-11-28 10:22:12,840][87426] Updated weights for policy 1, policy_version 386950 (0.0011) -[2023-11-28 10:22:13,219][87426] Updated weights for policy 1, policy_version 386960 (0.0012) -[2023-11-28 10:22:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 198205440. Throughput: 0: 2698.5, 1: 2704.7. Samples: 198220036. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:13,445][86177] Avg episode reward: [(0, '-532.410'), (1, '-612.410')] -[2023-11-28 10:22:13,599][87426] Updated weights for policy 1, policy_version 386970 (0.0011) -[2023-11-28 10:22:15,233][87424] Updated weights for policy 0, policy_version 387299 (0.0011) -[2023-11-28 10:22:15,625][87424] Updated weights for policy 0, policy_version 387309 (0.0010) -[2023-11-28 10:22:15,745][87426] Updated weights for policy 1, policy_version 386980 (0.0011) -[2023-11-28 10:22:15,995][87424] Updated weights for policy 0, policy_version 387319 (0.0011) -[2023-11-28 10:22:16,122][87426] Updated weights for policy 1, policy_version 386990 (0.0011) -[2023-11-28 10:22:16,500][87426] Updated weights for policy 1, policy_version 387000 (0.0012) -[2023-11-28 10:22:17,910][87424] Updated weights for policy 0, policy_version 387329 (0.0012) -[2023-11-28 10:22:18,288][87424] Updated weights for policy 0, policy_version 387339 (0.0012) -[2023-11-28 10:22:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 198230016. Throughput: 0: 2697.6, 1: 2697.7. Samples: 198244612. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:18,445][86177] Avg episode reward: [(0, '-533.150'), (1, '-629.230')] -[2023-11-28 10:22:18,453][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000387008_99074048.pth... -[2023-11-28 10:22:18,484][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000384512_98435072.pth -[2023-11-28 10:22:18,668][87424] Updated weights for policy 0, policy_version 387349 (0.0012) -[2023-11-28 10:22:18,691][87426] Updated weights for policy 1, policy_version 387010 (0.0011) -[2023-11-28 10:22:19,059][87424] Updated weights for policy 0, policy_version 387359 (0.0012) -[2023-11-28 10:22:19,071][87426] Updated weights for policy 1, policy_version 387020 (0.0008) -[2023-11-28 10:22:19,097][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000387360_99164160.pth... -[2023-11-28 10:22:19,143][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000384800_98508800.pth -[2023-11-28 10:22:19,444][87426] Updated weights for policy 1, policy_version 387030 (0.0008) -[2023-11-28 10:22:19,818][87426] Updated weights for policy 1, policy_version 387040 (0.0008) -[2023-11-28 10:22:21,119][87424] Updated weights for policy 0, policy_version 387369 (0.0010) -[2023-11-28 10:22:21,501][87424] Updated weights for policy 0, policy_version 387379 (0.0008) -[2023-11-28 10:22:21,892][87424] Updated weights for policy 0, policy_version 387389 (0.0009) -[2023-11-28 10:22:22,409][87426] Updated weights for policy 1, policy_version 387050 (0.0011) -[2023-11-28 10:22:22,793][87426] Updated weights for policy 1, policy_version 387060 (0.0011) -[2023-11-28 10:22:23,167][87426] Updated weights for policy 1, policy_version 387070 (0.0011) -[2023-11-28 10:22:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 198262784. Throughput: 0: 2688.5, 1: 2673.0. Samples: 198275848. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:23,445][86177] Avg episode reward: [(0, '-532.740'), (1, '-645.240')] -[2023-11-28 10:22:24,066][87424] Updated weights for policy 0, policy_version 387399 (0.0011) -[2023-11-28 10:22:24,445][87424] Updated weights for policy 0, policy_version 387409 (0.0011) -[2023-11-28 10:22:24,830][87424] Updated weights for policy 0, policy_version 387419 (0.0008) -[2023-11-28 10:22:25,303][87426] Updated weights for policy 1, policy_version 387080 (0.0008) -[2023-11-28 10:22:25,687][87426] Updated weights for policy 1, policy_version 387090 (0.0007) -[2023-11-28 10:22:26,072][87426] Updated weights for policy 1, policy_version 387100 (0.0007) -[2023-11-28 10:22:26,626][87424] Updated weights for policy 0, policy_version 387429 (0.0010) -[2023-11-28 10:22:27,011][87424] Updated weights for policy 0, policy_version 387439 (0.0007) -[2023-11-28 10:22:27,388][87424] Updated weights for policy 0, policy_version 387449 (0.0007) -[2023-11-28 10:22:27,853][87426] Updated weights for policy 1, policy_version 387110 (0.0007) -[2023-11-28 10:22:28,234][87426] Updated weights for policy 1, policy_version 387120 (0.0008) -[2023-11-28 10:22:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5442.8). Total num frames: 198287360. Throughput: 0: 2697.2, 1: 2680.7. Samples: 198300832. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:28,445][86177] Avg episode reward: [(0, '-536.890'), (1, '-586.030')] -[2023-11-28 10:22:28,611][87426] Updated weights for policy 1, policy_version 387130 (0.0007) -[2023-11-28 10:22:29,861][87424] Updated weights for policy 0, policy_version 387459 (0.0008) -[2023-11-28 10:22:30,233][87424] Updated weights for policy 0, policy_version 387469 (0.0008) -[2023-11-28 10:22:30,522][87426] Updated weights for policy 1, policy_version 387140 (0.0010) -[2023-11-28 10:22:30,619][87424] Updated weights for policy 0, policy_version 387479 (0.0008) -[2023-11-28 10:22:30,892][87426] Updated weights for policy 1, policy_version 387150 (0.0007) -[2023-11-28 10:22:31,278][87426] Updated weights for policy 1, policy_version 387160 (0.0007) -[2023-11-28 10:22:33,183][87424] Updated weights for policy 0, policy_version 387489 (0.0009) -[2023-11-28 10:22:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 198311936. Throughput: 0: 2685.8, 1: 2675.4. Samples: 198325228. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:33,445][86177] Avg episode reward: [(0, '-537.030'), (1, '-578.760')] -[2023-11-28 10:22:33,564][87424] Updated weights for policy 0, policy_version 387499 (0.0011) -[2023-11-28 10:22:33,602][87426] Updated weights for policy 1, policy_version 387170 (0.0008) -[2023-11-28 10:22:33,941][87424] Updated weights for policy 0, policy_version 387509 (0.0008) -[2023-11-28 10:22:33,985][87426] Updated weights for policy 1, policy_version 387180 (0.0007) -[2023-11-28 10:22:34,324][87424] Updated weights for policy 0, policy_version 387519 (0.0007) -[2023-11-28 10:22:34,362][87426] Updated weights for policy 1, policy_version 387190 (0.0007) -[2023-11-28 10:22:34,736][87426] Updated weights for policy 1, policy_version 387200 (0.0008) -[2023-11-28 10:22:36,931][87424] Updated weights for policy 0, policy_version 387529 (0.0009) -[2023-11-28 10:22:37,198][87426] Updated weights for policy 1, policy_version 387210 (0.0008) -[2023-11-28 10:22:37,321][87424] Updated weights for policy 0, policy_version 387539 (0.0010) -[2023-11-28 10:22:37,582][87426] Updated weights for policy 1, policy_version 387220 (0.0009) -[2023-11-28 10:22:37,704][87424] Updated weights for policy 0, policy_version 387549 (0.0012) -[2023-11-28 10:22:37,962][87426] Updated weights for policy 1, policy_version 387230 (0.0012) -[2023-11-28 10:22:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 198344704. Throughput: 0: 2688.6, 1: 2670.9. Samples: 198356856. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:38,445][86177] Avg episode reward: [(0, '-539.220'), (1, '-549.770')] -[2023-11-28 10:22:39,808][87424] Updated weights for policy 0, policy_version 387559 (0.0010) -[2023-11-28 10:22:40,069][87426] Updated weights for policy 1, policy_version 387240 (0.0016) -[2023-11-28 10:22:40,194][87424] Updated weights for policy 0, policy_version 387569 (0.0011) -[2023-11-28 10:22:40,445][87426] Updated weights for policy 1, policy_version 387250 (0.0011) -[2023-11-28 10:22:40,579][87424] Updated weights for policy 0, policy_version 387579 (0.0012) -[2023-11-28 10:22:40,829][87426] Updated weights for policy 1, policy_version 387260 (0.0011) -[2023-11-28 10:22:43,116][87424] Updated weights for policy 0, policy_version 387589 (0.0011) -[2023-11-28 10:22:43,422][87426] Updated weights for policy 1, policy_version 387270 (0.0010) -[2023-11-28 10:22:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 198361088. Throughput: 0: 2686.0, 1: 2695.6. Samples: 198380612. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:43,445][86177] Avg episode reward: [(0, '-534.360'), (1, '-550.050')] -[2023-11-28 10:22:43,485][87424] Updated weights for policy 0, policy_version 387599 (0.0010) -[2023-11-28 10:22:43,800][87426] Updated weights for policy 1, policy_version 387280 (0.0007) -[2023-11-28 10:22:43,868][87424] Updated weights for policy 0, policy_version 387609 (0.0007) -[2023-11-28 10:22:44,180][87426] Updated weights for policy 1, policy_version 387290 (0.0008) -[2023-11-28 10:22:46,131][87424] Updated weights for policy 0, policy_version 387619 (0.0008) -[2023-11-28 10:22:46,184][87426] Updated weights for policy 1, policy_version 387300 (0.0009) -[2023-11-28 10:22:46,519][87424] Updated weights for policy 0, policy_version 387629 (0.0009) -[2023-11-28 10:22:46,554][87426] Updated weights for policy 1, policy_version 387310 (0.0011) -[2023-11-28 10:22:46,905][87424] Updated weights for policy 0, policy_version 387639 (0.0011) -[2023-11-28 10:22:46,932][87426] Updated weights for policy 1, policy_version 387320 (0.0012) -[2023-11-28 10:22:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 198393856. Throughput: 0: 2663.0, 1: 2703.8. Samples: 198405116. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:48,445][86177] Avg episode reward: [(0, '-537.150'), (1, '-525.230')] -[2023-11-28 10:22:48,725][87424] Updated weights for policy 0, policy_version 387649 (0.0008) -[2023-11-28 10:22:49,052][87426] Updated weights for policy 1, policy_version 387330 (0.0011) -[2023-11-28 10:22:49,111][87424] Updated weights for policy 0, policy_version 387659 (0.0011) -[2023-11-28 10:22:49,429][87426] Updated weights for policy 1, policy_version 387340 (0.0010) -[2023-11-28 10:22:49,487][87424] Updated weights for policy 0, policy_version 387669 (0.0012) -[2023-11-28 10:22:49,813][87426] Updated weights for policy 1, policy_version 387350 (0.0009) -[2023-11-28 10:22:49,868][87424] Updated weights for policy 0, policy_version 387679 (0.0012) -[2023-11-28 10:22:50,184][87426] Updated weights for policy 1, policy_version 387360 (0.0008) -[2023-11-28 10:22:51,944][87424] Updated weights for policy 0, policy_version 387689 (0.0012) -[2023-11-28 10:22:52,324][87424] Updated weights for policy 0, policy_version 387699 (0.0012) -[2023-11-28 10:22:52,693][87426] Updated weights for policy 1, policy_version 387370 (0.0009) -[2023-11-28 10:22:52,703][87424] Updated weights for policy 0, policy_version 387709 (0.0008) -[2023-11-28 10:22:53,075][87426] Updated weights for policy 1, policy_version 387380 (0.0012) -[2023-11-28 10:22:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 198418432. Throughput: 0: 2677.4, 1: 2670.6. Samples: 198437352. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:53,445][86177] Avg episode reward: [(0, '-552.270'), (1, '-531.310')] -[2023-11-28 10:22:53,448][87426] Updated weights for policy 1, policy_version 387390 (0.0013) -[2023-11-28 10:22:55,098][87424] Updated weights for policy 0, policy_version 387719 (0.0011) -[2023-11-28 10:22:55,475][87424] Updated weights for policy 0, policy_version 387729 (0.0010) -[2023-11-28 10:22:55,858][87424] Updated weights for policy 0, policy_version 387739 (0.0007) -[2023-11-28 10:22:56,075][87426] Updated weights for policy 1, policy_version 387400 (0.0010) -[2023-11-28 10:22:56,453][87426] Updated weights for policy 1, policy_version 387410 (0.0011) -[2023-11-28 10:22:56,828][87426] Updated weights for policy 1, policy_version 387420 (0.0010) -[2023-11-28 10:22:57,672][87424] Updated weights for policy 0, policy_version 387749 (0.0010) -[2023-11-28 10:22:58,063][87424] Updated weights for policy 0, policy_version 387759 (0.0011) -[2023-11-28 10:22:58,434][87426] Updated weights for policy 1, policy_version 387430 (0.0007) -[2023-11-28 10:22:58,434][87424] Updated weights for policy 0, policy_version 387769 (0.0012) -[2023-11-28 10:22:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 198443008. Throughput: 0: 2667.1, 1: 2703.6. Samples: 198461720. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:22:58,445][86177] Avg episode reward: [(0, '-562.360'), (1, '-521.740')] -[2023-11-28 10:22:58,820][87426] Updated weights for policy 1, policy_version 387440 (0.0008) -[2023-11-28 10:22:59,196][87426] Updated weights for policy 1, policy_version 387450 (0.0008) -[2023-11-28 10:23:00,745][87424] Updated weights for policy 0, policy_version 387779 (0.0012) -[2023-11-28 10:23:00,927][87426] Updated weights for policy 1, policy_version 387460 (0.0009) -[2023-11-28 10:23:01,132][87424] Updated weights for policy 0, policy_version 387789 (0.0012) -[2023-11-28 10:23:01,311][87426] Updated weights for policy 1, policy_version 387470 (0.0010) -[2023-11-28 10:23:01,513][87424] Updated weights for policy 0, policy_version 387799 (0.0011) -[2023-11-28 10:23:01,683][87426] Updated weights for policy 1, policy_version 387480 (0.0011) -[2023-11-28 10:23:03,401][87424] Updated weights for policy 0, policy_version 387809 (0.0010) -[2023-11-28 10:23:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 198475776. Throughput: 0: 2661.3, 1: 2706.4. Samples: 198486160. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:23:03,445][86177] Avg episode reward: [(0, '-576.440'), (1, '-554.340')] -[2023-11-28 10:23:03,787][87424] Updated weights for policy 0, policy_version 387819 (0.0008) -[2023-11-28 10:23:04,102][87426] Updated weights for policy 1, policy_version 387490 (0.0010) -[2023-11-28 10:23:04,178][87424] Updated weights for policy 0, policy_version 387829 (0.0008) -[2023-11-28 10:23:04,489][87426] Updated weights for policy 1, policy_version 387500 (0.0008) -[2023-11-28 10:23:04,563][87424] Updated weights for policy 0, policy_version 387839 (0.0008) -[2023-11-28 10:23:04,865][87426] Updated weights for policy 1, policy_version 387510 (0.0010) -[2023-11-28 10:23:05,244][87426] Updated weights for policy 1, policy_version 387520 (0.0008) -[2023-11-28 10:23:06,673][87424] Updated weights for policy 0, policy_version 387849 (0.0011) -[2023-11-28 10:23:06,951][87426] Updated weights for policy 1, policy_version 387530 (0.0010) -[2023-11-28 10:23:07,055][87424] Updated weights for policy 0, policy_version 387859 (0.0010) -[2023-11-28 10:23:07,322][87426] Updated weights for policy 1, policy_version 387540 (0.0008) -[2023-11-28 10:23:07,434][87424] Updated weights for policy 0, policy_version 387869 (0.0011) -[2023-11-28 10:23:07,708][87426] Updated weights for policy 1, policy_version 387550 (0.0008) -[2023-11-28 10:23:08,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 198508544. Throughput: 0: 2670.8, 1: 2724.2. Samples: 198518624. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:23:08,445][86177] Avg episode reward: [(0, '-605.210'), (1, '-556.050')] -[2023-11-28 10:23:09,745][87424] Updated weights for policy 0, policy_version 387879 (0.0012) -[2023-11-28 10:23:10,131][87424] Updated weights for policy 0, policy_version 387889 (0.0011) -[2023-11-28 10:23:10,143][87426] Updated weights for policy 1, policy_version 387560 (0.0012) -[2023-11-28 10:23:10,505][87424] Updated weights for policy 0, policy_version 387899 (0.0011) -[2023-11-28 10:23:10,509][87426] Updated weights for policy 1, policy_version 387570 (0.0009) -[2023-11-28 10:23:10,887][87426] Updated weights for policy 1, policy_version 387580 (0.0011) -[2023-11-28 10:23:13,140][87424] Updated weights for policy 0, policy_version 387909 (0.0009) -[2023-11-28 10:23:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 198524928. Throughput: 0: 2665.4, 1: 2702.4. Samples: 198542384. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:23:13,445][86177] Avg episode reward: [(0, '-594.620'), (1, '-543.750')] -[2023-11-28 10:23:13,518][87424] Updated weights for policy 0, policy_version 387919 (0.0010) -[2023-11-28 10:23:13,577][87426] Updated weights for policy 1, policy_version 387590 (0.0011) -[2023-11-28 10:23:13,903][87424] Updated weights for policy 0, policy_version 387929 (0.0007) -[2023-11-28 10:23:13,952][87426] Updated weights for policy 1, policy_version 387600 (0.0010) -[2023-11-28 10:23:14,329][87426] Updated weights for policy 1, policy_version 387610 (0.0007) -[2023-11-28 10:23:16,332][87424] Updated weights for policy 0, policy_version 387939 (0.0009) -[2023-11-28 10:23:16,421][87426] Updated weights for policy 1, policy_version 387620 (0.0008) -[2023-11-28 10:23:16,702][87424] Updated weights for policy 0, policy_version 387949 (0.0012) -[2023-11-28 10:23:16,803][87426] Updated weights for policy 1, policy_version 387630 (0.0007) -[2023-11-28 10:23:17,082][87424] Updated weights for policy 0, policy_version 387959 (0.0012) -[2023-11-28 10:23:17,194][87426] Updated weights for policy 1, policy_version 387640 (0.0008) -[2023-11-28 10:23:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 198557696. Throughput: 0: 2684.0, 1: 2682.0. Samples: 198566700. Policy #0 lag: (min: 18.0, avg: 31.8, max: 50.0) -[2023-11-28 10:23:18,445][86177] Avg episode reward: [(0, '-577.480'), (1, '-543.860')] -[2023-11-28 10:23:18,941][87424] Updated weights for policy 0, policy_version 387969 (0.0012) -[2023-11-28 10:23:19,323][87424] Updated weights for policy 0, policy_version 387979 (0.0011) -[2023-11-28 10:23:19,700][87424] Updated weights for policy 0, policy_version 387989 (0.0012) -[2023-11-28 10:23:19,707][87426] Updated weights for policy 1, policy_version 387650 (0.0008) -[2023-11-28 10:23:20,077][87426] Updated weights for policy 1, policy_version 387660 (0.0012) -[2023-11-28 10:23:20,086][87424] Updated weights for policy 0, policy_version 387999 (0.0012) -[2023-11-28 10:23:20,457][87426] Updated weights for policy 1, policy_version 387670 (0.0010) -[2023-11-28 10:23:20,840][87426] Updated weights for policy 1, policy_version 387680 (0.0008) -[2023-11-28 10:23:22,316][87424] Updated weights for policy 0, policy_version 388009 (0.0010) -[2023-11-28 10:23:22,693][87424] Updated weights for policy 0, policy_version 388019 (0.0011) -[2023-11-28 10:23:23,072][87424] Updated weights for policy 0, policy_version 388029 (0.0011) -[2023-11-28 10:23:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 198582272. Throughput: 0: 2704.9, 1: 2655.1. Samples: 198598056. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:23:23,445][86177] Avg episode reward: [(0, '-575.510'), (1, '-503.900')] -[2023-11-28 10:23:23,486][87426] Updated weights for policy 1, policy_version 387690 (0.0012) -[2023-11-28 10:23:23,860][87426] Updated weights for policy 1, policy_version 387700 (0.0012) -[2023-11-28 10:23:24,235][87426] Updated weights for policy 1, policy_version 387710 (0.0012) -[2023-11-28 10:23:25,008][87424] Updated weights for policy 0, policy_version 388039 (0.0012) -[2023-11-28 10:23:25,391][87424] Updated weights for policy 0, policy_version 388049 (0.0010) -[2023-11-28 10:23:25,772][87424] Updated weights for policy 0, policy_version 388059 (0.0007) -[2023-11-28 10:23:26,571][87426] Updated weights for policy 1, policy_version 387720 (0.0011) -[2023-11-28 10:23:26,951][87426] Updated weights for policy 1, policy_version 387730 (0.0007) -[2023-11-28 10:23:27,334][87426] Updated weights for policy 1, policy_version 387740 (0.0007) -[2023-11-28 10:23:27,397][87424] Updated weights for policy 0, policy_version 388069 (0.0008) -[2023-11-28 10:23:27,786][87424] Updated weights for policy 0, policy_version 388079 (0.0007) -[2023-11-28 10:23:28,167][87424] Updated weights for policy 0, policy_version 388089 (0.0007) -[2023-11-28 10:23:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 198615040. Throughput: 0: 2722.7, 1: 2651.5. Samples: 198622448. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:23:28,445][86177] Avg episode reward: [(0, '-544.270'), (1, '-512.920')] -[2023-11-28 10:23:29,739][87426] Updated weights for policy 1, policy_version 387750 (0.0008) -[2023-11-28 10:23:30,108][87426] Updated weights for policy 1, policy_version 387760 (0.0010) -[2023-11-28 10:23:30,260][87424] Updated weights for policy 0, policy_version 388099 (0.0009) -[2023-11-28 10:23:30,483][87426] Updated weights for policy 1, policy_version 387770 (0.0012) -[2023-11-28 10:23:30,636][87424] Updated weights for policy 0, policy_version 388109 (0.0012) -[2023-11-28 10:23:31,015][87424] Updated weights for policy 0, policy_version 388119 (0.0008) -[2023-11-28 10:23:32,722][87426] Updated weights for policy 1, policy_version 387780 (0.0010) -[2023-11-28 10:23:33,095][87426] Updated weights for policy 1, policy_version 387790 (0.0010) -[2023-11-28 10:23:33,317][87424] Updated weights for policy 0, policy_version 388129 (0.0008) -[2023-11-28 10:23:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 198631424. Throughput: 0: 2749.8, 1: 2634.1. Samples: 198647392. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:23:33,445][86177] Avg episode reward: [(0, '-544.430'), (1, '-506.080')] -[2023-11-28 10:23:33,472][87426] Updated weights for policy 1, policy_version 387800 (0.0011) -[2023-11-28 10:23:33,698][87424] Updated weights for policy 0, policy_version 388139 (0.0008) -[2023-11-28 10:23:34,085][87424] Updated weights for policy 0, policy_version 388149 (0.0012) -[2023-11-28 10:23:34,467][87424] Updated weights for policy 0, policy_version 388159 (0.0012) -[2023-11-28 10:23:35,208][87426] Updated weights for policy 1, policy_version 387810 (0.0009) -[2023-11-28 10:23:35,589][87426] Updated weights for policy 1, policy_version 387820 (0.0011) -[2023-11-28 10:23:35,965][87426] Updated weights for policy 1, policy_version 387830 (0.0012) -[2023-11-28 10:23:36,338][87426] Updated weights for policy 1, policy_version 387840 (0.0012) -[2023-11-28 10:23:37,008][87424] Updated weights for policy 0, policy_version 388169 (0.0012) -[2023-11-28 10:23:37,390][87424] Updated weights for policy 0, policy_version 388179 (0.0012) -[2023-11-28 10:23:37,774][87424] Updated weights for policy 0, policy_version 388189 (0.0008) -[2023-11-28 10:23:38,195][87426] Updated weights for policy 1, policy_version 387850 (0.0008) -[2023-11-28 10:23:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5442.8). Total num frames: 198664192. Throughput: 0: 2735.0, 1: 2664.7. Samples: 198680340. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:23:38,445][86177] Avg episode reward: [(0, '-544.120'), (1, '-522.410')] -[2023-11-28 10:23:38,578][87426] Updated weights for policy 1, policy_version 387860 (0.0012) -[2023-11-28 10:23:38,959][87426] Updated weights for policy 1, policy_version 387870 (0.0011) -[2023-11-28 10:23:40,291][87424] Updated weights for policy 0, policy_version 388199 (0.0011) -[2023-11-28 10:23:40,669][87424] Updated weights for policy 0, policy_version 388209 (0.0012) -[2023-11-28 10:23:41,043][87424] Updated weights for policy 0, policy_version 388219 (0.0012) -[2023-11-28 10:23:41,461][87426] Updated weights for policy 1, policy_version 387880 (0.0011) -[2023-11-28 10:23:41,846][87426] Updated weights for policy 1, policy_version 387890 (0.0011) -[2023-11-28 10:23:42,219][87426] Updated weights for policy 1, policy_version 387900 (0.0012) -[2023-11-28 10:23:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 198688768. Throughput: 0: 2750.0, 1: 2642.9. Samples: 198704400. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:23:43,445][86177] Avg episode reward: [(0, '-542.290'), (1, '-522.490')] -[2023-11-28 10:23:43,621][87424] Updated weights for policy 0, policy_version 388229 (0.0010) -[2023-11-28 10:23:43,998][87424] Updated weights for policy 0, policy_version 388239 (0.0008) -[2023-11-28 10:23:44,197][87426] Updated weights for policy 1, policy_version 387910 (0.0009) -[2023-11-28 10:23:44,389][87424] Updated weights for policy 0, policy_version 388249 (0.0008) -[2023-11-28 10:23:44,581][87426] Updated weights for policy 1, policy_version 387920 (0.0008) -[2023-11-28 10:23:44,966][87426] Updated weights for policy 1, policy_version 387930 (0.0007) -[2023-11-28 10:23:46,390][87424] Updated weights for policy 0, policy_version 388259 (0.0009) -[2023-11-28 10:23:46,767][87424] Updated weights for policy 0, policy_version 388269 (0.0012) -[2023-11-28 10:23:47,144][87424] Updated weights for policy 0, policy_version 388279 (0.0012) -[2023-11-28 10:23:47,537][87426] Updated weights for policy 1, policy_version 387940 (0.0009) -[2023-11-28 10:23:47,919][87426] Updated weights for policy 1, policy_version 387950 (0.0009) -[2023-11-28 10:23:48,309][87426] Updated weights for policy 1, policy_version 387960 (0.0007) -[2023-11-28 10:23:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 198713344. Throughput: 0: 2739.3, 1: 2653.1. Samples: 198728820. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:23:48,446][86177] Avg episode reward: [(0, '-537.970'), (1, '-563.170')] -[2023-11-28 10:23:49,689][87424] Updated weights for policy 0, policy_version 388289 (0.0011) -[2023-11-28 10:23:50,074][87424] Updated weights for policy 0, policy_version 388299 (0.0011) -[2023-11-28 10:23:50,462][87424] Updated weights for policy 0, policy_version 388309 (0.0011) -[2023-11-28 10:23:50,761][87426] Updated weights for policy 1, policy_version 387970 (0.0008) -[2023-11-28 10:23:50,855][87424] Updated weights for policy 0, policy_version 388319 (0.0008) -[2023-11-28 10:23:51,145][87426] Updated weights for policy 1, policy_version 387980 (0.0012) -[2023-11-28 10:23:51,518][87426] Updated weights for policy 1, policy_version 387990 (0.0012) -[2023-11-28 10:23:51,895][87426] Updated weights for policy 1, policy_version 388000 (0.0012) -[2023-11-28 10:23:53,353][87424] Updated weights for policy 0, policy_version 388329 (0.0011) -[2023-11-28 10:23:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 198737920. Throughput: 0: 2712.7, 1: 2627.5. Samples: 198758932. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:23:53,445][86177] Avg episode reward: [(0, '-536.870'), (1, '-571.100')] -[2023-11-28 10:23:53,736][87424] Updated weights for policy 0, policy_version 388339 (0.0010) -[2023-11-28 10:23:54,133][87424] Updated weights for policy 0, policy_version 388349 (0.0010) -[2023-11-28 10:23:54,447][87426] Updated weights for policy 1, policy_version 388010 (0.0012) -[2023-11-28 10:23:54,831][87426] Updated weights for policy 1, policy_version 388020 (0.0012) -[2023-11-28 10:23:55,207][87426] Updated weights for policy 1, policy_version 388030 (0.0012) -[2023-11-28 10:23:56,158][87424] Updated weights for policy 0, policy_version 388359 (0.0010) -[2023-11-28 10:23:56,527][87424] Updated weights for policy 0, policy_version 388369 (0.0016) -[2023-11-28 10:23:56,906][87424] Updated weights for policy 0, policy_version 388379 (0.0011) -[2023-11-28 10:23:57,122][87426] Updated weights for policy 1, policy_version 388040 (0.0008) -[2023-11-28 10:23:57,498][87426] Updated weights for policy 1, policy_version 388050 (0.0007) -[2023-11-28 10:23:57,880][87426] Updated weights for policy 1, policy_version 388060 (0.0009) -[2023-11-28 10:23:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 198770688. Throughput: 0: 2717.3, 1: 2624.3. Samples: 198782756. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:23:58,445][86177] Avg episode reward: [(0, '-540.450'), (1, '-596.110')] -[2023-11-28 10:23:59,347][87424] Updated weights for policy 0, policy_version 388389 (0.0010) -[2023-11-28 10:23:59,720][87424] Updated weights for policy 0, policy_version 388399 (0.0012) -[2023-11-28 10:23:59,894][87426] Updated weights for policy 1, policy_version 388070 (0.0011) -[2023-11-28 10:24:00,097][87424] Updated weights for policy 0, policy_version 388409 (0.0011) -[2023-11-28 10:24:00,273][87426] Updated weights for policy 1, policy_version 388080 (0.0011) -[2023-11-28 10:24:00,652][87426] Updated weights for policy 1, policy_version 388090 (0.0012) -[2023-11-28 10:24:02,751][87424] Updated weights for policy 0, policy_version 388419 (0.0011) -[2023-11-28 10:24:02,836][87426] Updated weights for policy 1, policy_version 388100 (0.0012) -[2023-11-28 10:24:03,137][87424] Updated weights for policy 0, policy_version 388429 (0.0012) -[2023-11-28 10:24:03,217][87426] Updated weights for policy 1, policy_version 388110 (0.0014) -[2023-11-28 10:24:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 198787072. Throughput: 0: 2685.8, 1: 2642.8. Samples: 198806488. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:24:03,445][86177] Avg episode reward: [(0, '-544.330'), (1, '-623.420')] -[2023-11-28 10:24:03,507][87424] Updated weights for policy 0, policy_version 388439 (0.0012) -[2023-11-28 10:24:03,598][87426] Updated weights for policy 1, policy_version 388120 (0.0011) -[2023-11-28 10:24:05,531][87424] Updated weights for policy 0, policy_version 388449 (0.0011) -[2023-11-28 10:24:05,910][87424] Updated weights for policy 0, policy_version 388459 (0.0009) -[2023-11-28 10:24:06,015][87426] Updated weights for policy 1, policy_version 388130 (0.0011) -[2023-11-28 10:24:06,296][87424] Updated weights for policy 0, policy_version 388469 (0.0009) -[2023-11-28 10:24:06,398][87426] Updated weights for policy 1, policy_version 388140 (0.0007) -[2023-11-28 10:24:06,679][87424] Updated weights for policy 0, policy_version 388479 (0.0008) -[2023-11-28 10:24:06,776][87426] Updated weights for policy 1, policy_version 388150 (0.0009) -[2023-11-28 10:24:07,151][87426] Updated weights for policy 1, policy_version 388160 (0.0011) -[2023-11-28 10:24:08,388][87424] Updated weights for policy 0, policy_version 388489 (0.0008) -[2023-11-28 10:24:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 198819840. Throughput: 0: 2663.6, 1: 2670.5. Samples: 198838092. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:24:08,445][86177] Avg episode reward: [(0, '-545.600'), (1, '-576.630')] -[2023-11-28 10:24:08,774][87424] Updated weights for policy 0, policy_version 388499 (0.0008) -[2023-11-28 10:24:09,147][87424] Updated weights for policy 0, policy_version 388509 (0.0010) -[2023-11-28 10:24:09,660][87426] Updated weights for policy 1, policy_version 388170 (0.0011) -[2023-11-28 10:24:10,040][87426] Updated weights for policy 1, policy_version 388180 (0.0011) -[2023-11-28 10:24:10,426][87426] Updated weights for policy 1, policy_version 388190 (0.0012) -[2023-11-28 10:24:11,583][87424] Updated weights for policy 0, policy_version 388519 (0.0011) -[2023-11-28 10:24:11,966][87424] Updated weights for policy 0, policy_version 388529 (0.0011) -[2023-11-28 10:24:12,349][87424] Updated weights for policy 0, policy_version 388539 (0.0012) -[2023-11-28 10:24:12,785][87426] Updated weights for policy 1, policy_version 388200 (0.0011) -[2023-11-28 10:24:13,162][87426] Updated weights for policy 1, policy_version 388210 (0.0012) -[2023-11-28 10:24:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 198844416. Throughput: 0: 2661.4, 1: 2656.1. Samples: 198861736. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:24:13,445][86177] Avg episode reward: [(0, '-551.780'), (1, '-530.530')] -[2023-11-28 10:24:13,541][87426] Updated weights for policy 1, policy_version 388220 (0.0012) -[2023-11-28 10:24:14,574][87424] Updated weights for policy 0, policy_version 388549 (0.0011) -[2023-11-28 10:24:14,950][87424] Updated weights for policy 0, policy_version 388559 (0.0007) -[2023-11-28 10:24:15,340][87424] Updated weights for policy 0, policy_version 388569 (0.0008) -[2023-11-28 10:24:15,579][87426] Updated weights for policy 1, policy_version 388230 (0.0011) -[2023-11-28 10:24:15,969][87426] Updated weights for policy 1, policy_version 388240 (0.0011) -[2023-11-28 10:24:16,339][87426] Updated weights for policy 1, policy_version 388250 (0.0009) -[2023-11-28 10:24:17,174][87424] Updated weights for policy 0, policy_version 388579 (0.0011) -[2023-11-28 10:24:17,546][87424] Updated weights for policy 0, policy_version 388589 (0.0009) -[2023-11-28 10:24:17,930][87424] Updated weights for policy 0, policy_version 388599 (0.0011) -[2023-11-28 10:24:18,355][87426] Updated weights for policy 1, policy_version 388260 (0.0009) -[2023-11-28 10:24:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 198877184. Throughput: 0: 2653.0, 1: 2669.3. Samples: 198886896. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:24:18,445][86177] Avg episode reward: [(0, '-551.270'), (1, '-530.580')] -[2023-11-28 10:24:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000388608_99483648.pth... -[2023-11-28 10:24:18,501][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000386080_98836480.pth -[2023-11-28 10:24:18,719][87426] Updated weights for policy 1, policy_version 388270 (0.0012) -[2023-11-28 10:24:19,096][87426] Updated weights for policy 1, policy_version 388280 (0.0012) -[2023-11-28 10:24:19,399][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000388288_99401728.pth... -[2023-11-28 10:24:19,446][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000385760_98754560.pth -[2023-11-28 10:24:19,954][87424] Updated weights for policy 0, policy_version 388609 (0.0012) -[2023-11-28 10:24:20,335][87424] Updated weights for policy 0, policy_version 388619 (0.0010) -[2023-11-28 10:24:20,724][87424] Updated weights for policy 0, policy_version 388629 (0.0011) -[2023-11-28 10:24:21,100][87424] Updated weights for policy 0, policy_version 388639 (0.0011) -[2023-11-28 10:24:21,604][87426] Updated weights for policy 1, policy_version 388290 (0.0011) -[2023-11-28 10:24:21,992][87426] Updated weights for policy 1, policy_version 388300 (0.0011) -[2023-11-28 10:24:22,369][87426] Updated weights for policy 1, policy_version 388310 (0.0011) -[2023-11-28 10:24:22,749][87426] Updated weights for policy 1, policy_version 388320 (0.0010) -[2023-11-28 10:24:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 198901760. Throughput: 0: 2671.6, 1: 2655.7. Samples: 198920068. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:24:23,445][86177] Avg episode reward: [(0, '-544.030'), (1, '-505.340')] -[2023-11-28 10:24:23,512][87424] Updated weights for policy 0, policy_version 388649 (0.0008) -[2023-11-28 10:24:23,895][87424] Updated weights for policy 0, policy_version 388659 (0.0009) -[2023-11-28 10:24:24,269][87424] Updated weights for policy 0, policy_version 388669 (0.0011) -[2023-11-28 10:24:24,949][87426] Updated weights for policy 1, policy_version 388330 (0.0012) -[2023-11-28 10:24:25,328][87426] Updated weights for policy 1, policy_version 388340 (0.0010) -[2023-11-28 10:24:25,704][87426] Updated weights for policy 1, policy_version 388350 (0.0010) -[2023-11-28 10:24:26,366][87424] Updated weights for policy 0, policy_version 388679 (0.0011) -[2023-11-28 10:24:26,742][87424] Updated weights for policy 0, policy_version 388689 (0.0012) -[2023-11-28 10:24:27,126][87424] Updated weights for policy 0, policy_version 388699 (0.0012) -[2023-11-28 10:24:28,147][87426] Updated weights for policy 1, policy_version 388360 (0.0012) -[2023-11-28 10:24:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 198926336. Throughput: 0: 2670.3, 1: 2658.5. Samples: 198944196. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:24:28,445][86177] Avg episode reward: [(0, '-539.430'), (1, '-507.440')] -[2023-11-28 10:24:28,527][87426] Updated weights for policy 1, policy_version 388370 (0.0012) -[2023-11-28 10:24:28,916][87426] Updated weights for policy 1, policy_version 388380 (0.0012) -[2023-11-28 10:24:29,269][87424] Updated weights for policy 0, policy_version 388709 (0.0010) -[2023-11-28 10:24:29,650][87424] Updated weights for policy 0, policy_version 388719 (0.0011) -[2023-11-28 10:24:30,036][87424] Updated weights for policy 0, policy_version 388729 (0.0011) -[2023-11-28 10:24:30,888][87426] Updated weights for policy 1, policy_version 388390 (0.0014) -[2023-11-28 10:24:31,272][87426] Updated weights for policy 1, policy_version 388400 (0.0007) -[2023-11-28 10:24:31,650][87426] Updated weights for policy 1, policy_version 388410 (0.0008) -[2023-11-28 10:24:32,198][87424] Updated weights for policy 0, policy_version 388739 (0.0011) -[2023-11-28 10:24:32,574][87424] Updated weights for policy 0, policy_version 388749 (0.0011) -[2023-11-28 10:24:32,955][87424] Updated weights for policy 0, policy_version 388759 (0.0011) -[2023-11-28 10:24:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 198959104. Throughput: 0: 2675.7, 1: 2663.0. Samples: 198969064. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:24:33,445][86177] Avg episode reward: [(0, '-539.810'), (1, '-505.980')] -[2023-11-28 10:24:33,858][87426] Updated weights for policy 1, policy_version 388420 (0.0011) -[2023-11-28 10:24:34,254][87426] Updated weights for policy 1, policy_version 388430 (0.0012) -[2023-11-28 10:24:34,617][87426] Updated weights for policy 1, policy_version 388440 (0.0012) -[2023-11-28 10:24:34,775][87424] Updated weights for policy 0, policy_version 388769 (0.0010) -[2023-11-28 10:24:35,156][87424] Updated weights for policy 0, policy_version 388779 (0.0008) -[2023-11-28 10:24:35,536][87424] Updated weights for policy 0, policy_version 388789 (0.0008) -[2023-11-28 10:24:35,922][87424] Updated weights for policy 0, policy_version 388799 (0.0012) -[2023-11-28 10:24:36,870][87426] Updated weights for policy 1, policy_version 388450 (0.0011) -[2023-11-28 10:24:37,237][87426] Updated weights for policy 1, policy_version 388460 (0.0012) -[2023-11-28 10:24:37,614][87426] Updated weights for policy 1, policy_version 388470 (0.0011) -[2023-11-28 10:24:37,877][87424] Updated weights for policy 0, policy_version 388809 (0.0011) -[2023-11-28 10:24:37,987][87426] Updated weights for policy 1, policy_version 388480 (0.0010) -[2023-11-28 10:24:38,269][87424] Updated weights for policy 0, policy_version 388819 (0.0012) -[2023-11-28 10:24:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 198983680. Throughput: 0: 2723.3, 1: 2682.0. Samples: 199002168. Policy #0 lag: (min: 31.0, avg: 55.9, max: 91.0) -[2023-11-28 10:24:38,445][86177] Avg episode reward: [(0, '-541.360'), (1, '-544.010')] -[2023-11-28 10:24:38,647][87424] Updated weights for policy 0, policy_version 388829 (0.0012) -[2023-11-28 10:24:40,459][87426] Updated weights for policy 1, policy_version 388490 (0.0011) -[2023-11-28 10:24:40,551][87424] Updated weights for policy 0, policy_version 388839 (0.0011) -[2023-11-28 10:24:40,835][87426] Updated weights for policy 1, policy_version 388500 (0.0011) -[2023-11-28 10:24:40,928][87424] Updated weights for policy 0, policy_version 388849 (0.0011) -[2023-11-28 10:24:41,214][87426] Updated weights for policy 1, policy_version 388510 (0.0012) -[2023-11-28 10:24:41,311][87424] Updated weights for policy 0, policy_version 388859 (0.0011) -[2023-11-28 10:24:43,259][87426] Updated weights for policy 1, policy_version 388520 (0.0012) -[2023-11-28 10:24:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 199008256. Throughput: 0: 2724.6, 1: 2678.3. Samples: 199025888. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:24:43,445][86177] Avg episode reward: [(0, '-544.210'), (1, '-548.980')] -[2023-11-28 10:24:43,608][87424] Updated weights for policy 0, policy_version 388869 (0.0012) -[2023-11-28 10:24:43,642][87426] Updated weights for policy 1, policy_version 388530 (0.0012) -[2023-11-28 10:24:43,990][87424] Updated weights for policy 0, policy_version 388879 (0.0008) -[2023-11-28 10:24:44,013][87426] Updated weights for policy 1, policy_version 388540 (0.0008) -[2023-11-28 10:24:44,367][87424] Updated weights for policy 0, policy_version 388889 (0.0008) -[2023-11-28 10:24:46,259][87426] Updated weights for policy 1, policy_version 388550 (0.0007) -[2023-11-28 10:24:46,639][87426] Updated weights for policy 1, policy_version 388560 (0.0007) -[2023-11-28 10:24:46,753][87424] Updated weights for policy 0, policy_version 388899 (0.0009) -[2023-11-28 10:24:47,016][87426] Updated weights for policy 1, policy_version 388570 (0.0007) -[2023-11-28 10:24:47,134][87424] Updated weights for policy 0, policy_version 388909 (0.0011) -[2023-11-28 10:24:47,518][87424] Updated weights for policy 0, policy_version 388919 (0.0011) -[2023-11-28 10:24:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 199041024. Throughput: 0: 2743.0, 1: 2663.0. Samples: 199049760. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:24:48,445][86177] Avg episode reward: [(0, '-546.510'), (1, '-541.640')] -[2023-11-28 10:24:48,742][87426] Updated weights for policy 1, policy_version 388580 (0.0008) -[2023-11-28 10:24:49,121][87426] Updated weights for policy 1, policy_version 388590 (0.0009) -[2023-11-28 10:24:49,491][87426] Updated weights for policy 1, policy_version 388600 (0.0008) -[2023-11-28 10:24:50,073][87424] Updated weights for policy 0, policy_version 388929 (0.0008) -[2023-11-28 10:24:50,454][87424] Updated weights for policy 0, policy_version 388939 (0.0012) -[2023-11-28 10:24:50,837][87424] Updated weights for policy 0, policy_version 388949 (0.0012) -[2023-11-28 10:24:51,211][87424] Updated weights for policy 0, policy_version 388959 (0.0011) -[2023-11-28 10:24:51,779][87426] Updated weights for policy 1, policy_version 388610 (0.0009) -[2023-11-28 10:24:52,168][87426] Updated weights for policy 1, policy_version 388620 (0.0011) -[2023-11-28 10:24:52,550][87426] Updated weights for policy 1, policy_version 388630 (0.0008) -[2023-11-28 10:24:52,929][87426] Updated weights for policy 1, policy_version 388640 (0.0008) -[2023-11-28 10:24:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 199065600. Throughput: 0: 2739.6, 1: 2680.0. Samples: 199081976. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:24:53,445][86177] Avg episode reward: [(0, '-537.220'), (1, '-542.740')] -[2023-11-28 10:24:53,753][87424] Updated weights for policy 0, policy_version 388969 (0.0015) -[2023-11-28 10:24:54,133][87424] Updated weights for policy 0, policy_version 388979 (0.0012) -[2023-11-28 10:24:54,520][87424] Updated weights for policy 0, policy_version 388989 (0.0011) -[2023-11-28 10:24:55,256][87426] Updated weights for policy 1, policy_version 388650 (0.0012) -[2023-11-28 10:24:55,630][87426] Updated weights for policy 1, policy_version 388660 (0.0012) -[2023-11-28 10:24:56,011][87426] Updated weights for policy 1, policy_version 388670 (0.0012) -[2023-11-28 10:24:56,348][87424] Updated weights for policy 0, policy_version 388999 (0.0012) -[2023-11-28 10:24:56,719][87424] Updated weights for policy 0, policy_version 389009 (0.0012) -[2023-11-28 10:24:57,110][87424] Updated weights for policy 0, policy_version 389019 (0.0008) -[2023-11-28 10:24:58,186][87426] Updated weights for policy 1, policy_version 388680 (0.0011) -[2023-11-28 10:24:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 199090176. Throughput: 0: 2737.7, 1: 2702.8. Samples: 199106556. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:24:58,445][86177] Avg episode reward: [(0, '-553.420'), (1, '-503.060')] -[2023-11-28 10:24:58,568][87426] Updated weights for policy 1, policy_version 388690 (0.0010) -[2023-11-28 10:24:58,952][87426] Updated weights for policy 1, policy_version 388700 (0.0009) -[2023-11-28 10:24:59,244][87424] Updated weights for policy 0, policy_version 389029 (0.0010) -[2023-11-28 10:24:59,619][87424] Updated weights for policy 0, policy_version 389039 (0.0012) -[2023-11-28 10:24:59,999][87424] Updated weights for policy 0, policy_version 389049 (0.0012) -[2023-11-28 10:25:01,074][87426] Updated weights for policy 1, policy_version 388710 (0.0012) -[2023-11-28 10:25:01,451][87426] Updated weights for policy 1, policy_version 388720 (0.0012) -[2023-11-28 10:25:01,830][87426] Updated weights for policy 1, policy_version 388730 (0.0012) -[2023-11-28 10:25:02,336][87424] Updated weights for policy 0, policy_version 389059 (0.0012) -[2023-11-28 10:25:02,714][87424] Updated weights for policy 0, policy_version 389069 (0.0011) -[2023-11-28 10:25:03,099][87424] Updated weights for policy 0, policy_version 389079 (0.0008) -[2023-11-28 10:25:03,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5597.8, 300 sec: 5415.0). Total num frames: 199122944. Throughput: 0: 2728.6, 1: 2692.9. Samples: 199130864. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:03,445][86177] Avg episode reward: [(0, '-551.980'), (1, '-500.950')] -[2023-11-28 10:25:04,094][87426] Updated weights for policy 1, policy_version 388740 (0.0012) -[2023-11-28 10:25:04,471][87426] Updated weights for policy 1, policy_version 388750 (0.0010) -[2023-11-28 10:25:04,852][87426] Updated weights for policy 1, policy_version 388760 (0.0011) -[2023-11-28 10:25:05,200][87424] Updated weights for policy 0, policy_version 389089 (0.0007) -[2023-11-28 10:25:05,584][87424] Updated weights for policy 0, policy_version 389099 (0.0012) -[2023-11-28 10:25:05,970][87424] Updated weights for policy 0, policy_version 389109 (0.0012) -[2023-11-28 10:25:06,335][87424] Updated weights for policy 0, policy_version 389119 (0.0012) -[2023-11-28 10:25:07,079][87426] Updated weights for policy 1, policy_version 388770 (0.0011) -[2023-11-28 10:25:07,453][87426] Updated weights for policy 1, policy_version 388780 (0.0012) -[2023-11-28 10:25:07,837][87426] Updated weights for policy 1, policy_version 388790 (0.0012) -[2023-11-28 10:25:08,217][87426] Updated weights for policy 1, policy_version 388800 (0.0009) -[2023-11-28 10:25:08,301][87424] Updated weights for policy 0, policy_version 389129 (0.0011) -[2023-11-28 10:25:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 199147520. Throughput: 0: 2720.9, 1: 2697.6. Samples: 199163900. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:08,445][86177] Avg episode reward: [(0, '-549.010'), (1, '-503.190')] -[2023-11-28 10:25:08,675][87424] Updated weights for policy 0, policy_version 389139 (0.0012) -[2023-11-28 10:25:09,046][87424] Updated weights for policy 0, policy_version 389149 (0.0012) -[2023-11-28 10:25:10,673][87426] Updated weights for policy 1, policy_version 388810 (0.0009) -[2023-11-28 10:25:11,049][87426] Updated weights for policy 1, policy_version 388820 (0.0007) -[2023-11-28 10:25:11,431][87426] Updated weights for policy 1, policy_version 388830 (0.0009) -[2023-11-28 10:25:11,482][87424] Updated weights for policy 0, policy_version 389159 (0.0012) -[2023-11-28 10:25:11,865][87424] Updated weights for policy 0, policy_version 389169 (0.0010) -[2023-11-28 10:25:12,238][87424] Updated weights for policy 0, policy_version 389179 (0.0011) -[2023-11-28 10:25:13,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 199172096. Throughput: 0: 2716.4, 1: 2688.0. Samples: 199187392. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:13,445][86177] Avg episode reward: [(0, '-546.470'), (1, '-543.810')] -[2023-11-28 10:25:13,605][87426] Updated weights for policy 1, policy_version 388840 (0.0011) -[2023-11-28 10:25:13,979][87426] Updated weights for policy 1, policy_version 388850 (0.0012) -[2023-11-28 10:25:14,350][87426] Updated weights for policy 1, policy_version 388860 (0.0012) -[2023-11-28 10:25:14,894][87424] Updated weights for policy 0, policy_version 389189 (0.0012) -[2023-11-28 10:25:15,276][87424] Updated weights for policy 0, policy_version 389199 (0.0008) -[2023-11-28 10:25:15,660][87424] Updated weights for policy 0, policy_version 389209 (0.0010) -[2023-11-28 10:25:16,391][87426] Updated weights for policy 1, policy_version 388870 (0.0012) -[2023-11-28 10:25:16,771][87426] Updated weights for policy 1, policy_version 388880 (0.0011) -[2023-11-28 10:25:17,156][87426] Updated weights for policy 1, policy_version 388890 (0.0008) -[2023-11-28 10:25:17,706][87424] Updated weights for policy 0, policy_version 389219 (0.0008) -[2023-11-28 10:25:18,085][87424] Updated weights for policy 0, policy_version 389229 (0.0007) -[2023-11-28 10:25:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 199196672. Throughput: 0: 2684.8, 1: 2680.8. Samples: 199210516. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:18,445][86177] Avg episode reward: [(0, '-533.400'), (1, '-541.690')] -[2023-11-28 10:25:18,464][87424] Updated weights for policy 0, policy_version 389239 (0.0007) -[2023-11-28 10:25:19,387][87426] Updated weights for policy 1, policy_version 388900 (0.0009) -[2023-11-28 10:25:19,775][87426] Updated weights for policy 1, policy_version 388910 (0.0008) -[2023-11-28 10:25:20,154][87426] Updated weights for policy 1, policy_version 388920 (0.0011) -[2023-11-28 10:25:20,943][87424] Updated weights for policy 0, policy_version 389249 (0.0007) -[2023-11-28 10:25:21,322][87424] Updated weights for policy 0, policy_version 389259 (0.0040) -[2023-11-28 10:25:21,703][87424] Updated weights for policy 0, policy_version 389269 (0.0011) -[2023-11-28 10:25:22,084][87424] Updated weights for policy 0, policy_version 389279 (0.0010) -[2023-11-28 10:25:22,604][87426] Updated weights for policy 1, policy_version 388930 (0.0011) -[2023-11-28 10:25:22,982][87426] Updated weights for policy 1, policy_version 388940 (0.0009) -[2023-11-28 10:25:23,359][87426] Updated weights for policy 1, policy_version 388950 (0.0011) -[2023-11-28 10:25:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 199221248. Throughput: 0: 2646.2, 1: 2667.4. Samples: 199241280. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:23,445][86177] Avg episode reward: [(0, '-532.130'), (1, '-536.630')] -[2023-11-28 10:25:23,730][87426] Updated weights for policy 1, policy_version 388960 (0.0009) -[2023-11-28 10:25:24,586][87424] Updated weights for policy 0, policy_version 389289 (0.0011) -[2023-11-28 10:25:24,966][87424] Updated weights for policy 0, policy_version 389299 (0.0009) -[2023-11-28 10:25:25,339][87424] Updated weights for policy 0, policy_version 389309 (0.0010) -[2023-11-28 10:25:26,344][87426] Updated weights for policy 1, policy_version 388970 (0.0007) -[2023-11-28 10:25:26,724][87426] Updated weights for policy 1, policy_version 388980 (0.0007) -[2023-11-28 10:25:27,095][87426] Updated weights for policy 1, policy_version 388990 (0.0007) -[2023-11-28 10:25:27,366][87424] Updated weights for policy 0, policy_version 389319 (0.0011) -[2023-11-28 10:25:27,739][87424] Updated weights for policy 0, policy_version 389329 (0.0010) -[2023-11-28 10:25:28,128][87424] Updated weights for policy 0, policy_version 389339 (0.0008) -[2023-11-28 10:25:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 199254016. Throughput: 0: 2634.0, 1: 2653.2. Samples: 199263812. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:28,445][86177] Avg episode reward: [(0, '-528.580'), (1, '-539.120')] -[2023-11-28 10:25:29,529][87426] Updated weights for policy 1, policy_version 389000 (0.0011) -[2023-11-28 10:25:29,867][87424] Updated weights for policy 0, policy_version 389349 (0.0011) -[2023-11-28 10:25:29,905][87426] Updated weights for policy 1, policy_version 389010 (0.0011) -[2023-11-28 10:25:30,253][87424] Updated weights for policy 0, policy_version 389359 (0.0011) -[2023-11-28 10:25:30,283][87426] Updated weights for policy 1, policy_version 389020 (0.0009) -[2023-11-28 10:25:30,632][87424] Updated weights for policy 0, policy_version 389369 (0.0010) -[2023-11-28 10:25:32,748][87426] Updated weights for policy 1, policy_version 389030 (0.0009) -[2023-11-28 10:25:33,124][87426] Updated weights for policy 1, policy_version 389040 (0.0009) -[2023-11-28 10:25:33,239][87424] Updated weights for policy 0, policy_version 389379 (0.0011) -[2023-11-28 10:25:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 199270400. Throughput: 0: 2655.6, 1: 2658.1. Samples: 199288876. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:33,445][86177] Avg episode reward: [(0, '-531.560'), (1, '-500.720')] -[2023-11-28 10:25:33,500][87426] Updated weights for policy 1, policy_version 389050 (0.0008) -[2023-11-28 10:25:33,614][87424] Updated weights for policy 0, policy_version 389389 (0.0011) -[2023-11-28 10:25:34,001][87424] Updated weights for policy 0, policy_version 389399 (0.0012) -[2023-11-28 10:25:35,524][87426] Updated weights for policy 1, policy_version 389060 (0.0008) -[2023-11-28 10:25:35,910][87426] Updated weights for policy 1, policy_version 389070 (0.0008) -[2023-11-28 10:25:36,231][87424] Updated weights for policy 0, policy_version 389409 (0.0012) -[2023-11-28 10:25:36,281][87426] Updated weights for policy 1, policy_version 389080 (0.0012) -[2023-11-28 10:25:36,622][87424] Updated weights for policy 0, policy_version 389419 (0.0012) -[2023-11-28 10:25:36,990][87424] Updated weights for policy 0, policy_version 389429 (0.0011) -[2023-11-28 10:25:37,372][87424] Updated weights for policy 0, policy_version 389439 (0.0009) -[2023-11-28 10:25:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 199303168. Throughput: 0: 2662.5, 1: 2641.6. Samples: 199320660. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:38,445][86177] Avg episode reward: [(0, '-558.380'), (1, '-504.990')] -[2023-11-28 10:25:38,530][87426] Updated weights for policy 1, policy_version 389090 (0.0011) -[2023-11-28 10:25:38,904][87426] Updated weights for policy 1, policy_version 389100 (0.0012) -[2023-11-28 10:25:39,118][87424] Updated weights for policy 0, policy_version 389449 (0.0010) -[2023-11-28 10:25:39,281][87426] Updated weights for policy 1, policy_version 389110 (0.0012) -[2023-11-28 10:25:39,509][87424] Updated weights for policy 0, policy_version 389459 (0.0009) -[2023-11-28 10:25:39,662][87426] Updated weights for policy 1, policy_version 389120 (0.0009) -[2023-11-28 10:25:39,895][87424] Updated weights for policy 0, policy_version 389469 (0.0012) -[2023-11-28 10:25:41,879][87424] Updated weights for policy 0, policy_version 389479 (0.0010) -[2023-11-28 10:25:41,998][87426] Updated weights for policy 1, policy_version 389130 (0.0011) -[2023-11-28 10:25:42,263][87424] Updated weights for policy 0, policy_version 389489 (0.0011) -[2023-11-28 10:25:42,377][87426] Updated weights for policy 1, policy_version 389140 (0.0012) -[2023-11-28 10:25:42,636][87424] Updated weights for policy 0, policy_version 389499 (0.0011) -[2023-11-28 10:25:42,745][87426] Updated weights for policy 1, policy_version 389150 (0.0011) -[2023-11-28 10:25:43,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 199335936. Throughput: 0: 2674.6, 1: 2631.7. Samples: 199345340. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:43,445][86177] Avg episode reward: [(0, '-567.850'), (1, '-504.930')] -[2023-11-28 10:25:44,582][87426] Updated weights for policy 1, policy_version 389160 (0.0010) -[2023-11-28 10:25:44,866][87424] Updated weights for policy 0, policy_version 389509 (0.0012) -[2023-11-28 10:25:44,956][87426] Updated weights for policy 1, policy_version 389170 (0.0010) -[2023-11-28 10:25:45,251][87424] Updated weights for policy 0, policy_version 389519 (0.0012) -[2023-11-28 10:25:45,342][87426] Updated weights for policy 1, policy_version 389180 (0.0011) -[2023-11-28 10:25:45,637][87424] Updated weights for policy 0, policy_version 389529 (0.0012) -[2023-11-28 10:25:47,745][87426] Updated weights for policy 1, policy_version 389190 (0.0012) -[2023-11-28 10:25:48,129][87426] Updated weights for policy 1, policy_version 389200 (0.0012) -[2023-11-28 10:25:48,143][87424] Updated weights for policy 0, policy_version 389539 (0.0012) -[2023-11-28 10:25:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 199352320. Throughput: 0: 2675.5, 1: 2644.6. Samples: 199370268. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:48,445][86177] Avg episode reward: [(0, '-565.110'), (1, '-506.440')] -[2023-11-28 10:25:48,515][87426] Updated weights for policy 1, policy_version 389210 (0.0011) -[2023-11-28 10:25:48,533][87424] Updated weights for policy 0, policy_version 389549 (0.0007) -[2023-11-28 10:25:48,921][87424] Updated weights for policy 0, policy_version 389559 (0.0008) -[2023-11-28 10:25:50,550][87426] Updated weights for policy 1, policy_version 389220 (0.0010) -[2023-11-28 10:25:50,924][87426] Updated weights for policy 1, policy_version 389230 (0.0009) -[2023-11-28 10:25:51,302][87426] Updated weights for policy 1, policy_version 389240 (0.0008) -[2023-11-28 10:25:51,486][87424] Updated weights for policy 0, policy_version 389569 (0.0008) -[2023-11-28 10:25:51,868][87424] Updated weights for policy 0, policy_version 389579 (0.0012) -[2023-11-28 10:25:52,271][87424] Updated weights for policy 0, policy_version 389589 (0.0012) -[2023-11-28 10:25:52,656][87424] Updated weights for policy 0, policy_version 389599 (0.0011) -[2023-11-28 10:25:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 199385088. Throughput: 0: 2634.5, 1: 2642.8. Samples: 199401376. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:53,445][86177] Avg episode reward: [(0, '-563.960'), (1, '-508.200')] -[2023-11-28 10:25:53,860][87426] Updated weights for policy 1, policy_version 389250 (0.0010) -[2023-11-28 10:25:54,239][87426] Updated weights for policy 1, policy_version 389260 (0.0007) -[2023-11-28 10:25:54,623][87426] Updated weights for policy 1, policy_version 389270 (0.0007) -[2023-11-28 10:25:55,004][87426] Updated weights for policy 1, policy_version 389280 (0.0011) -[2023-11-28 10:25:55,087][87424] Updated weights for policy 0, policy_version 389609 (0.0009) -[2023-11-28 10:25:55,472][87424] Updated weights for policy 0, policy_version 389619 (0.0008) -[2023-11-28 10:25:55,847][87424] Updated weights for policy 0, policy_version 389629 (0.0012) -[2023-11-28 10:25:57,404][87426] Updated weights for policy 1, policy_version 389290 (0.0012) -[2023-11-28 10:25:57,636][87424] Updated weights for policy 0, policy_version 389639 (0.0011) -[2023-11-28 10:25:57,786][87426] Updated weights for policy 1, policy_version 389300 (0.0011) -[2023-11-28 10:25:58,008][87424] Updated weights for policy 0, policy_version 389649 (0.0012) -[2023-11-28 10:25:58,180][87426] Updated weights for policy 1, policy_version 389310 (0.0011) -[2023-11-28 10:25:58,399][87424] Updated weights for policy 0, policy_version 389659 (0.0011) -[2023-11-28 10:25:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 199409664. Throughput: 0: 2637.4, 1: 2640.2. Samples: 199424884. Policy #0 lag: (min: 3.0, avg: 33.1, max: 67.0) -[2023-11-28 10:25:58,445][86177] Avg episode reward: [(0, '-535.960'), (1, '-509.220')] -[2023-11-28 10:25:59,982][87426] Updated weights for policy 1, policy_version 389320 (0.0010) -[2023-11-28 10:26:00,361][87426] Updated weights for policy 1, policy_version 389330 (0.0008) -[2023-11-28 10:26:00,713][87424] Updated weights for policy 0, policy_version 389669 (0.0008) -[2023-11-28 10:26:00,746][87426] Updated weights for policy 1, policy_version 389340 (0.0011) -[2023-11-28 10:26:01,099][87424] Updated weights for policy 0, policy_version 389679 (0.0008) -[2023-11-28 10:26:01,476][87424] Updated weights for policy 0, policy_version 389689 (0.0008) -[2023-11-28 10:26:03,003][87426] Updated weights for policy 1, policy_version 389350 (0.0011) -[2023-11-28 10:26:03,377][87426] Updated weights for policy 1, policy_version 389360 (0.0012) -[2023-11-28 10:26:03,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 199434240. Throughput: 0: 2671.0, 1: 2652.3. Samples: 199450068. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:03,446][86177] Avg episode reward: [(0, '-533.150'), (1, '-514.000')] -[2023-11-28 10:26:03,756][87426] Updated weights for policy 1, policy_version 389370 (0.0012) -[2023-11-28 10:26:04,054][87424] Updated weights for policy 0, policy_version 389699 (0.0011) -[2023-11-28 10:26:04,426][87424] Updated weights for policy 0, policy_version 389709 (0.0012) -[2023-11-28 10:26:04,802][87424] Updated weights for policy 0, policy_version 389719 (0.0012) -[2023-11-28 10:26:05,842][87426] Updated weights for policy 1, policy_version 389380 (0.0010) -[2023-11-28 10:26:06,224][87426] Updated weights for policy 1, policy_version 389390 (0.0007) -[2023-11-28 10:26:06,604][87426] Updated weights for policy 1, policy_version 389400 (0.0007) -[2023-11-28 10:26:07,021][87424] Updated weights for policy 0, policy_version 389729 (0.0012) -[2023-11-28 10:26:07,402][87424] Updated weights for policy 0, policy_version 389739 (0.0012) -[2023-11-28 10:26:07,789][87424] Updated weights for policy 0, policy_version 389749 (0.0012) -[2023-11-28 10:26:08,174][87424] Updated weights for policy 0, policy_version 389759 (0.0012) -[2023-11-28 10:26:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 199467008. Throughput: 0: 2671.0, 1: 2688.3. Samples: 199482448. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:08,445][86177] Avg episode reward: [(0, '-534.530'), (1, '-523.140')] -[2023-11-28 10:26:08,462][87426] Updated weights for policy 1, policy_version 389410 (0.0009) -[2023-11-28 10:26:08,836][87426] Updated weights for policy 1, policy_version 389420 (0.0012) -[2023-11-28 10:26:09,217][87426] Updated weights for policy 1, policy_version 389430 (0.0012) -[2023-11-28 10:26:09,590][87426] Updated weights for policy 1, policy_version 389440 (0.0012) -[2023-11-28 10:26:10,270][87424] Updated weights for policy 0, policy_version 389769 (0.0011) -[2023-11-28 10:26:10,651][87424] Updated weights for policy 0, policy_version 389779 (0.0012) -[2023-11-28 10:26:11,047][87424] Updated weights for policy 0, policy_version 389789 (0.0012) -[2023-11-28 10:26:11,937][87426] Updated weights for policy 1, policy_version 389450 (0.0010) -[2023-11-28 10:26:12,327][87426] Updated weights for policy 1, policy_version 389460 (0.0008) -[2023-11-28 10:26:12,700][87426] Updated weights for policy 1, policy_version 389470 (0.0008) -[2023-11-28 10:26:13,279][87424] Updated weights for policy 0, policy_version 389799 (0.0011) -[2023-11-28 10:26:13,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 199491584. Throughput: 0: 2676.0, 1: 2710.7. Samples: 199506212. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:13,445][86177] Avg episode reward: [(0, '-533.090'), (1, '-523.240')] -[2023-11-28 10:26:13,655][87424] Updated weights for policy 0, policy_version 389809 (0.0011) -[2023-11-28 10:26:14,037][87424] Updated weights for policy 0, policy_version 389819 (0.0008) -[2023-11-28 10:26:14,617][87426] Updated weights for policy 1, policy_version 389480 (0.0012) -[2023-11-28 10:26:14,989][87426] Updated weights for policy 1, policy_version 389490 (0.0008) -[2023-11-28 10:26:15,368][87426] Updated weights for policy 1, policy_version 389500 (0.0010) -[2023-11-28 10:26:15,946][87424] Updated weights for policy 0, policy_version 389829 (0.0010) -[2023-11-28 10:26:16,329][87424] Updated weights for policy 0, policy_version 389839 (0.0012) -[2023-11-28 10:26:16,709][87424] Updated weights for policy 0, policy_version 389849 (0.0012) -[2023-11-28 10:26:17,767][87426] Updated weights for policy 1, policy_version 389510 (0.0011) -[2023-11-28 10:26:18,146][87426] Updated weights for policy 1, policy_version 389520 (0.0012) -[2023-11-28 10:26:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 199516160. Throughput: 0: 2651.0, 1: 2718.4. Samples: 199530500. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:18,446][86177] Avg episode reward: [(0, '-539.160'), (1, '-524.480')] -[2023-11-28 10:26:18,457][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000389856_99803136.pth... -[2023-11-28 10:26:18,489][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000387360_99164160.pth -[2023-11-28 10:26:18,529][87426] Updated weights for policy 1, policy_version 389530 (0.0012) -[2023-11-28 10:26:18,750][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000389536_99721216.pth... -[2023-11-28 10:26:18,781][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000387008_99074048.pth -[2023-11-28 10:26:19,181][87424] Updated weights for policy 0, policy_version 389859 (0.0012) -[2023-11-28 10:26:19,562][87424] Updated weights for policy 0, policy_version 389869 (0.0012) -[2023-11-28 10:26:19,944][87424] Updated weights for policy 0, policy_version 389879 (0.0012) -[2023-11-28 10:26:20,615][87426] Updated weights for policy 1, policy_version 389540 (0.0011) -[2023-11-28 10:26:20,995][87426] Updated weights for policy 1, policy_version 389550 (0.0008) -[2023-11-28 10:26:21,392][87426] Updated weights for policy 1, policy_version 389560 (0.0008) -[2023-11-28 10:26:22,252][87424] Updated weights for policy 0, policy_version 389889 (0.0011) -[2023-11-28 10:26:22,632][87424] Updated weights for policy 0, policy_version 389899 (0.0012) -[2023-11-28 10:26:23,017][87424] Updated weights for policy 0, policy_version 389909 (0.0011) -[2023-11-28 10:26:23,393][87424] Updated weights for policy 0, policy_version 389919 (0.0011) -[2023-11-28 10:26:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 199548928. Throughput: 0: 2643.4, 1: 2730.6. Samples: 199562488. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:23,445][86177] Avg episode reward: [(0, '-541.600'), (1, '-560.180')] -[2023-11-28 10:26:23,702][87426] Updated weights for policy 1, policy_version 389570 (0.0010) -[2023-11-28 10:26:24,073][87426] Updated weights for policy 1, policy_version 389580 (0.0007) -[2023-11-28 10:26:24,452][87426] Updated weights for policy 1, policy_version 389590 (0.0008) -[2023-11-28 10:26:24,836][87426] Updated weights for policy 1, policy_version 389600 (0.0007) -[2023-11-28 10:26:25,936][87424] Updated weights for policy 0, policy_version 389929 (0.0012) -[2023-11-28 10:26:26,319][87424] Updated weights for policy 0, policy_version 389939 (0.0011) -[2023-11-28 10:26:26,555][87426] Updated weights for policy 1, policy_version 389610 (0.0011) -[2023-11-28 10:26:26,697][87424] Updated weights for policy 0, policy_version 389949 (0.0011) -[2023-11-28 10:26:26,939][87426] Updated weights for policy 1, policy_version 389620 (0.0008) -[2023-11-28 10:26:27,315][87426] Updated weights for policy 1, policy_version 389630 (0.0012) -[2023-11-28 10:26:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 199573504. Throughput: 0: 2622.7, 1: 2779.9. Samples: 199588460. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:28,446][86177] Avg episode reward: [(0, '-549.860'), (1, '-552.440')] -[2023-11-28 10:26:28,890][87426] Updated weights for policy 1, policy_version 389640 (0.0009) -[2023-11-28 10:26:29,093][87424] Updated weights for policy 0, policy_version 389959 (0.0009) -[2023-11-28 10:26:29,273][87426] Updated weights for policy 1, policy_version 389650 (0.0011) -[2023-11-28 10:26:29,490][87424] Updated weights for policy 0, policy_version 389969 (0.0009) -[2023-11-28 10:26:29,648][87426] Updated weights for policy 1, policy_version 389660 (0.0011) -[2023-11-28 10:26:29,873][87424] Updated weights for policy 0, policy_version 389979 (0.0011) -[2023-11-28 10:26:31,753][87426] Updated weights for policy 1, policy_version 389670 (0.0011) -[2023-11-28 10:26:31,928][87424] Updated weights for policy 0, policy_version 389989 (0.0009) -[2023-11-28 10:26:32,127][87426] Updated weights for policy 1, policy_version 389680 (0.0011) -[2023-11-28 10:26:32,301][87424] Updated weights for policy 0, policy_version 389999 (0.0011) -[2023-11-28 10:26:32,502][87426] Updated weights for policy 1, policy_version 389690 (0.0008) -[2023-11-28 10:26:32,683][87424] Updated weights for policy 0, policy_version 390009 (0.0011) -[2023-11-28 10:26:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 199606272. Throughput: 0: 2618.4, 1: 2789.4. Samples: 199613620. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:33,445][86177] Avg episode reward: [(0, '-545.290'), (1, '-555.960')] -[2023-11-28 10:26:34,719][87426] Updated weights for policy 1, policy_version 389700 (0.0009) -[2023-11-28 10:26:34,889][87424] Updated weights for policy 0, policy_version 390019 (0.0010) -[2023-11-28 10:26:35,100][87426] Updated weights for policy 1, policy_version 389710 (0.0011) -[2023-11-28 10:26:35,271][87424] Updated weights for policy 0, policy_version 390029 (0.0011) -[2023-11-28 10:26:35,478][87426] Updated weights for policy 1, policy_version 389720 (0.0011) -[2023-11-28 10:26:35,651][87424] Updated weights for policy 0, policy_version 390039 (0.0012) -[2023-11-28 10:26:37,618][87426] Updated weights for policy 1, policy_version 389730 (0.0008) -[2023-11-28 10:26:37,701][87424] Updated weights for policy 0, policy_version 390049 (0.0012) -[2023-11-28 10:26:37,982][87426] Updated weights for policy 1, policy_version 389740 (0.0011) -[2023-11-28 10:26:38,092][87424] Updated weights for policy 0, policy_version 390059 (0.0009) -[2023-11-28 10:26:38,369][87426] Updated weights for policy 1, policy_version 389750 (0.0011) -[2023-11-28 10:26:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 199622656. Throughput: 0: 2653.7, 1: 2771.9. Samples: 199645528. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:38,445][86177] Avg episode reward: [(0, '-550.940'), (1, '-552.110')] -[2023-11-28 10:26:38,476][87424] Updated weights for policy 0, policy_version 390069 (0.0009) -[2023-11-28 10:26:38,744][87426] Updated weights for policy 1, policy_version 389760 (0.0009) -[2023-11-28 10:26:38,853][87424] Updated weights for policy 0, policy_version 390079 (0.0009) -[2023-11-28 10:26:40,712][87426] Updated weights for policy 1, policy_version 389770 (0.0012) -[2023-11-28 10:26:41,094][87426] Updated weights for policy 1, policy_version 389780 (0.0011) -[2023-11-28 10:26:41,419][87424] Updated weights for policy 0, policy_version 390089 (0.0011) -[2023-11-28 10:26:41,474][87426] Updated weights for policy 1, policy_version 389790 (0.0010) -[2023-11-28 10:26:41,798][87424] Updated weights for policy 0, policy_version 390099 (0.0012) -[2023-11-28 10:26:42,175][87424] Updated weights for policy 0, policy_version 390109 (0.0012) -[2023-11-28 10:26:43,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 199655424. Throughput: 0: 2656.6, 1: 2773.5. Samples: 199669240. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:43,445][86177] Avg episode reward: [(0, '-536.770'), (1, '-554.650')] -[2023-11-28 10:26:44,124][87426] Updated weights for policy 1, policy_version 389800 (0.0010) -[2023-11-28 10:26:44,499][87426] Updated weights for policy 1, policy_version 389810 (0.0008) -[2023-11-28 10:26:44,837][87424] Updated weights for policy 0, policy_version 390119 (0.0010) -[2023-11-28 10:26:44,881][87426] Updated weights for policy 1, policy_version 389820 (0.0008) -[2023-11-28 10:26:45,216][87424] Updated weights for policy 0, policy_version 390129 (0.0007) -[2023-11-28 10:26:45,597][87424] Updated weights for policy 0, policy_version 390139 (0.0008) -[2023-11-28 10:26:47,202][87426] Updated weights for policy 1, policy_version 389830 (0.0007) -[2023-11-28 10:26:47,555][87424] Updated weights for policy 0, policy_version 390149 (0.0009) -[2023-11-28 10:26:47,589][87426] Updated weights for policy 1, policy_version 389840 (0.0008) -[2023-11-28 10:26:47,938][87424] Updated weights for policy 0, policy_version 390159 (0.0010) -[2023-11-28 10:26:47,971][87426] Updated weights for policy 1, policy_version 389850 (0.0009) -[2023-11-28 10:26:48,314][87424] Updated weights for policy 0, policy_version 390169 (0.0010) -[2023-11-28 10:26:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 199680000. Throughput: 0: 2644.3, 1: 2762.8. Samples: 199693384. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:48,445][86177] Avg episode reward: [(0, '-543.540'), (1, '-560.790')] -[2023-11-28 10:26:49,883][87426] Updated weights for policy 1, policy_version 389860 (0.0011) -[2023-11-28 10:26:50,264][87426] Updated weights for policy 1, policy_version 389870 (0.0012) -[2023-11-28 10:26:50,450][87424] Updated weights for policy 0, policy_version 390179 (0.0008) -[2023-11-28 10:26:50,631][87426] Updated weights for policy 1, policy_version 389880 (0.0010) -[2023-11-28 10:26:50,834][87424] Updated weights for policy 0, policy_version 390189 (0.0008) -[2023-11-28 10:26:51,212][87424] Updated weights for policy 0, policy_version 390199 (0.0009) -[2023-11-28 10:26:53,249][87426] Updated weights for policy 1, policy_version 389890 (0.0008) -[2023-11-28 10:26:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 199704576. Throughput: 0: 2660.7, 1: 2749.6. Samples: 199725912. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:53,445][86177] Avg episode reward: [(0, '-546.440'), (1, '-563.400')] -[2023-11-28 10:26:53,490][87424] Updated weights for policy 0, policy_version 390209 (0.0011) -[2023-11-28 10:26:53,634][87426] Updated weights for policy 1, policy_version 389900 (0.0012) -[2023-11-28 10:26:53,862][87424] Updated weights for policy 0, policy_version 390219 (0.0011) -[2023-11-28 10:26:54,004][87426] Updated weights for policy 1, policy_version 389910 (0.0011) -[2023-11-28 10:26:54,242][87424] Updated weights for policy 0, policy_version 390229 (0.0009) -[2023-11-28 10:26:54,383][87426] Updated weights for policy 1, policy_version 389920 (0.0010) -[2023-11-28 10:26:54,622][87424] Updated weights for policy 0, policy_version 390239 (0.0007) -[2023-11-28 10:26:57,015][87426] Updated weights for policy 1, policy_version 389930 (0.0007) -[2023-11-28 10:26:57,280][87424] Updated weights for policy 0, policy_version 390249 (0.0011) -[2023-11-28 10:26:57,387][87426] Updated weights for policy 1, policy_version 389940 (0.0008) -[2023-11-28 10:26:57,655][87424] Updated weights for policy 0, policy_version 390259 (0.0007) -[2023-11-28 10:26:57,763][87426] Updated weights for policy 1, policy_version 389950 (0.0008) -[2023-11-28 10:26:58,039][87424] Updated weights for policy 0, policy_version 390269 (0.0007) -[2023-11-28 10:26:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 199737344. Throughput: 0: 2660.6, 1: 2751.6. Samples: 199749764. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:26:58,445][86177] Avg episode reward: [(0, '-543.790'), (1, '-581.960')] -[2023-11-28 10:26:59,836][87424] Updated weights for policy 0, policy_version 390279 (0.0010) -[2023-11-28 10:27:00,194][87426] Updated weights for policy 1, policy_version 389960 (0.0011) -[2023-11-28 10:27:00,227][87424] Updated weights for policy 0, policy_version 390289 (0.0011) -[2023-11-28 10:27:00,566][87426] Updated weights for policy 1, policy_version 389970 (0.0009) -[2023-11-28 10:27:00,602][87424] Updated weights for policy 0, policy_version 390299 (0.0011) -[2023-11-28 10:27:00,954][87426] Updated weights for policy 1, policy_version 389980 (0.0008) -[2023-11-28 10:27:03,093][87426] Updated weights for policy 1, policy_version 389990 (0.0011) -[2023-11-28 10:27:03,134][87424] Updated weights for policy 0, policy_version 390309 (0.0009) -[2023-11-28 10:27:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 199753728. Throughput: 0: 2663.7, 1: 2737.3. Samples: 199773540. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:27:03,445][86177] Avg episode reward: [(0, '-550.290'), (1, '-542.900')] -[2023-11-28 10:27:03,468][87426] Updated weights for policy 1, policy_version 390000 (0.0011) -[2023-11-28 10:27:03,520][87424] Updated weights for policy 0, policy_version 390319 (0.0010) -[2023-11-28 10:27:03,854][87426] Updated weights for policy 1, policy_version 390010 (0.0008) -[2023-11-28 10:27:03,899][87424] Updated weights for policy 0, policy_version 390329 (0.0007) -[2023-11-28 10:27:05,850][87426] Updated weights for policy 1, policy_version 390020 (0.0008) -[2023-11-28 10:27:06,231][87426] Updated weights for policy 1, policy_version 390030 (0.0007) -[2023-11-28 10:27:06,308][87424] Updated weights for policy 0, policy_version 390339 (0.0011) -[2023-11-28 10:27:06,613][87426] Updated weights for policy 1, policy_version 390040 (0.0010) -[2023-11-28 10:27:06,693][87424] Updated weights for policy 0, policy_version 390349 (0.0008) -[2023-11-28 10:27:07,073][87424] Updated weights for policy 0, policy_version 390359 (0.0011) -[2023-11-28 10:27:08,376][87426] Updated weights for policy 1, policy_version 390050 (0.0009) -[2023-11-28 10:27:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 199786496. Throughput: 0: 2652.4, 1: 2724.4. Samples: 199804444. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:27:08,445][86177] Avg episode reward: [(0, '-541.410'), (1, '-544.000')] -[2023-11-28 10:27:08,757][87426] Updated weights for policy 1, policy_version 390060 (0.0007) -[2023-11-28 10:27:08,960][87424] Updated weights for policy 0, policy_version 390369 (0.0010) -[2023-11-28 10:27:09,129][87426] Updated weights for policy 1, policy_version 390070 (0.0009) -[2023-11-28 10:27:09,349][87424] Updated weights for policy 0, policy_version 390379 (0.0011) -[2023-11-28 10:27:09,505][87426] Updated weights for policy 1, policy_version 390080 (0.0007) -[2023-11-28 10:27:09,743][87424] Updated weights for policy 0, policy_version 390389 (0.0009) -[2023-11-28 10:27:10,124][87424] Updated weights for policy 0, policy_version 390399 (0.0012) -[2023-11-28 10:27:11,793][87426] Updated weights for policy 1, policy_version 390090 (0.0010) -[2023-11-28 10:27:12,172][87426] Updated weights for policy 1, policy_version 390100 (0.0011) -[2023-11-28 10:27:12,534][87424] Updated weights for policy 0, policy_version 390409 (0.0011) -[2023-11-28 10:27:12,548][87426] Updated weights for policy 1, policy_version 390110 (0.0011) -[2023-11-28 10:27:12,920][87424] Updated weights for policy 0, policy_version 390419 (0.0012) -[2023-11-28 10:27:13,308][87424] Updated weights for policy 0, policy_version 390429 (0.0012) -[2023-11-28 10:27:13,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 199819264. Throughput: 0: 2664.5, 1: 2685.5. Samples: 199829212. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:27:13,445][86177] Avg episode reward: [(0, '-569.140'), (1, '-542.600')] -[2023-11-28 10:27:14,536][87426] Updated weights for policy 1, policy_version 390120 (0.0011) -[2023-11-28 10:27:14,925][87426] Updated weights for policy 1, policy_version 390130 (0.0012) -[2023-11-28 10:27:15,291][87426] Updated weights for policy 1, policy_version 390140 (0.0012) -[2023-11-28 10:27:15,486][87424] Updated weights for policy 0, policy_version 390439 (0.0010) -[2023-11-28 10:27:15,867][87424] Updated weights for policy 0, policy_version 390449 (0.0008) -[2023-11-28 10:27:16,257][87424] Updated weights for policy 0, policy_version 390459 (0.0008) -[2023-11-28 10:27:17,338][87426] Updated weights for policy 1, policy_version 390150 (0.0012) -[2023-11-28 10:27:17,715][87426] Updated weights for policy 1, policy_version 390160 (0.0012) -[2023-11-28 10:27:18,003][87424] Updated weights for policy 0, policy_version 390469 (0.0008) -[2023-11-28 10:27:18,099][87426] Updated weights for policy 1, policy_version 390170 (0.0012) -[2023-11-28 10:27:18,383][87424] Updated weights for policy 0, policy_version 390479 (0.0007) -[2023-11-28 10:27:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.4, 300 sec: 5359.5). Total num frames: 199843840. Throughput: 0: 2662.8, 1: 2691.4. Samples: 199854556. Policy #0 lag: (min: 4.0, avg: 26.0, max: 36.0) -[2023-11-28 10:27:18,445][86177] Avg episode reward: [(0, '-564.590'), (1, '-518.070')] -[2023-11-28 10:27:18,765][87424] Updated weights for policy 0, policy_version 390489 (0.0007) -[2023-11-28 10:27:20,101][87426] Updated weights for policy 1, policy_version 390180 (0.0011) -[2023-11-28 10:27:20,483][87426] Updated weights for policy 1, policy_version 390190 (0.0009) -[2023-11-28 10:27:20,855][87426] Updated weights for policy 1, policy_version 390200 (0.0012) -[2023-11-28 10:27:20,964][87424] Updated weights for policy 0, policy_version 390499 (0.0011) -[2023-11-28 10:27:21,345][87424] Updated weights for policy 0, policy_version 390509 (0.0011) -[2023-11-28 10:27:21,725][87424] Updated weights for policy 0, policy_version 390519 (0.0012) -[2023-11-28 10:27:23,379][87426] Updated weights for policy 1, policy_version 390210 (0.0011) -[2023-11-28 10:27:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 199868416. Throughput: 0: 2660.2, 1: 2703.7. Samples: 199886904. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:27:23,445][86177] Avg episode reward: [(0, '-560.210'), (1, '-559.760')] -[2023-11-28 10:27:23,753][87426] Updated weights for policy 1, policy_version 390220 (0.0008) -[2023-11-28 10:27:24,132][87426] Updated weights for policy 1, policy_version 390230 (0.0008) -[2023-11-28 10:27:24,196][87424] Updated weights for policy 0, policy_version 390529 (0.0012) -[2023-11-28 10:27:24,512][87426] Updated weights for policy 1, policy_version 390240 (0.0008) -[2023-11-28 10:27:24,576][87424] Updated weights for policy 0, policy_version 390539 (0.0007) -[2023-11-28 10:27:24,955][87424] Updated weights for policy 0, policy_version 390549 (0.0008) -[2023-11-28 10:27:25,336][87424] Updated weights for policy 0, policy_version 390559 (0.0007) -[2023-11-28 10:27:26,986][87426] Updated weights for policy 1, policy_version 390250 (0.0007) -[2023-11-28 10:27:27,375][87426] Updated weights for policy 1, policy_version 390260 (0.0007) -[2023-11-28 10:27:27,522][87424] Updated weights for policy 0, policy_version 390569 (0.0011) -[2023-11-28 10:27:27,749][87426] Updated weights for policy 1, policy_version 390270 (0.0009) -[2023-11-28 10:27:27,917][87424] Updated weights for policy 0, policy_version 390579 (0.0012) -[2023-11-28 10:27:28,289][87424] Updated weights for policy 0, policy_version 390589 (0.0012) -[2023-11-28 10:27:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 199901184. Throughput: 0: 2656.9, 1: 2696.7. Samples: 199910152. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:27:28,445][86177] Avg episode reward: [(0, '-551.530'), (1, '-595.780')] -[2023-11-28 10:27:29,910][87426] Updated weights for policy 1, policy_version 390280 (0.0009) -[2023-11-28 10:27:30,301][87426] Updated weights for policy 1, policy_version 390290 (0.0011) -[2023-11-28 10:27:30,304][87424] Updated weights for policy 0, policy_version 390599 (0.0012) -[2023-11-28 10:27:30,672][87426] Updated weights for policy 1, policy_version 390300 (0.0011) -[2023-11-28 10:27:30,685][87424] Updated weights for policy 0, policy_version 390609 (0.0010) -[2023-11-28 10:27:31,059][87424] Updated weights for policy 0, policy_version 390619 (0.0008) -[2023-11-28 10:27:32,839][87426] Updated weights for policy 1, policy_version 390310 (0.0011) -[2023-11-28 10:27:33,217][87426] Updated weights for policy 1, policy_version 390320 (0.0012) -[2023-11-28 10:27:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 199917568. Throughput: 0: 2663.7, 1: 2688.3. Samples: 199934224. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:27:33,445][86177] Avg episode reward: [(0, '-533.300'), (1, '-593.720')] -[2023-11-28 10:27:33,475][87424] Updated weights for policy 0, policy_version 390629 (0.0009) -[2023-11-28 10:27:33,596][87426] Updated weights for policy 1, policy_version 390330 (0.0011) -[2023-11-28 10:27:33,856][87424] Updated weights for policy 0, policy_version 390639 (0.0011) -[2023-11-28 10:27:34,246][87424] Updated weights for policy 0, policy_version 390649 (0.0012) -[2023-11-28 10:27:35,452][87426] Updated weights for policy 1, policy_version 390340 (0.0012) -[2023-11-28 10:27:35,833][87426] Updated weights for policy 1, policy_version 390350 (0.0012) -[2023-11-28 10:27:35,978][87424] Updated weights for policy 0, policy_version 390659 (0.0012) -[2023-11-28 10:27:36,212][87426] Updated weights for policy 1, policy_version 390360 (0.0012) -[2023-11-28 10:27:36,356][87424] Updated weights for policy 0, policy_version 390669 (0.0012) -[2023-11-28 10:27:36,734][87424] Updated weights for policy 0, policy_version 390679 (0.0009) -[2023-11-28 10:27:38,402][87424] Updated weights for policy 0, policy_version 390689 (0.0011) -[2023-11-28 10:27:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 199950336. Throughput: 0: 2678.7, 1: 2698.5. Samples: 199967884. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:27:38,445][86177] Avg episode reward: [(0, '-539.580'), (1, '-610.970')] -[2023-11-28 10:27:38,725][87426] Updated weights for policy 1, policy_version 390370 (0.0011) -[2023-11-28 10:27:38,776][87424] Updated weights for policy 0, policy_version 390699 (0.0011) -[2023-11-28 10:27:39,084][87426] Updated weights for policy 1, policy_version 390380 (0.0008) -[2023-11-28 10:27:39,161][87424] Updated weights for policy 0, policy_version 390709 (0.0010) -[2023-11-28 10:27:39,462][87426] Updated weights for policy 1, policy_version 390390 (0.0011) -[2023-11-28 10:27:39,543][87424] Updated weights for policy 0, policy_version 390719 (0.0012) -[2023-11-28 10:27:39,839][87426] Updated weights for policy 1, policy_version 390400 (0.0012) -[2023-11-28 10:27:42,072][87424] Updated weights for policy 0, policy_version 390729 (0.0010) -[2023-11-28 10:27:42,348][87426] Updated weights for policy 1, policy_version 390410 (0.0009) -[2023-11-28 10:27:42,447][87424] Updated weights for policy 0, policy_version 390739 (0.0009) -[2023-11-28 10:27:42,726][87426] Updated weights for policy 1, policy_version 390420 (0.0012) -[2023-11-28 10:27:42,827][87424] Updated weights for policy 0, policy_version 390749 (0.0008) -[2023-11-28 10:27:43,104][87426] Updated weights for policy 1, policy_version 390430 (0.0012) -[2023-11-28 10:27:43,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 199983104. Throughput: 0: 2699.0, 1: 2678.4. Samples: 199991748. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:27:43,446][86177] Avg episode reward: [(0, '-542.770'), (1, '-575.070')] -[2023-11-28 10:27:44,897][87426] Updated weights for policy 1, policy_version 390440 (0.0012) -[2023-11-28 10:27:45,281][87426] Updated weights for policy 1, policy_version 390450 (0.0011) -[2023-11-28 10:27:45,389][87424] Updated weights for policy 0, policy_version 390759 (0.0009) -[2023-11-28 10:27:45,655][87426] Updated weights for policy 1, policy_version 390460 (0.0011) -[2023-11-28 10:27:45,765][87424] Updated weights for policy 0, policy_version 390769 (0.0010) -[2023-11-28 10:27:46,144][87424] Updated weights for policy 0, policy_version 390779 (0.0011) -[2023-11-28 10:27:47,999][87426] Updated weights for policy 1, policy_version 390470 (0.0012) -[2023-11-28 10:27:48,347][87424] Updated weights for policy 0, policy_version 390789 (0.0010) -[2023-11-28 10:27:48,371][87426] Updated weights for policy 1, policy_version 390480 (0.0010) -[2023-11-28 10:27:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 199999488. Throughput: 0: 2693.3, 1: 2685.2. Samples: 200015576. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:27:48,445][86177] Avg episode reward: [(0, '-567.800'), (1, '-574.560')] -[2023-11-28 10:27:48,720][87424] Updated weights for policy 0, policy_version 390799 (0.0011) -[2023-11-28 10:27:48,751][87426] Updated weights for policy 1, policy_version 390490 (0.0012) -[2023-11-28 10:27:49,105][87424] Updated weights for policy 0, policy_version 390809 (0.0011) -[2023-11-28 10:27:51,237][87424] Updated weights for policy 0, policy_version 390819 (0.0012) -[2023-11-28 10:27:51,370][87426] Updated weights for policy 1, policy_version 390500 (0.0011) -[2023-11-28 10:27:51,599][87424] Updated weights for policy 0, policy_version 390829 (0.0011) -[2023-11-28 10:27:51,747][87426] Updated weights for policy 1, policy_version 390510 (0.0010) -[2023-11-28 10:27:51,986][87424] Updated weights for policy 0, policy_version 390839 (0.0011) -[2023-11-28 10:27:52,128][87426] Updated weights for policy 1, policy_version 390520 (0.0010) -[2023-11-28 10:27:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200032256. Throughput: 0: 2721.9, 1: 2687.3. Samples: 200047856. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:27:53,445][86177] Avg episode reward: [(0, '-567.240'), (1, '-540.810')] -[2023-11-28 10:27:54,091][87424] Updated weights for policy 0, policy_version 390849 (0.0009) -[2023-11-28 10:27:54,350][87426] Updated weights for policy 1, policy_version 390530 (0.0012) -[2023-11-28 10:27:54,470][87424] Updated weights for policy 0, policy_version 390859 (0.0008) -[2023-11-28 10:27:54,722][87426] Updated weights for policy 1, policy_version 390540 (0.0012) -[2023-11-28 10:27:54,851][87424] Updated weights for policy 0, policy_version 390869 (0.0010) -[2023-11-28 10:27:55,099][87426] Updated weights for policy 1, policy_version 390550 (0.0011) -[2023-11-28 10:27:55,236][87424] Updated weights for policy 0, policy_version 390879 (0.0008) -[2023-11-28 10:27:55,478][87426] Updated weights for policy 1, policy_version 390560 (0.0007) -[2023-11-28 10:27:57,205][87424] Updated weights for policy 0, policy_version 390889 (0.0011) -[2023-11-28 10:27:57,398][87426] Updated weights for policy 1, policy_version 390570 (0.0012) -[2023-11-28 10:27:57,576][87424] Updated weights for policy 0, policy_version 390899 (0.0007) -[2023-11-28 10:27:57,772][87426] Updated weights for policy 1, policy_version 390580 (0.0012) -[2023-11-28 10:27:57,959][87424] Updated weights for policy 0, policy_version 390909 (0.0008) -[2023-11-28 10:27:58,148][87426] Updated weights for policy 1, policy_version 390590 (0.0010) -[2023-11-28 10:27:58,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200065024. Throughput: 0: 2715.5, 1: 2670.2. Samples: 200071568. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:27:58,446][86177] Avg episode reward: [(0, '-567.250'), (1, '-549.710')] -[2023-11-28 10:27:59,714][87424] Updated weights for policy 0, policy_version 390919 (0.0010) -[2023-11-28 10:28:00,092][87424] Updated weights for policy 0, policy_version 390929 (0.0011) -[2023-11-28 10:28:00,470][87424] Updated weights for policy 0, policy_version 390939 (0.0011) -[2023-11-28 10:28:00,474][87426] Updated weights for policy 1, policy_version 390600 (0.0010) -[2023-11-28 10:28:00,850][87426] Updated weights for policy 1, policy_version 390610 (0.0011) -[2023-11-28 10:28:01,229][87426] Updated weights for policy 1, policy_version 390620 (0.0011) -[2023-11-28 10:28:02,914][87424] Updated weights for policy 0, policy_version 390949 (0.0011) -[2023-11-28 10:28:03,296][87424] Updated weights for policy 0, policy_version 390959 (0.0012) -[2023-11-28 10:28:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5331.7). Total num frames: 200081408. Throughput: 0: 2732.1, 1: 2654.1. Samples: 200096936. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:28:03,445][86177] Avg episode reward: [(0, '-572.710'), (1, '-544.170')] -[2023-11-28 10:28:03,602][87426] Updated weights for policy 1, policy_version 390630 (0.0010) -[2023-11-28 10:28:03,684][87424] Updated weights for policy 0, policy_version 390969 (0.0010) -[2023-11-28 10:28:03,977][87426] Updated weights for policy 1, policy_version 390640 (0.0012) -[2023-11-28 10:28:04,359][87426] Updated weights for policy 1, policy_version 390650 (0.0011) -[2023-11-28 10:28:05,662][87424] Updated weights for policy 0, policy_version 390979 (0.0011) -[2023-11-28 10:28:06,038][87424] Updated weights for policy 0, policy_version 390989 (0.0011) -[2023-11-28 10:28:06,421][87424] Updated weights for policy 0, policy_version 390999 (0.0011) -[2023-11-28 10:28:06,684][87426] Updated weights for policy 1, policy_version 390660 (0.0011) -[2023-11-28 10:28:07,052][87426] Updated weights for policy 1, policy_version 390670 (0.0012) -[2023-11-28 10:28:07,435][87426] Updated weights for policy 1, policy_version 390680 (0.0012) -[2023-11-28 10:28:08,410][87424] Updated weights for policy 0, policy_version 391009 (0.0010) -[2023-11-28 10:28:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200114176. Throughput: 0: 2749.4, 1: 2649.6. Samples: 200129860. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:28:08,445][86177] Avg episode reward: [(0, '-556.360'), (1, '-580.230')] -[2023-11-28 10:28:08,794][87424] Updated weights for policy 0, policy_version 391019 (0.0012) -[2023-11-28 10:28:09,176][87424] Updated weights for policy 0, policy_version 391029 (0.0012) -[2023-11-28 10:28:09,218][87426] Updated weights for policy 1, policy_version 390690 (0.0012) -[2023-11-28 10:28:09,557][87424] Updated weights for policy 0, policy_version 391039 (0.0011) -[2023-11-28 10:28:09,599][87426] Updated weights for policy 1, policy_version 390700 (0.0012) -[2023-11-28 10:28:09,972][87426] Updated weights for policy 1, policy_version 390710 (0.0011) -[2023-11-28 10:28:10,348][87426] Updated weights for policy 1, policy_version 390720 (0.0009) -[2023-11-28 10:28:12,025][87424] Updated weights for policy 0, policy_version 391049 (0.0012) -[2023-11-28 10:28:12,405][87424] Updated weights for policy 0, policy_version 391059 (0.0012) -[2023-11-28 10:28:12,482][87426] Updated weights for policy 1, policy_version 390730 (0.0011) -[2023-11-28 10:28:12,801][87424] Updated weights for policy 0, policy_version 391069 (0.0009) -[2023-11-28 10:28:12,865][87426] Updated weights for policy 1, policy_version 390740 (0.0011) -[2023-11-28 10:28:13,243][87426] Updated weights for policy 1, policy_version 390750 (0.0012) -[2023-11-28 10:28:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200146944. Throughput: 0: 2746.9, 1: 2674.4. Samples: 200154112. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:28:13,445][86177] Avg episode reward: [(0, '-553.500'), (1, '-608.240')] -[2023-11-28 10:28:15,201][87424] Updated weights for policy 0, policy_version 391079 (0.0008) -[2023-11-28 10:28:15,527][87426] Updated weights for policy 1, policy_version 390760 (0.0011) -[2023-11-28 10:28:15,579][87424] Updated weights for policy 0, policy_version 391089 (0.0010) -[2023-11-28 10:28:15,906][87426] Updated weights for policy 1, policy_version 390770 (0.0012) -[2023-11-28 10:28:15,962][87424] Updated weights for policy 0, policy_version 391099 (0.0012) -[2023-11-28 10:28:16,283][87426] Updated weights for policy 1, policy_version 390780 (0.0011) -[2023-11-28 10:28:17,822][87424] Updated weights for policy 0, policy_version 391109 (0.0011) -[2023-11-28 10:28:18,208][87424] Updated weights for policy 0, policy_version 391119 (0.0012) -[2023-11-28 10:28:18,372][87426] Updated weights for policy 1, policy_version 390790 (0.0009) -[2023-11-28 10:28:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 200163328. Throughput: 0: 2729.3, 1: 2693.6. Samples: 200178256. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:28:18,445][86177] Avg episode reward: [(0, '-539.730'), (1, '-611.360')] -[2023-11-28 10:28:18,585][87424] Updated weights for policy 0, policy_version 391129 (0.0012) -[2023-11-28 10:28:18,761][87426] Updated weights for policy 1, policy_version 390800 (0.0007) -[2023-11-28 10:28:18,850][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000391136_100130816.pth... -[2023-11-28 10:28:18,898][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000388608_99483648.pth -[2023-11-28 10:28:19,143][87426] Updated weights for policy 1, policy_version 390810 (0.0009) -[2023-11-28 10:28:19,368][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000390816_100048896.pth... -[2023-11-28 10:28:19,400][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000388288_99401728.pth -[2023-11-28 10:28:20,920][87424] Updated weights for policy 0, policy_version 391139 (0.0011) -[2023-11-28 10:28:21,314][87424] Updated weights for policy 0, policy_version 391149 (0.0012) -[2023-11-28 10:28:21,447][87426] Updated weights for policy 1, policy_version 390820 (0.0009) -[2023-11-28 10:28:21,694][87424] Updated weights for policy 0, policy_version 391159 (0.0012) -[2023-11-28 10:28:21,827][87426] Updated weights for policy 1, policy_version 390830 (0.0012) -[2023-11-28 10:28:22,213][87426] Updated weights for policy 1, policy_version 390840 (0.0010) -[2023-11-28 10:28:23,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 200196096. Throughput: 0: 2717.2, 1: 2686.5. Samples: 200211052. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:28:23,445][86177] Avg episode reward: [(0, '-537.430'), (1, '-618.790')] -[2023-11-28 10:28:24,291][87424] Updated weights for policy 0, policy_version 391169 (0.0010) -[2023-11-28 10:28:24,292][87426] Updated weights for policy 1, policy_version 390850 (0.0011) -[2023-11-28 10:28:24,668][87426] Updated weights for policy 1, policy_version 390860 (0.0012) -[2023-11-28 10:28:24,677][87424] Updated weights for policy 0, policy_version 391179 (0.0008) -[2023-11-28 10:28:25,051][87426] Updated weights for policy 1, policy_version 390870 (0.0011) -[2023-11-28 10:28:25,053][87424] Updated weights for policy 0, policy_version 391189 (0.0011) -[2023-11-28 10:28:25,421][87426] Updated weights for policy 1, policy_version 390880 (0.0011) -[2023-11-28 10:28:25,441][87424] Updated weights for policy 0, policy_version 391199 (0.0008) -[2023-11-28 10:28:27,287][87424] Updated weights for policy 0, policy_version 391209 (0.0011) -[2023-11-28 10:28:27,667][87424] Updated weights for policy 0, policy_version 391219 (0.0011) -[2023-11-28 10:28:27,737][87426] Updated weights for policy 1, policy_version 390890 (0.0011) -[2023-11-28 10:28:28,047][87424] Updated weights for policy 0, policy_version 391229 (0.0012) -[2023-11-28 10:28:28,116][87426] Updated weights for policy 1, policy_version 390900 (0.0010) -[2023-11-28 10:28:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 200220672. Throughput: 0: 2704.0, 1: 2712.4. Samples: 200235484. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:28:28,445][86177] Avg episode reward: [(0, '-541.220'), (1, '-622.580')] -[2023-11-28 10:28:28,499][87426] Updated weights for policy 1, policy_version 390910 (0.0008) -[2023-11-28 10:28:30,310][87424] Updated weights for policy 0, policy_version 391239 (0.0008) -[2023-11-28 10:28:30,692][87424] Updated weights for policy 0, policy_version 391249 (0.0011) -[2023-11-28 10:28:30,970][87426] Updated weights for policy 1, policy_version 390920 (0.0010) -[2023-11-28 10:28:31,076][87424] Updated weights for policy 0, policy_version 391259 (0.0011) -[2023-11-28 10:28:31,357][87426] Updated weights for policy 1, policy_version 390930 (0.0008) -[2023-11-28 10:28:31,724][87426] Updated weights for policy 1, policy_version 390940 (0.0010) -[2023-11-28 10:28:33,236][87424] Updated weights for policy 0, policy_version 391269 (0.0012) -[2023-11-28 10:28:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 200245248. Throughput: 0: 2721.1, 1: 2702.3. Samples: 200259628. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:28:33,445][86177] Avg episode reward: [(0, '-539.200'), (1, '-702.350')] -[2023-11-28 10:28:33,615][87424] Updated weights for policy 0, policy_version 391279 (0.0010) -[2023-11-28 10:28:33,842][87426] Updated weights for policy 1, policy_version 390950 (0.0012) -[2023-11-28 10:28:33,993][87424] Updated weights for policy 0, policy_version 391289 (0.0007) -[2023-11-28 10:28:34,218][87426] Updated weights for policy 1, policy_version 390960 (0.0011) -[2023-11-28 10:28:34,597][87426] Updated weights for policy 1, policy_version 390970 (0.0011) -[2023-11-28 10:28:36,236][87424] Updated weights for policy 0, policy_version 391299 (0.0009) -[2023-11-28 10:28:36,625][87424] Updated weights for policy 0, policy_version 391309 (0.0012) -[2023-11-28 10:28:36,767][87426] Updated weights for policy 1, policy_version 390980 (0.0011) -[2023-11-28 10:28:36,996][87424] Updated weights for policy 0, policy_version 391319 (0.0011) -[2023-11-28 10:28:37,149][87426] Updated weights for policy 1, policy_version 390990 (0.0012) -[2023-11-28 10:28:37,521][87426] Updated weights for policy 1, policy_version 391000 (0.0010) -[2023-11-28 10:28:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200278016. Throughput: 0: 2727.5, 1: 2696.3. Samples: 200291924. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:28:38,446][86177] Avg episode reward: [(0, '-544.460'), (1, '-655.000')] -[2023-11-28 10:28:39,233][87424] Updated weights for policy 0, policy_version 391329 (0.0010) -[2023-11-28 10:28:39,616][87424] Updated weights for policy 0, policy_version 391339 (0.0012) -[2023-11-28 10:28:39,998][87424] Updated weights for policy 0, policy_version 391349 (0.0011) -[2023-11-28 10:28:40,029][87426] Updated weights for policy 1, policy_version 391010 (0.0008) -[2023-11-28 10:28:40,378][87424] Updated weights for policy 0, policy_version 391359 (0.0011) -[2023-11-28 10:28:40,406][87426] Updated weights for policy 1, policy_version 391020 (0.0010) -[2023-11-28 10:28:40,785][87426] Updated weights for policy 1, policy_version 391030 (0.0010) -[2023-11-28 10:28:41,170][87426] Updated weights for policy 1, policy_version 391040 (0.0012) -[2023-11-28 10:28:42,592][87424] Updated weights for policy 0, policy_version 391369 (0.0013) -[2023-11-28 10:28:42,968][87424] Updated weights for policy 0, policy_version 391379 (0.0012) -[2023-11-28 10:28:43,351][87424] Updated weights for policy 0, policy_version 391389 (0.0011) -[2023-11-28 10:28:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 200294400. Throughput: 0: 2727.1, 1: 2702.7. Samples: 200315908. Policy #0 lag: (min: 28.0, avg: 56.4, max: 89.0) -[2023-11-28 10:28:43,445][86177] Avg episode reward: [(0, '-547.610'), (1, '-666.140')] -[2023-11-28 10:28:43,584][87426] Updated weights for policy 1, policy_version 391050 (0.0012) -[2023-11-28 10:28:43,964][87426] Updated weights for policy 1, policy_version 391060 (0.0012) -[2023-11-28 10:28:44,337][87426] Updated weights for policy 1, policy_version 391070 (0.0011) -[2023-11-28 10:28:45,865][87424] Updated weights for policy 0, policy_version 391399 (0.0012) -[2023-11-28 10:28:46,252][87424] Updated weights for policy 0, policy_version 391409 (0.0012) -[2023-11-28 10:28:46,576][87426] Updated weights for policy 1, policy_version 391080 (0.0011) -[2023-11-28 10:28:46,628][87424] Updated weights for policy 0, policy_version 391419 (0.0011) -[2023-11-28 10:28:46,968][87426] Updated weights for policy 1, policy_version 391090 (0.0012) -[2023-11-28 10:28:47,336][87426] Updated weights for policy 1, policy_version 391100 (0.0012) -[2023-11-28 10:28:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200327168. Throughput: 0: 2705.2, 1: 2692.8. Samples: 200339844. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:28:48,445][86177] Avg episode reward: [(0, '-534.240'), (1, '-698.120')] -[2023-11-28 10:28:48,584][87424] Updated weights for policy 0, policy_version 391429 (0.0011) -[2023-11-28 10:28:48,960][87424] Updated weights for policy 0, policy_version 391439 (0.0012) -[2023-11-28 10:28:49,339][87424] Updated weights for policy 0, policy_version 391449 (0.0012) -[2023-11-28 10:28:49,760][87426] Updated weights for policy 1, policy_version 391110 (0.0011) -[2023-11-28 10:28:50,135][87426] Updated weights for policy 1, policy_version 391120 (0.0009) -[2023-11-28 10:28:50,528][87426] Updated weights for policy 1, policy_version 391130 (0.0009) -[2023-11-28 10:28:51,571][87424] Updated weights for policy 0, policy_version 391459 (0.0011) -[2023-11-28 10:28:51,958][87424] Updated weights for policy 0, policy_version 391469 (0.0011) -[2023-11-28 10:28:52,336][87424] Updated weights for policy 0, policy_version 391479 (0.0012) -[2023-11-28 10:28:52,689][87426] Updated weights for policy 1, policy_version 391140 (0.0011) -[2023-11-28 10:28:53,067][87426] Updated weights for policy 1, policy_version 391150 (0.0010) -[2023-11-28 10:28:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 200351744. Throughput: 0: 2684.1, 1: 2692.5. Samples: 200371808. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:28:53,445][86177] Avg episode reward: [(0, '-536.120'), (1, '-672.670')] -[2023-11-28 10:28:53,459][87426] Updated weights for policy 1, policy_version 391160 (0.0010) -[2023-11-28 10:28:54,547][87424] Updated weights for policy 0, policy_version 391489 (0.0008) -[2023-11-28 10:28:54,924][87424] Updated weights for policy 0, policy_version 391499 (0.0009) -[2023-11-28 10:28:55,315][87424] Updated weights for policy 0, policy_version 391509 (0.0010) -[2023-11-28 10:28:55,502][87426] Updated weights for policy 1, policy_version 391170 (0.0010) -[2023-11-28 10:28:55,703][87424] Updated weights for policy 0, policy_version 391519 (0.0009) -[2023-11-28 10:28:55,886][87426] Updated weights for policy 1, policy_version 391180 (0.0008) -[2023-11-28 10:28:56,269][87426] Updated weights for policy 1, policy_version 391190 (0.0012) -[2023-11-28 10:28:56,654][87426] Updated weights for policy 1, policy_version 391200 (0.0008) -[2023-11-28 10:28:57,925][87424] Updated weights for policy 0, policy_version 391529 (0.0010) -[2023-11-28 10:28:58,302][87424] Updated weights for policy 0, policy_version 391539 (0.0008) -[2023-11-28 10:28:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 200376320. Throughput: 0: 2685.5, 1: 2687.2. Samples: 200395884. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:28:58,445][86177] Avg episode reward: [(0, '-537.340'), (1, '-602.530')] -[2023-11-28 10:28:58,677][87426] Updated weights for policy 1, policy_version 391210 (0.0012) -[2023-11-28 10:28:58,696][87424] Updated weights for policy 0, policy_version 391549 (0.0007) -[2023-11-28 10:28:59,055][87426] Updated weights for policy 1, policy_version 391220 (0.0011) -[2023-11-28 10:28:59,436][87426] Updated weights for policy 1, policy_version 391230 (0.0011) -[2023-11-28 10:29:01,224][87424] Updated weights for policy 0, policy_version 391559 (0.0011) -[2023-11-28 10:29:01,612][87424] Updated weights for policy 0, policy_version 391569 (0.0012) -[2023-11-28 10:29:01,759][87426] Updated weights for policy 1, policy_version 391240 (0.0011) -[2023-11-28 10:29:01,995][87424] Updated weights for policy 0, policy_version 391579 (0.0011) -[2023-11-28 10:29:02,134][87426] Updated weights for policy 1, policy_version 391250 (0.0011) -[2023-11-28 10:29:02,504][87426] Updated weights for policy 1, policy_version 391260 (0.0011) -[2023-11-28 10:29:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200409088. Throughput: 0: 2675.0, 1: 2678.0. Samples: 200419144. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:03,445][86177] Avg episode reward: [(0, '-538.020'), (1, '-605.930')] -[2023-11-28 10:29:04,400][87424] Updated weights for policy 0, policy_version 391589 (0.0012) -[2023-11-28 10:29:04,785][87424] Updated weights for policy 0, policy_version 391599 (0.0012) -[2023-11-28 10:29:05,012][87426] Updated weights for policy 1, policy_version 391270 (0.0011) -[2023-11-28 10:29:05,166][87424] Updated weights for policy 0, policy_version 391609 (0.0011) -[2023-11-28 10:29:05,400][87426] Updated weights for policy 1, policy_version 391280 (0.0011) -[2023-11-28 10:29:05,784][87426] Updated weights for policy 1, policy_version 391290 (0.0011) -[2023-11-28 10:29:07,705][87426] Updated weights for policy 1, policy_version 391300 (0.0011) -[2023-11-28 10:29:07,765][87424] Updated weights for policy 0, policy_version 391619 (0.0011) -[2023-11-28 10:29:08,093][87426] Updated weights for policy 1, policy_version 391310 (0.0011) -[2023-11-28 10:29:08,141][87424] Updated weights for policy 0, policy_version 391629 (0.0011) -[2023-11-28 10:29:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 200425472. Throughput: 0: 2654.9, 1: 2680.1. Samples: 200451128. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:08,445][86177] Avg episode reward: [(0, '-531.400'), (1, '-586.720')] -[2023-11-28 10:29:08,472][87426] Updated weights for policy 1, policy_version 391320 (0.0008) -[2023-11-28 10:29:08,527][87424] Updated weights for policy 0, policy_version 391639 (0.0008) -[2023-11-28 10:29:10,549][87426] Updated weights for policy 1, policy_version 391330 (0.0008) -[2023-11-28 10:29:10,881][87424] Updated weights for policy 0, policy_version 391649 (0.0008) -[2023-11-28 10:29:10,934][87426] Updated weights for policy 1, policy_version 391340 (0.0011) -[2023-11-28 10:29:11,266][87424] Updated weights for policy 0, policy_version 391659 (0.0008) -[2023-11-28 10:29:11,318][87426] Updated weights for policy 1, policy_version 391350 (0.0009) -[2023-11-28 10:29:11,658][87424] Updated weights for policy 0, policy_version 391669 (0.0009) -[2023-11-28 10:29:11,686][87426] Updated weights for policy 1, policy_version 391360 (0.0009) -[2023-11-28 10:29:12,030][87424] Updated weights for policy 0, policy_version 391679 (0.0011) -[2023-11-28 10:29:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 200458240. Throughput: 0: 2643.6, 1: 2663.8. Samples: 200474320. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:13,445][86177] Avg episode reward: [(0, '-546.960'), (1, '-522.540')] -[2023-11-28 10:29:14,083][87426] Updated weights for policy 1, policy_version 391370 (0.0009) -[2023-11-28 10:29:14,191][87424] Updated weights for policy 0, policy_version 391689 (0.0011) -[2023-11-28 10:29:14,465][87426] Updated weights for policy 1, policy_version 391380 (0.0011) -[2023-11-28 10:29:14,573][87424] Updated weights for policy 0, policy_version 391699 (0.0007) -[2023-11-28 10:29:14,837][87426] Updated weights for policy 1, policy_version 391390 (0.0011) -[2023-11-28 10:29:14,954][87424] Updated weights for policy 0, policy_version 391709 (0.0008) -[2023-11-28 10:29:16,869][87426] Updated weights for policy 1, policy_version 391400 (0.0012) -[2023-11-28 10:29:17,136][87424] Updated weights for policy 0, policy_version 391719 (0.0011) -[2023-11-28 10:29:17,246][87426] Updated weights for policy 1, policy_version 391410 (0.0010) -[2023-11-28 10:29:17,519][87424] Updated weights for policy 0, policy_version 391729 (0.0011) -[2023-11-28 10:29:17,623][87426] Updated weights for policy 1, policy_version 391420 (0.0012) -[2023-11-28 10:29:17,901][87424] Updated weights for policy 0, policy_version 391739 (0.0012) -[2023-11-28 10:29:18,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200491008. Throughput: 0: 2629.6, 1: 2671.2. Samples: 200498164. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:18,445][86177] Avg episode reward: [(0, '-539.720'), (1, '-520.840')] -[2023-11-28 10:29:20,069][87424] Updated weights for policy 0, policy_version 391749 (0.0011) -[2023-11-28 10:29:20,106][87426] Updated weights for policy 1, policy_version 391430 (0.0011) -[2023-11-28 10:29:20,454][87424] Updated weights for policy 0, policy_version 391759 (0.0009) -[2023-11-28 10:29:20,490][87426] Updated weights for policy 1, policy_version 391440 (0.0009) -[2023-11-28 10:29:20,843][87424] Updated weights for policy 0, policy_version 391769 (0.0012) -[2023-11-28 10:29:20,867][87426] Updated weights for policy 1, policy_version 391450 (0.0011) -[2023-11-28 10:29:23,087][87424] Updated weights for policy 0, policy_version 391779 (0.0010) -[2023-11-28 10:29:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 200507392. Throughput: 0: 2615.4, 1: 2667.2. Samples: 200529640. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:23,445][86177] Avg episode reward: [(0, '-542.480'), (1, '-568.950')] -[2023-11-28 10:29:23,466][87426] Updated weights for policy 1, policy_version 391460 (0.0011) -[2023-11-28 10:29:23,472][87424] Updated weights for policy 0, policy_version 391789 (0.0008) -[2023-11-28 10:29:23,842][87426] Updated weights for policy 1, policy_version 391470 (0.0012) -[2023-11-28 10:29:23,865][87424] Updated weights for policy 0, policy_version 391799 (0.0008) -[2023-11-28 10:29:24,215][87426] Updated weights for policy 1, policy_version 391480 (0.0012) -[2023-11-28 10:29:25,671][87424] Updated weights for policy 0, policy_version 391809 (0.0011) -[2023-11-28 10:29:26,047][87424] Updated weights for policy 0, policy_version 391819 (0.0012) -[2023-11-28 10:29:26,283][87426] Updated weights for policy 1, policy_version 391490 (0.0012) -[2023-11-28 10:29:26,421][87424] Updated weights for policy 0, policy_version 391829 (0.0012) -[2023-11-28 10:29:26,663][87426] Updated weights for policy 1, policy_version 391500 (0.0008) -[2023-11-28 10:29:26,798][87424] Updated weights for policy 0, policy_version 391839 (0.0010) -[2023-11-28 10:29:27,065][87426] Updated weights for policy 1, policy_version 391510 (0.0008) -[2023-11-28 10:29:27,431][87426] Updated weights for policy 1, policy_version 391520 (0.0009) -[2023-11-28 10:29:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 200540160. Throughput: 0: 2634.0, 1: 2680.9. Samples: 200555080. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:28,445][86177] Avg episode reward: [(0, '-556.880'), (1, '-632.530')] -[2023-11-28 10:29:29,216][87424] Updated weights for policy 0, policy_version 391849 (0.0011) -[2023-11-28 10:29:29,599][87424] Updated weights for policy 0, policy_version 391859 (0.0012) -[2023-11-28 10:29:29,796][87426] Updated weights for policy 1, policy_version 391530 (0.0010) -[2023-11-28 10:29:29,981][87424] Updated weights for policy 0, policy_version 391869 (0.0011) -[2023-11-28 10:29:30,175][87426] Updated weights for policy 1, policy_version 391540 (0.0008) -[2023-11-28 10:29:30,563][87426] Updated weights for policy 1, policy_version 391550 (0.0009) -[2023-11-28 10:29:32,186][87424] Updated weights for policy 0, policy_version 391879 (0.0010) -[2023-11-28 10:29:32,490][87426] Updated weights for policy 1, policy_version 391560 (0.0010) -[2023-11-28 10:29:32,566][87424] Updated weights for policy 0, policy_version 391889 (0.0011) -[2023-11-28 10:29:32,870][87426] Updated weights for policy 1, policy_version 391570 (0.0011) -[2023-11-28 10:29:32,959][87424] Updated weights for policy 0, policy_version 391899 (0.0010) -[2023-11-28 10:29:33,248][87426] Updated weights for policy 1, policy_version 391580 (0.0011) -[2023-11-28 10:29:33,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200572928. Throughput: 0: 2643.5, 1: 2692.1. Samples: 200579944. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:33,445][86177] Avg episode reward: [(0, '-563.110'), (1, '-650.220')] -[2023-11-28 10:29:35,334][87426] Updated weights for policy 1, policy_version 391590 (0.0010) -[2023-11-28 10:29:35,376][87424] Updated weights for policy 0, policy_version 391909 (0.0009) -[2023-11-28 10:29:35,721][87426] Updated weights for policy 1, policy_version 391600 (0.0010) -[2023-11-28 10:29:35,751][87424] Updated weights for policy 0, policy_version 391919 (0.0010) -[2023-11-28 10:29:36,086][87426] Updated weights for policy 1, policy_version 391610 (0.0012) -[2023-11-28 10:29:36,130][87424] Updated weights for policy 0, policy_version 391929 (0.0011) -[2023-11-28 10:29:38,176][87426] Updated weights for policy 1, policy_version 391620 (0.0010) -[2023-11-28 10:29:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 200589312. Throughput: 0: 2622.7, 1: 2682.8. Samples: 200610552. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:38,445][86177] Avg episode reward: [(0, '-572.450'), (1, '-654.360')] -[2023-11-28 10:29:38,551][87426] Updated weights for policy 1, policy_version 391630 (0.0012) -[2023-11-28 10:29:38,642][87424] Updated weights for policy 0, policy_version 391939 (0.0012) -[2023-11-28 10:29:38,930][87426] Updated weights for policy 1, policy_version 391640 (0.0010) -[2023-11-28 10:29:39,029][87424] Updated weights for policy 0, policy_version 391949 (0.0012) -[2023-11-28 10:29:39,404][87424] Updated weights for policy 0, policy_version 391959 (0.0011) -[2023-11-28 10:29:41,140][87426] Updated weights for policy 1, policy_version 391650 (0.0010) -[2023-11-28 10:29:41,296][87424] Updated weights for policy 0, policy_version 391969 (0.0012) -[2023-11-28 10:29:41,524][87426] Updated weights for policy 1, policy_version 391660 (0.0008) -[2023-11-28 10:29:41,680][87424] Updated weights for policy 0, policy_version 391979 (0.0012) -[2023-11-28 10:29:41,905][87426] Updated weights for policy 1, policy_version 391670 (0.0011) -[2023-11-28 10:29:42,065][87424] Updated weights for policy 0, policy_version 391989 (0.0011) -[2023-11-28 10:29:42,269][87426] Updated weights for policy 1, policy_version 391680 (0.0012) -[2023-11-28 10:29:42,441][87424] Updated weights for policy 0, policy_version 391999 (0.0009) -[2023-11-28 10:29:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 200622080. Throughput: 0: 2616.8, 1: 2670.1. Samples: 200633792. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:43,445][86177] Avg episode reward: [(0, '-575.380'), (1, '-607.150')] -[2023-11-28 10:29:44,309][87426] Updated weights for policy 1, policy_version 391690 (0.0010) -[2023-11-28 10:29:44,623][87424] Updated weights for policy 0, policy_version 392009 (0.0011) -[2023-11-28 10:29:44,677][87426] Updated weights for policy 1, policy_version 391700 (0.0009) -[2023-11-28 10:29:45,001][87424] Updated weights for policy 0, policy_version 392019 (0.0009) -[2023-11-28 10:29:45,056][87426] Updated weights for policy 1, policy_version 391710 (0.0009) -[2023-11-28 10:29:45,381][87424] Updated weights for policy 0, policy_version 392029 (0.0009) -[2023-11-28 10:29:47,343][87426] Updated weights for policy 1, policy_version 391720 (0.0012) -[2023-11-28 10:29:47,402][87424] Updated weights for policy 0, policy_version 392039 (0.0011) -[2023-11-28 10:29:47,718][87426] Updated weights for policy 1, policy_version 391730 (0.0008) -[2023-11-28 10:29:47,777][87424] Updated weights for policy 0, policy_version 392049 (0.0012) -[2023-11-28 10:29:48,099][87426] Updated weights for policy 1, policy_version 391740 (0.0007) -[2023-11-28 10:29:48,160][87424] Updated weights for policy 0, policy_version 392059 (0.0009) -[2023-11-28 10:29:48,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200654848. Throughput: 0: 2656.5, 1: 2670.7. Samples: 200658868. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:48,445][86177] Avg episode reward: [(0, '-567.930'), (1, '-620.280')] -[2023-11-28 10:29:50,068][87426] Updated weights for policy 1, policy_version 391750 (0.0010) -[2023-11-28 10:29:50,450][87426] Updated weights for policy 1, policy_version 391760 (0.0011) -[2023-11-28 10:29:50,475][87424] Updated weights for policy 0, policy_version 392069 (0.0010) -[2023-11-28 10:29:50,830][87426] Updated weights for policy 1, policy_version 391770 (0.0008) -[2023-11-28 10:29:50,854][87424] Updated weights for policy 0, policy_version 392079 (0.0010) -[2023-11-28 10:29:51,231][87424] Updated weights for policy 0, policy_version 392089 (0.0011) -[2023-11-28 10:29:53,402][87426] Updated weights for policy 1, policy_version 391780 (0.0010) -[2023-11-28 10:29:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 200671232. Throughput: 0: 2663.9, 1: 2659.2. Samples: 200690668. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:53,445][86177] Avg episode reward: [(0, '-563.710'), (1, '-622.340')] -[2023-11-28 10:29:53,727][87424] Updated weights for policy 0, policy_version 392099 (0.0012) -[2023-11-28 10:29:53,780][87426] Updated weights for policy 1, policy_version 391790 (0.0011) -[2023-11-28 10:29:54,101][87424] Updated weights for policy 0, policy_version 392109 (0.0010) -[2023-11-28 10:29:54,161][87426] Updated weights for policy 1, policy_version 391800 (0.0011) -[2023-11-28 10:29:54,483][87424] Updated weights for policy 0, policy_version 392119 (0.0008) -[2023-11-28 10:29:56,573][87426] Updated weights for policy 1, policy_version 391810 (0.0008) -[2023-11-28 10:29:56,712][87424] Updated weights for policy 0, policy_version 392129 (0.0008) -[2023-11-28 10:29:56,961][87426] Updated weights for policy 1, policy_version 391820 (0.0012) -[2023-11-28 10:29:57,098][87424] Updated weights for policy 0, policy_version 392139 (0.0012) -[2023-11-28 10:29:57,345][87426] Updated weights for policy 1, policy_version 391830 (0.0011) -[2023-11-28 10:29:57,484][87424] Updated weights for policy 0, policy_version 392149 (0.0012) -[2023-11-28 10:29:57,720][87426] Updated weights for policy 1, policy_version 391840 (0.0011) -[2023-11-28 10:29:57,865][87424] Updated weights for policy 0, policy_version 392159 (0.0012) -[2023-11-28 10:29:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 200704000. Throughput: 0: 2679.9, 1: 2646.0. Samples: 200713984. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:29:58,445][86177] Avg episode reward: [(0, '-551.840'), (1, '-602.760')] -[2023-11-28 10:29:59,954][87424] Updated weights for policy 0, policy_version 392169 (0.0010) -[2023-11-28 10:30:00,089][87426] Updated weights for policy 1, policy_version 391850 (0.0011) -[2023-11-28 10:30:00,334][87424] Updated weights for policy 0, policy_version 392179 (0.0010) -[2023-11-28 10:30:00,470][87426] Updated weights for policy 1, policy_version 391860 (0.0012) -[2023-11-28 10:30:00,727][87424] Updated weights for policy 0, policy_version 392189 (0.0011) -[2023-11-28 10:30:00,846][87426] Updated weights for policy 1, policy_version 391870 (0.0011) -[2023-11-28 10:30:03,100][87424] Updated weights for policy 0, policy_version 392199 (0.0010) -[2023-11-28 10:30:03,247][87426] Updated weights for policy 1, policy_version 391880 (0.0011) -[2023-11-28 10:30:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 200720384. Throughput: 0: 2705.8, 1: 2642.0. Samples: 200738816. Policy #0 lag: (min: 31.0, avg: 39.5, max: 63.0) -[2023-11-28 10:30:03,445][86177] Avg episode reward: [(0, '-542.390'), (1, '-612.010')] -[2023-11-28 10:30:03,486][87424] Updated weights for policy 0, policy_version 392209 (0.0008) -[2023-11-28 10:30:03,626][87426] Updated weights for policy 1, policy_version 391890 (0.0012) -[2023-11-28 10:30:03,865][87424] Updated weights for policy 0, policy_version 392219 (0.0008) -[2023-11-28 10:30:04,002][87426] Updated weights for policy 1, policy_version 391900 (0.0010) -[2023-11-28 10:30:05,787][87424] Updated weights for policy 0, policy_version 392229 (0.0009) -[2023-11-28 10:30:05,812][87426] Updated weights for policy 1, policy_version 391910 (0.0012) -[2023-11-28 10:30:06,161][87424] Updated weights for policy 0, policy_version 392239 (0.0009) -[2023-11-28 10:30:06,198][87426] Updated weights for policy 1, policy_version 391920 (0.0011) -[2023-11-28 10:30:06,548][87424] Updated weights for policy 0, policy_version 392249 (0.0007) -[2023-11-28 10:30:06,584][87426] Updated weights for policy 1, policy_version 391930 (0.0012) -[2023-11-28 10:30:08,350][87424] Updated weights for policy 0, policy_version 392259 (0.0010) -[2023-11-28 10:30:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 200753152. Throughput: 0: 2716.2, 1: 2668.7. Samples: 200771960. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:08,445][86177] Avg episode reward: [(0, '-548.720'), (1, '-549.080')] -[2023-11-28 10:30:08,735][87424] Updated weights for policy 0, policy_version 392269 (0.0007) -[2023-11-28 10:30:08,777][87426] Updated weights for policy 1, policy_version 391940 (0.0011) -[2023-11-28 10:30:09,120][87424] Updated weights for policy 0, policy_version 392279 (0.0010) -[2023-11-28 10:30:09,157][87426] Updated weights for policy 1, policy_version 391950 (0.0011) -[2023-11-28 10:30:09,534][87426] Updated weights for policy 1, policy_version 391960 (0.0012) -[2023-11-28 10:30:11,278][87424] Updated weights for policy 0, policy_version 392289 (0.0011) -[2023-11-28 10:30:11,623][87426] Updated weights for policy 1, policy_version 391970 (0.0011) -[2023-11-28 10:30:11,662][87424] Updated weights for policy 0, policy_version 392299 (0.0010) -[2023-11-28 10:30:12,003][87426] Updated weights for policy 1, policy_version 391980 (0.0012) -[2023-11-28 10:30:12,045][87424] Updated weights for policy 0, policy_version 392309 (0.0011) -[2023-11-28 10:30:12,387][87426] Updated weights for policy 1, policy_version 391990 (0.0011) -[2023-11-28 10:30:12,430][87424] Updated weights for policy 0, policy_version 392319 (0.0011) -[2023-11-28 10:30:12,759][87426] Updated weights for policy 1, policy_version 392000 (0.0010) -[2023-11-28 10:30:13,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 200785920. Throughput: 0: 2703.2, 1: 2655.6. Samples: 200796228. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:13,445][86177] Avg episode reward: [(0, '-559.800'), (1, '-546.690')] -[2023-11-28 10:30:14,867][87424] Updated weights for policy 0, policy_version 392329 (0.0011) -[2023-11-28 10:30:14,915][87426] Updated weights for policy 1, policy_version 392010 (0.0009) -[2023-11-28 10:30:15,259][87424] Updated weights for policy 0, policy_version 392339 (0.0011) -[2023-11-28 10:30:15,296][87426] Updated weights for policy 1, policy_version 392020 (0.0008) -[2023-11-28 10:30:15,640][87424] Updated weights for policy 0, policy_version 392349 (0.0011) -[2023-11-28 10:30:15,669][87426] Updated weights for policy 1, policy_version 392030 (0.0011) -[2023-11-28 10:30:17,992][87426] Updated weights for policy 1, policy_version 392040 (0.0011) -[2023-11-28 10:30:18,015][87424] Updated weights for policy 0, policy_version 392359 (0.0010) -[2023-11-28 10:30:18,376][87426] Updated weights for policy 1, policy_version 392050 (0.0012) -[2023-11-28 10:30:18,405][87424] Updated weights for policy 0, policy_version 392369 (0.0007) -[2023-11-28 10:30:18,445][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.2, 300 sec: 5359.5). Total num frames: 200802304. Throughput: 0: 2682.3, 1: 2651.4. Samples: 200819960. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:18,446][86177] Avg episode reward: [(0, '-554.010'), (1, '-564.060')] -[2023-11-28 10:30:18,749][87426] Updated weights for policy 1, policy_version 392060 (0.0011) -[2023-11-28 10:30:18,784][87424] Updated weights for policy 0, policy_version 392379 (0.0010) -[2023-11-28 10:30:18,894][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000392064_100368384.pth... -[2023-11-28 10:30:18,938][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000389536_99721216.pth -[2023-11-28 10:30:18,982][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000392384_100450304.pth... -[2023-11-28 10:30:19,031][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000389856_99803136.pth -[2023-11-28 10:30:20,980][87424] Updated weights for policy 0, policy_version 392389 (0.0012) -[2023-11-28 10:30:21,352][87426] Updated weights for policy 1, policy_version 392070 (0.0010) -[2023-11-28 10:30:21,358][87424] Updated weights for policy 0, policy_version 392399 (0.0011) -[2023-11-28 10:30:21,729][87426] Updated weights for policy 1, policy_version 392080 (0.0010) -[2023-11-28 10:30:21,739][87424] Updated weights for policy 0, policy_version 392409 (0.0012) -[2023-11-28 10:30:22,098][87426] Updated weights for policy 1, policy_version 392090 (0.0010) -[2023-11-28 10:30:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 200835072. Throughput: 0: 2709.4, 1: 2646.8. Samples: 200851584. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:23,445][86177] Avg episode reward: [(0, '-548.730'), (1, '-554.730')] -[2023-11-28 10:30:24,042][87426] Updated weights for policy 1, policy_version 392100 (0.0012) -[2023-11-28 10:30:24,144][87424] Updated weights for policy 0, policy_version 392419 (0.0012) -[2023-11-28 10:30:24,420][87426] Updated weights for policy 1, policy_version 392110 (0.0007) -[2023-11-28 10:30:24,528][87424] Updated weights for policy 0, policy_version 392429 (0.0008) -[2023-11-28 10:30:24,801][87426] Updated weights for policy 1, policy_version 392120 (0.0007) -[2023-11-28 10:30:24,905][87424] Updated weights for policy 0, policy_version 392439 (0.0008) -[2023-11-28 10:30:26,598][87424] Updated weights for policy 0, policy_version 392449 (0.0007) -[2023-11-28 10:30:26,988][87424] Updated weights for policy 0, policy_version 392459 (0.0011) -[2023-11-28 10:30:27,023][87426] Updated weights for policy 1, policy_version 392130 (0.0010) -[2023-11-28 10:30:27,359][87424] Updated weights for policy 0, policy_version 392469 (0.0012) -[2023-11-28 10:30:27,387][87426] Updated weights for policy 1, policy_version 392140 (0.0009) -[2023-11-28 10:30:27,747][87424] Updated weights for policy 0, policy_version 392479 (0.0010) -[2023-11-28 10:30:27,767][87426] Updated weights for policy 1, policy_version 392150 (0.0008) -[2023-11-28 10:30:28,147][87426] Updated weights for policy 1, policy_version 392160 (0.0007) -[2023-11-28 10:30:28,444][86177] Fps is (10 sec: 6553.8, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 200867840. Throughput: 0: 2716.7, 1: 2678.4. Samples: 200876572. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:28,445][86177] Avg episode reward: [(0, '-566.870'), (1, '-558.830')] -[2023-11-28 10:30:30,072][87424] Updated weights for policy 0, policy_version 392489 (0.0009) -[2023-11-28 10:30:30,432][87426] Updated weights for policy 1, policy_version 392170 (0.0009) -[2023-11-28 10:30:30,452][87424] Updated weights for policy 0, policy_version 392499 (0.0009) -[2023-11-28 10:30:30,808][87426] Updated weights for policy 1, policy_version 392180 (0.0009) -[2023-11-28 10:30:30,836][87424] Updated weights for policy 0, policy_version 392509 (0.0012) -[2023-11-28 10:30:31,185][87426] Updated weights for policy 1, policy_version 392190 (0.0010) -[2023-11-28 10:30:32,853][87424] Updated weights for policy 0, policy_version 392519 (0.0009) -[2023-11-28 10:30:33,228][87424] Updated weights for policy 0, policy_version 392529 (0.0011) -[2023-11-28 10:30:33,301][87426] Updated weights for policy 1, policy_version 392200 (0.0008) -[2023-11-28 10:30:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 200884224. Throughput: 0: 2696.6, 1: 2675.6. Samples: 200900620. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:33,445][86177] Avg episode reward: [(0, '-564.670'), (1, '-584.190')] -[2023-11-28 10:30:33,606][87424] Updated weights for policy 0, policy_version 392539 (0.0010) -[2023-11-28 10:30:33,686][87426] Updated weights for policy 1, policy_version 392210 (0.0008) -[2023-11-28 10:30:34,058][87426] Updated weights for policy 1, policy_version 392220 (0.0007) -[2023-11-28 10:30:36,139][87424] Updated weights for policy 0, policy_version 392549 (0.0010) -[2023-11-28 10:30:36,310][87426] Updated weights for policy 1, policy_version 392230 (0.0009) -[2023-11-28 10:30:36,513][87424] Updated weights for policy 0, policy_version 392559 (0.0008) -[2023-11-28 10:30:36,685][87426] Updated weights for policy 1, policy_version 392240 (0.0009) -[2023-11-28 10:30:36,895][87424] Updated weights for policy 0, policy_version 392569 (0.0010) -[2023-11-28 10:30:37,061][87426] Updated weights for policy 1, policy_version 392250 (0.0012) -[2023-11-28 10:30:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 200916992. Throughput: 0: 2689.6, 1: 2665.3. Samples: 200931640. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:38,445][86177] Avg episode reward: [(0, '-561.010'), (1, '-562.180')] -[2023-11-28 10:30:39,046][87424] Updated weights for policy 0, policy_version 392579 (0.0012) -[2023-11-28 10:30:39,348][87426] Updated weights for policy 1, policy_version 392260 (0.0011) -[2023-11-28 10:30:39,426][87424] Updated weights for policy 0, policy_version 392589 (0.0012) -[2023-11-28 10:30:39,727][87426] Updated weights for policy 1, policy_version 392270 (0.0011) -[2023-11-28 10:30:39,814][87424] Updated weights for policy 0, policy_version 392599 (0.0012) -[2023-11-28 10:30:40,112][87426] Updated weights for policy 1, policy_version 392280 (0.0010) -[2023-11-28 10:30:42,021][87424] Updated weights for policy 0, policy_version 392609 (0.0011) -[2023-11-28 10:30:42,392][87424] Updated weights for policy 0, policy_version 392619 (0.0011) -[2023-11-28 10:30:42,755][87426] Updated weights for policy 1, policy_version 392290 (0.0010) -[2023-11-28 10:30:42,772][87424] Updated weights for policy 0, policy_version 392629 (0.0011) -[2023-11-28 10:30:43,132][87426] Updated weights for policy 1, policy_version 392300 (0.0012) -[2023-11-28 10:30:43,155][87424] Updated weights for policy 0, policy_version 392639 (0.0009) -[2023-11-28 10:30:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 200941568. Throughput: 0: 2693.8, 1: 2681.3. Samples: 200955864. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:43,445][86177] Avg episode reward: [(0, '-564.310'), (1, '-573.750')] -[2023-11-28 10:30:43,507][87426] Updated weights for policy 1, policy_version 392310 (0.0012) -[2023-11-28 10:30:43,888][87426] Updated weights for policy 1, policy_version 392320 (0.0011) -[2023-11-28 10:30:45,074][87424] Updated weights for policy 0, policy_version 392649 (0.0011) -[2023-11-28 10:30:45,452][87424] Updated weights for policy 0, policy_version 392659 (0.0012) -[2023-11-28 10:30:45,826][87424] Updated weights for policy 0, policy_version 392669 (0.0010) -[2023-11-28 10:30:46,106][87426] Updated weights for policy 1, policy_version 392330 (0.0011) -[2023-11-28 10:30:46,485][87426] Updated weights for policy 1, policy_version 392340 (0.0012) -[2023-11-28 10:30:46,867][87426] Updated weights for policy 1, policy_version 392350 (0.0012) -[2023-11-28 10:30:47,883][87424] Updated weights for policy 0, policy_version 392679 (0.0010) -[2023-11-28 10:30:48,259][87424] Updated weights for policy 0, policy_version 392689 (0.0012) -[2023-11-28 10:30:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 200966144. Throughput: 0: 2691.0, 1: 2683.4. Samples: 200980664. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:48,445][86177] Avg episode reward: [(0, '-586.640'), (1, '-589.590')] -[2023-11-28 10:30:48,645][87424] Updated weights for policy 0, policy_version 392699 (0.0012) -[2023-11-28 10:30:49,335][87426] Updated weights for policy 1, policy_version 392360 (0.0012) -[2023-11-28 10:30:49,711][87426] Updated weights for policy 1, policy_version 392370 (0.0012) -[2023-11-28 10:30:50,092][87426] Updated weights for policy 1, policy_version 392380 (0.0012) -[2023-11-28 10:30:51,129][87424] Updated weights for policy 0, policy_version 392709 (0.0011) -[2023-11-28 10:30:51,523][87424] Updated weights for policy 0, policy_version 392719 (0.0009) -[2023-11-28 10:30:51,915][87424] Updated weights for policy 0, policy_version 392729 (0.0018) -[2023-11-28 10:30:52,614][87426] Updated weights for policy 1, policy_version 392390 (0.0012) -[2023-11-28 10:30:53,004][87426] Updated weights for policy 1, policy_version 392400 (0.0012) -[2023-11-28 10:30:53,377][87426] Updated weights for policy 1, policy_version 392410 (0.0012) -[2023-11-28 10:30:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 200990720. Throughput: 0: 2691.1, 1: 2666.8. Samples: 201013064. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:53,445][86177] Avg episode reward: [(0, '-552.450'), (1, '-594.640')] -[2023-11-28 10:30:54,033][87424] Updated weights for policy 0, policy_version 392739 (0.0011) -[2023-11-28 10:30:54,424][87424] Updated weights for policy 0, policy_version 392749 (0.0011) -[2023-11-28 10:30:54,803][87424] Updated weights for policy 0, policy_version 392759 (0.0012) -[2023-11-28 10:30:55,192][87426] Updated weights for policy 1, policy_version 392420 (0.0011) -[2023-11-28 10:30:55,574][87426] Updated weights for policy 1, policy_version 392430 (0.0011) -[2023-11-28 10:30:55,956][87426] Updated weights for policy 1, policy_version 392440 (0.0011) -[2023-11-28 10:30:57,006][87424] Updated weights for policy 0, policy_version 392769 (0.0011) -[2023-11-28 10:30:57,392][87424] Updated weights for policy 0, policy_version 392779 (0.0012) -[2023-11-28 10:30:57,618][87426] Updated weights for policy 1, policy_version 392450 (0.0011) -[2023-11-28 10:30:57,768][87424] Updated weights for policy 0, policy_version 392789 (0.0010) -[2023-11-28 10:30:57,997][87426] Updated weights for policy 1, policy_version 392460 (0.0011) -[2023-11-28 10:30:58,169][87424] Updated weights for policy 0, policy_version 392799 (0.0011) -[2023-11-28 10:30:58,370][87426] Updated weights for policy 1, policy_version 392470 (0.0011) -[2023-11-28 10:30:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 201023488. Throughput: 0: 2684.2, 1: 2668.0. Samples: 201037076. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:30:58,445][86177] Avg episode reward: [(0, '-553.870'), (1, '-571.930')] -[2023-11-28 10:30:58,751][87426] Updated weights for policy 1, policy_version 392480 (0.0008) -[2023-11-28 10:31:00,307][87424] Updated weights for policy 0, policy_version 392809 (0.0008) -[2023-11-28 10:31:00,677][87424] Updated weights for policy 0, policy_version 392819 (0.0009) -[2023-11-28 10:31:01,066][87424] Updated weights for policy 0, policy_version 392829 (0.0009) -[2023-11-28 10:31:01,246][87426] Updated weights for policy 1, policy_version 392490 (0.0011) -[2023-11-28 10:31:01,626][87426] Updated weights for policy 1, policy_version 392500 (0.0011) -[2023-11-28 10:31:02,006][87426] Updated weights for policy 1, policy_version 392510 (0.0011) -[2023-11-28 10:31:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 201048064. Throughput: 0: 2701.9, 1: 2659.5. Samples: 201061220. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:31:03,445][86177] Avg episode reward: [(0, '-528.140'), (1, '-597.230')] -[2023-11-28 10:31:03,591][87424] Updated weights for policy 0, policy_version 392839 (0.0010) -[2023-11-28 10:31:03,838][87426] Updated weights for policy 1, policy_version 392520 (0.0011) -[2023-11-28 10:31:03,963][87424] Updated weights for policy 0, policy_version 392849 (0.0010) -[2023-11-28 10:31:04,213][87426] Updated weights for policy 1, policy_version 392530 (0.0011) -[2023-11-28 10:31:04,344][87424] Updated weights for policy 0, policy_version 392859 (0.0008) -[2023-11-28 10:31:04,590][87426] Updated weights for policy 1, policy_version 392540 (0.0012) -[2023-11-28 10:31:06,428][87424] Updated weights for policy 0, policy_version 392869 (0.0011) -[2023-11-28 10:31:06,800][87424] Updated weights for policy 0, policy_version 392879 (0.0011) -[2023-11-28 10:31:07,119][87426] Updated weights for policy 1, policy_version 392550 (0.0012) -[2023-11-28 10:31:07,176][87424] Updated weights for policy 0, policy_version 392889 (0.0012) -[2023-11-28 10:31:07,502][87426] Updated weights for policy 1, policy_version 392560 (0.0012) -[2023-11-28 10:31:07,879][87426] Updated weights for policy 1, policy_version 392570 (0.0012) -[2023-11-28 10:31:08,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201080832. Throughput: 0: 2692.3, 1: 2686.1. Samples: 201093612. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:31:08,445][86177] Avg episode reward: [(0, '-526.620'), (1, '-592.340')] -[2023-11-28 10:31:08,993][87424] Updated weights for policy 0, policy_version 392899 (0.0012) -[2023-11-28 10:31:09,378][87424] Updated weights for policy 0, policy_version 392909 (0.0012) -[2023-11-28 10:31:09,746][87424] Updated weights for policy 0, policy_version 392919 (0.0012) -[2023-11-28 10:31:10,483][87426] Updated weights for policy 1, policy_version 392580 (0.0011) -[2023-11-28 10:31:10,857][87426] Updated weights for policy 1, policy_version 392590 (0.0012) -[2023-11-28 10:31:11,239][87426] Updated weights for policy 1, policy_version 392600 (0.0008) -[2023-11-28 10:31:12,237][87424] Updated weights for policy 0, policy_version 392929 (0.0012) -[2023-11-28 10:31:12,615][87424] Updated weights for policy 0, policy_version 392939 (0.0011) -[2023-11-28 10:31:13,000][87424] Updated weights for policy 0, policy_version 392949 (0.0012) -[2023-11-28 10:31:13,381][87424] Updated weights for policy 0, policy_version 392959 (0.0014) -[2023-11-28 10:31:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 201105408. Throughput: 0: 2703.1, 1: 2663.5. Samples: 201118068. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:31:13,445][86177] Avg episode reward: [(0, '-526.800'), (1, '-559.840')] -[2023-11-28 10:31:13,774][87426] Updated weights for policy 1, policy_version 392610 (0.0008) -[2023-11-28 10:31:14,157][87426] Updated weights for policy 1, policy_version 392620 (0.0010) -[2023-11-28 10:31:14,542][87426] Updated weights for policy 1, policy_version 392630 (0.0009) -[2023-11-28 10:31:14,923][87426] Updated weights for policy 1, policy_version 392640 (0.0007) -[2023-11-28 10:31:15,530][87424] Updated weights for policy 0, policy_version 392969 (0.0009) -[2023-11-28 10:31:15,911][87424] Updated weights for policy 0, policy_version 392979 (0.0008) -[2023-11-28 10:31:16,293][87424] Updated weights for policy 0, policy_version 392989 (0.0008) -[2023-11-28 10:31:16,590][87426] Updated weights for policy 1, policy_version 392650 (0.0009) -[2023-11-28 10:31:16,978][87426] Updated weights for policy 1, policy_version 392660 (0.0007) -[2023-11-28 10:31:17,365][87426] Updated weights for policy 1, policy_version 392670 (0.0007) -[2023-11-28 10:31:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5359.5). Total num frames: 201129984. Throughput: 0: 2706.7, 1: 2672.8. Samples: 201142696. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:31:18,445][86177] Avg episode reward: [(0, '-522.400'), (1, '-558.020')] -[2023-11-28 10:31:18,689][87424] Updated weights for policy 0, policy_version 392999 (0.0010) -[2023-11-28 10:31:19,063][87424] Updated weights for policy 0, policy_version 393009 (0.0011) -[2023-11-28 10:31:19,154][87426] Updated weights for policy 1, policy_version 392680 (0.0008) -[2023-11-28 10:31:19,441][87424] Updated weights for policy 0, policy_version 393019 (0.0010) -[2023-11-28 10:31:19,532][87426] Updated weights for policy 1, policy_version 392690 (0.0010) -[2023-11-28 10:31:19,908][87426] Updated weights for policy 1, policy_version 392700 (0.0010) -[2023-11-28 10:31:21,506][87424] Updated weights for policy 0, policy_version 393029 (0.0011) -[2023-11-28 10:31:21,884][87424] Updated weights for policy 0, policy_version 393039 (0.0012) -[2023-11-28 10:31:22,268][87424] Updated weights for policy 0, policy_version 393049 (0.0010) -[2023-11-28 10:31:22,543][87426] Updated weights for policy 1, policy_version 392710 (0.0011) -[2023-11-28 10:31:22,923][87426] Updated weights for policy 1, policy_version 392720 (0.0011) -[2023-11-28 10:31:23,300][87426] Updated weights for policy 1, policy_version 392730 (0.0009) -[2023-11-28 10:31:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 201154560. Throughput: 0: 2724.0, 1: 2673.5. Samples: 201174528. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:31:23,445][86177] Avg episode reward: [(0, '-530.480'), (1, '-540.680')] -[2023-11-28 10:31:24,804][87424] Updated weights for policy 0, policy_version 393059 (0.0011) -[2023-11-28 10:31:25,186][87424] Updated weights for policy 0, policy_version 393069 (0.0011) -[2023-11-28 10:31:25,436][87426] Updated weights for policy 1, policy_version 392740 (0.0010) -[2023-11-28 10:31:25,567][87424] Updated weights for policy 0, policy_version 393079 (0.0008) -[2023-11-28 10:31:25,807][87426] Updated weights for policy 1, policy_version 392750 (0.0012) -[2023-11-28 10:31:26,186][87426] Updated weights for policy 1, policy_version 392760 (0.0011) -[2023-11-28 10:31:27,778][87424] Updated weights for policy 0, policy_version 393089 (0.0007) -[2023-11-28 10:31:27,929][87426] Updated weights for policy 1, policy_version 392770 (0.0011) -[2023-11-28 10:31:28,149][87424] Updated weights for policy 0, policy_version 393099 (0.0011) -[2023-11-28 10:31:28,315][87426] Updated weights for policy 1, policy_version 392780 (0.0009) -[2023-11-28 10:31:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 201179136. Throughput: 0: 2702.1, 1: 2713.2. Samples: 201199552. Policy #0 lag: (min: 13.0, avg: 32.6, max: 52.0) -[2023-11-28 10:31:28,445][86177] Avg episode reward: [(0, '-529.200'), (1, '-537.840')] -[2023-11-28 10:31:28,528][87424] Updated weights for policy 0, policy_version 393109 (0.0012) -[2023-11-28 10:31:28,690][87426] Updated weights for policy 1, policy_version 392790 (0.0011) -[2023-11-28 10:31:28,912][87424] Updated weights for policy 0, policy_version 393119 (0.0012) -[2023-11-28 10:31:29,071][87426] Updated weights for policy 1, policy_version 392800 (0.0011) -[2023-11-28 10:31:30,883][87426] Updated weights for policy 1, policy_version 392810 (0.0010) -[2023-11-28 10:31:30,978][87424] Updated weights for policy 0, policy_version 393129 (0.0012) -[2023-11-28 10:31:31,268][87426] Updated weights for policy 1, policy_version 392820 (0.0011) -[2023-11-28 10:31:31,363][87424] Updated weights for policy 0, policy_version 393139 (0.0012) -[2023-11-28 10:31:31,644][87426] Updated weights for policy 1, policy_version 392830 (0.0012) -[2023-11-28 10:31:31,743][87424] Updated weights for policy 0, policy_version 393149 (0.0011) -[2023-11-28 10:31:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201211904. Throughput: 0: 2680.5, 1: 2721.4. Samples: 201223752. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:31:33,445][86177] Avg episode reward: [(0, '-539.530'), (1, '-579.380')] -[2023-11-28 10:31:33,858][87424] Updated weights for policy 0, policy_version 393159 (0.0008) -[2023-11-28 10:31:34,035][87426] Updated weights for policy 1, policy_version 392840 (0.0011) -[2023-11-28 10:31:34,246][87424] Updated weights for policy 0, policy_version 393169 (0.0007) -[2023-11-28 10:31:34,411][87426] Updated weights for policy 1, policy_version 392850 (0.0007) -[2023-11-28 10:31:34,625][87424] Updated weights for policy 0, policy_version 393179 (0.0008) -[2023-11-28 10:31:34,795][87426] Updated weights for policy 1, policy_version 392860 (0.0009) -[2023-11-28 10:31:37,024][87424] Updated weights for policy 0, policy_version 393189 (0.0011) -[2023-11-28 10:31:37,142][87426] Updated weights for policy 1, policy_version 392870 (0.0010) -[2023-11-28 10:31:37,402][87424] Updated weights for policy 0, policy_version 393199 (0.0011) -[2023-11-28 10:31:37,509][87426] Updated weights for policy 1, policy_version 392880 (0.0011) -[2023-11-28 10:31:37,787][87424] Updated weights for policy 0, policy_version 393209 (0.0008) -[2023-11-28 10:31:37,886][87426] Updated weights for policy 1, policy_version 392890 (0.0011) -[2023-11-28 10:31:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201244672. Throughput: 0: 2678.8, 1: 2736.8. Samples: 201256764. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:31:38,445][86177] Avg episode reward: [(0, '-546.890'), (1, '-581.930')] -[2023-11-28 10:31:39,933][87424] Updated weights for policy 0, policy_version 393219 (0.0009) -[2023-11-28 10:31:40,154][87426] Updated weights for policy 1, policy_version 392900 (0.0011) -[2023-11-28 10:31:40,321][87424] Updated weights for policy 0, policy_version 393229 (0.0012) -[2023-11-28 10:31:40,525][87426] Updated weights for policy 1, policy_version 392910 (0.0008) -[2023-11-28 10:31:40,700][87424] Updated weights for policy 0, policy_version 393239 (0.0012) -[2023-11-28 10:31:40,905][87426] Updated weights for policy 1, policy_version 392920 (0.0008) -[2023-11-28 10:31:43,032][87424] Updated weights for policy 0, policy_version 393249 (0.0011) -[2023-11-28 10:31:43,282][87426] Updated weights for policy 1, policy_version 392930 (0.0011) -[2023-11-28 10:31:43,418][87424] Updated weights for policy 0, policy_version 393259 (0.0011) -[2023-11-28 10:31:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 201261056. Throughput: 0: 2681.0, 1: 2739.3. Samples: 201280988. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:31:43,445][86177] Avg episode reward: [(0, '-538.130'), (1, '-595.420')] -[2023-11-28 10:31:43,671][87426] Updated weights for policy 1, policy_version 392940 (0.0009) -[2023-11-28 10:31:43,797][87424] Updated weights for policy 0, policy_version 393269 (0.0011) -[2023-11-28 10:31:44,038][87426] Updated weights for policy 1, policy_version 392950 (0.0011) -[2023-11-28 10:31:44,185][87424] Updated weights for policy 0, policy_version 393279 (0.0011) -[2023-11-28 10:31:44,424][87426] Updated weights for policy 1, policy_version 392960 (0.0009) -[2023-11-28 10:31:46,301][87426] Updated weights for policy 1, policy_version 392970 (0.0011) -[2023-11-28 10:31:46,459][87424] Updated weights for policy 0, policy_version 393289 (0.0011) -[2023-11-28 10:31:46,671][87426] Updated weights for policy 1, policy_version 392980 (0.0011) -[2023-11-28 10:31:46,835][87424] Updated weights for policy 0, policy_version 393299 (0.0009) -[2023-11-28 10:31:47,051][87426] Updated weights for policy 1, policy_version 392990 (0.0011) -[2023-11-28 10:31:47,225][87424] Updated weights for policy 0, policy_version 393309 (0.0010) -[2023-11-28 10:31:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201293824. Throughput: 0: 2674.8, 1: 2739.6. Samples: 201304868. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:31:48,445][86177] Avg episode reward: [(0, '-541.190'), (1, '-557.560')] -[2023-11-28 10:31:48,846][87424] Updated weights for policy 0, policy_version 393319 (0.0011) -[2023-11-28 10:31:48,884][87426] Updated weights for policy 1, policy_version 393000 (0.0009) -[2023-11-28 10:31:49,237][87424] Updated weights for policy 0, policy_version 393329 (0.0012) -[2023-11-28 10:31:49,270][87426] Updated weights for policy 1, policy_version 393010 (0.0009) -[2023-11-28 10:31:49,615][87424] Updated weights for policy 0, policy_version 393339 (0.0010) -[2023-11-28 10:31:49,646][87426] Updated weights for policy 1, policy_version 393020 (0.0010) -[2023-11-28 10:31:51,760][87424] Updated weights for policy 0, policy_version 393349 (0.0011) -[2023-11-28 10:31:51,976][87426] Updated weights for policy 1, policy_version 393030 (0.0010) -[2023-11-28 10:31:52,136][87424] Updated weights for policy 0, policy_version 393359 (0.0011) -[2023-11-28 10:31:52,357][87426] Updated weights for policy 1, policy_version 393040 (0.0009) -[2023-11-28 10:31:52,520][87424] Updated weights for policy 0, policy_version 393369 (0.0010) -[2023-11-28 10:31:52,738][87426] Updated weights for policy 1, policy_version 393050 (0.0007) -[2023-11-28 10:31:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 201326592. Throughput: 0: 2677.2, 1: 2756.9. Samples: 201338144. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:31:53,445][86177] Avg episode reward: [(0, '-538.240'), (1, '-556.210')] -[2023-11-28 10:31:54,586][87424] Updated weights for policy 0, policy_version 393379 (0.0008) -[2023-11-28 10:31:54,915][87426] Updated weights for policy 1, policy_version 393060 (0.0010) -[2023-11-28 10:31:54,974][87424] Updated weights for policy 0, policy_version 393389 (0.0009) -[2023-11-28 10:31:55,290][87426] Updated weights for policy 1, policy_version 393070 (0.0011) -[2023-11-28 10:31:55,359][87424] Updated weights for policy 0, policy_version 393399 (0.0008) -[2023-11-28 10:31:55,669][87426] Updated weights for policy 1, policy_version 393080 (0.0012) -[2023-11-28 10:31:57,542][87426] Updated weights for policy 1, policy_version 393090 (0.0011) -[2023-11-28 10:31:57,820][87424] Updated weights for policy 0, policy_version 393409 (0.0009) -[2023-11-28 10:31:57,913][87426] Updated weights for policy 1, policy_version 393100 (0.0007) -[2023-11-28 10:31:58,204][87424] Updated weights for policy 0, policy_version 393419 (0.0007) -[2023-11-28 10:31:58,309][87426] Updated weights for policy 1, policy_version 393110 (0.0007) -[2023-11-28 10:31:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 201342976. Throughput: 0: 2666.8, 1: 2778.6. Samples: 201363112. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:31:58,445][86177] Avg episode reward: [(0, '-532.830'), (1, '-552.260')] -[2023-11-28 10:31:58,586][87424] Updated weights for policy 0, policy_version 393429 (0.0008) -[2023-11-28 10:31:58,680][87426] Updated weights for policy 1, policy_version 393120 (0.0010) -[2023-11-28 10:31:58,965][87424] Updated weights for policy 0, policy_version 393439 (0.0008) -[2023-11-28 10:32:00,393][87426] Updated weights for policy 1, policy_version 393130 (0.0008) -[2023-11-28 10:32:00,786][87426] Updated weights for policy 1, policy_version 393140 (0.0008) -[2023-11-28 10:32:01,156][87426] Updated weights for policy 1, policy_version 393150 (0.0008) -[2023-11-28 10:32:01,285][87424] Updated weights for policy 0, policy_version 393449 (0.0008) -[2023-11-28 10:32:01,669][87424] Updated weights for policy 0, policy_version 393459 (0.0009) -[2023-11-28 10:32:02,049][87424] Updated weights for policy 0, policy_version 393469 (0.0009) -[2023-11-28 10:32:03,410][87426] Updated weights for policy 1, policy_version 393160 (0.0008) -[2023-11-28 10:32:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201375744. Throughput: 0: 2671.7, 1: 2776.3. Samples: 201387856. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:03,445][86177] Avg episode reward: [(0, '-532.080'), (1, '-559.650')] -[2023-11-28 10:32:03,788][87426] Updated weights for policy 1, policy_version 393170 (0.0008) -[2023-11-28 10:32:04,168][87426] Updated weights for policy 1, policy_version 393180 (0.0011) -[2023-11-28 10:32:04,544][87424] Updated weights for policy 0, policy_version 393479 (0.0010) -[2023-11-28 10:32:04,933][87424] Updated weights for policy 0, policy_version 393489 (0.0009) -[2023-11-28 10:32:05,316][87424] Updated weights for policy 0, policy_version 393499 (0.0009) -[2023-11-28 10:32:06,320][87426] Updated weights for policy 1, policy_version 393190 (0.0011) -[2023-11-28 10:32:06,700][87426] Updated weights for policy 1, policy_version 393200 (0.0012) -[2023-11-28 10:32:07,015][87424] Updated weights for policy 0, policy_version 393509 (0.0010) -[2023-11-28 10:32:07,073][87426] Updated weights for policy 1, policy_version 393210 (0.0012) -[2023-11-28 10:32:07,384][87424] Updated weights for policy 0, policy_version 393519 (0.0012) -[2023-11-28 10:32:07,769][87424] Updated weights for policy 0, policy_version 393529 (0.0012) -[2023-11-28 10:32:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201408512. Throughput: 0: 2671.8, 1: 2803.1. Samples: 201420900. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:08,445][86177] Avg episode reward: [(0, '-527.820'), (1, '-577.920')] -[2023-11-28 10:32:08,926][87426] Updated weights for policy 1, policy_version 393220 (0.0010) -[2023-11-28 10:32:09,309][87426] Updated weights for policy 1, policy_version 393230 (0.0012) -[2023-11-28 10:32:09,688][87426] Updated weights for policy 1, policy_version 393240 (0.0012) -[2023-11-28 10:32:10,274][87424] Updated weights for policy 0, policy_version 393539 (0.0012) -[2023-11-28 10:32:10,659][87424] Updated weights for policy 0, policy_version 393549 (0.0013) -[2023-11-28 10:32:11,038][87424] Updated weights for policy 0, policy_version 393559 (0.0010) -[2023-11-28 10:32:12,118][87426] Updated weights for policy 1, policy_version 393250 (0.0013) -[2023-11-28 10:32:12,498][87426] Updated weights for policy 1, policy_version 393260 (0.0012) -[2023-11-28 10:32:12,879][87426] Updated weights for policy 1, policy_version 393270 (0.0012) -[2023-11-28 10:32:13,221][87424] Updated weights for policy 0, policy_version 393569 (0.0009) -[2023-11-28 10:32:13,252][87426] Updated weights for policy 1, policy_version 393280 (0.0011) -[2023-11-28 10:32:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201433088. Throughput: 0: 2674.4, 1: 2777.4. Samples: 201444884. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:13,445][86177] Avg episode reward: [(0, '-524.570'), (1, '-571.390')] -[2023-11-28 10:32:13,596][87424] Updated weights for policy 0, policy_version 393579 (0.0011) -[2023-11-28 10:32:13,979][87424] Updated weights for policy 0, policy_version 393589 (0.0012) -[2023-11-28 10:32:14,359][87424] Updated weights for policy 0, policy_version 393599 (0.0012) -[2023-11-28 10:32:15,456][87426] Updated weights for policy 1, policy_version 393290 (0.0009) -[2023-11-28 10:32:15,833][87426] Updated weights for policy 1, policy_version 393300 (0.0009) -[2023-11-28 10:32:16,212][87426] Updated weights for policy 1, policy_version 393310 (0.0011) -[2023-11-28 10:32:16,828][87424] Updated weights for policy 0, policy_version 393609 (0.0008) -[2023-11-28 10:32:17,212][87424] Updated weights for policy 0, policy_version 393619 (0.0007) -[2023-11-28 10:32:17,587][87424] Updated weights for policy 0, policy_version 393629 (0.0007) -[2023-11-28 10:32:18,192][87426] Updated weights for policy 1, policy_version 393320 (0.0012) -[2023-11-28 10:32:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201457664. Throughput: 0: 2663.1, 1: 2787.0. Samples: 201469008. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:18,445][86177] Avg episode reward: [(0, '-527.650'), (1, '-581.040')] -[2023-11-28 10:32:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000393632_100769792.pth... -[2023-11-28 10:32:18,498][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000391136_100130816.pth -[2023-11-28 10:32:18,504][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000393632_100769792.pth -[2023-11-28 10:32:18,571][87426] Updated weights for policy 1, policy_version 393330 (0.0011) -[2023-11-28 10:32:18,952][87426] Updated weights for policy 1, policy_version 393340 (0.0011) -[2023-11-28 10:32:19,090][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000393344_100696064.pth... -[2023-11-28 10:32:19,137][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000390816_100048896.pth -[2023-11-28 10:32:19,144][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000393344_100696064.pth -[2023-11-28 10:32:20,051][87424] Updated weights for policy 0, policy_version 393639 (0.0010) -[2023-11-28 10:32:20,437][87424] Updated weights for policy 0, policy_version 393649 (0.0011) -[2023-11-28 10:32:20,818][87424] Updated weights for policy 0, policy_version 393659 (0.0009) -[2023-11-28 10:32:21,162][87426] Updated weights for policy 1, policy_version 393350 (0.0011) -[2023-11-28 10:32:21,531][87426] Updated weights for policy 1, policy_version 393360 (0.0008) -[2023-11-28 10:32:21,908][87426] Updated weights for policy 1, policy_version 393370 (0.0010) -[2023-11-28 10:32:23,280][87424] Updated weights for policy 0, policy_version 393669 (0.0011) -[2023-11-28 10:32:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 201482240. Throughput: 0: 2638.3, 1: 2777.8. Samples: 201500488. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:23,445][86177] Avg episode reward: [(0, '-531.000'), (1, '-578.730')] -[2023-11-28 10:32:23,664][87424] Updated weights for policy 0, policy_version 393679 (0.0012) -[2023-11-28 10:32:24,036][87426] Updated weights for policy 1, policy_version 393380 (0.0011) -[2023-11-28 10:32:24,056][87424] Updated weights for policy 0, policy_version 393689 (0.0012) -[2023-11-28 10:32:24,416][87426] Updated weights for policy 1, policy_version 393390 (0.0011) -[2023-11-28 10:32:24,790][87426] Updated weights for policy 1, policy_version 393400 (0.0012) -[2023-11-28 10:32:26,015][87424] Updated weights for policy 0, policy_version 393699 (0.0010) -[2023-11-28 10:32:26,407][87424] Updated weights for policy 0, policy_version 393709 (0.0010) -[2023-11-28 10:32:26,793][87424] Updated weights for policy 0, policy_version 393719 (0.0008) -[2023-11-28 10:32:26,992][87426] Updated weights for policy 1, policy_version 393410 (0.0009) -[2023-11-28 10:32:27,360][87426] Updated weights for policy 1, policy_version 393420 (0.0012) -[2023-11-28 10:32:27,732][87426] Updated weights for policy 1, policy_version 393430 (0.0011) -[2023-11-28 10:32:28,111][87426] Updated weights for policy 1, policy_version 393440 (0.0012) -[2023-11-28 10:32:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 201515008. Throughput: 0: 2650.8, 1: 2783.5. Samples: 201525532. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:28,445][86177] Avg episode reward: [(0, '-530.400'), (1, '-576.460')] -[2023-11-28 10:32:28,667][87424] Updated weights for policy 0, policy_version 393729 (0.0008) -[2023-11-28 10:32:29,048][87424] Updated weights for policy 0, policy_version 393739 (0.0012) -[2023-11-28 10:32:29,430][87424] Updated weights for policy 0, policy_version 393749 (0.0012) -[2023-11-28 10:32:29,807][87424] Updated weights for policy 0, policy_version 393759 (0.0011) -[2023-11-28 10:32:29,947][87426] Updated weights for policy 1, policy_version 393450 (0.0012) -[2023-11-28 10:32:30,323][87426] Updated weights for policy 1, policy_version 393460 (0.0010) -[2023-11-28 10:32:30,704][87426] Updated weights for policy 1, policy_version 393470 (0.0010) -[2023-11-28 10:32:31,723][87424] Updated weights for policy 0, policy_version 393769 (0.0012) -[2023-11-28 10:32:32,108][87424] Updated weights for policy 0, policy_version 393779 (0.0012) -[2023-11-28 10:32:32,489][87424] Updated weights for policy 0, policy_version 393789 (0.0012) -[2023-11-28 10:32:33,191][87426] Updated weights for policy 1, policy_version 393480 (0.0008) -[2023-11-28 10:32:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201539584. Throughput: 0: 2673.1, 1: 2802.0. Samples: 201551248. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:33,445][86177] Avg episode reward: [(0, '-552.050'), (1, '-575.480')] -[2023-11-28 10:32:33,569][87426] Updated weights for policy 1, policy_version 393490 (0.0008) -[2023-11-28 10:32:33,948][87426] Updated weights for policy 1, policy_version 393500 (0.0007) -[2023-11-28 10:32:34,523][87424] Updated weights for policy 0, policy_version 393799 (0.0012) -[2023-11-28 10:32:34,913][87424] Updated weights for policy 0, policy_version 393809 (0.0012) -[2023-11-28 10:32:35,288][87424] Updated weights for policy 0, policy_version 393819 (0.0012) -[2023-11-28 10:32:36,243][87426] Updated weights for policy 1, policy_version 393510 (0.0010) -[2023-11-28 10:32:36,624][87426] Updated weights for policy 1, policy_version 393520 (0.0012) -[2023-11-28 10:32:37,000][87426] Updated weights for policy 1, policy_version 393530 (0.0011) -[2023-11-28 10:32:37,496][87424] Updated weights for policy 0, policy_version 393829 (0.0010) -[2023-11-28 10:32:37,879][87424] Updated weights for policy 0, policy_version 393839 (0.0008) -[2023-11-28 10:32:38,260][87424] Updated weights for policy 0, policy_version 393849 (0.0008) -[2023-11-28 10:32:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 201564160. Throughput: 0: 2698.2, 1: 2775.6. Samples: 201584468. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:38,445][86177] Avg episode reward: [(0, '-546.300'), (1, '-583.650')] -[2023-11-28 10:32:39,539][87426] Updated weights for policy 1, policy_version 393540 (0.0011) -[2023-11-28 10:32:39,914][87426] Updated weights for policy 1, policy_version 393550 (0.0010) -[2023-11-28 10:32:40,296][87426] Updated weights for policy 1, policy_version 393560 (0.0009) -[2023-11-28 10:32:40,591][87424] Updated weights for policy 0, policy_version 393859 (0.0009) -[2023-11-28 10:32:40,976][87424] Updated weights for policy 0, policy_version 393869 (0.0012) -[2023-11-28 10:32:41,359][87424] Updated weights for policy 0, policy_version 393879 (0.0011) -[2023-11-28 10:32:42,607][87426] Updated weights for policy 1, policy_version 393570 (0.0011) -[2023-11-28 10:32:42,984][87426] Updated weights for policy 1, policy_version 393580 (0.0011) -[2023-11-28 10:32:43,362][87426] Updated weights for policy 1, policy_version 393590 (0.0009) -[2023-11-28 10:32:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201588736. Throughput: 0: 2689.2, 1: 2742.3. Samples: 201607528. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:43,445][86177] Avg episode reward: [(0, '-546.980'), (1, '-602.700')] -[2023-11-28 10:32:43,744][87426] Updated weights for policy 1, policy_version 393600 (0.0008) -[2023-11-28 10:32:43,909][87424] Updated weights for policy 0, policy_version 393889 (0.0012) -[2023-11-28 10:32:44,290][87424] Updated weights for policy 0, policy_version 393899 (0.0010) -[2023-11-28 10:32:44,671][87424] Updated weights for policy 0, policy_version 393909 (0.0011) -[2023-11-28 10:32:45,068][87424] Updated weights for policy 0, policy_version 393919 (0.0009) -[2023-11-28 10:32:45,721][87426] Updated weights for policy 1, policy_version 393610 (0.0011) -[2023-11-28 10:32:46,099][87426] Updated weights for policy 1, policy_version 393620 (0.0009) -[2023-11-28 10:32:46,471][87426] Updated weights for policy 1, policy_version 393630 (0.0007) -[2023-11-28 10:32:47,518][87424] Updated weights for policy 0, policy_version 393929 (0.0010) -[2023-11-28 10:32:47,915][87424] Updated weights for policy 0, policy_version 393939 (0.0011) -[2023-11-28 10:32:48,295][87424] Updated weights for policy 0, policy_version 393949 (0.0012) -[2023-11-28 10:32:48,410][87426] Updated weights for policy 1, policy_version 393640 (0.0010) -[2023-11-28 10:32:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201621504. Throughput: 0: 2668.9, 1: 2736.4. Samples: 201631092. Policy #0 lag: (min: 22.0, avg: 29.6, max: 54.0) -[2023-11-28 10:32:48,445][86177] Avg episode reward: [(0, '-556.520'), (1, '-610.130')] -[2023-11-28 10:32:48,791][87426] Updated weights for policy 1, policy_version 393650 (0.0012) -[2023-11-28 10:32:49,165][87426] Updated weights for policy 1, policy_version 393660 (0.0012) -[2023-11-28 10:32:50,256][87424] Updated weights for policy 0, policy_version 393959 (0.0011) -[2023-11-28 10:32:50,632][87424] Updated weights for policy 0, policy_version 393969 (0.0012) -[2023-11-28 10:32:51,017][87424] Updated weights for policy 0, policy_version 393979 (0.0011) -[2023-11-28 10:32:51,498][87426] Updated weights for policy 1, policy_version 393670 (0.0012) -[2023-11-28 10:32:51,880][87426] Updated weights for policy 1, policy_version 393680 (0.0012) -[2023-11-28 10:32:52,254][87426] Updated weights for policy 1, policy_version 393690 (0.0012) -[2023-11-28 10:32:53,176][87424] Updated weights for policy 0, policy_version 393989 (0.0010) -[2023-11-28 10:32:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 201646080. Throughput: 0: 2681.3, 1: 2729.2. Samples: 201664372. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:32:53,445][86177] Avg episode reward: [(0, '-538.080'), (1, '-620.220')] -[2023-11-28 10:32:53,546][87424] Updated weights for policy 0, policy_version 393999 (0.0010) -[2023-11-28 10:32:53,931][87424] Updated weights for policy 0, policy_version 394009 (0.0009) -[2023-11-28 10:32:54,749][87426] Updated weights for policy 1, policy_version 393700 (0.0012) -[2023-11-28 10:32:55,134][87426] Updated weights for policy 1, policy_version 393710 (0.0011) -[2023-11-28 10:32:55,506][87426] Updated weights for policy 1, policy_version 393720 (0.0009) -[2023-11-28 10:32:56,078][87424] Updated weights for policy 0, policy_version 394019 (0.0009) -[2023-11-28 10:32:56,465][87424] Updated weights for policy 0, policy_version 394029 (0.0012) -[2023-11-28 10:32:56,837][87424] Updated weights for policy 0, policy_version 394039 (0.0012) -[2023-11-28 10:32:57,904][87426] Updated weights for policy 1, policy_version 393730 (0.0012) -[2023-11-28 10:32:58,279][87426] Updated weights for policy 1, policy_version 393740 (0.0012) -[2023-11-28 10:32:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201670656. Throughput: 0: 2696.6, 1: 2705.1. Samples: 201687964. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:32:58,445][86177] Avg episode reward: [(0, '-545.070'), (1, '-607.770')] -[2023-11-28 10:32:58,663][87426] Updated weights for policy 1, policy_version 393750 (0.0012) -[2023-11-28 10:32:58,836][87424] Updated weights for policy 0, policy_version 394049 (0.0011) -[2023-11-28 10:32:59,047][87426] Updated weights for policy 1, policy_version 393760 (0.0010) -[2023-11-28 10:32:59,215][87424] Updated weights for policy 0, policy_version 394059 (0.0012) -[2023-11-28 10:32:59,595][87424] Updated weights for policy 0, policy_version 394069 (0.0012) -[2023-11-28 10:32:59,973][87424] Updated weights for policy 0, policy_version 394079 (0.0015) -[2023-11-28 10:33:01,457][87426] Updated weights for policy 1, policy_version 393770 (0.0007) -[2023-11-28 10:33:01,839][87426] Updated weights for policy 1, policy_version 393780 (0.0009) -[2023-11-28 10:33:02,226][87426] Updated weights for policy 1, policy_version 393790 (0.0010) -[2023-11-28 10:33:02,434][87424] Updated weights for policy 0, policy_version 394089 (0.0010) -[2023-11-28 10:33:02,822][87424] Updated weights for policy 0, policy_version 394099 (0.0010) -[2023-11-28 10:33:03,199][87424] Updated weights for policy 0, policy_version 394109 (0.0011) -[2023-11-28 10:33:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201703424. Throughput: 0: 2724.4, 1: 2694.8. Samples: 201712868. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:03,445][86177] Avg episode reward: [(0, '-544.730'), (1, '-609.580')] -[2023-11-28 10:33:04,350][87426] Updated weights for policy 1, policy_version 393800 (0.0011) -[2023-11-28 10:33:04,737][87426] Updated weights for policy 1, policy_version 393810 (0.0012) -[2023-11-28 10:33:05,111][87426] Updated weights for policy 1, policy_version 393820 (0.0010) -[2023-11-28 10:33:05,169][87424] Updated weights for policy 0, policy_version 394119 (0.0009) -[2023-11-28 10:33:05,550][87424] Updated weights for policy 0, policy_version 394129 (0.0007) -[2023-11-28 10:33:05,931][87424] Updated weights for policy 0, policy_version 394139 (0.0007) -[2023-11-28 10:33:06,973][87426] Updated weights for policy 1, policy_version 393830 (0.0011) -[2023-11-28 10:33:07,350][87426] Updated weights for policy 1, policy_version 393840 (0.0012) -[2023-11-28 10:33:07,730][87426] Updated weights for policy 1, policy_version 393850 (0.0010) -[2023-11-28 10:33:08,234][87424] Updated weights for policy 0, policy_version 394149 (0.0009) -[2023-11-28 10:33:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 201728000. Throughput: 0: 2753.7, 1: 2675.3. Samples: 201744792. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:08,445][86177] Avg episode reward: [(0, '-549.690'), (1, '-608.270')] -[2023-11-28 10:33:08,610][87424] Updated weights for policy 0, policy_version 394159 (0.0012) -[2023-11-28 10:33:08,985][87424] Updated weights for policy 0, policy_version 394169 (0.0012) -[2023-11-28 10:33:09,509][87426] Updated weights for policy 1, policy_version 393860 (0.0009) -[2023-11-28 10:33:09,892][87426] Updated weights for policy 1, policy_version 393870 (0.0010) -[2023-11-28 10:33:10,270][87426] Updated weights for policy 1, policy_version 393880 (0.0012) -[2023-11-28 10:33:11,305][87424] Updated weights for policy 0, policy_version 394179 (0.0011) -[2023-11-28 10:33:11,685][87424] Updated weights for policy 0, policy_version 394189 (0.0011) -[2023-11-28 10:33:12,064][87424] Updated weights for policy 0, policy_version 394199 (0.0009) -[2023-11-28 10:33:12,426][87426] Updated weights for policy 1, policy_version 393890 (0.0010) -[2023-11-28 10:33:12,800][87426] Updated weights for policy 1, policy_version 393900 (0.0012) -[2023-11-28 10:33:13,180][87426] Updated weights for policy 1, policy_version 393910 (0.0011) -[2023-11-28 10:33:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 201752576. Throughput: 0: 2741.7, 1: 2662.9. Samples: 201768740. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:13,445][86177] Avg episode reward: [(0, '-539.750'), (1, '-579.040')] -[2023-11-28 10:33:13,560][87426] Updated weights for policy 1, policy_version 393920 (0.0011) -[2023-11-28 10:33:14,027][87424] Updated weights for policy 0, policy_version 394209 (0.0009) -[2023-11-28 10:33:14,419][87424] Updated weights for policy 0, policy_version 394219 (0.0009) -[2023-11-28 10:33:14,810][87424] Updated weights for policy 0, policy_version 394229 (0.0011) -[2023-11-28 10:33:15,182][87424] Updated weights for policy 0, policy_version 394239 (0.0011) -[2023-11-28 10:33:16,123][87426] Updated weights for policy 1, policy_version 393930 (0.0008) -[2023-11-28 10:33:16,503][87426] Updated weights for policy 1, policy_version 393940 (0.0008) -[2023-11-28 10:33:16,894][87426] Updated weights for policy 1, policy_version 393950 (0.0008) -[2023-11-28 10:33:17,468][87424] Updated weights for policy 0, policy_version 394249 (0.0007) -[2023-11-28 10:33:17,844][87424] Updated weights for policy 0, policy_version 394259 (0.0008) -[2023-11-28 10:33:18,224][87424] Updated weights for policy 0, policy_version 394269 (0.0007) -[2023-11-28 10:33:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201785344. Throughput: 0: 2725.9, 1: 2646.0. Samples: 201792980. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:18,445][86177] Avg episode reward: [(0, '-533.990'), (1, '-570.190')] -[2023-11-28 10:33:18,902][87426] Updated weights for policy 1, policy_version 393960 (0.0011) -[2023-11-28 10:33:19,287][87426] Updated weights for policy 1, policy_version 393970 (0.0012) -[2023-11-28 10:33:19,660][87426] Updated weights for policy 1, policy_version 393980 (0.0012) -[2023-11-28 10:33:20,152][87424] Updated weights for policy 0, policy_version 394279 (0.0010) -[2023-11-28 10:33:20,536][87424] Updated weights for policy 0, policy_version 394289 (0.0012) -[2023-11-28 10:33:20,924][87424] Updated weights for policy 0, policy_version 394299 (0.0012) -[2023-11-28 10:33:21,992][87426] Updated weights for policy 1, policy_version 393990 (0.0011) -[2023-11-28 10:33:22,367][87426] Updated weights for policy 1, policy_version 394000 (0.0010) -[2023-11-28 10:33:22,749][87426] Updated weights for policy 1, policy_version 394010 (0.0010) -[2023-11-28 10:33:23,298][87424] Updated weights for policy 0, policy_version 394309 (0.0010) -[2023-11-28 10:33:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201809920. Throughput: 0: 2692.5, 1: 2649.3. Samples: 201824852. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:23,445][86177] Avg episode reward: [(0, '-535.390'), (1, '-564.230')] -[2023-11-28 10:33:23,673][87424] Updated weights for policy 0, policy_version 394319 (0.0011) -[2023-11-28 10:33:24,051][87424] Updated weights for policy 0, policy_version 394329 (0.0009) -[2023-11-28 10:33:25,040][87426] Updated weights for policy 1, policy_version 394020 (0.0011) -[2023-11-28 10:33:25,439][87426] Updated weights for policy 1, policy_version 394030 (0.0012) -[2023-11-28 10:33:25,817][87426] Updated weights for policy 1, policy_version 394040 (0.0012) -[2023-11-28 10:33:26,574][87424] Updated weights for policy 0, policy_version 394339 (0.0008) -[2023-11-28 10:33:26,960][87424] Updated weights for policy 0, policy_version 394349 (0.0007) -[2023-11-28 10:33:27,351][87424] Updated weights for policy 0, policy_version 394359 (0.0008) -[2023-11-28 10:33:28,021][87426] Updated weights for policy 1, policy_version 394050 (0.0011) -[2023-11-28 10:33:28,409][87426] Updated weights for policy 1, policy_version 394060 (0.0011) -[2023-11-28 10:33:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 201834496. Throughput: 0: 2691.4, 1: 2698.5. Samples: 201850072. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:28,445][86177] Avg episode reward: [(0, '-536.350'), (1, '-547.590')] -[2023-11-28 10:33:28,783][87426] Updated weights for policy 1, policy_version 394070 (0.0011) -[2023-11-28 10:33:29,161][87426] Updated weights for policy 1, policy_version 394080 (0.0009) -[2023-11-28 10:33:29,444][87424] Updated weights for policy 0, policy_version 394369 (0.0012) -[2023-11-28 10:33:29,825][87424] Updated weights for policy 0, policy_version 394379 (0.0012) -[2023-11-28 10:33:30,216][87424] Updated weights for policy 0, policy_version 394389 (0.0012) -[2023-11-28 10:33:30,593][87424] Updated weights for policy 0, policy_version 394399 (0.0012) -[2023-11-28 10:33:31,306][87426] Updated weights for policy 1, policy_version 394090 (0.0007) -[2023-11-28 10:33:31,690][87426] Updated weights for policy 1, policy_version 394100 (0.0008) -[2023-11-28 10:33:32,062][87426] Updated weights for policy 1, policy_version 394110 (0.0011) -[2023-11-28 10:33:32,659][87424] Updated weights for policy 0, policy_version 394409 (0.0012) -[2023-11-28 10:33:33,039][87424] Updated weights for policy 0, policy_version 394419 (0.0012) -[2023-11-28 10:33:33,414][87424] Updated weights for policy 0, policy_version 394429 (0.0012) -[2023-11-28 10:33:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 201859072. Throughput: 0: 2721.6, 1: 2692.8. Samples: 201874740. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:33,445][86177] Avg episode reward: [(0, '-553.160'), (1, '-546.270')] -[2023-11-28 10:33:34,449][87426] Updated weights for policy 1, policy_version 394120 (0.0011) -[2023-11-28 10:33:34,827][87426] Updated weights for policy 1, policy_version 394130 (0.0020) -[2023-11-28 10:33:35,208][87426] Updated weights for policy 1, policy_version 394140 (0.0011) -[2023-11-28 10:33:35,368][87424] Updated weights for policy 0, policy_version 394439 (0.0010) -[2023-11-28 10:33:35,734][87424] Updated weights for policy 0, policy_version 394449 (0.0008) -[2023-11-28 10:33:36,112][87424] Updated weights for policy 0, policy_version 394459 (0.0009) -[2023-11-28 10:33:37,171][87426] Updated weights for policy 1, policy_version 394150 (0.0011) -[2023-11-28 10:33:37,547][87426] Updated weights for policy 1, policy_version 394160 (0.0012) -[2023-11-28 10:33:37,925][87426] Updated weights for policy 1, policy_version 394170 (0.0012) -[2023-11-28 10:33:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 201891840. Throughput: 0: 2720.5, 1: 2674.2. Samples: 201907136. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:38,445][86177] Avg episode reward: [(0, '-553.720'), (1, '-538.670')] -[2023-11-28 10:33:38,626][87424] Updated weights for policy 0, policy_version 394469 (0.0010) -[2023-11-28 10:33:39,002][87424] Updated weights for policy 0, policy_version 394479 (0.0011) -[2023-11-28 10:33:39,389][87424] Updated weights for policy 0, policy_version 394489 (0.0010) -[2023-11-28 10:33:40,500][87426] Updated weights for policy 1, policy_version 394180 (0.0012) -[2023-11-28 10:33:40,878][87426] Updated weights for policy 1, policy_version 394190 (0.0008) -[2023-11-28 10:33:41,265][87426] Updated weights for policy 1, policy_version 394200 (0.0011) -[2023-11-28 10:33:41,513][87424] Updated weights for policy 0, policy_version 394499 (0.0010) -[2023-11-28 10:33:41,892][87424] Updated weights for policy 0, policy_version 394509 (0.0011) -[2023-11-28 10:33:42,277][87424] Updated weights for policy 0, policy_version 394519 (0.0010) -[2023-11-28 10:33:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201916416. Throughput: 0: 2727.4, 1: 2674.3. Samples: 201931040. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:43,445][86177] Avg episode reward: [(0, '-589.900'), (1, '-535.180')] -[2023-11-28 10:33:43,743][87426] Updated weights for policy 1, policy_version 394210 (0.0011) -[2023-11-28 10:33:44,126][87426] Updated weights for policy 1, policy_version 394220 (0.0007) -[2023-11-28 10:33:44,439][87424] Updated weights for policy 0, policy_version 394529 (0.0011) -[2023-11-28 10:33:44,503][87426] Updated weights for policy 1, policy_version 394230 (0.0008) -[2023-11-28 10:33:44,814][87424] Updated weights for policy 0, policy_version 394539 (0.0012) -[2023-11-28 10:33:44,884][87426] Updated weights for policy 1, policy_version 394240 (0.0009) -[2023-11-28 10:33:45,201][87424] Updated weights for policy 0, policy_version 394549 (0.0012) -[2023-11-28 10:33:45,574][87424] Updated weights for policy 0, policy_version 394559 (0.0012) -[2023-11-28 10:33:47,072][87426] Updated weights for policy 1, policy_version 394250 (0.0012) -[2023-11-28 10:33:47,452][87426] Updated weights for policy 1, policy_version 394260 (0.0012) -[2023-11-28 10:33:47,818][87426] Updated weights for policy 1, policy_version 394270 (0.0009) -[2023-11-28 10:33:47,887][87424] Updated weights for policy 0, policy_version 394569 (0.0011) -[2023-11-28 10:33:48,257][87424] Updated weights for policy 0, policy_version 394579 (0.0012) -[2023-11-28 10:33:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 201940992. Throughput: 0: 2706.6, 1: 2678.1. Samples: 201955180. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:48,445][86177] Avg episode reward: [(0, '-577.710'), (1, '-548.940')] -[2023-11-28 10:33:48,634][87424] Updated weights for policy 0, policy_version 394589 (0.0012) -[2023-11-28 10:33:49,894][87426] Updated weights for policy 1, policy_version 394280 (0.0011) -[2023-11-28 10:33:50,270][87426] Updated weights for policy 1, policy_version 394290 (0.0009) -[2023-11-28 10:33:50,574][87424] Updated weights for policy 0, policy_version 394599 (0.0011) -[2023-11-28 10:33:50,648][87426] Updated weights for policy 1, policy_version 394300 (0.0010) -[2023-11-28 10:33:50,959][87424] Updated weights for policy 0, policy_version 394609 (0.0011) -[2023-11-28 10:33:51,337][87424] Updated weights for policy 0, policy_version 394619 (0.0011) -[2023-11-28 10:33:52,712][87426] Updated weights for policy 1, policy_version 394310 (0.0011) -[2023-11-28 10:33:53,092][87426] Updated weights for policy 1, policy_version 394320 (0.0009) -[2023-11-28 10:33:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 201965568. Throughput: 0: 2702.4, 1: 2694.8. Samples: 201987664. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:53,445][86177] Avg episode reward: [(0, '-597.870'), (1, '-548.690')] -[2023-11-28 10:33:53,477][87426] Updated weights for policy 1, policy_version 394330 (0.0010) -[2023-11-28 10:33:53,838][87424] Updated weights for policy 0, policy_version 394629 (0.0012) -[2023-11-28 10:33:54,216][87424] Updated weights for policy 0, policy_version 394639 (0.0012) -[2023-11-28 10:33:54,606][87424] Updated weights for policy 0, policy_version 394649 (0.0012) -[2023-11-28 10:33:55,928][87426] Updated weights for policy 1, policy_version 394340 (0.0011) -[2023-11-28 10:33:56,312][87426] Updated weights for policy 1, policy_version 394350 (0.0011) -[2023-11-28 10:33:56,535][87424] Updated weights for policy 0, policy_version 394659 (0.0010) -[2023-11-28 10:33:56,694][87426] Updated weights for policy 1, policy_version 394360 (0.0009) -[2023-11-28 10:33:56,915][87424] Updated weights for policy 0, policy_version 394669 (0.0007) -[2023-11-28 10:33:57,293][87424] Updated weights for policy 0, policy_version 394679 (0.0008) -[2023-11-28 10:33:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 201998336. Throughput: 0: 2703.0, 1: 2704.8. Samples: 202012092. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:33:58,445][86177] Avg episode reward: [(0, '-586.960'), (1, '-549.160')] -[2023-11-28 10:33:58,683][87426] Updated weights for policy 1, policy_version 394370 (0.0007) -[2023-11-28 10:33:59,069][87426] Updated weights for policy 1, policy_version 394380 (0.0008) -[2023-11-28 10:33:59,149][87424] Updated weights for policy 0, policy_version 394689 (0.0008) -[2023-11-28 10:33:59,448][87426] Updated weights for policy 1, policy_version 394390 (0.0010) -[2023-11-28 10:33:59,532][87424] Updated weights for policy 0, policy_version 394699 (0.0009) -[2023-11-28 10:33:59,824][87426] Updated weights for policy 1, policy_version 394400 (0.0008) -[2023-11-28 10:33:59,907][87424] Updated weights for policy 0, policy_version 394709 (0.0008) -[2023-11-28 10:34:00,289][87424] Updated weights for policy 0, policy_version 394719 (0.0008) -[2023-11-28 10:34:01,643][87426] Updated weights for policy 1, policy_version 394410 (0.0008) -[2023-11-28 10:34:02,019][87426] Updated weights for policy 1, policy_version 394420 (0.0009) -[2023-11-28 10:34:02,406][87426] Updated weights for policy 1, policy_version 394430 (0.0010) -[2023-11-28 10:34:02,437][87424] Updated weights for policy 0, policy_version 394729 (0.0011) -[2023-11-28 10:34:02,816][87424] Updated weights for policy 0, policy_version 394739 (0.0012) -[2023-11-28 10:34:03,207][87424] Updated weights for policy 0, policy_version 394749 (0.0012) -[2023-11-28 10:34:03,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 202031104. Throughput: 0: 2714.8, 1: 2720.9. Samples: 202037584. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:34:03,445][86177] Avg episode reward: [(0, '-546.880'), (1, '-585.850')] -[2023-11-28 10:34:04,771][87426] Updated weights for policy 1, policy_version 394440 (0.0010) -[2023-11-28 10:34:05,151][87426] Updated weights for policy 1, policy_version 394450 (0.0010) -[2023-11-28 10:34:05,538][87426] Updated weights for policy 1, policy_version 394460 (0.0011) -[2023-11-28 10:34:05,766][87424] Updated weights for policy 0, policy_version 394759 (0.0008) -[2023-11-28 10:34:06,165][87424] Updated weights for policy 0, policy_version 394769 (0.0007) -[2023-11-28 10:34:06,539][87424] Updated weights for policy 0, policy_version 394779 (0.0007) -[2023-11-28 10:34:07,912][87426] Updated weights for policy 1, policy_version 394470 (0.0010) -[2023-11-28 10:34:08,294][87426] Updated weights for policy 1, policy_version 394480 (0.0010) -[2023-11-28 10:34:08,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 202047488. Throughput: 0: 2714.1, 1: 2697.9. Samples: 202068392. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:34:08,445][86177] Avg episode reward: [(0, '-558.300'), (1, '-565.200')] -[2023-11-28 10:34:08,469][87424] Updated weights for policy 0, policy_version 394789 (0.0009) -[2023-11-28 10:34:08,678][87426] Updated weights for policy 1, policy_version 394490 (0.0012) -[2023-11-28 10:34:08,845][87424] Updated weights for policy 0, policy_version 394799 (0.0011) -[2023-11-28 10:34:09,237][87424] Updated weights for policy 0, policy_version 394809 (0.0012) -[2023-11-28 10:34:10,699][87426] Updated weights for policy 1, policy_version 394500 (0.0012) -[2023-11-28 10:34:11,066][87426] Updated weights for policy 1, policy_version 394510 (0.0012) -[2023-11-28 10:34:11,448][87426] Updated weights for policy 1, policy_version 394520 (0.0012) -[2023-11-28 10:34:11,812][87424] Updated weights for policy 0, policy_version 394819 (0.0011) -[2023-11-28 10:34:12,200][87424] Updated weights for policy 0, policy_version 394829 (0.0010) -[2023-11-28 10:34:12,579][87424] Updated weights for policy 0, policy_version 394839 (0.0010) -[2023-11-28 10:34:13,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 202080256. Throughput: 0: 2725.7, 1: 2647.6. Samples: 202091868. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:13,445][86177] Avg episode reward: [(0, '-528.980'), (1, '-563.410')] -[2023-11-28 10:34:13,938][87426] Updated weights for policy 1, policy_version 394530 (0.0011) -[2023-11-28 10:34:14,321][87426] Updated weights for policy 1, policy_version 394540 (0.0007) -[2023-11-28 10:34:14,487][87424] Updated weights for policy 0, policy_version 394849 (0.0010) -[2023-11-28 10:34:14,701][87426] Updated weights for policy 1, policy_version 394550 (0.0009) -[2023-11-28 10:34:14,869][87424] Updated weights for policy 0, policy_version 394859 (0.0008) -[2023-11-28 10:34:15,077][87426] Updated weights for policy 1, policy_version 394560 (0.0012) -[2023-11-28 10:34:15,253][87424] Updated weights for policy 0, policy_version 394869 (0.0011) -[2023-11-28 10:34:15,636][87424] Updated weights for policy 0, policy_version 394879 (0.0012) -[2023-11-28 10:34:17,311][87426] Updated weights for policy 1, policy_version 394570 (0.0012) -[2023-11-28 10:34:17,692][87426] Updated weights for policy 1, policy_version 394580 (0.0012) -[2023-11-28 10:34:17,769][87424] Updated weights for policy 0, policy_version 394889 (0.0012) -[2023-11-28 10:34:18,070][87426] Updated weights for policy 1, policy_version 394590 (0.0011) -[2023-11-28 10:34:18,152][87424] Updated weights for policy 0, policy_version 394899 (0.0011) -[2023-11-28 10:34:18,445][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 202104832. Throughput: 0: 2717.7, 1: 2648.2. Samples: 202116204. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:18,446][86177] Avg episode reward: [(0, '-535.260'), (1, '-562.970')] -[2023-11-28 10:34:18,456][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000394592_101015552.pth... -[2023-11-28 10:34:18,506][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000392064_100368384.pth -[2023-11-28 10:34:18,536][87424] Updated weights for policy 0, policy_version 394909 (0.0009) -[2023-11-28 10:34:18,647][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000394912_101097472.pth... -[2023-11-28 10:34:18,677][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000392384_100450304.pth -[2023-11-28 10:34:20,448][87426] Updated weights for policy 1, policy_version 394600 (0.0008) -[2023-11-28 10:34:20,733][87424] Updated weights for policy 0, policy_version 394919 (0.0010) -[2023-11-28 10:34:20,823][87426] Updated weights for policy 1, policy_version 394610 (0.0011) -[2023-11-28 10:34:21,110][87424] Updated weights for policy 0, policy_version 394929 (0.0009) -[2023-11-28 10:34:21,205][87426] Updated weights for policy 1, policy_version 394620 (0.0011) -[2023-11-28 10:34:21,498][87424] Updated weights for policy 0, policy_version 394939 (0.0012) -[2023-11-28 10:34:23,293][87426] Updated weights for policy 1, policy_version 394630 (0.0012) -[2023-11-28 10:34:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 202129408. Throughput: 0: 2705.1, 1: 2653.2. Samples: 202148260. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:23,445][86177] Avg episode reward: [(0, '-548.250'), (1, '-525.690')] -[2023-11-28 10:34:23,671][87426] Updated weights for policy 1, policy_version 394640 (0.0012) -[2023-11-28 10:34:24,052][87426] Updated weights for policy 1, policy_version 394650 (0.0011) -[2023-11-28 10:34:24,130][87424] Updated weights for policy 0, policy_version 394949 (0.0009) -[2023-11-28 10:34:24,515][87424] Updated weights for policy 0, policy_version 394959 (0.0011) -[2023-11-28 10:34:24,902][87424] Updated weights for policy 0, policy_version 394969 (0.0012) -[2023-11-28 10:34:25,968][87426] Updated weights for policy 1, policy_version 394660 (0.0012) -[2023-11-28 10:34:26,349][87426] Updated weights for policy 1, policy_version 394670 (0.0012) -[2023-11-28 10:34:26,685][87424] Updated weights for policy 0, policy_version 394979 (0.0010) -[2023-11-28 10:34:26,722][87426] Updated weights for policy 1, policy_version 394680 (0.0008) -[2023-11-28 10:34:27,061][87424] Updated weights for policy 0, policy_version 394989 (0.0007) -[2023-11-28 10:34:27,441][87424] Updated weights for policy 0, policy_version 394999 (0.0007) -[2023-11-28 10:34:28,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 202162176. Throughput: 0: 2696.6, 1: 2694.1. Samples: 202173624. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:28,445][86177] Avg episode reward: [(0, '-549.540'), (1, '-535.670')] -[2023-11-28 10:34:28,661][87426] Updated weights for policy 1, policy_version 394690 (0.0007) -[2023-11-28 10:34:29,030][87426] Updated weights for policy 1, policy_version 394700 (0.0009) -[2023-11-28 10:34:29,406][87426] Updated weights for policy 1, policy_version 394710 (0.0009) -[2023-11-28 10:34:29,456][87424] Updated weights for policy 0, policy_version 395009 (0.0008) -[2023-11-28 10:34:29,791][87426] Updated weights for policy 1, policy_version 394720 (0.0008) -[2023-11-28 10:34:29,837][87424] Updated weights for policy 0, policy_version 395019 (0.0010) -[2023-11-28 10:34:30,221][87424] Updated weights for policy 0, policy_version 395029 (0.0010) -[2023-11-28 10:34:30,603][87424] Updated weights for policy 0, policy_version 395039 (0.0010) -[2023-11-28 10:34:32,104][87426] Updated weights for policy 1, policy_version 394730 (0.0012) -[2023-11-28 10:34:32,476][87426] Updated weights for policy 1, policy_version 394740 (0.0011) -[2023-11-28 10:34:32,771][87424] Updated weights for policy 0, policy_version 395049 (0.0011) -[2023-11-28 10:34:32,856][87426] Updated weights for policy 1, policy_version 394750 (0.0010) -[2023-11-28 10:34:33,154][87424] Updated weights for policy 0, policy_version 395059 (0.0009) -[2023-11-28 10:34:33,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 202186752. Throughput: 0: 2719.9, 1: 2694.1. Samples: 202198812. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:33,445][86177] Avg episode reward: [(0, '-534.650'), (1, '-528.690')] -[2023-11-28 10:34:33,540][87424] Updated weights for policy 0, policy_version 395069 (0.0008) -[2023-11-28 10:34:34,632][87426] Updated weights for policy 1, policy_version 394760 (0.0009) -[2023-11-28 10:34:35,016][87426] Updated weights for policy 1, policy_version 394770 (0.0010) -[2023-11-28 10:34:35,396][87426] Updated weights for policy 1, policy_version 394780 (0.0010) -[2023-11-28 10:34:36,091][87424] Updated weights for policy 0, policy_version 395079 (0.0010) -[2023-11-28 10:34:36,483][87424] Updated weights for policy 0, policy_version 395089 (0.0012) -[2023-11-28 10:34:36,871][87424] Updated weights for policy 0, policy_version 395099 (0.0011) -[2023-11-28 10:34:37,801][87426] Updated weights for policy 1, policy_version 394790 (0.0012) -[2023-11-28 10:34:38,177][87426] Updated weights for policy 1, policy_version 394800 (0.0010) -[2023-11-28 10:34:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 202211328. Throughput: 0: 2704.2, 1: 2710.9. Samples: 202231344. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:38,445][86177] Avg episode reward: [(0, '-574.360'), (1, '-526.710')] -[2023-11-28 10:34:38,562][87426] Updated weights for policy 1, policy_version 394810 (0.0011) -[2023-11-28 10:34:38,895][87424] Updated weights for policy 0, policy_version 395109 (0.0012) -[2023-11-28 10:34:39,283][87424] Updated weights for policy 0, policy_version 395119 (0.0011) -[2023-11-28 10:34:39,664][87424] Updated weights for policy 0, policy_version 395129 (0.0012) -[2023-11-28 10:34:41,113][87426] Updated weights for policy 1, policy_version 394820 (0.0009) -[2023-11-28 10:34:41,498][87426] Updated weights for policy 1, policy_version 394830 (0.0008) -[2023-11-28 10:34:41,880][87426] Updated weights for policy 1, policy_version 394840 (0.0010) -[2023-11-28 10:34:41,962][87424] Updated weights for policy 0, policy_version 395139 (0.0011) -[2023-11-28 10:34:42,340][87424] Updated weights for policy 0, policy_version 395149 (0.0009) -[2023-11-28 10:34:42,728][87424] Updated weights for policy 0, policy_version 395159 (0.0010) -[2023-11-28 10:34:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 202244096. Throughput: 0: 2703.3, 1: 2689.4. Samples: 202254764. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:43,445][86177] Avg episode reward: [(0, '-573.250'), (1, '-524.560')] -[2023-11-28 10:34:44,326][87426] Updated weights for policy 1, policy_version 394850 (0.0009) -[2023-11-28 10:34:44,704][87426] Updated weights for policy 1, policy_version 394860 (0.0011) -[2023-11-28 10:34:44,911][87424] Updated weights for policy 0, policy_version 395169 (0.0011) -[2023-11-28 10:34:45,086][87426] Updated weights for policy 1, policy_version 394870 (0.0011) -[2023-11-28 10:34:45,296][87424] Updated weights for policy 0, policy_version 395179 (0.0011) -[2023-11-28 10:34:45,458][87426] Updated weights for policy 1, policy_version 394880 (0.0012) -[2023-11-28 10:34:45,672][87424] Updated weights for policy 0, policy_version 395189 (0.0010) -[2023-11-28 10:34:46,052][87424] Updated weights for policy 0, policy_version 395199 (0.0009) -[2023-11-28 10:34:47,390][87426] Updated weights for policy 1, policy_version 394890 (0.0012) -[2023-11-28 10:34:47,761][87426] Updated weights for policy 1, policy_version 394900 (0.0008) -[2023-11-28 10:34:48,141][87426] Updated weights for policy 1, policy_version 394910 (0.0010) -[2023-11-28 10:34:48,178][87424] Updated weights for policy 0, policy_version 395209 (0.0008) -[2023-11-28 10:34:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 202268672. Throughput: 0: 2698.5, 1: 2681.4. Samples: 202279680. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:48,445][86177] Avg episode reward: [(0, '-572.940'), (1, '-527.450')] -[2023-11-28 10:34:48,561][87424] Updated weights for policy 0, policy_version 395219 (0.0007) -[2023-11-28 10:34:48,952][87424] Updated weights for policy 0, policy_version 395229 (0.0009) -[2023-11-28 10:34:50,610][87426] Updated weights for policy 1, policy_version 394920 (0.0011) -[2023-11-28 10:34:50,976][87426] Updated weights for policy 1, policy_version 394930 (0.0010) -[2023-11-28 10:34:51,150][87424] Updated weights for policy 0, policy_version 395239 (0.0009) -[2023-11-28 10:34:51,356][87426] Updated weights for policy 1, policy_version 394940 (0.0010) -[2023-11-28 10:34:51,537][87424] Updated weights for policy 0, policy_version 395249 (0.0009) -[2023-11-28 10:34:51,918][87424] Updated weights for policy 0, policy_version 395259 (0.0012) -[2023-11-28 10:34:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 202293248. Throughput: 0: 2720.1, 1: 2676.1. Samples: 202311220. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:53,445][86177] Avg episode reward: [(0, '-571.390'), (1, '-565.440')] -[2023-11-28 10:34:53,732][87426] Updated weights for policy 1, policy_version 394950 (0.0011) -[2023-11-28 10:34:54,103][87426] Updated weights for policy 1, policy_version 394960 (0.0012) -[2023-11-28 10:34:54,315][87424] Updated weights for policy 0, policy_version 395269 (0.0011) -[2023-11-28 10:34:54,488][87426] Updated weights for policy 1, policy_version 394970 (0.0009) -[2023-11-28 10:34:54,689][87424] Updated weights for policy 0, policy_version 395279 (0.0011) -[2023-11-28 10:34:55,073][87424] Updated weights for policy 0, policy_version 395289 (0.0012) -[2023-11-28 10:34:56,898][87424] Updated weights for policy 0, policy_version 395299 (0.0012) -[2023-11-28 10:34:57,052][87426] Updated weights for policy 1, policy_version 394980 (0.0009) -[2023-11-28 10:34:57,282][87424] Updated weights for policy 0, policy_version 395309 (0.0011) -[2023-11-28 10:34:57,430][87426] Updated weights for policy 1, policy_version 394990 (0.0011) -[2023-11-28 10:34:57,669][87424] Updated weights for policy 0, policy_version 395319 (0.0012) -[2023-11-28 10:34:57,806][87426] Updated weights for policy 1, policy_version 395000 (0.0009) -[2023-11-28 10:34:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5442.8). Total num frames: 202326016. Throughput: 0: 2721.8, 1: 2673.1. Samples: 202334636. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:34:58,445][86177] Avg episode reward: [(0, '-531.420'), (1, '-567.740')] -[2023-11-28 10:34:59,370][87424] Updated weights for policy 0, policy_version 395329 (0.0012) -[2023-11-28 10:34:59,755][87424] Updated weights for policy 0, policy_version 395339 (0.0012) -[2023-11-28 10:35:00,061][87426] Updated weights for policy 1, policy_version 395010 (0.0010) -[2023-11-28 10:35:00,138][87424] Updated weights for policy 0, policy_version 395349 (0.0010) -[2023-11-28 10:35:00,441][87426] Updated weights for policy 1, policy_version 395020 (0.0009) -[2023-11-28 10:35:00,518][87424] Updated weights for policy 0, policy_version 395359 (0.0010) -[2023-11-28 10:35:00,824][87426] Updated weights for policy 1, policy_version 395030 (0.0008) -[2023-11-28 10:35:01,205][87426] Updated weights for policy 1, policy_version 395040 (0.0008) -[2023-11-28 10:35:02,729][87424] Updated weights for policy 0, policy_version 395369 (0.0011) -[2023-11-28 10:35:03,107][87424] Updated weights for policy 0, policy_version 395379 (0.0011) -[2023-11-28 10:35:03,330][87426] Updated weights for policy 1, policy_version 395050 (0.0010) -[2023-11-28 10:35:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 202342400. Throughput: 0: 2736.8, 1: 2682.5. Samples: 202360072. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:35:03,445][86177] Avg episode reward: [(0, '-543.390'), (1, '-567.410')] -[2023-11-28 10:35:03,489][87424] Updated weights for policy 0, policy_version 395389 (0.0010) -[2023-11-28 10:35:03,707][87426] Updated weights for policy 1, policy_version 395060 (0.0011) -[2023-11-28 10:35:04,096][87426] Updated weights for policy 1, policy_version 395070 (0.0011) -[2023-11-28 10:35:05,591][87424] Updated weights for policy 0, policy_version 395399 (0.0010) -[2023-11-28 10:35:05,971][87424] Updated weights for policy 0, policy_version 395409 (0.0012) -[2023-11-28 10:35:06,359][87424] Updated weights for policy 0, policy_version 395419 (0.0011) -[2023-11-28 10:35:06,683][87426] Updated weights for policy 1, policy_version 395080 (0.0012) -[2023-11-28 10:35:07,060][87426] Updated weights for policy 1, policy_version 395090 (0.0012) -[2023-11-28 10:35:07,435][87426] Updated weights for policy 1, policy_version 395100 (0.0012) -[2023-11-28 10:35:08,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 202375168. Throughput: 0: 2738.5, 1: 2686.0. Samples: 202392364. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:35:08,445][86177] Avg episode reward: [(0, '-524.780'), (1, '-565.620')] -[2023-11-28 10:35:08,643][87424] Updated weights for policy 0, policy_version 395429 (0.0011) -[2023-11-28 10:35:09,025][87424] Updated weights for policy 0, policy_version 395439 (0.0012) -[2023-11-28 10:35:09,408][87424] Updated weights for policy 0, policy_version 395449 (0.0012) -[2023-11-28 10:35:09,705][87426] Updated weights for policy 1, policy_version 395110 (0.0010) -[2023-11-28 10:35:10,080][87426] Updated weights for policy 1, policy_version 395120 (0.0012) -[2023-11-28 10:35:10,463][87426] Updated weights for policy 1, policy_version 395130 (0.0012) -[2023-11-28 10:35:11,538][87424] Updated weights for policy 0, policy_version 395459 (0.0012) -[2023-11-28 10:35:11,918][87424] Updated weights for policy 0, policy_version 395469 (0.0012) -[2023-11-28 10:35:12,301][87424] Updated weights for policy 0, policy_version 395479 (0.0012) -[2023-11-28 10:35:13,020][87426] Updated weights for policy 1, policy_version 395140 (0.0012) -[2023-11-28 10:35:13,390][87426] Updated weights for policy 1, policy_version 395150 (0.0009) -[2023-11-28 10:35:13,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 202399744. Throughput: 0: 2733.3, 1: 2650.8. Samples: 202415912. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:35:13,445][86177] Avg episode reward: [(0, '-584.600'), (1, '-528.690')] -[2023-11-28 10:35:13,769][87426] Updated weights for policy 1, policy_version 395160 (0.0008) -[2023-11-28 10:35:14,457][87424] Updated weights for policy 0, policy_version 395489 (0.0008) -[2023-11-28 10:35:14,830][87424] Updated weights for policy 0, policy_version 395499 (0.0010) -[2023-11-28 10:35:15,218][87424] Updated weights for policy 0, policy_version 395509 (0.0007) -[2023-11-28 10:35:15,616][87424] Updated weights for policy 0, policy_version 395519 (0.0010) -[2023-11-28 10:35:16,322][87426] Updated weights for policy 1, policy_version 395170 (0.0008) -[2023-11-28 10:35:16,705][87426] Updated weights for policy 1, policy_version 395180 (0.0009) -[2023-11-28 10:35:17,093][87426] Updated weights for policy 1, policy_version 395190 (0.0007) -[2023-11-28 10:35:17,460][87426] Updated weights for policy 1, policy_version 395200 (0.0007) -[2023-11-28 10:35:18,064][87424] Updated weights for policy 0, policy_version 395529 (0.0012) -[2023-11-28 10:35:18,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 202424320. Throughput: 0: 2728.7, 1: 2625.2. Samples: 202439736. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:35:18,445][86177] Avg episode reward: [(0, '-578.440'), (1, '-527.990')] -[2023-11-28 10:35:18,445][87424] Updated weights for policy 0, policy_version 395539 (0.0012) -[2023-11-28 10:35:18,824][87424] Updated weights for policy 0, policy_version 395549 (0.0012) -[2023-11-28 10:35:19,627][87426] Updated weights for policy 1, policy_version 395210 (0.0012) -[2023-11-28 10:35:20,004][87426] Updated weights for policy 1, policy_version 395220 (0.0012) -[2023-11-28 10:35:20,381][87426] Updated weights for policy 1, policy_version 395230 (0.0012) -[2023-11-28 10:35:21,226][87424] Updated weights for policy 0, policy_version 395559 (0.0011) -[2023-11-28 10:35:21,604][87424] Updated weights for policy 0, policy_version 395569 (0.0012) -[2023-11-28 10:35:21,978][87424] Updated weights for policy 0, policy_version 395579 (0.0010) -[2023-11-28 10:35:22,820][87426] Updated weights for policy 1, policy_version 395240 (0.0012) -[2023-11-28 10:35:23,191][87426] Updated weights for policy 1, policy_version 395250 (0.0008) -[2023-11-28 10:35:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 202448896. Throughput: 0: 2728.0, 1: 2595.9. Samples: 202470920. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:35:23,445][86177] Avg episode reward: [(0, '-572.030'), (1, '-531.830')] -[2023-11-28 10:35:23,565][87426] Updated weights for policy 1, policy_version 395260 (0.0007) -[2023-11-28 10:35:24,277][87424] Updated weights for policy 0, policy_version 395589 (0.0011) -[2023-11-28 10:35:24,670][87424] Updated weights for policy 0, policy_version 395599 (0.0011) -[2023-11-28 10:35:25,047][87424] Updated weights for policy 0, policy_version 395609 (0.0011) -[2023-11-28 10:35:25,435][87426] Updated weights for policy 1, policy_version 395270 (0.0008) -[2023-11-28 10:35:25,817][87426] Updated weights for policy 1, policy_version 395280 (0.0007) -[2023-11-28 10:35:26,192][87426] Updated weights for policy 1, policy_version 395290 (0.0007) -[2023-11-28 10:35:27,111][87424] Updated weights for policy 0, policy_version 395619 (0.0012) -[2023-11-28 10:35:27,491][87424] Updated weights for policy 0, policy_version 395629 (0.0009) -[2023-11-28 10:35:27,873][87424] Updated weights for policy 0, policy_version 395639 (0.0008) -[2023-11-28 10:35:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 202481664. Throughput: 0: 2734.0, 1: 2604.4. Samples: 202494996. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:35:28,446][86177] Avg episode reward: [(0, '-583.000'), (1, '-526.270')] -[2023-11-28 10:35:28,679][87426] Updated weights for policy 1, policy_version 395300 (0.0007) -[2023-11-28 10:35:29,056][87426] Updated weights for policy 1, policy_version 395310 (0.0009) -[2023-11-28 10:35:29,429][87426] Updated weights for policy 1, policy_version 395320 (0.0008) -[2023-11-28 10:35:30,080][87424] Updated weights for policy 0, policy_version 395649 (0.0010) -[2023-11-28 10:35:30,462][87424] Updated weights for policy 0, policy_version 395659 (0.0012) -[2023-11-28 10:35:30,848][87424] Updated weights for policy 0, policy_version 395669 (0.0012) -[2023-11-28 10:35:31,225][87424] Updated weights for policy 0, policy_version 395679 (0.0011) -[2023-11-28 10:35:31,687][87426] Updated weights for policy 1, policy_version 395330 (0.0009) -[2023-11-28 10:35:32,062][87426] Updated weights for policy 1, policy_version 395340 (0.0012) -[2023-11-28 10:35:32,435][87426] Updated weights for policy 1, policy_version 395350 (0.0012) -[2023-11-28 10:35:32,810][87426] Updated weights for policy 1, policy_version 395360 (0.0009) -[2023-11-28 10:35:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 202506240. Throughput: 0: 2730.0, 1: 2601.3. Samples: 202519592. Policy #0 lag: (min: 22.0, avg: 31.0, max: 54.0) -[2023-11-28 10:35:33,445][86177] Avg episode reward: [(0, '-526.960'), (1, '-522.520')] -[2023-11-28 10:35:33,566][87424] Updated weights for policy 0, policy_version 395689 (0.0011) -[2023-11-28 10:35:33,949][87424] Updated weights for policy 0, policy_version 395699 (0.0012) -[2023-11-28 10:35:34,325][87424] Updated weights for policy 0, policy_version 395709 (0.0011) -[2023-11-28 10:35:34,849][87426] Updated weights for policy 1, policy_version 395370 (0.0011) -[2023-11-28 10:35:35,227][87426] Updated weights for policy 1, policy_version 395380 (0.0009) -[2023-11-28 10:35:35,610][87426] Updated weights for policy 1, policy_version 395390 (0.0011) -[2023-11-28 10:35:36,221][87424] Updated weights for policy 0, policy_version 395719 (0.0009) -[2023-11-28 10:35:36,604][87424] Updated weights for policy 0, policy_version 395729 (0.0009) -[2023-11-28 10:35:37,003][87424] Updated weights for policy 0, policy_version 395739 (0.0010) -[2023-11-28 10:35:37,332][87426] Updated weights for policy 1, policy_version 395400 (0.0011) -[2023-11-28 10:35:37,714][87426] Updated weights for policy 1, policy_version 395410 (0.0012) -[2023-11-28 10:35:38,093][87426] Updated weights for policy 1, policy_version 395420 (0.0012) -[2023-11-28 10:35:38,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 202539008. Throughput: 0: 2732.8, 1: 2658.8. Samples: 202553840. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:35:38,445][86177] Avg episode reward: [(0, '-525.730'), (1, '-523.470')] -[2023-11-28 10:35:38,876][87424] Updated weights for policy 0, policy_version 395749 (0.0011) -[2023-11-28 10:35:39,256][87424] Updated weights for policy 0, policy_version 395759 (0.0010) -[2023-11-28 10:35:39,642][87424] Updated weights for policy 0, policy_version 395769 (0.0007) -[2023-11-28 10:35:40,597][87426] Updated weights for policy 1, policy_version 395430 (0.0011) -[2023-11-28 10:35:40,985][87426] Updated weights for policy 1, policy_version 395440 (0.0010) -[2023-11-28 10:35:41,374][87426] Updated weights for policy 1, policy_version 395450 (0.0008) -[2023-11-28 10:35:41,483][87424] Updated weights for policy 0, policy_version 395779 (0.0009) -[2023-11-28 10:35:41,862][87424] Updated weights for policy 0, policy_version 395789 (0.0012) -[2023-11-28 10:35:42,246][87424] Updated weights for policy 0, policy_version 395799 (0.0011) -[2023-11-28 10:35:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 202563584. Throughput: 0: 2730.6, 1: 2656.0. Samples: 202577032. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:35:43,445][86177] Avg episode reward: [(0, '-518.380'), (1, '-518.710')] -[2023-11-28 10:35:43,828][87426] Updated weights for policy 1, policy_version 395460 (0.0010) -[2023-11-28 10:35:44,210][87426] Updated weights for policy 1, policy_version 395470 (0.0012) -[2023-11-28 10:35:44,394][87424] Updated weights for policy 0, policy_version 395809 (0.0010) -[2023-11-28 10:35:44,590][87426] Updated weights for policy 1, policy_version 395480 (0.0011) -[2023-11-28 10:35:44,776][87424] Updated weights for policy 0, policy_version 395819 (0.0009) -[2023-11-28 10:35:45,162][87424] Updated weights for policy 0, policy_version 395829 (0.0012) -[2023-11-28 10:35:45,538][87424] Updated weights for policy 0, policy_version 395839 (0.0012) -[2023-11-28 10:35:46,612][87426] Updated weights for policy 1, policy_version 395490 (0.0009) -[2023-11-28 10:35:46,991][87426] Updated weights for policy 1, policy_version 395500 (0.0007) -[2023-11-28 10:35:47,368][87426] Updated weights for policy 1, policy_version 395510 (0.0007) -[2023-11-28 10:35:47,588][87424] Updated weights for policy 0, policy_version 395849 (0.0009) -[2023-11-28 10:35:47,746][87426] Updated weights for policy 1, policy_version 395520 (0.0009) -[2023-11-28 10:35:47,974][87424] Updated weights for policy 0, policy_version 395859 (0.0008) -[2023-11-28 10:35:48,360][87424] Updated weights for policy 0, policy_version 395869 (0.0008) -[2023-11-28 10:35:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5415.0). Total num frames: 202588160. Throughput: 0: 2715.0, 1: 2641.3. Samples: 202601108. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:35:48,446][86177] Avg episode reward: [(0, '-509.940'), (1, '-518.660')] -[2023-11-28 10:35:50,267][87426] Updated weights for policy 1, policy_version 395530 (0.0011) -[2023-11-28 10:35:50,645][87426] Updated weights for policy 1, policy_version 395540 (0.0010) -[2023-11-28 10:35:50,885][87424] Updated weights for policy 0, policy_version 395879 (0.0010) -[2023-11-28 10:35:51,025][87426] Updated weights for policy 1, policy_version 395550 (0.0007) -[2023-11-28 10:35:51,260][87424] Updated weights for policy 0, policy_version 395889 (0.0012) -[2023-11-28 10:35:51,644][87424] Updated weights for policy 0, policy_version 395899 (0.0012) -[2023-11-28 10:35:53,350][87426] Updated weights for policy 1, policy_version 395560 (0.0011) -[2023-11-28 10:35:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 202612736. Throughput: 0: 2702.1, 1: 2638.9. Samples: 202632708. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:35:53,445][86177] Avg episode reward: [(0, '-510.110'), (1, '-514.700')] -[2023-11-28 10:35:53,724][87426] Updated weights for policy 1, policy_version 395570 (0.0011) -[2023-11-28 10:35:54,104][87426] Updated weights for policy 1, policy_version 395580 (0.0012) -[2023-11-28 10:35:54,105][87424] Updated weights for policy 0, policy_version 395909 (0.0010) -[2023-11-28 10:35:54,480][87424] Updated weights for policy 0, policy_version 395919 (0.0009) -[2023-11-28 10:35:54,863][87424] Updated weights for policy 0, policy_version 395929 (0.0008) -[2023-11-28 10:35:56,302][87426] Updated weights for policy 1, policy_version 395590 (0.0012) -[2023-11-28 10:35:56,577][87424] Updated weights for policy 0, policy_version 395939 (0.0008) -[2023-11-28 10:35:56,685][87426] Updated weights for policy 1, policy_version 395600 (0.0012) -[2023-11-28 10:35:56,963][87424] Updated weights for policy 0, policy_version 395949 (0.0008) -[2023-11-28 10:35:57,066][87426] Updated weights for policy 1, policy_version 395610 (0.0012) -[2023-11-28 10:35:57,339][87424] Updated weights for policy 0, policy_version 395959 (0.0008) -[2023-11-28 10:35:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 202645504. Throughput: 0: 2695.5, 1: 2658.8. Samples: 202656852. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:35:58,445][86177] Avg episode reward: [(0, '-514.820'), (1, '-528.220')] -[2023-11-28 10:35:58,989][87426] Updated weights for policy 1, policy_version 395620 (0.0012) -[2023-11-28 10:35:59,299][87424] Updated weights for policy 0, policy_version 395969 (0.0012) -[2023-11-28 10:35:59,363][87426] Updated weights for policy 1, policy_version 395630 (0.0012) -[2023-11-28 10:35:59,677][87424] Updated weights for policy 0, policy_version 395979 (0.0012) -[2023-11-28 10:35:59,742][87426] Updated weights for policy 1, policy_version 395640 (0.0012) -[2023-11-28 10:36:00,057][87424] Updated weights for policy 0, policy_version 395989 (0.0011) -[2023-11-28 10:36:00,443][87424] Updated weights for policy 0, policy_version 395999 (0.0012) -[2023-11-28 10:36:01,908][87426] Updated weights for policy 1, policy_version 395650 (0.0011) -[2023-11-28 10:36:02,286][87426] Updated weights for policy 1, policy_version 395660 (0.0010) -[2023-11-28 10:36:02,667][87426] Updated weights for policy 1, policy_version 395670 (0.0007) -[2023-11-28 10:36:02,807][87424] Updated weights for policy 0, policy_version 396009 (0.0012) -[2023-11-28 10:36:03,049][87426] Updated weights for policy 1, policy_version 395680 (0.0008) -[2023-11-28 10:36:03,186][87424] Updated weights for policy 0, policy_version 396019 (0.0011) -[2023-11-28 10:36:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 202670080. Throughput: 0: 2699.3, 1: 2676.5. Samples: 202681644. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:03,445][86177] Avg episode reward: [(0, '-518.690'), (1, '-532.230')] -[2023-11-28 10:36:03,564][87424] Updated weights for policy 0, policy_version 396029 (0.0011) -[2023-11-28 10:36:05,619][87426] Updated weights for policy 1, policy_version 395690 (0.0012) -[2023-11-28 10:36:05,987][87426] Updated weights for policy 1, policy_version 395700 (0.0011) -[2023-11-28 10:36:06,171][87424] Updated weights for policy 0, policy_version 396039 (0.0008) -[2023-11-28 10:36:06,368][87426] Updated weights for policy 1, policy_version 395710 (0.0012) -[2023-11-28 10:36:06,553][87424] Updated weights for policy 0, policy_version 396049 (0.0008) -[2023-11-28 10:36:06,935][87424] Updated weights for policy 0, policy_version 396059 (0.0009) -[2023-11-28 10:36:08,416][87426] Updated weights for policy 1, policy_version 395720 (0.0010) -[2023-11-28 10:36:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 202694656. Throughput: 0: 2715.5, 1: 2671.9. Samples: 202713352. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:08,445][86177] Avg episode reward: [(0, '-520.960'), (1, '-535.420')] -[2023-11-28 10:36:08,792][87426] Updated weights for policy 1, policy_version 395730 (0.0008) -[2023-11-28 10:36:09,171][87426] Updated weights for policy 1, policy_version 395740 (0.0008) -[2023-11-28 10:36:09,540][87424] Updated weights for policy 0, policy_version 396069 (0.0011) -[2023-11-28 10:36:09,921][87424] Updated weights for policy 0, policy_version 396079 (0.0012) -[2023-11-28 10:36:10,308][87424] Updated weights for policy 0, policy_version 396089 (0.0012) -[2023-11-28 10:36:11,120][87426] Updated weights for policy 1, policy_version 395750 (0.0010) -[2023-11-28 10:36:11,499][87426] Updated weights for policy 1, policy_version 395760 (0.0012) -[2023-11-28 10:36:11,880][87426] Updated weights for policy 1, policy_version 395770 (0.0012) -[2023-11-28 10:36:12,427][87424] Updated weights for policy 0, policy_version 396099 (0.0011) -[2023-11-28 10:36:12,809][87424] Updated weights for policy 0, policy_version 396109 (0.0010) -[2023-11-28 10:36:13,192][87424] Updated weights for policy 0, policy_version 396119 (0.0012) -[2023-11-28 10:36:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 202719232. Throughput: 0: 2706.7, 1: 2676.7. Samples: 202737248. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:13,445][86177] Avg episode reward: [(0, '-515.970'), (1, '-562.790')] -[2023-11-28 10:36:14,182][87426] Updated weights for policy 1, policy_version 395780 (0.0012) -[2023-11-28 10:36:14,565][87426] Updated weights for policy 1, policy_version 395790 (0.0012) -[2023-11-28 10:36:14,948][87426] Updated weights for policy 1, policy_version 395800 (0.0012) -[2023-11-28 10:36:15,055][87424] Updated weights for policy 0, policy_version 396129 (0.0012) -[2023-11-28 10:36:15,434][87424] Updated weights for policy 0, policy_version 396139 (0.0011) -[2023-11-28 10:36:15,819][87424] Updated weights for policy 0, policy_version 396149 (0.0012) -[2023-11-28 10:36:16,196][87424] Updated weights for policy 0, policy_version 396159 (0.0012) -[2023-11-28 10:36:17,033][87426] Updated weights for policy 1, policy_version 395810 (0.0012) -[2023-11-28 10:36:17,408][87426] Updated weights for policy 1, policy_version 395820 (0.0012) -[2023-11-28 10:36:17,782][87426] Updated weights for policy 1, policy_version 395830 (0.0012) -[2023-11-28 10:36:18,155][87426] Updated weights for policy 1, policy_version 395840 (0.0010) -[2023-11-28 10:36:18,309][87424] Updated weights for policy 0, policy_version 396169 (0.0012) -[2023-11-28 10:36:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 202752000. Throughput: 0: 2712.1, 1: 2684.1. Samples: 202762420. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:18,445][86177] Avg episode reward: [(0, '-521.670'), (1, '-549.920')] -[2023-11-28 10:36:18,452][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000395840_101335040.pth... -[2023-11-28 10:36:18,491][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000393344_100696064.pth -[2023-11-28 10:36:18,694][87424] Updated weights for policy 0, policy_version 396179 (0.0012) -[2023-11-28 10:36:19,078][87424] Updated weights for policy 0, policy_version 396189 (0.0012) -[2023-11-28 10:36:19,188][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000396192_101425152.pth... -[2023-11-28 10:36:19,228][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000393632_100769792.pth -[2023-11-28 10:36:20,164][87426] Updated weights for policy 1, policy_version 395850 (0.0009) -[2023-11-28 10:36:20,552][87426] Updated weights for policy 1, policy_version 395860 (0.0011) -[2023-11-28 10:36:20,925][87426] Updated weights for policy 1, policy_version 395870 (0.0010) -[2023-11-28 10:36:20,927][87424] Updated weights for policy 0, policy_version 396199 (0.0012) -[2023-11-28 10:36:21,311][87424] Updated weights for policy 0, policy_version 396209 (0.0012) -[2023-11-28 10:36:21,688][87424] Updated weights for policy 0, policy_version 396219 (0.0012) -[2023-11-28 10:36:23,002][87426] Updated weights for policy 1, policy_version 395880 (0.0011) -[2023-11-28 10:36:23,385][87426] Updated weights for policy 1, policy_version 395890 (0.0012) -[2023-11-28 10:36:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 202776576. Throughput: 0: 2701.2, 1: 2653.1. Samples: 202794780. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:23,445][86177] Avg episode reward: [(0, '-520.530'), (1, '-550.290')] -[2023-11-28 10:36:23,760][87426] Updated weights for policy 1, policy_version 395900 (0.0012) -[2023-11-28 10:36:24,298][87424] Updated weights for policy 0, policy_version 396229 (0.0009) -[2023-11-28 10:36:24,670][87424] Updated weights for policy 0, policy_version 396239 (0.0008) -[2023-11-28 10:36:25,059][87424] Updated weights for policy 0, policy_version 396249 (0.0008) -[2023-11-28 10:36:26,151][87426] Updated weights for policy 1, policy_version 395910 (0.0012) -[2023-11-28 10:36:26,528][87426] Updated weights for policy 1, policy_version 395920 (0.0012) -[2023-11-28 10:36:26,904][87426] Updated weights for policy 1, policy_version 395930 (0.0010) -[2023-11-28 10:36:27,097][87424] Updated weights for policy 0, policy_version 396259 (0.0007) -[2023-11-28 10:36:27,473][87424] Updated weights for policy 0, policy_version 396269 (0.0007) -[2023-11-28 10:36:27,855][87424] Updated weights for policy 0, policy_version 396279 (0.0008) -[2023-11-28 10:36:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 202809344. Throughput: 0: 2699.9, 1: 2697.5. Samples: 202819916. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:28,446][86177] Avg episode reward: [(0, '-530.380'), (1, '-552.770')] -[2023-11-28 10:36:28,914][87426] Updated weights for policy 1, policy_version 395940 (0.0007) -[2023-11-28 10:36:29,297][87426] Updated weights for policy 1, policy_version 395950 (0.0008) -[2023-11-28 10:36:29,684][87426] Updated weights for policy 1, policy_version 395960 (0.0008) -[2023-11-28 10:36:30,302][87424] Updated weights for policy 0, policy_version 396289 (0.0010) -[2023-11-28 10:36:30,689][87424] Updated weights for policy 0, policy_version 396299 (0.0012) -[2023-11-28 10:36:31,068][87424] Updated weights for policy 0, policy_version 396309 (0.0011) -[2023-11-28 10:36:31,450][87424] Updated weights for policy 0, policy_version 396319 (0.0009) -[2023-11-28 10:36:31,689][87426] Updated weights for policy 1, policy_version 395970 (0.0010) -[2023-11-28 10:36:32,059][87426] Updated weights for policy 1, policy_version 395980 (0.0008) -[2023-11-28 10:36:32,438][87426] Updated weights for policy 1, policy_version 395990 (0.0010) -[2023-11-28 10:36:32,814][87426] Updated weights for policy 1, policy_version 396000 (0.0011) -[2023-11-28 10:36:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 202833920. Throughput: 0: 2695.1, 1: 2714.0. Samples: 202844516. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:33,445][86177] Avg episode reward: [(0, '-534.900'), (1, '-529.740')] -[2023-11-28 10:36:33,724][87424] Updated weights for policy 0, policy_version 396329 (0.0008) -[2023-11-28 10:36:34,100][87424] Updated weights for policy 0, policy_version 396339 (0.0012) -[2023-11-28 10:36:34,486][87424] Updated weights for policy 0, policy_version 396349 (0.0011) -[2023-11-28 10:36:34,644][87426] Updated weights for policy 1, policy_version 396010 (0.0009) -[2023-11-28 10:36:35,036][87426] Updated weights for policy 1, policy_version 396020 (0.0011) -[2023-11-28 10:36:35,413][87426] Updated weights for policy 1, policy_version 396030 (0.0011) -[2023-11-28 10:36:36,330][87424] Updated weights for policy 0, policy_version 396359 (0.0010) -[2023-11-28 10:36:36,710][87424] Updated weights for policy 0, policy_version 396369 (0.0009) -[2023-11-28 10:36:37,103][87424] Updated weights for policy 0, policy_version 396379 (0.0012) -[2023-11-28 10:36:37,681][87426] Updated weights for policy 1, policy_version 396040 (0.0011) -[2023-11-28 10:36:38,062][87426] Updated weights for policy 1, policy_version 396050 (0.0012) -[2023-11-28 10:36:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5415.1). Total num frames: 202858496. Throughput: 0: 2700.7, 1: 2746.5. Samples: 202877832. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:38,445][86177] Avg episode reward: [(0, '-539.200'), (1, '-525.620')] -[2023-11-28 10:36:38,454][87426] Updated weights for policy 1, policy_version 396060 (0.0011) -[2023-11-28 10:36:39,256][87424] Updated weights for policy 0, policy_version 396389 (0.0010) -[2023-11-28 10:36:39,636][87424] Updated weights for policy 0, policy_version 396399 (0.0008) -[2023-11-28 10:36:40,021][87424] Updated weights for policy 0, policy_version 396409 (0.0010) -[2023-11-28 10:36:40,485][87426] Updated weights for policy 1, policy_version 396070 (0.0011) -[2023-11-28 10:36:40,865][87426] Updated weights for policy 1, policy_version 396080 (0.0012) -[2023-11-28 10:36:41,252][87426] Updated weights for policy 1, policy_version 396090 (0.0012) -[2023-11-28 10:36:42,264][87424] Updated weights for policy 0, policy_version 396419 (0.0011) -[2023-11-28 10:36:42,640][87424] Updated weights for policy 0, policy_version 396429 (0.0009) -[2023-11-28 10:36:43,027][87424] Updated weights for policy 0, policy_version 396439 (0.0011) -[2023-11-28 10:36:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 202891264. Throughput: 0: 2716.1, 1: 2722.9. Samples: 202901608. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:43,445][86177] Avg episode reward: [(0, '-552.260'), (1, '-524.760')] -[2023-11-28 10:36:43,717][87426] Updated weights for policy 1, policy_version 396100 (0.0012) -[2023-11-28 10:36:44,097][87426] Updated weights for policy 1, policy_version 396110 (0.0011) -[2023-11-28 10:36:44,482][87426] Updated weights for policy 1, policy_version 396120 (0.0012) -[2023-11-28 10:36:45,176][87424] Updated weights for policy 0, policy_version 396449 (0.0011) -[2023-11-28 10:36:45,556][87424] Updated weights for policy 0, policy_version 396459 (0.0010) -[2023-11-28 10:36:45,937][87424] Updated weights for policy 0, policy_version 396469 (0.0011) -[2023-11-28 10:36:46,319][87424] Updated weights for policy 0, policy_version 396479 (0.0012) -[2023-11-28 10:36:46,785][87426] Updated weights for policy 1, policy_version 396130 (0.0010) -[2023-11-28 10:36:47,167][87426] Updated weights for policy 1, policy_version 396140 (0.0010) -[2023-11-28 10:36:47,559][87426] Updated weights for policy 1, policy_version 396150 (0.0008) -[2023-11-28 10:36:47,943][87426] Updated weights for policy 1, policy_version 396160 (0.0008) -[2023-11-28 10:36:48,221][87424] Updated weights for policy 0, policy_version 396489 (0.0012) -[2023-11-28 10:36:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 202915840. Throughput: 0: 2711.4, 1: 2730.3. Samples: 202926520. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:48,445][86177] Avg episode reward: [(0, '-576.450'), (1, '-525.020')] -[2023-11-28 10:36:48,597][87424] Updated weights for policy 0, policy_version 396499 (0.0012) -[2023-11-28 10:36:48,990][87424] Updated weights for policy 0, policy_version 396509 (0.0009) -[2023-11-28 10:36:49,902][87426] Updated weights for policy 1, policy_version 396170 (0.0012) -[2023-11-28 10:36:50,306][87426] Updated weights for policy 1, policy_version 396180 (0.0012) -[2023-11-28 10:36:50,678][87426] Updated weights for policy 1, policy_version 396190 (0.0012) -[2023-11-28 10:36:51,183][87424] Updated weights for policy 0, policy_version 396519 (0.0011) -[2023-11-28 10:36:51,571][87424] Updated weights for policy 0, policy_version 396529 (0.0011) -[2023-11-28 10:36:51,954][87424] Updated weights for policy 0, policy_version 396539 (0.0012) -[2023-11-28 10:36:53,077][87426] Updated weights for policy 1, policy_version 396200 (0.0012) -[2023-11-28 10:36:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.0). Total num frames: 202940416. Throughput: 0: 2719.9, 1: 2740.2. Samples: 202959056. Policy #0 lag: (min: 5.0, avg: 26.6, max: 37.0) -[2023-11-28 10:36:53,445][86177] Avg episode reward: [(0, '-577.130'), (1, '-526.600')] -[2023-11-28 10:36:53,445][87426] Updated weights for policy 1, policy_version 396210 (0.0011) -[2023-11-28 10:36:53,835][87426] Updated weights for policy 1, policy_version 396220 (0.0012) -[2023-11-28 10:36:54,255][87424] Updated weights for policy 0, policy_version 396549 (0.0012) -[2023-11-28 10:36:54,633][87424] Updated weights for policy 0, policy_version 396559 (0.0012) -[2023-11-28 10:36:55,017][87424] Updated weights for policy 0, policy_version 396569 (0.0012) -[2023-11-28 10:36:55,654][87426] Updated weights for policy 1, policy_version 396230 (0.0011) -[2023-11-28 10:36:56,029][87426] Updated weights for policy 1, policy_version 396240 (0.0012) -[2023-11-28 10:36:56,405][87426] Updated weights for policy 1, policy_version 396250 (0.0012) -[2023-11-28 10:36:57,199][87424] Updated weights for policy 0, policy_version 396579 (0.0008) -[2023-11-28 10:36:57,583][87424] Updated weights for policy 0, policy_version 396589 (0.0007) -[2023-11-28 10:36:57,968][87424] Updated weights for policy 0, policy_version 396599 (0.0007) -[2023-11-28 10:36:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 202973184. Throughput: 0: 2721.2, 1: 2753.5. Samples: 202983608. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:36:58,445][86177] Avg episode reward: [(0, '-565.450'), (1, '-525.060')] -[2023-11-28 10:36:58,665][87426] Updated weights for policy 1, policy_version 396260 (0.0012) -[2023-11-28 10:36:59,044][87426] Updated weights for policy 1, policy_version 396270 (0.0011) -[2023-11-28 10:36:59,421][87426] Updated weights for policy 1, policy_version 396280 (0.0012) -[2023-11-28 10:36:59,866][87424] Updated weights for policy 0, policy_version 396609 (0.0007) -[2023-11-28 10:37:00,250][87424] Updated weights for policy 0, policy_version 396619 (0.0008) -[2023-11-28 10:37:00,631][87424] Updated weights for policy 0, policy_version 396629 (0.0012) -[2023-11-28 10:37:01,014][87424] Updated weights for policy 0, policy_version 396639 (0.0012) -[2023-11-28 10:37:01,769][87426] Updated weights for policy 1, policy_version 396290 (0.0012) -[2023-11-28 10:37:02,142][87426] Updated weights for policy 1, policy_version 396300 (0.0012) -[2023-11-28 10:37:02,520][87426] Updated weights for policy 1, policy_version 396310 (0.0012) -[2023-11-28 10:37:02,902][87426] Updated weights for policy 1, policy_version 396320 (0.0011) -[2023-11-28 10:37:03,180][87424] Updated weights for policy 0, policy_version 396649 (0.0012) -[2023-11-28 10:37:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 202997760. Throughput: 0: 2724.7, 1: 2743.6. Samples: 203008492. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:03,445][86177] Avg episode reward: [(0, '-563.740'), (1, '-527.420')] -[2023-11-28 10:37:03,564][87424] Updated weights for policy 0, policy_version 396659 (0.0010) -[2023-11-28 10:37:03,935][87424] Updated weights for policy 0, policy_version 396669 (0.0011) -[2023-11-28 10:37:05,062][87426] Updated weights for policy 1, policy_version 396330 (0.0012) -[2023-11-28 10:37:05,437][87426] Updated weights for policy 1, policy_version 396340 (0.0012) -[2023-11-28 10:37:05,806][87426] Updated weights for policy 1, policy_version 396350 (0.0012) -[2023-11-28 10:37:06,351][87424] Updated weights for policy 0, policy_version 396679 (0.0012) -[2023-11-28 10:37:06,732][87424] Updated weights for policy 0, policy_version 396689 (0.0011) -[2023-11-28 10:37:07,112][87424] Updated weights for policy 0, policy_version 396699 (0.0011) -[2023-11-28 10:37:07,708][87426] Updated weights for policy 1, policy_version 396360 (0.0012) -[2023-11-28 10:37:08,085][87426] Updated weights for policy 1, policy_version 396370 (0.0012) -[2023-11-28 10:37:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203022336. Throughput: 0: 2709.4, 1: 2748.9. Samples: 203040404. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:08,445][86177] Avg episode reward: [(0, '-541.390'), (1, '-516.480')] -[2023-11-28 10:37:08,468][87426] Updated weights for policy 1, policy_version 396380 (0.0012) -[2023-11-28 10:37:09,301][87424] Updated weights for policy 0, policy_version 396709 (0.0012) -[2023-11-28 10:37:09,681][87424] Updated weights for policy 0, policy_version 396719 (0.0012) -[2023-11-28 10:37:10,073][87424] Updated weights for policy 0, policy_version 396729 (0.0012) -[2023-11-28 10:37:11,097][87426] Updated weights for policy 1, policy_version 396390 (0.0012) -[2023-11-28 10:37:11,469][87426] Updated weights for policy 1, policy_version 396400 (0.0011) -[2023-11-28 10:37:11,854][87426] Updated weights for policy 1, policy_version 396410 (0.0010) -[2023-11-28 10:37:12,712][87424] Updated weights for policy 0, policy_version 396739 (0.0012) -[2023-11-28 10:37:13,091][87424] Updated weights for policy 0, policy_version 396749 (0.0010) -[2023-11-28 10:37:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203046912. Throughput: 0: 2717.3, 1: 2730.8. Samples: 203065076. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:13,445][86177] Avg episode reward: [(0, '-532.860'), (1, '-508.720')] -[2023-11-28 10:37:13,473][87424] Updated weights for policy 0, policy_version 396759 (0.0010) -[2023-11-28 10:37:13,849][87426] Updated weights for policy 1, policy_version 396420 (0.0009) -[2023-11-28 10:37:14,234][87426] Updated weights for policy 1, policy_version 396430 (0.0010) -[2023-11-28 10:37:14,604][87426] Updated weights for policy 1, policy_version 396440 (0.0011) -[2023-11-28 10:37:15,320][87424] Updated weights for policy 0, policy_version 396769 (0.0010) -[2023-11-28 10:37:15,706][87424] Updated weights for policy 0, policy_version 396779 (0.0012) -[2023-11-28 10:37:16,086][87424] Updated weights for policy 0, policy_version 396789 (0.0012) -[2023-11-28 10:37:16,471][87424] Updated weights for policy 0, policy_version 396799 (0.0012) -[2023-11-28 10:37:17,148][87426] Updated weights for policy 1, policy_version 396450 (0.0012) -[2023-11-28 10:37:17,522][87426] Updated weights for policy 1, policy_version 396460 (0.0012) -[2023-11-28 10:37:17,895][87426] Updated weights for policy 1, policy_version 396470 (0.0012) -[2023-11-28 10:37:18,268][87426] Updated weights for policy 1, policy_version 396480 (0.0012) -[2023-11-28 10:37:18,338][87424] Updated weights for policy 0, policy_version 396809 (0.0012) -[2023-11-28 10:37:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 203079680. Throughput: 0: 2712.1, 1: 2712.6. Samples: 203088628. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:18,445][86177] Avg episode reward: [(0, '-542.470'), (1, '-508.280')] -[2023-11-28 10:37:18,727][87424] Updated weights for policy 0, policy_version 396819 (0.0012) -[2023-11-28 10:37:19,103][87424] Updated weights for policy 0, policy_version 396829 (0.0012) -[2023-11-28 10:37:20,711][87426] Updated weights for policy 1, policy_version 396490 (0.0012) -[2023-11-28 10:37:20,975][87424] Updated weights for policy 0, policy_version 396839 (0.0010) -[2023-11-28 10:37:21,096][87426] Updated weights for policy 1, policy_version 396500 (0.0011) -[2023-11-28 10:37:21,359][87424] Updated weights for policy 0, policy_version 396849 (0.0012) -[2023-11-28 10:37:21,485][87426] Updated weights for policy 1, policy_version 396510 (0.0010) -[2023-11-28 10:37:21,738][87424] Updated weights for policy 0, policy_version 396859 (0.0012) -[2023-11-28 10:37:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203104256. Throughput: 0: 2721.2, 1: 2672.5. Samples: 203120552. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:23,445][86177] Avg episode reward: [(0, '-543.840'), (1, '-522.160')] -[2023-11-28 10:37:23,645][87426] Updated weights for policy 1, policy_version 396520 (0.0008) -[2023-11-28 10:37:24,026][87426] Updated weights for policy 1, policy_version 396530 (0.0008) -[2023-11-28 10:37:24,294][87424] Updated weights for policy 0, policy_version 396869 (0.0012) -[2023-11-28 10:37:24,407][87426] Updated weights for policy 1, policy_version 396540 (0.0009) -[2023-11-28 10:37:24,683][87424] Updated weights for policy 0, policy_version 396879 (0.0009) -[2023-11-28 10:37:25,066][87424] Updated weights for policy 0, policy_version 396889 (0.0008) -[2023-11-28 10:37:26,715][87426] Updated weights for policy 1, policy_version 396550 (0.0007) -[2023-11-28 10:37:27,096][87426] Updated weights for policy 1, policy_version 396560 (0.0008) -[2023-11-28 10:37:27,485][87426] Updated weights for policy 1, policy_version 396570 (0.0008) -[2023-11-28 10:37:27,529][87424] Updated weights for policy 0, policy_version 396899 (0.0010) -[2023-11-28 10:37:27,907][87424] Updated weights for policy 0, policy_version 396909 (0.0012) -[2023-11-28 10:37:28,291][87424] Updated weights for policy 0, policy_version 396919 (0.0012) -[2023-11-28 10:37:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203128832. Throughput: 0: 2707.9, 1: 2714.9. Samples: 203145636. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:28,445][86177] Avg episode reward: [(0, '-557.270'), (1, '-523.430')] -[2023-11-28 10:37:29,462][87426] Updated weights for policy 1, policy_version 396580 (0.0009) -[2023-11-28 10:37:29,844][87426] Updated weights for policy 1, policy_version 396590 (0.0012) -[2023-11-28 10:37:30,218][87426] Updated weights for policy 1, policy_version 396600 (0.0012) -[2023-11-28 10:37:30,677][87424] Updated weights for policy 0, policy_version 396929 (0.0012) -[2023-11-28 10:37:31,066][87424] Updated weights for policy 0, policy_version 396939 (0.0008) -[2023-11-28 10:37:31,443][87424] Updated weights for policy 0, policy_version 396949 (0.0008) -[2023-11-28 10:37:31,832][87424] Updated weights for policy 0, policy_version 396959 (0.0009) -[2023-11-28 10:37:32,426][87426] Updated weights for policy 1, policy_version 396610 (0.0009) -[2023-11-28 10:37:32,811][87426] Updated weights for policy 1, policy_version 396620 (0.0011) -[2023-11-28 10:37:33,196][87426] Updated weights for policy 1, policy_version 396630 (0.0010) -[2023-11-28 10:37:33,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203153408. Throughput: 0: 2683.6, 1: 2712.4. Samples: 203169336. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:33,445][86177] Avg episode reward: [(0, '-563.330'), (1, '-522.550')] -[2023-11-28 10:37:33,573][87426] Updated weights for policy 1, policy_version 396640 (0.0008) -[2023-11-28 10:37:33,836][87424] Updated weights for policy 0, policy_version 396969 (0.0011) -[2023-11-28 10:37:34,228][87424] Updated weights for policy 0, policy_version 396979 (0.0011) -[2023-11-28 10:37:34,610][87424] Updated weights for policy 0, policy_version 396989 (0.0008) -[2023-11-28 10:37:35,636][87426] Updated weights for policy 1, policy_version 396650 (0.0007) -[2023-11-28 10:37:36,011][87426] Updated weights for policy 1, policy_version 396660 (0.0009) -[2023-11-28 10:37:36,388][87426] Updated weights for policy 1, policy_version 396670 (0.0010) -[2023-11-28 10:37:37,174][87424] Updated weights for policy 0, policy_version 396999 (0.0010) -[2023-11-28 10:37:37,557][87424] Updated weights for policy 0, policy_version 397009 (0.0008) -[2023-11-28 10:37:37,941][87424] Updated weights for policy 0, policy_version 397019 (0.0007) -[2023-11-28 10:37:38,287][87426] Updated weights for policy 1, policy_version 396680 (0.0008) -[2023-11-28 10:37:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 203186176. Throughput: 0: 2664.3, 1: 2724.2. Samples: 203201536. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:38,445][86177] Avg episode reward: [(0, '-558.860'), (1, '-550.960')] -[2023-11-28 10:37:38,665][87426] Updated weights for policy 1, policy_version 396690 (0.0008) -[2023-11-28 10:37:39,048][87426] Updated weights for policy 1, policy_version 396700 (0.0009) -[2023-11-28 10:37:40,466][87424] Updated weights for policy 0, policy_version 397029 (0.0010) -[2023-11-28 10:37:40,846][87424] Updated weights for policy 0, policy_version 397039 (0.0012) -[2023-11-28 10:37:41,144][87426] Updated weights for policy 1, policy_version 396710 (0.0009) -[2023-11-28 10:37:41,225][87424] Updated weights for policy 0, policy_version 397049 (0.0009) -[2023-11-28 10:37:41,517][87426] Updated weights for policy 1, policy_version 396720 (0.0009) -[2023-11-28 10:37:41,894][87426] Updated weights for policy 1, policy_version 396730 (0.0011) -[2023-11-28 10:37:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203210752. Throughput: 0: 2659.6, 1: 2711.8. Samples: 203225320. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:43,445][86177] Avg episode reward: [(0, '-549.120'), (1, '-534.430')] -[2023-11-28 10:37:43,784][87424] Updated weights for policy 0, policy_version 397059 (0.0009) -[2023-11-28 10:37:44,174][87424] Updated weights for policy 0, policy_version 397069 (0.0008) -[2023-11-28 10:37:44,416][87426] Updated weights for policy 1, policy_version 396740 (0.0008) -[2023-11-28 10:37:44,561][87424] Updated weights for policy 0, policy_version 397079 (0.0007) -[2023-11-28 10:37:44,801][87426] Updated weights for policy 1, policy_version 396750 (0.0007) -[2023-11-28 10:37:45,171][87426] Updated weights for policy 1, policy_version 396760 (0.0007) -[2023-11-28 10:37:46,950][87426] Updated weights for policy 1, policy_version 396770 (0.0009) -[2023-11-28 10:37:47,110][87424] Updated weights for policy 0, policy_version 397089 (0.0008) -[2023-11-28 10:37:47,324][87426] Updated weights for policy 1, policy_version 396780 (0.0012) -[2023-11-28 10:37:47,482][87424] Updated weights for policy 0, policy_version 397099 (0.0011) -[2023-11-28 10:37:47,692][87426] Updated weights for policy 1, policy_version 396790 (0.0011) -[2023-11-28 10:37:47,864][87424] Updated weights for policy 0, policy_version 397109 (0.0010) -[2023-11-28 10:37:48,075][87426] Updated weights for policy 1, policy_version 396800 (0.0011) -[2023-11-28 10:37:48,251][87424] Updated weights for policy 0, policy_version 397119 (0.0010) -[2023-11-28 10:37:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 203243520. Throughput: 0: 2623.4, 1: 2719.5. Samples: 203248920. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:48,445][86177] Avg episode reward: [(0, '-558.300'), (1, '-537.320')] -[2023-11-28 10:37:50,170][87424] Updated weights for policy 0, policy_version 397129 (0.0009) -[2023-11-28 10:37:50,541][87424] Updated weights for policy 0, policy_version 397139 (0.0010) -[2023-11-28 10:37:50,760][87426] Updated weights for policy 1, policy_version 396810 (0.0010) -[2023-11-28 10:37:50,930][87424] Updated weights for policy 0, policy_version 397149 (0.0009) -[2023-11-28 10:37:51,134][87426] Updated weights for policy 1, policy_version 396820 (0.0011) -[2023-11-28 10:37:51,519][87426] Updated weights for policy 1, policy_version 396830 (0.0012) -[2023-11-28 10:37:53,188][87424] Updated weights for policy 0, policy_version 397159 (0.0009) -[2023-11-28 10:37:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203259904. Throughput: 0: 2626.9, 1: 2693.0. Samples: 203279800. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:53,445][86177] Avg episode reward: [(0, '-547.630'), (1, '-547.540')] -[2023-11-28 10:37:53,585][87424] Updated weights for policy 0, policy_version 397169 (0.0012) -[2023-11-28 10:37:53,812][87426] Updated weights for policy 1, policy_version 396840 (0.0011) -[2023-11-28 10:37:53,962][87424] Updated weights for policy 0, policy_version 397179 (0.0012) -[2023-11-28 10:37:54,194][87426] Updated weights for policy 1, policy_version 396850 (0.0007) -[2023-11-28 10:37:54,576][87426] Updated weights for policy 1, policy_version 396860 (0.0008) -[2023-11-28 10:37:56,515][87424] Updated weights for policy 0, policy_version 397189 (0.0009) -[2023-11-28 10:37:56,721][87426] Updated weights for policy 1, policy_version 396870 (0.0011) -[2023-11-28 10:37:56,889][87424] Updated weights for policy 0, policy_version 397199 (0.0007) -[2023-11-28 10:37:57,090][87426] Updated weights for policy 1, policy_version 396880 (0.0008) -[2023-11-28 10:37:57,270][87424] Updated weights for policy 0, policy_version 397209 (0.0008) -[2023-11-28 10:37:57,477][87426] Updated weights for policy 1, policy_version 396890 (0.0007) -[2023-11-28 10:37:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203292672. Throughput: 0: 2601.1, 1: 2685.5. Samples: 203302972. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:37:58,445][86177] Avg episode reward: [(0, '-542.420'), (1, '-527.130')] -[2023-11-28 10:37:59,289][87426] Updated weights for policy 1, policy_version 396900 (0.0007) -[2023-11-28 10:37:59,668][87426] Updated weights for policy 1, policy_version 396910 (0.0008) -[2023-11-28 10:37:59,798][87424] Updated weights for policy 0, policy_version 397219 (0.0008) -[2023-11-28 10:38:00,043][87426] Updated weights for policy 1, policy_version 396920 (0.0010) -[2023-11-28 10:38:00,175][87424] Updated weights for policy 0, policy_version 397229 (0.0009) -[2023-11-28 10:38:00,554][87424] Updated weights for policy 0, policy_version 397239 (0.0010) -[2023-11-28 10:38:02,428][87424] Updated weights for policy 0, policy_version 397249 (0.0011) -[2023-11-28 10:38:02,506][87426] Updated weights for policy 1, policy_version 396930 (0.0009) -[2023-11-28 10:38:02,802][87424] Updated weights for policy 0, policy_version 397259 (0.0012) -[2023-11-28 10:38:02,882][87426] Updated weights for policy 1, policy_version 396940 (0.0012) -[2023-11-28 10:38:03,180][87424] Updated weights for policy 0, policy_version 397269 (0.0011) -[2023-11-28 10:38:03,260][87426] Updated weights for policy 1, policy_version 396950 (0.0012) -[2023-11-28 10:38:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 203309056. Throughput: 0: 2597.9, 1: 2697.7. Samples: 203326928. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:38:03,445][86177] Avg episode reward: [(0, '-568.700'), (1, '-532.630')] -[2023-11-28 10:38:03,561][87424] Updated weights for policy 0, policy_version 397279 (0.0012) -[2023-11-28 10:38:03,643][87426] Updated weights for policy 1, policy_version 396960 (0.0012) -[2023-11-28 10:38:05,680][87424] Updated weights for policy 0, policy_version 397289 (0.0010) -[2023-11-28 10:38:05,807][87426] Updated weights for policy 1, policy_version 396970 (0.0008) -[2023-11-28 10:38:06,055][87424] Updated weights for policy 0, policy_version 397299 (0.0007) -[2023-11-28 10:38:06,199][87426] Updated weights for policy 1, policy_version 396980 (0.0011) -[2023-11-28 10:38:06,435][87424] Updated weights for policy 0, policy_version 397309 (0.0009) -[2023-11-28 10:38:06,574][87426] Updated weights for policy 1, policy_version 396990 (0.0010) -[2023-11-28 10:38:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203341824. Throughput: 0: 2599.4, 1: 2710.9. Samples: 203359516. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:38:08,445][86177] Avg episode reward: [(0, '-544.970'), (1, '-536.030')] -[2023-11-28 10:38:08,767][87426] Updated weights for policy 1, policy_version 397000 (0.0008) -[2023-11-28 10:38:09,017][87424] Updated weights for policy 0, policy_version 397319 (0.0012) -[2023-11-28 10:38:09,143][87426] Updated weights for policy 1, policy_version 397010 (0.0010) -[2023-11-28 10:38:09,396][87424] Updated weights for policy 0, policy_version 397329 (0.0010) -[2023-11-28 10:38:09,524][87426] Updated weights for policy 1, policy_version 397020 (0.0011) -[2023-11-28 10:38:09,775][87424] Updated weights for policy 0, policy_version 397339 (0.0012) -[2023-11-28 10:38:11,608][87426] Updated weights for policy 1, policy_version 397030 (0.0009) -[2023-11-28 10:38:11,988][87426] Updated weights for policy 1, policy_version 397040 (0.0010) -[2023-11-28 10:38:12,361][87426] Updated weights for policy 1, policy_version 397050 (0.0012) -[2023-11-28 10:38:12,492][87424] Updated weights for policy 0, policy_version 397349 (0.0011) -[2023-11-28 10:38:12,877][87424] Updated weights for policy 0, policy_version 397359 (0.0012) -[2023-11-28 10:38:13,256][87424] Updated weights for policy 0, policy_version 397369 (0.0008) -[2023-11-28 10:38:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 203366400. Throughput: 0: 2595.7, 1: 2687.0. Samples: 203383360. Policy #0 lag: (min: 19.0, avg: 32.5, max: 49.0) -[2023-11-28 10:38:13,446][86177] Avg episode reward: [(0, '-562.410'), (1, '-528.910')] -[2023-11-28 10:38:14,618][87426] Updated weights for policy 1, policy_version 397060 (0.0010) -[2023-11-28 10:38:14,999][87426] Updated weights for policy 1, policy_version 397070 (0.0011) -[2023-11-28 10:38:15,025][87424] Updated weights for policy 0, policy_version 397379 (0.0008) -[2023-11-28 10:38:15,372][87426] Updated weights for policy 1, policy_version 397080 (0.0012) -[2023-11-28 10:38:15,420][87424] Updated weights for policy 0, policy_version 397389 (0.0011) -[2023-11-28 10:38:15,795][87424] Updated weights for policy 0, policy_version 397399 (0.0012) -[2023-11-28 10:38:17,454][87426] Updated weights for policy 1, policy_version 397090 (0.0012) -[2023-11-28 10:38:17,826][87426] Updated weights for policy 1, policy_version 397100 (0.0011) -[2023-11-28 10:38:18,145][87424] Updated weights for policy 0, policy_version 397409 (0.0012) -[2023-11-28 10:38:18,213][87426] Updated weights for policy 1, policy_version 397110 (0.0008) -[2023-11-28 10:38:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 203390976. Throughput: 0: 2613.4, 1: 2692.9. Samples: 203408120. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:38:18,445][86177] Avg episode reward: [(0, '-578.460'), (1, '-517.140')] -[2023-11-28 10:38:18,531][87424] Updated weights for policy 0, policy_version 397419 (0.0011) -[2023-11-28 10:38:18,585][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000397120_101662720.pth... -[2023-11-28 10:38:18,588][87426] Updated weights for policy 1, policy_version 397120 (0.0011) -[2023-11-28 10:38:18,619][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000394592_101015552.pth -[2023-11-28 10:38:18,904][87424] Updated weights for policy 0, policy_version 397429 (0.0008) -[2023-11-28 10:38:19,283][87424] Updated weights for policy 0, policy_version 397439 (0.0011) -[2023-11-28 10:38:19,321][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000397440_101744640.pth... -[2023-11-28 10:38:19,366][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000394912_101097472.pth -[2023-11-28 10:38:20,769][87426] Updated weights for policy 1, policy_version 397130 (0.0012) -[2023-11-28 10:38:21,142][87426] Updated weights for policy 1, policy_version 397140 (0.0011) -[2023-11-28 10:38:21,525][87426] Updated weights for policy 1, policy_version 397150 (0.0011) -[2023-11-28 10:38:21,659][87424] Updated weights for policy 0, policy_version 397449 (0.0011) -[2023-11-28 10:38:22,043][87424] Updated weights for policy 0, policy_version 397459 (0.0012) -[2023-11-28 10:38:22,432][87424] Updated weights for policy 0, policy_version 397469 (0.0008) -[2023-11-28 10:38:23,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203423744. Throughput: 0: 2609.9, 1: 2682.5. Samples: 203439692. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:38:23,445][86177] Avg episode reward: [(0, '-566.290'), (1, '-517.770')] -[2023-11-28 10:38:24,270][87426] Updated weights for policy 1, policy_version 397160 (0.0010) -[2023-11-28 10:38:24,654][87426] Updated weights for policy 1, policy_version 397170 (0.0008) -[2023-11-28 10:38:24,734][87424] Updated weights for policy 0, policy_version 397479 (0.0010) -[2023-11-28 10:38:25,034][87426] Updated weights for policy 1, policy_version 397180 (0.0011) -[2023-11-28 10:38:25,113][87424] Updated weights for policy 0, policy_version 397489 (0.0011) -[2023-11-28 10:38:25,500][87424] Updated weights for policy 0, policy_version 397499 (0.0012) -[2023-11-28 10:38:26,794][87426] Updated weights for policy 1, policy_version 397190 (0.0010) -[2023-11-28 10:38:27,179][87426] Updated weights for policy 1, policy_version 397200 (0.0011) -[2023-11-28 10:38:27,565][87426] Updated weights for policy 1, policy_version 397210 (0.0010) -[2023-11-28 10:38:27,618][87424] Updated weights for policy 0, policy_version 397509 (0.0012) -[2023-11-28 10:38:28,002][87424] Updated weights for policy 0, policy_version 397519 (0.0012) -[2023-11-28 10:38:28,379][87424] Updated weights for policy 0, policy_version 397529 (0.0012) -[2023-11-28 10:38:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203448320. Throughput: 0: 2609.8, 1: 2687.7. Samples: 203463708. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:38:28,445][86177] Avg episode reward: [(0, '-572.320'), (1, '-527.750')] -[2023-11-28 10:38:30,120][87426] Updated weights for policy 1, policy_version 397220 (0.0009) -[2023-11-28 10:38:30,235][87424] Updated weights for policy 0, policy_version 397539 (0.0011) -[2023-11-28 10:38:30,503][87426] Updated weights for policy 1, policy_version 397230 (0.0011) -[2023-11-28 10:38:30,625][87424] Updated weights for policy 0, policy_version 397549 (0.0010) -[2023-11-28 10:38:30,876][87426] Updated weights for policy 1, policy_version 397240 (0.0012) -[2023-11-28 10:38:30,999][87424] Updated weights for policy 0, policy_version 397559 (0.0010) -[2023-11-28 10:38:32,923][87426] Updated weights for policy 1, policy_version 397250 (0.0011) -[2023-11-28 10:38:32,953][87424] Updated weights for policy 0, policy_version 397569 (0.0008) -[2023-11-28 10:38:33,299][87426] Updated weights for policy 1, policy_version 397260 (0.0012) -[2023-11-28 10:38:33,329][87424] Updated weights for policy 0, policy_version 397579 (0.0012) -[2023-11-28 10:38:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 203472896. Throughput: 0: 2661.9, 1: 2679.1. Samples: 203489264. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:38:33,445][86177] Avg episode reward: [(0, '-555.340'), (1, '-526.140')] -[2023-11-28 10:38:33,672][87426] Updated weights for policy 1, policy_version 397270 (0.0010) -[2023-11-28 10:38:33,705][87424] Updated weights for policy 0, policy_version 397589 (0.0011) -[2023-11-28 10:38:34,050][87426] Updated weights for policy 1, policy_version 397280 (0.0009) -[2023-11-28 10:38:34,077][87424] Updated weights for policy 0, policy_version 397599 (0.0012) -[2023-11-28 10:38:35,917][87426] Updated weights for policy 1, policy_version 397290 (0.0012) -[2023-11-28 10:38:36,294][87426] Updated weights for policy 1, policy_version 397300 (0.0012) -[2023-11-28 10:38:36,565][87424] Updated weights for policy 0, policy_version 397609 (0.0011) -[2023-11-28 10:38:36,680][87426] Updated weights for policy 1, policy_version 397310 (0.0011) -[2023-11-28 10:38:36,946][87424] Updated weights for policy 0, policy_version 397619 (0.0012) -[2023-11-28 10:38:37,334][87424] Updated weights for policy 0, policy_version 397629 (0.0012) -[2023-11-28 10:38:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203505664. Throughput: 0: 2669.6, 1: 2716.1. Samples: 203522156. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:38:38,445][86177] Avg episode reward: [(0, '-545.970'), (1, '-525.580')] -[2023-11-28 10:38:38,789][87426] Updated weights for policy 1, policy_version 397320 (0.0011) -[2023-11-28 10:38:39,185][87426] Updated weights for policy 1, policy_version 397330 (0.0009) -[2023-11-28 10:38:39,568][87426] Updated weights for policy 1, policy_version 397340 (0.0010) -[2023-11-28 10:38:39,684][87424] Updated weights for policy 0, policy_version 397639 (0.0012) -[2023-11-28 10:38:40,064][87424] Updated weights for policy 0, policy_version 397649 (0.0011) -[2023-11-28 10:38:40,444][87424] Updated weights for policy 0, policy_version 397659 (0.0008) -[2023-11-28 10:38:41,976][87426] Updated weights for policy 1, policy_version 397350 (0.0009) -[2023-11-28 10:38:42,349][87426] Updated weights for policy 1, policy_version 397360 (0.0009) -[2023-11-28 10:38:42,731][87426] Updated weights for policy 1, policy_version 397370 (0.0012) -[2023-11-28 10:38:42,761][87424] Updated weights for policy 0, policy_version 397669 (0.0010) -[2023-11-28 10:38:43,141][87424] Updated weights for policy 0, policy_version 397679 (0.0012) -[2023-11-28 10:38:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203530240. Throughput: 0: 2687.5, 1: 2703.7. Samples: 203545576. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:38:43,445][86177] Avg episode reward: [(0, '-535.650'), (1, '-527.820')] -[2023-11-28 10:38:43,529][87424] Updated weights for policy 0, policy_version 397689 (0.0012) -[2023-11-28 10:38:44,699][87426] Updated weights for policy 1, policy_version 397380 (0.0012) -[2023-11-28 10:38:45,075][87426] Updated weights for policy 1, policy_version 397390 (0.0012) -[2023-11-28 10:38:45,458][87426] Updated weights for policy 1, policy_version 397400 (0.0011) -[2023-11-28 10:38:46,045][87424] Updated weights for policy 0, policy_version 397699 (0.0012) -[2023-11-28 10:38:46,423][87424] Updated weights for policy 0, policy_version 397709 (0.0012) -[2023-11-28 10:38:46,799][87424] Updated weights for policy 0, policy_version 397719 (0.0012) -[2023-11-28 10:38:47,627][87426] Updated weights for policy 1, policy_version 397410 (0.0010) -[2023-11-28 10:38:48,008][87426] Updated weights for policy 1, policy_version 397420 (0.0012) -[2023-11-28 10:38:48,387][87426] Updated weights for policy 1, policy_version 397430 (0.0011) -[2023-11-28 10:38:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 203554816. Throughput: 0: 2673.3, 1: 2704.5. Samples: 203568932. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:38:48,445][86177] Avg episode reward: [(0, '-520.420'), (1, '-523.980')] -[2023-11-28 10:38:48,772][87426] Updated weights for policy 1, policy_version 397440 (0.0009) -[2023-11-28 10:38:49,043][87424] Updated weights for policy 0, policy_version 397729 (0.0011) -[2023-11-28 10:38:49,433][87424] Updated weights for policy 0, policy_version 397739 (0.0010) -[2023-11-28 10:38:49,807][87424] Updated weights for policy 0, policy_version 397749 (0.0012) -[2023-11-28 10:38:50,188][87424] Updated weights for policy 0, policy_version 397759 (0.0012) -[2023-11-28 10:38:51,205][87426] Updated weights for policy 1, policy_version 397450 (0.0012) -[2023-11-28 10:38:51,582][87426] Updated weights for policy 1, policy_version 397460 (0.0012) -[2023-11-28 10:38:51,958][87426] Updated weights for policy 1, policy_version 397470 (0.0011) -[2023-11-28 10:38:52,146][87424] Updated weights for policy 0, policy_version 397769 (0.0011) -[2023-11-28 10:38:52,531][87424] Updated weights for policy 0, policy_version 397779 (0.0012) -[2023-11-28 10:38:52,910][87424] Updated weights for policy 0, policy_version 397789 (0.0012) -[2023-11-28 10:38:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203587584. Throughput: 0: 2677.2, 1: 2677.1. Samples: 203600456. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:38:53,445][86177] Avg episode reward: [(0, '-523.690'), (1, '-554.650')] -[2023-11-28 10:38:54,447][87426] Updated weights for policy 1, policy_version 397480 (0.0011) -[2023-11-28 10:38:54,826][87426] Updated weights for policy 1, policy_version 397490 (0.0009) -[2023-11-28 10:38:55,213][87426] Updated weights for policy 1, policy_version 397500 (0.0009) -[2023-11-28 10:38:55,485][87424] Updated weights for policy 0, policy_version 397799 (0.0012) -[2023-11-28 10:38:55,864][87424] Updated weights for policy 0, policy_version 397809 (0.0012) -[2023-11-28 10:38:56,262][87424] Updated weights for policy 0, policy_version 397819 (0.0009) -[2023-11-28 10:38:57,289][87426] Updated weights for policy 1, policy_version 397510 (0.0011) -[2023-11-28 10:38:57,660][87426] Updated weights for policy 1, policy_version 397520 (0.0012) -[2023-11-28 10:38:57,976][87424] Updated weights for policy 0, policy_version 397829 (0.0010) -[2023-11-28 10:38:58,031][87426] Updated weights for policy 1, policy_version 397530 (0.0012) -[2023-11-28 10:38:58,366][87424] Updated weights for policy 0, policy_version 397839 (0.0009) -[2023-11-28 10:38:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 203612160. Throughput: 0: 2685.6, 1: 2700.0. Samples: 203625712. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:38:58,445][86177] Avg episode reward: [(0, '-523.870'), (1, '-566.300')] -[2023-11-28 10:38:58,750][87424] Updated weights for policy 0, policy_version 397849 (0.0010) -[2023-11-28 10:39:00,367][87426] Updated weights for policy 1, policy_version 397540 (0.0012) -[2023-11-28 10:39:00,750][87426] Updated weights for policy 1, policy_version 397550 (0.0011) -[2023-11-28 10:39:00,993][87424] Updated weights for policy 0, policy_version 397859 (0.0011) -[2023-11-28 10:39:01,129][87426] Updated weights for policy 1, policy_version 397560 (0.0011) -[2023-11-28 10:39:01,382][87424] Updated weights for policy 0, policy_version 397869 (0.0010) -[2023-11-28 10:39:01,750][87424] Updated weights for policy 0, policy_version 397879 (0.0012) -[2023-11-28 10:39:02,831][87426] Updated weights for policy 1, policy_version 397570 (0.0011) -[2023-11-28 10:39:03,203][87426] Updated weights for policy 1, policy_version 397580 (0.0010) -[2023-11-28 10:39:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203636736. Throughput: 0: 2682.0, 1: 2706.8. Samples: 203650612. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:39:03,445][86177] Avg episode reward: [(0, '-529.500'), (1, '-565.130')] -[2023-11-28 10:39:03,580][87426] Updated weights for policy 1, policy_version 397590 (0.0010) -[2023-11-28 10:39:03,959][87426] Updated weights for policy 1, policy_version 397600 (0.0007) -[2023-11-28 10:39:03,991][87424] Updated weights for policy 0, policy_version 397889 (0.0011) -[2023-11-28 10:39:04,367][87424] Updated weights for policy 0, policy_version 397899 (0.0011) -[2023-11-28 10:39:04,749][87424] Updated weights for policy 0, policy_version 397909 (0.0010) -[2023-11-28 10:39:05,128][87424] Updated weights for policy 0, policy_version 397919 (0.0010) -[2023-11-28 10:39:05,964][87426] Updated weights for policy 1, policy_version 397610 (0.0012) -[2023-11-28 10:39:06,360][87426] Updated weights for policy 1, policy_version 397620 (0.0012) -[2023-11-28 10:39:06,738][87426] Updated weights for policy 1, policy_version 397630 (0.0012) -[2023-11-28 10:39:07,182][87424] Updated weights for policy 0, policy_version 397929 (0.0012) -[2023-11-28 10:39:07,565][87424] Updated weights for policy 0, policy_version 397939 (0.0012) -[2023-11-28 10:39:07,943][87424] Updated weights for policy 0, policy_version 397949 (0.0012) -[2023-11-28 10:39:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203669504. Throughput: 0: 2701.1, 1: 2725.5. Samples: 203683888. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:39:08,445][86177] Avg episode reward: [(0, '-532.040'), (1, '-561.320')] -[2023-11-28 10:39:08,868][87426] Updated weights for policy 1, policy_version 397640 (0.0011) -[2023-11-28 10:39:09,249][87426] Updated weights for policy 1, policy_version 397650 (0.0009) -[2023-11-28 10:39:09,624][87426] Updated weights for policy 1, policy_version 397660 (0.0010) -[2023-11-28 10:39:10,189][87424] Updated weights for policy 0, policy_version 397959 (0.0009) -[2023-11-28 10:39:10,568][87424] Updated weights for policy 0, policy_version 397969 (0.0009) -[2023-11-28 10:39:10,953][87424] Updated weights for policy 0, policy_version 397979 (0.0009) -[2023-11-28 10:39:11,971][87426] Updated weights for policy 1, policy_version 397670 (0.0011) -[2023-11-28 10:39:12,347][87426] Updated weights for policy 1, policy_version 397680 (0.0012) -[2023-11-28 10:39:12,719][87426] Updated weights for policy 1, policy_version 397690 (0.0012) -[2023-11-28 10:39:13,220][87424] Updated weights for policy 0, policy_version 397989 (0.0011) -[2023-11-28 10:39:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203694080. Throughput: 0: 2700.2, 1: 2710.9. Samples: 203707208. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:39:13,445][86177] Avg episode reward: [(0, '-531.370'), (1, '-532.780')] -[2023-11-28 10:39:13,598][87424] Updated weights for policy 0, policy_version 397999 (0.0011) -[2023-11-28 10:39:13,988][87424] Updated weights for policy 0, policy_version 398009 (0.0012) -[2023-11-28 10:39:15,070][87426] Updated weights for policy 1, policy_version 397700 (0.0011) -[2023-11-28 10:39:15,451][87426] Updated weights for policy 1, policy_version 397710 (0.0009) -[2023-11-28 10:39:15,833][87426] Updated weights for policy 1, policy_version 397720 (0.0009) -[2023-11-28 10:39:16,315][87424] Updated weights for policy 0, policy_version 398019 (0.0009) -[2023-11-28 10:39:16,694][87424] Updated weights for policy 0, policy_version 398029 (0.0010) -[2023-11-28 10:39:17,081][87424] Updated weights for policy 0, policy_version 398039 (0.0012) -[2023-11-28 10:39:17,729][87426] Updated weights for policy 1, policy_version 397730 (0.0008) -[2023-11-28 10:39:18,105][87426] Updated weights for policy 1, policy_version 397740 (0.0010) -[2023-11-28 10:39:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203718656. Throughput: 0: 2669.8, 1: 2725.0. Samples: 203732028. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:39:18,445][86177] Avg episode reward: [(0, '-533.620'), (1, '-515.430')] -[2023-11-28 10:39:18,480][87426] Updated weights for policy 1, policy_version 397750 (0.0011) -[2023-11-28 10:39:18,857][87426] Updated weights for policy 1, policy_version 397760 (0.0011) -[2023-11-28 10:39:19,540][87424] Updated weights for policy 0, policy_version 398049 (0.0012) -[2023-11-28 10:39:19,914][87424] Updated weights for policy 0, policy_version 398059 (0.0011) -[2023-11-28 10:39:20,295][87424] Updated weights for policy 0, policy_version 398069 (0.0012) -[2023-11-28 10:39:20,681][87424] Updated weights for policy 0, policy_version 398079 (0.0011) -[2023-11-28 10:39:21,244][87426] Updated weights for policy 1, policy_version 397770 (0.0012) -[2023-11-28 10:39:21,631][87426] Updated weights for policy 1, policy_version 397780 (0.0012) -[2023-11-28 10:39:22,008][87426] Updated weights for policy 1, policy_version 397790 (0.0013) -[2023-11-28 10:39:22,911][87424] Updated weights for policy 0, policy_version 398089 (0.0011) -[2023-11-28 10:39:23,300][87424] Updated weights for policy 0, policy_version 398099 (0.0012) -[2023-11-28 10:39:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 203743232. Throughput: 0: 2673.0, 1: 2713.1. Samples: 203764532. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:39:23,445][86177] Avg episode reward: [(0, '-526.700'), (1, '-516.240')] -[2023-11-28 10:39:23,683][87424] Updated weights for policy 0, policy_version 398109 (0.0011) -[2023-11-28 10:39:24,193][87426] Updated weights for policy 1, policy_version 397800 (0.0012) -[2023-11-28 10:39:24,572][87426] Updated weights for policy 1, policy_version 397810 (0.0010) -[2023-11-28 10:39:24,953][87426] Updated weights for policy 1, policy_version 397820 (0.0009) -[2023-11-28 10:39:25,825][87424] Updated weights for policy 0, policy_version 398119 (0.0010) -[2023-11-28 10:39:26,200][87424] Updated weights for policy 0, policy_version 398129 (0.0011) -[2023-11-28 10:39:26,586][87424] Updated weights for policy 0, policy_version 398139 (0.0010) -[2023-11-28 10:39:26,909][87426] Updated weights for policy 1, policy_version 397830 (0.0007) -[2023-11-28 10:39:27,286][87426] Updated weights for policy 1, policy_version 397840 (0.0007) -[2023-11-28 10:39:27,665][87426] Updated weights for policy 1, policy_version 397850 (0.0007) -[2023-11-28 10:39:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203776000. Throughput: 0: 2679.7, 1: 2734.7. Samples: 203789228. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:39:28,445][86177] Avg episode reward: [(0, '-531.510'), (1, '-548.240')] -[2023-11-28 10:39:28,469][87424] Updated weights for policy 0, policy_version 398149 (0.0011) -[2023-11-28 10:39:28,844][87424] Updated weights for policy 0, policy_version 398159 (0.0012) -[2023-11-28 10:39:29,224][87424] Updated weights for policy 0, policy_version 398169 (0.0012) -[2023-11-28 10:39:30,216][87426] Updated weights for policy 1, policy_version 397860 (0.0009) -[2023-11-28 10:39:30,593][87426] Updated weights for policy 1, policy_version 397870 (0.0010) -[2023-11-28 10:39:30,980][87426] Updated weights for policy 1, policy_version 397880 (0.0008) -[2023-11-28 10:39:31,340][87424] Updated weights for policy 0, policy_version 398179 (0.0010) -[2023-11-28 10:39:31,719][87424] Updated weights for policy 0, policy_version 398189 (0.0009) -[2023-11-28 10:39:32,103][87424] Updated weights for policy 0, policy_version 398199 (0.0012) -[2023-11-28 10:39:33,184][87426] Updated weights for policy 1, policy_version 397890 (0.0008) -[2023-11-28 10:39:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203800576. Throughput: 0: 2704.2, 1: 2720.3. Samples: 203813032. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:39:33,445][86177] Avg episode reward: [(0, '-531.360'), (1, '-554.940')] -[2023-11-28 10:39:33,556][87426] Updated weights for policy 1, policy_version 397900 (0.0010) -[2023-11-28 10:39:33,937][87426] Updated weights for policy 1, policy_version 397910 (0.0007) -[2023-11-28 10:39:34,318][87426] Updated weights for policy 1, policy_version 397920 (0.0007) -[2023-11-28 10:39:34,506][87424] Updated weights for policy 0, policy_version 398209 (0.0011) -[2023-11-28 10:39:34,877][87424] Updated weights for policy 0, policy_version 398219 (0.0010) -[2023-11-28 10:39:35,266][87424] Updated weights for policy 0, policy_version 398229 (0.0011) -[2023-11-28 10:39:35,642][87424] Updated weights for policy 0, policy_version 398239 (0.0012) -[2023-11-28 10:39:36,651][87426] Updated weights for policy 1, policy_version 397930 (0.0011) -[2023-11-28 10:39:37,030][87426] Updated weights for policy 1, policy_version 397940 (0.0012) -[2023-11-28 10:39:37,411][87426] Updated weights for policy 1, policy_version 397950 (0.0010) -[2023-11-28 10:39:37,980][87424] Updated weights for policy 0, policy_version 398249 (0.0012) -[2023-11-28 10:39:38,362][87424] Updated weights for policy 0, policy_version 398259 (0.0012) -[2023-11-28 10:39:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 203825152. Throughput: 0: 2689.9, 1: 2759.4. Samples: 203845672. Policy #0 lag: (min: 31.0, avg: 45.8, max: 63.0) -[2023-11-28 10:39:38,445][86177] Avg episode reward: [(0, '-533.100'), (1, '-565.510')] -[2023-11-28 10:39:38,749][87424] Updated weights for policy 0, policy_version 398269 (0.0012) -[2023-11-28 10:39:39,666][87426] Updated weights for policy 1, policy_version 397960 (0.0010) -[2023-11-28 10:39:40,043][87426] Updated weights for policy 1, policy_version 397970 (0.0010) -[2023-11-28 10:39:40,429][87426] Updated weights for policy 1, policy_version 397980 (0.0008) -[2023-11-28 10:39:40,798][87424] Updated weights for policy 0, policy_version 398279 (0.0011) -[2023-11-28 10:39:41,185][87424] Updated weights for policy 0, policy_version 398289 (0.0008) -[2023-11-28 10:39:41,561][87424] Updated weights for policy 0, policy_version 398299 (0.0008) -[2023-11-28 10:39:42,421][87426] Updated weights for policy 1, policy_version 397990 (0.0010) -[2023-11-28 10:39:42,791][87426] Updated weights for policy 1, policy_version 398000 (0.0008) -[2023-11-28 10:39:43,170][87426] Updated weights for policy 1, policy_version 398010 (0.0010) -[2023-11-28 10:39:43,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203857920. Throughput: 0: 2687.2, 1: 2736.6. Samples: 203869784. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:39:43,445][86177] Avg episode reward: [(0, '-533.530'), (1, '-566.230')] -[2023-11-28 10:39:43,717][87424] Updated weights for policy 0, policy_version 398309 (0.0010) -[2023-11-28 10:39:44,092][87424] Updated weights for policy 0, policy_version 398319 (0.0008) -[2023-11-28 10:39:44,472][87424] Updated weights for policy 0, policy_version 398329 (0.0008) -[2023-11-28 10:39:45,127][87426] Updated weights for policy 1, policy_version 398020 (0.0009) -[2023-11-28 10:39:45,514][87426] Updated weights for policy 1, policy_version 398030 (0.0010) -[2023-11-28 10:39:45,897][87426] Updated weights for policy 1, policy_version 398040 (0.0011) -[2023-11-28 10:39:47,021][87424] Updated weights for policy 0, policy_version 398339 (0.0009) -[2023-11-28 10:39:47,395][87424] Updated weights for policy 0, policy_version 398349 (0.0012) -[2023-11-28 10:39:47,786][87424] Updated weights for policy 0, policy_version 398359 (0.0012) -[2023-11-28 10:39:48,217][87426] Updated weights for policy 1, policy_version 398050 (0.0008) -[2023-11-28 10:39:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 203882496. Throughput: 0: 2672.9, 1: 2723.7. Samples: 203893460. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:39:48,445][86177] Avg episode reward: [(0, '-537.650'), (1, '-558.040')] -[2023-11-28 10:39:48,596][87426] Updated weights for policy 1, policy_version 398060 (0.0008) -[2023-11-28 10:39:48,978][87426] Updated weights for policy 1, policy_version 398070 (0.0007) -[2023-11-28 10:39:49,355][87426] Updated weights for policy 1, policy_version 398080 (0.0008) -[2023-11-28 10:39:50,385][87424] Updated weights for policy 0, policy_version 398369 (0.0012) -[2023-11-28 10:39:50,763][87424] Updated weights for policy 0, policy_version 398379 (0.0012) -[2023-11-28 10:39:51,142][87424] Updated weights for policy 0, policy_version 398389 (0.0012) -[2023-11-28 10:39:51,408][87426] Updated weights for policy 1, policy_version 398090 (0.0012) -[2023-11-28 10:39:51,519][87424] Updated weights for policy 0, policy_version 398399 (0.0010) -[2023-11-28 10:39:51,795][87426] Updated weights for policy 1, policy_version 398100 (0.0010) -[2023-11-28 10:39:52,168][87426] Updated weights for policy 1, policy_version 398110 (0.0011) -[2023-11-28 10:39:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 203907072. Throughput: 0: 2639.9, 1: 2710.7. Samples: 203924664. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:39:53,445][86177] Avg episode reward: [(0, '-540.970'), (1, '-550.860')] -[2023-11-28 10:39:53,565][87424] Updated weights for policy 0, policy_version 398409 (0.0011) -[2023-11-28 10:39:53,941][87424] Updated weights for policy 0, policy_version 398419 (0.0010) -[2023-11-28 10:39:54,337][87424] Updated weights for policy 0, policy_version 398429 (0.0011) -[2023-11-28 10:39:54,722][87426] Updated weights for policy 1, policy_version 398120 (0.0011) -[2023-11-28 10:39:55,097][87426] Updated weights for policy 1, policy_version 398130 (0.0009) -[2023-11-28 10:39:55,480][87426] Updated weights for policy 1, policy_version 398140 (0.0007) -[2023-11-28 10:39:56,792][87424] Updated weights for policy 0, policy_version 398439 (0.0010) -[2023-11-28 10:39:57,187][87424] Updated weights for policy 0, policy_version 398449 (0.0008) -[2023-11-28 10:39:57,485][87426] Updated weights for policy 1, policy_version 398150 (0.0010) -[2023-11-28 10:39:57,559][87424] Updated weights for policy 0, policy_version 398459 (0.0008) -[2023-11-28 10:39:57,860][87426] Updated weights for policy 1, policy_version 398160 (0.0012) -[2023-11-28 10:39:58,247][87426] Updated weights for policy 1, policy_version 398170 (0.0011) -[2023-11-28 10:39:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203931648. Throughput: 0: 2637.8, 1: 2726.4. Samples: 203948596. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:39:58,445][86177] Avg episode reward: [(0, '-537.930'), (1, '-547.130')] -[2023-11-28 10:39:59,953][87424] Updated weights for policy 0, policy_version 398469 (0.0014) -[2023-11-28 10:40:00,327][87424] Updated weights for policy 0, policy_version 398479 (0.0012) -[2023-11-28 10:40:00,373][87426] Updated weights for policy 1, policy_version 398180 (0.0012) -[2023-11-28 10:40:00,704][87424] Updated weights for policy 0, policy_version 398489 (0.0011) -[2023-11-28 10:40:00,745][87426] Updated weights for policy 1, policy_version 398190 (0.0011) -[2023-11-28 10:40:01,120][87426] Updated weights for policy 1, policy_version 398200 (0.0011) -[2023-11-28 10:40:03,226][87424] Updated weights for policy 0, policy_version 398499 (0.0011) -[2023-11-28 10:40:03,436][87426] Updated weights for policy 1, policy_version 398210 (0.0011) -[2023-11-28 10:40:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 203956224. Throughput: 0: 2631.4, 1: 2721.9. Samples: 203972924. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:03,445][86177] Avg episode reward: [(0, '-544.430'), (1, '-537.080')] -[2023-11-28 10:40:03,604][87424] Updated weights for policy 0, policy_version 398509 (0.0009) -[2023-11-28 10:40:03,817][87426] Updated weights for policy 1, policy_version 398220 (0.0008) -[2023-11-28 10:40:03,991][87424] Updated weights for policy 0, policy_version 398519 (0.0007) -[2023-11-28 10:40:04,203][87426] Updated weights for policy 1, policy_version 398230 (0.0008) -[2023-11-28 10:40:04,578][87426] Updated weights for policy 1, policy_version 398240 (0.0008) -[2023-11-28 10:40:06,135][87424] Updated weights for policy 0, policy_version 398529 (0.0007) -[2023-11-28 10:40:06,529][87424] Updated weights for policy 0, policy_version 398539 (0.0008) -[2023-11-28 10:40:06,781][87426] Updated weights for policy 1, policy_version 398250 (0.0010) -[2023-11-28 10:40:06,903][87424] Updated weights for policy 0, policy_version 398549 (0.0010) -[2023-11-28 10:40:07,171][87426] Updated weights for policy 1, policy_version 398260 (0.0009) -[2023-11-28 10:40:07,287][87424] Updated weights for policy 0, policy_version 398559 (0.0010) -[2023-11-28 10:40:07,546][87426] Updated weights for policy 1, policy_version 398270 (0.0011) -[2023-11-28 10:40:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 203988992. Throughput: 0: 2623.9, 1: 2726.3. Samples: 204005292. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:08,445][86177] Avg episode reward: [(0, '-538.860'), (1, '-509.980')] -[2023-11-28 10:40:09,135][87424] Updated weights for policy 0, policy_version 398569 (0.0012) -[2023-11-28 10:40:09,499][87426] Updated weights for policy 1, policy_version 398280 (0.0012) -[2023-11-28 10:40:09,512][87424] Updated weights for policy 0, policy_version 398579 (0.0011) -[2023-11-28 10:40:09,871][87426] Updated weights for policy 1, policy_version 398290 (0.0012) -[2023-11-28 10:40:09,897][87424] Updated weights for policy 0, policy_version 398589 (0.0011) -[2023-11-28 10:40:10,251][87426] Updated weights for policy 1, policy_version 398300 (0.0010) -[2023-11-28 10:40:11,983][87424] Updated weights for policy 0, policy_version 398599 (0.0011) -[2023-11-28 10:40:12,382][87424] Updated weights for policy 0, policy_version 398609 (0.0019) -[2023-11-28 10:40:12,624][87426] Updated weights for policy 1, policy_version 398310 (0.0011) -[2023-11-28 10:40:12,754][87424] Updated weights for policy 0, policy_version 398619 (0.0011) -[2023-11-28 10:40:13,002][87426] Updated weights for policy 1, policy_version 398320 (0.0011) -[2023-11-28 10:40:13,384][87426] Updated weights for policy 1, policy_version 398330 (0.0011) -[2023-11-28 10:40:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204013568. Throughput: 0: 2630.1, 1: 2704.7. Samples: 204029292. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:13,445][86177] Avg episode reward: [(0, '-537.340'), (1, '-514.690')] -[2023-11-28 10:40:14,935][87424] Updated weights for policy 0, policy_version 398629 (0.0011) -[2023-11-28 10:40:15,272][87426] Updated weights for policy 1, policy_version 398340 (0.0009) -[2023-11-28 10:40:15,308][87424] Updated weights for policy 0, policy_version 398639 (0.0010) -[2023-11-28 10:40:15,657][87426] Updated weights for policy 1, policy_version 398350 (0.0010) -[2023-11-28 10:40:15,694][87424] Updated weights for policy 0, policy_version 398649 (0.0011) -[2023-11-28 10:40:16,030][87426] Updated weights for policy 1, policy_version 398360 (0.0010) -[2023-11-28 10:40:18,004][87426] Updated weights for policy 1, policy_version 398370 (0.0008) -[2023-11-28 10:40:18,121][87424] Updated weights for policy 0, policy_version 398659 (0.0011) -[2023-11-28 10:40:18,380][87426] Updated weights for policy 1, policy_version 398380 (0.0010) -[2023-11-28 10:40:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204038144. Throughput: 0: 2621.8, 1: 2730.9. Samples: 204053904. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:18,445][86177] Avg episode reward: [(0, '-536.580'), (1, '-519.680')] -[2023-11-28 10:40:18,504][87424] Updated weights for policy 0, policy_version 398669 (0.0011) -[2023-11-28 10:40:18,753][87426] Updated weights for policy 1, policy_version 398390 (0.0010) -[2023-11-28 10:40:18,886][87424] Updated weights for policy 0, policy_version 398679 (0.0011) -[2023-11-28 10:40:19,129][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000398400_101990400.pth... -[2023-11-28 10:40:19,131][87426] Updated weights for policy 1, policy_version 398400 (0.0011) -[2023-11-28 10:40:19,171][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000395840_101335040.pth -[2023-11-28 10:40:19,225][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000398688_102064128.pth... -[2023-11-28 10:40:19,272][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000396192_101425152.pth -[2023-11-28 10:40:21,151][87424] Updated weights for policy 0, policy_version 398689 (0.0011) -[2023-11-28 10:40:21,234][87426] Updated weights for policy 1, policy_version 398410 (0.0009) -[2023-11-28 10:40:21,538][87424] Updated weights for policy 0, policy_version 398699 (0.0010) -[2023-11-28 10:40:21,608][87426] Updated weights for policy 1, policy_version 398420 (0.0011) -[2023-11-28 10:40:21,920][87424] Updated weights for policy 0, policy_version 398709 (0.0011) -[2023-11-28 10:40:21,987][87426] Updated weights for policy 1, policy_version 398430 (0.0012) -[2023-11-28 10:40:22,302][87424] Updated weights for policy 0, policy_version 398719 (0.0012) -[2023-11-28 10:40:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204070912. Throughput: 0: 2615.0, 1: 2730.6. Samples: 204086224. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:23,445][86177] Avg episode reward: [(0, '-549.730'), (1, '-524.100')] -[2023-11-28 10:40:24,376][87426] Updated weights for policy 1, policy_version 398440 (0.0010) -[2023-11-28 10:40:24,487][87424] Updated weights for policy 0, policy_version 398729 (0.0011) -[2023-11-28 10:40:24,756][87426] Updated weights for policy 1, policy_version 398450 (0.0012) -[2023-11-28 10:40:24,870][87424] Updated weights for policy 0, policy_version 398739 (0.0011) -[2023-11-28 10:40:25,142][87426] Updated weights for policy 1, policy_version 398460 (0.0012) -[2023-11-28 10:40:25,257][87424] Updated weights for policy 0, policy_version 398749 (0.0011) -[2023-11-28 10:40:27,353][87424] Updated weights for policy 0, policy_version 398759 (0.0009) -[2023-11-28 10:40:27,504][87426] Updated weights for policy 1, policy_version 398470 (0.0012) -[2023-11-28 10:40:27,731][87424] Updated weights for policy 0, policy_version 398769 (0.0008) -[2023-11-28 10:40:27,875][87426] Updated weights for policy 1, policy_version 398480 (0.0009) -[2023-11-28 10:40:28,104][87424] Updated weights for policy 0, policy_version 398779 (0.0008) -[2023-11-28 10:40:28,258][87426] Updated weights for policy 1, policy_version 398490 (0.0007) -[2023-11-28 10:40:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204095488. Throughput: 0: 2628.8, 1: 2747.9. Samples: 204111736. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:28,445][86177] Avg episode reward: [(0, '-559.710'), (1, '-522.920')] -[2023-11-28 10:40:30,087][87426] Updated weights for policy 1, policy_version 398500 (0.0009) -[2023-11-28 10:40:30,242][87424] Updated weights for policy 0, policy_version 398789 (0.0009) -[2023-11-28 10:40:30,471][87426] Updated weights for policy 1, policy_version 398510 (0.0011) -[2023-11-28 10:40:30,622][87424] Updated weights for policy 0, policy_version 398799 (0.0010) -[2023-11-28 10:40:30,847][87426] Updated weights for policy 1, policy_version 398520 (0.0008) -[2023-11-28 10:40:30,995][87424] Updated weights for policy 0, policy_version 398809 (0.0008) -[2023-11-28 10:40:32,940][87426] Updated weights for policy 1, policy_version 398530 (0.0009) -[2023-11-28 10:40:33,055][87424] Updated weights for policy 0, policy_version 398819 (0.0009) -[2023-11-28 10:40:33,321][87426] Updated weights for policy 1, policy_version 398540 (0.0011) -[2023-11-28 10:40:33,432][87424] Updated weights for policy 0, policy_version 398829 (0.0012) -[2023-11-28 10:40:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 204120064. Throughput: 0: 2646.1, 1: 2749.0. Samples: 204136240. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:33,445][86177] Avg episode reward: [(0, '-565.680'), (1, '-517.800')] -[2023-11-28 10:40:33,692][87426] Updated weights for policy 1, policy_version 398550 (0.0010) -[2023-11-28 10:40:33,817][87424] Updated weights for policy 0, policy_version 398839 (0.0012) -[2023-11-28 10:40:34,070][87426] Updated weights for policy 1, policy_version 398560 (0.0011) -[2023-11-28 10:40:35,800][87424] Updated weights for policy 0, policy_version 398849 (0.0012) -[2023-11-28 10:40:36,184][87424] Updated weights for policy 0, policy_version 398859 (0.0011) -[2023-11-28 10:40:36,449][87426] Updated weights for policy 1, policy_version 398570 (0.0009) -[2023-11-28 10:40:36,560][87424] Updated weights for policy 0, policy_version 398869 (0.0008) -[2023-11-28 10:40:36,834][87426] Updated weights for policy 1, policy_version 398580 (0.0010) -[2023-11-28 10:40:36,945][87424] Updated weights for policy 0, policy_version 398879 (0.0010) -[2023-11-28 10:40:37,206][87426] Updated weights for policy 1, policy_version 398590 (0.0012) -[2023-11-28 10:40:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204152832. Throughput: 0: 2694.5, 1: 2735.4. Samples: 204169008. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:38,445][86177] Avg episode reward: [(0, '-596.650'), (1, '-513.350')] -[2023-11-28 10:40:38,928][87424] Updated weights for policy 0, policy_version 398889 (0.0010) -[2023-11-28 10:40:39,316][87424] Updated weights for policy 0, policy_version 398899 (0.0010) -[2023-11-28 10:40:39,663][87426] Updated weights for policy 1, policy_version 398600 (0.0011) -[2023-11-28 10:40:39,685][87424] Updated weights for policy 0, policy_version 398909 (0.0010) -[2023-11-28 10:40:40,046][87426] Updated weights for policy 1, policy_version 398610 (0.0012) -[2023-11-28 10:40:40,428][87426] Updated weights for policy 1, policy_version 398620 (0.0012) -[2023-11-28 10:40:41,926][87424] Updated weights for policy 0, policy_version 398919 (0.0018) -[2023-11-28 10:40:42,302][87424] Updated weights for policy 0, policy_version 398929 (0.0011) -[2023-11-28 10:40:42,613][87426] Updated weights for policy 1, policy_version 398630 (0.0009) -[2023-11-28 10:40:42,686][87424] Updated weights for policy 0, policy_version 398939 (0.0011) -[2023-11-28 10:40:42,991][87426] Updated weights for policy 1, policy_version 398640 (0.0010) -[2023-11-28 10:40:43,374][87426] Updated weights for policy 1, policy_version 398650 (0.0008) -[2023-11-28 10:40:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204177408. Throughput: 0: 2712.6, 1: 2734.3. Samples: 204193708. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:43,445][86177] Avg episode reward: [(0, '-586.000'), (1, '-537.540')] -[2023-11-28 10:40:44,873][87424] Updated weights for policy 0, policy_version 398949 (0.0012) -[2023-11-28 10:40:45,250][87424] Updated weights for policy 0, policy_version 398959 (0.0012) -[2023-11-28 10:40:45,626][87426] Updated weights for policy 1, policy_version 398660 (0.0009) -[2023-11-28 10:40:45,632][87424] Updated weights for policy 0, policy_version 398969 (0.0012) -[2023-11-28 10:40:46,018][87426] Updated weights for policy 1, policy_version 398670 (0.0011) -[2023-11-28 10:40:46,385][87426] Updated weights for policy 1, policy_version 398680 (0.0008) -[2023-11-28 10:40:48,033][87424] Updated weights for policy 0, policy_version 398979 (0.0009) -[2023-11-28 10:40:48,066][87426] Updated weights for policy 1, policy_version 398690 (0.0010) -[2023-11-28 10:40:48,417][87424] Updated weights for policy 0, policy_version 398989 (0.0010) -[2023-11-28 10:40:48,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204201984. Throughput: 0: 2718.7, 1: 2725.3. Samples: 204217904. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:48,445][86177] Avg episode reward: [(0, '-571.310'), (1, '-537.700')] -[2023-11-28 10:40:48,456][87426] Updated weights for policy 1, policy_version 398700 (0.0010) -[2023-11-28 10:40:48,801][87424] Updated weights for policy 0, policy_version 398999 (0.0008) -[2023-11-28 10:40:48,843][87426] Updated weights for policy 1, policy_version 398710 (0.0011) -[2023-11-28 10:40:49,217][87426] Updated weights for policy 1, policy_version 398720 (0.0010) -[2023-11-28 10:40:51,285][87426] Updated weights for policy 1, policy_version 398730 (0.0011) -[2023-11-28 10:40:51,301][87424] Updated weights for policy 0, policy_version 399009 (0.0011) -[2023-11-28 10:40:51,655][87426] Updated weights for policy 1, policy_version 398740 (0.0012) -[2023-11-28 10:40:51,673][87424] Updated weights for policy 0, policy_version 399019 (0.0011) -[2023-11-28 10:40:52,032][87426] Updated weights for policy 1, policy_version 398750 (0.0012) -[2023-11-28 10:40:52,058][87424] Updated weights for policy 0, policy_version 399029 (0.0010) -[2023-11-28 10:40:52,452][87424] Updated weights for policy 0, policy_version 399039 (0.0010) -[2023-11-28 10:40:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204234752. Throughput: 0: 2705.8, 1: 2717.2. Samples: 204249328. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:53,445][86177] Avg episode reward: [(0, '-569.820'), (1, '-537.420')] -[2023-11-28 10:40:54,208][87426] Updated weights for policy 1, policy_version 398760 (0.0011) -[2023-11-28 10:40:54,581][87426] Updated weights for policy 1, policy_version 398770 (0.0009) -[2023-11-28 10:40:54,706][87424] Updated weights for policy 0, policy_version 399049 (0.0011) -[2023-11-28 10:40:54,967][87426] Updated weights for policy 1, policy_version 398780 (0.0007) -[2023-11-28 10:40:55,090][87424] Updated weights for policy 0, policy_version 399059 (0.0012) -[2023-11-28 10:40:55,472][87424] Updated weights for policy 0, policy_version 399069 (0.0009) -[2023-11-28 10:40:57,142][87426] Updated weights for policy 1, policy_version 398790 (0.0010) -[2023-11-28 10:40:57,335][87424] Updated weights for policy 0, policy_version 399079 (0.0007) -[2023-11-28 10:40:57,528][87426] Updated weights for policy 1, policy_version 398800 (0.0011) -[2023-11-28 10:40:57,724][87424] Updated weights for policy 0, policy_version 399089 (0.0008) -[2023-11-28 10:40:57,907][87426] Updated weights for policy 1, policy_version 398810 (0.0011) -[2023-11-28 10:40:58,099][87424] Updated weights for policy 0, policy_version 399099 (0.0008) -[2023-11-28 10:40:58,444][86177] Fps is (10 sec: 6553.7, 60 sec: 5597.9, 300 sec: 5415.0). Total num frames: 204267520. Throughput: 0: 2691.5, 1: 2754.7. Samples: 204274372. Policy #0 lag: (min: 31.0, avg: 36.8, max: 63.0) -[2023-11-28 10:40:58,445][86177] Avg episode reward: [(0, '-544.730'), (1, '-532.140')] -[2023-11-28 10:40:59,605][87426] Updated weights for policy 1, policy_version 398820 (0.0012) -[2023-11-28 10:40:59,994][87426] Updated weights for policy 1, policy_version 398830 (0.0010) -[2023-11-28 10:41:00,302][87424] Updated weights for policy 0, policy_version 399109 (0.0010) -[2023-11-28 10:41:00,371][87426] Updated weights for policy 1, policy_version 398840 (0.0009) -[2023-11-28 10:41:00,668][87424] Updated weights for policy 0, policy_version 399119 (0.0009) -[2023-11-28 10:41:01,062][87424] Updated weights for policy 0, policy_version 399129 (0.0009) -[2023-11-28 10:41:02,927][87426] Updated weights for policy 1, policy_version 398850 (0.0011) -[2023-11-28 10:41:03,312][87426] Updated weights for policy 1, policy_version 398860 (0.0009) -[2023-11-28 10:41:03,409][87424] Updated weights for policy 0, policy_version 399139 (0.0012) -[2023-11-28 10:41:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204283904. Throughput: 0: 2727.5, 1: 2745.9. Samples: 204300204. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:03,445][86177] Avg episode reward: [(0, '-542.090'), (1, '-509.440')] -[2023-11-28 10:41:03,679][87426] Updated weights for policy 1, policy_version 398870 (0.0008) -[2023-11-28 10:41:03,782][87424] Updated weights for policy 0, policy_version 399149 (0.0012) -[2023-11-28 10:41:04,055][87426] Updated weights for policy 1, policy_version 398880 (0.0010) -[2023-11-28 10:41:04,165][87424] Updated weights for policy 0, policy_version 399159 (0.0011) -[2023-11-28 10:41:06,079][87426] Updated weights for policy 1, policy_version 398890 (0.0012) -[2023-11-28 10:41:06,182][87424] Updated weights for policy 0, policy_version 399169 (0.0011) -[2023-11-28 10:41:06,458][87426] Updated weights for policy 1, policy_version 398900 (0.0009) -[2023-11-28 10:41:06,576][87424] Updated weights for policy 0, policy_version 399179 (0.0010) -[2023-11-28 10:41:06,845][87426] Updated weights for policy 1, policy_version 398910 (0.0008) -[2023-11-28 10:41:06,955][87424] Updated weights for policy 0, policy_version 399189 (0.0010) -[2023-11-28 10:41:07,329][87424] Updated weights for policy 0, policy_version 399199 (0.0011) -[2023-11-28 10:41:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 204316672. Throughput: 0: 2734.0, 1: 2747.0. Samples: 204332868. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:08,445][86177] Avg episode reward: [(0, '-556.950'), (1, '-526.640')] -[2023-11-28 10:41:08,622][87426] Updated weights for policy 1, policy_version 398920 (0.0007) -[2023-11-28 10:41:08,994][87426] Updated weights for policy 1, policy_version 398930 (0.0009) -[2023-11-28 10:41:09,372][87426] Updated weights for policy 1, policy_version 398940 (0.0009) -[2023-11-28 10:41:09,663][87424] Updated weights for policy 0, policy_version 399209 (0.0009) -[2023-11-28 10:41:10,045][87424] Updated weights for policy 0, policy_version 399219 (0.0010) -[2023-11-28 10:41:10,441][87424] Updated weights for policy 0, policy_version 399229 (0.0009) -[2023-11-28 10:41:11,753][87426] Updated weights for policy 1, policy_version 398950 (0.0011) -[2023-11-28 10:41:12,131][87426] Updated weights for policy 1, policy_version 398960 (0.0012) -[2023-11-28 10:41:12,511][87426] Updated weights for policy 1, policy_version 398970 (0.0011) -[2023-11-28 10:41:12,675][87424] Updated weights for policy 0, policy_version 399239 (0.0012) -[2023-11-28 10:41:13,054][87424] Updated weights for policy 0, policy_version 399249 (0.0012) -[2023-11-28 10:41:13,443][87424] Updated weights for policy 0, policy_version 399259 (0.0009) -[2023-11-28 10:41:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204341248. Throughput: 0: 2725.3, 1: 2731.2. Samples: 204357280. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:13,445][86177] Avg episode reward: [(0, '-553.980'), (1, '-525.430')] -[2023-11-28 10:41:14,553][87426] Updated weights for policy 1, policy_version 398980 (0.0011) -[2023-11-28 10:41:14,943][87426] Updated weights for policy 1, policy_version 398990 (0.0008) -[2023-11-28 10:41:15,319][87426] Updated weights for policy 1, policy_version 399000 (0.0009) -[2023-11-28 10:41:15,556][87424] Updated weights for policy 0, policy_version 399269 (0.0012) -[2023-11-28 10:41:15,941][87424] Updated weights for policy 0, policy_version 399279 (0.0011) -[2023-11-28 10:41:16,336][87424] Updated weights for policy 0, policy_version 399289 (0.0012) -[2023-11-28 10:41:17,348][87426] Updated weights for policy 1, policy_version 399010 (0.0011) -[2023-11-28 10:41:17,733][87426] Updated weights for policy 1, policy_version 399020 (0.0012) -[2023-11-28 10:41:18,101][87426] Updated weights for policy 1, policy_version 399030 (0.0012) -[2023-11-28 10:41:18,363][87424] Updated weights for policy 0, policy_version 399299 (0.0012) -[2023-11-28 10:41:18,445][86177] Fps is (10 sec: 4915.0, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204365824. Throughput: 0: 2722.5, 1: 2736.9. Samples: 204381916. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:18,446][86177] Avg episode reward: [(0, '-542.160'), (1, '-524.910')] -[2023-11-28 10:41:18,479][87426] Updated weights for policy 1, policy_version 399040 (0.0012) -[2023-11-28 10:41:18,755][87424] Updated weights for policy 0, policy_version 399309 (0.0009) -[2023-11-28 10:41:19,129][87424] Updated weights for policy 0, policy_version 399319 (0.0010) -[2023-11-28 10:41:20,452][87426] Updated weights for policy 1, policy_version 399050 (0.0010) -[2023-11-28 10:41:20,830][87426] Updated weights for policy 1, policy_version 399060 (0.0008) -[2023-11-28 10:41:21,214][87426] Updated weights for policy 1, policy_version 399070 (0.0008) -[2023-11-28 10:41:21,550][87424] Updated weights for policy 0, policy_version 399329 (0.0011) -[2023-11-28 10:41:21,940][87424] Updated weights for policy 0, policy_version 399339 (0.0011) -[2023-11-28 10:41:22,329][87424] Updated weights for policy 0, policy_version 399349 (0.0012) -[2023-11-28 10:41:22,716][87424] Updated weights for policy 0, policy_version 399359 (0.0012) -[2023-11-28 10:41:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204398592. Throughput: 0: 2699.3, 1: 2740.7. Samples: 204413808. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:23,445][86177] Avg episode reward: [(0, '-527.040'), (1, '-547.700')] -[2023-11-28 10:41:23,793][87426] Updated weights for policy 1, policy_version 399080 (0.0010) -[2023-11-28 10:41:24,172][87426] Updated weights for policy 1, policy_version 399090 (0.0008) -[2023-11-28 10:41:24,556][87426] Updated weights for policy 1, policy_version 399100 (0.0009) -[2023-11-28 10:41:25,113][87424] Updated weights for policy 0, policy_version 399369 (0.0011) -[2023-11-28 10:41:25,497][87424] Updated weights for policy 0, policy_version 399379 (0.0008) -[2023-11-28 10:41:25,885][87424] Updated weights for policy 0, policy_version 399389 (0.0007) -[2023-11-28 10:41:26,440][87426] Updated weights for policy 1, policy_version 399110 (0.0011) -[2023-11-28 10:41:26,813][87426] Updated weights for policy 1, policy_version 399120 (0.0012) -[2023-11-28 10:41:27,209][87426] Updated weights for policy 1, policy_version 399130 (0.0012) -[2023-11-28 10:41:28,376][87424] Updated weights for policy 0, policy_version 399399 (0.0007) -[2023-11-28 10:41:28,444][86177] Fps is (10 sec: 5734.7, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204423168. Throughput: 0: 2691.0, 1: 2745.2. Samples: 204438336. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:28,445][86177] Avg episode reward: [(0, '-513.060'), (1, '-528.990')] -[2023-11-28 10:41:28,748][87424] Updated weights for policy 0, policy_version 399409 (0.0007) -[2023-11-28 10:41:29,128][87424] Updated weights for policy 0, policy_version 399419 (0.0008) -[2023-11-28 10:41:29,762][87426] Updated weights for policy 1, policy_version 399140 (0.0011) -[2023-11-28 10:41:30,137][87426] Updated weights for policy 1, policy_version 399150 (0.0010) -[2023-11-28 10:41:30,512][87426] Updated weights for policy 1, policy_version 399160 (0.0010) -[2023-11-28 10:41:31,147][87424] Updated weights for policy 0, policy_version 399429 (0.0010) -[2023-11-28 10:41:31,524][87424] Updated weights for policy 0, policy_version 399439 (0.0008) -[2023-11-28 10:41:31,908][87424] Updated weights for policy 0, policy_version 399449 (0.0010) -[2023-11-28 10:41:32,669][87426] Updated weights for policy 1, policy_version 399170 (0.0010) -[2023-11-28 10:41:33,051][87426] Updated weights for policy 1, policy_version 399180 (0.0011) -[2023-11-28 10:41:33,433][87426] Updated weights for policy 1, policy_version 399190 (0.0010) -[2023-11-28 10:41:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204447744. Throughput: 0: 2687.2, 1: 2748.8. Samples: 204462524. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:33,445][86177] Avg episode reward: [(0, '-508.600'), (1, '-532.060')] -[2023-11-28 10:41:33,810][87426] Updated weights for policy 1, policy_version 399200 (0.0007) -[2023-11-28 10:41:34,093][87424] Updated weights for policy 0, policy_version 399459 (0.0012) -[2023-11-28 10:41:34,470][87424] Updated weights for policy 0, policy_version 399469 (0.0012) -[2023-11-28 10:41:34,850][87424] Updated weights for policy 0, policy_version 399479 (0.0011) -[2023-11-28 10:41:36,176][87426] Updated weights for policy 1, policy_version 399210 (0.0010) -[2023-11-28 10:41:36,557][87426] Updated weights for policy 1, policy_version 399220 (0.0012) -[2023-11-28 10:41:36,703][87424] Updated weights for policy 0, policy_version 399489 (0.0011) -[2023-11-28 10:41:36,945][87426] Updated weights for policy 1, policy_version 399230 (0.0012) -[2023-11-28 10:41:37,093][87424] Updated weights for policy 0, policy_version 399499 (0.0011) -[2023-11-28 10:41:37,473][87424] Updated weights for policy 0, policy_version 399509 (0.0010) -[2023-11-28 10:41:37,847][87424] Updated weights for policy 0, policy_version 399519 (0.0012) -[2023-11-28 10:41:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204480512. Throughput: 0: 2715.6, 1: 2763.3. Samples: 204495876. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:38,445][86177] Avg episode reward: [(0, '-526.220'), (1, '-534.670')] -[2023-11-28 10:41:39,316][87426] Updated weights for policy 1, policy_version 399240 (0.0011) -[2023-11-28 10:41:39,608][87424] Updated weights for policy 0, policy_version 399529 (0.0012) -[2023-11-28 10:41:39,694][87426] Updated weights for policy 1, policy_version 399250 (0.0011) -[2023-11-28 10:41:39,992][87424] Updated weights for policy 0, policy_version 399539 (0.0011) -[2023-11-28 10:41:40,076][87426] Updated weights for policy 1, policy_version 399260 (0.0014) -[2023-11-28 10:41:40,370][87424] Updated weights for policy 0, policy_version 399549 (0.0010) -[2023-11-28 10:41:42,568][87426] Updated weights for policy 1, policy_version 399270 (0.0011) -[2023-11-28 10:41:42,879][87424] Updated weights for policy 0, policy_version 399559 (0.0010) -[2023-11-28 10:41:42,946][87426] Updated weights for policy 1, policy_version 399280 (0.0012) -[2023-11-28 10:41:43,260][87424] Updated weights for policy 0, policy_version 399569 (0.0011) -[2023-11-28 10:41:43,324][87426] Updated weights for policy 1, policy_version 399290 (0.0011) -[2023-11-28 10:41:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 204496896. Throughput: 0: 2714.7, 1: 2730.1. Samples: 204519388. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:43,445][86177] Avg episode reward: [(0, '-533.060'), (1, '-513.970')] -[2023-11-28 10:41:43,643][87424] Updated weights for policy 0, policy_version 399579 (0.0010) -[2023-11-28 10:41:45,222][87426] Updated weights for policy 1, policy_version 399300 (0.0010) -[2023-11-28 10:41:45,603][87426] Updated weights for policy 1, policy_version 399310 (0.0010) -[2023-11-28 10:41:45,985][87426] Updated weights for policy 1, policy_version 399320 (0.0008) -[2023-11-28 10:41:46,114][87424] Updated weights for policy 0, policy_version 399589 (0.0008) -[2023-11-28 10:41:46,490][87424] Updated weights for policy 0, policy_version 399599 (0.0010) -[2023-11-28 10:41:46,874][87424] Updated weights for policy 0, policy_version 399609 (0.0009) -[2023-11-28 10:41:47,997][87426] Updated weights for policy 1, policy_version 399330 (0.0010) -[2023-11-28 10:41:48,388][87426] Updated weights for policy 1, policy_version 399340 (0.0011) -[2023-11-28 10:41:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 204529664. Throughput: 0: 2654.3, 1: 2740.9. Samples: 204542988. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:48,445][86177] Avg episode reward: [(0, '-543.660'), (1, '-520.680')] -[2023-11-28 10:41:48,755][87426] Updated weights for policy 1, policy_version 399350 (0.0012) -[2023-11-28 10:41:48,851][87424] Updated weights for policy 0, policy_version 399619 (0.0009) -[2023-11-28 10:41:49,149][87426] Updated weights for policy 1, policy_version 399360 (0.0009) -[2023-11-28 10:41:49,231][87424] Updated weights for policy 0, policy_version 399629 (0.0009) -[2023-11-28 10:41:49,619][87424] Updated weights for policy 0, policy_version 399639 (0.0008) -[2023-11-28 10:41:51,647][87426] Updated weights for policy 1, policy_version 399370 (0.0008) -[2023-11-28 10:41:52,011][87424] Updated weights for policy 0, policy_version 399649 (0.0010) -[2023-11-28 10:41:52,019][87426] Updated weights for policy 1, policy_version 399380 (0.0010) -[2023-11-28 10:41:52,397][87424] Updated weights for policy 0, policy_version 399659 (0.0009) -[2023-11-28 10:41:52,397][87426] Updated weights for policy 1, policy_version 399390 (0.0010) -[2023-11-28 10:41:52,781][87424] Updated weights for policy 0, policy_version 399669 (0.0009) -[2023-11-28 10:41:53,170][87424] Updated weights for policy 0, policy_version 399679 (0.0012) -[2023-11-28 10:41:53,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204562432. Throughput: 0: 2647.8, 1: 2718.1. Samples: 204574336. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:53,445][86177] Avg episode reward: [(0, '-557.340'), (1, '-531.290')] -[2023-11-28 10:41:54,965][87426] Updated weights for policy 1, policy_version 399400 (0.0012) -[2023-11-28 10:41:55,348][87426] Updated weights for policy 1, policy_version 399410 (0.0010) -[2023-11-28 10:41:55,456][87424] Updated weights for policy 0, policy_version 399689 (0.0008) -[2023-11-28 10:41:55,723][87426] Updated weights for policy 1, policy_version 399420 (0.0011) -[2023-11-28 10:41:55,838][87424] Updated weights for policy 0, policy_version 399699 (0.0008) -[2023-11-28 10:41:56,218][87424] Updated weights for policy 0, policy_version 399709 (0.0012) -[2023-11-28 10:41:57,461][87426] Updated weights for policy 1, policy_version 399430 (0.0009) -[2023-11-28 10:41:57,847][87426] Updated weights for policy 1, policy_version 399440 (0.0008) -[2023-11-28 10:41:58,228][87426] Updated weights for policy 1, policy_version 399450 (0.0011) -[2023-11-28 10:41:58,253][87424] Updated weights for policy 0, policy_version 399719 (0.0009) -[2023-11-28 10:41:58,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 204578816. Throughput: 0: 2663.1, 1: 2706.0. Samples: 204598892. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:41:58,445][86177] Avg episode reward: [(0, '-610.880'), (1, '-536.160')] -[2023-11-28 10:41:58,641][87424] Updated weights for policy 0, policy_version 399729 (0.0011) -[2023-11-28 10:41:59,011][87424] Updated weights for policy 0, policy_version 399739 (0.0012) -[2023-11-28 10:41:59,979][87426] Updated weights for policy 1, policy_version 399460 (0.0016) -[2023-11-28 10:42:00,361][87426] Updated weights for policy 1, policy_version 399470 (0.0011) -[2023-11-28 10:42:00,737][87426] Updated weights for policy 1, policy_version 399480 (0.0012) -[2023-11-28 10:42:01,218][87424] Updated weights for policy 0, policy_version 399749 (0.0009) -[2023-11-28 10:42:01,604][87424] Updated weights for policy 0, policy_version 399759 (0.0008) -[2023-11-28 10:42:01,990][87424] Updated weights for policy 0, policy_version 399769 (0.0010) -[2023-11-28 10:42:03,204][87426] Updated weights for policy 1, policy_version 399490 (0.0010) -[2023-11-28 10:42:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204611584. Throughput: 0: 2683.8, 1: 2686.7. Samples: 204623588. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:42:03,445][86177] Avg episode reward: [(0, '-612.140'), (1, '-580.020')] -[2023-11-28 10:42:03,584][87426] Updated weights for policy 1, policy_version 399500 (0.0008) -[2023-11-28 10:42:03,969][87426] Updated weights for policy 1, policy_version 399510 (0.0011) -[2023-11-28 10:42:04,036][87424] Updated weights for policy 0, policy_version 399779 (0.0011) -[2023-11-28 10:42:04,348][87426] Updated weights for policy 1, policy_version 399520 (0.0008) -[2023-11-28 10:42:04,419][87424] Updated weights for policy 0, policy_version 399789 (0.0009) -[2023-11-28 10:42:04,798][87424] Updated weights for policy 0, policy_version 399799 (0.0010) -[2023-11-28 10:42:06,649][87424] Updated weights for policy 0, policy_version 399809 (0.0012) -[2023-11-28 10:42:06,832][87426] Updated weights for policy 1, policy_version 399530 (0.0011) -[2023-11-28 10:42:07,021][87424] Updated weights for policy 0, policy_version 399819 (0.0009) -[2023-11-28 10:42:07,207][87426] Updated weights for policy 1, policy_version 399540 (0.0009) -[2023-11-28 10:42:07,405][87424] Updated weights for policy 0, policy_version 399829 (0.0009) -[2023-11-28 10:42:07,591][87426] Updated weights for policy 1, policy_version 399550 (0.0010) -[2023-11-28 10:42:07,794][87424] Updated weights for policy 0, policy_version 399839 (0.0011) -[2023-11-28 10:42:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 204644352. Throughput: 0: 2694.2, 1: 2668.1. Samples: 204655112. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:42:08,445][86177] Avg episode reward: [(0, '-637.760'), (1, '-568.870')] -[2023-11-28 10:42:09,769][87426] Updated weights for policy 1, policy_version 399560 (0.0011) -[2023-11-28 10:42:09,951][87424] Updated weights for policy 0, policy_version 399849 (0.0010) -[2023-11-28 10:42:10,146][87426] Updated weights for policy 1, policy_version 399570 (0.0016) -[2023-11-28 10:42:10,333][87424] Updated weights for policy 0, policy_version 399859 (0.0008) -[2023-11-28 10:42:10,528][87426] Updated weights for policy 1, policy_version 399580 (0.0012) -[2023-11-28 10:42:10,728][87424] Updated weights for policy 0, policy_version 399869 (0.0010) -[2023-11-28 10:42:12,871][87426] Updated weights for policy 1, policy_version 399590 (0.0011) -[2023-11-28 10:42:13,249][87426] Updated weights for policy 1, policy_version 399600 (0.0012) -[2023-11-28 10:42:13,383][87424] Updated weights for policy 0, policy_version 399879 (0.0009) -[2023-11-28 10:42:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 204660736. Throughput: 0: 2679.8, 1: 2667.2. Samples: 204678952. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:42:13,445][86177] Avg episode reward: [(0, '-636.970'), (1, '-562.000')] -[2023-11-28 10:42:13,623][87426] Updated weights for policy 1, policy_version 399610 (0.0009) -[2023-11-28 10:42:13,756][87424] Updated weights for policy 0, policy_version 399889 (0.0010) -[2023-11-28 10:42:14,136][87424] Updated weights for policy 0, policy_version 399899 (0.0010) -[2023-11-28 10:42:16,170][87426] Updated weights for policy 1, policy_version 399620 (0.0009) -[2023-11-28 10:42:16,565][87426] Updated weights for policy 1, policy_version 399630 (0.0010) -[2023-11-28 10:42:16,723][87424] Updated weights for policy 0, policy_version 399909 (0.0008) -[2023-11-28 10:42:16,937][87426] Updated weights for policy 1, policy_version 399640 (0.0012) -[2023-11-28 10:42:17,114][87424] Updated weights for policy 0, policy_version 399919 (0.0008) -[2023-11-28 10:42:17,499][87424] Updated weights for policy 0, policy_version 399929 (0.0008) -[2023-11-28 10:42:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 204693504. Throughput: 0: 2657.7, 1: 2670.8. Samples: 204702308. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:42:18,445][86177] Avg episode reward: [(0, '-593.720'), (1, '-558.230')] -[2023-11-28 10:42:18,455][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000399648_102309888.pth... -[2023-11-28 10:42:18,455][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000399936_102383616.pth... -[2023-11-28 10:42:18,499][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000397120_101662720.pth -[2023-11-28 10:42:18,503][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000397440_101744640.pth -[2023-11-28 10:42:18,819][87426] Updated weights for policy 1, policy_version 399650 (0.0012) -[2023-11-28 10:42:19,210][87426] Updated weights for policy 1, policy_version 399660 (0.0012) -[2023-11-28 10:42:19,586][87426] Updated weights for policy 1, policy_version 399670 (0.0012) -[2023-11-28 10:42:19,862][87424] Updated weights for policy 0, policy_version 399939 (0.0009) -[2023-11-28 10:42:19,962][87426] Updated weights for policy 1, policy_version 399680 (0.0011) -[2023-11-28 10:42:20,240][87424] Updated weights for policy 0, policy_version 399949 (0.0011) -[2023-11-28 10:42:20,624][87424] Updated weights for policy 0, policy_version 399959 (0.0011) -[2023-11-28 10:42:22,151][87426] Updated weights for policy 1, policy_version 399690 (0.0012) -[2023-11-28 10:42:22,531][87426] Updated weights for policy 1, policy_version 399700 (0.0014) -[2023-11-28 10:42:22,910][87426] Updated weights for policy 1, policy_version 399710 (0.0011) -[2023-11-28 10:42:23,083][87424] Updated weights for policy 0, policy_version 399969 (0.0011) -[2023-11-28 10:42:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204718080. Throughput: 0: 2640.2, 1: 2668.6. Samples: 204734772. Policy #0 lag: (min: 31.0, avg: 39.2, max: 63.0) -[2023-11-28 10:42:23,445][86177] Avg episode reward: [(0, '-574.820'), (1, '-521.140')] -[2023-11-28 10:42:23,470][87424] Updated weights for policy 0, policy_version 399979 (0.0012) -[2023-11-28 10:42:23,858][87424] Updated weights for policy 0, policy_version 399989 (0.0012) -[2023-11-28 10:42:24,231][87424] Updated weights for policy 0, policy_version 399999 (0.0012) -[2023-11-28 10:42:24,873][87426] Updated weights for policy 1, policy_version 399720 (0.0012) -[2023-11-28 10:42:25,255][87426] Updated weights for policy 1, policy_version 399730 (0.0011) -[2023-11-28 10:42:25,621][87426] Updated weights for policy 1, policy_version 399740 (0.0011) -[2023-11-28 10:42:26,619][87424] Updated weights for policy 0, policy_version 400009 (0.0011) -[2023-11-28 10:42:26,994][87424] Updated weights for policy 0, policy_version 400019 (0.0009) -[2023-11-28 10:42:27,377][87424] Updated weights for policy 0, policy_version 400029 (0.0008) -[2023-11-28 10:42:28,080][87426] Updated weights for policy 1, policy_version 399750 (0.0009) -[2023-11-28 10:42:28,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204742656. Throughput: 0: 2644.3, 1: 2685.1. Samples: 204759208. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:42:28,445][86177] Avg episode reward: [(0, '-563.890'), (1, '-527.340')] -[2023-11-28 10:42:28,455][87426] Updated weights for policy 1, policy_version 399760 (0.0007) -[2023-11-28 10:42:28,842][87426] Updated weights for policy 1, policy_version 399770 (0.0007) -[2023-11-28 10:42:29,106][87424] Updated weights for policy 0, policy_version 400039 (0.0008) -[2023-11-28 10:42:29,486][87424] Updated weights for policy 0, policy_version 400049 (0.0007) -[2023-11-28 10:42:29,868][87424] Updated weights for policy 0, policy_version 400059 (0.0008) -[2023-11-28 10:42:31,367][87426] Updated weights for policy 1, policy_version 399780 (0.0010) -[2023-11-28 10:42:31,745][87426] Updated weights for policy 1, policy_version 399790 (0.0011) -[2023-11-28 10:42:32,128][87426] Updated weights for policy 1, policy_version 399800 (0.0013) -[2023-11-28 10:42:32,219][87424] Updated weights for policy 0, policy_version 400069 (0.0010) -[2023-11-28 10:42:32,610][87424] Updated weights for policy 0, policy_version 400079 (0.0009) -[2023-11-28 10:42:33,001][87424] Updated weights for policy 0, policy_version 400089 (0.0008) -[2023-11-28 10:42:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 204775424. Throughput: 0: 2699.9, 1: 2662.9. Samples: 204784316. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:42:33,445][86177] Avg episode reward: [(0, '-579.750'), (1, '-526.950')] -[2023-11-28 10:42:34,341][87426] Updated weights for policy 1, policy_version 399810 (0.0012) -[2023-11-28 10:42:34,715][87426] Updated weights for policy 1, policy_version 399820 (0.0009) -[2023-11-28 10:42:35,073][87424] Updated weights for policy 0, policy_version 400099 (0.0008) -[2023-11-28 10:42:35,097][87426] Updated weights for policy 1, policy_version 399830 (0.0009) -[2023-11-28 10:42:35,454][87424] Updated weights for policy 0, policy_version 400109 (0.0011) -[2023-11-28 10:42:35,471][87426] Updated weights for policy 1, policy_version 399840 (0.0010) -[2023-11-28 10:42:35,848][87424] Updated weights for policy 0, policy_version 400119 (0.0012) -[2023-11-28 10:42:37,205][87426] Updated weights for policy 1, policy_version 399850 (0.0012) -[2023-11-28 10:42:37,584][87426] Updated weights for policy 1, policy_version 399860 (0.0009) -[2023-11-28 10:42:37,960][87426] Updated weights for policy 1, policy_version 399870 (0.0010) -[2023-11-28 10:42:38,191][87424] Updated weights for policy 0, policy_version 400129 (0.0009) -[2023-11-28 10:42:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204800000. Throughput: 0: 2703.3, 1: 2676.3. Samples: 204816420. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:42:38,446][86177] Avg episode reward: [(0, '-583.730'), (1, '-531.730')] -[2023-11-28 10:42:38,576][87424] Updated weights for policy 0, policy_version 400139 (0.0011) -[2023-11-28 10:42:38,964][87424] Updated weights for policy 0, policy_version 400149 (0.0011) -[2023-11-28 10:42:39,337][87424] Updated weights for policy 0, policy_version 400159 (0.0011) -[2023-11-28 10:42:40,443][87426] Updated weights for policy 1, policy_version 399880 (0.0009) -[2023-11-28 10:42:40,830][87426] Updated weights for policy 1, policy_version 399890 (0.0013) -[2023-11-28 10:42:41,209][87426] Updated weights for policy 1, policy_version 399900 (0.0012) -[2023-11-28 10:42:41,644][87424] Updated weights for policy 0, policy_version 400169 (0.0010) -[2023-11-28 10:42:42,017][87424] Updated weights for policy 0, policy_version 400179 (0.0011) -[2023-11-28 10:42:42,397][87424] Updated weights for policy 0, policy_version 400189 (0.0013) -[2023-11-28 10:42:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 204824576. Throughput: 0: 2675.8, 1: 2654.8. Samples: 204838768. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:42:43,445][86177] Avg episode reward: [(0, '-562.170'), (1, '-526.660')] -[2023-11-28 10:42:43,770][87426] Updated weights for policy 1, policy_version 399910 (0.0009) -[2023-11-28 10:42:44,152][87426] Updated weights for policy 1, policy_version 399920 (0.0007) -[2023-11-28 10:42:44,530][87426] Updated weights for policy 1, policy_version 399930 (0.0007) -[2023-11-28 10:42:44,628][87424] Updated weights for policy 0, policy_version 400199 (0.0011) -[2023-11-28 10:42:45,024][87424] Updated weights for policy 0, policy_version 400209 (0.0012) -[2023-11-28 10:42:45,395][87424] Updated weights for policy 0, policy_version 400219 (0.0011) -[2023-11-28 10:42:46,522][87426] Updated weights for policy 1, policy_version 399940 (0.0011) -[2023-11-28 10:42:46,901][87426] Updated weights for policy 1, policy_version 399950 (0.0012) -[2023-11-28 10:42:47,289][87426] Updated weights for policy 1, policy_version 399960 (0.0012) -[2023-11-28 10:42:47,707][87424] Updated weights for policy 0, policy_version 400229 (0.0010) -[2023-11-28 10:42:48,087][87424] Updated weights for policy 0, policy_version 400239 (0.0012) -[2023-11-28 10:42:48,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204849152. Throughput: 0: 2650.8, 1: 2665.2. Samples: 204862812. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:42:48,445][86177] Avg episode reward: [(0, '-546.820'), (1, '-524.960')] -[2023-11-28 10:42:48,471][87424] Updated weights for policy 0, policy_version 400249 (0.0012) -[2023-11-28 10:42:49,599][87426] Updated weights for policy 1, policy_version 399970 (0.0012) -[2023-11-28 10:42:49,992][87426] Updated weights for policy 1, policy_version 399980 (0.0012) -[2023-11-28 10:42:50,365][87426] Updated weights for policy 1, policy_version 399990 (0.0012) -[2023-11-28 10:42:50,595][87424] Updated weights for policy 0, policy_version 400259 (0.0012) -[2023-11-28 10:42:50,740][87426] Updated weights for policy 1, policy_version 400000 (0.0010) -[2023-11-28 10:42:50,975][87424] Updated weights for policy 0, policy_version 400269 (0.0012) -[2023-11-28 10:42:51,357][87424] Updated weights for policy 0, policy_version 400279 (0.0012) -[2023-11-28 10:42:52,874][87426] Updated weights for policy 1, policy_version 400010 (0.0012) -[2023-11-28 10:42:53,260][87426] Updated weights for policy 1, policy_version 400020 (0.0008) -[2023-11-28 10:42:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 204873728. Throughput: 0: 2651.6, 1: 2680.4. Samples: 204895052. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:42:53,445][86177] Avg episode reward: [(0, '-512.670'), (1, '-522.550')] -[2023-11-28 10:42:53,636][87426] Updated weights for policy 1, policy_version 400030 (0.0011) -[2023-11-28 10:42:53,893][87424] Updated weights for policy 0, policy_version 400289 (0.0012) -[2023-11-28 10:42:54,282][87424] Updated weights for policy 0, policy_version 400299 (0.0012) -[2023-11-28 10:42:54,663][87424] Updated weights for policy 0, policy_version 400309 (0.0011) -[2023-11-28 10:42:55,055][87424] Updated weights for policy 0, policy_version 400319 (0.0011) -[2023-11-28 10:42:56,161][87426] Updated weights for policy 1, policy_version 400040 (0.0010) -[2023-11-28 10:42:56,542][87426] Updated weights for policy 1, policy_version 400050 (0.0009) -[2023-11-28 10:42:56,921][87426] Updated weights for policy 1, policy_version 400060 (0.0007) -[2023-11-28 10:42:57,420][87424] Updated weights for policy 0, policy_version 400329 (0.0011) -[2023-11-28 10:42:57,801][87424] Updated weights for policy 0, policy_version 400339 (0.0012) -[2023-11-28 10:42:58,183][87424] Updated weights for policy 0, policy_version 400349 (0.0011) -[2023-11-28 10:42:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 204906496. Throughput: 0: 2654.2, 1: 2693.2. Samples: 204919584. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:42:58,445][86177] Avg episode reward: [(0, '-507.340'), (1, '-523.230')] -[2023-11-28 10:42:58,495][87426] Updated weights for policy 1, policy_version 400070 (0.0009) -[2023-11-28 10:42:58,874][87426] Updated weights for policy 1, policy_version 400080 (0.0012) -[2023-11-28 10:42:59,252][87426] Updated weights for policy 1, policy_version 400090 (0.0007) -[2023-11-28 10:43:00,147][87424] Updated weights for policy 0, policy_version 400359 (0.0011) -[2023-11-28 10:43:00,522][87424] Updated weights for policy 0, policy_version 400369 (0.0011) -[2023-11-28 10:43:00,903][87424] Updated weights for policy 0, policy_version 400379 (0.0012) -[2023-11-28 10:43:01,596][87426] Updated weights for policy 1, policy_version 400100 (0.0009) -[2023-11-28 10:43:01,967][87426] Updated weights for policy 1, policy_version 400110 (0.0012) -[2023-11-28 10:43:02,349][87426] Updated weights for policy 1, policy_version 400120 (0.0010) -[2023-11-28 10:43:02,942][87424] Updated weights for policy 0, policy_version 400389 (0.0011) -[2023-11-28 10:43:03,326][87424] Updated weights for policy 0, policy_version 400399 (0.0011) -[2023-11-28 10:43:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 204931072. Throughput: 0: 2675.1, 1: 2680.8. Samples: 204943324. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:43:03,445][86177] Avg episode reward: [(0, '-509.370'), (1, '-521.890')] -[2023-11-28 10:43:03,704][87424] Updated weights for policy 0, policy_version 400409 (0.0010) -[2023-11-28 10:43:04,837][87426] Updated weights for policy 1, policy_version 400130 (0.0011) -[2023-11-28 10:43:05,231][87426] Updated weights for policy 1, policy_version 400140 (0.0009) -[2023-11-28 10:43:05,610][87426] Updated weights for policy 1, policy_version 400150 (0.0008) -[2023-11-28 10:43:05,889][87424] Updated weights for policy 0, policy_version 400419 (0.0009) -[2023-11-28 10:43:05,987][87426] Updated weights for policy 1, policy_version 400160 (0.0008) -[2023-11-28 10:43:06,275][87424] Updated weights for policy 0, policy_version 400429 (0.0011) -[2023-11-28 10:43:06,670][87424] Updated weights for policy 0, policy_version 400439 (0.0010) -[2023-11-28 10:43:08,393][87426] Updated weights for policy 1, policy_version 400170 (0.0012) -[2023-11-28 10:43:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5387.3). Total num frames: 204955648. Throughput: 0: 2678.4, 1: 2655.6. Samples: 204974804. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:43:08,445][86177] Avg episode reward: [(0, '-512.500'), (1, '-535.680')] -[2023-11-28 10:43:08,766][87426] Updated weights for policy 1, policy_version 400180 (0.0012) -[2023-11-28 10:43:09,121][87424] Updated weights for policy 0, policy_version 400449 (0.0010) -[2023-11-28 10:43:09,145][87426] Updated weights for policy 1, policy_version 400190 (0.0012) -[2023-11-28 10:43:09,506][87424] Updated weights for policy 0, policy_version 400459 (0.0011) -[2023-11-28 10:43:09,890][87424] Updated weights for policy 0, policy_version 400469 (0.0012) -[2023-11-28 10:43:10,262][87424] Updated weights for policy 0, policy_version 400479 (0.0012) -[2023-11-28 10:43:11,138][87426] Updated weights for policy 1, policy_version 400200 (0.0009) -[2023-11-28 10:43:11,520][87426] Updated weights for policy 1, policy_version 400210 (0.0007) -[2023-11-28 10:43:11,907][87426] Updated weights for policy 1, policy_version 400220 (0.0014) -[2023-11-28 10:43:12,393][87424] Updated weights for policy 0, policy_version 400489 (0.0011) -[2023-11-28 10:43:12,777][87424] Updated weights for policy 0, policy_version 400499 (0.0012) -[2023-11-28 10:43:13,164][87424] Updated weights for policy 0, policy_version 400509 (0.0012) -[2023-11-28 10:43:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5415.1). Total num frames: 204988416. Throughput: 0: 2665.2, 1: 2650.0. Samples: 204998392. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:43:13,445][86177] Avg episode reward: [(0, '-520.150'), (1, '-532.930')] -[2023-11-28 10:43:14,194][87426] Updated weights for policy 1, policy_version 400230 (0.0011) -[2023-11-28 10:43:14,565][87426] Updated weights for policy 1, policy_version 400240 (0.0012) -[2023-11-28 10:43:14,945][87426] Updated weights for policy 1, policy_version 400250 (0.0012) -[2023-11-28 10:43:14,990][87424] Updated weights for policy 0, policy_version 400519 (0.0012) -[2023-11-28 10:43:15,368][87424] Updated weights for policy 0, policy_version 400529 (0.0011) -[2023-11-28 10:43:15,746][87424] Updated weights for policy 0, policy_version 400539 (0.0012) -[2023-11-28 10:43:17,320][87426] Updated weights for policy 1, policy_version 400260 (0.0012) -[2023-11-28 10:43:17,707][87426] Updated weights for policy 1, policy_version 400270 (0.0012) -[2023-11-28 10:43:18,079][87426] Updated weights for policy 1, policy_version 400280 (0.0012) -[2023-11-28 10:43:18,266][87424] Updated weights for policy 0, policy_version 400549 (0.0010) -[2023-11-28 10:43:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205012992. Throughput: 0: 2638.7, 1: 2659.8. Samples: 205022752. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:43:18,445][86177] Avg episode reward: [(0, '-522.840'), (1, '-532.280')] -[2023-11-28 10:43:18,656][87424] Updated weights for policy 0, policy_version 400559 (0.0008) -[2023-11-28 10:43:19,039][87424] Updated weights for policy 0, policy_version 400569 (0.0008) -[2023-11-28 10:43:20,470][87426] Updated weights for policy 1, policy_version 400290 (0.0012) -[2023-11-28 10:43:20,845][87426] Updated weights for policy 1, policy_version 400300 (0.0012) -[2023-11-28 10:43:21,220][87426] Updated weights for policy 1, policy_version 400310 (0.0012) -[2023-11-28 10:43:21,244][87424] Updated weights for policy 0, policy_version 400579 (0.0008) -[2023-11-28 10:43:21,595][87426] Updated weights for policy 1, policy_version 400320 (0.0011) -[2023-11-28 10:43:21,625][87424] Updated weights for policy 0, policy_version 400589 (0.0010) -[2023-11-28 10:43:22,016][87424] Updated weights for policy 0, policy_version 400599 (0.0010) -[2023-11-28 10:43:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205037568. Throughput: 0: 2639.9, 1: 2652.5. Samples: 205054576. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:43:23,445][86177] Avg episode reward: [(0, '-524.280'), (1, '-534.560')] -[2023-11-28 10:43:24,151][87426] Updated weights for policy 1, policy_version 400330 (0.0008) -[2023-11-28 10:43:24,405][87424] Updated weights for policy 0, policy_version 400609 (0.0010) -[2023-11-28 10:43:24,534][87426] Updated weights for policy 1, policy_version 400340 (0.0009) -[2023-11-28 10:43:24,782][87424] Updated weights for policy 0, policy_version 400619 (0.0012) -[2023-11-28 10:43:24,910][87426] Updated weights for policy 1, policy_version 400350 (0.0011) -[2023-11-28 10:43:25,168][87424] Updated weights for policy 0, policy_version 400629 (0.0011) -[2023-11-28 10:43:25,551][87424] Updated weights for policy 0, policy_version 400639 (0.0011) -[2023-11-28 10:43:26,558][87426] Updated weights for policy 1, policy_version 400360 (0.0012) -[2023-11-28 10:43:26,937][87426] Updated weights for policy 1, policy_version 400370 (0.0007) -[2023-11-28 10:43:27,324][87426] Updated weights for policy 1, policy_version 400380 (0.0008) -[2023-11-28 10:43:27,821][87424] Updated weights for policy 0, policy_version 400649 (0.0008) -[2023-11-28 10:43:28,209][87424] Updated weights for policy 0, policy_version 400659 (0.0007) -[2023-11-28 10:43:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205062144. Throughput: 0: 2650.7, 1: 2696.3. Samples: 205079384. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:43:28,445][86177] Avg episode reward: [(0, '-520.180'), (1, '-519.710')] -[2023-11-28 10:43:28,587][87424] Updated weights for policy 0, policy_version 400669 (0.0007) -[2023-11-28 10:43:29,621][87426] Updated weights for policy 1, policy_version 400390 (0.0009) -[2023-11-28 10:43:30,001][87426] Updated weights for policy 1, policy_version 400400 (0.0009) -[2023-11-28 10:43:30,388][87426] Updated weights for policy 1, policy_version 400410 (0.0008) -[2023-11-28 10:43:31,000][87424] Updated weights for policy 0, policy_version 400679 (0.0008) -[2023-11-28 10:43:31,378][87424] Updated weights for policy 0, policy_version 400689 (0.0008) -[2023-11-28 10:43:31,756][87424] Updated weights for policy 0, policy_version 400699 (0.0010) -[2023-11-28 10:43:32,861][87426] Updated weights for policy 1, policy_version 400420 (0.0008) -[2023-11-28 10:43:33,236][87426] Updated weights for policy 1, policy_version 400430 (0.0011) -[2023-11-28 10:43:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 205086720. Throughput: 0: 2658.0, 1: 2685.0. Samples: 205103244. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:43:33,445][86177] Avg episode reward: [(0, '-518.760'), (1, '-518.720')] -[2023-11-28 10:43:33,624][87426] Updated weights for policy 1, policy_version 400440 (0.0008) -[2023-11-28 10:43:33,782][87424] Updated weights for policy 0, policy_version 400709 (0.0010) -[2023-11-28 10:43:34,168][87424] Updated weights for policy 0, policy_version 400719 (0.0007) -[2023-11-28 10:43:34,555][87424] Updated weights for policy 0, policy_version 400729 (0.0007) -[2023-11-28 10:43:36,011][87426] Updated weights for policy 1, policy_version 400450 (0.0010) -[2023-11-28 10:43:36,395][87426] Updated weights for policy 1, policy_version 400460 (0.0012) -[2023-11-28 10:43:36,719][87424] Updated weights for policy 0, policy_version 400739 (0.0010) -[2023-11-28 10:43:36,789][87426] Updated weights for policy 1, policy_version 400470 (0.0011) -[2023-11-28 10:43:37,104][87424] Updated weights for policy 0, policy_version 400749 (0.0008) -[2023-11-28 10:43:37,160][87426] Updated weights for policy 1, policy_version 400480 (0.0011) -[2023-11-28 10:43:37,488][87424] Updated weights for policy 0, policy_version 400759 (0.0008) -[2023-11-28 10:43:38,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205119488. Throughput: 0: 2662.5, 1: 2669.8. Samples: 205135004. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:43:38,445][86177] Avg episode reward: [(0, '-515.720'), (1, '-514.920')] -[2023-11-28 10:43:39,514][87426] Updated weights for policy 1, policy_version 400490 (0.0011) -[2023-11-28 10:43:39,892][87426] Updated weights for policy 1, policy_version 400500 (0.0019) -[2023-11-28 10:43:39,982][87424] Updated weights for policy 0, policy_version 400769 (0.0011) -[2023-11-28 10:43:40,272][87426] Updated weights for policy 1, policy_version 400510 (0.0011) -[2023-11-28 10:43:40,361][87424] Updated weights for policy 0, policy_version 400779 (0.0012) -[2023-11-28 10:43:40,740][87424] Updated weights for policy 0, policy_version 400789 (0.0011) -[2023-11-28 10:43:41,112][87424] Updated weights for policy 0, policy_version 400799 (0.0012) -[2023-11-28 10:43:42,189][87426] Updated weights for policy 1, policy_version 400520 (0.0011) -[2023-11-28 10:43:42,572][87426] Updated weights for policy 1, policy_version 400530 (0.0012) -[2023-11-28 10:43:42,943][87426] Updated weights for policy 1, policy_version 400540 (0.0012) -[2023-11-28 10:43:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205144064. Throughput: 0: 2652.6, 1: 2640.0. Samples: 205157752. Policy #0 lag: (min: 18.0, avg: 45.2, max: 56.0) -[2023-11-28 10:43:43,445][86177] Avg episode reward: [(0, '-525.780'), (1, '-511.730')] -[2023-11-28 10:43:43,719][87424] Updated weights for policy 0, policy_version 400809 (0.0012) -[2023-11-28 10:43:44,086][87424] Updated weights for policy 0, policy_version 400819 (0.0012) -[2023-11-28 10:43:44,473][87424] Updated weights for policy 0, policy_version 400829 (0.0012) -[2023-11-28 10:43:44,778][87426] Updated weights for policy 1, policy_version 400550 (0.0011) -[2023-11-28 10:43:45,152][87426] Updated weights for policy 1, policy_version 400560 (0.0008) -[2023-11-28 10:43:45,528][87426] Updated weights for policy 1, policy_version 400570 (0.0010) -[2023-11-28 10:43:46,628][87424] Updated weights for policy 0, policy_version 400839 (0.0012) -[2023-11-28 10:43:47,033][87424] Updated weights for policy 0, policy_version 400849 (0.0012) -[2023-11-28 10:43:47,410][87424] Updated weights for policy 0, policy_version 400859 (0.0011) -[2023-11-28 10:43:48,010][87426] Updated weights for policy 1, policy_version 400580 (0.0011) -[2023-11-28 10:43:48,391][87426] Updated weights for policy 1, policy_version 400590 (0.0012) -[2023-11-28 10:43:48,444][86177] Fps is (10 sec: 4915.0, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205168640. Throughput: 0: 2639.8, 1: 2654.7. Samples: 205181576. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:43:48,446][86177] Avg episode reward: [(0, '-526.380'), (1, '-513.880')] -[2023-11-28 10:43:48,764][87426] Updated weights for policy 1, policy_version 400600 (0.0011) -[2023-11-28 10:43:49,718][87424] Updated weights for policy 0, policy_version 400869 (0.0011) -[2023-11-28 10:43:50,097][87424] Updated weights for policy 0, policy_version 400879 (0.0011) -[2023-11-28 10:43:50,478][87424] Updated weights for policy 0, policy_version 400889 (0.0013) -[2023-11-28 10:43:50,572][87426] Updated weights for policy 1, policy_version 400610 (0.0011) -[2023-11-28 10:43:50,956][87426] Updated weights for policy 1, policy_version 400620 (0.0009) -[2023-11-28 10:43:51,334][87426] Updated weights for policy 1, policy_version 400630 (0.0008) -[2023-11-28 10:43:51,719][87426] Updated weights for policy 1, policy_version 400640 (0.0009) -[2023-11-28 10:43:52,926][87424] Updated weights for policy 0, policy_version 400899 (0.0012) -[2023-11-28 10:43:53,305][87424] Updated weights for policy 0, policy_version 400909 (0.0012) -[2023-11-28 10:43:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205193216. Throughput: 0: 2630.0, 1: 2681.3. Samples: 205213816. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:43:53,445][86177] Avg episode reward: [(0, '-532.790'), (1, '-510.820')] -[2023-11-28 10:43:53,687][87424] Updated weights for policy 0, policy_version 400919 (0.0012) -[2023-11-28 10:43:54,348][87426] Updated weights for policy 1, policy_version 400650 (0.0012) -[2023-11-28 10:43:54,724][87426] Updated weights for policy 1, policy_version 400660 (0.0012) -[2023-11-28 10:43:55,115][87426] Updated weights for policy 1, policy_version 400670 (0.0012) -[2023-11-28 10:43:55,578][87424] Updated weights for policy 0, policy_version 400929 (0.0012) -[2023-11-28 10:43:55,978][87424] Updated weights for policy 0, policy_version 400939 (0.0012) -[2023-11-28 10:43:56,352][87424] Updated weights for policy 0, policy_version 400949 (0.0009) -[2023-11-28 10:43:56,737][87424] Updated weights for policy 0, policy_version 400959 (0.0008) -[2023-11-28 10:43:56,827][87426] Updated weights for policy 1, policy_version 400680 (0.0010) -[2023-11-28 10:43:57,209][87426] Updated weights for policy 1, policy_version 400690 (0.0007) -[2023-11-28 10:43:57,589][87426] Updated weights for policy 1, policy_version 400700 (0.0008) -[2023-11-28 10:43:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205225984. Throughput: 0: 2641.6, 1: 2695.8. Samples: 205238576. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:43:58,445][86177] Avg episode reward: [(0, '-541.240'), (1, '-514.790')] -[2023-11-28 10:43:58,764][87424] Updated weights for policy 0, policy_version 400969 (0.0008) -[2023-11-28 10:43:59,150][87424] Updated weights for policy 0, policy_version 400979 (0.0009) -[2023-11-28 10:43:59,235][87426] Updated weights for policy 1, policy_version 400710 (0.0010) -[2023-11-28 10:43:59,538][87424] Updated weights for policy 0, policy_version 400989 (0.0008) -[2023-11-28 10:43:59,612][87426] Updated weights for policy 1, policy_version 400720 (0.0010) -[2023-11-28 10:44:00,002][87426] Updated weights for policy 1, policy_version 400730 (0.0009) -[2023-11-28 10:44:01,640][87424] Updated weights for policy 0, policy_version 400999 (0.0011) -[2023-11-28 10:44:02,026][87424] Updated weights for policy 0, policy_version 401009 (0.0012) -[2023-11-28 10:44:02,403][87424] Updated weights for policy 0, policy_version 401019 (0.0011) -[2023-11-28 10:44:02,434][87426] Updated weights for policy 1, policy_version 400740 (0.0010) -[2023-11-28 10:44:02,814][87426] Updated weights for policy 1, policy_version 400750 (0.0012) -[2023-11-28 10:44:03,203][87426] Updated weights for policy 1, policy_version 400760 (0.0012) -[2023-11-28 10:44:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205250560. Throughput: 0: 2662.0, 1: 2693.3. Samples: 205263744. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:03,445][86177] Avg episode reward: [(0, '-529.950'), (1, '-526.140')] -[2023-11-28 10:44:04,615][87424] Updated weights for policy 0, policy_version 401029 (0.0010) -[2023-11-28 10:44:04,980][87426] Updated weights for policy 1, policy_version 400770 (0.0011) -[2023-11-28 10:44:05,002][87424] Updated weights for policy 0, policy_version 401039 (0.0011) -[2023-11-28 10:44:05,355][87426] Updated weights for policy 1, policy_version 400780 (0.0009) -[2023-11-28 10:44:05,386][87424] Updated weights for policy 0, policy_version 401049 (0.0011) -[2023-11-28 10:44:05,735][87426] Updated weights for policy 1, policy_version 400790 (0.0007) -[2023-11-28 10:44:06,113][87426] Updated weights for policy 1, policy_version 400800 (0.0008) -[2023-11-28 10:44:07,624][87424] Updated weights for policy 0, policy_version 401059 (0.0010) -[2023-11-28 10:44:08,011][87424] Updated weights for policy 0, policy_version 401069 (0.0009) -[2023-11-28 10:44:08,393][87424] Updated weights for policy 0, policy_version 401079 (0.0008) -[2023-11-28 10:44:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205275136. Throughput: 0: 2666.2, 1: 2708.5. Samples: 205296440. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:08,445][86177] Avg episode reward: [(0, '-537.400'), (1, '-526.120')] -[2023-11-28 10:44:08,573][87426] Updated weights for policy 1, policy_version 400810 (0.0007) -[2023-11-28 10:44:08,957][87426] Updated weights for policy 1, policy_version 400820 (0.0012) -[2023-11-28 10:44:09,339][87426] Updated weights for policy 1, policy_version 400830 (0.0012) -[2023-11-28 10:44:10,390][87424] Updated weights for policy 0, policy_version 401089 (0.0008) -[2023-11-28 10:44:10,772][87424] Updated weights for policy 0, policy_version 401099 (0.0012) -[2023-11-28 10:44:11,154][87424] Updated weights for policy 0, policy_version 401109 (0.0012) -[2023-11-28 10:44:11,534][87424] Updated weights for policy 0, policy_version 401119 (0.0011) -[2023-11-28 10:44:11,600][87426] Updated weights for policy 1, policy_version 400840 (0.0009) -[2023-11-28 10:44:11,980][87426] Updated weights for policy 1, policy_version 400850 (0.0009) -[2023-11-28 10:44:12,354][87426] Updated weights for policy 1, policy_version 400860 (0.0011) -[2023-11-28 10:44:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205307904. Throughput: 0: 2659.6, 1: 2683.6. Samples: 205319824. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:13,445][86177] Avg episode reward: [(0, '-526.620'), (1, '-534.300')] -[2023-11-28 10:44:14,082][87424] Updated weights for policy 0, policy_version 401129 (0.0012) -[2023-11-28 10:44:14,465][87424] Updated weights for policy 0, policy_version 401139 (0.0012) -[2023-11-28 10:44:14,515][87426] Updated weights for policy 1, policy_version 400870 (0.0011) -[2023-11-28 10:44:14,851][87424] Updated weights for policy 0, policy_version 401149 (0.0011) -[2023-11-28 10:44:14,893][87426] Updated weights for policy 1, policy_version 400880 (0.0008) -[2023-11-28 10:44:15,271][87426] Updated weights for policy 1, policy_version 400890 (0.0011) -[2023-11-28 10:44:17,289][87424] Updated weights for policy 0, policy_version 401159 (0.0008) -[2023-11-28 10:44:17,668][87424] Updated weights for policy 0, policy_version 401169 (0.0007) -[2023-11-28 10:44:17,710][87426] Updated weights for policy 1, policy_version 400900 (0.0010) -[2023-11-28 10:44:18,057][87424] Updated weights for policy 0, policy_version 401179 (0.0007) -[2023-11-28 10:44:18,084][87426] Updated weights for policy 1, policy_version 400910 (0.0011) -[2023-11-28 10:44:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205332480. Throughput: 0: 2653.5, 1: 2699.2. Samples: 205344116. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:18,445][86177] Avg episode reward: [(0, '-521.330'), (1, '-531.820')] -[2023-11-28 10:44:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000401184_102703104.pth... -[2023-11-28 10:44:18,463][87426] Updated weights for policy 1, policy_version 400920 (0.0011) -[2023-11-28 10:44:18,482][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000398688_102064128.pth -[2023-11-28 10:44:18,767][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000400928_102637568.pth... -[2023-11-28 10:44:18,798][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000398400_101990400.pth -[2023-11-28 10:44:20,287][87424] Updated weights for policy 0, policy_version 401189 (0.0011) -[2023-11-28 10:44:20,675][87424] Updated weights for policy 0, policy_version 401199 (0.0011) -[2023-11-28 10:44:20,712][87426] Updated weights for policy 1, policy_version 400930 (0.0011) -[2023-11-28 10:44:21,058][87424] Updated weights for policy 0, policy_version 401209 (0.0010) -[2023-11-28 10:44:21,093][87426] Updated weights for policy 1, policy_version 400940 (0.0012) -[2023-11-28 10:44:21,465][87426] Updated weights for policy 1, policy_version 400950 (0.0012) -[2023-11-28 10:44:21,847][87426] Updated weights for policy 1, policy_version 400960 (0.0012) -[2023-11-28 10:44:23,315][87424] Updated weights for policy 0, policy_version 401219 (0.0011) -[2023-11-28 10:44:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205357056. Throughput: 0: 2629.0, 1: 2723.1. Samples: 205375848. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:23,445][86177] Avg episode reward: [(0, '-524.690'), (1, '-521.600')] -[2023-11-28 10:44:23,693][87424] Updated weights for policy 0, policy_version 401229 (0.0012) -[2023-11-28 10:44:24,011][87426] Updated weights for policy 1, policy_version 400970 (0.0012) -[2023-11-28 10:44:24,080][87424] Updated weights for policy 0, policy_version 401239 (0.0012) -[2023-11-28 10:44:24,385][87426] Updated weights for policy 1, policy_version 400980 (0.0012) -[2023-11-28 10:44:24,767][87426] Updated weights for policy 1, policy_version 400990 (0.0011) -[2023-11-28 10:44:26,174][87424] Updated weights for policy 0, policy_version 401249 (0.0009) -[2023-11-28 10:44:26,557][87424] Updated weights for policy 0, policy_version 401259 (0.0012) -[2023-11-28 10:44:26,943][87424] Updated weights for policy 0, policy_version 401269 (0.0012) -[2023-11-28 10:44:27,166][87426] Updated weights for policy 1, policy_version 401000 (0.0012) -[2023-11-28 10:44:27,320][87424] Updated weights for policy 0, policy_version 401279 (0.0011) -[2023-11-28 10:44:27,539][87426] Updated weights for policy 1, policy_version 401010 (0.0012) -[2023-11-28 10:44:27,918][87426] Updated weights for policy 1, policy_version 401020 (0.0012) -[2023-11-28 10:44:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 205389824. Throughput: 0: 2662.0, 1: 2735.6. Samples: 205400648. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:28,445][86177] Avg episode reward: [(0, '-529.870'), (1, '-517.180')] -[2023-11-28 10:44:28,998][87424] Updated weights for policy 0, policy_version 401289 (0.0012) -[2023-11-28 10:44:29,381][87424] Updated weights for policy 0, policy_version 401299 (0.0009) -[2023-11-28 10:44:29,773][87424] Updated weights for policy 0, policy_version 401309 (0.0010) -[2023-11-28 10:44:30,263][87426] Updated weights for policy 1, policy_version 401030 (0.0012) -[2023-11-28 10:44:30,636][87426] Updated weights for policy 1, policy_version 401040 (0.0012) -[2023-11-28 10:44:31,012][87426] Updated weights for policy 1, policy_version 401050 (0.0012) -[2023-11-28 10:44:32,075][87424] Updated weights for policy 0, policy_version 401319 (0.0012) -[2023-11-28 10:44:32,451][87424] Updated weights for policy 0, policy_version 401329 (0.0012) -[2023-11-28 10:44:32,835][87424] Updated weights for policy 0, policy_version 401339 (0.0012) -[2023-11-28 10:44:33,403][87426] Updated weights for policy 1, policy_version 401060 (0.0012) -[2023-11-28 10:44:33,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 205414400. Throughput: 0: 2692.2, 1: 2720.8. Samples: 205425160. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:33,445][86177] Avg episode reward: [(0, '-535.180'), (1, '-521.220')] -[2023-11-28 10:44:33,779][87426] Updated weights for policy 1, policy_version 401070 (0.0012) -[2023-11-28 10:44:34,144][87426] Updated weights for policy 1, policy_version 401080 (0.0012) -[2023-11-28 10:44:34,880][87424] Updated weights for policy 0, policy_version 401349 (0.0012) -[2023-11-28 10:44:35,272][87424] Updated weights for policy 0, policy_version 401359 (0.0016) -[2023-11-28 10:44:35,645][87424] Updated weights for policy 0, policy_version 401369 (0.0010) -[2023-11-28 10:44:36,230][87426] Updated weights for policy 1, policy_version 401090 (0.0012) -[2023-11-28 10:44:36,613][87426] Updated weights for policy 1, policy_version 401100 (0.0009) -[2023-11-28 10:44:36,996][87426] Updated weights for policy 1, policy_version 401110 (0.0011) -[2023-11-28 10:44:37,377][87426] Updated weights for policy 1, policy_version 401120 (0.0010) -[2023-11-28 10:44:37,934][87424] Updated weights for policy 0, policy_version 401379 (0.0010) -[2023-11-28 10:44:38,309][87424] Updated weights for policy 0, policy_version 401389 (0.0012) -[2023-11-28 10:44:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205438976. Throughput: 0: 2715.9, 1: 2716.0. Samples: 205458252. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:38,445][86177] Avg episode reward: [(0, '-533.640'), (1, '-516.040')] -[2023-11-28 10:44:38,698][87424] Updated weights for policy 0, policy_version 401399 (0.0012) -[2023-11-28 10:44:39,478][87426] Updated weights for policy 1, policy_version 401130 (0.0012) -[2023-11-28 10:44:39,858][87426] Updated weights for policy 1, policy_version 401140 (0.0012) -[2023-11-28 10:44:40,238][87426] Updated weights for policy 1, policy_version 401150 (0.0011) -[2023-11-28 10:44:41,017][87424] Updated weights for policy 0, policy_version 401409 (0.0012) -[2023-11-28 10:44:41,401][87424] Updated weights for policy 0, policy_version 401419 (0.0012) -[2023-11-28 10:44:41,780][87424] Updated weights for policy 0, policy_version 401429 (0.0012) -[2023-11-28 10:44:42,163][87424] Updated weights for policy 0, policy_version 401439 (0.0012) -[2023-11-28 10:44:42,584][87426] Updated weights for policy 1, policy_version 401160 (0.0011) -[2023-11-28 10:44:42,955][87426] Updated weights for policy 1, policy_version 401170 (0.0012) -[2023-11-28 10:44:43,344][87426] Updated weights for policy 1, policy_version 401180 (0.0012) -[2023-11-28 10:44:43,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205463552. Throughput: 0: 2705.8, 1: 2690.8. Samples: 205481424. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:43,445][86177] Avg episode reward: [(0, '-547.880'), (1, '-521.390')] -[2023-11-28 10:44:44,563][87424] Updated weights for policy 0, policy_version 401449 (0.0008) -[2023-11-28 10:44:44,953][87424] Updated weights for policy 0, policy_version 401459 (0.0007) -[2023-11-28 10:44:45,345][87424] Updated weights for policy 0, policy_version 401469 (0.0009) -[2023-11-28 10:44:45,603][87426] Updated weights for policy 1, policy_version 401190 (0.0012) -[2023-11-28 10:44:45,988][87426] Updated weights for policy 1, policy_version 401200 (0.0012) -[2023-11-28 10:44:46,362][87426] Updated weights for policy 1, policy_version 401210 (0.0011) -[2023-11-28 10:44:47,139][87424] Updated weights for policy 0, policy_version 401479 (0.0012) -[2023-11-28 10:44:47,520][87424] Updated weights for policy 0, policy_version 401489 (0.0012) -[2023-11-28 10:44:47,909][87424] Updated weights for policy 0, policy_version 401499 (0.0011) -[2023-11-28 10:44:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 205496320. Throughput: 0: 2695.6, 1: 2708.0. Samples: 205506908. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:48,446][86177] Avg episode reward: [(0, '-583.430'), (1, '-518.540')] -[2023-11-28 10:44:48,938][87426] Updated weights for policy 1, policy_version 401220 (0.0011) -[2023-11-28 10:44:49,327][87426] Updated weights for policy 1, policy_version 401230 (0.0011) -[2023-11-28 10:44:49,695][87426] Updated weights for policy 1, policy_version 401240 (0.0011) -[2023-11-28 10:44:50,432][87424] Updated weights for policy 0, policy_version 401509 (0.0010) -[2023-11-28 10:44:50,815][87424] Updated weights for policy 0, policy_version 401519 (0.0011) -[2023-11-28 10:44:51,196][87424] Updated weights for policy 0, policy_version 401529 (0.0011) -[2023-11-28 10:44:51,542][87426] Updated weights for policy 1, policy_version 401250 (0.0011) -[2023-11-28 10:44:51,940][87426] Updated weights for policy 1, policy_version 401260 (0.0010) -[2023-11-28 10:44:52,330][87426] Updated weights for policy 1, policy_version 401270 (0.0011) -[2023-11-28 10:44:52,708][87426] Updated weights for policy 1, policy_version 401280 (0.0011) -[2023-11-28 10:44:53,269][87424] Updated weights for policy 0, policy_version 401539 (0.0011) -[2023-11-28 10:44:53,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 205520896. Throughput: 0: 2679.6, 1: 2675.8. Samples: 205537436. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:53,445][86177] Avg episode reward: [(0, '-566.010'), (1, '-515.600')] -[2023-11-28 10:44:53,646][87424] Updated weights for policy 0, policy_version 401549 (0.0010) -[2023-11-28 10:44:54,029][87424] Updated weights for policy 0, policy_version 401559 (0.0010) -[2023-11-28 10:44:55,181][87426] Updated weights for policy 1, policy_version 401290 (0.0011) -[2023-11-28 10:44:55,566][87426] Updated weights for policy 1, policy_version 401300 (0.0011) -[2023-11-28 10:44:55,946][87426] Updated weights for policy 1, policy_version 401310 (0.0012) -[2023-11-28 10:44:56,498][87424] Updated weights for policy 0, policy_version 401569 (0.0008) -[2023-11-28 10:44:56,882][87424] Updated weights for policy 0, policy_version 401579 (0.0008) -[2023-11-28 10:44:57,268][87424] Updated weights for policy 0, policy_version 401589 (0.0007) -[2023-11-28 10:44:57,649][87424] Updated weights for policy 0, policy_version 401599 (0.0008) -[2023-11-28 10:44:57,772][87426] Updated weights for policy 1, policy_version 401320 (0.0011) -[2023-11-28 10:44:58,150][87426] Updated weights for policy 1, policy_version 401330 (0.0012) -[2023-11-28 10:44:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205545472. Throughput: 0: 2671.1, 1: 2706.3. Samples: 205561808. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:44:58,445][86177] Avg episode reward: [(0, '-573.260'), (1, '-545.400')] -[2023-11-28 10:44:58,529][87426] Updated weights for policy 1, policy_version 401340 (0.0012) -[2023-11-28 10:45:00,219][87424] Updated weights for policy 0, policy_version 401609 (0.0011) -[2023-11-28 10:45:00,495][87426] Updated weights for policy 1, policy_version 401350 (0.0011) -[2023-11-28 10:45:00,610][87424] Updated weights for policy 0, policy_version 401619 (0.0013) -[2023-11-28 10:45:00,868][87426] Updated weights for policy 1, policy_version 401360 (0.0009) -[2023-11-28 10:45:00,989][87424] Updated weights for policy 0, policy_version 401629 (0.0011) -[2023-11-28 10:45:01,250][87426] Updated weights for policy 1, policy_version 401370 (0.0011) -[2023-11-28 10:45:03,440][87426] Updated weights for policy 1, policy_version 401380 (0.0008) -[2023-11-28 10:45:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205570048. Throughput: 0: 2661.7, 1: 2700.3. Samples: 205585404. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:45:03,445][86177] Avg episode reward: [(0, '-557.730'), (1, '-548.720')] -[2023-11-28 10:45:03,484][87424] Updated weights for policy 0, policy_version 401639 (0.0011) -[2023-11-28 10:45:03,826][87426] Updated weights for policy 1, policy_version 401390 (0.0008) -[2023-11-28 10:45:03,856][87424] Updated weights for policy 0, policy_version 401649 (0.0010) -[2023-11-28 10:45:04,204][87426] Updated weights for policy 1, policy_version 401400 (0.0008) -[2023-11-28 10:45:04,248][87424] Updated weights for policy 0, policy_version 401659 (0.0011) -[2023-11-28 10:45:06,069][87424] Updated weights for policy 0, policy_version 401669 (0.0011) -[2023-11-28 10:45:06,337][87426] Updated weights for policy 1, policy_version 401410 (0.0008) -[2023-11-28 10:45:06,454][87424] Updated weights for policy 0, policy_version 401679 (0.0011) -[2023-11-28 10:45:06,727][87426] Updated weights for policy 1, policy_version 401420 (0.0009) -[2023-11-28 10:45:06,833][87424] Updated weights for policy 0, policy_version 401689 (0.0010) -[2023-11-28 10:45:07,094][87426] Updated weights for policy 1, policy_version 401430 (0.0010) -[2023-11-28 10:45:07,471][87426] Updated weights for policy 1, policy_version 401440 (0.0012) -[2023-11-28 10:45:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 205602816. Throughput: 0: 2662.8, 1: 2722.4. Samples: 205618180. Policy #0 lag: (min: 31.0, avg: 40.2, max: 63.0) -[2023-11-28 10:45:08,445][86177] Avg episode reward: [(0, '-530.780'), (1, '-567.330')] -[2023-11-28 10:45:08,632][87424] Updated weights for policy 0, policy_version 401699 (0.0009) -[2023-11-28 10:45:09,032][87424] Updated weights for policy 0, policy_version 401709 (0.0012) -[2023-11-28 10:45:09,419][87424] Updated weights for policy 0, policy_version 401719 (0.0012) -[2023-11-28 10:45:09,880][87426] Updated weights for policy 1, policy_version 401450 (0.0010) -[2023-11-28 10:45:10,264][87426] Updated weights for policy 1, policy_version 401460 (0.0012) -[2023-11-28 10:45:10,640][87426] Updated weights for policy 1, policy_version 401470 (0.0012) -[2023-11-28 10:45:11,537][87424] Updated weights for policy 0, policy_version 401729 (0.0011) -[2023-11-28 10:45:11,918][87424] Updated weights for policy 0, policy_version 401739 (0.0013) -[2023-11-28 10:45:12,309][87424] Updated weights for policy 0, policy_version 401749 (0.0011) -[2023-11-28 10:45:12,695][87424] Updated weights for policy 0, policy_version 401759 (0.0012) -[2023-11-28 10:45:12,879][87426] Updated weights for policy 1, policy_version 401480 (0.0012) -[2023-11-28 10:45:13,262][87426] Updated weights for policy 1, policy_version 401490 (0.0012) -[2023-11-28 10:45:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205627392. Throughput: 0: 2657.7, 1: 2695.7. Samples: 205641552. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:13,445][86177] Avg episode reward: [(0, '-559.850'), (1, '-579.330')] -[2023-11-28 10:45:13,648][87426] Updated weights for policy 1, policy_version 401500 (0.0012) -[2023-11-28 10:45:15,004][87424] Updated weights for policy 0, policy_version 401769 (0.0012) -[2023-11-28 10:45:15,396][87424] Updated weights for policy 0, policy_version 401779 (0.0012) -[2023-11-28 10:45:15,544][87426] Updated weights for policy 1, policy_version 401510 (0.0012) -[2023-11-28 10:45:15,781][87424] Updated weights for policy 0, policy_version 401789 (0.0011) -[2023-11-28 10:45:15,923][87426] Updated weights for policy 1, policy_version 401520 (0.0012) -[2023-11-28 10:45:16,305][87426] Updated weights for policy 1, policy_version 401530 (0.0009) -[2023-11-28 10:45:17,821][87424] Updated weights for policy 0, policy_version 401799 (0.0011) -[2023-11-28 10:45:18,191][87424] Updated weights for policy 0, policy_version 401809 (0.0011) -[2023-11-28 10:45:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205651968. Throughput: 0: 2670.9, 1: 2705.9. Samples: 205667116. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:18,445][86177] Avg episode reward: [(0, '-555.950'), (1, '-582.110')] -[2023-11-28 10:45:18,575][87424] Updated weights for policy 0, policy_version 401819 (0.0012) -[2023-11-28 10:45:18,749][87426] Updated weights for policy 1, policy_version 401540 (0.0008) -[2023-11-28 10:45:19,123][87426] Updated weights for policy 1, policy_version 401550 (0.0008) -[2023-11-28 10:45:19,505][87426] Updated weights for policy 1, policy_version 401560 (0.0008) -[2023-11-28 10:45:20,841][87424] Updated weights for policy 0, policy_version 401829 (0.0012) -[2023-11-28 10:45:21,232][87424] Updated weights for policy 0, policy_version 401839 (0.0012) -[2023-11-28 10:45:21,632][87424] Updated weights for policy 0, policy_version 401849 (0.0011) -[2023-11-28 10:45:21,972][87426] Updated weights for policy 1, policy_version 401570 (0.0012) -[2023-11-28 10:45:22,345][87426] Updated weights for policy 1, policy_version 401580 (0.0010) -[2023-11-28 10:45:22,722][87426] Updated weights for policy 1, policy_version 401590 (0.0008) -[2023-11-28 10:45:23,106][87426] Updated weights for policy 1, policy_version 401600 (0.0009) -[2023-11-28 10:45:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 205684736. Throughput: 0: 2679.6, 1: 2670.8. Samples: 205699024. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:23,445][86177] Avg episode reward: [(0, '-562.420'), (1, '-548.500')] -[2023-11-28 10:45:24,151][87424] Updated weights for policy 0, policy_version 401859 (0.0010) -[2023-11-28 10:45:24,542][87424] Updated weights for policy 0, policy_version 401869 (0.0010) -[2023-11-28 10:45:24,926][87424] Updated weights for policy 0, policy_version 401879 (0.0007) -[2023-11-28 10:45:25,609][87426] Updated weights for policy 1, policy_version 401610 (0.0012) -[2023-11-28 10:45:25,989][87426] Updated weights for policy 1, policy_version 401620 (0.0012) -[2023-11-28 10:45:26,370][87426] Updated weights for policy 1, policy_version 401630 (0.0012) -[2023-11-28 10:45:27,187][87424] Updated weights for policy 0, policy_version 401889 (0.0008) -[2023-11-28 10:45:27,565][87424] Updated weights for policy 0, policy_version 401899 (0.0012) -[2023-11-28 10:45:27,942][87424] Updated weights for policy 0, policy_version 401909 (0.0011) -[2023-11-28 10:45:28,223][87426] Updated weights for policy 1, policy_version 401640 (0.0008) -[2023-11-28 10:45:28,329][87424] Updated weights for policy 0, policy_version 401919 (0.0007) -[2023-11-28 10:45:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 205709312. Throughput: 0: 2686.1, 1: 2702.0. Samples: 205723888. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:28,445][86177] Avg episode reward: [(0, '-598.950'), (1, '-539.480')] -[2023-11-28 10:45:28,609][87426] Updated weights for policy 1, policy_version 401650 (0.0010) -[2023-11-28 10:45:28,992][87426] Updated weights for policy 1, policy_version 401660 (0.0011) -[2023-11-28 10:45:30,238][87424] Updated weights for policy 0, policy_version 401929 (0.0011) -[2023-11-28 10:45:30,625][87424] Updated weights for policy 0, policy_version 401939 (0.0012) -[2023-11-28 10:45:30,999][87424] Updated weights for policy 0, policy_version 401949 (0.0012) -[2023-11-28 10:45:31,318][87426] Updated weights for policy 1, policy_version 401670 (0.0010) -[2023-11-28 10:45:31,706][87426] Updated weights for policy 1, policy_version 401680 (0.0012) -[2023-11-28 10:45:32,089][87426] Updated weights for policy 1, policy_version 401690 (0.0011) -[2023-11-28 10:45:33,438][87424] Updated weights for policy 0, policy_version 401959 (0.0011) -[2023-11-28 10:45:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205733888. Throughput: 0: 2679.2, 1: 2686.9. Samples: 205748384. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:33,445][86177] Avg episode reward: [(0, '-591.690'), (1, '-529.160')] -[2023-11-28 10:45:33,826][87424] Updated weights for policy 0, policy_version 401969 (0.0012) -[2023-11-28 10:45:34,214][87424] Updated weights for policy 0, policy_version 401979 (0.0012) -[2023-11-28 10:45:34,661][87426] Updated weights for policy 1, policy_version 401700 (0.0012) -[2023-11-28 10:45:35,036][87426] Updated weights for policy 1, policy_version 401710 (0.0012) -[2023-11-28 10:45:35,416][87426] Updated weights for policy 1, policy_version 401720 (0.0012) -[2023-11-28 10:45:36,459][87424] Updated weights for policy 0, policy_version 401989 (0.0010) -[2023-11-28 10:45:36,854][87424] Updated weights for policy 0, policy_version 401999 (0.0011) -[2023-11-28 10:45:37,226][87424] Updated weights for policy 0, policy_version 402009 (0.0012) -[2023-11-28 10:45:37,749][87426] Updated weights for policy 1, policy_version 401730 (0.0012) -[2023-11-28 10:45:38,136][87426] Updated weights for policy 1, policy_version 401740 (0.0008) -[2023-11-28 10:45:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205758464. Throughput: 0: 2693.6, 1: 2707.2. Samples: 205780472. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:38,445][86177] Avg episode reward: [(0, '-592.800'), (1, '-535.170')] -[2023-11-28 10:45:38,505][87426] Updated weights for policy 1, policy_version 401750 (0.0008) -[2023-11-28 10:45:38,885][87426] Updated weights for policy 1, policy_version 401760 (0.0008) -[2023-11-28 10:45:38,900][87424] Updated weights for policy 0, policy_version 402019 (0.0011) -[2023-11-28 10:45:39,278][87424] Updated weights for policy 0, policy_version 402029 (0.0012) -[2023-11-28 10:45:39,656][87424] Updated weights for policy 0, policy_version 402039 (0.0013) -[2023-11-28 10:45:40,881][87426] Updated weights for policy 1, policy_version 401770 (0.0012) -[2023-11-28 10:45:41,258][87426] Updated weights for policy 1, policy_version 401780 (0.0011) -[2023-11-28 10:45:41,645][87426] Updated weights for policy 1, policy_version 401790 (0.0008) -[2023-11-28 10:45:42,233][87424] Updated weights for policy 0, policy_version 402049 (0.0012) -[2023-11-28 10:45:42,614][87424] Updated weights for policy 0, policy_version 402059 (0.0012) -[2023-11-28 10:45:43,004][87424] Updated weights for policy 0, policy_version 402069 (0.0011) -[2023-11-28 10:45:43,385][87424] Updated weights for policy 0, policy_version 402079 (0.0011) -[2023-11-28 10:45:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 205791232. Throughput: 0: 2716.9, 1: 2665.0. Samples: 205803992. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:43,445][86177] Avg episode reward: [(0, '-588.910'), (1, '-547.570')] -[2023-11-28 10:45:43,960][87426] Updated weights for policy 1, policy_version 401800 (0.0008) -[2023-11-28 10:45:44,347][87426] Updated weights for policy 1, policy_version 401810 (0.0007) -[2023-11-28 10:45:44,729][87426] Updated weights for policy 1, policy_version 401820 (0.0007) -[2023-11-28 10:45:45,968][87424] Updated weights for policy 0, policy_version 402089 (0.0011) -[2023-11-28 10:45:46,344][87424] Updated weights for policy 0, policy_version 402099 (0.0012) -[2023-11-28 10:45:46,726][87424] Updated weights for policy 0, policy_version 402109 (0.0012) -[2023-11-28 10:45:46,823][87426] Updated weights for policy 1, policy_version 401830 (0.0011) -[2023-11-28 10:45:47,201][87426] Updated weights for policy 1, policy_version 401840 (0.0012) -[2023-11-28 10:45:47,577][87426] Updated weights for policy 1, policy_version 401850 (0.0011) -[2023-11-28 10:45:48,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205815808. Throughput: 0: 2701.5, 1: 2659.4. Samples: 205826644. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:48,445][86177] Avg episode reward: [(0, '-544.440'), (1, '-540.970')] -[2023-11-28 10:45:49,017][87424] Updated weights for policy 0, policy_version 402119 (0.0009) -[2023-11-28 10:45:49,404][87424] Updated weights for policy 0, policy_version 402129 (0.0010) -[2023-11-28 10:45:49,795][87424] Updated weights for policy 0, policy_version 402139 (0.0010) -[2023-11-28 10:45:49,954][87426] Updated weights for policy 1, policy_version 401860 (0.0011) -[2023-11-28 10:45:50,351][87426] Updated weights for policy 1, policy_version 401870 (0.0011) -[2023-11-28 10:45:50,723][87426] Updated weights for policy 1, policy_version 401880 (0.0010) -[2023-11-28 10:45:52,087][87424] Updated weights for policy 0, policy_version 402149 (0.0012) -[2023-11-28 10:45:52,458][87424] Updated weights for policy 0, policy_version 402159 (0.0011) -[2023-11-28 10:45:52,840][87424] Updated weights for policy 0, policy_version 402169 (0.0011) -[2023-11-28 10:45:53,009][87426] Updated weights for policy 1, policy_version 401890 (0.0010) -[2023-11-28 10:45:53,387][87426] Updated weights for policy 1, policy_version 401900 (0.0009) -[2023-11-28 10:45:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 205840384. Throughput: 0: 2716.8, 1: 2629.5. Samples: 205858764. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:53,445][86177] Avg episode reward: [(0, '-539.090'), (1, '-569.240')] -[2023-11-28 10:45:53,768][87426] Updated weights for policy 1, policy_version 401910 (0.0011) -[2023-11-28 10:45:54,149][87426] Updated weights for policy 1, policy_version 401920 (0.0010) -[2023-11-28 10:45:55,181][87424] Updated weights for policy 0, policy_version 402179 (0.0009) -[2023-11-28 10:45:55,569][87424] Updated weights for policy 0, policy_version 402189 (0.0007) -[2023-11-28 10:45:55,950][87424] Updated weights for policy 0, policy_version 402199 (0.0007) -[2023-11-28 10:45:56,490][87426] Updated weights for policy 1, policy_version 401930 (0.0007) -[2023-11-28 10:45:56,871][87426] Updated weights for policy 1, policy_version 401940 (0.0007) -[2023-11-28 10:45:57,265][87426] Updated weights for policy 1, policy_version 401950 (0.0008) -[2023-11-28 10:45:57,681][87424] Updated weights for policy 0, policy_version 402209 (0.0009) -[2023-11-28 10:45:58,057][87424] Updated weights for policy 0, policy_version 402219 (0.0012) -[2023-11-28 10:45:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205864960. Throughput: 0: 2717.3, 1: 2675.1. Samples: 205884212. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:45:58,445][86177] Avg episode reward: [(0, '-513.730'), (1, '-562.130')] -[2023-11-28 10:45:58,447][87424] Updated weights for policy 0, policy_version 402229 (0.0011) -[2023-11-28 10:45:58,819][87426] Updated weights for policy 1, policy_version 401960 (0.0012) -[2023-11-28 10:45:58,826][87424] Updated weights for policy 0, policy_version 402239 (0.0012) -[2023-11-28 10:45:59,203][87426] Updated weights for policy 1, policy_version 401970 (0.0011) -[2023-11-28 10:45:59,581][87426] Updated weights for policy 1, policy_version 401980 (0.0012) -[2023-11-28 10:46:00,886][87424] Updated weights for policy 0, policy_version 402249 (0.0012) -[2023-11-28 10:46:01,265][87424] Updated weights for policy 0, policy_version 402259 (0.0010) -[2023-11-28 10:46:01,650][87424] Updated weights for policy 0, policy_version 402269 (0.0011) -[2023-11-28 10:46:01,998][87426] Updated weights for policy 1, policy_version 401990 (0.0011) -[2023-11-28 10:46:02,380][87426] Updated weights for policy 1, policy_version 402000 (0.0011) -[2023-11-28 10:46:02,758][87426] Updated weights for policy 1, policy_version 402010 (0.0011) -[2023-11-28 10:46:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 205897728. Throughput: 0: 2679.2, 1: 2679.0. Samples: 205908236. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:46:03,445][86177] Avg episode reward: [(0, '-514.380'), (1, '-550.130')] -[2023-11-28 10:46:03,638][87424] Updated weights for policy 0, policy_version 402279 (0.0011) -[2023-11-28 10:46:04,031][87424] Updated weights for policy 0, policy_version 402289 (0.0012) -[2023-11-28 10:46:04,410][87424] Updated weights for policy 0, policy_version 402299 (0.0011) -[2023-11-28 10:46:05,177][87426] Updated weights for policy 1, policy_version 402020 (0.0010) -[2023-11-28 10:46:05,558][87426] Updated weights for policy 1, policy_version 402030 (0.0008) -[2023-11-28 10:46:05,928][87426] Updated weights for policy 1, policy_version 402040 (0.0008) -[2023-11-28 10:46:06,816][87424] Updated weights for policy 0, policy_version 402309 (0.0011) -[2023-11-28 10:46:07,202][87424] Updated weights for policy 0, policy_version 402319 (0.0010) -[2023-11-28 10:46:07,577][87424] Updated weights for policy 0, policy_version 402329 (0.0012) -[2023-11-28 10:46:08,437][87426] Updated weights for policy 1, policy_version 402050 (0.0007) -[2023-11-28 10:46:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205922304. Throughput: 0: 2658.3, 1: 2697.2. Samples: 205940024. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:46:08,445][86177] Avg episode reward: [(0, '-516.120'), (1, '-545.760')] -[2023-11-28 10:46:08,818][87426] Updated weights for policy 1, policy_version 402060 (0.0007) -[2023-11-28 10:46:09,204][87426] Updated weights for policy 1, policy_version 402070 (0.0008) -[2023-11-28 10:46:09,577][87426] Updated weights for policy 1, policy_version 402080 (0.0007) -[2023-11-28 10:46:09,581][87424] Updated weights for policy 0, policy_version 402339 (0.0012) -[2023-11-28 10:46:09,959][87424] Updated weights for policy 0, policy_version 402349 (0.0010) -[2023-11-28 10:46:10,351][87424] Updated weights for policy 0, policy_version 402359 (0.0011) -[2023-11-28 10:46:11,731][87426] Updated weights for policy 1, policy_version 402090 (0.0011) -[2023-11-28 10:46:12,104][87426] Updated weights for policy 1, policy_version 402100 (0.0011) -[2023-11-28 10:46:12,489][87426] Updated weights for policy 1, policy_version 402110 (0.0011) -[2023-11-28 10:46:12,885][87424] Updated weights for policy 0, policy_version 402369 (0.0011) -[2023-11-28 10:46:13,263][87424] Updated weights for policy 0, policy_version 402379 (0.0011) -[2023-11-28 10:46:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 205946880. Throughput: 0: 2658.8, 1: 2674.3. Samples: 205963876. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:46:13,445][86177] Avg episode reward: [(0, '-521.920'), (1, '-512.100')] -[2023-11-28 10:46:13,647][87424] Updated weights for policy 0, policy_version 402389 (0.0012) -[2023-11-28 10:46:14,024][87424] Updated weights for policy 0, policy_version 402399 (0.0007) -[2023-11-28 10:46:14,346][87426] Updated weights for policy 1, policy_version 402120 (0.0010) -[2023-11-28 10:46:14,730][87426] Updated weights for policy 1, policy_version 402130 (0.0010) -[2023-11-28 10:46:15,103][87426] Updated weights for policy 1, policy_version 402140 (0.0008) -[2023-11-28 10:46:16,118][87424] Updated weights for policy 0, policy_version 402409 (0.0011) -[2023-11-28 10:46:16,504][87424] Updated weights for policy 0, policy_version 402419 (0.0012) -[2023-11-28 10:46:16,887][87424] Updated weights for policy 0, policy_version 402429 (0.0012) -[2023-11-28 10:46:17,247][87426] Updated weights for policy 1, policy_version 402150 (0.0011) -[2023-11-28 10:46:17,616][87426] Updated weights for policy 1, policy_version 402160 (0.0012) -[2023-11-28 10:46:17,998][87426] Updated weights for policy 1, policy_version 402170 (0.0012) -[2023-11-28 10:46:18,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 205979648. Throughput: 0: 2665.7, 1: 2671.5. Samples: 205988556. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:46:18,445][86177] Avg episode reward: [(0, '-528.630'), (1, '-512.160')] -[2023-11-28 10:46:18,454][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000402432_103022592.pth... -[2023-11-28 10:46:18,454][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000402176_102957056.pth... -[2023-11-28 10:46:18,486][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000399648_102309888.pth -[2023-11-28 10:46:18,486][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000399936_102383616.pth -[2023-11-28 10:46:19,238][87424] Updated weights for policy 0, policy_version 402439 (0.0011) -[2023-11-28 10:46:19,619][87424] Updated weights for policy 0, policy_version 402449 (0.0011) -[2023-11-28 10:46:20,018][87424] Updated weights for policy 0, policy_version 402459 (0.0011) -[2023-11-28 10:46:20,263][87426] Updated weights for policy 1, policy_version 402180 (0.0012) -[2023-11-28 10:46:20,640][87426] Updated weights for policy 1, policy_version 402190 (0.0012) -[2023-11-28 10:46:21,015][87426] Updated weights for policy 1, policy_version 402200 (0.0012) -[2023-11-28 10:46:22,547][87424] Updated weights for policy 0, policy_version 402469 (0.0009) -[2023-11-28 10:46:22,926][87424] Updated weights for policy 0, policy_version 402479 (0.0010) -[2023-11-28 10:46:23,306][87424] Updated weights for policy 0, policy_version 402489 (0.0011) -[2023-11-28 10:46:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5331.7). Total num frames: 205996032. Throughput: 0: 2647.1, 1: 2659.2. Samples: 206019256. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:46:23,445][86177] Avg episode reward: [(0, '-533.760'), (1, '-511.230')] -[2023-11-28 10:46:23,594][87426] Updated weights for policy 1, policy_version 402210 (0.0011) -[2023-11-28 10:46:23,968][87426] Updated weights for policy 1, policy_version 402220 (0.0012) -[2023-11-28 10:46:24,356][87426] Updated weights for policy 1, policy_version 402230 (0.0012) -[2023-11-28 10:46:24,735][87426] Updated weights for policy 1, policy_version 402240 (0.0012) -[2023-11-28 10:46:25,405][87424] Updated weights for policy 0, policy_version 402499 (0.0010) -[2023-11-28 10:46:25,787][87424] Updated weights for policy 0, policy_version 402509 (0.0007) -[2023-11-28 10:46:26,178][87424] Updated weights for policy 0, policy_version 402519 (0.0007) -[2023-11-28 10:46:27,348][87426] Updated weights for policy 1, policy_version 402250 (0.0008) -[2023-11-28 10:46:27,737][87426] Updated weights for policy 1, policy_version 402260 (0.0007) -[2023-11-28 10:46:27,901][87424] Updated weights for policy 0, policy_version 402529 (0.0008) -[2023-11-28 10:46:28,121][87426] Updated weights for policy 1, policy_version 402270 (0.0007) -[2023-11-28 10:46:28,290][87424] Updated weights for policy 0, policy_version 402539 (0.0011) -[2023-11-28 10:46:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206028800. Throughput: 0: 2660.0, 1: 2661.8. Samples: 206043472. Policy #0 lag: (min: 10.0, avg: 40.0, max: 72.0) -[2023-11-28 10:46:28,445][86177] Avg episode reward: [(0, '-535.100'), (1, '-513.450')] -[2023-11-28 10:46:28,676][87424] Updated weights for policy 0, policy_version 402549 (0.0012) -[2023-11-28 10:46:29,053][87424] Updated weights for policy 0, policy_version 402559 (0.0011) -[2023-11-28 10:46:30,603][87426] Updated weights for policy 1, policy_version 402280 (0.0010) -[2023-11-28 10:46:30,987][87426] Updated weights for policy 1, policy_version 402290 (0.0008) -[2023-11-28 10:46:31,023][87424] Updated weights for policy 0, policy_version 402569 (0.0008) -[2023-11-28 10:46:31,361][87426] Updated weights for policy 1, policy_version 402300 (0.0010) -[2023-11-28 10:46:31,401][87424] Updated weights for policy 0, policy_version 402579 (0.0008) -[2023-11-28 10:46:31,784][87424] Updated weights for policy 0, policy_version 402589 (0.0010) -[2023-11-28 10:46:33,232][87426] Updated weights for policy 1, policy_version 402310 (0.0010) -[2023-11-28 10:46:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 206053376. Throughput: 0: 2723.6, 1: 2652.6. Samples: 206068576. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:46:33,445][86177] Avg episode reward: [(0, '-528.570'), (1, '-518.910')] -[2023-11-28 10:46:33,609][87426] Updated weights for policy 1, policy_version 402320 (0.0012) -[2023-11-28 10:46:33,629][87424] Updated weights for policy 0, policy_version 402599 (0.0012) -[2023-11-28 10:46:33,991][87426] Updated weights for policy 1, policy_version 402330 (0.0011) -[2023-11-28 10:46:34,017][87424] Updated weights for policy 0, policy_version 402609 (0.0012) -[2023-11-28 10:46:34,391][87424] Updated weights for policy 0, policy_version 402619 (0.0012) -[2023-11-28 10:46:36,143][87426] Updated weights for policy 1, policy_version 402340 (0.0012) -[2023-11-28 10:46:36,514][87424] Updated weights for policy 0, policy_version 402629 (0.0009) -[2023-11-28 10:46:36,516][87426] Updated weights for policy 1, policy_version 402350 (0.0012) -[2023-11-28 10:46:36,897][87426] Updated weights for policy 1, policy_version 402360 (0.0012) -[2023-11-28 10:46:36,898][87424] Updated weights for policy 0, policy_version 402639 (0.0009) -[2023-11-28 10:46:37,280][87424] Updated weights for policy 0, policy_version 402649 (0.0011) -[2023-11-28 10:46:38,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206086144. Throughput: 0: 2722.7, 1: 2676.5. Samples: 206101728. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:46:38,445][86177] Avg episode reward: [(0, '-528.450'), (1, '-518.700')] -[2023-11-28 10:46:38,938][87426] Updated weights for policy 1, policy_version 402370 (0.0011) -[2023-11-28 10:46:39,321][87426] Updated weights for policy 1, policy_version 402380 (0.0010) -[2023-11-28 10:46:39,676][87424] Updated weights for policy 0, policy_version 402659 (0.0009) -[2023-11-28 10:46:39,705][87426] Updated weights for policy 1, policy_version 402390 (0.0011) -[2023-11-28 10:46:40,049][87424] Updated weights for policy 0, policy_version 402669 (0.0011) -[2023-11-28 10:46:40,085][87426] Updated weights for policy 1, policy_version 402400 (0.0012) -[2023-11-28 10:46:40,432][87424] Updated weights for policy 0, policy_version 402679 (0.0012) -[2023-11-28 10:46:41,824][87426] Updated weights for policy 1, policy_version 402410 (0.0012) -[2023-11-28 10:46:42,201][87426] Updated weights for policy 1, policy_version 402420 (0.0012) -[2023-11-28 10:46:42,581][87426] Updated weights for policy 1, policy_version 402430 (0.0008) -[2023-11-28 10:46:42,829][87424] Updated weights for policy 0, policy_version 402689 (0.0012) -[2023-11-28 10:46:43,214][87424] Updated weights for policy 0, policy_version 402699 (0.0011) -[2023-11-28 10:46:43,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206110720. Throughput: 0: 2700.5, 1: 2667.6. Samples: 206125776. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:46:43,445][86177] Avg episode reward: [(0, '-522.680'), (1, '-519.130')] -[2023-11-28 10:46:43,588][87424] Updated weights for policy 0, policy_version 402709 (0.0010) -[2023-11-28 10:46:43,973][87424] Updated weights for policy 0, policy_version 402719 (0.0010) -[2023-11-28 10:46:44,822][87426] Updated weights for policy 1, policy_version 402440 (0.0011) -[2023-11-28 10:46:45,204][87426] Updated weights for policy 1, policy_version 402450 (0.0011) -[2023-11-28 10:46:45,586][87426] Updated weights for policy 1, policy_version 402460 (0.0011) -[2023-11-28 10:46:46,316][87424] Updated weights for policy 0, policy_version 402729 (0.0009) -[2023-11-28 10:46:46,699][87424] Updated weights for policy 0, policy_version 402739 (0.0007) -[2023-11-28 10:46:47,092][87424] Updated weights for policy 0, policy_version 402749 (0.0007) -[2023-11-28 10:46:47,536][87426] Updated weights for policy 1, policy_version 402470 (0.0009) -[2023-11-28 10:46:47,918][87426] Updated weights for policy 1, policy_version 402480 (0.0008) -[2023-11-28 10:46:48,298][87426] Updated weights for policy 1, policy_version 402490 (0.0008) -[2023-11-28 10:46:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 206135296. Throughput: 0: 2699.2, 1: 2657.5. Samples: 206149288. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:46:48,445][86177] Avg episode reward: [(0, '-520.560'), (1, '-519.790')] -[2023-11-28 10:46:49,593][87424] Updated weights for policy 0, policy_version 402759 (0.0010) -[2023-11-28 10:46:49,971][87424] Updated weights for policy 0, policy_version 402769 (0.0010) -[2023-11-28 10:46:50,353][87424] Updated weights for policy 0, policy_version 402779 (0.0009) -[2023-11-28 10:46:50,803][87426] Updated weights for policy 1, policy_version 402500 (0.0009) -[2023-11-28 10:46:51,171][87426] Updated weights for policy 1, policy_version 402510 (0.0012) -[2023-11-28 10:46:51,550][87426] Updated weights for policy 1, policy_version 402520 (0.0011) -[2023-11-28 10:46:52,514][87424] Updated weights for policy 0, policy_version 402789 (0.0010) -[2023-11-28 10:46:52,905][87424] Updated weights for policy 0, policy_version 402799 (0.0011) -[2023-11-28 10:46:53,296][87424] Updated weights for policy 0, policy_version 402809 (0.0008) -[2023-11-28 10:46:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206159872. Throughput: 0: 2709.2, 1: 2646.1. Samples: 206181016. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:46:53,445][86177] Avg episode reward: [(0, '-530.000'), (1, '-517.150')] -[2023-11-28 10:46:53,672][87426] Updated weights for policy 1, policy_version 402530 (0.0010) -[2023-11-28 10:46:54,052][87426] Updated weights for policy 1, policy_version 402540 (0.0008) -[2023-11-28 10:46:54,429][87426] Updated weights for policy 1, policy_version 402550 (0.0007) -[2023-11-28 10:46:54,811][87426] Updated weights for policy 1, policy_version 402560 (0.0007) -[2023-11-28 10:46:55,283][87424] Updated weights for policy 0, policy_version 402819 (0.0010) -[2023-11-28 10:46:55,662][87424] Updated weights for policy 0, policy_version 402829 (0.0012) -[2023-11-28 10:46:56,043][87424] Updated weights for policy 0, policy_version 402839 (0.0012) -[2023-11-28 10:46:57,049][87426] Updated weights for policy 1, policy_version 402570 (0.0012) -[2023-11-28 10:46:57,424][87426] Updated weights for policy 1, policy_version 402580 (0.0012) -[2023-11-28 10:46:57,798][87426] Updated weights for policy 1, policy_version 402590 (0.0011) -[2023-11-28 10:46:58,062][87424] Updated weights for policy 0, policy_version 402849 (0.0012) -[2023-11-28 10:46:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 206192640. Throughput: 0: 2720.3, 1: 2653.6. Samples: 206205704. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:46:58,446][86177] Avg episode reward: [(0, '-519.400'), (1, '-526.350')] -[2023-11-28 10:46:58,447][87424] Updated weights for policy 0, policy_version 402859 (0.0012) -[2023-11-28 10:46:58,821][87424] Updated weights for policy 0, policy_version 402869 (0.0012) -[2023-11-28 10:46:59,198][87424] Updated weights for policy 0, policy_version 402879 (0.0008) -[2023-11-28 10:46:59,910][87426] Updated weights for policy 1, policy_version 402600 (0.0011) -[2023-11-28 10:47:00,294][87426] Updated weights for policy 1, policy_version 402610 (0.0012) -[2023-11-28 10:47:00,668][87426] Updated weights for policy 1, policy_version 402620 (0.0012) -[2023-11-28 10:47:01,330][87424] Updated weights for policy 0, policy_version 402889 (0.0007) -[2023-11-28 10:47:01,721][87424] Updated weights for policy 0, policy_version 402899 (0.0008) -[2023-11-28 10:47:02,101][87424] Updated weights for policy 0, policy_version 402909 (0.0011) -[2023-11-28 10:47:03,265][87426] Updated weights for policy 1, policy_version 402630 (0.0012) -[2023-11-28 10:47:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 206217216. Throughput: 0: 2714.9, 1: 2657.0. Samples: 206230292. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:03,445][86177] Avg episode reward: [(0, '-525.700'), (1, '-526.680')] -[2023-11-28 10:47:03,641][87426] Updated weights for policy 1, policy_version 402640 (0.0009) -[2023-11-28 10:47:04,018][87426] Updated weights for policy 1, policy_version 402650 (0.0007) -[2023-11-28 10:47:04,280][87424] Updated weights for policy 0, policy_version 402919 (0.0012) -[2023-11-28 10:47:04,663][87424] Updated weights for policy 0, policy_version 402929 (0.0012) -[2023-11-28 10:47:05,038][87424] Updated weights for policy 0, policy_version 402939 (0.0012) -[2023-11-28 10:47:06,545][87426] Updated weights for policy 1, policy_version 402660 (0.0009) -[2023-11-28 10:47:06,920][87426] Updated weights for policy 1, policy_version 402670 (0.0011) -[2023-11-28 10:47:07,141][87424] Updated weights for policy 0, policy_version 402949 (0.0011) -[2023-11-28 10:47:07,299][87426] Updated weights for policy 1, policy_version 402680 (0.0009) -[2023-11-28 10:47:07,522][87424] Updated weights for policy 0, policy_version 402959 (0.0012) -[2023-11-28 10:47:07,915][87424] Updated weights for policy 0, policy_version 402969 (0.0011) -[2023-11-28 10:47:08,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206249984. Throughput: 0: 2754.0, 1: 2654.0. Samples: 206262620. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:08,445][86177] Avg episode reward: [(0, '-520.980'), (1, '-541.170')] -[2023-11-28 10:47:09,350][87426] Updated weights for policy 1, policy_version 402690 (0.0009) -[2023-11-28 10:47:09,725][87426] Updated weights for policy 1, policy_version 402700 (0.0012) -[2023-11-28 10:47:10,104][87426] Updated weights for policy 1, policy_version 402710 (0.0010) -[2023-11-28 10:47:10,268][87424] Updated weights for policy 0, policy_version 402979 (0.0011) -[2023-11-28 10:47:10,490][87426] Updated weights for policy 1, policy_version 402720 (0.0010) -[2023-11-28 10:47:10,650][87424] Updated weights for policy 0, policy_version 402989 (0.0012) -[2023-11-28 10:47:11,031][87424] Updated weights for policy 0, policy_version 402999 (0.0012) -[2023-11-28 10:47:12,272][87426] Updated weights for policy 1, policy_version 402730 (0.0012) -[2023-11-28 10:47:12,652][87426] Updated weights for policy 1, policy_version 402740 (0.0012) -[2023-11-28 10:47:13,034][87426] Updated weights for policy 1, policy_version 402750 (0.0012) -[2023-11-28 10:47:13,264][87424] Updated weights for policy 0, policy_version 403009 (0.0012) -[2023-11-28 10:47:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 206274560. Throughput: 0: 2724.1, 1: 2674.7. Samples: 206286416. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:13,445][86177] Avg episode reward: [(0, '-520.280'), (1, '-534.580')] -[2023-11-28 10:47:13,655][87424] Updated weights for policy 0, policy_version 403019 (0.0012) -[2023-11-28 10:47:14,033][87424] Updated weights for policy 0, policy_version 403029 (0.0012) -[2023-11-28 10:47:14,424][87424] Updated weights for policy 0, policy_version 403039 (0.0010) -[2023-11-28 10:47:15,107][87426] Updated weights for policy 1, policy_version 402760 (0.0012) -[2023-11-28 10:47:15,495][87426] Updated weights for policy 1, policy_version 402770 (0.0012) -[2023-11-28 10:47:15,873][87426] Updated weights for policy 1, policy_version 402780 (0.0012) -[2023-11-28 10:47:16,501][87424] Updated weights for policy 0, policy_version 403049 (0.0009) -[2023-11-28 10:47:16,883][87424] Updated weights for policy 0, policy_version 403059 (0.0009) -[2023-11-28 10:47:17,267][87424] Updated weights for policy 0, policy_version 403069 (0.0012) -[2023-11-28 10:47:18,390][87426] Updated weights for policy 1, policy_version 402790 (0.0012) -[2023-11-28 10:47:18,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206299136. Throughput: 0: 2687.2, 1: 2692.3. Samples: 206310656. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:18,445][86177] Avg episode reward: [(0, '-522.370'), (1, '-530.500')] -[2023-11-28 10:47:18,765][87426] Updated weights for policy 1, policy_version 402800 (0.0012) -[2023-11-28 10:47:19,139][87426] Updated weights for policy 1, policy_version 402810 (0.0011) -[2023-11-28 10:47:19,208][87424] Updated weights for policy 0, policy_version 403079 (0.0011) -[2023-11-28 10:47:19,593][87424] Updated weights for policy 0, policy_version 403089 (0.0011) -[2023-11-28 10:47:19,977][87424] Updated weights for policy 0, policy_version 403099 (0.0011) -[2023-11-28 10:47:21,379][87426] Updated weights for policy 1, policy_version 402820 (0.0011) -[2023-11-28 10:47:21,762][87426] Updated weights for policy 1, policy_version 402830 (0.0009) -[2023-11-28 10:47:22,146][87426] Updated weights for policy 1, policy_version 402840 (0.0011) -[2023-11-28 10:47:22,585][87424] Updated weights for policy 0, policy_version 403109 (0.0010) -[2023-11-28 10:47:22,969][87424] Updated weights for policy 0, policy_version 403119 (0.0012) -[2023-11-28 10:47:23,357][87424] Updated weights for policy 0, policy_version 403129 (0.0011) -[2023-11-28 10:47:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 206323712. Throughput: 0: 2678.6, 1: 2699.9. Samples: 206343760. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:23,445][86177] Avg episode reward: [(0, '-517.270'), (1, '-518.210')] -[2023-11-28 10:47:24,518][87426] Updated weights for policy 1, policy_version 402850 (0.0009) -[2023-11-28 10:47:24,903][87426] Updated weights for policy 1, policy_version 402860 (0.0009) -[2023-11-28 10:47:25,276][87426] Updated weights for policy 1, policy_version 402870 (0.0010) -[2023-11-28 10:47:25,651][87426] Updated weights for policy 1, policy_version 402880 (0.0008) -[2023-11-28 10:47:25,898][87424] Updated weights for policy 0, policy_version 403139 (0.0010) -[2023-11-28 10:47:26,278][87424] Updated weights for policy 0, policy_version 403149 (0.0009) -[2023-11-28 10:47:26,659][87424] Updated weights for policy 0, policy_version 403159 (0.0012) -[2023-11-28 10:47:28,171][87426] Updated weights for policy 1, policy_version 402890 (0.0012) -[2023-11-28 10:47:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 206348288. Throughput: 0: 2675.6, 1: 2687.5. Samples: 206367116. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:28,445][86177] Avg episode reward: [(0, '-546.330'), (1, '-511.430')] -[2023-11-28 10:47:28,563][87426] Updated weights for policy 1, policy_version 402900 (0.0009) -[2023-11-28 10:47:28,726][87424] Updated weights for policy 0, policy_version 403169 (0.0012) -[2023-11-28 10:47:28,934][87426] Updated weights for policy 1, policy_version 402910 (0.0008) -[2023-11-28 10:47:29,107][87424] Updated weights for policy 0, policy_version 403179 (0.0010) -[2023-11-28 10:47:29,483][87424] Updated weights for policy 0, policy_version 403189 (0.0008) -[2023-11-28 10:47:29,869][87424] Updated weights for policy 0, policy_version 403199 (0.0008) -[2023-11-28 10:47:30,993][87426] Updated weights for policy 1, policy_version 402920 (0.0009) -[2023-11-28 10:47:31,377][87426] Updated weights for policy 1, policy_version 402930 (0.0008) -[2023-11-28 10:47:31,749][87426] Updated weights for policy 1, policy_version 402940 (0.0012) -[2023-11-28 10:47:31,906][87424] Updated weights for policy 0, policy_version 403209 (0.0009) -[2023-11-28 10:47:32,294][87424] Updated weights for policy 0, policy_version 403219 (0.0009) -[2023-11-28 10:47:32,674][87424] Updated weights for policy 0, policy_version 403229 (0.0009) -[2023-11-28 10:47:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 206381056. Throughput: 0: 2699.0, 1: 2684.1. Samples: 206391528. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:33,445][86177] Avg episode reward: [(0, '-544.830'), (1, '-512.060')] -[2023-11-28 10:47:33,981][87426] Updated weights for policy 1, policy_version 402950 (0.0012) -[2023-11-28 10:47:34,359][87426] Updated weights for policy 1, policy_version 402960 (0.0010) -[2023-11-28 10:47:34,416][87424] Updated weights for policy 0, policy_version 403239 (0.0010) -[2023-11-28 10:47:34,737][87426] Updated weights for policy 1, policy_version 402970 (0.0011) -[2023-11-28 10:47:34,793][87424] Updated weights for policy 0, policy_version 403249 (0.0009) -[2023-11-28 10:47:35,173][87424] Updated weights for policy 0, policy_version 403259 (0.0011) -[2023-11-28 10:47:36,706][87426] Updated weights for policy 1, policy_version 402980 (0.0011) -[2023-11-28 10:47:37,089][87426] Updated weights for policy 1, policy_version 402990 (0.0008) -[2023-11-28 10:47:37,347][87424] Updated weights for policy 0, policy_version 403269 (0.0010) -[2023-11-28 10:47:37,460][87426] Updated weights for policy 1, policy_version 403000 (0.0009) -[2023-11-28 10:47:37,736][87424] Updated weights for policy 0, policy_version 403279 (0.0011) -[2023-11-28 10:47:38,120][87424] Updated weights for policy 0, policy_version 403289 (0.0012) -[2023-11-28 10:47:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206413824. Throughput: 0: 2709.2, 1: 2694.8. Samples: 206424192. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:38,445][86177] Avg episode reward: [(0, '-544.150'), (1, '-502.610')] -[2023-11-28 10:47:39,866][87426] Updated weights for policy 1, policy_version 403010 (0.0009) -[2023-11-28 10:47:40,241][87426] Updated weights for policy 1, policy_version 403020 (0.0010) -[2023-11-28 10:47:40,603][87424] Updated weights for policy 0, policy_version 403299 (0.0011) -[2023-11-28 10:47:40,625][87426] Updated weights for policy 1, policy_version 403030 (0.0009) -[2023-11-28 10:47:40,987][87424] Updated weights for policy 0, policy_version 403309 (0.0011) -[2023-11-28 10:47:41,004][87426] Updated weights for policy 1, policy_version 403040 (0.0010) -[2023-11-28 10:47:41,375][87424] Updated weights for policy 0, policy_version 403319 (0.0012) -[2023-11-28 10:47:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206430208. Throughput: 0: 2692.1, 1: 2685.0. Samples: 206447672. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:43,445][86177] Avg episode reward: [(0, '-545.870'), (1, '-504.330')] -[2023-11-28 10:47:43,458][87426] Updated weights for policy 1, policy_version 403050 (0.0012) -[2023-11-28 10:47:43,845][87426] Updated weights for policy 1, policy_version 403060 (0.0012) -[2023-11-28 10:47:43,961][87424] Updated weights for policy 0, policy_version 403329 (0.0011) -[2023-11-28 10:47:44,226][87426] Updated weights for policy 1, policy_version 403070 (0.0011) -[2023-11-28 10:47:44,342][87424] Updated weights for policy 0, policy_version 403339 (0.0010) -[2023-11-28 10:47:44,726][87424] Updated weights for policy 0, policy_version 403349 (0.0008) -[2023-11-28 10:47:45,121][87424] Updated weights for policy 0, policy_version 403359 (0.0009) -[2023-11-28 10:47:46,577][87426] Updated weights for policy 1, policy_version 403080 (0.0011) -[2023-11-28 10:47:46,964][87426] Updated weights for policy 1, policy_version 403090 (0.0012) -[2023-11-28 10:47:47,354][87426] Updated weights for policy 1, policy_version 403100 (0.0011) -[2023-11-28 10:47:47,646][87424] Updated weights for policy 0, policy_version 403369 (0.0011) -[2023-11-28 10:47:48,031][87424] Updated weights for policy 0, policy_version 403379 (0.0012) -[2023-11-28 10:47:48,410][87424] Updated weights for policy 0, policy_version 403389 (0.0012) -[2023-11-28 10:47:48,444][86177] Fps is (10 sec: 4096.0, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206454784. Throughput: 0: 2678.8, 1: 2672.8. Samples: 206471112. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:48,445][86177] Avg episode reward: [(0, '-523.260'), (1, '-509.050')] -[2023-11-28 10:47:49,493][87426] Updated weights for policy 1, policy_version 403110 (0.0011) -[2023-11-28 10:47:49,873][87426] Updated weights for policy 1, policy_version 403120 (0.0012) -[2023-11-28 10:47:50,260][87426] Updated weights for policy 1, policy_version 403130 (0.0011) -[2023-11-28 10:47:50,405][87424] Updated weights for policy 0, policy_version 403399 (0.0012) -[2023-11-28 10:47:50,781][87424] Updated weights for policy 0, policy_version 403409 (0.0012) -[2023-11-28 10:47:51,164][87424] Updated weights for policy 0, policy_version 403419 (0.0012) -[2023-11-28 10:47:52,513][87426] Updated weights for policy 1, policy_version 403140 (0.0012) -[2023-11-28 10:47:52,890][87426] Updated weights for policy 1, policy_version 403150 (0.0012) -[2023-11-28 10:47:53,266][87426] Updated weights for policy 1, policy_version 403160 (0.0011) -[2023-11-28 10:47:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 206479360. Throughput: 0: 2658.5, 1: 2680.0. Samples: 206502852. Policy #0 lag: (min: 11.0, avg: 35.3, max: 69.0) -[2023-11-28 10:47:53,445][86177] Avg episode reward: [(0, '-522.500'), (1, '-509.950')] -[2023-11-28 10:47:53,535][87424] Updated weights for policy 0, policy_version 403429 (0.0012) -[2023-11-28 10:47:53,910][87424] Updated weights for policy 0, policy_version 403439 (0.0011) -[2023-11-28 10:47:54,290][87424] Updated weights for policy 0, policy_version 403449 (0.0011) -[2023-11-28 10:47:55,500][87426] Updated weights for policy 1, policy_version 403170 (0.0010) -[2023-11-28 10:47:55,882][87426] Updated weights for policy 1, policy_version 403180 (0.0007) -[2023-11-28 10:47:56,274][87426] Updated weights for policy 1, policy_version 403190 (0.0008) -[2023-11-28 10:47:56,644][87426] Updated weights for policy 1, policy_version 403200 (0.0007) -[2023-11-28 10:47:56,895][87424] Updated weights for policy 0, policy_version 403459 (0.0010) -[2023-11-28 10:47:57,269][87424] Updated weights for policy 0, policy_version 403469 (0.0008) -[2023-11-28 10:47:57,662][87424] Updated weights for policy 0, policy_version 403479 (0.0007) -[2023-11-28 10:47:58,219][87426] Updated weights for policy 1, policy_version 403210 (0.0008) -[2023-11-28 10:47:58,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206512128. Throughput: 0: 2650.0, 1: 2704.4. Samples: 206527368. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:47:58,445][86177] Avg episode reward: [(0, '-522.570'), (1, '-512.840')] -[2023-11-28 10:47:58,602][87426] Updated weights for policy 1, policy_version 403220 (0.0008) -[2023-11-28 10:47:58,981][87426] Updated weights for policy 1, policy_version 403230 (0.0007) -[2023-11-28 10:47:59,885][87424] Updated weights for policy 0, policy_version 403489 (0.0009) -[2023-11-28 10:48:00,264][87424] Updated weights for policy 0, policy_version 403499 (0.0012) -[2023-11-28 10:48:00,647][87424] Updated weights for policy 0, policy_version 403509 (0.0011) -[2023-11-28 10:48:00,780][87426] Updated weights for policy 1, policy_version 403240 (0.0011) -[2023-11-28 10:48:01,023][87424] Updated weights for policy 0, policy_version 403519 (0.0008) -[2023-11-28 10:48:01,158][87426] Updated weights for policy 1, policy_version 403250 (0.0008) -[2023-11-28 10:48:01,538][87426] Updated weights for policy 1, policy_version 403260 (0.0007) -[2023-11-28 10:48:03,372][87424] Updated weights for policy 0, policy_version 403529 (0.0011) -[2023-11-28 10:48:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206536704. Throughput: 0: 2650.1, 1: 2701.3. Samples: 206551472. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:03,445][86177] Avg episode reward: [(0, '-529.790'), (1, '-519.290')] -[2023-11-28 10:48:03,747][87426] Updated weights for policy 1, policy_version 403270 (0.0011) -[2023-11-28 10:48:03,754][87424] Updated weights for policy 0, policy_version 403539 (0.0012) -[2023-11-28 10:48:04,117][87426] Updated weights for policy 1, policy_version 403280 (0.0012) -[2023-11-28 10:48:04,134][87424] Updated weights for policy 0, policy_version 403549 (0.0011) -[2023-11-28 10:48:04,489][87426] Updated weights for policy 1, policy_version 403290 (0.0011) -[2023-11-28 10:48:06,250][87424] Updated weights for policy 0, policy_version 403559 (0.0011) -[2023-11-28 10:48:06,623][87424] Updated weights for policy 0, policy_version 403569 (0.0011) -[2023-11-28 10:48:06,788][87426] Updated weights for policy 1, policy_version 403300 (0.0011) -[2023-11-28 10:48:07,008][87424] Updated weights for policy 0, policy_version 403579 (0.0012) -[2023-11-28 10:48:07,166][87426] Updated weights for policy 1, policy_version 403310 (0.0010) -[2023-11-28 10:48:07,545][87426] Updated weights for policy 1, policy_version 403320 (0.0008) -[2023-11-28 10:48:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206569472. Throughput: 0: 2639.3, 1: 2685.0. Samples: 206583352. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:08,445][86177] Avg episode reward: [(0, '-534.060'), (1, '-525.450')] -[2023-11-28 10:48:09,200][87424] Updated weights for policy 0, policy_version 403589 (0.0010) -[2023-11-28 10:48:09,578][87424] Updated weights for policy 0, policy_version 403599 (0.0011) -[2023-11-28 10:48:09,962][87424] Updated weights for policy 0, policy_version 403609 (0.0010) -[2023-11-28 10:48:10,098][87426] Updated weights for policy 1, policy_version 403330 (0.0008) -[2023-11-28 10:48:10,466][87426] Updated weights for policy 1, policy_version 403340 (0.0010) -[2023-11-28 10:48:10,845][87426] Updated weights for policy 1, policy_version 403350 (0.0011) -[2023-11-28 10:48:11,225][87426] Updated weights for policy 1, policy_version 403360 (0.0010) -[2023-11-28 10:48:12,228][87424] Updated weights for policy 0, policy_version 403619 (0.0010) -[2023-11-28 10:48:12,613][87424] Updated weights for policy 0, policy_version 403629 (0.0012) -[2023-11-28 10:48:12,995][87424] Updated weights for policy 0, policy_version 403639 (0.0012) -[2023-11-28 10:48:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206594048. Throughput: 0: 2654.2, 1: 2683.6. Samples: 206607316. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:13,445][86177] Avg episode reward: [(0, '-533.150'), (1, '-531.180')] -[2023-11-28 10:48:13,598][87426] Updated weights for policy 1, policy_version 403370 (0.0012) -[2023-11-28 10:48:13,971][87426] Updated weights for policy 1, policy_version 403380 (0.0009) -[2023-11-28 10:48:14,351][87426] Updated weights for policy 1, policy_version 403390 (0.0008) -[2023-11-28 10:48:15,235][87424] Updated weights for policy 0, policy_version 403649 (0.0010) -[2023-11-28 10:48:15,608][87424] Updated weights for policy 0, policy_version 403659 (0.0009) -[2023-11-28 10:48:15,997][87424] Updated weights for policy 0, policy_version 403669 (0.0011) -[2023-11-28 10:48:16,369][87424] Updated weights for policy 0, policy_version 403679 (0.0008) -[2023-11-28 10:48:16,823][87426] Updated weights for policy 1, policy_version 403400 (0.0011) -[2023-11-28 10:48:17,201][87426] Updated weights for policy 1, policy_version 403410 (0.0012) -[2023-11-28 10:48:17,568][87426] Updated weights for policy 1, policy_version 403420 (0.0012) -[2023-11-28 10:48:18,327][87424] Updated weights for policy 0, policy_version 403689 (0.0011) -[2023-11-28 10:48:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206618624. Throughput: 0: 2640.8, 1: 2701.8. Samples: 206631944. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:18,445][86177] Avg episode reward: [(0, '-530.050'), (1, '-536.800')] -[2023-11-28 10:48:18,457][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000403424_103276544.pth... -[2023-11-28 10:48:18,496][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000400928_102637568.pth -[2023-11-28 10:48:18,706][87424] Updated weights for policy 0, policy_version 403699 (0.0012) -[2023-11-28 10:48:19,092][87424] Updated weights for policy 0, policy_version 403709 (0.0012) -[2023-11-28 10:48:19,208][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000403712_103350272.pth... -[2023-11-28 10:48:19,254][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000401184_102703104.pth -[2023-11-28 10:48:19,829][87426] Updated weights for policy 1, policy_version 403430 (0.0012) -[2023-11-28 10:48:20,209][87426] Updated weights for policy 1, policy_version 403440 (0.0012) -[2023-11-28 10:48:20,592][87426] Updated weights for policy 1, policy_version 403450 (0.0012) -[2023-11-28 10:48:21,212][87424] Updated weights for policy 0, policy_version 403719 (0.0012) -[2023-11-28 10:48:21,586][87424] Updated weights for policy 0, policy_version 403729 (0.0012) -[2023-11-28 10:48:21,967][87424] Updated weights for policy 0, policy_version 403739 (0.0010) -[2023-11-28 10:48:23,089][87426] Updated weights for policy 1, policy_version 403460 (0.0011) -[2023-11-28 10:48:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206643200. Throughput: 0: 2622.8, 1: 2692.4. Samples: 206663380. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:23,445][86177] Avg episode reward: [(0, '-532.040'), (1, '-538.860')] -[2023-11-28 10:48:23,472][87426] Updated weights for policy 1, policy_version 403470 (0.0012) -[2023-11-28 10:48:23,853][87426] Updated weights for policy 1, policy_version 403480 (0.0012) -[2023-11-28 10:48:24,566][87424] Updated weights for policy 0, policy_version 403749 (0.0012) -[2023-11-28 10:48:24,946][87424] Updated weights for policy 0, policy_version 403759 (0.0010) -[2023-11-28 10:48:25,321][87424] Updated weights for policy 0, policy_version 403769 (0.0008) -[2023-11-28 10:48:25,974][87426] Updated weights for policy 1, policy_version 403490 (0.0011) -[2023-11-28 10:48:26,356][87426] Updated weights for policy 1, policy_version 403500 (0.0009) -[2023-11-28 10:48:26,741][87426] Updated weights for policy 1, policy_version 403510 (0.0010) -[2023-11-28 10:48:27,110][87426] Updated weights for policy 1, policy_version 403520 (0.0008) -[2023-11-28 10:48:27,188][87424] Updated weights for policy 0, policy_version 403779 (0.0010) -[2023-11-28 10:48:27,579][87424] Updated weights for policy 0, policy_version 403789 (0.0011) -[2023-11-28 10:48:27,968][87424] Updated weights for policy 0, policy_version 403799 (0.0011) -[2023-11-28 10:48:28,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206675968. Throughput: 0: 2630.0, 1: 2710.5. Samples: 206687992. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:28,445][86177] Avg episode reward: [(0, '-513.490'), (1, '-533.540')] -[2023-11-28 10:48:28,982][87426] Updated weights for policy 1, policy_version 403530 (0.0011) -[2023-11-28 10:48:29,366][87426] Updated weights for policy 1, policy_version 403540 (0.0011) -[2023-11-28 10:48:29,736][87426] Updated weights for policy 1, policy_version 403550 (0.0012) -[2023-11-28 10:48:30,108][87424] Updated weights for policy 0, policy_version 403809 (0.0011) -[2023-11-28 10:48:30,493][87424] Updated weights for policy 0, policy_version 403819 (0.0011) -[2023-11-28 10:48:30,873][87424] Updated weights for policy 0, policy_version 403829 (0.0009) -[2023-11-28 10:48:31,258][87424] Updated weights for policy 0, policy_version 403839 (0.0011) -[2023-11-28 10:48:31,551][87426] Updated weights for policy 1, policy_version 403560 (0.0011) -[2023-11-28 10:48:31,931][87426] Updated weights for policy 1, policy_version 403570 (0.0011) -[2023-11-28 10:48:32,312][87426] Updated weights for policy 1, policy_version 403580 (0.0012) -[2023-11-28 10:48:33,132][87424] Updated weights for policy 0, policy_version 403849 (0.0012) -[2023-11-28 10:48:33,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206700544. Throughput: 0: 2662.2, 1: 2722.3. Samples: 206713416. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:33,445][86177] Avg episode reward: [(0, '-513.350'), (1, '-533.840')] -[2023-11-28 10:48:33,510][87424] Updated weights for policy 0, policy_version 403859 (0.0012) -[2023-11-28 10:48:33,897][87424] Updated weights for policy 0, policy_version 403869 (0.0012) -[2023-11-28 10:48:34,507][87426] Updated weights for policy 1, policy_version 403590 (0.0012) -[2023-11-28 10:48:34,887][87426] Updated weights for policy 1, policy_version 403600 (0.0010) -[2023-11-28 10:48:35,270][87426] Updated weights for policy 1, policy_version 403610 (0.0008) -[2023-11-28 10:48:36,301][87424] Updated weights for policy 0, policy_version 403879 (0.0012) -[2023-11-28 10:48:36,683][87424] Updated weights for policy 0, policy_version 403889 (0.0012) -[2023-11-28 10:48:37,061][87424] Updated weights for policy 0, policy_version 403899 (0.0012) -[2023-11-28 10:48:37,254][87426] Updated weights for policy 1, policy_version 403620 (0.0009) -[2023-11-28 10:48:37,636][87426] Updated weights for policy 1, policy_version 403630 (0.0011) -[2023-11-28 10:48:38,006][87426] Updated weights for policy 1, policy_version 403640 (0.0012) -[2023-11-28 10:48:38,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 206733312. Throughput: 0: 2685.4, 1: 2737.7. Samples: 206746892. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:38,445][86177] Avg episode reward: [(0, '-515.990'), (1, '-549.480')] -[2023-11-28 10:48:39,017][87424] Updated weights for policy 0, policy_version 403909 (0.0011) -[2023-11-28 10:48:39,392][87424] Updated weights for policy 0, policy_version 403919 (0.0012) -[2023-11-28 10:48:39,772][87424] Updated weights for policy 0, policy_version 403929 (0.0012) -[2023-11-28 10:48:40,223][87426] Updated weights for policy 1, policy_version 403650 (0.0011) -[2023-11-28 10:48:40,597][87426] Updated weights for policy 1, policy_version 403660 (0.0011) -[2023-11-28 10:48:40,974][87426] Updated weights for policy 1, policy_version 403670 (0.0009) -[2023-11-28 10:48:41,354][87426] Updated weights for policy 1, policy_version 403680 (0.0011) -[2023-11-28 10:48:42,362][87424] Updated weights for policy 0, policy_version 403939 (0.0012) -[2023-11-28 10:48:42,744][87424] Updated weights for policy 0, policy_version 403949 (0.0011) -[2023-11-28 10:48:43,123][87424] Updated weights for policy 0, policy_version 403959 (0.0012) -[2023-11-28 10:48:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 206749696. Throughput: 0: 2709.8, 1: 2712.3. Samples: 206771360. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:43,445][86177] Avg episode reward: [(0, '-511.410'), (1, '-547.860')] -[2023-11-28 10:48:43,833][87426] Updated weights for policy 1, policy_version 403690 (0.0009) -[2023-11-28 10:48:44,206][87426] Updated weights for policy 1, policy_version 403700 (0.0008) -[2023-11-28 10:48:44,592][87426] Updated weights for policy 1, policy_version 403710 (0.0008) -[2023-11-28 10:48:45,167][87424] Updated weights for policy 0, policy_version 403969 (0.0011) -[2023-11-28 10:48:45,547][87424] Updated weights for policy 0, policy_version 403979 (0.0011) -[2023-11-28 10:48:45,929][87424] Updated weights for policy 0, policy_version 403989 (0.0012) -[2023-11-28 10:48:46,317][87424] Updated weights for policy 0, policy_version 403999 (0.0011) -[2023-11-28 10:48:46,453][87426] Updated weights for policy 1, policy_version 403720 (0.0009) -[2023-11-28 10:48:46,833][87426] Updated weights for policy 1, policy_version 403730 (0.0009) -[2023-11-28 10:48:47,202][87426] Updated weights for policy 1, policy_version 403740 (0.0007) -[2023-11-28 10:48:48,307][87424] Updated weights for policy 0, policy_version 404009 (0.0008) -[2023-11-28 10:48:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206782464. Throughput: 0: 2686.8, 1: 2713.2. Samples: 206794472. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:48,445][86177] Avg episode reward: [(0, '-522.000'), (1, '-543.760')] -[2023-11-28 10:48:48,687][87424] Updated weights for policy 0, policy_version 404019 (0.0008) -[2023-11-28 10:48:49,072][87424] Updated weights for policy 0, policy_version 404029 (0.0009) -[2023-11-28 10:48:49,569][87426] Updated weights for policy 1, policy_version 403750 (0.0008) -[2023-11-28 10:48:49,956][87426] Updated weights for policy 1, policy_version 403760 (0.0010) -[2023-11-28 10:48:50,336][87426] Updated weights for policy 1, policy_version 403770 (0.0011) -[2023-11-28 10:48:51,351][87424] Updated weights for policy 0, policy_version 404039 (0.0010) -[2023-11-28 10:48:51,732][87424] Updated weights for policy 0, policy_version 404049 (0.0011) -[2023-11-28 10:48:52,117][87424] Updated weights for policy 0, policy_version 404059 (0.0009) -[2023-11-28 10:48:52,714][87426] Updated weights for policy 1, policy_version 403780 (0.0011) -[2023-11-28 10:48:53,088][87426] Updated weights for policy 1, policy_version 403790 (0.0011) -[2023-11-28 10:48:53,448][86177] Fps is (10 sec: 5732.3, 60 sec: 5461.0, 300 sec: 5359.4). Total num frames: 206807040. Throughput: 0: 2705.2, 1: 2716.8. Samples: 206827364. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:53,449][86177] Avg episode reward: [(0, '-534.620'), (1, '-547.100')] -[2023-11-28 10:48:53,465][87426] Updated weights for policy 1, policy_version 403800 (0.0012) -[2023-11-28 10:48:54,303][87424] Updated weights for policy 0, policy_version 404069 (0.0012) -[2023-11-28 10:48:54,678][87424] Updated weights for policy 0, policy_version 404079 (0.0012) -[2023-11-28 10:48:55,063][87424] Updated weights for policy 0, policy_version 404089 (0.0009) -[2023-11-28 10:48:55,646][87426] Updated weights for policy 1, policy_version 403810 (0.0010) -[2023-11-28 10:48:56,035][87426] Updated weights for policy 1, policy_version 403820 (0.0008) -[2023-11-28 10:48:56,414][87426] Updated weights for policy 1, policy_version 403830 (0.0007) -[2023-11-28 10:48:56,789][87426] Updated weights for policy 1, policy_version 403840 (0.0007) -[2023-11-28 10:48:56,912][87424] Updated weights for policy 0, policy_version 404099 (0.0010) -[2023-11-28 10:48:57,304][87424] Updated weights for policy 0, policy_version 404109 (0.0007) -[2023-11-28 10:48:57,692][87424] Updated weights for policy 0, policy_version 404119 (0.0007) -[2023-11-28 10:48:58,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206839808. Throughput: 0: 2714.2, 1: 2717.9. Samples: 206851760. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:48:58,445][86177] Avg episode reward: [(0, '-550.060'), (1, '-526.830')] -[2023-11-28 10:48:58,788][87426] Updated weights for policy 1, policy_version 403850 (0.0007) -[2023-11-28 10:48:59,170][87426] Updated weights for policy 1, policy_version 403860 (0.0008) -[2023-11-28 10:48:59,553][87426] Updated weights for policy 1, policy_version 403870 (0.0007) -[2023-11-28 10:48:59,662][87424] Updated weights for policy 0, policy_version 404129 (0.0008) -[2023-11-28 10:49:00,045][87424] Updated weights for policy 0, policy_version 404139 (0.0012) -[2023-11-28 10:49:00,424][87424] Updated weights for policy 0, policy_version 404149 (0.0012) -[2023-11-28 10:49:00,803][87424] Updated weights for policy 0, policy_version 404159 (0.0012) -[2023-11-28 10:49:01,769][87426] Updated weights for policy 1, policy_version 403880 (0.0010) -[2023-11-28 10:49:02,151][87426] Updated weights for policy 1, policy_version 403890 (0.0011) -[2023-11-28 10:49:02,528][87426] Updated weights for policy 1, policy_version 403900 (0.0012) -[2023-11-28 10:49:03,111][87424] Updated weights for policy 0, policy_version 404169 (0.0012) -[2023-11-28 10:49:03,444][86177] Fps is (10 sec: 5736.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206864384. Throughput: 0: 2730.9, 1: 2697.6. Samples: 206876224. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:49:03,445][86177] Avg episode reward: [(0, '-567.590'), (1, '-526.830')] -[2023-11-28 10:49:03,505][87424] Updated weights for policy 0, policy_version 404179 (0.0012) -[2023-11-28 10:49:03,886][87424] Updated weights for policy 0, policy_version 404189 (0.0012) -[2023-11-28 10:49:04,532][87426] Updated weights for policy 1, policy_version 403910 (0.0012) -[2023-11-28 10:49:04,913][87426] Updated weights for policy 1, policy_version 403920 (0.0012) -[2023-11-28 10:49:05,298][87426] Updated weights for policy 1, policy_version 403930 (0.0012) -[2023-11-28 10:49:06,176][87424] Updated weights for policy 0, policy_version 404199 (0.0012) -[2023-11-28 10:49:06,554][87424] Updated weights for policy 0, policy_version 404209 (0.0011) -[2023-11-28 10:49:06,938][87424] Updated weights for policy 0, policy_version 404219 (0.0010) -[2023-11-28 10:49:07,368][87426] Updated weights for policy 1, policy_version 403940 (0.0011) -[2023-11-28 10:49:07,743][87426] Updated weights for policy 1, policy_version 403950 (0.0009) -[2023-11-28 10:49:08,127][87426] Updated weights for policy 1, policy_version 403960 (0.0012) -[2023-11-28 10:49:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206897152. Throughput: 0: 2753.3, 1: 2725.5. Samples: 206909928. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:49:08,445][86177] Avg episode reward: [(0, '-567.020'), (1, '-527.530')] -[2023-11-28 10:49:09,302][87424] Updated weights for policy 0, policy_version 404229 (0.0012) -[2023-11-28 10:49:09,685][87424] Updated weights for policy 0, policy_version 404239 (0.0012) -[2023-11-28 10:49:10,052][87426] Updated weights for policy 1, policy_version 403970 (0.0008) -[2023-11-28 10:49:10,063][87424] Updated weights for policy 0, policy_version 404249 (0.0011) -[2023-11-28 10:49:10,436][87426] Updated weights for policy 1, policy_version 403980 (0.0011) -[2023-11-28 10:49:10,811][87426] Updated weights for policy 1, policy_version 403990 (0.0010) -[2023-11-28 10:49:11,191][87426] Updated weights for policy 1, policy_version 404000 (0.0011) -[2023-11-28 10:49:12,073][87424] Updated weights for policy 0, policy_version 404259 (0.0011) -[2023-11-28 10:49:12,459][87424] Updated weights for policy 0, policy_version 404269 (0.0011) -[2023-11-28 10:49:12,831][87424] Updated weights for policy 0, policy_version 404279 (0.0011) -[2023-11-28 10:49:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206921728. Throughput: 0: 2762.4, 1: 2719.2. Samples: 206934664. Policy #0 lag: (min: 31.0, avg: 40.9, max: 63.0) -[2023-11-28 10:49:13,445][86177] Avg episode reward: [(0, '-569.800'), (1, '-533.640')] -[2023-11-28 10:49:13,563][87426] Updated weights for policy 1, policy_version 404010 (0.0011) -[2023-11-28 10:49:13,942][87426] Updated weights for policy 1, policy_version 404020 (0.0008) -[2023-11-28 10:49:14,319][87426] Updated weights for policy 1, policy_version 404030 (0.0007) -[2023-11-28 10:49:15,284][87424] Updated weights for policy 0, policy_version 404289 (0.0011) -[2023-11-28 10:49:15,663][87424] Updated weights for policy 0, policy_version 404299 (0.0012) -[2023-11-28 10:49:16,047][87424] Updated weights for policy 0, policy_version 404309 (0.0016) -[2023-11-28 10:49:16,432][87424] Updated weights for policy 0, policy_version 404319 (0.0011) -[2023-11-28 10:49:16,616][87426] Updated weights for policy 1, policy_version 404040 (0.0011) -[2023-11-28 10:49:16,998][87426] Updated weights for policy 1, policy_version 404050 (0.0011) -[2023-11-28 10:49:17,382][87426] Updated weights for policy 1, policy_version 404060 (0.0012) -[2023-11-28 10:49:18,310][87424] Updated weights for policy 0, policy_version 404329 (0.0009) -[2023-11-28 10:49:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 206946304. Throughput: 0: 2736.6, 1: 2714.8. Samples: 206958728. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:49:18,445][86177] Avg episode reward: [(0, '-604.510'), (1, '-557.120')] -[2023-11-28 10:49:18,695][87424] Updated weights for policy 0, policy_version 404339 (0.0010) -[2023-11-28 10:49:19,100][87424] Updated weights for policy 0, policy_version 404349 (0.0009) -[2023-11-28 10:49:19,219][87426] Updated weights for policy 1, policy_version 404070 (0.0010) -[2023-11-28 10:49:19,596][87426] Updated weights for policy 1, policy_version 404080 (0.0008) -[2023-11-28 10:49:19,975][87426] Updated weights for policy 1, policy_version 404090 (0.0012) -[2023-11-28 10:49:21,211][87424] Updated weights for policy 0, policy_version 404359 (0.0012) -[2023-11-28 10:49:21,601][87424] Updated weights for policy 0, policy_version 404369 (0.0012) -[2023-11-28 10:49:21,981][87424] Updated weights for policy 0, policy_version 404379 (0.0012) -[2023-11-28 10:49:22,321][87426] Updated weights for policy 1, policy_version 404100 (0.0012) -[2023-11-28 10:49:22,703][87426] Updated weights for policy 1, policy_version 404110 (0.0011) -[2023-11-28 10:49:23,088][87426] Updated weights for policy 1, policy_version 404120 (0.0010) -[2023-11-28 10:49:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5597.9, 300 sec: 5387.3). Total num frames: 206979072. Throughput: 0: 2723.9, 1: 2703.8. Samples: 206991140. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:49:23,445][86177] Avg episode reward: [(0, '-587.950'), (1, '-560.290')] -[2023-11-28 10:49:24,201][87424] Updated weights for policy 0, policy_version 404389 (0.0012) -[2023-11-28 10:49:24,587][87424] Updated weights for policy 0, policy_version 404399 (0.0011) -[2023-11-28 10:49:24,974][87424] Updated weights for policy 0, policy_version 404409 (0.0011) -[2023-11-28 10:49:25,689][87426] Updated weights for policy 1, policy_version 404130 (0.0012) -[2023-11-28 10:49:26,071][87426] Updated weights for policy 1, policy_version 404140 (0.0011) -[2023-11-28 10:49:26,456][87426] Updated weights for policy 1, policy_version 404150 (0.0008) -[2023-11-28 10:49:26,700][87424] Updated weights for policy 0, policy_version 404419 (0.0009) -[2023-11-28 10:49:26,832][87426] Updated weights for policy 1, policy_version 404160 (0.0007) -[2023-11-28 10:49:27,075][87424] Updated weights for policy 0, policy_version 404429 (0.0012) -[2023-11-28 10:49:27,455][87424] Updated weights for policy 0, policy_version 404439 (0.0010) -[2023-11-28 10:49:28,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207003648. Throughput: 0: 2733.4, 1: 2711.0. Samples: 207016360. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:49:28,445][86177] Avg episode reward: [(0, '-575.310'), (1, '-559.880')] -[2023-11-28 10:49:28,554][87426] Updated weights for policy 1, policy_version 404170 (0.0009) -[2023-11-28 10:49:28,934][87426] Updated weights for policy 1, policy_version 404180 (0.0008) -[2023-11-28 10:49:29,317][87426] Updated weights for policy 1, policy_version 404190 (0.0007) -[2023-11-28 10:49:29,906][87424] Updated weights for policy 0, policy_version 404449 (0.0008) -[2023-11-28 10:49:30,297][87424] Updated weights for policy 0, policy_version 404459 (0.0009) -[2023-11-28 10:49:30,682][87424] Updated weights for policy 0, policy_version 404469 (0.0010) -[2023-11-28 10:49:31,058][87424] Updated weights for policy 0, policy_version 404479 (0.0008) -[2023-11-28 10:49:31,511][87426] Updated weights for policy 1, policy_version 404200 (0.0011) -[2023-11-28 10:49:31,895][87426] Updated weights for policy 1, policy_version 404210 (0.0011) -[2023-11-28 10:49:32,279][87426] Updated weights for policy 1, policy_version 404220 (0.0010) -[2023-11-28 10:49:32,911][87424] Updated weights for policy 0, policy_version 404489 (0.0012) -[2023-11-28 10:49:33,297][87424] Updated weights for policy 0, policy_version 404499 (0.0012) -[2023-11-28 10:49:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207028224. Throughput: 0: 2782.0, 1: 2708.4. Samples: 207041540. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:49:33,445][86177] Avg episode reward: [(0, '-573.570'), (1, '-547.360')] -[2023-11-28 10:49:33,674][87424] Updated weights for policy 0, policy_version 404509 (0.0012) -[2023-11-28 10:49:34,677][87426] Updated weights for policy 1, policy_version 404230 (0.0011) -[2023-11-28 10:49:35,055][87426] Updated weights for policy 1, policy_version 404240 (0.0012) -[2023-11-28 10:49:35,433][87426] Updated weights for policy 1, policy_version 404250 (0.0012) -[2023-11-28 10:49:36,228][87424] Updated weights for policy 0, policy_version 404519 (0.0011) -[2023-11-28 10:49:36,613][87424] Updated weights for policy 0, policy_version 404529 (0.0009) -[2023-11-28 10:49:36,993][87424] Updated weights for policy 0, policy_version 404539 (0.0008) -[2023-11-28 10:49:37,431][87426] Updated weights for policy 1, policy_version 404260 (0.0011) -[2023-11-28 10:49:37,799][87426] Updated weights for policy 1, policy_version 404270 (0.0008) -[2023-11-28 10:49:38,186][87426] Updated weights for policy 1, policy_version 404280 (0.0007) -[2023-11-28 10:49:38,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 207052800. Throughput: 0: 2766.9, 1: 2714.4. Samples: 207074004. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:49:38,445][86177] Avg episode reward: [(0, '-535.690'), (1, '-522.920')] -[2023-11-28 10:49:39,545][87424] Updated weights for policy 0, policy_version 404549 (0.0010) -[2023-11-28 10:49:39,933][87424] Updated weights for policy 0, policy_version 404559 (0.0012) -[2023-11-28 10:49:40,315][87424] Updated weights for policy 0, policy_version 404569 (0.0013) -[2023-11-28 10:49:40,726][87426] Updated weights for policy 1, policy_version 404290 (0.0009) -[2023-11-28 10:49:41,104][87426] Updated weights for policy 1, policy_version 404300 (0.0011) -[2023-11-28 10:49:41,481][87426] Updated weights for policy 1, policy_version 404310 (0.0012) -[2023-11-28 10:49:41,855][87426] Updated weights for policy 1, policy_version 404320 (0.0012) -[2023-11-28 10:49:42,951][87424] Updated weights for policy 0, policy_version 404579 (0.0011) -[2023-11-28 10:49:43,337][87424] Updated weights for policy 0, policy_version 404589 (0.0012) -[2023-11-28 10:49:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 207077376. Throughput: 0: 2738.4, 1: 2695.6. Samples: 207096288. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:49:43,445][86177] Avg episode reward: [(0, '-565.770'), (1, '-518.620')] -[2023-11-28 10:49:43,711][87424] Updated weights for policy 0, policy_version 404599 (0.0009) -[2023-11-28 10:49:44,363][87426] Updated weights for policy 1, policy_version 404330 (0.0009) -[2023-11-28 10:49:44,745][87426] Updated weights for policy 1, policy_version 404340 (0.0011) -[2023-11-28 10:49:45,130][87426] Updated weights for policy 1, policy_version 404350 (0.0012) -[2023-11-28 10:49:46,038][87424] Updated weights for policy 0, policy_version 404609 (0.0009) -[2023-11-28 10:49:46,427][87424] Updated weights for policy 0, policy_version 404619 (0.0010) -[2023-11-28 10:49:46,800][87424] Updated weights for policy 0, policy_version 404629 (0.0011) -[2023-11-28 10:49:47,091][87426] Updated weights for policy 1, policy_version 404360 (0.0011) -[2023-11-28 10:49:47,176][87424] Updated weights for policy 0, policy_version 404639 (0.0010) -[2023-11-28 10:49:47,471][87426] Updated weights for policy 1, policy_version 404370 (0.0011) -[2023-11-28 10:49:47,838][87426] Updated weights for policy 1, policy_version 404380 (0.0012) -[2023-11-28 10:49:48,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207110144. Throughput: 0: 2713.7, 1: 2710.7. Samples: 207120320. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:49:48,445][86177] Avg episode reward: [(0, '-581.430'), (1, '-519.440')] -[2023-11-28 10:49:49,049][87424] Updated weights for policy 0, policy_version 404649 (0.0011) -[2023-11-28 10:49:49,442][87424] Updated weights for policy 0, policy_version 404659 (0.0008) -[2023-11-28 10:49:49,816][87424] Updated weights for policy 0, policy_version 404669 (0.0009) -[2023-11-28 10:49:50,474][87426] Updated weights for policy 1, policy_version 404390 (0.0012) -[2023-11-28 10:49:50,858][87426] Updated weights for policy 1, policy_version 404400 (0.0012) -[2023-11-28 10:49:51,240][87426] Updated weights for policy 1, policy_version 404410 (0.0010) -[2023-11-28 10:49:52,044][87424] Updated weights for policy 0, policy_version 404679 (0.0011) -[2023-11-28 10:49:52,422][87424] Updated weights for policy 0, policy_version 404689 (0.0012) -[2023-11-28 10:49:52,800][87424] Updated weights for policy 0, policy_version 404699 (0.0012) -[2023-11-28 10:49:53,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.7, 300 sec: 5387.3). Total num frames: 207134720. Throughput: 0: 2674.8, 1: 2679.9. Samples: 207150892. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:49:53,445][86177] Avg episode reward: [(0, '-597.470'), (1, '-509.410')] -[2023-11-28 10:49:53,613][87426] Updated weights for policy 1, policy_version 404420 (0.0009) -[2023-11-28 10:49:53,999][87426] Updated weights for policy 1, policy_version 404430 (0.0010) -[2023-11-28 10:49:54,378][87426] Updated weights for policy 1, policy_version 404440 (0.0010) -[2023-11-28 10:49:55,433][87424] Updated weights for policy 0, policy_version 404709 (0.0024) -[2023-11-28 10:49:55,816][87424] Updated weights for policy 0, policy_version 404719 (0.0007) -[2023-11-28 10:49:56,209][87424] Updated weights for policy 0, policy_version 404729 (0.0010) -[2023-11-28 10:49:56,863][87426] Updated weights for policy 1, policy_version 404450 (0.0010) -[2023-11-28 10:49:57,248][87426] Updated weights for policy 1, policy_version 404460 (0.0008) -[2023-11-28 10:49:57,627][87426] Updated weights for policy 1, policy_version 404470 (0.0007) -[2023-11-28 10:49:58,002][87426] Updated weights for policy 1, policy_version 404480 (0.0010) -[2023-11-28 10:49:58,080][87424] Updated weights for policy 0, policy_version 404739 (0.0009) -[2023-11-28 10:49:58,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 207159296. Throughput: 0: 2667.6, 1: 2665.2. Samples: 207174640. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:49:58,445][86177] Avg episode reward: [(0, '-590.070'), (1, '-515.210')] -[2023-11-28 10:49:58,460][87424] Updated weights for policy 0, policy_version 404749 (0.0009) -[2023-11-28 10:49:58,842][87424] Updated weights for policy 0, policy_version 404759 (0.0008) -[2023-11-28 10:50:00,317][87426] Updated weights for policy 1, policy_version 404490 (0.0012) -[2023-11-28 10:50:00,694][87426] Updated weights for policy 1, policy_version 404500 (0.0009) -[2023-11-28 10:50:00,993][87424] Updated weights for policy 0, policy_version 404769 (0.0008) -[2023-11-28 10:50:01,067][87426] Updated weights for policy 1, policy_version 404510 (0.0010) -[2023-11-28 10:50:01,377][87424] Updated weights for policy 0, policy_version 404779 (0.0011) -[2023-11-28 10:50:01,756][87424] Updated weights for policy 0, policy_version 404789 (0.0010) -[2023-11-28 10:50:02,147][87424] Updated weights for policy 0, policy_version 404799 (0.0011) -[2023-11-28 10:50:03,092][87426] Updated weights for policy 1, policy_version 404520 (0.0011) -[2023-11-28 10:50:03,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 207183872. Throughput: 0: 2692.1, 1: 2659.1. Samples: 207199532. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:50:03,446][86177] Avg episode reward: [(0, '-555.890'), (1, '-523.570')] -[2023-11-28 10:50:03,482][87426] Updated weights for policy 1, policy_version 404530 (0.0012) -[2023-11-28 10:50:03,855][87426] Updated weights for policy 1, policy_version 404540 (0.0011) -[2023-11-28 10:50:04,686][87424] Updated weights for policy 0, policy_version 404809 (0.0009) -[2023-11-28 10:50:05,066][87424] Updated weights for policy 0, policy_version 404819 (0.0011) -[2023-11-28 10:50:05,440][87424] Updated weights for policy 0, policy_version 404829 (0.0008) -[2023-11-28 10:50:06,135][87426] Updated weights for policy 1, policy_version 404550 (0.0011) -[2023-11-28 10:50:06,515][87426] Updated weights for policy 1, policy_version 404560 (0.0012) -[2023-11-28 10:50:06,898][87426] Updated weights for policy 1, policy_version 404570 (0.0011) -[2023-11-28 10:50:07,262][87424] Updated weights for policy 0, policy_version 404839 (0.0011) -[2023-11-28 10:50:07,643][87424] Updated weights for policy 0, policy_version 404849 (0.0009) -[2023-11-28 10:50:08,026][87424] Updated weights for policy 0, policy_version 404859 (0.0007) -[2023-11-28 10:50:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 207216640. Throughput: 0: 2679.5, 1: 2664.1. Samples: 207231600. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:50:08,445][86177] Avg episode reward: [(0, '-541.760'), (1, '-521.930')] -[2023-11-28 10:50:08,836][87426] Updated weights for policy 1, policy_version 404580 (0.0012) -[2023-11-28 10:50:09,224][87426] Updated weights for policy 1, policy_version 404590 (0.0011) -[2023-11-28 10:50:09,601][87426] Updated weights for policy 1, policy_version 404600 (0.0012) -[2023-11-28 10:50:10,432][87424] Updated weights for policy 0, policy_version 404869 (0.0009) -[2023-11-28 10:50:10,811][87424] Updated weights for policy 0, policy_version 404879 (0.0010) -[2023-11-28 10:50:11,203][87424] Updated weights for policy 0, policy_version 404889 (0.0011) -[2023-11-28 10:50:11,940][87426] Updated weights for policy 1, policy_version 404610 (0.0016) -[2023-11-28 10:50:12,314][87426] Updated weights for policy 1, policy_version 404620 (0.0010) -[2023-11-28 10:50:12,683][87426] Updated weights for policy 1, policy_version 404630 (0.0012) -[2023-11-28 10:50:13,065][87426] Updated weights for policy 1, policy_version 404640 (0.0011) -[2023-11-28 10:50:13,444][86177] Fps is (10 sec: 5734.5, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 207241216. Throughput: 0: 2648.5, 1: 2672.8. Samples: 207255816. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:50:13,445][86177] Avg episode reward: [(0, '-526.560'), (1, '-526.030')] -[2023-11-28 10:50:13,667][87424] Updated weights for policy 0, policy_version 404899 (0.0012) -[2023-11-28 10:50:14,047][87424] Updated weights for policy 0, policy_version 404909 (0.0012) -[2023-11-28 10:50:14,429][87424] Updated weights for policy 0, policy_version 404919 (0.0012) -[2023-11-28 10:50:14,935][87426] Updated weights for policy 1, policy_version 404650 (0.0012) -[2023-11-28 10:50:15,312][87426] Updated weights for policy 1, policy_version 404660 (0.0012) -[2023-11-28 10:50:15,683][87426] Updated weights for policy 1, policy_version 404670 (0.0012) -[2023-11-28 10:50:16,748][87424] Updated weights for policy 0, policy_version 404929 (0.0012) -[2023-11-28 10:50:17,127][87424] Updated weights for policy 0, policy_version 404939 (0.0011) -[2023-11-28 10:50:17,509][87424] Updated weights for policy 0, policy_version 404949 (0.0012) -[2023-11-28 10:50:17,719][87426] Updated weights for policy 1, policy_version 404680 (0.0011) -[2023-11-28 10:50:17,903][87424] Updated weights for policy 0, policy_version 404959 (0.0010) -[2023-11-28 10:50:18,092][87426] Updated weights for policy 1, policy_version 404690 (0.0009) -[2023-11-28 10:50:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 207265792. Throughput: 0: 2605.5, 1: 2691.8. Samples: 207279920. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:50:18,445][86177] Avg episode reward: [(0, '-504.390'), (1, '-523.910')] -[2023-11-28 10:50:18,452][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000404960_103669760.pth... -[2023-11-28 10:50:18,470][87426] Updated weights for policy 1, policy_version 404700 (0.0007) -[2023-11-28 10:50:18,482][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000402432_103022592.pth -[2023-11-28 10:50:18,616][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000404704_103604224.pth... -[2023-11-28 10:50:18,646][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000402176_102957056.pth -[2023-11-28 10:50:19,778][87424] Updated weights for policy 0, policy_version 404969 (0.0009) -[2023-11-28 10:50:20,163][87424] Updated weights for policy 0, policy_version 404979 (0.0010) -[2023-11-28 10:50:20,543][87426] Updated weights for policy 1, policy_version 404710 (0.0009) -[2023-11-28 10:50:20,544][87424] Updated weights for policy 0, policy_version 404989 (0.0011) -[2023-11-28 10:50:20,926][87426] Updated weights for policy 1, policy_version 404720 (0.0012) -[2023-11-28 10:50:21,316][87426] Updated weights for policy 1, policy_version 404730 (0.0012) -[2023-11-28 10:50:23,148][87424] Updated weights for policy 0, policy_version 404999 (0.0011) -[2023-11-28 10:50:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 207290368. Throughput: 0: 2597.9, 1: 2668.1. Samples: 207310972. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:50:23,445][86177] Avg episode reward: [(0, '-510.730'), (1, '-529.900')] -[2023-11-28 10:50:23,527][87424] Updated weights for policy 0, policy_version 405009 (0.0010) -[2023-11-28 10:50:23,869][87426] Updated weights for policy 1, policy_version 404740 (0.0010) -[2023-11-28 10:50:23,909][87424] Updated weights for policy 0, policy_version 405019 (0.0008) -[2023-11-28 10:50:24,249][87426] Updated weights for policy 1, policy_version 404750 (0.0008) -[2023-11-28 10:50:24,634][87426] Updated weights for policy 1, policy_version 404760 (0.0012) -[2023-11-28 10:50:25,980][87424] Updated weights for policy 0, policy_version 405029 (0.0010) -[2023-11-28 10:50:26,356][87424] Updated weights for policy 0, policy_version 405039 (0.0012) -[2023-11-28 10:50:26,729][87424] Updated weights for policy 0, policy_version 405049 (0.0010) -[2023-11-28 10:50:26,874][87426] Updated weights for policy 1, policy_version 404770 (0.0012) -[2023-11-28 10:50:27,251][87426] Updated weights for policy 1, policy_version 404780 (0.0012) -[2023-11-28 10:50:27,630][87426] Updated weights for policy 1, policy_version 404790 (0.0012) -[2023-11-28 10:50:28,010][87426] Updated weights for policy 1, policy_version 404800 (0.0010) -[2023-11-28 10:50:28,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 207323136. Throughput: 0: 2614.0, 1: 2680.0. Samples: 207334516. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:50:28,445][86177] Avg episode reward: [(0, '-520.670'), (1, '-528.540')] -[2023-11-28 10:50:29,028][87424] Updated weights for policy 0, policy_version 405059 (0.0008) -[2023-11-28 10:50:29,408][87424] Updated weights for policy 0, policy_version 405069 (0.0010) -[2023-11-28 10:50:29,791][87424] Updated weights for policy 0, policy_version 405079 (0.0009) -[2023-11-28 10:50:30,307][87426] Updated weights for policy 1, policy_version 404810 (0.0011) -[2023-11-28 10:50:30,676][87426] Updated weights for policy 1, policy_version 404820 (0.0012) -[2023-11-28 10:50:31,058][87426] Updated weights for policy 1, policy_version 404830 (0.0012) -[2023-11-28 10:50:32,297][87424] Updated weights for policy 0, policy_version 405089 (0.0009) -[2023-11-28 10:50:32,679][87424] Updated weights for policy 0, policy_version 405099 (0.0012) -[2023-11-28 10:50:33,063][87424] Updated weights for policy 0, policy_version 405109 (0.0011) -[2023-11-28 10:50:33,353][87426] Updated weights for policy 1, policy_version 404840 (0.0011) -[2023-11-28 10:50:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 207339520. Throughput: 0: 2618.8, 1: 2668.7. Samples: 207358256. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:50:33,445][86177] Avg episode reward: [(0, '-537.310'), (1, '-530.260')] -[2023-11-28 10:50:33,450][87424] Updated weights for policy 0, policy_version 405119 (0.0011) -[2023-11-28 10:50:33,739][87426] Updated weights for policy 1, policy_version 404850 (0.0012) -[2023-11-28 10:50:34,120][87426] Updated weights for policy 1, policy_version 404860 (0.0011) -[2023-11-28 10:50:35,668][87424] Updated weights for policy 0, policy_version 405129 (0.0012) -[2023-11-28 10:50:35,997][87426] Updated weights for policy 1, policy_version 404870 (0.0012) -[2023-11-28 10:50:36,042][87424] Updated weights for policy 0, policy_version 405139 (0.0012) -[2023-11-28 10:50:36,368][87426] Updated weights for policy 1, policy_version 404880 (0.0011) -[2023-11-28 10:50:36,430][87424] Updated weights for policy 0, policy_version 405149 (0.0009) -[2023-11-28 10:50:36,747][87426] Updated weights for policy 1, policy_version 404890 (0.0009) -[2023-11-28 10:50:38,430][87426] Updated weights for policy 1, policy_version 404900 (0.0009) -[2023-11-28 10:50:38,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 207372288. Throughput: 0: 2629.4, 1: 2702.7. Samples: 207390836. Policy #0 lag: (min: 31.0, avg: 35.4, max: 63.0) -[2023-11-28 10:50:38,445][86177] Avg episode reward: [(0, '-569.780'), (1, '-523.930')] -[2023-11-28 10:50:38,716][87424] Updated weights for policy 0, policy_version 405159 (0.0009) -[2023-11-28 10:50:38,811][87426] Updated weights for policy 1, policy_version 404910 (0.0008) -[2023-11-28 10:50:39,101][87424] Updated weights for policy 0, policy_version 405169 (0.0008) -[2023-11-28 10:50:39,195][87426] Updated weights for policy 1, policy_version 404920 (0.0012) -[2023-11-28 10:50:39,475][87424] Updated weights for policy 0, policy_version 405179 (0.0009) -[2023-11-28 10:50:41,585][87426] Updated weights for policy 1, policy_version 404930 (0.0011) -[2023-11-28 10:50:41,723][87424] Updated weights for policy 0, policy_version 405189 (0.0012) -[2023-11-28 10:50:41,964][87426] Updated weights for policy 1, policy_version 404940 (0.0011) -[2023-11-28 10:50:42,116][87424] Updated weights for policy 0, policy_version 405199 (0.0011) -[2023-11-28 10:50:42,348][87426] Updated weights for policy 1, policy_version 404950 (0.0012) -[2023-11-28 10:50:42,509][87424] Updated weights for policy 0, policy_version 405209 (0.0012) -[2023-11-28 10:50:42,727][87426] Updated weights for policy 1, policy_version 404960 (0.0009) -[2023-11-28 10:50:43,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207405056. Throughput: 0: 2628.3, 1: 2702.8. Samples: 207414540. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:50:43,445][86177] Avg episode reward: [(0, '-587.190'), (1, '-520.350')] -[2023-11-28 10:50:44,482][87424] Updated weights for policy 0, policy_version 405219 (0.0011) -[2023-11-28 10:50:44,865][87424] Updated weights for policy 0, policy_version 405229 (0.0012) -[2023-11-28 10:50:44,927][87426] Updated weights for policy 1, policy_version 404970 (0.0011) -[2023-11-28 10:50:45,248][87424] Updated weights for policy 0, policy_version 405239 (0.0011) -[2023-11-28 10:50:45,303][87426] Updated weights for policy 1, policy_version 404980 (0.0011) -[2023-11-28 10:50:45,678][87426] Updated weights for policy 1, policy_version 404990 (0.0010) -[2023-11-28 10:50:47,376][87424] Updated weights for policy 0, policy_version 405249 (0.0011) -[2023-11-28 10:50:47,751][87424] Updated weights for policy 0, policy_version 405259 (0.0009) -[2023-11-28 10:50:48,042][87426] Updated weights for policy 1, policy_version 405000 (0.0012) -[2023-11-28 10:50:48,139][87424] Updated weights for policy 0, policy_version 405269 (0.0007) -[2023-11-28 10:50:48,412][87426] Updated weights for policy 1, policy_version 405010 (0.0007) -[2023-11-28 10:50:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 207421440. Throughput: 0: 2624.6, 1: 2705.7. Samples: 207439396. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:50:48,445][86177] Avg episode reward: [(0, '-585.250'), (1, '-527.840')] -[2023-11-28 10:50:48,511][87424] Updated weights for policy 0, policy_version 405279 (0.0007) -[2023-11-28 10:50:48,801][87426] Updated weights for policy 1, policy_version 405020 (0.0007) -[2023-11-28 10:50:50,910][87424] Updated weights for policy 0, policy_version 405289 (0.0011) -[2023-11-28 10:50:51,076][87426] Updated weights for policy 1, policy_version 405030 (0.0008) -[2023-11-28 10:50:51,298][87424] Updated weights for policy 0, policy_version 405299 (0.0011) -[2023-11-28 10:50:51,466][87426] Updated weights for policy 1, policy_version 405040 (0.0010) -[2023-11-28 10:50:51,686][87424] Updated weights for policy 0, policy_version 405309 (0.0011) -[2023-11-28 10:50:51,839][87426] Updated weights for policy 1, policy_version 405050 (0.0011) -[2023-11-28 10:50:53,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 207454208. Throughput: 0: 2640.0, 1: 2699.7. Samples: 207471888. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:50:53,445][86177] Avg episode reward: [(0, '-570.680'), (1, '-531.470')] -[2023-11-28 10:50:53,730][87424] Updated weights for policy 0, policy_version 405319 (0.0011) -[2023-11-28 10:50:54,107][87424] Updated weights for policy 0, policy_version 405329 (0.0011) -[2023-11-28 10:50:54,115][87426] Updated weights for policy 1, policy_version 405060 (0.0010) -[2023-11-28 10:50:54,484][87424] Updated weights for policy 0, policy_version 405339 (0.0012) -[2023-11-28 10:50:54,492][87426] Updated weights for policy 1, policy_version 405070 (0.0008) -[2023-11-28 10:50:54,865][87426] Updated weights for policy 1, policy_version 405080 (0.0008) -[2023-11-28 10:50:56,972][87424] Updated weights for policy 0, policy_version 405349 (0.0012) -[2023-11-28 10:50:57,335][87426] Updated weights for policy 1, policy_version 405090 (0.0010) -[2023-11-28 10:50:57,363][87424] Updated weights for policy 0, policy_version 405359 (0.0011) -[2023-11-28 10:50:57,711][87426] Updated weights for policy 1, policy_version 405100 (0.0012) -[2023-11-28 10:50:57,745][87424] Updated weights for policy 0, policy_version 405369 (0.0013) -[2023-11-28 10:50:58,081][87426] Updated weights for policy 1, policy_version 405110 (0.0011) -[2023-11-28 10:50:58,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 207478784. Throughput: 0: 2649.5, 1: 2701.4. Samples: 207496608. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:50:58,445][86177] Avg episode reward: [(0, '-541.220'), (1, '-526.780')] -[2023-11-28 10:50:58,469][87426] Updated weights for policy 1, policy_version 405120 (0.0012) -[2023-11-28 10:50:59,874][87424] Updated weights for policy 0, policy_version 405379 (0.0012) -[2023-11-28 10:51:00,249][87424] Updated weights for policy 0, policy_version 405389 (0.0011) -[2023-11-28 10:51:00,299][87426] Updated weights for policy 1, policy_version 405130 (0.0010) -[2023-11-28 10:51:00,630][87424] Updated weights for policy 0, policy_version 405399 (0.0012) -[2023-11-28 10:51:00,668][87426] Updated weights for policy 1, policy_version 405140 (0.0011) -[2023-11-28 10:51:01,051][87426] Updated weights for policy 1, policy_version 405150 (0.0010) -[2023-11-28 10:51:02,641][87424] Updated weights for policy 0, policy_version 405409 (0.0011) -[2023-11-28 10:51:03,028][87424] Updated weights for policy 0, policy_version 405419 (0.0010) -[2023-11-28 10:51:03,162][87426] Updated weights for policy 1, policy_version 405160 (0.0011) -[2023-11-28 10:51:03,402][87424] Updated weights for policy 0, policy_version 405429 (0.0008) -[2023-11-28 10:51:03,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 207503360. Throughput: 0: 2684.1, 1: 2692.6. Samples: 207521872. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:03,445][86177] Avg episode reward: [(0, '-525.780'), (1, '-524.860')] -[2023-11-28 10:51:03,547][87426] Updated weights for policy 1, policy_version 405170 (0.0010) -[2023-11-28 10:51:03,782][87424] Updated weights for policy 0, policy_version 405439 (0.0009) -[2023-11-28 10:51:03,929][87426] Updated weights for policy 1, policy_version 405180 (0.0011) -[2023-11-28 10:51:06,191][87426] Updated weights for policy 1, policy_version 405190 (0.0011) -[2023-11-28 10:51:06,193][87424] Updated weights for policy 0, policy_version 405449 (0.0008) -[2023-11-28 10:51:06,567][87426] Updated weights for policy 1, policy_version 405200 (0.0009) -[2023-11-28 10:51:06,581][87424] Updated weights for policy 0, policy_version 405459 (0.0009) -[2023-11-28 10:51:06,943][87426] Updated weights for policy 1, policy_version 405210 (0.0011) -[2023-11-28 10:51:06,965][87424] Updated weights for policy 0, policy_version 405469 (0.0010) -[2023-11-28 10:51:08,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 207536128. Throughput: 0: 2686.7, 1: 2693.7. Samples: 207553088. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:08,445][86177] Avg episode reward: [(0, '-514.430'), (1, '-523.090')] -[2023-11-28 10:51:09,330][87426] Updated weights for policy 1, policy_version 405220 (0.0008) -[2023-11-28 10:51:09,426][87424] Updated weights for policy 0, policy_version 405479 (0.0011) -[2023-11-28 10:51:09,695][87426] Updated weights for policy 1, policy_version 405230 (0.0011) -[2023-11-28 10:51:09,817][87424] Updated weights for policy 0, policy_version 405489 (0.0011) -[2023-11-28 10:51:10,095][87426] Updated weights for policy 1, policy_version 405240 (0.0011) -[2023-11-28 10:51:10,190][87424] Updated weights for policy 0, policy_version 405499 (0.0010) -[2023-11-28 10:51:12,188][87426] Updated weights for policy 1, policy_version 405250 (0.0010) -[2023-11-28 10:51:12,441][87424] Updated weights for policy 0, policy_version 405509 (0.0011) -[2023-11-28 10:51:12,557][87426] Updated weights for policy 1, policy_version 405260 (0.0010) -[2023-11-28 10:51:12,821][87424] Updated weights for policy 0, policy_version 405519 (0.0010) -[2023-11-28 10:51:12,938][87426] Updated weights for policy 1, policy_version 405270 (0.0009) -[2023-11-28 10:51:13,210][87424] Updated weights for policy 0, policy_version 405529 (0.0009) -[2023-11-28 10:51:13,317][87426] Updated weights for policy 1, policy_version 405280 (0.0007) -[2023-11-28 10:51:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 207560704. Throughput: 0: 2674.6, 1: 2702.7. Samples: 207576492. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:13,445][86177] Avg episode reward: [(0, '-513.070'), (1, '-519.560')] -[2023-11-28 10:51:15,181][87424] Updated weights for policy 0, policy_version 405539 (0.0009) -[2023-11-28 10:51:15,570][87424] Updated weights for policy 0, policy_version 405549 (0.0011) -[2023-11-28 10:51:15,585][87426] Updated weights for policy 1, policy_version 405290 (0.0010) -[2023-11-28 10:51:15,960][87424] Updated weights for policy 0, policy_version 405559 (0.0009) -[2023-11-28 10:51:15,965][87426] Updated weights for policy 1, policy_version 405300 (0.0010) -[2023-11-28 10:51:16,340][87426] Updated weights for policy 1, policy_version 405310 (0.0011) -[2023-11-28 10:51:17,786][87424] Updated weights for policy 0, policy_version 405569 (0.0011) -[2023-11-28 10:51:18,167][87424] Updated weights for policy 0, policy_version 405579 (0.0007) -[2023-11-28 10:51:18,329][87426] Updated weights for policy 1, policy_version 405320 (0.0012) -[2023-11-28 10:51:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 207585280. Throughput: 0: 2696.0, 1: 2714.9. Samples: 207601748. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:18,445][86177] Avg episode reward: [(0, '-511.670'), (1, '-518.590')] -[2023-11-28 10:51:18,555][87424] Updated weights for policy 0, policy_version 405589 (0.0007) -[2023-11-28 10:51:18,715][87426] Updated weights for policy 1, policy_version 405330 (0.0011) -[2023-11-28 10:51:18,933][87424] Updated weights for policy 0, policy_version 405599 (0.0008) -[2023-11-28 10:51:19,093][87426] Updated weights for policy 1, policy_version 405340 (0.0010) -[2023-11-28 10:51:21,379][87426] Updated weights for policy 1, policy_version 405350 (0.0010) -[2023-11-28 10:51:21,435][87424] Updated weights for policy 0, policy_version 405609 (0.0011) -[2023-11-28 10:51:21,758][87426] Updated weights for policy 1, policy_version 405360 (0.0010) -[2023-11-28 10:51:21,823][87424] Updated weights for policy 0, policy_version 405619 (0.0011) -[2023-11-28 10:51:22,143][87426] Updated weights for policy 1, policy_version 405370 (0.0011) -[2023-11-28 10:51:22,197][87424] Updated weights for policy 0, policy_version 405629 (0.0012) -[2023-11-28 10:51:23,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207618048. Throughput: 0: 2699.6, 1: 2709.3. Samples: 207634232. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:23,445][86177] Avg episode reward: [(0, '-512.700'), (1, '-522.030')] -[2023-11-28 10:51:24,492][87426] Updated weights for policy 1, policy_version 405380 (0.0011) -[2023-11-28 10:51:24,501][87424] Updated weights for policy 0, policy_version 405639 (0.0010) -[2023-11-28 10:51:24,876][87426] Updated weights for policy 1, policy_version 405390 (0.0010) -[2023-11-28 10:51:24,890][87424] Updated weights for policy 0, policy_version 405649 (0.0012) -[2023-11-28 10:51:25,256][87426] Updated weights for policy 1, policy_version 405400 (0.0008) -[2023-11-28 10:51:25,277][87424] Updated weights for policy 0, policy_version 405659 (0.0009) -[2023-11-28 10:51:27,394][87426] Updated weights for policy 1, policy_version 405410 (0.0008) -[2023-11-28 10:51:27,673][87424] Updated weights for policy 0, policy_version 405669 (0.0008) -[2023-11-28 10:51:27,771][87426] Updated weights for policy 1, policy_version 405420 (0.0011) -[2023-11-28 10:51:28,054][87424] Updated weights for policy 0, policy_version 405679 (0.0008) -[2023-11-28 10:51:28,153][87426] Updated weights for policy 1, policy_version 405430 (0.0011) -[2023-11-28 10:51:28,434][87424] Updated weights for policy 0, policy_version 405689 (0.0007) -[2023-11-28 10:51:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 207634432. Throughput: 0: 2695.3, 1: 2716.8. Samples: 207658084. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:28,445][86177] Avg episode reward: [(0, '-513.710'), (1, '-553.630')] -[2023-11-28 10:51:28,537][87426] Updated weights for policy 1, policy_version 405440 (0.0012) -[2023-11-28 10:51:30,961][87424] Updated weights for policy 0, policy_version 405699 (0.0008) -[2023-11-28 10:51:31,042][87426] Updated weights for policy 1, policy_version 405450 (0.0011) -[2023-11-28 10:51:31,335][87424] Updated weights for policy 0, policy_version 405709 (0.0012) -[2023-11-28 10:51:31,420][87426] Updated weights for policy 1, policy_version 405460 (0.0009) -[2023-11-28 10:51:31,721][87424] Updated weights for policy 0, policy_version 405719 (0.0011) -[2023-11-28 10:51:31,801][87426] Updated weights for policy 1, policy_version 405470 (0.0011) -[2023-11-28 10:51:33,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 207667200. Throughput: 0: 2660.0, 1: 2704.0. Samples: 207680776. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:33,445][86177] Avg episode reward: [(0, '-511.320'), (1, '-559.970')] -[2023-11-28 10:51:33,810][87426] Updated weights for policy 1, policy_version 405480 (0.0011) -[2023-11-28 10:51:33,831][87424] Updated weights for policy 0, policy_version 405729 (0.0009) -[2023-11-28 10:51:34,192][87426] Updated weights for policy 1, policy_version 405490 (0.0009) -[2023-11-28 10:51:34,208][87424] Updated weights for policy 0, policy_version 405739 (0.0010) -[2023-11-28 10:51:34,570][87426] Updated weights for policy 1, policy_version 405500 (0.0007) -[2023-11-28 10:51:34,588][87424] Updated weights for policy 0, policy_version 405749 (0.0012) -[2023-11-28 10:51:34,971][87424] Updated weights for policy 0, policy_version 405759 (0.0012) -[2023-11-28 10:51:36,751][87424] Updated weights for policy 0, policy_version 405769 (0.0009) -[2023-11-28 10:51:36,886][87426] Updated weights for policy 1, policy_version 405510 (0.0011) -[2023-11-28 10:51:37,136][87424] Updated weights for policy 0, policy_version 405779 (0.0012) -[2023-11-28 10:51:37,264][87426] Updated weights for policy 1, policy_version 405520 (0.0011) -[2023-11-28 10:51:37,521][87424] Updated weights for policy 0, policy_version 405789 (0.0011) -[2023-11-28 10:51:37,634][87426] Updated weights for policy 1, policy_version 405530 (0.0012) -[2023-11-28 10:51:38,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207699968. Throughput: 0: 2669.0, 1: 2714.0. Samples: 207714124. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:38,445][86177] Avg episode reward: [(0, '-506.790'), (1, '-559.550')] -[2023-11-28 10:51:39,209][87424] Updated weights for policy 0, policy_version 405799 (0.0012) -[2023-11-28 10:51:39,567][87426] Updated weights for policy 1, policy_version 405540 (0.0010) -[2023-11-28 10:51:39,591][87424] Updated weights for policy 0, policy_version 405809 (0.0012) -[2023-11-28 10:51:39,964][87424] Updated weights for policy 0, policy_version 405819 (0.0014) -[2023-11-28 10:51:39,969][87426] Updated weights for policy 1, policy_version 405550 (0.0009) -[2023-11-28 10:51:40,351][87426] Updated weights for policy 1, policy_version 405560 (0.0010) -[2023-11-28 10:51:42,586][87424] Updated weights for policy 0, policy_version 405829 (0.0011) -[2023-11-28 10:51:42,668][87426] Updated weights for policy 1, policy_version 405570 (0.0010) -[2023-11-28 10:51:42,967][87424] Updated weights for policy 0, policy_version 405839 (0.0010) -[2023-11-28 10:51:43,045][87426] Updated weights for policy 1, policy_version 405580 (0.0010) -[2023-11-28 10:51:43,352][87424] Updated weights for policy 0, policy_version 405849 (0.0009) -[2023-11-28 10:51:43,420][87426] Updated weights for policy 1, policy_version 405590 (0.0010) -[2023-11-28 10:51:43,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 207716352. Throughput: 0: 2684.8, 1: 2694.3. Samples: 207738668. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:43,445][86177] Avg episode reward: [(0, '-512.520'), (1, '-562.530')] -[2023-11-28 10:51:43,803][87426] Updated weights for policy 1, policy_version 405600 (0.0012) -[2023-11-28 10:51:45,122][87424] Updated weights for policy 0, policy_version 405859 (0.0012) -[2023-11-28 10:51:45,502][87424] Updated weights for policy 0, policy_version 405869 (0.0011) -[2023-11-28 10:51:45,711][87426] Updated weights for policy 1, policy_version 405610 (0.0012) -[2023-11-28 10:51:45,884][87424] Updated weights for policy 0, policy_version 405879 (0.0010) -[2023-11-28 10:51:46,079][87426] Updated weights for policy 1, policy_version 405620 (0.0011) -[2023-11-28 10:51:46,456][87426] Updated weights for policy 1, policy_version 405630 (0.0009) -[2023-11-28 10:51:48,417][87424] Updated weights for policy 0, policy_version 405889 (0.0012) -[2023-11-28 10:51:48,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207749120. Throughput: 0: 2665.3, 1: 2697.2. Samples: 207763184. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:48,445][86177] Avg episode reward: [(0, '-512.340'), (1, '-531.400')] -[2023-11-28 10:51:48,524][87426] Updated weights for policy 1, policy_version 405640 (0.0009) -[2023-11-28 10:51:48,792][87424] Updated weights for policy 0, policy_version 405899 (0.0011) -[2023-11-28 10:51:48,901][87426] Updated weights for policy 1, policy_version 405650 (0.0008) -[2023-11-28 10:51:49,169][87424] Updated weights for policy 0, policy_version 405909 (0.0009) -[2023-11-28 10:51:49,277][87426] Updated weights for policy 1, policy_version 405660 (0.0011) -[2023-11-28 10:51:49,553][87424] Updated weights for policy 0, policy_version 405919 (0.0009) -[2023-11-28 10:51:51,681][87426] Updated weights for policy 1, policy_version 405670 (0.0011) -[2023-11-28 10:51:52,059][87426] Updated weights for policy 1, policy_version 405680 (0.0009) -[2023-11-28 10:51:52,210][87424] Updated weights for policy 0, policy_version 405929 (0.0011) -[2023-11-28 10:51:52,433][87426] Updated weights for policy 1, policy_version 405690 (0.0010) -[2023-11-28 10:51:52,602][87424] Updated weights for policy 0, policy_version 405939 (0.0008) -[2023-11-28 10:51:52,978][87424] Updated weights for policy 0, policy_version 405949 (0.0009) -[2023-11-28 10:51:53,444][86177] Fps is (10 sec: 6553.5, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207781888. Throughput: 0: 2646.6, 1: 2713.9. Samples: 207794312. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:53,445][86177] Avg episode reward: [(0, '-511.240'), (1, '-520.700')] -[2023-11-28 10:51:54,887][87426] Updated weights for policy 1, policy_version 405700 (0.0011) -[2023-11-28 10:51:55,196][87424] Updated weights for policy 0, policy_version 405959 (0.0010) -[2023-11-28 10:51:55,266][87426] Updated weights for policy 1, policy_version 405710 (0.0010) -[2023-11-28 10:51:55,572][87424] Updated weights for policy 0, policy_version 405969 (0.0011) -[2023-11-28 10:51:55,650][87426] Updated weights for policy 1, policy_version 405720 (0.0011) -[2023-11-28 10:51:55,954][87424] Updated weights for policy 0, policy_version 405979 (0.0016) -[2023-11-28 10:51:57,631][87426] Updated weights for policy 1, policy_version 405730 (0.0010) -[2023-11-28 10:51:58,002][87424] Updated weights for policy 0, policy_version 405989 (0.0012) -[2023-11-28 10:51:58,010][87426] Updated weights for policy 1, policy_version 405740 (0.0011) -[2023-11-28 10:51:58,377][87424] Updated weights for policy 0, policy_version 405999 (0.0009) -[2023-11-28 10:51:58,390][87426] Updated weights for policy 1, policy_version 405750 (0.0008) -[2023-11-28 10:51:58,444][86177] Fps is (10 sec: 4915.1, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 207798272. Throughput: 0: 2663.1, 1: 2714.2. Samples: 207818472. Policy #0 lag: (min: 31.0, avg: 36.7, max: 63.0) -[2023-11-28 10:51:58,446][86177] Avg episode reward: [(0, '-525.610'), (1, '-524.410')] -[2023-11-28 10:51:58,766][87424] Updated weights for policy 0, policy_version 406009 (0.0009) -[2023-11-28 10:51:58,767][87426] Updated weights for policy 1, policy_version 405760 (0.0009) -[2023-11-28 10:52:01,119][87426] Updated weights for policy 1, policy_version 405770 (0.0008) -[2023-11-28 10:52:01,171][87424] Updated weights for policy 0, policy_version 406019 (0.0011) -[2023-11-28 10:52:01,500][87426] Updated weights for policy 1, policy_version 405780 (0.0009) -[2023-11-28 10:52:01,546][87424] Updated weights for policy 0, policy_version 406029 (0.0012) -[2023-11-28 10:52:01,874][87426] Updated weights for policy 1, policy_version 405790 (0.0011) -[2023-11-28 10:52:01,931][87424] Updated weights for policy 0, policy_version 406039 (0.0010) -[2023-11-28 10:52:03,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 207831040. Throughput: 0: 2656.2, 1: 2700.9. Samples: 207842816. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:03,445][86177] Avg episode reward: [(0, '-517.850'), (1, '-520.450')] -[2023-11-28 10:52:03,914][87426] Updated weights for policy 1, policy_version 405800 (0.0012) -[2023-11-28 10:52:04,067][87424] Updated weights for policy 0, policy_version 406049 (0.0011) -[2023-11-28 10:52:04,303][87426] Updated weights for policy 1, policy_version 405810 (0.0011) -[2023-11-28 10:52:04,443][87424] Updated weights for policy 0, policy_version 406059 (0.0011) -[2023-11-28 10:52:04,678][87426] Updated weights for policy 1, policy_version 405820 (0.0011) -[2023-11-28 10:52:04,832][87424] Updated weights for policy 0, policy_version 406069 (0.0010) -[2023-11-28 10:52:05,217][87424] Updated weights for policy 0, policy_version 406079 (0.0012) -[2023-11-28 10:52:06,352][87426] Updated weights for policy 1, policy_version 405830 (0.0011) -[2023-11-28 10:52:06,732][87426] Updated weights for policy 1, policy_version 405840 (0.0011) -[2023-11-28 10:52:07,101][87426] Updated weights for policy 1, policy_version 405850 (0.0008) -[2023-11-28 10:52:07,528][87424] Updated weights for policy 0, policy_version 406089 (0.0010) -[2023-11-28 10:52:07,902][87424] Updated weights for policy 0, policy_version 406099 (0.0008) -[2023-11-28 10:52:08,280][87424] Updated weights for policy 0, policy_version 406109 (0.0008) -[2023-11-28 10:52:08,444][86177] Fps is (10 sec: 6553.6, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207863808. Throughput: 0: 2654.7, 1: 2700.1. Samples: 207875196. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:08,445][86177] Avg episode reward: [(0, '-517.010'), (1, '-515.940')] -[2023-11-28 10:52:09,565][87426] Updated weights for policy 1, policy_version 405860 (0.0008) -[2023-11-28 10:52:09,958][87426] Updated weights for policy 1, policy_version 405870 (0.0009) -[2023-11-28 10:52:10,329][87426] Updated weights for policy 1, policy_version 405880 (0.0010) -[2023-11-28 10:52:10,815][87424] Updated weights for policy 0, policy_version 406119 (0.0010) -[2023-11-28 10:52:11,196][87424] Updated weights for policy 0, policy_version 406129 (0.0009) -[2023-11-28 10:52:11,580][87424] Updated weights for policy 0, policy_version 406139 (0.0008) -[2023-11-28 10:52:13,014][87426] Updated weights for policy 1, policy_version 405890 (0.0011) -[2023-11-28 10:52:13,393][87426] Updated weights for policy 1, policy_version 405900 (0.0007) -[2023-11-28 10:52:13,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 207880192. Throughput: 0: 2651.2, 1: 2687.4. Samples: 207898320. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:13,445][86177] Avg episode reward: [(0, '-517.460'), (1, '-518.150')] -[2023-11-28 10:52:13,770][87426] Updated weights for policy 1, policy_version 405910 (0.0007) -[2023-11-28 10:52:14,016][87424] Updated weights for policy 0, policy_version 406149 (0.0010) -[2023-11-28 10:52:14,152][87426] Updated weights for policy 1, policy_version 405920 (0.0009) -[2023-11-28 10:52:14,405][87424] Updated weights for policy 0, policy_version 406159 (0.0007) -[2023-11-28 10:52:14,798][87424] Updated weights for policy 0, policy_version 406169 (0.0009) -[2023-11-28 10:52:15,915][87426] Updated weights for policy 1, policy_version 405930 (0.0007) -[2023-11-28 10:52:16,306][87426] Updated weights for policy 1, policy_version 405940 (0.0008) -[2023-11-28 10:52:16,681][87426] Updated weights for policy 1, policy_version 405950 (0.0007) -[2023-11-28 10:52:16,842][87424] Updated weights for policy 0, policy_version 406179 (0.0010) -[2023-11-28 10:52:17,236][87424] Updated weights for policy 0, policy_version 406189 (0.0012) -[2023-11-28 10:52:17,616][87424] Updated weights for policy 0, policy_version 406199 (0.0012) -[2023-11-28 10:52:18,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 207912960. Throughput: 0: 2660.4, 1: 2702.7. Samples: 207922116. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:18,445][86177] Avg episode reward: [(0, '-507.150'), (1, '-518.400')] -[2023-11-28 10:52:18,453][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000406208_103989248.pth... -[2023-11-28 10:52:18,485][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000403712_103350272.pth -[2023-11-28 10:52:18,490][87281] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p0/milestones/checkpoint_000406208_103989248.pth -[2023-11-28 10:52:18,745][87426] Updated weights for policy 1, policy_version 405960 (0.0011) -[2023-11-28 10:52:19,123][87426] Updated weights for policy 1, policy_version 405970 (0.0012) -[2023-11-28 10:52:19,502][87426] Updated weights for policy 1, policy_version 405980 (0.0012) -[2023-11-28 10:52:19,650][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000405984_103931904.pth... -[2023-11-28 10:52:19,697][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000403424_103276544.pth -[2023-11-28 10:52:19,703][87320] Saving a milestone ./train_atari/atari_skiing_APPO/checkpoint_p1/milestones/checkpoint_000405984_103931904.pth -[2023-11-28 10:52:19,940][87424] Updated weights for policy 0, policy_version 406209 (0.0012) -[2023-11-28 10:52:20,321][87424] Updated weights for policy 0, policy_version 406219 (0.0009) -[2023-11-28 10:52:20,698][87424] Updated weights for policy 0, policy_version 406229 (0.0010) -[2023-11-28 10:52:21,092][87424] Updated weights for policy 0, policy_version 406239 (0.0011) -[2023-11-28 10:52:21,693][87426] Updated weights for policy 1, policy_version 405990 (0.0012) -[2023-11-28 10:52:22,073][87426] Updated weights for policy 1, policy_version 406000 (0.0009) -[2023-11-28 10:52:22,455][87426] Updated weights for policy 1, policy_version 406010 (0.0011) -[2023-11-28 10:52:23,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 207937536. Throughput: 0: 2630.7, 1: 2688.8. Samples: 207953504. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:23,446][86177] Avg episode reward: [(0, '-508.460'), (1, '-517.540')] -[2023-11-28 10:52:23,577][87424] Updated weights for policy 0, policy_version 406249 (0.0008) -[2023-11-28 10:52:23,953][87424] Updated weights for policy 0, policy_version 406259 (0.0011) -[2023-11-28 10:52:24,339][87424] Updated weights for policy 0, policy_version 406269 (0.0012) -[2023-11-28 10:52:25,029][87426] Updated weights for policy 1, policy_version 406020 (0.0009) -[2023-11-28 10:52:25,413][87426] Updated weights for policy 1, policy_version 406030 (0.0009) -[2023-11-28 10:52:25,786][87426] Updated weights for policy 1, policy_version 406040 (0.0010) -[2023-11-28 10:52:26,937][87424] Updated weights for policy 0, policy_version 406279 (0.0007) -[2023-11-28 10:52:27,314][87424] Updated weights for policy 0, policy_version 406289 (0.0007) -[2023-11-28 10:52:27,702][87424] Updated weights for policy 0, policy_version 406299 (0.0007) -[2023-11-28 10:52:27,893][87426] Updated weights for policy 1, policy_version 406050 (0.0009) -[2023-11-28 10:52:28,265][87426] Updated weights for policy 1, policy_version 406060 (0.0012) -[2023-11-28 10:52:28,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5461.3, 300 sec: 5359.5). Total num frames: 207962112. Throughput: 0: 2605.6, 1: 2699.4. Samples: 207977392. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:28,445][86177] Avg episode reward: [(0, '-511.700'), (1, '-524.880')] -[2023-11-28 10:52:28,631][87426] Updated weights for policy 1, policy_version 406070 (0.0012) -[2023-11-28 10:52:29,004][87426] Updated weights for policy 1, policy_version 406080 (0.0012) -[2023-11-28 10:52:29,536][87424] Updated weights for policy 0, policy_version 406309 (0.0010) -[2023-11-28 10:52:29,903][87424] Updated weights for policy 0, policy_version 406319 (0.0012) -[2023-11-28 10:52:30,288][87424] Updated weights for policy 0, policy_version 406329 (0.0012) -[2023-11-28 10:52:31,549][87426] Updated weights for policy 1, policy_version 406090 (0.0009) -[2023-11-28 10:52:31,935][87426] Updated weights for policy 1, policy_version 406100 (0.0010) -[2023-11-28 10:52:32,317][87426] Updated weights for policy 1, policy_version 406110 (0.0012) -[2023-11-28 10:52:32,540][87424] Updated weights for policy 0, policy_version 406339 (0.0009) -[2023-11-28 10:52:32,918][87424] Updated weights for policy 0, policy_version 406349 (0.0009) -[2023-11-28 10:52:33,301][87424] Updated weights for policy 0, policy_version 406359 (0.0008) -[2023-11-28 10:52:33,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5324.8, 300 sec: 5331.7). Total num frames: 207986688. Throughput: 0: 2604.5, 1: 2679.4. Samples: 208000960. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:33,445][86177] Avg episode reward: [(0, '-528.320'), (1, '-519.200')] -[2023-11-28 10:52:34,702][87426] Updated weights for policy 1, policy_version 406120 (0.0011) -[2023-11-28 10:52:35,084][87426] Updated weights for policy 1, policy_version 406130 (0.0011) -[2023-11-28 10:52:35,446][87424] Updated weights for policy 0, policy_version 406369 (0.0007) -[2023-11-28 10:52:35,461][87426] Updated weights for policy 1, policy_version 406140 (0.0012) -[2023-11-28 10:52:35,819][87424] Updated weights for policy 0, policy_version 406379 (0.0007) -[2023-11-28 10:52:36,199][87424] Updated weights for policy 0, policy_version 406389 (0.0007) -[2023-11-28 10:52:36,578][87424] Updated weights for policy 0, policy_version 406399 (0.0007) -[2023-11-28 10:52:37,457][87426] Updated weights for policy 1, policy_version 406150 (0.0011) -[2023-11-28 10:52:37,838][87426] Updated weights for policy 1, policy_version 406160 (0.0012) -[2023-11-28 10:52:38,219][87426] Updated weights for policy 1, policy_version 406170 (0.0011) -[2023-11-28 10:52:38,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 208011264. Throughput: 0: 2641.4, 1: 2685.2. Samples: 208034008. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:38,445][86177] Avg episode reward: [(0, '-524.890'), (1, '-516.820')] -[2023-11-28 10:52:39,122][87424] Updated weights for policy 0, policy_version 406409 (0.0011) -[2023-11-28 10:52:39,501][87424] Updated weights for policy 0, policy_version 406419 (0.0011) -[2023-11-28 10:52:39,886][87424] Updated weights for policy 0, policy_version 406429 (0.0011) -[2023-11-28 10:52:40,347][87426] Updated weights for policy 1, policy_version 406180 (0.0012) -[2023-11-28 10:52:40,720][87426] Updated weights for policy 1, policy_version 406190 (0.0009) -[2023-11-28 10:52:41,097][87426] Updated weights for policy 1, policy_version 406200 (0.0008) -[2023-11-28 10:52:42,310][87424] Updated weights for policy 0, policy_version 406439 (0.0012) -[2023-11-28 10:52:42,694][87424] Updated weights for policy 0, policy_version 406449 (0.0012) -[2023-11-28 10:52:43,085][87424] Updated weights for policy 0, policy_version 406459 (0.0013) -[2023-11-28 10:52:43,322][87426] Updated weights for policy 1, policy_version 406210 (0.0010) -[2023-11-28 10:52:43,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 208044032. Throughput: 0: 2637.2, 1: 2697.4. Samples: 208058532. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:43,445][86177] Avg episode reward: [(0, '-525.500'), (1, '-509.790')] -[2023-11-28 10:52:43,698][87426] Updated weights for policy 1, policy_version 406220 (0.0012) -[2023-11-28 10:52:44,091][87426] Updated weights for policy 1, policy_version 406230 (0.0012) -[2023-11-28 10:52:44,471][87426] Updated weights for policy 1, policy_version 406240 (0.0012) -[2023-11-28 10:52:45,138][87424] Updated weights for policy 0, policy_version 406469 (0.0012) -[2023-11-28 10:52:45,518][87424] Updated weights for policy 0, policy_version 406479 (0.0011) -[2023-11-28 10:52:45,890][87424] Updated weights for policy 0, policy_version 406489 (0.0012) -[2023-11-28 10:52:46,512][87426] Updated weights for policy 1, policy_version 406250 (0.0011) -[2023-11-28 10:52:46,890][87426] Updated weights for policy 1, policy_version 406260 (0.0011) -[2023-11-28 10:52:47,268][87426] Updated weights for policy 1, policy_version 406270 (0.0012) -[2023-11-28 10:52:47,553][87424] Updated weights for policy 0, policy_version 406499 (0.0012) -[2023-11-28 10:52:47,938][87424] Updated weights for policy 0, policy_version 406509 (0.0012) -[2023-11-28 10:52:48,318][87424] Updated weights for policy 0, policy_version 406519 (0.0012) -[2023-11-28 10:52:48,444][86177] Fps is (10 sec: 5734.2, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 208068608. Throughput: 0: 2641.9, 1: 2688.5. Samples: 208082688. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:48,446][86177] Avg episode reward: [(0, '-506.820'), (1, '-506.990')] -[2023-11-28 10:52:49,532][87426] Updated weights for policy 1, policy_version 406280 (0.0009) -[2023-11-28 10:52:49,920][87426] Updated weights for policy 1, policy_version 406290 (0.0008) -[2023-11-28 10:52:50,296][87426] Updated weights for policy 1, policy_version 406300 (0.0011) -[2023-11-28 10:52:50,317][87424] Updated weights for policy 0, policy_version 406529 (0.0012) -[2023-11-28 10:52:50,697][87424] Updated weights for policy 0, policy_version 406539 (0.0011) -[2023-11-28 10:52:51,081][87424] Updated weights for policy 0, policy_version 406549 (0.0012) -[2023-11-28 10:52:51,465][87424] Updated weights for policy 0, policy_version 406559 (0.0012) -[2023-11-28 10:52:52,645][87426] Updated weights for policy 1, policy_version 406310 (0.0020) -[2023-11-28 10:52:53,023][87426] Updated weights for policy 1, policy_version 406320 (0.0012) -[2023-11-28 10:52:53,404][87426] Updated weights for policy 1, policy_version 406330 (0.0011) -[2023-11-28 10:52:53,444][86177] Fps is (10 sec: 4915.3, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 208093184. Throughput: 0: 2668.1, 1: 2694.5. Samples: 208116512. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:53,445][86177] Avg episode reward: [(0, '-508.020'), (1, '-507.080')] -[2023-11-28 10:52:53,916][87424] Updated weights for policy 0, policy_version 406569 (0.0010) -[2023-11-28 10:52:54,299][87424] Updated weights for policy 0, policy_version 406579 (0.0008) -[2023-11-28 10:52:54,672][87424] Updated weights for policy 0, policy_version 406589 (0.0008) -[2023-11-28 10:52:55,296][87426] Updated weights for policy 1, policy_version 406340 (0.0012) -[2023-11-28 10:52:55,670][87426] Updated weights for policy 1, policy_version 406350 (0.0012) -[2023-11-28 10:52:56,049][87426] Updated weights for policy 1, policy_version 406360 (0.0012) -[2023-11-28 10:52:56,955][87424] Updated weights for policy 0, policy_version 406599 (0.0010) -[2023-11-28 10:52:57,338][87424] Updated weights for policy 0, policy_version 406609 (0.0012) -[2023-11-28 10:52:57,730][87424] Updated weights for policy 0, policy_version 406619 (0.0012) -[2023-11-28 10:52:58,365][87426] Updated weights for policy 1, policy_version 406370 (0.0011) -[2023-11-28 10:52:58,444][86177] Fps is (10 sec: 5734.6, 60 sec: 5461.4, 300 sec: 5387.3). Total num frames: 208125952. Throughput: 0: 2679.3, 1: 2707.8. Samples: 208140740. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:52:58,445][86177] Avg episode reward: [(0, '-515.850'), (1, '-513.640')] -[2023-11-28 10:52:58,761][87426] Updated weights for policy 1, policy_version 406380 (0.0007) -[2023-11-28 10:52:59,137][87426] Updated weights for policy 1, policy_version 406390 (0.0010) -[2023-11-28 10:52:59,520][87426] Updated weights for policy 1, policy_version 406400 (0.0009) -[2023-11-28 10:52:59,834][87424] Updated weights for policy 0, policy_version 406629 (0.0010) -[2023-11-28 10:53:00,211][87424] Updated weights for policy 0, policy_version 406639 (0.0008) -[2023-11-28 10:53:00,593][87424] Updated weights for policy 0, policy_version 406649 (0.0008) -[2023-11-28 10:53:01,812][87426] Updated weights for policy 1, policy_version 406410 (0.0010) -[2023-11-28 10:53:02,194][87426] Updated weights for policy 1, policy_version 406420 (0.0011) -[2023-11-28 10:53:02,572][87426] Updated weights for policy 1, policy_version 406430 (0.0011) -[2023-11-28 10:53:02,698][87424] Updated weights for policy 0, policy_version 406659 (0.0010) -[2023-11-28 10:53:03,096][87424] Updated weights for policy 0, policy_version 406669 (0.0009) -[2023-11-28 10:53:03,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 208150528. Throughput: 0: 2697.8, 1: 2714.8. Samples: 208165680. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:53:03,445][86177] Avg episode reward: [(0, '-513.410'), (1, '-521.140')] -[2023-11-28 10:53:03,479][87424] Updated weights for policy 0, policy_version 406679 (0.0008) -[2023-11-28 10:53:04,576][87426] Updated weights for policy 1, policy_version 406440 (0.0008) -[2023-11-28 10:53:04,960][87426] Updated weights for policy 1, policy_version 406450 (0.0010) -[2023-11-28 10:53:05,344][87426] Updated weights for policy 1, policy_version 406460 (0.0011) -[2023-11-28 10:53:05,383][87424] Updated weights for policy 0, policy_version 406689 (0.0008) -[2023-11-28 10:53:05,755][87424] Updated weights for policy 0, policy_version 406699 (0.0009) -[2023-11-28 10:53:06,144][87424] Updated weights for policy 0, policy_version 406709 (0.0008) -[2023-11-28 10:53:06,530][87424] Updated weights for policy 0, policy_version 406719 (0.0008) -[2023-11-28 10:53:07,741][87426] Updated weights for policy 1, policy_version 406470 (0.0009) -[2023-11-28 10:53:08,125][87426] Updated weights for policy 1, policy_version 406480 (0.0011) -[2023-11-28 10:53:08,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5188.3, 300 sec: 5359.5). Total num frames: 208175104. Throughput: 0: 2730.1, 1: 2700.7. Samples: 208197892. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:53:08,445][86177] Avg episode reward: [(0, '-517.810'), (1, '-516.900')] -[2023-11-28 10:53:08,506][87426] Updated weights for policy 1, policy_version 406490 (0.0008) -[2023-11-28 10:53:08,874][87424] Updated weights for policy 0, policy_version 406729 (0.0009) -[2023-11-28 10:53:09,261][87424] Updated weights for policy 0, policy_version 406739 (0.0011) -[2023-11-28 10:53:09,637][87424] Updated weights for policy 0, policy_version 406749 (0.0012) -[2023-11-28 10:53:11,084][87426] Updated weights for policy 1, policy_version 406500 (0.0010) -[2023-11-28 10:53:11,465][87426] Updated weights for policy 1, policy_version 406510 (0.0009) -[2023-11-28 10:53:11,524][87424] Updated weights for policy 0, policy_version 406759 (0.0012) -[2023-11-28 10:53:11,845][87426] Updated weights for policy 1, policy_version 406520 (0.0011) -[2023-11-28 10:53:11,890][87424] Updated weights for policy 0, policy_version 406769 (0.0015) -[2023-11-28 10:53:12,275][87424] Updated weights for policy 0, policy_version 406779 (0.0012) -[2023-11-28 10:53:13,444][86177] Fps is (10 sec: 5734.4, 60 sec: 5461.3, 300 sec: 5387.3). Total num frames: 208207872. Throughput: 0: 2748.0, 1: 2689.4. Samples: 208222076. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:53:13,445][86177] Avg episode reward: [(0, '-514.870'), (1, '-517.670')] -[2023-11-28 10:53:13,674][87426] Updated weights for policy 1, policy_version 406530 (0.0012) -[2023-11-28 10:53:14,046][87426] Updated weights for policy 1, policy_version 406540 (0.0012) -[2023-11-28 10:53:14,409][87424] Updated weights for policy 0, policy_version 406789 (0.0012) -[2023-11-28 10:53:14,436][87426] Updated weights for policy 1, policy_version 406550 (0.0011) -[2023-11-28 10:53:14,791][87424] Updated weights for policy 0, policy_version 406799 (0.0009) -[2023-11-28 10:53:14,814][87426] Updated weights for policy 1, policy_version 406560 (0.0010) -[2023-11-28 10:53:15,181][87424] Updated weights for policy 0, policy_version 406809 (0.0012) -[2023-11-28 10:53:16,802][87426] Updated weights for policy 1, policy_version 406570 (0.0012) -[2023-11-28 10:53:17,174][87426] Updated weights for policy 1, policy_version 406580 (0.0011) -[2023-11-28 10:53:17,537][87424] Updated weights for policy 0, policy_version 406819 (0.0010) -[2023-11-28 10:53:17,552][87426] Updated weights for policy 1, policy_version 406590 (0.0012) -[2023-11-28 10:53:17,918][87424] Updated weights for policy 0, policy_version 406829 (0.0012) -[2023-11-28 10:53:18,307][87424] Updated weights for policy 0, policy_version 406839 (0.0012) -[2023-11-28 10:53:18,444][86177] Fps is (10 sec: 5734.3, 60 sec: 5324.8, 300 sec: 5387.3). Total num frames: 208232448. Throughput: 0: 2739.5, 1: 2704.5. Samples: 208245940. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:53:18,445][86177] Avg episode reward: [(0, '-518.890'), (1, '-516.510')] -[2023-11-28 10:53:19,306][87426] Updated weights for policy 1, policy_version 406600 (0.0009) -[2023-11-28 10:53:19,685][87426] Updated weights for policy 1, policy_version 406610 (0.0010) -[2023-11-28 10:53:20,070][87426] Updated weights for policy 1, policy_version 406620 (0.0010) -[2023-11-28 10:53:20,773][87424] Updated weights for policy 0, policy_version 406849 (0.0009) -[2023-11-28 10:53:21,161][87424] Updated weights for policy 0, policy_version 406859 (0.0010) -[2023-11-28 10:53:21,545][87424] Updated weights for policy 0, policy_version 406869 (0.0010) -[2023-11-28 10:53:21,927][87424] Updated weights for policy 0, policy_version 406879 (0.0012) -[2023-11-28 10:53:22,536][87426] Updated weights for policy 1, policy_version 406630 (0.0008) -[2023-11-28 10:53:22,911][87426] Updated weights for policy 1, policy_version 406640 (0.0015) -[2023-11-28 10:53:23,288][87426] Updated weights for policy 1, policy_version 406650 (0.0009) -[2023-11-28 10:53:23,444][86177] Fps is (10 sec: 4915.2, 60 sec: 5324.8, 300 sec: 5359.5). Total num frames: 208257024. Throughput: 0: 2713.8, 1: 2687.3. Samples: 208277056. Policy #0 lag: (min: 31.0, avg: 39.6, max: 63.0) -[2023-11-28 10:53:23,445][86177] Avg episode reward: [(0, '-516.500'), (1, '-520.570')] -[2023-11-28 10:53:24,206][87424] Updated weights for policy 0, policy_version 406889 (0.0011) -[2023-11-28 10:53:24,579][87424] Updated weights for policy 0, policy_version 406899 (0.0009) -[2023-11-28 10:53:24,959][87424] Updated weights for policy 0, policy_version 406909 (0.0007) -[2023-11-28 10:53:25,849][87426] Updated weights for policy 1, policy_version 406660 (0.0009) -[2023-11-28 10:53:26,226][87426] Updated weights for policy 1, policy_version 406670 (0.0012) -[2023-11-28 10:53:26,603][87426] Updated weights for policy 1, policy_version 406680 (0.0012) -[2023-11-28 10:53:27,173][87424] Updated weights for policy 0, policy_version 406919 (0.0009) -[2023-11-28 10:53:27,562][87424] Updated weights for policy 0, policy_version 406929 (0.0008) -[2023-11-28 10:53:27,936][87424] Updated weights for policy 0, policy_version 406939 (0.0010) -[2023-11-28 10:53:28,358][86177] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 86177], exiting... -[2023-11-28 10:53:28,359][86177] Runner profile tree view: -main_loop: 38464.1145 -[2023-11-28 10:53:28,359][87320] Stopping Batcher_1... -[2023-11-28 10:53:28,359][87281] Stopping Batcher_0... -[2023-11-28 10:53:28,359][86177] Collected {0: 104177664, 1: 104112128}, FPS: 5415.2 -[2023-11-28 10:53:28,360][87320] Loop batcher_evt_loop terminating... -[2023-11-28 10:53:28,360][87281] Loop batcher_evt_loop terminating... -[2023-11-28 10:53:28,361][87281] Saving ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000406944_104177664.pth... -[2023-11-28 10:53:28,361][87320] Saving ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000406688_104112128.pth... -[2023-11-28 10:53:28,366][87504] Stopping RolloutWorker_w13... -[2023-11-28 10:53:28,366][87430] Stopping RolloutWorker_w2... -[2023-11-28 10:53:28,366][87504] Loop rollout_proc13_evt_loop terminating... -[2023-11-28 10:53:28,366][87430] Loop rollout_proc2_evt_loop terminating... -[2023-11-28 10:53:28,367][87468] Stopping RolloutWorker_w7... -[2023-11-28 10:53:28,367][87468] Loop rollout_proc7_evt_loop terminating... -[2023-11-28 10:53:28,367][87448] Stopping RolloutWorker_w6... -[2023-11-28 10:53:28,367][87448] Loop rollout_proc6_evt_loop terminating... -[2023-11-28 10:53:28,369][88215] Stopping RolloutWorker_w14... -[2023-11-28 10:53:28,370][88215] Loop rollout_proc14_evt_loop terminating... -[2023-11-28 10:53:28,370][87431] Stopping RolloutWorker_w5... -[2023-11-28 10:53:28,370][87431] Loop rollout_proc5_evt_loop terminating... -[2023-11-28 10:53:28,371][87432] Stopping RolloutWorker_w3... -[2023-11-28 10:53:28,371][87432] Loop rollout_proc3_evt_loop terminating... -[2023-11-28 10:53:28,372][88248] Stopping RolloutWorker_w15... -[2023-11-28 10:53:28,372][88248] Loop rollout_proc15_evt_loop terminating... -[2023-11-28 10:53:28,374][87505] Stopping RolloutWorker_w11... -[2023-11-28 10:53:28,374][87505] Loop rollout_proc11_evt_loop terminating... -[2023-11-28 10:53:28,374][87506] Stopping RolloutWorker_w12... -[2023-11-28 10:53:28,374][87434] Stopping RolloutWorker_w4... -[2023-11-28 10:53:28,375][87434] Loop rollout_proc4_evt_loop terminating... -[2023-11-28 10:53:28,375][87506] Loop rollout_proc12_evt_loop terminating... -[2023-11-28 10:53:28,375][87472] Stopping RolloutWorker_w10... -[2023-11-28 10:53:28,376][87472] Loop rollout_proc10_evt_loop terminating... -[2023-11-28 10:53:28,377][87469] Stopping RolloutWorker_w8... -[2023-11-28 10:53:28,378][87469] Loop rollout_proc8_evt_loop terminating... -[2023-11-28 10:53:28,378][87471] Stopping RolloutWorker_w9... -[2023-11-28 10:53:28,378][87428] Stopping RolloutWorker_w1... -[2023-11-28 10:53:28,379][87427] Stopping RolloutWorker_w0... -[2023-11-28 10:53:28,379][87428] Loop rollout_proc1_evt_loop terminating... -[2023-11-28 10:53:28,379][87471] Loop rollout_proc9_evt_loop terminating... -[2023-11-28 10:53:28,379][87427] Loop rollout_proc0_evt_loop terminating... -[2023-11-28 10:53:28,385][87426] Weights refcount: 2 0 -[2023-11-28 10:53:28,387][87424] Weights refcount: 2 0 -[2023-11-28 10:53:28,387][87426] Stopping InferenceWorker_p1-w0... -[2023-11-28 10:53:28,387][87426] Loop inference_proc1-0_evt_loop terminating... -[2023-11-28 10:53:28,388][87424] Stopping InferenceWorker_p0-w0... -[2023-11-28 10:53:28,389][87424] Loop inference_proc0-0_evt_loop terminating... -[2023-11-28 10:53:28,401][87320] Removing ./train_atari/atari_skiing_APPO/checkpoint_p1/checkpoint_000404704_103604224.pth -[2023-11-28 10:53:28,406][87320] Stopping LearnerWorker_p1... -[2023-11-28 10:53:28,406][87320] Loop learner_proc1_evt_loop terminating... -[2023-11-28 10:53:28,408][87281] Removing ./train_atari/atari_skiing_APPO/checkpoint_p0/checkpoint_000404960_103669760.pth -[2023-11-28 10:53:28,415][87281] Stopping LearnerWorker_p0... -[2023-11-28 10:53:28,417][87281] Loop learner_proc0_evt_loop terminating... +version https://git-lfs.github.com/spec/v1 +oid sha256:5e33f59f24a6af9c6c2e73ec11dc5e922eb01e4763f7efff11f708f697dfd146 +size 49671868